diff options
598 files changed, 6673 insertions, 3418 deletions
diff --git a/Documentation/admin-guide/laptops/thinkpad-acpi.rst b/Documentation/admin-guide/laptops/thinkpad-acpi.rst index 7f674a6cfa8a..4ab0fef7d440 100644 --- a/Documentation/admin-guide/laptops/thinkpad-acpi.rst +++ b/Documentation/admin-guide/laptops/thinkpad-acpi.rst @@ -445,8 +445,10 @@ event code Key Notes 0x1008 0x07 FN+F8 IBM: toggle screen expand Lenovo: configure UltraNav, or toggle screen expand. - On newer platforms (2024+) - replaced by 0x131f (see below) + On 2024 platforms replaced by + 0x131f (see below) and on newer + platforms (2025 +) keycode is + replaced by 0x1401 (see below). 0x1009 0x08 FN+F9 - @@ -506,9 +508,11 @@ event code Key Notes 0x1019 0x18 unknown -0x131f ... FN+F8 Platform Mode change. +0x131f ... FN+F8 Platform Mode change (2024 systems). Implemented in driver. +0x1401 ... FN+F8 Platform Mode change (2025 + systems). + Implemented in driver. ... ... ... 0x1020 0x1F unknown diff --git a/Documentation/arch/arm64/silicon-errata.rst b/Documentation/arch/arm64/silicon-errata.rst index 77db10e944f0..b42fea07c5ce 100644 --- a/Documentation/arch/arm64/silicon-errata.rst +++ b/Documentation/arch/arm64/silicon-errata.rst @@ -255,8 +255,9 @@ stable kernels. +----------------+-----------------+-----------------+-----------------------------+ | Hisilicon | Hip08 SMMU PMCG | #162001800 | N/A | +----------------+-----------------+-----------------+-----------------------------+ -| Hisilicon | Hip{08,09,10,10C| #162001900 | N/A | -| | ,11} SMMU PMCG | | | +| Hisilicon | Hip{08,09,09A,10| #162001900 | N/A | +| | ,10C,11} | | | +| | SMMU PMCG | | | +----------------+-----------------+-----------------+-----------------------------+ | Hisilicon | Hip09 | #162100801 | HISILICON_ERRATUM_162100801 | +----------------+-----------------+-----------------+-----------------------------+ diff --git a/Documentation/devicetree/bindings/display/bridge/adi,adv7533.yaml b/Documentation/devicetree/bindings/display/bridge/adi,adv7533.yaml index df20a3c9c744..ec89115c74e4 100644 --- a/Documentation/devicetree/bindings/display/bridge/adi,adv7533.yaml +++ b/Documentation/devicetree/bindings/display/bridge/adi,adv7533.yaml @@ -90,7 +90,7 @@ properties: adi,dsi-lanes: description: Number of DSI data lanes connected to the DSI host. $ref: /schemas/types.yaml#/definitions/uint32 - enum: [ 1, 2, 3, 4 ] + enum: [ 2, 3, 4 ] "#sound-dai-cells": const: 0 diff --git a/Documentation/devicetree/bindings/sound/realtek,rt5645.yaml b/Documentation/devicetree/bindings/sound/realtek,rt5645.yaml index 13f09f1bc800..0a698798c22b 100644 --- a/Documentation/devicetree/bindings/sound/realtek,rt5645.yaml +++ b/Documentation/devicetree/bindings/sound/realtek,rt5645.yaml @@ -51,7 +51,7 @@ properties: description: Power supply for AVDD, providing 1.8V. cpvdd-supply: - description: Power supply for CPVDD, providing 3.5V. + description: Power supply for CPVDD, providing 1.8V. hp-detect-gpios: description: diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst index eacf8983e230..dcbb6f6caf6d 100644 --- a/Documentation/networking/ip-sysctl.rst +++ b/Documentation/networking/ip-sysctl.rst @@ -2170,6 +2170,12 @@ nexthop_compat_mode - BOOLEAN understands the new API, this sysctl can be disabled to achieve full performance benefits of the new API by disabling the nexthop expansion and extraneous notifications. + + Note that as a backward-compatible mode, dumping of modern features + might be incomplete or wrong. For example, resilient groups will not be + shown as such, but rather as just a list of next hops. Also weights that + do not fit into 8 bits will show incorrectly. + Default: true (backward compat mode) fib_notify_on_flag_change - INTEGER diff --git a/Documentation/power/runtime_pm.rst b/Documentation/power/runtime_pm.rst index 53d1996460ab..12f429359a82 100644 --- a/Documentation/power/runtime_pm.rst +++ b/Documentation/power/runtime_pm.rst @@ -347,7 +347,9 @@ drivers/base/power/runtime.c and include/linux/pm_runtime.h: `int pm_runtime_resume_and_get(struct device *dev);` - run pm_runtime_resume(dev) and if successful, increment the device's - usage counter; return the result of pm_runtime_resume + usage counter; returns 0 on success (whether or not the device's + runtime PM status was already 'active') or the error code from + pm_runtime_resume() on failure. `int pm_request_idle(struct device *dev);` - submit a request to execute the subsystem-level idle callback for the @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 6 PATCHLEVEL = 12 -SUBLEVEL = 5 +SUBLEVEL = 9 EXTRAVERSION = NAME = Baby Opossum Posse diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig index 5b2488142041..69c6e71fa1e6 100644 --- a/arch/arc/Kconfig +++ b/arch/arc/Kconfig @@ -297,7 +297,6 @@ config ARC_PAGE_SIZE_16K config ARC_PAGE_SIZE_4K bool "4KB" select HAVE_PAGE_SIZE_4KB - depends on ARC_MMU_V3 || ARC_MMU_V4 endchoice @@ -474,7 +473,8 @@ config HIGHMEM config ARC_HAS_PAE40 bool "Support for the 40-bit Physical Address Extension" - depends on ISA_ARCV2 + depends on MMU_V4 + depends on !ARC_PAGE_SIZE_4K select HIGHMEM select PHYS_ADDR_T_64BIT help diff --git a/arch/arc/Makefile b/arch/arc/Makefile index 2390dd042e36..fb98478ed1ab 100644 --- a/arch/arc/Makefile +++ b/arch/arc/Makefile @@ -6,7 +6,7 @@ KBUILD_DEFCONFIG := haps_hs_smp_defconfig ifeq ($(CROSS_COMPILE),) -CROSS_COMPILE := $(call cc-cross-prefix, arc-linux- arceb-linux-) +CROSS_COMPILE := $(call cc-cross-prefix, arc-linux- arceb-linux- arc-linux-gnu-) endif cflags-y += -fno-common -pipe -fno-builtin -mmedium-calls -D__linux__ diff --git a/arch/arc/include/asm/cmpxchg.h b/arch/arc/include/asm/cmpxchg.h index 58045c898340..76f43db0890f 100644 --- a/arch/arc/include/asm/cmpxchg.h +++ b/arch/arc/include/asm/cmpxchg.h @@ -48,7 +48,7 @@ \ switch(sizeof((_p_))) { \ case 1: \ - _prev_ = (__typeof__(*(ptr)))cmpxchg_emu_u8((volatile u8 *)_p_, (uintptr_t)_o_, (uintptr_t)_n_); \ + _prev_ = (__typeof__(*(ptr)))cmpxchg_emu_u8((volatile u8 *__force)_p_, (uintptr_t)_o_, (uintptr_t)_n_); \ break; \ case 4: \ _prev_ = __cmpxchg(_p_, _o_, _n_); \ diff --git a/arch/arc/net/bpf_jit_arcv2.c b/arch/arc/net/bpf_jit_arcv2.c index 4458e409ca0a..6d989b6d88c6 100644 --- a/arch/arc/net/bpf_jit_arcv2.c +++ b/arch/arc/net/bpf_jit_arcv2.c @@ -2916,7 +2916,7 @@ bool check_jmp_32(u32 curr_off, u32 targ_off, u8 cond) addendum = (cond == ARC_CC_AL) ? 0 : INSN_len_normal; disp = get_displacement(curr_off + addendum, targ_off); - if (ARC_CC_AL) + if (cond == ARC_CC_AL) return is_valid_far_disp(disp); else return is_valid_near_disp(disp); diff --git a/arch/arm64/boot/dts/broadcom/bcm2712.dtsi b/arch/arm64/boot/dts/broadcom/bcm2712.dtsi index 6e5a984c1d4e..26a29e5e5078 100644 --- a/arch/arm64/boot/dts/broadcom/bcm2712.dtsi +++ b/arch/arm64/boot/dts/broadcom/bcm2712.dtsi @@ -67,7 +67,7 @@ l2_cache_l0: l2-cache-l0 { compatible = "cache"; cache-size = <0x80000>; - cache-line-size = <128>; + cache-line-size = <64>; cache-sets = <1024>; //512KiB(size)/64(line-size)=8192ways/8-way set cache-level = <2>; cache-unified; @@ -91,7 +91,7 @@ l2_cache_l1: l2-cache-l1 { compatible = "cache"; cache-size = <0x80000>; - cache-line-size = <128>; + cache-line-size = <64>; cache-sets = <1024>; //512KiB(size)/64(line-size)=8192ways/8-way set cache-level = <2>; cache-unified; @@ -115,7 +115,7 @@ l2_cache_l2: l2-cache-l2 { compatible = "cache"; cache-size = <0x80000>; - cache-line-size = <128>; + cache-line-size = <64>; cache-sets = <1024>; //512KiB(size)/64(line-size)=8192ways/8-way set cache-level = <2>; cache-unified; @@ -139,7 +139,7 @@ l2_cache_l3: l2-cache-l3 { compatible = "cache"; cache-size = <0x80000>; - cache-line-size = <128>; + cache-line-size = <64>; cache-sets = <1024>; //512KiB(size)/64(line-size)=8192ways/8-way set cache-level = <2>; cache-unified; diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index ff8c4e1b847e..42791971f758 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -1535,6 +1535,7 @@ static u64 __kvm_read_sanitised_id_reg(const struct kvm_vcpu *vcpu, val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_MTEX); val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_DF2); val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_PFAR); + val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_MPAM_frac); break; case SYS_ID_AA64PFR2_EL1: /* We only expose FPMR */ @@ -1724,6 +1725,13 @@ static u64 read_sanitised_id_aa64pfr0_el1(struct kvm_vcpu *vcpu, val &= ~ID_AA64PFR0_EL1_AMU_MASK; + /* + * MPAM is disabled by default as KVM also needs a set of PARTID to + * program the MPAMVPMx_EL2 PARTID remapping registers with. But some + * older kernels let the guest see the ID bit. + */ + val &= ~ID_AA64PFR0_EL1_MPAM_MASK; + return val; } @@ -1834,6 +1842,42 @@ static int set_id_dfr0_el1(struct kvm_vcpu *vcpu, return set_id_reg(vcpu, rd, val); } +static int set_id_aa64pfr0_el1(struct kvm_vcpu *vcpu, + const struct sys_reg_desc *rd, u64 user_val) +{ + u64 hw_val = read_sanitised_ftr_reg(SYS_ID_AA64PFR0_EL1); + u64 mpam_mask = ID_AA64PFR0_EL1_MPAM_MASK; + + /* + * Commit 011e5f5bf529f ("arm64/cpufeature: Add remaining feature bits + * in ID_AA64PFR0 register") exposed the MPAM field of AA64PFR0_EL1 to + * guests, but didn't add trap handling. KVM doesn't support MPAM and + * always returns an UNDEF for these registers. The guest must see 0 + * for this field. + * + * But KVM must also accept values from user-space that were provided + * by KVM. On CPUs that support MPAM, permit user-space to write + * the sanitizied value to ID_AA64PFR0_EL1.MPAM, but ignore this field. + */ + if ((hw_val & mpam_mask) == (user_val & mpam_mask)) + user_val &= ~ID_AA64PFR0_EL1_MPAM_MASK; + + return set_id_reg(vcpu, rd, user_val); +} + +static int set_id_aa64pfr1_el1(struct kvm_vcpu *vcpu, + const struct sys_reg_desc *rd, u64 user_val) +{ + u64 hw_val = read_sanitised_ftr_reg(SYS_ID_AA64PFR1_EL1); + u64 mpam_mask = ID_AA64PFR1_EL1_MPAM_frac_MASK; + + /* See set_id_aa64pfr0_el1 for comment about MPAM */ + if ((hw_val & mpam_mask) == (user_val & mpam_mask)) + user_val &= ~ID_AA64PFR1_EL1_MPAM_frac_MASK; + + return set_id_reg(vcpu, rd, user_val); +} + /* * cpufeature ID register user accessors * @@ -2377,7 +2421,7 @@ static const struct sys_reg_desc sys_reg_descs[] = { { SYS_DESC(SYS_ID_AA64PFR0_EL1), .access = access_id_reg, .get_user = get_id_reg, - .set_user = set_id_reg, + .set_user = set_id_aa64pfr0_el1, .reset = read_sanitised_id_aa64pfr0_el1, .val = ~(ID_AA64PFR0_EL1_AMU | ID_AA64PFR0_EL1_MPAM | @@ -2385,7 +2429,12 @@ static const struct sys_reg_desc sys_reg_descs[] = { ID_AA64PFR0_EL1_RAS | ID_AA64PFR0_EL1_AdvSIMD | ID_AA64PFR0_EL1_FP), }, - ID_WRITABLE(ID_AA64PFR1_EL1, ~(ID_AA64PFR1_EL1_PFAR | + { SYS_DESC(SYS_ID_AA64PFR1_EL1), + .access = access_id_reg, + .get_user = get_id_reg, + .set_user = set_id_aa64pfr1_el1, + .reset = kvm_read_sanitised_id_reg, + .val = ~(ID_AA64PFR1_EL1_PFAR | ID_AA64PFR1_EL1_DF2 | ID_AA64PFR1_EL1_MTEX | ID_AA64PFR1_EL1_THE | @@ -2397,7 +2446,7 @@ static const struct sys_reg_desc sys_reg_descs[] = { ID_AA64PFR1_EL1_RES0 | ID_AA64PFR1_EL1_MPAM_frac | ID_AA64PFR1_EL1_RAS_frac | - ID_AA64PFR1_EL1_MTE)), + ID_AA64PFR1_EL1_MTE), }, ID_WRITABLE(ID_AA64PFR2_EL1, ID_AA64PFR2_EL1_FPMR), ID_UNALLOCATED(4,3), ID_WRITABLE(ID_AA64ZFR0_EL1, ~ID_AA64ZFR0_EL1_RES0), @@ -2454,7 +2503,8 @@ static const struct sys_reg_desc sys_reg_descs[] = { ID_WRITABLE(ID_AA64MMFR0_EL1, ~(ID_AA64MMFR0_EL1_RES0 | ID_AA64MMFR0_EL1_TGRAN4_2 | ID_AA64MMFR0_EL1_TGRAN64_2 | - ID_AA64MMFR0_EL1_TGRAN16_2)), + ID_AA64MMFR0_EL1_TGRAN16_2 | + ID_AA64MMFR0_EL1_ASIDBITS)), ID_WRITABLE(ID_AA64MMFR1_EL1, ~(ID_AA64MMFR1_EL1_RES0 | ID_AA64MMFR1_EL1_HCX | ID_AA64MMFR1_EL1_TWED | diff --git a/arch/hexagon/Makefile b/arch/hexagon/Makefile index 92d005958dfb..ff172cbe5881 100644 --- a/arch/hexagon/Makefile +++ b/arch/hexagon/Makefile @@ -32,3 +32,9 @@ KBUILD_LDFLAGS += $(ldflags-y) TIR_NAME := r19 KBUILD_CFLAGS += -ffixed-$(TIR_NAME) -DTHREADINFO_REG=$(TIR_NAME) -D__linux__ KBUILD_AFLAGS += -DTHREADINFO_REG=$(TIR_NAME) + +# Disable HexagonConstExtenders pass for LLVM versions prior to 19.1.0 +# https://github.com/llvm/llvm-project/issues/99714 +ifneq ($(call clang-min-version, 190100),y) +KBUILD_CFLAGS += -mllvm -hexagon-cext=false +endif diff --git a/arch/loongarch/include/asm/inst.h b/arch/loongarch/include/asm/inst.h index 944482063f14..3089785ca97e 100644 --- a/arch/loongarch/include/asm/inst.h +++ b/arch/loongarch/include/asm/inst.h @@ -683,7 +683,17 @@ DEF_EMIT_REG2I16_FORMAT(blt, blt_op) DEF_EMIT_REG2I16_FORMAT(bge, bge_op) DEF_EMIT_REG2I16_FORMAT(bltu, bltu_op) DEF_EMIT_REG2I16_FORMAT(bgeu, bgeu_op) -DEF_EMIT_REG2I16_FORMAT(jirl, jirl_op) + +static inline void emit_jirl(union loongarch_instruction *insn, + enum loongarch_gpr rd, + enum loongarch_gpr rj, + int offset) +{ + insn->reg2i16_format.opcode = jirl_op; + insn->reg2i16_format.immediate = offset; + insn->reg2i16_format.rd = rd; + insn->reg2i16_format.rj = rj; +} #define DEF_EMIT_REG2BSTRD_FORMAT(NAME, OP) \ static inline void emit_##NAME(union loongarch_instruction *insn, \ diff --git a/arch/loongarch/kernel/efi.c b/arch/loongarch/kernel/efi.c index 2bf86aeda874..de21e72759ee 100644 --- a/arch/loongarch/kernel/efi.c +++ b/arch/loongarch/kernel/efi.c @@ -95,7 +95,7 @@ static void __init init_screen_info(void) memset(si, 0, sizeof(*si)); early_memunmap(si, sizeof(*si)); - memblock_reserve(screen_info.lfb_base, screen_info.lfb_size); + memblock_reserve(__screen_info_lfb_base(&screen_info), screen_info.lfb_size); } void __init efi_init(void) diff --git a/arch/loongarch/kernel/inst.c b/arch/loongarch/kernel/inst.c index 3050329556d1..14d7d700bcb9 100644 --- a/arch/loongarch/kernel/inst.c +++ b/arch/loongarch/kernel/inst.c @@ -332,7 +332,7 @@ u32 larch_insn_gen_jirl(enum loongarch_gpr rd, enum loongarch_gpr rj, int imm) return INSN_BREAK; } - emit_jirl(&insn, rj, rd, imm >> 2); + emit_jirl(&insn, rd, rj, imm >> 2); return insn.word; } diff --git a/arch/loongarch/net/bpf_jit.c b/arch/loongarch/net/bpf_jit.c index dd350cba1252..ea357a3edc09 100644 --- a/arch/loongarch/net/bpf_jit.c +++ b/arch/loongarch/net/bpf_jit.c @@ -181,13 +181,13 @@ static void __build_epilogue(struct jit_ctx *ctx, bool is_tail_call) /* Set return value */ emit_insn(ctx, addiw, LOONGARCH_GPR_A0, regmap[BPF_REG_0], 0); /* Return to the caller */ - emit_insn(ctx, jirl, LOONGARCH_GPR_RA, LOONGARCH_GPR_ZERO, 0); + emit_insn(ctx, jirl, LOONGARCH_GPR_ZERO, LOONGARCH_GPR_RA, 0); } else { /* * Call the next bpf prog and skip the first instruction * of TCC initialization. */ - emit_insn(ctx, jirl, LOONGARCH_GPR_T3, LOONGARCH_GPR_ZERO, 1); + emit_insn(ctx, jirl, LOONGARCH_GPR_ZERO, LOONGARCH_GPR_T3, 1); } } @@ -904,7 +904,7 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, bool ext return ret; move_addr(ctx, t1, func_addr); - emit_insn(ctx, jirl, t1, LOONGARCH_GPR_RA, 0); + emit_insn(ctx, jirl, LOONGARCH_GPR_RA, t1, 0); move_reg(ctx, regmap[BPF_REG_0], LOONGARCH_GPR_A0); break; diff --git a/arch/powerpc/platforms/book3s/vas-api.c b/arch/powerpc/platforms/book3s/vas-api.c index f381b177ea06..0b6365d85d11 100644 --- a/arch/powerpc/platforms/book3s/vas-api.c +++ b/arch/powerpc/platforms/book3s/vas-api.c @@ -464,7 +464,43 @@ static vm_fault_t vas_mmap_fault(struct vm_fault *vmf) return VM_FAULT_SIGBUS; } +/* + * During mmap() paste address, mapping VMA is saved in VAS window + * struct which is used to unmap during migration if the window is + * still open. But the user space can remove this mapping with + * munmap() before closing the window and the VMA address will + * be invalid. Set VAS window VMA to NULL in this function which + * is called before VMA free. + */ +static void vas_mmap_close(struct vm_area_struct *vma) +{ + struct file *fp = vma->vm_file; + struct coproc_instance *cp_inst = fp->private_data; + struct vas_window *txwin; + + /* Should not happen */ + if (!cp_inst || !cp_inst->txwin) { + pr_err("No attached VAS window for the paste address mmap\n"); + return; + } + + txwin = cp_inst->txwin; + /* + * task_ref.vma is set in coproc_mmap() during mmap paste + * address. So it has to be the same VMA that is getting freed. + */ + if (WARN_ON(txwin->task_ref.vma != vma)) { + pr_err("Invalid paste address mmaping\n"); + return; + } + + mutex_lock(&txwin->task_ref.mmap_mutex); + txwin->task_ref.vma = NULL; + mutex_unlock(&txwin->task_ref.mmap_mutex); +} + static const struct vm_operations_struct vas_vm_ops = { + .close = vas_mmap_close, .fault = vas_mmap_fault, }; diff --git a/arch/riscv/include/asm/kfence.h b/arch/riscv/include/asm/kfence.h index 7388edd88986..d08bf7fb3aee 100644 --- a/arch/riscv/include/asm/kfence.h +++ b/arch/riscv/include/asm/kfence.h @@ -22,7 +22,9 @@ static inline bool kfence_protect_page(unsigned long addr, bool protect) else set_pte(pte, __pte(pte_val(ptep_get(pte)) | _PAGE_PRESENT)); - flush_tlb_kernel_range(addr, addr + PAGE_SIZE); + preempt_disable(); + local_flush_tlb_kernel_range(addr, addr + PAGE_SIZE); + preempt_enable(); return true; } diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c index 26c886db4fb3..2b3c152d3c91 100644 --- a/arch/riscv/kernel/setup.c +++ b/arch/riscv/kernel/setup.c @@ -227,7 +227,7 @@ static void __init init_resources(void) static void __init parse_dtb(void) { /* Early scan of device tree from init memory */ - if (early_init_dt_scan(dtb_early_va, __pa(dtb_early_va))) { + if (early_init_dt_scan(dtb_early_va, dtb_early_pa)) { const char *name = of_flat_dt_get_machine_name(); if (name) { diff --git a/arch/riscv/kvm/aia.c b/arch/riscv/kvm/aia.c index 2967d305c442..9f3b527596de 100644 --- a/arch/riscv/kvm/aia.c +++ b/arch/riscv/kvm/aia.c @@ -552,7 +552,7 @@ void kvm_riscv_aia_enable(void) csr_set(CSR_HIE, BIT(IRQ_S_GEXT)); /* Enable IRQ filtering for overflow interrupt only if sscofpmf is present */ if (__riscv_isa_extension_available(NULL, RISCV_ISA_EXT_SSCOFPMF)) - csr_write(CSR_HVIEN, BIT(IRQ_PMU_OVF)); + csr_set(CSR_HVIEN, BIT(IRQ_PMU_OVF)); } void kvm_riscv_aia_disable(void) diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index 0e8c20adcd98..fc53ce748c80 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -1566,7 +1566,7 @@ static void __meminit free_pte_table(pte_t *pte_start, pmd_t *pmd) pmd_clear(pmd); } -static void __meminit free_pmd_table(pmd_t *pmd_start, pud_t *pud) +static void __meminit free_pmd_table(pmd_t *pmd_start, pud_t *pud, bool is_vmemmap) { struct page *page = pud_page(*pud); struct ptdesc *ptdesc = page_ptdesc(page); @@ -1579,7 +1579,8 @@ static void __meminit free_pmd_table(pmd_t *pmd_start, pud_t *pud) return; } - pagetable_pmd_dtor(ptdesc); + if (!is_vmemmap) + pagetable_pmd_dtor(ptdesc); if (PageReserved(page)) free_reserved_page(page); else @@ -1703,7 +1704,7 @@ static void __meminit remove_pud_mapping(pud_t *pud_base, unsigned long addr, un remove_pmd_mapping(pmd_base, addr, next, is_vmemmap, altmap); if (pgtable_l4_enabled) - free_pmd_table(pmd_base, pudp); + free_pmd_table(pmd_base, pudp, is_vmemmap); } } diff --git a/arch/s390/boot/startup.c b/arch/s390/boot/startup.c index c8f149ad77e5..c2ee0745f59e 100644 --- a/arch/s390/boot/startup.c +++ b/arch/s390/boot/startup.c @@ -231,6 +231,8 @@ static unsigned long get_vmem_size(unsigned long identity_size, vsize = round_up(SZ_2G + max_mappable, rte_size) + round_up(vmemmap_size, rte_size) + FIXMAP_SIZE + MODULES_LEN + KASLR_LEN; + if (IS_ENABLED(CONFIG_KMSAN)) + vsize += MODULES_LEN * 2; return size_add(vsize, vmalloc_size); } diff --git a/arch/s390/boot/vmem.c b/arch/s390/boot/vmem.c index 145035f84a0e..3fa28db2fe59 100644 --- a/arch/s390/boot/vmem.c +++ b/arch/s390/boot/vmem.c @@ -306,7 +306,7 @@ static void pgtable_pte_populate(pmd_t *pmd, unsigned long addr, unsigned long e pages++; } } - if (mode == POPULATE_DIRECT) + if (mode == POPULATE_IDENTITY) update_page_count(PG_DIRECT_MAP_4K, pages); } @@ -339,7 +339,7 @@ static void pgtable_pmd_populate(pud_t *pud, unsigned long addr, unsigned long e } pgtable_pte_populate(pmd, addr, next, mode); } - if (mode == POPULATE_DIRECT) + if (mode == POPULATE_IDENTITY) update_page_count(PG_DIRECT_MAP_1M, pages); } @@ -372,7 +372,7 @@ static void pgtable_pud_populate(p4d_t *p4d, unsigned long addr, unsigned long e } pgtable_pmd_populate(pud, addr, next, mode); } - if (mode == POPULATE_DIRECT) + if (mode == POPULATE_IDENTITY) update_page_count(PG_DIRECT_MAP_2G, pages); } diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c index f17bb7bf9392..5fa203f4bc6b 100644 --- a/arch/s390/kernel/ipl.c +++ b/arch/s390/kernel/ipl.c @@ -270,7 +270,7 @@ static ssize_t sys_##_prefix##_##_name##_store(struct kobject *kobj, \ if (len >= sizeof(_value)) \ return -E2BIG; \ len = strscpy(_value, buf, sizeof(_value)); \ - if (len < 0) \ + if ((ssize_t)len < 0) \ return len; \ strim(_value); \ return len; \ diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index d879478db3f5..f558be868a50 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -429,6 +429,16 @@ static struct event_constraint intel_lnc_event_constraints[] = { EVENT_CONSTRAINT_END }; +static struct extra_reg intel_lnc_extra_regs[] __read_mostly = { + INTEL_UEVENT_EXTRA_REG(0x012a, MSR_OFFCORE_RSP_0, 0xfffffffffffull, RSP_0), + INTEL_UEVENT_EXTRA_REG(0x012b, MSR_OFFCORE_RSP_1, 0xfffffffffffull, RSP_1), + INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x01cd), + INTEL_UEVENT_EXTRA_REG(0x02c6, MSR_PEBS_FRONTEND, 0x9, FE), + INTEL_UEVENT_EXTRA_REG(0x03c6, MSR_PEBS_FRONTEND, 0x7fff1f, FE), + INTEL_UEVENT_EXTRA_REG(0x40ad, MSR_PEBS_FRONTEND, 0xf, FE), + INTEL_UEVENT_EXTRA_REG(0x04c2, MSR_PEBS_FRONTEND, 0x8, FE), + EVENT_EXTRA_END +}; EVENT_ATTR_STR(mem-loads, mem_ld_nhm, "event=0x0b,umask=0x10,ldlat=3"); EVENT_ATTR_STR(mem-loads, mem_ld_snb, "event=0xcd,umask=0x1,ldlat=3"); @@ -6344,7 +6354,7 @@ static __always_inline void intel_pmu_init_lnc(struct pmu *pmu) intel_pmu_init_glc(pmu); hybrid(pmu, event_constraints) = intel_lnc_event_constraints; hybrid(pmu, pebs_constraints) = intel_lnc_pebs_event_constraints; - hybrid(pmu, extra_regs) = intel_rwc_extra_regs; + hybrid(pmu, extra_regs) = intel_lnc_extra_regs; } static __always_inline void intel_pmu_init_skt(struct pmu *pmu) @@ -7057,6 +7067,7 @@ __init int intel_pmu_init(void) case INTEL_METEORLAKE: case INTEL_METEORLAKE_L: + case INTEL_ARROWLAKE_U: intel_pmu_init_hybrid(hybrid_big_small); x86_pmu.pebs_latency_data = cmt_latency_data; diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index fa5ea65de0d0..19a9fd974e3e 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -1468,7 +1468,7 @@ void intel_pmu_pebs_enable(struct perf_event *event) * hence we need to drain when changing said * size. */ - intel_pmu_drain_large_pebs(cpuc); + intel_pmu_drain_pebs_buffer(); adaptive_pebs_record_size_update(); wrmsrl(MSR_PEBS_DATA_CFG, pebs_data_cfg); cpuc->active_pebs_data_cfg = pebs_data_cfg; @@ -2496,6 +2496,7 @@ void __init intel_ds_init(void) x86_pmu.large_pebs_flags |= PERF_SAMPLE_TIME; break; + case 6: case 5: x86_pmu.pebs_ept = 1; fallthrough; diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c index d98fac567684..e7aba7349231 100644 --- a/arch/x86/events/intel/uncore.c +++ b/arch/x86/events/intel/uncore.c @@ -1910,6 +1910,7 @@ static const struct x86_cpu_id intel_uncore_match[] __initconst = { X86_MATCH_VFM(INTEL_ATOM_GRACEMONT, &adl_uncore_init), X86_MATCH_VFM(INTEL_ATOM_CRESTMONT_X, &gnr_uncore_init), X86_MATCH_VFM(INTEL_ATOM_CRESTMONT, &gnr_uncore_init), + X86_MATCH_VFM(INTEL_ATOM_DARKMONT_X, &gnr_uncore_init), {}, }; MODULE_DEVICE_TABLE(x86cpu, intel_uncore_match); diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 4a686f0e5dbf..2d776635aa53 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -212,6 +212,8 @@ static inline unsigned long long l1tf_pfn_limit(void) return BIT_ULL(boot_cpu_data.x86_cache_bits - 1 - PAGE_SHIFT); } +void init_cpu_devs(void); +void get_cpu_vendor(struct cpuinfo_x86 *c); extern void early_cpu_init(void); extern void identify_secondary_cpu(struct cpuinfo_x86 *); extern void print_cpu_info(struct cpuinfo_x86 *); diff --git a/arch/x86/include/asm/static_call.h b/arch/x86/include/asm/static_call.h index 125c407e2abe..41502bd2afd6 100644 --- a/arch/x86/include/asm/static_call.h +++ b/arch/x86/include/asm/static_call.h @@ -65,4 +65,19 @@ extern bool __static_call_fixup(void *tramp, u8 op, void *dest); +extern void __static_call_update_early(void *tramp, void *func); + +#define static_call_update_early(name, _func) \ +({ \ + typeof(&STATIC_CALL_TRAMP(name)) __F = (_func); \ + if (static_call_initialized) { \ + __static_call_update(&STATIC_CALL_KEY(name), \ + STATIC_CALL_TRAMP_ADDR(name), __F);\ + } else { \ + WRITE_ONCE(STATIC_CALL_KEY(name).func, _func); \ + __static_call_update_early(STATIC_CALL_TRAMP_ADDR(name),\ + __F); \ + } \ +}) + #endif /* _ASM_STATIC_CALL_H */ diff --git a/arch/x86/include/asm/sync_core.h b/arch/x86/include/asm/sync_core.h index ab7382f92aff..96bda43538ee 100644 --- a/arch/x86/include/asm/sync_core.h +++ b/arch/x86/include/asm/sync_core.h @@ -8,7 +8,7 @@ #include <asm/special_insns.h> #ifdef CONFIG_X86_32 -static inline void iret_to_self(void) +static __always_inline void iret_to_self(void) { asm volatile ( "pushfl\n\t" @@ -19,7 +19,7 @@ static inline void iret_to_self(void) : ASM_CALL_CONSTRAINT : : "memory"); } #else -static inline void iret_to_self(void) +static __always_inline void iret_to_self(void) { unsigned int tmp; @@ -55,7 +55,7 @@ static inline void iret_to_self(void) * Like all of Linux's memory ordering operations, this is a * compiler barrier as well. */ -static inline void sync_core(void) +static __always_inline void sync_core(void) { /* * The SERIALIZE instruction is the most straightforward way to diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h index a2dd24947eb8..97771b9d33af 100644 --- a/arch/x86/include/asm/xen/hypercall.h +++ b/arch/x86/include/asm/xen/hypercall.h @@ -39,9 +39,11 @@ #include <linux/string.h> #include <linux/types.h> #include <linux/pgtable.h> +#include <linux/instrumentation.h> #include <trace/events/xen.h> +#include <asm/alternative.h> #include <asm/page.h> #include <asm/smap.h> #include <asm/nospec-branch.h> @@ -86,11 +88,20 @@ struct xen_dm_op_buf; * there aren't more than 5 arguments...) */ -extern struct { char _entry[32]; } hypercall_page[]; +void xen_hypercall_func(void); +DECLARE_STATIC_CALL(xen_hypercall, xen_hypercall_func); -#define __HYPERCALL "call hypercall_page+%c[offset]" -#define __HYPERCALL_ENTRY(x) \ - [offset] "i" (__HYPERVISOR_##x * sizeof(hypercall_page[0])) +#ifdef MODULE +#define __ADDRESSABLE_xen_hypercall +#else +#define __ADDRESSABLE_xen_hypercall __ADDRESSABLE_ASM_STR(__SCK__xen_hypercall) +#endif + +#define __HYPERCALL \ + __ADDRESSABLE_xen_hypercall \ + "call __SCT__xen_hypercall" + +#define __HYPERCALL_ENTRY(x) "a" (x) #ifdef CONFIG_X86_32 #define __HYPERCALL_RETREG "eax" @@ -148,7 +159,7 @@ extern struct { char _entry[32]; } hypercall_page[]; __HYPERCALL_0ARG(); \ asm volatile (__HYPERCALL \ : __HYPERCALL_0PARAM \ - : __HYPERCALL_ENTRY(name) \ + : __HYPERCALL_ENTRY(__HYPERVISOR_ ## name) \ : __HYPERCALL_CLOBBER0); \ (type)__res; \ }) @@ -159,7 +170,7 @@ extern struct { char _entry[32]; } hypercall_page[]; __HYPERCALL_1ARG(a1); \ asm volatile (__HYPERCALL \ : __HYPERCALL_1PARAM \ - : __HYPERCALL_ENTRY(name) \ + : __HYPERCALL_ENTRY(__HYPERVISOR_ ## name) \ : __HYPERCALL_CLOBBER1); \ (type)__res; \ }) @@ -170,7 +181,7 @@ extern struct { char _entry[32]; } hypercall_page[]; __HYPERCALL_2ARG(a1, a2); \ asm volatile (__HYPERCALL \ : __HYPERCALL_2PARAM \ - : __HYPERCALL_ENTRY(name) \ + : __HYPERCALL_ENTRY(__HYPERVISOR_ ## name) \ : __HYPERCALL_CLOBBER2); \ (type)__res; \ }) @@ -181,7 +192,7 @@ extern struct { char _entry[32]; } hypercall_page[]; __HYPERCALL_3ARG(a1, a2, a3); \ asm volatile (__HYPERCALL \ : __HYPERCALL_3PARAM \ - : __HYPERCALL_ENTRY(name) \ + : __HYPERCALL_ENTRY(__HYPERVISOR_ ## name) \ : __HYPERCALL_CLOBBER3); \ (type)__res; \ }) @@ -192,7 +203,7 @@ extern struct { char _entry[32]; } hypercall_page[]; __HYPERCALL_4ARG(a1, a2, a3, a4); \ asm volatile (__HYPERCALL \ : __HYPERCALL_4PARAM \ - : __HYPERCALL_ENTRY(name) \ + : __HYPERCALL_ENTRY(__HYPERVISOR_ ## name) \ : __HYPERCALL_CLOBBER4); \ (type)__res; \ }) @@ -206,12 +217,9 @@ xen_single_call(unsigned int call, __HYPERCALL_DECLS; __HYPERCALL_5ARG(a1, a2, a3, a4, a5); - if (call >= PAGE_SIZE / sizeof(hypercall_page[0])) - return -EINVAL; - - asm volatile(CALL_NOSPEC + asm volatile(__HYPERCALL : __HYPERCALL_5PARAM - : [thunk_target] "a" (&hypercall_page[call]) + : __HYPERCALL_ENTRY(call) : __HYPERCALL_CLOBBER5); return (long)__res; diff --git a/arch/x86/kernel/callthunks.c b/arch/x86/kernel/callthunks.c index 465647456753..f17d16607882 100644 --- a/arch/x86/kernel/callthunks.c +++ b/arch/x86/kernel/callthunks.c @@ -143,11 +143,6 @@ static bool skip_addr(void *dest) dest < (void*)relocate_kernel + KEXEC_CONTROL_CODE_MAX_SIZE) return true; #endif -#ifdef CONFIG_XEN - if (dest >= (void *)hypercall_page && - dest < (void*)hypercall_page + PAGE_SIZE) - return true; -#endif return false; } diff --git a/arch/x86/kernel/cet.c b/arch/x86/kernel/cet.c index d2c732a34e5d..303bf74d175b 100644 --- a/arch/x86/kernel/cet.c +++ b/arch/x86/kernel/cet.c @@ -81,6 +81,34 @@ static void do_user_cp_fault(struct pt_regs *regs, unsigned long error_code) static __ro_after_init bool ibt_fatal = true; +/* + * By definition, all missing-ENDBRANCH #CPs are a result of WFE && !ENDBR. + * + * For the kernel IBT no ENDBR selftest where #CPs are deliberately triggered, + * the WFE state of the interrupted context needs to be cleared to let execution + * continue. Otherwise when the CPU resumes from the instruction that just + * caused the previous #CP, another missing-ENDBRANCH #CP is raised and the CPU + * enters a dead loop. + * + * This is not a problem with IDT because it doesn't preserve WFE and IRET doesn't + * set WFE. But FRED provides space on the entry stack (in an expanded CS area) + * to save and restore the WFE state, thus the WFE state is no longer clobbered, + * so software must clear it. + */ +static void ibt_clear_fred_wfe(struct pt_regs *regs) +{ + /* + * No need to do any FRED checks. + * + * For IDT event delivery, the high-order 48 bits of CS are pushed + * as 0s into the stack, and later IRET ignores these bits. + * + * For FRED, a test to check if fred_cs.wfe is set would be dropped + * by compilers. + */ + regs->fred_cs.wfe = 0; +} + static void do_kernel_cp_fault(struct pt_regs *regs, unsigned long error_code) { if ((error_code & CP_EC) != CP_ENDBR) { @@ -90,6 +118,7 @@ static void do_kernel_cp_fault(struct pt_regs *regs, unsigned long error_code) if (unlikely(regs->ip == (unsigned long)&ibt_selftest_noendbr)) { regs->ax = 0; + ibt_clear_fred_wfe(regs); return; } @@ -97,6 +126,7 @@ static void do_kernel_cp_fault(struct pt_regs *regs, unsigned long error_code) if (!ibt_fatal) { printk(KERN_DEFAULT CUT_HERE); __warn(__FILE__, __LINE__, (void *)regs->ip, TAINT_WARN, regs, NULL); + ibt_clear_fred_wfe(regs); return; } BUG(); diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index b17bcf9b67ee..f439763f45ae 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -868,7 +868,7 @@ static void cpu_detect_tlb(struct cpuinfo_x86 *c) tlb_lld_4m[ENTRIES], tlb_lld_1g[ENTRIES]); } -static void get_cpu_vendor(struct cpuinfo_x86 *c) +void get_cpu_vendor(struct cpuinfo_x86 *c) { char *v = c->x86_vendor_id; int i; @@ -1652,15 +1652,11 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c) detect_nopl(); } -void __init early_cpu_init(void) +void __init init_cpu_devs(void) { const struct cpu_dev *const *cdev; int count = 0; -#ifdef CONFIG_PROCESSOR_SELECT - pr_info("KERNEL supported cpus:\n"); -#endif - for (cdev = __x86_cpu_dev_start; cdev < __x86_cpu_dev_end; cdev++) { const struct cpu_dev *cpudev = *cdev; @@ -1668,20 +1664,30 @@ void __init early_cpu_init(void) break; cpu_devs[count] = cpudev; count++; + } +} +void __init early_cpu_init(void) +{ #ifdef CONFIG_PROCESSOR_SELECT - { - unsigned int j; - - for (j = 0; j < 2; j++) { - if (!cpudev->c_ident[j]) - continue; - pr_info(" %s %s\n", cpudev->c_vendor, - cpudev->c_ident[j]); - } - } + unsigned int i, j; + + pr_info("KERNEL supported cpus:\n"); #endif + + init_cpu_devs(); + +#ifdef CONFIG_PROCESSOR_SELECT + for (i = 0; i < X86_VENDOR_NUM && cpu_devs[i]; i++) { + for (j = 0; j < 2; j++) { + if (!cpu_devs[i]->c_ident[j]) + continue; + pr_info(" %s %s\n", cpu_devs[i]->c_vendor, + cpu_devs[i]->c_ident[j]); + } } +#endif + early_identify_cpu(&boot_cpu_data); } diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index d18078834ded..dc12fe5ef3ca 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -223,6 +223,63 @@ static void hv_machine_crash_shutdown(struct pt_regs *regs) hyperv_cleanup(); } #endif /* CONFIG_CRASH_DUMP */ + +static u64 hv_ref_counter_at_suspend; +static void (*old_save_sched_clock_state)(void); +static void (*old_restore_sched_clock_state)(void); + +/* + * Hyper-V clock counter resets during hibernation. Save and restore clock + * offset during suspend/resume, while also considering the time passed + * before suspend. This is to make sure that sched_clock using hv tsc page + * based clocksource, proceeds from where it left off during suspend and + * it shows correct time for the timestamps of kernel messages after resume. + */ +static void save_hv_clock_tsc_state(void) +{ + hv_ref_counter_at_suspend = hv_read_reference_counter(); +} + +static void restore_hv_clock_tsc_state(void) +{ + /* + * Adjust the offsets used by hv tsc clocksource to + * account for the time spent before hibernation. + * adjusted value = reference counter (time) at suspend + * - reference counter (time) now. + */ + hv_adj_sched_clock_offset(hv_ref_counter_at_suspend - hv_read_reference_counter()); +} + +/* + * Functions to override save_sched_clock_state and restore_sched_clock_state + * functions of x86_platform. The Hyper-V clock counter is reset during + * suspend-resume and the offset used to measure time needs to be + * corrected, post resume. + */ +static void hv_save_sched_clock_state(void) +{ + old_save_sched_clock_state(); + save_hv_clock_tsc_state(); +} + +static void hv_restore_sched_clock_state(void) +{ + restore_hv_clock_tsc_state(); + old_restore_sched_clock_state(); +} + +static void __init x86_setup_ops_for_tsc_pg_clock(void) +{ + if (!(ms_hyperv.features & HV_MSR_REFERENCE_TSC_AVAILABLE)) + return; + + old_save_sched_clock_state = x86_platform.save_sched_clock_state; + x86_platform.save_sched_clock_state = hv_save_sched_clock_state; + + old_restore_sched_clock_state = x86_platform.restore_sched_clock_state; + x86_platform.restore_sched_clock_state = hv_restore_sched_clock_state; +} #endif /* CONFIG_HYPERV */ static uint32_t __init ms_hyperv_platform(void) @@ -579,6 +636,7 @@ static void __init ms_hyperv_init_platform(void) /* Register Hyper-V specific clocksource */ hv_init_clocksource(); + x86_setup_ops_for_tsc_pg_clock(); hv_vtl_init_platform(); #endif /* diff --git a/arch/x86/kernel/static_call.c b/arch/x86/kernel/static_call.c index 4eefaac64c6c..9eed0c144dad 100644 --- a/arch/x86/kernel/static_call.c +++ b/arch/x86/kernel/static_call.c @@ -172,6 +172,15 @@ void arch_static_call_transform(void *site, void *tramp, void *func, bool tail) } EXPORT_SYMBOL_GPL(arch_static_call_transform); +noinstr void __static_call_update_early(void *tramp, void *func) +{ + BUG_ON(system_state != SYSTEM_BOOTING); + BUG_ON(!early_boot_irqs_disabled); + BUG_ON(static_call_initialized); + __text_gen_insn(tramp, JMP32_INSN_OPCODE, tramp, func, JMP32_INSN_SIZE); + sync_core(); +} + #ifdef CONFIG_MITIGATION_RETHUNK /* * This is called by apply_returns() to fix up static call trampolines, diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 41786b834b16..83bfecd1a6e4 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -36,6 +36,26 @@ u32 kvm_cpu_caps[NR_KVM_CPU_CAPS] __read_mostly; EXPORT_SYMBOL_GPL(kvm_cpu_caps); +struct cpuid_xstate_sizes { + u32 eax; + u32 ebx; + u32 ecx; +}; + +static struct cpuid_xstate_sizes xstate_sizes[XFEATURE_MAX] __ro_after_init; + +void __init kvm_init_xstate_sizes(void) +{ + u32 ign; + int i; + + for (i = XFEATURE_YMM; i < ARRAY_SIZE(xstate_sizes); i++) { + struct cpuid_xstate_sizes *xs = &xstate_sizes[i]; + + cpuid_count(0xD, i, &xs->eax, &xs->ebx, &xs->ecx, &ign); + } +} + u32 xstate_required_size(u64 xstate_bv, bool compacted) { int feature_bit = 0; @@ -44,14 +64,15 @@ u32 xstate_required_size(u64 xstate_bv, bool compacted) xstate_bv &= XFEATURE_MASK_EXTEND; while (xstate_bv) { if (xstate_bv & 0x1) { - u32 eax, ebx, ecx, edx, offset; - cpuid_count(0xD, feature_bit, &eax, &ebx, &ecx, &edx); + struct cpuid_xstate_sizes *xs = &xstate_sizes[feature_bit]; + u32 offset; + /* ECX[1]: 64B alignment in compacted form */ if (compacted) - offset = (ecx & 0x2) ? ALIGN(ret, 64) : ret; + offset = (xs->ecx & 0x2) ? ALIGN(ret, 64) : ret; else - offset = ebx; - ret = max(ret, offset + eax); + offset = xs->ebx; + ret = max(ret, offset + xs->eax); } xstate_bv >>= 1; diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h index 41697cca354e..ad479cfb91bc 100644 --- a/arch/x86/kvm/cpuid.h +++ b/arch/x86/kvm/cpuid.h @@ -32,6 +32,7 @@ int kvm_vcpu_ioctl_get_cpuid2(struct kvm_vcpu *vcpu, bool kvm_cpuid(struct kvm_vcpu *vcpu, u32 *eax, u32 *ebx, u32 *ecx, u32 *edx, bool exact_only); +void __init kvm_init_xstate_sizes(void); u32 xstate_required_size(u64 xstate_bv, bool compacted); int cpuid_query_maxphyaddr(struct kvm_vcpu *vcpu); diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 9df3e1e5ae81..4543dd6bcab2 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -3199,15 +3199,6 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) if (data & ~supported_de_cfg) return 1; - /* - * Don't let the guest change the host-programmed value. The - * MSR is very model specific, i.e. contains multiple bits that - * are completely unknown to KVM, and the one bit known to KVM - * is simply a reflection of hardware capabilities. - */ - if (!msr->host_initiated && data != svm->msr_decfg) - return 1; - svm->msr_decfg = data; break; } diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 83fe0a78146f..b49e2eb48930 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -9991,7 +9991,7 @@ static int complete_hypercall_exit(struct kvm_vcpu *vcpu) { u64 ret = vcpu->run->hypercall.ret; - if (!is_64_bit_mode(vcpu)) + if (!is_64_bit_hypercall(vcpu)) ret = (u32)ret; kvm_rax_write(vcpu, ret); ++vcpu->stat.hypercalls; @@ -14010,6 +14010,8 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_rmp_fault); static int __init kvm_x86_init(void) { + kvm_init_xstate_sizes(); + kvm_mmu_x86_module_init(); mitigate_smt_rsb &= boot_cpu_has_bug(X86_BUG_SMT_RSB) && cpu_smt_possible(); return 0; diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 84e5adbd0925..b4f3784f27e9 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -2,6 +2,7 @@ #include <linux/console.h> #include <linux/cpu.h> +#include <linux/instrumentation.h> #include <linux/kexec.h> #include <linux/memblock.h> #include <linux/slab.h> @@ -21,7 +22,8 @@ #include "xen-ops.h" -EXPORT_SYMBOL_GPL(hypercall_page); +DEFINE_STATIC_CALL(xen_hypercall, xen_hypercall_hvm); +EXPORT_STATIC_CALL_TRAMP(xen_hypercall); /* * Pointer to the xen_vcpu_info structure or @@ -68,6 +70,66 @@ EXPORT_SYMBOL(xen_start_flags); */ struct shared_info *HYPERVISOR_shared_info = &xen_dummy_shared_info; +static __ref void xen_get_vendor(void) +{ + init_cpu_devs(); + cpu_detect(&boot_cpu_data); + get_cpu_vendor(&boot_cpu_data); +} + +void xen_hypercall_setfunc(void) +{ + if (static_call_query(xen_hypercall) != xen_hypercall_hvm) + return; + + if ((boot_cpu_data.x86_vendor == X86_VENDOR_AMD || + boot_cpu_data.x86_vendor == X86_VENDOR_HYGON)) + static_call_update(xen_hypercall, xen_hypercall_amd); + else + static_call_update(xen_hypercall, xen_hypercall_intel); +} + +/* + * Evaluate processor vendor in order to select the correct hypercall + * function for HVM/PVH guests. + * Might be called very early in boot before vendor has been set by + * early_cpu_init(). + */ +noinstr void *__xen_hypercall_setfunc(void) +{ + void (*func)(void); + + /* + * Xen is supported only on CPUs with CPUID, so testing for + * X86_FEATURE_CPUID is a test for early_cpu_init() having been + * run. + * + * Note that __xen_hypercall_setfunc() is noinstr only due to a nasty + * dependency chain: it is being called via the xen_hypercall static + * call when running as a PVH or HVM guest. Hypercalls need to be + * noinstr due to PV guests using hypercalls in noinstr code. So we + * the PV guest requirement is not of interest here (xen_get_vendor() + * calls noinstr functions, and static_call_update_early() might do + * so, too). + */ + instrumentation_begin(); + + if (!boot_cpu_has(X86_FEATURE_CPUID)) + xen_get_vendor(); + + if ((boot_cpu_data.x86_vendor == X86_VENDOR_AMD || + boot_cpu_data.x86_vendor == X86_VENDOR_HYGON)) + func = xen_hypercall_amd; + else + func = xen_hypercall_intel; + + static_call_update_early(xen_hypercall, func); + + instrumentation_end(); + + return func; +} + static int xen_cpu_up_online(unsigned int cpu) { xen_init_lock_cpu(cpu); diff --git a/arch/x86/xen/enlighten_hvm.c b/arch/x86/xen/enlighten_hvm.c index 24d2957a4726..fe57ff85d004 100644 --- a/arch/x86/xen/enlighten_hvm.c +++ b/arch/x86/xen/enlighten_hvm.c @@ -106,15 +106,8 @@ static void __init init_hvm_pv_info(void) /* PVH set up hypercall page in xen_prepare_pvh(). */ if (xen_pvh_domain()) pv_info.name = "Xen PVH"; - else { - u64 pfn; - uint32_t msr; - + else pv_info.name = "Xen HVM"; - msr = cpuid_ebx(base + 2); - pfn = __pa(hypercall_page); - wrmsr_safe(msr, (u32)pfn, (u32)(pfn >> 32)); - } xen_setup_features(); @@ -300,6 +293,10 @@ static uint32_t __init xen_platform_hvm(void) if (xen_pv_domain()) return 0; + /* Set correct hypercall function. */ + if (xen_domain) + xen_hypercall_setfunc(); + if (xen_pvh_domain() && nopv) { /* Guest booting via the Xen-PVH boot entry goes here */ pr_info("\"nopv\" parameter is ignored in PVH guest\n"); diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c index d6818c6cafda..a8eb7e0c473c 100644 --- a/arch/x86/xen/enlighten_pv.c +++ b/arch/x86/xen/enlighten_pv.c @@ -1341,6 +1341,9 @@ asmlinkage __visible void __init xen_start_kernel(struct start_info *si) xen_domain_type = XEN_PV_DOMAIN; xen_start_flags = xen_start_info->flags; + /* Interrupts are guaranteed to be off initially. */ + early_boot_irqs_disabled = true; + static_call_update_early(xen_hypercall, xen_hypercall_pv); xen_setup_features(); @@ -1431,7 +1434,6 @@ asmlinkage __visible void __init xen_start_kernel(struct start_info *si) WARN_ON(xen_cpuhp_setup(xen_cpu_up_prepare_pv, xen_cpu_dead_pv)); local_irq_disable(); - early_boot_irqs_disabled = true; xen_raw_console_write("mapping kernel into physical memory\n"); xen_setup_kernel_pagetable((pgd_t *)xen_start_info->pt_base, diff --git a/arch/x86/xen/enlighten_pvh.c b/arch/x86/xen/enlighten_pvh.c index bf68c329fc01..0e3d930bcb89 100644 --- a/arch/x86/xen/enlighten_pvh.c +++ b/arch/x86/xen/enlighten_pvh.c @@ -129,17 +129,10 @@ static void __init pvh_arch_setup(void) void __init xen_pvh_init(struct boot_params *boot_params) { - u32 msr; - u64 pfn; - xen_pvh = 1; xen_domain_type = XEN_HVM_DOMAIN; xen_start_flags = pvh_start_info.flags; - msr = cpuid_ebx(xen_cpuid_base() + 2); - pfn = __pa(hypercall_page); - wrmsr_safe(msr, (u32)pfn, (u32)(pfn >> 32)); - x86_init.oem.arch_setup = pvh_arch_setup; x86_init.oem.banner = xen_banner; diff --git a/arch/x86/xen/xen-asm.S b/arch/x86/xen/xen-asm.S index 83189cf5cdce..b518f36d1ca2 100644 --- a/arch/x86/xen/xen-asm.S +++ b/arch/x86/xen/xen-asm.S @@ -20,10 +20,33 @@ #include <linux/init.h> #include <linux/linkage.h> +#include <linux/objtool.h> #include <../entry/calling.h> .pushsection .noinstr.text, "ax" /* + * PV hypercall interface to the hypervisor. + * + * Called via inline asm(), so better preserve %rcx and %r11. + * + * Input: + * %eax: hypercall number + * %rdi, %rsi, %rdx, %r10, %r8: args 1..5 for the hypercall + * Output: %rax + */ +SYM_FUNC_START(xen_hypercall_pv) + ANNOTATE_NOENDBR + push %rcx + push %r11 + UNWIND_HINT_SAVE + syscall + UNWIND_HINT_RESTORE + pop %r11 + pop %rcx + RET +SYM_FUNC_END(xen_hypercall_pv) + +/* * Disabling events is simply a matter of making the event mask * non-zero. */ @@ -176,7 +199,6 @@ SYM_CODE_START(xen_early_idt_handler_array) SYM_CODE_END(xen_early_idt_handler_array) __FINIT -hypercall_iret = hypercall_page + __HYPERVISOR_iret * 32 /* * Xen64 iret frame: * @@ -186,17 +208,28 @@ hypercall_iret = hypercall_page + __HYPERVISOR_iret * 32 * cs * rip <-- standard iret frame * - * flags + * flags <-- xen_iret must push from here on * - * rcx } - * r11 }<-- pushed by hypercall page - * rsp->rax } + * rcx + * r11 + * rsp->rax */ +.macro xen_hypercall_iret + pushq $0 /* Flags */ + push %rcx + push %r11 + push %rax + mov $__HYPERVISOR_iret, %eax + syscall /* Do the IRET. */ +#ifdef CONFIG_MITIGATION_SLS + int3 +#endif +.endm + SYM_CODE_START(xen_iret) UNWIND_HINT_UNDEFINED ANNOTATE_NOENDBR - pushq $0 - jmp hypercall_iret + xen_hypercall_iret SYM_CODE_END(xen_iret) /* @@ -301,8 +334,7 @@ SYM_CODE_START(xen_entry_SYSENTER_compat) ENDBR lea 16(%rsp), %rsp /* strip %rcx, %r11 */ mov $-ENOSYS, %rax - pushq $0 - jmp hypercall_iret + xen_hypercall_iret SYM_CODE_END(xen_entry_SYSENTER_compat) SYM_CODE_END(xen_entry_SYSCALL_compat) diff --git a/arch/x86/xen/xen-head.S b/arch/x86/xen/xen-head.S index 758bcd47b72d..721a57700a3b 100644 --- a/arch/x86/xen/xen-head.S +++ b/arch/x86/xen/xen-head.S @@ -6,9 +6,11 @@ #include <linux/elfnote.h> #include <linux/init.h> +#include <linux/instrumentation.h> #include <asm/boot.h> #include <asm/asm.h> +#include <asm/frame.h> #include <asm/msr.h> #include <asm/page_types.h> #include <asm/percpu.h> @@ -20,28 +22,6 @@ #include <xen/interface/xen-mca.h> #include <asm/xen/interface.h> -.pushsection .noinstr.text, "ax" - .balign PAGE_SIZE -SYM_CODE_START(hypercall_page) - .rept (PAGE_SIZE / 32) - UNWIND_HINT_FUNC - ANNOTATE_NOENDBR - ANNOTATE_UNRET_SAFE - ret - /* - * Xen will write the hypercall page, and sort out ENDBR. - */ - .skip 31, 0xcc - .endr - -#define HYPERCALL(n) \ - .equ xen_hypercall_##n, hypercall_page + __HYPERVISOR_##n * 32; \ - .type xen_hypercall_##n, @function; .size xen_hypercall_##n, 32 -#include <asm/xen-hypercalls.h> -#undef HYPERCALL -SYM_CODE_END(hypercall_page) -.popsection - #ifdef CONFIG_XEN_PV __INIT SYM_CODE_START(startup_xen) @@ -87,6 +67,87 @@ SYM_CODE_END(xen_cpu_bringup_again) #endif #endif + .pushsection .noinstr.text, "ax" +/* + * Xen hypercall interface to the hypervisor. + * + * Input: + * %eax: hypercall number + * 32-bit: + * %ebx, %ecx, %edx, %esi, %edi: args 1..5 for the hypercall + * 64-bit: + * %rdi, %rsi, %rdx, %r10, %r8: args 1..5 for the hypercall + * Output: %[er]ax + */ +SYM_FUNC_START(xen_hypercall_hvm) + ENDBR + FRAME_BEGIN + /* Save all relevant registers (caller save and arguments). */ +#ifdef CONFIG_X86_32 + push %eax + push %ebx + push %ecx + push %edx + push %esi + push %edi +#else + push %rax + push %rcx + push %rdx + push %rdi + push %rsi + push %r11 + push %r10 + push %r9 + push %r8 +#ifdef CONFIG_FRAME_POINTER + pushq $0 /* Dummy push for stack alignment. */ +#endif +#endif + /* Set the vendor specific function. */ + call __xen_hypercall_setfunc + /* Set ZF = 1 if AMD, Restore saved registers. */ +#ifdef CONFIG_X86_32 + lea xen_hypercall_amd, %ebx + cmp %eax, %ebx + pop %edi + pop %esi + pop %edx + pop %ecx + pop %ebx + pop %eax +#else + lea xen_hypercall_amd(%rip), %rbx + cmp %rax, %rbx +#ifdef CONFIG_FRAME_POINTER + pop %rax /* Dummy pop. */ +#endif + pop %r8 + pop %r9 + pop %r10 + pop %r11 + pop %rsi + pop %rdi + pop %rdx + pop %rcx + pop %rax +#endif + /* Use correct hypercall function. */ + jz xen_hypercall_amd + jmp xen_hypercall_intel +SYM_FUNC_END(xen_hypercall_hvm) + +SYM_FUNC_START(xen_hypercall_amd) + vmmcall + RET +SYM_FUNC_END(xen_hypercall_amd) + +SYM_FUNC_START(xen_hypercall_intel) + vmcall + RET +SYM_FUNC_END(xen_hypercall_intel) + .popsection + ELFNOTE(Xen, XEN_ELFNOTE_GUEST_OS, .asciz "linux") ELFNOTE(Xen, XEN_ELFNOTE_GUEST_VERSION, .asciz "2.6") ELFNOTE(Xen, XEN_ELFNOTE_XEN_VERSION, .asciz "xen-3.0") @@ -115,7 +176,6 @@ SYM_CODE_END(xen_cpu_bringup_again) #else # define FEATURES_DOM0 0 #endif - ELFNOTE(Xen, XEN_ELFNOTE_HYPERCALL_PAGE, _ASM_PTR hypercall_page) ELFNOTE(Xen, XEN_ELFNOTE_SUPPORTED_FEATURES, .long FEATURES_PV | FEATURES_PVH | FEATURES_DOM0) ELFNOTE(Xen, XEN_ELFNOTE_LOADER, .asciz "generic") diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h index e1b782e823e6..63c13a2ccf55 100644 --- a/arch/x86/xen/xen-ops.h +++ b/arch/x86/xen/xen-ops.h @@ -326,4 +326,13 @@ static inline void xen_smp_intr_free_pv(unsigned int cpu) {} static inline void xen_smp_count_cpus(void) { } #endif /* CONFIG_SMP */ +#ifdef CONFIG_XEN_PV +void xen_hypercall_pv(void); +#endif +void xen_hypercall_hvm(void); +void xen_hypercall_amd(void); +void xen_hypercall_intel(void); +void xen_hypercall_setfunc(void); +void *__xen_hypercall_setfunc(void); + #endif /* XEN_OPS_H */ diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index e68c725cf8d9..45a395862fbc 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -1324,10 +1324,14 @@ void blkcg_unpin_online(struct cgroup_subsys_state *blkcg_css) struct blkcg *blkcg = css_to_blkcg(blkcg_css); do { + struct blkcg *parent; + if (!refcount_dec_and_test(&blkcg->online_pin)) break; + + parent = blkcg_parent(blkcg); blkcg_destroy_blkgs(blkcg); - blkcg = blkcg_parent(blkcg); + blkcg = parent; } while (blkcg); } diff --git a/block/blk-iocost.c b/block/blk-iocost.c index 384aa15e8260..a5894ec9696e 100644 --- a/block/blk-iocost.c +++ b/block/blk-iocost.c @@ -1098,7 +1098,14 @@ static void __propagate_weights(struct ioc_gq *iocg, u32 active, u32 inuse, inuse = DIV64_U64_ROUND_UP(active * iocg->child_inuse_sum, iocg->child_active_sum); } else { - inuse = clamp_t(u32, inuse, 1, active); + /* + * It may be tempting to turn this into a clamp expression with + * a lower limit of 1 but active may be 0, which cannot be used + * as an upper limit in that situation. This expression allows + * active to clamp inuse unless it is 0, in which case inuse + * becomes 1. + */ + inuse = min(inuse, active) ?: 1; } iocg->last_inuse = iocg->inuse; diff --git a/block/blk-mq.c b/block/blk-mq.c index b4fba7b398e5..4e76651e786d 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -43,6 +43,7 @@ static DEFINE_PER_CPU(struct llist_head, blk_cpu_done); static DEFINE_PER_CPU(call_single_data_t, blk_cpu_csd); +static DEFINE_MUTEX(blk_mq_cpuhp_lock); static void blk_mq_insert_request(struct request *rq, blk_insert_t flags); static void blk_mq_request_bypass_insert(struct request *rq, @@ -3740,13 +3741,91 @@ static int blk_mq_hctx_notify_dead(unsigned int cpu, struct hlist_node *node) return 0; } -static void blk_mq_remove_cpuhp(struct blk_mq_hw_ctx *hctx) +static void __blk_mq_remove_cpuhp(struct blk_mq_hw_ctx *hctx) { - if (!(hctx->flags & BLK_MQ_F_STACKING)) + lockdep_assert_held(&blk_mq_cpuhp_lock); + + if (!(hctx->flags & BLK_MQ_F_STACKING) && + !hlist_unhashed(&hctx->cpuhp_online)) { cpuhp_state_remove_instance_nocalls(CPUHP_AP_BLK_MQ_ONLINE, &hctx->cpuhp_online); - cpuhp_state_remove_instance_nocalls(CPUHP_BLK_MQ_DEAD, - &hctx->cpuhp_dead); + INIT_HLIST_NODE(&hctx->cpuhp_online); + } + + if (!hlist_unhashed(&hctx->cpuhp_dead)) { + cpuhp_state_remove_instance_nocalls(CPUHP_BLK_MQ_DEAD, + &hctx->cpuhp_dead); + INIT_HLIST_NODE(&hctx->cpuhp_dead); + } +} + +static void blk_mq_remove_cpuhp(struct blk_mq_hw_ctx *hctx) +{ + mutex_lock(&blk_mq_cpuhp_lock); + __blk_mq_remove_cpuhp(hctx); + mutex_unlock(&blk_mq_cpuhp_lock); +} + +static void __blk_mq_add_cpuhp(struct blk_mq_hw_ctx *hctx) +{ + lockdep_assert_held(&blk_mq_cpuhp_lock); + + if (!(hctx->flags & BLK_MQ_F_STACKING) && + hlist_unhashed(&hctx->cpuhp_online)) + cpuhp_state_add_instance_nocalls(CPUHP_AP_BLK_MQ_ONLINE, + &hctx->cpuhp_online); + + if (hlist_unhashed(&hctx->cpuhp_dead)) + cpuhp_state_add_instance_nocalls(CPUHP_BLK_MQ_DEAD, + &hctx->cpuhp_dead); +} + +static void __blk_mq_remove_cpuhp_list(struct list_head *head) +{ + struct blk_mq_hw_ctx *hctx; + + lockdep_assert_held(&blk_mq_cpuhp_lock); + + list_for_each_entry(hctx, head, hctx_list) + __blk_mq_remove_cpuhp(hctx); +} + +/* + * Unregister cpuhp callbacks from exited hw queues + * + * Safe to call if this `request_queue` is live + */ +static void blk_mq_remove_hw_queues_cpuhp(struct request_queue *q) +{ + LIST_HEAD(hctx_list); + + spin_lock(&q->unused_hctx_lock); + list_splice_init(&q->unused_hctx_list, &hctx_list); + spin_unlock(&q->unused_hctx_lock); + + mutex_lock(&blk_mq_cpuhp_lock); + __blk_mq_remove_cpuhp_list(&hctx_list); + mutex_unlock(&blk_mq_cpuhp_lock); + + spin_lock(&q->unused_hctx_lock); + list_splice(&hctx_list, &q->unused_hctx_list); + spin_unlock(&q->unused_hctx_lock); +} + +/* + * Register cpuhp callbacks from all hw queues + * + * Safe to call if this `request_queue` is live + */ +static void blk_mq_add_hw_queues_cpuhp(struct request_queue *q) +{ + struct blk_mq_hw_ctx *hctx; + unsigned long i; + + mutex_lock(&blk_mq_cpuhp_lock); + queue_for_each_hw_ctx(q, hctx, i) + __blk_mq_add_cpuhp(hctx); + mutex_unlock(&blk_mq_cpuhp_lock); } /* @@ -3797,8 +3876,6 @@ static void blk_mq_exit_hctx(struct request_queue *q, if (set->ops->exit_hctx) set->ops->exit_hctx(hctx, hctx_idx); - blk_mq_remove_cpuhp(hctx); - xa_erase(&q->hctx_table, hctx_idx); spin_lock(&q->unused_hctx_lock); @@ -3815,6 +3892,7 @@ static void blk_mq_exit_hw_queues(struct request_queue *q, queue_for_each_hw_ctx(q, hctx, i) { if (i == nr_queue) break; + blk_mq_remove_cpuhp(hctx); blk_mq_exit_hctx(q, set, hctx, i); } } @@ -3825,16 +3903,11 @@ static int blk_mq_init_hctx(struct request_queue *q, { hctx->queue_num = hctx_idx; - if (!(hctx->flags & BLK_MQ_F_STACKING)) - cpuhp_state_add_instance_nocalls(CPUHP_AP_BLK_MQ_ONLINE, - &hctx->cpuhp_online); - cpuhp_state_add_instance_nocalls(CPUHP_BLK_MQ_DEAD, &hctx->cpuhp_dead); - hctx->tags = set->tags[hctx_idx]; if (set->ops->init_hctx && set->ops->init_hctx(hctx, set->driver_data, hctx_idx)) - goto unregister_cpu_notifier; + goto fail; if (blk_mq_init_request(set, hctx->fq->flush_rq, hctx_idx, hctx->numa_node)) @@ -3843,6 +3916,11 @@ static int blk_mq_init_hctx(struct request_queue *q, if (xa_insert(&q->hctx_table, hctx_idx, hctx, GFP_KERNEL)) goto exit_flush_rq; + if (!(hctx->flags & BLK_MQ_F_STACKING)) + cpuhp_state_add_instance_nocalls(CPUHP_AP_BLK_MQ_ONLINE, + &hctx->cpuhp_online); + cpuhp_state_add_instance_nocalls(CPUHP_BLK_MQ_DEAD, &hctx->cpuhp_dead); + return 0; exit_flush_rq: @@ -3851,8 +3929,7 @@ static int blk_mq_init_hctx(struct request_queue *q, exit_hctx: if (set->ops->exit_hctx) set->ops->exit_hctx(hctx, hctx_idx); - unregister_cpu_notifier: - blk_mq_remove_cpuhp(hctx); + fail: return -1; } @@ -3878,6 +3955,8 @@ blk_mq_alloc_hctx(struct request_queue *q, struct blk_mq_tag_set *set, INIT_DELAYED_WORK(&hctx->run_work, blk_mq_run_work_fn); spin_lock_init(&hctx->lock); INIT_LIST_HEAD(&hctx->dispatch); + INIT_HLIST_NODE(&hctx->cpuhp_dead); + INIT_HLIST_NODE(&hctx->cpuhp_online); hctx->queue = q; hctx->flags = set->flags & ~BLK_MQ_F_TAG_QUEUE_SHARED; @@ -4341,6 +4420,15 @@ struct gendisk *blk_mq_alloc_disk_for_queue(struct request_queue *q, } EXPORT_SYMBOL(blk_mq_alloc_disk_for_queue); +/* + * Only hctx removed from cpuhp list can be reused + */ +static bool blk_mq_hctx_is_reusable(struct blk_mq_hw_ctx *hctx) +{ + return hlist_unhashed(&hctx->cpuhp_online) && + hlist_unhashed(&hctx->cpuhp_dead); +} + static struct blk_mq_hw_ctx *blk_mq_alloc_and_init_hctx( struct blk_mq_tag_set *set, struct request_queue *q, int hctx_idx, int node) @@ -4350,7 +4438,7 @@ static struct blk_mq_hw_ctx *blk_mq_alloc_and_init_hctx( /* reuse dead hctx first */ spin_lock(&q->unused_hctx_lock); list_for_each_entry(tmp, &q->unused_hctx_list, hctx_list) { - if (tmp->numa_node == node) { + if (tmp->numa_node == node && blk_mq_hctx_is_reusable(tmp)) { hctx = tmp; break; } @@ -4416,6 +4504,12 @@ static void blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set, xa_for_each_start(&q->hctx_table, j, hctx, j) blk_mq_exit_hctx(q, set, hctx, j); mutex_unlock(&q->sysfs_lock); + + /* unregister cpuhp callbacks for exited hctxs */ + blk_mq_remove_hw_queues_cpuhp(q); + + /* register cpuhp for new initialized hctxs */ + blk_mq_add_hw_queues_cpuhp(q); } int blk_mq_init_allocated_queue(struct blk_mq_tag_set *set, diff --git a/block/blk-zoned.c b/block/blk-zoned.c index 0b1184176ce7..767bcbce74fa 100644 --- a/block/blk-zoned.c +++ b/block/blk-zoned.c @@ -18,7 +18,7 @@ #include <linux/vmalloc.h> #include <linux/sched/mm.h> #include <linux/spinlock.h> -#include <linux/atomic.h> +#include <linux/refcount.h> #include <linux/mempool.h> #include "blk.h" @@ -41,7 +41,6 @@ static const char *const zone_cond_name[] = { /* * Per-zone write plug. * @node: hlist_node structure for managing the plug using a hash table. - * @link: To list the plug in the zone write plug error list of the disk. * @ref: Zone write plug reference counter. A zone write plug reference is * always at least 1 when the plug is hashed in the disk plug hash table. * The reference is incremented whenever a new BIO needing plugging is @@ -63,8 +62,7 @@ static const char *const zone_cond_name[] = { */ struct blk_zone_wplug { struct hlist_node node; - struct list_head link; - atomic_t ref; + refcount_t ref; spinlock_t lock; unsigned int flags; unsigned int zone_no; @@ -80,8 +78,8 @@ struct blk_zone_wplug { * - BLK_ZONE_WPLUG_PLUGGED: Indicates that the zone write plug is plugged, * that is, that write BIOs are being throttled due to a write BIO already * being executed or the zone write plug bio list is not empty. - * - BLK_ZONE_WPLUG_ERROR: Indicates that a write error happened which will be - * recovered with a report zone to update the zone write pointer offset. + * - BLK_ZONE_WPLUG_NEED_WP_UPDATE: Indicates that we lost track of a zone + * write pointer offset and need to update it. * - BLK_ZONE_WPLUG_UNHASHED: Indicates that the zone write plug was removed * from the disk hash table and that the initial reference to the zone * write plug set when the plug was first added to the hash table has been @@ -91,11 +89,9 @@ struct blk_zone_wplug { * freed once all remaining references from BIOs or functions are dropped. */ #define BLK_ZONE_WPLUG_PLUGGED (1U << 0) -#define BLK_ZONE_WPLUG_ERROR (1U << 1) +#define BLK_ZONE_WPLUG_NEED_WP_UPDATE (1U << 1) #define BLK_ZONE_WPLUG_UNHASHED (1U << 2) -#define BLK_ZONE_WPLUG_BUSY (BLK_ZONE_WPLUG_PLUGGED | BLK_ZONE_WPLUG_ERROR) - /** * blk_zone_cond_str - Return string XXX in BLK_ZONE_COND_XXX. * @zone_cond: BLK_ZONE_COND_XXX. @@ -115,6 +111,30 @@ const char *blk_zone_cond_str(enum blk_zone_cond zone_cond) } EXPORT_SYMBOL_GPL(blk_zone_cond_str); +struct disk_report_zones_cb_args { + struct gendisk *disk; + report_zones_cb user_cb; + void *user_data; +}; + +static void disk_zone_wplug_sync_wp_offset(struct gendisk *disk, + struct blk_zone *zone); + +static int disk_report_zones_cb(struct blk_zone *zone, unsigned int idx, + void *data) +{ + struct disk_report_zones_cb_args *args = data; + struct gendisk *disk = args->disk; + + if (disk->zone_wplugs_hash) + disk_zone_wplug_sync_wp_offset(disk, zone); + + if (!args->user_cb) + return 0; + + return args->user_cb(zone, idx, args->user_data); +} + /** * blkdev_report_zones - Get zones information * @bdev: Target block device @@ -139,6 +159,11 @@ int blkdev_report_zones(struct block_device *bdev, sector_t sector, { struct gendisk *disk = bdev->bd_disk; sector_t capacity = get_capacity(disk); + struct disk_report_zones_cb_args args = { + .disk = disk, + .user_cb = cb, + .user_data = data, + }; if (!bdev_is_zoned(bdev) || WARN_ON_ONCE(!disk->fops->report_zones)) return -EOPNOTSUPP; @@ -146,7 +171,8 @@ int blkdev_report_zones(struct block_device *bdev, sector_t sector, if (!nr_zones || sector >= capacity) return 0; - return disk->fops->report_zones(disk, sector, nr_zones, cb, data); + return disk->fops->report_zones(disk, sector, nr_zones, + disk_report_zones_cb, &args); } EXPORT_SYMBOL_GPL(blkdev_report_zones); @@ -417,7 +443,7 @@ static struct blk_zone_wplug *disk_get_zone_wplug(struct gendisk *disk, hlist_for_each_entry_rcu(zwplug, &disk->zone_wplugs_hash[idx], node) { if (zwplug->zone_no == zno && - atomic_inc_not_zero(&zwplug->ref)) { + refcount_inc_not_zero(&zwplug->ref)) { rcu_read_unlock(); return zwplug; } @@ -438,9 +464,9 @@ static void disk_free_zone_wplug_rcu(struct rcu_head *rcu_head) static inline void disk_put_zone_wplug(struct blk_zone_wplug *zwplug) { - if (atomic_dec_and_test(&zwplug->ref)) { + if (refcount_dec_and_test(&zwplug->ref)) { WARN_ON_ONCE(!bio_list_empty(&zwplug->bio_list)); - WARN_ON_ONCE(!list_empty(&zwplug->link)); + WARN_ON_ONCE(zwplug->flags & BLK_ZONE_WPLUG_PLUGGED); WARN_ON_ONCE(!(zwplug->flags & BLK_ZONE_WPLUG_UNHASHED)); call_rcu(&zwplug->rcu_head, disk_free_zone_wplug_rcu); @@ -454,8 +480,8 @@ static inline bool disk_should_remove_zone_wplug(struct gendisk *disk, if (zwplug->flags & BLK_ZONE_WPLUG_UNHASHED) return false; - /* If the zone write plug is still busy, it cannot be removed. */ - if (zwplug->flags & BLK_ZONE_WPLUG_BUSY) + /* If the zone write plug is still plugged, it cannot be removed. */ + if (zwplug->flags & BLK_ZONE_WPLUG_PLUGGED) return false; /* @@ -469,7 +495,7 @@ static inline bool disk_should_remove_zone_wplug(struct gendisk *disk, * taken when the plug was allocated and another reference taken by the * caller context). */ - if (atomic_read(&zwplug->ref) > 2) + if (refcount_read(&zwplug->ref) > 2) return false; /* We can remove zone write plugs for zones that are empty or full. */ @@ -538,12 +564,11 @@ again: return NULL; INIT_HLIST_NODE(&zwplug->node); - INIT_LIST_HEAD(&zwplug->link); - atomic_set(&zwplug->ref, 2); + refcount_set(&zwplug->ref, 2); spin_lock_init(&zwplug->lock); zwplug->flags = 0; zwplug->zone_no = zno; - zwplug->wp_offset = sector & (disk->queue->limits.chunk_sectors - 1); + zwplug->wp_offset = bdev_offset_from_zone_start(disk->part0, sector); bio_list_init(&zwplug->bio_list); INIT_WORK(&zwplug->bio_work, blk_zone_wplug_bio_work); zwplug->disk = disk; @@ -587,124 +612,81 @@ static void disk_zone_wplug_abort(struct blk_zone_wplug *zwplug) } /* - * Abort (fail) all plugged BIOs of a zone write plug that are not aligned - * with the assumed write pointer location of the zone when the BIO will - * be unplugged. + * Set a zone write plug write pointer offset to the specified value. + * This aborts all plugged BIOs, which is fine as this function is called for + * a zone reset operation, a zone finish operation or if the zone needs a wp + * update from a report zone after a write error. */ -static void disk_zone_wplug_abort_unaligned(struct gendisk *disk, - struct blk_zone_wplug *zwplug) -{ - unsigned int wp_offset = zwplug->wp_offset; - struct bio_list bl = BIO_EMPTY_LIST; - struct bio *bio; - - while ((bio = bio_list_pop(&zwplug->bio_list))) { - if (disk_zone_is_full(disk, zwplug->zone_no, wp_offset) || - (bio_op(bio) != REQ_OP_ZONE_APPEND && - bio_offset_from_zone_start(bio) != wp_offset)) { - blk_zone_wplug_bio_io_error(zwplug, bio); - continue; - } - - wp_offset += bio_sectors(bio); - bio_list_add(&bl, bio); - } - - bio_list_merge(&zwplug->bio_list, &bl); -} - -static inline void disk_zone_wplug_set_error(struct gendisk *disk, - struct blk_zone_wplug *zwplug) +static void disk_zone_wplug_set_wp_offset(struct gendisk *disk, + struct blk_zone_wplug *zwplug, + unsigned int wp_offset) { - unsigned long flags; + lockdep_assert_held(&zwplug->lock); - if (zwplug->flags & BLK_ZONE_WPLUG_ERROR) - return; + /* Update the zone write pointer and abort all plugged BIOs. */ + zwplug->flags &= ~BLK_ZONE_WPLUG_NEED_WP_UPDATE; + zwplug->wp_offset = wp_offset; + disk_zone_wplug_abort(zwplug); /* - * At this point, we already have a reference on the zone write plug. - * However, since we are going to add the plug to the disk zone write - * plugs work list, increase its reference count. This reference will - * be dropped in disk_zone_wplugs_work() once the error state is - * handled, or in disk_zone_wplug_clear_error() if the zone is reset or - * finished. + * The zone write plug now has no BIO plugged: remove it from the + * hash table so that it cannot be seen. The plug will be freed + * when the last reference is dropped. */ - zwplug->flags |= BLK_ZONE_WPLUG_ERROR; - atomic_inc(&zwplug->ref); - - spin_lock_irqsave(&disk->zone_wplugs_lock, flags); - list_add_tail(&zwplug->link, &disk->zone_wplugs_err_list); - spin_unlock_irqrestore(&disk->zone_wplugs_lock, flags); + if (disk_should_remove_zone_wplug(disk, zwplug)) + disk_remove_zone_wplug(disk, zwplug); } -static inline void disk_zone_wplug_clear_error(struct gendisk *disk, - struct blk_zone_wplug *zwplug) +static unsigned int blk_zone_wp_offset(struct blk_zone *zone) { - unsigned long flags; - - if (!(zwplug->flags & BLK_ZONE_WPLUG_ERROR)) - return; - - /* - * We are racing with the error handling work which drops the reference - * on the zone write plug after handling the error state. So remove the - * plug from the error list and drop its reference count only if the - * error handling has not yet started, that is, if the zone write plug - * is still listed. - */ - spin_lock_irqsave(&disk->zone_wplugs_lock, flags); - if (!list_empty(&zwplug->link)) { - list_del_init(&zwplug->link); - zwplug->flags &= ~BLK_ZONE_WPLUG_ERROR; - disk_put_zone_wplug(zwplug); + switch (zone->cond) { + case BLK_ZONE_COND_IMP_OPEN: + case BLK_ZONE_COND_EXP_OPEN: + case BLK_ZONE_COND_CLOSED: + return zone->wp - zone->start; + case BLK_ZONE_COND_FULL: + return zone->len; + case BLK_ZONE_COND_EMPTY: + return 0; + case BLK_ZONE_COND_NOT_WP: + case BLK_ZONE_COND_OFFLINE: + case BLK_ZONE_COND_READONLY: + default: + /* + * Conventional, offline and read-only zones do not have a valid + * write pointer. + */ + return UINT_MAX; } - spin_unlock_irqrestore(&disk->zone_wplugs_lock, flags); } -/* - * Set a zone write plug write pointer offset to either 0 (zone reset case) - * or to the zone size (zone finish case). This aborts all plugged BIOs, which - * is fine to do as doing a zone reset or zone finish while writes are in-flight - * is a mistake from the user which will most likely cause all plugged BIOs to - * fail anyway. - */ -static void disk_zone_wplug_set_wp_offset(struct gendisk *disk, - struct blk_zone_wplug *zwplug, - unsigned int wp_offset) +static void disk_zone_wplug_sync_wp_offset(struct gendisk *disk, + struct blk_zone *zone) { + struct blk_zone_wplug *zwplug; unsigned long flags; - spin_lock_irqsave(&zwplug->lock, flags); - - /* - * Make sure that a BIO completion or another zone reset or finish - * operation has not already removed the plug from the hash table. - */ - if (zwplug->flags & BLK_ZONE_WPLUG_UNHASHED) { - spin_unlock_irqrestore(&zwplug->lock, flags); + zwplug = disk_get_zone_wplug(disk, zone->start); + if (!zwplug) return; - } - /* Update the zone write pointer and abort all plugged BIOs. */ - zwplug->wp_offset = wp_offset; - disk_zone_wplug_abort(zwplug); + spin_lock_irqsave(&zwplug->lock, flags); + if (zwplug->flags & BLK_ZONE_WPLUG_NEED_WP_UPDATE) + disk_zone_wplug_set_wp_offset(disk, zwplug, + blk_zone_wp_offset(zone)); + spin_unlock_irqrestore(&zwplug->lock, flags); - /* - * Updating the write pointer offset puts back the zone - * in a good state. So clear the error flag and decrement the - * error count if we were in error state. - */ - disk_zone_wplug_clear_error(disk, zwplug); + disk_put_zone_wplug(zwplug); +} - /* - * The zone write plug now has no BIO plugged: remove it from the - * hash table so that it cannot be seen. The plug will be freed - * when the last reference is dropped. - */ - if (disk_should_remove_zone_wplug(disk, zwplug)) - disk_remove_zone_wplug(disk, zwplug); +static int disk_zone_sync_wp_offset(struct gendisk *disk, sector_t sector) +{ + struct disk_report_zones_cb_args args = { + .disk = disk, + }; - spin_unlock_irqrestore(&zwplug->lock, flags); + return disk->fops->report_zones(disk, sector, 1, + disk_report_zones_cb, &args); } static bool blk_zone_wplug_handle_reset_or_finish(struct bio *bio, @@ -713,6 +695,7 @@ static bool blk_zone_wplug_handle_reset_or_finish(struct bio *bio, struct gendisk *disk = bio->bi_bdev->bd_disk; sector_t sector = bio->bi_iter.bi_sector; struct blk_zone_wplug *zwplug; + unsigned long flags; /* Conventional zones cannot be reset nor finished. */ if (disk_zone_is_conv(disk, sector)) { @@ -721,6 +704,15 @@ static bool blk_zone_wplug_handle_reset_or_finish(struct bio *bio, } /* + * No-wait reset or finish BIOs do not make much sense as the callers + * issue these as blocking operations in most cases. To avoid issues + * the BIO execution potentially failing with BLK_STS_AGAIN, warn about + * REQ_NOWAIT being set and ignore that flag. + */ + if (WARN_ON_ONCE(bio->bi_opf & REQ_NOWAIT)) + bio->bi_opf &= ~REQ_NOWAIT; + + /* * If we have a zone write plug, set its write pointer offset to 0 * (reset case) or to the zone size (finish case). This will abort all * BIOs plugged for the target zone. It is fine as resetting or @@ -729,7 +721,9 @@ static bool blk_zone_wplug_handle_reset_or_finish(struct bio *bio, */ zwplug = disk_get_zone_wplug(disk, sector); if (zwplug) { + spin_lock_irqsave(&zwplug->lock, flags); disk_zone_wplug_set_wp_offset(disk, zwplug, wp_offset); + spin_unlock_irqrestore(&zwplug->lock, flags); disk_put_zone_wplug(zwplug); } @@ -740,6 +734,7 @@ static bool blk_zone_wplug_handle_reset_all(struct bio *bio) { struct gendisk *disk = bio->bi_bdev->bd_disk; struct blk_zone_wplug *zwplug; + unsigned long flags; sector_t sector; /* @@ -751,7 +746,9 @@ static bool blk_zone_wplug_handle_reset_all(struct bio *bio) sector += disk->queue->limits.chunk_sectors) { zwplug = disk_get_zone_wplug(disk, sector); if (zwplug) { + spin_lock_irqsave(&zwplug->lock, flags); disk_zone_wplug_set_wp_offset(disk, zwplug, 0); + spin_unlock_irqrestore(&zwplug->lock, flags); disk_put_zone_wplug(zwplug); } } @@ -759,10 +756,26 @@ static bool blk_zone_wplug_handle_reset_all(struct bio *bio) return false; } -static inline void blk_zone_wplug_add_bio(struct blk_zone_wplug *zwplug, - struct bio *bio, unsigned int nr_segs) +static void disk_zone_wplug_schedule_bio_work(struct gendisk *disk, + struct blk_zone_wplug *zwplug) { /* + * Take a reference on the zone write plug and schedule the submission + * of the next plugged BIO. blk_zone_wplug_bio_work() will release the + * reference we take here. + */ + WARN_ON_ONCE(!(zwplug->flags & BLK_ZONE_WPLUG_PLUGGED)); + refcount_inc(&zwplug->ref); + queue_work(disk->zone_wplugs_wq, &zwplug->bio_work); +} + +static inline void disk_zone_wplug_add_bio(struct gendisk *disk, + struct blk_zone_wplug *zwplug, + struct bio *bio, unsigned int nr_segs) +{ + bool schedule_bio_work = false; + + /* * Grab an extra reference on the BIO request queue usage counter. * This reference will be reused to submit a request for the BIO for * blk-mq devices and dropped when the BIO is failed and after @@ -778,6 +791,16 @@ static inline void blk_zone_wplug_add_bio(struct blk_zone_wplug *zwplug, bio_clear_polled(bio); /* + * REQ_NOWAIT BIOs are always handled using the zone write plug BIO + * work, which can block. So clear the REQ_NOWAIT flag and schedule the + * work if this is the first BIO we are plugging. + */ + if (bio->bi_opf & REQ_NOWAIT) { + schedule_bio_work = !(zwplug->flags & BLK_ZONE_WPLUG_PLUGGED); + bio->bi_opf &= ~REQ_NOWAIT; + } + + /* * Reuse the poll cookie field to store the number of segments when * split to the hardware limits. */ @@ -790,6 +813,11 @@ static inline void blk_zone_wplug_add_bio(struct blk_zone_wplug *zwplug, * at the tail of the list to preserve the sequential write order. */ bio_list_add(&zwplug->bio_list, bio); + + zwplug->flags |= BLK_ZONE_WPLUG_PLUGGED; + + if (schedule_bio_work) + disk_zone_wplug_schedule_bio_work(disk, zwplug); } /* @@ -903,12 +931,22 @@ static bool blk_zone_wplug_prepare_bio(struct blk_zone_wplug *zwplug, struct gendisk *disk = bio->bi_bdev->bd_disk; /* + * If we lost track of the zone write pointer due to a write error, + * the user must either execute a report zones, reset the zone or finish + * the to recover a reliable write pointer position. Fail BIOs if the + * user did not do that as we cannot handle emulated zone append + * otherwise. + */ + if (zwplug->flags & BLK_ZONE_WPLUG_NEED_WP_UPDATE) + return false; + + /* * Check that the user is not attempting to write to a full zone. * We know such BIO will fail, and that would potentially overflow our * write pointer offset beyond the end of the zone. */ if (disk_zone_wplug_is_full(disk, zwplug)) - goto err; + return false; if (bio_op(bio) == REQ_OP_ZONE_APPEND) { /* @@ -927,24 +965,18 @@ static bool blk_zone_wplug_prepare_bio(struct blk_zone_wplug *zwplug, bio_set_flag(bio, BIO_EMULATES_ZONE_APPEND); } else { /* - * Check for non-sequential writes early because we avoid a - * whole lot of error handling trouble if we don't send it off - * to the driver. + * Check for non-sequential writes early as we know that BIOs + * with a start sector not unaligned to the zone write pointer + * will fail. */ if (bio_offset_from_zone_start(bio) != zwplug->wp_offset) - goto err; + return false; } /* Advance the zone write pointer offset. */ zwplug->wp_offset += bio_sectors(bio); return true; - -err: - /* We detected an invalid write BIO: schedule error recovery. */ - disk_zone_wplug_set_error(disk, zwplug); - kblockd_schedule_work(&disk->zone_wplugs_work); - return false; } static bool blk_zone_wplug_handle_write(struct bio *bio, unsigned int nr_segs) @@ -983,7 +1015,10 @@ static bool blk_zone_wplug_handle_write(struct bio *bio, unsigned int nr_segs) zwplug = disk_get_and_lock_zone_wplug(disk, sector, gfp_mask, &flags); if (!zwplug) { - bio_io_error(bio); + if (bio->bi_opf & REQ_NOWAIT) + bio_wouldblock_error(bio); + else + bio_io_error(bio); return true; } @@ -991,18 +1026,20 @@ static bool blk_zone_wplug_handle_write(struct bio *bio, unsigned int nr_segs) bio_set_flag(bio, BIO_ZONE_WRITE_PLUGGING); /* - * If the zone is already plugged or has a pending error, add the BIO - * to the plug BIO list. Otherwise, plug and let the BIO execute. + * If the zone is already plugged, add the BIO to the plug BIO list. + * Do the same for REQ_NOWAIT BIOs to ensure that we will not see a + * BLK_STS_AGAIN failure if we let the BIO execute. + * Otherwise, plug and let the BIO execute. */ - if (zwplug->flags & BLK_ZONE_WPLUG_BUSY) + if ((zwplug->flags & BLK_ZONE_WPLUG_PLUGGED) || + (bio->bi_opf & REQ_NOWAIT)) goto plug; - /* - * If an error is detected when preparing the BIO, add it to the BIO - * list so that error recovery can deal with it. - */ - if (!blk_zone_wplug_prepare_bio(zwplug, bio)) - goto plug; + if (!blk_zone_wplug_prepare_bio(zwplug, bio)) { + spin_unlock_irqrestore(&zwplug->lock, flags); + bio_io_error(bio); + return true; + } zwplug->flags |= BLK_ZONE_WPLUG_PLUGGED; @@ -1011,8 +1048,7 @@ static bool blk_zone_wplug_handle_write(struct bio *bio, unsigned int nr_segs) return false; plug: - zwplug->flags |= BLK_ZONE_WPLUG_PLUGGED; - blk_zone_wplug_add_bio(zwplug, bio, nr_segs); + disk_zone_wplug_add_bio(disk, zwplug, bio, nr_segs); spin_unlock_irqrestore(&zwplug->lock, flags); @@ -1096,19 +1132,6 @@ bool blk_zone_plug_bio(struct bio *bio, unsigned int nr_segs) } EXPORT_SYMBOL_GPL(blk_zone_plug_bio); -static void disk_zone_wplug_schedule_bio_work(struct gendisk *disk, - struct blk_zone_wplug *zwplug) -{ - /* - * Take a reference on the zone write plug and schedule the submission - * of the next plugged BIO. blk_zone_wplug_bio_work() will release the - * reference we take here. - */ - WARN_ON_ONCE(!(zwplug->flags & BLK_ZONE_WPLUG_PLUGGED)); - atomic_inc(&zwplug->ref); - queue_work(disk->zone_wplugs_wq, &zwplug->bio_work); -} - static void disk_zone_wplug_unplug_bio(struct gendisk *disk, struct blk_zone_wplug *zwplug) { @@ -1116,16 +1139,6 @@ static void disk_zone_wplug_unplug_bio(struct gendisk *disk, spin_lock_irqsave(&zwplug->lock, flags); - /* - * If we had an error, schedule error recovery. The recovery work - * will restart submission of plugged BIOs. - */ - if (zwplug->flags & BLK_ZONE_WPLUG_ERROR) { - spin_unlock_irqrestore(&zwplug->lock, flags); - kblockd_schedule_work(&disk->zone_wplugs_work); - return; - } - /* Schedule submission of the next plugged BIO if we have one. */ if (!bio_list_empty(&zwplug->bio_list)) { disk_zone_wplug_schedule_bio_work(disk, zwplug); @@ -1168,12 +1181,13 @@ void blk_zone_write_plug_bio_endio(struct bio *bio) } /* - * If the BIO failed, mark the plug as having an error to trigger - * recovery. + * If the BIO failed, abort all plugged BIOs and mark the plug as + * needing a write pointer update. */ if (bio->bi_status != BLK_STS_OK) { spin_lock_irqsave(&zwplug->lock, flags); - disk_zone_wplug_set_error(disk, zwplug); + disk_zone_wplug_abort(zwplug); + zwplug->flags |= BLK_ZONE_WPLUG_NEED_WP_UPDATE; spin_unlock_irqrestore(&zwplug->lock, flags); } @@ -1229,6 +1243,7 @@ static void blk_zone_wplug_bio_work(struct work_struct *work) */ spin_lock_irqsave(&zwplug->lock, flags); +again: bio = bio_list_pop(&zwplug->bio_list); if (!bio) { zwplug->flags &= ~BLK_ZONE_WPLUG_PLUGGED; @@ -1237,10 +1252,8 @@ static void blk_zone_wplug_bio_work(struct work_struct *work) } if (!blk_zone_wplug_prepare_bio(zwplug, bio)) { - /* Error recovery will decide what to do with the BIO. */ - bio_list_add_head(&zwplug->bio_list, bio); - spin_unlock_irqrestore(&zwplug->lock, flags); - goto put_zwplug; + blk_zone_wplug_bio_io_error(zwplug, bio); + goto again; } spin_unlock_irqrestore(&zwplug->lock, flags); @@ -1262,120 +1275,6 @@ put_zwplug: disk_put_zone_wplug(zwplug); } -static unsigned int blk_zone_wp_offset(struct blk_zone *zone) -{ - switch (zone->cond) { - case BLK_ZONE_COND_IMP_OPEN: - case BLK_ZONE_COND_EXP_OPEN: - case BLK_ZONE_COND_CLOSED: - return zone->wp - zone->start; - case BLK_ZONE_COND_FULL: - return zone->len; - case BLK_ZONE_COND_EMPTY: - return 0; - case BLK_ZONE_COND_NOT_WP: - case BLK_ZONE_COND_OFFLINE: - case BLK_ZONE_COND_READONLY: - default: - /* - * Conventional, offline and read-only zones do not have a valid - * write pointer. - */ - return UINT_MAX; - } -} - -static int blk_zone_wplug_report_zone_cb(struct blk_zone *zone, - unsigned int idx, void *data) -{ - struct blk_zone *zonep = data; - - *zonep = *zone; - return 0; -} - -static void disk_zone_wplug_handle_error(struct gendisk *disk, - struct blk_zone_wplug *zwplug) -{ - sector_t zone_start_sector = - bdev_zone_sectors(disk->part0) * zwplug->zone_no; - unsigned int noio_flag; - struct blk_zone zone; - unsigned long flags; - int ret; - - /* Get the current zone information from the device. */ - noio_flag = memalloc_noio_save(); - ret = disk->fops->report_zones(disk, zone_start_sector, 1, - blk_zone_wplug_report_zone_cb, &zone); - memalloc_noio_restore(noio_flag); - - spin_lock_irqsave(&zwplug->lock, flags); - - /* - * A zone reset or finish may have cleared the error already. In such - * case, do nothing as the report zones may have seen the "old" write - * pointer value before the reset/finish operation completed. - */ - if (!(zwplug->flags & BLK_ZONE_WPLUG_ERROR)) - goto unlock; - - zwplug->flags &= ~BLK_ZONE_WPLUG_ERROR; - - if (ret != 1) { - /* - * We failed to get the zone information, meaning that something - * is likely really wrong with the device. Abort all remaining - * plugged BIOs as otherwise we could endup waiting forever on - * plugged BIOs to complete if there is a queue freeze on-going. - */ - disk_zone_wplug_abort(zwplug); - goto unplug; - } - - /* Update the zone write pointer offset. */ - zwplug->wp_offset = blk_zone_wp_offset(&zone); - disk_zone_wplug_abort_unaligned(disk, zwplug); - - /* Restart BIO submission if we still have any BIO left. */ - if (!bio_list_empty(&zwplug->bio_list)) { - disk_zone_wplug_schedule_bio_work(disk, zwplug); - goto unlock; - } - -unplug: - zwplug->flags &= ~BLK_ZONE_WPLUG_PLUGGED; - if (disk_should_remove_zone_wplug(disk, zwplug)) - disk_remove_zone_wplug(disk, zwplug); - -unlock: - spin_unlock_irqrestore(&zwplug->lock, flags); -} - -static void disk_zone_wplugs_work(struct work_struct *work) -{ - struct gendisk *disk = - container_of(work, struct gendisk, zone_wplugs_work); - struct blk_zone_wplug *zwplug; - unsigned long flags; - - spin_lock_irqsave(&disk->zone_wplugs_lock, flags); - - while (!list_empty(&disk->zone_wplugs_err_list)) { - zwplug = list_first_entry(&disk->zone_wplugs_err_list, - struct blk_zone_wplug, link); - list_del_init(&zwplug->link); - spin_unlock_irqrestore(&disk->zone_wplugs_lock, flags); - - disk_zone_wplug_handle_error(disk, zwplug); - disk_put_zone_wplug(zwplug); - - spin_lock_irqsave(&disk->zone_wplugs_lock, flags); - } - - spin_unlock_irqrestore(&disk->zone_wplugs_lock, flags); -} - static inline unsigned int disk_zone_wplugs_hash_size(struct gendisk *disk) { return 1U << disk->zone_wplugs_hash_bits; @@ -1384,8 +1283,6 @@ static inline unsigned int disk_zone_wplugs_hash_size(struct gendisk *disk) void disk_init_zone_resources(struct gendisk *disk) { spin_lock_init(&disk->zone_wplugs_lock); - INIT_LIST_HEAD(&disk->zone_wplugs_err_list); - INIT_WORK(&disk->zone_wplugs_work, disk_zone_wplugs_work); } /* @@ -1450,7 +1347,7 @@ static void disk_destroy_zone_wplugs_hash_table(struct gendisk *disk) while (!hlist_empty(&disk->zone_wplugs_hash[i])) { zwplug = hlist_entry(disk->zone_wplugs_hash[i].first, struct blk_zone_wplug, node); - atomic_inc(&zwplug->ref); + refcount_inc(&zwplug->ref); disk_remove_zone_wplug(disk, zwplug); disk_put_zone_wplug(zwplug); } @@ -1484,8 +1381,6 @@ void disk_free_zone_resources(struct gendisk *disk) if (!disk->zone_wplugs_pool) return; - cancel_work_sync(&disk->zone_wplugs_work); - if (disk->zone_wplugs_wq) { destroy_workqueue(disk->zone_wplugs_wq); disk->zone_wplugs_wq = NULL; @@ -1682,6 +1577,8 @@ static int blk_revalidate_seq_zone(struct blk_zone *zone, unsigned int idx, if (!disk->zone_wplugs_hash) return 0; + disk_zone_wplug_sync_wp_offset(disk, zone); + wp_offset = blk_zone_wp_offset(zone); if (!wp_offset || wp_offset >= zone->capacity) return 0; @@ -1818,6 +1715,7 @@ int blk_revalidate_disk_zones(struct gendisk *disk) memalloc_noio_restore(noio_flag); return ret; } + ret = disk->fops->report_zones(disk, 0, UINT_MAX, blk_revalidate_zone_cb, &args); if (!ret) { @@ -1854,6 +1752,48 @@ int blk_revalidate_disk_zones(struct gendisk *disk) } EXPORT_SYMBOL_GPL(blk_revalidate_disk_zones); +/** + * blk_zone_issue_zeroout - zero-fill a block range in a zone + * @bdev: blockdev to write + * @sector: start sector + * @nr_sects: number of sectors to write + * @gfp_mask: memory allocation flags (for bio_alloc) + * + * Description: + * Zero-fill a block range in a zone (@sector must be equal to the zone write + * pointer), handling potential errors due to the (initially unknown) lack of + * hardware offload (See blkdev_issue_zeroout()). + */ +int blk_zone_issue_zeroout(struct block_device *bdev, sector_t sector, + sector_t nr_sects, gfp_t gfp_mask) +{ + int ret; + + if (WARN_ON_ONCE(!bdev_is_zoned(bdev))) + return -EIO; + + ret = blkdev_issue_zeroout(bdev, sector, nr_sects, gfp_mask, + BLKDEV_ZERO_NOFALLBACK); + if (ret != -EOPNOTSUPP) + return ret; + + /* + * The failed call to blkdev_issue_zeroout() advanced the zone write + * pointer. Undo this using a report zone to update the zone write + * pointer to the correct current value. + */ + ret = disk_zone_sync_wp_offset(bdev->bd_disk, sector); + if (ret != 1) + return ret < 0 ? ret : -EIO; + + /* + * Retry without BLKDEV_ZERO_NOFALLBACK to force the fallback to a + * regular write with zero-pages. + */ + return blkdev_issue_zeroout(bdev, sector, nr_sects, gfp_mask, 0); +} +EXPORT_SYMBOL_GPL(blk_zone_issue_zeroout); + #ifdef CONFIG_BLK_DEBUG_FS int queue_zone_wplugs_show(void *data, struct seq_file *m) @@ -1876,7 +1816,7 @@ int queue_zone_wplugs_show(void *data, struct seq_file *m) spin_lock_irqsave(&zwplug->lock, flags); zwp_zone_no = zwplug->zone_no; zwp_flags = zwplug->flags; - zwp_ref = atomic_read(&zwplug->ref); + zwp_ref = refcount_read(&zwplug->ref); zwp_wp_offset = zwplug->wp_offset; zwp_bio_list_size = bio_list_size(&zwplug->bio_list); spin_unlock_irqrestore(&zwplug->lock, flags); diff --git a/block/blk.h b/block/blk.h index 88fab6a81701..1426f9c28197 100644 --- a/block/blk.h +++ b/block/blk.h @@ -469,11 +469,6 @@ static inline bool bio_zone_write_plugging(struct bio *bio) { return bio_flagged(bio, BIO_ZONE_WRITE_PLUGGING); } -static inline bool bio_is_zone_append(struct bio *bio) -{ - return bio_op(bio) == REQ_OP_ZONE_APPEND || - bio_flagged(bio, BIO_EMULATES_ZONE_APPEND); -} void blk_zone_write_plug_bio_merged(struct bio *bio); void blk_zone_write_plug_init_request(struct request *rq); static inline void blk_zone_update_request_bio(struct request *rq, @@ -522,10 +517,6 @@ static inline bool bio_zone_write_plugging(struct bio *bio) { return false; } -static inline bool bio_is_zone_append(struct bio *bio) -{ - return false; -} static inline void blk_zone_write_plug_bio_merged(struct bio *bio) { } diff --git a/drivers/accel/ivpu/ivpu_gem.c b/drivers/accel/ivpu/ivpu_gem.c index 1b409dbd332d..c8daffd90f30 100644 --- a/drivers/accel/ivpu/ivpu_gem.c +++ b/drivers/accel/ivpu/ivpu_gem.c @@ -406,7 +406,7 @@ static void ivpu_bo_print_info(struct ivpu_bo *bo, struct drm_printer *p) mutex_lock(&bo->lock); drm_printf(p, "%-9p %-3u 0x%-12llx %-10lu 0x%-8x %-4u", - bo, bo->ctx->id, bo->vpu_addr, bo->base.base.size, + bo, bo->ctx ? bo->ctx->id : 0, bo->vpu_addr, bo->base.base.size, bo->flags, kref_read(&bo->base.base.refcount)); if (bo->base.pages) diff --git a/drivers/accel/ivpu/ivpu_pm.c b/drivers/accel/ivpu/ivpu_pm.c index 59d3170f5e35..10b7ae0f866c 100644 --- a/drivers/accel/ivpu/ivpu_pm.c +++ b/drivers/accel/ivpu/ivpu_pm.c @@ -364,6 +364,7 @@ void ivpu_pm_init(struct ivpu_device *vdev) pm_runtime_use_autosuspend(dev); pm_runtime_set_autosuspend_delay(dev, delay); + pm_runtime_set_active(dev); ivpu_dbg(vdev, PM, "Autosuspend delay = %d\n", delay); } @@ -378,7 +379,6 @@ void ivpu_pm_enable(struct ivpu_device *vdev) { struct device *dev = vdev->drm.dev; - pm_runtime_set_active(dev); pm_runtime_allow(dev); pm_runtime_mark_last_busy(dev); pm_runtime_put_autosuspend(dev); diff --git a/drivers/acpi/acpica/evxfregn.c b/drivers/acpi/acpica/evxfregn.c index 95f78383bbdb..bff2d099f469 100644 --- a/drivers/acpi/acpica/evxfregn.c +++ b/drivers/acpi/acpica/evxfregn.c @@ -232,8 +232,6 @@ acpi_remove_address_space_handler(acpi_handle device, /* Now we can delete the handler object */ - acpi_os_release_mutex(handler_obj->address_space. - context_mutex); acpi_ut_remove_reference(handler_obj); goto unlock_and_exit; } diff --git a/drivers/acpi/arm64/iort.c b/drivers/acpi/arm64/iort.c index 4c745a26226b..bf3be532e089 100644 --- a/drivers/acpi/arm64/iort.c +++ b/drivers/acpi/arm64/iort.c @@ -1703,6 +1703,8 @@ static struct acpi_platform_list pmcg_plat_info[] __initdata = { /* HiSilicon Hip09 Platform */ {"HISI ", "HIP09 ", 0, ACPI_SIG_IORT, greater_than_or_equal, "Erratum #162001900", IORT_SMMU_V3_PMCG_HISI_HIP09}, + {"HISI ", "HIP09A ", 0, ACPI_SIG_IORT, greater_than_or_equal, + "Erratum #162001900", IORT_SMMU_V3_PMCG_HISI_HIP09}, /* HiSilicon Hip10/11 Platform uses the same SMMU IP with Hip09 */ {"HISI ", "HIP10 ", 0, ACPI_SIG_IORT, greater_than_or_equal, "Erratum #162001900", IORT_SMMU_V3_PMCG_HISI_HIP09}, diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c index 5429ec9ef06f..a5d47819b3a4 100644 --- a/drivers/acpi/nfit/core.c +++ b/drivers/acpi/nfit/core.c @@ -454,8 +454,13 @@ int acpi_nfit_ctl(struct nvdimm_bus_descriptor *nd_desc, struct nvdimm *nvdimm, if (cmd_rc) *cmd_rc = -EINVAL; - if (cmd == ND_CMD_CALL) + if (cmd == ND_CMD_CALL) { + if (!buf || buf_len < sizeof(*call_pkg)) + return -EINVAL; + call_pkg = buf; + } + func = cmd_to_func(nfit_mem, cmd, call_pkg, &family); if (func < 0) return func; diff --git a/drivers/acpi/resource.c b/drivers/acpi/resource.c index 7fe842dae1ec..821867de43be 100644 --- a/drivers/acpi/resource.c +++ b/drivers/acpi/resource.c @@ -250,6 +250,9 @@ static bool acpi_decode_space(struct resource_win *win, switch (addr->resource_type) { case ACPI_MEMORY_RANGE: acpi_dev_memresource_flags(res, len, wp); + + if (addr->info.mem.caching == ACPI_PREFETCHABLE_MEMORY) + res->flags |= IORESOURCE_PREFETCH; break; case ACPI_IO_RANGE: acpi_dev_ioresource_flags(res, len, iodec, @@ -265,9 +268,6 @@ static bool acpi_decode_space(struct resource_win *win, if (addr->producer_consumer == ACPI_PRODUCER) res->flags |= IORESOURCE_WINDOW; - if (addr->info.mem.caching == ACPI_PREFETCHABLE_MEMORY) - res->flags |= IORESOURCE_PREFETCH; - return !(res->flags & IORESOURCE_DISABLED); } diff --git a/drivers/ata/sata_highbank.c b/drivers/ata/sata_highbank.c index 63ef7bb073ce..596c6d294da9 100644 --- a/drivers/ata/sata_highbank.c +++ b/drivers/ata/sata_highbank.c @@ -348,6 +348,7 @@ static int highbank_initialize_phys(struct device *dev, void __iomem *addr) phy_nodes[phy] = phy_data.np; cphy_base[phy] = of_iomap(phy_nodes[phy], 0); if (cphy_base[phy] == NULL) { + of_node_put(phy_data.np); return 0; } phy_count += 1; diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c index e3e2afc2c83c..5962ea1230a1 100644 --- a/drivers/base/regmap/regmap.c +++ b/drivers/base/regmap/regmap.c @@ -1063,13 +1063,13 @@ skip_format_initialization: /* Sanity check */ if (range_cfg->range_max < range_cfg->range_min) { - dev_err(map->dev, "Invalid range %d: %d < %d\n", i, + dev_err(map->dev, "Invalid range %d: %u < %u\n", i, range_cfg->range_max, range_cfg->range_min); goto err_range; } if (range_cfg->range_max > map->max_register) { - dev_err(map->dev, "Invalid range %d: %d > %d\n", i, + dev_err(map->dev, "Invalid range %d: %u > %u\n", i, range_cfg->range_max, map->max_register); goto err_range; } diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c index 90bc605ff6c2..458ac54e7b20 100644 --- a/drivers/block/ublk_drv.c +++ b/drivers/block/ublk_drv.c @@ -1599,6 +1599,21 @@ static void ublk_unquiesce_dev(struct ublk_device *ub) blk_mq_kick_requeue_list(ub->ub_disk->queue); } +static struct gendisk *ublk_detach_disk(struct ublk_device *ub) +{ + struct gendisk *disk; + + /* Sync with ublk_abort_queue() by holding the lock */ + spin_lock(&ub->lock); + disk = ub->ub_disk; + ub->dev_info.state = UBLK_S_DEV_DEAD; + ub->dev_info.ublksrv_pid = -1; + ub->ub_disk = NULL; + spin_unlock(&ub->lock); + + return disk; +} + static void ublk_stop_dev(struct ublk_device *ub) { struct gendisk *disk; @@ -1612,14 +1627,7 @@ static void ublk_stop_dev(struct ublk_device *ub) ublk_unquiesce_dev(ub); } del_gendisk(ub->ub_disk); - - /* Sync with ublk_abort_queue() by holding the lock */ - spin_lock(&ub->lock); - disk = ub->ub_disk; - ub->dev_info.state = UBLK_S_DEV_DEAD; - ub->dev_info.ublksrv_pid = -1; - ub->ub_disk = NULL; - spin_unlock(&ub->lock); + disk = ublk_detach_disk(ub); put_disk(disk); unlock: mutex_unlock(&ub->mutex); @@ -2295,7 +2303,7 @@ static int ublk_ctrl_start_dev(struct ublk_device *ub, struct io_uring_cmd *cmd) out_put_cdev: if (ret) { - ub->dev_info.state = UBLK_S_DEV_DEAD; + ublk_detach_disk(ub); ublk_put_device(ub); } if (ret) diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index 43c96b73a711..0e50b65e1dbf 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -1587,9 +1587,12 @@ static void virtblk_remove(struct virtio_device *vdev) static int virtblk_freeze(struct virtio_device *vdev) { struct virtio_blk *vblk = vdev->priv; + struct request_queue *q = vblk->disk->queue; /* Ensure no requests in virtqueues before deleting vqs. */ - blk_mq_freeze_queue(vblk->disk->queue); + blk_mq_freeze_queue(q); + blk_mq_quiesce_queue_nowait(q); + blk_mq_unfreeze_queue(q); /* Ensure we don't receive any more interrupts */ virtio_reset_device(vdev); @@ -1613,8 +1616,8 @@ static int virtblk_restore(struct virtio_device *vdev) return ret; virtio_device_ready(vdev); + blk_mq_unquiesce_queue(vblk->disk->queue); - blk_mq_unfreeze_queue(vblk->disk->queue); return 0; } #endif diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index d0432b1707ce..bf83a104086c 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -524,6 +524,12 @@ static ssize_t backing_dev_store(struct device *dev, } nr_pages = i_size_read(inode) >> PAGE_SHIFT; + /* Refuse to use zero sized device (also prevents self reference) */ + if (!nr_pages) { + err = -EINVAL; + goto out; + } + bitmap_sz = BITS_TO_LONGS(nr_pages) * sizeof(long); bitmap = kvzalloc(bitmap_sz, GFP_KERNEL); if (!bitmap) { @@ -1319,12 +1325,16 @@ static void zram_meta_free(struct zram *zram, u64 disksize) size_t num_pages = disksize >> PAGE_SHIFT; size_t index; + if (!zram->table) + return; + /* Free all pages that are still in this zram device */ for (index = 0; index < num_pages; index++) zram_free_page(zram, index); zs_destroy_pool(zram->mem_pool); vfree(zram->table); + zram->table = NULL; } static bool zram_meta_alloc(struct zram *zram, u64 disksize) @@ -2165,11 +2175,6 @@ static void zram_reset_device(struct zram *zram) zram->limit_pages = 0; - if (!init_done(zram)) { - up_write(&zram->init_lock); - return; - } - set_capacity_and_notify(zram->disk, 0); part_stat_set_all(zram->disk->part0, 0); diff --git a/drivers/bluetooth/btmtk.c b/drivers/bluetooth/btmtk.c index 480e4adba9fa..85e99641eaae 100644 --- a/drivers/bluetooth/btmtk.c +++ b/drivers/bluetooth/btmtk.c @@ -395,6 +395,7 @@ int btmtk_process_coredump(struct hci_dev *hdev, struct sk_buff *skb) { struct btmtk_data *data = hci_get_priv(hdev); int err; + bool complete = false; if (!IS_ENABLED(CONFIG_DEV_COREDUMP)) { kfree_skb(skb); @@ -416,19 +417,22 @@ int btmtk_process_coredump(struct hci_dev *hdev, struct sk_buff *skb) fallthrough; case HCI_DEVCOREDUMP_ACTIVE: default: + /* Mediatek coredump data would be more than MTK_COREDUMP_NUM */ + if (data->cd_info.cnt >= MTK_COREDUMP_NUM && + skb->len > MTK_COREDUMP_END_LEN) + if (!memcmp((char *)&skb->data[skb->len - MTK_COREDUMP_END_LEN], + MTK_COREDUMP_END, MTK_COREDUMP_END_LEN - 1)) + complete = true; + err = hci_devcd_append(hdev, skb); if (err < 0) break; data->cd_info.cnt++; - /* Mediatek coredump data would be more than MTK_COREDUMP_NUM */ - if (data->cd_info.cnt > MTK_COREDUMP_NUM && - skb->len > MTK_COREDUMP_END_LEN) - if (!memcmp((char *)&skb->data[skb->len - MTK_COREDUMP_END_LEN], - MTK_COREDUMP_END, MTK_COREDUMP_END_LEN - 1)) { - bt_dev_info(hdev, "Mediatek coredump end"); - hci_devcd_complete(hdev); - } + if (complete) { + bt_dev_info(hdev, "Mediatek coredump end"); + hci_devcd_complete(hdev); + } break; } diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index 11755cb1eb16..0c85c981a833 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -870,6 +870,7 @@ struct btusb_data { int (*suspend)(struct hci_dev *hdev); int (*resume)(struct hci_dev *hdev); + int (*disconnect)(struct hci_dev *hdev); int oob_wake_irq; /* irq for out-of-band wake-on-bt */ unsigned cmd_timeout_cnt; @@ -2643,11 +2644,11 @@ static void btusb_mtk_claim_iso_intf(struct btusb_data *data) init_usb_anchor(&btmtk_data->isopkt_anchor); } -static void btusb_mtk_release_iso_intf(struct btusb_data *data) +static void btusb_mtk_release_iso_intf(struct hci_dev *hdev) { - struct btmtk_data *btmtk_data = hci_get_priv(data->hdev); + struct btmtk_data *btmtk_data = hci_get_priv(hdev); - if (btmtk_data->isopkt_intf) { + if (test_bit(BTMTK_ISOPKT_OVER_INTR, &btmtk_data->flags)) { usb_kill_anchored_urbs(&btmtk_data->isopkt_anchor); clear_bit(BTMTK_ISOPKT_RUNNING, &btmtk_data->flags); @@ -2661,6 +2662,16 @@ static void btusb_mtk_release_iso_intf(struct btusb_data *data) clear_bit(BTMTK_ISOPKT_OVER_INTR, &btmtk_data->flags); } +static int btusb_mtk_disconnect(struct hci_dev *hdev) +{ + /* This function describes the specific additional steps taken by MediaTek + * when Bluetooth usb driver's resume function is called. + */ + btusb_mtk_release_iso_intf(hdev); + + return 0; +} + static int btusb_mtk_reset(struct hci_dev *hdev, void *rst_data) { struct btusb_data *data = hci_get_drvdata(hdev); @@ -2677,8 +2688,8 @@ static int btusb_mtk_reset(struct hci_dev *hdev, void *rst_data) if (err < 0) return err; - if (test_bit(BTMTK_ISOPKT_RUNNING, &btmtk_data->flags)) - btusb_mtk_release_iso_intf(data); + /* Release MediaTek ISO data interface */ + btusb_mtk_release_iso_intf(hdev); btusb_stop_traffic(data); usb_kill_anchored_urbs(&data->tx_anchor); @@ -2723,22 +2734,24 @@ static int btusb_mtk_setup(struct hci_dev *hdev) btmtk_data->reset_sync = btusb_mtk_reset; /* Claim ISO data interface and endpoint */ - btmtk_data->isopkt_intf = usb_ifnum_to_if(data->udev, MTK_ISO_IFNUM); - if (btmtk_data->isopkt_intf) + if (!test_bit(BTMTK_ISOPKT_OVER_INTR, &btmtk_data->flags)) { + btmtk_data->isopkt_intf = usb_ifnum_to_if(data->udev, MTK_ISO_IFNUM); btusb_mtk_claim_iso_intf(data); + } return btmtk_usb_setup(hdev); } static int btusb_mtk_shutdown(struct hci_dev *hdev) { - struct btusb_data *data = hci_get_drvdata(hdev); - struct btmtk_data *btmtk_data = hci_get_priv(hdev); + int ret; - if (test_bit(BTMTK_ISOPKT_RUNNING, &btmtk_data->flags)) - btusb_mtk_release_iso_intf(data); + ret = btmtk_usb_shutdown(hdev); - return btmtk_usb_shutdown(hdev); + /* Release MediaTek iso interface after shutdown */ + btusb_mtk_release_iso_intf(hdev); + + return ret; } #ifdef CONFIG_PM @@ -3850,6 +3863,7 @@ static int btusb_probe(struct usb_interface *intf, data->recv_acl = btmtk_usb_recv_acl; data->suspend = btmtk_usb_suspend; data->resume = btmtk_usb_resume; + data->disconnect = btusb_mtk_disconnect; } if (id->driver_info & BTUSB_SWAVE) { @@ -4040,6 +4054,9 @@ static void btusb_disconnect(struct usb_interface *intf) if (data->diag) usb_set_intfdata(data->diag, NULL); + if (data->disconnect) + data->disconnect(hdev); + hci_unregister_dev(hdev); if (intf == data->intf) { diff --git a/drivers/clk/clk-en7523.c b/drivers/clk/clk-en7523.c index bc21b2921449..62a62eaba2aa 100644 --- a/drivers/clk/clk-en7523.c +++ b/drivers/clk/clk-en7523.c @@ -92,6 +92,7 @@ static const u32 slic_base[] = { 100000000, 3125000 }; static const u32 npu_base[] = { 333000000, 400000000, 500000000 }; /* EN7581 */ static const u32 emi7581_base[] = { 540000000, 480000000, 400000000, 300000000 }; +static const u32 bus7581_base[] = { 600000000, 540000000 }; static const u32 npu7581_base[] = { 800000000, 750000000, 720000000, 600000000 }; static const u32 crypto_base[] = { 540000000, 480000000 }; @@ -227,8 +228,8 @@ static const struct en_clk_desc en7581_base_clks[] = { .base_reg = REG_BUS_CLK_DIV_SEL, .base_bits = 1, .base_shift = 8, - .base_values = bus_base, - .n_base_values = ARRAY_SIZE(bus_base), + .base_values = bus7581_base, + .n_base_values = ARRAY_SIZE(bus7581_base), .div_bits = 3, .div_shift = 0, diff --git a/drivers/clk/imx/clk-imx8mp-audiomix.c b/drivers/clk/imx/clk-imx8mp-audiomix.c index b2cb157703c5..c409fc7e0618 100644 --- a/drivers/clk/imx/clk-imx8mp-audiomix.c +++ b/drivers/clk/imx/clk-imx8mp-audiomix.c @@ -278,7 +278,8 @@ static int clk_imx8mp_audiomix_reset_controller_register(struct device *dev, #else /* !CONFIG_RESET_CONTROLLER */ -static int clk_imx8mp_audiomix_reset_controller_register(struct clk_imx8mp_audiomix_priv *priv) +static int clk_imx8mp_audiomix_reset_controller_register(struct device *dev, + struct clk_imx8mp_audiomix_priv *priv) { return 0; } diff --git a/drivers/clk/thead/clk-th1520-ap.c b/drivers/clk/thead/clk-th1520-ap.c index 17e32ae08720..1015fab95251 100644 --- a/drivers/clk/thead/clk-th1520-ap.c +++ b/drivers/clk/thead/clk-th1520-ap.c @@ -779,6 +779,13 @@ static struct ccu_div dpu1_clk = { }, }; +static CLK_FIXED_FACTOR_HW(emmc_sdio_ref_clk, "emmc-sdio-ref", + &video_pll_clk.common.hw, 4, 1, 0); + +static const struct clk_parent_data emmc_sdio_ref_clk_pd[] = { + { .hw = &emmc_sdio_ref_clk.hw }, +}; + static CCU_GATE(CLK_BROM, brom_clk, "brom", ahb2_cpusys_hclk_pd, 0x100, BIT(4), 0); static CCU_GATE(CLK_BMU, bmu_clk, "bmu", axi4_cpusys2_aclk_pd, 0x100, BIT(5), 0); static CCU_GATE(CLK_AON2CPU_A2X, aon2cpu_a2x_clk, "aon2cpu-a2x", axi4_cpusys2_aclk_pd, @@ -798,7 +805,7 @@ static CCU_GATE(CLK_PERISYS_APB4_HCLK, perisys_apb4_hclk, "perisys-apb4-hclk", p 0x150, BIT(12), 0); static CCU_GATE(CLK_NPU_AXI, npu_axi_clk, "npu-axi", axi_aclk_pd, 0x1c8, BIT(5), 0); static CCU_GATE(CLK_CPU2VP, cpu2vp_clk, "cpu2vp", axi_aclk_pd, 0x1e0, BIT(13), 0); -static CCU_GATE(CLK_EMMC_SDIO, emmc_sdio_clk, "emmc-sdio", video_pll_clk_pd, 0x204, BIT(30), 0); +static CCU_GATE(CLK_EMMC_SDIO, emmc_sdio_clk, "emmc-sdio", emmc_sdio_ref_clk_pd, 0x204, BIT(30), 0); static CCU_GATE(CLK_GMAC1, gmac1_clk, "gmac1", gmac_pll_clk_pd, 0x204, BIT(26), 0); static CCU_GATE(CLK_PADCTRL1, padctrl1_clk, "padctrl1", perisys_apb_pclk_pd, 0x204, BIT(24), 0); static CCU_GATE(CLK_DSMART, dsmart_clk, "dsmart", perisys_apb_pclk_pd, 0x204, BIT(23), 0); @@ -1059,6 +1066,10 @@ static int th1520_clk_probe(struct platform_device *pdev) return ret; priv->hws[CLK_PLL_GMAC_100M] = &gmac_pll_clk_100m.hw; + ret = devm_clk_hw_register(dev, &emmc_sdio_ref_clk.hw); + if (ret) + return ret; + ret = devm_of_clk_add_hw_provider(dev, of_clk_hw_onecell_get, priv); if (ret) return ret; diff --git a/drivers/clocksource/hyperv_timer.c b/drivers/clocksource/hyperv_timer.c index 99177835cade..b39dee7b93af 100644 --- a/drivers/clocksource/hyperv_timer.c +++ b/drivers/clocksource/hyperv_timer.c @@ -27,7 +27,8 @@ #include <asm/mshyperv.h> static struct clock_event_device __percpu *hv_clock_event; -static u64 hv_sched_clock_offset __ro_after_init; +/* Note: offset can hold negative values after hibernation. */ +static u64 hv_sched_clock_offset __read_mostly; /* * If false, we're using the old mechanism for stimer0 interrupts @@ -470,6 +471,17 @@ static void resume_hv_clock_tsc(struct clocksource *arg) hv_set_msr(HV_MSR_REFERENCE_TSC, tsc_msr.as_uint64); } +/* + * Called during resume from hibernation, from overridden + * x86_platform.restore_sched_clock_state routine. This is to adjust offsets + * used to calculate time for hv tsc page based sched_clock, to account for + * time spent before hibernation. + */ +void hv_adj_sched_clock_offset(u64 offset) +{ + hv_sched_clock_offset -= offset; +} + #ifdef HAVE_VDSO_CLOCKMODE_HVCLOCK static int hv_cs_enable(struct clocksource *cs) { diff --git a/drivers/crypto/hisilicon/debugfs.c b/drivers/crypto/hisilicon/debugfs.c index 1b9b7bccdeff..45e130b901eb 100644 --- a/drivers/crypto/hisilicon/debugfs.c +++ b/drivers/crypto/hisilicon/debugfs.c @@ -192,7 +192,7 @@ static int qm_sqc_dump(struct hisi_qm *qm, char *s, char *name) down_read(&qm->qps_lock); if (qm->sqc) { - memcpy(&sqc, qm->sqc + qp_id * sizeof(struct qm_sqc), sizeof(struct qm_sqc)); + memcpy(&sqc, qm->sqc + qp_id, sizeof(struct qm_sqc)); sqc.base_h = cpu_to_le32(QM_XQC_ADDR_MASK); sqc.base_l = cpu_to_le32(QM_XQC_ADDR_MASK); dump_show(qm, &sqc, sizeof(struct qm_sqc), "SOFT SQC"); @@ -229,7 +229,7 @@ static int qm_cqc_dump(struct hisi_qm *qm, char *s, char *name) down_read(&qm->qps_lock); if (qm->cqc) { - memcpy(&cqc, qm->cqc + qp_id * sizeof(struct qm_cqc), sizeof(struct qm_cqc)); + memcpy(&cqc, qm->cqc + qp_id, sizeof(struct qm_cqc)); cqc.base_h = cpu_to_le32(QM_XQC_ADDR_MASK); cqc.base_l = cpu_to_le32(QM_XQC_ADDR_MASK); dump_show(qm, &cqc, sizeof(struct qm_cqc), "SOFT CQC"); diff --git a/drivers/cxl/core/region.c b/drivers/cxl/core/region.c index dff618c708dc..a0d6e8d7f42c 100644 --- a/drivers/cxl/core/region.c +++ b/drivers/cxl/core/region.c @@ -1295,6 +1295,7 @@ static int cxl_port_setup_targets(struct cxl_port *port, struct cxl_region_params *p = &cxlr->params; struct cxl_decoder *cxld = cxl_rr->decoder; struct cxl_switch_decoder *cxlsd; + struct cxl_port *iter = port; u16 eig, peig; u8 eiw, peiw; @@ -1311,16 +1312,26 @@ static int cxl_port_setup_targets(struct cxl_port *port, cxlsd = to_cxl_switch_decoder(&cxld->dev); if (cxl_rr->nr_targets_set) { - int i, distance; + int i, distance = 1; + struct cxl_region_ref *cxl_rr_iter; /* - * Passthrough decoders impose no distance requirements between - * peers + * The "distance" between peer downstream ports represents which + * endpoint positions in the region interleave a given port can + * host. + * + * For example, at the root of a hierarchy the distance is + * always 1 as every index targets a different host-bridge. At + * each subsequent switch level those ports map every Nth region + * position where N is the width of the switch == distance. */ - if (cxl_rr->nr_targets == 1) - distance = 0; - else - distance = p->nr_targets / cxl_rr->nr_targets; + do { + cxl_rr_iter = cxl_rr_load(iter, cxlr); + distance *= cxl_rr_iter->nr_targets; + iter = to_cxl_port(iter->dev.parent); + } while (!is_cxl_root(iter)); + distance *= cxlrd->cxlsd.cxld.interleave_ways; + for (i = 0; i < cxl_rr->nr_targets_set; i++) if (ep->dport == cxlsd->target[i]) { rc = check_last_peer(cxled, ep, cxl_rr, diff --git a/drivers/cxl/pci.c b/drivers/cxl/pci.c index 188412d45e0d..6e553b5752b1 100644 --- a/drivers/cxl/pci.c +++ b/drivers/cxl/pci.c @@ -942,8 +942,7 @@ static int cxl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) if (rc) return rc; - rc = cxl_pci_ras_unmask(pdev); - if (rc) + if (cxl_pci_ras_unmask(pdev)) dev_dbg(&pdev->dev, "No RAS reporting unmasked\n"); pci_save_state(pdev); diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c index 8892bc701a66..afb8c1c50107 100644 --- a/drivers/dma-buf/dma-buf.c +++ b/drivers/dma-buf/dma-buf.c @@ -60,7 +60,7 @@ static void __dma_buf_debugfs_list_add(struct dma_buf *dmabuf) { } -static void __dma_buf_debugfs_list_del(struct file *file) +static void __dma_buf_debugfs_list_del(struct dma_buf *dmabuf) { } #endif diff --git a/drivers/dma-buf/udmabuf.c b/drivers/dma-buf/udmabuf.c index a3638ccc15f5..5e836e4e5b44 100644 --- a/drivers/dma-buf/udmabuf.c +++ b/drivers/dma-buf/udmabuf.c @@ -256,15 +256,12 @@ static const struct dma_buf_ops udmabuf_ops = { }; #define SEALS_WANTED (F_SEAL_SHRINK) -#define SEALS_DENIED (F_SEAL_WRITE) +#define SEALS_DENIED (F_SEAL_WRITE|F_SEAL_FUTURE_WRITE) static int check_memfd_seals(struct file *memfd) { int seals; - if (!memfd) - return -EBADFD; - if (!shmem_file(memfd) && !is_file_hugepages(memfd)) return -EBADFD; @@ -279,12 +276,10 @@ static int check_memfd_seals(struct file *memfd) return 0; } -static int export_udmabuf(struct udmabuf *ubuf, - struct miscdevice *device, - u32 flags) +static struct dma_buf *export_udmabuf(struct udmabuf *ubuf, + struct miscdevice *device) { DEFINE_DMA_BUF_EXPORT_INFO(exp_info); - struct dma_buf *buf; ubuf->device = device; exp_info.ops = &udmabuf_ops; @@ -292,24 +287,72 @@ static int export_udmabuf(struct udmabuf *ubuf, exp_info.priv = ubuf; exp_info.flags = O_RDWR; - buf = dma_buf_export(&exp_info); - if (IS_ERR(buf)) - return PTR_ERR(buf); + return dma_buf_export(&exp_info); +} + +static long udmabuf_pin_folios(struct udmabuf *ubuf, struct file *memfd, + loff_t start, loff_t size) +{ + pgoff_t pgoff, pgcnt, upgcnt = ubuf->pagecount; + struct folio **folios = NULL; + u32 cur_folio, cur_pgcnt; + long nr_folios; + long ret = 0; + loff_t end; + + pgcnt = size >> PAGE_SHIFT; + folios = kvmalloc_array(pgcnt, sizeof(*folios), GFP_KERNEL); + if (!folios) + return -ENOMEM; + + end = start + (pgcnt << PAGE_SHIFT) - 1; + nr_folios = memfd_pin_folios(memfd, start, end, folios, pgcnt, &pgoff); + if (nr_folios <= 0) { + ret = nr_folios ? nr_folios : -EINVAL; + goto end; + } - return dma_buf_fd(buf, flags); + cur_pgcnt = 0; + for (cur_folio = 0; cur_folio < nr_folios; ++cur_folio) { + pgoff_t subpgoff = pgoff; + size_t fsize = folio_size(folios[cur_folio]); + + ret = add_to_unpin_list(&ubuf->unpin_list, folios[cur_folio]); + if (ret < 0) + goto end; + + for (; subpgoff < fsize; subpgoff += PAGE_SIZE) { + ubuf->folios[upgcnt] = folios[cur_folio]; + ubuf->offsets[upgcnt] = subpgoff; + ++upgcnt; + + if (++cur_pgcnt >= pgcnt) + goto end; + } + + /** + * In a given range, only the first subpage of the first folio + * has an offset, that is returned by memfd_pin_folios(). + * The first subpages of other folios (in the range) have an + * offset of 0. + */ + pgoff = 0; + } +end: + ubuf->pagecount = upgcnt; + kvfree(folios); + return ret; } static long udmabuf_create(struct miscdevice *device, struct udmabuf_create_list *head, struct udmabuf_create_item *list) { - pgoff_t pgoff, pgcnt, pglimit, pgbuf = 0; - long nr_folios, ret = -EINVAL; - struct file *memfd = NULL; - struct folio **folios; + pgoff_t pgcnt = 0, pglimit; struct udmabuf *ubuf; - u32 i, j, k, flags; - loff_t end; + struct dma_buf *dmabuf; + long ret = -EINVAL; + u32 i, flags; ubuf = kzalloc(sizeof(*ubuf), GFP_KERNEL); if (!ubuf) @@ -318,93 +361,76 @@ static long udmabuf_create(struct miscdevice *device, INIT_LIST_HEAD(&ubuf->unpin_list); pglimit = (size_limit_mb * 1024 * 1024) >> PAGE_SHIFT; for (i = 0; i < head->count; i++) { - if (!IS_ALIGNED(list[i].offset, PAGE_SIZE)) + if (!PAGE_ALIGNED(list[i].offset)) goto err; - if (!IS_ALIGNED(list[i].size, PAGE_SIZE)) + if (!PAGE_ALIGNED(list[i].size)) goto err; - ubuf->pagecount += list[i].size >> PAGE_SHIFT; - if (ubuf->pagecount > pglimit) + + pgcnt += list[i].size >> PAGE_SHIFT; + if (pgcnt > pglimit) goto err; } - if (!ubuf->pagecount) + if (!pgcnt) goto err; - ubuf->folios = kvmalloc_array(ubuf->pagecount, sizeof(*ubuf->folios), - GFP_KERNEL); + ubuf->folios = kvmalloc_array(pgcnt, sizeof(*ubuf->folios), GFP_KERNEL); if (!ubuf->folios) { ret = -ENOMEM; goto err; } - ubuf->offsets = kvcalloc(ubuf->pagecount, sizeof(*ubuf->offsets), - GFP_KERNEL); + + ubuf->offsets = kvcalloc(pgcnt, sizeof(*ubuf->offsets), GFP_KERNEL); if (!ubuf->offsets) { ret = -ENOMEM; goto err; } - pgbuf = 0; for (i = 0; i < head->count; i++) { - memfd = fget(list[i].memfd); - ret = check_memfd_seals(memfd); - if (ret < 0) - goto err; - - pgcnt = list[i].size >> PAGE_SHIFT; - folios = kvmalloc_array(pgcnt, sizeof(*folios), GFP_KERNEL); - if (!folios) { - ret = -ENOMEM; - goto err; - } + struct file *memfd = fget(list[i].memfd); - end = list[i].offset + (pgcnt << PAGE_SHIFT) - 1; - ret = memfd_pin_folios(memfd, list[i].offset, end, - folios, pgcnt, &pgoff); - if (ret <= 0) { - kvfree(folios); - if (!ret) - ret = -EINVAL; + if (!memfd) { + ret = -EBADFD; goto err; } - nr_folios = ret; - pgoff >>= PAGE_SHIFT; - for (j = 0, k = 0; j < pgcnt; j++) { - ubuf->folios[pgbuf] = folios[k]; - ubuf->offsets[pgbuf] = pgoff << PAGE_SHIFT; - - if (j == 0 || ubuf->folios[pgbuf-1] != folios[k]) { - ret = add_to_unpin_list(&ubuf->unpin_list, - folios[k]); - if (ret < 0) { - kfree(folios); - goto err; - } - } - - pgbuf++; - if (++pgoff == folio_nr_pages(folios[k])) { - pgoff = 0; - if (++k == nr_folios) - break; - } - } + /* + * Take the inode lock to protect against concurrent + * memfd_add_seals(), which takes this lock in write mode. + */ + inode_lock_shared(file_inode(memfd)); + ret = check_memfd_seals(memfd); + if (ret) + goto out_unlock; - kvfree(folios); + ret = udmabuf_pin_folios(ubuf, memfd, list[i].offset, + list[i].size); +out_unlock: + inode_unlock_shared(file_inode(memfd)); fput(memfd); - memfd = NULL; + if (ret) + goto err; } flags = head->flags & UDMABUF_FLAGS_CLOEXEC ? O_CLOEXEC : 0; - ret = export_udmabuf(ubuf, device, flags); - if (ret < 0) + dmabuf = export_udmabuf(ubuf, device); + if (IS_ERR(dmabuf)) { + ret = PTR_ERR(dmabuf); goto err; + } + /* + * Ownership of ubuf is held by the dmabuf from here. + * If the following dma_buf_fd() fails, dma_buf_put() cleans up both the + * dmabuf and the ubuf (through udmabuf_ops.release). + */ + + ret = dma_buf_fd(dmabuf, flags); + if (ret < 0) + dma_buf_put(dmabuf); return ret; err: - if (memfd) - fput(memfd); unpin_all_folios(&ubuf->unpin_list); kvfree(ubuf->offsets); kvfree(ubuf->folios); diff --git a/drivers/dma/amd/qdma/qdma.c b/drivers/dma/amd/qdma/qdma.c index b0a1f3ad851b..4761fa255015 100644 --- a/drivers/dma/amd/qdma/qdma.c +++ b/drivers/dma/amd/qdma/qdma.c @@ -7,9 +7,9 @@ #include <linux/bitfield.h> #include <linux/bitops.h> #include <linux/dmaengine.h> +#include <linux/dma-mapping.h> #include <linux/module.h> #include <linux/mod_devicetable.h> -#include <linux/dma-map-ops.h> #include <linux/platform_device.h> #include <linux/platform_data/amd_qdma.h> #include <linux/regmap.h> @@ -492,18 +492,9 @@ static int qdma_device_verify(struct qdma_device *qdev) static int qdma_device_setup(struct qdma_device *qdev) { - struct device *dev = &qdev->pdev->dev; u32 ring_sz = QDMA_DEFAULT_RING_SIZE; int ret = 0; - while (dev && get_dma_ops(dev)) - dev = dev->parent; - if (!dev) { - qdma_err(qdev, "dma device not found"); - return -EINVAL; - } - set_dma_ops(&qdev->pdev->dev, get_dma_ops(dev)); - ret = qdma_setup_fmap_context(qdev); if (ret) { qdma_err(qdev, "Failed setup fmap context"); @@ -548,11 +539,12 @@ static void qdma_free_queue_resources(struct dma_chan *chan) { struct qdma_queue *queue = to_qdma_queue(chan); struct qdma_device *qdev = queue->qdev; - struct device *dev = qdev->dma_dev.dev; + struct qdma_platdata *pdata; qdma_clear_queue_context(queue); vchan_free_chan_resources(&queue->vchan); - dma_free_coherent(dev, queue->ring_size * QDMA_MM_DESC_SIZE, + pdata = dev_get_platdata(&qdev->pdev->dev); + dma_free_coherent(pdata->dma_dev, queue->ring_size * QDMA_MM_DESC_SIZE, queue->desc_base, queue->dma_desc_base); } @@ -565,6 +557,7 @@ static int qdma_alloc_queue_resources(struct dma_chan *chan) struct qdma_queue *queue = to_qdma_queue(chan); struct qdma_device *qdev = queue->qdev; struct qdma_ctxt_sw_desc desc; + struct qdma_platdata *pdata; size_t size; int ret; @@ -572,8 +565,9 @@ static int qdma_alloc_queue_resources(struct dma_chan *chan) if (ret) return ret; + pdata = dev_get_platdata(&qdev->pdev->dev); size = queue->ring_size * QDMA_MM_DESC_SIZE; - queue->desc_base = dma_alloc_coherent(qdev->dma_dev.dev, size, + queue->desc_base = dma_alloc_coherent(pdata->dma_dev, size, &queue->dma_desc_base, GFP_KERNEL); if (!queue->desc_base) { @@ -588,7 +582,7 @@ static int qdma_alloc_queue_resources(struct dma_chan *chan) if (ret) { qdma_err(qdev, "Failed to setup SW desc ctxt for %s", chan->name); - dma_free_coherent(qdev->dma_dev.dev, size, queue->desc_base, + dma_free_coherent(pdata->dma_dev, size, queue->desc_base, queue->dma_desc_base); return ret; } @@ -948,8 +942,9 @@ static int qdma_init_error_irq(struct qdma_device *qdev) static int qdmam_alloc_qintr_rings(struct qdma_device *qdev) { - u32 ctxt[QDMA_CTXT_REGMAP_LEN]; + struct qdma_platdata *pdata = dev_get_platdata(&qdev->pdev->dev); struct device *dev = &qdev->pdev->dev; + u32 ctxt[QDMA_CTXT_REGMAP_LEN]; struct qdma_intr_ring *ring; struct qdma_ctxt_intr intr_ctxt; u32 vector; @@ -969,7 +964,8 @@ static int qdmam_alloc_qintr_rings(struct qdma_device *qdev) ring->msix_id = qdev->err_irq_idx + i + 1; ring->ridx = i; ring->color = 1; - ring->base = dmam_alloc_coherent(dev, QDMA_INTR_RING_SIZE, + ring->base = dmam_alloc_coherent(pdata->dma_dev, + QDMA_INTR_RING_SIZE, &ring->dev_base, GFP_KERNEL); if (!ring->base) { qdma_err(qdev, "Failed to alloc intr ring %d", i); diff --git a/drivers/dma/apple-admac.c b/drivers/dma/apple-admac.c index 9588773dd2eb..037ec38730cf 100644 --- a/drivers/dma/apple-admac.c +++ b/drivers/dma/apple-admac.c @@ -153,6 +153,8 @@ static int admac_alloc_sram_carveout(struct admac_data *ad, { struct admac_sram *sram; int i, ret = 0, nblocks; + ad->txcache.size = readl_relaxed(ad->base + REG_TX_SRAM_SIZE); + ad->rxcache.size = readl_relaxed(ad->base + REG_RX_SRAM_SIZE); if (dir == DMA_MEM_TO_DEV) sram = &ad->txcache; @@ -912,12 +914,7 @@ static int admac_probe(struct platform_device *pdev) goto free_irq; } - ad->txcache.size = readl_relaxed(ad->base + REG_TX_SRAM_SIZE); - ad->rxcache.size = readl_relaxed(ad->base + REG_RX_SRAM_SIZE); - dev_info(&pdev->dev, "Audio DMA Controller\n"); - dev_info(&pdev->dev, "imprint %x TX cache %u RX cache %u\n", - readl_relaxed(ad->base + REG_IMPRINT), ad->txcache.size, ad->rxcache.size); return 0; diff --git a/drivers/dma/at_xdmac.c b/drivers/dma/at_xdmac.c index 299396121e6d..e847ad66dc0b 100644 --- a/drivers/dma/at_xdmac.c +++ b/drivers/dma/at_xdmac.c @@ -1363,6 +1363,8 @@ at_xdmac_prep_dma_memset(struct dma_chan *chan, dma_addr_t dest, int value, return NULL; desc = at_xdmac_memset_create_desc(chan, atchan, dest, len, value); + if (!desc) + return NULL; list_add_tail(&desc->desc_node, &desc->descs_list); desc->tx_dma_desc.cookie = -EBUSY; diff --git a/drivers/dma/dw/acpi.c b/drivers/dma/dw/acpi.c index c510c109d2c3..b6452fffa657 100644 --- a/drivers/dma/dw/acpi.c +++ b/drivers/dma/dw/acpi.c @@ -8,13 +8,15 @@ static bool dw_dma_acpi_filter(struct dma_chan *chan, void *param) { + struct dw_dma *dw = to_dw_dma(chan->device); + struct dw_dma_chip_pdata *data = dev_get_drvdata(dw->dma.dev); struct acpi_dma_spec *dma_spec = param; struct dw_dma_slave slave = { .dma_dev = dma_spec->dev, .src_id = dma_spec->slave_id, .dst_id = dma_spec->slave_id, - .m_master = 0, - .p_master = 1, + .m_master = data->m_master, + .p_master = data->p_master, }; return dw_dma_filter(chan, &slave); diff --git a/drivers/dma/dw/internal.h b/drivers/dma/dw/internal.h index 563ce73488db..f1bd06a20cd6 100644 --- a/drivers/dma/dw/internal.h +++ b/drivers/dma/dw/internal.h @@ -51,11 +51,15 @@ struct dw_dma_chip_pdata { int (*probe)(struct dw_dma_chip *chip); int (*remove)(struct dw_dma_chip *chip); struct dw_dma_chip *chip; + u8 m_master; + u8 p_master; }; static __maybe_unused const struct dw_dma_chip_pdata dw_dma_chip_pdata = { .probe = dw_dma_probe, .remove = dw_dma_remove, + .m_master = 0, + .p_master = 1, }; static const struct dw_dma_platform_data idma32_pdata = { @@ -72,6 +76,8 @@ static __maybe_unused const struct dw_dma_chip_pdata idma32_chip_pdata = { .pdata = &idma32_pdata, .probe = idma32_dma_probe, .remove = idma32_dma_remove, + .m_master = 0, + .p_master = 0, }; static const struct dw_dma_platform_data xbar_pdata = { @@ -88,6 +94,8 @@ static __maybe_unused const struct dw_dma_chip_pdata xbar_chip_pdata = { .pdata = &xbar_pdata, .probe = idma32_dma_probe, .remove = idma32_dma_remove, + .m_master = 0, + .p_master = 0, }; #endif /* _DMA_DW_INTERNAL_H */ diff --git a/drivers/dma/dw/pci.c b/drivers/dma/dw/pci.c index ad2d4d012cf7..e8a0eb81726a 100644 --- a/drivers/dma/dw/pci.c +++ b/drivers/dma/dw/pci.c @@ -56,10 +56,10 @@ static int dw_pci_probe(struct pci_dev *pdev, const struct pci_device_id *pid) if (ret) return ret; - dw_dma_acpi_controller_register(chip->dw); - pci_set_drvdata(pdev, data); + dw_dma_acpi_controller_register(chip->dw); + return 0; } diff --git a/drivers/dma/fsl-edma-common.h b/drivers/dma/fsl-edma-common.h index ce37e1ee9c46..fe8f103d4a63 100644 --- a/drivers/dma/fsl-edma-common.h +++ b/drivers/dma/fsl-edma-common.h @@ -166,6 +166,7 @@ struct fsl_edma_chan { struct work_struct issue_worker; struct platform_device *pdev; struct device *pd_dev; + struct device_link *pd_dev_link; u32 srcid; struct clk *clk; int priority; diff --git a/drivers/dma/fsl-edma-main.c b/drivers/dma/fsl-edma-main.c index f9f1eda79254..70cb7fda757a 100644 --- a/drivers/dma/fsl-edma-main.c +++ b/drivers/dma/fsl-edma-main.c @@ -417,10 +417,33 @@ static const struct of_device_id fsl_edma_dt_ids[] = { }; MODULE_DEVICE_TABLE(of, fsl_edma_dt_ids); +static void fsl_edma3_detach_pd(struct fsl_edma_engine *fsl_edma) +{ + struct fsl_edma_chan *fsl_chan; + int i; + + for (i = 0; i < fsl_edma->n_chans; i++) { + if (fsl_edma->chan_masked & BIT(i)) + continue; + fsl_chan = &fsl_edma->chans[i]; + if (fsl_chan->pd_dev_link) + device_link_del(fsl_chan->pd_dev_link); + if (fsl_chan->pd_dev) { + dev_pm_domain_detach(fsl_chan->pd_dev, false); + pm_runtime_dont_use_autosuspend(fsl_chan->pd_dev); + pm_runtime_set_suspended(fsl_chan->pd_dev); + } + } +} + +static void devm_fsl_edma3_detach_pd(void *data) +{ + fsl_edma3_detach_pd(data); +} + static int fsl_edma3_attach_pd(struct platform_device *pdev, struct fsl_edma_engine *fsl_edma) { struct fsl_edma_chan *fsl_chan; - struct device_link *link; struct device *pd_chan; struct device *dev; int i; @@ -436,15 +459,16 @@ static int fsl_edma3_attach_pd(struct platform_device *pdev, struct fsl_edma_eng pd_chan = dev_pm_domain_attach_by_id(dev, i); if (IS_ERR_OR_NULL(pd_chan)) { dev_err(dev, "Failed attach pd %d\n", i); - return -EINVAL; + goto detach; } - link = device_link_add(dev, pd_chan, DL_FLAG_STATELESS | + fsl_chan->pd_dev_link = device_link_add(dev, pd_chan, DL_FLAG_STATELESS | DL_FLAG_PM_RUNTIME | DL_FLAG_RPM_ACTIVE); - if (!link) { + if (!fsl_chan->pd_dev_link) { dev_err(dev, "Failed to add device_link to %d\n", i); - return -EINVAL; + dev_pm_domain_detach(pd_chan, false); + goto detach; } fsl_chan->pd_dev = pd_chan; @@ -455,6 +479,10 @@ static int fsl_edma3_attach_pd(struct platform_device *pdev, struct fsl_edma_eng } return 0; + +detach: + fsl_edma3_detach_pd(fsl_edma); + return -EINVAL; } static int fsl_edma_probe(struct platform_device *pdev) @@ -544,6 +572,9 @@ static int fsl_edma_probe(struct platform_device *pdev) ret = fsl_edma3_attach_pd(pdev, fsl_edma); if (ret) return ret; + ret = devm_add_action_or_reset(&pdev->dev, devm_fsl_edma3_detach_pd, fsl_edma); + if (ret) + return ret; } if (drvdata->flags & FSL_EDMA_DRV_TCD64) diff --git a/drivers/dma/ls2x-apb-dma.c b/drivers/dma/ls2x-apb-dma.c index 9652e8666722..b4f18be62945 100644 --- a/drivers/dma/ls2x-apb-dma.c +++ b/drivers/dma/ls2x-apb-dma.c @@ -31,7 +31,7 @@ #define LDMA_ASK_VALID BIT(2) #define LDMA_START BIT(3) /* DMA start operation */ #define LDMA_STOP BIT(4) /* DMA stop operation */ -#define LDMA_CONFIG_MASK GENMASK(4, 0) /* DMA controller config bits mask */ +#define LDMA_CONFIG_MASK GENMASK_ULL(4, 0) /* DMA controller config bits mask */ /* Bitfields in ndesc_addr field of HW descriptor */ #define LDMA_DESC_EN BIT(0) /*1: The next descriptor is valid */ diff --git a/drivers/dma/mv_xor.c b/drivers/dma/mv_xor.c index 43efce77bb57..40b76b40bc30 100644 --- a/drivers/dma/mv_xor.c +++ b/drivers/dma/mv_xor.c @@ -1388,6 +1388,7 @@ static int mv_xor_probe(struct platform_device *pdev) irq = irq_of_parse_and_map(np, 0); if (!irq) { ret = -ENODEV; + of_node_put(np); goto err_channel_add; } @@ -1396,6 +1397,7 @@ static int mv_xor_probe(struct platform_device *pdev) if (IS_ERR(chan)) { ret = PTR_ERR(chan); irq_dispose_mapping(irq); + of_node_put(np); goto err_channel_add; } diff --git a/drivers/dma/tegra186-gpc-dma.c b/drivers/dma/tegra186-gpc-dma.c index 3642508e88bb..adca05ee98c9 100644 --- a/drivers/dma/tegra186-gpc-dma.c +++ b/drivers/dma/tegra186-gpc-dma.c @@ -231,6 +231,7 @@ struct tegra_dma_channel { bool config_init; char name[30]; enum dma_transfer_direction sid_dir; + enum dma_status status; int id; int irq; int slave_id; @@ -393,6 +394,8 @@ static int tegra_dma_pause(struct tegra_dma_channel *tdc) tegra_dma_dump_chan_regs(tdc); } + tdc->status = DMA_PAUSED; + return ret; } @@ -419,6 +422,8 @@ static void tegra_dma_resume(struct tegra_dma_channel *tdc) val = tdc_read(tdc, TEGRA_GPCDMA_CHAN_CSRE); val &= ~TEGRA_GPCDMA_CHAN_CSRE_PAUSE; tdc_write(tdc, TEGRA_GPCDMA_CHAN_CSRE, val); + + tdc->status = DMA_IN_PROGRESS; } static int tegra_dma_device_resume(struct dma_chan *dc) @@ -544,6 +549,7 @@ static void tegra_dma_xfer_complete(struct tegra_dma_channel *tdc) tegra_dma_sid_free(tdc); tdc->dma_desc = NULL; + tdc->status = DMA_COMPLETE; } static void tegra_dma_chan_decode_error(struct tegra_dma_channel *tdc, @@ -716,6 +722,7 @@ static int tegra_dma_terminate_all(struct dma_chan *dc) tdc->dma_desc = NULL; } + tdc->status = DMA_COMPLETE; tegra_dma_sid_free(tdc); vchan_get_all_descriptors(&tdc->vc, &head); spin_unlock_irqrestore(&tdc->vc.lock, flags); @@ -769,6 +776,9 @@ static enum dma_status tegra_dma_tx_status(struct dma_chan *dc, if (ret == DMA_COMPLETE) return ret; + if (tdc->status == DMA_PAUSED) + ret = DMA_PAUSED; + spin_lock_irqsave(&tdc->vc.lock, flags); vd = vchan_find_desc(&tdc->vc, cookie); if (vd) { diff --git a/drivers/edac/amd64_edac.c b/drivers/edac/amd64_edac.c index ddfbdb66b794..5d356b7c4589 100644 --- a/drivers/edac/amd64_edac.c +++ b/drivers/edac/amd64_edac.c @@ -3362,36 +3362,24 @@ static bool dct_ecc_enabled(struct amd64_pvt *pvt) static bool umc_ecc_enabled(struct amd64_pvt *pvt) { - u8 umc_en_mask = 0, ecc_en_mask = 0; - u16 nid = pvt->mc_node_id; struct amd64_umc *umc; - u8 ecc_en = 0, i; + bool ecc_en = false; + int i; + /* Check whether at least one UMC is enabled: */ for_each_umc(i) { umc = &pvt->umc[i]; - /* Only check enabled UMCs. */ - if (!(umc->sdp_ctrl & UMC_SDP_INIT)) - continue; - - umc_en_mask |= BIT(i); - - if (umc->umc_cap_hi & UMC_ECC_ENABLED) - ecc_en_mask |= BIT(i); + if (umc->sdp_ctrl & UMC_SDP_INIT && + umc->umc_cap_hi & UMC_ECC_ENABLED) { + ecc_en = true; + break; + } } - /* Check whether at least one UMC is enabled: */ - if (umc_en_mask) - ecc_en = umc_en_mask == ecc_en_mask; - else - edac_dbg(0, "Node %d: No enabled UMCs.\n", nid); - - edac_dbg(3, "Node %d: DRAM ECC %s.\n", nid, (ecc_en ? "enabled" : "disabled")); + edac_dbg(3, "Node %d: DRAM ECC %s.\n", pvt->mc_node_id, (ecc_en ? "enabled" : "disabled")); - if (!ecc_en) - return false; - else - return true; + return ecc_en; } static inline void diff --git a/drivers/firmware/arm_ffa/bus.c b/drivers/firmware/arm_ffa/bus.c index eb17d03b66fe..dfda5ffc14db 100644 --- a/drivers/firmware/arm_ffa/bus.c +++ b/drivers/firmware/arm_ffa/bus.c @@ -187,13 +187,18 @@ bool ffa_device_is_valid(struct ffa_device *ffa_dev) return valid; } -struct ffa_device *ffa_device_register(const uuid_t *uuid, int vm_id, - const struct ffa_ops *ops) +struct ffa_device * +ffa_device_register(const struct ffa_partition_info *part_info, + const struct ffa_ops *ops) { int id, ret; + uuid_t uuid; struct device *dev; struct ffa_device *ffa_dev; + if (!part_info) + return NULL; + id = ida_alloc_min(&ffa_bus_id, 1, GFP_KERNEL); if (id < 0) return NULL; @@ -210,9 +215,11 @@ struct ffa_device *ffa_device_register(const uuid_t *uuid, int vm_id, dev_set_name(&ffa_dev->dev, "arm-ffa-%d", id); ffa_dev->id = id; - ffa_dev->vm_id = vm_id; + ffa_dev->vm_id = part_info->id; + ffa_dev->properties = part_info->properties; ffa_dev->ops = ops; - uuid_copy(&ffa_dev->uuid, uuid); + import_uuid(&uuid, (u8 *)part_info->uuid); + uuid_copy(&ffa_dev->uuid, &uuid); ret = device_register(&ffa_dev->dev); if (ret) { diff --git a/drivers/firmware/arm_ffa/driver.c b/drivers/firmware/arm_ffa/driver.c index b14cbdae94e8..2c2ec3c35f15 100644 --- a/drivers/firmware/arm_ffa/driver.c +++ b/drivers/firmware/arm_ffa/driver.c @@ -1387,7 +1387,6 @@ static struct notifier_block ffa_bus_nb = { static int ffa_setup_partitions(void) { int count, idx, ret; - uuid_t uuid; struct ffa_device *ffa_dev; struct ffa_dev_part_info *info; struct ffa_partition_info *pbuf, *tpbuf; @@ -1406,23 +1405,19 @@ static int ffa_setup_partitions(void) xa_init(&drv_info->partition_info); for (idx = 0, tpbuf = pbuf; idx < count; idx++, tpbuf++) { - import_uuid(&uuid, (u8 *)tpbuf->uuid); - /* Note that if the UUID will be uuid_null, that will require * ffa_bus_notifier() to find the UUID of this partition id * with help of ffa_device_match_uuid(). FF-A v1.1 and above * provides UUID here for each partition as part of the * discovery API and the same is passed. */ - ffa_dev = ffa_device_register(&uuid, tpbuf->id, &ffa_drv_ops); + ffa_dev = ffa_device_register(tpbuf, &ffa_drv_ops); if (!ffa_dev) { pr_err("%s: failed to register partition ID 0x%x\n", __func__, tpbuf->id); continue; } - ffa_dev->properties = tpbuf->properties; - if (drv_info->version > FFA_VERSION_1_0 && !(tpbuf->properties & FFA_PARTITION_AARCH64_EXEC)) ffa_mode_32bit_set(ffa_dev); diff --git a/drivers/firmware/arm_scmi/vendors/imx/Kconfig b/drivers/firmware/arm_scmi/vendors/imx/Kconfig index 2883ed24a84d..a01bf5e47301 100644 --- a/drivers/firmware/arm_scmi/vendors/imx/Kconfig +++ b/drivers/firmware/arm_scmi/vendors/imx/Kconfig @@ -15,6 +15,7 @@ config IMX_SCMI_BBM_EXT config IMX_SCMI_MISC_EXT tristate "i.MX SCMI MISC EXTENSION" depends on ARM_SCMI_PROTOCOL || (COMPILE_TEST && OF) + depends on IMX_SCMI_MISC_DRV default y if ARCH_MXC help This enables i.MX System MISC control logic such as gpio expander diff --git a/drivers/firmware/imx/Kconfig b/drivers/firmware/imx/Kconfig index 477d3f32d99a..907cd149c40a 100644 --- a/drivers/firmware/imx/Kconfig +++ b/drivers/firmware/imx/Kconfig @@ -25,7 +25,6 @@ config IMX_SCU config IMX_SCMI_MISC_DRV tristate "IMX SCMI MISC Protocol driver" - depends on IMX_SCMI_MISC_EXT || COMPILE_TEST default y if ARCH_MXC help The System Controller Management Interface firmware (SCMI FW) is diff --git a/drivers/gpio/gpio-graniterapids.c b/drivers/gpio/gpio-graniterapids.c index f2e911a3d2ca..ad6a045fd3d2 100644 --- a/drivers/gpio/gpio-graniterapids.c +++ b/drivers/gpio/gpio-graniterapids.c @@ -32,12 +32,14 @@ #define GNR_PINS_PER_REG 32 #define GNR_NUM_REGS DIV_ROUND_UP(GNR_NUM_PINS, GNR_PINS_PER_REG) -#define GNR_CFG_BAR 0x00 +#define GNR_CFG_PADBAR 0x00 #define GNR_CFG_LOCK_OFFSET 0x04 -#define GNR_GPI_STATUS_OFFSET 0x20 +#define GNR_GPI_STATUS_OFFSET 0x14 #define GNR_GPI_ENABLE_OFFSET 0x24 -#define GNR_CFG_DW_RX_MASK GENMASK(25, 22) +#define GNR_CFG_DW_HOSTSW_MODE BIT(27) +#define GNR_CFG_DW_RX_MASK GENMASK(23, 22) +#define GNR_CFG_DW_INTSEL_MASK GENMASK(21, 14) #define GNR_CFG_DW_RX_DISABLE FIELD_PREP(GNR_CFG_DW_RX_MASK, 2) #define GNR_CFG_DW_RX_EDGE FIELD_PREP(GNR_CFG_DW_RX_MASK, 1) #define GNR_CFG_DW_RX_LEVEL FIELD_PREP(GNR_CFG_DW_RX_MASK, 0) @@ -50,6 +52,7 @@ * struct gnr_gpio - Intel Granite Rapids-D vGPIO driver state * @gc: GPIO controller interface * @reg_base: base address of the GPIO registers + * @pad_base: base address of the vGPIO pad configuration registers * @ro_bitmap: bitmap of read-only pins * @lock: guard the registers * @pad_backup: backup of the register state for suspend @@ -57,6 +60,7 @@ struct gnr_gpio { struct gpio_chip gc; void __iomem *reg_base; + void __iomem *pad_base; DECLARE_BITMAP(ro_bitmap, GNR_NUM_PINS); raw_spinlock_t lock; u32 pad_backup[]; @@ -65,7 +69,7 @@ struct gnr_gpio { static void __iomem *gnr_gpio_get_padcfg_addr(const struct gnr_gpio *priv, unsigned int gpio) { - return priv->reg_base + gpio * sizeof(u32); + return priv->pad_base + gpio * sizeof(u32); } static int gnr_gpio_configure_line(struct gpio_chip *gc, unsigned int gpio, @@ -88,6 +92,20 @@ static int gnr_gpio_configure_line(struct gpio_chip *gc, unsigned int gpio, return 0; } +static int gnr_gpio_request(struct gpio_chip *gc, unsigned int gpio) +{ + struct gnr_gpio *priv = gpiochip_get_data(gc); + u32 dw; + + dw = readl(gnr_gpio_get_padcfg_addr(priv, gpio)); + if (!(dw & GNR_CFG_DW_HOSTSW_MODE)) { + dev_warn(gc->parent, "GPIO %u is not owned by host", gpio); + return -EBUSY; + } + + return 0; +} + static int gnr_gpio_get(struct gpio_chip *gc, unsigned int gpio) { const struct gnr_gpio *priv = gpiochip_get_data(gc); @@ -139,6 +157,7 @@ static int gnr_gpio_direction_output(struct gpio_chip *gc, unsigned int gpio, in static const struct gpio_chip gnr_gpio_chip = { .owner = THIS_MODULE, + .request = gnr_gpio_request, .get = gnr_gpio_get, .set = gnr_gpio_set, .get_direction = gnr_gpio_get_direction, @@ -166,7 +185,7 @@ static void gnr_gpio_irq_ack(struct irq_data *d) guard(raw_spinlock_irqsave)(&priv->lock); reg = readl(addr); - reg &= ~BIT(bit_idx); + reg |= BIT(bit_idx); writel(reg, addr); } @@ -209,10 +228,18 @@ static void gnr_gpio_irq_unmask(struct irq_data *d) static int gnr_gpio_irq_set_type(struct irq_data *d, unsigned int type) { struct gpio_chip *gc = irq_data_get_irq_chip_data(d); - irq_hw_number_t pin = irqd_to_hwirq(d); - u32 mask = GNR_CFG_DW_RX_MASK; + struct gnr_gpio *priv = gpiochip_get_data(gc); + irq_hw_number_t hwirq = irqd_to_hwirq(d); + u32 reg; u32 set; + /* Allow interrupts only if Interrupt Select field is non-zero */ + reg = readl(gnr_gpio_get_padcfg_addr(priv, hwirq)); + if (!(reg & GNR_CFG_DW_INTSEL_MASK)) { + dev_dbg(gc->parent, "GPIO %lu cannot be used as IRQ", hwirq); + return -EPERM; + } + /* Falling edge and level low triggers not supported by the GPIO controller */ switch (type) { case IRQ_TYPE_NONE: @@ -230,10 +257,11 @@ static int gnr_gpio_irq_set_type(struct irq_data *d, unsigned int type) return -EINVAL; } - return gnr_gpio_configure_line(gc, pin, mask, set); + return gnr_gpio_configure_line(gc, hwirq, GNR_CFG_DW_RX_MASK, set); } static const struct irq_chip gnr_gpio_irq_chip = { + .name = "gpio-graniterapids", .irq_ack = gnr_gpio_irq_ack, .irq_mask = gnr_gpio_irq_mask, .irq_unmask = gnr_gpio_irq_unmask, @@ -291,6 +319,7 @@ static int gnr_gpio_probe(struct platform_device *pdev) struct gnr_gpio *priv; void __iomem *regs; int irq, ret; + u32 offset; priv = devm_kzalloc(dev, struct_size(priv, pad_backup, num_backup_pins), GFP_KERNEL); if (!priv) @@ -302,6 +331,10 @@ static int gnr_gpio_probe(struct platform_device *pdev) if (IS_ERR(regs)) return PTR_ERR(regs); + priv->reg_base = regs; + offset = readl(priv->reg_base + GNR_CFG_PADBAR); + priv->pad_base = priv->reg_base + offset; + irq = platform_get_irq(pdev, 0); if (irq < 0) return irq; @@ -311,8 +344,6 @@ static int gnr_gpio_probe(struct platform_device *pdev) if (ret) return dev_err_probe(dev, ret, "failed to request interrupt\n"); - priv->reg_base = regs + readl(regs + GNR_CFG_BAR); - gnr_gpio_init_pin_ro_bits(dev, priv->reg_base + GNR_CFG_LOCK_OFFSET, priv->ro_bitmap); @@ -324,7 +355,6 @@ static int gnr_gpio_probe(struct platform_device *pdev) girq = &priv->gc.irq; gpio_irq_chip_set_chip(girq, &gnr_gpio_irq_chip); - girq->chip->name = dev_name(dev); girq->parent_handler = NULL; girq->num_parents = 0; girq->parents = NULL; diff --git a/drivers/gpio/gpio-ljca.c b/drivers/gpio/gpio-ljca.c index dfec9fbfc7a9..c2a9b4253974 100644 --- a/drivers/gpio/gpio-ljca.c +++ b/drivers/gpio/gpio-ljca.c @@ -82,9 +82,9 @@ static int ljca_gpio_config(struct ljca_gpio_dev *ljca_gpio, u8 gpio_id, int ret; mutex_lock(&ljca_gpio->trans_lock); + packet->num = 1; packet->item[0].index = gpio_id; packet->item[0].value = config | ljca_gpio->connect_mode[gpio_id]; - packet->num = 1; ret = ljca_transfer(ljca_gpio->ljca, LJCA_GPIO_CONFIG, (u8 *)packet, struct_size(packet, item, packet->num), NULL, 0); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c index d891ab779ca7..5df21529b3b1 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c @@ -1801,13 +1801,18 @@ int amdgpu_cs_find_mapping(struct amdgpu_cs_parser *parser, if (dma_resv_locking_ctx((*bo)->tbo.base.resv) != &parser->exec.ticket) return -EINVAL; + /* Make sure VRAM is allocated contigiously */ (*bo)->flags |= AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS; - amdgpu_bo_placement_from_domain(*bo, (*bo)->allowed_domains); - for (i = 0; i < (*bo)->placement.num_placement; i++) - (*bo)->placements[i].flags |= TTM_PL_FLAG_CONTIGUOUS; - r = ttm_bo_validate(&(*bo)->tbo, &(*bo)->placement, &ctx); - if (r) - return r; + if ((*bo)->tbo.resource->mem_type == TTM_PL_VRAM && + !((*bo)->tbo.resource->placement & TTM_PL_FLAG_CONTIGUOUS)) { + + amdgpu_bo_placement_from_domain(*bo, (*bo)->allowed_domains); + for (i = 0; i < (*bo)->placement.num_placement; i++) + (*bo)->placements[i].flags |= TTM_PL_FLAG_CONTIGUOUS; + r = ttm_bo_validate(&(*bo)->tbo, &(*bo)->placement, &ctx); + if (r) + return r; + } return amdgpu_ttm_alloc_gart(&(*bo)->tbo); } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dev_coredump.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dev_coredump.c index 5ac59b62020c..18b3b1aaa1d3 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dev_coredump.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dev_coredump.c @@ -345,11 +345,10 @@ void amdgpu_coredump(struct amdgpu_device *adev, bool skip_vram_check, coredump->skip_vram_check = skip_vram_check; coredump->reset_vram_lost = vram_lost; - if (job && job->vm) { - struct amdgpu_vm *vm = job->vm; + if (job && job->pasid) { struct amdgpu_task_info *ti; - ti = amdgpu_vm_get_task_info_vm(vm); + ti = amdgpu_vm_get_task_info_pasid(adev, job->pasid); if (ti) { coredump->reset_task_info = *ti; amdgpu_vm_put_task_info(ti); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 51904906545e..45e28726e148 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -3721,8 +3721,12 @@ static int amdgpu_device_ip_resume_phase3(struct amdgpu_device *adev) continue; if (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_DCE) { r = adev->ip_blocks[i].version->funcs->resume(adev); - if (r) + if (r) { + DRM_ERROR("resume of IP block <%s> failed %d\n", + adev->ip_blocks[i].version->funcs->name, r); return r; + } + adev->ip_blocks[i].status.hw = true; } } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c index 16f2605ac50b..1ce20a19be8b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c @@ -253,7 +253,6 @@ void amdgpu_job_set_resources(struct amdgpu_job *job, struct amdgpu_bo *gds, void amdgpu_job_free_resources(struct amdgpu_job *job) { - struct amdgpu_ring *ring = to_amdgpu_ring(job->base.sched); struct dma_fence *f; unsigned i; @@ -266,7 +265,7 @@ void amdgpu_job_free_resources(struct amdgpu_job *job) f = NULL; for (i = 0; i < job->num_ibs; ++i) - amdgpu_ib_free(ring->adev, &job->ibs[i], f); + amdgpu_ib_free(NULL, &job->ibs[i], f); } static void amdgpu_job_free_cb(struct drm_sched_job *s_job) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c index 31fd30dcd593..65bb26215e86 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c @@ -551,6 +551,8 @@ static void amdgpu_uvd_force_into_uvd_segment(struct amdgpu_bo *abo) for (i = 0; i < abo->placement.num_placement; ++i) { abo->placements[i].fpfn = 0 >> PAGE_SHIFT; abo->placements[i].lpfn = (256 * 1024 * 1024) >> PAGE_SHIFT; + if (abo->placements[i].mem_type == TTM_PL_VRAM) + abo->placements[i].flags |= TTM_PL_FLAG_CONTIGUOUS; } } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index 6005280f5f38..73e02141a6e2 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -674,12 +674,8 @@ int amdgpu_vm_flush(struct amdgpu_ring *ring, struct amdgpu_job *job, pasid_mapping_needed &= adev->gmc.gmc_funcs->emit_pasid_mapping && ring->funcs->emit_wreg; - if (adev->gfx.enable_cleaner_shader && - ring->funcs->emit_cleaner_shader && - job->enforce_isolation) - ring->funcs->emit_cleaner_shader(ring); - - if (!vm_flush_needed && !gds_switch_needed && !need_pipe_sync) + if (!vm_flush_needed && !gds_switch_needed && !need_pipe_sync && + !(job->enforce_isolation && !job->vmid)) return 0; amdgpu_ring_ib_begin(ring); @@ -690,6 +686,11 @@ int amdgpu_vm_flush(struct amdgpu_ring *ring, struct amdgpu_job *job, if (need_pipe_sync) amdgpu_ring_emit_pipeline_sync(ring); + if (adev->gfx.enable_cleaner_shader && + ring->funcs->emit_cleaner_shader && + job->enforce_isolation) + ring->funcs->emit_cleaner_shader(ring); + if (vm_flush_needed) { trace_amdgpu_vm_flush(ring, job->vmid, job->vm_pd_addr); amdgpu_ring_emit_vm_flush(ring, job->vmid, job->vm_pd_addr); @@ -1259,10 +1260,9 @@ int amdgpu_vm_bo_update(struct amdgpu_device *adev, struct amdgpu_bo_va *bo_va, * next command submission. */ if (amdgpu_vm_is_bo_always_valid(vm, bo)) { - uint32_t mem_type = bo->tbo.resource->mem_type; - - if (!(bo->preferred_domains & - amdgpu_mem_type_to_domain(mem_type))) + if (bo->tbo.resource && + !(bo->preferred_domains & + amdgpu_mem_type_to_domain(bo->tbo.resource->mem_type))) amdgpu_vm_bo_evicted(&bo_va->base); else amdgpu_vm_bo_idle(&bo_va->base); diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c index 47b47d21f464..6c19626ec59e 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c @@ -4105,7 +4105,7 @@ static int gfx_v12_0_set_clockgating_state(void *handle, if (amdgpu_sriov_vf(adev)) return 0; - switch (adev->ip_versions[GC_HWIP][0]) { + switch (amdgpu_ip_version(adev, GC_HWIP, 0)) { case IP_VERSION(12, 0, 0): case IP_VERSION(12, 0, 1): gfx_v12_0_update_gfx_clock_gating(adev, diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c index c100845409f7..ffdb966c4127 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c @@ -45,6 +45,8 @@ MODULE_FIRMWARE("amdgpu/gc_9_4_3_mec.bin"); MODULE_FIRMWARE("amdgpu/gc_9_4_4_mec.bin"); MODULE_FIRMWARE("amdgpu/gc_9_4_3_rlc.bin"); MODULE_FIRMWARE("amdgpu/gc_9_4_4_rlc.bin"); +MODULE_FIRMWARE("amdgpu/gc_9_4_3_sjt_mec.bin"); +MODULE_FIRMWARE("amdgpu/gc_9_4_4_sjt_mec.bin"); #define GFX9_MEC_HPD_SIZE 4096 #define RLCG_UCODE_LOADING_START_ADDRESS 0x00002000L @@ -574,8 +576,12 @@ static int gfx_v9_4_3_init_cp_compute_microcode(struct amdgpu_device *adev, { int err; - err = amdgpu_ucode_request(adev, &adev->gfx.mec_fw, - "amdgpu/%s_mec.bin", chip_name); + if (amdgpu_sriov_vf(adev)) + err = amdgpu_ucode_request(adev, &adev->gfx.mec_fw, + "amdgpu/%s_sjt_mec.bin", chip_name); + else + err = amdgpu_ucode_request(adev, &adev->gfx.mec_fw, + "amdgpu/%s_mec.bin", chip_name); if (err) goto out; amdgpu_gfx_cp_init_microcode(adev, AMDGPU_UCODE_ID_CP_MEC1); diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v4_1_0.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v4_1_0.c index 0fbc3be81f14..f2ab5001b492 100644 --- a/drivers/gpu/drm/amd/amdgpu/mmhub_v4_1_0.c +++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v4_1_0.c @@ -108,7 +108,7 @@ mmhub_v4_1_0_print_l2_protection_fault_status(struct amdgpu_device *adev, dev_err(adev->dev, "MMVM_L2_PROTECTION_FAULT_STATUS_LO32:0x%08X\n", status); - switch (adev->ip_versions[MMHUB_HWIP][0]) { + switch (amdgpu_ip_version(adev, MMHUB_HWIP, 0)) { case IP_VERSION(4, 1, 0): mmhub_cid = mmhub_client_ids_v4_1_0[cid][rw]; break; diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_0.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_0.c index b1b57dcc5a73..d1032e9992b4 100644 --- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_0.c +++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_0.c @@ -271,8 +271,19 @@ const struct nbio_hdp_flush_reg nbio_v7_0_hdp_flush_reg = { .ref_and_mask_sdma1 = GPU_HDP_FLUSH_DONE__SDMA1_MASK, }; +#define regRCC_DEV0_EPF6_STRAP4 0xd304 +#define regRCC_DEV0_EPF6_STRAP4_BASE_IDX 5 + static void nbio_v7_0_init_registers(struct amdgpu_device *adev) { + uint32_t data; + + switch (amdgpu_ip_version(adev, NBIO_HWIP, 0)) { + case IP_VERSION(2, 5, 0): + data = RREG32_SOC15(NBIO, 0, regRCC_DEV0_EPF6_STRAP4) & ~BIT(23); + WREG32_SOC15(NBIO, 0, regRCC_DEV0_EPF6_STRAP4, data); + break; + } } #define MMIO_REG_HOLE_OFFSET (0x80000 - PAGE_SIZE) diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_11.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_11.c index 814ab59fdd4a..41421da63a08 100644 --- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_11.c +++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_11.c @@ -275,7 +275,7 @@ static void nbio_v7_11_init_registers(struct amdgpu_device *adev) if (def != data) WREG32_SOC15(NBIO, 0, regBIF_BIF256_CI256_RC3X4_USB4_PCIE_MST_CTRL_3, data); - switch (adev->ip_versions[NBIO_HWIP][0]) { + switch (amdgpu_ip_version(adev, NBIO_HWIP, 0)) { case IP_VERSION(7, 11, 0): case IP_VERSION(7, 11, 1): case IP_VERSION(7, 11, 2): diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_7.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_7.c index 1ac730328516..3fb6d2aa7e3b 100644 --- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_7.c +++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_7.c @@ -247,7 +247,7 @@ static void nbio_v7_7_init_registers(struct amdgpu_device *adev) if (def != data) WREG32_SOC15(NBIO, 0, regBIF0_PCIE_MST_CTRL_3, data); - switch (adev->ip_versions[NBIO_HWIP][0]) { + switch (amdgpu_ip_version(adev, NBIO_HWIP, 0)) { case IP_VERSION(7, 7, 0): data = RREG32_SOC15(NBIO, 0, regRCC_DEV0_EPF5_STRAP4) & ~BIT(23); WREG32_SOC15(NBIO, 0, regRCC_DEV0_EPF5_STRAP4, data); diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c index 6068b784dc69..9a30b8c10838 100644 --- a/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c +++ b/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c @@ -1289,7 +1289,7 @@ static int uvd_v7_0_ring_patch_cs_in_place(struct amdgpu_cs_parser *p, struct amdgpu_job *job, struct amdgpu_ib *ib) { - struct amdgpu_ring *ring = to_amdgpu_ring(job->base.sched); + struct amdgpu_ring *ring = amdgpu_job_ring(job); unsigned i; /* No patching necessary for the first instance */ diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_crat.c b/drivers/gpu/drm/amd/amdkfd/kfd_crat.c index 8de61cc524c9..d2993594c848 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_crat.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_crat.c @@ -1422,6 +1422,7 @@ err: static int kfd_fill_gpu_cache_info_from_gfx_config(struct kfd_dev *kdev, + bool cache_line_size_missing, struct kfd_gpu_cache_info *pcache_info) { struct amdgpu_device *adev = kdev->adev; @@ -1436,6 +1437,8 @@ static int kfd_fill_gpu_cache_info_from_gfx_config(struct kfd_dev *kdev, CRAT_CACHE_FLAGS_SIMD_CACHE); pcache_info[i].num_cu_shared = adev->gfx.config.gc_num_tcp_per_wpg / 2; pcache_info[i].cache_line_size = adev->gfx.config.gc_tcp_cache_line_size; + if (cache_line_size_missing && !pcache_info[i].cache_line_size) + pcache_info[i].cache_line_size = 128; i++; } /* Scalar L1 Instruction Cache per SQC */ @@ -1448,6 +1451,8 @@ static int kfd_fill_gpu_cache_info_from_gfx_config(struct kfd_dev *kdev, CRAT_CACHE_FLAGS_SIMD_CACHE); pcache_info[i].num_cu_shared = adev->gfx.config.gc_num_sqc_per_wgp * 2; pcache_info[i].cache_line_size = adev->gfx.config.gc_instruction_cache_line_size; + if (cache_line_size_missing && !pcache_info[i].cache_line_size) + pcache_info[i].cache_line_size = 128; i++; } /* Scalar L1 Data Cache per SQC */ @@ -1459,6 +1464,8 @@ static int kfd_fill_gpu_cache_info_from_gfx_config(struct kfd_dev *kdev, CRAT_CACHE_FLAGS_SIMD_CACHE); pcache_info[i].num_cu_shared = adev->gfx.config.gc_num_sqc_per_wgp * 2; pcache_info[i].cache_line_size = adev->gfx.config.gc_scalar_data_cache_line_size; + if (cache_line_size_missing && !pcache_info[i].cache_line_size) + pcache_info[i].cache_line_size = 64; i++; } /* GL1 Data Cache per SA */ @@ -1471,7 +1478,8 @@ static int kfd_fill_gpu_cache_info_from_gfx_config(struct kfd_dev *kdev, CRAT_CACHE_FLAGS_DATA_CACHE | CRAT_CACHE_FLAGS_SIMD_CACHE); pcache_info[i].num_cu_shared = adev->gfx.config.max_cu_per_sh; - pcache_info[i].cache_line_size = 0; + if (cache_line_size_missing) + pcache_info[i].cache_line_size = 128; i++; } /* L2 Data Cache per GPU (Total Tex Cache) */ @@ -1483,6 +1491,8 @@ static int kfd_fill_gpu_cache_info_from_gfx_config(struct kfd_dev *kdev, CRAT_CACHE_FLAGS_SIMD_CACHE); pcache_info[i].num_cu_shared = adev->gfx.config.max_cu_per_sh; pcache_info[i].cache_line_size = adev->gfx.config.gc_tcc_cache_line_size; + if (cache_line_size_missing && !pcache_info[i].cache_line_size) + pcache_info[i].cache_line_size = 128; i++; } /* L3 Data Cache per GPU */ @@ -1493,7 +1503,7 @@ static int kfd_fill_gpu_cache_info_from_gfx_config(struct kfd_dev *kdev, CRAT_CACHE_FLAGS_DATA_CACHE | CRAT_CACHE_FLAGS_SIMD_CACHE); pcache_info[i].num_cu_shared = adev->gfx.config.max_cu_per_sh; - pcache_info[i].cache_line_size = 0; + pcache_info[i].cache_line_size = 64; i++; } return i; @@ -1568,6 +1578,7 @@ static int kfd_fill_gpu_cache_info_from_gfx_config_v2(struct kfd_dev *kdev, int kfd_get_gpu_cache_info(struct kfd_node *kdev, struct kfd_gpu_cache_info **pcache_info) { int num_of_cache_types = 0; + bool cache_line_size_missing = false; switch (kdev->adev->asic_type) { case CHIP_KAVERI: @@ -1691,10 +1702,17 @@ int kfd_get_gpu_cache_info(struct kfd_node *kdev, struct kfd_gpu_cache_info **pc case IP_VERSION(11, 5, 0): case IP_VERSION(11, 5, 1): case IP_VERSION(11, 5, 2): + /* Cacheline size not available in IP discovery for gc11. + * kfd_fill_gpu_cache_info_from_gfx_config to hard code it + */ + cache_line_size_missing = true; + fallthrough; case IP_VERSION(12, 0, 0): case IP_VERSION(12, 0, 1): num_of_cache_types = - kfd_fill_gpu_cache_info_from_gfx_config(kdev->kfd, *pcache_info); + kfd_fill_gpu_cache_info_from_gfx_config(kdev->kfd, + cache_line_size_missing, + *pcache_info); break; default: *pcache_info = dummy_cache_info; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c index 648f40091aa3..f5b3ed20e891 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c @@ -205,6 +205,21 @@ static int add_queue_mes(struct device_queue_manager *dqm, struct queue *q, if (!down_read_trylock(&adev->reset_domain->sem)) return -EIO; + if (!pdd->proc_ctx_cpu_ptr) { + r = amdgpu_amdkfd_alloc_gtt_mem(adev, + AMDGPU_MES_PROC_CTX_SIZE, + &pdd->proc_ctx_bo, + &pdd->proc_ctx_gpu_addr, + &pdd->proc_ctx_cpu_ptr, + false); + if (r) { + dev_err(adev->dev, + "failed to allocate process context bo\n"); + return r; + } + memset(pdd->proc_ctx_cpu_ptr, 0, AMDGPU_MES_PROC_CTX_SIZE); + } + memset(&queue_input, 0x0, sizeof(struct mes_add_queue_input)); queue_input.process_id = qpd->pqm->process->pasid; queue_input.page_table_base_addr = qpd->page_table_base; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c index 8ee3d07ffbdf..f31e9fbf634a 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c @@ -306,7 +306,7 @@ svm_migrate_copy_to_vram(struct kfd_node *node, struct svm_range *prange, spage = migrate_pfn_to_page(migrate->src[i]); if (spage && !is_zone_device_page(spage)) { src[i] = dma_map_page(dev, spage, 0, PAGE_SIZE, - DMA_TO_DEVICE); + DMA_BIDIRECTIONAL); r = dma_mapping_error(dev, src[i]); if (r) { dev_err(dev, "%s: fail %d dma_map_page\n", @@ -630,7 +630,7 @@ svm_migrate_copy_to_ram(struct amdgpu_device *adev, struct svm_range *prange, goto out_oom; } - dst[i] = dma_map_page(dev, dpage, 0, PAGE_SIZE, DMA_FROM_DEVICE); + dst[i] = dma_map_page(dev, dpage, 0, PAGE_SIZE, DMA_BIDIRECTIONAL); r = dma_mapping_error(dev, dst[i]); if (r) { dev_err(adev->dev, "%s: fail %d dma_map_page\n", __func__, r); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c index ff34bb1ac9db..3139987b82b1 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c @@ -1076,7 +1076,8 @@ static void kfd_process_destroy_pdds(struct kfd_process *p) kfd_free_process_doorbells(pdd->dev->kfd, pdd); - if (pdd->dev->kfd->shared_resources.enable_mes) + if (pdd->dev->kfd->shared_resources.enable_mes && + pdd->proc_ctx_cpu_ptr) amdgpu_amdkfd_free_gtt_mem(pdd->dev->adev, &pdd->proc_ctx_bo); /* @@ -1610,7 +1611,6 @@ struct kfd_process_device *kfd_create_process_device_data(struct kfd_node *dev, struct kfd_process *p) { struct kfd_process_device *pdd = NULL; - int retval = 0; if (WARN_ON_ONCE(p->n_pdds >= MAX_GPU_INSTANCE)) return NULL; @@ -1634,21 +1634,6 @@ struct kfd_process_device *kfd_create_process_device_data(struct kfd_node *dev, pdd->user_gpu_id = dev->id; atomic64_set(&pdd->evict_duration_counter, 0); - if (dev->kfd->shared_resources.enable_mes) { - retval = amdgpu_amdkfd_alloc_gtt_mem(dev->adev, - AMDGPU_MES_PROC_CTX_SIZE, - &pdd->proc_ctx_bo, - &pdd->proc_ctx_gpu_addr, - &pdd->proc_ctx_cpu_ptr, - false); - if (retval) { - dev_err(dev->adev->dev, - "failed to allocate process context bo\n"); - goto err_free_pdd; - } - memset(pdd->proc_ctx_cpu_ptr, 0, AMDGPU_MES_PROC_CTX_SIZE); - } - p->pdds[p->n_pdds++] = pdd; if (kfd_dbg_is_per_vmid_supported(pdd->dev)) pdd->spi_dbg_override = pdd->dev->kfd2kgd->disable_debug_trap( @@ -1660,10 +1645,6 @@ struct kfd_process_device *kfd_create_process_device_data(struct kfd_node *dev, idr_init(&pdd->alloc_idr); return pdd; - -err_free_pdd: - kfree(pdd); - return NULL; } /** diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c index 01b960b15274..ead4317a2168 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c @@ -212,13 +212,17 @@ static void pqm_clean_queue_resource(struct process_queue_manager *pqm, void pqm_uninit(struct process_queue_manager *pqm) { struct process_queue_node *pqn, *next; - struct kfd_process_device *pdd; list_for_each_entry_safe(pqn, next, &pqm->queues, process_queue_list) { if (pqn->q) { - pdd = kfd_get_process_device_data(pqn->q->device, pqm->process); - kfd_queue_unref_bo_vas(pdd, &pqn->q->properties); - kfd_queue_release_buffers(pdd, &pqn->q->properties); + struct kfd_process_device *pdd = kfd_get_process_device_data(pqn->q->device, + pqm->process); + if (pdd) { + kfd_queue_unref_bo_vas(pdd, &pqn->q->properties); + kfd_queue_release_buffers(pdd, &pqn->q->properties); + } else { + WARN_ON(!pdd); + } pqm_clean_queue_resource(pqm, pqn); } diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c index d0e6d051e9cf..1aedfafa507f 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c @@ -2717,4 +2717,5 @@ void smu_v13_0_7_set_ppt_funcs(struct smu_context *smu) smu->workload_map = smu_v13_0_7_workload_map; smu->smc_driver_if_version = SMU13_0_7_DRIVER_IF_VERSION; smu_v13_0_set_smu_mailbox_registers(smu); + smu->power_profile_mode = PP_SMC_POWER_PROFILE_BOOTUP_DEFAULT; } diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c index b22fb7eafcd3..9ec53431f2c3 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c @@ -2108,7 +2108,7 @@ static int smu_v14_0_2_enable_gfx_features(struct smu_context *smu) { struct amdgpu_device *adev = smu->adev; - if (adev->ip_versions[MP1_HWIP][0] == IP_VERSION(14, 0, 2)) + if (amdgpu_ip_version(adev, MP1_HWIP, 0) == IP_VERSION(14, 0, 2)) return smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_EnableAllSmuFeatures, FEATURE_PWR_GFX, NULL); else diff --git a/drivers/gpu/drm/bridge/adv7511/adv7511_audio.c b/drivers/gpu/drm/bridge/adv7511/adv7511_audio.c index 61f4a38e7d2b..8f786592143b 100644 --- a/drivers/gpu/drm/bridge/adv7511/adv7511_audio.c +++ b/drivers/gpu/drm/bridge/adv7511/adv7511_audio.c @@ -153,7 +153,16 @@ static int adv7511_hdmi_hw_params(struct device *dev, void *data, ADV7511_AUDIO_CFG3_LEN_MASK, len); regmap_update_bits(adv7511->regmap, ADV7511_REG_I2C_FREQ_ID_CFG, ADV7511_I2C_FREQ_ID_CFG_RATE_MASK, rate << 4); - regmap_write(adv7511->regmap, 0x73, 0x1); + + /* send current Audio infoframe values while updating */ + regmap_update_bits(adv7511->regmap, ADV7511_REG_INFOFRAME_UPDATE, + BIT(5), BIT(5)); + + regmap_write(adv7511->regmap, ADV7511_REG_AUDIO_INFOFRAME(0), 0x1); + + /* use Audio infoframe updated info */ + regmap_update_bits(adv7511->regmap, ADV7511_REG_INFOFRAME_UPDATE, + BIT(5), 0); return 0; } @@ -184,8 +193,9 @@ static int audio_startup(struct device *dev, void *data) regmap_update_bits(adv7511->regmap, ADV7511_REG_GC(0), BIT(7) | BIT(6), BIT(7)); /* use Audio infoframe updated info */ - regmap_update_bits(adv7511->regmap, ADV7511_REG_GC(1), + regmap_update_bits(adv7511->regmap, ADV7511_REG_INFOFRAME_UPDATE, BIT(5), 0); + /* enable SPDIF receiver */ if (adv7511->audio_source == ADV7511_AUDIO_SOURCE_SPDIF) regmap_update_bits(adv7511->regmap, ADV7511_REG_AUDIO_CONFIG, diff --git a/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c b/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c index eb5919b38263..a13b3d8ab6ac 100644 --- a/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c +++ b/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c @@ -1241,8 +1241,10 @@ static int adv7511_probe(struct i2c_client *i2c) return ret; ret = adv7511_init_regulators(adv7511); - if (ret) - return dev_err_probe(dev, ret, "failed to init regulators\n"); + if (ret) { + dev_err_probe(dev, ret, "failed to init regulators\n"); + goto err_of_node_put; + } /* * The power down GPIO is optional. If present, toggle it from active to @@ -1363,6 +1365,8 @@ err_i2c_unregister_edid: i2c_unregister_device(adv7511->i2c_edid); uninit_regulators: adv7511_uninit_regulators(adv7511); +err_of_node_put: + of_node_put(adv7511->host_node); return ret; } @@ -1371,6 +1375,8 @@ static void adv7511_remove(struct i2c_client *i2c) { struct adv7511 *adv7511 = i2c_get_clientdata(i2c); + of_node_put(adv7511->host_node); + adv7511_uninit_regulators(adv7511); drm_bridge_remove(&adv7511->bridge); diff --git a/drivers/gpu/drm/bridge/adv7511/adv7533.c b/drivers/gpu/drm/bridge/adv7511/adv7533.c index 4481489aaf5e..122ad91e8a32 100644 --- a/drivers/gpu/drm/bridge/adv7511/adv7533.c +++ b/drivers/gpu/drm/bridge/adv7511/adv7533.c @@ -172,7 +172,7 @@ int adv7533_parse_dt(struct device_node *np, struct adv7511 *adv) of_property_read_u32(np, "adi,dsi-lanes", &num_lanes); - if (num_lanes < 1 || num_lanes > 4) + if (num_lanes < 2 || num_lanes > 4) return -EINVAL; adv->num_dsi_lanes = num_lanes; @@ -181,8 +181,6 @@ int adv7533_parse_dt(struct device_node *np, struct adv7511 *adv) if (!adv->host_node) return -ENODEV; - of_node_put(adv->host_node); - adv->use_timing_gen = !of_property_read_bool(np, "adi,disable-timing-generator"); diff --git a/drivers/gpu/drm/display/drm_dp_mst_topology.c b/drivers/gpu/drm/display/drm_dp_mst_topology.c index bcf3a33123be..f0c6d50d8c33 100644 --- a/drivers/gpu/drm/display/drm_dp_mst_topology.c +++ b/drivers/gpu/drm/display/drm_dp_mst_topology.c @@ -4108,9 +4108,10 @@ static void drm_dp_mst_up_req_work(struct work_struct *work) static int drm_dp_mst_handle_up_req(struct drm_dp_mst_topology_mgr *mgr) { struct drm_dp_pending_up_req *up_req; + struct drm_dp_mst_branch *mst_primary; if (!drm_dp_get_one_sb_msg(mgr, true, NULL)) - goto out; + goto out_clear_reply; if (!mgr->up_req_recv.have_eomt) return 0; @@ -4128,10 +4129,19 @@ static int drm_dp_mst_handle_up_req(struct drm_dp_mst_topology_mgr *mgr) drm_dbg_kms(mgr->dev, "Received unknown up req type, ignoring: %x\n", up_req->msg.req_type); kfree(up_req); - goto out; + goto out_clear_reply; + } + + mutex_lock(&mgr->lock); + mst_primary = mgr->mst_primary; + if (!mst_primary || !drm_dp_mst_topology_try_get_mstb(mst_primary)) { + mutex_unlock(&mgr->lock); + kfree(up_req); + goto out_clear_reply; } + mutex_unlock(&mgr->lock); - drm_dp_send_up_ack_reply(mgr, mgr->mst_primary, up_req->msg.req_type, + drm_dp_send_up_ack_reply(mgr, mst_primary, up_req->msg.req_type, false); if (up_req->msg.req_type == DP_CONNECTION_STATUS_NOTIFY) { @@ -4148,13 +4158,13 @@ static int drm_dp_mst_handle_up_req(struct drm_dp_mst_topology_mgr *mgr) conn_stat->peer_device_type); mutex_lock(&mgr->probe_lock); - handle_csn = mgr->mst_primary->link_address_sent; + handle_csn = mst_primary->link_address_sent; mutex_unlock(&mgr->probe_lock); if (!handle_csn) { drm_dbg_kms(mgr->dev, "Got CSN before finish topology probing. Skip it."); kfree(up_req); - goto out; + goto out_put_primary; } } else if (up_req->msg.req_type == DP_RESOURCE_STATUS_NOTIFY) { const struct drm_dp_resource_status_notify *res_stat = @@ -4171,7 +4181,9 @@ static int drm_dp_mst_handle_up_req(struct drm_dp_mst_topology_mgr *mgr) mutex_unlock(&mgr->up_req_lock); queue_work(system_long_wq, &mgr->up_req_work); -out: +out_put_primary: + drm_dp_mst_topology_put_mstb(mst_primary); +out_clear_reply: memset(&mgr->up_req_recv, 0, sizeof(struct drm_dp_sideband_msg_rx)); return 0; } diff --git a/drivers/gpu/drm/display/drm_dp_tunnel.c b/drivers/gpu/drm/display/drm_dp_tunnel.c index 48b2df120086..90fe07a89260 100644 --- a/drivers/gpu/drm/display/drm_dp_tunnel.c +++ b/drivers/gpu/drm/display/drm_dp_tunnel.c @@ -1896,8 +1896,8 @@ static void destroy_mgr(struct drm_dp_tunnel_mgr *mgr) * * Creates a DP tunnel manager for @dev. * - * Returns a pointer to the tunnel manager if created successfully or NULL in - * case of an error. + * Returns a pointer to the tunnel manager if created successfully or error + * pointer in case of failure. */ struct drm_dp_tunnel_mgr * drm_dp_tunnel_mgr_create(struct drm_device *dev, int max_group_count) @@ -1907,7 +1907,7 @@ drm_dp_tunnel_mgr_create(struct drm_device *dev, int max_group_count) mgr = kzalloc(sizeof(*mgr), GFP_KERNEL); if (!mgr) - return NULL; + return ERR_PTR(-ENOMEM); mgr->dev = dev; init_waitqueue_head(&mgr->bw_req_queue); @@ -1916,7 +1916,7 @@ drm_dp_tunnel_mgr_create(struct drm_device *dev, int max_group_count) if (!mgr->groups) { kfree(mgr); - return NULL; + return ERR_PTR(-ENOMEM); } #ifdef CONFIG_DRM_DISPLAY_DP_TUNNEL_STATE_DEBUG @@ -1927,7 +1927,7 @@ drm_dp_tunnel_mgr_create(struct drm_device *dev, int max_group_count) if (!init_group(mgr, &mgr->groups[i])) { destroy_mgr(mgr); - return NULL; + return ERR_PTR(-ENOMEM); } mgr->group_count++; diff --git a/drivers/gpu/drm/drm_modes.c b/drivers/gpu/drm/drm_modes.c index 6ba167a33461..71573b85d924 100644 --- a/drivers/gpu/drm/drm_modes.c +++ b/drivers/gpu/drm/drm_modes.c @@ -1287,14 +1287,11 @@ EXPORT_SYMBOL(drm_mode_set_name); */ int drm_mode_vrefresh(const struct drm_display_mode *mode) { - unsigned int num, den; + unsigned int num = 1, den = 1; if (mode->htotal == 0 || mode->vtotal == 0) return 0; - num = mode->clock; - den = mode->htotal * mode->vtotal; - if (mode->flags & DRM_MODE_FLAG_INTERLACE) num *= 2; if (mode->flags & DRM_MODE_FLAG_DBLSCAN) @@ -1302,6 +1299,12 @@ int drm_mode_vrefresh(const struct drm_display_mode *mode) if (mode->vscan > 1) den *= mode->vscan; + if (check_mul_overflow(mode->clock, num, &num)) + return 0; + + if (check_mul_overflow(mode->htotal * mode->vtotal, den, &den)) + return 0; + return DIV_ROUND_CLOSEST_ULL(mul_u32_u32(num, 1000), den); } EXPORT_SYMBOL(drm_mode_vrefresh); diff --git a/drivers/gpu/drm/drm_panic_qr.rs b/drivers/gpu/drm/drm_panic_qr.rs index 1ef56cb07dfb..447740d79d3d 100644 --- a/drivers/gpu/drm/drm_panic_qr.rs +++ b/drivers/gpu/drm/drm_panic_qr.rs @@ -929,7 +929,6 @@ impl QrImage<'_> { /// * `tmp` must be valid for reading and writing for `tmp_size` bytes. /// /// They must remain valid for the duration of the function call. - #[no_mangle] pub unsafe extern "C" fn drm_panic_qr_generate( url: *const i8, diff --git a/drivers/gpu/drm/i915/display/intel_color.c b/drivers/gpu/drm/i915/display/intel_color.c index 5d701f48351b..ec55cb651d44 100644 --- a/drivers/gpu/drm/i915/display/intel_color.c +++ b/drivers/gpu/drm/i915/display/intel_color.c @@ -1333,19 +1333,29 @@ static void ilk_load_lut_8(const struct intel_crtc_state *crtc_state, lut = blob->data; /* - * DSB fails to correctly load the legacy LUT - * unless we either write each entry twice, - * or use non-posted writes + * DSB fails to correctly load the legacy LUT unless + * we either write each entry twice when using posted + * writes, or we use non-posted writes. + * + * If palette anti-collision is active during LUT + * register writes: + * - posted writes simply get dropped and thus the LUT + * contents may not be correctly updated + * - non-posted writes are blocked and thus the LUT + * contents are always correct, but simultaneous CPU + * MMIO access will start to fail + * + * Choose the lesser of two evils and use posted writes. + * Using posted writes is also faster, even when having + * to write each register twice. */ - if (crtc_state->dsb_color_vblank) - intel_dsb_nonpost_start(crtc_state->dsb_color_vblank); - - for (i = 0; i < 256; i++) + for (i = 0; i < 256; i++) { ilk_lut_write(crtc_state, LGC_PALETTE(pipe, i), i9xx_lut_8(&lut[i])); - - if (crtc_state->dsb_color_vblank) - intel_dsb_nonpost_end(crtc_state->dsb_color_vblank); + if (crtc_state->dsb_color_vblank) + ilk_lut_write(crtc_state, LGC_PALETTE(pipe, i), + i9xx_lut_8(&lut[i])); + } } static void ilk_load_lut_10(const struct intel_crtc_state *crtc_state, diff --git a/drivers/gpu/drm/i915/display/intel_cx0_phy.c b/drivers/gpu/drm/i915/display/intel_cx0_phy.c index 4a6c3040ca15..f11309efff33 100644 --- a/drivers/gpu/drm/i915/display/intel_cx0_phy.c +++ b/drivers/gpu/drm/i915/display/intel_cx0_phy.c @@ -2084,14 +2084,6 @@ static void intel_c10_pll_program(struct drm_i915_private *i915, 0, C10_VDR_CTRL_MSGBUS_ACCESS, MB_WRITE_COMMITTED); - /* Custom width needs to be programmed to 0 for both the phy lanes */ - intel_cx0_rmw(encoder, INTEL_CX0_BOTH_LANES, PHY_C10_VDR_CUSTOM_WIDTH, - C10_VDR_CUSTOM_WIDTH_MASK, C10_VDR_CUSTOM_WIDTH_8_10, - MB_WRITE_COMMITTED); - intel_cx0_rmw(encoder, INTEL_CX0_BOTH_LANES, PHY_C10_VDR_CONTROL(1), - 0, C10_VDR_CTRL_UPDATE_CFG, - MB_WRITE_COMMITTED); - /* Program the pll values only for the master lane */ for (i = 0; i < ARRAY_SIZE(pll_state->pll); i++) intel_cx0_write(encoder, INTEL_CX0_LANE0, PHY_C10_VDR_PLL(i), @@ -2101,6 +2093,10 @@ static void intel_c10_pll_program(struct drm_i915_private *i915, intel_cx0_write(encoder, INTEL_CX0_LANE0, PHY_C10_VDR_CMN(0), pll_state->cmn, MB_WRITE_COMMITTED); intel_cx0_write(encoder, INTEL_CX0_LANE0, PHY_C10_VDR_TX(0), pll_state->tx, MB_WRITE_COMMITTED); + /* Custom width needs to be programmed to 0 for both the phy lanes */ + intel_cx0_rmw(encoder, INTEL_CX0_BOTH_LANES, PHY_C10_VDR_CUSTOM_WIDTH, + C10_VDR_CUSTOM_WIDTH_MASK, C10_VDR_CUSTOM_WIDTH_8_10, + MB_WRITE_COMMITTED); intel_cx0_rmw(encoder, INTEL_CX0_LANE0, PHY_C10_VDR_CONTROL(1), 0, C10_VDR_CTRL_MASTER_LANE | C10_VDR_CTRL_UPDATE_CFG, MB_WRITE_COMMITTED); diff --git a/drivers/gpu/drm/i915/gt/intel_engine_types.h b/drivers/gpu/drm/i915/gt/intel_engine_types.h index ba55c059063d..fe1f85e5dda3 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_types.h +++ b/drivers/gpu/drm/i915/gt/intel_engine_types.h @@ -343,6 +343,11 @@ struct intel_engine_guc_stats { * @start_gt_clk: GT clock time of last idle to active transition. */ u64 start_gt_clk; + + /** + * @total: The last value of total returned + */ + u64 total; }; union intel_engine_tlb_inv_reg { diff --git a/drivers/gpu/drm/i915/gt/intel_rc6.c b/drivers/gpu/drm/i915/gt/intel_rc6.c index c864d101faf9..9378d5901c49 100644 --- a/drivers/gpu/drm/i915/gt/intel_rc6.c +++ b/drivers/gpu/drm/i915/gt/intel_rc6.c @@ -133,7 +133,7 @@ static void gen11_rc6_enable(struct intel_rc6 *rc6) GEN9_MEDIA_PG_ENABLE | GEN11_MEDIA_SAMPLER_PG_ENABLE; - if (GRAPHICS_VER(gt->i915) >= 12) { + if (GRAPHICS_VER(gt->i915) >= 12 && !IS_DG1(gt->i915)) { for (i = 0; i < I915_MAX_VCS; i++) if (HAS_ENGINE(gt, _VCS(i))) pg_enable |= (VDN_HCP_POWERGATE_ENABLE(i) | diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c index ed979847187f..ee12ee0ed418 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c @@ -1243,6 +1243,21 @@ static void __get_engine_usage_record(struct intel_engine_cs *engine, } while (++i < 6); } +static void __set_engine_usage_record(struct intel_engine_cs *engine, + u32 last_in, u32 id, u32 total) +{ + struct iosys_map rec_map = intel_guc_engine_usage_record_map(engine); + +#define record_write(map_, field_, val_) \ + iosys_map_wr_field(map_, 0, struct guc_engine_usage_record, field_, val_) + + record_write(&rec_map, last_switch_in_stamp, last_in); + record_write(&rec_map, current_context_index, id); + record_write(&rec_map, total_runtime, total); + +#undef record_write +} + static void guc_update_engine_gt_clks(struct intel_engine_cs *engine) { struct intel_engine_guc_stats *stats = &engine->stats.guc; @@ -1363,9 +1378,12 @@ static ktime_t guc_engine_busyness(struct intel_engine_cs *engine, ktime_t *now) total += intel_gt_clock_interval_to_ns(gt, clk); } + if (total > stats->total) + stats->total = total; + spin_unlock_irqrestore(&guc->timestamp.lock, flags); - return ns_to_ktime(total); + return ns_to_ktime(stats->total); } static void guc_enable_busyness_worker(struct intel_guc *guc) @@ -1431,8 +1449,21 @@ static void __reset_guc_busyness_stats(struct intel_guc *guc) guc_update_pm_timestamp(guc, &unused); for_each_engine(engine, gt, id) { + struct intel_engine_guc_stats *stats = &engine->stats.guc; + guc_update_engine_gt_clks(engine); - engine->stats.guc.prev_total = 0; + + /* + * If resetting a running context, accumulate the active + * time as well since there will be no context switch. + */ + if (stats->running) { + u64 clk = guc->timestamp.gt_stamp - stats->start_gt_clk; + + stats->total_gt_clks += clk; + } + stats->prev_total = 0; + stats->running = 0; } spin_unlock_irqrestore(&guc->timestamp.lock, flags); @@ -1543,6 +1574,9 @@ err_trylock: static int guc_action_enable_usage_stats(struct intel_guc *guc) { + struct intel_gt *gt = guc_to_gt(guc); + struct intel_engine_cs *engine; + enum intel_engine_id id; u32 offset = intel_guc_engine_usage_offset(guc); u32 action[] = { INTEL_GUC_ACTION_SET_ENG_UTIL_BUFF, @@ -1550,6 +1584,9 @@ static int guc_action_enable_usage_stats(struct intel_guc *guc) 0, }; + for_each_engine(engine, gt, id) + __set_engine_usage_record(engine, 0, 0xffffffff, 0); + return intel_guc_send(guc, action, ARRAY_SIZE(action)); } diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c index 6469b9bcf2ec..082ac72c757a 100644 --- a/drivers/gpu/drm/i915/i915_gpu_error.c +++ b/drivers/gpu/drm/i915/i915_gpu_error.c @@ -1652,9 +1652,21 @@ capture_engine(struct intel_engine_cs *engine, return NULL; intel_engine_get_hung_entity(engine, &ce, &rq); - if (rq && !i915_request_started(rq)) - drm_info(&engine->gt->i915->drm, "Got hung context on %s with active request %lld:%lld [0x%04X] not yet started\n", - engine->name, rq->fence.context, rq->fence.seqno, ce->guc_id.id); + if (rq && !i915_request_started(rq)) { + /* + * We want to know also what is the guc_id of the context, + * but if we don't have the context reference, then skip + * printing it. + */ + if (ce) + drm_info(&engine->gt->i915->drm, + "Got hung context on %s with active request %lld:%lld [0x%04X] not yet started\n", + engine->name, rq->fence.context, rq->fence.seqno, ce->guc_id.id); + else + drm_info(&engine->gt->i915->drm, + "Got hung context on %s with active request %lld:%lld not yet started\n", + engine->name, rq->fence.context, rq->fence.seqno); + } if (rq) { capture = intel_engine_coredump_add_request(ee, rq, ATOMIC_MAYFAIL); diff --git a/drivers/gpu/drm/i915/i915_scheduler.c b/drivers/gpu/drm/i915/i915_scheduler.c index 762127dd56c5..70a854557e6e 100644 --- a/drivers/gpu/drm/i915/i915_scheduler.c +++ b/drivers/gpu/drm/i915/i915_scheduler.c @@ -506,6 +506,6 @@ int __init i915_scheduler_module_init(void) return 0; err_priorities: - kmem_cache_destroy(slab_priorities); + kmem_cache_destroy(slab_dependencies); return -ENOMEM; } diff --git a/drivers/gpu/drm/panel/panel-himax-hx83102.c b/drivers/gpu/drm/panel/panel-himax-hx83102.c index 8b48bba18131..3644a7544b93 100644 --- a/drivers/gpu/drm/panel/panel-himax-hx83102.c +++ b/drivers/gpu/drm/panel/panel-himax-hx83102.c @@ -565,6 +565,8 @@ static int hx83102_get_modes(struct drm_panel *panel, struct drm_display_mode *mode; mode = drm_mode_duplicate(connector->dev, m); + if (!mode) + return -ENOMEM; mode->type = DRM_MODE_TYPE_DRIVER | DRM_MODE_TYPE_PREFERRED; drm_mode_set_name(mode); diff --git a/drivers/gpu/drm/panel/panel-novatek-nt35950.c b/drivers/gpu/drm/panel/panel-novatek-nt35950.c index b036208f9356..08b22b592ab0 100644 --- a/drivers/gpu/drm/panel/panel-novatek-nt35950.c +++ b/drivers/gpu/drm/panel/panel-novatek-nt35950.c @@ -481,9 +481,9 @@ static int nt35950_probe(struct mipi_dsi_device *dsi) return dev_err_probe(dev, -EPROBE_DEFER, "Cannot get secondary DSI host\n"); nt->dsi[1] = mipi_dsi_device_register_full(dsi_r_host, info); - if (!nt->dsi[1]) { + if (IS_ERR(nt->dsi[1])) { dev_err(dev, "Cannot get secondary DSI node\n"); - return -ENODEV; + return PTR_ERR(nt->dsi[1]); } num_dsis++; } diff --git a/drivers/gpu/drm/panel/panel-sitronix-st7701.c b/drivers/gpu/drm/panel/panel-sitronix-st7701.c index eef03d04e0cd..1f72ef7ca74c 100644 --- a/drivers/gpu/drm/panel/panel-sitronix-st7701.c +++ b/drivers/gpu/drm/panel/panel-sitronix-st7701.c @@ -1177,6 +1177,7 @@ static int st7701_probe(struct device *dev, int connector_type) return dev_err_probe(dev, ret, "Failed to get orientation\n"); drm_panel_init(&st7701->panel, dev, &st7701_funcs, connector_type); + st7701->panel.prepare_prev_first = true; /** * Once sleep out has been issued, ST7701 IC required to wait 120ms diff --git a/drivers/gpu/drm/panel/panel-synaptics-r63353.c b/drivers/gpu/drm/panel/panel-synaptics-r63353.c index 169c629746c7..17349825543f 100644 --- a/drivers/gpu/drm/panel/panel-synaptics-r63353.c +++ b/drivers/gpu/drm/panel/panel-synaptics-r63353.c @@ -325,7 +325,7 @@ static void r63353_panel_shutdown(struct mipi_dsi_device *dsi) { struct r63353_panel *rpanel = mipi_dsi_get_drvdata(dsi); - r63353_panel_unprepare(&rpanel->base); + drm_panel_unprepare(&rpanel->base); } static const struct r63353_desc sharp_ls068b3sx02_data = { diff --git a/drivers/gpu/drm/xe/tests/xe_migrate.c b/drivers/gpu/drm/xe/tests/xe_migrate.c index 1a192a2a941b..3bbdb362d6f0 100644 --- a/drivers/gpu/drm/xe/tests/xe_migrate.c +++ b/drivers/gpu/drm/xe/tests/xe_migrate.c @@ -224,8 +224,8 @@ static void xe_migrate_sanity_test(struct xe_migrate *m, struct kunit *test) XE_BO_FLAG_VRAM_IF_DGFX(tile) | XE_BO_FLAG_PINNED); if (IS_ERR(tiny)) { - KUNIT_FAIL(test, "Failed to allocate fake pt: %li\n", - PTR_ERR(pt)); + KUNIT_FAIL(test, "Failed to allocate tiny fake pt: %li\n", + PTR_ERR(tiny)); goto free_pt; } diff --git a/drivers/gpu/drm/xe/xe_bo.c b/drivers/gpu/drm/xe/xe_bo.c index 2a093540354e..84e327b56925 100644 --- a/drivers/gpu/drm/xe/xe_bo.c +++ b/drivers/gpu/drm/xe/xe_bo.c @@ -722,7 +722,7 @@ static int xe_bo_move(struct ttm_buffer_object *ttm_bo, bool evict, new_mem->mem_type == XE_PL_SYSTEM) { long timeout = dma_resv_wait_timeout(ttm_bo->base.resv, DMA_RESV_USAGE_BOOKKEEP, - true, + false, MAX_SCHEDULE_TIMEOUT); if (timeout < 0) { ret = timeout; @@ -846,8 +846,16 @@ static int xe_bo_move(struct ttm_buffer_object *ttm_bo, bool evict, out: if ((!ttm_bo->resource || ttm_bo->resource->mem_type == XE_PL_SYSTEM) && - ttm_bo->ttm) + ttm_bo->ttm) { + long timeout = dma_resv_wait_timeout(ttm_bo->base.resv, + DMA_RESV_USAGE_KERNEL, + false, + MAX_SCHEDULE_TIMEOUT); + if (timeout < 0) + ret = timeout; + xe_tt_unmap_sg(ttm_bo->ttm); + } return ret; } diff --git a/drivers/gpu/drm/xe/xe_devcoredump.c b/drivers/gpu/drm/xe/xe_devcoredump.c index 5221ee3f1214..85aa3ab0da3b 100644 --- a/drivers/gpu/drm/xe/xe_devcoredump.c +++ b/drivers/gpu/drm/xe/xe_devcoredump.c @@ -20,6 +20,7 @@ #include "xe_guc_ct.h" #include "xe_guc_submit.h" #include "xe_hw_engine.h" +#include "xe_pm.h" #include "xe_sched_job.h" #include "xe_vm.h" @@ -103,7 +104,11 @@ static ssize_t __xe_devcoredump_read(char *buffer, size_t count, drm_puts(&p, "\n**** GuC CT ****\n"); xe_guc_ct_snapshot_print(ss->ct, &p); - drm_puts(&p, "\n**** Contexts ****\n"); + /* + * Don't add a new section header here because the mesa debug decoder + * tool expects the context information to be in the 'GuC CT' section. + */ + /* drm_puts(&p, "\n**** Contexts ****\n"); */ xe_guc_exec_queue_snapshot_print(ss->ge, &p); drm_puts(&p, "\n**** Job ****\n"); @@ -143,31 +148,6 @@ static void xe_devcoredump_snapshot_free(struct xe_devcoredump_snapshot *ss) ss->vm = NULL; } -static void xe_devcoredump_deferred_snap_work(struct work_struct *work) -{ - struct xe_devcoredump_snapshot *ss = container_of(work, typeof(*ss), work); - struct xe_devcoredump *coredump = container_of(ss, typeof(*coredump), snapshot); - unsigned int fw_ref; - - /* keep going if fw fails as we still want to save the memory and SW data */ - fw_ref = xe_force_wake_get(gt_to_fw(ss->gt), XE_FORCEWAKE_ALL); - if (!xe_force_wake_ref_has_domain(fw_ref, XE_FORCEWAKE_ALL)) - xe_gt_info(ss->gt, "failed to get forcewake for coredump capture\n"); - xe_vm_snapshot_capture_delayed(ss->vm); - xe_guc_exec_queue_snapshot_capture_delayed(ss->ge); - xe_force_wake_put(gt_to_fw(ss->gt), fw_ref); - - /* Calculate devcoredump size */ - ss->read.size = __xe_devcoredump_read(NULL, INT_MAX, coredump); - - ss->read.buffer = kvmalloc(ss->read.size, GFP_USER); - if (!ss->read.buffer) - return; - - __xe_devcoredump_read(ss->read.buffer, ss->read.size, coredump); - xe_devcoredump_snapshot_free(ss); -} - static ssize_t xe_devcoredump_read(char *buffer, loff_t offset, size_t count, void *data, size_t datalen) { @@ -216,6 +196,45 @@ static void xe_devcoredump_free(void *data) "Xe device coredump has been deleted.\n"); } +static void xe_devcoredump_deferred_snap_work(struct work_struct *work) +{ + struct xe_devcoredump_snapshot *ss = container_of(work, typeof(*ss), work); + struct xe_devcoredump *coredump = container_of(ss, typeof(*coredump), snapshot); + struct xe_device *xe = coredump_to_xe(coredump); + unsigned int fw_ref; + + /* + * NB: Despite passing a GFP_ flags parameter here, more allocations are done + * internally using GFP_KERNEL expliictly. Hence this call must be in the worker + * thread and not in the initial capture call. + */ + dev_coredumpm_timeout(gt_to_xe(ss->gt)->drm.dev, THIS_MODULE, coredump, 0, GFP_KERNEL, + xe_devcoredump_read, xe_devcoredump_free, + XE_COREDUMP_TIMEOUT_JIFFIES); + + xe_pm_runtime_get(xe); + + /* keep going if fw fails as we still want to save the memory and SW data */ + fw_ref = xe_force_wake_get(gt_to_fw(ss->gt), XE_FORCEWAKE_ALL); + if (!xe_force_wake_ref_has_domain(fw_ref, XE_FORCEWAKE_ALL)) + xe_gt_info(ss->gt, "failed to get forcewake for coredump capture\n"); + xe_vm_snapshot_capture_delayed(ss->vm); + xe_guc_exec_queue_snapshot_capture_delayed(ss->ge); + xe_force_wake_put(gt_to_fw(ss->gt), fw_ref); + + xe_pm_runtime_put(xe); + + /* Calculate devcoredump size */ + ss->read.size = __xe_devcoredump_read(NULL, INT_MAX, coredump); + + ss->read.buffer = kvmalloc(ss->read.size, GFP_USER); + if (!ss->read.buffer) + return; + + __xe_devcoredump_read(ss->read.buffer, ss->read.size, coredump); + xe_devcoredump_snapshot_free(ss); +} + static void devcoredump_snapshot(struct xe_devcoredump *coredump, struct xe_sched_job *job) { @@ -299,10 +318,6 @@ void xe_devcoredump(struct xe_sched_job *job) drm_info(&xe->drm, "Xe device coredump has been created\n"); drm_info(&xe->drm, "Check your /sys/class/drm/card%d/device/devcoredump/data\n", xe->drm.primary->index); - - dev_coredumpm_timeout(xe->drm.dev, THIS_MODULE, coredump, 0, GFP_KERNEL, - xe_devcoredump_read, xe_devcoredump_free, - XE_COREDUMP_TIMEOUT_JIFFIES); } static void xe_driver_devcoredump_fini(void *arg) @@ -347,6 +362,15 @@ void xe_print_blob_ascii85(struct drm_printer *p, const char *prefix, char buff[ASCII85_BUFSZ], *line_buff; size_t line_pos = 0; + /* + * Splitting blobs across multiple lines is not compatible with the mesa + * debug decoder tool. Note that even dropping the explicit '\n' below + * doesn't help because the GuC log is so big some underlying implementation + * still splits the lines at 512K characters. So just bail completely for + * the moment. + */ + return; + #define DMESG_MAX_LINE_LEN 800 #define MIN_SPACE (ASCII85_BUFSZ + 2) /* 85 + "\n\0" */ diff --git a/drivers/gpu/drm/xe/xe_exec_queue.c b/drivers/gpu/drm/xe/xe_exec_queue.c index fd0f3b3c9101..268cd3123be9 100644 --- a/drivers/gpu/drm/xe/xe_exec_queue.c +++ b/drivers/gpu/drm/xe/xe_exec_queue.c @@ -8,6 +8,7 @@ #include <linux/nospec.h> #include <drm/drm_device.h> +#include <drm/drm_drv.h> #include <drm/drm_file.h> #include <uapi/drm/xe_drm.h> @@ -762,9 +763,11 @@ bool xe_exec_queue_is_idle(struct xe_exec_queue *q) */ void xe_exec_queue_update_run_ticks(struct xe_exec_queue *q) { + struct xe_device *xe = gt_to_xe(q->gt); struct xe_file *xef; struct xe_lrc *lrc; u32 old_ts, new_ts; + int idx; /* * Jobs that are run during driver load may use an exec_queue, but are @@ -774,6 +777,10 @@ void xe_exec_queue_update_run_ticks(struct xe_exec_queue *q) if (!q->vm || !q->vm->xef) return; + /* Synchronize with unbind while holding the xe file open */ + if (!drm_dev_enter(&xe->drm, &idx)) + return; + xef = q->vm->xef; /* @@ -787,6 +794,8 @@ void xe_exec_queue_update_run_ticks(struct xe_exec_queue *q) lrc = q->lrc[0]; new_ts = xe_lrc_update_timestamp(lrc, &old_ts); xef->run_ticks[q->class] += (new_ts - old_ts) * q->width; + + drm_dev_exit(idx); } /** diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c b/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c index afdb477ecf83..c9ed996b9cb0 100644 --- a/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c +++ b/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c @@ -2038,7 +2038,7 @@ static int pf_validate_vf_config(struct xe_gt *gt, unsigned int vfid) valid_any = valid_any || (valid_ggtt && is_primary); if (IS_DGFX(xe)) { - bool valid_lmem = pf_get_vf_config_ggtt(primary_gt, vfid); + bool valid_lmem = pf_get_vf_config_lmem(primary_gt, vfid); valid_any = valid_any || (valid_lmem && is_primary); valid_all = valid_all && valid_lmem; diff --git a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c index 9d82ea30f4df..7e385940df08 100644 --- a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c +++ b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c @@ -65,6 +65,14 @@ invalidation_fence_signal(struct xe_device *xe, struct xe_gt_tlb_invalidation_fe __invalidation_fence_signal(xe, fence); } +void xe_gt_tlb_invalidation_fence_signal(struct xe_gt_tlb_invalidation_fence *fence) +{ + if (WARN_ON_ONCE(!fence->gt)) + return; + + __invalidation_fence_signal(gt_to_xe(fence->gt), fence); +} + static void xe_gt_tlb_fence_timeout(struct work_struct *work) { struct xe_gt *gt = container_of(work, struct xe_gt, diff --git a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h index f430d5797af7..00b1c6c01e8d 100644 --- a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h +++ b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h @@ -28,6 +28,7 @@ int xe_guc_tlb_invalidation_done_handler(struct xe_guc *guc, u32 *msg, u32 len); void xe_gt_tlb_invalidation_fence_init(struct xe_gt *gt, struct xe_gt_tlb_invalidation_fence *fence, bool stack); +void xe_gt_tlb_invalidation_fence_signal(struct xe_gt_tlb_invalidation_fence *fence); static inline void xe_gt_tlb_invalidation_fence_wait(struct xe_gt_tlb_invalidation_fence *fence) diff --git a/drivers/gpu/drm/xe/xe_pt.c b/drivers/gpu/drm/xe/xe_pt.c index f27f579f4d85..797576690356 100644 --- a/drivers/gpu/drm/xe/xe_pt.c +++ b/drivers/gpu/drm/xe/xe_pt.c @@ -1333,8 +1333,7 @@ static void invalidation_fence_cb(struct dma_fence *fence, queue_work(system_wq, &ifence->work); } else { ifence->base.base.error = ifence->fence->error; - dma_fence_signal(&ifence->base.base); - dma_fence_put(&ifence->base.base); + xe_gt_tlb_invalidation_fence_signal(&ifence->base); } dma_fence_put(ifence->fence); } diff --git a/drivers/gpu/drm/xe/xe_reg_sr.c b/drivers/gpu/drm/xe/xe_reg_sr.c index 440ac572f6e5..52969c090965 100644 --- a/drivers/gpu/drm/xe/xe_reg_sr.c +++ b/drivers/gpu/drm/xe/xe_reg_sr.c @@ -26,46 +26,27 @@ #include "xe_reg_whitelist.h" #include "xe_rtp_types.h" -#define XE_REG_SR_GROW_STEP_DEFAULT 16 - static void reg_sr_fini(struct drm_device *drm, void *arg) { struct xe_reg_sr *sr = arg; + struct xe_reg_sr_entry *entry; + unsigned long reg; + + xa_for_each(&sr->xa, reg, entry) + kfree(entry); xa_destroy(&sr->xa); - kfree(sr->pool.arr); - memset(&sr->pool, 0, sizeof(sr->pool)); } int xe_reg_sr_init(struct xe_reg_sr *sr, const char *name, struct xe_device *xe) { xa_init(&sr->xa); - memset(&sr->pool, 0, sizeof(sr->pool)); - sr->pool.grow_step = XE_REG_SR_GROW_STEP_DEFAULT; sr->name = name; return drmm_add_action_or_reset(&xe->drm, reg_sr_fini, sr); } EXPORT_SYMBOL_IF_KUNIT(xe_reg_sr_init); -static struct xe_reg_sr_entry *alloc_entry(struct xe_reg_sr *sr) -{ - if (sr->pool.used == sr->pool.allocated) { - struct xe_reg_sr_entry *arr; - - arr = krealloc_array(sr->pool.arr, - ALIGN(sr->pool.allocated + 1, sr->pool.grow_step), - sizeof(*arr), GFP_KERNEL); - if (!arr) - return NULL; - - sr->pool.arr = arr; - sr->pool.allocated += sr->pool.grow_step; - } - - return &sr->pool.arr[sr->pool.used++]; -} - static bool compatible_entries(const struct xe_reg_sr_entry *e1, const struct xe_reg_sr_entry *e2) { @@ -111,7 +92,7 @@ int xe_reg_sr_add(struct xe_reg_sr *sr, return 0; } - pentry = alloc_entry(sr); + pentry = kmalloc(sizeof(*pentry), GFP_KERNEL); if (!pentry) { ret = -ENOMEM; goto fail; diff --git a/drivers/gpu/drm/xe/xe_reg_sr_types.h b/drivers/gpu/drm/xe/xe_reg_sr_types.h index ad48a52b824a..ebe11f237fa2 100644 --- a/drivers/gpu/drm/xe/xe_reg_sr_types.h +++ b/drivers/gpu/drm/xe/xe_reg_sr_types.h @@ -20,12 +20,6 @@ struct xe_reg_sr_entry { }; struct xe_reg_sr { - struct { - struct xe_reg_sr_entry *arr; - unsigned int used; - unsigned int allocated; - unsigned int grow_step; - } pool; struct xarray xa; const char *name; diff --git a/drivers/hv/hv_kvp.c b/drivers/hv/hv_kvp.c index d35b60c06114..77017d951826 100644 --- a/drivers/hv/hv_kvp.c +++ b/drivers/hv/hv_kvp.c @@ -767,6 +767,12 @@ hv_kvp_init(struct hv_util_service *srv) */ kvp_transaction.state = HVUTIL_DEVICE_INIT; + return 0; +} + +int +hv_kvp_init_transport(void) +{ hvt = hvutil_transport_init(kvp_devname, CN_KVP_IDX, CN_KVP_VAL, kvp_on_msg, kvp_on_reset); if (!hvt) diff --git a/drivers/hv/hv_snapshot.c b/drivers/hv/hv_snapshot.c index 0d2184be1691..397f4c8fa46c 100644 --- a/drivers/hv/hv_snapshot.c +++ b/drivers/hv/hv_snapshot.c @@ -388,6 +388,12 @@ hv_vss_init(struct hv_util_service *srv) */ vss_transaction.state = HVUTIL_DEVICE_INIT; + return 0; +} + +int +hv_vss_init_transport(void) +{ hvt = hvutil_transport_init(vss_devname, CN_VSS_IDX, CN_VSS_VAL, vss_on_msg, vss_on_reset); if (!hvt) { diff --git a/drivers/hv/hv_util.c b/drivers/hv/hv_util.c index c4f525325790..3d9360fd909a 100644 --- a/drivers/hv/hv_util.c +++ b/drivers/hv/hv_util.c @@ -141,6 +141,7 @@ static struct hv_util_service util_heartbeat = { static struct hv_util_service util_kvp = { .util_cb = hv_kvp_onchannelcallback, .util_init = hv_kvp_init, + .util_init_transport = hv_kvp_init_transport, .util_pre_suspend = hv_kvp_pre_suspend, .util_pre_resume = hv_kvp_pre_resume, .util_deinit = hv_kvp_deinit, @@ -149,6 +150,7 @@ static struct hv_util_service util_kvp = { static struct hv_util_service util_vss = { .util_cb = hv_vss_onchannelcallback, .util_init = hv_vss_init, + .util_init_transport = hv_vss_init_transport, .util_pre_suspend = hv_vss_pre_suspend, .util_pre_resume = hv_vss_pre_resume, .util_deinit = hv_vss_deinit, @@ -613,6 +615,13 @@ static int util_probe(struct hv_device *dev, if (ret) goto error; + if (srv->util_init_transport) { + ret = srv->util_init_transport(); + if (ret) { + vmbus_close(dev->channel); + goto error; + } + } return 0; error: diff --git a/drivers/hv/hyperv_vmbus.h b/drivers/hv/hyperv_vmbus.h index d2856023d53c..52cb744b4d7f 100644 --- a/drivers/hv/hyperv_vmbus.h +++ b/drivers/hv/hyperv_vmbus.h @@ -370,12 +370,14 @@ void vmbus_on_event(unsigned long data); void vmbus_on_msg_dpc(unsigned long data); int hv_kvp_init(struct hv_util_service *srv); +int hv_kvp_init_transport(void); void hv_kvp_deinit(void); int hv_kvp_pre_suspend(void); int hv_kvp_pre_resume(void); void hv_kvp_onchannelcallback(void *context); int hv_vss_init(struct hv_util_service *srv); +int hv_vss_init_transport(void); void hv_vss_deinit(void); int hv_vss_pre_suspend(void); int hv_vss_pre_resume(void); diff --git a/drivers/hwmon/tmp513.c b/drivers/hwmon/tmp513.c index 926d28cd3fab..1c2cb12071b8 100644 --- a/drivers/hwmon/tmp513.c +++ b/drivers/hwmon/tmp513.c @@ -182,7 +182,7 @@ struct tmp51x_data { struct regmap *regmap; }; -// Set the shift based on the gain 8=4, 4=3, 2=2, 1=1 +// Set the shift based on the gain: 8 -> 1, 4 -> 2, 2 -> 3, 1 -> 4 static inline u8 tmp51x_get_pga_shift(struct tmp51x_data *data) { return 5 - ffs(data->pga_gain); @@ -204,7 +204,9 @@ static int tmp51x_get_value(struct tmp51x_data *data, u8 reg, u8 pos, * 2's complement number shifted by one to four depending * on the pga gain setting. 1lsb = 10uV */ - *val = sign_extend32(regval, 17 - tmp51x_get_pga_shift(data)); + *val = sign_extend32(regval, + reg == TMP51X_SHUNT_CURRENT_RESULT ? + 16 - tmp51x_get_pga_shift(data) : 15); *val = DIV_ROUND_CLOSEST(*val * 10 * MILLI, data->shunt_uohms); break; case TMP51X_BUS_VOLTAGE_RESULT: @@ -220,7 +222,7 @@ static int tmp51x_get_value(struct tmp51x_data *data, u8 reg, u8 pos, break; case TMP51X_BUS_CURRENT_RESULT: // Current = (ShuntVoltage * CalibrationRegister) / 4096 - *val = sign_extend32(regval, 16) * data->curr_lsb_ua; + *val = sign_extend32(regval, 15) * (long)data->curr_lsb_ua; *val = DIV_ROUND_CLOSEST(*val, MILLI); break; case TMP51X_LOCAL_TEMP_RESULT: @@ -232,7 +234,7 @@ static int tmp51x_get_value(struct tmp51x_data *data, u8 reg, u8 pos, case TMP51X_REMOTE_TEMP_LIMIT_2: case TMP513_REMOTE_TEMP_LIMIT_3: // 1lsb = 0.0625 degrees centigrade - *val = sign_extend32(regval, 16) >> TMP51X_TEMP_SHIFT; + *val = sign_extend32(regval, 15) >> TMP51X_TEMP_SHIFT; *val = DIV_ROUND_CLOSEST(*val * 625, 10); break; case TMP51X_N_FACTOR_AND_HYST_1: diff --git a/drivers/i2c/busses/i2c-imx.c b/drivers/i2c/busses/i2c-imx.c index 98539313cbc9..c5224d43eea4 100644 --- a/drivers/i2c/busses/i2c-imx.c +++ b/drivers/i2c/busses/i2c-imx.c @@ -282,6 +282,7 @@ static const struct of_device_id i2c_imx_dt_ids[] = { { .compatible = "fsl,imx6sll-i2c", .data = &imx6_i2c_hwdata, }, { .compatible = "fsl,imx6sx-i2c", .data = &imx6_i2c_hwdata, }, { .compatible = "fsl,imx6ul-i2c", .data = &imx6_i2c_hwdata, }, + { .compatible = "fsl,imx7d-i2c", .data = &imx6_i2c_hwdata, }, { .compatible = "fsl,imx7s-i2c", .data = &imx6_i2c_hwdata, }, { .compatible = "fsl,imx8mm-i2c", .data = &imx6_i2c_hwdata, }, { .compatible = "fsl,imx8mn-i2c", .data = &imx6_i2c_hwdata, }, diff --git a/drivers/i2c/busses/i2c-microchip-corei2c.c b/drivers/i2c/busses/i2c-microchip-corei2c.c index 0b0a1c4d17ca..b0a51695138a 100644 --- a/drivers/i2c/busses/i2c-microchip-corei2c.c +++ b/drivers/i2c/busses/i2c-microchip-corei2c.c @@ -93,27 +93,35 @@ * @base: pointer to register struct * @dev: device reference * @i2c_clk: clock reference for i2c input clock + * @msg_queue: pointer to the messages requiring sending * @buf: pointer to msg buffer for easier use * @msg_complete: xfer completion object * @adapter: core i2c abstraction * @msg_err: error code for completed message * @bus_clk_rate: current i2c bus clock rate * @isr_status: cached copy of local ISR status + * @total_num: total number of messages to be sent/received + * @current_num: index of the current message being sent/received * @msg_len: number of bytes transferred in msg * @addr: address of the current slave + * @restart_needed: whether or not a repeated start is required after current message */ struct mchp_corei2c_dev { void __iomem *base; struct device *dev; struct clk *i2c_clk; + struct i2c_msg *msg_queue; u8 *buf; struct completion msg_complete; struct i2c_adapter adapter; int msg_err; + int total_num; + int current_num; u32 bus_clk_rate; u32 isr_status; u16 msg_len; u8 addr; + bool restart_needed; }; static void mchp_corei2c_core_disable(struct mchp_corei2c_dev *idev) @@ -222,6 +230,47 @@ static int mchp_corei2c_fill_tx(struct mchp_corei2c_dev *idev) return 0; } +static void mchp_corei2c_next_msg(struct mchp_corei2c_dev *idev) +{ + struct i2c_msg *this_msg; + u8 ctrl; + + if (idev->current_num >= idev->total_num) { + complete(&idev->msg_complete); + return; + } + + /* + * If there's been an error, the isr needs to return control + * to the "main" part of the driver, so as not to keep sending + * messages once it completes and clears the SI bit. + */ + if (idev->msg_err) { + complete(&idev->msg_complete); + return; + } + + this_msg = idev->msg_queue++; + + if (idev->current_num < (idev->total_num - 1)) { + struct i2c_msg *next_msg = idev->msg_queue; + + idev->restart_needed = next_msg->flags & I2C_M_RD; + } else { + idev->restart_needed = false; + } + + idev->addr = i2c_8bit_addr_from_msg(this_msg); + idev->msg_len = this_msg->len; + idev->buf = this_msg->buf; + + ctrl = readb(idev->base + CORE_I2C_CTRL); + ctrl |= CTRL_STA; + writeb(ctrl, idev->base + CORE_I2C_CTRL); + + idev->current_num++; +} + static irqreturn_t mchp_corei2c_handle_isr(struct mchp_corei2c_dev *idev) { u32 status = idev->isr_status; @@ -238,8 +287,6 @@ static irqreturn_t mchp_corei2c_handle_isr(struct mchp_corei2c_dev *idev) ctrl &= ~CTRL_STA; writeb(idev->addr, idev->base + CORE_I2C_DATA); writeb(ctrl, idev->base + CORE_I2C_CTRL); - if (idev->msg_len == 0) - finished = true; break; case STATUS_M_ARB_LOST: idev->msg_err = -EAGAIN; @@ -247,10 +294,14 @@ static irqreturn_t mchp_corei2c_handle_isr(struct mchp_corei2c_dev *idev) break; case STATUS_M_SLAW_ACK: case STATUS_M_TX_DATA_ACK: - if (idev->msg_len > 0) + if (idev->msg_len > 0) { mchp_corei2c_fill_tx(idev); - else - last_byte = true; + } else { + if (idev->restart_needed) + finished = true; + else + last_byte = true; + } break; case STATUS_M_TX_DATA_NACK: case STATUS_M_SLAR_NACK: @@ -287,7 +338,7 @@ static irqreturn_t mchp_corei2c_handle_isr(struct mchp_corei2c_dev *idev) mchp_corei2c_stop(idev); if (last_byte || finished) - complete(&idev->msg_complete); + mchp_corei2c_next_msg(idev); return IRQ_HANDLED; } @@ -311,21 +362,48 @@ static irqreturn_t mchp_corei2c_isr(int irq, void *_dev) return ret; } -static int mchp_corei2c_xfer_msg(struct mchp_corei2c_dev *idev, - struct i2c_msg *msg) +static int mchp_corei2c_xfer(struct i2c_adapter *adap, struct i2c_msg *msgs, + int num) { - u8 ctrl; + struct mchp_corei2c_dev *idev = i2c_get_adapdata(adap); + struct i2c_msg *this_msg = msgs; unsigned long time_left; + u8 ctrl; + + mchp_corei2c_core_enable(idev); + + /* + * The isr controls the flow of a transfer, this info needs to be saved + * to a location that it can access the queue information from. + */ + idev->restart_needed = false; + idev->msg_queue = msgs; + idev->total_num = num; + idev->current_num = 0; - idev->addr = i2c_8bit_addr_from_msg(msg); - idev->msg_len = msg->len; - idev->buf = msg->buf; + /* + * But the first entry to the isr is triggered by the start in this + * function, so the first message needs to be "dequeued". + */ + idev->addr = i2c_8bit_addr_from_msg(this_msg); + idev->msg_len = this_msg->len; + idev->buf = this_msg->buf; idev->msg_err = 0; - reinit_completion(&idev->msg_complete); + if (idev->total_num > 1) { + struct i2c_msg *next_msg = msgs + 1; - mchp_corei2c_core_enable(idev); + idev->restart_needed = next_msg->flags & I2C_M_RD; + } + idev->current_num++; + idev->msg_queue++; + + reinit_completion(&idev->msg_complete); + + /* + * Send the first start to pass control to the isr + */ ctrl = readb(idev->base + CORE_I2C_CTRL); ctrl |= CTRL_STA; writeb(ctrl, idev->base + CORE_I2C_CTRL); @@ -335,20 +413,8 @@ static int mchp_corei2c_xfer_msg(struct mchp_corei2c_dev *idev, if (!time_left) return -ETIMEDOUT; - return idev->msg_err; -} - -static int mchp_corei2c_xfer(struct i2c_adapter *adap, struct i2c_msg *msgs, - int num) -{ - struct mchp_corei2c_dev *idev = i2c_get_adapdata(adap); - int i, ret; - - for (i = 0; i < num; i++) { - ret = mchp_corei2c_xfer_msg(idev, msgs++); - if (ret) - return ret; - } + if (idev->msg_err) + return idev->msg_err; return num; } diff --git a/drivers/i2c/busses/i2c-pnx.c b/drivers/i2c/busses/i2c-pnx.c index 1dafadda73af..135300f3b534 100644 --- a/drivers/i2c/busses/i2c-pnx.c +++ b/drivers/i2c/busses/i2c-pnx.c @@ -95,7 +95,7 @@ enum { static inline int wait_timeout(struct i2c_pnx_algo_data *data) { - long timeout = data->timeout; + long timeout = jiffies_to_msecs(data->timeout); while (timeout > 0 && (ioread32(I2C_REG_STS(data)) & mstatus_active)) { mdelay(1); @@ -106,7 +106,7 @@ static inline int wait_timeout(struct i2c_pnx_algo_data *data) static inline int wait_reset(struct i2c_pnx_algo_data *data) { - long timeout = data->timeout; + long timeout = jiffies_to_msecs(data->timeout); while (timeout > 0 && (ioread32(I2C_REG_CTL(data)) & mcntrl_reset)) { mdelay(1); diff --git a/drivers/i2c/busses/i2c-riic.c b/drivers/i2c/busses/i2c-riic.c index c7f3a4c02470..2c982199782f 100644 --- a/drivers/i2c/busses/i2c-riic.c +++ b/drivers/i2c/busses/i2c-riic.c @@ -352,7 +352,7 @@ static int riic_init_hw(struct riic_dev *riic) if (brl <= (0x1F + 3)) break; - total_ticks /= 2; + total_ticks = DIV_ROUND_UP(total_ticks, 2); rate /= 2; } diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c index 64ace0b968f0..91db10515d74 100644 --- a/drivers/infiniband/core/cma.c +++ b/drivers/infiniband/core/cma.c @@ -690,6 +690,7 @@ cma_validate_port(struct ib_device *device, u32 port, int bound_if_index = dev_addr->bound_dev_if; int dev_type = dev_addr->dev_type; struct net_device *ndev = NULL; + struct net_device *pdev = NULL; if (!rdma_dev_access_netns(device, id_priv->id.route.addr.dev_addr.net)) goto out; @@ -714,6 +715,21 @@ cma_validate_port(struct ib_device *device, u32 port, rcu_read_lock(); ndev = rcu_dereference(sgid_attr->ndev); + if (ndev->ifindex != bound_if_index) { + pdev = dev_get_by_index_rcu(dev_addr->net, bound_if_index); + if (pdev) { + if (is_vlan_dev(pdev)) { + pdev = vlan_dev_real_dev(pdev); + if (ndev->ifindex == pdev->ifindex) + bound_if_index = pdev->ifindex; + } + if (is_vlan_dev(ndev)) { + pdev = vlan_dev_real_dev(ndev); + if (bound_if_index == pdev->ifindex) + bound_if_index = ndev->ifindex; + } + } + } if (!net_eq(dev_net(ndev), dev_addr->net) || ndev->ifindex != bound_if_index) { rdma_put_gid_attr(sgid_attr); diff --git a/drivers/infiniband/core/nldev.c b/drivers/infiniband/core/nldev.c index 7dc8e2ec62cc..f12189986303 100644 --- a/drivers/infiniband/core/nldev.c +++ b/drivers/infiniband/core/nldev.c @@ -2802,8 +2802,8 @@ int rdma_nl_notify_event(struct ib_device *device, u32 port_num, enum rdma_nl_notify_event_type type) { struct sk_buff *skb; + int ret = -EMSGSIZE; struct net *net; - int ret = 0; void *nlh; net = read_pnet(&device->coredev.rdma_net); diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c index a4cce360df21..edef79daed3f 100644 --- a/drivers/infiniband/core/uverbs_cmd.c +++ b/drivers/infiniband/core/uverbs_cmd.c @@ -161,7 +161,7 @@ static const void __user *uverbs_request_next_ptr(struct uverbs_req_iter *iter, { const void __user *res = iter->cur; - if (iter->cur + len > iter->end) + if (len > iter->end - iter->cur) return (void __force __user *)ERR_PTR(-ENOSPC); iter->cur += len; return res; @@ -2010,11 +2010,13 @@ static int ib_uverbs_post_send(struct uverbs_attr_bundle *attrs) ret = uverbs_request_start(attrs, &iter, &cmd, sizeof(cmd)); if (ret) return ret; - wqes = uverbs_request_next_ptr(&iter, cmd.wqe_size * cmd.wr_count); + wqes = uverbs_request_next_ptr(&iter, size_mul(cmd.wqe_size, + cmd.wr_count)); if (IS_ERR(wqes)) return PTR_ERR(wqes); - sgls = uverbs_request_next_ptr( - &iter, cmd.sge_count * sizeof(struct ib_uverbs_sge)); + sgls = uverbs_request_next_ptr(&iter, + size_mul(cmd.sge_count, + sizeof(struct ib_uverbs_sge))); if (IS_ERR(sgls)) return PTR_ERR(sgls); ret = uverbs_request_finish(&iter); @@ -2200,11 +2202,11 @@ ib_uverbs_unmarshall_recv(struct uverbs_req_iter *iter, u32 wr_count, if (wqe_size < sizeof(struct ib_uverbs_recv_wr)) return ERR_PTR(-EINVAL); - wqes = uverbs_request_next_ptr(iter, wqe_size * wr_count); + wqes = uverbs_request_next_ptr(iter, size_mul(wqe_size, wr_count)); if (IS_ERR(wqes)) return ERR_CAST(wqes); - sgls = uverbs_request_next_ptr( - iter, sge_count * sizeof(struct ib_uverbs_sge)); + sgls = uverbs_request_next_ptr(iter, size_mul(sge_count, + sizeof(struct ib_uverbs_sge))); if (IS_ERR(sgls)) return ERR_CAST(sgls); ret = uverbs_request_finish(iter); diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.c b/drivers/infiniband/hw/bnxt_re/ib_verbs.c index 160096792224..b20cffcc3e7d 100644 --- a/drivers/infiniband/hw/bnxt_re/ib_verbs.c +++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.c @@ -156,7 +156,7 @@ int bnxt_re_query_device(struct ib_device *ibdev, ib_attr->vendor_id = rdev->en_dev->pdev->vendor; ib_attr->vendor_part_id = rdev->en_dev->pdev->device; - ib_attr->hw_ver = rdev->en_dev->pdev->subsystem_device; + ib_attr->hw_ver = rdev->en_dev->pdev->revision; ib_attr->max_qp = dev_attr->max_qp; ib_attr->max_qp_wr = dev_attr->max_qp_wqes; ib_attr->device_cap_flags = @@ -2107,18 +2107,20 @@ int bnxt_re_modify_qp(struct ib_qp *ib_qp, struct ib_qp_attr *qp_attr, } } - if (qp_attr_mask & IB_QP_PATH_MTU) { - qp->qplib_qp.modify_flags |= - CMDQ_MODIFY_QP_MODIFY_MASK_PATH_MTU; - qp->qplib_qp.path_mtu = __from_ib_mtu(qp_attr->path_mtu); - qp->qplib_qp.mtu = ib_mtu_enum_to_int(qp_attr->path_mtu); - } else if (qp_attr->qp_state == IB_QPS_RTR) { - qp->qplib_qp.modify_flags |= - CMDQ_MODIFY_QP_MODIFY_MASK_PATH_MTU; - qp->qplib_qp.path_mtu = - __from_ib_mtu(iboe_get_mtu(rdev->netdev->mtu)); - qp->qplib_qp.mtu = - ib_mtu_enum_to_int(iboe_get_mtu(rdev->netdev->mtu)); + if (qp_attr->qp_state == IB_QPS_RTR) { + enum ib_mtu qpmtu; + + qpmtu = iboe_get_mtu(rdev->netdev->mtu); + if (qp_attr_mask & IB_QP_PATH_MTU) { + if (ib_mtu_enum_to_int(qp_attr->path_mtu) > + ib_mtu_enum_to_int(qpmtu)) + return -EINVAL; + qpmtu = qp_attr->path_mtu; + } + + qp->qplib_qp.modify_flags |= CMDQ_MODIFY_QP_MODIFY_MASK_PATH_MTU; + qp->qplib_qp.path_mtu = __from_ib_mtu(qpmtu); + qp->qplib_qp.mtu = ib_mtu_enum_to_int(qpmtu); } if (qp_attr_mask & IB_QP_TIMEOUT) { @@ -2763,7 +2765,8 @@ bad: wr = wr->next; } bnxt_qplib_post_send_db(&qp->qplib_qp); - bnxt_ud_qp_hw_stall_workaround(qp); + if (!bnxt_qplib_is_chip_gen_p5_p7(qp->rdev->chip_ctx)) + bnxt_ud_qp_hw_stall_workaround(qp); spin_unlock_irqrestore(&qp->sq_lock, flags); return rc; } @@ -2875,7 +2878,8 @@ bad: wr = wr->next; } bnxt_qplib_post_send_db(&qp->qplib_qp); - bnxt_ud_qp_hw_stall_workaround(qp); + if (!bnxt_qplib_is_chip_gen_p5_p7(qp->rdev->chip_ctx)) + bnxt_ud_qp_hw_stall_workaround(qp); spin_unlock_irqrestore(&qp->sq_lock, flags); return rc; diff --git a/drivers/infiniband/hw/bnxt_re/main.c b/drivers/infiniband/hw/bnxt_re/main.c index 2ac8ddbed576..8abd1b723f8f 100644 --- a/drivers/infiniband/hw/bnxt_re/main.c +++ b/drivers/infiniband/hw/bnxt_re/main.c @@ -1435,11 +1435,8 @@ static bool bnxt_re_is_qp1_or_shadow_qp(struct bnxt_re_dev *rdev, static void bnxt_re_dev_stop(struct bnxt_re_dev *rdev) { - int mask = IB_QP_STATE; - struct ib_qp_attr qp_attr; struct bnxt_re_qp *qp; - qp_attr.qp_state = IB_QPS_ERR; mutex_lock(&rdev->qp_lock); list_for_each_entry(qp, &rdev->qp_list, list) { /* Modify the state of all QPs except QP1/Shadow QP */ @@ -1447,12 +1444,9 @@ static void bnxt_re_dev_stop(struct bnxt_re_dev *rdev) if (qp->qplib_qp.state != CMDQ_MODIFY_QP_NEW_STATE_RESET && qp->qplib_qp.state != - CMDQ_MODIFY_QP_NEW_STATE_ERR) { + CMDQ_MODIFY_QP_NEW_STATE_ERR) bnxt_re_dispatch_event(&rdev->ibdev, &qp->ib_qp, 1, IB_EVENT_QP_FATAL); - bnxt_re_modify_qp(&qp->ib_qp, &qp_attr, mask, - NULL); - } } } mutex_unlock(&rdev->qp_lock); diff --git a/drivers/infiniband/hw/bnxt_re/qplib_fp.c b/drivers/infiniband/hw/bnxt_re/qplib_fp.c index 7ad83566ab0f..828e2f980801 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_fp.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_fp.c @@ -658,13 +658,6 @@ int bnxt_qplib_create_srq(struct bnxt_qplib_res *res, rc = bnxt_qplib_alloc_init_hwq(&srq->hwq, &hwq_attr); if (rc) return rc; - - srq->swq = kcalloc(srq->hwq.max_elements, sizeof(*srq->swq), - GFP_KERNEL); - if (!srq->swq) { - rc = -ENOMEM; - goto fail; - } srq->dbinfo.flags = 0; bnxt_qplib_rcfw_cmd_prep((struct cmdq_base *)&req, CMDQ_BASE_OPCODE_CREATE_SRQ, @@ -693,9 +686,17 @@ int bnxt_qplib_create_srq(struct bnxt_qplib_res *res, spin_lock_init(&srq->lock); srq->start_idx = 0; srq->last_idx = srq->hwq.max_elements - 1; - for (idx = 0; idx < srq->hwq.max_elements; idx++) - srq->swq[idx].next_idx = idx + 1; - srq->swq[srq->last_idx].next_idx = -1; + if (!srq->hwq.is_user) { + srq->swq = kcalloc(srq->hwq.max_elements, sizeof(*srq->swq), + GFP_KERNEL); + if (!srq->swq) { + rc = -ENOMEM; + goto fail; + } + for (idx = 0; idx < srq->hwq.max_elements; idx++) + srq->swq[idx].next_idx = idx + 1; + srq->swq[srq->last_idx].next_idx = -1; + } srq->id = le32_to_cpu(resp.xid); srq->dbinfo.hwq = &srq->hwq; @@ -999,9 +1000,7 @@ int bnxt_qplib_create_qp(struct bnxt_qplib_res *res, struct bnxt_qplib_qp *qp) u32 tbl_indx; u16 nsge; - if (res->dattr) - qp->is_host_msn_tbl = _is_host_msn_table(res->dattr->dev_cap_flags2); - + qp->is_host_msn_tbl = _is_host_msn_table(res->dattr->dev_cap_flags2); sq->dbinfo.flags = 0; bnxt_qplib_rcfw_cmd_prep((struct cmdq_base *)&req, CMDQ_BASE_OPCODE_CREATE_QP, @@ -1033,7 +1032,12 @@ int bnxt_qplib_create_qp(struct bnxt_qplib_res *res, struct bnxt_qplib_qp *qp) : 0; /* Update msn tbl size */ if (qp->is_host_msn_tbl && psn_sz) { - hwq_attr.aux_depth = roundup_pow_of_two(bnxt_qplib_set_sq_size(sq, qp->wqe_mode)); + if (qp->wqe_mode == BNXT_QPLIB_WQE_MODE_STATIC) + hwq_attr.aux_depth = + roundup_pow_of_two(bnxt_qplib_set_sq_size(sq, qp->wqe_mode)); + else + hwq_attr.aux_depth = + roundup_pow_of_two(bnxt_qplib_set_sq_size(sq, qp->wqe_mode)) / 2; qp->msn_tbl_sz = hwq_attr.aux_depth; qp->msn = 0; } @@ -1043,13 +1047,14 @@ int bnxt_qplib_create_qp(struct bnxt_qplib_res *res, struct bnxt_qplib_qp *qp) if (rc) return rc; - rc = bnxt_qplib_alloc_init_swq(sq); - if (rc) - goto fail_sq; - - if (psn_sz) - bnxt_qplib_init_psn_ptr(qp, psn_sz); + if (!sq->hwq.is_user) { + rc = bnxt_qplib_alloc_init_swq(sq); + if (rc) + goto fail_sq; + if (psn_sz) + bnxt_qplib_init_psn_ptr(qp, psn_sz); + } req.sq_size = cpu_to_le32(bnxt_qplib_set_sq_size(sq, qp->wqe_mode)); pbl = &sq->hwq.pbl[PBL_LVL_0]; req.sq_pbl = cpu_to_le64(pbl->pg_map_arr[0]); @@ -1075,9 +1080,11 @@ int bnxt_qplib_create_qp(struct bnxt_qplib_res *res, struct bnxt_qplib_qp *qp) rc = bnxt_qplib_alloc_init_hwq(&rq->hwq, &hwq_attr); if (rc) goto sq_swq; - rc = bnxt_qplib_alloc_init_swq(rq); - if (rc) - goto fail_rq; + if (!rq->hwq.is_user) { + rc = bnxt_qplib_alloc_init_swq(rq); + if (rc) + goto fail_rq; + } req.rq_size = cpu_to_le32(rq->max_wqe); pbl = &rq->hwq.pbl[PBL_LVL_0]; @@ -1173,9 +1180,11 @@ int bnxt_qplib_create_qp(struct bnxt_qplib_res *res, struct bnxt_qplib_qp *qp) rq->dbinfo.db = qp->dpi->dbr; rq->dbinfo.max_slot = bnxt_qplib_set_rq_max_slot(rq->wqe_size); } + spin_lock_bh(&rcfw->tbl_lock); tbl_indx = map_qp_id_to_tbl_indx(qp->id, rcfw); rcfw->qp_tbl[tbl_indx].qp_id = qp->id; rcfw->qp_tbl[tbl_indx].qp_handle = (void *)qp; + spin_unlock_bh(&rcfw->tbl_lock); return 0; fail: @@ -2596,10 +2605,12 @@ static int bnxt_qplib_cq_process_req(struct bnxt_qplib_cq *cq, bnxt_qplib_add_flush_qp(qp); } else { /* Before we complete, do WA 9060 */ - if (do_wa9060(qp, cq, cq_cons, sq->swq_last, - cqe_sq_cons)) { - *lib_qp = qp; - goto out; + if (!bnxt_qplib_is_chip_gen_p5_p7(qp->cctx)) { + if (do_wa9060(qp, cq, cq_cons, sq->swq_last, + cqe_sq_cons)) { + *lib_qp = qp; + goto out; + } } if (swq->flags & SQ_SEND_FLAGS_SIGNAL_COMP) { cqe->status = CQ_REQ_STATUS_OK; diff --git a/drivers/infiniband/hw/bnxt_re/qplib_fp.h b/drivers/infiniband/hw/bnxt_re/qplib_fp.h index f55958e5fddb..d8c71c024613 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_fp.h +++ b/drivers/infiniband/hw/bnxt_re/qplib_fp.h @@ -114,7 +114,6 @@ struct bnxt_qplib_sge { u32 size; }; -#define BNXT_QPLIB_QP_MAX_SGL 6 struct bnxt_qplib_swq { u64 wr_id; int next_idx; @@ -154,7 +153,7 @@ struct bnxt_qplib_swqe { #define BNXT_QPLIB_SWQE_FLAGS_UC_FENCE BIT(2) #define BNXT_QPLIB_SWQE_FLAGS_SOLICIT_EVENT BIT(3) #define BNXT_QPLIB_SWQE_FLAGS_INLINE BIT(4) - struct bnxt_qplib_sge sg_list[BNXT_QPLIB_QP_MAX_SGL]; + struct bnxt_qplib_sge sg_list[BNXT_VAR_MAX_SGE]; int num_sge; /* Max inline data is 96 bytes */ u32 inline_len; diff --git a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c index e82bd37158ad..7a099580ca8b 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c @@ -424,7 +424,8 @@ static int __send_message_basic_sanity(struct bnxt_qplib_rcfw *rcfw, /* Prevent posting if f/w is not in a state to process */ if (test_bit(ERR_DEVICE_DETACHED, &rcfw->cmdq.flags)) - return bnxt_qplib_map_rc(opcode); + return -ENXIO; + if (test_bit(FIRMWARE_STALL_DETECTED, &cmdq->flags)) return -ETIMEDOUT; @@ -493,7 +494,7 @@ static int __bnxt_qplib_rcfw_send_message(struct bnxt_qplib_rcfw *rcfw, rc = __send_message_basic_sanity(rcfw, msg, opcode); if (rc) - return rc; + return rc == -ENXIO ? bnxt_qplib_map_rc(opcode) : rc; rc = __send_message(rcfw, msg, opcode); if (rc) diff --git a/drivers/infiniband/hw/bnxt_re/qplib_sp.c b/drivers/infiniband/hw/bnxt_re/qplib_sp.c index e29fbbdab9fd..3cca7b1395f6 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_sp.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_sp.c @@ -129,12 +129,18 @@ int bnxt_qplib_get_dev_attr(struct bnxt_qplib_rcfw *rcfw, attr->max_qp_init_rd_atom = sb->max_qp_init_rd_atom > BNXT_QPLIB_MAX_OUT_RD_ATOM ? BNXT_QPLIB_MAX_OUT_RD_ATOM : sb->max_qp_init_rd_atom; - attr->max_qp_wqes = le16_to_cpu(sb->max_qp_wr); - /* - * 128 WQEs needs to be reserved for the HW (8916). Prevent - * reporting the max number - */ - attr->max_qp_wqes -= BNXT_QPLIB_RESERVED_QP_WRS + 1; + attr->max_qp_wqes = le16_to_cpu(sb->max_qp_wr) - 1; + if (!bnxt_qplib_is_chip_gen_p5_p7(rcfw->res->cctx)) { + /* + * 128 WQEs needs to be reserved for the HW (8916). Prevent + * reporting the max number on legacy devices + */ + attr->max_qp_wqes -= BNXT_QPLIB_RESERVED_QP_WRS + 1; + } + + /* Adjust for max_qp_wqes for variable wqe */ + if (cctx->modes.wqe_mode == BNXT_QPLIB_WQE_MODE_VARIABLE) + attr->max_qp_wqes = BNXT_VAR_MAX_WQE - 1; attr->max_qp_sges = cctx->modes.wqe_mode == BNXT_QPLIB_WQE_MODE_VARIABLE ? min_t(u32, sb->max_sge_var_wqe, BNXT_VAR_MAX_SGE) : 6; diff --git a/drivers/infiniband/hw/hns/hns_roce_hem.c b/drivers/infiniband/hw/hns/hns_roce_hem.c index f84521be3bea..605562122ecc 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hem.c +++ b/drivers/infiniband/hw/hns/hns_roce_hem.c @@ -931,6 +931,7 @@ struct hns_roce_hem_item { size_t count; /* max ba numbers */ int start; /* start buf offset in this hem */ int end; /* end buf offset in this hem */ + bool exist_bt; }; /* All HEM items are linked in a tree structure */ @@ -959,6 +960,7 @@ hem_list_alloc_item(struct hns_roce_dev *hr_dev, int start, int end, int count, } } + hem->exist_bt = exist_bt; hem->count = count; hem->start = start; hem->end = end; @@ -969,22 +971,22 @@ hem_list_alloc_item(struct hns_roce_dev *hr_dev, int start, int end, int count, } static void hem_list_free_item(struct hns_roce_dev *hr_dev, - struct hns_roce_hem_item *hem, bool exist_bt) + struct hns_roce_hem_item *hem) { - if (exist_bt) + if (hem->exist_bt) dma_free_coherent(hr_dev->dev, hem->count * BA_BYTE_LEN, hem->addr, hem->dma_addr); kfree(hem); } static void hem_list_free_all(struct hns_roce_dev *hr_dev, - struct list_head *head, bool exist_bt) + struct list_head *head) { struct hns_roce_hem_item *hem, *temp_hem; list_for_each_entry_safe(hem, temp_hem, head, list) { list_del(&hem->list); - hem_list_free_item(hr_dev, hem, exist_bt); + hem_list_free_item(hr_dev, hem); } } @@ -1084,6 +1086,10 @@ int hns_roce_hem_list_calc_root_ba(const struct hns_roce_buf_region *regions, for (i = 0; i < region_cnt; i++) { r = (struct hns_roce_buf_region *)®ions[i]; + /* when r->hopnum = 0, the region should not occupy root_ba. */ + if (!r->hopnum) + continue; + if (r->hopnum > 1) { step = hem_list_calc_ba_range(r->hopnum, 1, unit); if (step > 0) @@ -1177,7 +1183,7 @@ static int hem_list_alloc_mid_bt(struct hns_roce_dev *hr_dev, err_exit: for (level = 1; level < hopnum; level++) - hem_list_free_all(hr_dev, &temp_list[level], true); + hem_list_free_all(hr_dev, &temp_list[level]); return ret; } @@ -1218,16 +1224,26 @@ static int alloc_fake_root_bt(struct hns_roce_dev *hr_dev, void *cpu_base, { struct hns_roce_hem_item *hem; + /* This is on the has_mtt branch, if r->hopnum + * is 0, there is no root_ba to reuse for the + * region's fake hem, so a dma_alloc request is + * necessary here. + */ hem = hem_list_alloc_item(hr_dev, r->offset, r->offset + r->count - 1, - r->count, false); + r->count, !r->hopnum); if (!hem) return -ENOMEM; - hem_list_assign_bt(hem, cpu_base, phy_base); + /* The root_ba can be reused only when r->hopnum > 0. */ + if (r->hopnum) + hem_list_assign_bt(hem, cpu_base, phy_base); list_add(&hem->list, branch_head); list_add(&hem->sibling, leaf_head); - return r->count; + /* If r->hopnum == 0, 0 is returned, + * so that the root_bt entry is not occupied. + */ + return r->hopnum ? r->count : 0; } static int setup_middle_bt(struct hns_roce_dev *hr_dev, void *cpu_base, @@ -1271,7 +1287,7 @@ setup_root_hem(struct hns_roce_dev *hr_dev, struct hns_roce_hem_list *hem_list, return -ENOMEM; total = 0; - for (i = 0; i < region_cnt && total < max_ba_num; i++) { + for (i = 0; i < region_cnt && total <= max_ba_num; i++) { r = ®ions[i]; if (!r->count) continue; @@ -1337,9 +1353,9 @@ static int hem_list_alloc_root_bt(struct hns_roce_dev *hr_dev, region_cnt); if (ret) { for (i = 0; i < region_cnt; i++) - hem_list_free_all(hr_dev, &head.branch[i], false); + hem_list_free_all(hr_dev, &head.branch[i]); - hem_list_free_all(hr_dev, &head.root, true); + hem_list_free_all(hr_dev, &head.root); } return ret; @@ -1402,10 +1418,9 @@ void hns_roce_hem_list_release(struct hns_roce_dev *hr_dev, for (i = 0; i < HNS_ROCE_MAX_BT_REGION; i++) for (j = 0; j < HNS_ROCE_MAX_BT_LEVEL; j++) - hem_list_free_all(hr_dev, &hem_list->mid_bt[i][j], - j != 0); + hem_list_free_all(hr_dev, &hem_list->mid_bt[i][j]); - hem_list_free_all(hr_dev, &hem_list->root_bt, true); + hem_list_free_all(hr_dev, &hem_list->root_bt); INIT_LIST_HEAD(&hem_list->btm_bt); hem_list->root_ba = 0; } diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c index 697b17cca02e..0144e7210d05 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c @@ -468,7 +468,7 @@ static inline int set_ud_wqe(struct hns_roce_qp *qp, valid_num_sge = calc_wr_sge_num(wr, &msg_len); ret = set_ud_opcode(ud_sq_wqe, wr); - if (WARN_ON(ret)) + if (WARN_ON_ONCE(ret)) return ret; ud_sq_wqe->msg_len = cpu_to_le32(msg_len); @@ -572,7 +572,7 @@ static inline int set_rc_wqe(struct hns_roce_qp *qp, rc_sq_wqe->msg_len = cpu_to_le32(msg_len); ret = set_rc_opcode(hr_dev, rc_sq_wqe, wr); - if (WARN_ON(ret)) + if (WARN_ON_ONCE(ret)) return ret; hr_reg_write(rc_sq_wqe, RC_SEND_WQE_SO, @@ -670,6 +670,10 @@ static void write_dwqe(struct hns_roce_dev *hr_dev, struct hns_roce_qp *qp, #define HNS_ROCE_SL_SHIFT 2 struct hns_roce_v2_rc_send_wqe *rc_sq_wqe = wqe; + if (unlikely(qp->state == IB_QPS_ERR)) { + flush_cqe(hr_dev, qp); + return; + } /* All kinds of DirectWQE have the same header field layout */ hr_reg_enable(rc_sq_wqe, RC_SEND_WQE_FLAG); hr_reg_write(rc_sq_wqe, RC_SEND_WQE_DB_SL_L, qp->sl); @@ -5619,6 +5623,9 @@ static void put_dip_ctx_idx(struct hns_roce_dev *hr_dev, { struct hns_roce_dip *hr_dip = hr_qp->dip; + if (!hr_dip) + return; + xa_lock(&hr_dev->qp_table.dip_xa); hr_dip->qp_cnt--; diff --git a/drivers/infiniband/hw/hns/hns_roce_mr.c b/drivers/infiniband/hw/hns/hns_roce_mr.c index bf30b3a65a9b..55b9283bfc6f 100644 --- a/drivers/infiniband/hw/hns/hns_roce_mr.c +++ b/drivers/infiniband/hw/hns/hns_roce_mr.c @@ -814,11 +814,6 @@ int hns_roce_mtr_map(struct hns_roce_dev *hr_dev, struct hns_roce_mtr *mtr, for (i = 0, mapped_cnt = 0; i < mtr->hem_cfg.region_count && mapped_cnt < page_cnt; i++) { r = &mtr->hem_cfg.region[i]; - /* if hopnum is 0, no need to map pages in this region */ - if (!r->hopnum) { - mapped_cnt += r->count; - continue; - } if (r->offset + r->count > page_cnt) { ret = -EINVAL; diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index ac20ab3bbabf..8c47cb4edd0a 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -2831,7 +2831,7 @@ static int mlx5_ib_get_plane_num(struct mlx5_core_dev *mdev, u8 *num_plane) int err; *num_plane = 0; - if (!MLX5_CAP_GEN(mdev, ib_virt)) + if (!MLX5_CAP_GEN(mdev, ib_virt) || !MLX5_CAP_GEN_2(mdev, multiplane)) return 0; err = mlx5_query_hca_vport_context(mdev, 0, 1, 0, &vport_ctx); @@ -3631,7 +3631,8 @@ static int mlx5_ib_init_multiport_master(struct mlx5_ib_dev *dev) list_for_each_entry(mpi, &mlx5_ib_unaffiliated_port_list, list) { if (dev->sys_image_guid == mpi->sys_image_guid && - (mlx5_core_native_port_num(mpi->mdev) - 1) == i) { + (mlx5_core_native_port_num(mpi->mdev) - 1) == i && + mlx5_core_same_coredev_type(dev->mdev, mpi->mdev)) { bound = mlx5_ib_bind_slave_port(dev, mpi); } @@ -4776,7 +4777,8 @@ static int mlx5r_mp_probe(struct auxiliary_device *adev, mutex_lock(&mlx5_ib_multiport_mutex); list_for_each_entry(dev, &mlx5_ib_dev_list, ib_dev_list) { - if (dev->sys_image_guid == mpi->sys_image_guid) + if (dev->sys_image_guid == mpi->sys_image_guid && + mlx5_core_same_coredev_type(dev->mdev, mpi->mdev)) bound = mlx5_ib_bind_slave_port(dev, mpi); if (bound) { diff --git a/drivers/infiniband/sw/rxe/rxe.c b/drivers/infiniband/sw/rxe/rxe.c index 255677bc12b2..1ba4a0c8726a 100644 --- a/drivers/infiniband/sw/rxe/rxe.c +++ b/drivers/infiniband/sw/rxe/rxe.c @@ -40,6 +40,8 @@ void rxe_dealloc(struct ib_device *ib_dev) /* initialize rxe device parameters */ static void rxe_init_device_param(struct rxe_dev *rxe) { + struct net_device *ndev; + rxe->max_inline_data = RXE_MAX_INLINE_DATA; rxe->attr.vendor_id = RXE_VENDOR_ID; @@ -71,8 +73,15 @@ static void rxe_init_device_param(struct rxe_dev *rxe) rxe->attr.max_fast_reg_page_list_len = RXE_MAX_FMR_PAGE_LIST_LEN; rxe->attr.max_pkeys = RXE_MAX_PKEYS; rxe->attr.local_ca_ack_delay = RXE_LOCAL_CA_ACK_DELAY; + + ndev = rxe_ib_device_get_netdev(&rxe->ib_dev); + if (!ndev) + return; + addrconf_addr_eui48((unsigned char *)&rxe->attr.sys_image_guid, - rxe->ndev->dev_addr); + ndev->dev_addr); + + dev_put(ndev); rxe->max_ucontext = RXE_MAX_UCONTEXT; } @@ -109,10 +118,15 @@ static void rxe_init_port_param(struct rxe_port *port) static void rxe_init_ports(struct rxe_dev *rxe) { struct rxe_port *port = &rxe->port; + struct net_device *ndev; rxe_init_port_param(port); + ndev = rxe_ib_device_get_netdev(&rxe->ib_dev); + if (!ndev) + return; addrconf_addr_eui48((unsigned char *)&port->port_guid, - rxe->ndev->dev_addr); + ndev->dev_addr); + dev_put(ndev); spin_lock_init(&port->port_lock); } @@ -167,12 +181,13 @@ void rxe_set_mtu(struct rxe_dev *rxe, unsigned int ndev_mtu) /* called by ifc layer to create new rxe device. * The caller should allocate memory for rxe by calling ib_alloc_device. */ -int rxe_add(struct rxe_dev *rxe, unsigned int mtu, const char *ibdev_name) +int rxe_add(struct rxe_dev *rxe, unsigned int mtu, const char *ibdev_name, + struct net_device *ndev) { rxe_init(rxe); rxe_set_mtu(rxe, mtu); - return rxe_register_device(rxe, ibdev_name); + return rxe_register_device(rxe, ibdev_name, ndev); } static int rxe_newlink(const char *ibdev_name, struct net_device *ndev) diff --git a/drivers/infiniband/sw/rxe/rxe.h b/drivers/infiniband/sw/rxe/rxe.h index d8fb2c7af30a..fe7f97066732 100644 --- a/drivers/infiniband/sw/rxe/rxe.h +++ b/drivers/infiniband/sw/rxe/rxe.h @@ -139,7 +139,8 @@ enum resp_states { void rxe_set_mtu(struct rxe_dev *rxe, unsigned int dev_mtu); -int rxe_add(struct rxe_dev *rxe, unsigned int mtu, const char *ibdev_name); +int rxe_add(struct rxe_dev *rxe, unsigned int mtu, const char *ibdev_name, + struct net_device *ndev); void rxe_rcv(struct sk_buff *skb); diff --git a/drivers/infiniband/sw/rxe/rxe_mcast.c b/drivers/infiniband/sw/rxe/rxe_mcast.c index 86cc2e18a7fd..07ff47bae31d 100644 --- a/drivers/infiniband/sw/rxe/rxe_mcast.c +++ b/drivers/infiniband/sw/rxe/rxe_mcast.c @@ -31,10 +31,19 @@ static int rxe_mcast_add(struct rxe_dev *rxe, union ib_gid *mgid) { unsigned char ll_addr[ETH_ALEN]; + struct net_device *ndev; + int ret; + + ndev = rxe_ib_device_get_netdev(&rxe->ib_dev); + if (!ndev) + return -ENODEV; ipv6_eth_mc_map((struct in6_addr *)mgid->raw, ll_addr); - return dev_mc_add(rxe->ndev, ll_addr); + ret = dev_mc_add(ndev, ll_addr); + dev_put(ndev); + + return ret; } /** @@ -47,10 +56,19 @@ static int rxe_mcast_add(struct rxe_dev *rxe, union ib_gid *mgid) static int rxe_mcast_del(struct rxe_dev *rxe, union ib_gid *mgid) { unsigned char ll_addr[ETH_ALEN]; + struct net_device *ndev; + int ret; + + ndev = rxe_ib_device_get_netdev(&rxe->ib_dev); + if (!ndev) + return -ENODEV; ipv6_eth_mc_map((struct in6_addr *)mgid->raw, ll_addr); - return dev_mc_del(rxe->ndev, ll_addr); + ret = dev_mc_del(ndev, ll_addr); + dev_put(ndev); + + return ret; } /** diff --git a/drivers/infiniband/sw/rxe/rxe_net.c b/drivers/infiniband/sw/rxe/rxe_net.c index 75d1407db52d..8cc64ceeb356 100644 --- a/drivers/infiniband/sw/rxe/rxe_net.c +++ b/drivers/infiniband/sw/rxe/rxe_net.c @@ -524,7 +524,16 @@ out: */ const char *rxe_parent_name(struct rxe_dev *rxe, unsigned int port_num) { - return rxe->ndev->name; + struct net_device *ndev; + char *ndev_name; + + ndev = rxe_ib_device_get_netdev(&rxe->ib_dev); + if (!ndev) + return NULL; + ndev_name = ndev->name; + dev_put(ndev); + + return ndev_name; } int rxe_net_add(const char *ibdev_name, struct net_device *ndev) @@ -536,10 +545,9 @@ int rxe_net_add(const char *ibdev_name, struct net_device *ndev) if (!rxe) return -ENOMEM; - rxe->ndev = ndev; ib_mark_name_assigned_by_user(&rxe->ib_dev); - err = rxe_add(rxe, ndev->mtu, ibdev_name); + err = rxe_add(rxe, ndev->mtu, ibdev_name, ndev); if (err) { ib_dealloc_device(&rxe->ib_dev); return err; @@ -587,10 +595,18 @@ void rxe_port_down(struct rxe_dev *rxe) void rxe_set_port_state(struct rxe_dev *rxe) { - if (netif_running(rxe->ndev) && netif_carrier_ok(rxe->ndev)) + struct net_device *ndev; + + ndev = rxe_ib_device_get_netdev(&rxe->ib_dev); + if (!ndev) + return; + + if (netif_running(ndev) && netif_carrier_ok(ndev)) rxe_port_up(rxe); else rxe_port_down(rxe); + + dev_put(ndev); } static int rxe_notify(struct notifier_block *not_blk, diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.c b/drivers/infiniband/sw/rxe/rxe_verbs.c index 5c18f7e342f2..8a5fc20fd186 100644 --- a/drivers/infiniband/sw/rxe/rxe_verbs.c +++ b/drivers/infiniband/sw/rxe/rxe_verbs.c @@ -41,6 +41,7 @@ static int rxe_query_port(struct ib_device *ibdev, u32 port_num, struct ib_port_attr *attr) { struct rxe_dev *rxe = to_rdev(ibdev); + struct net_device *ndev; int err, ret; if (port_num != 1) { @@ -49,6 +50,12 @@ static int rxe_query_port(struct ib_device *ibdev, goto err_out; } + ndev = rxe_ib_device_get_netdev(ibdev); + if (!ndev) { + err = -ENODEV; + goto err_out; + } + memcpy(attr, &rxe->port.attr, sizeof(*attr)); mutex_lock(&rxe->usdev_lock); @@ -57,13 +64,14 @@ static int rxe_query_port(struct ib_device *ibdev, if (attr->state == IB_PORT_ACTIVE) attr->phys_state = IB_PORT_PHYS_STATE_LINK_UP; - else if (dev_get_flags(rxe->ndev) & IFF_UP) + else if (dev_get_flags(ndev) & IFF_UP) attr->phys_state = IB_PORT_PHYS_STATE_POLLING; else attr->phys_state = IB_PORT_PHYS_STATE_DISABLED; mutex_unlock(&rxe->usdev_lock); + dev_put(ndev); return ret; err_out: @@ -1425,9 +1433,16 @@ static const struct attribute_group rxe_attr_group = { static int rxe_enable_driver(struct ib_device *ib_dev) { struct rxe_dev *rxe = container_of(ib_dev, struct rxe_dev, ib_dev); + struct net_device *ndev; + + ndev = rxe_ib_device_get_netdev(ib_dev); + if (!ndev) + return -ENODEV; rxe_set_port_state(rxe); - dev_info(&rxe->ib_dev.dev, "added %s\n", netdev_name(rxe->ndev)); + dev_info(&rxe->ib_dev.dev, "added %s\n", netdev_name(ndev)); + + dev_put(ndev); return 0; } @@ -1495,7 +1510,8 @@ static const struct ib_device_ops rxe_dev_ops = { INIT_RDMA_OBJ_SIZE(ib_mw, rxe_mw, ibmw), }; -int rxe_register_device(struct rxe_dev *rxe, const char *ibdev_name) +int rxe_register_device(struct rxe_dev *rxe, const char *ibdev_name, + struct net_device *ndev) { int err; struct ib_device *dev = &rxe->ib_dev; @@ -1507,13 +1523,13 @@ int rxe_register_device(struct rxe_dev *rxe, const char *ibdev_name) dev->num_comp_vectors = num_possible_cpus(); dev->local_dma_lkey = 0; addrconf_addr_eui48((unsigned char *)&dev->node_guid, - rxe->ndev->dev_addr); + ndev->dev_addr); dev->uverbs_cmd_mask |= BIT_ULL(IB_USER_VERBS_CMD_POST_SEND) | BIT_ULL(IB_USER_VERBS_CMD_REQ_NOTIFY_CQ); ib_set_device_ops(dev, &rxe_dev_ops); - err = ib_device_set_netdev(&rxe->ib_dev, rxe->ndev, 1); + err = ib_device_set_netdev(&rxe->ib_dev, ndev, 1); if (err) return err; diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.h b/drivers/infiniband/sw/rxe/rxe_verbs.h index 3c1354f82283..6573ceec0ef5 100644 --- a/drivers/infiniband/sw/rxe/rxe_verbs.h +++ b/drivers/infiniband/sw/rxe/rxe_verbs.h @@ -370,6 +370,7 @@ struct rxe_port { u32 qp_gsi_index; }; +#define RXE_PORT 1 struct rxe_dev { struct ib_device ib_dev; struct ib_device_attr attr; @@ -377,8 +378,6 @@ struct rxe_dev { int max_inline_data; struct mutex usdev_lock; - struct net_device *ndev; - struct rxe_pool uc_pool; struct rxe_pool pd_pool; struct rxe_pool ah_pool; @@ -406,6 +405,11 @@ struct rxe_dev { struct crypto_shash *tfm; }; +static inline struct net_device *rxe_ib_device_get_netdev(struct ib_device *dev) +{ + return ib_device_get_netdev(dev, RXE_PORT); +} + static inline void rxe_counter_inc(struct rxe_dev *rxe, enum rxe_counters index) { atomic64_inc(&rxe->stats_counters[index]); @@ -471,6 +475,7 @@ static inline struct rxe_pd *rxe_mw_pd(struct rxe_mw *mw) return to_rpd(mw->ibmw.pd); } -int rxe_register_device(struct rxe_dev *rxe, const char *ibdev_name); +int rxe_register_device(struct rxe_dev *rxe, const char *ibdev_name, + struct net_device *ndev); #endif /* RXE_VERBS_H */ diff --git a/drivers/infiniband/sw/siw/siw.h b/drivers/infiniband/sw/siw/siw.h index 86d4d6a2170e..ea5eee50dc39 100644 --- a/drivers/infiniband/sw/siw/siw.h +++ b/drivers/infiniband/sw/siw/siw.h @@ -46,6 +46,9 @@ */ #define SIW_IRQ_MAXBURST_SQ_ACTIVE 4 +/* There is always only a port 1 per siw device */ +#define SIW_PORT 1 + struct siw_dev_cap { int max_qp; int max_qp_wr; @@ -69,16 +72,12 @@ struct siw_pd { struct siw_device { struct ib_device base_dev; - struct net_device *netdev; struct siw_dev_cap attrs; u32 vendor_part_id; int numa_node; char raw_gid[ETH_ALEN]; - /* physical port state (only one port per device) */ - enum ib_port_state state; - spinlock_t lock; struct xarray qp_xa; diff --git a/drivers/infiniband/sw/siw/siw_cm.c b/drivers/infiniband/sw/siw/siw_cm.c index 86323918a570..708b13993fdf 100644 --- a/drivers/infiniband/sw/siw/siw_cm.c +++ b/drivers/infiniband/sw/siw/siw_cm.c @@ -1759,6 +1759,7 @@ int siw_create_listen(struct iw_cm_id *id, int backlog) { struct socket *s; struct siw_cep *cep = NULL; + struct net_device *ndev = NULL; struct siw_device *sdev = to_siw_dev(id->device); int addr_family = id->local_addr.ss_family; int rv = 0; @@ -1779,9 +1780,15 @@ int siw_create_listen(struct iw_cm_id *id, int backlog) struct sockaddr_in *laddr = &to_sockaddr_in(id->local_addr); /* For wildcard addr, limit binding to current device only */ - if (ipv4_is_zeronet(laddr->sin_addr.s_addr)) - s->sk->sk_bound_dev_if = sdev->netdev->ifindex; - + if (ipv4_is_zeronet(laddr->sin_addr.s_addr)) { + ndev = ib_device_get_netdev(id->device, SIW_PORT); + if (ndev) { + s->sk->sk_bound_dev_if = ndev->ifindex; + } else { + rv = -ENODEV; + goto error; + } + } rv = s->ops->bind(s, (struct sockaddr *)laddr, sizeof(struct sockaddr_in)); } else { @@ -1797,9 +1804,15 @@ int siw_create_listen(struct iw_cm_id *id, int backlog) } /* For wildcard addr, limit binding to current device only */ - if (ipv6_addr_any(&laddr->sin6_addr)) - s->sk->sk_bound_dev_if = sdev->netdev->ifindex; - + if (ipv6_addr_any(&laddr->sin6_addr)) { + ndev = ib_device_get_netdev(id->device, SIW_PORT); + if (ndev) { + s->sk->sk_bound_dev_if = ndev->ifindex; + } else { + rv = -ENODEV; + goto error; + } + } rv = s->ops->bind(s, (struct sockaddr *)laddr, sizeof(struct sockaddr_in6)); } @@ -1860,6 +1873,7 @@ int siw_create_listen(struct iw_cm_id *id, int backlog) } list_add_tail(&cep->listenq, (struct list_head *)id->provider_data); cep->state = SIW_EPSTATE_LISTENING; + dev_put(ndev); siw_dbg(id->device, "Listen at laddr %pISp\n", &id->local_addr); @@ -1879,6 +1893,7 @@ error: siw_cep_set_free_and_put(cep); } sock_release(s); + dev_put(ndev); return rv; } diff --git a/drivers/infiniband/sw/siw/siw_main.c b/drivers/infiniband/sw/siw/siw_main.c index 17abef48abcd..14d3103aee6f 100644 --- a/drivers/infiniband/sw/siw/siw_main.c +++ b/drivers/infiniband/sw/siw/siw_main.c @@ -287,7 +287,6 @@ static struct siw_device *siw_device_create(struct net_device *netdev) return NULL; base_dev = &sdev->base_dev; - sdev->netdev = netdev; if (netdev->addr_len) { memcpy(sdev->raw_gid, netdev->dev_addr, @@ -381,12 +380,10 @@ static int siw_netdev_event(struct notifier_block *nb, unsigned long event, switch (event) { case NETDEV_UP: - sdev->state = IB_PORT_ACTIVE; siw_port_event(sdev, 1, IB_EVENT_PORT_ACTIVE); break; case NETDEV_DOWN: - sdev->state = IB_PORT_DOWN; siw_port_event(sdev, 1, IB_EVENT_PORT_ERR); break; @@ -407,12 +404,8 @@ static int siw_netdev_event(struct notifier_block *nb, unsigned long event, siw_port_event(sdev, 1, IB_EVENT_LID_CHANGE); break; /* - * Todo: Below netdev events are currently not handled. + * All other events are not handled */ - case NETDEV_CHANGEMTU: - case NETDEV_CHANGE: - break; - default: break; } @@ -442,12 +435,6 @@ static int siw_newlink(const char *basedev_name, struct net_device *netdev) sdev = siw_device_create(netdev); if (sdev) { dev_dbg(&netdev->dev, "siw: new device\n"); - - if (netif_running(netdev) && netif_carrier_ok(netdev)) - sdev->state = IB_PORT_ACTIVE; - else - sdev->state = IB_PORT_DOWN; - ib_mark_name_assigned_by_user(&sdev->base_dev); rv = siw_device_register(sdev, basedev_name); if (rv) diff --git a/drivers/infiniband/sw/siw/siw_verbs.c b/drivers/infiniband/sw/siw/siw_verbs.c index 986666c19378..7ca0297d68a4 100644 --- a/drivers/infiniband/sw/siw/siw_verbs.c +++ b/drivers/infiniband/sw/siw/siw_verbs.c @@ -171,21 +171,29 @@ int siw_query_device(struct ib_device *base_dev, struct ib_device_attr *attr, int siw_query_port(struct ib_device *base_dev, u32 port, struct ib_port_attr *attr) { - struct siw_device *sdev = to_siw_dev(base_dev); + struct net_device *ndev; int rv; memset(attr, 0, sizeof(*attr)); rv = ib_get_eth_speed(base_dev, port, &attr->active_speed, &attr->active_width); + if (rv) + return rv; + + ndev = ib_device_get_netdev(base_dev, SIW_PORT); + if (!ndev) + return -ENODEV; + attr->gid_tbl_len = 1; attr->max_msg_sz = -1; - attr->max_mtu = ib_mtu_int_to_enum(sdev->netdev->mtu); - attr->active_mtu = ib_mtu_int_to_enum(sdev->netdev->mtu); - attr->phys_state = sdev->state == IB_PORT_ACTIVE ? + attr->max_mtu = ib_mtu_int_to_enum(ndev->max_mtu); + attr->active_mtu = ib_mtu_int_to_enum(READ_ONCE(ndev->mtu)); + attr->phys_state = (netif_running(ndev) && netif_carrier_ok(ndev)) ? IB_PORT_PHYS_STATE_LINK_UP : IB_PORT_PHYS_STATE_DISABLED; + attr->state = attr->phys_state == IB_PORT_PHYS_STATE_LINK_UP ? + IB_PORT_ACTIVE : IB_PORT_DOWN; attr->port_cap_flags = IB_PORT_CM_SUP | IB_PORT_DEVICE_MGMT_SUP; - attr->state = sdev->state; /* * All zero * @@ -199,6 +207,7 @@ int siw_query_port(struct ib_device *base_dev, u32 port, * attr->subnet_timeout = 0; * attr->init_type_repy = 0; */ + dev_put(ndev); return rv; } @@ -505,21 +514,24 @@ int siw_query_qp(struct ib_qp *base_qp, struct ib_qp_attr *qp_attr, int qp_attr_mask, struct ib_qp_init_attr *qp_init_attr) { struct siw_qp *qp; - struct siw_device *sdev; + struct net_device *ndev; - if (base_qp && qp_attr && qp_init_attr) { + if (base_qp && qp_attr && qp_init_attr) qp = to_siw_qp(base_qp); - sdev = to_siw_dev(base_qp->device); - } else { + else return -EINVAL; - } + + ndev = ib_device_get_netdev(base_qp->device, SIW_PORT); + if (!ndev) + return -ENODEV; + qp_attr->qp_state = siw_qp_state_to_ib_qp_state[qp->attrs.state]; qp_attr->cap.max_inline_data = SIW_MAX_INLINE; qp_attr->cap.max_send_wr = qp->attrs.sq_size; qp_attr->cap.max_send_sge = qp->attrs.sq_max_sges; qp_attr->cap.max_recv_wr = qp->attrs.rq_size; qp_attr->cap.max_recv_sge = qp->attrs.rq_max_sges; - qp_attr->path_mtu = ib_mtu_int_to_enum(sdev->netdev->mtu); + qp_attr->path_mtu = ib_mtu_int_to_enum(READ_ONCE(ndev->mtu)); qp_attr->max_rd_atomic = qp->attrs.irq_size; qp_attr->max_dest_rd_atomic = qp->attrs.orq_size; @@ -534,6 +546,7 @@ int siw_query_qp(struct ib_qp *base_qp, struct ib_qp_attr *qp_attr, qp_init_attr->cap = qp_attr->cap; + dev_put(ndev); return 0; } diff --git a/drivers/infiniband/ulp/rtrs/rtrs-srv.c b/drivers/infiniband/ulp/rtrs/rtrs-srv.c index e83d95647852..ef4abdea3c2d 100644 --- a/drivers/infiniband/ulp/rtrs/rtrs-srv.c +++ b/drivers/infiniband/ulp/rtrs/rtrs-srv.c @@ -349,6 +349,7 @@ static int send_io_resp_imm(struct rtrs_srv_con *con, struct rtrs_srv_op *id, struct rtrs_srv_mr *srv_mr; bool need_inval = false; enum ib_send_flags flags; + struct ib_sge list; u32 imm; int err; @@ -401,7 +402,6 @@ static int send_io_resp_imm(struct rtrs_srv_con *con, struct rtrs_srv_op *id, imm = rtrs_to_io_rsp_imm(id->msg_id, errno, need_inval); imm_wr.wr.next = NULL; if (always_invalidate) { - struct ib_sge list; struct rtrs_msg_rkey_rsp *msg; srv_mr = &srv_path->mrs[id->msg_id]; diff --git a/drivers/iommu/arm/arm-smmu-v3/tegra241-cmdqv.c b/drivers/iommu/arm/arm-smmu-v3/tegra241-cmdqv.c index c8ec74f089f3..6e41ddaa24d6 100644 --- a/drivers/iommu/arm/arm-smmu-v3/tegra241-cmdqv.c +++ b/drivers/iommu/arm/arm-smmu-v3/tegra241-cmdqv.c @@ -339,7 +339,7 @@ tegra241_cmdqv_get_cmdq(struct arm_smmu_device *smmu, * one CPU at a time can enter the process, while the others * will be spinning at the same lock. */ - lidx = smp_processor_id() % cmdqv->num_lvcmdqs_per_vintf; + lidx = raw_smp_processor_id() % cmdqv->num_lvcmdqs_per_vintf; vcmdq = vintf->lvcmdqs[lidx]; if (!vcmdq || !READ_ONCE(vcmdq->enabled)) return NULL; diff --git a/drivers/iommu/intel/cache.c b/drivers/iommu/intel/cache.c index e5b89f728ad3..09694cca8752 100644 --- a/drivers/iommu/intel/cache.c +++ b/drivers/iommu/intel/cache.c @@ -105,12 +105,35 @@ static void cache_tag_unassign(struct dmar_domain *domain, u16 did, spin_unlock_irqrestore(&domain->cache_lock, flags); } +/* domain->qi_batch will be freed in iommu_free_domain() path. */ +static int domain_qi_batch_alloc(struct dmar_domain *domain) +{ + unsigned long flags; + int ret = 0; + + spin_lock_irqsave(&domain->cache_lock, flags); + if (domain->qi_batch) + goto out_unlock; + + domain->qi_batch = kzalloc(sizeof(*domain->qi_batch), GFP_ATOMIC); + if (!domain->qi_batch) + ret = -ENOMEM; +out_unlock: + spin_unlock_irqrestore(&domain->cache_lock, flags); + + return ret; +} + static int __cache_tag_assign_domain(struct dmar_domain *domain, u16 did, struct device *dev, ioasid_t pasid) { struct device_domain_info *info = dev_iommu_priv_get(dev); int ret; + ret = domain_qi_batch_alloc(domain); + if (ret) + return ret; + ret = cache_tag_assign(domain, did, dev, pasid, CACHE_TAG_IOTLB); if (ret || !info->ats_enabled) return ret; @@ -139,6 +162,10 @@ static int __cache_tag_assign_parent_domain(struct dmar_domain *domain, u16 did, struct device_domain_info *info = dev_iommu_priv_get(dev); int ret; + ret = domain_qi_batch_alloc(domain); + if (ret) + return ret; + ret = cache_tag_assign(domain, did, dev, pasid, CACHE_TAG_NESTING_IOTLB); if (ret || !info->ats_enabled) return ret; @@ -190,13 +217,6 @@ int cache_tag_assign_domain(struct dmar_domain *domain, u16 did = domain_get_id_for_dev(domain, dev); int ret; - /* domain->qi_bach will be freed in iommu_free_domain() path. */ - if (!domain->qi_batch) { - domain->qi_batch = kzalloc(sizeof(*domain->qi_batch), GFP_KERNEL); - if (!domain->qi_batch) - return -ENOMEM; - } - ret = __cache_tag_assign_domain(domain, did, dev, pasid); if (ret || domain->domain.type != IOMMU_DOMAIN_NESTED) return ret; diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index a167d59101ae..cc23cfcdeb2d 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -3372,6 +3372,9 @@ void device_block_translation(struct device *dev) struct intel_iommu *iommu = info->iommu; unsigned long flags; + if (info->domain) + cache_tag_unassign_domain(info->domain, dev, IOMMU_NO_PASID); + iommu_disable_pci_caps(info); if (!dev_is_real_dma_subdevice(dev)) { if (sm_supported(iommu)) @@ -3388,7 +3391,6 @@ void device_block_translation(struct device *dev) list_del(&info->link); spin_unlock_irqrestore(&info->domain->lock, flags); - cache_tag_unassign_domain(info->domain, dev, IOMMU_NO_PASID); domain_detach_iommu(info->domain, iommu); info->domain = NULL; } diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c index 8b6159f4cdaf..b0bfb61539c2 100644 --- a/drivers/irqchip/irq-gic-v3.c +++ b/drivers/irqchip/irq-gic-v3.c @@ -161,7 +161,22 @@ static bool cpus_have_group0 __ro_after_init; static void __init gic_prio_init(void) { - cpus_have_security_disabled = gic_dist_security_disabled(); + bool ds; + + ds = gic_dist_security_disabled(); + if (!ds) { + u32 val; + + val = readl_relaxed(gic_data.dist_base + GICD_CTLR); + val |= GICD_CTLR_DS; + writel_relaxed(val, gic_data.dist_base + GICD_CTLR); + + ds = gic_dist_security_disabled(); + if (ds) + pr_warn("Broken GIC integration, security disabled"); + } + + cpus_have_security_disabled = ds; cpus_have_group0 = gic_has_group0(); /* diff --git a/drivers/irqchip/irq-gic.c b/drivers/irqchip/irq-gic.c index 3be7bd8cd8cd..32abc2916b40 100644 --- a/drivers/irqchip/irq-gic.c +++ b/drivers/irqchip/irq-gic.c @@ -64,7 +64,7 @@ static void gic_check_cpu_features(void) union gic_base { void __iomem *common_base; - void __percpu * __iomem *percpu_base; + void __iomem * __percpu *percpu_base; }; struct gic_chip_data { diff --git a/drivers/md/dm-zoned-reclaim.c b/drivers/md/dm-zoned-reclaim.c index d58db9a27e6c..76e2c6868548 100644 --- a/drivers/md/dm-zoned-reclaim.c +++ b/drivers/md/dm-zoned-reclaim.c @@ -76,9 +76,9 @@ static int dmz_reclaim_align_wp(struct dmz_reclaim *zrc, struct dm_zone *zone, * pointer and the requested position. */ nr_blocks = block - wp_block; - ret = blkdev_issue_zeroout(dev->bdev, - dmz_start_sect(zmd, zone) + dmz_blk2sect(wp_block), - dmz_blk2sect(nr_blocks), GFP_NOIO, 0); + ret = blk_zone_issue_zeroout(dev->bdev, + dmz_start_sect(zmd, zone) + dmz_blk2sect(wp_block), + dmz_blk2sect(nr_blocks), GFP_NOIO); if (ret) { dmz_dev_err(dev, "Align zone %u wp %llu to %llu (wp+%u) blocks failed %d", diff --git a/drivers/media/dvb-frontends/dib3000mb.c b/drivers/media/dvb-frontends/dib3000mb.c index c598b2a63325..7c452ddd9e40 100644 --- a/drivers/media/dvb-frontends/dib3000mb.c +++ b/drivers/media/dvb-frontends/dib3000mb.c @@ -51,7 +51,7 @@ MODULE_PARM_DESC(debug, "set debugging level (1=info,2=xfer,4=setfe,8=getfe (|-a static int dib3000_read_reg(struct dib3000_state *state, u16 reg) { u8 wb[] = { ((reg >> 8) | 0x80) & 0xff, reg & 0xff }; - u8 rb[2]; + u8 rb[2] = {}; struct i2c_msg msg[] = { { .addr = state->config.demod_address, .flags = 0, .buf = wb, .len = 2 }, { .addr = state->config.demod_address, .flags = I2C_M_RD, .buf = rb, .len = 2 }, diff --git a/drivers/mmc/host/mtk-sd.c b/drivers/mmc/host/mtk-sd.c index 813bc20cfb5a..6e62415de2e5 100644 --- a/drivers/mmc/host/mtk-sd.c +++ b/drivers/mmc/host/mtk-sd.c @@ -2924,6 +2924,7 @@ release_clk: msdc_gate_clock(host); platform_set_drvdata(pdev, NULL); release_mem: + device_init_wakeup(&pdev->dev, false); if (host->dma.gpd) dma_free_coherent(&pdev->dev, 2 * sizeof(struct mt_gpdma_desc), @@ -2957,6 +2958,7 @@ static void msdc_drv_remove(struct platform_device *pdev) host->dma.gpd, host->dma.gpd_addr); dma_free_coherent(&pdev->dev, MAX_BD_NUM * sizeof(struct mt_bdma_desc), host->dma.bd, host->dma.bd_addr); + device_init_wakeup(&pdev->dev, false); } static void msdc_save_reg(struct msdc_host *host) diff --git a/drivers/mmc/host/sdhci-msm.c b/drivers/mmc/host/sdhci-msm.c index e113b99a3eab..8716004fcf6c 100644 --- a/drivers/mmc/host/sdhci-msm.c +++ b/drivers/mmc/host/sdhci-msm.c @@ -1867,20 +1867,20 @@ static int sdhci_msm_program_key(struct cqhci_host *cq_host, struct sdhci_msm_host *msm_host = sdhci_pltfm_priv(pltfm_host); union cqhci_crypto_cap_entry cap; + if (!(cfg->config_enable & CQHCI_CRYPTO_CONFIGURATION_ENABLE)) + return qcom_ice_evict_key(msm_host->ice, slot); + /* Only AES-256-XTS has been tested so far. */ cap = cq_host->crypto_cap_array[cfg->crypto_cap_idx]; if (cap.algorithm_id != CQHCI_CRYPTO_ALG_AES_XTS || cap.key_size != CQHCI_CRYPTO_KEY_SIZE_256) return -EINVAL; - if (cfg->config_enable & CQHCI_CRYPTO_CONFIGURATION_ENABLE) - return qcom_ice_program_key(msm_host->ice, - QCOM_ICE_CRYPTO_ALG_AES_XTS, - QCOM_ICE_CRYPTO_KEY_SIZE_256, - cfg->crypto_key, - cfg->data_unit_size, slot); - else - return qcom_ice_evict_key(msm_host->ice, slot); + return qcom_ice_program_key(msm_host->ice, + QCOM_ICE_CRYPTO_ALG_AES_XTS, + QCOM_ICE_CRYPTO_KEY_SIZE_256, + cfg->crypto_key, + cfg->data_unit_size, slot); } #else /* CONFIG_MMC_CRYPTO */ diff --git a/drivers/mmc/host/sdhci-tegra.c b/drivers/mmc/host/sdhci-tegra.c index 1ad0a6b3a2eb..7b6b82bec855 100644 --- a/drivers/mmc/host/sdhci-tegra.c +++ b/drivers/mmc/host/sdhci-tegra.c @@ -1525,7 +1525,6 @@ static const struct sdhci_pltfm_data sdhci_tegra186_pdata = { .quirks = SDHCI_QUIRK_BROKEN_TIMEOUT_VAL | SDHCI_QUIRK_SINGLE_POWER_WRITE | SDHCI_QUIRK_NO_HISPD_BIT | - SDHCI_QUIRK_BROKEN_ADMA_ZEROLEN_DESC | SDHCI_QUIRK_CAP_CLOCK_BASE_BROKEN, .quirks2 = SDHCI_QUIRK2_PRESET_VALUE_BROKEN | SDHCI_QUIRK2_ISSUE_CMD_DAT_RESET_TOGETHER, diff --git a/drivers/mtd/nand/raw/arasan-nand-controller.c b/drivers/mtd/nand/raw/arasan-nand-controller.c index 5436ec4a8fde..a52a9f5a75e0 100644 --- a/drivers/mtd/nand/raw/arasan-nand-controller.c +++ b/drivers/mtd/nand/raw/arasan-nand-controller.c @@ -1409,8 +1409,8 @@ static int anfc_parse_cs(struct arasan_nfc *nfc) * case, the "not" chosen CS is assigned to nfc->spare_cs and selected * whenever a GPIO CS must be asserted. */ - if (nfc->cs_array && nfc->ncs > 2) { - if (!nfc->cs_array[0] && !nfc->cs_array[1]) { + if (nfc->cs_array) { + if (nfc->ncs > 2 && !nfc->cs_array[0] && !nfc->cs_array[1]) { dev_err(nfc->dev, "Assign a single native CS when using GPIOs\n"); return -EINVAL; @@ -1478,8 +1478,15 @@ static int anfc_probe(struct platform_device *pdev) static void anfc_remove(struct platform_device *pdev) { + int i; struct arasan_nfc *nfc = platform_get_drvdata(pdev); + for (i = 0; i < nfc->ncs; i++) { + if (nfc->cs_array[i]) { + gpiod_put(nfc->cs_array[i]); + } + } + anfc_chips_cleanup(nfc); } diff --git a/drivers/mtd/nand/raw/atmel/pmecc.c b/drivers/mtd/nand/raw/atmel/pmecc.c index a22aab4ed4e8..3c7dee1be21d 100644 --- a/drivers/mtd/nand/raw/atmel/pmecc.c +++ b/drivers/mtd/nand/raw/atmel/pmecc.c @@ -380,10 +380,8 @@ atmel_pmecc_create_user(struct atmel_pmecc *pmecc, user->delta = user->dmu + req->ecc.strength + 1; gf_tables = atmel_pmecc_get_gf_tables(req); - if (IS_ERR(gf_tables)) { - kfree(user); + if (IS_ERR(gf_tables)) return ERR_CAST(gf_tables); - } user->gf_tables = gf_tables; diff --git a/drivers/mtd/nand/raw/diskonchip.c b/drivers/mtd/nand/raw/diskonchip.c index 8db7fc424571..70d6c2250f32 100644 --- a/drivers/mtd/nand/raw/diskonchip.c +++ b/drivers/mtd/nand/raw/diskonchip.c @@ -1098,7 +1098,7 @@ static inline int __init inftl_partscan(struct mtd_info *mtd, struct mtd_partiti (i == 0) && (ip->firstUnit > 0)) { parts[0].name = " DiskOnChip IPL / Media Header partition"; parts[0].offset = 0; - parts[0].size = mtd->erasesize * ip->firstUnit; + parts[0].size = (uint64_t)mtd->erasesize * ip->firstUnit; numparts = 1; } diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 15e0f14d0d49..4d73abae503d 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1520,9 +1520,7 @@ static netdev_features_t bond_fix_features(struct net_device *dev, struct slave *slave; mask = features; - - features &= ~NETIF_F_ONE_FOR_ALL; - features |= NETIF_F_ALL_FOR_ALL; + features = netdev_base_features(features); bond_for_each_slave(bond, slave, iter) { features = netdev_increment_features(features, @@ -1536,6 +1534,7 @@ static netdev_features_t bond_fix_features(struct net_device *dev, #define BOND_VLAN_FEATURES (NETIF_F_HW_CSUM | NETIF_F_SG | \ NETIF_F_FRAGLIST | NETIF_F_GSO_SOFTWARE | \ + NETIF_F_GSO_ENCAP_ALL | \ NETIF_F_HIGHDMA | NETIF_F_LRO) #define BOND_ENC_FEATURES (NETIF_F_HW_CSUM | NETIF_F_SG | \ @@ -1564,8 +1563,9 @@ static void bond_compute_features(struct bonding *bond) if (!bond_has_slaves(bond)) goto done; - vlan_features &= NETIF_F_ALL_FOR_ALL; - mpls_features &= NETIF_F_ALL_FOR_ALL; + + vlan_features = netdev_base_features(vlan_features); + mpls_features = netdev_base_features(mpls_features); bond_for_each_slave(bond, slave, iter) { vlan_features = netdev_increment_features(vlan_features, diff --git a/drivers/net/can/m_can/m_can.c b/drivers/net/can/m_can/m_can.c index 533bcb77c9f9..97cd8bbf2e32 100644 --- a/drivers/net/can/m_can/m_can.c +++ b/drivers/net/can/m_can/m_can.c @@ -1220,20 +1220,32 @@ static void m_can_coalescing_update(struct m_can_classdev *cdev, u32 ir) static int m_can_interrupt_handler(struct m_can_classdev *cdev) { struct net_device *dev = cdev->net; - u32 ir; + u32 ir = 0, ir_read; int ret; if (pm_runtime_suspended(cdev->dev)) return IRQ_NONE; - ir = m_can_read(cdev, M_CAN_IR); + /* The m_can controller signals its interrupt status as a level, but + * depending in the integration the CPU may interpret the signal as + * edge-triggered (for example with m_can_pci). For these + * edge-triggered integrations, we must observe that IR is 0 at least + * once to be sure that the next interrupt will generate an edge. + */ + while ((ir_read = m_can_read(cdev, M_CAN_IR)) != 0) { + ir |= ir_read; + + /* ACK all irqs */ + m_can_write(cdev, M_CAN_IR, ir); + + if (!cdev->irq_edge_triggered) + break; + } + m_can_coalescing_update(cdev, ir); if (!ir) return IRQ_NONE; - /* ACK all irqs */ - m_can_write(cdev, M_CAN_IR, ir); - if (cdev->ops->clear_interrupts) cdev->ops->clear_interrupts(cdev); @@ -1695,6 +1707,14 @@ static int m_can_dev_setup(struct m_can_classdev *cdev) return -EINVAL; } + /* Write the INIT bit, in case no hardware reset has happened before + * the probe (for example, it was observed that the Intel Elkhart Lake + * SoCs do not properly reset the CAN controllers on reboot) + */ + err = m_can_cccr_update_bits(cdev, CCCR_INIT, CCCR_INIT); + if (err) + return err; + if (!cdev->is_peripheral) netif_napi_add(dev, &cdev->napi, m_can_poll); @@ -1746,11 +1766,7 @@ static int m_can_dev_setup(struct m_can_classdev *cdev) return -EINVAL; } - /* Forcing standby mode should be redundant, as the chip should be in - * standby after a reset. Write the INIT bit anyways, should the chip - * be configured by previous stage. - */ - return m_can_cccr_update_bits(cdev, CCCR_INIT, CCCR_INIT); + return 0; } static void m_can_stop(struct net_device *dev) diff --git a/drivers/net/can/m_can/m_can.h b/drivers/net/can/m_can/m_can.h index 92b2bd8628e6..ef39e8e527ab 100644 --- a/drivers/net/can/m_can/m_can.h +++ b/drivers/net/can/m_can/m_can.h @@ -99,6 +99,7 @@ struct m_can_classdev { int pm_clock_support; int pm_wake_source; int is_peripheral; + bool irq_edge_triggered; // Cached M_CAN_IE register content u32 active_interrupts; diff --git a/drivers/net/can/m_can/m_can_pci.c b/drivers/net/can/m_can/m_can_pci.c index d72fe771dfc7..9ad7419f88f8 100644 --- a/drivers/net/can/m_can/m_can_pci.c +++ b/drivers/net/can/m_can/m_can_pci.c @@ -127,6 +127,7 @@ static int m_can_pci_probe(struct pci_dev *pci, const struct pci_device_id *id) mcan_class->pm_clock_support = 1; mcan_class->pm_wake_source = 0; mcan_class->can.clock.freq = id->driver_data; + mcan_class->irq_edge_triggered = true; mcan_class->ops = &m_can_pci_ops; pci_set_drvdata(pci, mcan_class); diff --git a/drivers/net/dsa/microchip/ksz9477.c b/drivers/net/dsa/microchip/ksz9477.c index 0ba658a72d8f..22556d339d6e 100644 --- a/drivers/net/dsa/microchip/ksz9477.c +++ b/drivers/net/dsa/microchip/ksz9477.c @@ -2,7 +2,7 @@ /* * Microchip KSZ9477 switch driver main logic * - * Copyright (C) 2017-2019 Microchip Technology Inc. + * Copyright (C) 2017-2024 Microchip Technology Inc. */ #include <linux/kernel.h> @@ -983,26 +983,51 @@ void ksz9477_get_caps(struct ksz_device *dev, int port, int ksz9477_set_ageing_time(struct ksz_device *dev, unsigned int msecs) { u32 secs = msecs / 1000; - u8 value; - u8 data; + u8 data, mult, value; + u32 max_val; int ret; - value = FIELD_GET(SW_AGE_PERIOD_7_0_M, secs); +#define MAX_TIMER_VAL ((1 << 8) - 1) - ret = ksz_write8(dev, REG_SW_LUE_CTRL_3, value); - if (ret < 0) - return ret; + /* The aging timer comprises a 3-bit multiplier and an 8-bit second + * value. Either of them cannot be zero. The maximum timer is then + * 7 * 255 = 1785 seconds. + */ + if (!secs) + secs = 1; - data = FIELD_GET(SW_AGE_PERIOD_10_8_M, secs); + /* Return error if too large. */ + else if (secs > 7 * MAX_TIMER_VAL) + return -EINVAL; ret = ksz_read8(dev, REG_SW_LUE_CTRL_0, &value); if (ret < 0) return ret; - value &= ~SW_AGE_CNT_M; - value |= FIELD_PREP(SW_AGE_CNT_M, data); + /* Check whether there is need to update the multiplier. */ + mult = FIELD_GET(SW_AGE_CNT_M, value); + max_val = MAX_TIMER_VAL; + if (mult > 0) { + /* Try to use the same multiplier already in the register as + * the hardware default uses multiplier 4 and 75 seconds for + * 300 seconds. + */ + max_val = DIV_ROUND_UP(secs, mult); + if (max_val > MAX_TIMER_VAL || max_val * mult != secs) + max_val = MAX_TIMER_VAL; + } + + data = DIV_ROUND_UP(secs, max_val); + if (mult != data) { + value &= ~SW_AGE_CNT_M; + value |= FIELD_PREP(SW_AGE_CNT_M, data); + ret = ksz_write8(dev, REG_SW_LUE_CTRL_0, value); + if (ret < 0) + return ret; + } - return ksz_write8(dev, REG_SW_LUE_CTRL_0, value); + value = DIV_ROUND_UP(secs, data); + return ksz_write8(dev, REG_SW_LUE_CTRL_3, value); } void ksz9477_port_queue_split(struct ksz_device *dev, int port) diff --git a/drivers/net/dsa/microchip/ksz9477_reg.h b/drivers/net/dsa/microchip/ksz9477_reg.h index 04235c22bf40..ff579920078e 100644 --- a/drivers/net/dsa/microchip/ksz9477_reg.h +++ b/drivers/net/dsa/microchip/ksz9477_reg.h @@ -2,7 +2,7 @@ /* * Microchip KSZ9477 register definitions * - * Copyright (C) 2017-2018 Microchip Technology Inc. + * Copyright (C) 2017-2024 Microchip Technology Inc. */ #ifndef __KSZ9477_REGS_H @@ -165,8 +165,6 @@ #define SW_VLAN_ENABLE BIT(7) #define SW_DROP_INVALID_VID BIT(6) #define SW_AGE_CNT_M GENMASK(5, 3) -#define SW_AGE_CNT_S 3 -#define SW_AGE_PERIOD_10_8_M GENMASK(10, 8) #define SW_RESV_MCAST_ENABLE BIT(2) #define SW_HASH_OPTION_M 0x03 #define SW_HASH_OPTION_CRC 1 diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c index 5290f5ad98f3..bf26cd0abf6d 100644 --- a/drivers/net/dsa/microchip/ksz_common.c +++ b/drivers/net/dsa/microchip/ksz_common.c @@ -1098,10 +1098,9 @@ static const struct regmap_range ksz9896_valid_regs[] = { regmap_reg_range(0x1030, 0x1030), regmap_reg_range(0x1100, 0x1115), regmap_reg_range(0x111a, 0x111f), - regmap_reg_range(0x1122, 0x1127), - regmap_reg_range(0x112a, 0x112b), - regmap_reg_range(0x1136, 0x1139), - regmap_reg_range(0x113e, 0x113f), + regmap_reg_range(0x1120, 0x112b), + regmap_reg_range(0x1134, 0x113b), + regmap_reg_range(0x113c, 0x113f), regmap_reg_range(0x1400, 0x1401), regmap_reg_range(0x1403, 0x1403), regmap_reg_range(0x1410, 0x1417), @@ -1128,10 +1127,9 @@ static const struct regmap_range ksz9896_valid_regs[] = { regmap_reg_range(0x2030, 0x2030), regmap_reg_range(0x2100, 0x2115), regmap_reg_range(0x211a, 0x211f), - regmap_reg_range(0x2122, 0x2127), - regmap_reg_range(0x212a, 0x212b), - regmap_reg_range(0x2136, 0x2139), - regmap_reg_range(0x213e, 0x213f), + regmap_reg_range(0x2120, 0x212b), + regmap_reg_range(0x2134, 0x213b), + regmap_reg_range(0x213c, 0x213f), regmap_reg_range(0x2400, 0x2401), regmap_reg_range(0x2403, 0x2403), regmap_reg_range(0x2410, 0x2417), @@ -1158,10 +1156,9 @@ static const struct regmap_range ksz9896_valid_regs[] = { regmap_reg_range(0x3030, 0x3030), regmap_reg_range(0x3100, 0x3115), regmap_reg_range(0x311a, 0x311f), - regmap_reg_range(0x3122, 0x3127), - regmap_reg_range(0x312a, 0x312b), - regmap_reg_range(0x3136, 0x3139), - regmap_reg_range(0x313e, 0x313f), + regmap_reg_range(0x3120, 0x312b), + regmap_reg_range(0x3134, 0x313b), + regmap_reg_range(0x313c, 0x313f), regmap_reg_range(0x3400, 0x3401), regmap_reg_range(0x3403, 0x3403), regmap_reg_range(0x3410, 0x3417), @@ -1188,10 +1185,9 @@ static const struct regmap_range ksz9896_valid_regs[] = { regmap_reg_range(0x4030, 0x4030), regmap_reg_range(0x4100, 0x4115), regmap_reg_range(0x411a, 0x411f), - regmap_reg_range(0x4122, 0x4127), - regmap_reg_range(0x412a, 0x412b), - regmap_reg_range(0x4136, 0x4139), - regmap_reg_range(0x413e, 0x413f), + regmap_reg_range(0x4120, 0x412b), + regmap_reg_range(0x4134, 0x413b), + regmap_reg_range(0x413c, 0x413f), regmap_reg_range(0x4400, 0x4401), regmap_reg_range(0x4403, 0x4403), regmap_reg_range(0x4410, 0x4417), @@ -1218,10 +1214,9 @@ static const struct regmap_range ksz9896_valid_regs[] = { regmap_reg_range(0x5030, 0x5030), regmap_reg_range(0x5100, 0x5115), regmap_reg_range(0x511a, 0x511f), - regmap_reg_range(0x5122, 0x5127), - regmap_reg_range(0x512a, 0x512b), - regmap_reg_range(0x5136, 0x5139), - regmap_reg_range(0x513e, 0x513f), + regmap_reg_range(0x5120, 0x512b), + regmap_reg_range(0x5134, 0x513b), + regmap_reg_range(0x513c, 0x513f), regmap_reg_range(0x5400, 0x5401), regmap_reg_range(0x5403, 0x5403), regmap_reg_range(0x5410, 0x5417), @@ -1248,10 +1243,9 @@ static const struct regmap_range ksz9896_valid_regs[] = { regmap_reg_range(0x6030, 0x6030), regmap_reg_range(0x6100, 0x6115), regmap_reg_range(0x611a, 0x611f), - regmap_reg_range(0x6122, 0x6127), - regmap_reg_range(0x612a, 0x612b), - regmap_reg_range(0x6136, 0x6139), - regmap_reg_range(0x613e, 0x613f), + regmap_reg_range(0x6120, 0x612b), + regmap_reg_range(0x6134, 0x613b), + regmap_reg_range(0x613c, 0x613f), regmap_reg_range(0x6300, 0x6301), regmap_reg_range(0x6400, 0x6401), regmap_reg_range(0x6403, 0x6403), diff --git a/drivers/net/dsa/microchip/lan937x_main.c b/drivers/net/dsa/microchip/lan937x_main.c index 824d9309a3d3..7fe127a075de 100644 --- a/drivers/net/dsa/microchip/lan937x_main.c +++ b/drivers/net/dsa/microchip/lan937x_main.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* Microchip LAN937X switch driver main logic - * Copyright (C) 2019-2022 Microchip Technology Inc. + * Copyright (C) 2019-2024 Microchip Technology Inc. */ #include <linux/kernel.h> #include <linux/module.h> @@ -260,10 +260,66 @@ int lan937x_change_mtu(struct ksz_device *dev, int port, int new_mtu) int lan937x_set_ageing_time(struct ksz_device *dev, unsigned int msecs) { - u32 secs = msecs / 1000; - u32 value; + u8 data, mult, value8; + bool in_msec = false; + u32 max_val, value; + u32 secs = msecs; int ret; +#define MAX_TIMER_VAL ((1 << 20) - 1) + + /* The aging timer comprises a 3-bit multiplier and a 20-bit second + * value. Either of them cannot be zero. The maximum timer is then + * 7 * 1048575 = 7340025 seconds. As this value is too large for + * practical use it can be interpreted as microseconds, making the + * maximum timer 7340 seconds with finer control. This allows for + * maximum 122 minutes compared to 29 minutes in KSZ9477 switch. + */ + if (msecs % 1000) + in_msec = true; + else + secs /= 1000; + if (!secs) + secs = 1; + + /* Return error if too large. */ + else if (secs > 7 * MAX_TIMER_VAL) + return -EINVAL; + + /* Configure how to interpret the number value. */ + ret = ksz_rmw8(dev, REG_SW_LUE_CTRL_2, SW_AGE_CNT_IN_MICROSEC, + in_msec ? SW_AGE_CNT_IN_MICROSEC : 0); + if (ret < 0) + return ret; + + ret = ksz_read8(dev, REG_SW_LUE_CTRL_0, &value8); + if (ret < 0) + return ret; + + /* Check whether there is need to update the multiplier. */ + mult = FIELD_GET(SW_AGE_CNT_M, value8); + max_val = MAX_TIMER_VAL; + if (mult > 0) { + /* Try to use the same multiplier already in the register as + * the hardware default uses multiplier 4 and 75 seconds for + * 300 seconds. + */ + max_val = DIV_ROUND_UP(secs, mult); + if (max_val > MAX_TIMER_VAL || max_val * mult != secs) + max_val = MAX_TIMER_VAL; + } + + data = DIV_ROUND_UP(secs, max_val); + if (mult != data) { + value8 &= ~SW_AGE_CNT_M; + value8 |= FIELD_PREP(SW_AGE_CNT_M, data); + ret = ksz_write8(dev, REG_SW_LUE_CTRL_0, value8); + if (ret < 0) + return ret; + } + + secs = DIV_ROUND_UP(secs, data); + value = FIELD_GET(SW_AGE_PERIOD_7_0_M, secs); ret = ksz_write8(dev, REG_SW_AGE_PERIOD__1, value); diff --git a/drivers/net/dsa/microchip/lan937x_reg.h b/drivers/net/dsa/microchip/lan937x_reg.h index 2f22a9d01de3..35269f74a314 100644 --- a/drivers/net/dsa/microchip/lan937x_reg.h +++ b/drivers/net/dsa/microchip/lan937x_reg.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* Microchip LAN937X switch register definitions - * Copyright (C) 2019-2021 Microchip Technology Inc. + * Copyright (C) 2019-2024 Microchip Technology Inc. */ #ifndef __LAN937X_REG_H #define __LAN937X_REG_H @@ -52,8 +52,7 @@ #define SW_VLAN_ENABLE BIT(7) #define SW_DROP_INVALID_VID BIT(6) -#define SW_AGE_CNT_M 0x7 -#define SW_AGE_CNT_S 3 +#define SW_AGE_CNT_M GENMASK(5, 3) #define SW_RESV_MCAST_ENABLE BIT(2) #define REG_SW_LUE_CTRL_1 0x0311 @@ -66,6 +65,10 @@ #define SW_FAST_AGING BIT(1) #define SW_LINK_AUTO_AGING BIT(0) +#define REG_SW_LUE_CTRL_2 0x0312 + +#define SW_AGE_CNT_IN_MICROSEC BIT(7) + #define REG_SW_AGE_PERIOD__1 0x0313 #define SW_AGE_PERIOD_7_0_M GENMASK(7, 0) diff --git a/drivers/net/dsa/ocelot/felix_vsc9959.c b/drivers/net/dsa/ocelot/felix_vsc9959.c index 0102a82e88cc..940f1b71226d 100644 --- a/drivers/net/dsa/ocelot/felix_vsc9959.c +++ b/drivers/net/dsa/ocelot/felix_vsc9959.c @@ -24,7 +24,7 @@ #define VSC9959_NUM_PORTS 6 #define VSC9959_TAS_GCL_ENTRY_MAX 63 -#define VSC9959_TAS_MIN_GATE_LEN_NS 33 +#define VSC9959_TAS_MIN_GATE_LEN_NS 35 #define VSC9959_VCAP_POLICER_BASE 63 #define VSC9959_VCAP_POLICER_MAX 383 #define VSC9959_SWITCH_PCI_BAR 4 @@ -1056,11 +1056,15 @@ static void vsc9959_mdio_bus_free(struct ocelot *ocelot) mdiobus_free(felix->imdio); } -/* The switch considers any frame (regardless of size) as eligible for - * transmission if the traffic class gate is open for at least 33 ns. +/* The switch considers any frame (regardless of size) as eligible + * for transmission if the traffic class gate is open for at least + * VSC9959_TAS_MIN_GATE_LEN_NS. + * * Overruns are prevented by cropping an interval at the end of the gate time - * slot for which egress scheduling is blocked, but we need to still keep 33 ns - * available for one packet to be transmitted, otherwise the port tc will hang. + * slot for which egress scheduling is blocked, but we need to still keep + * VSC9959_TAS_MIN_GATE_LEN_NS available for one packet to be transmitted, + * otherwise the port tc will hang. + * * This function returns the size of a gate interval that remains available for * setting the guard band, after reserving the space for one egress frame. */ @@ -1303,7 +1307,8 @@ static void vsc9959_tas_guard_bands_update(struct ocelot *ocelot, int port) * per-tc static guard band lengths, so it reduces the * useful gate interval length. Therefore, be careful * to calculate a guard band (and therefore max_sdu) - * that still leaves 33 ns available in the time slot. + * that still leaves VSC9959_TAS_MIN_GATE_LEN_NS + * available in the time slot. */ max_sdu = div_u64(remaining_gate_len_ps, picos_per_byte); /* A TC gate may be completely closed, which is a diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c index 0a68b526e4a8..2b784ced0645 100644 --- a/drivers/net/ethernet/broadcom/bcmsysport.c +++ b/drivers/net/ethernet/broadcom/bcmsysport.c @@ -1967,7 +1967,11 @@ static int bcm_sysport_open(struct net_device *dev) unsigned int i; int ret; - clk_prepare_enable(priv->clk); + ret = clk_prepare_enable(priv->clk); + if (ret) { + netdev_err(dev, "could not enable priv clock\n"); + return ret; + } /* Reset UniMAC */ umac_reset(priv); @@ -2625,7 +2629,11 @@ static int bcm_sysport_probe(struct platform_device *pdev) goto err_deregister_notifier; } - clk_prepare_enable(priv->clk); + ret = clk_prepare_enable(priv->clk); + if (ret) { + dev_err(&pdev->dev, "could not enable priv clock\n"); + goto err_deregister_netdev; + } priv->rev = topctrl_readl(priv, REV_CNTL) & REV_MASK; dev_info(&pdev->dev, @@ -2639,6 +2647,8 @@ static int bcm_sysport_probe(struct platform_device *pdev) return 0; +err_deregister_netdev: + unregister_netdev(dev); err_deregister_notifier: unregister_netdevice_notifier(&priv->netdev_notifier); err_deregister_fixed_link: @@ -2808,7 +2818,12 @@ static int __maybe_unused bcm_sysport_resume(struct device *d) if (!netif_running(dev)) return 0; - clk_prepare_enable(priv->clk); + ret = clk_prepare_enable(priv->clk); + if (ret) { + netdev_err(dev, "could not enable priv clock\n"); + return ret; + } + if (priv->wolopts) clk_disable_unprepare(priv->wol_clk); diff --git a/drivers/net/ethernet/broadcom/bgmac-platform.c b/drivers/net/ethernet/broadcom/bgmac-platform.c index 77425c7a32db..78f7862ca006 100644 --- a/drivers/net/ethernet/broadcom/bgmac-platform.c +++ b/drivers/net/ethernet/broadcom/bgmac-platform.c @@ -171,6 +171,7 @@ static int platform_phy_connect(struct bgmac *bgmac) static int bgmac_probe(struct platform_device *pdev) { struct device_node *np = pdev->dev.of_node; + struct device_node *phy_node; struct bgmac *bgmac; struct resource *regs; int ret; @@ -236,7 +237,9 @@ static int bgmac_probe(struct platform_device *pdev) bgmac->cco_ctl_maskset = platform_bgmac_cco_ctl_maskset; bgmac->get_bus_clock = platform_bgmac_get_bus_clock; bgmac->cmn_maskset32 = platform_bgmac_cmn_maskset32; - if (of_parse_phandle(np, "phy-handle", 0)) { + phy_node = of_parse_phandle(np, "phy-handle", 0); + if (phy_node) { + of_node_put(phy_node); bgmac->phy_connect = platform_phy_connect; } else { bgmac->phy_connect = bgmac_phy_connect_direct; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 3d9ee91e1f8b..dafc5a4039cd 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -1518,7 +1518,7 @@ static void bnxt_tpa_start(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, if (TPA_START_IS_IPV6(tpa_start1)) tpa_info->gso_type = SKB_GSO_TCPV6; /* RSS profiles 1 and 3 with extract code 0 for inner 4-tuple */ - else if (cmp_type == CMP_TYPE_RX_L2_TPA_START_CMP && + else if (!BNXT_CHIP_P4_PLUS(bp) && TPA_START_HASH_TYPE(tpa_start) == 3) tpa_info->gso_type = SKB_GSO_TCPV6; tpa_info->rss_hash = @@ -2212,15 +2212,13 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr, if (cmp_type == CMP_TYPE_RX_L2_V3_CMP) { type = bnxt_rss_ext_op(bp, rxcmp); } else { - u32 hash_type = RX_CMP_HASH_TYPE(rxcmp); + u32 itypes = RX_CMP_ITYPES(rxcmp); - /* RSS profiles 1 and 3 with extract code 0 for inner - * 4-tuple - */ - if (hash_type != 1 && hash_type != 3) - type = PKT_HASH_TYPE_L3; - else + if (itypes == RX_CMP_FLAGS_ITYPE_TCP || + itypes == RX_CMP_FLAGS_ITYPE_UDP) type = PKT_HASH_TYPE_L4; + else + type = PKT_HASH_TYPE_L3; } skb_set_hash(skb, le32_to_cpu(rxcmp->rx_cmp_rss_hash), type); } diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index 69231e85140b..9e05704d9445 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -267,6 +267,9 @@ struct rx_cmp { (((le32_to_cpu((rxcmp)->rx_cmp_misc_v1) & RX_CMP_RSS_HASH_TYPE) >>\ RX_CMP_RSS_HASH_TYPE_SHIFT) & RSS_PROFILE_ID_MASK) +#define RX_CMP_ITYPES(rxcmp) \ + (le32_to_cpu((rxcmp)->rx_cmp_len_flags_type) & RX_CMP_FLAGS_ITYPES_MASK) + #define RX_CMP_V3_HASH_TYPE_LEGACY(rxcmp) \ ((le32_to_cpu((rxcmp)->rx_cmp_misc_v1) & RX_CMP_V3_RSS_EXT_OP_LEGACY) >>\ RX_CMP_V3_RSS_EXT_OP_LEGACY_SHIFT) @@ -378,7 +381,7 @@ struct rx_agg_cmp { u32 rx_agg_cmp_opaque; __le32 rx_agg_cmp_v; #define RX_AGG_CMP_V (1 << 0) - #define RX_AGG_CMP_AGG_ID (0xffff << 16) + #define RX_AGG_CMP_AGG_ID (0x0fff << 16) #define RX_AGG_CMP_AGG_ID_SHIFT 16 __le32 rx_agg_cmp_unused; }; @@ -416,7 +419,7 @@ struct rx_tpa_start_cmp { #define RX_TPA_START_CMP_V3_RSS_HASH_TYPE_SHIFT 7 #define RX_TPA_START_CMP_AGG_ID (0x7f << 25) #define RX_TPA_START_CMP_AGG_ID_SHIFT 25 - #define RX_TPA_START_CMP_AGG_ID_P5 (0xffff << 16) + #define RX_TPA_START_CMP_AGG_ID_P5 (0x0fff << 16) #define RX_TPA_START_CMP_AGG_ID_SHIFT_P5 16 #define RX_TPA_START_CMP_METADATA1 (0xf << 28) #define RX_TPA_START_CMP_METADATA1_SHIFT 28 @@ -540,7 +543,7 @@ struct rx_tpa_end_cmp { #define RX_TPA_END_CMP_PAYLOAD_OFFSET_SHIFT 16 #define RX_TPA_END_CMP_AGG_ID (0x7f << 25) #define RX_TPA_END_CMP_AGG_ID_SHIFT 25 - #define RX_TPA_END_CMP_AGG_ID_P5 (0xffff << 16) + #define RX_TPA_END_CMP_AGG_ID_P5 (0x0fff << 16) #define RX_TPA_END_CMP_AGG_ID_SHIFT_P5 16 __le32 rx_tpa_end_cmp_tsdelta; diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h index bbf7641a0fc7..7e13cd69f68a 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h @@ -2077,7 +2077,7 @@ void t4_idma_monitor(struct adapter *adapter, struct sge_idma_monitor_state *idma, int hz, int ticks); int t4_set_vf_mac_acl(struct adapter *adapter, unsigned int vf, - unsigned int naddr, u8 *addr); + u8 start, unsigned int naddr, u8 *addr); void t4_tp_pio_read(struct adapter *adap, u32 *buff, u32 nregs, u32 start_index, bool sleep_ok); void t4_tp_tm_pio_read(struct adapter *adap, u32 *buff, u32 nregs, diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c index 2418645c8823..fb3933fbb842 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c @@ -3246,7 +3246,7 @@ static int cxgb4_mgmt_set_vf_mac(struct net_device *dev, int vf, u8 *mac) dev_info(pi->adapter->pdev_dev, "Setting MAC %pM on VF %d\n", mac, vf); - ret = t4_set_vf_mac_acl(adap, vf + 1, 1, mac); + ret = t4_set_vf_mac_acl(adap, vf + 1, pi->lport, 1, mac); if (!ret) ether_addr_copy(adap->vfinfo[vf].vf_mac_addr, mac); return ret; diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c index 76de55306c4d..175bf9b13058 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c @@ -10215,11 +10215,12 @@ out: * t4_set_vf_mac_acl - Set MAC address for the specified VF * @adapter: The adapter * @vf: one of the VFs instantiated by the specified PF + * @start: The start port id associated with specified VF * @naddr: the number of MAC addresses * @addr: the MAC address(es) to be set to the specified VF */ int t4_set_vf_mac_acl(struct adapter *adapter, unsigned int vf, - unsigned int naddr, u8 *addr) + u8 start, unsigned int naddr, u8 *addr) { struct fw_acl_mac_cmd cmd; @@ -10234,7 +10235,7 @@ int t4_set_vf_mac_acl(struct adapter *adapter, unsigned int vf, cmd.en_to_len16 = cpu_to_be32((unsigned int)FW_LEN16(cmd)); cmd.nmac = naddr; - switch (adapter->pf) { + switch (start) { case 3: memcpy(cmd.macaddr3, addr, sizeof(cmd.macaddr3)); break; diff --git a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_main.c b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_main.c index 455a54708be4..a83e7d3c2485 100644 --- a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_main.c +++ b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_main.c @@ -346,8 +346,9 @@ static struct sk_buff *copy_gl_to_skb_pkt(const struct pkt_gl *gl, * driver. Once driver synthesizes cpl_pass_accpet_req the skb will go * through the regular cpl_pass_accept_req processing in TOM. */ - skb = alloc_skb(gl->tot_len + sizeof(struct cpl_pass_accept_req) - - pktshift, GFP_ATOMIC); + skb = alloc_skb(size_add(gl->tot_len, + sizeof(struct cpl_pass_accept_req)) - + pktshift, GFP_ATOMIC); if (unlikely(!skb)) return NULL; __skb_put(skb, gl->tot_len + sizeof(struct cpl_pass_accept_req) diff --git a/drivers/net/ethernet/google/gve/gve.h b/drivers/net/ethernet/google/gve/gve.h index 301fa1ea4f51..95471cfcff42 100644 --- a/drivers/net/ethernet/google/gve/gve.h +++ b/drivers/net/ethernet/google/gve/gve.h @@ -1134,6 +1134,7 @@ int gve_xdp_xmit_one(struct gve_priv *priv, struct gve_tx_ring *tx, void gve_xdp_tx_flush(struct gve_priv *priv, u32 xdp_qid); bool gve_tx_poll(struct gve_notify_block *block, int budget); bool gve_xdp_poll(struct gve_notify_block *block, int budget); +int gve_xsk_tx_poll(struct gve_notify_block *block, int budget); int gve_tx_alloc_rings_gqi(struct gve_priv *priv, struct gve_tx_alloc_rings_cfg *cfg); void gve_tx_free_rings_gqi(struct gve_priv *priv, diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c index 661566db68c8..d404819ebc9b 100644 --- a/drivers/net/ethernet/google/gve/gve_main.c +++ b/drivers/net/ethernet/google/gve/gve_main.c @@ -333,6 +333,14 @@ int gve_napi_poll(struct napi_struct *napi, int budget) if (block->rx) { work_done = gve_rx_poll(block, budget); + + /* Poll XSK TX as part of RX NAPI. Setup re-poll based on max of + * TX and RX work done. + */ + if (priv->xdp_prog) + work_done = max_t(int, work_done, + gve_xsk_tx_poll(block, budget)); + reschedule |= work_done == budget; } @@ -922,11 +930,13 @@ static void gve_init_sync_stats(struct gve_priv *priv) static void gve_tx_get_curr_alloc_cfg(struct gve_priv *priv, struct gve_tx_alloc_rings_cfg *cfg) { + int num_xdp_queues = priv->xdp_prog ? priv->rx_cfg.num_queues : 0; + cfg->qcfg = &priv->tx_cfg; cfg->raw_addressing = !gve_is_qpl(priv); cfg->ring_size = priv->tx_desc_cnt; cfg->start_idx = 0; - cfg->num_rings = gve_num_tx_queues(priv); + cfg->num_rings = priv->tx_cfg.num_queues + num_xdp_queues; cfg->tx = priv->tx; } @@ -1623,8 +1633,8 @@ static int gve_xsk_pool_enable(struct net_device *dev, if (err) return err; - /* If XDP prog is not installed, return */ - if (!priv->xdp_prog) + /* If XDP prog is not installed or interface is down, return. */ + if (!priv->xdp_prog || !netif_running(dev)) return 0; rx = &priv->rx[qid]; @@ -1669,21 +1679,16 @@ static int gve_xsk_pool_disable(struct net_device *dev, if (qid >= priv->rx_cfg.num_queues) return -EINVAL; - /* If XDP prog is not installed, unmap DMA and return */ - if (!priv->xdp_prog) - goto done; - - tx_qid = gve_xdp_tx_queue_id(priv, qid); - if (!netif_running(dev)) { - priv->rx[qid].xsk_pool = NULL; - xdp_rxq_info_unreg(&priv->rx[qid].xsk_rxq); - priv->tx[tx_qid].xsk_pool = NULL; + /* If XDP prog is not installed or interface is down, unmap DMA and + * return. + */ + if (!priv->xdp_prog || !netif_running(dev)) goto done; - } napi_rx = &priv->ntfy_blocks[priv->rx[qid].ntfy_id].napi; napi_disable(napi_rx); /* make sure current rx poll is done */ + tx_qid = gve_xdp_tx_queue_id(priv, qid); napi_tx = &priv->ntfy_blocks[priv->tx[tx_qid].ntfy_id].napi; napi_disable(napi_tx); /* make sure current tx poll is done */ @@ -1709,24 +1714,20 @@ done: static int gve_xsk_wakeup(struct net_device *dev, u32 queue_id, u32 flags) { struct gve_priv *priv = netdev_priv(dev); - int tx_queue_id = gve_xdp_tx_queue_id(priv, queue_id); + struct napi_struct *napi; + + if (!gve_get_napi_enabled(priv)) + return -ENETDOWN; if (queue_id >= priv->rx_cfg.num_queues || !priv->xdp_prog) return -EINVAL; - if (flags & XDP_WAKEUP_TX) { - struct gve_tx_ring *tx = &priv->tx[tx_queue_id]; - struct napi_struct *napi = - &priv->ntfy_blocks[tx->ntfy_id].napi; - - if (!napi_if_scheduled_mark_missed(napi)) { - /* Call local_bh_enable to trigger SoftIRQ processing */ - local_bh_disable(); - napi_schedule(napi); - local_bh_enable(); - } - - tx->xdp_xsk_wakeup++; + napi = &priv->ntfy_blocks[gve_rx_idx_to_ntfy(priv, queue_id)].napi; + if (!napi_if_scheduled_mark_missed(napi)) { + /* Call local_bh_enable to trigger SoftIRQ processing */ + local_bh_disable(); + napi_schedule(napi); + local_bh_enable(); } return 0; @@ -1837,6 +1838,7 @@ int gve_adjust_queues(struct gve_priv *priv, { struct gve_tx_alloc_rings_cfg tx_alloc_cfg = {0}; struct gve_rx_alloc_rings_cfg rx_alloc_cfg = {0}; + int num_xdp_queues; int err; gve_get_curr_alloc_cfgs(priv, &tx_alloc_cfg, &rx_alloc_cfg); @@ -1847,6 +1849,10 @@ int gve_adjust_queues(struct gve_priv *priv, rx_alloc_cfg.qcfg = &new_rx_config; tx_alloc_cfg.num_rings = new_tx_config.num_queues; + /* Add dedicated XDP TX queues if enabled. */ + num_xdp_queues = priv->xdp_prog ? new_rx_config.num_queues : 0; + tx_alloc_cfg.num_rings += num_xdp_queues; + if (netif_running(priv->dev)) { err = gve_adjust_config(priv, &tx_alloc_cfg, &rx_alloc_cfg); return err; @@ -1891,6 +1897,9 @@ static void gve_turndown(struct gve_priv *priv) gve_clear_napi_enabled(priv); gve_clear_report_stats(priv); + + /* Make sure that all traffic is finished processing. */ + synchronize_net(); } static void gve_turnup(struct gve_priv *priv) diff --git a/drivers/net/ethernet/google/gve/gve_tx.c b/drivers/net/ethernet/google/gve/gve_tx.c index e7fb7d6d283d..4350ebd9c2bd 100644 --- a/drivers/net/ethernet/google/gve/gve_tx.c +++ b/drivers/net/ethernet/google/gve/gve_tx.c @@ -206,7 +206,10 @@ void gve_tx_stop_ring_gqi(struct gve_priv *priv, int idx) return; gve_remove_napi(priv, ntfy_idx); - gve_clean_tx_done(priv, tx, priv->tx_desc_cnt, false); + if (tx->q_num < priv->tx_cfg.num_queues) + gve_clean_tx_done(priv, tx, priv->tx_desc_cnt, false); + else + gve_clean_xdp_done(priv, tx, priv->tx_desc_cnt); netdev_tx_reset_queue(tx->netdev_txq); gve_tx_remove_from_block(priv, idx); } @@ -834,9 +837,12 @@ int gve_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames, struct gve_tx_ring *tx; int i, err = 0, qid; - if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK)) + if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK) || !priv->xdp_prog) return -EINVAL; + if (!gve_get_napi_enabled(priv)) + return -ENETDOWN; + qid = gve_xdp_tx_queue_id(priv, smp_processor_id() % priv->num_xdp_queues); @@ -975,33 +981,41 @@ out: return sent; } +int gve_xsk_tx_poll(struct gve_notify_block *rx_block, int budget) +{ + struct gve_rx_ring *rx = rx_block->rx; + struct gve_priv *priv = rx->gve; + struct gve_tx_ring *tx; + int sent = 0; + + tx = &priv->tx[gve_xdp_tx_queue_id(priv, rx->q_num)]; + if (tx->xsk_pool) { + sent = gve_xsk_tx(priv, tx, budget); + + u64_stats_update_begin(&tx->statss); + tx->xdp_xsk_sent += sent; + u64_stats_update_end(&tx->statss); + if (xsk_uses_need_wakeup(tx->xsk_pool)) + xsk_set_tx_need_wakeup(tx->xsk_pool); + } + + return sent; +} + bool gve_xdp_poll(struct gve_notify_block *block, int budget) { struct gve_priv *priv = block->priv; struct gve_tx_ring *tx = block->tx; u32 nic_done; - bool repoll; u32 to_do; /* Find out how much work there is to be done */ nic_done = gve_tx_load_event_counter(priv, tx); to_do = min_t(u32, (nic_done - tx->done), budget); gve_clean_xdp_done(priv, tx, to_do); - repoll = nic_done != tx->done; - - if (tx->xsk_pool) { - int sent = gve_xsk_tx(priv, tx, budget); - - u64_stats_update_begin(&tx->statss); - tx->xdp_xsk_sent += sent; - u64_stats_update_end(&tx->statss); - repoll |= (sent == budget); - if (xsk_uses_need_wakeup(tx->xsk_pool)) - xsk_set_tx_need_wakeup(tx->xsk_pool); - } /* If we still have work we want to repoll */ - return repoll; + return nic_done != tx->done; } bool gve_tx_poll(struct gve_notify_block *block, int budget) diff --git a/drivers/net/ethernet/huawei/hinic/hinic_main.c b/drivers/net/ethernet/huawei/hinic/hinic_main.c index 890f213da8d1..ae1f523d6841 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_main.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_main.c @@ -172,6 +172,7 @@ err_init_txq: hinic_sq_dbgfs_uninit(nic_dev); devm_kfree(&netdev->dev, nic_dev->txqs); + nic_dev->txqs = NULL; return err; } @@ -268,6 +269,7 @@ err_init_rxq: hinic_rq_dbgfs_uninit(nic_dev); devm_kfree(&netdev->dev, nic_dev->rxqs); + nic_dev->rxqs = NULL; return err; } diff --git a/drivers/net/ethernet/marvell/mv643xx_eth.c b/drivers/net/ethernet/marvell/mv643xx_eth.c index 9e80899546d9..83b9905666e2 100644 --- a/drivers/net/ethernet/marvell/mv643xx_eth.c +++ b/drivers/net/ethernet/marvell/mv643xx_eth.c @@ -2708,9 +2708,15 @@ static struct platform_device *port_platdev[3]; static void mv643xx_eth_shared_of_remove(void) { + struct mv643xx_eth_platform_data *pd; int n; for (n = 0; n < 3; n++) { + if (!port_platdev[n]) + continue; + pd = dev_get_platdata(&port_platdev[n]->dev); + if (pd) + of_node_put(pd->phy_node); platform_device_del(port_platdev[n]); port_platdev[n] = NULL; } @@ -2773,8 +2779,10 @@ static int mv643xx_eth_shared_of_add_port(struct platform_device *pdev, } ppdev = platform_device_alloc(MV643XX_ETH_NAME, dev_num); - if (!ppdev) - return -ENOMEM; + if (!ppdev) { + ret = -ENOMEM; + goto put_err; + } ppdev->dev.coherent_dma_mask = DMA_BIT_MASK(32); ppdev->dev.of_node = pnp; @@ -2796,6 +2804,8 @@ static int mv643xx_eth_shared_of_add_port(struct platform_device *pdev, port_err: platform_device_put(ppdev); +put_err: + of_node_put(ppd.phy_node); return ret; } diff --git a/drivers/net/ethernet/marvell/sky2.c b/drivers/net/ethernet/marvell/sky2.c index a7a16eac1891..52d99908d0e9 100644 --- a/drivers/net/ethernet/marvell/sky2.c +++ b/drivers/net/ethernet/marvell/sky2.c @@ -130,6 +130,7 @@ static const struct pci_device_id sky2_id_table[] = { { PCI_DEVICE(PCI_VENDOR_ID_MARVELL, 0x436C) }, /* 88E8072 */ { PCI_DEVICE(PCI_VENDOR_ID_MARVELL, 0x436D) }, /* 88E8055 */ { PCI_DEVICE(PCI_VENDOR_ID_MARVELL, 0x4370) }, /* 88E8075 */ + { PCI_DEVICE(PCI_VENDOR_ID_MARVELL, 0x4373) }, /* 88E8075 */ { PCI_DEVICE(PCI_VENDOR_ID_MARVELL, 0x4380) }, /* 88E8057 */ { PCI_DEVICE(PCI_VENDOR_ID_MARVELL, 0x4381) }, /* 88E8059 */ { PCI_DEVICE(PCI_VENDOR_ID_MARVELL, 0x4382) }, /* 88E8079 */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c index cc9bcc420032..6ab02f3fc291 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c @@ -339,9 +339,13 @@ static int mlx5e_macsec_init_sa_fs(struct macsec_context *ctx, { struct mlx5e_priv *priv = macsec_netdev_priv(ctx->netdev); struct mlx5_macsec_fs *macsec_fs = priv->mdev->macsec_fs; + const struct macsec_tx_sc *tx_sc = &ctx->secy->tx_sc; struct mlx5_macsec_rule_attrs rule_attrs; union mlx5_macsec_rule *macsec_rule; + if (is_tx && tx_sc->encoding_sa != sa->assoc_num) + return 0; + rule_attrs.macsec_obj_id = sa->macsec_obj_id; rule_attrs.sci = sa->sci; rule_attrs.assoc_num = sa->assoc_num; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index c14bef83d84d..62b8a7c1c6b5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -6510,8 +6510,23 @@ static void _mlx5e_remove(struct auxiliary_device *adev) mlx5_core_uplink_netdev_set(mdev, NULL); mlx5e_dcbnl_delete_app(priv); - unregister_netdev(priv->netdev); - _mlx5e_suspend(adev, false); + /* When unload driver, the netdev is in registered state + * if it's from legacy mode. If from switchdev mode, it + * is already unregistered before changing to NIC profile. + */ + if (priv->netdev->reg_state == NETREG_REGISTERED) { + unregister_netdev(priv->netdev); + _mlx5e_suspend(adev, false); + } else { + struct mlx5_core_dev *pos; + int i; + + if (test_bit(MLX5E_STATE_DESTROYING, &priv->state)) + mlx5_sd_for_each_dev(i, mdev, pos) + mlx5e_destroy_mdev_resources(pos); + else + _mlx5e_suspend(adev, true); + } /* Avoid cleanup if profile rollback failed. */ if (priv->profile) priv->profile->cleanup(priv); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index 92094bf60d59..0657d1076535 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -1508,6 +1508,21 @@ mlx5e_vport_uplink_rep_unload(struct mlx5e_rep_priv *rpriv) priv = netdev_priv(netdev); + /* This bit is set when using devlink to change eswitch mode from + * switchdev to legacy. As need to keep uplink netdev ifindex, we + * detach uplink representor profile and attach NIC profile only. + * The netdev will be unregistered later when unload NIC auxiliary + * driver for this case. + * We explicitly block devlink eswitch mode change if any IPSec rules + * offloaded, but can't block other cases, such as driver unload + * and devlink reload. We have to unregister netdev before profile + * change for those cases. This is to avoid resource leak because + * the offloaded rules don't have the chance to be unoffloaded before + * cleanup which is triggered by detach uplink representor profile. + */ + if (!(priv->mdev->priv.flags & MLX5_PRIV_FLAGS_SWITCH_LEGACY)) + unregister_netdev(netdev); + mlx5e_netdev_attach_nic_profile(priv); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c index 5a0047bdcb51..ed977ae75fab 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c @@ -150,11 +150,11 @@ void mlx5_esw_ipsec_restore_dest_uplink(struct mlx5_core_dev *mdev) unsigned long i; int err; - xa_for_each(&esw->offloads.vport_reps, i, rep) { - rpriv = rep->rep_data[REP_ETH].priv; - if (!rpriv || !rpriv->netdev) + mlx5_esw_for_each_rep(esw, i, rep) { + if (atomic_read(&rep->rep_data[REP_ETH].state) != REP_LOADED) continue; + rpriv = rep->rep_data[REP_ETH].priv; rhashtable_walk_enter(&rpriv->tc_ht, &iter); rhashtable_walk_start(&iter); while ((flow = rhashtable_walk_next(&iter)) != NULL) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index f44b4c7ebcfd..48fd0400ffd4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -716,6 +716,9 @@ void mlx5e_tc_clean_fdb_peer_flows(struct mlx5_eswitch *esw); MLX5_CAP_GEN_2((esw->dev), ec_vf_vport_base) +\ (last) - 1) +#define mlx5_esw_for_each_rep(esw, i, rep) \ + xa_for_each(&((esw)->offloads.vport_reps), i, rep) + struct mlx5_eswitch *__must_check mlx5_devlink_eswitch_get(struct devlink *devlink); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 8cf61ae8b89d..3950b1d4b3d8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -53,9 +53,6 @@ #include "lag/lag.h" #include "en/tc/post_meter.h" -#define mlx5_esw_for_each_rep(esw, i, rep) \ - xa_for_each(&((esw)->offloads.vport_reps), i, rep) - /* There are two match-all miss flows, one for unicast dst mac and * one for multicast. */ @@ -3762,6 +3759,8 @@ int mlx5_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode, esw->eswitch_operation_in_progress = true; up_write(&esw->mode_lock); + if (mode == DEVLINK_ESWITCH_MODE_LEGACY) + esw->dev->priv.flags |= MLX5_PRIV_FLAGS_SWITCH_LEGACY; mlx5_eswitch_disable_locked(esw); if (mode == DEVLINK_ESWITCH_MODE_SWITCHDEV) { if (mlx5_devlink_trap_get_num_active(esw->dev)) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c index 3d74109f8230..49f22cad92bf 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c @@ -297,7 +297,9 @@ dr_domain_add_vport_cap(struct mlx5dr_domain *dmn, u16 vport) if (ret) { mlx5dr_dbg(dmn, "Couldn't insert new vport into xarray (%d)\n", ret); kvfree(vport_caps); - return ERR_PTR(ret); + if (ret == -EBUSY) + return ERR_PTR(-EBUSY); + return NULL; } return vport_caps; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c index 6fa06ba2d346..f57c84e5128b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c @@ -1067,7 +1067,6 @@ static struct mlx5dr_cq *dr_create_cq(struct mlx5_core_dev *mdev, int inlen, err, eqn; void *cqc, *in; __be64 *pas; - int vector; u32 i; cq = kzalloc(sizeof(*cq), GFP_KERNEL); @@ -1096,8 +1095,7 @@ static struct mlx5dr_cq *dr_create_cq(struct mlx5_core_dev *mdev, if (!in) goto err_cqwq; - vector = raw_smp_processor_id() % mlx5_comp_vectors_max(mdev); - err = mlx5_comp_eqn_get(mdev, vector, &eqn); + err = mlx5_comp_eqn_get(mdev, 0, &eqn); if (err) { kvfree(in); goto err_cqwq; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c index 4b5fd71c897d..32d2e61f2b82 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c @@ -423,8 +423,7 @@ mlxsw_sp_span_gretap4_route(const struct net_device *to_dev, parms = mlxsw_sp_ipip_netdev_parms4(to_dev); ip_tunnel_init_flow(&fl4, parms.iph.protocol, *daddrp, *saddrp, - 0, 0, dev_net(to_dev), parms.link, tun->fwmark, 0, - 0); + 0, 0, tun->net, parms.link, tun->fwmark, 0, 0); rt = ip_route_output_key(tun->net, &fl4); if (IS_ERR(rt)) diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_main.c b/drivers/net/ethernet/microchip/sparx5/sparx5_main.c index b64c814eac11..0c4c75b3682f 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_main.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_main.c @@ -693,12 +693,11 @@ static int sparx5_start(struct sparx5 *sparx5) err = -ENXIO; if (sparx5->fdma_irq >= 0) { if (GCB_CHIP_ID_REV_ID_GET(sparx5->chip_id) > 0) - err = devm_request_threaded_irq(sparx5->dev, - sparx5->fdma_irq, - NULL, - sparx5_fdma_handler, - IRQF_ONESHOT, - "sparx5-fdma", sparx5); + err = devm_request_irq(sparx5->dev, + sparx5->fdma_irq, + sparx5_fdma_handler, + 0, + "sparx5-fdma", sparx5); if (!err) err = sparx5_fdma_start(sparx5); if (err) diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_port.c b/drivers/net/ethernet/microchip/sparx5/sparx5_port.c index 062e486c002c..672508efce5c 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_port.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_port.c @@ -1119,7 +1119,7 @@ int sparx5_port_init(struct sparx5 *sparx5, spx5_inst_rmw(DEV10G_MAC_MAXLEN_CFG_MAX_LEN_SET(ETH_MAXLEN), DEV10G_MAC_MAXLEN_CFG_MAX_LEN, devinst, - DEV10G_MAC_ENA_CFG(0)); + DEV10G_MAC_MAXLEN_CFG(0)); /* Handle Signal Detect in 10G PCS */ spx5_inst_wr(PCS10G_BR_PCS_SD_CFG_SD_POL_SET(sd_pol) | diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c index ca4ed58f1206..0c2ba2fa88c4 100644 --- a/drivers/net/ethernet/microsoft/mana/gdma_main.c +++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c @@ -1315,7 +1315,7 @@ static int mana_gd_setup_irqs(struct pci_dev *pdev) GFP_KERNEL); if (!gc->irq_contexts) { err = -ENOMEM; - goto free_irq_vector; + goto free_irq_array; } for (i = 0; i < nvec; i++) { @@ -1372,6 +1372,7 @@ static int mana_gd_setup_irqs(struct pci_dev *pdev) gc->max_num_msix = nvec; gc->num_msix_usable = nvec; cpus_read_unlock(); + kfree(irqs); return 0; free_irq: @@ -1384,8 +1385,9 @@ free_irq: } kfree(gc->irq_contexts); - kfree(irqs); gc->irq_contexts = NULL; +free_irq_array: + kfree(irqs); free_irq_vector: cpus_read_unlock(); pci_free_irq_vectors(pdev); diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c index 3d72aa7b1305..ef93df520887 100644 --- a/drivers/net/ethernet/mscc/ocelot.c +++ b/drivers/net/ethernet/mscc/ocelot.c @@ -1432,7 +1432,7 @@ void ocelot_ifh_set_basic(void *ifh, struct ocelot *ocelot, int port, memset(ifh, 0, OCELOT_TAG_LEN); ocelot_ifh_set_bypass(ifh, 1); - ocelot_ifh_set_src(ifh, BIT_ULL(ocelot->num_phys_ports)); + ocelot_ifh_set_src(ifh, ocelot->num_phys_ports); ocelot_ifh_set_dest(ifh, BIT_ULL(port)); ocelot_ifh_set_qos_class(ifh, qos_class); ocelot_ifh_set_tag_type(ifh, tag_type); diff --git a/drivers/net/ethernet/mscc/ocelot_ptp.c b/drivers/net/ethernet/mscc/ocelot_ptp.c index e172638b0601..808ce8e68d39 100644 --- a/drivers/net/ethernet/mscc/ocelot_ptp.c +++ b/drivers/net/ethernet/mscc/ocelot_ptp.c @@ -14,6 +14,8 @@ #include <soc/mscc/ocelot.h> #include "ocelot.h" +#define OCELOT_PTP_TX_TSTAMP_TIMEOUT (5 * HZ) + int ocelot_ptp_gettime64(struct ptp_clock_info *ptp, struct timespec64 *ts) { struct ocelot *ocelot = container_of(ptp, struct ocelot, ptp_info); @@ -495,6 +497,28 @@ static int ocelot_traps_to_ptp_rx_filter(unsigned int proto) return HWTSTAMP_FILTER_NONE; } +static int ocelot_ptp_tx_type_to_cmd(int tx_type, int *ptp_cmd) +{ + switch (tx_type) { + case HWTSTAMP_TX_ON: + *ptp_cmd = IFH_REW_OP_TWO_STEP_PTP; + break; + case HWTSTAMP_TX_ONESTEP_SYNC: + /* IFH_REW_OP_ONE_STEP_PTP updates the correctionField, + * what we need to update is the originTimestamp. + */ + *ptp_cmd = IFH_REW_OP_ORIGIN_PTP; + break; + case HWTSTAMP_TX_OFF: + *ptp_cmd = 0; + break; + default: + return -ERANGE; + } + + return 0; +} + int ocelot_hwstamp_get(struct ocelot *ocelot, int port, struct ifreq *ifr) { struct ocelot_port *ocelot_port = ocelot->ports[port]; @@ -521,30 +545,19 @@ EXPORT_SYMBOL(ocelot_hwstamp_get); int ocelot_hwstamp_set(struct ocelot *ocelot, int port, struct ifreq *ifr) { struct ocelot_port *ocelot_port = ocelot->ports[port]; + int ptp_cmd, old_ptp_cmd = ocelot_port->ptp_cmd; bool l2 = false, l4 = false; struct hwtstamp_config cfg; + bool old_l2, old_l4; int err; if (copy_from_user(&cfg, ifr->ifr_data, sizeof(cfg))) return -EFAULT; /* Tx type sanity check */ - switch (cfg.tx_type) { - case HWTSTAMP_TX_ON: - ocelot_port->ptp_cmd = IFH_REW_OP_TWO_STEP_PTP; - break; - case HWTSTAMP_TX_ONESTEP_SYNC: - /* IFH_REW_OP_ONE_STEP_PTP updates the correctional field, we - * need to update the origin time. - */ - ocelot_port->ptp_cmd = IFH_REW_OP_ORIGIN_PTP; - break; - case HWTSTAMP_TX_OFF: - ocelot_port->ptp_cmd = 0; - break; - default: - return -ERANGE; - } + err = ocelot_ptp_tx_type_to_cmd(cfg.tx_type, &ptp_cmd); + if (err) + return err; switch (cfg.rx_filter) { case HWTSTAMP_FILTER_NONE: @@ -569,13 +582,27 @@ int ocelot_hwstamp_set(struct ocelot *ocelot, int port, struct ifreq *ifr) return -ERANGE; } + old_l2 = ocelot_port->trap_proto & OCELOT_PROTO_PTP_L2; + old_l4 = ocelot_port->trap_proto & OCELOT_PROTO_PTP_L4; + err = ocelot_setup_ptp_traps(ocelot, port, l2, l4); if (err) return err; + ocelot_port->ptp_cmd = ptp_cmd; + cfg.rx_filter = ocelot_traps_to_ptp_rx_filter(ocelot_port->trap_proto); - return copy_to_user(ifr->ifr_data, &cfg, sizeof(cfg)) ? -EFAULT : 0; + if (copy_to_user(ifr->ifr_data, &cfg, sizeof(cfg))) { + err = -EFAULT; + goto out_restore_ptp_traps; + } + + return 0; +out_restore_ptp_traps: + ocelot_setup_ptp_traps(ocelot, port, old_l2, old_l4); + ocelot_port->ptp_cmd = old_ptp_cmd; + return err; } EXPORT_SYMBOL(ocelot_hwstamp_set); @@ -603,34 +630,87 @@ int ocelot_get_ts_info(struct ocelot *ocelot, int port, } EXPORT_SYMBOL(ocelot_get_ts_info); -static int ocelot_port_add_txtstamp_skb(struct ocelot *ocelot, int port, - struct sk_buff *clone) +static struct sk_buff *ocelot_port_dequeue_ptp_tx_skb(struct ocelot *ocelot, + int port, u8 ts_id, + u32 seqid) { struct ocelot_port *ocelot_port = ocelot->ports[port]; - unsigned long flags; + struct sk_buff *skb, *skb_tmp, *skb_match = NULL; + struct ptp_header *hdr; - spin_lock_irqsave(&ocelot->ts_id_lock, flags); + spin_lock(&ocelot->ts_id_lock); - if (ocelot_port->ptp_skbs_in_flight == OCELOT_MAX_PTP_ID || - ocelot->ptp_skbs_in_flight == OCELOT_PTP_FIFO_SIZE) { - spin_unlock_irqrestore(&ocelot->ts_id_lock, flags); - return -EBUSY; + skb_queue_walk_safe(&ocelot_port->tx_skbs, skb, skb_tmp) { + if (OCELOT_SKB_CB(skb)->ts_id != ts_id) + continue; + + /* Check that the timestamp ID is for the expected PTP + * sequenceId. We don't have to test ptp_parse_header() against + * NULL, because we've pre-validated the packet's ptp_class. + */ + hdr = ptp_parse_header(skb, OCELOT_SKB_CB(skb)->ptp_class); + if (seqid != ntohs(hdr->sequence_id)) + continue; + + __skb_unlink(skb, &ocelot_port->tx_skbs); + ocelot->ptp_skbs_in_flight--; + skb_match = skb; + break; } - skb_shinfo(clone)->tx_flags |= SKBTX_IN_PROGRESS; - /* Store timestamp ID in OCELOT_SKB_CB(clone)->ts_id */ - OCELOT_SKB_CB(clone)->ts_id = ocelot_port->ts_id; + spin_unlock(&ocelot->ts_id_lock); - ocelot_port->ts_id++; - if (ocelot_port->ts_id == OCELOT_MAX_PTP_ID) - ocelot_port->ts_id = 0; + return skb_match; +} + +static int ocelot_port_queue_ptp_tx_skb(struct ocelot *ocelot, int port, + struct sk_buff *clone) +{ + struct ocelot_port *ocelot_port = ocelot->ports[port]; + DECLARE_BITMAP(ts_id_in_flight, OCELOT_MAX_PTP_ID); + struct sk_buff *skb, *skb_tmp; + unsigned long n; + + spin_lock(&ocelot->ts_id_lock); + + /* To get a better chance of acquiring a timestamp ID, first flush the + * stale packets still waiting in the TX timestamping queue. They are + * probably lost. + */ + skb_queue_walk_safe(&ocelot_port->tx_skbs, skb, skb_tmp) { + if (time_before(OCELOT_SKB_CB(skb)->ptp_tx_time + + OCELOT_PTP_TX_TSTAMP_TIMEOUT, jiffies)) { + dev_warn_ratelimited(ocelot->dev, + "port %d invalidating stale timestamp ID %u which seems lost\n", + port, OCELOT_SKB_CB(skb)->ts_id); + __skb_unlink(skb, &ocelot_port->tx_skbs); + kfree_skb(skb); + ocelot->ptp_skbs_in_flight--; + } else { + __set_bit(OCELOT_SKB_CB(skb)->ts_id, ts_id_in_flight); + } + } + + if (ocelot->ptp_skbs_in_flight == OCELOT_PTP_FIFO_SIZE) { + spin_unlock(&ocelot->ts_id_lock); + return -EBUSY; + } + + n = find_first_zero_bit(ts_id_in_flight, OCELOT_MAX_PTP_ID); + if (n == OCELOT_MAX_PTP_ID) { + spin_unlock(&ocelot->ts_id_lock); + return -EBUSY; + } - ocelot_port->ptp_skbs_in_flight++; + /* Found an available timestamp ID, use it */ + OCELOT_SKB_CB(clone)->ts_id = n; + OCELOT_SKB_CB(clone)->ptp_tx_time = jiffies; ocelot->ptp_skbs_in_flight++; + __skb_queue_tail(&ocelot_port->tx_skbs, clone); - skb_queue_tail(&ocelot_port->tx_skbs, clone); + spin_unlock(&ocelot->ts_id_lock); - spin_unlock_irqrestore(&ocelot->ts_id_lock, flags); + dev_dbg_ratelimited(ocelot->dev, "port %d timestamp id %lu\n", port, n); return 0; } @@ -687,10 +767,14 @@ int ocelot_port_txtstamp_request(struct ocelot *ocelot, int port, if (!(*clone)) return -ENOMEM; - err = ocelot_port_add_txtstamp_skb(ocelot, port, *clone); - if (err) + /* Store timestamp ID in OCELOT_SKB_CB(clone)->ts_id */ + err = ocelot_port_queue_ptp_tx_skb(ocelot, port, *clone); + if (err) { + kfree_skb(*clone); return err; + } + skb_shinfo(*clone)->tx_flags |= SKBTX_IN_PROGRESS; OCELOT_SKB_CB(skb)->ptp_cmd = ptp_cmd; OCELOT_SKB_CB(*clone)->ptp_class = ptp_class; } @@ -726,28 +810,15 @@ static void ocelot_get_hwtimestamp(struct ocelot *ocelot, spin_unlock_irqrestore(&ocelot->ptp_clock_lock, flags); } -static bool ocelot_validate_ptp_skb(struct sk_buff *clone, u16 seqid) -{ - struct ptp_header *hdr; - - hdr = ptp_parse_header(clone, OCELOT_SKB_CB(clone)->ptp_class); - if (WARN_ON(!hdr)) - return false; - - return seqid == ntohs(hdr->sequence_id); -} - void ocelot_get_txtstamp(struct ocelot *ocelot) { int budget = OCELOT_PTP_QUEUE_SZ; while (budget--) { - struct sk_buff *skb, *skb_tmp, *skb_match = NULL; struct skb_shared_hwtstamps shhwtstamps; u32 val, id, seqid, txport; - struct ocelot_port *port; + struct sk_buff *skb_match; struct timespec64 ts; - unsigned long flags; val = ocelot_read(ocelot, SYS_PTP_STATUS); @@ -762,36 +833,14 @@ void ocelot_get_txtstamp(struct ocelot *ocelot) txport = SYS_PTP_STATUS_PTP_MESS_TXPORT_X(val); seqid = SYS_PTP_STATUS_PTP_MESS_SEQ_ID(val); - port = ocelot->ports[txport]; - - spin_lock(&ocelot->ts_id_lock); - port->ptp_skbs_in_flight--; - ocelot->ptp_skbs_in_flight--; - spin_unlock(&ocelot->ts_id_lock); - /* Retrieve its associated skb */ -try_again: - spin_lock_irqsave(&port->tx_skbs.lock, flags); - - skb_queue_walk_safe(&port->tx_skbs, skb, skb_tmp) { - if (OCELOT_SKB_CB(skb)->ts_id != id) - continue; - __skb_unlink(skb, &port->tx_skbs); - skb_match = skb; - break; - } - - spin_unlock_irqrestore(&port->tx_skbs.lock, flags); - - if (WARN_ON(!skb_match)) - continue; - - if (!ocelot_validate_ptp_skb(skb_match, seqid)) { - dev_err_ratelimited(ocelot->dev, - "port %d received stale TX timestamp for seqid %d, discarding\n", - txport, seqid); - dev_kfree_skb_any(skb); - goto try_again; + skb_match = ocelot_port_dequeue_ptp_tx_skb(ocelot, txport, id, + seqid); + if (!skb_match) { + dev_warn_ratelimited(ocelot->dev, + "port %d received TX timestamp (seqid %d, ts id %u) for packet previously declared stale\n", + txport, seqid, id); + goto next_ts; } /* Get the h/w timestamp */ @@ -802,7 +851,7 @@ try_again: shhwtstamps.hwtstamp = ktime_set(ts.tv_sec, ts.tv_nsec); skb_complete_tx_timestamp(skb_match, &shhwtstamps); - /* Next ts */ +next_ts: ocelot_write(ocelot, SYS_PTP_NXT_PTP_NXT, SYS_PTP_NXT); } } diff --git a/drivers/net/ethernet/oa_tc6.c b/drivers/net/ethernet/oa_tc6.c index f9c0dcd965c2..db200e4ec284 100644 --- a/drivers/net/ethernet/oa_tc6.c +++ b/drivers/net/ethernet/oa_tc6.c @@ -113,6 +113,7 @@ struct oa_tc6 { struct mii_bus *mdiobus; struct spi_device *spi; struct mutex spi_ctrl_lock; /* Protects spi control transfer */ + spinlock_t tx_skb_lock; /* Protects tx skb handling */ void *spi_ctrl_tx_buf; void *spi_ctrl_rx_buf; void *spi_data_tx_buf; @@ -1004,8 +1005,10 @@ static u16 oa_tc6_prepare_spi_tx_buf_for_tx_skbs(struct oa_tc6 *tc6) for (used_tx_credits = 0; used_tx_credits < tc6->tx_credits; used_tx_credits++) { if (!tc6->ongoing_tx_skb) { + spin_lock_bh(&tc6->tx_skb_lock); tc6->ongoing_tx_skb = tc6->waiting_tx_skb; tc6->waiting_tx_skb = NULL; + spin_unlock_bh(&tc6->tx_skb_lock); } if (!tc6->ongoing_tx_skb) break; @@ -1111,8 +1114,9 @@ static int oa_tc6_spi_thread_handler(void *data) /* This kthread will be waken up if there is a tx skb or mac-phy * interrupt to perform spi transfer with tx chunks. */ - wait_event_interruptible(tc6->spi_wq, tc6->waiting_tx_skb || - tc6->int_flag || + wait_event_interruptible(tc6->spi_wq, tc6->int_flag || + (tc6->waiting_tx_skb && + tc6->tx_credits) || kthread_should_stop()); if (kthread_should_stop()) @@ -1209,7 +1213,9 @@ netdev_tx_t oa_tc6_start_xmit(struct oa_tc6 *tc6, struct sk_buff *skb) return NETDEV_TX_OK; } + spin_lock_bh(&tc6->tx_skb_lock); tc6->waiting_tx_skb = skb; + spin_unlock_bh(&tc6->tx_skb_lock); /* Wake spi kthread to perform spi transfer */ wake_up_interruptible(&tc6->spi_wq); @@ -1239,6 +1245,7 @@ struct oa_tc6 *oa_tc6_init(struct spi_device *spi, struct net_device *netdev) tc6->netdev = netdev; SET_NETDEV_DEV(netdev, &spi->dev); mutex_init(&tc6->spi_ctrl_lock); + spin_lock_init(&tc6->tx_skb_lock); /* Set the SPI controller to pump at realtime priority */ tc6->spi->rt = true; diff --git a/drivers/net/ethernet/pensando/ionic/ionic_dev.c b/drivers/net/ethernet/pensando/ionic/ionic_dev.c index 9e42d599840d..57edcde9e6f8 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_dev.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_dev.c @@ -277,7 +277,10 @@ void ionic_dev_teardown(struct ionic *ionic) idev->phy_cmb_pages = 0; idev->cmb_npages = 0; - destroy_workqueue(ionic->wq); + if (ionic->wq) { + destroy_workqueue(ionic->wq); + ionic->wq = NULL; + } mutex_destroy(&idev->cmb_inuse_lock); } diff --git a/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c b/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c index dda22fa4448c..9b7f78b6cdb1 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c @@ -961,8 +961,8 @@ static int ionic_get_module_eeprom(struct net_device *netdev, len = min_t(u32, sizeof(xcvr->sprom), ee->len); do { - memcpy(data, xcvr->sprom, len); - memcpy(tbuf, xcvr->sprom, len); + memcpy(data, &xcvr->sprom[ee->offset], len); + memcpy(tbuf, &xcvr->sprom[ee->offset], len); /* Let's make sure we got a consistent copy */ if (!memcmp(data, tbuf, len)) diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c index 40496587b2b3..3d3f936779f7 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c @@ -3869,8 +3869,8 @@ int ionic_lif_register(struct ionic_lif *lif) /* only register LIF0 for now */ err = register_netdev(lif->netdev); if (err) { - dev_err(lif->ionic->dev, "Cannot register net device, aborting\n"); - ionic_lif_unregister_phc(lif); + dev_err(lif->ionic->dev, "Cannot register net device: %d, aborting\n", err); + ionic_lif_unregister(lif); return err; } diff --git a/drivers/net/ethernet/qualcomm/qca_spi.c b/drivers/net/ethernet/qualcomm/qca_spi.c index 8f7ce6b51a1c..6b4b40c6e1fe 100644 --- a/drivers/net/ethernet/qualcomm/qca_spi.c +++ b/drivers/net/ethernet/qualcomm/qca_spi.c @@ -53,7 +53,7 @@ MODULE_PARM_DESC(qcaspi_burst_len, "Number of data bytes per burst. Use 1-5000." #define QCASPI_PLUGGABLE_MIN 0 #define QCASPI_PLUGGABLE_MAX 1 -static int qcaspi_pluggable = QCASPI_PLUGGABLE_MIN; +static int qcaspi_pluggable = QCASPI_PLUGGABLE_MAX; module_param(qcaspi_pluggable, int, 0); MODULE_PARM_DESC(qcaspi_pluggable, "Pluggable SPI connection (yes/no)."); @@ -812,7 +812,6 @@ qcaspi_netdev_init(struct net_device *dev) dev->mtu = QCAFRM_MAX_MTU; dev->type = ARPHRD_ETHER; - qca->clkspeed = qcaspi_clkspeed; qca->burst_len = qcaspi_burst_len; qca->spi_thread = NULL; qca->buffer_size = (QCAFRM_MAX_MTU + VLAN_ETH_HLEN + QCAFRM_HEADER_LEN + @@ -903,17 +902,15 @@ qca_spi_probe(struct spi_device *spi) legacy_mode = of_property_read_bool(spi->dev.of_node, "qca,legacy-mode"); - if (qcaspi_clkspeed == 0) { - if (spi->max_speed_hz) - qcaspi_clkspeed = spi->max_speed_hz; - else - qcaspi_clkspeed = QCASPI_CLK_SPEED; - } + if (qcaspi_clkspeed) + spi->max_speed_hz = qcaspi_clkspeed; + else if (!spi->max_speed_hz) + spi->max_speed_hz = QCASPI_CLK_SPEED; - if ((qcaspi_clkspeed < QCASPI_CLK_SPEED_MIN) || - (qcaspi_clkspeed > QCASPI_CLK_SPEED_MAX)) { - dev_err(&spi->dev, "Invalid clkspeed: %d\n", - qcaspi_clkspeed); + if (spi->max_speed_hz < QCASPI_CLK_SPEED_MIN || + spi->max_speed_hz > QCASPI_CLK_SPEED_MAX) { + dev_err(&spi->dev, "Invalid clkspeed: %u\n", + spi->max_speed_hz); return -EINVAL; } @@ -938,14 +935,13 @@ qca_spi_probe(struct spi_device *spi) return -EINVAL; } - dev_info(&spi->dev, "ver=%s, clkspeed=%d, burst_len=%d, pluggable=%d\n", + dev_info(&spi->dev, "ver=%s, clkspeed=%u, burst_len=%d, pluggable=%d\n", QCASPI_DRV_VERSION, - qcaspi_clkspeed, + spi->max_speed_hz, qcaspi_burst_len, qcaspi_pluggable); spi->mode = SPI_MODE_3; - spi->max_speed_hz = qcaspi_clkspeed; if (spi_setup(spi) < 0) { dev_err(&spi->dev, "Unable to setup SPI device\n"); return -EFAULT; diff --git a/drivers/net/ethernet/qualcomm/qca_spi.h b/drivers/net/ethernet/qualcomm/qca_spi.h index 8f4808695e82..0831cefc58b8 100644 --- a/drivers/net/ethernet/qualcomm/qca_spi.h +++ b/drivers/net/ethernet/qualcomm/qca_spi.h @@ -89,7 +89,6 @@ struct qcaspi { #endif /* user configurable options */ - u32 clkspeed; u8 legacy_mode; u16 burst_len; }; diff --git a/drivers/net/ethernet/renesas/rswitch.c b/drivers/net/ethernet/renesas/rswitch.c index b80aa27a7214..f86fcecb91a8 100644 --- a/drivers/net/ethernet/renesas/rswitch.c +++ b/drivers/net/ethernet/renesas/rswitch.c @@ -547,7 +547,6 @@ static int rswitch_gwca_ts_queue_alloc(struct rswitch_private *priv) desc = &gq->ts_ring[gq->ring_size]; desc->desc.die_dt = DT_LINKFIX; rswitch_desc_set_dptr(&desc->desc, gq->ring_dma); - INIT_LIST_HEAD(&priv->gwca.ts_info_list); return 0; } @@ -862,13 +861,10 @@ static void rswitch_tx_free(struct net_device *ndev) struct rswitch_ext_desc *desc; struct sk_buff *skb; - for (; rswitch_get_num_cur_queues(gq) > 0; - gq->dirty = rswitch_next_queue_index(gq, false, 1)) { - desc = &gq->tx_ring[gq->dirty]; - if ((desc->desc.die_dt & DT_MASK) != DT_FEMPTY) - break; - + desc = &gq->tx_ring[gq->dirty]; + while ((desc->desc.die_dt & DT_MASK) == DT_FEMPTY) { dma_rmb(); + skb = gq->skbs[gq->dirty]; if (skb) { rdev->ndev->stats.tx_packets++; @@ -879,7 +875,10 @@ static void rswitch_tx_free(struct net_device *ndev) dev_kfree_skb_any(gq->skbs[gq->dirty]); gq->skbs[gq->dirty] = NULL; } + desc->desc.die_dt = DT_EEMPTY; + gq->dirty = rswitch_next_queue_index(gq, false, 1); + desc = &gq->tx_ring[gq->dirty]; } } @@ -908,8 +907,10 @@ retry: if (napi_complete_done(napi, budget - quota)) { spin_lock_irqsave(&priv->lock, flags); - rswitch_enadis_data_irq(priv, rdev->tx_queue->index, true); - rswitch_enadis_data_irq(priv, rdev->rx_queue->index, true); + if (test_bit(rdev->port, priv->opened_ports)) { + rswitch_enadis_data_irq(priv, rdev->tx_queue->index, true); + rswitch_enadis_data_irq(priv, rdev->rx_queue->index, true); + } spin_unlock_irqrestore(&priv->lock, flags); } @@ -1001,9 +1002,10 @@ static int rswitch_gwca_request_irqs(struct rswitch_private *priv) static void rswitch_ts(struct rswitch_private *priv) { struct rswitch_gwca_queue *gq = &priv->gwca.ts_queue; - struct rswitch_gwca_ts_info *ts_info, *ts_info2; struct skb_shared_hwtstamps shhwtstamps; struct rswitch_ts_desc *desc; + struct rswitch_device *rdev; + struct sk_buff *ts_skb; struct timespec64 ts; unsigned int num; u32 tag, port; @@ -1013,23 +1015,28 @@ static void rswitch_ts(struct rswitch_private *priv) dma_rmb(); port = TS_DESC_DPN(__le32_to_cpu(desc->desc.dptrl)); - tag = TS_DESC_TSUN(__le32_to_cpu(desc->desc.dptrl)); - - list_for_each_entry_safe(ts_info, ts_info2, &priv->gwca.ts_info_list, list) { - if (!(ts_info->port == port && ts_info->tag == tag)) - continue; - - memset(&shhwtstamps, 0, sizeof(shhwtstamps)); - ts.tv_sec = __le32_to_cpu(desc->ts_sec); - ts.tv_nsec = __le32_to_cpu(desc->ts_nsec & cpu_to_le32(0x3fffffff)); - shhwtstamps.hwtstamp = timespec64_to_ktime(ts); - skb_tstamp_tx(ts_info->skb, &shhwtstamps); - dev_consume_skb_irq(ts_info->skb); - list_del(&ts_info->list); - kfree(ts_info); - break; - } + if (unlikely(port >= RSWITCH_NUM_PORTS)) + goto next; + rdev = priv->rdev[port]; + tag = TS_DESC_TSUN(__le32_to_cpu(desc->desc.dptrl)); + if (unlikely(tag >= TS_TAGS_PER_PORT)) + goto next; + ts_skb = xchg(&rdev->ts_skb[tag], NULL); + smp_mb(); /* order rdev->ts_skb[] read before bitmap update */ + clear_bit(tag, rdev->ts_skb_used); + + if (unlikely(!ts_skb)) + goto next; + + memset(&shhwtstamps, 0, sizeof(shhwtstamps)); + ts.tv_sec = __le32_to_cpu(desc->ts_sec); + ts.tv_nsec = __le32_to_cpu(desc->ts_nsec & cpu_to_le32(0x3fffffff)); + shhwtstamps.hwtstamp = timespec64_to_ktime(ts); + skb_tstamp_tx(ts_skb, &shhwtstamps); + dev_consume_skb_irq(ts_skb); + +next: gq->cur = rswitch_next_queue_index(gq, true, 1); desc = &gq->ts_ring[gq->cur]; } @@ -1114,25 +1121,40 @@ static int rswitch_etha_wait_link_verification(struct rswitch_etha *etha) static void rswitch_rmac_setting(struct rswitch_etha *etha, const u8 *mac) { - u32 val; + u32 pis, lsc; rswitch_etha_write_mac_address(etha, mac); + switch (etha->phy_interface) { + case PHY_INTERFACE_MODE_SGMII: + pis = MPIC_PIS_GMII; + break; + case PHY_INTERFACE_MODE_USXGMII: + case PHY_INTERFACE_MODE_5GBASER: + pis = MPIC_PIS_XGMII; + break; + default: + pis = FIELD_GET(MPIC_PIS, ioread32(etha->addr + MPIC)); + break; + } + switch (etha->speed) { case 100: - val = MPIC_LSC_100M; + lsc = MPIC_LSC_100M; break; case 1000: - val = MPIC_LSC_1G; + lsc = MPIC_LSC_1G; break; case 2500: - val = MPIC_LSC_2_5G; + lsc = MPIC_LSC_2_5G; break; default: - return; + lsc = FIELD_GET(MPIC_LSC, ioread32(etha->addr + MPIC)); + break; } - iowrite32(MPIC_PIS_GMII | val, etha->addr + MPIC); + rswitch_modify(etha->addr, MPIC, MPIC_PIS | MPIC_LSC, + FIELD_PREP(MPIC_PIS, pis) | FIELD_PREP(MPIC_LSC, lsc)); } static void rswitch_etha_enable_mii(struct rswitch_etha *etha) @@ -1538,20 +1560,20 @@ static int rswitch_open(struct net_device *ndev) struct rswitch_device *rdev = netdev_priv(ndev); unsigned long flags; - phy_start(ndev->phydev); + if (bitmap_empty(rdev->priv->opened_ports, RSWITCH_NUM_PORTS)) + iowrite32(GWCA_TS_IRQ_BIT, rdev->priv->addr + GWTSDIE); napi_enable(&rdev->napi); - netif_start_queue(ndev); spin_lock_irqsave(&rdev->priv->lock, flags); + bitmap_set(rdev->priv->opened_ports, rdev->port, 1); rswitch_enadis_data_irq(rdev->priv, rdev->tx_queue->index, true); rswitch_enadis_data_irq(rdev->priv, rdev->rx_queue->index, true); spin_unlock_irqrestore(&rdev->priv->lock, flags); - if (bitmap_empty(rdev->priv->opened_ports, RSWITCH_NUM_PORTS)) - iowrite32(GWCA_TS_IRQ_BIT, rdev->priv->addr + GWTSDIE); + phy_start(ndev->phydev); - bitmap_set(rdev->priv->opened_ports, rdev->port, 1); + netif_start_queue(ndev); return 0; }; @@ -1559,31 +1581,34 @@ static int rswitch_open(struct net_device *ndev) static int rswitch_stop(struct net_device *ndev) { struct rswitch_device *rdev = netdev_priv(ndev); - struct rswitch_gwca_ts_info *ts_info, *ts_info2; + struct sk_buff *ts_skb; unsigned long flags; + unsigned int tag; netif_tx_stop_all_queues(ndev); - bitmap_clear(rdev->priv->opened_ports, rdev->port, 1); - - if (bitmap_empty(rdev->priv->opened_ports, RSWITCH_NUM_PORTS)) - iowrite32(GWCA_TS_IRQ_BIT, rdev->priv->addr + GWTSDID); - list_for_each_entry_safe(ts_info, ts_info2, &rdev->priv->gwca.ts_info_list, list) { - if (ts_info->port != rdev->port) - continue; - dev_kfree_skb_irq(ts_info->skb); - list_del(&ts_info->list); - kfree(ts_info); - } + phy_stop(ndev->phydev); spin_lock_irqsave(&rdev->priv->lock, flags); rswitch_enadis_data_irq(rdev->priv, rdev->tx_queue->index, false); rswitch_enadis_data_irq(rdev->priv, rdev->rx_queue->index, false); + bitmap_clear(rdev->priv->opened_ports, rdev->port, 1); spin_unlock_irqrestore(&rdev->priv->lock, flags); - phy_stop(ndev->phydev); napi_disable(&rdev->napi); + if (bitmap_empty(rdev->priv->opened_ports, RSWITCH_NUM_PORTS)) + iowrite32(GWCA_TS_IRQ_BIT, rdev->priv->addr + GWTSDID); + + for (tag = find_first_bit(rdev->ts_skb_used, TS_TAGS_PER_PORT); + tag < TS_TAGS_PER_PORT; + tag = find_next_bit(rdev->ts_skb_used, TS_TAGS_PER_PORT, tag + 1)) { + ts_skb = xchg(&rdev->ts_skb[tag], NULL); + clear_bit(tag, rdev->ts_skb_used); + if (ts_skb) + dev_kfree_skb(ts_skb); + } + return 0; }; @@ -1594,20 +1619,17 @@ static bool rswitch_ext_desc_set_info1(struct rswitch_device *rdev, desc->info1 = cpu_to_le64(INFO1_DV(BIT(rdev->etha->index)) | INFO1_IPV(GWCA_IPV_NUM) | INFO1_FMT); if (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) { - struct rswitch_gwca_ts_info *ts_info; + unsigned int tag; - ts_info = kzalloc(sizeof(*ts_info), GFP_ATOMIC); - if (!ts_info) + tag = find_first_zero_bit(rdev->ts_skb_used, TS_TAGS_PER_PORT); + if (tag == TS_TAGS_PER_PORT) return false; + smp_mb(); /* order bitmap read before rdev->ts_skb[] write */ + rdev->ts_skb[tag] = skb_get(skb); + set_bit(tag, rdev->ts_skb_used); skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS; - rdev->ts_tag++; - desc->info1 |= cpu_to_le64(INFO1_TSUN(rdev->ts_tag) | INFO1_TXC); - - ts_info->skb = skb_get(skb); - ts_info->port = rdev->port; - ts_info->tag = rdev->ts_tag; - list_add_tail(&ts_info->list, &rdev->priv->gwca.ts_info_list); + desc->info1 |= cpu_to_le64(INFO1_TSUN(tag) | INFO1_TXC); skb_tx_timestamp(skb); } @@ -1681,8 +1703,11 @@ static netdev_tx_t rswitch_start_xmit(struct sk_buff *skb, struct net_device *nd if (dma_mapping_error(ndev->dev.parent, dma_addr_orig)) goto err_kfree; - gq->skbs[gq->cur] = skb; - gq->unmap_addrs[gq->cur] = dma_addr_orig; + /* Stored the skb at the last descriptor to avoid skb free before hardware completes send */ + gq->skbs[(gq->cur + nr_desc - 1) % gq->ring_size] = skb; + gq->unmap_addrs[(gq->cur + nr_desc - 1) % gq->ring_size] = dma_addr_orig; + + dma_wmb(); /* DT_FSTART should be set at last. So, this is reverse order. */ for (i = nr_desc; i-- > 0; ) { @@ -1694,14 +1719,13 @@ static netdev_tx_t rswitch_start_xmit(struct sk_buff *skb, struct net_device *nd goto err_unmap; } - wmb(); /* gq->cur must be incremented after die_dt was set */ - gq->cur = rswitch_next_queue_index(gq, true, nr_desc); rswitch_modify(rdev->addr, GWTRC(gq->index), 0, BIT(gq->index % 32)); return ret; err_unmap: + gq->skbs[(gq->cur + nr_desc - 1) % gq->ring_size] = NULL; dma_unmap_single(ndev->dev.parent, dma_addr_orig, skb->len, DMA_TO_DEVICE); err_kfree: @@ -1889,7 +1913,6 @@ static int rswitch_device_alloc(struct rswitch_private *priv, unsigned int index rdev->np_port = rswitch_get_port_node(rdev); rdev->disabled = !rdev->np_port; err = of_get_ethdev_address(rdev->np_port, ndev); - of_node_put(rdev->np_port); if (err) { if (is_valid_ether_addr(rdev->etha->mac_addr)) eth_hw_addr_set(ndev, rdev->etha->mac_addr); @@ -1919,6 +1942,7 @@ out_txdmac: out_rxdmac: out_get_params: + of_node_put(rdev->np_port); netif_napi_del(&rdev->napi); free_netdev(ndev); @@ -1932,6 +1956,7 @@ static void rswitch_device_free(struct rswitch_private *priv, unsigned int index rswitch_txdmac_free(ndev); rswitch_rxdmac_free(ndev); + of_node_put(rdev->np_port); netif_napi_del(&rdev->napi); free_netdev(ndev); } diff --git a/drivers/net/ethernet/renesas/rswitch.h b/drivers/net/ethernet/renesas/rswitch.h index 72e3ff596d31..d8d4ed7d7f8b 100644 --- a/drivers/net/ethernet/renesas/rswitch.h +++ b/drivers/net/ethernet/renesas/rswitch.h @@ -724,13 +724,13 @@ enum rswitch_etha_mode { #define EAVCC_VEM_SC_TAG (0x3 << 16) -#define MPIC_PIS_MII 0x00 -#define MPIC_PIS_GMII 0x02 -#define MPIC_PIS_XGMII 0x04 -#define MPIC_LSC_SHIFT 3 -#define MPIC_LSC_100M (1 << MPIC_LSC_SHIFT) -#define MPIC_LSC_1G (2 << MPIC_LSC_SHIFT) -#define MPIC_LSC_2_5G (3 << MPIC_LSC_SHIFT) +#define MPIC_PIS GENMASK(2, 0) +#define MPIC_PIS_GMII 2 +#define MPIC_PIS_XGMII 4 +#define MPIC_LSC GENMASK(5, 3) +#define MPIC_LSC_100M 1 +#define MPIC_LSC_1G 2 +#define MPIC_LSC_2_5G 3 #define MDIO_READ_C45 0x03 #define MDIO_WRITE_C45 0x01 @@ -972,14 +972,6 @@ struct rswitch_gwca_queue { }; }; -struct rswitch_gwca_ts_info { - struct sk_buff *skb; - struct list_head list; - - int port; - u8 tag; -}; - #define RSWITCH_NUM_IRQ_REGS (RSWITCH_MAX_NUM_QUEUES / BITS_PER_TYPE(u32)) struct rswitch_gwca { unsigned int index; @@ -989,7 +981,6 @@ struct rswitch_gwca { struct rswitch_gwca_queue *queues; int num_queues; struct rswitch_gwca_queue ts_queue; - struct list_head ts_info_list; DECLARE_BITMAP(used, RSWITCH_MAX_NUM_QUEUES); u32 tx_irq_bits[RSWITCH_NUM_IRQ_REGS]; u32 rx_irq_bits[RSWITCH_NUM_IRQ_REGS]; @@ -997,6 +988,7 @@ struct rswitch_gwca { }; #define NUM_QUEUES_PER_NDEV 2 +#define TS_TAGS_PER_PORT 256 struct rswitch_device { struct rswitch_private *priv; struct net_device *ndev; @@ -1004,7 +996,8 @@ struct rswitch_device { void __iomem *addr; struct rswitch_gwca_queue *tx_queue; struct rswitch_gwca_queue *rx_queue; - u8 ts_tag; + struct sk_buff *ts_skb[TS_TAGS_PER_PORT]; + DECLARE_BITMAP(ts_skb_used, TS_TAGS_PER_PORT); bool disabled; int port; diff --git a/drivers/net/ethernet/sfc/tc_conntrack.c b/drivers/net/ethernet/sfc/tc_conntrack.c index d90206f27161..c0603f54cec3 100644 --- a/drivers/net/ethernet/sfc/tc_conntrack.c +++ b/drivers/net/ethernet/sfc/tc_conntrack.c @@ -16,7 +16,7 @@ static int efx_tc_flow_block(enum tc_setup_type type, void *type_data, void *cb_priv); static const struct rhashtable_params efx_tc_ct_zone_ht_params = { - .key_len = offsetof(struct efx_tc_ct_zone, linkage), + .key_len = sizeof_field(struct efx_tc_ct_zone, zone), .key_offset = 0, .head_offset = offsetof(struct efx_tc_ct_zone, linkage), }; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 766213ee82c1..cf7b59b8cc64 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -4220,8 +4220,8 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev) struct stmmac_txq_stats *txq_stats; struct stmmac_tx_queue *tx_q; u32 pay_len, mss, queue; + dma_addr_t tso_des, des; u8 proto_hdr_len, hdr; - dma_addr_t des; bool set_ic; int i; @@ -4317,14 +4317,15 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev) /* If needed take extra descriptors to fill the remaining payload */ tmp_pay_len = pay_len - TSO_MAX_BUFF_SIZE; + tso_des = des; } else { stmmac_set_desc_addr(priv, first, des); tmp_pay_len = pay_len; - des += proto_hdr_len; + tso_des = des + proto_hdr_len; pay_len = 0; } - stmmac_tso_allocator(priv, des, tmp_pay_len, (nfrags == 0), queue); + stmmac_tso_allocator(priv, tso_des, tmp_pay_len, (nfrags == 0), queue); /* In case two or more DMA transmit descriptors are allocated for this * non-paged SKB data, the DMA buffer address should be saved to diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index ad868e8d195d..aaf008bdbbcd 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -406,22 +406,6 @@ static int stmmac_of_get_mac_mode(struct device_node *np) } /** - * stmmac_remove_config_dt - undo the effects of stmmac_probe_config_dt() - * @pdev: platform_device structure - * @plat: driver data platform structure - * - * Release resources claimed by stmmac_probe_config_dt(). - */ -static void stmmac_remove_config_dt(struct platform_device *pdev, - struct plat_stmmacenet_data *plat) -{ - clk_disable_unprepare(plat->stmmac_clk); - clk_disable_unprepare(plat->pclk); - of_node_put(plat->phy_node); - of_node_put(plat->mdio_node); -} - -/** * stmmac_probe_config_dt - parse device-tree driver parameters * @pdev: platform_device structure * @mac: MAC address to use @@ -490,8 +474,10 @@ stmmac_probe_config_dt(struct platform_device *pdev, u8 *mac) dev_warn(&pdev->dev, "snps,phy-addr property is deprecated\n"); rc = stmmac_mdio_setup(plat, np, &pdev->dev); - if (rc) - return ERR_PTR(rc); + if (rc) { + ret = ERR_PTR(rc); + goto error_put_phy; + } of_property_read_u32(np, "tx-fifo-depth", &plat->tx_fifo_size); @@ -580,8 +566,8 @@ stmmac_probe_config_dt(struct platform_device *pdev, u8 *mac) dma_cfg = devm_kzalloc(&pdev->dev, sizeof(*dma_cfg), GFP_KERNEL); if (!dma_cfg) { - stmmac_remove_config_dt(pdev, plat); - return ERR_PTR(-ENOMEM); + ret = ERR_PTR(-ENOMEM); + goto error_put_mdio; } plat->dma_cfg = dma_cfg; @@ -609,8 +595,8 @@ stmmac_probe_config_dt(struct platform_device *pdev, u8 *mac) rc = stmmac_mtl_setup(pdev, plat); if (rc) { - stmmac_remove_config_dt(pdev, plat); - return ERR_PTR(rc); + ret = ERR_PTR(rc); + goto error_put_mdio; } /* clock setup */ @@ -662,6 +648,10 @@ error_hw_init: clk_disable_unprepare(plat->pclk); error_pclk_get: clk_disable_unprepare(plat->stmmac_clk); +error_put_mdio: + of_node_put(plat->mdio_node); +error_put_phy: + of_node_put(plat->phy_node); return ret; } @@ -670,16 +660,17 @@ static void devm_stmmac_remove_config_dt(void *data) { struct plat_stmmacenet_data *plat = data; - /* Platform data argument is unused */ - stmmac_remove_config_dt(NULL, plat); + clk_disable_unprepare(plat->stmmac_clk); + clk_disable_unprepare(plat->pclk); + of_node_put(plat->mdio_node); + of_node_put(plat->phy_node); } /** * devm_stmmac_probe_config_dt * @pdev: platform_device structure * @mac: MAC address to use - * Description: Devres variant of stmmac_probe_config_dt(). Does not require - * the user to call stmmac_remove_config_dt() at driver detach. + * Description: Devres variant of stmmac_probe_config_dt(). */ struct plat_stmmacenet_data * devm_stmmac_probe_config_dt(struct platform_device *pdev, u8 *mac) diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c index ba6db61dd227..dfca13b82bdc 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c +++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c @@ -3525,7 +3525,7 @@ static int am65_cpsw_nuss_probe(struct platform_device *pdev) init_completion(&common->tdown_complete); common->tx_ch_num = AM65_CPSW_DEFAULT_TX_CHNS; common->rx_ch_num_flows = AM65_CPSW_DEFAULT_RX_CHN_FLOWS; - common->pf_p0_rx_ptype_rrobin = false; + common->pf_p0_rx_ptype_rrobin = true; common->default_vlan = 1; common->ports = devm_kcalloc(dev, common->port_num, diff --git a/drivers/net/ethernet/ti/icssg/icss_iep.c b/drivers/net/ethernet/ti/icssg/icss_iep.c index 5d6d1cf78e93..768578c0d958 100644 --- a/drivers/net/ethernet/ti/icssg/icss_iep.c +++ b/drivers/net/ethernet/ti/icssg/icss_iep.c @@ -215,6 +215,9 @@ static void icss_iep_enable_shadow_mode(struct icss_iep *iep) for (cmp = IEP_MIN_CMP; cmp < IEP_MAX_CMP; cmp++) { regmap_update_bits(iep->map, ICSS_IEP_CMP_STAT_REG, IEP_CMP_STATUS(cmp), IEP_CMP_STATUS(cmp)); + + regmap_update_bits(iep->map, ICSS_IEP_CMP_CFG_REG, + IEP_CMP_CFG_CMP_EN(cmp), 0); } /* enable reset counter on CMP0 event */ @@ -780,6 +783,11 @@ int icss_iep_exit(struct icss_iep *iep) } icss_iep_disable(iep); + if (iep->pps_enabled) + icss_iep_pps_enable(iep, false); + else if (iep->perout_enabled) + icss_iep_perout_enable(iep, NULL, false); + return 0; } EXPORT_SYMBOL_GPL(icss_iep_exit); diff --git a/drivers/net/ethernet/ti/icssg/icssg_common.c b/drivers/net/ethernet/ti/icssg/icssg_common.c index fdebeb2f84e0..74f0f200a89d 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_common.c +++ b/drivers/net/ethernet/ti/icssg/icssg_common.c @@ -855,31 +855,6 @@ irqreturn_t prueth_rx_irq(int irq, void *dev_id) } EXPORT_SYMBOL_GPL(prueth_rx_irq); -void prueth_emac_stop(struct prueth_emac *emac) -{ - struct prueth *prueth = emac->prueth; - int slice; - - switch (emac->port_id) { - case PRUETH_PORT_MII0: - slice = ICSS_SLICE0; - break; - case PRUETH_PORT_MII1: - slice = ICSS_SLICE1; - break; - default: - netdev_err(emac->ndev, "invalid port\n"); - return; - } - - emac->fw_running = 0; - if (!emac->is_sr1) - rproc_shutdown(prueth->txpru[slice]); - rproc_shutdown(prueth->rtu[slice]); - rproc_shutdown(prueth->pru[slice]); -} -EXPORT_SYMBOL_GPL(prueth_emac_stop); - void prueth_cleanup_tx_ts(struct prueth_emac *emac) { int i; diff --git a/drivers/net/ethernet/ti/icssg/icssg_config.c b/drivers/net/ethernet/ti/icssg/icssg_config.c index 5d2491c2943a..ddfd1c02a885 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_config.c +++ b/drivers/net/ethernet/ti/icssg/icssg_config.c @@ -397,7 +397,7 @@ static int prueth_emac_buffer_setup(struct prueth_emac *emac) return 0; } -static void icssg_init_emac_mode(struct prueth *prueth) +void icssg_init_emac_mode(struct prueth *prueth) { /* When the device is configured as a bridge and it is being brought * back to the emac mode, the host mac address has to be set as 0. @@ -406,9 +406,6 @@ static void icssg_init_emac_mode(struct prueth *prueth) int i; u8 mac[ETH_ALEN] = { 0 }; - if (prueth->emacs_initialized) - return; - /* Set VLAN TABLE address base */ regmap_update_bits(prueth->miig_rt, FDB_GEN_CFG1, SMEM_VLAN_OFFSET_MASK, addr << SMEM_VLAN_OFFSET); @@ -423,15 +420,13 @@ static void icssg_init_emac_mode(struct prueth *prueth) /* Clear host MAC address */ icssg_class_set_host_mac_addr(prueth->miig_rt, mac); } +EXPORT_SYMBOL_GPL(icssg_init_emac_mode); -static void icssg_init_fw_offload_mode(struct prueth *prueth) +void icssg_init_fw_offload_mode(struct prueth *prueth) { u32 addr = prueth->shram.pa + EMAC_ICSSG_SWITCH_DEFAULT_VLAN_TABLE_OFFSET; int i; - if (prueth->emacs_initialized) - return; - /* Set VLAN TABLE address base */ regmap_update_bits(prueth->miig_rt, FDB_GEN_CFG1, SMEM_VLAN_OFFSET_MASK, addr << SMEM_VLAN_OFFSET); @@ -448,6 +443,7 @@ static void icssg_init_fw_offload_mode(struct prueth *prueth) icssg_class_set_host_mac_addr(prueth->miig_rt, prueth->hw_bridge_dev->dev_addr); icssg_set_pvid(prueth, prueth->default_vlan, PRUETH_PORT_HOST); } +EXPORT_SYMBOL_GPL(icssg_init_fw_offload_mode); int icssg_config(struct prueth *prueth, struct prueth_emac *emac, int slice) { @@ -455,11 +451,6 @@ int icssg_config(struct prueth *prueth, struct prueth_emac *emac, int slice) struct icssg_flow_cfg __iomem *flow_cfg; int ret; - if (prueth->is_switch_mode || prueth->is_hsr_offload_mode) - icssg_init_fw_offload_mode(prueth); - else - icssg_init_emac_mode(prueth); - memset_io(config, 0, TAS_GATE_MASK_LIST0); icssg_miig_queues_init(prueth, slice); @@ -786,3 +777,27 @@ void icssg_set_pvid(struct prueth *prueth, u8 vid, u8 port) writel(pvid, prueth->shram.va + EMAC_ICSSG_SWITCH_PORT0_DEFAULT_VLAN_OFFSET); } EXPORT_SYMBOL_GPL(icssg_set_pvid); + +int emac_fdb_flow_id_updated(struct prueth_emac *emac) +{ + struct mgmt_cmd_rsp fdb_cmd_rsp = { 0 }; + int slice = prueth_emac_slice(emac); + struct mgmt_cmd fdb_cmd = { 0 }; + int ret; + + fdb_cmd.header = ICSSG_FW_MGMT_CMD_HEADER; + fdb_cmd.type = ICSSG_FW_MGMT_FDB_CMD_TYPE_RX_FLOW; + fdb_cmd.seqnum = ++(emac->prueth->icssg_hwcmdseq); + fdb_cmd.param = 0; + + fdb_cmd.param |= (slice << 4); + fdb_cmd.cmd_args[0] = 0; + + ret = icssg_send_fdb_msg(emac, &fdb_cmd, &fdb_cmd_rsp); + if (ret) + return ret; + + WARN_ON(fdb_cmd.seqnum != fdb_cmd_rsp.seqnum); + return fdb_cmd_rsp.status == 1 ? 0 : -EINVAL; +} +EXPORT_SYMBOL_GPL(emac_fdb_flow_id_updated); diff --git a/drivers/net/ethernet/ti/icssg/icssg_config.h b/drivers/net/ethernet/ti/icssg/icssg_config.h index 92c2deaa3068..c884e9fa099e 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_config.h +++ b/drivers/net/ethernet/ti/icssg/icssg_config.h @@ -55,6 +55,7 @@ struct icssg_rxq_ctx { #define ICSSG_FW_MGMT_FDB_CMD_TYPE 0x03 #define ICSSG_FW_MGMT_CMD_TYPE 0x04 #define ICSSG_FW_MGMT_PKT 0x80000000 +#define ICSSG_FW_MGMT_FDB_CMD_TYPE_RX_FLOW 0x05 struct icssg_r30_cmd { u32 cmd[4]; diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.c b/drivers/net/ethernet/ti/icssg/icssg_prueth.c index fe2fd1bfc904..cb11635a8d12 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_prueth.c +++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.c @@ -164,11 +164,26 @@ static struct icssg_firmwares icssg_emac_firmwares[] = { } }; -static int prueth_emac_start(struct prueth *prueth, struct prueth_emac *emac) +static int prueth_start(struct rproc *rproc, const char *fw_name) +{ + int ret; + + ret = rproc_set_firmware(rproc, fw_name); + if (ret) + return ret; + return rproc_boot(rproc); +} + +static void prueth_shutdown(struct rproc *rproc) +{ + rproc_shutdown(rproc); +} + +static int prueth_emac_start(struct prueth *prueth) { struct icssg_firmwares *firmwares; struct device *dev = prueth->dev; - int slice, ret; + int ret, slice; if (prueth->is_switch_mode) firmwares = icssg_switch_firmwares; @@ -177,49 +192,126 @@ static int prueth_emac_start(struct prueth *prueth, struct prueth_emac *emac) else firmwares = icssg_emac_firmwares; - slice = prueth_emac_slice(emac); - if (slice < 0) { - netdev_err(emac->ndev, "invalid port\n"); - return -EINVAL; + for (slice = 0; slice < PRUETH_NUM_MACS; slice++) { + ret = prueth_start(prueth->pru[slice], firmwares[slice].pru); + if (ret) { + dev_err(dev, "failed to boot PRU%d: %d\n", slice, ret); + goto unwind_slices; + } + + ret = prueth_start(prueth->rtu[slice], firmwares[slice].rtu); + if (ret) { + dev_err(dev, "failed to boot RTU%d: %d\n", slice, ret); + rproc_shutdown(prueth->pru[slice]); + goto unwind_slices; + } + + ret = prueth_start(prueth->txpru[slice], firmwares[slice].txpru); + if (ret) { + dev_err(dev, "failed to boot TX_PRU%d: %d\n", slice, ret); + rproc_shutdown(prueth->rtu[slice]); + rproc_shutdown(prueth->pru[slice]); + goto unwind_slices; + } } - ret = icssg_config(prueth, emac, slice); - if (ret) - return ret; + return 0; - ret = rproc_set_firmware(prueth->pru[slice], firmwares[slice].pru); - ret = rproc_boot(prueth->pru[slice]); - if (ret) { - dev_err(dev, "failed to boot PRU%d: %d\n", slice, ret); - return -EINVAL; +unwind_slices: + while (--slice >= 0) { + prueth_shutdown(prueth->txpru[slice]); + prueth_shutdown(prueth->rtu[slice]); + prueth_shutdown(prueth->pru[slice]); } - ret = rproc_set_firmware(prueth->rtu[slice], firmwares[slice].rtu); - ret = rproc_boot(prueth->rtu[slice]); - if (ret) { - dev_err(dev, "failed to boot RTU%d: %d\n", slice, ret); - goto halt_pru; + return ret; +} + +static void prueth_emac_stop(struct prueth *prueth) +{ + int slice; + + for (slice = 0; slice < PRUETH_NUM_MACS; slice++) { + prueth_shutdown(prueth->txpru[slice]); + prueth_shutdown(prueth->rtu[slice]); + prueth_shutdown(prueth->pru[slice]); } +} + +static int prueth_emac_common_start(struct prueth *prueth) +{ + struct prueth_emac *emac; + int ret = 0; + int slice; + + if (!prueth->emac[ICSS_SLICE0] && !prueth->emac[ICSS_SLICE1]) + return -EINVAL; + + /* clear SMEM and MSMC settings for all slices */ + memset_io(prueth->msmcram.va, 0, prueth->msmcram.size); + memset_io(prueth->shram.va, 0, ICSSG_CONFIG_OFFSET_SLICE1 * PRUETH_NUM_MACS); + + icssg_class_default(prueth->miig_rt, ICSS_SLICE0, 0, false); + icssg_class_default(prueth->miig_rt, ICSS_SLICE1, 0, false); + + if (prueth->is_switch_mode || prueth->is_hsr_offload_mode) + icssg_init_fw_offload_mode(prueth); + else + icssg_init_emac_mode(prueth); + + for (slice = 0; slice < PRUETH_NUM_MACS; slice++) { + emac = prueth->emac[slice]; + if (!emac) + continue; + ret = icssg_config(prueth, emac, slice); + if (ret) + goto disable_class; + } + + ret = prueth_emac_start(prueth); + if (ret) + goto disable_class; - ret = rproc_set_firmware(prueth->txpru[slice], firmwares[slice].txpru); - ret = rproc_boot(prueth->txpru[slice]); + emac = prueth->emac[ICSS_SLICE0] ? prueth->emac[ICSS_SLICE0] : + prueth->emac[ICSS_SLICE1]; + ret = icss_iep_init(emac->iep, &prueth_iep_clockops, + emac, IEP_DEFAULT_CYCLE_TIME_NS); if (ret) { - dev_err(dev, "failed to boot TX_PRU%d: %d\n", slice, ret); - goto halt_rtu; + dev_err(prueth->dev, "Failed to initialize IEP module\n"); + goto stop_pruss; } - emac->fw_running = 1; return 0; -halt_rtu: - rproc_shutdown(prueth->rtu[slice]); +stop_pruss: + prueth_emac_stop(prueth); -halt_pru: - rproc_shutdown(prueth->pru[slice]); +disable_class: + icssg_class_disable(prueth->miig_rt, ICSS_SLICE0); + icssg_class_disable(prueth->miig_rt, ICSS_SLICE1); return ret; } +static int prueth_emac_common_stop(struct prueth *prueth) +{ + struct prueth_emac *emac; + + if (!prueth->emac[ICSS_SLICE0] && !prueth->emac[ICSS_SLICE1]) + return -EINVAL; + + icssg_class_disable(prueth->miig_rt, ICSS_SLICE0); + icssg_class_disable(prueth->miig_rt, ICSS_SLICE1); + + prueth_emac_stop(prueth); + + emac = prueth->emac[ICSS_SLICE0] ? prueth->emac[ICSS_SLICE0] : + prueth->emac[ICSS_SLICE1]; + icss_iep_exit(emac->iep); + + return 0; +} + /* called back by PHY layer if there is change in link state of hw port*/ static void emac_adjust_link(struct net_device *ndev) { @@ -374,9 +466,6 @@ static void prueth_iep_settime(void *clockops_data, u64 ns) u32 cycletime; int timeout; - if (!emac->fw_running) - return; - sc_descp = emac->prueth->shram.va + TIMESYNC_FW_WC_SETCLOCK_DESC_OFFSET; cycletime = IEP_DEFAULT_CYCLE_TIME_NS; @@ -543,23 +632,17 @@ static int emac_ndo_open(struct net_device *ndev) { struct prueth_emac *emac = netdev_priv(ndev); int ret, i, num_data_chn = emac->tx_ch_num; + struct icssg_flow_cfg __iomem *flow_cfg; struct prueth *prueth = emac->prueth; int slice = prueth_emac_slice(emac); struct device *dev = prueth->dev; int max_rx_flows; int rx_flow; - /* clear SMEM and MSMC settings for all slices */ - if (!prueth->emacs_initialized) { - memset_io(prueth->msmcram.va, 0, prueth->msmcram.size); - memset_io(prueth->shram.va, 0, ICSSG_CONFIG_OFFSET_SLICE1 * PRUETH_NUM_MACS); - } - /* set h/w MAC as user might have re-configured */ ether_addr_copy(emac->mac_addr, ndev->dev_addr); icssg_class_set_mac_addr(prueth->miig_rt, slice, emac->mac_addr); - icssg_class_default(prueth->miig_rt, slice, 0, false); icssg_ft1_set_mac_addr(prueth->miig_rt, slice, emac->mac_addr); /* Notify the stack of the actual queue counts. */ @@ -597,18 +680,23 @@ static int emac_ndo_open(struct net_device *ndev) goto cleanup_napi; } - /* reset and start PRU firmware */ - ret = prueth_emac_start(prueth, emac); - if (ret) - goto free_rx_irq; + if (!prueth->emacs_initialized) { + ret = prueth_emac_common_start(prueth); + if (ret) + goto free_rx_irq; + } - icssg_mii_update_mtu(prueth->mii_rt, slice, ndev->max_mtu); + flow_cfg = emac->dram.va + ICSSG_CONFIG_OFFSET + PSI_L_REGULAR_FLOW_ID_BASE_OFFSET; + writew(emac->rx_flow_id_base, &flow_cfg->rx_base_flow); + ret = emac_fdb_flow_id_updated(emac); - if (!prueth->emacs_initialized) { - ret = icss_iep_init(emac->iep, &prueth_iep_clockops, - emac, IEP_DEFAULT_CYCLE_TIME_NS); + if (ret) { + netdev_err(ndev, "Failed to update Rx Flow ID %d", ret); + goto stop; } + icssg_mii_update_mtu(prueth->mii_rt, slice, ndev->max_mtu); + ret = request_threaded_irq(emac->tx_ts_irq, NULL, prueth_tx_ts_irq, IRQF_ONESHOT, dev_name(dev), emac); if (ret) @@ -653,7 +741,8 @@ reset_rx_chn: free_tx_ts_irq: free_irq(emac->tx_ts_irq, emac); stop: - prueth_emac_stop(emac); + if (!prueth->emacs_initialized) + prueth_emac_common_stop(prueth); free_rx_irq: free_irq(emac->rx_chns.irq[rx_flow], emac); cleanup_napi: @@ -689,8 +778,6 @@ static int emac_ndo_stop(struct net_device *ndev) if (ndev->phydev) phy_stop(ndev->phydev); - icssg_class_disable(prueth->miig_rt, prueth_emac_slice(emac)); - if (emac->prueth->is_hsr_offload_mode) __dev_mc_unsync(ndev, icssg_prueth_hsr_del_mcast); else @@ -728,11 +815,9 @@ static int emac_ndo_stop(struct net_device *ndev) /* Destroying the queued work in ndo_stop() */ cancel_delayed_work_sync(&emac->stats_work); - if (prueth->emacs_initialized == 1) - icss_iep_exit(emac->iep); - /* stop PRUs */ - prueth_emac_stop(emac); + if (prueth->emacs_initialized == 1) + prueth_emac_common_stop(prueth); free_irq(emac->tx_ts_irq, emac); @@ -1010,10 +1095,11 @@ static void prueth_offload_fwd_mark_update(struct prueth *prueth) } } -static void prueth_emac_restart(struct prueth *prueth) +static int prueth_emac_restart(struct prueth *prueth) { struct prueth_emac *emac0 = prueth->emac[PRUETH_MAC0]; struct prueth_emac *emac1 = prueth->emac[PRUETH_MAC1]; + int ret; /* Detach the net_device for both PRUeth ports*/ if (netif_running(emac0->ndev)) @@ -1022,36 +1108,46 @@ static void prueth_emac_restart(struct prueth *prueth) netif_device_detach(emac1->ndev); /* Disable both PRUeth ports */ - icssg_set_port_state(emac0, ICSSG_EMAC_PORT_DISABLE); - icssg_set_port_state(emac1, ICSSG_EMAC_PORT_DISABLE); + ret = icssg_set_port_state(emac0, ICSSG_EMAC_PORT_DISABLE); + ret |= icssg_set_port_state(emac1, ICSSG_EMAC_PORT_DISABLE); + if (ret) + return ret; /* Stop both pru cores for both PRUeth ports*/ - prueth_emac_stop(emac0); - prueth->emacs_initialized--; - prueth_emac_stop(emac1); - prueth->emacs_initialized--; + ret = prueth_emac_common_stop(prueth); + if (ret) { + dev_err(prueth->dev, "Failed to stop the firmwares"); + return ret; + } /* Start both pru cores for both PRUeth ports */ - prueth_emac_start(prueth, emac0); - prueth->emacs_initialized++; - prueth_emac_start(prueth, emac1); - prueth->emacs_initialized++; + ret = prueth_emac_common_start(prueth); + if (ret) { + dev_err(prueth->dev, "Failed to start the firmwares"); + return ret; + } /* Enable forwarding for both PRUeth ports */ - icssg_set_port_state(emac0, ICSSG_EMAC_PORT_FORWARD); - icssg_set_port_state(emac1, ICSSG_EMAC_PORT_FORWARD); + ret = icssg_set_port_state(emac0, ICSSG_EMAC_PORT_FORWARD); + ret |= icssg_set_port_state(emac1, ICSSG_EMAC_PORT_FORWARD); /* Attache net_device for both PRUeth ports */ netif_device_attach(emac0->ndev); netif_device_attach(emac1->ndev); + + return ret; } static void icssg_change_mode(struct prueth *prueth) { struct prueth_emac *emac; - int mac; + int mac, ret; - prueth_emac_restart(prueth); + ret = prueth_emac_restart(prueth); + if (ret) { + dev_err(prueth->dev, "Failed to restart the firmwares, aborting the process"); + return; + } for (mac = PRUETH_MAC0; mac < PRUETH_NUM_MACS; mac++) { emac = prueth->emac[mac]; @@ -1130,13 +1226,18 @@ static void prueth_netdevice_port_unlink(struct net_device *ndev) { struct prueth_emac *emac = netdev_priv(ndev); struct prueth *prueth = emac->prueth; + int ret; prueth->br_members &= ~BIT(emac->port_id); if (prueth->is_switch_mode) { prueth->is_switch_mode = false; emac->port_vlan = 0; - prueth_emac_restart(prueth); + ret = prueth_emac_restart(prueth); + if (ret) { + dev_err(prueth->dev, "Failed to restart the firmwares, aborting the process"); + return; + } } prueth_offload_fwd_mark_update(prueth); @@ -1185,6 +1286,7 @@ static void prueth_hsr_port_unlink(struct net_device *ndev) struct prueth *prueth = emac->prueth; struct prueth_emac *emac0; struct prueth_emac *emac1; + int ret; emac0 = prueth->emac[PRUETH_MAC0]; emac1 = prueth->emac[PRUETH_MAC1]; @@ -1195,7 +1297,11 @@ static void prueth_hsr_port_unlink(struct net_device *ndev) emac0->port_vlan = 0; emac1->port_vlan = 0; prueth->hsr_dev = NULL; - prueth_emac_restart(prueth); + ret = prueth_emac_restart(prueth); + if (ret) { + dev_err(prueth->dev, "Failed to restart the firmwares, aborting the process"); + return; + } netdev_dbg(ndev, "Disabling HSR Offload mode\n"); } } @@ -1370,13 +1476,10 @@ static int prueth_probe(struct platform_device *pdev) prueth->pa_stats = NULL; } - if (eth0_node) { + if (eth0_node || eth1_node) { ret = prueth_get_cores(prueth, ICSS_SLICE0, false); if (ret) goto put_cores; - } - - if (eth1_node) { ret = prueth_get_cores(prueth, ICSS_SLICE1, false); if (ret) goto put_cores; @@ -1575,14 +1678,12 @@ put_pruss: pruss_put(prueth->pruss); put_cores: - if (eth1_node) { - prueth_put_cores(prueth, ICSS_SLICE1); - of_node_put(eth1_node); - } - - if (eth0_node) { + if (eth0_node || eth1_node) { prueth_put_cores(prueth, ICSS_SLICE0); of_node_put(eth0_node); + + prueth_put_cores(prueth, ICSS_SLICE1); + of_node_put(eth1_node); } return ret; diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.h b/drivers/net/ethernet/ti/icssg/icssg_prueth.h index f5c1d473e9f9..5473315ea204 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_prueth.h +++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.h @@ -140,7 +140,6 @@ struct prueth_rx_chn { /* data for each emac port */ struct prueth_emac { bool is_sr1; - bool fw_running; struct prueth *prueth; struct net_device *ndev; u8 mac_addr[6]; @@ -361,6 +360,8 @@ int icssg_set_port_state(struct prueth_emac *emac, enum icssg_port_state_cmd state); void icssg_config_set_speed(struct prueth_emac *emac); void icssg_config_half_duplex(struct prueth_emac *emac); +void icssg_init_emac_mode(struct prueth *prueth); +void icssg_init_fw_offload_mode(struct prueth *prueth); /* Buffer queue helpers */ int icssg_queue_pop(struct prueth *prueth, u8 queue); @@ -377,6 +378,7 @@ void icssg_vtbl_modify(struct prueth_emac *emac, u8 vid, u8 port_mask, u8 untag_mask, bool add); u16 icssg_get_pvid(struct prueth_emac *emac); void icssg_set_pvid(struct prueth *prueth, u8 vid, u8 port); +int emac_fdb_flow_id_updated(struct prueth_emac *emac); #define prueth_napi_to_tx_chn(pnapi) \ container_of(pnapi, struct prueth_tx_chn, napi_tx) @@ -407,7 +409,6 @@ void emac_rx_timestamp(struct prueth_emac *emac, struct sk_buff *skb, u32 *psdata); enum netdev_tx icssg_ndo_start_xmit(struct sk_buff *skb, struct net_device *ndev); irqreturn_t prueth_rx_irq(int irq, void *dev_id); -void prueth_emac_stop(struct prueth_emac *emac); void prueth_cleanup_tx_ts(struct prueth_emac *emac); int icssg_napi_rx_poll(struct napi_struct *napi_rx, int budget); int prueth_prepare_rx_chan(struct prueth_emac *emac, diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth_sr1.c b/drivers/net/ethernet/ti/icssg/icssg_prueth_sr1.c index 292f04d29f4f..f88cdc8f012f 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_prueth_sr1.c +++ b/drivers/net/ethernet/ti/icssg/icssg_prueth_sr1.c @@ -440,7 +440,6 @@ static int prueth_emac_start(struct prueth *prueth, struct prueth_emac *emac) goto halt_pru; } - emac->fw_running = 1; return 0; halt_pru: @@ -449,6 +448,29 @@ halt_pru: return ret; } +static void prueth_emac_stop(struct prueth_emac *emac) +{ + struct prueth *prueth = emac->prueth; + int slice; + + switch (emac->port_id) { + case PRUETH_PORT_MII0: + slice = ICSS_SLICE0; + break; + case PRUETH_PORT_MII1: + slice = ICSS_SLICE1; + break; + default: + netdev_err(emac->ndev, "invalid port\n"); + return; + } + + if (!emac->is_sr1) + rproc_shutdown(prueth->txpru[slice]); + rproc_shutdown(prueth->rtu[slice]); + rproc_shutdown(prueth->pru[slice]); +} + /** * emac_ndo_open - EMAC device open * @ndev: network adapter device diff --git a/drivers/net/mdio/fwnode_mdio.c b/drivers/net/mdio/fwnode_mdio.c index b156493d7084..aea0f0357568 100644 --- a/drivers/net/mdio/fwnode_mdio.c +++ b/drivers/net/mdio/fwnode_mdio.c @@ -40,6 +40,7 @@ fwnode_find_pse_control(struct fwnode_handle *fwnode) static struct mii_timestamper * fwnode_find_mii_timestamper(struct fwnode_handle *fwnode) { + struct mii_timestamper *mii_ts; struct of_phandle_args arg; int err; @@ -53,10 +54,16 @@ fwnode_find_mii_timestamper(struct fwnode_handle *fwnode) else if (err) return ERR_PTR(err); - if (arg.args_count != 1) - return ERR_PTR(-EINVAL); + if (arg.args_count != 1) { + mii_ts = ERR_PTR(-EINVAL); + goto put_node; + } + + mii_ts = register_mii_timestamper(arg.np, arg.args[0]); - return register_mii_timestamper(arg.np, arg.args[0]); +put_node: + of_node_put(arg.np); + return mii_ts; } int fwnode_mdiobus_phy_device_register(struct mii_bus *mdio, diff --git a/drivers/net/netdevsim/health.c b/drivers/net/netdevsim/health.c index 70e8bdf34be9..688f05316b5e 100644 --- a/drivers/net/netdevsim/health.c +++ b/drivers/net/netdevsim/health.c @@ -149,6 +149,8 @@ static ssize_t nsim_dev_health_break_write(struct file *file, char *break_msg; int err; + if (count == 0 || count > PAGE_SIZE) + return -EINVAL; break_msg = memdup_user_nul(data, count); if (IS_ERR(break_msg)) return PTR_ERR(break_msg); diff --git a/drivers/net/netdevsim/netdev.c b/drivers/net/netdevsim/netdev.c index 017a6102be0a..1b29d1d794a2 100644 --- a/drivers/net/netdevsim/netdev.c +++ b/drivers/net/netdevsim/netdev.c @@ -596,10 +596,10 @@ nsim_pp_hold_write(struct file *file, const char __user *data, page_pool_put_full_page(ns->page->pp, ns->page, false); ns->page = NULL; } - rtnl_unlock(); exit: - return count; + rtnl_unlock(); + return ret; } static const struct file_operations nsim_pp_hold_fops = { diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c index 65b0a3115e14..64926240b007 100644 --- a/drivers/net/phy/micrel.c +++ b/drivers/net/phy/micrel.c @@ -432,10 +432,12 @@ struct kszphy_ptp_priv { struct kszphy_priv { struct kszphy_ptp_priv ptp_priv; const struct kszphy_type *type; + struct clk *clk; int led_mode; u16 vct_ctrl1000; bool rmii_ref_clk_sel; bool rmii_ref_clk_sel_val; + bool clk_enable; u64 stats[ARRAY_SIZE(kszphy_hw_stats)]; }; @@ -2052,6 +2054,46 @@ static void kszphy_get_stats(struct phy_device *phydev, data[i] = kszphy_get_stat(phydev, i); } +static void kszphy_enable_clk(struct phy_device *phydev) +{ + struct kszphy_priv *priv = phydev->priv; + + if (!priv->clk_enable && priv->clk) { + clk_prepare_enable(priv->clk); + priv->clk_enable = true; + } +} + +static void kszphy_disable_clk(struct phy_device *phydev) +{ + struct kszphy_priv *priv = phydev->priv; + + if (priv->clk_enable && priv->clk) { + clk_disable_unprepare(priv->clk); + priv->clk_enable = false; + } +} + +static int kszphy_generic_resume(struct phy_device *phydev) +{ + kszphy_enable_clk(phydev); + + return genphy_resume(phydev); +} + +static int kszphy_generic_suspend(struct phy_device *phydev) +{ + int ret; + + ret = genphy_suspend(phydev); + if (ret) + return ret; + + kszphy_disable_clk(phydev); + + return 0; +} + static int kszphy_suspend(struct phy_device *phydev) { /* Disable PHY Interrupts */ @@ -2061,7 +2103,7 @@ static int kszphy_suspend(struct phy_device *phydev) phydev->drv->config_intr(phydev); } - return genphy_suspend(phydev); + return kszphy_generic_suspend(phydev); } static void kszphy_parse_led_mode(struct phy_device *phydev) @@ -2092,7 +2134,9 @@ static int kszphy_resume(struct phy_device *phydev) { int ret; - genphy_resume(phydev); + ret = kszphy_generic_resume(phydev); + if (ret) + return ret; /* After switching from power-down to normal mode, an internal global * reset is automatically generated. Wait a minimum of 1 ms before @@ -2114,6 +2158,24 @@ static int kszphy_resume(struct phy_device *phydev) return 0; } +/* Because of errata DS80000700A, receiver error following software + * power down. Suspend and resume callbacks only disable and enable + * external rmii reference clock. + */ +static int ksz8041_resume(struct phy_device *phydev) +{ + kszphy_enable_clk(phydev); + + return 0; +} + +static int ksz8041_suspend(struct phy_device *phydev) +{ + kszphy_disable_clk(phydev); + + return 0; +} + static int ksz9477_resume(struct phy_device *phydev) { int ret; @@ -2161,7 +2223,10 @@ static int ksz8061_resume(struct phy_device *phydev) if (!(ret & BMCR_PDOWN)) return 0; - genphy_resume(phydev); + ret = kszphy_generic_resume(phydev); + if (ret) + return ret; + usleep_range(1000, 2000); /* Re-program the value after chip is reset. */ @@ -2179,6 +2244,11 @@ static int ksz8061_resume(struct phy_device *phydev) return 0; } +static int ksz8061_suspend(struct phy_device *phydev) +{ + return kszphy_suspend(phydev); +} + static int kszphy_probe(struct phy_device *phydev) { const struct kszphy_type *type = phydev->drv->driver_data; @@ -2219,10 +2289,14 @@ static int kszphy_probe(struct phy_device *phydev) } else if (!clk) { /* unnamed clock from the generic ethernet-phy binding */ clk = devm_clk_get_optional_enabled(&phydev->mdio.dev, NULL); - if (IS_ERR(clk)) - return PTR_ERR(clk); } + if (IS_ERR(clk)) + return PTR_ERR(clk); + + clk_disable_unprepare(clk); + priv->clk = clk; + if (ksz8041_fiber_mode(phydev)) phydev->port = PORT_FIBRE; @@ -5292,6 +5366,21 @@ static int lan8841_probe(struct phy_device *phydev) return 0; } +static int lan8804_resume(struct phy_device *phydev) +{ + return kszphy_resume(phydev); +} + +static int lan8804_suspend(struct phy_device *phydev) +{ + return kszphy_generic_suspend(phydev); +} + +static int lan8841_resume(struct phy_device *phydev) +{ + return kszphy_generic_resume(phydev); +} + static int lan8841_suspend(struct phy_device *phydev) { struct kszphy_priv *priv = phydev->priv; @@ -5300,7 +5389,7 @@ static int lan8841_suspend(struct phy_device *phydev) if (ptp_priv->ptp_clock) ptp_cancel_worker_sync(ptp_priv->ptp_clock); - return genphy_suspend(phydev); + return kszphy_generic_suspend(phydev); } static struct phy_driver ksphy_driver[] = { @@ -5360,9 +5449,8 @@ static struct phy_driver ksphy_driver[] = { .get_sset_count = kszphy_get_sset_count, .get_strings = kszphy_get_strings, .get_stats = kszphy_get_stats, - /* No suspend/resume callbacks because of errata DS80000700A, - * receiver error following software power down. - */ + .suspend = ksz8041_suspend, + .resume = ksz8041_resume, }, { .phy_id = PHY_ID_KSZ8041RNLI, .phy_id_mask = MICREL_PHY_ID_MASK, @@ -5438,7 +5526,7 @@ static struct phy_driver ksphy_driver[] = { .soft_reset = genphy_soft_reset, .config_intr = kszphy_config_intr, .handle_interrupt = kszphy_handle_interrupt, - .suspend = kszphy_suspend, + .suspend = ksz8061_suspend, .resume = ksz8061_resume, }, { .phy_id = PHY_ID_KSZ9021, @@ -5509,8 +5597,8 @@ static struct phy_driver ksphy_driver[] = { .get_sset_count = kszphy_get_sset_count, .get_strings = kszphy_get_strings, .get_stats = kszphy_get_stats, - .suspend = genphy_suspend, - .resume = kszphy_resume, + .suspend = lan8804_suspend, + .resume = lan8804_resume, .config_intr = lan8804_config_intr, .handle_interrupt = lan8804_handle_interrupt, }, { @@ -5528,7 +5616,7 @@ static struct phy_driver ksphy_driver[] = { .get_strings = kszphy_get_strings, .get_stats = kszphy_get_stats, .suspend = lan8841_suspend, - .resume = genphy_resume, + .resume = lan8841_resume, .cable_test_start = lan8814_cable_test_start, .cable_test_get_status = ksz886x_cable_test_get_status, }, { diff --git a/drivers/net/pse-pd/tps23881.c b/drivers/net/pse-pd/tps23881.c index 5c4e88be46ee..8797ca1a8a21 100644 --- a/drivers/net/pse-pd/tps23881.c +++ b/drivers/net/pse-pd/tps23881.c @@ -64,15 +64,11 @@ static int tps23881_pi_enable(struct pse_controller_dev *pcdev, int id) if (id >= TPS23881_MAX_CHANS) return -ERANGE; - ret = i2c_smbus_read_word_data(client, TPS23881_REG_PW_STATUS); - if (ret < 0) - return ret; - chan = priv->port[id].chan[0]; if (chan < 4) - val = (u16)(ret | BIT(chan)); + val = BIT(chan); else - val = (u16)(ret | BIT(chan + 4)); + val = BIT(chan + 4); if (priv->port[id].is_4p) { chan = priv->port[id].chan[1]; @@ -100,15 +96,11 @@ static int tps23881_pi_disable(struct pse_controller_dev *pcdev, int id) if (id >= TPS23881_MAX_CHANS) return -ERANGE; - ret = i2c_smbus_read_word_data(client, TPS23881_REG_PW_STATUS); - if (ret < 0) - return ret; - chan = priv->port[id].chan[0]; if (chan < 4) - val = (u16)(ret | BIT(chan + 4)); + val = BIT(chan + 4); else - val = (u16)(ret | BIT(chan + 8)); + val = BIT(chan + 8); if (priv->port[id].is_4p) { chan = priv->port[id].chan[1]; diff --git a/drivers/net/team/team_core.c b/drivers/net/team/team_core.c index 18191d5a8bd4..1c85dda83825 100644 --- a/drivers/net/team/team_core.c +++ b/drivers/net/team/team_core.c @@ -983,7 +983,8 @@ static void team_port_disable(struct team *team, #define TEAM_VLAN_FEATURES (NETIF_F_HW_CSUM | NETIF_F_SG | \ NETIF_F_FRAGLIST | NETIF_F_GSO_SOFTWARE | \ - NETIF_F_HIGHDMA | NETIF_F_LRO) + NETIF_F_HIGHDMA | NETIF_F_LRO | \ + NETIF_F_GSO_ENCAP_ALL) #define TEAM_ENC_FEATURES (NETIF_F_HW_CSUM | NETIF_F_SG | \ NETIF_F_RXCSUM | NETIF_F_GSO_SOFTWARE) @@ -991,14 +992,19 @@ static void team_port_disable(struct team *team, static void __team_compute_features(struct team *team) { struct team_port *port; - netdev_features_t vlan_features = TEAM_VLAN_FEATURES & - NETIF_F_ALL_FOR_ALL; + netdev_features_t vlan_features = TEAM_VLAN_FEATURES; netdev_features_t enc_features = TEAM_ENC_FEATURES; unsigned short max_hard_header_len = ETH_HLEN; unsigned int dst_release_flag = IFF_XMIT_DST_RELEASE | IFF_XMIT_DST_RELEASE_PERM; rcu_read_lock(); + if (list_empty(&team->port_list)) + goto done; + + vlan_features = netdev_base_features(vlan_features); + enc_features = netdev_base_features(enc_features); + list_for_each_entry_rcu(port, &team->port_list, list) { vlan_features = netdev_increment_features(vlan_features, port->dev->vlan_features, @@ -1008,11 +1014,11 @@ static void __team_compute_features(struct team *team) port->dev->hw_enc_features, TEAM_ENC_FEATURES); - dst_release_flag &= port->dev->priv_flags; if (port->dev->hard_header_len > max_hard_header_len) max_hard_header_len = port->dev->hard_header_len; } +done: rcu_read_unlock(); team->dev->vlan_features = vlan_features; @@ -2012,8 +2018,7 @@ static netdev_features_t team_fix_features(struct net_device *dev, netdev_features_t mask; mask = features; - features &= ~NETIF_F_ONE_FOR_ALL; - features |= NETIF_F_ALL_FOR_ALL; + features = netdev_base_features(features); rcu_read_lock(); list_for_each_entry_rcu(port, &team->port_list, list) { diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 9a0f6eb32016..03fe9e3ee7af 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -1481,7 +1481,7 @@ static struct sk_buff *tun_napi_alloc_frags(struct tun_file *tfile, skb->truesize += skb->data_len; for (i = 1; i < it->nr_segs; i++) { - const struct iovec *iov = iter_iov(it); + const struct iovec *iov = iter_iov(it) + i; size_t fragsz = iov->iov_len; struct page *page; void *frag; diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 0c011d8f5d4d..9fe7f704a2f7 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -1365,6 +1365,9 @@ static const struct usb_device_id products[] = { {QMI_QUIRK_SET_DTR(0x1bc7, 0x10a0, 0)}, /* Telit FN920C04 */ {QMI_QUIRK_SET_DTR(0x1bc7, 0x10a4, 0)}, /* Telit FN920C04 */ {QMI_QUIRK_SET_DTR(0x1bc7, 0x10a9, 0)}, /* Telit FN920C04 */ + {QMI_QUIRK_SET_DTR(0x1bc7, 0x10c0, 0)}, /* Telit FE910C04 */ + {QMI_QUIRK_SET_DTR(0x1bc7, 0x10c4, 0)}, /* Telit FE910C04 */ + {QMI_QUIRK_SET_DTR(0x1bc7, 0x10c8, 0)}, /* Telit FE910C04 */ {QMI_FIXED_INTF(0x1bc7, 0x1100, 3)}, /* Telit ME910 */ {QMI_FIXED_INTF(0x1bc7, 0x1101, 3)}, /* Telit ME910 dual modem */ {QMI_FIXED_INTF(0x1bc7, 0x1200, 5)}, /* Telit LE920 */ diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index c897afef0b41..60027b439021 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -502,6 +502,7 @@ struct virtio_net_common_hdr { }; static void virtnet_sq_free_unused_buf(struct virtqueue *vq, void *buf); +static void virtnet_sq_free_unused_buf_done(struct virtqueue *vq); static int virtnet_xdp_handler(struct bpf_prog *xdp_prog, struct xdp_buff *xdp, struct net_device *dev, unsigned int *xdp_xmit, @@ -2898,7 +2899,6 @@ static int virtnet_enable_queue_pair(struct virtnet_info *vi, int qp_index) if (err < 0) goto err_xdp_reg_mem_model; - netdev_tx_reset_queue(netdev_get_tx_queue(vi->dev, qp_index)); virtnet_napi_enable(vi->rq[qp_index].vq, &vi->rq[qp_index].napi); virtnet_napi_tx_enable(vi, vi->sq[qp_index].vq, &vi->sq[qp_index].napi); @@ -3166,7 +3166,7 @@ static int virtnet_rx_resize(struct virtnet_info *vi, virtnet_rx_pause(vi, rq); - err = virtqueue_resize(rq->vq, ring_num, virtnet_rq_unmap_free_buf); + err = virtqueue_resize(rq->vq, ring_num, virtnet_rq_unmap_free_buf, NULL); if (err) netdev_err(vi->dev, "resize rx fail: rx queue index: %d err: %d\n", qindex, err); @@ -3229,7 +3229,8 @@ static int virtnet_tx_resize(struct virtnet_info *vi, struct send_queue *sq, virtnet_tx_pause(vi, sq); - err = virtqueue_resize(sq->vq, ring_num, virtnet_sq_free_unused_buf); + err = virtqueue_resize(sq->vq, ring_num, virtnet_sq_free_unused_buf, + virtnet_sq_free_unused_buf_done); if (err) netdev_err(vi->dev, "resize tx fail: tx queue index: %d err: %d\n", qindex, err); @@ -5997,6 +5998,14 @@ static void virtnet_sq_free_unused_buf(struct virtqueue *vq, void *buf) xdp_return_frame(ptr_to_xdp(buf)); } +static void virtnet_sq_free_unused_buf_done(struct virtqueue *vq) +{ + struct virtnet_info *vi = vq->vdev->priv; + int i = vq2txq(vq); + + netdev_tx_reset_queue(netdev_get_tx_queue(vi->dev, i)); +} + static void free_unused_bufs(struct virtnet_info *vi) { void *buf; @@ -6728,11 +6737,20 @@ free: static void remove_vq_common(struct virtnet_info *vi) { + int i; + virtio_reset_device(vi->vdev); /* Free unused buffers in both send and recv, if any. */ free_unused_bufs(vi); + /* + * Rule of thumb is netdev_tx_reset_queue() should follow any + * skb freeing not followed by netdev_tx_completed_queue() + */ + for (i = 0; i < vi->max_queue_pairs; i++) + netdev_tx_reset_queue(netdev_get_tx_queue(vi->dev, i)); + free_receive_bufs(vi); free_receive_page_frags(vi); diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/bz.c b/drivers/net/wireless/intel/iwlwifi/cfg/bz.c index fa1be8c54d3c..c18c6e933f47 100644 --- a/drivers/net/wireless/intel/iwlwifi/cfg/bz.c +++ b/drivers/net/wireless/intel/iwlwifi/cfg/bz.c @@ -161,6 +161,7 @@ const struct iwl_cfg_trans_params iwl_gl_trans_cfg = { const char iwl_bz_name[] = "Intel(R) TBD Bz device"; const char iwl_fm_name[] = "Intel(R) Wi-Fi 7 BE201 320MHz"; +const char iwl_wh_name[] = "Intel(R) Wi-Fi 7 BE211 320MHz"; const char iwl_gl_name[] = "Intel(R) Wi-Fi 7 BE200 320MHz"; const char iwl_mtp_name[] = "Intel(R) Wi-Fi 7 BE202 160MHz"; diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-config.h b/drivers/net/wireless/intel/iwlwifi/iwl-config.h index 34c91deca57b..17721bb47e25 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-config.h +++ b/drivers/net/wireless/intel/iwlwifi/iwl-config.h @@ -545,6 +545,7 @@ extern const char iwl_ax231_name[]; extern const char iwl_ax411_name[]; extern const char iwl_bz_name[]; extern const char iwl_fm_name[]; +extern const char iwl_wh_name[]; extern const char iwl_gl_name[]; extern const char iwl_mtp_name[]; extern const char iwl_sc_name[]; diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-trans.h b/drivers/net/wireless/intel/iwlwifi/iwl-trans.h index e95ffe303547..c70da7281551 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-trans.h +++ b/drivers/net/wireless/intel/iwlwifi/iwl-trans.h @@ -1074,12 +1074,13 @@ int iwl_trans_read_config32(struct iwl_trans *trans, u32 ofs, void iwl_trans_debugfs_cleanup(struct iwl_trans *trans); #endif -#define iwl_trans_read_mem_bytes(trans, addr, buf, bufsize) \ - do { \ - if (__builtin_constant_p(bufsize)) \ - BUILD_BUG_ON((bufsize) % sizeof(u32)); \ - iwl_trans_read_mem(trans, addr, buf, (bufsize) / sizeof(u32));\ - } while (0) +#define iwl_trans_read_mem_bytes(trans, addr, buf, bufsize) \ + ({ \ + if (__builtin_constant_p(bufsize)) \ + BUILD_BUG_ON((bufsize) % sizeof(u32)); \ + iwl_trans_read_mem(trans, addr, buf, \ + (bufsize) / sizeof(u32)); \ + }) int iwl_trans_write_imr_mem(struct iwl_trans *trans, u32 dst_addr, u64 src_addr, u32 byte_cnt); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/d3.c b/drivers/net/wireless/intel/iwlwifi/mvm/d3.c index 244ca8cab9d1..6a4300c01d41 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/d3.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/d3.c @@ -2871,6 +2871,7 @@ static void iwl_mvm_query_set_freqs(struct iwl_mvm *mvm, int idx) { int i; + int n_channels = 0; if (fw_has_api(&mvm->fw->ucode_capa, IWL_UCODE_TLV_API_SCAN_OFFLOAD_CHANS)) { @@ -2879,7 +2880,7 @@ static void iwl_mvm_query_set_freqs(struct iwl_mvm *mvm, for (i = 0; i < SCAN_OFFLOAD_MATCHING_CHANNELS_LEN * 8; i++) if (matches[idx].matching_channels[i / 8] & (BIT(i % 8))) - match->channels[match->n_channels++] = + match->channels[n_channels++] = mvm->nd_channels[i]->center_freq; } else { struct iwl_scan_offload_profile_match_v1 *matches = @@ -2887,9 +2888,11 @@ static void iwl_mvm_query_set_freqs(struct iwl_mvm *mvm, for (i = 0; i < SCAN_OFFLOAD_MATCHING_CHANNELS_LEN_V1 * 8; i++) if (matches[idx].matching_channels[i / 8] & (BIT(i % 8))) - match->channels[match->n_channels++] = + match->channels[n_channels++] = mvm->nd_channels[i]->center_freq; } + /* We may have ended up with fewer channels than we allocated. */ + match->n_channels = n_channels; } /** @@ -2970,6 +2973,8 @@ static void iwl_mvm_query_netdetect_reasons(struct iwl_mvm *mvm, GFP_KERNEL); if (!net_detect || !n_matches) goto out_report_nd; + net_detect->n_matches = n_matches; + n_matches = 0; for_each_set_bit(i, &matched_profiles, mvm->n_nd_match_sets) { struct cfg80211_wowlan_nd_match *match; @@ -2983,8 +2988,9 @@ static void iwl_mvm_query_netdetect_reasons(struct iwl_mvm *mvm, GFP_KERNEL); if (!match) goto out_report_nd; + match->n_channels = n_channels; - net_detect->matches[net_detect->n_matches++] = match; + net_detect->matches[n_matches++] = match; /* We inverted the order of the SSIDs in the scan * request, so invert the index here. @@ -2999,6 +3005,8 @@ static void iwl_mvm_query_netdetect_reasons(struct iwl_mvm *mvm, iwl_mvm_query_set_freqs(mvm, d3_data->nd_results, match, i); } + /* We may have fewer matches than we allocated. */ + net_detect->n_matches = n_matches; out_report_nd: wakeup.net_detect = net_detect; @@ -3032,13 +3040,18 @@ static bool iwl_mvm_rt_status(struct iwl_trans *trans, u32 base, u32 *err_id) /* cf. struct iwl_error_event_table */ u32 valid; __le32 err_id; - } err_info; + } err_info = {}; + int ret; if (!base) return false; - iwl_trans_read_mem_bytes(trans, base, - &err_info, sizeof(err_info)); + ret = iwl_trans_read_mem_bytes(trans, base, + &err_info, sizeof(err_info)); + + if (ret) + return true; + if (err_info.valid && err_id) *err_id = le32_to_cpu(err_info.err_id); @@ -3635,22 +3648,31 @@ int iwl_mvm_fast_resume(struct iwl_mvm *mvm) iwl_fw_dbg_read_d3_debug_data(&mvm->fwrt); if (iwl_mvm_check_rt_status(mvm, NULL)) { + IWL_ERR(mvm, + "iwl_mvm_check_rt_status failed, device is gone during suspend\n"); set_bit(STATUS_FW_ERROR, &mvm->trans->status); iwl_mvm_dump_nic_error_log(mvm); iwl_dbg_tlv_time_point(&mvm->fwrt, IWL_FW_INI_TIME_POINT_FW_ASSERT, NULL); iwl_fw_dbg_collect_desc(&mvm->fwrt, &iwl_dump_desc_assert, false, 0); - return -ENODEV; + mvm->trans->state = IWL_TRANS_NO_FW; + ret = -ENODEV; + + goto out; } ret = iwl_mvm_d3_notif_wait(mvm, &d3_data); + + if (ret) { + IWL_ERR(mvm, "Couldn't get the d3 notif %d\n", ret); + mvm->trans->state = IWL_TRANS_NO_FW; + } + +out: clear_bit(IWL_MVM_STATUS_IN_D3, &mvm->status); mvm->trans->system_pm_mode = IWL_PLAT_PM_MODE_DISABLED; mvm->fast_resume = false; - if (ret) - IWL_ERR(mvm, "Couldn't get the d3 notif %d\n", ret); - return ret; } diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c index a7a10e716e65..e96ddaeeeeff 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c @@ -1967,7 +1967,7 @@ void iwl_mvm_channel_switch_error_notif(struct iwl_mvm *mvm, if (csa_err_mask & (CS_ERR_COUNT_ERROR | CS_ERR_LONG_DELAY_AFTER_CS | CS_ERR_TX_BLOCK_TIMER_EXPIRED)) - ieee80211_channel_switch_disconnect(vif, true); + ieee80211_channel_switch_disconnect(vif); rcu_read_unlock(); } diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c index 805fb249a0c6..8fb2aa282242 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c @@ -1106,19 +1106,54 @@ VISIBLE_IF_IWLWIFI_KUNIT const struct iwl_dev_info iwl_dev_info_table[] = { iwlax210_2ax_cfg_so_jf_b0, iwl9462_name), /* Bz */ -/* FIXME: need to change the naming according to the actual CRF */ _IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_MAC_TYPE_BZ, IWL_CFG_ANY, + IWL_CFG_RF_TYPE_HR2, IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY, + iwl_cfg_bz, iwl_ax201_name), + + _IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY, + IWL_CFG_MAC_TYPE_BZ, IWL_CFG_ANY, + IWL_CFG_RF_TYPE_GF, IWL_CFG_ANY, IWL_CFG_ANY, + IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY, + iwl_cfg_bz, iwl_ax211_name), + + _IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY, + IWL_CFG_MAC_TYPE_BZ, IWL_CFG_ANY, + IWL_CFG_RF_TYPE_FM, IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY, iwl_cfg_bz, iwl_fm_name), _IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY, + IWL_CFG_MAC_TYPE_BZ, IWL_CFG_ANY, + IWL_CFG_RF_TYPE_WH, IWL_CFG_ANY, IWL_CFG_ANY, + IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY, + iwl_cfg_bz, iwl_wh_name), + + _IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_MAC_TYPE_BZ_W, IWL_CFG_ANY, + IWL_CFG_RF_TYPE_HR2, IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY, + iwl_cfg_bz, iwl_ax201_name), + + _IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY, + IWL_CFG_MAC_TYPE_BZ_W, IWL_CFG_ANY, + IWL_CFG_RF_TYPE_GF, IWL_CFG_ANY, IWL_CFG_ANY, + IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY, + iwl_cfg_bz, iwl_ax211_name), + + _IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY, + IWL_CFG_MAC_TYPE_BZ_W, IWL_CFG_ANY, + IWL_CFG_RF_TYPE_FM, IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY, iwl_cfg_bz, iwl_fm_name), + _IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY, + IWL_CFG_MAC_TYPE_BZ_W, IWL_CFG_ANY, + IWL_CFG_RF_TYPE_WH, IWL_CFG_ANY, IWL_CFG_ANY, + IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY, + iwl_cfg_bz, iwl_wh_name), + /* Ga (Gl) */ _IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_MAC_TYPE_GL, IWL_CFG_ANY, diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c index 3b9943eb6934..d19b3bd0866b 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c @@ -1643,6 +1643,8 @@ int iwl_trans_pcie_d3_resume(struct iwl_trans *trans, out: if (*status == IWL_D3_STATUS_ALIVE) ret = iwl_pcie_d3_handshake(trans, false); + else + trans->state = IWL_TRANS_NO_FW; return ret; } diff --git a/drivers/net/wwan/iosm/iosm_ipc_mmio.c b/drivers/net/wwan/iosm/iosm_ipc_mmio.c index 63eb08c43c05..6764c13530b9 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_mmio.c +++ b/drivers/net/wwan/iosm/iosm_ipc_mmio.c @@ -104,7 +104,7 @@ struct iosm_mmio *ipc_mmio_init(void __iomem *mmio, struct device *dev) break; msleep(20); - } while (retries-- > 0); + } while (--retries > 0); if (!retries) { dev_err(ipc_mmio->dev, "invalid exec stage %X", stage); diff --git a/drivers/net/wwan/t7xx/t7xx_state_monitor.c b/drivers/net/wwan/t7xx/t7xx_state_monitor.c index 3931c7a13f5a..cbdbb91e8381 100644 --- a/drivers/net/wwan/t7xx/t7xx_state_monitor.c +++ b/drivers/net/wwan/t7xx/t7xx_state_monitor.c @@ -104,14 +104,21 @@ void t7xx_fsm_broadcast_state(struct t7xx_fsm_ctl *ctl, enum md_state state) fsm_state_notify(ctl->md, state); } +static void fsm_release_command(struct kref *ref) +{ + struct t7xx_fsm_command *cmd = container_of(ref, typeof(*cmd), refcnt); + + kfree(cmd); +} + static void fsm_finish_command(struct t7xx_fsm_ctl *ctl, struct t7xx_fsm_command *cmd, int result) { if (cmd->flag & FSM_CMD_FLAG_WAIT_FOR_COMPLETION) { - *cmd->ret = result; - complete_all(cmd->done); + cmd->result = result; + complete_all(&cmd->done); } - kfree(cmd); + kref_put(&cmd->refcnt, fsm_release_command); } static void fsm_del_kf_event(struct t7xx_fsm_event *event) @@ -475,7 +482,6 @@ static int fsm_main_thread(void *data) int t7xx_fsm_append_cmd(struct t7xx_fsm_ctl *ctl, enum t7xx_fsm_cmd_state cmd_id, unsigned int flag) { - DECLARE_COMPLETION_ONSTACK(done); struct t7xx_fsm_command *cmd; unsigned long flags; int ret; @@ -487,11 +493,13 @@ int t7xx_fsm_append_cmd(struct t7xx_fsm_ctl *ctl, enum t7xx_fsm_cmd_state cmd_id INIT_LIST_HEAD(&cmd->entry); cmd->cmd_id = cmd_id; cmd->flag = flag; + kref_init(&cmd->refcnt); if (flag & FSM_CMD_FLAG_WAIT_FOR_COMPLETION) { - cmd->done = &done; - cmd->ret = &ret; + init_completion(&cmd->done); + kref_get(&cmd->refcnt); } + kref_get(&cmd->refcnt); spin_lock_irqsave(&ctl->command_lock, flags); list_add_tail(&cmd->entry, &ctl->command_queue); spin_unlock_irqrestore(&ctl->command_lock, flags); @@ -501,11 +509,11 @@ int t7xx_fsm_append_cmd(struct t7xx_fsm_ctl *ctl, enum t7xx_fsm_cmd_state cmd_id if (flag & FSM_CMD_FLAG_WAIT_FOR_COMPLETION) { unsigned long wait_ret; - wait_ret = wait_for_completion_timeout(&done, + wait_ret = wait_for_completion_timeout(&cmd->done, msecs_to_jiffies(FSM_CMD_TIMEOUT_MS)); - if (!wait_ret) - return -ETIMEDOUT; + ret = wait_ret ? cmd->result : -ETIMEDOUT; + kref_put(&cmd->refcnt, fsm_release_command); return ret; } diff --git a/drivers/net/wwan/t7xx/t7xx_state_monitor.h b/drivers/net/wwan/t7xx/t7xx_state_monitor.h index 7b0a9baf488c..6e0601bb752e 100644 --- a/drivers/net/wwan/t7xx/t7xx_state_monitor.h +++ b/drivers/net/wwan/t7xx/t7xx_state_monitor.h @@ -110,8 +110,9 @@ struct t7xx_fsm_command { struct list_head entry; enum t7xx_fsm_cmd_state cmd_id; unsigned int flag; - struct completion *done; - int *ret; + struct completion done; + int result; + struct kref refcnt; }; struct t7xx_fsm_notifier { diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c index 4265c1cd0ff7..63fe51d0e64d 100644 --- a/drivers/net/xen-netfront.c +++ b/drivers/net/xen-netfront.c @@ -867,7 +867,7 @@ static netdev_tx_t xennet_start_xmit(struct sk_buff *skb, struct net_device *dev static int xennet_close(struct net_device *dev) { struct netfront_info *np = netdev_priv(dev); - unsigned int num_queues = dev->real_num_tx_queues; + unsigned int num_queues = np->queues ? dev->real_num_tx_queues : 0; unsigned int i; struct netfront_queue *queue; netif_tx_stop_all_queues(np->netdev); @@ -882,6 +882,9 @@ static void xennet_destroy_queues(struct netfront_info *info) { unsigned int i; + if (!info->queues) + return; + for (i = 0; i < info->netdev->real_num_tx_queues; i++) { struct netfront_queue *queue = &info->queues[i]; diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index 093cb423f536..61bba5513de0 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -173,6 +173,11 @@ enum nvme_quirks { * MSI (but not MSI-X) interrupts are broken and never fire. */ NVME_QUIRK_BROKEN_MSI = (1 << 21), + + /* + * Align dma pool segment size to 512 bytes + */ + NVME_QUIRK_DMAPOOL_ALIGN_512 = (1 << 22), }; /* diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 55af3dfbc260..76b3f7b396c8 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -2690,15 +2690,20 @@ static int nvme_disable_prepare_reset(struct nvme_dev *dev, bool shutdown) static int nvme_setup_prp_pools(struct nvme_dev *dev) { + size_t small_align = 256; + dev->prp_page_pool = dma_pool_create("prp list page", dev->dev, NVME_CTRL_PAGE_SIZE, NVME_CTRL_PAGE_SIZE, 0); if (!dev->prp_page_pool) return -ENOMEM; + if (dev->ctrl.quirks & NVME_QUIRK_DMAPOOL_ALIGN_512) + small_align = 512; + /* Optimisation for I/Os between 4k and 128k */ dev->prp_small_pool = dma_pool_create("prp list 256", dev->dev, - 256, 256, 0); + 256, small_align, 0); if (!dev->prp_small_pool) { dma_pool_destroy(dev->prp_page_pool); return -ENOMEM; @@ -3446,7 +3451,7 @@ static const struct pci_device_id nvme_id_table[] = { { PCI_VDEVICE(REDHAT, 0x0010), /* Qemu emulated controller */ .driver_data = NVME_QUIRK_BOGUS_NID, }, { PCI_DEVICE(0x1217, 0x8760), /* O2 Micro 64GB Steam Deck */ - .driver_data = NVME_QUIRK_QDEPTH_ONE }, + .driver_data = NVME_QUIRK_DMAPOOL_ALIGN_512, }, { PCI_DEVICE(0x126f, 0x2262), /* Silicon Motion generic */ .driver_data = NVME_QUIRK_NO_DEEPEST_PS | NVME_QUIRK_BOGUS_NID, }, diff --git a/drivers/nvme/target/configfs.c b/drivers/nvme/target/configfs.c index 685e89b35d33..cfbab198693b 100644 --- a/drivers/nvme/target/configfs.c +++ b/drivers/nvme/target/configfs.c @@ -2227,12 +2227,17 @@ static ssize_t nvmet_root_discovery_nqn_store(struct config_item *item, const char *page, size_t count) { struct list_head *entry; + char *old_nqn, *new_nqn; size_t len; len = strcspn(page, "\n"); if (!len || len > NVMF_NQN_FIELD_LEN - 1) return -EINVAL; + new_nqn = kstrndup(page, len, GFP_KERNEL); + if (!new_nqn) + return -ENOMEM; + down_write(&nvmet_config_sem); list_for_each(entry, &nvmet_subsystems_group.cg_children) { struct config_item *item = @@ -2241,13 +2246,15 @@ static ssize_t nvmet_root_discovery_nqn_store(struct config_item *item, if (!strncmp(config_item_name(item), page, len)) { pr_err("duplicate NQN %s\n", config_item_name(item)); up_write(&nvmet_config_sem); + kfree(new_nqn); return -EINVAL; } } - memset(nvmet_disc_subsys->subsysnqn, 0, NVMF_NQN_FIELD_LEN); - memcpy(nvmet_disc_subsys->subsysnqn, page, len); + old_nqn = nvmet_disc_subsys->subsysnqn; + nvmet_disc_subsys->subsysnqn = new_nqn; up_write(&nvmet_config_sem); + kfree(old_nqn); return len; } diff --git a/drivers/of/address.c b/drivers/of/address.c index 286f0c161e33..a565b8c91da5 100644 --- a/drivers/of/address.c +++ b/drivers/of/address.c @@ -455,7 +455,8 @@ static int of_translate_one(struct device_node *parent, struct of_bus *bus, } if (ranges == NULL || rlen == 0) { offset = of_read_number(addr, na); - memset(addr, 0, pna * 4); + /* set address to zero, pass flags through */ + memset(addr + pbus->flag_cells, 0, (pna - pbus->flag_cells) * 4); pr_debug("empty ranges; 1:1 translation\n"); goto finish; } @@ -615,7 +616,7 @@ struct device_node *__of_get_dma_parent(const struct device_node *np) if (ret < 0) return of_get_parent(np); - return of_node_get(args.np); + return args.np; } #endif diff --git a/drivers/of/base.c b/drivers/of/base.c index 20603d3c9931..63161d0f72b4 100644 --- a/drivers/of/base.c +++ b/drivers/of/base.c @@ -1455,8 +1455,10 @@ int of_parse_phandle_with_args_map(const struct device_node *np, map_len--; /* Check if not found */ - if (!new) + if (!new) { + ret = -EINVAL; goto put; + } if (!of_device_is_available(new)) match = 0; @@ -1466,17 +1468,20 @@ int of_parse_phandle_with_args_map(const struct device_node *np, goto put; /* Check for malformed properties */ - if (WARN_ON(new_size > MAX_PHANDLE_ARGS)) - goto put; - if (map_len < new_size) + if (WARN_ON(new_size > MAX_PHANDLE_ARGS) || + map_len < new_size) { + ret = -EINVAL; goto put; + } /* Move forward by new node's #<list>-cells amount */ map += new_size; map_len -= new_size; } - if (!match) + if (!match) { + ret = -ENOENT; goto put; + } /* Get the <list>-map-pass-thru property (optional) */ pass = of_get_property(cur, pass_name, NULL); diff --git a/drivers/of/irq.c b/drivers/of/irq.c index a494f56a0d0e..1fb329c0a55b 100644 --- a/drivers/of/irq.c +++ b/drivers/of/irq.c @@ -111,6 +111,7 @@ const __be32 *of_irq_parse_imap_parent(const __be32 *imap, int len, struct of_ph else np = of_find_node_by_phandle(be32_to_cpup(imap)); imap++; + len--; /* Check if not found */ if (!np) { @@ -354,6 +355,7 @@ int of_irq_parse_one(struct device_node *device, int index, struct of_phandle_ar return of_irq_parse_oldworld(device, index, out_irq); /* Get the reg property (if any) */ + addr_len = 0; addr = of_get_property(device, "reg", &addr_len); /* Prevent out-of-bounds read in case of longer interrupt parent address size */ diff --git a/drivers/of/property.c b/drivers/of/property.c index 11b922fde7af..7bd8390f2fba 100644 --- a/drivers/of/property.c +++ b/drivers/of/property.c @@ -1213,7 +1213,6 @@ DEFINE_SIMPLE_PROP(iommus, "iommus", "#iommu-cells") DEFINE_SIMPLE_PROP(mboxes, "mboxes", "#mbox-cells") DEFINE_SIMPLE_PROP(io_channels, "io-channels", "#io-channel-cells") DEFINE_SIMPLE_PROP(io_backends, "io-backends", "#io-backend-cells") -DEFINE_SIMPLE_PROP(interrupt_parent, "interrupt-parent", NULL) DEFINE_SIMPLE_PROP(dmas, "dmas", "#dma-cells") DEFINE_SIMPLE_PROP(power_domains, "power-domains", "#power-domain-cells") DEFINE_SIMPLE_PROP(hwlocks, "hwlocks", "#hwlock-cells") @@ -1359,7 +1358,6 @@ static const struct supplier_bindings of_supplier_bindings[] = { { .parse_prop = parse_mboxes, }, { .parse_prop = parse_io_channels, }, { .parse_prop = parse_io_backends, }, - { .parse_prop = parse_interrupt_parent, }, { .parse_prop = parse_dmas, .optional = true, }, { .parse_prop = parse_power_domains, }, { .parse_prop = parse_hwlocks, }, diff --git a/drivers/pci/msi/irqdomain.c b/drivers/pci/msi/irqdomain.c index 569125726b3e..d7ba8795d60f 100644 --- a/drivers/pci/msi/irqdomain.c +++ b/drivers/pci/msi/irqdomain.c @@ -350,8 +350,11 @@ bool pci_msi_domain_supports(struct pci_dev *pdev, unsigned int feature_mask, domain = dev_get_msi_domain(&pdev->dev); - if (!domain || !irq_domain_is_hierarchy(domain)) - return mode == ALLOW_LEGACY; + if (!domain || !irq_domain_is_hierarchy(domain)) { + if (IS_ENABLED(CONFIG_PCI_MSI_ARCH_FALLBACKS)) + return mode == ALLOW_LEGACY; + return false; + } if (!irq_domain_is_msi_parent(domain)) { /* diff --git a/drivers/pci/msi/msi.c b/drivers/pci/msi/msi.c index 3a45879d85db..2f647cac4cae 100644 --- a/drivers/pci/msi/msi.c +++ b/drivers/pci/msi/msi.c @@ -433,6 +433,10 @@ int __pci_enable_msi_range(struct pci_dev *dev, int minvec, int maxvec, if (WARN_ON_ONCE(dev->msi_enabled)) return -EINVAL; + /* Test for the availability of MSI support */ + if (!pci_msi_domain_supports(dev, 0, ALLOW_LEGACY)) + return -ENOTSUPP; + nvec = pci_msi_vec_count(dev); if (nvec < 0) return nvec; diff --git a/drivers/phy/broadcom/phy-brcm-usb-init-synopsys.c b/drivers/phy/broadcom/phy-brcm-usb-init-synopsys.c index 950b7ae1d1a8..dc452610934a 100644 --- a/drivers/phy/broadcom/phy-brcm-usb-init-synopsys.c +++ b/drivers/phy/broadcom/phy-brcm-usb-init-synopsys.c @@ -325,6 +325,12 @@ static void usb_init_common_7216(struct brcm_usb_init_params *params) void __iomem *ctrl = params->regs[BRCM_REGS_CTRL]; USB_CTRL_UNSET(ctrl, USB_PM, XHC_S2_CLK_SWITCH_EN); + + /* + * The PHY might be in a bad state if it is already powered + * up. Toggle the power just in case. + */ + USB_CTRL_SET(ctrl, USB_PM, USB_PWRDN); USB_CTRL_UNSET(ctrl, USB_PM, USB_PWRDN); /* 1 millisecond - for USB clocks to settle down */ diff --git a/drivers/phy/phy-core.c b/drivers/phy/phy-core.c index f053b525ccff..413f76e2d174 100644 --- a/drivers/phy/phy-core.c +++ b/drivers/phy/phy-core.c @@ -145,8 +145,10 @@ static struct phy_provider *of_phy_provider_lookup(struct device_node *node) return phy_provider; for_each_child_of_node(phy_provider->children, child) - if (child == node) + if (child == node) { + of_node_put(child); return phy_provider; + } } return ERR_PTR(-EPROBE_DEFER); @@ -629,8 +631,10 @@ static struct phy *_of_phy_get(struct device_node *np, int index) return ERR_PTR(-ENODEV); /* This phy type handled by the usb-phy subsystem for now */ - if (of_device_is_compatible(args.np, "usb-nop-xceiv")) - return ERR_PTR(-ENODEV); + if (of_device_is_compatible(args.np, "usb-nop-xceiv")) { + phy = ERR_PTR(-ENODEV); + goto out_put_node; + } mutex_lock(&phy_provider_mutex); phy_provider = of_phy_provider_lookup(args.np); @@ -652,6 +656,7 @@ out_put_module: out_unlock: mutex_unlock(&phy_provider_mutex); +out_put_node: of_node_put(args.np); return phy; @@ -737,7 +742,7 @@ void devm_phy_put(struct device *dev, struct phy *phy) if (!phy) return; - r = devres_destroy(dev, devm_phy_release, devm_phy_match, phy); + r = devres_release(dev, devm_phy_release, devm_phy_match, phy); dev_WARN_ONCE(dev, r, "couldn't find PHY resource\n"); } EXPORT_SYMBOL_GPL(devm_phy_put); @@ -1121,7 +1126,7 @@ void devm_phy_destroy(struct device *dev, struct phy *phy) { int r; - r = devres_destroy(dev, devm_phy_consume, devm_phy_match, phy); + r = devres_release(dev, devm_phy_consume, devm_phy_match, phy); dev_WARN_ONCE(dev, r, "couldn't find PHY resource\n"); } EXPORT_SYMBOL_GPL(devm_phy_destroy); @@ -1259,12 +1264,12 @@ EXPORT_SYMBOL_GPL(of_phy_provider_unregister); * of_phy_provider_unregister to unregister the phy provider. */ void devm_of_phy_provider_unregister(struct device *dev, - struct phy_provider *phy_provider) + struct phy_provider *phy_provider) { int r; - r = devres_destroy(dev, devm_phy_provider_release, devm_phy_match, - phy_provider); + r = devres_release(dev, devm_phy_provider_release, devm_phy_match, + phy_provider); dev_WARN_ONCE(dev, r, "couldn't find PHY provider device resource\n"); } EXPORT_SYMBOL_GPL(devm_of_phy_provider_unregister); diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-usb.c b/drivers/phy/qualcomm/phy-qcom-qmp-usb.c index 1246d3bc8b92..8e2cd2c178d6 100644 --- a/drivers/phy/qualcomm/phy-qcom-qmp-usb.c +++ b/drivers/phy/qualcomm/phy-qcom-qmp-usb.c @@ -1008,7 +1008,7 @@ static const struct qmp_phy_init_tbl sc8280xp_usb3_uniphy_rx_tbl[] = { QMP_PHY_INIT_CFG(QSERDES_V5_RX_UCDR_FASTLOCK_FO_GAIN, 0x2f), QMP_PHY_INIT_CFG(QSERDES_V5_RX_UCDR_FASTLOCK_COUNT_LOW, 0xff), QMP_PHY_INIT_CFG(QSERDES_V5_RX_UCDR_FASTLOCK_COUNT_HIGH, 0x0f), - QMP_PHY_INIT_CFG(QSERDES_V5_RX_UCDR_SO_GAIN, 0x0a), + QMP_PHY_INIT_CFG(QSERDES_V5_RX_UCDR_FO_GAIN, 0x0a), QMP_PHY_INIT_CFG(QSERDES_V5_RX_VGA_CAL_CNTRL1, 0x54), QMP_PHY_INIT_CFG(QSERDES_V5_RX_VGA_CAL_CNTRL2, 0x0f), QMP_PHY_INIT_CFG(QSERDES_V5_RX_RX_EQU_ADAPTOR_CNTRL2, 0x0f), diff --git a/drivers/phy/rockchip/phy-rockchip-naneng-combphy.c b/drivers/phy/rockchip/phy-rockchip-naneng-combphy.c index 0a9989e41237..2eb3329ca23f 100644 --- a/drivers/phy/rockchip/phy-rockchip-naneng-combphy.c +++ b/drivers/phy/rockchip/phy-rockchip-naneng-combphy.c @@ -309,7 +309,7 @@ static int rockchip_combphy_parse_dt(struct device *dev, struct rockchip_combphy priv->ext_refclk = device_property_present(dev, "rockchip,ext-refclk"); - priv->phy_rst = devm_reset_control_array_get_exclusive(dev); + priv->phy_rst = devm_reset_control_get(dev, "phy"); if (IS_ERR(priv->phy_rst)) return dev_err_probe(dev, PTR_ERR(priv->phy_rst), "failed to get phy reset\n"); diff --git a/drivers/phy/rockchip/phy-rockchip-samsung-hdptx.c b/drivers/phy/rockchip/phy-rockchip-samsung-hdptx.c index 9f084697dd05..69c3ec0938f7 100644 --- a/drivers/phy/rockchip/phy-rockchip-samsung-hdptx.c +++ b/drivers/phy/rockchip/phy-rockchip-samsung-hdptx.c @@ -1116,6 +1116,8 @@ static int rk_hdptx_phy_probe(struct platform_device *pdev) return dev_err_probe(dev, PTR_ERR(hdptx->grf), "Could not get GRF syscon\n"); + platform_set_drvdata(pdev, hdptx); + ret = devm_pm_runtime_enable(dev); if (ret) return dev_err_probe(dev, ret, "Failed to enable runtime PM\n"); @@ -1125,7 +1127,6 @@ static int rk_hdptx_phy_probe(struct platform_device *pdev) return dev_err_probe(dev, PTR_ERR(hdptx->phy), "Failed to create HDMI PHY\n"); - platform_set_drvdata(pdev, hdptx); phy_set_drvdata(hdptx->phy, hdptx); phy_set_bus_width(hdptx->phy, 8); diff --git a/drivers/pinctrl/pinctrl-mcp23s08.c b/drivers/pinctrl/pinctrl-mcp23s08.c index 737d0ae3d0b6..f384c72d9554 100644 --- a/drivers/pinctrl/pinctrl-mcp23s08.c +++ b/drivers/pinctrl/pinctrl-mcp23s08.c @@ -86,6 +86,7 @@ const struct regmap_config mcp23x08_regmap = { .num_reg_defaults = ARRAY_SIZE(mcp23x08_defaults), .cache_type = REGCACHE_FLAT, .max_register = MCP_OLAT, + .disable_locking = true, /* mcp->lock protects the regmap */ }; EXPORT_SYMBOL_GPL(mcp23x08_regmap); @@ -132,6 +133,7 @@ const struct regmap_config mcp23x17_regmap = { .num_reg_defaults = ARRAY_SIZE(mcp23x17_defaults), .cache_type = REGCACHE_FLAT, .val_format_endian = REGMAP_ENDIAN_LITTLE, + .disable_locking = true, /* mcp->lock protects the regmap */ }; EXPORT_SYMBOL_GPL(mcp23x17_regmap); @@ -228,7 +230,9 @@ static int mcp_pinconf_get(struct pinctrl_dev *pctldev, unsigned int pin, switch (param) { case PIN_CONFIG_BIAS_PULL_UP: + mutex_lock(&mcp->lock); ret = mcp_read(mcp, MCP_GPPU, &data); + mutex_unlock(&mcp->lock); if (ret < 0) return ret; status = (data & BIT(pin)) ? 1 : 0; @@ -257,7 +261,9 @@ static int mcp_pinconf_set(struct pinctrl_dev *pctldev, unsigned int pin, switch (param) { case PIN_CONFIG_BIAS_PULL_UP: + mutex_lock(&mcp->lock); ret = mcp_set_bit(mcp, MCP_GPPU, pin, arg); + mutex_unlock(&mcp->lock); break; default: dev_dbg(mcp->dev, "Invalid config param %04x\n", param); diff --git a/drivers/platform/chrome/cros_ec_lpc.c b/drivers/platform/chrome/cros_ec_lpc.c index c784119ab5dc..626e2635e3da 100644 --- a/drivers/platform/chrome/cros_ec_lpc.c +++ b/drivers/platform/chrome/cros_ec_lpc.c @@ -707,7 +707,7 @@ static const struct dmi_system_id cros_ec_lpc_dmi_table[] __initconst = { /* Framework Laptop (12th Gen Intel Core) */ .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Framework"), - DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "12th Gen Intel Core"), + DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "Laptop (12th Gen Intel Core)"), }, .driver_data = (void *)&framework_laptop_mec_lpc_driver_data, }, @@ -715,7 +715,7 @@ static const struct dmi_system_id cros_ec_lpc_dmi_table[] __initconst = { /* Framework Laptop (13th Gen Intel Core) */ .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Framework"), - DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "13th Gen Intel Core"), + DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "Laptop (13th Gen Intel Core)"), }, .driver_data = (void *)&framework_laptop_mec_lpc_driver_data, }, diff --git a/drivers/platform/x86/asus-nb-wmi.c b/drivers/platform/x86/asus-nb-wmi.c index ef04d396f61c..a5933980ade3 100644 --- a/drivers/platform/x86/asus-nb-wmi.c +++ b/drivers/platform/x86/asus-nb-wmi.c @@ -623,6 +623,7 @@ static const struct key_entry asus_nb_wmi_keymap[] = { { KE_KEY, 0xC4, { KEY_KBDILLUMUP } }, { KE_KEY, 0xC5, { KEY_KBDILLUMDOWN } }, { KE_IGNORE, 0xC6, }, /* Ambient Light Sensor notification */ + { KE_IGNORE, 0xCF, }, /* AC mode */ { KE_KEY, 0xFA, { KEY_PROG2 } }, /* Lid flip action */ { KE_KEY, 0xBD, { KEY_PROG2 } }, /* Lid flip action on ROG xflow laptops */ { KE_END, 0}, diff --git a/drivers/platform/x86/hp/hp-wmi.c b/drivers/platform/x86/hp/hp-wmi.c index 8c05e0dd2a21..3ba9c43d5516 100644 --- a/drivers/platform/x86/hp/hp-wmi.c +++ b/drivers/platform/x86/hp/hp-wmi.c @@ -64,7 +64,7 @@ static const char * const omen_thermal_profile_boards[] = { "874A", "8603", "8604", "8748", "886B", "886C", "878A", "878B", "878C", "88C8", "88CB", "8786", "8787", "8788", "88D1", "88D2", "88F4", "88FD", "88F5", "88F6", "88F7", "88FE", "88FF", "8900", "8901", "8902", "8912", - "8917", "8918", "8949", "894A", "89EB", "8BAD", "8A42" + "8917", "8918", "8949", "894A", "89EB", "8BAD", "8A42", "8A15" }; /* DMI Board names of Omen laptops that are specifically set to be thermal @@ -80,7 +80,7 @@ static const char * const omen_thermal_profile_force_v0_boards[] = { * "balanced" when reaching zero. */ static const char * const omen_timed_thermal_profile_boards[] = { - "8BAD", "8A42" + "8BAD", "8A42", "8A15" }; /* DMI Board names of Victus laptops */ diff --git a/drivers/platform/x86/mlx-platform.c b/drivers/platform/x86/mlx-platform.c index 9d70146fd742..1a09f2dfb7bc 100644 --- a/drivers/platform/x86/mlx-platform.c +++ b/drivers/platform/x86/mlx-platform.c @@ -6237,6 +6237,7 @@ fail_pci_set_dma_mask: fail_pci_request_regions: pci_disable_device(pci_dev); fail_pci_enable_device: + pci_dev_put(pci_dev); return err; } @@ -6247,6 +6248,7 @@ mlxplat_pci_fpga_device_exit(struct pci_dev *pci_bridge, iounmap(pci_bridge_addr); pci_release_regions(pci_bridge); pci_disable_device(pci_bridge); + pci_dev_put(pci_bridge); } static int diff --git a/drivers/platform/x86/p2sb.c b/drivers/platform/x86/p2sb.c index 31f38309b389..c56650b9ff96 100644 --- a/drivers/platform/x86/p2sb.c +++ b/drivers/platform/x86/p2sb.c @@ -42,6 +42,7 @@ struct p2sb_res_cache { }; static struct p2sb_res_cache p2sb_resources[NR_P2SB_RES_CACHE]; +static bool p2sb_hidden_by_bios; static void p2sb_get_devfn(unsigned int *devfn) { @@ -96,6 +97,12 @@ static void p2sb_scan_and_cache_devfn(struct pci_bus *bus, unsigned int devfn) static int p2sb_scan_and_cache(struct pci_bus *bus, unsigned int devfn) { + /* + * The BIOS prevents the P2SB device from being enumerated by the PCI + * subsystem, so we need to unhide and hide it back to lookup the BAR. + */ + pci_bus_write_config_dword(bus, devfn, P2SBC, 0); + /* Scan the P2SB device and cache its BAR0 */ p2sb_scan_and_cache_devfn(bus, devfn); @@ -103,6 +110,8 @@ static int p2sb_scan_and_cache(struct pci_bus *bus, unsigned int devfn) if (devfn == P2SB_DEVFN_GOLDMONT) p2sb_scan_and_cache_devfn(bus, SPI_DEVFN_GOLDMONT); + pci_bus_write_config_dword(bus, devfn, P2SBC, P2SBC_HIDE); + if (!p2sb_valid_resource(&p2sb_resources[PCI_FUNC(devfn)].res)) return -ENOENT; @@ -128,7 +137,7 @@ static int p2sb_cache_resources(void) u32 value = P2SBC_HIDE; struct pci_bus *bus; u16 class; - int ret; + int ret = 0; /* Get devfn for P2SB device itself */ p2sb_get_devfn(&devfn_p2sb); @@ -151,22 +160,53 @@ static int p2sb_cache_resources(void) */ pci_lock_rescan_remove(); + pci_bus_read_config_dword(bus, devfn_p2sb, P2SBC, &value); + p2sb_hidden_by_bios = value & P2SBC_HIDE; + /* - * The BIOS prevents the P2SB device from being enumerated by the PCI - * subsystem, so we need to unhide and hide it back to lookup the BAR. - * Unhide the P2SB device here, if needed. + * If the BIOS does not hide the P2SB device then its resources + * are accesilble. Cache them only if the P2SB device is hidden. */ - pci_bus_read_config_dword(bus, devfn_p2sb, P2SBC, &value); - if (value & P2SBC_HIDE) - pci_bus_write_config_dword(bus, devfn_p2sb, P2SBC, 0); + if (p2sb_hidden_by_bios) + ret = p2sb_scan_and_cache(bus, devfn_p2sb); - ret = p2sb_scan_and_cache(bus, devfn_p2sb); + pci_unlock_rescan_remove(); - /* Hide the P2SB device, if it was hidden */ - if (value & P2SBC_HIDE) - pci_bus_write_config_dword(bus, devfn_p2sb, P2SBC, P2SBC_HIDE); + return ret; +} - pci_unlock_rescan_remove(); +static int p2sb_read_from_cache(struct pci_bus *bus, unsigned int devfn, + struct resource *mem) +{ + struct p2sb_res_cache *cache = &p2sb_resources[PCI_FUNC(devfn)]; + + if (cache->bus_dev_id != bus->dev.id) + return -ENODEV; + + if (!p2sb_valid_resource(&cache->res)) + return -ENOENT; + + memcpy(mem, &cache->res, sizeof(*mem)); + + return 0; +} + +static int p2sb_read_from_dev(struct pci_bus *bus, unsigned int devfn, + struct resource *mem) +{ + struct pci_dev *pdev; + int ret = 0; + + pdev = pci_get_slot(bus, devfn); + if (!pdev) + return -ENODEV; + + if (p2sb_valid_resource(pci_resource_n(pdev, 0))) + p2sb_read_bar0(pdev, mem); + else + ret = -ENOENT; + + pci_dev_put(pdev); return ret; } @@ -187,8 +227,6 @@ static int p2sb_cache_resources(void) */ int p2sb_bar(struct pci_bus *bus, unsigned int devfn, struct resource *mem) { - struct p2sb_res_cache *cache; - bus = p2sb_get_bus(bus); if (!bus) return -ENODEV; @@ -196,15 +234,10 @@ int p2sb_bar(struct pci_bus *bus, unsigned int devfn, struct resource *mem) if (!devfn) p2sb_get_devfn(&devfn); - cache = &p2sb_resources[PCI_FUNC(devfn)]; - if (cache->bus_dev_id != bus->dev.id) - return -ENODEV; + if (p2sb_hidden_by_bios) + return p2sb_read_from_cache(bus, devfn, mem); - if (!p2sb_valid_resource(&cache->res)) - return -ENOENT; - - memcpy(mem, &cache->res, sizeof(*mem)); - return 0; + return p2sb_read_from_dev(bus, devfn, mem); } EXPORT_SYMBOL_GPL(p2sb_bar); diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c index 6371a9f765c1..2cfb2ac3f465 100644 --- a/drivers/platform/x86/thinkpad_acpi.c +++ b/drivers/platform/x86/thinkpad_acpi.c @@ -184,7 +184,8 @@ enum tpacpi_hkey_event_t { */ TP_HKEY_EV_AMT_TOGGLE = 0x131a, /* Toggle AMT on/off */ TP_HKEY_EV_DOUBLETAP_TOGGLE = 0x131c, /* Toggle trackpoint doubletap on/off */ - TP_HKEY_EV_PROFILE_TOGGLE = 0x131f, /* Toggle platform profile */ + TP_HKEY_EV_PROFILE_TOGGLE = 0x131f, /* Toggle platform profile in 2024 systems */ + TP_HKEY_EV_PROFILE_TOGGLE2 = 0x1401, /* Toggle platform profile in 2025 + systems */ /* Reasons for waking up from S3/S4 */ TP_HKEY_EV_WKUP_S3_UNDOCK = 0x2304, /* undock requested, S3 */ @@ -11200,6 +11201,7 @@ static bool tpacpi_driver_event(const unsigned int hkey_event) tp_features.trackpoint_doubletap = !tp_features.trackpoint_doubletap; return true; case TP_HKEY_EV_PROFILE_TOGGLE: + case TP_HKEY_EV_PROFILE_TOGGLE2: platform_profile_cycle(); return true; } diff --git a/drivers/pmdomain/core.c b/drivers/pmdomain/core.c index 778ff187ac59..88819659df83 100644 --- a/drivers/pmdomain/core.c +++ b/drivers/pmdomain/core.c @@ -2141,6 +2141,11 @@ static int genpd_set_default_power_state(struct generic_pm_domain *genpd) return 0; } +static void genpd_provider_release(struct device *dev) +{ + /* nothing to be done here */ +} + static int genpd_alloc_data(struct generic_pm_domain *genpd) { struct genpd_governor_data *gd = NULL; @@ -2172,6 +2177,7 @@ static int genpd_alloc_data(struct generic_pm_domain *genpd) genpd->gd = gd; device_initialize(&genpd->dev); + genpd->dev.release = genpd_provider_release; if (!genpd_is_dev_name_fw(genpd)) { dev_set_name(&genpd->dev, "%s", genpd->name); diff --git a/drivers/pmdomain/imx/gpcv2.c b/drivers/pmdomain/imx/gpcv2.c index 3f0e6960f47f..e03c2cb39a69 100644 --- a/drivers/pmdomain/imx/gpcv2.c +++ b/drivers/pmdomain/imx/gpcv2.c @@ -1458,12 +1458,12 @@ static int imx_gpcv2_probe(struct platform_device *pdev) .max_register = SZ_4K, }; struct device *dev = &pdev->dev; - struct device_node *pgc_np; + struct device_node *pgc_np __free(device_node) = + of_get_child_by_name(dev->of_node, "pgc"); struct regmap *regmap; void __iomem *base; int ret; - pgc_np = of_get_child_by_name(dev->of_node, "pgc"); if (!pgc_np) { dev_err(dev, "No power domains specified in DT\n"); return -EINVAL; diff --git a/drivers/power/supply/bq24190_charger.c b/drivers/power/supply/bq24190_charger.c index 2b393eb5c282..c47f32f152e6 100644 --- a/drivers/power/supply/bq24190_charger.c +++ b/drivers/power/supply/bq24190_charger.c @@ -567,6 +567,7 @@ static int bq24190_set_otg_vbus(struct bq24190_dev_info *bdi, bool enable) static int bq24296_set_otg_vbus(struct bq24190_dev_info *bdi, bool enable) { + union power_supply_propval val = { .intval = bdi->charge_type }; int ret; ret = pm_runtime_resume_and_get(bdi->dev); @@ -587,13 +588,18 @@ static int bq24296_set_otg_vbus(struct bq24190_dev_info *bdi, bool enable) ret = bq24190_write_mask(bdi, BQ24190_REG_POC, BQ24296_REG_POC_OTG_CONFIG_MASK, - BQ24296_REG_POC_CHG_CONFIG_SHIFT, + BQ24296_REG_POC_OTG_CONFIG_SHIFT, BQ24296_REG_POC_OTG_CONFIG_OTG); - } else + } else { ret = bq24190_write_mask(bdi, BQ24190_REG_POC, BQ24296_REG_POC_OTG_CONFIG_MASK, - BQ24296_REG_POC_CHG_CONFIG_SHIFT, + BQ24296_REG_POC_OTG_CONFIG_SHIFT, BQ24296_REG_POC_OTG_CONFIG_DISABLE); + if (ret < 0) + goto out; + + ret = bq24190_charger_set_charge_type(bdi, &val); + } out: pm_runtime_mark_last_busy(bdi->dev); diff --git a/drivers/power/supply/cros_charge-control.c b/drivers/power/supply/cros_charge-control.c index 17c53591ce19..9b0a7500296b 100644 --- a/drivers/power/supply/cros_charge-control.c +++ b/drivers/power/supply/cros_charge-control.c @@ -7,8 +7,10 @@ #include <acpi/battery.h> #include <linux/container_of.h> #include <linux/dmi.h> +#include <linux/lockdep.h> #include <linux/mod_devicetable.h> #include <linux/module.h> +#include <linux/mutex.h> #include <linux/platform_data/cros_ec_commands.h> #include <linux/platform_data/cros_ec_proto.h> #include <linux/platform_device.h> @@ -49,6 +51,7 @@ struct cros_chctl_priv { struct attribute *attributes[_CROS_CHCTL_ATTR_COUNT]; struct attribute_group group; + struct mutex lock; /* protects fields below and cros_ec */ enum power_supply_charge_behaviour current_behaviour; u8 current_start_threshold, current_end_threshold; }; @@ -85,6 +88,8 @@ static int cros_chctl_configure_ec(struct cros_chctl_priv *priv) { struct ec_params_charge_control req = {}; + lockdep_assert_held(&priv->lock); + req.cmd = EC_CHARGE_CONTROL_CMD_SET; switch (priv->current_behaviour) { @@ -134,11 +139,15 @@ static ssize_t cros_chctl_store_threshold(struct device *dev, struct cros_chctl_ return -EINVAL; if (is_end_threshold) { - if (val <= priv->current_start_threshold) + /* Start threshold is not exposed, use fixed value */ + if (priv->cmd_version == 2) + priv->current_start_threshold = val == 100 ? 0 : val; + + if (val < priv->current_start_threshold) return -EINVAL; priv->current_end_threshold = val; } else { - if (val >= priv->current_end_threshold) + if (val > priv->current_end_threshold) return -EINVAL; priv->current_start_threshold = val; } @@ -159,6 +168,7 @@ static ssize_t charge_control_start_threshold_show(struct device *dev, struct cros_chctl_priv *priv = cros_chctl_attr_to_priv(&attr->attr, CROS_CHCTL_ATTR_START_THRESHOLD); + guard(mutex)(&priv->lock); return sysfs_emit(buf, "%u\n", (unsigned int)priv->current_start_threshold); } @@ -169,6 +179,7 @@ static ssize_t charge_control_start_threshold_store(struct device *dev, struct cros_chctl_priv *priv = cros_chctl_attr_to_priv(&attr->attr, CROS_CHCTL_ATTR_START_THRESHOLD); + guard(mutex)(&priv->lock); return cros_chctl_store_threshold(dev, priv, 0, buf, count); } @@ -178,6 +189,7 @@ static ssize_t charge_control_end_threshold_show(struct device *dev, struct devi struct cros_chctl_priv *priv = cros_chctl_attr_to_priv(&attr->attr, CROS_CHCTL_ATTR_END_THRESHOLD); + guard(mutex)(&priv->lock); return sysfs_emit(buf, "%u\n", (unsigned int)priv->current_end_threshold); } @@ -187,6 +199,7 @@ static ssize_t charge_control_end_threshold_store(struct device *dev, struct dev struct cros_chctl_priv *priv = cros_chctl_attr_to_priv(&attr->attr, CROS_CHCTL_ATTR_END_THRESHOLD); + guard(mutex)(&priv->lock); return cros_chctl_store_threshold(dev, priv, 1, buf, count); } @@ -195,6 +208,7 @@ static ssize_t charge_behaviour_show(struct device *dev, struct device_attribute struct cros_chctl_priv *priv = cros_chctl_attr_to_priv(&attr->attr, CROS_CHCTL_ATTR_CHARGE_BEHAVIOUR); + guard(mutex)(&priv->lock); return power_supply_charge_behaviour_show(dev, EC_CHARGE_CONTROL_BEHAVIOURS, priv->current_behaviour, buf); } @@ -210,6 +224,7 @@ static ssize_t charge_behaviour_store(struct device *dev, struct device_attribut if (ret < 0) return ret; + guard(mutex)(&priv->lock); priv->current_behaviour = ret; ret = cros_chctl_configure_ec(priv); @@ -223,12 +238,10 @@ static umode_t cros_chtl_attr_is_visible(struct kobject *kobj, struct attribute { struct cros_chctl_priv *priv = cros_chctl_attr_to_priv(attr, n); - if (priv->cmd_version < 2) { - if (n == CROS_CHCTL_ATTR_START_THRESHOLD) - return 0; - if (n == CROS_CHCTL_ATTR_END_THRESHOLD) - return 0; - } + if (n == CROS_CHCTL_ATTR_START_THRESHOLD && priv->cmd_version < 3) + return 0; + else if (n == CROS_CHCTL_ATTR_END_THRESHOLD && priv->cmd_version < 2) + return 0; return attr->mode; } @@ -290,6 +303,10 @@ static int cros_chctl_probe(struct platform_device *pdev) if (!priv) return -ENOMEM; + ret = devm_mutex_init(dev, &priv->lock); + if (ret) + return ret; + ret = cros_ec_get_cmd_versions(cros_ec, EC_CMD_CHARGE_CONTROL); if (ret < 0) return ret; @@ -327,7 +344,8 @@ static int cros_chctl_probe(struct platform_device *pdev) priv->current_end_threshold = 100; /* Bring EC into well-known state */ - ret = cros_chctl_configure_ec(priv); + scoped_guard(mutex, &priv->lock) + ret = cros_chctl_configure_ec(priv); if (ret < 0) return ret; diff --git a/drivers/power/supply/gpio-charger.c b/drivers/power/supply/gpio-charger.c index 68212b39785b..6139f736ecbe 100644 --- a/drivers/power/supply/gpio-charger.c +++ b/drivers/power/supply/gpio-charger.c @@ -67,6 +67,14 @@ static int set_charge_current_limit(struct gpio_charger *gpio_charger, int val) if (gpio_charger->current_limit_map[i].limit_ua <= val) break; } + + /* + * If a valid charge current limit isn't found, default to smallest + * current limitation for safety reasons. + */ + if (i >= gpio_charger->current_limit_map_size) + i = gpio_charger->current_limit_map_size - 1; + mapping = gpio_charger->current_limit_map[i]; for (i = 0; i < ndescs; i++) { diff --git a/drivers/ptp/ptp_kvm_x86.c b/drivers/ptp/ptp_kvm_x86.c index 617c8d6706d3..6cea4fe39bcf 100644 --- a/drivers/ptp/ptp_kvm_x86.c +++ b/drivers/ptp/ptp_kvm_x86.c @@ -26,7 +26,7 @@ int kvm_arch_ptp_init(void) long ret; if (!kvm_para_available()) - return -ENODEV; + return -EOPNOTSUPP; if (cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT)) { p = alloc_page(GFP_KERNEL | __GFP_ZERO); @@ -46,14 +46,14 @@ int kvm_arch_ptp_init(void) clock_pair_gpa = slow_virt_to_phys(clock_pair); if (!pvclock_get_pvti_cpu0_va()) { - ret = -ENODEV; + ret = -EOPNOTSUPP; goto err; } ret = kvm_hypercall2(KVM_HC_CLOCK_PAIRING, clock_pair_gpa, KVM_CLOCK_PAIRING_WALLCLOCK); if (ret == -KVM_ENOSYS) { - ret = -ENODEV; + ret = -EOPNOTSUPP; goto err; } diff --git a/drivers/regulator/axp20x-regulator.c b/drivers/regulator/axp20x-regulator.c index a8e91d9d028b..945d2917b91b 100644 --- a/drivers/regulator/axp20x-regulator.c +++ b/drivers/regulator/axp20x-regulator.c @@ -371,8 +371,8 @@ .ops = &axp20x_ops, \ } -#define AXP_DESC(_family, _id, _match, _supply, _min, _max, _step, _vreg, \ - _vmask, _ereg, _emask) \ +#define AXP_DESC_DELAY(_family, _id, _match, _supply, _min, _max, _step, _vreg, \ + _vmask, _ereg, _emask, _ramp_delay) \ [_family##_##_id] = { \ .name = (_match), \ .supply_name = (_supply), \ @@ -388,9 +388,15 @@ .vsel_mask = (_vmask), \ .enable_reg = (_ereg), \ .enable_mask = (_emask), \ + .ramp_delay = (_ramp_delay), \ .ops = &axp20x_ops, \ } +#define AXP_DESC(_family, _id, _match, _supply, _min, _max, _step, _vreg, \ + _vmask, _ereg, _emask) \ + AXP_DESC_DELAY(_family, _id, _match, _supply, _min, _max, _step, _vreg, \ + _vmask, _ereg, _emask, 0) + #define AXP_DESC_SW(_family, _id, _match, _supply, _ereg, _emask) \ [_family##_##_id] = { \ .name = (_match), \ @@ -419,8 +425,8 @@ .ops = &axp20x_ops_fixed \ } -#define AXP_DESC_RANGES(_family, _id, _match, _supply, _ranges, _n_voltages, \ - _vreg, _vmask, _ereg, _emask) \ +#define AXP_DESC_RANGES_DELAY(_family, _id, _match, _supply, _ranges, _n_voltages, \ + _vreg, _vmask, _ereg, _emask, _ramp_delay) \ [_family##_##_id] = { \ .name = (_match), \ .supply_name = (_supply), \ @@ -436,9 +442,15 @@ .enable_mask = (_emask), \ .linear_ranges = (_ranges), \ .n_linear_ranges = ARRAY_SIZE(_ranges), \ + .ramp_delay = (_ramp_delay), \ .ops = &axp20x_ops_range, \ } +#define AXP_DESC_RANGES(_family, _id, _match, _supply, _ranges, _n_voltages, \ + _vreg, _vmask, _ereg, _emask) \ + AXP_DESC_RANGES_DELAY(_family, _id, _match, _supply, _ranges, \ + _n_voltages, _vreg, _vmask, _ereg, _emask, 0) + static const int axp209_dcdc2_ldo3_slew_rates[] = { 1600, 800, @@ -781,21 +793,21 @@ static const struct linear_range axp717_dcdc3_ranges[] = { }; static const struct regulator_desc axp717_regulators[] = { - AXP_DESC_RANGES(AXP717, DCDC1, "dcdc1", "vin1", + AXP_DESC_RANGES_DELAY(AXP717, DCDC1, "dcdc1", "vin1", axp717_dcdc1_ranges, AXP717_DCDC1_NUM_VOLTAGES, AXP717_DCDC1_CONTROL, AXP717_DCDC_V_OUT_MASK, - AXP717_DCDC_OUTPUT_CONTROL, BIT(0)), - AXP_DESC_RANGES(AXP717, DCDC2, "dcdc2", "vin2", + AXP717_DCDC_OUTPUT_CONTROL, BIT(0), 640), + AXP_DESC_RANGES_DELAY(AXP717, DCDC2, "dcdc2", "vin2", axp717_dcdc2_ranges, AXP717_DCDC2_NUM_VOLTAGES, AXP717_DCDC2_CONTROL, AXP717_DCDC_V_OUT_MASK, - AXP717_DCDC_OUTPUT_CONTROL, BIT(1)), - AXP_DESC_RANGES(AXP717, DCDC3, "dcdc3", "vin3", + AXP717_DCDC_OUTPUT_CONTROL, BIT(1), 640), + AXP_DESC_RANGES_DELAY(AXP717, DCDC3, "dcdc3", "vin3", axp717_dcdc3_ranges, AXP717_DCDC3_NUM_VOLTAGES, AXP717_DCDC3_CONTROL, AXP717_DCDC_V_OUT_MASK, - AXP717_DCDC_OUTPUT_CONTROL, BIT(2)), - AXP_DESC(AXP717, DCDC4, "dcdc4", "vin4", 1000, 3700, 100, + AXP717_DCDC_OUTPUT_CONTROL, BIT(2), 640), + AXP_DESC_DELAY(AXP717, DCDC4, "dcdc4", "vin4", 1000, 3700, 100, AXP717_DCDC4_CONTROL, AXP717_DCDC_V_OUT_MASK, - AXP717_DCDC_OUTPUT_CONTROL, BIT(3)), + AXP717_DCDC_OUTPUT_CONTROL, BIT(3), 6400), AXP_DESC(AXP717, ALDO1, "aldo1", "aldoin", 500, 3500, 100, AXP717_ALDO1_CONTROL, AXP717_LDO_V_OUT_MASK, AXP717_LDO0_OUTPUT_CONTROL, BIT(0)), diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c index 8e75e2e279a4..50f1dcb6d584 100644 --- a/drivers/scsi/megaraid/megaraid_sas_base.c +++ b/drivers/scsi/megaraid/megaraid_sas_base.c @@ -8907,8 +8907,11 @@ megasas_aen_polling(struct work_struct *work) (ld_target_id / MEGASAS_MAX_DEV_PER_CHANNEL), (ld_target_id % MEGASAS_MAX_DEV_PER_CHANNEL), 0); - if (sdev1) + if (sdev1) { + mutex_unlock(&instance->reset_mutex); megasas_remove_scsi_device(sdev1); + mutex_lock(&instance->reset_mutex); + } event_type = SCAN_VD_CHANNEL; break; diff --git a/drivers/scsi/mpi3mr/mpi3mr.h b/drivers/scsi/mpi3mr/mpi3mr.h index 81bb408ce56d..1e715fd65a7d 100644 --- a/drivers/scsi/mpi3mr/mpi3mr.h +++ b/drivers/scsi/mpi3mr/mpi3mr.h @@ -134,8 +134,6 @@ extern atomic64_t event_counter; #define MPI3MR_WATCHDOG_INTERVAL 1000 /* in milli seconds */ -#define MPI3MR_DEFAULT_CFG_PAGE_SZ 1024 /* in bytes */ - #define MPI3MR_RESET_TOPOLOGY_SETTLE_TIME 10 #define MPI3MR_SCMD_TIMEOUT (60 * HZ) @@ -1133,9 +1131,6 @@ struct scmd_priv { * @io_throttle_low: I/O size to stop throttle in 512b blocks * @num_io_throttle_group: Maximum number of throttle groups * @throttle_groups: Pointer to throttle group info structures - * @cfg_page: Default memory for configuration pages - * @cfg_page_dma: Configuration page DMA address - * @cfg_page_sz: Default configuration page memory size * @sas_transport_enabled: SAS transport enabled or not * @scsi_device_channel: Channel ID for SCSI devices * @transport_cmds: Command tracker for SAS transport commands @@ -1332,10 +1327,6 @@ struct mpi3mr_ioc { u16 num_io_throttle_group; struct mpi3mr_throttle_group_info *throttle_groups; - void *cfg_page; - dma_addr_t cfg_page_dma; - u16 cfg_page_sz; - u8 sas_transport_enabled; u8 scsi_device_channel; struct mpi3mr_drv_cmd transport_cmds; diff --git a/drivers/scsi/mpi3mr/mpi3mr_app.c b/drivers/scsi/mpi3mr/mpi3mr_app.c index 01f035f9330e..10b8e4dc64f8 100644 --- a/drivers/scsi/mpi3mr/mpi3mr_app.c +++ b/drivers/scsi/mpi3mr/mpi3mr_app.c @@ -2329,6 +2329,15 @@ static long mpi3mr_bsg_process_mpt_cmds(struct bsg_job *job) if (!mrioc) return -ENODEV; + if (mutex_lock_interruptible(&mrioc->bsg_cmds.mutex)) + return -ERESTARTSYS; + + if (mrioc->bsg_cmds.state & MPI3MR_CMD_PENDING) { + dprint_bsg_err(mrioc, "%s: command is in use\n", __func__); + mutex_unlock(&mrioc->bsg_cmds.mutex); + return -EAGAIN; + } + if (!mrioc->ioctl_sges_allocated) { dprint_bsg_err(mrioc, "%s: DMA memory was not allocated\n", __func__); @@ -2339,13 +2348,16 @@ static long mpi3mr_bsg_process_mpt_cmds(struct bsg_job *job) karg->timeout = MPI3MR_APP_DEFAULT_TIMEOUT; mpi_req = kzalloc(MPI3MR_ADMIN_REQ_FRAME_SZ, GFP_KERNEL); - if (!mpi_req) + if (!mpi_req) { + mutex_unlock(&mrioc->bsg_cmds.mutex); return -ENOMEM; + } mpi_header = (struct mpi3_request_header *)mpi_req; bufcnt = karg->buf_entry_list.num_of_entries; drv_bufs = kzalloc((sizeof(*drv_bufs) * bufcnt), GFP_KERNEL); if (!drv_bufs) { + mutex_unlock(&mrioc->bsg_cmds.mutex); rval = -ENOMEM; goto out; } @@ -2353,6 +2365,7 @@ static long mpi3mr_bsg_process_mpt_cmds(struct bsg_job *job) dout_buf = kzalloc(job->request_payload.payload_len, GFP_KERNEL); if (!dout_buf) { + mutex_unlock(&mrioc->bsg_cmds.mutex); rval = -ENOMEM; goto out; } @@ -2360,6 +2373,7 @@ static long mpi3mr_bsg_process_mpt_cmds(struct bsg_job *job) din_buf = kzalloc(job->reply_payload.payload_len, GFP_KERNEL); if (!din_buf) { + mutex_unlock(&mrioc->bsg_cmds.mutex); rval = -ENOMEM; goto out; } @@ -2435,6 +2449,7 @@ static long mpi3mr_bsg_process_mpt_cmds(struct bsg_job *job) (mpi_msg_size > MPI3MR_ADMIN_REQ_FRAME_SZ)) { dprint_bsg_err(mrioc, "%s: invalid MPI message size\n", __func__); + mutex_unlock(&mrioc->bsg_cmds.mutex); rval = -EINVAL; goto out; } @@ -2447,6 +2462,7 @@ static long mpi3mr_bsg_process_mpt_cmds(struct bsg_job *job) if (invalid_be) { dprint_bsg_err(mrioc, "%s: invalid buffer entries passed\n", __func__); + mutex_unlock(&mrioc->bsg_cmds.mutex); rval = -EINVAL; goto out; } @@ -2454,12 +2470,14 @@ static long mpi3mr_bsg_process_mpt_cmds(struct bsg_job *job) if (sgl_dout_iter > (dout_buf + job->request_payload.payload_len)) { dprint_bsg_err(mrioc, "%s: data_out buffer length mismatch\n", __func__); + mutex_unlock(&mrioc->bsg_cmds.mutex); rval = -EINVAL; goto out; } if (sgl_din_iter > (din_buf + job->reply_payload.payload_len)) { dprint_bsg_err(mrioc, "%s: data_in buffer length mismatch\n", __func__); + mutex_unlock(&mrioc->bsg_cmds.mutex); rval = -EINVAL; goto out; } @@ -2472,6 +2490,7 @@ static long mpi3mr_bsg_process_mpt_cmds(struct bsg_job *job) dprint_bsg_err(mrioc, "%s:%d: invalid data transfer size passed for function 0x%x din_size = %d, dout_size = %d\n", __func__, __LINE__, mpi_header->function, din_size, dout_size); + mutex_unlock(&mrioc->bsg_cmds.mutex); rval = -EINVAL; goto out; } @@ -2480,6 +2499,7 @@ static long mpi3mr_bsg_process_mpt_cmds(struct bsg_job *job) dprint_bsg_err(mrioc, "%s:%d: invalid data transfer size passed for function 0x%x din_size=%d\n", __func__, __LINE__, mpi_header->function, din_size); + mutex_unlock(&mrioc->bsg_cmds.mutex); rval = -EINVAL; goto out; } @@ -2487,6 +2507,7 @@ static long mpi3mr_bsg_process_mpt_cmds(struct bsg_job *job) dprint_bsg_err(mrioc, "%s:%d: invalid data transfer size passed for function 0x%x dout_size = %d\n", __func__, __LINE__, mpi_header->function, dout_size); + mutex_unlock(&mrioc->bsg_cmds.mutex); rval = -EINVAL; goto out; } @@ -2497,6 +2518,7 @@ static long mpi3mr_bsg_process_mpt_cmds(struct bsg_job *job) dprint_bsg_err(mrioc, "%s:%d: invalid message size passed:%d:%d:%d:%d\n", __func__, __LINE__, din_cnt, dout_cnt, din_size, dout_size); + mutex_unlock(&mrioc->bsg_cmds.mutex); rval = -EINVAL; goto out; } @@ -2544,6 +2566,7 @@ static long mpi3mr_bsg_process_mpt_cmds(struct bsg_job *job) continue; if (mpi3mr_map_data_buffer_dma(mrioc, drv_buf_iter, desc_count)) { rval = -ENOMEM; + mutex_unlock(&mrioc->bsg_cmds.mutex); dprint_bsg_err(mrioc, "%s:%d: mapping data buffers failed\n", __func__, __LINE__); goto out; @@ -2556,20 +2579,11 @@ static long mpi3mr_bsg_process_mpt_cmds(struct bsg_job *job) sense_buff_k = kzalloc(erbsz, GFP_KERNEL); if (!sense_buff_k) { rval = -ENOMEM; + mutex_unlock(&mrioc->bsg_cmds.mutex); goto out; } } - if (mutex_lock_interruptible(&mrioc->bsg_cmds.mutex)) { - rval = -ERESTARTSYS; - goto out; - } - if (mrioc->bsg_cmds.state & MPI3MR_CMD_PENDING) { - rval = -EAGAIN; - dprint_bsg_err(mrioc, "%s: command is in use\n", __func__); - mutex_unlock(&mrioc->bsg_cmds.mutex); - goto out; - } if (mrioc->unrecoverable) { dprint_bsg_err(mrioc, "%s: unrecoverable controller\n", __func__); diff --git a/drivers/scsi/mpi3mr/mpi3mr_fw.c b/drivers/scsi/mpi3mr/mpi3mr_fw.c index f1ab76351bd8..5ed31fe57474 100644 --- a/drivers/scsi/mpi3mr/mpi3mr_fw.c +++ b/drivers/scsi/mpi3mr/mpi3mr_fw.c @@ -1036,6 +1036,36 @@ static const char *mpi3mr_reset_type_name(u16 reset_type) } /** + * mpi3mr_is_fault_recoverable - Read fault code and decide + * whether the controller can be recoverable + * @mrioc: Adapter instance reference + * Return: true if fault is recoverable, false otherwise. + */ +static inline bool mpi3mr_is_fault_recoverable(struct mpi3mr_ioc *mrioc) +{ + u32 fault; + + fault = (readl(&mrioc->sysif_regs->fault) & + MPI3_SYSIF_FAULT_CODE_MASK); + + switch (fault) { + case MPI3_SYSIF_FAULT_CODE_COMPLETE_RESET_NEEDED: + case MPI3_SYSIF_FAULT_CODE_POWER_CYCLE_REQUIRED: + ioc_warn(mrioc, + "controller requires system power cycle, marking controller as unrecoverable\n"); + return false; + case MPI3_SYSIF_FAULT_CODE_INSUFFICIENT_PCI_SLOT_POWER: + ioc_warn(mrioc, + "controller faulted due to insufficient power,\n" + " try by connecting it to a different slot\n"); + return false; + default: + break; + } + return true; +} + +/** * mpi3mr_print_fault_info - Display fault information * @mrioc: Adapter instance reference * @@ -1373,6 +1403,11 @@ retry_bring_ioc_ready: ioc_info(mrioc, "ioc_status(0x%08x), ioc_config(0x%08x), ioc_info(0x%016llx) at the bringup\n", ioc_status, ioc_config, base_info); + if (!mpi3mr_is_fault_recoverable(mrioc)) { + mrioc->unrecoverable = 1; + goto out_device_not_present; + } + /*The timeout value is in 2sec unit, changing it to seconds*/ mrioc->ready_timeout = ((base_info & MPI3_SYSIF_IOC_INFO_LOW_TIMEOUT_MASK) >> @@ -2734,6 +2769,11 @@ static void mpi3mr_watchdog_work(struct work_struct *work) mpi3mr_print_fault_info(mrioc); mrioc->diagsave_timeout = 0; + if (!mpi3mr_is_fault_recoverable(mrioc)) { + mrioc->unrecoverable = 1; + goto schedule_work; + } + switch (trigger_data.fault) { case MPI3_SYSIF_FAULT_CODE_COMPLETE_RESET_NEEDED: case MPI3_SYSIF_FAULT_CODE_POWER_CYCLE_REQUIRED: @@ -4186,17 +4226,6 @@ retry_init: mpi3mr_read_tsu_interval(mrioc); mpi3mr_print_ioc_info(mrioc); - if (!mrioc->cfg_page) { - dprint_init(mrioc, "allocating config page buffers\n"); - mrioc->cfg_page_sz = MPI3MR_DEFAULT_CFG_PAGE_SZ; - mrioc->cfg_page = dma_alloc_coherent(&mrioc->pdev->dev, - mrioc->cfg_page_sz, &mrioc->cfg_page_dma, GFP_KERNEL); - if (!mrioc->cfg_page) { - retval = -1; - goto out_failed_noretry; - } - } - dprint_init(mrioc, "allocating host diag buffers\n"); mpi3mr_alloc_diag_bufs(mrioc); @@ -4768,11 +4797,7 @@ void mpi3mr_free_mem(struct mpi3mr_ioc *mrioc) mrioc->admin_req_base, mrioc->admin_req_dma); mrioc->admin_req_base = NULL; } - if (mrioc->cfg_page) { - dma_free_coherent(&mrioc->pdev->dev, mrioc->cfg_page_sz, - mrioc->cfg_page, mrioc->cfg_page_dma); - mrioc->cfg_page = NULL; - } + if (mrioc->pel_seqnum_virt) { dma_free_coherent(&mrioc->pdev->dev, mrioc->pel_seqnum_sz, mrioc->pel_seqnum_virt, mrioc->pel_seqnum_dma); @@ -5392,55 +5417,6 @@ out: return retval; } - -/** - * mpi3mr_free_config_dma_memory - free memory for config page - * @mrioc: Adapter instance reference - * @mem_desc: memory descriptor structure - * - * Check whether the size of the buffer specified by the memory - * descriptor is greater than the default page size if so then - * free the memory pointed by the descriptor. - * - * Return: Nothing. - */ -static void mpi3mr_free_config_dma_memory(struct mpi3mr_ioc *mrioc, - struct dma_memory_desc *mem_desc) -{ - if ((mem_desc->size > mrioc->cfg_page_sz) && mem_desc->addr) { - dma_free_coherent(&mrioc->pdev->dev, mem_desc->size, - mem_desc->addr, mem_desc->dma_addr); - mem_desc->addr = NULL; - } -} - -/** - * mpi3mr_alloc_config_dma_memory - Alloc memory for config page - * @mrioc: Adapter instance reference - * @mem_desc: Memory descriptor to hold dma memory info - * - * This function allocates new dmaable memory or provides the - * default config page dmaable memory based on the memory size - * described by the descriptor. - * - * Return: 0 on success, non-zero on failure. - */ -static int mpi3mr_alloc_config_dma_memory(struct mpi3mr_ioc *mrioc, - struct dma_memory_desc *mem_desc) -{ - if (mem_desc->size > mrioc->cfg_page_sz) { - mem_desc->addr = dma_alloc_coherent(&mrioc->pdev->dev, - mem_desc->size, &mem_desc->dma_addr, GFP_KERNEL); - if (!mem_desc->addr) - return -ENOMEM; - } else { - mem_desc->addr = mrioc->cfg_page; - mem_desc->dma_addr = mrioc->cfg_page_dma; - memset(mem_desc->addr, 0, mrioc->cfg_page_sz); - } - return 0; -} - /** * mpi3mr_post_cfg_req - Issue config requests and wait * @mrioc: Adapter instance reference @@ -5596,8 +5572,12 @@ static int mpi3mr_process_cfg_req(struct mpi3mr_ioc *mrioc, cfg_req->page_length = cfg_hdr->page_length; cfg_req->page_version = cfg_hdr->page_version; } - if (mpi3mr_alloc_config_dma_memory(mrioc, &mem_desc)) - goto out; + + mem_desc.addr = dma_alloc_coherent(&mrioc->pdev->dev, + mem_desc.size, &mem_desc.dma_addr, GFP_KERNEL); + + if (!mem_desc.addr) + return retval; mpi3mr_add_sg_single(&cfg_req->sgl, sgl_flags, mem_desc.size, mem_desc.dma_addr); @@ -5626,7 +5606,12 @@ static int mpi3mr_process_cfg_req(struct mpi3mr_ioc *mrioc, } out: - mpi3mr_free_config_dma_memory(mrioc, &mem_desc); + if (mem_desc.addr) { + dma_free_coherent(&mrioc->pdev->dev, mem_desc.size, + mem_desc.addr, mem_desc.dma_addr); + mem_desc.addr = NULL; + } + return retval; } diff --git a/drivers/scsi/mpi3mr/mpi3mr_os.c b/drivers/scsi/mpi3mr/mpi3mr_os.c index 5f2f67acf8bf..1bef88130d0c 100644 --- a/drivers/scsi/mpi3mr/mpi3mr_os.c +++ b/drivers/scsi/mpi3mr/mpi3mr_os.c @@ -5215,7 +5215,7 @@ mpi3mr_probe(struct pci_dev *pdev, const struct pci_device_id *id) } mrioc = shost_priv(shost); - retval = ida_alloc_range(&mrioc_ida, 1, U8_MAX, GFP_KERNEL); + retval = ida_alloc_range(&mrioc_ida, 0, U8_MAX, GFP_KERNEL); if (retval < 0) goto id_alloc_failed; mrioc->id = (u8)retval; diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c index ed5046593fda..16ac2267c71e 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_base.c +++ b/drivers/scsi/mpt3sas/mpt3sas_base.c @@ -7041,11 +7041,12 @@ _base_handshake_req_reply_wait(struct MPT3SAS_ADAPTER *ioc, int request_bytes, int i; u8 failed; __le32 *mfp; + int ret_val; /* make sure doorbell is not in use */ if ((ioc->base_readl_ext_retry(&ioc->chip->Doorbell) & MPI2_DOORBELL_USED)) { ioc_err(ioc, "doorbell is in use (line=%d)\n", __LINE__); - return -EFAULT; + goto doorbell_diag_reset; } /* clear pending doorbell interrupts from previous state changes */ @@ -7135,6 +7136,10 @@ _base_handshake_req_reply_wait(struct MPT3SAS_ADAPTER *ioc, int request_bytes, le32_to_cpu(mfp[i])); } return 0; + +doorbell_diag_reset: + ret_val = _base_diag_reset(ioc); + return ret_val; } /** diff --git a/drivers/scsi/qla1280.h b/drivers/scsi/qla1280.h index d309e2ca14de..dea2290b37d4 100644 --- a/drivers/scsi/qla1280.h +++ b/drivers/scsi/qla1280.h @@ -116,12 +116,12 @@ struct device_reg { uint16_t id_h; /* ID high */ uint16_t cfg_0; /* Configuration 0 */ #define ISP_CFG0_HWMSK 0x000f /* Hardware revision mask */ -#define ISP_CFG0_1020 BIT_0 /* ISP1020 */ -#define ISP_CFG0_1020A BIT_1 /* ISP1020A */ -#define ISP_CFG0_1040 BIT_2 /* ISP1040 */ -#define ISP_CFG0_1040A BIT_3 /* ISP1040A */ -#define ISP_CFG0_1040B BIT_4 /* ISP1040B */ -#define ISP_CFG0_1040C BIT_5 /* ISP1040C */ +#define ISP_CFG0_1020 1 /* ISP1020 */ +#define ISP_CFG0_1020A 2 /* ISP1020A */ +#define ISP_CFG0_1040 3 /* ISP1040 */ +#define ISP_CFG0_1040A 4 /* ISP1040A */ +#define ISP_CFG0_1040B 5 /* ISP1040B */ +#define ISP_CFG0_1040C 6 /* ISP1040C */ uint16_t cfg_1; /* Configuration 1 */ #define ISP_CFG1_F128 BIT_6 /* 128-byte FIFO threshold */ #define ISP_CFG1_F64 BIT_4|BIT_5 /* 128-byte FIFO threshold */ diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c index 7ceb982040a5..d0b55c1fa908 100644 --- a/drivers/scsi/storvsc_drv.c +++ b/drivers/scsi/storvsc_drv.c @@ -149,6 +149,8 @@ struct hv_fc_wwn_packet { */ static int vmstor_proto_version; +static bool hv_dev_is_fc(struct hv_device *hv_dev); + #define STORVSC_LOGGING_NONE 0 #define STORVSC_LOGGING_ERROR 1 #define STORVSC_LOGGING_WARN 2 @@ -1138,6 +1140,7 @@ static void storvsc_on_io_completion(struct storvsc_device *stor_device, * not correctly handle: * INQUIRY command with page code parameter set to 0x80 * MODE_SENSE command with cmd[2] == 0x1c + * MAINTENANCE_IN is not supported by HyperV FC passthrough * * Setup srb and scsi status so this won't be fatal. * We do this so we can distinguish truly fatal failues @@ -1145,7 +1148,9 @@ static void storvsc_on_io_completion(struct storvsc_device *stor_device, */ if ((stor_pkt->vm_srb.cdb[0] == INQUIRY) || - (stor_pkt->vm_srb.cdb[0] == MODE_SENSE)) { + (stor_pkt->vm_srb.cdb[0] == MODE_SENSE) || + (stor_pkt->vm_srb.cdb[0] == MAINTENANCE_IN && + hv_dev_is_fc(device))) { vstor_packet->vm_srb.scsi_status = 0; vstor_packet->vm_srb.srb_status = SRB_STATUS_SUCCESS; } diff --git a/drivers/spi/spi-aspeed-smc.c b/drivers/spi/spi-aspeed-smc.c index bbd417c55e7f..b0e3f307b283 100644 --- a/drivers/spi/spi-aspeed-smc.c +++ b/drivers/spi/spi-aspeed-smc.c @@ -239,7 +239,7 @@ static ssize_t aspeed_spi_read_user(struct aspeed_spi_chip *chip, ret = aspeed_spi_send_cmd_addr(chip, op->addr.nbytes, offset, op->cmd.opcode); if (ret < 0) - return ret; + goto stop_user; if (op->dummy.buswidth && op->dummy.nbytes) { for (i = 0; i < op->dummy.nbytes / op->dummy.buswidth; i++) @@ -249,8 +249,9 @@ static ssize_t aspeed_spi_read_user(struct aspeed_spi_chip *chip, aspeed_spi_set_io_mode(chip, io_mode); aspeed_spi_read_from_ahb(buf, chip->ahb_base, len); +stop_user: aspeed_spi_stop_user(chip); - return 0; + return ret; } static ssize_t aspeed_spi_write_user(struct aspeed_spi_chip *chip, @@ -261,10 +262,11 @@ static ssize_t aspeed_spi_write_user(struct aspeed_spi_chip *chip, aspeed_spi_start_user(chip); ret = aspeed_spi_send_cmd_addr(chip, op->addr.nbytes, op->addr.val, op->cmd.opcode); if (ret < 0) - return ret; + goto stop_user; aspeed_spi_write_to_ahb(chip->ahb_base, op->data.buf.out, op->data.nbytes); +stop_user: aspeed_spi_stop_user(chip); - return 0; + return ret; } /* support for 1-1-1, 1-1-2 or 1-1-4 */ diff --git a/drivers/spi/spi-cadence-quadspi.c b/drivers/spi/spi-cadence-quadspi.c index 1755ca026f08..73b1edd0531b 100644 --- a/drivers/spi/spi-cadence-quadspi.c +++ b/drivers/spi/spi-cadence-quadspi.c @@ -43,6 +43,7 @@ static_assert(CQSPI_MAX_CHIPSELECT <= SPI_CS_CNT_MAX); #define CQSPI_SLOW_SRAM BIT(4) #define CQSPI_NEEDS_APB_AHB_HAZARD_WAR BIT(5) #define CQSPI_RD_NO_IRQ BIT(6) +#define CQSPI_DISABLE_STIG_MODE BIT(7) /* Capabilities */ #define CQSPI_SUPPORTS_OCTAL BIT(0) @@ -103,6 +104,7 @@ struct cqspi_st { bool apb_ahb_hazard; bool is_jh7110; /* Flag for StarFive JH7110 SoC */ + bool disable_stig_mode; const struct cqspi_driver_platdata *ddata; }; @@ -1416,7 +1418,8 @@ static int cqspi_mem_process(struct spi_mem *mem, const struct spi_mem_op *op) * reads, prefer STIG mode for such small reads. */ if (!op->addr.nbytes || - op->data.nbytes <= CQSPI_STIG_DATA_LEN_MAX) + (op->data.nbytes <= CQSPI_STIG_DATA_LEN_MAX && + !cqspi->disable_stig_mode)) return cqspi_command_read(f_pdata, op); return cqspi_read(f_pdata, op); @@ -1880,6 +1883,8 @@ static int cqspi_probe(struct platform_device *pdev) if (ret) goto probe_reset_failed; } + if (ddata->quirks & CQSPI_DISABLE_STIG_MODE) + cqspi->disable_stig_mode = true; if (of_device_is_compatible(pdev->dev.of_node, "xlnx,versal-ospi-1.0")) { @@ -2043,7 +2048,8 @@ static const struct cqspi_driver_platdata intel_lgm_qspi = { static const struct cqspi_driver_platdata socfpga_qspi = { .quirks = CQSPI_DISABLE_DAC_MODE | CQSPI_NO_SUPPORT_WR_COMPLETION - | CQSPI_SLOW_SRAM, + | CQSPI_SLOW_SRAM + | CQSPI_DISABLE_STIG_MODE, }; static const struct cqspi_driver_platdata versal_ospi = { diff --git a/drivers/spi/spi-intel-pci.c b/drivers/spi/spi-intel-pci.c index 4337ca51d7aa..5c0dec90eec1 100644 --- a/drivers/spi/spi-intel-pci.c +++ b/drivers/spi/spi-intel-pci.c @@ -86,6 +86,8 @@ static const struct pci_device_id intel_spi_pci_ids[] = { { PCI_VDEVICE(INTEL, 0xa324), (unsigned long)&cnl_info }, { PCI_VDEVICE(INTEL, 0xa3a4), (unsigned long)&cnl_info }, { PCI_VDEVICE(INTEL, 0xa823), (unsigned long)&cnl_info }, + { PCI_VDEVICE(INTEL, 0xe323), (unsigned long)&cnl_info }, + { PCI_VDEVICE(INTEL, 0xe423), (unsigned long)&cnl_info }, { }, }; MODULE_DEVICE_TABLE(pci, intel_spi_pci_ids); diff --git a/drivers/spi/spi-omap2-mcspi.c b/drivers/spi/spi-omap2-mcspi.c index 2c043817c66a..4a2f84c4d22e 100644 --- a/drivers/spi/spi-omap2-mcspi.c +++ b/drivers/spi/spi-omap2-mcspi.c @@ -1561,10 +1561,10 @@ static int omap2_mcspi_probe(struct platform_device *pdev) } mcspi->ref_clk = devm_clk_get_optional_enabled(&pdev->dev, NULL); - if (mcspi->ref_clk) - mcspi->ref_clk_hz = clk_get_rate(mcspi->ref_clk); - else + if (IS_ERR(mcspi->ref_clk)) mcspi->ref_clk_hz = OMAP2_MCSPI_MAX_FREQ; + else + mcspi->ref_clk_hz = clk_get_rate(mcspi->ref_clk); ctlr->max_speed_hz = mcspi->ref_clk_hz; ctlr->min_speed_hz = mcspi->ref_clk_hz >> 15; diff --git a/drivers/spi/spi-rockchip.c b/drivers/spi/spi-rockchip.c index 0bb33c43b1b4..40a64a598a74 100644 --- a/drivers/spi/spi-rockchip.c +++ b/drivers/spi/spi-rockchip.c @@ -241,6 +241,20 @@ static void rockchip_spi_set_cs(struct spi_device *spi, bool enable) struct spi_controller *ctlr = spi->controller; struct rockchip_spi *rs = spi_controller_get_devdata(ctlr); bool cs_asserted = spi->mode & SPI_CS_HIGH ? enable : !enable; + bool cs_actual; + + /* + * SPI subsystem tries to avoid no-op calls that would break the PM + * refcount below. It can't however for the first time it is used. + * To detect this case we read it here and bail out early for no-ops. + */ + if (spi_get_csgpiod(spi, 0)) + cs_actual = !!(readl_relaxed(rs->regs + ROCKCHIP_SPI_SER) & 1); + else + cs_actual = !!(readl_relaxed(rs->regs + ROCKCHIP_SPI_SER) & + BIT(spi_get_chipselect(spi, 0))); + if (unlikely(cs_actual == cs_asserted)) + return; if (cs_asserted) { /* Keep things powered as long as CS is asserted */ diff --git a/drivers/thunderbolt/nhi.c b/drivers/thunderbolt/nhi.c index 7af2642b97cb..7c42e303740a 100644 --- a/drivers/thunderbolt/nhi.c +++ b/drivers/thunderbolt/nhi.c @@ -1520,6 +1520,14 @@ static struct pci_device_id nhi_ids[] = { .driver_data = (kernel_ulong_t)&icl_nhi_ops }, { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_LNL_NHI1), .driver_data = (kernel_ulong_t)&icl_nhi_ops }, + { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_PTL_M_NHI0), + .driver_data = (kernel_ulong_t)&icl_nhi_ops }, + { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_PTL_M_NHI1), + .driver_data = (kernel_ulong_t)&icl_nhi_ops }, + { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_PTL_P_NHI0), + .driver_data = (kernel_ulong_t)&icl_nhi_ops }, + { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_PTL_P_NHI1), + .driver_data = (kernel_ulong_t)&icl_nhi_ops }, { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_BARLOW_RIDGE_HOST_80G_NHI) }, { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_BARLOW_RIDGE_HOST_40G_NHI) }, diff --git a/drivers/thunderbolt/nhi.h b/drivers/thunderbolt/nhi.h index 7a07c7c1a9c2..16744f25a9a0 100644 --- a/drivers/thunderbolt/nhi.h +++ b/drivers/thunderbolt/nhi.h @@ -92,6 +92,10 @@ extern const struct tb_nhi_ops icl_nhi_ops; #define PCI_DEVICE_ID_INTEL_RPL_NHI1 0xa76d #define PCI_DEVICE_ID_INTEL_LNL_NHI0 0xa833 #define PCI_DEVICE_ID_INTEL_LNL_NHI1 0xa834 +#define PCI_DEVICE_ID_INTEL_PTL_M_NHI0 0xe333 +#define PCI_DEVICE_ID_INTEL_PTL_M_NHI1 0xe334 +#define PCI_DEVICE_ID_INTEL_PTL_P_NHI0 0xe433 +#define PCI_DEVICE_ID_INTEL_PTL_P_NHI1 0xe434 #define PCI_CLASS_SERIAL_USB_USB4 0x0c0340 diff --git a/drivers/thunderbolt/retimer.c b/drivers/thunderbolt/retimer.c index 89d2919d0193..eeb64433ebbc 100644 --- a/drivers/thunderbolt/retimer.c +++ b/drivers/thunderbolt/retimer.c @@ -103,6 +103,7 @@ static int tb_retimer_nvm_add(struct tb_retimer *rt) err_nvm: dev_dbg(&rt->dev, "NVM upgrade disabled\n"); + rt->no_nvm_upgrade = true; if (!IS_ERR(nvm)) tb_nvm_free(nvm); @@ -182,8 +183,6 @@ static ssize_t nvm_authenticate_show(struct device *dev, if (!rt->nvm) ret = -EAGAIN; - else if (rt->no_nvm_upgrade) - ret = -EOPNOTSUPP; else ret = sysfs_emit(buf, "%#x\n", rt->auth_status); @@ -323,8 +322,6 @@ static ssize_t nvm_version_show(struct device *dev, if (!rt->nvm) ret = -EAGAIN; - else if (rt->no_nvm_upgrade) - ret = -EOPNOTSUPP; else ret = sysfs_emit(buf, "%x.%x\n", rt->nvm->major, rt->nvm->minor); @@ -342,6 +339,19 @@ static ssize_t vendor_show(struct device *dev, struct device_attribute *attr, } static DEVICE_ATTR_RO(vendor); +static umode_t retimer_is_visible(struct kobject *kobj, struct attribute *attr, + int n) +{ + struct device *dev = kobj_to_dev(kobj); + struct tb_retimer *rt = tb_to_retimer(dev); + + if (attr == &dev_attr_nvm_authenticate.attr || + attr == &dev_attr_nvm_version.attr) + return rt->no_nvm_upgrade ? 0 : attr->mode; + + return attr->mode; +} + static struct attribute *retimer_attrs[] = { &dev_attr_device.attr, &dev_attr_nvm_authenticate.attr, @@ -351,6 +361,7 @@ static struct attribute *retimer_attrs[] = { }; static const struct attribute_group retimer_group = { + .is_visible = retimer_is_visible, .attrs = retimer_attrs, }; diff --git a/drivers/thunderbolt/tb.c b/drivers/thunderbolt/tb.c index 4f777788e917..a7c6919fbf97 100644 --- a/drivers/thunderbolt/tb.c +++ b/drivers/thunderbolt/tb.c @@ -2059,6 +2059,37 @@ static void tb_exit_redrive(struct tb_port *port) } } +static void tb_switch_enter_redrive(struct tb_switch *sw) +{ + struct tb_port *port; + + tb_switch_for_each_port(sw, port) + tb_enter_redrive(port); +} + +/* + * Called during system and runtime suspend to forcefully exit redrive + * mode without querying whether the resource is available. + */ +static void tb_switch_exit_redrive(struct tb_switch *sw) +{ + struct tb_port *port; + + if (!(sw->quirks & QUIRK_KEEP_POWER_IN_DP_REDRIVE)) + return; + + tb_switch_for_each_port(sw, port) { + if (!tb_port_is_dpin(port)) + continue; + + if (port->redrive) { + port->redrive = false; + pm_runtime_put(&sw->dev); + tb_port_dbg(port, "exit redrive mode\n"); + } + } +} + static void tb_dp_resource_unavailable(struct tb *tb, struct tb_port *port) { struct tb_port *in, *out; @@ -2909,6 +2940,7 @@ static int tb_start(struct tb *tb, bool reset) tb_create_usb3_tunnels(tb->root_switch); /* Add DP IN resources for the root switch */ tb_add_dp_resources(tb->root_switch); + tb_switch_enter_redrive(tb->root_switch); /* Make the discovered switches available to the userspace */ device_for_each_child(&tb->root_switch->dev, NULL, tb_scan_finalize_switch); @@ -2924,6 +2956,7 @@ static int tb_suspend_noirq(struct tb *tb) tb_dbg(tb, "suspending...\n"); tb_disconnect_and_release_dp(tb); + tb_switch_exit_redrive(tb->root_switch); tb_switch_suspend(tb->root_switch, false); tcm->hotplug_active = false; /* signal tb_handle_hotplug to quit */ tb_dbg(tb, "suspend finished\n"); @@ -3016,6 +3049,7 @@ static int tb_resume_noirq(struct tb *tb) tb_dbg(tb, "tunnels restarted, sleeping for 100ms\n"); msleep(100); } + tb_switch_enter_redrive(tb->root_switch); /* Allow tb_handle_hotplug to progress events */ tcm->hotplug_active = true; tb_dbg(tb, "resume finished\n"); @@ -3079,6 +3113,12 @@ static int tb_runtime_suspend(struct tb *tb) struct tb_cm *tcm = tb_priv(tb); mutex_lock(&tb->lock); + /* + * The below call only releases DP resources to allow exiting and + * re-entering redrive mode. + */ + tb_disconnect_and_release_dp(tb); + tb_switch_exit_redrive(tb->root_switch); tb_switch_suspend(tb->root_switch, true); tcm->hotplug_active = false; mutex_unlock(&tb->lock); @@ -3110,6 +3150,7 @@ static int tb_runtime_resume(struct tb *tb) tb_restore_children(tb->root_switch); list_for_each_entry_safe(tunnel, n, &tcm->tunnel_list, list) tb_tunnel_restart(tunnel); + tb_switch_enter_redrive(tb->root_switch); tcm->hotplug_active = true; mutex_unlock(&tb->lock); diff --git a/drivers/tty/serial/sh-sci.c b/drivers/tty/serial/sh-sci.c index b80e9a528e17..bdf17eafd359 100644 --- a/drivers/tty/serial/sh-sci.c +++ b/drivers/tty/serial/sh-sci.c @@ -157,6 +157,7 @@ struct sci_port { bool has_rtscts; bool autorts; + bool tx_occurred; }; #define SCI_NPORTS CONFIG_SERIAL_SH_SCI_NR_UARTS @@ -850,6 +851,7 @@ static void sci_transmit_chars(struct uart_port *port) { struct tty_port *tport = &port->state->port; unsigned int stopped = uart_tx_stopped(port); + struct sci_port *s = to_sci_port(port); unsigned short status; unsigned short ctrl; int count; @@ -885,6 +887,7 @@ static void sci_transmit_chars(struct uart_port *port) } sci_serial_out(port, SCxTDR, c); + s->tx_occurred = true; port->icount.tx++; } while (--count > 0); @@ -1241,6 +1244,8 @@ static void sci_dma_tx_complete(void *arg) if (kfifo_len(&tport->xmit_fifo) < WAKEUP_CHARS) uart_write_wakeup(port); + s->tx_occurred = true; + if (!kfifo_is_empty(&tport->xmit_fifo)) { s->cookie_tx = 0; schedule_work(&s->work_tx); @@ -1731,6 +1736,19 @@ static void sci_flush_buffer(struct uart_port *port) s->cookie_tx = -EINVAL; } } + +static void sci_dma_check_tx_occurred(struct sci_port *s) +{ + struct dma_tx_state state; + enum dma_status status; + + if (!s->chan_tx) + return; + + status = dmaengine_tx_status(s->chan_tx, s->cookie_tx, &state); + if (status == DMA_COMPLETE || status == DMA_IN_PROGRESS) + s->tx_occurred = true; +} #else /* !CONFIG_SERIAL_SH_SCI_DMA */ static inline void sci_request_dma(struct uart_port *port) { @@ -1740,6 +1758,10 @@ static inline void sci_free_dma(struct uart_port *port) { } +static void sci_dma_check_tx_occurred(struct sci_port *s) +{ +} + #define sci_flush_buffer NULL #endif /* !CONFIG_SERIAL_SH_SCI_DMA */ @@ -2076,6 +2098,12 @@ static unsigned int sci_tx_empty(struct uart_port *port) { unsigned short status = sci_serial_in(port, SCxSR); unsigned short in_tx_fifo = sci_txfill(port); + struct sci_port *s = to_sci_port(port); + + sci_dma_check_tx_occurred(s); + + if (!s->tx_occurred) + return TIOCSER_TEMT; return (status & SCxSR_TEND(port)) && !in_tx_fifo ? TIOCSER_TEMT : 0; } @@ -2247,6 +2275,7 @@ static int sci_startup(struct uart_port *port) dev_dbg(port->dev, "%s(%d)\n", __func__, port->line); + s->tx_occurred = false; sci_request_dma(port); ret = sci_request_irq(s); diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c index cfebe4a1af9e..bc13133efaa5 100644 --- a/drivers/ufs/core/ufshcd.c +++ b/drivers/ufs/core/ufshcd.c @@ -5566,6 +5566,7 @@ void ufshcd_compl_one_cqe(struct ufs_hba *hba, int task_tag, lrbp = &hba->lrb[task_tag]; lrbp->compl_time_stamp = ktime_get(); + lrbp->compl_time_stamp_local_clock = local_clock(); cmd = lrbp->cmd; if (cmd) { if (unlikely(ufshcd_should_inform_monitor(hba, lrbp))) diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c index 500dc35e6477..0b2490347b9f 100644 --- a/drivers/usb/core/hcd.c +++ b/drivers/usb/core/hcd.c @@ -2794,8 +2794,14 @@ int usb_add_hcd(struct usb_hcd *hcd, int retval; struct usb_device *rhdev; struct usb_hcd *shared_hcd; + int skip_phy_initialization; - if (!hcd->skip_phy_initialization) { + if (usb_hcd_is_primary_hcd(hcd)) + skip_phy_initialization = hcd->skip_phy_initialization; + else + skip_phy_initialization = hcd->primary_hcd->skip_phy_initialization; + + if (!skip_phy_initialization) { if (usb_hcd_is_primary_hcd(hcd)) { hcd->phy_roothub = usb_phy_roothub_alloc(hcd->self.sysdev); if (IS_ERR(hcd->phy_roothub)) diff --git a/drivers/usb/dwc2/hcd.c b/drivers/usb/dwc2/hcd.c index cb54390e7de4..8c3941ecaaf5 100644 --- a/drivers/usb/dwc2/hcd.c +++ b/drivers/usb/dwc2/hcd.c @@ -3546,11 +3546,9 @@ static int dwc2_hcd_hub_control(struct dwc2_hsotg *hsotg, u16 typereq, port_status |= USB_PORT_STAT_C_OVERCURRENT << 16; } - if (!hsotg->flags.b.port_connect_status) { + if (dwc2_is_device_mode(hsotg)) { /* - * The port is disconnected, which means the core is - * either in device mode or it soon will be. Just - * return 0's for the remainder of the port status + * Just return 0's for the remainder of the port status * since the port register can't be read if the core * is in device mode. */ @@ -3620,13 +3618,11 @@ static int dwc2_hcd_hub_control(struct dwc2_hsotg *hsotg, u16 typereq, if (wvalue != USB_PORT_FEAT_TEST && (!windex || windex > 1)) goto error; - if (!hsotg->flags.b.port_connect_status) { + if (dwc2_is_device_mode(hsotg)) { /* - * The port is disconnected, which means the core is - * either in device mode or it soon will be. Just - * return without doing anything since the port - * register can't be written if the core is in device - * mode. + * Just return 0's for the remainder of the port status + * since the port register can't be read if the core + * is in device mode. */ break; } @@ -4349,7 +4345,7 @@ static int _dwc2_hcd_suspend(struct usb_hcd *hcd) if (hsotg->bus_suspended) goto skip_power_saving; - if (hsotg->flags.b.port_connect_status == 0) + if (!(dwc2_read_hprt0(hsotg) & HPRT0_CONNSTS)) goto skip_power_saving; switch (hsotg->params.power_down) { @@ -4431,6 +4427,7 @@ static int _dwc2_hcd_resume(struct usb_hcd *hcd) * Power Down mode. */ if (hprt0 & HPRT0_CONNSTS) { + set_bit(HCD_FLAG_HW_ACCESSIBLE, &hcd->flags); hsotg->lx_state = DWC2_L0; goto unlock; } diff --git a/drivers/usb/dwc3/dwc3-imx8mp.c b/drivers/usb/dwc3/dwc3-imx8mp.c index 64c0cd1995aa..e99faf014c78 100644 --- a/drivers/usb/dwc3/dwc3-imx8mp.c +++ b/drivers/usb/dwc3/dwc3-imx8mp.c @@ -129,6 +129,16 @@ static void dwc3_imx8mp_wakeup_disable(struct dwc3_imx8mp *dwc3_imx) writel(val, dwc3_imx->hsio_blk_base + USB_WAKEUP_CTRL); } +static const struct property_entry dwc3_imx8mp_properties[] = { + PROPERTY_ENTRY_BOOL("xhci-missing-cas-quirk"), + PROPERTY_ENTRY_BOOL("xhci-skip-phy-init-quirk"), + {}, +}; + +static const struct software_node dwc3_imx8mp_swnode = { + .properties = dwc3_imx8mp_properties, +}; + static irqreturn_t dwc3_imx8mp_interrupt(int irq, void *_dwc3_imx) { struct dwc3_imx8mp *dwc3_imx = _dwc3_imx; @@ -148,17 +158,6 @@ static irqreturn_t dwc3_imx8mp_interrupt(int irq, void *_dwc3_imx) return IRQ_HANDLED; } -static int dwc3_imx8mp_set_software_node(struct device *dev) -{ - struct property_entry props[3] = { 0 }; - int prop_idx = 0; - - props[prop_idx++] = PROPERTY_ENTRY_BOOL("xhci-missing-cas-quirk"); - props[prop_idx++] = PROPERTY_ENTRY_BOOL("xhci-skip-phy-init-quirk"); - - return device_create_managed_software_node(dev, props, NULL); -} - static int dwc3_imx8mp_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; @@ -221,17 +220,17 @@ static int dwc3_imx8mp_probe(struct platform_device *pdev) if (err < 0) goto disable_rpm; - err = dwc3_imx8mp_set_software_node(dev); + err = device_add_software_node(dev, &dwc3_imx8mp_swnode); if (err) { err = -ENODEV; - dev_err(dev, "failed to create software node\n"); + dev_err(dev, "failed to add software node\n"); goto disable_rpm; } err = of_platform_populate(node, NULL, NULL, dev); if (err) { dev_err(&pdev->dev, "failed to create dwc3 core\n"); - goto disable_rpm; + goto remove_swnode; } dwc3_imx->dwc3 = of_find_device_by_node(dwc3_np); @@ -255,6 +254,8 @@ static int dwc3_imx8mp_probe(struct platform_device *pdev) depopulate: of_platform_depopulate(dev); +remove_swnode: + device_remove_software_node(dev); disable_rpm: pm_runtime_disable(dev); pm_runtime_put_noidle(dev); @@ -268,6 +269,7 @@ static void dwc3_imx8mp_remove(struct platform_device *pdev) pm_runtime_get_sync(dev); of_platform_depopulate(dev); + device_remove_software_node(dev); pm_runtime_disable(dev); pm_runtime_put_noidle(dev); diff --git a/drivers/usb/dwc3/dwc3-xilinx.c b/drivers/usb/dwc3/dwc3-xilinx.c index b5e5be424ce9..96c87dc4757f 100644 --- a/drivers/usb/dwc3/dwc3-xilinx.c +++ b/drivers/usb/dwc3/dwc3-xilinx.c @@ -121,8 +121,11 @@ static int dwc3_xlnx_init_zynqmp(struct dwc3_xlnx *priv_data) * in use but the usb3-phy entry is missing from the device tree. * Therefore, skip these operations in this case. */ - if (!priv_data->usb3_phy) + if (!priv_data->usb3_phy) { + /* Deselect the PIPE Clock Select bit in FPD PIPE Clock register */ + writel(PIPE_CLK_DESELECT, priv_data->regs + XLNX_USB_FPD_PIPE_CLK); goto skip_usb3_phy; + } crst = devm_reset_control_get_exclusive(dev, "usb_crst"); if (IS_ERR(crst)) { diff --git a/drivers/usb/gadget/function/f_midi2.c b/drivers/usb/gadget/function/f_midi2.c index 8285df9ed6fd..8c9d0074db58 100644 --- a/drivers/usb/gadget/function/f_midi2.c +++ b/drivers/usb/gadget/function/f_midi2.c @@ -1593,7 +1593,11 @@ static int f_midi2_create_card(struct f_midi2 *midi2) fb->info.midi_ci_version = b->midi_ci_version; fb->info.ui_hint = reverse_dir(b->ui_hint); fb->info.sysex8_streams = b->sysex8_streams; - fb->info.flags |= b->is_midi1; + if (b->is_midi1 < 2) + fb->info.flags |= b->is_midi1; + else + fb->info.flags |= SNDRV_UMP_BLOCK_IS_MIDI1 | + SNDRV_UMP_BLOCK_IS_LOWSPEED; strscpy(fb->info.name, ump_fb_name(b), sizeof(fb->info.name)); } diff --git a/drivers/usb/gadget/function/u_serial.c b/drivers/usb/gadget/function/u_serial.c index 0a8c05b2746b..53d9fc41acc5 100644 --- a/drivers/usb/gadget/function/u_serial.c +++ b/drivers/usb/gadget/function/u_serial.c @@ -579,9 +579,12 @@ static int gs_start_io(struct gs_port *port) * we didn't in gs_start_tx() */ tty_wakeup(port->port.tty); } else { - gs_free_requests(ep, head, &port->read_allocated); - gs_free_requests(port->port_usb->in, &port->write_pool, - &port->write_allocated); + /* Free reqs only if we are still connected */ + if (port->port_usb) { + gs_free_requests(ep, head, &port->read_allocated); + gs_free_requests(port->port_usb->in, &port->write_pool, + &port->write_allocated); + } status = -EIO; } diff --git a/drivers/usb/host/ehci-sh.c b/drivers/usb/host/ehci-sh.c index d31d9506e41a..7c2b2339e674 100644 --- a/drivers/usb/host/ehci-sh.c +++ b/drivers/usb/host/ehci-sh.c @@ -119,8 +119,12 @@ static int ehci_hcd_sh_probe(struct platform_device *pdev) if (IS_ERR(priv->iclk)) priv->iclk = NULL; - clk_enable(priv->fclk); - clk_enable(priv->iclk); + ret = clk_enable(priv->fclk); + if (ret) + goto fail_request_resource; + ret = clk_enable(priv->iclk); + if (ret) + goto fail_iclk; ret = usb_add_hcd(hcd, irq, IRQF_SHARED); if (ret != 0) { @@ -136,6 +140,7 @@ static int ehci_hcd_sh_probe(struct platform_device *pdev) fail_add_hcd: clk_disable(priv->iclk); +fail_iclk: clk_disable(priv->fclk); fail_request_resource: diff --git a/drivers/usb/host/max3421-hcd.c b/drivers/usb/host/max3421-hcd.c index 9fe4f48b1898..0881fdd1823e 100644 --- a/drivers/usb/host/max3421-hcd.c +++ b/drivers/usb/host/max3421-hcd.c @@ -779,11 +779,17 @@ max3421_check_unlink(struct usb_hcd *hcd) retval = 1; dev_dbg(&spi->dev, "%s: URB %p unlinked=%d", __func__, urb, urb->unlinked); - usb_hcd_unlink_urb_from_ep(hcd, urb); - spin_unlock_irqrestore(&max3421_hcd->lock, - flags); - usb_hcd_giveback_urb(hcd, urb, 0); - spin_lock_irqsave(&max3421_hcd->lock, flags); + if (urb == max3421_hcd->curr_urb) { + max3421_hcd->urb_done = 1; + max3421_hcd->hien &= ~(BIT(MAX3421_HI_HXFRDN_BIT) | + BIT(MAX3421_HI_RCVDAV_BIT)); + } else { + usb_hcd_unlink_urb_from_ep(hcd, urb); + spin_unlock_irqrestore(&max3421_hcd->lock, + flags); + usb_hcd_giveback_urb(hcd, urb, 0); + spin_lock_irqsave(&max3421_hcd->lock, flags); + } } } } diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c index f318864732f2..b267dae14d39 100644 --- a/drivers/usb/host/xhci-ring.c +++ b/drivers/usb/host/xhci-ring.c @@ -1192,8 +1192,6 @@ static void xhci_handle_cmd_stop_ep(struct xhci_hcd *xhci, int slot_id, * Keep retrying until the EP starts and stops again, on * chips where this is known to help. Wait for 100ms. */ - if (!(xhci->quirks & XHCI_NEC_HOST)) - break; if (time_is_before_jiffies(ep->stop_time + msecs_to_jiffies(100))) break; fallthrough; diff --git a/drivers/usb/misc/onboard_usb_dev.c b/drivers/usb/misc/onboard_usb_dev.c index 75dfdca04ff1..27b0a6e18267 100644 --- a/drivers/usb/misc/onboard_usb_dev.c +++ b/drivers/usb/misc/onboard_usb_dev.c @@ -407,8 +407,10 @@ static int onboard_dev_probe(struct platform_device *pdev) } if (of_device_is_compatible(pdev->dev.of_node, "usb424,2744") || - of_device_is_compatible(pdev->dev.of_node, "usb424,5744")) + of_device_is_compatible(pdev->dev.of_node, "usb424,5744")) { err = onboard_dev_5744_i2c_init(client); + onboard_dev->always_powered_in_suspend = true; + } put_device(&client->dev); if (err < 0) diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index 9ba5584061c8..64317b390d22 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -625,6 +625,8 @@ static void option_instat_callback(struct urb *urb); #define MEIGSMART_PRODUCT_SRM825L 0x4d22 /* MeiG Smart SLM320 based on UNISOC UIS8910 */ #define MEIGSMART_PRODUCT_SLM320 0x4d41 +/* MeiG Smart SLM770A based on ASR1803 */ +#define MEIGSMART_PRODUCT_SLM770A 0x4d57 /* Device flags */ @@ -1395,6 +1397,12 @@ static const struct usb_device_id option_ids[] = { .driver_info = RSVD(0) | NCTRL(2) | RSVD(3) | RSVD(4) }, { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x10aa, 0xff), /* Telit FN920C04 (MBIM) */ .driver_info = NCTRL(3) | RSVD(4) | RSVD(5) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x10c0, 0xff), /* Telit FE910C04 (rmnet) */ + .driver_info = RSVD(0) | NCTRL(3) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x10c4, 0xff), /* Telit FE910C04 (rmnet) */ + .driver_info = RSVD(0) | NCTRL(3) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x10c8, 0xff), /* Telit FE910C04 (rmnet) */ + .driver_info = RSVD(0) | NCTRL(2) | RSVD(3) | RSVD(4) }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_ME910), .driver_info = NCTRL(0) | RSVD(1) | RSVD(3) }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_ME910_DUAL_MODEM), @@ -2247,6 +2255,8 @@ static const struct usb_device_id option_ids[] = { .driver_info = NCTRL(2) }, { USB_DEVICE_AND_INTERFACE_INFO(MEDIATEK_VENDOR_ID, 0x7127, 0xff, 0x00, 0x00), .driver_info = NCTRL(2) | NCTRL(3) | NCTRL(4) }, + { USB_DEVICE_AND_INTERFACE_INFO(MEDIATEK_VENDOR_ID, 0x7129, 0xff, 0x00, 0x00), /* MediaTek T7XX */ + .driver_info = NCTRL(2) | NCTRL(3) | NCTRL(4) }, { USB_DEVICE(CELLIENT_VENDOR_ID, CELLIENT_PRODUCT_MEN200) }, { USB_DEVICE(CELLIENT_VENDOR_ID, CELLIENT_PRODUCT_MPL200), .driver_info = RSVD(1) | RSVD(4) }, @@ -2375,6 +2385,18 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_AND_INTERFACE_INFO(0x3731, 0x0116, 0xff, 0xff, 0x30) }, /* NetPrisma LCUK54-WWD for Golbal EDU */ { USB_DEVICE_AND_INTERFACE_INFO(0x3731, 0x0116, 0xff, 0x00, 0x40) }, { USB_DEVICE_AND_INTERFACE_INFO(0x3731, 0x0116, 0xff, 0xff, 0x40) }, + { USB_DEVICE_AND_INTERFACE_INFO(0x3731, 0x010a, 0xff, 0xff, 0x30) }, /* NetPrisma LCUK54-WRD for WWAN Ready */ + { USB_DEVICE_AND_INTERFACE_INFO(0x3731, 0x010a, 0xff, 0x00, 0x40) }, + { USB_DEVICE_AND_INTERFACE_INFO(0x3731, 0x010a, 0xff, 0xff, 0x40) }, + { USB_DEVICE_AND_INTERFACE_INFO(0x3731, 0x010b, 0xff, 0xff, 0x30) }, /* NetPrisma LCUK54-WWD for WWAN Ready */ + { USB_DEVICE_AND_INTERFACE_INFO(0x3731, 0x010b, 0xff, 0x00, 0x40) }, + { USB_DEVICE_AND_INTERFACE_INFO(0x3731, 0x010b, 0xff, 0xff, 0x40) }, + { USB_DEVICE_AND_INTERFACE_INFO(0x3731, 0x010c, 0xff, 0xff, 0x30) }, /* NetPrisma LCUK54-WRD for WWAN Ready */ + { USB_DEVICE_AND_INTERFACE_INFO(0x3731, 0x010c, 0xff, 0x00, 0x40) }, + { USB_DEVICE_AND_INTERFACE_INFO(0x3731, 0x010c, 0xff, 0xff, 0x40) }, + { USB_DEVICE_AND_INTERFACE_INFO(0x3731, 0x010d, 0xff, 0xff, 0x30) }, /* NetPrisma LCUK54-WWD for WWAN Ready */ + { USB_DEVICE_AND_INTERFACE_INFO(0x3731, 0x010d, 0xff, 0x00, 0x40) }, + { USB_DEVICE_AND_INTERFACE_INFO(0x3731, 0x010d, 0xff, 0xff, 0x40) }, { USB_DEVICE_AND_INTERFACE_INFO(OPPO_VENDOR_ID, OPPO_PRODUCT_R11, 0xff, 0xff, 0x30) }, { USB_DEVICE_AND_INTERFACE_INFO(SIERRA_VENDOR_ID, SIERRA_PRODUCT_EM9191, 0xff, 0xff, 0x30) }, { USB_DEVICE_AND_INTERFACE_INFO(SIERRA_VENDOR_ID, SIERRA_PRODUCT_EM9191, 0xff, 0xff, 0x40) }, @@ -2382,9 +2404,14 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_AND_INTERFACE_INFO(UNISOC_VENDOR_ID, TOZED_PRODUCT_LT70C, 0xff, 0, 0) }, { USB_DEVICE_AND_INTERFACE_INFO(UNISOC_VENDOR_ID, LUAT_PRODUCT_AIR720U, 0xff, 0, 0) }, { USB_DEVICE_AND_INTERFACE_INFO(MEIGSMART_VENDOR_ID, MEIGSMART_PRODUCT_SLM320, 0xff, 0, 0) }, + { USB_DEVICE_AND_INTERFACE_INFO(MEIGSMART_VENDOR_ID, MEIGSMART_PRODUCT_SLM770A, 0xff, 0, 0) }, { USB_DEVICE_AND_INTERFACE_INFO(MEIGSMART_VENDOR_ID, MEIGSMART_PRODUCT_SRM825L, 0xff, 0xff, 0x30) }, { USB_DEVICE_AND_INTERFACE_INFO(MEIGSMART_VENDOR_ID, MEIGSMART_PRODUCT_SRM825L, 0xff, 0xff, 0x40) }, { USB_DEVICE_AND_INTERFACE_INFO(MEIGSMART_VENDOR_ID, MEIGSMART_PRODUCT_SRM825L, 0xff, 0xff, 0x60) }, + { USB_DEVICE_INTERFACE_CLASS(0x1bbb, 0x0530, 0xff), /* TCL IK512 MBIM */ + .driver_info = NCTRL(1) }, + { USB_DEVICE_INTERFACE_CLASS(0x1bbb, 0x0640, 0xff), /* TCL IK512 ECM */ + .driver_info = NCTRL(3) }, { } /* Terminating entry */ }; MODULE_DEVICE_TABLE(usb, option_ids); diff --git a/drivers/usb/typec/anx7411.c b/drivers/usb/typec/anx7411.c index d1e7c487ddfb..0ae0a5ee3fae 100644 --- a/drivers/usb/typec/anx7411.c +++ b/drivers/usb/typec/anx7411.c @@ -290,6 +290,8 @@ struct anx7411_data { struct power_supply *psy; struct power_supply_desc psy_desc; struct device *dev; + struct fwnode_handle *switch_node; + struct fwnode_handle *mux_node; }; static u8 snk_identity[] = { @@ -1021,6 +1023,16 @@ static void anx7411_port_unregister_altmodes(struct typec_altmode **adev) } } +static void anx7411_port_unregister(struct typec_params *typecp) +{ + fwnode_handle_put(typecp->caps.fwnode); + anx7411_port_unregister_altmodes(typecp->port_amode); + if (typecp->port) + typec_unregister_port(typecp->port); + if (typecp->role_sw) + usb_role_switch_put(typecp->role_sw); +} + static int anx7411_usb_mux_set(struct typec_mux_dev *mux, struct typec_mux_state *state) { @@ -1089,6 +1101,7 @@ static void anx7411_unregister_mux(struct anx7411_data *ctx) if (ctx->typec.typec_mux) { typec_mux_unregister(ctx->typec.typec_mux); ctx->typec.typec_mux = NULL; + fwnode_handle_put(ctx->mux_node); } } @@ -1097,6 +1110,7 @@ static void anx7411_unregister_switch(struct anx7411_data *ctx) if (ctx->typec.typec_switch) { typec_switch_unregister(ctx->typec.typec_switch); ctx->typec.typec_switch = NULL; + fwnode_handle_put(ctx->switch_node); } } @@ -1104,28 +1118,29 @@ static int anx7411_typec_switch_probe(struct anx7411_data *ctx, struct device *dev) { int ret; - struct device_node *node; - node = of_get_child_by_name(dev->of_node, "orientation_switch"); - if (!node) + ctx->switch_node = device_get_named_child_node(dev, "orientation_switch"); + if (!ctx->switch_node) return 0; - ret = anx7411_register_switch(ctx, dev, &node->fwnode); + ret = anx7411_register_switch(ctx, dev, ctx->switch_node); if (ret) { dev_err(dev, "failed register switch"); + fwnode_handle_put(ctx->switch_node); return ret; } - node = of_get_child_by_name(dev->of_node, "mode_switch"); - if (!node) { + ctx->mux_node = device_get_named_child_node(dev, "mode_switch"); + if (!ctx->mux_node) { dev_err(dev, "no typec mux exist"); ret = -ENODEV; goto unregister_switch; } - ret = anx7411_register_mux(ctx, dev, &node->fwnode); + ret = anx7411_register_mux(ctx, dev, ctx->mux_node); if (ret) { dev_err(dev, "failed register mode switch"); + fwnode_handle_put(ctx->mux_node); ret = -ENODEV; goto unregister_switch; } @@ -1154,34 +1169,34 @@ static int anx7411_typec_port_probe(struct anx7411_data *ctx, ret = fwnode_property_read_string(fwnode, "power-role", &buf); if (ret) { dev_err(dev, "power-role not found: %d\n", ret); - return ret; + goto put_fwnode; } ret = typec_find_port_power_role(buf); if (ret < 0) - return ret; + goto put_fwnode; cap->type = ret; ret = fwnode_property_read_string(fwnode, "data-role", &buf); if (ret) { dev_err(dev, "data-role not found: %d\n", ret); - return ret; + goto put_fwnode; } ret = typec_find_port_data_role(buf); if (ret < 0) - return ret; + goto put_fwnode; cap->data = ret; ret = fwnode_property_read_string(fwnode, "try-power-role", &buf); if (ret) { dev_err(dev, "try-power-role not found: %d\n", ret); - return ret; + goto put_fwnode; } ret = typec_find_power_role(buf); if (ret < 0) - return ret; + goto put_fwnode; cap->prefer_role = ret; /* Get source pdos */ @@ -1193,7 +1208,7 @@ static int anx7411_typec_port_probe(struct anx7411_data *ctx, typecp->src_pdo_nr); if (ret < 0) { dev_err(dev, "source cap validate failed: %d\n", ret); - return -EINVAL; + goto put_fwnode; } typecp->caps_flags |= HAS_SOURCE_CAP; @@ -1207,7 +1222,7 @@ static int anx7411_typec_port_probe(struct anx7411_data *ctx, typecp->sink_pdo_nr); if (ret < 0) { dev_err(dev, "sink cap validate failed: %d\n", ret); - return -EINVAL; + goto put_fwnode; } for (i = 0; i < typecp->sink_pdo_nr; i++) { @@ -1251,13 +1266,21 @@ static int anx7411_typec_port_probe(struct anx7411_data *ctx, ret = PTR_ERR(ctx->typec.port); ctx->typec.port = NULL; dev_err(dev, "Failed to register type c port %d\n", ret); - return ret; + goto put_usb_role_switch; } typec_port_register_altmodes(ctx->typec.port, NULL, ctx, ctx->typec.port_amode, MAX_ALTMODE); return 0; + +put_usb_role_switch: + if (ctx->typec.role_sw) + usb_role_switch_put(ctx->typec.role_sw); +put_fwnode: + fwnode_handle_put(fwnode); + + return ret; } static int anx7411_typec_check_connection(struct anx7411_data *ctx) @@ -1523,8 +1546,7 @@ free_wq: destroy_workqueue(plat->workqueue); free_typec_port: - typec_unregister_port(plat->typec.port); - anx7411_port_unregister_altmodes(plat->typec.port_amode); + anx7411_port_unregister(&plat->typec); free_typec_switch: anx7411_unregister_switch(plat); @@ -1548,17 +1570,11 @@ static void anx7411_i2c_remove(struct i2c_client *client) i2c_unregister_device(plat->spi_client); - if (plat->typec.role_sw) - usb_role_switch_put(plat->typec.role_sw); - anx7411_unregister_mux(plat); anx7411_unregister_switch(plat); - if (plat->typec.port) - typec_unregister_port(plat->typec.port); - - anx7411_port_unregister_altmodes(plat->typec.port_amode); + anx7411_port_unregister(&plat->typec); } static const struct i2c_device_id anx7411_id[] = { diff --git a/drivers/usb/typec/ucsi/ucsi.c b/drivers/usb/typec/ucsi/ucsi.c index e0f3925e401b..7a3f0f5af38f 100644 --- a/drivers/usb/typec/ucsi/ucsi.c +++ b/drivers/usb/typec/ucsi/ucsi.c @@ -46,11 +46,11 @@ void ucsi_notify_common(struct ucsi *ucsi, u32 cci) ucsi_connector_change(ucsi, UCSI_CCI_CONNECTOR(cci)); if (cci & UCSI_CCI_ACK_COMPLETE && - test_bit(ACK_PENDING, &ucsi->flags)) + test_and_clear_bit(ACK_PENDING, &ucsi->flags)) complete(&ucsi->complete); if (cci & UCSI_CCI_COMMAND_COMPLETE && - test_bit(COMMAND_PENDING, &ucsi->flags)) + test_and_clear_bit(COMMAND_PENDING, &ucsi->flags)) complete(&ucsi->complete); } EXPORT_SYMBOL_GPL(ucsi_notify_common); @@ -65,6 +65,8 @@ int ucsi_sync_control_common(struct ucsi *ucsi, u64 command) else set_bit(COMMAND_PENDING, &ucsi->flags); + reinit_completion(&ucsi->complete); + ret = ucsi->ops->async_control(ucsi, command); if (ret) goto out_clear_bit; diff --git a/drivers/virt/coco/tdx-guest/tdx-guest.c b/drivers/virt/coco/tdx-guest/tdx-guest.c index d7db6c824e13..224e7dde9cde 100644 --- a/drivers/virt/coco/tdx-guest/tdx-guest.c +++ b/drivers/virt/coco/tdx-guest/tdx-guest.c @@ -124,10 +124,8 @@ static void *alloc_quote_buf(void) if (!addr) return NULL; - if (set_memory_decrypted((unsigned long)addr, count)) { - free_pages_exact(addr, len); + if (set_memory_decrypted((unsigned long)addr, count)) return NULL; - } return addr; } diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c index 98374ed7c577..0112742e4504 100644 --- a/drivers/virtio/virtio_ring.c +++ b/drivers/virtio/virtio_ring.c @@ -2716,6 +2716,7 @@ EXPORT_SYMBOL_GPL(vring_create_virtqueue_dma); * @_vq: the struct virtqueue we're talking about. * @num: new ring num * @recycle: callback to recycle unused buffers + * @recycle_done: callback to be invoked when recycle for all unused buffers done * * When it is really necessary to create a new vring, it will set the current vq * into the reset state. Then call the passed callback to recycle the buffer @@ -2736,7 +2737,8 @@ EXPORT_SYMBOL_GPL(vring_create_virtqueue_dma); * */ int virtqueue_resize(struct virtqueue *_vq, u32 num, - void (*recycle)(struct virtqueue *vq, void *buf)) + void (*recycle)(struct virtqueue *vq, void *buf), + void (*recycle_done)(struct virtqueue *vq)) { struct vring_virtqueue *vq = to_vvq(_vq); int err; @@ -2753,6 +2755,8 @@ int virtqueue_resize(struct virtqueue *_vq, u32 num, err = virtqueue_disable_and_recycle(_vq, recycle); if (err) return err; + if (recycle_done) + recycle_done(_vq); if (vq->packed_ring) err = virtqueue_resize_packed(_vq, num); diff --git a/drivers/watchdog/Kconfig b/drivers/watchdog/Kconfig index 94c96bcfefe3..0b59c669c26d 100644 --- a/drivers/watchdog/Kconfig +++ b/drivers/watchdog/Kconfig @@ -549,6 +549,7 @@ config S3C2410_WATCHDOG tristate "S3C6410/S5Pv210/Exynos Watchdog" depends on ARCH_S3C64XX || ARCH_S5PV210 || ARCH_EXYNOS || COMPILE_TEST select WATCHDOG_CORE + select MFD_SYSCON if ARCH_EXYNOS help Watchdog timer block in the Samsung S3C64xx, S5Pv210 and Exynos SoCs. This will reboot the system when the timer expires with diff --git a/drivers/watchdog/it87_wdt.c b/drivers/watchdog/it87_wdt.c index 3e8c15138edd..1a5a0a2c3f2e 100644 --- a/drivers/watchdog/it87_wdt.c +++ b/drivers/watchdog/it87_wdt.c @@ -20,6 +20,8 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include <linux/bits.h> +#include <linux/dmi.h> #include <linux/init.h> #include <linux/io.h> #include <linux/kernel.h> @@ -40,6 +42,7 @@ #define VAL 0x2f /* Logical device Numbers LDN */ +#define EC 0x04 #define GPIO 0x07 /* Configuration Registers and Functions */ @@ -73,6 +76,12 @@ #define IT8784_ID 0x8784 #define IT8786_ID 0x8786 +/* Environment Controller Configuration Registers LDN=0x04 */ +#define SCR1 0xfa + +/* Environment Controller Bits SCR1 */ +#define WDT_PWRGD 0x20 + /* GPIO Configuration Registers LDN=0x07 */ #define WDTCTRL 0x71 #define WDTCFG 0x72 @@ -240,6 +249,21 @@ static int wdt_set_timeout(struct watchdog_device *wdd, unsigned int t) return ret; } +enum { + IT87_WDT_OUTPUT_THROUGH_PWRGD = BIT(0), +}; + +static const struct dmi_system_id it87_quirks[] = { + { + /* Qotom Q30900P (IT8786) */ + .matches = { + DMI_EXACT_MATCH(DMI_BOARD_NAME, "QCML04"), + }, + .driver_data = (void *)IT87_WDT_OUTPUT_THROUGH_PWRGD, + }, + {} +}; + static const struct watchdog_info ident = { .options = WDIOF_SETTIMEOUT | WDIOF_MAGICCLOSE | WDIOF_KEEPALIVEPING, .firmware_version = 1, @@ -261,8 +285,10 @@ static struct watchdog_device wdt_dev = { static int __init it87_wdt_init(void) { + const struct dmi_system_id *dmi_id; u8 chip_rev; u8 ctrl; + int quirks = 0; int rc; rc = superio_enter(); @@ -273,6 +299,10 @@ static int __init it87_wdt_init(void) chip_rev = superio_inb(CHIPREV) & 0x0f; superio_exit(); + dmi_id = dmi_first_match(it87_quirks); + if (dmi_id) + quirks = (long)dmi_id->driver_data; + switch (chip_type) { case IT8702_ID: max_units = 255; @@ -333,6 +363,15 @@ static int __init it87_wdt_init(void) superio_outb(0x00, WDTCTRL); } + if (quirks & IT87_WDT_OUTPUT_THROUGH_PWRGD) { + superio_select(EC); + ctrl = superio_inb(SCR1); + if (!(ctrl & WDT_PWRGD)) { + ctrl |= WDT_PWRGD; + superio_outb(ctrl, SCR1); + } + } + superio_exit(); if (timeout < 1 || timeout > max_units * 60) { diff --git a/drivers/watchdog/mtk_wdt.c b/drivers/watchdog/mtk_wdt.c index e2d7a57d6ea2..91d110646e16 100644 --- a/drivers/watchdog/mtk_wdt.c +++ b/drivers/watchdog/mtk_wdt.c @@ -10,6 +10,7 @@ */ #include <dt-bindings/reset/mt2712-resets.h> +#include <dt-bindings/reset/mediatek,mt6735-wdt.h> #include <dt-bindings/reset/mediatek,mt6795-resets.h> #include <dt-bindings/reset/mt7986-resets.h> #include <dt-bindings/reset/mt8183-resets.h> @@ -87,6 +88,10 @@ static const struct mtk_wdt_data mt2712_data = { .toprgu_sw_rst_num = MT2712_TOPRGU_SW_RST_NUM, }; +static const struct mtk_wdt_data mt6735_data = { + .toprgu_sw_rst_num = MT6735_TOPRGU_RST_NUM, +}; + static const struct mtk_wdt_data mt6795_data = { .toprgu_sw_rst_num = MT6795_TOPRGU_SW_RST_NUM, }; @@ -489,6 +494,7 @@ static int mtk_wdt_resume(struct device *dev) static const struct of_device_id mtk_wdt_dt_ids[] = { { .compatible = "mediatek,mt2712-wdt", .data = &mt2712_data }, { .compatible = "mediatek,mt6589-wdt" }, + { .compatible = "mediatek,mt6735-wdt", .data = &mt6735_data }, { .compatible = "mediatek,mt6795-wdt", .data = &mt6795_data }, { .compatible = "mediatek,mt7986-wdt", .data = &mt7986_data }, { .compatible = "mediatek,mt7988-wdt", .data = &mt7988_data }, diff --git a/drivers/watchdog/rzg2l_wdt.c b/drivers/watchdog/rzg2l_wdt.c index 2a35f890a288..11bbe48160ec 100644 --- a/drivers/watchdog/rzg2l_wdt.c +++ b/drivers/watchdog/rzg2l_wdt.c @@ -12,6 +12,7 @@ #include <linux/module.h> #include <linux/of.h> #include <linux/platform_device.h> +#include <linux/pm_domain.h> #include <linux/pm_runtime.h> #include <linux/reset.h> #include <linux/units.h> @@ -166,8 +167,22 @@ static int rzg2l_wdt_restart(struct watchdog_device *wdev, struct rzg2l_wdt_priv *priv = watchdog_get_drvdata(wdev); int ret; - clk_prepare_enable(priv->pclk); - clk_prepare_enable(priv->osc_clk); + /* + * In case of RZ/G3S the watchdog device may be part of an IRQ safe power + * domain that is currently powered off. In this case we need to power + * it on before accessing registers. Along with this the clocks will be + * enabled. We don't undo the pm_runtime_resume_and_get() as the device + * need to be on for the reboot to happen. + * + * For the rest of SoCs not registering a watchdog IRQ safe power + * domain it is safe to call pm_runtime_resume_and_get() as the + * irq_safe_dev_in_sleep_domain() call in genpd_runtime_resume() + * returns non zero value and the genpd_lock() is avoided, thus, there + * will be no invalid wait context reported by lockdep. + */ + ret = pm_runtime_resume_and_get(wdev->parent); + if (ret) + return ret; if (priv->devtype == WDT_RZG2L) { ret = reset_control_deassert(priv->rstc); @@ -275,6 +290,7 @@ static int rzg2l_wdt_probe(struct platform_device *pdev) priv->devtype = (uintptr_t)of_device_get_match_data(dev); + pm_runtime_irq_safe(&pdev->dev); pm_runtime_enable(&pdev->dev); priv->wdev.info = &rzg2l_wdt_ident; diff --git a/drivers/watchdog/s3c2410_wdt.c b/drivers/watchdog/s3c2410_wdt.c index 686cf544d0ae..349d30462c8c 100644 --- a/drivers/watchdog/s3c2410_wdt.c +++ b/drivers/watchdog/s3c2410_wdt.c @@ -24,9 +24,9 @@ #include <linux/slab.h> #include <linux/err.h> #include <linux/of.h> +#include <linux/mfd/syscon.h> #include <linux/regmap.h> #include <linux/delay.h> -#include <linux/soc/samsung/exynos-pmu.h> #define S3C2410_WTCON 0x00 #define S3C2410_WTDAT 0x04 @@ -699,11 +699,11 @@ static int s3c2410wdt_probe(struct platform_device *pdev) return ret; if (wdt->drv_data->quirks & QUIRKS_HAVE_PMUREG) { - wdt->pmureg = exynos_get_pmu_regmap_by_phandle(dev->of_node, - "samsung,syscon-phandle"); + wdt->pmureg = syscon_regmap_lookup_by_phandle(dev->of_node, + "samsung,syscon-phandle"); if (IS_ERR(wdt->pmureg)) return dev_err_probe(dev, PTR_ERR(wdt->pmureg), - "PMU regmap lookup failed.\n"); + "syscon regmap lookup failed.\n"); } wdt_irq = platform_get_irq(pdev, 0); diff --git a/fs/btrfs/bio.c b/fs/btrfs/bio.c index 7e0f9600b80c..5fd0b39d8c70 100644 --- a/fs/btrfs/bio.c +++ b/fs/btrfs/bio.c @@ -81,6 +81,9 @@ static struct btrfs_bio *btrfs_split_bio(struct btrfs_fs_info *fs_info, bio = bio_split(&orig_bbio->bio, map_length >> SECTOR_SHIFT, GFP_NOFS, &btrfs_clone_bioset); + if (IS_ERR(bio)) + return ERR_CAST(bio); + bbio = btrfs_bio(bio); btrfs_bio_init(bbio, fs_info, NULL, orig_bbio); bbio->inode = orig_bbio->inode; @@ -355,7 +358,7 @@ static void btrfs_simple_end_io(struct bio *bio) INIT_WORK(&bbio->end_io_work, btrfs_end_bio_work); queue_work(btrfs_end_io_wq(fs_info, bio), &bbio->end_io_work); } else { - if (bio_op(bio) == REQ_OP_ZONE_APPEND && !bio->bi_status) + if (bio_is_zone_append(bio) && !bio->bi_status) btrfs_record_physical_zoned(bbio); btrfs_bio_end_io(bbio, bbio->bio.bi_status); } @@ -398,7 +401,7 @@ static void btrfs_orig_write_end_io(struct bio *bio) else bio->bi_status = BLK_STS_OK; - if (bio_op(bio) == REQ_OP_ZONE_APPEND && !bio->bi_status) + if (bio_is_zone_append(bio) && !bio->bi_status) stripe->physical = bio->bi_iter.bi_sector << SECTOR_SHIFT; btrfs_bio_end_io(bbio, bbio->bio.bi_status); @@ -412,7 +415,7 @@ static void btrfs_clone_write_end_io(struct bio *bio) if (bio->bi_status) { atomic_inc(&stripe->bioc->error); btrfs_log_dev_io_error(bio, stripe->dev); - } else if (bio_op(bio) == REQ_OP_ZONE_APPEND) { + } else if (bio_is_zone_append(bio)) { stripe->physical = bio->bi_iter.bi_sector << SECTOR_SHIFT; } @@ -649,8 +652,14 @@ static u64 btrfs_append_map_length(struct btrfs_bio *bbio, u64 map_length) map_length = min(map_length, bbio->fs_info->max_zone_append_size); sector_offset = bio_split_rw_at(&bbio->bio, &bbio->fs_info->limits, &nr_segs, map_length); - if (sector_offset) - return sector_offset << SECTOR_SHIFT; + if (sector_offset) { + /* + * bio_split_rw_at() could split at a size smaller than our + * sectorsize and thus cause unaligned I/Os. Fix that by + * always rounding down to the nearest boundary. + */ + return ALIGN_DOWN(sector_offset << SECTOR_SHIFT, bbio->fs_info->sectorsize); + } return map_length; } @@ -678,7 +687,8 @@ static bool btrfs_submit_chunk(struct btrfs_bio *bbio, int mirror_num) &bioc, &smap, &mirror_num); if (error) { ret = errno_to_blk_status(error); - goto fail; + btrfs_bio_counter_dec(fs_info); + goto end_bbio; } map_length = min(map_length, length); @@ -686,7 +696,15 @@ static bool btrfs_submit_chunk(struct btrfs_bio *bbio, int mirror_num) map_length = btrfs_append_map_length(bbio, map_length); if (map_length < length) { - bbio = btrfs_split_bio(fs_info, bbio, map_length); + struct btrfs_bio *split; + + split = btrfs_split_bio(fs_info, bbio, map_length); + if (IS_ERR(split)) { + ret = errno_to_blk_status(PTR_ERR(split)); + btrfs_bio_counter_dec(fs_info); + goto end_bbio; + } + bbio = split; bio = &bbio->bio; } @@ -760,6 +778,7 @@ fail: btrfs_bio_end_io(remaining, ret); } +end_bbio: btrfs_bio_end_io(bbio, ret); /* Do not submit another chunk */ return true; diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index 9c05cab473f5..29c164597401 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -654,6 +654,8 @@ int btrfs_force_cow_block(struct btrfs_trans_handle *trans, goto error_unlock_cow; } } + + trace_btrfs_cow_block(root, buf, cow); if (unlock_orig) btrfs_tree_unlock(buf); free_extent_buffer_stale(buf); @@ -710,7 +712,6 @@ int btrfs_cow_block(struct btrfs_trans_handle *trans, { struct btrfs_fs_info *fs_info = root->fs_info; u64 search_start; - int ret; if (unlikely(test_bit(BTRFS_ROOT_DELETING, &root->state))) { btrfs_abort_transaction(trans, -EUCLEAN); @@ -751,12 +752,8 @@ int btrfs_cow_block(struct btrfs_trans_handle *trans, * Also We don't care about the error, as it's handled internally. */ btrfs_qgroup_trace_subtree_after_cow(trans, root, buf); - ret = btrfs_force_cow_block(trans, root, buf, parent, parent_slot, - cow_ret, search_start, 0, nest); - - trace_btrfs_cow_block(root, buf, *cow_ret); - - return ret; + return btrfs_force_cow_block(trans, root, buf, parent, parent_slot, + cow_ret, search_start, 0, nest); } ALLOW_ERROR_INJECTION(btrfs_cow_block, ERRNO); diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 317a3712270f..2034d3710833 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -371,6 +371,25 @@ static inline void btrfs_set_root_last_trans(struct btrfs_root *root, u64 transi } /* + * Return the generation this root started with. + * + * Every normal root that is created with root->root_key.offset set to it's + * originating generation. If it is a snapshot it is the generation when the + * snapshot was created. + * + * However for TREE_RELOC roots root_key.offset is the objectid of the owning + * tree root. Thankfully we copy the root item of the owning tree root, which + * has it's last_snapshot set to what we would have root_key.offset set to, so + * return that if this is a TREE_RELOC root. + */ +static inline u64 btrfs_root_origin_generation(const struct btrfs_root *root) +{ + if (btrfs_root_id(root) == BTRFS_TREE_RELOC_OBJECTID) + return btrfs_root_last_snapshot(&root->root_item); + return root->root_key.offset; +} + +/* * Structure that conveys information about an extent that is going to replace * all the extents in a file range. */ diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 43b7b331b2da..563f106774e5 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -4264,6 +4264,15 @@ void __cold close_ctree(struct btrfs_fs_info *fs_info) * already the cleaner, but below we run all pending delayed iputs. */ btrfs_flush_workqueue(fs_info->fixup_workers); + /* + * Similar case here, we have to wait for delalloc workers before we + * proceed below and stop the cleaner kthread, otherwise we trigger a + * use-after-tree on the cleaner kthread task_struct when a delalloc + * worker running submit_compressed_extents() adds a delayed iput, which + * does a wake up on the cleaner kthread, which was already freed below + * when we call kthread_stop(). + */ + btrfs_flush_workqueue(fs_info->delalloc_workers); /* * After we parked the cleaner kthread, ordered extents may have diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index b43a8611aca5..f3e93ba7ec97 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -5308,7 +5308,7 @@ static bool visit_node_for_delete(struct btrfs_root *root, struct walk_control * * reference to it. */ generation = btrfs_node_ptr_generation(eb, slot); - if (!wc->update_ref || generation <= root->root_key.offset) + if (!wc->update_ref || generation <= btrfs_root_origin_generation(root)) return false; /* @@ -5363,7 +5363,7 @@ static noinline void reada_walk_down(struct btrfs_trans_handle *trans, goto reada; if (wc->stage == UPDATE_BACKREF && - generation <= root->root_key.offset) + generation <= btrfs_root_origin_generation(root)) continue; /* We don't lock the tree block, it's OK to be racy here */ @@ -5706,7 +5706,7 @@ static noinline int do_walk_down(struct btrfs_trans_handle *trans, * for the subtree */ if (wc->stage == UPDATE_BACKREF && - generation <= root->root_key.offset) { + generation <= btrfs_root_origin_generation(root)) { wc->lookup_info = 1; return 1; } diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 58ffe78132d9..b5cfb85af937 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -7117,6 +7117,8 @@ noinline int can_nocow_extent(struct inode *inode, u64 offset, u64 *len, ret = -EAGAIN; goto out; } + + cond_resched(); } if (file_extent) @@ -9780,15 +9782,25 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, struct btrfs_fs_info *fs_info = root->fs_info; struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree; struct extent_state *cached_state = NULL; - struct extent_map *em = NULL; struct btrfs_chunk_map *map = NULL; struct btrfs_device *device = NULL; struct btrfs_swap_info bsi = { .lowest_ppage = (sector_t)-1ULL, }; + struct btrfs_backref_share_check_ctx *backref_ctx = NULL; + struct btrfs_path *path = NULL; int ret = 0; u64 isize; - u64 start; + u64 prev_extent_end = 0; + + /* + * Acquire the inode's mmap lock to prevent races with memory mapped + * writes, as they could happen after we flush delalloc below and before + * we lock the extent range further below. The inode was already locked + * up in the call chain. + */ + btrfs_assert_inode_locked(BTRFS_I(inode)); + down_write(&BTRFS_I(inode)->i_mmap_lock); /* * If the swap file was just created, make sure delalloc is done. If the @@ -9797,22 +9809,32 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, */ ret = btrfs_wait_ordered_range(BTRFS_I(inode), 0, (u64)-1); if (ret) - return ret; + goto out_unlock_mmap; /* * The inode is locked, so these flags won't change after we check them. */ if (BTRFS_I(inode)->flags & BTRFS_INODE_COMPRESS) { btrfs_warn(fs_info, "swapfile must not be compressed"); - return -EINVAL; + ret = -EINVAL; + goto out_unlock_mmap; } if (!(BTRFS_I(inode)->flags & BTRFS_INODE_NODATACOW)) { btrfs_warn(fs_info, "swapfile must not be copy-on-write"); - return -EINVAL; + ret = -EINVAL; + goto out_unlock_mmap; } if (!(BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM)) { btrfs_warn(fs_info, "swapfile must not be checksummed"); - return -EINVAL; + ret = -EINVAL; + goto out_unlock_mmap; + } + + path = btrfs_alloc_path(); + backref_ctx = btrfs_alloc_backref_share_check_ctx(); + if (!path || !backref_ctx) { + ret = -ENOMEM; + goto out_unlock_mmap; } /* @@ -9827,7 +9849,8 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, if (!btrfs_exclop_start(fs_info, BTRFS_EXCLOP_SWAP_ACTIVATE)) { btrfs_warn(fs_info, "cannot activate swapfile while exclusive operation is running"); - return -EBUSY; + ret = -EBUSY; + goto out_unlock_mmap; } /* @@ -9841,7 +9864,8 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, btrfs_exclop_finish(fs_info); btrfs_warn(fs_info, "cannot activate swapfile because snapshot creation is in progress"); - return -EINVAL; + ret = -EINVAL; + goto out_unlock_mmap; } /* * Snapshots can create extents which require COW even if NODATACOW is @@ -9862,7 +9886,8 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, btrfs_warn(fs_info, "cannot activate swapfile because subvolume %llu is being deleted", btrfs_root_id(root)); - return -EPERM; + ret = -EPERM; + goto out_unlock_mmap; } atomic_inc(&root->nr_swapfiles); spin_unlock(&root->root_item_lock); @@ -9870,24 +9895,39 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, isize = ALIGN_DOWN(inode->i_size, fs_info->sectorsize); lock_extent(io_tree, 0, isize - 1, &cached_state); - start = 0; - while (start < isize) { - u64 logical_block_start, physical_block_start; + while (prev_extent_end < isize) { + struct btrfs_key key; + struct extent_buffer *leaf; + struct btrfs_file_extent_item *ei; struct btrfs_block_group *bg; - u64 len = isize - start; + u64 logical_block_start; + u64 physical_block_start; + u64 extent_gen; + u64 disk_bytenr; + u64 len; - em = btrfs_get_extent(BTRFS_I(inode), NULL, start, len); - if (IS_ERR(em)) { - ret = PTR_ERR(em); + key.objectid = btrfs_ino(BTRFS_I(inode)); + key.type = BTRFS_EXTENT_DATA_KEY; + key.offset = prev_extent_end; + + ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); + if (ret < 0) goto out; - } - if (em->disk_bytenr == EXTENT_MAP_HOLE) { + /* + * If key not found it means we have an implicit hole (NO_HOLES + * is enabled). + */ + if (ret > 0) { btrfs_warn(fs_info, "swapfile must not have holes"); ret = -EINVAL; goto out; } - if (em->disk_bytenr == EXTENT_MAP_INLINE) { + + leaf = path->nodes[0]; + ei = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_file_extent_item); + + if (btrfs_file_extent_type(leaf, ei) == BTRFS_FILE_EXTENT_INLINE) { /* * It's unlikely we'll ever actually find ourselves * here, as a file small enough to fit inline won't be @@ -9899,23 +9939,45 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, ret = -EINVAL; goto out; } - if (extent_map_is_compressed(em)) { + + if (btrfs_file_extent_compression(leaf, ei) != BTRFS_COMPRESS_NONE) { btrfs_warn(fs_info, "swapfile must not be compressed"); ret = -EINVAL; goto out; } - logical_block_start = extent_map_block_start(em) + (start - em->start); - len = min(len, em->len - (start - em->start)); - free_extent_map(em); - em = NULL; + disk_bytenr = btrfs_file_extent_disk_bytenr(leaf, ei); + if (disk_bytenr == 0) { + btrfs_warn(fs_info, "swapfile must not have holes"); + ret = -EINVAL; + goto out; + } - ret = can_nocow_extent(inode, start, &len, NULL, false, true); + logical_block_start = disk_bytenr + btrfs_file_extent_offset(leaf, ei); + extent_gen = btrfs_file_extent_generation(leaf, ei); + prev_extent_end = btrfs_file_extent_end(path); + + if (prev_extent_end > isize) + len = isize - key.offset; + else + len = btrfs_file_extent_num_bytes(leaf, ei); + + backref_ctx->curr_leaf_bytenr = leaf->start; + + /* + * Don't need the path anymore, release to avoid deadlocks when + * calling btrfs_is_data_extent_shared() because when joining a + * transaction it can block waiting for the current one's commit + * which in turn may be trying to lock the same leaf to flush + * delayed items for example. + */ + btrfs_release_path(path); + + ret = btrfs_is_data_extent_shared(BTRFS_I(inode), disk_bytenr, + extent_gen, backref_ctx); if (ret < 0) { goto out; - } else if (ret) { - ret = 0; - } else { + } else if (ret > 0) { btrfs_warn(fs_info, "swapfile must not be copy-on-write"); ret = -EINVAL; @@ -9950,7 +10012,6 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, physical_block_start = (map->stripes[0].physical + (logical_block_start - map->start)); - len = min(len, map->chunk_len - (logical_block_start - map->start)); btrfs_free_chunk_map(map); map = NULL; @@ -9991,20 +10052,21 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, if (ret) goto out; } - bsi.start = start; + bsi.start = key.offset; bsi.block_start = physical_block_start; bsi.block_len = len; } - start += len; + if (fatal_signal_pending(current)) { + ret = -EINTR; + goto out; + } } if (bsi.block_len) ret = btrfs_add_swap_extent(sis, &bsi); out: - if (!IS_ERR_OR_NULL(em)) - free_extent_map(em); if (!IS_ERR_OR_NULL(map)) btrfs_free_chunk_map(map); @@ -10017,6 +10079,10 @@ out: btrfs_exclop_finish(fs_info); +out_unlock_mmap: + up_write(&BTRFS_I(inode)->i_mmap_lock); + btrfs_free_backref_share_ctx(backref_ctx); + btrfs_free_path(path); if (ret) return ret; diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index a0e8deca87a7..e70ed857fc74 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -1122,6 +1122,7 @@ int btrfs_quota_enable(struct btrfs_fs_info *fs_info, fs_info->qgroup_flags = BTRFS_QGROUP_STATUS_FLAG_ON; if (simple) { fs_info->qgroup_flags |= BTRFS_QGROUP_STATUS_FLAG_SIMPLE_MODE; + btrfs_set_fs_incompat(fs_info, SIMPLE_QUOTA); btrfs_set_qgroup_status_enable_gen(leaf, ptr, trans->transid); } else { fs_info->qgroup_flags |= BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT; @@ -1255,8 +1256,6 @@ out_add_root: spin_lock(&fs_info->qgroup_lock); fs_info->quota_root = quota_root; set_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags); - if (simple) - btrfs_set_fs_incompat(fs_info, SIMPLE_QUOTA); spin_unlock(&fs_info->qgroup_lock); /* Skip rescan for simple qgroups. */ diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index f3834f8d26b4..adcbdc970f9e 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -2902,6 +2902,7 @@ static int relocate_one_folio(struct reloc_control *rc, const bool use_rst = btrfs_need_stripe_tree_update(fs_info, rc->block_group->flags); ASSERT(index <= last_index); +again: folio = filemap_lock_folio(inode->i_mapping, index); if (IS_ERR(folio)) { @@ -2937,6 +2938,11 @@ static int relocate_one_folio(struct reloc_control *rc, ret = -EIO; goto release_folio; } + if (folio->mapping != inode->i_mapping) { + folio_unlock(folio); + folio_put(folio); + goto again; + } } /* diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index 0cb11dcd10cd..b1015f383f75 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -5291,6 +5291,7 @@ static int put_file_data(struct send_ctx *sctx, u64 offset, u32 len) unsigned cur_len = min_t(unsigned, len, PAGE_SIZE - pg_offset); +again: folio = filemap_lock_folio(mapping, index); if (IS_ERR(folio)) { page_cache_sync_readahead(mapping, @@ -5323,6 +5324,11 @@ static int put_file_data(struct send_ctx *sctx, u64 offset, u32 len) ret = -EIO; break; } + if (folio->mapping != mapping) { + folio_unlock(folio); + folio_put(folio); + goto again; + } } memcpy_from_folio(sctx->send_buf + sctx->send_size, folio, diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c index 03926ad467c9..5912d5057766 100644 --- a/fs/btrfs/sysfs.c +++ b/fs/btrfs/sysfs.c @@ -1118,7 +1118,7 @@ static ssize_t btrfs_nodesize_show(struct kobject *kobj, { struct btrfs_fs_info *fs_info = to_fs_info(kobj); - return sysfs_emit(buf, "%u\n", fs_info->super_copy->nodesize); + return sysfs_emit(buf, "%u\n", fs_info->nodesize); } BTRFS_ATTR(, nodesize, btrfs_nodesize_show); @@ -1128,7 +1128,7 @@ static ssize_t btrfs_sectorsize_show(struct kobject *kobj, { struct btrfs_fs_info *fs_info = to_fs_info(kobj); - return sysfs_emit(buf, "%u\n", fs_info->super_copy->sectorsize); + return sysfs_emit(buf, "%u\n", fs_info->sectorsize); } BTRFS_ATTR(, sectorsize, btrfs_sectorsize_show); @@ -1180,7 +1180,7 @@ static ssize_t btrfs_clone_alignment_show(struct kobject *kobj, { struct btrfs_fs_info *fs_info = to_fs_info(kobj); - return sysfs_emit(buf, "%u\n", fs_info->super_copy->sectorsize); + return sysfs_emit(buf, "%u\n", fs_info->sectorsize); } BTRFS_ATTR(, clone_alignment, btrfs_clone_alignment_show); diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c index 7b50263723bc..ffa5b83d3a4a 100644 --- a/fs/btrfs/tree-checker.c +++ b/fs/btrfs/tree-checker.c @@ -1527,6 +1527,11 @@ static int check_extent_item(struct extent_buffer *leaf, dref_offset, fs_info->sectorsize); return -EUCLEAN; } + if (unlikely(btrfs_extent_data_ref_count(leaf, dref) == 0)) { + extent_err(leaf, slot, + "invalid data ref count, should have non-zero value"); + return -EUCLEAN; + } inline_refs += btrfs_extent_data_ref_count(leaf, dref); break; /* Contains parent bytenr and ref count */ @@ -1539,6 +1544,11 @@ static int check_extent_item(struct extent_buffer *leaf, inline_offset, fs_info->sectorsize); return -EUCLEAN; } + if (unlikely(btrfs_shared_data_ref_count(leaf, sref) == 0)) { + extent_err(leaf, slot, + "invalid shared data ref count, should have non-zero value"); + return -EUCLEAN; + } inline_refs += btrfs_shared_data_ref_count(leaf, sref); break; case BTRFS_EXTENT_OWNER_REF_KEY: @@ -1611,8 +1621,18 @@ static int check_simple_keyed_refs(struct extent_buffer *leaf, { u32 expect_item_size = 0; - if (key->type == BTRFS_SHARED_DATA_REF_KEY) + if (key->type == BTRFS_SHARED_DATA_REF_KEY) { + struct btrfs_shared_data_ref *sref; + + sref = btrfs_item_ptr(leaf, slot, struct btrfs_shared_data_ref); + if (unlikely(btrfs_shared_data_ref_count(leaf, sref) == 0)) { + extent_err(leaf, slot, + "invalid shared data backref count, should have non-zero value"); + return -EUCLEAN; + } + expect_item_size = sizeof(struct btrfs_shared_data_ref); + } if (unlikely(btrfs_item_size(leaf, slot) != expect_item_size)) { generic_err(leaf, slot, @@ -1689,6 +1709,11 @@ static int check_extent_data_ref(struct extent_buffer *leaf, offset, leaf->fs_info->sectorsize); return -EUCLEAN; } + if (unlikely(btrfs_extent_data_ref_count(leaf, dref) == 0)) { + extent_err(leaf, slot, + "invalid extent data backref count, should have non-zero value"); + return -EUCLEAN; + } } return 0; } diff --git a/fs/ceph/file.c b/fs/ceph/file.c index 4b8d59ebda00..851d70200c6b 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -1066,7 +1066,7 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos, if (ceph_inode_is_shutdown(inode)) return -EIO; - if (!len) + if (!len || !i_size) return 0; /* * flush any page cache pages in this range. this @@ -1086,7 +1086,7 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos, int num_pages; size_t page_off; bool more; - int idx; + int idx = 0; size_t left; struct ceph_osd_req_op *op; u64 read_off = off; @@ -1116,6 +1116,16 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos, len = read_off + read_len - off; more = len < iov_iter_count(to); + op = &req->r_ops[0]; + if (sparse) { + extent_cnt = __ceph_sparse_read_ext_count(inode, read_len); + ret = ceph_alloc_sparse_ext_map(op, extent_cnt); + if (ret) { + ceph_osdc_put_request(req); + break; + } + } + num_pages = calc_pages_for(read_off, read_len); page_off = offset_in_page(off); pages = ceph_alloc_page_vector(num_pages, GFP_KERNEL); @@ -1127,17 +1137,7 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos, osd_req_op_extent_osd_data_pages(req, 0, pages, read_len, offset_in_page(read_off), - false, false); - - op = &req->r_ops[0]; - if (sparse) { - extent_cnt = __ceph_sparse_read_ext_count(inode, read_len); - ret = ceph_alloc_sparse_ext_map(op, extent_cnt); - if (ret) { - ceph_osdc_put_request(req); - break; - } - } + false, true); ceph_osdc_start_request(osdc, req); ret = ceph_osdc_wait_request(osdc, req); @@ -1160,7 +1160,14 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos, else if (ret == -ENOENT) ret = 0; - if (ret > 0 && IS_ENCRYPTED(inode)) { + if (ret < 0) { + ceph_osdc_put_request(req); + if (ret == -EBLOCKLISTED) + fsc->blocklisted = true; + break; + } + + if (IS_ENCRYPTED(inode)) { int fret; fret = ceph_fscrypt_decrypt_extents(inode, pages, @@ -1186,10 +1193,8 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos, ret = min_t(ssize_t, fret, len); } - ceph_osdc_put_request(req); - /* Short read but not EOF? Zero out the remainder. */ - if (ret >= 0 && ret < len && (off + ret < i_size)) { + if (ret < len && (off + ret < i_size)) { int zlen = min(len - ret, i_size - off - ret); int zoff = page_off + ret; @@ -1199,13 +1204,11 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos, ret += zlen; } - idx = 0; - if (ret <= 0) - left = 0; - else if (off + ret > i_size) - left = i_size - off; + if (off + ret > i_size) + left = (i_size > off) ? i_size - off : 0; else left = ret; + while (left > 0) { size_t plen, copied; @@ -1221,13 +1224,8 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos, break; } } - ceph_release_page_vector(pages, num_pages); - if (ret < 0) { - if (ret == -EBLOCKLISTED) - fsc->blocklisted = true; - break; - } + ceph_osdc_put_request(req); if (off >= i_size || !more) break; @@ -1553,6 +1551,16 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter, break; } + op = &req->r_ops[0]; + if (!write && sparse) { + extent_cnt = __ceph_sparse_read_ext_count(inode, size); + ret = ceph_alloc_sparse_ext_map(op, extent_cnt); + if (ret) { + ceph_osdc_put_request(req); + break; + } + } + len = iter_get_bvecs_alloc(iter, size, &bvecs, &num_pages); if (len < 0) { ceph_osdc_put_request(req); @@ -1562,6 +1570,8 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter, if (len != size) osd_req_op_extent_update(req, 0, len); + osd_req_op_extent_osd_data_bvecs(req, 0, bvecs, num_pages, len); + /* * To simplify error handling, allow AIO when IO within i_size * or IO can be satisfied by single OSD request. @@ -1593,17 +1603,6 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter, req->r_mtime = mtime; } - osd_req_op_extent_osd_data_bvecs(req, 0, bvecs, num_pages, len); - op = &req->r_ops[0]; - if (sparse) { - extent_cnt = __ceph_sparse_read_ext_count(inode, size); - ret = ceph_alloc_sparse_ext_map(op, extent_cnt); - if (ret) { - ceph_osdc_put_request(req); - break; - } - } - if (aio_req) { aio_req->total_len += len; aio_req->num_reqs++; diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index cf92b75745e2..f48242262b21 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -2808,12 +2808,11 @@ retry: if (pos < 0) { /* - * A rename didn't occur, but somehow we didn't end up where - * we thought we would. Throw a warning and try again. + * The path is longer than PATH_MAX and this function + * cannot ever succeed. Creating paths that long is + * possible with Ceph, but Linux cannot use them. */ - pr_warn_client(cl, "did not end path lookup where expected (pos = %d)\n", - pos); - goto retry; + return ERR_PTR(-ENAMETOOLONG); } *pbase = base; diff --git a/fs/ceph/super.c b/fs/ceph/super.c index 86480e5a215e..c235f9a60394 100644 --- a/fs/ceph/super.c +++ b/fs/ceph/super.c @@ -431,6 +431,8 @@ static int ceph_parse_mount_param(struct fs_context *fc, switch (token) { case Opt_snapdirname: + if (strlen(param->string) > NAME_MAX) + return invalfc(fc, "snapdirname too long"); kfree(fsopt->snapdir_name); fsopt->snapdir_name = param->string; param->string = NULL; diff --git a/fs/efivarfs/inode.c b/fs/efivarfs/inode.c index 586446e02ef7..ec23da8405ff 100644 --- a/fs/efivarfs/inode.c +++ b/fs/efivarfs/inode.c @@ -51,7 +51,7 @@ struct inode *efivarfs_get_inode(struct super_block *sb, * * VariableName-12345678-1234-1234-1234-1234567891bc */ -bool efivarfs_valid_name(const char *str, int len) +static bool efivarfs_valid_name(const char *str, int len) { const char *s = str + len - EFI_VARIABLE_GUID_LEN; diff --git a/fs/efivarfs/internal.h b/fs/efivarfs/internal.h index d71d2e08422f..74f0602a9e01 100644 --- a/fs/efivarfs/internal.h +++ b/fs/efivarfs/internal.h @@ -60,7 +60,6 @@ bool efivar_variable_is_removable(efi_guid_t vendor, const char *name, extern const struct file_operations efivarfs_file_operations; extern const struct inode_operations efivarfs_dir_inode_operations; -extern bool efivarfs_valid_name(const char *str, int len); extern struct inode *efivarfs_get_inode(struct super_block *sb, const struct inode *dir, int mode, dev_t dev, bool is_removable); diff --git a/fs/efivarfs/super.c b/fs/efivarfs/super.c index a929f1b613be..beba15673be8 100644 --- a/fs/efivarfs/super.c +++ b/fs/efivarfs/super.c @@ -144,9 +144,6 @@ static int efivarfs_d_hash(const struct dentry *dentry, struct qstr *qstr) const unsigned char *s = qstr->name; unsigned int len = qstr->len; - if (!efivarfs_valid_name(s, len)) - return -EINVAL; - while (len-- > EFI_VARIABLE_GUID_LEN) hash = partial_name_hash(*s++, hash); diff --git a/fs/erofs/data.c b/fs/erofs/data.c index fa51437e1d99..722151d3fee8 100644 --- a/fs/erofs/data.c +++ b/fs/erofs/data.c @@ -63,10 +63,10 @@ void erofs_init_metabuf(struct erofs_buf *buf, struct super_block *sb) buf->file = NULL; if (erofs_is_fileio_mode(sbi)) { - buf->file = sbi->fdev; /* some fs like FUSE needs it */ + buf->file = sbi->dif0.file; /* some fs like FUSE needs it */ buf->mapping = buf->file->f_mapping; } else if (erofs_is_fscache_mode(sb)) - buf->mapping = sbi->s_fscache->inode->i_mapping; + buf->mapping = sbi->dif0.fscache->inode->i_mapping; else buf->mapping = sb->s_bdev->bd_mapping; } @@ -186,19 +186,13 @@ out: } static void erofs_fill_from_devinfo(struct erofs_map_dev *map, - struct erofs_device_info *dif) + struct super_block *sb, struct erofs_device_info *dif) { + map->m_sb = sb; + map->m_dif = dif; map->m_bdev = NULL; - map->m_fp = NULL; - if (dif->file) { - if (S_ISBLK(file_inode(dif->file)->i_mode)) - map->m_bdev = file_bdev(dif->file); - else - map->m_fp = dif->file; - } - map->m_daxdev = dif->dax_dev; - map->m_dax_part_off = dif->dax_part_off; - map->m_fscache = dif->fscache; + if (dif->file && S_ISBLK(file_inode(dif->file)->i_mode)) + map->m_bdev = file_bdev(dif->file); } int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *map) @@ -208,12 +202,8 @@ int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *map) erofs_off_t startoff, length; int id; - map->m_bdev = sb->s_bdev; - map->m_daxdev = EROFS_SB(sb)->dax_dev; - map->m_dax_part_off = EROFS_SB(sb)->dax_part_off; - map->m_fscache = EROFS_SB(sb)->s_fscache; - map->m_fp = EROFS_SB(sb)->fdev; - + erofs_fill_from_devinfo(map, sb, &EROFS_SB(sb)->dif0); + map->m_bdev = sb->s_bdev; /* use s_bdev for the primary device */ if (map->m_deviceid) { down_read(&devs->rwsem); dif = idr_find(&devs->tree, map->m_deviceid - 1); @@ -226,7 +216,7 @@ int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *map) up_read(&devs->rwsem); return 0; } - erofs_fill_from_devinfo(map, dif); + erofs_fill_from_devinfo(map, sb, dif); up_read(&devs->rwsem); } else if (devs->extra_devices && !devs->flatdev) { down_read(&devs->rwsem); @@ -239,7 +229,7 @@ int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *map) if (map->m_pa >= startoff && map->m_pa < startoff + length) { map->m_pa -= startoff; - erofs_fill_from_devinfo(map, dif); + erofs_fill_from_devinfo(map, sb, dif); break; } } @@ -309,7 +299,7 @@ static int erofs_iomap_begin(struct inode *inode, loff_t offset, loff_t length, iomap->offset = map.m_la; if (flags & IOMAP_DAX) - iomap->dax_dev = mdev.m_daxdev; + iomap->dax_dev = mdev.m_dif->dax_dev; else iomap->bdev = mdev.m_bdev; iomap->length = map.m_llen; @@ -338,7 +328,7 @@ static int erofs_iomap_begin(struct inode *inode, loff_t offset, loff_t length, iomap->type = IOMAP_MAPPED; iomap->addr = mdev.m_pa; if (flags & IOMAP_DAX) - iomap->addr += mdev.m_dax_part_off; + iomap->addr += mdev.m_dif->dax_part_off; } return 0; } diff --git a/fs/erofs/fileio.c b/fs/erofs/fileio.c index 3af96b1e2c2a..33f8539dda4a 100644 --- a/fs/erofs/fileio.c +++ b/fs/erofs/fileio.c @@ -9,6 +9,7 @@ struct erofs_fileio_rq { struct bio_vec bvecs[BIO_MAX_VECS]; struct bio bio; struct kiocb iocb; + struct super_block *sb; }; struct erofs_fileio { @@ -52,8 +53,9 @@ static void erofs_fileio_rq_submit(struct erofs_fileio_rq *rq) rq->iocb.ki_pos = rq->bio.bi_iter.bi_sector << SECTOR_SHIFT; rq->iocb.ki_ioprio = get_current_ioprio(); rq->iocb.ki_complete = erofs_fileio_ki_complete; - rq->iocb.ki_flags = (rq->iocb.ki_filp->f_mode & FMODE_CAN_ODIRECT) ? - IOCB_DIRECT : 0; + if (test_opt(&EROFS_SB(rq->sb)->opt, DIRECT_IO) && + rq->iocb.ki_filp->f_mode & FMODE_CAN_ODIRECT) + rq->iocb.ki_flags = IOCB_DIRECT; iov_iter_bvec(&iter, ITER_DEST, rq->bvecs, rq->bio.bi_vcnt, rq->bio.bi_iter.bi_size); ret = vfs_iocb_iter_read(rq->iocb.ki_filp, &rq->iocb, &iter); @@ -67,7 +69,8 @@ static struct erofs_fileio_rq *erofs_fileio_rq_alloc(struct erofs_map_dev *mdev) GFP_KERNEL | __GFP_NOFAIL); bio_init(&rq->bio, NULL, rq->bvecs, BIO_MAX_VECS, REQ_OP_READ); - rq->iocb.ki_filp = mdev->m_fp; + rq->iocb.ki_filp = mdev->m_dif->file; + rq->sb = mdev->m_sb; return rq; } diff --git a/fs/erofs/fscache.c b/fs/erofs/fscache.c index fda16eedafb5..ce3d8737df85 100644 --- a/fs/erofs/fscache.c +++ b/fs/erofs/fscache.c @@ -198,7 +198,7 @@ struct bio *erofs_fscache_bio_alloc(struct erofs_map_dev *mdev) io = kmalloc(sizeof(*io), GFP_KERNEL | __GFP_NOFAIL); bio_init(&io->bio, NULL, io->bvecs, BIO_MAX_VECS, REQ_OP_READ); - io->io.private = mdev->m_fscache->cookie; + io->io.private = mdev->m_dif->fscache->cookie; io->io.end_io = erofs_fscache_bio_endio; refcount_set(&io->io.ref, 1); return &io->bio; @@ -316,7 +316,7 @@ static int erofs_fscache_data_read_slice(struct erofs_fscache_rq *req) if (!io) return -ENOMEM; iov_iter_xarray(&io->iter, ITER_DEST, &mapping->i_pages, pos, count); - ret = erofs_fscache_read_io_async(mdev.m_fscache->cookie, + ret = erofs_fscache_read_io_async(mdev.m_dif->fscache->cookie, mdev.m_pa + (pos - map.m_la), io); erofs_fscache_req_io_put(io); @@ -657,7 +657,7 @@ int erofs_fscache_register_fs(struct super_block *sb) if (IS_ERR(fscache)) return PTR_ERR(fscache); - sbi->s_fscache = fscache; + sbi->dif0.fscache = fscache; return 0; } @@ -665,14 +665,14 @@ void erofs_fscache_unregister_fs(struct super_block *sb) { struct erofs_sb_info *sbi = EROFS_SB(sb); - erofs_fscache_unregister_cookie(sbi->s_fscache); + erofs_fscache_unregister_cookie(sbi->dif0.fscache); if (sbi->domain) erofs_fscache_domain_put(sbi->domain); else fscache_relinquish_volume(sbi->volume, NULL, false); - sbi->s_fscache = NULL; + sbi->dif0.fscache = NULL; sbi->volume = NULL; sbi->domain = NULL; } diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h index 9b03c8f323a7..77e785a6dfa7 100644 --- a/fs/erofs/internal.h +++ b/fs/erofs/internal.h @@ -113,6 +113,7 @@ struct erofs_xattr_prefix_item { }; struct erofs_sb_info { + struct erofs_device_info dif0; struct erofs_mount_opts opt; /* options */ #ifdef CONFIG_EROFS_FS_ZIP /* list for all registered superblocks, mainly for shrinker */ @@ -130,13 +131,9 @@ struct erofs_sb_info { struct erofs_sb_lz4_info lz4; #endif /* CONFIG_EROFS_FS_ZIP */ - struct file *fdev; struct inode *packed_inode; struct erofs_dev_context *devs; - struct dax_device *dax_dev; - u64 dax_part_off; u64 total_blocks; - u32 primarydevice_blocks; u32 meta_blkaddr; #ifdef CONFIG_EROFS_FS_XATTR @@ -172,7 +169,6 @@ struct erofs_sb_info { /* fscache support */ struct fscache_volume *volume; - struct erofs_fscache *s_fscache; struct erofs_domain *domain; char *fsid; char *domain_id; @@ -186,6 +182,7 @@ struct erofs_sb_info { #define EROFS_MOUNT_POSIX_ACL 0x00000020 #define EROFS_MOUNT_DAX_ALWAYS 0x00000040 #define EROFS_MOUNT_DAX_NEVER 0x00000080 +#define EROFS_MOUNT_DIRECT_IO 0x00000100 #define clear_opt(opt, option) ((opt)->mount_opt &= ~EROFS_MOUNT_##option) #define set_opt(opt, option) ((opt)->mount_opt |= EROFS_MOUNT_##option) @@ -193,7 +190,7 @@ struct erofs_sb_info { static inline bool erofs_is_fileio_mode(struct erofs_sb_info *sbi) { - return IS_ENABLED(CONFIG_EROFS_FS_BACKED_BY_FILE) && sbi->fdev; + return IS_ENABLED(CONFIG_EROFS_FS_BACKED_BY_FILE) && sbi->dif0.file; } static inline bool erofs_is_fscache_mode(struct super_block *sb) @@ -370,11 +367,9 @@ enum { }; struct erofs_map_dev { - struct erofs_fscache *m_fscache; + struct super_block *m_sb; + struct erofs_device_info *m_dif; struct block_device *m_bdev; - struct dax_device *m_daxdev; - struct file *m_fp; - u64 m_dax_part_off; erofs_off_t m_pa; unsigned int m_deviceid; diff --git a/fs/erofs/super.c b/fs/erofs/super.c index 2dd7d819572f..5b279977c9d5 100644 --- a/fs/erofs/super.c +++ b/fs/erofs/super.c @@ -218,7 +218,7 @@ static int erofs_scan_devices(struct super_block *sb, struct erofs_device_info *dif; int id, err = 0; - sbi->total_blocks = sbi->primarydevice_blocks; + sbi->total_blocks = sbi->dif0.blocks; if (!erofs_sb_has_device_table(sbi)) ondisk_extradevs = 0; else @@ -322,7 +322,7 @@ static int erofs_read_superblock(struct super_block *sb) sbi->sb_size); goto out; } - sbi->primarydevice_blocks = le32_to_cpu(dsb->blocks); + sbi->dif0.blocks = le32_to_cpu(dsb->blocks); sbi->meta_blkaddr = le32_to_cpu(dsb->meta_blkaddr); #ifdef CONFIG_EROFS_FS_XATTR sbi->xattr_blkaddr = le32_to_cpu(dsb->xattr_blkaddr); @@ -379,14 +379,8 @@ static void erofs_default_options(struct erofs_sb_info *sbi) } enum { - Opt_user_xattr, - Opt_acl, - Opt_cache_strategy, - Opt_dax, - Opt_dax_enum, - Opt_device, - Opt_fsid, - Opt_domain_id, + Opt_user_xattr, Opt_acl, Opt_cache_strategy, Opt_dax, Opt_dax_enum, + Opt_device, Opt_fsid, Opt_domain_id, Opt_directio, Opt_err }; @@ -413,6 +407,7 @@ static const struct fs_parameter_spec erofs_fs_parameters[] = { fsparam_string("device", Opt_device), fsparam_string("fsid", Opt_fsid), fsparam_string("domain_id", Opt_domain_id), + fsparam_flag_no("directio", Opt_directio), {} }; @@ -526,6 +521,16 @@ static int erofs_fc_parse_param(struct fs_context *fc, errorfc(fc, "%s option not supported", erofs_fs_parameters[opt].name); break; #endif + case Opt_directio: +#ifdef CONFIG_EROFS_FS_BACKED_BY_FILE + if (result.boolean) + set_opt(&sbi->opt, DIRECT_IO); + else + clear_opt(&sbi->opt, DIRECT_IO); +#else + errorfc(fc, "%s option not supported", erofs_fs_parameters[opt].name); +#endif + break; default: return -ENOPARAM; } @@ -617,9 +622,8 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc) return -EINVAL; } - sbi->dax_dev = fs_dax_get_by_bdev(sb->s_bdev, - &sbi->dax_part_off, - NULL, NULL); + sbi->dif0.dax_dev = fs_dax_get_by_bdev(sb->s_bdev, + &sbi->dif0.dax_part_off, NULL, NULL); } err = erofs_read_superblock(sb); @@ -642,7 +646,7 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc) } if (test_opt(&sbi->opt, DAX_ALWAYS)) { - if (!sbi->dax_dev) { + if (!sbi->dif0.dax_dev) { errorfc(fc, "DAX unsupported by block device. Turning off DAX."); clear_opt(&sbi->opt, DAX_ALWAYS); } else if (sbi->blkszbits != PAGE_SHIFT) { @@ -718,16 +722,18 @@ static int erofs_fc_get_tree(struct fs_context *fc) GET_TREE_BDEV_QUIET_LOOKUP : 0); #ifdef CONFIG_EROFS_FS_BACKED_BY_FILE if (ret == -ENOTBLK) { + struct file *file; + if (!fc->source) return invalf(fc, "No source specified"); - sbi->fdev = filp_open(fc->source, O_RDONLY | O_LARGEFILE, 0); - if (IS_ERR(sbi->fdev)) - return PTR_ERR(sbi->fdev); + file = filp_open(fc->source, O_RDONLY | O_LARGEFILE, 0); + if (IS_ERR(file)) + return PTR_ERR(file); + sbi->dif0.file = file; - if (S_ISREG(file_inode(sbi->fdev)->i_mode) && - sbi->fdev->f_mapping->a_ops->read_folio) + if (S_ISREG(file_inode(sbi->dif0.file)->i_mode) && + sbi->dif0.file->f_mapping->a_ops->read_folio) return get_tree_nodev(fc, erofs_fc_fill_super); - fput(sbi->fdev); } #endif return ret; @@ -778,19 +784,24 @@ static void erofs_free_dev_context(struct erofs_dev_context *devs) kfree(devs); } -static void erofs_fc_free(struct fs_context *fc) +static void erofs_sb_free(struct erofs_sb_info *sbi) { - struct erofs_sb_info *sbi = fc->s_fs_info; - - if (!sbi) - return; - erofs_free_dev_context(sbi->devs); kfree(sbi->fsid); kfree(sbi->domain_id); + if (sbi->dif0.file) + fput(sbi->dif0.file); kfree(sbi); } +static void erofs_fc_free(struct fs_context *fc) +{ + struct erofs_sb_info *sbi = fc->s_fs_info; + + if (sbi) /* free here if an error occurs before transferring to sb */ + erofs_sb_free(sbi); +} + static const struct fs_context_operations erofs_context_ops = { .parse_param = erofs_fc_parse_param, .get_tree = erofs_fc_get_tree, @@ -824,19 +835,14 @@ static void erofs_kill_sb(struct super_block *sb) { struct erofs_sb_info *sbi = EROFS_SB(sb); - if ((IS_ENABLED(CONFIG_EROFS_FS_ONDEMAND) && sbi->fsid) || sbi->fdev) + if ((IS_ENABLED(CONFIG_EROFS_FS_ONDEMAND) && sbi->fsid) || + sbi->dif0.file) kill_anon_super(sb); else kill_block_super(sb); - - erofs_free_dev_context(sbi->devs); - fs_put_dax(sbi->dax_dev, NULL); + fs_put_dax(sbi->dif0.dax_dev, NULL); erofs_fscache_unregister_fs(sb); - kfree(sbi->fsid); - kfree(sbi->domain_id); - if (sbi->fdev) - fput(sbi->fdev); - kfree(sbi); + erofs_sb_free(sbi); sb->s_fs_info = NULL; } @@ -962,6 +968,8 @@ static int erofs_show_options(struct seq_file *seq, struct dentry *root) seq_puts(seq, ",dax=always"); if (test_opt(opt, DAX_NEVER)) seq_puts(seq, ",dax=never"); + if (erofs_is_fileio_mode(sbi) && test_opt(opt, DIRECT_IO)) + seq_puts(seq, ",directio"); #ifdef CONFIG_EROFS_FS_ONDEMAND if (sbi->fsid) seq_printf(seq, ",fsid=%s", sbi->fsid); diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c index a569ff9dfd04..1a00f061798a 100644 --- a/fs/erofs/zdata.c +++ b/fs/erofs/zdata.c @@ -1679,9 +1679,9 @@ drain_io: erofs_fscache_submit_bio(bio); else submit_bio(bio); - if (memstall) - psi_memstall_leave(&pflags); } + if (memstall) + psi_memstall_leave(&pflags); /* * although background is preferred, no one is pending for submission. diff --git a/fs/eventpoll.c b/fs/eventpoll.c index 90fbab6b6f03..1a06e462b6ef 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -1373,7 +1373,10 @@ static int ep_poll_callback(wait_queue_entry_t *wait, unsigned mode, int sync, v break; } } - wake_up(&ep->wq); + if (sync) + wake_up_sync(&ep->wq); + else + wake_up(&ep->wq); } if (waitqueue_active(&ep->poll_wait)) pwake++; diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 5cf327337e22..c0856585bb63 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -893,7 +893,7 @@ static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset, error = PTR_ERR(folio); goto out; } - folio_zero_user(folio, ALIGN_DOWN(addr, hpage_size)); + folio_zero_user(folio, addr); __folio_mark_uptodate(folio); error = hugetlb_add_to_page_cache(folio, mapping, index); if (unlikely(error)) { diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 0d16b383a452..5f582713bf05 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -1308,7 +1308,7 @@ pnfs_prepare_layoutreturn(struct pnfs_layout_hdr *lo, enum pnfs_iomode *iomode) { /* Serialise LAYOUTGET/LAYOUTRETURN */ - if (atomic_read(&lo->plh_outstanding) != 0) + if (atomic_read(&lo->plh_outstanding) != 0 && lo->plh_return_seq == 0) return false; if (test_and_set_bit(NFS_LAYOUT_RETURN_LOCK, &lo->plh_flags)) return false; diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c index 6d0455973d64..49aede376d86 100644 --- a/fs/nfsd/export.c +++ b/fs/nfsd/export.c @@ -40,24 +40,15 @@ #define EXPKEY_HASHMAX (1 << EXPKEY_HASHBITS) #define EXPKEY_HASHMASK (EXPKEY_HASHMAX -1) -static void expkey_put_work(struct work_struct *work) +static void expkey_put(struct kref *ref) { - struct svc_expkey *key = - container_of(to_rcu_work(work), struct svc_expkey, ek_rcu_work); + struct svc_expkey *key = container_of(ref, struct svc_expkey, h.ref); if (test_bit(CACHE_VALID, &key->h.flags) && !test_bit(CACHE_NEGATIVE, &key->h.flags)) path_put(&key->ek_path); auth_domain_put(key->ek_client); - kfree(key); -} - -static void expkey_put(struct kref *ref) -{ - struct svc_expkey *key = container_of(ref, struct svc_expkey, h.ref); - - INIT_RCU_WORK(&key->ek_rcu_work, expkey_put_work); - queue_rcu_work(system_wq, &key->ek_rcu_work); + kfree_rcu(key, ek_rcu); } static int expkey_upcall(struct cache_detail *cd, struct cache_head *h) @@ -364,26 +355,16 @@ static void export_stats_destroy(struct export_stats *stats) EXP_STATS_COUNTERS_NUM); } -static void svc_export_put_work(struct work_struct *work) +static void svc_export_put(struct kref *ref) { - struct svc_export *exp = - container_of(to_rcu_work(work), struct svc_export, ex_rcu_work); - + struct svc_export *exp = container_of(ref, struct svc_export, h.ref); path_put(&exp->ex_path); auth_domain_put(exp->ex_client); nfsd4_fslocs_free(&exp->ex_fslocs); export_stats_destroy(exp->ex_stats); kfree(exp->ex_stats); kfree(exp->ex_uuid); - kfree(exp); -} - -static void svc_export_put(struct kref *ref) -{ - struct svc_export *exp = container_of(ref, struct svc_export, h.ref); - - INIT_RCU_WORK(&exp->ex_rcu_work, svc_export_put_work); - queue_rcu_work(system_wq, &exp->ex_rcu_work); + kfree_rcu(exp, ex_rcu); } static int svc_export_upcall(struct cache_detail *cd, struct cache_head *h) diff --git a/fs/nfsd/export.h b/fs/nfsd/export.h index 081afb68681e..3794ae253a70 100644 --- a/fs/nfsd/export.h +++ b/fs/nfsd/export.h @@ -75,7 +75,7 @@ struct svc_export { u32 ex_layout_types; struct nfsd4_deviceid_map *ex_devid_map; struct cache_detail *cd; - struct rcu_work ex_rcu_work; + struct rcu_head ex_rcu; unsigned long ex_xprtsec_modes; struct export_stats *ex_stats; }; @@ -92,7 +92,7 @@ struct svc_expkey { u32 ek_fsid[6]; struct path ek_path; - struct rcu_work ek_rcu_work; + struct rcu_head ek_rcu; }; #define EX_ISSYNC(exp) (!((exp)->ex_flags & NFSEXP_ASYNC)) diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c index b8cbb1556004..de0763652549 100644 --- a/fs/nfsd/nfs4callback.c +++ b/fs/nfsd/nfs4callback.c @@ -1058,7 +1058,7 @@ static int setup_callback_client(struct nfs4_client *clp, struct nfs4_cb_conn *c args.authflavor = clp->cl_cred.cr_flavor; clp->cl_cb_ident = conn->cb_ident; } else { - if (!conn->cb_xprt) + if (!conn->cb_xprt || !ses) return -EINVAL; clp->cl_cb_session = ses; args.bc_xprt = conn->cb_xprt; @@ -1461,8 +1461,6 @@ static void nfsd4_process_cb_update(struct nfsd4_callback *cb) ses = c->cn_session; } spin_unlock(&clp->cl_lock); - if (!c) - return; err = setup_callback_client(clp, &conn, ses); if (err) { diff --git a/fs/nilfs2/btnode.c b/fs/nilfs2/btnode.c index 501ad7be5174..54a3fa0cf67e 100644 --- a/fs/nilfs2/btnode.c +++ b/fs/nilfs2/btnode.c @@ -35,6 +35,7 @@ void nilfs_init_btnc_inode(struct inode *btnc_inode) ii->i_flags = 0; memset(&ii->i_bmap_data, 0, sizeof(struct nilfs_bmap)); mapping_set_gfp_mask(btnc_inode->i_mapping, GFP_NOFS); + btnc_inode->i_mapping->a_ops = &nilfs_buffer_cache_aops; } void nilfs_btnode_cache_clear(struct address_space *btnc) diff --git a/fs/nilfs2/gcinode.c b/fs/nilfs2/gcinode.c index ace22253fed0..2dbb15767df1 100644 --- a/fs/nilfs2/gcinode.c +++ b/fs/nilfs2/gcinode.c @@ -163,7 +163,7 @@ int nilfs_init_gcinode(struct inode *inode) inode->i_mode = S_IFREG; mapping_set_gfp_mask(inode->i_mapping, GFP_NOFS); - inode->i_mapping->a_ops = &empty_aops; + inode->i_mapping->a_ops = &nilfs_buffer_cache_aops; ii->i_flags = 0; nilfs_bmap_init_gc(ii->i_bmap); diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c index be6acf6e2bfc..aaca34ec678f 100644 --- a/fs/nilfs2/inode.c +++ b/fs/nilfs2/inode.c @@ -307,6 +307,10 @@ const struct address_space_operations nilfs_aops = { .is_partially_uptodate = block_is_partially_uptodate, }; +const struct address_space_operations nilfs_buffer_cache_aops = { + .invalidate_folio = block_invalidate_folio, +}; + static int nilfs_insert_inode_locked(struct inode *inode, struct nilfs_root *root, unsigned long ino) @@ -575,8 +579,14 @@ struct inode *nilfs_iget(struct super_block *sb, struct nilfs_root *root, inode = nilfs_iget_locked(sb, root, ino); if (unlikely(!inode)) return ERR_PTR(-ENOMEM); - if (!(inode->i_state & I_NEW)) + + if (!(inode->i_state & I_NEW)) { + if (!inode->i_nlink) { + iput(inode); + return ERR_PTR(-ESTALE); + } return inode; + } err = __nilfs_read_inode(sb, root, ino, inode); if (unlikely(err)) { @@ -706,6 +716,7 @@ struct inode *nilfs_iget_for_shadow(struct inode *inode) NILFS_I(s_inode)->i_flags = 0; memset(NILFS_I(s_inode)->i_bmap, 0, sizeof(struct nilfs_bmap)); mapping_set_gfp_mask(s_inode->i_mapping, GFP_NOFS); + s_inode->i_mapping->a_ops = &nilfs_buffer_cache_aops; err = nilfs_attach_btree_node_cache(s_inode); if (unlikely(err)) { diff --git a/fs/nilfs2/namei.c b/fs/nilfs2/namei.c index 9b108052d9f7..1d836a5540f3 100644 --- a/fs/nilfs2/namei.c +++ b/fs/nilfs2/namei.c @@ -67,6 +67,11 @@ nilfs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) inode = NULL; } else { inode = nilfs_iget(dir->i_sb, NILFS_I(dir)->i_root, ino); + if (inode == ERR_PTR(-ESTALE)) { + nilfs_error(dir->i_sb, + "deleted inode referenced: %lu", ino); + return ERR_PTR(-EIO); + } } return d_splice_alias(inode, dentry); diff --git a/fs/nilfs2/nilfs.h b/fs/nilfs2/nilfs.h index 45d03826eaf1..dff241c53fc5 100644 --- a/fs/nilfs2/nilfs.h +++ b/fs/nilfs2/nilfs.h @@ -401,6 +401,7 @@ extern const struct file_operations nilfs_dir_operations; extern const struct inode_operations nilfs_file_inode_operations; extern const struct file_operations nilfs_file_operations; extern const struct address_space_operations nilfs_aops; +extern const struct address_space_operations nilfs_buffer_cache_aops; extern const struct inode_operations nilfs_dir_inode_operations; extern const struct inode_operations nilfs_special_inode_operations; extern const struct inode_operations nilfs_symlink_inode_operations; diff --git a/fs/ocfs2/localalloc.c b/fs/ocfs2/localalloc.c index 5df34561c551..d1aa04a5af1b 100644 --- a/fs/ocfs2/localalloc.c +++ b/fs/ocfs2/localalloc.c @@ -971,9 +971,9 @@ static int ocfs2_sync_local_to_main(struct ocfs2_super *osb, start = count = 0; left = le32_to_cpu(alloc->id1.bitmap1.i_total); - while ((bit_off = ocfs2_find_next_zero_bit(bitmap, left, start)) < - left) { - if (bit_off == start) { + while (1) { + bit_off = ocfs2_find_next_zero_bit(bitmap, left, start); + if ((bit_off < left) && (bit_off == start)) { count++; start++; continue; @@ -998,6 +998,8 @@ static int ocfs2_sync_local_to_main(struct ocfs2_super *osb, } } + if (bit_off >= left) + break; count = 1; start = bit_off + 1; } diff --git a/fs/ocfs2/quota_global.c b/fs/ocfs2/quota_global.c index 2b0daced98eb..3404e7a30c33 100644 --- a/fs/ocfs2/quota_global.c +++ b/fs/ocfs2/quota_global.c @@ -893,7 +893,7 @@ static int ocfs2_get_next_id(struct super_block *sb, struct kqid *qid) int status = 0; trace_ocfs2_get_next_id(from_kqid(&init_user_ns, *qid), type); - if (!sb_has_quota_loaded(sb, type)) { + if (!sb_has_quota_active(sb, type)) { status = -ESRCH; goto out; } diff --git a/fs/ocfs2/quota_local.c b/fs/ocfs2/quota_local.c index 73d3367c533b..2956d888c131 100644 --- a/fs/ocfs2/quota_local.c +++ b/fs/ocfs2/quota_local.c @@ -867,6 +867,7 @@ out: brelse(oinfo->dqi_libh); brelse(oinfo->dqi_lqi_bh); kfree(oinfo); + info->dqi_priv = NULL; return status; } diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 7eb010de39fe..536b7dc45381 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -1810,7 +1810,7 @@ static int pagemap_pmd_range(pmd_t *pmdp, unsigned long addr, unsigned long end, } for (; addr != end; addr += PAGE_SIZE, idx++) { - unsigned long cur_flags = flags; + u64 cur_flags = flags; pagemap_entry_t pme; if (folio && (flags & PM_PRESENT) && diff --git a/fs/smb/client/Kconfig b/fs/smb/client/Kconfig index 2aff6d1395ce..9f05f94e265a 100644 --- a/fs/smb/client/Kconfig +++ b/fs/smb/client/Kconfig @@ -2,7 +2,6 @@ config CIFS tristate "SMB3 and CIFS support (advanced network filesystem)" depends on INET - select NETFS_SUPPORT select NLS select NLS_UCS2_UTILS select CRYPTO diff --git a/fs/smb/client/cifsfs.c b/fs/smb/client/cifsfs.c index bf909c2f6b96..0ceebde38f9f 100644 --- a/fs/smb/client/cifsfs.c +++ b/fs/smb/client/cifsfs.c @@ -2018,6 +2018,7 @@ exit_cifs(void) destroy_workqueue(decrypt_wq); destroy_workqueue(fileinfo_put_wq); destroy_workqueue(serverclose_wq); + destroy_workqueue(cfid_put_wq); destroy_workqueue(cifsiod_wq); cifs_proc_clean(); } diff --git a/fs/smb/client/connect.c b/fs/smb/client/connect.c index feff3324d39c..fe40152b915d 100644 --- a/fs/smb/client/connect.c +++ b/fs/smb/client/connect.c @@ -987,9 +987,13 @@ clean_demultiplex_info(struct TCP_Server_Info *server) msleep(125); if (cifs_rdma_enabled(server)) smbd_destroy(server); + if (server->ssocket) { sock_release(server->ssocket); server->ssocket = NULL; + + /* Release netns reference for the socket. */ + put_net(cifs_net_ns(server)); } if (!list_empty(&server->pending_mid_q)) { @@ -1037,6 +1041,7 @@ clean_demultiplex_info(struct TCP_Server_Info *server) */ } + /* Release netns reference for this server. */ put_net(cifs_net_ns(server)); kfree(server->leaf_fullpath); kfree(server); @@ -1713,6 +1718,8 @@ cifs_get_tcp_session(struct smb3_fs_context *ctx, tcp_ses->ops = ctx->ops; tcp_ses->vals = ctx->vals; + + /* Grab netns reference for this server. */ cifs_set_net_ns(tcp_ses, get_net(current->nsproxy->net_ns)); tcp_ses->conn_id = atomic_inc_return(&tcpSesNextId); @@ -1844,6 +1851,7 @@ smbd_connected: out_err_crypto_release: cifs_crypto_secmech_release(tcp_ses); + /* Release netns reference for this server. */ put_net(cifs_net_ns(tcp_ses)); out_err: @@ -1852,8 +1860,10 @@ out_err: cifs_put_tcp_session(tcp_ses->primary_server, false); kfree(tcp_ses->hostname); kfree(tcp_ses->leaf_fullpath); - if (tcp_ses->ssocket) + if (tcp_ses->ssocket) { sock_release(tcp_ses->ssocket); + put_net(cifs_net_ns(tcp_ses)); + } kfree(tcp_ses); } return ERR_PTR(rc); @@ -3111,20 +3121,20 @@ generic_ip_connect(struct TCP_Server_Info *server) socket = server->ssocket; } else { struct net *net = cifs_net_ns(server); - struct sock *sk; - rc = __sock_create(net, sfamily, SOCK_STREAM, - IPPROTO_TCP, &server->ssocket, 1); + rc = sock_create_kern(net, sfamily, SOCK_STREAM, IPPROTO_TCP, &server->ssocket); if (rc < 0) { cifs_server_dbg(VFS, "Error %d creating socket\n", rc); return rc; } - sk = server->ssocket->sk; - __netns_tracker_free(net, &sk->ns_tracker, false); - sk->sk_net_refcnt = 1; - get_net_track(net, &sk->ns_tracker, GFP_KERNEL); - sock_inuse_add(net, 1); + /* + * Grab netns reference for the socket. + * + * It'll be released here, on error, or in clean_demultiplex_info() upon server + * teardown. + */ + get_net(net); /* BB other socket options to set KEEPALIVE, NODELAY? */ cifs_dbg(FYI, "Socket created\n"); @@ -3138,8 +3148,10 @@ generic_ip_connect(struct TCP_Server_Info *server) } rc = bind_socket(server); - if (rc < 0) + if (rc < 0) { + put_net(cifs_net_ns(server)); return rc; + } /* * Eventually check for other socket options to change from @@ -3176,6 +3188,7 @@ generic_ip_connect(struct TCP_Server_Info *server) if (rc < 0) { cifs_dbg(FYI, "Error %d connecting to server\n", rc); trace_smb3_connect_err(server->hostname, server->conn_id, &server->dstaddr, rc); + put_net(cifs_net_ns(server)); sock_release(socket); server->ssocket = NULL; return rc; @@ -3184,6 +3197,9 @@ generic_ip_connect(struct TCP_Server_Info *server) if (sport == htons(RFC1001_PORT)) rc = ip_rfc1001_connect(server); + if (rc < 0) + put_net(cifs_net_ns(server)); + return rc; } diff --git a/fs/smb/client/inode.c b/fs/smb/client/inode.c index b35fe1075503..fafc07e38663 100644 --- a/fs/smb/client/inode.c +++ b/fs/smb/client/inode.c @@ -1925,6 +1925,7 @@ int cifs_unlink(struct inode *dir, struct dentry *dentry) goto unlink_out; } + netfs_wait_for_outstanding_io(inode); cifs_close_deferred_file_under_dentry(tcon, full_path); #ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY if (cap_unix(tcon->ses) && (CIFS_UNIX_POSIX_PATH_OPS_CAP & @@ -2442,8 +2443,10 @@ cifs_rename2(struct mnt_idmap *idmap, struct inode *source_dir, } cifs_close_deferred_file_under_dentry(tcon, from_name); - if (d_inode(target_dentry) != NULL) + if (d_inode(target_dentry) != NULL) { + netfs_wait_for_outstanding_io(d_inode(target_dentry)); cifs_close_deferred_file_under_dentry(tcon, to_name); + } rc = cifs_do_rename(xid, source_dentry, from_name, target_dentry, to_name); diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c index d1bd69cbfe09..4750505465ae 100644 --- a/fs/smb/client/smb2pdu.c +++ b/fs/smb/client/smb2pdu.c @@ -4855,6 +4855,8 @@ smb2_writev_callback(struct mid_q_entry *mid) if (written > wdata->subreq.len) written &= 0xFFFF; + cifs_stats_bytes_written(tcon, written); + if (written < wdata->subreq.len) wdata->result = -ENOSPC; else @@ -5171,6 +5173,7 @@ replay_again: cifs_dbg(VFS, "Send error in write = %d\n", rc); } else { *nbytes = le32_to_cpu(rsp->DataLength); + cifs_stats_bytes_written(io_parms->tcon, *nbytes); trace_smb3_write_done(0, 0, xid, req->PersistentFileId, io_parms->tcon->tid, diff --git a/fs/smb/server/auth.c b/fs/smb/server/auth.c index 611716bc8f27..8892177e500f 100644 --- a/fs/smb/server/auth.c +++ b/fs/smb/server/auth.c @@ -1016,6 +1016,8 @@ static int ksmbd_get_encryption_key(struct ksmbd_work *work, __u64 ses_id, ses_enc_key = enc ? sess->smb3encryptionkey : sess->smb3decryptionkey; + if (enc) + ksmbd_user_session_get(sess); memcpy(key, ses_enc_key, SMB3_ENC_DEC_KEY_SIZE); return 0; diff --git a/fs/smb/server/connection.c b/fs/smb/server/connection.c index e6a72f75ab94..bf45822db5d5 100644 --- a/fs/smb/server/connection.c +++ b/fs/smb/server/connection.c @@ -70,7 +70,6 @@ struct ksmbd_conn *ksmbd_conn_alloc(void) atomic_set(&conn->req_running, 0); atomic_set(&conn->r_count, 0); atomic_set(&conn->refcnt, 1); - atomic_set(&conn->mux_smb_requests, 0); conn->total_credits = 1; conn->outstanding_credits = 0; @@ -120,8 +119,8 @@ void ksmbd_conn_enqueue_request(struct ksmbd_work *work) if (conn->ops->get_cmd_val(work) != SMB2_CANCEL_HE) requests_queue = &conn->requests; + atomic_inc(&conn->req_running); if (requests_queue) { - atomic_inc(&conn->req_running); spin_lock(&conn->request_lock); list_add_tail(&work->request_entry, requests_queue); spin_unlock(&conn->request_lock); @@ -132,11 +131,14 @@ void ksmbd_conn_try_dequeue_request(struct ksmbd_work *work) { struct ksmbd_conn *conn = work->conn; + atomic_dec(&conn->req_running); + if (waitqueue_active(&conn->req_running_q)) + wake_up(&conn->req_running_q); + if (list_empty(&work->request_entry) && list_empty(&work->async_request_entry)) return; - atomic_dec(&conn->req_running); spin_lock(&conn->request_lock); list_del_init(&work->request_entry); spin_unlock(&conn->request_lock); @@ -308,7 +310,7 @@ int ksmbd_conn_handler_loop(void *p) { struct ksmbd_conn *conn = (struct ksmbd_conn *)p; struct ksmbd_transport *t = conn->transport; - unsigned int pdu_size, max_allowed_pdu_size; + unsigned int pdu_size, max_allowed_pdu_size, max_req; char hdr_buf[4] = {0,}; int size; @@ -318,6 +320,7 @@ int ksmbd_conn_handler_loop(void *p) if (t->ops->prepare && t->ops->prepare(t)) goto out; + max_req = server_conf.max_inflight_req; conn->last_active = jiffies; set_freezable(); while (ksmbd_conn_alive(conn)) { @@ -327,6 +330,13 @@ int ksmbd_conn_handler_loop(void *p) kvfree(conn->request_buf); conn->request_buf = NULL; +recheck: + if (atomic_read(&conn->req_running) + 1 > max_req) { + wait_event_interruptible(conn->req_running_q, + atomic_read(&conn->req_running) < max_req); + goto recheck; + } + size = t->ops->read(t, hdr_buf, sizeof(hdr_buf), -1); if (size != sizeof(hdr_buf)) break; diff --git a/fs/smb/server/connection.h b/fs/smb/server/connection.h index 8ddd5a3c7baf..b379ae4fdcdf 100644 --- a/fs/smb/server/connection.h +++ b/fs/smb/server/connection.h @@ -107,7 +107,6 @@ struct ksmbd_conn { __le16 signing_algorithm; bool binding; atomic_t refcnt; - atomic_t mux_smb_requests; }; struct ksmbd_conn_ops { diff --git a/fs/smb/server/mgmt/user_session.c b/fs/smb/server/mgmt/user_session.c index ad02fe555fda..d960ddcbba16 100644 --- a/fs/smb/server/mgmt/user_session.c +++ b/fs/smb/server/mgmt/user_session.c @@ -263,8 +263,10 @@ struct ksmbd_session *ksmbd_session_lookup(struct ksmbd_conn *conn, down_read(&conn->session_lock); sess = xa_load(&conn->sessions, id); - if (sess) + if (sess) { sess->last_active = jiffies; + ksmbd_user_session_get(sess); + } up_read(&conn->session_lock); return sess; } @@ -275,6 +277,8 @@ struct ksmbd_session *ksmbd_session_lookup_slowpath(unsigned long long id) down_read(&sessions_table_lock); sess = __session_lookup(id); + if (sess) + ksmbd_user_session_get(sess); up_read(&sessions_table_lock); return sess; diff --git a/fs/smb/server/server.c b/fs/smb/server/server.c index c8cc6fa6fc3e..d146b0e7c3a9 100644 --- a/fs/smb/server/server.c +++ b/fs/smb/server/server.c @@ -241,14 +241,14 @@ send: if (work->tcon) ksmbd_tree_connect_put(work->tcon); smb3_preauth_hash_rsp(work); - if (work->sess) - ksmbd_user_session_put(work->sess); if (work->sess && work->sess->enc && work->encrypted && conn->ops->encrypt_resp) { rc = conn->ops->encrypt_resp(work); if (rc < 0) conn->ops->set_rsp_status(work, STATUS_DATA_ERROR); } + if (work->sess) + ksmbd_user_session_put(work->sess); ksmbd_conn_write(work); } @@ -270,7 +270,6 @@ static void handle_ksmbd_work(struct work_struct *wk) ksmbd_conn_try_dequeue_request(work); ksmbd_free_work_struct(work); - atomic_dec(&conn->mux_smb_requests); /* * Checking waitqueue to dropping pending requests on * disconnection. waitqueue_active is safe because it @@ -300,11 +299,6 @@ static int queue_ksmbd_work(struct ksmbd_conn *conn) if (err) return 0; - if (atomic_inc_return(&conn->mux_smb_requests) >= conn->vals->max_credits) { - atomic_dec_return(&conn->mux_smb_requests); - return -ENOSPC; - } - work = ksmbd_alloc_work_struct(); if (!work) { pr_err("allocation for work failed\n"); @@ -367,6 +361,7 @@ static int server_conf_init(void) server_conf.auth_mechs |= KSMBD_AUTH_KRB5 | KSMBD_AUTH_MSKRB5; #endif + server_conf.max_inflight_req = SMB2_MAX_CREDITS; return 0; } diff --git a/fs/smb/server/server.h b/fs/smb/server/server.h index 4fc529335271..94187628ff08 100644 --- a/fs/smb/server/server.h +++ b/fs/smb/server/server.h @@ -42,6 +42,7 @@ struct ksmbd_server_config { struct smb_sid domain_sid; unsigned int auth_mechs; unsigned int max_connections; + unsigned int max_inflight_req; char *conf[SERVER_CONF_WORK_GROUP + 1]; struct task_struct *dh_task; diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index d0836d710f18..04ffc5b158c3 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -67,8 +67,10 @@ static inline bool check_session_id(struct ksmbd_conn *conn, u64 id) return false; sess = ksmbd_session_lookup_all(conn, id); - if (sess) + if (sess) { + ksmbd_user_session_put(sess); return true; + } pr_err("Invalid user session id: %llu\n", id); return false; } @@ -605,10 +607,8 @@ int smb2_check_user_session(struct ksmbd_work *work) /* Check for validity of user session */ work->sess = ksmbd_session_lookup_all(conn, sess_id); - if (work->sess) { - ksmbd_user_session_get(work->sess); + if (work->sess) return 1; - } ksmbd_debug(SMB, "Invalid user session, Uid %llu\n", sess_id); return -ENOENT; } @@ -1701,29 +1701,35 @@ int smb2_sess_setup(struct ksmbd_work *work) if (conn->dialect != sess->dialect) { rc = -EINVAL; + ksmbd_user_session_put(sess); goto out_err; } if (!(req->hdr.Flags & SMB2_FLAGS_SIGNED)) { rc = -EINVAL; + ksmbd_user_session_put(sess); goto out_err; } if (strncmp(conn->ClientGUID, sess->ClientGUID, SMB2_CLIENT_GUID_SIZE)) { rc = -ENOENT; + ksmbd_user_session_put(sess); goto out_err; } if (sess->state == SMB2_SESSION_IN_PROGRESS) { rc = -EACCES; + ksmbd_user_session_put(sess); goto out_err; } if (sess->state == SMB2_SESSION_EXPIRED) { rc = -EFAULT; + ksmbd_user_session_put(sess); goto out_err; } + ksmbd_user_session_put(sess); if (ksmbd_conn_need_reconnect(conn)) { rc = -EFAULT; @@ -1731,7 +1737,8 @@ int smb2_sess_setup(struct ksmbd_work *work) goto out_err; } - if (ksmbd_session_lookup(conn, sess_id)) { + sess = ksmbd_session_lookup(conn, sess_id); + if (!sess) { rc = -EACCES; goto out_err; } @@ -1742,7 +1749,6 @@ int smb2_sess_setup(struct ksmbd_work *work) } conn->binding = true; - ksmbd_user_session_get(sess); } else if ((conn->dialect < SMB30_PROT_ID || server_conf.flags & KSMBD_GLOBAL_FLAG_SMB3_MULTICHANNEL) && (req->Flags & SMB2_SESSION_REQ_FLAG_BINDING)) { @@ -1769,7 +1775,6 @@ int smb2_sess_setup(struct ksmbd_work *work) } conn->binding = false; - ksmbd_user_session_get(sess); } work->sess = sess; @@ -2195,9 +2200,9 @@ err_out: int smb2_session_logoff(struct ksmbd_work *work) { struct ksmbd_conn *conn = work->conn; + struct ksmbd_session *sess = work->sess; struct smb2_logoff_req *req; struct smb2_logoff_rsp *rsp; - struct ksmbd_session *sess; u64 sess_id; int err; @@ -2219,11 +2224,6 @@ int smb2_session_logoff(struct ksmbd_work *work) ksmbd_close_session_fds(work); ksmbd_conn_wait_idle(conn); - /* - * Re-lookup session to validate if session is deleted - * while waiting request complete - */ - sess = ksmbd_session_lookup_all(conn, sess_id); if (ksmbd_tree_conn_session_logoff(sess)) { ksmbd_debug(SMB, "Invalid tid %d\n", req->hdr.Id.SyncId.TreeId); rsp->hdr.Status = STATUS_NETWORK_NAME_DELETED; @@ -4224,6 +4224,7 @@ static bool __query_dir(struct dir_context *ctx, const char *name, int namlen, /* dot and dotdot entries are already reserved */ if (!strcmp(".", name) || !strcmp("..", name)) return true; + d_info->num_scan++; if (ksmbd_share_veto_filename(priv->work->tcon->share_conf, name)) return true; if (!match_pattern(name, namlen, priv->search_pattern)) @@ -4384,9 +4385,18 @@ int smb2_query_dir(struct ksmbd_work *work) query_dir_private.info_level = req->FileInformationClass; dir_fp->readdir_data.private = &query_dir_private; set_ctx_actor(&dir_fp->readdir_data.ctx, __query_dir); - +again: + d_info.num_scan = 0; rc = iterate_dir(dir_fp->filp, &dir_fp->readdir_data.ctx); /* + * num_entry can be 0 if the directory iteration stops before reaching + * the end of the directory and no file is matched with the search + * pattern. + */ + if (rc >= 0 && !d_info.num_entry && d_info.num_scan && + d_info.out_buf_len > 0) + goto again; + /* * req->OutputBufferLength is too small to contain even one entry. * In this case, it immediately returns OutputBufferLength 0 to client. */ @@ -6006,15 +6016,13 @@ static int set_file_basic_info(struct ksmbd_file *fp, attrs.ia_valid |= (ATTR_ATIME | ATTR_ATIME_SET); } - attrs.ia_valid |= ATTR_CTIME; if (file_info->ChangeTime) - attrs.ia_ctime = ksmbd_NTtimeToUnix(file_info->ChangeTime); - else - attrs.ia_ctime = inode_get_ctime(inode); + inode_set_ctime_to_ts(inode, + ksmbd_NTtimeToUnix(file_info->ChangeTime)); if (file_info->LastWriteTime) { attrs.ia_mtime = ksmbd_NTtimeToUnix(file_info->LastWriteTime); - attrs.ia_valid |= (ATTR_MTIME | ATTR_MTIME_SET); + attrs.ia_valid |= (ATTR_MTIME | ATTR_MTIME_SET | ATTR_CTIME); } if (file_info->Attributes) { @@ -6056,8 +6064,6 @@ static int set_file_basic_info(struct ksmbd_file *fp, return -EACCES; inode_lock(inode); - inode_set_ctime_to_ts(inode, attrs.ia_ctime); - attrs.ia_valid &= ~ATTR_CTIME; rc = notify_change(idmap, dentry, &attrs, NULL); inode_unlock(inode); } @@ -8962,6 +8968,7 @@ int smb3_decrypt_req(struct ksmbd_work *work) le64_to_cpu(tr_hdr->SessionId)); return -ECONNABORTED; } + ksmbd_user_session_put(sess); iov[0].iov_base = buf; iov[0].iov_len = sizeof(struct smb2_transform_hdr) + 4; diff --git a/fs/smb/server/smb_common.c b/fs/smb/server/smb_common.c index 75b4eb856d32..af8e24163bf2 100644 --- a/fs/smb/server/smb_common.c +++ b/fs/smb/server/smb_common.c @@ -18,8 +18,8 @@ #include "mgmt/share_config.h" /*for shortname implementation */ -static const char basechars[43] = "0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZ_-!@#$%"; -#define MANGLE_BASE (sizeof(basechars) / sizeof(char) - 1) +static const char *basechars = "0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZ_-!@#$%"; +#define MANGLE_BASE (strlen(basechars) - 1) #define MAGIC_CHAR '~' #define PERIOD '.' #define mangle(V) ((char)(basechars[(V) % MANGLE_BASE])) diff --git a/fs/smb/server/transport_ipc.c b/fs/smb/server/transport_ipc.c index 2f27afb695f6..6de351cc2b60 100644 --- a/fs/smb/server/transport_ipc.c +++ b/fs/smb/server/transport_ipc.c @@ -319,8 +319,11 @@ static int ipc_server_config_on_startup(struct ksmbd_startup_request *req) init_smb2_max_write_size(req->smb2_max_write); if (req->smb2_max_trans) init_smb2_max_trans_size(req->smb2_max_trans); - if (req->smb2_max_credits) + if (req->smb2_max_credits) { init_smb2_max_credits(req->smb2_max_credits); + server_conf.max_inflight_req = + req->smb2_max_credits; + } if (req->smbd_max_io_size) init_smbd_max_io_size(req->smbd_max_io_size); diff --git a/fs/smb/server/vfs.h b/fs/smb/server/vfs.h index cb76f4b5bafe..06903024a2d8 100644 --- a/fs/smb/server/vfs.h +++ b/fs/smb/server/vfs.h @@ -43,6 +43,7 @@ struct ksmbd_dir_info { char *rptr; int name_len; int out_buf_len; + int num_scan; int num_entry; int data_count; int last_entry_offset; diff --git a/fs/udf/namei.c b/fs/udf/namei.c index 78a603129dd5..2cb49b6b0716 100644 --- a/fs/udf/namei.c +++ b/fs/udf/namei.c @@ -517,7 +517,11 @@ static int udf_rmdir(struct inode *dir, struct dentry *dentry) inode->i_nlink); clear_nlink(inode); inode->i_size = 0; - inode_dec_link_count(dir); + if (dir->i_nlink >= 3) + inode_dec_link_count(dir); + else + udf_warn(inode->i_sb, "parent dir link count too low (%u)\n", + dir->i_nlink); udf_add_fid_counter(dir->i_sb, true, -1); inode_set_mtime_to_ts(dir, inode_set_ctime_to_ts(dir, inode_set_ctime_current(inode))); @@ -787,8 +791,18 @@ static int udf_rename(struct mnt_idmap *idmap, struct inode *old_dir, retval = -ENOTEMPTY; if (!empty_dir(new_inode)) goto out_oiter; + retval = -EFSCORRUPTED; + if (new_inode->i_nlink != 2) + goto out_oiter; } + retval = -EFSCORRUPTED; + if (old_dir->i_nlink < 3) + goto out_oiter; is_dir = true; + } else if (new_inode) { + retval = -EFSCORRUPTED; + if (new_inode->i_nlink < 1) + goto out_oiter; } if (is_dir && old_dir != new_dir) { retval = udf_fiiter_find_entry(old_inode, &dotdot_name, diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c index a5c4af148853..134d87b3489a 100644 --- a/fs/xfs/libxfs/xfs_btree.c +++ b/fs/xfs/libxfs/xfs_btree.c @@ -3569,14 +3569,31 @@ xfs_btree_insrec( xfs_btree_log_block(cur, bp, XFS_BB_NUMRECS); /* - * If we just inserted into a new tree block, we have to - * recalculate nkey here because nkey is out of date. + * Update btree keys to reflect the newly added record or keyptr. + * There are three cases here to be aware of. Normally, all we have to + * do is walk towards the root, updating keys as necessary. * - * Otherwise we're just updating an existing block (having shoved - * some records into the new tree block), so use the regular key - * update mechanism. + * If the caller had us target a full block for the insertion, we dealt + * with that by calling the _make_block_unfull function. If the + * "make unfull" function splits the block, it'll hand us back the key + * and pointer of the new block. We haven't yet added the new block to + * the next level up, so if we decide to add the new record to the new + * block (bp->b_bn != old_bn), we have to update the caller's pointer + * so that the caller adds the new block with the correct key. + * + * However, there is a third possibility-- if the selected block is the + * root block of an inode-rooted btree and cannot be expanded further, + * the "make unfull" function moves the root block contents to a new + * block and updates the root block to point to the new block. In this + * case, no block pointer is passed back because the block has already + * been added to the btree. In this case, we need to use the regular + * key update function, just like the first case. This is critical for + * overlapping btrees, because the high key must be updated to reflect + * the entire tree, not just the subtree accessible through the first + * child of the root (which is now two levels down from the root). */ - if (bp && xfs_buf_daddr(bp) != old_bn) { + if (!xfs_btree_ptr_is_null(cur, &nptr) && + bp && xfs_buf_daddr(bp) != old_bn) { xfs_btree_get_keys(cur, block, lkey); } else if (xfs_btree_needs_key_update(cur, optr)) { error = xfs_btree_update_keys(cur, level); @@ -5156,7 +5173,7 @@ xfs_btree_count_blocks_helper( int level, void *data) { - xfs_extlen_t *blocks = data; + xfs_filblks_t *blocks = data; (*blocks)++; return 0; @@ -5166,7 +5183,7 @@ xfs_btree_count_blocks_helper( int xfs_btree_count_blocks( struct xfs_btree_cur *cur, - xfs_extlen_t *blocks) + xfs_filblks_t *blocks) { *blocks = 0; return xfs_btree_visit_blocks(cur, xfs_btree_count_blocks_helper, diff --git a/fs/xfs/libxfs/xfs_btree.h b/fs/xfs/libxfs/xfs_btree.h index 10b7ddc3b2b3..91e0b6dac31e 100644 --- a/fs/xfs/libxfs/xfs_btree.h +++ b/fs/xfs/libxfs/xfs_btree.h @@ -485,7 +485,7 @@ typedef int (*xfs_btree_visit_blocks_fn)(struct xfs_btree_cur *cur, int level, int xfs_btree_visit_blocks(struct xfs_btree_cur *cur, xfs_btree_visit_blocks_fn fn, unsigned int flags, void *data); -int xfs_btree_count_blocks(struct xfs_btree_cur *cur, xfs_extlen_t *blocks); +int xfs_btree_count_blocks(struct xfs_btree_cur *cur, xfs_filblks_t *blocks); union xfs_btree_rec *xfs_btree_rec_addr(struct xfs_btree_cur *cur, int n, struct xfs_btree_block *block); diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c index 271855227514..6258527315f2 100644 --- a/fs/xfs/libxfs/xfs_ialloc.c +++ b/fs/xfs/libxfs/xfs_ialloc.c @@ -855,7 +855,8 @@ sparse_alloc: * the end of the AG. */ args.min_agbno = args.mp->m_sb.sb_inoalignmt; - args.max_agbno = round_down(args.mp->m_sb.sb_agblocks, + args.max_agbno = round_down(xfs_ag_block_count(args.mp, + pag->pag_agno), args.mp->m_sb.sb_inoalignmt) - igeo->ialloc_blks; @@ -2332,9 +2333,9 @@ xfs_difree( return -EINVAL; } agbno = XFS_AGINO_TO_AGBNO(mp, agino); - if (agbno >= mp->m_sb.sb_agblocks) { - xfs_warn(mp, "%s: agbno >= mp->m_sb.sb_agblocks (%d >= %d).", - __func__, agbno, mp->m_sb.sb_agblocks); + if (agbno >= xfs_ag_block_count(mp, pag->pag_agno)) { + xfs_warn(mp, "%s: agbno >= xfs_ag_block_count (%d >= %d).", + __func__, agbno, xfs_ag_block_count(mp, pag->pag_agno)); ASSERT(0); return -EINVAL; } @@ -2457,7 +2458,7 @@ xfs_imap( */ agino = XFS_INO_TO_AGINO(mp, ino); agbno = XFS_AGINO_TO_AGBNO(mp, agino); - if (agbno >= mp->m_sb.sb_agblocks || + if (agbno >= xfs_ag_block_count(mp, pag->pag_agno) || ino != XFS_AGINO_TO_INO(mp, pag->pag_agno, agino)) { error = -EINVAL; #ifdef DEBUG @@ -2467,11 +2468,12 @@ xfs_imap( */ if (flags & XFS_IGET_UNTRUSTED) return error; - if (agbno >= mp->m_sb.sb_agblocks) { + if (agbno >= xfs_ag_block_count(mp, pag->pag_agno)) { xfs_alert(mp, "%s: agbno (0x%llx) >= mp->m_sb.sb_agblocks (0x%lx)", __func__, (unsigned long long)agbno, - (unsigned long)mp->m_sb.sb_agblocks); + (unsigned long)xfs_ag_block_count(mp, + pag->pag_agno)); } if (ino != XFS_AGINO_TO_INO(mp, pag->pag_agno, agino)) { xfs_alert(mp, diff --git a/fs/xfs/libxfs/xfs_ialloc_btree.c b/fs/xfs/libxfs/xfs_ialloc_btree.c index 401b42d52af6..6aa43f3fc68e 100644 --- a/fs/xfs/libxfs/xfs_ialloc_btree.c +++ b/fs/xfs/libxfs/xfs_ialloc_btree.c @@ -743,6 +743,7 @@ xfs_finobt_count_blocks( { struct xfs_buf *agbp = NULL; struct xfs_btree_cur *cur; + xfs_filblks_t blocks; int error; error = xfs_ialloc_read_agi(pag, tp, 0, &agbp); @@ -750,9 +751,10 @@ xfs_finobt_count_blocks( return error; cur = xfs_finobt_init_cursor(pag, tp, agbp); - error = xfs_btree_count_blocks(cur, tree_blocks); + error = xfs_btree_count_blocks(cur, &blocks); xfs_btree_del_cursor(cur, error); xfs_trans_brelse(tp, agbp); + *tree_blocks = blocks; return error; } diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c index 02ebcbc4882f..e27b63281d01 100644 --- a/fs/xfs/libxfs/xfs_sb.c +++ b/fs/xfs/libxfs/xfs_sb.c @@ -391,6 +391,21 @@ xfs_validate_sb_common( sbp->sb_inoalignmt, align); return -EINVAL; } + + if (sbp->sb_spino_align && + (sbp->sb_spino_align > sbp->sb_inoalignmt || + (sbp->sb_inoalignmt % sbp->sb_spino_align) != 0)) { + xfs_warn(mp, +"Sparse inode alignment (%u) is invalid, must be integer factor of (%u).", + sbp->sb_spino_align, + sbp->sb_inoalignmt); + return -EINVAL; + } + } else if (sbp->sb_spino_align) { + xfs_warn(mp, + "Sparse inode alignment (%u) should be zero.", + sbp->sb_spino_align); + return -EINVAL; } } else if (sbp->sb_qflags & (XFS_PQUOTA_ENFD | XFS_GQUOTA_ENFD | XFS_PQUOTA_CHKD | XFS_GQUOTA_CHKD)) { diff --git a/fs/xfs/libxfs/xfs_symlink_remote.c b/fs/xfs/libxfs/xfs_symlink_remote.c index f228127a88ff..fb47a76ead18 100644 --- a/fs/xfs/libxfs/xfs_symlink_remote.c +++ b/fs/xfs/libxfs/xfs_symlink_remote.c @@ -92,8 +92,10 @@ xfs_symlink_verify( struct xfs_mount *mp = bp->b_mount; struct xfs_dsymlink_hdr *dsl = bp->b_addr; + /* no verification of non-crc buffers */ if (!xfs_has_crc(mp)) - return __this_address; + return NULL; + if (!xfs_verify_magic(bp, dsl->sl_magic)) return __this_address; if (!uuid_equal(&dsl->sl_uuid, &mp->m_sb.sb_meta_uuid)) diff --git a/fs/xfs/scrub/agheader.c b/fs/xfs/scrub/agheader.c index f8e5b67128d2..0f2f1852d58f 100644 --- a/fs/xfs/scrub/agheader.c +++ b/fs/xfs/scrub/agheader.c @@ -60,6 +60,30 @@ xchk_superblock_xref( } /* + * Calculate the ondisk superblock size in bytes given the feature set of the + * mounted filesystem (aka the primary sb). This is subtlely different from + * the logic in xfs_repair, which computes the size of a secondary sb given the + * featureset listed in the secondary sb. + */ +STATIC size_t +xchk_superblock_ondisk_size( + struct xfs_mount *mp) +{ + if (xfs_has_metauuid(mp)) + return offsetofend(struct xfs_dsb, sb_meta_uuid); + if (xfs_has_crc(mp)) + return offsetofend(struct xfs_dsb, sb_lsn); + if (xfs_sb_version_hasmorebits(&mp->m_sb)) + return offsetofend(struct xfs_dsb, sb_bad_features2); + if (xfs_has_logv2(mp)) + return offsetofend(struct xfs_dsb, sb_logsunit); + if (xfs_has_sector(mp)) + return offsetofend(struct xfs_dsb, sb_logsectsize); + /* only support dirv2 or more recent */ + return offsetofend(struct xfs_dsb, sb_dirblklog); +} + +/* * Scrub the filesystem superblock. * * Note: We do /not/ attempt to check AG 0's superblock. Mount is @@ -75,6 +99,7 @@ xchk_superblock( struct xfs_buf *bp; struct xfs_dsb *sb; struct xfs_perag *pag; + size_t sblen; xfs_agnumber_t agno; uint32_t v2_ok; __be32 features_mask; @@ -350,8 +375,8 @@ xchk_superblock( } /* Everything else must be zero. */ - if (memchr_inv(sb + 1, 0, - BBTOB(bp->b_length) - sizeof(struct xfs_dsb))) + sblen = xchk_superblock_ondisk_size(mp); + if (memchr_inv((char *)sb + sblen, 0, BBTOB(bp->b_length) - sblen)) xchk_block_set_corrupt(sc, bp); xchk_superblock_xref(sc, bp); @@ -434,7 +459,7 @@ xchk_agf_xref_btreeblks( { struct xfs_agf *agf = sc->sa.agf_bp->b_addr; struct xfs_mount *mp = sc->mp; - xfs_agblock_t blocks; + xfs_filblks_t blocks; xfs_agblock_t btreeblks; int error; @@ -483,7 +508,7 @@ xchk_agf_xref_refcblks( struct xfs_scrub *sc) { struct xfs_agf *agf = sc->sa.agf_bp->b_addr; - xfs_agblock_t blocks; + xfs_filblks_t blocks; int error; if (!sc->sa.refc_cur) @@ -816,7 +841,7 @@ xchk_agi_xref_fiblocks( struct xfs_scrub *sc) { struct xfs_agi *agi = sc->sa.agi_bp->b_addr; - xfs_agblock_t blocks; + xfs_filblks_t blocks; int error = 0; if (!xfs_has_inobtcounts(sc->mp)) diff --git a/fs/xfs/scrub/agheader_repair.c b/fs/xfs/scrub/agheader_repair.c index 2f98d90d7fd6..69b003259784 100644 --- a/fs/xfs/scrub/agheader_repair.c +++ b/fs/xfs/scrub/agheader_repair.c @@ -256,7 +256,7 @@ xrep_agf_calc_from_btrees( struct xfs_agf *agf = agf_bp->b_addr; struct xfs_mount *mp = sc->mp; xfs_agblock_t btreeblks; - xfs_agblock_t blocks; + xfs_filblks_t blocks; int error; /* Update the AGF counters from the bnobt. */ @@ -946,7 +946,7 @@ xrep_agi_calc_from_btrees( if (error) goto err; if (xfs_has_inobtcounts(mp)) { - xfs_agblock_t blocks; + xfs_filblks_t blocks; error = xfs_btree_count_blocks(cur, &blocks); if (error) @@ -959,7 +959,7 @@ xrep_agi_calc_from_btrees( agi->agi_freecount = cpu_to_be32(freecount); if (xfs_has_finobt(mp) && xfs_has_inobtcounts(mp)) { - xfs_agblock_t blocks; + xfs_filblks_t blocks; cur = xfs_finobt_init_cursor(sc->sa.pag, sc->tp, agi_bp); error = xfs_btree_count_blocks(cur, &blocks); diff --git a/fs/xfs/scrub/fscounters.c b/fs/xfs/scrub/fscounters.c index 1d3e98346933..454f17595c9c 100644 --- a/fs/xfs/scrub/fscounters.c +++ b/fs/xfs/scrub/fscounters.c @@ -261,7 +261,7 @@ xchk_fscount_btreeblks( struct xchk_fscounters *fsc, xfs_agnumber_t agno) { - xfs_extlen_t blocks; + xfs_filblks_t blocks; int error; error = xchk_ag_init_existing(sc, agno, &sc->sa); diff --git a/fs/xfs/scrub/ialloc.c b/fs/xfs/scrub/ialloc.c index 750d7b0cd25a..a59c44e5903a 100644 --- a/fs/xfs/scrub/ialloc.c +++ b/fs/xfs/scrub/ialloc.c @@ -652,8 +652,8 @@ xchk_iallocbt_xref_rmap_btreeblks( struct xfs_scrub *sc) { xfs_filblks_t blocks; - xfs_extlen_t inobt_blocks = 0; - xfs_extlen_t finobt_blocks = 0; + xfs_filblks_t inobt_blocks = 0; + xfs_filblks_t finobt_blocks = 0; int error; if (!sc->sa.ino_cur || !sc->sa.rmap_cur || diff --git a/fs/xfs/scrub/refcount.c b/fs/xfs/scrub/refcount.c index d0c7d4a29c0f..cccf39d917a0 100644 --- a/fs/xfs/scrub/refcount.c +++ b/fs/xfs/scrub/refcount.c @@ -490,7 +490,7 @@ xchk_refcount_xref_rmap( struct xfs_scrub *sc, xfs_filblks_t cow_blocks) { - xfs_extlen_t refcbt_blocks = 0; + xfs_filblks_t refcbt_blocks = 0; xfs_filblks_t blocks; int error; diff --git a/fs/xfs/scrub/symlink_repair.c b/fs/xfs/scrub/symlink_repair.c index d015a86ef460..953ce7be78dc 100644 --- a/fs/xfs/scrub/symlink_repair.c +++ b/fs/xfs/scrub/symlink_repair.c @@ -36,6 +36,7 @@ #include "scrub/tempfile.h" #include "scrub/tempexch.h" #include "scrub/reap.h" +#include "scrub/health.h" /* * Symbolic Link Repair @@ -233,7 +234,7 @@ xrep_symlink_salvage( * target zapped flag. */ if (buflen == 0) { - sc->sick_mask |= XFS_SICK_INO_SYMLINK_ZAPPED; + xchk_mark_healthy_if_clean(sc, XFS_SICK_INO_SYMLINK_ZAPPED); sprintf(target_buf, DUMMY_TARGET); } diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h index c886d5d0eb02..da773fee8638 100644 --- a/fs/xfs/scrub/trace.h +++ b/fs/xfs/scrub/trace.h @@ -601,7 +601,7 @@ TRACE_EVENT(xchk_ifork_btree_op_error, TP_fast_assign( xfs_fsblock_t fsbno = xchk_btree_cur_fsbno(cur, level); __entry->dev = sc->mp->m_super->s_dev; - __entry->ino = sc->ip->i_ino; + __entry->ino = cur->bc_ino.ip->i_ino; __entry->whichfork = cur->bc_ino.whichfork; __entry->type = sc->sm->sm_type; __assign_str(name); diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c index edaf193dbd5c..95f8a09f96ae 100644 --- a/fs/xfs/xfs_bmap_util.c +++ b/fs/xfs/xfs_bmap_util.c @@ -111,7 +111,7 @@ xfs_bmap_count_blocks( struct xfs_mount *mp = ip->i_mount; struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork); struct xfs_btree_cur *cur; - xfs_extlen_t btblocks = 0; + xfs_filblks_t btblocks = 0; int error; *nextents = 0; diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index b19916b11fd5..aba54e3c5836 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -1228,6 +1228,14 @@ out_unlock: xfs_iunlock2_remapping(src, dest); if (ret) trace_xfs_reflink_remap_range_error(dest, ret, _RET_IP_); + /* + * If the caller did not set CAN_SHORTEN, then it is not prepared to + * handle partial results -- either the whole remap succeeds, or we + * must say why it did not. In this case, any error should be returned + * to the caller. + */ + if (ret && remapped < len && !(remap_flags & REMAP_FILE_CAN_SHORTEN)) + return ret; return remapped > 0 ? remapped : ret; } diff --git a/fs/xfs/xfs_fsmap.c b/fs/xfs/xfs_fsmap.c index ae18ab86e608..8712b891defb 100644 --- a/fs/xfs/xfs_fsmap.c +++ b/fs/xfs/xfs_fsmap.c @@ -162,7 +162,8 @@ struct xfs_getfsmap_info { xfs_daddr_t next_daddr; /* next daddr we expect */ /* daddr of low fsmap key when we're using the rtbitmap */ xfs_daddr_t low_daddr; - xfs_daddr_t end_daddr; /* daddr of high fsmap key */ + /* daddr of high fsmap key, or the last daddr on the device */ + xfs_daddr_t end_daddr; u64 missing_owner; /* owner of holes */ u32 dev; /* device id */ /* @@ -306,7 +307,7 @@ xfs_getfsmap_helper( * Note that if the btree query found a mapping, there won't be a gap. */ if (info->last && info->end_daddr != XFS_BUF_DADDR_NULL) - rec_daddr = info->end_daddr; + rec_daddr = info->end_daddr + 1; /* Are we just counting mappings? */ if (info->head->fmh_count == 0) { @@ -898,7 +899,10 @@ xfs_getfsmap( struct xfs_trans *tp = NULL; struct xfs_fsmap dkeys[2]; /* per-dev keys */ struct xfs_getfsmap_dev handlers[XFS_GETFSMAP_DEVS]; - struct xfs_getfsmap_info info = { NULL }; + struct xfs_getfsmap_info info = { + .fsmap_recs = fsmap_recs, + .head = head, + }; bool use_rmap; int i; int error = 0; @@ -963,9 +967,6 @@ xfs_getfsmap( info.next_daddr = head->fmh_keys[0].fmr_physical + head->fmh_keys[0].fmr_length; - info.end_daddr = XFS_BUF_DADDR_NULL; - info.fsmap_recs = fsmap_recs; - info.head = head; /* For each device we support... */ for (i = 0; i < XFS_GETFSMAP_DEVS; i++) { @@ -978,17 +979,23 @@ xfs_getfsmap( break; /* - * If this device number matches the high key, we have - * to pass the high key to the handler to limit the - * query results. If the device number exceeds the - * low key, zero out the low key so that we get - * everything from the beginning. + * If this device number matches the high key, we have to pass + * the high key to the handler to limit the query results, and + * set the end_daddr so that we can synthesize records at the + * end of the query range or device. */ if (handlers[i].dev == head->fmh_keys[1].fmr_device) { dkeys[1] = head->fmh_keys[1]; info.end_daddr = min(handlers[i].nr_sectors - 1, dkeys[1].fmr_physical); + } else { + info.end_daddr = handlers[i].nr_sectors - 1; } + + /* + * If the device number exceeds the low key, zero out the low + * key so that we get everything from the beginning. + */ if (handlers[i].dev > head->fmh_keys[0].fmr_device) memset(&dkeys[0], 0, sizeof(struct xfs_fsmap)); diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c index 3a2005a1e673..8caa55b81674 100644 --- a/fs/xfs/xfs_rtalloc.c +++ b/fs/xfs/xfs_rtalloc.c @@ -1295,7 +1295,7 @@ xfs_rtallocate( * For an allocation to an empty file at offset 0, pick an extent that * will space things out in the rt area. */ - if (bno_hint) + if (bno_hint != NULLFSBLOCK) start = xfs_rtb_to_rtx(args.mp, bno_hint); else if (initial_user_data) start = xfs_rtpick_extent(args.mp, tp, maxlen); diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c index bdf3704dc301..30e03342287a 100644 --- a/fs/xfs/xfs_trans.c +++ b/fs/xfs/xfs_trans.c @@ -834,13 +834,6 @@ __xfs_trans_commit( trace_xfs_trans_commit(tp, _RET_IP_); - error = xfs_trans_run_precommits(tp); - if (error) { - if (tp->t_flags & XFS_TRANS_PERM_LOG_RES) - xfs_defer_cancel(tp); - goto out_unreserve; - } - /* * Finish deferred items on final commit. Only permanent transactions * should ever have deferred ops. @@ -851,13 +844,12 @@ __xfs_trans_commit( error = xfs_defer_finish_noroll(&tp); if (error) goto out_unreserve; - - /* Run precommits from final tx in defer chain. */ - error = xfs_trans_run_precommits(tp); - if (error) - goto out_unreserve; } + error = xfs_trans_run_precommits(tp); + if (error) + goto out_unreserve; + /* * If there is nothing to be logged by the transaction, * then unlock all of the items associated with the @@ -1382,5 +1374,8 @@ done: out_cancel: xfs_trans_cancel(tp); + xfs_iunlock(dp, XFS_ILOCK_EXCL); + if (dp != ip) + xfs_iunlock(ip, XFS_ILOCK_EXCL); return error; } diff --git a/include/clocksource/hyperv_timer.h b/include/clocksource/hyperv_timer.h index 6cdc873ac907..aa5233b1eba9 100644 --- a/include/clocksource/hyperv_timer.h +++ b/include/clocksource/hyperv_timer.h @@ -38,6 +38,8 @@ extern void hv_remap_tsc_clocksource(void); extern unsigned long hv_get_tsc_pfn(void); extern struct ms_hyperv_tsc_page *hv_get_tsc_page(void); +extern void hv_adj_sched_clock_offset(u64 offset); + static __always_inline bool hv_read_tsc_page_tsc(const struct ms_hyperv_tsc_page *tsc_pg, u64 *cur_tsc, u64 *time) diff --git a/include/linux/alloc_tag.h b/include/linux/alloc_tag.h index 941deffc590d..6073a8f13c41 100644 --- a/include/linux/alloc_tag.h +++ b/include/linux/alloc_tag.h @@ -48,7 +48,12 @@ static inline void set_codetag_empty(union codetag_ref *ref) #else /* CONFIG_MEM_ALLOC_PROFILING_DEBUG */ static inline bool is_codetag_empty(union codetag_ref *ref) { return false; } -static inline void set_codetag_empty(union codetag_ref *ref) {} + +static inline void set_codetag_empty(union codetag_ref *ref) +{ + if (ref) + ref->ct = NULL; +} #endif /* CONFIG_MEM_ALLOC_PROFILING_DEBUG */ diff --git a/include/linux/arm_ffa.h b/include/linux/arm_ffa.h index a28e2a6a13d0..74169dd0f659 100644 --- a/include/linux/arm_ffa.h +++ b/include/linux/arm_ffa.h @@ -166,9 +166,12 @@ static inline void *ffa_dev_get_drvdata(struct ffa_device *fdev) return dev_get_drvdata(&fdev->dev); } +struct ffa_partition_info; + #if IS_REACHABLE(CONFIG_ARM_FFA_TRANSPORT) -struct ffa_device *ffa_device_register(const uuid_t *uuid, int vm_id, - const struct ffa_ops *ops); +struct ffa_device * +ffa_device_register(const struct ffa_partition_info *part_info, + const struct ffa_ops *ops); void ffa_device_unregister(struct ffa_device *ffa_dev); int ffa_driver_register(struct ffa_driver *driver, struct module *owner, const char *mod_name); @@ -176,9 +179,9 @@ void ffa_driver_unregister(struct ffa_driver *driver); bool ffa_device_is_valid(struct ffa_device *ffa_dev); #else -static inline -struct ffa_device *ffa_device_register(const uuid_t *uuid, int vm_id, - const struct ffa_ops *ops) +static inline struct ffa_device * +ffa_device_register(const struct ffa_partition_info *part_info, + const struct ffa_ops *ops) { return NULL; } diff --git a/include/linux/bio.h b/include/linux/bio.h index faceadb040f9..66b7620a1b53 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -677,6 +677,23 @@ static inline void bio_clear_polled(struct bio *bio) bio->bi_opf &= ~REQ_POLLED; } +/** + * bio_is_zone_append - is this a zone append bio? + * @bio: bio to check + * + * Check if @bio is a zone append operation. Core block layer code and end_io + * handlers must use this instead of an open coded REQ_OP_ZONE_APPEND check + * because the block layer can rewrite REQ_OP_ZONE_APPEND to REQ_OP_WRITE if + * it is not natively supported. + */ +static inline bool bio_is_zone_append(struct bio *bio) +{ + if (!IS_ENABLED(CONFIG_BLK_DEV_ZONED)) + return false; + return bio_op(bio) == REQ_OP_ZONE_APPEND || + bio_flagged(bio, BIO_EMULATES_ZONE_APPEND); +} + struct bio *blk_next_bio(struct bio *bio, struct block_device *bdev, unsigned int nr_pages, blk_opf_t opf, gfp_t gfp); struct bio *bio_chain_and_submit(struct bio *prev, struct bio *new); diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 6b4bc85f4999..b7f327ce797e 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -200,8 +200,6 @@ struct gendisk { spinlock_t zone_wplugs_lock; struct mempool_s *zone_wplugs_pool; struct hlist_head *zone_wplugs_hash; - struct list_head zone_wplugs_err_list; - struct work_struct zone_wplugs_work; struct workqueue_struct *zone_wplugs_wq; #endif /* CONFIG_BLK_DEV_ZONED */ @@ -1386,6 +1384,9 @@ static inline bool bdev_is_zone_start(struct block_device *bdev, return bdev_offset_from_zone_start(bdev, sector) == 0; } +int blk_zone_issue_zeroout(struct block_device *bdev, sector_t sector, + sector_t nr_sects, gfp_t gfp_mask); + static inline int queue_dma_alignment(const struct request_queue *q) { return q->limits.dma_alignment; diff --git a/include/linux/bpf.h b/include/linux/bpf.h index cbe235091246..a7af13f550e0 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -2157,26 +2157,25 @@ bpf_prog_run_array(const struct bpf_prog_array *array, * rcu-protected dynamically sized maps. */ static __always_inline u32 -bpf_prog_run_array_uprobe(const struct bpf_prog_array __rcu *array_rcu, +bpf_prog_run_array_uprobe(const struct bpf_prog_array *array, const void *ctx, bpf_prog_run_fn run_prog) { const struct bpf_prog_array_item *item; const struct bpf_prog *prog; - const struct bpf_prog_array *array; struct bpf_run_ctx *old_run_ctx; struct bpf_trace_run_ctx run_ctx; u32 ret = 1; might_fault(); + RCU_LOCKDEP_WARN(!rcu_read_lock_trace_held(), "no rcu lock held"); + + if (unlikely(!array)) + return ret; - rcu_read_lock_trace(); migrate_disable(); run_ctx.is_uprobe = true; - array = rcu_dereference_check(array_rcu, rcu_read_lock_trace_held()); - if (unlikely(!array)) - goto out; old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx); item = &array->items[0]; while ((prog = READ_ONCE(item->prog))) { @@ -2191,9 +2190,7 @@ bpf_prog_run_array_uprobe(const struct bpf_prog_array __rcu *array_rcu, rcu_read_unlock(); } bpf_reset_run_ctx(old_run_ctx); -out: migrate_enable(); - rcu_read_unlock_trace(); return ret; } @@ -3471,10 +3468,4 @@ static inline bool bpf_is_subprog(const struct bpf_prog *prog) return prog->aux->func_idx != 0; } -static inline bool bpf_prog_is_raw_tp(const struct bpf_prog *prog) -{ - return prog->type == BPF_PROG_TYPE_TRACING && - prog->expected_attach_type == BPF_TRACE_RAW_TP; -} - #endif /* _LINUX_BPF_H */ diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 4d4e23b6e3e7..2d962dade9fa 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -216,28 +216,43 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, #endif /* __KERNEL__ */ +/** + * offset_to_ptr - convert a relative memory offset to an absolute pointer + * @off: the address of the 32-bit offset value + */ +static inline void *offset_to_ptr(const int *off) +{ + return (void *)((unsigned long)off + *off); +} + +#endif /* __ASSEMBLY__ */ + +#ifdef CONFIG_64BIT +#define ARCH_SEL(a,b) a +#else +#define ARCH_SEL(a,b) b +#endif + /* * Force the compiler to emit 'sym' as a symbol, so that we can reference * it from inline assembler. Necessary in case 'sym' could be inlined * otherwise, or eliminated entirely due to lack of references that are * visible to the compiler. */ -#define ___ADDRESSABLE(sym, __attrs) \ - static void * __used __attrs \ +#define ___ADDRESSABLE(sym, __attrs) \ + static void * __used __attrs \ __UNIQUE_ID(__PASTE(__addressable_,sym)) = (void *)(uintptr_t)&sym; + #define __ADDRESSABLE(sym) \ ___ADDRESSABLE(sym, __section(".discard.addressable")) -/** - * offset_to_ptr - convert a relative memory offset to an absolute pointer - * @off: the address of the 32-bit offset value - */ -static inline void *offset_to_ptr(const int *off) -{ - return (void *)((unsigned long)off + *off); -} +#define __ADDRESSABLE_ASM(sym) \ + .pushsection .discard.addressable,"aw"; \ + .align ARCH_SEL(8,4); \ + ARCH_SEL(.quad, .long) __stringify(sym); \ + .popsection; -#endif /* __ASSEMBLY__ */ +#define __ADDRESSABLE_ASM_STR(sym) __stringify(__ADDRESSABLE_ASM(sym)) /* &a[0] degrades to a pointer: a different type from an array */ #define __must_be_array(a) BUILD_BUG_ON_ZERO(__same_type((a), &(a)[0])) diff --git a/include/linux/dsa/ocelot.h b/include/linux/dsa/ocelot.h index 6fbfbde68a37..620a3260fc08 100644 --- a/include/linux/dsa/ocelot.h +++ b/include/linux/dsa/ocelot.h @@ -15,6 +15,7 @@ struct ocelot_skb_cb { struct sk_buff *clone; unsigned int ptp_class; /* valid only for clones */ + unsigned long ptp_tx_time; /* valid only for clones */ u32 tstamp_lo; u8 ptp_cmd; u8 ts_id; diff --git a/include/linux/filter.h b/include/linux/filter.h index 7d7578a8eac1..5118caf8aa1c 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -1121,7 +1121,7 @@ bool bpf_jit_supports_arena(void); bool bpf_jit_supports_insn(struct bpf_insn *insn, bool in_arena); u64 bpf_arch_uaddress_limit(void); void arch_bpf_stack_walk(bool (*consume_fn)(void *cookie, u64 ip, u64 sp, u64 bp), void *cookie); -bool bpf_helper_changes_pkt_data(void *func); +bool bpf_helper_changes_pkt_data(enum bpf_func_id func_id); static inline bool bpf_dump_raw_ok(const struct cred *cred) { diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 22c22fb91042..02a226bcf0ed 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -1559,6 +1559,7 @@ struct hv_util_service { void *channel; void (*util_cb)(void *); int (*util_init)(struct hv_util_service *); + int (*util_init_transport)(void); void (*util_deinit)(void); int (*util_pre_suspend)(void); int (*util_pre_resume)(void); diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index c1645c86eed9..d65b5d71b93b 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -585,13 +585,16 @@ static inline int vlan_get_tag(const struct sk_buff *skb, u16 *vlan_tci) * vlan_get_protocol - get protocol EtherType. * @skb: skbuff to query * @type: first vlan protocol + * @mac_offset: MAC offset * @depth: buffer to store length of eth and vlan tags in bytes * * Returns the EtherType of the packet, regardless of whether it is * vlan encapsulated (normal or hardware accelerated) or not. */ -static inline __be16 __vlan_get_protocol(const struct sk_buff *skb, __be16 type, - int *depth) +static inline __be16 __vlan_get_protocol_offset(const struct sk_buff *skb, + __be16 type, + int mac_offset, + int *depth) { unsigned int vlan_depth = skb->mac_len, parse_depth = VLAN_MAX_DEPTH; @@ -610,7 +613,8 @@ static inline __be16 __vlan_get_protocol(const struct sk_buff *skb, __be16 type, do { struct vlan_hdr vhdr, *vh; - vh = skb_header_pointer(skb, vlan_depth, sizeof(vhdr), &vhdr); + vh = skb_header_pointer(skb, mac_offset + vlan_depth, + sizeof(vhdr), &vhdr); if (unlikely(!vh || !--parse_depth)) return 0; @@ -625,6 +629,12 @@ static inline __be16 __vlan_get_protocol(const struct sk_buff *skb, __be16 type, return type; } +static inline __be16 __vlan_get_protocol(const struct sk_buff *skb, __be16 type, + int *depth) +{ + return __vlan_get_protocol_offset(skb, type, 0, depth); +} + /** * vlan_get_protocol - get protocol EtherType. * @skb: skbuff to query diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h index e123d5e17b52..85fe4e6b275c 100644 --- a/include/linux/io_uring.h +++ b/include/linux/io_uring.h @@ -15,10 +15,8 @@ bool io_is_uring_fops(struct file *file); static inline void io_uring_files_cancel(void) { - if (current->io_uring) { - io_uring_unreg_ringfd(); + if (current->io_uring) __io_uring_cancel(false); - } } static inline void io_uring_task_cancel(void) { diff --git a/include/linux/memfd.h b/include/linux/memfd.h index 3f2cf339ceaf..d437e3070850 100644 --- a/include/linux/memfd.h +++ b/include/linux/memfd.h @@ -7,6 +7,7 @@ #ifdef CONFIG_MEMFD_CREATE extern long memfd_fcntl(struct file *file, unsigned int cmd, unsigned int arg); struct folio *memfd_alloc_folio(struct file *memfd, pgoff_t idx); +unsigned int *memfd_file_seals_ptr(struct file *file); #else static inline long memfd_fcntl(struct file *f, unsigned int c, unsigned int a) { @@ -16,6 +17,19 @@ static inline struct folio *memfd_alloc_folio(struct file *memfd, pgoff_t idx) { return ERR_PTR(-EINVAL); } + +static inline unsigned int *memfd_file_seals_ptr(struct file *file) +{ + return NULL; +} #endif +/* Retrieve memfd seals associated with the file, if any. */ +static inline unsigned int memfd_file_seals(struct file *file) +{ + unsigned int *sealsp = memfd_file_seals_ptr(file); + + return sealsp ? *sealsp : 0; +} + #endif /* __LINUX_MEMFD_H */ diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index e23c692a34c7..82c7056e2759 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -555,6 +555,7 @@ enum { * creation/deletion on drivers rescan. Unset during device attach. */ MLX5_PRIV_FLAGS_DETACH = 1 << 2, + MLX5_PRIV_FLAGS_SWITCH_LEGACY = 1 << 3, }; struct mlx5_adev { @@ -1233,6 +1234,12 @@ static inline bool mlx5_core_is_vf(const struct mlx5_core_dev *dev) return dev->coredev_type == MLX5_COREDEV_VF; } +static inline bool mlx5_core_same_coredev_type(const struct mlx5_core_dev *dev1, + const struct mlx5_core_dev *dev2) +{ + return dev1->coredev_type == dev2->coredev_type; +} + static inline bool mlx5_core_is_ecpf(const struct mlx5_core_dev *dev) { return dev->caps.embedded_cpu; diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 96d369112bfa..512e25c416ae 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -2113,7 +2113,9 @@ struct mlx5_ifc_cmd_hca_cap_2_bits { u8 migration_in_chunks[0x1]; u8 reserved_at_d1[0x1]; u8 sf_eq_usage[0x1]; - u8 reserved_at_d3[0xd]; + u8 reserved_at_d3[0x5]; + u8 multiplane[0x1]; + u8 reserved_at_d9[0x7]; u8 cross_vhca_object_to_object_supported[0x20]; diff --git a/include/linux/mm.h b/include/linux/mm.h index 61fff5d34ed5..8617adc6becd 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3100,6 +3100,7 @@ static inline bool pagetable_pmd_ctor(struct ptdesc *ptdesc) if (!pmd_ptlock_init(ptdesc)) return false; __folio_set_pgtable(folio); + ptdesc_pmd_pts_init(ptdesc); lruvec_stat_add_folio(folio, NR_PAGETABLE); return true; } @@ -4079,6 +4080,37 @@ void mem_dump_obj(void *object); static inline void mem_dump_obj(void *object) {} #endif +static inline bool is_write_sealed(int seals) +{ + return seals & (F_SEAL_WRITE | F_SEAL_FUTURE_WRITE); +} + +/** + * is_readonly_sealed - Checks whether write-sealed but mapped read-only, + * in which case writes should be disallowing moving + * forwards. + * @seals: the seals to check + * @vm_flags: the VMA flags to check + * + * Returns whether readonly sealed, in which case writess should be disallowed + * going forward. + */ +static inline bool is_readonly_sealed(int seals, vm_flags_t vm_flags) +{ + /* + * Since an F_SEAL_[FUTURE_]WRITE sealed memfd can be mapped as + * MAP_SHARED and read-only, take care to not allow mprotect to + * revert protections on such mappings. Do this only for shared + * mappings. For private mappings, don't need to mask + * VM_MAYWRITE as we still want them to be COW-writable. + */ + if (is_write_sealed(seals) && + ((vm_flags & (VM_SHARED | VM_WRITE)) == VM_SHARED)) + return true; + + return false; +} + /** * seal_check_write - Check for F_SEAL_WRITE or F_SEAL_FUTURE_WRITE flags and * handle them. @@ -4090,24 +4122,15 @@ static inline void mem_dump_obj(void *object) {} */ static inline int seal_check_write(int seals, struct vm_area_struct *vma) { - if (seals & (F_SEAL_WRITE | F_SEAL_FUTURE_WRITE)) { - /* - * New PROT_WRITE and MAP_SHARED mmaps are not allowed when - * write seals are active. - */ - if ((vma->vm_flags & VM_SHARED) && (vma->vm_flags & VM_WRITE)) - return -EPERM; - - /* - * Since an F_SEAL_[FUTURE_]WRITE sealed memfd can be mapped as - * MAP_SHARED and read-only, take care to not allow mprotect to - * revert protections on such mappings. Do this only for shared - * mappings. For private mappings, don't need to mask - * VM_MAYWRITE as we still want them to be COW-writable. - */ - if (vma->vm_flags & VM_SHARED) - vm_flags_clear(vma, VM_MAYWRITE); - } + if (!is_write_sealed(seals)) + return 0; + + /* + * New PROT_WRITE and MAP_SHARED mmaps are not allowed when + * write seals are active. + */ + if ((vma->vm_flags & VM_SHARED) && (vma->vm_flags & VM_WRITE)) + return -EPERM; return 0; } diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 6e3bdf8e38bc..6894de506b36 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -445,6 +445,7 @@ FOLIO_MATCH(compound_head, _head_2a); * @pt_index: Used for s390 gmap. * @pt_mm: Used for x86 pgds. * @pt_frag_refcount: For fragmented page table tracking. Powerpc only. + * @pt_share_count: Used for HugeTLB PMD page table share count. * @_pt_pad_2: Padding to ensure proper alignment. * @ptl: Lock for the page table. * @__page_type: Same as page->page_type. Unused for page tables. @@ -471,6 +472,9 @@ struct ptdesc { pgoff_t pt_index; struct mm_struct *pt_mm; atomic_t pt_frag_refcount; +#ifdef CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING + atomic_t pt_share_count; +#endif }; union { @@ -516,6 +520,32 @@ static_assert(sizeof(struct ptdesc) <= sizeof(struct page)); const struct page *: (const struct ptdesc *)(p), \ struct page *: (struct ptdesc *)(p))) +#ifdef CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING +static inline void ptdesc_pmd_pts_init(struct ptdesc *ptdesc) +{ + atomic_set(&ptdesc->pt_share_count, 0); +} + +static inline void ptdesc_pmd_pts_inc(struct ptdesc *ptdesc) +{ + atomic_inc(&ptdesc->pt_share_count); +} + +static inline void ptdesc_pmd_pts_dec(struct ptdesc *ptdesc) +{ + atomic_dec(&ptdesc->pt_share_count); +} + +static inline int ptdesc_pmd_pts_count(struct ptdesc *ptdesc) +{ + return atomic_read(&ptdesc->pt_share_count); +} +#else +static inline void ptdesc_pmd_pts_init(struct ptdesc *ptdesc) +{ +} +#endif + /* * Used for sizing the vmemmap region on some architectures */ diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h index 66e7d26b70a4..11be70a7929f 100644 --- a/include/linux/netdev_features.h +++ b/include/linux/netdev_features.h @@ -253,4 +253,11 @@ static inline int find_next_netdev_feature(u64 feature, unsigned long start) NETIF_F_GSO_UDP_TUNNEL | \ NETIF_F_GSO_UDP_TUNNEL_CSUM) +static inline netdev_features_t netdev_base_features(netdev_features_t features) +{ + features &= ~NETIF_F_ONE_FOR_ALL; + features |= NETIF_F_ALL_FOR_ALL; + return features; +} + #endif /* _LINUX_NETDEV_FEATURES_H */ diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 74aa9fbbdae7..48c66b846682 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -860,18 +860,10 @@ static inline void ClearPageCompound(struct page *page) ClearPageHead(page); } FOLIO_FLAG(large_rmappable, FOLIO_SECOND_PAGE) -FOLIO_TEST_FLAG(partially_mapped, FOLIO_SECOND_PAGE) -/* - * PG_partially_mapped is protected by deferred_split split_queue_lock, - * so its safe to use non-atomic set/clear. - */ -__FOLIO_SET_FLAG(partially_mapped, FOLIO_SECOND_PAGE) -__FOLIO_CLEAR_FLAG(partially_mapped, FOLIO_SECOND_PAGE) +FOLIO_FLAG(partially_mapped, FOLIO_SECOND_PAGE) #else FOLIO_FLAG_FALSE(large_rmappable) -FOLIO_TEST_FLAG_FALSE(partially_mapped) -__FOLIO_SET_FLAG_NOOP(partially_mapped) -__FOLIO_CLEAR_FLAG_NOOP(partially_mapped) +FOLIO_FLAG_FALSE(partially_mapped) #endif #define PG_head_mask ((1UL << PG_head)) diff --git a/include/linux/platform_data/amd_qdma.h b/include/linux/platform_data/amd_qdma.h index 576d952f97ed..967a6ef31cf9 100644 --- a/include/linux/platform_data/amd_qdma.h +++ b/include/linux/platform_data/amd_qdma.h @@ -26,11 +26,13 @@ struct dma_slave_map; * @max_mm_channels: Maximum number of MM DMA channels in each direction * @device_map: DMA slave map * @irq_index: The index of first IRQ + * @dma_dev: The device pointer for dma operations */ struct qdma_platdata { u32 max_mm_channels; u32 irq_index; struct dma_slave_map *device_map; + struct device *dma_dev; }; #endif /* _PLATDATA_AMD_QDMA_H */ diff --git a/include/linux/sched.h b/include/linux/sched.h index bb343136ddd0..02eaf84c8626 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -656,6 +656,12 @@ struct sched_dl_entity { * @dl_defer_armed tells if the deferrable server is waiting * for the replenishment timer to activate it. * + * @dl_server_active tells if the dlserver is active(started). + * dlserver is started on first cfs enqueue on an idle runqueue + * and is stopped when a dequeue results in 0 cfs tasks on the + * runqueue. In other words, dlserver is active only when cpu's + * runqueue has atleast one cfs task. + * * @dl_defer_running tells if the deferrable server is actually * running, skipping the defer phase. */ @@ -664,6 +670,7 @@ struct sched_dl_entity { unsigned int dl_non_contending : 1; unsigned int dl_overrun : 1; unsigned int dl_server : 1; + unsigned int dl_server_active : 1; unsigned int dl_defer : 1; unsigned int dl_defer_armed : 1; unsigned int dl_defer_running : 1; @@ -1626,8 +1633,9 @@ static inline unsigned int __task_state_index(unsigned int tsk_state, * We're lying here, but rather than expose a completely new task state * to userspace, we can make this appear as if the task has gone through * a regular rt_mutex_lock() call. + * Report frozen tasks as uninterruptible. */ - if (tsk_state & TASK_RTLOCK_WAIT) + if ((tsk_state & TASK_RTLOCK_WAIT) || (tsk_state & TASK_FROZEN)) state = TASK_UNINTERRUPTIBLE; return fls(state); diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index d9b03e0746e7..2cbe0c22a32f 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -317,17 +317,22 @@ static inline void sock_drop(struct sock *sk, struct sk_buff *skb) kfree_skb(skb); } -static inline void sk_psock_queue_msg(struct sk_psock *psock, +static inline bool sk_psock_queue_msg(struct sk_psock *psock, struct sk_msg *msg) { + bool ret; + spin_lock_bh(&psock->ingress_lock); - if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) + if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) { list_add_tail(&msg->list, &psock->ingress_msg); - else { + ret = true; + } else { sk_msg_free(psock->sk, msg); kfree(msg); + ret = false; } spin_unlock_bh(&psock->ingress_lock); + return ret; } static inline struct sk_msg *sk_psock_dequeue_msg(struct sk_psock *psock) diff --git a/include/linux/static_call.h b/include/linux/static_call.h index 141e6b176a1b..78a77a4ae0ea 100644 --- a/include/linux/static_call.h +++ b/include/linux/static_call.h @@ -160,6 +160,8 @@ extern void arch_static_call_transform(void *site, void *tramp, void *func, bool #ifdef CONFIG_HAVE_STATIC_CALL_INLINE +extern int static_call_initialized; + extern int __init static_call_init(void); extern void static_call_force_reinit(void); @@ -225,6 +227,8 @@ extern long __static_call_return0(void); #elif defined(CONFIG_HAVE_STATIC_CALL) +#define static_call_initialized 0 + static inline int static_call_init(void) { return 0; } #define DEFINE_STATIC_CALL(name, _func) \ @@ -281,6 +285,8 @@ extern long __static_call_return0(void); #else /* Generic implementation */ +#define static_call_initialized 0 + static inline int static_call_init(void) { return 0; } static inline long __static_call_return0(void) diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 42bedcddd511..77769ff50544 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -285,7 +285,8 @@ struct trace_event_fields { const char *name; const int size; const int align; - const int is_signed; + const unsigned int is_signed:1; + unsigned int needs_test:1; const int filter_type; const int len; }; @@ -337,6 +338,7 @@ enum { TRACE_EVENT_FL_EPROBE_BIT, TRACE_EVENT_FL_FPROBE_BIT, TRACE_EVENT_FL_CUSTOM_BIT, + TRACE_EVENT_FL_TEST_STR_BIT, }; /* @@ -354,6 +356,7 @@ enum { * CUSTOM - Event is a custom event (to be attached to an exsiting tracepoint) * This is set when the custom event has not been attached * to a tracepoint yet, then it is cleared when it is. + * TEST_STR - The event has a "%s" that points to a string outside the event */ enum { TRACE_EVENT_FL_FILTERED = (1 << TRACE_EVENT_FL_FILTERED_BIT), @@ -367,6 +370,7 @@ enum { TRACE_EVENT_FL_EPROBE = (1 << TRACE_EVENT_FL_EPROBE_BIT), TRACE_EVENT_FL_FPROBE = (1 << TRACE_EVENT_FL_FPROBE_BIT), TRACE_EVENT_FL_CUSTOM = (1 << TRACE_EVENT_FL_CUSTOM_BIT), + TRACE_EVENT_FL_TEST_STR = (1 << TRACE_EVENT_FL_TEST_STR_BIT), }; #define TRACE_EVENT_FL_UKPROBE (TRACE_EVENT_FL_KPROBE | TRACE_EVENT_FL_UPROBE) @@ -375,7 +379,7 @@ struct trace_event_call { struct list_head list; struct trace_event_class *class; union { - char *name; + const char *name; /* Set TRACE_EVENT_FL_TRACEPOINT flag when using "tp" */ struct tracepoint *tp; }; diff --git a/include/linux/virtio.h b/include/linux/virtio.h index 306137a15d07..73c8922e69e0 100644 --- a/include/linux/virtio.h +++ b/include/linux/virtio.h @@ -100,7 +100,8 @@ dma_addr_t virtqueue_get_avail_addr(const struct virtqueue *vq); dma_addr_t virtqueue_get_used_addr(const struct virtqueue *vq); int virtqueue_resize(struct virtqueue *vq, u32 num, - void (*recycle)(struct virtqueue *vq, void *buf)); + void (*recycle)(struct virtqueue *vq, void *buf), + void (*recycle_done)(struct virtqueue *vq)); int virtqueue_reset(struct virtqueue *vq, void (*recycle)(struct virtqueue *vq, void *buf)); diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index d2761bf8ff32..9f3a04345b86 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -515,7 +515,7 @@ static inline const char *node_stat_name(enum node_stat_item item) static inline const char *lru_list_name(enum lru_list lru) { - return node_stat_name(NR_LRU_BASE + lru) + 3; // skip "nr_" + return node_stat_name(NR_LRU_BASE + (enum node_stat_item)lru) + 3; // skip "nr_" } #if defined(CONFIG_VM_EVENT_COUNTERS) || defined(CONFIG_MEMCG) diff --git a/include/linux/wait.h b/include/linux/wait.h index 8aa3372f21a0..2b322a9b88a2 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -221,6 +221,7 @@ void __wake_up_pollfree(struct wait_queue_head *wq_head); #define wake_up_all(x) __wake_up(x, TASK_NORMAL, 0, NULL) #define wake_up_locked(x) __wake_up_locked((x), TASK_NORMAL, 1) #define wake_up_all_locked(x) __wake_up_locked((x), TASK_NORMAL, 0) +#define wake_up_sync(x) __wake_up_sync(x, TASK_NORMAL) #define wake_up_interruptible(x) __wake_up(x, TASK_INTERRUPTIBLE, 1, NULL) #define wake_up_interruptible_nr(x, nr) __wake_up(x, TASK_INTERRUPTIBLE, nr, NULL) diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h index f66bc85c6411..435250c72d56 100644 --- a/include/net/bluetooth/bluetooth.h +++ b/include/net/bluetooth/bluetooth.h @@ -123,6 +123,7 @@ struct bt_voice { #define BT_VOICE_TRANSPARENT 0x0003 #define BT_VOICE_CVSD_16BIT 0x0060 +#define BT_VOICE_TRANSPARENT_16BIT 0x0063 #define BT_SNDMTU 12 #define BT_RCVMTU 13 @@ -590,15 +591,6 @@ static inline struct sk_buff *bt_skb_sendmmsg(struct sock *sk, return skb; } -static inline int bt_copy_from_sockptr(void *dst, size_t dst_size, - sockptr_t src, size_t src_size) -{ - if (dst_size > src_size) - return -EINVAL; - - return copy_from_sockptr(dst, src, dst_size); -} - int bt_to_errno(u16 code); __u8 bt_status(int err); diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index c95f7e6ba255..ba7b52584770 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -804,7 +804,6 @@ struct hci_conn_params { extern struct list_head hci_dev_list; extern struct list_head hci_cb_list; extern rwlock_t hci_dev_list_lock; -extern struct mutex hci_cb_list_lock; #define hci_dev_set_flag(hdev, nr) set_bit((nr), (hdev)->dev_flags) #define hci_dev_clear_flag(hdev, nr) clear_bit((nr), (hdev)->dev_flags) @@ -2007,24 +2006,47 @@ struct hci_cb { char *name; + bool (*match) (struct hci_conn *conn); void (*connect_cfm) (struct hci_conn *conn, __u8 status); void (*disconn_cfm) (struct hci_conn *conn, __u8 status); void (*security_cfm) (struct hci_conn *conn, __u8 status, - __u8 encrypt); + __u8 encrypt); void (*key_change_cfm) (struct hci_conn *conn, __u8 status); void (*role_switch_cfm) (struct hci_conn *conn, __u8 status, __u8 role); }; +static inline void hci_cb_lookup(struct hci_conn *conn, struct list_head *list) +{ + struct hci_cb *cb, *cpy; + + rcu_read_lock(); + list_for_each_entry_rcu(cb, &hci_cb_list, list) { + if (cb->match && cb->match(conn)) { + cpy = kmalloc(sizeof(*cpy), GFP_ATOMIC); + if (!cpy) + break; + + *cpy = *cb; + INIT_LIST_HEAD(&cpy->list); + list_add_rcu(&cpy->list, list); + } + } + rcu_read_unlock(); +} + static inline void hci_connect_cfm(struct hci_conn *conn, __u8 status) { - struct hci_cb *cb; + struct list_head list; + struct hci_cb *cb, *tmp; + + INIT_LIST_HEAD(&list); + hci_cb_lookup(conn, &list); - mutex_lock(&hci_cb_list_lock); - list_for_each_entry(cb, &hci_cb_list, list) { + list_for_each_entry_safe(cb, tmp, &list, list) { if (cb->connect_cfm) cb->connect_cfm(conn, status); + kfree(cb); } - mutex_unlock(&hci_cb_list_lock); if (conn->connect_cfm_cb) conn->connect_cfm_cb(conn, status); @@ -2032,43 +2054,55 @@ static inline void hci_connect_cfm(struct hci_conn *conn, __u8 status) static inline void hci_disconn_cfm(struct hci_conn *conn, __u8 reason) { - struct hci_cb *cb; + struct list_head list; + struct hci_cb *cb, *tmp; + + INIT_LIST_HEAD(&list); + hci_cb_lookup(conn, &list); - mutex_lock(&hci_cb_list_lock); - list_for_each_entry(cb, &hci_cb_list, list) { + list_for_each_entry_safe(cb, tmp, &list, list) { if (cb->disconn_cfm) cb->disconn_cfm(conn, reason); + kfree(cb); } - mutex_unlock(&hci_cb_list_lock); if (conn->disconn_cfm_cb) conn->disconn_cfm_cb(conn, reason); } -static inline void hci_auth_cfm(struct hci_conn *conn, __u8 status) +static inline void hci_security_cfm(struct hci_conn *conn, __u8 status, + __u8 encrypt) { - struct hci_cb *cb; - __u8 encrypt; - - if (test_bit(HCI_CONN_ENCRYPT_PEND, &conn->flags)) - return; + struct list_head list; + struct hci_cb *cb, *tmp; - encrypt = test_bit(HCI_CONN_ENCRYPT, &conn->flags) ? 0x01 : 0x00; + INIT_LIST_HEAD(&list); + hci_cb_lookup(conn, &list); - mutex_lock(&hci_cb_list_lock); - list_for_each_entry(cb, &hci_cb_list, list) { + list_for_each_entry_safe(cb, tmp, &list, list) { if (cb->security_cfm) cb->security_cfm(conn, status, encrypt); + kfree(cb); } - mutex_unlock(&hci_cb_list_lock); if (conn->security_cfm_cb) conn->security_cfm_cb(conn, status); } +static inline void hci_auth_cfm(struct hci_conn *conn, __u8 status) +{ + __u8 encrypt; + + if (test_bit(HCI_CONN_ENCRYPT_PEND, &conn->flags)) + return; + + encrypt = test_bit(HCI_CONN_ENCRYPT, &conn->flags) ? 0x01 : 0x00; + + hci_security_cfm(conn, status, encrypt); +} + static inline void hci_encrypt_cfm(struct hci_conn *conn, __u8 status) { - struct hci_cb *cb; __u8 encrypt; if (conn->state == BT_CONFIG) { @@ -2095,40 +2129,38 @@ static inline void hci_encrypt_cfm(struct hci_conn *conn, __u8 status) conn->sec_level = conn->pending_sec_level; } - mutex_lock(&hci_cb_list_lock); - list_for_each_entry(cb, &hci_cb_list, list) { - if (cb->security_cfm) - cb->security_cfm(conn, status, encrypt); - } - mutex_unlock(&hci_cb_list_lock); - - if (conn->security_cfm_cb) - conn->security_cfm_cb(conn, status); + hci_security_cfm(conn, status, encrypt); } static inline void hci_key_change_cfm(struct hci_conn *conn, __u8 status) { - struct hci_cb *cb; + struct list_head list; + struct hci_cb *cb, *tmp; + + INIT_LIST_HEAD(&list); + hci_cb_lookup(conn, &list); - mutex_lock(&hci_cb_list_lock); - list_for_each_entry(cb, &hci_cb_list, list) { + list_for_each_entry_safe(cb, tmp, &list, list) { if (cb->key_change_cfm) cb->key_change_cfm(conn, status); + kfree(cb); } - mutex_unlock(&hci_cb_list_lock); } static inline void hci_role_switch_cfm(struct hci_conn *conn, __u8 status, __u8 role) { - struct hci_cb *cb; + struct list_head list; + struct hci_cb *cb, *tmp; + + INIT_LIST_HEAD(&list); + hci_cb_lookup(conn, &list); - mutex_lock(&hci_cb_list_lock); - list_for_each_entry(cb, &hci_cb_list, list) { + list_for_each_entry_safe(cb, tmp, &list, list) { if (cb->role_switch_cfm) cb->role_switch_cfm(conn, status, role); + kfree(cb); } - mutex_unlock(&hci_cb_list_lock); } static inline bool hci_bdaddr_is_rpa(bdaddr_t *bdaddr, u8 addr_type) diff --git a/include/net/lapb.h b/include/net/lapb.h index 124ee122f2c8..6c07420644e4 100644 --- a/include/net/lapb.h +++ b/include/net/lapb.h @@ -4,7 +4,7 @@ #include <linux/lapb.h> #include <linux/refcount.h> -#define LAPB_HEADER_LEN 20 /* LAPB over Ethernet + a bit more */ +#define LAPB_HEADER_LEN MAX_HEADER /* LAPB over Ethernet + a bit more */ #define LAPB_ACK_PENDING_CONDITION 0x01 #define LAPB_REJECT_CONDITION 0x02 diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 333e0fae6796..5b712582f9a9 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -6770,14 +6770,12 @@ void ieee80211_chswitch_done(struct ieee80211_vif *vif, bool success, /** * ieee80211_channel_switch_disconnect - disconnect due to channel switch error * @vif: &struct ieee80211_vif pointer from the add_interface callback. - * @block_tx: if %true, do not send deauth frame. * * Instruct mac80211 to disconnect due to a channel switch error. The channel * switch can request to block the tx and so, we need to make sure we do not send * a deauth frame in this case. */ -void ieee80211_channel_switch_disconnect(struct ieee80211_vif *vif, - bool block_tx); +void ieee80211_channel_switch_disconnect(struct ieee80211_vif *vif); /** * ieee80211_request_smps - request SM PS transition diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index e67b483cc8bb..9398c8f49953 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -80,6 +80,7 @@ struct net { * or to unregister pernet ops * (pernet_ops_rwsem write locked). */ + struct llist_node defer_free_list; struct llist_node cleanup_list; /* namespaces on death row */ #ifdef CONFIG_KEYS diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 066a3ea33b12..471c353d32a4 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -733,15 +733,18 @@ struct nft_set_ext_tmpl { /** * struct nft_set_ext - set extensions * - * @genmask: generation mask + * @genmask: generation mask, but also flags (see NFT_SET_ELEM_DEAD_BIT) * @offset: offsets of individual extension types * @data: beginning of extension data + * + * This structure must be aligned to word size, otherwise atomic bitops + * on genmask field can cause alignment failure on some archs. */ struct nft_set_ext { u8 genmask; u8 offset[NFT_SET_EXT_NUM]; char data[]; -}; +} __aligned(BITS_PER_LONG / 8); static inline void nft_set_ext_prepare(struct nft_set_ext_tmpl *tmpl) { @@ -1103,7 +1106,6 @@ struct nft_rule_blob { * @name: name of the chain * @udlen: user data length * @udata: user data in the chain - * @rcu_head: rcu head for deferred release * @blob_next: rule blob pointer to the next in the chain */ struct nft_chain { @@ -1121,7 +1123,6 @@ struct nft_chain { char *name; u16 udlen; u8 *udata; - struct rcu_head rcu_head; /* Only used during control plane commit phase: */ struct nft_rule_blob *blob_next; @@ -1265,7 +1266,6 @@ static inline void nft_use_inc_restore(u32 *use) * @sets: sets in the table * @objects: stateful objects in the table * @flowtables: flow tables in the table - * @net: netnamespace this table belongs to * @hgenerator: handle generator state * @handle: table handle * @use: number of chain references to this table @@ -1285,7 +1285,6 @@ struct nft_table { struct list_head sets; struct list_head objects; struct list_head flowtables; - possible_net_t net; u64 hgenerator; u64 handle; u32 use; diff --git a/include/net/sock.h b/include/net/sock.h index f29c14448938..fa055cf1785e 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1521,7 +1521,7 @@ static inline bool sk_wmem_schedule(struct sock *sk, int size) } static inline bool -sk_rmem_schedule(struct sock *sk, struct sk_buff *skb, int size) +__sk_rmem_schedule(struct sock *sk, int size, bool pfmemalloc) { int delta; @@ -1529,7 +1529,13 @@ sk_rmem_schedule(struct sock *sk, struct sk_buff *skb, int size) return true; delta = size - sk->sk_forward_alloc; return delta <= 0 || __sk_mem_schedule(sk, delta, SK_MEM_RECV) || - skb_pfmemalloc(skb); + pfmemalloc; +} + +static inline bool +sk_rmem_schedule(struct sock *sk, struct sk_buff *skb, int size) +{ + return __sk_rmem_schedule(sk, size, skb_pfmemalloc(skb)); } static inline int sk_unused_reserved_mem(const struct sock *sk) diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index 462c653e1017..2db9ae0575b6 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -778,7 +778,6 @@ struct ocelot_port { phy_interface_t phy_mode; - unsigned int ptp_skbs_in_flight; struct sk_buff_head tx_skbs; unsigned int trap_proto; @@ -786,7 +785,6 @@ struct ocelot_port { u16 mrp_ring_id; u8 ptp_cmd; - u8 ts_id; u8 index; diff --git a/include/sound/cs35l56.h b/include/sound/cs35l56.h index 94e8185c4795..3dc7a1551ac3 100644 --- a/include/sound/cs35l56.h +++ b/include/sound/cs35l56.h @@ -271,12 +271,6 @@ struct cs35l56_base { struct gpio_desc *reset_gpio; }; -/* Temporary to avoid a build break with the HDA driver */ -static inline int cs35l56_force_sync_asp1_registers_from_cache(struct cs35l56_base *cs35l56_base) -{ - return 0; -} - static inline bool cs35l56_is_otp_register(unsigned int reg) { return (reg >> 16) == 3; diff --git a/include/uapi/linux/stddef.h b/include/uapi/linux/stddef.h index 58154117d9b0..a6fce46aeb37 100644 --- a/include/uapi/linux/stddef.h +++ b/include/uapi/linux/stddef.h @@ -8,6 +8,13 @@ #define __always_inline inline #endif +/* Not all C++ standards support type declarations inside an anonymous union */ +#ifndef __cplusplus +#define __struct_group_tag(TAG) TAG +#else +#define __struct_group_tag(TAG) +#endif + /** * __struct_group() - Create a mirrored named and anonyomous struct * @@ -20,13 +27,13 @@ * and size: one anonymous and one named. The former's members can be used * normally without sub-struct naming, and the latter can be used to * reason about the start, end, and size of the group of struct members. - * The named struct can also be explicitly tagged for layer reuse, as well - * as both having struct attributes appended. + * The named struct can also be explicitly tagged for layer reuse (C only), + * as well as both having struct attributes appended. */ #define __struct_group(TAG, NAME, ATTRS, MEMBERS...) \ union { \ struct { MEMBERS } ATTRS; \ - struct TAG { MEMBERS } ATTRS NAME; \ + struct __struct_group_tag(TAG) { MEMBERS } ATTRS NAME; \ } ATTRS #ifdef __cplusplus diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index b2736e3491b8..9849da128364 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -515,7 +515,11 @@ static void io_queue_iowq(struct io_kiocb *req) struct io_uring_task *tctx = req->task->io_uring; BUG_ON(!tctx); - BUG_ON(!tctx->io_wq); + + if ((current->flags & PF_KTHREAD) || !tctx->io_wq) { + io_req_task_queue_fail(req, -ECANCELED); + return; + } /* init ->work of the whole link before punting */ io_prep_async_link(req); @@ -3230,6 +3234,7 @@ end_wait: void __io_uring_cancel(bool cancel_all) { + io_uring_unreg_ringfd(); io_uring_cancel_generic(cancel_all, NULL); } diff --git a/io_uring/kbuf.c b/io_uring/kbuf.c index d407576ddfb7..eec5eb7de843 100644 --- a/io_uring/kbuf.c +++ b/io_uring/kbuf.c @@ -139,6 +139,7 @@ static void __user *io_ring_buffer_select(struct io_kiocb *req, size_t *len, struct io_uring_buf_ring *br = bl->buf_ring; __u16 tail, head = bl->head; struct io_uring_buf *buf; + void __user *ret; tail = smp_load_acquire(&br->tail); if (unlikely(tail == head)) @@ -153,6 +154,7 @@ static void __user *io_ring_buffer_select(struct io_kiocb *req, size_t *len, req->flags |= REQ_F_BUFFER_RING | REQ_F_BUFFERS_COMMIT; req->buf_list = bl; req->buf_index = buf->bid; + ret = u64_to_user_ptr(buf->addr); if (issue_flags & IO_URING_F_UNLOCKED || !io_file_can_poll(req)) { /* @@ -168,7 +170,7 @@ static void __user *io_ring_buffer_select(struct io_kiocb *req, size_t *len, io_kbuf_commit(req, bl, *len, 1); req->buf_list = NULL; } - return u64_to_user_ptr(buf->addr); + return ret; } void __user *io_buffer_select(struct io_kiocb *req, size_t *len, diff --git a/io_uring/net.c b/io_uring/net.c index 18507658a921..7f549be9abd1 100644 --- a/io_uring/net.c +++ b/io_uring/net.c @@ -748,6 +748,7 @@ static int io_recvmsg_prep_setup(struct io_kiocb *req) if (req->opcode == IORING_OP_RECV) { kmsg->msg.msg_name = NULL; kmsg->msg.msg_namelen = 0; + kmsg->msg.msg_inq = 0; kmsg->msg.msg_control = NULL; kmsg->msg.msg_get_inq = 1; kmsg->msg.msg_controllen = 0; diff --git a/io_uring/rw.c b/io_uring/rw.c index 155938f10093..39ad25d16ed4 100644 --- a/io_uring/rw.c +++ b/io_uring/rw.c @@ -979,6 +979,8 @@ int io_read_mshot(struct io_kiocb *req, unsigned int issue_flags) io_kbuf_recycle(req, issue_flags); if (ret < 0) req_set_fail(req); + } else if (!(req->flags & REQ_F_APOLL_MULTISHOT)) { + cflags = io_put_kbuf(req, ret, issue_flags); } else { /* * Any successful return value will keep the multishot read diff --git a/io_uring/sqpoll.c b/io_uring/sqpoll.c index a26593979887..1cfcc735b8e3 100644 --- a/io_uring/sqpoll.c +++ b/io_uring/sqpoll.c @@ -412,6 +412,7 @@ void io_sqpoll_wait_sq(struct io_ring_ctx *ctx) __cold int io_sq_offload_create(struct io_ring_ctx *ctx, struct io_uring_params *p) { + struct task_struct *task_to_put = NULL; int ret; /* Retain compatibility with failing for an invalid attach attempt */ @@ -492,6 +493,7 @@ __cold int io_sq_offload_create(struct io_ring_ctx *ctx, } sqd->thread = tsk; + task_to_put = get_task_struct(tsk); ret = io_uring_alloc_task_context(tsk, ctx); wake_up_new_task(tsk); if (ret) @@ -502,11 +504,15 @@ __cold int io_sq_offload_create(struct io_ring_ctx *ctx, goto err; } + if (task_to_put) + put_task_struct(task_to_put); return 0; err_sqpoll: complete(&ctx->sq_data->exited); err: io_sq_thread_finish(ctx); + if (task_to_put) + put_task_struct(task_to_put); return ret; } diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 346826e3c933..41d20b7199c4 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -6415,6 +6415,101 @@ int btf_ctx_arg_offset(const struct btf *btf, const struct btf_type *func_proto, return off; } +struct bpf_raw_tp_null_args { + const char *func; + u64 mask; +}; + +static const struct bpf_raw_tp_null_args raw_tp_null_args[] = { + /* sched */ + { "sched_pi_setprio", 0x10 }, + /* ... from sched_numa_pair_template event class */ + { "sched_stick_numa", 0x100 }, + { "sched_swap_numa", 0x100 }, + /* afs */ + { "afs_make_fs_call", 0x10 }, + { "afs_make_fs_calli", 0x10 }, + { "afs_make_fs_call1", 0x10 }, + { "afs_make_fs_call2", 0x10 }, + { "afs_protocol_error", 0x1 }, + { "afs_flock_ev", 0x10 }, + /* cachefiles */ + { "cachefiles_lookup", 0x1 | 0x200 }, + { "cachefiles_unlink", 0x1 }, + { "cachefiles_rename", 0x1 }, + { "cachefiles_prep_read", 0x1 }, + { "cachefiles_mark_active", 0x1 }, + { "cachefiles_mark_failed", 0x1 }, + { "cachefiles_mark_inactive", 0x1 }, + { "cachefiles_vfs_error", 0x1 }, + { "cachefiles_io_error", 0x1 }, + { "cachefiles_ondemand_open", 0x1 }, + { "cachefiles_ondemand_copen", 0x1 }, + { "cachefiles_ondemand_close", 0x1 }, + { "cachefiles_ondemand_read", 0x1 }, + { "cachefiles_ondemand_cread", 0x1 }, + { "cachefiles_ondemand_fd_write", 0x1 }, + { "cachefiles_ondemand_fd_release", 0x1 }, + /* ext4, from ext4__mballoc event class */ + { "ext4_mballoc_discard", 0x10 }, + { "ext4_mballoc_free", 0x10 }, + /* fib */ + { "fib_table_lookup", 0x100 }, + /* filelock */ + /* ... from filelock_lock event class */ + { "posix_lock_inode", 0x10 }, + { "fcntl_setlk", 0x10 }, + { "locks_remove_posix", 0x10 }, + { "flock_lock_inode", 0x10 }, + /* ... from filelock_lease event class */ + { "break_lease_noblock", 0x10 }, + { "break_lease_block", 0x10 }, + { "break_lease_unblock", 0x10 }, + { "generic_delete_lease", 0x10 }, + { "time_out_leases", 0x10 }, + /* host1x */ + { "host1x_cdma_push_gather", 0x10000 }, + /* huge_memory */ + { "mm_khugepaged_scan_pmd", 0x10 }, + { "mm_collapse_huge_page_isolate", 0x1 }, + { "mm_khugepaged_scan_file", 0x10 }, + { "mm_khugepaged_collapse_file", 0x10 }, + /* kmem */ + { "mm_page_alloc", 0x1 }, + { "mm_page_pcpu_drain", 0x1 }, + /* .. from mm_page event class */ + { "mm_page_alloc_zone_locked", 0x1 }, + /* netfs */ + { "netfs_failure", 0x10 }, + /* power */ + { "device_pm_callback_start", 0x10 }, + /* qdisc */ + { "qdisc_dequeue", 0x1000 }, + /* rxrpc */ + { "rxrpc_recvdata", 0x1 }, + { "rxrpc_resend", 0x10 }, + /* sunrpc */ + { "xs_stream_read_data", 0x1 }, + /* ... from xprt_cong_event event class */ + { "xprt_reserve_cong", 0x10 }, + { "xprt_release_cong", 0x10 }, + { "xprt_get_cong", 0x10 }, + { "xprt_put_cong", 0x10 }, + /* tcp */ + { "tcp_send_reset", 0x11 }, + /* tegra_apb_dma */ + { "tegra_dma_tx_status", 0x100 }, + /* timer_migration */ + { "tmigr_update_events", 0x1 }, + /* writeback, from writeback_folio_template event class */ + { "writeback_dirty_folio", 0x10 }, + { "folio_wait_writeback", 0x10 }, + /* rdma */ + { "mr_integ_alloc", 0x2000 }, + /* bpf_testmod */ + { "bpf_testmod_test_read", 0x0 }, +}; + bool btf_ctx_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) @@ -6425,6 +6520,7 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type, const char *tname = prog->aux->attach_func_name; struct bpf_verifier_log *log = info->log; const struct btf_param *args; + bool ptr_err_raw_tp = false; const char *tag_value; u32 nr_args, arg; int i, ret; @@ -6519,6 +6615,12 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type, return false; } + if (size != sizeof(u64)) { + bpf_log(log, "func '%s' size %d must be 8\n", + tname, size); + return false; + } + /* check for PTR_TO_RDONLY_BUF_OR_NULL or PTR_TO_RDWR_BUF_OR_NULL */ for (i = 0; i < prog->aux->ctx_arg_info_size; i++) { const struct bpf_ctx_arg_aux *ctx_arg_info = &prog->aux->ctx_arg_info[i]; @@ -6564,12 +6666,42 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type, if (prog_args_trusted(prog)) info->reg_type |= PTR_TRUSTED; - /* Raw tracepoint arguments always get marked as maybe NULL */ - if (bpf_prog_is_raw_tp(prog)) - info->reg_type |= PTR_MAYBE_NULL; - else if (btf_param_match_suffix(btf, &args[arg], "__nullable")) + if (btf_param_match_suffix(btf, &args[arg], "__nullable")) info->reg_type |= PTR_MAYBE_NULL; + if (prog->expected_attach_type == BPF_TRACE_RAW_TP) { + struct btf *btf = prog->aux->attach_btf; + const struct btf_type *t; + const char *tname; + + /* BTF lookups cannot fail, return false on error */ + t = btf_type_by_id(btf, prog->aux->attach_btf_id); + if (!t) + return false; + tname = btf_name_by_offset(btf, t->name_off); + if (!tname) + return false; + /* Checked by bpf_check_attach_target */ + tname += sizeof("btf_trace_") - 1; + for (i = 0; i < ARRAY_SIZE(raw_tp_null_args); i++) { + /* Is this a func with potential NULL args? */ + if (strcmp(tname, raw_tp_null_args[i].func)) + continue; + if (raw_tp_null_args[i].mask & (0x1 << (arg * 4))) + info->reg_type |= PTR_MAYBE_NULL; + /* Is the current arg IS_ERR? */ + if (raw_tp_null_args[i].mask & (0x2 << (arg * 4))) + ptr_err_raw_tp = true; + break; + } + /* If we don't know NULL-ness specification and the tracepoint + * is coming from a loadable module, be conservative and mark + * argument as PTR_MAYBE_NULL. + */ + if (i == ARRAY_SIZE(raw_tp_null_args) && btf_is_module(btf)) + info->reg_type |= PTR_MAYBE_NULL; + } + if (tgt_prog) { enum bpf_prog_type tgt_type; @@ -6614,6 +6746,15 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type, bpf_log(log, "func '%s' arg%d has btf_id %d type %s '%s'\n", tname, arg, info->btf_id, btf_type_str(t), __btf_name_by_offset(btf, t->name_off)); + + /* Perform all checks on the validity of type for this argument, but if + * we know it can be IS_ERR at runtime, scrub pointer type and mark as + * scalar. + */ + if (ptr_err_raw_tp) { + bpf_log(log, "marking pointer arg%d as scalar as it may encode error", arg); + info->reg_type = SCALAR_VALUE; + } return true; } EXPORT_SYMBOL_GPL(btf_ctx_access); diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 233ea78f8f1b..2b9c8c168a0b 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -539,6 +539,8 @@ struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off, int bpf_remove_insns(struct bpf_prog *prog, u32 off, u32 cnt) { + int err; + /* Branch offsets can't overflow when program is shrinking, no need * to call bpf_adj_branches(..., true) here */ @@ -546,7 +548,9 @@ int bpf_remove_insns(struct bpf_prog *prog, u32 off, u32 cnt) sizeof(struct bpf_insn) * (prog->len - off - cnt)); prog->len -= cnt; - return WARN_ON_ONCE(bpf_adj_branches(prog, off, off + cnt, off, false)); + err = bpf_adj_branches(prog, off, off + cnt, off, false); + WARN_ON_ONCE(err); + return err; } static void bpf_prog_kallsyms_del_subprogs(struct bpf_prog *fp) @@ -2936,7 +2940,7 @@ void __weak bpf_jit_compile(struct bpf_prog *prog) { } -bool __weak bpf_helper_changes_pkt_data(void *func) +bool __weak bpf_helper_changes_pkt_data(enum bpf_func_id func_id) { return false; } diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index b2008076df9c..a0cab0d0252f 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -418,25 +418,6 @@ static struct btf_record *reg_btf_record(const struct bpf_reg_state *reg) return rec; } -static bool mask_raw_tp_reg_cond(const struct bpf_verifier_env *env, struct bpf_reg_state *reg) { - return reg->type == (PTR_TO_BTF_ID | PTR_TRUSTED | PTR_MAYBE_NULL) && - bpf_prog_is_raw_tp(env->prog) && !reg->ref_obj_id; -} - -static bool mask_raw_tp_reg(const struct bpf_verifier_env *env, struct bpf_reg_state *reg) -{ - if (!mask_raw_tp_reg_cond(env, reg)) - return false; - reg->type &= ~PTR_MAYBE_NULL; - return true; -} - -static void unmask_raw_tp_reg(struct bpf_reg_state *reg, bool result) -{ - if (result) - reg->type |= PTR_MAYBE_NULL; -} - static bool subprog_is_global(const struct bpf_verifier_env *env, int subprog) { struct bpf_func_info_aux *aux = env->prog->aux->func_info_aux; @@ -6618,7 +6599,6 @@ static int check_ptr_to_btf_access(struct bpf_verifier_env *env, const char *field_name = NULL; enum bpf_type_flag flag = 0; u32 btf_id = 0; - bool mask; int ret; if (!env->allow_ptr_leaks) { @@ -6690,21 +6670,7 @@ static int check_ptr_to_btf_access(struct bpf_verifier_env *env, if (ret < 0) return ret; - /* For raw_tp progs, we allow dereference of PTR_MAYBE_NULL - * trusted PTR_TO_BTF_ID, these are the ones that are possibly - * arguments to the raw_tp. Since internal checks in for trusted - * reg in check_ptr_to_btf_access would consider PTR_MAYBE_NULL - * modifier as problematic, mask it out temporarily for the - * check. Don't apply this to pointers with ref_obj_id > 0, as - * those won't be raw_tp args. - * - * We may end up applying this relaxation to other trusted - * PTR_TO_BTF_ID with maybe null flag, since we cannot - * distinguish PTR_MAYBE_NULL tagged for arguments vs normal - * tagging, but that should expand allowed behavior, and not - * cause regression for existing behavior. - */ - mask = mask_raw_tp_reg(env, reg); + if (ret != PTR_TO_BTF_ID) { /* just mark; */ @@ -6765,13 +6731,8 @@ static int check_ptr_to_btf_access(struct bpf_verifier_env *env, clear_trusted_flags(&flag); } - if (atype == BPF_READ && value_regno >= 0) { + if (atype == BPF_READ && value_regno >= 0) mark_btf_ld_reg(env, regs, value_regno, ret, reg->btf, btf_id, flag); - /* We've assigned a new type to regno, so don't undo masking. */ - if (regno == value_regno) - mask = false; - } - unmask_raw_tp_reg(reg, mask); return 0; } @@ -7146,7 +7107,7 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn if (!err && t == BPF_READ && value_regno >= 0) mark_reg_unknown(env, regs, value_regno); } else if (base_type(reg->type) == PTR_TO_BTF_ID && - (mask_raw_tp_reg_cond(env, reg) || !type_may_be_null(reg->type))) { + !type_may_be_null(reg->type)) { err = check_ptr_to_btf_access(env, regs, regno, off, size, t, value_regno); } else if (reg->type == CONST_PTR_TO_MAP) { @@ -7907,7 +7868,7 @@ static int process_dynptr_func(struct bpf_verifier_env *env, int regno, int insn if (reg->type != PTR_TO_STACK && reg->type != CONST_PTR_TO_DYNPTR) { verbose(env, "arg#%d expected pointer to stack or const struct bpf_dynptr\n", - regno); + regno - 1); return -EINVAL; } @@ -7961,7 +7922,7 @@ static int process_dynptr_func(struct bpf_verifier_env *env, int regno, int insn if (!is_dynptr_reg_valid_init(env, reg)) { verbose(env, "Expected an initialized dynptr as arg #%d\n", - regno); + regno - 1); return -EINVAL; } @@ -7969,7 +7930,7 @@ static int process_dynptr_func(struct bpf_verifier_env *env, int regno, int insn if (!is_dynptr_type_expected(env, reg, arg_type & ~MEM_RDONLY)) { verbose(env, "Expected a dynptr of type %s as arg #%d\n", - dynptr_type_str(arg_to_dynptr_type(arg_type)), regno); + dynptr_type_str(arg_to_dynptr_type(arg_type)), regno - 1); return -EINVAL; } @@ -8038,7 +7999,7 @@ static int process_iter_arg(struct bpf_verifier_env *env, int regno, int insn_id */ btf_id = btf_check_iter_arg(meta->btf, meta->func_proto, regno - 1); if (btf_id < 0) { - verbose(env, "expected valid iter pointer as arg #%d\n", regno); + verbose(env, "expected valid iter pointer as arg #%d\n", regno - 1); return -EINVAL; } t = btf_type_by_id(meta->btf, btf_id); @@ -8048,7 +8009,7 @@ static int process_iter_arg(struct bpf_verifier_env *env, int regno, int insn_id /* bpf_iter_<type>_new() expects pointer to uninit iter state */ if (!is_iter_reg_valid_uninit(env, reg, nr_slots)) { verbose(env, "expected uninitialized iter_%s as arg #%d\n", - iter_type_str(meta->btf, btf_id), regno); + iter_type_str(meta->btf, btf_id), regno - 1); return -EINVAL; } @@ -8072,7 +8033,7 @@ static int process_iter_arg(struct bpf_verifier_env *env, int regno, int insn_id break; case -EINVAL: verbose(env, "expected an initialized iter_%s as arg #%d\n", - iter_type_str(meta->btf, btf_id), regno); + iter_type_str(meta->btf, btf_id), regno - 1); return err; case -EPROTO: verbose(env, "expected an RCU CS when using %s\n", meta->func_name); @@ -8844,7 +8805,6 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 arg, enum bpf_reg_type type = reg->type; u32 *arg_btf_id = NULL; int err = 0; - bool mask; if (arg_type == ARG_DONTCARE) return 0; @@ -8885,11 +8845,11 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 arg, base_type(arg_type) == ARG_PTR_TO_SPIN_LOCK) arg_btf_id = fn->arg_btf_id[arg]; - mask = mask_raw_tp_reg(env, reg); err = check_reg_type(env, regno, arg_type, arg_btf_id, meta); + if (err) + return err; - err = err ?: check_func_arg_reg_off(env, reg, regno, arg_type); - unmask_raw_tp_reg(reg, mask); + err = check_func_arg_reg_off(env, reg, regno, arg_type); if (err) return err; @@ -9684,17 +9644,14 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env, int subprog, return ret; } else if (base_type(arg->arg_type) == ARG_PTR_TO_BTF_ID) { struct bpf_call_arg_meta meta; - bool mask; int err; if (register_is_null(reg) && type_may_be_null(arg->arg_type)) continue; memset(&meta, 0, sizeof(meta)); /* leave func_id as zero */ - mask = mask_raw_tp_reg(env, reg); err = check_reg_type(env, regno, arg->arg_type, &arg->btf_id, &meta); err = err ?: check_func_arg_reg_off(env, reg, regno, arg->arg_type); - unmask_raw_tp_reg(reg, mask); if (err) return err; } else { @@ -10519,7 +10476,7 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn } /* With LD_ABS/IND some JITs save/restore skb from r1. */ - changes_data = bpf_helper_changes_pkt_data(fn->func); + changes_data = bpf_helper_changes_pkt_data(func_id); if (changes_data && fn->arg1_type != ARG_PTR_TO_CTX) { verbose(env, "kernel subsystem misconfigured func %s#%d: r1 != ctx\n", func_id_name(func_id), func_id); @@ -12009,7 +11966,6 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_ enum bpf_arg_type arg_type = ARG_DONTCARE; u32 regno = i + 1, ref_id, type_size; bool is_ret_buf_sz = false; - bool mask = false; int kf_arg_type; t = btf_type_skip_modifiers(btf, args[i].type, NULL); @@ -12068,15 +12024,12 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_ return -EINVAL; } - mask = mask_raw_tp_reg(env, reg); if ((is_kfunc_trusted_args(meta) || is_kfunc_rcu(meta)) && (register_is_null(reg) || type_may_be_null(reg->type)) && !is_kfunc_arg_nullable(meta->btf, &args[i])) { verbose(env, "Possibly NULL pointer passed to trusted arg%d\n", i); - unmask_raw_tp_reg(reg, mask); return -EACCES; } - unmask_raw_tp_reg(reg, mask); if (reg->ref_obj_id) { if (is_kfunc_release(meta) && meta->ref_obj_id) { @@ -12134,24 +12087,16 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_ if (!is_kfunc_trusted_args(meta) && !is_kfunc_rcu(meta)) break; - /* Allow passing maybe NULL raw_tp arguments to - * kfuncs for compatibility. Don't apply this to - * arguments with ref_obj_id > 0. - */ - mask = mask_raw_tp_reg(env, reg); if (!is_trusted_reg(reg)) { if (!is_kfunc_rcu(meta)) { verbose(env, "R%d must be referenced or trusted\n", regno); - unmask_raw_tp_reg(reg, mask); return -EINVAL; } if (!is_rcu_reg(reg)) { verbose(env, "R%d must be a rcu pointer\n", regno); - unmask_raw_tp_reg(reg, mask); return -EINVAL; } } - unmask_raw_tp_reg(reg, mask); fallthrough; case KF_ARG_PTR_TO_CTX: case KF_ARG_PTR_TO_DYNPTR: @@ -12174,9 +12119,7 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_ if (is_kfunc_release(meta) && reg->ref_obj_id) arg_type |= OBJ_RELEASE; - mask = mask_raw_tp_reg(env, reg); ret = check_func_arg_reg_off(env, reg, regno, arg_type); - unmask_raw_tp_reg(reg, mask); if (ret < 0) return ret; @@ -12353,7 +12296,6 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_ ref_tname = btf_name_by_offset(btf, ref_t->name_off); fallthrough; case KF_ARG_PTR_TO_BTF_ID: - mask = mask_raw_tp_reg(env, reg); /* Only base_type is checked, further checks are done here */ if ((base_type(reg->type) != PTR_TO_BTF_ID || (bpf_type_has_unsafe_modifiers(reg->type) && !is_rcu_reg(reg))) && @@ -12362,11 +12304,9 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_ verbose(env, "expected %s or socket\n", reg_type_str(env, base_type(reg->type) | (type_flag(reg->type) & BPF_REG_TRUSTED_MODIFIERS))); - unmask_raw_tp_reg(reg, mask); return -EINVAL; } ret = process_kf_arg_ptr_to_btf_id(env, reg, ref_t, ref_tname, ref_id, meta, i); - unmask_raw_tp_reg(reg, mask); if (ret < 0) return ret; break; @@ -13336,7 +13276,7 @@ static int sanitize_check_bounds(struct bpf_verifier_env *env, */ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, struct bpf_insn *insn, - struct bpf_reg_state *ptr_reg, + const struct bpf_reg_state *ptr_reg, const struct bpf_reg_state *off_reg) { struct bpf_verifier_state *vstate = env->cur_state; @@ -13350,7 +13290,6 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, struct bpf_sanitize_info info = {}; u8 opcode = BPF_OP(insn->code); u32 dst = insn->dst_reg; - bool mask; int ret; dst_reg = ®s[dst]; @@ -13377,14 +13316,11 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, return -EACCES; } - mask = mask_raw_tp_reg(env, ptr_reg); if (ptr_reg->type & PTR_MAYBE_NULL) { verbose(env, "R%d pointer arithmetic on %s prohibited, null-check it first\n", dst, reg_type_str(env, ptr_reg->type)); - unmask_raw_tp_reg(ptr_reg, mask); return -EACCES; } - unmask_raw_tp_reg(ptr_reg, mask); switch (base_type(ptr_reg->type)) { case PTR_TO_CTX: @@ -19934,7 +19870,6 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) * for this case. */ case PTR_TO_BTF_ID | MEM_ALLOC | PTR_UNTRUSTED: - case PTR_TO_BTF_ID | PTR_TRUSTED | PTR_MAYBE_NULL: if (type == BPF_READ) { if (BPF_MODE(insn->code) == BPF_MEM) insn->code = BPF_LDX | BPF_PROBE_MEM | @@ -21150,11 +21085,15 @@ patch_map_ops_generic: * changed in some incompatible and hard to support * way, it's fine to back out this inlining logic */ +#ifdef CONFIG_SMP insn_buf[0] = BPF_MOV32_IMM(BPF_REG_0, (u32)(unsigned long)&pcpu_hot.cpu_number); insn_buf[1] = BPF_MOV64_PERCPU_REG(BPF_REG_0, BPF_REG_0); insn_buf[2] = BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, 0); cnt = 3; - +#else + insn_buf[0] = BPF_ALU32_REG(BPF_XOR, BPF_REG_0, BPF_REG_0); + cnt = 1; +#endif new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); if (!new_prog) return -ENOMEM; diff --git a/kernel/fork.c b/kernel/fork.c index ce8be55e5e04..e192bdbc9ade 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -640,11 +640,8 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm, LIST_HEAD(uf); VMA_ITERATOR(vmi, mm, 0); - uprobe_start_dup_mmap(); - if (mmap_write_lock_killable(oldmm)) { - retval = -EINTR; - goto fail_uprobe_end; - } + if (mmap_write_lock_killable(oldmm)) + return -EINTR; flush_cache_dup_mm(oldmm); uprobe_dup_mmap(oldmm, mm); /* @@ -783,8 +780,6 @@ out: dup_userfaultfd_complete(&uf); else dup_userfaultfd_fail(&uf); -fail_uprobe_end: - uprobe_end_dup_mmap(); return retval; fail_nomem_anon_vma_fork: @@ -1692,9 +1687,11 @@ static struct mm_struct *dup_mm(struct task_struct *tsk, if (!mm_init(mm, tsk, mm->user_ns)) goto fail_nomem; + uprobe_start_dup_mmap(); err = dup_mmap(mm, oldmm); if (err) goto free_pt; + uprobe_end_dup_mmap(); mm->hiwater_rss = get_mm_rss(mm); mm->hiwater_vm = mm->total_vm; @@ -1709,6 +1706,8 @@ free_pt: mm->binfmt = NULL; mm_init_owner(mm, NULL); mmput(mm); + if (err) + uprobe_end_dup_mmap(); fail_nomem: return NULL; diff --git a/kernel/kcov.c b/kernel/kcov.c index 28a6be6e64fd..187ba1b80bda 100644 --- a/kernel/kcov.c +++ b/kernel/kcov.c @@ -166,7 +166,7 @@ static void kcov_remote_area_put(struct kcov_remote_area *area, * Unlike in_serving_softirq(), this function returns false when called during * a hardirq or an NMI that happened in the softirq context. */ -static inline bool in_softirq_really(void) +static __always_inline bool in_softirq_really(void) { return in_serving_softirq() && !in_hardirq() && !in_nmi(); } diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 6cc12777bb11..d07dc87787df 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1300,7 +1300,7 @@ bool sched_can_stop_tick(struct rq *rq) if (scx_enabled() && !scx_can_stop_tick(rq)) return false; - if (rq->cfs.nr_running > 1) + if (rq->cfs.h_nr_running > 1) return false; /* diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index 40a1ad4493b4..a17c23b53049 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -781,7 +781,7 @@ static inline void replenish_dl_new_period(struct sched_dl_entity *dl_se, * If it is a deferred reservation, and the server * is not handling an starvation case, defer it. */ - if (dl_se->dl_defer & !dl_se->dl_defer_running) { + if (dl_se->dl_defer && !dl_se->dl_defer_running) { dl_se->dl_throttled = 1; dl_se->dl_defer_armed = 1; } @@ -1647,6 +1647,7 @@ void dl_server_start(struct sched_dl_entity *dl_se) if (!dl_se->dl_runtime) return; + dl_se->dl_server_active = 1; enqueue_dl_entity(dl_se, ENQUEUE_WAKEUP); if (!dl_task(dl_se->rq->curr) || dl_entity_preempt(dl_se, &rq->curr->dl)) resched_curr(dl_se->rq); @@ -1661,6 +1662,7 @@ void dl_server_stop(struct sched_dl_entity *dl_se) hrtimer_try_to_cancel(&dl_se->dl_timer); dl_se->dl_defer_armed = 0; dl_se->dl_throttled = 0; + dl_se->dl_server_active = 0; } void dl_server_init(struct sched_dl_entity *dl_se, struct rq *rq, @@ -2420,8 +2422,10 @@ again: if (dl_server(dl_se)) { p = dl_se->server_pick_task(dl_se); if (!p) { - dl_se->dl_yielded = 1; - update_curr_dl_se(rq, dl_se, 0); + if (dl_server_active(dl_se)) { + dl_se->dl_yielded = 1; + update_curr_dl_se(rq, dl_se, 0); + } goto again; } rq->dl_server = dl_se; diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index f4035c7a0fa1..82b165bf48c4 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -844,6 +844,7 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq) SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "spread", SPLIT_NS(spread)); SEQ_printf(m, " .%-30s: %d\n", "nr_running", cfs_rq->nr_running); SEQ_printf(m, " .%-30s: %d\n", "h_nr_running", cfs_rq->h_nr_running); + SEQ_printf(m, " .%-30s: %d\n", "h_nr_delayed", cfs_rq->h_nr_delayed); SEQ_printf(m, " .%-30s: %d\n", "idle_nr_running", cfs_rq->idle_nr_running); SEQ_printf(m, " .%-30s: %d\n", "idle_h_nr_running", diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index 79bb18651cdb..40f915f893e2 100644 --- a/kernel/sched/ext.c +++ b/kernel/sched/ext.c @@ -4367,7 +4367,7 @@ static void scx_ops_bypass(bool bypass) * sees scx_rq_bypassing() before moving tasks to SCX. */ if (!scx_enabled()) { - rq_unlock_irqrestore(rq, &rf); + rq_unlock(rq, &rf); continue; } @@ -6637,7 +6637,7 @@ __bpf_kfunc int bpf_iter_scx_dsq_new(struct bpf_iter_scx_dsq *it, u64 dsq_id, return -ENOENT; INIT_LIST_HEAD(&kit->cursor.node); - kit->cursor.flags |= SCX_DSQ_LNODE_ITER_CURSOR | flags; + kit->cursor.flags = SCX_DSQ_LNODE_ITER_CURSOR | flags; kit->cursor.priv = READ_ONCE(kit->dsq->seq); return 0; diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 782ce70ebd1b..1ca96c99872f 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -1159,8 +1159,6 @@ static inline void update_curr_task(struct task_struct *p, s64 delta_exec) trace_sched_stat_runtime(p, delta_exec); account_group_exec_runtime(p, delta_exec); cgroup_account_cputime(p, delta_exec); - if (p->dl_server) - dl_server_update(p->dl_server, delta_exec); } static inline bool did_preempt_short(struct cfs_rq *cfs_rq, struct sched_entity *curr) @@ -1237,11 +1235,16 @@ static void update_curr(struct cfs_rq *cfs_rq) update_curr_task(p, delta_exec); /* - * Any fair task that runs outside of fair_server should - * account against fair_server such that it can account for - * this time and possibly avoid running this period. + * If the fair_server is active, we need to account for the + * fair_server time whether or not the task is running on + * behalf of fair_server or not: + * - If the task is running on behalf of fair_server, we need + * to limit its time based on the assigned runtime. + * - Fair task that runs outside of fair_server should account + * against fair_server such that it can account for this time + * and possibly avoid running this period. */ - if (p->dl_server != &rq->fair_server) + if (dl_server_active(&rq->fair_server)) dl_server_update(&rq->fair_server, delta_exec); } @@ -5471,9 +5474,33 @@ static void clear_buddies(struct cfs_rq *cfs_rq, struct sched_entity *se) static __always_inline void return_cfs_rq_runtime(struct cfs_rq *cfs_rq); -static inline void finish_delayed_dequeue_entity(struct sched_entity *se) +static void set_delayed(struct sched_entity *se) +{ + se->sched_delayed = 1; + for_each_sched_entity(se) { + struct cfs_rq *cfs_rq = cfs_rq_of(se); + + cfs_rq->h_nr_delayed++; + if (cfs_rq_throttled(cfs_rq)) + break; + } +} + +static void clear_delayed(struct sched_entity *se) { se->sched_delayed = 0; + for_each_sched_entity(se) { + struct cfs_rq *cfs_rq = cfs_rq_of(se); + + cfs_rq->h_nr_delayed--; + if (cfs_rq_throttled(cfs_rq)) + break; + } +} + +static inline void finish_delayed_dequeue_entity(struct sched_entity *se) +{ + clear_delayed(se); if (sched_feat(DELAY_ZERO) && se->vlag > 0) se->vlag = 0; } @@ -5484,6 +5511,7 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) bool sleep = flags & DEQUEUE_SLEEP; update_curr(cfs_rq); + clear_buddies(cfs_rq, se); if (flags & DEQUEUE_DELAYED) { SCHED_WARN_ON(!se->sched_delayed); @@ -5500,10 +5528,8 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) if (sched_feat(DELAY_DEQUEUE) && delay && !entity_eligible(cfs_rq, se)) { - if (cfs_rq->next == se) - cfs_rq->next = NULL; update_load_avg(cfs_rq, se, 0); - se->sched_delayed = 1; + set_delayed(se); return false; } } @@ -5526,8 +5552,6 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) update_stats_dequeue_fair(cfs_rq, se, flags); - clear_buddies(cfs_rq, se); - update_entity_lag(cfs_rq, se); if (sched_feat(PLACE_REL_DEADLINE) && !sleep) { se->deadline -= se->vruntime; @@ -5923,7 +5947,7 @@ static bool throttle_cfs_rq(struct cfs_rq *cfs_rq) struct rq *rq = rq_of(cfs_rq); struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg); struct sched_entity *se; - long task_delta, idle_task_delta, dequeue = 1; + long task_delta, idle_task_delta, delayed_delta, dequeue = 1; long rq_h_nr_running = rq->cfs.h_nr_running; raw_spin_lock(&cfs_b->lock); @@ -5956,6 +5980,7 @@ static bool throttle_cfs_rq(struct cfs_rq *cfs_rq) task_delta = cfs_rq->h_nr_running; idle_task_delta = cfs_rq->idle_h_nr_running; + delayed_delta = cfs_rq->h_nr_delayed; for_each_sched_entity(se) { struct cfs_rq *qcfs_rq = cfs_rq_of(se); int flags; @@ -5979,6 +6004,7 @@ static bool throttle_cfs_rq(struct cfs_rq *cfs_rq) qcfs_rq->h_nr_running -= task_delta; qcfs_rq->idle_h_nr_running -= idle_task_delta; + qcfs_rq->h_nr_delayed -= delayed_delta; if (qcfs_rq->load.weight) { /* Avoid re-evaluating load for this entity: */ @@ -6001,6 +6027,7 @@ static bool throttle_cfs_rq(struct cfs_rq *cfs_rq) qcfs_rq->h_nr_running -= task_delta; qcfs_rq->idle_h_nr_running -= idle_task_delta; + qcfs_rq->h_nr_delayed -= delayed_delta; } /* At this point se is NULL and we are at root level*/ @@ -6026,7 +6053,7 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq) struct rq *rq = rq_of(cfs_rq); struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg); struct sched_entity *se; - long task_delta, idle_task_delta; + long task_delta, idle_task_delta, delayed_delta; long rq_h_nr_running = rq->cfs.h_nr_running; se = cfs_rq->tg->se[cpu_of(rq)]; @@ -6062,6 +6089,7 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq) task_delta = cfs_rq->h_nr_running; idle_task_delta = cfs_rq->idle_h_nr_running; + delayed_delta = cfs_rq->h_nr_delayed; for_each_sched_entity(se) { struct cfs_rq *qcfs_rq = cfs_rq_of(se); @@ -6079,6 +6107,7 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq) qcfs_rq->h_nr_running += task_delta; qcfs_rq->idle_h_nr_running += idle_task_delta; + qcfs_rq->h_nr_delayed += delayed_delta; /* end evaluation on encountering a throttled cfs_rq */ if (cfs_rq_throttled(qcfs_rq)) @@ -6096,6 +6125,7 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq) qcfs_rq->h_nr_running += task_delta; qcfs_rq->idle_h_nr_running += idle_task_delta; + qcfs_rq->h_nr_delayed += delayed_delta; /* end evaluation on encountering a throttled cfs_rq */ if (cfs_rq_throttled(qcfs_rq)) @@ -6949,7 +6979,7 @@ requeue_delayed_entity(struct sched_entity *se) } update_load_avg(cfs_rq, se, 0); - se->sched_delayed = 0; + clear_delayed(se); } /* @@ -6963,6 +6993,7 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags) struct cfs_rq *cfs_rq; struct sched_entity *se = &p->se; int idle_h_nr_running = task_has_idle_policy(p); + int h_nr_delayed = 0; int task_new = !(flags & ENQUEUE_WAKEUP); int rq_h_nr_running = rq->cfs.h_nr_running; u64 slice = 0; @@ -6989,6 +7020,9 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags) if (p->in_iowait) cpufreq_update_util(rq, SCHED_CPUFREQ_IOWAIT); + if (task_new) + h_nr_delayed = !!se->sched_delayed; + for_each_sched_entity(se) { if (se->on_rq) { if (se->sched_delayed) @@ -7011,6 +7045,7 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags) cfs_rq->h_nr_running++; cfs_rq->idle_h_nr_running += idle_h_nr_running; + cfs_rq->h_nr_delayed += h_nr_delayed; if (cfs_rq_is_idle(cfs_rq)) idle_h_nr_running = 1; @@ -7034,6 +7069,7 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags) cfs_rq->h_nr_running++; cfs_rq->idle_h_nr_running += idle_h_nr_running; + cfs_rq->h_nr_delayed += h_nr_delayed; if (cfs_rq_is_idle(cfs_rq)) idle_h_nr_running = 1; @@ -7096,6 +7132,7 @@ static int dequeue_entities(struct rq *rq, struct sched_entity *se, int flags) struct task_struct *p = NULL; int idle_h_nr_running = 0; int h_nr_running = 0; + int h_nr_delayed = 0; struct cfs_rq *cfs_rq; u64 slice = 0; @@ -7103,6 +7140,8 @@ static int dequeue_entities(struct rq *rq, struct sched_entity *se, int flags) p = task_of(se); h_nr_running = 1; idle_h_nr_running = task_has_idle_policy(p); + if (!task_sleep && !task_delayed) + h_nr_delayed = !!se->sched_delayed; } else { cfs_rq = group_cfs_rq(se); slice = cfs_rq_min_slice(cfs_rq); @@ -7120,6 +7159,7 @@ static int dequeue_entities(struct rq *rq, struct sched_entity *se, int flags) cfs_rq->h_nr_running -= h_nr_running; cfs_rq->idle_h_nr_running -= idle_h_nr_running; + cfs_rq->h_nr_delayed -= h_nr_delayed; if (cfs_rq_is_idle(cfs_rq)) idle_h_nr_running = h_nr_running; @@ -7158,6 +7198,7 @@ static int dequeue_entities(struct rq *rq, struct sched_entity *se, int flags) cfs_rq->h_nr_running -= h_nr_running; cfs_rq->idle_h_nr_running -= idle_h_nr_running; + cfs_rq->h_nr_delayed -= h_nr_delayed; if (cfs_rq_is_idle(cfs_rq)) idle_h_nr_running = h_nr_running; @@ -8786,7 +8827,7 @@ static void check_preempt_wakeup_fair(struct rq *rq, struct task_struct *p, int if (unlikely(throttled_hierarchy(cfs_rq_of(pse)))) return; - if (sched_feat(NEXT_BUDDY) && !(wake_flags & WF_FORK)) { + if (sched_feat(NEXT_BUDDY) && !(wake_flags & WF_FORK) && !pse->sched_delayed) { set_next_buddy(pse); } diff --git a/kernel/sched/pelt.c b/kernel/sched/pelt.c index a9c65d97b3ca..171a802420a1 100644 --- a/kernel/sched/pelt.c +++ b/kernel/sched/pelt.c @@ -321,7 +321,7 @@ int __update_load_avg_cfs_rq(u64 now, struct cfs_rq *cfs_rq) { if (___update_load_sum(now, &cfs_rq->avg, scale_load_down(cfs_rq->load.weight), - cfs_rq->h_nr_running, + cfs_rq->h_nr_running - cfs_rq->h_nr_delayed, cfs_rq->curr != NULL)) { ___update_load_avg(&cfs_rq->avg, 1); diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index c03b3d7b320e..f2ef520513c4 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -398,6 +398,11 @@ extern void __dl_server_attach_root(struct sched_dl_entity *dl_se, struct rq *rq extern int dl_server_apply_params(struct sched_dl_entity *dl_se, u64 runtime, u64 period, bool init); +static inline bool dl_server_active(struct sched_dl_entity *dl_se) +{ + return dl_se->dl_server_active; +} + #ifdef CONFIG_CGROUP_SCHED extern struct list_head task_groups; @@ -649,6 +654,7 @@ struct cfs_rq { unsigned int h_nr_running; /* SCHED_{NORMAL,BATCH,IDLE} */ unsigned int idle_nr_running; /* SCHED_IDLE */ unsigned int idle_h_nr_running; /* SCHED_IDLE */ + unsigned int h_nr_delayed; s64 avg_vruntime; u64 avg_load; @@ -898,8 +904,11 @@ struct dl_rq { static inline void se_update_runnable(struct sched_entity *se) { - if (!entity_is_task(se)) - se->runnable_weight = se->my_q->h_nr_running; + if (!entity_is_task(se)) { + struct cfs_rq *cfs_rq = se->my_q; + + se->runnable_weight = cfs_rq->h_nr_running - cfs_rq->h_nr_delayed; + } } static inline long se_runnable(struct sched_entity *se) diff --git a/kernel/static_call_inline.c b/kernel/static_call_inline.c index 5259cda486d0..bb7d066a7c39 100644 --- a/kernel/static_call_inline.c +++ b/kernel/static_call_inline.c @@ -15,7 +15,7 @@ extern struct static_call_site __start_static_call_sites[], extern struct static_call_tramp_key __start_static_call_tramp_key[], __stop_static_call_tramp_key[]; -static int static_call_initialized; +int static_call_initialized; /* * Must be called before early_initcall() to be effective. diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 792dc35414a3..50881898e758 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -2215,6 +2215,9 @@ void perf_event_detach_bpf_prog(struct perf_event *event) goto unlock; old_array = bpf_event_rcu_dereference(event->tp_event->prog_array); + if (!old_array) + goto put; + ret = bpf_prog_array_copy(old_array, event->prog, NULL, 0, &new_array); if (ret < 0) { bpf_prog_array_delete_safe(old_array, event->prog); @@ -2223,6 +2226,14 @@ void perf_event_detach_bpf_prog(struct perf_event *event) bpf_prog_array_free_sleepable(old_array); } +put: + /* + * It could be that the bpf_prog is not sleepable (and will be freed + * via normal RCU), but is called from a point that supports sleepable + * programs and uses tasks-trace-RCU. + */ + synchronize_rcu_tasks_trace(); + bpf_prog_put(event->prog); event->prog = NULL; diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c index 69e226a48daa..c12335499ec9 100644 --- a/kernel/trace/fgraph.c +++ b/kernel/trace/fgraph.c @@ -802,7 +802,7 @@ static unsigned long __ftrace_return_to_handler(struct fgraph_ret_regs *ret_regs #endif { for_each_set_bit(i, &bitmap, sizeof(bitmap) * BITS_PER_BYTE) { - struct fgraph_ops *gops = fgraph_array[i]; + struct fgraph_ops *gops = READ_ONCE(fgraph_array[i]); if (gops == &fgraph_stub) continue; @@ -1160,7 +1160,7 @@ void fgraph_update_pid_func(void) static int start_graph_tracing(void) { unsigned long **ret_stack_list; - int ret; + int ret, cpu; ret_stack_list = kcalloc(FTRACE_RETSTACK_ALLOC_SIZE, sizeof(*ret_stack_list), GFP_KERNEL); @@ -1168,6 +1168,12 @@ static int start_graph_tracing(void) if (!ret_stack_list) return -ENOMEM; + /* The cpu_boot init_task->ret_stack will never be freed */ + for_each_online_cpu(cpu) { + if (!idle_task(cpu)->ret_stack) + ftrace_graph_init_idle_task(idle_task(cpu), cpu); + } + do { ret = alloc_retstack_tasklist(ret_stack_list); } while (ret == -EAGAIN); diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 3dd3b97d8049..cd9dbfb30383 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -883,16 +883,13 @@ static void profile_graph_return(struct ftrace_graph_ret *trace, } static struct fgraph_ops fprofiler_ops = { - .ops = { - .flags = FTRACE_OPS_FL_INITIALIZED, - INIT_OPS_HASH(fprofiler_ops.ops) - }, .entryfunc = &profile_graph_entry, .retfunc = &profile_graph_return, }; static int register_ftrace_profiler(void) { + ftrace_ops_set_global_filter(&fprofiler_ops.ops); return register_ftrace_graph(&fprofiler_ops); } @@ -903,12 +900,11 @@ static void unregister_ftrace_profiler(void) #else static struct ftrace_ops ftrace_profile_ops __read_mostly = { .func = function_profile_call, - .flags = FTRACE_OPS_FL_INITIALIZED, - INIT_OPS_HASH(ftrace_profile_ops) }; static int register_ftrace_profiler(void) { + ftrace_ops_set_global_filter(&ftrace_profile_ops); return register_ftrace_function(&ftrace_profile_ops); } diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 366eb4c4f28e..703978b2d557 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -7019,7 +7019,11 @@ static int __rb_map_vma(struct ring_buffer_per_cpu *cpu_buffer, lockdep_assert_held(&cpu_buffer->mapping_lock); nr_subbufs = cpu_buffer->nr_pages + 1; /* + reader-subbuf */ - nr_pages = ((nr_subbufs + 1) << subbuf_order) - pgoff; /* + meta-page */ + nr_pages = ((nr_subbufs + 1) << subbuf_order); /* + meta-page */ + if (nr_pages <= pgoff) + return -EINVAL; + + nr_pages -= pgoff; nr_vma_pages = vma_pages(vma); if (!nr_vma_pages || nr_vma_pages > nr_pages) diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 17d2ffde0bb6..b04990385a6a 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -3635,17 +3635,12 @@ char *trace_iter_expand_format(struct trace_iterator *iter) } /* Returns true if the string is safe to dereference from an event */ -static bool trace_safe_str(struct trace_iterator *iter, const char *str, - bool star, int len) +static bool trace_safe_str(struct trace_iterator *iter, const char *str) { unsigned long addr = (unsigned long)str; struct trace_event *trace_event; struct trace_event_call *event; - /* Ignore strings with no length */ - if (star && !len) - return true; - /* OK if part of the event data */ if ((addr >= (unsigned long)iter->ent) && (addr < (unsigned long)iter->ent + iter->ent_size)) @@ -3685,181 +3680,69 @@ static bool trace_safe_str(struct trace_iterator *iter, const char *str, return false; } -static DEFINE_STATIC_KEY_FALSE(trace_no_verify); - -static int test_can_verify_check(const char *fmt, ...) -{ - char buf[16]; - va_list ap; - int ret; - - /* - * The verifier is dependent on vsnprintf() modifies the va_list - * passed to it, where it is sent as a reference. Some architectures - * (like x86_32) passes it by value, which means that vsnprintf() - * does not modify the va_list passed to it, and the verifier - * would then need to be able to understand all the values that - * vsnprintf can use. If it is passed by value, then the verifier - * is disabled. - */ - va_start(ap, fmt); - vsnprintf(buf, 16, "%d", ap); - ret = va_arg(ap, int); - va_end(ap); - - return ret; -} - -static void test_can_verify(void) -{ - if (!test_can_verify_check("%d %d", 0, 1)) { - pr_info("trace event string verifier disabled\n"); - static_branch_inc(&trace_no_verify); - } -} - /** - * trace_check_vprintf - Check dereferenced strings while writing to the seq buffer + * ignore_event - Check dereferenced fields while writing to the seq buffer * @iter: The iterator that holds the seq buffer and the event being printed - * @fmt: The format used to print the event - * @ap: The va_list holding the data to print from @fmt. * - * This writes the data into the @iter->seq buffer using the data from - * @fmt and @ap. If the format has a %s, then the source of the string - * is examined to make sure it is safe to print, otherwise it will - * warn and print "[UNSAFE MEMORY]" in place of the dereferenced string - * pointer. + * At boot up, test_event_printk() will flag any event that dereferences + * a string with "%s" that does exist in the ring buffer. It may still + * be valid, as the string may point to a static string in the kernel + * rodata that never gets freed. But if the string pointer is pointing + * to something that was allocated, there's a chance that it can be freed + * by the time the user reads the trace. This would cause a bad memory + * access by the kernel and possibly crash the system. + * + * This function will check if the event has any fields flagged as needing + * to be checked at runtime and perform those checks. + * + * If it is found that a field is unsafe, it will write into the @iter->seq + * a message stating what was found to be unsafe. + * + * @return: true if the event is unsafe and should be ignored, + * false otherwise. */ -void trace_check_vprintf(struct trace_iterator *iter, const char *fmt, - va_list ap) +bool ignore_event(struct trace_iterator *iter) { - long text_delta = 0; - long data_delta = 0; - const char *p = fmt; - const char *str; - bool good; - int i, j; + struct ftrace_event_field *field; + struct trace_event *trace_event; + struct trace_event_call *event; + struct list_head *head; + struct trace_seq *seq; + const void *ptr; - if (WARN_ON_ONCE(!fmt)) - return; + trace_event = ftrace_find_event(iter->ent->type); - if (static_branch_unlikely(&trace_no_verify)) - goto print; + seq = &iter->seq; - /* - * When the kernel is booted with the tp_printk command line - * parameter, trace events go directly through to printk(). - * It also is checked by this function, but it does not - * have an associated trace_array (tr) for it. - */ - if (iter->tr) { - text_delta = iter->tr->text_delta; - data_delta = iter->tr->data_delta; + if (!trace_event) { + trace_seq_printf(seq, "EVENT ID %d NOT FOUND?\n", iter->ent->type); + return true; } - /* Don't bother checking when doing a ftrace_dump() */ - if (iter->fmt == static_fmt_buf) - goto print; - - while (*p) { - bool star = false; - int len = 0; - - j = 0; - - /* - * We only care about %s and variants - * as well as %p[sS] if delta is non-zero - */ - for (i = 0; p[i]; i++) { - if (i + 1 >= iter->fmt_size) { - /* - * If we can't expand the copy buffer, - * just print it. - */ - if (!trace_iter_expand_format(iter)) - goto print; - } - - if (p[i] == '\\' && p[i+1]) { - i++; - continue; - } - if (p[i] == '%') { - /* Need to test cases like %08.*s */ - for (j = 1; p[i+j]; j++) { - if (isdigit(p[i+j]) || - p[i+j] == '.') - continue; - if (p[i+j] == '*') { - star = true; - continue; - } - break; - } - if (p[i+j] == 's') - break; - - if (text_delta && p[i+1] == 'p' && - ((p[i+2] == 's' || p[i+2] == 'S'))) - break; - - star = false; - } - j = 0; - } - /* If no %s found then just print normally */ - if (!p[i]) - break; - - /* Copy up to the %s, and print that */ - strncpy(iter->fmt, p, i); - iter->fmt[i] = '\0'; - trace_seq_vprintf(&iter->seq, iter->fmt, ap); + event = container_of(trace_event, struct trace_event_call, event); + if (!(event->flags & TRACE_EVENT_FL_TEST_STR)) + return false; - /* Add delta to %pS pointers */ - if (p[i+1] == 'p') { - unsigned long addr; - char fmt[4]; + head = trace_get_fields(event); + if (!head) { + trace_seq_printf(seq, "FIELDS FOR EVENT '%s' NOT FOUND?\n", + trace_event_name(event)); + return true; + } - fmt[0] = '%'; - fmt[1] = 'p'; - fmt[2] = p[i+2]; /* Either %ps or %pS */ - fmt[3] = '\0'; + /* Offsets are from the iter->ent that points to the raw event */ + ptr = iter->ent; - addr = va_arg(ap, unsigned long); - addr += text_delta; - trace_seq_printf(&iter->seq, fmt, (void *)addr); + list_for_each_entry(field, head, link) { + const char *str; + bool good; - p += i + 3; + if (!field->needs_test) continue; - } - - /* - * If iter->seq is full, the above call no longer guarantees - * that ap is in sync with fmt processing, and further calls - * to va_arg() can return wrong positional arguments. - * - * Ensure that ap is no longer used in this case. - */ - if (iter->seq.full) { - p = ""; - break; - } - if (star) - len = va_arg(ap, int); + str = *(const char **)(ptr + field->offset); - /* The ap now points to the string data of the %s */ - str = va_arg(ap, const char *); - - good = trace_safe_str(iter, str, star, len); - - /* Could be from the last boot */ - if (data_delta && !good) { - str += data_delta; - good = trace_safe_str(iter, str, star, len); - } + good = trace_safe_str(iter, str); /* * If you hit this warning, it is likely that the @@ -3870,44 +3753,14 @@ void trace_check_vprintf(struct trace_iterator *iter, const char *fmt, * instead. See samples/trace_events/trace-events-sample.h * for reference. */ - if (WARN_ONCE(!good, "fmt: '%s' current_buffer: '%s'", - fmt, seq_buf_str(&iter->seq.seq))) { - int ret; - - /* Try to safely read the string */ - if (star) { - if (len + 1 > iter->fmt_size) - len = iter->fmt_size - 1; - if (len < 0) - len = 0; - ret = copy_from_kernel_nofault(iter->fmt, str, len); - iter->fmt[len] = 0; - star = false; - } else { - ret = strncpy_from_kernel_nofault(iter->fmt, str, - iter->fmt_size); - } - if (ret < 0) - trace_seq_printf(&iter->seq, "(0x%px)", str); - else - trace_seq_printf(&iter->seq, "(0x%px:%s)", - str, iter->fmt); - str = "[UNSAFE-MEMORY]"; - strcpy(iter->fmt, "%s"); - } else { - strncpy(iter->fmt, p + i, j + 1); - iter->fmt[j+1] = '\0'; + if (WARN_ONCE(!good, "event '%s' has unsafe pointer field '%s'", + trace_event_name(event), field->name)) { + trace_seq_printf(seq, "EVENT %s: HAS UNSAFE POINTER FIELD '%s'\n", + trace_event_name(event), field->name); + return true; } - if (star) - trace_seq_printf(&iter->seq, iter->fmt, len, str); - else - trace_seq_printf(&iter->seq, iter->fmt, str); - - p += i + j + 1; } - print: - if (*p) - trace_seq_vprintf(&iter->seq, p, ap); + return false; } const char *trace_event_format(struct trace_iterator *iter, const char *fmt) @@ -4377,6 +4230,15 @@ static enum print_line_t print_trace_fmt(struct trace_iterator *iter) if (event) { if (tr->trace_flags & TRACE_ITER_FIELDS) return print_event_fields(iter, event); + /* + * For TRACE_EVENT() events, the print_fmt is not + * safe to use if the array has delta offsets + * Force printing via the fields. + */ + if ((tr->text_delta || tr->data_delta) && + event->type > __TRACE_LAST_TYPE) + return print_event_fields(iter, event); + return event->funcs->trace(iter, sym_flags, event); } @@ -5249,6 +5111,9 @@ tracing_cpumask_write(struct file *filp, const char __user *ubuf, cpumask_var_t tracing_cpumask_new; int err; + if (count == 0 || count > KMALLOC_MAX_SIZE) + return -EINVAL; + if (!zalloc_cpumask_var(&tracing_cpumask_new, GFP_KERNEL)) return -ENOMEM; @@ -10794,8 +10659,6 @@ __init static int tracer_alloc_buffers(void) register_snapshot_cmd(); - test_can_verify(); - return 0; out_free_pipe_cpumask: diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 30d6675c78cf..04ea327198ba 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -664,9 +664,8 @@ void trace_buffer_unlock_commit_nostack(struct trace_buffer *buffer, bool trace_is_tracepoint_string(const char *str); const char *trace_event_format(struct trace_iterator *iter, const char *fmt); -void trace_check_vprintf(struct trace_iterator *iter, const char *fmt, - va_list ap) __printf(2, 0); char *trace_iter_expand_format(struct trace_iterator *iter); +bool ignore_event(struct trace_iterator *iter); int trace_empty(struct trace_iterator *iter); @@ -1402,7 +1401,8 @@ struct ftrace_event_field { int filter_type; int offset; int size; - int is_signed; + unsigned int is_signed:1; + unsigned int needs_test:1; int len; }; diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 7266ec2a4eea..ea9b44847ce6 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -82,7 +82,7 @@ static int system_refcount_dec(struct event_subsystem *system) } static struct ftrace_event_field * -__find_event_field(struct list_head *head, char *name) +__find_event_field(struct list_head *head, const char *name) { struct ftrace_event_field *field; @@ -114,7 +114,8 @@ trace_find_event_field(struct trace_event_call *call, char *name) static int __trace_define_field(struct list_head *head, const char *type, const char *name, int offset, int size, - int is_signed, int filter_type, int len) + int is_signed, int filter_type, int len, + int need_test) { struct ftrace_event_field *field; @@ -133,6 +134,7 @@ static int __trace_define_field(struct list_head *head, const char *type, field->offset = offset; field->size = size; field->is_signed = is_signed; + field->needs_test = need_test; field->len = len; list_add(&field->link, head); @@ -151,13 +153,13 @@ int trace_define_field(struct trace_event_call *call, const char *type, head = trace_get_fields(call); return __trace_define_field(head, type, name, offset, size, - is_signed, filter_type, 0); + is_signed, filter_type, 0, 0); } EXPORT_SYMBOL_GPL(trace_define_field); static int trace_define_field_ext(struct trace_event_call *call, const char *type, const char *name, int offset, int size, int is_signed, - int filter_type, int len) + int filter_type, int len, int need_test) { struct list_head *head; @@ -166,13 +168,13 @@ static int trace_define_field_ext(struct trace_event_call *call, const char *typ head = trace_get_fields(call); return __trace_define_field(head, type, name, offset, size, - is_signed, filter_type, len); + is_signed, filter_type, len, need_test); } #define __generic_field(type, item, filter_type) \ ret = __trace_define_field(&ftrace_generic_fields, #type, \ #item, 0, 0, is_signed_type(type), \ - filter_type, 0); \ + filter_type, 0, 0); \ if (ret) \ return ret; @@ -181,7 +183,8 @@ static int trace_define_field_ext(struct trace_event_call *call, const char *typ "common_" #item, \ offsetof(typeof(ent), item), \ sizeof(ent.item), \ - is_signed_type(type), FILTER_OTHER, 0); \ + is_signed_type(type), FILTER_OTHER, \ + 0, 0); \ if (ret) \ return ret; @@ -244,19 +247,16 @@ int trace_event_get_offsets(struct trace_event_call *call) return tail->offset + tail->size; } -/* - * Check if the referenced field is an array and return true, - * as arrays are OK to dereference. - */ -static bool test_field(const char *fmt, struct trace_event_call *call) + +static struct trace_event_fields *find_event_field(const char *fmt, + struct trace_event_call *call) { struct trace_event_fields *field = call->class->fields_array; - const char *array_descriptor; const char *p = fmt; int len; if (!(len = str_has_prefix(fmt, "REC->"))) - return false; + return NULL; fmt += len; for (p = fmt; *p; p++) { if (!isalnum(*p) && *p != '_') @@ -265,16 +265,141 @@ static bool test_field(const char *fmt, struct trace_event_call *call) len = p - fmt; for (; field->type; field++) { - if (strncmp(field->name, fmt, len) || - field->name[len]) + if (strncmp(field->name, fmt, len) || field->name[len]) continue; - array_descriptor = strchr(field->type, '['); - /* This is an array and is OK to dereference. */ - return array_descriptor != NULL; + + return field; + } + return NULL; +} + +/* + * Check if the referenced field is an array and return true, + * as arrays are OK to dereference. + */ +static bool test_field(const char *fmt, struct trace_event_call *call) +{ + struct trace_event_fields *field; + + field = find_event_field(fmt, call); + if (!field) + return false; + + /* This is an array and is OK to dereference. */ + return strchr(field->type, '[') != NULL; +} + +/* Look for a string within an argument */ +static bool find_print_string(const char *arg, const char *str, const char *end) +{ + const char *r; + + r = strstr(arg, str); + return r && r < end; +} + +/* Return true if the argument pointer is safe */ +static bool process_pointer(const char *fmt, int len, struct trace_event_call *call) +{ + const char *r, *e, *a; + + e = fmt + len; + + /* Find the REC-> in the argument */ + r = strstr(fmt, "REC->"); + if (r && r < e) { + /* + * Addresses of events on the buffer, or an array on the buffer is + * OK to dereference. There's ways to fool this, but + * this is to catch common mistakes, not malicious code. + */ + a = strchr(fmt, '&'); + if ((a && (a < r)) || test_field(r, call)) + return true; + } else if (find_print_string(fmt, "__get_dynamic_array(", e)) { + return true; + } else if (find_print_string(fmt, "__get_rel_dynamic_array(", e)) { + return true; + } else if (find_print_string(fmt, "__get_dynamic_array_len(", e)) { + return true; + } else if (find_print_string(fmt, "__get_rel_dynamic_array_len(", e)) { + return true; + } else if (find_print_string(fmt, "__get_sockaddr(", e)) { + return true; + } else if (find_print_string(fmt, "__get_rel_sockaddr(", e)) { + return true; } return false; } +/* Return true if the string is safe */ +static bool process_string(const char *fmt, int len, struct trace_event_call *call) +{ + struct trace_event_fields *field; + const char *r, *e, *s; + + e = fmt + len; + + /* + * There are several helper functions that return strings. + * If the argument contains a function, then assume its field is valid. + * It is considered that the argument has a function if it has: + * alphanumeric or '_' before a parenthesis. + */ + s = fmt; + do { + r = strstr(s, "("); + if (!r || r >= e) + break; + for (int i = 1; r - i >= s; i++) { + char ch = *(r - i); + if (isspace(ch)) + continue; + if (isalnum(ch) || ch == '_') + return true; + /* Anything else, this isn't a function */ + break; + } + /* A function could be wrapped in parethesis, try the next one */ + s = r + 1; + } while (s < e); + + /* + * Check for arrays. If the argument has: foo[REC->val] + * then it is very likely that foo is an array of strings + * that are safe to use. + */ + r = strstr(s, "["); + if (r && r < e) { + r = strstr(r, "REC->"); + if (r && r < e) + return true; + } + + /* + * If there's any strings in the argument consider this arg OK as it + * could be: REC->field ? "foo" : "bar" and we don't want to get into + * verifying that logic here. + */ + if (find_print_string(fmt, "\"", e)) + return true; + + /* Dereferenced strings are also valid like any other pointer */ + if (process_pointer(fmt, len, call)) + return true; + + /* Make sure the field is found */ + field = find_event_field(fmt, call); + if (!field) + return false; + + /* Test this field's string before printing the event */ + call->flags |= TRACE_EVENT_FL_TEST_STR; + field->needs_test = 1; + + return true; +} + /* * Examine the print fmt of the event looking for unsafe dereference * pointers using %p* that could be recorded in the trace event and @@ -284,13 +409,14 @@ static bool test_field(const char *fmt, struct trace_event_call *call) static void test_event_printk(struct trace_event_call *call) { u64 dereference_flags = 0; + u64 string_flags = 0; bool first = true; - const char *fmt, *c, *r, *a; + const char *fmt; int parens = 0; char in_quote = 0; int start_arg = 0; int arg = 0; - int i; + int i, e; fmt = call->print_fmt; @@ -374,8 +500,16 @@ static void test_event_printk(struct trace_event_call *call) star = true; continue; } - if ((fmt[i + j] == 's') && star) - arg++; + if ((fmt[i + j] == 's')) { + if (star) + arg++; + if (WARN_ONCE(arg == 63, + "Too many args for event: %s", + trace_event_name(call))) + return; + dereference_flags |= 1ULL << arg; + string_flags |= 1ULL << arg; + } break; } break; @@ -403,42 +537,47 @@ static void test_event_printk(struct trace_event_call *call) case ',': if (in_quote || parens) continue; + e = i; i++; while (isspace(fmt[i])) i++; - start_arg = i; - if (!(dereference_flags & (1ULL << arg))) - goto next_arg; - /* Find the REC-> in the argument */ - c = strchr(fmt + i, ','); - r = strstr(fmt + i, "REC->"); - if (r && (!c || r < c)) { - /* - * Addresses of events on the buffer, - * or an array on the buffer is - * OK to dereference. - * There's ways to fool this, but - * this is to catch common mistakes, - * not malicious code. - */ - a = strchr(fmt + i, '&'); - if ((a && (a < r)) || test_field(r, call)) + /* + * If start_arg is zero, then this is the start of the + * first argument. The processing of the argument happens + * when the end of the argument is found, as it needs to + * handle paranthesis and such. + */ + if (!start_arg) { + start_arg = i; + /* Balance out the i++ in the for loop */ + i--; + continue; + } + + if (dereference_flags & (1ULL << arg)) { + if (string_flags & (1ULL << arg)) { + if (process_string(fmt + start_arg, e - start_arg, call)) + dereference_flags &= ~(1ULL << arg); + } else if (process_pointer(fmt + start_arg, e - start_arg, call)) dereference_flags &= ~(1ULL << arg); - } else if ((r = strstr(fmt + i, "__get_dynamic_array(")) && - (!c || r < c)) { - dereference_flags &= ~(1ULL << arg); - } else if ((r = strstr(fmt + i, "__get_sockaddr(")) && - (!c || r < c)) { - dereference_flags &= ~(1ULL << arg); } - next_arg: - i--; + start_arg = i; arg++; + /* Balance out the i++ in the for loop */ + i--; } } + if (dereference_flags & (1ULL << arg)) { + if (string_flags & (1ULL << arg)) { + if (process_string(fmt + start_arg, i - start_arg, call)) + dereference_flags &= ~(1ULL << arg); + } else if (process_pointer(fmt + start_arg, i - start_arg, call)) + dereference_flags &= ~(1ULL << arg); + } + /* * If you triggered the below warning, the trace event reported * uses an unsafe dereference pointer %p*. As the data stored @@ -2471,7 +2610,7 @@ event_define_fields(struct trace_event_call *call) ret = trace_define_field_ext(call, field->type, field->name, offset, field->size, field->is_signed, field->filter_type, - field->len); + field->len, field->needs_test); if (WARN_ON_ONCE(ret)) { pr_err("error code is %d\n", ret); break; diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 263fac44d3ca..935a886af40c 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -725,7 +725,7 @@ static int trace_kprobe_module_callback(struct notifier_block *nb, static struct notifier_block trace_kprobe_module_nb = { .notifier_call = trace_kprobe_module_callback, - .priority = 1 /* Invoked after kprobe module callback */ + .priority = 2 /* Invoked after kprobe and jump_label module callback */ }; static int trace_kprobe_register_module_notifier(void) { diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c index c14573e5a903..6e7090e8bf30 100644 --- a/kernel/trace/trace_output.c +++ b/kernel/trace/trace_output.c @@ -317,10 +317,14 @@ EXPORT_SYMBOL(trace_raw_output_prep); void trace_event_printf(struct trace_iterator *iter, const char *fmt, ...) { + struct trace_seq *s = &iter->seq; va_list ap; + if (ignore_event(iter)) + return; + va_start(ap, fmt); - trace_check_vprintf(iter, trace_event_format(iter, fmt), ap); + trace_seq_vprintf(s, trace_event_format(iter, fmt), ap); va_end(ap); } EXPORT_SYMBOL(trace_event_printf); diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index b30fc8fcd095..b085a8a164ea 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -1400,9 +1400,13 @@ static void __uprobe_perf_func(struct trace_uprobe *tu, #ifdef CONFIG_BPF_EVENTS if (bpf_prog_array_valid(call)) { + const struct bpf_prog_array *array; u32 ret; - ret = bpf_prog_run_array_uprobe(call->prog_array, regs, bpf_prog_run); + rcu_read_lock_trace(); + array = rcu_dereference_check(call->prog_array, rcu_read_lock_trace_held()); + ret = bpf_prog_run_array_uprobe(array, regs, bpf_prog_run); + rcu_read_unlock_trace(); if (!ret) return; } diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 9949ffad8df0..cee65cb43108 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -3680,23 +3680,27 @@ void workqueue_softirq_dead(unsigned int cpu) * check_flush_dependency - check for flush dependency sanity * @target_wq: workqueue being flushed * @target_work: work item being flushed (NULL for workqueue flushes) + * @from_cancel: are we called from the work cancel path * * %current is trying to flush the whole @target_wq or @target_work on it. - * If @target_wq doesn't have %WQ_MEM_RECLAIM, verify that %current is not - * reclaiming memory or running on a workqueue which doesn't have - * %WQ_MEM_RECLAIM as that can break forward-progress guarantee leading to - * a deadlock. + * If this is not the cancel path (which implies work being flushed is either + * already running, or will not be at all), check if @target_wq doesn't have + * %WQ_MEM_RECLAIM and verify that %current is not reclaiming memory or running + * on a workqueue which doesn't have %WQ_MEM_RECLAIM as that can break forward- + * progress guarantee leading to a deadlock. */ static void check_flush_dependency(struct workqueue_struct *target_wq, - struct work_struct *target_work) + struct work_struct *target_work, + bool from_cancel) { - work_func_t target_func = target_work ? target_work->func : NULL; + work_func_t target_func; struct worker *worker; - if (target_wq->flags & WQ_MEM_RECLAIM) + if (from_cancel || target_wq->flags & WQ_MEM_RECLAIM) return; worker = current_wq_worker(); + target_func = target_work ? target_work->func : NULL; WARN_ONCE(current->flags & PF_MEMALLOC, "workqueue: PF_MEMALLOC task %d(%s) is flushing !WQ_MEM_RECLAIM %s:%ps", @@ -3966,7 +3970,7 @@ void __flush_workqueue(struct workqueue_struct *wq) list_add_tail(&this_flusher.list, &wq->flusher_overflow); } - check_flush_dependency(wq, NULL); + check_flush_dependency(wq, NULL, false); mutex_unlock(&wq->mutex); @@ -4141,7 +4145,7 @@ static bool start_flush_work(struct work_struct *work, struct wq_barrier *barr, } wq = pwq->wq; - check_flush_dependency(wq, work); + check_flush_dependency(wq, work, from_cancel); insert_wq_barrier(pwq, barr, work, worker); raw_spin_unlock_irq(&pool->lock); @@ -5627,6 +5631,7 @@ static void wq_adjust_max_active(struct workqueue_struct *wq) } while (activated); } +__printf(1, 0) static struct workqueue_struct *__alloc_workqueue(const char *fmt, unsigned int flags, int max_active, va_list args) diff --git a/lib/maple_tree.c b/lib/maple_tree.c index 8d83e2172719..0cbe913634be 100644 --- a/lib/maple_tree.c +++ b/lib/maple_tree.c @@ -4367,6 +4367,7 @@ int mas_alloc_cyclic(struct ma_state *mas, unsigned long *startp, ret = 1; } if (ret < 0 && range_lo > min) { + mas_reset(mas); ret = mas_empty_area(mas, min, range_hi, 1); if (ret == 0) ret = 1; diff --git a/mm/damon/core.c b/mm/damon/core.c index 511c3f61ab44..54f4dd8d549f 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -868,6 +868,11 @@ static int damon_commit_schemes(struct damon_ctx *dst, struct damon_ctx *src) NUMA_NO_NODE); if (!new_scheme) return -ENOMEM; + err = damos_commit(new_scheme, src_scheme); + if (err) { + damon_destroy_scheme(new_scheme); + return err; + } damon_add_scheme(dst, new_scheme); } return 0; @@ -961,8 +966,11 @@ static int damon_commit_targets( return -ENOMEM; err = damon_commit_target(new_target, false, src_target, damon_target_has_pid(src)); - if (err) + if (err) { + damon_destroy_target(new_target); return err; + } + damon_add_target(dst, new_target); } return 0; } diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 5734d5d5060f..7e0f72cd9fd4 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -3503,7 +3503,7 @@ int split_huge_page_to_list_to_order(struct page *page, struct list_head *list, !list_empty(&folio->_deferred_list)) { ds_queue->split_queue_len--; if (folio_test_partially_mapped(folio)) { - __folio_clear_partially_mapped(folio); + folio_clear_partially_mapped(folio); mod_mthp_stat(folio_order(folio), MTHP_STAT_NR_ANON_PARTIALLY_MAPPED, -1); } @@ -3615,7 +3615,7 @@ bool __folio_unqueue_deferred_split(struct folio *folio) if (!list_empty(&folio->_deferred_list)) { ds_queue->split_queue_len--; if (folio_test_partially_mapped(folio)) { - __folio_clear_partially_mapped(folio); + folio_clear_partially_mapped(folio); mod_mthp_stat(folio_order(folio), MTHP_STAT_NR_ANON_PARTIALLY_MAPPED, -1); } @@ -3659,7 +3659,7 @@ void deferred_split_folio(struct folio *folio, bool partially_mapped) spin_lock_irqsave(&ds_queue->split_queue_lock, flags); if (partially_mapped) { if (!folio_test_partially_mapped(folio)) { - __folio_set_partially_mapped(folio); + folio_set_partially_mapped(folio); if (folio_test_pmd_mappable(folio)) count_vm_event(THP_DEFERRED_SPLIT_PAGE); count_mthp_stat(folio_order(folio), MTHP_STAT_SPLIT_DEFERRED); @@ -3752,7 +3752,7 @@ static unsigned long deferred_split_scan(struct shrinker *shrink, } else { /* We lost race with folio_put() */ if (folio_test_partially_mapped(folio)) { - __folio_clear_partially_mapped(folio); + folio_clear_partially_mapped(folio); mod_mthp_stat(folio_order(folio), MTHP_STAT_NR_ANON_PARTIALLY_MAPPED, -1); } diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 190fa05635f4..2fa87b9ecec6 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -5333,7 +5333,7 @@ again: break; } ret = copy_user_large_folio(new_folio, pte_folio, - ALIGN_DOWN(addr, sz), dst_vma); + addr, dst_vma); folio_put(pte_folio); if (ret) { folio_put(new_folio); @@ -6632,8 +6632,7 @@ int hugetlb_mfill_atomic_pte(pte_t *dst_pte, *foliop = NULL; goto out; } - ret = copy_user_large_folio(folio, *foliop, - ALIGN_DOWN(dst_addr, size), dst_vma); + ret = copy_user_large_folio(folio, *foliop, dst_addr, dst_vma); folio_put(*foliop); *foliop = NULL; if (ret) { @@ -7201,7 +7200,7 @@ pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma, spte = hugetlb_walk(svma, saddr, vma_mmu_pagesize(svma)); if (spte) { - get_page(virt_to_page(spte)); + ptdesc_pmd_pts_inc(virt_to_ptdesc(spte)); break; } } @@ -7216,7 +7215,7 @@ pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma, (pmd_t *)((unsigned long)spte & PAGE_MASK)); mm_inc_nr_pmds(mm); } else { - put_page(virt_to_page(spte)); + ptdesc_pmd_pts_dec(virt_to_ptdesc(spte)); } spin_unlock(&mm->page_table_lock); out: @@ -7228,10 +7227,6 @@ out: /* * unmap huge page backed by shared pte. * - * Hugetlb pte page is ref counted at the time of mapping. If pte is shared - * indicated by page_count > 1, unmap is achieved by clearing pud and - * decrementing the ref count. If count == 1, the pte page is not shared. - * * Called with page table lock held. * * returns: 1 successfully unmapped a shared pte page @@ -7240,18 +7235,20 @@ out: int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { + unsigned long sz = huge_page_size(hstate_vma(vma)); pgd_t *pgd = pgd_offset(mm, addr); p4d_t *p4d = p4d_offset(pgd, addr); pud_t *pud = pud_offset(p4d, addr); i_mmap_assert_write_locked(vma->vm_file->f_mapping); hugetlb_vma_assert_locked(vma); - BUG_ON(page_count(virt_to_page(ptep)) == 0); - if (page_count(virt_to_page(ptep)) == 1) + if (sz != PMD_SIZE) + return 0; + if (!ptdesc_pmd_pts_count(virt_to_ptdesc(ptep))) return 0; pud_clear(pud); - put_page(virt_to_page(ptep)); + ptdesc_pmd_pts_dec(virt_to_ptdesc(ptep)); mm_dec_nr_pmds(mm); return 1; } diff --git a/mm/kmemleak.c b/mm/kmemleak.c index 0400f5e8ac60..74f5f4c51ab8 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -373,7 +373,7 @@ static void print_unreferenced(struct seq_file *seq, for (i = 0; i < nr_entries; i++) { void *ptr = (void *)entries[i]; - warn_or_seq_printf(seq, " [<%pK>] %pS\n", ptr, ptr); + warn_or_seq_printf(seq, " %pS\n", ptr); } } diff --git a/mm/memfd.c b/mm/memfd.c index c17c3ea701a1..35a370d75c9a 100644 --- a/mm/memfd.c +++ b/mm/memfd.c @@ -170,7 +170,7 @@ static int memfd_wait_for_pins(struct address_space *mapping) return error; } -static unsigned int *memfd_file_seals_ptr(struct file *file) +unsigned int *memfd_file_seals_ptr(struct file *file) { if (shmem_file(file)) return &SHMEM_I(file_inode(file))->seals; diff --git a/mm/memory.c b/mm/memory.c index bdf77a3ec47b..d322ddfe6791 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -6780,9 +6780,10 @@ static inline int process_huge_page( return 0; } -static void clear_gigantic_page(struct folio *folio, unsigned long addr, +static void clear_gigantic_page(struct folio *folio, unsigned long addr_hint, unsigned int nr_pages) { + unsigned long addr = ALIGN_DOWN(addr_hint, folio_size(folio)); int i; might_sleep(); @@ -6816,13 +6817,14 @@ void folio_zero_user(struct folio *folio, unsigned long addr_hint) } static int copy_user_gigantic_page(struct folio *dst, struct folio *src, - unsigned long addr, + unsigned long addr_hint, struct vm_area_struct *vma, unsigned int nr_pages) { - int i; + unsigned long addr = ALIGN_DOWN(addr_hint, folio_size(dst)); struct page *dst_page; struct page *src_page; + int i; for (i = 0; i < nr_pages; i++) { dst_page = folio_page(dst, i); diff --git a/mm/mmap.c b/mm/mmap.c index 7fb4c1e97175..6183805f6f9e 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -47,6 +47,7 @@ #include <linux/oom.h> #include <linux/sched/mm.h> #include <linux/ksm.h> +#include <linux/memfd.h> #include <linux/uaccess.h> #include <asm/cacheflush.h> @@ -368,6 +369,7 @@ unsigned long do_mmap(struct file *file, unsigned long addr, if (file) { struct inode *inode = file_inode(file); + unsigned int seals = memfd_file_seals(file); unsigned long flags_mask; if (!file_mmap_ok(file, inode, pgoff, len)) @@ -408,6 +410,8 @@ unsigned long do_mmap(struct file *file, unsigned long addr, vm_flags |= VM_SHARED | VM_MAYSHARE; if (!(file->f_mode & FMODE_WRITE)) vm_flags &= ~(VM_MAYWRITE | VM_SHARED); + else if (is_readonly_sealed(seals, vm_flags)) + vm_flags &= ~VM_MAYWRITE; fallthrough; case MAP_PRIVATE: if (!(file->f_mode & FMODE_READ)) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index b6958333054d..de65e8b4f75f 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1238,13 +1238,15 @@ static void split_large_buddy(struct zone *zone, struct page *page, if (order > pageblock_order) order = pageblock_order; - while (pfn != end) { + do { int mt = get_pfnblock_migratetype(page, pfn); __free_one_page(page, pfn, zone, order, mt, fpi); pfn += 1 << order; + if (pfn == end) + break; page = pfn_to_page(pfn); - } + } while (1); } static void free_one_page(struct zone *zone, struct page *page, diff --git a/mm/readahead.c b/mm/readahead.c index 99fdb2b5b568..bf79275060f3 100644 --- a/mm/readahead.c +++ b/mm/readahead.c @@ -641,7 +641,11 @@ void page_cache_async_ra(struct readahead_control *ractl, 1UL << order); if (index == expected) { ra->start += ra->size; - ra->size = get_next_ra_size(ra, max_pages); + /* + * In the case of MADV_HUGEPAGE, the actual size might exceed + * the readahead window. + */ + ra->size = max(ra->size, get_next_ra_size(ra, max_pages)); ra->async_size = ra->size; goto readit; } diff --git a/mm/shmem.c b/mm/shmem.c index 568bb290bdce..dd4eb11c84b5 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -779,6 +779,14 @@ static bool shmem_huge_global_enabled(struct inode *inode, pgoff_t index, } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ +static void shmem_update_stats(struct folio *folio, int nr_pages) +{ + if (folio_test_pmd_mappable(folio)) + __lruvec_stat_mod_folio(folio, NR_SHMEM_THPS, nr_pages); + __lruvec_stat_mod_folio(folio, NR_FILE_PAGES, nr_pages); + __lruvec_stat_mod_folio(folio, NR_SHMEM, nr_pages); +} + /* * Somewhat like filemap_add_folio, but error if expected item has gone. */ @@ -813,10 +821,7 @@ static int shmem_add_to_page_cache(struct folio *folio, xas_store(&xas, folio); if (xas_error(&xas)) goto unlock; - if (folio_test_pmd_mappable(folio)) - __lruvec_stat_mod_folio(folio, NR_SHMEM_THPS, nr); - __lruvec_stat_mod_folio(folio, NR_FILE_PAGES, nr); - __lruvec_stat_mod_folio(folio, NR_SHMEM, nr); + shmem_update_stats(folio, nr); mapping->nrpages += nr; unlock: xas_unlock_irq(&xas); @@ -844,8 +849,7 @@ static void shmem_delete_from_page_cache(struct folio *folio, void *radswap) error = shmem_replace_entry(mapping, folio->index, folio, radswap); folio->mapping = NULL; mapping->nrpages -= nr; - __lruvec_stat_mod_folio(folio, NR_FILE_PAGES, -nr); - __lruvec_stat_mod_folio(folio, NR_SHMEM, -nr); + shmem_update_stats(folio, -nr); xa_unlock_irq(&mapping->i_pages); folio_put_refs(folio, nr); BUG_ON(error); @@ -1523,7 +1527,7 @@ try_split: !shmem_falloc->waitq && index >= shmem_falloc->start && index < shmem_falloc->next) - shmem_falloc->nr_unswapped++; + shmem_falloc->nr_unswapped += nr_pages; else shmem_falloc = NULL; spin_unlock(&inode->i_lock); @@ -1660,6 +1664,7 @@ unsigned long shmem_allowable_huge_orders(struct inode *inode, unsigned long mask = READ_ONCE(huge_shmem_orders_always); unsigned long within_size_orders = READ_ONCE(huge_shmem_orders_within_size); unsigned long vm_flags = vma ? vma->vm_flags : 0; + pgoff_t aligned_index; bool global_huge; loff_t i_size; int order; @@ -1694,9 +1699,9 @@ unsigned long shmem_allowable_huge_orders(struct inode *inode, /* Allow mTHP that will be fully within i_size. */ order = highest_order(within_size_orders); while (within_size_orders) { - index = round_up(index + 1, order); + aligned_index = round_up(index + 1, 1 << order); i_size = round_up(i_size_read(inode), PAGE_SIZE); - if (i_size >> PAGE_SHIFT >= index) { + if (i_size >> PAGE_SHIFT >= aligned_index) { mask |= within_size_orders; break; } @@ -1944,10 +1949,8 @@ static int shmem_replace_folio(struct folio **foliop, gfp_t gfp, } if (!error) { mem_cgroup_replace_folio(old, new); - __lruvec_stat_mod_folio(new, NR_FILE_PAGES, nr_pages); - __lruvec_stat_mod_folio(new, NR_SHMEM, nr_pages); - __lruvec_stat_mod_folio(old, NR_FILE_PAGES, -nr_pages); - __lruvec_stat_mod_folio(old, NR_SHMEM, -nr_pages); + shmem_update_stats(new, nr_pages); + shmem_update_stats(old, -nr_pages); } xa_unlock_irq(&swap_mapping->i_pages); diff --git a/mm/slub.c b/mm/slub.c index 15ba89fef89a..b9447a955f61 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -2199,9 +2199,24 @@ bool memcg_slab_post_charge(void *p, gfp_t flags) folio = virt_to_folio(p); if (!folio_test_slab(folio)) { - return folio_memcg_kmem(folio) || - (__memcg_kmem_charge_page(folio_page(folio, 0), flags, - folio_order(folio)) == 0); + int size; + + if (folio_memcg_kmem(folio)) + return true; + + if (__memcg_kmem_charge_page(folio_page(folio, 0), flags, + folio_order(folio))) + return false; + + /* + * This folio has already been accounted in the global stats but + * not in the memcg stats. So, subtract from the global and use + * the interface which adds to both global and memcg stats. + */ + size = folio_size(folio); + node_stat_mod_folio(folio, NR_SLAB_UNRECLAIMABLE_B, -size); + lruvec_stat_mod_folio(folio, NR_SLAB_UNRECLAIMABLE_B, size); + return true; } slab = folio_slab(folio); diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 0161cb4391e1..3f9255dfacb0 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -3369,7 +3369,8 @@ void vfree(const void *addr) struct page *page = vm->pages[i]; BUG_ON(!page); - mod_memcg_page_state(page, MEMCG_VMALLOC, -1); + if (!(vm->flags & VM_MAP_PUT_PAGES)) + mod_memcg_page_state(page, MEMCG_VMALLOC, -1); /* * High-order allocs for huge vmallocs are split, so * can be freed as an array of order-0 allocations @@ -3377,7 +3378,8 @@ void vfree(const void *addr) __free_page(page); cond_resched(); } - atomic_long_sub(vm->nr_pages, &nr_vmalloc_pages); + if (!(vm->flags & VM_MAP_PUT_PAGES)) + atomic_long_sub(vm->nr_pages, &nr_vmalloc_pages); kvfree(vm->pages); kfree(vm); } diff --git a/mm/vmscan.c b/mm/vmscan.c index 28ba2b06fc7d..67a680e4b484 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -374,7 +374,14 @@ unsigned long zone_reclaimable_pages(struct zone *zone) if (can_reclaim_anon_pages(NULL, zone_to_nid(zone), NULL)) nr += zone_page_state_snapshot(zone, NR_ZONE_INACTIVE_ANON) + zone_page_state_snapshot(zone, NR_ZONE_ACTIVE_ANON); - + /* + * If there are no reclaimable file-backed or anonymous pages, + * ensure zones with sufficient free pages are not skipped. + * This prevents zones like DMA32 from being ignored in reclaim + * scenarios where they can still help alleviate memory pressure. + */ + if (nr == 0) + nr = zone_page_state_snapshot(zone, NR_FREE_PAGES); return nr; } diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index 2243cec18ecc..53dea8ae96e4 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -990,16 +990,25 @@ static void batadv_tt_tvlv_container_update(struct batadv_priv *bat_priv) int tt_diff_len, tt_change_len = 0; int tt_diff_entries_num = 0; int tt_diff_entries_count = 0; + bool drop_changes = false; + size_t tt_extra_len = 0; u16 tvlv_len; tt_diff_entries_num = atomic_read(&bat_priv->tt.local_changes); tt_diff_len = batadv_tt_len(tt_diff_entries_num); /* if we have too many changes for one packet don't send any - * and wait for the tt table request which will be fragmented + * and wait for the tt table request so we can reply with the full + * (fragmented) table. + * + * The local change history should still be cleaned up so the next + * TT round can start again with a clean state. */ - if (tt_diff_len > bat_priv->soft_iface->mtu) + if (tt_diff_len > bat_priv->soft_iface->mtu) { tt_diff_len = 0; + tt_diff_entries_num = 0; + drop_changes = true; + } tvlv_len = batadv_tt_prepare_tvlv_local_data(bat_priv, &tt_data, &tt_change, &tt_diff_len); @@ -1008,7 +1017,7 @@ static void batadv_tt_tvlv_container_update(struct batadv_priv *bat_priv) tt_data->flags = BATADV_TT_OGM_DIFF; - if (tt_diff_len == 0) + if (!drop_changes && tt_diff_len == 0) goto container_register; spin_lock_bh(&bat_priv->tt.changes_list_lock); @@ -1027,6 +1036,9 @@ static void batadv_tt_tvlv_container_update(struct batadv_priv *bat_priv) } spin_unlock_bh(&bat_priv->tt.changes_list_lock); + tt_extra_len = batadv_tt_len(tt_diff_entries_num - + tt_diff_entries_count); + /* Keep the buffer for possible tt_request */ spin_lock_bh(&bat_priv->tt.last_changeset_lock); kfree(bat_priv->tt.last_changeset); @@ -1035,6 +1047,7 @@ static void batadv_tt_tvlv_container_update(struct batadv_priv *bat_priv) tt_change_len = batadv_tt_len(tt_diff_entries_count); /* check whether this new OGM has no changes due to size problems */ if (tt_diff_entries_count > 0) { + tt_diff_len -= tt_extra_len; /* if kmalloc() fails we will reply with the full table * instead of providing the diff */ @@ -1047,6 +1060,8 @@ static void batadv_tt_tvlv_container_update(struct batadv_priv *bat_priv) } spin_unlock_bh(&bat_priv->tt.last_changeset_lock); + /* Remove extra packet space for OGM */ + tvlv_len -= tt_extra_len; container_register: batadv_tvlv_container_register(bat_priv, BATADV_TVLV_TT, 1, tt_data, tvlv_len); @@ -2747,14 +2762,16 @@ static bool batadv_tt_global_valid(const void *entry_ptr, * * Fills the tvlv buff with the tt entries from the specified hash. If valid_cb * is not provided then this becomes a no-op. + * + * Return: Remaining unused length in tvlv_buff. */ -static void batadv_tt_tvlv_generate(struct batadv_priv *bat_priv, - struct batadv_hashtable *hash, - void *tvlv_buff, u16 tt_len, - bool (*valid_cb)(const void *, - const void *, - u8 *flags), - void *cb_data) +static u16 batadv_tt_tvlv_generate(struct batadv_priv *bat_priv, + struct batadv_hashtable *hash, + void *tvlv_buff, u16 tt_len, + bool (*valid_cb)(const void *, + const void *, + u8 *flags), + void *cb_data) { struct batadv_tt_common_entry *tt_common_entry; struct batadv_tvlv_tt_change *tt_change; @@ -2768,7 +2785,7 @@ static void batadv_tt_tvlv_generate(struct batadv_priv *bat_priv, tt_change = tvlv_buff; if (!valid_cb) - return; + return tt_len; rcu_read_lock(); for (i = 0; i < hash->size; i++) { @@ -2794,6 +2811,8 @@ static void batadv_tt_tvlv_generate(struct batadv_priv *bat_priv, } } rcu_read_unlock(); + + return batadv_tt_len(tt_tot - tt_num_entries); } /** @@ -3069,10 +3088,11 @@ static bool batadv_send_other_tt_response(struct batadv_priv *bat_priv, goto out; /* fill the rest of the tvlv with the real TT entries */ - batadv_tt_tvlv_generate(bat_priv, bat_priv->tt.global_hash, - tt_change, tt_len, - batadv_tt_global_valid, - req_dst_orig_node); + tvlv_len -= batadv_tt_tvlv_generate(bat_priv, + bat_priv->tt.global_hash, + tt_change, tt_len, + batadv_tt_global_valid, + req_dst_orig_node); } /* Don't send the response, if larger than fragmented packet. */ @@ -3196,9 +3216,11 @@ static bool batadv_send_my_tt_response(struct batadv_priv *bat_priv, goto out; /* fill the rest of the tvlv with the real TT entries */ - batadv_tt_tvlv_generate(bat_priv, bat_priv->tt.local_hash, - tt_change, tt_len, - batadv_tt_local_valid, NULL); + tvlv_len -= batadv_tt_tvlv_generate(bat_priv, + bat_priv->tt.local_hash, + tt_change, tt_len, + batadv_tt_local_valid, + NULL); } tvlv_tt_data->flags = BATADV_TT_RESPONSE; diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 72439764186e..b5553c08e731 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -57,7 +57,6 @@ DEFINE_RWLOCK(hci_dev_list_lock); /* HCI callback list */ LIST_HEAD(hci_cb_list); -DEFINE_MUTEX(hci_cb_list_lock); /* HCI ID Numbering */ static DEFINE_IDA(hci_index_ida); @@ -2993,9 +2992,7 @@ int hci_register_cb(struct hci_cb *cb) { BT_DBG("%p name %s", cb, cb->name); - mutex_lock(&hci_cb_list_lock); - list_add_tail(&cb->list, &hci_cb_list); - mutex_unlock(&hci_cb_list_lock); + list_add_tail_rcu(&cb->list, &hci_cb_list); return 0; } @@ -3005,9 +3002,8 @@ int hci_unregister_cb(struct hci_cb *cb) { BT_DBG("%p name %s", cb, cb->name); - mutex_lock(&hci_cb_list_lock); - list_del(&cb->list); - mutex_unlock(&hci_cb_list_lock); + list_del_rcu(&cb->list); + synchronize_rcu(); return 0; } diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 2b5ba8acd1d8..388d46c6a043 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -6872,38 +6872,27 @@ static void hci_le_create_big_complete_evt(struct hci_dev *hdev, void *data, return; hci_dev_lock(hdev); - rcu_read_lock(); /* Connect all BISes that are bound to the BIG */ - list_for_each_entry_rcu(conn, &hdev->conn_hash.list, list) { - if (bacmp(&conn->dst, BDADDR_ANY) || - conn->type != ISO_LINK || - conn->iso_qos.bcast.big != ev->handle) + while ((conn = hci_conn_hash_lookup_big_state(hdev, ev->handle, + BT_BOUND))) { + if (ev->status) { + hci_connect_cfm(conn, ev->status); + hci_conn_del(conn); continue; + } if (hci_conn_set_handle(conn, __le16_to_cpu(ev->bis_handle[i++]))) continue; - if (!ev->status) { - conn->state = BT_CONNECTED; - set_bit(HCI_CONN_BIG_CREATED, &conn->flags); - rcu_read_unlock(); - hci_debugfs_create_conn(conn); - hci_conn_add_sysfs(conn); - hci_iso_setup_path(conn); - rcu_read_lock(); - continue; - } - - hci_connect_cfm(conn, ev->status); - rcu_read_unlock(); - hci_conn_del(conn); - rcu_read_lock(); + conn->state = BT_CONNECTED; + set_bit(HCI_CONN_BIG_CREATED, &conn->flags); + hci_debugfs_create_conn(conn); + hci_conn_add_sysfs(conn); + hci_iso_setup_path(conn); } - rcu_read_unlock(); - if (!ev->status && !i) /* If no BISes have been connected for the BIG, * terminate. This is in case all bound connections diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c index 2272e1849ebd..022b86797acd 100644 --- a/net/bluetooth/hci_sock.c +++ b/net/bluetooth/hci_sock.c @@ -1926,7 +1926,7 @@ drop: } static int hci_sock_setsockopt_old(struct socket *sock, int level, int optname, - sockptr_t optval, unsigned int len) + sockptr_t optval, unsigned int optlen) { struct hci_ufilter uf = { .opcode = 0 }; struct sock *sk = sock->sk; @@ -1943,7 +1943,7 @@ static int hci_sock_setsockopt_old(struct socket *sock, int level, int optname, switch (optname) { case HCI_DATA_DIR: - err = bt_copy_from_sockptr(&opt, sizeof(opt), optval, len); + err = copy_safe_from_sockptr(&opt, sizeof(opt), optval, optlen); if (err) break; @@ -1954,7 +1954,7 @@ static int hci_sock_setsockopt_old(struct socket *sock, int level, int optname, break; case HCI_TIME_STAMP: - err = bt_copy_from_sockptr(&opt, sizeof(opt), optval, len); + err = copy_safe_from_sockptr(&opt, sizeof(opt), optval, optlen); if (err) break; @@ -1974,7 +1974,7 @@ static int hci_sock_setsockopt_old(struct socket *sock, int level, int optname, uf.event_mask[1] = *((u32 *) f->event_mask + 1); } - err = bt_copy_from_sockptr(&uf, sizeof(uf), optval, len); + err = copy_safe_from_sockptr(&uf, sizeof(uf), optval, optlen); if (err) break; @@ -2005,7 +2005,7 @@ done: } static int hci_sock_setsockopt(struct socket *sock, int level, int optname, - sockptr_t optval, unsigned int len) + sockptr_t optval, unsigned int optlen) { struct sock *sk = sock->sk; int err = 0; @@ -2015,7 +2015,7 @@ static int hci_sock_setsockopt(struct socket *sock, int level, int optname, if (level == SOL_HCI) return hci_sock_setsockopt_old(sock, level, optname, optval, - len); + optlen); if (level != SOL_BLUETOOTH) return -ENOPROTOOPT; @@ -2035,7 +2035,7 @@ static int hci_sock_setsockopt(struct socket *sock, int level, int optname, goto done; } - err = bt_copy_from_sockptr(&opt, sizeof(opt), optval, len); + err = copy_safe_from_sockptr(&opt, sizeof(opt), optval, optlen); if (err) break; diff --git a/net/bluetooth/iso.c b/net/bluetooth/iso.c index 5e2d9758bd3c..bda2f2da7d73 100644 --- a/net/bluetooth/iso.c +++ b/net/bluetooth/iso.c @@ -1129,6 +1129,7 @@ static int iso_listen_bis(struct sock *sk) return -EHOSTUNREACH; hci_dev_lock(hdev); + lock_sock(sk); /* Fail if user set invalid QoS */ if (iso_pi(sk)->qos_user_set && !check_bcast_qos(&iso_pi(sk)->qos)) { @@ -1158,10 +1159,10 @@ static int iso_listen_bis(struct sock *sk) goto unlock; } - hci_dev_put(hdev); - unlock: + release_sock(sk); hci_dev_unlock(hdev); + hci_dev_put(hdev); return err; } @@ -1188,6 +1189,7 @@ static int iso_sock_listen(struct socket *sock, int backlog) BT_DBG("sk %p backlog %d", sk, backlog); + sock_hold(sk); lock_sock(sk); if (sk->sk_state != BT_BOUND) { @@ -1200,10 +1202,16 @@ static int iso_sock_listen(struct socket *sock, int backlog) goto done; } - if (!bacmp(&iso_pi(sk)->dst, BDADDR_ANY)) + if (!bacmp(&iso_pi(sk)->dst, BDADDR_ANY)) { err = iso_listen_cis(sk); - else + } else { + /* Drop sock lock to avoid potential + * deadlock with the hdev lock. + */ + release_sock(sk); err = iso_listen_bis(sk); + lock_sock(sk); + } if (err) goto done; @@ -1215,6 +1223,7 @@ static int iso_sock_listen(struct socket *sock, int backlog) done: release_sock(sk); + sock_put(sk); return err; } @@ -1226,7 +1235,11 @@ static int iso_sock_accept(struct socket *sock, struct socket *newsock, long timeo; int err = 0; - lock_sock(sk); + /* Use explicit nested locking to avoid lockdep warnings generated + * because the parent socket and the child socket are locked on the + * same thread. + */ + lock_sock_nested(sk, SINGLE_DEPTH_NESTING); timeo = sock_rcvtimeo(sk, arg->flags & O_NONBLOCK); @@ -1257,7 +1270,7 @@ static int iso_sock_accept(struct socket *sock, struct socket *newsock, release_sock(sk); timeo = wait_woken(&wait, TASK_INTERRUPTIBLE, timeo); - lock_sock(sk); + lock_sock_nested(sk, SINGLE_DEPTH_NESTING); } remove_wait_queue(sk_sleep(sk), &wait); @@ -1398,6 +1411,7 @@ static void iso_conn_big_sync(struct sock *sk) * change. */ hci_dev_lock(hdev); + lock_sock(sk); if (!test_and_set_bit(BT_SK_BIG_SYNC, &iso_pi(sk)->flags)) { err = hci_le_big_create_sync(hdev, iso_pi(sk)->conn->hcon, @@ -1410,6 +1424,7 @@ static void iso_conn_big_sync(struct sock *sk) err); } + release_sock(sk); hci_dev_unlock(hdev); } @@ -1418,39 +1433,57 @@ static int iso_sock_recvmsg(struct socket *sock, struct msghdr *msg, { struct sock *sk = sock->sk; struct iso_pinfo *pi = iso_pi(sk); + bool early_ret = false; + int err = 0; BT_DBG("sk %p", sk); if (test_and_clear_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags)) { + sock_hold(sk); lock_sock(sk); + switch (sk->sk_state) { case BT_CONNECT2: if (test_bit(BT_SK_PA_SYNC, &pi->flags)) { + release_sock(sk); iso_conn_big_sync(sk); + lock_sock(sk); + sk->sk_state = BT_LISTEN; } else { iso_conn_defer_accept(pi->conn->hcon); sk->sk_state = BT_CONFIG; } - release_sock(sk); - return 0; + + early_ret = true; + break; case BT_CONNECTED: if (test_bit(BT_SK_PA_SYNC, &iso_pi(sk)->flags)) { + release_sock(sk); iso_conn_big_sync(sk); + lock_sock(sk); + sk->sk_state = BT_LISTEN; - release_sock(sk); - return 0; + early_ret = true; } - release_sock(sk); break; case BT_CONNECT: release_sock(sk); - return iso_connect_cis(sk); + err = iso_connect_cis(sk); + lock_sock(sk); + + early_ret = true; + break; default: - release_sock(sk); break; } + + release_sock(sk); + sock_put(sk); + + if (early_ret) + return err; } return bt_sock_recvmsg(sock, msg, len, flags); @@ -1566,7 +1599,7 @@ static int iso_sock_setsockopt(struct socket *sock, int level, int optname, break; } - err = bt_copy_from_sockptr(&opt, sizeof(opt), optval, optlen); + err = copy_safe_from_sockptr(&opt, sizeof(opt), optval, optlen); if (err) break; @@ -1577,7 +1610,7 @@ static int iso_sock_setsockopt(struct socket *sock, int level, int optname, break; case BT_PKT_STATUS: - err = bt_copy_from_sockptr(&opt, sizeof(opt), optval, optlen); + err = copy_safe_from_sockptr(&opt, sizeof(opt), optval, optlen); if (err) break; @@ -1596,7 +1629,7 @@ static int iso_sock_setsockopt(struct socket *sock, int level, int optname, break; } - err = bt_copy_from_sockptr(&qos, sizeof(qos), optval, optlen); + err = copy_safe_from_sockptr(&qos, sizeof(qos), optval, optlen); if (err) break; @@ -1617,8 +1650,8 @@ static int iso_sock_setsockopt(struct socket *sock, int level, int optname, break; } - err = bt_copy_from_sockptr(iso_pi(sk)->base, optlen, optval, - optlen); + err = copy_safe_from_sockptr(iso_pi(sk)->base, optlen, optval, + optlen); if (err) break; @@ -2104,6 +2137,11 @@ done: return HCI_LM_ACCEPT; } +static bool iso_match(struct hci_conn *hcon) +{ + return hcon->type == ISO_LINK || hcon->type == LE_LINK; +} + static void iso_connect_cfm(struct hci_conn *hcon, __u8 status) { if (hcon->type != ISO_LINK) { @@ -2285,6 +2323,7 @@ drop: static struct hci_cb iso_cb = { .name = "ISO", + .match = iso_match, .connect_cfm = iso_connect_cfm, .disconn_cfm = iso_disconn_cfm, }; diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index 6544c1ed7143..27b4c4a2ba1f 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -7217,6 +7217,11 @@ static struct l2cap_chan *l2cap_global_fixed_chan(struct l2cap_chan *c, return NULL; } +static bool l2cap_match(struct hci_conn *hcon) +{ + return hcon->type == ACL_LINK || hcon->type == LE_LINK; +} + static void l2cap_connect_cfm(struct hci_conn *hcon, u8 status) { struct hci_dev *hdev = hcon->hdev; @@ -7224,9 +7229,6 @@ static void l2cap_connect_cfm(struct hci_conn *hcon, u8 status) struct l2cap_chan *pchan; u8 dst_type; - if (hcon->type != ACL_LINK && hcon->type != LE_LINK) - return; - BT_DBG("hcon %p bdaddr %pMR status %d", hcon, &hcon->dst, status); if (status) { @@ -7291,9 +7293,6 @@ int l2cap_disconn_ind(struct hci_conn *hcon) static void l2cap_disconn_cfm(struct hci_conn *hcon, u8 reason) { - if (hcon->type != ACL_LINK && hcon->type != LE_LINK) - return; - BT_DBG("hcon %p reason %d", hcon, reason); l2cap_conn_del(hcon, bt_to_errno(reason)); @@ -7572,6 +7571,7 @@ drop: static struct hci_cb l2cap_cb = { .name = "L2CAP", + .match = l2cap_match, .connect_cfm = l2cap_connect_cfm, .disconn_cfm = l2cap_disconn_cfm, .security_cfm = l2cap_security_cfm, diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index 18e89e764f3b..3d2553dcdb1b 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -755,7 +755,8 @@ static int l2cap_sock_setsockopt_old(struct socket *sock, int optname, opts.max_tx = chan->max_tx; opts.txwin_size = chan->tx_win; - err = bt_copy_from_sockptr(&opts, sizeof(opts), optval, optlen); + err = copy_safe_from_sockptr(&opts, sizeof(opts), optval, + optlen); if (err) break; @@ -800,7 +801,7 @@ static int l2cap_sock_setsockopt_old(struct socket *sock, int optname, break; case L2CAP_LM: - err = bt_copy_from_sockptr(&opt, sizeof(opt), optval, optlen); + err = copy_safe_from_sockptr(&opt, sizeof(opt), optval, optlen); if (err) break; @@ -909,7 +910,7 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname, sec.level = BT_SECURITY_LOW; - err = bt_copy_from_sockptr(&sec, sizeof(sec), optval, optlen); + err = copy_safe_from_sockptr(&sec, sizeof(sec), optval, optlen); if (err) break; @@ -956,7 +957,7 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname, break; } - err = bt_copy_from_sockptr(&opt, sizeof(opt), optval, optlen); + err = copy_safe_from_sockptr(&opt, sizeof(opt), optval, optlen); if (err) break; @@ -970,7 +971,7 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname, break; case BT_FLUSHABLE: - err = bt_copy_from_sockptr(&opt, sizeof(opt), optval, optlen); + err = copy_safe_from_sockptr(&opt, sizeof(opt), optval, optlen); if (err) break; @@ -1004,7 +1005,7 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname, pwr.force_active = BT_POWER_FORCE_ACTIVE_ON; - err = bt_copy_from_sockptr(&pwr, sizeof(pwr), optval, optlen); + err = copy_safe_from_sockptr(&pwr, sizeof(pwr), optval, optlen); if (err) break; @@ -1015,7 +1016,7 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname, break; case BT_CHANNEL_POLICY: - err = bt_copy_from_sockptr(&opt, sizeof(opt), optval, optlen); + err = copy_safe_from_sockptr(&opt, sizeof(opt), optval, optlen); if (err) break; @@ -1046,7 +1047,7 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname, break; } - err = bt_copy_from_sockptr(&mtu, sizeof(mtu), optval, optlen); + err = copy_safe_from_sockptr(&mtu, sizeof(mtu), optval, optlen); if (err) break; @@ -1076,7 +1077,8 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname, break; } - err = bt_copy_from_sockptr(&mode, sizeof(mode), optval, optlen); + err = copy_safe_from_sockptr(&mode, sizeof(mode), optval, + optlen); if (err) break; diff --git a/net/bluetooth/rfcomm/core.c b/net/bluetooth/rfcomm/core.c index ad5177e3a69b..4c56ca5a216c 100644 --- a/net/bluetooth/rfcomm/core.c +++ b/net/bluetooth/rfcomm/core.c @@ -2134,6 +2134,11 @@ static int rfcomm_run(void *unused) return 0; } +static bool rfcomm_match(struct hci_conn *hcon) +{ + return hcon->type == ACL_LINK; +} + static void rfcomm_security_cfm(struct hci_conn *conn, u8 status, u8 encrypt) { struct rfcomm_session *s; @@ -2180,6 +2185,7 @@ static void rfcomm_security_cfm(struct hci_conn *conn, u8 status, u8 encrypt) static struct hci_cb rfcomm_cb = { .name = "RFCOMM", + .match = rfcomm_match, .security_cfm = rfcomm_security_cfm }; diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c index 40766f8119ed..913402806fa0 100644 --- a/net/bluetooth/rfcomm/sock.c +++ b/net/bluetooth/rfcomm/sock.c @@ -629,10 +629,9 @@ static int rfcomm_sock_setsockopt_old(struct socket *sock, int optname, switch (optname) { case RFCOMM_LM: - if (bt_copy_from_sockptr(&opt, sizeof(opt), optval, optlen)) { - err = -EFAULT; + err = copy_safe_from_sockptr(&opt, sizeof(opt), optval, optlen); + if (err) break; - } if (opt & RFCOMM_LM_FIPS) { err = -EINVAL; @@ -685,7 +684,7 @@ static int rfcomm_sock_setsockopt(struct socket *sock, int level, int optname, sec.level = BT_SECURITY_LOW; - err = bt_copy_from_sockptr(&sec, sizeof(sec), optval, optlen); + err = copy_safe_from_sockptr(&sec, sizeof(sec), optval, optlen); if (err) break; @@ -703,7 +702,7 @@ static int rfcomm_sock_setsockopt(struct socket *sock, int level, int optname, break; } - err = bt_copy_from_sockptr(&opt, sizeof(opt), optval, optlen); + err = copy_safe_from_sockptr(&opt, sizeof(opt), optval, optlen); if (err) break; diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index 1c7252a36866..071c404c790a 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -267,10 +267,13 @@ static int sco_connect(struct sock *sk) else type = SCO_LINK; - if (sco_pi(sk)->setting == BT_VOICE_TRANSPARENT && - (!lmp_transp_capable(hdev) || !lmp_esco_capable(hdev))) { - err = -EOPNOTSUPP; - goto unlock; + switch (sco_pi(sk)->setting & SCO_AIRMODE_MASK) { + case SCO_AIRMODE_TRANSP: + if (!lmp_transp_capable(hdev) || !lmp_esco_capable(hdev)) { + err = -EOPNOTSUPP; + goto unlock; + } + break; } hcon = hci_connect_sco(hdev, type, &sco_pi(sk)->dst, @@ -853,7 +856,7 @@ static int sco_sock_setsockopt(struct socket *sock, int level, int optname, break; } - err = bt_copy_from_sockptr(&opt, sizeof(opt), optval, optlen); + err = copy_safe_from_sockptr(&opt, sizeof(opt), optval, optlen); if (err) break; @@ -872,18 +875,11 @@ static int sco_sock_setsockopt(struct socket *sock, int level, int optname, voice.setting = sco_pi(sk)->setting; - err = bt_copy_from_sockptr(&voice, sizeof(voice), optval, - optlen); + err = copy_safe_from_sockptr(&voice, sizeof(voice), optval, + optlen); if (err) break; - /* Explicitly check for these values */ - if (voice.setting != BT_VOICE_TRANSPARENT && - voice.setting != BT_VOICE_CVSD_16BIT) { - err = -EINVAL; - break; - } - sco_pi(sk)->setting = voice.setting; hdev = hci_get_route(&sco_pi(sk)->dst, &sco_pi(sk)->src, BDADDR_BREDR); @@ -891,14 +887,19 @@ static int sco_sock_setsockopt(struct socket *sock, int level, int optname, err = -EBADFD; break; } - if (enhanced_sync_conn_capable(hdev) && - voice.setting == BT_VOICE_TRANSPARENT) - sco_pi(sk)->codec.id = BT_CODEC_TRANSPARENT; + + switch (sco_pi(sk)->setting & SCO_AIRMODE_MASK) { + case SCO_AIRMODE_TRANSP: + if (enhanced_sync_conn_capable(hdev)) + sco_pi(sk)->codec.id = BT_CODEC_TRANSPARENT; + break; + } + hci_dev_put(hdev); break; case BT_PKT_STATUS: - err = bt_copy_from_sockptr(&opt, sizeof(opt), optval, optlen); + err = copy_safe_from_sockptr(&opt, sizeof(opt), optval, optlen); if (err) break; @@ -941,7 +942,8 @@ static int sco_sock_setsockopt(struct socket *sock, int level, int optname, break; } - err = bt_copy_from_sockptr(buffer, optlen, optval, optlen); + err = copy_struct_from_sockptr(buffer, sizeof(buffer), optval, + optlen); if (err) { hci_dev_put(hdev); break; @@ -1353,11 +1355,13 @@ int sco_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, __u8 *flags) return lm; } -static void sco_connect_cfm(struct hci_conn *hcon, __u8 status) +static bool sco_match(struct hci_conn *hcon) { - if (hcon->type != SCO_LINK && hcon->type != ESCO_LINK) - return; + return hcon->type == SCO_LINK || hcon->type == ESCO_LINK; +} +static void sco_connect_cfm(struct hci_conn *hcon, __u8 status) +{ BT_DBG("hcon %p bdaddr %pMR status %u", hcon, &hcon->dst, status); if (!status) { @@ -1372,9 +1376,6 @@ static void sco_connect_cfm(struct hci_conn *hcon, __u8 status) static void sco_disconn_cfm(struct hci_conn *hcon, __u8 reason) { - if (hcon->type != SCO_LINK && hcon->type != ESCO_LINK) - return; - BT_DBG("hcon %p reason %d", hcon, reason); sco_conn_del(hcon, bt_to_errno(reason)); @@ -1400,6 +1401,7 @@ drop: static struct hci_cb sco_cb = { .name = "SCO", + .match = sco_match, .connect_cfm = sco_connect_cfm, .disconn_cfm = sco_disconn_cfm, }; diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index 9d078b37fe0b..abac770bc0b4 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -1173,6 +1173,8 @@ EXPORT_SYMBOL(ceph_osdc_new_request); int __ceph_alloc_sparse_ext_map(struct ceph_osd_req_op *op, int cnt) { + WARN_ON(op->op != CEPH_OSD_OP_SPARSE_READ); + op->extent.sparse_ext_cnt = cnt; op->extent.sparse_ext = kmalloc_array(cnt, sizeof(*op->extent.sparse_ext), diff --git a/net/core/dev.c b/net/core/dev.c index 8453e14d301b..f3fa8353d262 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3640,8 +3640,10 @@ int skb_csum_hwoffload_help(struct sk_buff *skb, if (features & (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM)) { if (vlan_get_protocol(skb) == htons(ETH_P_IPV6) && - skb_network_header_len(skb) != sizeof(struct ipv6hdr)) + skb_network_header_len(skb) != sizeof(struct ipv6hdr) && + !ipv6_has_hopopt_jumbo(skb)) goto sw_checksum; + switch (skb->csum_offset) { case offsetof(struct tcphdr, check): case offsetof(struct udphdr, check): diff --git a/net/core/filter.c b/net/core/filter.c index 9a459213d283..54a53fae9e98 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -3751,13 +3751,22 @@ static const struct bpf_func_proto bpf_skb_adjust_room_proto = { static u32 __bpf_skb_min_len(const struct sk_buff *skb) { - u32 min_len = skb_network_offset(skb); + int offset = skb_network_offset(skb); + u32 min_len = 0; - if (skb_transport_header_was_set(skb)) - min_len = skb_transport_offset(skb); - if (skb->ip_summed == CHECKSUM_PARTIAL) - min_len = skb_checksum_start_offset(skb) + - skb->csum_offset + sizeof(__sum16); + if (offset > 0) + min_len = offset; + if (skb_transport_header_was_set(skb)) { + offset = skb_transport_offset(skb); + if (offset > 0) + min_len = offset; + } + if (skb->ip_summed == CHECKSUM_PARTIAL) { + offset = skb_checksum_start_offset(skb) + + skb->csum_offset + sizeof(__sum16); + if (offset > 0) + min_len = offset; + } return min_len; } @@ -7909,42 +7918,37 @@ static const struct bpf_func_proto bpf_tcp_raw_check_syncookie_ipv6_proto = { #endif /* CONFIG_INET */ -bool bpf_helper_changes_pkt_data(void *func) -{ - if (func == bpf_skb_vlan_push || - func == bpf_skb_vlan_pop || - func == bpf_skb_store_bytes || - func == bpf_skb_change_proto || - func == bpf_skb_change_head || - func == sk_skb_change_head || - func == bpf_skb_change_tail || - func == sk_skb_change_tail || - func == bpf_skb_adjust_room || - func == sk_skb_adjust_room || - func == bpf_skb_pull_data || - func == sk_skb_pull_data || - func == bpf_clone_redirect || - func == bpf_l3_csum_replace || - func == bpf_l4_csum_replace || - func == bpf_xdp_adjust_head || - func == bpf_xdp_adjust_meta || - func == bpf_msg_pull_data || - func == bpf_msg_push_data || - func == bpf_msg_pop_data || - func == bpf_xdp_adjust_tail || -#if IS_ENABLED(CONFIG_IPV6_SEG6_BPF) - func == bpf_lwt_seg6_store_bytes || - func == bpf_lwt_seg6_adjust_srh || - func == bpf_lwt_seg6_action || -#endif -#ifdef CONFIG_INET - func == bpf_sock_ops_store_hdr_opt || -#endif - func == bpf_lwt_in_push_encap || - func == bpf_lwt_xmit_push_encap) +bool bpf_helper_changes_pkt_data(enum bpf_func_id func_id) +{ + switch (func_id) { + case BPF_FUNC_clone_redirect: + case BPF_FUNC_l3_csum_replace: + case BPF_FUNC_l4_csum_replace: + case BPF_FUNC_lwt_push_encap: + case BPF_FUNC_lwt_seg6_action: + case BPF_FUNC_lwt_seg6_adjust_srh: + case BPF_FUNC_lwt_seg6_store_bytes: + case BPF_FUNC_msg_pop_data: + case BPF_FUNC_msg_pull_data: + case BPF_FUNC_msg_push_data: + case BPF_FUNC_skb_adjust_room: + case BPF_FUNC_skb_change_head: + case BPF_FUNC_skb_change_proto: + case BPF_FUNC_skb_change_tail: + case BPF_FUNC_skb_pull_data: + case BPF_FUNC_skb_store_bytes: + case BPF_FUNC_skb_vlan_pop: + case BPF_FUNC_skb_vlan_push: + case BPF_FUNC_store_hdr_opt: + case BPF_FUNC_xdp_adjust_head: + case BPF_FUNC_xdp_adjust_meta: + case BPF_FUNC_xdp_adjust_tail: + /* tail-called program could call any of the above */ + case BPF_FUNC_tail_call: return true; - - return false; + default: + return false; + } } const struct bpf_func_proto bpf_event_output_data_proto __weak; diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index e39479f1c9a4..70fea7c1a4b0 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -443,6 +443,21 @@ out_free: goto out; } +static LLIST_HEAD(defer_free_list); + +static void net_complete_free(void) +{ + struct llist_node *kill_list; + struct net *net, *next; + + /* Get the list of namespaces to free from last round. */ + kill_list = llist_del_all(&defer_free_list); + + llist_for_each_entry_safe(net, next, kill_list, defer_free_list) + kmem_cache_free(net_cachep, net); + +} + static void net_free(struct net *net) { if (refcount_dec_and_test(&net->passive)) { @@ -451,7 +466,8 @@ static void net_free(struct net *net) /* There should not be any trackers left there. */ ref_tracker_dir_exit(&net->notrefcnt_tracker); - kmem_cache_free(net_cachep, net); + /* Wait for an extra rcu_barrier() before final free. */ + llist_add(&net->defer_free_list, &defer_free_list); } } @@ -636,6 +652,8 @@ static void cleanup_net(struct work_struct *work) */ rcu_barrier(); + net_complete_free(); + /* Finally it is safe to free my network namespace structure */ list_for_each_entry_safe(net, tmp, &net_exit_list, exit_list) { list_del_init(&net->exit_list); diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c index d2baa1af9df0..d58270b48cb2 100644 --- a/net/core/netdev-genl.c +++ b/net/core/netdev-genl.c @@ -228,8 +228,12 @@ int netdev_nl_napi_get_doit(struct sk_buff *skb, struct genl_info *info) rcu_read_unlock(); rtnl_unlock(); - if (err) + if (err) { + goto err_free_msg; + } else if (!rsp->len) { + err = -ENOENT; goto err_free_msg; + } return genlmsg_reply(rsp, info); @@ -359,10 +363,10 @@ static int netdev_nl_queue_fill(struct sk_buff *rsp, struct net_device *netdev, u32 q_idx, u32 q_type, const struct genl_info *info) { - int err = 0; + int err; if (!(netdev->flags & IFF_UP)) - return err; + return -ENOENT; err = netdev_nl_queue_validate(netdev, q_idx, q_type); if (err) @@ -417,24 +421,21 @@ netdev_nl_queue_dump_one(struct net_device *netdev, struct sk_buff *rsp, struct netdev_nl_dump_ctx *ctx) { int err = 0; - int i; if (!(netdev->flags & IFF_UP)) return err; - for (i = ctx->rxq_idx; i < netdev->real_num_rx_queues;) { - err = netdev_nl_queue_fill_one(rsp, netdev, i, + for (; ctx->rxq_idx < netdev->real_num_rx_queues; ctx->rxq_idx++) { + err = netdev_nl_queue_fill_one(rsp, netdev, ctx->rxq_idx, NETDEV_QUEUE_TYPE_RX, info); if (err) return err; - ctx->rxq_idx = i++; } - for (i = ctx->txq_idx; i < netdev->real_num_tx_queues;) { - err = netdev_nl_queue_fill_one(rsp, netdev, i, + for (; ctx->txq_idx < netdev->real_num_tx_queues; ctx->txq_idx++) { + err = netdev_nl_queue_fill_one(rsp, netdev, ctx->txq_idx, NETDEV_QUEUE_TYPE_TX, info); if (err) return err; - ctx->txq_idx = i++; } return err; @@ -600,7 +601,7 @@ netdev_nl_stats_by_queue(struct net_device *netdev, struct sk_buff *rsp, i, info); if (err) return err; - ctx->rxq_idx = i++; + ctx->rxq_idx = ++i; } i = ctx->txq_idx; while (ops->get_queue_stats_tx && i < netdev->real_num_tx_queues) { @@ -608,7 +609,7 @@ netdev_nl_stats_by_queue(struct net_device *netdev, struct sk_buff *rsp, i, info); if (err) return err; - ctx->txq_idx = i++; + ctx->txq_idx = ++i; } ctx->rxq_idx = 0; diff --git a/net/core/skmsg.c b/net/core/skmsg.c index e90fbab703b2..8ad7e6755fd6 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -445,8 +445,10 @@ int sk_msg_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg, if (likely(!peek)) { sge->offset += copy; sge->length -= copy; - if (!msg_rx->skb) + if (!msg_rx->skb) { sk_mem_uncharge(sk, copy); + atomic_sub(copy, &sk->sk_rmem_alloc); + } msg_rx->sg.size -= copy; if (!sge->length) { @@ -772,6 +774,8 @@ static void __sk_psock_purge_ingress_msg(struct sk_psock *psock) list_for_each_entry_safe(msg, tmp, &psock->ingress_msg, list) { list_del(&msg->list); + if (!msg->skb) + atomic_sub(msg->sg.size, &psock->sk->sk_rmem_alloc); sk_msg_free(psock->sk, msg); kfree(msg); } diff --git a/net/core/sock.c b/net/core/sock.c index da50df485090..a83f64a1d96a 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1300,7 +1300,10 @@ int sk_setsockopt(struct sock *sk, int level, int optname, sk->sk_reuse = (valbool ? SK_CAN_REUSE : SK_NO_REUSE); break; case SO_REUSEPORT: - sk->sk_reuseport = valbool; + if (valbool && !sk_is_inet(sk)) + ret = -EOPNOTSUPP; + else + sk->sk_reuseport = valbool; break; case SO_DONTROUTE: sock_valbool_flag(sk, SOCK_LOCALROUTE, valbool); diff --git a/net/core/sock_map.c b/net/core/sock_map.c index 78347d7d25ef..f1b9b3958792 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -159,6 +159,7 @@ static void sock_map_del_link(struct sock *sk, verdict_stop = true; list_del(&link->list); sk_psock_free_link(link); + break; } } spin_unlock_bh(&psock->link_lock); @@ -411,12 +412,11 @@ static void *sock_map_lookup_sys(struct bpf_map *map, void *key) static int __sock_map_delete(struct bpf_stab *stab, struct sock *sk_test, struct sock **psk) { - struct sock *sk; + struct sock *sk = NULL; int err = 0; spin_lock_bh(&stab->lock); - sk = *psk; - if (!sk_test || sk_test == sk) + if (!sk_test || sk_test == *psk) sk = xchg(psk, NULL); if (likely(sk)) diff --git a/net/dsa/tag.h b/net/dsa/tag.h index d5707870906b..5d80ddad4ff6 100644 --- a/net/dsa/tag.h +++ b/net/dsa/tag.h @@ -138,9 +138,10 @@ static inline void dsa_software_untag_vlan_unaware_bridge(struct sk_buff *skb, * dsa_software_vlan_untag: Software VLAN untagging in DSA receive path * @skb: Pointer to socket buffer (packet) * - * Receive path method for switches which cannot avoid tagging all packets - * towards the CPU port. Called when ds->untag_bridge_pvid (legacy) or - * ds->untag_vlan_aware_bridge_pvid is set to true. + * Receive path method for switches which send some packets as VLAN-tagged + * towards the CPU port (generally from VLAN-aware bridge ports) even when the + * packet was not tagged on the wire. Called when ds->untag_bridge_pvid + * (legacy) or ds->untag_vlan_aware_bridge_pvid is set to true. * * As a side effect of this method, any VLAN tag from the skb head is moved * to hwaccel. @@ -149,14 +150,19 @@ static inline struct sk_buff *dsa_software_vlan_untag(struct sk_buff *skb) { struct dsa_port *dp = dsa_user_to_port(skb->dev); struct net_device *br = dsa_port_bridge_dev_get(dp); - u16 vid; + u16 vid, proto; + int err; /* software untagging for standalone ports not yet necessary */ if (!br) return skb; + err = br_vlan_get_proto(br, &proto); + if (err) + return skb; + /* Move VLAN tag from data to hwaccel */ - if (!skb_vlan_tag_present(skb)) { + if (!skb_vlan_tag_present(skb) && skb->protocol == htons(proto)) { skb = skb_vlan_untag(skb); if (!skb) return NULL; diff --git a/net/dsa/tag_ocelot_8021q.c b/net/dsa/tag_ocelot_8021q.c index 8e8b1bef6af6..11ea8cfd6266 100644 --- a/net/dsa/tag_ocelot_8021q.c +++ b/net/dsa/tag_ocelot_8021q.c @@ -79,7 +79,7 @@ static struct sk_buff *ocelot_xmit(struct sk_buff *skb, static struct sk_buff *ocelot_rcv(struct sk_buff *skb, struct net_device *netdev) { - int src_port, switch_id; + int src_port = -1, switch_id = -1; dsa_8021q_rcv(skb, &src_port, &switch_id, NULL, NULL); diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index 25505f9b724c..09b73acf037a 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -294,7 +294,7 @@ static int ip_tunnel_bind_dev(struct net_device *dev) ip_tunnel_init_flow(&fl4, iph->protocol, iph->daddr, iph->saddr, tunnel->parms.o_key, - iph->tos & INET_DSCP_MASK, dev_net(dev), + iph->tos & INET_DSCP_MASK, tunnel->net, tunnel->parms.link, tunnel->fwmark, 0, 0); rt = ip_route_output_key(tunnel->net, &fl4); @@ -611,7 +611,7 @@ void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, } ip_tunnel_init_flow(&fl4, proto, key->u.ipv4.dst, key->u.ipv4.src, tunnel_id_to_key32(key->tun_id), - tos & INET_DSCP_MASK, dev_net(dev), 0, skb->mark, + tos & INET_DSCP_MASK, tunnel->net, 0, skb->mark, skb_get_hash(skb), key->flow_flags); if (!tunnel_hlen) @@ -774,7 +774,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, ip_tunnel_init_flow(&fl4, protocol, dst, tnl_params->saddr, tunnel->parms.o_key, tos & INET_DSCP_MASK, - dev_net(dev), READ_ONCE(tunnel->parms.link), + tunnel->net, READ_ONCE(tunnel->parms.link), tunnel->fwmark, skb_get_hash(skb), 0); if (ip_tunnel_encap(skb, &tunnel->encap, &protocol, &fl4) < 0) diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index 99cef92e6290..392678ae80f4 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -49,13 +49,14 @@ static int bpf_tcp_ingress(struct sock *sk, struct sk_psock *psock, sge = sk_msg_elem(msg, i); size = (apply && apply_bytes < sge->length) ? apply_bytes : sge->length; - if (!sk_wmem_schedule(sk, size)) { + if (!__sk_rmem_schedule(sk, size, false)) { if (!copied) ret = -ENOMEM; break; } sk_mem_charge(sk, size); + atomic_add(size, &sk->sk_rmem_alloc); sk_msg_xfer(tmp, msg, i, size); copied += size; if (sge->length) @@ -74,7 +75,8 @@ static int bpf_tcp_ingress(struct sock *sk, struct sk_psock *psock, if (!ret) { msg->sg.start = i; - sk_psock_queue_msg(psock, tmp); + if (!sk_psock_queue_msg(psock, tmp)) + atomic_sub(copied, &sk->sk_rmem_alloc); sk_psock_data_ready(sk, psock); } else { sk_msg_free(sk, tmp); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 2d844e1f867f..2d43b29da15e 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -7328,6 +7328,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, if (unlikely(!inet_csk_reqsk_queue_hash_add(sk, req, req->timeout))) { reqsk_free(req); + dst_release(dst); return 0; } diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 68804fd01daf..8efc58716ce9 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -883,8 +883,10 @@ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb, unsigned int size; if (mptcp_syn_options(sk, skb, &size, &opts->mptcp)) { - opts->options |= OPTION_MPTCP; - remaining -= size; + if (remaining >= size) { + opts->options |= OPTION_MPTCP; + remaining -= size; + } } } diff --git a/net/ipv6/ila/ila_xlat.c b/net/ipv6/ila/ila_xlat.c index 534a4498e280..fff09f5a796a 100644 --- a/net/ipv6/ila/ila_xlat.c +++ b/net/ipv6/ila/ila_xlat.c @@ -200,6 +200,8 @@ static const struct nf_hook_ops ila_nf_hook_ops[] = { }, }; +static DEFINE_MUTEX(ila_mutex); + static int ila_add_mapping(struct net *net, struct ila_xlat_params *xp) { struct ila_net *ilan = net_generic(net, ila_net_id); @@ -207,16 +209,20 @@ static int ila_add_mapping(struct net *net, struct ila_xlat_params *xp) spinlock_t *lock = ila_get_lock(ilan, xp->ip.locator_match); int err = 0, order; - if (!ilan->xlat.hooks_registered) { + if (!READ_ONCE(ilan->xlat.hooks_registered)) { /* We defer registering net hooks in the namespace until the * first mapping is added. */ - err = nf_register_net_hooks(net, ila_nf_hook_ops, - ARRAY_SIZE(ila_nf_hook_ops)); + mutex_lock(&ila_mutex); + if (!ilan->xlat.hooks_registered) { + err = nf_register_net_hooks(net, ila_nf_hook_ops, + ARRAY_SIZE(ila_nf_hook_ops)); + if (!err) + WRITE_ONCE(ilan->xlat.hooks_registered, true); + } + mutex_unlock(&ila_mutex); if (err) return err; - - ilan->xlat.hooks_registered = true; } ila = kzalloc(sizeof(*ila), GFP_KERNEL); diff --git a/net/llc/llc_input.c b/net/llc/llc_input.c index 51bccfb00a9c..61b0159b2fbe 100644 --- a/net/llc/llc_input.c +++ b/net/llc/llc_input.c @@ -124,8 +124,8 @@ static inline int llc_fixup_skb(struct sk_buff *skb) if (unlikely(!pskb_may_pull(skb, llc_len))) return 0; - skb->transport_header += llc_len; skb_pull(skb, llc_len); + skb_reset_transport_header(skb); if (skb->protocol == htons(ETH_P_802_2)) { __be16 pdulen; s32 data_size; diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 6dfc61a9acd4..f11fd360b422 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -1061,13 +1061,13 @@ ieee80211_copy_mbssid_beacon(u8 *pos, struct cfg80211_mbssid_elems *dst, { int i, offset = 0; + dst->cnt = src->cnt; for (i = 0; i < src->cnt; i++) { memcpy(pos + offset, src->elem[i].data, src->elem[i].len); dst->elem[i].len = src->elem[i].len; dst->elem[i].data = pos + offset; offset += dst->elem[i].len; } - dst->cnt = src->cnt; return offset; } @@ -1911,6 +1911,8 @@ static int sta_link_apply_parameters(struct ieee80211_local *local, params->eht_capa_len, link_sta); + ieee80211_sta_init_nss(link_sta); + if (params->opmode_notif_used) { /* returned value is only needed for rc update, but the * rc isn't initialized here yet, so ignore it @@ -1920,8 +1922,6 @@ static int sta_link_apply_parameters(struct ieee80211_local *local, sband->band); } - ieee80211_sta_init_nss(link_sta); - return 0; } @@ -3674,13 +3674,12 @@ void ieee80211_csa_finish(struct ieee80211_vif *vif, unsigned int link_id) } EXPORT_SYMBOL(ieee80211_csa_finish); -void ieee80211_channel_switch_disconnect(struct ieee80211_vif *vif, bool block_tx) +void ieee80211_channel_switch_disconnect(struct ieee80211_vif *vif) { struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; struct ieee80211_local *local = sdata->local; - sdata->csa_blocked_queues = block_tx; sdata_info(sdata, "channel switch failed, disconnecting\n"); wiphy_work_queue(local->hw.wiphy, &ifmgd->csa_connection_drop_work); } @@ -4993,10 +4992,16 @@ static void ieee80211_del_intf_link(struct wiphy *wiphy, unsigned int link_id) { struct ieee80211_sub_if_data *sdata = IEEE80211_WDEV_TO_SUB_IF(wdev); + u16 new_links = wdev->valid_links & ~BIT(link_id); lockdep_assert_wiphy(sdata->local->hw.wiphy); - ieee80211_vif_set_links(sdata, wdev->valid_links, 0); + /* During the link teardown process, certain functions require the + * link_id to remain in the valid_links bitmap. Therefore, instead + * of removing the link_id from the bitmap, pass a masked value to + * simulate as if link_id does not exist anymore. + */ + ieee80211_vif_set_links(sdata, new_links, 0); } static int diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 3d3c9139ff5e..7a0242e937d3 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -1106,8 +1106,6 @@ struct ieee80211_sub_if_data { unsigned long state; - bool csa_blocked_queues; - char name[IFNAMSIZ]; struct ieee80211_fragment_cache frags; @@ -2411,17 +2409,13 @@ void ieee80211_send_4addr_nullfunc(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata); void ieee80211_sta_tx_notify(struct ieee80211_sub_if_data *sdata, struct ieee80211_hdr *hdr, bool ack, u16 tx_time); - +unsigned int +ieee80211_get_vif_queues(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata); void ieee80211_wake_queues_by_reason(struct ieee80211_hw *hw, unsigned long queues, enum queue_stop_reason reason, bool refcounted); -void ieee80211_stop_vif_queues(struct ieee80211_local *local, - struct ieee80211_sub_if_data *sdata, - enum queue_stop_reason reason); -void ieee80211_wake_vif_queues(struct ieee80211_local *local, - struct ieee80211_sub_if_data *sdata, - enum queue_stop_reason reason); void ieee80211_stop_queues_by_reason(struct ieee80211_hw *hw, unsigned long queues, enum queue_stop_reason reason, @@ -2432,6 +2426,43 @@ void ieee80211_wake_queue_by_reason(struct ieee80211_hw *hw, int queue, void ieee80211_stop_queue_by_reason(struct ieee80211_hw *hw, int queue, enum queue_stop_reason reason, bool refcounted); +static inline void +ieee80211_stop_vif_queues(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata, + enum queue_stop_reason reason) +{ + ieee80211_stop_queues_by_reason(&local->hw, + ieee80211_get_vif_queues(local, sdata), + reason, true); +} + +static inline void +ieee80211_wake_vif_queues(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata, + enum queue_stop_reason reason) +{ + ieee80211_wake_queues_by_reason(&local->hw, + ieee80211_get_vif_queues(local, sdata), + reason, true); +} +static inline void +ieee80211_stop_vif_queues_norefcount(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata, + enum queue_stop_reason reason) +{ + ieee80211_stop_queues_by_reason(&local->hw, + ieee80211_get_vif_queues(local, sdata), + reason, false); +} +static inline void +ieee80211_wake_vif_queues_norefcount(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata, + enum queue_stop_reason reason) +{ + ieee80211_wake_queues_by_reason(&local->hw, + ieee80211_get_vif_queues(local, sdata), + reason, false); +} void ieee80211_add_pending_skb(struct ieee80211_local *local, struct sk_buff *skb); void ieee80211_add_pending_skbs(struct ieee80211_local *local, diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index 6ef0990d3d29..af9055252e6d 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -2364,18 +2364,14 @@ void ieee80211_vif_block_queues_csa(struct ieee80211_sub_if_data *sdata) if (ieee80211_hw_check(&local->hw, HANDLES_QUIET_CSA)) return; - ieee80211_stop_vif_queues(local, sdata, - IEEE80211_QUEUE_STOP_REASON_CSA); - sdata->csa_blocked_queues = true; + ieee80211_stop_vif_queues_norefcount(local, sdata, + IEEE80211_QUEUE_STOP_REASON_CSA); } void ieee80211_vif_unblock_queues_csa(struct ieee80211_sub_if_data *sdata) { struct ieee80211_local *local = sdata->local; - if (sdata->csa_blocked_queues) { - ieee80211_wake_vif_queues(local, sdata, - IEEE80211_QUEUE_STOP_REASON_CSA); - sdata->csa_blocked_queues = false; - } + ieee80211_wake_vif_queues_norefcount(local, sdata, + IEEE80211_QUEUE_STOP_REASON_CSA); } diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c index 640239f4425b..50eb1d8cd43d 100644 --- a/net/mac80211/mesh.c +++ b/net/mac80211/mesh.c @@ -1157,14 +1157,14 @@ void ieee80211_mbss_info_change_notify(struct ieee80211_sub_if_data *sdata, u64 changed) { struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh; - unsigned long bits = changed; + unsigned long bits[] = { BITMAP_FROM_U64(changed) }; u32 bit; - if (!bits) + if (!changed) return; /* if we race with running work, worst case this work becomes a noop */ - for_each_set_bit(bit, &bits, sizeof(changed) * BITS_PER_BYTE) + for_each_set_bit(bit, bits, sizeof(changed) * BITS_PER_BYTE) set_bit(bit, ifmsh->mbss_changed); set_bit(MESH_WORK_MBSS_CHANGED, &ifmsh->wrkq_flags); wiphy_work_queue(sdata->local->hw.wiphy, &sdata->work); diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 0303972c23e4..111066928b96 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -2636,8 +2636,6 @@ ieee80211_sta_process_chanswitch(struct ieee80211_link_data *link, */ link->conf->csa_active = true; link->u.mgd.csa.blocked_tx = csa_ie.mode; - sdata->csa_blocked_queues = - csa_ie.mode && !ieee80211_hw_check(&local->hw, HANDLES_QUIET_CSA); wiphy_work_queue(sdata->local->hw.wiphy, &ifmgd->csa_connection_drop_work); diff --git a/net/mac80211/util.c b/net/mac80211/util.c index f94faa86ba8a..38c30e4ddda9 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -657,7 +657,7 @@ void ieee80211_wake_queues(struct ieee80211_hw *hw) } EXPORT_SYMBOL(ieee80211_wake_queues); -static unsigned int +unsigned int ieee80211_get_vif_queues(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata) { @@ -669,7 +669,8 @@ ieee80211_get_vif_queues(struct ieee80211_local *local, queues = 0; for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) - queues |= BIT(sdata->vif.hw_queue[ac]); + if (sdata->vif.hw_queue[ac] != IEEE80211_INVAL_HW_QUEUE) + queues |= BIT(sdata->vif.hw_queue[ac]); if (sdata->vif.cab_queue != IEEE80211_INVAL_HW_QUEUE) queues |= BIT(sdata->vif.cab_queue); } else { @@ -724,24 +725,6 @@ void ieee80211_flush_queues(struct ieee80211_local *local, __ieee80211_flush_queues(local, sdata, 0, drop); } -void ieee80211_stop_vif_queues(struct ieee80211_local *local, - struct ieee80211_sub_if_data *sdata, - enum queue_stop_reason reason) -{ - ieee80211_stop_queues_by_reason(&local->hw, - ieee80211_get_vif_queues(local, sdata), - reason, true); -} - -void ieee80211_wake_vif_queues(struct ieee80211_local *local, - struct ieee80211_sub_if_data *sdata, - enum queue_stop_reason reason) -{ - ieee80211_wake_queues_by_reason(&local->hw, - ieee80211_get_vif_queues(local, sdata), - reason, true); -} - static void __iterate_interfaces(struct ieee80211_local *local, u32 iter_flags, void (*iterator)(void *data, u8 *mac, @@ -1842,6 +1825,9 @@ int ieee80211_reconfig(struct ieee80211_local *local) WARN(1, "Hardware became unavailable upon resume. This could be a software issue prior to suspend or a hardware issue.\n"); else WARN(1, "Hardware became unavailable during restart.\n"); + ieee80211_wake_queues_by_reason(hw, IEEE80211_MAX_QUEUE_MAP, + IEEE80211_QUEUE_STOP_REASON_SUSPEND, + false); ieee80211_handle_reconfig_failure(local); return res; } diff --git a/net/mctp/route.c b/net/mctp/route.c index 597e9cf5aa64..3f2bd65ff5e3 100644 --- a/net/mctp/route.c +++ b/net/mctp/route.c @@ -374,8 +374,13 @@ static int mctp_route_input(struct mctp_route *route, struct sk_buff *skb) msk = NULL; rc = -EINVAL; - /* we may be receiving a locally-routed packet; drop source sk - * accounting + /* We may be receiving a locally-routed packet; drop source sk + * accounting. + * + * From here, we will either queue the skb - either to a frag_queue, or + * to a receiving socket. When that succeeds, we clear the skb pointer; + * a non-NULL skb on exit will be otherwise unowned, and hence + * kfree_skb()-ed. */ skb_orphan(skb); @@ -434,7 +439,9 @@ static int mctp_route_input(struct mctp_route *route, struct sk_buff *skb) * pending key. */ if (flags & MCTP_HDR_FLAG_EOM) { - sock_queue_rcv_skb(&msk->sk, skb); + rc = sock_queue_rcv_skb(&msk->sk, skb); + if (!rc) + skb = NULL; if (key) { /* we've hit a pending reassembly; not much we * can do but drop it @@ -443,7 +450,6 @@ static int mctp_route_input(struct mctp_route *route, struct sk_buff *skb) MCTP_TRACE_KEY_REPLIED); key = NULL; } - rc = 0; goto out_unlock; } @@ -470,8 +476,10 @@ static int mctp_route_input(struct mctp_route *route, struct sk_buff *skb) * this function. */ rc = mctp_key_add(key, msk); - if (!rc) + if (!rc) { trace_mctp_key_acquire(key); + skb = NULL; + } /* we don't need to release key->lock on exit, so * clean up here and suppress the unlock via @@ -489,6 +497,8 @@ static int mctp_route_input(struct mctp_route *route, struct sk_buff *skb) key = NULL; } else { rc = mctp_frag_queue(key, skb); + if (!rc) + skb = NULL; } } @@ -503,12 +513,19 @@ static int mctp_route_input(struct mctp_route *route, struct sk_buff *skb) else rc = mctp_frag_queue(key, skb); + if (rc) + goto out_unlock; + + /* we've queued; the queue owns the skb now */ + skb = NULL; + /* end of message? deliver to socket, and we're done with * the reassembly/response key */ - if (!rc && flags & MCTP_HDR_FLAG_EOM) { - sock_queue_rcv_skb(key->sk, key->reasm_head); - key->reasm_head = NULL; + if (flags & MCTP_HDR_FLAG_EOM) { + rc = sock_queue_rcv_skb(key->sk, key->reasm_head); + if (!rc) + key->reasm_head = NULL; __mctp_key_done_in(key, net, f, MCTP_TRACE_KEY_REPLIED); key = NULL; } @@ -527,8 +544,7 @@ out_unlock: if (any_key) mctp_key_unref(any_key); out: - if (rc) - kfree_skb(skb); + kfree_skb(skb); return rc; } diff --git a/net/mctp/test/route-test.c b/net/mctp/test/route-test.c index 8551dab1d1e6..17165b86ce22 100644 --- a/net/mctp/test/route-test.c +++ b/net/mctp/test/route-test.c @@ -837,6 +837,90 @@ static void mctp_test_route_input_multiple_nets_key(struct kunit *test) mctp_test_route_input_multiple_nets_key_fini(test, &t2); } +/* Input route to socket, using a single-packet message, where sock delivery + * fails. Ensure we're handling the failure appropriately. + */ +static void mctp_test_route_input_sk_fail_single(struct kunit *test) +{ + const struct mctp_hdr hdr = RX_HDR(1, 10, 8, FL_S | FL_E | FL_TO); + struct mctp_test_route *rt; + struct mctp_test_dev *dev; + struct socket *sock; + struct sk_buff *skb; + int rc; + + __mctp_route_test_init(test, &dev, &rt, &sock, MCTP_NET_ANY); + + /* No rcvbuf space, so delivery should fail. __sock_set_rcvbuf will + * clamp the minimum to SOCK_MIN_RCVBUF, so we open-code this. + */ + lock_sock(sock->sk); + WRITE_ONCE(sock->sk->sk_rcvbuf, 0); + release_sock(sock->sk); + + skb = mctp_test_create_skb(&hdr, 10); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, skb); + skb_get(skb); + + mctp_test_skb_set_dev(skb, dev); + + /* do route input, which should fail */ + rc = mctp_route_input(&rt->rt, skb); + KUNIT_EXPECT_NE(test, rc, 0); + + /* we should hold the only reference to skb */ + KUNIT_EXPECT_EQ(test, refcount_read(&skb->users), 1); + kfree_skb(skb); + + __mctp_route_test_fini(test, dev, rt, sock); +} + +/* Input route to socket, using a fragmented message, where sock delivery fails. + */ +static void mctp_test_route_input_sk_fail_frag(struct kunit *test) +{ + const struct mctp_hdr hdrs[2] = { RX_FRAG(FL_S, 0), RX_FRAG(FL_E, 1) }; + struct mctp_test_route *rt; + struct mctp_test_dev *dev; + struct sk_buff *skbs[2]; + struct socket *sock; + unsigned int i; + int rc; + + __mctp_route_test_init(test, &dev, &rt, &sock, MCTP_NET_ANY); + + lock_sock(sock->sk); + WRITE_ONCE(sock->sk->sk_rcvbuf, 0); + release_sock(sock->sk); + + for (i = 0; i < ARRAY_SIZE(skbs); i++) { + skbs[i] = mctp_test_create_skb(&hdrs[i], 10); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, skbs[i]); + skb_get(skbs[i]); + + mctp_test_skb_set_dev(skbs[i], dev); + } + + /* first route input should succeed, we're only queueing to the + * frag list + */ + rc = mctp_route_input(&rt->rt, skbs[0]); + KUNIT_EXPECT_EQ(test, rc, 0); + + /* final route input should fail to deliver to the socket */ + rc = mctp_route_input(&rt->rt, skbs[1]); + KUNIT_EXPECT_NE(test, rc, 0); + + /* we should hold the only reference to both skbs */ + KUNIT_EXPECT_EQ(test, refcount_read(&skbs[0]->users), 1); + kfree_skb(skbs[0]); + + KUNIT_EXPECT_EQ(test, refcount_read(&skbs[1]->users), 1); + kfree_skb(skbs[1]); + + __mctp_route_test_fini(test, dev, rt, sock); +} + #if IS_ENABLED(CONFIG_MCTP_FLOWS) static void mctp_test_flow_init(struct kunit *test, @@ -1053,6 +1137,8 @@ static struct kunit_case mctp_test_cases[] = { mctp_route_input_sk_reasm_gen_params), KUNIT_CASE_PARAM(mctp_test_route_input_sk_keys, mctp_route_input_sk_keys_gen_params), + KUNIT_CASE(mctp_test_route_input_sk_fail_single), + KUNIT_CASE(mctp_test_route_input_sk_fail_frag), KUNIT_CASE(mctp_test_route_input_multiple_nets_bind), KUNIT_CASE(mctp_test_route_input_multiple_nets_key), KUNIT_CASE(mctp_test_packet_flow), diff --git a/net/mptcp/options.c b/net/mptcp/options.c index 1603b3702e22..a62bc874bf1e 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -667,8 +667,15 @@ static bool mptcp_established_options_add_addr(struct sock *sk, struct sk_buff * &echo, &drop_other_suboptions)) return false; + /* + * Later on, mptcp_write_options() will enforce mutually exclusion with + * DSS, bail out if such option is set and we can't drop it. + */ if (drop_other_suboptions) remaining += opt_size; + else if (opts->suboptions & OPTION_MPTCP_DSS) + return false; + len = mptcp_add_addr_len(opts->addr.family, echo, !!opts->addr.port); if (remaining < len) return false; diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 8a8e8fee337f..4b9d850ce85a 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -528,13 +528,13 @@ static void mptcp_send_ack(struct mptcp_sock *msk) mptcp_subflow_send_ack(mptcp_subflow_tcp_sock(subflow)); } -static void mptcp_subflow_cleanup_rbuf(struct sock *ssk) +static void mptcp_subflow_cleanup_rbuf(struct sock *ssk, int copied) { bool slow; slow = lock_sock_fast(ssk); if (tcp_can_send_ack(ssk)) - tcp_cleanup_rbuf(ssk, 1); + tcp_cleanup_rbuf(ssk, copied); unlock_sock_fast(ssk, slow); } @@ -551,7 +551,7 @@ static bool mptcp_subflow_could_cleanup(const struct sock *ssk, bool rx_empty) (ICSK_ACK_PUSHED2 | ICSK_ACK_PUSHED))); } -static void mptcp_cleanup_rbuf(struct mptcp_sock *msk) +static void mptcp_cleanup_rbuf(struct mptcp_sock *msk, int copied) { int old_space = READ_ONCE(msk->old_wspace); struct mptcp_subflow_context *subflow; @@ -559,14 +559,14 @@ static void mptcp_cleanup_rbuf(struct mptcp_sock *msk) int space = __mptcp_space(sk); bool cleanup, rx_empty; - cleanup = (space > 0) && (space >= (old_space << 1)); - rx_empty = !__mptcp_rmem(sk); + cleanup = (space > 0) && (space >= (old_space << 1)) && copied; + rx_empty = !__mptcp_rmem(sk) && copied; mptcp_for_each_subflow(msk, subflow) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); if (cleanup || mptcp_subflow_could_cleanup(ssk, rx_empty)) - mptcp_subflow_cleanup_rbuf(ssk); + mptcp_subflow_cleanup_rbuf(ssk, copied); } } @@ -1939,6 +1939,8 @@ do_error: goto out; } +static void mptcp_rcv_space_adjust(struct mptcp_sock *msk, int copied); + static int __mptcp_recvmsg_mskq(struct mptcp_sock *msk, struct msghdr *msg, size_t len, int flags, @@ -1992,6 +1994,7 @@ static int __mptcp_recvmsg_mskq(struct mptcp_sock *msk, break; } + mptcp_rcv_space_adjust(msk, copied); return copied; } @@ -2217,9 +2220,6 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, copied += bytes_read; - /* be sure to advertise window change */ - mptcp_cleanup_rbuf(msk); - if (skb_queue_empty(&msk->receive_queue) && __mptcp_move_skbs(msk)) continue; @@ -2268,7 +2268,7 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, } pr_debug("block timeout %ld\n", timeo); - mptcp_rcv_space_adjust(msk, copied); + mptcp_cleanup_rbuf(msk, copied); err = sk_wait_data(sk, &timeo, NULL); if (err < 0) { err = copied ? : err; @@ -2276,7 +2276,7 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, } } - mptcp_rcv_space_adjust(msk, copied); + mptcp_cleanup_rbuf(msk, copied); out_err: if (cmsg_flags && copied >= 0) { diff --git a/net/netfilter/ipset/ip_set_list_set.c b/net/netfilter/ipset/ip_set_list_set.c index bfae7066936b..db794fe1300e 100644 --- a/net/netfilter/ipset/ip_set_list_set.c +++ b/net/netfilter/ipset/ip_set_list_set.c @@ -611,6 +611,8 @@ init_list_set(struct net *net, struct ip_set *set, u32 size) return true; } +static struct lock_class_key list_set_lockdep_key; + static int list_set_create(struct net *net, struct ip_set *set, struct nlattr *tb[], u32 flags) @@ -627,6 +629,7 @@ list_set_create(struct net *net, struct ip_set *set, struct nlattr *tb[], if (size < IP_SET_LIST_MIN_SIZE) size = IP_SET_LIST_MIN_SIZE; + lockdep_set_class(&set->lock, &list_set_lockdep_key); set->variant = &set_variant; set->dsize = ip_set_elem_len(set, tb, sizeof(struct set_elem), __alignof__(struct set_elem)); diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index 98d7dbe3d787..c0289f83f96d 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -1495,8 +1495,8 @@ int __init ip_vs_conn_init(void) max_avail -= 2; /* ~4 in hash row */ max_avail -= 1; /* IPVS up to 1/2 of mem */ max_avail -= order_base_2(sizeof(struct ip_vs_conn)); - max = clamp(max, min, max_avail); - ip_vs_conn_tab_bits = clamp_val(ip_vs_conn_tab_bits, min, max); + max = clamp(max_avail, min, max); + ip_vs_conn_tab_bits = clamp(ip_vs_conn_tab_bits, min, max); ip_vs_conn_tab_size = 1 << ip_vs_conn_tab_bits; ip_vs_conn_tab_mask = ip_vs_conn_tab_size - 1; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 4a137afaf0b8..0c5ff4afc370 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -1495,7 +1495,6 @@ static int nf_tables_newtable(struct sk_buff *skb, const struct nfnl_info *info, INIT_LIST_HEAD(&table->sets); INIT_LIST_HEAD(&table->objects); INIT_LIST_HEAD(&table->flowtables); - write_pnet(&table->net, net); table->family = family; table->flags = flags; table->handle = ++nft_net->table_handle; @@ -3884,8 +3883,11 @@ void nf_tables_rule_destroy(const struct nft_ctx *ctx, struct nft_rule *rule) kfree(rule); } +/* can only be used if rule is no longer visible to dumps */ static void nf_tables_rule_release(const struct nft_ctx *ctx, struct nft_rule *rule) { + lockdep_commit_lock_is_held(ctx->net); + nft_rule_expr_deactivate(ctx, rule, NFT_TRANS_RELEASE); nf_tables_rule_destroy(ctx, rule); } @@ -5650,6 +5652,8 @@ void nf_tables_deactivate_set(const struct nft_ctx *ctx, struct nft_set *set, struct nft_set_binding *binding, enum nft_trans_phase phase) { + lockdep_commit_lock_is_held(ctx->net); + switch (phase) { case NFT_TRANS_PREPARE_ERROR: nft_set_trans_unbind(ctx, set); @@ -11456,19 +11460,6 @@ static void __nft_release_basechain_now(struct nft_ctx *ctx) nf_tables_chain_destroy(ctx->chain); } -static void nft_release_basechain_rcu(struct rcu_head *head) -{ - struct nft_chain *chain = container_of(head, struct nft_chain, rcu_head); - struct nft_ctx ctx = { - .family = chain->table->family, - .chain = chain, - .net = read_pnet(&chain->table->net), - }; - - __nft_release_basechain_now(&ctx); - put_net(ctx.net); -} - int __nft_release_basechain(struct nft_ctx *ctx) { struct nft_rule *rule; @@ -11483,11 +11474,18 @@ int __nft_release_basechain(struct nft_ctx *ctx) nft_chain_del(ctx->chain); nft_use_dec(&ctx->table->use); - if (maybe_get_net(ctx->net)) - call_rcu(&ctx->chain->rcu_head, nft_release_basechain_rcu); - else + if (!maybe_get_net(ctx->net)) { __nft_release_basechain_now(ctx); + return 0; + } + + /* wait for ruleset dumps to complete. Owning chain is no longer in + * lists, so new dumps can't find any of these rules anymore. + */ + synchronize_rcu(); + __nft_release_basechain_now(ctx); + put_net(ctx->net); return 0; } EXPORT_SYMBOL_GPL(__nft_release_basechain); diff --git a/net/netfilter/xt_IDLETIMER.c b/net/netfilter/xt_IDLETIMER.c index f8b25b6f5da7..9869ef3c2ab3 100644 --- a/net/netfilter/xt_IDLETIMER.c +++ b/net/netfilter/xt_IDLETIMER.c @@ -409,21 +409,23 @@ static void idletimer_tg_destroy(const struct xt_tgdtor_param *par) mutex_lock(&list_mutex); - if (--info->timer->refcnt == 0) { - pr_debug("deleting timer %s\n", info->label); - - list_del(&info->timer->entry); - timer_shutdown_sync(&info->timer->timer); - cancel_work_sync(&info->timer->work); - sysfs_remove_file(idletimer_tg_kobj, &info->timer->attr.attr); - kfree(info->timer->attr.attr.name); - kfree(info->timer); - } else { + if (--info->timer->refcnt > 0) { pr_debug("decreased refcnt of timer %s to %u\n", info->label, info->timer->refcnt); + mutex_unlock(&list_mutex); + return; } + pr_debug("deleting timer %s\n", info->label); + + list_del(&info->timer->entry); mutex_unlock(&list_mutex); + + timer_shutdown_sync(&info->timer->timer); + cancel_work_sync(&info->timer->work); + sysfs_remove_file(idletimer_tg_kobj, &info->timer->attr.attr); + kfree(info->timer->attr.attr.name); + kfree(info->timer); } static void idletimer_tg_destroy_v1(const struct xt_tgdtor_param *par) @@ -434,25 +436,27 @@ static void idletimer_tg_destroy_v1(const struct xt_tgdtor_param *par) mutex_lock(&list_mutex); - if (--info->timer->refcnt == 0) { - pr_debug("deleting timer %s\n", info->label); - - list_del(&info->timer->entry); - if (info->timer->timer_type & XT_IDLETIMER_ALARM) { - alarm_cancel(&info->timer->alarm); - } else { - timer_shutdown_sync(&info->timer->timer); - } - cancel_work_sync(&info->timer->work); - sysfs_remove_file(idletimer_tg_kobj, &info->timer->attr.attr); - kfree(info->timer->attr.attr.name); - kfree(info->timer); - } else { + if (--info->timer->refcnt > 0) { pr_debug("decreased refcnt of timer %s to %u\n", info->label, info->timer->refcnt); + mutex_unlock(&list_mutex); + return; } + pr_debug("deleting timer %s\n", info->label); + + list_del(&info->timer->entry); mutex_unlock(&list_mutex); + + if (info->timer->timer_type & XT_IDLETIMER_ALARM) { + alarm_cancel(&info->timer->alarm); + } else { + timer_shutdown_sync(&info->timer->timer); + } + cancel_work_sync(&info->timer->work); + sysfs_remove_file(idletimer_tg_kobj, &info->timer->attr.attr); + kfree(info->timer->attr.attr.name); + kfree(info->timer); } diff --git a/net/netrom/nr_route.c b/net/netrom/nr_route.c index 2b5e246b8d9a..b94cb2ffbaf8 100644 --- a/net/netrom/nr_route.c +++ b/net/netrom/nr_route.c @@ -754,6 +754,12 @@ int nr_route_frame(struct sk_buff *skb, ax25_cb *ax25) int ret; struct sk_buff *skbn; + /* + * Reject malformed packets early. Check that it contains at least 2 + * addresses and 1 byte more for Time-To-Live + */ + if (skb->len < 2 * sizeof(ax25_address) + 1) + return 0; nr_src = (ax25_address *)(skb->data + 0); nr_dest = (ax25_address *)(skb->data + 7); diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 97774bd4b6cb..f3cecb3e4bcb 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -538,10 +538,8 @@ static void *packet_current_frame(struct packet_sock *po, return packet_lookup_frame(po, rb, rb->head, status); } -static u16 vlan_get_tci(struct sk_buff *skb, struct net_device *dev) +static u16 vlan_get_tci(const struct sk_buff *skb, struct net_device *dev) { - u8 *skb_orig_data = skb->data; - int skb_orig_len = skb->len; struct vlan_hdr vhdr, *vh; unsigned int header_len; @@ -562,33 +560,21 @@ static u16 vlan_get_tci(struct sk_buff *skb, struct net_device *dev) else return 0; - skb_push(skb, skb->data - skb_mac_header(skb)); - vh = skb_header_pointer(skb, header_len, sizeof(vhdr), &vhdr); - if (skb_orig_data != skb->data) { - skb->data = skb_orig_data; - skb->len = skb_orig_len; - } + vh = skb_header_pointer(skb, skb_mac_offset(skb) + header_len, + sizeof(vhdr), &vhdr); if (unlikely(!vh)) return 0; return ntohs(vh->h_vlan_TCI); } -static __be16 vlan_get_protocol_dgram(struct sk_buff *skb) +static __be16 vlan_get_protocol_dgram(const struct sk_buff *skb) { __be16 proto = skb->protocol; - if (unlikely(eth_type_vlan(proto))) { - u8 *skb_orig_data = skb->data; - int skb_orig_len = skb->len; - - skb_push(skb, skb->data - skb_mac_header(skb)); - proto = __vlan_get_protocol(skb, proto, NULL); - if (skb_orig_data != skb->data) { - skb->data = skb_orig_data; - skb->len = skb_orig_len; - } - } + if (unlikely(eth_type_vlan(proto))) + proto = __vlan_get_protocol_offset(skb, proto, + skb_mac_offset(skb), NULL); return proto; } diff --git a/net/psample/psample.c b/net/psample/psample.c index a0ddae8a65f9..25f92ba0840c 100644 --- a/net/psample/psample.c +++ b/net/psample/psample.c @@ -393,7 +393,9 @@ void psample_sample_packet(struct psample_group *group, nla_total_size_64bit(sizeof(u64)) + /* timestamp */ nla_total_size(sizeof(u16)) + /* protocol */ (md->user_cookie_len ? - nla_total_size(md->user_cookie_len) : 0); /* user cookie */ + nla_total_size(md->user_cookie_len) : 0) + /* user cookie */ + (md->rate_as_probability ? + nla_total_size(0) : 0); /* rate as probability */ #ifdef CONFIG_INET tun_info = skb_tunnel_info(skb); @@ -498,8 +500,9 @@ void psample_sample_packet(struct psample_group *group, md->user_cookie)) goto error; - if (md->rate_as_probability) - nla_put_flag(nl_skb, PSAMPLE_ATTR_SAMPLE_PROBABILITY); + if (md->rate_as_probability && + nla_put_flag(nl_skb, PSAMPLE_ATTR_SAMPLE_PROBABILITY)) + goto error; genlmsg_end(nl_skb, data); genlmsg_multicast_netns(&psample_nl_family, group->net, nl_skb, 0, diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c index f2f9b75008bb..8d8b2db4653c 100644 --- a/net/sched/sch_cake.c +++ b/net/sched/sch_cake.c @@ -1525,7 +1525,6 @@ static unsigned int cake_drop(struct Qdisc *sch, struct sk_buff **to_free) b->backlogs[idx] -= len; b->tin_backlog -= len; sch->qstats.backlog -= len; - qdisc_tree_reduce_backlog(sch, 1, len); flow->dropped++; b->tin_dropped++; @@ -1536,6 +1535,7 @@ static unsigned int cake_drop(struct Qdisc *sch, struct sk_buff **to_free) __qdisc_drop(skb, to_free); sch->q.qlen--; + qdisc_tree_reduce_backlog(sch, 1, len); cake_heapify(q, 0); diff --git a/net/sched/sch_choke.c b/net/sched/sch_choke.c index 91072010923d..757b89292e7e 100644 --- a/net/sched/sch_choke.c +++ b/net/sched/sch_choke.c @@ -123,10 +123,10 @@ static void choke_drop_by_idx(struct Qdisc *sch, unsigned int idx, if (idx == q->tail) choke_zap_tail_holes(q); + --sch->q.qlen; qdisc_qstats_backlog_dec(sch, skb); qdisc_tree_reduce_backlog(sch, 1, qdisc_pkt_len(skb)); qdisc_drop(skb, sch, to_free); - --sch->q.qlen; } struct choke_skb_cb { diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index 39382ee1e331..3b519adc0125 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -78,6 +78,8 @@ struct netem_sched_data { struct sk_buff *t_head; struct sk_buff *t_tail; + u32 t_len; + /* optional qdisc for classful handling (NULL at netem init) */ struct Qdisc *qdisc; @@ -382,6 +384,7 @@ static void tfifo_reset(struct Qdisc *sch) rtnl_kfree_skbs(q->t_head, q->t_tail); q->t_head = NULL; q->t_tail = NULL; + q->t_len = 0; } static void tfifo_enqueue(struct sk_buff *nskb, struct Qdisc *sch) @@ -411,6 +414,7 @@ static void tfifo_enqueue(struct sk_buff *nskb, struct Qdisc *sch) rb_link_node(&nskb->rbnode, parent, p); rb_insert_color(&nskb->rbnode, &q->t_root); } + q->t_len++; sch->q.qlen++; } @@ -517,7 +521,7 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, 1<<get_random_u32_below(8); } - if (unlikely(sch->q.qlen >= sch->limit)) { + if (unlikely(q->t_len >= sch->limit)) { /* re-link segs, so that qdisc_drop_all() frees them all */ skb->next = segs; qdisc_drop_all(skb, sch, to_free); @@ -701,8 +705,8 @@ static struct sk_buff *netem_dequeue(struct Qdisc *sch) tfifo_dequeue: skb = __qdisc_dequeue_head(&sch->q); if (skb) { - qdisc_qstats_backlog_dec(sch, skb); deliver: + qdisc_qstats_backlog_dec(sch, skb); qdisc_bstats_update(sch, skb); return skb; } @@ -718,8 +722,7 @@ deliver: if (time_to_send <= now && q->slot.slot_next <= now) { netem_erase_head(q, skb); - sch->q.qlen--; - qdisc_qstats_backlog_dec(sch, skb); + q->t_len--; skb->next = NULL; skb->prev = NULL; /* skb->dev shares skb->rbnode area, @@ -746,16 +749,21 @@ deliver: if (net_xmit_drop_count(err)) qdisc_qstats_drop(sch); qdisc_tree_reduce_backlog(sch, 1, pkt_len); + sch->qstats.backlog -= pkt_len; + sch->q.qlen--; } goto tfifo_dequeue; } + sch->q.qlen--; goto deliver; } if (q->qdisc) { skb = q->qdisc->ops->dequeue(q->qdisc); - if (skb) + if (skb) { + sch->q.qlen--; goto deliver; + } } qdisc_watchdog_schedule_ns(&q->watchdog, @@ -765,8 +773,10 @@ deliver: if (q->qdisc) { skb = q->qdisc->ops->dequeue(q->qdisc); - if (skb) + if (skb) { + sch->q.qlen--; goto deliver; + } } return NULL; } diff --git a/net/sctp/associola.c b/net/sctp/associola.c index c45c192b7878..0b0794f164cf 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -137,7 +137,8 @@ static struct sctp_association *sctp_association_init( = 5 * asoc->rto_max; asoc->timeouts[SCTP_EVENT_TIMEOUT_SACK] = asoc->sackdelay; - asoc->timeouts[SCTP_EVENT_TIMEOUT_AUTOCLOSE] = sp->autoclose * HZ; + asoc->timeouts[SCTP_EVENT_TIMEOUT_AUTOCLOSE] = + (unsigned long)sp->autoclose * HZ; /* Initializes the timers */ for (i = SCTP_EVENT_TIMEOUT_NONE; i < SCTP_NUM_TIMEOUT_TYPES; ++i) diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 9e6c69d18581..6cc7b846cff1 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -2032,6 +2032,8 @@ static int smc_listen_prfx_check(struct smc_sock *new_smc, if (pclc->hdr.typev1 == SMC_TYPE_N) return 0; pclc_prfx = smc_clc_proposal_get_prefix(pclc); + if (!pclc_prfx) + return -EPROTO; if (smc_clc_prfx_match(newclcsock, pclc_prfx)) return SMC_CLC_DECL_DIFFPREFIX; @@ -2145,6 +2147,8 @@ static void smc_find_ism_v2_device_serv(struct smc_sock *new_smc, pclc_smcd = smc_get_clc_msg_smcd(pclc); smc_v2_ext = smc_get_clc_v2_ext(pclc); smcd_v2_ext = smc_get_clc_smcd_v2_ext(smc_v2_ext); + if (!pclc_smcd || !smc_v2_ext || !smcd_v2_ext) + goto not_found; mutex_lock(&smcd_dev_list.mutex); if (pclc_smcd->ism.chid) { @@ -2221,7 +2225,9 @@ static void smc_find_ism_v1_device_serv(struct smc_sock *new_smc, int rc = 0; /* check if ISM V1 is available */ - if (!(ini->smcd_version & SMC_V1) || !smcd_indicated(ini->smc_type_v1)) + if (!(ini->smcd_version & SMC_V1) || + !smcd_indicated(ini->smc_type_v1) || + !pclc_smcd) goto not_found; ini->is_smcd = true; /* prepare ISM check */ ini->ism_peer_gid[0].gid = ntohll(pclc_smcd->ism.gid); @@ -2272,7 +2278,8 @@ static void smc_find_rdma_v2_device_serv(struct smc_sock *new_smc, goto not_found; smc_v2_ext = smc_get_clc_v2_ext(pclc); - if (!smc_clc_match_eid(ini->negotiated_eid, smc_v2_ext, NULL, NULL)) + if (!smc_v2_ext || + !smc_clc_match_eid(ini->negotiated_eid, smc_v2_ext, NULL, NULL)) goto not_found; /* prepare RDMA check */ @@ -2881,6 +2888,13 @@ __poll_t smc_poll(struct file *file, struct socket *sock, } else { sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk); set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); + + if (sk->sk_state != SMC_INIT) { + /* Race breaker the same way as tcp_poll(). */ + smp_mb__after_atomic(); + if (atomic_read(&smc->conn.sndbuf_space)) + mask |= EPOLLOUT | EPOLLWRNORM; + } } if (atomic_read(&smc->conn.bytes_to_rcv)) mask |= EPOLLIN | EPOLLRDNORM; diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c index 33fa787c28eb..521f5df80e10 100644 --- a/net/smc/smc_clc.c +++ b/net/smc/smc_clc.c @@ -352,8 +352,11 @@ static bool smc_clc_msg_prop_valid(struct smc_clc_msg_proposal *pclc) struct smc_clc_msg_hdr *hdr = &pclc->hdr; struct smc_clc_v2_extension *v2_ext; - v2_ext = smc_get_clc_v2_ext(pclc); pclc_prfx = smc_clc_proposal_get_prefix(pclc); + if (!pclc_prfx || + pclc_prfx->ipv6_prefixes_cnt > SMC_CLC_MAX_V6_PREFIX) + return false; + if (hdr->version == SMC_V1) { if (hdr->typev1 == SMC_TYPE_N) return false; @@ -365,6 +368,13 @@ static bool smc_clc_msg_prop_valid(struct smc_clc_msg_proposal *pclc) sizeof(struct smc_clc_msg_trail)) return false; } else { + v2_ext = smc_get_clc_v2_ext(pclc); + if ((hdr->typev2 != SMC_TYPE_N && + (!v2_ext || v2_ext->hdr.eid_cnt > SMC_CLC_MAX_UEID)) || + (smcd_indicated(hdr->typev2) && + v2_ext->hdr.ism_gid_cnt > SMCD_CLC_MAX_V2_GID_ENTRIES)) + return false; + if (ntohs(hdr->length) != sizeof(*pclc) + sizeof(struct smc_clc_msg_smcd) + @@ -764,6 +774,11 @@ int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen, SMC_CLC_RECV_BUF_LEN : datlen; iov_iter_kvec(&msg.msg_iter, ITER_DEST, &vec, 1, recvlen); len = sock_recvmsg(smc->clcsock, &msg, krflags); + if (len < recvlen) { + smc->sk.sk_err = EPROTO; + reason_code = -EPROTO; + goto out; + } datlen -= len; } if (clcm->type == SMC_CLC_DECLINE) { diff --git a/net/smc/smc_clc.h b/net/smc/smc_clc.h index 5625fda2960b..1a7676227f16 100644 --- a/net/smc/smc_clc.h +++ b/net/smc/smc_clc.h @@ -336,8 +336,12 @@ struct smc_clc_msg_decline_v2 { /* clc decline message */ static inline struct smc_clc_msg_proposal_prefix * smc_clc_proposal_get_prefix(struct smc_clc_msg_proposal *pclc) { + u16 offset = ntohs(pclc->iparea_offset); + + if (offset > sizeof(struct smc_clc_msg_smcd)) + return NULL; return (struct smc_clc_msg_proposal_prefix *) - ((u8 *)pclc + sizeof(*pclc) + ntohs(pclc->iparea_offset)); + ((u8 *)pclc + sizeof(*pclc) + offset); } static inline bool smcr_indicated(int smc_type) @@ -376,8 +380,14 @@ static inline struct smc_clc_v2_extension * smc_get_clc_v2_ext(struct smc_clc_msg_proposal *prop) { struct smc_clc_msg_smcd *prop_smcd = smc_get_clc_msg_smcd(prop); + u16 max_offset; - if (!prop_smcd || !ntohs(prop_smcd->v2_ext_offset)) + max_offset = offsetof(struct smc_clc_msg_proposal_area, pclc_v2_ext) - + offsetof(struct smc_clc_msg_proposal_area, pclc_smcd) - + offsetofend(struct smc_clc_msg_smcd, v2_ext_offset); + + if (!prop_smcd || !ntohs(prop_smcd->v2_ext_offset) || + ntohs(prop_smcd->v2_ext_offset) > max_offset) return NULL; return (struct smc_clc_v2_extension *) @@ -390,9 +400,15 @@ smc_get_clc_v2_ext(struct smc_clc_msg_proposal *prop) static inline struct smc_clc_smcd_v2_extension * smc_get_clc_smcd_v2_ext(struct smc_clc_v2_extension *prop_v2ext) { + u16 max_offset = offsetof(struct smc_clc_msg_proposal_area, pclc_smcd_v2_ext) - + offsetof(struct smc_clc_msg_proposal_area, pclc_v2_ext) - + offsetof(struct smc_clc_v2_extension, hdr) - + offsetofend(struct smc_clnt_opts_area_hdr, smcd_v2_ext_offset); + if (!prop_v2ext) return NULL; - if (!ntohs(prop_v2ext->hdr.smcd_v2_ext_offset)) + if (!ntohs(prop_v2ext->hdr.smcd_v2_ext_offset) || + ntohs(prop_v2ext->hdr.smcd_v2_ext_offset) > max_offset) return NULL; return (struct smc_clc_smcd_v2_extension *) diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index 4e694860ece4..68515a41d776 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -1818,7 +1818,9 @@ void smcr_link_down_cond_sched(struct smc_link *lnk) { if (smc_link_downing(&lnk->state)) { trace_smcr_link_down(lnk, __builtin_return_address(0)); - schedule_work(&lnk->link_down_wrk); + smcr_link_hold(lnk); /* smcr_link_put in link_down_wrk */ + if (!schedule_work(&lnk->link_down_wrk)) + smcr_link_put(lnk); } } @@ -1850,11 +1852,14 @@ static void smc_link_down_work(struct work_struct *work) struct smc_link_group *lgr = link->lgr; if (list_empty(&lgr->list)) - return; + goto out; wake_up_all(&lgr->llc_msg_waiter); down_write(&lgr->llc_conf_mutex); smcr_link_down(link); up_write(&lgr->llc_conf_mutex); + +out: + smcr_link_put(link); /* smcr_link_hold by schedulers of link_down_work */ } static int smc_vlan_by_tcpsk_walk(struct net_device *lower_dev, diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c index b7e25e7e9933..108a4cc2e001 100644 --- a/net/tipc/udp_media.c +++ b/net/tipc/udp_media.c @@ -807,6 +807,7 @@ static void cleanup_bearer(struct work_struct *work) { struct udp_bearer *ub = container_of(work, struct udp_bearer, work); struct udp_replicast *rcast, *tmp; + struct tipc_net *tn; list_for_each_entry_safe(rcast, tmp, &ub->rcast.list, list) { dst_cache_destroy(&rcast->dst_cache); @@ -814,10 +815,14 @@ static void cleanup_bearer(struct work_struct *work) kfree_rcu(rcast, rcu); } + tn = tipc_net(sock_net(ub->ubsock->sk)); + dst_cache_destroy(&ub->rcast.dst_cache); udp_tunnel_sock_release(ub->ubsock); + + /* Note: could use a call_rcu() to avoid another synchronize_net() */ synchronize_net(); - atomic_dec(&tipc_net(sock_net(ub->ubsock->sk))->wq_count); + atomic_dec(&tn->wq_count); kfree(ub); } diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 001ccc55ef0f..6b1762300443 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -2313,6 +2313,7 @@ static int unix_stream_sendmsg(struct socket *sock, struct msghdr *msg, fds_sent = true; if (unlikely(msg->msg_flags & MSG_SPLICE_PAGES)) { + skb->ip_summed = CHECKSUM_UNNECESSARY; err = skb_splice_from_iter(skb, &msg->msg_iter, size, sk->sk_allocation); if (err < 0) { diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 9b1b9dc5a7eb..1e78f575fb56 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -814,7 +814,7 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [NL80211_ATTR_MLO_LINKS] = NLA_POLICY_NESTED_ARRAY(nl80211_policy), [NL80211_ATTR_MLO_LINK_ID] = - NLA_POLICY_RANGE(NLA_U8, 0, IEEE80211_MLD_MAX_NUM_LINKS), + NLA_POLICY_RANGE(NLA_U8, 0, IEEE80211_MLD_MAX_NUM_LINKS - 1), [NL80211_ATTR_MLD_ADDR] = NLA_POLICY_EXACT_LEN(ETH_ALEN), [NL80211_ATTR_MLO_SUPPORT] = { .type = NLA_FLAG }, [NL80211_ATTR_MAX_NUM_AKM_SUITES] = { .type = NLA_REJECT }, diff --git a/net/wireless/sme.c b/net/wireless/sme.c index 431da30817a6..268171600087 100644 --- a/net/wireless/sme.c +++ b/net/wireless/sme.c @@ -83,6 +83,7 @@ static int cfg80211_conn_scan(struct wireless_dev *wdev) if (!request) return -ENOMEM; + request->n_channels = n_channels; if (wdev->conn->params.channel) { enum nl80211_band band = wdev->conn->params.channel->band; struct ieee80211_supported_band *sband = diff --git a/net/wireless/util.c b/net/wireless/util.c index f49b55724f83..18585b1416c6 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -2843,10 +2843,9 @@ void cfg80211_remove_link(struct wireless_dev *wdev, unsigned int link_id) break; } - wdev->valid_links &= ~BIT(link_id); - rdev_del_intf_link(rdev, wdev, link_id); + wdev->valid_links &= ~BIT(link_id); eth_zero_addr(wdev->links[link_id].addr); } diff --git a/rust/Makefile b/rust/Makefile index b5e0a73b78f3..9f59baacaf77 100644 --- a/rust/Makefile +++ b/rust/Makefile @@ -267,9 +267,22 @@ endif bindgen_c_flags_final = $(bindgen_c_flags_lto) -D__BINDGEN__ +# Each `bindgen` release may upgrade the list of Rust target versions. By +# default, the highest stable release in their list is used. Thus we need to set +# a `--rust-target` to avoid future `bindgen` releases emitting code that +# `rustc` may not understand. On top of that, `bindgen` does not support passing +# an unknown Rust target version. +# +# Therefore, the Rust target for `bindgen` can be only as high as the minimum +# Rust version the kernel supports and only as high as the greatest stable Rust +# target supported by the minimum `bindgen` version the kernel supports (that +# is, if we do not test the actual `rustc`/`bindgen` versions running). +# +# Starting with `bindgen` 0.71.0, we will be able to set any future Rust version +# instead, i.e. we will be able to set here our minimum supported Rust version. quiet_cmd_bindgen = BINDGEN $@ cmd_bindgen = \ - $(BINDGEN) $< $(bindgen_target_flags) \ + $(BINDGEN) $< $(bindgen_target_flags) --rust-target 1.68 \ --use-core --with-derive-default --ctypes-prefix core::ffi --no-layout-tests \ --no-debug '.*' --enable-function-attribute-detection \ -o $@ -- $(bindgen_c_flags_final) -DMODULE \ diff --git a/scripts/mksysmap b/scripts/mksysmap index c12723a04655..3accbdb269ac 100755 --- a/scripts/mksysmap +++ b/scripts/mksysmap @@ -26,7 +26,7 @@ # (do not forget a space before each pattern) # local symbols for ARM, MIPS, etc. -/ \\$/d +/ \$/d # local labels, .LBB, .Ltmpxxx, .L__unnamed_xx, .LASANPC, etc. / \.L/d @@ -39,7 +39,7 @@ / __pi_\.L/d # arm64 local symbols in non-VHE KVM namespace -/ __kvm_nvhe_\\$/d +/ __kvm_nvhe_\$/d / __kvm_nvhe_\.L/d # lld arm/aarch64/mips thunks diff --git a/scripts/mod/file2alias.c b/scripts/mod/file2alias.c index 634e40748287..721e0e9f17ca 100644 --- a/scripts/mod/file2alias.c +++ b/scripts/mod/file2alias.c @@ -742,7 +742,7 @@ static void do_input(char *alias, for (i = min / BITS_PER_LONG; i < max / BITS_PER_LONG + 1; i++) arr[i] = TO_NATIVE(arr[i]); - for (i = min; i < max; i++) + for (i = min; i <= max; i++) if (arr[i / BITS_PER_LONG] & (1ULL << (i%BITS_PER_LONG))) sprintf(alias + strlen(alias), "%X,*", i); } diff --git a/scripts/package/PKGBUILD b/scripts/package/PKGBUILD index f83493838cf9..dca706617adc 100644 --- a/scripts/package/PKGBUILD +++ b/scripts/package/PKGBUILD @@ -103,7 +103,7 @@ _package-headers() { _package-api-headers() { pkgdesc="Kernel headers sanitized for use in userspace" - provides=(linux-api-headers) + provides=(linux-api-headers="${pkgver}") conflicts=(linux-api-headers) _prologue diff --git a/scripts/sorttable.h b/scripts/sorttable.h index 7bd0184380d3..a7c5445baf00 100644 --- a/scripts/sorttable.h +++ b/scripts/sorttable.h @@ -110,7 +110,7 @@ static inline unsigned long orc_ip(const int *ip) static int orc_sort_cmp(const void *_a, const void *_b) { - struct orc_entry *orc_a; + struct orc_entry *orc_a, *orc_b; const int *a = g_orc_ip_table + *(int *)_a; const int *b = g_orc_ip_table + *(int *)_b; unsigned long a_val = orc_ip(a); @@ -128,6 +128,9 @@ static int orc_sort_cmp(const void *_a, const void *_b) * whitelisted .o files which didn't get objtool generation. */ orc_a = g_orc_table + (a - g_orc_ip_table); + orc_b = g_orc_table + (b - g_orc_ip_table); + if (orc_a->type == ORC_TYPE_UNDEFINED && orc_b->type == ORC_TYPE_UNDEFINED) + return 0; return orc_a->type == ORC_TYPE_UNDEFINED ? -1 : 1; } diff --git a/security/selinux/ss/services.c b/security/selinux/ss/services.c index a9830fbfc5c6..88850405ded9 100644 --- a/security/selinux/ss/services.c +++ b/security/selinux/ss/services.c @@ -955,7 +955,10 @@ void services_compute_xperms_decision(struct extended_perms_decision *xpermd, xpermd->driver)) return; } else { - BUG(); + pr_warn_once( + "SELinux: unknown extended permission (%u) will be ignored\n", + node->datum.u.xperms->specified); + return; } if (node->key.specified == AVTAB_XPERMS_ALLOWED) { @@ -992,7 +995,8 @@ void services_compute_xperms_decision(struct extended_perms_decision *xpermd, node->datum.u.xperms->perms.p[i]; } } else { - BUG(); + pr_warn_once("SELinux: unknown specified key (%u)\n", + node->key.specified); } } diff --git a/sound/core/control_led.c b/sound/core/control_led.c index 65a1ebe87776..e33dfcf863cf 100644 --- a/sound/core/control_led.c +++ b/sound/core/control_led.c @@ -668,10 +668,16 @@ static void snd_ctl_led_sysfs_add(struct snd_card *card) goto cerr; led->cards[card->number] = led_card; snprintf(link_name, sizeof(link_name), "led-%s", led->name); - WARN(sysfs_create_link(&card->ctl_dev->kobj, &led_card->dev.kobj, link_name), - "can't create symlink to controlC%i device\n", card->number); - WARN(sysfs_create_link(&led_card->dev.kobj, &card->card_dev.kobj, "card"), - "can't create symlink to card%i\n", card->number); + if (sysfs_create_link(&card->ctl_dev->kobj, &led_card->dev.kobj, + link_name)) + dev_err(card->dev, + "%s: can't create symlink to controlC%i device\n", + __func__, card->number); + if (sysfs_create_link(&led_card->dev.kobj, &card->card_dev.kobj, + "card")) + dev_err(card->dev, + "%s: can't create symlink to card%i\n", + __func__, card->number); continue; cerr: diff --git a/sound/core/memalloc.c b/sound/core/memalloc.c index 13b71069ae18..b3853583d2ae 100644 --- a/sound/core/memalloc.c +++ b/sound/core/memalloc.c @@ -505,7 +505,7 @@ static void *snd_dma_wc_alloc(struct snd_dma_buffer *dmab, size_t size) if (!p) return NULL; dmab->addr = dma_map_single(dmab->dev.dev, p, size, DMA_BIDIRECTIONAL); - if (dmab->addr == DMA_MAPPING_ERROR) { + if (dma_mapping_error(dmab->dev.dev, dmab->addr)) { do_free_pages(dmab->area, size, true); return NULL; } diff --git a/sound/core/seq/oss/seq_oss_synth.c b/sound/core/seq/oss/seq_oss_synth.c index e3394919daa0..51ee4c00a843 100644 --- a/sound/core/seq/oss/seq_oss_synth.c +++ b/sound/core/seq/oss/seq_oss_synth.c @@ -66,6 +66,7 @@ static struct seq_oss_synth midi_synth_dev = { }; static DEFINE_SPINLOCK(register_lock); +static DEFINE_MUTEX(sysex_mutex); /* * prototypes @@ -497,6 +498,7 @@ snd_seq_oss_synth_sysex(struct seq_oss_devinfo *dp, int dev, unsigned char *buf, if (!info) return -ENXIO; + guard(mutex)(&sysex_mutex); sysex = info->sysex; if (sysex == NULL) { sysex = kzalloc(sizeof(*sysex), GFP_KERNEL); diff --git a/sound/core/seq/seq_clientmgr.c b/sound/core/seq/seq_clientmgr.c index 3930e2f9082f..77b6ac9b5c11 100644 --- a/sound/core/seq/seq_clientmgr.c +++ b/sound/core/seq/seq_clientmgr.c @@ -1275,10 +1275,16 @@ static int snd_seq_ioctl_set_client_info(struct snd_seq_client *client, if (client->type != client_info->type) return -EINVAL; - /* check validity of midi_version field */ - if (client->user_pversion >= SNDRV_PROTOCOL_VERSION(1, 0, 3) && - client_info->midi_version > SNDRV_SEQ_CLIENT_UMP_MIDI_2_0) - return -EINVAL; + if (client->user_pversion >= SNDRV_PROTOCOL_VERSION(1, 0, 3)) { + /* check validity of midi_version field */ + if (client_info->midi_version > SNDRV_SEQ_CLIENT_UMP_MIDI_2_0) + return -EINVAL; + + /* check if UMP is supported in kernel */ + if (!IS_ENABLED(CONFIG_SND_SEQ_UMP) && + client_info->midi_version > 0) + return -EINVAL; + } /* fill the info fields */ if (client_info->name[0]) diff --git a/sound/core/ump.c b/sound/core/ump.c index 8d37f237f83b..abc537d54b73 100644 --- a/sound/core/ump.c +++ b/sound/core/ump.c @@ -37,6 +37,7 @@ static int process_legacy_output(struct snd_ump_endpoint *ump, u32 *buffer, int count); static void process_legacy_input(struct snd_ump_endpoint *ump, const u32 *src, int words); +static void update_legacy_names(struct snd_ump_endpoint *ump); #else static inline int process_legacy_output(struct snd_ump_endpoint *ump, u32 *buffer, int count) @@ -47,6 +48,9 @@ static inline void process_legacy_input(struct snd_ump_endpoint *ump, const u32 *src, int words) { } +static inline void update_legacy_names(struct snd_ump_endpoint *ump) +{ +} #endif static const struct snd_rawmidi_global_ops snd_ump_rawmidi_ops = { @@ -861,6 +865,7 @@ static int ump_handle_fb_info_msg(struct snd_ump_endpoint *ump, fill_fb_info(ump, &fb->info, buf); if (ump->parsed) { snd_ump_update_group_attrs(ump); + update_legacy_names(ump); seq_notify_fb_change(ump, fb); } } @@ -893,6 +898,7 @@ static int ump_handle_fb_name_msg(struct snd_ump_endpoint *ump, /* notify the FB name update to sequencer, too */ if (ret > 0 && ump->parsed) { snd_ump_update_group_attrs(ump); + update_legacy_names(ump); seq_notify_fb_change(ump, fb); } return ret; @@ -1087,6 +1093,8 @@ static int snd_ump_legacy_open(struct snd_rawmidi_substream *substream) guard(mutex)(&ump->open_mutex); if (ump->legacy_substreams[dir][group]) return -EBUSY; + if (!ump->groups[group].active) + return -ENODEV; if (dir == SNDRV_RAWMIDI_STREAM_OUTPUT) { if (!ump->legacy_out_opens) { err = snd_rawmidi_kernel_open(&ump->core, 0, @@ -1236,7 +1244,7 @@ static int fill_legacy_mapping(struct snd_ump_endpoint *ump) num = 0; for (i = 0; i < SNDRV_UMP_MAX_GROUPS; i++) - if ((group_maps & (1U << i)) && ump->groups[i].valid) + if (group_maps & (1U << i)) ump->legacy_mapping[num++] = i; return num; @@ -1254,11 +1262,20 @@ static void fill_substream_names(struct snd_ump_endpoint *ump, name = ump->groups[idx].name; if (!*name) name = ump->info.name; - snprintf(s->name, sizeof(s->name), "Group %d (%.16s)", - idx + 1, name); + scnprintf(s->name, sizeof(s->name), "Group %d (%.16s)%s", + idx + 1, name, + ump->groups[idx].active ? "" : " [Inactive]"); } } +static void update_legacy_names(struct snd_ump_endpoint *ump) +{ + struct snd_rawmidi *rmidi = ump->legacy_rmidi; + + fill_substream_names(ump, rmidi, SNDRV_RAWMIDI_STREAM_INPUT); + fill_substream_names(ump, rmidi, SNDRV_RAWMIDI_STREAM_OUTPUT); +} + int snd_ump_attach_legacy_rawmidi(struct snd_ump_endpoint *ump, char *id, int device) { @@ -1295,10 +1312,7 @@ int snd_ump_attach_legacy_rawmidi(struct snd_ump_endpoint *ump, rmidi->ops = &snd_ump_legacy_ops; rmidi->private_data = ump; ump->legacy_rmidi = rmidi; - if (input) - fill_substream_names(ump, rmidi, SNDRV_RAWMIDI_STREAM_INPUT); - if (output) - fill_substream_names(ump, rmidi, SNDRV_RAWMIDI_STREAM_OUTPUT); + update_legacy_names(ump); ump_dbg(ump, "Created a legacy rawmidi #%d (%s)\n", device, id); return 0; diff --git a/sound/pci/hda/cs35l56_hda.c b/sound/pci/hda/cs35l56_hda.c index e3ac0e23ae32..7baf3b506eef 100644 --- a/sound/pci/hda/cs35l56_hda.c +++ b/sound/pci/hda/cs35l56_hda.c @@ -151,10 +151,6 @@ static int cs35l56_hda_runtime_resume(struct device *dev) } } - ret = cs35l56_force_sync_asp1_registers_from_cache(&cs35l56->base); - if (ret) - goto err; - return 0; err: @@ -1059,9 +1055,6 @@ int cs35l56_hda_common_probe(struct cs35l56_hda *cs35l56, int hid, int id) regmap_multi_reg_write(cs35l56->base.regmap, cs35l56_hda_dai_config, ARRAY_SIZE(cs35l56_hda_dai_config)); - ret = cs35l56_force_sync_asp1_registers_from_cache(&cs35l56->base); - if (ret) - goto dsp_err; /* * By default only enable one ASP1TXn, where n=amplifier index, @@ -1087,7 +1080,6 @@ int cs35l56_hda_common_probe(struct cs35l56_hda *cs35l56, int hid, int id) pm_err: pm_runtime_disable(cs35l56->base.dev); -dsp_err: cs_dsp_remove(&cs35l56->cs_dsp); err: gpiod_set_value_cansleep(cs35l56->base.reset_gpio, 0); diff --git a/sound/pci/hda/patch_ca0132.c b/sound/pci/hda/patch_ca0132.c index e4673a71551a..d40197fb5fbd 100644 --- a/sound/pci/hda/patch_ca0132.c +++ b/sound/pci/hda/patch_ca0132.c @@ -1134,7 +1134,6 @@ struct ca0132_spec { struct hda_codec *codec; struct delayed_work unsol_hp_work; - int quirk; #ifdef ENABLE_TUNING_CONTROLS long cur_ctl_vals[TUNING_CTLS_COUNT]; @@ -1166,7 +1165,6 @@ struct ca0132_spec { * CA0132 quirks table */ enum { - QUIRK_NONE, QUIRK_ALIENWARE, QUIRK_ALIENWARE_M17XR4, QUIRK_SBZ, @@ -1176,10 +1174,11 @@ enum { QUIRK_R3D, QUIRK_AE5, QUIRK_AE7, + QUIRK_NONE = HDA_FIXUP_ID_NOT_SET, }; #ifdef CONFIG_PCI -#define ca0132_quirk(spec) ((spec)->quirk) +#define ca0132_quirk(spec) ((spec)->codec->fixup_id) #define ca0132_use_pci_mmio(spec) ((spec)->use_pci_mmio) #define ca0132_use_alt_functions(spec) ((spec)->use_alt_functions) #define ca0132_use_alt_controls(spec) ((spec)->use_alt_controls) @@ -1293,7 +1292,7 @@ static const struct hda_pintbl ae7_pincfgs[] = { {} }; -static const struct snd_pci_quirk ca0132_quirks[] = { +static const struct hda_quirk ca0132_quirks[] = { SND_PCI_QUIRK(0x1028, 0x057b, "Alienware M17x R4", QUIRK_ALIENWARE_M17XR4), SND_PCI_QUIRK(0x1028, 0x0685, "Alienware 15 2015", QUIRK_ALIENWARE), SND_PCI_QUIRK(0x1028, 0x0688, "Alienware 17 2015", QUIRK_ALIENWARE), @@ -1316,6 +1315,19 @@ static const struct snd_pci_quirk ca0132_quirks[] = { {} }; +static const struct hda_model_fixup ca0132_quirk_models[] = { + { .id = QUIRK_ALIENWARE, .name = "alienware" }, + { .id = QUIRK_ALIENWARE_M17XR4, .name = "alienware-m17xr4" }, + { .id = QUIRK_SBZ, .name = "sbz" }, + { .id = QUIRK_ZXR, .name = "zxr" }, + { .id = QUIRK_ZXR_DBPRO, .name = "zxr-dbpro" }, + { .id = QUIRK_R3DI, .name = "r3di" }, + { .id = QUIRK_R3D, .name = "r3d" }, + { .id = QUIRK_AE5, .name = "ae5" }, + { .id = QUIRK_AE7, .name = "ae7" }, + {} +}; + /* Output selection quirk info structures. */ #define MAX_QUIRK_MMIO_GPIO_SET_VALS 3 #define MAX_QUIRK_SCP_SET_VALS 2 @@ -9957,17 +9969,15 @@ static int ca0132_prepare_verbs(struct hda_codec *codec) */ static void sbz_detect_quirk(struct hda_codec *codec) { - struct ca0132_spec *spec = codec->spec; - switch (codec->core.subsystem_id) { case 0x11020033: - spec->quirk = QUIRK_ZXR; + codec->fixup_id = QUIRK_ZXR; break; case 0x1102003f: - spec->quirk = QUIRK_ZXR_DBPRO; + codec->fixup_id = QUIRK_ZXR_DBPRO; break; default: - spec->quirk = QUIRK_SBZ; + codec->fixup_id = QUIRK_SBZ; break; } } @@ -9976,7 +9986,6 @@ static int patch_ca0132(struct hda_codec *codec) { struct ca0132_spec *spec; int err; - const struct snd_pci_quirk *quirk; codec_dbg(codec, "patch_ca0132\n"); @@ -9987,11 +9996,7 @@ static int patch_ca0132(struct hda_codec *codec) spec->codec = codec; /* Detect codec quirk */ - quirk = snd_pci_quirk_lookup(codec->bus->pci, ca0132_quirks); - if (quirk) - spec->quirk = quirk->value; - else - spec->quirk = QUIRK_NONE; + snd_hda_pick_fixup(codec, ca0132_quirk_models, ca0132_quirks, NULL); if (ca0132_quirk(spec) == QUIRK_SBZ) sbz_detect_quirk(codec); @@ -10068,7 +10073,7 @@ static int patch_ca0132(struct hda_codec *codec) spec->mem_base = pci_iomap(codec->bus->pci, 2, 0xC20); if (spec->mem_base == NULL) { codec_warn(codec, "pci_iomap failed! Setting quirk to QUIRK_NONE."); - spec->quirk = QUIRK_NONE; + codec->fixup_id = QUIRK_NONE; } } #endif diff --git a/sound/pci/hda/patch_conexant.c b/sound/pci/hda/patch_conexant.c index 2e9f817b948e..538c37a78a56 100644 --- a/sound/pci/hda/patch_conexant.c +++ b/sound/pci/hda/patch_conexant.c @@ -307,6 +307,7 @@ enum { CXT_FIXUP_HP_MIC_NO_PRESENCE, CXT_PINCFG_SWS_JS201D, CXT_PINCFG_TOP_SPEAKER, + CXT_FIXUP_HP_A_U, }; /* for hda_fixup_thinkpad_acpi() */ @@ -774,6 +775,18 @@ static void cxt_setup_mute_led(struct hda_codec *codec, } } +static void cxt_setup_gpio_unmute(struct hda_codec *codec, + unsigned int gpio_mute_mask) +{ + if (gpio_mute_mask) { + // set gpio data to 0. + snd_hda_codec_write(codec, 0x01, 0, AC_VERB_SET_GPIO_DATA, 0); + snd_hda_codec_write(codec, 0x01, 0, AC_VERB_SET_GPIO_MASK, gpio_mute_mask); + snd_hda_codec_write(codec, 0x01, 0, AC_VERB_SET_GPIO_DIRECTION, gpio_mute_mask); + snd_hda_codec_write(codec, 0x01, 0, AC_VERB_SET_GPIO_STICKY_MASK, 0); + } +} + static void cxt_fixup_mute_led_gpio(struct hda_codec *codec, const struct hda_fixup *fix, int action) { @@ -788,6 +801,15 @@ static void cxt_fixup_hp_zbook_mute_led(struct hda_codec *codec, cxt_setup_mute_led(codec, 0x10, 0x20); } +static void cxt_fixup_hp_a_u(struct hda_codec *codec, + const struct hda_fixup *fix, int action) +{ + // Init vers in BIOS mute the spk/hp by set gpio high to avoid pop noise, + // so need to unmute once by clearing the gpio data when runs into the system. + if (action == HDA_FIXUP_ACT_INIT) + cxt_setup_gpio_unmute(codec, 0x2); +} + /* ThinkPad X200 & co with cxt5051 */ static const struct hda_pintbl cxt_pincfg_lenovo_x200[] = { { 0x16, 0x042140ff }, /* HP (seq# overridden) */ @@ -998,6 +1020,10 @@ static const struct hda_fixup cxt_fixups[] = { { } }, }, + [CXT_FIXUP_HP_A_U] = { + .type = HDA_FIXUP_FUNC, + .v.func = cxt_fixup_hp_a_u, + }, }; static const struct hda_quirk cxt5045_fixups[] = { @@ -1072,6 +1098,7 @@ static const struct hda_quirk cxt5066_fixups[] = { SND_PCI_QUIRK(0x103c, 0x8457, "HP Z2 G4 mini", CXT_FIXUP_HP_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x103c, 0x8458, "HP Z2 G4 mini premium", CXT_FIXUP_HP_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1043, 0x138d, "Asus", CXT_FIXUP_HEADPHONE_MIC_PIN), + SND_PCI_QUIRK(0x14f1, 0x0252, "MBX-Z60MR100", CXT_FIXUP_HP_A_U), SND_PCI_QUIRK(0x14f1, 0x0265, "SWS JS201D", CXT_PINCFG_SWS_JS201D), SND_PCI_QUIRK(0x152d, 0x0833, "OLPC XO-1.5", CXT_FIXUP_OLPC_XO), SND_PCI_QUIRK(0x17aa, 0x20f2, "Lenovo T400", CXT_PINCFG_LENOVO_TP410), @@ -1117,6 +1144,7 @@ static const struct hda_model_fixup cxt5066_fixup_models[] = { { .id = CXT_PINCFG_LENOVO_NOTEBOOK, .name = "lenovo-20149" }, { .id = CXT_PINCFG_SWS_JS201D, .name = "sws-js201d" }, { .id = CXT_PINCFG_TOP_SPEAKER, .name = "sirius-top-speaker" }, + { .id = CXT_FIXUP_HP_A_U, .name = "HP-U-support" }, {} }; diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 973671e0cdb0..3ed82f98e2de 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -7704,6 +7704,7 @@ enum { ALC274_FIXUP_HP_MIC, ALC274_FIXUP_HP_HEADSET_MIC, ALC274_FIXUP_HP_ENVY_GPIO, + ALC274_FIXUP_ASUS_ZEN_AIO_27, ALC256_FIXUP_ASUS_HPE, ALC285_FIXUP_THINKPAD_NO_BASS_SPK_HEADSET_JACK, ALC287_FIXUP_HP_GPIO_LED, @@ -9505,6 +9506,26 @@ static const struct hda_fixup alc269_fixups[] = { .type = HDA_FIXUP_FUNC, .v.func = alc274_fixup_hp_envy_gpio, }, + [ALC274_FIXUP_ASUS_ZEN_AIO_27] = { + .type = HDA_FIXUP_VERBS, + .v.verbs = (const struct hda_verb[]) { + { 0x20, AC_VERB_SET_COEF_INDEX, 0x10 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0xc420 }, + { 0x20, AC_VERB_SET_COEF_INDEX, 0x40 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0x8800 }, + { 0x20, AC_VERB_SET_COEF_INDEX, 0x49 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0x0249 }, + { 0x20, AC_VERB_SET_COEF_INDEX, 0x4a }, + { 0x20, AC_VERB_SET_PROC_COEF, 0x202b }, + { 0x20, AC_VERB_SET_COEF_INDEX, 0x62 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0xa007 }, + { 0x20, AC_VERB_SET_COEF_INDEX, 0x6b }, + { 0x20, AC_VERB_SET_PROC_COEF, 0x5060 }, + {} + }, + .chained = true, + .chain_id = ALC2XX_FIXUP_HEADSET_MIC, + }, [ALC256_FIXUP_ASUS_HPE] = { .type = HDA_FIXUP_VERBS, .v.verbs = (const struct hda_verb[]) { @@ -10127,6 +10148,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1025, 0x1430, "Acer TravelMate B311R-31", ALC256_FIXUP_ACER_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1025, 0x1466, "Acer Aspire A515-56", ALC255_FIXUP_ACER_HEADPHONE_AND_MIC), SND_PCI_QUIRK(0x1025, 0x1534, "Acer Predator PH315-54", ALC255_FIXUP_ACER_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1025, 0x159c, "Acer Nitro 5 AN515-58", ALC2XX_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x1025, 0x169a, "Acer Swift SFG16", ALC256_FIXUP_ACER_SFG16_MICMUTE_LED), SND_PCI_QUIRK(0x1028, 0x0470, "Dell M101z", ALC269_FIXUP_DELL_M101Z), SND_PCI_QUIRK(0x1028, 0x053c, "Dell Latitude E5430", ALC292_FIXUP_DELL_E7X), @@ -10614,6 +10636,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1043, 0x1f62, "ASUS UX7602ZM", ALC245_FIXUP_CS35L41_SPI_2), SND_PCI_QUIRK(0x1043, 0x1f92, "ASUS ROG Flow X16", ALC289_FIXUP_ASUS_GA401), SND_PCI_QUIRK(0x1043, 0x3030, "ASUS ZN270IE", ALC256_FIXUP_ASUS_AIO_GPIO2), + SND_PCI_QUIRK(0x1043, 0x31d0, "ASUS Zen AIO 27 Z272SD_A272SD", ALC274_FIXUP_ASUS_ZEN_AIO_27), SND_PCI_QUIRK(0x1043, 0x3a20, "ASUS G614JZR", ALC285_FIXUP_ASUS_SPI_REAR_SPEAKERS), SND_PCI_QUIRK(0x1043, 0x3a30, "ASUS G814JVR/JIR", ALC285_FIXUP_ASUS_SPI_REAR_SPEAKERS), SND_PCI_QUIRK(0x1043, 0x3a40, "ASUS G814JZR", ALC285_FIXUP_ASUS_SPI_REAR_SPEAKERS), @@ -10970,6 +10993,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0xf111, 0x0001, "Framework Laptop", ALC295_FIXUP_FRAMEWORK_LAPTOP_MIC_NO_PRESENCE), SND_PCI_QUIRK(0xf111, 0x0006, "Framework Laptop", ALC295_FIXUP_FRAMEWORK_LAPTOP_MIC_NO_PRESENCE), SND_PCI_QUIRK(0xf111, 0x0009, "Framework Laptop", ALC295_FIXUP_FRAMEWORK_LAPTOP_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0xf111, 0x000c, "Framework Laptop", ALC295_FIXUP_FRAMEWORK_LAPTOP_MIC_NO_PRESENCE), #if 0 /* Below is a quirk table taken from the old code. @@ -11161,6 +11185,7 @@ static const struct hda_model_fixup alc269_fixup_models[] = { {.id = ALC255_FIXUP_ACER_HEADPHONE_AND_MIC, .name = "alc255-acer-headphone-and-mic"}, {.id = ALC285_FIXUP_HP_GPIO_AMP_INIT, .name = "alc285-hp-amp-init"}, {.id = ALC236_FIXUP_LENOVO_INV_DMIC, .name = "alc236-fixup-lenovo-inv-mic"}, + {.id = ALC2XX_FIXUP_HEADSET_MIC, .name = "alc2xx-fixup-headset-mic"}, {} }; #define ALC225_STANDARD_PINS \ diff --git a/sound/sh/sh_dac_audio.c b/sound/sh/sh_dac_audio.c index e7b6ce7bd086..1c1c14708f01 100644 --- a/sound/sh/sh_dac_audio.c +++ b/sound/sh/sh_dac_audio.c @@ -163,7 +163,7 @@ static int snd_sh_dac_pcm_copy(struct snd_pcm_substream *substream, /* channel is not used (interleaved data) */ struct snd_sh_dac *chip = snd_pcm_substream_chip(substream); - if (copy_from_iter_toio(chip->data_buffer + pos, src, count)) + if (copy_from_iter(chip->data_buffer + pos, count, src) != count) return -EFAULT; chip->buffer_end = chip->data_buffer + pos + count; @@ -182,7 +182,7 @@ static int snd_sh_dac_pcm_silence(struct snd_pcm_substream *substream, /* channel is not used (interleaved data) */ struct snd_sh_dac *chip = snd_pcm_substream_chip(substream); - memset_io(chip->data_buffer + pos, 0, count); + memset(chip->data_buffer + pos, 0, count); chip->buffer_end = chip->data_buffer + pos + count; if (chip->empty) { @@ -211,7 +211,6 @@ static const struct snd_pcm_ops snd_sh_dac_pcm_ops = { .pointer = snd_sh_dac_pcm_pointer, .copy = snd_sh_dac_pcm_copy, .fill_silence = snd_sh_dac_pcm_silence, - .mmap = snd_pcm_lib_mmap_iomem, }; static int snd_sh_dac_pcm(struct snd_sh_dac *chip, int device) diff --git a/sound/soc/amd/ps/pci-ps.c b/sound/soc/amd/ps/pci-ps.c index c72d666d51bd..5c4a0be7a788 100644 --- a/sound/soc/amd/ps/pci-ps.c +++ b/sound/soc/amd/ps/pci-ps.c @@ -375,11 +375,18 @@ static int get_acp63_device_config(struct pci_dev *pci, struct acp63_dev_data *a { struct acpi_device *pdm_dev; const union acpi_object *obj; + acpi_handle handle; + acpi_integer dmic_status; u32 config; bool is_dmic_dev = false; bool is_sdw_dev = false; + bool wov_en, dmic_en; int ret; + /* IF WOV entry not found, enable dmic based on acp-audio-device-type entry*/ + wov_en = true; + dmic_en = false; + config = readl(acp_data->acp63_base + ACP_PIN_CONFIG); switch (config) { case ACP_CONFIG_4: @@ -412,10 +419,18 @@ static int get_acp63_device_config(struct pci_dev *pci, struct acp63_dev_data *a if (!acpi_dev_get_property(pdm_dev, "acp-audio-device-type", ACPI_TYPE_INTEGER, &obj) && obj->integer.value == ACP_DMIC_DEV) - is_dmic_dev = true; + dmic_en = true; } + + handle = ACPI_HANDLE(&pci->dev); + ret = acpi_evaluate_integer(handle, "_WOV", NULL, &dmic_status); + if (!ACPI_FAILURE(ret)) + wov_en = dmic_status; } + if (dmic_en && wov_en) + is_dmic_dev = true; + if (acp_data->is_sdw_config) { ret = acp_scan_sdw_devices(&pci->dev, ACP63_SDW_ADDR); if (!ret && acp_data->info.link_mask) diff --git a/sound/soc/amd/yc/acp6x-mach.c b/sound/soc/amd/yc/acp6x-mach.c index e38c5885dadf..ecf57a6cb7c3 100644 --- a/sound/soc/amd/yc/acp6x-mach.c +++ b/sound/soc/amd/yc/acp6x-mach.c @@ -578,14 +578,19 @@ static int acp6x_probe(struct platform_device *pdev) handle = ACPI_HANDLE(pdev->dev.parent); ret = acpi_evaluate_integer(handle, "_WOV", NULL, &dmic_status); - if (!ACPI_FAILURE(ret)) + if (!ACPI_FAILURE(ret)) { wov_en = dmic_status; + if (!wov_en) + return -ENODEV; + } else { + /* Incase of ACPI method read failure then jump to check_dmi_entry */ + goto check_dmi_entry; + } - if (is_dmic_enable && wov_en) + if (is_dmic_enable) platform_set_drvdata(pdev, &acp6x_card); - else - return 0; +check_dmi_entry: /* check for any DMI overrides */ dmi_id = dmi_first_match(yc_acp_quirk_table); if (dmi_id) diff --git a/sound/soc/codecs/tas2781-i2c.c b/sound/soc/codecs/tas2781-i2c.c index 12d093437ba9..1b2f55030c39 100644 --- a/sound/soc/codecs/tas2781-i2c.c +++ b/sound/soc/codecs/tas2781-i2c.c @@ -370,7 +370,7 @@ static void sngl_calib_start(struct tasdevice_priv *tas_priv, int i, tasdevice_dev_read(tas_priv, i, p[j].reg, (int *)&p[j].val[0]); } else { - switch (p[j].reg) { + switch (tas2781_cali_start_reg[j].reg) { case 0: { if (!reg[0]) continue; diff --git a/sound/soc/fsl/Kconfig b/sound/soc/fsl/Kconfig index e283751abfef..678540b78280 100644 --- a/sound/soc/fsl/Kconfig +++ b/sound/soc/fsl/Kconfig @@ -29,6 +29,7 @@ config SND_SOC_FSL_SAI config SND_SOC_FSL_MQS tristate "Medium Quality Sound (MQS) module support" depends on SND_SOC_FSL_SAI + depends on IMX_SCMI_MISC_DRV || !IMX_SCMI_MISC_DRV select REGMAP_MMIO help Say Y if you want to add Medium Quality Sound (MQS) diff --git a/sound/soc/fsl/fsl_spdif.c b/sound/soc/fsl/fsl_spdif.c index b6ff04f7138a..ee946e0d3f49 100644 --- a/sound/soc/fsl/fsl_spdif.c +++ b/sound/soc/fsl/fsl_spdif.c @@ -1204,7 +1204,7 @@ static struct snd_kcontrol_new fsl_spdif_ctrls[] = { }, /* DPLL lock info get controller */ { - .iface = SNDRV_CTL_ELEM_IFACE_PCM, + .iface = SNDRV_CTL_ELEM_IFACE_MIXER, .name = RX_SAMPLE_RATE_KCONTROL, .access = SNDRV_CTL_ELEM_ACCESS_READ | SNDRV_CTL_ELEM_ACCESS_VOLATILE, diff --git a/sound/soc/fsl/fsl_xcvr.c b/sound/soc/fsl/fsl_xcvr.c index beede7344efd..4341269eb977 100644 --- a/sound/soc/fsl/fsl_xcvr.c +++ b/sound/soc/fsl/fsl_xcvr.c @@ -169,7 +169,7 @@ static int fsl_xcvr_capds_put(struct snd_kcontrol *kcontrol, } static struct snd_kcontrol_new fsl_xcvr_earc_capds_kctl = { - .iface = SNDRV_CTL_ELEM_IFACE_PCM, + .iface = SNDRV_CTL_ELEM_IFACE_MIXER, .name = "Capabilities Data Structure", .access = SNDRV_CTL_ELEM_ACCESS_READWRITE, .info = fsl_xcvr_type_capds_bytes_info, diff --git a/sound/soc/generic/audio-graph-card2.c b/sound/soc/generic/audio-graph-card2.c index 93eee40cec76..63837e259659 100644 --- a/sound/soc/generic/audio-graph-card2.c +++ b/sound/soc/generic/audio-graph-card2.c @@ -779,7 +779,7 @@ static void graph_link_init(struct simple_util_priv *priv, of_node_get(port_codec); if (graph_lnk_is_multi(port_codec)) { ep_codec = graph_get_next_multi_ep(&port_codec); - of_node_put(port_cpu); + of_node_put(port_codec); port_codec = ep_to_port(ep_codec); } else { ep_codec = port_to_endpoint(port_codec); diff --git a/sound/soc/intel/boards/sof_sdw.c b/sound/soc/intel/boards/sof_sdw.c index a58842a8c8a6..41042259f2b2 100644 --- a/sound/soc/intel/boards/sof_sdw.c +++ b/sound/soc/intel/boards/sof_sdw.c @@ -608,7 +608,7 @@ static const struct dmi_system_id sof_sdw_quirk_table[] = { .callback = sof_sdw_quirk_cb, .matches = { DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), - DMI_EXACT_MATCH(DMI_PRODUCT_SKU, "233C") + DMI_MATCH(DMI_PRODUCT_NAME, "21QB") }, /* Note this quirk excludes the CODEC mic */ .driver_data = (void *)(SOC_SDW_CODEC_MIC), @@ -617,9 +617,26 @@ static const struct dmi_system_id sof_sdw_quirk_table[] = { .callback = sof_sdw_quirk_cb, .matches = { DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), - DMI_EXACT_MATCH(DMI_PRODUCT_SKU, "233B") + DMI_MATCH(DMI_PRODUCT_NAME, "21QA") }, - .driver_data = (void *)(SOC_SDW_SIDECAR_AMPS), + /* Note this quirk excludes the CODEC mic */ + .driver_data = (void *)(SOC_SDW_CODEC_MIC), + }, + { + .callback = sof_sdw_quirk_cb, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_NAME, "21Q6") + }, + .driver_data = (void *)(SOC_SDW_SIDECAR_AMPS | SOC_SDW_CODEC_MIC), + }, + { + .callback = sof_sdw_quirk_cb, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_NAME, "21Q7") + }, + .driver_data = (void *)(SOC_SDW_SIDECAR_AMPS | SOC_SDW_CODEC_MIC), }, /* ArrowLake devices */ @@ -1003,8 +1020,12 @@ static int sof_card_dai_links_create(struct snd_soc_card *card) return ret; } - /* One per DAI link, worst case is a DAI link for every endpoint */ - sof_dais = kcalloc(num_ends, sizeof(*sof_dais), GFP_KERNEL); + /* + * One per DAI link, worst case is a DAI link for every endpoint, also + * add one additional to act as a terminator such that code can iterate + * until it hits an uninitialised DAI. + */ + sof_dais = kcalloc(num_ends + 1, sizeof(*sof_dais), GFP_KERNEL); if (!sof_dais) return -ENOMEM; diff --git a/sound/soc/sof/intel/hda-dai.c b/sound/soc/sof/intel/hda-dai.c index ac505c7ad342..82f46ecd9430 100644 --- a/sound/soc/sof/intel/hda-dai.c +++ b/sound/soc/sof/intel/hda-dai.c @@ -103,8 +103,10 @@ hda_dai_get_ops(struct snd_pcm_substream *substream, struct snd_soc_dai *cpu_dai return sdai->platform_private; } -int hda_link_dma_cleanup(struct snd_pcm_substream *substream, struct hdac_ext_stream *hext_stream, - struct snd_soc_dai *cpu_dai) +static int +hda_link_dma_cleanup(struct snd_pcm_substream *substream, + struct hdac_ext_stream *hext_stream, + struct snd_soc_dai *cpu_dai, bool release) { const struct hda_dai_widget_dma_ops *ops = hda_dai_get_ops(substream, cpu_dai); struct sof_intel_hda_stream *hda_stream; @@ -128,6 +130,17 @@ int hda_link_dma_cleanup(struct snd_pcm_substream *substream, struct hdac_ext_st snd_hdac_ext_bus_link_clear_stream_id(hlink, stream_tag); } + if (!release) { + /* + * Force stream reconfiguration without releasing the channel on + * subsequent stream restart (without free), including LinkDMA + * reset. + * The stream is released via hda_dai_hw_free() + */ + hext_stream->link_prepared = 0; + return 0; + } + if (ops->release_hext_stream) ops->release_hext_stream(sdev, cpu_dai, substream); @@ -211,7 +224,7 @@ static int __maybe_unused hda_dai_hw_free(struct snd_pcm_substream *substream, if (!hext_stream) return 0; - return hda_link_dma_cleanup(substream, hext_stream, cpu_dai); + return hda_link_dma_cleanup(substream, hext_stream, cpu_dai, true); } static int __maybe_unused hda_dai_hw_params_data(struct snd_pcm_substream *substream, @@ -304,7 +317,8 @@ static int __maybe_unused hda_dai_trigger(struct snd_pcm_substream *substream, i switch (cmd) { case SNDRV_PCM_TRIGGER_STOP: case SNDRV_PCM_TRIGGER_SUSPEND: - ret = hda_link_dma_cleanup(substream, hext_stream, dai); + ret = hda_link_dma_cleanup(substream, hext_stream, dai, + cmd == SNDRV_PCM_TRIGGER_STOP ? false : true); if (ret < 0) { dev_err(sdev->dev, "%s: failed to clean up link DMA\n", __func__); return ret; @@ -656,8 +670,7 @@ static int hda_dai_suspend(struct hdac_bus *bus) } ret = hda_link_dma_cleanup(hext_stream->link_substream, - hext_stream, - cpu_dai); + hext_stream, cpu_dai, true); if (ret < 0) return ret; } diff --git a/sound/soc/sof/intel/hda.h b/sound/soc/sof/intel/hda.h index b74a472435b5..4a4a0b55f0bc 100644 --- a/sound/soc/sof/intel/hda.h +++ b/sound/soc/sof/intel/hda.h @@ -1028,8 +1028,6 @@ const struct hda_dai_widget_dma_ops * hda_select_dai_widget_ops(struct snd_sof_dev *sdev, struct snd_sof_widget *swidget); int hda_dai_config(struct snd_soc_dapm_widget *w, unsigned int flags, struct snd_sof_dai_config_data *data); -int hda_link_dma_cleanup(struct snd_pcm_substream *substream, struct hdac_ext_stream *hext_stream, - struct snd_soc_dai *cpu_dai); static inline struct snd_sof_dev *widget_to_sdev(struct snd_soc_dapm_widget *w) { diff --git a/sound/usb/format.c b/sound/usb/format.c index 0cbf1d4fbe6e..6049d957694c 100644 --- a/sound/usb/format.c +++ b/sound/usb/format.c @@ -60,6 +60,8 @@ static u64 parse_audio_format_i_type(struct snd_usb_audio *chip, pcm_formats |= SNDRV_PCM_FMTBIT_SPECIAL; /* flag potentially raw DSD capable altsettings */ fp->dsd_raw = true; + /* clear special format bit to avoid "unsupported format" msg below */ + format &= ~UAC2_FORMAT_TYPE_I_RAW_DATA; } format <<= 1; @@ -71,8 +73,11 @@ static u64 parse_audio_format_i_type(struct snd_usb_audio *chip, sample_width = as->bBitResolution; sample_bytes = as->bSubslotSize; - if (format & UAC3_FORMAT_TYPE_I_RAW_DATA) + if (format & UAC3_FORMAT_TYPE_I_RAW_DATA) { pcm_formats |= SNDRV_PCM_FMTBIT_SPECIAL; + /* clear special format bit to avoid "unsupported format" msg below */ + format &= ~UAC3_FORMAT_TYPE_I_RAW_DATA; + } format <<= 1; break; diff --git a/sound/usb/mixer_us16x08.c b/sound/usb/mixer_us16x08.c index 6eb7d93b358d..20ac32635f1f 100644 --- a/sound/usb/mixer_us16x08.c +++ b/sound/usb/mixer_us16x08.c @@ -687,7 +687,7 @@ static int snd_us16x08_meter_get(struct snd_kcontrol *kcontrol, struct usb_mixer_elem_info *elem = kcontrol->private_data; struct snd_usb_audio *chip = elem->head.mixer->chip; struct snd_us16x08_meter_store *store = elem->private_data; - u8 meter_urb[64]; + u8 meter_urb[64] = {0}; switch (kcontrol->private_value) { case 0: { diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index 00101875d9a8..8ba0aff8be2e 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -2179,6 +2179,8 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = { QUIRK_FLAG_CTL_MSG_DELAY_1M | QUIRK_FLAG_MIC_RES_384), DEVICE_FLG(0x046d, 0x09a4, /* Logitech QuickCam E 3500 */ QUIRK_FLAG_CTL_MSG_DELAY_1M | QUIRK_FLAG_IGNORE_CTL_ERROR), + DEVICE_FLG(0x0499, 0x1506, /* Yamaha THR5 */ + QUIRK_FLAG_GENERIC_IMPLICIT_FB), DEVICE_FLG(0x0499, 0x1509, /* Steinberg UR22 */ QUIRK_FLAG_GENERIC_IMPLICIT_FB), DEVICE_FLG(0x0499, 0x3108, /* Yamaha YIT-W12TX */ @@ -2323,6 +2325,8 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = { QUIRK_FLAG_DSD_RAW), DEVICE_FLG(0x2522, 0x0007, /* LH Labs Geek Out HD Audio 1V5 */ QUIRK_FLAG_SET_IFACE_FIRST), + DEVICE_FLG(0x262a, 0x9302, /* ddHiFi TC44C */ + QUIRK_FLAG_DSD_RAW), DEVICE_FLG(0x2708, 0x0002, /* Audient iD14 */ QUIRK_FLAG_IGNORE_CTL_ERROR), DEVICE_FLG(0x2912, 0x30c8, /* Audioengine D1 */ diff --git a/tools/hv/hv_fcopy_uio_daemon.c b/tools/hv/hv_fcopy_uio_daemon.c index 7a00f3066a98..12743d7f164f 100644 --- a/tools/hv/hv_fcopy_uio_daemon.c +++ b/tools/hv/hv_fcopy_uio_daemon.c @@ -35,8 +35,6 @@ #define WIN8_SRV_MINOR 1 #define WIN8_SRV_VERSION (WIN8_SRV_MAJOR << 16 | WIN8_SRV_MINOR) -#define MAX_FOLDER_NAME 15 -#define MAX_PATH_LEN 15 #define FCOPY_UIO "/sys/bus/vmbus/devices/eb765408-105f-49b6-b4aa-c123b64d17d4/uio" #define FCOPY_VER_COUNT 1 @@ -51,7 +49,7 @@ static const int fw_versions[] = { #define HV_RING_SIZE 0x4000 /* 16KB ring buffer size */ -unsigned char desc[HV_RING_SIZE]; +static unsigned char desc[HV_RING_SIZE]; static int target_fd; static char target_fname[PATH_MAX]; @@ -409,8 +407,8 @@ int main(int argc, char *argv[]) struct vmbus_br txbr, rxbr; void *ring; uint32_t len = HV_RING_SIZE; - char uio_name[MAX_FOLDER_NAME] = {0}; - char uio_dev_path[MAX_PATH_LEN] = {0}; + char uio_name[NAME_MAX] = {0}; + char uio_dev_path[PATH_MAX] = {0}; static struct option long_options[] = { {"help", no_argument, 0, 'h' }, diff --git a/tools/hv/hv_set_ifconfig.sh b/tools/hv/hv_set_ifconfig.sh index 440a91b35823..2f8baed2b8f7 100755 --- a/tools/hv/hv_set_ifconfig.sh +++ b/tools/hv/hv_set_ifconfig.sh @@ -81,7 +81,7 @@ echo "ONBOOT=yes" >> $1 cp $1 /etc/sysconfig/network-scripts/ -chmod 600 $2 +umask 0177 interface=$(echo $2 | awk -F - '{ print $2 }') filename="${2##*/}" diff --git a/tools/include/uapi/linux/stddef.h b/tools/include/uapi/linux/stddef.h index bb6ea517efb5..c53cde425406 100644 --- a/tools/include/uapi/linux/stddef.h +++ b/tools/include/uapi/linux/stddef.h @@ -8,6 +8,13 @@ #define __always_inline __inline__ #endif +/* Not all C++ standards support type declarations inside an anonymous union */ +#ifndef __cplusplus +#define __struct_group_tag(TAG) TAG +#else +#define __struct_group_tag(TAG) +#endif + /** * __struct_group() - Create a mirrored named and anonyomous struct * @@ -20,14 +27,14 @@ * and size: one anonymous and one named. The former's members can be used * normally without sub-struct naming, and the latter can be used to * reason about the start, end, and size of the group of struct members. - * The named struct can also be explicitly tagged for layer reuse, as well - * as both having struct attributes appended. + * The named struct can also be explicitly tagged for layer reuse (C only), + * as well as both having struct attributes appended. */ #define __struct_group(TAG, NAME, ATTRS, MEMBERS...) \ union { \ struct { MEMBERS } ATTRS; \ - struct TAG { MEMBERS } ATTRS NAME; \ - } + struct __struct_group_tag(TAG) { MEMBERS } ATTRS NAME; \ + } ATTRS /** * __DECLARE_FLEX_ARRAY() - Declare a flexible array usable in a union diff --git a/tools/lib/perf/evlist.c b/tools/lib/perf/evlist.c index c6d67fc9e57e..83c43dc13313 100644 --- a/tools/lib/perf/evlist.c +++ b/tools/lib/perf/evlist.c @@ -47,6 +47,20 @@ static void __perf_evlist__propagate_maps(struct perf_evlist *evlist, */ perf_cpu_map__put(evsel->cpus); evsel->cpus = perf_cpu_map__intersect(evlist->user_requested_cpus, evsel->own_cpus); + + /* + * Empty cpu lists would eventually get opened as "any" so remove + * genuinely empty ones before they're opened in the wrong place. + */ + if (perf_cpu_map__is_empty(evsel->cpus)) { + struct perf_evsel *next = perf_evlist__next(evlist, evsel); + + perf_evlist__remove(evlist, evsel); + /* Keep idx contiguous */ + if (next) + list_for_each_entry_from(next, &evlist->entries, node) + next->idx--; + } } else if (!evsel->own_cpus || evlist->has_user_cpus || (!evsel->requires_cpu && perf_cpu_map__has_any_cpu(evlist->user_requested_cpus))) { /* @@ -80,11 +94,11 @@ static void __perf_evlist__propagate_maps(struct perf_evlist *evlist, static void perf_evlist__propagate_maps(struct perf_evlist *evlist) { - struct perf_evsel *evsel; + struct perf_evsel *evsel, *n; evlist->needs_map_propagation = true; - perf_evlist__for_each_evsel(evlist, evsel) + list_for_each_entry_safe(evsel, n, &evlist->entries, node) __perf_evlist__propagate_maps(evlist, evsel); } diff --git a/tools/net/ynl/lib/ynl.py b/tools/net/ynl/lib/ynl.py index c22c22bf2cb7..a3f741fed0a3 100644 --- a/tools/net/ynl/lib/ynl.py +++ b/tools/net/ynl/lib/ynl.py @@ -553,10 +553,10 @@ class YnlFamily(SpecFamily): if attr["type"] == 'nest': nl_type |= Netlink.NLA_F_NESTED attr_payload = b'' - sub_attrs = SpaceAttrs(self.attr_sets[space], value, search_attrs) + sub_space = attr['nested-attributes'] + sub_attrs = SpaceAttrs(self.attr_sets[sub_space], value, search_attrs) for subname, subvalue in value.items(): - attr_payload += self._add_attr(attr['nested-attributes'], - subname, subvalue, sub_attrs) + attr_payload += self._add_attr(sub_space, subname, subvalue, sub_attrs) elif attr["type"] == 'flag': if not value: # If value is absent or false then skip attribute creation. diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 6604f5d038aa..f0d8796b984a 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -3820,9 +3820,12 @@ static int validate_branch(struct objtool_file *file, struct symbol *func, break; case INSN_CONTEXT_SWITCH: - if (func && (!next_insn || !next_insn->hint)) { - WARN_INSN(insn, "unsupported instruction in callable function"); - return 1; + if (func) { + if (!next_insn || !next_insn->hint) { + WARN_INSN(insn, "unsupported instruction in callable function"); + return 1; + } + break; } return 0; diff --git a/tools/objtool/noreturns.h b/tools/objtool/noreturns.h index e7da92489167..f98dc0e1c99c 100644 --- a/tools/objtool/noreturns.h +++ b/tools/objtool/noreturns.h @@ -20,6 +20,7 @@ NORETURN(__x64_sys_exit_group) NORETURN(arch_cpu_idle_dead) NORETURN(bch2_trans_in_restart_error) NORETURN(bch2_trans_restart_error) +NORETURN(bch2_trans_unlocked_error) NORETURN(cpu_bringup_and_idle) NORETURN(cpu_startup_entry) NORETURN(do_exit) diff --git a/tools/perf/builtin-ftrace.c b/tools/perf/builtin-ftrace.c index 272d3c70810e..a56cf8b0a7d4 100644 --- a/tools/perf/builtin-ftrace.c +++ b/tools/perf/builtin-ftrace.c @@ -1151,8 +1151,9 @@ static int cmp_profile_data(const void *a, const void *b) if (v1 > v2) return -1; - else + if (v1 < v2) return 1; + return 0; } static void print_profile_result(struct perf_ftrace *ftrace) diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c index 8982f68e7230..e763e8d99a43 100644 --- a/tools/perf/util/build-id.c +++ b/tools/perf/util/build-id.c @@ -277,7 +277,7 @@ static int write_buildid(const char *name, size_t name_len, struct build_id *bid struct perf_record_header_build_id b; size_t len; - len = sizeof(b) + name_len + 1; + len = name_len + 1; len = PERF_ALIGN(len, sizeof(u64)); memset(&b, 0, sizeof(b)); @@ -286,7 +286,7 @@ static int write_buildid(const char *name, size_t name_len, struct build_id *bid misc |= PERF_RECORD_MISC_BUILD_ID_SIZE; b.pid = pid; b.header.misc = misc; - b.header.size = len; + b.header.size = sizeof(b) + len; err = do_write(fd, &b, sizeof(b)); if (err < 0) diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 4f0ac998b0cc..27d5345d2b30 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -134,6 +134,8 @@ struct machine *machine__new_host(void) if (machine__create_kernel_maps(machine) < 0) goto out_delete; + + machine->env = &perf_env; } return machine; diff --git a/tools/sched_ext/scx_central.c b/tools/sched_ext/scx_central.c index 21deea320bd7..e938156ed0a0 100644 --- a/tools/sched_ext/scx_central.c +++ b/tools/sched_ext/scx_central.c @@ -97,7 +97,7 @@ restart: SCX_BUG_ON(!cpuset, "Failed to allocate cpuset"); CPU_ZERO(cpuset); CPU_SET(skel->rodata->central_cpu, cpuset); - SCX_BUG_ON(sched_setaffinity(0, sizeof(cpuset), cpuset), + SCX_BUG_ON(sched_setaffinity(0, sizeof(*cpuset), cpuset), "Failed to affinitize to central CPU %d (max %d)", skel->rodata->central_cpu, skel->rodata->nr_cpu_ids - 1); CPU_FREE(cpuset); diff --git a/tools/testing/selftests/arm64/abi/syscall-abi-asm.S b/tools/testing/selftests/arm64/abi/syscall-abi-asm.S index df3230fdac39..66ab2e0bae5f 100644 --- a/tools/testing/selftests/arm64/abi/syscall-abi-asm.S +++ b/tools/testing/selftests/arm64/abi/syscall-abi-asm.S @@ -81,32 +81,31 @@ do_syscall: stp x27, x28, [sp, #96] // Set SVCR if we're doing SME - cbz x1, 1f + cbz x1, load_gpr adrp x2, svcr_in ldr x2, [x2, :lo12:svcr_in] msr S3_3_C4_C2_2, x2 -1: // Load ZA and ZT0 if enabled - uses x12 as scratch due to SME LDR - tbz x2, #SVCR_ZA_SHIFT, 1f + tbz x2, #SVCR_ZA_SHIFT, load_gpr mov w12, #0 ldr x2, =za_in -2: _ldr_za 12, 2 +1: _ldr_za 12, 2 add x2, x2, x1 add x12, x12, #1 cmp x1, x12 - bne 2b + bne 1b // ZT0 mrs x2, S3_0_C0_C4_5 // ID_AA64SMFR0_EL1 ubfx x2, x2, #ID_AA64SMFR0_EL1_SMEver_SHIFT, \ #ID_AA64SMFR0_EL1_SMEver_WIDTH - cbz x2, 1f + cbz x2, load_gpr adrp x2, zt_in add x2, x2, :lo12:zt_in _ldr_zt 2 -1: +load_gpr: // Load GPRs x8-x28, and save our SP/FP for later comparison ldr x2, =gpr_in add x2, x2, #64 @@ -125,9 +124,9 @@ do_syscall: str x30, [x2], #8 // LR // Load FPRs if we're not doing neither SVE nor streaming SVE - cbnz x0, 1f + cbnz x0, check_sve_in ldr x2, =svcr_in - tbnz x2, #SVCR_SM_SHIFT, 1f + tbnz x2, #SVCR_SM_SHIFT, check_sve_in ldr x2, =fpr_in ldp q0, q1, [x2] @@ -148,8 +147,8 @@ do_syscall: ldp q30, q31, [x2, #16 * 30] b 2f -1: +check_sve_in: // Load the SVE registers if we're doing SVE/SME ldr x2, =z_in @@ -256,32 +255,31 @@ do_syscall: stp q30, q31, [x2, #16 * 30] // Save SVCR if we're doing SME - cbz x1, 1f + cbz x1, check_sve_out mrs x2, S3_3_C4_C2_2 adrp x3, svcr_out str x2, [x3, :lo12:svcr_out] -1: // Save ZA if it's enabled - uses x12 as scratch due to SME STR - tbz x2, #SVCR_ZA_SHIFT, 1f + tbz x2, #SVCR_ZA_SHIFT, check_sve_out mov w12, #0 ldr x2, =za_out -2: _str_za 12, 2 +1: _str_za 12, 2 add x2, x2, x1 add x12, x12, #1 cmp x1, x12 - bne 2b + bne 1b // ZT0 mrs x2, S3_0_C0_C4_5 // ID_AA64SMFR0_EL1 ubfx x2, x2, #ID_AA64SMFR0_EL1_SMEver_SHIFT, \ #ID_AA64SMFR0_EL1_SMEver_WIDTH - cbz x2, 1f + cbz x2, check_sve_out adrp x2, zt_out add x2, x2, :lo12:zt_out _str_zt 2 -1: +check_sve_out: // Save the SVE state if we have some cbz x0, 1f diff --git a/tools/testing/selftests/bpf/progs/dynptr_fail.c b/tools/testing/selftests/bpf/progs/dynptr_fail.c index 8f36c9de7591..dfd817d0348c 100644 --- a/tools/testing/selftests/bpf/progs/dynptr_fail.c +++ b/tools/testing/selftests/bpf/progs/dynptr_fail.c @@ -149,7 +149,7 @@ int ringbuf_release_uninit_dynptr(void *ctx) /* A dynptr can't be used after it has been invalidated */ SEC("?raw_tp") -__failure __msg("Expected an initialized dynptr as arg #3") +__failure __msg("Expected an initialized dynptr as arg #2") int use_after_invalid(void *ctx) { struct bpf_dynptr ptr; @@ -428,7 +428,7 @@ int invalid_helper2(void *ctx) /* A bpf_dynptr is invalidated if it's been written into */ SEC("?raw_tp") -__failure __msg("Expected an initialized dynptr as arg #1") +__failure __msg("Expected an initialized dynptr as arg #0") int invalid_write1(void *ctx) { struct bpf_dynptr ptr; @@ -1407,7 +1407,7 @@ int invalid_slice_rdwr_rdonly(struct __sk_buff *skb) /* bpf_dynptr_adjust can only be called on initialized dynptrs */ SEC("?raw_tp") -__failure __msg("Expected an initialized dynptr as arg #1") +__failure __msg("Expected an initialized dynptr as arg #0") int dynptr_adjust_invalid(void *ctx) { struct bpf_dynptr ptr = {}; @@ -1420,7 +1420,7 @@ int dynptr_adjust_invalid(void *ctx) /* bpf_dynptr_is_null can only be called on initialized dynptrs */ SEC("?raw_tp") -__failure __msg("Expected an initialized dynptr as arg #1") +__failure __msg("Expected an initialized dynptr as arg #0") int dynptr_is_null_invalid(void *ctx) { struct bpf_dynptr ptr = {}; @@ -1433,7 +1433,7 @@ int dynptr_is_null_invalid(void *ctx) /* bpf_dynptr_is_rdonly can only be called on initialized dynptrs */ SEC("?raw_tp") -__failure __msg("Expected an initialized dynptr as arg #1") +__failure __msg("Expected an initialized dynptr as arg #0") int dynptr_is_rdonly_invalid(void *ctx) { struct bpf_dynptr ptr = {}; @@ -1446,7 +1446,7 @@ int dynptr_is_rdonly_invalid(void *ctx) /* bpf_dynptr_size can only be called on initialized dynptrs */ SEC("?raw_tp") -__failure __msg("Expected an initialized dynptr as arg #1") +__failure __msg("Expected an initialized dynptr as arg #0") int dynptr_size_invalid(void *ctx) { struct bpf_dynptr ptr = {}; @@ -1459,7 +1459,7 @@ int dynptr_size_invalid(void *ctx) /* Only initialized dynptrs can be cloned */ SEC("?raw_tp") -__failure __msg("Expected an initialized dynptr as arg #1") +__failure __msg("Expected an initialized dynptr as arg #0") int clone_invalid1(void *ctx) { struct bpf_dynptr ptr1 = {}; @@ -1493,7 +1493,7 @@ int clone_invalid2(struct xdp_md *xdp) /* Invalidating a dynptr should invalidate its clones */ SEC("?raw_tp") -__failure __msg("Expected an initialized dynptr as arg #3") +__failure __msg("Expected an initialized dynptr as arg #2") int clone_invalidate1(void *ctx) { struct bpf_dynptr clone; @@ -1514,7 +1514,7 @@ int clone_invalidate1(void *ctx) /* Invalidating a dynptr should invalidate its parent */ SEC("?raw_tp") -__failure __msg("Expected an initialized dynptr as arg #3") +__failure __msg("Expected an initialized dynptr as arg #2") int clone_invalidate2(void *ctx) { struct bpf_dynptr ptr; @@ -1535,7 +1535,7 @@ int clone_invalidate2(void *ctx) /* Invalidating a dynptr should invalidate its siblings */ SEC("?raw_tp") -__failure __msg("Expected an initialized dynptr as arg #3") +__failure __msg("Expected an initialized dynptr as arg #2") int clone_invalidate3(void *ctx) { struct bpf_dynptr ptr; @@ -1723,7 +1723,7 @@ __noinline long global_call_bpf_dynptr(const struct bpf_dynptr *dynptr) } SEC("?raw_tp") -__failure __msg("arg#1 expected pointer to stack or const struct bpf_dynptr") +__failure __msg("arg#0 expected pointer to stack or const struct bpf_dynptr") int test_dynptr_reg_type(void *ctx) { struct task_struct *current = NULL; diff --git a/tools/testing/selftests/bpf/progs/iters_state_safety.c b/tools/testing/selftests/bpf/progs/iters_state_safety.c index d47e59aba6de..f41257eadbb2 100644 --- a/tools/testing/selftests/bpf/progs/iters_state_safety.c +++ b/tools/testing/selftests/bpf/progs/iters_state_safety.c @@ -73,7 +73,7 @@ int create_and_forget_to_destroy_fail(void *ctx) } SEC("?raw_tp") -__failure __msg("expected an initialized iter_num as arg #1") +__failure __msg("expected an initialized iter_num as arg #0") int destroy_without_creating_fail(void *ctx) { /* init with zeros to stop verifier complaining about uninit stack */ @@ -91,7 +91,7 @@ int destroy_without_creating_fail(void *ctx) } SEC("?raw_tp") -__failure __msg("expected an initialized iter_num as arg #1") +__failure __msg("expected an initialized iter_num as arg #0") int compromise_iter_w_direct_write_fail(void *ctx) { struct bpf_iter_num iter; @@ -143,7 +143,7 @@ int compromise_iter_w_direct_write_and_skip_destroy_fail(void *ctx) } SEC("?raw_tp") -__failure __msg("expected an initialized iter_num as arg #1") +__failure __msg("expected an initialized iter_num as arg #0") int compromise_iter_w_helper_write_fail(void *ctx) { struct bpf_iter_num iter; @@ -230,7 +230,7 @@ int valid_stack_reuse(void *ctx) } SEC("?raw_tp") -__failure __msg("expected uninitialized iter_num as arg #1") +__failure __msg("expected uninitialized iter_num as arg #0") int double_create_fail(void *ctx) { struct bpf_iter_num iter; @@ -258,7 +258,7 @@ int double_create_fail(void *ctx) } SEC("?raw_tp") -__failure __msg("expected an initialized iter_num as arg #1") +__failure __msg("expected an initialized iter_num as arg #0") int double_destroy_fail(void *ctx) { struct bpf_iter_num iter; @@ -284,7 +284,7 @@ int double_destroy_fail(void *ctx) } SEC("?raw_tp") -__failure __msg("expected an initialized iter_num as arg #1") +__failure __msg("expected an initialized iter_num as arg #0") int next_without_new_fail(void *ctx) { struct bpf_iter_num iter; @@ -305,7 +305,7 @@ int next_without_new_fail(void *ctx) } SEC("?raw_tp") -__failure __msg("expected an initialized iter_num as arg #1") +__failure __msg("expected an initialized iter_num as arg #0") int next_after_destroy_fail(void *ctx) { struct bpf_iter_num iter; diff --git a/tools/testing/selftests/bpf/progs/iters_testmod_seq.c b/tools/testing/selftests/bpf/progs/iters_testmod_seq.c index 4a176e6aede8..6543d5b6e0a9 100644 --- a/tools/testing/selftests/bpf/progs/iters_testmod_seq.c +++ b/tools/testing/selftests/bpf/progs/iters_testmod_seq.c @@ -79,7 +79,7 @@ int testmod_seq_truncated(const void *ctx) SEC("?raw_tp") __failure -__msg("expected an initialized iter_testmod_seq as arg #2") +__msg("expected an initialized iter_testmod_seq as arg #1") int testmod_seq_getter_before_bad(const void *ctx) { struct bpf_iter_testmod_seq it; @@ -89,7 +89,7 @@ int testmod_seq_getter_before_bad(const void *ctx) SEC("?raw_tp") __failure -__msg("expected an initialized iter_testmod_seq as arg #2") +__msg("expected an initialized iter_testmod_seq as arg #1") int testmod_seq_getter_after_bad(const void *ctx) { struct bpf_iter_testmod_seq it; diff --git a/tools/testing/selftests/bpf/progs/tc_bpf2bpf.c b/tools/testing/selftests/bpf/progs/tc_bpf2bpf.c index 8a0632c37839..79f5087dade2 100644 --- a/tools/testing/selftests/bpf/progs/tc_bpf2bpf.c +++ b/tools/testing/selftests/bpf/progs/tc_bpf2bpf.c @@ -10,6 +10,8 @@ int subprog(struct __sk_buff *skb) int ret = 1; __sink(ret); + /* let verifier know that 'subprog_tc' can change pointers to skb->data */ + bpf_skb_change_proto(skb, 0, 0); return ret; } diff --git a/tools/testing/selftests/bpf/progs/test_kfunc_dynptr_param.c b/tools/testing/selftests/bpf/progs/test_kfunc_dynptr_param.c index e68667aec6a6..cd4d752bd089 100644 --- a/tools/testing/selftests/bpf/progs/test_kfunc_dynptr_param.c +++ b/tools/testing/selftests/bpf/progs/test_kfunc_dynptr_param.c @@ -45,7 +45,7 @@ int BPF_PROG(not_valid_dynptr, int cmd, union bpf_attr *attr, unsigned int size) } SEC("?lsm.s/bpf") -__failure __msg("arg#1 expected pointer to stack or const struct bpf_dynptr") +__failure __msg("arg#0 expected pointer to stack or const struct bpf_dynptr") int BPF_PROG(not_ptr_to_stack, int cmd, union bpf_attr *attr, unsigned int size) { unsigned long val = 0; diff --git a/tools/testing/selftests/bpf/progs/test_tp_btf_nullable.c b/tools/testing/selftests/bpf/progs/test_tp_btf_nullable.c index 5aaf2b065f86..bba3e37f749b 100644 --- a/tools/testing/selftests/bpf/progs/test_tp_btf_nullable.c +++ b/tools/testing/selftests/bpf/progs/test_tp_btf_nullable.c @@ -7,11 +7,7 @@ #include "bpf_misc.h" SEC("tp_btf/bpf_testmod_test_nullable_bare") -/* This used to be a failure test, but raw_tp nullable arguments can now - * directly be dereferenced, whether they have nullable annotation or not, - * and don't need to be explicitly checked. - */ -__success +__failure __msg("R1 invalid mem access 'trusted_ptr_or_null_'") int BPF_PROG(handle_tp_btf_nullable_bare1, struct bpf_testmod_test_read_ctx *nullable_ctx) { return nullable_ctx->len; diff --git a/tools/testing/selftests/bpf/progs/verifier_bits_iter.c b/tools/testing/selftests/bpf/progs/verifier_bits_iter.c index a7a6ae6c162f..8bcddadfc4da 100644 --- a/tools/testing/selftests/bpf/progs/verifier_bits_iter.c +++ b/tools/testing/selftests/bpf/progs/verifier_bits_iter.c @@ -32,7 +32,7 @@ int BPF_PROG(no_destroy, struct bpf_iter_meta *meta, struct cgroup *cgrp) SEC("iter/cgroup") __description("uninitialized iter in ->next()") -__failure __msg("expected an initialized iter_bits as arg #1") +__failure __msg("expected an initialized iter_bits as arg #0") int BPF_PROG(next_uninit, struct bpf_iter_meta *meta, struct cgroup *cgrp) { struct bpf_iter_bits it = {}; @@ -43,7 +43,7 @@ int BPF_PROG(next_uninit, struct bpf_iter_meta *meta, struct cgroup *cgrp) SEC("iter/cgroup") __description("uninitialized iter in ->destroy()") -__failure __msg("expected an initialized iter_bits as arg #1") +__failure __msg("expected an initialized iter_bits as arg #0") int BPF_PROG(destroy_uninit, struct bpf_iter_meta *meta, struct cgroup *cgrp) { struct bpf_iter_bits it = {}; diff --git a/tools/testing/selftests/bpf/progs/verifier_btf_ctx_access.c b/tools/testing/selftests/bpf/progs/verifier_btf_ctx_access.c index a570e48b917a..bfc3bf18fed4 100644 --- a/tools/testing/selftests/bpf/progs/verifier_btf_ctx_access.c +++ b/tools/testing/selftests/bpf/progs/verifier_btf_ctx_access.c @@ -11,7 +11,7 @@ __success __retval(0) __naked void btf_ctx_access_accept(void) { asm volatile (" \ - r2 = *(u32*)(r1 + 8); /* load 2nd argument value (int pointer) */\ + r2 = *(u64 *)(r1 + 8); /* load 2nd argument value (int pointer) */\ r0 = 0; \ exit; \ " ::: __clobber_all); @@ -23,7 +23,7 @@ __success __retval(0) __naked void ctx_access_u32_pointer_accept(void) { asm volatile (" \ - r2 = *(u32*)(r1 + 0); /* load 1nd argument value (u32 pointer) */\ + r2 = *(u64 *)(r1 + 0); /* load 1nd argument value (u32 pointer) */\ r0 = 0; \ exit; \ " ::: __clobber_all); diff --git a/tools/testing/selftests/bpf/progs/verifier_d_path.c b/tools/testing/selftests/bpf/progs/verifier_d_path.c index ec79cbcfde91..87e51a215558 100644 --- a/tools/testing/selftests/bpf/progs/verifier_d_path.c +++ b/tools/testing/selftests/bpf/progs/verifier_d_path.c @@ -11,7 +11,7 @@ __success __retval(0) __naked void d_path_accept(void) { asm volatile (" \ - r1 = *(u32*)(r1 + 0); \ + r1 = *(u64 *)(r1 + 0); \ r2 = r10; \ r2 += -8; \ r6 = 0; \ @@ -31,7 +31,7 @@ __failure __msg("helper call is not allowed in probe") __naked void d_path_reject(void) { asm volatile (" \ - r1 = *(u32*)(r1 + 0); \ + r1 = *(u64 *)(r1 + 0); \ r2 = r10; \ r2 += -8; \ r6 = 0; \ diff --git a/tools/testing/selftests/bpf/sdt.h b/tools/testing/selftests/bpf/sdt.h index ca0162b4dc57..1fcfa5160231 100644 --- a/tools/testing/selftests/bpf/sdt.h +++ b/tools/testing/selftests/bpf/sdt.h @@ -102,6 +102,8 @@ # define STAP_SDT_ARG_CONSTRAINT nZr # elif defined __arm__ # define STAP_SDT_ARG_CONSTRAINT g +# elif defined __loongarch__ +# define STAP_SDT_ARG_CONSTRAINT nmr # else # define STAP_SDT_ARG_CONSTRAINT nor # endif diff --git a/tools/testing/selftests/bpf/trace_helpers.c b/tools/testing/selftests/bpf/trace_helpers.c index 2d742fdac6b9..81943c6254e6 100644 --- a/tools/testing/selftests/bpf/trace_helpers.c +++ b/tools/testing/selftests/bpf/trace_helpers.c @@ -293,6 +293,10 @@ static int procmap_query(int fd, const void *addr, __u32 query_flags, size_t *st return 0; } #else +# ifndef PROCMAP_QUERY_VMA_EXECUTABLE +# define PROCMAP_QUERY_VMA_EXECUTABLE 0x04 +# endif + static int procmap_query(int fd, const void *addr, __u32 query_flags, size_t *start, size_t *offset, int *flags) { return -EOPNOTSUPP; diff --git a/tools/testing/selftests/drivers/net/mlxsw/sharedbuffer.sh b/tools/testing/selftests/drivers/net/mlxsw/sharedbuffer.sh index 0c47faff9274..c068e6c2a580 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/sharedbuffer.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/sharedbuffer.sh @@ -22,20 +22,34 @@ SB_ITC=0 h1_create() { simple_if_init $h1 192.0.1.1/24 + tc qdisc add dev $h1 clsact + + # Add egress filter on $h1 that will guarantee that the packet sent, + # will be the only packet being passed to the device. + tc filter add dev $h1 egress pref 2 handle 102 matchall action drop } h1_destroy() { + tc filter del dev $h1 egress pref 2 handle 102 matchall action drop + tc qdisc del dev $h1 clsact simple_if_fini $h1 192.0.1.1/24 } h2_create() { simple_if_init $h2 192.0.1.2/24 + tc qdisc add dev $h2 clsact + + # Add egress filter on $h2 that will guarantee that the packet sent, + # will be the only packet being passed to the device. + tc filter add dev $h2 egress pref 1 handle 101 matchall action drop } h2_destroy() { + tc filter del dev $h2 egress pref 1 handle 101 matchall action drop + tc qdisc del dev $h2 clsact simple_if_fini $h2 192.0.1.2/24 } @@ -101,6 +115,11 @@ port_pool_test() local exp_max_occ=$(devlink_cell_size_get) local max_occ + tc filter add dev $h1 egress protocol ip pref 1 handle 101 flower \ + src_mac $h1mac dst_mac $h2mac \ + src_ip 192.0.1.1 dst_ip 192.0.1.2 \ + action pass + devlink sb occupancy clearmax $DEVLINK_DEV $MZ $h1 -c 1 -p 10 -a $h1mac -b $h2mac -A 192.0.1.1 -B 192.0.1.2 \ @@ -109,11 +128,6 @@ port_pool_test() devlink sb occupancy snapshot $DEVLINK_DEV RET=0 - max_occ=$(sb_occ_pool_check $dl_port1 $SB_POOL_ING $exp_max_occ) - check_err $? "Expected iPool($SB_POOL_ING) max occupancy to be $exp_max_occ, but got $max_occ" - log_test "physical port's($h1) ingress pool" - - RET=0 max_occ=$(sb_occ_pool_check $dl_port2 $SB_POOL_ING $exp_max_occ) check_err $? "Expected iPool($SB_POOL_ING) max occupancy to be $exp_max_occ, but got $max_occ" log_test "physical port's($h2) ingress pool" @@ -122,6 +136,11 @@ port_pool_test() max_occ=$(sb_occ_pool_check $cpu_dl_port $SB_POOL_EGR_CPU $exp_max_occ) check_err $? "Expected ePool($SB_POOL_EGR_CPU) max occupancy to be $exp_max_occ, but got $max_occ" log_test "CPU port's egress pool" + + tc filter del dev $h1 egress protocol ip pref 1 handle 101 flower \ + src_mac $h1mac dst_mac $h2mac \ + src_ip 192.0.1.1 dst_ip 192.0.1.2 \ + action pass } port_tc_ip_test() @@ -129,6 +148,11 @@ port_tc_ip_test() local exp_max_occ=$(devlink_cell_size_get) local max_occ + tc filter add dev $h1 egress protocol ip pref 1 handle 101 flower \ + src_mac $h1mac dst_mac $h2mac \ + src_ip 192.0.1.1 dst_ip 192.0.1.2 \ + action pass + devlink sb occupancy clearmax $DEVLINK_DEV $MZ $h1 -c 1 -p 10 -a $h1mac -b $h2mac -A 192.0.1.1 -B 192.0.1.2 \ @@ -139,17 +163,17 @@ port_tc_ip_test() RET=0 max_occ=$(sb_occ_itc_check $dl_port2 $SB_ITC $exp_max_occ) check_err $? "Expected ingress TC($SB_ITC) max occupancy to be $exp_max_occ, but got $max_occ" - log_test "physical port's($h1) ingress TC - IP packet" - - RET=0 - max_occ=$(sb_occ_itc_check $dl_port2 $SB_ITC $exp_max_occ) - check_err $? "Expected ingress TC($SB_ITC) max occupancy to be $exp_max_occ, but got $max_occ" log_test "physical port's($h2) ingress TC - IP packet" RET=0 max_occ=$(sb_occ_etc_check $cpu_dl_port $SB_ITC_CPU_IP $exp_max_occ) check_err $? "Expected egress TC($SB_ITC_CPU_IP) max occupancy to be $exp_max_occ, but got $max_occ" log_test "CPU port's egress TC - IP packet" + + tc filter del dev $h1 egress protocol ip pref 1 handle 101 flower \ + src_mac $h1mac dst_mac $h2mac \ + src_ip 192.0.1.1 dst_ip 192.0.1.2 \ + action pass } port_tc_arp_test() @@ -157,6 +181,9 @@ port_tc_arp_test() local exp_max_occ=$(devlink_cell_size_get) local max_occ + tc filter add dev $h1 egress protocol arp pref 1 handle 101 flower \ + src_mac $h1mac action pass + devlink sb occupancy clearmax $DEVLINK_DEV $MZ $h1 -c 1 -p 10 -a $h1mac -A 192.0.1.1 -t arp -q @@ -166,17 +193,15 @@ port_tc_arp_test() RET=0 max_occ=$(sb_occ_itc_check $dl_port2 $SB_ITC $exp_max_occ) check_err $? "Expected ingress TC($SB_ITC) max occupancy to be $exp_max_occ, but got $max_occ" - log_test "physical port's($h1) ingress TC - ARP packet" - - RET=0 - max_occ=$(sb_occ_itc_check $dl_port2 $SB_ITC $exp_max_occ) - check_err $? "Expected ingress TC($SB_ITC) max occupancy to be $exp_max_occ, but got $max_occ" log_test "physical port's($h2) ingress TC - ARP packet" RET=0 max_occ=$(sb_occ_etc_check $cpu_dl_port $SB_ITC_CPU_ARP $exp_max_occ) check_err $? "Expected egress TC($SB_ITC_IP2ME) max occupancy to be $exp_max_occ, but got $max_occ" log_test "CPU port's egress TC - ARP packet" + + tc filter del dev $h1 egress protocol arp pref 1 handle 101 flower \ + src_mac $h1mac action pass } setup_prepare() diff --git a/tools/testing/selftests/memfd/memfd_test.c b/tools/testing/selftests/memfd/memfd_test.c index 95af2d78fd31..0a0b55516028 100644 --- a/tools/testing/selftests/memfd/memfd_test.c +++ b/tools/testing/selftests/memfd/memfd_test.c @@ -9,6 +9,7 @@ #include <fcntl.h> #include <linux/memfd.h> #include <sched.h> +#include <stdbool.h> #include <stdio.h> #include <stdlib.h> #include <signal.h> @@ -1557,6 +1558,11 @@ static void test_share_fork(char *banner, char *b_suffix) close(fd); } +static bool pid_ns_supported(void) +{ + return access("/proc/self/ns/pid", F_OK) == 0; +} + int main(int argc, char **argv) { pid_t pid; @@ -1591,8 +1597,12 @@ int main(int argc, char **argv) test_seal_grow(); test_seal_resize(); - test_sysctl_simple(); - test_sysctl_nested(); + if (pid_ns_supported()) { + test_sysctl_simple(); + test_sysctl_nested(); + } else { + printf("PID namespaces are not supported; skipping sysctl tests\n"); + } test_share_dup("SHARE-DUP", ""); test_share_mmap("SHARE-MMAP", ""); diff --git a/tools/testing/selftests/net/forwarding/local_termination.sh b/tools/testing/selftests/net/forwarding/local_termination.sh index c35548767756..ecd34f364125 100755 --- a/tools/testing/selftests/net/forwarding/local_termination.sh +++ b/tools/testing/selftests/net/forwarding/local_termination.sh @@ -7,7 +7,6 @@ ALL_TESTS="standalone vlan_unaware_bridge vlan_aware_bridge test_vlan \ NUM_NETIFS=2 PING_COUNT=1 REQUIRE_MTOOLS=yes -REQUIRE_MZ=no source lib.sh diff --git a/tools/testing/selftests/net/netfilter/rpath.sh b/tools/testing/selftests/net/netfilter/rpath.sh index 4485fd7675ed..86ec4e68594d 100755 --- a/tools/testing/selftests/net/netfilter/rpath.sh +++ b/tools/testing/selftests/net/netfilter/rpath.sh @@ -61,9 +61,20 @@ ip -net "$ns2" a a 192.168.42.1/24 dev d0 ip -net "$ns1" a a fec0:42::2/64 dev v0 nodad ip -net "$ns2" a a fec0:42::1/64 dev d0 nodad +# avoid neighbor lookups and enable martian IPv6 pings +ns2_hwaddr=$(ip -net "$ns2" link show dev v0 | \ + sed -n 's, *link/ether \([^ ]*\) .*,\1,p') +ns1_hwaddr=$(ip -net "$ns1" link show dev v0 | \ + sed -n 's, *link/ether \([^ ]*\) .*,\1,p') +ip -net "$ns1" neigh add fec0:42::1 lladdr "$ns2_hwaddr" nud permanent dev v0 +ip -net "$ns1" neigh add fec0:23::1 lladdr "$ns2_hwaddr" nud permanent dev v0 +ip -net "$ns2" neigh add fec0:42::2 lladdr "$ns1_hwaddr" nud permanent dev d0 +ip -net "$ns2" neigh add fec0:23::2 lladdr "$ns1_hwaddr" nud permanent dev v0 + # firewall matches to test [ -n "$iptables" ] && { common='-t raw -A PREROUTING -s 192.168.0.0/16' + common+=' -p icmp --icmp-type echo-request' if ! ip netns exec "$ns2" "$iptables" $common -m rpfilter;then echo "Cannot add rpfilter rule" exit $ksft_skip @@ -72,6 +83,7 @@ ip -net "$ns2" a a fec0:42::1/64 dev d0 nodad } [ -n "$ip6tables" ] && { common='-t raw -A PREROUTING -s fec0::/16' + common+=' -p icmpv6 --icmpv6-type echo-request' if ! ip netns exec "$ns2" "$ip6tables" $common -m rpfilter;then echo "Cannot add rpfilter rule" exit $ksft_skip @@ -82,8 +94,10 @@ ip -net "$ns2" a a fec0:42::1/64 dev d0 nodad table inet t { chain c { type filter hook prerouting priority raw; - ip saddr 192.168.0.0/16 fib saddr . iif oif exists counter - ip6 saddr fec0::/16 fib saddr . iif oif exists counter + ip saddr 192.168.0.0/16 icmp type echo-request \ + fib saddr . iif oif exists counter + ip6 saddr fec0::/16 icmpv6 type echo-request \ + fib saddr . iif oif exists counter } } EOF diff --git a/tools/testing/selftests/net/openvswitch/openvswitch.sh b/tools/testing/selftests/net/openvswitch/openvswitch.sh index cc0bfae2bafa..960e1ab4dd04 100755 --- a/tools/testing/selftests/net/openvswitch/openvswitch.sh +++ b/tools/testing/selftests/net/openvswitch/openvswitch.sh @@ -171,8 +171,10 @@ ovs_add_netns_and_veths () { ovs_add_if "$1" "$2" "$4" -u || return 1 fi - [ $TRACING -eq 1 ] && ovs_netns_spawn_daemon "$1" "$ns" \ - tcpdump -i any -s 65535 + if [ $TRACING -eq 1 ]; then + ovs_netns_spawn_daemon "$1" "$3" tcpdump -l -i any -s 6553 + ovs_wait grep -q "listening on any" ${ovs_dir}/stderr + fi return 0 } diff --git a/tools/tracing/rtla/src/timerlat_hist.c b/tools/tracing/rtla/src/timerlat_hist.c index ae55cd791283..2cc3ffcbc983 100644 --- a/tools/tracing/rtla/src/timerlat_hist.c +++ b/tools/tracing/rtla/src/timerlat_hist.c @@ -281,6 +281,21 @@ static void timerlat_hist_header(struct osnoise_tool *tool) } /* + * format_summary_value - format a line of summary value (min, max or avg) + * of hist data + */ +static void format_summary_value(struct trace_seq *seq, + int count, + unsigned long long val, + bool avg) +{ + if (count) + trace_seq_printf(seq, "%9llu ", avg ? val / count : val); + else + trace_seq_printf(seq, "%9c ", '-'); +} + +/* * timerlat_print_summary - print the summary of the hist data to the output */ static void @@ -327,29 +342,23 @@ timerlat_print_summary(struct timerlat_hist_params *params, if (!data->hist[cpu].irq_count && !data->hist[cpu].thread_count) continue; - if (!params->no_irq) { - if (data->hist[cpu].irq_count) - trace_seq_printf(trace->seq, "%9llu ", - data->hist[cpu].min_irq); - else - trace_seq_printf(trace->seq, " - "); - } + if (!params->no_irq) + format_summary_value(trace->seq, + data->hist[cpu].irq_count, + data->hist[cpu].min_irq, + false); - if (!params->no_thread) { - if (data->hist[cpu].thread_count) - trace_seq_printf(trace->seq, "%9llu ", - data->hist[cpu].min_thread); - else - trace_seq_printf(trace->seq, " - "); - } + if (!params->no_thread) + format_summary_value(trace->seq, + data->hist[cpu].thread_count, + data->hist[cpu].min_thread, + false); - if (params->user_hist) { - if (data->hist[cpu].user_count) - trace_seq_printf(trace->seq, "%9llu ", - data->hist[cpu].min_user); - else - trace_seq_printf(trace->seq, " - "); - } + if (params->user_hist) + format_summary_value(trace->seq, + data->hist[cpu].user_count, + data->hist[cpu].min_user, + false); } trace_seq_printf(trace->seq, "\n"); @@ -363,29 +372,23 @@ timerlat_print_summary(struct timerlat_hist_params *params, if (!data->hist[cpu].irq_count && !data->hist[cpu].thread_count) continue; - if (!params->no_irq) { - if (data->hist[cpu].irq_count) - trace_seq_printf(trace->seq, "%9llu ", - data->hist[cpu].sum_irq / data->hist[cpu].irq_count); - else - trace_seq_printf(trace->seq, " - "); - } + if (!params->no_irq) + format_summary_value(trace->seq, + data->hist[cpu].irq_count, + data->hist[cpu].sum_irq, + true); - if (!params->no_thread) { - if (data->hist[cpu].thread_count) - trace_seq_printf(trace->seq, "%9llu ", - data->hist[cpu].sum_thread / data->hist[cpu].thread_count); - else - trace_seq_printf(trace->seq, " - "); - } + if (!params->no_thread) + format_summary_value(trace->seq, + data->hist[cpu].thread_count, + data->hist[cpu].sum_thread, + true); - if (params->user_hist) { - if (data->hist[cpu].user_count) - trace_seq_printf(trace->seq, "%9llu ", - data->hist[cpu].sum_user / data->hist[cpu].user_count); - else - trace_seq_printf(trace->seq, " - "); - } + if (params->user_hist) + format_summary_value(trace->seq, + data->hist[cpu].user_count, + data->hist[cpu].sum_user, + true); } trace_seq_printf(trace->seq, "\n"); @@ -399,29 +402,23 @@ timerlat_print_summary(struct timerlat_hist_params *params, if (!data->hist[cpu].irq_count && !data->hist[cpu].thread_count) continue; - if (!params->no_irq) { - if (data->hist[cpu].irq_count) - trace_seq_printf(trace->seq, "%9llu ", - data->hist[cpu].max_irq); - else - trace_seq_printf(trace->seq, " - "); - } + if (!params->no_irq) + format_summary_value(trace->seq, + data->hist[cpu].irq_count, + data->hist[cpu].max_irq, + false); - if (!params->no_thread) { - if (data->hist[cpu].thread_count) - trace_seq_printf(trace->seq, "%9llu ", - data->hist[cpu].max_thread); - else - trace_seq_printf(trace->seq, " - "); - } + if (!params->no_thread) + format_summary_value(trace->seq, + data->hist[cpu].thread_count, + data->hist[cpu].max_thread, + false); - if (params->user_hist) { - if (data->hist[cpu].user_count) - trace_seq_printf(trace->seq, "%9llu ", - data->hist[cpu].max_user); - else - trace_seq_printf(trace->seq, " - "); - } + if (params->user_hist) + format_summary_value(trace->seq, + data->hist[cpu].user_count, + data->hist[cpu].max_user, + false); } trace_seq_printf(trace->seq, "\n"); trace_seq_do_printf(trace->seq); @@ -505,16 +502,22 @@ timerlat_print_stats_all(struct timerlat_hist_params *params, trace_seq_printf(trace->seq, "min: "); if (!params->no_irq) - trace_seq_printf(trace->seq, "%9llu ", - sum.min_irq); + format_summary_value(trace->seq, + sum.irq_count, + sum.min_irq, + false); if (!params->no_thread) - trace_seq_printf(trace->seq, "%9llu ", - sum.min_thread); + format_summary_value(trace->seq, + sum.thread_count, + sum.min_thread, + false); if (params->user_hist) - trace_seq_printf(trace->seq, "%9llu ", - sum.min_user); + format_summary_value(trace->seq, + sum.user_count, + sum.min_user, + false); trace_seq_printf(trace->seq, "\n"); @@ -522,16 +525,22 @@ timerlat_print_stats_all(struct timerlat_hist_params *params, trace_seq_printf(trace->seq, "avg: "); if (!params->no_irq) - trace_seq_printf(trace->seq, "%9llu ", - sum.sum_irq / sum.irq_count); + format_summary_value(trace->seq, + sum.irq_count, + sum.sum_irq, + true); if (!params->no_thread) - trace_seq_printf(trace->seq, "%9llu ", - sum.sum_thread / sum.thread_count); + format_summary_value(trace->seq, + sum.thread_count, + sum.sum_thread, + true); if (params->user_hist) - trace_seq_printf(trace->seq, "%9llu ", - sum.sum_user / sum.user_count); + format_summary_value(trace->seq, + sum.user_count, + sum.sum_user, + true); trace_seq_printf(trace->seq, "\n"); @@ -539,16 +548,22 @@ timerlat_print_stats_all(struct timerlat_hist_params *params, trace_seq_printf(trace->seq, "max: "); if (!params->no_irq) - trace_seq_printf(trace->seq, "%9llu ", - sum.max_irq); + format_summary_value(trace->seq, + sum.irq_count, + sum.max_irq, + false); if (!params->no_thread) - trace_seq_printf(trace->seq, "%9llu ", - sum.max_thread); + format_summary_value(trace->seq, + sum.thread_count, + sum.max_thread, + false); if (params->user_hist) - trace_seq_printf(trace->seq, "%9llu ", - sum.max_user); + format_summary_value(trace->seq, + sum.user_count, + sum.max_user, + false); trace_seq_printf(trace->seq, "\n"); trace_seq_do_printf(trace->seq); |