diff --git a/MAINTAINERS b/MAINTAINERS index 07a9c274c0e29..13d1078808bb5 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -10803,6 +10803,8 @@ L: linux-kernel@vger.kernel.org S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git irq/core F: kernel/irq/ +F: include/linux/group_cpus.h +F: lib/group_cpus.c IRQCHIP DRIVERS M: Thomas Gleixner diff --git a/Makefile b/Makefile index 2840e36fd5596..bad3387b3251c 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 6 PATCHLEVEL = 1 -SUBLEVEL = 71 +SUBLEVEL = 72 EXTRAVERSION = NAME = Curry Ramen diff --git a/arch/Kconfig b/arch/Kconfig index b60d271bf76a9..14273a6203dfc 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -34,6 +34,9 @@ config ARCH_HAS_SUBPAGE_FAULTS config HOTPLUG_SMT bool +config SMT_NUM_THREADS_DYNAMIC + bool + config GENERIC_ENTRY bool diff --git a/arch/arm/mach-sunxi/mc_smp.c b/arch/arm/mach-sunxi/mc_smp.c index 26cbce1353387..b2f5f4f28705f 100644 --- a/arch/arm/mach-sunxi/mc_smp.c +++ b/arch/arm/mach-sunxi/mc_smp.c @@ -808,12 +808,12 @@ static int __init sunxi_mc_smp_init(void) break; } - is_a83t = sunxi_mc_smp_data[i].is_a83t; - of_node_put(node); if (ret) return -ENODEV; + is_a83t = sunxi_mc_smp_data[i].is_a83t; + if (!sunxi_mc_smp_cpu_table_init()) return -EINVAL; diff --git a/arch/arm64/boot/dts/qcom/sdm845-cheza.dtsi b/arch/arm64/boot/dts/qcom/sdm845-cheza.dtsi index a5c0c788969fb..43ee28db61aa8 100644 --- a/arch/arm64/boot/dts/qcom/sdm845-cheza.dtsi +++ b/arch/arm64/boot/dts/qcom/sdm845-cheza.dtsi @@ -150,15 +150,15 @@ }; &psci { - /delete-node/ cpu0; - /delete-node/ cpu1; - /delete-node/ cpu2; - /delete-node/ cpu3; - /delete-node/ cpu4; - /delete-node/ cpu5; - /delete-node/ cpu6; - /delete-node/ cpu7; - /delete-node/ cpu-cluster0; + /delete-node/ power-domain-cpu0; + /delete-node/ power-domain-cpu1; + /delete-node/ power-domain-cpu2; + /delete-node/ power-domain-cpu3; + /delete-node/ power-domain-cpu4; + /delete-node/ power-domain-cpu5; + /delete-node/ power-domain-cpu6; + /delete-node/ power-domain-cpu7; + /delete-node/ power-domain-cluster; }; &cpus { @@ -351,7 +351,9 @@ &apps_rsc { - pm8998-rpmh-regulators { + /delete-property/ power-domains; + + regulators-0 { compatible = "qcom,pm8998-rpmh-regulators"; qcom,pmic-id = "a"; @@ -633,7 +635,7 @@ }; }; - pm8005-rpmh-regulators { + regulators-1 { compatible = "qcom,pm8005-rpmh-regulators"; qcom,pmic-id = "c"; diff --git a/arch/arm64/boot/dts/qcom/sdm845-db845c.dts b/arch/arm64/boot/dts/qcom/sdm845-db845c.dts index c9efcb894a52f..8c9ccf5b4ea41 100644 --- a/arch/arm64/boot/dts/qcom/sdm845-db845c.dts +++ b/arch/arm64/boot/dts/qcom/sdm845-db845c.dts @@ -271,7 +271,7 @@ }; &apps_rsc { - pm8998-rpmh-regulators { + regulators-0 { compatible = "qcom,pm8998-rpmh-regulators"; qcom,pmic-id = "a"; vdd-s1-supply = <&vph_pwr>; @@ -396,7 +396,7 @@ }; }; - pmi8998-rpmh-regulators { + regulators-1 { compatible = "qcom,pmi8998-rpmh-regulators"; qcom,pmic-id = "b"; diff --git a/arch/arm64/boot/dts/qcom/sdm845-lg-common.dtsi b/arch/arm64/boot/dts/qcom/sdm845-lg-common.dtsi index 20f275f8694dc..e2921640880a1 100644 --- a/arch/arm64/boot/dts/qcom/sdm845-lg-common.dtsi +++ b/arch/arm64/boot/dts/qcom/sdm845-lg-common.dtsi @@ -166,7 +166,7 @@ }; &apps_rsc { - pm8998-rpmh-regulators { + regulators-0 { compatible = "qcom,pm8998-rpmh-regulators"; qcom,pmic-id = "a"; @@ -419,7 +419,7 @@ }; }; - pmi8998-rpmh-regulators { + regulators-1 { compatible = "qcom,pmi8998-rpmh-regulators"; qcom,pmic-id = "b"; @@ -433,7 +433,7 @@ }; }; - pm8005-rpmh-regulators { + regulators-2 { compatible = "qcom,pm8005-rpmh-regulators"; qcom,pmic-id = "c"; diff --git a/arch/arm64/boot/dts/qcom/sdm845-mtp.dts b/arch/arm64/boot/dts/qcom/sdm845-mtp.dts index 64958dee17d8b..b47e333aa3510 100644 --- a/arch/arm64/boot/dts/qcom/sdm845-mtp.dts +++ b/arch/arm64/boot/dts/qcom/sdm845-mtp.dts @@ -117,7 +117,7 @@ }; &apps_rsc { - pm8998-rpmh-regulators { + regulators-0 { compatible = "qcom,pm8998-rpmh-regulators"; qcom,pmic-id = "a"; @@ -382,7 +382,7 @@ }; }; - pmi8998-rpmh-regulators { + regulators-1 { compatible = "qcom,pmi8998-rpmh-regulators"; qcom,pmic-id = "b"; @@ -396,7 +396,7 @@ }; }; - pm8005-rpmh-regulators { + regulators-2 { compatible = "qcom,pm8005-rpmh-regulators"; qcom,pmic-id = "c"; diff --git a/arch/arm64/boot/dts/qcom/sdm845-oneplus-common.dtsi b/arch/arm64/boot/dts/qcom/sdm845-oneplus-common.dtsi index 392461c29e76e..0713b774a97be 100644 --- a/arch/arm64/boot/dts/qcom/sdm845-oneplus-common.dtsi +++ b/arch/arm64/boot/dts/qcom/sdm845-oneplus-common.dtsi @@ -144,7 +144,7 @@ }; &apps_rsc { - pm8998-rpmh-regulators { + regulators-0 { compatible = "qcom,pm8998-rpmh-regulators"; qcom,pmic-id = "a"; @@ -280,7 +280,7 @@ }; }; - pmi8998-rpmh-regulators { + regulators-1 { compatible = "qcom,pmi8998-rpmh-regulators"; qcom,pmic-id = "b"; @@ -294,7 +294,7 @@ }; }; - pm8005-rpmh-regulators { + regulators-2 { compatible = "qcom,pm8005-rpmh-regulators"; qcom,pmic-id = "c"; diff --git a/arch/arm64/boot/dts/qcom/sdm845-shift-axolotl.dts b/arch/arm64/boot/dts/qcom/sdm845-shift-axolotl.dts index 83261c9bb4f23..b65c35865dab9 100644 --- a/arch/arm64/boot/dts/qcom/sdm845-shift-axolotl.dts +++ b/arch/arm64/boot/dts/qcom/sdm845-shift-axolotl.dts @@ -110,7 +110,7 @@ }; &apps_rsc { - pm8998-rpmh-regulators { + regulators-0 { compatible = "qcom,pm8998-rpmh-regulators"; qcom,pmic-id = "a"; @@ -375,7 +375,7 @@ }; }; - pmi8998-rpmh-regulators { + regulators-1 { compatible = "qcom,pmi8998-rpmh-regulators"; qcom,pmic-id = "b"; @@ -389,7 +389,7 @@ }; }; - pm8005-rpmh-regulators { + regulators-2 { compatible = "qcom,pm8005-rpmh-regulators"; qcom,pmic-id = "c"; diff --git a/arch/arm64/boot/dts/qcom/sdm845-sony-xperia-tama.dtsi b/arch/arm64/boot/dts/qcom/sdm845-sony-xperia-tama.dtsi index d6918e6d19799..249a715d5aae1 100644 --- a/arch/arm64/boot/dts/qcom/sdm845-sony-xperia-tama.dtsi +++ b/arch/arm64/boot/dts/qcom/sdm845-sony-xperia-tama.dtsi @@ -78,7 +78,7 @@ }; &apps_rsc { - pm8998-rpmh-regulators { + regulators-0 { compatible = "qcom,pm8998-rpmh-regulators"; qcom,pmic-id = "a"; @@ -308,7 +308,7 @@ }; }; - pmi8998-rpmh-regulators { + regulators-1 { compatible = "qcom,pmi8998-rpmh-regulators"; qcom,pmic-id = "b"; @@ -319,7 +319,7 @@ }; }; - pm8005-rpmh-regulators { + regulators-2 { compatible = "qcom,pm8005-rpmh-regulators"; qcom,pmic-id = "c"; diff --git a/arch/arm64/boot/dts/qcom/sdm845-xiaomi-beryllium.dts b/arch/arm64/boot/dts/qcom/sdm845-xiaomi-beryllium.dts index 0f470cf1ed1c1..6d6b3dd699475 100644 --- a/arch/arm64/boot/dts/qcom/sdm845-xiaomi-beryllium.dts +++ b/arch/arm64/boot/dts/qcom/sdm845-xiaomi-beryllium.dts @@ -125,7 +125,7 @@ }; &apps_rsc { - pm8998-rpmh-regulators { + regulators-0 { compatible = "qcom,pm8998-rpmh-regulators"; qcom,pmic-id = "a"; diff --git a/arch/arm64/boot/dts/qcom/sdm845-xiaomi-polaris.dts b/arch/arm64/boot/dts/qcom/sdm845-xiaomi-polaris.dts index 093b04359ec39..ffbe45a99b74a 100644 --- a/arch/arm64/boot/dts/qcom/sdm845-xiaomi-polaris.dts +++ b/arch/arm64/boot/dts/qcom/sdm845-xiaomi-polaris.dts @@ -143,7 +143,7 @@ }; &apps_rsc { - pm8998-rpmh-regulators { + regulators-0 { compatible = "qcom,pm8998-rpmh-regulators"; qcom,pmic-id = "a"; @@ -343,7 +343,7 @@ }; }; - pmi8998-rpmh-regulators { + regulators-1 { compatible = "qcom,pmi8998-rpmh-regulators"; qcom,pmic-id = "b"; @@ -355,7 +355,7 @@ }; }; - pm8005-rpmh-regulators { + regulators-2 { compatible = "qcom,pm8005-rpmh-regulators"; qcom,pmic-id = "c"; diff --git a/arch/arm64/boot/dts/qcom/sdm850-lenovo-yoga-c630.dts b/arch/arm64/boot/dts/qcom/sdm850-lenovo-yoga-c630.dts index 74f43da51fa50..48a41ace8fc58 100644 --- a/arch/arm64/boot/dts/qcom/sdm850-lenovo-yoga-c630.dts +++ b/arch/arm64/boot/dts/qcom/sdm850-lenovo-yoga-c630.dts @@ -99,7 +99,7 @@ }; &apps_rsc { - pm8998-rpmh-regulators { + regulators-0 { compatible = "qcom,pm8998-rpmh-regulators"; qcom,pmic-id = "a"; diff --git a/arch/arm64/boot/dts/qcom/sdm850-samsung-w737.dts b/arch/arm64/boot/dts/qcom/sdm850-samsung-w737.dts index d028a7eb364a6..c169d2870bdf4 100644 --- a/arch/arm64/boot/dts/qcom/sdm850-samsung-w737.dts +++ b/arch/arm64/boot/dts/qcom/sdm850-samsung-w737.dts @@ -129,7 +129,7 @@ }; &apps_rsc { - pm8998-rpmh-regulators { + regulators-0 { compatible = "qcom,pm8998-rpmh-regulators"; qcom,pmic-id = "a"; diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c index f043a7ff220b7..28fa80fd69fa0 100644 --- a/arch/s390/kernel/perf_cpum_cf.c +++ b/arch/s390/kernel/perf_cpum_cf.c @@ -2,7 +2,7 @@ /* * Performance event support for s390x - CPU-measurement Counter Facility * - * Copyright IBM Corp. 2012, 2021 + * Copyright IBM Corp. 2012, 2022 * Author(s): Hendrik Brueckner * Thomas Richter */ @@ -434,6 +434,12 @@ static void cpumf_hw_inuse(void) mutex_unlock(&pmc_reserve_mutex); } +static int is_userspace_event(u64 ev) +{ + return cpumf_generic_events_user[PERF_COUNT_HW_CPU_CYCLES] == ev || + cpumf_generic_events_user[PERF_COUNT_HW_INSTRUCTIONS] == ev; +} + static int __hw_perf_event_init(struct perf_event *event, unsigned int type) { struct perf_event_attr *attr = &event->attr; @@ -456,19 +462,26 @@ static int __hw_perf_event_init(struct perf_event *event, unsigned int type) if (is_sampling_event(event)) /* No sampling support */ return -ENOENT; ev = attr->config; - /* Count user space (problem-state) only */ if (!attr->exclude_user && attr->exclude_kernel) { - if (ev >= ARRAY_SIZE(cpumf_generic_events_user)) - return -EOPNOTSUPP; - ev = cpumf_generic_events_user[ev]; - - /* No support for kernel space counters only */ + /* + * Count user space (problem-state) only + * Handle events 32 and 33 as 0:u and 1:u + */ + if (!is_userspace_event(ev)) { + if (ev >= ARRAY_SIZE(cpumf_generic_events_user)) + return -EOPNOTSUPP; + ev = cpumf_generic_events_user[ev]; + } } else if (!attr->exclude_kernel && attr->exclude_user) { + /* No support for kernel space counters only */ return -EOPNOTSUPP; - } else { /* Count user and kernel space */ - if (ev >= ARRAY_SIZE(cpumf_generic_events_basic)) - return -EOPNOTSUPP; - ev = cpumf_generic_events_basic[ev]; + } else { + /* Count user and kernel space, incl. events 32 + 33 */ + if (!is_userspace_event(ev)) { + if (ev >= ARRAY_SIZE(cpumf_generic_events_basic)) + return -EOPNOTSUPP; + ev = cpumf_generic_events_basic[ev]; + } } break; diff --git a/arch/s390/mm/vmem.c b/arch/s390/mm/vmem.c index 9a0ce5315f36d..3cbb461820666 100644 --- a/arch/s390/mm/vmem.c +++ b/arch/s390/mm/vmem.c @@ -11,6 +11,7 @@ #include #include #include +#include #include #include #include @@ -44,8 +45,11 @@ void *vmem_crst_alloc(unsigned long val) unsigned long *table; table = vmem_alloc_pages(CRST_ALLOC_ORDER); - if (table) - crst_table_init(table, val); + if (!table) + return NULL; + crst_table_init(table, val); + if (slab_is_available()) + arch_set_page_dat(virt_to_page(table), CRST_ALLOC_ORDER); return table; } diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 2fb5e1541efc1..949129443b1c0 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -4033,12 +4033,17 @@ static struct perf_guest_switch_msr *intel_guest_get_msrs(int *nr, void *data) u64 pebs_mask = cpuc->pebs_enabled & x86_pmu.pebs_capable; int global_ctrl, pebs_enable; + /* + * In addition to obeying exclude_guest/exclude_host, remove bits being + * used for PEBS when running a guest, because PEBS writes to virtual + * addresses (not physical addresses). + */ *nr = 0; global_ctrl = (*nr)++; arr[global_ctrl] = (struct perf_guest_switch_msr){ .msr = MSR_CORE_PERF_GLOBAL_CTRL, .host = intel_ctrl & ~cpuc->intel_ctrl_guest_mask, - .guest = intel_ctrl & (~cpuc->intel_ctrl_host_mask | ~pebs_mask), + .guest = intel_ctrl & ~cpuc->intel_ctrl_host_mask & ~pebs_mask, }; if (!x86_pmu.pebs) diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index ea155f0cf545c..6120f25b0d5cc 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -549,7 +549,8 @@ static void kprobe_emulate_call_indirect(struct kprobe *p, struct pt_regs *regs) { unsigned long offs = addrmode_regoffs[p->ainsn.indirect.reg]; - int3_emulate_call(regs, regs_get_register(regs, offs)); + int3_emulate_push(regs, regs->ip - INT3_INSN_SIZE + p->ainsn.size); + int3_emulate_jmp(regs, regs_get_register(regs, offs)); } NOKPROBE_SYMBOL(kprobe_emulate_call_indirect); diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 4686c1d9d0cfd..b69aee6245e4a 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -893,6 +893,10 @@ static void emit_nops(u8 **pprog, int len) #define INSN_SZ_DIFF (((addrs[i] - addrs[i - 1]) - (prog - temp))) +/* mov rax, qword ptr [rbp - rounded_stack_depth - 8] */ +#define RESTORE_TAIL_CALL_CNT(stack) \ + EMIT3_off32(0x48, 0x8B, 0x85, -round_up(stack, 8) - 8) + static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, u8 *rw_image, int oldproglen, struct jit_context *ctx, bool jmp_padding) { @@ -1436,9 +1440,7 @@ st: if (is_imm8(insn->off)) case BPF_JMP | BPF_CALL: func = (u8 *) __bpf_call_base + imm32; if (tail_call_reachable) { - /* mov rax, qword ptr [rbp - rounded_stack_depth - 8] */ - EMIT3_off32(0x48, 0x8B, 0x85, - -round_up(bpf_prog->aux->stack_depth, 8) - 8); + RESTORE_TAIL_CALL_CNT(bpf_prog->aux->stack_depth); if (!imm32 || emit_call(&prog, func, image + addrs[i - 1] + 7)) return -EINVAL; } else { @@ -1623,16 +1625,24 @@ emit_cond_jmp: /* Convert BPF opcode to x86 */ break; case BPF_JMP | BPF_JA: - if (insn->off == -1) - /* -1 jmp instructions will always jump - * backwards two bytes. Explicitly handling - * this case avoids wasting too many passes - * when there are long sequences of replaced - * dead code. - */ - jmp_offset = -2; - else - jmp_offset = addrs[i + insn->off] - addrs[i]; + case BPF_JMP32 | BPF_JA: + if (BPF_CLASS(insn->code) == BPF_JMP) { + if (insn->off == -1) + /* -1 jmp instructions will always jump + * backwards two bytes. Explicitly handling + * this case avoids wasting too many passes + * when there are long sequences of replaced + * dead code. + */ + jmp_offset = -2; + else + jmp_offset = addrs[i + insn->off] - addrs[i]; + } else { + if (insn->imm == -1) + jmp_offset = -2; + else + jmp_offset = addrs[i + insn->imm] - addrs[i]; + } if (!jmp_offset) { /* @@ -1750,63 +1760,37 @@ emit_jmp: return proglen; } -static void save_regs(const struct btf_func_model *m, u8 **prog, int nr_args, +static void save_regs(const struct btf_func_model *m, u8 **prog, int nr_regs, int stack_size) { - int i, j, arg_size, nr_regs; + int i; + /* Store function arguments to stack. * For a function that accepts two pointers the sequence will be: * mov QWORD PTR [rbp-0x10],rdi * mov QWORD PTR [rbp-0x8],rsi */ - for (i = 0, j = 0; i < min(nr_args, 6); i++) { - if (m->arg_flags[i] & BTF_FMODEL_STRUCT_ARG) { - nr_regs = (m->arg_size[i] + 7) / 8; - arg_size = 8; - } else { - nr_regs = 1; - arg_size = m->arg_size[i]; - } - - while (nr_regs) { - emit_stx(prog, bytes_to_bpf_size(arg_size), - BPF_REG_FP, - j == 5 ? X86_REG_R9 : BPF_REG_1 + j, - -(stack_size - j * 8)); - nr_regs--; - j++; - } - } + for (i = 0; i < min(nr_regs, 6); i++) + emit_stx(prog, BPF_DW, BPF_REG_FP, + i == 5 ? X86_REG_R9 : BPF_REG_1 + i, + -(stack_size - i * 8)); } -static void restore_regs(const struct btf_func_model *m, u8 **prog, int nr_args, +static void restore_regs(const struct btf_func_model *m, u8 **prog, int nr_regs, int stack_size) { - int i, j, arg_size, nr_regs; + int i; /* Restore function arguments from stack. * For a function that accepts two pointers the sequence will be: * EMIT4(0x48, 0x8B, 0x7D, 0xF0); mov rdi,QWORD PTR [rbp-0x10] * EMIT4(0x48, 0x8B, 0x75, 0xF8); mov rsi,QWORD PTR [rbp-0x8] */ - for (i = 0, j = 0; i < min(nr_args, 6); i++) { - if (m->arg_flags[i] & BTF_FMODEL_STRUCT_ARG) { - nr_regs = (m->arg_size[i] + 7) / 8; - arg_size = 8; - } else { - nr_regs = 1; - arg_size = m->arg_size[i]; - } - - while (nr_regs) { - emit_ldx(prog, bytes_to_bpf_size(arg_size), - j == 5 ? X86_REG_R9 : BPF_REG_1 + j, - BPF_REG_FP, - -(stack_size - j * 8)); - nr_regs--; - j++; - } - } + for (i = 0; i < min(nr_regs, 6); i++) + emit_ldx(prog, BPF_DW, + i == 5 ? X86_REG_R9 : BPF_REG_1 + i, + BPF_REG_FP, + -(stack_size - i * 8)); } static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog, @@ -2031,8 +2015,8 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i struct bpf_tramp_links *tlinks, void *func_addr) { - int ret, i, nr_args = m->nr_args, extra_nregs = 0; - int regs_off, ip_off, args_off, stack_size = nr_args * 8, run_ctx_off; + int i, ret, nr_regs = m->nr_args, stack_size = 0; + int regs_off, nregs_off, ip_off, run_ctx_off; struct bpf_tramp_links *fentry = &tlinks[BPF_TRAMP_FENTRY]; struct bpf_tramp_links *fexit = &tlinks[BPF_TRAMP_FEXIT]; struct bpf_tramp_links *fmod_ret = &tlinks[BPF_TRAMP_MODIFY_RETURN]; @@ -2041,17 +2025,14 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i u8 *prog; bool save_ret; - /* x86-64 supports up to 6 arguments. 7+ can be added in the future */ - if (nr_args > 6) - return -ENOTSUPP; - - for (i = 0; i < MAX_BPF_FUNC_ARGS; i++) { + /* extra registers for struct arguments */ + for (i = 0; i < m->nr_args; i++) if (m->arg_flags[i] & BTF_FMODEL_STRUCT_ARG) - extra_nregs += (m->arg_size[i] + 7) / 8 - 1; - } - if (nr_args + extra_nregs > 6) + nr_regs += (m->arg_size[i] + 7) / 8 - 1; + + /* x86-64 supports up to 6 arguments. 7+ can be added in the future */ + if (nr_regs > 6) return -ENOTSUPP; - stack_size += extra_nregs * 8; /* Generated trampoline stack layout: * @@ -2065,11 +2046,12 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i * [ ... ] * RBP - regs_off [ reg_arg1 ] program's ctx pointer * - * RBP - args_off [ arg regs count ] always + * RBP - nregs_off [ regs count ] always * * RBP - ip_off [ traced function ] BPF_TRAMP_F_IP_ARG flag * * RBP - run_ctx_off [ bpf_tramp_run_ctx ] + * RSP [ tail_call_cnt ] BPF_TRAMP_F_TAIL_CALL_CTX */ /* room for return value of orig_call or fentry prog */ @@ -2077,11 +2059,12 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i if (save_ret) stack_size += 8; + stack_size += nr_regs * 8; regs_off = stack_size; - /* args count */ + /* regs count */ stack_size += 8; - args_off = stack_size; + nregs_off = stack_size; if (flags & BPF_TRAMP_F_IP_ARG) stack_size += 8; /* room for IP address argument */ @@ -2106,14 +2089,16 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i EMIT1(0x55); /* push rbp */ EMIT3(0x48, 0x89, 0xE5); /* mov rbp, rsp */ EMIT4(0x48, 0x83, 0xEC, stack_size); /* sub rsp, stack_size */ + if (flags & BPF_TRAMP_F_TAIL_CALL_CTX) + EMIT1(0x50); /* push rax */ EMIT1(0x53); /* push rbx */ /* Store number of argument registers of the traced function: - * mov rax, nr_args + extra_nregs - * mov QWORD PTR [rbp - args_off], rax + * mov rax, nr_regs + * mov QWORD PTR [rbp - nregs_off], rax */ - emit_mov_imm64(&prog, BPF_REG_0, 0, (u32) nr_args + extra_nregs); - emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_0, -args_off); + emit_mov_imm64(&prog, BPF_REG_0, 0, (u32) nr_regs); + emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_0, -nregs_off); if (flags & BPF_TRAMP_F_IP_ARG) { /* Store IP address of the traced function: @@ -2124,7 +2109,7 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_0, -ip_off); } - save_regs(m, &prog, nr_args, regs_off); + save_regs(m, &prog, nr_regs, regs_off); if (flags & BPF_TRAMP_F_CALL_ORIG) { /* arg1: mov rdi, im */ @@ -2154,11 +2139,17 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i } if (flags & BPF_TRAMP_F_CALL_ORIG) { - restore_regs(m, &prog, nr_args, regs_off); + restore_regs(m, &prog, nr_regs, regs_off); + + if (flags & BPF_TRAMP_F_TAIL_CALL_CTX) + /* Before calling the original function, restore the + * tail_call_cnt from stack to rax. + */ + RESTORE_TAIL_CALL_CNT(stack_size); if (flags & BPF_TRAMP_F_ORIG_STACK) { - emit_ldx(&prog, BPF_DW, BPF_REG_0, BPF_REG_FP, 8); - EMIT2(0xff, 0xd0); /* call *rax */ + emit_ldx(&prog, BPF_DW, BPF_REG_6, BPF_REG_FP, 8); + EMIT2(0xff, 0xd3); /* call *rbx */ } else { /* call original function */ if (emit_call(&prog, orig_call, prog)) { @@ -2195,7 +2186,7 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i } if (flags & BPF_TRAMP_F_RESTORE_REGS) - restore_regs(m, &prog, nr_args, regs_off); + restore_regs(m, &prog, nr_regs, regs_off); /* This needs to be done regardless. If there were fmod_ret programs, * the return value is only updated on the stack and still needs to be @@ -2209,7 +2200,12 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i ret = -EINVAL; goto cleanup; } - } + } else if (flags & BPF_TRAMP_F_TAIL_CALL_CTX) + /* Before running the original function, restore the + * tail_call_cnt from stack to rax. + */ + RESTORE_TAIL_CALL_CNT(stack_size); + /* restore return value of orig_call or fentry prog back into RAX */ if (save_ret) emit_ldx(&prog, BPF_DW, BPF_REG_0, BPF_REG_FP, -8); diff --git a/block/bdev.c b/block/bdev.c index d699ecdb32604..b61502ec8da06 100644 --- a/block/bdev.c +++ b/block/bdev.c @@ -507,6 +507,8 @@ struct block_device *bdev_alloc(struct gendisk *disk, u8 partno) void bdev_add(struct block_device *bdev, dev_t dev) { + if (bdev_stable_writes(bdev)) + mapping_set_stable_writes(bdev->bd_inode->i_mapping); bdev->bd_dev = dev; bdev->bd_inode->i_rdev = dev; bdev->bd_inode->i_ino = dev; diff --git a/block/blk-mq.c b/block/blk-mq.c index 100fb0c3114f8..383d94615e502 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -2855,11 +2855,8 @@ static struct request *blk_mq_get_new_requests(struct request_queue *q, }; struct request *rq; - if (unlikely(bio_queue_enter(bio))) - return NULL; - if (blk_mq_attempt_bio_merge(q, bio, nsegs)) - goto queue_exit; + return NULL; rq_qos_throttle(q, bio); @@ -2875,35 +2872,23 @@ static struct request *blk_mq_get_new_requests(struct request_queue *q, rq_qos_cleanup(q, bio); if (bio->bi_opf & REQ_NOWAIT) bio_wouldblock_error(bio); -queue_exit: - blk_queue_exit(q); return NULL; } -static inline struct request *blk_mq_get_cached_request(struct request_queue *q, - struct blk_plug *plug, struct bio **bio, unsigned int nsegs) +/* return true if this @rq can be used for @bio */ +static bool blk_mq_can_use_cached_rq(struct request *rq, struct blk_plug *plug, + struct bio *bio) { - struct request *rq; - enum hctx_type type, hctx_type; + enum hctx_type type = blk_mq_get_hctx_type(bio->bi_opf); + enum hctx_type hctx_type = rq->mq_hctx->type; - if (!plug) - return NULL; - rq = rq_list_peek(&plug->cached_rq); - if (!rq || rq->q != q) - return NULL; - - if (blk_mq_attempt_bio_merge(q, *bio, nsegs)) { - *bio = NULL; - return NULL; - } + WARN_ON_ONCE(rq_list_peek(&plug->cached_rq) != rq); - type = blk_mq_get_hctx_type((*bio)->bi_opf); - hctx_type = rq->mq_hctx->type; if (type != hctx_type && !(type == HCTX_TYPE_READ && hctx_type == HCTX_TYPE_DEFAULT)) - return NULL; - if (op_is_flush(rq->cmd_flags) != op_is_flush((*bio)->bi_opf)) - return NULL; + return false; + if (op_is_flush(rq->cmd_flags) != op_is_flush(bio->bi_opf)) + return false; /* * If any qos ->throttle() end up blocking, we will have flushed the @@ -2911,11 +2896,11 @@ static inline struct request *blk_mq_get_cached_request(struct request_queue *q, * before we throttle. */ plug->cached_rq = rq_list_next(rq); - rq_qos_throttle(q, *bio); + rq_qos_throttle(rq->q, bio); - rq->cmd_flags = (*bio)->bi_opf; + rq->cmd_flags = bio->bi_opf; INIT_LIST_HEAD(&rq->queuelist); - return rq; + return true; } static void bio_set_ioprio(struct bio *bio) @@ -2944,7 +2929,7 @@ void blk_mq_submit_bio(struct bio *bio) struct request_queue *q = bdev_get_queue(bio->bi_bdev); struct blk_plug *plug = blk_mq_plug(bio); const int is_sync = op_is_sync(bio->bi_opf); - struct request *rq; + struct request *rq = NULL; unsigned int nr_segs = 1; blk_status_t ret; @@ -2955,20 +2940,36 @@ void blk_mq_submit_bio(struct bio *bio) return; } - if (!bio_integrity_prep(bio)) - return; - bio_set_ioprio(bio); - rq = blk_mq_get_cached_request(q, plug, &bio, nr_segs); - if (!rq) { - if (!bio) + if (plug) { + rq = rq_list_peek(&plug->cached_rq); + if (rq && rq->q != q) + rq = NULL; + } + if (rq) { + if (!bio_integrity_prep(bio)) return; - rq = blk_mq_get_new_requests(q, plug, bio, nr_segs); - if (unlikely(!rq)) + if (blk_mq_attempt_bio_merge(q, bio, nr_segs)) return; + if (blk_mq_can_use_cached_rq(rq, plug, bio)) + goto done; + percpu_ref_get(&q->q_usage_counter); + } else { + if (unlikely(bio_queue_enter(bio))) + return; + if (!bio_integrity_prep(bio)) + goto fail; + } + + rq = blk_mq_get_new_requests(q, plug, bio, nr_segs); + if (unlikely(!rq)) { +fail: + blk_queue_exit(q); + return; } +done: trace_block_getrq(bio); rq_qos_track(q, rq, bio); diff --git a/block/fops.c b/block/fops.c index 6197d1c41652d..01cb6260fa24d 100644 --- a/block/fops.c +++ b/block/fops.c @@ -655,24 +655,35 @@ static long blkdev_fallocate(struct file *file, int mode, loff_t start, filemap_invalidate_lock(inode->i_mapping); - /* Invalidate the page cache, including dirty pages. */ - error = truncate_bdev_range(bdev, file->f_mode, start, end); - if (error) - goto fail; - + /* + * Invalidate the page cache, including dirty pages, for valid + * de-allocate mode calls to fallocate(). + */ switch (mode) { case FALLOC_FL_ZERO_RANGE: case FALLOC_FL_ZERO_RANGE | FALLOC_FL_KEEP_SIZE: + error = truncate_bdev_range(bdev, file->f_mode, start, end); + if (error) + goto fail; + error = blkdev_issue_zeroout(bdev, start >> SECTOR_SHIFT, len >> SECTOR_SHIFT, GFP_KERNEL, BLKDEV_ZERO_NOUNMAP); break; case FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE: + error = truncate_bdev_range(bdev, file->f_mode, start, end); + if (error) + goto fail; + error = blkdev_issue_zeroout(bdev, start >> SECTOR_SHIFT, len >> SECTOR_SHIFT, GFP_KERNEL, BLKDEV_ZERO_NOFALLBACK); break; case FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE | FALLOC_FL_NO_HIDE_STALE: + error = truncate_bdev_range(bdev, file->f_mode, start, end); + if (error) + goto fail; + error = blkdev_issue_discard(bdev, start >> SECTOR_SHIFT, len >> SECTOR_SHIFT, GFP_KERNEL); break; diff --git a/drivers/base/memory.c b/drivers/base/memory.c index 9aa0da991cfb9..5d39f3e374dae 100644 --- a/drivers/base/memory.c +++ b/drivers/base/memory.c @@ -175,6 +175,9 @@ int memory_notify(unsigned long val, void *v) return blocking_notifier_call_chain(&memory_chain, val, v); } +/* + * Must acquire mem_hotplug_lock in write mode. + */ static int memory_block_online(struct memory_block *mem) { unsigned long start_pfn = section_nr_to_pfn(mem->start_section_nr); @@ -193,10 +196,11 @@ static int memory_block_online(struct memory_block *mem) * stage helps to keep accounting easier to follow - e.g vmemmaps * belong to the same zone as the memory they backed. */ + mem_hotplug_begin(); if (nr_vmemmap_pages) { ret = mhp_init_memmap_on_memory(start_pfn, nr_vmemmap_pages, zone); if (ret) - return ret; + goto out; } ret = online_pages(start_pfn + nr_vmemmap_pages, @@ -204,7 +208,7 @@ static int memory_block_online(struct memory_block *mem) if (ret) { if (nr_vmemmap_pages) mhp_deinit_memmap_on_memory(start_pfn, nr_vmemmap_pages); - return ret; + goto out; } /* @@ -216,9 +220,14 @@ static int memory_block_online(struct memory_block *mem) nr_vmemmap_pages); mem->zone = zone; +out: + mem_hotplug_done(); return ret; } +/* + * Must acquire mem_hotplug_lock in write mode. + */ static int memory_block_offline(struct memory_block *mem) { unsigned long start_pfn = section_nr_to_pfn(mem->start_section_nr); @@ -233,6 +242,7 @@ static int memory_block_offline(struct memory_block *mem) * Unaccount before offlining, such that unpopulated zone and kthreads * can properly be torn down in offline_pages(). */ + mem_hotplug_begin(); if (nr_vmemmap_pages) adjust_present_page_count(pfn_to_page(start_pfn), mem->group, -nr_vmemmap_pages); @@ -244,13 +254,15 @@ static int memory_block_offline(struct memory_block *mem) if (nr_vmemmap_pages) adjust_present_page_count(pfn_to_page(start_pfn), mem->group, nr_vmemmap_pages); - return ret; + goto out; } if (nr_vmemmap_pages) mhp_deinit_memmap_on_memory(start_pfn, nr_vmemmap_pages); mem->zone = NULL; +out: + mem_hotplug_done(); return ret; } diff --git a/drivers/firewire/ohci.c b/drivers/firewire/ohci.c index 17c9d825188bb..667ff40f39353 100644 --- a/drivers/firewire/ohci.c +++ b/drivers/firewire/ohci.c @@ -279,6 +279,51 @@ static char ohci_driver_name[] = KBUILD_MODNAME; #define QUIRK_TI_SLLZ059 0x20 #define QUIRK_IR_WAKE 0x40 +// On PCI Express Root Complex in any type of AMD Ryzen machine, VIA VT6306/6307/6308 with Asmedia +// ASM1083/1085 brings an inconvenience that the read accesses to 'Isochronous Cycle Timer' register +// (at offset 0xf0 in PCI I/O space) often causes unexpected system reboot. The mechanism is not +// clear, since the read access to the other registers is enough safe; e.g. 'Node ID' register, +// while it is probable due to detection of any type of PCIe error. +#define QUIRK_REBOOT_BY_CYCLE_TIMER_READ 0x80000000 + +#if IS_ENABLED(CONFIG_X86) + +static bool has_reboot_by_cycle_timer_read_quirk(const struct fw_ohci *ohci) +{ + return !!(ohci->quirks & QUIRK_REBOOT_BY_CYCLE_TIMER_READ); +} + +#define PCI_DEVICE_ID_ASMEDIA_ASM108X 0x1080 + +static bool detect_vt630x_with_asm1083_on_amd_ryzen_machine(const struct pci_dev *pdev) +{ + const struct pci_dev *pcie_to_pci_bridge; + + // Detect any type of AMD Ryzen machine. + if (!static_cpu_has(X86_FEATURE_ZEN)) + return false; + + // Detect VIA VT6306/6307/6308. + if (pdev->vendor != PCI_VENDOR_ID_VIA) + return false; + if (pdev->device != PCI_DEVICE_ID_VIA_VT630X) + return false; + + // Detect Asmedia ASM1083/1085. + pcie_to_pci_bridge = pdev->bus->self; + if (pcie_to_pci_bridge->vendor != PCI_VENDOR_ID_ASMEDIA) + return false; + if (pcie_to_pci_bridge->device != PCI_DEVICE_ID_ASMEDIA_ASM108X) + return false; + + return true; +} + +#else +#define has_reboot_by_cycle_timer_read_quirk(ohci) false +#define detect_vt630x_with_asm1083_on_amd_ryzen_machine(pdev) false +#endif + /* In case of multiple matches in ohci_quirks[], only the first one is used. */ static const struct { unsigned short vendor, device, revision, flags; @@ -1713,6 +1758,9 @@ static u32 get_cycle_time(struct fw_ohci *ohci) s32 diff01, diff12; int i; + if (has_reboot_by_cycle_timer_read_quirk(ohci)) + return 0; + c2 = reg_read(ohci, OHCI1394_IsochronousCycleTimer); if (ohci->quirks & QUIRK_CYCLE_TIMER) { @@ -3615,6 +3663,9 @@ static int pci_probe(struct pci_dev *dev, if (param_quirks) ohci->quirks = param_quirks; + if (detect_vt630x_with_asm1083_on_amd_ryzen_machine(dev)) + ohci->quirks |= QUIRK_REBOOT_BY_CYCLE_TIMER_READ; + /* * Because dma_alloc_coherent() allocates at least one page, * we save space by using a common buffer for the AR request/ diff --git a/drivers/firmware/arm_scmi/perf.c b/drivers/firmware/arm_scmi/perf.c index 431bda9165c3d..2775bcafe40f6 100644 --- a/drivers/firmware/arm_scmi/perf.c +++ b/drivers/firmware/arm_scmi/perf.c @@ -131,7 +131,7 @@ struct perf_dom_info { u32 opp_count; u32 sustained_freq_khz; u32 sustained_perf_level; - u32 mult_factor; + unsigned long mult_factor; char name[SCMI_MAX_STR_SIZE]; struct scmi_opp opp[MAX_OPPS]; struct scmi_fc_info *fc_info; @@ -223,8 +223,8 @@ scmi_perf_domain_attributes_get(const struct scmi_protocol_handle *ph, dom_info->mult_factor = 1000; else dom_info->mult_factor = - (dom_info->sustained_freq_khz * 1000) / - dom_info->sustained_perf_level; + (dom_info->sustained_freq_khz * 1000UL) + / dom_info->sustained_perf_level; strscpy(dom_info->name, attr->name, SCMI_SHORT_NAME_MAX_SIZE); } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 8a1b84aaaf717..a5352e5e2bd47 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -1976,15 +1976,8 @@ static int amdgpu_device_parse_gpu_info_fw(struct amdgpu_device *adev) adev->firmware.gpu_info_fw = NULL; - if (adev->mman.discovery_bin) { - /* - * FIXME: The bounding box is still needed by Navi12, so - * temporarily read it from gpu_info firmware. Should be dropped - * when DAL no longer needs it. - */ - if (adev->asic_type != CHIP_NAVI12) - return 0; - } + if (adev->mman.discovery_bin) + return 0; switch (adev->asic_type) { default: diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c index 9d224bb2b3df6..ce893fe1c69f4 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c @@ -438,7 +438,115 @@ struct _vcs_dpi_soc_bounding_box_st dcn2_0_nv14_soc = { .use_urgent_burst_bw = 0 }; -struct _vcs_dpi_soc_bounding_box_st dcn2_0_nv12_soc = { 0 }; +struct _vcs_dpi_soc_bounding_box_st dcn2_0_nv12_soc = { + .clock_limits = { + { + .state = 0, + .dcfclk_mhz = 560.0, + .fabricclk_mhz = 560.0, + .dispclk_mhz = 513.0, + .dppclk_mhz = 513.0, + .phyclk_mhz = 540.0, + .socclk_mhz = 560.0, + .dscclk_mhz = 171.0, + .dram_speed_mts = 1069.0, + }, + { + .state = 1, + .dcfclk_mhz = 694.0, + .fabricclk_mhz = 694.0, + .dispclk_mhz = 642.0, + .dppclk_mhz = 642.0, + .phyclk_mhz = 600.0, + .socclk_mhz = 694.0, + .dscclk_mhz = 214.0, + .dram_speed_mts = 1324.0, + }, + { + .state = 2, + .dcfclk_mhz = 875.0, + .fabricclk_mhz = 875.0, + .dispclk_mhz = 734.0, + .dppclk_mhz = 734.0, + .phyclk_mhz = 810.0, + .socclk_mhz = 875.0, + .dscclk_mhz = 245.0, + .dram_speed_mts = 1670.0, + }, + { + .state = 3, + .dcfclk_mhz = 1000.0, + .fabricclk_mhz = 1000.0, + .dispclk_mhz = 1100.0, + .dppclk_mhz = 1100.0, + .phyclk_mhz = 810.0, + .socclk_mhz = 1000.0, + .dscclk_mhz = 367.0, + .dram_speed_mts = 2000.0, + }, + { + .state = 4, + .dcfclk_mhz = 1200.0, + .fabricclk_mhz = 1200.0, + .dispclk_mhz = 1284.0, + .dppclk_mhz = 1284.0, + .phyclk_mhz = 810.0, + .socclk_mhz = 1200.0, + .dscclk_mhz = 428.0, + .dram_speed_mts = 2000.0, + }, + { + .state = 5, + .dcfclk_mhz = 1200.0, + .fabricclk_mhz = 1200.0, + .dispclk_mhz = 1284.0, + .dppclk_mhz = 1284.0, + .phyclk_mhz = 810.0, + .socclk_mhz = 1200.0, + .dscclk_mhz = 428.0, + .dram_speed_mts = 2000.0, + }, + }, + + .num_states = 5, + .sr_exit_time_us = 1.9, + .sr_enter_plus_exit_time_us = 4.4, + .urgent_latency_us = 3.0, + .urgent_latency_pixel_data_only_us = 4.0, + .urgent_latency_pixel_mixed_with_vm_data_us = 4.0, + .urgent_latency_vm_data_only_us = 4.0, + .urgent_out_of_order_return_per_channel_pixel_only_bytes = 4096, + .urgent_out_of_order_return_per_channel_pixel_and_vm_bytes = 4096, + .urgent_out_of_order_return_per_channel_vm_only_bytes = 4096, + .pct_ideal_dram_sdp_bw_after_urgent_pixel_only = 40.0, + .pct_ideal_dram_sdp_bw_after_urgent_pixel_and_vm = 40.0, + .pct_ideal_dram_sdp_bw_after_urgent_vm_only = 40.0, + .max_avg_sdp_bw_use_normal_percent = 40.0, + .max_avg_dram_bw_use_normal_percent = 40.0, + .writeback_latency_us = 12.0, + .ideal_dram_bw_after_urgent_percent = 40.0, + .max_request_size_bytes = 256, + .dram_channel_width_bytes = 16, + .fabric_datapath_to_dcn_data_return_bytes = 64, + .dcn_downspread_percent = 0.5, + .downspread_percent = 0.5, + .dram_page_open_time_ns = 50.0, + .dram_rw_turnaround_time_ns = 17.5, + .dram_return_buffer_per_channel_bytes = 8192, + .round_trip_ping_latency_dcfclk_cycles = 131, + .urgent_out_of_order_return_per_channel_bytes = 4096, + .channel_interleave_bytes = 256, + .num_banks = 8, + .num_chans = 16, + .vmm_page_size_bytes = 4096, + .dram_clock_change_latency_us = 45.0, + .writeback_dram_clock_change_latency_us = 23.0, + .return_bus_width_bytes = 64, + .dispclk_dppclk_vco_speed_mhz = 3850, + .xfc_bus_transport_time_us = 20, + .xfc_xbuf_latency_tolerance_us = 50, + .use_urgent_burst_bw = 0, +}; struct _vcs_dpi_ip_params_st dcn2_1_ip = { .odm_capable = 1, diff --git a/drivers/gpu/drm/bridge/ti-sn65dsi86.c b/drivers/gpu/drm/bridge/ti-sn65dsi86.c index 1b5c27ed27370..ff4d0564122a3 100644 --- a/drivers/gpu/drm/bridge/ti-sn65dsi86.c +++ b/drivers/gpu/drm/bridge/ti-sn65dsi86.c @@ -527,6 +527,7 @@ static ssize_t ti_sn_aux_transfer(struct drm_dp_aux *aux, u32 request_val = AUX_CMD_REQ(msg->request); u8 *buf = msg->buffer; unsigned int len = msg->size; + unsigned int short_len; unsigned int val; int ret; u8 addr_len[SN_AUX_LENGTH_REG + 1 - SN_AUX_ADDR_19_16_REG]; @@ -600,7 +601,8 @@ static ssize_t ti_sn_aux_transfer(struct drm_dp_aux *aux, } if (val & AUX_IRQ_STATUS_AUX_SHORT) { - ret = regmap_read(pdata->regmap, SN_AUX_LENGTH_REG, &len); + ret = regmap_read(pdata->regmap, SN_AUX_LENGTH_REG, &short_len); + len = min(len, short_len); if (ret) goto exit; } else if (val & AUX_IRQ_STATUS_NAT_I2C_FAIL) { diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c index 5970f4149090f..4699c21102261 100644 --- a/drivers/gpu/drm/i915/display/intel_dp.c +++ b/drivers/gpu/drm/i915/display/intel_dp.c @@ -3707,7 +3707,7 @@ static void intel_dp_process_phy_request(struct intel_dp *intel_dp, intel_dp->train_set, crtc_state->lane_count); drm_dp_set_phy_test_pattern(&intel_dp->aux, data, - link_status[DP_DPCD_REV]); + intel_dp->dpcd[DP_DPCD_REV]); } static u8 intel_dp_autotest_phy_pattern(struct intel_dp *intel_dp) diff --git a/drivers/gpu/drm/mgag200/mgag200_drv.h b/drivers/gpu/drm/mgag200/mgag200_drv.h index f0c2349404b46..aebd09e2d4087 100644 --- a/drivers/gpu/drm/mgag200/mgag200_drv.h +++ b/drivers/gpu/drm/mgag200/mgag200_drv.h @@ -390,6 +390,11 @@ void mgag200_primary_plane_helper_atomic_disable(struct drm_plane *plane, .destroy = drm_plane_cleanup, \ DRM_GEM_SHADOW_PLANE_FUNCS +void mgag200_crtc_set_gamma_linear(struct mga_device *mdev, const struct drm_format_info *format); +void mgag200_crtc_set_gamma(struct mga_device *mdev, + const struct drm_format_info *format, + struct drm_color_lut *lut); + enum drm_mode_status mgag200_crtc_helper_mode_valid(struct drm_crtc *crtc, const struct drm_display_mode *mode); int mgag200_crtc_helper_atomic_check(struct drm_crtc *crtc, struct drm_atomic_state *new_state); diff --git a/drivers/gpu/drm/mgag200/mgag200_g200er.c b/drivers/gpu/drm/mgag200/mgag200_g200er.c index bce267e0f7de3..8d4538b710477 100644 --- a/drivers/gpu/drm/mgag200/mgag200_g200er.c +++ b/drivers/gpu/drm/mgag200/mgag200_g200er.c @@ -202,6 +202,11 @@ static void mgag200_g200er_crtc_helper_atomic_enable(struct drm_crtc *crtc, mgag200_g200er_reset_tagfifo(mdev); + if (crtc_state->gamma_lut) + mgag200_crtc_set_gamma(mdev, format, crtc_state->gamma_lut->data); + else + mgag200_crtc_set_gamma_linear(mdev, format); + mgag200_enable_display(mdev); if (funcs->enable_vidrst) diff --git a/drivers/gpu/drm/mgag200/mgag200_g200ev.c b/drivers/gpu/drm/mgag200/mgag200_g200ev.c index ac957f42abe18..56e6f986bff31 100644 --- a/drivers/gpu/drm/mgag200/mgag200_g200ev.c +++ b/drivers/gpu/drm/mgag200/mgag200_g200ev.c @@ -203,6 +203,11 @@ static void mgag200_g200ev_crtc_helper_atomic_enable(struct drm_crtc *crtc, mgag200_g200ev_set_hiprilvl(mdev); + if (crtc_state->gamma_lut) + mgag200_crtc_set_gamma(mdev, format, crtc_state->gamma_lut->data); + else + mgag200_crtc_set_gamma_linear(mdev, format); + mgag200_enable_display(mdev); if (funcs->enable_vidrst) diff --git a/drivers/gpu/drm/mgag200/mgag200_g200se.c b/drivers/gpu/drm/mgag200/mgag200_g200se.c index bd6e573c9a1a3..ff2b3c6622e7a 100644 --- a/drivers/gpu/drm/mgag200/mgag200_g200se.c +++ b/drivers/gpu/drm/mgag200/mgag200_g200se.c @@ -334,6 +334,11 @@ static void mgag200_g200se_crtc_helper_atomic_enable(struct drm_crtc *crtc, mgag200_g200se_set_hiprilvl(mdev, adjusted_mode, format); + if (crtc_state->gamma_lut) + mgag200_crtc_set_gamma(mdev, format, crtc_state->gamma_lut->data); + else + mgag200_crtc_set_gamma_linear(mdev, format); + mgag200_enable_display(mdev); if (funcs->enable_vidrst) diff --git a/drivers/gpu/drm/mgag200/mgag200_mode.c b/drivers/gpu/drm/mgag200/mgag200_mode.c index ae90b260312a5..554adf05e0734 100644 --- a/drivers/gpu/drm/mgag200/mgag200_mode.c +++ b/drivers/gpu/drm/mgag200/mgag200_mode.c @@ -28,8 +28,8 @@ * This file contains setup code for the CRTC. */ -static void mgag200_crtc_set_gamma_linear(struct mga_device *mdev, - const struct drm_format_info *format) +void mgag200_crtc_set_gamma_linear(struct mga_device *mdev, + const struct drm_format_info *format) { int i; @@ -65,9 +65,9 @@ static void mgag200_crtc_set_gamma_linear(struct mga_device *mdev, } } -static void mgag200_crtc_set_gamma(struct mga_device *mdev, - const struct drm_format_info *format, - struct drm_color_lut *lut) +void mgag200_crtc_set_gamma(struct mga_device *mdev, + const struct drm_format_info *format, + struct drm_color_lut *lut) { int i; diff --git a/drivers/i2c/i2c-core.h b/drivers/i2c/i2c-core.h index 05b8b8dfa9bdd..36587f38dff3d 100644 --- a/drivers/i2c/i2c-core.h +++ b/drivers/i2c/i2c-core.h @@ -3,6 +3,7 @@ * i2c-core.h - interfaces internal to the I2C framework */ +#include #include struct i2c_devinfo { @@ -29,7 +30,8 @@ int i2c_dev_irq_from_resources(const struct resource *resources, */ static inline bool i2c_in_atomic_xfer_mode(void) { - return system_state > SYSTEM_RUNNING && !preemptible(); + return system_state > SYSTEM_RUNNING && + (IS_ENABLED(CONFIG_PREEMPT_COUNT) ? !preemptible() : irqs_disabled()); } static inline int __i2c_lock_bus_helper(struct i2c_adapter *adap) diff --git a/drivers/interconnect/qcom/sm8250.c b/drivers/interconnect/qcom/sm8250.c index 9c2dd40d9a559..5cdb058fa0959 100644 --- a/drivers/interconnect/qcom/sm8250.c +++ b/drivers/interconnect/qcom/sm8250.c @@ -551,7 +551,6 @@ static struct platform_driver qnoc_driver = { .driver = { .name = "qnoc-sm8250", .of_match_table = qnoc_of_match, - .sync_state = icc_sync_state, }, }; module_platform_driver(qnoc_driver); diff --git a/drivers/media/platform/qcom/camss/camss-csid-gen2.c b/drivers/media/platform/qcom/camss/camss-csid-gen2.c index 904208f6f9546..0147cc062e1ae 100644 --- a/drivers/media/platform/qcom/camss/camss-csid-gen2.c +++ b/drivers/media/platform/qcom/camss/camss-csid-gen2.c @@ -334,13 +334,14 @@ static const struct csid_format csid_formats[] = { }, }; -static void csid_configure_stream(struct csid_device *csid, u8 enable) +static void __csid_configure_stream(struct csid_device *csid, u8 enable, u8 vc) { struct csid_testgen_config *tg = &csid->testgen; u32 val; u32 phy_sel = 0; u8 lane_cnt = csid->phy.lane_cnt; - struct v4l2_mbus_framefmt *input_format = &csid->fmt[MSM_CSID_PAD_SRC]; + /* Source pads matching RDI channels on hardware. Pad 1 -> RDI0, Pad 2 -> RDI1, etc. */ + struct v4l2_mbus_framefmt *input_format = &csid->fmt[MSM_CSID_PAD_FIRST_SRC + vc]; const struct csid_format *format = csid_get_fmt_entry(csid->formats, csid->nformats, input_format->code); @@ -351,8 +352,19 @@ static void csid_configure_stream(struct csid_device *csid, u8 enable) phy_sel = csid->phy.csiphy_id; if (enable) { - u8 vc = 0; /* Virtual Channel 0 */ - u8 dt_id = vc * 4; + /* + * DT_ID is a two bit bitfield that is concatenated with + * the four least significant bits of the five bit VC + * bitfield to generate an internal CID value. + * + * CSID_RDI_CFG0(vc) + * DT_ID : 28:27 + * VC : 26:22 + * DT : 21:16 + * + * CID : VC 3:0 << 2 | DT_ID 1:0 + */ + u8 dt_id = vc & 0x03; if (tg->enabled) { /* configure one DT, infinite frames */ @@ -392,42 +404,42 @@ static void csid_configure_stream(struct csid_device *csid, u8 enable) val |= format->data_type << RDI_CFG0_DATA_TYPE; val |= vc << RDI_CFG0_VIRTUAL_CHANNEL; val |= dt_id << RDI_CFG0_DT_ID; - writel_relaxed(val, csid->base + CSID_RDI_CFG0(0)); + writel_relaxed(val, csid->base + CSID_RDI_CFG0(vc)); /* CSID_TIMESTAMP_STB_POST_IRQ */ val = 2 << RDI_CFG1_TIMESTAMP_STB_SEL; - writel_relaxed(val, csid->base + CSID_RDI_CFG1(0)); + writel_relaxed(val, csid->base + CSID_RDI_CFG1(vc)); val = 1; - writel_relaxed(val, csid->base + CSID_RDI_FRM_DROP_PERIOD(0)); + writel_relaxed(val, csid->base + CSID_RDI_FRM_DROP_PERIOD(vc)); val = 0; - writel_relaxed(val, csid->base + CSID_RDI_FRM_DROP_PATTERN(0)); + writel_relaxed(val, csid->base + CSID_RDI_FRM_DROP_PATTERN(vc)); val = 1; - writel_relaxed(val, csid->base + CSID_RDI_IRQ_SUBSAMPLE_PERIOD(0)); + writel_relaxed(val, csid->base + CSID_RDI_IRQ_SUBSAMPLE_PERIOD(vc)); val = 0; - writel_relaxed(val, csid->base + CSID_RDI_IRQ_SUBSAMPLE_PATTERN(0)); + writel_relaxed(val, csid->base + CSID_RDI_IRQ_SUBSAMPLE_PATTERN(vc)); val = 1; - writel_relaxed(val, csid->base + CSID_RDI_RPP_PIX_DROP_PERIOD(0)); + writel_relaxed(val, csid->base + CSID_RDI_RPP_PIX_DROP_PERIOD(vc)); val = 0; - writel_relaxed(val, csid->base + CSID_RDI_RPP_PIX_DROP_PATTERN(0)); + writel_relaxed(val, csid->base + CSID_RDI_RPP_PIX_DROP_PATTERN(vc)); val = 1; - writel_relaxed(val, csid->base + CSID_RDI_RPP_LINE_DROP_PERIOD(0)); + writel_relaxed(val, csid->base + CSID_RDI_RPP_LINE_DROP_PERIOD(vc)); val = 0; - writel_relaxed(val, csid->base + CSID_RDI_RPP_LINE_DROP_PATTERN(0)); + writel_relaxed(val, csid->base + CSID_RDI_RPP_LINE_DROP_PATTERN(vc)); val = 0; - writel_relaxed(val, csid->base + CSID_RDI_CTRL(0)); + writel_relaxed(val, csid->base + CSID_RDI_CTRL(vc)); - val = readl_relaxed(csid->base + CSID_RDI_CFG0(0)); + val = readl_relaxed(csid->base + CSID_RDI_CFG0(vc)); val |= 1 << RDI_CFG0_ENABLE; - writel_relaxed(val, csid->base + CSID_RDI_CFG0(0)); + writel_relaxed(val, csid->base + CSID_RDI_CFG0(vc)); } if (tg->enabled) { @@ -446,6 +458,8 @@ static void csid_configure_stream(struct csid_device *csid, u8 enable) writel_relaxed(val, csid->base + CSID_CSI2_RX_CFG0); val = 1 << CSI2_RX_CFG1_PACKET_ECC_CORRECTION_EN; + if (vc > 3) + val |= 1 << CSI2_RX_CFG1_VC_MODE; val |= 1 << CSI2_RX_CFG1_MISR_EN; writel_relaxed(val, csid->base + CSID_CSI2_RX_CFG1); @@ -453,7 +467,16 @@ static void csid_configure_stream(struct csid_device *csid, u8 enable) val = HALT_CMD_RESUME_AT_FRAME_BOUNDARY << RDI_CTRL_HALT_CMD; else val = HALT_CMD_HALT_AT_FRAME_BOUNDARY << RDI_CTRL_HALT_CMD; - writel_relaxed(val, csid->base + CSID_RDI_CTRL(0)); + writel_relaxed(val, csid->base + CSID_RDI_CTRL(vc)); +} + +static void csid_configure_stream(struct csid_device *csid, u8 enable) +{ + u8 i; + /* Loop through all enabled VCs and configure stream for each */ + for (i = 0; i < MSM_CSID_MAX_SRC_STREAMS; i++) + if (csid->phy.en_vc & BIT(i)) + __csid_configure_stream(csid, enable, i); } static int csid_configure_testgen_pattern(struct csid_device *csid, s32 val) @@ -499,6 +522,7 @@ static irqreturn_t csid_isr(int irq, void *dev) struct csid_device *csid = dev; u32 val; u8 reset_done; + int i; val = readl_relaxed(csid->base + CSID_TOP_IRQ_STATUS); writel_relaxed(val, csid->base + CSID_TOP_IRQ_CLEAR); @@ -507,8 +531,12 @@ static irqreturn_t csid_isr(int irq, void *dev) val = readl_relaxed(csid->base + CSID_CSI2_RX_IRQ_STATUS); writel_relaxed(val, csid->base + CSID_CSI2_RX_IRQ_CLEAR); - val = readl_relaxed(csid->base + CSID_CSI2_RDIN_IRQ_STATUS(0)); - writel_relaxed(val, csid->base + CSID_CSI2_RDIN_IRQ_CLEAR(0)); + /* Read and clear IRQ status for each enabled RDI channel */ + for (i = 0; i < MSM_CSID_MAX_SRC_STREAMS; i++) + if (csid->phy.en_vc & BIT(i)) { + val = readl_relaxed(csid->base + CSID_CSI2_RDIN_IRQ_STATUS(i)); + writel_relaxed(val, csid->base + CSID_CSI2_RDIN_IRQ_CLEAR(i)); + } val = 1 << IRQ_CMD_CLEAR; writel_relaxed(val, csid->base + CSID_IRQ_CMD); diff --git a/drivers/media/platform/qcom/camss/camss-csid.c b/drivers/media/platform/qcom/camss/camss-csid.c index 88f188e0f7501..6360314f04a63 100644 --- a/drivers/media/platform/qcom/camss/camss-csid.c +++ b/drivers/media/platform/qcom/camss/camss-csid.c @@ -196,6 +196,8 @@ static int csid_set_power(struct v4l2_subdev *sd, int on) return ret; } + csid->phy.need_vc_update = true; + enable_irq(csid->irq); ret = csid->ops->reset(csid); @@ -249,7 +251,10 @@ static int csid_set_stream(struct v4l2_subdev *sd, int enable) return -ENOLINK; } - csid->ops->configure_stream(csid, enable); + if (csid->phy.need_vc_update) { + csid->ops->configure_stream(csid, enable); + csid->phy.need_vc_update = false; + } return 0; } @@ -460,6 +465,7 @@ static int csid_set_format(struct v4l2_subdev *sd, { struct csid_device *csid = v4l2_get_subdevdata(sd); struct v4l2_mbus_framefmt *format; + int i; format = __csid_get_format(csid, sd_state, fmt->pad, fmt->which); if (format == NULL) @@ -468,14 +474,14 @@ static int csid_set_format(struct v4l2_subdev *sd, csid_try_format(csid, sd_state, fmt->pad, &fmt->format, fmt->which); *format = fmt->format; - /* Propagate the format from sink to source */ + /* Propagate the format from sink to source pads */ if (fmt->pad == MSM_CSID_PAD_SINK) { - format = __csid_get_format(csid, sd_state, MSM_CSID_PAD_SRC, - fmt->which); + for (i = MSM_CSID_PAD_FIRST_SRC; i < MSM_CSID_PADS_NUM; ++i) { + format = __csid_get_format(csid, sd_state, i, fmt->which); - *format = fmt->format; - csid_try_format(csid, sd_state, MSM_CSID_PAD_SRC, format, - fmt->which); + *format = fmt->format; + csid_try_format(csid, sd_state, i, format, fmt->which); + } } return 0; @@ -738,7 +744,6 @@ static int csid_link_setup(struct media_entity *entity, struct csid_device *csid; struct csiphy_device *csiphy; struct csiphy_lanes_cfg *lane_cfg; - struct v4l2_subdev_format format = { 0 }; sd = media_entity_to_v4l2_subdev(entity); csid = v4l2_get_subdevdata(sd); @@ -761,11 +766,22 @@ static int csid_link_setup(struct media_entity *entity, lane_cfg = &csiphy->cfg.csi2->lane_cfg; csid->phy.lane_cnt = lane_cfg->num_data; csid->phy.lane_assign = csid_get_lane_assign(lane_cfg); + } + /* Decide which virtual channels to enable based on which source pads are enabled */ + if (local->flags & MEDIA_PAD_FL_SOURCE) { + struct v4l2_subdev *sd = media_entity_to_v4l2_subdev(entity); + struct csid_device *csid = v4l2_get_subdevdata(sd); + struct device *dev = csid->camss->dev; + + if (flags & MEDIA_LNK_FL_ENABLED) + csid->phy.en_vc |= BIT(local->index - 1); + else + csid->phy.en_vc &= ~BIT(local->index - 1); - /* Reset format on source pad to sink pad format */ - format.pad = MSM_CSID_PAD_SRC; - format.which = V4L2_SUBDEV_FORMAT_ACTIVE; - csid_set_format(&csid->subdev, NULL, &format); + csid->phy.need_vc_update = true; + + dev_dbg(dev, "%s: Enabled CSID virtual channels mask 0x%x\n", + __func__, csid->phy.en_vc); } return 0; @@ -816,6 +832,7 @@ int msm_csid_register_entity(struct csid_device *csid, struct v4l2_subdev *sd = &csid->subdev; struct media_pad *pads = csid->pads; struct device *dev = csid->camss->dev; + int i; int ret; v4l2_subdev_init(sd, &csid_v4l2_ops); @@ -852,7 +869,8 @@ int msm_csid_register_entity(struct csid_device *csid, } pads[MSM_CSID_PAD_SINK].flags = MEDIA_PAD_FL_SINK; - pads[MSM_CSID_PAD_SRC].flags = MEDIA_PAD_FL_SOURCE; + for (i = MSM_CSID_PAD_FIRST_SRC; i < MSM_CSID_PADS_NUM; ++i) + pads[i].flags = MEDIA_PAD_FL_SOURCE; sd->entity.function = MEDIA_ENT_F_PROC_VIDEO_PIXEL_FORMATTER; sd->entity.ops = &csid_media_ops; diff --git a/drivers/media/platform/qcom/camss/camss-csid.h b/drivers/media/platform/qcom/camss/camss-csid.h index f06040e44c515..d4b48432a0973 100644 --- a/drivers/media/platform/qcom/camss/camss-csid.h +++ b/drivers/media/platform/qcom/camss/camss-csid.h @@ -19,8 +19,13 @@ #include #define MSM_CSID_PAD_SINK 0 -#define MSM_CSID_PAD_SRC 1 -#define MSM_CSID_PADS_NUM 2 +#define MSM_CSID_PAD_FIRST_SRC 1 +#define MSM_CSID_PADS_NUM 5 + +#define MSM_CSID_PAD_SRC (MSM_CSID_PAD_FIRST_SRC) + +/* CSID hardware can demultiplex up to 4 outputs */ +#define MSM_CSID_MAX_SRC_STREAMS 4 #define DATA_TYPE_EMBEDDED_DATA_8BIT 0x12 #define DATA_TYPE_YUV420_8BIT 0x18 @@ -81,6 +86,8 @@ struct csid_phy_config { u8 csiphy_id; u8 lane_cnt; u32 lane_assign; + u32 en_vc; + u8 need_vc_update; }; struct csid_device; diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c index 770490234c872..e9ce53d200bc1 100644 --- a/drivers/mmc/core/block.c +++ b/drivers/mmc/core/block.c @@ -866,9 +866,10 @@ static const struct block_device_operations mmc_bdops = { static int mmc_blk_part_switch_pre(struct mmc_card *card, unsigned int part_type) { + const unsigned int mask = EXT_CSD_PART_CONFIG_ACC_RPMB; int ret = 0; - if (part_type == EXT_CSD_PART_CONFIG_ACC_RPMB) { + if ((part_type & mask) == mask) { if (card->ext_csd.cmdq_en) { ret = mmc_cmdq_disable(card); if (ret) @@ -883,9 +884,10 @@ static int mmc_blk_part_switch_pre(struct mmc_card *card, static int mmc_blk_part_switch_post(struct mmc_card *card, unsigned int part_type) { + const unsigned int mask = EXT_CSD_PART_CONFIG_ACC_RPMB; int ret = 0; - if (part_type == EXT_CSD_PART_CONFIG_ACC_RPMB) { + if ((part_type & mask) == mask) { mmc_retune_unpause(card->host); if (card->reenable_cmdq && !card->ext_csd.cmdq_en) ret = mmc_cmdq_enable(card); @@ -3180,4 +3182,3 @@ module_exit(mmc_blk_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Multimedia Card (MMC) block device driver"); - diff --git a/drivers/mmc/core/host.c b/drivers/mmc/core/host.c index b89dca1f15e9c..25c152ef5d60e 100644 --- a/drivers/mmc/core/host.c +++ b/drivers/mmc/core/host.c @@ -670,6 +670,7 @@ EXPORT_SYMBOL(mmc_remove_host); */ void mmc_free_host(struct mmc_host *host) { + cancel_delayed_work_sync(&host->detect); mmc_pwrseq_free(host); put_device(&host->class_dev); } diff --git a/drivers/mmc/host/meson-mx-sdhc-mmc.c b/drivers/mmc/host/meson-mx-sdhc-mmc.c index da85c2f2acb83..c0e3b1634a88a 100644 --- a/drivers/mmc/host/meson-mx-sdhc-mmc.c +++ b/drivers/mmc/host/meson-mx-sdhc-mmc.c @@ -269,7 +269,7 @@ static int meson_mx_sdhc_enable_clks(struct mmc_host *mmc) static int meson_mx_sdhc_set_clk(struct mmc_host *mmc, struct mmc_ios *ios) { struct meson_mx_sdhc_host *host = mmc_priv(mmc); - u32 rx_clk_phase; + u32 val, rx_clk_phase; int ret; meson_mx_sdhc_disable_clks(mmc); @@ -290,27 +290,11 @@ static int meson_mx_sdhc_set_clk(struct mmc_host *mmc, struct mmc_ios *ios) mmc->actual_clock = clk_get_rate(host->sd_clk); /* - * according to Amlogic the following latching points are - * selected with empirical values, there is no (known) formula - * to calculate these. + * Phase 90 should work in most cases. For data transmission, + * meson_mx_sdhc_execute_tuning() will find a accurate value */ - if (mmc->actual_clock > 100000000) { - rx_clk_phase = 1; - } else if (mmc->actual_clock > 45000000) { - if (ios->signal_voltage == MMC_SIGNAL_VOLTAGE_330) - rx_clk_phase = 15; - else - rx_clk_phase = 11; - } else if (mmc->actual_clock >= 25000000) { - rx_clk_phase = 15; - } else if (mmc->actual_clock > 5000000) { - rx_clk_phase = 23; - } else if (mmc->actual_clock > 1000000) { - rx_clk_phase = 55; - } else { - rx_clk_phase = 1061; - } - + regmap_read(host->regmap, MESON_SDHC_CLKC, &val); + rx_clk_phase = FIELD_GET(MESON_SDHC_CLKC_CLK_DIV, val) / 4; regmap_update_bits(host->regmap, MESON_SDHC_CLK2, MESON_SDHC_CLK2_RX_CLK_PHASE, FIELD_PREP(MESON_SDHC_CLK2_RX_CLK_PHASE, diff --git a/drivers/mmc/host/sdhci-sprd.c b/drivers/mmc/host/sdhci-sprd.c index 2101b6e794c0e..66c1782823d89 100644 --- a/drivers/mmc/host/sdhci-sprd.c +++ b/drivers/mmc/host/sdhci-sprd.c @@ -228,15 +228,19 @@ static inline void _sdhci_sprd_set_clock(struct sdhci_host *host, div = ((div & 0x300) >> 2) | ((div & 0xFF) << 8); sdhci_enable_clk(host, div); + val = sdhci_readl(host, SDHCI_SPRD_REG_32_BUSY_POSI); + mask = SDHCI_SPRD_BIT_OUTR_CLK_AUTO_EN | SDHCI_SPRD_BIT_INNR_CLK_AUTO_EN; /* Enable CLK_AUTO when the clock is greater than 400K. */ if (clk > 400000) { - val = sdhci_readl(host, SDHCI_SPRD_REG_32_BUSY_POSI); - mask = SDHCI_SPRD_BIT_OUTR_CLK_AUTO_EN | - SDHCI_SPRD_BIT_INNR_CLK_AUTO_EN; if (mask != (val & mask)) { val |= mask; sdhci_writel(host, val, SDHCI_SPRD_REG_32_BUSY_POSI); } + } else { + if (val & mask) { + val &= ~mask; + sdhci_writel(host, val, SDHCI_SPRD_REG_32_BUSY_POSI); + } } } diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 623cdeb29ed90..df4d88d35701b 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -12081,6 +12081,8 @@ static void bnxt_sp_task(struct work_struct *work) bnxt_cfg_ntp_filters(bp); if (test_and_clear_bit(BNXT_HWRM_EXEC_FWD_REQ_SP_EVENT, &bp->sp_event)) bnxt_hwrm_exec_fwd_req(bp); + if (test_and_clear_bit(BNXT_HWRM_PF_UNLOAD_SP_EVENT, &bp->sp_event)) + netdev_info(bp->dev, "Receive PF driver unload event!\n"); if (test_and_clear_bit(BNXT_PERIODIC_STATS_SP_EVENT, &bp->sp_event)) { bnxt_hwrm_port_qstats(bp, 0); bnxt_hwrm_port_qstats_ext(bp, 0); @@ -13059,8 +13061,6 @@ static void bnxt_cfg_ntp_filters(struct bnxt *bp) } } } - if (test_and_clear_bit(BNXT_HWRM_PF_UNLOAD_SP_EVENT, &bp->sp_event)) - netdev_info(bp->dev, "Receive PF driver unload event!\n"); } #else diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index 1ae082eb9e905..c2a9913082153 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -2131,8 +2131,10 @@ static netdev_tx_t bcmgenet_xmit(struct sk_buff *skb, struct net_device *dev) /* Note: if we ever change from DMA_TX_APPEND_CRC below we * will need to restore software padding of "runt" packets */ + len_stat |= DMA_TX_APPEND_CRC; + if (!i) { - len_stat |= DMA_TX_APPEND_CRC | DMA_SOP; + len_stat |= DMA_SOP; if (skb->ip_summed == CHECKSUM_PARTIAL) len_stat |= DMA_TX_DO_CSUM; } diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c index b58162ce81d87..de62eee58a00e 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c @@ -509,8 +509,6 @@ static struct sk_buff *dpaa2_eth_copybreak(struct dpaa2_eth_channel *ch, memcpy(skb->data, fd_vaddr + fd_offset, fd_length); - dpaa2_eth_recycle_buf(priv, ch, dpaa2_fd_get_addr(fd)); - return skb; } @@ -528,6 +526,7 @@ static void dpaa2_eth_rx(struct dpaa2_eth_priv *priv, struct dpaa2_eth_drv_stats *percpu_extras; struct device *dev = priv->net_dev->dev.parent; struct dpaa2_fas *fas; + bool recycle_rx_buf = false; void *buf_data; u32 status = 0; u32 xdp_act; @@ -560,6 +559,8 @@ static void dpaa2_eth_rx(struct dpaa2_eth_priv *priv, dma_unmap_page(dev, addr, priv->rx_buf_size, DMA_BIDIRECTIONAL); skb = dpaa2_eth_build_linear_skb(ch, fd, vaddr); + } else { + recycle_rx_buf = true; } } else if (fd_format == dpaa2_fd_sg) { WARN_ON(priv->xdp_prog); @@ -607,6 +608,8 @@ static void dpaa2_eth_rx(struct dpaa2_eth_priv *priv, list_add_tail(&skb->list, ch->rx_list); + if (recycle_rx_buf) + dpaa2_eth_recycle_buf(priv, ch, dpaa2_fd_get_addr(fd)); return; err_build_skb: diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c index eea7d7a07c007..59888826469b9 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c @@ -227,17 +227,8 @@ static void dpaa2_eth_get_ethtool_stats(struct net_device *net_dev, struct ethtool_stats *stats, u64 *data) { - int i = 0; - int j, k, err; - int num_cnt; - union dpni_statistics dpni_stats; - u32 fcnt, bcnt; - u32 fcnt_rx_total = 0, fcnt_tx_total = 0; - u32 bcnt_rx_total = 0, bcnt_tx_total = 0; - u32 buf_cnt; struct dpaa2_eth_priv *priv = netdev_priv(net_dev); - struct dpaa2_eth_drv_stats *extras; - struct dpaa2_eth_ch_stats *ch_stats; + union dpni_statistics dpni_stats; int dpni_stats_page_size[DPNI_STATISTICS_CNT] = { sizeof(dpni_stats.page_0), sizeof(dpni_stats.page_1), @@ -247,6 +238,13 @@ static void dpaa2_eth_get_ethtool_stats(struct net_device *net_dev, sizeof(dpni_stats.page_5), sizeof(dpni_stats.page_6), }; + u32 fcnt_rx_total = 0, fcnt_tx_total = 0; + u32 bcnt_rx_total = 0, bcnt_tx_total = 0; + struct dpaa2_eth_ch_stats *ch_stats; + struct dpaa2_eth_drv_stats *extras; + int j, k, err, num_cnt, i = 0; + u32 fcnt, bcnt; + u32 buf_cnt; memset(data, 0, sizeof(u64) * (DPAA2_ETH_NUM_STATS + DPAA2_ETH_NUM_EXTRA_STATS)); diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index b4157ff370a31..63d43ef86f9b9 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -104,12 +104,18 @@ static struct workqueue_struct *i40e_wq; static void netdev_hw_addr_refcnt(struct i40e_mac_filter *f, struct net_device *netdev, int delta) { + struct netdev_hw_addr_list *ha_list; struct netdev_hw_addr *ha; if (!f || !netdev) return; - netdev_for_each_mc_addr(ha, netdev) { + if (is_unicast_ether_addr(f->macaddr) || is_link_local_ether_addr(f->macaddr)) + ha_list = &netdev->uc; + else + ha_list = &netdev->mc; + + netdev_hw_addr_list_for_each(ha, ha_list) { if (ether_addr_equal(ha->addr, f->macaddr)) { ha->refcount += delta; if (ha->refcount <= 0) @@ -16444,6 +16450,9 @@ static void i40e_pci_error_reset_done(struct pci_dev *pdev) return; i40e_reset_and_rebuild(pf, false, false); +#ifdef CONFIG_PCI_IOV + i40e_restore_all_vfs_msi_state(pdev); +#endif /* CONFIG_PCI_IOV */ } /** diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index cb925baf72ce0..c7d761426d6ce 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -152,6 +152,32 @@ void i40e_vc_notify_reset(struct i40e_pf *pf) (u8 *)&pfe, sizeof(struct virtchnl_pf_event)); } +#ifdef CONFIG_PCI_IOV +void i40e_restore_all_vfs_msi_state(struct pci_dev *pdev) +{ + u16 vf_id; + u16 pos; + + /* Continue only if this is a PF */ + if (!pdev->is_physfn) + return; + + if (!pci_num_vf(pdev)) + return; + + pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_SRIOV); + if (pos) { + struct pci_dev *vf_dev = NULL; + + pci_read_config_word(pdev, pos + PCI_SRIOV_VF_DID, &vf_id); + while ((vf_dev = pci_get_device(pdev->vendor, vf_id, vf_dev))) { + if (vf_dev->is_virtfn && vf_dev->physfn == pdev) + pci_restore_msi_state(vf_dev); + } + } +} +#endif /* CONFIG_PCI_IOV */ + /** * i40e_vc_notify_vf_reset * @vf: pointer to the VF structure @@ -3451,16 +3477,16 @@ static int i40e_validate_cloud_filter(struct i40e_vf *vf, bool found = false; int bkt; - if (!tc_filter->action) { + if (tc_filter->action != VIRTCHNL_ACTION_TC_REDIRECT) { dev_info(&pf->pdev->dev, - "VF %d: Currently ADq doesn't support Drop Action\n", - vf->vf_id); + "VF %d: ADQ doesn't support this action (%d)\n", + vf->vf_id, tc_filter->action); goto err; } /* action_meta is TC number here to which the filter is applied */ if (!tc_filter->action_meta || - tc_filter->action_meta > I40E_MAX_VF_VSI) { + tc_filter->action_meta > vf->num_tc) { dev_info(&pf->pdev->dev, "VF %d: Invalid TC number %u\n", vf->vf_id, tc_filter->action_meta); goto err; diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h index 358bbdb587951..bd497cc5303a1 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h @@ -135,6 +135,9 @@ int i40e_ndo_set_vf_spoofchk(struct net_device *netdev, int vf_id, bool enable); void i40e_vc_notify_link_state(struct i40e_pf *pf); void i40e_vc_notify_reset(struct i40e_pf *pf); +#ifdef CONFIG_PCI_IOV +void i40e_restore_all_vfs_msi_state(struct pci_dev *pdev); +#endif /* CONFIG_PCI_IOV */ int i40e_get_vf_stats(struct net_device *netdev, int vf_id, struct ifla_vf_stats *vf_stats); diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index f0f39364819ac..ab46cfca4028d 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -2138,7 +2138,7 @@ static int ice_configure_phy(struct ice_vsi *vsi) /* Ensure we have media as we cannot configure a medialess port */ if (!(phy->link_info.link_info & ICE_AQ_MEDIA_AVAILABLE)) - return -EPERM; + return -ENOMEDIUM; ice_print_topo_conflict(vsi); @@ -9065,8 +9065,14 @@ int ice_stop(struct net_device *netdev) int link_err = ice_force_phys_link_state(vsi, false); if (link_err) { - netdev_err(vsi->netdev, "Failed to set physical link down, VSI %d error %d\n", - vsi->vsi_num, link_err); + if (link_err == -ENOMEDIUM) + netdev_info(vsi->netdev, "Skipping link reconfig - no media attached, VSI %d\n", + vsi->vsi_num); + else + netdev_err(vsi->netdev, "Failed to set physical link down, VSI %d error %d\n", + vsi->vsi_num, link_err); + + ice_vsi_close(vsi); return -EIO; } } diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h index 43c05b41627f7..2a894ca49d93b 100644 --- a/drivers/net/ethernet/intel/igc/igc.h +++ b/drivers/net/ethernet/intel/igc/igc.h @@ -538,6 +538,7 @@ struct igc_nfc_filter { u16 etype; __be16 vlan_etype; u16 vlan_tci; + u16 vlan_tci_mask; u8 src_addr[ETH_ALEN]; u8 dst_addr[ETH_ALEN]; u8 user_data[8]; diff --git a/drivers/net/ethernet/intel/igc/igc_ethtool.c b/drivers/net/ethernet/intel/igc/igc_ethtool.c index 81897f7a90a91..2bee9cace5983 100644 --- a/drivers/net/ethernet/intel/igc/igc_ethtool.c +++ b/drivers/net/ethernet/intel/igc/igc_ethtool.c @@ -957,6 +957,7 @@ static int igc_ethtool_set_coalesce(struct net_device *netdev, } #define ETHER_TYPE_FULL_MASK ((__force __be16)~0) +#define VLAN_TCI_FULL_MASK ((__force __be16)~0) static int igc_ethtool_get_nfc_rule(struct igc_adapter *adapter, struct ethtool_rxnfc *cmd) { @@ -979,10 +980,16 @@ static int igc_ethtool_get_nfc_rule(struct igc_adapter *adapter, fsp->m_u.ether_spec.h_proto = ETHER_TYPE_FULL_MASK; } + if (rule->filter.match_flags & IGC_FILTER_FLAG_VLAN_ETYPE) { + fsp->flow_type |= FLOW_EXT; + fsp->h_ext.vlan_etype = rule->filter.vlan_etype; + fsp->m_ext.vlan_etype = ETHER_TYPE_FULL_MASK; + } + if (rule->filter.match_flags & IGC_FILTER_FLAG_VLAN_TCI) { fsp->flow_type |= FLOW_EXT; fsp->h_ext.vlan_tci = htons(rule->filter.vlan_tci); - fsp->m_ext.vlan_tci = htons(VLAN_PRIO_MASK); + fsp->m_ext.vlan_tci = htons(rule->filter.vlan_tci_mask); } if (rule->filter.match_flags & IGC_FILTER_FLAG_DST_MAC_ADDR) { @@ -1217,6 +1224,7 @@ static void igc_ethtool_init_nfc_rule(struct igc_nfc_rule *rule, if ((fsp->flow_type & FLOW_EXT) && fsp->m_ext.vlan_tci) { rule->filter.vlan_tci = ntohs(fsp->h_ext.vlan_tci); + rule->filter.vlan_tci_mask = ntohs(fsp->m_ext.vlan_tci); rule->filter.match_flags |= IGC_FILTER_FLAG_VLAN_TCI; } @@ -1254,11 +1262,19 @@ static void igc_ethtool_init_nfc_rule(struct igc_nfc_rule *rule, memcpy(rule->filter.user_mask, fsp->m_ext.data, sizeof(fsp->m_ext.data)); } - /* When multiple filter options or user data or vlan etype is set, use a - * flex filter. + /* The i225/i226 has various different filters. Flex filters provide a + * way to match up to the first 128 bytes of a packet. Use them for: + * a) For specific user data + * b) For VLAN EtherType + * c) For full TCI match + * d) Or in case multiple filter criteria are set + * + * Otherwise, use the simple MAC, VLAN PRIO or EtherType filters. */ if ((rule->filter.match_flags & IGC_FILTER_FLAG_USER_DATA) || (rule->filter.match_flags & IGC_FILTER_FLAG_VLAN_ETYPE) || + ((rule->filter.match_flags & IGC_FILTER_FLAG_VLAN_TCI) && + rule->filter.vlan_tci_mask == ntohs(VLAN_TCI_FULL_MASK)) || (rule->filter.match_flags & (rule->filter.match_flags - 1))) rule->flex = true; else @@ -1328,6 +1344,26 @@ static int igc_ethtool_add_nfc_rule(struct igc_adapter *adapter, return -EINVAL; } + /* There are two ways to match the VLAN TCI: + * 1. Match on PCP field and use vlan prio filter for it + * 2. Match on complete TCI field and use flex filter for it + */ + if ((fsp->flow_type & FLOW_EXT) && + fsp->m_ext.vlan_tci && + fsp->m_ext.vlan_tci != htons(VLAN_PRIO_MASK) && + fsp->m_ext.vlan_tci != VLAN_TCI_FULL_MASK) { + netdev_dbg(netdev, "VLAN mask not supported\n"); + return -EOPNOTSUPP; + } + + /* VLAN EtherType can only be matched by full mask. */ + if ((fsp->flow_type & FLOW_EXT) && + fsp->m_ext.vlan_etype && + fsp->m_ext.vlan_etype != ETHER_TYPE_FULL_MASK) { + netdev_dbg(netdev, "VLAN EtherType mask not supported\n"); + return -EOPNOTSUPP; + } + if (fsp->location >= IGC_MAX_RXNFC_RULES) { netdev_dbg(netdev, "Invalid location\n"); return -EINVAL; diff --git a/drivers/net/ethernet/intel/igc/igc_tsn.c b/drivers/net/ethernet/intel/igc/igc_tsn.c index 725db36e399d2..31ea0781b65ec 100644 --- a/drivers/net/ethernet/intel/igc/igc_tsn.c +++ b/drivers/net/ethernet/intel/igc/igc_tsn.c @@ -178,7 +178,7 @@ static int igc_tsn_enable_offload(struct igc_adapter *adapter) wr32(IGC_TQAVCC(i), tqavcc); wr32(IGC_TQAVHC(i), - 0x80000000 + ring->hicredit * 0x7735); + 0x80000000 + ring->hicredit * 0x7736); } else { /* Disable any CBS for the queue */ txqctl &= ~(IGC_TXQCTL_QAV_SEL_MASK); diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c index 65c0373d34d12..90be87dc105d3 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c @@ -78,7 +78,7 @@ static bool is_dev_rpm(void *cgxd) bool is_lmac_valid(struct cgx *cgx, int lmac_id) { - if (!cgx || lmac_id < 0 || lmac_id >= MAX_LMAC_PER_CGX) + if (!cgx || lmac_id < 0 || lmac_id >= cgx->max_lmac_per_mac) return false; return test_bit(lmac_id, &cgx->lmac_bmap); } @@ -90,7 +90,7 @@ static int get_sequence_id_of_lmac(struct cgx *cgx, int lmac_id) { int tmp, id = 0; - for_each_set_bit(tmp, &cgx->lmac_bmap, MAX_LMAC_PER_CGX) { + for_each_set_bit(tmp, &cgx->lmac_bmap, cgx->max_lmac_per_mac) { if (tmp == lmac_id) break; id++; @@ -121,7 +121,7 @@ u64 cgx_read(struct cgx *cgx, u64 lmac, u64 offset) struct lmac *lmac_pdata(u8 lmac_id, struct cgx *cgx) { - if (!cgx || lmac_id >= MAX_LMAC_PER_CGX) + if (!cgx || lmac_id >= cgx->max_lmac_per_mac) return NULL; return cgx->lmac_idmap[lmac_id]; @@ -1410,7 +1410,7 @@ int cgx_get_fwdata_base(u64 *base) if (!cgx) return -ENXIO; - first_lmac = find_first_bit(&cgx->lmac_bmap, MAX_LMAC_PER_CGX); + first_lmac = find_first_bit(&cgx->lmac_bmap, cgx->max_lmac_per_mac); req = FIELD_SET(CMDREG_ID, CGX_CMD_GET_FWD_BASE, req); err = cgx_fwi_cmd_generic(req, &resp, cgx, first_lmac); if (!err) @@ -1499,7 +1499,7 @@ static int cgx_fwi_link_change(struct cgx *cgx, int lmac_id, bool enable) static inline int cgx_fwi_read_version(u64 *resp, struct cgx *cgx) { - int first_lmac = find_first_bit(&cgx->lmac_bmap, MAX_LMAC_PER_CGX); + int first_lmac = find_first_bit(&cgx->lmac_bmap, cgx->max_lmac_per_mac); u64 req = 0; req = FIELD_SET(CMDREG_ID, CGX_CMD_GET_FW_VER, req); @@ -1537,7 +1537,7 @@ static void cgx_lmac_linkup_work(struct work_struct *work) int i, err; /* Do Link up for all the enabled lmacs */ - for_each_set_bit(i, &cgx->lmac_bmap, MAX_LMAC_PER_CGX) { + for_each_set_bit(i, &cgx->lmac_bmap, cgx->max_lmac_per_mac) { err = cgx_fwi_link_change(cgx, i, true); if (err) dev_info(dev, "cgx port %d:%d Link up command failed\n", @@ -1557,14 +1557,6 @@ int cgx_lmac_linkup_start(void *cgxd) return 0; } -static void cgx_lmac_get_fifolen(struct cgx *cgx) -{ - u64 cfg; - - cfg = cgx_read(cgx, 0, CGX_CONST); - cgx->mac_ops->fifo_len = FIELD_GET(CGX_CONST_RXFIFO_SIZE, cfg); -} - static int cgx_configure_interrupt(struct cgx *cgx, struct lmac *lmac, int cnt, bool req_free) { @@ -1619,17 +1611,14 @@ static int cgx_lmac_init(struct cgx *cgx) u64 lmac_list; int i, err; - cgx_lmac_get_fifolen(cgx); - - cgx->lmac_count = cgx->mac_ops->get_nr_lmacs(cgx); /* lmac_list specifies which lmacs are enabled * when bit n is set to 1, LMAC[n] is enabled */ if (cgx->mac_ops->non_contiguous_serdes_lane) lmac_list = cgx_read(cgx, 0, CGXX_CMRX_RX_LMACS) & 0xFULL; - if (cgx->lmac_count > MAX_LMAC_PER_CGX) - cgx->lmac_count = MAX_LMAC_PER_CGX; + if (cgx->lmac_count > cgx->max_lmac_per_mac) + cgx->lmac_count = cgx->max_lmac_per_mac; for (i = 0; i < cgx->lmac_count; i++) { lmac = kzalloc(sizeof(struct lmac), GFP_KERNEL); @@ -1707,7 +1696,7 @@ static int cgx_lmac_exit(struct cgx *cgx) } /* Free all lmac related resources */ - for_each_set_bit(i, &cgx->lmac_bmap, MAX_LMAC_PER_CGX) { + for_each_set_bit(i, &cgx->lmac_bmap, cgx->max_lmac_per_mac) { lmac = cgx->lmac_idmap[i]; if (!lmac) continue; @@ -1723,6 +1712,12 @@ static int cgx_lmac_exit(struct cgx *cgx) static void cgx_populate_features(struct cgx *cgx) { + u64 cfg; + + cfg = cgx_read(cgx, 0, CGX_CONST); + cgx->mac_ops->fifo_len = FIELD_GET(CGX_CONST_RXFIFO_SIZE, cfg); + cgx->max_lmac_per_mac = FIELD_GET(CGX_CONST_MAX_LMACS, cfg); + if (is_dev_rpm(cgx)) cgx->hw_features = (RVU_LMAC_FEAT_DMACF | RVU_MAC_RPM | RVU_LMAC_FEAT_FC | RVU_LMAC_FEAT_PTP); diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx.h b/drivers/net/ethernet/marvell/octeontx2/af/cgx.h index 04338db38671b..09ddb00f63cc7 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/cgx.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx.h @@ -18,11 +18,8 @@ /* PCI BAR nos */ #define PCI_CFG_REG_BAR_NUM 0 -#define CGX_ID_MASK 0x7 -#define MAX_LMAC_PER_CGX 4 +#define CGX_ID_MASK 0xF #define MAX_DMAC_ENTRIES_PER_CGX 32 -#define CGX_FIFO_LEN 65536 /* 64K for both Rx & Tx */ -#define CGX_OFFSET(x) ((x) * MAX_LMAC_PER_CGX) /* Registers */ #define CGXX_CMRX_CFG 0x00 @@ -56,6 +53,7 @@ #define CGXX_SCRATCH1_REG 0x1058 #define CGX_CONST 0x2000 #define CGX_CONST_RXFIFO_SIZE GENMASK_ULL(23, 0) +#define CGX_CONST_MAX_LMACS GENMASK_ULL(31, 24) #define CGXX_SPUX_CONTROL1 0x10000 #define CGXX_SPUX_LNX_FEC_CORR_BLOCKS 0x10700 #define CGXX_SPUX_LNX_FEC_UNCORR_BLOCKS 0x10800 diff --git a/drivers/net/ethernet/marvell/octeontx2/af/lmac_common.h b/drivers/net/ethernet/marvell/octeontx2/af/lmac_common.h index 52b6016789fa4..697cfec74aa1e 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/lmac_common.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/lmac_common.h @@ -128,7 +128,10 @@ struct cgx { struct pci_dev *pdev; u8 cgx_id; u8 lmac_count; - struct lmac *lmac_idmap[MAX_LMAC_PER_CGX]; + /* number of LMACs per MAC could be 4 or 8 */ + u8 max_lmac_per_mac; +#define MAX_LMAC_COUNT 8 + struct lmac *lmac_idmap[MAX_LMAC_COUNT]; struct work_struct cgx_cmd_work; struct workqueue_struct *cgx_cmd_workq; struct list_head cgx_list; diff --git a/drivers/net/ethernet/marvell/octeontx2/af/npc.h b/drivers/net/ethernet/marvell/octeontx2/af/npc.h index d027c23b8ef8e..aaff91bc7415a 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/npc.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/npc.h @@ -514,7 +514,7 @@ struct npc_lt_def { u8 ltype_mask; u8 ltype_match; u8 lid; -}; +} __packed; struct npc_lt_def_ipsec { u8 ltype_mask; @@ -522,7 +522,7 @@ struct npc_lt_def_ipsec { u8 lid; u8 spi_offset; u8 spi_nz; -}; +} __packed; struct npc_lt_def_apad { u8 ltype_mask; diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rpm.c b/drivers/net/ethernet/marvell/octeontx2/af/rpm.c index a70e1153fa04b..6b4792a942d84 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rpm.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rpm.c @@ -283,6 +283,11 @@ void rpm_lmac_pause_frm_config(void *rpmd, int lmac_id, bool enable) cfg = FIELD_SET(RPM_PFC_CLASS_MASK, 0, cfg); rpm_write(rpm, lmac_id, RPMX_CMRX_PRT_CBFC_CTL, cfg); + /* Disable forward pause to driver */ + cfg = rpm_read(rpm, lmac_id, RPMX_MTI_MAC100X_COMMAND_CONFIG); + cfg &= ~RPMX_MTI_MAC100X_COMMAND_CONFIG_PAUSE_FWD; + rpm_write(rpm, lmac_id, RPMX_MTI_MAC100X_COMMAND_CONFIG, cfg); + /* Enable channel mask for all LMACS */ rpm_write(rpm, 0, RPMX_CMR_CHAN_MSK_OR, ~0ULL); } @@ -451,12 +456,10 @@ int rpm_lmac_pfc_config(void *rpmd, int lmac_id, u8 tx_pause, u8 rx_pause, u16 p if (rx_pause) { cfg &= ~(RPMX_MTI_MAC100X_COMMAND_CONFIG_RX_P_DISABLE | - RPMX_MTI_MAC100X_COMMAND_CONFIG_PAUSE_IGNORE | - RPMX_MTI_MAC100X_COMMAND_CONFIG_PAUSE_FWD); + RPMX_MTI_MAC100X_COMMAND_CONFIG_PAUSE_IGNORE); } else { cfg |= (RPMX_MTI_MAC100X_COMMAND_CONFIG_RX_P_DISABLE | - RPMX_MTI_MAC100X_COMMAND_CONFIG_PAUSE_IGNORE | - RPMX_MTI_MAC100X_COMMAND_CONFIG_PAUSE_FWD); + RPMX_MTI_MAC100X_COMMAND_CONFIG_PAUSE_IGNORE); } if (tx_pause) { diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h index 95a7bc396e8ea..0b76dfa979d4e 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h @@ -480,7 +480,7 @@ struct rvu { u8 cgx_mapped_pfs; u8 cgx_cnt_max; /* CGX port count max */ u8 *pf2cgxlmac_map; /* pf to cgx_lmac map */ - u16 *cgxlmac2pf_map; /* bitmap of mapped pfs for + u64 *cgxlmac2pf_map; /* bitmap of mapped pfs for * every cgx lmac port */ unsigned long pf_notify_bmap; /* Flags for PF notification */ @@ -850,6 +850,7 @@ u32 rvu_cgx_get_fifolen(struct rvu *rvu); void *rvu_first_cgx_pdata(struct rvu *rvu); int cgxlmac_to_pf(struct rvu *rvu, int cgx_id, int lmac_id); int rvu_cgx_config_tx(void *cgxd, int lmac_id, bool enable); +int rvu_cgx_tx_enable(struct rvu *rvu, u16 pcifunc, bool enable); int rvu_cgx_prio_flow_ctrl_cfg(struct rvu *rvu, u16 pcifunc, u8 tx_pause, u8 rx_pause, u16 pfc_en); int rvu_cgx_cfg_pause_frm(struct rvu *rvu, u16 pcifunc, u8 tx_pause, u8 rx_pause); diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c index c60b9580ca969..bcb4385d0621c 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c @@ -55,8 +55,9 @@ bool is_mac_feature_supported(struct rvu *rvu, int pf, int feature) return (cgx_features_get(cgxd) & feature); } +#define CGX_OFFSET(x) ((x) * rvu->hw->lmac_per_cgx) /* Returns bitmap of mapped PFs */ -static u16 cgxlmac_to_pfmap(struct rvu *rvu, u8 cgx_id, u8 lmac_id) +static u64 cgxlmac_to_pfmap(struct rvu *rvu, u8 cgx_id, u8 lmac_id) { return rvu->cgxlmac2pf_map[CGX_OFFSET(cgx_id) + lmac_id]; } @@ -71,7 +72,8 @@ int cgxlmac_to_pf(struct rvu *rvu, int cgx_id, int lmac_id) if (!pfmap) return -ENODEV; else - return find_first_bit(&pfmap, 16); + return find_first_bit(&pfmap, + rvu->cgx_cnt_max * rvu->hw->lmac_per_cgx); } static u8 cgxlmac_id_to_bmap(u8 cgx_id, u8 lmac_id) @@ -129,14 +131,14 @@ static int rvu_map_cgx_lmac_pf(struct rvu *rvu) if (!cgx_cnt_max) return 0; - if (cgx_cnt_max > 0xF || MAX_LMAC_PER_CGX > 0xF) + if (cgx_cnt_max > 0xF || rvu->hw->lmac_per_cgx > 0xF) return -EINVAL; /* Alloc map table * An additional entry is required since PF id starts from 1 and * hence entry at offset 0 is invalid. */ - size = (cgx_cnt_max * MAX_LMAC_PER_CGX + 1) * sizeof(u8); + size = (cgx_cnt_max * rvu->hw->lmac_per_cgx + 1) * sizeof(u8); rvu->pf2cgxlmac_map = devm_kmalloc(rvu->dev, size, GFP_KERNEL); if (!rvu->pf2cgxlmac_map) return -ENOMEM; @@ -145,9 +147,10 @@ static int rvu_map_cgx_lmac_pf(struct rvu *rvu) memset(rvu->pf2cgxlmac_map, 0xFF, size); /* Reverse map table */ - rvu->cgxlmac2pf_map = devm_kzalloc(rvu->dev, - cgx_cnt_max * MAX_LMAC_PER_CGX * sizeof(u16), - GFP_KERNEL); + rvu->cgxlmac2pf_map = + devm_kzalloc(rvu->dev, + cgx_cnt_max * rvu->hw->lmac_per_cgx * sizeof(u64), + GFP_KERNEL); if (!rvu->cgxlmac2pf_map) return -ENOMEM; @@ -156,7 +159,7 @@ static int rvu_map_cgx_lmac_pf(struct rvu *rvu) if (!rvu_cgx_pdata(cgx, rvu)) continue; lmac_bmap = cgx_get_lmac_bmap(rvu_cgx_pdata(cgx, rvu)); - for_each_set_bit(iter, &lmac_bmap, MAX_LMAC_PER_CGX) { + for_each_set_bit(iter, &lmac_bmap, rvu->hw->lmac_per_cgx) { lmac = cgx_get_lmacid(rvu_cgx_pdata(cgx, rvu), iter); rvu->pf2cgxlmac_map[pf] = cgxlmac_id_to_bmap(cgx, lmac); @@ -235,7 +238,8 @@ static void cgx_notify_pfs(struct cgx_link_event *event, struct rvu *rvu) pfmap = cgxlmac_to_pfmap(rvu, event->cgx_id, event->lmac_id); do { - pfid = find_first_bit(&pfmap, 16); + pfid = find_first_bit(&pfmap, + rvu->cgx_cnt_max * rvu->hw->lmac_per_cgx); clear_bit(pfid, &pfmap); /* check if notification is enabled */ @@ -310,7 +314,7 @@ static int cgx_lmac_event_handler_init(struct rvu *rvu) if (!cgxd) continue; lmac_bmap = cgx_get_lmac_bmap(cgxd); - for_each_set_bit(lmac, &lmac_bmap, MAX_LMAC_PER_CGX) { + for_each_set_bit(lmac, &lmac_bmap, rvu->hw->lmac_per_cgx) { err = cgx_lmac_evh_register(&cb, cgxd, lmac); if (err) dev_err(rvu->dev, @@ -396,7 +400,7 @@ int rvu_cgx_exit(struct rvu *rvu) if (!cgxd) continue; lmac_bmap = cgx_get_lmac_bmap(cgxd); - for_each_set_bit(lmac, &lmac_bmap, MAX_LMAC_PER_CGX) + for_each_set_bit(lmac, &lmac_bmap, rvu->hw->lmac_per_cgx) cgx_lmac_evh_unregister(cgxd, lmac); } @@ -456,6 +460,23 @@ int rvu_cgx_config_rxtx(struct rvu *rvu, u16 pcifunc, bool start) return mac_ops->mac_rx_tx_enable(cgxd, lmac_id, start); } +int rvu_cgx_tx_enable(struct rvu *rvu, u16 pcifunc, bool enable) +{ + int pf = rvu_get_pf(pcifunc); + struct mac_ops *mac_ops; + u8 cgx_id, lmac_id; + void *cgxd; + + if (!is_cgx_config_permitted(rvu, pcifunc)) + return LMAC_AF_ERR_PERM_DENIED; + + rvu_get_cgx_lmac_id(rvu->pf2cgxlmac_map[pf], &cgx_id, &lmac_id); + cgxd = rvu_cgx_pdata(cgx_id, rvu); + mac_ops = get_mac_ops(cgxd); + + return mac_ops->mac_tx_enable(cgxd, lmac_id, enable); +} + int rvu_cgx_config_tx(void *cgxd, int lmac_id, bool enable) { struct mac_ops *mac_ops; diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c index 5c9dc3f9262f5..cc5d342e026c7 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c @@ -2618,7 +2618,7 @@ static void rvu_dbg_cgx_init(struct rvu *rvu) rvu->rvu_dbg.cgx = debugfs_create_dir(dname, rvu->rvu_dbg.cgx_root); - for_each_set_bit(lmac_id, &lmac_bmap, MAX_LMAC_PER_CGX) { + for_each_set_bit(lmac_id, &lmac_bmap, rvu->hw->lmac_per_cgx) { /* lmac debugfs dir */ sprintf(dname, "lmac%d", lmac_id); rvu->rvu_dbg.lmac = diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c index 959f36efdc4a6..bb99302eab67a 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c @@ -3923,90 +3923,18 @@ static void nix_find_link_frs(struct rvu *rvu, req->minlen = minlen; } -static int -nix_config_link_credits(struct rvu *rvu, int blkaddr, int link, - u16 pcifunc, u64 tx_credits) -{ - struct rvu_hwinfo *hw = rvu->hw; - int pf = rvu_get_pf(pcifunc); - u8 cgx_id = 0, lmac_id = 0; - unsigned long poll_tmo; - bool restore_tx_en = 0; - struct nix_hw *nix_hw; - u64 cfg, sw_xoff = 0; - u32 schq = 0; - u32 credits; - int rc; - - nix_hw = get_nix_hw(rvu->hw, blkaddr); - if (!nix_hw) - return NIX_AF_ERR_INVALID_NIXBLK; - - if (tx_credits == nix_hw->tx_credits[link]) - return 0; - - /* Enable cgx tx if disabled for credits to be back */ - if (is_pf_cgxmapped(rvu, pf)) { - rvu_get_cgx_lmac_id(rvu->pf2cgxlmac_map[pf], &cgx_id, &lmac_id); - restore_tx_en = !rvu_cgx_config_tx(rvu_cgx_pdata(cgx_id, rvu), - lmac_id, true); - } - - mutex_lock(&rvu->rsrc_lock); - /* Disable new traffic to link */ - if (hw->cap.nix_shaping) { - schq = nix_get_tx_link(rvu, pcifunc); - sw_xoff = rvu_read64(rvu, blkaddr, NIX_AF_TL1X_SW_XOFF(schq)); - rvu_write64(rvu, blkaddr, - NIX_AF_TL1X_SW_XOFF(schq), BIT_ULL(0)); - } - - rc = NIX_AF_ERR_LINK_CREDITS; - poll_tmo = jiffies + usecs_to_jiffies(200000); - /* Wait for credits to return */ - do { - if (time_after(jiffies, poll_tmo)) - goto exit; - usleep_range(100, 200); - - cfg = rvu_read64(rvu, blkaddr, - NIX_AF_TX_LINKX_NORM_CREDIT(link)); - credits = (cfg >> 12) & 0xFFFFFULL; - } while (credits != nix_hw->tx_credits[link]); - - cfg &= ~(0xFFFFFULL << 12); - cfg |= (tx_credits << 12); - rvu_write64(rvu, blkaddr, NIX_AF_TX_LINKX_NORM_CREDIT(link), cfg); - rc = 0; - - nix_hw->tx_credits[link] = tx_credits; - -exit: - /* Enable traffic back */ - if (hw->cap.nix_shaping && !sw_xoff) - rvu_write64(rvu, blkaddr, NIX_AF_TL1X_SW_XOFF(schq), 0); - - /* Restore state of cgx tx */ - if (restore_tx_en) - rvu_cgx_config_tx(rvu_cgx_pdata(cgx_id, rvu), lmac_id, false); - - mutex_unlock(&rvu->rsrc_lock); - return rc; -} - int rvu_mbox_handler_nix_set_hw_frs(struct rvu *rvu, struct nix_frs_cfg *req, struct msg_rsp *rsp) { struct rvu_hwinfo *hw = rvu->hw; u16 pcifunc = req->hdr.pcifunc; int pf = rvu_get_pf(pcifunc); - int blkaddr, schq, link = -1; - struct nix_txsch *txsch; - u64 cfg, lmac_fifo_len; + int blkaddr, link = -1; struct nix_hw *nix_hw; struct rvu_pfvf *pfvf; u8 cgx = 0, lmac = 0; u16 max_mtu; + u64 cfg; blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NIX, pcifunc); if (blkaddr < 0) @@ -4027,25 +3955,6 @@ int rvu_mbox_handler_nix_set_hw_frs(struct rvu *rvu, struct nix_frs_cfg *req, if (req->update_minlen && req->minlen < NIC_HW_MIN_FRS) return NIX_AF_ERR_FRS_INVALID; - /* Check if requester wants to update SMQ's */ - if (!req->update_smq) - goto rx_frscfg; - - /* Update min/maxlen in each of the SMQ attached to this PF/VF */ - txsch = &nix_hw->txsch[NIX_TXSCH_LVL_SMQ]; - mutex_lock(&rvu->rsrc_lock); - for (schq = 0; schq < txsch->schq.max; schq++) { - if (TXSCH_MAP_FUNC(txsch->pfvf_map[schq]) != pcifunc) - continue; - cfg = rvu_read64(rvu, blkaddr, NIX_AF_SMQX_CFG(schq)); - cfg = (cfg & ~(0xFFFFULL << 8)) | ((u64)req->maxlen << 8); - if (req->update_minlen) - cfg = (cfg & ~0x7FULL) | ((u64)req->minlen & 0x7F); - rvu_write64(rvu, blkaddr, NIX_AF_SMQX_CFG(schq), cfg); - } - mutex_unlock(&rvu->rsrc_lock); - -rx_frscfg: /* Check if config is for SDP link */ if (req->sdp_link) { if (!hw->sdp_links) @@ -4068,7 +3977,6 @@ rx_frscfg: if (link < 0) return NIX_AF_ERR_RX_LINK_INVALID; - linkcfg: nix_find_link_frs(rvu, req, pcifunc); @@ -4078,19 +3986,7 @@ linkcfg: cfg = (cfg & ~0xFFFFULL) | req->minlen; rvu_write64(rvu, blkaddr, NIX_AF_RX_LINKX_CFG(link), cfg); - if (req->sdp_link || pf == 0) - return 0; - - /* Update transmit credits for CGX links */ - lmac_fifo_len = rvu_cgx_get_lmac_fifolen(rvu, cgx, lmac); - if (!lmac_fifo_len) { - dev_err(rvu->dev, - "%s: Failed to get CGX/RPM%d:LMAC%d FIFO size\n", - __func__, cgx, lmac); - return 0; - } - return nix_config_link_credits(rvu, blkaddr, link, pcifunc, - (lmac_fifo_len - req->maxlen) / 16); + return 0; } int rvu_mbox_handler_nix_set_rx_cfg(struct rvu *rvu, struct nix_rx_cfg *req, @@ -4183,7 +4079,7 @@ static void nix_link_config(struct rvu *rvu, int blkaddr, /* Get LMAC id's from bitmap */ lmac_bmap = cgx_get_lmac_bmap(rvu_cgx_pdata(cgx, rvu)); - for_each_set_bit(iter, &lmac_bmap, MAX_LMAC_PER_CGX) { + for_each_set_bit(iter, &lmac_bmap, rvu->hw->lmac_per_cgx) { lmac_fifo_len = rvu_cgx_get_lmac_fifolen(rvu, cgx, iter); if (!lmac_fifo_len) { dev_err(rvu->dev, @@ -4610,7 +4506,13 @@ int rvu_mbox_handler_nix_lf_stop_rx(struct rvu *rvu, struct msg_req *req, pfvf = rvu_get_pfvf(rvu, pcifunc); clear_bit(NIXLF_INITIALIZED, &pfvf->flags); - return rvu_cgx_start_stop_io(rvu, pcifunc, false); + err = rvu_cgx_start_stop_io(rvu, pcifunc, false); + if (err) + return err; + + rvu_cgx_tx_enable(rvu, pcifunc, true); + + return 0; } #define RX_SA_BASE GENMASK_ULL(52, 7) diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_hash.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_hash.c index 34fa59575fa91..54e0dfdc9d984 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_hash.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_hash.c @@ -1999,7 +1999,9 @@ int rvu_npc_exact_init(struct rvu *rvu) /* Install SDP drop rule */ drop_mcam_idx = &table->num_drop_rules; - max_lmac_cnt = rvu->cgx_cnt_max * MAX_LMAC_PER_CGX + PF_CGXMAP_BASE; + max_lmac_cnt = rvu->cgx_cnt_max * rvu->hw->lmac_per_cgx + + PF_CGXMAP_BASE; + for (i = PF_CGXMAP_BASE; i < max_lmac_cnt; i++) { if (rvu->pf2cgxlmac_map[i] == 0xFF) continue; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c index d136360ac6a98..a6d3fc96e1685 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c @@ -25,7 +25,7 @@ struct mlx5_irq { struct atomic_notifier_head nh; cpumask_var_t mask; - char name[MLX5_MAX_IRQ_NAME]; + char name[MLX5_MAX_IRQ_FORMATTED_NAME]; struct mlx5_irq_pool *pool; int refcount; u32 index; @@ -236,8 +236,8 @@ struct mlx5_irq *mlx5_irq_alloc(struct mlx5_irq_pool *pool, int i, else irq_sf_set_name(pool, name, i); ATOMIC_INIT_NOTIFIER_HEAD(&irq->nh); - snprintf(irq->name, MLX5_MAX_IRQ_NAME, - "%s@pci:%s", name, pci_name(dev->pdev)); + snprintf(irq->name, MLX5_MAX_IRQ_FORMATTED_NAME, + MLX5_IRQ_NAME_FORMAT_STR, name, pci_name(dev->pdev)); err = request_irq(irq->irqn, irq_int_handler, 0, irq->name, &irq->nh); if (err) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.h b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.h index 5c7e68bee43a0..4047179307c4a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.h @@ -7,6 +7,9 @@ #include #define MLX5_MAX_IRQ_NAME (32) +#define MLX5_IRQ_NAME_FORMAT_STR ("%s@pci:%s") +#define MLX5_MAX_IRQ_FORMATTED_NAME \ + (MLX5_MAX_IRQ_NAME + sizeof(MLX5_IRQ_NAME_FORMAT_STR)) /* max irq_index is 2047, so four chars */ #define MLX5_MAX_IRQ_IDX_CHARS (4) #define MLX5_EQ_REFS_PER_IRQ (2) diff --git a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_rx.c b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_rx.c index 0d5a41a2ae010..227d01cace3f0 100644 --- a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_rx.c +++ b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_rx.c @@ -267,6 +267,13 @@ static bool mlxbf_gige_rx_packet(struct mlxbf_gige *priv, int *rx_pkts) priv->stats.rx_truncate_errors++; } + /* Read receive consumer index before replenish so that this routine + * returns accurate return value even if packet is received into + * just-replenished buffer prior to exiting this routine. + */ + rx_ci = readq(priv->base + MLXBF_GIGE_RX_CQE_PACKET_CI); + rx_ci_rem = rx_ci % priv->rx_q_entries; + /* Let hardware know we've replenished one buffer */ rx_pi++; @@ -279,8 +286,6 @@ static bool mlxbf_gige_rx_packet(struct mlxbf_gige *priv, int *rx_pkts) rx_pi_rem = rx_pi % priv->rx_q_entries; if (rx_pi_rem == 0) priv->valid_polarity ^= 1; - rx_ci = readq(priv->base + MLXBF_GIGE_RX_CQE_PACKET_CI); - rx_ci_rem = rx_ci % priv->rx_q_entries; if (skb) netif_receive_skb(skb); diff --git a/drivers/net/ethernet/qlogic/qla3xxx.c b/drivers/net/ethernet/qlogic/qla3xxx.c index 0d57ffcedf0c6..fc78bc959ded8 100644 --- a/drivers/net/ethernet/qlogic/qla3xxx.c +++ b/drivers/net/ethernet/qlogic/qla3xxx.c @@ -2591,6 +2591,7 @@ static int ql_alloc_buffer_queues(struct ql3_adapter *qdev) if (qdev->lrg_buf_q_alloc_virt_addr == NULL) { netdev_err(qdev->ndev, "lBufQ failed\n"); + kfree(qdev->lrg_buf); return -ENOMEM; } qdev->lrg_buf_q_virt_addr = qdev->lrg_buf_q_alloc_virt_addr; @@ -2615,6 +2616,7 @@ static int ql_alloc_buffer_queues(struct ql3_adapter *qdev) qdev->lrg_buf_q_alloc_size, qdev->lrg_buf_q_alloc_virt_addr, qdev->lrg_buf_q_alloc_phy_addr); + kfree(qdev->lrg_buf); return -ENOMEM; } diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index d22457f2cf9cf..06663c11ca96d 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -1145,7 +1145,7 @@ static void rtl8168ep_driver_start(struct rtl8169_private *tp) { r8168ep_ocp_write(tp, 0x01, 0x180, OOB_CMD_DRIVER_START); r8168ep_ocp_write(tp, 0x01, 0x30, r8168ep_ocp_read(tp, 0x30) | 0x01); - rtl_loop_wait_high(tp, &rtl_ep_ocp_read_cond, 10000, 10); + rtl_loop_wait_high(tp, &rtl_ep_ocp_read_cond, 10000, 30); } static void rtl8168_driver_start(struct rtl8169_private *tp) diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index 68cb5616ef991..c2c56a5289caf 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -68,16 +68,27 @@ int ravb_wait(struct net_device *ndev, enum ravb_reg reg, u32 mask, u32 value) return -ETIMEDOUT; } -static int ravb_config(struct net_device *ndev) +static int ravb_set_opmode(struct net_device *ndev, u32 opmode) { + u32 csr_ops = 1U << (opmode & CCC_OPC); + u32 ccc_mask = CCC_OPC; int error; - /* Set config mode */ - ravb_modify(ndev, CCC, CCC_OPC, CCC_OPC_CONFIG); - /* Check if the operating mode is changed to the config mode */ - error = ravb_wait(ndev, CSR, CSR_OPS, CSR_OPS_CONFIG); - if (error) - netdev_err(ndev, "failed to switch device to config mode\n"); + /* If gPTP active in config mode is supported it needs to be configured + * along with CSEL and operating mode in the same access. This is a + * hardware limitation. + */ + if (opmode & CCC_GAC) + ccc_mask |= CCC_GAC | CCC_CSEL; + + /* Set operating mode */ + ravb_modify(ndev, CCC, ccc_mask, opmode); + /* Check if the operating mode is changed to the requested one */ + error = ravb_wait(ndev, CSR, CSR_OPS, csr_ops); + if (error) { + netdev_err(ndev, "failed to switch device to requested mode (%u)\n", + opmode & CCC_OPC); + } return error; } @@ -675,7 +686,7 @@ static int ravb_dmac_init(struct net_device *ndev) int error; /* Set CONFIG mode */ - error = ravb_config(ndev); + error = ravb_set_opmode(ndev, CCC_OPC_CONFIG); if (error) return error; @@ -684,9 +695,7 @@ static int ravb_dmac_init(struct net_device *ndev) return error; /* Setting the control will start the AVB-DMAC process. */ - ravb_modify(ndev, CCC, CCC_OPC, CCC_OPC_OPERATION); - - return 0; + return ravb_set_opmode(ndev, CCC_OPC_OPERATION); } static void ravb_get_tx_tstamp(struct net_device *ndev) @@ -1048,7 +1057,7 @@ static int ravb_stop_dma(struct net_device *ndev) return error; /* Stop AVB-DMAC process */ - return ravb_config(ndev); + return ravb_set_opmode(ndev, CCC_OPC_CONFIG); } /* E-MAC interrupt handler */ @@ -2576,21 +2585,25 @@ static int ravb_set_gti(struct net_device *ndev) return 0; } -static void ravb_set_config_mode(struct net_device *ndev) +static int ravb_set_config_mode(struct net_device *ndev) { struct ravb_private *priv = netdev_priv(ndev); const struct ravb_hw_info *info = priv->info; + int error; if (info->gptp) { - ravb_modify(ndev, CCC, CCC_OPC, CCC_OPC_CONFIG); + error = ravb_set_opmode(ndev, CCC_OPC_CONFIG); + if (error) + return error; /* Set CSEL value */ ravb_modify(ndev, CCC, CCC_CSEL, CCC_CSEL_HPB); } else if (info->ccc_gac) { - ravb_modify(ndev, CCC, CCC_OPC, CCC_OPC_CONFIG | - CCC_GAC | CCC_CSEL_HPB); + error = ravb_set_opmode(ndev, CCC_OPC_CONFIG | CCC_GAC | CCC_CSEL_HPB); } else { - ravb_modify(ndev, CCC, CCC_OPC, CCC_OPC_CONFIG); + error = ravb_set_opmode(ndev, CCC_OPC_CONFIG); } + + return error; } /* Set tx and rx clock internal delay modes */ @@ -2810,7 +2823,9 @@ static int ravb_probe(struct platform_device *pdev) ndev->ethtool_ops = &ravb_ethtool_ops; /* Set AVB config mode */ - ravb_set_config_mode(ndev); + error = ravb_set_config_mode(ndev); + if (error) + goto out_disable_gptp_clk; if (info->gptp || info->ccc_gac) { /* Set GTI value */ @@ -2933,8 +2948,7 @@ static int ravb_remove(struct platform_device *pdev) dma_free_coherent(ndev->dev.parent, priv->desc_bat_size, priv->desc_bat, priv->desc_bat_dma); - /* Set reset mode */ - ravb_write(ndev, CCC_OPC_RESET, CCC); + ravb_set_opmode(ndev, CCC_OPC_RESET); clk_disable_unprepare(priv->gptp_clk); clk_disable_unprepare(priv->refclk); @@ -3018,8 +3032,11 @@ static int __maybe_unused ravb_resume(struct device *dev) int ret = 0; /* If WoL is enabled set reset mode to rearm the WoL logic */ - if (priv->wol_enabled) - ravb_write(ndev, CCC_OPC_RESET, CCC); + if (priv->wol_enabled) { + ret = ravb_set_opmode(ndev, CCC_OPC_RESET); + if (ret) + return ret; + } /* All register have been reset to default values. * Restore all registers which where setup at probe time and @@ -3027,7 +3044,9 @@ static int __maybe_unused ravb_resume(struct device *dev) */ /* Set AVB config mode */ - ravb_set_config_mode(ndev); + ret = ravb_set_config_mode(ndev); + if (ret) + return ret; if (info->gptp || info->ccc_gac) { /* Set GTI value */ diff --git a/drivers/net/ethernet/sfc/rx_common.c b/drivers/net/ethernet/sfc/rx_common.c index 9220afeddee81..3f290791df1c4 100644 --- a/drivers/net/ethernet/sfc/rx_common.c +++ b/drivers/net/ethernet/sfc/rx_common.c @@ -820,8 +820,10 @@ int efx_probe_filters(struct efx_nic *efx) } if (!success) { - efx_for_each_channel(channel, efx) + efx_for_each_channel(channel, efx) { kfree(channel->rps_flow_id); + channel->rps_flow_id = NULL; + } efx->type->filter_table_remove(efx); rc = -ENOMEM; goto out_unlock; diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c index 477b4d4f860bd..bace989591f75 100644 --- a/drivers/net/gtp.c +++ b/drivers/net/gtp.c @@ -629,7 +629,7 @@ static void __gtp_encap_destroy(struct sock *sk) gtp->sk0 = NULL; else gtp->sk1u = NULL; - udp_sk(sk)->encap_type = 0; + WRITE_ONCE(udp_sk(sk)->encap_type, 0); rcu_assign_sk_user_data(sk, NULL); release_sock(sk); sock_put(sk); @@ -681,7 +681,7 @@ static int gtp_encap_recv(struct sock *sk, struct sk_buff *skb) netdev_dbg(gtp->dev, "encap_recv sk=%p\n", sk); - switch (udp_sk(sk)->encap_type) { + switch (READ_ONCE(udp_sk(sk)->encap_type)) { case UDP_ENCAP_GTP0: netdev_dbg(gtp->dev, "received GTP0 packet\n"); ret = gtp0_udp_encap_recv(gtp, skb); diff --git a/drivers/net/usb/ax88172a.c b/drivers/net/usb/ax88172a.c index 3777c7e2e6fc0..e47bb125048d4 100644 --- a/drivers/net/usb/ax88172a.c +++ b/drivers/net/usb/ax88172a.c @@ -161,7 +161,9 @@ static int ax88172a_bind(struct usbnet *dev, struct usb_interface *intf) u8 buf[ETH_ALEN]; struct ax88172a_private *priv; - usbnet_get_endpoints(dev, intf); + ret = usbnet_get_endpoints(dev, intf); + if (ret) + return ret; priv = kzalloc(sizeof(*priv), GFP_KERNEL); if (!priv) diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-prph.h b/drivers/net/wireless/intel/iwlwifi/iwl-prph.h index 157d1f31c4871..c5a306b01fe20 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-prph.h +++ b/drivers/net/wireless/intel/iwlwifi/iwl-prph.h @@ -348,8 +348,8 @@ #define RFIC_REG_RD 0xAD0470 #define WFPM_CTRL_REG 0xA03030 #define WFPM_OTP_CFG1_ADDR 0x00a03098 -#define WFPM_OTP_CFG1_IS_JACKET_BIT BIT(4) -#define WFPM_OTP_CFG1_IS_CDB_BIT BIT(5) +#define WFPM_OTP_CFG1_IS_JACKET_BIT BIT(5) +#define WFPM_OTP_CFG1_IS_CDB_BIT BIT(4) #define WFPM_GP2 0xA030B4 diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/internal.h b/drivers/net/wireless/intel/iwlwifi/pcie/internal.h index 69b95ad5993b0..2ec4ee8ab317c 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/internal.h +++ b/drivers/net/wireless/intel/iwlwifi/pcie/internal.h @@ -745,7 +745,7 @@ static inline void iwl_enable_rfkill_int(struct iwl_trans *trans) } } -void iwl_pcie_handle_rfkill_irq(struct iwl_trans *trans); +void iwl_pcie_handle_rfkill_irq(struct iwl_trans *trans, bool from_irq); static inline bool iwl_is_rfkill_set(struct iwl_trans *trans) { @@ -792,7 +792,7 @@ static inline bool iwl_pcie_dbg_on(struct iwl_trans *trans) return (trans->dbg.dest_tlv || iwl_trans_dbg_ini_valid(trans)); } -void iwl_trans_pcie_rf_kill(struct iwl_trans *trans, bool state); +void iwl_trans_pcie_rf_kill(struct iwl_trans *trans, bool state, bool from_irq); void iwl_trans_pcie_dump_regs(struct iwl_trans *trans); #ifdef CONFIG_IWLWIFI_DEBUGFS diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/rx.c b/drivers/net/wireless/intel/iwlwifi/pcie/rx.c index 90a46faaaffdf..57a11ee05bc36 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/rx.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/rx.c @@ -1781,7 +1781,7 @@ static u32 iwl_pcie_int_cause_ict(struct iwl_trans *trans) return inta; } -void iwl_pcie_handle_rfkill_irq(struct iwl_trans *trans) +void iwl_pcie_handle_rfkill_irq(struct iwl_trans *trans, bool from_irq) { struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans); struct isr_statistics *isr_stats = &trans_pcie->isr_stats; @@ -1805,7 +1805,7 @@ void iwl_pcie_handle_rfkill_irq(struct iwl_trans *trans) isr_stats->rfkill++; if (prev != report) - iwl_trans_pcie_rf_kill(trans, report); + iwl_trans_pcie_rf_kill(trans, report, from_irq); mutex_unlock(&trans_pcie->mutex); if (hw_rfkill) { @@ -1945,7 +1945,7 @@ irqreturn_t iwl_pcie_irq_handler(int irq, void *dev_id) /* HW RF KILL switch toggled */ if (inta & CSR_INT_BIT_RF_KILL) { - iwl_pcie_handle_rfkill_irq(trans); + iwl_pcie_handle_rfkill_irq(trans, true); handled |= CSR_INT_BIT_RF_KILL; } @@ -2362,7 +2362,7 @@ irqreturn_t iwl_pcie_irq_msix_handler(int irq, void *dev_id) /* HW RF KILL switch toggled */ if (inta_hw & MSIX_HW_INT_CAUSES_REG_RF_KILL) - iwl_pcie_handle_rfkill_irq(trans); + iwl_pcie_handle_rfkill_irq(trans, true); if (inta_hw & MSIX_HW_INT_CAUSES_REG_HW_ERR) { IWL_ERR(trans, diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c index 796972f224326..c7ed35b3dd8d5 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c @@ -1080,7 +1080,7 @@ bool iwl_pcie_check_hw_rf_kill(struct iwl_trans *trans) report = test_bit(STATUS_RFKILL_OPMODE, &trans->status); if (prev != report) - iwl_trans_pcie_rf_kill(trans, report); + iwl_trans_pcie_rf_kill(trans, report, false); return hw_rfkill; } @@ -1234,7 +1234,7 @@ static void iwl_pcie_init_msix(struct iwl_trans_pcie *trans_pcie) trans_pcie->hw_mask = trans_pcie->hw_init_mask; } -static void _iwl_trans_pcie_stop_device(struct iwl_trans *trans) +static void _iwl_trans_pcie_stop_device(struct iwl_trans *trans, bool from_irq) { struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans); @@ -1261,7 +1261,8 @@ static void _iwl_trans_pcie_stop_device(struct iwl_trans *trans) if (test_and_clear_bit(STATUS_DEVICE_ENABLED, &trans->status)) { IWL_DEBUG_INFO(trans, "DEVICE_ENABLED bit was set and is now cleared\n"); - iwl_pcie_synchronize_irqs(trans); + if (!from_irq) + iwl_pcie_synchronize_irqs(trans); iwl_pcie_rx_napi_sync(trans); iwl_pcie_tx_stop(trans); iwl_pcie_rx_stop(trans); @@ -1451,7 +1452,7 @@ void iwl_trans_pcie_handle_stop_rfkill(struct iwl_trans *trans, clear_bit(STATUS_RFKILL_OPMODE, &trans->status); } if (hw_rfkill != was_in_rfkill) - iwl_trans_pcie_rf_kill(trans, hw_rfkill); + iwl_trans_pcie_rf_kill(trans, hw_rfkill, false); } static void iwl_trans_pcie_stop_device(struct iwl_trans *trans) @@ -1466,12 +1467,12 @@ static void iwl_trans_pcie_stop_device(struct iwl_trans *trans) mutex_lock(&trans_pcie->mutex); trans_pcie->opmode_down = true; was_in_rfkill = test_bit(STATUS_RFKILL_OPMODE, &trans->status); - _iwl_trans_pcie_stop_device(trans); + _iwl_trans_pcie_stop_device(trans, false); iwl_trans_pcie_handle_stop_rfkill(trans, was_in_rfkill); mutex_unlock(&trans_pcie->mutex); } -void iwl_trans_pcie_rf_kill(struct iwl_trans *trans, bool state) +void iwl_trans_pcie_rf_kill(struct iwl_trans *trans, bool state, bool from_irq) { struct iwl_trans_pcie __maybe_unused *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans); @@ -1484,7 +1485,7 @@ void iwl_trans_pcie_rf_kill(struct iwl_trans *trans, bool state) if (trans->trans_cfg->gen2) _iwl_trans_pcie_gen2_stop_device(trans); else - _iwl_trans_pcie_stop_device(trans); + _iwl_trans_pcie_stop_device(trans, from_irq); } } @@ -2815,7 +2816,7 @@ static ssize_t iwl_dbgfs_rfkill_write(struct file *file, IWL_WARN(trans, "changing debug rfkill %d->%d\n", trans_pcie->debug_rfkill, new_value); trans_pcie->debug_rfkill = new_value; - iwl_pcie_handle_rfkill_irq(trans); + iwl_pcie_handle_rfkill_irq(trans, false); return count; } diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 8df156c28aade..5368a37154cf9 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -1302,6 +1302,9 @@ static int pci_set_full_power_state(struct pci_dev *dev) pci_restore_bars(dev); } + if (dev->bus->self) + pcie_aspm_pm_state_change(dev->bus->self); + return 0; } @@ -1396,6 +1399,9 @@ static int pci_set_low_power_state(struct pci_dev *dev, pci_power_t state) pci_power_name(dev->current_state), pci_power_name(state)); + if (dev->bus->self) + pcie_aspm_pm_state_change(dev->bus->self); + return 0; } diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index ffccb03933e27..ed6d75d138c7a 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -561,10 +561,12 @@ bool pcie_wait_for_link(struct pci_dev *pdev, bool active); #ifdef CONFIG_PCIEASPM void pcie_aspm_init_link_state(struct pci_dev *pdev); void pcie_aspm_exit_link_state(struct pci_dev *pdev); +void pcie_aspm_pm_state_change(struct pci_dev *pdev); void pcie_aspm_powersave_config_link(struct pci_dev *pdev); #else static inline void pcie_aspm_init_link_state(struct pci_dev *pdev) { } static inline void pcie_aspm_exit_link_state(struct pci_dev *pdev) { } +static inline void pcie_aspm_pm_state_change(struct pci_dev *pdev) { } static inline void pcie_aspm_powersave_config_link(struct pci_dev *pdev) { } #endif diff --git a/drivers/pci/pcie/aspm.c b/drivers/pci/pcie/aspm.c index 5d1756f53ba84..25736d408e88e 100644 --- a/drivers/pci/pcie/aspm.c +++ b/drivers/pci/pcie/aspm.c @@ -1055,6 +1055,25 @@ void pcie_aspm_exit_link_state(struct pci_dev *pdev) up_read(&pci_bus_sem); } +/* @pdev: the root port or switch downstream port */ +void pcie_aspm_pm_state_change(struct pci_dev *pdev) +{ + struct pcie_link_state *link = pdev->link_state; + + if (aspm_disabled || !link) + return; + /* + * Devices changed PM state, we should recheck if latency + * meets all functions' requirement + */ + down_read(&pci_bus_sem); + mutex_lock(&aspm_lock); + pcie_update_aspm_capable(link->root); + pcie_config_aspm_path(link); + mutex_unlock(&aspm_lock); + up_read(&pci_bus_sem); +} + void pcie_aspm_powersave_config_link(struct pci_dev *pdev) { struct pcie_link_state *link = pdev->link_state; diff --git a/drivers/video/fbdev/imsttfb.c b/drivers/video/fbdev/imsttfb.c index b194e71f07bfc..aa51cb72cbba5 100644 --- a/drivers/video/fbdev/imsttfb.c +++ b/drivers/video/fbdev/imsttfb.c @@ -1419,7 +1419,6 @@ static int init_imstt(struct fb_info *info) if ((info->var.xres * info->var.yres) * (info->var.bits_per_pixel >> 3) > info->fix.smem_len || !(compute_imstt_regvals(par, info->var.xres, info->var.yres))) { printk("imsttfb: %ux%ux%u not supported\n", info->var.xres, info->var.yres, info->var.bits_per_pixel); - framebuffer_release(info); return -ENODEV; } @@ -1452,10 +1451,11 @@ static int init_imstt(struct fb_info *info) FBINFO_HWACCEL_FILLRECT | FBINFO_HWACCEL_YPAN; - fb_alloc_cmap(&info->cmap, 0, 0); + if (fb_alloc_cmap(&info->cmap, 0, 0)) + return -ENODEV; if (register_framebuffer(info) < 0) { - framebuffer_release(info); + fb_dealloc_cmap(&info->cmap); return -ENODEV; } diff --git a/fs/9p/cache.c b/fs/9p/cache.c index cebba4eaa0b57..12c0ae29f1857 100644 --- a/fs/9p/cache.c +++ b/fs/9p/cache.c @@ -68,6 +68,8 @@ void v9fs_cache_inode_get_cookie(struct inode *inode) &path, sizeof(path), &version, sizeof(version), i_size_read(&v9inode->netfs.inode)); + if (v9inode->netfs.cache) + mapping_set_release_always(inode->i_mapping); p9_debug(P9_DEBUG_FSC, "inode %p get cookie %p\n", inode, v9fs_inode_cookie(v9inode)); diff --git a/fs/afs/internal.h b/fs/afs/internal.h index fcbb598d8c85d..a25fdc3e52310 100644 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@ -682,6 +682,8 @@ static inline void afs_vnode_set_cache(struct afs_vnode *vnode, { #ifdef CONFIG_AFS_FSCACHE vnode->netfs.cache = cookie; + if (cookie) + mapping_set_release_always(vnode->netfs.inode.i_mapping); #endif } diff --git a/fs/btrfs/delalloc-space.c b/fs/btrfs/delalloc-space.c index 0b62ce77053f5..f2bc5563c0f92 100644 --- a/fs/btrfs/delalloc-space.c +++ b/fs/btrfs/delalloc-space.c @@ -197,7 +197,7 @@ void btrfs_free_reserved_data_space(struct btrfs_inode *inode, start = round_down(start, fs_info->sectorsize); btrfs_free_reserved_data_space_noquota(fs_info, len); - btrfs_qgroup_free_data(inode, reserved, start, len); + btrfs_qgroup_free_data(inode, reserved, start, len, NULL); } /** diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c index b14d2da9b26d3..14478da875313 100644 --- a/fs/btrfs/file-item.c +++ b/fs/btrfs/file-item.c @@ -602,7 +602,7 @@ int btrfs_lookup_csums_range(struct btrfs_root *root, u64 start, u64 end, } sums->bytenr = start; - sums->len = (int)size; + sums->len = size; offset = (start - key.offset) >> fs_info->sectorsize_bits; offset *= csum_size; diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 0a46fff3dd067..1783a0fbf1665 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -3191,7 +3191,7 @@ static long btrfs_fallocate(struct file *file, int mode, qgroup_reserved -= range->len; } else if (qgroup_reserved > 0) { btrfs_qgroup_free_data(BTRFS_I(inode), data_reserved, - range->start, range->len); + range->start, range->len, NULL); qgroup_reserved -= range->len; } list_del(&range->list); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 81eac121c6b23..9a7d77c410e22 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -466,7 +466,7 @@ out: * And at reserve time, it's always aligned to page size, so * just free one page here. */ - btrfs_qgroup_free_data(inode, NULL, 0, PAGE_SIZE); + btrfs_qgroup_free_data(inode, NULL, 0, PAGE_SIZE, NULL); btrfs_free_path(path); btrfs_end_transaction(trans); return ret; @@ -5372,7 +5372,7 @@ static void evict_inode_truncate_pages(struct inode *inode) */ if (state_flags & EXTENT_DELALLOC) btrfs_qgroup_free_data(BTRFS_I(inode), NULL, start, - end - start + 1); + end - start + 1, NULL); clear_extent_bit(io_tree, start, end, EXTENT_CLEAR_ALL_BITS | EXTENT_DO_ACCOUNTING, @@ -8440,7 +8440,7 @@ next: * reserved data space. * Since the IO will never happen for this page. */ - btrfs_qgroup_free_data(inode, NULL, cur, range_end + 1 - cur); + btrfs_qgroup_free_data(inode, NULL, cur, range_end + 1 - cur, NULL); if (!inode_evicting) { clear_extent_bit(tree, cur, range_end, EXTENT_LOCKED | EXTENT_DELALLOC | EXTENT_UPTODATE | @@ -9902,7 +9902,7 @@ static struct btrfs_trans_handle *insert_prealloc_file_extent( struct btrfs_path *path; u64 start = ins->objectid; u64 len = ins->offset; - int qgroup_released; + u64 qgroup_released = 0; int ret; memset(&stack_fi, 0, sizeof(stack_fi)); @@ -9915,9 +9915,9 @@ static struct btrfs_trans_handle *insert_prealloc_file_extent( btrfs_set_stack_file_extent_compression(&stack_fi, BTRFS_COMPRESS_NONE); /* Encryption and other encoding is reserved and all 0 */ - qgroup_released = btrfs_qgroup_release_data(inode, file_offset, len); - if (qgroup_released < 0) - return ERR_PTR(qgroup_released); + ret = btrfs_qgroup_release_data(inode, file_offset, len, &qgroup_released); + if (ret < 0) + return ERR_PTR(ret); if (trans) { ret = insert_reserved_file_extent(trans, inode, @@ -10903,7 +10903,7 @@ out_delalloc_release: btrfs_delalloc_release_metadata(inode, disk_num_bytes, ret < 0); out_qgroup_free_data: if (ret < 0) - btrfs_qgroup_free_data(inode, data_reserved, start, num_bytes); + btrfs_qgroup_free_data(inode, data_reserved, start, num_bytes, NULL); out_free_data_space: /* * If btrfs_reserve_extent() succeeded, then we already decremented diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c index 0321753c16b9f..1b2af4785c0e2 100644 --- a/fs/btrfs/ordered-data.c +++ b/fs/btrfs/ordered-data.c @@ -172,11 +172,12 @@ int btrfs_add_ordered_extent(struct btrfs_inode *inode, u64 file_offset, struct rb_node *node; struct btrfs_ordered_extent *entry; int ret; + u64 qgroup_rsv = 0; if (flags & ((1 << BTRFS_ORDERED_NOCOW) | (1 << BTRFS_ORDERED_PREALLOC))) { /* For nocow write, we can release the qgroup rsv right now */ - ret = btrfs_qgroup_free_data(inode, NULL, file_offset, num_bytes); + ret = btrfs_qgroup_free_data(inode, NULL, file_offset, num_bytes, &qgroup_rsv); if (ret < 0) return ret; ret = 0; @@ -185,7 +186,7 @@ int btrfs_add_ordered_extent(struct btrfs_inode *inode, u64 file_offset, * The ordered extent has reserved qgroup space, release now * and pass the reserved number for qgroup_record to free. */ - ret = btrfs_qgroup_release_data(inode, file_offset, num_bytes); + ret = btrfs_qgroup_release_data(inode, file_offset, num_bytes, &qgroup_rsv); if (ret < 0) return ret; } @@ -203,7 +204,7 @@ int btrfs_add_ordered_extent(struct btrfs_inode *inode, u64 file_offset, entry->inode = igrab(&inode->vfs_inode); entry->compress_type = compress_type; entry->truncated_len = (u64)-1; - entry->qgroup_rsv = ret; + entry->qgroup_rsv = qgroup_rsv; entry->physical = (u64)-1; ASSERT((flags & ~BTRFS_ORDERED_TYPE_FLAGS) == 0); diff --git a/fs/btrfs/ordered-data.h b/fs/btrfs/ordered-data.h index f59f2dbdb25ed..cc3ca4bb9bd54 100644 --- a/fs/btrfs/ordered-data.h +++ b/fs/btrfs/ordered-data.h @@ -20,7 +20,7 @@ struct btrfs_ordered_sum { /* * this is the length in bytes covered by the sums array below. */ - int len; + u32 len; struct list_head list; /* last field is a variable length array of csums */ u8 sums[]; diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index 26cabffd59710..96ec9ccc2ef61 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -3833,13 +3833,14 @@ int btrfs_qgroup_reserve_data(struct btrfs_inode *inode, /* Free ranges specified by @reserved, normally in error path */ static int qgroup_free_reserved_data(struct btrfs_inode *inode, - struct extent_changeset *reserved, u64 start, u64 len) + struct extent_changeset *reserved, + u64 start, u64 len, u64 *freed_ret) { struct btrfs_root *root = inode->root; struct ulist_node *unode; struct ulist_iterator uiter; struct extent_changeset changeset; - int freed = 0; + u64 freed = 0; int ret; extent_changeset_init(&changeset); @@ -3880,7 +3881,9 @@ static int qgroup_free_reserved_data(struct btrfs_inode *inode, } btrfs_qgroup_free_refroot(root->fs_info, root->root_key.objectid, freed, BTRFS_QGROUP_RSV_DATA); - ret = freed; + if (freed_ret) + *freed_ret = freed; + ret = 0; out: extent_changeset_release(&changeset); return ret; @@ -3888,7 +3891,7 @@ out: static int __btrfs_qgroup_release_data(struct btrfs_inode *inode, struct extent_changeset *reserved, u64 start, u64 len, - int free) + u64 *released, int free) { struct extent_changeset changeset; int trace_op = QGROUP_RELEASE; @@ -3900,7 +3903,7 @@ static int __btrfs_qgroup_release_data(struct btrfs_inode *inode, /* In release case, we shouldn't have @reserved */ WARN_ON(!free && reserved); if (free && reserved) - return qgroup_free_reserved_data(inode, reserved, start, len); + return qgroup_free_reserved_data(inode, reserved, start, len, released); extent_changeset_init(&changeset); ret = clear_record_extent_bits(&inode->io_tree, start, start + len -1, EXTENT_QGROUP_RESERVED, &changeset); @@ -3915,7 +3918,8 @@ static int __btrfs_qgroup_release_data(struct btrfs_inode *inode, btrfs_qgroup_free_refroot(inode->root->fs_info, inode->root->root_key.objectid, changeset.bytes_changed, BTRFS_QGROUP_RSV_DATA); - ret = changeset.bytes_changed; + if (released) + *released = changeset.bytes_changed; out: extent_changeset_release(&changeset); return ret; @@ -3934,9 +3938,10 @@ out: * NOTE: This function may sleep for memory allocation. */ int btrfs_qgroup_free_data(struct btrfs_inode *inode, - struct extent_changeset *reserved, u64 start, u64 len) + struct extent_changeset *reserved, + u64 start, u64 len, u64 *freed) { - return __btrfs_qgroup_release_data(inode, reserved, start, len, 1); + return __btrfs_qgroup_release_data(inode, reserved, start, len, freed, 1); } /* @@ -3954,9 +3959,9 @@ int btrfs_qgroup_free_data(struct btrfs_inode *inode, * * NOTE: This function may sleep for memory allocation. */ -int btrfs_qgroup_release_data(struct btrfs_inode *inode, u64 start, u64 len) +int btrfs_qgroup_release_data(struct btrfs_inode *inode, u64 start, u64 len, u64 *released) { - return __btrfs_qgroup_release_data(inode, NULL, start, len, 0); + return __btrfs_qgroup_release_data(inode, NULL, start, len, released, 0); } static void add_root_meta_rsv(struct btrfs_root *root, int num_bytes, diff --git a/fs/btrfs/qgroup.h b/fs/btrfs/qgroup.h index 578c77e94200f..c382923f7628e 100644 --- a/fs/btrfs/qgroup.h +++ b/fs/btrfs/qgroup.h @@ -360,10 +360,10 @@ int btrfs_verify_qgroup_counts(struct btrfs_fs_info *fs_info, u64 qgroupid, /* New io_tree based accurate qgroup reserve API */ int btrfs_qgroup_reserve_data(struct btrfs_inode *inode, struct extent_changeset **reserved, u64 start, u64 len); -int btrfs_qgroup_release_data(struct btrfs_inode *inode, u64 start, u64 len); +int btrfs_qgroup_release_data(struct btrfs_inode *inode, u64 start, u64 len, u64 *released); int btrfs_qgroup_free_data(struct btrfs_inode *inode, struct extent_changeset *reserved, u64 start, - u64 len); + u64 len, u64 *freed); int btrfs_qgroup_reserve_meta(struct btrfs_root *root, int num_bytes, enum btrfs_qgroup_rsv_type type, bool enforce); int __btrfs_qgroup_reserve_meta(struct btrfs_root *root, int num_bytes, diff --git a/fs/cachefiles/namei.c b/fs/cachefiles/namei.c index 03ca8f2f657ab..50b2ee163af60 100644 --- a/fs/cachefiles/namei.c +++ b/fs/cachefiles/namei.c @@ -584,6 +584,8 @@ static bool cachefiles_open_file(struct cachefiles_object *object, if (ret < 0) goto check_failed; + clear_bit(FSCACHE_COOKIE_NO_DATA_TO_READ, &object->cookie->flags); + object->file = file; /* Always update the atime on an object we've just looked up (this is diff --git a/fs/ceph/cache.c b/fs/ceph/cache.c index 177d8e8d73fe4..de1dee46d3df7 100644 --- a/fs/ceph/cache.c +++ b/fs/ceph/cache.c @@ -36,6 +36,8 @@ void ceph_fscache_register_inode_cookie(struct inode *inode) &ci->i_vino, sizeof(ci->i_vino), &ci->i_version, sizeof(ci->i_version), i_size_read(inode)); + if (ci->netfs.cache) + mapping_set_release_always(inode->i_mapping); } void ceph_fscache_unregister_inode_cookie(struct ceph_inode_info *ci) diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c index 044e34cd835c1..dedc9d445f243 100644 --- a/fs/ext4/move_extent.c +++ b/fs/ext4/move_extent.c @@ -253,6 +253,7 @@ move_extent_per_page(struct file *o_filp, struct inode *donor_inode, { struct inode *orig_inode = file_inode(o_filp); struct page *pagep[2] = {NULL, NULL}; + struct folio *folio[2] = {NULL, NULL}; handle_t *handle; ext4_lblk_t orig_blk_offset, donor_blk_offset; unsigned long blocksize = orig_inode->i_sb->s_blocksize; @@ -313,6 +314,13 @@ again: * hold page's lock, if it is still the case data copy is not * necessary, just swap data blocks between orig and donor. */ + folio[0] = page_folio(pagep[0]); + folio[1] = page_folio(pagep[1]); + + VM_BUG_ON_FOLIO(folio_test_large(folio[0]), folio[0]); + VM_BUG_ON_FOLIO(folio_test_large(folio[1]), folio[1]); + VM_BUG_ON_FOLIO(folio_nr_pages(folio[0]) != folio_nr_pages(folio[1]), folio[1]); + if (unwritten) { ext4_double_down_write_data_sem(orig_inode, donor_inode); /* If any of extents in range became initialized we have to @@ -331,10 +339,8 @@ again: ext4_double_up_write_data_sem(orig_inode, donor_inode); goto data_copy; } - if ((page_has_private(pagep[0]) && - !try_to_release_page(pagep[0], 0)) || - (page_has_private(pagep[1]) && - !try_to_release_page(pagep[1], 0))) { + if (!filemap_release_folio(folio[0], 0) || + !filemap_release_folio(folio[1], 0)) { *err = -EBUSY; goto drop_data_sem; } @@ -344,19 +350,19 @@ again: block_len_in_page, 1, err); drop_data_sem: ext4_double_up_write_data_sem(orig_inode, donor_inode); - goto unlock_pages; + goto unlock_folios; } data_copy: - *err = mext_page_mkuptodate(pagep[0], from, from + replaced_size); + *err = mext_page_mkuptodate(&folio[0]->page, from, from + replaced_size); if (*err) - goto unlock_pages; + goto unlock_folios; /* At this point all buffers in range are uptodate, old mapping layout * is no longer required, try to drop it now. */ - if ((page_has_private(pagep[0]) && !try_to_release_page(pagep[0], 0)) || - (page_has_private(pagep[1]) && !try_to_release_page(pagep[1], 0))) { + if (!filemap_release_folio(folio[0], 0) || + !filemap_release_folio(folio[1], 0)) { *err = -EBUSY; - goto unlock_pages; + goto unlock_folios; } ext4_double_down_write_data_sem(orig_inode, donor_inode); replaced_count = ext4_swap_extents(handle, orig_inode, donor_inode, @@ -369,13 +375,13 @@ data_copy: replaced_size = block_len_in_page << orig_inode->i_blkbits; } else - goto unlock_pages; + goto unlock_folios; } /* Perform all necessary steps similar write_begin()/write_end() * but keeping in mind that i_size will not change */ - if (!page_has_buffers(pagep[0])) - create_empty_buffers(pagep[0], 1 << orig_inode->i_blkbits, 0); - bh = page_buffers(pagep[0]); + if (!folio_buffers(folio[0])) + create_empty_buffers(&folio[0]->page, 1 << orig_inode->i_blkbits, 0); + bh = folio_buffers(folio[0]); for (i = 0; i < data_offset_in_page; i++) bh = bh->b_this_page; for (i = 0; i < block_len_in_page; i++) { @@ -385,7 +391,7 @@ data_copy: bh = bh->b_this_page; } if (!*err) - *err = block_commit_write(pagep[0], from, from + replaced_size); + *err = block_commit_write(&folio[0]->page, from, from + replaced_size); if (unlikely(*err < 0)) goto repair_branches; @@ -395,11 +401,11 @@ data_copy: *err = ext4_jbd2_inode_add_write(handle, orig_inode, (loff_t)orig_page_offset << PAGE_SHIFT, replaced_size); -unlock_pages: - unlock_page(pagep[0]); - put_page(pagep[0]); - unlock_page(pagep[1]); - put_page(pagep[1]); +unlock_folios: + folio_unlock(folio[0]); + folio_put(folio[0]); + folio_unlock(folio[1]); + folio_put(folio[1]); stop_journal: ext4_journal_stop(handle); if (*err == -ENOSPC && @@ -430,7 +436,7 @@ repair_branches: *err = -EIO; } replaced_count = 0; - goto unlock_pages; + goto unlock_folios; } /** diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c index 5df04ed010cae..eb4d69f53337f 100644 --- a/fs/f2fs/checkpoint.c +++ b/fs/f2fs/checkpoint.c @@ -984,7 +984,7 @@ int f2fs_get_valid_checkpoint(struct f2fs_sb_info *sbi) cp_blk_no = le32_to_cpu(fsb->cp_blkaddr); if (cur_page == cp2) - cp_blk_no += 1 << le32_to_cpu(fsb->log_blocks_per_seg); + cp_blk_no += BIT(le32_to_cpu(fsb->log_blocks_per_seg)); for (i = 1; i < cp_blks; i++) { void *sit_bitmap_ptr; diff --git a/fs/f2fs/compress.c b/fs/f2fs/compress.c index 11d9dce994dbe..4cb58e8d699e2 100644 --- a/fs/f2fs/compress.c +++ b/fs/f2fs/compress.c @@ -241,7 +241,7 @@ static int lz4_init_compress_ctx(struct compress_ctx *cc) unsigned int size = LZ4_MEM_COMPRESS; #ifdef CONFIG_F2FS_FS_LZ4HC - if (F2FS_I(cc->inode)->i_compress_flag >> COMPRESS_LEVEL_OFFSET) + if (F2FS_I(cc->inode)->i_compress_level) size = LZ4HC_MEM_COMPRESS; #endif @@ -267,8 +267,7 @@ static void lz4_destroy_compress_ctx(struct compress_ctx *cc) #ifdef CONFIG_F2FS_FS_LZ4HC static int lz4hc_compress_pages(struct compress_ctx *cc) { - unsigned char level = F2FS_I(cc->inode)->i_compress_flag >> - COMPRESS_LEVEL_OFFSET; + unsigned char level = F2FS_I(cc->inode)->i_compress_level; int len; if (level) @@ -332,17 +331,15 @@ static const struct f2fs_compress_ops f2fs_lz4_ops = { #endif #ifdef CONFIG_F2FS_FS_ZSTD -#define F2FS_ZSTD_DEFAULT_CLEVEL 1 - static int zstd_init_compress_ctx(struct compress_ctx *cc) { zstd_parameters params; zstd_cstream *stream; void *workspace; unsigned int workspace_size; - unsigned char level = F2FS_I(cc->inode)->i_compress_flag >> - COMPRESS_LEVEL_OFFSET; + unsigned char level = F2FS_I(cc->inode)->i_compress_level; + /* Need to remain this for backward compatibility */ if (!level) level = F2FS_ZSTD_DEFAULT_CLEVEL; @@ -675,7 +672,7 @@ static int f2fs_compress_pages(struct compress_ctx *cc) cc->cbuf->clen = cpu_to_le32(cc->clen); - if (fi->i_compress_flag & 1 << COMPRESS_CHKSUM) + if (fi->i_compress_flag & BIT(COMPRESS_CHKSUM)) chksum = f2fs_crc32(F2FS_I_SB(cc->inode), cc->cbuf->cdata, cc->clen); cc->cbuf->chksum = cpu_to_le32(chksum); @@ -773,7 +770,7 @@ void f2fs_decompress_cluster(struct decompress_io_ctx *dic, bool in_task) ret = cops->decompress_pages(dic); - if (!ret && (fi->i_compress_flag & 1 << COMPRESS_CHKSUM)) { + if (!ret && (fi->i_compress_flag & BIT(COMPRESS_CHKSUM))) { u32 provided = le32_to_cpu(dic->cbuf->chksum); u32 calculated = f2fs_crc32(sbi, dic->cbuf->cdata, dic->clen); diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index ea05710ca9bdf..3666c1fd77a64 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -95,17 +95,17 @@ static enum count_type __read_io_type(struct page *page) /* postprocessing steps for read bios */ enum bio_post_read_step { #ifdef CONFIG_FS_ENCRYPTION - STEP_DECRYPT = 1 << 0, + STEP_DECRYPT = BIT(0), #else STEP_DECRYPT = 0, /* compile out the decryption-related code */ #endif #ifdef CONFIG_F2FS_FS_COMPRESSION - STEP_DECOMPRESS = 1 << 1, + STEP_DECOMPRESS = BIT(1), #else STEP_DECOMPRESS = 0, /* compile out the decompression-related code */ #endif #ifdef CONFIG_FS_VERITY - STEP_VERITY = 1 << 2, + STEP_VERITY = BIT(2), #else STEP_VERITY = 0, /* compile out the verity-related code */ #endif @@ -409,7 +409,7 @@ int f2fs_target_device_index(struct f2fs_sb_info *sbi, block_t blkaddr) static blk_opf_t f2fs_io_flags(struct f2fs_io_info *fio) { - unsigned int temp_mask = (1 << NR_TEMP_TYPE) - 1; + unsigned int temp_mask = GENMASK(NR_TEMP_TYPE - 1, 0); unsigned int fua_flag, meta_flag, io_flag; blk_opf_t op_flags = 0; @@ -431,9 +431,9 @@ static blk_opf_t f2fs_io_flags(struct f2fs_io_info *fio) * 5 | 4 | 3 | 2 | 1 | 0 | * Cold | Warm | Hot | Cold | Warm | Hot | */ - if ((1 << fio->temp) & meta_flag) + if (BIT(fio->temp) & meta_flag) op_flags |= REQ_META; - if ((1 << fio->temp) & fua_flag) + if (BIT(fio->temp) & fua_flag) op_flags |= REQ_FUA; return op_flags; } diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c index 8373eba3a1337..510736d2ae110 100644 --- a/fs/f2fs/dir.c +++ b/fs/f2fs/dir.c @@ -29,7 +29,7 @@ static unsigned long dir_blocks(struct inode *inode) static unsigned int dir_buckets(unsigned int level, int dir_level) { if (level + dir_level < MAX_DIR_HASH_DEPTH / 2) - return 1 << (level + dir_level); + return BIT(level + dir_level); else return MAX_DIR_BUCKETS; } diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index f56abb39601ac..5c76ba764b71f 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -64,7 +64,7 @@ enum { }; #ifdef CONFIG_F2FS_FAULT_INJECTION -#define F2FS_ALL_FAULT_TYPE ((1 << FAULT_MAX) - 1) +#define F2FS_ALL_FAULT_TYPE (GENMASK(FAULT_MAX - 1, 0)) struct f2fs_fault_info { atomic_t inject_ops; @@ -73,7 +73,7 @@ struct f2fs_fault_info { }; extern const char *f2fs_fault_name[FAULT_MAX]; -#define IS_FAULT_SET(fi, type) ((fi)->inject_type & (1 << (type))) +#define IS_FAULT_SET(fi, type) ((fi)->inject_type & BIT(type)) #endif /* @@ -840,7 +840,7 @@ struct f2fs_inode_info { unsigned char i_compress_algorithm; /* algorithm type */ unsigned char i_log_cluster_size; /* log of cluster size */ unsigned char i_compress_level; /* compress level (lz4hc,zstd) */ - unsigned short i_compress_flag; /* compress flag */ + unsigned char i_compress_flag; /* compress flag */ unsigned int i_cluster_size; /* cluster size */ unsigned int atomic_write_cnt; @@ -1412,7 +1412,7 @@ static inline void set_page_private_##name(struct page *page) \ static inline void clear_page_private_##name(struct page *page) \ { \ clear_bit(PAGE_PRIVATE_##flagname, &page_private(page)); \ - if (page_private(page) == 1 << PAGE_PRIVATE_NOT_POINTER) { \ + if (page_private(page) == BIT(PAGE_PRIVATE_NOT_POINTER)) { \ set_page_private(page, 0); \ if (PagePrivate(page)) { \ ClearPagePrivate(page); \ @@ -1462,8 +1462,8 @@ static inline void set_page_private_data(struct page *page, unsigned long data) static inline void clear_page_private_data(struct page *page) { - page_private(page) &= (1 << PAGE_PRIVATE_MAX) - 1; - if (page_private(page) == 1 << PAGE_PRIVATE_NOT_POINTER) { + page_private(page) &= GENMASK(PAGE_PRIVATE_MAX - 1, 0); + if (page_private(page) == BIT(PAGE_PRIVATE_NOT_POINTER)) { set_page_private(page, 0); if (PagePrivate(page)) { ClearPagePrivate(page); @@ -1501,6 +1501,8 @@ struct compress_data { #define F2FS_COMPRESSED_PAGE_MAGIC 0xF5F2C000 +#define F2FS_ZSTD_DEFAULT_CLEVEL 1 + #define COMPRESS_LEVEL_OFFSET 8 /* compress context */ @@ -2882,7 +2884,7 @@ static inline int f2fs_test_bit(unsigned int nr, char *addr) int mask; addr += (nr >> 3); - mask = 1 << (7 - (nr & 0x07)); + mask = BIT(7 - (nr & 0x07)); return mask & *addr; } @@ -2891,7 +2893,7 @@ static inline void f2fs_set_bit(unsigned int nr, char *addr) int mask; addr += (nr >> 3); - mask = 1 << (7 - (nr & 0x07)); + mask = BIT(7 - (nr & 0x07)); *addr |= mask; } @@ -2900,7 +2902,7 @@ static inline void f2fs_clear_bit(unsigned int nr, char *addr) int mask; addr += (nr >> 3); - mask = 1 << (7 - (nr & 0x07)); + mask = BIT(7 - (nr & 0x07)); *addr &= ~mask; } @@ -2910,7 +2912,7 @@ static inline int f2fs_test_and_set_bit(unsigned int nr, char *addr) int ret; addr += (nr >> 3); - mask = 1 << (7 - (nr & 0x07)); + mask = BIT(7 - (nr & 0x07)); ret = mask & *addr; *addr |= mask; return ret; @@ -2922,7 +2924,7 @@ static inline int f2fs_test_and_clear_bit(unsigned int nr, char *addr) int ret; addr += (nr >> 3); - mask = 1 << (7 - (nr & 0x07)); + mask = BIT(7 - (nr & 0x07)); ret = mask & *addr; *addr &= ~mask; return ret; @@ -2933,7 +2935,7 @@ static inline void f2fs_change_bit(unsigned int nr, char *addr) int mask; addr += (nr >> 3); - mask = 1 << (7 - (nr & 0x07)); + mask = BIT(7 - (nr & 0x07)); *addr ^= mask; } @@ -4333,15 +4335,14 @@ static inline int set_compress_context(struct inode *inode) F2FS_OPTION(sbi).compress_log_size; F2FS_I(inode)->i_compress_flag = F2FS_OPTION(sbi).compress_chksum ? - 1 << COMPRESS_CHKSUM : 0; + BIT(COMPRESS_CHKSUM) : 0; F2FS_I(inode)->i_cluster_size = - 1 << F2FS_I(inode)->i_log_cluster_size; + BIT(F2FS_I(inode)->i_log_cluster_size); if ((F2FS_I(inode)->i_compress_algorithm == COMPRESS_LZ4 || F2FS_I(inode)->i_compress_algorithm == COMPRESS_ZSTD) && F2FS_OPTION(sbi).compress_level) - F2FS_I(inode)->i_compress_flag |= - F2FS_OPTION(sbi).compress_level << - COMPRESS_LEVEL_OFFSET; + F2FS_I(inode)->i_compress_level = + F2FS_OPTION(sbi).compress_level; F2FS_I(inode)->i_flags |= F2FS_COMPR_FL; set_inode_flag(inode, FI_COMPRESSED_FILE); stat_inc_compr_inode(inode); diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index d0c17366ebf48..9b9fb3c57ec6c 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -3983,7 +3983,16 @@ static int f2fs_ioc_set_compress_option(struct file *filp, unsigned long arg) F2FS_I(inode)->i_compress_algorithm = option.algorithm; F2FS_I(inode)->i_log_cluster_size = option.log_cluster_size; - F2FS_I(inode)->i_cluster_size = 1 << option.log_cluster_size; + F2FS_I(inode)->i_cluster_size = BIT(option.log_cluster_size); + /* Set default level */ + if (F2FS_I(inode)->i_compress_algorithm == COMPRESS_ZSTD) + F2FS_I(inode)->i_compress_level = F2FS_ZSTD_DEFAULT_CLEVEL; + else + F2FS_I(inode)->i_compress_level = 0; + /* Adjust mount option level */ + if (option.algorithm == F2FS_OPTION(sbi).compress_algorithm && + F2FS_OPTION(sbi).compress_level) + F2FS_I(inode)->i_compress_level = F2FS_OPTION(sbi).compress_level; f2fs_mark_inode_dirty_sync(inode, true); if (!f2fs_is_compress_backend_ready(inode)) diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c index 1fc7760499f10..0010579f17368 100644 --- a/fs/f2fs/inode.c +++ b/fs/f2fs/inode.c @@ -450,12 +450,18 @@ static int do_read_inode(struct inode *inode) (fi->i_flags & F2FS_COMPR_FL)) { if (F2FS_FITS_IN_INODE(ri, fi->i_extra_isize, i_log_cluster_size)) { + unsigned short compress_flag; + atomic_set(&fi->i_compr_blocks, le64_to_cpu(ri->i_compr_blocks)); fi->i_compress_algorithm = ri->i_compress_algorithm; fi->i_log_cluster_size = ri->i_log_cluster_size; - fi->i_compress_flag = le16_to_cpu(ri->i_compress_flag); - fi->i_cluster_size = 1 << fi->i_log_cluster_size; + compress_flag = le16_to_cpu(ri->i_compress_flag); + fi->i_compress_level = compress_flag >> + COMPRESS_LEVEL_OFFSET; + fi->i_compress_flag = compress_flag & + GENMASK(COMPRESS_LEVEL_OFFSET - 1, 0); + fi->i_cluster_size = BIT(fi->i_log_cluster_size); set_inode_flag(inode, FI_COMPRESSED_FILE); } } @@ -675,13 +681,17 @@ void f2fs_update_inode(struct inode *inode, struct page *node_page) if (f2fs_sb_has_compression(F2FS_I_SB(inode)) && F2FS_FITS_IN_INODE(ri, F2FS_I(inode)->i_extra_isize, i_log_cluster_size)) { + unsigned short compress_flag; + ri->i_compr_blocks = cpu_to_le64(atomic_read( &F2FS_I(inode)->i_compr_blocks)); ri->i_compress_algorithm = F2FS_I(inode)->i_compress_algorithm; - ri->i_compress_flag = - cpu_to_le16(F2FS_I(inode)->i_compress_flag); + compress_flag = F2FS_I(inode)->i_compress_flag | + F2FS_I(inode)->i_compress_level << + COMPRESS_LEVEL_OFFSET; + ri->i_compress_flag = cpu_to_le16(compress_flag); ri->i_log_cluster_size = F2FS_I(inode)->i_log_cluster_size; } diff --git a/fs/f2fs/node.h b/fs/f2fs/node.h index 0aa48704c77a0..7068f3ac036a5 100644 --- a/fs/f2fs/node.h +++ b/fs/f2fs/node.h @@ -93,17 +93,15 @@ static inline void copy_node_info(struct node_info *dst, static inline void set_nat_flag(struct nat_entry *ne, unsigned int type, bool set) { - unsigned char mask = 0x01 << type; if (set) - ne->ni.flag |= mask; + ne->ni.flag |= BIT(type); else - ne->ni.flag &= ~mask; + ne->ni.flag &= ~BIT(type); } static inline bool get_nat_flag(struct nat_entry *ne, unsigned int type) { - unsigned char mask = 0x01 << type; - return ne->ni.flag & mask; + return ne->ni.flag & BIT(type); } static inline void nat_reset_flag(struct nat_entry *ne) @@ -224,7 +222,7 @@ static inline pgoff_t next_nat_addr(struct f2fs_sb_info *sbi, struct f2fs_nm_info *nm_i = NM_I(sbi); block_addr -= nm_i->nat_blkaddr; - block_addr ^= 1 << sbi->log_blocks_per_seg; + block_addr ^= BIT(sbi->log_blocks_per_seg); return block_addr + nm_i->nat_blkaddr; } @@ -394,7 +392,7 @@ static inline nid_t get_nid(struct page *p, int off, bool i) static inline int is_node(struct page *page, int type) { struct f2fs_node *rn = F2FS_NODE(page); - return le32_to_cpu(rn->footer.flag) & (1 << type); + return le32_to_cpu(rn->footer.flag) & BIT(type); } #define is_cold_node(page) is_node(page, COLD_BIT_SHIFT) @@ -407,9 +405,9 @@ static inline void set_cold_node(struct page *page, bool is_dir) unsigned int flag = le32_to_cpu(rn->footer.flag); if (is_dir) - flag &= ~(0x1 << COLD_BIT_SHIFT); + flag &= ~BIT(COLD_BIT_SHIFT); else - flag |= (0x1 << COLD_BIT_SHIFT); + flag |= BIT(COLD_BIT_SHIFT); rn->footer.flag = cpu_to_le32(flag); } @@ -418,9 +416,9 @@ static inline void set_mark(struct page *page, int mark, int type) struct f2fs_node *rn = F2FS_NODE(page); unsigned int flag = le32_to_cpu(rn->footer.flag); if (mark) - flag |= (0x1 << type); + flag |= BIT(type); else - flag &= ~(0x1 << type); + flag &= ~BIT(type); rn->footer.flag = cpu_to_le32(flag); #ifdef CONFIG_F2FS_CHECK_FS diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index 1ba85ef97cbd3..3805162dcef2b 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -613,14 +613,12 @@ static int f2fs_set_lz4hc_level(struct f2fs_sb_info *sbi, const char *str) { #ifdef CONFIG_F2FS_FS_LZ4HC unsigned int level; -#endif if (strlen(str) == 3) { F2FS_OPTION(sbi).compress_level = 0; return 0; } -#ifdef CONFIG_F2FS_FS_LZ4HC str += 3; if (str[0] != ':') { @@ -638,6 +636,10 @@ static int f2fs_set_lz4hc_level(struct f2fs_sb_info *sbi, const char *str) F2FS_OPTION(sbi).compress_level = level; return 0; #else + if (strlen(str) == 3) { + F2FS_OPTION(sbi).compress_level = 0; + return 0; + } f2fs_info(sbi, "kernel doesn't support lz4hc compression"); return -EINVAL; #endif @@ -651,7 +653,7 @@ static int f2fs_set_zstd_level(struct f2fs_sb_info *sbi, const char *str) int len = 4; if (strlen(str) == len) { - F2FS_OPTION(sbi).compress_level = 0; + F2FS_OPTION(sbi).compress_level = F2FS_ZSTD_DEFAULT_CLEVEL; return 0; } @@ -664,7 +666,7 @@ static int f2fs_set_zstd_level(struct f2fs_sb_info *sbi, const char *str) if (kstrtouint(str + 1, 10, &level)) return -EINVAL; - if (!level || level > zstd_max_clevel()) { + if (level < zstd_min_clevel() || level > zstd_max_clevel()) { f2fs_info(sbi, "invalid zstd compress level: %d", level); return -EINVAL; } @@ -898,8 +900,8 @@ static int parse_options(struct super_block *sb, char *options, bool is_remount) if (args->from && match_int(args, &arg)) return -EINVAL; if (arg <= 0 || arg > __ilog2_u32(BIO_MAX_VECS)) { - f2fs_warn(sbi, "Not support %d, larger than %d", - 1 << arg, BIO_MAX_VECS); + f2fs_warn(sbi, "Not support %ld, larger than %d", + BIT(arg), BIO_MAX_VECS); return -EINVAL; } F2FS_OPTION(sbi).write_io_size_bits = arg; @@ -1340,7 +1342,7 @@ default_check: #endif if (F2FS_IO_SIZE_BITS(sbi) && !f2fs_lfs_mode(sbi)) { - f2fs_err(sbi, "Should set mode=lfs with %uKB-sized IO", + f2fs_err(sbi, "Should set mode=lfs with %luKB-sized IO", F2FS_IO_SIZE_KB(sbi)); return -EINVAL; } @@ -3356,7 +3358,7 @@ static int sanity_check_raw_super(struct f2fs_sb_info *sbi, total_sections = le32_to_cpu(raw_super->section_count); /* blocks_per_seg should be 512, given the above check */ - blocks_per_seg = 1 << le32_to_cpu(raw_super->log_blocks_per_seg); + blocks_per_seg = BIT(le32_to_cpu(raw_super->log_blocks_per_seg)); if (segment_count > F2FS_MAX_SEGMENT || segment_count < F2FS_MIN_SEGMENTS) { @@ -3625,9 +3627,9 @@ static void init_sb_info(struct f2fs_sb_info *sbi) sbi->log_sectors_per_block = le32_to_cpu(raw_super->log_sectors_per_block); sbi->log_blocksize = le32_to_cpu(raw_super->log_blocksize); - sbi->blocksize = 1 << sbi->log_blocksize; + sbi->blocksize = BIT(sbi->log_blocksize); sbi->log_blocks_per_seg = le32_to_cpu(raw_super->log_blocks_per_seg); - sbi->blocks_per_seg = 1 << sbi->log_blocks_per_seg; + sbi->blocks_per_seg = BIT(sbi->log_blocks_per_seg); sbi->segs_per_sec = le32_to_cpu(raw_super->segs_per_sec); sbi->secs_per_zone = le32_to_cpu(raw_super->secs_per_zone); sbi->total_sections = le32_to_cpu(raw_super->section_count); @@ -3883,7 +3885,7 @@ void f2fs_handle_stop(struct f2fs_sb_info *sbi, unsigned char reason) f2fs_down_write(&sbi->sb_lock); - if (raw_super->s_stop_reason[reason] < ((1 << BITS_PER_BYTE) - 1)) + if (raw_super->s_stop_reason[reason] < GENMASK(BITS_PER_BYTE - 1, 0)) raw_super->s_stop_reason[reason]++; err = f2fs_commit_super(sbi, false); @@ -4033,7 +4035,7 @@ static int f2fs_scan_devices(struct f2fs_sb_info *sbi) FDEV(i).start_blk, FDEV(i).end_blk); } f2fs_info(sbi, - "IO Block Size: %8d KB", F2FS_IO_SIZE_KB(sbi)); + "IO Block Size: %8ld KB", F2FS_IO_SIZE_KB(sbi)); return 0; } diff --git a/fs/f2fs/sysfs.c b/fs/f2fs/sysfs.c index 3d68bfa75cf2a..751a108e612ff 100644 --- a/fs/f2fs/sysfs.c +++ b/fs/f2fs/sysfs.c @@ -451,7 +451,7 @@ out: if (ret < 0) return ret; #ifdef CONFIG_F2FS_FAULT_INJECTION - if (a->struct_type == FAULT_INFO_TYPE && t >= (1 << FAULT_MAX)) + if (a->struct_type == FAULT_INFO_TYPE && t >= BIT(FAULT_MAX)) return -EINVAL; if (a->struct_type == FAULT_INFO_RATE && t >= UINT_MAX) return -EINVAL; diff --git a/fs/inode.c b/fs/inode.c index 73ad1b0d47758..8cfda7a6d5900 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -215,6 +215,8 @@ int inode_init_always(struct super_block *sb, struct inode *inode) lockdep_set_class_and_name(&mapping->invalidate_lock, &sb->s_type->invalidate_lock_key, "mapping.invalidate_lock"); + if (sb->s_iflags & SB_I_STABLE_WRITES) + mapping_set_stable_writes(mapping); inode->i_private = NULL; inode->i_mapping = mapping; INIT_HLIST_HEAD(&inode->i_dentry); /* buggered by rcu freeing */ diff --git a/fs/nfs/fscache.c b/fs/nfs/fscache.c index e731c00a9fcbc..d3c938dd2b12a 100644 --- a/fs/nfs/fscache.c +++ b/fs/nfs/fscache.c @@ -176,6 +176,9 @@ void nfs_fscache_init_inode(struct inode *inode) &auxdata, /* aux_data */ sizeof(auxdata), i_size_read(inode)); + + if (netfs_inode(inode)->cache) + mapping_set_release_always(inode->i_mapping); } /* diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h index 512ac9dea9787..7f1aea4c11b9c 100644 --- a/fs/smb/client/cifsglob.h +++ b/fs/smb/client/cifsglob.h @@ -972,7 +972,6 @@ release_iface(struct kref *ref) struct cifs_server_iface *iface = container_of(ref, struct cifs_server_iface, refcount); - list_del_init(&iface->iface_head); kfree(iface); } diff --git a/fs/smb/client/connect.c b/fs/smb/client/connect.c index f725a119ce312..49fdc6dfdcf8d 100644 --- a/fs/smb/client/connect.c +++ b/fs/smb/client/connect.c @@ -258,10 +258,13 @@ cifs_mark_tcp_ses_conns_for_reconnect(struct TCP_Server_Info *server, spin_lock(&cifs_tcp_ses_lock); list_for_each_entry_safe(ses, nses, &pserver->smb_ses_list, smb_ses_list) { /* check if iface is still active */ - if (!cifs_chan_is_iface_active(ses, server)) + spin_lock(&ses->chan_lock); + if (!cifs_chan_is_iface_active(ses, server)) { + spin_unlock(&ses->chan_lock); cifs_chan_update_iface(ses, server); + spin_lock(&ses->chan_lock); + } - spin_lock(&ses->chan_lock); if (!mark_smb_session && cifs_chan_needs_reconnect(ses, server)) { spin_unlock(&ses->chan_lock); continue; diff --git a/fs/smb/client/fscache.c b/fs/smb/client/fscache.c index e73625b5d0cc6..f64bad513ba6d 100644 --- a/fs/smb/client/fscache.c +++ b/fs/smb/client/fscache.c @@ -108,6 +108,8 @@ void cifs_fscache_get_inode_cookie(struct inode *inode) &cifsi->uniqueid, sizeof(cifsi->uniqueid), &cd, sizeof(cd), i_size_read(&cifsi->netfs.inode)); + if (cifsi->netfs.cache) + mapping_set_release_always(inode->i_mapping); } void cifs_fscache_unuse_inode_cookie(struct inode *inode, bool update) diff --git a/fs/smb/client/inode.c b/fs/smb/client/inode.c index 7be51f9d2fa18..5343898bac8a6 100644 --- a/fs/smb/client/inode.c +++ b/fs/smb/client/inode.c @@ -264,7 +264,7 @@ cifs_unix_basic_to_fattr(struct cifs_fattr *fattr, FILE_UNIX_BASIC_INFO *info, fattr->cf_dtype = DT_REG; break; case UNIX_SYMLINK: - fattr->cf_mode |= S_IFLNK; + fattr->cf_mode |= S_IFLNK | cifs_sb->ctx->file_mode; fattr->cf_dtype = DT_LNK; break; case UNIX_DIR: diff --git a/fs/smb/client/smb2file.c b/fs/smb/client/smb2file.c index ba6cc50af390f..a7475bc05cac0 100644 --- a/fs/smb/client/smb2file.c +++ b/fs/smb/client/smb2file.c @@ -34,7 +34,7 @@ static struct smb2_symlink_err_rsp *symlink_data(const struct kvec *iov) len = (u32)err->ErrorContextCount * (offsetof(struct smb2_error_context_rsp, ErrorContextData) + sizeof(struct smb2_symlink_err_rsp)); - if (le32_to_cpu(err->ByteCount) < len || iov->iov_len < len + sizeof(*err)) + if (le32_to_cpu(err->ByteCount) < len || iov->iov_len < len + sizeof(*err) + 1) return ERR_PTR(-EINVAL); p = (struct smb2_error_context_rsp *)err->ErrorData; diff --git a/fs/smb/client/smb2misc.c b/fs/smb/client/smb2misc.c index 88942b1fb4318..fdf7a7f188c5f 100644 --- a/fs/smb/client/smb2misc.c +++ b/fs/smb/client/smb2misc.c @@ -113,7 +113,7 @@ static __u32 get_neg_ctxt_len(struct smb2_hdr *hdr, __u32 len, } else if (nc_offset + 1 == non_ctxlen) { cifs_dbg(FYI, "no SPNEGO security blob in negprot rsp\n"); size_of_pad_before_neg_ctxts = 0; - } else if (non_ctxlen == SMB311_NEGPROT_BASE_SIZE) + } else if (non_ctxlen == SMB311_NEGPROT_BASE_SIZE + 1) /* has padding, but no SPNEGO blob */ size_of_pad_before_neg_ctxts = nc_offset - non_ctxlen + 1; else diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c index df03d80ab6d5f..4596d2dfdec3a 100644 --- a/fs/smb/client/smb2ops.c +++ b/fs/smb/client/smb2ops.c @@ -588,16 +588,12 @@ parse_server_interfaces(struct network_interface_info_ioctl_rsp *buf, } /* - * Go through iface_list and do kref_put to remove - * any unused ifaces. ifaces in use will be removed - * when the last user calls a kref_put on it + * Go through iface_list and mark them as inactive */ list_for_each_entry_safe(iface, niface, &ses->iface_list, - iface_head) { + iface_head) iface->is_active = 0; - kref_put(&iface->refcount, release_iface); - ses->iface_count--; - } + spin_unlock(&ses->iface_lock); /* @@ -672,10 +668,7 @@ parse_server_interfaces(struct network_interface_info_ioctl_rsp *buf, iface_head) { ret = iface_cmp(iface, &tmp_iface); if (!ret) { - /* just get a ref so that it doesn't get picked/freed */ iface->is_active = 1; - kref_get(&iface->refcount); - ses->iface_count++; spin_unlock(&ses->iface_lock); goto next_iface; } else if (ret < 0) { @@ -742,6 +735,20 @@ next_iface: } out: + /* + * Go through the list again and put the inactive entries + */ + spin_lock(&ses->iface_lock); + list_for_each_entry_safe(iface, niface, &ses->iface_list, + iface_head) { + if (!iface->is_active) { + list_del(&iface->iface_head); + kref_put(&iface->refcount, release_iface); + ses->iface_count--; + } + } + spin_unlock(&ses->iface_lock); + return rc; } @@ -778,9 +785,14 @@ SMB3_request_interfaces(const unsigned int xid, struct cifs_tcon *tcon, bool in_ goto out; /* check if iface is still active */ + spin_lock(&ses->chan_lock); pserver = ses->chans[0].server; - if (pserver && !cifs_chan_is_iface_active(ses, pserver)) + if (pserver && !cifs_chan_is_iface_active(ses, pserver)) { + spin_unlock(&ses->chan_lock); cifs_chan_update_iface(ses, pserver); + spin_lock(&ses->chan_lock); + } + spin_unlock(&ses->chan_lock); out: kfree(out_buf); @@ -5752,7 +5764,7 @@ struct smb_version_values smb20_values = { .header_size = sizeof(struct smb2_hdr), .header_preamble_size = 0, .max_header_size = MAX_SMB2_HDR_SIZE, - .read_rsp_size = sizeof(struct smb2_read_rsp) - 1, + .read_rsp_size = sizeof(struct smb2_read_rsp), .lock_cmd = SMB2_LOCK, .cap_unix = 0, .cap_nt_find = SMB2_NT_FIND, @@ -5774,7 +5786,7 @@ struct smb_version_values smb21_values = { .header_size = sizeof(struct smb2_hdr), .header_preamble_size = 0, .max_header_size = MAX_SMB2_HDR_SIZE, - .read_rsp_size = sizeof(struct smb2_read_rsp) - 1, + .read_rsp_size = sizeof(struct smb2_read_rsp), .lock_cmd = SMB2_LOCK, .cap_unix = 0, .cap_nt_find = SMB2_NT_FIND, @@ -5795,7 +5807,7 @@ struct smb_version_values smb3any_values = { .header_size = sizeof(struct smb2_hdr), .header_preamble_size = 0, .max_header_size = MAX_SMB2_HDR_SIZE, - .read_rsp_size = sizeof(struct smb2_read_rsp) - 1, + .read_rsp_size = sizeof(struct smb2_read_rsp), .lock_cmd = SMB2_LOCK, .cap_unix = 0, .cap_nt_find = SMB2_NT_FIND, @@ -5816,7 +5828,7 @@ struct smb_version_values smbdefault_values = { .header_size = sizeof(struct smb2_hdr), .header_preamble_size = 0, .max_header_size = MAX_SMB2_HDR_SIZE, - .read_rsp_size = sizeof(struct smb2_read_rsp) - 1, + .read_rsp_size = sizeof(struct smb2_read_rsp), .lock_cmd = SMB2_LOCK, .cap_unix = 0, .cap_nt_find = SMB2_NT_FIND, @@ -5837,7 +5849,7 @@ struct smb_version_values smb30_values = { .header_size = sizeof(struct smb2_hdr), .header_preamble_size = 0, .max_header_size = MAX_SMB2_HDR_SIZE, - .read_rsp_size = sizeof(struct smb2_read_rsp) - 1, + .read_rsp_size = sizeof(struct smb2_read_rsp), .lock_cmd = SMB2_LOCK, .cap_unix = 0, .cap_nt_find = SMB2_NT_FIND, @@ -5858,7 +5870,7 @@ struct smb_version_values smb302_values = { .header_size = sizeof(struct smb2_hdr), .header_preamble_size = 0, .max_header_size = MAX_SMB2_HDR_SIZE, - .read_rsp_size = sizeof(struct smb2_read_rsp) - 1, + .read_rsp_size = sizeof(struct smb2_read_rsp), .lock_cmd = SMB2_LOCK, .cap_unix = 0, .cap_nt_find = SMB2_NT_FIND, @@ -5879,7 +5891,7 @@ struct smb_version_values smb311_values = { .header_size = sizeof(struct smb2_hdr), .header_preamble_size = 0, .max_header_size = MAX_SMB2_HDR_SIZE, - .read_rsp_size = sizeof(struct smb2_read_rsp) - 1, + .read_rsp_size = sizeof(struct smb2_read_rsp), .lock_cmd = SMB2_LOCK, .cap_unix = 0, .cap_nt_find = SMB2_NT_FIND, diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c index 05ff8a457a3d7..2dfbf1b23cfa0 100644 --- a/fs/smb/client/smb2pdu.c +++ b/fs/smb/client/smb2pdu.c @@ -1386,7 +1386,7 @@ SMB2_sess_sendreceive(struct SMB2_sess_data *sess_data) /* Testing shows that buffer offset must be at location of Buffer[0] */ req->SecurityBufferOffset = - cpu_to_le16(sizeof(struct smb2_sess_setup_req) - 1 /* pad */); + cpu_to_le16(sizeof(struct smb2_sess_setup_req)); req->SecurityBufferLength = cpu_to_le16(sess_data->iov[1].iov_len); memset(&rqst, 0, sizeof(struct smb_rqst)); @@ -1905,8 +1905,7 @@ SMB2_tcon(const unsigned int xid, struct cifs_ses *ses, const char *tree, iov[0].iov_len = total_len - 1; /* Testing shows that buffer offset must be at location of Buffer[0] */ - req->PathOffset = cpu_to_le16(sizeof(struct smb2_tree_connect_req) - - 1 /* pad */); + req->PathOffset = cpu_to_le16(sizeof(struct smb2_tree_connect_req)); req->PathLength = cpu_to_le16(unc_path_len - 2); iov[1].iov_base = unc_path; iov[1].iov_len = unc_path_len; @@ -3796,7 +3795,7 @@ SMB2_change_notify(const unsigned int xid, struct cifs_tcon *tcon, ses->Suid, (u8)watch_tree, completion_filter); /* validate that notify information is plausible */ if ((rsp_iov.iov_base == NULL) || - (rsp_iov.iov_len < sizeof(struct smb2_change_notify_rsp))) + (rsp_iov.iov_len < sizeof(struct smb2_change_notify_rsp) + 1)) goto cnotify_exit; smb_rsp = (struct smb2_change_notify_rsp *)rsp_iov.iov_base; @@ -5009,7 +5008,7 @@ int SMB2_query_directory_init(const unsigned int xid, memcpy(bufptr, &asteriks, len); req->FileNameOffset = - cpu_to_le16(sizeof(struct smb2_query_directory_req) - 1); + cpu_to_le16(sizeof(struct smb2_query_directory_req)); req->FileNameLength = cpu_to_le16(len); /* * BB could be 30 bytes or so longer if we used SMB2 specific @@ -5205,8 +5204,7 @@ SMB2_set_info_init(struct cifs_tcon *tcon, struct TCP_Server_Info *server, req->VolatileFileId = volatile_fid; req->AdditionalInformation = cpu_to_le32(additional_info); - req->BufferOffset = - cpu_to_le16(sizeof(struct smb2_set_info_req) - 1); + req->BufferOffset = cpu_to_le16(sizeof(struct smb2_set_info_req)); req->BufferLength = cpu_to_le32(*size); memcpy(req->Buffer, *data, *size); @@ -5440,9 +5438,9 @@ build_qfs_info_req(struct kvec *iov, struct cifs_tcon *tcon, req->VolatileFileId = volatile_fid; /* 1 for pad */ req->InputBufferOffset = - cpu_to_le16(sizeof(struct smb2_query_info_req) - 1); + cpu_to_le16(sizeof(struct smb2_query_info_req)); req->OutputBufferLength = cpu_to_le32( - outbuf_len + sizeof(struct smb2_query_info_rsp) - 1); + outbuf_len + sizeof(struct smb2_query_info_rsp)); iov->iov_base = (char *)req; iov->iov_len = total_len; diff --git a/fs/smb/client/smb2pdu.h b/fs/smb/client/smb2pdu.h index 1237bb86e93a8..a5773a06aba8e 100644 --- a/fs/smb/client/smb2pdu.h +++ b/fs/smb/client/smb2pdu.h @@ -57,7 +57,7 @@ struct smb2_rdma_crypto_transform { #define COMPOUND_FID 0xFFFFFFFFFFFFFFFFULL #define SMB2_SYMLINK_STRUCT_SIZE \ - (sizeof(struct smb2_err_rsp) - 1 + sizeof(struct smb2_symlink_err_rsp)) + (sizeof(struct smb2_err_rsp) + sizeof(struct smb2_symlink_err_rsp)) #define SYMLINK_ERROR_TAG 0x4c4d5953 diff --git a/fs/smb/common/smb2pdu.h b/fs/smb/common/smb2pdu.h index 07549957b3099..5593bb49954c6 100644 --- a/fs/smb/common/smb2pdu.h +++ b/fs/smb/common/smb2pdu.h @@ -189,7 +189,7 @@ struct smb2_err_rsp { __u8 ErrorContextCount; __u8 Reserved; __le32 ByteCount; /* even if zero, at least one byte follows */ - __u8 ErrorData[1]; /* variable length */ + __u8 ErrorData[]; /* variable length */ } __packed; #define SMB3_AES_CCM_NONCE 11 @@ -330,7 +330,7 @@ struct smb2_tree_connect_req { __le16 Flags; /* Flags in SMB3.1.1 */ __le16 PathOffset; __le16 PathLength; - __u8 Buffer[1]; /* variable length */ + __u8 Buffer[]; /* variable length */ } __packed; /* Possible ShareType values */ @@ -617,7 +617,7 @@ struct smb2_negotiate_rsp { __le16 SecurityBufferOffset; __le16 SecurityBufferLength; __le32 NegotiateContextOffset; /* Pre:SMB3.1.1 was reserved/ignored */ - __u8 Buffer[1]; /* variable length GSS security buffer */ + __u8 Buffer[]; /* variable length GSS security buffer */ } __packed; @@ -638,7 +638,7 @@ struct smb2_sess_setup_req { __le16 SecurityBufferOffset; __le16 SecurityBufferLength; __le64 PreviousSessionId; - __u8 Buffer[1]; /* variable length GSS security buffer */ + __u8 Buffer[]; /* variable length GSS security buffer */ } __packed; /* Currently defined SessionFlags */ @@ -655,7 +655,7 @@ struct smb2_sess_setup_rsp { __le16 SessionFlags; __le16 SecurityBufferOffset; __le16 SecurityBufferLength; - __u8 Buffer[1]; /* variable length GSS security buffer */ + __u8 Buffer[]; /* variable length GSS security buffer */ } __packed; @@ -737,7 +737,7 @@ struct smb2_read_req { __le32 RemainingBytes; __le16 ReadChannelInfoOffset; __le16 ReadChannelInfoLength; - __u8 Buffer[1]; + __u8 Buffer[]; } __packed; /* Read flags */ @@ -752,7 +752,7 @@ struct smb2_read_rsp { __le32 DataLength; __le32 DataRemaining; __le32 Flags; - __u8 Buffer[1]; + __u8 Buffer[]; } __packed; @@ -776,7 +776,7 @@ struct smb2_write_req { __le16 WriteChannelInfoOffset; __le16 WriteChannelInfoLength; __le32 Flags; - __u8 Buffer[1]; + __u8 Buffer[]; } __packed; struct smb2_write_rsp { @@ -787,7 +787,7 @@ struct smb2_write_rsp { __le32 DataLength; __le32 DataRemaining; __u32 Reserved2; - __u8 Buffer[1]; + __u8 Buffer[]; } __packed; @@ -834,7 +834,10 @@ struct smb2_lock_req { __u64 PersistentFileId; __u64 VolatileFileId; /* Followed by at least one */ - struct smb2_lock_element locks[1]; + union { + struct smb2_lock_element lock; + DECLARE_FLEX_ARRAY(struct smb2_lock_element, locks); + }; } __packed; struct smb2_lock_rsp { @@ -888,7 +891,7 @@ struct smb2_query_directory_req { __le16 FileNameOffset; __le16 FileNameLength; __le32 OutputBufferLength; - __u8 Buffer[1]; + __u8 Buffer[]; } __packed; struct smb2_query_directory_rsp { @@ -896,7 +899,7 @@ struct smb2_query_directory_rsp { __le16 StructureSize; /* Must be 9 */ __le16 OutputBufferOffset; __le32 OutputBufferLength; - __u8 Buffer[1]; + __u8 Buffer[]; } __packed; /* @@ -919,7 +922,7 @@ struct smb2_set_info_req { __le32 AdditionalInformation; __u64 PersistentFileId; __u64 VolatileFileId; - __u8 Buffer[1]; + __u8 Buffer[]; } __packed; struct smb2_set_info_rsp { @@ -974,7 +977,7 @@ struct smb2_change_notify_rsp { __le16 StructureSize; /* Must be 9 */ __le16 OutputBufferOffset; __le32 OutputBufferLength; - __u8 Buffer[1]; /* array of file notify structs */ + __u8 Buffer[]; /* array of file notify structs */ } __packed; @@ -1180,7 +1183,7 @@ struct smb2_create_rsp { __u64 VolatileFileId; __le32 CreateContextsOffset; __le32 CreateContextsLength; - __u8 Buffer[1]; + __u8 Buffer[]; } __packed; struct create_posix { @@ -1524,7 +1527,7 @@ struct smb2_query_info_req { __le32 Flags; __u64 PersistentFileId; __u64 VolatileFileId; - __u8 Buffer[1]; + __u8 Buffer[]; } __packed; struct smb2_query_info_rsp { @@ -1532,7 +1535,7 @@ struct smb2_query_info_rsp { __le16 StructureSize; /* Must be 9 */ __le16 OutputBufferOffset; __le32 OutputBufferLength; - __u8 Buffer[1]; + __u8 Buffer[]; } __packed; /* @@ -1593,7 +1596,10 @@ struct smb2_file_all_info { /* data block encoding of response to level 18 */ __le32 Mode; __le32 AlignmentRequirement; __le32 FileNameLength; - char FileName[1]; + union { + char __pad; /* Legacy structure padding */ + DECLARE_FLEX_ARRAY(char, FileName); + }; } __packed; /* level 18 Query */ struct smb2_file_eof_info { /* encoding of request for level 10 */ diff --git a/fs/smb/server/smb2ops.c b/fs/smb/server/smb2ops.c index 535402629655e..27a9dce3e03ab 100644 --- a/fs/smb/server/smb2ops.c +++ b/fs/smb/server/smb2ops.c @@ -26,7 +26,7 @@ static struct smb_version_values smb21_server_values = { .unlock_lock_type = SMB2_LOCKFLAG_UNLOCK, .header_size = sizeof(struct smb2_hdr), .max_header_size = MAX_SMB2_HDR_SIZE, - .read_rsp_size = sizeof(struct smb2_read_rsp) - 1, + .read_rsp_size = sizeof(struct smb2_read_rsp), .lock_cmd = SMB2_LOCK, .cap_unix = 0, .cap_nt_find = SMB2_NT_FIND, @@ -52,7 +52,7 @@ static struct smb_version_values smb30_server_values = { .unlock_lock_type = SMB2_LOCKFLAG_UNLOCK, .header_size = sizeof(struct smb2_hdr), .max_header_size = MAX_SMB2_HDR_SIZE, - .read_rsp_size = sizeof(struct smb2_read_rsp) - 1, + .read_rsp_size = sizeof(struct smb2_read_rsp), .lock_cmd = SMB2_LOCK, .cap_unix = 0, .cap_nt_find = SMB2_NT_FIND, @@ -79,7 +79,7 @@ static struct smb_version_values smb302_server_values = { .unlock_lock_type = SMB2_LOCKFLAG_UNLOCK, .header_size = sizeof(struct smb2_hdr), .max_header_size = MAX_SMB2_HDR_SIZE, - .read_rsp_size = sizeof(struct smb2_read_rsp) - 1, + .read_rsp_size = sizeof(struct smb2_read_rsp), .lock_cmd = SMB2_LOCK, .cap_unix = 0, .cap_nt_find = SMB2_NT_FIND, @@ -106,7 +106,7 @@ static struct smb_version_values smb311_server_values = { .unlock_lock_type = SMB2_LOCKFLAG_UNLOCK, .header_size = sizeof(struct smb2_hdr), .max_header_size = MAX_SMB2_HDR_SIZE, - .read_rsp_size = sizeof(struct smb2_read_rsp) - 1, + .read_rsp_size = sizeof(struct smb2_read_rsp), .lock_cmd = SMB2_LOCK, .cap_unix = 0, .cap_nt_find = SMB2_NT_FIND, diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index ea48dd06d4da3..6e5ed0ac578a6 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -294,8 +294,7 @@ int init_smb2_neg_rsp(struct ksmbd_work *work) if (server_conf.signing == KSMBD_CONFIG_OPT_MANDATORY) rsp->SecurityMode |= SMB2_NEGOTIATE_SIGNING_REQUIRED_LE; err = ksmbd_iov_pin_rsp(work, rsp, - sizeof(struct smb2_negotiate_rsp) - - sizeof(rsp->Buffer) + AUTH_GSS_LENGTH); + sizeof(struct smb2_negotiate_rsp) + AUTH_GSS_LENGTH); if (err) return err; conn->use_spnego = true; @@ -1263,9 +1262,8 @@ err_out: if (!rc) rc = ksmbd_iov_pin_rsp(work, rsp, - sizeof(struct smb2_negotiate_rsp) - - sizeof(rsp->Buffer) + - AUTH_GSS_LENGTH + neg_ctxt_len); + sizeof(struct smb2_negotiate_rsp) + + AUTH_GSS_LENGTH + neg_ctxt_len); if (rc < 0) smb2_set_err_rsp(work); return rc; diff --git a/fs/splice.c b/fs/splice.c index 5969b7a1d353a..d0230cf8ec571 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -65,8 +65,7 @@ static bool page_cache_pipe_buf_try_steal(struct pipe_inode_info *pipe, */ folio_wait_writeback(folio); - if (folio_has_private(folio) && - !filemap_release_folio(folio, GFP_KERNEL)) + if (!filemap_release_folio(folio, GFP_KERNEL)) goto out_unlock; /* @@ -764,6 +763,17 @@ static long do_splice_from(struct pipe_inode_info *pipe, struct file *out, return out->f_op->splice_write(pipe, out, ppos, len, flags); } +/* + * Indicate to the caller that there was a premature EOF when reading from the + * source and the caller didn't indicate they would be sending more data after + * this. + */ +static void do_splice_eof(struct splice_desc *sd) +{ + if (sd->splice_eof) + sd->splice_eof(sd); +} + /* * Attempt to initiate a splice from a file to a pipe. */ @@ -864,7 +874,7 @@ ssize_t splice_direct_to_actor(struct file *in, struct splice_desc *sd, ret = do_splice_to(in, &pos, pipe, len, flags); if (unlikely(ret <= 0)) - goto out_release; + goto read_failure; read_len = ret; sd->total_len = read_len; @@ -904,6 +914,15 @@ done: file_accessed(in); return bytes; +read_failure: + /* + * If the user did *not* set SPLICE_F_MORE *and* we didn't hit that + * "use all of len" case that cleared SPLICE_F_MORE, *and* we did a + * "->splice_in()" that returned EOF (ie zero) *and* we have sent at + * least 1 byte *then* we will also do the ->splice_eof() call. + */ + if (ret == 0 && !more && len > 0 && bytes) + do_splice_eof(sd); out_release: /* * If we did an incomplete transfer we must release @@ -932,6 +951,14 @@ static int direct_splice_actor(struct pipe_inode_info *pipe, sd->flags); } +static void direct_file_splice_eof(struct splice_desc *sd) +{ + struct file *file = sd->u.file; + + if (file->f_op->splice_eof) + file->f_op->splice_eof(file); +} + /** * do_splice_direct - splices data directly between two files * @in: file to splice from @@ -957,6 +984,7 @@ long do_splice_direct(struct file *in, loff_t *ppos, struct file *out, .flags = flags, .pos = *ppos, .u.file = out, + .splice_eof = direct_file_splice_eof, .opos = opos, }; long ret; diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 3ce9e39ecdb85..ba22cf4f5fc0e 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -702,10 +702,14 @@ bpf_ctx_record_field_size(struct bpf_insn_access_aux *aux, u32 size) aux->ctx_field_size = size; } +static bool bpf_is_ldimm64(const struct bpf_insn *insn) +{ + return insn->code == (BPF_LD | BPF_IMM | BPF_DW); +} + static inline bool bpf_pseudo_func(const struct bpf_insn *insn) { - return insn->code == (BPF_LD | BPF_IMM | BPF_DW) && - insn->src_reg == BPF_PSEUDO_FUNC; + return bpf_is_ldimm64(insn) && insn->src_reg == BPF_PSEUDO_FUNC; } struct bpf_prog_ops { @@ -825,6 +829,11 @@ struct btf_func_model { */ #define BPF_TRAMP_F_SHARE_IPMODIFY BIT(6) +/* Indicate that current trampoline is in a tail call context. Then, it has to + * cache and restore tail_call_cnt to avoid infinite tail call loop. + */ +#define BPF_TRAMP_F_TAIL_CALL_CTX BIT(7) + /* Each call __bpf_prog_enter + call bpf_func + call __bpf_prog_exit is ~50 * bytes on x86. */ diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 1a32baa78ce26..f080ccf27d256 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -429,6 +429,7 @@ struct bpf_insn_aux_data { /* below fields are initialized once */ unsigned int orig_idx; /* original instruction index */ bool prune_point; + bool jmp_point; }; #define MAX_USED_MAPS 64 /* max number of maps accessed by one eBPF program */ diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h index ee0d75d9a302d..1e0df607e40c4 100644 --- a/include/linux/f2fs_fs.h +++ b/include/linux/f2fs_fs.h @@ -40,9 +40,8 @@ #define F2FS_ENC_UTF8_12_1 1 -#define F2FS_IO_SIZE(sbi) (1 << F2FS_OPTION(sbi).write_io_size_bits) /* Blocks */ -#define F2FS_IO_SIZE_KB(sbi) (1 << (F2FS_OPTION(sbi).write_io_size_bits + 2)) /* KB */ -#define F2FS_IO_SIZE_BYTES(sbi) (1 << (F2FS_OPTION(sbi).write_io_size_bits + 12)) /* B */ +#define F2FS_IO_SIZE(sbi) BIT(F2FS_OPTION(sbi).write_io_size_bits) /* Blocks */ +#define F2FS_IO_SIZE_KB(sbi) BIT(F2FS_OPTION(sbi).write_io_size_bits + 2) /* KB */ #define F2FS_IO_SIZE_BITS(sbi) (F2FS_OPTION(sbi).write_io_size_bits) /* power of 2 */ #define F2FS_IO_SIZE_MASK(sbi) (F2FS_IO_SIZE(sbi) - 1) #define F2FS_IO_ALIGNED(sbi) (F2FS_IO_SIZE(sbi) > 1) @@ -340,7 +339,7 @@ enum { OFFSET_BIT_SHIFT }; -#define OFFSET_BIT_MASK (0x07) /* (0x01 << OFFSET_BIT_SHIFT) - 1 */ +#define OFFSET_BIT_MASK GENMASK(OFFSET_BIT_SHIFT - 1, 0) struct node_footer { __le32 nid; /* node id */ @@ -545,7 +544,7 @@ typedef __le32 f2fs_hash_t; #define MAX_DIR_HASH_DEPTH 63 /* MAX buckets in one level of dir */ -#define MAX_DIR_BUCKETS (1 << ((MAX_DIR_HASH_DEPTH / 2) - 1)) +#define MAX_DIR_BUCKETS BIT((MAX_DIR_HASH_DEPTH / 2) - 1) /* * space utilization of regular dentry and inline dentry (w/o extra reservation) diff --git a/include/linux/fs.h b/include/linux/fs.h index b6af6abc7a77f..4a1911dcf834b 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2177,6 +2177,7 @@ struct file_operations { int (*flock) (struct file *, int, struct file_lock *); ssize_t (*splice_write)(struct pipe_inode_info *, struct file *, loff_t *, size_t, unsigned int); ssize_t (*splice_read)(struct file *, loff_t *, struct pipe_inode_info *, size_t, unsigned int); + void (*splice_eof)(struct file *file); int (*setlease)(struct file *, long, struct file_lock **, void **); long (*fallocate)(struct file *file, int mode, loff_t offset, loff_t len); diff --git a/include/linux/group_cpus.h b/include/linux/group_cpus.h new file mode 100644 index 0000000000000..e42807ec61f6e --- /dev/null +++ b/include/linux/group_cpus.h @@ -0,0 +1,14 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2016 Thomas Gleixner. + * Copyright (C) 2016-2017 Christoph Hellwig. + */ + +#ifndef __LINUX_GROUP_CPUS_H +#define __LINUX_GROUP_CPUS_H +#include +#include + +struct cpumask *group_cpus_evenly(unsigned int numgrps); + +#endif diff --git a/include/linux/net.h b/include/linux/net.h index 18d942bbdf6e0..25baca60f6cba 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -209,6 +209,7 @@ struct proto_ops { int offset, size_t size, int flags); ssize_t (*splice_read)(struct socket *sock, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags); + void (*splice_eof)(struct socket *sock); int (*set_peek_off)(struct sock *sk, int val); int (*peek_len)(struct socket *sock); diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 03307b72de6c6..1be5a1fa6a3a8 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -199,6 +199,9 @@ enum mapping_flags { /* writeback related tags are not used */ AS_NO_WRITEBACK_TAGS = 5, AS_LARGE_FOLIO_SUPPORT = 6, + AS_RELEASE_ALWAYS, /* Call ->release_folio(), even if no private data */ + AS_STABLE_WRITES, /* must wait for writeback before modifying + folio contents */ }; /** @@ -269,6 +272,36 @@ static inline int mapping_use_writeback_tags(struct address_space *mapping) return !test_bit(AS_NO_WRITEBACK_TAGS, &mapping->flags); } +static inline bool mapping_release_always(const struct address_space *mapping) +{ + return test_bit(AS_RELEASE_ALWAYS, &mapping->flags); +} + +static inline void mapping_set_release_always(struct address_space *mapping) +{ + set_bit(AS_RELEASE_ALWAYS, &mapping->flags); +} + +static inline void mapping_clear_release_always(struct address_space *mapping) +{ + clear_bit(AS_RELEASE_ALWAYS, &mapping->flags); +} + +static inline bool mapping_stable_writes(const struct address_space *mapping) +{ + return test_bit(AS_STABLE_WRITES, &mapping->flags); +} + +static inline void mapping_set_stable_writes(struct address_space *mapping) +{ + set_bit(AS_STABLE_WRITES, &mapping->flags); +} + +static inline void mapping_clear_stable_writes(struct address_space *mapping) +{ + clear_bit(AS_STABLE_WRITES, &mapping->flags); +} + static inline gfp_t mapping_gfp_mask(struct address_space * mapping) { return mapping->gfp_mask; diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index c1637515a8a41..c953b8c0d2f43 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -106,6 +106,7 @@ struct sk_psock { struct mutex work_mutex; struct sk_psock_work_state work_state; struct delayed_work work; + struct sock *sk_pair; struct rcu_work rwork; }; diff --git a/include/linux/socket.h b/include/linux/socket.h index 1db29aab8f9c3..b3c58042bd254 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -324,6 +324,7 @@ struct ucred { */ #define MSG_ZEROCOPY 0x4000000 /* Use user data in kernel path */ +#define MSG_SPLICE_PAGES 0x8000000 /* Splice the pages from the iterator in sendmsg() */ #define MSG_FASTOPEN 0x20000000 /* Send data in TCP SYN */ #define MSG_CMSG_CLOEXEC 0x40000000 /* Set close_on_exec for file descriptor received through @@ -334,6 +335,8 @@ struct ucred { #define MSG_CMSG_COMPAT 0 /* We never have 32 bit fixups */ #endif +/* Flags to be cleared on entry by sendmsg and sendmmsg syscalls */ +#define MSG_INTERNAL_SENDMSG_FLAGS (MSG_SPLICE_PAGES) /* Setsockoptions(2) level. Thanks to BSD these must match IPPROTO_xxx */ #define SOL_IP 0 diff --git a/include/linux/splice.h b/include/linux/splice.h index a55179fd60fc3..41a70687be853 100644 --- a/include/linux/splice.h +++ b/include/linux/splice.h @@ -38,6 +38,7 @@ struct splice_desc { struct file *file; /* file to read/write */ void *data; /* cookie */ } u; + void (*splice_eof)(struct splice_desc *sd); /* Unexpected EOF handler */ loff_t pos; /* file position */ loff_t *opos; /* sendfile: output position */ size_t num_spliced; /* number of bytes already spliced */ diff --git a/include/linux/udp.h b/include/linux/udp.h index e96da4157d04d..efd9ab6df3797 100644 --- a/include/linux/udp.h +++ b/include/linux/udp.h @@ -30,25 +30,33 @@ static inline u32 udp_hashfn(const struct net *net, u32 num, u32 mask) return (num + net_hash_mix(net)) & mask; } +enum { + UDP_FLAGS_CORK, /* Cork is required */ + UDP_FLAGS_NO_CHECK6_TX, /* Send zero UDP6 checksums on TX? */ + UDP_FLAGS_NO_CHECK6_RX, /* Allow zero UDP6 checksums on RX? */ + UDP_FLAGS_GRO_ENABLED, /* Request GRO aggregation */ + UDP_FLAGS_ACCEPT_FRAGLIST, + UDP_FLAGS_ACCEPT_L4, + UDP_FLAGS_ENCAP_ENABLED, /* This socket enabled encap */ +}; + struct udp_sock { /* inet_sock has to be the first member */ struct inet_sock inet; #define udp_port_hash inet.sk.__sk_common.skc_u16hashes[0] #define udp_portaddr_hash inet.sk.__sk_common.skc_u16hashes[1] #define udp_portaddr_node inet.sk.__sk_common.skc_portaddr_node + + unsigned long udp_flags; + int pending; /* Any pending frames ? */ - unsigned int corkflag; /* Cork is required */ __u8 encap_type; /* Is this an Encapsulation socket? */ - unsigned char no_check6_tx:1,/* Send zero UDP6 checksums on TX? */ - no_check6_rx:1,/* Allow zero UDP6 checksums on RX? */ - encap_enabled:1, /* This socket enabled encap - * processing; UDP tunnels and - * different encapsulation layer set - * this - */ - gro_enabled:1, /* Request GRO aggregation */ - accept_udp_l4:1, - accept_udp_fraglist:1; + +/* indicator bits used by pcflag: */ +#define UDPLITE_BIT 0x1 /* set by udplite proto init function */ +#define UDPLITE_SEND_CC 0x2 /* set via udplite setsockopt */ +#define UDPLITE_RECV_CC 0x4 /* set via udplite setsocktopt */ + __u8 pcflag; /* marks socket as UDP-Lite if > 0 */ /* * Following member retains the information to create a UDP header * when the socket is uncorked. @@ -60,12 +68,6 @@ struct udp_sock { */ __u16 pcslen; __u16 pcrlen; -/* indicator bits used by pcflag: */ -#define UDPLITE_BIT 0x1 /* set by udplite proto init function */ -#define UDPLITE_SEND_CC 0x2 /* set via udplite setsockopt */ -#define UDPLITE_RECV_CC 0x4 /* set via udplite setsocktopt */ - __u8 pcflag; /* marks socket as UDP-Lite if > 0 */ - __u8 unused[3]; /* * For encapsulation sockets. */ @@ -89,6 +91,17 @@ struct udp_sock { int forward_deficit; }; +#define udp_test_bit(nr, sk) \ + test_bit(UDP_FLAGS_##nr, &udp_sk(sk)->udp_flags) +#define udp_set_bit(nr, sk) \ + set_bit(UDP_FLAGS_##nr, &udp_sk(sk)->udp_flags) +#define udp_test_and_set_bit(nr, sk) \ + test_and_set_bit(UDP_FLAGS_##nr, &udp_sk(sk)->udp_flags) +#define udp_clear_bit(nr, sk) \ + clear_bit(UDP_FLAGS_##nr, &udp_sk(sk)->udp_flags) +#define udp_assign_bit(nr, sk, val) \ + assign_bit(UDP_FLAGS_##nr, &udp_sk(sk)->udp_flags, val) + #define UDP_MAX_SEGMENTS (1 << 6UL) static inline struct udp_sock *udp_sk(const struct sock *sk) @@ -98,22 +111,22 @@ static inline struct udp_sock *udp_sk(const struct sock *sk) static inline void udp_set_no_check6_tx(struct sock *sk, bool val) { - udp_sk(sk)->no_check6_tx = val; + udp_assign_bit(NO_CHECK6_TX, sk, val); } static inline void udp_set_no_check6_rx(struct sock *sk, bool val) { - udp_sk(sk)->no_check6_rx = val; + udp_assign_bit(NO_CHECK6_RX, sk, val); } -static inline bool udp_get_no_check6_tx(struct sock *sk) +static inline bool udp_get_no_check6_tx(const struct sock *sk) { - return udp_sk(sk)->no_check6_tx; + return udp_test_bit(NO_CHECK6_TX, sk); } -static inline bool udp_get_no_check6_rx(struct sock *sk) +static inline bool udp_get_no_check6_rx(const struct sock *sk) { - return udp_sk(sk)->no_check6_rx; + return udp_test_bit(NO_CHECK6_RX, sk); } static inline void udp_cmsg_recv(struct msghdr *msg, struct sock *sk, @@ -132,10 +145,12 @@ static inline bool udp_unexpected_gso(struct sock *sk, struct sk_buff *skb) if (!skb_is_gso(skb)) return false; - if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4 && !udp_sk(sk)->accept_udp_l4) + if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4 && + !udp_test_bit(ACCEPT_L4, sk)) return true; - if (skb_shinfo(skb)->gso_type & SKB_GSO_FRAGLIST && !udp_sk(sk)->accept_udp_fraglist) + if (skb_shinfo(skb)->gso_type & SKB_GSO_FRAGLIST && + !udp_test_bit(ACCEPT_FRAGLIST, sk)) return true; return false; @@ -143,8 +158,8 @@ static inline bool udp_unexpected_gso(struct sock *sk, struct sk_buff *skb) static inline void udp_allow_gso(struct sock *sk) { - udp_sk(sk)->accept_udp_l4 = 1; - udp_sk(sk)->accept_udp_fraglist = 1; + udp_set_bit(ACCEPT_L4, sk); + udp_set_bit(ACCEPT_FRAGLIST, sk); } #define udp_portaddr_for_each_entry(__sk, list) \ diff --git a/include/net/af_unix.h b/include/net/af_unix.h index 480fa579787e5..55ca217c626b7 100644 --- a/include/net/af_unix.h +++ b/include/net/af_unix.h @@ -77,6 +77,7 @@ static inline struct unix_sock *unix_sk(const struct sock *sk) { return (struct unix_sock *)sk; } +#define unix_peer(sk) (unix_sk(sk)->peer) #define peer_wait peer_wq.wait diff --git a/include/net/inet_common.h b/include/net/inet_common.h index cec453c18f1d6..4673bbfd2811f 100644 --- a/include/net/inet_common.h +++ b/include/net/inet_common.h @@ -33,6 +33,7 @@ int inet_accept(struct socket *sock, struct socket *newsock, int flags, bool kern); int inet_send_prepare(struct sock *sk); int inet_sendmsg(struct socket *sock, struct msghdr *msg, size_t size); +void inet_splice_eof(struct socket *sock); ssize_t inet_sendpage(struct socket *sock, struct page *page, int offset, size_t size, int flags); int inet_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, diff --git a/include/net/ip.h b/include/net/ip.h index c286344628dba..c83c09c65623f 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -95,7 +95,7 @@ static inline void ipcm_init_sk(struct ipcm_cookie *ipcm, ipcm_init(ipcm); ipcm->sockc.mark = READ_ONCE(inet->sk.sk_mark); - ipcm->sockc.tsflags = inet->sk.sk_tsflags; + ipcm->sockc.tsflags = READ_ONCE(inet->sk.sk_tsflags); ipcm->oif = READ_ONCE(inet->sk.sk_bound_dev_if); ipcm->addr = inet->inet_saddr; ipcm->protocol = inet->inet_num; diff --git a/include/net/netfilter/nf_conntrack_act_ct.h b/include/net/netfilter/nf_conntrack_act_ct.h index 078d3c52c03f9..e5f2f0b73a9a0 100644 --- a/include/net/netfilter/nf_conntrack_act_ct.h +++ b/include/net/netfilter/nf_conntrack_act_ct.h @@ -20,7 +20,22 @@ static inline struct nf_conn_act_ct_ext *nf_conn_act_ct_ext_find(const struct nf #endif } -static inline struct nf_conn_act_ct_ext *nf_conn_act_ct_ext_add(struct nf_conn *ct) +static inline void nf_conn_act_ct_ext_fill(struct sk_buff *skb, struct nf_conn *ct, + enum ip_conntrack_info ctinfo) +{ +#if IS_ENABLED(CONFIG_NET_ACT_CT) + struct nf_conn_act_ct_ext *act_ct_ext; + + act_ct_ext = nf_conn_act_ct_ext_find(ct); + if (dev_net(skb->dev) == &init_net && act_ct_ext) + act_ct_ext->ifindex[CTINFO2DIR(ctinfo)] = skb->dev->ifindex; +#endif +} + +static inline struct +nf_conn_act_ct_ext *nf_conn_act_ct_ext_add(struct sk_buff *skb, + struct nf_conn *ct, + enum ip_conntrack_info ctinfo) { #if IS_ENABLED(CONFIG_NET_ACT_CT) struct nf_conn_act_ct_ext *act_ct = nf_ct_ext_find(ct, NF_CT_EXT_ACT_CT); @@ -29,22 +44,11 @@ static inline struct nf_conn_act_ct_ext *nf_conn_act_ct_ext_add(struct nf_conn * return act_ct; act_ct = nf_ct_ext_add(ct, NF_CT_EXT_ACT_CT, GFP_ATOMIC); + nf_conn_act_ct_ext_fill(skb, ct, ctinfo); return act_ct; #else return NULL; #endif } -static inline void nf_conn_act_ct_ext_fill(struct sk_buff *skb, struct nf_conn *ct, - enum ip_conntrack_info ctinfo) -{ -#if IS_ENABLED(CONFIG_NET_ACT_CT) - struct nf_conn_act_ct_ext *act_ct_ext; - - act_ct_ext = nf_conn_act_ct_ext_find(ct); - if (dev_net(skb->dev) == &init_net && act_ct_ext) - act_ct_ext->ifindex[CTINFO2DIR(ctinfo)] = skb->dev->ifindex; -#endif -} - #endif /* _NF_CONNTRACK_ACT_CT_H */ diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h index cd982f4a0f50c..dde4dd9c4012c 100644 --- a/include/net/netfilter/nf_flow_table.h +++ b/include/net/netfilter/nf_flow_table.h @@ -53,14 +53,17 @@ struct nf_flowtable_type { struct list_head list; int family; int (*init)(struct nf_flowtable *ft); + bool (*gc)(const struct flow_offload *flow); int (*setup)(struct nf_flowtable *ft, struct net_device *dev, enum flow_block_command cmd); int (*action)(struct net *net, - const struct flow_offload *flow, + struct flow_offload *flow, enum flow_offload_tuple_dir dir, struct nf_flow_rule *flow_rule); void (*free)(struct nf_flowtable *ft); + void (*get)(struct nf_flowtable *ft); + void (*put)(struct nf_flowtable *ft); nf_hookfn *hook; struct module *owner; }; @@ -164,6 +167,8 @@ enum nf_flow_flags { NF_FLOW_HW_DYING, NF_FLOW_HW_DEAD, NF_FLOW_HW_PENDING, + NF_FLOW_HW_BIDIRECTIONAL, + NF_FLOW_HW_ESTABLISHED, }; enum flow_offload_type { @@ -237,6 +242,11 @@ nf_flow_table_offload_add_cb(struct nf_flowtable *flow_table, } list_add_tail(&block_cb->list, &block->cb_list); + up_write(&flow_table->flow_block_lock); + + if (flow_table->type->get) + flow_table->type->get(flow_table); + return 0; unlock: up_write(&flow_table->flow_block_lock); @@ -259,6 +269,9 @@ nf_flow_table_offload_del_cb(struct nf_flowtable *flow_table, WARN_ON(true); } up_write(&flow_table->flow_block_lock); + + if (flow_table->type->put) + flow_table->type->put(flow_table); } int flow_offload_route_init(struct flow_offload *flow, @@ -266,7 +279,7 @@ int flow_offload_route_init(struct flow_offload *flow, int flow_offload_add(struct nf_flowtable *flow_table, struct flow_offload *flow); void flow_offload_refresh(struct nf_flowtable *flow_table, - struct flow_offload *flow); + struct flow_offload *flow, bool force); struct flow_offload_tuple_rhash *flow_offload_lookup(struct nf_flowtable *flow_table, struct flow_offload_tuple *tuple); @@ -312,10 +325,10 @@ void nf_flow_table_offload_flush_cleanup(struct nf_flowtable *flowtable); int nf_flow_table_offload_setup(struct nf_flowtable *flowtable, struct net_device *dev, enum flow_block_command cmd); -int nf_flow_rule_route_ipv4(struct net *net, const struct flow_offload *flow, +int nf_flow_rule_route_ipv4(struct net *net, struct flow_offload *flow, enum flow_offload_tuple_dir dir, struct nf_flow_rule *flow_rule); -int nf_flow_rule_route_ipv6(struct net *net, const struct flow_offload *flow, +int nf_flow_rule_route_ipv6(struct net *net, struct flow_offload *flow, enum flow_offload_tuple_dir dir, struct nf_flow_rule *flow_rule); diff --git a/include/net/netfilter/nf_tables_ipv4.h b/include/net/netfilter/nf_tables_ipv4.h index c4a6147b0ef8c..5225d2bd1a6e9 100644 --- a/include/net/netfilter/nf_tables_ipv4.h +++ b/include/net/netfilter/nf_tables_ipv4.h @@ -29,8 +29,8 @@ static inline int __nft_set_pktinfo_ipv4_validate(struct nft_pktinfo *pkt) if (iph->ihl < 5 || iph->version != 4) return -1; - len = ntohs(iph->tot_len); - thoff = iph->ihl * 4; + len = iph_totlen(pkt->skb, iph); + thoff = skb_network_offset(pkt->skb) + (iph->ihl * 4); if (pkt->skb->len < len) return -1; else if (len < thoff) @@ -62,7 +62,7 @@ static inline int nft_set_pktinfo_ipv4_ingress(struct nft_pktinfo *pkt) if (iph->ihl < 5 || iph->version != 4) goto inhdr_error; - len = ntohs(iph->tot_len); + len = iph_totlen(pkt->skb, iph); thoff = iph->ihl * 4; if (pkt->skb->len < len) { __IP_INC_STATS(nft_net(pkt), IPSTATS_MIB_INTRUNCATEDPKTS); diff --git a/include/net/sock.h b/include/net/sock.h index b6027b01c2455..6b51e85ae69e3 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1279,6 +1279,7 @@ struct proto { size_t len, int flags, int *addr_len); int (*sendpage)(struct sock *sk, struct page *page, int offset, size_t size, int flags); + void (*splice_eof)(struct socket *sock); int (*bind)(struct sock *sk, struct sockaddr *addr, int addr_len); int (*bind_add)(struct sock *sk, @@ -1928,7 +1929,9 @@ struct sockcm_cookie { static inline void sockcm_init(struct sockcm_cookie *sockc, const struct sock *sk) { - *sockc = (struct sockcm_cookie) { .tsflags = sk->sk_tsflags }; + *sockc = (struct sockcm_cookie) { + .tsflags = READ_ONCE(sk->sk_tsflags) + }; } int __sock_cmsg_send(struct sock *sk, struct msghdr *msg, struct cmsghdr *cmsg, @@ -2741,9 +2744,9 @@ void __sock_recv_wifi_status(struct msghdr *msg, struct sock *sk, static inline void sock_recv_timestamp(struct msghdr *msg, struct sock *sk, struct sk_buff *skb) { - ktime_t kt = skb->tstamp; struct skb_shared_hwtstamps *hwtstamps = skb_hwtstamps(skb); - + u32 tsflags = READ_ONCE(sk->sk_tsflags); + ktime_t kt = skb->tstamp; /* * generate control messages if * - receive time stamping in software requested @@ -2751,10 +2754,10 @@ sock_recv_timestamp(struct msghdr *msg, struct sock *sk, struct sk_buff *skb) * - hardware time stamps available and wanted */ if (sock_flag(sk, SOCK_RCVTSTAMP) || - (sk->sk_tsflags & SOF_TIMESTAMPING_RX_SOFTWARE) || - (kt && sk->sk_tsflags & SOF_TIMESTAMPING_SOFTWARE) || + (tsflags & SOF_TIMESTAMPING_RX_SOFTWARE) || + (kt && tsflags & SOF_TIMESTAMPING_SOFTWARE) || (hwtstamps->hwtstamp && - (sk->sk_tsflags & SOF_TIMESTAMPING_RAW_HARDWARE))) + (tsflags & SOF_TIMESTAMPING_RAW_HARDWARE))) __sock_recv_timestamp(msg, sk, skb); else sock_write_timestamp(sk, kt); @@ -2776,7 +2779,8 @@ static inline void sock_recv_cmsgs(struct msghdr *msg, struct sock *sk, #define TSFLAGS_ANY (SOF_TIMESTAMPING_SOFTWARE | \ SOF_TIMESTAMPING_RAW_HARDWARE) - if (sk->sk_flags & FLAGS_RECV_CMSGS || sk->sk_tsflags & TSFLAGS_ANY) + if (sk->sk_flags & FLAGS_RECV_CMSGS || + READ_ONCE(sk->sk_tsflags) & TSFLAGS_ANY) __sock_recv_cmsgs(msg, sk, skb); else if (unlikely(sock_flag(sk, SOCK_TIMESTAMP))) sock_write_timestamp(sk, skb->tstamp); @@ -2825,6 +2829,11 @@ static inline bool sk_is_tcp(const struct sock *sk) return sk->sk_type == SOCK_STREAM && sk->sk_protocol == IPPROTO_TCP; } +static inline bool sk_is_stream_unix(const struct sock *sk) +{ + return sk->sk_family == AF_UNIX && sk->sk_type == SOCK_STREAM; +} + /** * sk_eat_skb - Release a skb if it is no longer needed * @sk: socket to eat this skb from diff --git a/include/net/tcp.h b/include/net/tcp.h index c3d56b337f358..4c838f7290dd9 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -332,6 +332,7 @@ int tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size); int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size); int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, int *copied, size_t size, struct ubuf_info *uarg); +void tcp_splice_eof(struct socket *sock); int tcp_sendpage(struct sock *sk, struct page *page, int offset, size_t size, int flags); int tcp_sendpage_locked(struct sock *sk, struct page *page, int offset, diff --git a/include/net/udp.h b/include/net/udp.h index fee053bcd17c6..fa4cdbe55552c 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -269,6 +269,7 @@ int udp_get_port(struct sock *sk, unsigned short snum, int udp_err(struct sk_buff *, u32); int udp_abort(struct sock *sk, int err); int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len); +void udp_splice_eof(struct socket *sock); int udp_push_pending_frames(struct sock *sk); void udp_flush_pending_frames(struct sock *sk); int udp_cmsg_send(struct sock *sk, struct msghdr *msg, u16 *gso_size); diff --git a/include/net/udp_tunnel.h b/include/net/udp_tunnel.h index 72394f441dad8..e5f81710b18f4 100644 --- a/include/net/udp_tunnel.h +++ b/include/net/udp_tunnel.h @@ -174,16 +174,13 @@ static inline int udp_tunnel_handle_offloads(struct sk_buff *skb, bool udp_csum) } #endif -static inline void udp_tunnel_encap_enable(struct socket *sock) +static inline void udp_tunnel_encap_enable(struct sock *sk) { - struct udp_sock *up = udp_sk(sock->sk); - - if (up->encap_enabled) + if (udp_test_and_set_bit(ENCAP_ENABLED, sk)) return; - up->encap_enabled = 1; #if IS_ENABLED(CONFIG_IPV6) - if (sock->sk->sk_family == PF_INET6) + if (READ_ONCE(sk->sk_family) == PF_INET6) ipv6_stub->udpv6_encap_enable(); #endif udp_encap_enable(); diff --git a/io_uring/net.c b/io_uring/net.c index 57c626cb4d1a5..67f09a40bcb21 100644 --- a/io_uring/net.c +++ b/io_uring/net.c @@ -389,6 +389,7 @@ int io_send(struct io_kiocb *req, unsigned int issue_flags) if (flags & MSG_WAITALL) min_ret = iov_iter_count(&msg.msg_iter); + flags &= ~MSG_INTERNAL_SENDMSG_FLAGS; msg.msg_flags = flags; ret = sock_sendmsg(sock, &msg); if (ret < min_ret) { @@ -1137,6 +1138,7 @@ int io_send_zc(struct io_kiocb *req, unsigned int issue_flags) msg_flags |= MSG_DONTWAIT; if (msg_flags & MSG_WAITALL) min_ret = iov_iter_count(&msg.msg_iter); + msg_flags &= ~MSG_INTERNAL_SENDMSG_FLAGS; msg.msg_flags = msg_flags; msg.msg_ubuf = &io_notif_to_data(zc->notif)->uarg; diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 7225cb67c0d3a..76bf1de261152 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -365,9 +365,18 @@ static int bpf_adj_delta_to_imm(struct bpf_insn *insn, u32 pos, s32 end_old, static int bpf_adj_delta_to_off(struct bpf_insn *insn, u32 pos, s32 end_old, s32 end_new, s32 curr, const bool probe_pass) { - const s32 off_min = S16_MIN, off_max = S16_MAX; + s64 off_min, off_max, off; s32 delta = end_new - end_old; - s32 off = insn->off; + + if (insn->code == (BPF_JMP32 | BPF_JA)) { + off = insn->imm; + off_min = S32_MIN; + off_max = S32_MAX; + } else { + off = insn->off; + off_min = S16_MIN; + off_max = S16_MAX; + } if (curr < pos && curr + off + 1 >= end_old) off += delta; @@ -375,8 +384,12 @@ static int bpf_adj_delta_to_off(struct bpf_insn *insn, u32 pos, s32 end_old, off -= delta; if (off < off_min || off > off_max) return -ERANGE; - if (!probe_pass) - insn->off = off; + if (!probe_pass) { + if (insn->code == (BPF_JMP32 | BPF_JA)) + insn->imm = off; + else + insn->off = off; + } return 0; } @@ -1586,6 +1599,7 @@ EXPORT_SYMBOL_GPL(__bpf_call_base); INSN_3(JMP, JSLE, K), \ INSN_3(JMP, JSET, K), \ INSN_2(JMP, JA), \ + INSN_2(JMP32, JA), \ /* Store instructions. */ \ /* Register based. */ \ INSN_3(STX, MEM, B), \ @@ -1862,6 +1876,9 @@ out: JMP_JA: insn += insn->off; CONT; + JMP32_JA: + insn += insn->imm; + CONT; JMP_EXIT: return BPF_R0; /* JMP */ diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c index c4381dfcd6b09..748ac86169941 100644 --- a/kernel/bpf/trampoline.c +++ b/kernel/bpf/trampoline.c @@ -443,8 +443,8 @@ static int bpf_trampoline_update(struct bpf_trampoline *tr, bool lock_direct_mut goto out; } - /* clear all bits except SHARE_IPMODIFY */ - tr->flags &= BPF_TRAMP_F_SHARE_IPMODIFY; + /* clear all bits except SHARE_IPMODIFY and TAIL_CALL_CTX */ + tr->flags &= (BPF_TRAMP_F_SHARE_IPMODIFY | BPF_TRAMP_F_TAIL_CALL_CTX); if (tlinks[BPF_TRAMP_FEXIT].nr_links || tlinks[BPF_TRAMP_MODIFY_RETURN].nr_links) { diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 12d360d80c149..142e10d49fd81 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -2254,7 +2254,10 @@ static int check_subprogs(struct bpf_verifier_env *env) goto next; if (BPF_OP(code) == BPF_EXIT || BPF_OP(code) == BPF_CALL) goto next; - off = i + insn[i].off + 1; + if (code == (BPF_JMP32 | BPF_JA)) + off = i + insn[i].imm + 1; + else + off = i + insn[i].off + 1; if (off < subprog_start || off >= subprog_end) { verbose(env, "jump out of range from insn %d to %d\n", i, off); return -EINVAL; @@ -2266,6 +2269,7 @@ next: * or unconditional jump back */ if (code != (BPF_JMP | BPF_EXIT) && + code != (BPF_JMP32 | BPF_JA) && code != (BPF_JMP | BPF_JA)) { verbose(env, "last insn is not an exit or jmp\n"); return -EINVAL; @@ -2512,6 +2516,16 @@ static int check_reg_arg(struct bpf_verifier_env *env, u32 regno, return 0; } +static void mark_jmp_point(struct bpf_verifier_env *env, int idx) +{ + env->insn_aux_data[idx].jmp_point = true; +} + +static bool is_jmp_point(struct bpf_verifier_env *env, int insn_idx) +{ + return env->insn_aux_data[insn_idx].jmp_point; +} + /* for any branch, call, exit record the history of jmps in the given state */ static int push_jmp_history(struct bpf_verifier_env *env, struct bpf_verifier_state *cur) @@ -2520,6 +2534,9 @@ static int push_jmp_history(struct bpf_verifier_env *env, struct bpf_idx_pair *p; size_t alloc_size; + if (!is_jmp_point(env, env->insn_idx)) + return 0; + cnt++; alloc_size = kmalloc_size_roundup(size_mul(cnt, sizeof(*p))); p = krealloc(cur->jmp_history, alloc_size, GFP_USER); @@ -2534,12 +2551,29 @@ static int push_jmp_history(struct bpf_verifier_env *env, /* Backtrack one insn at a time. If idx is not at the top of recorded * history then previous instruction came from straight line execution. + * Return -ENOENT if we exhausted all instructions within given state. + * + * It's legal to have a bit of a looping with the same starting and ending + * insn index within the same state, e.g.: 3->4->5->3, so just because current + * instruction index is the same as state's first_idx doesn't mean we are + * done. If there is still some jump history left, we should keep going. We + * need to take into account that we might have a jump history between given + * state's parent and itself, due to checkpointing. In this case, we'll have + * history entry recording a jump from last instruction of parent state and + * first instruction of given state. */ static int get_prev_insn_idx(struct bpf_verifier_state *st, int i, u32 *history) { u32 cnt = *history; + if (i == st->first_insn_idx) { + if (cnt == 0) + return -ENOENT; + if (cnt == 1 && st->jmp_history[0].idx == i) + return -ENOENT; + } + if (cnt && st->jmp_history[cnt - 1].idx == i) { i = st->jmp_history[cnt - 1].prev_idx; (*history)--; @@ -3035,9 +3069,9 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int frame, int r * Nothing to be tracked further in the parent state. */ return 0; - if (i == first_idx) - break; i = get_prev_insn_idx(st, i, &history); + if (i == -ENOENT) + break; if (i >= env->prog->len) { /* This can happen if backtracking reached insn 0 * and there are still reg_mask or stack_mask @@ -11000,11 +11034,16 @@ static struct bpf_verifier_state_list **explored_state( return &env->explored_states[(idx ^ state->callsite) % state_htab_size(env)]; } -static void init_explored_state(struct bpf_verifier_env *env, int idx) +static void mark_prune_point(struct bpf_verifier_env *env, int idx) { env->insn_aux_data[idx].prune_point = true; } +static bool is_prune_point(struct bpf_verifier_env *env, int insn_idx) +{ + return env->insn_aux_data[insn_idx].prune_point; +} + enum { DONE_EXPLORING = 0, KEEP_EXPLORING = 1, @@ -11033,9 +11072,11 @@ static int push_insn(int t, int w, int e, struct bpf_verifier_env *env, return -EINVAL; } - if (e == BRANCH) + if (e == BRANCH) { /* mark branch target for state pruning */ - init_explored_state(env, w); + mark_prune_point(env, w); + mark_jmp_point(env, w); + } if (insn_state[w] == 0) { /* tree-edge */ @@ -11062,21 +11103,23 @@ static int push_insn(int t, int w, int e, struct bpf_verifier_env *env, return DONE_EXPLORING; } -static int visit_func_call_insn(int t, int insn_cnt, - struct bpf_insn *insns, +static int visit_func_call_insn(int t, struct bpf_insn *insns, struct bpf_verifier_env *env, bool visit_callee) { - int ret; + int ret, insn_sz; - ret = push_insn(t, t + 1, FALLTHROUGH, env, false); + insn_sz = bpf_is_ldimm64(&insns[t]) ? 2 : 1; + ret = push_insn(t, t + insn_sz, FALLTHROUGH, env, false); if (ret) return ret; - if (t + 1 < insn_cnt) - init_explored_state(env, t + 1); + mark_prune_point(env, t + insn_sz); + /* when we exit from subprog, we need to record non-linear history */ + mark_jmp_point(env, t + insn_sz); + if (visit_callee) { - init_explored_state(env, t); + mark_prune_point(env, t); ret = push_insn(t, t + insns[t].imm + 1, BRANCH, env, /* It's ok to allow recursion from CFG point of * view. __check_func_call() will do the actual @@ -11092,65 +11135,64 @@ static int visit_func_call_insn(int t, int insn_cnt, * DONE_EXPLORING - the instruction was fully explored * KEEP_EXPLORING - there is still work to be done before it is fully explored */ -static int visit_insn(int t, int insn_cnt, struct bpf_verifier_env *env) +static int visit_insn(int t, struct bpf_verifier_env *env) { - struct bpf_insn *insns = env->prog->insnsi; - int ret; + struct bpf_insn *insns = env->prog->insnsi, *insn = &insns[t]; + int ret, off, insn_sz; - if (bpf_pseudo_func(insns + t)) - return visit_func_call_insn(t, insn_cnt, insns, env, true); + if (bpf_pseudo_func(insn)) + return visit_func_call_insn(t, insns, env, true); /* All non-branch instructions have a single fall-through edge. */ - if (BPF_CLASS(insns[t].code) != BPF_JMP && - BPF_CLASS(insns[t].code) != BPF_JMP32) - return push_insn(t, t + 1, FALLTHROUGH, env, false); + if (BPF_CLASS(insn->code) != BPF_JMP && + BPF_CLASS(insn->code) != BPF_JMP32) { + insn_sz = bpf_is_ldimm64(insn) ? 2 : 1; + return push_insn(t, t + insn_sz, FALLTHROUGH, env, false); + } - switch (BPF_OP(insns[t].code)) { + switch (BPF_OP(insn->code)) { case BPF_EXIT: return DONE_EXPLORING; case BPF_CALL: - if (insns[t].imm == BPF_FUNC_timer_set_callback) - /* Mark this call insn to trigger is_state_visited() check - * before call itself is processed by __check_func_call(). - * Otherwise new async state will be pushed for further - * exploration. + if (insn->imm == BPF_FUNC_timer_set_callback) + /* Mark this call insn as a prune point to trigger + * is_state_visited() check before call itself is + * processed by __check_func_call(). Otherwise new + * async state will be pushed for further exploration. */ - init_explored_state(env, t); - return visit_func_call_insn(t, insn_cnt, insns, env, - insns[t].src_reg == BPF_PSEUDO_CALL); + mark_prune_point(env, t); + return visit_func_call_insn(t, insns, env, insn->src_reg == BPF_PSEUDO_CALL); case BPF_JA: - if (BPF_SRC(insns[t].code) != BPF_K) + if (BPF_SRC(insn->code) != BPF_K) return -EINVAL; + if (BPF_CLASS(insn->code) == BPF_JMP) + off = insn->off; + else + off = insn->imm; + /* unconditional jump with single edge */ - ret = push_insn(t, t + insns[t].off + 1, FALLTHROUGH, env, + ret = push_insn(t, t + off + 1, FALLTHROUGH, env, true); if (ret) return ret; - /* unconditional jmp is not a good pruning point, - * but it's marked, since backtracking needs - * to record jmp history in is_state_visited(). - */ - init_explored_state(env, t + insns[t].off + 1); - /* tell verifier to check for equivalent states - * after every call and jump - */ - if (t + 1 < insn_cnt) - init_explored_state(env, t + 1); + mark_prune_point(env, t + off + 1); + mark_jmp_point(env, t + off + 1); return ret; default: /* conditional jump with two edges */ - init_explored_state(env, t); + mark_prune_point(env, t); + ret = push_insn(t, t + 1, FALLTHROUGH, env, true); if (ret) return ret; - return push_insn(t, t + insns[t].off + 1, BRANCH, env, true); + return push_insn(t, t + insn->off + 1, BRANCH, env, true); } } @@ -11181,7 +11223,7 @@ static int check_cfg(struct bpf_verifier_env *env) while (env->cfg.cur_stack > 0) { int t = insn_stack[env->cfg.cur_stack - 1]; - ret = visit_insn(t, insn_cnt, env); + ret = visit_insn(t, env); switch (ret) { case DONE_EXPLORING: insn_state[t] = EXPLORED; @@ -11205,11 +11247,21 @@ static int check_cfg(struct bpf_verifier_env *env) } for (i = 0; i < insn_cnt; i++) { + struct bpf_insn *insn = &env->prog->insnsi[i]; + if (insn_state[i] != EXPLORED) { verbose(env, "unreachable insn %d\n", i); ret = -EINVAL; goto err_free; } + if (bpf_is_ldimm64(insn)) { + if (insn_state[i + 1] != 0) { + verbose(env, "jump into the middle of ldimm64 insn %d\n", i); + ret = -EINVAL; + goto err_free; + } + i++; /* skip second half of ldimm64 */ + } } ret = 0; /* cfg looks good */ @@ -12178,11 +12230,11 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) bool add_new_state = env->test_state_freq ? true : false; cur->last_insn_idx = env->prev_insn_idx; - if (!env->insn_aux_data[insn_idx].prune_point) + if (!is_prune_point(env, insn_idx)) /* this 'insn_idx' instruction wasn't marked, so we will not * be doing state search here */ - return 0; + return push_jmp_history(env, cur); /* bpf progs typically have pruning point every 4 instructions * http://vger.kernel.org/bpfconf2019.html#session-1 @@ -12674,15 +12726,18 @@ static int do_check(struct bpf_verifier_env *env) return err; } else if (opcode == BPF_JA) { if (BPF_SRC(insn->code) != BPF_K || - insn->imm != 0 || insn->src_reg != BPF_REG_0 || insn->dst_reg != BPF_REG_0 || - class == BPF_JMP32) { + (class == BPF_JMP && insn->imm != 0) || + (class == BPF_JMP32 && insn->off != 0)) { verbose(env, "BPF_JA uses reserved fields\n"); return -EINVAL; } - env->insn_idx += insn->off + 1; + if (class == BPF_JMP) + env->insn_idx += insn->off + 1; + else + env->insn_idx += insn->imm + 1; continue; } else if (opcode == BPF_EXIT) { @@ -13508,13 +13563,13 @@ static bool insn_is_cond_jump(u8 code) { u8 op; + op = BPF_OP(code); if (BPF_CLASS(code) == BPF_JMP32) - return true; + return op != BPF_JA; if (BPF_CLASS(code) != BPF_JMP) return false; - op = BPF_OP(code); return op != BPF_JA && op != BPF_EXIT && op != BPF_CALL; } @@ -15442,6 +15497,9 @@ static int check_attach_btf_id(struct bpf_verifier_env *env) if (!tr) return -ENOMEM; + if (tgt_prog && tgt_prog->aux->tail_call_reachable) + tr->flags = BPF_TRAMP_F_TAIL_CALL_CTX; + prog->aux->dst_trampoline = tr; return 0; } diff --git a/kernel/cpu.c b/kernel/cpu.c index 551468d9c5a85..e6f0101941ed8 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -446,9 +446,31 @@ static int __init smt_cmdline_disable(char *str) } early_param("nosmt", smt_cmdline_disable); -static inline bool cpu_smt_allowed(unsigned int cpu) +/* + * For Archicture supporting partial SMT states check if the thread is allowed. + * Otherwise this has already been checked through cpu_smt_max_threads when + * setting the SMT level. + */ +static inline bool cpu_smt_thread_allowed(unsigned int cpu) { - if (cpu_smt_control == CPU_SMT_ENABLED) +#ifdef CONFIG_SMT_NUM_THREADS_DYNAMIC + return topology_smt_thread_allowed(cpu); +#else + return true; +#endif +} + +static inline bool cpu_bootable(unsigned int cpu) +{ + if (cpu_smt_control == CPU_SMT_ENABLED && cpu_smt_thread_allowed(cpu)) + return true; + + /* All CPUs are bootable if controls are not configured */ + if (cpu_smt_control == CPU_SMT_NOT_IMPLEMENTED) + return true; + + /* All CPUs are bootable if CPU is not SMT capable */ + if (cpu_smt_control == CPU_SMT_NOT_SUPPORTED) return true; if (topology_is_primary_thread(cpu)) @@ -471,7 +493,7 @@ bool cpu_smt_possible(void) } EXPORT_SYMBOL_GPL(cpu_smt_possible); #else -static inline bool cpu_smt_allowed(unsigned int cpu) { return true; } +static inline bool cpu_bootable(unsigned int cpu) { return true; } #endif static inline enum cpuhp_state @@ -574,10 +596,10 @@ static int bringup_wait_for_ap(unsigned int cpu) * SMT soft disabling on X86 requires to bring the CPU out of the * BIOS 'wait for SIPI' state in order to set the CR4.MCE bit. The * CPU marked itself as booted_once in notify_cpu_starting() so the - * cpu_smt_allowed() check will now return false if this is not the + * cpu_bootable() check will now return false if this is not the * primary sibling. */ - if (!cpu_smt_allowed(cpu)) + if (!cpu_bootable(cpu)) return -ECANCELED; if (st->target <= CPUHP_AP_ONLINE_IDLE) @@ -1464,7 +1486,7 @@ static int cpu_up(unsigned int cpu, enum cpuhp_state target) err = -EBUSY; goto out; } - if (!cpu_smt_allowed(cpu)) { + if (!cpu_bootable(cpu)) { err = -EPERM; goto out; } @@ -2294,6 +2316,12 @@ int cpuhp_smt_disable(enum cpuhp_smt_control ctrlval) for_each_online_cpu(cpu) { if (topology_is_primary_thread(cpu)) continue; + /* + * Disable can be called with CPU_SMT_ENABLED when changing + * from a higher to lower number of SMT threads per core. + */ + if (ctrlval == CPU_SMT_ENABLED && cpu_smt_thread_allowed(cpu)) + continue; ret = cpu_down_maps_locked(cpu, CPUHP_OFFLINE); if (ret) break; @@ -2328,6 +2356,8 @@ int cpuhp_smt_enable(void) /* Skip online CPUs and CPUs on offline nodes */ if (cpu_online(cpu) || !node_online(cpu_to_node(cpu))) continue; + if (!cpu_smt_thread_allowed(cpu)) + continue; ret = _cpu_up(cpu, 0, CPUHP_ONLINE); if (ret) break; diff --git a/kernel/irq/affinity.c b/kernel/irq/affinity.c index d9a5c1d65a79d..44a4eba80315c 100644 --- a/kernel/irq/affinity.c +++ b/kernel/irq/affinity.c @@ -7,398 +7,7 @@ #include #include #include -#include - -static void irq_spread_init_one(struct cpumask *irqmsk, struct cpumask *nmsk, - unsigned int cpus_per_vec) -{ - const struct cpumask *siblmsk; - int cpu, sibl; - - for ( ; cpus_per_vec > 0; ) { - cpu = cpumask_first(nmsk); - - /* Should not happen, but I'm too lazy to think about it */ - if (cpu >= nr_cpu_ids) - return; - - cpumask_clear_cpu(cpu, nmsk); - cpumask_set_cpu(cpu, irqmsk); - cpus_per_vec--; - - /* If the cpu has siblings, use them first */ - siblmsk = topology_sibling_cpumask(cpu); - for (sibl = -1; cpus_per_vec > 0; ) { - sibl = cpumask_next(sibl, siblmsk); - if (sibl >= nr_cpu_ids) - break; - if (!cpumask_test_and_clear_cpu(sibl, nmsk)) - continue; - cpumask_set_cpu(sibl, irqmsk); - cpus_per_vec--; - } - } -} - -static cpumask_var_t *alloc_node_to_cpumask(void) -{ - cpumask_var_t *masks; - int node; - - masks = kcalloc(nr_node_ids, sizeof(cpumask_var_t), GFP_KERNEL); - if (!masks) - return NULL; - - for (node = 0; node < nr_node_ids; node++) { - if (!zalloc_cpumask_var(&masks[node], GFP_KERNEL)) - goto out_unwind; - } - - return masks; - -out_unwind: - while (--node >= 0) - free_cpumask_var(masks[node]); - kfree(masks); - return NULL; -} - -static void free_node_to_cpumask(cpumask_var_t *masks) -{ - int node; - - for (node = 0; node < nr_node_ids; node++) - free_cpumask_var(masks[node]); - kfree(masks); -} - -static void build_node_to_cpumask(cpumask_var_t *masks) -{ - int cpu; - - for_each_possible_cpu(cpu) - cpumask_set_cpu(cpu, masks[cpu_to_node(cpu)]); -} - -static int get_nodes_in_cpumask(cpumask_var_t *node_to_cpumask, - const struct cpumask *mask, nodemask_t *nodemsk) -{ - int n, nodes = 0; - - /* Calculate the number of nodes in the supplied affinity mask */ - for_each_node(n) { - if (cpumask_intersects(mask, node_to_cpumask[n])) { - node_set(n, *nodemsk); - nodes++; - } - } - return nodes; -} - -struct node_vectors { - unsigned id; - - union { - unsigned nvectors; - unsigned ncpus; - }; -}; - -static int ncpus_cmp_func(const void *l, const void *r) -{ - const struct node_vectors *ln = l; - const struct node_vectors *rn = r; - - return ln->ncpus - rn->ncpus; -} - -/* - * Allocate vector number for each node, so that for each node: - * - * 1) the allocated number is >= 1 - * - * 2) the allocated numbver is <= active CPU number of this node - * - * The actual allocated total vectors may be less than @numvecs when - * active total CPU number is less than @numvecs. - * - * Active CPUs means the CPUs in '@cpu_mask AND @node_to_cpumask[]' - * for each node. - */ -static void alloc_nodes_vectors(unsigned int numvecs, - cpumask_var_t *node_to_cpumask, - const struct cpumask *cpu_mask, - const nodemask_t nodemsk, - struct cpumask *nmsk, - struct node_vectors *node_vectors) -{ - unsigned n, remaining_ncpus = 0; - - for (n = 0; n < nr_node_ids; n++) { - node_vectors[n].id = n; - node_vectors[n].ncpus = UINT_MAX; - } - - for_each_node_mask(n, nodemsk) { - unsigned ncpus; - - cpumask_and(nmsk, cpu_mask, node_to_cpumask[n]); - ncpus = cpumask_weight(nmsk); - - if (!ncpus) - continue; - remaining_ncpus += ncpus; - node_vectors[n].ncpus = ncpus; - } - - numvecs = min_t(unsigned, remaining_ncpus, numvecs); - - sort(node_vectors, nr_node_ids, sizeof(node_vectors[0]), - ncpus_cmp_func, NULL); - - /* - * Allocate vectors for each node according to the ratio of this - * node's nr_cpus to remaining un-assigned ncpus. 'numvecs' is - * bigger than number of active numa nodes. Always start the - * allocation from the node with minimized nr_cpus. - * - * This way guarantees that each active node gets allocated at - * least one vector, and the theory is simple: over-allocation - * is only done when this node is assigned by one vector, so - * other nodes will be allocated >= 1 vector, since 'numvecs' is - * bigger than number of numa nodes. - * - * One perfect invariant is that number of allocated vectors for - * each node is <= CPU count of this node: - * - * 1) suppose there are two nodes: A and B - * ncpu(X) is CPU count of node X - * vecs(X) is the vector count allocated to node X via this - * algorithm - * - * ncpu(A) <= ncpu(B) - * ncpu(A) + ncpu(B) = N - * vecs(A) + vecs(B) = V - * - * vecs(A) = max(1, round_down(V * ncpu(A) / N)) - * vecs(B) = V - vecs(A) - * - * both N and V are integer, and 2 <= V <= N, suppose - * V = N - delta, and 0 <= delta <= N - 2 - * - * 2) obviously vecs(A) <= ncpu(A) because: - * - * if vecs(A) is 1, then vecs(A) <= ncpu(A) given - * ncpu(A) >= 1 - * - * otherwise, - * vecs(A) <= V * ncpu(A) / N <= ncpu(A), given V <= N - * - * 3) prove how vecs(B) <= ncpu(B): - * - * if round_down(V * ncpu(A) / N) == 0, vecs(B) won't be - * over-allocated, so vecs(B) <= ncpu(B), - * - * otherwise: - * - * vecs(A) = - * round_down(V * ncpu(A) / N) = - * round_down((N - delta) * ncpu(A) / N) = - * round_down((N * ncpu(A) - delta * ncpu(A)) / N) >= - * round_down((N * ncpu(A) - delta * N) / N) = - * cpu(A) - delta - * - * then: - * - * vecs(A) - V >= ncpu(A) - delta - V - * => - * V - vecs(A) <= V + delta - ncpu(A) - * => - * vecs(B) <= N - ncpu(A) - * => - * vecs(B) <= cpu(B) - * - * For nodes >= 3, it can be thought as one node and another big - * node given that is exactly what this algorithm is implemented, - * and we always re-calculate 'remaining_ncpus' & 'numvecs', and - * finally for each node X: vecs(X) <= ncpu(X). - * - */ - for (n = 0; n < nr_node_ids; n++) { - unsigned nvectors, ncpus; - - if (node_vectors[n].ncpus == UINT_MAX) - continue; - - WARN_ON_ONCE(numvecs == 0); - - ncpus = node_vectors[n].ncpus; - nvectors = max_t(unsigned, 1, - numvecs * ncpus / remaining_ncpus); - WARN_ON_ONCE(nvectors > ncpus); - - node_vectors[n].nvectors = nvectors; - - remaining_ncpus -= ncpus; - numvecs -= nvectors; - } -} - -static int __irq_build_affinity_masks(unsigned int startvec, - unsigned int numvecs, - unsigned int firstvec, - cpumask_var_t *node_to_cpumask, - const struct cpumask *cpu_mask, - struct cpumask *nmsk, - struct irq_affinity_desc *masks) -{ - unsigned int i, n, nodes, cpus_per_vec, extra_vecs, done = 0; - unsigned int last_affv = firstvec + numvecs; - unsigned int curvec = startvec; - nodemask_t nodemsk = NODE_MASK_NONE; - struct node_vectors *node_vectors; - - if (cpumask_empty(cpu_mask)) - return 0; - - nodes = get_nodes_in_cpumask(node_to_cpumask, cpu_mask, &nodemsk); - - /* - * If the number of nodes in the mask is greater than or equal the - * number of vectors we just spread the vectors across the nodes. - */ - if (numvecs <= nodes) { - for_each_node_mask(n, nodemsk) { - /* Ensure that only CPUs which are in both masks are set */ - cpumask_and(nmsk, cpu_mask, node_to_cpumask[n]); - cpumask_or(&masks[curvec].mask, &masks[curvec].mask, nmsk); - if (++curvec == last_affv) - curvec = firstvec; - } - return numvecs; - } - - node_vectors = kcalloc(nr_node_ids, - sizeof(struct node_vectors), - GFP_KERNEL); - if (!node_vectors) - return -ENOMEM; - - /* allocate vector number for each node */ - alloc_nodes_vectors(numvecs, node_to_cpumask, cpu_mask, - nodemsk, nmsk, node_vectors); - - for (i = 0; i < nr_node_ids; i++) { - unsigned int ncpus, v; - struct node_vectors *nv = &node_vectors[i]; - - if (nv->nvectors == UINT_MAX) - continue; - - /* Get the cpus on this node which are in the mask */ - cpumask_and(nmsk, cpu_mask, node_to_cpumask[nv->id]); - ncpus = cpumask_weight(nmsk); - if (!ncpus) - continue; - - WARN_ON_ONCE(nv->nvectors > ncpus); - - /* Account for rounding errors */ - extra_vecs = ncpus - nv->nvectors * (ncpus / nv->nvectors); - - /* Spread allocated vectors on CPUs of the current node */ - for (v = 0; v < nv->nvectors; v++, curvec++) { - cpus_per_vec = ncpus / nv->nvectors; - - /* Account for extra vectors to compensate rounding errors */ - if (extra_vecs) { - cpus_per_vec++; - --extra_vecs; - } - - /* - * wrapping has to be considered given 'startvec' - * may start anywhere - */ - if (curvec >= last_affv) - curvec = firstvec; - irq_spread_init_one(&masks[curvec].mask, nmsk, - cpus_per_vec); - } - done += nv->nvectors; - } - kfree(node_vectors); - return done; -} - -/* - * build affinity in two stages: - * 1) spread present CPU on these vectors - * 2) spread other possible CPUs on these vectors - */ -static int irq_build_affinity_masks(unsigned int startvec, unsigned int numvecs, - unsigned int firstvec, - struct irq_affinity_desc *masks) -{ - unsigned int curvec = startvec, nr_present = 0, nr_others = 0; - cpumask_var_t *node_to_cpumask; - cpumask_var_t nmsk, npresmsk; - int ret = -ENOMEM; - - if (!zalloc_cpumask_var(&nmsk, GFP_KERNEL)) - return ret; - - if (!zalloc_cpumask_var(&npresmsk, GFP_KERNEL)) - goto fail_nmsk; - - node_to_cpumask = alloc_node_to_cpumask(); - if (!node_to_cpumask) - goto fail_npresmsk; - - /* Stabilize the cpumasks */ - cpus_read_lock(); - build_node_to_cpumask(node_to_cpumask); - - /* Spread on present CPUs starting from affd->pre_vectors */ - ret = __irq_build_affinity_masks(curvec, numvecs, firstvec, - node_to_cpumask, cpu_present_mask, - nmsk, masks); - if (ret < 0) - goto fail_build_affinity; - nr_present = ret; - - /* - * Spread on non present CPUs starting from the next vector to be - * handled. If the spreading of present CPUs already exhausted the - * vector space, assign the non present CPUs to the already spread - * out vectors. - */ - if (nr_present >= numvecs) - curvec = firstvec; - else - curvec = firstvec + nr_present; - cpumask_andnot(npresmsk, cpu_possible_mask, cpu_present_mask); - ret = __irq_build_affinity_masks(curvec, numvecs, firstvec, - node_to_cpumask, npresmsk, nmsk, - masks); - if (ret >= 0) - nr_others = ret; - - fail_build_affinity: - cpus_read_unlock(); - - if (ret >= 0) - WARN_ON(nr_present + nr_others < numvecs); - - free_node_to_cpumask(node_to_cpumask); - - fail_npresmsk: - free_cpumask_var(npresmsk); - - fail_nmsk: - free_cpumask_var(nmsk); - return ret < 0 ? ret : 0; -} +#include static void default_calc_sets(struct irq_affinity *affd, unsigned int affvecs) { @@ -461,14 +70,18 @@ irq_create_affinity_masks(unsigned int nvecs, struct irq_affinity *affd) */ for (i = 0, usedvecs = 0; i < affd->nr_sets; i++) { unsigned int this_vecs = affd->set_size[i]; - int ret; + int j; + struct cpumask *result = group_cpus_evenly(this_vecs); - ret = irq_build_affinity_masks(curvec, this_vecs, - curvec, masks); - if (ret) { + if (!result) { kfree(masks); return NULL; } + + for (j = 0; j < this_vecs; j++) + cpumask_copy(&masks[curvec + j].mask, &result[j]); + kfree(result); + curvec += this_vecs; usedvecs += this_vecs; } diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c index 8fdf076720384..929dcbc04d29c 100644 --- a/kernel/rcu/srcutree.c +++ b/kernel/rcu/srcutree.c @@ -1100,10 +1100,37 @@ static unsigned long srcu_gp_start_if_needed(struct srcu_struct *ssp, spin_lock_irqsave_sdp_contention(sdp, &flags); if (rhp) rcu_segcblist_enqueue(&sdp->srcu_cblist, rhp); + /* + * The snapshot for acceleration must be taken _before_ the read of the + * current gp sequence used for advancing, otherwise advancing may fail + * and acceleration may then fail too. + * + * This could happen if: + * + * 1) The RCU_WAIT_TAIL segment has callbacks (gp_num = X + 4) and the + * RCU_NEXT_READY_TAIL also has callbacks (gp_num = X + 8). + * + * 2) The grace period for RCU_WAIT_TAIL is seen as started but not + * completed so rcu_seq_current() returns X + SRCU_STATE_SCAN1. + * + * 3) This value is passed to rcu_segcblist_advance() which can't move + * any segment forward and fails. + * + * 4) srcu_gp_start_if_needed() still proceeds with callback acceleration. + * But then the call to rcu_seq_snap() observes the grace period for the + * RCU_WAIT_TAIL segment as completed and the subsequent one for the + * RCU_NEXT_READY_TAIL segment as started (ie: X + 4 + SRCU_STATE_SCAN1) + * so it returns a snapshot of the next grace period, which is X + 12. + * + * 5) The value of X + 12 is passed to rcu_segcblist_accelerate() but the + * freshly enqueued callback in RCU_NEXT_TAIL can't move to + * RCU_NEXT_READY_TAIL which already has callbacks for a previous grace + * period (gp_num = X + 8). So acceleration fails. + */ + s = rcu_seq_snap(&ssp->srcu_gp_seq); rcu_segcblist_advance(&sdp->srcu_cblist, rcu_seq_current(&ssp->srcu_gp_seq)); - s = rcu_seq_snap(&ssp->srcu_gp_seq); - (void)rcu_segcblist_accelerate(&sdp->srcu_cblist, s); + WARN_ON_ONCE(!rcu_segcblist_accelerate(&sdp->srcu_cblist, s) && rhp); if (ULONG_CMP_LT(sdp->srcu_gp_seq_needed, s)) { sdp->srcu_gp_seq_needed = s; needgp = true; diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 06d52525407b8..71cad4f1323c6 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -646,8 +646,8 @@ static inline bool __rb_time_read(rb_time_t *t, u64 *ret, unsigned long *cnt) *cnt = rb_time_cnt(top); - /* If top and msb counts don't match, this interrupted a write */ - if (*cnt != rb_time_cnt(msb)) + /* If top, msb or bottom counts don't match, this interrupted a write */ + if (*cnt != rb_time_cnt(msb) || *cnt != rb_time_cnt(bottom)) return false; /* The shift to msb will lose its cnt bits */ diff --git a/lib/Makefile b/lib/Makefile index 5ffe72ec99797..6f1611d053e6a 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -361,6 +361,8 @@ obj-$(CONFIG_SBITMAP) += sbitmap.o obj-$(CONFIG_PARMAN) += parman.o +obj-y += group_cpus.o + # GCC library routines obj-$(CONFIG_GENERIC_LIB_ASHLDI3) += ashldi3.o obj-$(CONFIG_GENERIC_LIB_ASHRDI3) += ashrdi3.o diff --git a/lib/group_cpus.c b/lib/group_cpus.c new file mode 100644 index 0000000000000..0292611901b8b --- /dev/null +++ b/lib/group_cpus.c @@ -0,0 +1,438 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2016 Thomas Gleixner. + * Copyright (C) 2016-2017 Christoph Hellwig. + */ +#include +#include +#include +#include +#include + +#ifdef CONFIG_SMP + +static void grp_spread_init_one(struct cpumask *irqmsk, struct cpumask *nmsk, + unsigned int cpus_per_grp) +{ + const struct cpumask *siblmsk; + int cpu, sibl; + + for ( ; cpus_per_grp > 0; ) { + cpu = cpumask_first(nmsk); + + /* Should not happen, but I'm too lazy to think about it */ + if (cpu >= nr_cpu_ids) + return; + + cpumask_clear_cpu(cpu, nmsk); + cpumask_set_cpu(cpu, irqmsk); + cpus_per_grp--; + + /* If the cpu has siblings, use them first */ + siblmsk = topology_sibling_cpumask(cpu); + for (sibl = -1; cpus_per_grp > 0; ) { + sibl = cpumask_next(sibl, siblmsk); + if (sibl >= nr_cpu_ids) + break; + if (!cpumask_test_and_clear_cpu(sibl, nmsk)) + continue; + cpumask_set_cpu(sibl, irqmsk); + cpus_per_grp--; + } + } +} + +static cpumask_var_t *alloc_node_to_cpumask(void) +{ + cpumask_var_t *masks; + int node; + + masks = kcalloc(nr_node_ids, sizeof(cpumask_var_t), GFP_KERNEL); + if (!masks) + return NULL; + + for (node = 0; node < nr_node_ids; node++) { + if (!zalloc_cpumask_var(&masks[node], GFP_KERNEL)) + goto out_unwind; + } + + return masks; + +out_unwind: + while (--node >= 0) + free_cpumask_var(masks[node]); + kfree(masks); + return NULL; +} + +static void free_node_to_cpumask(cpumask_var_t *masks) +{ + int node; + + for (node = 0; node < nr_node_ids; node++) + free_cpumask_var(masks[node]); + kfree(masks); +} + +static void build_node_to_cpumask(cpumask_var_t *masks) +{ + int cpu; + + for_each_possible_cpu(cpu) + cpumask_set_cpu(cpu, masks[cpu_to_node(cpu)]); +} + +static int get_nodes_in_cpumask(cpumask_var_t *node_to_cpumask, + const struct cpumask *mask, nodemask_t *nodemsk) +{ + int n, nodes = 0; + + /* Calculate the number of nodes in the supplied affinity mask */ + for_each_node(n) { + if (cpumask_intersects(mask, node_to_cpumask[n])) { + node_set(n, *nodemsk); + nodes++; + } + } + return nodes; +} + +struct node_groups { + unsigned id; + + union { + unsigned ngroups; + unsigned ncpus; + }; +}; + +static int ncpus_cmp_func(const void *l, const void *r) +{ + const struct node_groups *ln = l; + const struct node_groups *rn = r; + + return ln->ncpus - rn->ncpus; +} + +/* + * Allocate group number for each node, so that for each node: + * + * 1) the allocated number is >= 1 + * + * 2) the allocated number is <= active CPU number of this node + * + * The actual allocated total groups may be less than @numgrps when + * active total CPU number is less than @numgrps. + * + * Active CPUs means the CPUs in '@cpu_mask AND @node_to_cpumask[]' + * for each node. + */ +static void alloc_nodes_groups(unsigned int numgrps, + cpumask_var_t *node_to_cpumask, + const struct cpumask *cpu_mask, + const nodemask_t nodemsk, + struct cpumask *nmsk, + struct node_groups *node_groups) +{ + unsigned n, remaining_ncpus = 0; + + for (n = 0; n < nr_node_ids; n++) { + node_groups[n].id = n; + node_groups[n].ncpus = UINT_MAX; + } + + for_each_node_mask(n, nodemsk) { + unsigned ncpus; + + cpumask_and(nmsk, cpu_mask, node_to_cpumask[n]); + ncpus = cpumask_weight(nmsk); + + if (!ncpus) + continue; + remaining_ncpus += ncpus; + node_groups[n].ncpus = ncpus; + } + + numgrps = min_t(unsigned, remaining_ncpus, numgrps); + + sort(node_groups, nr_node_ids, sizeof(node_groups[0]), + ncpus_cmp_func, NULL); + + /* + * Allocate groups for each node according to the ratio of this + * node's nr_cpus to remaining un-assigned ncpus. 'numgrps' is + * bigger than number of active numa nodes. Always start the + * allocation from the node with minimized nr_cpus. + * + * This way guarantees that each active node gets allocated at + * least one group, and the theory is simple: over-allocation + * is only done when this node is assigned by one group, so + * other nodes will be allocated >= 1 groups, since 'numgrps' is + * bigger than number of numa nodes. + * + * One perfect invariant is that number of allocated groups for + * each node is <= CPU count of this node: + * + * 1) suppose there are two nodes: A and B + * ncpu(X) is CPU count of node X + * grps(X) is the group count allocated to node X via this + * algorithm + * + * ncpu(A) <= ncpu(B) + * ncpu(A) + ncpu(B) = N + * grps(A) + grps(B) = G + * + * grps(A) = max(1, round_down(G * ncpu(A) / N)) + * grps(B) = G - grps(A) + * + * both N and G are integer, and 2 <= G <= N, suppose + * G = N - delta, and 0 <= delta <= N - 2 + * + * 2) obviously grps(A) <= ncpu(A) because: + * + * if grps(A) is 1, then grps(A) <= ncpu(A) given + * ncpu(A) >= 1 + * + * otherwise, + * grps(A) <= G * ncpu(A) / N <= ncpu(A), given G <= N + * + * 3) prove how grps(B) <= ncpu(B): + * + * if round_down(G * ncpu(A) / N) == 0, vecs(B) won't be + * over-allocated, so grps(B) <= ncpu(B), + * + * otherwise: + * + * grps(A) = + * round_down(G * ncpu(A) / N) = + * round_down((N - delta) * ncpu(A) / N) = + * round_down((N * ncpu(A) - delta * ncpu(A)) / N) >= + * round_down((N * ncpu(A) - delta * N) / N) = + * cpu(A) - delta + * + * then: + * + * grps(A) - G >= ncpu(A) - delta - G + * => + * G - grps(A) <= G + delta - ncpu(A) + * => + * grps(B) <= N - ncpu(A) + * => + * grps(B) <= cpu(B) + * + * For nodes >= 3, it can be thought as one node and another big + * node given that is exactly what this algorithm is implemented, + * and we always re-calculate 'remaining_ncpus' & 'numgrps', and + * finally for each node X: grps(X) <= ncpu(X). + * + */ + for (n = 0; n < nr_node_ids; n++) { + unsigned ngroups, ncpus; + + if (node_groups[n].ncpus == UINT_MAX) + continue; + + WARN_ON_ONCE(numgrps == 0); + + ncpus = node_groups[n].ncpus; + ngroups = max_t(unsigned, 1, + numgrps * ncpus / remaining_ncpus); + WARN_ON_ONCE(ngroups > ncpus); + + node_groups[n].ngroups = ngroups; + + remaining_ncpus -= ncpus; + numgrps -= ngroups; + } +} + +static int __group_cpus_evenly(unsigned int startgrp, unsigned int numgrps, + cpumask_var_t *node_to_cpumask, + const struct cpumask *cpu_mask, + struct cpumask *nmsk, struct cpumask *masks) +{ + unsigned int i, n, nodes, cpus_per_grp, extra_grps, done = 0; + unsigned int last_grp = numgrps; + unsigned int curgrp = startgrp; + nodemask_t nodemsk = NODE_MASK_NONE; + struct node_groups *node_groups; + + if (cpumask_empty(cpu_mask)) + return 0; + + nodes = get_nodes_in_cpumask(node_to_cpumask, cpu_mask, &nodemsk); + + /* + * If the number of nodes in the mask is greater than or equal the + * number of groups we just spread the groups across the nodes. + */ + if (numgrps <= nodes) { + for_each_node_mask(n, nodemsk) { + /* Ensure that only CPUs which are in both masks are set */ + cpumask_and(nmsk, cpu_mask, node_to_cpumask[n]); + cpumask_or(&masks[curgrp], &masks[curgrp], nmsk); + if (++curgrp == last_grp) + curgrp = 0; + } + return numgrps; + } + + node_groups = kcalloc(nr_node_ids, + sizeof(struct node_groups), + GFP_KERNEL); + if (!node_groups) + return -ENOMEM; + + /* allocate group number for each node */ + alloc_nodes_groups(numgrps, node_to_cpumask, cpu_mask, + nodemsk, nmsk, node_groups); + for (i = 0; i < nr_node_ids; i++) { + unsigned int ncpus, v; + struct node_groups *nv = &node_groups[i]; + + if (nv->ngroups == UINT_MAX) + continue; + + /* Get the cpus on this node which are in the mask */ + cpumask_and(nmsk, cpu_mask, node_to_cpumask[nv->id]); + ncpus = cpumask_weight(nmsk); + if (!ncpus) + continue; + + WARN_ON_ONCE(nv->ngroups > ncpus); + + /* Account for rounding errors */ + extra_grps = ncpus - nv->ngroups * (ncpus / nv->ngroups); + + /* Spread allocated groups on CPUs of the current node */ + for (v = 0; v < nv->ngroups; v++, curgrp++) { + cpus_per_grp = ncpus / nv->ngroups; + + /* Account for extra groups to compensate rounding errors */ + if (extra_grps) { + cpus_per_grp++; + --extra_grps; + } + + /* + * wrapping has to be considered given 'startgrp' + * may start anywhere + */ + if (curgrp >= last_grp) + curgrp = 0; + grp_spread_init_one(&masks[curgrp], nmsk, + cpus_per_grp); + } + done += nv->ngroups; + } + kfree(node_groups); + return done; +} + +/** + * group_cpus_evenly - Group all CPUs evenly per NUMA/CPU locality + * @numgrps: number of groups + * + * Return: cpumask array if successful, NULL otherwise. And each element + * includes CPUs assigned to this group + * + * Try to put close CPUs from viewpoint of CPU and NUMA locality into + * same group, and run two-stage grouping: + * 1) allocate present CPUs on these groups evenly first + * 2) allocate other possible CPUs on these groups evenly + * + * We guarantee in the resulted grouping that all CPUs are covered, and + * no same CPU is assigned to multiple groups + */ +struct cpumask *group_cpus_evenly(unsigned int numgrps) +{ + unsigned int curgrp = 0, nr_present = 0, nr_others = 0; + cpumask_var_t *node_to_cpumask; + cpumask_var_t nmsk, npresmsk; + int ret = -ENOMEM; + struct cpumask *masks = NULL; + + if (!zalloc_cpumask_var(&nmsk, GFP_KERNEL)) + return NULL; + + if (!zalloc_cpumask_var(&npresmsk, GFP_KERNEL)) + goto fail_nmsk; + + node_to_cpumask = alloc_node_to_cpumask(); + if (!node_to_cpumask) + goto fail_npresmsk; + + masks = kcalloc(numgrps, sizeof(*masks), GFP_KERNEL); + if (!masks) + goto fail_node_to_cpumask; + + build_node_to_cpumask(node_to_cpumask); + + /* + * Make a local cache of 'cpu_present_mask', so the two stages + * spread can observe consistent 'cpu_present_mask' without holding + * cpu hotplug lock, then we can reduce deadlock risk with cpu + * hotplug code. + * + * Here CPU hotplug may happen when reading `cpu_present_mask`, and + * we can live with the case because it only affects that hotplug + * CPU is handled in the 1st or 2nd stage, and either way is correct + * from API user viewpoint since 2-stage spread is sort of + * optimization. + */ + cpumask_copy(npresmsk, data_race(cpu_present_mask)); + + /* grouping present CPUs first */ + ret = __group_cpus_evenly(curgrp, numgrps, node_to_cpumask, + npresmsk, nmsk, masks); + if (ret < 0) + goto fail_build_affinity; + nr_present = ret; + + /* + * Allocate non present CPUs starting from the next group to be + * handled. If the grouping of present CPUs already exhausted the + * group space, assign the non present CPUs to the already + * allocated out groups. + */ + if (nr_present >= numgrps) + curgrp = 0; + else + curgrp = nr_present; + cpumask_andnot(npresmsk, cpu_possible_mask, npresmsk); + ret = __group_cpus_evenly(curgrp, numgrps, node_to_cpumask, + npresmsk, nmsk, masks); + if (ret >= 0) + nr_others = ret; + + fail_build_affinity: + if (ret >= 0) + WARN_ON(nr_present + nr_others < numgrps); + + fail_node_to_cpumask: + free_node_to_cpumask(node_to_cpumask); + + fail_npresmsk: + free_cpumask_var(npresmsk); + + fail_nmsk: + free_cpumask_var(nmsk); + if (ret < 0) { + kfree(masks); + return NULL; + } + return masks; +} +#else /* CONFIG_SMP */ +struct cpumask *group_cpus_evenly(unsigned int numgrps) +{ + struct cpumask *masks = kcalloc(numgrps, sizeof(*masks), GFP_KERNEL); + + if (!masks) + return NULL; + + /* assign all CPUs(cpu 0) to the 1st group only */ + cpumask_copy(&masks[0], cpu_possible_mask); + return masks; +} +#endif /* CONFIG_SMP */ diff --git a/mm/filemap.c b/mm/filemap.c index 10fe6430693bd..2809b1174f04e 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -4005,6 +4005,8 @@ bool filemap_release_folio(struct folio *folio, gfp_t gfp) struct address_space * const mapping = folio->mapping; BUG_ON(!folio_test_locked(folio)); + if (!folio_needs_release(folio)) + return true; if (folio_test_writeback(folio)) return false; diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 2753fb54cdf38..59577946735b1 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2694,8 +2694,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list) gfp = current_gfp_context(mapping_gfp_mask(mapping) & GFP_RECLAIM_MASK); - if (folio_test_private(folio) && - !filemap_release_folio(folio, gfp)) { + if (!filemap_release_folio(folio, gfp)) { ret = -EBUSY; goto out; } diff --git a/mm/internal.h b/mm/internal.h index 6b7ef495b56d3..d01130efce5fb 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -163,6 +163,17 @@ static inline void set_page_refcounted(struct page *page) set_page_count(page, 1); } +/* + * Return true if a folio needs ->release_folio() calling upon it. + */ +static inline bool folio_needs_release(struct folio *folio) +{ + struct address_space *mapping = folio_mapping(folio); + + return folio_has_private(folio) || + (mapping && mapping_release_always(mapping)); +} + extern unsigned long highest_memmap_pfn; /* diff --git a/mm/khugepaged.c b/mm/khugepaged.c index ef72d3df4b65b..65bd0b105266a 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -1818,6 +1818,7 @@ static int collapse_file(struct mm_struct *mm, unsigned long addr, xas_set(&xas, start); for (index = start; index < end; index++) { struct page *page = xas_next(&xas); + struct folio *folio; VM_BUG_ON(index != xas.xa_index); if (is_shmem) { @@ -1844,8 +1845,6 @@ static int collapse_file(struct mm_struct *mm, unsigned long addr, } if (xa_is_value(page) || !PageUptodate(page)) { - struct folio *folio; - xas_unlock_irq(&xas); /* swap in or instantiate fallocated page */ if (shmem_get_folio(mapping->host, index, @@ -1933,13 +1932,15 @@ static int collapse_file(struct mm_struct *mm, unsigned long addr, goto out_unlock; } - if (page_mapping(page) != mapping) { + folio = page_folio(page); + + if (folio_mapping(folio) != mapping) { result = SCAN_TRUNCATED; goto out_unlock; } - if (!is_shmem && (PageDirty(page) || - PageWriteback(page))) { + if (!is_shmem && (folio_test_dirty(folio) || + folio_test_writeback(folio))) { /* * khugepaged only works on read-only fd, so this * page is dirty because it hasn't been flushed @@ -1949,20 +1950,19 @@ static int collapse_file(struct mm_struct *mm, unsigned long addr, goto out_unlock; } - if (isolate_lru_page(page)) { + if (folio_isolate_lru(folio)) { result = SCAN_DEL_PAGE_LRU; goto out_unlock; } - if (page_has_private(page) && - !try_to_release_page(page, GFP_KERNEL)) { + if (!filemap_release_folio(folio, GFP_KERNEL)) { result = SCAN_PAGE_HAS_PRIVATE; - putback_lru_page(page); + folio_putback_lru(folio); goto out_unlock; } - if (page_mapped(page)) - try_to_unmap(page_folio(page), + if (folio_mapped(folio)) + try_to_unmap(folio, TTU_IGNORE_MLOCK | TTU_BATCH_FLUSH); xas_lock_irq(&xas); diff --git a/mm/memory-failure.c b/mm/memory-failure.c index ebd717157c813..5b846ed5dcbe9 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -827,16 +827,15 @@ static int truncate_error_page(struct page *p, unsigned long pfn, int ret = MF_FAILED; if (mapping->a_ops->error_remove_page) { + struct folio *folio = page_folio(p); int err = mapping->a_ops->error_remove_page(mapping, p); - if (err != 0) { + if (err != 0) pr_info("%#lx: Failed to punch page: %d\n", pfn, err); - } else if (page_has_private(p) && - !try_to_release_page(p, GFP_NOIO)) { + else if (!filemap_release_folio(folio, GFP_NOIO)) pr_info("%#lx: failed to release buffers\n", pfn); - } else { + else ret = MF_RECOVERED; - } } else { /* * If the file system doesn't support it just invalidate diff --git a/mm/memory.c b/mm/memory.c index 0d1b3ee8fcd7a..fc8b264ec0cac 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3617,8 +3617,8 @@ EXPORT_SYMBOL_GPL(unmap_mapping_pages); void unmap_mapping_range(struct address_space *mapping, loff_t const holebegin, loff_t const holelen, int even_cows) { - pgoff_t hba = holebegin >> PAGE_SHIFT; - pgoff_t hlen = (holelen + PAGE_SIZE - 1) >> PAGE_SHIFT; + pgoff_t hba = (pgoff_t)(holebegin) >> PAGE_SHIFT; + pgoff_t hlen = ((pgoff_t)(holelen) + PAGE_SIZE - 1) >> PAGE_SHIFT; /* Check for overflow. */ if (sizeof(holelen) > sizeof(hlen)) { diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index bd2570b4f9b7b..3b9d3a4b43869 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1069,6 +1069,9 @@ void mhp_deinit_memmap_on_memory(unsigned long pfn, unsigned long nr_pages) kasan_remove_zero_shadow(__va(PFN_PHYS(pfn)), PFN_PHYS(nr_pages)); } +/* + * Must be called with mem_hotplug_lock in write mode. + */ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, struct zone *zone, struct memory_group *group) { @@ -1089,7 +1092,6 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, !IS_ALIGNED(pfn + nr_pages, PAGES_PER_SECTION))) return -EINVAL; - mem_hotplug_begin(); /* associate pfn range with the zone */ move_pfn_range_to_zone(zone, pfn, nr_pages, NULL, MIGRATE_ISOLATE); @@ -1148,7 +1150,6 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, writeback_set_ratelimit(); memory_notify(MEM_ONLINE, &arg); - mem_hotplug_done(); return 0; failed_addition: @@ -1157,7 +1158,6 @@ failed_addition: (((unsigned long long) pfn + nr_pages) << PAGE_SHIFT) - 1); memory_notify(MEM_CANCEL_ONLINE, &arg); remove_pfn_range_from_zone(zone, pfn, nr_pages); - mem_hotplug_done(); return ret; } @@ -1382,7 +1382,7 @@ int __ref add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags) ret = create_memory_block_devices(start, size, mhp_altmap.alloc, group); if (ret) { - arch_remove_memory(start, size, NULL); + arch_remove_memory(start, size, params.altmap); goto error; } @@ -1787,6 +1787,9 @@ static int count_system_ram_pages_cb(unsigned long start_pfn, return 0; } +/* + * Must be called with mem_hotplug_lock in write mode. + */ int __ref offline_pages(unsigned long start_pfn, unsigned long nr_pages, struct zone *zone, struct memory_group *group) { @@ -1809,8 +1812,6 @@ int __ref offline_pages(unsigned long start_pfn, unsigned long nr_pages, !IS_ALIGNED(start_pfn + nr_pages, PAGES_PER_SECTION))) return -EINVAL; - mem_hotplug_begin(); - /* * Don't allow to offline memory blocks that contain holes. * Consequently, memory blocks with holes can never get onlined @@ -1946,7 +1947,6 @@ int __ref offline_pages(unsigned long start_pfn, unsigned long nr_pages, memory_notify(MEM_OFFLINE, &arg); remove_pfn_range_from_zone(zone, start_pfn, nr_pages); - mem_hotplug_done(); return 0; failed_removal_isolated: @@ -1961,7 +1961,6 @@ failed_removal: (unsigned long long) start_pfn << PAGE_SHIFT, ((unsigned long long) end_pfn << PAGE_SHIFT) - 1, reason); - mem_hotplug_done(); return ret; } diff --git a/mm/migrate.c b/mm/migrate.c index 91bd69c61148e..c93dd6a31c31a 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -914,8 +914,7 @@ static int fallback_migrate_folio(struct address_space *mapping, * Buffers may be managed in a filesystem specific way. * We must have no buffers or drop them. */ - if (folio_test_private(src) && - !filemap_release_folio(src, GFP_KERNEL)) + if (!filemap_release_folio(src, GFP_KERNEL)) return mode == MIGRATE_SYNC ? -EAGAIN : -EBUSY; return migrate_folio(mapping, dst, src, mode); diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 7e9d8d857ecca..de5f69921b946 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -3078,7 +3078,7 @@ EXPORT_SYMBOL_GPL(folio_wait_writeback_killable); */ void folio_wait_stable(struct folio *folio) { - if (folio_inode(folio)->i_sb->s_iflags & SB_I_STABLE_WRITES) + if (mapping_stable_writes(folio_mapping(folio))) folio_wait_writeback(folio); } EXPORT_SYMBOL_GPL(folio_wait_stable); diff --git a/mm/truncate.c b/mm/truncate.c index c0be77e5c0083..0d4dd233f5187 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -19,7 +19,6 @@ #include #include #include -#include /* grr. try_to_release_page */ #include #include #include "internal.h" @@ -276,7 +275,7 @@ static long mapping_evict_folio(struct address_space *mapping, if (folio_ref_count(folio) > folio_nr_pages(folio) + folio_has_private(folio) + 1) return 0; - if (folio_has_private(folio) && !filemap_release_folio(folio, 0)) + if (!filemap_release_folio(folio, 0)) return 0; return remove_mapping(mapping, folio); @@ -581,8 +580,7 @@ static int invalidate_complete_folio2(struct address_space *mapping, if (folio->mapping != mapping) return 0; - if (folio_has_private(folio) && - !filemap_release_folio(folio, GFP_KERNEL)) + if (!filemap_release_folio(folio, GFP_KERNEL)) return 0; spin_lock(&mapping->host->i_lock); diff --git a/mm/vmscan.c b/mm/vmscan.c index 3f090faa6377f..9f3cfb7caa48d 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1992,7 +1992,7 @@ retry: * (refcount == 1) it can be freed. Otherwise, leave * the folio on the LRU so it is swappable. */ - if (folio_has_private(folio)) { + if (folio_needs_release(folio)) { if (!filemap_release_folio(folio, sc->gfp_mask)) goto activate_locked; if (!mapping && folio_ref_count(folio) == 1) { @@ -2618,9 +2618,9 @@ static void shrink_active_list(unsigned long nr_to_scan, } if (unlikely(buffer_heads_over_limit)) { - if (folio_test_private(folio) && folio_trylock(folio)) { - if (folio_test_private(folio)) - filemap_release_folio(folio, 0); + if (folio_needs_release(folio) && + folio_trylock(folio)) { + filemap_release_folio(folio, 0); folio_unlock(folio); } } diff --git a/net/can/j1939/socket.c b/net/can/j1939/socket.c index 9c828067b4481..b0be23559243c 100644 --- a/net/can/j1939/socket.c +++ b/net/can/j1939/socket.c @@ -974,6 +974,7 @@ static void __j1939_sk_errqueue(struct j1939_session *session, struct sock *sk, struct sock_exterr_skb *serr; struct sk_buff *skb; char *state = "UNK"; + u32 tsflags; int err; jsk = j1939_sk(sk); @@ -981,13 +982,14 @@ static void __j1939_sk_errqueue(struct j1939_session *session, struct sock *sk, if (!(jsk->state & J1939_SOCK_ERRQUEUE)) return; + tsflags = READ_ONCE(sk->sk_tsflags); switch (type) { case J1939_ERRQUEUE_TX_ACK: - if (!(sk->sk_tsflags & SOF_TIMESTAMPING_TX_ACK)) + if (!(tsflags & SOF_TIMESTAMPING_TX_ACK)) return; break; case J1939_ERRQUEUE_TX_SCHED: - if (!(sk->sk_tsflags & SOF_TIMESTAMPING_TX_SCHED)) + if (!(tsflags & SOF_TIMESTAMPING_TX_SCHED)) return; break; case J1939_ERRQUEUE_TX_ABORT: @@ -997,7 +999,7 @@ static void __j1939_sk_errqueue(struct j1939_session *session, struct sock *sk, case J1939_ERRQUEUE_RX_DPO: fallthrough; case J1939_ERRQUEUE_RX_ABORT: - if (!(sk->sk_tsflags & SOF_TIMESTAMPING_RX_SOFTWARE)) + if (!(tsflags & SOF_TIMESTAMPING_RX_SOFTWARE)) return; break; default: @@ -1054,7 +1056,7 @@ static void __j1939_sk_errqueue(struct j1939_session *session, struct sock *sk, } serr->opt_stats = true; - if (sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID) + if (tsflags & SOF_TIMESTAMPING_OPT_ID) serr->ee.ee_data = session->tskey; netdev_dbg(session->priv->ndev, "%s: 0x%p tskey: %i, state: %s\n", diff --git a/net/can/raw.c b/net/can/raw.c index 8c104339d538d..488320738e319 100644 --- a/net/can/raw.c +++ b/net/can/raw.c @@ -881,6 +881,7 @@ static int raw_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) skb->dev = dev; skb->priority = sk->sk_priority; + skb->mark = sk->sk_mark; skb->tstamp = sockc.transmit_time; skb_setup_tx_timestamp(skb, sockc.tsflags); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 73b1e0e53534e..8a819d0a7bfb0 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -4913,7 +4913,7 @@ static void __skb_complete_tx_timestamp(struct sk_buff *skb, serr->ee.ee_info = tstype; serr->opt_stats = opt_stats; serr->header.h4.iif = skb->dev ? skb->dev->ifindex : 0; - if (sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID) { + if (READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_OPT_ID) { serr->ee.ee_data = skb_shinfo(skb)->tskey; if (sk_is_tcp(sk)) serr->ee.ee_data -= atomic_read(&sk->sk_tskey); @@ -4969,21 +4969,23 @@ void __skb_tstamp_tx(struct sk_buff *orig_skb, { struct sk_buff *skb; bool tsonly, opt_stats = false; + u32 tsflags; if (!sk) return; - if (!hwtstamps && !(sk->sk_tsflags & SOF_TIMESTAMPING_OPT_TX_SWHW) && + tsflags = READ_ONCE(sk->sk_tsflags); + if (!hwtstamps && !(tsflags & SOF_TIMESTAMPING_OPT_TX_SWHW) && skb_shinfo(orig_skb)->tx_flags & SKBTX_IN_PROGRESS) return; - tsonly = sk->sk_tsflags & SOF_TIMESTAMPING_OPT_TSONLY; + tsonly = tsflags & SOF_TIMESTAMPING_OPT_TSONLY; if (!skb_may_tx_timestamp(sk, tsonly)) return; if (tsonly) { #ifdef CONFIG_INET - if ((sk->sk_tsflags & SOF_TIMESTAMPING_OPT_STATS) && + if ((tsflags & SOF_TIMESTAMPING_OPT_STATS) && sk_is_tcp(sk)) { skb = tcp_get_timestamping_opt_stats(sk, orig_skb, ack_skb); diff --git a/net/core/skmsg.c b/net/core/skmsg.c index a5c1f67dc96ec..3818035ea0021 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -825,6 +825,8 @@ static void sk_psock_destroy(struct work_struct *work) if (psock->sk_redir) sock_put(psock->sk_redir); + if (psock->sk_pair) + sock_put(psock->sk_pair); sock_put(psock->sk); kfree(psock); } diff --git a/net/core/sock.c b/net/core/sock.c index 4305e55dbfba4..c50a14a02edd4 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -890,7 +890,7 @@ static int sock_timestamping_bind_phc(struct sock *sk, int phc_index) if (!match) return -EINVAL; - sk->sk_bind_phc = phc_index; + WRITE_ONCE(sk->sk_bind_phc, phc_index); return 0; } @@ -926,7 +926,7 @@ int sock_set_timestamping(struct sock *sk, int optname, return ret; } - sk->sk_tsflags = val; + WRITE_ONCE(sk->sk_tsflags, val); sock_valbool_flag(sk, SOCK_TSTAMP_NEW, optname == SO_TIMESTAMPING_NEW); if (val & SOF_TIMESTAMPING_RX_SOFTWARE) @@ -1704,9 +1704,16 @@ int sk_getsockopt(struct sock *sk, int level, int optname, break; case SO_TIMESTAMPING_OLD: + case SO_TIMESTAMPING_NEW: lv = sizeof(v.timestamping); - v.timestamping.flags = sk->sk_tsflags; - v.timestamping.bind_phc = sk->sk_bind_phc; + /* For the later-added case SO_TIMESTAMPING_NEW: Be strict about only + * returning the flags when they were set through the same option. + * Don't change the beviour for the old case SO_TIMESTAMPING_OLD. + */ + if (optname == SO_TIMESTAMPING_OLD || sock_flag(sk, SOCK_TSTAMP_NEW)) { + v.timestamping.flags = READ_ONCE(sk->sk_tsflags); + v.timestamping.bind_phc = READ_ONCE(sk->sk_bind_phc); + } break; case SO_RCVTIMEO_OLD: @@ -2764,6 +2771,7 @@ int __sock_cmsg_send(struct sock *sk, struct msghdr *msg, struct cmsghdr *cmsg, sockc->mark = *(u32 *)CMSG_DATA(cmsg); break; case SO_TIMESTAMPING_OLD: + case SO_TIMESTAMPING_NEW: if (cmsg->cmsg_len != CMSG_LEN(sizeof(u32))) return -EINVAL; diff --git a/net/core/sock_map.c b/net/core/sock_map.c index 38e01f82f2ef3..91140bc0541f3 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -538,6 +538,8 @@ static bool sock_map_sk_state_allowed(const struct sock *sk) { if (sk_is_tcp(sk)) return (1 << sk->sk_state) & (TCPF_ESTABLISHED | TCPF_LISTEN); + if (sk_is_stream_unix(sk)) + return (1 << sk->sk_state) & TCPF_ESTABLISHED; return true; } diff --git a/net/dns_resolver/dns_key.c b/net/dns_resolver/dns_key.c index 03f8f33dc134c..8324e9f970668 100644 --- a/net/dns_resolver/dns_key.c +++ b/net/dns_resolver/dns_key.c @@ -91,8 +91,6 @@ const struct cred *dns_resolver_cache; static int dns_resolver_preparse(struct key_preparsed_payload *prep) { - const struct dns_server_list_v1_header *v1; - const struct dns_payload_header *bin; struct user_key_payload *upayload; unsigned long derrno; int ret; @@ -103,27 +101,28 @@ dns_resolver_preparse(struct key_preparsed_payload *prep) return -EINVAL; if (data[0] == 0) { + const struct dns_server_list_v1_header *v1; + /* It may be a server list. */ - if (datalen <= sizeof(*bin)) + if (datalen <= sizeof(*v1)) return -EINVAL; - bin = (const struct dns_payload_header *)data; - kenter("[%u,%u],%u", bin->content, bin->version, datalen); - if (bin->content != DNS_PAYLOAD_IS_SERVER_LIST) { + v1 = (const struct dns_server_list_v1_header *)data; + kenter("[%u,%u],%u", v1->hdr.content, v1->hdr.version, datalen); + if (v1->hdr.content != DNS_PAYLOAD_IS_SERVER_LIST) { pr_warn_ratelimited( "dns_resolver: Unsupported content type (%u)\n", - bin->content); + v1->hdr.content); return -EINVAL; } - if (bin->version != 1) { + if (v1->hdr.version != 1) { pr_warn_ratelimited( "dns_resolver: Unsupported server list version (%u)\n", - bin->version); + v1->hdr.version); return -EINVAL; } - v1 = (const struct dns_server_list_v1_header *)bin; if ((v1->status != DNS_LOOKUP_GOOD && v1->status != DNS_LOOKUP_GOOD_WITH_BAD)) { if (prep->expiry == TIME64_MAX) diff --git a/net/ethtool/netlink.c b/net/ethtool/netlink.c index 1a4c11356c96c..fc4ccecf9495c 100644 --- a/net/ethtool/netlink.c +++ b/net/ethtool/netlink.c @@ -509,7 +509,7 @@ lock_and_cont: cont: idx++; } - + ret = 0; } rtnl_unlock(); diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 5d379df90c826..347c3768df6e8 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -838,6 +838,21 @@ int inet_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) } EXPORT_SYMBOL(inet_sendmsg); +void inet_splice_eof(struct socket *sock) +{ + const struct proto *prot; + struct sock *sk = sock->sk; + + if (unlikely(inet_send_prepare(sk))) + return; + + /* IPV6_ADDRFORM can change sk->sk_prot under us. */ + prot = READ_ONCE(sk->sk_prot); + if (prot->splice_eof) + prot->splice_eof(sock); +} +EXPORT_SYMBOL_GPL(inet_splice_eof); + ssize_t inet_sendpage(struct socket *sock, struct page *page, int offset, size_t size, int flags) { @@ -1057,6 +1072,7 @@ const struct proto_ops inet_stream_ops = { #ifdef CONFIG_MMU .mmap = tcp_mmap, #endif + .splice_eof = inet_splice_eof, .sendpage = inet_sendpage, .splice_read = tcp_splice_read, .read_sock = tcp_read_sock, @@ -1091,6 +1107,7 @@ const struct proto_ops inet_dgram_ops = { .read_skb = udp_read_skb, .recvmsg = inet_recvmsg, .mmap = sock_no_mmap, + .splice_eof = inet_splice_eof, .sendpage = inet_sendpage, .set_peek_off = sk_set_peek_off, #ifdef CONFIG_COMPAT @@ -1122,6 +1139,7 @@ static const struct proto_ops inet_sockraw_ops = { .sendmsg = inet_sendmsg, .recvmsg = inet_recvmsg, .mmap = sock_no_mmap, + .splice_eof = inet_splice_eof, .sendpage = inet_sendpage, #ifdef CONFIG_COMPAT .compat_ioctl = inet_compat_ioctl, diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 493c679ea54f3..e19ef88ae181f 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -990,8 +990,8 @@ static int __ip_append_data(struct sock *sk, mtu = cork->gso_size ? IP_MAX_MTU : cork->fragsize; paged = !!cork->gso_size; - if (cork->tx_flags & SKBTX_ANY_SW_TSTAMP && - sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID) + if (cork->tx_flags & SKBTX_ANY_TSTAMP && + READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_OPT_ID) tskey = atomic_inc_return(&sk->sk_tskey) - 1; hh_len = LL_RESERVED_SPACE(rt->dst.dev); diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 63aa52becd880..c1fb7580ea581 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -509,7 +509,7 @@ static bool ipv4_datagram_support_cmsg(const struct sock *sk, * or without payload (SOF_TIMESTAMPING_OPT_TSONLY). */ info = PKTINFO_SKB_CB(skb); - if (!(sk->sk_tsflags & SOF_TIMESTAMPING_OPT_CMSG) || + if (!(READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_OPT_CMSG) || !info->ipi_ifindex) return false; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 58409ea2da0af..0b7844a8d5711 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1492,6 +1492,22 @@ int tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) } EXPORT_SYMBOL(tcp_sendmsg); +void tcp_splice_eof(struct socket *sock) +{ + struct sock *sk = sock->sk; + struct tcp_sock *tp = tcp_sk(sk); + int mss_now, size_goal; + + if (!tcp_write_queue_tail(sk)) + return; + + lock_sock(sk); + mss_now = tcp_send_mss(sk, &size_goal, 0); + tcp_push(sk, 0, mss_now, tp->nonagle, size_goal); + release_sock(sk); +} +EXPORT_SYMBOL_GPL(tcp_splice_eof); + /* * Handle reading urgent data. BSD has very simple semantics for * this, no blocking and very strange errors 8) @@ -2359,14 +2375,14 @@ void tcp_recv_timestamp(struct msghdr *msg, const struct sock *sk, } } - if (sk->sk_tsflags & SOF_TIMESTAMPING_SOFTWARE) + if (READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_SOFTWARE) has_timestamping = true; else tss->ts[0] = (struct timespec64) {0}; } if (tss->ts[2].tv_sec || tss->ts[2].tv_nsec) { - if (sk->sk_tsflags & SOF_TIMESTAMPING_RAW_HARDWARE) + if (READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_RAW_HARDWARE) has_timestamping = true; else tss->ts[2] = (struct timespec64) {0}; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 7ebbbe561e402..be2c807eed15d 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -3067,6 +3067,7 @@ struct proto tcp_prot = { .keepalive = tcp_set_keepalive, .recvmsg = tcp_recvmsg, .sendmsg = tcp_sendmsg, + .splice_eof = tcp_splice_eof, .sendpage = tcp_sendpage, .backlog_rcv = tcp_v4_do_rcv, .release_cb = tcp_release_cb, diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 65abc92a81bd0..5672d9a86c5d2 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -733,7 +733,7 @@ int __udp4_lib_err(struct sk_buff *skb, u32 info, struct udp_table *udptable) iph->saddr, uh->source, skb->dev->ifindex, inet_sdif(skb), udptable, NULL); - if (!sk || udp_sk(sk)->encap_type) { + if (!sk || READ_ONCE(udp_sk(sk)->encap_type)) { /* No socket for error: try tunnels before discarding */ if (static_branch_unlikely(&udp_encap_needed_key)) { sk = __udp4_lib_err_encap(net, iph, uh, udptable, sk, skb, @@ -1068,7 +1068,7 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) __be16 dport; u8 tos; int err, is_udplite = IS_UDPLITE(sk); - int corkreq = READ_ONCE(up->corkflag) || msg->msg_flags&MSG_MORE; + int corkreq = udp_test_bit(CORK, sk) || msg->msg_flags & MSG_MORE; int (*getfrag)(void *, char *, int, int, int, struct sk_buff *); struct sk_buff *skb; struct ip_options_data opt_copy; @@ -1332,57 +1332,33 @@ do_confirm: } EXPORT_SYMBOL(udp_sendmsg); -int udp_sendpage(struct sock *sk, struct page *page, int offset, - size_t size, int flags) +void udp_splice_eof(struct socket *sock) { - struct inet_sock *inet = inet_sk(sk); + struct sock *sk = sock->sk; struct udp_sock *up = udp_sk(sk); - int ret; - if (flags & MSG_SENDPAGE_NOTLAST) - flags |= MSG_MORE; - - if (!up->pending) { - struct msghdr msg = { .msg_flags = flags|MSG_MORE }; - - /* Call udp_sendmsg to specify destination address which - * sendpage interface can't pass. - * This will succeed only when the socket is connected. - */ - ret = udp_sendmsg(sk, &msg, 0); - if (ret < 0) - return ret; - } + if (!up->pending || udp_test_bit(CORK, sk)) + return; lock_sock(sk); + if (up->pending && !udp_test_bit(CORK, sk)) + udp_push_pending_frames(sk); + release_sock(sk); +} +EXPORT_SYMBOL_GPL(udp_splice_eof); - if (unlikely(!up->pending)) { - release_sock(sk); - - net_dbg_ratelimited("cork failed\n"); - return -EINVAL; - } +int udp_sendpage(struct sock *sk, struct page *page, int offset, + size_t size, int flags) +{ + struct bio_vec bvec; + struct msghdr msg = { .msg_flags = flags | MSG_SPLICE_PAGES }; - ret = ip_append_page(sk, &inet->cork.fl.u.ip4, - page, offset, size, flags); - if (ret == -EOPNOTSUPP) { - release_sock(sk); - return sock_no_sendpage(sk->sk_socket, page, offset, - size, flags); - } - if (ret < 0) { - udp_flush_pending_frames(sk); - goto out; - } + if (flags & MSG_SENDPAGE_NOTLAST) + msg.msg_flags |= MSG_MORE; - up->len += size; - if (!(READ_ONCE(up->corkflag) || (flags&MSG_MORE))) - ret = udp_push_pending_frames(sk); - if (!ret) - ret = size; -out: - release_sock(sk); - return ret; + bvec_set_page(&bvec, page, size, offset); + iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, &bvec, 1, size); + return udp_sendmsg(sk, &msg, size); } #define UDP_SKB_IS_STATELESS 0x80000000 @@ -1925,7 +1901,7 @@ try_again: (struct sockaddr *)sin); } - if (udp_sk(sk)->gro_enabled) + if (udp_test_bit(GRO_ENABLED, sk)) udp_cmsg_recv(msg, sk, skb); if (inet->cmsg_flags) @@ -2138,7 +2114,8 @@ static int udp_queue_rcv_one_skb(struct sock *sk, struct sk_buff *skb) } nf_reset_ct(skb); - if (static_branch_unlikely(&udp_encap_needed_key) && up->encap_type) { + if (static_branch_unlikely(&udp_encap_needed_key) && + READ_ONCE(up->encap_type)) { int (*encap_rcv)(struct sock *sk, struct sk_buff *skb); /* @@ -2669,7 +2646,7 @@ void udp_destroy_sock(struct sock *sk) if (encap_destroy) encap_destroy(sk); } - if (up->encap_enabled) + if (udp_test_bit(ENCAP_ENABLED, sk)) static_branch_dec(&udp_encap_needed_key); } } @@ -2697,9 +2674,9 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname, switch (optname) { case UDP_CORK: if (val != 0) { - WRITE_ONCE(up->corkflag, 1); + udp_set_bit(CORK, sk); } else { - WRITE_ONCE(up->corkflag, 0); + udp_clear_bit(CORK, sk); lock_sock(sk); push_pending_frames(sk); release_sock(sk); @@ -2723,10 +2700,8 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname, #endif fallthrough; case UDP_ENCAP_L2TPINUDP: - up->encap_type = val; - lock_sock(sk); - udp_tunnel_encap_enable(sk->sk_socket); - release_sock(sk); + WRITE_ONCE(up->encap_type, val); + udp_tunnel_encap_enable(sk); break; default: err = -ENOPROTOOPT; @@ -2735,11 +2710,11 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname, break; case UDP_NO_CHECK6_TX: - up->no_check6_tx = valbool; + udp_set_no_check6_tx(sk, valbool); break; case UDP_NO_CHECK6_RX: - up->no_check6_rx = valbool; + udp_set_no_check6_rx(sk, valbool); break; case UDP_SEGMENT: @@ -2749,14 +2724,12 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname, break; case UDP_GRO: - lock_sock(sk); /* when enabling GRO, accept the related GSO packet type */ if (valbool) - udp_tunnel_encap_enable(sk->sk_socket); - up->gro_enabled = valbool; - up->accept_udp_l4 = valbool; - release_sock(sk); + udp_tunnel_encap_enable(sk); + udp_assign_bit(GRO_ENABLED, sk, valbool); + udp_assign_bit(ACCEPT_L4, sk, valbool); break; /* @@ -2824,19 +2797,19 @@ int udp_lib_getsockopt(struct sock *sk, int level, int optname, switch (optname) { case UDP_CORK: - val = READ_ONCE(up->corkflag); + val = udp_test_bit(CORK, sk); break; case UDP_ENCAP: - val = up->encap_type; + val = READ_ONCE(up->encap_type); break; case UDP_NO_CHECK6_TX: - val = up->no_check6_tx; + val = udp_get_no_check6_tx(sk); break; case UDP_NO_CHECK6_RX: - val = up->no_check6_rx; + val = udp_get_no_check6_rx(sk); break; case UDP_SEGMENT: @@ -2844,7 +2817,7 @@ int udp_lib_getsockopt(struct sock *sk, int level, int optname, break; case UDP_GRO: - val = up->gro_enabled; + val = udp_test_bit(GRO_ENABLED, sk); break; /* The following two cannot be changed on UDP sockets, the return is @@ -2946,6 +2919,7 @@ struct proto udp_prot = { .getsockopt = udp_getsockopt, .sendmsg = udp_sendmsg, .recvmsg = udp_recvmsg, + .splice_eof = udp_splice_eof, .sendpage = udp_sendpage, .release_cb = ip4_datagram_release_cb, .hash = udp_lib_hash, diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index 6d1a4bec2614d..8096576fd9bde 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -549,10 +549,10 @@ struct sk_buff *udp_gro_receive(struct list_head *head, struct sk_buff *skb, NAPI_GRO_CB(skb)->is_flist = 0; if (!sk || !udp_sk(sk)->gro_receive) { if (skb->dev->features & NETIF_F_GRO_FRAGLIST) - NAPI_GRO_CB(skb)->is_flist = sk ? !udp_sk(sk)->gro_enabled : 1; + NAPI_GRO_CB(skb)->is_flist = sk ? !udp_test_bit(GRO_ENABLED, sk) : 1; if ((!sk && (skb->dev->features & NETIF_F_GRO_UDP_FWD)) || - (sk && udp_sk(sk)->gro_enabled) || NAPI_GRO_CB(skb)->is_flist) + (sk && udp_test_bit(GRO_ENABLED, sk)) || NAPI_GRO_CB(skb)->is_flist) return call_gro_receive(udp_gro_receive_segment, head, skb); /* no GRO, be sure flush the current packet */ diff --git a/net/ipv4/udp_tunnel_core.c b/net/ipv4/udp_tunnel_core.c index 5f8104cf082d0..732e21b75ba28 100644 --- a/net/ipv4/udp_tunnel_core.c +++ b/net/ipv4/udp_tunnel_core.c @@ -78,7 +78,7 @@ void setup_udp_tunnel_sock(struct net *net, struct socket *sock, udp_sk(sk)->gro_receive = cfg->gro_receive; udp_sk(sk)->gro_complete = cfg->gro_complete; - udp_tunnel_encap_enable(sock); + udp_tunnel_encap_enable(sk); } EXPORT_SYMBOL_GPL(setup_udp_tunnel_sock); diff --git a/net/ipv4/xfrm4_input.c b/net/ipv4/xfrm4_input.c index eac206a290d05..183f6dc372429 100644 --- a/net/ipv4/xfrm4_input.c +++ b/net/ipv4/xfrm4_input.c @@ -85,11 +85,11 @@ int xfrm4_udp_encap_rcv(struct sock *sk, struct sk_buff *skb) struct udphdr *uh; struct iphdr *iph; int iphlen, len; - __u8 *udpdata; __be32 *udpdata32; - __u16 encap_type = up->encap_type; + u16 encap_type; + encap_type = READ_ONCE(up->encap_type); /* if this is not encapsulated socket, then just return now */ if (!encap_type) return 1; diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index b5309ae87fd79..a2f29ca516000 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -711,6 +711,7 @@ const struct proto_ops inet6_stream_ops = { #ifdef CONFIG_MMU .mmap = tcp_mmap, #endif + .splice_eof = inet_splice_eof, .sendpage = inet_sendpage, .sendmsg_locked = tcp_sendmsg_locked, .sendpage_locked = tcp_sendpage_locked, diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 3c2b2a85de367..e9ae084d038d1 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -1506,8 +1506,8 @@ static int __ip6_append_data(struct sock *sk, mtu = cork->gso_size ? IP6_MAX_MTU : cork->fragsize; orig_mtu = mtu; - if (cork->tx_flags & SKBTX_ANY_SW_TSTAMP && - sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID) + if (cork->tx_flags & SKBTX_ANY_TSTAMP && + READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_OPT_ID) tskey = atomic_inc_return(&sk->sk_tskey) - 1; hh_len = LL_RESERVED_SPACE(rt->dst.dev); diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c index 4d5a27dd9a4b2..a5d7d1915ba7e 100644 --- a/net/ipv6/ping.c +++ b/net/ipv6/ping.c @@ -119,7 +119,7 @@ static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) return -EINVAL; ipcm6_init_sk(&ipc6, np); - ipc6.sockc.tsflags = sk->sk_tsflags; + ipc6.sockc.tsflags = READ_ONCE(sk->sk_tsflags); ipc6.sockc.mark = READ_ONCE(sk->sk_mark); fl6.flowi6_oif = oif; diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index df3abd9e5237c..dc31752a7edcc 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -776,7 +776,7 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) fl6.flowi6_uid = sk->sk_uid; ipcm6_init(&ipc6); - ipc6.sockc.tsflags = sk->sk_tsflags; + ipc6.sockc.tsflags = READ_ONCE(sk->sk_tsflags); ipc6.sockc.mark = fl6.flowi6_mark; if (sin6) { diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 7be89dcfd5fc5..ba9a22db5805c 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -2158,6 +2158,7 @@ struct proto tcpv6_prot = { .keepalive = tcp_set_keepalive, .recvmsg = tcp_recvmsg, .sendmsg = tcp_sendmsg, + .splice_eof = tcp_splice_eof, .sendpage = tcp_sendpage, .backlog_rcv = tcp_v6_do_rcv, .release_cb = tcp_release_cb, diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 64b36c2ba774a..961106eda69d0 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -440,7 +440,7 @@ try_again: (struct sockaddr *)sin6); } - if (udp_sk(sk)->gro_enabled) + if (udp_test_bit(GRO_ENABLED, sk)) udp_cmsg_recv(msg, sk, skb); if (np->rxopt.all) @@ -598,7 +598,7 @@ int __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt, sk = __udp6_lib_lookup(net, daddr, uh->dest, saddr, uh->source, inet6_iif(skb), inet6_sdif(skb), udptable, NULL); - if (!sk || udp_sk(sk)->encap_type) { + if (!sk || READ_ONCE(udp_sk(sk)->encap_type)) { /* No socket for error: try tunnels before discarding */ if (static_branch_unlikely(&udpv6_encap_needed_key)) { sk = __udp6_lib_err_encap(net, hdr, offset, uh, @@ -712,7 +712,8 @@ static int udpv6_queue_rcv_one_skb(struct sock *sk, struct sk_buff *skb) } nf_reset_ct(skb); - if (static_branch_unlikely(&udpv6_encap_needed_key) && up->encap_type) { + if (static_branch_unlikely(&udpv6_encap_needed_key) && + READ_ONCE(up->encap_type)) { int (*encap_rcv)(struct sock *sk, struct sk_buff *skb); /* @@ -882,7 +883,7 @@ start_lookup: /* If zero checksum and no_check is not on for * the socket then skip it. */ - if (!uh->check && !udp_sk(sk)->no_check6_rx) + if (!uh->check && !udp_get_no_check6_rx(sk)) continue; if (!first) { first = sk; @@ -1000,7 +1001,7 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, if (unlikely(rcu_dereference(sk->sk_rx_dst) != dst)) udp6_sk_rx_dst_set(sk, dst); - if (!uh->check && !udp_sk(sk)->no_check6_rx) { + if (!uh->check && !udp_get_no_check6_rx(sk)) { if (refcounted) sock_put(sk); goto report_csum_error; @@ -1022,7 +1023,7 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, /* Unicast */ sk = __udp6_lib_lookup_skb(skb, uh->source, uh->dest, udptable); if (sk) { - if (!uh->check && !udp_sk(sk)->no_check6_rx) + if (!uh->check && !udp_get_no_check6_rx(sk)) goto report_csum_error; return udp6_unicast_rcv_skb(sk, skb, uh); } @@ -1260,7 +1261,7 @@ static int udp_v6_send_skb(struct sk_buff *skb, struct flowi6 *fl6, kfree_skb(skb); return -EINVAL; } - if (udp_sk(sk)->no_check6_tx) { + if (udp_get_no_check6_tx(sk)) { kfree_skb(skb); return -EINVAL; } @@ -1281,7 +1282,7 @@ static int udp_v6_send_skb(struct sk_buff *skb, struct flowi6 *fl6, if (is_udplite) csum = udplite_csum(skb); - else if (udp_sk(sk)->no_check6_tx) { /* UDP csum disabled */ + else if (udp_get_no_check6_tx(sk)) { /* UDP csum disabled */ skb->ip_summed = CHECKSUM_NONE; goto send; } else if (skb->ip_summed == CHECKSUM_PARTIAL) { /* UDP hardware csum */ @@ -1351,14 +1352,14 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) int addr_len = msg->msg_namelen; bool connected = false; int ulen = len; - int corkreq = READ_ONCE(up->corkflag) || msg->msg_flags&MSG_MORE; + int corkreq = udp_test_bit(CORK, sk) || msg->msg_flags & MSG_MORE; int err; int is_udplite = IS_UDPLITE(sk); int (*getfrag)(void *, char *, int, int, int, struct sk_buff *); ipcm6_init(&ipc6); ipc6.gso_size = READ_ONCE(up->gso_size); - ipc6.sockc.tsflags = sk->sk_tsflags; + ipc6.sockc.tsflags = READ_ONCE(sk->sk_tsflags); ipc6.sockc.mark = READ_ONCE(sk->sk_mark); /* destination address check */ @@ -1657,6 +1658,20 @@ do_confirm: goto out; } +static void udpv6_splice_eof(struct socket *sock) +{ + struct sock *sk = sock->sk; + struct udp_sock *up = udp_sk(sk); + + if (!up->pending || udp_test_bit(CORK, sk)) + return; + + lock_sock(sk); + if (up->pending && !udp_test_bit(CORK, sk)) + udp_v6_push_pending_frames(sk); + release_sock(sk); +} + void udpv6_destroy_sock(struct sock *sk) { struct udp_sock *up = udp_sk(sk); @@ -1674,7 +1689,7 @@ void udpv6_destroy_sock(struct sock *sk) if (encap_destroy) encap_destroy(sk); } - if (up->encap_enabled) { + if (udp_test_bit(ENCAP_ENABLED, sk)) { static_branch_dec(&udpv6_encap_needed_key); udp_encap_disable(); } @@ -1768,6 +1783,7 @@ struct proto udpv6_prot = { .getsockopt = udpv6_getsockopt, .sendmsg = udpv6_sendmsg, .recvmsg = udpv6_recvmsg, + .splice_eof = udpv6_splice_eof, .release_cb = ip6_datagram_release_cb, .hash = udp_lib_hash, .unhash = udp_lib_unhash, diff --git a/net/ipv6/xfrm6_input.c b/net/ipv6/xfrm6_input.c index 4907ab241d6be..4156387248e40 100644 --- a/net/ipv6/xfrm6_input.c +++ b/net/ipv6/xfrm6_input.c @@ -81,14 +81,14 @@ int xfrm6_udp_encap_rcv(struct sock *sk, struct sk_buff *skb) struct ipv6hdr *ip6h; int len; int ip6hlen = sizeof(struct ipv6hdr); - __u8 *udpdata; __be32 *udpdata32; - __u16 encap_type = up->encap_type; + u16 encap_type; if (skb->protocol == htons(ETH_P_IP)) return xfrm4_udp_encap_rcv(sk, skb); + encap_type = READ_ONCE(up->encap_type); /* if this is not encapsulated socket, then just return now */ if (!encap_type) return 1; diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index 03608d3ded4b8..8d21ff25f1602 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -1139,9 +1139,9 @@ static void l2tp_tunnel_destruct(struct sock *sk) switch (tunnel->encap) { case L2TP_ENCAPTYPE_UDP: /* No longer an encapsulation socket. See net/ipv4/udp.c */ - (udp_sk(sk))->encap_type = 0; - (udp_sk(sk))->encap_rcv = NULL; - (udp_sk(sk))->encap_destroy = NULL; + WRITE_ONCE(udp_sk(sk)->encap_type, 0); + udp_sk(sk)->encap_rcv = NULL; + udp_sk(sk)->encap_destroy = NULL; break; case L2TP_ENCAPTYPE_IP: break; diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index d611783c2601f..8ed7769cae836 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -1899,6 +1899,17 @@ static void tcp_release_cb_override(struct sock *ssk) tcp_release_cb(ssk); } +static int tcp_abort_override(struct sock *ssk, int err) +{ + /* closing a listener subflow requires a great deal of care. + * keep it simple and just prevent such operation + */ + if (inet_sk_state_load(ssk) == TCP_LISTEN) + return -EINVAL; + + return tcp_abort(ssk, err); +} + static struct tcp_ulp_ops subflow_ulp_ops __read_mostly = { .name = "mptcp", .owner = THIS_MODULE, @@ -1942,6 +1953,7 @@ void __init mptcp_subflow_init(void) tcp_prot_override = tcp_prot; tcp_prot_override.release_cb = tcp_release_cb_override; + tcp_prot_override.diag_destroy = tcp_abort_override; #if IS_ENABLED(CONFIG_MPTCP_IPV6) /* In struct mptcp_subflow_request_sock, we assume the TCP request sock @@ -1977,6 +1989,7 @@ void __init mptcp_subflow_init(void) tcpv6_prot_override = tcpv6_prot; tcpv6_prot_override.release_cb = tcp_release_cb_override; + tcpv6_prot_override.diag_destroy = tcp_abort_override; #endif mptcp_diag_subflow_init(&subflow_ulp_ops); diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index 7243079ef3546..b452eb3ddcecb 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -994,7 +994,7 @@ ip_vs_prepare_tunneled_skb(struct sk_buff *skb, int skb_af, old_dsfield = ipv4_get_dsfield(old_iph); *ttl = old_iph->ttl; if (payload_len) - *payload_len = ntohs(old_iph->tot_len); + *payload_len = skb_ip_totlen(skb); } /* Implement full-functionality option for ECN encapsulation */ diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c index 81c26a96c30bb..c1d99cb370b44 100644 --- a/net/netfilter/nf_flow_table_core.c +++ b/net/netfilter/nf_flow_table_core.c @@ -314,12 +314,12 @@ int flow_offload_add(struct nf_flowtable *flow_table, struct flow_offload *flow) EXPORT_SYMBOL_GPL(flow_offload_add); void flow_offload_refresh(struct nf_flowtable *flow_table, - struct flow_offload *flow) + struct flow_offload *flow, bool force) { u32 timeout; timeout = nf_flowtable_time_stamp + flow_offload_get_timeout(flow); - if (timeout - READ_ONCE(flow->timeout) > HZ) + if (force || timeout - READ_ONCE(flow->timeout) > HZ) WRITE_ONCE(flow->timeout, timeout); else return; @@ -416,11 +416,18 @@ nf_flow_table_iterate(struct nf_flowtable *flow_table, return err; } +static bool nf_flow_custom_gc(struct nf_flowtable *flow_table, + const struct flow_offload *flow) +{ + return flow_table->type->gc && flow_table->type->gc(flow); +} + static void nf_flow_offload_gc_step(struct nf_flowtable *flow_table, struct flow_offload *flow, void *data) { if (nf_flow_has_expired(flow) || - nf_ct_is_dying(flow->ct)) + nf_ct_is_dying(flow->ct) || + nf_flow_custom_gc(flow_table, flow)) flow_offload_teardown(flow); if (test_bit(NF_FLOW_TEARDOWN, &flow->flags)) { diff --git a/net/netfilter/nf_flow_table_inet.c b/net/netfilter/nf_flow_table_inet.c index 0ccabf3fa6aa3..9505f9d188ff2 100644 --- a/net/netfilter/nf_flow_table_inet.c +++ b/net/netfilter/nf_flow_table_inet.c @@ -39,7 +39,7 @@ nf_flow_offload_inet_hook(void *priv, struct sk_buff *skb, } static int nf_flow_rule_route_inet(struct net *net, - const struct flow_offload *flow, + struct flow_offload *flow, enum flow_offload_tuple_dir dir, struct nf_flow_rule *flow_rule) { diff --git a/net/netfilter/nf_flow_table_ip.c b/net/netfilter/nf_flow_table_ip.c index b350fe9d00b0b..6feaac9ab05c8 100644 --- a/net/netfilter/nf_flow_table_ip.c +++ b/net/netfilter/nf_flow_table_ip.c @@ -384,7 +384,7 @@ nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb, if (skb_try_make_writable(skb, thoff + hdrsize)) return NF_DROP; - flow_offload_refresh(flow_table, flow); + flow_offload_refresh(flow_table, flow, false); nf_flow_encap_pop(skb, tuplehash); thoff -= offset; @@ -646,7 +646,7 @@ nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb, if (skb_try_make_writable(skb, thoff + hdrsize)) return NF_DROP; - flow_offload_refresh(flow_table, flow); + flow_offload_refresh(flow_table, flow, false); nf_flow_encap_pop(skb, tuplehash); diff --git a/net/netfilter/nf_flow_table_offload.c b/net/netfilter/nf_flow_table_offload.c index 4d9b99abe37d6..1c26f03fc6617 100644 --- a/net/netfilter/nf_flow_table_offload.c +++ b/net/netfilter/nf_flow_table_offload.c @@ -679,7 +679,7 @@ nf_flow_rule_route_common(struct net *net, const struct flow_offload *flow, return 0; } -int nf_flow_rule_route_ipv4(struct net *net, const struct flow_offload *flow, +int nf_flow_rule_route_ipv4(struct net *net, struct flow_offload *flow, enum flow_offload_tuple_dir dir, struct nf_flow_rule *flow_rule) { @@ -704,7 +704,7 @@ int nf_flow_rule_route_ipv4(struct net *net, const struct flow_offload *flow, } EXPORT_SYMBOL_GPL(nf_flow_rule_route_ipv4); -int nf_flow_rule_route_ipv6(struct net *net, const struct flow_offload *flow, +int nf_flow_rule_route_ipv6(struct net *net, struct flow_offload *flow, enum flow_offload_tuple_dir dir, struct nf_flow_rule *flow_rule) { @@ -735,7 +735,7 @@ nf_flow_offload_rule_alloc(struct net *net, { const struct nf_flowtable *flowtable = offload->flowtable; const struct flow_offload_tuple *tuple, *other_tuple; - const struct flow_offload *flow = offload->flow; + struct flow_offload *flow = offload->flow; struct dst_entry *other_dst = NULL; struct nf_flow_rule *flow_rule; int err = -ENOMEM; @@ -895,8 +895,9 @@ static int flow_offload_rule_add(struct flow_offload_work *offload, ok_count += flow_offload_tuple_add(offload, flow_rule[0], FLOW_OFFLOAD_DIR_ORIGINAL); - ok_count += flow_offload_tuple_add(offload, flow_rule[1], - FLOW_OFFLOAD_DIR_REPLY); + if (test_bit(NF_FLOW_HW_BIDIRECTIONAL, &offload->flow->flags)) + ok_count += flow_offload_tuple_add(offload, flow_rule[1], + FLOW_OFFLOAD_DIR_REPLY); if (ok_count == 0) return -ENOENT; @@ -926,7 +927,8 @@ static void flow_offload_work_del(struct flow_offload_work *offload) { clear_bit(IPS_HW_OFFLOAD_BIT, &offload->flow->ct->status); flow_offload_tuple_del(offload, FLOW_OFFLOAD_DIR_ORIGINAL); - flow_offload_tuple_del(offload, FLOW_OFFLOAD_DIR_REPLY); + if (test_bit(NF_FLOW_HW_BIDIRECTIONAL, &offload->flow->flags)) + flow_offload_tuple_del(offload, FLOW_OFFLOAD_DIR_REPLY); set_bit(NF_FLOW_HW_DEAD, &offload->flow->flags); } @@ -946,7 +948,9 @@ static void flow_offload_work_stats(struct flow_offload_work *offload) u64 lastused; flow_offload_tuple_stats(offload, FLOW_OFFLOAD_DIR_ORIGINAL, &stats[0]); - flow_offload_tuple_stats(offload, FLOW_OFFLOAD_DIR_REPLY, &stats[1]); + if (test_bit(NF_FLOW_HW_BIDIRECTIONAL, &offload->flow->flags)) + flow_offload_tuple_stats(offload, FLOW_OFFLOAD_DIR_REPLY, + &stats[1]); lastused = max_t(u64, stats[0].lastused, stats[1].lastused); offload->flow->timeout = max_t(u64, offload->flow->timeout, diff --git a/net/netfilter/nf_log_syslog.c b/net/netfilter/nf_log_syslog.c index cb894f0d63e9d..c66689ad2b491 100644 --- a/net/netfilter/nf_log_syslog.c +++ b/net/netfilter/nf_log_syslog.c @@ -322,7 +322,7 @@ dump_ipv4_packet(struct net *net, struct nf_log_buf *m, /* Max length: 46 "LEN=65535 TOS=0xFF PREC=0xFF TTL=255 ID=65535 " */ nf_log_buf_add(m, "LEN=%u TOS=0x%02X PREC=0x%02X TTL=%u ID=%u ", - ntohs(ih->tot_len), ih->tos & IPTOS_TOS_MASK, + iph_totlen(skb, ih), ih->tos & IPTOS_TOS_MASK, ih->tos & IPTOS_PREC_MASK, ih->ttl, ntohs(ih->id)); /* Max length: 6 "CE DF MF " */ diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c index cee3e4e905ec8..e0c117229ee9d 100644 --- a/net/netfilter/nf_tables_core.c +++ b/net/netfilter/nf_tables_core.c @@ -141,7 +141,7 @@ static bool nft_payload_fast_eval(const struct nft_expr *expr, else { if (!(pkt->flags & NFT_PKTINFO_L4PROTO)) return false; - ptr = skb_network_header(skb) + nft_thoff(pkt); + ptr = skb->data + nft_thoff(pkt); } ptr += priv->offset; diff --git a/net/netfilter/nft_immediate.c b/net/netfilter/nft_immediate.c index 5f59dbab3e933..55fcf0280c5c3 100644 --- a/net/netfilter/nft_immediate.c +++ b/net/netfilter/nft_immediate.c @@ -78,7 +78,7 @@ static int nft_immediate_init(const struct nft_ctx *ctx, case NFT_GOTO: err = nf_tables_bind_chain(ctx, chain); if (err < 0) - return err; + goto err1; break; default: break; diff --git a/net/netfilter/xt_length.c b/net/netfilter/xt_length.c index 9fbfad13176f0..ca730cedb5d41 100644 --- a/net/netfilter/xt_length.c +++ b/net/netfilter/xt_length.c @@ -21,7 +21,7 @@ static bool length_mt(const struct sk_buff *skb, struct xt_action_param *par) { const struct xt_length_info *info = par->matchinfo; - u_int16_t pktlen = ntohs(ip_hdr(skb)->tot_len); + u32 pktlen = skb_ip_totlen(skb); return (pktlen >= info->min && pktlen <= info->max) ^ info->invert; } diff --git a/net/nfc/llcp_core.c b/net/nfc/llcp_core.c index 1dac28136e6a3..18be13fb9b75a 100644 --- a/net/nfc/llcp_core.c +++ b/net/nfc/llcp_core.c @@ -145,6 +145,13 @@ static void nfc_llcp_socket_release(struct nfc_llcp_local *local, bool device, static struct nfc_llcp_local *nfc_llcp_local_get(struct nfc_llcp_local *local) { + /* Since using nfc_llcp_local may result in usage of nfc_dev, whenever + * we hold a reference to local, we also need to hold a reference to + * the device to avoid UAF. + */ + if (!nfc_get_device(local->dev->idx)) + return NULL; + kref_get(&local->ref); return local; @@ -177,10 +184,18 @@ static void local_release(struct kref *ref) int nfc_llcp_local_put(struct nfc_llcp_local *local) { + struct nfc_dev *dev; + int ret; + if (local == NULL) return 0; - return kref_put(&local->ref, local_release); + dev = local->dev; + + ret = kref_put(&local->ref, local_release); + nfc_put_device(dev); + + return ret; } static struct nfc_llcp_sock *nfc_llcp_sock_get(struct nfc_llcp_local *local, @@ -959,8 +974,17 @@ static void nfc_llcp_recv_connect(struct nfc_llcp_local *local, } new_sock = nfc_llcp_sock(new_sk); - new_sock->dev = local->dev; + new_sock->local = nfc_llcp_local_get(local); + if (!new_sock->local) { + reason = LLCP_DM_REJ; + sock_put(&new_sock->sk); + release_sock(&sock->sk); + sock_put(&sock->sk); + goto fail; + } + + new_sock->dev = local->dev; new_sock->rw = sock->rw; new_sock->miux = sock->miux; new_sock->nfc_protocol = sock->nfc_protocol; @@ -1597,7 +1621,16 @@ int nfc_llcp_register_device(struct nfc_dev *ndev) if (local == NULL) return -ENOMEM; - local->dev = ndev; + /* As we are going to initialize local's refcount, we need to get the + * nfc_dev to avoid UAF, otherwise there is no point in continuing. + * See nfc_llcp_local_get(). + */ + local->dev = nfc_get_device(ndev->idx); + if (!local->dev) { + kfree(local); + return -ENODEV; + } + INIT_LIST_HEAD(&local->list); kref_init(&local->ref); mutex_init(&local->sdp_lock); diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index c8eaf4234b2e0..0591cfb289d50 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -1252,7 +1252,7 @@ static int ovs_ct_commit(struct net *net, struct sw_flow_key *key, if (err) return err; - nf_conn_act_ct_ext_add(ct); + nf_conn_act_ct_ext_add(skb, ct, ctinfo); } else if (IS_ENABLED(CONFIG_NF_CONNTRACK_LABELS) && labels_nonzero(&info->labels.mask)) { err = ovs_ct_set_labels(ct, key, &info->labels.value, diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index 4c7f7861ea967..d6d33f854050a 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -168,11 +168,11 @@ tcf_ct_flow_table_add_action_nat_udp(const struct nf_conntrack_tuple *tuple, static void tcf_ct_flow_table_add_action_meta(struct nf_conn *ct, enum ip_conntrack_dir dir, + enum ip_conntrack_info ctinfo, struct flow_action *action) { struct nf_conn_labels *ct_labels; struct flow_action_entry *entry; - enum ip_conntrack_info ctinfo; u32 *act_ct_labels; entry = tcf_ct_flow_table_flow_action_get_next(action); @@ -180,8 +180,6 @@ static void tcf_ct_flow_table_add_action_meta(struct nf_conn *ct, #if IS_ENABLED(CONFIG_NF_CONNTRACK_MARK) entry->ct_metadata.mark = READ_ONCE(ct->mark); #endif - ctinfo = dir == IP_CT_DIR_ORIGINAL ? IP_CT_ESTABLISHED : - IP_CT_ESTABLISHED_REPLY; /* aligns with the CT reference on the SKB nf_ct_set */ entry->ct_metadata.cookie = (unsigned long)ct | ctinfo; entry->ct_metadata.orig_dir = dir == IP_CT_DIR_ORIGINAL; @@ -235,22 +233,26 @@ static int tcf_ct_flow_table_add_action_nat(struct net *net, } static int tcf_ct_flow_table_fill_actions(struct net *net, - const struct flow_offload *flow, + struct flow_offload *flow, enum flow_offload_tuple_dir tdir, struct nf_flow_rule *flow_rule) { struct flow_action *action = &flow_rule->rule->action; int num_entries = action->num_entries; struct nf_conn *ct = flow->ct; + enum ip_conntrack_info ctinfo; enum ip_conntrack_dir dir; int i, err; switch (tdir) { case FLOW_OFFLOAD_DIR_ORIGINAL: dir = IP_CT_DIR_ORIGINAL; + ctinfo = IP_CT_ESTABLISHED; + set_bit(NF_FLOW_HW_ESTABLISHED, &flow->flags); break; case FLOW_OFFLOAD_DIR_REPLY: dir = IP_CT_DIR_REPLY; + ctinfo = IP_CT_ESTABLISHED_REPLY; break; default: return -EOPNOTSUPP; @@ -260,7 +262,7 @@ static int tcf_ct_flow_table_fill_actions(struct net *net, if (err) goto err_nat; - tcf_ct_flow_table_add_action_meta(ct, dir, action); + tcf_ct_flow_table_add_action_meta(ct, dir, ctinfo, action); return 0; err_nat: @@ -272,8 +274,39 @@ err_nat: return err; } +static bool tcf_ct_flow_is_outdated(const struct flow_offload *flow) +{ + return test_bit(IPS_SEEN_REPLY_BIT, &flow->ct->status) && + test_bit(IPS_HW_OFFLOAD_BIT, &flow->ct->status) && + !test_bit(NF_FLOW_HW_PENDING, &flow->flags) && + !test_bit(NF_FLOW_HW_ESTABLISHED, &flow->flags); +} + +static void tcf_ct_flow_table_get_ref(struct tcf_ct_flow_table *ct_ft); + +static void tcf_ct_nf_get(struct nf_flowtable *ft) +{ + struct tcf_ct_flow_table *ct_ft = + container_of(ft, struct tcf_ct_flow_table, nf_ft); + + tcf_ct_flow_table_get_ref(ct_ft); +} + +static void tcf_ct_flow_table_put(struct tcf_ct_flow_table *ct_ft); + +static void tcf_ct_nf_put(struct nf_flowtable *ft) +{ + struct tcf_ct_flow_table *ct_ft = + container_of(ft, struct tcf_ct_flow_table, nf_ft); + + tcf_ct_flow_table_put(ct_ft); +} + static struct nf_flowtable_type flowtable_ct = { + .gc = tcf_ct_flow_is_outdated, .action = tcf_ct_flow_table_fill_actions, + .get = tcf_ct_nf_get, + .put = tcf_ct_nf_put, .owner = THIS_MODULE, }; @@ -322,9 +355,13 @@ err_alloc: return err; } +static void tcf_ct_flow_table_get_ref(struct tcf_ct_flow_table *ct_ft) +{ + refcount_inc(&ct_ft->ref); +} + static void tcf_ct_flow_table_cleanup_work(struct work_struct *work) { - struct flow_block_cb *block_cb, *tmp_cb; struct tcf_ct_flow_table *ct_ft; struct flow_block *block; @@ -332,24 +369,18 @@ static void tcf_ct_flow_table_cleanup_work(struct work_struct *work) rwork); nf_flow_table_free(&ct_ft->nf_ft); - /* Remove any remaining callbacks before cleanup */ block = &ct_ft->nf_ft.flow_block; down_write(&ct_ft->nf_ft.flow_block_lock); - list_for_each_entry_safe(block_cb, tmp_cb, &block->cb_list, list) { - list_del(&block_cb->list); - flow_block_cb_free(block_cb); - } + WARN_ON(!list_empty(&block->cb_list)); up_write(&ct_ft->nf_ft.flow_block_lock); kfree(ct_ft); module_put(THIS_MODULE); } -static void tcf_ct_flow_table_put(struct tcf_ct_params *params) +static void tcf_ct_flow_table_put(struct tcf_ct_flow_table *ct_ft) { - struct tcf_ct_flow_table *ct_ft = params->ct_ft; - - if (refcount_dec_and_test(¶ms->ct_ft->ref)) { + if (refcount_dec_and_test(&ct_ft->ref)) { rhashtable_remove_fast(&zones_ht, &ct_ft->node, zones_params); INIT_RCU_WORK(&ct_ft->rwork, tcf_ct_flow_table_cleanup_work); queue_rcu_work(act_ct_wq, &ct_ft->rwork); @@ -363,9 +394,20 @@ static void tcf_ct_flow_tc_ifidx(struct flow_offload *entry, entry->tuplehash[dir].tuple.tc.iifidx = act_ct_ext->ifindex[dir]; } +static void tcf_ct_flow_ct_ext_ifidx_update(struct flow_offload *entry) +{ + struct nf_conn_act_ct_ext *act_ct_ext; + + act_ct_ext = nf_conn_act_ct_ext_find(entry->ct); + if (act_ct_ext) { + tcf_ct_flow_tc_ifidx(entry, act_ct_ext, FLOW_OFFLOAD_DIR_ORIGINAL); + tcf_ct_flow_tc_ifidx(entry, act_ct_ext, FLOW_OFFLOAD_DIR_REPLY); + } +} + static void tcf_ct_flow_table_add(struct tcf_ct_flow_table *ct_ft, struct nf_conn *ct, - bool tcp) + bool tcp, bool bidirectional) { struct nf_conn_act_ct_ext *act_ct_ext; struct flow_offload *entry; @@ -384,6 +426,8 @@ static void tcf_ct_flow_table_add(struct tcf_ct_flow_table *ct_ft, ct->proto.tcp.seen[0].flags |= IP_CT_TCP_FLAG_BE_LIBERAL; ct->proto.tcp.seen[1].flags |= IP_CT_TCP_FLAG_BE_LIBERAL; } + if (bidirectional) + __set_bit(NF_FLOW_HW_BIDIRECTIONAL, &entry->flags); act_ct_ext = nf_conn_act_ct_ext_find(ct); if (act_ct_ext) { @@ -407,26 +451,34 @@ static void tcf_ct_flow_table_process_conn(struct tcf_ct_flow_table *ct_ft, struct nf_conn *ct, enum ip_conntrack_info ctinfo) { - bool tcp = false; - - if ((ctinfo != IP_CT_ESTABLISHED && ctinfo != IP_CT_ESTABLISHED_REPLY) || - !test_bit(IPS_ASSURED_BIT, &ct->status)) - return; + bool tcp = false, bidirectional = true; switch (nf_ct_protonum(ct)) { case IPPROTO_TCP: - tcp = true; - if (ct->proto.tcp.state != TCP_CONNTRACK_ESTABLISHED) + if ((ctinfo != IP_CT_ESTABLISHED && + ctinfo != IP_CT_ESTABLISHED_REPLY) || + !test_bit(IPS_ASSURED_BIT, &ct->status) || + ct->proto.tcp.state != TCP_CONNTRACK_ESTABLISHED) return; + + tcp = true; break; case IPPROTO_UDP: + if (!nf_ct_is_confirmed(ct)) + return; + if (!test_bit(IPS_ASSURED_BIT, &ct->status)) + bidirectional = false; break; #ifdef CONFIG_NF_CT_PROTO_GRE case IPPROTO_GRE: { struct nf_conntrack_tuple *tuple; - if (ct->status & IPS_NAT_MASK) + if ((ctinfo != IP_CT_ESTABLISHED && + ctinfo != IP_CT_ESTABLISHED_REPLY) || + !test_bit(IPS_ASSURED_BIT, &ct->status) || + ct->status & IPS_NAT_MASK) return; + tuple = &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple; /* No support for GRE v1 */ if (tuple->src.u.gre.key || tuple->dst.u.gre.key) @@ -442,7 +494,7 @@ static void tcf_ct_flow_table_process_conn(struct tcf_ct_flow_table *ct_ft, ct->status & IPS_SEQ_ADJUST) return; - tcf_ct_flow_table_add(ct_ft, ct, tcp); + tcf_ct_flow_table_add(ct_ft, ct, tcp, bidirectional); } static bool @@ -596,6 +648,7 @@ static bool tcf_ct_flow_table_lookup(struct tcf_ct_params *p, struct flow_offload_tuple tuple = {}; enum ip_conntrack_info ctinfo; struct tcphdr *tcph = NULL; + bool force_refresh = false; struct flow_offload *flow; struct nf_conn *ct; u8 dir; @@ -621,15 +674,40 @@ static bool tcf_ct_flow_table_lookup(struct tcf_ct_params *p, flow = container_of(tuplehash, struct flow_offload, tuplehash[dir]); ct = flow->ct; + if (dir == FLOW_OFFLOAD_DIR_REPLY && + !test_bit(NF_FLOW_HW_BIDIRECTIONAL, &flow->flags)) { + /* Only offload reply direction after connection became + * assured. + */ + if (test_bit(IPS_ASSURED_BIT, &ct->status)) + set_bit(NF_FLOW_HW_BIDIRECTIONAL, &flow->flags); + else if (test_bit(NF_FLOW_HW_ESTABLISHED, &flow->flags)) + /* If flow_table flow has already been updated to the + * established state, then don't refresh. + */ + return false; + force_refresh = true; + } + if (tcph && (unlikely(tcph->fin || tcph->rst))) { flow_offload_teardown(flow); return false; } - ctinfo = dir == FLOW_OFFLOAD_DIR_ORIGINAL ? IP_CT_ESTABLISHED : - IP_CT_ESTABLISHED_REPLY; + if (dir == FLOW_OFFLOAD_DIR_ORIGINAL) + ctinfo = test_bit(IPS_SEEN_REPLY_BIT, &ct->status) ? + IP_CT_ESTABLISHED : IP_CT_NEW; + else + ctinfo = IP_CT_ESTABLISHED_REPLY; + + nf_conn_act_ct_ext_fill(skb, ct, ctinfo); + tcf_ct_flow_ct_ext_ifidx_update(flow); + flow_offload_refresh(nf_ft, flow, force_refresh); + if (!test_bit(IPS_ASSURED_BIT, &ct->status)) { + /* Process this flow in SW to allow promoting to ASSURED */ + return false; + } - flow_offload_refresh(nf_ft, flow); nf_conntrack_get(&ct->ct_general); nf_ct_set(skb, ct, ctinfo); if (nf_ft->flags & NF_FLOWTABLE_COUNTER) @@ -832,18 +910,23 @@ out_free: return err; } -static void tcf_ct_params_free(struct rcu_head *head) +static void tcf_ct_params_free(struct tcf_ct_params *params) { - struct tcf_ct_params *params = container_of(head, - struct tcf_ct_params, rcu); - - tcf_ct_flow_table_put(params); - + if (params->ct_ft) + tcf_ct_flow_table_put(params->ct_ft); if (params->tmpl) nf_ct_put(params->tmpl); kfree(params); } +static void tcf_ct_params_free_rcu(struct rcu_head *head) +{ + struct tcf_ct_params *params; + + params = container_of(head, struct tcf_ct_params, rcu); + tcf_ct_params_free(params); +} + #if IS_ENABLED(CONFIG_NF_NAT) /* Modelled after nf_nat_ipv[46]_fn(). * range is only used for new, uninitialized NAT state. @@ -1121,7 +1204,7 @@ do_nat: tcf_ct_act_set_labels(ct, p->labels, p->labels_mask); if (!nf_ct_is_confirmed(ct)) - nf_conn_act_ct_ext_add(ct); + nf_conn_act_ct_ext_add(skb, ct, ctinfo); /* This will take care of sending queued events * even if the connection is already confirmed. @@ -1390,7 +1473,7 @@ static int tcf_ct_init(struct net *net, struct nlattr *nla, err = tcf_ct_flow_table_get(net, params); if (err) - goto cleanup_params; + goto cleanup; spin_lock_bh(&c->tcf_lock); goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch); @@ -1401,17 +1484,15 @@ static int tcf_ct_init(struct net *net, struct nlattr *nla, if (goto_ch) tcf_chain_put_by_act(goto_ch); if (params) - call_rcu(¶ms->rcu, tcf_ct_params_free); + call_rcu(¶ms->rcu, tcf_ct_params_free_rcu); return res; -cleanup_params: - if (params->tmpl) - nf_ct_put(params->tmpl); cleanup: if (goto_ch) tcf_chain_put_by_act(goto_ch); - kfree(params); + if (params) + tcf_ct_params_free(params); tcf_idr_release(*a, bind); return err; } @@ -1423,7 +1504,7 @@ static void tcf_ct_cleanup(struct tc_action *a) params = rcu_dereference_protected(c->params, 1); if (params) - call_rcu(¶ms->rcu, tcf_ct_params_free); + call_rcu(¶ms->rcu, tcf_ct_params_free_rcu); } static int tcf_ct_dump_key_val(struct sk_buff *skb, diff --git a/net/sched/em_text.c b/net/sched/em_text.c index 6f3c1fb2fb44c..f176afb70559e 100644 --- a/net/sched/em_text.c +++ b/net/sched/em_text.c @@ -97,8 +97,10 @@ retry: static void em_text_destroy(struct tcf_ematch *m) { - if (EM_TEXT_PRIV(m) && EM_TEXT_PRIV(m)->config) + if (EM_TEXT_PRIV(m) && EM_TEXT_PRIV(m)->config) { textsearch_destroy(EM_TEXT_PRIV(m)->config); + kfree(EM_TEXT_PRIV(m)); + } } static int em_text_dump(struct sk_buff *skb, struct tcf_ematch *m) diff --git a/net/smc/smc_diag.c b/net/smc/smc_diag.c index 80ea7d954eceb..801044e7d1949 100644 --- a/net/smc/smc_diag.c +++ b/net/smc/smc_diag.c @@ -153,8 +153,7 @@ static int __smc_diag_dump(struct sock *sk, struct sk_buff *skb, .lnk[0].link_id = link->link_id, }; - memcpy(linfo.lnk[0].ibname, - smc->conn.lgr->lnk[0].smcibdev->ibdev->name, + memcpy(linfo.lnk[0].ibname, link->smcibdev->ibdev->name, sizeof(link->smcibdev->ibdev->name)); smc_gid_be16_convert(linfo.lnk[0].gid, link->gid); smc_gid_be16_convert(linfo.lnk[0].peer_gid, link->peer_gid); diff --git a/net/socket.c b/net/socket.c index 04cba91c7cbe5..639d76f20384e 100644 --- a/net/socket.c +++ b/net/socket.c @@ -130,6 +130,7 @@ static ssize_t sock_sendpage(struct file *file, struct page *page, static ssize_t sock_splice_read(struct file *file, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags); +static void sock_splice_eof(struct file *file); #ifdef CONFIG_PROC_FS static void sock_show_fdinfo(struct seq_file *m, struct file *f) @@ -164,6 +165,7 @@ static const struct file_operations socket_file_ops = { .sendpage = sock_sendpage, .splice_write = generic_splice_sendpage, .splice_read = sock_splice_read, + .splice_eof = sock_splice_eof, .show_fdinfo = sock_show_fdinfo, }; @@ -740,6 +742,7 @@ int sock_sendmsg(struct socket *sock, struct msghdr *msg) { struct sockaddr_storage *save_addr = (struct sockaddr_storage *)msg->msg_name; struct sockaddr_storage address; + int save_len = msg->msg_namelen; int ret; if (msg->msg_name) { @@ -749,6 +752,7 @@ int sock_sendmsg(struct socket *sock, struct msghdr *msg) ret = __sock_sendmsg(sock, msg); msg->msg_name = save_addr; + msg->msg_namelen = save_len; return ret; } @@ -826,7 +830,7 @@ static bool skb_is_swtx_tstamp(const struct sk_buff *skb, int false_tstamp) static ktime_t get_timestamp(struct sock *sk, struct sk_buff *skb, int *if_index) { - bool cycles = sk->sk_tsflags & SOF_TIMESTAMPING_BIND_PHC; + bool cycles = READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_BIND_PHC; struct skb_shared_hwtstamps *shhwtstamps = skb_hwtstamps(skb); struct net_device *orig_dev; ktime_t hwtstamp; @@ -878,12 +882,12 @@ void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk, int need_software_tstamp = sock_flag(sk, SOCK_RCVTSTAMP); int new_tstamp = sock_flag(sk, SOCK_TSTAMP_NEW); struct scm_timestamping_internal tss; - int empty = 1, false_tstamp = 0; struct skb_shared_hwtstamps *shhwtstamps = skb_hwtstamps(skb); int if_index; ktime_t hwtstamp; + u32 tsflags; /* Race occurred between timestamp enabling and packet receiving. Fill in the current time for now. */ @@ -925,11 +929,12 @@ void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk, } memset(&tss, 0, sizeof(tss)); - if ((sk->sk_tsflags & SOF_TIMESTAMPING_SOFTWARE) && + tsflags = READ_ONCE(sk->sk_tsflags); + if ((tsflags & SOF_TIMESTAMPING_SOFTWARE) && ktime_to_timespec64_cond(skb->tstamp, tss.ts + 0)) empty = 0; if (shhwtstamps && - (sk->sk_tsflags & SOF_TIMESTAMPING_RAW_HARDWARE) && + (tsflags & SOF_TIMESTAMPING_RAW_HARDWARE) && !skb_is_swtx_tstamp(skb, false_tstamp)) { if_index = 0; if (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP_NETDEV) @@ -937,14 +942,14 @@ void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk, else hwtstamp = shhwtstamps->hwtstamp; - if (sk->sk_tsflags & SOF_TIMESTAMPING_BIND_PHC) + if (tsflags & SOF_TIMESTAMPING_BIND_PHC) hwtstamp = ptp_convert_timestamp(&hwtstamp, - sk->sk_bind_phc); + READ_ONCE(sk->sk_bind_phc)); if (ktime_to_timespec64_cond(hwtstamp, tss.ts + 2)) { empty = 0; - if ((sk->sk_tsflags & SOF_TIMESTAMPING_OPT_PKTINFO) && + if ((tsflags & SOF_TIMESTAMPING_OPT_PKTINFO) && !skb_is_err_queue(skb)) put_ts_pktinfo(msg, skb, if_index); } @@ -1088,6 +1093,14 @@ static ssize_t sock_splice_read(struct file *file, loff_t *ppos, return sock->ops->splice_read(sock, ppos, pipe, len, flags); } +static void sock_splice_eof(struct file *file) +{ + struct socket *sock = file->private_data; + + if (sock->ops->splice_eof) + sock->ops->splice_eof(sock); +} + static ssize_t sock_read_iter(struct kiocb *iocb, struct iov_iter *to) { struct file *file = iocb->ki_filp; @@ -2128,6 +2141,7 @@ int __sys_sendto(int fd, void __user *buff, size_t len, unsigned int flags, msg.msg_name = (struct sockaddr *)&address; msg.msg_namelen = addr_len; } + flags &= ~MSG_INTERNAL_SENDMSG_FLAGS; if (sock->file->f_flags & O_NONBLOCK) flags |= MSG_DONTWAIT; msg.msg_flags = flags; @@ -2479,6 +2493,7 @@ static int ____sys_sendmsg(struct socket *sock, struct msghdr *msg_sys, msg_sys->msg_control = ctl_buf; msg_sys->msg_control_is_user = false; } + flags &= ~MSG_INTERNAL_SENDMSG_FLAGS; msg_sys->msg_flags = flags; if (sock->file->f_flags & O_NONBLOCK) diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 6dbeb80073338..be2ed7b0fe21c 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -211,8 +211,6 @@ static inline bool unix_secdata_eq(struct scm_cookie *scm, struct sk_buff *skb) } #endif /* CONFIG_SECURITY_NETWORK */ -#define unix_peer(sk) (unix_sk(sk)->peer) - static inline int unix_our_peer(struct sock *sk, struct sock *osk) { return unix_peer(osk) == sk; diff --git a/net/unix/unix_bpf.c b/net/unix/unix_bpf.c index 2f9d8271c6ec7..7ea7c3a0d0d06 100644 --- a/net/unix/unix_bpf.c +++ b/net/unix/unix_bpf.c @@ -159,12 +159,17 @@ int unix_dgram_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool re int unix_stream_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore) { + struct sock *sk_pair; + if (restore) { sk->sk_write_space = psock->saved_write_space; sock_replace_proto(sk, psock->sk_proto); return 0; } + sk_pair = unix_peer(sk); + sock_hold(sk_pair); + psock->sk_pair = sk_pair; unix_stream_bpf_check_needs_rebuild(psock->sk_proto); sock_replace_proto(sk, &unix_stream_bpf_prot); return 0; diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index a88ed60dcd96a..1c8ffc5cf97f6 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -9581,6 +9581,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x84da, "HP OMEN dc0019-ur", ALC295_FIXUP_HP_OMEN), SND_PCI_QUIRK(0x103c, 0x84e7, "HP Pavilion 15", ALC269_FIXUP_HP_MUTE_LED_MIC3), SND_PCI_QUIRK(0x103c, 0x8519, "HP Spectre x360 15-df0xxx", ALC285_FIXUP_HP_SPECTRE_X360), + SND_PCI_QUIRK(0x103c, 0x8537, "HP ProBook 440 G6", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), SND_PCI_QUIRK(0x103c, 0x860f, "HP ZBook 15 G6", ALC285_FIXUP_HP_GPIO_AMP_INIT), SND_PCI_QUIRK(0x103c, 0x861f, "HP Elite Dragonfly G1", ALC285_FIXUP_HP_GPIO_AMP_INIT), SND_PCI_QUIRK(0x103c, 0x869d, "HP", ALC236_FIXUP_HP_MUTE_LED), @@ -9663,6 +9664,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x89c6, "Zbook Fury 17 G9", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x89ca, "HP", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), SND_PCI_QUIRK(0x103c, 0x89d3, "HP EliteBook 645 G9 (MB 89D2)", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), + SND_PCI_QUIRK(0x103c, 0x8a0f, "HP Pavilion 14-ec1xxx", ALC287_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8a20, "HP Laptop 15s-fq5xxx", ALC236_FIXUP_HP_MUTE_LED_COEFBIT2), SND_PCI_QUIRK(0x103c, 0x8a25, "HP Victus 16-d1xxx (MB 8A25)", ALC245_FIXUP_HP_MUTE_LED_COEFBIT), SND_PCI_QUIRK(0x103c, 0x8a78, "HP Dev One", ALC285_FIXUP_HP_LIMIT_INT_MIC_BOOST), @@ -9707,6 +9709,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8c70, "HP EliteBook 835 G11", ALC287_FIXUP_CS35L41_I2C_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8c71, "HP EliteBook 845 G11", ALC287_FIXUP_CS35L41_I2C_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8c72, "HP EliteBook 865 G11", ALC287_FIXUP_CS35L41_I2C_2_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8c96, "HP", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), SND_PCI_QUIRK(0x103c, 0x8ca4, "HP ZBook Fury", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8ca7, "HP ZBook Fury", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8cf5, "HP ZBook Studio 16", ALC245_FIXUP_CS35L41_SPI_4_HP_GPIO_LED), @@ -9904,6 +9907,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1558, 0xc019, "Clevo NH77D[BE]Q", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0xc022, "Clevo NH77[DC][QW]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x17aa, 0x1036, "Lenovo P520", ALC233_FIXUP_LENOVO_MULTI_CODECS), + SND_PCI_QUIRK(0x17aa, 0x3882, "Lenovo Yoga Pro 7 14APH8", ALC287_FIXUP_YOGA9_14IAP7_BASS_SPK_PIN), SND_PCI_QUIRK(0x17aa, 0x1048, "ThinkCentre Station", ALC623_FIXUP_LENOVO_THINKSTATION_P340), SND_PCI_QUIRK(0x17aa, 0x20f2, "Thinkpad SL410/510", ALC269_FIXUP_SKU_IGNORE), SND_PCI_QUIRK(0x17aa, 0x215e, "Thinkpad L512", ALC269_FIXUP_SKU_IGNORE), diff --git a/sound/soc/fsl/fsl_rpmsg.c b/sound/soc/fsl/fsl_rpmsg.c index bf94838bdbefe..5c07a8ff0c9c0 100644 --- a/sound/soc/fsl/fsl_rpmsg.c +++ b/sound/soc/fsl/fsl_rpmsg.c @@ -231,7 +231,7 @@ static int fsl_rpmsg_probe(struct platform_device *pdev) ret = devm_snd_soc_register_component(&pdev->dev, &fsl_component, &fsl_rpmsg_dai, 1); if (ret) - return ret; + goto err_pm_disable; rpmsg->card_pdev = platform_device_register_data(&pdev->dev, "imx-audio-rpmsg", @@ -241,16 +241,22 @@ static int fsl_rpmsg_probe(struct platform_device *pdev) if (IS_ERR(rpmsg->card_pdev)) { dev_err(&pdev->dev, "failed to register rpmsg card\n"); ret = PTR_ERR(rpmsg->card_pdev); - return ret; + goto err_pm_disable; } return 0; + +err_pm_disable: + pm_runtime_disable(&pdev->dev); + return ret; } static int fsl_rpmsg_remove(struct platform_device *pdev) { struct fsl_rpmsg *rpmsg = platform_get_drvdata(pdev); + pm_runtime_disable(&pdev->dev); + if (rpmsg->card_pdev) platform_device_unregister(rpmsg->card_pdev); diff --git a/sound/soc/mediatek/mt8186/mt8186-dai-adda.c b/sound/soc/mediatek/mt8186/mt8186-dai-adda.c index 094402470dc23..858b95b199dcb 100644 --- a/sound/soc/mediatek/mt8186/mt8186-dai-adda.c +++ b/sound/soc/mediatek/mt8186/mt8186-dai-adda.c @@ -499,7 +499,7 @@ static const struct snd_soc_dapm_widget mtk_dai_adda_widgets[] = { SND_SOC_DAPM_PRE_PMU | SND_SOC_DAPM_POST_PMD), SND_SOC_DAPM_SUPPLY_S("AUD_PAD_TOP", SUPPLY_SEQ_ADDA_AUD_PAD_TOP, - 0, 0, 0, + AFE_AUD_PAD_TOP, RG_RX_FIFO_ON_SFT, 0, mtk_adda_pad_top_event, SND_SOC_DAPM_PRE_PMU), SND_SOC_DAPM_SUPPLY_S("ADDA_MTKAIF_CFG", SUPPLY_SEQ_ADDA_MTKAIF_CFG, diff --git a/sound/soc/meson/g12a-toacodec.c b/sound/soc/meson/g12a-toacodec.c index ddc667956cf5e..8d8d848ebd58b 100644 --- a/sound/soc/meson/g12a-toacodec.c +++ b/sound/soc/meson/g12a-toacodec.c @@ -71,6 +71,9 @@ static int g12a_toacodec_mux_put_enum(struct snd_kcontrol *kcontrol, struct soc_enum *e = (struct soc_enum *)kcontrol->private_value; unsigned int mux, reg; + if (ucontrol->value.enumerated.item[0] >= e->items) + return -EINVAL; + mux = snd_soc_enum_item_to_val(e, ucontrol->value.enumerated.item[0]); regmap_field_read(priv->field_dat_sel, ®); @@ -101,7 +104,7 @@ static int g12a_toacodec_mux_put_enum(struct snd_kcontrol *kcontrol, snd_soc_dapm_mux_update_power(dapm, kcontrol, mux, e, NULL); - return 0; + return 1; } static SOC_ENUM_SINGLE_DECL(g12a_toacodec_mux_enum, TOACODEC_CTRL0, diff --git a/sound/soc/meson/g12a-tohdmitx.c b/sound/soc/meson/g12a-tohdmitx.c index 579a04ad4d197..154c324fdd42a 100644 --- a/sound/soc/meson/g12a-tohdmitx.c +++ b/sound/soc/meson/g12a-tohdmitx.c @@ -45,6 +45,9 @@ static int g12a_tohdmitx_i2s_mux_put_enum(struct snd_kcontrol *kcontrol, struct soc_enum *e = (struct soc_enum *)kcontrol->private_value; unsigned int mux, changed; + if (ucontrol->value.enumerated.item[0] >= e->items) + return -EINVAL; + mux = snd_soc_enum_item_to_val(e, ucontrol->value.enumerated.item[0]); changed = snd_soc_component_test_bits(component, e->reg, CTRL0_I2S_DAT_SEL, @@ -93,6 +96,9 @@ static int g12a_tohdmitx_spdif_mux_put_enum(struct snd_kcontrol *kcontrol, struct soc_enum *e = (struct soc_enum *)kcontrol->private_value; unsigned int mux, changed; + if (ucontrol->value.enumerated.item[0] >= e->items) + return -EINVAL; + mux = snd_soc_enum_item_to_val(e, ucontrol->value.enumerated.item[0]); changed = snd_soc_component_test_bits(component, TOHDMITX_CTRL0, CTRL0_SPDIF_SEL, @@ -112,7 +118,7 @@ static int g12a_tohdmitx_spdif_mux_put_enum(struct snd_kcontrol *kcontrol, snd_soc_dapm_mux_update_power(dapm, kcontrol, mux, e, NULL); - return 0; + return 1; } static SOC_ENUM_SINGLE_DECL(g12a_tohdmitx_spdif_mux_enum, TOHDMITX_CTRL0, diff --git a/tools/testing/selftests/bpf/verifier/ld_imm64.c b/tools/testing/selftests/bpf/verifier/ld_imm64.c index f9297900cea6d..78f19c255f20b 100644 --- a/tools/testing/selftests/bpf/verifier/ld_imm64.c +++ b/tools/testing/selftests/bpf/verifier/ld_imm64.c @@ -9,8 +9,8 @@ BPF_MOV64_IMM(BPF_REG_0, 2), BPF_EXIT_INSN(), }, - .errstr = "invalid BPF_LD_IMM insn", - .errstr_unpriv = "R1 pointer comparison", + .errstr = "jump into the middle of ldimm64 insn 1", + .errstr_unpriv = "jump into the middle of ldimm64 insn 1", .result = REJECT, }, { @@ -23,8 +23,8 @@ BPF_LD_IMM64(BPF_REG_0, 1), BPF_EXIT_INSN(), }, - .errstr = "invalid BPF_LD_IMM insn", - .errstr_unpriv = "R1 pointer comparison", + .errstr = "jump into the middle of ldimm64 insn 1", + .errstr_unpriv = "jump into the middle of ldimm64 insn 1", .result = REJECT, }, { diff --git a/tools/testing/selftests/drivers/net/bonding/bond-arp-interval-causes-panic.sh b/tools/testing/selftests/drivers/net/bonding/bond-arp-interval-causes-panic.sh index 71c00bfafbc99..2ff58fed76e28 100755 --- a/tools/testing/selftests/drivers/net/bonding/bond-arp-interval-causes-panic.sh +++ b/tools/testing/selftests/drivers/net/bonding/bond-arp-interval-causes-panic.sh @@ -33,16 +33,16 @@ ip netns add "client" ip link set dev link1_1 netns client down name eth0 ip netns exec client ip link add dev bond0 down type bond mode 1 \ miimon 100 all_slaves_active 1 -ip netns exec client ip link set dev eth0 down master bond0 +ip netns exec client ip link set dev eth0 master bond0 ip netns exec client ip link set dev bond0 up ip netns exec client ip addr add ${client_ip4}/24 dev bond0 ip netns exec client ping -c 5 $server_ip4 >/dev/null -ip netns exec client ip link set dev eth0 down nomaster +ip netns exec client ip link set dev eth0 nomaster ip netns exec client ip link set dev bond0 down ip netns exec client ip link set dev bond0 type bond mode 0 \ arp_interval 1000 arp_ip_target "+${server_ip4}" -ip netns exec client ip link set dev eth0 down master bond0 +ip netns exec client ip link set dev eth0 master bond0 ip netns exec client ip link set dev bond0 up ip netns exec client ping -c 5 $server_ip4 >/dev/null diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index e52d513009fb0..2107579e2939d 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -2167,9 +2167,9 @@ link_failure_tests() pm_nl_set_limits $ns1 0 2 pm_nl_add_endpoint $ns1 10.0.2.1 dev ns1eth2 flags signal pm_nl_set_limits $ns2 1 2 - FAILING_LINKS="1" pm_nl_add_endpoint $ns2 10.0.3.2 dev ns2eth3 flags subflow,backup - run_tests $ns1 $ns2 10.0.1.1 1 + FAILING_LINKS="1" \ + run_tests $ns1 $ns2 10.0.1.1 1 chk_join_nr 2 2 2 chk_add_nr 1 1 chk_link_usage $ns2 ns2eth3 $cinsent 0 @@ -2183,8 +2183,8 @@ link_failure_tests() pm_nl_add_endpoint $ns1 10.0.2.1 dev ns1eth2 flags signal pm_nl_set_limits $ns2 1 2 pm_nl_add_endpoint $ns2 10.0.3.2 dev ns2eth3 flags subflow,backup - FAILING_LINKS="1 2" - run_tests $ns1 $ns2 10.0.1.1 1 + FAILING_LINKS="1 2" \ + run_tests $ns1 $ns2 10.0.1.1 1 chk_join_nr 2 2 2 chk_add_nr 1 1 chk_stale_nr $ns2 2 4 2 @@ -2199,8 +2199,8 @@ link_failure_tests() pm_nl_add_endpoint $ns1 10.0.2.1 dev ns1eth2 flags signal pm_nl_set_limits $ns2 1 3 pm_nl_add_endpoint $ns2 10.0.3.2 dev ns2eth3 flags subflow,backup - FAILING_LINKS="1 2" - run_tests $ns1 $ns2 10.0.1.1 2 + FAILING_LINKS="1 2" \ + run_tests $ns1 $ns2 10.0.1.1 2 chk_join_nr 2 2 2 chk_add_nr 1 1 chk_stale_nr $ns2 1 -1 2 @@ -3041,7 +3041,7 @@ fastclose_tests() if reset_check_counter "fastclose server test" "MPTcpExtMPFastcloseRx"; then run_tests $ns1 $ns2 10.0.1.1 1024 0 fastclose_server - chk_join_nr 0 0 0 + chk_join_nr 0 0 0 0 0 0 1 chk_fclose_nr 1 1 invert chk_rst_nr 1 1 fi diff --git a/tools/testing/selftests/vm/memfd_secret.c b/tools/testing/selftests/vm/memfd_secret.c index 957b9e18c7295..9b298f6a04b37 100644 --- a/tools/testing/selftests/vm/memfd_secret.c +++ b/tools/testing/selftests/vm/memfd_secret.c @@ -62,6 +62,9 @@ static void test_mlock_limit(int fd) char *mem; len = mlock_limit_cur; + if (len % page_size != 0) + len = (len/page_size) * page_size; + mem = mmap(NULL, len, prot, mode, fd, 0); if (mem == MAP_FAILED) { fail("unable to mmap secret memory\n");