diff options
379 files changed, 4448 insertions, 2106 deletions
diff --git a/Documentation/ABI/stable/sysfs-block b/Documentation/ABI/stable/sysfs-block index 803f578dc023..0ddffc9133d0 100644 --- a/Documentation/ABI/stable/sysfs-block +++ b/Documentation/ABI/stable/sysfs-block @@ -731,7 +731,7 @@ Contact: linux-block@vger.kernel.org Description: [RW] If the device is registered for writeback throttling, then this file shows the target minimum read latency. If this latency - is exceeded in a given window of time (see wb_window_usec), then + is exceeded in a given window of time (see curr_win_nsec), then the writeback throttling will start scaling back writes. Writing a value of '0' to this file disables the feature. Writing a value of '-1' to this file resets the value to the default diff --git a/Documentation/admin-guide/blockdev/zoned_loop.rst b/Documentation/admin-guide/blockdev/zoned_loop.rst index 9c7aa3b482f3..64dcfde7450a 100644 --- a/Documentation/admin-guide/blockdev/zoned_loop.rst +++ b/Documentation/admin-guide/blockdev/zoned_loop.rst @@ -79,7 +79,7 @@ zone_capacity_mb Device zone capacity (must always be equal to or lower than the zone size. Default: zone size. conv_zones Total number of conventioanl zones starting from sector 0. Default: 8. -base_dir Path to the base directoy where to create the directory +base_dir Path to the base directory where to create the directory containing the zone files of the device. Default=/var/local/zloop. The device directory containing the zone files is always diff --git a/Documentation/admin-guide/hw-vuln/attack_vector_controls.rst b/Documentation/admin-guide/hw-vuln/attack_vector_controls.rst index b4de16f5ec44..6dd0800146f6 100644 --- a/Documentation/admin-guide/hw-vuln/attack_vector_controls.rst +++ b/Documentation/admin-guide/hw-vuln/attack_vector_controls.rst @@ -214,7 +214,7 @@ Spectre_v1 X Spectre_v2 X X Spectre_v2_user X X * (Note 1) SRBDS X X X X -SRSO X X +SRSO X X X X SSB (Note 4) TAA X X X X * (Note 2) TSA X X X X diff --git a/Documentation/core-api/symbol-namespaces.rst b/Documentation/core-api/symbol-namespaces.rst index 32fc73dc5529..034898e81ba2 100644 --- a/Documentation/core-api/symbol-namespaces.rst +++ b/Documentation/core-api/symbol-namespaces.rst @@ -76,20 +76,21 @@ unit as preprocessor statement. The above example would then read:: within the corresponding compilation unit before the #include for <linux/export.h>. Typically it's placed before the first #include statement. -Using the EXPORT_SYMBOL_GPL_FOR_MODULES() macro ------------------------------------------------ +Using the EXPORT_SYMBOL_FOR_MODULES() macro +------------------------------------------- Symbols exported using this macro are put into a module namespace. This -namespace cannot be imported. +namespace cannot be imported. These exports are GPL-only as they are only +intended for in-tree modules. The macro takes a comma separated list of module names, allowing only those modules to access this symbol. Simple tail-globs are supported. For example:: - EXPORT_SYMBOL_GPL_FOR_MODULES(preempt_notifier_inc, "kvm,kvm-*") + EXPORT_SYMBOL_FOR_MODULES(preempt_notifier_inc, "kvm,kvm-*") -will limit usage of this symbol to modules whoes name matches the given +will limit usage of this symbol to modules whose name matches the given patterns. How to use Symbols exported in Namespaces diff --git a/Documentation/devicetree/bindings/net/thead,th1520-gmac.yaml b/Documentation/devicetree/bindings/net/thead,th1520-gmac.yaml index 6d9de3303762..b3492a9aa4ef 100644 --- a/Documentation/devicetree/bindings/net/thead,th1520-gmac.yaml +++ b/Documentation/devicetree/bindings/net/thead,th1520-gmac.yaml @@ -62,11 +62,13 @@ properties: items: - description: GMAC main clock - description: Peripheral registers interface clock + - description: APB glue registers interface clock clock-names: items: - const: stmmaceth - const: pclk + - const: apb interrupts: items: @@ -88,8 +90,8 @@ examples: compatible = "thead,th1520-gmac", "snps,dwmac-3.70a"; reg = <0xe7070000 0x2000>, <0xec003000 0x1000>; reg-names = "dwmac", "apb"; - clocks = <&clk 1>, <&clk 2>; - clock-names = "stmmaceth", "pclk"; + clocks = <&clk 1>, <&clk 2>, <&clk 3>; + clock-names = "stmmaceth", "pclk", "apb"; interrupts = <66>; interrupt-names = "macirq"; phy-mode = "rgmii-id"; diff --git a/Documentation/devicetree/bindings/regulator/infineon,ir38060.yaml b/Documentation/devicetree/bindings/regulator/infineon,ir38060.yaml index e6ffbc2a2298..57ff6bf1e188 100644 --- a/Documentation/devicetree/bindings/regulator/infineon,ir38060.yaml +++ b/Documentation/devicetree/bindings/regulator/infineon,ir38060.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Infineon Buck Regulators with PMBUS interfaces maintainers: - - Not Me. + - Guenter Roeck <linux@roeck-us.net> allOf: - $ref: regulator.yaml# diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst index bb620f554598..9756d16e3df1 100644 --- a/Documentation/networking/ip-sysctl.rst +++ b/Documentation/networking/ip-sysctl.rst @@ -1420,7 +1420,7 @@ udp_hash_entries - INTEGER A negative value means the networking namespace does not own its hash buckets and shares the initial networking namespace's one. -udp_child_ehash_entries - INTEGER +udp_child_hash_entries - INTEGER Control the number of hash buckets for UDP sockets in the child networking namespace, which must be set before clone() or unshare(). diff --git a/Documentation/networking/mptcp-sysctl.rst b/Documentation/networking/mptcp-sysctl.rst index 5bfab01eff5a..1683c139821e 100644 --- a/Documentation/networking/mptcp-sysctl.rst +++ b/Documentation/networking/mptcp-sysctl.rst @@ -12,6 +12,8 @@ add_addr_timeout - INTEGER (seconds) resent to an MPTCP peer that has not acknowledged a previous ADD_ADDR message. + Do not retransmit if set to 0. + The default value matches TCP_RTO_MAX. This is a per-namespace sysctl. diff --git a/MAINTAINERS b/MAINTAINERS index fe168477caa4..2720544cd91f 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -11438,6 +11438,7 @@ F: drivers/tty/hvc/ HUNG TASK DETECTOR M: Andrew Morton <akpm@linux-foundation.org> R: Lance Yang <lance.yang@linux.dev> +R: Masami Hiramatsu <mhiramat@kernel.org> L: linux-kernel@vger.kernel.org S: Maintained F: include/linux/hung_task.h @@ -12583,10 +12584,9 @@ S: Supported F: drivers/cpufreq/intel_pstate.c INTEL PTP DFL ToD DRIVER -M: Tianfei Zhang <tianfei.zhang@intel.com> L: linux-fpga@vger.kernel.org L: netdev@vger.kernel.org -S: Maintained +S: Orphan F: drivers/ptp/ptp_dfl_tod.c INTEL QUADRATURE ENCODER PERIPHERAL DRIVER @@ -12724,9 +12724,8 @@ S: Maintained F: drivers/platform/x86/intel/wmi/thunderbolt.c INTEL WWAN IOSM DRIVER -M: M Chetan Kumar <m.chetan.kumar@intel.com> L: netdev@vger.kernel.org -S: Maintained +S: Orphan F: drivers/net/wwan/iosm/ INTEL(R) FLEXIBLE RETURN AND EVENT DELIVERY @@ -13686,7 +13685,6 @@ F: scripts/Makefile.kmsan KPROBES M: Naveen N Rao <naveen@kernel.org> -M: Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com> M: "David S. Miller" <davem@davemloft.net> M: Masami Hiramatsu <mhiramat@kernel.org> L: linux-kernel@vger.kernel.org @@ -15674,7 +15672,6 @@ MEDIATEK T7XX 5G WWAN MODEM DRIVER M: Chandrashekar Devegowda <chandrashekar.devegowda@intel.com> R: Chiranjeevi Rapolu <chiranjeevi.rapolu@linux.intel.com> R: Liu Haijun <haijun.liu@mediatek.com> -R: M Chetan Kumar <m.chetan.kumar@linux.intel.com> R: Ricardo Martinez <ricardo.martinez@linux.intel.com> L: netdev@vger.kernel.org S: Supported @@ -17451,6 +17448,7 @@ F: drivers/net/ethernet/neterion/ NETFILTER M: Pablo Neira Ayuso <pablo@netfilter.org> M: Jozsef Kadlecsik <kadlec@netfilter.org> +M: Florian Westphal <fw@strlen.de> L: netfilter-devel@vger.kernel.org L: coreteam@netfilter.org S: Maintained @@ -22176,7 +22174,7 @@ F: arch/s390/mm S390 NETWORK DRIVERS M: Alexandra Winter <wintera@linux.ibm.com> -M: Thorsten Winkler <twinkler@linux.ibm.com> +R: Aswin Karuvally <aswin@linux.ibm.com> L: linux-s390@vger.kernel.org L: netdev@vger.kernel.org S: Supported @@ -1,8 +1,8 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 6 -PATCHLEVEL = 16 +PATCHLEVEL = 17 SUBLEVEL = 0 -EXTRAVERSION = +EXTRAVERSION = -rc2 NAME = Baby Opossum Posse # *DOCUMENTATION* diff --git a/arch/loongarch/Makefile b/arch/loongarch/Makefile index b0703a4e02a2..a3a9759414f4 100644 --- a/arch/loongarch/Makefile +++ b/arch/loongarch/Makefile @@ -102,7 +102,13 @@ KBUILD_CFLAGS += $(call cc-option,-mthin-add-sub) $(call cc-option,-Wa$(comma) ifdef CONFIG_OBJTOOL ifdef CONFIG_CC_HAS_ANNOTATE_TABLEJUMP +# The annotate-tablejump option can not be passed to LLVM backend when LTO is enabled. +# Ensure it is aware of linker with LTO, '--loongarch-annotate-tablejump' also needs to +# be passed via '-mllvm' to ld.lld. KBUILD_CFLAGS += -mannotate-tablejump +ifdef CONFIG_LTO_CLANG +KBUILD_LDFLAGS += -mllvm --loongarch-annotate-tablejump +endif else KBUILD_CFLAGS += -fno-jump-tables # keep compatibility with older compilers endif diff --git a/arch/loongarch/include/asm/stackframe.h b/arch/loongarch/include/asm/stackframe.h index 3eda298702b1..5cb568a60cf8 100644 --- a/arch/loongarch/include/asm/stackframe.h +++ b/arch/loongarch/include/asm/stackframe.h @@ -58,7 +58,7 @@ .endm .macro STACKLEAK_ERASE -#ifdef CONFIG_GCC_PLUGIN_STACKLEAK +#ifdef CONFIG_KSTACK_ERASE bl stackleak_erase_on_task_stack #endif .endm diff --git a/arch/loongarch/include/uapi/asm/setup.h b/arch/loongarch/include/uapi/asm/setup.h new file mode 100644 index 000000000000..d46363ce3e02 --- /dev/null +++ b/arch/loongarch/include/uapi/asm/setup.h @@ -0,0 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ + +#ifndef _UAPI_ASM_LOONGARCH_SETUP_H +#define _UAPI_ASM_LOONGARCH_SETUP_H + +#define COMMAND_LINE_SIZE 4096 + +#endif /* _UAPI_ASM_LOONGARCH_SETUP_H */ diff --git a/arch/loongarch/kernel/module-sections.c b/arch/loongarch/kernel/module-sections.c index e2f30ff9afde..a43ba7f9f987 100644 --- a/arch/loongarch/kernel/module-sections.c +++ b/arch/loongarch/kernel/module-sections.c @@ -8,6 +8,7 @@ #include <linux/module.h> #include <linux/moduleloader.h> #include <linux/ftrace.h> +#include <linux/sort.h> Elf_Addr module_emit_got_entry(struct module *mod, Elf_Shdr *sechdrs, Elf_Addr val) { @@ -61,39 +62,38 @@ Elf_Addr module_emit_plt_entry(struct module *mod, Elf_Shdr *sechdrs, Elf_Addr v return (Elf_Addr)&plt[nr]; } -static int is_rela_equal(const Elf_Rela *x, const Elf_Rela *y) -{ - return x->r_info == y->r_info && x->r_addend == y->r_addend; -} +#define cmp_3way(a, b) ((a) < (b) ? -1 : (a) > (b)) -static bool duplicate_rela(const Elf_Rela *rela, int idx) +static int compare_rela(const void *x, const void *y) { - int i; + int ret; + const Elf_Rela *rela_x = x, *rela_y = y; - for (i = 0; i < idx; i++) { - if (is_rela_equal(&rela[i], &rela[idx])) - return true; - } + ret = cmp_3way(rela_x->r_info, rela_y->r_info); + if (ret == 0) + ret = cmp_3way(rela_x->r_addend, rela_y->r_addend); - return false; + return ret; } static void count_max_entries(Elf_Rela *relas, int num, unsigned int *plts, unsigned int *gots) { - unsigned int i, type; + unsigned int i; + + sort(relas, num, sizeof(Elf_Rela), compare_rela, NULL); for (i = 0; i < num; i++) { - type = ELF_R_TYPE(relas[i].r_info); - switch (type) { + if (i && !compare_rela(&relas[i-1], &relas[i])) + continue; + + switch (ELF_R_TYPE(relas[i].r_info)) { case R_LARCH_SOP_PUSH_PLT_PCREL: case R_LARCH_B26: - if (!duplicate_rela(relas, i)) - (*plts)++; + (*plts)++; break; case R_LARCH_GOT_PC_HI20: - if (!duplicate_rela(relas, i)) - (*gots)++; + (*gots)++; break; default: break; /* Do nothing. */ diff --git a/arch/loongarch/kernel/signal.c b/arch/loongarch/kernel/signal.c index 4740cb5b2388..c9f7ca778364 100644 --- a/arch/loongarch/kernel/signal.c +++ b/arch/loongarch/kernel/signal.c @@ -677,6 +677,11 @@ static int setup_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc, for (i = 1; i < 32; i++) err |= __put_user(regs->regs[i], &sc->sc_regs[i]); +#ifdef CONFIG_CPU_HAS_LBT + if (extctx->lbt.addr) + err |= protected_save_lbt_context(extctx); +#endif + if (extctx->lasx.addr) err |= protected_save_lasx_context(extctx); else if (extctx->lsx.addr) @@ -684,11 +689,6 @@ static int setup_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc, else if (extctx->fpu.addr) err |= protected_save_fpu_context(extctx); -#ifdef CONFIG_CPU_HAS_LBT - if (extctx->lbt.addr) - err |= protected_save_lbt_context(extctx); -#endif - /* Set the "end" magic */ info = (struct sctx_info *)extctx->end.addr; err |= __put_user(0, &info->magic); diff --git a/arch/loongarch/kernel/time.c b/arch/loongarch/kernel/time.c index 367906b10f81..f3092f2de8b5 100644 --- a/arch/loongarch/kernel/time.c +++ b/arch/loongarch/kernel/time.c @@ -5,6 +5,7 @@ * Copyright (C) 2020-2022 Loongson Technology Corporation Limited */ #include <linux/clockchips.h> +#include <linux/cpuhotplug.h> #include <linux/delay.h> #include <linux/export.h> #include <linux/init.h> @@ -102,6 +103,23 @@ static int constant_timer_next_event(unsigned long delta, struct clock_event_dev return 0; } +static int arch_timer_starting(unsigned int cpu) +{ + set_csr_ecfg(ECFGF_TIMER); + + return 0; +} + +static int arch_timer_dying(unsigned int cpu) +{ + constant_set_state_shutdown(this_cpu_ptr(&constant_clockevent_device)); + + /* Clear Timer Interrupt */ + write_csr_tintclear(CSR_TINTCLR_TI); + + return 0; +} + static unsigned long get_loops_per_jiffy(void) { unsigned long lpj = (unsigned long)const_clock_freq; @@ -172,6 +190,10 @@ int constant_clockevent_init(void) lpj_fine = get_loops_per_jiffy(); pr_info("Constant clock event device register\n"); + cpuhp_setup_state(CPUHP_AP_LOONGARCH_ARCH_TIMER_STARTING, + "clockevents/loongarch/timer:starting", + arch_timer_starting, arch_timer_dying); + return 0; } diff --git a/arch/loongarch/kvm/intc/eiointc.c b/arch/loongarch/kvm/intc/eiointc.c index a3a12af9ecbf..026b139dcff2 100644 --- a/arch/loongarch/kvm/intc/eiointc.c +++ b/arch/loongarch/kvm/intc/eiointc.c @@ -45,7 +45,12 @@ static void eiointc_update_irq(struct loongarch_eiointc *s, int irq, int level) } cpu = s->sw_coremap[irq]; - vcpu = kvm_get_vcpu(s->kvm, cpu); + vcpu = kvm_get_vcpu_by_id(s->kvm, cpu); + if (unlikely(vcpu == NULL)) { + kvm_err("%s: invalid target cpu: %d\n", __func__, cpu); + return; + } + if (level) { /* if not enable return false */ if (!test_bit(irq, (unsigned long *)s->enable.reg_u32)) diff --git a/arch/loongarch/kvm/intc/ipi.c b/arch/loongarch/kvm/intc/ipi.c index e658d5b37c04..5a8481dda052 100644 --- a/arch/loongarch/kvm/intc/ipi.c +++ b/arch/loongarch/kvm/intc/ipi.c @@ -99,7 +99,7 @@ static void write_mailbox(struct kvm_vcpu *vcpu, int offset, uint64_t data, int static int send_ipi_data(struct kvm_vcpu *vcpu, gpa_t addr, uint64_t data) { int i, idx, ret; - uint32_t val = 0, mask = 0; + uint64_t val = 0, mask = 0; /* * Bit 27-30 is mask for byte writing. @@ -108,7 +108,7 @@ static int send_ipi_data(struct kvm_vcpu *vcpu, gpa_t addr, uint64_t data) if ((data >> 27) & 0xf) { /* Read the old val */ idx = srcu_read_lock(&vcpu->kvm->srcu); - ret = kvm_io_bus_read(vcpu, KVM_IOCSR_BUS, addr, sizeof(val), &val); + ret = kvm_io_bus_read(vcpu, KVM_IOCSR_BUS, addr, 4, &val); srcu_read_unlock(&vcpu->kvm->srcu, idx); if (unlikely(ret)) { kvm_err("%s: : read data from addr %llx failed\n", __func__, addr); @@ -124,7 +124,7 @@ static int send_ipi_data(struct kvm_vcpu *vcpu, gpa_t addr, uint64_t data) } val |= ((uint32_t)(data >> 32) & ~mask); idx = srcu_read_lock(&vcpu->kvm->srcu); - ret = kvm_io_bus_write(vcpu, KVM_IOCSR_BUS, addr, sizeof(val), &val); + ret = kvm_io_bus_write(vcpu, KVM_IOCSR_BUS, addr, 4, &val); srcu_read_unlock(&vcpu->kvm->srcu, idx); if (unlikely(ret)) kvm_err("%s: : write data to addr %llx failed\n", __func__, addr); @@ -298,7 +298,7 @@ static int kvm_ipi_regs_access(struct kvm_device *dev, cpu = (attr->attr >> 16) & 0x3ff; addr = attr->attr & 0xff; - vcpu = kvm_get_vcpu(dev->kvm, cpu); + vcpu = kvm_get_vcpu_by_id(dev->kvm, cpu); if (unlikely(vcpu == NULL)) { kvm_err("%s: invalid target cpu: %d\n", __func__, cpu); return -EINVAL; diff --git a/arch/loongarch/kvm/intc/pch_pic.c b/arch/loongarch/kvm/intc/pch_pic.c index 6f00ffe05c54..119290bcea79 100644 --- a/arch/loongarch/kvm/intc/pch_pic.c +++ b/arch/loongarch/kvm/intc/pch_pic.c @@ -195,6 +195,11 @@ static int kvm_pch_pic_read(struct kvm_vcpu *vcpu, return -EINVAL; } + if (addr & (len - 1)) { + kvm_err("%s: pch pic not aligned addr %llx len %d\n", __func__, addr, len); + return -EINVAL; + } + /* statistics of pch pic reading */ vcpu->stat.pch_pic_read_exits++; ret = loongarch_pch_pic_read(s, addr, len, val); @@ -302,6 +307,11 @@ static int kvm_pch_pic_write(struct kvm_vcpu *vcpu, return -EINVAL; } + if (addr & (len - 1)) { + kvm_err("%s: pch pic not aligned addr %llx len %d\n", __func__, addr, len); + return -EINVAL; + } + /* statistics of pch pic writing */ vcpu->stat.pch_pic_write_exits++; ret = loongarch_pch_pic_write(s, addr, len, val); diff --git a/arch/loongarch/kvm/vcpu.c b/arch/loongarch/kvm/vcpu.c index d1b8c50941ca..ce478151466c 100644 --- a/arch/loongarch/kvm/vcpu.c +++ b/arch/loongarch/kvm/vcpu.c @@ -1283,9 +1283,11 @@ int kvm_own_lbt(struct kvm_vcpu *vcpu) return -EINVAL; preempt_disable(); - set_csr_euen(CSR_EUEN_LBTEN); - _restore_lbt(&vcpu->arch.lbt); - vcpu->arch.aux_inuse |= KVM_LARCH_LBT; + if (!(vcpu->arch.aux_inuse & KVM_LARCH_LBT)) { + set_csr_euen(CSR_EUEN_LBTEN); + _restore_lbt(&vcpu->arch.lbt); + vcpu->arch.aux_inuse |= KVM_LARCH_LBT; + } preempt_enable(); return 0; diff --git a/arch/riscv/boot/dts/thead/th1520.dtsi b/arch/riscv/boot/dts/thead/th1520.dtsi index 42724bf7e90e..03f1d7319049 100644 --- a/arch/riscv/boot/dts/thead/th1520.dtsi +++ b/arch/riscv/boot/dts/thead/th1520.dtsi @@ -297,8 +297,9 @@ reg-names = "dwmac", "apb"; interrupts = <67 IRQ_TYPE_LEVEL_HIGH>; interrupt-names = "macirq"; - clocks = <&clk CLK_GMAC_AXI>, <&clk CLK_GMAC1>; - clock-names = "stmmaceth", "pclk"; + clocks = <&clk CLK_GMAC_AXI>, <&clk CLK_GMAC1>, + <&clk CLK_PERISYS_APB4_HCLK>; + clock-names = "stmmaceth", "pclk", "apb"; snps,pbl = <32>; snps,fixed-burst; snps,multicast-filter-bins = <64>; @@ -319,8 +320,9 @@ reg-names = "dwmac", "apb"; interrupts = <66 IRQ_TYPE_LEVEL_HIGH>; interrupt-names = "macirq"; - clocks = <&clk CLK_GMAC_AXI>, <&clk CLK_GMAC0>; - clock-names = "stmmaceth", "pclk"; + clocks = <&clk CLK_GMAC_AXI>, <&clk CLK_GMAC0>, + <&clk CLK_PERISYS_APB4_HCLK>; + clock-names = "stmmaceth", "pclk", "apb"; snps,pbl = <32>; snps,fixed-burst; snps,multicast-filter-bins = <64>; diff --git a/arch/x86/boot/cpuflags.c b/arch/x86/boot/cpuflags.c index 916bac09b464..63e037e94e4c 100644 --- a/arch/x86/boot/cpuflags.c +++ b/arch/x86/boot/cpuflags.c @@ -106,5 +106,18 @@ void get_cpuflags(void) cpuid(0x80000001, &ignored, &ignored, &cpu.flags[6], &cpu.flags[1]); } + + if (max_amd_level >= 0x8000001f) { + u32 ebx; + + /* + * The X86_FEATURE_COHERENCY_SFW_NO feature bit is in + * the virtualization flags entry (word 8) and set by + * scattered.c, so the bit needs to be explicitly set. + */ + cpuid(0x8000001f, &ignored, &ebx, &ignored, &ignored); + if (ebx & BIT(31)) + set_bit(X86_FEATURE_COHERENCY_SFW_NO, cpu.flags); + } } } diff --git a/arch/x86/boot/startup/sev-shared.c b/arch/x86/boot/startup/sev-shared.c index 7a706db87b93..a34cd19796f9 100644 --- a/arch/x86/boot/startup/sev-shared.c +++ b/arch/x86/boot/startup/sev-shared.c @@ -785,6 +785,7 @@ static void __head svsm_pval_4k_page(unsigned long paddr, bool validate) pc->entry[0].page_size = RMP_PG_SIZE_4K; pc->entry[0].action = validate; pc->entry[0].ignore_cf = 0; + pc->entry[0].rsvd = 0; pc->entry[0].pfn = paddr >> PAGE_SHIFT; /* Protocol 0, Call ID 1 */ @@ -810,6 +811,13 @@ static void __head pvalidate_4k_page(unsigned long vaddr, unsigned long paddr, if (ret) sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_PVALIDATE); } + + /* + * If validating memory (making it private) and affected by the + * cache-coherency vulnerability, perform the cache eviction mitigation. + */ + if (validate && !has_cpuflag(X86_FEATURE_COHERENCY_SFW_NO)) + sev_evict_cache((void *)vaddr, 1); } /* diff --git a/arch/x86/coco/sev/core.c b/arch/x86/coco/sev/core.c index fc59ce78c477..14ef5908fb27 100644 --- a/arch/x86/coco/sev/core.c +++ b/arch/x86/coco/sev/core.c @@ -227,6 +227,7 @@ static u64 svsm_build_ca_from_pfn_range(u64 pfn, u64 pfn_end, bool action, pe->page_size = RMP_PG_SIZE_4K; pe->action = action; pe->ignore_cf = 0; + pe->rsvd = 0; pe->pfn = pfn; pe++; @@ -257,6 +258,7 @@ static int svsm_build_ca_from_psc_desc(struct snp_psc_desc *desc, unsigned int d pe->page_size = e->pagesize ? RMP_PG_SIZE_2M : RMP_PG_SIZE_4K; pe->action = e->operation == SNP_PAGE_STATE_PRIVATE; pe->ignore_cf = 0; + pe->rsvd = 0; pe->pfn = e->gfn; pe++; @@ -358,10 +360,31 @@ static void svsm_pval_pages(struct snp_psc_desc *desc) static void pvalidate_pages(struct snp_psc_desc *desc) { + struct psc_entry *e; + unsigned int i; + if (snp_vmpl) svsm_pval_pages(desc); else pval_pages(desc); + + /* + * If not affected by the cache-coherency vulnerability there is no need + * to perform the cache eviction mitigation. + */ + if (cpu_feature_enabled(X86_FEATURE_COHERENCY_SFW_NO)) + return; + + for (i = 0; i <= desc->hdr.end_entry; i++) { + e = &desc->entries[i]; + + /* + * If validating memory (making it private) perform the cache + * eviction mitigation. + */ + if (e->operation == SNP_PAGE_STATE_PRIVATE) + sev_evict_cache(pfn_to_kaddr(e->gfn), e->pagesize ? 512 : 1); + } } static int vmgexit_psc(struct ghcb *ghcb, struct snp_psc_desc *desc) diff --git a/arch/x86/coco/sev/vc-handle.c b/arch/x86/coco/sev/vc-handle.c index faf1fce89ed4..c3b4acbde0d8 100644 --- a/arch/x86/coco/sev/vc-handle.c +++ b/arch/x86/coco/sev/vc-handle.c @@ -371,29 +371,30 @@ static enum es_result __vc_handle_msr_caa(struct pt_regs *regs, bool write) * executing with Secure TSC enabled, so special handling is required for * accesses of MSR_IA32_TSC and MSR_AMD64_GUEST_TSC_FREQ. */ -static enum es_result __vc_handle_secure_tsc_msrs(struct pt_regs *regs, bool write) +static enum es_result __vc_handle_secure_tsc_msrs(struct es_em_ctxt *ctxt, bool write) { + struct pt_regs *regs = ctxt->regs; u64 tsc; /* - * GUEST_TSC_FREQ should not be intercepted when Secure TSC is enabled. - * Terminate the SNP guest when the interception is enabled. + * Writing to MSR_IA32_TSC can cause subsequent reads of the TSC to + * return undefined values, and GUEST_TSC_FREQ is read-only. Generate + * a #GP on all writes. */ - if (regs->cx == MSR_AMD64_GUEST_TSC_FREQ) - return ES_VMM_ERROR; + if (write) { + ctxt->fi.vector = X86_TRAP_GP; + ctxt->fi.error_code = 0; + return ES_EXCEPTION; + } /* - * Writes: Writing to MSR_IA32_TSC can cause subsequent reads of the TSC - * to return undefined values, so ignore all writes. - * - * Reads: Reads of MSR_IA32_TSC should return the current TSC value, use - * the value returned by rdtsc_ordered(). + * GUEST_TSC_FREQ read should not be intercepted when Secure TSC is + * enabled. Terminate the guest if a read is attempted. */ - if (write) { - WARN_ONCE(1, "TSC MSR writes are verboten!\n"); - return ES_OK; - } + if (regs->cx == MSR_AMD64_GUEST_TSC_FREQ) + return ES_VMM_ERROR; + /* Reads of MSR_IA32_TSC should return the current TSC value. */ tsc = rdtsc_ordered(); regs->ax = lower_32_bits(tsc); regs->dx = upper_32_bits(tsc); @@ -416,7 +417,7 @@ static enum es_result vc_handle_msr(struct ghcb *ghcb, struct es_em_ctxt *ctxt) case MSR_IA32_TSC: case MSR_AMD64_GUEST_TSC_FREQ: if (sev_status & MSR_AMD64_SNP_SECURE_TSC) - return __vc_handle_secure_tsc_msrs(regs, write); + return __vc_handle_secure_tsc_msrs(ctxt, write); break; default: break; diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 602957dd2609..06fc0479a23f 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -218,6 +218,7 @@ #define X86_FEATURE_FLEXPRIORITY ( 8*32+ 1) /* "flexpriority" Intel FlexPriority */ #define X86_FEATURE_EPT ( 8*32+ 2) /* "ept" Intel Extended Page Table */ #define X86_FEATURE_VPID ( 8*32+ 3) /* "vpid" Intel Virtual Processor ID */ +#define X86_FEATURE_COHERENCY_SFW_NO ( 8*32+ 4) /* SNP cache coherency software work around not needed */ #define X86_FEATURE_VMMCALL ( 8*32+15) /* "vmmcall" Prefer VMMCALL to VMCALL */ #define X86_FEATURE_XENPV ( 8*32+16) /* Xen paravirtual guest */ diff --git a/arch/x86/include/asm/cpuid.h b/arch/x86/include/asm/cpuid.h deleted file mode 100644 index d5749b25fa10..000000000000 --- a/arch/x86/include/asm/cpuid.h +++ /dev/null @@ -1,8 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ - -#ifndef _ASM_X86_CPUID_H -#define _ASM_X86_CPUID_H - -#include <asm/cpuid/api.h> - -#endif /* _ASM_X86_CPUID_H */ diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h index 162ebd73a698..cbe19e669080 100644 --- a/arch/x86/include/asm/hw_irq.h +++ b/arch/x86/include/asm/hw_irq.h @@ -92,8 +92,6 @@ struct irq_cfg { extern struct irq_cfg *irq_cfg(unsigned int irq); extern struct irq_cfg *irqd_cfg(struct irq_data *irq_data); -extern void lock_vector_lock(void); -extern void unlock_vector_lock(void); #ifdef CONFIG_SMP extern void vector_schedule_cleanup(struct irq_cfg *); extern void irq_complete_move(struct irq_cfg *cfg); @@ -101,12 +99,16 @@ extern void irq_complete_move(struct irq_cfg *cfg); static inline void vector_schedule_cleanup(struct irq_cfg *c) { } static inline void irq_complete_move(struct irq_cfg *c) { } #endif - extern void apic_ack_edge(struct irq_data *data); -#else /* CONFIG_IRQ_DOMAIN_HIERARCHY */ +#endif /* CONFIG_IRQ_DOMAIN_HIERARCHY */ + +#ifdef CONFIG_X86_LOCAL_APIC +extern void lock_vector_lock(void); +extern void unlock_vector_lock(void); +#else static inline void lock_vector_lock(void) {} static inline void unlock_vector_lock(void) {} -#endif /* CONFIG_IRQ_DOMAIN_HIERARCHY */ +#endif /* Statistics */ extern atomic_t irq_err_count; diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h index be10c188614f..e345dbdf933e 100644 --- a/arch/x86/include/asm/intel-family.h +++ b/arch/x86/include/asm/intel-family.h @@ -150,6 +150,11 @@ #define INTEL_PANTHERLAKE_L IFM(6, 0xCC) /* Cougar Cove / Crestmont */ +#define INTEL_WILDCATLAKE_L IFM(6, 0xD5) + +#define INTEL_NOVALAKE IFM(18, 0x01) +#define INTEL_NOVALAKE_L IFM(18, 0x03) + /* "Small Core" Processors (Atom/E-Core) */ #define INTEL_ATOM_BONNELL IFM(6, 0x1C) /* Diamondville, Pineview */ diff --git a/arch/x86/include/asm/sev.h b/arch/x86/include/asm/sev.h index 89075ff19afa..02236962fdb1 100644 --- a/arch/x86/include/asm/sev.h +++ b/arch/x86/include/asm/sev.h @@ -619,6 +619,24 @@ int rmp_make_shared(u64 pfn, enum pg_level level); void snp_leak_pages(u64 pfn, unsigned int npages); void kdump_sev_callback(void); void snp_fixup_e820_tables(void); + +static inline void sev_evict_cache(void *va, int npages) +{ + volatile u8 val __always_unused; + u8 *bytes = va; + int page_idx; + + /* + * For SEV guests, a read from the first/last cache-lines of a 4K page + * using the guest key is sufficient to cause a flush of all cache-lines + * associated with that 4K page without incurring all the overhead of a + * full CLFLUSH sequence. + */ + for (page_idx = 0; page_idx < npages; page_idx++) { + val = bytes[page_idx * PAGE_SIZE]; + val = bytes[page_idx * PAGE_SIZE + PAGE_SIZE - 1]; + } +} #else static inline bool snp_probe_rmptable_info(void) { return false; } static inline int snp_rmptable_init(void) { return -ENOSYS; } @@ -634,6 +652,7 @@ static inline int rmp_make_shared(u64 pfn, enum pg_level level) { return -ENODEV static inline void snp_leak_pages(u64 pfn, unsigned int npages) {} static inline void kdump_sev_callback(void) { } static inline void snp_fixup_e820_tables(void) {} +static inline void sev_evict_cache(void *va, int npages) {} #endif #endif diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index b74bf937cd9f..2186a771b9fc 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -386,7 +386,6 @@ static bool __init should_mitigate_vuln(unsigned int bug) case X86_BUG_SPECTRE_V2: case X86_BUG_RETBLEED: - case X86_BUG_SRSO: case X86_BUG_L1TF: case X86_BUG_ITS: return cpu_attack_vector_mitigated(CPU_MITIGATE_USER_KERNEL) || @@ -3184,8 +3183,18 @@ static void __init srso_select_mitigation(void) } if (srso_mitigation == SRSO_MITIGATION_AUTO) { - if (should_mitigate_vuln(X86_BUG_SRSO)) { + /* + * Use safe-RET if user->kernel or guest->host protection is + * required. Otherwise the 'microcode' mitigation is sufficient + * to protect the user->user and guest->guest vectors. + */ + if (cpu_attack_vector_mitigated(CPU_MITIGATE_GUEST_HOST) || + (cpu_attack_vector_mitigated(CPU_MITIGATE_USER_KERNEL) && + !boot_cpu_has(X86_FEATURE_SRSO_USER_KERNEL_NO))) { srso_mitigation = SRSO_MITIGATION_SAFE_RET; + } else if (cpu_attack_vector_mitigated(CPU_MITIGATE_USER_USER) || + cpu_attack_vector_mitigated(CPU_MITIGATE_GUEST_GUEST)) { + srso_mitigation = SRSO_MITIGATION_MICROCODE; } else { srso_mitigation = SRSO_MITIGATION_NONE; return; diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c index b4a1f6732a3a..6b868afb26c3 100644 --- a/arch/x86/kernel/cpu/scattered.c +++ b/arch/x86/kernel/cpu/scattered.c @@ -48,6 +48,7 @@ static const struct cpuid_bit cpuid_bits[] = { { X86_FEATURE_PROC_FEEDBACK, CPUID_EDX, 11, 0x80000007, 0 }, { X86_FEATURE_AMD_FAST_CPPC, CPUID_EDX, 15, 0x80000007, 0 }, { X86_FEATURE_MBA, CPUID_EBX, 6, 0x80000008, 0 }, + { X86_FEATURE_COHERENCY_SFW_NO, CPUID_EBX, 31, 0x8000001f, 0 }, { X86_FEATURE_SMBA, CPUID_EBX, 2, 0x80000020, 0 }, { X86_FEATURE_BMEC, CPUID_EBX, 3, 0x80000020, 0 }, { X86_FEATURE_TSA_SQ_NO, CPUID_ECX, 1, 0x80000021, 0 }, diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index 12ed75c1b567..28e4fd65c9da 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -1881,19 +1881,20 @@ long fpu_xstate_prctl(int option, unsigned long arg2) #ifdef CONFIG_PROC_PID_ARCH_STATUS /* * Report the amount of time elapsed in millisecond since last AVX512 - * use in the task. + * use in the task. Report -1 if no AVX-512 usage. */ static void avx512_status(struct seq_file *m, struct task_struct *task) { - unsigned long timestamp = READ_ONCE(x86_task_fpu(task)->avx512_timestamp); - long delta; + unsigned long timestamp; + long delta = -1; - if (!timestamp) { - /* - * Report -1 if no AVX512 usage - */ - delta = -1; - } else { + /* AVX-512 usage is not tracked for kernel threads. Don't report anything. */ + if (task->flags & (PF_KTHREAD | PF_USER_WORKER)) + return; + + timestamp = READ_ONCE(x86_task_fpu(task)->avx512_timestamp); + + if (timestamp) { delta = (long)(jiffies - timestamp); /* * Cap to LONG_MAX if time difference > LONG_MAX diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c index 9ed29ff10e59..10721a125226 100644 --- a/arch/x86/kernel/irq.c +++ b/arch/x86/kernel/irq.c @@ -256,26 +256,59 @@ static __always_inline void handle_irq(struct irq_desc *desc, __handle_irq(desc, regs); } -static __always_inline int call_irq_handler(int vector, struct pt_regs *regs) +static struct irq_desc *reevaluate_vector(int vector) { - struct irq_desc *desc; - int ret = 0; + struct irq_desc *desc = __this_cpu_read(vector_irq[vector]); + + if (!IS_ERR_OR_NULL(desc)) + return desc; + + if (desc == VECTOR_UNUSED) + pr_emerg_ratelimited("No irq handler for %d.%u\n", smp_processor_id(), vector); + else + __this_cpu_write(vector_irq[vector], VECTOR_UNUSED); + return NULL; +} + +static __always_inline bool call_irq_handler(int vector, struct pt_regs *regs) +{ + struct irq_desc *desc = __this_cpu_read(vector_irq[vector]); - desc = __this_cpu_read(vector_irq[vector]); if (likely(!IS_ERR_OR_NULL(desc))) { handle_irq(desc, regs); - } else { - ret = -EINVAL; - if (desc == VECTOR_UNUSED) { - pr_emerg_ratelimited("%s: %d.%u No irq handler for vector\n", - __func__, smp_processor_id(), - vector); - } else { - __this_cpu_write(vector_irq[vector], VECTOR_UNUSED); - } + return true; } - return ret; + /* + * Reevaluate with vector_lock held to prevent a race against + * request_irq() setting up the vector: + * + * CPU0 CPU1 + * interrupt is raised in APIC IRR + * but not handled + * free_irq() + * per_cpu(vector_irq, CPU1)[vector] = VECTOR_SHUTDOWN; + * + * request_irq() common_interrupt() + * d = this_cpu_read(vector_irq[vector]); + * + * per_cpu(vector_irq, CPU1)[vector] = desc; + * + * if (d == VECTOR_SHUTDOWN) + * this_cpu_write(vector_irq[vector], VECTOR_UNUSED); + * + * This requires that the same vector on the same target CPU is + * handed out or that a spurious interrupt hits that CPU/vector. + */ + lock_vector_lock(); + desc = reevaluate_vector(vector); + unlock_vector_lock(); + + if (!desc) + return false; + + handle_irq(desc, regs); + return true; } /* @@ -289,7 +322,7 @@ DEFINE_IDTENTRY_IRQ(common_interrupt) /* entry code tells RCU that we're not quiescent. Check it. */ RCU_LOCKDEP_WARN(!rcu_is_watching(), "IRQ failed to wake up RCU"); - if (unlikely(call_irq_handler(vector, regs))) + if (unlikely(!call_irq_handler(vector, regs))) apic_eoi(); set_irq_regs(old_regs); diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c index 3bf76902f07f..50e51047e1fe 100644 --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -5847,8 +5847,7 @@ static struct bfq_queue *bfq_get_queue(struct bfq_data *bfqd, goto out; } - bfqq = kmem_cache_alloc_node(bfq_pool, - GFP_NOWAIT | __GFP_ZERO | __GFP_NOWARN, + bfqq = kmem_cache_alloc_node(bfq_pool, GFP_NOWAIT | __GFP_ZERO, bfqd->queue->node); if (bfqq) { diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index 5936db7f8475..fe9ebd6a2e14 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -394,7 +394,7 @@ static struct blkcg_gq *blkg_create(struct blkcg *blkcg, struct gendisk *disk, /* allocate */ if (!new_blkg) { - new_blkg = blkg_alloc(blkcg, disk, GFP_NOWAIT | __GFP_NOWARN); + new_blkg = blkg_alloc(blkcg, disk, GFP_NOWAIT); if (unlikely(!new_blkg)) { ret = -ENOMEM; goto err_put_css; @@ -1467,7 +1467,7 @@ blkcg_css_alloc(struct cgroup_subsys_state *parent_css) spin_lock_init(&blkcg->lock); refcount_set(&blkcg->online_pin, 1); - INIT_RADIX_TREE(&blkcg->blkg_tree, GFP_NOWAIT | __GFP_NOWARN); + INIT_RADIX_TREE(&blkcg->blkg_tree, GFP_NOWAIT); INIT_HLIST_HEAD(&blkcg->blkg_list); #ifdef CONFIG_CGROUP_WRITEBACK INIT_LIST_HEAD(&blkcg->cgwb_list); @@ -1630,7 +1630,7 @@ retry: pd_prealloc = NULL; } else { pd = pol->pd_alloc_fn(disk, blkg->blkcg, - GFP_NOWAIT | __GFP_NOWARN); + GFP_NOWAIT); } if (!pd) { diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index 396cded255ea..4a7f1a349998 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -847,7 +847,7 @@ static void blk_queue_release(struct kobject *kobj) /* nothing to do here, all data is associated with the parent gendisk */ } -static const struct kobj_type blk_queue_ktype = { +const struct kobj_type blk_queue_ktype = { .default_groups = blk_queue_attr_groups, .sysfs_ops = &queue_sysfs_ops, .release = blk_queue_release, @@ -875,15 +875,14 @@ int blk_register_queue(struct gendisk *disk) struct request_queue *q = disk->queue; int ret; - kobject_init(&disk->queue_kobj, &blk_queue_ktype); ret = kobject_add(&disk->queue_kobj, &disk_to_dev(disk)->kobj, "queue"); if (ret < 0) - goto out_put_queue_kobj; + return ret; if (queue_is_mq(q)) { ret = blk_mq_sysfs_register(disk); if (ret) - goto out_put_queue_kobj; + goto out_del_queue_kobj; } mutex_lock(&q->sysfs_lock); @@ -903,9 +902,9 @@ int blk_register_queue(struct gendisk *disk) if (queue_is_mq(q)) elevator_set_default(q); - wbt_enable_default(disk); blk_queue_flag_set(QUEUE_FLAG_REGISTERED, q); + wbt_enable_default(disk); /* Now everything is ready and send out KOBJ_ADD uevent */ kobject_uevent(&disk->queue_kobj, KOBJ_ADD); @@ -934,8 +933,8 @@ out_debugfs_remove: mutex_unlock(&q->sysfs_lock); if (queue_is_mq(q)) blk_mq_sysfs_unregister(disk); -out_put_queue_kobj: - kobject_put(&disk->queue_kobj); +out_del_queue_kobj: + kobject_del(&disk->queue_kobj); return ret; } @@ -986,5 +985,4 @@ void blk_unregister_queue(struct gendisk *disk) elevator_set_none(q); blk_debugfs_remove(disk); - kobject_put(&disk->queue_kobj); } diff --git a/block/blk-wbt.c b/block/blk-wbt.c index a50d4cd55f41..eb8037bae0bd 100644 --- a/block/blk-wbt.c +++ b/block/blk-wbt.c @@ -85,8 +85,8 @@ struct rq_wb { u64 sync_issue; void *sync_cookie; - unsigned long last_issue; /* last non-throttled issue */ - unsigned long last_comp; /* last non-throttled comp */ + unsigned long last_issue; /* issue time of last read rq */ + unsigned long last_comp; /* completion time of last read rq */ unsigned long min_lat_nsec; struct rq_qos rqos; struct rq_wait rq_wait[WBT_NUM_RWQ]; @@ -248,13 +248,14 @@ static void wbt_done(struct rq_qos *rqos, struct request *rq) struct rq_wb *rwb = RQWB(rqos); if (!wbt_is_tracked(rq)) { - if (rwb->sync_cookie == rq) { - rwb->sync_issue = 0; - rwb->sync_cookie = NULL; - } + if (wbt_is_read(rq)) { + if (rwb->sync_cookie == rq) { + rwb->sync_issue = 0; + rwb->sync_cookie = NULL; + } - if (wbt_is_read(rq)) wb_timestamp(rwb, &rwb->last_comp); + } } else { WARN_ON_ONCE(rq == rwb->sync_cookie); __wbt_done(rqos, wbt_flags(rq)); diff --git a/block/blk.h b/block/blk.h index 0a2eccf28ca4..46f566f9b126 100644 --- a/block/blk.h +++ b/block/blk.h @@ -29,6 +29,7 @@ struct elevator_tags; /* Max future timer expiry for timeouts */ #define BLK_MAX_TIMEOUT (5 * HZ) +extern const struct kobj_type blk_queue_ktype; extern struct dentry *blk_debugfs_root; struct blk_flush_queue { diff --git a/block/genhd.c b/block/genhd.c index c26733f6324b..9bbc38d12792 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -1303,6 +1303,7 @@ static void disk_release(struct device *dev) disk_free_zone_resources(disk); xa_destroy(&disk->part_tbl); + kobject_put(&disk->queue_kobj); disk->queue->disk = NULL; blk_put_queue(disk->queue); @@ -1486,6 +1487,7 @@ struct gendisk *__alloc_disk_node(struct request_queue *q, int node_id, INIT_LIST_HEAD(&disk->slave_bdevs); #endif mutex_init(&disk->rqos_state_mutex); + kobject_init(&disk->queue_kobj, &blk_queue_ktype); return disk; out_erase_part0: diff --git a/drivers/accel/habanalabs/common/memory.c b/drivers/accel/habanalabs/common/memory.c index 601fdbe70179..61472a381904 100644 --- a/drivers/accel/habanalabs/common/memory.c +++ b/drivers/accel/habanalabs/common/memory.c @@ -1829,9 +1829,6 @@ static void hl_release_dmabuf(struct dma_buf *dmabuf) struct hl_dmabuf_priv *hl_dmabuf = dmabuf->priv; struct hl_ctx *ctx; - if (!hl_dmabuf) - return; - ctx = hl_dmabuf->ctx; if (hl_dmabuf->memhash_hnode) @@ -1859,7 +1856,12 @@ static int export_dmabuf(struct hl_ctx *ctx, { DEFINE_DMA_BUF_EXPORT_INFO(exp_info); struct hl_device *hdev = ctx->hdev; - int rc, fd; + CLASS(get_unused_fd, fd)(flags); + + if (fd < 0) { + dev_err(hdev->dev, "failed to get a file descriptor for a dma-buf, %d\n", fd); + return fd; + } exp_info.ops = &habanalabs_dmabuf_ops; exp_info.size = total_size; @@ -1872,13 +1874,6 @@ static int export_dmabuf(struct hl_ctx *ctx, return PTR_ERR(hl_dmabuf->dmabuf); } - fd = dma_buf_fd(hl_dmabuf->dmabuf, flags); - if (fd < 0) { - dev_err(hdev->dev, "failed to get a file descriptor for a dma-buf, %d\n", fd); - rc = fd; - goto err_dma_buf_put; - } - hl_dmabuf->ctx = ctx; hl_ctx_get(hl_dmabuf->ctx); atomic_inc(&ctx->hdev->dmabuf_export_cnt); @@ -1890,13 +1885,9 @@ static int export_dmabuf(struct hl_ctx *ctx, get_file(ctx->hpriv->file_priv->filp); *dmabuf_fd = fd; + fd_install(take_fd(fd), hl_dmabuf->dmabuf->file); return 0; - -err_dma_buf_put: - hl_dmabuf->dmabuf->priv = NULL; - dma_buf_put(hl_dmabuf->dmabuf); - return rc; } static int validate_export_params_common(struct hl_device *hdev, u64 addr, u64 size, u64 offset) diff --git a/drivers/acpi/apei/einj-core.c b/drivers/acpi/apei/einj-core.c index bf8dc92a373a..2561b045acc7 100644 --- a/drivers/acpi/apei/einj-core.c +++ b/drivers/acpi/apei/einj-core.c @@ -315,7 +315,7 @@ static void __iomem *einj_get_parameter_address(void) memcpy_fromio(&v5param, p, v5param_size); acpi5 = 1; check_vendor_extension(pa_v5, &v5param); - if (available_error_type & ACPI65_EINJV2_SUPP) { + if (is_v2 && available_error_type & ACPI65_EINJV2_SUPP) { len = v5param.einjv2_struct.length; offset = offsetof(struct einjv2_extension_struct, component_arr); max_nr_components = (len - offset) / @@ -540,6 +540,9 @@ static int __einj_error_inject(u32 type, u32 flags, u64 param1, u64 param2, struct set_error_type_with_address *v5param; v5param = kmalloc(v5param_size, GFP_KERNEL); + if (!v5param) + return -ENOMEM; + memcpy_fromio(v5param, einj_param, v5param_size); v5param->type = type; if (type & ACPI5_VENDOR_BIT) { @@ -1091,7 +1094,7 @@ err_put_table: return rc; } -static void __exit einj_remove(struct faux_device *fdev) +static void einj_remove(struct faux_device *fdev) { struct apei_exec_context ctx; @@ -1114,15 +1117,9 @@ static void __exit einj_remove(struct faux_device *fdev) } static struct faux_device *einj_dev; -/* - * einj_remove() lives in .exit.text. For drivers registered via - * platform_driver_probe() this is ok because they cannot get unbound at - * runtime. So mark the driver struct with __refdata to prevent modpost - * triggering a section mismatch warning. - */ -static struct faux_device_ops einj_device_ops __refdata = { +static struct faux_device_ops einj_device_ops = { .probe = einj_probe, - .remove = __exit_p(einj_remove), + .remove = einj_remove, }; static int __init einj_init(void) diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c index 75c7db8b156a..7855bbf752b1 100644 --- a/drivers/acpi/ec.c +++ b/drivers/acpi/ec.c @@ -2033,7 +2033,7 @@ void __init acpi_ec_ecdt_probe(void) goto out; } - if (!strstarts(ecdt_ptr->id, "\\")) { + if (!strlen(ecdt_ptr->id)) { /* * The ECDT table on some MSI notebooks contains invalid data, together * with an empty ID string (""). @@ -2042,9 +2042,13 @@ void __init acpi_ec_ecdt_probe(void) * a "fully qualified reference to the (...) embedded controller device", * so this string always has to start with a backslash. * - * By verifying this we can avoid such faulty ECDT tables in a safe way. + * However some ThinkBook machines have a ECDT table with a valid EC + * description but an invalid ID string ("_SB.PC00.LPCB.EC0"). + * + * Because of this we only check if the ID string is empty in order to + * avoid the obvious cases. */ - pr_err(FW_BUG "Ignoring ECDT due to invalid ID string \"%s\"\n", ecdt_ptr->id); + pr_err(FW_BUG "Ignoring ECDT due to empty ID string\n"); goto out; } diff --git a/drivers/acpi/pfr_update.c b/drivers/acpi/pfr_update.c index 318683744ed1..11b1c2828005 100644 --- a/drivers/acpi/pfr_update.c +++ b/drivers/acpi/pfr_update.c @@ -329,7 +329,7 @@ static bool applicable_image(const void *data, struct pfru_update_cap_info *cap, if (type == PFRU_CODE_INJECT_TYPE) return payload_hdr->rt_ver >= cap->code_rt_version; - return payload_hdr->rt_ver >= cap->drv_rt_version; + return payload_hdr->svn_ver >= cap->drv_svn; } static void print_update_debug_info(struct pfru_updated_result *result, diff --git a/drivers/acpi/processor_perflib.c b/drivers/acpi/processor_perflib.c index 755003bf3a45..8972446b7162 100644 --- a/drivers/acpi/processor_perflib.c +++ b/drivers/acpi/processor_perflib.c @@ -180,7 +180,7 @@ void acpi_processor_ppc_init(struct cpufreq_policy *policy) struct acpi_processor *pr = per_cpu(processors, cpu); int ret; - if (!pr || !pr->performance) + if (!pr) continue; /* @@ -197,6 +197,9 @@ void acpi_processor_ppc_init(struct cpufreq_policy *policy) pr_err("Failed to add freq constraint for CPU%d (%d)\n", cpu, ret); + if (!pr->performance) + continue; + ret = acpi_processor_get_platform_limit(pr); if (ret) pr_err("Failed to update freq constraint for CPU%d (%d)\n", diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c index 2946ae6d4b2c..2586e77ebf45 100644 --- a/drivers/ata/libata-eh.c +++ b/drivers/ata/libata-eh.c @@ -2075,7 +2075,7 @@ out: * Check if a link is established. This is a relaxed version of * ata_phys_link_online() which accounts for the fact that this is potentially * called after changing the link power management policy, which may not be - * reflected immediately in the SSTAUS register (e.g., we may still be seeing + * reflected immediately in the SStatus register (e.g., we may still be seeing * the PHY in partial, slumber or devsleep Partial power management state. * So check that: * - A device is still present, that is, DET is 1h (Device presence detected @@ -2089,8 +2089,13 @@ static bool ata_eh_link_established(struct ata_link *link) u32 sstatus; u8 det, ipm; + /* + * For old IDE/PATA adapters that do not have a valid scr_read method, + * or if reading the SStatus register fails, assume that the device is + * present. Device probe will determine if that is really the case. + */ if (sata_scr_read(link, SCR_STATUS, &sstatus)) - return false; + return true; det = sstatus & 0x0f; ipm = (sstatus >> 8) & 0x0f; diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index 57f674f51b0c..2ded5e476d6e 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -3904,21 +3904,16 @@ static int ata_mselect_control_ata_feature(struct ata_queued_cmd *qc, /* Check cdl_ctrl */ switch (buf[0] & 0x03) { case 0: - /* Disable CDL if it is enabled */ - if (!(dev->flags & ATA_DFLAG_CDL_ENABLED)) - return 0; + /* Disable CDL */ ata_dev_dbg(dev, "Disabling CDL\n"); cdl_action = 0; dev->flags &= ~ATA_DFLAG_CDL_ENABLED; break; case 0x02: /* - * Enable CDL if not already enabled. Since this is mutually - * exclusive with NCQ priority, allow this only if NCQ priority - * is disabled. + * Enable CDL. Since CDL is mutually exclusive with NCQ + * priority, allow this only if NCQ priority is disabled. */ - if (dev->flags & ATA_DFLAG_CDL_ENABLED) - return 0; if (dev->flags & ATA_DFLAG_NCQ_PRIO_ENABLED) { ata_dev_err(dev, "NCQ priority must be disabled to enable CDL\n"); diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h index e21492981f7d..f6d6276974ee 100644 --- a/drivers/block/drbd/drbd_int.h +++ b/drivers/block/drbd/drbd_int.h @@ -380,6 +380,9 @@ enum { /* this is/was a write request */ __EE_WRITE, + /* hand back using mempool_free(e, drbd_buffer_page_pool) */ + __EE_RELEASE_TO_MEMPOOL, + /* this is/was a write same request */ __EE_WRITE_SAME, @@ -402,6 +405,7 @@ enum { #define EE_IN_INTERVAL_TREE (1<<__EE_IN_INTERVAL_TREE) #define EE_SUBMITTED (1<<__EE_SUBMITTED) #define EE_WRITE (1<<__EE_WRITE) +#define EE_RELEASE_TO_MEMPOOL (1<<__EE_RELEASE_TO_MEMPOOL) #define EE_WRITE_SAME (1<<__EE_WRITE_SAME) #define EE_APPLICATION (1<<__EE_APPLICATION) #define EE_RS_THIN_REQ (1<<__EE_RS_THIN_REQ) @@ -858,7 +862,6 @@ struct drbd_device { struct list_head sync_ee; /* IO in progress (P_RS_DATA_REPLY gets written to disk) */ struct list_head done_ee; /* need to send P_WRITE_ACK */ struct list_head read_ee; /* [RS]P_DATA_REQUEST being read */ - struct list_head net_ee; /* zero-copy network send in progress */ struct list_head resync_reads; atomic_t pp_in_use; /* allocated from page pool */ @@ -1329,24 +1332,6 @@ extern struct kmem_cache *drbd_al_ext_cache; /* activity log extents */ extern mempool_t drbd_request_mempool; extern mempool_t drbd_ee_mempool; -/* drbd's page pool, used to buffer data received from the peer, - * or data requested by the peer. - * - * This does not have an emergency reserve. - * - * When allocating from this pool, it first takes pages from the pool. - * Only if the pool is depleted will try to allocate from the system. - * - * The assumption is that pages taken from this pool will be processed, - * and given back, "quickly", and then can be recycled, so we can avoid - * frequent calls to alloc_page(), and still will be able to make progress even - * under memory pressure. - */ -extern struct page *drbd_pp_pool; -extern spinlock_t drbd_pp_lock; -extern int drbd_pp_vacant; -extern wait_queue_head_t drbd_pp_wait; - /* We also need a standard (emergency-reserve backed) page pool * for meta data IO (activity log, bitmap). * We can keep it global, as long as it is used as "N pages at a time". @@ -1354,6 +1339,7 @@ extern wait_queue_head_t drbd_pp_wait; */ #define DRBD_MIN_POOL_PAGES 128 extern mempool_t drbd_md_io_page_pool; +extern mempool_t drbd_buffer_page_pool; /* We also need to make sure we get a bio * when we need it for housekeeping purposes */ @@ -1488,10 +1474,7 @@ extern struct drbd_peer_request *drbd_alloc_peer_req(struct drbd_peer_device *, sector_t, unsigned int, unsigned int, gfp_t) __must_hold(local); -extern void __drbd_free_peer_req(struct drbd_device *, struct drbd_peer_request *, - int); -#define drbd_free_peer_req(m,e) __drbd_free_peer_req(m, e, 0) -#define drbd_free_net_peer_req(m,e) __drbd_free_peer_req(m, e, 1) +extern void drbd_free_peer_req(struct drbd_device *device, struct drbd_peer_request *req); extern struct page *drbd_alloc_pages(struct drbd_peer_device *, unsigned int, bool); extern void _drbd_clear_done_ee(struct drbd_device *device, struct list_head *to_be_freed); extern int drbd_connected(struct drbd_peer_device *); @@ -1610,16 +1593,6 @@ static inline struct page *page_chain_next(struct page *page) for (; page && ({ n = page_chain_next(page); 1; }); page = n) -static inline int drbd_peer_req_has_active_page(struct drbd_peer_request *peer_req) -{ - struct page *page = peer_req->pages; - page_chain_for_each(page) { - if (page_count(page) > 1) - return 1; - } - return 0; -} - static inline union drbd_state drbd_read_state(struct drbd_device *device) { struct drbd_resource *resource = device->resource; diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c index 52724b79be30..c73376886e7a 100644 --- a/drivers/block/drbd/drbd_main.c +++ b/drivers/block/drbd/drbd_main.c @@ -114,20 +114,10 @@ struct kmem_cache *drbd_al_ext_cache; /* activity log extents */ mempool_t drbd_request_mempool; mempool_t drbd_ee_mempool; mempool_t drbd_md_io_page_pool; +mempool_t drbd_buffer_page_pool; struct bio_set drbd_md_io_bio_set; struct bio_set drbd_io_bio_set; -/* I do not use a standard mempool, because: - 1) I want to hand out the pre-allocated objects first. - 2) I want to be able to interrupt sleeping allocation with a signal. - Note: This is a single linked list, the next pointer is the private - member of struct page. - */ -struct page *drbd_pp_pool; -DEFINE_SPINLOCK(drbd_pp_lock); -int drbd_pp_vacant; -wait_queue_head_t drbd_pp_wait; - DEFINE_RATELIMIT_STATE(drbd_ratelimit_state, 5 * HZ, 5); static const struct block_device_operations drbd_ops = { @@ -1611,6 +1601,7 @@ static int _drbd_send_zc_bio(struct drbd_peer_device *peer_device, struct bio *b static int _drbd_send_zc_ee(struct drbd_peer_device *peer_device, struct drbd_peer_request *peer_req) { + bool use_sendpage = !(peer_req->flags & EE_RELEASE_TO_MEMPOOL); struct page *page = peer_req->pages; unsigned len = peer_req->i.size; int err; @@ -1619,8 +1610,13 @@ static int _drbd_send_zc_ee(struct drbd_peer_device *peer_device, page_chain_for_each(page) { unsigned l = min_t(unsigned, len, PAGE_SIZE); - err = _drbd_send_page(peer_device, page, 0, l, - page_chain_next(page) ? MSG_MORE : 0); + if (likely(use_sendpage)) + err = _drbd_send_page(peer_device, page, 0, l, + page_chain_next(page) ? MSG_MORE : 0); + else + err = _drbd_no_send_page(peer_device, page, 0, l, + page_chain_next(page) ? MSG_MORE : 0); + if (err) return err; len -= l; @@ -1962,7 +1958,6 @@ void drbd_init_set_defaults(struct drbd_device *device) INIT_LIST_HEAD(&device->sync_ee); INIT_LIST_HEAD(&device->done_ee); INIT_LIST_HEAD(&device->read_ee); - INIT_LIST_HEAD(&device->net_ee); INIT_LIST_HEAD(&device->resync_reads); INIT_LIST_HEAD(&device->resync_work.list); INIT_LIST_HEAD(&device->unplug_work.list); @@ -2043,7 +2038,6 @@ void drbd_device_cleanup(struct drbd_device *device) D_ASSERT(device, list_empty(&device->sync_ee)); D_ASSERT(device, list_empty(&device->done_ee)); D_ASSERT(device, list_empty(&device->read_ee)); - D_ASSERT(device, list_empty(&device->net_ee)); D_ASSERT(device, list_empty(&device->resync_reads)); D_ASSERT(device, list_empty(&first_peer_device(device)->connection->sender_work.q)); D_ASSERT(device, list_empty(&device->resync_work.list)); @@ -2055,19 +2049,11 @@ void drbd_device_cleanup(struct drbd_device *device) static void drbd_destroy_mempools(void) { - struct page *page; - - while (drbd_pp_pool) { - page = drbd_pp_pool; - drbd_pp_pool = (struct page *)page_private(page); - __free_page(page); - drbd_pp_vacant--; - } - /* D_ASSERT(device, atomic_read(&drbd_pp_vacant)==0); */ bioset_exit(&drbd_io_bio_set); bioset_exit(&drbd_md_io_bio_set); + mempool_exit(&drbd_buffer_page_pool); mempool_exit(&drbd_md_io_page_pool); mempool_exit(&drbd_ee_mempool); mempool_exit(&drbd_request_mempool); @@ -2086,9 +2072,8 @@ static void drbd_destroy_mempools(void) static int drbd_create_mempools(void) { - struct page *page; const int number = (DRBD_MAX_BIO_SIZE/PAGE_SIZE) * drbd_minor_count; - int i, ret; + int ret; /* caches */ drbd_request_cache = kmem_cache_create( @@ -2125,6 +2110,10 @@ static int drbd_create_mempools(void) if (ret) goto Enomem; + ret = mempool_init_page_pool(&drbd_buffer_page_pool, number, 0); + if (ret) + goto Enomem; + ret = mempool_init_slab_pool(&drbd_request_mempool, number, drbd_request_cache); if (ret) @@ -2134,15 +2123,6 @@ static int drbd_create_mempools(void) if (ret) goto Enomem; - for (i = 0; i < number; i++) { - page = alloc_page(GFP_HIGHUSER); - if (!page) - goto Enomem; - set_page_private(page, (unsigned long)drbd_pp_pool); - drbd_pp_pool = page; - } - drbd_pp_vacant = number; - return 0; Enomem: @@ -2169,10 +2149,6 @@ static void drbd_release_all_peer_reqs(struct drbd_device *device) rr = drbd_free_peer_reqs(device, &device->done_ee); if (rr) drbd_err(device, "%d EEs in done list found!\n", rr); - - rr = drbd_free_peer_reqs(device, &device->net_ee); - if (rr) - drbd_err(device, "%d EEs in net list found!\n", rr); } /* caution. no locking. */ @@ -2863,11 +2839,6 @@ static int __init drbd_init(void) return err; } - /* - * allocate all necessary structs - */ - init_waitqueue_head(&drbd_pp_wait); - drbd_proc = NULL; /* play safe for drbd_cleanup */ idr_init(&drbd_devices); diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c index 975024cf03c5..caaf2781136d 100644 --- a/drivers/block/drbd/drbd_receiver.c +++ b/drivers/block/drbd/drbd_receiver.c @@ -33,6 +33,7 @@ #include <linux/string.h> #include <linux/scatterlist.h> #include <linux/part_stat.h> +#include <linux/mempool.h> #include "drbd_int.h" #include "drbd_protocol.h" #include "drbd_req.h" @@ -63,182 +64,31 @@ static int e_end_block(struct drbd_work *, int); #define GFP_TRY (__GFP_HIGHMEM | __GFP_NOWARN) -/* - * some helper functions to deal with single linked page lists, - * page->private being our "next" pointer. - */ - -/* If at least n pages are linked at head, get n pages off. - * Otherwise, don't modify head, and return NULL. - * Locking is the responsibility of the caller. - */ -static struct page *page_chain_del(struct page **head, int n) -{ - struct page *page; - struct page *tmp; - - BUG_ON(!n); - BUG_ON(!head); - - page = *head; - - if (!page) - return NULL; - - while (page) { - tmp = page_chain_next(page); - if (--n == 0) - break; /* found sufficient pages */ - if (tmp == NULL) - /* insufficient pages, don't use any of them. */ - return NULL; - page = tmp; - } - - /* add end of list marker for the returned list */ - set_page_private(page, 0); - /* actual return value, and adjustment of head */ - page = *head; - *head = tmp; - return page; -} - -/* may be used outside of locks to find the tail of a (usually short) - * "private" page chain, before adding it back to a global chain head - * with page_chain_add() under a spinlock. */ -static struct page *page_chain_tail(struct page *page, int *len) -{ - struct page *tmp; - int i = 1; - while ((tmp = page_chain_next(page))) { - ++i; - page = tmp; - } - if (len) - *len = i; - return page; -} - -static int page_chain_free(struct page *page) -{ - struct page *tmp; - int i = 0; - page_chain_for_each_safe(page, tmp) { - put_page(page); - ++i; - } - return i; -} - -static void page_chain_add(struct page **head, - struct page *chain_first, struct page *chain_last) -{ -#if 1 - struct page *tmp; - tmp = page_chain_tail(chain_first, NULL); - BUG_ON(tmp != chain_last); -#endif - - /* add chain to head */ - set_page_private(chain_last, (unsigned long)*head); - *head = chain_first; -} - -static struct page *__drbd_alloc_pages(struct drbd_device *device, - unsigned int number) +static struct page *__drbd_alloc_pages(unsigned int number) { struct page *page = NULL; struct page *tmp = NULL; unsigned int i = 0; - /* Yes, testing drbd_pp_vacant outside the lock is racy. - * So what. It saves a spin_lock. */ - if (drbd_pp_vacant >= number) { - spin_lock(&drbd_pp_lock); - page = page_chain_del(&drbd_pp_pool, number); - if (page) - drbd_pp_vacant -= number; - spin_unlock(&drbd_pp_lock); - if (page) - return page; - } - /* GFP_TRY, because we must not cause arbitrary write-out: in a DRBD * "criss-cross" setup, that might cause write-out on some other DRBD, * which in turn might block on the other node at this very place. */ for (i = 0; i < number; i++) { - tmp = alloc_page(GFP_TRY); + tmp = mempool_alloc(&drbd_buffer_page_pool, GFP_TRY); if (!tmp) - break; + goto fail; set_page_private(tmp, (unsigned long)page); page = tmp; } - - if (i == number) - return page; - - /* Not enough pages immediately available this time. - * No need to jump around here, drbd_alloc_pages will retry this - * function "soon". */ - if (page) { - tmp = page_chain_tail(page, NULL); - spin_lock(&drbd_pp_lock); - page_chain_add(&drbd_pp_pool, page, tmp); - drbd_pp_vacant += i; - spin_unlock(&drbd_pp_lock); + return page; +fail: + page_chain_for_each_safe(page, tmp) { + set_page_private(page, 0); + mempool_free(page, &drbd_buffer_page_pool); } return NULL; } -static void reclaim_finished_net_peer_reqs(struct drbd_device *device, - struct list_head *to_be_freed) -{ - struct drbd_peer_request *peer_req, *tmp; - - /* The EEs are always appended to the end of the list. Since - they are sent in order over the wire, they have to finish - in order. As soon as we see the first not finished we can - stop to examine the list... */ - - list_for_each_entry_safe(peer_req, tmp, &device->net_ee, w.list) { - if (drbd_peer_req_has_active_page(peer_req)) - break; - list_move(&peer_req->w.list, to_be_freed); - } -} - -static void drbd_reclaim_net_peer_reqs(struct drbd_device *device) -{ - LIST_HEAD(reclaimed); - struct drbd_peer_request *peer_req, *t; - - spin_lock_irq(&device->resource->req_lock); - reclaim_finished_net_peer_reqs(device, &reclaimed); - spin_unlock_irq(&device->resource->req_lock); - list_for_each_entry_safe(peer_req, t, &reclaimed, w.list) - drbd_free_net_peer_req(device, peer_req); -} - -static void conn_reclaim_net_peer_reqs(struct drbd_connection *connection) -{ - struct drbd_peer_device *peer_device; - int vnr; - - rcu_read_lock(); - idr_for_each_entry(&connection->peer_devices, peer_device, vnr) { - struct drbd_device *device = peer_device->device; - if (!atomic_read(&device->pp_in_use_by_net)) - continue; - - kref_get(&device->kref); - rcu_read_unlock(); - drbd_reclaim_net_peer_reqs(device); - kref_put(&device->kref, drbd_destroy_device); - rcu_read_lock(); - } - rcu_read_unlock(); -} - /** * drbd_alloc_pages() - Returns @number pages, retries forever (or until signalled) * @peer_device: DRBD device. @@ -263,9 +113,8 @@ struct page *drbd_alloc_pages(struct drbd_peer_device *peer_device, unsigned int bool retry) { struct drbd_device *device = peer_device->device; - struct page *page = NULL; + struct page *page; struct net_conf *nc; - DEFINE_WAIT(wait); unsigned int mxb; rcu_read_lock(); @@ -273,37 +122,9 @@ struct page *drbd_alloc_pages(struct drbd_peer_device *peer_device, unsigned int mxb = nc ? nc->max_buffers : 1000000; rcu_read_unlock(); - if (atomic_read(&device->pp_in_use) < mxb) - page = __drbd_alloc_pages(device, number); - - /* Try to keep the fast path fast, but occasionally we need - * to reclaim the pages we lended to the network stack. */ - if (page && atomic_read(&device->pp_in_use_by_net) > 512) - drbd_reclaim_net_peer_reqs(device); - - while (page == NULL) { - prepare_to_wait(&drbd_pp_wait, &wait, TASK_INTERRUPTIBLE); - - drbd_reclaim_net_peer_reqs(device); - - if (atomic_read(&device->pp_in_use) < mxb) { - page = __drbd_alloc_pages(device, number); - if (page) - break; - } - - if (!retry) - break; - - if (signal_pending(current)) { - drbd_warn(device, "drbd_alloc_pages interrupted!\n"); - break; - } - - if (schedule_timeout(HZ/10) == 0) - mxb = UINT_MAX; - } - finish_wait(&drbd_pp_wait, &wait); + if (atomic_read(&device->pp_in_use) >= mxb) + schedule_timeout_interruptible(HZ / 10); + page = __drbd_alloc_pages(number); if (page) atomic_add(number, &device->pp_in_use); @@ -314,29 +135,25 @@ struct page *drbd_alloc_pages(struct drbd_peer_device *peer_device, unsigned int * Is also used from inside an other spin_lock_irq(&resource->req_lock); * Either links the page chain back to the global pool, * or returns all pages to the system. */ -static void drbd_free_pages(struct drbd_device *device, struct page *page, int is_net) +static void drbd_free_pages(struct drbd_device *device, struct page *page) { - atomic_t *a = is_net ? &device->pp_in_use_by_net : &device->pp_in_use; - int i; + struct page *tmp; + int i = 0; if (page == NULL) return; - if (drbd_pp_vacant > (DRBD_MAX_BIO_SIZE/PAGE_SIZE) * drbd_minor_count) - i = page_chain_free(page); - else { - struct page *tmp; - tmp = page_chain_tail(page, &i); - spin_lock(&drbd_pp_lock); - page_chain_add(&drbd_pp_pool, page, tmp); - drbd_pp_vacant += i; - spin_unlock(&drbd_pp_lock); - } - i = atomic_sub_return(i, a); + page_chain_for_each_safe(page, tmp) { + set_page_private(page, 0); + if (page_count(page) == 1) + mempool_free(page, &drbd_buffer_page_pool); + else + put_page(page); + i++; + } + i = atomic_sub_return(i, &device->pp_in_use); if (i < 0) - drbd_warn(device, "ASSERTION FAILED: %s: %d < 0\n", - is_net ? "pp_in_use_by_net" : "pp_in_use", i); - wake_up(&drbd_pp_wait); + drbd_warn(device, "ASSERTION FAILED: pp_in_use: %d < 0\n", i); } /* @@ -380,6 +197,8 @@ drbd_alloc_peer_req(struct drbd_peer_device *peer_device, u64 id, sector_t secto gfpflags_allow_blocking(gfp_mask)); if (!page) goto fail; + if (!mempool_is_saturated(&drbd_buffer_page_pool)) + peer_req->flags |= EE_RELEASE_TO_MEMPOOL; } memset(peer_req, 0, sizeof(*peer_req)); @@ -403,13 +222,12 @@ drbd_alloc_peer_req(struct drbd_peer_device *peer_device, u64 id, sector_t secto return NULL; } -void __drbd_free_peer_req(struct drbd_device *device, struct drbd_peer_request *peer_req, - int is_net) +void drbd_free_peer_req(struct drbd_device *device, struct drbd_peer_request *peer_req) { might_sleep(); if (peer_req->flags & EE_HAS_DIGEST) kfree(peer_req->digest); - drbd_free_pages(device, peer_req->pages, is_net); + drbd_free_pages(device, peer_req->pages); D_ASSERT(device, atomic_read(&peer_req->pending_bios) == 0); D_ASSERT(device, drbd_interval_empty(&peer_req->i)); if (!expect(device, !(peer_req->flags & EE_CALL_AL_COMPLETE_IO))) { @@ -424,14 +242,13 @@ int drbd_free_peer_reqs(struct drbd_device *device, struct list_head *list) LIST_HEAD(work_list); struct drbd_peer_request *peer_req, *t; int count = 0; - int is_net = list == &device->net_ee; spin_lock_irq(&device->resource->req_lock); list_splice_init(list, &work_list); spin_unlock_irq(&device->resource->req_lock); list_for_each_entry_safe(peer_req, t, &work_list, w.list) { - __drbd_free_peer_req(device, peer_req, is_net); + drbd_free_peer_req(device, peer_req); count++; } return count; @@ -443,18 +260,13 @@ int drbd_free_peer_reqs(struct drbd_device *device, struct list_head *list) static int drbd_finish_peer_reqs(struct drbd_device *device) { LIST_HEAD(work_list); - LIST_HEAD(reclaimed); struct drbd_peer_request *peer_req, *t; int err = 0; spin_lock_irq(&device->resource->req_lock); - reclaim_finished_net_peer_reqs(device, &reclaimed); list_splice_init(&device->done_ee, &work_list); spin_unlock_irq(&device->resource->req_lock); - list_for_each_entry_safe(peer_req, t, &reclaimed, w.list) - drbd_free_net_peer_req(device, peer_req); - /* possible callbacks here: * e_end_block, and e_end_resync_block, e_send_superseded. * all ignore the last argument. @@ -1975,7 +1787,7 @@ static int drbd_drain_block(struct drbd_peer_device *peer_device, int data_size) data_size -= len; } kunmap(page); - drbd_free_pages(peer_device->device, page, 0); + drbd_free_pages(peer_device->device, page); return err; } @@ -5224,16 +5036,6 @@ static int drbd_disconnected(struct drbd_peer_device *peer_device) put_ldev(device); } - /* tcp_close and release of sendpage pages can be deferred. I don't - * want to use SO_LINGER, because apparently it can be deferred for - * more than 20 seconds (longest time I checked). - * - * Actually we don't care for exactly when the network stack does its - * put_page(), but release our reference on these pages right here. - */ - i = drbd_free_peer_reqs(device, &device->net_ee); - if (i) - drbd_info(device, "net_ee not empty, killed %u entries\n", i); i = atomic_read(&device->pp_in_use_by_net); if (i) drbd_info(device, "pp_in_use_by_net = %d, expected 0\n", i); @@ -5980,8 +5782,6 @@ int drbd_ack_receiver(struct drbd_thread *thi) while (get_t_state(thi) == RUNNING) { drbd_thread_current_set_cpu(thi); - conn_reclaim_net_peer_reqs(connection); - if (test_and_clear_bit(SEND_PING, &connection->flags)) { if (drbd_send_ping(connection)) { drbd_err(connection, "drbd_send_ping has failed\n"); diff --git a/drivers/block/drbd/drbd_worker.c b/drivers/block/drbd/drbd_worker.c index a6ea737b3b71..dea3e79d044f 100644 --- a/drivers/block/drbd/drbd_worker.c +++ b/drivers/block/drbd/drbd_worker.c @@ -1030,22 +1030,6 @@ out: return 1; } -/* helper */ -static void move_to_net_ee_or_free(struct drbd_device *device, struct drbd_peer_request *peer_req) -{ - if (drbd_peer_req_has_active_page(peer_req)) { - /* This might happen if sendpage() has not finished */ - int i = PFN_UP(peer_req->i.size); - atomic_add(i, &device->pp_in_use_by_net); - atomic_sub(i, &device->pp_in_use); - spin_lock_irq(&device->resource->req_lock); - list_add_tail(&peer_req->w.list, &device->net_ee); - spin_unlock_irq(&device->resource->req_lock); - wake_up(&drbd_pp_wait); - } else - drbd_free_peer_req(device, peer_req); -} - /** * w_e_end_data_req() - Worker callback, to send a P_DATA_REPLY packet in response to a P_DATA_REQUEST * @w: work object. @@ -1059,9 +1043,8 @@ int w_e_end_data_req(struct drbd_work *w, int cancel) int err; if (unlikely(cancel)) { - drbd_free_peer_req(device, peer_req); - dec_unacked(device); - return 0; + err = 0; + goto out; } if (likely((peer_req->flags & EE_WAS_ERROR) == 0)) { @@ -1074,12 +1057,12 @@ int w_e_end_data_req(struct drbd_work *w, int cancel) err = drbd_send_ack(peer_device, P_NEG_DREPLY, peer_req); } - dec_unacked(device); - - move_to_net_ee_or_free(device, peer_req); - if (unlikely(err)) drbd_err(device, "drbd_send_block() failed\n"); +out: + dec_unacked(device); + drbd_free_peer_req(device, peer_req); + return err; } @@ -1120,9 +1103,8 @@ int w_e_end_rsdata_req(struct drbd_work *w, int cancel) int err; if (unlikely(cancel)) { - drbd_free_peer_req(device, peer_req); - dec_unacked(device); - return 0; + err = 0; + goto out; } if (get_ldev_if_state(device, D_FAILED)) { @@ -1155,13 +1137,12 @@ int w_e_end_rsdata_req(struct drbd_work *w, int cancel) /* update resync data with failure */ drbd_rs_failed_io(peer_device, peer_req->i.sector, peer_req->i.size); } - - dec_unacked(device); - - move_to_net_ee_or_free(device, peer_req); - if (unlikely(err)) drbd_err(device, "drbd_send_block() failed\n"); +out: + dec_unacked(device); + drbd_free_peer_req(device, peer_req); + return err; } @@ -1176,9 +1157,8 @@ int w_e_end_csum_rs_req(struct drbd_work *w, int cancel) int err, eq = 0; if (unlikely(cancel)) { - drbd_free_peer_req(device, peer_req); - dec_unacked(device); - return 0; + err = 0; + goto out; } if (get_ldev(device)) { @@ -1220,12 +1200,12 @@ int w_e_end_csum_rs_req(struct drbd_work *w, int cancel) if (drbd_ratelimit()) drbd_err(device, "Sending NegDReply. I guess it gets messy.\n"); } - - dec_unacked(device); - move_to_net_ee_or_free(device, peer_req); - if (unlikely(err)) drbd_err(device, "drbd_send_block/ack() failed\n"); +out: + dec_unacked(device); + drbd_free_peer_req(device, peer_req); + return err; } diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c index 6561d2a561fa..99abd67b708b 100644 --- a/drivers/block/ublk_drv.c +++ b/drivers/block/ublk_drv.c @@ -235,7 +235,7 @@ struct ublk_device { struct completion completion; unsigned int nr_queues_ready; - unsigned int nr_privileged_daemon; + bool unprivileged_daemons; struct mutex cancel_mutex; bool canceling; pid_t ublksrv_tgid; @@ -1389,7 +1389,7 @@ static blk_status_t ublk_prep_req(struct ublk_queue *ubq, struct request *rq, { blk_status_t res; - if (unlikely(ubq->fail_io)) + if (unlikely(READ_ONCE(ubq->fail_io))) return BLK_STS_TARGET; /* With recovery feature enabled, force_abort is set in @@ -1401,7 +1401,8 @@ static blk_status_t ublk_prep_req(struct ublk_queue *ubq, struct request *rq, * Note: force_abort is guaranteed to be seen because it is set * before request queue is unqiuesced. */ - if (ublk_nosrv_should_queue_io(ubq) && unlikely(ubq->force_abort)) + if (ublk_nosrv_should_queue_io(ubq) && + unlikely(READ_ONCE(ubq->force_abort))) return BLK_STS_IOERR; if (check_cancel && unlikely(ubq->canceling)) @@ -1550,7 +1551,7 @@ static void ublk_reset_ch_dev(struct ublk_device *ub) /* set to NULL, otherwise new tasks cannot mmap io_cmd_buf */ ub->mm = NULL; ub->nr_queues_ready = 0; - ub->nr_privileged_daemon = 0; + ub->unprivileged_daemons = false; ub->ublksrv_tgid = -1; } @@ -1644,7 +1645,6 @@ static int ublk_ch_release(struct inode *inode, struct file *filp) * Transition the device to the nosrv state. What exactly this * means depends on the recovery flags */ - blk_mq_quiesce_queue(disk->queue); if (ublk_nosrv_should_stop_dev(ub)) { /* * Allow any pending/future I/O to pass through quickly @@ -1652,8 +1652,7 @@ static int ublk_ch_release(struct inode *inode, struct file *filp) * waits for all pending I/O to complete */ for (i = 0; i < ub->dev_info.nr_hw_queues; i++) - ublk_get_queue(ub, i)->force_abort = true; - blk_mq_unquiesce_queue(disk->queue); + WRITE_ONCE(ublk_get_queue(ub, i)->force_abort, true); ublk_stop_dev_unlocked(ub); } else { @@ -1663,9 +1662,8 @@ static int ublk_ch_release(struct inode *inode, struct file *filp) } else { ub->dev_info.state = UBLK_S_DEV_FAIL_IO; for (i = 0; i < ub->dev_info.nr_hw_queues; i++) - ublk_get_queue(ub, i)->fail_io = true; + WRITE_ONCE(ublk_get_queue(ub, i)->fail_io, true); } - blk_mq_unquiesce_queue(disk->queue); } unlock: mutex_unlock(&ub->mutex); @@ -1980,12 +1978,10 @@ static void ublk_mark_io_ready(struct ublk_device *ub, struct ublk_queue *ubq) __must_hold(&ub->mutex) { ubq->nr_io_ready++; - if (ublk_queue_ready(ubq)) { + if (ublk_queue_ready(ubq)) ub->nr_queues_ready++; - - if (capable(CAP_SYS_ADMIN)) - ub->nr_privileged_daemon++; - } + if (!ub->unprivileged_daemons && !capable(CAP_SYS_ADMIN)) + ub->unprivileged_daemons = true; if (ub->nr_queues_ready == ub->dev_info.nr_hw_queues) { /* now we are ready for handling ublk io request */ @@ -2880,8 +2876,8 @@ static int ublk_ctrl_start_dev(struct ublk_device *ub, ublk_apply_params(ub); - /* don't probe partitions if any one ubq daemon is un-trusted */ - if (ub->nr_privileged_daemon != ub->nr_queues_ready) + /* don't probe partitions if any daemon task is un-trusted */ + if (ub->unprivileged_daemons) set_bit(GD_SUPPRESS_PART_SCAN, &disk->state); ublk_get_device(ub); diff --git a/drivers/bluetooth/btmtk.c b/drivers/bluetooth/btmtk.c index 4390fd571dbd..a8c520dc09e1 100644 --- a/drivers/bluetooth/btmtk.c +++ b/drivers/bluetooth/btmtk.c @@ -642,12 +642,7 @@ static int btmtk_usb_hci_wmt_sync(struct hci_dev *hdev, * WMT command. */ err = wait_on_bit_timeout(&data->flags, BTMTK_TX_WAIT_VND_EVT, - TASK_INTERRUPTIBLE, HCI_INIT_TIMEOUT); - if (err == -EINTR) { - bt_dev_err(hdev, "Execution of wmt command interrupted"); - clear_bit(BTMTK_TX_WAIT_VND_EVT, &data->flags); - goto err_free_wc; - } + TASK_UNINTERRUPTIBLE, HCI_INIT_TIMEOUT); if (err) { bt_dev_err(hdev, "Execution of wmt command timed out"); diff --git a/drivers/bluetooth/btnxpuart.c b/drivers/bluetooth/btnxpuart.c index 73a4a325c867..76e7f857fb7d 100644 --- a/drivers/bluetooth/btnxpuart.c +++ b/drivers/bluetooth/btnxpuart.c @@ -543,10 +543,10 @@ static int ps_setup(struct hci_dev *hdev) } if (psdata->wakeup_source) { - ret = devm_request_irq(&serdev->dev, psdata->irq_handler, - ps_host_wakeup_irq_handler, - IRQF_ONESHOT | IRQF_TRIGGER_FALLING, - dev_name(&serdev->dev), nxpdev); + ret = devm_request_threaded_irq(&serdev->dev, psdata->irq_handler, + NULL, ps_host_wakeup_irq_handler, + IRQF_ONESHOT, + dev_name(&serdev->dev), nxpdev); if (ret) bt_dev_info(hdev, "error setting wakeup IRQ handler, ignoring\n"); disable_irq(psdata->irq_handler); diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index 06a1c7dd081f..f366d35c5840 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -2793,6 +2793,7 @@ static const struct x86_cpu_id intel_pstate_cpu_oob_ids[] __initconst = { X86_MATCH(INTEL_GRANITERAPIDS_X, core_funcs), X86_MATCH(INTEL_ATOM_CRESTMONT, core_funcs), X86_MATCH(INTEL_ATOM_CRESTMONT_X, core_funcs), + X86_MATCH(INTEL_ATOM_DARKMONT_X, core_funcs), {} }; #endif diff --git a/drivers/cpuidle/governors/menu.c b/drivers/cpuidle/governors/menu.c index 52d5d26fc7c6..b2e3d0b0a116 100644 --- a/drivers/cpuidle/governors/menu.c +++ b/drivers/cpuidle/governors/menu.c @@ -97,6 +97,14 @@ static inline int which_bucket(u64 duration_ns) static DEFINE_PER_CPU(struct menu_device, menu_devices); +static void menu_update_intervals(struct menu_device *data, unsigned int interval_us) +{ + /* Update the repeating-pattern data. */ + data->intervals[data->interval_ptr++] = interval_us; + if (data->interval_ptr >= INTERVALS) + data->interval_ptr = 0; +} + static void menu_update(struct cpuidle_driver *drv, struct cpuidle_device *dev); /* @@ -222,6 +230,14 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev, if (data->needs_update) { menu_update(drv, dev); data->needs_update = 0; + } else if (!dev->last_residency_ns) { + /* + * This happens when the driver rejects the previously selected + * idle state and returns an error, so update the recent + * intervals table to prevent invalid information from being + * used going forward. + */ + menu_update_intervals(data, UINT_MAX); } /* Find the shortest expected idle interval. */ @@ -271,20 +287,15 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev, return 0; } - if (tick_nohz_tick_stopped()) { - /* - * If the tick is already stopped, the cost of possible short - * idle duration misprediction is much higher, because the CPU - * may be stuck in a shallow idle state for a long time as a - * result of it. In that case say we might mispredict and use - * the known time till the closest timer event for the idle - * state selection. - */ - if (predicted_ns < TICK_NSEC) - predicted_ns = data->next_timer_ns; - } else if (latency_req > predicted_ns) { - latency_req = predicted_ns; - } + /* + * If the tick is already stopped, the cost of possible short idle + * duration misprediction is much higher, because the CPU may be stuck + * in a shallow idle state for a long time as a result of it. In that + * case, say we might mispredict and use the known time till the closest + * timer event for the idle state selection. + */ + if (tick_nohz_tick_stopped() && predicted_ns < TICK_NSEC) + predicted_ns = data->next_timer_ns; /* * Find the idle state with the lowest power while satisfying @@ -300,13 +311,15 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev, if (idx == -1) idx = i; /* first enabled state */ + if (s->exit_latency_ns > latency_req) + break; + if (s->target_residency_ns > predicted_ns) { /* * Use a physical idle state, not busy polling, unless * a timer is going to trigger soon enough. */ if ((drv->states[idx].flags & CPUIDLE_FLAG_POLLING) && - s->exit_latency_ns <= latency_req && s->target_residency_ns <= data->next_timer_ns) { predicted_ns = s->target_residency_ns; idx = i; @@ -338,8 +351,6 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev, return idx; } - if (s->exit_latency_ns > latency_req) - break; idx = i; } @@ -482,10 +493,7 @@ static void menu_update(struct cpuidle_driver *drv, struct cpuidle_device *dev) data->correction_factor[data->bucket] = new_factor; - /* update the repeating-pattern data */ - data->intervals[data->interval_ptr++] = ktime_to_us(measured_ns); - if (data->interval_ptr >= INTERVALS) - data->interval_ptr = 0; + menu_update_intervals(data, ktime_to_us(measured_ns)); } /** diff --git a/drivers/firewire/core-transaction.c b/drivers/firewire/core-transaction.c index d28477d84697..1d1c2d8f85ae 100644 --- a/drivers/firewire/core-transaction.c +++ b/drivers/firewire/core-transaction.c @@ -550,6 +550,23 @@ const struct fw_address_region fw_unit_space_region = { .start = 0xfffff0000900ULL, .end = 0x1000000000000ULL, }; #endif /* 0 */ +static void complete_address_handler(struct kref *kref) +{ + struct fw_address_handler *handler = container_of(kref, struct fw_address_handler, kref); + + complete(&handler->done); +} + +static void get_address_handler(struct fw_address_handler *handler) +{ + kref_get(&handler->kref); +} + +static int put_address_handler(struct fw_address_handler *handler) +{ + return kref_put(&handler->kref, complete_address_handler); +} + /** * fw_core_add_address_handler() - register for incoming requests * @handler: callback @@ -596,6 +613,8 @@ int fw_core_add_address_handler(struct fw_address_handler *handler, if (other != NULL) { handler->offset += other->length; } else { + init_completion(&handler->done); + kref_init(&handler->kref); list_add_tail_rcu(&handler->link, &address_handler_list); ret = 0; break; @@ -621,6 +640,9 @@ void fw_core_remove_address_handler(struct fw_address_handler *handler) list_del_rcu(&handler->link); synchronize_rcu(); + + if (!put_address_handler(handler)) + wait_for_completion(&handler->done); } EXPORT_SYMBOL(fw_core_remove_address_handler); @@ -914,22 +936,31 @@ static void handle_exclusive_region_request(struct fw_card *card, handler = lookup_enclosing_address_handler(&address_handler_list, offset, request->length); if (handler) - handler->address_callback(card, request, tcode, destination, source, - p->generation, offset, request->data, - request->length, handler->callback_data); + get_address_handler(handler); } - if (!handler) + if (!handler) { fw_send_response(card, request, RCODE_ADDRESS_ERROR); + return; + } + + // Outside the RCU read-side critical section. Without spinlock. With reference count. + handler->address_callback(card, request, tcode, destination, source, p->generation, offset, + request->data, request->length, handler->callback_data); + put_address_handler(handler); } +// To use kmalloc allocator efficiently, this should be power of two. +#define BUFFER_ON_KERNEL_STACK_SIZE 4 + static void handle_fcp_region_request(struct fw_card *card, struct fw_packet *p, struct fw_request *request, unsigned long long offset) { - struct fw_address_handler *handler; - int tcode, destination, source; + struct fw_address_handler *buffer_on_kernel_stack[BUFFER_ON_KERNEL_STACK_SIZE]; + struct fw_address_handler *handler, **handlers; + int tcode, destination, source, i, count, buffer_size; if ((offset != (CSR_REGISTER_BASE | CSR_FCP_COMMAND) && offset != (CSR_REGISTER_BASE | CSR_FCP_RESPONSE)) || @@ -950,15 +981,55 @@ static void handle_fcp_region_request(struct fw_card *card, return; } + count = 0; + handlers = buffer_on_kernel_stack; + buffer_size = ARRAY_SIZE(buffer_on_kernel_stack); scoped_guard(rcu) { list_for_each_entry_rcu(handler, &address_handler_list, link) { - if (is_enclosing_handler(handler, offset, request->length)) - handler->address_callback(card, request, tcode, destination, source, - p->generation, offset, request->data, - request->length, handler->callback_data); + if (is_enclosing_handler(handler, offset, request->length)) { + if (count >= buffer_size) { + int next_size = buffer_size * 2; + struct fw_address_handler **buffer_on_kernel_heap; + + if (handlers == buffer_on_kernel_stack) + buffer_on_kernel_heap = NULL; + else + buffer_on_kernel_heap = handlers; + + buffer_on_kernel_heap = + krealloc_array(buffer_on_kernel_heap, next_size, + sizeof(*buffer_on_kernel_heap), GFP_ATOMIC); + // FCP is used for purposes unrelated to significant system + // resources (e.g. storage or networking), so allocation + // failures are not considered so critical. + if (!buffer_on_kernel_heap) + break; + + if (handlers == buffer_on_kernel_stack) { + memcpy(buffer_on_kernel_heap, buffer_on_kernel_stack, + sizeof(buffer_on_kernel_stack)); + } + + handlers = buffer_on_kernel_heap; + buffer_size = next_size; + } + get_address_handler(handler); + handlers[count++] = handler; + } } } + for (i = 0; i < count; ++i) { + handler = handlers[i]; + handler->address_callback(card, request, tcode, destination, source, + p->generation, offset, request->data, + request->length, handler->callback_data); + put_address_handler(handler); + } + + if (handlers != buffer_on_kernel_stack) + kfree(handlers); + fw_send_response(card, request, RCODE_COMPLETE); } diff --git a/drivers/gpio/gpio-mlxbf3.c b/drivers/gpio/gpio-mlxbf3.c index 9875e34bde72..ed29b07d16c1 100644 --- a/drivers/gpio/gpio-mlxbf3.c +++ b/drivers/gpio/gpio-mlxbf3.c @@ -190,9 +190,7 @@ static int mlxbf3_gpio_probe(struct platform_device *pdev) struct mlxbf3_gpio_context *gs; struct gpio_irq_chip *girq; struct gpio_chip *gc; - char *colon_ptr; int ret, irq; - long num; gs = devm_kzalloc(dev, sizeof(*gs), GFP_KERNEL); if (!gs) @@ -229,39 +227,25 @@ static int mlxbf3_gpio_probe(struct platform_device *pdev) gc->owner = THIS_MODULE; gc->add_pin_ranges = mlxbf3_gpio_add_pin_ranges; - colon_ptr = strchr(dev_name(dev), ':'); - if (!colon_ptr) { - dev_err(dev, "invalid device name format\n"); - return -EINVAL; - } - - ret = kstrtol(++colon_ptr, 16, &num); - if (ret) { - dev_err(dev, "invalid device instance\n"); - return ret; - } - - if (!num) { - irq = platform_get_irq(pdev, 0); - if (irq >= 0) { - girq = &gs->gc.irq; - gpio_irq_chip_set_chip(girq, &gpio_mlxbf3_irqchip); - girq->default_type = IRQ_TYPE_NONE; - /* This will let us handle the parent IRQ in the driver */ - girq->num_parents = 0; - girq->parents = NULL; - girq->parent_handler = NULL; - girq->handler = handle_bad_irq; - - /* - * Directly request the irq here instead of passing - * a flow-handler because the irq is shared. - */ - ret = devm_request_irq(dev, irq, mlxbf3_gpio_irq_handler, - IRQF_SHARED, dev_name(dev), gs); - if (ret) - return dev_err_probe(dev, ret, "failed to request IRQ"); - } + irq = platform_get_irq_optional(pdev, 0); + if (irq >= 0) { + girq = &gs->gc.irq; + gpio_irq_chip_set_chip(girq, &gpio_mlxbf3_irqchip); + girq->default_type = IRQ_TYPE_NONE; + /* This will let us handle the parent IRQ in the driver */ + girq->num_parents = 0; + girq->parents = NULL; + girq->parent_handler = NULL; + girq->handler = handle_bad_irq; + + /* + * Directly request the irq here instead of passing + * a flow-handler because the irq is shared. + */ + ret = devm_request_irq(dev, irq, mlxbf3_gpio_irq_handler, + IRQF_SHARED, dev_name(dev), gs); + if (ret) + return dev_err_probe(dev, ret, "failed to request IRQ"); } platform_set_drvdata(pdev, gs); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c index a2adaacf6adb..d3f220be2ef9 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c @@ -1139,6 +1139,9 @@ static int amdgpu_cs_vm_handling(struct amdgpu_cs_parser *p) } } + if (!amdgpu_vm_ready(vm)) + return -EINVAL; + r = amdgpu_vm_clear_freed(adev, vm, NULL); if (r) return r; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_csa.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_csa.c index 02138aa55793..dfb6cfd83760 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_csa.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_csa.c @@ -88,8 +88,8 @@ int amdgpu_map_static_csa(struct amdgpu_device *adev, struct amdgpu_vm *vm, } r = amdgpu_vm_bo_map(adev, *bo_va, csa_addr, 0, size, - AMDGPU_PTE_READABLE | AMDGPU_PTE_WRITEABLE | - AMDGPU_PTE_EXECUTABLE); + AMDGPU_VM_PAGE_READABLE | AMDGPU_VM_PAGE_WRITEABLE | + AMDGPU_VM_PAGE_EXECUTABLE); if (r) { DRM_ERROR("failed to do bo_map on static CSA, err=%d\n", r); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c index 0bd51a04be79..23484317a5fa 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c @@ -1039,15 +1039,28 @@ int psp_update_fw_reservation(struct psp_context *psp) { int ret; uint64_t reserv_addr, reserv_addr_ext; - uint32_t reserv_size, reserv_size_ext; + uint32_t reserv_size, reserv_size_ext, mp0_ip_ver; struct amdgpu_device *adev = psp->adev; + mp0_ip_ver = amdgpu_ip_version(adev, MP0_HWIP, 0); + if (amdgpu_sriov_vf(psp->adev)) return 0; - if ((amdgpu_ip_version(adev, MP0_HWIP, 0) != IP_VERSION(14, 0, 2)) && - (amdgpu_ip_version(adev, MP0_HWIP, 0) != IP_VERSION(14, 0, 3))) + switch (mp0_ip_ver) { + case IP_VERSION(14, 0, 2): + if (adev->psp.sos.fw_version < 0x3b0e0d) + return 0; + break; + + case IP_VERSION(14, 0, 3): + if (adev->psp.sos.fw_version < 0x3a0e14) + return 0; + break; + + default: return 0; + } ret = psp_get_fw_reservation_info(psp, GFX_CMD_ID_FB_FW_RESERV_ADDR, &reserv_addr, &reserv_size); if (ret) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index 5cacf5717016..0b87798daebd 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -654,11 +654,10 @@ int amdgpu_vm_validate(struct amdgpu_device *adev, struct amdgpu_vm *vm, * Check if all VM PDs/PTs are ready for updates * * Returns: - * True if VM is not evicting. + * True if VM is not evicting and all VM entities are not stopped */ bool amdgpu_vm_ready(struct amdgpu_vm *vm) { - bool empty; bool ret; amdgpu_vm_eviction_lock(vm); @@ -666,10 +665,18 @@ bool amdgpu_vm_ready(struct amdgpu_vm *vm) amdgpu_vm_eviction_unlock(vm); spin_lock(&vm->status_lock); - empty = list_empty(&vm->evicted); + ret &= list_empty(&vm->evicted); spin_unlock(&vm->status_lock); - return ret && empty; + spin_lock(&vm->immediate.lock); + ret &= !vm->immediate.stopped; + spin_unlock(&vm->immediate.lock); + + spin_lock(&vm->delayed.lock); + ret &= !vm->delayed.stopped; + spin_unlock(&vm->delayed.lock); + + return ret; } /** diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c index 07c936e90d8e..78f9e86ccc09 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c @@ -648,9 +648,8 @@ static void amdgpu_vram_mgr_del(struct ttm_resource_manager *man, list_for_each_entry(block, &vres->blocks, link) vis_usage += amdgpu_vram_mgr_vis_size(adev, block); - amdgpu_vram_mgr_do_reserve(man); - drm_buddy_free_list(mm, &vres->blocks, vres->flags); + amdgpu_vram_mgr_do_reserve(man); mutex_unlock(&mgr->lock); atomic64_sub(vis_usage, &mgr->vis_usage); diff --git a/drivers/gpu/drm/bridge/aux-bridge.c b/drivers/gpu/drm/bridge/aux-bridge.c index b63304d3a80f..b3e4cdff61d6 100644 --- a/drivers/gpu/drm/bridge/aux-bridge.c +++ b/drivers/gpu/drm/bridge/aux-bridge.c @@ -18,6 +18,7 @@ static void drm_aux_bridge_release(struct device *dev) { struct auxiliary_device *adev = to_auxiliary_dev(dev); + of_node_put(dev->of_node); ida_free(&drm_aux_bridge_ida, adev->id); kfree(adev); @@ -65,6 +66,7 @@ int drm_aux_bridge_register(struct device *parent) ret = auxiliary_device_init(adev); if (ret) { + of_node_put(adev->dev.of_node); ida_free(&drm_aux_bridge_ida, adev->id); kfree(adev); return ret; diff --git a/drivers/gpu/drm/drm_bridge.c b/drivers/gpu/drm/drm_bridge.c index dd45d9b504d8..4bde00083047 100644 --- a/drivers/gpu/drm/drm_bridge.c +++ b/drivers/gpu/drm/drm_bridge.c @@ -1227,6 +1227,7 @@ EXPORT_SYMBOL(drm_atomic_bridge_chain_check); /** * drm_bridge_detect - check if anything is attached to the bridge output * @bridge: bridge control structure + * @connector: attached connector * * If the bridge supports output detection, as reported by the * DRM_BRIDGE_OP_DETECT bridge ops flag, call &drm_bridge_funcs.detect for the diff --git a/drivers/gpu/drm/i915/display/intel_fbc.c b/drivers/gpu/drm/i915/display/intel_fbc.c index 6e26cb4c5724..685ac98bd001 100644 --- a/drivers/gpu/drm/i915/display/intel_fbc.c +++ b/drivers/gpu/drm/i915/display/intel_fbc.c @@ -552,10 +552,6 @@ static void ilk_fbc_deactivate(struct intel_fbc *fbc) if (dpfc_ctl & DPFC_CTL_EN) { dpfc_ctl &= ~DPFC_CTL_EN; intel_de_write(display, ILK_DPFC_CONTROL(fbc->id), dpfc_ctl); - - /* wa_18038517565 Enable DPFC clock gating after FBC disable */ - if (display->platform.dg2 || DISPLAY_VER(display) >= 14) - fbc_compressor_clkgate_disable_wa(fbc, false); } } @@ -1710,6 +1706,10 @@ static void __intel_fbc_disable(struct intel_fbc *fbc) __intel_fbc_cleanup_cfb(fbc); + /* wa_18038517565 Enable DPFC clock gating after FBC disable */ + if (display->platform.dg2 || DISPLAY_VER(display) >= 14) + fbc_compressor_clkgate_disable_wa(fbc, false); + fbc->state.plane = NULL; fbc->flip_pending = false; fbc->busy_bits = 0; diff --git a/drivers/gpu/drm/i915/display/intel_psr.c b/drivers/gpu/drm/i915/display/intel_psr.c index ae9053919211..41988e193a41 100644 --- a/drivers/gpu/drm/i915/display/intel_psr.c +++ b/drivers/gpu/drm/i915/display/intel_psr.c @@ -3275,7 +3275,9 @@ static void intel_psr_configure_full_frame_update(struct intel_dp *intel_dp) static void _psr_invalidate_handle(struct intel_dp *intel_dp) { - if (intel_dp->psr.psr2_sel_fetch_enabled) { + struct intel_display *display = to_intel_display(intel_dp); + + if (DISPLAY_VER(display) < 20 && intel_dp->psr.psr2_sel_fetch_enabled) { if (!intel_dp->psr.psr2_sel_fetch_cff_enabled) { intel_dp->psr.psr2_sel_fetch_cff_enabled = true; intel_psr_configure_full_frame_update(intel_dp); @@ -3361,7 +3363,7 @@ static void _psr_flush_handle(struct intel_dp *intel_dp) { struct intel_display *display = to_intel_display(intel_dp); - if (intel_dp->psr.psr2_sel_fetch_enabled) { + if (DISPLAY_VER(display) < 20 && intel_dp->psr.psr2_sel_fetch_enabled) { if (intel_dp->psr.psr2_sel_fetch_cff_enabled) { /* can we turn CFF off? */ if (intel_dp->psr.busy_frontbuffer_bits == 0) @@ -3378,11 +3380,13 @@ static void _psr_flush_handle(struct intel_dp *intel_dp) * existing SU configuration */ intel_psr_configure_full_frame_update(intel_dp); - } - intel_psr_force_update(intel_dp); + intel_psr_force_update(intel_dp); + } else { + intel_psr_exit(intel_dp); + } - if (!intel_dp->psr.psr2_sel_fetch_enabled && !intel_dp->psr.active && + if ((!intel_dp->psr.psr2_sel_fetch_enabled || DISPLAY_VER(display) >= 20) && !intel_dp->psr.busy_frontbuffer_bits) queue_work(display->wq.unordered, &intel_dp->psr.work); } diff --git a/drivers/gpu/drm/nouveau/nouveau_display.c b/drivers/gpu/drm/nouveau/nouveau_display.c index e1e542126310..805d0a87aa54 100644 --- a/drivers/gpu/drm/nouveau/nouveau_display.c +++ b/drivers/gpu/drm/nouveau/nouveau_display.c @@ -253,6 +253,7 @@ nouveau_check_bl_size(struct nouveau_drm *drm, struct nouveau_bo *nvbo, int nouveau_framebuffer_new(struct drm_device *dev, + const struct drm_format_info *info, const struct drm_mode_fb_cmd2 *mode_cmd, struct drm_gem_object *gem, struct drm_framebuffer **pfb) @@ -260,7 +261,6 @@ nouveau_framebuffer_new(struct drm_device *dev, struct nouveau_drm *drm = nouveau_drm(dev); struct nouveau_bo *nvbo = nouveau_gem_object(gem); struct drm_framebuffer *fb; - const struct drm_format_info *info; unsigned int height, i; uint32_t tile_mode; uint8_t kind; @@ -295,9 +295,6 @@ nouveau_framebuffer_new(struct drm_device *dev, kind = nvbo->kind; } - info = drm_get_format_info(dev, mode_cmd->pixel_format, - mode_cmd->modifier[0]); - for (i = 0; i < info->num_planes; i++) { height = drm_format_info_plane_height(info, mode_cmd->height, @@ -321,7 +318,7 @@ nouveau_framebuffer_new(struct drm_device *dev, if (!(fb = *pfb = kzalloc(sizeof(*fb), GFP_KERNEL))) return -ENOMEM; - drm_helper_mode_fill_fb_struct(dev, fb, NULL, mode_cmd); + drm_helper_mode_fill_fb_struct(dev, fb, info, mode_cmd); fb->obj[0] = gem; ret = drm_framebuffer_init(dev, fb, &nouveau_framebuffer_funcs); @@ -344,7 +341,7 @@ nouveau_user_framebuffer_create(struct drm_device *dev, if (!gem) return ERR_PTR(-ENOENT); - ret = nouveau_framebuffer_new(dev, mode_cmd, gem, &fb); + ret = nouveau_framebuffer_new(dev, info, mode_cmd, gem, &fb); if (ret == 0) return fb; diff --git a/drivers/gpu/drm/nouveau/nouveau_display.h b/drivers/gpu/drm/nouveau/nouveau_display.h index e45f211501f6..470e0910d484 100644 --- a/drivers/gpu/drm/nouveau/nouveau_display.h +++ b/drivers/gpu/drm/nouveau/nouveau_display.h @@ -8,8 +8,11 @@ #include <drm/drm_framebuffer.h> +struct drm_format_info; + int nouveau_framebuffer_new(struct drm_device *dev, + const struct drm_format_info *info, const struct drm_mode_fb_cmd2 *mode_cmd, struct drm_gem_object *gem, struct drm_framebuffer **pfb); diff --git a/drivers/gpu/drm/omapdrm/omap_fb.c b/drivers/gpu/drm/omapdrm/omap_fb.c index 30c81e2e5d6b..bb3105556f19 100644 --- a/drivers/gpu/drm/omapdrm/omap_fb.c +++ b/drivers/gpu/drm/omapdrm/omap_fb.c @@ -351,7 +351,7 @@ struct drm_framebuffer *omap_framebuffer_create(struct drm_device *dev, } } - fb = omap_framebuffer_init(dev, mode_cmd, bos); + fb = omap_framebuffer_init(dev, info, mode_cmd, bos); if (IS_ERR(fb)) goto error; @@ -365,9 +365,9 @@ error: } struct drm_framebuffer *omap_framebuffer_init(struct drm_device *dev, + const struct drm_format_info *info, const struct drm_mode_fb_cmd2 *mode_cmd, struct drm_gem_object **bos) { - const struct drm_format_info *format = NULL; struct omap_framebuffer *omap_fb = NULL; struct drm_framebuffer *fb = NULL; unsigned int pitch = mode_cmd->pitches[0]; @@ -377,15 +377,12 @@ struct drm_framebuffer *omap_framebuffer_init(struct drm_device *dev, dev, mode_cmd, mode_cmd->width, mode_cmd->height, (char *)&mode_cmd->pixel_format); - format = drm_get_format_info(dev, mode_cmd->pixel_format, - mode_cmd->modifier[0]); - for (i = 0; i < ARRAY_SIZE(formats); i++) { if (formats[i] == mode_cmd->pixel_format) break; } - if (!format || i == ARRAY_SIZE(formats)) { + if (i == ARRAY_SIZE(formats)) { dev_dbg(dev->dev, "unsupported pixel format: %4.4s\n", (char *)&mode_cmd->pixel_format); ret = -EINVAL; @@ -399,7 +396,7 @@ struct drm_framebuffer *omap_framebuffer_init(struct drm_device *dev, } fb = &omap_fb->base; - omap_fb->format = format; + omap_fb->format = info; mutex_init(&omap_fb->lock); /* @@ -407,23 +404,23 @@ struct drm_framebuffer *omap_framebuffer_init(struct drm_device *dev, * that the two planes of multiplane formats need the same number of * bytes per pixel. */ - if (format->num_planes == 2 && pitch != mode_cmd->pitches[1]) { + if (info->num_planes == 2 && pitch != mode_cmd->pitches[1]) { dev_dbg(dev->dev, "pitches differ between planes 0 and 1\n"); ret = -EINVAL; goto fail; } - if (pitch % format->cpp[0]) { + if (pitch % info->cpp[0]) { dev_dbg(dev->dev, "buffer pitch (%u bytes) is not a multiple of pixel size (%u bytes)\n", - pitch, format->cpp[0]); + pitch, info->cpp[0]); ret = -EINVAL; goto fail; } - for (i = 0; i < format->num_planes; i++) { + for (i = 0; i < info->num_planes; i++) { struct plane *plane = &omap_fb->planes[i]; - unsigned int vsub = i == 0 ? 1 : format->vsub; + unsigned int vsub = i == 0 ? 1 : info->vsub; unsigned int size; size = pitch * mode_cmd->height / vsub; @@ -440,7 +437,7 @@ struct drm_framebuffer *omap_framebuffer_init(struct drm_device *dev, plane->dma_addr = 0; } - drm_helper_mode_fill_fb_struct(dev, fb, NULL, mode_cmd); + drm_helper_mode_fill_fb_struct(dev, fb, info, mode_cmd); ret = drm_framebuffer_init(dev, fb, &omap_framebuffer_funcs); if (ret) { diff --git a/drivers/gpu/drm/omapdrm/omap_fb.h b/drivers/gpu/drm/omapdrm/omap_fb.h index 0873f953cf1d..e6010302a22b 100644 --- a/drivers/gpu/drm/omapdrm/omap_fb.h +++ b/drivers/gpu/drm/omapdrm/omap_fb.h @@ -13,6 +13,7 @@ struct drm_connector; struct drm_device; struct drm_file; struct drm_framebuffer; +struct drm_format_info; struct drm_gem_object; struct drm_mode_fb_cmd2; struct drm_plane_state; @@ -23,6 +24,7 @@ struct drm_framebuffer *omap_framebuffer_create(struct drm_device *dev, struct drm_file *file, const struct drm_format_info *info, const struct drm_mode_fb_cmd2 *mode_cmd); struct drm_framebuffer *omap_framebuffer_init(struct drm_device *dev, + const struct drm_format_info *info, const struct drm_mode_fb_cmd2 *mode_cmd, struct drm_gem_object **bos); int omap_framebuffer_pin(struct drm_framebuffer *fb); void omap_framebuffer_unpin(struct drm_framebuffer *fb); diff --git a/drivers/gpu/drm/omapdrm/omap_fbdev.c b/drivers/gpu/drm/omapdrm/omap_fbdev.c index 7b6396890681..948af7ec1130 100644 --- a/drivers/gpu/drm/omapdrm/omap_fbdev.c +++ b/drivers/gpu/drm/omapdrm/omap_fbdev.c @@ -197,7 +197,10 @@ int omap_fbdev_driver_fbdev_probe(struct drm_fb_helper *helper, goto fail; } - fb = omap_framebuffer_init(dev, &mode_cmd, &bo); + fb = omap_framebuffer_init(dev, + drm_get_format_info(dev, mode_cmd.pixel_format, + mode_cmd.modifier[0]), + &mode_cmd, &bo); if (IS_ERR(fb)) { dev_err(dev->dev, "failed to allocate fb\n"); /* note: if fb creation failed, we can't rely on fb destroy diff --git a/drivers/gpu/drm/panfrost/panfrost_gem.c b/drivers/gpu/drm/panfrost/panfrost_gem.c index bb73f2a68a12..85d6289a6eda 100644 --- a/drivers/gpu/drm/panfrost/panfrost_gem.c +++ b/drivers/gpu/drm/panfrost/panfrost_gem.c @@ -432,7 +432,7 @@ static void panfrost_gem_debugfs_bo_print(struct panfrost_gem_object *bo, if (!refcount) return; - resident_size = bo->base.pages ? bo->base.base.size : 0; + resident_size = panfrost_gem_rss(&bo->base.base); snprintf(creator_info, sizeof(creator_info), "%s/%d", bo->debugfs.creator.process_name, bo->debugfs.creator.tgid); diff --git a/drivers/gpu/drm/radeon/radeon_display.c b/drivers/gpu/drm/radeon/radeon_display.c index b4bf5dfeea2d..4dc77c398617 100644 --- a/drivers/gpu/drm/radeon/radeon_display.c +++ b/drivers/gpu/drm/radeon/radeon_display.c @@ -1297,12 +1297,13 @@ static const struct drm_framebuffer_funcs radeon_fb_funcs = { int radeon_framebuffer_init(struct drm_device *dev, struct drm_framebuffer *fb, + const struct drm_format_info *info, const struct drm_mode_fb_cmd2 *mode_cmd, struct drm_gem_object *obj) { int ret; fb->obj[0] = obj; - drm_helper_mode_fill_fb_struct(dev, fb, NULL, mode_cmd); + drm_helper_mode_fill_fb_struct(dev, fb, info, mode_cmd); ret = drm_framebuffer_init(dev, fb, &radeon_fb_funcs); if (ret) { fb->obj[0] = NULL; @@ -1341,7 +1342,7 @@ radeon_user_framebuffer_create(struct drm_device *dev, return ERR_PTR(-ENOMEM); } - ret = radeon_framebuffer_init(dev, fb, mode_cmd, obj); + ret = radeon_framebuffer_init(dev, fb, info, mode_cmd, obj); if (ret) { kfree(fb); drm_gem_object_put(obj); diff --git a/drivers/gpu/drm/radeon/radeon_fbdev.c b/drivers/gpu/drm/radeon/radeon_fbdev.c index e3a481bbee7b..dc81b0c2dbff 100644 --- a/drivers/gpu/drm/radeon/radeon_fbdev.c +++ b/drivers/gpu/drm/radeon/radeon_fbdev.c @@ -53,10 +53,10 @@ static void radeon_fbdev_destroy_pinned_object(struct drm_gem_object *gobj) } static int radeon_fbdev_create_pinned_object(struct drm_fb_helper *fb_helper, + const struct drm_format_info *info, struct drm_mode_fb_cmd2 *mode_cmd, struct drm_gem_object **gobj_p) { - const struct drm_format_info *info; struct radeon_device *rdev = fb_helper->dev->dev_private; struct drm_gem_object *gobj = NULL; struct radeon_bo *rbo = NULL; @@ -67,8 +67,6 @@ static int radeon_fbdev_create_pinned_object(struct drm_fb_helper *fb_helper, int height = mode_cmd->height; u32 cpp; - info = drm_get_format_info(rdev_to_drm(rdev), mode_cmd->pixel_format, - mode_cmd->modifier[0]); cpp = info->cpp[0]; /* need to align pitch with crtc limits */ @@ -206,6 +204,7 @@ int radeon_fbdev_driver_fbdev_probe(struct drm_fb_helper *fb_helper, struct drm_fb_helper_surface_size *sizes) { struct radeon_device *rdev = fb_helper->dev->dev_private; + const struct drm_format_info *format_info; struct drm_mode_fb_cmd2 mode_cmd = { }; struct fb_info *info; struct drm_gem_object *gobj; @@ -224,7 +223,9 @@ int radeon_fbdev_driver_fbdev_probe(struct drm_fb_helper *fb_helper, mode_cmd.pixel_format = drm_mode_legacy_fb_format(sizes->surface_bpp, sizes->surface_depth); - ret = radeon_fbdev_create_pinned_object(fb_helper, &mode_cmd, &gobj); + format_info = drm_get_format_info(rdev_to_drm(rdev), mode_cmd.pixel_format, + mode_cmd.modifier[0]); + ret = radeon_fbdev_create_pinned_object(fb_helper, format_info, &mode_cmd, &gobj); if (ret) { DRM_ERROR("failed to create fbcon object %d\n", ret); return ret; @@ -236,7 +237,7 @@ int radeon_fbdev_driver_fbdev_probe(struct drm_fb_helper *fb_helper, ret = -ENOMEM; goto err_radeon_fbdev_destroy_pinned_object; } - ret = radeon_framebuffer_init(rdev_to_drm(rdev), fb, &mode_cmd, gobj); + ret = radeon_framebuffer_init(rdev_to_drm(rdev), fb, format_info, &mode_cmd, gobj); if (ret) { DRM_ERROR("failed to initialize framebuffer %d\n", ret); goto err_kfree; diff --git a/drivers/gpu/drm/radeon/radeon_mode.h b/drivers/gpu/drm/radeon/radeon_mode.h index 3102f6c2d055..9e34da2cacef 100644 --- a/drivers/gpu/drm/radeon/radeon_mode.h +++ b/drivers/gpu/drm/radeon/radeon_mode.h @@ -40,6 +40,7 @@ struct drm_fb_helper; struct drm_fb_helper_surface_size; +struct drm_format_info; struct edid; struct drm_edid; @@ -890,6 +891,7 @@ extern void radeon_combios_encoder_dpms_scratch_regs(struct drm_encoder *encoder, bool on); int radeon_framebuffer_init(struct drm_device *dev, struct drm_framebuffer *rfb, + const struct drm_format_info *info, const struct drm_mode_fb_cmd2 *mode_cmd, struct drm_gem_object *obj); diff --git a/drivers/gpu/drm/xe/regs/xe_bars.h b/drivers/gpu/drm/xe/regs/xe_bars.h index ce05b6ae832f..880140d6ccdc 100644 --- a/drivers/gpu/drm/xe/regs/xe_bars.h +++ b/drivers/gpu/drm/xe/regs/xe_bars.h @@ -7,5 +7,6 @@ #define GTTMMADR_BAR 0 /* MMIO + GTT */ #define LMEM_BAR 2 /* VRAM */ +#define VF_LMEM_BAR 9 /* VF VRAM */ #endif diff --git a/drivers/gpu/drm/xe/xe_hwmon.c b/drivers/gpu/drm/xe/xe_hwmon.c index f08fc4377d25..c17ed1ae8649 100644 --- a/drivers/gpu/drm/xe/xe_hwmon.c +++ b/drivers/gpu/drm/xe/xe_hwmon.c @@ -332,6 +332,7 @@ static int xe_hwmon_power_max_write(struct xe_hwmon *hwmon, u32 attr, int channe int ret = 0; u32 reg_val, max; struct xe_reg rapl_limit; + u64 max_supp_power_limit = 0; mutex_lock(&hwmon->hwmon_lock); @@ -356,6 +357,20 @@ static int xe_hwmon_power_max_write(struct xe_hwmon *hwmon, u32 attr, int channe goto unlock; } + /* + * If the sysfs value exceeds the maximum pcode supported power limit value, clamp it to + * the supported maximum (U12.3 format). + * This is to avoid truncation during reg_val calculation below and ensure the valid + * power limit is sent for pcode which would clamp it to card-supported value. + */ + max_supp_power_limit = ((PWR_LIM_VAL) >> hwmon->scl_shift_power) * SF_POWER; + if (value > max_supp_power_limit) { + value = max_supp_power_limit; + drm_info(&hwmon->xe->drm, + "Power limit clamped as selected %s exceeds channel %d limit\n", + PWR_ATTR_TO_STR(attr), channel); + } + /* Computation in 64-bits to avoid overflow. Round to nearest. */ reg_val = DIV_ROUND_CLOSEST_ULL((u64)value << hwmon->scl_shift_power, SF_POWER); @@ -739,9 +754,23 @@ static int xe_hwmon_power_curr_crit_write(struct xe_hwmon *hwmon, int channel, { int ret; u32 uval; + u64 max_crit_power_curr = 0; mutex_lock(&hwmon->hwmon_lock); + /* + * If the sysfs value exceeds the pcode mailbox cmd POWER_SETUP_SUBCOMMAND_WRITE_I1 + * max supported value, clamp it to the command's max (U10.6 format). + * This is to avoid truncation during uval calculation below and ensure the valid power + * limit is sent for pcode which would clamp it to card-supported value. + */ + max_crit_power_curr = (POWER_SETUP_I1_DATA_MASK >> POWER_SETUP_I1_SHIFT) * scale_factor; + if (value > max_crit_power_curr) { + value = max_crit_power_curr; + drm_info(&hwmon->xe->drm, + "Power limit clamped as selected exceeds channel %d limit\n", + channel); + } uval = DIV_ROUND_CLOSEST_ULL(value << POWER_SETUP_I1_SHIFT, scale_factor); ret = xe_hwmon_pcode_write_i1(hwmon, uval); diff --git a/drivers/gpu/drm/xe/xe_migrate.c b/drivers/gpu/drm/xe/xe_migrate.c index ba1cff2e4cda..7d20ac4bb633 100644 --- a/drivers/gpu/drm/xe/xe_migrate.c +++ b/drivers/gpu/drm/xe/xe_migrate.c @@ -1820,15 +1820,19 @@ int xe_migrate_access_memory(struct xe_migrate *m, struct xe_bo *bo, if (!IS_ALIGNED(len, XE_CACHELINE_BYTES) || !IS_ALIGNED((unsigned long)buf + offset, XE_CACHELINE_BYTES)) { int buf_offset = 0; + void *bounce; + int err; + + BUILD_BUG_ON(!is_power_of_2(XE_CACHELINE_BYTES)); + bounce = kmalloc(XE_CACHELINE_BYTES, GFP_KERNEL); + if (!bounce) + return -ENOMEM; /* * Less than ideal for large unaligned access but this should be * fairly rare, can fixup if this becomes common. */ do { - u8 bounce[XE_CACHELINE_BYTES]; - void *ptr = (void *)bounce; - int err; int copy_bytes = min_t(int, bytes_left, XE_CACHELINE_BYTES - (offset & XE_CACHELINE_MASK)); @@ -1837,22 +1841,22 @@ int xe_migrate_access_memory(struct xe_migrate *m, struct xe_bo *bo, err = xe_migrate_access_memory(m, bo, offset & ~XE_CACHELINE_MASK, - (void *)ptr, - sizeof(bounce), 0); + bounce, + XE_CACHELINE_BYTES, 0); if (err) - return err; + break; if (write) { - memcpy(ptr + ptr_offset, buf + buf_offset, copy_bytes); + memcpy(bounce + ptr_offset, buf + buf_offset, copy_bytes); err = xe_migrate_access_memory(m, bo, offset & ~XE_CACHELINE_MASK, - (void *)ptr, - sizeof(bounce), write); + bounce, + XE_CACHELINE_BYTES, write); if (err) - return err; + break; } else { - memcpy(buf + buf_offset, ptr + ptr_offset, + memcpy(buf + buf_offset, bounce + ptr_offset, copy_bytes); } @@ -1861,7 +1865,8 @@ int xe_migrate_access_memory(struct xe_migrate *m, struct xe_bo *bo, offset += copy_bytes; } while (bytes_left); - return 0; + kfree(bounce); + return err; } dma_addr = xe_migrate_dma_map(xe, buf, len + page_offset, write); @@ -1882,8 +1887,11 @@ int xe_migrate_access_memory(struct xe_migrate *m, struct xe_bo *bo, else current_bytes = min_t(int, bytes_left, cursor.size); - if (fence) - dma_fence_put(fence); + if (current_bytes & ~PAGE_MASK) { + int pitch = 4; + + current_bytes = min_t(int, current_bytes, S16_MAX * pitch); + } __fence = xe_migrate_vram(m, current_bytes, (unsigned long)buf & ~PAGE_MASK, @@ -1892,11 +1900,15 @@ int xe_migrate_access_memory(struct xe_migrate *m, struct xe_bo *bo, XE_MIGRATE_COPY_TO_VRAM : XE_MIGRATE_COPY_TO_SRAM); if (IS_ERR(__fence)) { - if (fence) + if (fence) { dma_fence_wait(fence, false); + dma_fence_put(fence); + } fence = __fence; goto out_err; } + + dma_fence_put(fence); fence = __fence; buf += current_bytes; diff --git a/drivers/gpu/drm/xe/xe_pci_sriov.c b/drivers/gpu/drm/xe/xe_pci_sriov.c index 447a7867eecb..af05db07162e 100644 --- a/drivers/gpu/drm/xe/xe_pci_sriov.c +++ b/drivers/gpu/drm/xe/xe_pci_sriov.c @@ -3,6 +3,10 @@ * Copyright © 2023-2024 Intel Corporation */ +#include <linux/bitops.h> +#include <linux/pci.h> + +#include "regs/xe_bars.h" #include "xe_assert.h" #include "xe_device.h" #include "xe_gt_sriov_pf_config.h" @@ -128,6 +132,18 @@ static void pf_engine_activity_stats(struct xe_device *xe, unsigned int num_vfs, } } +static int resize_vf_vram_bar(struct xe_device *xe, int num_vfs) +{ + struct pci_dev *pdev = to_pci_dev(xe->drm.dev); + u32 sizes; + + sizes = pci_iov_vf_bar_get_sizes(pdev, VF_LMEM_BAR, num_vfs); + if (!sizes) + return 0; + + return pci_iov_vf_bar_set_size(pdev, VF_LMEM_BAR, __fls(sizes)); +} + static int pf_enable_vfs(struct xe_device *xe, int num_vfs) { struct pci_dev *pdev = to_pci_dev(xe->drm.dev); @@ -158,6 +174,12 @@ static int pf_enable_vfs(struct xe_device *xe, int num_vfs) if (err < 0) goto failed; + if (IS_DGFX(xe)) { + err = resize_vf_vram_bar(xe, num_vfs); + if (err) + xe_sriov_info(xe, "Failed to set VF LMEM BAR size: %d\n", err); + } + err = pci_enable_sriov(pdev, num_vfs); if (err < 0) goto failed; diff --git a/drivers/gpu/drm/xe/xe_shrinker.c b/drivers/gpu/drm/xe/xe_shrinker.c index 1c3c04d52f55..90244fe59b59 100644 --- a/drivers/gpu/drm/xe/xe_shrinker.c +++ b/drivers/gpu/drm/xe/xe_shrinker.c @@ -54,10 +54,10 @@ xe_shrinker_mod_pages(struct xe_shrinker *shrinker, long shrinkable, long purgea write_unlock(&shrinker->lock); } -static s64 xe_shrinker_walk(struct xe_device *xe, - struct ttm_operation_ctx *ctx, - const struct xe_bo_shrink_flags flags, - unsigned long to_scan, unsigned long *scanned) +static s64 __xe_shrinker_walk(struct xe_device *xe, + struct ttm_operation_ctx *ctx, + const struct xe_bo_shrink_flags flags, + unsigned long to_scan, unsigned long *scanned) { unsigned int mem_type; s64 freed = 0, lret; @@ -93,6 +93,48 @@ static s64 xe_shrinker_walk(struct xe_device *xe, return freed; } +/* + * Try shrinking idle objects without writeback first, then if not sufficient, + * try also non-idle objects and finally if that's not sufficient either, + * add writeback. This avoids stalls and explicit writebacks with light or + * moderate memory pressure. + */ +static s64 xe_shrinker_walk(struct xe_device *xe, + struct ttm_operation_ctx *ctx, + const struct xe_bo_shrink_flags flags, + unsigned long to_scan, unsigned long *scanned) +{ + bool no_wait_gpu = true; + struct xe_bo_shrink_flags save_flags = flags; + s64 lret, freed; + + swap(no_wait_gpu, ctx->no_wait_gpu); + save_flags.writeback = false; + lret = __xe_shrinker_walk(xe, ctx, save_flags, to_scan, scanned); + swap(no_wait_gpu, ctx->no_wait_gpu); + if (lret < 0 || *scanned >= to_scan) + return lret; + + freed = lret; + if (!ctx->no_wait_gpu) { + lret = __xe_shrinker_walk(xe, ctx, save_flags, to_scan, scanned); + if (lret < 0) + return lret; + freed += lret; + if (*scanned >= to_scan) + return freed; + } + + if (flags.writeback) { + lret = __xe_shrinker_walk(xe, ctx, flags, to_scan, scanned); + if (lret < 0) + return lret; + freed += lret; + } + + return freed; +} + static unsigned long xe_shrinker_count(struct shrinker *shrink, struct shrink_control *sc) { @@ -199,6 +241,7 @@ static unsigned long xe_shrinker_scan(struct shrinker *shrink, struct shrink_con runtime_pm = xe_shrinker_runtime_pm_get(shrinker, true, 0, can_backup); shrink_flags.purge = false; + lret = xe_shrinker_walk(shrinker->xe, &ctx, shrink_flags, nr_to_scan, &nr_scanned); if (lret >= 0) diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c index 73747d20df85..91a7b7e7c0c8 100644 --- a/drivers/idle/intel_idle.c +++ b/drivers/idle/intel_idle.c @@ -1679,7 +1679,7 @@ static const struct x86_cpu_id intel_idle_ids[] __initconst = { }; static const struct x86_cpu_id intel_mwait_ids[] __initconst = { - X86_MATCH_VENDOR_FAM_FEATURE(INTEL, 6, X86_FEATURE_MWAIT, NULL), + X86_MATCH_VENDOR_FAM_FEATURE(INTEL, X86_FAMILY_ANY, X86_FEATURE_MWAIT, NULL), {} }; diff --git a/drivers/irqchip/Kconfig b/drivers/irqchip/Kconfig index 39a6ae1d574b..6d12c6ab9ea4 100644 --- a/drivers/irqchip/Kconfig +++ b/drivers/irqchip/Kconfig @@ -554,6 +554,7 @@ config IMX_MU_MSI tristate "i.MX MU used as MSI controller" depends on OF && HAS_IOMEM depends on ARCH_MXC || COMPILE_TEST + depends on ARM || ARM64 default m if ARCH_MXC select IRQ_DOMAIN select IRQ_DOMAIN_HIERARCHY diff --git a/drivers/irqchip/irq-gic-v5-its.c b/drivers/irqchip/irq-gic-v5-its.c index 340640fdbdf6..9290ac741949 100644 --- a/drivers/irqchip/irq-gic-v5-its.c +++ b/drivers/irqchip/irq-gic-v5-its.c @@ -973,7 +973,6 @@ static int gicv5_its_irq_domain_alloc(struct irq_domain *domain, unsigned int vi irqd = irq_get_irq_data(virq + i); irqd_set_single_target(irqd); irqd_set_affinity_on_activate(irqd); - irqd_set_resend_when_in_progress(irqd); } return 0; diff --git a/drivers/irqchip/irq-gic-v5-iwb.c b/drivers/irqchip/irq-gic-v5-iwb.c index ed72fbdd4900..ad9fdc14d1c6 100644 --- a/drivers/irqchip/irq-gic-v5-iwb.c +++ b/drivers/irqchip/irq-gic-v5-iwb.c @@ -241,7 +241,6 @@ static int gicv5_iwb_device_probe(struct platform_device *pdev) struct gicv5_iwb_chip_data *iwb_node; void __iomem *iwb_base; struct resource *res; - int ret; res = platform_get_resource(pdev, IORESOURCE_MEM, 0); if (!res) @@ -254,16 +253,10 @@ static int gicv5_iwb_device_probe(struct platform_device *pdev) } iwb_node = gicv5_iwb_init_bases(iwb_base, pdev); - if (IS_ERR(iwb_node)) { - ret = PTR_ERR(iwb_node); - goto out_unmap; - } + if (IS_ERR(iwb_node)) + return PTR_ERR(iwb_node); return 0; - -out_unmap: - iounmap(iwb_base); - return ret; } static const struct of_device_id gicv5_iwb_of_match[] = { diff --git a/drivers/irqchip/irq-msi-lib.c b/drivers/irqchip/irq-msi-lib.c index 454c7f16dd4d..908944009c21 100644 --- a/drivers/irqchip/irq-msi-lib.c +++ b/drivers/irqchip/irq-msi-lib.c @@ -133,13 +133,13 @@ int msi_lib_irq_domain_select(struct irq_domain *d, struct irq_fwspec *fwspec, { const struct msi_parent_ops *ops = d->msi_parent_ops; u32 busmask = BIT(bus_token); - struct fwnode_handle *fwh; if (!ops) return 0; - fwh = d->flags & IRQ_DOMAIN_FLAG_FWNODE_PARENT ? fwnode_get_parent(fwspec->fwnode) - : fwspec->fwnode; + struct fwnode_handle *fwh __free(fwnode_handle) = + d->flags & IRQ_DOMAIN_FLAG_FWNODE_PARENT ? fwnode_get_parent(fwspec->fwnode) + : fwnode_handle_get(fwspec->fwnode); if (fwh != d->fwnode || fwspec->param_count != 0) return 0; diff --git a/drivers/irqchip/irq-mvebu-gicp.c b/drivers/irqchip/irq-mvebu-gicp.c index d3232d6d8dce..54833717f8a7 100644 --- a/drivers/irqchip/irq-mvebu-gicp.c +++ b/drivers/irqchip/irq-mvebu-gicp.c @@ -177,6 +177,7 @@ static int mvebu_gicp_probe(struct platform_device *pdev) .ops = &gicp_domain_ops, }; struct mvebu_gicp *gicp; + void __iomem *base; int ret, i; gicp = devm_kzalloc(&pdev->dev, sizeof(*gicp), GFP_KERNEL); @@ -236,6 +237,15 @@ static int mvebu_gicp_probe(struct platform_device *pdev) return -ENODEV; } + base = ioremap(gicp->res->start, resource_size(gicp->res)); + if (IS_ERR(base)) { + dev_err(&pdev->dev, "ioremap() failed. Unable to clear pending interrupts.\n"); + } else { + for (i = 0; i < 64; i++) + writel(i, base + GICP_CLRSPI_NSR_OFFSET); + iounmap(base); + } + return msi_create_parent_irq_domain(&info, &gicp_msi_parent_ops) ? 0 : -ENOMEM; } diff --git a/drivers/irqchip/irq-riscv-imsic-platform.c b/drivers/irqchip/irq-riscv-imsic-platform.c index 74a2a28f9403..643c8e459611 100644 --- a/drivers/irqchip/irq-riscv-imsic-platform.c +++ b/drivers/irqchip/irq-riscv-imsic-platform.c @@ -308,7 +308,6 @@ static const struct msi_parent_ops imsic_msi_parent_ops = { int imsic_irqdomain_init(void) { struct irq_domain_info info = { - .fwnode = imsic->fwnode, .ops = &imsic_base_domain_ops, .host_data = imsic, }; @@ -325,6 +324,7 @@ int imsic_irqdomain_init(void) } /* Create Base IRQ domain */ + info.fwnode = imsic->fwnode, imsic->base_domain = msi_create_parent_irq_domain(&info, &imsic_msi_parent_ops); if (!imsic->base_domain) { pr_err("%pfwP: failed to create IMSIC base domain\n", imsic->fwnode); diff --git a/drivers/net/bonding/bond_3ad.c b/drivers/net/bonding/bond_3ad.c index 2fca8e84ab10..4edc8e6b6b64 100644 --- a/drivers/net/bonding/bond_3ad.c +++ b/drivers/net/bonding/bond_3ad.c @@ -95,13 +95,13 @@ static int ad_marker_send(struct port *port, struct bond_marker *marker); static void ad_mux_machine(struct port *port, bool *update_slave_arr); static void ad_rx_machine(struct lacpdu *lacpdu, struct port *port); static void ad_tx_machine(struct port *port); -static void ad_periodic_machine(struct port *port, struct bond_params *bond_params); +static void ad_periodic_machine(struct port *port); static void ad_port_selection_logic(struct port *port, bool *update_slave_arr); static void ad_agg_selection_logic(struct aggregator *aggregator, bool *update_slave_arr); static void ad_clear_agg(struct aggregator *aggregator); static void ad_initialize_agg(struct aggregator *aggregator); -static void ad_initialize_port(struct port *port, int lacp_fast); +static void ad_initialize_port(struct port *port, const struct bond_params *bond_params); static void ad_enable_collecting(struct port *port); static void ad_disable_distributing(struct port *port, bool *update_slave_arr); @@ -1307,10 +1307,16 @@ static void ad_rx_machine(struct lacpdu *lacpdu, struct port *port) * case of EXPIRED even if LINK_DOWN didn't arrive for * the port. */ - port->partner_oper.port_state &= ~LACP_STATE_SYNCHRONIZATION; port->sm_vars &= ~AD_PORT_MATCHED; + /* Based on IEEE 8021AX-2014, Figure 6-18 - Receive + * machine state diagram, the statue should be + * Partner_Oper_Port_State.Synchronization = FALSE; + * Partner_Oper_Port_State.LACP_Timeout = Short Timeout; + * start current_while_timer(Short Timeout); + * Actor_Oper_Port_State.Expired = TRUE; + */ + port->partner_oper.port_state &= ~LACP_STATE_SYNCHRONIZATION; port->partner_oper.port_state |= LACP_STATE_LACP_TIMEOUT; - port->partner_oper.port_state |= LACP_STATE_LACP_ACTIVITY; port->sm_rx_timer_counter = __ad_timer_to_ticks(AD_CURRENT_WHILE_TIMER, (u16)(AD_SHORT_TIMEOUT)); port->actor_oper_port_state |= LACP_STATE_EXPIRED; port->sm_vars |= AD_PORT_CHURNED; @@ -1417,11 +1423,10 @@ static void ad_tx_machine(struct port *port) /** * ad_periodic_machine - handle a port's periodic state machine * @port: the port we're looking at - * @bond_params: bond parameters we will use * * Turn ntt flag on priodically to perform periodic transmission of lacpdu's. */ -static void ad_periodic_machine(struct port *port, struct bond_params *bond_params) +static void ad_periodic_machine(struct port *port) { periodic_states_t last_state; @@ -1430,8 +1435,7 @@ static void ad_periodic_machine(struct port *port, struct bond_params *bond_para /* check if port was reinitialized */ if (((port->sm_vars & AD_PORT_BEGIN) || !(port->sm_vars & AD_PORT_LACP_ENABLED) || !port->is_enabled) || - (!(port->actor_oper_port_state & LACP_STATE_LACP_ACTIVITY) && !(port->partner_oper.port_state & LACP_STATE_LACP_ACTIVITY)) || - !bond_params->lacp_active) { + (!(port->actor_oper_port_state & LACP_STATE_LACP_ACTIVITY) && !(port->partner_oper.port_state & LACP_STATE_LACP_ACTIVITY))) { port->sm_periodic_state = AD_NO_PERIODIC; } /* check if state machine should change state */ @@ -1955,16 +1959,16 @@ static void ad_initialize_agg(struct aggregator *aggregator) /** * ad_initialize_port - initialize a given port's parameters * @port: the port we're looking at - * @lacp_fast: boolean. whether fast periodic should be used + * @bond_params: bond parameters we will use */ -static void ad_initialize_port(struct port *port, int lacp_fast) +static void ad_initialize_port(struct port *port, const struct bond_params *bond_params) { static const struct port_params tmpl = { .system_priority = 0xffff, .key = 1, .port_number = 1, .port_priority = 0xff, - .port_state = 1, + .port_state = 0, }; static const struct lacpdu lacpdu = { .subtype = 0x01, @@ -1982,12 +1986,14 @@ static void ad_initialize_port(struct port *port, int lacp_fast) port->actor_port_priority = 0xff; port->actor_port_aggregator_identifier = 0; port->ntt = false; - port->actor_admin_port_state = LACP_STATE_AGGREGATION | - LACP_STATE_LACP_ACTIVITY; - port->actor_oper_port_state = LACP_STATE_AGGREGATION | - LACP_STATE_LACP_ACTIVITY; + port->actor_admin_port_state = LACP_STATE_AGGREGATION; + port->actor_oper_port_state = LACP_STATE_AGGREGATION; + if (bond_params->lacp_active) { + port->actor_admin_port_state |= LACP_STATE_LACP_ACTIVITY; + port->actor_oper_port_state |= LACP_STATE_LACP_ACTIVITY; + } - if (lacp_fast) + if (bond_params->lacp_fast) port->actor_oper_port_state |= LACP_STATE_LACP_TIMEOUT; memcpy(&port->partner_admin, &tmpl, sizeof(tmpl)); @@ -2201,7 +2207,7 @@ void bond_3ad_bind_slave(struct slave *slave) /* port initialization */ port = &(SLAVE_AD_INFO(slave)->port); - ad_initialize_port(port, bond->params.lacp_fast); + ad_initialize_port(port, &bond->params); port->slave = slave; port->actor_port_number = SLAVE_AD_INFO(slave)->id; @@ -2513,7 +2519,7 @@ void bond_3ad_state_machine_handler(struct work_struct *work) } ad_rx_machine(NULL, port); - ad_periodic_machine(port, &bond->params); + ad_periodic_machine(port); ad_port_selection_logic(port, &update_slave_arr); ad_mux_machine(port, &update_slave_arr); ad_tx_machine(port); @@ -2883,6 +2889,31 @@ void bond_3ad_update_lacp_rate(struct bonding *bond) spin_unlock_bh(&bond->mode_lock); } +/** + * bond_3ad_update_lacp_active - change the lacp active + * @bond: bonding struct + * + * Update actor_oper_port_state when lacp_active is modified. + */ +void bond_3ad_update_lacp_active(struct bonding *bond) +{ + struct port *port = NULL; + struct list_head *iter; + struct slave *slave; + int lacp_active; + + lacp_active = bond->params.lacp_active; + spin_lock_bh(&bond->mode_lock); + bond_for_each_slave(bond, slave, iter) { + port = &(SLAVE_AD_INFO(slave)->port); + if (lacp_active) + port->actor_oper_port_state |= LACP_STATE_LACP_ACTIVITY; + else + port->actor_oper_port_state &= ~LACP_STATE_LACP_ACTIVITY; + } + spin_unlock_bh(&bond->mode_lock); +} + size_t bond_3ad_stats_size(void) { return nla_total_size_64bit(sizeof(u64)) + /* BOND_3AD_STAT_LACPDU_RX */ diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c index 1d639a3be6ba..3b6f815c55ff 100644 --- a/drivers/net/bonding/bond_options.c +++ b/drivers/net/bonding/bond_options.c @@ -1660,6 +1660,7 @@ static int bond_option_lacp_active_set(struct bonding *bond, netdev_dbg(bond->dev, "Setting LACP active to %s (%llu)\n", newval->string, newval->value); bond->params.lacp_active = newval->value; + bond_3ad_update_lacp_active(bond); return 0; } diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c index 9942fb6f7f4b..829b1f087e9e 100644 --- a/drivers/net/dsa/b53/b53_common.c +++ b/drivers/net/dsa/b53/b53_common.c @@ -2078,7 +2078,7 @@ int b53_fdb_dump(struct dsa_switch *ds, int port, /* Start search operation */ reg = ARL_SRCH_STDN; - b53_write8(priv, offset, B53_ARL_SRCH_CTL, reg); + b53_write8(priv, B53_ARLIO_PAGE, offset, reg); do { ret = b53_arl_search_wait(priv); diff --git a/drivers/net/dsa/microchip/ksz8.c b/drivers/net/dsa/microchip/ksz8.c index 76e490070e9c..c354abdafc1b 100644 --- a/drivers/net/dsa/microchip/ksz8.c +++ b/drivers/net/dsa/microchip/ksz8.c @@ -36,15 +36,14 @@ static void ksz_cfg(struct ksz_device *dev, u32 addr, u8 bits, bool set) { - regmap_update_bits(ksz_regmap_8(dev), addr, bits, set ? bits : 0); + ksz_rmw8(dev, addr, bits, set ? bits : 0); } static void ksz_port_cfg(struct ksz_device *dev, int port, int offset, u8 bits, bool set) { - regmap_update_bits(ksz_regmap_8(dev), - dev->dev_ops->get_port_addr(port, offset), - bits, set ? bits : 0); + ksz_rmw8(dev, dev->dev_ops->get_port_addr(port, offset), bits, + set ? bits : 0); } /** @@ -1955,16 +1954,19 @@ int ksz8_setup(struct dsa_switch *ds) ksz_cfg(dev, S_LINK_AGING_CTRL, SW_LINK_AUTO_AGING, true); /* Enable aggressive back off algorithm in half duplex mode. */ - regmap_update_bits(ksz_regmap_8(dev), REG_SW_CTRL_1, - SW_AGGR_BACKOFF, SW_AGGR_BACKOFF); + ret = ksz_rmw8(dev, REG_SW_CTRL_1, SW_AGGR_BACKOFF, SW_AGGR_BACKOFF); + if (ret) + return ret; /* * Make sure unicast VLAN boundary is set as default and * enable no excessive collision drop. */ - regmap_update_bits(ksz_regmap_8(dev), REG_SW_CTRL_2, - UNICAST_VLAN_BOUNDARY | NO_EXC_COLLISION_DROP, - UNICAST_VLAN_BOUNDARY | NO_EXC_COLLISION_DROP); + ret = ksz_rmw8(dev, REG_SW_CTRL_2, + UNICAST_VLAN_BOUNDARY | NO_EXC_COLLISION_DROP, + UNICAST_VLAN_BOUNDARY | NO_EXC_COLLISION_DROP); + if (ret) + return ret; ksz_cfg(dev, S_REPLACE_VID_CTRL, SW_REPLACE_VID, false); diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c index 7292bfe2f7ca..9568cc391fe3 100644 --- a/drivers/net/dsa/microchip/ksz_common.c +++ b/drivers/net/dsa/microchip/ksz_common.c @@ -1447,6 +1447,7 @@ static const struct regmap_range ksz8873_valid_regs[] = { regmap_reg_range(0x3f, 0x3f), /* advanced control registers */ + regmap_reg_range(0x43, 0x43), regmap_reg_range(0x60, 0x6f), regmap_reg_range(0x70, 0x75), regmap_reg_range(0x76, 0x78), @@ -2456,6 +2457,12 @@ static void ksz_update_port_member(struct ksz_device *dev, int port) dev->dev_ops->cfg_port_member(dev, i, val | cpu_port); } + /* HSR ports are setup once so need to use the assigned membership + * when the port is enabled. + */ + if (!port_member && p->stp_state == BR_STATE_FORWARDING && + (dev->hsr_ports & BIT(port))) + port_member = dev->hsr_ports; dev->dev_ops->cfg_port_member(dev, port, port_member | cpu_port); } diff --git a/drivers/net/ethernet/airoha/airoha_ppe.c b/drivers/net/ethernet/airoha/airoha_ppe.c index 47411d2cbd28..88694b08afa1 100644 --- a/drivers/net/ethernet/airoha/airoha_ppe.c +++ b/drivers/net/ethernet/airoha/airoha_ppe.c @@ -736,10 +736,8 @@ static void airoha_ppe_foe_insert_entry(struct airoha_ppe *ppe, continue; } - if (commit_done || !airoha_ppe_foe_compare_entry(e, hwe)) { - e->hash = 0xffff; + if (!airoha_ppe_foe_compare_entry(e, hwe)) continue; - } airoha_ppe_foe_commit_entry(ppe, &e->data, hash); commit_done = true; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 5578ddcb465d..207a8bb36ae5 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -926,15 +926,21 @@ static struct page *__bnxt_alloc_rx_page(struct bnxt *bp, dma_addr_t *mapping, static netmem_ref __bnxt_alloc_rx_netmem(struct bnxt *bp, dma_addr_t *mapping, struct bnxt_rx_ring_info *rxr, + unsigned int *offset, gfp_t gfp) { netmem_ref netmem; - netmem = page_pool_alloc_netmems(rxr->page_pool, gfp); + if (PAGE_SIZE > BNXT_RX_PAGE_SIZE) { + netmem = page_pool_alloc_frag_netmem(rxr->page_pool, offset, BNXT_RX_PAGE_SIZE, gfp); + } else { + netmem = page_pool_alloc_netmems(rxr->page_pool, gfp); + *offset = 0; + } if (!netmem) return 0; - *mapping = page_pool_get_dma_addr_netmem(netmem); + *mapping = page_pool_get_dma_addr_netmem(netmem) + *offset; return netmem; } @@ -1029,7 +1035,7 @@ static int bnxt_alloc_rx_netmem(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, dma_addr_t mapping; netmem_ref netmem; - netmem = __bnxt_alloc_rx_netmem(bp, &mapping, rxr, gfp); + netmem = __bnxt_alloc_rx_netmem(bp, &mapping, rxr, &offset, gfp); if (!netmem) return -ENOMEM; @@ -3819,7 +3825,6 @@ static int bnxt_alloc_rx_page_pool(struct bnxt *bp, if (BNXT_RX_PAGE_MODE(bp)) pp.pool_size += bp->rx_ring_size / rx_size_fac; pp.nid = numa_node; - pp.napi = &rxr->bnapi->napi; pp.netdev = bp->dev; pp.dev = &bp->pdev->dev; pp.dma_dir = bp->rx_dir; @@ -3851,6 +3856,12 @@ err_destroy_pp: return PTR_ERR(pool); } +static void bnxt_enable_rx_page_pool(struct bnxt_rx_ring_info *rxr) +{ + page_pool_enable_direct_recycling(rxr->head_pool, &rxr->bnapi->napi); + page_pool_enable_direct_recycling(rxr->page_pool, &rxr->bnapi->napi); +} + static int bnxt_alloc_rx_agg_bmap(struct bnxt *bp, struct bnxt_rx_ring_info *rxr) { u16 mem_size; @@ -3889,6 +3900,7 @@ static int bnxt_alloc_rx_rings(struct bnxt *bp) rc = bnxt_alloc_rx_page_pool(bp, rxr, cpu_node); if (rc) return rc; + bnxt_enable_rx_page_pool(rxr); rc = xdp_rxq_info_reg(&rxr->xdp_rxq, bp->dev, i, 0); if (rc < 0) @@ -5320,7 +5332,7 @@ static void bnxt_free_ntp_fltrs(struct bnxt *bp, bool all) { int i; - netdev_assert_locked(bp->dev); + netdev_assert_locked_or_invisible(bp->dev); /* Under netdev instance lock and all our NAPIs have been disabled. * It's safe to delete the hash table. @@ -16031,6 +16043,7 @@ static int bnxt_queue_start(struct net_device *dev, void *qmem, int idx) goto err_reset; } + bnxt_enable_rx_page_pool(rxr); napi_enable_locked(&bnapi->napi); bnxt_db_nq_arm(bp, &cpr->cp_db, cpr->cp_raw_cons); diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index ce95fad8cedd..9693f0289435 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -5113,7 +5113,8 @@ static const struct macb_config sama7g5_gem_config = { static const struct macb_config sama7g5_emac_config = { .caps = MACB_CAPS_USRIO_DEFAULT_IS_MII_GMII | - MACB_CAPS_MIIONRGMII | MACB_CAPS_GEM_HAS_PTP, + MACB_CAPS_USRIO_HAS_CLKEN | MACB_CAPS_MIIONRGMII | + MACB_CAPS_GEM_HAS_PTP, .dma_burst_length = 16, .clk_init = macb_clk_init, .init = macb_init, diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c index 1f411d7c4373..1be1b1ef31ee 100644 --- a/drivers/net/ethernet/google/gve/gve_main.c +++ b/drivers/net/ethernet/google/gve/gve_main.c @@ -2870,6 +2870,8 @@ static void gve_shutdown(struct pci_dev *pdev) struct gve_priv *priv = netdev_priv(netdev); bool was_up = netif_running(priv->dev); + netif_device_detach(netdev); + rtnl_lock(); netdev_lock(netdev); if (was_up && gve_close(priv->dev)) { diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_err.c b/drivers/net/ethernet/hisilicon/hibmcge/hbg_err.c index 503cfbfb4a8a..83cf75bf7a17 100644 --- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_err.c +++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_err.c @@ -53,9 +53,11 @@ static int hbg_reset_prepare(struct hbg_priv *priv, enum hbg_reset_type type) { int ret; - ASSERT_RTNL(); + if (test_and_set_bit(HBG_NIC_STATE_RESETTING, &priv->state)) + return -EBUSY; if (netif_running(priv->netdev)) { + clear_bit(HBG_NIC_STATE_RESETTING, &priv->state); dev_warn(&priv->pdev->dev, "failed to reset because port is up\n"); return -EBUSY; @@ -64,7 +66,6 @@ static int hbg_reset_prepare(struct hbg_priv *priv, enum hbg_reset_type type) netif_device_detach(priv->netdev); priv->reset_type = type; - set_bit(HBG_NIC_STATE_RESETTING, &priv->state); clear_bit(HBG_NIC_STATE_RESET_FAIL, &priv->state); ret = hbg_hw_event_notify(priv, HBG_HW_EVENT_RESET); if (ret) { @@ -84,29 +85,26 @@ static int hbg_reset_done(struct hbg_priv *priv, enum hbg_reset_type type) type != priv->reset_type) return 0; - ASSERT_RTNL(); - - clear_bit(HBG_NIC_STATE_RESETTING, &priv->state); ret = hbg_rebuild(priv); if (ret) { priv->stats.reset_fail_cnt++; set_bit(HBG_NIC_STATE_RESET_FAIL, &priv->state); + clear_bit(HBG_NIC_STATE_RESETTING, &priv->state); dev_err(&priv->pdev->dev, "failed to rebuild after reset\n"); return ret; } netif_device_attach(priv->netdev); + clear_bit(HBG_NIC_STATE_RESETTING, &priv->state); dev_info(&priv->pdev->dev, "reset done\n"); return ret; } -/* must be protected by rtnl lock */ int hbg_reset(struct hbg_priv *priv) { int ret; - ASSERT_RTNL(); ret = hbg_reset_prepare(priv, HBG_RESET_TYPE_FUNCTION); if (ret) return ret; @@ -171,7 +169,6 @@ static void hbg_pci_err_reset_prepare(struct pci_dev *pdev) struct net_device *netdev = pci_get_drvdata(pdev); struct hbg_priv *priv = netdev_priv(netdev); - rtnl_lock(); hbg_reset_prepare(priv, HBG_RESET_TYPE_FLR); } @@ -181,7 +178,6 @@ static void hbg_pci_err_reset_done(struct pci_dev *pdev) struct hbg_priv *priv = netdev_priv(netdev); hbg_reset_done(priv, HBG_RESET_TYPE_FLR); - rtnl_unlock(); } static const struct pci_error_handlers hbg_pci_err_handler = { diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_hw.c b/drivers/net/ethernet/hisilicon/hibmcge/hbg_hw.c index 8cca8316ba40..d0aa0661ecd4 100644 --- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_hw.c +++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_hw.c @@ -12,6 +12,8 @@ #define HBG_HW_EVENT_WAIT_TIMEOUT_US (2 * 1000 * 1000) #define HBG_HW_EVENT_WAIT_INTERVAL_US (10 * 1000) +#define HBG_MAC_LINK_WAIT_TIMEOUT_US (500 * 1000) +#define HBG_MAC_LINK_WAIT_INTERVAL_US (5 * 1000) /* little endian or big endian. * ctrl means packet description, data means skb packet data */ @@ -228,6 +230,9 @@ void hbg_hw_fill_buffer(struct hbg_priv *priv, u32 buffer_dma_addr) void hbg_hw_adjust_link(struct hbg_priv *priv, u32 speed, u32 duplex) { + u32 link_status; + int ret; + hbg_hw_mac_enable(priv, HBG_STATUS_DISABLE); hbg_reg_write_field(priv, HBG_REG_PORT_MODE_ADDR, @@ -239,8 +244,14 @@ void hbg_hw_adjust_link(struct hbg_priv *priv, u32 speed, u32 duplex) hbg_hw_mac_enable(priv, HBG_STATUS_ENABLE); - if (!hbg_reg_read_field(priv, HBG_REG_AN_NEG_STATE_ADDR, - HBG_REG_AN_NEG_STATE_NP_LINK_OK_B)) + /* wait MAC link up */ + ret = readl_poll_timeout(priv->io_base + HBG_REG_AN_NEG_STATE_ADDR, + link_status, + FIELD_GET(HBG_REG_AN_NEG_STATE_NP_LINK_OK_B, + link_status), + HBG_MAC_LINK_WAIT_INTERVAL_US, + HBG_MAC_LINK_WAIT_TIMEOUT_US); + if (ret) hbg_np_link_fail_task_schedule(priv); } diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_txrx.h b/drivers/net/ethernet/hisilicon/hibmcge/hbg_txrx.h index 2883a5899ae2..8b6110599e10 100644 --- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_txrx.h +++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_txrx.h @@ -29,7 +29,12 @@ static inline bool hbg_fifo_is_full(struct hbg_priv *priv, enum hbg_dir dir) static inline u32 hbg_get_queue_used_num(struct hbg_ring *ring) { - return (ring->ntu + ring->len - ring->ntc) % ring->len; + u32 len = READ_ONCE(ring->len); + + if (!len) + return 0; + + return (READ_ONCE(ring->ntu) + len - READ_ONCE(ring->ntc)) % len; } netdev_tx_t hbg_net_start_xmit(struct sk_buff *skb, struct net_device *netdev); diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index 458e5eaa92e5..e79b14d50b24 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -7149,6 +7149,13 @@ static int igc_probe(struct pci_dev *pdev, adapter->port_num = hw->bus.func; adapter->msg_enable = netif_msg_init(debug, DEFAULT_MSG_ENABLE); + /* PCI config space info */ + hw->vendor_id = pdev->vendor; + hw->device_id = pdev->device; + hw->revision_id = pdev->revision; + hw->subsystem_vendor_id = pdev->subsystem_vendor; + hw->subsystem_device_id = pdev->subsystem_device; + /* Disable ASPM L1.2 on I226 devices to avoid packet loss */ if (igc_is_device_id_i226(hw)) pci_disable_link_state(pdev, PCIE_LINK_STATE_L1_2); @@ -7175,13 +7182,6 @@ static int igc_probe(struct pci_dev *pdev, netdev->mem_start = pci_resource_start(pdev, 0); netdev->mem_end = pci_resource_end(pdev, 0); - /* PCI config space info */ - hw->vendor_id = pdev->vendor; - hw->device_id = pdev->device; - hw->revision_id = pdev->revision; - hw->subsystem_vendor_id = pdev->subsystem_vendor; - hw->subsystem_device_id = pdev->subsystem_device; - /* Copy the default MAC and PHY function pointers */ memcpy(&hw->mac.ops, ei->mac_ops, sizeof(hw->mac.ops)); memcpy(&hw->phy.ops, ei->phy_ops, sizeof(hw->phy.ops)); diff --git a/drivers/net/ethernet/intel/ixgbe/devlink/devlink.c b/drivers/net/ethernet/intel/ixgbe/devlink/devlink.c index 54f1b83dfe42..d227f4d2a2d1 100644 --- a/drivers/net/ethernet/intel/ixgbe/devlink/devlink.c +++ b/drivers/net/ethernet/intel/ixgbe/devlink/devlink.c @@ -543,6 +543,7 @@ int ixgbe_devlink_register_port(struct ixgbe_adapter *adapter) attrs.flavour = DEVLINK_PORT_FLAVOUR_PHYSICAL; attrs.phys.port_number = adapter->hw.bus.func; + attrs.no_phys_port_name = 1; ixgbe_devlink_set_switch_id(adapter, &attrs.switch_id); devlink_port_attrs_set(devlink_port, &attrs); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 6122a0abb41f..80e6a2ef1350 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -968,10 +968,6 @@ static void ixgbe_update_xoff_rx_lfc(struct ixgbe_adapter *adapter) for (i = 0; i < adapter->num_tx_queues; i++) clear_bit(__IXGBE_HANG_CHECK_ARMED, &adapter->tx_ring[i]->state); - - for (i = 0; i < adapter->num_xdp_queues; i++) - clear_bit(__IXGBE_HANG_CHECK_ARMED, - &adapter->xdp_ring[i]->state); } static void ixgbe_update_xoff_received(struct ixgbe_adapter *adapter) @@ -1214,7 +1210,7 @@ static void ixgbe_pf_handle_tx_hang(struct ixgbe_ring *tx_ring, struct ixgbe_adapter *adapter = netdev_priv(tx_ring->netdev); struct ixgbe_hw *hw = &adapter->hw; - e_err(drv, "Detected Tx Unit Hang%s\n" + e_err(drv, "Detected Tx Unit Hang\n" " Tx Queue <%d>\n" " TDH, TDT <%x>, <%x>\n" " next_to_use <%x>\n" @@ -1222,16 +1218,14 @@ static void ixgbe_pf_handle_tx_hang(struct ixgbe_ring *tx_ring, "tx_buffer_info[next_to_clean]\n" " time_stamp <%lx>\n" " jiffies <%lx>\n", - ring_is_xdp(tx_ring) ? " (XDP)" : "", tx_ring->queue_index, IXGBE_READ_REG(hw, IXGBE_TDH(tx_ring->reg_idx)), IXGBE_READ_REG(hw, IXGBE_TDT(tx_ring->reg_idx)), tx_ring->next_to_use, next, tx_ring->tx_buffer_info[next].time_stamp, jiffies); - if (!ring_is_xdp(tx_ring)) - netif_stop_subqueue(tx_ring->netdev, - tx_ring->queue_index); + netif_stop_subqueue(tx_ring->netdev, + tx_ring->queue_index); } /** @@ -1451,6 +1445,9 @@ static bool ixgbe_clean_tx_irq(struct ixgbe_q_vector *q_vector, total_bytes); adapter->tx_ipsec += total_ipsec; + if (ring_is_xdp(tx_ring)) + return !!budget; + if (check_for_tx_hang(tx_ring) && ixgbe_check_tx_hang(tx_ring)) { if (adapter->hw.mac.type == ixgbe_mac_e610) ixgbe_handle_mdd_event(adapter, tx_ring); @@ -1468,9 +1465,6 @@ static bool ixgbe_clean_tx_irq(struct ixgbe_q_vector *q_vector, return true; } - if (ring_is_xdp(tx_ring)) - return !!budget; - #define TX_WAKE_THRESHOLD (DESC_NEEDED * 2) txq = netdev_get_tx_queue(tx_ring->netdev, tx_ring->queue_index); if (!__netif_txq_completed_wake(txq, total_packets, total_bytes, @@ -7974,12 +7968,9 @@ static void ixgbe_check_hang_subtask(struct ixgbe_adapter *adapter) return; /* Force detection of hung controller */ - if (netif_carrier_ok(adapter->netdev)) { + if (netif_carrier_ok(adapter->netdev)) for (i = 0; i < adapter->num_tx_queues; i++) set_check_for_tx_hang(adapter->tx_ring[i]); - for (i = 0; i < adapter->num_xdp_queues; i++) - set_check_for_tx_hang(adapter->xdp_ring[i]); - } if (!(adapter->flags & IXGBE_FLAG_MSIX_ENABLED)) { /* @@ -8199,13 +8190,6 @@ static bool ixgbe_ring_tx_pending(struct ixgbe_adapter *adapter) return true; } - for (i = 0; i < adapter->num_xdp_queues; i++) { - struct ixgbe_ring *ring = adapter->xdp_ring[i]; - - if (ring->next_to_use != ring->next_to_clean) - return true; - } - return false; } @@ -11005,6 +10989,10 @@ static int ixgbe_xdp_xmit(struct net_device *dev, int n, if (unlikely(test_bit(__IXGBE_DOWN, &adapter->state))) return -ENETDOWN; + if (!netif_carrier_ok(adapter->netdev) || + !netif_running(adapter->netdev)) + return -ENETDOWN; + if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK)) return -EINVAL; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c index ac58964b2f08..7b941505a9d0 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c @@ -398,7 +398,7 @@ static bool ixgbe_xmit_zc(struct ixgbe_ring *xdp_ring, unsigned int budget) dma_addr_t dma; u32 cmd_type; - while (budget-- > 0) { + while (likely(budget)) { if (unlikely(!ixgbe_desc_unused(xdp_ring))) { work_done = false; break; @@ -433,6 +433,8 @@ static bool ixgbe_xmit_zc(struct ixgbe_ring *xdp_ring, unsigned int budget) xdp_ring->next_to_use++; if (xdp_ring->next_to_use == xdp_ring->count) xdp_ring->next_to_use = 0; + + budget--; } if (tx_desc) { diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c index 1b765045aa63..b56395ac5a74 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c @@ -606,8 +606,8 @@ static void npc_set_features(struct rvu *rvu, int blkaddr, u8 intf) if (!npc_check_field(rvu, blkaddr, NPC_LB, intf)) *features &= ~BIT_ULL(NPC_OUTER_VID); - /* Set SPI flag only if AH/ESP and IPSEC_SPI are in the key */ - if (npc_check_field(rvu, blkaddr, NPC_IPSEC_SPI, intf) && + /* Allow extracting SPI field from AH and ESP headers at same offset */ + if (npc_is_field_present(rvu, NPC_IPSEC_SPI, intf) && (*features & (BIT_ULL(NPC_IPPROTO_ESP) | BIT_ULL(NPC_IPPROTO_AH)))) *features |= BIT_ULL(NPC_IPSEC_SPI); diff --git a/drivers/net/ethernet/mediatek/mtk_ppe_offload.c b/drivers/net/ethernet/mediatek/mtk_ppe_offload.c index c855fb799ce1..e9bd32741983 100644 --- a/drivers/net/ethernet/mediatek/mtk_ppe_offload.c +++ b/drivers/net/ethernet/mediatek/mtk_ppe_offload.c @@ -101,7 +101,9 @@ mtk_flow_get_wdma_info(struct net_device *dev, const u8 *addr, struct mtk_wdma_i if (!IS_ENABLED(CONFIG_NET_MEDIATEK_SOC_WED)) return -1; + rcu_read_lock(); err = dev_fill_forward_path(dev, addr, &stack); + rcu_read_unlock(); if (err) return err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/dcbnl.h b/drivers/net/ethernet/mellanox/mlx5/core/en/dcbnl.h index b59aee75de94..2c98a5299df3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/dcbnl.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/dcbnl.h @@ -26,7 +26,6 @@ struct mlx5e_dcbx { u8 cap; /* Buffer configuration */ - bool manual_buffer; u32 cable_len; u32 xoff; u16 port_buff_cell_sz; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c b/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c index 5ae787656a7c..3efa8bf1d14e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c @@ -272,8 +272,8 @@ static int port_update_shared_buffer(struct mlx5_core_dev *mdev, /* Total shared buffer size is split in a ratio of 3:1 between * lossy and lossless pools respectively. */ - lossy_epool_size = (shared_buffer_size / 4) * 3; lossless_ipool_size = shared_buffer_size / 4; + lossy_epool_size = shared_buffer_size - lossless_ipool_size; mlx5e_port_set_sbpr(mdev, 0, MLX5_EGRESS_DIR, MLX5_LOSSY_POOL, 0, lossy_epool_size); @@ -288,14 +288,12 @@ static int port_set_buffer(struct mlx5e_priv *priv, u16 port_buff_cell_sz = priv->dcbx.port_buff_cell_sz; struct mlx5_core_dev *mdev = priv->mdev; int sz = MLX5_ST_SZ_BYTES(pbmc_reg); - u32 new_headroom_size = 0; - u32 current_headroom_size; + u32 current_headroom_cells = 0; + u32 new_headroom_cells = 0; void *in; int err; int i; - current_headroom_size = port_buffer->headroom_size; - in = kzalloc(sz, GFP_KERNEL); if (!in) return -ENOMEM; @@ -306,12 +304,14 @@ static int port_set_buffer(struct mlx5e_priv *priv, for (i = 0; i < MLX5E_MAX_NETWORK_BUFFER; i++) { void *buffer = MLX5_ADDR_OF(pbmc_reg, in, buffer[i]); + current_headroom_cells += MLX5_GET(bufferx_reg, buffer, size); + u64 size = port_buffer->buffer[i].size; u64 xoff = port_buffer->buffer[i].xoff; u64 xon = port_buffer->buffer[i].xon; - new_headroom_size += size; do_div(size, port_buff_cell_sz); + new_headroom_cells += size; do_div(xoff, port_buff_cell_sz); do_div(xon, port_buff_cell_sz); MLX5_SET(bufferx_reg, buffer, size, size); @@ -320,10 +320,8 @@ static int port_set_buffer(struct mlx5e_priv *priv, MLX5_SET(bufferx_reg, buffer, xon_threshold, xon); } - new_headroom_size /= port_buff_cell_sz; - current_headroom_size /= port_buff_cell_sz; - err = port_update_shared_buffer(priv->mdev, current_headroom_size, - new_headroom_size); + err = port_update_shared_buffer(priv->mdev, current_headroom_cells, + new_headroom_cells); if (err) goto out; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs_hmfs.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs_hmfs.c index a4263137fef5..01d522b02947 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs_hmfs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs_hmfs.c @@ -173,6 +173,8 @@ static void mlx5_ct_fs_hmfs_fill_rule_actions(struct mlx5_ct_fs_hmfs *fs_hmfs, memset(rule_actions, 0, NUM_CT_HMFS_RULES * sizeof(*rule_actions)); rule_actions[0].action = mlx5_fc_get_hws_action(fs_hmfs->ctx, attr->counter); + rule_actions[0].counter.offset = + attr->counter->id - attr->counter->bulk->base_id; /* Modify header is special, it may require extra arguments outside the action itself. */ if (mh_action->mh_data) { rule_actions[1].modify_header.offset = mh_action->mh_data->offset; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c index 5fe016e477b3..d166c0d5189e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c @@ -362,6 +362,7 @@ static int mlx5e_dcbnl_ieee_getpfc(struct net_device *dev, static int mlx5e_dcbnl_ieee_setpfc(struct net_device *dev, struct ieee_pfc *pfc) { + u8 buffer_ownership = MLX5_BUF_OWNERSHIP_UNKNOWN; struct mlx5e_priv *priv = netdev_priv(dev); struct mlx5_core_dev *mdev = priv->mdev; u32 old_cable_len = priv->dcbx.cable_len; @@ -389,7 +390,14 @@ static int mlx5e_dcbnl_ieee_setpfc(struct net_device *dev, if (MLX5_BUFFER_SUPPORTED(mdev)) { pfc_new.pfc_en = (changed & MLX5E_PORT_BUFFER_PFC) ? pfc->pfc_en : curr_pfc_en; - if (priv->dcbx.manual_buffer) + ret = mlx5_query_port_buffer_ownership(mdev, + &buffer_ownership); + if (ret) + netdev_err(dev, + "%s, Failed to get buffer ownership: %d\n", + __func__, ret); + + if (buffer_ownership == MLX5_BUF_OWNERSHIP_SW_OWNED) ret = mlx5e_port_manual_buffer_config(priv, changed, dev->mtu, &pfc_new, NULL, NULL); @@ -982,7 +990,6 @@ static int mlx5e_dcbnl_setbuffer(struct net_device *dev, if (!changed) return 0; - priv->dcbx.manual_buffer = true; err = mlx5e_port_manual_buffer_config(priv, changed, dev->mtu, NULL, buffer_size, prio2buffer); return err; @@ -1252,7 +1259,6 @@ void mlx5e_dcbnl_initialize(struct mlx5e_priv *priv) priv->dcbx.cap |= DCB_CAP_DCBX_HOST; priv->dcbx.port_buff_cell_sz = mlx5e_query_port_buffers_cell_size(priv); - priv->dcbx.manual_buffer = false; priv->dcbx.cable_len = MLX5E_DEFAULT_CABLE_LEN; mlx5e_ets_init(priv); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c index b7102e14d23d..c33accadae0f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c @@ -47,10 +47,12 @@ static void mlx5_esw_offloads_pf_vf_devlink_port_attrs_set(struct mlx5_eswitch * devlink_port_attrs_pci_vf_set(dl_port, controller_num, pfnum, vport_num - 1, external); } else if (mlx5_core_is_ec_vf_vport(esw->dev, vport_num)) { + u16 base_vport = mlx5_core_ec_vf_vport_base(dev); + memcpy(dl_port->attrs.switch_id.id, ppid.id, ppid.id_len); dl_port->attrs.switch_id.id_len = ppid.id_len; devlink_port_attrs_pci_vf_set(dl_port, 0, pfnum, - vport_num - 1, false); + vport_num - base_vport, false); } } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c index 91d863c8c152..8b4977650183 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c @@ -102,6 +102,8 @@ struct mlx5_esw_sched_node { u8 level; /* Valid only when this node represents a traffic class. */ u8 tc; + /* Valid only for a TC arbiter node or vport TC arbiter. */ + u32 tc_bw[DEVLINK_RATE_TCS_MAX]; }; static void esw_qos_node_attach_to_parent(struct mlx5_esw_sched_node *node) @@ -462,6 +464,7 @@ static int esw_qos_vport_create_sched_element(struct mlx5_esw_sched_node *vport_node, struct netlink_ext_ack *extack) { + struct mlx5_esw_sched_node *parent = vport_node->parent; u32 sched_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {}; struct mlx5_core_dev *dev = vport_node->esw->dev; void *attr; @@ -477,7 +480,7 @@ esw_qos_vport_create_sched_element(struct mlx5_esw_sched_node *vport_node, attr = MLX5_ADDR_OF(scheduling_context, sched_ctx, element_attributes); MLX5_SET(vport_element, attr, vport_number, vport_node->vport->vport); MLX5_SET(scheduling_context, sched_ctx, parent_element_id, - vport_node->parent->ix); + parent ? parent->ix : vport_node->esw->qos.root_tsar_ix); MLX5_SET(scheduling_context, sched_ctx, max_average_bw, vport_node->max_rate); @@ -608,10 +611,7 @@ static void esw_qos_tc_arbiter_get_bw_shares(struct mlx5_esw_sched_node *tc_arbiter_node, u32 *tc_bw) { - struct mlx5_esw_sched_node *vports_tc_node; - - list_for_each_entry(vports_tc_node, &tc_arbiter_node->children, entry) - tc_bw[vports_tc_node->tc] = vports_tc_node->bw_share; + memcpy(tc_bw, tc_arbiter_node->tc_bw, sizeof(tc_arbiter_node->tc_bw)); } static void @@ -628,6 +628,7 @@ esw_qos_set_tc_arbiter_bw_shares(struct mlx5_esw_sched_node *tc_arbiter_node, u8 tc = vports_tc_node->tc; u32 bw_share; + tc_arbiter_node->tc_bw[tc] = tc_bw[tc]; bw_share = tc_bw[tc] * fw_max_bw_share; bw_share = esw_qos_calc_bw_share(bw_share, divider, fw_max_bw_share); @@ -786,48 +787,15 @@ static int esw_qos_create(struct mlx5_eswitch *esw, struct netlink_ext_ack *exta return err; } - if (MLX5_CAP_QOS(dev, log_esw_max_sched_depth)) { - esw->qos.node0 = __esw_qos_create_vports_sched_node(esw, NULL, extack); - } else { - /* The eswitch doesn't support scheduling nodes. - * Create a software-only node0 using the root TSAR to attach vport QoS to. - */ - if (!__esw_qos_alloc_node(esw, - esw->qos.root_tsar_ix, - SCHED_NODE_TYPE_VPORTS_TSAR, - NULL)) - esw->qos.node0 = ERR_PTR(-ENOMEM); - else - list_add_tail(&esw->qos.node0->entry, - &esw->qos.domain->nodes); - } - if (IS_ERR(esw->qos.node0)) { - err = PTR_ERR(esw->qos.node0); - esw_warn(dev, "E-Switch create rate node 0 failed (%d)\n", err); - goto err_node0; - } refcount_set(&esw->qos.refcnt, 1); return 0; - -err_node0: - if (mlx5_destroy_scheduling_element_cmd(esw->dev, SCHEDULING_HIERARCHY_E_SWITCH, - esw->qos.root_tsar_ix)) - esw_warn(esw->dev, "E-Switch destroy root TSAR failed.\n"); - - return err; } static void esw_qos_destroy(struct mlx5_eswitch *esw) { int err; - if (esw->qos.node0->ix != esw->qos.root_tsar_ix) - __esw_qos_destroy_node(esw->qos.node0, NULL); - else - __esw_qos_free_node(esw->qos.node0); - esw->qos.node0 = NULL; - err = mlx5_destroy_scheduling_element_cmd(esw->dev, SCHEDULING_HIERARCHY_E_SWITCH, esw->qos.root_tsar_ix); @@ -990,13 +958,16 @@ esw_qos_vport_tc_enable(struct mlx5_vport *vport, enum sched_node_type type, struct netlink_ext_ack *extack) { struct mlx5_esw_sched_node *vport_node = vport->qos.sched_node; - int err, new_level, max_level; + struct mlx5_esw_sched_node *parent = vport_node->parent; + int err; if (type == SCHED_NODE_TYPE_TC_ARBITER_TSAR) { + int new_level, max_level; + /* Increase the parent's level by 2 to account for both the * TC arbiter and the vports TC scheduling element. */ - new_level = vport_node->parent->level + 2; + new_level = (parent ? parent->level : 2) + 2; max_level = 1 << MLX5_CAP_QOS(vport_node->esw->dev, log_esw_max_sched_depth); if (new_level > max_level) { @@ -1033,9 +1004,7 @@ esw_qos_vport_tc_enable(struct mlx5_vport *vport, enum sched_node_type type, err_sched_nodes: if (type == SCHED_NODE_TYPE_RATE_LIMITER) { esw_qos_node_destroy_sched_element(vport_node, NULL); - list_add_tail(&vport_node->entry, - &vport_node->parent->children); - vport_node->level = vport_node->parent->level + 1; + esw_qos_node_attach_to_parent(vport_node); } else { esw_qos_tc_arbiter_scheduling_teardown(vport_node, NULL); } @@ -1083,7 +1052,6 @@ err_out: static void esw_qos_vport_disable(struct mlx5_vport *vport, struct netlink_ext_ack *extack) { struct mlx5_esw_sched_node *vport_node = vport->qos.sched_node; - struct mlx5_esw_sched_node *parent = vport_node->parent; enum sched_node_type curr_type = vport_node->type; if (curr_type == SCHED_NODE_TYPE_VPORT) @@ -1092,8 +1060,9 @@ static void esw_qos_vport_disable(struct mlx5_vport *vport, struct netlink_ext_a esw_qos_vport_tc_disable(vport, extack); vport_node->bw_share = 0; + memset(vport_node->tc_bw, 0, sizeof(vport_node->tc_bw)); list_del_init(&vport_node->entry); - esw_qos_normalize_min_rate(parent->esw, parent, extack); + esw_qos_normalize_min_rate(vport_node->esw, vport_node->parent, extack); trace_mlx5_esw_vport_qos_destroy(vport_node->esw->dev, vport); } @@ -1103,25 +1072,23 @@ static int esw_qos_vport_enable(struct mlx5_vport *vport, struct mlx5_esw_sched_node *parent, struct netlink_ext_ack *extack) { + struct mlx5_esw_sched_node *vport_node = vport->qos.sched_node; int err; esw_assert_qos_lock_held(vport->dev->priv.eswitch); - esw_qos_node_set_parent(vport->qos.sched_node, parent); - if (type == SCHED_NODE_TYPE_VPORT) { - err = esw_qos_vport_create_sched_element(vport->qos.sched_node, - extack); - } else { + esw_qos_node_set_parent(vport_node, parent); + if (type == SCHED_NODE_TYPE_VPORT) + err = esw_qos_vport_create_sched_element(vport_node, extack); + else err = esw_qos_vport_tc_enable(vport, type, extack); - } if (err) return err; - vport->qos.sched_node->type = type; - esw_qos_normalize_min_rate(parent->esw, parent, extack); - trace_mlx5_esw_vport_qos_create(vport->dev, vport, - vport->qos.sched_node->max_rate, - vport->qos.sched_node->bw_share); + vport_node->type = type; + esw_qos_normalize_min_rate(vport_node->esw, parent, extack); + trace_mlx5_esw_vport_qos_create(vport->dev, vport, vport_node->max_rate, + vport_node->bw_share); return 0; } @@ -1132,6 +1099,7 @@ static int mlx5_esw_qos_vport_enable(struct mlx5_vport *vport, enum sched_node_t { struct mlx5_eswitch *esw = vport->dev->priv.eswitch; struct mlx5_esw_sched_node *sched_node; + struct mlx5_eswitch *parent_esw; int err; esw_assert_qos_lock_held(esw); @@ -1139,10 +1107,14 @@ static int mlx5_esw_qos_vport_enable(struct mlx5_vport *vport, enum sched_node_t if (err) return err; - parent = parent ?: esw->qos.node0; - sched_node = __esw_qos_alloc_node(parent->esw, 0, type, parent); - if (!sched_node) + parent_esw = parent ? parent->esw : esw; + sched_node = __esw_qos_alloc_node(parent_esw, 0, type, parent); + if (!sched_node) { + esw_qos_put(esw); return -ENOMEM; + } + if (!parent) + list_add_tail(&sched_node->entry, &esw->qos.domain->nodes); sched_node->max_rate = max_rate; sched_node->min_rate = min_rate; @@ -1150,6 +1122,7 @@ static int mlx5_esw_qos_vport_enable(struct mlx5_vport *vport, enum sched_node_t vport->qos.sched_node = sched_node; err = esw_qos_vport_enable(vport, type, parent, extack); if (err) { + __esw_qos_free_node(sched_node); esw_qos_put(esw); vport->qos.sched_node = NULL; } @@ -1157,6 +1130,19 @@ static int mlx5_esw_qos_vport_enable(struct mlx5_vport *vport, enum sched_node_t return err; } +static void mlx5_esw_qos_vport_disable_locked(struct mlx5_vport *vport) +{ + struct mlx5_eswitch *esw = vport->dev->priv.eswitch; + + esw_assert_qos_lock_held(esw); + if (!vport->qos.sched_node) + return; + + esw_qos_vport_disable(vport, NULL); + mlx5_esw_qos_vport_qos_free(vport); + esw_qos_put(esw); +} + void mlx5_esw_qos_vport_disable(struct mlx5_vport *vport) { struct mlx5_eswitch *esw = vport->dev->priv.eswitch; @@ -1168,11 +1154,9 @@ void mlx5_esw_qos_vport_disable(struct mlx5_vport *vport) goto unlock; parent = vport->qos.sched_node->parent; - WARN(parent != esw->qos.node0, "Disabling QoS on port before detaching it from node"); + WARN(parent, "Disabling QoS on port before detaching it from node"); - esw_qos_vport_disable(vport, NULL); - mlx5_esw_qos_vport_qos_free(vport); - esw_qos_put(esw); + mlx5_esw_qos_vport_disable_locked(vport); unlock: esw_qos_unlock(esw); } @@ -1262,13 +1246,13 @@ static int esw_qos_vport_update(struct mlx5_vport *vport, struct mlx5_esw_sched_node *parent, struct netlink_ext_ack *extack) { - struct mlx5_esw_sched_node *curr_parent = vport->qos.sched_node->parent; - enum sched_node_type curr_type = vport->qos.sched_node->type; + struct mlx5_esw_sched_node *vport_node = vport->qos.sched_node; + struct mlx5_esw_sched_node *curr_parent = vport_node->parent; + enum sched_node_type curr_type = vport_node->type; u32 curr_tc_bw[DEVLINK_RATE_TCS_MAX] = {0}; int err; esw_assert_qos_lock_held(vport->dev->priv.eswitch); - parent = parent ?: curr_parent; if (curr_type == type && curr_parent == parent) return 0; @@ -1276,10 +1260,8 @@ static int esw_qos_vport_update(struct mlx5_vport *vport, if (err) return err; - if (curr_type == SCHED_NODE_TYPE_TC_ARBITER_TSAR && curr_type == type) { - esw_qos_tc_arbiter_get_bw_shares(vport->qos.sched_node, - curr_tc_bw); - } + if (curr_type == SCHED_NODE_TYPE_TC_ARBITER_TSAR && curr_type == type) + esw_qos_tc_arbiter_get_bw_shares(vport_node, curr_tc_bw); esw_qos_vport_disable(vport, extack); @@ -1290,8 +1272,8 @@ static int esw_qos_vport_update(struct mlx5_vport *vport, } if (curr_type == SCHED_NODE_TYPE_TC_ARBITER_TSAR && curr_type == type) { - esw_qos_set_tc_arbiter_bw_shares(vport->qos.sched_node, - curr_tc_bw, extack); + esw_qos_set_tc_arbiter_bw_shares(vport_node, curr_tc_bw, + extack); } return err; @@ -1306,16 +1288,16 @@ static int esw_qos_vport_update_parent(struct mlx5_vport *vport, struct mlx5_esw esw_assert_qos_lock_held(esw); curr_parent = vport->qos.sched_node->parent; - parent = parent ?: esw->qos.node0; if (curr_parent == parent) return 0; /* Set vport QoS type based on parent node type if different from * default QoS; otherwise, use the vport's current QoS type. */ - if (parent->type == SCHED_NODE_TYPE_TC_ARBITER_TSAR) + if (parent && parent->type == SCHED_NODE_TYPE_TC_ARBITER_TSAR) type = SCHED_NODE_TYPE_RATE_LIMITER; - else if (curr_parent->type == SCHED_NODE_TYPE_TC_ARBITER_TSAR) + else if (curr_parent && + curr_parent->type == SCHED_NODE_TYPE_TC_ARBITER_TSAR) type = SCHED_NODE_TYPE_VPORT; else type = vport->qos.sched_node->type; @@ -1654,9 +1636,10 @@ static bool esw_qos_validate_unsupported_tc_bw(struct mlx5_eswitch *esw, static bool esw_qos_vport_validate_unsupported_tc_bw(struct mlx5_vport *vport, u32 *tc_bw) { - struct mlx5_eswitch *esw = vport->qos.sched_node ? - vport->qos.sched_node->parent->esw : - vport->dev->priv.eswitch; + struct mlx5_esw_sched_node *node = vport->qos.sched_node; + struct mlx5_eswitch *esw = vport->dev->priv.eswitch; + + esw = (node && node->parent) ? node->parent->esw : esw; return esw_qos_validate_unsupported_tc_bw(esw, tc_bw); } @@ -1673,6 +1656,21 @@ static bool esw_qos_tc_bw_disabled(u32 *tc_bw) return true; } +static void esw_vport_qos_prune_empty(struct mlx5_vport *vport) +{ + struct mlx5_esw_sched_node *vport_node = vport->qos.sched_node; + + esw_assert_qos_lock_held(vport->dev->priv.eswitch); + if (!vport_node) + return; + + if (vport_node->parent || vport_node->max_rate || + vport_node->min_rate || !esw_qos_tc_bw_disabled(vport_node->tc_bw)) + return; + + mlx5_esw_qos_vport_disable_locked(vport); +} + int mlx5_esw_qos_init(struct mlx5_eswitch *esw) { if (esw->qos.domain) @@ -1706,6 +1704,10 @@ int mlx5_esw_devlink_rate_leaf_tx_share_set(struct devlink_rate *rate_leaf, void esw_qos_lock(esw); err = mlx5_esw_qos_set_vport_min_rate(vport, tx_share, extack); + if (err) + goto out; + esw_vport_qos_prune_empty(vport); +out: esw_qos_unlock(esw); return err; } @@ -1727,6 +1729,10 @@ int mlx5_esw_devlink_rate_leaf_tx_max_set(struct devlink_rate *rate_leaf, void * esw_qos_lock(esw); err = mlx5_esw_qos_set_vport_max_rate(vport, tx_max, extack); + if (err) + goto out; + esw_vport_qos_prune_empty(vport); +out: esw_qos_unlock(esw); return err; } @@ -1763,7 +1769,8 @@ int mlx5_esw_devlink_rate_leaf_tc_bw_set(struct devlink_rate *rate_leaf, if (disable) { if (vport_node->type == SCHED_NODE_TYPE_TC_ARBITER_TSAR) err = esw_qos_vport_update(vport, SCHED_NODE_TYPE_VPORT, - NULL, extack); + vport_node->parent, extack); + esw_vport_qos_prune_empty(vport); goto unlock; } @@ -1775,7 +1782,7 @@ int mlx5_esw_devlink_rate_leaf_tc_bw_set(struct devlink_rate *rate_leaf, } else { err = esw_qos_vport_update(vport, SCHED_NODE_TYPE_TC_ARBITER_TSAR, - NULL, extack); + vport_node->parent, extack); } if (!err) esw_qos_set_tc_arbiter_bw_shares(vport_node, tc_bw, extack); @@ -1924,14 +1931,20 @@ int mlx5_esw_devlink_rate_leaf_parent_set(struct devlink_rate *devlink_rate, void *priv, void *parent_priv, struct netlink_ext_ack *extack) { - struct mlx5_esw_sched_node *node; + struct mlx5_esw_sched_node *node = parent ? parent_priv : NULL; struct mlx5_vport *vport = priv; + int err; - if (!parent) - return mlx5_esw_qos_vport_update_parent(vport, NULL, extack); + err = mlx5_esw_qos_vport_update_parent(vport, node, extack); + if (!err) { + struct mlx5_eswitch *esw = vport->dev->priv.eswitch; + + esw_qos_lock(esw); + esw_vport_qos_prune_empty(vport); + esw_qos_unlock(esw); + } - node = parent_priv; - return mlx5_esw_qos_vport_update_parent(vport, node, extack); + return err; } static bool esw_qos_is_node_empty(struct mlx5_esw_sched_node *node) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index b0b8ef3ec3c4..45506ad56847 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -373,11 +373,6 @@ struct mlx5_eswitch { refcount_t refcnt; u32 root_tsar_ix; struct mlx5_qos_domain *domain; - /* Contains all vports with QoS enabled but no explicit node. - * Cannot be NULL if QoS is enabled, but may be a fake node - * referencing the root TSAR if the esw doesn't support nodes. - */ - struct mlx5_esw_sched_node *node0; } qos; struct mlx5_esw_bridge_offloads *br_offloads; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h index b6d53db27cd5..9d3504f5abfa 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h @@ -367,6 +367,8 @@ int mlx5_query_port_dcbx_param(struct mlx5_core_dev *mdev, u32 *out); int mlx5_set_port_dcbx_param(struct mlx5_core_dev *mdev, u32 *in); int mlx5_set_trust_state(struct mlx5_core_dev *mdev, u8 trust_state); int mlx5_query_trust_state(struct mlx5_core_dev *mdev, u8 *trust_state); +int mlx5_query_port_buffer_ownership(struct mlx5_core_dev *mdev, + u8 *buffer_ownership); int mlx5_set_dscp2prio(struct mlx5_core_dev *mdev, u8 dscp, u8 prio); int mlx5_query_dscp2prio(struct mlx5_core_dev *mdev, u8 *dscp2prio); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/port.c b/drivers/net/ethernet/mellanox/mlx5/core/port.c index 549f1066d2a5..2d7adf7444ba 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/port.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/port.c @@ -968,6 +968,26 @@ int mlx5_query_trust_state(struct mlx5_core_dev *mdev, u8 *trust_state) return err; } +int mlx5_query_port_buffer_ownership(struct mlx5_core_dev *mdev, + u8 *buffer_ownership) +{ + u32 out[MLX5_ST_SZ_DW(pfcc_reg)] = {}; + int err; + + if (!MLX5_CAP_PCAM_FEATURE(mdev, buffer_ownership)) { + *buffer_ownership = MLX5_BUF_OWNERSHIP_UNKNOWN; + return 0; + } + + err = mlx5_query_pfcc_reg(mdev, out, sizeof(out)); + if (err) + return err; + + *buffer_ownership = MLX5_GET(pfcc_reg, out, buf_ownership); + + return 0; +} + int mlx5_set_dscp2prio(struct mlx5_core_dev *mdev, u8 dscp, u8 prio) { int sz = MLX5_ST_SZ_BYTES(qpdpm_reg); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc.c index 92de4b761a83..adeccc588e5d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc.c @@ -74,9 +74,9 @@ static void hws_bwc_matcher_init_attr(struct mlx5hws_bwc_matcher *bwc_matcher, static int hws_bwc_matcher_move_all_simple(struct mlx5hws_bwc_matcher *bwc_matcher) { - bool move_error = false, poll_error = false, drain_error = false; struct mlx5hws_context *ctx = bwc_matcher->matcher->tbl->ctx; struct mlx5hws_matcher *matcher = bwc_matcher->matcher; + int drain_error = 0, move_error = 0, poll_error = 0; u16 bwc_queues = mlx5hws_bwc_queues(ctx); struct mlx5hws_rule_attr rule_attr; struct mlx5hws_bwc_rule *bwc_rule; @@ -84,6 +84,7 @@ hws_bwc_matcher_move_all_simple(struct mlx5hws_bwc_matcher *bwc_matcher) struct list_head *rules_list; u32 pending_rules; int i, ret = 0; + bool drain; mlx5hws_bwc_rule_fill_attr(bwc_matcher, 0, 0, &rule_attr); @@ -99,23 +100,37 @@ hws_bwc_matcher_move_all_simple(struct mlx5hws_bwc_matcher *bwc_matcher) ret = mlx5hws_matcher_resize_rule_move(matcher, bwc_rule->rule, &rule_attr); - if (unlikely(ret && !move_error)) { - mlx5hws_err(ctx, - "Moving BWC rule: move failed (%d), attempting to move rest of the rules\n", - ret); - move_error = true; + if (unlikely(ret)) { + if (!move_error) { + mlx5hws_err(ctx, + "Moving BWC rule: move failed (%d), attempting to move rest of the rules\n", + ret); + move_error = ret; + } + /* Rule wasn't queued, no need to poll */ + continue; } pending_rules++; + drain = pending_rules >= + hws_bwc_get_burst_th(ctx, rule_attr.queue_id); ret = mlx5hws_bwc_queue_poll(ctx, rule_attr.queue_id, &pending_rules, - false); - if (unlikely(ret && !poll_error)) { - mlx5hws_err(ctx, - "Moving BWC rule: poll failed (%d), attempting to move rest of the rules\n", - ret); - poll_error = true; + drain); + if (unlikely(ret)) { + if (ret == -ETIMEDOUT) { + mlx5hws_err(ctx, + "Moving BWC rule: timeout polling for completions (%d), aborting rehash\n", + ret); + return ret; + } + if (!poll_error) { + mlx5hws_err(ctx, + "Moving BWC rule: polling for completions failed (%d), attempting to move rest of the rules\n", + ret); + poll_error = ret; + } } } @@ -126,17 +141,30 @@ hws_bwc_matcher_move_all_simple(struct mlx5hws_bwc_matcher *bwc_matcher) rule_attr.queue_id, &pending_rules, true); - if (unlikely(ret && !drain_error)) { - mlx5hws_err(ctx, - "Moving BWC rule: drain failed (%d), attempting to move rest of the rules\n", - ret); - drain_error = true; + if (unlikely(ret)) { + if (ret == -ETIMEDOUT) { + mlx5hws_err(ctx, + "Moving bwc rule: timeout draining completions (%d), aborting rehash\n", + ret); + return ret; + } + if (!drain_error) { + mlx5hws_err(ctx, + "Moving bwc rule: drain failed (%d), attempting to move rest of the rules\n", + ret); + drain_error = ret; + } } } } - if (move_error || poll_error || drain_error) - ret = -EINVAL; + /* Return the first error that happened */ + if (unlikely(move_error)) + return move_error; + if (unlikely(poll_error)) + return poll_error; + if (unlikely(drain_error)) + return drain_error; return ret; } @@ -1035,6 +1063,21 @@ int mlx5hws_bwc_rule_create_simple(struct mlx5hws_bwc_rule *bwc_rule, return 0; /* rule inserted successfully */ } + /* Rule insertion could fail due to queue being full, timeout, or + * matcher in resize. In such cases, no point in trying to rehash. + */ + if (ret == -EBUSY || ret == -ETIMEDOUT || ret == -EAGAIN) { + mutex_unlock(queue_lock); + mlx5hws_err(ctx, + "BWC rule insertion failed - %s (%d)\n", + ret == -EBUSY ? "queue is full" : + ret == -ETIMEDOUT ? "timeout" : + ret == -EAGAIN ? "matcher in resize" : "N/A", + ret); + hws_bwc_rule_cnt_dec(bwc_rule); + return ret; + } + /* At this point the rule wasn't added. * It could be because there was collision, or some other problem. * Try rehash by size and insert rule again - last chance. diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc_complex.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc_complex.c index ca7501c57468..14e79579c719 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc_complex.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc_complex.c @@ -1328,11 +1328,11 @@ mlx5hws_bwc_matcher_move_all_complex(struct mlx5hws_bwc_matcher *bwc_matcher) { struct mlx5hws_context *ctx = bwc_matcher->matcher->tbl->ctx; struct mlx5hws_matcher *matcher = bwc_matcher->matcher; - bool move_error = false, poll_error = false; u16 bwc_queues = mlx5hws_bwc_queues(ctx); struct mlx5hws_bwc_rule *tmp_bwc_rule; struct mlx5hws_rule_attr rule_attr; struct mlx5hws_table *isolated_tbl; + int move_error = 0, poll_error = 0; struct mlx5hws_rule *tmp_rule; struct list_head *rules_list; u32 expected_completions = 1; @@ -1391,11 +1391,15 @@ mlx5hws_bwc_matcher_move_all_complex(struct mlx5hws_bwc_matcher *bwc_matcher) ret = mlx5hws_matcher_resize_rule_move(matcher, tmp_rule, &rule_attr); - if (unlikely(ret && !move_error)) { - mlx5hws_err(ctx, - "Moving complex BWC rule failed (%d), attempting to move rest of the rules\n", - ret); - move_error = true; + if (unlikely(ret)) { + if (!move_error) { + mlx5hws_err(ctx, + "Moving complex BWC rule: move failed (%d), attempting to move rest of the rules\n", + ret); + move_error = ret; + } + /* Rule wasn't queued, no need to poll */ + continue; } expected_completions = 1; @@ -1403,11 +1407,19 @@ mlx5hws_bwc_matcher_move_all_complex(struct mlx5hws_bwc_matcher *bwc_matcher) rule_attr.queue_id, &expected_completions, true); - if (unlikely(ret && !poll_error)) { - mlx5hws_err(ctx, - "Moving complex BWC rule: poll failed (%d), attempting to move rest of the rules\n", - ret); - poll_error = true; + if (unlikely(ret)) { + if (ret == -ETIMEDOUT) { + mlx5hws_err(ctx, + "Moving complex BWC rule: timeout polling for completions (%d), aborting rehash\n", + ret); + return ret; + } + if (!poll_error) { + mlx5hws_err(ctx, + "Moving complex BWC rule: polling for completions failed (%d), attempting to move rest of the rules\n", + ret); + poll_error = ret; + } } /* Done moving the rule to the new matcher, @@ -1422,8 +1434,11 @@ mlx5hws_bwc_matcher_move_all_complex(struct mlx5hws_bwc_matcher *bwc_matcher) } } - if (move_error || poll_error) - ret = -EINVAL; + /* Return the first error that happened */ + if (unlikely(move_error)) + return move_error; + if (unlikely(poll_error)) + return poll_error; return ret; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/cmd.c index 9c83753e4592..0bdcab2e5cf3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/cmd.c @@ -55,6 +55,7 @@ int mlx5hws_cmd_flow_table_create(struct mlx5_core_dev *mdev, MLX5_SET(create_flow_table_in, in, opcode, MLX5_CMD_OP_CREATE_FLOW_TABLE); MLX5_SET(create_flow_table_in, in, table_type, ft_attr->type); + MLX5_SET(create_flow_table_in, in, uid, ft_attr->uid); ft_ctx = MLX5_ADDR_OF(create_flow_table_in, in, flow_table_context); MLX5_SET(flow_table_context, ft_ctx, level, ft_attr->level); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/cmd.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/cmd.h index fa6bff210266..122ccc671628 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/cmd.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/cmd.h @@ -36,6 +36,7 @@ struct mlx5hws_cmd_set_fte_attr { struct mlx5hws_cmd_ft_create_attr { u8 type; u8 level; + u16 uid; bool rtc_valid; bool decap_en; bool reformat_en; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws.c index 57592b92e24b..131e74b2b774 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws.c @@ -267,6 +267,7 @@ static int mlx5_cmd_hws_create_flow_table(struct mlx5_flow_root_namespace *ns, tbl_attr.type = MLX5HWS_TABLE_TYPE_FDB; tbl_attr.level = ft_attr->level; + tbl_attr.uid = ft_attr->uid; tbl = mlx5hws_table_create(ctx, &tbl_attr); if (!tbl) { mlx5_core_err(ns->dev, "Failed creating hws flow_table\n"); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/matcher.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/matcher.c index f3ea09caba2b..32f87fdf3213 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/matcher.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/matcher.c @@ -85,6 +85,7 @@ static int hws_matcher_create_end_ft_isolated(struct mlx5hws_matcher *matcher) ret = mlx5hws_table_create_default_ft(tbl->ctx->mdev, tbl, + 0, &matcher->end_ft_id); if (ret) { mlx5hws_err(tbl->ctx, "Isolated matcher: failed to create end flow table\n"); @@ -112,7 +113,9 @@ static int hws_matcher_create_end_ft(struct mlx5hws_matcher *matcher) if (mlx5hws_matcher_is_isolated(matcher)) ret = hws_matcher_create_end_ft_isolated(matcher); else - ret = mlx5hws_table_create_default_ft(tbl->ctx->mdev, tbl, + ret = mlx5hws_table_create_default_ft(tbl->ctx->mdev, + tbl, + 0, &matcher->end_ft_id); if (ret) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws.h index 59c14745ed0c..2498ceff2060 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws.h @@ -75,6 +75,7 @@ struct mlx5hws_context_attr { struct mlx5hws_table_attr { enum mlx5hws_table_type type; u32 level; + u16 uid; }; enum mlx5hws_matcher_flow_src { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/send.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/send.c index c4b22be19a9b..b0595c9b09e4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/send.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/send.c @@ -964,7 +964,6 @@ static int hws_send_ring_open_cq(struct mlx5_core_dev *mdev, return -ENOMEM; MLX5_SET(cqc, cqc_data, uar_page, mdev->priv.uar->index); - MLX5_SET(cqc, cqc_data, cqe_sz, queue->num_entries); MLX5_SET(cqc, cqc_data, log_cq_size, ilog2(queue->num_entries)); err = hws_send_ring_alloc_cq(mdev, numa_node, queue, cqc_data, cq); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/table.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/table.c index 568f691733f3..6113383ae47b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/table.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/table.c @@ -9,6 +9,7 @@ u32 mlx5hws_table_get_id(struct mlx5hws_table *tbl) } static void hws_table_init_next_ft_attr(struct mlx5hws_table *tbl, + u16 uid, struct mlx5hws_cmd_ft_create_attr *ft_attr) { ft_attr->type = tbl->fw_ft_type; @@ -16,7 +17,9 @@ static void hws_table_init_next_ft_attr(struct mlx5hws_table *tbl, ft_attr->level = tbl->ctx->caps->fdb_ft.max_level - 1; else ft_attr->level = tbl->ctx->caps->nic_ft.max_level - 1; + ft_attr->rtc_valid = true; + ft_attr->uid = uid; } static void hws_table_set_cap_attr(struct mlx5hws_table *tbl, @@ -119,12 +122,12 @@ static int hws_table_connect_to_default_miss_tbl(struct mlx5hws_table *tbl, u32 int mlx5hws_table_create_default_ft(struct mlx5_core_dev *mdev, struct mlx5hws_table *tbl, - u32 *ft_id) + u16 uid, u32 *ft_id) { struct mlx5hws_cmd_ft_create_attr ft_attr = {0}; int ret; - hws_table_init_next_ft_attr(tbl, &ft_attr); + hws_table_init_next_ft_attr(tbl, uid, &ft_attr); hws_table_set_cap_attr(tbl, &ft_attr); ret = mlx5hws_cmd_flow_table_create(mdev, &ft_attr, ft_id); @@ -189,7 +192,10 @@ static int hws_table_init(struct mlx5hws_table *tbl) } mutex_lock(&ctx->ctrl_lock); - ret = mlx5hws_table_create_default_ft(tbl->ctx->mdev, tbl, &tbl->ft_id); + ret = mlx5hws_table_create_default_ft(tbl->ctx->mdev, + tbl, + tbl->uid, + &tbl->ft_id); if (ret) { mlx5hws_err(tbl->ctx, "Failed to create flow table object\n"); mutex_unlock(&ctx->ctrl_lock); @@ -239,6 +245,7 @@ struct mlx5hws_table *mlx5hws_table_create(struct mlx5hws_context *ctx, tbl->ctx = ctx; tbl->type = attr->type; tbl->level = attr->level; + tbl->uid = attr->uid; ret = hws_table_init(tbl); if (ret) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/table.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/table.h index 0400cce0c317..1246f9bd8422 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/table.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/table.h @@ -18,6 +18,7 @@ struct mlx5hws_table { enum mlx5hws_table_type type; u32 fw_ft_type; u32 level; + u16 uid; struct list_head matchers_list; struct list_head tbl_list_node; struct mlx5hws_default_miss default_miss; @@ -47,7 +48,7 @@ u32 mlx5hws_table_get_res_fw_ft_type(enum mlx5hws_table_type tbl_type, int mlx5hws_table_create_default_ft(struct mlx5_core_dev *mdev, struct mlx5hws_table *tbl, - u32 *ft_id); + u16 uid, u32 *ft_id); void mlx5hws_table_destroy_default_ft(struct mlx5hws_table *tbl, u32 ft_id); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 618957d65663..9a2d64a0a858 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -2375,6 +2375,8 @@ static const struct mlxsw_listener mlxsw_sp_listener[] = { ROUTER_EXP, false), MLXSW_SP_RXL_NO_MARK(DISCARD_ING_ROUTER_DIP_LINK_LOCAL, FORWARD, ROUTER_EXP, false), + MLXSW_SP_RXL_NO_MARK(DISCARD_ING_ROUTER_SIP_LINK_LOCAL, FORWARD, + ROUTER_EXP, false), /* Multicast Router Traps */ MLXSW_SP_RXL_MARK(ACL1, TRAP_TO_CPU, MULTICAST, false), MLXSW_SP_RXL_L3_MARK(ACL2, TRAP_TO_CPU, MULTICAST, false), diff --git a/drivers/net/ethernet/mellanox/mlxsw/trap.h b/drivers/net/ethernet/mellanox/mlxsw/trap.h index 80ee5c4825dc..9962dc157901 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/trap.h +++ b/drivers/net/ethernet/mellanox/mlxsw/trap.h @@ -94,6 +94,7 @@ enum { MLXSW_TRAP_ID_DISCARD_ING_ROUTER_IPV4_SIP_BC = 0x16A, MLXSW_TRAP_ID_DISCARD_ING_ROUTER_IPV4_DIP_LOCAL_NET = 0x16B, MLXSW_TRAP_ID_DISCARD_ING_ROUTER_DIP_LINK_LOCAL = 0x16C, + MLXSW_TRAP_ID_DISCARD_ING_ROUTER_SIP_LINK_LOCAL = 0x16D, MLXSW_TRAP_ID_DISCARD_ROUTER_IRIF_EN = 0x178, MLXSW_TRAP_ID_DISCARD_ROUTER_ERIF_EN = 0x179, MLXSW_TRAP_ID_DISCARD_ROUTER_LPM4 = 0x17B, diff --git a/drivers/net/ethernet/microchip/lan865x/lan865x.c b/drivers/net/ethernet/microchip/lan865x/lan865x.c index dd436bdff0f8..84c41f193561 100644 --- a/drivers/net/ethernet/microchip/lan865x/lan865x.c +++ b/drivers/net/ethernet/microchip/lan865x/lan865x.c @@ -32,6 +32,10 @@ /* MAC Specific Addr 1 Top Reg */ #define LAN865X_REG_MAC_H_SADDR1 0x00010023 +/* MAC TSU Timer Increment Register */ +#define LAN865X_REG_MAC_TSU_TIMER_INCR 0x00010077 +#define MAC_TSU_TIMER_INCR_COUNT_NANOSECONDS 0x0028 + struct lan865x_priv { struct work_struct multicast_work; struct net_device *netdev; @@ -311,6 +315,8 @@ static int lan865x_net_open(struct net_device *netdev) phy_start(netdev->phydev); + netif_start_queue(netdev); + return 0; } @@ -344,6 +350,21 @@ static int lan865x_probe(struct spi_device *spi) goto free_netdev; } + /* LAN865x Rev.B0/B1 configuration parameters from AN1760 + * As per the Configuration Application Note AN1760 published in the + * link, https://www.microchip.com/en-us/application-notes/an1760 + * Revision F (DS60001760G - June 2024), configure the MAC to set time + * stamping at the end of the Start of Frame Delimiter (SFD) and set the + * Timer Increment reg to 40 ns to be used as a 25 MHz internal clock. + */ + ret = oa_tc6_write_register(priv->tc6, LAN865X_REG_MAC_TSU_TIMER_INCR, + MAC_TSU_TIMER_INCR_COUNT_NANOSECONDS); + if (ret) { + dev_err(&spi->dev, "Failed to config TSU Timer Incr reg: %d\n", + ret); + goto oa_tc6_exit; + } + /* As per the point s3 in the below errata, SPI receive Ethernet frame * transfer may halt when starting the next frame in the same data block * (chunk) as the end of a previous frame. The RFA field should be diff --git a/drivers/net/ethernet/realtek/rtase/rtase.h b/drivers/net/ethernet/realtek/rtase/rtase.h index 20decdeb9fdb..b9209eb6ea73 100644 --- a/drivers/net/ethernet/realtek/rtase/rtase.h +++ b/drivers/net/ethernet/realtek/rtase/rtase.h @@ -241,7 +241,7 @@ union rtase_rx_desc { #define RTASE_RX_RES BIT(20) #define RTASE_RX_RUNT BIT(19) #define RTASE_RX_RWT BIT(18) -#define RTASE_RX_CRC BIT(16) +#define RTASE_RX_CRC BIT(17) #define RTASE_RX_V6F BIT(31) #define RTASE_RX_V4F BIT(30) #define RTASE_RX_UDPT BIT(29) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c index 09ae16e026eb..6c363f9b0ce2 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c @@ -330,15 +330,11 @@ static int dwc_eth_dwmac_probe(struct platform_device *pdev) if (IS_ERR(plat_dat)) return PTR_ERR(plat_dat); - ret = devm_clk_bulk_get_all(&pdev->dev, &plat_dat->clks); + ret = devm_clk_bulk_get_all_enabled(&pdev->dev, &plat_dat->clks); if (ret < 0) - return dev_err_probe(&pdev->dev, ret, "Failed to retrieve all required clocks\n"); + return dev_err_probe(&pdev->dev, ret, "Failed to retrieve and enable all required clocks\n"); plat_dat->num_clks = ret; - ret = clk_bulk_prepare_enable(plat_dat->num_clks, plat_dat->clks); - if (ret) - return dev_err_probe(&pdev->dev, ret, "Failed to enable clocks\n"); - plat_dat->stmmac_clk = stmmac_pltfr_find_clk(plat_dat, data->stmmac_clk_name); @@ -346,7 +342,6 @@ static int dwc_eth_dwmac_probe(struct platform_device *pdev) ret = data->probe(pdev, plat_dat, &stmmac_res); if (ret < 0) { dev_err_probe(&pdev->dev, ret, "failed to probe subdriver\n"); - clk_bulk_disable_unprepare(plat_dat->num_clks, plat_dat->clks); return ret; } @@ -370,15 +365,11 @@ remove: static void dwc_eth_dwmac_remove(struct platform_device *pdev) { const struct dwc_eth_dwmac_data *data = device_get_match_data(&pdev->dev); - struct plat_stmmacenet_data *plat_dat = dev_get_platdata(&pdev->dev); stmmac_dvr_remove(&pdev->dev); if (data->remove) data->remove(pdev); - - if (plat_dat) - clk_bulk_disable_unprepare(plat_dat->num_clks, plat_dat->clks); } static const struct of_device_id dwc_eth_dwmac_match[] = { diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c index 79b92130a03f..f6687c2f30f6 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c @@ -1765,11 +1765,15 @@ err_gmac_powerdown: static void rk_gmac_remove(struct platform_device *pdev) { - struct rk_priv_data *bsp_priv = get_stmmac_bsp_priv(&pdev->dev); + struct stmmac_priv *priv = netdev_priv(platform_get_drvdata(pdev)); + struct rk_priv_data *bsp_priv = priv->plat->bsp_priv; stmmac_dvr_remove(&pdev->dev); rk_gmac_powerdown(bsp_priv); + + if (priv->plat->phy_node && bsp_priv->integrated_phy) + clk_put(bsp_priv->clk_phy); } #ifdef CONFIG_PM_SLEEP diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-thead.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-thead.c index c72ee759aae5..6c6c49e4b66f 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-thead.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-thead.c @@ -152,7 +152,7 @@ static int thead_set_clk_tx_rate(void *bsp_priv, struct clk *clk_tx_i, static int thead_dwmac_enable_clk(struct plat_stmmacenet_data *plat) { struct thead_dwmac *dwmac = plat->bsp_priv; - u32 reg; + u32 reg, div; switch (plat->mac_interface) { case PHY_INTERFACE_MODE_MII: @@ -164,6 +164,13 @@ static int thead_dwmac_enable_clk(struct plat_stmmacenet_data *plat) case PHY_INTERFACE_MODE_RGMII_RXID: case PHY_INTERFACE_MODE_RGMII_TXID: /* use pll */ + div = clk_get_rate(plat->stmmac_clk) / rgmii_clock(SPEED_1000); + reg = FIELD_PREP(GMAC_PLLCLK_DIV_EN, 1) | + FIELD_PREP(GMAC_PLLCLK_DIV_NUM, div); + + writel(0, dwmac->apb_base + GMAC_PLLCLK_DIV); + writel(reg, dwmac->apb_base + GMAC_PLLCLK_DIV); + writel(GMAC_GTXCLK_SEL_PLL, dwmac->apb_base + GMAC_GTXCLK_SEL); reg = GMAC_TX_CLK_EN | GMAC_TX_CLK_N_EN | GMAC_TX_CLK_OUT_EN | GMAC_RX_CLK_EN | GMAC_RX_CLK_N_EN; @@ -211,6 +218,7 @@ static int thead_dwmac_probe(struct platform_device *pdev) struct stmmac_resources stmmac_res; struct plat_stmmacenet_data *plat; struct thead_dwmac *dwmac; + struct clk *apb_clk; void __iomem *apb; int ret; @@ -224,6 +232,19 @@ static int thead_dwmac_probe(struct platform_device *pdev) return dev_err_probe(&pdev->dev, PTR_ERR(plat), "dt configuration failed\n"); + /* + * The APB clock is essential for accessing glue registers. However, + * old devicetrees don't describe it correctly. We continue to probe + * and emit a warning if it isn't present. + */ + apb_clk = devm_clk_get_enabled(&pdev->dev, "apb"); + if (PTR_ERR(apb_clk) == -ENOENT) + dev_warn(&pdev->dev, + "cannot get apb clock, link may break after speed changes\n"); + else if (IS_ERR(apb_clk)) + return dev_err_probe(&pdev->dev, PTR_ERR(apb_clk), + "failed to get apb clock\n"); + dwmac = devm_kzalloc(&pdev->dev, sizeof(*dwmac), GFP_KERNEL); if (!dwmac) return -ENOMEM; diff --git a/drivers/net/ethernet/ti/icssg/icss_iep.c b/drivers/net/ethernet/ti/icssg/icss_iep.c index 50bfbc2779e4..d8c9fe1d98c4 100644 --- a/drivers/net/ethernet/ti/icssg/icss_iep.c +++ b/drivers/net/ethernet/ti/icssg/icss_iep.c @@ -621,7 +621,8 @@ exit: static int icss_iep_extts_enable(struct icss_iep *iep, u32 index, int on) { - u32 val, cap, ret = 0; + u32 val, cap; + int ret = 0; mutex_lock(&iep->ptp_clk_mutex); diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.c b/drivers/net/ethernet/ti/icssg/icssg_prueth.c index 2b973d6e2341..dadce6009791 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_prueth.c +++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.c @@ -50,6 +50,8 @@ /* CTRLMMR_ICSSG_RGMII_CTRL register bits */ #define ICSSG_CTRL_RGMII_ID_MODE BIT(24) +static void emac_adjust_link(struct net_device *ndev); + static int emac_get_tx_ts(struct prueth_emac *emac, struct emac_tx_ts_response *rsp) { @@ -201,6 +203,44 @@ static void prueth_emac_stop(struct prueth *prueth) } } +static void icssg_enable_fw_offload(struct prueth *prueth) +{ + struct prueth_emac *emac; + int mac; + + for (mac = PRUETH_MAC0; mac < PRUETH_NUM_MACS; mac++) { + emac = prueth->emac[mac]; + if (prueth->is_hsr_offload_mode) { + if (emac->ndev->features & NETIF_F_HW_HSR_TAG_RM) + icssg_set_port_state(emac, ICSSG_EMAC_HSR_RX_OFFLOAD_ENABLE); + else + icssg_set_port_state(emac, ICSSG_EMAC_HSR_RX_OFFLOAD_DISABLE); + } + + if (prueth->is_switch_mode || prueth->is_hsr_offload_mode) { + if (netif_running(emac->ndev)) { + icssg_fdb_add_del(emac, eth_stp_addr, prueth->default_vlan, + ICSSG_FDB_ENTRY_P0_MEMBERSHIP | + ICSSG_FDB_ENTRY_P1_MEMBERSHIP | + ICSSG_FDB_ENTRY_P2_MEMBERSHIP | + ICSSG_FDB_ENTRY_BLOCK, + true); + icssg_vtbl_modify(emac, emac->port_vlan | DEFAULT_VID, + BIT(emac->port_id) | DEFAULT_PORT_MASK, + BIT(emac->port_id) | DEFAULT_UNTAG_MASK, + true); + if (prueth->is_hsr_offload_mode) + icssg_vtbl_modify(emac, DEFAULT_VID, + DEFAULT_PORT_MASK, + DEFAULT_UNTAG_MASK, true); + icssg_set_pvid(prueth, emac->port_vlan, emac->port_id); + if (prueth->is_switch_mode) + icssg_set_port_state(emac, ICSSG_EMAC_PORT_VLAN_AWARE_ENABLE); + } + } + } +} + static int prueth_emac_common_start(struct prueth *prueth) { struct prueth_emac *emac; @@ -229,6 +269,10 @@ static int prueth_emac_common_start(struct prueth *prueth) ret = icssg_config(prueth, emac, slice); if (ret) goto disable_class; + + mutex_lock(&emac->ndev->phydev->lock); + emac_adjust_link(emac->ndev); + mutex_unlock(&emac->ndev->phydev->lock); } ret = prueth_emac_start(prueth); @@ -747,6 +791,7 @@ static int emac_ndo_open(struct net_device *ndev) ret = prueth_emac_common_start(prueth); if (ret) goto free_rx_irq; + icssg_enable_fw_offload(prueth); } flow_cfg = emac->dram.va + ICSSG_CONFIG_OFFSET + PSI_L_REGULAR_FLOW_ID_BASE_OFFSET; @@ -1354,8 +1399,7 @@ static int prueth_emac_restart(struct prueth *prueth) static void icssg_change_mode(struct prueth *prueth) { - struct prueth_emac *emac; - int mac, ret; + int ret; ret = prueth_emac_restart(prueth); if (ret) { @@ -1363,35 +1407,7 @@ static void icssg_change_mode(struct prueth *prueth) return; } - for (mac = PRUETH_MAC0; mac < PRUETH_NUM_MACS; mac++) { - emac = prueth->emac[mac]; - if (prueth->is_hsr_offload_mode) { - if (emac->ndev->features & NETIF_F_HW_HSR_TAG_RM) - icssg_set_port_state(emac, ICSSG_EMAC_HSR_RX_OFFLOAD_ENABLE); - else - icssg_set_port_state(emac, ICSSG_EMAC_HSR_RX_OFFLOAD_DISABLE); - } - - if (netif_running(emac->ndev)) { - icssg_fdb_add_del(emac, eth_stp_addr, prueth->default_vlan, - ICSSG_FDB_ENTRY_P0_MEMBERSHIP | - ICSSG_FDB_ENTRY_P1_MEMBERSHIP | - ICSSG_FDB_ENTRY_P2_MEMBERSHIP | - ICSSG_FDB_ENTRY_BLOCK, - true); - icssg_vtbl_modify(emac, emac->port_vlan | DEFAULT_VID, - BIT(emac->port_id) | DEFAULT_PORT_MASK, - BIT(emac->port_id) | DEFAULT_UNTAG_MASK, - true); - if (prueth->is_hsr_offload_mode) - icssg_vtbl_modify(emac, DEFAULT_VID, - DEFAULT_PORT_MASK, - DEFAULT_UNTAG_MASK, true); - icssg_set_pvid(prueth, emac->port_vlan, emac->port_id); - if (prueth->is_switch_mode) - icssg_set_port_state(emac, ICSSG_EMAC_PORT_VLAN_AWARE_ENABLE); - } - } + icssg_enable_fw_offload(prueth); } static int prueth_netdevice_port_link(struct net_device *ndev, diff --git a/drivers/net/ethernet/wangxun/libwx/wx_vf_lib.c b/drivers/net/ethernet/wangxun/libwx/wx_vf_lib.c index 5d48df7a849f..3023ea2732ef 100644 --- a/drivers/net/ethernet/wangxun/libwx/wx_vf_lib.c +++ b/drivers/net/ethernet/wangxun/libwx/wx_vf_lib.c @@ -192,7 +192,7 @@ void wx_setup_vfmrqc_vf(struct wx *wx) u8 i, j; /* Fill out hash function seeds */ - netdev_rss_key_fill(wx->rss_key, sizeof(wx->rss_key)); + netdev_rss_key_fill(wx->rss_key, WX_RSS_KEY_SIZE); for (i = 0; i < WX_RSS_KEY_SIZE / 4; i++) wr32(wx, WX_VXRSSRK(i), wx->rss_key[i]); diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c index 6011d7eae0c7..0d8a05fe541a 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c +++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c @@ -1160,6 +1160,7 @@ static void axienet_dma_rx_cb(void *data, const struct dmaengine_result *result) struct axienet_local *lp = data; struct sk_buff *skb; u32 *app_metadata; + int i; skbuf_dma = axienet_get_rx_desc(lp, lp->rx_ring_tail++); skb = skbuf_dma->skb; @@ -1178,7 +1179,10 @@ static void axienet_dma_rx_cb(void *data, const struct dmaengine_result *result) u64_stats_add(&lp->rx_packets, 1); u64_stats_add(&lp->rx_bytes, rx_len); u64_stats_update_end(&lp->rx_stat_sync); - axienet_rx_submit_desc(lp->ndev); + + for (i = 0; i < CIRC_SPACE(lp->rx_ring_head, lp->rx_ring_tail, + RX_BUF_NUM_DEFAULT); i++) + axienet_rx_submit_desc(lp->ndev); dma_async_issue_pending(lp->rx_chan); } @@ -1457,7 +1461,6 @@ static void axienet_rx_submit_desc(struct net_device *ndev) if (!skbuf_dma) return; - lp->rx_ring_head++; skb = netdev_alloc_skb(ndev, lp->max_frm_size); if (!skb) return; @@ -1482,6 +1485,7 @@ static void axienet_rx_submit_desc(struct net_device *ndev) skbuf_dma->desc = dma_rx_desc; dma_rx_desc->callback_param = lp; dma_rx_desc->callback_result = axienet_dma_rx_cb; + lp->rx_ring_head++; dmaengine_submit(dma_rx_desc); return; diff --git a/drivers/net/hamradio/bpqether.c b/drivers/net/hamradio/bpqether.c index 0e0fe32d2da4..045c5177262e 100644 --- a/drivers/net/hamradio/bpqether.c +++ b/drivers/net/hamradio/bpqether.c @@ -138,7 +138,7 @@ static inline struct net_device *bpq_get_ax25_dev(struct net_device *dev) static inline int dev_is_ethdev(struct net_device *dev) { - return dev->type == ARPHRD_ETHER && strncmp(dev->name, "dummy", 5); + return dev->type == ARPHRD_ETHER && !netdev_need_ops_lock(dev); } /* ------------------------------------------------------------------------ */ diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h index cb6f5482d203..7397c693f984 100644 --- a/drivers/net/hyperv/hyperv_net.h +++ b/drivers/net/hyperv/hyperv_net.h @@ -1061,6 +1061,7 @@ struct net_device_context { struct net_device __rcu *vf_netdev; struct netvsc_vf_pcpu_stats __percpu *vf_stats; struct delayed_work vf_takeover; + struct delayed_work vfns_work; /* 1: allocated, serial number is valid. 0: not allocated */ u32 vf_alloc; @@ -1075,6 +1076,8 @@ struct net_device_context { struct netvsc_device_info *saved_netvsc_dev_info; }; +void netvsc_vfns_work(struct work_struct *w); + /* Azure hosts don't support non-TCP port numbers in hashing for fragmented * packets. We can use ethtool to change UDP hash level when necessary. */ diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index f44753756358..39c892e46cb0 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -2522,6 +2522,7 @@ static int netvsc_probe(struct hv_device *dev, spin_lock_init(&net_device_ctx->lock); INIT_LIST_HEAD(&net_device_ctx->reconfig_events); INIT_DELAYED_WORK(&net_device_ctx->vf_takeover, netvsc_vf_setup); + INIT_DELAYED_WORK(&net_device_ctx->vfns_work, netvsc_vfns_work); net_device_ctx->vf_stats = netdev_alloc_pcpu_stats(struct netvsc_vf_pcpu_stats); @@ -2666,6 +2667,8 @@ static void netvsc_remove(struct hv_device *dev) cancel_delayed_work_sync(&ndev_ctx->dwork); rtnl_lock(); + cancel_delayed_work_sync(&ndev_ctx->vfns_work); + nvdev = rtnl_dereference(ndev_ctx->nvdev); if (nvdev) { cancel_work_sync(&nvdev->subchan_work); @@ -2707,6 +2710,7 @@ static int netvsc_suspend(struct hv_device *dev) cancel_delayed_work_sync(&ndev_ctx->dwork); rtnl_lock(); + cancel_delayed_work_sync(&ndev_ctx->vfns_work); nvdev = rtnl_dereference(ndev_ctx->nvdev); if (nvdev == NULL) { @@ -2800,6 +2804,27 @@ static void netvsc_event_set_vf_ns(struct net_device *ndev) } } +void netvsc_vfns_work(struct work_struct *w) +{ + struct net_device_context *ndev_ctx = + container_of(w, struct net_device_context, vfns_work.work); + struct net_device *ndev; + + if (!rtnl_trylock()) { + schedule_delayed_work(&ndev_ctx->vfns_work, 1); + return; + } + + ndev = hv_get_drvdata(ndev_ctx->device_ctx); + if (!ndev) + goto out; + + netvsc_event_set_vf_ns(ndev); + +out: + rtnl_unlock(); +} + /* * On Hyper-V, every VF interface is matched with a corresponding * synthetic interface. The synthetic interface is presented first @@ -2810,10 +2835,12 @@ static int netvsc_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *event_dev = netdev_notifier_info_to_dev(ptr); + struct net_device_context *ndev_ctx; int ret = 0; if (event_dev->netdev_ops == &device_ops && event == NETDEV_REGISTER) { - netvsc_event_set_vf_ns(event_dev); + ndev_ctx = netdev_priv(event_dev); + schedule_delayed_work(&ndev_ctx->vfns_work, 0); return NOTIFY_DONE; } diff --git a/drivers/net/netdevsim/netdev.c b/drivers/net/netdevsim/netdev.c index 39fe28af48b9..0178219f0db5 100644 --- a/drivers/net/netdevsim/netdev.c +++ b/drivers/net/netdevsim/netdev.c @@ -710,9 +710,13 @@ static struct nsim_rq *nsim_queue_alloc(void) static void nsim_queue_free(struct net_device *dev, struct nsim_rq *rq) { hrtimer_cancel(&rq->napi_timer); - local_bh_disable(); - dev_dstats_rx_dropped_add(dev, rq->skb_queue.qlen); - local_bh_enable(); + + if (rq->skb_queue.qlen) { + local_bh_disable(); + dev_dstats_rx_dropped_add(dev, rq->skb_queue.qlen); + local_bh_enable(); + } + skb_queue_purge_reason(&rq->skb_queue, SKB_DROP_REASON_QUEUE_PURGE); kfree(rq); } diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c index fda2e27c1810..cad6ed3aa10b 100644 --- a/drivers/net/phy/mdio_bus.c +++ b/drivers/net/phy/mdio_bus.c @@ -91,6 +91,7 @@ int mdiobus_unregister_device(struct mdio_device *mdiodev) if (mdiodev->bus->mdio_map[mdiodev->addr] != mdiodev) return -EINVAL; + gpiod_put(mdiodev->reset_gpio); reset_control_put(mdiodev->reset_ctrl); mdiodev->bus->mdio_map[mdiodev->addr] = NULL; diff --git a/drivers/net/phy/mdio_bus_provider.c b/drivers/net/phy/mdio_bus_provider.c index 48dc4bf85125..f43973e73ea3 100644 --- a/drivers/net/phy/mdio_bus_provider.c +++ b/drivers/net/phy/mdio_bus_provider.c @@ -443,9 +443,6 @@ void mdiobus_unregister(struct mii_bus *bus) if (!mdiodev) continue; - if (mdiodev->reset_gpio) - gpiod_put(mdiodev->reset_gpio); - mdiodev->device_remove(mdiodev); mdiodev->device_free(mdiodev); } diff --git a/drivers/net/phy/mscc/mscc.h b/drivers/net/phy/mscc/mscc.h index 6a3d8a754eb8..58c6d47fbe04 100644 --- a/drivers/net/phy/mscc/mscc.h +++ b/drivers/net/phy/mscc/mscc.h @@ -362,6 +362,13 @@ struct vsc85xx_hw_stat { u16 mask; }; +struct vsc8531_skb_cb { + u32 ns; +}; + +#define VSC8531_SKB_CB(skb) \ + ((struct vsc8531_skb_cb *)((skb)->cb)) + struct vsc8531_private { int rate_magic; u16 supp_led_modes; @@ -410,6 +417,11 @@ struct vsc8531_private { */ struct mutex ts_lock; struct mutex phc_lock; + + /* list of skbs that were received and need timestamp information but it + * didn't received it yet + */ + struct sk_buff_head rx_skbs_list; }; /* Shared structure between the PHYs of the same package. diff --git a/drivers/net/phy/mscc/mscc_main.c b/drivers/net/phy/mscc/mscc_main.c index 7ed6522fb0ef..f1c9ce351ab4 100644 --- a/drivers/net/phy/mscc/mscc_main.c +++ b/drivers/net/phy/mscc/mscc_main.c @@ -2335,6 +2335,13 @@ static int vsc85xx_probe(struct phy_device *phydev) return vsc85xx_dt_led_modes_get(phydev, default_mode); } +static void vsc85xx_remove(struct phy_device *phydev) +{ + struct vsc8531_private *priv = phydev->priv; + + skb_queue_purge(&priv->rx_skbs_list); +} + /* Microsemi VSC85xx PHYs */ static struct phy_driver vsc85xx_driver[] = { { @@ -2589,6 +2596,7 @@ static struct phy_driver vsc85xx_driver[] = { .config_intr = &vsc85xx_config_intr, .suspend = &genphy_suspend, .resume = &genphy_resume, + .remove = &vsc85xx_remove, .probe = &vsc8574_probe, .set_wol = &vsc85xx_wol_set, .get_wol = &vsc85xx_wol_get, @@ -2614,6 +2622,7 @@ static struct phy_driver vsc85xx_driver[] = { .config_intr = &vsc85xx_config_intr, .suspend = &genphy_suspend, .resume = &genphy_resume, + .remove = &vsc85xx_remove, .probe = &vsc8574_probe, .set_wol = &vsc85xx_wol_set, .get_wol = &vsc85xx_wol_get, @@ -2639,6 +2648,7 @@ static struct phy_driver vsc85xx_driver[] = { .config_intr = &vsc85xx_config_intr, .suspend = &genphy_suspend, .resume = &genphy_resume, + .remove = &vsc85xx_remove, .probe = &vsc8584_probe, .get_tunable = &vsc85xx_get_tunable, .set_tunable = &vsc85xx_set_tunable, @@ -2662,6 +2672,7 @@ static struct phy_driver vsc85xx_driver[] = { .config_intr = &vsc85xx_config_intr, .suspend = &genphy_suspend, .resume = &genphy_resume, + .remove = &vsc85xx_remove, .probe = &vsc8584_probe, .get_tunable = &vsc85xx_get_tunable, .set_tunable = &vsc85xx_set_tunable, @@ -2685,6 +2696,7 @@ static struct phy_driver vsc85xx_driver[] = { .config_intr = &vsc85xx_config_intr, .suspend = &genphy_suspend, .resume = &genphy_resume, + .remove = &vsc85xx_remove, .probe = &vsc8584_probe, .get_tunable = &vsc85xx_get_tunable, .set_tunable = &vsc85xx_set_tunable, diff --git a/drivers/net/phy/mscc/mscc_ptp.c b/drivers/net/phy/mscc/mscc_ptp.c index 275706de5847..de6c7312e8f2 100644 --- a/drivers/net/phy/mscc/mscc_ptp.c +++ b/drivers/net/phy/mscc/mscc_ptp.c @@ -1194,9 +1194,7 @@ static bool vsc85xx_rxtstamp(struct mii_timestamper *mii_ts, { struct vsc8531_private *vsc8531 = container_of(mii_ts, struct vsc8531_private, mii_ts); - struct skb_shared_hwtstamps *shhwtstamps = NULL; struct vsc85xx_ptphdr *ptphdr; - struct timespec64 ts; unsigned long ns; if (!vsc8531->ptp->configured) @@ -1206,27 +1204,52 @@ static bool vsc85xx_rxtstamp(struct mii_timestamper *mii_ts, type == PTP_CLASS_NONE) return false; - vsc85xx_gettime(&vsc8531->ptp->caps, &ts); - ptphdr = get_ptp_header_rx(skb, vsc8531->ptp->rx_filter); if (!ptphdr) return false; - shhwtstamps = skb_hwtstamps(skb); - memset(shhwtstamps, 0, sizeof(struct skb_shared_hwtstamps)); - ns = ntohl(ptphdr->rsrvd2); - /* nsec is in reserved field */ - if (ts.tv_nsec < ns) - ts.tv_sec--; + VSC8531_SKB_CB(skb)->ns = ns; + skb_queue_tail(&vsc8531->rx_skbs_list, skb); - shhwtstamps->hwtstamp = ktime_set(ts.tv_sec, ns); - netif_rx(skb); + ptp_schedule_worker(vsc8531->ptp->ptp_clock, 0); return true; } +static long vsc85xx_do_aux_work(struct ptp_clock_info *info) +{ + struct vsc85xx_ptp *ptp = container_of(info, struct vsc85xx_ptp, caps); + struct skb_shared_hwtstamps *shhwtstamps = NULL; + struct phy_device *phydev = ptp->phydev; + struct vsc8531_private *priv = phydev->priv; + struct sk_buff_head received; + struct sk_buff *rx_skb; + struct timespec64 ts; + unsigned long flags; + + __skb_queue_head_init(&received); + spin_lock_irqsave(&priv->rx_skbs_list.lock, flags); + skb_queue_splice_tail_init(&priv->rx_skbs_list, &received); + spin_unlock_irqrestore(&priv->rx_skbs_list.lock, flags); + + vsc85xx_gettime(info, &ts); + while ((rx_skb = __skb_dequeue(&received)) != NULL) { + shhwtstamps = skb_hwtstamps(rx_skb); + memset(shhwtstamps, 0, sizeof(struct skb_shared_hwtstamps)); + + if (ts.tv_nsec < VSC8531_SKB_CB(rx_skb)->ns) + ts.tv_sec--; + + shhwtstamps->hwtstamp = ktime_set(ts.tv_sec, + VSC8531_SKB_CB(rx_skb)->ns); + netif_rx(rx_skb); + } + + return -1; +} + static const struct ptp_clock_info vsc85xx_clk_caps = { .owner = THIS_MODULE, .name = "VSC85xx timer", @@ -1240,6 +1263,7 @@ static const struct ptp_clock_info vsc85xx_clk_caps = { .adjfine = &vsc85xx_adjfine, .gettime64 = &vsc85xx_gettime, .settime64 = &vsc85xx_settime, + .do_aux_work = &vsc85xx_do_aux_work, }; static struct vsc8531_private *vsc8584_base_priv(struct phy_device *phydev) @@ -1567,6 +1591,7 @@ int vsc8584_ptp_probe(struct phy_device *phydev) mutex_init(&vsc8531->phc_lock); mutex_init(&vsc8531->ts_lock); + skb_queue_head_init(&vsc8531->rx_skbs_list); /* Retrieve the shared load/save GPIO. Request it as non exclusive as * the same GPIO can be requested by all the PHYs of the same package. diff --git a/drivers/net/phy/nxp-c45-tja11xx.c b/drivers/net/phy/nxp-c45-tja11xx.c index 4c6d905f0a9f..87adb6508017 100644 --- a/drivers/net/phy/nxp-c45-tja11xx.c +++ b/drivers/net/phy/nxp-c45-tja11xx.c @@ -1965,24 +1965,27 @@ static int nxp_c45_macsec_ability(struct phy_device *phydev) return macsec_ability; } +static bool tja11xx_phy_id_compare(struct phy_device *phydev, + const struct phy_driver *phydrv) +{ + u32 id = phydev->is_c45 ? phydev->c45_ids.device_ids[MDIO_MMD_PMAPMD] : + phydev->phy_id; + + return phy_id_compare(id, phydrv->phy_id, phydrv->phy_id_mask); +} + static int tja11xx_no_macsec_match_phy_device(struct phy_device *phydev, const struct phy_driver *phydrv) { - if (!phy_id_compare(phydev->phy_id, phydrv->phy_id, - phydrv->phy_id_mask)) - return 0; - - return !nxp_c45_macsec_ability(phydev); + return tja11xx_phy_id_compare(phydev, phydrv) && + !nxp_c45_macsec_ability(phydev); } static int tja11xx_macsec_match_phy_device(struct phy_device *phydev, const struct phy_driver *phydrv) { - if (!phy_id_compare(phydev->phy_id, phydrv->phy_id, - phydrv->phy_id_mask)) - return 0; - - return nxp_c45_macsec_ability(phydev); + return tja11xx_phy_id_compare(phydev, phydrv) && + nxp_c45_macsec_ability(phydev); } static const struct nxp_c45_regmap tja1120_regmap = { diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c index 8c98cbd4b06d..824c8dc4120b 100644 --- a/drivers/net/ppp/ppp_generic.c +++ b/drivers/net/ppp/ppp_generic.c @@ -33,6 +33,7 @@ #include <linux/ppp_channel.h> #include <linux/ppp-comp.h> #include <linux/skbuff.h> +#include <linux/rculist.h> #include <linux/rtnetlink.h> #include <linux/if_arp.h> #include <linux/ip.h> @@ -1598,11 +1599,14 @@ static int ppp_fill_forward_path(struct net_device_path_ctx *ctx, if (ppp->flags & SC_MULTILINK) return -EOPNOTSUPP; - if (list_empty(&ppp->channels)) + pch = list_first_or_null_rcu(&ppp->channels, struct channel, clist); + if (!pch) + return -ENODEV; + + chan = READ_ONCE(pch->chan); + if (!chan) return -ENODEV; - pch = list_first_entry(&ppp->channels, struct channel, clist); - chan = pch->chan; if (!chan->ops->fill_forward_path) return -EOPNOTSUPP; @@ -2994,7 +2998,7 @@ ppp_unregister_channel(struct ppp_channel *chan) */ down_write(&pch->chan_sem); spin_lock_bh(&pch->downl); - pch->chan = NULL; + WRITE_ONCE(pch->chan, NULL); spin_unlock_bh(&pch->downl); up_write(&pch->chan_sem); ppp_disconnect_channel(pch); @@ -3515,7 +3519,7 @@ ppp_connect_channel(struct channel *pch, int unit) hdrlen = pch->file.hdrlen + 2; /* for protocol bytes */ if (hdrlen > ppp->dev->hard_header_len) ppp->dev->hard_header_len = hdrlen; - list_add_tail(&pch->clist, &ppp->channels); + list_add_tail_rcu(&pch->clist, &ppp->channels); ++ppp->n_channels; pch->ppp = ppp; refcount_inc(&ppp->file.refcnt); @@ -3545,10 +3549,11 @@ ppp_disconnect_channel(struct channel *pch) if (ppp) { /* remove it from the ppp unit's list */ ppp_lock(ppp); - list_del(&pch->clist); + list_del_rcu(&pch->clist); if (--ppp->n_channels == 0) wake_up_interruptible(&ppp->file.rwait); ppp_unlock(ppp); + synchronize_net(); if (refcount_dec_and_test(&ppp->file.refcnt)) ppp_destroy_interface(ppp); err = 0; diff --git a/drivers/net/pse-pd/pd692x0.c b/drivers/net/pse-pd/pd692x0.c index 399ce9febda4..f4e91ba64a66 100644 --- a/drivers/net/pse-pd/pd692x0.c +++ b/drivers/net/pse-pd/pd692x0.c @@ -1041,6 +1041,10 @@ pd692x0_configure_managers(struct pd692x0_priv *priv, int nmanagers) int pw_budget; pw_budget = regulator_get_unclaimed_power_budget(supply); + if (!pw_budget) + /* Do nothing if no power budget */ + continue; + /* Max power budget per manager */ if (pw_budget > 6000000) pw_budget = 6000000; @@ -1162,12 +1166,44 @@ pd692x0_write_ports_matrix(struct pd692x0_priv *priv, return 0; } +static void pd692x0_of_put_managers(struct pd692x0_priv *priv, + struct pd692x0_manager *manager, + int nmanagers) +{ + int i, j; + + for (i = 0; i < nmanagers; i++) { + for (j = 0; j < manager[i].nports; j++) + of_node_put(manager[i].port_node[j]); + of_node_put(manager[i].node); + } +} + +static void pd692x0_managers_free_pw_budget(struct pd692x0_priv *priv) +{ + int i; + + for (i = 0; i < PD692X0_MAX_MANAGERS; i++) { + struct regulator *supply; + + if (!priv->manager_reg[i] || !priv->manager_pw_budget[i]) + continue; + + supply = priv->manager_reg[i]->supply; + if (!supply) + continue; + + regulator_free_power_budget(supply, + priv->manager_pw_budget[i]); + } +} + static int pd692x0_setup_pi_matrix(struct pse_controller_dev *pcdev) { struct pd692x0_manager *manager __free(kfree) = NULL; struct pd692x0_priv *priv = to_pd692x0_priv(pcdev); struct pd692x0_matrix port_matrix[PD692X0_MAX_PIS]; - int ret, i, j, nmanagers; + int ret, nmanagers; /* Should we flash the port matrix */ if (priv->fw_state != PD692X0_FW_OK && @@ -1185,31 +1221,27 @@ static int pd692x0_setup_pi_matrix(struct pse_controller_dev *pcdev) nmanagers = ret; ret = pd692x0_register_managers_regulator(priv, manager, nmanagers); if (ret) - goto out; + goto err_of_managers; ret = pd692x0_configure_managers(priv, nmanagers); if (ret) - goto out; + goto err_of_managers; ret = pd692x0_set_ports_matrix(priv, manager, nmanagers, port_matrix); if (ret) - goto out; + goto err_managers_req_pw; ret = pd692x0_write_ports_matrix(priv, port_matrix); if (ret) - goto out; - -out: - for (i = 0; i < nmanagers; i++) { - struct regulator *supply = priv->manager_reg[i]->supply; + goto err_managers_req_pw; - regulator_free_power_budget(supply, - priv->manager_pw_budget[i]); + pd692x0_of_put_managers(priv, manager, nmanagers); + return 0; - for (j = 0; j < manager[i].nports; j++) - of_node_put(manager[i].port_node[j]); - of_node_put(manager[i].node); - } +err_managers_req_pw: + pd692x0_managers_free_pw_budget(priv); +err_of_managers: + pd692x0_of_put_managers(priv, manager, nmanagers); return ret; } @@ -1748,6 +1780,7 @@ static void pd692x0_i2c_remove(struct i2c_client *client) { struct pd692x0_priv *priv = i2c_get_clientdata(client); + pd692x0_managers_free_pw_budget(priv); firmware_upload_unregister(priv->fwl); } diff --git a/drivers/net/usb/asix_devices.c b/drivers/net/usb/asix_devices.c index 9b0318fb50b5..792ddda1ad49 100644 --- a/drivers/net/usb/asix_devices.c +++ b/drivers/net/usb/asix_devices.c @@ -676,6 +676,7 @@ static int ax88772_init_mdio(struct usbnet *dev) priv->mdio->read = &asix_mdio_bus_read; priv->mdio->write = &asix_mdio_bus_write; priv->mdio->name = "Asix MDIO Bus"; + priv->mdio->phy_mask = ~(BIT(priv->phy_addr & 0x1f) | BIT(AX_EMBD_PHY_ADDR)); /* mii bus name is usb-<usb bus number>-<usb device number> */ snprintf(priv->mdio->id, MII_BUS_ID_SIZE, "usb-%03d:%03d", dev->udev->bus->busnum, dev->udev->devnum); diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c index ea0e5e276cd6..5d123df0a866 100644 --- a/drivers/net/usb/cdc_ncm.c +++ b/drivers/net/usb/cdc_ncm.c @@ -2087,6 +2087,13 @@ static const struct usb_device_id cdc_devs[] = { .driver_info = (unsigned long)&wwan_info, }, + /* Intel modem (label from OEM reads Fibocom L850-GL) */ + { USB_DEVICE_AND_INTERFACE_INFO(0x8087, 0x095a, + USB_CLASS_COMM, + USB_CDC_SUBCLASS_NCM, USB_CDC_PROTO_NONE), + .driver_info = (unsigned long)&wwan_info, + }, + /* DisplayLink docking stations */ { .match_flags = USB_DEVICE_ID_MATCH_INT_INFO | USB_DEVICE_ID_MATCH_VENDOR, diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index f5647ee0adde..e56901bb6ebc 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -1361,6 +1361,7 @@ static const struct usb_device_id products[] = { {QMI_QUIRK_SET_DTR(0x1bc7, 0x1057, 2)}, /* Telit FN980 */ {QMI_QUIRK_SET_DTR(0x1bc7, 0x1060, 2)}, /* Telit LN920 */ {QMI_QUIRK_SET_DTR(0x1bc7, 0x1070, 2)}, /* Telit FN990A */ + {QMI_QUIRK_SET_DTR(0x1bc7, 0x1077, 2)}, /* Telit FN990A w/audio */ {QMI_QUIRK_SET_DTR(0x1bc7, 0x1080, 2)}, /* Telit FE990A */ {QMI_QUIRK_SET_DTR(0x1bc7, 0x10a0, 0)}, /* Telit FN920C04 */ {QMI_QUIRK_SET_DTR(0x1bc7, 0x10a4, 0)}, /* Telit FN920C04 */ diff --git a/drivers/net/wan/lapbether.c b/drivers/net/wan/lapbether.c index 995a7207bdf8..f357a7ac70ac 100644 --- a/drivers/net/wan/lapbether.c +++ b/drivers/net/wan/lapbether.c @@ -81,7 +81,7 @@ static struct lapbethdev *lapbeth_get_x25_dev(struct net_device *dev) static __inline__ int dev_is_ethdev(struct net_device *dev) { - return dev->type == ARPHRD_ETHER && strncmp(dev->name, "dummy", 5); + return dev->type == ARPHRD_ETHER && !netdev_need_ops_lock(dev); } /* ------------------------------------------------------------------------ */ diff --git a/drivers/pci/controller/pcie-xilinx.c b/drivers/pci/controller/pcie-xilinx.c index f121836c3cf4..937ea6ae1ac4 100644 --- a/drivers/pci/controller/pcie-xilinx.c +++ b/drivers/pci/controller/pcie-xilinx.c @@ -400,7 +400,7 @@ static irqreturn_t xilinx_pcie_intr_handler(int irq, void *data) if (val & XILINX_PCIE_RPIFR1_MSI_INTR) { val = pcie_read(pcie, XILINX_PCIE_REG_RPIFR2) & XILINX_PCIE_RPIFR2_MSG_DATA; - domain = pcie->msi_domain->parent; + domain = pcie->msi_domain; } else { val = (val & XILINX_PCIE_RPIFR1_INTR_MASK) >> XILINX_PCIE_RPIFR1_INTR_SHIFT; diff --git a/drivers/pci/controller/vmd.c b/drivers/pci/controller/vmd.c index b679c7f28f51..1bd5bf4a6097 100644 --- a/drivers/pci/controller/vmd.c +++ b/drivers/pci/controller/vmd.c @@ -306,9 +306,6 @@ static bool vmd_init_dev_msi_info(struct device *dev, struct irq_domain *domain, struct irq_domain *real_parent, struct msi_domain_info *info) { - if (WARN_ON_ONCE(info->bus_token != DOMAIN_BUS_PCI_DEVICE_MSIX)) - return false; - if (!msi_lib_init_dev_msi_info(dev, domain, real_parent, info)) return false; diff --git a/drivers/ptp/ptp_private.h b/drivers/ptp/ptp_private.h index a6aad743c282..b352df4cd3f9 100644 --- a/drivers/ptp/ptp_private.h +++ b/drivers/ptp/ptp_private.h @@ -24,6 +24,11 @@ #define PTP_DEFAULT_MAX_VCLOCKS 20 #define PTP_MAX_CHANNELS 2048 +enum { + PTP_LOCK_PHYSICAL = 0, + PTP_LOCK_VIRTUAL, +}; + struct timestamp_event_queue { struct ptp_extts_event buf[PTP_MAX_TIMESTAMPS]; int head; diff --git a/drivers/ptp/ptp_vclock.c b/drivers/ptp/ptp_vclock.c index 2fdeedd60e21..64c950456517 100644 --- a/drivers/ptp/ptp_vclock.c +++ b/drivers/ptp/ptp_vclock.c @@ -154,6 +154,11 @@ static long ptp_vclock_refresh(struct ptp_clock_info *ptp) return PTP_VCLOCK_REFRESH_INTERVAL; } +static void ptp_vclock_set_subclass(struct ptp_clock *ptp) +{ + lockdep_set_subclass(&ptp->clock.rwsem, PTP_LOCK_VIRTUAL); +} + static const struct ptp_clock_info ptp_vclock_info = { .owner = THIS_MODULE, .name = "ptp virtual clock", @@ -213,6 +218,8 @@ struct ptp_vclock *ptp_vclock_register(struct ptp_clock *pclock) return NULL; } + ptp_vclock_set_subclass(vclock->clock); + timecounter_init(&vclock->tc, &vclock->cc, 0); ptp_schedule_worker(vclock->clock, PTP_VCLOCK_REFRESH_INTERVAL); diff --git a/drivers/regulator/pca9450-regulator.c b/drivers/regulator/pca9450-regulator.c index feadb21a8f30..4be270f4d6c3 100644 --- a/drivers/regulator/pca9450-regulator.c +++ b/drivers/regulator/pca9450-regulator.c @@ -40,7 +40,6 @@ struct pca9450 { struct device *dev; struct regmap *regmap; struct gpio_desc *sd_vsel_gpio; - struct notifier_block restart_nb; enum pca9450_chip_type type; unsigned int rcnt; int irq; @@ -1100,10 +1099,9 @@ static irqreturn_t pca9450_irq_handler(int irq, void *data) return IRQ_HANDLED; } -static int pca9450_i2c_restart_handler(struct notifier_block *nb, - unsigned long action, void *data) +static int pca9450_i2c_restart_handler(struct sys_off_data *data) { - struct pca9450 *pca9450 = container_of(nb, struct pca9450, restart_nb); + struct pca9450 *pca9450 = data->cb_data; struct i2c_client *i2c = container_of(pca9450->dev, struct i2c_client, dev); dev_dbg(&i2c->dev, "Restarting device..\n"); @@ -1261,10 +1259,9 @@ static int pca9450_i2c_probe(struct i2c_client *i2c) pca9450->sd_vsel_fixed_low = of_property_read_bool(ldo5->dev.of_node, "nxp,sd-vsel-fixed-low"); - pca9450->restart_nb.notifier_call = pca9450_i2c_restart_handler; - pca9450->restart_nb.priority = PCA9450_RESTART_HANDLER_PRIORITY; - - if (register_restart_handler(&pca9450->restart_nb)) + if (devm_register_sys_off_handler(&i2c->dev, SYS_OFF_MODE_RESTART, + PCA9450_RESTART_HANDLER_PRIORITY, + pca9450_i2c_restart_handler, pca9450)) dev_warn(&i2c->dev, "Failed to register restart handler\n"); dev_info(&i2c->dev, "%s probed.\n", diff --git a/drivers/regulator/tps65219-regulator.c b/drivers/regulator/tps65219-regulator.c index 5e67fdc88f49..d77ca486879f 100644 --- a/drivers/regulator/tps65219-regulator.c +++ b/drivers/regulator/tps65219-regulator.c @@ -454,9 +454,9 @@ static int tps65219_regulator_probe(struct platform_device *pdev) irq_type->irq_name, irq_data); if (error) - return dev_err_probe(tps->dev, PTR_ERR(rdev), - "Failed to request %s IRQ %d: %d\n", - irq_type->irq_name, irq, error); + return dev_err_probe(tps->dev, error, + "Failed to request %s IRQ %d\n", + irq_type->irq_name, irq); } for (i = 0; i < pmic->dev_irq_size; ++i) { @@ -477,9 +477,9 @@ static int tps65219_regulator_probe(struct platform_device *pdev) irq_type->irq_name, irq_data); if (error) - return dev_err_probe(tps->dev, PTR_ERR(rdev), - "Failed to request %s IRQ %d: %d\n", - irq_type->irq_name, irq, error); + return dev_err_probe(tps->dev, error, + "Failed to request %s IRQ %d\n", + irq_type->irq_name, irq); } return 0; diff --git a/drivers/scsi/lpfc/lpfc_debugfs.c b/drivers/scsi/lpfc/lpfc_debugfs.c index 2db8d9529b8f..7c4d7bb3a56f 100644 --- a/drivers/scsi/lpfc/lpfc_debugfs.c +++ b/drivers/scsi/lpfc/lpfc_debugfs.c @@ -6280,7 +6280,6 @@ lpfc_debugfs_initialize(struct lpfc_vport *vport) } phba->nvmeio_trc_on = 1; phba->nvmeio_trc_output_idx = 0; - phba->nvmeio_trc = NULL; } else { nvmeio_off: phba->nvmeio_trc_size = 0; diff --git a/drivers/scsi/lpfc/lpfc_vport.c b/drivers/scsi/lpfc/lpfc_vport.c index 2797aa75a689..aff6c9d5e7c2 100644 --- a/drivers/scsi/lpfc/lpfc_vport.c +++ b/drivers/scsi/lpfc/lpfc_vport.c @@ -666,7 +666,7 @@ lpfc_vport_delete(struct fc_vport *fc_vport) * Take early refcount for outstanding I/O requests we schedule during * delete processing for unreg_vpi. Always keep this before * scsi_remove_host() as we can no longer obtain a reference through - * scsi_host_get() after scsi_host_remove as shost is set to SHOST_DEL. + * scsi_host_get() after scsi_remove_host as shost is set to SHOST_DEL. */ if (!scsi_host_get(shost)) return VPORT_INVAL; diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c index 0847767d4d43..353cb60e1abe 100644 --- a/drivers/scsi/scsi_debug.c +++ b/drivers/scsi/scsi_debug.c @@ -2674,8 +2674,10 @@ static int resp_rsup_tmfs(struct scsi_cmnd *scp, static int resp_err_recov_pg(unsigned char *p, int pcontrol, int target) { /* Read-Write Error Recovery page for mode_sense */ - unsigned char err_recov_pg[] = {0x1, 0xa, 0xc0, 11, 240, 0, 0, 0, - 5, 0, 0xff, 0xff}; + static const unsigned char err_recov_pg[] = { + 0x1, 0xa, 0xc0, 11, 240, 0, 0, 0, + 5, 0, 0xff, 0xff + }; memcpy(p, err_recov_pg, sizeof(err_recov_pg)); if (1 == pcontrol) @@ -2685,8 +2687,10 @@ static int resp_err_recov_pg(unsigned char *p, int pcontrol, int target) static int resp_disconnect_pg(unsigned char *p, int pcontrol, int target) { /* Disconnect-Reconnect page for mode_sense */ - unsigned char disconnect_pg[] = {0x2, 0xe, 128, 128, 0, 10, 0, 0, - 0, 0, 0, 0, 0, 0, 0, 0}; + static const unsigned char disconnect_pg[] = { + 0x2, 0xe, 128, 128, 0, 10, 0, 0, + 0, 0, 0, 0, 0, 0, 0, 0 + }; memcpy(p, disconnect_pg, sizeof(disconnect_pg)); if (1 == pcontrol) @@ -2696,9 +2700,11 @@ static int resp_disconnect_pg(unsigned char *p, int pcontrol, int target) static int resp_format_pg(unsigned char *p, int pcontrol, int target) { /* Format device page for mode_sense */ - unsigned char format_pg[] = {0x3, 0x16, 0, 0, 0, 0, 0, 0, - 0, 0, 0, 0, 0, 0, 0, 0, - 0, 0, 0, 0, 0x40, 0, 0, 0}; + static const unsigned char format_pg[] = { + 0x3, 0x16, 0, 0, 0, 0, 0, 0, + 0, 0, 0, 0, 0, 0, 0, 0, + 0, 0, 0, 0, 0x40, 0, 0, 0 + }; memcpy(p, format_pg, sizeof(format_pg)); put_unaligned_be16(sdebug_sectors_per, p + 10); @@ -2716,10 +2722,14 @@ static unsigned char caching_pg[] = {0x8, 18, 0x14, 0, 0xff, 0xff, 0, 0, static int resp_caching_pg(unsigned char *p, int pcontrol, int target) { /* Caching page for mode_sense */ - unsigned char ch_caching_pg[] = {/* 0x8, 18, */ 0x4, 0, 0, 0, 0, 0, - 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0}; - unsigned char d_caching_pg[] = {0x8, 18, 0x14, 0, 0xff, 0xff, 0, 0, - 0xff, 0xff, 0xff, 0xff, 0x80, 0x14, 0, 0, 0, 0, 0, 0}; + static const unsigned char ch_caching_pg[] = { + /* 0x8, 18, */ 0x4, 0, 0, 0, 0, 0, + 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 + }; + static const unsigned char d_caching_pg[] = { + 0x8, 18, 0x14, 0, 0xff, 0xff, 0, 0, + 0xff, 0xff, 0xff, 0xff, 0x80, 0x14, 0, 0, 0, 0, 0, 0 + }; if (SDEBUG_OPT_N_WCE & sdebug_opts) caching_pg[2] &= ~0x4; /* set WCE=0 (default WCE=1) */ @@ -2738,8 +2748,10 @@ static int resp_ctrl_m_pg(unsigned char *p, int pcontrol, int target) { /* Control mode page for mode_sense */ unsigned char ch_ctrl_m_pg[] = {/* 0xa, 10, */ 0x6, 0, 0, 0, 0, 0, 0, 0, 0, 0}; - unsigned char d_ctrl_m_pg[] = {0xa, 10, 2, 0, 0, 0, 0, 0, - 0, 0, 0x2, 0x4b}; + static const unsigned char d_ctrl_m_pg[] = { + 0xa, 10, 2, 0, 0, 0, 0, 0, + 0, 0, 0x2, 0x4b + }; if (sdebug_dsense) ctrl_m_pg[2] |= 0x4; @@ -2794,10 +2806,14 @@ static int resp_grouping_m_pg(unsigned char *p, int pcontrol, int target) static int resp_iec_m_pg(unsigned char *p, int pcontrol, int target) { /* Informational Exceptions control mode page for mode_sense */ - unsigned char ch_iec_m_pg[] = {/* 0x1c, 0xa, */ 0x4, 0xf, 0, 0, 0, 0, - 0, 0, 0x0, 0x0}; - unsigned char d_iec_m_pg[] = {0x1c, 0xa, 0x08, 0, 0, 0, 0, 0, - 0, 0, 0x0, 0x0}; + static const unsigned char ch_iec_m_pg[] = { + /* 0x1c, 0xa, */ 0x4, 0xf, 0, 0, 0, 0, + 0, 0, 0x0, 0x0 + }; + static const unsigned char d_iec_m_pg[] = { + 0x1c, 0xa, 0x08, 0, 0, 0, 0, 0, + 0, 0, 0x0, 0x0 + }; memcpy(p, iec_m_pg, sizeof(iec_m_pg)); if (1 == pcontrol) @@ -2809,8 +2825,9 @@ static int resp_iec_m_pg(unsigned char *p, int pcontrol, int target) static int resp_sas_sf_m_pg(unsigned char *p, int pcontrol, int target) { /* SAS SSP mode page - short format for mode_sense */ - unsigned char sas_sf_m_pg[] = {0x19, 0x6, - 0x6, 0x0, 0x7, 0xd0, 0x0, 0x0}; + static const unsigned char sas_sf_m_pg[] = { + 0x19, 0x6, 0x6, 0x0, 0x7, 0xd0, 0x0, 0x0 + }; memcpy(p, sas_sf_m_pg, sizeof(sas_sf_m_pg)); if (1 == pcontrol) @@ -2854,9 +2871,10 @@ static int resp_sas_pcd_m_spg(unsigned char *p, int pcontrol, int target, static int resp_sas_sha_m_spg(unsigned char *p, int pcontrol) { /* SAS SSP shared protocol specific port mode subpage */ - unsigned char sas_sha_m_pg[] = {0x59, 0x2, 0, 0xc, 0, 0x6, 0x10, 0, - 0, 0, 0, 0, 0, 0, 0, 0, - }; + static const unsigned char sas_sha_m_pg[] = { + 0x59, 0x2, 0, 0xc, 0, 0x6, 0x10, 0, + 0, 0, 0, 0, 0, 0, 0, 0, + }; memcpy(p, sas_sha_m_pg, sizeof(sas_sha_m_pg)); if (1 == pcontrol) @@ -2923,8 +2941,10 @@ static int process_medium_part_m_pg(struct sdebug_dev_info *devip, static int resp_compression_m_pg(unsigned char *p, int pcontrol, int target, unsigned char dce) { /* Compression page for mode_sense (tape) */ - unsigned char compression_pg[] = {0x0f, 14, 0x40, 0, 0, 0, 0, 0, - 0, 0, 0, 0, 00, 00}; + static const unsigned char compression_pg[] = { + 0x0f, 14, 0x40, 0, 0, 0, 0, 0, + 0, 0, 0, 0, 0, 0 + }; memcpy(p, compression_pg, sizeof(compression_pg)); if (dce) @@ -3282,9 +3302,10 @@ bad_pcode: static int resp_temp_l_pg(unsigned char *arr) { - unsigned char temp_l_pg[] = {0x0, 0x0, 0x3, 0x2, 0x0, 38, - 0x0, 0x1, 0x3, 0x2, 0x0, 65, - }; + static const unsigned char temp_l_pg[] = { + 0x0, 0x0, 0x3, 0x2, 0x0, 38, + 0x0, 0x1, 0x3, 0x2, 0x0, 65, + }; memcpy(arr, temp_l_pg, sizeof(temp_l_pg)); return sizeof(temp_l_pg); @@ -3292,8 +3313,9 @@ static int resp_temp_l_pg(unsigned char *arr) static int resp_ie_l_pg(unsigned char *arr) { - unsigned char ie_l_pg[] = {0x0, 0x0, 0x3, 0x3, 0x0, 0x0, 38, - }; + static const unsigned char ie_l_pg[] = { + 0x0, 0x0, 0x3, 0x3, 0x0, 0x0, 38, + }; memcpy(arr, ie_l_pg, sizeof(ie_l_pg)); if (iec_m_pg[2] & 0x4) { /* TEST bit set */ @@ -3305,11 +3327,12 @@ static int resp_ie_l_pg(unsigned char *arr) static int resp_env_rep_l_spg(unsigned char *arr) { - unsigned char env_rep_l_spg[] = {0x0, 0x0, 0x23, 0x8, - 0x0, 40, 72, 0xff, 45, 18, 0, 0, - 0x1, 0x0, 0x23, 0x8, - 0x0, 55, 72, 35, 55, 45, 0, 0, - }; + static const unsigned char env_rep_l_spg[] = { + 0x0, 0x0, 0x23, 0x8, + 0x0, 40, 72, 0xff, 45, 18, 0, 0, + 0x1, 0x0, 0x23, 0x8, + 0x0, 55, 72, 35, 55, 45, 0, 0, + }; memcpy(arr, env_rep_l_spg, sizeof(env_rep_l_spg)); return sizeof(env_rep_l_spg); diff --git a/drivers/scsi/scsi_sysfs.c b/drivers/scsi/scsi_sysfs.c index 169af7d47ce7..15ba493d2138 100644 --- a/drivers/scsi/scsi_sysfs.c +++ b/drivers/scsi/scsi_sysfs.c @@ -265,7 +265,7 @@ show_shost_supported_mode(struct device *dev, struct device_attribute *attr, return show_shost_mode(supported_mode, buf); } -static DEVICE_ATTR(supported_mode, S_IRUGO | S_IWUSR, show_shost_supported_mode, NULL); +static DEVICE_ATTR(supported_mode, S_IRUGO, show_shost_supported_mode, NULL); static ssize_t show_shost_active_mode(struct device *dev, @@ -279,7 +279,7 @@ show_shost_active_mode(struct device *dev, return show_shost_mode(shost->active_mode, buf); } -static DEVICE_ATTR(active_mode, S_IRUGO | S_IWUSR, show_shost_active_mode, NULL); +static DEVICE_ATTR(active_mode, S_IRUGO, show_shost_active_mode, NULL); static int check_reset_type(const char *str) { diff --git a/drivers/soc/tegra/pmc.c b/drivers/soc/tegra/pmc.c index 2a5f24ee858c..034a2a535a1e 100644 --- a/drivers/soc/tegra/pmc.c +++ b/drivers/soc/tegra/pmc.c @@ -1232,7 +1232,7 @@ err: } static int tegra_powergate_of_get_resets(struct tegra_powergate *pg, - struct device_node *np, bool off) + struct device_node *np) { struct device *dev = pg->pmc->dev; int err; @@ -1247,22 +1247,6 @@ static int tegra_powergate_of_get_resets(struct tegra_powergate *pg, err = reset_control_acquire(pg->reset); if (err < 0) { pr_err("failed to acquire resets: %d\n", err); - goto out; - } - - if (off) { - err = reset_control_assert(pg->reset); - } else { - err = reset_control_deassert(pg->reset); - if (err < 0) - goto out; - - reset_control_release(pg->reset); - } - -out: - if (err) { - reset_control_release(pg->reset); reset_control_put(pg->reset); } @@ -1308,20 +1292,43 @@ static int tegra_powergate_add(struct tegra_pmc *pmc, struct device_node *np) goto set_available; } - err = tegra_powergate_of_get_resets(pg, np, off); + err = tegra_powergate_of_get_resets(pg, np); if (err < 0) { dev_err(dev, "failed to get resets for %pOFn: %d\n", np, err); goto remove_clks; } - if (!IS_ENABLED(CONFIG_PM_GENERIC_DOMAINS)) { - if (off) - WARN_ON(tegra_powergate_power_up(pg, true)); + /* + * If the power-domain is off, then ensure the resets are asserted. + * If the power-domain is on, then power down to ensure that when is + * it turned on the power-domain, clocks and resets are all in the + * expected state. + */ + if (off) { + err = reset_control_assert(pg->reset); + if (err) { + pr_err("failed to assert resets: %d\n", err); + goto remove_resets; + } + } else { + err = tegra_powergate_power_down(pg); + if (err) { + dev_err(dev, "failed to turn off PM domain %s: %d\n", + pg->genpd.name, err); + goto remove_resets; + } + } + /* + * If PM_GENERIC_DOMAINS is not enabled, power-on + * the domain and skip the genpd registration. + */ + if (!IS_ENABLED(CONFIG_PM_GENERIC_DOMAINS)) { + WARN_ON(tegra_powergate_power_up(pg, true)); goto remove_resets; } - err = pm_genpd_init(&pg->genpd, NULL, off); + err = pm_genpd_init(&pg->genpd, NULL, true); if (err < 0) { dev_err(dev, "failed to initialise PM domain %pOFn: %d\n", np, err); diff --git a/drivers/spi/spi-fsl-lpspi.c b/drivers/spi/spi-fsl-lpspi.c index 67d4000c3cef..313e444a34f3 100644 --- a/drivers/spi/spi-fsl-lpspi.c +++ b/drivers/spi/spi-fsl-lpspi.c @@ -330,13 +330,11 @@ static int fsl_lpspi_set_bitrate(struct fsl_lpspi_data *fsl_lpspi) } if (config.speed_hz > perclk_rate / 2) { - dev_err(fsl_lpspi->dev, - "per-clk should be at least two times of transfer speed"); - return -EINVAL; + div = 2; + } else { + div = DIV_ROUND_UP(perclk_rate, config.speed_hz); } - div = DIV_ROUND_UP(perclk_rate, config.speed_hz); - for (prescale = 0; prescale <= prescale_max; prescale++) { scldiv = div / (1 << prescale) - 2; if (scldiv >= 0 && scldiv < 256) { diff --git a/drivers/spi/spi-mem.c b/drivers/spi/spi-mem.c index d3b7e857b377..064b99204d9a 100644 --- a/drivers/spi/spi-mem.c +++ b/drivers/spi/spi-mem.c @@ -265,6 +265,9 @@ static bool spi_mem_internal_supports_op(struct spi_mem *mem, */ bool spi_mem_supports_op(struct spi_mem *mem, const struct spi_mem_op *op) { + /* Make sure the operation frequency is correct before going futher */ + spi_mem_adjust_op_freq(mem, (struct spi_mem_op *)op); + if (spi_mem_check_op(op)) return false; @@ -577,6 +580,7 @@ EXPORT_SYMBOL_GPL(spi_mem_adjust_op_freq); * spi_mem_calc_op_duration() - Derives the theoretical length (in ns) of an * operation. This helps finding the best variant * among a list of possible choices. + * @mem: the SPI memory * @op: the operation to benchmark * * Some chips have per-op frequency limitations, PCBs usually have their own diff --git a/drivers/spi/spi-qpic-snand.c b/drivers/spi/spi-qpic-snand.c index a8c4eb1cbde1..0ceaad7dba3c 100644 --- a/drivers/spi/spi-qpic-snand.c +++ b/drivers/spi/spi-qpic-snand.c @@ -210,13 +210,21 @@ static int qcom_spi_ooblayout_ecc(struct mtd_info *mtd, int section, struct qcom_nand_controller *snandc = nand_to_qcom_snand(nand); struct qpic_ecc *qecc = snandc->qspi->ecc; - if (section > 1) - return -ERANGE; - - oobregion->length = qecc->ecc_bytes_hw + qecc->spare_bytes; - oobregion->offset = mtd->oobsize - oobregion->length; + switch (section) { + case 0: + oobregion->offset = 0; + oobregion->length = qecc->bytes * (qecc->steps - 1) + + qecc->bbm_size; + return 0; + case 1: + oobregion->offset = qecc->bytes * (qecc->steps - 1) + + qecc->bbm_size + + qecc->steps * 4; + oobregion->length = mtd->oobsize - oobregion->offset; + return 0; + } - return 0; + return -ERANGE; } static int qcom_spi_ooblayout_free(struct mtd_info *mtd, int section, @@ -1196,7 +1204,7 @@ static int qcom_spi_program_oob(struct qcom_nand_controller *snandc, u32 cfg0, cfg1, ecc_bch_cfg, ecc_buf_cfg; cfg0 = (ecc_cfg->cfg0 & ~CW_PER_PAGE_MASK) | - FIELD_PREP(CW_PER_PAGE_MASK, num_cw - 1); + FIELD_PREP(CW_PER_PAGE_MASK, 0); cfg1 = ecc_cfg->cfg1; ecc_bch_cfg = ecc_cfg->ecc_bch_cfg; ecc_buf_cfg = ecc_cfg->ecc_buf_cfg; diff --git a/drivers/spi/spi-st-ssc4.c b/drivers/spi/spi-st-ssc4.c index 49ab4c515156..c07c61dc4938 100644 --- a/drivers/spi/spi-st-ssc4.c +++ b/drivers/spi/spi-st-ssc4.c @@ -378,7 +378,7 @@ static void spi_st_remove(struct platform_device *pdev) pinctrl_pm_select_sleep_state(&pdev->dev); } -static int __maybe_unused spi_st_runtime_suspend(struct device *dev) +static int spi_st_runtime_suspend(struct device *dev) { struct spi_controller *host = dev_get_drvdata(dev); struct spi_st *spi_st = spi_controller_get_devdata(host); @@ -391,7 +391,7 @@ static int __maybe_unused spi_st_runtime_suspend(struct device *dev) return 0; } -static int __maybe_unused spi_st_runtime_resume(struct device *dev) +static int spi_st_runtime_resume(struct device *dev) { struct spi_controller *host = dev_get_drvdata(dev); struct spi_st *spi_st = spi_controller_get_devdata(host); @@ -428,8 +428,8 @@ static int __maybe_unused spi_st_resume(struct device *dev) } static const struct dev_pm_ops spi_st_pm = { - SET_SYSTEM_SLEEP_PM_OPS(spi_st_suspend, spi_st_resume) - SET_RUNTIME_PM_OPS(spi_st_runtime_suspend, spi_st_runtime_resume, NULL) + SYSTEM_SLEEP_PM_OPS(spi_st_suspend, spi_st_resume) + RUNTIME_PM_OPS(spi_st_runtime_suspend, spi_st_runtime_resume, NULL) }; static const struct of_device_id stm_spi_match[] = { @@ -441,7 +441,7 @@ MODULE_DEVICE_TABLE(of, stm_spi_match); static struct platform_driver spi_st_driver = { .driver = { .name = "spi-st", - .pm = pm_sleep_ptr(&spi_st_pm), + .pm = pm_ptr(&spi_st_pm), .of_match_table = of_match_ptr(stm_spi_match), }, .probe = spi_st_probe, diff --git a/drivers/tty/serial/8250/8250_rsa.c b/drivers/tty/serial/8250/8250_rsa.c index d34093cc03ad..12a65b79583c 100644 --- a/drivers/tty/serial/8250/8250_rsa.c +++ b/drivers/tty/serial/8250/8250_rsa.c @@ -147,7 +147,7 @@ void rsa_enable(struct uart_8250_port *up) if (up->port.uartclk == SERIAL_RSA_BAUD_BASE * 16) serial_out(up, UART_RSA_FRR, 0); } -EXPORT_SYMBOL_GPL_FOR_MODULES(rsa_enable, "8250_base"); +EXPORT_SYMBOL_FOR_MODULES(rsa_enable, "8250_base"); /* * Attempts to turn off the RSA FIFO and resets the RSA board back to 115kbps compat mode. It is @@ -179,7 +179,7 @@ void rsa_disable(struct uart_8250_port *up) up->port.uartclk = SERIAL_RSA_BAUD_BASE_LO * 16; uart_port_unlock_irq(&up->port); } -EXPORT_SYMBOL_GPL_FOR_MODULES(rsa_disable, "8250_base"); +EXPORT_SYMBOL_FOR_MODULES(rsa_disable, "8250_base"); void rsa_autoconfig(struct uart_8250_port *up) { @@ -192,7 +192,7 @@ void rsa_autoconfig(struct uart_8250_port *up) if (__rsa_enable(up)) up->port.type = PORT_RSA; } -EXPORT_SYMBOL_GPL_FOR_MODULES(rsa_autoconfig, "8250_base"); +EXPORT_SYMBOL_FOR_MODULES(rsa_autoconfig, "8250_base"); void rsa_reset(struct uart_8250_port *up) { @@ -201,7 +201,7 @@ void rsa_reset(struct uart_8250_port *up) serial_out(up, UART_RSA_FRR, 0); } -EXPORT_SYMBOL_GPL_FOR_MODULES(rsa_reset, "8250_base"); +EXPORT_SYMBOL_FOR_MODULES(rsa_reset, "8250_base"); #ifdef CONFIG_SERIAL_8250_DEPRECATED_OPTIONS #ifndef MODULE diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c index 96ad57c3144b..efd7a811a002 100644 --- a/drivers/ufs/core/ufshcd.c +++ b/drivers/ufs/core/ufshcd.c @@ -7138,14 +7138,19 @@ static irqreturn_t ufshcd_threaded_intr(int irq, void *__hba) static irqreturn_t ufshcd_intr(int irq, void *__hba) { struct ufs_hba *hba = __hba; + u32 intr_status, enabled_intr_status; /* Move interrupt handling to thread when MCQ & ESI are not enabled */ if (!hba->mcq_enabled || !hba->mcq_esi_enabled) return IRQ_WAKE_THREAD; + intr_status = ufshcd_readl(hba, REG_INTERRUPT_STATUS); + enabled_intr_status = intr_status & ufshcd_readl(hba, REG_INTERRUPT_ENABLE); + + ufshcd_writel(hba, intr_status, REG_INTERRUPT_STATUS); + /* Directly handle interrupts since MCQ ESI handlers does the hard job */ - return ufshcd_sl_intr(hba, ufshcd_readl(hba, REG_INTERRUPT_STATUS) & - ufshcd_readl(hba, REG_INTERRUPT_ENABLE)); + return ufshcd_sl_intr(hba, enabled_intr_status); } static int ufshcd_clear_tm_cmd(struct ufs_hba *hba, int tag) @@ -10516,8 +10521,7 @@ int ufshcd_alloc_host(struct device *dev, struct ufs_hba **hba_handle) err = devm_add_action_or_reset(dev, ufshcd_devres_release, host); if (err) - return dev_err_probe(dev, err, - "failed to add ufshcd dealloc action\n"); + return err; host->nr_maps = HCTX_TYPE_POLL + 1; hba = shost_priv(host); diff --git a/drivers/ufs/host/ufs-mediatek.c b/drivers/ufs/host/ufs-mediatek.c index 86ae73b89d4d..f902ce08c95a 100644 --- a/drivers/ufs/host/ufs-mediatek.c +++ b/drivers/ufs/host/ufs-mediatek.c @@ -818,7 +818,7 @@ static u32 ufs_mtk_mcq_get_irq(struct ufs_hba *hba, unsigned int cpu) unsigned int q_index; q_index = map->mq_map[cpu]; - if (q_index > nr) { + if (q_index >= nr) { dev_err(hba->dev, "hwq index %d exceed %d\n", q_index, nr); return MTK_MCQ_INVALID_IRQ; diff --git a/drivers/virt/coco/sev-guest/sev-guest.c b/drivers/virt/coco/sev-guest/sev-guest.c index d2b3ae7113ab..b01ec99106cd 100644 --- a/drivers/virt/coco/sev-guest/sev-guest.c +++ b/drivers/virt/coco/sev-guest/sev-guest.c @@ -116,13 +116,11 @@ e_free: static int get_derived_key(struct snp_guest_dev *snp_dev, struct snp_guest_request_ioctl *arg) { + struct snp_derived_key_resp *derived_key_resp __free(kfree) = NULL; struct snp_derived_key_req *derived_key_req __free(kfree) = NULL; - struct snp_derived_key_resp derived_key_resp = {0}; struct snp_msg_desc *mdesc = snp_dev->msg_desc; struct snp_guest_req req = {}; int rc, resp_len; - /* Response data is 64 bytes and max authsize for GCM is 16 bytes. */ - u8 buf[64 + 16]; if (!arg->req_data || !arg->resp_data) return -EINVAL; @@ -132,8 +130,9 @@ static int get_derived_key(struct snp_guest_dev *snp_dev, struct snp_guest_reque * response payload. Make sure that it has enough space to cover the * authtag. */ - resp_len = sizeof(derived_key_resp.data) + mdesc->ctx->authsize; - if (sizeof(buf) < resp_len) + resp_len = sizeof(derived_key_resp->data) + mdesc->ctx->authsize; + derived_key_resp = kzalloc(resp_len, GFP_KERNEL_ACCOUNT); + if (!derived_key_resp) return -ENOMEM; derived_key_req = kzalloc(sizeof(*derived_key_req), GFP_KERNEL_ACCOUNT); @@ -149,23 +148,21 @@ static int get_derived_key(struct snp_guest_dev *snp_dev, struct snp_guest_reque req.vmpck_id = mdesc->vmpck_id; req.req_buf = derived_key_req; req.req_sz = sizeof(*derived_key_req); - req.resp_buf = buf; + req.resp_buf = derived_key_resp; req.resp_sz = resp_len; req.exit_code = SVM_VMGEXIT_GUEST_REQUEST; rc = snp_send_guest_request(mdesc, &req); arg->exitinfo2 = req.exitinfo2; - if (rc) - return rc; - - memcpy(derived_key_resp.data, buf, sizeof(derived_key_resp.data)); - if (copy_to_user((void __user *)arg->resp_data, &derived_key_resp, - sizeof(derived_key_resp))) - rc = -EFAULT; + if (!rc) { + if (copy_to_user((void __user *)arg->resp_data, derived_key_resp, + sizeof(derived_key_resp->data))) + rc = -EFAULT; + } /* The response buffer contains the sensitive data, explicitly clear it. */ - memzero_explicit(buf, sizeof(buf)); - memzero_explicit(&derived_key_resp, sizeof(derived_key_resp)); + memzero_explicit(derived_key_resp, sizeof(*derived_key_resp)); + return rc; } diff --git a/fs/anon_inodes.c b/fs/anon_inodes.c index 1d847a939f29..180a458fc4f7 100644 --- a/fs/anon_inodes.c +++ b/fs/anon_inodes.c @@ -129,7 +129,7 @@ struct inode *anon_inode_make_secure_inode(struct super_block *sb, const char *n } return inode; } -EXPORT_SYMBOL_GPL_FOR_MODULES(anon_inode_make_secure_inode, "kvm"); +EXPORT_SYMBOL_FOR_MODULES(anon_inode_make_secure_inode, "kvm"); static struct file *__anon_inode_getfile(const char *name, const struct file_operations *fops, diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 835b0deef9bb..c953297aa89a 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -1512,7 +1512,7 @@ out: /* * Return 0 if we have submitted or queued the sector for submission. - * Return <0 for critical errors. + * Return <0 for critical errors, and the sector will have its dirty flag cleared. * * Caller should make sure filepos < i_size and handle filepos >= i_size case. */ @@ -1535,8 +1535,17 @@ static int submit_one_sector(struct btrfs_inode *inode, ASSERT(filepos < i_size); em = btrfs_get_extent(inode, NULL, filepos, sectorsize); - if (IS_ERR(em)) + if (IS_ERR(em)) { + /* + * When submission failed, we should still clear the folio dirty. + * Or the folio will be written back again but without any + * ordered extent. + */ + btrfs_folio_clear_dirty(fs_info, folio, filepos, sectorsize); + btrfs_folio_set_writeback(fs_info, folio, filepos, sectorsize); + btrfs_folio_clear_writeback(fs_info, folio, filepos, sectorsize); return PTR_ERR(em); + } extent_offset = filepos - em->start; em_end = btrfs_extent_map_end(em); @@ -1609,8 +1618,12 @@ static noinline_for_stack int extent_writepage_io(struct btrfs_inode *inode, folio_unlock(folio); return 1; } - if (ret < 0) + if (ret < 0) { + btrfs_folio_clear_dirty(fs_info, folio, start, len); + btrfs_folio_set_writeback(fs_info, folio, start, len); + btrfs_folio_clear_writeback(fs_info, folio, start, len); return ret; + } for (cur = start; cur < start + len; cur += fs_info->sectorsize) set_bit((cur - folio_start) >> fs_info->sectorsize_bits, &range_bitmap); @@ -1666,8 +1679,8 @@ static noinline_for_stack int extent_writepage_io(struct btrfs_inode *inode, * Here we set writeback and clear for the range. If the full folio * is no longer dirty then we clear the PAGECACHE_TAG_DIRTY tag. * - * If we hit any error, the corresponding sector will still be dirty - * thus no need to clear PAGECACHE_TAG_DIRTY. + * If we hit any error, the corresponding sector will have its dirty + * flag cleared and writeback finished, thus no need to handle the error case. */ if (!submitted_io && !error) { btrfs_folio_set_writeback(fs_info, folio, start, len); @@ -1813,6 +1826,7 @@ static noinline_for_stack bool lock_extent_buffer_for_io(struct extent_buffer *e xas_load(&xas); xas_set_mark(&xas, PAGECACHE_TAG_WRITEBACK); xas_clear_mark(&xas, PAGECACHE_TAG_DIRTY); + xas_clear_mark(&xas, PAGECACHE_TAG_TOWRITE); xas_unlock_irqrestore(&xas, flags); btrfs_set_header_flag(eb, BTRFS_HEADER_FLAG_WRITTEN); @@ -4331,15 +4345,18 @@ static int try_release_subpage_extent_buffer(struct folio *folio) unsigned long end = index + (PAGE_SIZE >> fs_info->nodesize_bits) - 1; int ret; - xa_lock_irq(&fs_info->buffer_tree); + rcu_read_lock(); xa_for_each_range(&fs_info->buffer_tree, index, eb, start, end) { /* * The same as try_release_extent_buffer(), to ensure the eb * won't disappear out from under us. */ spin_lock(&eb->refs_lock); + rcu_read_unlock(); + if (refcount_read(&eb->refs) != 1 || extent_buffer_under_io(eb)) { spin_unlock(&eb->refs_lock); + rcu_read_lock(); continue; } @@ -4358,11 +4375,10 @@ static int try_release_subpage_extent_buffer(struct folio *folio) * check the folio private at the end. And * release_extent_buffer() will release the refs_lock. */ - xa_unlock_irq(&fs_info->buffer_tree); release_extent_buffer(eb); - xa_lock_irq(&fs_info->buffer_tree); + rcu_read_lock(); } - xa_unlock_irq(&fs_info->buffer_tree); + rcu_read_unlock(); /* * Finally to check if we have cleared folio private, as if we have @@ -4375,7 +4391,6 @@ static int try_release_subpage_extent_buffer(struct folio *folio) ret = 0; spin_unlock(&folio->mapping->i_private_lock); return ret; - } int try_release_extent_buffer(struct folio *folio) diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index b77dd22b8cdb..9e4aec7330cb 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -401,10 +401,12 @@ static inline void btrfs_cleanup_ordered_extents(struct btrfs_inode *inode, while (index <= end_index) { folio = filemap_get_folio(inode->vfs_inode.i_mapping, index); - index++; - if (IS_ERR(folio)) + if (IS_ERR(folio)) { + index++; continue; + } + index = folio_end(folio) >> PAGE_SHIFT; /* * Here we just clear all Ordered bits for every page in the * range, then btrfs_mark_ordered_io_finished() will handle @@ -2013,7 +2015,7 @@ static int nocow_one_range(struct btrfs_inode *inode, struct folio *locked_folio * cleaered by the caller. */ if (ret < 0) - btrfs_cleanup_ordered_extents(inode, file_pos, end); + btrfs_cleanup_ordered_extents(inode, file_pos, len); return ret; } @@ -4187,6 +4189,23 @@ int btrfs_update_inode_fallback(struct btrfs_trans_handle *trans, return ret; } +static void update_time_after_link_or_unlink(struct btrfs_inode *dir) +{ + struct timespec64 now; + + /* + * If we are replaying a log tree, we do not want to update the mtime + * and ctime of the parent directory with the current time, since the + * log replay procedure is responsible for setting them to their correct + * values (the ones it had when the fsync was done). + */ + if (test_bit(BTRFS_FS_LOG_RECOVERING, &dir->root->fs_info->flags)) + return; + + now = inode_set_ctime_current(&dir->vfs_inode); + inode_set_mtime_to_ts(&dir->vfs_inode, now); +} + /* * unlink helper that gets used here in inode.c and in the tree logging * recovery code. It remove a link in a directory with a given name, and @@ -4287,7 +4306,7 @@ skip_backref: inode_inc_iversion(&inode->vfs_inode); inode_set_ctime_current(&inode->vfs_inode); inode_inc_iversion(&dir->vfs_inode); - inode_set_mtime_to_ts(&dir->vfs_inode, inode_set_ctime_current(&dir->vfs_inode)); + update_time_after_link_or_unlink(dir); return btrfs_update_inode(trans, dir); } @@ -6681,15 +6700,7 @@ int btrfs_add_link(struct btrfs_trans_handle *trans, btrfs_i_size_write(parent_inode, parent_inode->vfs_inode.i_size + name->len * 2); inode_inc_iversion(&parent_inode->vfs_inode); - /* - * If we are replaying a log tree, we do not want to update the mtime - * and ctime of the parent directory with the current time, since the - * log replay procedure is responsible for setting them to their correct - * values (the ones it had when the fsync was done). - */ - if (!test_bit(BTRFS_FS_LOG_RECOVERING, &root->fs_info->flags)) - inode_set_mtime_to_ts(&parent_inode->vfs_inode, - inode_set_ctime_current(&parent_inode->vfs_inode)); + update_time_after_link_or_unlink(parent_inode); ret = btrfs_update_inode(trans, parent_inode); if (ret) diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index 1a5972178b3a..ccaa9a3cf1ce 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -1453,7 +1453,6 @@ static int __qgroup_excl_accounting(struct btrfs_fs_info *fs_info, u64 ref_root, struct btrfs_qgroup *src, int sign) { struct btrfs_qgroup *qgroup; - struct btrfs_qgroup *cur; LIST_HEAD(qgroup_list); u64 num_bytes = src->excl; int ret = 0; @@ -1463,7 +1462,7 @@ static int __qgroup_excl_accounting(struct btrfs_fs_info *fs_info, u64 ref_root, goto out; qgroup_iterator_add(&qgroup_list, qgroup); - list_for_each_entry(cur, &qgroup_list, iterator) { + list_for_each_entry(qgroup, &qgroup_list, iterator) { struct btrfs_qgroup_list *glist; qgroup->rfer += sign * num_bytes; diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index e58151933844..7256f6748c8f 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -602,6 +602,25 @@ static struct btrfs_root *create_reloc_root(struct btrfs_trans_handle *trans, if (btrfs_root_id(root) == objectid) { u64 commit_root_gen; + /* + * Relocation will wait for cleaner thread, and any half-dropped + * subvolume will be fully cleaned up at mount time. + * So here we shouldn't hit a subvolume with non-zero drop_progress. + * + * If this isn't the case, error out since it can make us attempt to + * drop references for extents that were already dropped before. + */ + if (unlikely(btrfs_disk_key_objectid(&root->root_item.drop_progress))) { + struct btrfs_key cpu_key; + + btrfs_disk_key_to_cpu(&cpu_key, &root->root_item.drop_progress); + btrfs_err(fs_info, + "cannot relocate partially dropped subvolume %llu, drop progress key (%llu %u %llu)", + objectid, cpu_key.objectid, cpu_key.type, cpu_key.offset); + ret = -EUCLEAN; + goto fail; + } + /* called by btrfs_init_reloc_root */ ret = btrfs_copy_root(trans, root, root->commit_root, &eb, BTRFS_TREE_RELOC_OBJECTID); diff --git a/fs/btrfs/subpage.c b/fs/btrfs/subpage.c index c9b3821957f7..cb4f97833dc3 100644 --- a/fs/btrfs/subpage.c +++ b/fs/btrfs/subpage.c @@ -448,8 +448,25 @@ void btrfs_subpage_set_writeback(const struct btrfs_fs_info *fs_info, spin_lock_irqsave(&bfs->lock, flags); bitmap_set(bfs->bitmaps, start_bit, len >> fs_info->sectorsize_bits); + + /* + * Don't clear the TOWRITE tag when starting writeback on a still-dirty + * folio. Doing so can cause WB_SYNC_ALL writepages() to overlook it, + * assume writeback is complete, and exit too early — violating sync + * ordering guarantees. + */ if (!folio_test_writeback(folio)) - folio_start_writeback(folio); + __folio_start_writeback(folio, true); + if (!folio_test_dirty(folio)) { + struct address_space *mapping = folio_mapping(folio); + XA_STATE(xas, &mapping->i_pages, folio->index); + unsigned long flags; + + xas_lock_irqsave(&xas, flags); + xas_load(&xas); + xas_clear_mark(&xas, PAGECACHE_TAG_TOWRITE); + xas_unlock_irqrestore(&xas, flags); + } spin_unlock_irqrestore(&bfs->lock, flags); } diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 68e35a3700ff..a262b494a89f 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -88,6 +88,9 @@ struct btrfs_fs_context { refcount_t refs; }; +static void btrfs_emit_options(struct btrfs_fs_info *info, + struct btrfs_fs_context *old); + enum { Opt_acl, Opt_clear_cache, @@ -698,12 +701,9 @@ bool btrfs_check_options(const struct btrfs_fs_info *info, if (!test_bit(BTRFS_FS_STATE_REMOUNTING, &info->fs_state)) { if (btrfs_raw_test_opt(*mount_opt, SPACE_CACHE)) { - btrfs_info(info, "disk space caching is enabled"); btrfs_warn(info, "space cache v1 is being deprecated and will be removed in a future release, please use -o space_cache=v2"); } - if (btrfs_raw_test_opt(*mount_opt, FREE_SPACE_TREE)) - btrfs_info(info, "using free-space-tree"); } return ret; @@ -980,6 +980,8 @@ static int btrfs_fill_super(struct super_block *sb, return ret; } + btrfs_emit_options(fs_info, NULL); + inode = btrfs_iget(BTRFS_FIRST_FREE_OBJECTID, fs_info->fs_root); if (IS_ERR(inode)) { ret = PTR_ERR(inode); @@ -1437,7 +1439,7 @@ static void btrfs_emit_options(struct btrfs_fs_info *info, { btrfs_info_if_set(info, old, NODATASUM, "setting nodatasum"); btrfs_info_if_set(info, old, DEGRADED, "allowing degraded mounts"); - btrfs_info_if_set(info, old, NODATASUM, "setting nodatasum"); + btrfs_info_if_set(info, old, NODATACOW, "setting nodatacow"); btrfs_info_if_set(info, old, SSD, "enabling ssd optimizations"); btrfs_info_if_set(info, old, SSD_SPREAD, "using spread ssd allocation scheme"); btrfs_info_if_set(info, old, NOBARRIER, "turning off barriers"); @@ -1459,10 +1461,11 @@ static void btrfs_emit_options(struct btrfs_fs_info *info, btrfs_info_if_set(info, old, IGNOREMETACSUMS, "ignoring meta csums"); btrfs_info_if_set(info, old, IGNORESUPERFLAGS, "ignoring unknown super block flags"); + btrfs_info_if_unset(info, old, NODATASUM, "setting datasum"); btrfs_info_if_unset(info, old, NODATACOW, "setting datacow"); btrfs_info_if_unset(info, old, SSD, "not using ssd optimizations"); btrfs_info_if_unset(info, old, SSD_SPREAD, "not using spread ssd allocation scheme"); - btrfs_info_if_unset(info, old, NOBARRIER, "turning off barriers"); + btrfs_info_if_unset(info, old, NOBARRIER, "turning on barriers"); btrfs_info_if_unset(info, old, NOTREELOG, "enabling tree log"); btrfs_info_if_unset(info, old, SPACE_CACHE, "disabling disk space caching"); btrfs_info_if_unset(info, old, FREE_SPACE_TREE, "disabling free space tree"); diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 2186e87fb61b..69e11557fd13 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -2605,14 +2605,14 @@ static int replay_one_buffer(struct btrfs_root *log, struct extent_buffer *eb, /* * Correctly adjust the reserved bytes occupied by a log tree extent buffer */ -static void unaccount_log_buffer(struct btrfs_fs_info *fs_info, u64 start) +static int unaccount_log_buffer(struct btrfs_fs_info *fs_info, u64 start) { struct btrfs_block_group *cache; cache = btrfs_lookup_block_group(fs_info, start); if (!cache) { btrfs_err(fs_info, "unable to find block group for %llu", start); - return; + return -ENOENT; } spin_lock(&cache->space_info->lock); @@ -2623,27 +2623,22 @@ static void unaccount_log_buffer(struct btrfs_fs_info *fs_info, u64 start) spin_unlock(&cache->space_info->lock); btrfs_put_block_group(cache); + + return 0; } static int clean_log_buffer(struct btrfs_trans_handle *trans, struct extent_buffer *eb) { - int ret; - btrfs_tree_lock(eb); btrfs_clear_buffer_dirty(trans, eb); wait_on_extent_buffer_writeback(eb); btrfs_tree_unlock(eb); - if (trans) { - ret = btrfs_pin_reserved_extent(trans, eb); - if (ret) - return ret; - } else { - unaccount_log_buffer(eb->fs_info, eb->start); - } + if (trans) + return btrfs_pin_reserved_extent(trans, eb); - return 0; + return unaccount_log_buffer(eb->fs_info, eb->start); } static noinline int walk_down_log_tree(struct btrfs_trans_handle *trans, diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c index 245e813ecd78..ea662036f441 100644 --- a/fs/btrfs/zoned.c +++ b/fs/btrfs/zoned.c @@ -17,6 +17,7 @@ #include "accessors.h" #include "bio.h" #include "transaction.h" +#include "sysfs.h" /* Maximum number of zones to report per blkdev_report_zones() call */ #define BTRFS_REPORT_NR_ZONES 4096 @@ -42,6 +43,9 @@ /* Number of superblock log zones */ #define BTRFS_NR_SB_LOG_ZONES 2 +/* Default number of max active zones when the device has no limits. */ +#define BTRFS_DEFAULT_MAX_ACTIVE_ZONES 128 + /* * Minimum of active zones we need: * @@ -416,7 +420,10 @@ int btrfs_get_dev_zone_info(struct btrfs_device *device, bool populate_cache) if (!IS_ALIGNED(nr_sectors, zone_sectors)) zone_info->nr_zones++; - max_active_zones = bdev_max_active_zones(bdev); + max_active_zones = min_not_zero(bdev_max_active_zones(bdev), + bdev_max_open_zones(bdev)); + if (!max_active_zones && zone_info->nr_zones > BTRFS_DEFAULT_MAX_ACTIVE_ZONES) + max_active_zones = BTRFS_DEFAULT_MAX_ACTIVE_ZONES; if (max_active_zones && max_active_zones < BTRFS_MIN_ACTIVE_ZONES) { btrfs_err(fs_info, "zoned: %s: max active zones %u is too small, need at least %u active zones", @@ -2168,10 +2175,15 @@ bool btrfs_zone_activate(struct btrfs_block_group *block_group) goto out_unlock; } - /* No space left */ - if (btrfs_zoned_bg_is_full(block_group)) { - ret = false; - goto out_unlock; + if (block_group->flags & BTRFS_BLOCK_GROUP_DATA) { + /* The caller should check if the block group is full. */ + if (WARN_ON_ONCE(btrfs_zoned_bg_is_full(block_group))) { + ret = false; + goto out_unlock; + } + } else { + /* Since it is already written, it should have been active. */ + WARN_ON_ONCE(block_group->meta_write_pointer != block_group->start); } for (i = 0; i < map->num_stripes; i++) { @@ -2230,7 +2242,7 @@ static void wait_eb_writebacks(struct btrfs_block_group *block_group) struct btrfs_fs_info *fs_info = block_group->fs_info; const u64 end = block_group->start + block_group->length; struct extent_buffer *eb; - unsigned long index, start = (block_group->start >> fs_info->sectorsize_bits); + unsigned long index, start = (block_group->start >> fs_info->nodesize_bits); rcu_read_lock(); xa_for_each_start(&fs_info->buffer_tree, index, eb, start) { @@ -2245,6 +2257,40 @@ static void wait_eb_writebacks(struct btrfs_block_group *block_group) rcu_read_unlock(); } +static int call_zone_finish(struct btrfs_block_group *block_group, + struct btrfs_io_stripe *stripe) +{ + struct btrfs_device *device = stripe->dev; + const u64 physical = stripe->physical; + struct btrfs_zoned_device_info *zinfo = device->zone_info; + int ret; + + if (!device->bdev) + return 0; + + if (zinfo->max_active_zones == 0) + return 0; + + if (btrfs_dev_is_sequential(device, physical)) { + unsigned int nofs_flags; + + nofs_flags = memalloc_nofs_save(); + ret = blkdev_zone_mgmt(device->bdev, REQ_OP_ZONE_FINISH, + physical >> SECTOR_SHIFT, + zinfo->zone_size >> SECTOR_SHIFT); + memalloc_nofs_restore(nofs_flags); + + if (ret) + return ret; + } + + if (!(block_group->flags & BTRFS_BLOCK_GROUP_DATA)) + zinfo->reserved_active_zones++; + btrfs_dev_clear_active_zone(device, physical); + + return 0; +} + static int do_zone_finish(struct btrfs_block_group *block_group, bool fully_written) { struct btrfs_fs_info *fs_info = block_group->fs_info; @@ -2329,31 +2375,12 @@ static int do_zone_finish(struct btrfs_block_group *block_group, bool fully_writ down_read(&dev_replace->rwsem); map = block_group->physical_map; for (i = 0; i < map->num_stripes; i++) { - struct btrfs_device *device = map->stripes[i].dev; - const u64 physical = map->stripes[i].physical; - struct btrfs_zoned_device_info *zinfo = device->zone_info; - unsigned int nofs_flags; - - if (!device->bdev) - continue; - - if (zinfo->max_active_zones == 0) - continue; - - nofs_flags = memalloc_nofs_save(); - ret = blkdev_zone_mgmt(device->bdev, REQ_OP_ZONE_FINISH, - physical >> SECTOR_SHIFT, - zinfo->zone_size >> SECTOR_SHIFT); - memalloc_nofs_restore(nofs_flags); + ret = call_zone_finish(block_group, &map->stripes[i]); if (ret) { up_read(&dev_replace->rwsem); return ret; } - - if (!(block_group->flags & BTRFS_BLOCK_GROUP_DATA)) - zinfo->reserved_active_zones++; - btrfs_dev_clear_active_zone(device, physical); } up_read(&dev_replace->rwsem); @@ -2504,12 +2531,12 @@ void btrfs_clear_data_reloc_bg(struct btrfs_block_group *bg) void btrfs_zoned_reserve_data_reloc_bg(struct btrfs_fs_info *fs_info) { struct btrfs_space_info *data_sinfo = fs_info->data_sinfo; - struct btrfs_space_info *space_info = data_sinfo->sub_group[0]; + struct btrfs_space_info *space_info = data_sinfo; struct btrfs_trans_handle *trans; struct btrfs_block_group *bg; struct list_head *bg_list; u64 alloc_flags; - bool initial = false; + bool first = true; bool did_chunk_alloc = false; int index; int ret; @@ -2523,21 +2550,52 @@ void btrfs_zoned_reserve_data_reloc_bg(struct btrfs_fs_info *fs_info) if (sb_rdonly(fs_info->sb)) return; - ASSERT(space_info->subgroup_id == BTRFS_SUB_GROUP_DATA_RELOC); alloc_flags = btrfs_get_alloc_profile(fs_info, space_info->flags); index = btrfs_bg_flags_to_raid_index(alloc_flags); - bg_list = &data_sinfo->block_groups[index]; + /* Scan the data space_info to find empty block groups. Take the second one. */ again: + bg_list = &space_info->block_groups[index]; list_for_each_entry(bg, bg_list, list) { - if (bg->used > 0) + if (bg->alloc_offset != 0) continue; - if (!initial) { - initial = true; + if (first) { + first = false; continue; } + if (space_info == data_sinfo) { + /* Migrate the block group to the data relocation space_info. */ + struct btrfs_space_info *reloc_sinfo = data_sinfo->sub_group[0]; + int factor; + + ASSERT(reloc_sinfo->subgroup_id == BTRFS_SUB_GROUP_DATA_RELOC); + factor = btrfs_bg_type_to_factor(bg->flags); + + down_write(&space_info->groups_sem); + list_del_init(&bg->list); + /* We can assume this as we choose the second empty one. */ + ASSERT(!list_empty(&space_info->block_groups[index])); + up_write(&space_info->groups_sem); + + spin_lock(&space_info->lock); + space_info->total_bytes -= bg->length; + space_info->disk_total -= bg->length * factor; + /* There is no allocation ever happened. */ + ASSERT(bg->used == 0); + ASSERT(bg->zone_unusable == 0); + /* No super block in a block group on the zoned setup. */ + ASSERT(bg->bytes_super == 0); + spin_unlock(&space_info->lock); + + bg->space_info = reloc_sinfo; + if (reloc_sinfo->block_group_kobjs[index] == NULL) + btrfs_sysfs_add_block_group_type(bg); + + btrfs_add_bg_to_space_info(fs_info, bg); + } + fs_info->data_reloc_bg = bg->start; set_bit(BLOCK_GROUP_FLAG_ZONED_DATA_RELOC, &bg->runtime_flags); btrfs_zone_activate(bg); @@ -2552,11 +2610,18 @@ again: if (IS_ERR(trans)) return; + /* Allocate new BG in the data relocation space_info. */ + space_info = data_sinfo->sub_group[0]; + ASSERT(space_info->subgroup_id == BTRFS_SUB_GROUP_DATA_RELOC); ret = btrfs_chunk_alloc(trans, space_info, alloc_flags, CHUNK_ALLOC_FORCE); btrfs_end_transaction(trans); if (ret == 1) { + /* + * We allocated a new block group in the data relocation space_info. We + * can take that one. + */ + first = false; did_chunk_alloc = true; - bg_list = &space_info->block_groups[index]; goto again; } } @@ -2650,7 +2715,7 @@ int btrfs_zone_finish_one_bg(struct btrfs_fs_info *fs_info) spin_lock(&block_group->lock); if (block_group->reserved || block_group->alloc_offset == 0 || - (block_group->flags & BTRFS_BLOCK_GROUP_SYSTEM) || + !(block_group->flags & BTRFS_BLOCK_GROUP_DATA) || test_bit(BLOCK_GROUP_FLAG_ZONED_DATA_RELOC, &block_group->runtime_flags)) { spin_unlock(&block_group->lock); continue; diff --git a/fs/buffer.c b/fs/buffer.c index ead4dc85debd..6a8752f7bbed 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -157,8 +157,8 @@ static void __end_buffer_read_notouch(struct buffer_head *bh, int uptodate) */ void end_buffer_read_sync(struct buffer_head *bh, int uptodate) { - __end_buffer_read_notouch(bh, uptodate); put_bh(bh); + __end_buffer_read_notouch(bh, uptodate); } EXPORT_SYMBOL(end_buffer_read_sync); diff --git a/fs/coredump.c b/fs/coredump.c index fedbead956ed..5dce257c67fc 100644 --- a/fs/coredump.c +++ b/fs/coredump.c @@ -345,7 +345,7 @@ static bool coredump_parse(struct core_name *cn, struct coredump_params *cprm, was_space = false; err = cn_printf(cn, "%c", '\0'); if (err) - return err; + return false; (*argv)[(*argc)++] = cn->used; } } @@ -1743,6 +1743,9 @@ dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter, loff_t done = 0; int ret; + if (WARN_ON_ONCE(iocb->ki_flags & IOCB_ATOMIC)) + return -EIO; + if (!iomi.len) return 0; diff --git a/fs/erofs/Kconfig b/fs/erofs/Kconfig index 7b26efc271ee..d81f3318417d 100644 --- a/fs/erofs/Kconfig +++ b/fs/erofs/Kconfig @@ -3,8 +3,18 @@ config EROFS_FS tristate "EROFS filesystem support" depends on BLOCK + select CACHEFILES if EROFS_FS_ONDEMAND select CRC32 + select CRYPTO if EROFS_FS_ZIP_ACCEL + select CRYPTO_DEFLATE if EROFS_FS_ZIP_ACCEL select FS_IOMAP + select LZ4_DECOMPRESS if EROFS_FS_ZIP + select NETFS_SUPPORT if EROFS_FS_ONDEMAND + select XXHASH if EROFS_FS_XATTR + select XZ_DEC if EROFS_FS_ZIP_LZMA + select XZ_DEC_MICROLZMA if EROFS_FS_ZIP_LZMA + select ZLIB_INFLATE if EROFS_FS_ZIP_DEFLATE + select ZSTD_DECOMPRESS if EROFS_FS_ZIP_ZSTD help EROFS (Enhanced Read-Only File System) is a lightweight read-only file system with modern designs (e.g. no buffer heads, inline @@ -38,7 +48,6 @@ config EROFS_FS_DEBUG config EROFS_FS_XATTR bool "EROFS extended attributes" depends on EROFS_FS - select XXHASH default y help Extended attributes are name:value pairs associated with inodes by @@ -94,7 +103,6 @@ config EROFS_FS_BACKED_BY_FILE config EROFS_FS_ZIP bool "EROFS Data Compression Support" depends on EROFS_FS - select LZ4_DECOMPRESS default y help Enable transparent compression support for EROFS file systems. @@ -104,8 +112,6 @@ config EROFS_FS_ZIP config EROFS_FS_ZIP_LZMA bool "EROFS LZMA compressed data support" depends on EROFS_FS_ZIP - select XZ_DEC - select XZ_DEC_MICROLZMA help Saying Y here includes support for reading EROFS file systems containing LZMA compressed data, specifically called microLZMA. It @@ -117,7 +123,6 @@ config EROFS_FS_ZIP_LZMA config EROFS_FS_ZIP_DEFLATE bool "EROFS DEFLATE compressed data support" depends on EROFS_FS_ZIP - select ZLIB_INFLATE help Saying Y here includes support for reading EROFS file systems containing DEFLATE compressed data. It gives better compression @@ -132,7 +137,6 @@ config EROFS_FS_ZIP_DEFLATE config EROFS_FS_ZIP_ZSTD bool "EROFS Zstandard compressed data support" depends on EROFS_FS_ZIP - select ZSTD_DECOMPRESS help Saying Y here includes support for reading EROFS file systems containing Zstandard compressed data. It gives better compression @@ -147,8 +151,6 @@ config EROFS_FS_ZIP_ZSTD config EROFS_FS_ZIP_ACCEL bool "EROFS hardware decompression support" depends on EROFS_FS_ZIP - select CRYPTO - select CRYPTO_DEFLATE help Saying Y here includes hardware accelerator support for reading EROFS file systems containing compressed data. It gives better @@ -163,9 +165,7 @@ config EROFS_FS_ZIP_ACCEL config EROFS_FS_ONDEMAND bool "EROFS fscache-based on-demand read support (deprecated)" depends on EROFS_FS - select NETFS_SUPPORT select FSCACHE - select CACHEFILES select CACHEFILES_ONDEMAND help This permits EROFS to use fscache-backed data blobs with on-demand diff --git a/fs/erofs/super.c b/fs/erofs/super.c index e1020aa60771..1b529ace4db0 100644 --- a/fs/erofs/super.c +++ b/fs/erofs/super.c @@ -174,6 +174,11 @@ static int erofs_init_device(struct erofs_buf *buf, struct super_block *sb, if (!erofs_is_fileio_mode(sbi)) { dif->dax_dev = fs_dax_get_by_bdev(file_bdev(file), &dif->dax_part_off, NULL, NULL); + if (!dif->dax_dev && test_opt(&sbi->opt, DAX_ALWAYS)) { + erofs_info(sb, "DAX unsupported by %s. Turning off DAX.", + dif->path); + clear_opt(&sbi->opt, DAX_ALWAYS); + } } else if (!S_ISREG(file_inode(file)->i_mode)) { fput(file); return -EINVAL; @@ -210,8 +215,13 @@ static int erofs_scan_devices(struct super_block *sb, ondisk_extradevs, sbi->devs->extra_devices); return -EINVAL; } - if (!ondisk_extradevs) + if (!ondisk_extradevs) { + if (test_opt(&sbi->opt, DAX_ALWAYS) && !sbi->dif0.dax_dev) { + erofs_info(sb, "DAX unsupported by block device. Turning off DAX."); + clear_opt(&sbi->opt, DAX_ALWAYS); + } return 0; + } if (!sbi->devs->extra_devices && !erofs_is_fscache_mode(sb)) sbi->devs->flatdev = true; @@ -313,8 +323,8 @@ static int erofs_read_superblock(struct super_block *sb) sbi->islotbits = ilog2(sizeof(struct erofs_inode_compact)); if (erofs_sb_has_48bit(sbi) && dsb->rootnid_8b) { sbi->root_nid = le64_to_cpu(dsb->rootnid_8b); - sbi->dif0.blocks = (sbi->dif0.blocks << 32) | - le16_to_cpu(dsb->rb.blocks_hi); + sbi->dif0.blocks = sbi->dif0.blocks | + ((u64)le16_to_cpu(dsb->rb.blocks_hi) << 32); } else { sbi->root_nid = le16_to_cpu(dsb->rb.rootnid_2b); } @@ -338,7 +348,6 @@ static int erofs_read_superblock(struct super_block *sb) if (ret < 0) goto out; - /* handle multiple devices */ ret = erofs_scan_devices(sb, dsb); if (erofs_sb_has_48bit(sbi)) @@ -671,14 +680,9 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc) return invalfc(fc, "cannot use fsoffset in fscache mode"); } - if (test_opt(&sbi->opt, DAX_ALWAYS)) { - if (!sbi->dif0.dax_dev) { - errorfc(fc, "DAX unsupported by block device. Turning off DAX."); - clear_opt(&sbi->opt, DAX_ALWAYS); - } else if (sbi->blkszbits != PAGE_SHIFT) { - errorfc(fc, "unsupported blocksize for DAX"); - clear_opt(&sbi->opt, DAX_ALWAYS); - } + if (test_opt(&sbi->opt, DAX_ALWAYS) && sbi->blkszbits != PAGE_SHIFT) { + erofs_info(sb, "unsupported blocksize for DAX"); + clear_opt(&sbi->opt, DAX_ALWAYS); } sb->s_time_gran = 1; diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c index 792f20888a8f..2d73297003d2 100644 --- a/fs/erofs/zdata.c +++ b/fs/erofs/zdata.c @@ -1432,6 +1432,16 @@ static void z_erofs_decompressqueue_kthread_work(struct kthread_work *work) } #endif +/* Use (kthread_)work in atomic contexts to minimize scheduling overhead */ +static inline bool z_erofs_in_atomic(void) +{ + if (IS_ENABLED(CONFIG_PREEMPTION) && rcu_preempt_depth()) + return true; + if (!IS_ENABLED(CONFIG_PREEMPT_COUNT)) + return true; + return !preemptible(); +} + static void z_erofs_decompress_kickoff(struct z_erofs_decompressqueue *io, int bios) { @@ -1446,8 +1456,7 @@ static void z_erofs_decompress_kickoff(struct z_erofs_decompressqueue *io, if (atomic_add_return(bios, &io->pending_bios)) return; - /* Use (kthread_)work and sync decompression for atomic contexts only */ - if (!in_task() || irqs_disabled() || rcu_read_lock_any_held()) { + if (z_erofs_in_atomic()) { #ifdef CONFIG_EROFS_FS_PCPU_KTHREAD struct kthread_worker *worker; diff --git a/fs/ext4/fsmap.c b/fs/ext4/fsmap.c index 383c6edea6dd..91185c40f755 100644 --- a/fs/ext4/fsmap.c +++ b/fs/ext4/fsmap.c @@ -393,6 +393,14 @@ static unsigned int ext4_getfsmap_find_sb(struct super_block *sb, /* Reserved GDT blocks */ if (!ext4_has_feature_meta_bg(sb) || metagroup < first_meta_bg) { len = le16_to_cpu(sbi->s_es->s_reserved_gdt_blocks); + + /* + * mkfs.ext4 can set s_reserved_gdt_blocks as 0 in some cases, + * check for that. + */ + if (!len) + return 0; + error = ext4_getfsmap_fill(meta_list, fsb, len, EXT4_FMR_OWN_RESV_GDT); if (error) @@ -526,6 +534,7 @@ static int ext4_getfsmap_datadev(struct super_block *sb, ext4_group_t end_ag; ext4_grpblk_t first_cluster; ext4_grpblk_t last_cluster; + struct ext4_fsmap irec; int error = 0; bofs = le32_to_cpu(sbi->s_es->s_first_data_block); @@ -609,10 +618,18 @@ static int ext4_getfsmap_datadev(struct super_block *sb, goto err; } - /* Report any gaps at the end of the bg */ + /* + * The dummy record below will cause ext4_getfsmap_helper() to report + * any allocated blocks at the end of the range. + */ + irec.fmr_device = 0; + irec.fmr_physical = end_fsb + 1; + irec.fmr_length = 0; + irec.fmr_owner = EXT4_FMR_OWN_FREE; + irec.fmr_flags = 0; + info->gfi_last = true; - error = ext4_getfsmap_datadev_helper(sb, end_ag, last_cluster + 1, - 0, info); + error = ext4_getfsmap_helper(sb, info, &irec); if (error) goto err; diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c index 7de327fa7b1c..d45124318200 100644 --- a/fs/ext4/indirect.c +++ b/fs/ext4/indirect.c @@ -539,7 +539,7 @@ int ext4_ind_map_blocks(handle_t *handle, struct inode *inode, int indirect_blks; int blocks_to_boundary = 0; int depth; - int count = 0; + u64 count = 0; ext4_fsblk_t first_block = 0; trace_ext4_ind_map_blocks_enter(inode, map->m_lblk, map->m_len, flags); @@ -588,7 +588,7 @@ int ext4_ind_map_blocks(handle_t *handle, struct inode *inode, count++; /* Fill in size of a hole we found */ map->m_pblk = 0; - map->m_len = min_t(unsigned int, map->m_len, count); + map->m_len = umin(map->m_len, count); goto cleanup; } diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index ed54c4d0f2f9..5b7a15db4953 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -146,7 +146,7 @@ static inline int ext4_begin_ordered_truncate(struct inode *inode, */ int ext4_inode_is_fast_symlink(struct inode *inode) { - if (!(EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL)) { + if (!ext4_has_feature_ea_inode(inode->i_sb)) { int ea_blocks = EXT4_I(inode)->i_file_acl ? EXT4_CLUSTER_SIZE(inode->i_sb) >> 9 : 0; @@ -3155,7 +3155,7 @@ retry: folio_unlock(folio); folio_put(folio); /* - * block_write_begin may have instantiated a few blocks + * ext4_block_write_begin may have instantiated a few blocks * outside i_size. Trim these off again. Don't need * i_size_read because we hold inode lock. */ diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index d83f91b62317..2cd36f59c9e3 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -2965,7 +2965,6 @@ int ext4_init_new_dir(handle_t *handle, struct inode *dir, struct inode *inode) { struct buffer_head *dir_block = NULL; - struct ext4_dir_entry_2 *de; ext4_lblk_t block = 0; int err; @@ -2982,10 +2981,7 @@ int ext4_init_new_dir(handle_t *handle, struct inode *dir, dir_block = ext4_append(handle, inode, &block); if (IS_ERR(dir_block)) return PTR_ERR(dir_block); - de = (struct ext4_dir_entry_2 *)dir_block->b_data; err = ext4_init_dirblock(handle, inode, dir_block, dir->i_ino, NULL, 0); - if (err) - goto out; out: brelse(dir_block); return err; diff --git a/fs/ext4/orphan.c b/fs/ext4/orphan.c index 7c7f792ad6ab..524d4658fa40 100644 --- a/fs/ext4/orphan.c +++ b/fs/ext4/orphan.c @@ -589,8 +589,9 @@ int ext4_init_orphan_info(struct super_block *sb) } oi->of_blocks = inode->i_size >> sb->s_blocksize_bits; oi->of_csum_seed = EXT4_I(inode)->i_csum_seed; - oi->of_binfo = kmalloc(oi->of_blocks*sizeof(struct ext4_orphan_block), - GFP_KERNEL); + oi->of_binfo = kmalloc_array(oi->of_blocks, + sizeof(struct ext4_orphan_block), + GFP_KERNEL); if (!oi->of_binfo) { ret = -ENOMEM; goto out_put; diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c index 3d8b0f6d2dea..39abfeec5f36 100644 --- a/fs/ext4/page-io.c +++ b/fs/ext4/page-io.c @@ -547,7 +547,7 @@ int ext4_bio_write_folio(struct ext4_io_submit *io, struct folio *folio, * first page of the bio. Otherwise it can deadlock. */ if (io->io_bio) - gfp_flags = GFP_NOWAIT | __GFP_NOWARN; + gfp_flags = GFP_NOWAIT; retry_encrypt: bounce_page = fscrypt_encrypt_pagecache_blocks(folio, enc_bytes, 0, gfp_flags); diff --git a/fs/ext4/super.c b/fs/ext4/super.c index c7d39da7e733..699c15db28a8 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -268,7 +268,7 @@ struct buffer_head *ext4_sb_bread_unmovable(struct super_block *sb, void ext4_sb_breadahead_unmovable(struct super_block *sb, sector_t block) { struct buffer_head *bh = bdev_getblk(sb->s_bdev, block, - sb->s_blocksize, GFP_NOWAIT | __GFP_NOWARN); + sb->s_blocksize, GFP_NOWAIT); if (likely(bh)) { if (trylock_buffer(bh)) @@ -1998,6 +1998,9 @@ int ext4_init_fs_context(struct fs_context *fc) fc->fs_private = ctx; fc->ops = &ext4_context_ops; + /* i_version is always enabled now */ + fc->sb_flags |= SB_I_VERSION; + return 0; } @@ -2975,6 +2978,8 @@ static int _ext4_show_options(struct seq_file *seq, struct super_block *sb, SEQ_OPTS_PRINT("min_batch_time=%u", sbi->s_min_batch_time); if (nodefs || sbi->s_max_batch_time != EXT4_DEF_MAX_BATCH_TIME) SEQ_OPTS_PRINT("max_batch_time=%u", sbi->s_max_batch_time); + if (nodefs && sb->s_flags & SB_I_VERSION) + SEQ_OPTS_PUTS("i_version"); if (nodefs || sbi->s_stripe) SEQ_OPTS_PRINT("stripe=%lu", sbi->s_stripe); if (nodefs || EXT4_MOUNT_DATA_FLAGS & @@ -5314,9 +5319,6 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb) sb->s_flags = (sb->s_flags & ~SB_POSIXACL) | (test_opt(sb, POSIX_ACL) ? SB_POSIXACL : 0); - /* i_version is always enabled now */ - sb->s_flags |= SB_I_VERSION; - /* HSM events are allowed by default. */ sb->s_iflags |= SB_I_ALLOW_HSM; @@ -5414,6 +5416,8 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb) err = ext4_load_and_init_journal(sb, es, ctx); if (err) goto failed_mount3a; + if (bdev_read_only(sb->s_bdev)) + needs_recovery = 0; } else if (test_opt(sb, NOLOAD) && !sb_rdonly(sb) && ext4_has_feature_journal_needs_recovery(sb)) { ext4_msg(sb, KERN_ERR, "required journal recovery " diff --git a/fs/fhandle.c b/fs/fhandle.c index 7c236f64cdea..68a7d2861c58 100644 --- a/fs/fhandle.c +++ b/fs/fhandle.c @@ -402,7 +402,7 @@ static long do_handle_open(int mountdirfd, struct file_handle __user *ufh, if (retval) return retval; - CLASS(get_unused_fd, fd)(O_CLOEXEC); + CLASS(get_unused_fd, fd)(open_flag); if (fd < 0) return fd; diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index cc57367fb641..a07b8cf73ae2 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -2608,10 +2608,6 @@ void __mark_inode_dirty(struct inode *inode, int flags) wakeup_bdi = inode_io_list_move_locked(inode, wb, dirty_list); - spin_unlock(&wb->list_lock); - spin_unlock(&inode->i_lock); - trace_writeback_dirty_inode_enqueue(inode); - /* * If this is the first dirty inode for this bdi, * we have to wake-up the corresponding bdi thread @@ -2621,6 +2617,11 @@ void __mark_inode_dirty(struct inode *inode, int flags) if (wakeup_bdi && (wb->bdi->capabilities & BDI_CAP_WRITEBACK)) wb_wakeup_delayed(wb); + + spin_unlock(&wb->list_lock); + spin_unlock(&inode->i_lock); + trace_writeback_dirty_inode_enqueue(inode); + return; } } diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index ecb869e895ab..67c2318bfc42 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -289,11 +289,6 @@ void fuse_change_attributes_common(struct inode *inode, struct fuse_attr *attr, } } - if (attr->blksize != 0) - inode->i_blkbits = ilog2(attr->blksize); - else - inode->i_blkbits = inode->i_sb->s_blocksize_bits; - /* * Don't set the sticky bit in i_mode, unless we want the VFS * to check permissions. This prevents failures due to the diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c index 6f25d4cfea9f..b84f6af2eb4c 100644 --- a/fs/iomap/direct-io.c +++ b/fs/iomap/direct-io.c @@ -363,14 +363,14 @@ static int iomap_dio_bio_iter(struct iomap_iter *iter, struct iomap_dio *dio) if (iomap->flags & IOMAP_F_SHARED) dio->flags |= IOMAP_DIO_COW; - if (iomap->flags & IOMAP_F_NEW) { + if (iomap->flags & IOMAP_F_NEW) need_zeroout = true; - } else if (iomap->type == IOMAP_MAPPED) { - if (iomap_dio_can_use_fua(iomap, dio)) - bio_opf |= REQ_FUA; - else - dio->flags &= ~IOMAP_DIO_WRITE_THROUGH; - } + else if (iomap->type == IOMAP_MAPPED && + iomap_dio_can_use_fua(iomap, dio)) + bio_opf |= REQ_FUA; + + if (!(bio_opf & REQ_FUA)) + dio->flags &= ~IOMAP_DIO_WRITE_THROUGH; /* * We can only do deferred completion for pure overwrites that diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c index b3971e91e8eb..38861ca04899 100644 --- a/fs/jbd2/checkpoint.c +++ b/fs/jbd2/checkpoint.c @@ -285,6 +285,7 @@ restart: retry: if (batch_count) __flush_batch(journal, &batch_count); + cond_resched(); spin_lock(&journal->j_list_lock); goto restart; } diff --git a/fs/kernfs/inode.c b/fs/kernfs/inode.c index 3c293a5a21b1..457f91c412d4 100644 --- a/fs/kernfs/inode.c +++ b/fs/kernfs/inode.c @@ -142,9 +142,9 @@ ssize_t kernfs_iop_listxattr(struct dentry *dentry, char *buf, size_t size) struct kernfs_node *kn = kernfs_dentry_node(dentry); struct kernfs_iattrs *attrs; - attrs = kernfs_iattrs_noalloc(kn); + attrs = kernfs_iattrs(kn); if (!attrs) - return -ENODATA; + return -ENOMEM; return simple_xattr_list(d_inode(dentry), &attrs->xattrs, buf, size); } diff --git a/fs/namespace.c b/fs/namespace.c index ddfd4457d338..ae6d1312b184 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -1197,10 +1197,7 @@ static void commit_tree(struct mount *mnt) if (!mnt_ns_attached(mnt)) { for (struct mount *m = mnt; m; m = next_mnt(m, mnt)) - if (unlikely(mnt_ns_attached(m))) - m = skip_mnt_tree(m); - else - mnt_add_to_ns(n, m); + mnt_add_to_ns(n, m); n->nr_mounts += n->pending_mounts; n->pending_mounts = 0; } @@ -2704,6 +2701,7 @@ static int attach_recursive_mnt(struct mount *source_mnt, lock_mnt_tree(child); q = __lookup_mnt(&child->mnt_parent->mnt, child->mnt_mountpoint); + commit_tree(child); if (q) { struct mountpoint *mp = root.mp; struct mount *r = child; @@ -2713,7 +2711,6 @@ static int attach_recursive_mnt(struct mount *source_mnt, mp = shorter; mnt_change_mountpoint(r, mp, q); } - commit_tree(child); } unpin_mountpoint(&root); unlock_mount_hash(); @@ -2862,6 +2859,19 @@ static int graft_tree(struct mount *mnt, struct mount *p, struct mountpoint *mp) return attach_recursive_mnt(mnt, p, mp); } +static int may_change_propagation(const struct mount *m) +{ + struct mnt_namespace *ns = m->mnt_ns; + + // it must be mounted in some namespace + if (IS_ERR_OR_NULL(ns)) // is_mounted() + return -EINVAL; + // and the caller must be admin in userns of that namespace + if (!ns_capable(ns->user_ns, CAP_SYS_ADMIN)) + return -EPERM; + return 0; +} + /* * Sanity check the flags to change_mnt_propagation. */ @@ -2898,10 +2908,10 @@ static int do_change_type(struct path *path, int ms_flags) return -EINVAL; namespace_lock(); - if (!check_mnt(mnt)) { - err = -EINVAL; + err = may_change_propagation(mnt); + if (err) goto out_unlock; - } + if (type == MS_SHARED) { err = invent_group_ids(mnt, recurse); if (err) @@ -3347,18 +3357,11 @@ static int do_set_group(struct path *from_path, struct path *to_path) namespace_lock(); - err = -EINVAL; - /* To and From must be mounted */ - if (!is_mounted(&from->mnt)) - goto out; - if (!is_mounted(&to->mnt)) - goto out; - - err = -EPERM; - /* We should be allowed to modify mount namespaces of both mounts */ - if (!ns_capable(from->mnt_ns->user_ns, CAP_SYS_ADMIN)) + err = may_change_propagation(from); + if (err) goto out; - if (!ns_capable(to->mnt_ns->user_ns, CAP_SYS_ADMIN)) + err = may_change_propagation(to); + if (err) goto out; err = -EINVAL; @@ -4551,20 +4554,10 @@ SYSCALL_DEFINE5(move_mount, if (flags & MOVE_MOUNT_SET_GROUP) mflags |= MNT_TREE_PROPAGATION; if (flags & MOVE_MOUNT_BENEATH) mflags |= MNT_TREE_BENEATH; - lflags = 0; - if (flags & MOVE_MOUNT_F_SYMLINKS) lflags |= LOOKUP_FOLLOW; - if (flags & MOVE_MOUNT_F_AUTOMOUNTS) lflags |= LOOKUP_AUTOMOUNT; uflags = 0; - if (flags & MOVE_MOUNT_F_EMPTY_PATH) uflags = AT_EMPTY_PATH; - from_name = getname_maybe_null(from_pathname, uflags); - if (IS_ERR(from_name)) - return PTR_ERR(from_name); + if (flags & MOVE_MOUNT_T_EMPTY_PATH) + uflags = AT_EMPTY_PATH; - lflags = 0; - if (flags & MOVE_MOUNT_T_SYMLINKS) lflags |= LOOKUP_FOLLOW; - if (flags & MOVE_MOUNT_T_AUTOMOUNTS) lflags |= LOOKUP_AUTOMOUNT; - uflags = 0; - if (flags & MOVE_MOUNT_T_EMPTY_PATH) uflags = AT_EMPTY_PATH; to_name = getname_maybe_null(to_pathname, uflags); if (IS_ERR(to_name)) return PTR_ERR(to_name); @@ -4577,11 +4570,24 @@ SYSCALL_DEFINE5(move_mount, to_path = fd_file(f_to)->f_path; path_get(&to_path); } else { + lflags = 0; + if (flags & MOVE_MOUNT_T_SYMLINKS) + lflags |= LOOKUP_FOLLOW; + if (flags & MOVE_MOUNT_T_AUTOMOUNTS) + lflags |= LOOKUP_AUTOMOUNT; ret = filename_lookup(to_dfd, to_name, lflags, &to_path, NULL); if (ret) return ret; } + uflags = 0; + if (flags & MOVE_MOUNT_F_EMPTY_PATH) + uflags = AT_EMPTY_PATH; + + from_name = getname_maybe_null(from_pathname, uflags); + if (IS_ERR(from_name)) + return PTR_ERR(from_name); + if (!from_name && from_dfd >= 0) { CLASS(fd_raw, f_from)(from_dfd); if (fd_empty(f_from)) @@ -4590,6 +4596,11 @@ SYSCALL_DEFINE5(move_mount, return vfs_move_mount(&fd_file(f_from)->f_path, &to_path, mflags); } + lflags = 0; + if (flags & MOVE_MOUNT_F_SYMLINKS) + lflags |= LOOKUP_FOLLOW; + if (flags & MOVE_MOUNT_F_AUTOMOUNTS) + lflags |= LOOKUP_AUTOMOUNT; ret = filename_lookup(from_dfd, from_name, lflags, &from_path, NULL); if (ret) return ret; @@ -5176,7 +5187,8 @@ SYSCALL_DEFINE5(open_tree_attr, int, dfd, const char __user *, filename, int ret; struct mount_kattr kattr = {}; - kattr.kflags = MOUNT_KATTR_IDMAP_REPLACE; + if (flags & OPEN_TREE_CLONE) + kattr.kflags = MOUNT_KATTR_IDMAP_REPLACE; if (flags & AT_RECURSIVE) kattr.kflags |= MOUNT_KATTR_RECURSE; diff --git a/fs/netfs/read_collect.c b/fs/netfs/read_collect.c index 3e804da1e1eb..a95e7aadafd0 100644 --- a/fs/netfs/read_collect.c +++ b/fs/netfs/read_collect.c @@ -281,8 +281,10 @@ reassess: } else if (test_bit(NETFS_RREQ_SHORT_TRANSFER, &rreq->flags)) { notes |= MADE_PROGRESS; } else { - if (!stream->failed) + if (!stream->failed) { stream->transferred += transferred; + stream->transferred_valid = true; + } if (front->transferred < front->len) set_bit(NETFS_RREQ_SHORT_TRANSFER, &rreq->flags); notes |= MADE_PROGRESS; diff --git a/fs/netfs/write_collect.c b/fs/netfs/write_collect.c index 0f3a36852a4d..cbf3d9194c7b 100644 --- a/fs/netfs/write_collect.c +++ b/fs/netfs/write_collect.c @@ -254,6 +254,7 @@ reassess_streams: if (front->start + front->transferred > stream->collected_to) { stream->collected_to = front->start + front->transferred; stream->transferred = stream->collected_to - wreq->start; + stream->transferred_valid = true; notes |= MADE_PROGRESS; } if (test_bit(NETFS_SREQ_FAILED, &front->flags)) { @@ -356,6 +357,7 @@ bool netfs_write_collection(struct netfs_io_request *wreq) { struct netfs_inode *ictx = netfs_inode(wreq->inode); size_t transferred; + bool transferred_valid = false; int s; _enter("R=%x", wreq->debug_id); @@ -376,12 +378,16 @@ bool netfs_write_collection(struct netfs_io_request *wreq) continue; if (!list_empty(&stream->subrequests)) return false; - if (stream->transferred < transferred) + if (stream->transferred_valid && + stream->transferred < transferred) { transferred = stream->transferred; + transferred_valid = true; + } } /* Okay, declare that all I/O is complete. */ - wreq->transferred = transferred; + if (transferred_valid) + wreq->transferred = transferred; trace_netfs_rreq(wreq, netfs_rreq_trace_write_done); if (wreq->io_streams[1].active && diff --git a/fs/netfs/write_issue.c b/fs/netfs/write_issue.c index 50bee2c4130d..0584cba1a043 100644 --- a/fs/netfs/write_issue.c +++ b/fs/netfs/write_issue.c @@ -118,12 +118,12 @@ struct netfs_io_request *netfs_create_write_req(struct address_space *mapping, wreq->io_streams[0].prepare_write = ictx->ops->prepare_write; wreq->io_streams[0].issue_write = ictx->ops->issue_write; wreq->io_streams[0].collected_to = start; - wreq->io_streams[0].transferred = LONG_MAX; + wreq->io_streams[0].transferred = 0; wreq->io_streams[1].stream_nr = 1; wreq->io_streams[1].source = NETFS_WRITE_TO_CACHE; wreq->io_streams[1].collected_to = start; - wreq->io_streams[1].transferred = LONG_MAX; + wreq->io_streams[1].transferred = 0; if (fscache_resources_valid(&wreq->cache_resources)) { wreq->io_streams[1].avail = true; wreq->io_streams[1].active = true; diff --git a/fs/nfsd/localio.c b/fs/nfsd/localio.c index 4f6468eb2adf..cb237f1b902a 100644 --- a/fs/nfsd/localio.c +++ b/fs/nfsd/localio.c @@ -103,10 +103,11 @@ nfsd_open_local_fh(struct net *net, struct auth_domain *dom, if (nfsd_file_get(new) == NULL) goto again; /* - * Drop the ref we were going to install and the - * one we were going to return. + * Drop the ref we were going to install (both file and + * net) and the one we were going to return (only file). */ nfsd_file_put(localio); + nfsd_net_put(net); nfsd_file_put(localio); localio = new; } diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 98ab55ba3ced..edf050766e57 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -470,7 +470,15 @@ static int __nfsd_setattr(struct dentry *dentry, struct iattr *iap) if (!iap->ia_valid) return 0; - iap->ia_valid |= ATTR_CTIME; + /* + * If ATTR_DELEG is set, then this is an update from a client that + * holds a delegation. If this is an update for only the atime, the + * ctime should not be changed. If the update contains the mtime + * too, then ATTR_CTIME should already be set. + */ + if (!(iap->ia_valid & ATTR_DELEG)) + iap->ia_valid |= ATTR_CTIME; + return notify_change(&nop_mnt_idmap, dentry, iap, NULL); } diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c index 70b8687dc45e..dbd63a74df4b 100644 --- a/fs/overlayfs/dir.c +++ b/fs/overlayfs/dir.c @@ -225,7 +225,7 @@ struct dentry *ovl_create_temp(struct ovl_fs *ofs, struct dentry *workdir, struct ovl_cattr *attr) { struct dentry *ret; - inode_lock(workdir->d_inode); + inode_lock_nested(workdir->d_inode, I_MUTEX_PARENT); ret = ovl_create_real(ofs, workdir, ovl_lookup_temp(ofs, workdir), attr); inode_unlock(workdir->d_inode); diff --git a/fs/overlayfs/util.c b/fs/overlayfs/util.c index a33115e7384c..41033bac96cb 100644 --- a/fs/overlayfs/util.c +++ b/fs/overlayfs/util.c @@ -1552,7 +1552,8 @@ void ovl_copyattr(struct inode *inode) int ovl_parent_lock(struct dentry *parent, struct dentry *child) { inode_lock_nested(parent->d_inode, I_MUTEX_PARENT); - if (!child || child->d_parent == parent) + if (!child || + (!d_unhashed(child) && child->d_parent == parent)) return 0; inode_unlock(parent->d_inode); diff --git a/fs/pidfs.c b/fs/pidfs.c index edc35522d75c..108e7527f837 100644 --- a/fs/pidfs.c +++ b/fs/pidfs.c @@ -296,12 +296,12 @@ static __u32 pidfs_coredump_mask(unsigned long mm_flags) static long pidfd_info(struct file *file, unsigned int cmd, unsigned long arg) { struct pidfd_info __user *uinfo = (struct pidfd_info __user *)arg; + struct task_struct *task __free(put_task) = NULL; struct pid *pid = pidfd_pid(file); size_t usize = _IOC_SIZE(cmd); struct pidfd_info kinfo = {}; struct pidfs_exit_info *exit_info; struct user_namespace *user_ns; - struct task_struct *task; struct pidfs_attr *attr; const struct cred *c; __u64 mask; diff --git a/fs/pnode.c b/fs/pnode.c index 81f7599bdac4..6f7d02f3fa98 100644 --- a/fs/pnode.c +++ b/fs/pnode.c @@ -111,7 +111,8 @@ void change_mnt_propagation(struct mount *mnt, int type) return; } if (IS_MNT_SHARED(mnt)) { - m = propagation_source(mnt); + if (type == MS_SLAVE || !hlist_empty(&mnt->mnt_slave_list)) + m = propagation_source(mnt); if (list_empty(&mnt->mnt_share)) { mnt_release_group_id(mnt); } else { @@ -637,10 +638,11 @@ void propagate_umount(struct list_head *set) } // now to_umount consists of all acceptable candidates - // deal with reparenting of remaining overmounts on those + // deal with reparenting of surviving overmounts on those list_for_each_entry(m, &to_umount, mnt_list) { - if (m->overmount) - reparent(m->overmount); + struct mount *over = m->overmount; + if (over && !will_be_unmounted(over)) + reparent(over); } // and fold them into the set diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 3d6d8a9f13fc..29cca0e6d0ff 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -340,8 +340,8 @@ static int proc_maps_open(struct inode *inode, struct file *file, priv->inode = inode; priv->mm = proc_mem_open(inode, PTRACE_MODE_READ); - if (IS_ERR_OR_NULL(priv->mm)) { - int err = priv->mm ? PTR_ERR(priv->mm) : -ESRCH; + if (IS_ERR(priv->mm)) { + int err = PTR_ERR(priv->mm); seq_release_private(inode, file); return err; @@ -1148,10 +1148,13 @@ static int smaps_hugetlb_range(pte_t *pte, unsigned long hmask, { struct mem_size_stats *mss = walk->private; struct vm_area_struct *vma = walk->vma; - pte_t ptent = huge_ptep_get(walk->mm, addr, pte); struct folio *folio = NULL; bool present = false; + spinlock_t *ptl; + pte_t ptent; + ptl = huge_pte_lock(hstate_vma(vma), walk->mm, pte); + ptent = huge_ptep_get(walk->mm, addr, pte); if (pte_present(ptent)) { folio = page_folio(pte_page(ptent)); present = true; @@ -1170,6 +1173,7 @@ static int smaps_hugetlb_range(pte_t *pte, unsigned long hmask, else mss->private_hugetlb += huge_page_size(hstate_vma(vma)); } + spin_unlock(ptl); return 0; } #else @@ -2017,12 +2021,14 @@ static int pagemap_hugetlb_range(pte_t *ptep, unsigned long hmask, struct pagemapread *pm = walk->private; struct vm_area_struct *vma = walk->vma; u64 flags = 0, frame = 0; + spinlock_t *ptl; int err = 0; pte_t pte; if (vma->vm_flags & VM_SOFTDIRTY) flags |= PM_SOFT_DIRTY; + ptl = huge_pte_lock(hstate_vma(vma), walk->mm, ptep); pte = huge_ptep_get(walk->mm, addr, ptep); if (pte_present(pte)) { struct folio *folio = page_folio(pte_page(pte)); @@ -2050,11 +2056,12 @@ static int pagemap_hugetlb_range(pte_t *ptep, unsigned long hmask, err = add_to_pagemap(&pme, pm); if (err) - return err; + break; if (pm->show_pfn && (flags & PM_PRESENT)) frame++; } + spin_unlock(ptl); cond_resched(); return err; @@ -3128,17 +3135,22 @@ static int gather_pte_stats(pmd_t *pmd, unsigned long addr, static int gather_hugetlb_stats(pte_t *pte, unsigned long hmask, unsigned long addr, unsigned long end, struct mm_walk *walk) { - pte_t huge_pte = huge_ptep_get(walk->mm, addr, pte); + pte_t huge_pte; struct numa_maps *md; struct page *page; + spinlock_t *ptl; + ptl = huge_pte_lock(hstate_vma(walk->vma), walk->mm, pte); + huge_pte = huge_ptep_get(walk->mm, addr, pte); if (!pte_present(huge_pte)) - return 0; + goto out; page = pte_page(huge_pte); md = walk->private; gather_stats(page, md, pte_dirty(huge_pte), 1); +out: + spin_unlock(ptl); return 0; } diff --git a/fs/smb/client/cifs_spnego.c b/fs/smb/client/cifs_spnego.c index bc1c1e9b288a..43b86fa4d695 100644 --- a/fs/smb/client/cifs_spnego.c +++ b/fs/smb/client/cifs_spnego.c @@ -124,55 +124,44 @@ cifs_get_spnego_key(struct cifs_ses *sesInfo, dp = description; /* start with version and hostname portion of UNC string */ spnego_key = ERR_PTR(-EINVAL); - sprintf(dp, "ver=0x%x;host=%s;", CIFS_SPNEGO_UPCALL_VERSION, - hostname); - dp = description + strlen(description); + dp += sprintf(dp, "ver=0x%x;host=%s;", CIFS_SPNEGO_UPCALL_VERSION, + hostname); /* add the server address */ if (server->dstaddr.ss_family == AF_INET) - sprintf(dp, "ip4=%pI4", &sa->sin_addr); + dp += sprintf(dp, "ip4=%pI4", &sa->sin_addr); else if (server->dstaddr.ss_family == AF_INET6) - sprintf(dp, "ip6=%pI6", &sa6->sin6_addr); + dp += sprintf(dp, "ip6=%pI6", &sa6->sin6_addr); else goto out; - dp = description + strlen(description); - /* for now, only sec=krb5 and sec=mskrb5 and iakerb are valid */ if (server->sec_kerberos) - sprintf(dp, ";sec=krb5"); + dp += sprintf(dp, ";sec=krb5"); else if (server->sec_mskerberos) - sprintf(dp, ";sec=mskrb5"); + dp += sprintf(dp, ";sec=mskrb5"); else if (server->sec_iakerb) - sprintf(dp, ";sec=iakerb"); + dp += sprintf(dp, ";sec=iakerb"); else { cifs_dbg(VFS, "unknown or missing server auth type, use krb5\n"); - sprintf(dp, ";sec=krb5"); + dp += sprintf(dp, ";sec=krb5"); } - dp = description + strlen(description); - sprintf(dp, ";uid=0x%x", - from_kuid_munged(&init_user_ns, sesInfo->linux_uid)); + dp += sprintf(dp, ";uid=0x%x", + from_kuid_munged(&init_user_ns, sesInfo->linux_uid)); - dp = description + strlen(description); - sprintf(dp, ";creduid=0x%x", + dp += sprintf(dp, ";creduid=0x%x", from_kuid_munged(&init_user_ns, sesInfo->cred_uid)); - if (sesInfo->user_name) { - dp = description + strlen(description); - sprintf(dp, ";user=%s", sesInfo->user_name); - } + if (sesInfo->user_name) + dp += sprintf(dp, ";user=%s", sesInfo->user_name); - dp = description + strlen(description); - sprintf(dp, ";pid=0x%x", current->pid); + dp += sprintf(dp, ";pid=0x%x", current->pid); - if (sesInfo->upcall_target == UPTARGET_MOUNT) { - dp = description + strlen(description); - sprintf(dp, ";upcall_target=mount"); - } else { - dp = description + strlen(description); - sprintf(dp, ";upcall_target=app"); - } + if (sesInfo->upcall_target == UPTARGET_MOUNT) + dp += sprintf(dp, ";upcall_target=mount"); + else + dp += sprintf(dp, ";upcall_target=app"); cifs_dbg(FYI, "key description = %s\n", description); saved_cred = override_creds(spnego_cred); diff --git a/fs/smb/client/cifsfs.h b/fs/smb/client/cifsfs.h index 487f39cff77e..3ce7c614ccc0 100644 --- a/fs/smb/client/cifsfs.h +++ b/fs/smb/client/cifsfs.h @@ -145,6 +145,6 @@ extern const struct export_operations cifs_export_ops; #endif /* CONFIG_CIFS_NFSD_EXPORT */ /* when changing internal version - update following two lines at same time */ -#define SMB3_PRODUCT_BUILD 55 -#define CIFS_VERSION "2.55" +#define SMB3_PRODUCT_BUILD 56 +#define CIFS_VERSION "2.56" #endif /* _CIFSFS_H */ diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h index e6830ab3a546..1e64a4fb6af0 100644 --- a/fs/smb/client/cifsglob.h +++ b/fs/smb/client/cifsglob.h @@ -1732,6 +1732,7 @@ struct mid_q_entry { int mid_rc; /* rc for MID_RC */ __le16 command; /* smb command code */ unsigned int optype; /* operation type */ + spinlock_t mid_lock; bool wait_cancelled:1; /* Cancelled while waiting for response */ bool deleted_from_q:1; /* Whether Mid has been dequeued frem pending_mid_q */ bool large_buf:1; /* if valid response, is pointer to large buf */ @@ -2036,6 +2037,9 @@ require use of the stronger protocol */ * cifsFileInfo->file_info_lock cifsFileInfo->count cifs_new_fileinfo * ->invalidHandle initiate_cifs_search * ->oplock_break_cancelled + * mid_q_entry->mid_lock mid_q_entry->callback alloc_mid + * smb2_mid_entry_alloc + * (Any fields of mid_q_entry that will need protection) ****************************************************************************/ #ifdef DECLARE_GLOBALS_HERE @@ -2375,6 +2379,23 @@ static inline bool cifs_netbios_name(const char *name, size_t namelen) return ret; } +/* + * Execute mid callback atomically - ensures callback runs exactly once + * and prevents sleeping in atomic context. + */ +static inline void mid_execute_callback(struct mid_q_entry *mid) +{ + void (*callback)(struct mid_q_entry *mid); + + spin_lock(&mid->mid_lock); + callback = mid->callback; + mid->callback = NULL; /* Mark as executed, */ + spin_unlock(&mid->mid_lock); + + if (callback) + callback(mid); +} + #define CIFS_REPARSE_SUPPORT(tcon) \ ((tcon)->posix_extensions || \ (le32_to_cpu((tcon)->fsAttrInfo.Attributes) & \ diff --git a/fs/smb/client/cifstransport.c b/fs/smb/client/cifstransport.c index 352dafb888dd..e98b95eff8c9 100644 --- a/fs/smb/client/cifstransport.c +++ b/fs/smb/client/cifstransport.c @@ -46,6 +46,7 @@ alloc_mid(const struct smb_hdr *smb_buffer, struct TCP_Server_Info *server) temp = mempool_alloc(cifs_mid_poolp, GFP_NOFS); memset(temp, 0, sizeof(struct mid_q_entry)); kref_init(&temp->refcount); + spin_lock_init(&temp->mid_lock); temp->mid = get_mid(smb_buffer); temp->pid = current->pid; temp->command = cpu_to_le16(smb_buffer->Command); @@ -345,16 +346,15 @@ SendReceive(const unsigned int xid, struct cifs_ses *ses, rc = wait_for_response(server, midQ); if (rc != 0) { send_cancel(server, &rqst, midQ); - spin_lock(&server->mid_queue_lock); - if (midQ->mid_state == MID_REQUEST_SUBMITTED || - midQ->mid_state == MID_RESPONSE_RECEIVED) { + spin_lock(&midQ->mid_lock); + if (midQ->callback) { /* no longer considered to be "in-flight" */ midQ->callback = release_mid; - spin_unlock(&server->mid_queue_lock); + spin_unlock(&midQ->mid_lock); add_credits(server, &credits, 0); return rc; } - spin_unlock(&server->mid_queue_lock); + spin_unlock(&midQ->mid_lock); } rc = cifs_sync_mid_result(midQ, server); @@ -527,15 +527,14 @@ SendReceiveBlockingLock(const unsigned int xid, struct cifs_tcon *tcon, rc = wait_for_response(server, midQ); if (rc) { send_cancel(server, &rqst, midQ); - spin_lock(&server->mid_queue_lock); - if (midQ->mid_state == MID_REQUEST_SUBMITTED || - midQ->mid_state == MID_RESPONSE_RECEIVED) { + spin_lock(&midQ->mid_lock); + if (midQ->callback) { /* no longer considered to be "in-flight" */ midQ->callback = release_mid; - spin_unlock(&server->mid_queue_lock); + spin_unlock(&midQ->mid_lock); return rc; } - spin_unlock(&server->mid_queue_lock); + spin_unlock(&midQ->mid_lock); } /* We got the response - restart system call. */ diff --git a/fs/smb/client/compress.c b/fs/smb/client/compress.c index 766b4de13da7..db709f5cd2e1 100644 --- a/fs/smb/client/compress.c +++ b/fs/smb/client/compress.c @@ -155,58 +155,29 @@ static int cmp_bkt(const void *_a, const void *_b) } /* - * TODO: - * Support other iter types, if required. - * Only ITER_XARRAY is supported for now. + * Collect some 2K samples with 2K gaps between. */ -static int collect_sample(const struct iov_iter *iter, ssize_t max, u8 *sample) +static int collect_sample(const struct iov_iter *source, ssize_t max, u8 *sample) { - struct folio *folios[16], *folio; - unsigned int nr, i, j, npages; - loff_t start = iter->xarray_start + iter->iov_offset; - pgoff_t last, index = start / PAGE_SIZE; - size_t len, off, foff; - void *p; - int s = 0; - - last = (start + max - 1) / PAGE_SIZE; - do { - nr = xa_extract(iter->xarray, (void **)folios, index, last, ARRAY_SIZE(folios), - XA_PRESENT); - if (nr == 0) - return -EIO; - - for (i = 0; i < nr; i++) { - folio = folios[i]; - npages = folio_nr_pages(folio); - foff = start - folio_pos(folio); - off = foff % PAGE_SIZE; - - for (j = foff / PAGE_SIZE; j < npages; j++) { - size_t len2; - - len = min_t(size_t, max, PAGE_SIZE - off); - len2 = min_t(size_t, len, SZ_2K); - - p = kmap_local_page(folio_page(folio, j)); - memcpy(&sample[s], p, len2); - kunmap_local(p); - - s += len2; - - if (len2 < SZ_2K || s >= max - SZ_2K) - return s; - - max -= len; - if (max <= 0) - return s; - - start += len; - off = 0; - index++; - } - } - } while (nr == ARRAY_SIZE(folios)); + struct iov_iter iter = *source; + size_t s = 0; + + while (iov_iter_count(&iter) >= SZ_2K) { + size_t part = umin(umin(iov_iter_count(&iter), SZ_2K), max); + size_t n; + + n = copy_from_iter(sample + s, part, &iter); + if (n != part) + return -EFAULT; + + s += n; + max -= n; + + if (iov_iter_count(&iter) < PAGE_SIZE - SZ_2K) + break; + + iov_iter_advance(&iter, SZ_2K); + } return s; } diff --git a/fs/smb/client/connect.c b/fs/smb/client/connect.c index 587845a2452d..dd12f3eb61dc 100644 --- a/fs/smb/client/connect.c +++ b/fs/smb/client/connect.c @@ -335,7 +335,7 @@ cifs_abort_connection(struct TCP_Server_Info *server) cifs_dbg(FYI, "%s: issuing mid callbacks\n", __func__); list_for_each_entry_safe(mid, nmid, &retry_list, qhead) { list_del_init(&mid->qhead); - mid->callback(mid); + mid_execute_callback(mid); release_mid(mid); } @@ -919,7 +919,7 @@ is_smb_response(struct TCP_Server_Info *server, unsigned char type) list_del_init(&mid->qhead); mid->mid_rc = mid_rc; mid->mid_state = MID_RC; - mid->callback(mid); + mid_execute_callback(mid); release_mid(mid); } @@ -1117,7 +1117,7 @@ clean_demultiplex_info(struct TCP_Server_Info *server) mid_entry = list_entry(tmp, struct mid_q_entry, qhead); cifs_dbg(FYI, "Callback mid %llu\n", mid_entry->mid); list_del_init(&mid_entry->qhead); - mid_entry->callback(mid_entry); + mid_execute_callback(mid_entry); release_mid(mid_entry); } /* 1/8th of sec is more than enough time for them to exit */ @@ -1394,7 +1394,7 @@ next_pdu: } if (!mids[i]->multiRsp || mids[i]->multiEnd) - mids[i]->callback(mids[i]); + mid_execute_callback(mids[i]); release_mid(mids[i]); } else if (server->ops->is_oplock_break && @@ -4205,7 +4205,6 @@ retry: return 0; } - server->lstrp = jiffies; server->tcpStatus = CifsInNegotiate; server->neg_start = jiffies; spin_unlock(&server->srv_lock); diff --git a/fs/smb/client/inode.c b/fs/smb/client/inode.c index 75be4b46bc6f..fe453a4b3dc8 100644 --- a/fs/smb/client/inode.c +++ b/fs/smb/client/inode.c @@ -1943,15 +1943,24 @@ int cifs_unlink(struct inode *dir, struct dentry *dentry) struct cifs_sb_info *cifs_sb = CIFS_SB(sb); struct tcon_link *tlink; struct cifs_tcon *tcon; + __u32 dosattr = 0, origattr = 0; struct TCP_Server_Info *server; struct iattr *attrs = NULL; - __u32 dosattr = 0, origattr = 0; + bool rehash = false; cifs_dbg(FYI, "cifs_unlink, dir=0x%p, dentry=0x%p\n", dir, dentry); if (unlikely(cifs_forced_shutdown(cifs_sb))) return -EIO; + /* Unhash dentry in advance to prevent any concurrent opens */ + spin_lock(&dentry->d_lock); + if (!d_unhashed(dentry)) { + __d_drop(dentry); + rehash = true; + } + spin_unlock(&dentry->d_lock); + tlink = cifs_sb_tlink(cifs_sb); if (IS_ERR(tlink)) return PTR_ERR(tlink); @@ -2003,7 +2012,8 @@ psx_del_no_retry: cifs_drop_nlink(inode); } } else if (rc == -ENOENT) { - d_drop(dentry); + if (simple_positive(dentry)) + d_delete(dentry); } else if (rc == -EBUSY) { if (server->ops->rename_pending_delete) { rc = server->ops->rename_pending_delete(full_path, @@ -2056,6 +2066,8 @@ unlink_out: kfree(attrs); free_xid(xid); cifs_put_tlink(tlink); + if (rehash) + d_rehash(dentry); return rc; } @@ -2462,6 +2474,7 @@ cifs_rename2(struct mnt_idmap *idmap, struct inode *source_dir, struct cifs_sb_info *cifs_sb; struct tcon_link *tlink; struct cifs_tcon *tcon; + bool rehash = false; unsigned int xid; int rc, tmprc; int retry_count = 0; @@ -2477,6 +2490,17 @@ cifs_rename2(struct mnt_idmap *idmap, struct inode *source_dir, if (unlikely(cifs_forced_shutdown(cifs_sb))) return -EIO; + /* + * Prevent any concurrent opens on the target by unhashing the dentry. + * VFS already unhashes the target when renaming directories. + */ + if (d_is_positive(target_dentry) && !d_is_dir(target_dentry)) { + if (!d_unhashed(target_dentry)) { + d_drop(target_dentry); + rehash = true; + } + } + tlink = cifs_sb_tlink(cifs_sb); if (IS_ERR(tlink)) return PTR_ERR(tlink); @@ -2518,6 +2542,8 @@ cifs_rename2(struct mnt_idmap *idmap, struct inode *source_dir, } } + if (!rc) + rehash = false; /* * No-replace is the natural behavior for CIFS, so skip unlink hacks. */ @@ -2576,12 +2602,16 @@ unlink_target: goto cifs_rename_exit; rc = cifs_do_rename(xid, source_dentry, from_name, target_dentry, to_name); + if (!rc) + rehash = false; } /* force revalidate to go get info when needed */ CIFS_I(source_dir)->time = CIFS_I(target_dir)->time = 0; cifs_rename_exit: + if (rehash) + d_rehash(target_dentry); kfree(info_buf_source); free_dentry_path(page2); free_dentry_path(page1); diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c index ad8947434b71..3b251de874ec 100644 --- a/fs/smb/client/smb2ops.c +++ b/fs/smb/client/smb2ops.c @@ -772,6 +772,13 @@ next_iface: bytes_left -= sizeof(*p); break; } + /* Validate that Next doesn't point beyond the buffer */ + if (next > bytes_left) { + cifs_dbg(VFS, "%s: invalid Next pointer %zu > %zd\n", + __func__, next, bytes_left); + rc = -EINVAL; + goto out; + } p = (struct network_interface_info_ioctl_rsp *)((u8 *)p+next); bytes_left -= next; } @@ -783,7 +790,9 @@ next_iface: } /* Azure rounds the buffer size up 8, to a 16 byte boundary */ - if ((bytes_left > 8) || p->Next) + if ((bytes_left > 8) || + (bytes_left >= offsetof(struct network_interface_info_ioctl_rsp, Next) + + sizeof(p->Next) && p->Next)) cifs_dbg(VFS, "%s: incomplete interface info\n", __func__); ses->iface_last_update = jiffies; @@ -4805,7 +4814,7 @@ static void smb2_decrypt_offload(struct work_struct *work) dw->server->ops->is_network_name_deleted(dw->buf, dw->server); - mid->callback(mid); + mid_execute_callback(mid); } else { spin_lock(&dw->server->srv_lock); if (dw->server->tcpStatus == CifsNeedReconnect) { @@ -4813,7 +4822,7 @@ static void smb2_decrypt_offload(struct work_struct *work) mid->mid_state = MID_RETRY_NEEDED; spin_unlock(&dw->server->mid_queue_lock); spin_unlock(&dw->server->srv_lock); - mid->callback(mid); + mid_execute_callback(mid); } else { spin_lock(&dw->server->mid_queue_lock); mid->mid_state = MID_REQUEST_SUBMITTED; diff --git a/fs/smb/client/smb2transport.c b/fs/smb/client/smb2transport.c index ff9ef7fcd010..bc0e92eb2b64 100644 --- a/fs/smb/client/smb2transport.c +++ b/fs/smb/client/smb2transport.c @@ -771,6 +771,7 @@ smb2_mid_entry_alloc(const struct smb2_hdr *shdr, temp = mempool_alloc(cifs_mid_poolp, GFP_NOFS); memset(temp, 0, sizeof(struct mid_q_entry)); kref_init(&temp->refcount); + spin_lock_init(&temp->mid_lock); temp->mid = le64_to_cpu(shdr->MessageId); temp->credits = credits > 0 ? credits : 1; temp->pid = current->pid; diff --git a/fs/smb/client/smbdirect.c b/fs/smb/client/smbdirect.c index c628e91c328b..02d6db431fd4 100644 --- a/fs/smb/client/smbdirect.c +++ b/fs/smb/client/smbdirect.c @@ -1337,10 +1337,6 @@ void smbd_destroy(struct TCP_Server_Info *server) log_rdma_event(INFO, "cancelling idle timer\n"); cancel_delayed_work_sync(&info->idle_timer_work); - log_rdma_event(INFO, "wait for all send posted to IB to finish\n"); - wait_event(info->wait_send_pending, - atomic_read(&info->send_pending) == 0); - /* It's not possible for upper layer to get to reassembly */ log_rdma_event(INFO, "drain the reassembly queue\n"); do { @@ -1986,7 +1982,11 @@ int smbd_send(struct TCP_Server_Info *server, */ wait_event(info->wait_send_pending, - atomic_read(&info->send_pending) == 0); + atomic_read(&info->send_pending) == 0 || + sc->status != SMBDIRECT_SOCKET_CONNECTED); + + if (sc->status != SMBDIRECT_SOCKET_CONNECTED && rc == 0) + rc = -EAGAIN; return rc; } diff --git a/fs/smb/client/transport.c b/fs/smb/client/transport.c index 32d528b4dd83..a61ba7f3fb86 100644 --- a/fs/smb/client/transport.c +++ b/fs/smb/client/transport.c @@ -1005,15 +1005,14 @@ compound_send_recv(const unsigned int xid, struct cifs_ses *ses, cifs_server_dbg(FYI, "Cancelling wait for mid %llu cmd: %d\n", midQ[i]->mid, le16_to_cpu(midQ[i]->command)); send_cancel(server, &rqst[i], midQ[i]); - spin_lock(&server->mid_queue_lock); + spin_lock(&midQ[i]->mid_lock); midQ[i]->wait_cancelled = true; - if (midQ[i]->mid_state == MID_REQUEST_SUBMITTED || - midQ[i]->mid_state == MID_RESPONSE_RECEIVED) { + if (midQ[i]->callback) { midQ[i]->callback = cifs_cancelled_callback; cancelled_mid[i] = true; credits[i].value = 0; } - spin_unlock(&server->mid_queue_lock); + spin_unlock(&midQ[i]->mid_lock); } } diff --git a/fs/smb/server/connection.c b/fs/smb/server/connection.c index 3f04a2977ba8..67c4f73398df 100644 --- a/fs/smb/server/connection.c +++ b/fs/smb/server/connection.c @@ -504,7 +504,8 @@ void ksmbd_conn_transport_destroy(void) { mutex_lock(&init_lock); ksmbd_tcp_destroy(); - ksmbd_rdma_destroy(); + ksmbd_rdma_stop_listening(); stop_sessions(); + ksmbd_rdma_destroy(); mutex_unlock(&init_lock); } diff --git a/fs/smb/server/connection.h b/fs/smb/server/connection.h index 31dd1caac1e8..2aa8084bb593 100644 --- a/fs/smb/server/connection.h +++ b/fs/smb/server/connection.h @@ -46,7 +46,12 @@ struct ksmbd_conn { struct mutex srv_mutex; int status; unsigned int cli_cap; - __be32 inet_addr; + union { + __be32 inet_addr; +#if IS_ENABLED(CONFIG_IPV6) + u8 inet6_addr[16]; +#endif + }; char *request_buf; struct ksmbd_transport *transport; struct nls_table *local_nls; diff --git a/fs/smb/server/oplock.c b/fs/smb/server/oplock.c index d7a8a580d013..a04d5702820d 100644 --- a/fs/smb/server/oplock.c +++ b/fs/smb/server/oplock.c @@ -1102,8 +1102,10 @@ void smb_send_parent_lease_break_noti(struct ksmbd_file *fp, if (!atomic_inc_not_zero(&opinfo->refcount)) continue; - if (ksmbd_conn_releasing(opinfo->conn)) + if (ksmbd_conn_releasing(opinfo->conn)) { + opinfo_put(opinfo); continue; + } oplock_break(opinfo, SMB2_OPLOCK_LEVEL_NONE, NULL); opinfo_put(opinfo); @@ -1139,8 +1141,11 @@ void smb_lazy_parent_lease_break_close(struct ksmbd_file *fp) if (!atomic_inc_not_zero(&opinfo->refcount)) continue; - if (ksmbd_conn_releasing(opinfo->conn)) + if (ksmbd_conn_releasing(opinfo->conn)) { + opinfo_put(opinfo); continue; + } + oplock_break(opinfo, SMB2_OPLOCK_LEVEL_NONE, NULL); opinfo_put(opinfo); } @@ -1343,8 +1348,10 @@ void smb_break_all_levII_oplock(struct ksmbd_work *work, struct ksmbd_file *fp, if (!atomic_inc_not_zero(&brk_op->refcount)) continue; - if (ksmbd_conn_releasing(brk_op->conn)) + if (ksmbd_conn_releasing(brk_op->conn)) { + opinfo_put(brk_op); continue; + } if (brk_op->is_lease && (brk_op->o_lease->state & (~(SMB2_LEASE_READ_CACHING_LE | diff --git a/fs/smb/server/transport_rdma.c b/fs/smb/server/transport_rdma.c index 8d366db5f605..5466aa8c39b1 100644 --- a/fs/smb/server/transport_rdma.c +++ b/fs/smb/server/transport_rdma.c @@ -2194,7 +2194,7 @@ int ksmbd_rdma_init(void) return 0; } -void ksmbd_rdma_destroy(void) +void ksmbd_rdma_stop_listening(void) { if (!smb_direct_listener.cm_id) return; @@ -2203,7 +2203,10 @@ void ksmbd_rdma_destroy(void) rdma_destroy_id(smb_direct_listener.cm_id); smb_direct_listener.cm_id = NULL; +} +void ksmbd_rdma_destroy(void) +{ if (smb_direct_wq) { destroy_workqueue(smb_direct_wq); smb_direct_wq = NULL; diff --git a/fs/smb/server/transport_rdma.h b/fs/smb/server/transport_rdma.h index 77aee4e5c9dc..a2291b77488a 100644 --- a/fs/smb/server/transport_rdma.h +++ b/fs/smb/server/transport_rdma.h @@ -54,13 +54,15 @@ struct smb_direct_data_transfer { #ifdef CONFIG_SMB_SERVER_SMBDIRECT int ksmbd_rdma_init(void); +void ksmbd_rdma_stop_listening(void); void ksmbd_rdma_destroy(void); bool ksmbd_rdma_capable_netdev(struct net_device *netdev); void init_smbd_max_io_size(unsigned int sz); unsigned int get_smbd_max_read_write_size(void); #else static inline int ksmbd_rdma_init(void) { return 0; } -static inline int ksmbd_rdma_destroy(void) { return 0; } +static inline void ksmbd_rdma_stop_listening(void) { } +static inline void ksmbd_rdma_destroy(void) { } static inline bool ksmbd_rdma_capable_netdev(struct net_device *netdev) { return false; } static inline void init_smbd_max_io_size(unsigned int sz) { } static inline unsigned int get_smbd_max_read_write_size(void) { return 0; } diff --git a/fs/smb/server/transport_tcp.c b/fs/smb/server/transport_tcp.c index b1df02e321b0..4337df97987d 100644 --- a/fs/smb/server/transport_tcp.c +++ b/fs/smb/server/transport_tcp.c @@ -85,7 +85,14 @@ static struct tcp_transport *alloc_transport(struct socket *client_sk) return NULL; } +#if IS_ENABLED(CONFIG_IPV6) + if (client_sk->sk->sk_family == AF_INET6) + memcpy(&conn->inet6_addr, &client_sk->sk->sk_v6_daddr, 16); + else + conn->inet_addr = inet_sk(client_sk->sk)->inet_daddr; +#else conn->inet_addr = inet_sk(client_sk->sk)->inet_daddr; +#endif conn->transport = KSMBD_TRANS(t); KSMBD_TRANS(t)->conn = conn; KSMBD_TRANS(t)->ops = &ksmbd_tcp_transport_ops; @@ -229,7 +236,6 @@ static int ksmbd_kthread_fn(void *p) { struct socket *client_sk = NULL; struct interface *iface = (struct interface *)p; - struct inet_sock *csk_inet; struct ksmbd_conn *conn; int ret; @@ -252,13 +258,27 @@ static int ksmbd_kthread_fn(void *p) /* * Limits repeated connections from clients with the same IP. */ - csk_inet = inet_sk(client_sk->sk); down_read(&conn_list_lock); list_for_each_entry(conn, &conn_list, conns_list) - if (csk_inet->inet_daddr == conn->inet_addr) { +#if IS_ENABLED(CONFIG_IPV6) + if (client_sk->sk->sk_family == AF_INET6) { + if (memcmp(&client_sk->sk->sk_v6_daddr, + &conn->inet6_addr, 16) == 0) { + ret = -EAGAIN; + break; + } + } else if (inet_sk(client_sk->sk)->inet_daddr == + conn->inet_addr) { + ret = -EAGAIN; + break; + } +#else + if (inet_sk(client_sk->sk)->inet_daddr == + conn->inet_addr) { ret = -EAGAIN; break; } +#endif up_read(&conn_list_lock); if (ret == -EAGAIN) continue; diff --git a/fs/splice.c b/fs/splice.c index 4d6df083e0c0..f5094b6d00a0 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -739,6 +739,9 @@ iter_file_splice_write(struct pipe_inode_info *pipe, struct file *out, sd.pos = kiocb.ki_pos; if (ret <= 0) break; + WARN_ONCE(ret > sd.total_len - left, + "Splice Exceeded! ret=%zd tot=%zu left=%zu\n", + ret, sd.total_len, left); sd.num_spliced += ret; sd.total_len -= ret; diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h index 1e6e9c10cea2..a8187281eb96 100644 --- a/fs/xfs/scrub/trace.h +++ b/fs/xfs/scrub/trace.h @@ -479,7 +479,7 @@ DECLARE_EVENT_CLASS(xchk_dqiter_class, __field(xfs_exntst_t, state) ), TP_fast_assign( - __entry->dev = cursor->sc->ip->i_mount->m_super->s_dev; + __entry->dev = cursor->sc->mp->m_super->s_dev; __entry->dqtype = cursor->dqtype; __entry->ino = cursor->quota_ip->i_ino; __entry->cur_id = cursor->id; diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 55a304cb3aef..f96fbf5c54c9 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -1101,9 +1101,6 @@ xfs_file_write_iter( if (xfs_is_shutdown(ip->i_mount)) return -EIO; - if (IS_DAX(inode)) - return xfs_file_dax_write(iocb, from); - if (iocb->ki_flags & IOCB_ATOMIC) { if (ocount < xfs_get_atomic_write_min(ip)) return -EINVAL; @@ -1116,6 +1113,9 @@ xfs_file_write_iter( return ret; } + if (IS_DAX(inode)) + return xfs_file_dax_write(iocb, from); + if (iocb->ki_flags & IOCB_DIRECT) { /* * Allow a directio write to fall back to a buffered diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h index 07fbdcc4cbf5..bd6d33557194 100644 --- a/fs/xfs/xfs_inode.h +++ b/fs/xfs/xfs_inode.h @@ -358,9 +358,20 @@ static inline bool xfs_inode_has_bigrtalloc(const struct xfs_inode *ip) static inline bool xfs_inode_can_hw_atomic_write(const struct xfs_inode *ip) { + if (IS_DAX(VFS_IC(ip))) + return false; + return xfs_inode_buftarg(ip)->bt_awu_max > 0; } +static inline bool xfs_inode_can_sw_atomic_write(const struct xfs_inode *ip) +{ + if (IS_DAX(VFS_IC(ip))) + return false; + + return xfs_can_sw_atomic_write(ip->i_mount); +} + /* * In-core inode flags. */ diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index fe1f74a3b6a3..e1051a530a50 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -219,7 +219,7 @@ xfs_bulk_ireq_setup( else if (XFS_INO_TO_AGNO(mp, breq->startino) < hdr->agno) return -EINVAL; - breq->flags |= XFS_IBULK_SAME_AG; + breq->iwalk_flags |= XFS_IWALK_SAME_AG; /* Asking for an inode past the end of the AG? We're done! */ if (XFS_INO_TO_AGNO(mp, breq->startino) > hdr->agno) diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c index 149b5460fbfd..603effabe1ee 100644 --- a/fs/xfs/xfs_iops.c +++ b/fs/xfs/xfs_iops.c @@ -616,7 +616,8 @@ xfs_get_atomic_write_min( * write of exactly one single fsblock if the bdev will make that * guarantee for us. */ - if (xfs_inode_can_hw_atomic_write(ip) || xfs_can_sw_atomic_write(mp)) + if (xfs_inode_can_hw_atomic_write(ip) || + xfs_inode_can_sw_atomic_write(ip)) return mp->m_sb.sb_blocksize; return 0; @@ -633,7 +634,7 @@ xfs_get_atomic_write_max( * write of exactly one single fsblock if the bdev will make that * guarantee for us. */ - if (!xfs_can_sw_atomic_write(mp)) { + if (!xfs_inode_can_sw_atomic_write(ip)) { if (xfs_inode_can_hw_atomic_write(ip)) return mp->m_sb.sb_blocksize; return 0; diff --git a/fs/xfs/xfs_itable.c b/fs/xfs/xfs_itable.c index c8c9b8d8309f..2aa37a4d2706 100644 --- a/fs/xfs/xfs_itable.c +++ b/fs/xfs/xfs_itable.c @@ -307,7 +307,6 @@ xfs_bulkstat( .breq = breq, }; struct xfs_trans *tp; - unsigned int iwalk_flags = 0; int error; if (breq->idmap != &nop_mnt_idmap) { @@ -328,10 +327,7 @@ xfs_bulkstat( * locking abilities to detect cycles in the inobt without deadlocking. */ tp = xfs_trans_alloc_empty(breq->mp); - if (breq->flags & XFS_IBULK_SAME_AG) - iwalk_flags |= XFS_IWALK_SAME_AG; - - error = xfs_iwalk(breq->mp, tp, breq->startino, iwalk_flags, + error = xfs_iwalk(breq->mp, tp, breq->startino, breq->iwalk_flags, xfs_bulkstat_iwalk, breq->icount, &bc); xfs_trans_cancel(tp); kfree(bc.buf); @@ -457,7 +453,7 @@ xfs_inumbers( * locking abilities to detect cycles in the inobt without deadlocking. */ tp = xfs_trans_alloc_empty(breq->mp); - error = xfs_inobt_walk(breq->mp, tp, breq->startino, breq->flags, + error = xfs_inobt_walk(breq->mp, tp, breq->startino, breq->iwalk_flags, xfs_inumbers_walk, breq->icount, &ic); xfs_trans_cancel(tp); diff --git a/fs/xfs/xfs_itable.h b/fs/xfs/xfs_itable.h index f10e8f8f2335..2d0612f14d6e 100644 --- a/fs/xfs/xfs_itable.h +++ b/fs/xfs/xfs_itable.h @@ -13,17 +13,15 @@ struct xfs_ibulk { xfs_ino_t startino; /* start with this inode */ unsigned int icount; /* number of elements in ubuffer */ unsigned int ocount; /* number of records returned */ - unsigned int flags; /* see XFS_IBULK_FLAG_* */ + unsigned int flags; /* XFS_IBULK_FLAG_* */ + unsigned int iwalk_flags; /* XFS_IWALK_FLAG_* */ }; -/* Only iterate within the same AG as startino */ -#define XFS_IBULK_SAME_AG (1U << 0) - /* Fill out the bs_extents64 field if set. */ -#define XFS_IBULK_NREXT64 (1U << 1) +#define XFS_IBULK_NREXT64 (1U << 0) /* Signal that we can return metadata directories. */ -#define XFS_IBULK_METADIR (1U << 2) +#define XFS_IBULK_METADIR (1U << 1) /* * Advance the user buffer pointer by one record of the given size. If the diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c index 2133fbaf1766..dc32c5e34d81 100644 --- a/fs/xfs/xfs_mount.c +++ b/fs/xfs/xfs_mount.c @@ -779,6 +779,25 @@ xfs_set_max_atomic_write_opt( return -EINVAL; } + if (xfs_has_reflink(mp)) + goto set_limit; + + if (new_max_fsbs == 1) { + if (mp->m_ddev_targp->bt_awu_max || + (mp->m_rtdev_targp && mp->m_rtdev_targp->bt_awu_max)) { + } else { + xfs_warn(mp, + "cannot support atomic writes of size %lluk with no reflink or HW support", + new_max_bytes >> 10); + return -EINVAL; + } + } else { + xfs_warn(mp, + "cannot support atomic writes of size %lluk with no reflink support", + new_max_bytes >> 10); + return -EINVAL; + } + set_limit: error = xfs_calc_atomic_write_reservation(mp, new_max_fsbs); if (error) { diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h index e1794e3e3156..ac344e42846c 100644 --- a/fs/xfs/xfs_trace.h +++ b/fs/xfs/xfs_trace.h @@ -455,6 +455,7 @@ DEFINE_EVENT(xfs_zone_alloc_class, name, \ xfs_extlen_t len), \ TP_ARGS(oz, rgbno, len)) DEFINE_ZONE_ALLOC_EVENT(xfs_zone_record_blocks); +DEFINE_ZONE_ALLOC_EVENT(xfs_zone_skip_blocks); DEFINE_ZONE_ALLOC_EVENT(xfs_zone_alloc_blocks); TRACE_EVENT(xfs_zone_gc_select_victim, diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c index ece374d622b3..575e7028f423 100644 --- a/fs/xfs/xfs_trans.c +++ b/fs/xfs/xfs_trans.c @@ -253,8 +253,8 @@ xfs_trans_alloc( * by doing GFP_KERNEL allocations inside sb_start_intwrite(). */ retry: - WARN_ON(mp->m_super->s_writers.frozen == SB_FREEZE_COMPLETE); tp = __xfs_trans_alloc(mp, flags); + WARN_ON(mp->m_super->s_writers.frozen == SB_FREEZE_COMPLETE); error = xfs_trans_reserve(tp, resp, blocks, rtextents); if (error == -ENOSPC && want_retry) { xfs_trans_cancel(tp); diff --git a/fs/xfs/xfs_zone_alloc.c b/fs/xfs/xfs_zone_alloc.c index 33f7eee521a8..f8bd6d741755 100644 --- a/fs/xfs/xfs_zone_alloc.c +++ b/fs/xfs/xfs_zone_alloc.c @@ -166,10 +166,9 @@ xfs_open_zone_mark_full( static void xfs_zone_record_blocks( struct xfs_trans *tp, - xfs_fsblock_t fsbno, - xfs_filblks_t len, struct xfs_open_zone *oz, - bool used) + xfs_fsblock_t fsbno, + xfs_filblks_t len) { struct xfs_mount *mp = tp->t_mountp; struct xfs_rtgroup *rtg = oz->oz_rtg; @@ -179,18 +178,37 @@ xfs_zone_record_blocks( xfs_rtgroup_lock(rtg, XFS_RTGLOCK_RMAP); xfs_rtgroup_trans_join(tp, rtg, XFS_RTGLOCK_RMAP); - if (used) { - rmapip->i_used_blocks += len; - ASSERT(rmapip->i_used_blocks <= rtg_blocks(rtg)); - } else { - xfs_add_frextents(mp, len); - } + rmapip->i_used_blocks += len; + ASSERT(rmapip->i_used_blocks <= rtg_blocks(rtg)); oz->oz_written += len; if (oz->oz_written == rtg_blocks(rtg)) xfs_open_zone_mark_full(oz); xfs_trans_log_inode(tp, rmapip, XFS_ILOG_CORE); } +/* + * Called for blocks that have been written to disk, but not actually linked to + * an inode, which can happen when garbage collection races with user data + * writes to a file. + */ +static void +xfs_zone_skip_blocks( + struct xfs_open_zone *oz, + xfs_filblks_t len) +{ + struct xfs_rtgroup *rtg = oz->oz_rtg; + + trace_xfs_zone_skip_blocks(oz, 0, len); + + xfs_rtgroup_lock(rtg, XFS_RTGLOCK_RMAP); + oz->oz_written += len; + if (oz->oz_written == rtg_blocks(rtg)) + xfs_open_zone_mark_full(oz); + xfs_rtgroup_unlock(rtg, XFS_RTGLOCK_RMAP); + + xfs_add_frextents(rtg_mount(rtg), len); +} + static int xfs_zoned_map_extent( struct xfs_trans *tp, @@ -250,8 +268,7 @@ xfs_zoned_map_extent( } } - xfs_zone_record_blocks(tp, new->br_startblock, new->br_blockcount, oz, - true); + xfs_zone_record_blocks(tp, oz, new->br_startblock, new->br_blockcount); /* Map the new blocks into the data fork. */ xfs_bmap_map_extent(tp, ip, XFS_DATA_FORK, new); @@ -259,8 +276,7 @@ xfs_zoned_map_extent( skip: trace_xfs_reflink_cow_remap_skip(ip, new); - xfs_zone_record_blocks(tp, new->br_startblock, new->br_blockcount, oz, - false); + xfs_zone_skip_blocks(oz, new->br_blockcount); return 0; } diff --git a/include/drm/drm_bridge.h b/include/drm/drm_bridge.h index 8ed80cad77ec..b0e6653ee42e 100644 --- a/include/drm/drm_bridge.h +++ b/include/drm/drm_bridge.h @@ -866,13 +866,61 @@ struct drm_bridge_funcs { struct drm_connector *connector, bool enable, int direction); + /** + * @hdmi_cec_init: + * + * Initialize CEC part of the bridge. + * + * This callback is optional, it can be implemented by bridges that + * set the @DRM_BRIDGE_OP_HDMI_CEC_ADAPTER flag in their + * &drm_bridge->ops. + * + * Returns: + * 0 on success, a negative error code otherwise + */ int (*hdmi_cec_init)(struct drm_bridge *bridge, struct drm_connector *connector); + /** + * @hdmi_cec_enable: + * + * Enable or disable the CEC adapter inside the bridge. + * + * This callback is optional, it can be implemented by bridges that + * set the @DRM_BRIDGE_OP_HDMI_CEC_ADAPTER flag in their + * &drm_bridge->ops. + * + * Returns: + * 0 on success, a negative error code otherwise + */ int (*hdmi_cec_enable)(struct drm_bridge *bridge, bool enable); + /** + * @hdmi_cec_log_addr: + * + * Set the logical address of the CEC adapter inside the bridge. + * + * This callback is optional, it can be implemented by bridges that + * set the @DRM_BRIDGE_OP_HDMI_CEC_ADAPTER flag in their + * &drm_bridge->ops. + * + * Returns: + * 0 on success, a negative error code otherwise + */ int (*hdmi_cec_log_addr)(struct drm_bridge *bridge, u8 logical_addr); + /** + * @hdmi_cec_transmit: + * + * Transmit the message using the CEC adapter inside the bridge. + * + * This callback is optional, it can be implemented by bridges that + * set the @DRM_BRIDGE_OP_HDMI_CEC_ADAPTER flag in their + * &drm_bridge->ops. + * + * Returns: + * 0 on success, a negative error code otherwise + */ int (*hdmi_cec_transmit)(struct drm_bridge *bridge, u8 attempts, u32 signal_free_time, struct cec_msg *msg); diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index edfa61d80702..62cd7b35a29c 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -168,6 +168,7 @@ enum cpuhp_state { CPUHP_AP_QCOM_TIMER_STARTING, CPUHP_AP_TEGRA_TIMER_STARTING, CPUHP_AP_ARMADA_TIMER_STARTING, + CPUHP_AP_LOONGARCH_ARCH_TIMER_STARTING, CPUHP_AP_MIPS_GIC_TIMER_STARTING, CPUHP_AP_ARC_TIMER_STARTING, CPUHP_AP_REALTEK_TIMER_STARTING, diff --git a/include/linux/export.h b/include/linux/export.h index f35d03b4113b..a686fd0ba406 100644 --- a/include/linux/export.h +++ b/include/linux/export.h @@ -91,6 +91,6 @@ #define EXPORT_SYMBOL_NS(sym, ns) __EXPORT_SYMBOL(sym, "", ns) #define EXPORT_SYMBOL_NS_GPL(sym, ns) __EXPORT_SYMBOL(sym, "GPL", ns) -#define EXPORT_SYMBOL_GPL_FOR_MODULES(sym, mods) __EXPORT_SYMBOL(sym, "GPL", "module:" mods) +#define EXPORT_SYMBOL_FOR_MODULES(sym, mods) __EXPORT_SYMBOL(sym, "GPL", "module:" mods) #endif /* _LINUX_EXPORT_H */ diff --git a/include/linux/firewire.h b/include/linux/firewire.h index cceb70415ed2..d38c6e538e5c 100644 --- a/include/linux/firewire.h +++ b/include/linux/firewire.h @@ -341,7 +341,11 @@ struct fw_address_handler { u64 length; fw_address_callback_t address_callback; void *callback_data; + + // Only for core functions. struct list_head link; + struct kref kref; + struct completion done; }; struct fw_address_region { diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 5e5de4b0a433..f3a3b761abfb 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2071,6 +2071,8 @@ enum netdev_reg_state { * @max_pacing_offload_horizon: max EDT offload horizon in nsec. * @napi_config: An array of napi_config structures containing per-NAPI * settings. + * @num_napi_configs: number of allocated NAPI config structs, + * always >= max(num_rx_queues, num_tx_queues). * @gro_flush_timeout: timeout for GRO layer in NAPI * @napi_defer_hard_irqs: If not zero, provides a counter that would * allow to avoid NIC hard IRQ, on busy queues. @@ -2482,8 +2484,9 @@ struct net_device { u64 max_pacing_offload_horizon; struct napi_config *napi_config; - unsigned long gro_flush_timeout; + u32 num_napi_configs; u32 napi_defer_hard_irqs; + unsigned long gro_flush_timeout; /** * @up: copy of @state's IFF_UP, but safe to read with just @lock. diff --git a/include/linux/netfs.h b/include/linux/netfs.h index 185bd8196503..98c96d649bf9 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -150,6 +150,7 @@ struct netfs_io_stream { bool active; /* T if stream is active */ bool need_retry; /* T if this stream needs retrying */ bool failed; /* T if this stream failed */ + bool transferred_valid; /* T is ->transferred is valid */ }; /* diff --git a/include/linux/sched.h b/include/linux/sched.h index 2b272382673d..f8188b833350 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2152,6 +2152,8 @@ static inline struct mutex *__get_task_blocked_on(struct task_struct *p) static inline void __set_task_blocked_on(struct task_struct *p, struct mutex *m) { + struct mutex *blocked_on = READ_ONCE(p->blocked_on); + WARN_ON_ONCE(!m); /* The task should only be setting itself as blocked */ WARN_ON_ONCE(p != current); @@ -2162,8 +2164,8 @@ static inline void __set_task_blocked_on(struct task_struct *p, struct mutex *m) * with a different mutex. Note, setting it to the same * lock repeatedly is ok. */ - WARN_ON_ONCE(p->blocked_on && p->blocked_on != m); - p->blocked_on = m; + WARN_ON_ONCE(blocked_on && blocked_on != m); + WRITE_ONCE(p->blocked_on, m); } static inline void set_task_blocked_on(struct task_struct *p, struct mutex *m) @@ -2174,16 +2176,19 @@ static inline void set_task_blocked_on(struct task_struct *p, struct mutex *m) static inline void __clear_task_blocked_on(struct task_struct *p, struct mutex *m) { - WARN_ON_ONCE(!m); - /* Currently we serialize blocked_on under the mutex::wait_lock */ - lockdep_assert_held_once(&m->wait_lock); - /* - * There may be cases where we re-clear already cleared - * blocked_on relationships, but make sure we are not - * clearing the relationship with a different lock. - */ - WARN_ON_ONCE(m && p->blocked_on && p->blocked_on != m); - p->blocked_on = NULL; + if (m) { + struct mutex *blocked_on = READ_ONCE(p->blocked_on); + + /* Currently we serialize blocked_on under the mutex::wait_lock */ + lockdep_assert_held_once(&m->wait_lock); + /* + * There may be cases where we re-clear already cleared + * blocked_on relationships, but make sure we are not + * clearing the relationship with a different lock. + */ + WARN_ON_ONCE(blocked_on && blocked_on != m); + } + WRITE_ONCE(p->blocked_on, NULL); } static inline void clear_task_blocked_on(struct task_struct *p, struct mutex *m) diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h index ada5b56a4413..e5751f3070b8 100644 --- a/include/net/bluetooth/bluetooth.h +++ b/include/net/bluetooth/bluetooth.h @@ -647,7 +647,7 @@ static inline void sco_exit(void) #if IS_ENABLED(CONFIG_BT_LE) int iso_init(void); int iso_exit(void); -bool iso_enabled(void); +bool iso_inited(void); #else static inline int iso_init(void) { @@ -659,7 +659,7 @@ static inline int iso_exit(void) return 0; } -static inline bool iso_enabled(void) +static inline bool iso_inited(void) { return false; } diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 4dc11c66f7b8..6906af7a8f24 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -129,7 +129,9 @@ struct hci_conn_hash { struct list_head list; unsigned int acl_num; unsigned int sco_num; - unsigned int iso_num; + unsigned int cis_num; + unsigned int bis_num; + unsigned int pa_num; unsigned int le_num; unsigned int le_num_peripheral; }; @@ -1014,9 +1016,13 @@ static inline void hci_conn_hash_add(struct hci_dev *hdev, struct hci_conn *c) h->sco_num++; break; case CIS_LINK: + h->cis_num++; + break; case BIS_LINK: + h->bis_num++; + break; case PA_LINK: - h->iso_num++; + h->pa_num++; break; } } @@ -1042,9 +1048,13 @@ static inline void hci_conn_hash_del(struct hci_dev *hdev, struct hci_conn *c) h->sco_num--; break; case CIS_LINK: + h->cis_num--; + break; case BIS_LINK: + h->bis_num--; + break; case PA_LINK: - h->iso_num--; + h->pa_num--; break; } } @@ -1061,9 +1071,11 @@ static inline unsigned int hci_conn_num(struct hci_dev *hdev, __u8 type) case ESCO_LINK: return h->sco_num; case CIS_LINK: + return h->cis_num; case BIS_LINK: + return h->bis_num; case PA_LINK: - return h->iso_num; + return h->pa_num; default: return 0; } @@ -1073,7 +1085,15 @@ static inline unsigned int hci_conn_count(struct hci_dev *hdev) { struct hci_conn_hash *c = &hdev->conn_hash; - return c->acl_num + c->sco_num + c->le_num + c->iso_num; + return c->acl_num + c->sco_num + c->le_num + c->cis_num + c->bis_num + + c->pa_num; +} + +static inline unsigned int hci_iso_count(struct hci_dev *hdev) +{ + struct hci_conn_hash *c = &hdev->conn_hash; + + return c->cis_num + c->bis_num; } static inline bool hci_conn_valid(struct hci_dev *hdev, struct hci_conn *conn) @@ -1915,6 +1935,8 @@ void hci_conn_del_sysfs(struct hci_conn *conn); !hci_dev_test_flag(dev, HCI_RPA_EXPIRED)) #define adv_rpa_valid(adv) (bacmp(&adv->random_addr, BDADDR_ANY) && \ !adv->rpa_expired) +#define le_enabled(dev) (lmp_le_capable(dev) && \ + hci_dev_test_flag(dev, HCI_LE_ENABLED)) #define scan_1m(dev) (((dev)->le_tx_def_phys & HCI_LE_SET_PHY_1M) || \ ((dev)->le_rx_def_phys & HCI_LE_SET_PHY_1M)) @@ -1932,6 +1954,7 @@ void hci_conn_del_sysfs(struct hci_conn *conn); ((dev)->le_rx_def_phys & HCI_LE_SET_PHY_CODED)) #define ll_privacy_capable(dev) ((dev)->le_features[0] & HCI_LE_LL_PRIVACY) +#define ll_privacy_enabled(dev) (le_enabled(dev) && ll_privacy_capable(dev)) #define privacy_mode_capable(dev) (ll_privacy_capable(dev) && \ ((dev)->commands[39] & 0x04)) @@ -1981,14 +2004,23 @@ void hci_conn_del_sysfs(struct hci_conn *conn); /* CIS Master/Slave and BIS support */ #define iso_capable(dev) (cis_capable(dev) || bis_capable(dev)) +#define iso_enabled(dev) (le_enabled(dev) && iso_capable(dev)) #define cis_capable(dev) \ (cis_central_capable(dev) || cis_peripheral_capable(dev)) +#define cis_enabled(dev) (le_enabled(dev) && cis_capable(dev)) #define cis_central_capable(dev) \ ((dev)->le_features[3] & HCI_LE_CIS_CENTRAL) +#define cis_central_enabled(dev) \ + (le_enabled(dev) && cis_central_capable(dev)) #define cis_peripheral_capable(dev) \ ((dev)->le_features[3] & HCI_LE_CIS_PERIPHERAL) +#define cis_peripheral_enabled(dev) \ + (le_enabled(dev) && cis_peripheral_capable(dev)) #define bis_capable(dev) ((dev)->le_features[3] & HCI_LE_ISO_BROADCASTER) -#define sync_recv_capable(dev) ((dev)->le_features[3] & HCI_LE_ISO_SYNC_RECEIVER) +#define bis_enabled(dev) (le_enabled(dev) && bis_capable(dev)) +#define sync_recv_capable(dev) \ + ((dev)->le_features[3] & HCI_LE_ISO_SYNC_RECEIVER) +#define sync_recv_enabled(dev) (le_enabled(dev) && sync_recv_capable(dev)) #define mws_transport_config_capable(dev) (((dev)->commands[30] & 0x08) && \ (!hci_test_quirk((dev), HCI_QUIRK_BROKEN_MWS_TRANSPORT_CONFIG))) diff --git a/include/net/bond_3ad.h b/include/net/bond_3ad.h index 2053cd8e788a..dba369a2cf27 100644 --- a/include/net/bond_3ad.h +++ b/include/net/bond_3ad.h @@ -307,6 +307,7 @@ int bond_3ad_lacpdu_recv(const struct sk_buff *skb, struct bonding *bond, struct slave *slave); int bond_3ad_set_carrier(struct bonding *bond); void bond_3ad_update_lacp_rate(struct bonding *bond); +void bond_3ad_update_lacp_active(struct bonding *bond); void bond_3ad_update_ad_actor_settings(struct bonding *bond); int bond_3ad_stats_fill(struct sk_buff *skb, struct bond_3ad_stats *stats); size_t bond_3ad_stats_size(void); diff --git a/include/net/devlink.h b/include/net/devlink.h index 93640a29427c..b32c9ceeb81d 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -78,6 +78,9 @@ struct devlink_port_pci_sf_attrs { * @flavour: flavour of the port * @split: indicates if this is split port * @splittable: indicates if the port can be split. + * @no_phys_port_name: skip automatic phys_port_name generation; for + * compatibility only, newly added driver/port instance + * should never set this. * @lanes: maximum number of lanes the port supports. 0 value is not passed to netlink. * @switch_id: if the port is part of switch, this is buffer with ID, otherwise this is NULL * @phys: physical port attributes @@ -87,7 +90,8 @@ struct devlink_port_pci_sf_attrs { */ struct devlink_port_attrs { u8 split:1, - splittable:1; + splittable:1, + no_phys_port_name:1; u32 lanes; enum devlink_port_flavour flavour; struct netdev_phys_item_id switch_id; diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index ff406ef4fd4a..29a36709e7f3 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -1163,6 +1163,14 @@ static inline const struct cpumask *sysctl_est_cpulist(struct netns_ipvs *ipvs) return housekeeping_cpumask(HK_TYPE_KTHREAD); } +static inline const struct cpumask *sysctl_est_preferred_cpulist(struct netns_ipvs *ipvs) +{ + if (ipvs->est_cpulist_valid) + return ipvs->sysctl_est_cpulist; + else + return NULL; +} + static inline int sysctl_est_nice(struct netns_ipvs *ipvs) { return ipvs->sysctl_est_nice; @@ -1270,6 +1278,11 @@ static inline const struct cpumask *sysctl_est_cpulist(struct netns_ipvs *ipvs) return housekeeping_cpumask(HK_TYPE_KTHREAD); } +static inline const struct cpumask *sysctl_est_preferred_cpulist(struct netns_ipvs *ipvs) +{ + return NULL; +} + static inline int sysctl_est_nice(struct netns_ipvs *ipvs) { return IPVS_EST_NICE; diff --git a/include/net/kcm.h b/include/net/kcm.h index 441e993be634..d9c35e71ecea 100644 --- a/include/net/kcm.h +++ b/include/net/kcm.h @@ -71,7 +71,6 @@ struct kcm_sock { struct list_head wait_psock_list; struct sk_buff *seq_skb; struct mutex tx_mutex; - u32 tx_stopped : 1; /* Don't use bit fields here, these are set under different locks */ bool tx_wait; diff --git a/include/net/page_pool/types.h b/include/net/page_pool/types.h index 431b593de709..1509a536cb85 100644 --- a/include/net/page_pool/types.h +++ b/include/net/page_pool/types.h @@ -265,6 +265,8 @@ struct page_pool *page_pool_create_percpu(const struct page_pool_params *params, struct xdp_mem_info; #ifdef CONFIG_PAGE_POOL +void page_pool_enable_direct_recycling(struct page_pool *pool, + struct napi_struct *napi); void page_pool_disable_direct_recycling(struct page_pool *pool); void page_pool_destroy(struct page_pool *pool); void page_pool_use_xdp_mem(struct page_pool *pool, void (*disconnect)(void *), diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 638948be4c50..738cd5b13c62 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -1038,12 +1038,17 @@ static inline struct sk_buff *qdisc_dequeue_internal(struct Qdisc *sch, bool dir skb = __skb_dequeue(&sch->gso_skb); if (skb) { sch->q.qlen--; + qdisc_qstats_backlog_dec(sch, skb); return skb; } - if (direct) - return __qdisc_dequeue_head(&sch->q); - else + if (direct) { + skb = __qdisc_dequeue_head(&sch->q); + if (skb) + qdisc_qstats_backlog_dec(sch, skb); + return skb; + } else { return sch->dequeue(sch); + } } static inline struct sk_buff *qdisc_dequeue_head(struct Qdisc *sch) diff --git a/include/uapi/linux/pfrut.h b/include/uapi/linux/pfrut.h index 42fa15f8310d..b77d5c210c26 100644 --- a/include/uapi/linux/pfrut.h +++ b/include/uapi/linux/pfrut.h @@ -89,6 +89,7 @@ struct pfru_payload_hdr { __u32 hw_ver; __u32 rt_ver; __u8 platform_id[16]; + __u32 svn_ver; }; enum pfru_dsm_status { diff --git a/io_uring/io-wq.c b/io_uring/io-wq.c index be91edf34f01..17dfaa0395c4 100644 --- a/io_uring/io-wq.c +++ b/io_uring/io-wq.c @@ -357,6 +357,13 @@ static void create_worker_cb(struct callback_head *cb) worker = container_of(cb, struct io_worker, create_work); wq = worker->wq; acct = worker->acct; + + rcu_read_lock(); + do_create = !io_acct_activate_free_worker(acct); + rcu_read_unlock(); + if (!do_create) + goto no_need_create; + raw_spin_lock(&acct->workers_lock); if (acct->nr_workers < acct->max_workers) { @@ -367,6 +374,7 @@ static void create_worker_cb(struct callback_head *cb) if (do_create) { create_io_worker(wq, acct); } else { +no_need_create: atomic_dec(&acct->nr_running); io_worker_ref_put(wq); } diff --git a/io_uring/net.c b/io_uring/net.c index dd96e355982f..d69f2afa4f7a 100644 --- a/io_uring/net.c +++ b/io_uring/net.c @@ -494,6 +494,15 @@ static int io_bundle_nbufs(struct io_async_msghdr *kmsg, int ret) return nbufs; } +static int io_net_kbuf_recyle(struct io_kiocb *req, + struct io_async_msghdr *kmsg, int len) +{ + req->flags |= REQ_F_BL_NO_RECYCLE; + if (req->flags & REQ_F_BUFFERS_COMMIT) + io_kbuf_commit(req, req->buf_list, len, io_bundle_nbufs(kmsg, len)); + return IOU_RETRY; +} + static inline bool io_send_finish(struct io_kiocb *req, int *ret, struct io_async_msghdr *kmsg, unsigned issue_flags) @@ -562,8 +571,7 @@ int io_sendmsg(struct io_kiocb *req, unsigned int issue_flags) kmsg->msg.msg_controllen = 0; kmsg->msg.msg_control = NULL; sr->done_io += ret; - req->flags |= REQ_F_BL_NO_RECYCLE; - return -EAGAIN; + return io_net_kbuf_recyle(req, kmsg, ret); } if (ret == -ERESTARTSYS) ret = -EINTR; @@ -674,8 +682,7 @@ retry_bundle: sr->len -= ret; sr->buf += ret; sr->done_io += ret; - req->flags |= REQ_F_BL_NO_RECYCLE; - return -EAGAIN; + return io_net_kbuf_recyle(req, kmsg, ret); } if (ret == -ERESTARTSYS) ret = -EINTR; @@ -1071,8 +1078,7 @@ retry_multishot: } if (ret > 0 && io_net_retry(sock, flags)) { sr->done_io += ret; - req->flags |= REQ_F_BL_NO_RECYCLE; - return IOU_RETRY; + return io_net_kbuf_recyle(req, kmsg, ret); } if (ret == -ERESTARTSYS) ret = -EINTR; @@ -1218,8 +1224,7 @@ retry_multishot: sr->len -= ret; sr->buf += ret; sr->done_io += ret; - req->flags |= REQ_F_BL_NO_RECYCLE; - return -EAGAIN; + return io_net_kbuf_recyle(req, kmsg, ret); } if (ret == -ERESTARTSYS) ret = -EINTR; @@ -1500,8 +1505,7 @@ int io_send_zc(struct io_kiocb *req, unsigned int issue_flags) zc->len -= ret; zc->buf += ret; zc->done_io += ret; - req->flags |= REQ_F_BL_NO_RECYCLE; - return -EAGAIN; + return io_net_kbuf_recyle(req, kmsg, ret); } if (ret == -ERESTARTSYS) ret = -EINTR; @@ -1571,8 +1575,7 @@ int io_sendmsg_zc(struct io_kiocb *req, unsigned int issue_flags) if (ret > 0 && io_net_retry(sock, flags)) { sr->done_io += ret; - req->flags |= REQ_F_BL_NO_RECYCLE; - return -EAGAIN; + return io_net_kbuf_recyle(req, kmsg, ret); } if (ret == -ERESTARTSYS) ret = -EINTR; diff --git a/kernel/cpu.c b/kernel/cpu.c index faf0f23fc5d8..db9f6c539b28 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -1309,9 +1309,6 @@ static int takedown_cpu(unsigned int cpu) */ irq_lock_sparse(); - /* - * So now all preempt/rcu users must observe !cpu_active(). - */ err = stop_machine_cpuslocked(take_cpu_down, NULL, cpumask_of(cpu)); if (err) { /* CPU refused to die */ diff --git a/kernel/fork.c b/kernel/fork.c index c4ada32598bd..af673856499d 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -689,6 +689,7 @@ void __mmdrop(struct mm_struct *mm) mm_pasid_drop(mm); mm_destroy_cid(mm); percpu_counter_destroy_many(mm->rss_stat, NR_MM_COUNTERS); + futex_hash_free(mm); free_mm(mm); } @@ -1137,7 +1138,6 @@ static inline void __mmput(struct mm_struct *mm) if (mm->binfmt) module_put(mm->binfmt->module); lru_gen_del_mm(mm); - futex_hash_free(mm); mmdrop(mm); } diff --git a/kernel/futex/futex.h b/kernel/futex/futex.h index c74eac572acd..2cd57096c38e 100644 --- a/kernel/futex/futex.h +++ b/kernel/futex/futex.h @@ -319,13 +319,13 @@ static __always_inline int futex_put_value(u32 val, u32 __user *to) { if (can_do_masked_user_access()) to = masked_user_access_begin(to); - else if (!user_read_access_begin(to, sizeof(*to))) + else if (!user_write_access_begin(to, sizeof(*to))) return -EFAULT; unsafe_put_user(val, to, Efault); - user_read_access_end(); + user_write_access_end(); return 0; Efault: - user_read_access_end(); + user_write_access_end(); return -EFAULT; } diff --git a/kernel/irq/irq_test.c b/kernel/irq/irq_test.c index 5161b56a12f9..a75abebed7f2 100644 --- a/kernel/irq/irq_test.c +++ b/kernel/irq/irq_test.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: LGPL-2.1+ +#include <linux/cleanup.h> #include <linux/cpu.h> #include <linux/cpumask.h> #include <linux/interrupt.h> @@ -134,7 +135,8 @@ static void irq_shutdown_depth_test(struct kunit *test) disable_irq(virq); KUNIT_EXPECT_EQ(test, desc->depth, 1); - irq_shutdown_and_deactivate(desc); + scoped_guard(raw_spinlock_irqsave, &desc->lock) + irq_shutdown_and_deactivate(desc); KUNIT_EXPECT_FALSE(test, irqd_is_activated(data)); KUNIT_EXPECT_FALSE(test, irqd_is_started(data)); diff --git a/kernel/kthread.c b/kernel/kthread.c index 0e98b228a8ef..31b072e8d427 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -893,6 +893,7 @@ out: return ret; } +EXPORT_SYMBOL_GPL(kthread_affine_preferred); /* * Re-affine kthreads according to their preferences diff --git a/kernel/locking/ww_mutex.h b/kernel/locking/ww_mutex.h index 086fd5487ca7..31a785afee6c 100644 --- a/kernel/locking/ww_mutex.h +++ b/kernel/locking/ww_mutex.h @@ -342,8 +342,12 @@ static bool __ww_mutex_wound(struct MUTEX *lock, * When waking up the task to wound, be sure to clear the * blocked_on pointer. Otherwise we can see circular * blocked_on relationships that can't resolve. + * + * NOTE: We pass NULL here instead of lock, because we + * are waking the mutex owner, who may be currently + * blocked on a different mutex. */ - __clear_task_blocked_on(owner, lock); + __clear_task_blocked_on(owner, NULL); wake_q_add(wake_q, owner); } return true; diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 174ee243b349..8eff357b0436 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -4262,6 +4262,8 @@ int rcutree_prepare_cpu(unsigned int cpu) rdp->rcu_iw_gp_seq = rdp->gp_seq - 1; trace_rcu_grace_period(rcu_state.name, rdp->gp_seq, TPS("cpuonl")); raw_spin_unlock_irqrestore_rcu_node(rnp, flags); + + rcu_preempt_deferred_qs_init(rdp); rcu_spawn_rnp_kthreads(rnp); rcu_spawn_cpu_nocb_kthread(cpu); ASSERT_EXCLUSIVE_WRITER(rcu_state.n_online_cpus); diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index de6ca13a7b5f..b8bbe7960cda 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -488,6 +488,7 @@ static int rcu_print_task_exp_stall(struct rcu_node *rnp); static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp); static void rcu_flavor_sched_clock_irq(int user); static void dump_blkd_tasks(struct rcu_node *rnp, int ncheck); +static void rcu_preempt_deferred_qs_init(struct rcu_data *rdp); static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags); static void rcu_preempt_boost_start_gp(struct rcu_node *rnp); static bool rcu_is_callbacks_kthread(struct rcu_data *rdp); diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index fc14adf15cbb..4cd170b2d655 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -763,8 +763,6 @@ static void rcu_read_unlock_special(struct task_struct *t) cpu_online(rdp->cpu)) { // Get scheduler to re-evaluate and call hooks. // If !IRQ_WORK, FQS scan will eventually IPI. - rdp->defer_qs_iw = - IRQ_WORK_INIT_HARD(rcu_preempt_deferred_qs_handler); rdp->defer_qs_iw_pending = DEFER_QS_PENDING; irq_work_queue_on(&rdp->defer_qs_iw, rdp->cpu); } @@ -904,6 +902,10 @@ dump_blkd_tasks(struct rcu_node *rnp, int ncheck) } } +static void rcu_preempt_deferred_qs_init(struct rcu_data *rdp) +{ + rdp->defer_qs_iw = IRQ_WORK_INIT_HARD(rcu_preempt_deferred_qs_handler); +} #else /* #ifdef CONFIG_PREEMPT_RCU */ /* @@ -1103,6 +1105,8 @@ dump_blkd_tasks(struct rcu_node *rnp, int ncheck) WARN_ON_ONCE(!list_empty(&rnp->blkd_tasks)); } +static void rcu_preempt_deferred_qs_init(struct rcu_data *rdp) { } + #endif /* #else #ifdef CONFIG_PREEMPT_RCU */ /* diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index 7dedc9a16281..4ae32ef179dd 100644 --- a/kernel/sched/ext.c +++ b/kernel/sched/ext.c @@ -5749,6 +5749,9 @@ static int scx_enable(struct sched_ext_ops *ops, struct bpf_link *link) __setscheduler_class(p->policy, p->prio); struct sched_enq_and_set_ctx ctx; + if (!tryget_task_struct(p)) + continue; + if (old_class != new_class && p->se.sched_delayed) dequeue_task(task_rq(p), p, DEQUEUE_SLEEP | DEQUEUE_DELAYED); @@ -5761,6 +5764,7 @@ static int scx_enable(struct sched_ext_ops *ops, struct bpf_link *link) sched_enq_and_set_task(&ctx); check_class_changed(task_rq(p), p, old_class, p->prio); + put_task_struct(p); } scx_task_iter_stop(&sti); percpu_up_write(&scx_fork_rwsem); diff --git a/kernel/signal.c b/kernel/signal.c index e2c928de7d2c..fe9190d84f28 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -4067,6 +4067,7 @@ SYSCALL_DEFINE4(pidfd_send_signal, int, pidfd, int, sig, { struct pid *pid; enum pid_type type; + int ret; /* Enforce flags be set to 0 until we add an extension. */ if (flags & ~PIDFD_SEND_SIGNAL_FLAGS) @@ -4108,7 +4109,10 @@ SYSCALL_DEFINE4(pidfd_send_signal, int, pidfd, int, sig, } } - return do_pidfd_send_signal(pid, sig, type, info, flags); + ret = do_pidfd_send_signal(pid, sig, type, info, flags); + put_pid(pid); + + return ret; } static int diff --git a/kernel/smp.c b/kernel/smp.c index 4649fa4872ff..56f83aa58ec8 100644 --- a/kernel/smp.c +++ b/kernel/smp.c @@ -1018,7 +1018,7 @@ void __init smp_init(void) * @cond_func: A callback function that is passed a cpu id and * the info parameter. The function is called * with preemption disabled. The function should - * return a blooean value indicating whether to IPI + * return a boolean value indicating whether to IPI * the specified CPU. * @func: The function to run on all applicable CPUs. * This must be fast and non-blocking. diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 1dbf1d3cf2f1..5a6688832da8 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -2204,7 +2204,7 @@ static inline bool is_good_system_name(const char *name) static inline void sanitize_event_name(char *name) { while (*name++ != '\0') - if (*name == ':' || *name == '.') + if (*name == ':' || *name == '.' || *name == '*') *name = '_'; } diff --git a/lib/crypto/Kconfig b/lib/crypto/Kconfig index c2b65b6a9bb6..1e6b008f8fca 100644 --- a/lib/crypto/Kconfig +++ b/lib/crypto/Kconfig @@ -140,8 +140,8 @@ config CRYPTO_LIB_CHACHA20POLY1305 config CRYPTO_LIB_SHA1 tristate help - The SHA-1 library functions. Select this if your module uses any of - the functions from <crypto/sha1.h>. + The SHA-1 and HMAC-SHA1 library functions. Select this if your module + uses any of the functions from <crypto/sha1.h>. config CRYPTO_LIB_SHA1_ARCH bool @@ -157,9 +157,9 @@ config CRYPTO_LIB_SHA1_ARCH config CRYPTO_LIB_SHA256 tristate help - Enable the SHA-256 library interface. This interface may be fulfilled - by either the generic implementation or an arch-specific one, if one - is available and enabled. + The SHA-224, SHA-256, HMAC-SHA224, and HMAC-SHA256 library functions. + Select this if your module uses any of these functions from + <crypto/sha2.h>. config CRYPTO_LIB_SHA256_ARCH bool diff --git a/lib/crypto/Makefile b/lib/crypto/Makefile index e4151be2ebd4..539d5d59a50e 100644 --- a/lib/crypto/Makefile +++ b/lib/crypto/Makefile @@ -100,7 +100,6 @@ ifeq ($(CONFIG_ARM),y) libsha256-y += arm/sha256-ce.o arm/sha256-core.o $(obj)/arm/sha256-core.S: $(src)/arm/sha256-armv4.pl $(call cmd,perlasm) -clean-files += arm/sha256-core.S AFLAGS_arm/sha256-core.o += $(aflags-thumb2-y) endif @@ -108,7 +107,6 @@ ifeq ($(CONFIG_ARM64),y) libsha256-y += arm64/sha256-core.o $(obj)/arm64/sha256-core.S: $(src)/arm64/sha2-armv8.pl $(call cmd,perlasm_with_args) -clean-files += arm64/sha256-core.S libsha256-$(CONFIG_KERNEL_MODE_NEON) += arm64/sha256-ce.o endif @@ -132,7 +130,6 @@ ifeq ($(CONFIG_ARM),y) libsha512-y += arm/sha512-core.o $(obj)/arm/sha512-core.S: $(src)/arm/sha512-armv4.pl $(call cmd,perlasm) -clean-files += arm/sha512-core.S AFLAGS_arm/sha512-core.o += $(aflags-thumb2-y) endif @@ -140,7 +137,6 @@ ifeq ($(CONFIG_ARM64),y) libsha512-y += arm64/sha512-core.o $(obj)/arm64/sha512-core.S: $(src)/arm64/sha2-armv8.pl $(call cmd,perlasm_with_args) -clean-files += arm64/sha512-core.S libsha512-$(CONFIG_KERNEL_MODE_NEON) += arm64/sha512-ce-core.o endif @@ -167,3 +163,7 @@ obj-$(CONFIG_PPC) += powerpc/ obj-$(CONFIG_RISCV) += riscv/ obj-$(CONFIG_S390) += s390/ obj-$(CONFIG_X86) += x86/ + +# clean-files must be defined unconditionally +clean-files += arm/sha256-core.S arm/sha512-core.S +clean-files += arm64/sha256-core.S arm64/sha512-core.S diff --git a/lib/ref_tracker.c b/lib/ref_tracker.c index a9e6ffcff04b..cce12287708e 100644 --- a/lib/ref_tracker.c +++ b/lib/ref_tracker.c @@ -434,7 +434,7 @@ void ref_tracker_dir_debugfs(struct ref_tracker_dir *dir) if (dentry && !xa_is_err(dentry)) return; - ret = snprintf(name, sizeof(name), "%s@%px", dir->class, dir); + ret = snprintf(name, sizeof(name), "%s@%p", dir->class, dir); name[sizeof(name) - 1] = '\0'; if (ret < sizeof(name)) { diff --git a/mm/kasan/kasan_test_c.c b/mm/kasan/kasan_test_c.c index 2aa12dfa427a..e0968acc03aa 100644 --- a/mm/kasan/kasan_test_c.c +++ b/mm/kasan/kasan_test_c.c @@ -47,7 +47,7 @@ static struct { * Some tests use these global variables to store return values from function * calls that could otherwise be eliminated by the compiler as dead code. */ -static volatile void *kasan_ptr_result; +static void *volatile kasan_ptr_result; static volatile int kasan_int_result; /* Probe for console output: obtains test_status lines of interest. */ diff --git a/mm/khugepaged.c b/mm/khugepaged.c index 374a6a5193a7..6b40bdfd224c 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -1172,11 +1172,11 @@ static int collapse_huge_page(struct mm_struct *mm, unsigned long address, if (result != SCAN_SUCCEED) goto out_up_write; /* check if the pmd is still valid */ + vma_start_write(vma); result = check_pmd_still_valid(mm, address, pmd); if (result != SCAN_SUCCEED) goto out_up_write; - vma_start_write(vma); anon_vma_lock_write(vma->anon_vma); mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, address, diff --git a/mm/kmemleak.c b/mm/kmemleak.c index 8d588e685311..84265983f239 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -470,6 +470,7 @@ static struct kmemleak_object *mem_pool_alloc(gfp_t gfp) { unsigned long flags; struct kmemleak_object *object; + bool warn = false; /* try the slab allocator first */ if (object_cache) { @@ -488,8 +489,10 @@ static struct kmemleak_object *mem_pool_alloc(gfp_t gfp) else if (mem_pool_free_count) object = &mem_pool[--mem_pool_free_count]; else - pr_warn_once("Memory pool empty, consider increasing CONFIG_DEBUG_KMEMLEAK_MEM_POOL_SIZE\n"); + warn = true; raw_spin_unlock_irqrestore(&kmemleak_lock, flags); + if (warn) + pr_warn_once("Memory pool empty, consider increasing CONFIG_DEBUG_KMEMLEAK_MEM_POOL_SIZE\n"); return object; } @@ -2181,6 +2184,7 @@ static const struct file_operations kmemleak_fops = { static void __kmemleak_do_cleanup(void) { struct kmemleak_object *object, *tmp; + unsigned int cnt = 0; /* * Kmemleak has already been disabled, no need for RCU list traversal @@ -2189,6 +2193,10 @@ static void __kmemleak_do_cleanup(void) list_for_each_entry_safe(object, tmp, &object_list, object_list) { __remove_object(object); __delete_object(object); + + /* Call cond_resched() once per 64 iterations to avoid soft lockup */ + if (!(++cnt & 0x3f)) + cond_resched(); } } diff --git a/mm/mprotect.c b/mm/mprotect.c index 78bded7acf79..113b48985834 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -120,9 +120,8 @@ static int mprotect_folio_pte_batch(struct folio *folio, pte_t *ptep, static bool prot_numa_skip(struct vm_area_struct *vma, unsigned long addr, pte_t oldpte, pte_t *pte, int target_node, - struct folio **foliop) + struct folio *folio) { - struct folio *folio = NULL; bool ret = true; bool toptier; int nid; @@ -131,7 +130,6 @@ static bool prot_numa_skip(struct vm_area_struct *vma, unsigned long addr, if (pte_protnone(oldpte)) goto skip; - folio = vm_normal_folio(vma, addr, oldpte); if (!folio) goto skip; @@ -173,7 +171,6 @@ static bool prot_numa_skip(struct vm_area_struct *vma, unsigned long addr, folio_xchg_access_time(folio, jiffies_to_msecs(jiffies)); skip: - *foliop = folio; return ret; } @@ -231,10 +228,9 @@ static int page_anon_exclusive_sub_batch(int start_idx, int max_len, * retrieve sub-batches. */ static void commit_anon_folio_batch(struct vm_area_struct *vma, - struct folio *folio, unsigned long addr, pte_t *ptep, + struct folio *folio, struct page *first_page, unsigned long addr, pte_t *ptep, pte_t oldpte, pte_t ptent, int nr_ptes, struct mmu_gather *tlb) { - struct page *first_page = folio_page(folio, 0); bool expected_anon_exclusive; int sub_batch_idx = 0; int len; @@ -251,7 +247,7 @@ static void commit_anon_folio_batch(struct vm_area_struct *vma, } static void set_write_prot_commit_flush_ptes(struct vm_area_struct *vma, - struct folio *folio, unsigned long addr, pte_t *ptep, + struct folio *folio, struct page *page, unsigned long addr, pte_t *ptep, pte_t oldpte, pte_t ptent, int nr_ptes, struct mmu_gather *tlb) { bool set_write; @@ -270,7 +266,7 @@ static void set_write_prot_commit_flush_ptes(struct vm_area_struct *vma, /* idx = */ 0, set_write, tlb); return; } - commit_anon_folio_batch(vma, folio, addr, ptep, oldpte, ptent, nr_ptes, tlb); + commit_anon_folio_batch(vma, folio, page, addr, ptep, oldpte, ptent, nr_ptes, tlb); } static long change_pte_range(struct mmu_gather *tlb, @@ -305,15 +301,19 @@ static long change_pte_range(struct mmu_gather *tlb, const fpb_t flags = FPB_RESPECT_SOFT_DIRTY | FPB_RESPECT_WRITE; int max_nr_ptes = (end - addr) >> PAGE_SHIFT; struct folio *folio = NULL; + struct page *page; pte_t ptent; + page = vm_normal_page(vma, addr, oldpte); + if (page) + folio = page_folio(page); /* * Avoid trapping faults against the zero or KSM * pages. See similar comment in change_huge_pmd. */ if (prot_numa) { int ret = prot_numa_skip(vma, addr, oldpte, pte, - target_node, &folio); + target_node, folio); if (ret) { /* determine batch to skip */ @@ -323,9 +323,6 @@ static long change_pte_range(struct mmu_gather *tlb, } } - if (!folio) - folio = vm_normal_folio(vma, addr, oldpte); - nr_ptes = mprotect_folio_pte_batch(folio, pte, oldpte, max_nr_ptes, flags); oldpte = modify_prot_start_ptes(vma, addr, pte, nr_ptes); @@ -351,7 +348,7 @@ static long change_pte_range(struct mmu_gather *tlb, */ if ((cp_flags & MM_CP_TRY_CHANGE_WRITABLE) && !pte_write(ptent)) - set_write_prot_commit_flush_ptes(vma, folio, + set_write_prot_commit_flush_ptes(vma, folio, page, addr, pte, oldpte, ptent, nr_ptes, tlb); else prot_commit_flush_ptes(vma, addr, pte, oldpte, ptent, diff --git a/mm/mremap.c b/mm/mremap.c index 677a4d744df9..9afa8cd524f5 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -179,6 +179,10 @@ static int mremap_folio_pte_batch(struct vm_area_struct *vma, unsigned long addr if (max_nr == 1) return 1; + /* Avoid expensive folio lookup if we stand no chance of benefit. */ + if (pte_batch_hint(ptep, pte) == 1) + return 1; + folio = vm_normal_folio(vma, addr, pte); if (!folio || !folio_test_large(folio)) return 1; diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index cbed91b09640..45e6290e2e8b 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -1821,13 +1821,16 @@ ssize_t move_pages(struct userfaultfd_ctx *ctx, unsigned long dst_start, /* Check if we can move the pmd without splitting it. */ if (move_splits_huge_pmd(dst_addr, src_addr, src_start + len) || !pmd_none(dst_pmdval)) { - struct folio *folio = pmd_folio(*src_pmd); - - if (!folio || (!is_huge_zero_folio(folio) && - !PageAnonExclusive(&folio->page))) { - spin_unlock(ptl); - err = -EBUSY; - break; + /* Can be a migration entry */ + if (pmd_present(*src_pmd)) { + struct folio *folio = pmd_folio(*src_pmd); + + if (!is_huge_zero_folio(folio) && + !PageAnonExclusive(&folio->page)) { + spin_unlock(ptl); + err = -EBUSY; + break; + } } spin_unlock(ptl); diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index 7d1e79f69cd1..7a879290dd28 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -339,7 +339,8 @@ static int hci_enhanced_setup_sync(struct hci_dev *hdev, void *data) case BT_CODEC_TRANSPARENT: if (!find_next_esco_param(conn, esco_param_msbc, ARRAY_SIZE(esco_param_msbc))) - return false; + return -EINVAL; + param = &esco_param_msbc[conn->attempt - 1]; cp.tx_coding_format.id = 0x03; cp.rx_coding_format.id = 0x03; @@ -830,7 +831,17 @@ static void bis_cleanup(struct hci_conn *conn) /* Check if ISO connection is a BIS and terminate advertising * set and BIG if there are no other connections using it. */ - bis = hci_conn_hash_lookup_big(hdev, conn->iso_qos.bcast.big); + bis = hci_conn_hash_lookup_big_state(hdev, + conn->iso_qos.bcast.big, + BT_CONNECTED, + HCI_ROLE_MASTER); + if (bis) + return; + + bis = hci_conn_hash_lookup_big_state(hdev, + conn->iso_qos.bcast.big, + BT_CONNECT, + HCI_ROLE_MASTER); if (bis) return; @@ -2249,7 +2260,7 @@ struct hci_conn *hci_connect_bis(struct hci_dev *hdev, bdaddr_t *dst, * the start periodic advertising and create BIG commands have * been queued */ - hci_conn_hash_list_state(hdev, bis_mark_per_adv, PA_LINK, + hci_conn_hash_list_state(hdev, bis_mark_per_adv, BIS_LINK, BT_BOUND, &data); /* Queue start periodic advertising and create BIG */ diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 8aa5039b975a..fe7cdd67ad2a 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -6745,8 +6745,8 @@ static void hci_le_cis_established_evt(struct hci_dev *hdev, void *data, qos->ucast.out.latency = DIV_ROUND_CLOSEST(get_unaligned_le24(ev->p_latency), 1000); - qos->ucast.in.sdu = le16_to_cpu(ev->c_mtu); - qos->ucast.out.sdu = le16_to_cpu(ev->p_mtu); + qos->ucast.in.sdu = ev->c_bn ? le16_to_cpu(ev->c_mtu) : 0; + qos->ucast.out.sdu = ev->p_bn ? le16_to_cpu(ev->p_mtu) : 0; qos->ucast.in.phy = ev->c_phy; qos->ucast.out.phy = ev->p_phy; break; @@ -6760,8 +6760,8 @@ static void hci_le_cis_established_evt(struct hci_dev *hdev, void *data, qos->ucast.in.latency = DIV_ROUND_CLOSEST(get_unaligned_le24(ev->p_latency), 1000); - qos->ucast.out.sdu = le16_to_cpu(ev->c_mtu); - qos->ucast.in.sdu = le16_to_cpu(ev->p_mtu); + qos->ucast.out.sdu = ev->c_bn ? le16_to_cpu(ev->c_mtu) : 0; + qos->ucast.in.sdu = ev->p_bn ? le16_to_cpu(ev->p_mtu) : 0; qos->ucast.out.phy = ev->c_phy; qos->ucast.in.phy = ev->p_phy; break; @@ -6957,9 +6957,14 @@ static void hci_le_big_sync_established_evt(struct hci_dev *hdev, void *data, continue; } - if (ev->status != 0x42) + if (ev->status != 0x42) { /* Mark PA sync as established */ set_bit(HCI_CONN_PA_SYNC, &bis->flags); + /* Reset cleanup callback of PA Sync so it doesn't + * terminate the sync when deleting the connection. + */ + conn->cleanup = NULL; + } bis->sync_handle = conn->sync_handle; bis->iso_qos.bcast.big = ev->handle; diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c index 2b4f21fbf9c1..31d72b9683ef 100644 --- a/net/bluetooth/hci_sync.c +++ b/net/bluetooth/hci_sync.c @@ -3344,7 +3344,7 @@ static int hci_powered_update_adv_sync(struct hci_dev *hdev) * advertising data. This also applies to the case * where BR/EDR was toggled during the AUTO_OFF phase. */ - if (hci_dev_test_flag(hdev, HCI_ADVERTISING) || + if (hci_dev_test_flag(hdev, HCI_ADVERTISING) && list_empty(&hdev->adv_instances)) { if (ext_adv_capable(hdev)) { err = hci_setup_ext_adv_instance_sync(hdev, 0x00); @@ -4531,14 +4531,14 @@ static int hci_le_set_host_feature_sync(struct hci_dev *hdev) { struct hci_cp_le_set_host_feature cp; - if (!cis_capable(hdev)) + if (!iso_capable(hdev)) return 0; memset(&cp, 0, sizeof(cp)); /* Connected Isochronous Channels (Host Support) */ cp.bit_number = 32; - cp.bit_value = 1; + cp.bit_value = iso_enabled(hdev) ? 0x01 : 0x00; return __hci_cmd_sync_status(hdev, HCI_OP_LE_SET_HOST_FEATURE, sizeof(cp), &cp, HCI_CMD_TIMEOUT); @@ -6985,8 +6985,6 @@ static void create_pa_complete(struct hci_dev *hdev, void *data, int err) hci_dev_lock(hdev); - hci_dev_clear_flag(hdev, HCI_PA_SYNC); - if (!hci_conn_valid(hdev, conn)) clear_bit(HCI_CONN_CREATE_PA_SYNC, &conn->flags); @@ -7047,10 +7045,13 @@ static int hci_le_pa_create_sync(struct hci_dev *hdev, void *data) /* SID has not been set listen for HCI_EV_LE_EXT_ADV_REPORT to update * it. */ - if (conn->sid == HCI_SID_INVALID) - __hci_cmd_sync_status_sk(hdev, HCI_OP_NOP, 0, NULL, - HCI_EV_LE_EXT_ADV_REPORT, - conn->conn_timeout, NULL); + if (conn->sid == HCI_SID_INVALID) { + err = __hci_cmd_sync_status_sk(hdev, HCI_OP_NOP, 0, NULL, + HCI_EV_LE_EXT_ADV_REPORT, + conn->conn_timeout, NULL); + if (err == -ETIMEDOUT) + goto done; + } memset(&cp, 0, sizeof(cp)); cp.options = qos->bcast.options; @@ -7080,6 +7081,12 @@ static int hci_le_pa_create_sync(struct hci_dev *hdev, void *data) __hci_cmd_sync_status(hdev, HCI_OP_LE_PA_CREATE_SYNC_CANCEL, 0, NULL, HCI_CMD_TIMEOUT); +done: + hci_dev_clear_flag(hdev, HCI_PA_SYNC); + + /* Update passive scan since HCI_PA_SYNC flag has been cleared */ + hci_update_passive_scan_sync(hdev); + return err; } diff --git a/net/bluetooth/iso.c b/net/bluetooth/iso.c index 7bd3aa0a6db9..5ce823ca3aaf 100644 --- a/net/bluetooth/iso.c +++ b/net/bluetooth/iso.c @@ -1347,7 +1347,7 @@ static int iso_sock_getname(struct socket *sock, struct sockaddr *addr, bacpy(&sa->iso_bdaddr, &iso_pi(sk)->dst); sa->iso_bdaddr_type = iso_pi(sk)->dst_type; - if (hcon && hcon->type == BIS_LINK) { + if (hcon && (hcon->type == BIS_LINK || hcon->type == PA_LINK)) { sa->iso_bc->bc_sid = iso_pi(sk)->bc_sid; sa->iso_bc->bc_num_bis = iso_pi(sk)->bc_num_bis; memcpy(sa->iso_bc->bc_bis, iso_pi(sk)->bc_bis, @@ -2483,11 +2483,11 @@ static const struct net_proto_family iso_sock_family_ops = { .create = iso_sock_create, }; -static bool iso_inited; +static bool inited; -bool iso_enabled(void) +bool iso_inited(void) { - return iso_inited; + return inited; } int iso_init(void) @@ -2496,7 +2496,7 @@ int iso_init(void) BUILD_BUG_ON(sizeof(struct sockaddr_iso) > sizeof(struct sockaddr)); - if (iso_inited) + if (inited) return -EALREADY; err = proto_register(&iso_proto, 0); @@ -2524,7 +2524,7 @@ int iso_init(void) iso_debugfs = debugfs_create_file("iso", 0444, bt_debugfs, NULL, &iso_debugfs_fops); - iso_inited = true; + inited = true; return 0; @@ -2535,7 +2535,7 @@ error: int iso_exit(void) { - if (!iso_inited) + if (!inited) return -EALREADY; bt_procfs_cleanup(&init_net, "iso"); @@ -2549,7 +2549,7 @@ int iso_exit(void) proto_unregister(&iso_proto); - iso_inited = false; + inited = false; return 0; } diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index 1ce682038b51..3166f5fb876b 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -922,19 +922,19 @@ static u32 get_current_settings(struct hci_dev *hdev) if (hci_dev_test_flag(hdev, HCI_WIDEBAND_SPEECH_ENABLED)) settings |= MGMT_SETTING_WIDEBAND_SPEECH; - if (cis_central_capable(hdev)) + if (cis_central_enabled(hdev)) settings |= MGMT_SETTING_CIS_CENTRAL; - if (cis_peripheral_capable(hdev)) + if (cis_peripheral_enabled(hdev)) settings |= MGMT_SETTING_CIS_PERIPHERAL; - if (bis_capable(hdev)) + if (bis_enabled(hdev)) settings |= MGMT_SETTING_ISO_BROADCASTER; - if (sync_recv_capable(hdev)) + if (sync_recv_enabled(hdev)) settings |= MGMT_SETTING_ISO_SYNC_RECEIVER; - if (ll_privacy_capable(hdev)) + if (ll_privacy_enabled(hdev)) settings |= MGMT_SETTING_LL_PRIVACY; return settings; @@ -4513,7 +4513,7 @@ static int read_exp_features_info(struct sock *sk, struct hci_dev *hdev, } if (IS_ENABLED(CONFIG_BT_LE)) { - flags = iso_enabled() ? BIT(0) : 0; + flags = iso_inited() ? BIT(0) : 0; memcpy(rp->features[idx].uuid, iso_socket_uuid, 16); rp->features[idx].flags = cpu_to_le32(flags); idx++; diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 1377f31b719c..8ce145938b02 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -4818,6 +4818,14 @@ void br_multicast_set_query_intvl(struct net_bridge_mcast *brmctx, intvl_jiffies = BR_MULTICAST_QUERY_INTVL_MIN; } + if (intvl_jiffies > BR_MULTICAST_QUERY_INTVL_MAX) { + br_info(brmctx->br, + "trying to set multicast query interval above maximum, setting to %lu (%ums)\n", + jiffies_to_clock_t(BR_MULTICAST_QUERY_INTVL_MAX), + jiffies_to_msecs(BR_MULTICAST_QUERY_INTVL_MAX)); + intvl_jiffies = BR_MULTICAST_QUERY_INTVL_MAX; + } + brmctx->multicast_query_interval = intvl_jiffies; } @@ -4834,6 +4842,14 @@ void br_multicast_set_startup_query_intvl(struct net_bridge_mcast *brmctx, intvl_jiffies = BR_MULTICAST_STARTUP_QUERY_INTVL_MIN; } + if (intvl_jiffies > BR_MULTICAST_STARTUP_QUERY_INTVL_MAX) { + br_info(brmctx->br, + "trying to set multicast startup query interval above maximum, setting to %lu (%ums)\n", + jiffies_to_clock_t(BR_MULTICAST_STARTUP_QUERY_INTVL_MAX), + jiffies_to_msecs(BR_MULTICAST_STARTUP_QUERY_INTVL_MAX)); + intvl_jiffies = BR_MULTICAST_STARTUP_QUERY_INTVL_MAX; + } + brmctx->multicast_startup_query_interval = intvl_jiffies; } diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index b159aae594c0..8de0904b9627 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -31,6 +31,8 @@ #define BR_MULTICAST_DEFAULT_HASH_MAX 4096 #define BR_MULTICAST_QUERY_INTVL_MIN msecs_to_jiffies(1000) #define BR_MULTICAST_STARTUP_QUERY_INTVL_MIN BR_MULTICAST_QUERY_INTVL_MIN +#define BR_MULTICAST_QUERY_INTVL_MAX msecs_to_jiffies(86400000) /* 24 hours */ +#define BR_MULTICAST_STARTUP_QUERY_INTVL_MAX BR_MULTICAST_QUERY_INTVL_MAX #define BR_HWDOM_MAX BITS_PER_LONG diff --git a/net/bridge/netfilter/Kconfig b/net/bridge/netfilter/Kconfig index 60f28e4fb5c0..4fd5a6ea26b4 100644 --- a/net/bridge/netfilter/Kconfig +++ b/net/bridge/netfilter/Kconfig @@ -43,6 +43,7 @@ config NF_CONNTRACK_BRIDGE config BRIDGE_NF_EBTABLES_LEGACY tristate "Legacy EBTABLES support" depends on BRIDGE && NETFILTER_XTABLES_LEGACY + depends on NETFILTER_XTABLES default n help Legacy ebtables packet/frame classifier. diff --git a/net/core/dev.c b/net/core/dev.c index 68dc47d7e700..93a25d87b86b 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3779,6 +3779,18 @@ static netdev_features_t gso_features_check(const struct sk_buff *skb, features &= ~NETIF_F_TSO_MANGLEID; } + /* NETIF_F_IPV6_CSUM does not support IPv6 extension headers, + * so neither does TSO that depends on it. + */ + if (features & NETIF_F_IPV6_CSUM && + (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6 || + (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4 && + vlan_get_protocol(skb) == htons(ETH_P_IPV6))) && + skb_transport_header_was_set(skb) && + skb_network_header_len(skb) != sizeof(struct ipv6hdr) && + !ipv6_has_hopopt_jumbo(skb)) + features &= ~(NETIF_F_IPV6_CSUM | NETIF_F_TSO6 | NETIF_F_GSO_UDP_L4); + return features; } @@ -6999,7 +7011,7 @@ int netif_set_threaded(struct net_device *dev, enum netdev_napi_threaded threaded) { struct napi_struct *napi; - int err = 0; + int i, err = 0; netdev_assert_locked_or_invisible(dev); @@ -7021,6 +7033,10 @@ int netif_set_threaded(struct net_device *dev, list_for_each_entry(napi, &dev->napi_list, dev_list) WARN_ON_ONCE(napi_set_threaded(napi, threaded)); + /* Override the config for all NAPIs even if currently not listed */ + for (i = 0; i < dev->num_napi_configs; i++) + dev->napi_config[i].threaded = threaded; + return err; } @@ -7353,8 +7369,9 @@ void netif_napi_add_weight_locked(struct net_device *dev, * Clear dev->threaded if kthread creation failed so that * threaded mode will not be enabled in napi_enable(). */ - if (dev->threaded && napi_kthread_create(napi)) - dev->threaded = NETDEV_NAPI_THREADED_DISABLED; + if (napi_get_threaded_config(dev, napi)) + if (napi_kthread_create(napi)) + dev->threaded = NETDEV_NAPI_THREADED_DISABLED; netif_napi_set_irq_locked(napi, -1); } EXPORT_SYMBOL(netif_napi_add_weight_locked); @@ -11873,6 +11890,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, goto free_all; dev->cfg_pending = dev->cfg; + dev->num_napi_configs = maxqs; napi_config_sz = array_size(maxqs, sizeof(*dev->napi_config)); dev->napi_config = kvzalloc(napi_config_sz, GFP_KERNEL_ACCOUNT); if (!dev->napi_config) diff --git a/net/core/dev.h b/net/core/dev.h index ab69edc0c3e3..d6b08d435479 100644 --- a/net/core/dev.h +++ b/net/core/dev.h @@ -323,6 +323,14 @@ static inline enum netdev_napi_threaded napi_get_threaded(struct napi_struct *n) return NETDEV_NAPI_THREADED_DISABLED; } +static inline enum netdev_napi_threaded +napi_get_threaded_config(struct net_device *dev, struct napi_struct *n) +{ + if (n->config) + return n->config->threaded; + return dev->threaded; +} + int napi_set_threaded(struct napi_struct *n, enum netdev_napi_threaded threaded); diff --git a/net/core/page_pool.c b/net/core/page_pool.c index 05e2e22a8f7c..343a6cac21e3 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -1201,6 +1201,35 @@ void page_pool_use_xdp_mem(struct page_pool *pool, void (*disconnect)(void *), pool->xdp_mem_id = mem->id; } +/** + * page_pool_enable_direct_recycling() - mark page pool as owned by NAPI + * @pool: page pool to modify + * @napi: NAPI instance to associate the page pool with + * + * Associate a page pool with a NAPI instance for lockless page recycling. + * This is useful when a new page pool has to be added to a NAPI instance + * without disabling that NAPI instance, to mark the point at which control + * path "hands over" the page pool to the NAPI instance. In most cases driver + * can simply set the @napi field in struct page_pool_params, and does not + * have to call this helper. + * + * The function is idempotent, but does not implement any refcounting. + * Single page_pool_disable_direct_recycling() will disable recycling, + * no matter how many times enable was called. + */ +void page_pool_enable_direct_recycling(struct page_pool *pool, + struct napi_struct *napi) +{ + if (READ_ONCE(pool->p.napi) == napi) + return; + WARN_ON(!napi || pool->p.napi); + + mutex_lock(&page_pools_lock); + WRITE_ONCE(pool->p.napi, napi); + mutex_unlock(&page_pools_lock); +} +EXPORT_SYMBOL(page_pool_enable_direct_recycling); + void page_pool_disable_direct_recycling(struct page_pool *pool) { /* Disable direct recycling based on pool->cpuid. diff --git a/net/devlink/port.c b/net/devlink/port.c index 939081a0e615..cb8d4df61619 100644 --- a/net/devlink/port.c +++ b/net/devlink/port.c @@ -1519,7 +1519,7 @@ static int __devlink_port_phys_port_name_get(struct devlink_port *devlink_port, struct devlink_port_attrs *attrs = &devlink_port->attrs; int n = 0; - if (!devlink_port->attrs_set) + if (!devlink_port->attrs_set || devlink_port->attrs.no_phys_port_name) return -EOPNOTSUPP; switch (attrs->flavour) { diff --git a/net/hsr/hsr_slave.c b/net/hsr/hsr_slave.c index b87b6a6fe070..102eccf5ead7 100644 --- a/net/hsr/hsr_slave.c +++ b/net/hsr/hsr_slave.c @@ -63,8 +63,14 @@ static rx_handler_result_t hsr_handle_frame(struct sk_buff **pskb) skb_push(skb, ETH_HLEN); skb_reset_mac_header(skb); if ((!hsr->prot_version && protocol == htons(ETH_P_PRP)) || - protocol == htons(ETH_P_HSR)) + protocol == htons(ETH_P_HSR)) { + if (!pskb_may_pull(skb, ETH_HLEN + HSR_HLEN)) { + kfree_skb(skb); + goto finish_consume; + } + skb_set_network_header(skb, ETH_HLEN + HSR_HLEN); + } skb_reset_mac_len(skb); /* Only the frames received over the interlink port will assign a diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig index 2c438b140e88..7dc9772fe2d8 100644 --- a/net/ipv4/netfilter/Kconfig +++ b/net/ipv4/netfilter/Kconfig @@ -14,6 +14,7 @@ config NF_DEFRAG_IPV4 config IP_NF_IPTABLES_LEGACY tristate "Legacy IP tables support" depends on NETFILTER_XTABLES_LEGACY + depends on NETFILTER_XTABLES default m if NETFILTER_XTABLES_LEGACY help iptables is a legacy packet classifier. @@ -326,6 +327,7 @@ endif # IP_NF_IPTABLES config IP_NF_ARPTABLES tristate "Legacy ARPTABLES support" depends on NETFILTER_XTABLES_LEGACY + depends on NETFILTER_XTABLES default n help arptables is a legacy packet classifier. @@ -343,6 +345,7 @@ config IP_NF_ARPFILTER select IP_NF_ARPTABLES select NETFILTER_FAMILY_ARP depends on NETFILTER_XTABLES_LEGACY + depends on NETFILTER_XTABLES help ARP packet filtering defines a table `filter', which has a series of rules for simple ARP packet filtering at local input and diff --git a/net/ipv4/netfilter/nf_reject_ipv4.c b/net/ipv4/netfilter/nf_reject_ipv4.c index 87fd945a0d27..0d3cb2ba6fc8 100644 --- a/net/ipv4/netfilter/nf_reject_ipv4.c +++ b/net/ipv4/netfilter/nf_reject_ipv4.c @@ -247,8 +247,7 @@ void nf_send_reset(struct net *net, struct sock *sk, struct sk_buff *oldskb, if (!oth) return; - if ((hook == NF_INET_PRE_ROUTING || hook == NF_INET_INGRESS) && - nf_reject_fill_skb_dst(oldskb) < 0) + if (!skb_dst(oldskb) && nf_reject_fill_skb_dst(oldskb) < 0) return; if (skb_rtable(oldskb)->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST)) @@ -321,8 +320,7 @@ void nf_send_unreach(struct sk_buff *skb_in, int code, int hook) if (iph->frag_off & htons(IP_OFFSET)) return; - if ((hook == NF_INET_PRE_ROUTING || hook == NF_INET_INGRESS) && - nf_reject_fill_skb_dst(skb_in) < 0) + if (!skb_dst(skb_in) && nf_reject_fill_skb_dst(skb_in) < 0) return; if (skb_csum_unnecessary(skb_in) || diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index 5128e2a5b00a..b1f3fd302e9d 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -217,7 +217,7 @@ static struct sk_buff *__skb_udp_tunnel_segment(struct sk_buff *skb, remcsum = !!(skb_shinfo(skb)->gso_type & SKB_GSO_TUNNEL_REMCSUM); skb->remcsum_offload = remcsum; - need_ipsec = skb_dst(skb) && dst_xfrm(skb_dst(skb)); + need_ipsec = (skb_dst(skb) && dst_xfrm(skb_dst(skb))) || skb_sec_path(skb); /* Try to offload checksum if possible */ offload_csum = !!(need_csum && !need_ipsec && diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig index 276860f65baa..81daf82ddc2d 100644 --- a/net/ipv6/netfilter/Kconfig +++ b/net/ipv6/netfilter/Kconfig @@ -10,6 +10,7 @@ menu "IPv6: Netfilter Configuration" config IP6_NF_IPTABLES_LEGACY tristate "Legacy IP6 tables support" depends on INET && IPV6 && NETFILTER_XTABLES_LEGACY + depends on NETFILTER_XTABLES default m if NETFILTER_XTABLES_LEGACY help ip6tables is a legacy packet classifier. diff --git a/net/ipv6/netfilter/nf_reject_ipv6.c b/net/ipv6/netfilter/nf_reject_ipv6.c index 838295fa32e3..cb2d38e80de9 100644 --- a/net/ipv6/netfilter/nf_reject_ipv6.c +++ b/net/ipv6/netfilter/nf_reject_ipv6.c @@ -293,7 +293,7 @@ void nf_send_reset6(struct net *net, struct sock *sk, struct sk_buff *oldskb, fl6.fl6_sport = otcph->dest; fl6.fl6_dport = otcph->source; - if (hook == NF_INET_PRE_ROUTING || hook == NF_INET_INGRESS) { + if (!skb_dst(oldskb)) { nf_ip6_route(net, &dst, flowi6_to_flowi(&fl6), false); if (!dst) return; @@ -397,8 +397,7 @@ void nf_send_unreach6(struct net *net, struct sk_buff *skb_in, if (hooknum == NF_INET_LOCAL_OUT && skb_in->dev == NULL) skb_in->dev = net->loopback_dev; - if ((hooknum == NF_INET_PRE_ROUTING || hooknum == NF_INET_INGRESS) && - nf_reject6_fill_skb_dst(skb_in) < 0) + if (!skb_dst(skb_in) && nf_reject6_fill_skb_dst(skb_in) < 0) return; icmpv6_send(skb_in, ICMPV6_DEST_UNREACH, code, 0); diff --git a/net/ipv6/seg6_hmac.c b/net/ipv6/seg6_hmac.c index f78ecb6ad838..fd58426f222b 100644 --- a/net/ipv6/seg6_hmac.c +++ b/net/ipv6/seg6_hmac.c @@ -35,6 +35,7 @@ #include <net/xfrm.h> #include <crypto/hash.h> +#include <crypto/utils.h> #include <net/seg6.h> #include <net/genetlink.h> #include <net/seg6_hmac.h> @@ -280,7 +281,7 @@ bool seg6_hmac_validate_skb(struct sk_buff *skb) if (seg6_hmac_compute(hinfo, srh, &ipv6_hdr(skb)->saddr, hmac_output)) return false; - if (memcmp(hmac_output, tlv->hmac, SEG6_HMAC_FIELD_LEN) != 0) + if (crypto_memneq(hmac_output, tlv->hmac, SEG6_HMAC_FIELD_LEN)) return false; return true; @@ -304,6 +305,9 @@ int seg6_hmac_info_add(struct net *net, u32 key, struct seg6_hmac_info *hinfo) struct seg6_pernet_data *sdata = seg6_pernet(net); int err; + if (!__hmac_get_algo(hinfo->alg_id)) + return -EINVAL; + err = rhashtable_lookup_insert_fast(&sdata->hmac_infos, &hinfo->node, rht_params); diff --git a/net/ipv6/xfrm6_tunnel.c b/net/ipv6/xfrm6_tunnel.c index 5120a763da0d..0a0eeaed0591 100644 --- a/net/ipv6/xfrm6_tunnel.c +++ b/net/ipv6/xfrm6_tunnel.c @@ -334,7 +334,7 @@ static void __net_exit xfrm6_tunnel_net_exit(struct net *net) struct xfrm6_tunnel_net *xfrm6_tn = xfrm6_tunnel_pernet(net); unsigned int i; - xfrm_state_flush(net, IPSEC_PROTO_ANY, false); + xfrm_state_flush(net, 0, false); xfrm_flush_gc(); for (i = 0; i < XFRM6_TUNNEL_SPI_BYADDR_HSIZE; i++) diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c index a4971e6fa943..b4f01cb07561 100644 --- a/net/kcm/kcmsock.c +++ b/net/kcm/kcmsock.c @@ -430,7 +430,7 @@ static void psock_write_space(struct sock *sk) /* Check if the socket is reserved so someone is waiting for sending. */ kcm = psock->tx_kcm; - if (kcm && !unlikely(kcm->tx_stopped)) + if (kcm) queue_work(kcm_wq, &kcm->tx_work); spin_unlock_bh(&mux->lock); @@ -1693,12 +1693,6 @@ static int kcm_release(struct socket *sock) */ __skb_queue_purge(&sk->sk_write_queue); - /* Set tx_stopped. This is checked when psock is bound to a kcm and we - * get a writespace callback. This prevents further work being queued - * from the callback (unbinding the psock occurs after canceling work. - */ - kcm->tx_stopped = 1; - release_sock(sk); spin_lock_bh(&mux->lock); @@ -1714,7 +1708,7 @@ static int kcm_release(struct socket *sock) /* Cancel work. After this point there should be no outside references * to the kcm socket. */ - cancel_work_sync(&kcm->tx_work); + disable_work_sync(&kcm->tx_work); lock_sock(sk); psock = kcm->tx_psock; diff --git a/net/mctp/test/route-test.c b/net/mctp/test/route-test.c index fb6b46a952cb..69a3ccfc6310 100644 --- a/net/mctp/test/route-test.c +++ b/net/mctp/test/route-test.c @@ -1586,7 +1586,6 @@ static void mctp_test_bind_lookup(struct kunit *test) cleanup: kfree_skb(skb_sock); - kfree_skb(skb_pkt); /* Drop all binds */ for (size_t i = 0; i < ARRAY_SIZE(lookup_binds); i++) diff --git a/net/mptcp/options.c b/net/mptcp/options.c index 70c0ab0ecf90..2a8ea28442b2 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -1118,7 +1118,9 @@ static bool add_addr_hmac_valid(struct mptcp_sock *msk, return hmac == mp_opt->ahmac; } -/* Return false if a subflow has been reset, else return true */ +/* Return false in case of error (or subflow has been reset), + * else return true. + */ bool mptcp_incoming_options(struct sock *sk, struct sk_buff *skb) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); @@ -1222,7 +1224,7 @@ bool mptcp_incoming_options(struct sock *sk, struct sk_buff *skb) mpext = skb_ext_add(skb, SKB_EXT_MPTCP); if (!mpext) - return true; + return false; memset(mpext, 0, sizeof(*mpext)); diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c index 420d416e2603..136a380602ca 100644 --- a/net/mptcp/pm.c +++ b/net/mptcp/pm.c @@ -274,6 +274,7 @@ static void mptcp_pm_add_timer(struct timer_list *timer) add_timer); struct mptcp_sock *msk = entry->sock; struct sock *sk = (struct sock *)msk; + unsigned int timeout; pr_debug("msk=%p\n", msk); @@ -291,6 +292,10 @@ static void mptcp_pm_add_timer(struct timer_list *timer) goto out; } + timeout = mptcp_get_add_addr_timeout(sock_net(sk)); + if (!timeout) + goto out; + spin_lock_bh(&msk->pm.lock); if (!mptcp_pm_should_add_signal_addr(msk)) { @@ -302,7 +307,7 @@ static void mptcp_pm_add_timer(struct timer_list *timer) if (entry->retrans_times < ADD_ADDR_RETRANS_MAX) sk_reset_timer(sk, timer, - jiffies + mptcp_get_add_addr_timeout(sock_net(sk))); + jiffies + timeout); spin_unlock_bh(&msk->pm.lock); @@ -344,6 +349,7 @@ bool mptcp_pm_alloc_anno_list(struct mptcp_sock *msk, struct mptcp_pm_add_entry *add_entry = NULL; struct sock *sk = (struct sock *)msk; struct net *net = sock_net(sk); + unsigned int timeout; lockdep_assert_held(&msk->pm.lock); @@ -353,9 +359,7 @@ bool mptcp_pm_alloc_anno_list(struct mptcp_sock *msk, if (WARN_ON_ONCE(mptcp_pm_is_kernel(msk))) return false; - sk_reset_timer(sk, &add_entry->add_timer, - jiffies + mptcp_get_add_addr_timeout(net)); - return true; + goto reset_timer; } add_entry = kmalloc(sizeof(*add_entry), GFP_ATOMIC); @@ -369,8 +373,10 @@ bool mptcp_pm_alloc_anno_list(struct mptcp_sock *msk, add_entry->retrans_times = 0; timer_setup(&add_entry->add_timer, mptcp_pm_add_timer, 0); - sk_reset_timer(sk, &add_entry->add_timer, - jiffies + mptcp_get_add_addr_timeout(net)); +reset_timer: + timeout = mptcp_get_add_addr_timeout(net); + if (timeout) + sk_reset_timer(sk, &add_entry->add_timer, jiffies + timeout); return true; } diff --git a/net/mptcp/pm_kernel.c b/net/mptcp/pm_kernel.c index d39e7c178460..667803d72b64 100644 --- a/net/mptcp/pm_kernel.c +++ b/net/mptcp/pm_kernel.c @@ -1085,7 +1085,6 @@ static void __flush_addrs(struct list_head *list) static void __reset_counters(struct pm_nl_pernet *pernet) { WRITE_ONCE(pernet->add_addr_signal_max, 0); - WRITE_ONCE(pernet->add_addr_accept_max, 0); WRITE_ONCE(pernet->local_addr_max, 0); pernet->addrs = 0; } diff --git a/net/netfilter/ipvs/ip_vs_est.c b/net/netfilter/ipvs/ip_vs_est.c index f821ad2e19b3..15049b826732 100644 --- a/net/netfilter/ipvs/ip_vs_est.c +++ b/net/netfilter/ipvs/ip_vs_est.c @@ -265,7 +265,8 @@ int ip_vs_est_kthread_start(struct netns_ipvs *ipvs, } set_user_nice(kd->task, sysctl_est_nice(ipvs)); - set_cpus_allowed_ptr(kd->task, sysctl_est_cpulist(ipvs)); + if (sysctl_est_preferred_cpulist(ipvs)) + kthread_affine_preferred(kd->task, sysctl_est_preferred_cpulist(ipvs)); pr_info("starting estimator thread %d...\n", kd->id); wake_up_process(kd->task); diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 486d52b45fe5..50fd6809380f 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -884,8 +884,6 @@ errout: static int ctnetlink_done(struct netlink_callback *cb) { - if (cb->args[1]) - nf_ct_put((struct nf_conn *)cb->args[1]); kfree(cb->data); return 0; } @@ -1208,19 +1206,26 @@ ignore_entry: return 0; } +static unsigned long ctnetlink_get_id(const struct nf_conn *ct) +{ + unsigned long id = nf_ct_get_id(ct); + + return id ? id : 1; +} + static int ctnetlink_dump_table(struct sk_buff *skb, struct netlink_callback *cb) { unsigned int flags = cb->data ? NLM_F_DUMP_FILTERED : 0; struct net *net = sock_net(skb->sk); - struct nf_conn *ct, *last; + unsigned long last_id = cb->args[1]; struct nf_conntrack_tuple_hash *h; struct hlist_nulls_node *n; struct nf_conn *nf_ct_evict[8]; + struct nf_conn *ct; int res, i; spinlock_t *lockp; - last = (struct nf_conn *)cb->args[1]; i = 0; local_bh_disable(); @@ -1257,7 +1262,7 @@ restart: continue; if (cb->args[1]) { - if (ct != last) + if (ctnetlink_get_id(ct) != last_id) continue; cb->args[1] = 0; } @@ -1270,8 +1275,7 @@ restart: NFNL_MSG_TYPE(cb->nlh->nlmsg_type), ct, true, flags); if (res < 0) { - nf_conntrack_get(&ct->ct_general); - cb->args[1] = (unsigned long)ct; + cb->args[1] = ctnetlink_get_id(ct); spin_unlock(lockp); goto out; } @@ -1284,12 +1288,10 @@ restart: } out: local_bh_enable(); - if (last) { + if (last_id) { /* nf ct hash resize happened, now clear the leftover. */ - if ((struct nf_conn *)cb->args[1] == last) + if (cb->args[1] == last_id) cb->args[1] = 0; - - nf_ct_put(last); } while (i) { @@ -3168,23 +3170,27 @@ errout: return 0; } #endif -static int ctnetlink_exp_done(struct netlink_callback *cb) + +static unsigned long ctnetlink_exp_id(const struct nf_conntrack_expect *exp) { - if (cb->args[1]) - nf_ct_expect_put((struct nf_conntrack_expect *)cb->args[1]); - return 0; + unsigned long id = (unsigned long)exp; + + id += nf_ct_get_id(exp->master); + id += exp->class; + + return id ? id : 1; } static int ctnetlink_exp_dump_table(struct sk_buff *skb, struct netlink_callback *cb) { struct net *net = sock_net(skb->sk); - struct nf_conntrack_expect *exp, *last; struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh); u_int8_t l3proto = nfmsg->nfgen_family; + unsigned long last_id = cb->args[1]; + struct nf_conntrack_expect *exp; rcu_read_lock(); - last = (struct nf_conntrack_expect *)cb->args[1]; for (; cb->args[0] < nf_ct_expect_hsize; cb->args[0]++) { restart: hlist_for_each_entry_rcu(exp, &nf_ct_expect_hash[cb->args[0]], @@ -3196,7 +3202,7 @@ restart: continue; if (cb->args[1]) { - if (exp != last) + if (ctnetlink_exp_id(exp) != last_id) continue; cb->args[1] = 0; } @@ -3205,9 +3211,7 @@ restart: cb->nlh->nlmsg_seq, IPCTNL_MSG_EXP_NEW, exp) < 0) { - if (!refcount_inc_not_zero(&exp->use)) - continue; - cb->args[1] = (unsigned long)exp; + cb->args[1] = ctnetlink_exp_id(exp); goto out; } } @@ -3218,32 +3222,30 @@ restart: } out: rcu_read_unlock(); - if (last) - nf_ct_expect_put(last); - return skb->len; } static int ctnetlink_exp_ct_dump_table(struct sk_buff *skb, struct netlink_callback *cb) { - struct nf_conntrack_expect *exp, *last; struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh); struct nf_conn *ct = cb->data; struct nf_conn_help *help = nfct_help(ct); u_int8_t l3proto = nfmsg->nfgen_family; + unsigned long last_id = cb->args[1]; + struct nf_conntrack_expect *exp; if (cb->args[0]) return 0; rcu_read_lock(); - last = (struct nf_conntrack_expect *)cb->args[1]; + restart: hlist_for_each_entry_rcu(exp, &help->expectations, lnode) { if (l3proto && exp->tuple.src.l3num != l3proto) continue; if (cb->args[1]) { - if (exp != last) + if (ctnetlink_exp_id(exp) != last_id) continue; cb->args[1] = 0; } @@ -3251,9 +3253,7 @@ restart: cb->nlh->nlmsg_seq, IPCTNL_MSG_EXP_NEW, exp) < 0) { - if (!refcount_inc_not_zero(&exp->use)) - continue; - cb->args[1] = (unsigned long)exp; + cb->args[1] = ctnetlink_exp_id(exp); goto out; } } @@ -3264,9 +3264,6 @@ restart: cb->args[0] = 1; out: rcu_read_unlock(); - if (last) - nf_ct_expect_put(last); - return skb->len; } @@ -3285,7 +3282,6 @@ static int ctnetlink_dump_exp_ct(struct net *net, struct sock *ctnl, struct nf_conntrack_zone zone; struct netlink_dump_control c = { .dump = ctnetlink_exp_ct_dump_table, - .done = ctnetlink_exp_done, }; err = ctnetlink_parse_tuple(cda, &tuple, CTA_EXPECT_MASTER, @@ -3335,7 +3331,6 @@ static int ctnetlink_get_expect(struct sk_buff *skb, else { struct netlink_dump_control c = { .dump = ctnetlink_exp_dump_table, - .done = ctnetlink_exp_done, }; return netlink_dump_start(info->sk, skb, info->nlh, &c); } diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index 9b8b10a85233..1f14ef0436c6 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -567,16 +567,16 @@ nf_conntrack_log_invalid_sysctl(const struct ctl_table *table, int write, return ret; if (*(u8 *)table->data == 0) - return ret; + return 0; /* Load nf_log_syslog only if no logger is currently registered */ for (i = 0; i < NFPROTO_NUMPROTO; i++) { if (nf_log_is_registered(i)) - return ret; + return 0; } request_module("%s", "nf_log_syslog"); - return ret; + return 0; } static struct ctl_table_header *nf_ct_netfilter_header; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 13d0ed9d1895..58c5425d61c2 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -2803,6 +2803,7 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy, struct nft_chain *chain = ctx->chain; struct nft_chain_hook hook = {}; struct nft_stats __percpu *stats = NULL; + struct nftables_pernet *nft_net; struct nft_hook *h, *next; struct nf_hook_ops *ops; struct nft_trans *trans; @@ -2845,6 +2846,20 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy, if (nft_hook_list_find(&basechain->hook_list, h)) { list_del(&h->list); nft_netdev_hook_free(h); + continue; + } + + nft_net = nft_pernet(ctx->net); + list_for_each_entry(trans, &nft_net->commit_list, list) { + if (trans->msg_type != NFT_MSG_NEWCHAIN || + trans->table != ctx->table || + !nft_trans_chain_update(trans)) + continue; + + if (nft_hook_list_find(&nft_trans_chain_hooks(trans), h)) { + nft_chain_release_hook(&hook); + return -EEXIST; + } } } } else { @@ -9060,6 +9075,7 @@ static int nft_flowtable_update(struct nft_ctx *ctx, const struct nlmsghdr *nlh, { const struct nlattr * const *nla = ctx->nla; struct nft_flowtable_hook flowtable_hook; + struct nftables_pernet *nft_net; struct nft_hook *hook, *next; struct nf_hook_ops *ops; struct nft_trans *trans; @@ -9076,6 +9092,20 @@ static int nft_flowtable_update(struct nft_ctx *ctx, const struct nlmsghdr *nlh, if (nft_hook_list_find(&flowtable->hook_list, hook)) { list_del(&hook->list); nft_netdev_hook_free(hook); + continue; + } + + nft_net = nft_pernet(ctx->net); + list_for_each_entry(trans, &nft_net->commit_list, list) { + if (trans->msg_type != NFT_MSG_NEWFLOWTABLE || + trans->table != ctx->table || + !nft_trans_flowtable_update(trans)) + continue; + + if (nft_hook_list_find(&nft_trans_flowtable_hooks(trans), hook)) { + err = -EEXIST; + goto err_flowtable_update_hook; + } } } diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index 1a19649c2851..9a10251228fd 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -426,10 +426,9 @@ static struct nft_pipapo_elem *pipapo_get(const struct nft_pipapo_match *m, local_bh_disable(); - if (unlikely(!raw_cpu_ptr(m->scratch))) - goto out; - scratch = *raw_cpu_ptr(m->scratch); + if (unlikely(!scratch)) + goto out; map_index = scratch->map_index; diff --git a/net/netfilter/nft_set_pipapo_avx2.c b/net/netfilter/nft_set_pipapo_avx2.c index db5d367e43c4..2f090e253caf 100644 --- a/net/netfilter/nft_set_pipapo_avx2.c +++ b/net/netfilter/nft_set_pipapo_avx2.c @@ -1150,12 +1150,12 @@ nft_pipapo_avx2_lookup(const struct net *net, const struct nft_set *set, const u32 *key) { struct nft_pipapo *priv = nft_set_priv(set); + const struct nft_set_ext *ext = NULL; struct nft_pipapo_scratch *scratch; u8 genmask = nft_genmask_cur(net); const struct nft_pipapo_match *m; const struct nft_pipapo_field *f; const u8 *rp = (const u8 *)key; - const struct nft_set_ext *ext; unsigned long *res, *fill; bool map_index; int i; @@ -1246,13 +1246,13 @@ next_match: goto out; if (last) { - ext = &f->mt[ret].e->ext; - if (unlikely(nft_set_elem_expired(ext) || - !nft_set_elem_active(ext, genmask))) { - ext = NULL; + const struct nft_set_ext *e = &f->mt[ret].e->ext; + + if (unlikely(nft_set_elem_expired(e) || + !nft_set_elem_active(e, genmask))) goto next_match; - } + ext = e; goto out; } diff --git a/net/netfilter/nft_socket.c b/net/netfilter/nft_socket.c index 35d0409b0095..36affbb697c2 100644 --- a/net/netfilter/nft_socket.c +++ b/net/netfilter/nft_socket.c @@ -217,7 +217,7 @@ static int nft_socket_init(const struct nft_ctx *ctx, level += err; /* Implies a giant cgroup tree */ - if (WARN_ON_ONCE(level > 255)) + if (level > 255) return -EOPNOTSUPP; priv->level = level; diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c index dbcfb948c867..32bacfc314c2 100644 --- a/net/sched/sch_cake.c +++ b/net/sched/sch_cake.c @@ -1750,7 +1750,7 @@ static s32 cake_enqueue(struct sk_buff *skb, struct Qdisc *sch, ktime_t now = ktime_get(); struct cake_tin_data *b; struct cake_flow *flow; - u32 idx; + u32 idx, tin; /* choose flow to insert into */ idx = cake_classify(sch, &b, skb, q->flow_mode, &ret); @@ -1760,6 +1760,7 @@ static s32 cake_enqueue(struct sk_buff *skb, struct Qdisc *sch, __qdisc_drop(skb, to_free); return ret; } + tin = (u32)(b - q->tins); idx--; flow = &b->flows[idx]; @@ -1927,13 +1928,22 @@ static s32 cake_enqueue(struct sk_buff *skb, struct Qdisc *sch, q->buffer_max_used = q->buffer_used; if (q->buffer_used > q->buffer_limit) { + bool same_flow = false; u32 dropped = 0; + u32 drop_id; while (q->buffer_used > q->buffer_limit) { dropped++; - cake_drop(sch, to_free); + drop_id = cake_drop(sch, to_free); + + if ((drop_id >> 16) == tin && + (drop_id & 0xFFFF) == idx) + same_flow = true; } b->drop_overlimit += dropped; + + if (same_flow) + return NET_XMIT_CN; } return NET_XMIT_SUCCESS; } diff --git a/net/sched/sch_codel.c b/net/sched/sch_codel.c index c93761040c6e..fa0314679e43 100644 --- a/net/sched/sch_codel.c +++ b/net/sched/sch_codel.c @@ -101,9 +101,9 @@ static const struct nla_policy codel_policy[TCA_CODEL_MAX + 1] = { static int codel_change(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { + unsigned int dropped_pkts = 0, dropped_bytes = 0; struct codel_sched_data *q = qdisc_priv(sch); struct nlattr *tb[TCA_CODEL_MAX + 1]; - unsigned int qlen, dropped = 0; int err; err = nla_parse_nested_deprecated(tb, TCA_CODEL_MAX, opt, @@ -142,15 +142,17 @@ static int codel_change(struct Qdisc *sch, struct nlattr *opt, WRITE_ONCE(q->params.ecn, !!nla_get_u32(tb[TCA_CODEL_ECN])); - qlen = sch->q.qlen; while (sch->q.qlen > sch->limit) { struct sk_buff *skb = qdisc_dequeue_internal(sch, true); - dropped += qdisc_pkt_len(skb); - qdisc_qstats_backlog_dec(sch, skb); + if (!skb) + break; + + dropped_pkts++; + dropped_bytes += qdisc_pkt_len(skb); rtnl_qdisc_drop(skb, sch); } - qdisc_tree_reduce_backlog(sch, qlen - sch->q.qlen, dropped); + qdisc_tree_reduce_backlog(sch, dropped_pkts, dropped_bytes); sch_tree_unlock(sch); return 0; diff --git a/net/sched/sch_dualpi2.c b/net/sched/sch_dualpi2.c index 845375ebd4ea..4b975feb52b1 100644 --- a/net/sched/sch_dualpi2.c +++ b/net/sched/sch_dualpi2.c @@ -927,7 +927,8 @@ static int dualpi2_init(struct Qdisc *sch, struct nlattr *opt, q->sch = sch; dualpi2_reset_default(sch); - hrtimer_setup(&q->pi2_timer, dualpi2_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED); + hrtimer_setup(&q->pi2_timer, dualpi2_timer, CLOCK_MONOTONIC, + HRTIMER_MODE_ABS_PINNED_SOFT); if (opt && nla_len(opt)) { err = dualpi2_change(sch, opt, extack); @@ -937,7 +938,7 @@ static int dualpi2_init(struct Qdisc *sch, struct nlattr *opt, } hrtimer_start(&q->pi2_timer, next_pi2_timeout(q), - HRTIMER_MODE_ABS_PINNED); + HRTIMER_MODE_ABS_PINNED_SOFT); return 0; } diff --git a/net/sched/sch_ets.c b/net/sched/sch_ets.c index 037f764822b9..82635dd2cfa5 100644 --- a/net/sched/sch_ets.c +++ b/net/sched/sch_ets.c @@ -651,6 +651,12 @@ static int ets_qdisc_change(struct Qdisc *sch, struct nlattr *opt, sch_tree_lock(sch); + for (i = nbands; i < oldbands; i++) { + if (i >= q->nstrict && q->classes[i].qdisc->q.qlen) + list_del_init(&q->classes[i].alist); + qdisc_purge_queue(q->classes[i].qdisc); + } + WRITE_ONCE(q->nbands, nbands); for (i = nstrict; i < q->nstrict; i++) { if (q->classes[i].qdisc->q.qlen) { @@ -658,11 +664,6 @@ static int ets_qdisc_change(struct Qdisc *sch, struct nlattr *opt, q->classes[i].deficit = quanta[i]; } } - for (i = q->nbands; i < oldbands; i++) { - if (i >= q->nstrict && q->classes[i].qdisc->q.qlen) - list_del_init(&q->classes[i].alist); - qdisc_purge_queue(q->classes[i].qdisc); - } WRITE_ONCE(q->nstrict, nstrict); memcpy(q->prio2band, priomap, sizeof(priomap)); diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c index 902ff5470607..fee922da2f99 100644 --- a/net/sched/sch_fq.c +++ b/net/sched/sch_fq.c @@ -1013,11 +1013,11 @@ static int fq_load_priomap(struct fq_sched_data *q, static int fq_change(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { + unsigned int dropped_pkts = 0, dropped_bytes = 0; struct fq_sched_data *q = qdisc_priv(sch); struct nlattr *tb[TCA_FQ_MAX + 1]; - int err, drop_count = 0; - unsigned drop_len = 0; u32 fq_log; + int err; err = nla_parse_nested_deprecated(tb, TCA_FQ_MAX, opt, fq_policy, NULL); @@ -1135,16 +1135,18 @@ static int fq_change(struct Qdisc *sch, struct nlattr *opt, err = fq_resize(sch, fq_log); sch_tree_lock(sch); } + while (sch->q.qlen > sch->limit) { struct sk_buff *skb = qdisc_dequeue_internal(sch, false); if (!skb) break; - drop_len += qdisc_pkt_len(skb); + + dropped_pkts++; + dropped_bytes += qdisc_pkt_len(skb); rtnl_kfree_skbs(skb, skb); - drop_count++; } - qdisc_tree_reduce_backlog(sch, drop_count, drop_len); + qdisc_tree_reduce_backlog(sch, dropped_pkts, dropped_bytes); sch_tree_unlock(sch); return err; diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c index 2a0f3a513bfa..a14142392939 100644 --- a/net/sched/sch_fq_codel.c +++ b/net/sched/sch_fq_codel.c @@ -366,6 +366,7 @@ static const struct nla_policy fq_codel_policy[TCA_FQ_CODEL_MAX + 1] = { static int fq_codel_change(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { + unsigned int dropped_pkts = 0, dropped_bytes = 0; struct fq_codel_sched_data *q = qdisc_priv(sch); struct nlattr *tb[TCA_FQ_CODEL_MAX + 1]; u32 quantum = 0; @@ -443,13 +444,14 @@ static int fq_codel_change(struct Qdisc *sch, struct nlattr *opt, q->memory_usage > q->memory_limit) { struct sk_buff *skb = qdisc_dequeue_internal(sch, false); - q->cstats.drop_len += qdisc_pkt_len(skb); + if (!skb) + break; + + dropped_pkts++; + dropped_bytes += qdisc_pkt_len(skb); rtnl_kfree_skbs(skb, skb); - q->cstats.drop_count++; } - qdisc_tree_reduce_backlog(sch, q->cstats.drop_count, q->cstats.drop_len); - q->cstats.drop_count = 0; - q->cstats.drop_len = 0; + qdisc_tree_reduce_backlog(sch, dropped_pkts, dropped_bytes); sch_tree_unlock(sch); return 0; diff --git a/net/sched/sch_fq_pie.c b/net/sched/sch_fq_pie.c index b0e34daf1f75..7b96bc3ff891 100644 --- a/net/sched/sch_fq_pie.c +++ b/net/sched/sch_fq_pie.c @@ -287,10 +287,9 @@ begin: static int fq_pie_change(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { + unsigned int dropped_pkts = 0, dropped_bytes = 0; struct fq_pie_sched_data *q = qdisc_priv(sch); struct nlattr *tb[TCA_FQ_PIE_MAX + 1]; - unsigned int len_dropped = 0; - unsigned int num_dropped = 0; int err; err = nla_parse_nested(tb, TCA_FQ_PIE_MAX, opt, fq_pie_policy, extack); @@ -368,11 +367,14 @@ static int fq_pie_change(struct Qdisc *sch, struct nlattr *opt, while (sch->q.qlen > sch->limit) { struct sk_buff *skb = qdisc_dequeue_internal(sch, false); - len_dropped += qdisc_pkt_len(skb); - num_dropped += 1; + if (!skb) + break; + + dropped_pkts++; + dropped_bytes += qdisc_pkt_len(skb); rtnl_kfree_skbs(skb, skb); } - qdisc_tree_reduce_backlog(sch, num_dropped, len_dropped); + qdisc_tree_reduce_backlog(sch, dropped_pkts, dropped_bytes); sch_tree_unlock(sch); return 0; diff --git a/net/sched/sch_hhf.c b/net/sched/sch_hhf.c index 5aa434b46707..2d4855e28a28 100644 --- a/net/sched/sch_hhf.c +++ b/net/sched/sch_hhf.c @@ -508,9 +508,9 @@ static const struct nla_policy hhf_policy[TCA_HHF_MAX + 1] = { static int hhf_change(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { + unsigned int dropped_pkts = 0, dropped_bytes = 0; struct hhf_sched_data *q = qdisc_priv(sch); struct nlattr *tb[TCA_HHF_MAX + 1]; - unsigned int qlen, prev_backlog; int err; u64 non_hh_quantum; u32 new_quantum = q->quantum; @@ -561,15 +561,17 @@ static int hhf_change(struct Qdisc *sch, struct nlattr *opt, usecs_to_jiffies(us)); } - qlen = sch->q.qlen; - prev_backlog = sch->qstats.backlog; while (sch->q.qlen > sch->limit) { struct sk_buff *skb = qdisc_dequeue_internal(sch, false); + if (!skb) + break; + + dropped_pkts++; + dropped_bytes += qdisc_pkt_len(skb); rtnl_kfree_skbs(skb, skb); } - qdisc_tree_reduce_backlog(sch, qlen - sch->q.qlen, - prev_backlog - sch->qstats.backlog); + qdisc_tree_reduce_backlog(sch, dropped_pkts, dropped_bytes); sch_tree_unlock(sch); return 0; diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index c968ea763774..b5e40c51655a 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -592,7 +592,7 @@ htb_change_class_mode(struct htb_sched *q, struct htb_class *cl, s64 *diff) */ static inline void htb_activate(struct htb_sched *q, struct htb_class *cl) { - WARN_ON(cl->level || !cl->leaf.q || !cl->leaf.q->q.qlen); + WARN_ON(cl->level || !cl->leaf.q); if (!cl->prio_activity) { cl->prio_activity = 1 << cl->prio; diff --git a/net/sched/sch_pie.c b/net/sched/sch_pie.c index ad46ee3ed5a9..0a377313b6a9 100644 --- a/net/sched/sch_pie.c +++ b/net/sched/sch_pie.c @@ -141,9 +141,9 @@ static const struct nla_policy pie_policy[TCA_PIE_MAX + 1] = { static int pie_change(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { + unsigned int dropped_pkts = 0, dropped_bytes = 0; struct pie_sched_data *q = qdisc_priv(sch); struct nlattr *tb[TCA_PIE_MAX + 1]; - unsigned int qlen, dropped = 0; int err; err = nla_parse_nested_deprecated(tb, TCA_PIE_MAX, opt, pie_policy, @@ -193,15 +193,17 @@ static int pie_change(struct Qdisc *sch, struct nlattr *opt, nla_get_u32(tb[TCA_PIE_DQ_RATE_ESTIMATOR])); /* Drop excess packets if new limit is lower */ - qlen = sch->q.qlen; while (sch->q.qlen > sch->limit) { struct sk_buff *skb = qdisc_dequeue_internal(sch, true); - dropped += qdisc_pkt_len(skb); - qdisc_qstats_backlog_dec(sch, skb); + if (!skb) + break; + + dropped_pkts++; + dropped_bytes += qdisc_pkt_len(skb); rtnl_qdisc_drop(skb, sch); } - qdisc_tree_reduce_backlog(sch, qlen - sch->q.qlen, dropped); + qdisc_tree_reduce_backlog(sch, dropped_pkts, dropped_bytes); sch_tree_unlock(sch); return 0; diff --git a/net/sctp/input.c b/net/sctp/input.c index 2dc2666988fb..7e99894778d4 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -117,7 +117,7 @@ int sctp_rcv(struct sk_buff *skb) * it's better to just linearize it otherwise crc computing * takes longer. */ - if ((!is_gso && skb_linearize(skb)) || + if (((!is_gso || skb_cloned(skb)) && skb_linearize(skb)) || !pskb_may_pull(skb, sizeof(struct sctphdr))) goto discard_it; diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 9311c38f7abe..e0e48f24cd61 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -2568,8 +2568,9 @@ static void smc_listen_work(struct work_struct *work) goto out_decl; } - smc_listen_out_connected(new_smc); SMC_STAT_SERV_SUCC_INC(sock_net(newclcsock->sk), ini); + /* smc_listen_out() will release smcsk */ + smc_listen_out_connected(new_smc); goto out_free; out_unlock: diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index 46c156b121db..e2c5e0e626f9 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -257,20 +257,47 @@ svc_tcp_sock_process_cmsg(struct socket *sock, struct msghdr *msg, } static int -svc_tcp_sock_recv_cmsg(struct svc_sock *svsk, struct msghdr *msg) +svc_tcp_sock_recv_cmsg(struct socket *sock, unsigned int *msg_flags) { union { struct cmsghdr cmsg; u8 buf[CMSG_SPACE(sizeof(u8))]; } u; - struct socket *sock = svsk->sk_sock; + u8 alert[2]; + struct kvec alert_kvec = { + .iov_base = alert, + .iov_len = sizeof(alert), + }; + struct msghdr msg = { + .msg_flags = *msg_flags, + .msg_control = &u, + .msg_controllen = sizeof(u), + }; + int ret; + + iov_iter_kvec(&msg.msg_iter, ITER_DEST, &alert_kvec, 1, + alert_kvec.iov_len); + ret = sock_recvmsg(sock, &msg, MSG_DONTWAIT); + if (ret > 0 && + tls_get_record_type(sock->sk, &u.cmsg) == TLS_RECORD_TYPE_ALERT) { + iov_iter_revert(&msg.msg_iter, ret); + ret = svc_tcp_sock_process_cmsg(sock, &msg, &u.cmsg, -EAGAIN); + } + return ret; +} + +static int +svc_tcp_sock_recvmsg(struct svc_sock *svsk, struct msghdr *msg) +{ int ret; + struct socket *sock = svsk->sk_sock; - msg->msg_control = &u; - msg->msg_controllen = sizeof(u); ret = sock_recvmsg(sock, msg, MSG_DONTWAIT); - if (unlikely(msg->msg_controllen != sizeof(u))) - ret = svc_tcp_sock_process_cmsg(sock, msg, &u.cmsg, ret); + if (msg->msg_flags & MSG_CTRUNC) { + msg->msg_flags &= ~(MSG_CTRUNC | MSG_EOR); + if (ret == 0 || ret == -EIO) + ret = svc_tcp_sock_recv_cmsg(sock, &msg->msg_flags); + } return ret; } @@ -321,7 +348,7 @@ static ssize_t svc_tcp_read_msg(struct svc_rqst *rqstp, size_t buflen, iov_iter_advance(&msg.msg_iter, seek); buflen -= seek; } - len = svc_tcp_sock_recv_cmsg(svsk, &msg); + len = svc_tcp_sock_recvmsg(svsk, &msg); if (len > 0) svc_flush_bvec(bvec, len, seek); @@ -1018,7 +1045,7 @@ static ssize_t svc_tcp_read_marker(struct svc_sock *svsk, iov.iov_base = ((char *)&svsk->sk_marker) + svsk->sk_tcplen; iov.iov_len = want; iov_iter_kvec(&msg.msg_iter, ITER_DEST, &iov, 1, want); - len = svc_tcp_sock_recv_cmsg(svsk, &msg); + len = svc_tcp_sock_recvmsg(svsk, &msg); if (len < 0) return len; svsk->sk_tcplen += len; diff --git a/net/tls/tls.h b/net/tls/tls.h index 774859b63f0d..4e077068e6d9 100644 --- a/net/tls/tls.h +++ b/net/tls/tls.h @@ -196,7 +196,7 @@ void tls_strp_msg_done(struct tls_strparser *strp); int tls_rx_msg_size(struct tls_strparser *strp, struct sk_buff *skb); void tls_rx_msg_ready(struct tls_strparser *strp); -void tls_strp_msg_load(struct tls_strparser *strp, bool force_refresh); +bool tls_strp_msg_load(struct tls_strparser *strp, bool force_refresh); int tls_strp_msg_cow(struct tls_sw_context_rx *ctx); struct sk_buff *tls_strp_msg_detach(struct tls_sw_context_rx *ctx); int tls_strp_msg_hold(struct tls_strparser *strp, struct sk_buff_head *dst); diff --git a/net/tls/tls_strp.c b/net/tls/tls_strp.c index 095cf31bae0b..d71643b494a1 100644 --- a/net/tls/tls_strp.c +++ b/net/tls/tls_strp.c @@ -475,7 +475,7 @@ static void tls_strp_load_anchor_with_queue(struct tls_strparser *strp, int len) strp->stm.offset = offset; } -void tls_strp_msg_load(struct tls_strparser *strp, bool force_refresh) +bool tls_strp_msg_load(struct tls_strparser *strp, bool force_refresh) { struct strp_msg *rxm; struct tls_msg *tlm; @@ -484,8 +484,11 @@ void tls_strp_msg_load(struct tls_strparser *strp, bool force_refresh) DEBUG_NET_WARN_ON_ONCE(!strp->stm.full_len); if (!strp->copy_mode && force_refresh) { - if (WARN_ON(tcp_inq(strp->sk) < strp->stm.full_len)) - return; + if (unlikely(tcp_inq(strp->sk) < strp->stm.full_len)) { + WRITE_ONCE(strp->msg_ready, 0); + memset(&strp->stm, 0, sizeof(strp->stm)); + return false; + } tls_strp_load_anchor_with_queue(strp, strp->stm.full_len); } @@ -495,6 +498,8 @@ void tls_strp_msg_load(struct tls_strparser *strp, bool force_refresh) rxm->offset = strp->stm.offset; tlm = tls_msg(strp->anchor); tlm->control = strp->mark; + + return true; } /* Called with lock held on lower socket */ diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 549d1ea01a72..bac65d0d4e3e 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -1384,7 +1384,8 @@ tls_rx_rec_wait(struct sock *sk, struct sk_psock *psock, bool nonblock, return sock_intr_errno(timeo); } - tls_strp_msg_load(&ctx->strp, released); + if (unlikely(!tls_strp_msg_load(&ctx->strp, released))) + return tls_rx_rec_wait(sk, psock, nonblock, false); return 1; } @@ -1807,6 +1808,9 @@ int decrypt_skb(struct sock *sk, struct scatterlist *sgout) return tls_decrypt_sg(sk, NULL, sgout, &darg); } +/* All records returned from a recvmsg() call must have the same type. + * 0 is not a valid content type. Use it as "no type reported, yet". + */ static int tls_record_content_type(struct msghdr *msg, struct tls_msg *tlm, u8 *control) { @@ -2050,8 +2054,10 @@ int tls_sw_recvmsg(struct sock *sk, if (err < 0) goto end; + /* process_rx_list() will set @control if it processed any records */ copied = err; - if (len <= copied || (copied && control != TLS_RECORD_TYPE_DATA) || rx_more) + if (len <= copied || rx_more || + (control && control != TLS_RECORD_TYPE_DATA)) goto end; target = sock_rcvlowat(sk, flags & MSG_WAITALL, len); diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index ead6a3c14b87..bebb355f3ffe 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -689,7 +689,8 @@ static int __vsock_bind_connectible(struct vsock_sock *vsk, unsigned int i; for (i = 0; i < MAX_PORT_RETRIES; i++) { - if (port <= LAST_RESERVED_PORT) + if (port == VMADDR_PORT_ANY || + port <= LAST_RESERVED_PORT) port = LAST_RESERVED_PORT + 1; new_addr.svm_port = port++; diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c index d2819baea414..c7a1f080d2de 100644 --- a/net/xfrm/xfrm_device.c +++ b/net/xfrm/xfrm_device.c @@ -155,7 +155,8 @@ struct sk_buff *validate_xmit_xfrm(struct sk_buff *skb, netdev_features_t featur return skb; } - if (skb_is_gso(skb) && unlikely(xmit_xfrm_check_overflow(skb))) { + if (skb_is_gso(skb) && (unlikely(x->xso.dev != dev) || + unlikely(xmit_xfrm_check_overflow(skb)))) { struct sk_buff *segs; /* Packet got rerouted, fixup features and segment it. */ @@ -415,10 +416,12 @@ bool xfrm_dev_offload_ok(struct sk_buff *skb, struct xfrm_state *x) struct net_device *dev = x->xso.dev; bool check_tunnel_size; - if (x->xso.type == XFRM_DEV_OFFLOAD_UNSPECIFIED) + if (!x->type_offload || + (x->xso.type == XFRM_DEV_OFFLOAD_UNSPECIFIED && x->encap)) return false; - if ((dev == xfrm_dst_path(dst)->dev) && !xdst->child->xfrm) { + if ((!dev || dev == xfrm_dst_path(dst)->dev) && + !xdst->child->xfrm) { mtu = xfrm_state_mtu(x, xdst->child_mtu_cached); if (skb->len <= mtu) goto ok; @@ -430,6 +433,9 @@ bool xfrm_dev_offload_ok(struct sk_buff *skb, struct xfrm_state *x) return false; ok: + if (!dev) + return true; + check_tunnel_size = x->xso.type == XFRM_DEV_OFFLOAD_PACKET && x->props.mode == XFRM_MODE_TUNNEL; switch (x->props.family) { diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 77db3b5fe4ac..78fcbb89cf32 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -3297,7 +3297,7 @@ void xfrm_state_fini(struct net *net) unsigned int sz; flush_work(&net->xfrm.state_hash_work); - xfrm_state_flush(net, IPSEC_PROTO_ANY, false); + xfrm_state_flush(net, 0, false); flush_work(&xfrm_state_gc_work); WARN_ON(!list_empty(&net->xfrm.state_all)); diff --git a/rust/Makefile b/rust/Makefile index 4263462b8470..bfa915b0e588 100644 --- a/rust/Makefile +++ b/rust/Makefile @@ -65,6 +65,10 @@ core-cfgs = \ core-edition := $(if $(call rustc-min-version,108700),2024,2021) +# `rustdoc` did not save the target modifiers, thus workaround for +# the time being (https://github.com/rust-lang/rust/issues/144521). +rustdoc_modifiers_workaround := $(if $(call rustc-min-version,108800),-Cunsafe-allow-abi-mismatch=fixed-x18) + # `rustc` recognizes `--remap-path-prefix` since 1.26.0, but `rustdoc` only # since Rust 1.81.0. Moreover, `rustdoc` ICEs on out-of-tree builds since Rust # 1.82.0 (https://github.com/rust-lang/rust/issues/138520). Thus workaround both @@ -77,6 +81,7 @@ quiet_cmd_rustdoc = RUSTDOC $(if $(rustdoc_host),H, ) $< -Zunstable-options --generate-link-to-definition \ --output $(rustdoc_output) \ --crate-name $(subst rustdoc-,,$@) \ + $(rustdoc_modifiers_workaround) \ $(if $(rustdoc_host),,--sysroot=/dev/null) \ @$(objtree)/include/generated/rustc_cfg $< @@ -106,14 +111,14 @@ rustdoc: rustdoc-core rustdoc-macros rustdoc-compiler_builtins \ rustdoc-macros: private rustdoc_host = yes rustdoc-macros: private rustc_target_flags = --crate-type proc-macro \ --extern proc_macro -rustdoc-macros: $(src)/macros/lib.rs FORCE +rustdoc-macros: $(src)/macros/lib.rs rustdoc-clean FORCE +$(call if_changed,rustdoc) # Starting with Rust 1.82.0, skipping `-Wrustdoc::unescaped_backticks` should # not be needed -- see https://github.com/rust-lang/rust/pull/128307. rustdoc-core: private skip_flags = --edition=2021 -Wrustdoc::unescaped_backticks rustdoc-core: private rustc_target_flags = --edition=$(core-edition) $(core-cfgs) -rustdoc-core: $(RUST_LIB_SRC)/core/src/lib.rs FORCE +rustdoc-core: $(RUST_LIB_SRC)/core/src/lib.rs rustdoc-clean FORCE +$(call if_changed,rustdoc) rustdoc-compiler_builtins: $(src)/compiler_builtins.rs rustdoc-core FORCE @@ -125,7 +130,8 @@ rustdoc-ffi: $(src)/ffi.rs rustdoc-core FORCE rustdoc-pin_init_internal: private rustdoc_host = yes rustdoc-pin_init_internal: private rustc_target_flags = --cfg kernel \ --extern proc_macro --crate-type proc-macro -rustdoc-pin_init_internal: $(src)/pin-init/internal/src/lib.rs FORCE +rustdoc-pin_init_internal: $(src)/pin-init/internal/src/lib.rs \ + rustdoc-clean FORCE +$(call if_changed,rustdoc) rustdoc-pin_init: private rustdoc_host = yes @@ -143,6 +149,9 @@ rustdoc-kernel: $(src)/kernel/lib.rs rustdoc-core rustdoc-ffi rustdoc-macros \ $(obj)/bindings.o FORCE +$(call if_changed,rustdoc) +rustdoc-clean: FORCE + $(Q)rm -rf $(rustdoc_output) + quiet_cmd_rustc_test_library = $(RUSTC_OR_CLIPPY_QUIET) TL $< cmd_rustc_test_library = \ OBJTREE=$(abspath $(objtree)) \ @@ -215,6 +224,7 @@ quiet_cmd_rustdoc_test_kernel = RUSTDOC TK $< --extern bindings --extern uapi \ --no-run --crate-name kernel -Zunstable-options \ --sysroot=/dev/null \ + $(rustdoc_modifiers_workaround) \ --test-builder $(objtree)/scripts/rustdoc_test_builder \ $< $(rustdoc_test_kernel_quiet); \ $(objtree)/scripts/rustdoc_test_gen diff --git a/sound/hda/codecs/realtek/alc269.c b/sound/hda/codecs/realtek/alc269.c index e27a36e4e92a..e90c4047ea62 100644 --- a/sound/hda/codecs/realtek/alc269.c +++ b/sound/hda/codecs/realtek/alc269.c @@ -7140,6 +7140,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1d72, 0x1901, "RedmiBook 14", ALC256_FIXUP_ASUS_HEADSET_MIC), SND_PCI_QUIRK(0x1d72, 0x1945, "Redmi G", ALC256_FIXUP_ASUS_HEADSET_MIC), SND_PCI_QUIRK(0x1d72, 0x1947, "RedmiBook Air", ALC255_FIXUP_XIAOMI_HEADSET_MIC), + SND_PCI_QUIRK(0x1ee7, 0x2078, "HONOR BRB-X M1010", ALC2XX_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x1f66, 0x0105, "Ayaneo Portable Game Player", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x2014, 0x800a, "Positivo ARN50", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), SND_PCI_QUIRK(0x2782, 0x0214, "VAIO VJFE-CL", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), @@ -7158,6 +7159,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0xf111, 0x0001, "Framework Laptop", ALC295_FIXUP_FRAMEWORK_LAPTOP_MIC_NO_PRESENCE), SND_PCI_QUIRK(0xf111, 0x0006, "Framework Laptop", ALC295_FIXUP_FRAMEWORK_LAPTOP_MIC_NO_PRESENCE), SND_PCI_QUIRK(0xf111, 0x0009, "Framework Laptop", ALC295_FIXUP_FRAMEWORK_LAPTOP_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0xf111, 0x000b, "Framework Laptop", ALC295_FIXUP_FRAMEWORK_LAPTOP_MIC_NO_PRESENCE), SND_PCI_QUIRK(0xf111, 0x000c, "Framework Laptop", ALC295_FIXUP_FRAMEWORK_LAPTOP_MIC_NO_PRESENCE), #if 0 diff --git a/sound/hda/codecs/side-codecs/tas2781_hda_i2c.c b/sound/hda/codecs/side-codecs/tas2781_hda_i2c.c index 45ac5e41bd4f..06c7bc2b9e9d 100644 --- a/sound/hda/codecs/side-codecs/tas2781_hda_i2c.c +++ b/sound/hda/codecs/side-codecs/tas2781_hda_i2c.c @@ -265,7 +265,7 @@ static const struct snd_kcontrol_new tas2770_snd_controls[] = { }; static const struct snd_kcontrol_new tas2781_snd_controls[] = { - ACARD_SINGLE_RANGE_EXT_TLV("Speaker Analog Gain", TAS2781_AMP_LEVEL, + ACARD_SINGLE_RANGE_EXT_TLV("Speaker Analog Volume", TAS2781_AMP_LEVEL, 1, 0, 20, 0, tas2781_amp_getvol, tas2781_amp_putvol, amp_vol_tlv), ACARD_SINGLE_BOOL_EXT("Speaker Force Firmware Load", 0, diff --git a/sound/hda/controllers/intel.c b/sound/hda/controllers/intel.c index fcf67e97a546..1bb3ff55b115 100644 --- a/sound/hda/controllers/intel.c +++ b/sound/hda/controllers/intel.c @@ -2077,7 +2077,6 @@ static const struct pci_device_id driver_denylist[] = { { PCI_DEVICE_SUB(0x1022, 0x1487, 0x1043, 0x874f) }, /* ASUS ROG Zenith II / Strix */ { PCI_DEVICE_SUB(0x1022, 0x1487, 0x1462, 0xcb59) }, /* MSI TRX40 Creator */ { PCI_DEVICE_SUB(0x1022, 0x1487, 0x1462, 0xcb60) }, /* MSI TRX40 */ - { PCI_DEVICE_SUB(0x1022, 0x15e3, 0x1022, 0xd601) }, /* ASRock X670E Taichi */ {} }; diff --git a/sound/pci/azt3328.c b/sound/pci/azt3328.c index 4418b9ae33e6..b33344f65b8c 100644 --- a/sound/pci/azt3328.c +++ b/sound/pci/azt3328.c @@ -412,25 +412,25 @@ snd_azf3328_ctrl_outl(const struct snd_azf3328 *chip, unsigned reg, u32 value) outl(value, chip->ctrl_io + reg); } -static inline void +static inline void __maybe_unused snd_azf3328_game_outb(const struct snd_azf3328 *chip, unsigned reg, u8 value) { outb(value, chip->game_io + reg); } -static inline void +static inline void __maybe_unused snd_azf3328_game_outw(const struct snd_azf3328 *chip, unsigned reg, u16 value) { outw(value, chip->game_io + reg); } -static inline u8 +static inline u8 __maybe_unused snd_azf3328_game_inb(const struct snd_azf3328 *chip, unsigned reg) { return inb(chip->game_io + reg); } -static inline u16 +static inline u16 __maybe_unused snd_azf3328_game_inw(const struct snd_azf3328 *chip, unsigned reg) { return inw(chip->game_io + reg); diff --git a/sound/soc/Kconfig b/sound/soc/Kconfig index bf362bfca456..ce74818bd715 100644 --- a/sound/soc/Kconfig +++ b/sound/soc/Kconfig @@ -111,7 +111,6 @@ source "sound/soc/bcm/Kconfig" source "sound/soc/cirrus/Kconfig" source "sound/soc/dwc/Kconfig" source "sound/soc/fsl/Kconfig" -source "sound/soc/generic/Kconfig" source "sound/soc/google/Kconfig" source "sound/soc/hisilicon/Kconfig" source "sound/soc/jz4740/Kconfig" @@ -149,5 +148,8 @@ source "sound/soc/codecs/Kconfig" source "sound/soc/sdw_utils/Kconfig" +# generic frame-work +source "sound/soc/generic/Kconfig" + endif # SND_SOC diff --git a/sound/soc/codecs/aw87390.c b/sound/soc/codecs/aw87390.c index 110009616966..ef6f64856988 100644 --- a/sound/soc/codecs/aw87390.c +++ b/sound/soc/codecs/aw87390.c @@ -177,7 +177,7 @@ static int aw87390_profile_info(struct snd_kcontrol *kcontrol, { struct snd_soc_component *codec = snd_soc_kcontrol_component(kcontrol); struct aw87390 *aw87390 = snd_soc_component_get_drvdata(codec); - char *prof_name, *name; + char *prof_name; int count, ret; uinfo->type = SNDRV_CTL_ELEM_TYPE_ENUMERATED; @@ -194,17 +194,15 @@ static int aw87390_profile_info(struct snd_kcontrol *kcontrol, if (uinfo->value.enumerated.item >= count) uinfo->value.enumerated.item = count - 1; - name = uinfo->value.enumerated.name; count = uinfo->value.enumerated.item; ret = aw87390_dev_get_prof_name(aw87390->aw_pa, count, &prof_name); if (ret) { - strscpy(uinfo->value.enumerated.name, "null", - strlen("null") + 1); + strscpy(uinfo->value.enumerated.name, "null"); return 0; } - strscpy(name, prof_name, sizeof(uinfo->value.enumerated.name)); + strscpy(uinfo->value.enumerated.name, prof_name); return 0; } diff --git a/sound/soc/codecs/aw88081.c b/sound/soc/codecs/aw88081.c index 3dd8428f08cc..d61a7b8c5470 100644 --- a/sound/soc/codecs/aw88081.c +++ b/sound/soc/codecs/aw88081.c @@ -914,12 +914,11 @@ static int aw88081_profile_info(struct snd_kcontrol *kcontrol, ret = aw88081_dev_get_prof_name(aw88081->aw_pa, count, &prof_name); if (ret) { - strscpy(uinfo->value.enumerated.name, "null", - sizeof(uinfo->value.enumerated.name)); + strscpy(uinfo->value.enumerated.name, "null"); return 0; } - strscpy(uinfo->value.enumerated.name, prof_name, sizeof(uinfo->value.enumerated.name)); + strscpy(uinfo->value.enumerated.name, prof_name); return 0; } diff --git a/sound/soc/codecs/aw88166.c b/sound/soc/codecs/aw88166.c index 4f76ebe11cc7..28f62b991ef2 100644 --- a/sound/soc/codecs/aw88166.c +++ b/sound/soc/codecs/aw88166.c @@ -1478,7 +1478,7 @@ static int aw88166_profile_info(struct snd_kcontrol *kcontrol, { struct snd_soc_component *codec = snd_soc_kcontrol_component(kcontrol); struct aw88166 *aw88166 = snd_soc_component_get_drvdata(codec); - char *prof_name, *name; + char *prof_name; int count, ret; uinfo->type = SNDRV_CTL_ELEM_TYPE_ENUMERATED; @@ -1495,17 +1495,15 @@ static int aw88166_profile_info(struct snd_kcontrol *kcontrol, if (uinfo->value.enumerated.item >= count) uinfo->value.enumerated.item = count - 1; - name = uinfo->value.enumerated.name; count = uinfo->value.enumerated.item; ret = aw88166_dev_get_prof_name(aw88166->aw_pa, count, &prof_name); if (ret) { - strscpy(uinfo->value.enumerated.name, "null", - strlen("null") + 1); + strscpy(uinfo->value.enumerated.name, "null"); return 0; } - strscpy(name, prof_name, sizeof(uinfo->value.enumerated.name)); + strscpy(uinfo->value.enumerated.name, prof_name); return 0; } diff --git a/sound/soc/codecs/aw88261.c b/sound/soc/codecs/aw88261.c index fb99871578c5..de11ae8dd9d9 100644 --- a/sound/soc/codecs/aw88261.c +++ b/sound/soc/codecs/aw88261.c @@ -819,7 +819,7 @@ static int aw88261_profile_info(struct snd_kcontrol *kcontrol, { struct snd_soc_component *codec = snd_soc_kcontrol_component(kcontrol); struct aw88261 *aw88261 = snd_soc_component_get_drvdata(codec); - char *prof_name, *name; + char *prof_name; int count, ret; uinfo->type = SNDRV_CTL_ELEM_TYPE_ENUMERATED; @@ -836,17 +836,15 @@ static int aw88261_profile_info(struct snd_kcontrol *kcontrol, if (uinfo->value.enumerated.item >= count) uinfo->value.enumerated.item = count - 1; - name = uinfo->value.enumerated.name; count = uinfo->value.enumerated.item; ret = aw88261_dev_get_prof_name(aw88261->aw_pa, count, &prof_name); if (ret) { - strscpy(uinfo->value.enumerated.name, "null", - strlen("null") + 1); + strscpy(uinfo->value.enumerated.name, "null"); return 0; } - strscpy(name, prof_name, sizeof(uinfo->value.enumerated.name)); + strscpy(uinfo->value.enumerated.name, prof_name); return 0; } diff --git a/sound/soc/codecs/aw88395/aw88395.c b/sound/soc/codecs/aw88395/aw88395.c index aea44a199b98..fb563b4c6971 100644 --- a/sound/soc/codecs/aw88395/aw88395.c +++ b/sound/soc/codecs/aw88395/aw88395.c @@ -175,7 +175,7 @@ static int aw88395_profile_info(struct snd_kcontrol *kcontrol, { struct snd_soc_component *codec = snd_soc_kcontrol_component(kcontrol); struct aw88395 *aw88395 = snd_soc_component_get_drvdata(codec); - char *prof_name, *name; + char *prof_name; int count, ret; uinfo->type = SNDRV_CTL_ELEM_TYPE_ENUMERATED; @@ -192,17 +192,15 @@ static int aw88395_profile_info(struct snd_kcontrol *kcontrol, if (uinfo->value.enumerated.item >= count) uinfo->value.enumerated.item = count - 1; - name = uinfo->value.enumerated.name; count = uinfo->value.enumerated.item; ret = aw88395_dev_get_prof_name(aw88395->aw_pa, count, &prof_name); if (ret) { - strscpy(uinfo->value.enumerated.name, "null", - strlen("null") + 1); + strscpy(uinfo->value.enumerated.name, "null"); return 0; } - strscpy(name, prof_name, sizeof(uinfo->value.enumerated.name)); + strscpy(uinfo->value.enumerated.name, prof_name); return 0; } diff --git a/sound/soc/codecs/aw88399.c b/sound/soc/codecs/aw88399.c index c23e70d64d0c..58846feb013d 100644 --- a/sound/soc/codecs/aw88399.c +++ b/sound/soc/codecs/aw88399.c @@ -1831,7 +1831,7 @@ static int aw88399_profile_info(struct snd_kcontrol *kcontrol, { struct snd_soc_component *codec = snd_soc_kcontrol_component(kcontrol); struct aw88399 *aw88399 = snd_soc_component_get_drvdata(codec); - char *prof_name, *name; + char *prof_name; int count, ret; uinfo->type = SNDRV_CTL_ELEM_TYPE_ENUMERATED; @@ -1848,17 +1848,15 @@ static int aw88399_profile_info(struct snd_kcontrol *kcontrol, if (uinfo->value.enumerated.item >= count) uinfo->value.enumerated.item = count - 1; - name = uinfo->value.enumerated.name; count = uinfo->value.enumerated.item; ret = aw88399_dev_get_prof_name(aw88399->aw_pa, count, &prof_name); if (ret) { - strscpy(uinfo->value.enumerated.name, "null", - strlen("null") + 1); + strscpy(uinfo->value.enumerated.name, "null"); return 0; } - strscpy(name, prof_name, sizeof(uinfo->value.enumerated.name)); + strscpy(uinfo->value.enumerated.name, prof_name); return 0; } diff --git a/sound/soc/codecs/lpass-tx-macro.c b/sound/soc/codecs/lpass-tx-macro.c index 40d79bee4584..1da34cb3505f 100644 --- a/sound/soc/codecs/lpass-tx-macro.c +++ b/sound/soc/codecs/lpass-tx-macro.c @@ -2229,7 +2229,7 @@ static int tx_macro_register_mclk_output(struct tx_macro *tx) } static const struct snd_soc_component_driver tx_macro_component_drv = { - .name = "RX-MACRO", + .name = "TX-MACRO", .probe = tx_macro_component_probe, .controls = tx_macro_snd_controls, .num_controls = ARRAY_SIZE(tx_macro_snd_controls), diff --git a/sound/soc/codecs/rt1320-sdw.c b/sound/soc/codecs/rt1320-sdw.c index b13d7a99bf63..dcddc28e8856 100644 --- a/sound/soc/codecs/rt1320-sdw.c +++ b/sound/soc/codecs/rt1320-sdw.c @@ -109,6 +109,7 @@ static const struct reg_sequence rt1320_blind_write[] = { { 0x0000d540, 0x01 }, { 0xd172, 0x2a }, { 0xc5d6, 0x01 }, + { 0xd478, 0xff }, }; static const struct reg_sequence rt1320_vc_blind_write[] = { @@ -159,7 +160,7 @@ static const struct reg_sequence rt1320_vc_blind_write[] = { { 0xd471, 0x3a }, { 0xd474, 0x11 }, { 0xd475, 0x32 }, - { 0xd478, 0x64 }, + { 0xd478, 0xff }, { 0xd479, 0x20 }, { 0xd47a, 0x10 }, { 0xd47c, 0xff }, diff --git a/sound/soc/codecs/rt721-sdca.c b/sound/soc/codecs/rt721-sdca.c index f6f7c2ffde1c..a4bd29d7220b 100644 --- a/sound/soc/codecs/rt721-sdca.c +++ b/sound/soc/codecs/rt721-sdca.c @@ -278,6 +278,8 @@ static void rt721_sdca_jack_preset(struct rt721_sdca_priv *rt721) RT721_ENT_FLOAT_CTL1, 0x4040); rt_sdca_index_write(rt721->mbq_regmap, RT721_HDA_SDCA_FLOAT, RT721_ENT_FLOAT_CTL4, 0x1201); + rt_sdca_index_write(rt721->mbq_regmap, RT721_BOOST_CTRL, + RT721_BST_4CH_TOP_GATING_CTRL1, 0x002a); regmap_write(rt721->regmap, 0x2f58, 0x07); } diff --git a/sound/soc/codecs/rt721-sdca.h b/sound/soc/codecs/rt721-sdca.h index 0a82c107b19a..71fac9cd8739 100644 --- a/sound/soc/codecs/rt721-sdca.h +++ b/sound/soc/codecs/rt721-sdca.h @@ -56,6 +56,7 @@ struct rt721_sdca_dmic_kctrl_priv { #define RT721_CBJ_CTRL 0x0a #define RT721_CAP_PORT_CTRL 0x0c #define RT721_CLASD_AMP_CTRL 0x0d +#define RT721_BOOST_CTRL 0x0f #define RT721_VENDOR_REG 0x20 #define RT721_RC_CALIB_CTRL 0x40 #define RT721_VENDOR_EQ_L 0x53 @@ -93,6 +94,9 @@ struct rt721_sdca_dmic_kctrl_priv { /* Index (NID:0dh) */ #define RT721_CLASD_AMP_2CH_CAL 0x14 +/* Index (NID:0fh) */ +#define RT721_BST_4CH_TOP_GATING_CTRL1 0x05 + /* Index (NID:20h) */ #define RT721_JD_PRODUCT_NUM 0x00 #define RT721_ANALOG_BIAS_CTL3 0x04 diff --git a/sound/soc/codecs/sma1307.c b/sound/soc/codecs/sma1307.c index b3d401ada176..6a601e7134ea 100644 --- a/sound/soc/codecs/sma1307.c +++ b/sound/soc/codecs/sma1307.c @@ -1749,7 +1749,7 @@ static void sma1307_setting_loaded(struct sma1307_priv *sma1307, const char *fil sma1307->set.header_size * sizeof(int)); if ((sma1307->set.checksum >> 8) != SMA1307_SETTING_CHECKSUM) { - dev_err(sma1307->dev, "%s: failed by dismatch \"%s\"\n", + dev_err(sma1307->dev, "%s: checksum failed \"%s\"\n", __func__, setting_file); sma1307->set.status = false; return; diff --git a/sound/soc/codecs/tas2781-i2c.c b/sound/soc/codecs/tas2781-i2c.c index 9f4d965a1335..676130f4cf3e 100644 --- a/sound/soc/codecs/tas2781-i2c.c +++ b/sound/soc/codecs/tas2781-i2c.c @@ -908,10 +908,10 @@ static const struct snd_kcontrol_new tasdevice_cali_controls[] = { }; static const struct snd_kcontrol_new tas2781_snd_controls[] = { - SOC_SINGLE_RANGE_EXT_TLV("Speaker Analog Gain", TAS2781_AMP_LEVEL, + SOC_SINGLE_RANGE_EXT_TLV("Speaker Analog Volume", TAS2781_AMP_LEVEL, 1, 0, 20, 0, tas2781_amp_getvol, tas2781_amp_putvol, amp_vol_tlv), - SOC_SINGLE_RANGE_EXT_TLV("Speaker Digital Gain", TAS2781_DVC_LVL, + SOC_SINGLE_RANGE_EXT_TLV("Speaker Digital Volume", TAS2781_DVC_LVL, 0, 0, 200, 1, tas2781_digital_getvol, tas2781_digital_putvol, dvc_tlv), }; @@ -1480,7 +1480,7 @@ static ssize_t acoustic_ctl_write(struct file *file, return PTR_ERR(src); if (src[0] > max_pkg_len && src[0] != count) { - dev_err(priv->dev, "pkg(%u), max(%u), count(%u) dismatch.\n", + dev_err(priv->dev, "pkg(%u), max(%u), count(%u) mismatch.\n", src[0], max_pkg_len, (unsigned int)count); ret = 0; goto exit; diff --git a/sound/soc/fsl/fsl_sai.c b/sound/soc/fsl/fsl_sai.c index c313b654236c..d0367b21f775 100644 --- a/sound/soc/fsl/fsl_sai.c +++ b/sound/soc/fsl/fsl_sai.c @@ -809,9 +809,9 @@ static void fsl_sai_config_disable(struct fsl_sai *sai, int dir) * are running concurrently. */ /* Software Reset */ - regmap_write(sai->regmap, FSL_SAI_xCSR(tx, ofs), FSL_SAI_CSR_SR); + regmap_update_bits(sai->regmap, FSL_SAI_xCSR(tx, ofs), FSL_SAI_CSR_SR, FSL_SAI_CSR_SR); /* Clear SR bit to finish the reset */ - regmap_write(sai->regmap, FSL_SAI_xCSR(tx, ofs), 0); + regmap_update_bits(sai->regmap, FSL_SAI_xCSR(tx, ofs), FSL_SAI_CSR_SR, 0); } static int fsl_sai_trigger(struct snd_pcm_substream *substream, int cmd, @@ -930,11 +930,11 @@ static int fsl_sai_dai_probe(struct snd_soc_dai *cpu_dai) unsigned int ofs = sai->soc_data->reg_offset; /* Software Reset for both Tx and Rx */ - regmap_write(sai->regmap, FSL_SAI_TCSR(ofs), FSL_SAI_CSR_SR); - regmap_write(sai->regmap, FSL_SAI_RCSR(ofs), FSL_SAI_CSR_SR); + regmap_update_bits(sai->regmap, FSL_SAI_TCSR(ofs), FSL_SAI_CSR_SR, FSL_SAI_CSR_SR); + regmap_update_bits(sai->regmap, FSL_SAI_RCSR(ofs), FSL_SAI_CSR_SR, FSL_SAI_CSR_SR); /* Clear SR bit to finish the reset */ - regmap_write(sai->regmap, FSL_SAI_TCSR(ofs), 0); - regmap_write(sai->regmap, FSL_SAI_RCSR(ofs), 0); + regmap_update_bits(sai->regmap, FSL_SAI_TCSR(ofs), FSL_SAI_CSR_SR, 0); + regmap_update_bits(sai->regmap, FSL_SAI_RCSR(ofs), FSL_SAI_CSR_SR, 0); regmap_update_bits(sai->regmap, FSL_SAI_TCR1(ofs), FSL_SAI_CR1_RFW_MASK(sai->soc_data->fifo_depth), @@ -1824,11 +1824,11 @@ static int fsl_sai_runtime_resume(struct device *dev) regcache_cache_only(sai->regmap, false); regcache_mark_dirty(sai->regmap); - regmap_write(sai->regmap, FSL_SAI_TCSR(ofs), FSL_SAI_CSR_SR); - regmap_write(sai->regmap, FSL_SAI_RCSR(ofs), FSL_SAI_CSR_SR); + regmap_update_bits(sai->regmap, FSL_SAI_TCSR(ofs), FSL_SAI_CSR_SR, FSL_SAI_CSR_SR); + regmap_update_bits(sai->regmap, FSL_SAI_RCSR(ofs), FSL_SAI_CSR_SR, FSL_SAI_CSR_SR); usleep_range(1000, 2000); - regmap_write(sai->regmap, FSL_SAI_TCSR(ofs), 0); - regmap_write(sai->regmap, FSL_SAI_RCSR(ofs), 0); + regmap_update_bits(sai->regmap, FSL_SAI_TCSR(ofs), FSL_SAI_CSR_SR, 0); + regmap_update_bits(sai->regmap, FSL_SAI_RCSR(ofs), FSL_SAI_CSR_SR, 0); ret = regcache_sync(sai->regmap); if (ret) diff --git a/sound/soc/stm/stm32_i2s.c b/sound/soc/stm/stm32_i2s.c index 0e489097d9c1..6ca21780f21d 100644 --- a/sound/soc/stm/stm32_i2s.c +++ b/sound/soc/stm/stm32_i2s.c @@ -469,11 +469,8 @@ static int stm32_i2smclk_determine_rate(struct clk_hw *hw, int ret; ret = stm32_i2s_calc_clk_div(i2s, req->best_parent_rate, req->rate); - if (ret) { - req->rate = ret; - - return 0; - } + if (ret) + return ret; mclk->freq = req->best_parent_rate / i2s->divider; diff --git a/sound/usb/stream.c b/sound/usb/stream.c index ad6ced780634..acf3dc2d79e0 100644 --- a/sound/usb/stream.c +++ b/sound/usb/stream.c @@ -341,20 +341,28 @@ snd_pcm_chmap_elem *convert_chmap_v3(struct uac3_cluster_header_descriptor len = le16_to_cpu(cluster->wLength); c = 0; - p += sizeof(struct uac3_cluster_header_descriptor); + p += sizeof(*cluster); + len -= sizeof(*cluster); - while (((p - (void *)cluster) < len) && (c < channels)) { + while (len > 0 && (c < channels)) { struct uac3_cluster_segment_descriptor *cs_desc = p; u16 cs_len; u8 cs_type; + if (len < sizeof(*p)) + break; cs_len = le16_to_cpu(cs_desc->wLength); + if (len < cs_len) + break; cs_type = cs_desc->bSegmentType; if (cs_type == UAC3_CHANNEL_INFORMATION) { struct uac3_cluster_information_segment_descriptor *is = p; unsigned char map; + if (cs_len < sizeof(*is)) + break; + /* * TODO: this conversion is not complete, update it * after adding UAC3 values to asound.h @@ -456,6 +464,7 @@ snd_pcm_chmap_elem *convert_chmap_v3(struct uac3_cluster_header_descriptor chmap->map[c++] = map; } p += cs_len; + len -= cs_len; } if (channels < c) @@ -881,7 +890,7 @@ snd_usb_get_audioformat_uac3(struct snd_usb_audio *chip, u64 badd_formats = 0; unsigned int num_channels; struct audioformat *fp; - u16 cluster_id, wLength; + u16 cluster_id, wLength, cluster_wLength; int clock = 0; int err; @@ -1011,6 +1020,16 @@ snd_usb_get_audioformat_uac3(struct snd_usb_audio *chip, return ERR_PTR(-EIO); } + cluster_wLength = le16_to_cpu(cluster->wLength); + if (cluster_wLength < sizeof(*cluster) || + cluster_wLength > wLength) { + dev_err(&dev->dev, + "%u:%d : invalid Cluster Descriptor size\n", + iface_no, altno); + kfree(cluster); + return ERR_PTR(-EIO); + } + num_channels = cluster->bNrChannels; chmap = convert_chmap_v3(cluster); kfree(cluster); diff --git a/sound/usb/validate.c b/sound/usb/validate.c index 6fe206f6e911..4f4e8e87a14c 100644 --- a/sound/usb/validate.c +++ b/sound/usb/validate.c @@ -221,6 +221,17 @@ static bool validate_uac3_feature_unit(const void *p, return d->bLength >= sizeof(*d) + 4 + 2; } +static bool validate_uac3_power_domain_unit(const void *p, + const struct usb_desc_validator *v) +{ + const struct uac3_power_domain_descriptor *d = p; + + if (d->bLength < sizeof(*d)) + return false; + /* baEntities[] + wPDomainDescrStr */ + return d->bLength >= sizeof(*d) + d->bNrEntities + 2; +} + static bool validate_midi_out_jack(const void *p, const struct usb_desc_validator *v) { @@ -285,6 +296,7 @@ static const struct usb_desc_validator audio_validators[] = { struct uac3_clock_multiplier_descriptor), /* UAC_VERSION_3, UAC3_SAMPLE_RATE_CONVERTER: not implemented yet */ /* UAC_VERSION_3, UAC3_CONNECTORS: not implemented yet */ + FUNC(UAC_VERSION_3, UAC3_POWER_DOMAIN, validate_uac3_power_domain_unit), { } /* terminator */ }; diff --git a/tools/bootconfig/main.c b/tools/bootconfig/main.c index 57c669d2aa90..55d59ed507d5 100644 --- a/tools/bootconfig/main.c +++ b/tools/bootconfig/main.c @@ -193,7 +193,7 @@ static int load_xbc_from_initrd(int fd, char **buf) if (stat.st_size < BOOTCONFIG_FOOTER_SIZE) return 0; - if (lseek(fd, -BOOTCONFIG_MAGIC_LEN, SEEK_END) < 0) + if (lseek(fd, -(off_t)BOOTCONFIG_MAGIC_LEN, SEEK_END) < 0) return pr_errno("Failed to lseek for magic", -errno); if (read(fd, magic, BOOTCONFIG_MAGIC_LEN) < 0) @@ -203,7 +203,7 @@ static int load_xbc_from_initrd(int fd, char **buf) if (memcmp(magic, BOOTCONFIG_MAGIC, BOOTCONFIG_MAGIC_LEN) != 0) return 0; - if (lseek(fd, -BOOTCONFIG_FOOTER_SIZE, SEEK_END) < 0) + if (lseek(fd, -(off_t)BOOTCONFIG_FOOTER_SIZE, SEEK_END) < 0) return pr_errno("Failed to lseek for size", -errno); if (read(fd, &size, sizeof(uint32_t)) < 0) diff --git a/tools/objtool/arch/loongarch/special.c b/tools/objtool/arch/loongarch/special.c index e39f86d97002..a80b75f7b061 100644 --- a/tools/objtool/arch/loongarch/special.c +++ b/tools/objtool/arch/loongarch/special.c @@ -27,6 +27,7 @@ static void get_rodata_table_size_by_table_annotate(struct objtool_file *file, struct table_info *next_table; unsigned long tmp_insn_offset; unsigned long tmp_rodata_offset; + bool is_valid_list = false; rsec = find_section_by_name(file->elf, ".rela.discard.tablejump_annotate"); if (!rsec) @@ -35,6 +36,12 @@ static void get_rodata_table_size_by_table_annotate(struct objtool_file *file, INIT_LIST_HEAD(&table_list); for_each_reloc(rsec, reloc) { + if (reloc->sym->sec->rodata) + continue; + + if (strcmp(insn->sec->name, reloc->sym->sec->name)) + continue; + orig_table = malloc(sizeof(struct table_info)); if (!orig_table) { WARN("malloc failed"); @@ -49,6 +56,22 @@ static void get_rodata_table_size_by_table_annotate(struct objtool_file *file, if (reloc_idx(reloc) + 1 == sec_num_entries(rsec)) break; + + if (strcmp(insn->sec->name, (reloc + 1)->sym->sec->name)) { + list_for_each_entry(orig_table, &table_list, jump_info) { + if (orig_table->insn_offset == insn->offset) { + is_valid_list = true; + break; + } + } + + if (!is_valid_list) { + list_del_init(&table_list); + continue; + } + + break; + } } list_for_each_entry(orig_table, &table_list, jump_info) { diff --git a/tools/power/cpupower/man/cpupower-set.1 b/tools/power/cpupower/man/cpupower-set.1 index 500653ef98c7..8ac82b6f9189 100644 --- a/tools/power/cpupower/man/cpupower-set.1 +++ b/tools/power/cpupower/man/cpupower-set.1 @@ -81,10 +81,11 @@ Refer to the AMD P-State kernel documentation for further information. .RE .PP -\-\-turbo\-boost, \-t +\-\-turbo\-boost, \-\-boost, \-t .RS 4 -This option is used to enable or disable the turbo boost feature on -supported Intel and AMD processors. +This option is used to enable or disable the boost feature on +supported Intel and AMD processors, and other boost supported systems. +(The --boost option is an alias for the --turbo-boost option) This option takes as parameter either \fB1\fP to enable, or \fB0\fP to disable the feature. diff --git a/tools/power/cpupower/utils/cpufreq-info.c b/tools/power/cpupower/utils/cpufreq-info.c index fc750e127404..7d3732f5f2f6 100644 --- a/tools/power/cpupower/utils/cpufreq-info.c +++ b/tools/power/cpupower/utils/cpufreq-info.c @@ -128,7 +128,7 @@ static int get_boost_mode_x86(unsigned int cpu) /* ToDo: Make this more global */ unsigned long pstates[MAX_HW_PSTATES] = {0,}; - ret = cpufreq_has_boost_support(cpu, &support, &active, &b_states); + ret = cpufreq_has_x86_boost_support(cpu, &support, &active, &b_states); if (ret) { printf(_("Error while evaluating Boost Capabilities" " on CPU %d -- are you root?\n"), cpu); @@ -204,6 +204,18 @@ static int get_boost_mode_x86(unsigned int cpu) return 0; } +static int get_boost_mode_generic(unsigned int cpu) +{ + bool active; + + if (!cpufreq_has_generic_boost_support(&active)) { + printf(_(" boost state support:\n")); + printf(_(" Active: %s\n"), active ? _("yes") : _("no")); + } + + return 0; +} + /* --boost / -b */ static int get_boost_mode(unsigned int cpu) @@ -214,6 +226,8 @@ static int get_boost_mode(unsigned int cpu) cpupower_cpu_info.vendor == X86_VENDOR_HYGON || cpupower_cpu_info.vendor == X86_VENDOR_INTEL) return get_boost_mode_x86(cpu); + else + get_boost_mode_generic(cpu); freqs = cpufreq_get_boost_frequencies(cpu); if (freqs) { diff --git a/tools/power/cpupower/utils/cpupower-set.c b/tools/power/cpupower/utils/cpupower-set.c index 0677b58374ab..c2117e5650dd 100644 --- a/tools/power/cpupower/utils/cpupower-set.c +++ b/tools/power/cpupower/utils/cpupower-set.c @@ -21,6 +21,7 @@ static struct option set_opts[] = { {"epp", required_argument, NULL, 'e'}, {"amd-pstate-mode", required_argument, NULL, 'm'}, {"turbo-boost", required_argument, NULL, 't'}, + {"boost", required_argument, NULL, 't'}, { }, }; @@ -62,8 +63,8 @@ int cmd_set(int argc, char **argv) params.params = 0; /* parameter parsing */ - while ((ret = getopt_long(argc, argv, "b:e:m:", - set_opts, NULL)) != -1) { + while ((ret = getopt_long(argc, argv, "b:e:m:t:", + set_opts, NULL)) != -1) { switch (ret) { case 'b': if (params.perf_bias) diff --git a/tools/power/cpupower/utils/helpers/helpers.h b/tools/power/cpupower/utils/helpers/helpers.h index 95749b8ee475..82ea62bdf5a2 100644 --- a/tools/power/cpupower/utils/helpers/helpers.h +++ b/tools/power/cpupower/utils/helpers/helpers.h @@ -103,6 +103,9 @@ extern struct cpupower_cpu_info cpupower_cpu_info; /* cpuid and cpuinfo helpers **************************/ +int cpufreq_has_generic_boost_support(bool *active); +int cpupower_set_turbo_boost(int turbo_boost); + /* X86 ONLY ****************************************/ #if defined(__i386__) || defined(__x86_64__) @@ -118,7 +121,6 @@ extern unsigned long long msr_intel_get_turbo_ratio(unsigned int cpu); extern int cpupower_set_epp(unsigned int cpu, char *epp); extern int cpupower_set_amd_pstate_mode(char *mode); -extern int cpupower_set_turbo_boost(int turbo_boost); /* Read/Write msr ****************************/ @@ -139,8 +141,8 @@ extern int decode_pstates(unsigned int cpu, int boost_states, /* AMD HW pstate decoding **************************/ -extern int cpufreq_has_boost_support(unsigned int cpu, int *support, - int *active, int * states); +int cpufreq_has_x86_boost_support(unsigned int cpu, int *support, + int *active, int *states); /* AMD P-State stuff **************************/ bool cpupower_amd_pstate_enabled(void); @@ -181,13 +183,11 @@ static inline int cpupower_set_epp(unsigned int cpu, char *epp) { return -1; }; static inline int cpupower_set_amd_pstate_mode(char *mode) { return -1; }; -static inline int cpupower_set_turbo_boost(int turbo_boost) -{ return -1; }; /* Read/Write msr ****************************/ -static inline int cpufreq_has_boost_support(unsigned int cpu, int *support, - int *active, int * states) +static inline int cpufreq_has_x86_boost_support(unsigned int cpu, int *support, + int *active, int *states) { return -1; } static inline bool cpupower_amd_pstate_enabled(void) diff --git a/tools/power/cpupower/utils/helpers/misc.c b/tools/power/cpupower/utils/helpers/misc.c index 76e461ff4f74..166dc1e470ea 100644 --- a/tools/power/cpupower/utils/helpers/misc.c +++ b/tools/power/cpupower/utils/helpers/misc.c @@ -8,15 +8,14 @@ #include "helpers/helpers.h" #include "helpers/sysfs.h" #include "cpufreq.h" +#include "cpupower_intern.h" #if defined(__i386__) || defined(__x86_64__) -#include "cpupower_intern.h" - #define MSR_AMD_HWCR 0xc0010015 -int cpufreq_has_boost_support(unsigned int cpu, int *support, int *active, - int *states) +int cpufreq_has_x86_boost_support(unsigned int cpu, int *support, int *active, + int *states) { int ret; unsigned long long val; @@ -124,24 +123,6 @@ int cpupower_set_amd_pstate_mode(char *mode) return 0; } -int cpupower_set_turbo_boost(int turbo_boost) -{ - char path[SYSFS_PATH_MAX]; - char linebuf[2] = {}; - - snprintf(path, sizeof(path), PATH_TO_CPU "cpufreq/boost"); - - if (!is_valid_path(path)) - return -1; - - snprintf(linebuf, sizeof(linebuf), "%d", turbo_boost); - - if (cpupower_write_sysfs(path, linebuf, 2) <= 0) - return -1; - - return 0; -} - bool cpupower_amd_pstate_enabled(void) { char *driver = cpufreq_get_driver(0); @@ -160,6 +141,39 @@ bool cpupower_amd_pstate_enabled(void) #endif /* #if defined(__i386__) || defined(__x86_64__) */ +int cpufreq_has_generic_boost_support(bool *active) +{ + char path[SYSFS_PATH_MAX]; + char linebuf[2] = {}; + unsigned long val; + char *endp; + + snprintf(path, sizeof(path), PATH_TO_CPU "cpufreq/boost"); + + if (!is_valid_path(path)) + return -EACCES; + + if (cpupower_read_sysfs(path, linebuf, 2) <= 0) + return -EINVAL; + + val = strtoul(linebuf, &endp, 0); + if (endp == linebuf || errno == ERANGE) + return -EINVAL; + + switch (val) { + case 0: + *active = false; + break; + case 1: + *active = true; + break; + default: + return -EINVAL; + } + + return 0; +} + /* get_cpustate * * Gather the information of all online CPUs into bitmask struct @@ -259,3 +273,21 @@ void print_speed(unsigned long speed, int no_rounding) } } } + +int cpupower_set_turbo_boost(int turbo_boost) +{ + char path[SYSFS_PATH_MAX]; + char linebuf[2] = {}; + + snprintf(path, sizeof(path), PATH_TO_CPU "cpufreq/boost"); + + if (!is_valid_path(path)) + return -1; + + snprintf(linebuf, sizeof(linebuf), "%d", turbo_boost); + + if (cpupower_write_sysfs(path, linebuf, 2) <= 0) + return -1; + + return 0; +} diff --git a/tools/power/x86/turbostat/turbostat.8 b/tools/power/x86/turbostat/turbostat.8 index fb11108aaf42..3340def58d01 100644 --- a/tools/power/x86/turbostat/turbostat.8 +++ b/tools/power/x86/turbostat/turbostat.8 @@ -47,10 +47,11 @@ name as necessary to disambiguate it from others is necessary. Note that option MSRs are read as 64-bits, u32 truncates the displayed value to 32-bits. default: u64 - format: {\fBraw\fP | \fBdelta\fP | \fBpercent\fP} + format: {\fBraw\fP | \fBdelta\fP | \fBpercent\fP | \fBaverage\fP} 'raw' shows the MSR contents in hex. 'delta' shows the difference in values during the measurement interval. 'percent' shows the delta as a percentage of the cycles elapsed. + 'average' similar to raw, but also averaged for node/package summaries (or when using -S). default: delta name: "name_string" @@ -186,6 +187,14 @@ The system configuration dump (if --quiet is not used) is followed by statistics .PP \fBSAMAMHz\fP Instantaneous snapshot of what sysfs presents at the end of the measurement interval. From /sys/class/drm/card0/gt/gt1/rps_act_freq_mhz or /sys/class/drm/card0/device/tile0/gtN/freq0/act_freq depending on the graphics driver being used. .PP +\fBTotl%C0\fP Weighted percentage of time that CPUs are busy. If N CPUs are busy during an interval, the percentage is N * 100%. +.PP +\fBAny%C0\fP Percentage of time that at least one CPU is busy. +.PP +\fBGFX%C0\fP Percentage of time that at least one GFX compute engine is busy. +.PP +\fBCPUGFX%\fP Percentage of time that at least one CPU is busy at the same time as at least one Graphics compute enginer is busy. +.PP \fBPkg%pc2, Pkg%pc3, Pkg%pc6, Pkg%pc7\fP percentage residency in hardware package idle states. These numbers are from hardware residency counters. .PP \fBPkgWatt\fP Watts consumed by the whole package. diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c index 5230e072e414..72a280e7a9d5 100644 --- a/tools/power/x86/turbostat/turbostat.c +++ b/tools/power/x86/turbostat/turbostat.c @@ -67,6 +67,7 @@ #include <stdbool.h> #include <assert.h> #include <linux/kernel.h> +#include <limits.h> #define UNUSED(x) (void)(x) @@ -194,6 +195,7 @@ struct msr_counter bic[] = { { 0x0, "APIC", NULL, 0, 0, 0, NULL, 0 }, { 0x0, "X2APIC", NULL, 0, 0, 0, NULL, 0 }, { 0x0, "Die", NULL, 0, 0, 0, NULL, 0 }, + { 0x0, "L3", NULL, 0, 0, 0, NULL, 0 }, { 0x0, "GFXAMHz", NULL, 0, 0, 0, NULL, 0 }, { 0x0, "IPC", NULL, 0, 0, 0, NULL, 0 }, { 0x0, "CoreThr", NULL, 0, 0, 0, NULL, 0 }, @@ -209,91 +211,238 @@ struct msr_counter bic[] = { { 0x0, "pct_idle", NULL, 0, 0, 0, NULL, 0 }, }; -#define MAX_BIC (sizeof(bic) / sizeof(struct msr_counter)) -#define BIC_USEC (1ULL << 0) -#define BIC_TOD (1ULL << 1) -#define BIC_Package (1ULL << 2) -#define BIC_Node (1ULL << 3) -#define BIC_Avg_MHz (1ULL << 4) -#define BIC_Busy (1ULL << 5) -#define BIC_Bzy_MHz (1ULL << 6) -#define BIC_TSC_MHz (1ULL << 7) -#define BIC_IRQ (1ULL << 8) -#define BIC_SMI (1ULL << 9) -#define BIC_cpuidle (1ULL << 10) -#define BIC_CPU_c1 (1ULL << 11) -#define BIC_CPU_c3 (1ULL << 12) -#define BIC_CPU_c6 (1ULL << 13) -#define BIC_CPU_c7 (1ULL << 14) -#define BIC_ThreadC (1ULL << 15) -#define BIC_CoreTmp (1ULL << 16) -#define BIC_CoreCnt (1ULL << 17) -#define BIC_PkgTmp (1ULL << 18) -#define BIC_GFX_rc6 (1ULL << 19) -#define BIC_GFXMHz (1ULL << 20) -#define BIC_Pkgpc2 (1ULL << 21) -#define BIC_Pkgpc3 (1ULL << 22) -#define BIC_Pkgpc6 (1ULL << 23) -#define BIC_Pkgpc7 (1ULL << 24) -#define BIC_Pkgpc8 (1ULL << 25) -#define BIC_Pkgpc9 (1ULL << 26) -#define BIC_Pkgpc10 (1ULL << 27) -#define BIC_CPU_LPI (1ULL << 28) -#define BIC_SYS_LPI (1ULL << 29) -#define BIC_PkgWatt (1ULL << 30) -#define BIC_CorWatt (1ULL << 31) -#define BIC_GFXWatt (1ULL << 32) -#define BIC_PkgCnt (1ULL << 33) -#define BIC_RAMWatt (1ULL << 34) -#define BIC_PKG__ (1ULL << 35) -#define BIC_RAM__ (1ULL << 36) -#define BIC_Pkg_J (1ULL << 37) -#define BIC_Cor_J (1ULL << 38) -#define BIC_GFX_J (1ULL << 39) -#define BIC_RAM_J (1ULL << 40) -#define BIC_Mod_c6 (1ULL << 41) -#define BIC_Totl_c0 (1ULL << 42) -#define BIC_Any_c0 (1ULL << 43) -#define BIC_GFX_c0 (1ULL << 44) -#define BIC_CPUGFX (1ULL << 45) -#define BIC_Core (1ULL << 46) -#define BIC_CPU (1ULL << 47) -#define BIC_APIC (1ULL << 48) -#define BIC_X2APIC (1ULL << 49) -#define BIC_Die (1ULL << 50) -#define BIC_GFXACTMHz (1ULL << 51) -#define BIC_IPC (1ULL << 52) -#define BIC_CORE_THROT_CNT (1ULL << 53) -#define BIC_UNCORE_MHZ (1ULL << 54) -#define BIC_SAM_mc6 (1ULL << 55) -#define BIC_SAMMHz (1ULL << 56) -#define BIC_SAMACTMHz (1ULL << 57) -#define BIC_Diec6 (1ULL << 58) -#define BIC_SysWatt (1ULL << 59) -#define BIC_Sys_J (1ULL << 60) -#define BIC_NMI (1ULL << 61) -#define BIC_CPU_c1e (1ULL << 62) -#define BIC_pct_idle (1ULL << 63) - -#define BIC_GROUP_TOPOLOGY (BIC_Package | BIC_Node | BIC_CoreCnt | BIC_PkgCnt | BIC_Core | BIC_CPU | BIC_Die) -#define BIC_GROUP_THERMAL_PWR (BIC_CoreTmp | BIC_PkgTmp | BIC_PkgWatt | BIC_CorWatt | BIC_GFXWatt | BIC_RAMWatt | BIC_PKG__ | BIC_RAM__ | BIC_SysWatt) -#define BIC_GROUP_FREQUENCY (BIC_Avg_MHz | BIC_Busy | BIC_Bzy_MHz | BIC_TSC_MHz | BIC_GFXMHz | BIC_GFXACTMHz | BIC_SAMMHz | BIC_SAMACTMHz | BIC_UNCORE_MHZ) -#define BIC_GROUP_HW_IDLE (BIC_Busy | BIC_CPU_c1 | BIC_CPU_c3 | BIC_CPU_c6 | BIC_CPU_c7 | BIC_GFX_rc6 | BIC_Pkgpc2 | BIC_Pkgpc3 | BIC_Pkgpc6 | BIC_Pkgpc7 | BIC_Pkgpc8 | BIC_Pkgpc9 | BIC_Pkgpc10 | BIC_CPU_LPI | BIC_SYS_LPI | BIC_Mod_c6 | BIC_Totl_c0 | BIC_Any_c0 | BIC_GFX_c0 | BIC_CPUGFX | BIC_SAM_mc6 | BIC_Diec6) -#define BIC_GROUP_SW_IDLE (BIC_Busy | BIC_cpuidle | BIC_pct_idle ) -#define BIC_GROUP_IDLE (BIC_GROUP_HW_IDLE | BIC_pct_idle) -#define BIC_OTHER (BIC_IRQ | BIC_NMI | BIC_SMI | BIC_ThreadC | BIC_CoreTmp | BIC_IPC) - -#define BIC_DISABLED_BY_DEFAULT (BIC_USEC | BIC_TOD | BIC_APIC | BIC_X2APIC | BIC_cpuidle) - -unsigned long long bic_enabled = (0xFFFFFFFFFFFFFFFFULL & ~BIC_DISABLED_BY_DEFAULT); -unsigned long long bic_present = BIC_USEC | BIC_TOD | BIC_cpuidle | BIC_pct_idle | BIC_APIC | BIC_X2APIC; - -#define DO_BIC(COUNTER_NAME) (bic_enabled & bic_present & COUNTER_NAME) -#define DO_BIC_READ(COUNTER_NAME) (bic_present & COUNTER_NAME) -#define ENABLE_BIC(COUNTER_NAME) (bic_enabled |= COUNTER_NAME) -#define BIC_PRESENT(COUNTER_BIT) (bic_present |= COUNTER_BIT) -#define BIC_NOT_PRESENT(COUNTER_BIT) (bic_present &= ~COUNTER_BIT) -#define BIC_IS_ENABLED(COUNTER_BIT) (bic_enabled & COUNTER_BIT) +/* n.b. bic_names must match the order in bic[], above */ +enum bic_names { + BIC_USEC, + BIC_TOD, + BIC_Package, + BIC_Node, + BIC_Avg_MHz, + BIC_Busy, + BIC_Bzy_MHz, + BIC_TSC_MHz, + BIC_IRQ, + BIC_SMI, + BIC_cpuidle, + BIC_CPU_c1, + BIC_CPU_c3, + BIC_CPU_c6, + BIC_CPU_c7, + BIC_ThreadC, + BIC_CoreTmp, + BIC_CoreCnt, + BIC_PkgTmp, + BIC_GFX_rc6, + BIC_GFXMHz, + BIC_Pkgpc2, + BIC_Pkgpc3, + BIC_Pkgpc6, + BIC_Pkgpc7, + BIC_Pkgpc8, + BIC_Pkgpc9, + BIC_Pkgpc10, + BIC_CPU_LPI, + BIC_SYS_LPI, + BIC_PkgWatt, + BIC_CorWatt, + BIC_GFXWatt, + BIC_PkgCnt, + BIC_RAMWatt, + BIC_PKG__, + BIC_RAM__, + BIC_Pkg_J, + BIC_Cor_J, + BIC_GFX_J, + BIC_RAM_J, + BIC_Mod_c6, + BIC_Totl_c0, + BIC_Any_c0, + BIC_GFX_c0, + BIC_CPUGFX, + BIC_Core, + BIC_CPU, + BIC_APIC, + BIC_X2APIC, + BIC_Die, + BIC_L3, + BIC_GFXACTMHz, + BIC_IPC, + BIC_CORE_THROT_CNT, + BIC_UNCORE_MHZ, + BIC_SAM_mc6, + BIC_SAMMHz, + BIC_SAMACTMHz, + BIC_Diec6, + BIC_SysWatt, + BIC_Sys_J, + BIC_NMI, + BIC_CPU_c1e, + BIC_pct_idle, + MAX_BIC +}; + +void print_bic_set(char *s, cpu_set_t *set) +{ + int i; + + assert(MAX_BIC < CPU_SETSIZE); + + printf("%s:", s); + + for (i = 0; i <= MAX_BIC; ++i) { + + if (CPU_ISSET(i, set)) { + assert(i < MAX_BIC); + printf(" %s", bic[i].name); + } + } + putchar('\n'); +} + +static cpu_set_t bic_group_topology; +static cpu_set_t bic_group_thermal_pwr; +static cpu_set_t bic_group_frequency; +static cpu_set_t bic_group_hw_idle; +static cpu_set_t bic_group_sw_idle; +static cpu_set_t bic_group_idle; +static cpu_set_t bic_group_other; +static cpu_set_t bic_group_disabled_by_default; +static cpu_set_t bic_enabled; +static cpu_set_t bic_present; + +/* modify */ +#define BIC_INIT(set) CPU_ZERO(set) + +#define SET_BIC(COUNTER_NUMBER, set) CPU_SET(COUNTER_NUMBER, set) +#define CLR_BIC(COUNTER_NUMBER, set) CPU_CLR(COUNTER_NUMBER, set) + +#define BIC_PRESENT(COUNTER_NUMBER) SET_BIC(COUNTER_NUMBER, &bic_present) +#define BIC_NOT_PRESENT(COUNTER_NUMBER) CPU_CLR(COUNTER_NUMBER, &bic_present) + +/* test */ +#define BIC_IS_ENABLED(COUNTER_NUMBER) CPU_ISSET(COUNTER_NUMBER, &bic_enabled) +#define DO_BIC_READ(COUNTER_NUMBER) CPU_ISSET(COUNTER_NUMBER, &bic_present) +#define DO_BIC(COUNTER_NUMBER) (CPU_ISSET(COUNTER_NUMBER, &bic_enabled) && CPU_ISSET(COUNTER_NUMBER, &bic_present)) + +static void bic_set_all(cpu_set_t *set) +{ + int i; + + assert(MAX_BIC < CPU_SETSIZE); + + for (i = 0; i < MAX_BIC; ++i) + SET_BIC(i, set); +} + +/* + * bic_clear_bits() + * clear all the bits from "clr" in "dst" + */ +static void bic_clear_bits(cpu_set_t *dst, cpu_set_t *clr) +{ + int i; + + assert(MAX_BIC < CPU_SETSIZE); + + for (i = 0; i < MAX_BIC; ++i) + if (CPU_ISSET(i, clr)) + CLR_BIC(i, dst); +} + +static void bic_groups_init(void) +{ + BIC_INIT(&bic_group_topology); + SET_BIC(BIC_Package, &bic_group_topology); + SET_BIC(BIC_Node, &bic_group_topology); + SET_BIC(BIC_CoreCnt, &bic_group_topology); + SET_BIC(BIC_PkgCnt, &bic_group_topology); + SET_BIC(BIC_Core, &bic_group_topology); + SET_BIC(BIC_CPU, &bic_group_topology); + SET_BIC(BIC_Die, &bic_group_topology); + SET_BIC(BIC_L3, &bic_group_topology); + + BIC_INIT(&bic_group_thermal_pwr); + SET_BIC(BIC_CoreTmp, &bic_group_thermal_pwr); + SET_BIC(BIC_PkgTmp, &bic_group_thermal_pwr); + SET_BIC(BIC_PkgWatt, &bic_group_thermal_pwr); + SET_BIC(BIC_CorWatt, &bic_group_thermal_pwr); + SET_BIC(BIC_GFXWatt, &bic_group_thermal_pwr); + SET_BIC(BIC_RAMWatt, &bic_group_thermal_pwr); + SET_BIC(BIC_PKG__, &bic_group_thermal_pwr); + SET_BIC(BIC_RAM__, &bic_group_thermal_pwr); + SET_BIC(BIC_SysWatt, &bic_group_thermal_pwr); + + BIC_INIT(&bic_group_frequency); + SET_BIC(BIC_Avg_MHz, &bic_group_frequency); + SET_BIC(BIC_Busy, &bic_group_frequency); + SET_BIC(BIC_Bzy_MHz, &bic_group_frequency); + SET_BIC(BIC_TSC_MHz, &bic_group_frequency); + SET_BIC(BIC_GFXMHz, &bic_group_frequency); + SET_BIC(BIC_GFXACTMHz, &bic_group_frequency); + SET_BIC(BIC_SAMMHz, &bic_group_frequency); + SET_BIC(BIC_SAMACTMHz, &bic_group_frequency); + SET_BIC(BIC_UNCORE_MHZ, &bic_group_frequency); + + BIC_INIT(&bic_group_hw_idle); + SET_BIC(BIC_Busy, &bic_group_hw_idle); + SET_BIC(BIC_CPU_c1, &bic_group_hw_idle); + SET_BIC(BIC_CPU_c3, &bic_group_hw_idle); + SET_BIC(BIC_CPU_c6, &bic_group_hw_idle); + SET_BIC(BIC_CPU_c7, &bic_group_hw_idle); + SET_BIC(BIC_GFX_rc6, &bic_group_hw_idle); + SET_BIC(BIC_Pkgpc2, &bic_group_hw_idle); + SET_BIC(BIC_Pkgpc3, &bic_group_hw_idle); + SET_BIC(BIC_Pkgpc6, &bic_group_hw_idle); + SET_BIC(BIC_Pkgpc7, &bic_group_hw_idle); + SET_BIC(BIC_Pkgpc8, &bic_group_hw_idle); + SET_BIC(BIC_Pkgpc9, &bic_group_hw_idle); + SET_BIC(BIC_Pkgpc10, &bic_group_hw_idle); + SET_BIC(BIC_CPU_LPI, &bic_group_hw_idle); + SET_BIC(BIC_SYS_LPI, &bic_group_hw_idle); + SET_BIC(BIC_Mod_c6, &bic_group_hw_idle); + SET_BIC(BIC_Totl_c0, &bic_group_hw_idle); + SET_BIC(BIC_Any_c0, &bic_group_hw_idle); + SET_BIC(BIC_GFX_c0, &bic_group_hw_idle); + SET_BIC(BIC_CPUGFX, &bic_group_hw_idle); + SET_BIC(BIC_SAM_mc6, &bic_group_hw_idle); + SET_BIC(BIC_Diec6, &bic_group_hw_idle); + + BIC_INIT(&bic_group_sw_idle); + SET_BIC(BIC_Busy, &bic_group_sw_idle); + SET_BIC(BIC_cpuidle, &bic_group_sw_idle); + SET_BIC(BIC_pct_idle, &bic_group_sw_idle); + + BIC_INIT(&bic_group_idle); + CPU_OR(&bic_group_idle, &bic_group_idle, &bic_group_hw_idle); + SET_BIC(BIC_pct_idle, &bic_group_idle); + + BIC_INIT(&bic_group_other); + SET_BIC(BIC_IRQ, &bic_group_other); + SET_BIC(BIC_NMI, &bic_group_other); + SET_BIC(BIC_SMI, &bic_group_other); + SET_BIC(BIC_ThreadC, &bic_group_other); + SET_BIC(BIC_CoreTmp, &bic_group_other); + SET_BIC(BIC_IPC, &bic_group_other); + + BIC_INIT(&bic_group_disabled_by_default); + SET_BIC(BIC_USEC, &bic_group_disabled_by_default); + SET_BIC(BIC_TOD, &bic_group_disabled_by_default); + SET_BIC(BIC_cpuidle, &bic_group_disabled_by_default); + SET_BIC(BIC_APIC, &bic_group_disabled_by_default); + SET_BIC(BIC_X2APIC, &bic_group_disabled_by_default); + + BIC_INIT(&bic_enabled); + bic_set_all(&bic_enabled); + bic_clear_bits(&bic_enabled, &bic_group_disabled_by_default); + + BIC_INIT(&bic_present); + SET_BIC(BIC_USEC, &bic_present); + SET_BIC(BIC_TOD, &bic_present); + SET_BIC(BIC_cpuidle, &bic_present); + SET_BIC(BIC_APIC, &bic_present); + SET_BIC(BIC_X2APIC, &bic_present); + SET_BIC(BIC_pct_idle, &bic_present); +} /* * MSR_PKG_CST_CONFIG_CONTROL decoding for pkg_cstate_limit: @@ -840,20 +989,21 @@ static const struct platform_features spr_features = { }; static const struct platform_features dmr_features = { - .has_msr_misc_feature_control = spr_features.has_msr_misc_feature_control, - .has_msr_misc_pwr_mgmt = spr_features.has_msr_misc_pwr_mgmt, - .has_nhm_msrs = spr_features.has_nhm_msrs, - .has_config_tdp = spr_features.has_config_tdp, - .bclk_freq = spr_features.bclk_freq, - .supported_cstates = spr_features.supported_cstates, - .cst_limit = spr_features.cst_limit, - .has_msr_core_c1_res = spr_features.has_msr_core_c1_res, - .has_msr_module_c6_res_ms = 1, /* DMR has Dual Core Module and MC6 MSR */ - .has_irtl_msrs = spr_features.has_irtl_msrs, - .has_cst_prewake_bit = spr_features.has_cst_prewake_bit, - .has_fixed_rapl_psys_unit = spr_features.has_fixed_rapl_psys_unit, - .trl_msrs = spr_features.trl_msrs, - .rapl_msrs = 0, /* DMR does not have RAPL MSRs */ + .has_msr_misc_feature_control = spr_features.has_msr_misc_feature_control, + .has_msr_misc_pwr_mgmt = spr_features.has_msr_misc_pwr_mgmt, + .has_nhm_msrs = spr_features.has_nhm_msrs, + .bclk_freq = spr_features.bclk_freq, + .supported_cstates = spr_features.supported_cstates, + .cst_limit = spr_features.cst_limit, + .has_msr_core_c1_res = spr_features.has_msr_core_c1_res, + .has_cst_prewake_bit = spr_features.has_cst_prewake_bit, + .has_fixed_rapl_psys_unit = spr_features.has_fixed_rapl_psys_unit, + .trl_msrs = spr_features.trl_msrs, + .has_msr_module_c6_res_ms = 1, /* DMR has Dual-Core-Module and MC6 MSR */ + .rapl_msrs = 0, /* DMR does not have RAPL MSRs */ + .plr_msrs = 0, /* DMR does not have PLR MSRs */ + .has_irtl_msrs = 0, /* DMR does not have IRTL MSRs */ + .has_config_tdp = 0, /* DMR does not have CTDP MSRs */ }; static const struct platform_features srf_features = { @@ -1204,7 +1354,7 @@ struct rapl_counter_arch_info { int msr_shift; /* Positive mean shift right, negative mean shift left */ double *platform_rapl_msr_scale; /* Scale applied to values read by MSR (platform dependent, filled at runtime) */ unsigned int rci_index; /* Maps data from perf counters to global variables */ - unsigned long long bic; + unsigned int bic_number; double compat_scale; /* Some counters require constant scaling to be in the same range as other, similar ones */ unsigned long long flags; }; @@ -1219,7 +1369,20 @@ static const struct rapl_counter_arch_info rapl_counter_arch_infos[] = { .msr_shift = 0, .platform_rapl_msr_scale = &rapl_energy_units, .rci_index = RAPL_RCI_INDEX_ENERGY_PKG, - .bic = BIC_PkgWatt | BIC_Pkg_J, + .bic_number = BIC_PkgWatt, + .compat_scale = 1.0, + .flags = RAPL_COUNTER_FLAG_USE_MSR_SUM, + }, + { + .feature_mask = RAPL_PKG, + .perf_subsys = "power", + .perf_name = "energy-pkg", + .msr = MSR_PKG_ENERGY_STATUS, + .msr_mask = 0xFFFFFFFFFFFFFFFF, + .msr_shift = 0, + .platform_rapl_msr_scale = &rapl_energy_units, + .rci_index = RAPL_RCI_INDEX_ENERGY_PKG, + .bic_number = BIC_Pkg_J, .compat_scale = 1.0, .flags = RAPL_COUNTER_FLAG_USE_MSR_SUM, }, @@ -1232,7 +1395,33 @@ static const struct rapl_counter_arch_info rapl_counter_arch_infos[] = { .msr_shift = 0, .platform_rapl_msr_scale = &rapl_energy_units, .rci_index = RAPL_RCI_INDEX_ENERGY_PKG, - .bic = BIC_PkgWatt | BIC_Pkg_J, + .bic_number = BIC_PkgWatt, + .compat_scale = 1.0, + .flags = RAPL_COUNTER_FLAG_USE_MSR_SUM, + }, + { + .feature_mask = RAPL_AMD_F17H, + .perf_subsys = "power", + .perf_name = "energy-pkg", + .msr = MSR_PKG_ENERGY_STAT, + .msr_mask = 0xFFFFFFFFFFFFFFFF, + .msr_shift = 0, + .platform_rapl_msr_scale = &rapl_energy_units, + .rci_index = RAPL_RCI_INDEX_ENERGY_PKG, + .bic_number = BIC_Pkg_J, + .compat_scale = 1.0, + .flags = RAPL_COUNTER_FLAG_USE_MSR_SUM, + }, + { + .feature_mask = RAPL_CORE_ENERGY_STATUS, + .perf_subsys = "power", + .perf_name = "energy-cores", + .msr = MSR_PP0_ENERGY_STATUS, + .msr_mask = 0xFFFFFFFFFFFFFFFF, + .msr_shift = 0, + .platform_rapl_msr_scale = &rapl_energy_units, + .rci_index = RAPL_RCI_INDEX_ENERGY_CORES, + .bic_number = BIC_CorWatt, .compat_scale = 1.0, .flags = RAPL_COUNTER_FLAG_USE_MSR_SUM, }, @@ -1245,7 +1434,7 @@ static const struct rapl_counter_arch_info rapl_counter_arch_infos[] = { .msr_shift = 0, .platform_rapl_msr_scale = &rapl_energy_units, .rci_index = RAPL_RCI_INDEX_ENERGY_CORES, - .bic = BIC_CorWatt | BIC_Cor_J, + .bic_number = BIC_Cor_J, .compat_scale = 1.0, .flags = RAPL_COUNTER_FLAG_USE_MSR_SUM, }, @@ -1258,7 +1447,20 @@ static const struct rapl_counter_arch_info rapl_counter_arch_infos[] = { .msr_shift = 0, .platform_rapl_msr_scale = &rapl_dram_energy_units, .rci_index = RAPL_RCI_INDEX_DRAM, - .bic = BIC_RAMWatt | BIC_RAM_J, + .bic_number = BIC_RAMWatt, + .compat_scale = 1.0, + .flags = RAPL_COUNTER_FLAG_USE_MSR_SUM, + }, + { + .feature_mask = RAPL_DRAM, + .perf_subsys = "power", + .perf_name = "energy-ram", + .msr = MSR_DRAM_ENERGY_STATUS, + .msr_mask = 0xFFFFFFFFFFFFFFFF, + .msr_shift = 0, + .platform_rapl_msr_scale = &rapl_dram_energy_units, + .rci_index = RAPL_RCI_INDEX_DRAM, + .bic_number = BIC_RAM_J, .compat_scale = 1.0, .flags = RAPL_COUNTER_FLAG_USE_MSR_SUM, }, @@ -1271,7 +1473,20 @@ static const struct rapl_counter_arch_info rapl_counter_arch_infos[] = { .msr_shift = 0, .platform_rapl_msr_scale = &rapl_energy_units, .rci_index = RAPL_RCI_INDEX_GFX, - .bic = BIC_GFXWatt | BIC_GFX_J, + .bic_number = BIC_GFXWatt, + .compat_scale = 1.0, + .flags = RAPL_COUNTER_FLAG_USE_MSR_SUM, + }, + { + .feature_mask = RAPL_GFX, + .perf_subsys = "power", + .perf_name = "energy-gpu", + .msr = MSR_PP1_ENERGY_STATUS, + .msr_mask = 0xFFFFFFFFFFFFFFFF, + .msr_shift = 0, + .platform_rapl_msr_scale = &rapl_energy_units, + .rci_index = RAPL_RCI_INDEX_GFX, + .bic_number = BIC_GFX_J, .compat_scale = 1.0, .flags = RAPL_COUNTER_FLAG_USE_MSR_SUM, }, @@ -1284,7 +1499,7 @@ static const struct rapl_counter_arch_info rapl_counter_arch_infos[] = { .msr_shift = 0, .platform_rapl_msr_scale = &rapl_time_units, .rci_index = RAPL_RCI_INDEX_PKG_PERF_STATUS, - .bic = BIC_PKG__, + .bic_number = BIC_PKG__, .compat_scale = 100.0, .flags = RAPL_COUNTER_FLAG_USE_MSR_SUM, }, @@ -1297,7 +1512,7 @@ static const struct rapl_counter_arch_info rapl_counter_arch_infos[] = { .msr_shift = 0, .platform_rapl_msr_scale = &rapl_time_units, .rci_index = RAPL_RCI_INDEX_DRAM_PERF_STATUS, - .bic = BIC_RAM__, + .bic_number = BIC_RAM__, .compat_scale = 100.0, .flags = RAPL_COUNTER_FLAG_USE_MSR_SUM, }, @@ -1310,7 +1525,20 @@ static const struct rapl_counter_arch_info rapl_counter_arch_infos[] = { .msr_shift = 0, .platform_rapl_msr_scale = &rapl_energy_units, .rci_index = RAPL_RCI_INDEX_CORE_ENERGY, - .bic = BIC_CorWatt | BIC_Cor_J, + .bic_number = BIC_CorWatt, + .compat_scale = 1.0, + .flags = 0, + }, + { + .feature_mask = RAPL_AMD_F17H, + .perf_subsys = NULL, + .perf_name = NULL, + .msr = MSR_CORE_ENERGY_STAT, + .msr_mask = 0xFFFFFFFF, + .msr_shift = 0, + .platform_rapl_msr_scale = &rapl_energy_units, + .rci_index = RAPL_RCI_INDEX_CORE_ENERGY, + .bic_number = BIC_Cor_J, .compat_scale = 1.0, .flags = 0, }, @@ -1323,7 +1551,20 @@ static const struct rapl_counter_arch_info rapl_counter_arch_infos[] = { .msr_shift = 0, .platform_rapl_msr_scale = &rapl_psys_energy_units, .rci_index = RAPL_RCI_INDEX_ENERGY_PLATFORM, - .bic = BIC_SysWatt | BIC_Sys_J, + .bic_number = BIC_SysWatt, + .compat_scale = 1.0, + .flags = RAPL_COUNTER_FLAG_PLATFORM_COUNTER | RAPL_COUNTER_FLAG_USE_MSR_SUM, + }, + { + .feature_mask = RAPL_PSYS, + .perf_subsys = "power", + .perf_name = "energy-psys", + .msr = MSR_PLATFORM_ENERGY_STATUS, + .msr_mask = 0x00000000FFFFFFFF, + .msr_shift = 0, + .platform_rapl_msr_scale = &rapl_psys_energy_units, + .rci_index = RAPL_RCI_INDEX_ENERGY_PLATFORM, + .bic_number = BIC_Sys_J, .compat_scale = 1.0, .flags = RAPL_COUNTER_FLAG_PLATFORM_COUNTER | RAPL_COUNTER_FLAG_USE_MSR_SUM, }, @@ -1372,7 +1613,7 @@ struct cstate_counter_arch_info { const char *perf_name; unsigned long long msr; unsigned int rci_index; /* Maps data from perf counters to global variables */ - unsigned long long bic; + unsigned int bic_number; unsigned long long flags; int pkg_cstate_limit; }; @@ -1384,7 +1625,7 @@ static struct cstate_counter_arch_info ccstate_counter_arch_infos[] = { .perf_name = "c1-residency", .msr = MSR_CORE_C1_RES, .rci_index = CCSTATE_RCI_INDEX_C1_RESIDENCY, - .bic = BIC_CPU_c1, + .bic_number = BIC_CPU_c1, .flags = CSTATE_COUNTER_FLAG_COLLECT_PER_THREAD, .pkg_cstate_limit = 0, }, @@ -1394,7 +1635,7 @@ static struct cstate_counter_arch_info ccstate_counter_arch_infos[] = { .perf_name = "c3-residency", .msr = MSR_CORE_C3_RESIDENCY, .rci_index = CCSTATE_RCI_INDEX_C3_RESIDENCY, - .bic = BIC_CPU_c3, + .bic_number = BIC_CPU_c3, .flags = CSTATE_COUNTER_FLAG_COLLECT_PER_CORE | CSTATE_COUNTER_FLAG_SOFT_C1_DEPENDENCY, .pkg_cstate_limit = 0, }, @@ -1404,7 +1645,7 @@ static struct cstate_counter_arch_info ccstate_counter_arch_infos[] = { .perf_name = "c6-residency", .msr = MSR_CORE_C6_RESIDENCY, .rci_index = CCSTATE_RCI_INDEX_C6_RESIDENCY, - .bic = BIC_CPU_c6, + .bic_number = BIC_CPU_c6, .flags = CSTATE_COUNTER_FLAG_COLLECT_PER_CORE | CSTATE_COUNTER_FLAG_SOFT_C1_DEPENDENCY, .pkg_cstate_limit = 0, }, @@ -1414,7 +1655,7 @@ static struct cstate_counter_arch_info ccstate_counter_arch_infos[] = { .perf_name = "c7-residency", .msr = MSR_CORE_C7_RESIDENCY, .rci_index = CCSTATE_RCI_INDEX_C7_RESIDENCY, - .bic = BIC_CPU_c7, + .bic_number = BIC_CPU_c7, .flags = CSTATE_COUNTER_FLAG_COLLECT_PER_CORE | CSTATE_COUNTER_FLAG_SOFT_C1_DEPENDENCY, .pkg_cstate_limit = 0, }, @@ -1424,7 +1665,7 @@ static struct cstate_counter_arch_info ccstate_counter_arch_infos[] = { .perf_name = "c2-residency", .msr = MSR_PKG_C2_RESIDENCY, .rci_index = PCSTATE_RCI_INDEX_C2_RESIDENCY, - .bic = BIC_Pkgpc2, + .bic_number = BIC_Pkgpc2, .flags = 0, .pkg_cstate_limit = PCL__2, }, @@ -1434,7 +1675,7 @@ static struct cstate_counter_arch_info ccstate_counter_arch_infos[] = { .perf_name = "c3-residency", .msr = MSR_PKG_C3_RESIDENCY, .rci_index = PCSTATE_RCI_INDEX_C3_RESIDENCY, - .bic = BIC_Pkgpc3, + .bic_number = BIC_Pkgpc3, .flags = 0, .pkg_cstate_limit = PCL__3, }, @@ -1444,7 +1685,7 @@ static struct cstate_counter_arch_info ccstate_counter_arch_infos[] = { .perf_name = "c6-residency", .msr = MSR_PKG_C6_RESIDENCY, .rci_index = PCSTATE_RCI_INDEX_C6_RESIDENCY, - .bic = BIC_Pkgpc6, + .bic_number = BIC_Pkgpc6, .flags = 0, .pkg_cstate_limit = PCL__6, }, @@ -1454,7 +1695,7 @@ static struct cstate_counter_arch_info ccstate_counter_arch_infos[] = { .perf_name = "c7-residency", .msr = MSR_PKG_C7_RESIDENCY, .rci_index = PCSTATE_RCI_INDEX_C7_RESIDENCY, - .bic = BIC_Pkgpc7, + .bic_number = BIC_Pkgpc7, .flags = 0, .pkg_cstate_limit = PCL__7, }, @@ -1464,7 +1705,7 @@ static struct cstate_counter_arch_info ccstate_counter_arch_infos[] = { .perf_name = "c8-residency", .msr = MSR_PKG_C8_RESIDENCY, .rci_index = PCSTATE_RCI_INDEX_C8_RESIDENCY, - .bic = BIC_Pkgpc8, + .bic_number = BIC_Pkgpc8, .flags = 0, .pkg_cstate_limit = PCL__8, }, @@ -1474,7 +1715,7 @@ static struct cstate_counter_arch_info ccstate_counter_arch_infos[] = { .perf_name = "c9-residency", .msr = MSR_PKG_C9_RESIDENCY, .rci_index = PCSTATE_RCI_INDEX_C9_RESIDENCY, - .bic = BIC_Pkgpc9, + .bic_number = BIC_Pkgpc9, .flags = 0, .pkg_cstate_limit = PCL__9, }, @@ -1484,7 +1725,7 @@ static struct cstate_counter_arch_info ccstate_counter_arch_infos[] = { .perf_name = "c10-residency", .msr = MSR_PKG_C10_RESIDENCY, .rci_index = PCSTATE_RCI_INDEX_C10_RESIDENCY, - .bic = BIC_Pkgpc10, + .bic_number = BIC_Pkgpc10, .flags = 0, .pkg_cstate_limit = PCL_10, }, @@ -1840,8 +2081,6 @@ struct pkg_data { ((node_no) * topo.cores_per_node) + \ (core_no)) -#define GET_PKG(pkg_base, pkg_no) (pkg_base + pkg_no) - /* * The accumulated sum of MSR is defined as a monotonic * increasing MSR, it will be accumulated periodically, @@ -2036,6 +2275,7 @@ struct platform_counters { struct cpu_topology { int physical_package_id; int die_id; + int l3_id; int logical_cpu_id; int physical_node_id; int logical_node_id; /* 0-based count within the package */ @@ -2057,6 +2297,7 @@ struct topo_params { int max_core_id; int max_package_id; int max_die_id; + int max_l3_id; int max_node_num; int nodes_per_pkg; int cores_per_node; @@ -2090,6 +2331,8 @@ int cpu_is_not_allowed(int cpu) * skip non-present cpus */ +#define PER_THREAD_PARAMS struct thread_data *t, struct core_data *c, struct pkg_data *p + int for_all_cpus(int (func) (struct thread_data *, struct core_data *, struct pkg_data *), struct thread_data *thread_base, struct core_data *core_base, struct pkg_data *pkg_base) { @@ -2103,16 +2346,15 @@ int for_all_cpus(int (func) (struct thread_data *, struct core_data *, struct pk for (thread_no = 0; thread_no < topo.threads_per_core; ++thread_no) { struct thread_data *t; struct core_data *c; - struct pkg_data *p; + t = GET_THREAD(thread_base, thread_no, core_no, node_no, pkg_no); if (cpu_is_not_allowed(t->cpu_id)) continue; c = GET_CORE(core_base, core_no, node_no, pkg_no); - p = GET_PKG(pkg_base, pkg_no); - retval |= func(t, c, p); + retval |= func(t, c, &pkg_base[pkg_no]); } } } @@ -2120,21 +2362,21 @@ int for_all_cpus(int (func) (struct thread_data *, struct core_data *, struct pk return retval; } -int is_cpu_first_thread_in_core(struct thread_data *t, struct core_data *c, struct pkg_data *p) +int is_cpu_first_thread_in_core(PER_THREAD_PARAMS) { UNUSED(p); return ((int)t->cpu_id == c->base_cpu || c->base_cpu < 0); } -int is_cpu_first_core_in_package(struct thread_data *t, struct core_data *c, struct pkg_data *p) +int is_cpu_first_core_in_package(PER_THREAD_PARAMS) { UNUSED(c); return ((int)t->cpu_id == p->base_cpu || p->base_cpu < 0); } -int is_cpu_first_thread_in_package(struct thread_data *t, struct core_data *c, struct pkg_data *p) +int is_cpu_first_thread_in_package(PER_THREAD_PARAMS) { return is_cpu_first_thread_in_core(t, c, p) && is_cpu_first_core_in_package(t, c, p); } @@ -2179,10 +2421,13 @@ int get_msr_fd(int cpu) static void bic_disable_msr_access(void) { - const unsigned long bic_msrs = BIC_Mod_c6 | BIC_CoreTmp | - BIC_Totl_c0 | BIC_Any_c0 | BIC_GFX_c0 | BIC_CPUGFX | BIC_PkgTmp; - - bic_enabled &= ~bic_msrs; + CLR_BIC(BIC_Mod_c6, &bic_enabled); + CLR_BIC(BIC_CoreTmp, &bic_enabled); + CLR_BIC(BIC_Totl_c0, &bic_enabled); + CLR_BIC(BIC_Any_c0, &bic_enabled); + CLR_BIC(BIC_GFX_c0, &bic_enabled); + CLR_BIC(BIC_CPUGFX, &bic_enabled); + CLR_BIC(BIC_PkgTmp, &bic_enabled); free_sys_msr_counters(); } @@ -2310,6 +2555,8 @@ char *deferred_add_names[MAX_DEFERRED]; char *deferred_skip_names[MAX_DEFERRED]; int deferred_add_index; int deferred_skip_index; +unsigned int deferred_add_consumed; +unsigned int deferred_skip_consumed; /* * HIDE_LIST - hide this list of counters, show the rest [default] @@ -2380,10 +2627,9 @@ void help(void) * for all the strings in comma separate name_list, * set the approprate bit in return value. */ -unsigned long long bic_lookup(char *name_list, enum show_hide_mode mode) +void bic_lookup(cpu_set_t *ret_set, char *name_list, enum show_hide_mode mode) { unsigned int i; - unsigned long long retval = 0; while (name_list) { char *comma; @@ -2395,41 +2641,39 @@ unsigned long long bic_lookup(char *name_list, enum show_hide_mode mode) for (i = 0; i < MAX_BIC; ++i) { if (!strcmp(name_list, bic[i].name)) { - retval |= (1ULL << i); + SET_BIC(i, ret_set); break; } if (!strcmp(name_list, "all")) { - retval |= ~0; + bic_set_all(ret_set); break; } else if (!strcmp(name_list, "topology")) { - retval |= BIC_GROUP_TOPOLOGY; + CPU_OR(ret_set, ret_set, &bic_group_topology); break; } else if (!strcmp(name_list, "power")) { - retval |= BIC_GROUP_THERMAL_PWR; + CPU_OR(ret_set, ret_set, &bic_group_thermal_pwr); break; } else if (!strcmp(name_list, "idle")) { - retval |= BIC_GROUP_IDLE; + CPU_OR(ret_set, ret_set, &bic_group_idle); break; } else if (!strcmp(name_list, "swidle")) { - retval |= BIC_GROUP_SW_IDLE; + CPU_OR(ret_set, ret_set, &bic_group_sw_idle); break; } else if (!strcmp(name_list, "sysfs")) { /* legacy compatibility */ - retval |= BIC_GROUP_SW_IDLE; + CPU_OR(ret_set, ret_set, &bic_group_sw_idle); break; } else if (!strcmp(name_list, "hwidle")) { - retval |= BIC_GROUP_HW_IDLE; + CPU_OR(ret_set, ret_set, &bic_group_hw_idle); break; } else if (!strcmp(name_list, "frequency")) { - retval |= BIC_GROUP_FREQUENCY; + CPU_OR(ret_set, ret_set, &bic_group_frequency); break; } else if (!strcmp(name_list, "other")) { - retval |= BIC_OTHER; + CPU_OR(ret_set, ret_set, &bic_group_other); break; } - } if (i == MAX_BIC) { - fprintf(stderr, "deferred %s\n", name_list); if (mode == SHOW_LIST) { deferred_add_names[deferred_add_index++] = name_list; if (deferred_add_index >= MAX_DEFERRED) { @@ -2456,7 +2700,6 @@ unsigned long long bic_lookup(char *name_list, enum show_hide_mode mode) name_list++; } - return retval; } void print_header(char *delim) @@ -2474,6 +2717,8 @@ void print_header(char *delim) outp += sprintf(outp, "%sPackage", (printed++ ? delim : "")); if (DO_BIC(BIC_Die)) outp += sprintf(outp, "%sDie", (printed++ ? delim : "")); + if (DO_BIC(BIC_L3)) + outp += sprintf(outp, "%sL3", (printed++ ? delim : "")); if (DO_BIC(BIC_Node)) outp += sprintf(outp, "%sNode", (printed++ ? delim : "")); if (DO_BIC(BIC_Core)) @@ -2514,7 +2759,7 @@ void print_header(char *delim) for (mp = sys.tp; mp; mp = mp->next) { - if (mp->format == FORMAT_RAW) { + if (mp->format == FORMAT_RAW || mp->format == FORMAT_AVERAGE) { if (mp->width == 64) outp += sprintf(outp, "%s%18.18s", (printed++ ? delim : ""), mp->name); else @@ -2589,7 +2834,7 @@ void print_header(char *delim) } for (mp = sys.cp; mp; mp = mp->next) { - if (mp->format == FORMAT_RAW) { + if (mp->format == FORMAT_RAW || mp->format == FORMAT_AVERAGE) { if (mp->width == 64) outp += sprintf(outp, "%s%18.18s", delim, mp->name); else @@ -2719,7 +2964,7 @@ void print_header(char *delim) outp += sprintf(outp, "%sUncMHz", (printed++ ? delim : "")); for (mp = sys.pp; mp; mp = mp->next) { - if (mp->format == FORMAT_RAW) { + if (mp->format == FORMAT_RAW || mp->format == FORMAT_AVERAGE) { if (mp->width == 64) outp += sprintf(outp, "%s%18.18s", delim, mp->name); else if (mp->width == 32) @@ -2777,7 +3022,7 @@ void print_header(char *delim) outp += sprintf(outp, "\n"); } -int dump_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p) +int dump_counters(PER_THREAD_PARAMS) { int i; struct msr_counter *mp; @@ -2892,7 +3137,7 @@ double rapl_counter_get_value(const struct rapl_counter *c, enum rapl_unit desir /* * column formatting convention & formats */ -int format_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p) +int format_counters(PER_THREAD_PARAMS) { static int count; @@ -2945,6 +3190,8 @@ int format_counters(struct thread_data *t, struct core_data *c, struct pkg_data outp += sprintf(outp, "%s-", (printed++ ? delim : "")); if (DO_BIC(BIC_Die)) outp += sprintf(outp, "%s-", (printed++ ? delim : "")); + if (DO_BIC(BIC_L3)) + outp += sprintf(outp, "%s-", (printed++ ? delim : "")); if (DO_BIC(BIC_Node)) outp += sprintf(outp, "%s-", (printed++ ? delim : "")); if (DO_BIC(BIC_Core)) @@ -2968,6 +3215,12 @@ int format_counters(struct thread_data *t, struct core_data *c, struct pkg_data else outp += sprintf(outp, "%s-", (printed++ ? delim : "")); } + if (DO_BIC(BIC_L3)) { + if (c) + outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), cpus[t->cpu_id].l3_id); + else + outp += sprintf(outp, "%s-", (printed++ ? delim : "")); + } if (DO_BIC(BIC_Node)) { if (t) outp += sprintf(outp, "%s%d", @@ -3032,7 +3285,7 @@ int format_counters(struct thread_data *t, struct core_data *c, struct pkg_data /* Added counters */ for (i = 0, mp = sys.tp; mp; i++, mp = mp->next) { - if (mp->format == FORMAT_RAW) { + if (mp->format == FORMAT_RAW || mp->format == FORMAT_AVERAGE) { if (mp->width == 32) outp += sprintf(outp, "%s0x%08x", (printed++ ? delim : ""), (unsigned int)t->counter[i]); @@ -3129,7 +3382,7 @@ int format_counters(struct thread_data *t, struct core_data *c, struct pkg_data outp += sprintf(outp, "%s%lld", (printed++ ? delim : ""), c->core_throt_cnt); for (i = 0, mp = sys.cp; mp; i++, mp = mp->next) { - if (mp->format == FORMAT_RAW) { + if (mp->format == FORMAT_RAW || mp->format == FORMAT_AVERAGE) { if (mp->width == 32) outp += sprintf(outp, "%s0x%08x", (printed++ ? delim : ""), (unsigned int)c->counter[i]); @@ -3328,7 +3581,7 @@ int format_counters(struct thread_data *t, struct core_data *c, struct pkg_data outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), p->uncore_mhz); for (i = 0, mp = sys.pp; mp; i++, mp = mp->next) { - if (mp->format == FORMAT_RAW) { + if (mp->format == FORMAT_RAW || mp->format == FORMAT_AVERAGE) { if (mp->width == 32) outp += sprintf(outp, "%s0x%08x", (printed++ ? delim : ""), (unsigned int)p->counter[i]); @@ -3426,7 +3679,7 @@ void flush_output_stderr(void) outp = output_buffer; } -void format_all_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p) +void format_all_counters(PER_THREAD_PARAMS) { static int count; @@ -3505,7 +3758,7 @@ int delta_package(struct pkg_data *new, struct pkg_data *old) new->rapl_dram_perf_status.raw_value - old->rapl_dram_perf_status.raw_value; for (i = 0, mp = sys.pp; mp; i++, mp = mp->next) { - if (mp->format == FORMAT_RAW) + if (mp->format == FORMAT_RAW || mp->format == FORMAT_AVERAGE) old->counter[i] = new->counter[i]; else if (mp->format == FORMAT_AVERAGE) old->counter[i] = new->counter[i]; @@ -3549,7 +3802,7 @@ void delta_core(struct core_data *new, struct core_data *old) DELTA_WRAP32(new->core_energy.raw_value, old->core_energy.raw_value); for (i = 0, mp = sys.cp; mp; i++, mp = mp->next) { - if (mp->format == FORMAT_RAW) + if (mp->format == FORMAT_RAW || mp->format == FORMAT_AVERAGE) old->counter[i] = new->counter[i]; else old->counter[i] = new->counter[i] - old->counter[i]; @@ -3663,7 +3916,7 @@ int delta_thread(struct thread_data *new, struct thread_data *old, struct core_d old->smi_count = new->smi_count - old->smi_count; for (i = 0, mp = sys.tp; mp; i++, mp = mp->next) { - if (mp->format == FORMAT_RAW) + if (mp->format == FORMAT_RAW || mp->format == FORMAT_AVERAGE) old->counter[i] = new->counter[i]; else old->counter[i] = new->counter[i] - old->counter[i]; @@ -3717,7 +3970,7 @@ void rapl_counter_clear(struct rapl_counter *c) c->unit = RAPL_UNIT_INVALID; } -void clear_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p) +void clear_counters(PER_THREAD_PARAMS) { int i; struct msr_counter *mp; @@ -3814,7 +4067,7 @@ void rapl_counter_accumulate(struct rapl_counter *dst, const struct rapl_counter dst->raw_value += src->raw_value; } -int sum_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p) +int sum_counters(PER_THREAD_PARAMS) { int i; struct msr_counter *mp; @@ -3962,7 +4215,7 @@ int sum_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p) * sum the counters for all cpus in the system * compute the weighted average */ -void compute_average(struct thread_data *t, struct core_data *c, struct pkg_data *p) +void compute_average(PER_THREAD_PARAMS) { int i; struct msr_counter *mp; @@ -4545,7 +4798,7 @@ char *find_sysfs_path_by_id(struct sysfs_path *sp, int id) return NULL; } -int get_cstate_counters(unsigned int cpu, struct thread_data *t, struct core_data *c, struct pkg_data *p) +int get_cstate_counters(unsigned int cpu, PER_THREAD_PARAMS) { /* * Overcommit memory a little bit here, @@ -4845,7 +5098,7 @@ static inline int get_rapl_domain_id(int cpu) * migrate to cpu * acquire and record local counters for that cpu */ -int get_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p) +int get_counters(PER_THREAD_PARAMS) { int cpu = t->cpu_id; unsigned long long msr; @@ -5673,6 +5926,11 @@ int get_die_id(int cpu) return parse_int_file("/sys/devices/system/cpu/cpu%d/topology/die_id", cpu); } +int get_l3_id(int cpu) +{ + return parse_int_file("/sys/devices/system/cpu/cpu%d/cache/index3/id", cpu); +} + int get_core_id(int cpu) { return parse_int_file("/sys/devices/system/cpu/cpu%d/topology/core_id", cpu); @@ -5861,7 +6119,6 @@ int for_all_cpus_2(int (func) (struct thread_data *, struct core_data *, for (thread_no = 0; thread_no < topo.threads_per_core; ++thread_no) { struct thread_data *t, *t2; struct core_data *c, *c2; - struct pkg_data *p, *p2; t = GET_THREAD(thread_base, thread_no, core_no, node_no, pkg_no); @@ -5873,10 +6130,7 @@ int for_all_cpus_2(int (func) (struct thread_data *, struct core_data *, c = GET_CORE(core_base, core_no, node_no, pkg_no); c2 = GET_CORE(core_base2, core_no, node_no, pkg_no); - p = GET_PKG(pkg_base, pkg_no); - p2 = GET_PKG(pkg_base2, pkg_no); - - retval |= func(t, c, p, t2, c2, p2); + retval |= func(t, c, &pkg_base[pkg_no], t2, c2, &pkg_base2[pkg_no]); } } } @@ -6334,7 +6588,7 @@ int get_msr_sum(int cpu, off_t offset, unsigned long long *msr) timer_t timerid; /* Timer callback, update the sum of MSRs periodically. */ -static int update_msr_sum(struct thread_data *t, struct core_data *c, struct pkg_data *p) +static int update_msr_sum(PER_THREAD_PARAMS) { int i, ret; int cpu = t->cpu_id; @@ -6572,8 +6826,16 @@ int check_for_cap_sys_rawio(void) int ret = 0; caps = cap_get_proc(); - if (caps == NULL) + if (caps == NULL) { + /* + * CONFIG_MULTIUSER=n kernels have no cap_get_proc() + * Allow them to continue and attempt to access MSRs + */ + if (errno == ENOSYS) + return 0; + return 1; + } if (cap_get_flag(caps, CAP_SYS_RAWIO, CAP_EFFECTIVE, &cap_flag_value)) { ret = 1; @@ -6740,7 +7002,8 @@ static void probe_intel_uncore_frequency_legacy(void) sprintf(path_base, "/sys/devices/system/cpu/intel_uncore_frequency/package_%02d_die_%02d", i, j); - if (access(path_base, R_OK)) + sprintf(path, "%s/current_freq_khz", path_base); + if (access(path, R_OK)) continue; BIC_PRESENT(BIC_UNCORE_MHZ); @@ -7072,7 +7335,7 @@ static void dump_sysfs_pstate_config(void) * print_epb() * Decode the ENERGY_PERF_BIAS MSR */ -int print_epb(struct thread_data *t, struct core_data *c, struct pkg_data *p) +int print_epb(PER_THREAD_PARAMS) { char *epb_string; int cpu, epb; @@ -7121,7 +7384,7 @@ int print_epb(struct thread_data *t, struct core_data *c, struct pkg_data *p) * print_hwp() * Decode the MSR_HWP_CAPABILITIES */ -int print_hwp(struct thread_data *t, struct core_data *c, struct pkg_data *p) +int print_hwp(PER_THREAD_PARAMS) { unsigned long long msr; int cpu; @@ -7210,7 +7473,7 @@ int print_hwp(struct thread_data *t, struct core_data *c, struct pkg_data *p) /* * print_perf_limit() */ -int print_perf_limit(struct thread_data *t, struct core_data *c, struct pkg_data *p) +int print_perf_limit(PER_THREAD_PARAMS) { unsigned long long msr; int cpu; @@ -7335,21 +7598,28 @@ void rapl_probe_intel(void) unsigned long long msr; unsigned int time_unit; double tdp; - const unsigned long long bic_watt_bits = BIC_SysWatt | BIC_PkgWatt | BIC_CorWatt | BIC_RAMWatt | BIC_GFXWatt; - const unsigned long long bic_joules_bits = BIC_Sys_J | BIC_Pkg_J | BIC_Cor_J | BIC_RAM_J | BIC_GFX_J; - if (rapl_joules) - bic_enabled &= ~bic_watt_bits; - else - bic_enabled &= ~bic_joules_bits; + if (rapl_joules) { + CLR_BIC(BIC_SysWatt, &bic_enabled); + CLR_BIC(BIC_PkgWatt, &bic_enabled); + CLR_BIC(BIC_CorWatt, &bic_enabled); + CLR_BIC(BIC_RAMWatt, &bic_enabled); + CLR_BIC(BIC_GFXWatt, &bic_enabled); + } else { + CLR_BIC(BIC_Sys_J, &bic_enabled); + CLR_BIC(BIC_Pkg_J, &bic_enabled); + CLR_BIC(BIC_Cor_J, &bic_enabled); + CLR_BIC(BIC_RAM_J, &bic_enabled); + CLR_BIC(BIC_GFX_J, &bic_enabled); + } if (!platform->rapl_msrs || no_msr) return; if (!(platform->rapl_msrs & RAPL_PKG_PERF_STATUS)) - bic_enabled &= ~BIC_PKG__; + CLR_BIC(BIC_PKG__, &bic_enabled); if (!(platform->rapl_msrs & RAPL_DRAM_PERF_STATUS)) - bic_enabled &= ~BIC_RAM__; + CLR_BIC(BIC_RAM__, &bic_enabled); /* units on package 0, verify later other packages match */ if (get_msr(base_cpu, MSR_RAPL_POWER_UNIT, &msr)) @@ -7388,13 +7658,14 @@ void rapl_probe_amd(void) { unsigned long long msr; double tdp; - const unsigned long long bic_watt_bits = BIC_PkgWatt | BIC_CorWatt; - const unsigned long long bic_joules_bits = BIC_Pkg_J | BIC_Cor_J; - if (rapl_joules) - bic_enabled &= ~bic_watt_bits; - else - bic_enabled &= ~bic_joules_bits; + if (rapl_joules) { + CLR_BIC(BIC_SysWatt, &bic_enabled); + CLR_BIC(BIC_CorWatt, &bic_enabled); + } else { + CLR_BIC(BIC_Pkg_J, &bic_enabled); + CLR_BIC(BIC_Cor_J, &bic_enabled); + } if (!platform->rapl_msrs || no_msr) return; @@ -7577,7 +7848,7 @@ static int print_rapl_sysfs(void) return 0; } -int print_rapl(struct thread_data *t, struct core_data *c, struct pkg_data *p) +int print_rapl(PER_THREAD_PARAMS) { unsigned long long msr; const char *msr_name; @@ -7731,7 +8002,7 @@ void probe_rapl(void) * below this value, including the Digital Thermal Sensor (DTS), * Package Thermal Management Sensor (PTM), and thermal event thresholds. */ -int set_temperature_target(struct thread_data *t, struct core_data *c, struct pkg_data *p) +int set_temperature_target(PER_THREAD_PARAMS) { unsigned long long msr; unsigned int tcc_default, tcc_offset; @@ -7799,7 +8070,7 @@ guess: return 0; } -int print_thermal(struct thread_data *t, struct core_data *c, struct pkg_data *p) +int print_thermal(PER_THREAD_PARAMS) { unsigned long long msr; unsigned int dts, dts2; @@ -7879,7 +8150,7 @@ void probe_thermal(void) for_all_cpus(print_thermal, ODD_COUNTERS); } -int get_cpu_type(struct thread_data *t, struct core_data *c, struct pkg_data *p) +int get_cpu_type(PER_THREAD_PARAMS) { unsigned int eax, ebx, ecx, edx; @@ -8141,7 +8412,7 @@ void rapl_perf_init(void) enum rapl_unit unit; unsigned int next_domain; - if (!BIC_IS_ENABLED(cai->bic)) + if (!BIC_IS_ENABLED(cai->bic_number)) continue; memset(domain_visited, 0, num_domains * sizeof(*domain_visited)); @@ -8205,7 +8476,7 @@ void rapl_perf_init(void) /* If any CPU has access to the counter, make it present */ if (has_counter) - BIC_PRESENT(cai->bic); + BIC_PRESENT(cai->bic_number); } free(domain_visited); @@ -8426,7 +8697,7 @@ void cstate_perf_init_(bool soft_c1) if (!per_core && pkg_visited[pkg_id]) continue; - const bool counter_needed = BIC_IS_ENABLED(cai->bic) || + const bool counter_needed = BIC_IS_ENABLED(cai->bic_number) || (soft_c1 && (cai->flags & CSTATE_COUNTER_FLAG_SOFT_C1_DEPENDENCY)); const bool counter_supported = (platform->supported_cstates & cai->feature_mask); @@ -8453,7 +8724,7 @@ void cstate_perf_init_(bool soft_c1) /* If any CPU has access to the counter, make it present */ if (has_counter) - BIC_PRESENT(cai->bic); + BIC_PRESENT(cai->bic_number); } free(cores_visited); @@ -8949,6 +9220,11 @@ void topology_probe(bool startup) if (cpus[i].die_id > topo.max_die_id) topo.max_die_id = cpus[i].die_id; + /* get l3 information */ + cpus[i].l3_id = get_l3_id(i); + if (cpus[i].l3_id > topo.max_l3_id) + topo.max_l3_id = cpus[i].l3_id; + /* get numa node information */ cpus[i].physical_node_id = get_physical_node_id(&cpus[i]); if (cpus[i].physical_node_id > topo.max_node_num) @@ -8981,6 +9257,9 @@ void topology_probe(bool startup) if (!summary_only && topo.num_die > 1) BIC_PRESENT(BIC_Die); + if (!summary_only && topo.max_l3_id > 0) + BIC_PRESENT(BIC_L3); + topo.num_packages = max_package_id + 1; if (debug > 1) fprintf(outf, "max_package_id %d, sizing for %d packages\n", max_package_id, topo.num_packages); @@ -9004,8 +9283,8 @@ void topology_probe(bool startup) if (cpu_is_not_present(i)) continue; fprintf(outf, - "cpu %d pkg %d die %d node %d lnode %d core %d thread %d\n", - i, cpus[i].physical_package_id, cpus[i].die_id, + "cpu %d pkg %d die %d l3 %d node %d lnode %d core %d thread %d\n", + i, cpus[i].physical_package_id, cpus[i].die_id, cpus[i].l3_id, cpus[i].physical_node_id, cpus[i].logical_node_id, cpus[i].physical_core_id, cpus[i].thread_id); } @@ -9060,7 +9339,6 @@ void init_counter(struct thread_data *thread_base, struct core_data *core_base, int thread_id = cpus[cpu_id].thread_id; struct thread_data *t; struct core_data *c; - struct pkg_data *p; /* Workaround for systems where physical_node_id==-1 * and logical_node_id==(-1 - topo.num_cpus) @@ -9070,18 +9348,17 @@ void init_counter(struct thread_data *thread_base, struct core_data *core_base, t = GET_THREAD(thread_base, thread_id, core_id, node_id, pkg_id); c = GET_CORE(core_base, core_id, node_id, pkg_id); - p = GET_PKG(pkg_base, pkg_id); t->cpu_id = cpu_id; if (!cpu_is_not_allowed(cpu_id)) { if (c->base_cpu < 0) c->base_cpu = t->cpu_id; - if (p->base_cpu < 0) - p->base_cpu = t->cpu_id; + if (pkg_base[pkg_id].base_cpu < 0) + pkg_base[pkg_id].base_cpu = t->cpu_id; } c->core_id = core_id; - p->package_id = pkg_id; + pkg_base[pkg_id].package_id = pkg_id; } int initialize_counters(int cpu_id) @@ -9121,7 +9398,7 @@ void allocate_irq_buffers(void) err(-1, "calloc %d NMI", topo.max_cpu_num + 1); } -int update_topo(struct thread_data *t, struct core_data *c, struct pkg_data *p) +int update_topo(PER_THREAD_PARAMS) { topo.allowed_cpus++; if ((int)t->cpu_id == c->base_cpu) @@ -9189,7 +9466,7 @@ void check_msr_access(void) void check_perf_access(void) { if (no_perf || !BIC_IS_ENABLED(BIC_IPC) || !has_instr_count_access()) - bic_enabled &= ~BIC_IPC; + CLR_BIC(BIC_IPC, &bic_enabled); } bool perf_has_hybrid_devices(void) @@ -9758,8 +10035,8 @@ void turbostat_init() * disable more BICs, since it can't be reported accurately. */ if (platform->enable_tsc_tweak && !has_base_hz) { - bic_enabled &= ~BIC_Busy; - bic_enabled &= ~BIC_Bzy_MHz; + CLR_BIC(BIC_Busy, &bic_enabled); + CLR_BIC(BIC_Bzy_MHz, &bic_enabled); } } @@ -9817,6 +10094,7 @@ int fork_it(char **argv) timersub(&tv_odd, &tv_even, &tv_delta); if (for_all_cpus_2(delta_cpu, ODD_COUNTERS, EVEN_COUNTERS)) fprintf(outf, "%s: Counter reset detected\n", progname); + delta_platform(&platform_counters_odd, &platform_counters_even); compute_average(EVEN_COUNTERS); format_all_counters(EVEN_COUNTERS); @@ -9848,7 +10126,7 @@ int get_and_dump_counters(void) void print_version() { - fprintf(outf, "turbostat version 2025.06.08 - Len Brown <lenb@kernel.org>\n"); + fprintf(outf, "turbostat version 2025.09.09 - Len Brown <lenb@kernel.org>\n"); } #define COMMAND_LINE_SIZE 2048 @@ -10145,6 +10423,10 @@ void parse_add_command_msr(char *add_command) format = FORMAT_RAW; goto next; } + if (!strncmp(add_command, "average", strlen("average"))) { + format = FORMAT_AVERAGE; + goto next; + } if (!strncmp(add_command, "delta", strlen("delta"))) { format = FORMAT_DELTA; goto next; @@ -10417,13 +10699,19 @@ next: has_format = true; } + if (strcmp("average", format_name) == 0) { + format = FORMAT_AVERAGE; + has_format = true; + } + if (strcmp("delta", format_name) == 0) { format = FORMAT_DELTA; has_format = true; } if (!has_format) { - fprintf(stderr, "%s: Invalid format %s. Expected raw or delta\n", __func__, format_name); + fprintf(stderr, "%s: Invalid format %s. Expected raw, average or delta\n", + __func__, format_name); exit(1); } } @@ -10513,8 +10801,10 @@ int is_deferred_add(char *name) int i; for (i = 0; i < deferred_add_index; ++i) - if (!strcmp(name, deferred_add_names[i])) + if (!strcmp(name, deferred_add_names[i])) { + deferred_add_consumed |= (1 << i); return 1; + } return 0; } @@ -10523,11 +10813,34 @@ int is_deferred_skip(char *name) int i; for (i = 0; i < deferred_skip_index; ++i) - if (!strcmp(name, deferred_skip_names[i])) + if (!strcmp(name, deferred_skip_names[i])) { + deferred_skip_consumed |= (1 << i); return 1; + } return 0; } +void verify_deferred_consumed(void) +{ + int i; + int fail = 0; + + for (i = 0; i < deferred_add_index; ++i) { + if (!(deferred_add_consumed & (1 << i))) { + warnx("Counter '%s' can not be added.", deferred_add_names[i]); + fail++; + } + } + for (i = 0; i < deferred_skip_index; ++i) { + if (!(deferred_skip_consumed & (1 << i))) { + warnx("Counter '%s' can not be skipped.", deferred_skip_names[i]); + fail++; + } + } + if (fail) + exit(-EINVAL); +} + void probe_cpuidle_residency(void) { char path[64]; @@ -10537,9 +10850,6 @@ void probe_cpuidle_residency(void) int min_state = 1024, max_state = 0; char *sp; - if (!DO_BIC(BIC_pct_idle)) - return; - for (state = 10; state >= 0; --state) { sprintf(path, "/sys/devices/system/cpu/cpu%d/cpuidle/state%d/name", base_cpu, state); @@ -10752,22 +11062,29 @@ void cmdline(int argc, char **argv) no_perf = 1; break; case 'e': - /* --enable specified counter */ - bic_enabled = bic_enabled | bic_lookup(optarg, SHOW_LIST); + /* --enable specified counter, without clearning existing list */ + bic_lookup(&bic_enabled, optarg, SHOW_LIST); break; case 'f': force_load++; break; case 'd': debug++; - ENABLE_BIC(BIC_DISABLED_BY_DEFAULT); + bic_set_all(&bic_enabled); break; case 'H': /* * --hide: do not show those specified * multiple invocations simply clear more bits in enabled mask */ - bic_enabled &= ~bic_lookup(optarg, HIDE_LIST); + { + cpu_set_t bic_group_hide; + + BIC_INIT(&bic_group_hide); + + bic_lookup(&bic_group_hide, optarg, HIDE_LIST); + bic_clear_bits(&bic_enabled, &bic_group_hide); + } break; case 'h': default: @@ -10791,7 +11108,7 @@ void cmdline(int argc, char **argv) rapl_joules++; break; case 'l': - ENABLE_BIC(BIC_DISABLED_BY_DEFAULT); + bic_set_all(&bic_enabled); list_header_only++; quiet++; break; @@ -10828,9 +11145,8 @@ void cmdline(int argc, char **argv) * subsequent invocations can add to it. */ if (shown == 0) - bic_enabled = bic_lookup(optarg, SHOW_LIST); - else - bic_enabled |= bic_lookup(optarg, SHOW_LIST); + BIC_INIT(&bic_enabled); + bic_lookup(&bic_enabled, optarg, SHOW_LIST); shown = 1; break; case 'S': @@ -10867,6 +11183,8 @@ int main(int argc, char **argv) { int fd, ret; + bic_groups_init(); + fd = open("/sys/fs/cgroup/cgroup.procs", O_WRONLY); if (fd < 0) goto skip_cgroup_setting; @@ -10889,6 +11207,8 @@ skip_cgroup_setting: probe_cpuidle_residency(); probe_cpuidle_counts(); + verify_deferred_consumed(); + if (!getuid()) set_rlimit(); diff --git a/tools/testing/selftests/coredump/stackdump_test.c b/tools/testing/selftests/coredump/stackdump_test.c index 5a5a7a5f7e1d..a4ac80bb1003 100644 --- a/tools/testing/selftests/coredump/stackdump_test.c +++ b/tools/testing/selftests/coredump/stackdump_test.c @@ -446,9 +446,6 @@ TEST_F(coredump, socket_detect_userspace_client) if (info.coredump_mask & PIDFD_COREDUMPED) goto out; - if (read(fd_coredump, &c, 1) < 1) - goto out; - exit_code = EXIT_SUCCESS; out: if (fd_peer_pidfd >= 0) diff --git a/tools/testing/selftests/drivers/net/bonding/Makefile b/tools/testing/selftests/drivers/net/bonding/Makefile index 2b10854e4b1e..44b98f17f8ff 100644 --- a/tools/testing/selftests/drivers/net/bonding/Makefile +++ b/tools/testing/selftests/drivers/net/bonding/Makefile @@ -10,7 +10,8 @@ TEST_PROGS := \ mode-2-recovery-updelay.sh \ bond_options.sh \ bond-eth-type-change.sh \ - bond_macvlan_ipvlan.sh + bond_macvlan_ipvlan.sh \ + bond_passive_lacp.sh TEST_FILES := \ lag_lib.sh \ diff --git a/tools/testing/selftests/drivers/net/bonding/bond_passive_lacp.sh b/tools/testing/selftests/drivers/net/bonding/bond_passive_lacp.sh new file mode 100755 index 000000000000..9c3b089813df --- /dev/null +++ b/tools/testing/selftests/drivers/net/bonding/bond_passive_lacp.sh @@ -0,0 +1,105 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Test if a bond interface works with lacp_active=off. + +# shellcheck disable=SC2034 +REQUIRE_MZ=no +NUM_NETIFS=0 +lib_dir=$(dirname "$0") +# shellcheck disable=SC1091 +source "$lib_dir"/../../../net/forwarding/lib.sh + +# shellcheck disable=SC2317 +check_port_state() +{ + local netns=$1 + local port=$2 + local state=$3 + + ip -n "${netns}" -d -j link show "$port" | \ + jq -e ".[].linkinfo.info_slave_data.ad_actor_oper_port_state_str | index(\"${state}\") != null" > /dev/null +} + +check_pkt_count() +{ + RET=0 + local ns="$1" + local iface="$2" + + # wait 65s, one per 30s + slowwait_for_counter 65 2 tc_rule_handle_stats_get \ + "dev ${iface} egress" 101 ".packets" "-n ${ns}" &> /dev/null +} + +setup() { + setup_ns c_ns s_ns + + # shellcheck disable=SC2154 + ip -n "${c_ns}" link add eth0 type veth peer name eth0 netns "${s_ns}" + ip -n "${c_ns}" link add eth1 type veth peer name eth1 netns "${s_ns}" + + # Add tc filter to count the pkts + tc -n "${c_ns}" qdisc add dev eth0 clsact + tc -n "${c_ns}" filter add dev eth0 egress handle 101 protocol 0x8809 matchall action pass + tc -n "${s_ns}" qdisc add dev eth1 clsact + tc -n "${s_ns}" filter add dev eth1 egress handle 101 protocol 0x8809 matchall action pass + + ip -n "${s_ns}" link add bond0 type bond mode 802.3ad lacp_active on lacp_rate fast + ip -n "${s_ns}" link set eth0 master bond0 + ip -n "${s_ns}" link set eth1 master bond0 + + ip -n "${c_ns}" link add bond0 type bond mode 802.3ad lacp_active off lacp_rate fast + ip -n "${c_ns}" link set eth0 master bond0 + ip -n "${c_ns}" link set eth1 master bond0 + +} + +trap cleanup_all_ns EXIT +setup + +# The bond will send 2 lacpdu pkts during init time, let's wait at least 2s +# after interface up +ip -n "${c_ns}" link set bond0 up +sleep 2 + +# 1. The passive side shouldn't send LACPDU. +check_pkt_count "${c_ns}" "eth0" && RET=1 +log_test "802.3ad lacp_active off" "init port" + +ip -n "${s_ns}" link set bond0 up +# 2. The passive side should not have the 'active' flag. +RET=0 +slowwait 2 check_port_state "${c_ns}" "eth0" "active" && RET=1 +log_test "802.3ad lacp_active off" "port state active" + +# 3. The active side should have the 'active' flag. +RET=0 +slowwait 2 check_port_state "${s_ns}" "eth0" "active" || RET=1 +log_test "802.3ad lacp_active on" "port state active" + +# 4. Make sure the connection is not expired. +RET=0 +slowwait 5 check_port_state "${s_ns}" "eth0" "distributing" +slowwait 10 check_port_state "${s_ns}" "eth0" "expired" && RET=1 +log_test "bond 802.3ad lacp_active off" "port connection" + +# After testing, disconnect one port on each side to check the state. +ip -n "${s_ns}" link set eth0 nomaster +ip -n "${s_ns}" link set eth0 up +ip -n "${c_ns}" link set eth1 nomaster +ip -n "${c_ns}" link set eth1 up +# Due to Periodic Machine and Rx Machine state change, the bond will still +# send lacpdu pkts in a few seconds. sleep at lease 5s to make sure +# negotiation finished +sleep 5 + +# 5. The active side should keep sending LACPDU. +check_pkt_count "${s_ns}" "eth1" || RET=1 +log_test "bond 802.3ad lacp_active on" "port pkt after disconnect" + +# 6. The passive side shouldn't send LACPDU anymore. +check_pkt_count "${c_ns}" "eth0" && RET=1 +log_test "bond 802.3ad lacp_active off" "port pkt after disconnect" + +exit "$EXIT_STATUS" diff --git a/tools/testing/selftests/drivers/net/bonding/config b/tools/testing/selftests/drivers/net/bonding/config index dad4e5fda4db..4d16a69ffc65 100644 --- a/tools/testing/selftests/drivers/net/bonding/config +++ b/tools/testing/selftests/drivers/net/bonding/config @@ -6,6 +6,7 @@ CONFIG_MACVLAN=y CONFIG_IPVLAN=y CONFIG_NET_ACT_GACT=y CONFIG_NET_CLS_FLOWER=y +CONFIG_NET_CLS_MATCHALL=m CONFIG_NET_SCH_INGRESS=y CONFIG_NLMON=y CONFIG_VETH=y diff --git a/tools/testing/selftests/drivers/net/napi_threaded.py b/tools/testing/selftests/drivers/net/napi_threaded.py index b2698db39817..9699a100a87d 100755 --- a/tools/testing/selftests/drivers/net/napi_threaded.py +++ b/tools/testing/selftests/drivers/net/napi_threaded.py @@ -35,6 +35,8 @@ def _setup_deferred_cleanup(cfg) -> None: threaded = cmd(f"cat /sys/class/net/{cfg.ifname}/threaded").stdout defer(_set_threaded_state, cfg, threaded) + return combined + def enable_dev_threaded_disable_napi_threaded(cfg, nl) -> None: """ @@ -49,7 +51,7 @@ def enable_dev_threaded_disable_napi_threaded(cfg, nl) -> None: napi0_id = napis[0]['id'] napi1_id = napis[1]['id'] - _setup_deferred_cleanup(cfg) + qcnt = _setup_deferred_cleanup(cfg) # set threaded _set_threaded_state(cfg, 1) @@ -62,7 +64,7 @@ def enable_dev_threaded_disable_napi_threaded(cfg, nl) -> None: nl.napi_set({'id': napi1_id, 'threaded': 'disabled'}) cmd(f"ethtool -L {cfg.ifname} combined 1") - cmd(f"ethtool -L {cfg.ifname} combined 2") + cmd(f"ethtool -L {cfg.ifname} combined {qcnt}") _assert_napi_threaded_enabled(nl, napi0_id) _assert_napi_threaded_disabled(nl, napi1_id) @@ -80,7 +82,7 @@ def change_num_queues(cfg, nl) -> None: napi0_id = napis[0]['id'] napi1_id = napis[1]['id'] - _setup_deferred_cleanup(cfg) + qcnt = _setup_deferred_cleanup(cfg) # set threaded _set_threaded_state(cfg, 1) @@ -90,7 +92,7 @@ def change_num_queues(cfg, nl) -> None: _assert_napi_threaded_enabled(nl, napi1_id) cmd(f"ethtool -L {cfg.ifname} combined 1") - cmd(f"ethtool -L {cfg.ifname} combined 2") + cmd(f"ethtool -L {cfg.ifname} combined {qcnt}") # check napi threaded is set for both napis _assert_napi_threaded_enabled(nl, napi0_id) diff --git a/tools/testing/selftests/mount_setattr/mount_setattr_test.c b/tools/testing/selftests/mount_setattr/mount_setattr_test.c index b1e4618399be..a688871a98eb 100644 --- a/tools/testing/selftests/mount_setattr/mount_setattr_test.c +++ b/tools/testing/selftests/mount_setattr/mount_setattr_test.c @@ -107,6 +107,26 @@ #endif #endif +#ifndef __NR_open_tree_attr + #if defined __alpha__ + #define __NR_open_tree_attr 577 + #elif defined _MIPS_SIM + #if _MIPS_SIM == _MIPS_SIM_ABI32 /* o32 */ + #define __NR_open_tree_attr (467 + 4000) + #endif + #if _MIPS_SIM == _MIPS_SIM_NABI32 /* n32 */ + #define __NR_open_tree_attr (467 + 6000) + #endif + #if _MIPS_SIM == _MIPS_SIM_ABI64 /* n64 */ + #define __NR_open_tree_attr (467 + 5000) + #endif + #elif defined __ia64__ + #define __NR_open_tree_attr (467 + 1024) + #else + #define __NR_open_tree_attr 467 + #endif +#endif + #ifndef MOUNT_ATTR_IDMAP #define MOUNT_ATTR_IDMAP 0x00100000 #endif @@ -121,6 +141,12 @@ static inline int sys_mount_setattr(int dfd, const char *path, unsigned int flag return syscall(__NR_mount_setattr, dfd, path, flags, attr, size); } +static inline int sys_open_tree_attr(int dfd, const char *path, unsigned int flags, + struct mount_attr *attr, size_t size) +{ + return syscall(__NR_open_tree_attr, dfd, path, flags, attr, size); +} + static ssize_t write_nointr(int fd, const void *buf, size_t count) { ssize_t ret; @@ -1222,6 +1248,12 @@ TEST_F(mount_setattr_idmapped, attached_mount_inside_current_mount_namespace) attr.userns_fd = get_userns_fd(0, 10000, 10000); ASSERT_GE(attr.userns_fd, 0); ASSERT_NE(sys_mount_setattr(open_tree_fd, "", AT_EMPTY_PATH, &attr, sizeof(attr)), 0); + /* + * Make sure that open_tree_attr() without OPEN_TREE_CLONE is not a way + * to bypass this mount_setattr() restriction. + */ + ASSERT_LT(sys_open_tree_attr(open_tree_fd, "", AT_EMPTY_PATH, &attr, sizeof(attr)), 0); + ASSERT_EQ(close(attr.userns_fd), 0); ASSERT_EQ(close(open_tree_fd), 0); } @@ -1255,6 +1287,12 @@ TEST_F(mount_setattr_idmapped, attached_mount_outside_current_mount_namespace) ASSERT_GE(attr.userns_fd, 0); ASSERT_NE(sys_mount_setattr(open_tree_fd, "", AT_EMPTY_PATH, &attr, sizeof(attr)), 0); + /* + * Make sure that open_tree_attr() without OPEN_TREE_CLONE is not a way + * to bypass this mount_setattr() restriction. + */ + ASSERT_LT(sys_open_tree_attr(open_tree_fd, "", AT_EMPTY_PATH, &attr, sizeof(attr)), 0); + ASSERT_EQ(close(attr.userns_fd), 0); ASSERT_EQ(close(open_tree_fd), 0); } @@ -1321,6 +1359,19 @@ TEST_F(mount_setattr_idmapped, detached_mount_outside_current_mount_namespace) ASSERT_EQ(close(open_tree_fd), 0); } +static bool expected_uid_gid(int dfd, const char *path, int flags, + uid_t expected_uid, gid_t expected_gid) +{ + int ret; + struct stat st; + + ret = fstatat(dfd, path, &st, flags); + if (ret < 0) + return false; + + return st.st_uid == expected_uid && st.st_gid == expected_gid; +} + /** * Validate that currently changing the idmapping of an idmapped mount fails. */ @@ -1331,6 +1382,8 @@ TEST_F(mount_setattr_idmapped, change_idmapping) .attr_set = MOUNT_ATTR_IDMAP, }; + ASSERT_TRUE(expected_uid_gid(-EBADF, "/mnt/D", 0, 0, 0)); + if (!mount_setattr_supported()) SKIP(return, "mount_setattr syscall not supported"); @@ -1348,27 +1401,25 @@ TEST_F(mount_setattr_idmapped, change_idmapping) AT_EMPTY_PATH, &attr, sizeof(attr)), 0); ASSERT_EQ(close(attr.userns_fd), 0); + EXPECT_FALSE(expected_uid_gid(open_tree_fd, ".", 0, 0, 0)); + EXPECT_TRUE(expected_uid_gid(open_tree_fd, ".", 0, 10000, 10000)); + /* Change idmapping on a detached mount that is already idmapped. */ attr.userns_fd = get_userns_fd(0, 20000, 10000); ASSERT_GE(attr.userns_fd, 0); ASSERT_NE(sys_mount_setattr(open_tree_fd, "", AT_EMPTY_PATH, &attr, sizeof(attr)), 0); + /* + * Make sure that open_tree_attr() without OPEN_TREE_CLONE is not a way + * to bypass this mount_setattr() restriction. + */ + EXPECT_LT(sys_open_tree_attr(open_tree_fd, "", AT_EMPTY_PATH, &attr, sizeof(attr)), 0); + EXPECT_FALSE(expected_uid_gid(open_tree_fd, ".", 0, 20000, 20000)); + EXPECT_TRUE(expected_uid_gid(open_tree_fd, ".", 0, 10000, 10000)); + ASSERT_EQ(close(attr.userns_fd), 0); ASSERT_EQ(close(open_tree_fd), 0); } -static bool expected_uid_gid(int dfd, const char *path, int flags, - uid_t expected_uid, gid_t expected_gid) -{ - int ret; - struct stat st; - - ret = fstatat(dfd, path, &st, flags); - if (ret < 0) - return false; - - return st.st_uid == expected_uid && st.st_gid == expected_gid; -} - TEST_F(mount_setattr_idmapped, idmap_mount_tree_invalid) { int open_tree_fd = -EBADF; diff --git a/tools/testing/selftests/net/forwarding/router.sh b/tools/testing/selftests/net/forwarding/router.sh index b98ea9449b8b..dfb6646cb97b 100755 --- a/tools/testing/selftests/net/forwarding/router.sh +++ b/tools/testing/selftests/net/forwarding/router.sh @@ -18,6 +18,8 @@ # | 2001:db8:1::1/64 2001:db8:2::1/64 | # | | # +-----------------------------------------------------------------+ +# +#shellcheck disable=SC2034 # SC doesn't see our uses of global variables ALL_TESTS=" ping_ipv4 @@ -27,6 +29,7 @@ ALL_TESTS=" ipv4_sip_equal_dip ipv6_sip_equal_dip ipv4_dip_link_local + ipv4_sip_link_local " NUM_NETIFS=4 @@ -330,6 +333,32 @@ ipv4_dip_link_local() tc filter del dev $rp2 egress protocol ip pref 1 handle 101 flower } +ipv4_sip_link_local() +{ + local sip=169.254.1.1 + + RET=0 + + # Disable rpfilter to prevent packets to be dropped because of it. + sysctl_set net.ipv4.conf.all.rp_filter 0 + sysctl_set net.ipv4.conf."$rp1".rp_filter 0 + + tc filter add dev "$rp2" egress protocol ip pref 1 handle 101 \ + flower src_ip "$sip" action pass + + $MZ "$h1" -t udp "sp=54321,dp=12345" -c 5 -d 1msec -b "$rp1mac" \ + -A "$sip" -B 198.51.100.2 -q + + tc_check_packets "dev $rp2 egress" 101 5 + check_err $? "Packets were dropped" + + log_test "IPv4 source IP is link-local" + + tc filter del dev "$rp2" egress protocol ip pref 1 handle 101 flower + sysctl_restore net.ipv4.conf."$rp1".rp_filter + sysctl_restore net.ipv4.conf.all.rp_filter +} + trap cleanup EXIT setup_prepare diff --git a/tools/testing/selftests/net/forwarding/sch_ets.sh b/tools/testing/selftests/net/forwarding/sch_ets.sh index 1f6f53e284b5..6269d5e23487 100755 --- a/tools/testing/selftests/net/forwarding/sch_ets.sh +++ b/tools/testing/selftests/net/forwarding/sch_ets.sh @@ -11,6 +11,7 @@ ALL_TESTS=" ets_test_strict ets_test_mixed ets_test_dwrr + ets_test_plug classifier_mode ets_test_strict ets_test_mixed diff --git a/tools/testing/selftests/net/forwarding/sch_ets_tests.sh b/tools/testing/selftests/net/forwarding/sch_ets_tests.sh index 08240d3e3c87..79d837a2868a 100644 --- a/tools/testing/selftests/net/forwarding/sch_ets_tests.sh +++ b/tools/testing/selftests/net/forwarding/sch_ets_tests.sh @@ -224,3 +224,11 @@ ets_test_dwrr() ets_set_dwrr_two_bands xfail_on_slow ets_dwrr_test_01 } + +ets_test_plug() +{ + ets_change_qdisc $put 2 "3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3" "1514 1514" + tc qdisc add dev $put handle 20: parent 10:4 plug + start_traffic_pktsize 100 $h1.10 192.0.2.1 192.0.2.2 00:c1:a0:c1:a0:00 "-c 1" + ets_qdisc_setup $put 2 +} diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.c b/tools/testing/selftests/net/mptcp/mptcp_connect.c index ac1349c4b9e5..4f07ac9fa207 100644 --- a/tools/testing/selftests/net/mptcp/mptcp_connect.c +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.c @@ -183,9 +183,10 @@ static void xgetaddrinfo(const char *node, const char *service, struct addrinfo *hints, struct addrinfo **res) { -again: - int err = getaddrinfo(node, service, hints, res); + int err; +again: + err = getaddrinfo(node, service, hints, res); if (err) { const char *errstr; diff --git a/tools/testing/selftests/net/mptcp/mptcp_inq.c b/tools/testing/selftests/net/mptcp/mptcp_inq.c index 3cf1e2a612ce..f3bcaa48df8f 100644 --- a/tools/testing/selftests/net/mptcp/mptcp_inq.c +++ b/tools/testing/selftests/net/mptcp/mptcp_inq.c @@ -75,9 +75,10 @@ static void xgetaddrinfo(const char *node, const char *service, struct addrinfo *hints, struct addrinfo **res) { -again: - int err = getaddrinfo(node, service, hints, res); + int err; +again: + err = getaddrinfo(node, service, hints, res); if (err) { const char *errstr; diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index b8af65373b3a..82cae37d9c20 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -3842,6 +3842,7 @@ endpoint_tests() # remove and re-add if reset_with_events "delete re-add signal" && mptcp_lib_kallsyms_has "subflow_rebuild_header$"; then + ip netns exec $ns1 sysctl -q net.mptcp.add_addr_timeout=0 pm_nl_set_limits $ns1 0 3 pm_nl_set_limits $ns2 3 3 pm_nl_add_endpoint $ns1 10.0.2.1 id 1 flags signal diff --git a/tools/testing/selftests/net/mptcp/mptcp_sockopt.c b/tools/testing/selftests/net/mptcp/mptcp_sockopt.c index 9934a68df237..e934dd26a59d 100644 --- a/tools/testing/selftests/net/mptcp/mptcp_sockopt.c +++ b/tools/testing/selftests/net/mptcp/mptcp_sockopt.c @@ -162,9 +162,10 @@ static void xgetaddrinfo(const char *node, const char *service, struct addrinfo *hints, struct addrinfo **res) { -again: - int err = getaddrinfo(node, service, hints, res); + int err; +again: + err = getaddrinfo(node, service, hints, res); if (err) { const char *errstr; diff --git a/tools/testing/selftests/net/mptcp/pm_netlink.sh b/tools/testing/selftests/net/mptcp/pm_netlink.sh index 2e6648a2b2c0..ac7ec6f94023 100755 --- a/tools/testing/selftests/net/mptcp/pm_netlink.sh +++ b/tools/testing/selftests/net/mptcp/pm_netlink.sh @@ -198,6 +198,7 @@ set_limits 1 9 2>/dev/null check "get_limits" "${default_limits}" "subflows above hard limit" set_limits 8 8 +flush_endpoint ## to make sure it doesn't affect the limits check "get_limits" "$(format_limits 8 8)" "set limits" flush_endpoint diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c index 5ded3b3a7538..0f5640d8dc7f 100644 --- a/tools/testing/selftests/net/tls.c +++ b/tools/testing/selftests/net/tls.c @@ -181,13 +181,12 @@ static int tls_send_cmsg(int fd, unsigned char record_type, return sendmsg(fd, &msg, flags); } -static int tls_recv_cmsg(struct __test_metadata *_metadata, - int fd, unsigned char record_type, - void *data, size_t len, int flags) +static int __tls_recv_cmsg(struct __test_metadata *_metadata, + int fd, unsigned char *ctype, + void *data, size_t len, int flags) { char cbuf[CMSG_SPACE(sizeof(char))]; struct cmsghdr *cmsg; - unsigned char ctype; struct msghdr msg; struct iovec vec; int n; @@ -206,7 +205,20 @@ static int tls_recv_cmsg(struct __test_metadata *_metadata, EXPECT_NE(cmsg, NULL); EXPECT_EQ(cmsg->cmsg_level, SOL_TLS); EXPECT_EQ(cmsg->cmsg_type, TLS_GET_RECORD_TYPE); - ctype = *((unsigned char *)CMSG_DATA(cmsg)); + if (ctype) + *ctype = *((unsigned char *)CMSG_DATA(cmsg)); + + return n; +} + +static int tls_recv_cmsg(struct __test_metadata *_metadata, + int fd, unsigned char record_type, + void *data, size_t len, int flags) +{ + unsigned char ctype; + int n; + + n = __tls_recv_cmsg(_metadata, fd, &ctype, data, len, flags); EXPECT_EQ(ctype, record_type); return n; @@ -2164,6 +2176,284 @@ TEST_F(tls, rekey_poll_delay) } } +struct raw_rec { + unsigned int plain_len; + unsigned char plain_data[100]; + unsigned int cipher_len; + unsigned char cipher_data[128]; +}; + +/* TLS 1.2, AES_CCM, data, seqno:0, plaintext: 'Hello world' */ +static const struct raw_rec id0_data_l11 = { + .plain_len = 11, + .plain_data = { + 0x48, 0x65, 0x6c, 0x6c, 0x6f, 0x20, 0x77, 0x6f, + 0x72, 0x6c, 0x64, + }, + .cipher_len = 40, + .cipher_data = { + 0x17, 0x03, 0x03, 0x00, 0x23, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x26, 0xa2, 0x33, + 0xde, 0x8d, 0x94, 0xf0, 0x29, 0x6c, 0xb1, 0xaf, + 0x6a, 0x75, 0xb2, 0x93, 0xad, 0x45, 0xd5, 0xfd, + 0x03, 0x51, 0x57, 0x8f, 0xf9, 0xcc, 0x3b, 0x42, + }, +}; + +/* TLS 1.2, AES_CCM, ctrl, seqno:0, plaintext: '' */ +static const struct raw_rec id0_ctrl_l0 = { + .plain_len = 0, + .plain_data = { + }, + .cipher_len = 29, + .cipher_data = { + 0x16, 0x03, 0x03, 0x00, 0x18, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x13, 0x38, 0x7b, + 0xa6, 0x1c, 0xdd, 0xa7, 0x19, 0x33, 0xab, 0xae, + 0x88, 0xe1, 0xd2, 0x08, 0x4f, + }, +}; + +/* TLS 1.2, AES_CCM, data, seqno:0, plaintext: '' */ +static const struct raw_rec id0_data_l0 = { + .plain_len = 0, + .plain_data = { + }, + .cipher_len = 29, + .cipher_data = { + 0x17, 0x03, 0x03, 0x00, 0x18, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x00, 0xc5, 0x37, 0x90, + 0x70, 0x45, 0x89, 0xfb, 0x5c, 0xc7, 0x89, 0x03, + 0x68, 0x80, 0xd3, 0xd8, 0xcc, + }, +}; + +/* TLS 1.2, AES_CCM, data, seqno:1, plaintext: 'Hello world' */ +static const struct raw_rec id1_data_l11 = { + .plain_len = 11, + .plain_data = { + 0x48, 0x65, 0x6c, 0x6c, 0x6f, 0x20, 0x77, 0x6f, + 0x72, 0x6c, 0x64, + }, + .cipher_len = 40, + .cipher_data = { + 0x17, 0x03, 0x03, 0x00, 0x23, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x01, 0x3a, 0x1a, 0x9c, + 0xd0, 0xa8, 0x9a, 0xd6, 0x69, 0xd6, 0x1a, 0xe3, + 0xb5, 0x1f, 0x0d, 0x2c, 0xe2, 0x97, 0x46, 0xff, + 0x2b, 0xcc, 0x5a, 0xc4, 0xa3, 0xb9, 0xef, 0xba, + }, +}; + +/* TLS 1.2, AES_CCM, ctrl, seqno:1, plaintext: '' */ +static const struct raw_rec id1_ctrl_l0 = { + .plain_len = 0, + .plain_data = { + }, + .cipher_len = 29, + .cipher_data = { + 0x16, 0x03, 0x03, 0x00, 0x18, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x01, 0x3e, 0xf0, 0xfe, + 0xee, 0xd9, 0xe2, 0x5d, 0xc7, 0x11, 0x4c, 0xe6, + 0xb4, 0x7e, 0xef, 0x40, 0x2b, + }, +}; + +/* TLS 1.2, AES_CCM, data, seqno:1, plaintext: '' */ +static const struct raw_rec id1_data_l0 = { + .plain_len = 0, + .plain_data = { + }, + .cipher_len = 29, + .cipher_data = { + 0x17, 0x03, 0x03, 0x00, 0x18, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x01, 0xce, 0xfc, 0x86, + 0xc8, 0xf0, 0x55, 0xf9, 0x47, 0x3f, 0x74, 0xdc, + 0xc9, 0xbf, 0xfe, 0x5b, 0xb1, + }, +}; + +/* TLS 1.2, AES_CCM, ctrl, seqno:2, plaintext: 'Hello world' */ +static const struct raw_rec id2_ctrl_l11 = { + .plain_len = 11, + .plain_data = { + 0x48, 0x65, 0x6c, 0x6c, 0x6f, 0x20, 0x77, 0x6f, + 0x72, 0x6c, 0x64, + }, + .cipher_len = 40, + .cipher_data = { + 0x16, 0x03, 0x03, 0x00, 0x23, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x02, 0xe5, 0x3d, 0x19, + 0x3d, 0xca, 0xb8, 0x16, 0xb6, 0xff, 0x79, 0x87, + 0x2a, 0x04, 0x11, 0x3d, 0xf8, 0x64, 0x5f, 0x36, + 0x8b, 0xa8, 0xee, 0x4c, 0x6d, 0x62, 0xa5, 0x00, + }, +}; + +/* TLS 1.2, AES_CCM, data, seqno:2, plaintext: 'Hello world' */ +static const struct raw_rec id2_data_l11 = { + .plain_len = 11, + .plain_data = { + 0x48, 0x65, 0x6c, 0x6c, 0x6f, 0x20, 0x77, 0x6f, + 0x72, 0x6c, 0x64, + }, + .cipher_len = 40, + .cipher_data = { + 0x17, 0x03, 0x03, 0x00, 0x23, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x02, 0xe5, 0x3d, 0x19, + 0x3d, 0xca, 0xb8, 0x16, 0xb6, 0xff, 0x79, 0x87, + 0x8e, 0xa1, 0xd0, 0xcd, 0x33, 0xb5, 0x86, 0x2b, + 0x17, 0xf1, 0x52, 0x2a, 0x55, 0x62, 0x65, 0x11, + }, +}; + +/* TLS 1.2, AES_CCM, ctrl, seqno:2, plaintext: '' */ +static const struct raw_rec id2_ctrl_l0 = { + .plain_len = 0, + .plain_data = { + }, + .cipher_len = 29, + .cipher_data = { + 0x16, 0x03, 0x03, 0x00, 0x18, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x02, 0xdc, 0x5c, 0x0e, + 0x41, 0xdd, 0xba, 0xd3, 0xcc, 0xcf, 0x6d, 0xd9, + 0x06, 0xdb, 0x79, 0xe5, 0x5d, + }, +}; + +/* TLS 1.2, AES_CCM, data, seqno:2, plaintext: '' */ +static const struct raw_rec id2_data_l0 = { + .plain_len = 0, + .plain_data = { + }, + .cipher_len = 29, + .cipher_data = { + 0x17, 0x03, 0x03, 0x00, 0x18, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x02, 0xc3, 0xca, 0x26, + 0x22, 0xe4, 0x25, 0xfb, 0x5f, 0x6d, 0xbf, 0x83, + 0x30, 0x48, 0x69, 0x1a, 0x47, + }, +}; + +FIXTURE(zero_len) +{ + int fd, cfd; + bool notls; +}; + +FIXTURE_VARIANT(zero_len) +{ + const struct raw_rec *recs[4]; + ssize_t recv_ret[4]; +}; + +FIXTURE_VARIANT_ADD(zero_len, data_data_data) +{ + .recs = { &id0_data_l11, &id1_data_l11, &id2_data_l11, }, + .recv_ret = { 33, -EAGAIN, }, +}; + +FIXTURE_VARIANT_ADD(zero_len, data_0ctrl_data) +{ + .recs = { &id0_data_l11, &id1_ctrl_l0, &id2_data_l11, }, + .recv_ret = { 11, 0, 11, -EAGAIN, }, +}; + +FIXTURE_VARIANT_ADD(zero_len, 0data_0data_0data) +{ + .recs = { &id0_data_l0, &id1_data_l0, &id2_data_l0, }, + .recv_ret = { -EAGAIN, }, +}; + +FIXTURE_VARIANT_ADD(zero_len, 0data_0data_ctrl) +{ + .recs = { &id0_data_l0, &id1_data_l0, &id2_ctrl_l11, }, + .recv_ret = { 0, 11, -EAGAIN, }, +}; + +FIXTURE_VARIANT_ADD(zero_len, 0data_0data_0ctrl) +{ + .recs = { &id0_data_l0, &id1_data_l0, &id2_ctrl_l0, }, + .recv_ret = { 0, 0, -EAGAIN, }, +}; + +FIXTURE_VARIANT_ADD(zero_len, 0ctrl_0ctrl_0ctrl) +{ + .recs = { &id0_ctrl_l0, &id1_ctrl_l0, &id2_ctrl_l0, }, + .recv_ret = { 0, 0, 0, -EAGAIN, }, +}; + +FIXTURE_VARIANT_ADD(zero_len, 0data_0data_data) +{ + .recs = { &id0_data_l0, &id1_data_l0, &id2_data_l11, }, + .recv_ret = { 11, -EAGAIN, }, +}; + +FIXTURE_VARIANT_ADD(zero_len, data_0data_0data) +{ + .recs = { &id0_data_l11, &id1_data_l0, &id2_data_l0, }, + .recv_ret = { 11, -EAGAIN, }, +}; + +FIXTURE_SETUP(zero_len) +{ + struct tls_crypto_info_keys tls12; + int ret; + + tls_crypto_info_init(TLS_1_2_VERSION, TLS_CIPHER_AES_CCM_128, + &tls12, 0); + + ulp_sock_pair(_metadata, &self->fd, &self->cfd, &self->notls); + if (self->notls) + return; + + /* Don't install keys on fd, we'll send raw records */ + ret = setsockopt(self->cfd, SOL_TLS, TLS_RX, &tls12, tls12.len); + ASSERT_EQ(ret, 0); +} + +FIXTURE_TEARDOWN(zero_len) +{ + close(self->fd); + close(self->cfd); +} + +TEST_F(zero_len, test) +{ + const struct raw_rec *const *rec; + unsigned char buf[128]; + int rec_off; + int i; + + for (i = 0; i < 4 && variant->recs[i]; i++) + EXPECT_EQ(send(self->fd, variant->recs[i]->cipher_data, + variant->recs[i]->cipher_len, 0), + variant->recs[i]->cipher_len); + + rec = &variant->recs[0]; + rec_off = 0; + for (i = 0; i < 4; i++) { + int j, ret; + + ret = variant->recv_ret[i] >= 0 ? variant->recv_ret[i] : -1; + EXPECT_EQ(__tls_recv_cmsg(_metadata, self->cfd, NULL, + buf, sizeof(buf), MSG_DONTWAIT), ret); + if (ret == -1) + EXPECT_EQ(errno, -variant->recv_ret[i]); + if (variant->recv_ret[i] == -EAGAIN) + break; + + for (j = 0; j < ret; j++) { + while (rec_off == (*rec)->plain_len) { + rec++; + rec_off = 0; + } + EXPECT_EQ(buf[j], (*rec)->plain_data[rec_off]); + rec_off++; + } + } +}; + FIXTURE(tls_err) { int fd, cfd; @@ -2708,6 +2998,67 @@ TEST(prequeue) { close(cfd); } +TEST(data_steal) { + struct tls_crypto_info_keys tls; + char buf[20000], buf2[20000]; + struct sockaddr_in addr; + int sfd, cfd, ret, fd; + int pid, status; + socklen_t len; + + len = sizeof(addr); + memrnd(buf, sizeof(buf)); + + tls_crypto_info_init(TLS_1_2_VERSION, TLS_CIPHER_AES_GCM_256, &tls, 0); + + addr.sin_family = AF_INET; + addr.sin_addr.s_addr = htonl(INADDR_ANY); + addr.sin_port = 0; + + fd = socket(AF_INET, SOCK_STREAM, 0); + sfd = socket(AF_INET, SOCK_STREAM, 0); + + ASSERT_EQ(bind(sfd, &addr, sizeof(addr)), 0); + ASSERT_EQ(listen(sfd, 10), 0); + ASSERT_EQ(getsockname(sfd, &addr, &len), 0); + ASSERT_EQ(connect(fd, &addr, sizeof(addr)), 0); + ASSERT_GE(cfd = accept(sfd, &addr, &len), 0); + close(sfd); + + ret = setsockopt(fd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls")); + if (ret) { + ASSERT_EQ(errno, ENOENT); + SKIP(return, "no TLS support"); + } + ASSERT_EQ(setsockopt(cfd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls")), 0); + + /* Spawn a child and get it into the read wait path of the underlying + * TCP socket. + */ + pid = fork(); + ASSERT_GE(pid, 0); + if (!pid) { + EXPECT_EQ(recv(cfd, buf, sizeof(buf) / 2, MSG_WAITALL), + sizeof(buf) / 2); + exit(!__test_passed(_metadata)); + } + + usleep(10000); + ASSERT_EQ(setsockopt(fd, SOL_TLS, TLS_TX, &tls, tls.len), 0); + ASSERT_EQ(setsockopt(cfd, SOL_TLS, TLS_RX, &tls, tls.len), 0); + + EXPECT_EQ(send(fd, buf, sizeof(buf), 0), sizeof(buf)); + EXPECT_EQ(wait(&status), pid); + EXPECT_EQ(status, 0); + EXPECT_EQ(recv(cfd, buf2, sizeof(buf2), MSG_DONTWAIT), -1); + /* Don't check errno, the error will be different depending + * on what random bytes TLS interpreted as the record length. + */ + + close(fd); + close(cfd); +} + static void __attribute__((constructor)) fips_check(void) { int res; FILE *f; diff --git a/tools/testing/selftests/proc/proc-maps-race.c b/tools/testing/selftests/proc/proc-maps-race.c index 66773685a047..94bba4553130 100644 --- a/tools/testing/selftests/proc/proc-maps-race.c +++ b/tools/testing/selftests/proc/proc-maps-race.c @@ -202,11 +202,11 @@ static void print_first_lines(char *text, int nr) int offs = end - text; text[offs] = '\0'; - printf(text); + printf("%s", text); text[offs] = '\n'; printf("\n"); } else { - printf(text); + printf("%s", text); } } @@ -221,7 +221,7 @@ static void print_last_lines(char *text, int nr) nr--; start--; } - printf(start); + printf("%s", start); } static void print_boundaries(const char *title, FIXTURE_DATA(proc_maps_race) *self) diff --git a/tools/testing/selftests/sched_ext/hotplug.c b/tools/testing/selftests/sched_ext/hotplug.c index 1c9ceb661c43..0cfbb111a2d0 100644 --- a/tools/testing/selftests/sched_ext/hotplug.c +++ b/tools/testing/selftests/sched_ext/hotplug.c @@ -6,7 +6,6 @@ #include <bpf/bpf.h> #include <sched.h> #include <scx/common.h> -#include <sched.h> #include <sys/wait.h> #include <unistd.h> diff --git a/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json b/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json index 23a61e5b99d0..998e5a2f4579 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json +++ b/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json @@ -186,6 +186,204 @@ ] }, { + "id": "34c0", + "name": "Test TBF with HHF Backlog Accounting in gso_skb case against underflow", + "category": [ + "qdisc", + "tbf", + "hhf" + ], + "plugins": { + "requires": [ + "nsPlugin" + ] + }, + "setup": [ + "$IP link set dev $DUMMY up || true", + "$IP addr add 10.10.11.10/24 dev $DUMMY || true", + "$TC qdisc add dev $DUMMY root handle 1: tbf rate 8bit burst 100b latency 100ms", + "$TC qdisc replace dev $DUMMY handle 2: parent 1:1 hhf limit 1000", + [ + "ping -I $DUMMY -c2 10.10.11.11", + 1 + ], + "$TC qdisc change dev $DUMMY handle 2: parent 1:1 hhf limit 1" + ], + "cmdUnderTest": "$TC qdisc del dev $DUMMY handle 2: parent 1:1", + "expExitCode": "0", + "verifyCmd": "$TC -s qdisc show dev $DUMMY", + "matchPattern": "backlog 0b 0p", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root" + ] + }, + { + "id": "fd68", + "name": "Test TBF with CODEL Backlog Accounting in gso_skb case against underflow", + "category": [ + "qdisc", + "tbf", + "codel" + ], + "plugins": { + "requires": [ + "nsPlugin" + ] + }, + "setup": [ + "$IP link set dev $DUMMY up || true", + "$IP addr add 10.10.11.10/24 dev $DUMMY || true", + "$TC qdisc add dev $DUMMY root handle 1: tbf rate 8bit burst 100b latency 100ms", + "$TC qdisc replace dev $DUMMY handle 2: parent 1:1 codel limit 1000", + [ + "ping -I $DUMMY -c2 10.10.11.11", + 1 + ], + "$TC qdisc change dev $DUMMY handle 2: parent 1:1 codel limit 1" + ], + "cmdUnderTest": "$TC qdisc del dev $DUMMY handle 2: parent 1:1", + "expExitCode": "0", + "verifyCmd": "$TC -s qdisc show dev $DUMMY", + "matchPattern": "backlog 0b 0p", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root" + ] + }, + { + "id": "514e", + "name": "Test TBF with PIE Backlog Accounting in gso_skb case against underflow", + "category": [ + "qdisc", + "tbf", + "pie" + ], + "plugins": { + "requires": [ + "nsPlugin" + ] + }, + "setup": [ + "$IP link set dev $DUMMY up || true", + "$IP addr add 10.10.11.10/24 dev $DUMMY || true", + "$TC qdisc add dev $DUMMY root handle 1: tbf rate 8bit burst 100b latency 100ms", + "$TC qdisc replace dev $DUMMY handle 2: parent 1:1 pie limit 1000", + [ + "ping -I $DUMMY -c2 10.10.11.11", + 1 + ], + "$TC qdisc change dev $DUMMY handle 2: parent 1:1 pie limit 1" + ], + "cmdUnderTest": "$TC qdisc del dev $DUMMY handle 2: parent 1:1", + "expExitCode": "0", + "verifyCmd": "$TC -s qdisc show dev $DUMMY", + "matchPattern": "backlog 0b 0p", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root" + ] + }, + { + "id": "6c97", + "name": "Test TBF with FQ Backlog Accounting in gso_skb case against underflow", + "category": [ + "qdisc", + "tbf", + "fq" + ], + "plugins": { + "requires": [ + "nsPlugin" + ] + }, + "setup": [ + "$IP link set dev $DUMMY up || true", + "$IP addr add 10.10.11.10/24 dev $DUMMY || true", + "$TC qdisc add dev $DUMMY root handle 1: tbf rate 8bit burst 100b latency 100ms", + "$TC qdisc replace dev $DUMMY handle 2: parent 1:1 fq limit 1000", + [ + "ping -I $DUMMY -c2 10.10.11.11", + 1 + ], + "$TC qdisc change dev $DUMMY handle 2: parent 1:1 fq limit 1" + ], + "cmdUnderTest": "$TC qdisc del dev $DUMMY handle 2: parent 1:1", + "expExitCode": "0", + "verifyCmd": "$TC -s qdisc show dev $DUMMY", + "matchPattern": "backlog 0b 0p", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root" + ] + }, + { + "id": "5d0b", + "name": "Test TBF with FQ_CODEL Backlog Accounting in gso_skb case against underflow", + "category": [ + "qdisc", + "tbf", + "fq_codel" + ], + "plugins": { + "requires": [ + "nsPlugin" + ] + }, + "setup": [ + "$IP link set dev $DUMMY up || true", + "$IP addr add 10.10.11.10/24 dev $DUMMY || true", + "$TC qdisc add dev $DUMMY root handle 1: tbf rate 8bit burst 100b latency 100ms", + "$TC qdisc replace dev $DUMMY handle 2: parent 1:1 fq_codel limit 1000", + [ + "ping -I $DUMMY -c2 10.10.11.11", + 1 + ], + "$TC qdisc change dev $DUMMY handle 2: parent 1:1 fq_codel limit 1" + ], + "cmdUnderTest": "$TC qdisc del dev $DUMMY handle 2: parent 1:1", + "expExitCode": "0", + "verifyCmd": "$TC -s qdisc show dev $DUMMY", + "matchPattern": "backlog 0b 0p", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root" + ] + }, + { + "id": "21c3", + "name": "Test TBF with FQ_PIE Backlog Accounting in gso_skb case against underflow", + "category": [ + "qdisc", + "tbf", + "fq_pie" + ], + "plugins": { + "requires": [ + "nsPlugin" + ] + }, + "setup": [ + "$IP link set dev $DUMMY up || true", + "$IP addr add 10.10.11.10/24 dev $DUMMY || true", + "$TC qdisc add dev $DUMMY root handle 1: tbf rate 8bit burst 100b latency 100ms", + "$TC qdisc replace dev $DUMMY handle 2: parent 1:1 fq_pie limit 1000", + [ + "ping -I $DUMMY -c2 10.10.11.11", + 1 + ], + "$TC qdisc change dev $DUMMY handle 2: parent 1:1 fq_pie limit 1" + ], + "cmdUnderTest": "$TC qdisc del dev $DUMMY handle 2: parent 1:1", + "expExitCode": "0", + "verifyCmd": "$TC -s qdisc show dev $DUMMY", + "matchPattern": "backlog 0b 0p", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root" + ] + }, + { "id": "a4bb", "name": "Test FQ_CODEL with HTB parent - force packet drop with empty queue", "category": [ |