diff options
161 files changed, 2072 insertions, 674 deletions
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/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 daf520a13bdf..2720544cd91f 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -22174,7 +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 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/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/cpuidle/governors/menu.c b/drivers/cpuidle/governors/menu.c index 81306612a5c6..b2e3d0b0a116 100644 --- a/drivers/cpuidle/governors/menu.c +++ b/drivers/cpuidle/governors/menu.c @@ -287,20 +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 @@ -316,13 +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; @@ -354,8 +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; } 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/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c index 4cb14288ff0f..9568cc391fe3 100644 --- a/drivers/net/dsa/microchip/ksz_common.c +++ b/drivers/net/dsa/microchip/ksz_common.c @@ -2457,6 +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 2800a90fba1f..207a8bb36ae5 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -5332,7 +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. 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/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/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-thead.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-thead.c index f2946bea0bc2..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; diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.c b/drivers/net/ethernet/ti/icssg/icssg_prueth.c index 6c7d776ae4ee..dadce6009791 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_prueth.c +++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.c @@ -203,6 +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; @@ -753,6 +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; @@ -1360,8 +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) { @@ -1369,35 +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/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/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 d9f5942ccc44..792ddda1ad49 100644 --- a/drivers/net/usb/asix_devices.c +++ b/drivers/net/usb/asix_devices.c @@ -676,7 +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) | BIT(AX_EMBD_PHY_ADDR)); + 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/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/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/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 f23d75986947..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); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index d740910e071a..9e4aec7330cb 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -4189,6 +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 @@ -4289,7 +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); } @@ -6683,15 +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/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/zoned.c b/fs/btrfs/zoned.c index db11b5b5f0e6..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; } } 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; } } 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/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/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/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/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/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/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/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/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/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/core/dev.c b/net/core/dev.c index 5a3c0f40a93f..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; } 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/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/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/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/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_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/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/tls/tls_sw.c b/net/tls/tls_sw.c index 51c98a007dda..bac65d0d4e3e 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -1808,6 +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) { @@ -2051,8 +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/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/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/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."$rp1".rp_filter + sysctl_restore net.ipv4.conf.all.rp_filter +} + trap cleanup EXIT setup_prepare diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.c b/tools/testing/selftests/net/mptcp/mptcp_connect.c index ac1349c4b9e5..4f07ac9fa207 100644 --- a/tools/testing/selftests/net/mptcp/mptcp_connect.c +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.c @@ -183,9 +183,10 @@ static void xgetaddrinfo(const char *node, const char *service, struct addrinfo *hints, struct addrinfo **res) { -again: - int err = getaddrinfo(node, service, hints, res); + int err; +again: + err = getaddrinfo(node, service, hints, res); if (err) { const char *errstr; diff --git a/tools/testing/selftests/net/mptcp/mptcp_inq.c b/tools/testing/selftests/net/mptcp/mptcp_inq.c index 3cf1e2a612ce..f3bcaa48df8f 100644 --- a/tools/testing/selftests/net/mptcp/mptcp_inq.c +++ b/tools/testing/selftests/net/mptcp/mptcp_inq.c @@ -75,9 +75,10 @@ static void xgetaddrinfo(const char *node, const char *service, struct addrinfo *hints, struct addrinfo **res) { -again: - int err = getaddrinfo(node, service, hints, res); + int err; +again: + err = getaddrinfo(node, service, hints, res); if (err) { const char *errstr; diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index b8af65373b3a..82cae37d9c20 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -3842,6 +3842,7 @@ endpoint_tests() # remove and re-add if reset_with_events "delete re-add signal" && mptcp_lib_kallsyms_has "subflow_rebuild_header$"; 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 d8cfcf9bb825..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; @@ -2748,17 +3038,18 @@ TEST(data_steal) { pid = fork(); ASSERT_GE(pid, 0); if (!pid) { - EXPECT_EQ(recv(cfd, buf, sizeof(buf), MSG_WAITALL), - sizeof(buf)); + EXPECT_EQ(recv(cfd, buf, sizeof(buf) / 2, MSG_WAITALL), + sizeof(buf) / 2); exit(!__test_passed(_metadata)); } - usleep(2000); + 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)); - usleep(2000); + 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. @@ -2766,9 +3057,6 @@ TEST(data_steal) { close(fd); close(cfd); - - EXPECT_EQ(wait(&status), pid); - EXPECT_EQ(status, 0); } static void __attribute__((constructor)) fips_check(void) { 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": [ |