diff --git a/Documentation/networking/bonding.rst b/Documentation/networking/bonding.rst index c0a789b00806..ab98373535ea 100644 --- a/Documentation/networking/bonding.rst +++ b/Documentation/networking/bonding.rst @@ -422,6 +422,17 @@ arp_all_targets consider the slave up only when all of the arp_ip_targets are reachable

+arp_missed_max + + Specifies the number of arp_interval monitor checks that must + fail in order for an interface to be marked down by the ARP monitor. + + In order to provide orderly failover semantics, backup interfaces + are permitted an extra monitor check (i.e., they must fail + arp_missed_max + 1 times before being marked down). + + The default value is 2, and the allowable range is 1 - 255. + downdelay

Specifies the time, in milliseconds, to wait before disabling diff --git a/Makefile b/Makefile index 576636ef2f30..d14938eed4fc 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 5 PATCHLEVEL = 15 -SUBLEVEL = 114 +SUBLEVEL = 115 EXTRAVERSION = NAME = Trick or Treat

diff --git a/drivers/android/binder.c b/drivers/android/binder.c index c8d33c5dbe29..a4749b6c3d73 100644 --- a/drivers/android/binder.c +++ b/drivers/android/binder.c @@ -1903,24 +1903,23 @@ static void binder_deferred_fd_close(int fd) static void binder_transaction_buffer_release(struct binder_proc *proc, struct binder_thread *thread, struct binder_buffer *buffer, - binder_size_t failed_at, + binder_size_t off_end_offset, bool is_failure) { int debug_id = buffer->debug_id; - binder_size_t off_start_offset, buffer_offset, off_end_offset; + binder_size_t off_start_offset, buffer_offset;

binder_debug(BINDER_DEBUG_TRANSACTION, "%d buffer release %d, size %zd-%zd, failed at %llx\n", proc->pid, buffer->debug_id, buffer->data_size, buffer->offsets_size, - (unsigned long long)failed_at); + (unsigned long long)off_end_offset);

if (buffer->target_node) binder_dec_node(buffer->target_node, 1, 0);

off_start_offset = ALIGN(buffer->data_size, sizeof(void *)); - off_end_offset = is_failure && failed_at ? failed_at : - off_start_offset + buffer->offsets_size; + for (buffer_offset = off_start_offset; buffer_offset < off_end_offset; buffer_offset += sizeof(binder_size_t)) { struct binder_object_header *hdr; @@ -2080,6 +2079,21 @@ static void binder_transaction_buffer_release(struct binder_proc *proc, } }

+/* Clean up all the objects in the buffer */ +static inline void binder_release_entire_buffer(struct binder_proc *proc, + struct binder_thread *thread, + struct binder_buffer *buffer, + bool is_failure) +{ + binder_size_t off_end_offset; + + off_end_offset = ALIGN(buffer->data_size, sizeof(void *)); + off_end_offset += buffer->offsets_size; + + binder_transaction_buffer_release(proc, thread, buffer, + off_end_offset, is_failure); +} + static int binder_translate_binder(struct flat_binder_object *fp, struct binder_transaction *t, struct binder_thread *thread) @@ -3578,7 +3592,7 @@ binder_free_buf(struct binder_proc *proc, binder_node_inner_unlock(buf_node); } trace_binder_transaction_buffer_release(buffer); - binder_transaction_buffer_release(proc, thread, buffer, 0, is_failure); + binder_release_entire_buffer(proc, thread, buffer, is_failure); binder_alloc_free_buf(&proc->alloc, buffer); }

diff --git a/drivers/android/binder_alloc.c b/drivers/android/binder_alloc.c index 6acfb896b2e5..db01c5d423e6 100644 --- a/drivers/android/binder_alloc.c +++ b/drivers/android/binder_alloc.c @@ -212,8 +212,8 @@ static int binder_update_page_range(struct binder_alloc *alloc, int allocate, mm = alloc->vma_vm_mm;

if (mm) { - mmap_read_lock(mm); - vma = vma_lookup(mm, alloc->vma_addr); + mmap_write_lock(mm); + vma = alloc->vma; }

if (!vma && need_mm) { @@ -270,7 +270,7 @@ static int binder_update_page_range(struct binder_alloc *alloc, int allocate, trace_binder_alloc_page_end(alloc, index); } if (mm) { - mmap_read_unlock(mm); + mmap_write_unlock(mm); mmput(mm); } return 0; @@ -303,35 +303,24 @@ static int binder_update_page_range(struct binder_alloc *alloc, int allocate, } err_no_vma: if (mm) { - mmap_read_unlock(mm); + mmap_write_unlock(mm); mmput(mm); } return vma ? -ENOMEM : -ESRCH; }

- static inline void binder_alloc_set_vma(struct binder_alloc *alloc, struct vm_area_struct *vma) { - unsigned long vm_start = 0; - - if (vma) { - vm_start = vma->vm_start; - mmap_assert_write_locked(alloc->vma_vm_mm); - } - - alloc->vma_addr = vm_start; + /* pairs with smp_load_acquire in binder_alloc_get_vma() */ + smp_store_release(&alloc->vma, vma); }

static inline struct vm_area_struct *binder_alloc_get_vma( struct binder_alloc *alloc) { - struct vm_area_struct *vma = NULL; - - if (alloc->vma_addr) - vma = vma_lookup(alloc->vma_vm_mm, alloc->vma_addr); - - return vma; + /* pairs with smp_store_release in binder_alloc_set_vma() */ + return smp_load_acquire(&alloc->vma); }

static bool debug_low_async_space_locked(struct binder_alloc *alloc, int pid) @@ -394,15 +383,13 @@ static struct binder_buffer *binder_alloc_new_buf_locked( size_t size, data_offsets_size; int ret;

- mmap_read_lock(alloc->vma_vm_mm); + /* Check binder_alloc is fully initialized */ if (!binder_alloc_get_vma(alloc)) { - mmap_read_unlock(alloc->vma_vm_mm); binder_alloc_debug(BINDER_DEBUG_USER_ERROR, "%d: binder_alloc_buf, no vma\n", alloc->pid); return ERR_PTR(-ESRCH); } - mmap_read_unlock(alloc->vma_vm_mm);

data_offsets_size = ALIGN(data_size, sizeof(void *)) + ALIGN(offsets_size, sizeof(void *)); @@ -792,6 +779,8 @@ int binder_alloc_mmap_handler(struct binder_alloc *alloc, buffer->free = 1; binder_insert_free_buffer(alloc, buffer); alloc->free_async_space = alloc->buffer_size / 2; + + /* Signal binder_alloc is fully initialized */ binder_alloc_set_vma(alloc, vma);

return 0; @@ -822,8 +811,7 @@ void binder_alloc_deferred_release(struct binder_alloc *alloc)

buffers = 0; mutex_lock(&alloc->mutex); - BUG_ON(alloc->vma_addr && - vma_lookup(alloc->vma_vm_mm, alloc->vma_addr)); + BUG_ON(alloc->vma);

while ((n = rb_first(&alloc->allocated_buffers))) { buffer = rb_entry(n, struct binder_buffer, rb_node); @@ -930,25 +918,17 @@ void binder_alloc_print_pages(struct seq_file *m, * Make sure the binder_alloc is fully initialized, otherwise we might * read inconsistent state. */ - - mmap_read_lock(alloc->vma_vm_mm); - if (binder_alloc_get_vma(alloc) == NULL) { - mmap_read_unlock(alloc->vma_vm_mm); - goto uninitialized; - } - - mmap_read_unlock(alloc->vma_vm_mm); - for (i = 0; i < alloc->buffer_size / PAGE_SIZE; i++) { - page = &alloc->pages[i]; - if (!page->page_ptr) - free++; - else if (list_empty(&page->lru)) - active++; - else - lru++; + if (binder_alloc_get_vma(alloc) != NULL) { + for (i = 0; i < alloc->buffer_size / PAGE_SIZE; i++) { + page = &alloc->pages[i]; + if (!page->page_ptr) + free++; + else if (list_empty(&page->lru)) + active++; + else + lru++; + } } - -uninitialized: mutex_unlock(&alloc->mutex); seq_printf(m, " pages: %d:%d:%d\n", active, lru, free); seq_printf(m, " pages high watermark: %zu\n", alloc->pages_high); diff --git a/drivers/android/binder_alloc.h b/drivers/android/binder_alloc.h index 1e4fd37af5e0..7dea57a84c79 100644 --- a/drivers/android/binder_alloc.h +++ b/drivers/android/binder_alloc.h @@ -100,7 +100,7 @@ struct binder_lru_page { */ struct binder_alloc { struct mutex mutex; - unsigned long vma_addr; + struct vm_area_struct *vma; struct mm_struct *vma_vm_mm; void __user *buffer; struct list_head buffers; diff --git a/drivers/android/binder_alloc_selftest.c b/drivers/android/binder_alloc_selftest.c index 43a881073a42..c2b323bc3b3a 100644 --- a/drivers/android/binder_alloc_selftest.c +++ b/drivers/android/binder_alloc_selftest.c @@ -287,7 +287,7 @@ void binder_selftest_alloc(struct binder_alloc *alloc) if (!binder_selftest_run) return; mutex_lock(&binder_selftest_lock); - if (!binder_selftest_run || !alloc->vma_addr) + if (!binder_selftest_run || !alloc->vma) goto done; pr_info("STARTED\n"); binder_selftest_alloc_offset(alloc, end_offset, 0); diff --git a/drivers/irqchip/irq-mips-gic.c b/drivers/irqchip/irq-mips-gic.c index d815285f1efe..c654fe22fcf3 100644 --- a/drivers/irqchip/irq-mips-gic.c +++ b/drivers/irqchip/irq-mips-gic.c @@ -49,7 +49,7 @@ void __iomem *mips_gic_base;

static DEFINE_PER_CPU_READ_MOSTLY(unsigned long[GIC_MAX_LONGS], pcpu_masks);

-static DEFINE_SPINLOCK(gic_lock); +static DEFINE_RAW_SPINLOCK(gic_lock); static struct irq_domain *gic_irq_domain; static int gic_shared_intrs; static unsigned int gic_cpu_pin; @@ -210,7 +210,7 @@ static int gic_set_type(struct irq_data *d, unsigned int type)

irq = GIC_HWIRQ_TO_SHARED(d->hwirq);

- spin_lock_irqsave(&gic_lock, flags); + raw_spin_lock_irqsave(&gic_lock, flags); switch (type & IRQ_TYPE_SENSE_MASK) { case IRQ_TYPE_EDGE_FALLING: pol = GIC_POL_FALLING_EDGE; @@ -250,7 +250,7 @@ static int gic_set_type(struct irq_data *d, unsigned int type) else irq_set_chip_handler_name_locked(d, &gic_level_irq_controller, handle_level_irq, NULL); - spin_unlock_irqrestore(&gic_lock, flags); + raw_spin_unlock_irqrestore(&gic_lock, flags);

return 0; } @@ -268,7 +268,7 @@ static int gic_set_affinity(struct irq_data *d, const struct cpumask *cpumask, return -EINVAL;

/* Assumption : cpumask refers to a single CPU */ - spin_lock_irqsave(&gic_lock, flags); + raw_spin_lock_irqsave(&gic_lock, flags);

/* Re-route this IRQ */ write_gic_map_vp(irq, BIT(mips_cm_vp_id(cpu))); @@ -279,7 +279,7 @@ static int gic_set_affinity(struct irq_data *d, const struct cpumask *cpumask, set_bit(irq, per_cpu_ptr(pcpu_masks, cpu));

irq_data_update_effective_affinity(d, cpumask_of(cpu)); - spin_unlock_irqrestore(&gic_lock, flags); + raw_spin_unlock_irqrestore(&gic_lock, flags);

return IRQ_SET_MASK_OK; } @@ -357,12 +357,12 @@ static void gic_mask_local_irq_all_vpes(struct irq_data *d) cd = irq_data_get_irq_chip_data(d); cd->mask = false;

- spin_lock_irqsave(&gic_lock, flags); + raw_spin_lock_irqsave(&gic_lock, flags); for_each_online_cpu(cpu) { write_gic_vl_other(mips_cm_vp_id(cpu)); write_gic_vo_rmask(BIT(intr)); } - spin_unlock_irqrestore(&gic_lock, flags); + raw_spin_unlock_irqrestore(&gic_lock, flags); }

static void gic_unmask_local_irq_all_vpes(struct irq_data *d) @@ -375,32 +375,45 @@ static void gic_unmask_local_irq_all_vpes(struct irq_data *d) cd = irq_data_get_irq_chip_data(d); cd->mask = true;

- spin_lock_irqsave(&gic_lock, flags); + raw_spin_lock_irqsave(&gic_lock, flags); for_each_online_cpu(cpu) { write_gic_vl_other(mips_cm_vp_id(cpu)); write_gic_vo_smask(BIT(intr)); } - spin_unlock_irqrestore(&gic_lock, flags); + raw_spin_unlock_irqrestore(&gic_lock, flags); }

-static void gic_all_vpes_irq_cpu_online(struct irq_data *d) +static void gic_all_vpes_irq_cpu_online(void) { - struct gic_all_vpes_chip_data *cd; - unsigned int intr; + static const unsigned int local_intrs[] = { + GIC_LOCAL_INT_TIMER, + GIC_LOCAL_INT_PERFCTR, + GIC_LOCAL_INT_FDC, + }; + unsigned long flags; + int i;

- intr = GIC_HWIRQ_TO_LOCAL(d->hwirq); - cd = irq_data_get_irq_chip_data(d); + raw_spin_lock_irqsave(&gic_lock, flags);

- write_gic_vl_map(mips_gic_vx_map_reg(intr), cd->map); - if (cd->mask) - write_gic_vl_smask(BIT(intr)); + for (i = 0; i < ARRAY_SIZE(local_intrs); i++) { + unsigned int intr = local_intrs[i]; + struct gic_all_vpes_chip_data *cd; + + if (!gic_local_irq_is_routable(intr)) + continue; + cd = &gic_all_vpes_chip_data[intr]; + write_gic_vl_map(mips_gic_vx_map_reg(intr), cd->map); + if (cd->mask) + write_gic_vl_smask(BIT(intr)); + } + + raw_spin_unlock_irqrestore(&gic_lock, flags); }

static struct irq_chip gic_all_vpes_local_irq_controller = { .name = "MIPS GIC Local", .irq_mask = gic_mask_local_irq_all_vpes, .irq_unmask = gic_unmask_local_irq_all_vpes, - .irq_cpu_online = gic_all_vpes_irq_cpu_online, };

static void __gic_irq_dispatch(void) @@ -424,11 +437,11 @@ static int gic_shared_irq_domain_map(struct irq_domain *d, unsigned int virq,

data = irq_get_irq_data(virq);

- spin_lock_irqsave(&gic_lock, flags); + raw_spin_lock_irqsave(&gic_lock, flags); write_gic_map_pin(intr, GIC_MAP_PIN_MAP_TO_PIN | gic_cpu_pin); write_gic_map_vp(intr, BIT(mips_cm_vp_id(cpu))); irq_data_update_effective_affinity(data, cpumask_of(cpu)); - spin_unlock_irqrestore(&gic_lock, flags); + raw_spin_unlock_irqrestore(&gic_lock, flags);

return 0; } @@ -481,6 +494,10 @@ static int gic_irq_domain_map(struct irq_domain *d, unsigned int virq, intr = GIC_HWIRQ_TO_LOCAL(hwirq); map = GIC_MAP_PIN_MAP_TO_PIN | gic_cpu_pin;

+ /* + * If adding support for more per-cpu interrupts, keep the the + * array in gic_all_vpes_irq_cpu_online() in sync. + */ switch (intr) { case GIC_LOCAL_INT_TIMER: /* CONFIG_MIPS_CMP workaround (see __gic_init) */ @@ -519,12 +536,12 @@ static int gic_irq_domain_map(struct irq_domain *d, unsigned int virq, if (!gic_local_irq_is_routable(intr)) return -EPERM;

- spin_lock_irqsave(&gic_lock, flags); + raw_spin_lock_irqsave(&gic_lock, flags); for_each_online_cpu(cpu) { write_gic_vl_other(mips_cm_vp_id(cpu)); write_gic_vo_map(mips_gic_vx_map_reg(intr), map); } - spin_unlock_irqrestore(&gic_lock, flags); + raw_spin_unlock_irqrestore(&gic_lock, flags);

return 0; } @@ -711,8 +728,8 @@ static int gic_cpu_startup(unsigned int cpu) /* Clear all local IRQ masks (ie. disable all local interrupts) */ write_gic_vl_rmask(~0);

- /* Invoke irq_cpu_online callbacks to enable desired interrupts */ - irq_cpu_online(); + /* Enable desired interrupts */ + gic_all_vpes_irq_cpu_online();

return 0; } diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index a2ce9f0fb43c..b4d613bdbc06 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -3145,8 +3145,8 @@ static void bond_loadbalance_arp_mon(struct bonding *bond) * when the source ip is 0, so don't take the link down * if we don't know our ip yet */ - if (!bond_time_in_interval(bond, trans_start, 2) || - !bond_time_in_interval(bond, slave->last_rx, 2)) { + if (!bond_time_in_interval(bond, trans_start, bond->params.missed_max) || + !bond_time_in_interval(bond, slave->last_rx, bond->params.missed_max)) {

bond_propose_link_state(slave, BOND_LINK_DOWN); slave_state_changed = 1; @@ -3240,7 +3240,7 @@ static int bond_ab_arp_inspect(struct bonding *bond)

/* Backup slave is down if: * - No current_arp_slave AND - * - more than 3*delta since last receive AND + * - more than (missed_max+1)*delta since last receive AND * - the bond has an IP address * * Note: a non-null current_arp_slave indicates @@ -3252,20 +3252,20 @@ static int bond_ab_arp_inspect(struct bonding *bond) */ if (!bond_is_active_slave(slave) && !rcu_access_pointer(bond->current_arp_slave) && - !bond_time_in_interval(bond, last_rx, 3)) { + !bond_time_in_interval(bond, last_rx, bond->params.missed_max + 1)) { bond_propose_link_state(slave, BOND_LINK_DOWN); commit++; }

/* Active slave is down if: - * - more than 2*delta since transmitting OR - * - (more than 2*delta since receive AND + * - more than missed_max*delta since transmitting OR + * - (more than missed_max*delta since receive AND * the bond has an IP address) */ trans_start = dev_trans_start(slave->dev); if (bond_is_active_slave(slave) && - (!bond_time_in_interval(bond, trans_start, 2) || - !bond_time_in_interval(bond, last_rx, 2))) { + (!bond_time_in_interval(bond, trans_start, bond->params.missed_max) || + !bond_time_in_interval(bond, last_rx, bond->params.missed_max))) { bond_propose_link_state(slave, BOND_LINK_DOWN); commit++; } @@ -5886,6 +5886,7 @@ static int bond_check_params(struct bond_params *params) params->arp_interval = arp_interval; params->arp_validate = arp_validate_value; params->arp_all_targets = arp_all_targets_value; + params->missed_max = 2; params->updelay = updelay; params->downdelay = downdelay; params->peer_notif_delay = 0; diff --git a/drivers/net/bonding/bond_netlink.c b/drivers/net/bonding/bond_netlink.c index 5d54e11d18fa..7398accd4680 100644 --- a/drivers/net/bonding/bond_netlink.c +++ b/drivers/net/bonding/bond_netlink.c @@ -79,6 +79,11 @@ static int bond_fill_slave_info(struct sk_buff *skb, return -EMSGSIZE; }

+/* Limit the max delay range to 300s */ +static struct netlink_range_validation delay_range = { + .max = 300000, +}; + static const struct nla_policy bond_policy[IFLA_BOND_MAX + 1] = { [IFLA_BOND_MODE] = { .type = NLA_U8 }, [IFLA_BOND_ACTIVE_SLAVE] = { .type = NLA_U32 }, @@ -109,7 +114,8 @@ static const struct nla_policy bond_policy[IFLA_BOND_MAX + 1] = { [IFLA_BOND_AD_ACTOR_SYSTEM] = { .type = NLA_BINARY, .len = ETH_ALEN }, [IFLA_BOND_TLB_DYNAMIC_LB] = { .type = NLA_U8 }, - [IFLA_BOND_PEER_NOTIF_DELAY] = { .type = NLA_U32 }, + [IFLA_BOND_PEER_NOTIF_DELAY] = NLA_POLICY_FULL_RANGE(NLA_U32, &delay_range), + [IFLA_BOND_MISSED_MAX] = { .type = NLA_U8 }, };

static const struct nla_policy bond_slave_policy[IFLA_BOND_SLAVE_MAX + 1] = { @@ -453,6 +459,15 @@ static int bond_changelink(struct net_device *bond_dev, struct nlattr *tb[], return err; }

+ if (data[IFLA_BOND_MISSED_MAX]) { + int missed_max = nla_get_u8(data[IFLA_BOND_MISSED_MAX]); + + bond_opt_initval(&newval, missed_max); + err = __bond_opt_set(bond, BOND_OPT_MISSED_MAX, &newval); + if (err) + return err; + } + return 0; }

@@ -515,6 +530,7 @@ static size_t bond_get_size(const struct net_device *bond_dev) nla_total_size(ETH_ALEN) + /* IFLA_BOND_AD_ACTOR_SYSTEM */ nla_total_size(sizeof(u8)) + /* IFLA_BOND_TLB_DYNAMIC_LB */ nla_total_size(sizeof(u32)) + /* IFLA_BOND_PEER_NOTIF_DELAY */ + nla_total_size(sizeof(u8)) + /* IFLA_BOND_MISSED_MAX */ 0; }

@@ -650,6 +666,10 @@ static int bond_fill_info(struct sk_buff *skb, bond->params.tlb_dynamic_lb)) goto nla_put_failure;

+ if (nla_put_u8(skb, IFLA_BOND_MISSED_MAX, + bond->params.missed_max)) + goto nla_put_failure; + if (BOND_MODE(bond) == BOND_MODE_8023AD) { struct ad_info info;

diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c index b93337b5a721..5f883a18bbab 100644 --- a/drivers/net/bonding/bond_options.c +++ b/drivers/net/bonding/bond_options.c @@ -78,6 +78,8 @@ static int bond_option_ad_actor_system_set(struct bonding *bond, const struct bond_opt_value *newval); static int bond_option_ad_user_port_key_set(struct bonding *bond, const struct bond_opt_value *newval); +static int bond_option_missed_max_set(struct bonding *bond, + const struct bond_opt_value *newval);

static const struct bond_opt_value bond_mode_tbl[] = { @@ -163,6 +165,12 @@ static const struct bond_opt_value bond_num_peer_notif_tbl[] = { { NULL, -1, 0} };

+static const struct bond_opt_value bond_peer_notif_delay_tbl[] = { + { "off", 0, 0}, + { "maxval", 300000, BOND_VALFLAG_MAX}, + { NULL, -1, 0} +}; + static const struct bond_opt_value bond_primary_reselect_tbl[] = { { "always", BOND_PRI_RESELECT_ALWAYS, BOND_VALFLAG_DEFAULT}, { "better", BOND_PRI_RESELECT_BETTER, 0}, @@ -213,6 +221,13 @@ static const struct bond_opt_value bond_ad_user_port_key_tbl[] = { { NULL, -1, 0}, };

+static const struct bond_opt_value bond_missed_max_tbl[] = { + { "minval", 1, BOND_VALFLAG_MIN}, + { "maxval", 255, BOND_VALFLAG_MAX}, + { "default", 2, BOND_VALFLAG_DEFAULT}, + { NULL, -1, 0}, +}; + static const struct bond_option bond_opts[BOND_OPT_LAST] = { [BOND_OPT_MODE] = { .id = BOND_OPT_MODE, @@ -270,6 +285,15 @@ static const struct bond_option bond_opts[BOND_OPT_LAST] = { .values = bond_intmax_tbl, .set = bond_option_arp_interval_set }, + [BOND_OPT_MISSED_MAX] = { + .id = BOND_OPT_MISSED_MAX, + .name = "arp_missed_max", + .desc = "Maximum number of missed ARP interval", + .unsuppmodes = BIT(BOND_MODE_8023AD) | BIT(BOND_MODE_TLB) | + BIT(BOND_MODE_ALB), + .values = bond_missed_max_tbl, + .set = bond_option_missed_max_set + }, [BOND_OPT_ARP_TARGETS] = { .id = BOND_OPT_ARP_TARGETS, .name = "arp_ip_target", @@ -449,7 +473,7 @@ static const struct bond_option bond_opts[BOND_OPT_LAST] = { .id = BOND_OPT_PEER_NOTIF_DELAY, .name = "peer_notif_delay", .desc = "Delay between each peer notification on failover event, in milliseconds", - .values = bond_intmax_tbl, + .values = bond_peer_notif_delay_tbl, .set = bond_option_peer_notif_delay_set } }; @@ -1186,6 +1210,16 @@ static int bond_option_arp_all_targets_set(struct bonding *bond, return 0; }

+static int bond_option_missed_max_set(struct bonding *bond, + const struct bond_opt_value *newval) +{ + netdev_dbg(bond->dev, "Setting missed max to %s (%llu)\n", + newval->string, newval->value); + bond->params.missed_max = newval->value; + + return 0; +} + static int bond_option_primary_set(struct bonding *bond, const struct bond_opt_value *newval) { diff --git a/drivers/net/bonding/bond_procfs.c b/drivers/net/bonding/bond_procfs.c index f3e3bfd72556..2ec11af5f0cc 100644 --- a/drivers/net/bonding/bond_procfs.c +++ b/drivers/net/bonding/bond_procfs.c @@ -115,6 +115,8 @@ static void bond_info_show_master(struct seq_file *seq)

seq_printf(seq, "ARP Polling Interval (ms): %d\n", bond->params.arp_interval); + seq_printf(seq, "ARP Missed Max: %u\n", + bond->params.missed_max);

seq_printf(seq, "ARP IP target/s (n.n.n.n form):");

diff --git a/drivers/net/bonding/bond_sysfs.c b/drivers/net/bonding/bond_sysfs.c index b9e9842fed94..22aa22f4e088 100644 --- a/drivers/net/bonding/bond_sysfs.c +++ b/drivers/net/bonding/bond_sysfs.c @@ -303,6 +303,18 @@ static ssize_t bonding_show_arp_targets(struct device *d, static DEVICE_ATTR(arp_ip_target, 0644, bonding_show_arp_targets, bonding_sysfs_store_option);

+/* Show the arp missed max. */ +static ssize_t bonding_show_missed_max(struct device *d, + struct device_attribute *attr, + char *buf) +{ + struct bonding *bond = to_bond(d); + + return sprintf(buf, "%u\n", bond->params.missed_max); +} +static DEVICE_ATTR(arp_missed_max, 0644, + bonding_show_missed_max, bonding_sysfs_store_option); + /* Show the up and down delays. */ static ssize_t bonding_show_downdelay(struct device *d, struct device_attribute *attr, @@ -779,6 +791,7 @@ static struct attribute *per_bond_attrs[] = { &dev_attr_ad_actor_sys_prio.attr, &dev_attr_ad_actor_system.attr, &dev_attr_ad_user_port_key.attr, + &dev_attr_arp_missed_max.attr, NULL, };

diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c index e7a551570cf3..4ec598efc333 100644 --- a/drivers/net/dsa/mt7530.c +++ b/drivers/net/dsa/mt7530.c @@ -1010,9 +1010,9 @@ mt753x_cpu_port_enable(struct dsa_switch *ds, int port) mt7530_write(priv, MT7530_PVC_P(port), PORT_SPEC_TAG);

- /* Disable flooding by default */ - mt7530_rmw(priv, MT7530_MFC, BC_FFP_MASK | UNM_FFP_MASK | UNU_FFP_MASK, - BC_FFP(BIT(port)) | UNM_FFP(BIT(port)) | UNU_FFP(BIT(port))); + /* Enable flooding on the CPU port */ + mt7530_set(priv, MT7530_MFC, BC_FFP(BIT(port)) | UNM_FFP(BIT(port)) | + UNU_FFP(BIT(port)));

/* Set CPU port number */ if (priv->id == ID_MT7621) @@ -2094,11 +2094,12 @@ static int mt7530_setup(struct dsa_switch *ds) { struct mt7530_priv *priv = ds->priv; + struct device_node *dn = NULL; struct device_node *phy_node; struct device_node *mac_np; struct mt7530_dummy_poll p; phy_interface_t interface; - struct device_node *dn; + struct dsa_port *cpu_dp; u32 id, val; int ret, i;

@@ -2106,7 +2107,19 @@ mt7530_setup(struct dsa_switch *ds) * controller also is the container for two GMACs nodes representing * as two netdev instances. */ - dn = dsa_to_port(ds, MT7530_CPU_PORT)->master->dev.of_node->parent; + dsa_switch_for_each_cpu_port(cpu_dp, ds) { + dn = cpu_dp->master->dev.of_node->parent; + /* It doesn't matter which CPU port is found first, + * their masters should share the same parent OF node + */ + break; + } + + if (!dn) { + dev_err(ds->dev, "parent OF node of DSA master not found"); + return -EINVAL; + } + ds->assisted_learning_on_cpu_port = true; ds->mtu_enforcement_ingress = true;

@@ -2274,13 +2287,71 @@ mt7530_setup(struct dsa_switch *ds) return 0; }

+static int +mt7531_setup_common(struct dsa_switch *ds) +{ + struct mt7530_priv *priv = ds->priv; + struct dsa_port *cpu_dp; + int ret, i; + + /* BPDU to CPU port */ + dsa_switch_for_each_cpu_port(cpu_dp, ds) { + mt7530_rmw(priv, MT7531_CFC, MT7531_CPU_PMAP_MASK, + BIT(cpu_dp->index)); + break; + } + mt7530_rmw(priv, MT753X_BPC, MT753X_BPDU_PORT_FW_MASK, + MT753X_BPDU_CPU_ONLY); + + /* Enable and reset MIB counters */ + mt7530_mib_reset(ds); + + /* Disable flooding on all ports */ + mt7530_clear(priv, MT7530_MFC, BC_FFP_MASK | UNM_FFP_MASK | + UNU_FFP_MASK); + + for (i = 0; i < MT7530_NUM_PORTS; i++) { + /* Disable forwarding by default on all ports */ + mt7530_rmw(priv, MT7530_PCR_P(i), PCR_MATRIX_MASK, + PCR_MATRIX_CLR); + + /* Disable learning by default on all ports */ + mt7530_set(priv, MT7530_PSC_P(i), SA_DIS); + + mt7530_set(priv, MT7531_DBG_CNT(i), MT7531_DIS_CLR); + + if (dsa_is_cpu_port(ds, i)) { + ret = mt753x_cpu_port_enable(ds, i); + if (ret) + return ret; + } else { + mt7530_port_disable(ds, i); + + /* Set default PVID to 0 on all user ports */ + mt7530_rmw(priv, MT7530_PPBV1_P(i), G0_PORT_VID_MASK, + G0_PORT_VID_DEF); + } + + /* Enable consistent egress tag */ + mt7530_rmw(priv, MT7530_PVC_P(i), PVC_EG_TAG_MASK, + PVC_EG_TAG(MT7530_VLAN_EG_CONSISTENT)); + } + + /* Flush the FDB table */ + ret = mt7530_fdb_cmd(priv, MT7530_FDB_FLUSH, NULL); + if (ret < 0) + return ret; + + return 0; +} + static int mt7531_setup(struct dsa_switch *ds) { struct mt7530_priv *priv = ds->priv; struct mt7530_dummy_poll p; u32 val, id; - int ret, i; + int ret;

/* Reset whole chip through gpio pin or memory-mapped registers for * different type of hardware @@ -2352,41 +2423,7 @@ mt7531_setup(struct dsa_switch *ds) mt7531_ind_c45_phy_write(priv, MT753X_CTRL_PHY_ADDR, MDIO_MMD_VEND2, CORE_PLL_GROUP4, val);

- /* BPDU to CPU port */ - mt7530_rmw(priv, MT7531_CFC, MT7531_CPU_PMAP_MASK, - BIT(MT7530_CPU_PORT)); - mt7530_rmw(priv, MT753X_BPC, MT753X_BPDU_PORT_FW_MASK, - MT753X_BPDU_CPU_ONLY); - - /* Enable and reset MIB counters */ - mt7530_mib_reset(ds); - - for (i = 0; i < MT7530_NUM_PORTS; i++) { - /* Disable forwarding by default on all ports */ - mt7530_rmw(priv, MT7530_PCR_P(i), PCR_MATRIX_MASK, - PCR_MATRIX_CLR); - - /* Disable learning by default on all ports */ - mt7530_set(priv, MT7530_PSC_P(i), SA_DIS); - - mt7530_set(priv, MT7531_DBG_CNT(i), MT7531_DIS_CLR); - - if (dsa_is_cpu_port(ds, i)) { - ret = mt753x_cpu_port_enable(ds, i); - if (ret) - return ret; - } else { - mt7530_port_disable(ds, i); - - /* Set default PVID to 0 on all user ports */ - mt7530_rmw(priv, MT7530_PPBV1_P(i), G0_PORT_VID_MASK, - G0_PORT_VID_DEF); - } - - /* Enable consistent egress tag */ - mt7530_rmw(priv, MT7530_PVC_P(i), PVC_EG_TAG_MASK, - PVC_EG_TAG(MT7530_VLAN_EG_CONSISTENT)); - } + mt7531_setup_common(ds);

/* Setup VLAN ID 0 for VLAN-unaware bridges */ ret = mt7530_setup_vlan0(priv); @@ -2396,11 +2433,6 @@ mt7531_setup(struct dsa_switch *ds) ds->assisted_learning_on_cpu_port = true; ds->mtu_enforcement_ingress = true;

- /* Flush the FDB table */ - ret = mt7530_fdb_cmd(priv, MT7530_FDB_FLUSH, NULL); - if (ret < 0) - return ret; - return 0; }

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c index 3a86f66d1295..ee95cc3a0378 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c @@ -126,6 +126,8 @@ static bool mlx5e_ptp_poll_ts_cq(struct mlx5e_cq *cq, int budget) /* ensure cq space is freed before enabling more cqes */ wmb();

+ mlx5e_txqsq_wake(&ptpsq->txqsq); + return work_done == budget; }

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h index f5c872043bcb..cf62d1f6d7f2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h @@ -172,6 +172,8 @@ static inline u16 mlx5e_txqsq_get_next_pi(struct mlx5e_txqsq *sq, u16 size) return pi; }

+void mlx5e_txqsq_wake(struct mlx5e_txqsq *sq); + struct mlx5e_icosq_wqe_info { u8 wqe_type; u8 num_wqebbs; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 9ea4281a55b8..5cef556223e2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -1308,11 +1308,9 @@ bool mlx5e_tc_is_vf_tunnel(struct net_device *out_dev, struct net_device *route_ int mlx5e_tc_query_route_vport(struct net_device *out_dev, struct net_device *route_dev, u16 *vport) { struct mlx5e_priv *out_priv, *route_priv; - struct mlx5_devcom *devcom = NULL; struct mlx5_core_dev *route_mdev; struct mlx5_eswitch *esw; u16 vhca_id; - int err;

out_priv = netdev_priv(out_dev); esw = out_priv->mdev->priv.eswitch; @@ -1321,6 +1319,9 @@ int mlx5e_tc_query_route_vport(struct net_device *out_dev, struct net_device *ro

vhca_id = MLX5_CAP_GEN(route_mdev, vhca_id); if (mlx5_lag_is_active(out_priv->mdev)) { + struct mlx5_devcom *devcom; + int err; + /* In lag case we may get devices from different eswitch instances. * If we failed to get vport num, it means, mostly, that we on the wrong * eswitch. @@ -1329,16 +1330,16 @@ int mlx5e_tc_query_route_vport(struct net_device *out_dev, struct net_device *ro if (err != -ENOENT) return err;

+ rcu_read_lock(); devcom = out_priv->mdev->priv.devcom; - esw = mlx5_devcom_get_peer_data(devcom, MLX5_DEVCOM_ESW_OFFLOADS); - if (!esw) - return -ENODEV; + esw = mlx5_devcom_get_peer_data_rcu(devcom, MLX5_DEVCOM_ESW_OFFLOADS); + err = esw ? mlx5_eswitch_vhca_id_to_vport(esw, vhca_id, vport) : -ENODEV; + rcu_read_unlock(); + + return err; }

- err = mlx5_eswitch_vhca_id_to_vport(esw, vhca_id, vport); - if (devcom) - mlx5_devcom_release_peer_data(devcom, MLX5_DEVCOM_ESW_OFFLOADS); - return err; + return mlx5_eswitch_vhca_id_to_vport(esw, vhca_id, vport); }

int mlx5e_tc_add_flow_mod_hdr(struct mlx5e_priv *priv, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c index e18fa5ae0fd8..6813279b57f8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c @@ -810,6 +810,17 @@ static void mlx5e_tx_wi_consume_fifo_skbs(struct mlx5e_txqsq *sq, struct mlx5e_t } }

+void mlx5e_txqsq_wake(struct mlx5e_txqsq *sq) +{ + if (netif_tx_queue_stopped(sq->txq) && + mlx5e_wqc_has_room_for(&sq->wq, sq->cc, sq->pc, sq->stop_room) && + mlx5e_ptpsq_fifo_has_room(sq) && + !test_bit(MLX5E_SQ_STATE_RECOVERING, &sq->state)) { + netif_tx_wake_queue(sq->txq); + sq->stats->wake++; + } +} + bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget) { struct mlx5e_sq_stats *stats; @@ -909,13 +920,7 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget)

netdev_tx_completed_queue(sq->txq, npkts, nbytes);

- if (netif_tx_queue_stopped(sq->txq) && - mlx5e_wqc_has_room_for(&sq->wq, sq->cc, sq->pc, sq->stop_room) && - mlx5e_ptpsq_fifo_has_room(sq) && - !test_bit(MLX5E_SQ_STATE_RECOVERING, &sq->state)) { - netif_tx_wake_queue(sq->txq); - stats->wake++; - } + mlx5e_txqsq_wake(sq);

return (i == MLX5E_TX_CQ_POLL_BUDGET); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.c index abd066e95228..b7d779d08d83 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.c @@ -3,6 +3,7 @@

#include <linux/mlx5/vport.h> #include "lib/devcom.h" +#include "mlx5_core.h"

static LIST_HEAD(devcom_list);

@@ -13,8 +14,8 @@ static LIST_HEAD(devcom_list);

struct mlx5_devcom_component { struct { - void *data; - } device[MLX5_MAX_PORTS]; + void __rcu *data; + } device[MLX5_DEVCOM_PORTS_SUPPORTED];

mlx5_devcom_event_handler_t handler; struct rw_semaphore sem; @@ -25,7 +26,7 @@ struct mlx5_devcom_list { struct list_head list;

struct mlx5_devcom_component components[MLX5_DEVCOM_NUM_COMPONENTS]; - struct mlx5_core_dev *devs[MLX5_MAX_PORTS]; + struct mlx5_core_dev *devs[MLX5_DEVCOM_PORTS_SUPPORTED]; };

struct mlx5_devcom { @@ -74,13 +75,16 @@ struct mlx5_devcom *mlx5_devcom_register_device(struct mlx5_core_dev *dev)

if (!mlx5_core_is_pf(dev)) return NULL; + if (MLX5_CAP_GEN(dev, num_lag_ports) != MLX5_DEVCOM_PORTS_SUPPORTED) + return NULL;

+ mlx5_dev_list_lock(); sguid0 = mlx5_query_nic_system_image_guid(dev); list_for_each_entry(iter, &devcom_list, list) { struct mlx5_core_dev *tmp_dev = NULL;

idx = -1; - for (i = 0; i < MLX5_MAX_PORTS; i++) { + for (i = 0; i < MLX5_DEVCOM_PORTS_SUPPORTED; i++) { if (iter->devs[i]) tmp_dev = iter->devs[i]; else @@ -100,8 +104,10 @@ struct mlx5_devcom *mlx5_devcom_register_device(struct mlx5_core_dev *dev)

if (!priv) { priv = mlx5_devcom_list_alloc(); - if (!priv) - return ERR_PTR(-ENOMEM); + if (!priv) { + devcom = ERR_PTR(-ENOMEM); + goto out; + }

idx = 0; new_priv = true; @@ -112,12 +118,14 @@ struct mlx5_devcom *mlx5_devcom_register_device(struct mlx5_core_dev *dev) if (!devcom) { if (new_priv) kfree(priv); - return ERR_PTR(-ENOMEM); + devcom = ERR_PTR(-ENOMEM); + goto out; }

if (new_priv) list_add(&priv->list, &devcom_list); - +out: + mlx5_dev_list_unlock(); return devcom; }

@@ -130,20 +138,23 @@ void mlx5_devcom_unregister_device(struct mlx5_devcom *devcom) if (IS_ERR_OR_NULL(devcom)) return;

+ mlx5_dev_list_lock(); priv = devcom->priv; priv->devs[devcom->idx] = NULL;

kfree(devcom);

- for (i = 0; i < MLX5_MAX_PORTS; i++) + for (i = 0; i < MLX5_DEVCOM_PORTS_SUPPORTED; i++) if (priv->devs[i]) break;

- if (i != MLX5_MAX_PORTS) - return; + if (i != MLX5_DEVCOM_PORTS_SUPPORTED) + goto out;

list_del(&priv->list); kfree(priv); +out: + mlx5_dev_list_unlock(); }

void mlx5_devcom_register_component(struct mlx5_devcom *devcom, @@ -161,7 +172,7 @@ void mlx5_devcom_register_component(struct mlx5_devcom *devcom, comp = &devcom->priv->components[id]; down_write(&comp->sem); comp->handler = handler; - comp->device[devcom->idx].data = data; + rcu_assign_pointer(comp->device[devcom->idx].data, data); up_write(&comp->sem); }

@@ -175,8 +186,9 @@ void mlx5_devcom_unregister_component(struct mlx5_devcom *devcom,

comp = &devcom->priv->components[id]; down_write(&comp->sem); - comp->device[devcom->idx].data = NULL; + RCU_INIT_POINTER(comp->device[devcom->idx].data, NULL); up_write(&comp->sem); + synchronize_rcu(); }

int mlx5_devcom_send_event(struct mlx5_devcom *devcom, @@ -192,12 +204,15 @@ int mlx5_devcom_send_event(struct mlx5_devcom *devcom,

comp = &devcom->priv->components[id]; down_write(&comp->sem); - for (i = 0; i < MLX5_MAX_PORTS; i++) - if (i != devcom->idx && comp->device[i].data) { - err = comp->handler(event, comp->device[i].data, - event_data); + for (i = 0; i < MLX5_DEVCOM_PORTS_SUPPORTED; i++) { + void *data = rcu_dereference_protected(comp->device[i].data, + lockdep_is_held(&comp->sem)); + + if (i != devcom->idx && data) { + err = comp->handler(event, data, event_data); break; } + }

up_write(&comp->sem); return err; @@ -212,7 +227,7 @@ void mlx5_devcom_set_paired(struct mlx5_devcom *devcom, comp = &devcom->priv->components[id]; WARN_ON(!rwsem_is_locked(&comp->sem));

- comp->paired = paired; + WRITE_ONCE(comp->paired, paired); }

bool mlx5_devcom_is_paired(struct mlx5_devcom *devcom, @@ -221,7 +236,7 @@ bool mlx5_devcom_is_paired(struct mlx5_devcom *devcom, if (IS_ERR_OR_NULL(devcom)) return false;

- return devcom->priv->components[id].paired; + return READ_ONCE(devcom->priv->components[id].paired); }

void *mlx5_devcom_get_peer_data(struct mlx5_devcom *devcom, @@ -235,16 +250,38 @@ void *mlx5_devcom_get_peer_data(struct mlx5_devcom *devcom,

comp = &devcom->priv->components[id]; down_read(&comp->sem); - if (!comp->paired) { + if (!READ_ONCE(comp->paired)) { up_read(&comp->sem); return NULL; }

- for (i = 0; i < MLX5_MAX_PORTS; i++) + for (i = 0; i < MLX5_DEVCOM_PORTS_SUPPORTED; i++) if (i != devcom->idx) break;

- return comp->device[i].data; + return rcu_dereference_protected(comp->device[i].data, lockdep_is_held(&comp->sem)); +} + +void *mlx5_devcom_get_peer_data_rcu(struct mlx5_devcom *devcom, enum mlx5_devcom_components id) +{ + struct mlx5_devcom_component *comp; + int i; + + if (IS_ERR_OR_NULL(devcom)) + return NULL; + + for (i = 0; i < MLX5_DEVCOM_PORTS_SUPPORTED; i++) + if (i != devcom->idx) + break; + + comp = &devcom->priv->components[id]; + /* This can change concurrently, however 'data' pointer will remain + * valid for the duration of RCU read section. + */ + if (!READ_ONCE(comp->paired)) + return NULL; + + return rcu_dereference(comp->device[i].data); }

void mlx5_devcom_release_peer_data(struct mlx5_devcom *devcom, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.h index 939d5bf1581b..9a496f4722da 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.h @@ -6,6 +6,8 @@

#include <linux/mlx5/driver.h>

+#define MLX5_DEVCOM_PORTS_SUPPORTED 2 + enum mlx5_devcom_components { MLX5_DEVCOM_ESW_OFFLOADS,

@@ -39,6 +41,7 @@ bool mlx5_devcom_is_paired(struct mlx5_devcom *devcom,

void *mlx5_devcom_get_peer_data(struct mlx5_devcom *devcom, enum mlx5_devcom_components id); +void *mlx5_devcom_get_peer_data_rcu(struct mlx5_devcom *devcom, enum mlx5_devcom_components id); void mlx5_devcom_release_peer_data(struct mlx5_devcom *devcom, enum mlx5_devcom_components id);

diff --git a/drivers/net/phy/mscc/mscc.h b/drivers/net/phy/mscc/mscc.h index a50235fdf7d9..055e4ca5b3b5 100644 --- a/drivers/net/phy/mscc/mscc.h +++ b/drivers/net/phy/mscc/mscc.h @@ -179,6 +179,7 @@ enum rgmii_clock_delay { #define VSC8502_RGMII_CNTL 20 #define VSC8502_RGMII_RX_DELAY_MASK 0x0070 #define VSC8502_RGMII_TX_DELAY_MASK 0x0007 +#define VSC8502_RGMII_RX_CLK_DISABLE 0x0800

#define MSCC_PHY_WOL_LOWER_MAC_ADDR 21 #define MSCC_PHY_WOL_MID_MAC_ADDR 22 diff --git a/drivers/net/phy/mscc/mscc_main.c b/drivers/net/phy/mscc/mscc_main.c index 74f3aa752724..cef43b1344a9 100644 --- a/drivers/net/phy/mscc/mscc_main.c +++ b/drivers/net/phy/mscc/mscc_main.c @@ -527,14 +527,27 @@ static int vsc85xx_mac_if_set(struct phy_device *phydev, * * 2.0 ns (which causes the data to be sampled at exactly half way between * clock transitions at 1000 Mbps) if delays should be enabled */ -static int vsc85xx_rgmii_set_skews(struct phy_device *phydev, u32 rgmii_cntl, - u16 rgmii_rx_delay_mask, - u16 rgmii_tx_delay_mask) +static int vsc85xx_update_rgmii_cntl(struct phy_device *phydev, u32 rgmii_cntl, + u16 rgmii_rx_delay_mask, + u16 rgmii_tx_delay_mask) { u16 rgmii_rx_delay_pos = ffs(rgmii_rx_delay_mask) - 1; u16 rgmii_tx_delay_pos = ffs(rgmii_tx_delay_mask) - 1; u16 reg_val = 0; - int rc; + u16 mask = 0; + int rc = 0; + + /* For traffic to pass, the VSC8502 family needs the RX_CLK disable bit + * to be unset for all PHY modes, so do that as part of the paged + * register modification. + * For some family members (like VSC8530/31/40/41) this bit is reserved + * and read-only, and the RX clock is enabled by default. + */ + if (rgmii_cntl == VSC8502_RGMII_CNTL) + mask |= VSC8502_RGMII_RX_CLK_DISABLE; + + if (phy_interface_is_rgmii(phydev)) + mask |= rgmii_rx_delay_mask | rgmii_tx_delay_mask;

mutex_lock(&phydev->lock);

@@ -545,10 +558,9 @@ static int vsc85xx_rgmii_set_skews(struct phy_device *phydev, u32 rgmii_cntl, phydev->interface == PHY_INTERFACE_MODE_RGMII_ID) reg_val |= RGMII_CLK_DELAY_2_0_NS << rgmii_tx_delay_pos;

- rc = phy_modify_paged(phydev, MSCC_PHY_PAGE_EXTENDED_2, - rgmii_cntl, - rgmii_rx_delay_mask | rgmii_tx_delay_mask, - reg_val); + if (mask) + rc = phy_modify_paged(phydev, MSCC_PHY_PAGE_EXTENDED_2, + rgmii_cntl, mask, reg_val);

mutex_unlock(&phydev->lock);

@@ -557,19 +569,11 @@ static int vsc85xx_rgmii_set_skews(struct phy_device *phydev, u32 rgmii_cntl,

static int vsc85xx_default_config(struct phy_device *phydev) { - int rc; - phydev->mdix_ctrl = ETH_TP_MDI_AUTO;

- if (phy_interface_mode_is_rgmii(phydev->interface)) { - rc = vsc85xx_rgmii_set_skews(phydev, VSC8502_RGMII_CNTL, - VSC8502_RGMII_RX_DELAY_MASK, - VSC8502_RGMII_TX_DELAY_MASK); - if (rc) - return rc; - } - - return 0; + return vsc85xx_update_rgmii_cntl(phydev, VSC8502_RGMII_CNTL, + VSC8502_RGMII_RX_DELAY_MASK, + VSC8502_RGMII_TX_DELAY_MASK); }

static int vsc85xx_get_tunable(struct phy_device *phydev, @@ -1766,13 +1770,11 @@ static int vsc8584_config_init(struct phy_device *phydev) if (ret) return ret;

- if (phy_interface_is_rgmii(phydev)) { - ret = vsc85xx_rgmii_set_skews(phydev, VSC8572_RGMII_CNTL, - VSC8572_RGMII_RX_DELAY_MASK, - VSC8572_RGMII_TX_DELAY_MASK); - if (ret) - return ret; - } + ret = vsc85xx_update_rgmii_cntl(phydev, VSC8572_RGMII_CNTL, + VSC8572_RGMII_RX_DELAY_MASK, + VSC8572_RGMII_TX_DELAY_MASK); + if (ret) + return ret;

ret = genphy_soft_reset(phydev); if (ret) diff --git a/drivers/platform/x86/intel/speed_select_if/isst_if_common.c b/drivers/platform/x86/intel/speed_select_if/isst_if_common.c index e8424e70d81d..f6b32d31c511 100644 --- a/drivers/platform/x86/intel/speed_select_if/isst_if_common.c +++ b/drivers/platform/x86/intel/speed_select_if/isst_if_common.c @@ -277,39 +277,46 @@ static int isst_if_get_platform_info(void __user *argp) return 0; }

+#define ISST_MAX_BUS_NUMBER 2

struct isst_if_cpu_info { /* For BUS 0 and BUS 1 only, which we need for PUNIT interface */ - int bus_info[2]; - struct pci_dev *pci_dev[2]; + int bus_info[ISST_MAX_BUS_NUMBER]; + struct pci_dev *pci_dev[ISST_MAX_BUS_NUMBER]; int punit_cpu_id; int numa_node; };

+struct isst_if_pkg_info { + struct pci_dev *pci_dev[ISST_MAX_BUS_NUMBER]; +}; + static struct isst_if_cpu_info *isst_cpu_info; -#define ISST_MAX_PCI_DOMAINS 8 +static struct isst_if_pkg_info *isst_pkg_info;

static struct pci_dev *_isst_if_get_pci_dev(int cpu, int bus_no, int dev, int fn) { struct pci_dev *matched_pci_dev = NULL; struct pci_dev *pci_dev = NULL; - int no_matches = 0; - int i, bus_number; + struct pci_dev *_pci_dev = NULL; + int no_matches = 0, pkg_id; + int bus_number;

- if (bus_no < 0 || bus_no > 1 || cpu < 0 || cpu >= nr_cpu_ids || - cpu >= num_possible_cpus()) + if (bus_no < 0 || bus_no >= ISST_MAX_BUS_NUMBER || cpu < 0 || + cpu >= nr_cpu_ids || cpu >= num_possible_cpus()) return NULL;

+ pkg_id = topology_physical_package_id(cpu); + bus_number = isst_cpu_info[cpu].bus_info[bus_no]; if (bus_number < 0) return NULL;

- for (i = 0; i < ISST_MAX_PCI_DOMAINS; ++i) { - struct pci_dev *_pci_dev; + for_each_pci_dev(_pci_dev) { int node;

- _pci_dev = pci_get_domain_bus_and_slot(i, bus_number, PCI_DEVFN(dev, fn)); - if (!_pci_dev) + if (_pci_dev->bus->number != bus_number || + _pci_dev->devfn != PCI_DEVFN(dev, fn)) continue;

++no_matches; @@ -324,6 +331,8 @@ static struct pci_dev *_isst_if_get_pci_dev(int cpu, int bus_no, int dev, int fn }

if (node == isst_cpu_info[cpu].numa_node) { + isst_pkg_info[pkg_id].pci_dev[bus_no] = _pci_dev; + pci_dev = _pci_dev; break; } @@ -342,6 +351,10 @@ static struct pci_dev *_isst_if_get_pci_dev(int cpu, int bus_no, int dev, int fn if (!pci_dev && no_matches == 1) pci_dev = matched_pci_dev;

+ /* Return pci_dev pointer for any matched CPU in the package */ + if (!pci_dev) + pci_dev = isst_pkg_info[pkg_id].pci_dev[bus_no]; + return pci_dev; }

@@ -361,8 +374,8 @@ struct pci_dev *isst_if_get_pci_dev(int cpu, int bus_no, int dev, int fn) { struct pci_dev *pci_dev;

- if (bus_no < 0 || bus_no > 1 || cpu < 0 || cpu >= nr_cpu_ids || - cpu >= num_possible_cpus()) + if (bus_no < 0 || bus_no >= ISST_MAX_BUS_NUMBER || cpu < 0 || + cpu >= nr_cpu_ids || cpu >= num_possible_cpus()) return NULL;

pci_dev = isst_cpu_info[cpu].pci_dev[bus_no]; @@ -417,10 +430,19 @@ static int isst_if_cpu_info_init(void) if (!isst_cpu_info) return -ENOMEM;

+ isst_pkg_info = kcalloc(topology_max_packages(), + sizeof(*isst_pkg_info), + GFP_KERNEL); + if (!isst_pkg_info) { + kfree(isst_cpu_info); + return -ENOMEM; + } + ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "platform/x86/isst-if:online", isst_if_cpu_online, NULL); if (ret < 0) { + kfree(isst_pkg_info); kfree(isst_cpu_info); return ret; } @@ -433,6 +455,7 @@ static int isst_if_cpu_info_init(void) static void isst_if_cpu_info_exit(void) { cpuhp_remove_state(isst_if_online_id); + kfree(isst_pkg_info); kfree(isst_cpu_info); };

diff --git a/drivers/power/supply/bq24190_charger.c b/drivers/power/supply/bq24190_charger.c index ebb5ba7f8bb6..90ac5e59a5d6 100644 --- a/drivers/power/supply/bq24190_charger.c +++ b/drivers/power/supply/bq24190_charger.c @@ -1201,8 +1201,19 @@ static void bq24190_input_current_limit_work(struct work_struct *work) struct bq24190_dev_info *bdi = container_of(work, struct bq24190_dev_info, input_current_limit_work.work); + union power_supply_propval val; + int ret;

- power_supply_set_input_current_limit_from_supplier(bdi->charger); + ret = power_supply_get_property_from_supplier(bdi->charger, + POWER_SUPPLY_PROP_CURRENT_MAX, + &val); + if (ret) + return; + + bq24190_charger_set_property(bdi->charger, + POWER_SUPPLY_PROP_INPUT_CURRENT_LIMIT, + &val); + power_supply_changed(bdi->charger); }

/* Sync the input-current-limit with our parent supply (if we have one) */ diff --git a/drivers/power/supply/bq27xxx_battery.c b/drivers/power/supply/bq27xxx_battery.c index 7334a8b8007e..ffb5f5c02822 100644 --- a/drivers/power/supply/bq27xxx_battery.c +++ b/drivers/power/supply/bq27xxx_battery.c @@ -1572,14 +1572,6 @@ static int bq27xxx_battery_read_charge(struct bq27xxx_device_info *di, u8 reg) */ static inline int bq27xxx_battery_read_nac(struct bq27xxx_device_info *di) { - int flags; - - if (di->opts & BQ27XXX_O_ZERO) { - flags = bq27xxx_read(di, BQ27XXX_REG_FLAGS, true); - if (flags >= 0 && (flags & BQ27000_FLAG_CI)) - return -ENODATA; - } - return bq27xxx_battery_read_charge(di, BQ27XXX_REG_NAC); }

@@ -1742,6 +1734,18 @@ static bool bq27xxx_battery_dead(struct bq27xxx_device_info *di, u16 flags) return flags & (BQ27XXX_FLAG_SOC1 | BQ27XXX_FLAG_SOCF); }

+/* + * Returns true if reported battery capacity is inaccurate + */ +static bool bq27xxx_battery_capacity_inaccurate(struct bq27xxx_device_info *di, + u16 flags) +{ + if (di->opts & BQ27XXX_O_HAS_CI) + return (flags & BQ27000_FLAG_CI); + else + return false; +} + static int bq27xxx_battery_read_health(struct bq27xxx_device_info *di) { /* Unlikely but important to return first */ @@ -1751,83 +1755,12 @@ static int bq27xxx_battery_read_health(struct bq27xxx_device_info *di) return POWER_SUPPLY_HEALTH_COLD; if (unlikely(bq27xxx_battery_dead(di, di->cache.flags))) return POWER_SUPPLY_HEALTH_DEAD; + if (unlikely(bq27xxx_battery_capacity_inaccurate(di, di->cache.flags))) + return POWER_SUPPLY_HEALTH_CALIBRATION_REQUIRED;

return POWER_SUPPLY_HEALTH_GOOD; }

-static void bq27xxx_battery_update_unlocked(struct bq27xxx_device_info *di) -{ - struct bq27xxx_reg_cache cache = {0, }; - bool has_ci_flag = di->opts & BQ27XXX_O_HAS_CI; - bool has_singe_flag = di->opts & BQ27XXX_O_ZERO; - - cache.flags = bq27xxx_read(di, BQ27XXX_REG_FLAGS, has_singe_flag); - if ((cache.flags & 0xff) == 0xff) - cache.flags = -1; /* read error */ - if (cache.flags >= 0) { - cache.temperature = bq27xxx_battery_read_temperature(di); - if (has_ci_flag && (cache.flags & BQ27000_FLAG_CI)) { - dev_info_once(di->dev, "battery is not calibrated! ignoring capacity values\n"); - cache.capacity = -ENODATA; - cache.energy = -ENODATA; - cache.time_to_empty = -ENODATA; - cache.time_to_empty_avg = -ENODATA; - cache.time_to_full = -ENODATA; - cache.charge_full = -ENODATA; - cache.health = -ENODATA; - } else { - if (di->regs[BQ27XXX_REG_TTE] != INVALID_REG_ADDR) - cache.time_to_empty = bq27xxx_battery_read_time(di, BQ27XXX_REG_TTE); - if (di->regs[BQ27XXX_REG_TTECP] != INVALID_REG_ADDR) - cache.time_to_empty_avg = bq27xxx_battery_read_time(di, BQ27XXX_REG_TTECP); - if (di->regs[BQ27XXX_REG_TTF] != INVALID_REG_ADDR) - cache.time_to_full = bq27xxx_battery_read_time(di, BQ27XXX_REG_TTF); - - cache.charge_full = bq27xxx_battery_read_fcc(di); - cache.capacity = bq27xxx_battery_read_soc(di); - if (di->regs[BQ27XXX_REG_AE] != INVALID_REG_ADDR) - cache.energy = bq27xxx_battery_read_energy(di); - di->cache.flags = cache.flags; - cache.health = bq27xxx_battery_read_health(di); - } - if (di->regs[BQ27XXX_REG_CYCT] != INVALID_REG_ADDR) - cache.cycle_count = bq27xxx_battery_read_cyct(di); - - /* We only have to read charge design full once */ - if (di->charge_design_full <= 0) - di->charge_design_full = bq27xxx_battery_read_dcap(di); - } - - if ((di->cache.capacity != cache.capacity) || - (di->cache.flags != cache.flags)) - power_supply_changed(di->bat); - - if (memcmp(&di->cache, &cache, sizeof(cache)) != 0) - di->cache = cache; - - di->last_update = jiffies; - - if (!di->removed && poll_interval > 0) - mod_delayed_work(system_wq, &di->work, poll_interval * HZ); -} - -void bq27xxx_battery_update(struct bq27xxx_device_info *di) -{ - mutex_lock(&di->lock); - bq27xxx_battery_update_unlocked(di); - mutex_unlock(&di->lock); -} -EXPORT_SYMBOL_GPL(bq27xxx_battery_update); - -static void bq27xxx_battery_poll(struct work_struct *work) -{ - struct bq27xxx_device_info *di = - container_of(work, struct bq27xxx_device_info, - work.work); - - bq27xxx_battery_update(di); -} - static bool bq27xxx_battery_is_full(struct bq27xxx_device_info *di, int flags) { if (di->opts & BQ27XXX_O_ZERO) @@ -1901,6 +1834,78 @@ static int bq27xxx_battery_current_and_status( return 0; }

+static void bq27xxx_battery_update_unlocked(struct bq27xxx_device_info *di) +{ + union power_supply_propval status = di->last_status; + struct bq27xxx_reg_cache cache = {0, }; + bool has_singe_flag = di->opts & BQ27XXX_O_ZERO; + + cache.flags = bq27xxx_read(di, BQ27XXX_REG_FLAGS, has_singe_flag); + if ((cache.flags & 0xff) == 0xff) + cache.flags = -1; /* read error */ + if (cache.flags >= 0) { + cache.temperature = bq27xxx_battery_read_temperature(di); + if (di->regs[BQ27XXX_REG_TTE] != INVALID_REG_ADDR) + cache.time_to_empty = bq27xxx_battery_read_time(di, BQ27XXX_REG_TTE); + if (di->regs[BQ27XXX_REG_TTECP] != INVALID_REG_ADDR) + cache.time_to_empty_avg = bq27xxx_battery_read_time(di, BQ27XXX_REG_TTECP); + if (di->regs[BQ27XXX_REG_TTF] != INVALID_REG_ADDR) + cache.time_to_full = bq27xxx_battery_read_time(di, BQ27XXX_REG_TTF); + + cache.charge_full = bq27xxx_battery_read_fcc(di); + cache.capacity = bq27xxx_battery_read_soc(di); + if (di->regs[BQ27XXX_REG_AE] != INVALID_REG_ADDR) + cache.energy = bq27xxx_battery_read_energy(di); + di->cache.flags = cache.flags; + cache.health = bq27xxx_battery_read_health(di); + if (di->regs[BQ27XXX_REG_CYCT] != INVALID_REG_ADDR) + cache.cycle_count = bq27xxx_battery_read_cyct(di); + + /* + * On gauges with signed current reporting the current must be + * checked to detect charging <-> discharging status changes. + */ + if (!(di->opts & BQ27XXX_O_ZERO)) + bq27xxx_battery_current_and_status(di, NULL, &status, &cache); + + /* We only have to read charge design full once */ + if (di->charge_design_full <= 0) + di->charge_design_full = bq27xxx_battery_read_dcap(di); + } + + if ((di->cache.capacity != cache.capacity) || + (di->cache.flags != cache.flags) || + (di->last_status.intval != status.intval)) { + di->last_status.intval = status.intval; + power_supply_changed(di->bat); + } + + if (memcmp(&di->cache, &cache, sizeof(cache)) != 0) + di->cache = cache; + + di->last_update = jiffies; + + if (!di->removed && poll_interval > 0) + mod_delayed_work(system_wq, &di->work, poll_interval * HZ); +} + +void bq27xxx_battery_update(struct bq27xxx_device_info *di) +{ + mutex_lock(&di->lock); + bq27xxx_battery_update_unlocked(di); + mutex_unlock(&di->lock); +} +EXPORT_SYMBOL_GPL(bq27xxx_battery_update); + +static void bq27xxx_battery_poll(struct work_struct *work) +{ + struct bq27xxx_device_info *di = + container_of(work, struct bq27xxx_device_info, + work.work); + + bq27xxx_battery_update(di); +} + /* * Get the average power in µW * Return < 0 if something fails. @@ -2094,8 +2099,8 @@ static void bq27xxx_external_power_changed(struct power_supply *psy) { struct bq27xxx_device_info *di = power_supply_get_drvdata(psy);

- cancel_delayed_work_sync(&di->work); - schedule_delayed_work(&di->work, 0); + /* After charger plug in/out wait 0.5s for things to stabilize */ + mod_delayed_work(system_wq, &di->work, HZ / 2); }

int bq27xxx_battery_setup(struct bq27xxx_device_info *di) diff --git a/drivers/power/supply/power_supply_core.c b/drivers/power/supply/power_supply_core.c index 8161fad081a9..daf76d7885c0 100644 --- a/drivers/power/supply/power_supply_core.c +++ b/drivers/power/supply/power_supply_core.c @@ -375,46 +375,49 @@ int power_supply_is_system_supplied(void) } EXPORT_SYMBOL_GPL(power_supply_is_system_supplied);

-static int __power_supply_get_supplier_max_current(struct device *dev, - void *data) +struct psy_get_supplier_prop_data { + struct power_supply *psy; + enum power_supply_property psp; + union power_supply_propval *val; +}; + +static int __power_supply_get_supplier_property(struct device *dev, void *_data) { - union power_supply_propval ret = {0,}; struct power_supply *epsy = dev_get_drvdata(dev); - struct power_supply *psy = data; + struct psy_get_supplier_prop_data *data = _data;

- if (__power_supply_is_supplied_by(epsy, psy)) - if (!epsy->desc->get_property(epsy, - POWER_SUPPLY_PROP_CURRENT_MAX, - &ret)) - return ret.intval; + if (__power_supply_is_supplied_by(epsy, data->psy)) + if (!epsy->desc->get_property(epsy, data->psp, data->val)) + return 1; /* Success */

- return 0; + return 0; /* Continue iterating */ }

-int power_supply_set_input_current_limit_from_supplier(struct power_supply *psy) +int power_supply_get_property_from_supplier(struct power_supply *psy, + enum power_supply_property psp, + union power_supply_propval *val) { - union power_supply_propval val = {0,}; - int curr; - - if (!psy->desc->set_property) - return -EINVAL; + struct psy_get_supplier_prop_data data = { + .psy = psy, + .psp = psp, + .val = val, + }; + int ret;

/* * This function is not intended for use with a supply with multiple - * suppliers, we simply pick the first supply to report a non 0 - * max-current. + * suppliers, we simply pick the first supply to report the psp. */ - curr = class_for_each_device(power_supply_class, NULL, psy, - __power_supply_get_supplier_max_current); - if (curr <= 0) - return (curr == 0) ? -ENODEV : curr; - - val.intval = curr; + ret = class_for_each_device(power_supply_class, NULL, &data, + __power_supply_get_supplier_property); + if (ret < 0) + return ret; + if (ret == 0) + return -ENODEV;

- return psy->desc->set_property(psy, - POWER_SUPPLY_PROP_INPUT_CURRENT_LIMIT, &val); + return 0; } -EXPORT_SYMBOL_GPL(power_supply_set_input_current_limit_from_supplier); +EXPORT_SYMBOL_GPL(power_supply_get_property_from_supplier);

int power_supply_set_battery_charged(struct power_supply *psy) { diff --git a/include/linux/power/bq27xxx_battery.h b/include/linux/power/bq27xxx_battery.h index e3322dad9c85..7c8d65414a70 100644 --- a/include/linux/power/bq27xxx_battery.h +++ b/include/linux/power/bq27xxx_battery.h @@ -2,6 +2,8 @@ #ifndef __LINUX_BQ27X00_BATTERY_H__ #define __LINUX_BQ27X00_BATTERY_H__

+#include <linux/power_supply.h> + enum bq27xxx_chip { BQ27000 = 1, /* bq27000, bq27200 */ BQ27010, /* bq27010, bq27210 */ @@ -70,6 +72,7 @@ struct bq27xxx_device_info { int charge_design_full; bool removed; unsigned long last_update; + union power_supply_propval last_status; struct delayed_work work; struct power_supply *bat; struct list_head list; diff --git a/include/linux/power_supply.h b/include/linux/power_supply.h index 9ca1f120a211..0735b8963e0a 100644 --- a/include/linux/power_supply.h +++ b/include/linux/power_supply.h @@ -420,8 +420,9 @@ power_supply_temp2resist_simple(struct power_supply_resistance_temp_table *table int table_len, int temp); extern void power_supply_changed(struct power_supply *psy); extern int power_supply_am_i_supplied(struct power_supply *psy); -extern int power_supply_set_input_current_limit_from_supplier( - struct power_supply *psy); +int power_supply_get_property_from_supplier(struct power_supply *psy, + enum power_supply_property psp, + union power_supply_propval *val); extern int power_supply_set_battery_charged(struct power_supply *psy);

#ifdef CONFIG_POWER_SUPPLY diff --git a/include/net/bond_options.h b/include/net/bond_options.h index e64833a674eb..dd75c071f67e 100644 --- a/include/net/bond_options.h +++ b/include/net/bond_options.h @@ -65,6 +65,7 @@ enum { BOND_OPT_NUM_PEER_NOTIF_ALIAS, BOND_OPT_PEER_NOTIF_DELAY, BOND_OPT_LACP_ACTIVE, + BOND_OPT_MISSED_MAX, BOND_OPT_LAST };

diff --git a/include/net/bonding.h b/include/net/bonding.h index de0bdcc7dc7f..e4453cf4f017 100644 --- a/include/net/bonding.h +++ b/include/net/bonding.h @@ -121,6 +121,7 @@ struct bond_params { int xmit_policy; int miimon; u8 num_peer_notif; + u8 missed_max; int arp_interval; int arp_validate; int arp_all_targets; @@ -227,7 +228,7 @@ struct bonding { */ spinlock_t mode_lock; spinlock_t stats_lock; - u8 send_peer_notif; + u32 send_peer_notif; u8 igmp_retrans; #ifdef CONFIG_PROC_FS struct proc_dir_entry *proc_entry; diff --git a/include/net/dsa.h b/include/net/dsa.h index d784e76113b8..bec439c4a085 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -472,6 +472,34 @@ static inline bool dsa_is_user_port(struct dsa_switch *ds, int p) return dsa_to_port(ds, p)->type == DSA_PORT_TYPE_USER; }

+#define dsa_tree_for_each_user_port(_dp, _dst) \ + list_for_each_entry((_dp), &(_dst)->ports, list) \ + if (dsa_port_is_user((_dp))) + +#define dsa_switch_for_each_port(_dp, _ds) \ + list_for_each_entry((_dp), &(_ds)->dst->ports, list) \ + if ((_dp)->ds == (_ds)) + +#define dsa_switch_for_each_port_safe(_dp, _next, _ds) \ + list_for_each_entry_safe((_dp), (_next), &(_ds)->dst->ports, list) \ + if ((_dp)->ds == (_ds)) + +#define dsa_switch_for_each_port_continue_reverse(_dp, _ds) \ + list_for_each_entry_continue_reverse((_dp), &(_ds)->dst->ports, list) \ + if ((_dp)->ds == (_ds)) + +#define dsa_switch_for_each_available_port(_dp, _ds) \ + dsa_switch_for_each_port((_dp), (_ds)) \ + if (!dsa_port_is_unused((_dp))) + +#define dsa_switch_for_each_user_port(_dp, _ds) \ + dsa_switch_for_each_port((_dp), (_ds)) \ + if (dsa_port_is_user((_dp))) + +#define dsa_switch_for_each_cpu_port(_dp, _ds) \ + dsa_switch_for_each_port((_dp), (_ds)) \ + if (dsa_port_is_cpu((_dp))) + static inline u32 dsa_user_ports(struct dsa_switch *ds) { u32 mask = 0; diff --git a/include/net/ip.h b/include/net/ip.h index 6ae923c55cf4..fc05e016be06 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -75,6 +75,7 @@ struct ipcm_cookie { __be32 addr; int oif; struct ip_options_rcu *opt; + __u8 protocol; __u8 ttl; __s16 tos; char priority; @@ -95,6 +96,7 @@ static inline void ipcm_init_sk(struct ipcm_cookie *ipcm, ipcm->sockc.tsflags = inet->sk.sk_tsflags; ipcm->oif = inet->sk.sk_bound_dev_if; ipcm->addr = inet->inet_saddr; + ipcm->protocol = inet->inet_num; }

#define IPCB(skb) ((struct inet_skb_parm*)((skb)->cb)) diff --git a/include/net/page_pool.h b/include/net/page_pool.h index a4082406a003..edcc22605842 100644 --- a/include/net/page_pool.h +++ b/include/net/page_pool.h @@ -282,22 +282,4 @@ static inline void page_pool_nid_changed(struct page_pool *pool, int new_nid) page_pool_update_nid(pool, new_nid); }

-static inline void page_pool_ring_lock(struct page_pool *pool) - __acquires(&pool->ring.producer_lock) -{ - if (in_serving_softirq()) - spin_lock(&pool->ring.producer_lock); - else - spin_lock_bh(&pool->ring.producer_lock); -} - -static inline void page_pool_ring_unlock(struct page_pool *pool) - __releases(&pool->ring.producer_lock) -{ - if (in_serving_softirq()) - spin_unlock(&pool->ring.producer_lock); - else - spin_unlock_bh(&pool->ring.producer_lock); -} - #endif /* _NET_PAGE_POOL_H */ diff --git a/include/net/xdp.h b/include/net/xdp.h index ad5b02dcb6f4..b2ac69cb30b3 100644 --- a/include/net/xdp.h +++ b/include/net/xdp.h @@ -260,6 +260,9 @@ bool xdp_rxq_info_is_reg(struct xdp_rxq_info *xdp_rxq); int xdp_rxq_info_reg_mem_model(struct xdp_rxq_info *xdp_rxq, enum xdp_mem_type type, void *allocator); void xdp_rxq_info_unreg_mem_model(struct xdp_rxq_info *xdp_rxq); +int xdp_reg_mem_model(struct xdp_mem_info *mem, + enum xdp_mem_type type, void *allocator); +void xdp_unreg_mem_model(struct xdp_mem_info *mem);

/* Drivers not supporting XDP metadata can use this helper, which * rejects any room expansion for metadata as a result. diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index eebd3894fe89..4ac53b30b6dc 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -858,6 +858,7 @@ enum { IFLA_BOND_TLB_DYNAMIC_LB, IFLA_BOND_PEER_NOTIF_DELAY, IFLA_BOND_AD_LACP_ACTIVE, + IFLA_BOND_MISSED_MAX, __IFLA_BOND_MAX, };

diff --git a/include/uapi/linux/in.h b/include/uapi/linux/in.h index 14168225cecd..c4702fff64d3 100644 --- a/include/uapi/linux/in.h +++ b/include/uapi/linux/in.h @@ -159,6 +159,8 @@ struct in_addr { #define MCAST_MSFILTER 48 #define IP_MULTICAST_ALL 49 #define IP_UNICAST_IF 50 +#define IP_LOCAL_PORT_RANGE 51 +#define IP_PROTOCOL 52

#define MCAST_EXCLUDE 0 #define MCAST_INCLUDE 1 diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 10b37773d9e4..a63c68f5945c 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -1165,7 +1165,7 @@ static int htab_lru_map_update_elem(struct bpf_map *map, void *key, void *value,

ret = htab_lock_bucket(htab, b, hash, &flags); if (ret) - return ret; + goto err_lock_bucket;

l_old = lookup_elem_raw(head, hash, key, key_size);

@@ -1186,6 +1186,7 @@ static int htab_lru_map_update_elem(struct bpf_map *map, void *key, void *value, err: htab_unlock_bucket(htab, b, hash, flags);

+err_lock_bucket: if (ret) htab_lru_push_free(htab, l_new); else if (l_old) @@ -1288,7 +1289,7 @@ static int __htab_lru_percpu_map_update_elem(struct bpf_map *map, void *key,

ret = htab_lock_bucket(htab, b, hash, &flags); if (ret) - return ret; + goto err_lock_bucket;

l_old = lookup_elem_raw(head, hash, key, key_size);

@@ -1311,6 +1312,7 @@ static int __htab_lru_percpu_map_update_elem(struct bpf_map *map, void *key, ret = 0; err: htab_unlock_bucket(htab, b, hash, flags); +err_lock_bucket: if (l_new) bpf_lru_push_free(&htab->lru, &l_new->lru_node); return ret; diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c index 7905e005baa9..315f9ad3dc4d 100644 --- a/net/bluetooth/hci_sock.c +++ b/net/bluetooth/hci_sock.c @@ -980,6 +980,34 @@ static int hci_sock_ioctl(struct socket *sock, unsigned int cmd,

BT_DBG("cmd %x arg %lx", cmd, arg);

+ /* Make sure the cmd is valid before doing anything */ + switch (cmd) { + case HCIGETDEVLIST: + case HCIGETDEVINFO: + case HCIGETCONNLIST: + case HCIDEVUP: + case HCIDEVDOWN: + case HCIDEVRESET: + case HCIDEVRESTAT: + case HCISETSCAN: + case HCISETAUTH: + case HCISETENCRYPT: + case HCISETPTYPE: + case HCISETLINKPOL: + case HCISETLINKMODE: + case HCISETACLMTU: + case HCISETSCOMTU: + case HCIINQUIRY: + case HCISETRAW: + case HCIGETCONNINFO: + case HCIGETAUTHINFO: + case HCIBLOCKADDR: + case HCIUNBLOCKADDR: + break; + default: + return -ENOIOCTLCMD; + } + lock_sock(sk);

if (hci_pi(sk)->channel != HCI_CHANNEL_RAW) { diff --git a/net/core/page_pool.c b/net/core/page_pool.c index 1a6978427d6c..069d6ba0e33f 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -26,6 +26,29 @@

#define BIAS_MAX LONG_MAX

+static bool page_pool_producer_lock(struct page_pool *pool) + __acquires(&pool->ring.producer_lock) +{ + bool in_softirq = in_softirq(); + + if (in_softirq) + spin_lock(&pool->ring.producer_lock); + else + spin_lock_bh(&pool->ring.producer_lock); + + return in_softirq; +} + +static void page_pool_producer_unlock(struct page_pool *pool, + bool in_softirq) + __releases(&pool->ring.producer_lock) +{ + if (in_softirq) + spin_unlock(&pool->ring.producer_lock); + else + spin_unlock_bh(&pool->ring.producer_lock); +} + static int page_pool_init(struct page_pool *pool, const struct page_pool_params *params) { @@ -390,8 +413,8 @@ static void page_pool_return_page(struct page_pool *pool, struct page *page) static bool page_pool_recycle_in_ring(struct page_pool *pool, struct page *page) { int ret; - /* BH protection not needed if current is serving softirq */ - if (in_serving_softirq()) + /* BH protection not needed if current is softirq */ + if (in_softirq()) ret = ptr_ring_produce(&pool->ring, page); else ret = ptr_ring_produce_bh(&pool->ring, page); @@ -446,7 +469,7 @@ __page_pool_put_page(struct page_pool *pool, struct page *page, page_pool_dma_sync_for_device(pool, page, dma_sync_size);

- if (allow_direct && in_serving_softirq() && + if (allow_direct && in_softirq() && page_pool_recycle_in_cache(page, pool)) return NULL;

@@ -489,6 +512,7 @@ void page_pool_put_page_bulk(struct page_pool *pool, void **data, int count) { int i, bulk_len = 0; + bool in_softirq;

for (i = 0; i < count; i++) { struct page *page = virt_to_head_page(data[i]); @@ -503,12 +527,12 @@ void page_pool_put_page_bulk(struct page_pool *pool, void **data, return;

/* Bulk producer into ptr_ring page_pool cache */ - page_pool_ring_lock(pool); + in_softirq = page_pool_producer_lock(pool); for (i = 0; i < bulk_len; i++) { if (__ptr_ring_produce(&pool->ring, data[i])) break; /* ring full */ } - page_pool_ring_unlock(pool); + page_pool_producer_unlock(pool, in_softirq);

/* Hopefully all pages was return into ptr_ring */ if (likely(i == bulk_len)) diff --git a/net/core/xdp.c b/net/core/xdp.c index cc92ccb38432..a3e3d2538a3a 100644 --- a/net/core/xdp.c +++ b/net/core/xdp.c @@ -110,20 +110,15 @@ static void mem_allocator_disconnect(void *allocator) mutex_unlock(&mem_id_lock); }

-void xdp_rxq_info_unreg_mem_model(struct xdp_rxq_info *xdp_rxq) +void xdp_unreg_mem_model(struct xdp_mem_info *mem) { struct xdp_mem_allocator *xa; - int type = xdp_rxq->mem.type; - int id = xdp_rxq->mem.id; + int type = mem->type; + int id = mem->id;

/* Reset mem info to defaults */ - xdp_rxq->mem.id = 0; - xdp_rxq->mem.type = 0; - - if (xdp_rxq->reg_state != REG_STATE_REGISTERED) { - WARN(1, "Missing register, driver bug"); - return; - } + mem->id = 0; + mem->type = 0;

if (id == 0) return; @@ -135,6 +130,17 @@ void xdp_rxq_info_unreg_mem_model(struct xdp_rxq_info *xdp_rxq) rcu_read_unlock(); } } +EXPORT_SYMBOL_GPL(xdp_unreg_mem_model); + +void xdp_rxq_info_unreg_mem_model(struct xdp_rxq_info *xdp_rxq) +{ + if (xdp_rxq->reg_state != REG_STATE_REGISTERED) { + WARN(1, "Missing register, driver bug"); + return; + } + + xdp_unreg_mem_model(&xdp_rxq->mem); +} EXPORT_SYMBOL_GPL(xdp_rxq_info_unreg_mem_model);

void xdp_rxq_info_unreg(struct xdp_rxq_info *xdp_rxq) @@ -261,28 +267,24 @@ static bool __is_supported_mem_type(enum xdp_mem_type type) return true; }

-int xdp_rxq_info_reg_mem_model(struct xdp_rxq_info *xdp_rxq, - enum xdp_mem_type type, void *allocator) +static struct xdp_mem_allocator *__xdp_reg_mem_model(struct xdp_mem_info *mem, + enum xdp_mem_type type, + void *allocator) { struct xdp_mem_allocator *xdp_alloc; gfp_t gfp = GFP_KERNEL; int id, errno, ret; void *ptr;

- if (xdp_rxq->reg_state != REG_STATE_REGISTERED) { - WARN(1, "Missing register, driver bug"); - return -EFAULT; - } - if (!__is_supported_mem_type(type)) - return -EOPNOTSUPP; + return ERR_PTR(-EOPNOTSUPP);

- xdp_rxq->mem.type = type; + mem->type = type;

if (!allocator) { if (type == MEM_TYPE_PAGE_POOL) - return -EINVAL; /* Setup time check page_pool req */ - return 0; + return ERR_PTR(-EINVAL); /* Setup time check page_pool req */ + return NULL; }

/* Delay init of rhashtable to save memory if feature isn't used */ @@ -292,13 +294,13 @@ int xdp_rxq_info_reg_mem_model(struct xdp_rxq_info *xdp_rxq, mutex_unlock(&mem_id_lock); if (ret < 0) { WARN_ON(1); - return ret; + return ERR_PTR(ret); } }

xdp_alloc = kzalloc(sizeof(*xdp_alloc), gfp); if (!xdp_alloc) - return -ENOMEM; + return ERR_PTR(-ENOMEM);

mutex_lock(&mem_id_lock); id = __mem_id_cyclic_get(gfp); @@ -306,15 +308,15 @@ int xdp_rxq_info_reg_mem_model(struct xdp_rxq_info *xdp_rxq, errno = id; goto err; } - xdp_rxq->mem.id = id; - xdp_alloc->mem = xdp_rxq->mem; + mem->id = id; + xdp_alloc->mem = *mem; xdp_alloc->allocator = allocator;

/* Insert allocator into ID lookup table */ ptr = rhashtable_insert_slow(mem_id_ht, &id, &xdp_alloc->node); if (IS_ERR(ptr)) { - ida_simple_remove(&mem_id_pool, xdp_rxq->mem.id); - xdp_rxq->mem.id = 0; + ida_simple_remove(&mem_id_pool, mem->id); + mem->id = 0; errno = PTR_ERR(ptr); goto err; } @@ -324,13 +326,44 @@ int xdp_rxq_info_reg_mem_model(struct xdp_rxq_info *xdp_rxq,

mutex_unlock(&mem_id_lock);

- trace_mem_connect(xdp_alloc, xdp_rxq); - return 0; + return xdp_alloc; err: mutex_unlock(&mem_id_lock); kfree(xdp_alloc); - return errno; + return ERR_PTR(errno); +} + +int xdp_reg_mem_model(struct xdp_mem_info *mem, + enum xdp_mem_type type, void *allocator) +{ + struct xdp_mem_allocator *xdp_alloc; + + xdp_alloc = __xdp_reg_mem_model(mem, type, allocator); + if (IS_ERR(xdp_alloc)) + return PTR_ERR(xdp_alloc); + return 0; } +EXPORT_SYMBOL_GPL(xdp_reg_mem_model); + +int xdp_rxq_info_reg_mem_model(struct xdp_rxq_info *xdp_rxq, + enum xdp_mem_type type, void *allocator) +{ + struct xdp_mem_allocator *xdp_alloc; + + if (xdp_rxq->reg_state != REG_STATE_REGISTERED) { + WARN(1, "Missing register, driver bug"); + return -EFAULT; + } + + xdp_alloc = __xdp_reg_mem_model(&xdp_rxq->mem, type, allocator); + if (IS_ERR(xdp_alloc)) + return PTR_ERR(xdp_alloc); + + if (trace_mem_connect_enabled() && xdp_alloc) + trace_mem_connect(xdp_alloc, xdp_rxq); + return 0; +} + EXPORT_SYMBOL_GPL(xdp_rxq_info_reg_mem_model);

/* XDP RX runs under NAPI protection, and in different delivery error diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 1e2af5f8822d..540002c9f3b3 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -317,7 +317,14 @@ int ip_cmsg_send(struct sock *sk, struct msghdr *msg, struct ipcm_cookie *ipc, ipc->tos = val; ipc->priority = rt_tos2priority(ipc->tos); break; - + case IP_PROTOCOL: + if (cmsg->cmsg_len != CMSG_LEN(sizeof(int))) + return -EINVAL; + val = *(int *)CMSG_DATA(cmsg); + if (val < 1 || val > 255) + return -EINVAL; + ipc->protocol = val; + break; default: return -EINVAL; } @@ -1724,6 +1731,9 @@ static int do_ip_getsockopt(struct sock *sk, int level, int optname, case IP_MINTTL: val = inet->min_ttl; break; + case IP_PROTOCOL: + val = inet_sk(sk)->inet_num; + break; default: release_sock(sk); return -ENOPROTOOPT; diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index b8689052079c..f532589d2692 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -559,6 +559,9 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) }

ipcm_init_sk(&ipc, inet); + /* Keep backward compat */ + if (hdrincl) + ipc.protocol = IPPROTO_RAW;

if (msg->msg_controllen) { err = ip_cmsg_send(sk, msg, &ipc, false); @@ -626,7 +629,7 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)

flowi4_init_output(&fl4, ipc.oif, ipc.sockc.mark, tos, RT_SCOPE_UNIVERSE, - hdrincl ? IPPROTO_RAW : sk->sk_protocol, + hdrincl ? ipc.protocol : sk->sk_protocol, inet_sk_flowi_flags(sk) | (hdrincl ? FLOWI_FLAG_KNOWN_NH : 0), daddr, saddr, 0, 0, sk->sk_uid); diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 0c833f6b88bd..6ff25c3e9d5a 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -828,7 +828,8 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)

if (!proto) proto = inet->inet_num; - else if (proto != inet->inet_num) + else if (proto != inet->inet_num && + inet->inet_num != IPPROTO_RAW) return -EINVAL;

if (proto > 255) diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 8776e75b200f..0b8b8cb42a8a 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -1546,9 +1546,6 @@ static const struct nla_policy ct_nla_policy[CTA_MAX+1] = {

static int ctnetlink_flush_iterate(struct nf_conn *ct, void *data) { - if (test_bit(IPS_OFFLOAD_BIT, &ct->status)) - return 0; - return ctnetlink_filter_match(ct, data); }

@@ -1612,11 +1609,6 @@ static int ctnetlink_del_conntrack(struct sk_buff *skb,

ct = nf_ct_tuplehash_to_ctrack(h);

- if (test_bit(IPS_OFFLOAD_BIT, &ct->status)) { - nf_ct_put(ct); - return -EBUSY; - } - if (cda[CTA_ID]) { __be32 id = nla_get_be32(cda[CTA_ID]);

diff --git a/tools/include/uapi/linux/if_link.h b/tools/include/uapi/linux/if_link.h index b3610fdd1fee..4772a115231a 100644 --- a/tools/include/uapi/linux/if_link.h +++ b/tools/include/uapi/linux/if_link.h @@ -655,6 +655,7 @@ enum { IFLA_BOND_TLB_DYNAMIC_LB, IFLA_BOND_PEER_NOTIF_DELAY, IFLA_BOND_AD_LACP_ACTIVE, + IFLA_BOND_MISSED_MAX, __IFLA_BOND_MAX, };