diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2020-10-20 09:24:01 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2020-10-20 09:24:01 -0700 |
commit | 4a5bb973fa0353d25dbe854694c71bb58eb4cf78 (patch) | |
tree | 599b573d63e143df6cd1abf5dab8aae49b734a28 | |
parent | 709ebe6dff50405ae83551578bc08c0f78b05158 (diff) | |
parent | 5f7f77400ab5b357b5fdb7122c3442239672186c (diff) |
Merge tag 'for-linus-5.10b-rc1b-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip
Pull more xen updates from Juergen Gross:
- A single patch to fix the Xen security issue XSA-331 (malicious
guests can DoS dom0 by triggering NULL-pointer dereferences or access
to stale data).
- A larger series to fix the Xen security issue XSA-332 (malicious
guests can DoS dom0 by sending events at high frequency leading to
dom0's vcpus being busy in IRQ handling for elongated times).
* tag 'for-linus-5.10b-rc1b-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip:
xen/events: block rogue events for some time
xen/events: defer eoi in case of excessive number of events
xen/events: use a common cpu hotplug hook for event channels
xen/events: switch user event channels to lateeoi model
xen/pciback: use lateeoi irq binding
xen/pvcallsback: use lateeoi irq binding
xen/scsiback: use lateeoi irq binding
xen/netback: use lateeoi irq binding
xen/blkback: use lateeoi irq binding
xen/events: add a new "late EOI" evtchn framework
xen/events: fix race in evtchn_fifo_unmask()
xen/events: add a proper barrier to 2-level uevent unmasking
xen/events: avoid removing an event channel while handling it
-rw-r--r-- | Documentation/admin-guide/kernel-parameters.txt | 8 | ||||
-rw-r--r-- | drivers/block/xen-blkback/blkback.c | 22 | ||||
-rw-r--r-- | drivers/block/xen-blkback/xenbus.c | 5 | ||||
-rw-r--r-- | drivers/net/xen-netback/common.h | 15 | ||||
-rw-r--r-- | drivers/net/xen-netback/interface.c | 61 | ||||
-rw-r--r-- | drivers/net/xen-netback/netback.c | 11 | ||||
-rw-r--r-- | drivers/net/xen-netback/rx.c | 13 | ||||
-rw-r--r-- | drivers/xen/events/events_2l.c | 9 | ||||
-rw-r--r-- | drivers/xen/events/events_base.c | 423 | ||||
-rw-r--r-- | drivers/xen/events/events_fifo.c | 83 | ||||
-rw-r--r-- | drivers/xen/events/events_internal.h | 20 | ||||
-rw-r--r-- | drivers/xen/evtchn.c | 7 | ||||
-rw-r--r-- | drivers/xen/pvcalls-back.c | 76 | ||||
-rw-r--r-- | drivers/xen/xen-pciback/pci_stub.c | 13 | ||||
-rw-r--r-- | drivers/xen/xen-pciback/pciback.h | 12 | ||||
-rw-r--r-- | drivers/xen/xen-pciback/pciback_ops.c | 48 | ||||
-rw-r--r-- | drivers/xen/xen-pciback/xenbus.c | 2 | ||||
-rw-r--r-- | drivers/xen/xen-scsiback.c | 23 | ||||
-rw-r--r-- | include/xen/events.h | 21 |
19 files changed, 707 insertions, 165 deletions
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index f1eeba73d931..02d4adbf98d2 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -5970,6 +5970,14 @@ improve timer resolution at the expense of processing more timer interrupts. + xen.event_eoi_delay= [XEN] + How long to delay EOI handling in case of event + storms (jiffies). Default is 10. + + xen.event_loop_timeout= [XEN] + After which time (jiffies) the event handling loop + should start to delay EOI handling. Default is 2. + nopv= [X86,XEN,KVM,HYPER_V,VMWARE] Disables the PV optimizations forcing the guest to run as generic guest with no PV drivers. Currently support diff --git a/drivers/block/xen-blkback/blkback.c b/drivers/block/xen-blkback/blkback.c index adfc9352351d..501e9dacfff9 100644 --- a/drivers/block/xen-blkback/blkback.c +++ b/drivers/block/xen-blkback/blkback.c @@ -201,7 +201,7 @@ static inline void shrink_free_pagepool(struct xen_blkif_ring *ring, int num) #define vaddr(page) ((unsigned long)pfn_to_kaddr(page_to_pfn(page))) -static int do_block_io_op(struct xen_blkif_ring *ring); +static int do_block_io_op(struct xen_blkif_ring *ring, unsigned int *eoi_flags); static int dispatch_rw_block_io(struct xen_blkif_ring *ring, struct blkif_request *req, struct pending_req *pending_req); @@ -612,6 +612,8 @@ int xen_blkif_schedule(void *arg) struct xen_vbd *vbd = &blkif->vbd; unsigned long timeout; int ret; + bool do_eoi; + unsigned int eoi_flags = XEN_EOI_FLAG_SPURIOUS; set_freezable(); while (!kthread_should_stop()) { @@ -636,16 +638,23 @@ int xen_blkif_schedule(void *arg) if (timeout == 0) goto purge_gnt_list; + do_eoi = ring->waiting_reqs; + ring->waiting_reqs = 0; smp_mb(); /* clear flag *before* checking for work */ - ret = do_block_io_op(ring); + ret = do_block_io_op(ring, &eoi_flags); if (ret > 0) ring->waiting_reqs = 1; if (ret == -EACCES) wait_event_interruptible(ring->shutdown_wq, kthread_should_stop()); + if (do_eoi && !ring->waiting_reqs) { + xen_irq_lateeoi(ring->irq, eoi_flags); + eoi_flags |= XEN_EOI_FLAG_SPURIOUS; + } + purge_gnt_list: if (blkif->vbd.feature_gnt_persistent && time_after(jiffies, ring->next_lru)) { @@ -1121,7 +1130,7 @@ static void end_block_io_op(struct bio *bio) * and transmute it to the block API to hand it over to the proper block disk. */ static int -__do_block_io_op(struct xen_blkif_ring *ring) +__do_block_io_op(struct xen_blkif_ring *ring, unsigned int *eoi_flags) { union blkif_back_rings *blk_rings = &ring->blk_rings; struct blkif_request req; @@ -1144,6 +1153,9 @@ __do_block_io_op(struct xen_blkif_ring *ring) if (RING_REQUEST_CONS_OVERFLOW(&blk_rings->common, rc)) break; + /* We've seen a request, so clear spurious eoi flag. */ + *eoi_flags &= ~XEN_EOI_FLAG_SPURIOUS; + if (kthread_should_stop()) { more_to_do = 1; break; @@ -1202,13 +1214,13 @@ done: } static int -do_block_io_op(struct xen_blkif_ring *ring) +do_block_io_op(struct xen_blkif_ring *ring, unsigned int *eoi_flags) { union blkif_back_rings *blk_rings = &ring->blk_rings; int more_to_do; do { - more_to_do = __do_block_io_op(ring); + more_to_do = __do_block_io_op(ring, eoi_flags); if (more_to_do) break; diff --git a/drivers/block/xen-blkback/xenbus.c b/drivers/block/xen-blkback/xenbus.c index b9aa5d1ac10b..5e7c36d73dc6 100644 --- a/drivers/block/xen-blkback/xenbus.c +++ b/drivers/block/xen-blkback/xenbus.c @@ -246,9 +246,8 @@ static int xen_blkif_map(struct xen_blkif_ring *ring, grant_ref_t *gref, if (req_prod - rsp_prod > size) goto fail; - err = bind_interdomain_evtchn_to_irqhandler(blkif->domid, evtchn, - xen_blkif_be_int, 0, - "blkif-backend", ring); + err = bind_interdomain_evtchn_to_irqhandler_lateeoi(blkif->domid, + evtchn, xen_blkif_be_int, 0, "blkif-backend", ring); if (err < 0) goto fail; ring->irq = err; diff --git a/drivers/net/xen-netback/common.h b/drivers/net/xen-netback/common.h index ae477f7756af..8ee24e351bdc 100644 --- a/drivers/net/xen-netback/common.h +++ b/drivers/net/xen-netback/common.h @@ -140,6 +140,20 @@ struct xenvif_queue { /* Per-queue data for xenvif */ char name[QUEUE_NAME_SIZE]; /* DEVNAME-qN */ struct xenvif *vif; /* Parent VIF */ + /* + * TX/RX common EOI handling. + * When feature-split-event-channels = 0, interrupt handler sets + * NETBK_COMMON_EOI, otherwise NETBK_RX_EOI and NETBK_TX_EOI are set + * by the RX and TX interrupt handlers. + * RX and TX handler threads will issue an EOI when either + * NETBK_COMMON_EOI or their specific bits (NETBK_RX_EOI or + * NETBK_TX_EOI) are set and they will reset those bits. + */ + atomic_t eoi_pending; +#define NETBK_RX_EOI 0x01 +#define NETBK_TX_EOI 0x02 +#define NETBK_COMMON_EOI 0x04 + /* Use NAPI for guest TX */ struct napi_struct napi; /* When feature-split-event-channels = 0, tx_irq = rx_irq. */ @@ -378,6 +392,7 @@ int xenvif_dealloc_kthread(void *data); irqreturn_t xenvif_ctrl_irq_fn(int irq, void *data); +bool xenvif_have_rx_work(struct xenvif_queue *queue, bool test_kthread); void xenvif_rx_action(struct xenvif_queue *queue); void xenvif_rx_queue_tail(struct xenvif_queue *queue, struct sk_buff *skb); diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c index 8af497285691..acb786d8b1d8 100644 --- a/drivers/net/xen-netback/interface.c +++ b/drivers/net/xen-netback/interface.c @@ -77,12 +77,28 @@ int xenvif_schedulable(struct xenvif *vif) !vif->disabled; } +static bool xenvif_handle_tx_interrupt(struct xenvif_queue *queue) +{ + bool rc; + + rc = RING_HAS_UNCONSUMED_REQUESTS(&queue->tx); + if (rc) + napi_schedule(&queue->napi); + return rc; +} + static irqreturn_t xenvif_tx_interrupt(int irq, void *dev_id) { struct xenvif_queue *queue = dev_id; + int old; - if (RING_HAS_UNCONSUMED_REQUESTS(&queue->tx)) - napi_schedule(&queue->napi); + old = atomic_fetch_or(NETBK_TX_EOI, &queue->eoi_pending); + WARN(old & NETBK_TX_EOI, "Interrupt while EOI pending\n"); + + if (!xenvif_handle_tx_interrupt(queue)) { + atomic_andnot(NETBK_TX_EOI, &queue->eoi_pending); + xen_irq_lateeoi(irq, XEN_EOI_FLAG_SPURIOUS); + } return IRQ_HANDLED; } @@ -116,19 +132,46 @@ static int xenvif_poll(struct napi_struct *napi, int budget) return work_done; } +static bool xenvif_handle_rx_interrupt(struct xenvif_queue *queue) +{ + bool rc; + + rc = xenvif_have_rx_work(queue, false); + if (rc) + xenvif_kick_thread(queue); + return rc; +} + static irqreturn_t xenvif_rx_interrupt(int irq, void *dev_id) { struct xenvif_queue *queue = dev_id; + int old; - xenvif_kick_thread(queue); + old = atomic_fetch_or(NETBK_RX_EOI, &queue->eoi_pending); + WARN(old & NETBK_RX_EOI, "Interrupt while EOI pending\n"); + + if (!xenvif_handle_rx_interrupt(queue)) { + atomic_andnot(NETBK_RX_EOI, &queue->eoi_pending); + xen_irq_lateeoi(irq, XEN_EOI_FLAG_SPURIOUS); + } return IRQ_HANDLED; } irqreturn_t xenvif_interrupt(int irq, void *dev_id) { - xenvif_tx_interrupt(irq, dev_id); - xenvif_rx_interrupt(irq, dev_id); + struct xenvif_queue *queue = dev_id; + int old; + + old = atomic_fetch_or(NETBK_COMMON_EOI, &queue->eoi_pending); + WARN(old, "Interrupt while EOI pending\n"); + + /* Use bitwise or as we need to call both functions. */ + if ((!xenvif_handle_tx_interrupt(queue) | + !xenvif_handle_rx_interrupt(queue))) { + atomic_andnot(NETBK_COMMON_EOI, &queue->eoi_pending); + xen_irq_lateeoi(irq, XEN_EOI_FLAG_SPURIOUS); + } return IRQ_HANDLED; } @@ -605,7 +648,7 @@ int xenvif_connect_ctrl(struct xenvif *vif, grant_ref_t ring_ref, if (req_prod - rsp_prod > RING_SIZE(&vif->ctrl)) goto err_unmap; - err = bind_interdomain_evtchn_to_irq(vif->domid, evtchn); + err = bind_interdomain_evtchn_to_irq_lateeoi(vif->domid, evtchn); if (err < 0) goto err_unmap; @@ -709,7 +752,7 @@ int xenvif_connect_data(struct xenvif_queue *queue, if (tx_evtchn == rx_evtchn) { /* feature-split-event-channels == 0 */ - err = bind_interdomain_evtchn_to_irqhandler( + err = bind_interdomain_evtchn_to_irqhandler_lateeoi( queue->vif->domid, tx_evtchn, xenvif_interrupt, 0, queue->name, queue); if (err < 0) @@ -720,7 +763,7 @@ int xenvif_connect_data(struct xenvif_queue *queue, /* feature-split-event-channels == 1 */ snprintf(queue->tx_irq_name, sizeof(queue->tx_irq_name), "%s-tx", queue->name); - err = bind_interdomain_evtchn_to_irqhandler( + err = bind_interdomain_evtchn_to_irqhandler_lateeoi( queue->vif->domid, tx_evtchn, xenvif_tx_interrupt, 0, queue->tx_irq_name, queue); if (err < 0) @@ -730,7 +773,7 @@ int xenvif_connect_data(struct xenvif_queue *queue, snprintf(queue->rx_irq_name, sizeof(queue->rx_irq_name), "%s-rx", queue->name); - err = bind_interdomain_evtchn_to_irqhandler( + err = bind_interdomain_evtchn_to_irqhandler_lateeoi( queue->vif->domid, rx_evtchn, xenvif_rx_interrupt, 0, queue->rx_irq_name, queue); if (err < 0) diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c index 6dfca7265644..bc3421d14576 100644 --- a/drivers/net/xen-netback/netback.c +++ b/drivers/net/xen-netback/netback.c @@ -169,6 +169,10 @@ void xenvif_napi_schedule_or_enable_events(struct xenvif_queue *queue) if (more_to_do) napi_schedule(&queue->napi); + else if (atomic_fetch_andnot(NETBK_TX_EOI | NETBK_COMMON_EOI, + &queue->eoi_pending) & + (NETBK_TX_EOI | NETBK_COMMON_EOI)) + xen_irq_lateeoi(queue->tx_irq, 0); } static void tx_add_credit(struct xenvif_queue *queue) @@ -1643,9 +1647,14 @@ static bool xenvif_ctrl_work_todo(struct xenvif *vif) irqreturn_t xenvif_ctrl_irq_fn(int irq, void *data) { struct xenvif *vif = data; + unsigned int eoi_flag = XEN_EOI_FLAG_SPURIOUS; - while (xenvif_ctrl_work_todo(vif)) + while (xenvif_ctrl_work_todo(vif)) { xenvif_ctrl_action(vif); + eoi_flag = 0; + } + + xen_irq_lateeoi(irq, eoi_flag); return IRQ_HANDLED; } diff --git a/drivers/net/xen-netback/rx.c b/drivers/net/xen-netback/rx.c index ac034f69a170..b8febe1d1bfd 100644 --- a/drivers/net/xen-netback/rx.c +++ b/drivers/net/xen-netback/rx.c @@ -503,13 +503,13 @@ static bool xenvif_rx_queue_ready(struct xenvif_queue *queue) return queue->stalled && prod - cons >= 1; } -static bool xenvif_have_rx_work(struct xenvif_queue *queue) +bool xenvif_have_rx_work(struct xenvif_queue *queue, bool test_kthread) { return xenvif_rx_ring_slots_available(queue) || (queue->vif->stall_timeout && (xenvif_rx_queue_stalled(queue) || xenvif_rx_queue_ready(queue))) || - kthread_should_stop() || + (test_kthread && kthread_should_stop()) || queue->vif->disabled; } @@ -540,15 +540,20 @@ static void xenvif_wait_for_rx_work(struct xenvif_queue *queue) { DEFINE_WAIT(wait); - if (xenvif_have_rx_work(queue)) + if (xenvif_have_rx_work(queue, true)) return; for (;;) { long ret; prepare_to_wait(&queue->wq, &wait, TASK_INTERRUPTIBLE); - if (xenvif_have_rx_work(queue)) + if (xenvif_have_rx_work(queue, true)) break; + if (atomic_fetch_andnot(NETBK_RX_EOI | NETBK_COMMON_EOI, + &queue->eoi_pending) & + (NETBK_RX_EOI | NETBK_COMMON_EOI)) + xen_irq_lateeoi(queue->rx_irq, 0); + ret = schedule_timeout(xenvif_rx_queue_timeout(queue)); if (!ret) break; diff --git a/drivers/xen/events/events_2l.c b/drivers/xen/events/events_2l.c index 64df919a2111..fe5ad0e89cd8 100644 --- a/drivers/xen/events/events_2l.c +++ b/drivers/xen/events/events_2l.c @@ -91,6 +91,8 @@ static void evtchn_2l_unmask(evtchn_port_t port) BUG_ON(!irqs_disabled()); + smp_wmb(); /* All writes before unmask must be visible. */ + if (unlikely((cpu != cpu_from_evtchn(port)))) do_hypercall = 1; else { @@ -159,7 +161,7 @@ static inline xen_ulong_t active_evtchns(unsigned int cpu, * a bitset of words which contain pending event bits. The second * level is a bitset of pending events themselves. */ -static void evtchn_2l_handle_events(unsigned cpu) +static void evtchn_2l_handle_events(unsigned cpu, struct evtchn_loop_ctrl *ctrl) { int irq; xen_ulong_t pending_words; @@ -240,10 +242,7 @@ static void evtchn_2l_handle_events(unsigned cpu) /* Process port. */ port = (word_idx * BITS_PER_EVTCHN_WORD) + bit_idx; - irq = get_evtchn_to_irq(port); - - if (irq != -1) - generic_handle_irq(irq); + handle_irq_for_port(port, ctrl); bit_idx = (bit_idx + 1) % BITS_PER_EVTCHN_WORD; diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c index 6f02c18fa65c..cc317739e786 100644 --- a/drivers/xen/events/events_base.c +++ b/drivers/xen/events/events_base.c @@ -33,6 +33,10 @@ #include <linux/slab.h> #include <linux/irqnr.h> #include <linux/pci.h> +#include <linux/spinlock.h> +#include <linux/cpuhotplug.h> +#include <linux/atomic.h> +#include <linux/ktime.h> #ifdef CONFIG_X86 #include <asm/desc.h> @@ -63,6 +67,15 @@ #include "events_internal.h" +#undef MODULE_PARAM_PREFIX +#define MODULE_PARAM_PREFIX "xen." + +static uint __read_mostly event_loop_timeout = 2; +module_param(event_loop_timeout, uint, 0644); + +static uint __read_mostly event_eoi_delay = 10; +module_param(event_eoi_delay, uint, 0644); + const struct evtchn_ops *evtchn_ops; /* @@ -71,6 +84,24 @@ const struct evtchn_ops *evtchn_ops; */ static DEFINE_MUTEX(irq_mapping_update_lock); +/* + * Lock protecting event handling loop against removing event channels. + * Adding of event channels is no issue as the associated IRQ becomes active + * only after everything is setup (before request_[threaded_]irq() the handler + * can't be entered for an event, as the event channel will be unmasked only + * then). + */ +static DEFINE_RWLOCK(evtchn_rwlock); + +/* + * Lock hierarchy: + * + * irq_mapping_update_lock + * evtchn_rwlock + * IRQ-desc lock + * percpu eoi_list_lock + */ + static LIST_HEAD(xen_irq_list_head); /* IRQ <-> VIRQ mapping. */ @@ -95,17 +126,20 @@ static bool (*pirq_needs_eoi)(unsigned irq); static struct irq_info *legacy_info_ptrs[NR_IRQS_LEGACY]; static struct irq_chip xen_dynamic_chip; +static struct irq_chip xen_lateeoi_chip; static struct irq_chip xen_percpu_chip; static struct irq_chip xen_pirq_chip; static void enable_dynirq(struct irq_data *data); static void disable_dynirq(struct irq_data *data); +static DEFINE_PER_CPU(unsigned int, irq_epoch); + static void clear_evtchn_to_irq_row(unsigned row) { unsigned col; for (col = 0; col < EVTCHN_PER_ROW; col++) - evtchn_to_irq[row][col] = -1; + WRITE_ONCE(evtchn_to_irq[row][col], -1); } static void clear_evtchn_to_irq_all(void) @@ -142,7 +176,7 @@ static int set_evtchn_to_irq(evtchn_port_t evtchn, unsigned int irq) clear_evtchn_to_irq_row(row); } - evtchn_to_irq[row][col] = irq; + WRITE_ONCE(evtchn_to_irq[row][col], irq); return 0; } @@ -152,7 +186,7 @@ int get_evtchn_to_irq(evtchn_port_t evtchn) return -1; if (evtchn_to_irq[EVTCHN_ROW(evtchn)] == NULL) return -1; - return evtchn_to_irq[EVTCHN_ROW(evtchn)][EVTCHN_COL(evtchn)]; + return READ_ONCE(evtchn_to_irq[EVTCHN_ROW(evtchn)][EVTCHN_COL(evtchn)]); } /* Get info for IRQ */ @@ -261,10 +295,14 @@ static void xen_irq_info_cleanup(struct irq_info *info) */ evtchn_port_t evtchn_from_irq(unsigned irq) { - if (WARN(irq >= nr_irqs, "Invalid irq %d!\n", irq)) + const struct irq_info *info = NULL; + + if (likely(irq < nr_irqs)) + info = info_for_irq(irq); + if (!info) return 0; - return info_for_irq(irq)->evtchn; + return info->evtchn; } unsigned int irq_from_evtchn(evtchn_port_t evtchn) @@ -375,9 +413,157 @@ void notify_remote_via_irq(int irq) } EXPORT_SYMBOL_GPL(notify_remote_via_irq); +struct lateeoi_work { + struct delayed_work delayed; + spinlock_t eoi_list_lock; + struct list_head eoi_list; +}; + +static DEFINE_PER_CPU(struct lateeoi_work, lateeoi); + +static void lateeoi_list_del(struct irq_info *info) +{ + struct lateeoi_work *eoi = &per_cpu(lateeoi, info->eoi_cpu); + unsigned long flags; + + spin_lock_irqsave(&eoi->eoi_list_lock, flags); + list_del_init(&info->eoi_list); + spin_unlock_irqrestore(&eoi->eoi_list_lock, flags); +} + +static void lateeoi_list_add(struct irq_info *info) +{ + struct lateeoi_work *eoi = &per_cpu(lateeoi, info->eoi_cpu); + struct irq_info *elem; + u64 now = get_jiffies_64(); + unsigned long delay; + unsigned long flags; + + if (now < info->eoi_time) + delay = info->eoi_time - now; + else + delay = 1; + + spin_lock_irqsave(&eoi->eoi_list_lock, flags); + + if (list_empty(&eoi->eoi_list)) { + list_add(&info->eoi_list, &eoi->eoi_list); + mod_delayed_work_on(info->eoi_cpu, system_wq, + &eoi->delayed, delay); + } else { + list_for_each_entry_reverse(elem, &eoi->eoi_list, eoi_list) { + if (elem->eoi_time <= info->eoi_time) + break; + } + list_add(&info->eoi_list, &elem->eoi_list); + } + + spin_unlock_irqrestore(&eoi->eoi_list_lock, flags); +} + +static void xen_irq_lateeoi_locked(struct irq_info *info, bool spurious) +{ + evtchn_port_t evtchn; + unsigned int cpu; + unsigned int delay = 0; + + evtchn = info->evtchn; + if (!VALID_EVTCHN(evtchn) || !list_empty(&info->eoi_list)) + return; + + if (spurious) { + if ((1 << info->spurious_cnt) < (HZ << 2)) + info->spurious_cnt++; + if (info->spurious_cnt > 1) { + delay = 1 << (info->spurious_cnt - 2); + if (delay > HZ) + delay = HZ; + if (!info->eoi_time) + info->eoi_cpu = smp_processor_id(); + info->eoi_time = get_jiffies_64() + delay; + } + } else { + info->spurious_cnt = 0; + } + + cpu = info->eoi_cpu; + if (info->eoi_time && + (info->irq_epoch == per_cpu(irq_epoch, cpu) || delay)) { + lateeoi_list_add(info); + return; + } + + info->eoi_time = 0; + unmask_evtchn(evtchn); +} + +static void xen_irq_lateeoi_worker(struct work_struct *work) +{ + struct lateeoi_work *eoi; + struct irq_info *info; + u64 now = get_jiffies_64(); + unsigned long flags; + + eoi = container_of(to_delayed_work(work), struct lateeoi_work, delayed); + + read_lock_irqsave(&evtchn_rwlock, flags); + + while (true) { + spin_lock(&eoi->eoi_list_lock); + + info = list_first_entry_or_null(&eoi->eoi_list, struct irq_info, + eoi_list); + + if (info == NULL || now < info->eoi_time) { + spin_unlock(&eoi->eoi_list_lock); + break; + } + + list_del_init(&info->eoi_list); + + spin_unlock(&eoi->eoi_list_lock); + + info->eoi_time = 0; + + xen_irq_lateeoi_locked(info, false); + } + + if (info) + mod_delayed_work_on(info->eoi_cpu, system_wq, + &eoi->delayed, info->eoi_time - now); + + read_unlock_irqrestore(&evtchn_rwlock, flags); +} + +static void xen_cpu_init_eoi(unsigned int cpu) +{ + struct lateeoi_work *eoi = &per_cpu(lateeoi, cpu); + + INIT_DELAYED_WORK(&eoi->delayed, xen_irq_lateeoi_worker); + spin_lock_init(&eoi->eoi_list_lock); + INIT_LIST_HEAD(&eoi->eoi_list); +} + +void xen_irq_lateeoi(unsigned int irq, unsigned int eoi_flags) +{ + struct irq_info *info; + unsigned long flags; + + read_lock_irqsave(&evtchn_rwlock, flags); + + info = info_for_irq(irq); + + if (info) + xen_irq_lateeoi_locked(info, eoi_flags & XEN_EOI_FLAG_SPURIOUS); + + read_unlock_irqrestore(&evtchn_rwlock, flags); +} +EXPORT_SYMBOL_GPL(xen_irq_lateeoi); + static void xen_irq_init(unsigned irq) { struct irq_info *info; + #ifdef CONFIG_SMP /* By default all event channels notify CPU#0. */ cpumask_copy(irq_get_affinity_mask(irq), cpumask_of(0)); @@ -392,6 +578,7 @@ static void xen_irq_init(unsigned irq) set_info_for_irq(irq, info); + INIT_LIST_HEAD(&info->eoi_list); list_add_tail(&info->list, &xen_irq_list_head); } @@ -440,16 +627,24 @@ static int __must_check xen_allocate_irq_gsi(unsigned gsi) static void xen_free_irq(unsigned irq) { struct irq_info *info = info_for_irq(irq); + unsigned long flags; if (WARN_ON(!info)) return; + write_lock_irqsave(&evtchn_rwlock, flags); + + if (!list_empty(&info->eoi_list)) + lateeoi_list_del(info); + list_del(&info->list); set_info_for_irq(irq, NULL); WARN_ON(info->refcnt > 0); + write_unlock_irqrestore(&evtchn_rwlock, flags); + kfree(info); /* Legacy IRQ descriptors are managed by the arch. */ @@ -841,7 +1036,7 @@ int xen_pirq_from_irq(unsigned irq) } EXPORT_SYMBOL_GPL(xen_pirq_from_irq); -int bind_evtchn_to_irq(evtchn_port_t evtchn) +static int bind_evtchn_to_irq_chip(evtchn_port_t evtchn, struct irq_chip *chip) { int irq; int ret; @@ -858,7 +1053,7 @@ int bind_evtchn_to_irq(evtchn_port_t evtchn) if (irq < 0) goto out; - irq_set_chip_and_handler_name(irq, &xen_dynamic_chip, + irq_set_chip_and_handler_name(irq, chip, handle_edge_irq, "event"); ret = xen_irq_info_evtchn_setup(irq, evtchn); @@ -879,8 +1074,19 @@ out: return irq; } + +int bind_evtchn_to_irq(evtchn_port_t evtchn) +{ + return bind_evtchn_to_irq_chip(evtchn, &xen_dynamic_chip); +} EXPORT_SYMBOL_GPL(bind_evtchn_to_irq); +int bind_evtchn_to_irq_lateeoi(evtchn_port_t evtchn) +{ + return bind_evtchn_to_irq_chip(evtchn, &xen_lateeoi_chip); +} +EXPORT_SYMBOL_GPL(bind_evtchn_to_irq_lateeoi); + static int bind_ipi_to_irq(unsigned int ipi, unsigned int cpu) { struct evtchn_bind_ipi bind_ipi; @@ -922,8 +1128,9 @@ static int bind_ipi_to_irq(unsigned int ipi, unsigned int cpu) return irq; } -int bind_interdomain_evtchn_to_irq(unsigned int remote_domain, - evtchn_port_t remote_port) +static int bind_interdomain_evtchn_to_irq_chip(unsigned int remote_domain, + evtchn_port_t remote_port, + struct irq_chip *chip) { struct evtchn_bind_interdomain bind_interdomain; int err; @@ -934,10 +1141,26 @@ int bind_interdomain_evtchn_to_irq(unsigned int remote_domain, err = HYPERVISOR_event_channel_op(EVTCHNOP_bind_interdomain, &bind_interdomain); - return err ? : bind_evtchn_to_irq(bind_interdomain.local_port); + return err ? : bind_evtchn_to_irq_chip(bind_interdomain.local_port, + chip); +} + +int bind_interdomain_evtchn_to_irq(unsigned int remote_domain, + evtchn_port_t remote_port) +{ + return bind_interdomain_evtchn_to_irq_chip(remote_domain, remote_port, + &xen_dynamic_chip); } EXPORT_SYMBOL_GPL(bind_interdomain_evtchn_to_irq); +int bind_interdomain_evtchn_to_irq_lateeoi(unsigned int remote_domain, + evtchn_port_t remote_port) +{ + return bind_interdomain_evtchn_to_irq_chip(remote_domain, remote_port, + &xen_lateeoi_chip); +} +EXPORT_SYMBOL_GPL(bind_interdomain_evtchn_to_irq_lateeoi); + static int find_virq(unsigned int virq, unsigned int cpu, evtchn_port_t *evtchn) { struct evtchn_status status; @@ -1034,14 +1257,15 @@ static void unbind_from_irq(unsigned int irq) mutex_unlock(&irq_mapping_update_lock); } -int bind_evtchn_to_irqhandler(evtchn_port_t evtchn, - irq_handler_t handler, - unsigned long irqflags, - const char *devname, void *dev_id) +static int bind_evtchn_to_irqhandler_chip(evtchn_port_t evtchn, + irq_handler_t handler, + unsigned long irqflags, + const char *devname, void *dev_id, + struct irq_chip *chip) { int irq, retval; - irq = bind_evtchn_to_irq(evtchn); + irq = bind_evtchn_to_irq_chip(evtchn, chip); if (irq < 0) return irq; retval = request_irq(irq, handler, irqflags, devname, dev_id); @@ -1052,18 +1276,38 @@ int bind_evtchn_to_irqhandler(evtchn_port_t evtchn, return irq; } + +int bind_evtchn_to_irqhandler(evtchn_port_t evtchn, + irq_handler_t handler, + unsigned long irqflags, + const char *devname, void *dev_id) +{ + return bind_evtchn_to_irqhandler_chip(evtchn, handler, irqflags, + devname, dev_id, + &xen_dynamic_chip); +} EXPORT_SYMBOL_GPL(bind_evtchn_to_irqhandler); -int bind_interdomain_evtchn_to_irqhandler(unsigned int remote_domain, - evtchn_port_t remote_port, - irq_handler_t handler, - unsigned long irqflags, - const char *devname, - void *dev_id) +int bind_evtchn_to_irqhandler_lateeoi(evtchn_port_t evtchn, + irq_handler_t handler, + unsigned long irqflags, + const char *devname, void *dev_id) +{ + return bind_evtchn_to_irqhandler_chip(evtchn, handler, irqflags, + devname, dev_id, + &xen_lateeoi_chip); +} +EXPORT_SYMBOL_GPL(bind_evtchn_to_irqhandler_lateeoi); + +static int bind_interdomain_evtchn_to_irqhandler_chip( + unsigned int remote_domain, evtchn_port_t remote_port, + irq_handler_t handler, unsigned long irqflags, + const char *devname, void *dev_id, struct irq_chip *chip) { int irq, retval; - irq = bind_interdomain_evtchn_to_irq(remote_domain, remote_port); + irq = bind_interdomain_evtchn_to_irq_chip(remote_domain, remote_port, + chip); if (irq < 0) return irq; @@ -1075,8 +1319,33 @@ int bind_interdomain_evtchn_to_irqhandler(unsigned int remote_domain, return irq; } + +int bind_interdomain_evtchn_to_irqhandler(unsigned int remote_domain, + evtchn_port_t remote_port, + irq_handler_t handler, + unsigned long irqflags, + const char *devname, + void *dev_id) +{ + return bind_interdomain_evtchn_to_irqhandler_chip(remote_domain, + remote_port, handler, irqflags, devname, + dev_id, &xen_dynamic_chip); +} EXPORT_SYMBOL_GPL(bind_interdomain_evtchn_to_irqhandler); +int bind_interdomain_evtchn_to_irqhandler_lateeoi(unsigned int remote_domain, + evtchn_port_t remote_port, + irq_handler_t handler, + unsigned long irqflags, + const char *devname, + void *dev_id) +{ + return bind_interdomain_evtchn_to_irqhandler_chip(remote_domain, + remote_port, handler, irqflags, devname, + dev_id, &xen_lateeoi_chip); +} +EXPORT_SYMBOL_GPL(bind_interdomain_evtchn_to_irqhandler_lateeoi); + int bind_virq_to_irqhandler(unsigned int virq, unsigned int cpu, irq_handler_t handler, unsigned long irqflags, const char *devname, void *dev_id) @@ -1189,7 +1458,7 @@ int evtchn_get(evtchn_port_t evtchn) goto done; err = -EINVAL; - if (info->refcnt <= 0) + if (info->refcnt <= 0 || info->refcnt == SHRT_MAX) goto done; info->refcnt++; @@ -1228,21 +1497,81 @@ void xen_send_IPI_one(unsigned int cpu, enum ipi_vector vector) notify_remote_via_irq(irq); } +struct evtchn_loop_ctrl { + ktime_t timeout; + unsigned count; + bool defer_eoi; +}; + +void handle_irq_for_port(evtchn_port_t port, struct evtchn_loop_ctrl *ctrl) +{ + int irq; + struct irq_info *info; + + irq = get_evtchn_to_irq(port); + if (irq == -1) + return; + + /* + * Check for timeout every 256 events. + * We are setting the timeout value only after the first 256 + * events in order to not hurt the common case of few loop + * iterations. The 256 is basically an arbitrary value. + * + * In case we are hitting the timeout we need to defer all further + * EOIs in order to ensure to leave the event handling loop rather + * sooner than later. + */ + if (!ctrl->defer_eoi && !(++ctrl->count & 0xff)) { + ktime_t kt = ktime_get(); + + if (!ctrl->timeout) { + kt = ktime_add_ms(kt, + jiffies_to_msecs(event_loop_timeout)); + ctrl->timeout = kt; + } else if (kt > ctrl->timeout) { + ctrl->defer_eoi = true; + } + } + + info = info_for_irq(irq); + + if (ctrl->defer_eoi) { + info->eoi_cpu = smp_processor_id(); + info->irq_epoch = __this_cpu_read(irq_epoch); + info->eoi_time = get_jiffies_64() + event_eoi_delay; + } + + generic_handle_irq(irq); +} + static void __xen_evtchn_do_upcall(void) { struct vcpu_info *vcpu_info = __this_cpu_read(xen_vcpu); int cpu = smp_processor_id(); + struct evtchn_loop_ctrl ctrl = { 0 }; + + read_lock(&evtchn_rwlock); do { |