diff options
Diffstat (limited to 'drivers/xen')
| -rw-r--r-- | drivers/xen/Makefile | 1 | ||||
| -rw-r--r-- | drivers/xen/balloon.c | 72 | ||||
| -rw-r--r-- | drivers/xen/events/events_2l.c | 15 | ||||
| -rw-r--r-- | drivers/xen/events/events_base.c | 121 | ||||
| -rw-r--r-- | drivers/xen/events/events_fifo.c | 49 | ||||
| -rw-r--r-- | drivers/xen/events/events_internal.h | 1 | ||||
| -rw-r--r-- | drivers/xen/gntdev.c | 13 | ||||
| -rw-r--r-- | drivers/xen/grant-table.c | 156 | ||||
| -rw-r--r-- | drivers/xen/manage.c | 86 | ||||
| -rw-r--r-- | drivers/xen/pcpu.c | 1 | ||||
| -rw-r--r-- | drivers/xen/platform-pci.c | 2 | ||||
| -rw-r--r-- | drivers/xen/xen-acpi-cpuhotplug.c | 2 | ||||
| -rw-r--r-- | drivers/xen/xen-acpi-memhotplug.c | 2 | ||||
| -rw-r--r-- | drivers/xen/xen-acpi-pad.c | 26 | ||||
| -rw-r--r-- | drivers/xen/xen-acpi-processor.c | 19 | ||||
| -rw-r--r-- | drivers/xen/xen-pciback/pci_stub.c | 25 | ||||
| -rw-r--r-- | drivers/xen/xen-pciback/pciback_ops.c | 10 | ||||
| -rw-r--r-- | drivers/xen/xen-pciback/vpci.c | 2 | ||||
| -rw-r--r-- | drivers/xen/xen-pciback/xenbus.c | 4 | ||||
| -rw-r--r-- | drivers/xen/xen-selfballoon.c | 1 | ||||
| -rw-r--r-- | drivers/xen/xenbus/xenbus_client.c | 27 | ||||
| -rw-r--r-- | drivers/xen/xenbus/xenbus_xs.c | 44 | ||||
| -rw-r--r-- | drivers/xen/xencomm.c | 219 |
23 files changed, 300 insertions, 598 deletions
diff --git a/drivers/xen/Makefile b/drivers/xen/Makefile index d75c811bfa5..45e00afa7f2 100644 --- a/drivers/xen/Makefile +++ b/drivers/xen/Makefile @@ -16,7 +16,6 @@ xen-pad-$(CONFIG_X86) += xen-acpi-pad.o dom0-$(CONFIG_X86) += pcpu.o obj-$(CONFIG_XEN_DOM0) += $(dom0-y) obj-$(CONFIG_BLOCK) += biomerge.o -obj-$(CONFIG_XEN_XENCOMM) += xencomm.o obj-$(CONFIG_XEN_BALLOON) += xen-balloon.o obj-$(CONFIG_XEN_SELFBALLOONING) += xen-selfballoon.o obj-$(CONFIG_XEN_DEV_EVTCHN) += xen-evtchn.o diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c index 37d06ea624a..5c660c77f03 100644 --- a/drivers/xen/balloon.c +++ b/drivers/xen/balloon.c @@ -399,11 +399,25 @@ static enum bp_state decrease_reservation(unsigned long nr_pages, gfp_t gfp) state = BP_EAGAIN; break; } + scrub_page(page); - pfn = page_to_pfn(page); - frame_list[i] = pfn_to_mfn(pfn); + frame_list[i] = page_to_pfn(page); + } - scrub_page(page); + /* + * Ensure that ballooned highmem pages don't have kmaps. + * + * Do this before changing the p2m as kmap_flush_unused() + * reads PTEs to obtain pages (and hence needs the original + * p2m entry). + */ + kmap_flush_unused(); + + /* Update direct mapping, invalidate P2M, and add to balloon. */ + for (i = 0; i < nr_pages; i++) { + pfn = frame_list[i]; + frame_list[i] = pfn_to_mfn(pfn); + page = pfn_to_page(pfn); #ifdef CONFIG_XEN_HAVE_PVMMU /* @@ -412,28 +426,24 @@ static enum bp_state decrease_reservation(unsigned long nr_pages, gfp_t gfp) * p2m are consistent. */ if (!xen_feature(XENFEAT_auto_translated_physmap)) { - unsigned long p; - struct page *scratch_page = get_balloon_scratch_page(); - if (!PageHighMem(page)) { + struct page *scratch_page = get_balloon_scratch_page(); + ret = HYPERVISOR_update_va_mapping( (unsigned long)__va(pfn << PAGE_SHIFT), pfn_pte(page_to_pfn(scratch_page), PAGE_KERNEL_RO), 0); BUG_ON(ret); - } - p = page_to_pfn(scratch_page); - __set_phys_to_machine(pfn, pfn_to_mfn(p)); - put_balloon_scratch_page(); + put_balloon_scratch_page(); + } + __set_phys_to_machine(pfn, INVALID_P2M_ENTRY); } #endif - balloon_append(pfn_to_page(pfn)); + balloon_append(page); } - /* Ensure that ballooned highmem pages don't have kmaps. */ - kmap_flush_unused(); flush_tlb_all(); set_xen_guest_handle(reservation.extent_start, frame_list); @@ -592,19 +602,29 @@ static void __init balloon_add_region(unsigned long start_pfn, } } +static int alloc_balloon_scratch_page(int cpu) +{ + if (per_cpu(balloon_scratch_page, cpu) != NULL) + return 0; + + per_cpu(balloon_scratch_page, cpu) = alloc_page(GFP_KERNEL); + if (per_cpu(balloon_scratch_page, cpu) == NULL) { + pr_warn("Failed to allocate balloon_scratch_page for cpu %d\n", cpu); + return -ENOMEM; + } + + return 0; +} + + static int balloon_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu) { int cpu = (long)hcpu; switch (action) { case CPU_UP_PREPARE: - if (per_cpu(balloon_scratch_page, cpu) != NULL) - break; - per_cpu(balloon_scratch_page, cpu) = alloc_page(GFP_KERNEL); - if (per_cpu(balloon_scratch_page, cpu) == NULL) { - pr_warn("Failed to allocate balloon_scratch_page for cpu %d\n", cpu); + if (alloc_balloon_scratch_page(cpu)) return NOTIFY_BAD; - } break; default: break; @@ -624,15 +644,17 @@ static int __init balloon_init(void) return -ENODEV; if (!xen_feature(XENFEAT_auto_translated_physmap)) { - for_each_online_cpu(cpu) - { - per_cpu(balloon_scratch_page, cpu) = alloc_page(GFP_KERNEL); - if (per_cpu(balloon_scratch_page, cpu) == NULL) { - pr_warn("Failed to allocate balloon_scratch_page for cpu %d\n", cpu); + register_cpu_notifier(&balloon_cpu_notifier); + + get_online_cpus(); + for_each_online_cpu(cpu) { + if (alloc_balloon_scratch_page(cpu)) { + put_online_cpus(); + unregister_cpu_notifier(&balloon_cpu_notifier); return -ENOMEM; } } - register_cpu_notifier(&balloon_cpu_notifier); + put_online_cpus(); } pr_info("Initialising balloon driver\n"); diff --git a/drivers/xen/events/events_2l.c b/drivers/xen/events/events_2l.c index d7ff9175730..5db43fc100a 100644 --- a/drivers/xen/events/events_2l.c +++ b/drivers/xen/events/events_2l.c @@ -166,7 +166,6 @@ static void evtchn_2l_handle_events(unsigned cpu) int start_word_idx, start_bit_idx; int word_idx, bit_idx; int i; - struct irq_desc *desc; struct shared_info *s = HYPERVISOR_shared_info; struct vcpu_info *vcpu_info = __this_cpu_read(xen_vcpu); @@ -176,11 +175,8 @@ static void evtchn_2l_handle_events(unsigned cpu) unsigned int evtchn = evtchn_from_irq(irq); word_idx = evtchn / BITS_PER_LONG; bit_idx = evtchn % BITS_PER_LONG; - if (active_evtchns(cpu, s, word_idx) & (1ULL << bit_idx)) { - desc = irq_to_desc(irq); - if (desc) - generic_handle_irq_desc(irq, desc); - } + if (active_evtchns(cpu, s, word_idx) & (1ULL << bit_idx)) + generic_handle_irq(irq); } /* @@ -245,11 +241,8 @@ static void evtchn_2l_handle_events(unsigned cpu) port = (word_idx * BITS_PER_EVTCHN_WORD) + bit_idx; irq = get_evtchn_to_irq(port); - if (irq != -1) { - desc = irq_to_desc(irq); - if (desc) - generic_handle_irq_desc(irq, desc); - } + if (irq != -1) + generic_handle_irq(irq); 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 4672e003c0a..c919d3d5c84 100644 --- a/drivers/xen/events/events_base.c +++ b/drivers/xen/events/events_base.c @@ -336,9 +336,8 @@ static void bind_evtchn_to_cpu(unsigned int chn, unsigned int cpu) BUG_ON(irq == -1); #ifdef CONFIG_SMP - cpumask_copy(irq_to_desc(irq)->irq_data.affinity, cpumask_of(cpu)); + cpumask_copy(irq_get_irq_data(irq)->affinity, cpumask_of(cpu)); #endif - xen_evtchn_port_bind_to_cpu(info, cpu); info->cpu = cpu; @@ -373,10 +372,8 @@ static void xen_irq_init(unsigned irq) { struct irq_info *info; #ifdef CONFIG_SMP - struct irq_desc *desc = irq_to_desc(irq); - /* By default all event channels notify CPU#0. */ - cpumask_copy(desc->irq_data.affinity, cpumask_of(0)); + cpumask_copy(irq_get_irq_data(irq)->affinity, cpumask_of(0)); #endif info = kzalloc(sizeof(*info), GFP_KERNEL); @@ -391,29 +388,22 @@ static void xen_irq_init(unsigned irq) list_add_tail(&info->list, &xen_irq_list_head); } -static int __must_check xen_allocate_irq_dynamic(void) +static int __must_check xen_allocate_irqs_dynamic(int nvec) { - int first = 0; - int irq; + int i, irq = irq_alloc_descs(-1, 0, nvec, -1); -#ifdef CONFIG_X86_IO_APIC - /* - * For an HVM guest or domain 0 which see "real" (emulated or - * actual respectively) GSIs we allocate dynamic IRQs - * e.g. those corresponding to event channels or MSIs - * etc. from the range above those "real" GSIs to avoid - * collisions. - */ - if (xen_initial_domain() || xen_hvm_domain()) - first = get_nr_irqs_gsi(); -#endif + if (irq >= 0) { + for (i = 0; i < nvec; i++) + xen_irq_init(irq + i); + } - irq = irq_alloc_desc_from(first, -1); + return irq; +} - if (irq >= 0) - xen_irq_init(irq); +static inline int __must_check xen_allocate_irq_dynamic(void) +{ - return irq; + return xen_allocate_irqs_dynamic(1); } static int __must_check xen_allocate_irq_gsi(unsigned gsi) @@ -469,9 +459,6 @@ static void xen_evtchn_close(unsigned int port) close.port = port; if (HYPERVISOR_event_channel_op(EVTCHNOP_close, &close) != 0) BUG(); - - /* Closed ports are implicitly re-bound to VCPU0. */ - bind_evtchn_to_cpu(port, 0); } static void pirq_query_unmask(int irq) @@ -490,13 +477,6 @@ static void pirq_query_unmask(int irq) info->u.pirq.flags |= PIRQ_NEEDS_EOI; } -static bool probing_irq(int irq) -{ - struct irq_desc *desc = irq_to_desc(irq); - - return desc && desc->action == NULL; -} - static void eoi_pirq(struct irq_data *data) { int evtchn = evtchn_from_irq(data->irq); @@ -538,8 +518,7 @@ static unsigned int __startup_pirq(unsigned int irq) BIND_PIRQ__WILL_SHARE : 0; rc = HYPERVISOR_event_channel_op(EVTCHNOP_bind_pirq, &bind_pirq); if (rc != 0) { - if (!probing_irq(irq)) - pr_info("Failed to obtain physical IRQ %d\n", irq); + pr_warn("Failed to obtain physical IRQ %d\n", irq); return 0; } evtchn = bind_pirq.port; @@ -741,22 +720,25 @@ int xen_allocate_pirq_msi(struct pci_dev *dev, struct msi_desc *msidesc) } int xen_bind_pirq_msi_to_irq(struct pci_dev *dev, struct msi_desc *msidesc, - int pirq, const char *name, domid_t domid) + int pirq, int nvec, const char *name, domid_t domid) { - int irq, ret; + int i, irq, ret; mutex_lock(&irq_mapping_update_lock); - irq = xen_allocate_irq_dynamic(); + irq = xen_allocate_irqs_dynamic(nvec); if (irq < 0) goto out; - irq_set_chip_and_handler_name(irq, &xen_pirq_chip, handle_edge_irq, - name); + for (i = 0; i < nvec; i++) { + irq_set_chip_and_handler_name(irq + i, &xen_pirq_chip, handle_edge_irq, name); + + ret = xen_irq_info_pirq_setup(irq + i, 0, pirq + i, 0, domid, + i == 0 ? 0 : PIRQ_MSI_GROUP); + if (ret < 0) + goto error_irq; + } - ret = xen_irq_info_pirq_setup(irq, 0, pirq, 0, domid, 0); - if (ret < 0) - goto error_irq; ret = irq_set_msi_desc(irq, msidesc); if (ret < 0) goto error_irq; @@ -764,7 +746,8 @@ out: mutex_unlock(&irq_mapping_update_lock); return irq; error_irq: - __unbind_from_irq(irq); + for (; i >= 0; i--) + __unbind_from_irq(irq + i); mutex_unlock(&irq_mapping_update_lock); return ret; } @@ -772,18 +755,18 @@ error_irq: int xen_destroy_irq(int irq) { - struct irq_desc *desc; struct physdev_unmap_pirq unmap_irq; struct irq_info *info = info_for_irq(irq); int rc = -ENOENT; mutex_lock(&irq_mapping_update_lock); - desc = irq_to_desc(irq); - if (!desc) - goto out; - - if (xen_initial_domain()) { + /* + * If trying to remove a vector in a MSI group different + * than the first one skip the PIRQ unmap unless this vector + * is the first one in the group. + */ + if (xen_initial_domain() && !(info->u.pirq.flags & PIRQ_MSI_GROUP)) { unmap_irq.pirq = info->u.pirq.pirq; unmap_irq.domid = info->u.pirq.domid; rc = HYPERVISOR_physdev_op(PHYSDEVOP_unmap_pirq, &unmap_irq); @@ -862,6 +845,8 @@ int bind_evtchn_to_irq(unsigned int evtchn) irq = ret; goto out; } + /* New interdomain events are bound to VCPU 0. */ + bind_evtchn_to_cpu(evtchn, 0); } else { struct irq_info *info = info_for_irq(irq); WARN_ON(info == NULL || info->type != IRQT_EVTCHN); @@ -1248,6 +1233,7 @@ void xen_evtchn_do_upcall(struct pt_regs *regs) irq_enter(); #ifdef CONFIG_X86 exit_idle(); + inc_irq_stat(irq_hv_callback_count); #endif __xen_evtchn_do_upcall(); @@ -1337,31 +1323,11 @@ static int rebind_irq_to_cpu(unsigned irq, unsigned tcpu) static int set_affinity_irq(struct irq_data *data, const struct cpumask *dest, bool force) { - unsigned tcpu = cpumask_first(dest); + unsigned tcpu = cpumask_first_and(dest, cpu_online_mask); return rebind_irq_to_cpu(data->irq, tcpu); } -static int retrigger_evtchn(int evtchn) -{ - int masked; - - if (!VALID_EVTCHN(evtchn)) - return 0; - - masked = test_and_set_mask(evtchn); - set_evtchn(evtchn); - if (!masked) - unmask_evtchn(evtchn); - - return 1; -} - -int resend_irq_on_evtchn(unsigned int irq) -{ - return retrigger_evtchn(evtchn_from_irq(irq)); -} - static void enable_dynirq(struct irq_data *data) { int evtchn = evtchn_from_irq(data->irq); @@ -1396,7 +1362,18 @@ static void mask_ack_dynirq(struct irq_data *data) static int retrigger_dynirq(struct irq_data *data) { - return retrigger_evtchn(evtchn_from_irq(data->irq)); + unsigned int evtchn = evtchn_from_irq(data->irq); + int masked; + + if (!VALID_EVTCHN(evtchn)) + return 0; + + masked = test_and_set_mask(evtchn); + set_evtchn(evtchn); + if (!masked) + unmask_evtchn(evtchn); + + return 1; } static void restore_pirqs(void) diff --git a/drivers/xen/events/events_fifo.c b/drivers/xen/events/events_fifo.c index 1de2a191b39..84b4bfb8434 100644 --- a/drivers/xen/events/events_fifo.c +++ b/drivers/xen/events/events_fifo.c @@ -66,7 +66,22 @@ static DEFINE_PER_CPU(struct evtchn_fifo_queue, cpu_queue); static event_word_t *event_array[MAX_EVENT_ARRAY_PAGES] __read_mostly; static unsigned event_array_pages __read_mostly; +/* + * sync_set_bit() and friends must be unsigned long aligned on non-x86 + * platforms. + */ +#if !defined(CONFIG_X86) && BITS_PER_LONG > 32 + +#define BM(w) (unsigned long *)((unsigned long)w & ~0x7UL) +#define EVTCHN_FIFO_BIT(b, w) \ + (((unsigned long)w & 0x4UL) ? (EVTCHN_FIFO_ ##b + 32) : EVTCHN_FIFO_ ##b) + +#else + #define BM(w) ((unsigned long *)(w)) +#define EVTCHN_FIFO_BIT(b, w) EVTCHN_FIFO_ ##b + +#endif static inline event_word_t *event_word_from_port(unsigned port) { @@ -161,33 +176,38 @@ static void evtchn_fifo_bind_to_cpu(struct irq_info *info, unsigned cpu) static void evtchn_fifo_clear_pending(unsigned port) { event_word_t *word = event_word_from_port(port); - sync_clear_bit(EVTCHN_FIFO_PENDING, BM(word)); + sync_clear_bit(EVTCHN_FIFO_BIT(PENDING, word), BM(word)); } static void evtchn_fifo_set_pending(unsigned port) { event_word_t *word = event_word_from_port(port); - sync_set_bit(EVTCHN_FIFO_PENDING, BM(word)); + sync_set_bit(EVTCHN_FIFO_BIT(PENDING, word), BM(word)); } static bool evtchn_fifo_is_pending(unsigned port) { event_word_t *word = event_word_from_port(port); - return sync_test_bit(EVTCHN_FIFO_PENDING, BM(word)); + return sync_test_bit(EVTCHN_FIFO_BIT(PENDING, word), BM(word)); } static bool evtchn_fifo_test_and_set_mask(unsigned port) { event_word_t *word = event_word_from_port(port); - return sync_test_and_set_bit(EVTCHN_FIFO_MASKED, BM(word)); + return sync_test_and_set_bit(EVTCHN_FIFO_BIT(MASKED, word), BM(word)); } static void evtchn_fifo_mask(unsigned port) { event_word_t *word = event_word_from_port(port); - sync_set_bit(EVTCHN_FIFO_MASKED, BM(word)); + sync_set_bit(EVTCHN_FIFO_BIT(MASKED, word), BM(word)); } +static bool evtchn_fifo_is_masked(unsigned port) +{ + event_word_t *word = event_word_from_port(port); + return sync_test_bit(EVTCHN_FIFO_BIT(MASKED, word), BM(word)); +} /* * Clear MASKED, spinning if BUSY is set. */ @@ -211,7 +231,7 @@ static void evtchn_fifo_unmask(unsigned port) BUG_ON(!irqs_disabled()); clear_masked(word); - if (sync_test_bit(EVTCHN_FIFO_PENDING, BM(word))) { + if (evtchn_fifo_is_pending(port)) { struct evtchn_unmask unmask = { .port = port }; (void)HYPERVISOR_event_channel_op(EVTCHNOP_unmask, &unmask); } @@ -235,19 +255,15 @@ static uint32_t clear_linked(volatile event_word_t *word) static void handle_irq_for_port(unsigned port) { int irq; - struct irq_desc *desc; irq = get_evtchn_to_irq(port); - if (irq != -1) { - desc = irq_to_desc(irq); - if (desc) - generic_handle_irq_desc(irq, desc); - } + if (irq != -1) + generic_handle_irq(irq); } static void consume_one_event(unsigned cpu, struct evtchn_fifo_control_block *control_block, - unsigned priority, uint32_t *ready) + unsigned priority, unsigned long *ready) { struct evtchn_fifo_queue *q = &per_cpu(cpu_queue, cpu); uint32_t head; @@ -277,10 +293,9 @@ static void consume_one_event(unsigned cpu, * copy of the ready word. */ if (head == 0) - clear_bit(priority, BM(ready)); + clear_bit(priority, ready); - if (sync_test_bit(EVTCHN_FIFO_PENDING, BM(word)) - && !sync_test_bit(EVTCHN_FIFO_MASKED, BM(word))) + if (evtchn_fifo_is_pending(port) && !evtchn_fifo_is_masked(port)) handle_irq_for_port(port); q->head[priority] = head; @@ -289,7 +304,7 @@ static void consume_one_event(unsigned cpu, static void evtchn_fifo_handle_events(unsigned cpu) { struct evtchn_fifo_control_block *control_block; - uint32_t ready; + unsigned long ready; unsigned q; control_block = per_cpu(cpu_control_block, cpu); diff --git a/drivers/xen/events/events_internal.h b/drivers/xen/events/events_internal.h index 677f41a0fff..50c2050a1e3 100644 --- a/drivers/xen/events/events_internal.h +++ b/drivers/xen/events/events_internal.h @@ -53,6 +53,7 @@ struct irq_info { #define PIRQ_NEEDS_EOI (1 << 0) #define PIRQ_SHAREABLE (1 << 1) +#define PIRQ_MSI_GROUP (1 << 2) struct evtchn_ops { unsigned (*max_channels)(void); diff --git a/drivers/xen/gntdev.c b/drivers/xen/gntdev.c index 34a2704fbc8..073b4a19a8b 100644 --- a/drivers/xen/gntdev.c +++ b/drivers/xen/gntdev.c @@ -284,10 +284,8 @@ static int map_grant_pages(struct grant_map *map) } pr_debug("map %d+%d\n", map->index, map->count); - err = gnttab_map_refs_userspace(map->map_ops, - use_ptemod ? map->kmap_ops : NULL, - map->pages, - map->count); + err = gnttab_map_refs(map->map_ops, use_ptemod ? map->kmap_ops : NULL, + map->pages, map->count); if (err) return err; @@ -317,10 +315,9 @@ static int __unmap_grant_pages(struct grant_map *map, int offset, int pages) } } - err = gnttab_unmap_refs_userspace(map->unmap_ops + offset, - use_ptemod ? map->kmap_ops + offset : NULL, - map->pages + offset, - pages); + err = gnttab_unmap_refs(map->unmap_ops + offset, + use_ptemod ? map->kmap_ops + offset : NULL, map->pages + offset, + pages); if (err) return err; diff --git a/drivers/xen/grant-table.c b/drivers/xen/grant-table.c index 8ee13e2e45e..eeba7544f0c 100644 --- a/drivers/xen/grant-table.c +++ b/drivers/xen/grant-table.c @@ -928,17 +928,12 @@ void gnttab_batch_copy(struct gnttab_copy *batch, unsigned count) } EXPORT_SYMBOL_GPL(gnttab_batch_copy); -int __gnttab_map_refs(struct gnttab_map_grant_ref *map_ops, +int gnttab_map_refs(struct gnttab_map_grant_ref *map_ops, struct gnttab_map_grant_ref *kmap_ops, - struct page **pages, unsigned int count, - bool m2p_override) + struct page **pages, unsigned int count) { int i, ret; - bool lazy = false; - pte_t *pte; - unsigned long mfn, pfn; - BUG_ON(kmap_ops && !m2p_override); ret = HYPERVISOR_grant_table_op(GNTTABOP_map_grant_ref, map_ops, count); if (ret) return ret; @@ -949,149 +944,24 @@ int __gnttab_map_refs(struct gnttab_map_grant_ref *map_ops, gnttab_retry_eagain_gop(GNTTABOP_map_grant_ref, map_ops + i, &map_ops[i].status, __func__); - /* this is basically a nop on x86 */ - if (xen_feature(XENFEAT_auto_translated_physmap)) { - for (i = 0; i < count; i++) { - if (map_ops[i].status) - continue; - set_phys_to_machine(map_ops[i].host_addr >> PAGE_SHIFT, - map_ops[i].dev_bus_addr >> PAGE_SHIFT); - } - return 0; - } - - if (m2p_override && - !in_interrupt() && - paravirt_get_lazy_mode() == PARAVIRT_LAZY_NONE) { - arch_enter_lazy_mmu_mode(); - lazy = true; - } - - for (i = 0; i < count; i++) { - /* Do not add to override if the map failed. */ - if (map_ops[i].status) - continue; - - if (map_ops[i].flags & GNTMAP_contains_pte) { - pte = (pte_t *) (mfn_to_virt(PFN_DOWN(map_ops[i].host_addr)) + - (map_ops[i].host_addr & ~PAGE_MASK)); - mfn = pte_mfn(*pte); - } else { - mfn = PFN_DOWN(map_ops[i].dev_bus_addr); - } - pfn = page_to_pfn(pages[i]); - - WARN_ON(PagePrivate(pages[i])); - SetPagePrivate(pages[i]); - set_page_private(pages[i], mfn); - - pages[i]->index = pfn_to_mfn(pfn); - if (unlikely(!set_phys_to_machine(pfn, FOREIGN_FRAME(mfn)))) { - ret = -ENOMEM; - goto out; - } - if (m2p_override) - ret = m2p_add_override(mfn, pages[i], kmap_ops ? - &kmap_ops[i] : NULL); - if (ret) - goto out; - } - - out: - if (lazy) - arch_leave_lazy_mmu_mode(); - - return ret; -} - -int gnttab_map_refs(struct gnttab_map_grant_ref *map_ops, - struct page **pages, unsigned int count) -{ - return __gnttab_map_refs(map_ops, NULL, pages, count, false); + return set_foreign_p2m_mapping(map_ops, kmap_ops, pages, count); } EXPORT_SYMBOL_GPL(gnttab_map_refs); -int gnttab_map_refs_userspace(struct gnttab_map_grant_ref *map_ops, - struct gnttab_map_grant_ref *kmap_ops, - struct page **pages, unsigned int count) -{ - return __gnttab_map_refs(map_ops, kmap_ops, pages, count, true); -} -EXPORT_SYMBOL_GPL(gnttab_map_refs_userspace); - -int __gnttab_unmap_refs(struct gnttab_unmap_grant_ref *unmap_ops, +int gnttab_unmap_refs(struct gnttab_unmap_grant_ref *unmap_ops, struct gnttab_map_grant_ref *kmap_ops, - struct page **pages, unsigned int count, - bool m2p_override) + struct page **pages, unsigned int count) { - int i, ret; - bool lazy = false; - unsigned long pfn, mfn; + int ret; - BUG_ON(kmap_ops && !m2p_override); ret = HYPERVISOR_grant_table_op(GNTTABOP_unmap_grant_ref, unmap_ops, count); if (ret) return ret; - /* this is basically a nop on x86 */ - if (xen_feature(XENFEAT_auto_translated_physmap)) { - for (i = 0; i < count; i++) { - set_phys_to_machine(unmap_ops[i].host_addr >> PAGE_SHIFT, - INVALID_P2M_ENTRY); - } - return 0; - } - - if (m2p_override && - !in_interrupt() && - paravirt_get_lazy_mode() == PARAVIRT_LAZY_NONE) { - arch_enter_lazy_mmu_mode(); - lazy = true; - } - - for (i = 0; i < count; i++) { - pfn = page_to_pfn(pages[i]); - mfn = get_phys_to_machine(pfn); - if (mfn == INVALID_P2M_ENTRY || !(mfn & FOREIGN_FRAME_BIT)) { - ret = -EINVAL; - goto out; - } - - set_page_private(pages[i], INVALID_P2M_ENTRY); - WARN_ON(!PagePrivate(pages[i])); - ClearPagePrivate(pages[i]); - set_phys_to_machine(pfn, pages[i]->index); - if (m2p_override) - ret = m2p_remove_override(pages[i], - kmap_ops ? - &kmap_ops[i] : NULL, - mfn); - if (ret) - goto out; - } - - out: - if (lazy) - arch_leave_lazy_mmu_mode(); - - return ret; -} - -int gnttab_unmap_refs(struct gnttab_unmap_grant_ref *map_ops, - struct page **pages, unsigned int count) -{ - return __gnttab_unmap_refs(map_ops, NULL, pages, count, false); + return clear_foreign_p2m_mapping(unmap_ops, kmap_ops, pages, count); } EXPORT_SYMBOL_GPL(gnttab_unmap_refs); -int gnttab_unmap_refs_userspace(struct gnttab_unmap_grant_ref *map_ops, - struct gnttab_map_grant_ref *kmap_ops, - struct page **pages, unsigned int count) -{ - return __gnttab_unmap_refs(map_ops, kmap_ops, pages, count, true); -} -EXPORT_SYMBOL_GPL(gnttab_unmap_refs_userspace); - static unsigned nr_status_frames(unsigned nr_grant_frames) { BUG_ON(grefs_per_grant_frame == 0); @@ -1298,7 +1168,8 @@ int gnttab_resume(void) int gnttab_suspend(void) { - gnttab_interface->unmap_frames(); + if (!xen_feature(XENFEAT_auto_translated_physmap)) + gnttab_interface->unmap_frames(); return 0; } @@ -1324,18 +1195,20 @@ static int gnttab_expand(unsigned int req_entries) int gnttab_init(void) { int i; + unsigned long max_nr_grant_frames; unsigned int max_nr_glist_frames, nr_glist_frames; unsigned int nr_init_grefs; int ret; gnttab_request_version(); + max_nr_grant_frames = gnttab_max_grant_frames(); nr_grant_frames = 1; /* Determine the maximum number of frames required for the * grant reference free list on the current hypervisor. */ BUG_ON(grefs_per_grant_frame == 0); - max_nr_glist_frames = (gnttab_max_grant_frames() * + max_nr_glist_frames = (max_nr_grant_frames * grefs_per_grant_frame / RPP); gnttab_list = kmalloc(max_nr_glist_frames * sizeof(grant_ref_t *), @@ -1352,6 +1225,11 @@ int gnttab_init(void) } } + ret = arch_gnttab_init(max_nr_grant_frames, + nr_status_frames(max_nr_grant_frames)); + if (ret < 0) + goto ini_nomem; + if (gnttab_setup() < 0) { ret = -ENODEV; goto ini_nomem; diff --git a/drivers/xen/manage.c b/drivers/xen/manage.c index 624e8dc2453..5f1e1f3cd18 100644 --- a/drivers/xen/manage.c +++ b/drivers/xen/manage.c @@ -41,32 +41,23 @@ static enum shutdown_state shutting_down = SHUTDOWN_INVALID; struct suspend_info { int cancelled; - unsigned long arg; /* extra hypercall argument */ - void (*pre)(void); - void (*post)(int cancelled); }; -#ifdef CONFIG_HIBERNATE_CALLBACKS -static void xen_hvm_post_suspend(int cancelled) -{ - xen_arch_hvm_post_suspend(cancelled); - gnttab_resume(); -} +static RAW_NOTIFIER_HEAD(xen_resume_notifier); -static void xen_pre_suspend(void) +void xen_resume_notifier_register(struct notifier_block *nb) { - xen_mm_pin_all(); - gnttab_suspend(); - xen_arch_pre_suspend(); + raw_notifier_chain_register(&xen_resume_notifier, nb); } +EXPORT_SYMBOL_GPL(xen_resume_notifier_register); -static void xen_post_suspend(int cancelled) +void xen_resume_notifier_unregister(struct notifier_block *nb) { - xen_arch_post_suspend(cancelled); - gnttab_resume(); - xen_mm_unpin_all(); + raw_notifier_chain_unregister(&xen_resume_notifier, nb); } +EXPORT_SYMBOL_GPL(xen_resume_notifier_unregister); +#ifdef CONFIG_HIBERNATE_CALLBACKS static int xen_suspend(void *data) { struct suspend_info *si = data; @@ -80,22 +71,23 @@ static int xen_suspend(void *data) return err; } - if (si->pre) - si->pre(); + gnttab_suspend(); + xen_arch_pre_suspend(); /* * This hypercall returns 1 if suspend was cancelled * or the domain was merely checkpointed, and 0 if it * is resuming in a new domain. */ - si->cancelled = HYPERVISOR_suspend(si->arg); + si->cancelled = HYPERVISOR_suspend(xen_pv_domain() + ? virt_to_mfn(xen_start_info) + : 0); - if (si->post) - si->post(si->cancelled); + xen_arch_post_suspend(si->cancelled); + gnttab_resume(); if (!si->cancelled) { xen_irq_resume(); - xen_console_resume(); xen_timer_resume(); } @@ -140,18 +132,14 @@ static void do_suspend(void) si.cancelled = 1; - if (xen_hvm_domain()) { - si.arg = 0UL; - si.pre = NULL; - si.post = &xen_hvm_post_suspend; - } else { - si.arg = virt_to_mfn(xen_start_info); - si.pre = &xen_pre_suspend; - si.post = &xen_post_suspend; - } - err = stop_machine(xen_suspend, &si, cpumask_of(0)); + /* Resume console as early as possible. */ + if (!si.cancelled) + xen_console_resume(); + + raw_notifier_call_chain(&xen_resume_notifier, 0, NULL); + dpm_resume_start(si.cancelled ? PMSG_THAW : PMSG_RESTORE); if (err) { @@ -182,10 +170,32 @@ struct shutdown_handler { void (*cb)(void); }; +static int poweroff_nb(struct notifier_block *cb, unsigned long code, void *unused) +{ + switch (code) { + case SYS_DOWN: + case SYS_HALT: + case SYS_POWER_OFF: + shutting_down = SHUTDOWN_POWEROFF; + default: + break; + } + return NOTIFY_DONE; +} static void do_poweroff(void) { - shutting_down = SHUTDOWN_POWEROFF; - orderly_poweroff(false); + switch (system_state) { + case SYSTEM_BOOTING: + orderly_poweroff(true); + break; + case SYSTEM_RUNNING: + orderly_poweroff(false); + break; + default: + /* Don't do it when we are halting/rebooting. */ + pr_info("Ignoring Xen toolstack shutdown.\n"); + break; + } } static void do_reboot(void) @@ -291,6 +301,10 @@ static struct xenbus_watch shutdown_watch = { .callback = shutdown_handler }; +static struct notifier_block xen_reboot_nb = { + .notifier_call = poweroff_nb, +}; + static int setup_shutdown_watcher(void) { int err; @@ -301,6 +315,7 @@ static int setup_shutdown_watcher(void) return err; } + #ifdef CONFIG_MAGIC_SYSRQ err = register_xenbus_watch(&sysrq_watch); if (err) { @@ -329,6 +344,7 @@ int xen_setup_shutdown_event(void) if (!xen_domain()) return -ENODEV; register_xenstore_notifier(&xenstore_notifier); + register_reboot_notifier(&xen_reboot_nb); return 0; } diff --git a/drivers/xen/pcpu.c b/drivers/xen/pcpu.c index 79e1dff7ed4..0aac403d53f 100644 --- a/drivers/xen/pcpu.c +++ b/drivers/xen/pcpu.c @@ -40,6 +40,7 @@ #include <linux/capability.h> #include <xen/xen.h> +#include <xen/acpi.h> #include <xen/xenbus.h> #include <xen/events.h> #include <xen/interface/platform.h> diff --git a/drivers/xen/platform-pci.c b/drivers/xen/platform-pci.c index a1361c312c0..3454973dc3b 100644 --- a/drivers/xen/platform-pci.c +++ b/drivers/xen/platform-pci.c @@ -45,7 +45,7 @@ static unsigned long platform_mmio_alloc; static unsigned long platform_mmiolen; static uint64_t callback_via; -unsigned long alloc_xen_mmio(unsigned long len) +static unsigned long alloc_xen_mmio(unsigned long len) { unsigned long addr; diff --git a/drivers/xen/xen-acpi-cpuhotplug.c b/drivers/xen/xen-acpi-cpuhotplug.c index 80875fb770e..3e62ee4b3b6 100644 --- a/drivers/xen/xen-acpi-cpuhotplug.c +++ b/drivers/xen/xen-acpi-cpuhotplug.c @@ -313,7 +313,7 @@ static void acpi_processor_hotplug_notify(acpi_handle handle, goto out; } - (void) acpi_evaluate_hotplug_ost(handle, event, ost_code, NULL); + (void) acpi_evaluate_ost(handle, event, ost_code, NULL); out: acpi_scan_lock_release(); diff --git a/drivers/xen/xen-acpi-memhotplug.c b/drivers/xen/xen-acpi-memhotplug.c index f8d18626969..34e40b733f9 100644 --- a/drivers/xen/xen-acpi-memhotplug.c +++ b/drivers/xen/xen-acpi-memhotplug.c @@ -285,7 +285,7 @@ static void acpi_memory_device_notify(acpi_handle handle, u32 event, void *data) return; } - (void) acpi_evaluate_hotplug_ost(handle, event, ost_code, NULL); + (void) acpi_evaluate_ost(handle, event, ost_code, NULL); return; } diff --git a/drivers/xen/xen-acpi-pad.c b/drivers/xen/xen-acpi-pad.c index 40c4bc06b5f..f83b754505f 100644 --- a/drivers/xen/xen-acpi-pad.c +++ b/drivers/xen/xen-acpi-pad.c @@ -77,27 +77,14 @@ static int acpi_pad_pur(acpi_handle handle) return num; } -/* Notify firmware how many CPUs are idle */ -static void acpi_pad_ost(acpi_handle handle, int stat, - uint32_t idle_nums) -{ - union acpi_object params[3] = { - {.type = ACPI_TYPE_INTEGER,}, - {.type = ACPI_TYPE_INTEGER,}, - {.type = ACPI_TYPE_BUFFER,}, - }; - struct acpi_object_list arg_list = {3, params}; - - params[0].integer.value = ACPI_PROCESSOR_AGGREGATOR_NOTIFY; - params[1].integer.value = stat; - params[2].buffer.length = 4; - params[2].buffer.pointer = (void *)&idle_nums; - acpi_evaluate_object(handle, "_OST", &arg_list, NULL); -} - static void acpi_pad_handle_notify(acpi_handle handle) { int idle_nums; + struct acpi_buffer param = { + .length = 4, + .pointer = (void *)&idle_nums, + }; + mutex_lock(&xen_cpu_lock); idle_nums = acpi_pad_pur(handle); @@ -109,7 +96,8 @@ static void acpi_pad_handle_notify(acpi_handle handle) idle_nums = xen_acpi_pad_idle_cpus(idle_nums) ?: xen_acpi_pad_idle_cpus_num(); if (idle_nums >= 0) - acpi_pad_ost(handle, 0, idle_nums); + acpi_evaluate_ost(handle, ACPI_PROCESSOR_AGGREGATOR_NOTIFY, + 0, ¶m); mutex_unlock(&xen_cpu_lock); } diff --git a/drivers/xen/xen-acpi-processor.c b/drivers/xen/xen-acpi-processor.c index 7231859119f..59fc190f1e9 100644 --- a/drivers/xen/xen-acpi-processor.c +++ b/drivers/xen/xen-acpi-processor.c @@ -27,10 +27,10 @@ #include <linux/init.h> #include <linux/module.h> #include <linux/types.h> -#include <linux/syscore_ops.h> #include <linux/acpi.h> #include <acpi/processor.h> #include <xen/xen.h> +#include <xen/xen-ops.h> #include <xen/interface/platform.h> #include <asm/xen/hypercall.h> @@ -127,7 +127,7 @@ static int push_cxx_to_hypervisor(struct acpi_processor *_pr) pr_debug(" C%d: %s %d uS\n", cx->type, cx->desc, (u32)cx->latency); } - } else if (ret != -EINVAL) + } else if ((ret != -EINVAL) && (ret != -ENOSYS)) /* EINVAL means the ACPI ID is incorrect - meaning the ACPI * table is referencing a non-existing CPU - which can happen * with broken ACPI tables. */ @@ -259,7 +259,7 @@ static int push_pxx_to_hypervisor(struct acpi_processor *_pr) (u32) perf->states[i].power, (u32) perf->states[i].transition_latency); } - } else if (ret != -EINVAL) + } else if ((ret != -EINVAL) && (ret != -ENOSYS)) /* EINVAL means the ACPI ID is incorrect - meaning the ACPI * table is referencing a non-existing CPU - which can happen * with broken ACPI tables. */ @@ -495,14 +495,15 @@ static int xen_upload_processor_pm_data(void) return rc; } -static void xen_acpi_processor_resume(void) +static int xen_acpi_processor_resume(struct notifier_block *nb, + unsigned long action, void *data) { bitmap_zero(acpi_ids_done, nr_acpi_bits); - xen_upload_processor_pm_data(); + return xen_upload_processor_pm_data(); } -static struct syscore_ops xap_syscore_ops = { - .resume = xen_acpi_processor_resume, +struct notifier_block xen_acpi_processor_resume_nb = { + .notifier_call = xen_acpi_processor_resume, }; static int __init xen_acpi_processor_init(void) @@ -555,7 +556,7 @@ static int __init xen_acpi_processor_init(void) if (rc) goto err_unregister; - register_syscore_ops(&xap_syscore_ops); + xen_resume_notifier_register(&xen_acpi_processor_resume_nb); return 0; err_unregister: @@ -574,7 +575,7 @@ static void __exit xen_acpi_processor_exit(void) { int i; - unregister_syscore_ops(&xap_syscore_ops); + xen_resume_notifier_unregister(&xen_acpi_processor_resume_nb); kfree(acpi_ids_done); kfree(acpi_id_present); kfree(acpi_id_cst_present); diff --git a/drivers/xen/xen-pciback/pci_stub.c b/drivers/xen/xen-pciback/pci_stub.c index 62fcd485f0a..d57a173685f 100644 --- a/drivers/xen/xen-pciback/pci_stub.c +++ b/drivers/xen/xen-pciback/pci_stub.c @@ -242,6 +242,15 @@ struct pci_dev *pcistub_get_pci_dev(struct xen_pcibk_device *pdev, return found_dev; } +/* + * Called when: + * - XenBus state has been reconfigure (pci unplug). See xen_pcibk_remove_device + * - XenBus state has been disconnected (guest shutdown). See xen_pcibk_xenbus_remove + * - 'echo BDF > unbind' on pciback module with no guest attached. See pcistub_remove + * - 'echo BDF > unbind' with a guest still using it. See pcistub_remove + * + * As such we have to be careful. + */ void pcistub_put_pci_dev(struct pci_dev *dev) { struct pcistub_device *psdev, *found_psdev = NULL; @@ -272,16 +281,16 @@ void pcistub_put_pci_dev(struct pci_dev *dev) * and want to inhibit the user from fiddling with 'reset' */ pci_reset_function(dev); - pci_restore_state(psdev->dev); + pci_restore_state(dev); /* This disables the device. */ - xen_pcibk_reset_device(found_psdev->dev); + xen_pcibk_reset_device(dev); /* And cleanup up our emulated fields. */ - xen_pcibk_config_free_dyn_fields(found_psdev->dev); - xen_pcibk_config_reset_dev(found_psdev->dev); + xen_pcibk_config_reset_dev(dev); + xen_pcibk_config_free_dyn_fields(dev); - xen_unregister_device_domain_owner(found_psdev->dev); + xen_unregister_device_domain_owner(dev); spin_lock_irqsave(&found_psdev->lock, flags); found_psdev->pdev = NULL; @@ -493,6 +502,8 @@ static int pcistub_seize(struct pci_dev *dev) return err; } +/* Called when 'bind'. This means we must _NOT_ call pci_reset_function or + * other functions that take the sysfs lock. */ static int pcistub_probe(struct pci_dev *dev, const struct pci_device_id *id) { int err = 0; @@ -520,6 +531,8 @@ out: return err; } +/* Called when 'unbind'. This means we must _NOT_ call pci_reset_function or + * other functions that take the sysfs lock. */ static void pcistub_remove(struct pci_dev *dev) { struct pcistub_device *psdev, *found_psdev = NULL; @@ -551,6 +564,8 @@ static void pcistub_remove(struct pci_dev *dev) pr_warn("****** shutdown driver domain before binding device\n"); pr_warn("****** to other drivers or domains\n"); + /* N.B. This ends up calling pcistub_put_pci_dev which ends up + * doing the FLR. */ xen_pcibk_release_pci_dev(found_psdev->pdev, found_psdev->dev); } diff --git a/drivers/xen/xen-pciback/pciback_ops.c b/drivers/xen/xen-pciback/pciback_ops.c index 64eb0cd8b8a..c4a0666de6f 100644 --- a/drivers/xen/xen-pciback/pciback_ops.c +++ b/drivers/xen/xen-pciback/pciback_ops.c @@ -213,12 +213,11 @@ int xen_pcibk_enable_msix(struct xen_pcibk_device *pdev, entries[i].vector = op->msix_entries[i].vector; } - result = pci_enable_msix(dev, entries, op->value); - + result = pci_enable_msix_exact(dev, entries, op->value); if (result == 0) { for (i = 0; i < op->value; i++) { op->msix_entries[i].entry = entries[i].entry; - if (entries[i].vector) + if (entries[i].vector) { op->msix_entries[i].vector = xen_pirq_from_irq(entries[i].vector); if (unlikely(verbose_request)) @@ -226,6 +225,7 @@ int xen_pcibk_enable_msix(struct xen_pcibk_device *pdev, "MSI-X[%d]: %d\n", pci_name(dev), i, op->msix_entries[i].vector); + } } } else pr_warn_ratelimited("%s: error enabling MSI-X for guest %u: err %d!\n", @@ -348,9 +348,9 @@ void xen_pcibk_do_op(struct work_struct *data) notify_remote_via_irq(pdev->evtchn_irq); /* Mark that we're done. */ - smp_mb__before_clear_bit(); /* /after/ clearing PCIF_active */ + smp_mb__before_atomic(); /* /after/ clearing PCIF_active */ clear_bit(_PDEVF_op_active, &pdev->flags); - smp_mb__after_clear_bit(); /* /before/ final check for work */ + smp_mb__after_atomic(); /* /before/ final check for work */ /* Check to see if the driver domain tried to start another request in * between clearing _XEN_PCIF_active and clearing _PDEVF_op_active. diff --git a/drivers/xen/xen-pciback/vpci.c b/drivers/xen/xen-pciback/vpci.c index 3165ce361b0..51afff96c51 100644 --- a/drivers/xen/xen-pciback/vpci.c +++ b/drivers/xen/xen-pciback/vpci.c @@ -137,6 +137,8 @@ unlock: /* Publish this device. */ if (!err) err = publish_cb(pdev, 0, 0, PCI_DEVFN(slot, func), devid); + else + kfree(dev_entry); out: return err; diff --git a/drivers/xen/xen-pciback/xenbus.c b/drivers/xen/xen-pciback/xenbus.c index a9ed867afab..4a7e6e0a5f4 100644 --- a/drivers/xen/xen-pciback/xenbus.c +++ b/drivers/xen/xen-pciback/xenbus.c @@ -93,6 +93,8 @@ static void free_pdev(struct xen_pcibk_device *pdev) xen_pcibk_disconnect(pdev); + /* N.B. This calls pcistub_put_pci_dev which does the FLR on all + * of the PCIe devices. */ xen_pcibk_release_devices(pdev); dev_set_drvdata(&pdev->xdev->dev, NULL); @@ -286,6 +288,8 @@ static int xen_pcibk_remove_device(struct xen_pcibk_device *pdev, dev_dbg(&dev->dev, "unregistering for %d\n", pdev->xdev->otherend_id); xen_unregister_device_domain_owner(dev); + /* N.B. This ends up calling pcistub_put_pci_dev which ends up + * doing the FLR. */ xen_pcibk_release_pci_dev(pdev, dev); out: diff --git a/drivers/xen/xen-selfballoon.c b/drivers/xen/xen-selfballoon.c index 745ad79c1d8..3b2bffde534 100644 --- a/drivers/xen/xen-selfballoon.c +++ b/drivers/xen/xen-selfballoon.c @@ -170,6 +170,7 @@ static void frontswap_selfshrink(void) tgt_frontswap_pages = cur_frontswap_pages - (cur_frontswap_pages / frontswap_hysteresis); frontswap_shrink(tgt_frontswap_pages); + frontswap_inertia_counter = frontswap_inertia; } #endif /* CONFIG_FRONTSWAP */ diff --git a/drivers/xen/xenbus/xenbus_client.c b/drivers/xen/xenbus/xenbus_client.c index 01d59e66565..439c9dca9ee 100644 --- a/drivers/xen/xenbus/xenbus_client.c +++ b/drivers/xen/xenbus/xenbus_client.c @@ -401,33 +401,6 @@ EXPORT_SYMBOL_GPL(xenbus_alloc_evtchn); /** - * Bind to an existing interdomain event channel in another domain. Returns 0 - * on success and stores the local port in *port. On error, returns -errno, - * switches the device to XenbusStateClosing, and saves the error in XenStore. - */ -int xenbus_bind_evtchn(struct xenbus_device *dev, int remote_port, int *port) -{ - struct evtchn_bind_interdomain bind_interdomain; - int err; - - bind_interdomain.remote_dom = dev->otherend_id; - bind_interdomain.remote_port = remote_port; - - err = HYPERVISOR_event_channel_op(EVTCHNOP_bind_interdomain, - &bind_interdomain); - if (err) - xenbus_dev_fatal(dev, err, - "binding to event channel %d from domain %d", - remote_port, dev->otherend_id); - else - *port = bind_interdomain.local_port; - - return err; -} -EXPORT_SYMBOL_GPL(xenbus_bind_evtchn); - - -/** * Free an existing event channel. Returns 0 on success or -errno on error. */ int xenbus_free_evtchn(struct xenbus_device *dev, int port) diff --git a/drivers/xen/xenbus/xenbus_xs.c b/drivers/xen/xenbus/xenbus_xs.c index b6d5fff43d1..ba804f3d827 100644 --- a/drivers/xen/xenbus/xenbus_xs.c +++ b/drivers/xen/xenbus/xenbus_xs.c @@ -50,6 +50,7 @@ #include <xen/xenbus.h> #include <xen/xen.h> #include "xenbus_comms.h" +#include "xenbus_probe.h" struct xs_stored_msg { struct list_head list; @@ -139,6 +140,29 @@ static int get_error(const char *errorstring) return xsd_errors[i].errnum; } +static bool xenbus_ok(void) +{ + switch (xen_store_domain_type) { + case XS_LOCAL: + switch (system_state) { + case SYSTEM_POWER_OFF: + case SYSTEM_RESTART: + case SYSTEM_HALT: + return false; + default: + break; + } + return true; + case XS_PV: + case XS_HVM: + /* FIXME: Could check that the remote domain is alive, + * but it is normally initial domain. */ + return true; + default: + break; + } + return false; +} static void *read_reply(enum xsd_sockmsg_type *type, unsigned int *len) { struct xs_stored_msg *msg; @@ -148,9 +172,20 @@ static void *read_reply(enum xsd_sockmsg_type *type, unsigned int *len) while (list_empty(&xs_state.reply_list)) { spin_unlock(&xs_state.reply_lock); - /* XXX FIXME: Avoid synchronous wait for response here. */ - wait_event(xs_state.reply_waitq, - !list_empty(&xs_state.reply_list)); + if (xenbus_ok()) + /* XXX FIXME: Avoid synchronous wait for response here. */ + wait_event_timeout(xs_state.reply_waitq, + !list_empty(&xs_state.reply_list), + msecs_to_jiffies(500)); + else { + /* + * If we are in the process of being shut-down there is + * no point of trying to contact XenBus - it is either + * killed (xenstored application) or the other domain + * has been killed or is unreachable. + */ + return ERR_PTR(-EIO); + } spin_lock(&xs_state.reply_lock); } @@ -215,6 +250,9 @@ void *xenbus_dev_request_and_reply(struct xsd_sockmsg *msg) mutex_unlock(&xs_state.request_mutex); + if (IS_ERR(ret)) + return ret; + if ((msg->type == XS_TRANSACTION_END) || ((req_msg.type == XS_TRANSACTION_START) && (msg->type == XS_ERROR))) diff --git a/drivers/xen/xencomm.c b/drivers/xen/xencomm.c deleted file mode 100644 index 4793fc59454..00000000000 --- a/drivers/xen/xencomm.c +++ /dev/null @@ -1,219 +0,0 @@ -/* - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - * - * Copyright (C) IBM Corp. 2006 - * - * Authors: Hollis Blanchard <hollisb@us.ibm.com> - */ - -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt - -#include <linux/mm.h> -#include <linux/slab.h> -#include <asm/page.h> -#include <xen/xencomm.h> -#include <xen/interface/xen.h> -#include <asm/xen/xencomm.h> /* for xencomm_is_phys_contiguous() */ - -static int xencomm_init(struct xencomm_desc *desc, - void *buffer, unsigned long bytes) -{ - unsigned long recorded = 0; - int i = 0; - - while ((recorded < bytes) && (i < desc->nr_addrs)) { - unsigned long vaddr = (unsigned long)buffer + recorded; - unsigned long paddr; - int offset; - int chunksz; - - offset = vaddr % PAGE_SIZE; /* handle partial pages */ - chunksz = min(PAGE_SIZE - offset, bytes - recorded); - - paddr = xencomm_vtop(vaddr); - if (paddr == ~0UL) { - printk(KERN_DEBUG "%s: couldn't translate vaddr %lx\n", - __func__, vaddr); - return -EINVAL; - } - - desc->address[i++] = paddr; - recorded += chunksz; - } - - if (recorded < bytes) { - printk(KERN_DEBUG - "%s: could only translate %ld of %ld bytes\n", - __func__, recorded, bytes); - return -ENOSPC; - } - - /* mark remaining addresses invalid (just for safety) */ - while (i < desc->nr_addrs) - desc->address[i++] = XENCOMM_INVALID; - - desc->magic = XENCOMM_MAGIC; - - return 0; -} - -static struct xencomm_desc *xencomm_alloc(gfp_t gfp_mask, - void *buffer, unsigned long bytes) -{ - struct xencomm_desc *desc; - unsigned long buffer_ulong = (unsigned long)buffer; - unsigned long start = buffer_ulong & PAGE_MASK; - unsigned long end = (buffer_ulong + bytes) | ~PAGE_MASK; - unsigned long nr_addrs = (end - start + 1) >> PAGE_SHIFT; - unsigned long size = sizeof(*desc) + - sizeof(desc->address[0]) * nr_addrs; - - /* - * slab allocator returns at least sizeof(void*) aligned pointer. - * When sizeof(*desc) > sizeof(void*), struct xencomm_desc might - * cross page boundary. - */ - if (sizeof(*desc) > sizeof(void *)) { - unsigned long order = get_order(size); - desc = (struct xencomm_desc *)__get_free_pages(gfp_mask, - order); - if (desc == NULL) - return NULL; - - desc->nr_addrs = - ((PAGE_SIZE << order) - sizeof(struct xencomm_desc)) / - sizeof(*desc->address); - } else { - desc = kmalloc(size, gfp_mask); - if (desc == NULL) - return NULL; - - desc->nr_addrs = nr_addrs; - } - return desc; -} - -void xencomm_free(struct xencomm_handle *desc) -{ - if (desc && !((ulong)desc & XENCOMM_INLINE_FLAG)) { - struct xencomm_desc *desc__ = (struct xencomm_desc *)desc; - if (sizeof(*desc__) > sizeof(void *)) { - unsigned long size = sizeof(*desc__) + - sizeof(desc__->address[0]) * desc__->nr_addrs; - unsigned long order = get_order(size); - free_pages((unsigned long)__va(desc), order); - } else - kfree(__va(desc)); - } -} - -static int xencomm_create(void *buffer, unsigned long bytes, - struct xencomm_desc **ret, gfp_t gfp_mask) -{ - struct xencomm_desc *desc; - int rc; - - pr_debug("%s: %p[%ld]\n", __func__, buffer, bytes); - - if (bytes == 0) { - /* don't create a descriptor; Xen recognizes NULL. */ - BUG_ON(buffer != NULL); - *ret = NULL; - return 0; - } - - BUG_ON(buffer == NULL); /* 'bytes' is non-zero */ - - desc = xencomm_alloc(gfp_mask, buffer, bytes); - if (!desc) { - printk(KERN_DEBUG "%s failure\n", "xencomm_alloc"); - return -ENOMEM; - } - - rc = xencomm_init(desc, buffer, bytes); - if (rc) { - printk(KERN_DEBUG "%s failure: %d\n", "xencomm_init", rc); - xencomm_free((struct xencomm_handle *)__pa(desc)); - return rc; - } - - *ret = desc; - return 0; -} - -static struct xencomm_handle *xencomm_create_inline(void *ptr) -{ - unsigned long paddr; - - BUG_ON(!xencomm_is_phys_contiguous((unsigned long)ptr)); - - paddr = (unsigned long)xencomm_pa(ptr); - BUG_ON(paddr & XENCOMM_INLINE_FLAG); - return (struct xencomm_handle *)(paddr | XENCOMM_INLINE_FLAG); -} - -/* "mini" routine, for stack-based communications: */ -static int xencomm_create_mini(void *buffer, - unsigned long bytes, struct xencomm_mini *xc_desc, - struct xencomm_desc **ret) -{ - int rc = 0; - struct xencomm_desc *desc; - BUG_ON(((unsigned long)xc_desc) % sizeof(*xc_desc) != 0); - - desc = (void *)xc_desc; - - desc->nr_addrs = XENCOMM_MINI_ADDRS; - - rc = xencomm_init(desc, buffer, bytes); - if (!rc) - *ret = desc; - - return rc; -} - -struct xencomm_handle *xencomm_map(void *ptr, unsigned long bytes) -{ - int rc; - struct xencomm_desc *desc; - - if (xencomm_is_phys_contiguous((unsigned long)ptr)) - return xencomm_create_inline(ptr); - - rc = xencomm_create(ptr, bytes, &desc, GFP_KERNEL); - - if (rc || desc == NULL) - return NULL; - - return xencomm_pa(desc); -} - -struct xencomm_handle *__xencomm_map_no_alloc(void *ptr, unsigned long bytes, - struct xencomm_mini *xc_desc) -{ - int rc; - struct xencomm_desc *desc = NULL; - - if (xencomm_is_phys_contiguous((unsigned long)ptr)) - return xencomm_create_inline(ptr); - - rc = xencomm_create_mini(ptr, bytes, xc_desc, - &desc); - - if (rc) - return NULL; - - return xencomm_pa(desc); -} |
