diff options
Diffstat (limited to 'drivers/xen')
33 files changed, 342 insertions, 265 deletions
diff --git a/drivers/xen/Kconfig b/drivers/xen/Kconfig index f7d6f47971fd..f9a35ed266ec 100644 --- a/drivers/xen/Kconfig +++ b/drivers/xen/Kconfig @@ -138,6 +138,7 @@ config XEN_GNTDEV depends on XEN default m select MMU_NOTIFIER + select FIND_NORMAL_PAGE help Allows userspace processes to use grants. @@ -278,7 +279,7 @@ config XEN_PRIVCMD_EVENTFD config XEN_ACPI_PROCESSOR tristate "Xen ACPI processor" - depends on XEN && XEN_PV_DOM0 && X86 && ACPI_PROCESSOR && CPU_FREQ + depends on XEN && XEN_DOM0 && X86 && ACPI_PROCESSOR && CPU_FREQ default m help This ACPI processor uploads Power Management information to the Xen diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c index 528395133b4f..49c3f9926394 100644 --- a/drivers/xen/balloon.c +++ b/drivers/xen/balloon.c @@ -84,7 +84,7 @@ module_param(balloon_boot_timeout, uint, 0444); #ifdef CONFIG_XEN_BALLOON_MEMORY_HOTPLUG static int xen_hotplug_unpopulated; -static struct ctl_table balloon_table[] = { +static const struct ctl_table balloon_table[] = { { .procname = "hotplug_unpopulated", .data = &xen_hotplug_unpopulated, @@ -157,6 +157,8 @@ static void balloon_append(struct page *page) list_add(&page->lru, &ballooned_pages); balloon_stats.balloon_low++; } + inc_node_page_state(page, NR_BALLOON_PAGES); + wake_up(&balloon_wq); } @@ -179,6 +181,8 @@ static struct page *balloon_retrieve(bool require_lowmem) balloon_stats.balloon_low--; __ClearPageOffline(page); + dec_node_page_state(page, NR_BALLOON_PAGES); + return page; } @@ -298,7 +302,7 @@ static enum bp_state reserve_additional_memory(void) * are not restored since this region is now known not to * conflict with any devices. */ - if (!xen_feature(XENFEAT_auto_translated_physmap)) { + if (xen_pv_domain()) { unsigned long pfn, i; pfn = PFN_DOWN(resource->start); @@ -622,7 +626,7 @@ int xen_alloc_ballooned_pages(unsigned int nr_pages, struct page **pages) */ BUILD_BUG_ON(XEN_PAGE_SIZE != PAGE_SIZE); - if (!xen_feature(XENFEAT_auto_translated_physmap)) { + if (xen_pv_domain()) { ret = xen_alloc_p2m_entry(page_to_pfn(page)); if (ret < 0) goto out_undo; @@ -675,7 +679,7 @@ void xen_free_ballooned_pages(unsigned int nr_pages, struct page **pages) } EXPORT_SYMBOL(xen_free_ballooned_pages); -static void __init balloon_add_regions(void) +static int __init balloon_add_regions(void) { unsigned long start_pfn, pages; unsigned long pfn, extra_pfn_end; @@ -698,26 +702,41 @@ static void __init balloon_add_regions(void) for (pfn = start_pfn; pfn < extra_pfn_end; pfn++) balloon_append(pfn_to_page(pfn)); - balloon_stats.total_pages += extra_pfn_end - start_pfn; + /* + * Extra regions are accounted for in the physmap, but need + * decreasing from current_pages and target_pages to balloon + * down the initial allocation, because they are already + * accounted for in total_pages. + */ + pages = extra_pfn_end - start_pfn; + if (pages >= balloon_stats.current_pages || + pages >= balloon_stats.target_pages) { + WARN(1, "Extra pages underflow current target"); + return -ERANGE; + } + balloon_stats.current_pages -= pages; + balloon_stats.target_pages -= pages; } + + return 0; } static int __init balloon_init(void) { struct task_struct *task; + int rc; if (!xen_domain()) return -ENODEV; pr_info("Initialising balloon driver\n"); -#ifdef CONFIG_XEN_PV - balloon_stats.current_pages = xen_pv_domain() - ? min(xen_start_info->nr_pages - xen_released_pages, max_pfn) - : get_num_physpages(); -#else - balloon_stats.current_pages = get_num_physpages(); -#endif + if (xen_released_pages >= get_num_physpages()) { + WARN(1, "Released pages underflow current target"); + return -ERANGE; + } + + balloon_stats.current_pages = get_num_physpages() - xen_released_pages; balloon_stats.target_pages = balloon_stats.current_pages; balloon_stats.balloon_low = 0; balloon_stats.balloon_high = 0; @@ -734,7 +753,9 @@ static int __init balloon_init(void) register_sysctl_init("xen/balloon", balloon_table); #endif - balloon_add_regions(); + rc = balloon_add_regions(); + if (rc) + return rc; task = kthread_run(balloon_thread, NULL, "xen-balloon"); if (IS_ERR(task)) { diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c index 985e155ebe4b..9478fae014e5 100644 --- a/drivers/xen/events/events_base.c +++ b/drivers/xen/events/events_base.c @@ -722,12 +722,6 @@ static struct irq_info *xen_irq_init(unsigned int irq) INIT_RCU_WORK(&info->rwork, delayed_free_irq); set_info_for_irq(irq, info); - /* - * Interrupt affinity setting can be immediate. No point - * in delaying it until an interrupt is handled. - */ - irq_set_status_flags(irq, IRQ_MOVE_PCNTXT); - INIT_LIST_HEAD(&info->eoi_list); list_add_tail(&info->list, &xen_irq_list_head); } @@ -1320,14 +1314,17 @@ int bind_interdomain_evtchn_to_irq_lateeoi(struct xenbus_device *dev, } EXPORT_SYMBOL_GPL(bind_interdomain_evtchn_to_irq_lateeoi); -static int find_virq(unsigned int virq, unsigned int cpu, evtchn_port_t *evtchn) +static int find_virq(unsigned int virq, unsigned int cpu, evtchn_port_t *evtchn, + bool percpu) { struct evtchn_status status; evtchn_port_t port; - int rc = -ENOENT; + bool exists = false; memset(&status, 0, sizeof(status)); for (port = 0; port < xen_evtchn_max_channels(); port++) { + int rc; + status.dom = DOMID_SELF; status.port = port; rc = HYPERVISOR_event_channel_op(EVTCHNOP_status, &status); @@ -1335,12 +1332,16 @@ static int find_virq(unsigned int virq, unsigned int cpu, evtchn_port_t *evtchn) continue; if (status.status != EVTCHNSTAT_virq) continue; - if (status.u.virq == virq && status.vcpu == xen_vcpu_nr(cpu)) { + if (status.u.virq != virq) + continue; + if (status.vcpu == xen_vcpu_nr(cpu)) { *evtchn = port; - break; + return 0; + } else if (!percpu) { + exists = true; } } - return rc; + return exists ? -EEXIST : -ENOENT; } /** @@ -1387,8 +1388,11 @@ int bind_virq_to_irq(unsigned int virq, unsigned int cpu, bool percpu) evtchn = bind_virq.port; else { if (ret == -EEXIST) - ret = find_virq(virq, cpu, &evtchn); - BUG_ON(ret < 0); + ret = find_virq(virq, cpu, &evtchn, percpu); + if (ret) { + __unbind_from_irq(info, info->irq); + goto out; + } } ret = xen_irq_info_virq_setup(info, cpu, evtchn, virq); @@ -1793,9 +1797,20 @@ static int xen_rebind_evtchn_to_cpu(struct irq_info *info, unsigned int tcpu) * virq or IPI channel, which don't actually need to be rebound. Ignore * it, but don't do the xenlinux-level rebind in that case. */ - if (HYPERVISOR_event_channel_op(EVTCHNOP_bind_vcpu, &bind_vcpu) >= 0) + if (HYPERVISOR_event_channel_op(EVTCHNOP_bind_vcpu, &bind_vcpu) >= 0) { + int old_cpu = info->cpu; + bind_evtchn_to_cpu(info, tcpu, false); + if (info->type == IRQT_VIRQ) { + int virq = info->u.virq; + int irq = per_cpu(virq_to_irq, old_cpu)[virq]; + + per_cpu(virq_to_irq, old_cpu)[virq] = -1; + per_cpu(virq_to_irq, tcpu)[virq] = irq; + } + } + do_unmask(info, EVT_MASK_REASON_TEMPORARY); return 0; diff --git a/drivers/xen/gntdev-common.h b/drivers/xen/gntdev-common.h index 9c286b2a1900..ac8ce3179ba2 100644 --- a/drivers/xen/gntdev-common.h +++ b/drivers/xen/gntdev-common.h @@ -26,6 +26,10 @@ struct gntdev_priv { /* lock protects maps and freeable_maps. */ struct mutex lock; + /* Free instances of struct gntdev_copy_batch. */ + struct gntdev_copy_batch *batch; + struct mutex batch_lock; + #ifdef CONFIG_XEN_GRANT_DMA_ALLOC /* Device for which DMA memory is allocated. */ struct device *dma_dev; diff --git a/drivers/xen/gntdev-dmabuf.c b/drivers/xen/gntdev-dmabuf.c index 42adc2c1e06b..550980dd3b0b 100644 --- a/drivers/xen/gntdev-dmabuf.c +++ b/drivers/xen/gntdev-dmabuf.c @@ -23,7 +23,7 @@ #include "gntdev-common.h" #include "gntdev-dmabuf.h" -MODULE_IMPORT_NS(DMA_BUF); +MODULE_IMPORT_NS("DMA_BUF"); struct gntdev_dmabuf { struct gntdev_dmabuf_priv *priv; @@ -357,8 +357,11 @@ struct gntdev_dmabuf_export_args { static int dmabuf_exp_from_pages(struct gntdev_dmabuf_export_args *args) { DEFINE_DMA_BUF_EXPORT_INFO(exp_info); - struct gntdev_dmabuf *gntdev_dmabuf; - int ret; + struct gntdev_dmabuf *gntdev_dmabuf __free(kfree) = NULL; + CLASS(get_unused_fd, ret)(O_CLOEXEC); + + if (ret < 0) + return ret; gntdev_dmabuf = kzalloc(sizeof(*gntdev_dmabuf), GFP_KERNEL); if (!gntdev_dmabuf) @@ -383,32 +386,21 @@ static int dmabuf_exp_from_pages(struct gntdev_dmabuf_export_args *args) exp_info.priv = gntdev_dmabuf; gntdev_dmabuf->dmabuf = dma_buf_export(&exp_info); - if (IS_ERR(gntdev_dmabuf->dmabuf)) { - ret = PTR_ERR(gntdev_dmabuf->dmabuf); - gntdev_dmabuf->dmabuf = NULL; - goto fail; - } - - ret = dma_buf_fd(gntdev_dmabuf->dmabuf, O_CLOEXEC); - if (ret < 0) - goto fail; + if (IS_ERR(gntdev_dmabuf->dmabuf)) + return PTR_ERR(gntdev_dmabuf->dmabuf); gntdev_dmabuf->fd = ret; args->fd = ret; pr_debug("Exporting DMA buffer with fd %d\n", ret); + get_file(gntdev_dmabuf->priv->filp); mutex_lock(&args->dmabuf_priv->lock); list_add(&gntdev_dmabuf->next, &args->dmabuf_priv->exp_list); mutex_unlock(&args->dmabuf_priv->lock); - get_file(gntdev_dmabuf->priv->filp); - return 0; -fail: - if (gntdev_dmabuf->dmabuf) - dma_buf_put(gntdev_dmabuf->dmabuf); - kfree(gntdev_dmabuf); - return ret; + fd_install(take_fd(ret), no_free_ptr(gntdev_dmabuf)->dmabuf->file); + return 0; } static struct gntdev_grant_map * @@ -728,16 +720,15 @@ static void dmabuf_imp_release_all(struct gntdev_dmabuf_priv *priv) /* DMA buffer IOCTL support. */ -long gntdev_ioctl_dmabuf_exp_from_refs(struct gntdev_priv *priv, int use_ptemod, +long gntdev_ioctl_dmabuf_exp_from_refs(struct gntdev_priv *priv, struct ioctl_gntdev_dmabuf_exp_from_refs __user *u) { struct ioctl_gntdev_dmabuf_exp_from_refs op; u32 *refs; long ret; - if (use_ptemod) { - pr_debug("Cannot provide dma-buf: use_ptemode %d\n", - use_ptemod); + if (xen_pv_domain()) { + pr_debug("Cannot provide dma-buf in a PV domain\n"); return -EINVAL; } diff --git a/drivers/xen/gntdev-dmabuf.h b/drivers/xen/gntdev-dmabuf.h index 3d9b9cf9d5a1..9adf96ac74d3 100644 --- a/drivers/xen/gntdev-dmabuf.h +++ b/drivers/xen/gntdev-dmabuf.h @@ -18,7 +18,7 @@ struct gntdev_dmabuf_priv *gntdev_dmabuf_init(struct file *filp); void gntdev_dmabuf_fini(struct gntdev_dmabuf_priv *priv); -long gntdev_ioctl_dmabuf_exp_from_refs(struct gntdev_priv *priv, int use_ptemod, +long gntdev_ioctl_dmabuf_exp_from_refs(struct gntdev_priv *priv, struct ioctl_gntdev_dmabuf_exp_from_refs __user *u); long gntdev_ioctl_dmabuf_exp_wait_released(struct gntdev_priv *priv, diff --git a/drivers/xen/gntdev.c b/drivers/xen/gntdev.c index 61faea1f0663..2c960f187f7c 100644 --- a/drivers/xen/gntdev.c +++ b/drivers/xen/gntdev.c @@ -56,14 +56,23 @@ MODULE_AUTHOR("Derek G. Murray <Derek.Murray@cl.cam.ac.uk>, " "Gerd Hoffmann <kraxel@redhat.com>"); MODULE_DESCRIPTION("User-space granted page access driver"); +#define GNTDEV_COPY_BATCH 16 + +struct gntdev_copy_batch { + struct gnttab_copy ops[GNTDEV_COPY_BATCH]; + struct page *pages[GNTDEV_COPY_BATCH]; + s16 __user *status[GNTDEV_COPY_BATCH]; + unsigned int nr_ops; + unsigned int nr_pages; + bool writeable; + struct gntdev_copy_batch *next; +}; + static unsigned int limit = 64*1024; module_param(limit, uint, 0644); MODULE_PARM_DESC(limit, "Maximum number of grants that may be mapped by one mapping request"); -/* True in PV mode, false otherwise */ -static int use_ptemod; - static void unmap_grant_pages(struct gntdev_grant_map *map, int offset, int pages); @@ -151,7 +160,7 @@ struct gntdev_grant_map *gntdev_alloc_map(struct gntdev_priv *priv, int count, NULL == add->pages || NULL == add->being_removed) goto err; - if (use_ptemod) { + if (xen_pv_domain()) { add->kmap_ops = kvmalloc_array(count, sizeof(add->kmap_ops[0]), GFP_KERNEL); add->kunmap_ops = kvmalloc_array(count, sizeof(add->kunmap_ops[0]), @@ -199,7 +208,7 @@ struct gntdev_grant_map *gntdev_alloc_map(struct gntdev_priv *priv, int count, add->grants[i].ref = INVALID_GRANT_REF; add->map_ops[i].handle = INVALID_GRANT_HANDLE; add->unmap_ops[i].handle = INVALID_GRANT_HANDLE; - if (use_ptemod) { + if (xen_pv_domain()) { add->kmap_ops[i].handle = INVALID_GRANT_HANDLE; add->kunmap_ops[i].handle = INVALID_GRANT_HANDLE; } @@ -256,7 +265,7 @@ void gntdev_put_map(struct gntdev_priv *priv, struct gntdev_grant_map *map) if (!refcount_dec_and_test(&map->users)) return; - if (map->pages && !use_ptemod) { + if (map->pages && !xen_pv_domain()) { /* * Increment the reference count. This ensures that the * subsequent call to unmap_grant_pages() will not wind up @@ -286,7 +295,7 @@ void gntdev_put_map(struct gntdev_priv *priv, struct gntdev_grant_map *map) */ } - if (use_ptemod && map->notifier_init) + if (xen_pv_domain() && map->notifier_init) mmu_interval_notifier_remove(&map->notifier); if (map->notify.flags & UNMAP_NOTIFY_SEND_EVENT) { @@ -309,6 +318,7 @@ static int find_grant_ptes(pte_t *pte, unsigned long addr, void *data) BUG_ON(pgnr >= map->count); pte_maddr = arbitrary_virt_to_machine(pte).maddr; + /* Note: this will perform a pte_mkspecial() through the hypercall. */ gnttab_set_map_op(&map->map_ops[pgnr], pte_maddr, flags, map->grants[pgnr].ref, map->grants[pgnr].domid); @@ -322,7 +332,7 @@ int gntdev_map_grant_pages(struct gntdev_grant_map *map) size_t alloced = 0; int i, err = 0; - if (!use_ptemod) { + if (!xen_pv_domain()) { /* Note: it could already be mapped */ if (map->map_ops[0].handle != INVALID_GRANT_HANDLE) return 0; @@ -377,7 +387,7 @@ int gntdev_map_grant_pages(struct gntdev_grant_map *map) if (map->flags & GNTMAP_device_map) map->unmap_ops[i].dev_bus_addr = map->map_ops[i].dev_bus_addr; - if (use_ptemod) { + if (xen_pv_domain()) { if (map->kmap_ops[i].status == GNTST_okay) { alloced++; map->kunmap_ops[i].handle = map->kmap_ops[i].handle; @@ -409,7 +419,7 @@ static void __unmap_grant_pages_done(int result, map->unmap_ops[offset+i].handle, map->unmap_ops[offset+i].status); map->unmap_ops[offset+i].handle = INVALID_GRANT_HANDLE; - if (use_ptemod) { + if (xen_pv_domain()) { if (map->kunmap_ops[offset + i].status == GNTST_okay && map->kunmap_ops[offset + i].handle != INVALID_GRANT_HANDLE) successful_unmaps++; @@ -452,7 +462,7 @@ static void __unmap_grant_pages(struct gntdev_grant_map *map, int offset, } map->unmap_data.unmap_ops = map->unmap_ops + offset; - map->unmap_data.kunmap_ops = use_ptemod ? map->kunmap_ops + offset : NULL; + map->unmap_data.kunmap_ops = xen_pv_domain() ? map->kunmap_ops + offset : NULL; map->unmap_data.pages = map->pages + offset; map->unmap_data.count = pages; map->unmap_data.done = __unmap_grant_pages_done; @@ -516,7 +526,7 @@ static void gntdev_vma_close(struct vm_area_struct *vma) gntdev_put_map(priv, map); } -static struct page *gntdev_vma_find_special_page(struct vm_area_struct *vma, +static struct page *gntdev_vma_find_normal_page(struct vm_area_struct *vma, unsigned long addr) { struct gntdev_grant_map *map = vma->vm_private_data; @@ -527,7 +537,7 @@ static struct page *gntdev_vma_find_special_page(struct vm_area_struct *vma, static const struct vm_operations_struct gntdev_vmops = { .open = gntdev_vma_open, .close = gntdev_vma_close, - .find_special_page = gntdev_vma_find_special_page, + .find_normal_page = gntdev_vma_find_normal_page, }; /* ------------------------------------------------------------------ */ @@ -584,6 +594,8 @@ static int gntdev_open(struct inode *inode, struct file *flip) INIT_LIST_HEAD(&priv->maps); mutex_init(&priv->lock); + mutex_init(&priv->batch_lock); + #ifdef CONFIG_XEN_GNTDEV_DMABUF priv->dmabuf_priv = gntdev_dmabuf_init(flip); if (IS_ERR(priv->dmabuf_priv)) { @@ -608,6 +620,7 @@ static int gntdev_release(struct inode *inode, struct file *flip) { struct gntdev_priv *priv = flip->private_data; struct gntdev_grant_map *map; + struct gntdev_copy_batch *batch; pr_debug("priv %p\n", priv); @@ -620,6 +633,14 @@ static int gntdev_release(struct inode *inode, struct file *flip) } mutex_unlock(&priv->lock); + mutex_lock(&priv->batch_lock); + while (priv->batch) { + batch = priv->batch; + priv->batch = batch->next; + kfree(batch); + } + mutex_unlock(&priv->batch_lock); + #ifdef CONFIG_XEN_GNTDEV_DMABUF gntdev_dmabuf_fini(priv->dmabuf_priv); #endif @@ -785,17 +806,6 @@ static long gntdev_ioctl_notify(struct gntdev_priv *priv, void __user *u) return rc; } -#define GNTDEV_COPY_BATCH 16 - -struct gntdev_copy_batch { - struct gnttab_copy ops[GNTDEV_COPY_BATCH]; - struct page *pages[GNTDEV_COPY_BATCH]; - s16 __user *status[GNTDEV_COPY_BATCH]; - unsigned int nr_ops; - unsigned int nr_pages; - bool writeable; -}; - static int gntdev_get_page(struct gntdev_copy_batch *batch, void __user *virt, unsigned long *gfn) { @@ -953,36 +963,53 @@ static int gntdev_grant_copy_seg(struct gntdev_copy_batch *batch, static long gntdev_ioctl_grant_copy(struct gntdev_priv *priv, void __user *u) { struct ioctl_gntdev_grant_copy copy; - struct gntdev_copy_batch batch; + struct gntdev_copy_batch *batch; unsigned int i; int ret = 0; if (copy_from_user(©, u, sizeof(copy))) return -EFAULT; - batch.nr_ops = 0; - batch.nr_pages = 0; + mutex_lock(&priv->batch_lock); + if (!priv->batch) { + batch = kmalloc(sizeof(*batch), GFP_KERNEL); + } else { + batch = priv->batch; + priv->batch = batch->next; + } + mutex_unlock(&priv->batch_lock); + if (!batch) + return -ENOMEM; + + batch->nr_ops = 0; + batch->nr_pages = 0; for (i = 0; i < copy.count; i++) { struct gntdev_grant_copy_segment seg; if (copy_from_user(&seg, ©.segments[i], sizeof(seg))) { ret = -EFAULT; + gntdev_put_pages(batch); goto out; } - ret = gntdev_grant_copy_seg(&batch, &seg, ©.segments[i].status); - if (ret < 0) + ret = gntdev_grant_copy_seg(batch, &seg, ©.segments[i].status); + if (ret < 0) { + gntdev_put_pages(batch); goto out; + } cond_resched(); } - if (batch.nr_ops) - ret = gntdev_copy(&batch); - return ret; + if (batch->nr_ops) + ret = gntdev_copy(batch); + + out: + mutex_lock(&priv->batch_lock); + batch->next = priv->batch; + priv->batch = batch; + mutex_unlock(&priv->batch_lock); - out: - gntdev_put_pages(&batch); return ret; } @@ -1010,7 +1037,7 @@ static long gntdev_ioctl(struct file *flip, #ifdef CONFIG_XEN_GNTDEV_DMABUF case IOCTL_GNTDEV_DMABUF_EXP_FROM_REFS: - return gntdev_ioctl_dmabuf_exp_from_refs(priv, use_ptemod, ptr); + return gntdev_ioctl_dmabuf_exp_from_refs(priv, ptr); case IOCTL_GNTDEV_DMABUF_EXP_WAIT_RELEASED: return gntdev_ioctl_dmabuf_exp_wait_released(priv, ptr); @@ -1057,7 +1084,7 @@ static int gntdev_mmap(struct file *flip, struct vm_area_struct *vma) vm_flags_set(vma, VM_DONTEXPAND | VM_DONTDUMP | VM_MIXEDMAP); - if (use_ptemod) + if (xen_pv_domain()) vm_flags_set(vma, VM_DONTCOPY); vma->vm_private_data = map; @@ -1073,7 +1100,7 @@ static int gntdev_mmap(struct file *flip, struct vm_area_struct *vma) map->pages_vm_start = vma->vm_start; - if (use_ptemod) { + if (xen_pv_domain()) { err = mmu_interval_notifier_insert_locked( &map->notifier, vma->vm_mm, vma->vm_start, vma->vm_end - vma->vm_start, &gntdev_mmu_ops); @@ -1084,7 +1111,7 @@ static int gntdev_mmap(struct file *flip, struct vm_area_struct *vma) } mutex_unlock(&priv->lock); - if (use_ptemod) { + if (xen_pv_domain()) { /* * gntdev takes the address of the PTE in find_grant_ptes() and * passes it to the hypervisor in gntdev_map_grant_pages(). The @@ -1110,7 +1137,7 @@ static int gntdev_mmap(struct file *flip, struct vm_area_struct *vma) if (err) goto out_put_map; - if (!use_ptemod) { + if (!xen_pv_domain()) { err = vm_map_pages_zero(vma, map->pages, map->count); if (err) goto out_put_map; @@ -1125,7 +1152,7 @@ unlock_out: out_unlock_put: mutex_unlock(&priv->lock); out_put_map: - if (use_ptemod) + if (xen_pv_domain()) unmap_grant_pages(map, 0, map->count); gntdev_put_map(priv, map); return err; @@ -1154,8 +1181,6 @@ static int __init gntdev_init(void) if (!xen_domain()) return -ENODEV; - use_ptemod = !xen_feature(XENFEAT_auto_translated_physmap); - err = misc_register(&gntdev_miscdev); if (err != 0) { pr_err("Could not register gntdev device\n"); diff --git a/drivers/xen/grant-dma-iommu.c b/drivers/xen/grant-dma-iommu.c index 2ee750a03c2f..0965e2dd4edf 100644 --- a/drivers/xen/grant-dma-iommu.c +++ b/drivers/xen/grant-dma-iommu.c @@ -65,7 +65,7 @@ static struct platform_driver grant_dma_iommu_driver = { .of_match_table = grant_dma_iommu_of_match, }, .probe = grant_dma_iommu_probe, - .remove_new = grant_dma_iommu_remove, + .remove = grant_dma_iommu_remove, }; static int __init grant_dma_iommu_init(void) diff --git a/drivers/xen/grant-dma-ops.c b/drivers/xen/grant-dma-ops.c index 29257d2639db..14077d23f2a1 100644 --- a/drivers/xen/grant-dma-ops.c +++ b/drivers/xen/grant-dma-ops.c @@ -163,18 +163,22 @@ static void xen_grant_dma_free_pages(struct device *dev, size_t size, xen_grant_dma_free(dev, size, page_to_virt(vaddr), dma_handle, 0); } -static dma_addr_t xen_grant_dma_map_page(struct device *dev, struct page *page, - unsigned long offset, size_t size, +static dma_addr_t xen_grant_dma_map_phys(struct device *dev, phys_addr_t phys, + size_t size, enum dma_data_direction dir, unsigned long attrs) { struct xen_grant_dma_data *data; + unsigned long offset = offset_in_page(phys); unsigned long dma_offset = xen_offset_in_page(offset), pfn_offset = XEN_PFN_DOWN(offset); unsigned int i, n_pages = XEN_PFN_UP(dma_offset + size); grant_ref_t grant; dma_addr_t dma_handle; + if (unlikely(attrs & DMA_ATTR_MMIO)) + return DMA_MAPPING_ERROR; + if (WARN_ON(dir == DMA_NONE)) return DMA_MAPPING_ERROR; @@ -190,7 +194,7 @@ static dma_addr_t xen_grant_dma_map_page(struct device *dev, struct page *page, for (i = 0; i < n_pages; i++) { gnttab_grant_foreign_access_ref(grant + i, data->backend_domid, - pfn_to_gfn(page_to_xen_pfn(page) + i + pfn_offset), + pfn_to_gfn(page_to_xen_pfn(phys_to_page(phys)) + i + pfn_offset), dir == DMA_TO_DEVICE); } @@ -199,7 +203,7 @@ static dma_addr_t xen_grant_dma_map_page(struct device *dev, struct page *page, return dma_handle; } -static void xen_grant_dma_unmap_page(struct device *dev, dma_addr_t dma_handle, +static void xen_grant_dma_unmap_phys(struct device *dev, dma_addr_t dma_handle, size_t size, enum dma_data_direction dir, unsigned long attrs) { @@ -242,7 +246,7 @@ static void xen_grant_dma_unmap_sg(struct device *dev, struct scatterlist *sg, return; for_each_sg(sg, s, nents, i) - xen_grant_dma_unmap_page(dev, s->dma_address, sg_dma_len(s), dir, + xen_grant_dma_unmap_phys(dev, s->dma_address, sg_dma_len(s), dir, attrs); } @@ -257,7 +261,7 @@ static int xen_grant_dma_map_sg(struct device *dev, struct scatterlist *sg, return -EINVAL; for_each_sg(sg, s, nents, i) { - s->dma_address = xen_grant_dma_map_page(dev, sg_page(s), s->offset, + s->dma_address = xen_grant_dma_map_phys(dev, sg_phys(s), s->length, dir, attrs); if (s->dma_address == DMA_MAPPING_ERROR) goto out; @@ -286,8 +290,8 @@ static const struct dma_map_ops xen_grant_dma_ops = { .free_pages = xen_grant_dma_free_pages, .mmap = dma_common_mmap, .get_sgtable = dma_common_get_sgtable, - .map_page = xen_grant_dma_map_page, - .unmap_page = xen_grant_dma_unmap_page, + .map_phys = xen_grant_dma_map_phys, + .unmap_phys = xen_grant_dma_unmap_phys, .map_sg = xen_grant_dma_map_sg, .unmap_sg = xen_grant_dma_unmap_sg, .dma_supported = xen_grant_dma_supported, diff --git a/drivers/xen/grant-table.c b/drivers/xen/grant-table.c index 04a6b470b15d..3e76e33f6e08 100644 --- a/drivers/xen/grant-table.c +++ b/drivers/xen/grant-table.c @@ -1204,7 +1204,7 @@ void gnttab_foreach_grant_in_range(struct page *page, unsigned int glen; unsigned long xen_pfn; - len = min_t(unsigned int, PAGE_SIZE - offset, len); + len = min(PAGE_SIZE - offset, len); goffset = xen_offset_in_page(offset); xen_pfn = page_to_xen_pfn(page) + XEN_PFN_DOWN(offset); @@ -1449,7 +1449,7 @@ static int gnttab_map(unsigned int start_idx, unsigned int end_idx) unsigned int nr_gframes = end_idx + 1; int rc; - if (xen_feature(XENFEAT_auto_translated_physmap)) { + if (!xen_pv_domain()) { struct xen_add_to_physmap xatp; unsigned int i = end_idx; rc = 0; @@ -1570,7 +1570,7 @@ static int gnttab_setup(void) if (max_nr_gframes < nr_grant_frames) return -ENOSYS; - if (xen_feature(XENFEAT_auto_translated_physmap) && gnttab_shared.addr == NULL) { + if (!xen_pv_domain() && gnttab_shared.addr == NULL) { gnttab_shared.addr = xen_auto_xlat_grant_frames.vaddr; if (gnttab_shared.addr == NULL) { pr_warn("gnttab share frames is not mapped!\n"); @@ -1588,7 +1588,7 @@ int gnttab_resume(void) int gnttab_suspend(void) { - if (!xen_feature(XENFEAT_auto_translated_physmap)) + if (xen_pv_domain()) gnttab_interface->unmap_frames(); return 0; } diff --git a/drivers/xen/manage.c b/drivers/xen/manage.c index b4b4ebed68da..e20c40a62e64 100644 --- a/drivers/xen/manage.c +++ b/drivers/xen/manage.c @@ -11,6 +11,7 @@ #include <linux/reboot.h> #include <linux/sysrq.h> #include <linux/stop_machine.h> +#include <linux/suspend.h> #include <linux/freezer.h> #include <linux/syscore_ops.h> #include <linux/export.h> @@ -52,12 +53,6 @@ void xen_resume_notifier_register(struct notifier_block *nb) } EXPORT_SYMBOL_GPL(xen_resume_notifier_register); -void xen_resume_notifier_unregister(struct notifier_block *nb) -{ - 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) { @@ -101,10 +96,16 @@ static void do_suspend(void) shutting_down = SHUTDOWN_SUSPEND; + if (!mutex_trylock(&system_transition_mutex)) + { + pr_err("%s: failed to take system_transition_mutex\n", __func__); + goto out; + } + err = freeze_processes(); if (err) { pr_err("%s: freeze processes failed %d\n", __func__, err); - goto out; + goto out_unlock; } err = freeze_kernel_threads(); @@ -116,7 +117,7 @@ static void do_suspend(void) err = dpm_suspend_start(PMSG_FREEZE); if (err) { pr_err("%s: dpm_suspend_start %d\n", __func__, err); - goto out_thaw; + goto out_resume_end; } printk(KERN_DEBUG "suspending xenstore...\n"); @@ -156,10 +157,13 @@ out_resume: else xs_suspend_cancel(); +out_resume_end: dpm_resume_end(si.cancelled ? PMSG_THAW : PMSG_RESTORE); out_thaw: thaw_processes(); +out_unlock: + mutex_unlock(&system_transition_mutex); out: shutting_down = SHUTDOWN_INVALID; } diff --git a/drivers/xen/pci.c b/drivers/xen/pci.c index 416f231809cb..bfe07adb3e3a 100644 --- a/drivers/xen/pci.c +++ b/drivers/xen/pci.c @@ -43,6 +43,18 @@ static int xen_add_device(struct device *dev) pci_mcfg_reserved = true; } #endif + + if (pci_domain_nr(pci_dev->bus) >> 16) { + /* + * The hypercall interface is limited to 16bit PCI segment + * values, do not attempt to register devices with Xen in + * segments greater or equal than 0x10000. + */ + dev_info(dev, + "not registering with Xen: invalid PCI segment\n"); + return 0; + } + if (pci_seg_supported) { DEFINE_RAW_FLEX(struct physdev_pci_device_add, add, optarr, 1); @@ -149,6 +161,16 @@ static int xen_remove_device(struct device *dev) int r; struct pci_dev *pci_dev = to_pci_dev(dev); + if (pci_domain_nr(pci_dev->bus) >> 16) { + /* + * The hypercall interface is limited to 16bit PCI segment + * values. + */ + dev_info(dev, + "not unregistering with Xen: invalid PCI segment\n"); + return 0; + } + if (pci_seg_supported) { struct physdev_pci_device device = { .seg = pci_domain_nr(pci_dev->bus), @@ -182,6 +204,16 @@ int xen_reset_device(const struct pci_dev *dev) .flags = PCI_DEVICE_RESET_FLR, }; + if (pci_domain_nr(dev->bus) >> 16) { + /* + * The hypercall interface is limited to 16bit PCI segment + * values. + */ + dev_info(&dev->dev, + "unable to notify Xen of device reset: invalid PCI segment\n"); + return 0; + } + return HYPERVISOR_physdev_op(PHYSDEVOP_pci_device_reset, &device); } EXPORT_SYMBOL_GPL(xen_reset_device); diff --git a/drivers/xen/pcpu.c b/drivers/xen/pcpu.c index c63f317e3df3..093ad4a08672 100644 --- a/drivers/xen/pcpu.c +++ b/drivers/xen/pcpu.c @@ -105,7 +105,7 @@ static ssize_t online_show(struct device *dev, return sprintf(buf, "%u\n", !!(cpu->flags & XEN_PCPU_FLAGS_ONLINE)); } -static ssize_t __ref online_store(struct device *dev, +static ssize_t online_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { diff --git a/drivers/xen/platform-pci.c b/drivers/xen/platform-pci.c index 544d3f9010b9..1db82da56db6 100644 --- a/drivers/xen/platform-pci.c +++ b/drivers/xen/platform-pci.c @@ -26,6 +26,8 @@ #define DRV_NAME "xen-platform-pci" +#define PCI_DEVICE_ID_XEN_PLATFORM_XS61 0x0002 + static unsigned long platform_mmio; static unsigned long platform_mmio_alloc; static unsigned long platform_mmiolen; @@ -174,6 +176,8 @@ pci_out: static const struct pci_device_id platform_pci_tbl[] = { {PCI_VENDOR_ID_XEN, PCI_DEVICE_ID_XEN_PLATFORM, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0}, + {PCI_VENDOR_ID_XEN, PCI_DEVICE_ID_XEN_PLATFORM_XS61, + PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0}, {0,} }; diff --git a/drivers/xen/privcmd.c b/drivers/xen/privcmd.c index 13a10f3294a8..f52a457b302d 100644 --- a/drivers/xen/privcmd.c +++ b/drivers/xen/privcmd.c @@ -271,7 +271,7 @@ static long privcmd_ioctl_mmap(struct file *file, void __user *udata) struct mmap_gfn_state state; /* We only support privcmd_ioctl_mmap_batch for non-auto-translated. */ - if (xen_feature(XENFEAT_auto_translated_physmap)) + if (!xen_pv_domain()) return -ENOSYS; if (copy_from_user(&mmapcmd, udata, sizeof(mmapcmd))) @@ -353,7 +353,7 @@ static int mmap_batch_fn(void *data, int nr, void *state) struct page **cur_pages = NULL; int ret; - if (xen_feature(XENFEAT_auto_translated_physmap)) + if (!xen_pv_domain()) cur_pages = &pages[st->index]; BUG_ON(nr < 0); @@ -535,7 +535,7 @@ static long privcmd_ioctl_mmap_batch( ret = -EINVAL; goto out_unlock; } - if (xen_feature(XENFEAT_auto_translated_physmap)) { + if (!xen_pv_domain()) { ret = alloc_empty_pages(vma, nr_pages); if (ret < 0) goto out_unlock; @@ -779,8 +779,7 @@ static long privcmd_ioctl_mmap_resource(struct file *file, goto out; } - if (IS_ENABLED(CONFIG_XEN_AUTO_XLATE) && - xen_feature(XENFEAT_auto_translated_physmap)) { + if (IS_ENABLED(CONFIG_XEN_AUTO_XLATE) && !xen_pv_domain()) { unsigned int nr = DIV_ROUND_UP(kdata.num, XEN_PFN_PER_PAGE); struct page **pages; unsigned int i; @@ -811,8 +810,7 @@ static long privcmd_ioctl_mmap_resource(struct file *file, if (rc) goto out; - if (IS_ENABLED(CONFIG_XEN_AUTO_XLATE) && - xen_feature(XENFEAT_auto_translated_physmap)) { + if (IS_ENABLED(CONFIG_XEN_AUTO_XLATE) && !xen_pv_domain()) { rc = xen_remap_vma_range(vma, kdata.addr, kdata.num << PAGE_SHIFT); } else { unsigned int domid = @@ -1591,7 +1589,7 @@ static void privcmd_close(struct vm_area_struct *vma) int numgfns = (vma->vm_end - vma->vm_start) >> XEN_PAGE_SHIFT; int rc; - if (!xen_feature(XENFEAT_auto_translated_physmap) || !numpgs || !pages) + if (xen_pv_domain() || !numpgs || !pages) return; rc = xen_unmap_domain_gfn_range(vma, numgfns, pages); diff --git a/drivers/xen/pvcalls-back.c b/drivers/xen/pvcalls-back.c index fd7ed65e0197..c5b6f6fa11eb 100644 --- a/drivers/xen/pvcalls-back.c +++ b/drivers/xen/pvcalls-back.c @@ -409,7 +409,7 @@ static int pvcalls_back_connect(struct xenbus_device *dev, ret = sock_create(AF_INET, SOCK_STREAM, 0, &sock); if (ret < 0) goto out; - ret = inet_stream_connect(sock, sa, req->u.connect.len, 0); + ret = inet_stream_connect(sock, (struct sockaddr_unsized *)sa, req->u.connect.len, 0); if (ret < 0) { sock_release(sock); goto out; @@ -650,7 +650,7 @@ static int pvcalls_back_bind(struct xenbus_device *dev, if (ret < 0) goto out; - ret = inet_bind(map->sock, (struct sockaddr *)&req->u.bind.addr, + ret = inet_bind(map->sock, (struct sockaddr_unsized *)&req->u.bind.addr, req->u.bind.len); if (ret < 0) goto out; diff --git a/drivers/xen/pvcalls-front.c b/drivers/xen/pvcalls-front.c index b72ee9379d77..4926d4badc57 100644 --- a/drivers/xen/pvcalls-front.c +++ b/drivers/xen/pvcalls-front.c @@ -341,6 +341,7 @@ int pvcalls_front_socket(struct socket *sock) pvcalls_exit(); return ret; } +EXPORT_SYMBOL_GPL(pvcalls_front_socket); static void free_active_ring(struct sock_mapping *map) { @@ -486,6 +487,7 @@ int pvcalls_front_connect(struct socket *sock, struct sockaddr *addr, pvcalls_exit_sock(sock); return ret; } +EXPORT_SYMBOL_GPL(pvcalls_front_connect); static int __write_ring(struct pvcalls_data_intf *intf, struct pvcalls_data *data, @@ -581,6 +583,7 @@ again: pvcalls_exit_sock(sock); return tot_sent; } +EXPORT_SYMBOL_GPL(pvcalls_front_sendmsg); static int __read_ring(struct pvcalls_data_intf *intf, struct pvcalls_data *data, @@ -666,6 +669,7 @@ int pvcalls_front_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, pvcalls_exit_sock(sock); return ret; } +EXPORT_SYMBOL_GPL(pvcalls_front_recvmsg); int pvcalls_front_bind(struct socket *sock, struct sockaddr *addr, int addr_len) { @@ -719,6 +723,7 @@ int pvcalls_front_bind(struct socket *sock, struct sockaddr *addr, int addr_len) pvcalls_exit_sock(sock); return 0; } +EXPORT_SYMBOL_GPL(pvcalls_front_bind); int pvcalls_front_listen(struct socket *sock, int backlog) { @@ -768,8 +773,10 @@ int pvcalls_front_listen(struct socket *sock, int backlog) pvcalls_exit_sock(sock); return ret; } +EXPORT_SYMBOL_GPL(pvcalls_front_listen); -int pvcalls_front_accept(struct socket *sock, struct socket *newsock, int flags) +int pvcalls_front_accept(struct socket *sock, struct socket *newsock, + struct proto_accept_arg *arg) { struct pvcalls_bedata *bedata; struct sock_mapping *map; @@ -788,7 +795,7 @@ int pvcalls_front_accept(struct socket *sock, struct socket *newsock, int flags) return -EINVAL; } - nonblock = flags & SOCK_NONBLOCK; + nonblock = arg->flags & SOCK_NONBLOCK; /* * Backend only supports 1 inflight accept request, will return * errors for the others @@ -904,6 +911,7 @@ received: pvcalls_exit_sock(sock); return ret; } +EXPORT_SYMBOL_GPL(pvcalls_front_accept); static __poll_t pvcalls_front_poll_passive(struct file *file, struct pvcalls_bedata *bedata, @@ -1004,6 +1012,7 @@ __poll_t pvcalls_front_poll(struct file *file, struct socket *sock, pvcalls_exit_sock(sock); return ret; } +EXPORT_SYMBOL_GPL(pvcalls_front_poll); int pvcalls_front_release(struct socket *sock) { @@ -1087,6 +1096,7 @@ int pvcalls_front_release(struct socket *sock) pvcalls_exit(); return 0; } +EXPORT_SYMBOL_GPL(pvcalls_front_release); static const struct xenbus_device_id pvcalls_front_ids[] = { { "pvcalls" }, diff --git a/drivers/xen/pvcalls-front.h b/drivers/xen/pvcalls-front.h index f694ad77379f..881ef14660bc 100644 --- a/drivers/xen/pvcalls-front.h +++ b/drivers/xen/pvcalls-front.h @@ -12,7 +12,7 @@ int pvcalls_front_bind(struct socket *sock, int pvcalls_front_listen(struct socket *sock, int backlog); int pvcalls_front_accept(struct socket *sock, struct socket *newsock, - int flags); + struct proto_accept_arg *arg); int pvcalls_front_sendmsg(struct socket *sock, struct msghdr *msg, size_t len); diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c index a337edcf8faf..ccf25027bec1 100644 --- a/drivers/xen/swiotlb-xen.c +++ b/drivers/xen/swiotlb-xen.c @@ -74,19 +74,21 @@ static inline phys_addr_t xen_dma_to_phys(struct device *dev, return xen_bus_to_phys(dev, dma_to_phys(dev, dma_addr)); } +static inline bool range_requires_alignment(phys_addr_t p, size_t size) +{ + phys_addr_t algn = 1ULL << (get_order(size) + PAGE_SHIFT); + phys_addr_t bus_addr = pfn_to_bfn(XEN_PFN_DOWN(p)) << XEN_PAGE_SHIFT; + + return IS_ALIGNED(p, algn) && !IS_ALIGNED(bus_addr, algn); +} + static inline int range_straddles_page_boundary(phys_addr_t p, size_t size) { unsigned long next_bfn, xen_pfn = XEN_PFN_DOWN(p); unsigned int i, nr_pages = XEN_PFN_UP(xen_offset_in_page(p) + size); - phys_addr_t algn = 1ULL << (get_order(size) + PAGE_SHIFT); next_bfn = pfn_to_bfn(xen_pfn); - /* If buffer is physically aligned, ensure DMA alignment. */ - if (IS_ALIGNED(p, algn) && - !IS_ALIGNED((phys_addr_t)next_bfn << XEN_PAGE_SHIFT, algn)) - return 1; - for (i = 1; i < nr_pages; i++) if (pfn_to_bfn(++xen_pfn) != ++next_bfn) return 1; @@ -111,7 +113,7 @@ static struct io_tlb_pool *xen_swiotlb_find_pool(struct device *dev, } #ifdef CONFIG_X86 -int xen_swiotlb_fixup(void *buf, unsigned long nslabs) +int __init xen_swiotlb_fixup(void *buf, unsigned long nslabs) { int rc; unsigned int order = get_order(IO_TLB_SEGSIZE << IO_TLB_SHIFT); @@ -156,7 +158,8 @@ xen_swiotlb_alloc_coherent(struct device *dev, size_t size, *dma_handle = xen_phys_to_dma(dev, phys); if (*dma_handle + size - 1 > dma_mask || - range_straddles_page_boundary(phys, size)) { + range_straddles_page_boundary(phys, size) || + range_requires_alignment(phys, size)) { if (xen_create_contiguous_region(phys, order, fls64(dma_mask), dma_handle) != 0) goto out_free_pages; @@ -182,7 +185,8 @@ xen_swiotlb_free_coherent(struct device *dev, size_t size, void *vaddr, size = ALIGN(size, XEN_PAGE_SIZE); if (WARN_ON_ONCE(dma_handle + size - 1 > dev->coherent_dma_mask) || - WARN_ON_ONCE(range_straddles_page_boundary(phys, size))) + WARN_ON_ONCE(range_straddles_page_boundary(phys, size) || + range_requires_alignment(phys, size))) return; if (TestClearPageXenRemapped(virt_to_page(vaddr))) @@ -196,23 +200,39 @@ xen_swiotlb_free_coherent(struct device *dev, size_t size, void *vaddr, * physical address to use is returned. * * Once the device is given the dma address, the device owns this memory until - * either xen_swiotlb_unmap_page or xen_swiotlb_dma_sync_single is performed. + * either xen_swiotlb_unmap_phys or xen_swiotlb_dma_sync_single is performed. */ -static dma_addr_t xen_swiotlb_map_page(struct device *dev, struct page *page, - unsigned long offset, size_t size, - enum dma_data_direction dir, +static dma_addr_t xen_swiotlb_map_phys(struct device *dev, phys_addr_t phys, + size_t size, enum dma_data_direction dir, unsigned long attrs) { - phys_addr_t map, phys = page_to_phys(page) + offset; - dma_addr_t dev_addr = xen_phys_to_dma(dev, phys); + dma_addr_t dev_addr; + phys_addr_t map; BUG_ON(dir == DMA_NONE); + + if (attrs & DMA_ATTR_MMIO) { + if (unlikely(!dma_capable(dev, phys, size, false))) { + dev_err_once( + dev, + "DMA addr %pa+%zu overflow (mask %llx, bus limit %llx).\n", + &phys, size, *dev->dma_mask, + dev->bus_dma_limit); + WARN_ON_ONCE(1); + return DMA_MAPPING_ERROR; + } + return phys; + } + + dev_addr = xen_phys_to_dma(dev, phys); + /* * If the address happens to be in the device's DMA window, * we can safely return the device addr and not worry about bounce * buffering it. */ if (dma_capable(dev, dev_addr, size, true) && + !dma_kmalloc_needs_bounce(dev, size, dir) && !range_straddles_page_boundary(phys, size) && !xen_arch_need_swiotlb(dev, phys, dev_addr) && !is_swiotlb_force_bounce(dev)) @@ -252,13 +272,13 @@ done: /* * Unmap a single streaming mode DMA translation. The dma_addr and size must - * match what was provided for in a previous xen_swiotlb_map_page call. All + * match what was provided for in a previous xen_swiotlb_map_phys call. All * other usages are undefined. * * After this call, reads by the cpu to the buffer are guaranteed to see * whatever the device wrote there. */ -static void xen_swiotlb_unmap_page(struct device *hwdev, dma_addr_t dev_addr, +static void xen_swiotlb_unmap_phys(struct device *hwdev, dma_addr_t dev_addr, size_t size, enum dma_data_direction dir, unsigned long attrs) { phys_addr_t paddr = xen_dma_to_phys(hwdev, dev_addr); @@ -320,7 +340,7 @@ xen_swiotlb_sync_single_for_device(struct device *dev, dma_addr_t dma_addr, /* * Unmap a set of streaming mode DMA translations. Again, cpu read rules - * concerning calls here are the same as for swiotlb_unmap_page() above. + * concerning calls here are the same as for swiotlb_unmap_phys() above. */ static void xen_swiotlb_unmap_sg(struct device *hwdev, struct scatterlist *sgl, int nelems, @@ -332,7 +352,7 @@ xen_swiotlb_unmap_sg(struct device *hwdev, struct scatterlist *sgl, int nelems, BUG_ON(dir == DMA_NONE); for_each_sg(sgl, sg, nelems, i) - xen_swiotlb_unmap_page(hwdev, sg->dma_address, sg_dma_len(sg), + xen_swiotlb_unmap_phys(hwdev, sg->dma_address, sg_dma_len(sg), dir, attrs); } @@ -347,8 +367,8 @@ xen_swiotlb_map_sg(struct device *dev, struct scatterlist *sgl, int nelems, BUG_ON(dir == DMA_NONE); for_each_sg(sgl, sg, nelems, i) { - sg->dma_address = xen_swiotlb_map_page(dev, sg_page(sg), - sg->offset, sg->length, dir, attrs); + sg->dma_address = xen_swiotlb_map_phys(dev, sg_phys(sg), + sg->length, dir, attrs); if (sg->dma_address == DMA_MAPPING_ERROR) goto out_unmap; sg_dma_len(sg) = sg->length; @@ -413,8 +433,8 @@ const struct dma_map_ops xen_swiotlb_dma_ops = { .sync_sg_for_device = xen_swiotlb_sync_sg_for_device, .map_sg = xen_swiotlb_map_sg, .unmap_sg = xen_swiotlb_unmap_sg, - .map_page = xen_swiotlb_map_page, - .unmap_page = xen_swiotlb_unmap_page, + .map_phys = xen_swiotlb_map_phys, + .unmap_phys = xen_swiotlb_unmap_phys, .dma_supported = xen_swiotlb_dma_supported, .mmap = dma_common_mmap, .get_sgtable = dma_common_get_sgtable, diff --git a/drivers/xen/time.c b/drivers/xen/time.c index 152dd33bb223..5683383d2305 100644 --- a/drivers/xen/time.c +++ b/drivers/xen/time.c @@ -136,14 +136,6 @@ void xen_manage_runstate_time(int action) } } -/* - * Runstate accounting - */ -void xen_get_runstate_snapshot(struct vcpu_runstate_info *res) -{ - xen_get_runstate_snapshot_cpu(res, smp_processor_id()); -} - /* return true when a vcpu could run but has no real cpu to run on */ bool xen_vcpu_stolen(int vcpu) { diff --git a/drivers/xen/unpopulated-alloc.c b/drivers/xen/unpopulated-alloc.c index a39f2d36dd9c..d6fc2aefe264 100644 --- a/drivers/xen/unpopulated-alloc.c +++ b/drivers/xen/unpopulated-alloc.c @@ -105,7 +105,7 @@ static int fill_list(unsigned int nr_pages) * are not restored since this region is now known not to * conflict with any devices. */ - if (!xen_feature(XENFEAT_auto_translated_physmap)) { + if (xen_pv_domain()) { xen_pfn_t pfn = PFN_DOWN(res->start); for (i = 0; i < alloc_pages; i++) { @@ -184,7 +184,7 @@ int xen_alloc_unpopulated_pages(unsigned int nr_pages, struct page **pages) pages[i] = pg; #ifdef CONFIG_XEN_HAVE_PVMMU - if (!xen_feature(XENFEAT_auto_translated_physmap)) { + if (xen_pv_domain()) { ret = xen_alloc_p2m_entry(page_to_pfn(pg)); if (ret < 0) { unsigned int j; diff --git a/drivers/xen/xen-acpi-processor.c b/drivers/xen/xen-acpi-processor.c index 296703939846..f2e8eaf684ba 100644 --- a/drivers/xen/xen-acpi-processor.c +++ b/drivers/xen/xen-acpi-processor.c @@ -495,7 +495,7 @@ static void xen_acpi_processor_resume_worker(struct work_struct *dummy) pr_info("ACPI data upload failed, error = %d\n", rc); } -static void xen_acpi_processor_resume(void) +static void xen_acpi_processor_resume(void *data) { static DECLARE_WORK(wq, xen_acpi_processor_resume_worker); @@ -509,10 +509,14 @@ static void xen_acpi_processor_resume(void) schedule_work(&wq); } -static struct syscore_ops xap_syscore_ops = { +static const struct syscore_ops xap_syscore_ops = { .resume = xen_acpi_processor_resume, }; +static struct syscore xap_syscore = { + .ops = &xap_syscore_ops, +}; + static int __init xen_acpi_processor_init(void) { int i; @@ -563,7 +567,7 @@ static int __init xen_acpi_processor_init(void) if (rc) goto err_unregister; - register_syscore_ops(&xap_syscore_ops); + register_syscore(&xap_syscore); return 0; err_unregister: @@ -580,7 +584,7 @@ static void __exit xen_acpi_processor_exit(void) { int i; - unregister_syscore_ops(&xap_syscore_ops); + unregister_syscore(&xap_syscore); bitmap_free(acpi_ids_done); bitmap_free(acpi_id_present); bitmap_free(acpi_id_cst_present); diff --git a/drivers/xen/xen-pciback/pci_stub.c b/drivers/xen/xen-pciback/pci_stub.c index b616b7768c3b..045e74847fe6 100644 --- a/drivers/xen/xen-pciback/pci_stub.c +++ b/drivers/xen/xen-pciback/pci_stub.c @@ -262,26 +262,6 @@ struct pci_dev *pcistub_get_pci_dev_by_slot(struct xen_pcibk_device *pdev, return found_dev; } -struct pci_dev *pcistub_get_pci_dev(struct xen_pcibk_device *pdev, - struct pci_dev *dev) -{ - struct pcistub_device *psdev; - struct pci_dev *found_dev = NULL; - unsigned long flags; - - spin_lock_irqsave(&pcistub_devices_lock, flags); - - list_for_each_entry(psdev, &pcistub_devices, dev_list) { - if (psdev->dev == dev) { - found_dev = pcistub_device_get_pci_dev(pdev, psdev); - break; - } - } - - spin_unlock_irqrestore(&pcistub_devices_lock, flags); - return found_dev; -} - /* * Called when: * - XenBus state has been reconfigure (pci unplug). See xen_pcibk_remove_device @@ -1281,7 +1261,7 @@ static ssize_t slots_show(struct device_driver *drv, char *buf) if (count >= PAGE_SIZE) break; - count += scnprintf(buf + count, PAGE_SIZE - count, + count += sysfs_emit_at(buf, count, "%04x:%02x:%02x.%d\n", pci_dev_id->domain, pci_dev_id->bus, PCI_SLOT(pci_dev_id->devfn), @@ -1310,7 +1290,7 @@ static ssize_t irq_handlers_show(struct device_driver *drv, char *buf) if (!dev_data) continue; count += - scnprintf(buf + count, PAGE_SIZE - count, + sysfs_emit_at(buf, count, "%s:%s:%sing:%ld\n", pci_name(psdev->dev), dev_data->isr_on ? "on" : "off", @@ -1395,7 +1375,7 @@ static ssize_t quirks_show(struct device_driver *drv, char *buf) if (count >= PAGE_SIZE) goto out; - count += scnprintf(buf + count, PAGE_SIZE - count, + count += sysfs_emit_at(buf, count, "%02x:%02x.%01x\n\t%04x:%04x:%04x:%04x\n", quirk->pdev->bus->number, PCI_SLOT(quirk->pdev->devfn), @@ -1411,7 +1391,7 @@ static ssize_t quirks_show(struct device_driver *drv, char *buf) if (count >= PAGE_SIZE) goto out; - count += scnprintf(buf + count, PAGE_SIZE - count, + count += sysfs_emit_at(buf, count, "\t\t%08x:%01x:%08x\n", cfg_entry->base_offset + field->offset, field->size, @@ -1482,7 +1462,7 @@ static ssize_t permissive_show(struct device_driver *drv, char *buf) if (!dev_data || !dev_data->permissive) continue; count += - scnprintf(buf + count, PAGE_SIZE - count, "%s\n", + sysfs_emit_at(buf, count, "%s\n", pci_name(psdev->dev)); } spin_unlock_irqrestore(&pcistub_devices_lock, flags); @@ -1541,7 +1521,7 @@ static ssize_t allow_interrupt_control_show(struct device_driver *drv, if (!dev_data || !dev_data->allow_interrupt_control) continue; count += - scnprintf(buf + count, PAGE_SIZE - count, "%s\n", + sysfs_emit_at(buf, count, "%s\n", pci_name(psdev->dev)); } spin_unlock_irqrestore(&pcistub_devices_lock, flags); diff --git a/drivers/xen/xen-pciback/pciback.h b/drivers/xen/xen-pciback/pciback.h index f9599ed2f2e2..b786c1f74f85 100644 --- a/drivers/xen/xen-pciback/pciback.h +++ b/drivers/xen/xen-pciback/pciback.h @@ -67,8 +67,6 @@ extern struct list_head xen_pcibk_quirks; struct pci_dev *pcistub_get_pci_dev_by_slot(struct xen_pcibk_device *pdev, int domain, int bus, int slot, int func); -struct pci_dev *pcistub_get_pci_dev(struct xen_pcibk_device *pdev, - struct pci_dev *dev); void pcistub_put_pci_dev(struct pci_dev *dev); static inline bool xen_pcibk_pv_support(void) diff --git a/drivers/xen/xenbus/xenbus.h b/drivers/xen/xenbus/xenbus.h index 13821e7e825e..9ac0427724a3 100644 --- a/drivers/xen/xenbus/xenbus.h +++ b/drivers/xen/xenbus/xenbus.h @@ -77,6 +77,7 @@ enum xb_req_state { struct xb_req_data { struct list_head list; wait_queue_head_t wq; + struct kref kref; struct xsd_sockmsg msg; uint32_t caller_req_id; enum xsd_sockmsg_type type; @@ -103,6 +104,7 @@ int xb_init_comms(void); void xb_deinit_comms(void); int xs_watch_msg(struct xs_watch_event *event); void xs_request_exit(struct xb_req_data *req); +void xs_free_req(struct kref *kref); int xenbus_match(struct device *_dev, const struct device_driver *_drv); int xenbus_dev_probe(struct device *_dev); diff --git a/drivers/xen/xenbus/xenbus_client.c b/drivers/xen/xenbus/xenbus_client.c index 51b3124b0d56..2dc874fb5506 100644 --- a/drivers/xen/xenbus/xenbus_client.c +++ b/drivers/xen/xenbus/xenbus_client.c @@ -202,6 +202,7 @@ int xenbus_watch_pathfmt(struct xenbus_device *dev, } EXPORT_SYMBOL_GPL(xenbus_watch_pathfmt); +__printf(4, 5) static void xenbus_switch_fatal(struct xenbus_device *, int, int, const char *, ...); @@ -287,6 +288,7 @@ int xenbus_frontend_closed(struct xenbus_device *dev) } EXPORT_SYMBOL_GPL(xenbus_frontend_closed); +__printf(3, 0) static void xenbus_va_dev_error(struct xenbus_device *dev, int err, const char *fmt, va_list ap) { @@ -953,7 +955,7 @@ static const struct xenbus_ring_ops ring_ops_hvm = { void __init xenbus_ring_ops_init(void) { #ifdef CONFIG_XEN_PV - if (!xen_feature(XENFEAT_auto_translated_physmap)) + if (xen_pv_domain()) ring_ops = &ring_ops_pv; else #endif diff --git a/drivers/xen/xenbus/xenbus_comms.c b/drivers/xen/xenbus/xenbus_comms.c index e5fda0256feb..82df2da1b880 100644 --- a/drivers/xen/xenbus/xenbus_comms.c +++ b/drivers/xen/xenbus/xenbus_comms.c @@ -309,8 +309,8 @@ static int process_msg(void) virt_wmb(); req->state = xb_req_state_got_reply; req->cb(req); - } else - kfree(req); + } + kref_put(&req->kref, xs_free_req); } mutex_unlock(&xs_response_mutex); @@ -386,14 +386,13 @@ static int process_writes(void) state.req->msg.type = XS_ERROR; state.req->err = err; list_del(&state.req->list); - if (state.req->state == xb_req_state_aborted) - kfree(state.req); - else { + if (state.req->state != xb_req_state_aborted) { /* write err, then update state */ virt_wmb(); state.req->state = xb_req_state_got_reply; wake_up(&state.req->wq); } + kref_put(&state.req->kref, xs_free_req); mutex_unlock(&xb_write_mutex); diff --git a/drivers/xen/xenbus/xenbus_dev_frontend.c b/drivers/xen/xenbus/xenbus_dev_frontend.c index 46f8916597e5..f5c21ba64df5 100644 --- a/drivers/xen/xenbus/xenbus_dev_frontend.c +++ b/drivers/xen/xenbus/xenbus_dev_frontend.c @@ -406,7 +406,7 @@ void xenbus_dev_queue_reply(struct xb_req_data *req) mutex_unlock(&u->reply_mutex); kfree(req->body); - kfree(req); + kref_put(&req->kref, xs_free_req); kref_put(&u->kref, xenbus_file_free); diff --git a/drivers/xen/xenbus/xenbus_probe.c b/drivers/xen/xenbus/xenbus_probe.c index 6d32ffb01136..86fe6e779056 100644 --- a/drivers/xen/xenbus/xenbus_probe.c +++ b/drivers/xen/xenbus/xenbus_probe.c @@ -966,9 +966,15 @@ static int __init xenbus_init(void) if (xen_pv_domain()) xen_store_domain_type = XS_PV; if (xen_hvm_domain()) + { xen_store_domain_type = XS_HVM; - if (xen_hvm_domain() && xen_initial_domain()) - xen_store_domain_type = XS_LOCAL; + err = hvm_get_parameter(HVM_PARAM_STORE_EVTCHN, &v); + if (err) + goto out_error; + xen_store_evtchn = (int)v; + if (!v && xen_initial_domain()) + xen_store_domain_type = XS_LOCAL; + } if (xen_pv_domain() && !xen_start_info->store_evtchn) xen_store_domain_type = XS_LOCAL; if (xen_pv_domain() && xen_start_info->store_evtchn) @@ -987,10 +993,6 @@ static int __init xenbus_init(void) xen_store_interface = gfn_to_virt(xen_store_gfn); break; case XS_HVM: - err = hvm_get_parameter(HVM_PARAM_STORE_EVTCHN, &v); - if (err) - goto out_error; - xen_store_evtchn = (int)v; err = hvm_get_parameter(HVM_PARAM_STORE_PFN, &v); if (err) goto out_error; diff --git a/drivers/xen/xenbus/xenbus_probe_frontend.c b/drivers/xen/xenbus/xenbus_probe_frontend.c index fcb335bb7b18..6d1819269cbe 100644 --- a/drivers/xen/xenbus/xenbus_probe_frontend.c +++ b/drivers/xen/xenbus/xenbus_probe_frontend.c @@ -513,4 +513,5 @@ static int __init boot_wait_for_devices(void) late_initcall(boot_wait_for_devices); #endif +MODULE_DESCRIPTION("Xen PV-device frontend support"); MODULE_LICENSE("GPL"); diff --git a/drivers/xen/xenbus/xenbus_xs.c b/drivers/xen/xenbus/xenbus_xs.c index d32c726f7a12..15f18374020e 100644 --- a/drivers/xen/xenbus/xenbus_xs.c +++ b/drivers/xen/xenbus/xenbus_xs.c @@ -112,6 +112,12 @@ static void xs_suspend_exit(void) wake_up_all(&xs_state_enter_wq); } +void xs_free_req(struct kref *kref) +{ + struct xb_req_data *req = container_of(kref, struct xb_req_data, kref); + kfree(req); +} + static uint32_t xs_request_enter(struct xb_req_data *req) { uint32_t rq_id; @@ -237,6 +243,12 @@ static void xs_send(struct xb_req_data *req, struct xsd_sockmsg *msg) req->caller_req_id = req->msg.req_id; req->msg.req_id = xs_request_enter(req); + /* + * Take 2nd ref. One for this thread, and the second for the + * xenbus_thread. + */ + kref_get(&req->kref); + mutex_lock(&xb_write_mutex); list_add_tail(&req->list, &xb_write_list); notify = list_is_singular(&xb_write_list); @@ -261,8 +273,8 @@ static void *xs_wait_for_reply(struct xb_req_data *req, struct xsd_sockmsg *msg) if (req->state == xb_req_state_queued || req->state == xb_req_state_wait_reply) req->state = xb_req_state_aborted; - else - kfree(req); + + kref_put(&req->kref, xs_free_req); mutex_unlock(&xb_write_mutex); return ret; @@ -291,6 +303,7 @@ int xenbus_dev_request_and_reply(struct xsd_sockmsg *msg, void *par) req->cb = xenbus_dev_queue_reply; req->par = par; req->user_req = true; + kref_init(&req->kref); xs_send(req, msg); @@ -319,6 +332,7 @@ static void *xs_talkv(struct xenbus_transaction t, req->num_vecs = num_vecs; req->cb = xs_wake_up; req->user_req = false; + kref_init(&req->kref); msg.req_id = 0; msg.tx_id = t.id; @@ -393,10 +407,10 @@ static char *join(const char *dir, const char *name) buffer = kasprintf(GFP_NOIO | __GFP_HIGH, "%s", dir); else buffer = kasprintf(GFP_NOIO | __GFP_HIGH, "%s/%s", dir, name); - return (!buffer) ? ERR_PTR(-ENOMEM) : buffer; + return buffer ?: ERR_PTR(-ENOMEM); } -static char **split(char *strings, unsigned int len, unsigned int *num) +static char **split_strings(char *strings, unsigned int len, unsigned int *num) { char *p, **ret; @@ -434,7 +448,7 @@ char **xenbus_directory(struct xenbus_transaction t, if (IS_ERR(strings)) return ERR_CAST(strings); - return split(strings, len, num); + return split_strings(strings, len, num); } EXPORT_SYMBOL_GPL(xenbus_directory); @@ -498,23 +512,6 @@ int xenbus_write(struct xenbus_transaction t, } EXPORT_SYMBOL_GPL(xenbus_write); -/* Create a new directory. */ -int xenbus_mkdir(struct xenbus_transaction t, - const char *dir, const char *node) -{ - char *path; - int ret; - - path = join(dir, node); - if (IS_ERR(path)) - return PTR_ERR(path); - - ret = xs_error(xs_single(t, XS_MKDIR, path, NULL)); - kfree(path); - return ret; -} -EXPORT_SYMBOL_GPL(xenbus_mkdir); - /* Destroy a file or directory (directories must be empty). */ int xenbus_rm(struct xenbus_transaction t, const char *dir, const char *node) { @@ -549,18 +546,12 @@ int xenbus_transaction_start(struct xenbus_transaction *t) EXPORT_SYMBOL_GPL(xenbus_transaction_start); /* End a transaction. - * If abandon is true, transaction is discarded instead of committed. + * If abort is true, transaction is discarded instead of committed. */ -int xenbus_transaction_end(struct xenbus_transaction t, int abort) +int xenbus_transaction_end(struct xenbus_transaction t, bool abort) { - char abortstr[2]; - - if (abort) - strcpy(abortstr, "F"); - else - strcpy(abortstr, "T"); - - return xs_error(xs_single(t, XS_TRANSACTION_END, abortstr, NULL)); + return xs_error(xs_single(t, XS_TRANSACTION_END, abort ? "F" : "T", + NULL)); } EXPORT_SYMBOL_GPL(xenbus_transaction_end); @@ -721,26 +712,6 @@ int xs_watch_msg(struct xs_watch_event *event) return 0; } -/* - * Certain older XenBus toolstack cannot handle reading values that are - * not populated. Some Xen 3.4 installation are incapable of doing this - * so if we are running on anything older than 4 do not attempt to read - * control/platform-feature-xs_reset_watches. - */ -static bool xen_strict_xenbus_quirk(void) -{ -#ifdef CONFIG_X86 - uint32_t eax, ebx, ecx, edx, base; - - base = xen_cpuid_base(); - cpuid(base + 1, &eax, &ebx, &ecx, &edx); - - if ((eax >> 16) < 4) - return true; -#endif - return false; - -} static void xs_reset_watches(void) { int err; @@ -748,9 +719,6 @@ static void xs_reset_watches(void) if (!xen_hvm_domain() || xen_initial_domain()) return; - if (xen_strict_xenbus_quirk()) - return; - if (!xenbus_read_unsigned("control", "platform-feature-xs_reset_watches", 0)) return; diff --git a/drivers/xen/xenfs/super.c b/drivers/xen/xenfs/super.c index d7d64235010d..37ea7c5c0346 100644 --- a/drivers/xen/xenfs/super.c +++ b/drivers/xen/xenfs/super.c @@ -88,7 +88,7 @@ static struct file_system_type xenfs_type = { .owner = THIS_MODULE, .name = "xenfs", .init_fs_context = xenfs_init_fs_context, - .kill_sb = kill_litter_super, + .kill_sb = kill_anon_super, }; MODULE_ALIAS_FS("xenfs"); diff --git a/drivers/xen/xenfs/xensyms.c b/drivers/xen/xenfs/xensyms.c index b799bc759c15..088b7f02c358 100644 --- a/drivers/xen/xenfs/xensyms.c +++ b/drivers/xen/xenfs/xensyms.c @@ -48,7 +48,7 @@ static int xensyms_next_sym(struct xensyms *xs) return -ENOMEM; set_xen_guest_handle(symdata->name, xs->name); - symdata->symnum--; /* Rewind */ + symdata->symnum = symnum; /* Rewind */ ret = HYPERVISOR_platform_op(&xs->op); if (ret < 0) @@ -78,7 +78,7 @@ static void *xensyms_next(struct seq_file *m, void *p, loff_t *pos) { struct xensyms *xs = m->private; - xs->op.u.symdata.symnum = ++(*pos); + *pos = xs->op.u.symdata.symnum; if (xensyms_next_sym(xs)) return NULL; |