diff options
Diffstat (limited to 'drivers/xen')
33 files changed, 494 insertions, 205 deletions
diff --git a/drivers/xen/Kconfig b/drivers/xen/Kconfig index d5989871dd5d..24f485827e03 100644 --- a/drivers/xen/Kconfig +++ b/drivers/xen/Kconfig @@ -177,8 +177,8 @@ config XEN_GRANT_DMA_ALLOC config SWIOTLB_XEN def_bool y + depends on ARCH_HAS_DMA_OPS depends on XEN_PV || ARM || ARM64 - select DMA_OPS select SWIOTLB config XEN_PCI_STUB @@ -278,7 +278,7 @@ 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 @@ -348,10 +348,10 @@ config XEN_GRANT_DMA_IOMMU config XEN_GRANT_DMA_OPS bool - select DMA_OPS config XEN_VIRTIO bool "Xen virtio support" + depends on ARCH_HAS_DMA_OPS depends on VIRTIO select XEN_GRANT_DMA_OPS select XEN_GRANT_DMA_IOMMU if OF diff --git a/drivers/xen/acpi.c b/drivers/xen/acpi.c index 6893c79fd2a1..d2ee605c5ca1 100644 --- a/drivers/xen/acpi.c +++ b/drivers/xen/acpi.c @@ -30,6 +30,7 @@ * IN THE SOFTWARE. */ +#include <linux/pci.h> #include <xen/acpi.h> #include <xen/interface/platform.h> #include <asm/xen/hypercall.h> @@ -75,3 +76,76 @@ int xen_acpi_notify_hypervisor_extended_sleep(u8 sleep_state, return xen_acpi_notify_hypervisor_state(sleep_state, val_a, val_b, true); } + +struct acpi_prt_entry { + struct acpi_pci_id id; + u8 pin; + acpi_handle link; + u32 index; +}; + +int xen_acpi_get_gsi_info(struct pci_dev *dev, + int *gsi_out, + int *trigger_out, + int *polarity_out) +{ + int gsi; + u8 pin; + struct acpi_prt_entry *entry; + int trigger = ACPI_LEVEL_SENSITIVE; + int polarity = acpi_irq_model == ACPI_IRQ_MODEL_GIC ? + ACPI_ACTIVE_HIGH : ACPI_ACTIVE_LOW; + + if (!dev || !gsi_out || !trigger_out || !polarity_out) + return -EINVAL; + + pin = dev->pin; + if (!pin) + return -EINVAL; + + entry = acpi_pci_irq_lookup(dev, pin); + if (entry) { + if (entry->link) + gsi = acpi_pci_link_allocate_irq(entry->link, + entry->index, + &trigger, &polarity, + NULL); + else + gsi = entry->index; + } else + gsi = -1; + + if (gsi < 0) + return -EINVAL; + + *gsi_out = gsi; + *trigger_out = trigger; + *polarity_out = polarity; + + return 0; +} +EXPORT_SYMBOL_GPL(xen_acpi_get_gsi_info); + +static get_gsi_from_sbdf_t get_gsi_from_sbdf; +static DEFINE_RWLOCK(get_gsi_from_sbdf_lock); + +void xen_acpi_register_get_gsi_func(get_gsi_from_sbdf_t func) +{ + write_lock(&get_gsi_from_sbdf_lock); + get_gsi_from_sbdf = func; + write_unlock(&get_gsi_from_sbdf_lock); +} +EXPORT_SYMBOL_GPL(xen_acpi_register_get_gsi_func); + +int xen_acpi_get_gsi_from_sbdf(u32 sbdf) +{ + int ret = -EOPNOTSUPP; + + read_lock(&get_gsi_from_sbdf_lock); + if (get_gsi_from_sbdf) + ret = get_gsi_from_sbdf(sbdf); + read_unlock(&get_gsi_from_sbdf_lock); + + return ret; +} +EXPORT_SYMBOL_GPL(xen_acpi_get_gsi_from_sbdf); diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c index 976c6cdf9ee6..2de37dcd7556 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, @@ -146,7 +146,8 @@ static DECLARE_WAIT_QUEUE_HEAD(balloon_wq); /* balloon_append: add the given page to the balloon. */ static void balloon_append(struct page *page) { - __SetPageOffline(page); + if (!PageOffline(page)) + __SetPageOffline(page); /* Lowmem is re-populated first, so highmem pages go at list tail. */ if (PageHighMem(page)) { @@ -156,6 +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); } @@ -178,6 +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; } @@ -412,7 +417,11 @@ static enum bp_state increase_reservation(unsigned long nr_pages) xenmem_reservation_va_mapping_update(1, &page, &frame_list[i]); - /* Relinquish the page back to the allocator. */ + /* + * Relinquish the page back to the allocator. Note that + * some pages, including ones added via xen_online_page(), might + * not be marked reserved; free_reserved_page() will handle that. + */ free_reserved_page(page); } @@ -670,9 +679,8 @@ 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) { -#if defined(CONFIG_XEN_PV) unsigned long start_pfn, pages; unsigned long pfn, extra_pfn_end; unsigned int i; @@ -694,27 +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; } -#endif + + 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; @@ -731,7 +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 b8cfea7812d6..41309d38f78c 100644 --- a/drivers/xen/events/events_base.c +++ b/drivers/xen/events/events_base.c @@ -411,7 +411,7 @@ static evtchn_port_t evtchn_from_irq(unsigned int irq) { const struct irq_info *info = NULL; - if (likely(irq < nr_irqs)) + if (likely(irq < irq_get_nr_irqs())) info = info_for_irq(irq); if (!info) return 0; @@ -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); } @@ -923,8 +917,8 @@ static void shutdown_pirq(struct irq_data *data) return; do_mask(info, EVT_MASK_REASON_EXPLICIT); - xen_evtchn_close(evtchn); xen_irq_info_cleanup(info); + xen_evtchn_close(evtchn); } static void enable_pirq(struct irq_data *data) @@ -956,6 +950,7 @@ EXPORT_SYMBOL_GPL(xen_irq_from_gsi); static void __unbind_from_irq(struct irq_info *info, unsigned int irq) { evtchn_port_t evtchn; + bool close_evtchn = false; if (!info) { xen_irq_free_desc(irq); @@ -975,7 +970,7 @@ static void __unbind_from_irq(struct irq_info *info, unsigned int irq) struct xenbus_device *dev; if (!info->is_static) - xen_evtchn_close(evtchn); + close_evtchn = true; switch (info->type) { case IRQT_VIRQ: @@ -995,6 +990,9 @@ static void __unbind_from_irq(struct irq_info *info, unsigned int irq) } xen_irq_info_cleanup(info); + + if (close_evtchn) + xen_evtchn_close(evtchn); } xen_free_irq(info); @@ -1186,7 +1184,7 @@ int xen_pirq_from_irq(unsigned irq) EXPORT_SYMBOL_GPL(xen_pirq_from_irq); static int bind_evtchn_to_irq_chip(evtchn_port_t evtchn, struct irq_chip *chip, - struct xenbus_device *dev) + struct xenbus_device *dev, bool shared) { int ret = -ENOMEM; struct irq_info *info; @@ -1220,7 +1218,8 @@ static int bind_evtchn_to_irq_chip(evtchn_port_t evtchn, struct irq_chip *chip, */ bind_evtchn_to_cpu(info, 0, false); } else if (!WARN_ON(info->type != IRQT_EVTCHN)) { - info->refcnt++; + if (shared && !WARN_ON(info->refcnt < 0)) + info->refcnt++; } ret = info->irq; @@ -1233,13 +1232,13 @@ out: int bind_evtchn_to_irq(evtchn_port_t evtchn) { - return bind_evtchn_to_irq_chip(evtchn, &xen_dynamic_chip, NULL); + return bind_evtchn_to_irq_chip(evtchn, &xen_dynamic_chip, NULL, false); } EXPORT_SYMBOL_GPL(bind_evtchn_to_irq); int bind_evtchn_to_irq_lateeoi(evtchn_port_t evtchn) { - return bind_evtchn_to_irq_chip(evtchn, &xen_lateeoi_chip, NULL); + return bind_evtchn_to_irq_chip(evtchn, &xen_lateeoi_chip, NULL, false); } EXPORT_SYMBOL_GPL(bind_evtchn_to_irq_lateeoi); @@ -1291,7 +1290,8 @@ static int bind_ipi_to_irq(unsigned int ipi, unsigned int cpu) static int bind_interdomain_evtchn_to_irq_chip(struct xenbus_device *dev, evtchn_port_t remote_port, - struct irq_chip *chip) + struct irq_chip *chip, + bool shared) { struct evtchn_bind_interdomain bind_interdomain; int err; @@ -1303,14 +1303,14 @@ static int bind_interdomain_evtchn_to_irq_chip(struct xenbus_device *dev, &bind_interdomain); return err ? : bind_evtchn_to_irq_chip(bind_interdomain.local_port, - chip, dev); + chip, dev, shared); } int bind_interdomain_evtchn_to_irq_lateeoi(struct xenbus_device *dev, evtchn_port_t remote_port) { return bind_interdomain_evtchn_to_irq_chip(dev, remote_port, - &xen_lateeoi_chip); + &xen_lateeoi_chip, false); } EXPORT_SYMBOL_GPL(bind_interdomain_evtchn_to_irq_lateeoi); @@ -1426,7 +1426,8 @@ static int bind_evtchn_to_irqhandler_chip(evtchn_port_t evtchn, { int irq, retval; - irq = bind_evtchn_to_irq_chip(evtchn, chip, NULL); + irq = bind_evtchn_to_irq_chip(evtchn, chip, NULL, + irqflags & IRQF_SHARED); if (irq < 0) return irq; retval = request_irq(irq, handler, irqflags, devname, dev_id); @@ -1467,7 +1468,8 @@ static int bind_interdomain_evtchn_to_irqhandler_chip( { int irq, retval; - irq = bind_interdomain_evtchn_to_irq_chip(dev, remote_port, chip); + irq = bind_interdomain_evtchn_to_irq_chip(dev, remote_port, chip, + irqflags & IRQF_SHARED); if (irq < 0) return irq; @@ -2216,7 +2218,7 @@ static __init void xen_alloc_callback_vector(void) return; pr_info("Xen HVM callback vector for event delivery is enabled\n"); - alloc_intr_gate(HYPERVISOR_CALLBACK_VECTOR, asm_sysvec_xen_hvm_callback); + sysvec_install(HYPERVISOR_CALLBACK_VECTOR, sysvec_xen_hvm_callback); } #else void xen_setup_callback_vector(void) {} diff --git a/drivers/xen/evtchn.c b/drivers/xen/evtchn.c index 59717628ca42..7e4a13e632dc 100644 --- a/drivers/xen/evtchn.c +++ b/drivers/xen/evtchn.c @@ -85,6 +85,7 @@ struct user_evtchn { struct per_user_data *user; evtchn_port_t port; bool enabled; + bool unbinding; }; static void evtchn_free_ring(evtchn_port_t *ring) @@ -164,6 +165,10 @@ static irqreturn_t evtchn_interrupt(int irq, void *data) struct per_user_data *u = evtchn->user; unsigned int prod, cons; + /* Handler might be called when tearing down the IRQ. */ + if (evtchn->unbinding) + return IRQ_HANDLED; + WARN(!evtchn->enabled, "Interrupt for port %u, but apparently not enabled; per-user %p\n", evtchn->port, u); @@ -421,6 +426,7 @@ static void evtchn_unbind_from_user(struct per_user_data *u, BUG_ON(irq < 0); + evtchn->unbinding = true; unbind_from_irqhandler(irq, evtchn); del_evtchn(u, evtchn); @@ -688,7 +694,6 @@ static const struct file_operations evtchn_fops = { .fasync = evtchn_fasync, .open = evtchn_open, .release = evtchn_release, - .llseek = no_llseek, }; static struct miscdevice evtchn_miscdev = { @@ -723,4 +728,5 @@ static void __exit evtchn_cleanup(void) module_init(evtchn_init); module_exit(evtchn_cleanup); +MODULE_DESCRIPTION("Xen /dev/xen/evtchn device driver"); MODULE_LICENSE("GPL"); diff --git a/drivers/xen/gntalloc.c b/drivers/xen/gntalloc.c index 26ffb8755ffb..f93f73ecefee 100644 --- a/drivers/xen/gntalloc.c +++ b/drivers/xen/gntalloc.c @@ -317,7 +317,7 @@ static long gntalloc_ioctl_alloc(struct gntalloc_file_private_data *priv, rc = -EFAULT; goto out_free; } - if (copy_to_user(arg->gref_ids, gref_ids, + if (copy_to_user(arg->gref_ids_flex, gref_ids, sizeof(gref_ids[0]) * op.count)) { rc = -EFAULT; goto out_free; diff --git a/drivers/xen/gntdev-dmabuf.c b/drivers/xen/gntdev-dmabuf.c index 42adc2c1e06b..5453d86324f6 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; diff --git a/drivers/xen/grant-dma-iommu.c b/drivers/xen/grant-dma-iommu.c index 6a9fe02c6bfc..0965e2dd4edf 100644 --- a/drivers/xen/grant-dma-iommu.c +++ b/drivers/xen/grant-dma-iommu.c @@ -51,14 +51,12 @@ static int grant_dma_iommu_probe(struct platform_device *pdev) return 0; } -static int grant_dma_iommu_remove(struct platform_device *pdev) +static void grant_dma_iommu_remove(struct platform_device *pdev) { struct grant_dma_iommu_device *mmu = platform_get_drvdata(pdev); platform_set_drvdata(pdev, NULL); iommu_device_unregister(&mmu->iommu); - - return 0; } static struct platform_driver grant_dma_iommu_driver = { diff --git a/drivers/xen/grant-dma-ops.c b/drivers/xen/grant-dma-ops.c index 76f6f26265a3..29257d2639db 100644 --- a/drivers/xen/grant-dma-ops.c +++ b/drivers/xen/grant-dma-ops.c @@ -282,7 +282,7 @@ static int xen_grant_dma_supported(struct device *dev, u64 mask) static const struct dma_map_ops xen_grant_dma_ops = { .alloc = xen_grant_dma_alloc, .free = xen_grant_dma_free, - .alloc_pages = xen_grant_dma_alloc_pages, + .alloc_pages_op = xen_grant_dma_alloc_pages, .free_pages = xen_grant_dma_free_pages, .mmap = dma_common_mmap, .get_sgtable = dma_common_get_sgtable, diff --git a/drivers/xen/manage.c b/drivers/xen/manage.c index c16df629907e..b4b4ebed68da 100644 --- a/drivers/xen/manage.c +++ b/drivers/xen/manage.c @@ -208,7 +208,7 @@ static void do_reboot(void) orderly_reboot(); } -static struct shutdown_handler shutdown_handlers[] = { +static const struct shutdown_handler shutdown_handlers[] = { { "poweroff", true, do_poweroff }, { "halt", false, do_poweroff }, { "reboot", true, do_reboot }, diff --git a/drivers/xen/mcelog.c b/drivers/xen/mcelog.c index e9ac3b8c4167..4f65b641c054 100644 --- a/drivers/xen/mcelog.c +++ b/drivers/xen/mcelog.c @@ -182,7 +182,6 @@ static const struct file_operations xen_mce_chrdev_ops = { .read = xen_mce_chrdev_read, .poll = xen_mce_chrdev_poll, .unlocked_ioctl = xen_mce_chrdev_ioctl, - .llseek = no_llseek, }; static struct miscdevice xen_mce_chrdev_device = { diff --git a/drivers/xen/pci.c b/drivers/xen/pci.c index 72d4e3f193af..bfe07adb3e3a 100644 --- a/drivers/xen/pci.c +++ b/drivers/xen/pci.c @@ -43,16 +43,24 @@ 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) { - struct { - struct physdev_pci_device_add add; - uint32_t pxm; - } add_ext = { - .add.seg = pci_domain_nr(pci_dev->bus), - .add.bus = pci_dev->bus->number, - .add.devfn = pci_dev->devfn - }; - struct physdev_pci_device_add *add = &add_ext.add; + DEFINE_RAW_FLEX(struct physdev_pci_device_add, add, optarr, 1); + + add->seg = pci_domain_nr(pci_dev->bus); + add->bus = pci_dev->bus->number; + add->devfn = pci_dev->devfn; #ifdef CONFIG_ACPI acpi_handle handle; @@ -153,6 +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), @@ -177,6 +195,29 @@ static int xen_remove_device(struct device *dev) return r; } +int xen_reset_device(const struct pci_dev *dev) +{ + struct pci_device_reset device = { + .dev.seg = pci_domain_nr(dev->bus), + .dev.bus = dev->bus->number, + .dev.devfn = dev->devfn, + .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); + static int xen_pci_notifier(struct notifier_block *nb, unsigned long action, void *data) { diff --git a/drivers/xen/pcpu.c b/drivers/xen/pcpu.c index 508655273145..093ad4a08672 100644 --- a/drivers/xen/pcpu.c +++ b/drivers/xen/pcpu.c @@ -65,7 +65,7 @@ struct pcpu { uint32_t flags; }; -static struct bus_type xen_pcpu_subsys = { +static const struct bus_type xen_pcpu_subsys = { .name = "xen_cpu", .dev_name = "xen_cpu", }; @@ -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-buf.c b/drivers/xen/privcmd-buf.c index 2fa10ca5be14..0f0dad427d7e 100644 --- a/drivers/xen/privcmd-buf.c +++ b/drivers/xen/privcmd-buf.c @@ -19,6 +19,7 @@ #include "privcmd.h" +MODULE_DESCRIPTION("Xen Mmap of hypercall buffers"); MODULE_LICENSE("GPL"); struct privcmd_buf_private { diff --git a/drivers/xen/privcmd.c b/drivers/xen/privcmd.c index 35b6e306026a..13a10f3294a8 100644 --- a/drivers/xen/privcmd.c +++ b/drivers/xen/privcmd.c @@ -17,6 +17,7 @@ #include <linux/poll.h> #include <linux/sched.h> #include <linux/slab.h> +#include <linux/srcu.h> #include <linux/string.h> #include <linux/workqueue.h> #include <linux/errno.h> @@ -45,9 +46,13 @@ #include <xen/page.h> #include <xen/xen-ops.h> #include <xen/balloon.h> +#ifdef CONFIG_XEN_ACPI +#include <xen/acpi.h> +#endif #include "privcmd.h" +MODULE_DESCRIPTION("Xen hypercall passthrough driver"); MODULE_LICENSE("GPL"); #define PRIV_VMA_LOCKED ((void *)1) @@ -842,10 +847,34 @@ out: return rc; } +static long privcmd_ioctl_pcidev_get_gsi(struct file *file, void __user *udata) +{ +#if defined(CONFIG_XEN_ACPI) + int rc; + struct privcmd_pcidev_get_gsi kdata; + + if (copy_from_user(&kdata, udata, sizeof(kdata))) + return -EFAULT; + + rc = xen_acpi_get_gsi_from_sbdf(kdata.sbdf); + if (rc < 0) + return rc; + + kdata.gsi = rc; + if (copy_to_user(udata, &kdata, sizeof(kdata))) + return -EFAULT; + + return 0; +#else + return -EINVAL; +#endif +} + #ifdef CONFIG_XEN_PRIVCMD_EVENTFD /* Irqfd support */ static struct workqueue_struct *irqfd_cleanup_wq; -static DEFINE_MUTEX(irqfds_lock); +static DEFINE_SPINLOCK(irqfds_lock); +DEFINE_STATIC_SRCU(irqfds_srcu); static LIST_HEAD(irqfds_list); struct privcmd_kernel_irqfd { @@ -873,6 +902,9 @@ static void irqfd_shutdown(struct work_struct *work) container_of(work, struct privcmd_kernel_irqfd, shutdown); u64 cnt; + /* Make sure irqfd has been initialized in assign path */ + synchronize_srcu(&irqfds_srcu); + eventfd_ctx_remove_wait_queue(kirqfd->eventfd, &kirqfd->wait, &cnt); eventfd_ctx_put(kirqfd->eventfd); kfree(kirqfd); @@ -909,9 +941,11 @@ irqfd_wakeup(wait_queue_entry_t *wait, unsigned int mode, int sync, void *key) irqfd_inject(kirqfd); if (flags & EPOLLHUP) { - mutex_lock(&irqfds_lock); + unsigned long flags; + + spin_lock_irqsave(&irqfds_lock, flags); irqfd_deactivate(kirqfd); - mutex_unlock(&irqfds_lock); + spin_unlock_irqrestore(&irqfds_lock, flags); } return 0; @@ -929,10 +963,12 @@ irqfd_poll_func(struct file *file, wait_queue_head_t *wqh, poll_table *pt) static int privcmd_irqfd_assign(struct privcmd_irqfd *irqfd) { struct privcmd_kernel_irqfd *kirqfd, *tmp; + unsigned long flags; __poll_t events; - struct fd f; void *dm_op; - int ret; + int ret, idx; + + CLASS(fd, f)(irqfd->fd); kirqfd = kzalloc(sizeof(*kirqfd) + irqfd->size, GFP_KERNEL); if (!kirqfd) @@ -949,16 +985,15 @@ static int privcmd_irqfd_assign(struct privcmd_irqfd *irqfd) kirqfd->dom = irqfd->dom; INIT_WORK(&kirqfd->shutdown, irqfd_shutdown); - f = fdget(irqfd->fd); - if (!f.file) { + if (fd_empty(f)) { ret = -EBADF; goto error_kfree; } - kirqfd->eventfd = eventfd_ctx_fileget(f.file); + kirqfd->eventfd = eventfd_ctx_fileget(fd_file(f)); if (IS_ERR(kirqfd->eventfd)) { ret = PTR_ERR(kirqfd->eventfd); - goto error_fd_put; + goto error_kfree; } /* @@ -968,40 +1003,34 @@ static int privcmd_irqfd_assign(struct privcmd_irqfd *irqfd) init_waitqueue_func_entry(&kirqfd->wait, irqfd_wakeup); init_poll_funcptr(&kirqfd->pt, irqfd_poll_func); - mutex_lock(&irqfds_lock); + spin_lock_irqsave(&irqfds_lock, flags); list_for_each_entry(tmp, &irqfds_list, list) { if (kirqfd->eventfd == tmp->eventfd) { ret = -EBUSY; - mutex_unlock(&irqfds_lock); + spin_unlock_irqrestore(&irqfds_lock, flags); goto error_eventfd; } } + idx = srcu_read_lock(&irqfds_srcu); list_add_tail(&kirqfd->list, &irqfds_list); - mutex_unlock(&irqfds_lock); + spin_unlock_irqrestore(&irqfds_lock, flags); /* * Check if there was an event already pending on the eventfd before we * registered, and trigger it as if we didn't miss it. */ - events = vfs_poll(f.file, &kirqfd->pt); + events = vfs_poll(fd_file(f), &kirqfd->pt); if (events & EPOLLIN) irqfd_inject(kirqfd); - /* - * Do not drop the file until the kirqfd is fully initialized, otherwise - * we might race against the EPOLLHUP. - */ - fdput(f); + srcu_read_unlock(&irqfds_srcu, idx); return 0; error_eventfd: eventfd_ctx_put(kirqfd->eventfd); -error_fd_put: - fdput(f); - error_kfree: kfree(kirqfd); return ret; @@ -1011,12 +1040,13 @@ static int privcmd_irqfd_deassign(struct privcmd_irqfd *irqfd) { struct privcmd_kernel_irqfd *kirqfd; struct eventfd_ctx *eventfd; + unsigned long flags; eventfd = eventfd_ctx_fdget(irqfd->fd); if (IS_ERR(eventfd)) return PTR_ERR(eventfd); - mutex_lock(&irqfds_lock); + spin_lock_irqsave(&irqfds_lock, flags); list_for_each_entry(kirqfd, &irqfds_list, list) { if (kirqfd->eventfd == eventfd) { @@ -1025,7 +1055,7 @@ static int privcmd_irqfd_deassign(struct privcmd_irqfd *irqfd) } } - mutex_unlock(&irqfds_lock); + spin_unlock_irqrestore(&irqfds_lock, flags); eventfd_ctx_put(eventfd); @@ -1073,13 +1103,14 @@ static int privcmd_irqfd_init(void) static void privcmd_irqfd_exit(void) { struct privcmd_kernel_irqfd *kirqfd, *tmp; + unsigned long flags; - mutex_lock(&irqfds_lock); + spin_lock_irqsave(&irqfds_lock, flags); list_for_each_entry_safe(kirqfd, tmp, &irqfds_list, list) irqfd_deactivate(kirqfd); - mutex_unlock(&irqfds_lock); + spin_unlock_irqrestore(&irqfds_lock, flags); destroy_workqueue(irqfd_cleanup_wq); } @@ -1223,18 +1254,13 @@ struct privcmd_kernel_ioreq *alloc_ioreq(struct privcmd_ioeventfd *ioeventfd) kioreq->ioreq = (struct ioreq *)(page_to_virt(pages[0])); mmap_write_unlock(mm); - size = sizeof(*ports) * kioreq->vcpus; - ports = kzalloc(size, GFP_KERNEL); - if (!ports) { - ret = -ENOMEM; + ports = memdup_array_user(u64_to_user_ptr(ioeventfd->ports), + kioreq->vcpus, sizeof(*ports)); + if (IS_ERR(ports)) { + ret = PTR_ERR(ports); goto error_kfree; } - if (copy_from_user(ports, u64_to_user_ptr(ioeventfd->ports), size)) { - ret = -EFAULT; - goto error_kfree_ports; - } - for (i = 0; i < kioreq->vcpus; i++) { kioreq->ports[i].vcpu = i; kioreq->ports[i].port = ports[i]; @@ -1256,7 +1282,7 @@ struct privcmd_kernel_ioreq *alloc_ioreq(struct privcmd_ioeventfd *ioeventfd) error_unbind: while (--i >= 0) unbind_from_irqhandler(irq_from_evtchn(ports[i]), &kioreq->ports[i]); -error_kfree_ports: + kfree(ports); error_kfree: kfree(kioreq); @@ -1315,7 +1341,6 @@ static int privcmd_ioeventfd_assign(struct privcmd_ioeventfd *ioeventfd) struct privcmd_kernel_ioeventfd *kioeventfd; struct privcmd_kernel_ioreq *kioreq; unsigned long flags; - struct fd f; int ret; /* Check for range overflow */ @@ -1335,15 +1360,7 @@ static int privcmd_ioeventfd_assign(struct privcmd_ioeventfd *ioeventfd) if (!kioeventfd) return -ENOMEM; - f = fdget(ioeventfd->event_fd); - if (!f.file) { - ret = -EBADF; - goto error_kfree; - } - - kioeventfd->eventfd = eventfd_ctx_fileget(f.file); - fdput(f); - + kioeventfd->eventfd = eventfd_ctx_fdget(ioeventfd->event_fd); if (IS_ERR(kioeventfd->eventfd)) { ret = PTR_ERR(kioeventfd->eventfd); goto error_kfree; @@ -1534,6 +1551,10 @@ static long privcmd_ioctl(struct file *file, ret = privcmd_ioctl_ioeventfd(file, udata); break; + case IOCTL_PRIVCMD_PCIDEV_GET_GSI: + ret = privcmd_ioctl_pcidev_get_gsi(file, udata); + break; + default: break; } diff --git a/drivers/xen/pvcalls-back.c b/drivers/xen/pvcalls-back.c index d52593466a79..fd7ed65e0197 100644 --- a/drivers/xen/pvcalls-back.c +++ b/drivers/xen/pvcalls-back.c @@ -517,6 +517,10 @@ static void __pvcalls_back_accept(struct work_struct *work) { struct sockpass_mapping *mappass = container_of( work, struct sockpass_mapping, register_work); + struct proto_accept_arg arg = { + .flags = O_NONBLOCK, + .kern = true, + }; struct sock_mapping *map; struct pvcalls_ioworker *iow; struct pvcalls_fedata *fedata; @@ -548,7 +552,7 @@ static void __pvcalls_back_accept(struct work_struct *work) sock->type = mappass->sock->type; sock->ops = mappass->sock->ops; - ret = inet_accept(mappass->sock, sock, O_NONBLOCK, true); + ret = inet_accept(mappass->sock, sock, &arg); if (ret == -EAGAIN) { sock_release(sock); return; 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 0e6c6c25d154..da1a7d3d377c 100644 --- a/drivers/xen/swiotlb-xen.c +++ b/drivers/xen/swiotlb-xen.c @@ -74,6 +74,14 @@ 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); @@ -88,7 +96,8 @@ static inline int range_straddles_page_boundary(phys_addr_t p, size_t size) return 0; } -static int is_xen_swiotlb_buffer(struct device *dev, dma_addr_t dma_addr) +static struct io_tlb_pool *xen_swiotlb_find_pool(struct device *dev, + dma_addr_t dma_addr) { unsigned long bfn = XEN_PFN_DOWN(dma_to_phys(dev, dma_addr)); unsigned long xen_pfn = bfn_to_local_pfn(bfn); @@ -99,12 +108,12 @@ static int is_xen_swiotlb_buffer(struct device *dev, dma_addr_t dma_addr) * in our domain. Therefore _only_ check address within our domain. */ if (pfn_valid(PFN_DOWN(paddr))) - return is_swiotlb_buffer(dev, paddr); - return 0; + return swiotlb_find_pool(dev, paddr); + return NULL; } #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); @@ -140,7 +149,7 @@ xen_swiotlb_alloc_coherent(struct device *dev, size_t size, void *ret; /* Align the allocation to the Xen page size */ - size = 1UL << (order + XEN_PAGE_SHIFT); + size = ALIGN(size, XEN_PAGE_SIZE); ret = (void *)__get_free_pages(flags, get_order(size)); if (!ret) @@ -149,7 +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; @@ -172,10 +182,11 @@ xen_swiotlb_free_coherent(struct device *dev, size_t size, void *vaddr, int order = get_order(size); /* Convert the size to actually allocated. */ - size = 1UL << (order + XEN_PAGE_SHIFT); + 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))) @@ -206,6 +217,7 @@ static dma_addr_t xen_swiotlb_map_page(struct device *dev, struct page *page, * 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)) @@ -216,7 +228,7 @@ static dma_addr_t xen_swiotlb_map_page(struct device *dev, struct page *page, */ trace_swiotlb_bounced(dev, dev_addr, size); - map = swiotlb_tbl_map_single(dev, phys, size, size, 0, dir, attrs); + map = swiotlb_tbl_map_single(dev, phys, size, 0, dir, attrs); if (map == (phys_addr_t)DMA_MAPPING_ERROR) return DMA_MAPPING_ERROR; @@ -227,8 +239,9 @@ static dma_addr_t xen_swiotlb_map_page(struct device *dev, struct page *page, * Ensure that the address returned is DMA'ble */ if (unlikely(!dma_capable(dev, dev_addr, size, true))) { - swiotlb_tbl_unmap_single(dev, map, size, dir, - attrs | DMA_ATTR_SKIP_CPU_SYNC); + __swiotlb_tbl_unmap_single(dev, map, size, dir, + attrs | DMA_ATTR_SKIP_CPU_SYNC, + swiotlb_find_pool(dev, map)); return DMA_MAPPING_ERROR; } @@ -254,6 +267,7 @@ static void xen_swiotlb_unmap_page(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); + struct io_tlb_pool *pool; BUG_ON(dir == DMA_NONE); @@ -265,8 +279,10 @@ static void xen_swiotlb_unmap_page(struct device *hwdev, dma_addr_t dev_addr, } /* NOTE: We use dev_addr here, not paddr! */ - if (is_xen_swiotlb_buffer(hwdev, dev_addr)) - swiotlb_tbl_unmap_single(hwdev, paddr, size, dir, attrs); + pool = xen_swiotlb_find_pool(hwdev, dev_addr); + if (pool) + __swiotlb_tbl_unmap_single(hwdev, paddr, size, dir, + attrs, pool); } static void @@ -274,6 +290,7 @@ xen_swiotlb_sync_single_for_cpu(struct device *dev, dma_addr_t dma_addr, size_t size, enum dma_data_direction dir) { phys_addr_t paddr = xen_dma_to_phys(dev, dma_addr); + struct io_tlb_pool *pool; if (!dev_is_dma_coherent(dev)) { if (pfn_valid(PFN_DOWN(dma_to_phys(dev, dma_addr)))) @@ -282,8 +299,9 @@ xen_swiotlb_sync_single_for_cpu(struct device *dev, dma_addr_t dma_addr, xen_dma_sync_for_cpu(dev, dma_addr, size, dir); } - if (is_xen_swiotlb_buffer(dev, dma_addr)) - swiotlb_sync_single_for_cpu(dev, paddr, size, dir); + pool = xen_swiotlb_find_pool(dev, dma_addr); + if (pool) + __swiotlb_sync_single_for_cpu(dev, paddr, size, dir, pool); } static void @@ -291,9 +309,11 @@ xen_swiotlb_sync_single_for_device(struct device *dev, dma_addr_t dma_addr, size_t size, enum dma_data_direction dir) { phys_addr_t paddr = xen_dma_to_phys(dev, dma_addr); + struct io_tlb_pool *pool; - if (is_xen_swiotlb_buffer(dev, dma_addr)) - swiotlb_sync_single_for_device(dev, paddr, size, dir); + pool = xen_swiotlb_find_pool(dev, dma_addr); + if (pool) + __swiotlb_sync_single_for_device(dev, paddr, size, dir, pool); if (!dev_is_dma_coherent(dev)) { if (pfn_valid(PFN_DOWN(dma_to_phys(dev, dma_addr)))) @@ -403,7 +423,8 @@ const struct dma_map_ops xen_swiotlb_dma_ops = { .dma_supported = xen_swiotlb_dma_supported, .mmap = dma_common_mmap, .get_sgtable = dma_common_get_sgtable, - .alloc_pages = dma_common_alloc_pages, + .alloc_pages_op = dma_common_alloc_pages, .free_pages = dma_common_free_pages, .max_mapping_size = swiotlb_max_mapping_size, + .map_resource = dma_direct_map_resource, }; diff --git a/drivers/xen/xen-balloon.c b/drivers/xen/xen-balloon.c index 8cd583db20b1..b293d7652f15 100644 --- a/drivers/xen/xen-balloon.c +++ b/drivers/xen/xen-balloon.c @@ -237,7 +237,7 @@ static const struct attribute_group *balloon_groups[] = { NULL }; -static struct bus_type balloon_subsys = { +static const struct bus_type balloon_subsys = { .name = BALLOON_CLASS_NAME, .dev_name = BALLOON_CLASS_NAME, }; diff --git a/drivers/xen/xen-pciback/conf_space_capability.c b/drivers/xen/xen-pciback/conf_space_capability.c index 1948a9700c8f..cf568e899ee2 100644 --- a/drivers/xen/xen-pciback/conf_space_capability.c +++ b/drivers/xen/xen-pciback/conf_space_capability.c @@ -122,7 +122,7 @@ static int pm_ctrl_write(struct pci_dev *dev, int offset, u16 new_value, if (err) goto out; - new_state = (pci_power_t)(new_value & PCI_PM_CTRL_STATE_MASK); + new_state = (__force pci_power_t)(new_value & PCI_PM_CTRL_STATE_MASK); new_value &= PM_OK_BITS; if ((old_value & PM_OK_BITS) != new_value) { diff --git a/drivers/xen/xen-pciback/pci_stub.c b/drivers/xen/xen-pciback/pci_stub.c index e34b623e4b41..5c2f829d5b0b 100644 --- a/drivers/xen/xen-pciback/pci_stub.c +++ b/drivers/xen/xen-pciback/pci_stub.c @@ -21,6 +21,9 @@ #include <xen/events.h> #include <xen/pci.h> #include <xen/xen.h> +#ifdef CONFIG_XEN_ACPI +#include <xen/acpi.h> +#endif #include <asm/xen/hypervisor.h> #include <xen/interface/physdev.h> #include "pciback.h" @@ -53,6 +56,9 @@ struct pcistub_device { struct pci_dev *dev; struct xen_pcibk_device *pdev;/* non-NULL if struct pci_dev is in use */ +#ifdef CONFIG_XEN_ACPI + int gsi; +#endif }; /* Access to pcistub_devices & seized_devices lists and the initialize_devices @@ -85,10 +91,23 @@ static struct pcistub_device *pcistub_device_alloc(struct pci_dev *dev) kref_init(&psdev->kref); spin_lock_init(&psdev->lock); +#ifdef CONFIG_XEN_ACPI + psdev->gsi = -1; +#endif return psdev; } +static int pcistub_reset_device_state(struct pci_dev *dev) +{ + __pci_reset_function_locked(dev); + + if (!xen_pv_domain()) + return xen_reset_device(dev); + else + return 0; +} + /* Don't call this directly as it's called by pcistub_device_put */ static void pcistub_device_release(struct kref *kref) { @@ -107,7 +126,7 @@ static void pcistub_device_release(struct kref *kref) /* Call the reset function which does not take lock as this * is called from "unbind" which takes a device_lock mutex. */ - __pci_reset_function_locked(dev); + pcistub_reset_device_state(dev); if (dev_data && pci_load_and_free_saved_state(dev, &dev_data->pci_saved_state)) dev_info(&dev->dev, "Could not reload PCI state\n"); @@ -207,26 +226,27 @@ static struct pci_dev *pcistub_device_get_pci_dev(struct xen_pcibk_device *pdev, return pci_dev; } -struct pci_dev *pcistub_get_pci_dev_by_slot(struct xen_pcibk_device *pdev, - int domain, int bus, - int slot, int func) +#ifdef CONFIG_XEN_ACPI +static int pcistub_get_gsi_from_sbdf(unsigned int sbdf) { struct pcistub_device *psdev; - struct pci_dev *found_dev = NULL; - unsigned long flags; + int domain = (sbdf >> 16) & 0xffff; + int bus = PCI_BUS_NUM(sbdf); + int slot = PCI_SLOT(sbdf); + int func = PCI_FUNC(sbdf); - spin_lock_irqsave(&pcistub_devices_lock, flags); + psdev = pcistub_device_find(domain, bus, slot, func); - psdev = pcistub_device_find_locked(domain, bus, slot, func); - if (psdev) - found_dev = pcistub_device_get_pci_dev(pdev, psdev); + if (!psdev) + return -ENODEV; - spin_unlock_irqrestore(&pcistub_devices_lock, flags); - return found_dev; + return psdev->gsi; } +#endif -struct pci_dev *pcistub_get_pci_dev(struct xen_pcibk_device *pdev, - struct pci_dev *dev) +struct pci_dev *pcistub_get_pci_dev_by_slot(struct xen_pcibk_device *pdev, + int domain, int bus, + int slot, int func) { struct pcistub_device *psdev; struct pci_dev *found_dev = NULL; @@ -234,12 +254,9 @@ struct pci_dev *pcistub_get_pci_dev(struct xen_pcibk_device *pdev, 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; - } - } + psdev = pcistub_device_find_locked(domain, bus, slot, func); + if (psdev) + found_dev = pcistub_device_get_pci_dev(pdev, psdev); spin_unlock_irqrestore(&pcistub_devices_lock, flags); return found_dev; @@ -284,7 +301,7 @@ void pcistub_put_pci_dev(struct pci_dev *dev) * (so it's ready for the next domain) */ device_lock_assert(&dev->dev); - __pci_reset_function_locked(dev); + pcistub_reset_device_state(dev); dev_data = pci_get_drvdata(dev); ret = pci_load_saved_state(dev, dev_data->pci_saved_state); @@ -354,11 +371,20 @@ static int pcistub_match(struct pci_dev *dev) return found; } -static int pcistub_init_device(struct pci_dev *dev) +static int pcistub_init_device(struct pcistub_device *psdev) { struct xen_pcibk_dev_data *dev_data; + struct pci_dev *dev; +#ifdef CONFIG_XEN_ACPI + int gsi, trigger, polarity; +#endif int err = 0; + if (!psdev) + return -EINVAL; + + dev = psdev->dev; + dev_dbg(&dev->dev, "initializing...\n"); /* The PCI backend is not intended to be a module (or to work with @@ -420,9 +446,26 @@ static int pcistub_init_device(struct pci_dev *dev) dev_err(&dev->dev, "Could not store PCI conf saved state!\n"); else { dev_dbg(&dev->dev, "resetting (FLR, D3, etc) the device\n"); - __pci_reset_function_locked(dev); + err = pcistub_reset_device_state(dev); + if (err) + goto config_release; pci_restore_state(dev); } + +#ifdef CONFIG_XEN_ACPI + if (xen_initial_domain() && xen_pvh_domain()) { + err = xen_acpi_get_gsi_info(dev, &gsi, &trigger, &polarity); + if (err) { + dev_err(&dev->dev, "Fail to get gsi info!\n"); + goto config_release; + } + err = xen_pvh_setup_gsi(gsi, trigger, polarity); + if (err) + goto config_release; + psdev->gsi = gsi; + } +#endif + /* Now disable the device (this also ensures some private device * data is setup before we export) */ @@ -462,7 +505,7 @@ static int __init pcistub_init_devices_late(void) spin_unlock_irqrestore(&pcistub_devices_lock, flags); - err = pcistub_init_device(psdev->dev); + err = pcistub_init_device(psdev); if (err) { dev_err(&psdev->dev->dev, "error %d initializing device\n", err); @@ -532,7 +575,7 @@ static int pcistub_seize(struct pci_dev *dev, spin_unlock_irqrestore(&pcistub_devices_lock, flags); /* don't want irqs disabled when calling pcistub_init_device */ - err = pcistub_init_device(psdev->dev); + err = pcistub_init_device(psdev); spin_lock_irqsave(&pcistub_devices_lock, flags); @@ -757,7 +800,7 @@ static pci_ers_result_t common_process(struct pcistub_device *psdev, } clear_bit(_PCIB_op_pending, (unsigned long *)&pdev->flags); - res = (pci_ers_result_t)aer_op->err; + res = (__force pci_ers_result_t)aer_op->err; return res; } @@ -1693,11 +1736,19 @@ static int __init xen_pcibk_init(void) bus_register_notifier(&pci_bus_type, &pci_stub_nb); #endif +#ifdef CONFIG_XEN_ACPI + xen_acpi_register_get_gsi_func(pcistub_get_gsi_from_sbdf); +#endif + return err; } static void __exit xen_pcibk_cleanup(void) { +#ifdef CONFIG_XEN_ACPI + xen_acpi_register_get_gsi_func(NULL); +#endif + #ifdef CONFIG_PCI_IOV bus_unregister_notifier(&pci_bus_type, &pci_stub_nb); #endif @@ -1708,5 +1759,6 @@ static void __exit xen_pcibk_cleanup(void) module_init(xen_pcibk_init); module_exit(xen_pcibk_cleanup); +MODULE_DESCRIPTION("Xen PCI-device stub driver"); MODULE_LICENSE("Dual BSD/GPL"); MODULE_ALIAS("xen-backend:pci"); 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/Makefile b/drivers/xen/xenbus/Makefile index 0c7532110815..b0d69602214e 100644 --- a/drivers/xen/xenbus/Makefile +++ b/drivers/xen/xenbus/Makefile @@ -1,15 +1,13 @@ # SPDX-License-Identifier: GPL-2.0 obj-y += xenbus.o -obj-y += xenbus_dev_frontend.o -xenbus-objs = -xenbus-objs += xenbus_client.o -xenbus-objs += xenbus_comms.o -xenbus-objs += xenbus_xs.o -xenbus-objs += xenbus_probe.o +xenbus-y := xenbus_client.o +xenbus-y += xenbus_comms.o +xenbus-y += xenbus_xs.o +xenbus-y += xenbus_probe.o -xenbus-be-objs-$(CONFIG_XEN_BACKEND) += xenbus_probe_backend.o -xenbus-objs += $(xenbus-be-objs-y) +xenbus-$(CONFIG_XEN_BACKEND) += xenbus_probe_backend.o +obj-y += xenbus_dev_frontend.o obj-$(CONFIG_XEN_BACKEND) += xenbus_dev_backend.o obj-$(CONFIG_XEN_XENBUS_FRONTEND) += xenbus_probe_frontend.o diff --git a/drivers/xen/xenbus/xenbus.h b/drivers/xen/xenbus/xenbus.h index 2754bdfadcb8..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; @@ -103,8 +104,9 @@ 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, struct device_driver *_drv); +int xenbus_match(struct device *_dev, const struct device_driver *_drv); int xenbus_dev_probe(struct device *_dev); void xenbus_dev_remove(struct device *_dev); int xenbus_register_driver_common(struct xenbus_driver *drv, diff --git a/drivers/xen/xenbus/xenbus_client.c b/drivers/xen/xenbus/xenbus_client.c index 32835b4b9bc5..51b3124b0d56 100644 --- a/drivers/xen/xenbus/xenbus_client.c +++ b/drivers/xen/xenbus/xenbus_client.c @@ -116,14 +116,15 @@ EXPORT_SYMBOL_GPL(xenbus_strstate); * @dev: xenbus device * @path: path to watch * @watch: watch to register + * @will_handle: events queuing determine callback * @callback: callback to register * * Register a @watch on the given path, using the given xenbus_watch structure - * for storage, and the given @callback function as the callback. On success, - * the given @path will be saved as @watch->node, and remains the - * caller's to free. On error, @watch->node will - * be NULL, the device will switch to %XenbusStateClosing, and the error will - * be saved in the store. + * for storage, @will_handle function as the callback to determine if each + * event need to be queued, and the given @callback function as the callback. + * On success, the given @path will be saved as @watch->node, and remains the + * caller's to free. On error, @watch->node will be NULL, the device will + * switch to %XenbusStateClosing, and the error will be saved in the store. * * Returns: %0 on success or -errno on error */ @@ -158,11 +159,13 @@ EXPORT_SYMBOL_GPL(xenbus_watch_path); * xenbus_watch_pathfmt - register a watch on a sprintf-formatted path * @dev: xenbus device * @watch: watch to register + * @will_handle: events queuing determine callback * @callback: callback to register * @pathfmt: format of path to watch * * Register a watch on the given @path, using the given xenbus_watch - * structure for storage, and the given @callback function as the + * structure for storage, @will_handle function as the callback to determine if + * each event need to be queued, and the given @callback function as the * callback. On success, the watched path (@path/@path2) will be saved * as @watch->node, and becomes the caller's to kfree(). * On error, watch->node will be NULL, so the caller has nothing to 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 6f56640092a9..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); @@ -700,7 +700,6 @@ const struct file_operations xen_xenbus_fops = { .open = xenbus_file_open, .release = xenbus_file_release, .poll = xenbus_file_poll, - .llseek = no_llseek, }; EXPORT_SYMBOL_GPL(xen_xenbus_fops); diff --git a/drivers/xen/xenbus/xenbus_probe.c b/drivers/xen/xenbus/xenbus_probe.c index 3205e5d724c8..86fe6e779056 100644 --- a/drivers/xen/xenbus/xenbus_probe.c +++ b/drivers/xen/xenbus/xenbus_probe.c @@ -65,13 +65,17 @@ #include "xenbus.h" -static int xs_init_irq; +static int xs_init_irq = -1; int xen_store_evtchn; EXPORT_SYMBOL_GPL(xen_store_evtchn); struct xenstore_domain_interface *xen_store_interface; EXPORT_SYMBOL_GPL(xen_store_interface); +#define XS_INTERFACE_READY \ + ((xen_store_interface != NULL) && \ + (xen_store_interface->connection == XENSTORE_CONNECTED)) + enum xenstore_init xen_store_domain_type; EXPORT_SYMBOL_GPL(xen_store_domain_type); @@ -90,9 +94,9 @@ match_device(const struct xenbus_device_id *arr, struct xenbus_device *dev) return NULL; } -int xenbus_match(struct device *_dev, struct device_driver *_drv) +int xenbus_match(struct device *_dev, const struct device_driver *_drv) { - struct xenbus_driver *drv = to_xenbus_driver(_drv); + const struct xenbus_driver *drv = to_xenbus_driver(_drv); if (!drv->ids) return 0; @@ -309,7 +313,7 @@ int xenbus_dev_probe(struct device *_dev) if (err) { dev_warn(&dev->dev, "watch_otherend on %s failed.\n", dev->nodename); - return err; + goto fail_remove; } dev->spurious_threshold = 1; @@ -318,6 +322,12 @@ int xenbus_dev_probe(struct device *_dev) dev->nodename); return 0; +fail_remove: + if (drv->remove) { + down(&dev->reclaim_sem); + drv->remove(dev); + up(&dev->reclaim_sem); + } fail_put: module_put(drv->driver.owner); fail: @@ -751,19 +761,19 @@ static void xenbus_probe(void) { xenstored_ready = 1; - if (!xen_store_interface) { + if (!xen_store_interface) xen_store_interface = memremap(xen_store_gfn << XEN_PAGE_SHIFT, XEN_PAGE_SIZE, MEMREMAP_WB); - /* - * Now it is safe to free the IRQ used for xenstore late - * initialization. No need to unbind: it is about to be - * bound again from xb_init_comms. Note that calling - * unbind_from_irqhandler now would result in xen_evtchn_close() - * being called and the event channel not being enabled again - * afterwards, resulting in missed event notifications. - */ + /* + * Now it is safe to free the IRQ used for xenstore late + * initialization. No need to unbind: it is about to be + * bound again from xb_init_comms. Note that calling + * unbind_from_irqhandler now would result in xen_evtchn_close() + * being called and the event channel not being enabled again + * afterwards, resulting in missed event notifications. + */ + if (xs_init_irq >= 0) free_irq(xs_init_irq, &xb_waitq); - } /* * In the HVM case, xenbus_init() deferred its call to @@ -822,7 +832,7 @@ static int __init xenbus_probe_initcall(void) if (xen_store_domain_type == XS_PV || (xen_store_domain_type == XS_HVM && !xs_hvm_defer_init_for_callback() && - xen_store_interface != NULL)) + XS_INTERFACE_READY)) xenbus_probe(); /* @@ -831,7 +841,7 @@ static int __init xenbus_probe_initcall(void) * started, then probe. It will be triggered when communication * starts happening, by waiting on xb_waitq. */ - if (xen_store_domain_type == XS_LOCAL || xen_store_interface == NULL) { + if (xen_store_domain_type == XS_LOCAL || !XS_INTERFACE_READY) { struct task_struct *probe_task; probe_task = kthread_run(xenbus_probe_thread, NULL, @@ -956,9 +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) @@ -977,10 +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; @@ -1014,6 +1026,12 @@ static int __init xenbus_init(void) xen_store_interface = memremap(xen_store_gfn << XEN_PAGE_SHIFT, XEN_PAGE_SIZE, MEMREMAP_WB); + if (!xen_store_interface) { + pr_err("%s: cannot map HVM_PARAM_STORE_PFN=%llx\n", + __func__, v); + err = -EINVAL; + goto out_error; + } if (xen_store_interface->connection != XENSTORE_CONNECTED) wait = true; } 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 028a182bcc9e..dcf9182c8451 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; @@ -427,12 +441,12 @@ char **xenbus_directory(struct xenbus_transaction t, path = join(dir, node); if (IS_ERR(path)) - return (char **)path; + return ERR_CAST(path); strings = xs_single(t, XS_DIRECTORY, path, &len); kfree(path); if (IS_ERR(strings)) - return (char **)strings; + return ERR_CAST(strings); return split(strings, len, num); } @@ -465,7 +479,7 @@ void *xenbus_read(struct xenbus_transaction t, path = join(dir, node); if (IS_ERR(path)) - return (void *)path; + return ERR_CAST(path); ret = xs_single(t, XS_READ, path, len); kfree(path); 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; |