diff options
-rw-r--r-- | Documentation/ABI/testing/sysfs-driver-pciback | 26 | ||||
-rw-r--r-- | Documentation/kernel-parameters.txt | 4 | ||||
-rw-r--r-- | MAINTAINERS | 7 | ||||
-rw-r--r-- | arch/arm/xen/grant-table.c | 6 | ||||
-rw-r--r-- | arch/x86/xen/enlighten.c | 13 | ||||
-rw-r--r-- | arch/x86/xen/grant-table.c | 106 | ||||
-rw-r--r-- | drivers/xen/grant-table.c | 314 | ||||
-rw-r--r-- | drivers/xen/xen-pciback/passthrough.c | 14 | ||||
-rw-r--r-- | drivers/xen/xen-pciback/pci_stub.c | 42 | ||||
-rw-r--r-- | drivers/xen/xen-pciback/pciback.h | 7 | ||||
-rw-r--r-- | drivers/xen/xen-pciback/vpci.c | 14 | ||||
-rw-r--r-- | drivers/xen/xen-pciback/xenbus.c | 4 | ||||
-rw-r--r-- | include/linux/device.h | 5 | ||||
-rw-r--r-- | include/xen/grant_table.h | 29 |
14 files changed, 166 insertions, 425 deletions
diff --git a/Documentation/ABI/testing/sysfs-driver-pciback b/Documentation/ABI/testing/sysfs-driver-pciback new file mode 100644 index 000000000000..8440aa721951 --- /dev/null +++ b/Documentation/ABI/testing/sysfs-driver-pciback @@ -0,0 +1,26 @@ +What: /sys/bus/pci/drivers/pciback/quirks +Date: Oct 2011 +KernelVersion: 3.1 +Contact: xen-devel@lists.xenproject.org +Description: + If the permissive attribute is set, then writing a string in + the format of DDDD:BB:DD.F-REG:SIZE:MASK will allow the guest + to write and read from the PCI device. That is Domain:Bus: + Device.Function-Register:Size:Mask (Domain is optional). + For example: + #echo 00:19.0-E0:2:FF > /sys/bus/pci/drivers/pciback/quirks + will allow the guest to read and write to the configuration + register 0x0E. + +What: /sys/bus/pci/drivers/pciback/irq_handlers +Date: Oct 2011 +KernelVersion: 3.1 +Contact: xen-devel@lists.xenproject.org +Description: + A list of all of the PCI devices owned by Xen PCI back and + whether Xen PCI backend will acknowledge the interrupts received + and the amount of interrupts received. Xen PCI back acknowledges + said interrupts only when they are level, shared with another + guest, whether it will acknowledge interrupts, and enabled by + the guest. + diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 04de29c341b9..bdbecac35b52 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -3747,6 +3747,10 @@ bytes respectively. Such letter suffixes can also be entirely omitted. Disables the ticketlock slowpath using Xen PV optimizations. + xen_nopv [X86] + Disables the PV optimizations forcing the HVM guest to + run as generic HVM guest with no PV drivers. + xirc2ps_cs= [NET,PCMCIA] Format: <irq>,<irq_mask>,<io>,<full_duplex>,<do_sound>,<lockup_hack>[,<irq2>[,<irq3>[,<irq4>]]] diff --git a/MAINTAINERS b/MAINTAINERS index 7582e75a776e..15fdd27b4fc3 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -10077,6 +10077,13 @@ S: Supported F: arch/x86/pci/*xen* F: drivers/pci/*xen* +XEN BLOCK SUBSYSTEM +M: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> +L: xen-devel@lists.xenproject.org (moderated for non-subscribers) +S: Supported +F: drivers/block/xen-blkback/* +F: drivers/block/xen* + XEN SWIOTLB SUBSYSTEM M: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> L: xen-devel@lists.xenproject.org (moderated for non-subscribers) diff --git a/arch/arm/xen/grant-table.c b/arch/arm/xen/grant-table.c index 859a9bb002d5..e43791829ace 100644 --- a/arch/arm/xen/grant-table.c +++ b/arch/arm/xen/grant-table.c @@ -45,9 +45,7 @@ void arch_gnttab_unmap(void *shared, unsigned long nr_gframes) return; } -int arch_gnttab_map_status(uint64_t *frames, unsigned long nr_gframes, - unsigned long max_nr_gframes, - grant_status_t **__shared) +int arch_gnttab_init(unsigned long nr_shared) { - return -ENOSYS; + return 0; } diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index ffb101e45731..eb822391b84c 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -1826,8 +1826,19 @@ static void __init xen_hvm_guest_init(void) xen_hvm_init_mmu_ops(); } +static bool xen_nopv = false; +static __init int xen_parse_nopv(char *arg) +{ + xen_nopv = true; + return 0; +} +early_param("xen_nopv", xen_parse_nopv); + static uint32_t __init xen_hvm_platform(void) { + if (xen_nopv) + return 0; + if (xen_pv_domain()) return 0; @@ -1836,6 +1847,8 @@ static uint32_t __init xen_hvm_platform(void) bool xen_hvm_need_lapic(void) { + if (xen_nopv) + return false; if (xen_pv_domain()) return false; if (!xen_hvm_domain()) diff --git a/arch/x86/xen/grant-table.c b/arch/x86/xen/grant-table.c index c98583588580..c0413046483a 100644 --- a/arch/x86/xen/grant-table.c +++ b/arch/x86/xen/grant-table.c @@ -36,99 +36,83 @@ #include <linux/sched.h> #include <linux/mm.h> +#include <linux/slab.h> #include <linux/vmalloc.h> #include <xen/interface/xen.h> #include <xen/page.h> #include <xen/grant_table.h> +#include <xen/xen.h> #include <asm/pgtable.h> -static int map_pte_fn(pte_t *pte, struct page *pmd_page, - unsigned long addr, void *data) +static struct gnttab_vm_area { + struct vm_struct *area; + pte_t **ptes; +} gnttab_shared_vm_area; + +int arch_gnttab_map_shared(unsigned long *frames, unsigned long nr_gframes, + unsigned long max_nr_gframes, + void **__shared) { - unsigned long **frames = (unsigned long **)data; + void *shared = *__shared; + unsigned long addr; + unsigned long i; - set_pte_at(&init_mm, addr, pte, mfn_pte((*frames)[0], PAGE_KERNEL)); - (*frames)++; - return 0; -} + if (shared == NULL) + *__shared = shared = gnttab_shared_vm_area.area->addr; -/* - * This function is used to map shared frames to store grant status. It is - * different from map_pte_fn above, the frames type here is uint64_t. - */ -static int map_pte_fn_status(pte_t *pte, struct page *pmd_page, - unsigned long addr, void *data) -{ - uint64_t **frames = (uint64_t **)data; + addr = (unsigned long)shared; + + for (i = 0; i < nr_gframes; i++) { + set_pte_at(&init_mm, addr, gnttab_shared_vm_area.ptes[i], + mfn_pte(frames[i], PAGE_KERNEL)); + addr += PAGE_SIZE; + } - set_pte_at(&init_mm, addr, pte, mfn_pte((*frames)[0], PAGE_KERNEL)); - (*frames)++; return 0; } -static int unmap_pte_fn(pte_t *pte, struct page *pmd_page, - unsigned long addr, void *data) +void arch_gnttab_unmap(void *shared, unsigned long nr_gframes) { + unsigned long addr; + unsigned long i; - set_pte_at(&init_mm, addr, pte, __pte(0)); - return 0; + addr = (unsigned long)shared; + + for (i = 0; i < nr_gframes; i++) { + set_pte_at(&init_mm, addr, gnttab_shared_vm_area.ptes[i], + __pte(0)); + addr += PAGE_SIZE; + } } -int arch_gnttab_map_shared(unsigned long *frames, unsigned long nr_gframes, - unsigned long max_nr_gframes, - void **__shared) +static int arch_gnttab_valloc(struct gnttab_vm_area *area, unsigned nr_frames) { - int rc; - void *shared = *__shared; + area->ptes = kmalloc(sizeof(pte_t *) * nr_frames, GFP_KERNEL); + if (area->ptes == NULL) + return -ENOMEM; - if (shared == NULL) { - struct vm_struct *area = - alloc_vm_area(PAGE_SIZE * max_nr_gframes, NULL); - BUG_ON(area == NULL); - shared = area->addr; - *__shared = shared; + area->area = alloc_vm_area(PAGE_SIZE * nr_frames, area->ptes); + if (area->area == NULL) { + kfree(area->ptes); + return -ENOMEM; } - rc = apply_to_page_range(&init_mm, (unsigned long)shared, - PAGE_SIZE * nr_gframes, - map_pte_fn, &frames); - return rc; + return 0; } -int arch_gnttab_map_status(uint64_t *frames, unsigned long nr_gframes, - unsigned long max_nr_gframes, - grant_status_t **__shared) +int arch_gnttab_init(unsigned long nr_shared) { - int rc; - grant_status_t *shared = *__shared; - - if (shared == NULL) { - /* No need to pass in PTE as we are going to do it - * in apply_to_page_range anyhow. */ - struct vm_struct *area = - alloc_vm_area(PAGE_SIZE * max_nr_gframes, NULL); - BUG_ON(area == NULL); - shared = area->addr; - *__shared = shared; - } + if (!xen_pv_domain()) + return 0; - rc = apply_to_page_range(&init_mm, (unsigned long)shared, - PAGE_SIZE * nr_gframes, - map_pte_fn_status, &frames); - return rc; + return arch_gnttab_valloc(&gnttab_shared_vm_area, nr_shared); } -void arch_gnttab_unmap(void *shared, unsigned long nr_gframes) -{ - apply_to_page_range(&init_mm, (unsigned long)shared, - PAGE_SIZE * nr_gframes, unmap_pte_fn, NULL); -} #ifdef CONFIG_XEN_PVH #include <xen/balloon.h> #include <xen/events.h> -#include <xen/xen.h> #include <linux/slab.h> static int __init xlated_setup_gnttab_pages(void) { diff --git a/drivers/xen/grant-table.c b/drivers/xen/grant-table.c index 5d4de88fe5b8..c254ae036f18 100644 --- a/drivers/xen/grant-table.c +++ b/drivers/xen/grant-table.c @@ -69,7 +69,6 @@ struct grant_frames xen_auto_xlat_grant_frames; static union { struct grant_entry_v1 *v1; - union grant_entry_v2 *v2; void *addr; } gnttab_shared; @@ -120,36 +119,10 @@ struct gnttab_ops { * by bit operations. */ int (*query_foreign_access)(grant_ref_t ref); - /* - * Grant a domain to access a range of bytes within the page referred by - * an available grant entry. Ref parameter is reference of a grant entry - * which will be sub-page accessed, domid is id of grantee domain, frame - * is frame address of subpage grant, flags is grant type and flag - * information, page_off is offset of the range of bytes, and length is - * length of bytes to be accessed. - */ - void (*update_subpage_entry)(grant_ref_t ref, domid_t domid, - unsigned long frame, int flags, - unsigned page_off, unsigned length); - /* - * Redirect an available grant entry on domain A to another grant - * reference of domain B, then allow domain C to use grant reference - * of domain B transitively. Ref parameter is an available grant entry - * reference on domain A, domid is id of domain C which accesses grant - * entry transitively, flags is grant type and flag information, - * trans_domid is id of domain B whose grant entry is finally accessed - * transitively, trans_gref is grant entry transitive reference of - * domain B. - */ - void (*update_trans_entry)(grant_ref_t ref, domid_t domid, int flags, - domid_t trans_domid, grant_ref_t trans_gref); }; static struct gnttab_ops *gnttab_interface; -/*This reflects status of grant entries, so act as a global value*/ -static grant_status_t *grstatus; - static int grant_table_version; static int grefs_per_grant_frame; @@ -231,7 +204,7 @@ static void put_free_entry(grant_ref_t ref) } /* - * Following applies to gnttab_update_entry_v1 and gnttab_update_entry_v2. + * Following applies to gnttab_update_entry_v1. * Introducing a valid entry into the grant table: * 1. Write ent->domid. * 2. Write ent->frame: @@ -250,15 +223,6 @@ static void gnttab_update_entry_v1(grant_ref_t ref, domid_t domid, gnttab_shared.v1[ref].flags = flags; } -static void gnttab_update_entry_v2(grant_ref_t ref, domid_t domid, - unsigned long frame, unsigned flags) -{ - gnttab_shared.v2[ref].hdr.domid = domid; - gnttab_shared.v2[ref].full_page.frame = frame; - wmb(); - gnttab_shared.v2[ref].hdr.flags = GTF_permit_access | flags; -} - /* * Public grant-issuing interface functions */ @@ -285,132 +249,11 @@ int gnttab_grant_foreign_access(domid_t domid, unsigned long frame, } EXPORT_SYMBOL_GPL(gnttab_grant_foreign_access); -static void gnttab_update_subpage_entry_v2(grant_ref_t ref, domid_t domid, - unsigned long frame, int flags, - unsigned page_off, unsigned length) -{ - gnttab_shared.v2[ref].sub_page.frame = frame; - gnttab_shared.v2[ref].sub_page.page_off = page_off; - gnttab_shared.v2[ref].sub_page.length = length; - gnttab_shared.v2[ref].hdr.domid = domid; - wmb(); - gnttab_shared.v2[ref].hdr.flags = - GTF_permit_access | GTF_sub_page | flags; -} - -int gnttab_grant_foreign_access_subpage_ref(grant_ref_t ref, domid_t domid, - unsigned long frame, int flags, - unsigned page_off, - unsigned length) -{ - if (flags & (GTF_accept_transfer | GTF_reading | - GTF_writing | GTF_transitive)) - return -EPERM; - - if (gnttab_interface->update_subpage_entry == NULL) - return -ENOSYS; - - gnttab_interface->update_subpage_entry(ref, domid, frame, flags, - page_off, length); - - return 0; -} -EXPORT_SYMBOL_GPL(gnttab_grant_foreign_access_subpage_ref); - -int gnttab_grant_foreign_access_subpage(domid_t domid, unsigned long frame, - int flags, unsigned page_off, - unsigned length) -{ - int ref, rc; - - ref = get_free_entries(1); - if (unlikely(ref < 0)) - return -ENOSPC; - - rc = gnttab_grant_foreign_access_subpage_ref(ref, domid, frame, flags, - page_off, length); - if (rc < 0) { - put_free_entry(ref); - return rc; - } - - return ref; -} -EXPORT_SYMBOL_GPL(gnttab_grant_foreign_access_subpage); - -bool gnttab_subpage_grants_available(void) -{ - return gnttab_interface->update_subpage_entry != NULL; -} -EXPORT_SYMBOL_GPL(gnttab_subpage_grants_available); - -static void gnttab_update_trans_entry_v2(grant_ref_t ref, domid_t domid, - int flags, domid_t trans_domid, - grant_ref_t trans_gref) -{ - gnttab_shared.v2[ref].transitive.trans_domid = trans_domid; - gnttab_shared.v2[ref].transitive.gref = trans_gref; - gnttab_shared.v2[ref].hdr.domid = domid; - wmb(); - gnttab_shared.v2[ref].hdr.flags = - GTF_permit_access | GTF_transitive | flags; -} - -int gnttab_grant_foreign_access_trans_ref(grant_ref_t ref, domid_t domid, - int flags, domid_t trans_domid, - grant_ref_t trans_gref) -{ - if (flags & (GTF_accept_transfer | GTF_reading | - GTF_writing | GTF_sub_page)) - return -EPERM; - - if (gnttab_interface->update_trans_entry == NULL) - return -ENOSYS; - - gnttab_interface->update_trans_entry(ref, domid, flags, trans_domid, - trans_gref); - - return 0; -} -EXPORT_SYMBOL_GPL(gnttab_grant_foreign_access_trans_ref); - -int gnttab_grant_foreign_access_trans(domid_t domid, int flags, - domid_t trans_domid, - grant_ref_t trans_gref) -{ - int ref, rc; - - ref = get_free_entries(1); - if (unlikely(ref < 0)) - return -ENOSPC; - - rc = gnttab_grant_foreign_access_trans_ref(ref, domid, flags, - trans_domid, trans_gref); - if (rc < 0) { - put_free_entry(ref); - return rc; - } - - return ref; -} -EXPORT_SYMBOL_GPL(gnttab_grant_foreign_access_trans); - -bool gnttab_trans_grants_available(void) -{ - return gnttab_interface->update_trans_entry != NULL; -} -EXPORT_SYMBOL_GPL(gnttab_trans_grants_available); - static int gnttab_query_foreign_access_v1(grant_ref_t ref) { return gnttab_shared.v1[ref].flags & (GTF_reading|GTF_writing); } -static int gnttab_query_foreign_access_v2(grant_ref_t ref) -{ - return grstatus[ref] & (GTF_reading|GTF_writing); -} - int gnttab_query_foreign_access(grant_ref_t ref) { return gnttab_interface->query_foreign_access(ref); @@ -433,29 +276,6 @@ static int gnttab_end_foreign_access_ref_v1(grant_ref_t ref, int readonly) return 1; } -static int gnttab_end_foreign_access_ref_v2(grant_ref_t ref, int readonly) -{ - gnttab_shared.v2[ref].hdr.flags = 0; - mb(); - if (grstatus[ref] & (GTF_reading|GTF_writing)) { - return 0; - } else { - /* The read of grstatus needs to have acquire - semantics. On x86, reads already have - that, and we just need to protect against - compiler reorderings. On other - architectures we may need a full - barrier. */ -#ifdef CONFIG_X86 - barrier(); -#else - mb(); -#endif - } - - return 1; -} - static inline int _gnttab_end_foreign_access_ref(grant_ref_t ref, int readonly) { return gnttab_interface->end_foreign_access_ref(ref, readonly); @@ -616,37 +436,6 @@ static unsigned long gnttab_end_foreign_transfer_ref_v1(grant_ref_t ref) return frame; } -static unsigned long gnttab_end_foreign_transfer_ref_v2(grant_ref_t ref) -{ - unsigned long frame; - u16 flags; - u16 *pflags; - - pflags = &gnttab_shared.v2[ref].hdr.flags; - - /* - * If a transfer is not even yet started, try to reclaim the grant - * reference and return failure (== 0). - */ - while (!((flags = *pflags) & GTF_transfer_committed)) { - if (sync_cmpxchg(pflags, flags, 0) == flags) - return 0; - cpu_relax(); - } - - /* If a transfer is in progress then wait until it is completed. */ - while (!(flags & GTF_transfer_completed)) { - flags = *pflags; - cpu_relax(); - } - - rmb(); /* Read the frame number /after/ reading completion status. */ - frame = gnttab_shared.v2[ref].full_page.frame; - BUG_ON(frame == 0); - - return frame; -} - unsigned long gnttab_end_foreign_transfer_ref(grant_ref_t ref) { return gnttab_interface->end_foreign_transfer_ref(ref); @@ -962,12 +751,6 @@ int gnttab_unmap_refs(struct gnttab_unmap_grant_ref *unmap_ops, } EXPORT_SYMBOL_GPL(gnttab_unmap_refs); -static unsigned nr_status_frames(unsigned nr_grant_frames) -{ - BUG_ON(grefs_per_grant_frame == 0); - return (nr_grant_frames * grefs_per_grant_frame + SPP - 1) / SPP; -} - static int gnttab_map_frames_v1(xen_pfn_t *frames, unsigned int nr_gframes) { int rc; @@ -985,55 +768,6 @@ static void gnttab_unmap_frames_v1(void) arch_gnttab_unmap(gnttab_shared.addr, nr_grant_frames); } -static int gnttab_map_frames_v2(xen_pfn_t *frames, unsigned int nr_gframes) -{ - uint64_t *sframes; - unsigned int nr_sframes; - struct gnttab_get_status_frames getframes; - int rc; - - nr_sframes = nr_status_frames(nr_gframes); - - /* No need for kzalloc as it is initialized in following hypercall - * GNTTABOP_get_status_frames. - */ - sframes = kmalloc(nr_sframes * sizeof(uint64_t), GFP_ATOMIC); - if (!sframes) - return -ENOMEM; - - getframes.dom = DOMID_SELF; - getframes.nr_frames = nr_sframes; - set_xen_guest_handle(getframes.frame_list, sframes); - - rc = HYPERVISOR_grant_table_op(GNTTABOP_get_status_frames, - &getframes, 1); - if (rc == -ENOSYS) { - kfree(sframes); - return -ENOSYS; - } - - BUG_ON(rc || getframes.status); - - rc = arch_gnttab_map_status(sframes, nr_sframes, - nr_status_frames(gnttab_max_grant_frames()), - &grstatus); - BUG_ON(rc); - kfree(sframes); - - rc = arch_gnttab_map_shared(frames, nr_gframes, - gnttab_max_grant_frames(), - &gnttab_shared.addr); - BUG_ON(rc); - - return 0; -} - -static void gnttab_unmap_frames_v2(void) -{ - arch_gnttab_unmap(gnttab_shared.addr, nr_grant_frames); - arch_gnttab_unmap(grstatus, nr_status_frames(nr_grant_frames)); -} - static int gnttab_map(unsigned int start_idx, unsigned int end_idx) { struct gnttab_setup_table setup; @@ -1101,43 +835,13 @@ static struct gnttab_ops gnttab_v1_ops = { .query_foreign_access = gnttab_query_foreign_access_v1, }; -static struct gnttab_ops gnttab_v2_ops = { - .map_frames = gnttab_map_frames_v2, - .unmap_frames = gnttab_unmap_frames_v2, - .update_entry = gnttab_update_entry_v2, - .end_foreign_access_ref = gnttab_end_foreign_access_ref_v2, - .end_foreign_transfer_ref = gnttab_end_foreign_transfer_ref_v2, - .query_foreign_access = gnttab_query_foreign_access_v2, - .update_subpage_entry = gnttab_update_subpage_entry_v2, - .update_trans_entry = gnttab_update_trans_entry_v2, -}; - static void gnttab_request_version(void) { - int rc; - struct gnttab_set_version gsv; + /* Only version 1 is used, which will always be available. */ + grant_table_version = 1; + grefs_per_grant_frame = PAGE_SIZE / sizeof(struct grant_entry_v1); + gnttab_interface = &gnttab_v1_ops; - gsv.version = 1; - - rc = HYPERVISOR_grant_table_op(GNTTABOP_set_version, &gsv, 1); - if (rc == 0 && gsv.version == 2) { - grant_table_version = 2; - grefs_per_grant_frame = PAGE_SIZE / sizeof(union grant_entry_v2); - gnttab_interface = &gnttab_v2_ops; - } else if (grant_table_version == 2) { - /* - * If we've already used version 2 features, - * but then suddenly discover that they're not - * available (e.g. migrating to an older - * version of Xen), almost unbounded badness - * can happen. - */ - panic("we need grant tables version 2, but only version 1 is available"); - } else { - grant_table_version = 1; - grefs_per_grant_frame = PAGE_SIZE / sizeof(struct grant_entry_v1); - gnttab_interface = &gnttab_v1_ops; - } pr_info("Grant tables using version %d layout\n", grant_table_version); } @@ -1195,18 +899,20 @@ static int gnttab_expand(unsigned int req_entries) int gnttab_init(void) { int i; + unsigned long max_nr_grant_frames; unsigned int max_nr_glist_frames, nr_glist_frames; unsigned int nr_init_grefs; int ret; gnttab_request_version(); + max_nr_grant_frames = gnttab_max_grant_frames(); nr_grant_frames = 1; /* Determine the maximum number of frames required for the * grant reference free list on the current hypervisor. */ BUG_ON(grefs_per_grant_frame == 0); - max_nr_glist_frames = (gnttab_max_grant_frames() * + max_nr_glist_frames = (max_nr_grant_frames * grefs_per_grant_frame / RPP); gnttab_list = kmalloc(max_nr_glist_frames * sizeof(grant_ref_t *), @@ -1223,6 +929,10 @@ int gnttab_init(void) } } + ret = arch_gnttab_init(max_nr_grant_frames); + if (ret < 0) + goto ini_nomem; + if (gnttab_setup() < 0) { ret = -ENODEV; goto ini_nomem; diff --git a/drivers/xen/xen-pciback/passthrough.c b/drivers/xen/xen-pciback/passthrough.c index 828dddc360df..f16a30e2a110 100644 --- a/drivers/xen/xen-pciback/passthrough.c +++ b/drivers/xen/xen-pciback/passthrough.c @@ -69,7 +69,7 @@ static int __xen_pcibk_add_pci_dev(struct xen_pcibk_device *pdev, } static void __xen_pcibk_release_pci_dev(struct xen_pcibk_device *pdev, - struct pci_dev *dev) + struct pci_dev *dev, bool lock) { struct passthrough_dev_data *dev_data = pdev->pci_dev_data; struct pci_dev_entry *dev_entry, *t; @@ -87,8 +87,13 @@ static void __xen_pcibk_release_pci_dev(struct xen_pcibk_device *pdev, mutex_unlock(&dev_data->lock); - if (found_dev) + if (found_dev) { + if (lock) + device_lock(&found_dev->dev); pcistub_put_pci_dev(found_dev); + if (lock) + device_unlock(&found_dev->dev); + } } static int __xen_pcibk_init_devices(struct xen_pcibk_device *pdev) @@ -156,8 +161,11 @@ static void __xen_pcibk_release_devices(struct xen_pcibk_device *pdev) struct pci_dev_entry *dev_entry, *t; list_for_each_entry_safe(dev_entry, t, &dev_data->dev_list, list) { + struct pci_dev *dev = dev_entry->dev; list_del(&dev_entry->list); - pcistub_put_pci_dev(dev_entry->dev); + device_lock(&dev->dev); + pcistub_put_pci_dev(dev); + device_unlock(&dev->dev); kfree(dev_entry); } diff --git a/drivers/xen/xen-pciback/pci_stub.c b/drivers/xen/xen-pciback/pci_stub.c index d57a173685f3..1ddd22feb2c0 100644 --- a/drivers/xen/xen-pciback/pci_stub.c +++ b/drivers/xen/xen-pciback/pci_stub.c @@ -250,6 +250,8 @@ struct pci_dev *pcistub_get_pci_dev(struct xen_pcibk_device *pdev, * - 'echo BDF > unbind' with a guest still using it. See pcistub_remove * * As such we have to be careful. + * + * To make this easier, the caller has to hold the device lock. */ void pcistub_put_pci_dev(struct pci_dev *dev) { @@ -276,11 +278,8 @@ void pcistub_put_pci_dev(struct pci_dev *dev) /* Cleanup our device * (so it's ready for the next domain) */ - - /* This is OK - we are running from workqueue context - * and want to inhibit the user from fiddling with 'reset' - */ - pci_reset_function(dev); + device_lock_assert(&dev->dev); + __pci_reset_function_locked(dev); pci_restore_state(dev); /* This disables the device. */ @@ -554,12 +553,14 @@ static void pcistub_remove(struct pci_dev *dev) spin_unlock_irqrestore(&pcistub_devices_lock, flags); if (found_psdev) { - dev_dbg(&dev->dev, "found device to remove - in use? %p\n", - found_psdev->pdev); + dev_dbg(&dev->dev, "found device to remove %s\n", + found_psdev->pdev ? "- in-use" : ""); if (found_psdev->pdev) { - pr_warn("****** removing device %s while still in-use! ******\n", - pci_name(found_psdev->dev)); + int domid = xen_find_device_domain_owner(dev); + + pr_warn("****** removing device %s while still in-use by domain %d! ******\n", + pci_name(found_psdev->dev), domid); pr_warn("****** driver domain may still access this device's i/o resources!\n"); pr_warn("****** shutdown driver domain before binding device\n"); pr_warn("****** to other drivers or domains\n"); @@ -567,7 +568,8 @@ static void pcistub_remove(struct pci_dev *dev) /* N.B. This ends up calling pcistub_put_pci_dev which ends up * doing the FLR. */ xen_pcibk_release_pci_dev(found_psdev->pdev, - found_psdev->dev); + found_psdev->dev, + false /* caller holds the lock. */); } spin_lock_irqsave(&pcistub_devices_lock, flags); @@ -629,10 +631,12 @@ static pci_ers_result_t common_process(struct pcistub_device *psdev, { pci_ers_result_t res = result; struct xen_pcie_aer_op *aer_op; + struct xen_pcibk_device *pdev = psdev->pdev; + struct xen_pci_sharedinfo *sh_info = pdev->sh_info; int ret; /*with PV AER drivers*/ - aer_op = &(psdev->pdev->sh_info->aer_op); + aer_op = &(sh_info->aer_op); aer_op->cmd = aer_cmd ; /*useful for error_detected callback*/ aer_op->err = state; @@ -653,36 +657,36 @@ static pci_ers_result_t common_process(struct pcistub_device *psdev, * this flag to judge whether we need to check pci-front give aer * service ack signal */ - set_bit(_PCIB_op_pending, (unsigned long *)&psdev->pdev->flags); + set_bit(_PCIB_op_pending, (unsigned long *)&pdev->flags); /*It is possible that a pcifront conf_read_write ops request invokes * the callback which cause the spurious execution of wake_up. * Yet it is harmless and better than a spinlock here */ set_bit(_XEN_PCIB_active, - (unsigned long *)&psdev->pdev->sh_info->flags); + (unsigned long *)&sh_info->flags); wmb(); - notify_remote_via_irq(psdev->pdev->evtchn_irq); + notify_remote_via_irq(pdev->evtchn_irq); ret = wait_event_timeout(xen_pcibk_aer_wait_queue, !(test_bit(_XEN_PCIB_active, (unsigned long *) - &psdev->pdev->sh_info->flags)), 300*HZ); + &sh_info->flags)), 300*HZ); if (!ret) { if (test_bit(_XEN_PCIB_active, - (unsigned long *)&psdev->pdev->sh_info->flags)) { + (unsigned long *)&sh_info->flags)) { dev_err(&psdev->dev->dev, "pcifront aer process not responding!\n"); clear_bit(_XEN_PCIB_active, - (unsigned long *)&psdev->pdev->sh_info->flags); + (unsigned long *)&sh_info->flags); aer_op->err = PCI_ERS_RESULT_NONE; return res; } } - clear_bit(_PCIB_op_pending, (unsigned long *)&psdev->pdev->flags); + clear_bit(_PCIB_op_pending, (unsigned long *)&pdev->flags); if (test_bit(_XEN_PCIF_active, - (unsigned long *)&psdev->pdev->sh_info->flags)) { + (unsigned long *)&sh_info->flags)) { dev_dbg(&psdev->dev->dev, "schedule pci_conf service in " DRV_NAME "\n"); xen_pcibk_test_and_schedule_op(psdev->pdev); diff --git a/drivers/xen/xen-pciback/pciback.h b/drivers/xen/xen-pciback/pciback.h index f72af87640e0..58e38d586f52 100644 --- a/drivers/xen/xen-pciback/pciback.h +++ b/drivers/xen/xen-pciback/pciback.h @@ -99,7 +99,8 @@ struct xen_pcibk_backend { unsigned int *domain, unsigned int *bus, unsigned int *devfn); int (*publish)(struct xen_pcibk_device *pdev, publish_pci_root_cb cb); - void (*release)(struct xen_pcibk_device *pdev, struct pci_dev *dev); + void (*release)(struct xen_pcibk_device *pdev, struct pci_dev *dev, + bool lock); int (*add)(struct xen_pcibk_device *pdev, struct pci_dev *dev, int devid, publish_pci_dev_cb publish_cb); struct pci_dev *(*get)(struct xen_pcibk_device *pdev, @@ -122,10 +123,10 @@ static inline int xen_pcibk_add_pci_dev(struct xen_pcibk_device *pdev, } static inline void xen_pcibk_release_pci_dev(struct xen_pcibk_device *pdev, - struct pci_dev *dev) + struct pci_dev *dev, bool lock) { if (xen_pcibk_backend && xen_pcibk_backend->release) - return xen_pcibk_backend->release(pdev, dev); + return xen_pcibk_backend->release(pdev, dev, lock); } static inline struct pci_dev * diff --git a/drivers/xen/xen-pciback/vpci.c b/drivers/xen/xen-pciback/vpci.c index 51afff96c515..c99f8bb1c56c 100644 --- a/drivers/xen/xen-pciback/vpci.c +++ b/drivers/xen/xen-pciback/vpci.c @@ -145,7 +145,7 @@ out: } static void __xen_pcibk_release_pci_dev(struct xen_pcibk_device *pdev, - struct pci_dev *dev) + struct pci_dev *dev, bool lock) { int slot; struct vpci_dev_data *vpci_dev = pdev->pci_dev_data; @@ -169,8 +169,13 @@ static void __xen_pcibk_release_pci_dev(struct xen_pcibk_device *pdev, out: mutex_unlock(&vpci_dev->lock); - if (found_dev) + if (found_dev) { + if (lock) + device_lock(&found_dev->dev); pcistub_put_pci_dev(found_dev); + if (lock) + device_unlock(&found_dev->dev); + } } static int __xen_pcibk_init_devices(struct xen_pcibk_device *pdev) @@ -208,8 +213,11 @@ static void __xen_pcibk_release_devices(struct xen_pcibk_device *pdev) struct pci_dev_entry *e, *tmp; list_for_each_entry_safe(e, tmp, &vpci_dev->dev_list[slot], list) { + struct pci_dev *dev = e->dev; list_del(&e->list); - pcistub_put_pci_dev(e->dev); + device_lock(&dev->dev); + pcistub_put_pci_dev(dev); + device_unlock(&dev->dev); kfree(e); } } diff --git a/drivers/xen/xen-pciback/xenbus.c b/drivers/xen/xen-pciback/xenbus.c index 4a7e6e0a5f4c..53e2dda43446 100644 --- a/drivers/xen/xen-pciback/xenbus.c +++ b/drivers/xen/xen-pciback/xenbus.c @@ -246,7 +246,7 @@ static int xen_pcibk_export_device(struct xen_pcibk_device *pdev, if (err) goto out; - dev_dbg(&dev->dev, "registering for %d\n", pdev->xdev->otherend_id); + dev_info(&dev->dev, "registering for %d\n", pdev->xdev->otherend_id); if (xen_register_device_domain_owner(dev, pdev->xdev->otherend_id) != 0) { dev_err(&dev->dev, "Stealing ownership from dom%d.\n", @@ -290,7 +290,7 @@ static int xen_pcibk_remove_device(struct xen_pcibk_device *pdev, /* N.B. This ends up calling pcistub_put_pci_dev which ends up * doing the FLR. */ - xen_pcibk_release_pci_dev(pdev, dev); + xen_pcibk_release_pci_dev(pdev, dev, true /* use the lock. */); out: return err; diff --git a/include/linux/device.h b/include/linux/device.h index 75f5bcb8930b..cf20850a1c6a 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -908,6 +908,11 @@ static inline void device_unlock(struct device *dev) mutex_unlock(&dev->mutex); } +static inline void device_lock_assert(struct device *dev) +{ + lockdep_assert_held(&dev->mutex); +} + void driver_init(void); /* diff --git a/include/xen/grant_table.h b/include/xen/grant_table.h index a5af2a26d94f..3387465b9caa 100644 --- a/include/xen/grant_table.h +++ b/include/xen/grant_table.h @@ -64,24 +64,6 @@ int gnttab_resume(void); int gnttab_grant_foreign_access(domid_t domid, unsigned long frame, int readonly); -int gnttab_grant_foreign_access_subpage(domid_t domid, unsigned long frame, - int flags, unsigned page_off, - unsigned length); -int gnttab_grant_foreign_access_trans(domid_t domid, int flags, - domid_t trans_domid, - grant_ref_t trans_gref); - -/* - * Are sub-page grants available on this version of Xen? Returns true if they - * are, and false if they're not. - */ -bool gnttab_subpage_grants_available(void); - -/* - * Are transitive grants available on this version of Xen? Returns true if they - * are, and false if they're not. - */ -bool gnttab_trans_grants_available(void); /* * End access through the given grant reference, iff the grant entry is no @@ -128,13 +110,6 @@ void gnttab_cancel_free_callback(struct gnttab_free_callback *callback); void gnttab_grant_foreign_access_ref(grant_ref_t ref, domid_t domid, unsigned long frame, int readonly); -int gnttab_grant_foreign_access_subpage_ref(grant_ref_t ref, domid_t domid, - unsigned long frame, int flags, - unsigned page_off, - unsigned length); -int gnttab_grant_foreign_access_trans_ref(grant_ref_t ref, domid_t domid, - int flags, domid_t trans_domid, - grant_ref_t trans_gref); void gnttab_grant_foreign_transfer_ref(grant_ref_t, domid_t domid, unsigned long pfn); @@ -170,12 +145,10 @@ gnttab_set_unmap_op(struct gnttab_unmap_grant_ref *unmap, phys_addr_t addr, unmap->dev_bus_addr = 0; } +int arch_gnttab_init(unsigned long nr_shared); int arch_gnttab_map_shared(xen_pfn_t *frames, unsigned long nr_gframes, unsigned long max_nr_gframes, void **__shared); -int arch_gnttab_map_status(uint64_t *frames, unsigned long nr_gframes, - unsigned long max_nr_gframes, - grant_status_t **__shared); void arch_gnttab_unmap(void *shared, unsigned long nr_gframes); struct grant_frames { |