diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2015-04-16 21:01:03 +0200 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2015-04-16 21:01:03 +0200 |
commit | 497a5df7bf6ffd136ae21c49d1a01292930d7ca2 (patch) | |
tree | 774215d43cdc9fbd8660086d1801400163dcbd52 /drivers/xen | |
parent | Merge tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/a... (diff) | |
parent | xen/pci: Try harder to get PXM information for Xen (diff) | |
download | linux-497a5df7bf6ffd136ae21c49d1a01292930d7ca2.tar.xz linux-497a5df7bf6ffd136ae21c49d1a01292930d7ca2.zip |
Merge tag 'stable/for-linus-4.1-rc0-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip
Pull xen features and fixes from David Vrabel:
- use a single source list of hypercalls, generating other tables etc.
at build time.
- add a "Xen PV" APIC driver to support >255 VCPUs in PV guests.
- significant performance improve to guest save/restore/migration.
- scsiback/front save/restore support.
- infrastructure for multi-page xenbus rings.
- misc fixes.
* tag 'stable/for-linus-4.1-rc0-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip:
xen/pci: Try harder to get PXM information for Xen
xenbus_client: Extend interface to support multi-page ring
xen-pciback: also support disabling of bus-mastering and memory-write-invalidate
xen: support suspend/resume in pvscsi frontend
xen: scsiback: add LUN of restored domain
xen-scsiback: define a pr_fmt macro with xen-pvscsi
xen/mce: fix up xen_late_init_mcelog() error handling
xen/privcmd: improve performance of MMAPBATCH_V2
xen: unify foreign GFN map/unmap for auto-xlated physmap guests
x86/xen/apic: WARN with details.
x86/xen: Provide a "Xen PV" APIC driver to support >255 VCPUs
xen/pciback: Don't print scary messages when unsupported by hypervisor.
xen: use generated hypercall symbols in arch/x86/xen/xen-head.S
xen: use generated hypervisor symbols in arch/x86/xen/trace.c
xen: synchronize include/xen/interface/xen.h with xen
xen: build infrastructure for generating hypercall depending symbols
xen: balloon: Use static attribute groups for sysfs entries
xen: pcpu: Use static attribute groups for sysfs entry
Diffstat (limited to 'drivers/xen')
-rw-r--r-- | drivers/xen/Kconfig | 6 | ||||
-rw-r--r-- | drivers/xen/Makefile | 1 | ||||
-rw-r--r-- | drivers/xen/mcelog.c | 25 | ||||
-rw-r--r-- | drivers/xen/pci.c | 15 | ||||
-rw-r--r-- | drivers/xen/pcpu.c | 44 | ||||
-rw-r--r-- | drivers/xen/privcmd.c | 117 | ||||
-rw-r--r-- | drivers/xen/xen-balloon.c | 45 | ||||
-rw-r--r-- | drivers/xen/xen-pciback/conf_space_header.c | 15 | ||||
-rw-r--r-- | drivers/xen/xen-pciback/pci_stub.c | 4 | ||||
-rw-r--r-- | drivers/xen/xen-pciback/xenbus.c | 2 | ||||
-rw-r--r-- | drivers/xen/xen-scsiback.c | 96 | ||||
-rw-r--r-- | drivers/xen/xenbus/xenbus_client.c | 387 | ||||
-rw-r--r-- | drivers/xen/xlate_mmu.c | 143 |
13 files changed, 665 insertions, 235 deletions
diff --git a/drivers/xen/Kconfig b/drivers/xen/Kconfig index 94d96809e686..a270004c9605 100644 --- a/drivers/xen/Kconfig +++ b/drivers/xen/Kconfig @@ -270,4 +270,10 @@ config XEN_EFI def_bool y depends on X86_64 && EFI +config XEN_AUTO_XLATE + def_bool y + depends on ARM || ARM64 || XEN_PVHVM + help + Support for auto-translated physmap guests. + endmenu diff --git a/drivers/xen/Makefile b/drivers/xen/Makefile index 2ccd3592d41f..40edd1cbb60d 100644 --- a/drivers/xen/Makefile +++ b/drivers/xen/Makefile @@ -37,6 +37,7 @@ obj-$(CONFIG_XEN_ACPI_HOTPLUG_CPU) += xen-acpi-cpuhotplug.o obj-$(CONFIG_XEN_ACPI_PROCESSOR) += xen-acpi-processor.o obj-$(CONFIG_XEN_EFI) += efi.o obj-$(CONFIG_XEN_SCSI_BACKEND) += xen-scsiback.o +obj-$(CONFIG_XEN_AUTO_XLATE) += xlate_mmu.o xen-evtchn-y := evtchn.o xen-gntdev-y := gntdev.o xen-gntalloc-y := gntalloc.o diff --git a/drivers/xen/mcelog.c b/drivers/xen/mcelog.c index 6ab6a79c38a5..a493c7315e94 100644 --- a/drivers/xen/mcelog.c +++ b/drivers/xen/mcelog.c @@ -393,14 +393,25 @@ static int bind_virq_for_mce(void) static int __init xen_late_init_mcelog(void) { + int ret; + /* Only DOM0 is responsible for MCE logging */ - if (xen_initial_domain()) { - /* register character device /dev/mcelog for xen mcelog */ - if (misc_register(&xen_mce_chrdev_device)) - return -ENODEV; - return bind_virq_for_mce(); - } + if (!xen_initial_domain()) + return -ENODEV; + + /* register character device /dev/mcelog for xen mcelog */ + ret = misc_register(&xen_mce_chrdev_device); + if (ret) + return ret; + + ret = bind_virq_for_mce(); + if (ret) + goto deregister; - return -ENODEV; + return 0; + +deregister: + misc_deregister(&xen_mce_chrdev_device); + return ret; } device_initcall(xen_late_init_mcelog); diff --git a/drivers/xen/pci.c b/drivers/xen/pci.c index 95ee4302ffb8..7494dbeb4409 100644 --- a/drivers/xen/pci.c +++ b/drivers/xen/pci.c @@ -19,6 +19,7 @@ #include <linux/pci.h> #include <linux/acpi.h> +#include <linux/pci-acpi.h> #include <xen/xen.h> #include <xen/interface/physdev.h> #include <xen/interface/xen.h> @@ -67,12 +68,22 @@ static int xen_add_device(struct device *dev) #ifdef CONFIG_ACPI handle = ACPI_HANDLE(&pci_dev->dev); - if (!handle && pci_dev->bus->bridge) - handle = ACPI_HANDLE(pci_dev->bus->bridge); #ifdef CONFIG_PCI_IOV if (!handle && pci_dev->is_virtfn) handle = ACPI_HANDLE(physfn->bus->bridge); #endif + if (!handle) { + /* + * This device was not listed in the ACPI name space at + * all. Try to get acpi handle of parent pci bus. + */ + struct pci_bus *pbus; + for (pbus = pci_dev->bus; pbus; pbus = pbus->parent) { + handle = acpi_pci_get_bridge_handle(pbus); + if (handle) + break; + } + } if (handle) { acpi_status status; diff --git a/drivers/xen/pcpu.c b/drivers/xen/pcpu.c index 0aac403d53fd..49e88f2ce7a1 100644 --- a/drivers/xen/pcpu.c +++ b/drivers/xen/pcpu.c @@ -132,6 +132,33 @@ static ssize_t __ref store_online(struct device *dev, } static DEVICE_ATTR(online, S_IRUGO | S_IWUSR, show_online, store_online); +static struct attribute *pcpu_dev_attrs[] = { + &dev_attr_online.attr, + NULL +}; + +static umode_t pcpu_dev_is_visible(struct kobject *kobj, + struct attribute *attr, int idx) +{ + struct device *dev = kobj_to_dev(kobj); + /* + * Xen never offline cpu0 due to several restrictions + * and assumptions. This basically doesn't add a sys control + * to user, one cannot attempt to offline BSP. + */ + return dev->id ? attr->mode : 0; +} + +static const struct attribute_group pcpu_dev_group = { + .attrs = pcpu_dev_attrs, + .is_visible = pcpu_dev_is_visible, +}; + +static const struct attribute_group *pcpu_dev_groups[] = { + &pcpu_dev_group, + NULL +}; + static bool xen_pcpu_online(uint32_t flags) { return !!(flags & XEN_PCPU_FLAGS_ONLINE); @@ -181,9 +208,6 @@ static void unregister_and_remove_pcpu(struct pcpu *pcpu) return; dev = &pcpu->dev; - if (dev->id) - device_remove_file(dev, &dev_attr_online); - /* pcpu remove would be implicitly done */ device_unregister(dev); } @@ -200,6 +224,7 @@ static int register_pcpu(struct pcpu *pcpu) dev->bus = &xen_pcpu_subsys; dev->id = pcpu->cpu_id; dev->release = pcpu_release; + dev->groups = pcpu_dev_groups; err = device_register(dev); if (err) { @@ -207,19 +232,6 @@ static int register_pcpu(struct pcpu *pcpu) return err; } - /* - * Xen never offline cpu0 due to several restrictions - * and assumptions. This basically doesn't add a sys control - * to user, one cannot attempt to offline BSP. - */ - if (dev->id) { - err = device_create_file(dev, &dev_attr_online); - if (err) { - device_unregister(dev); - return err; - } - } - return 0; } diff --git a/drivers/xen/privcmd.c b/drivers/xen/privcmd.c index 59ac71c4a043..5a296161d843 100644 --- a/drivers/xen/privcmd.c +++ b/drivers/xen/privcmd.c @@ -159,6 +159,40 @@ static int traverse_pages(unsigned nelem, size_t size, return ret; } +/* + * Similar to traverse_pages, but use each page as a "block" of + * data to be processed as one unit. + */ +static int traverse_pages_block(unsigned nelem, size_t size, + struct list_head *pos, + int (*fn)(void *data, int nr, void *state), + void *state) +{ + void *pagedata; + unsigned pageidx; + int ret = 0; + + BUG_ON(size > PAGE_SIZE); + + pageidx = PAGE_SIZE; + + while (nelem) { + int nr = (PAGE_SIZE/size); + struct page *page; + if (nr > nelem) + nr = nelem; + pos = pos->next; + page = list_entry(pos, struct page, lru); + pagedata = page_address(page); + ret = (*fn)(pagedata, nr, state); + if (ret) + break; + nelem -= nr; + } + + return ret; +} + struct mmap_mfn_state { unsigned long va; struct vm_area_struct *vma; @@ -274,39 +308,25 @@ struct mmap_batch_state { /* auto translated dom0 note: if domU being created is PV, then mfn is * mfn(addr on bus). If it's auto xlated, then mfn is pfn (input to HAP). */ -static int mmap_batch_fn(void *data, void *state) +static int mmap_batch_fn(void *data, int nr, void *state) { xen_pfn_t *mfnp = data; struct mmap_batch_state *st = state; struct vm_area_struct *vma = st->vma; struct page **pages = vma->vm_private_data; - struct page *cur_page = NULL; + struct page **cur_pages = NULL; int ret; if (xen_feature(XENFEAT_auto_translated_physmap)) - cur_page = pages[st->index++]; + cur_pages = &pages[st->index]; - ret = xen_remap_domain_mfn_range(st->vma, st->va & PAGE_MASK, *mfnp, 1, - st->vma->vm_page_prot, st->domain, - &cur_page); + BUG_ON(nr < 0); + ret = xen_remap_domain_mfn_array(st->vma, st->va & PAGE_MASK, mfnp, nr, + (int *)mfnp, st->vma->vm_page_prot, + st->domain, cur_pages); - /* Store error code for second pass. */ - if (st->version == 1) { - if (ret < 0) { - /* - * V1 encodes the error codes in the 32bit top nibble of the - * mfn (with its known limitations vis-a-vis 64 bit callers). - */ - *mfnp |= (ret == -ENOENT) ? - PRIVCMD_MMAPBATCH_PAGED_ERROR : - PRIVCMD_MMAPBATCH_MFN_ERROR; - } - } else { /* st->version == 2 */ - *((int *) mfnp) = ret; - } - - /* And see if it affects the global_error. */ - if (ret < 0) { + /* Adjust the global_error? */ + if (ret != nr) { if (ret == -ENOENT) st->global_error = -ENOENT; else { @@ -315,23 +335,35 @@ static int mmap_batch_fn(void *data, void *state) st->global_error = 1; } } - st->va += PAGE_SIZE; + st->va += PAGE_SIZE * nr; + st->index += nr; return 0; } -static int mmap_return_errors(void *data, void *state) +static int mmap_return_error(int err, struct mmap_batch_state *st) { - struct mmap_batch_state *st = state; + int ret; if (st->version == 1) { - xen_pfn_t mfnp = *((xen_pfn_t *) data); - if (mfnp & PRIVCMD_MMAPBATCH_MFN_ERROR) - return __put_user(mfnp, st->user_mfn++); - else + if (err) { + xen_pfn_t mfn; + + ret = get_user(mfn, st->user_mfn); + if (ret < 0) + return ret; + /* + * V1 encodes the error codes in the 32bit top + * nibble of the mfn (with its known + * limitations vis-a-vis 64 bit callers). + */ + mfn |= (err == -ENOENT) ? + PRIVCMD_MMAPBATCH_PAGED_ERROR : + PRIVCMD_MMAPBATCH_MFN_ERROR; + return __put_user(mfn, st->user_mfn++); + } else st->user_mfn++; } else { /* st->version == 2 */ - int err = *((int *) data); if (err) return __put_user(err, st->user_err++); else @@ -341,6 +373,21 @@ static int mmap_return_errors(void *data, void *state) return 0; } +static int mmap_return_errors(void *data, int nr, void *state) +{ + struct mmap_batch_state *st = state; + int *errs = data; + int i; + int ret; + + for (i = 0; i < nr; i++) { + ret = mmap_return_error(errs[i], st); + if (ret < 0) + return ret; + } + return 0; +} + /* Allocate pfns that are then mapped with gmfns from foreign domid. Update * the vma with the page info to use later. * Returns: 0 if success, otherwise -errno @@ -472,8 +519,8 @@ static long privcmd_ioctl_mmap_batch(void __user *udata, int version) state.version = version; /* mmap_batch_fn guarantees ret == 0 */ - BUG_ON(traverse_pages(m.num, sizeof(xen_pfn_t), - &pagelist, mmap_batch_fn, &state)); + BUG_ON(traverse_pages_block(m.num, sizeof(xen_pfn_t), + &pagelist, mmap_batch_fn, &state)); up_write(&mm->mmap_sem); @@ -481,8 +528,8 @@ static long privcmd_ioctl_mmap_batch(void __user *udata, int version) /* Write back errors in second pass. */ state.user_mfn = (xen_pfn_t *)m.arr; state.user_err = m.err; - ret = traverse_pages(m.num, sizeof(xen_pfn_t), - &pagelist, mmap_return_errors, &state); + ret = traverse_pages_block(m.num, sizeof(xen_pfn_t), + &pagelist, mmap_return_errors, &state); } else ret = 0; diff --git a/drivers/xen/xen-balloon.c b/drivers/xen/xen-balloon.c index e555845d61fa..39e7ef8d3957 100644 --- a/drivers/xen/xen-balloon.c +++ b/drivers/xen/xen-balloon.c @@ -193,13 +193,18 @@ static DEVICE_ATTR(target, S_IRUGO | S_IWUSR, show_target, store_target); -static struct device_attribute *balloon_attrs[] = { - &dev_attr_target_kb, - &dev_attr_target, - &dev_attr_schedule_delay.attr, - &dev_attr_max_schedule_delay.attr, - &dev_attr_retry_count.attr, - &dev_attr_max_retry_count.attr +static struct attribute *balloon_attrs[] = { + &dev_attr_target_kb.attr, + &dev_attr_target.attr, + &dev_attr_schedule_delay.attr.attr, + &dev_attr_max_schedule_delay.attr.attr, + &dev_attr_retry_count.attr.attr, + &dev_attr_max_retry_count.attr.attr, + NULL +}; + +static const struct attribute_group balloon_group = { + .attrs = balloon_attrs }; static struct attribute *balloon_info_attrs[] = { @@ -214,6 +219,12 @@ static const struct attribute_group balloon_info_group = { .attrs = balloon_info_attrs }; +static const struct attribute_group *balloon_groups[] = { + &balloon_group, + &balloon_info_group, + NULL +}; + static struct bus_type balloon_subsys = { .name = BALLOON_CLASS_NAME, .dev_name = BALLOON_CLASS_NAME, @@ -221,7 +232,7 @@ static struct bus_type balloon_subsys = { static int register_balloon(struct device *dev) { - int i, error; + int error; error = subsys_system_register(&balloon_subsys, NULL); if (error) @@ -229,6 +240,7 @@ static int register_balloon(struct device *dev) dev->id = 0; dev->bus = &balloon_subsys; + dev->groups = balloon_groups; error = device_register(dev); if (error) { @@ -236,24 +248,7 @@ static int register_balloon(struct device *dev) return error; } - for (i = 0; i < ARRAY_SIZE(balloon_attrs); i++) { - error = device_create_file(dev, balloon_attrs[i]); - if (error) - goto fail; - } - - error = sysfs_create_group(&dev->kobj, &balloon_info_group); - if (error) - goto fail; - return 0; - - fail: - while (--i >= 0) - device_remove_file(dev, balloon_attrs[i]); - device_unregister(dev); - bus_unregister(&balloon_subsys); - return error; } MODULE_LICENSE("GPL"); diff --git a/drivers/xen/xen-pciback/conf_space_header.c b/drivers/xen/xen-pciback/conf_space_header.c index 2d7369391472..c2260a0456c9 100644 --- a/drivers/xen/xen-pciback/conf_space_header.c +++ b/drivers/xen/xen-pciback/conf_space_header.c @@ -88,9 +88,15 @@ static int command_write(struct pci_dev *dev, int offset, u16 value, void *data) printk(KERN_DEBUG DRV_NAME ": %s: set bus master\n", pci_name(dev)); pci_set_master(dev); + } else if (dev->is_busmaster && !is_master_cmd(value)) { + if (unlikely(verbose_request)) + printk(KERN_DEBUG DRV_NAME ": %s: clear bus master\n", + pci_name(dev)); + pci_clear_master(dev); } - if (value & PCI_COMMAND_INVALIDATE) { + if (!(cmd->val & PCI_COMMAND_INVALIDATE) && + (value & PCI_COMMAND_INVALIDATE)) { if (unlikely(verbose_request)) printk(KERN_DEBUG DRV_NAME ": %s: enable memory-write-invalidate\n", @@ -101,6 +107,13 @@ static int command_write(struct pci_dev *dev, int offset, u16 value, void *data) pci_name(dev), err); value &= ~PCI_COMMAND_INVALIDATE; } + } else if ((cmd->val & PCI_COMMAND_INVALIDATE) && + !(value & PCI_COMMAND_INVALIDATE)) { + if (unlikely(verbose_request)) + printk(KERN_DEBUG + DRV_NAME ": %s: disable memory-write-invalidate\n", + pci_name(dev)); + pci_clear_mwi(dev); } cmd->val = value; diff --git a/drivers/xen/xen-pciback/pci_stub.c b/drivers/xen/xen-pciback/pci_stub.c index cc3cbb4435f8..258b7c325649 100644 --- a/drivers/xen/xen-pciback/pci_stub.c +++ b/drivers/xen/xen-pciback/pci_stub.c @@ -118,7 +118,7 @@ static void pcistub_device_release(struct kref *kref) int err = HYPERVISOR_physdev_op(PHYSDEVOP_release_msix, &ppdev); - if (err) + if (err && err != -ENOSYS) dev_warn(&dev->dev, "MSI-X release failed (%d)\n", err); } @@ -402,7 +402,7 @@ static int pcistub_init_device(struct pci_dev *dev) }; err = HYPERVISOR_physdev_op(PHYSDEVOP_prepare_msix, &ppdev); - if (err) + if (err && err != -ENOSYS) dev_err(&dev->dev, "MSI-X preparation failed (%d)\n", err); } diff --git a/drivers/xen/xen-pciback/xenbus.c b/drivers/xen/xen-pciback/xenbus.c index fe17c80ff4b7..98bc345f296e 100644 --- a/drivers/xen/xen-pciback/xenbus.c +++ b/drivers/xen/xen-pciback/xenbus.c @@ -113,7 +113,7 @@ static int xen_pcibk_do_attach(struct xen_pcibk_device *pdev, int gnt_ref, "Attaching to frontend resources - gnt_ref=%d evtchn=%d\n", gnt_ref, remote_evtchn); - err = xenbus_map_ring_valloc(pdev->xdev, gnt_ref, &vaddr); + err = xenbus_map_ring_valloc(pdev->xdev, &gnt_ref, 1, &vaddr); if (err < 0) { xenbus_dev_fatal(pdev->xdev, err, "Error mapping other domain page in ours."); diff --git a/drivers/xen/xen-scsiback.c b/drivers/xen/xen-scsiback.c index 42bd55a6c237..07ef38325223 100644 --- a/drivers/xen/xen-scsiback.c +++ b/drivers/xen/xen-scsiback.c @@ -31,6 +31,8 @@ * IN THE SOFTWARE. */ +#define pr_fmt(fmt) "xen-pvscsi: " fmt + #include <stdarg.h> #include <linux/module.h> @@ -69,9 +71,6 @@ #include <xen/interface/grant_table.h> #include <xen/interface/io/vscsiif.h> -#define DPRINTK(_f, _a...) \ - pr_debug("(file=%s, line=%d) " _f, __FILE__ , __LINE__ , ## _a) - #define VSCSI_VERSION "v0.1" #define VSCSI_NAMELEN 32 @@ -271,7 +270,7 @@ static void scsiback_print_status(char *sense_buffer, int errors, { struct scsiback_tpg *tpg = pending_req->v2p->tpg; - pr_err("xen-pvscsi[%s:%d] cmnd[0]=%02x -> st=%02x msg=%02x host=%02x drv=%02x\n", + pr_err("[%s:%d] cmnd[0]=%02x -> st=%02x msg=%02x host=%02x drv=%02x\n", tpg->tport->tport_name, pending_req->v2p->lun, pending_req->cmnd[0], status_byte(errors), msg_byte(errors), host_byte(errors), driver_byte(errors)); @@ -427,7 +426,7 @@ static int scsiback_gnttab_data_map_batch(struct gnttab_map_grant_ref *map, BUG_ON(err); for (i = 0; i < cnt; i++) { if (unlikely(map[i].status != GNTST_okay)) { - pr_err("xen-pvscsi: invalid buffer -- could not remap it\n"); + pr_err("invalid buffer -- could not remap it\n"); map[i].handle = SCSIBACK_INVALID_HANDLE; err = -ENOMEM; } else { @@ -449,7 +448,7 @@ static int scsiback_gnttab_data_map_list(struct vscsibk_pend *pending_req, for (i = 0; i < cnt; i++) { if (get_free_page(pg + mapcount)) { put_free_pages(pg, mapcount); - pr_err("xen-pvscsi: no grant page\n"); + pr_err("no grant page\n"); return -ENOMEM; } gnttab_set_map_op(&map[mapcount], vaddr_page(pg[mapcount]), @@ -492,7 +491,7 @@ static int scsiback_gnttab_data_map(struct vscsiif_request *ring_req, return 0; if (nr_segments > VSCSIIF_SG_TABLESIZE) { - DPRINTK("xen-pvscsi: invalid parameter nr_seg = %d\n", + pr_debug("invalid parameter nr_seg = %d\n", ring_req->nr_segments); return -EINVAL; } @@ -516,13 +515,12 @@ static int scsiback_gnttab_data_map(struct vscsiif_request *ring_req, nr_segments += n_segs; } if (nr_segments > SG_ALL) { - DPRINTK("xen-pvscsi: invalid nr_seg = %d\n", - nr_segments); + pr_debug("invalid nr_seg = %d\n", nr_segments); return -EINVAL; } } - /* free of (sgl) in fast_flush_area()*/ + /* free of (sgl) in fast_flush_area() */ pending_req->sgl = kmalloc_array(nr_segments, sizeof(struct scatterlist), GFP_KERNEL); if (!pending_req->sgl) @@ -679,7 +677,8 @@ static int prepare_pending_reqs(struct vscsibk_info *info, v2p = scsiback_do_translation(info, &vir); if (!v2p) { pending_req->v2p = NULL; - DPRINTK("xen-pvscsi: doesn't exist.\n"); + pr_debug("the v2p of (chn:%d, tgt:%d, lun:%d) doesn't exist.\n", + vir.chn, vir.tgt, vir.lun); return -ENODEV; } pending_req->v2p = v2p; @@ -690,14 +689,14 @@ static int prepare_pending_reqs(struct vscsibk_info *info, (pending_req->sc_data_direction != DMA_TO_DEVICE) && (pending_req->sc_data_direction != DMA_FROM_DEVICE) && (pending_req->sc_data_direction != DMA_NONE)) { - DPRINTK("xen-pvscsi: invalid parameter data_dir = %d\n", + pr_debug("invalid parameter data_dir = %d\n", pending_req->sc_data_direction); return -EINVAL; } pending_req->cmd_len = ring_req->cmd_len; if (pending_req->cmd_len > VSCSIIF_MAX_COMMAND_SIZE) { - DPRINTK("xen-pvscsi: invalid parameter cmd_len = %d\n", + pr_debug("invalid parameter cmd_len = %d\n", pending_req->cmd_len); return -EINVAL; } @@ -721,7 +720,7 @@ static int scsiback_do_cmd_fn(struct vscsibk_info *info) if (RING_REQUEST_PROD_OVERFLOW(ring, rp)) { rc = ring->rsp_prod_pvt; - pr_warn("xen-pvscsi: Dom%d provided bogus ring requests (%#x - %#x = %u). Halting ring processing\n", + pr_warn("Dom%d provided bogus ring requests (%#x - %#x = %u). Halting ring processing\n", info->domid, rp, rc, rp - rc); info->ring_error = 1; return 0; @@ -772,7 +771,7 @@ static int scsiback_do_cmd_fn(struct vscsibk_info *info) scsiback_device_action(pending_req, TMR_LUN_RESET, 0); break; default: - pr_err_ratelimited("xen-pvscsi: invalid request\n"); + pr_err_ratelimited("invalid request\n"); scsiback_do_resp_with_sense(NULL, DRIVER_ERROR << 24, 0, pending_req); kmem_cache_free(scsiback_cachep, pending_req); @@ -810,7 +809,7 @@ static int scsiback_init_sring(struct vscsibk_info *info, grant_ref_t ring_ref, if (info->irq) return -1; - err = xenbus_map_ring_valloc(info->dev, ring_ref, &area); + err = xenbus_map_ring_valloc(info->dev, &ring_ref, 1, &area); if (err) return err; @@ -874,14 +873,13 @@ static int scsiback_add_translation_entry(struct vscsibk_info *info, lunp = strrchr(phy, ':'); if (!lunp) { - pr_err("xen-pvscsi: illegal format of physical device %s\n", - phy); + pr_err("illegal format of physical device %s\n", phy); return -EINVAL; } *lunp = 0; lunp++; if (kstrtouint(lunp, 10, &lun) || lun >= TRANSPORT_MAX_LUNS_PER_TPG) { - pr_err("xen-pvscsi: lun number not valid: %s\n", lunp); + pr_err("lun number not valid: %s\n", lunp); return -EINVAL; } @@ -909,7 +907,7 @@ static int scsiback_add_translation_entry(struct vscsibk_info *info, mutex_unlock(&scsiback_mutex); if (!tpg) { - pr_err("xen-pvscsi: %s:%d %s\n", phy, lun, error); + pr_err("%s:%d %s\n", phy, lun, error); return -ENODEV; } @@ -926,7 +924,7 @@ static int scsiback_add_translation_entry(struct vscsibk_info *info, if ((entry->v.chn == v->chn) && (entry->v.tgt == v->tgt) && (entry->v.lun == v->lun)) { - pr_warn("xen-pvscsi: Virtual ID is already used. Assignment was not performed.\n"); + pr_warn("Virtual ID is already used. Assignment was not performed.\n"); err = -EEXIST; goto out; } @@ -992,15 +990,15 @@ found: } static void scsiback_do_add_lun(struct vscsibk_info *info, const char *state, - char *phy, struct ids_tuple *vir) + char *phy, struct ids_tuple *vir, int try) { if (!scsiback_add_translation_entry(info, phy, vir)) { if (xenbus_printf(XBT_NIL, info->dev->nodename, state, "%d", XenbusStateInitialised)) { - pr_err("xen-pvscsi: xenbus_printf error %s\n", state); + pr_err("xenbus_printf error %s\n", state); scsiback_del_translation_entry(info, vir); } - } else { + } else if (!try) { xenbus_printf(XBT_NIL, info->dev->nodename, state, "%d", XenbusStateClosed); } @@ -1012,7 +1010,7 @@ static void scsiback_do_del_lun(struct vscsibk_info *info, const char *state, if (!scsiback_del_translation_entry(info, vir)) { if (xenbus_printf(XBT_NIL, info->dev->nodename, state, "%d", XenbusStateClosed)) - pr_err("xen-pvscsi: xenbus_printf error %s\n", state); + pr_err("xenbus_printf error %s\n", state); } } @@ -1060,10 +1058,19 @@ static void scsiback_do_1lun_hotplug(struct vscsibk_info *info, int op, switch (op) { case VSCSIBACK_OP_ADD_OR_DEL_LUN: - if (device_state == XenbusStateInitialising) - scsiback_do_add_lun(info, state, phy, &vir); - if (device_state == XenbusStateClosing) + switch (device_state) { + case XenbusStateInitialising: + scsiback_do_add_lun(info, state, phy, &vir, 0); + break; + case XenbusStateConnected: + scsiback_do_add_lun(info, state, phy, &vir, 1); + break; + case XenbusStateClosing: scsiback_do_del_lun(info, state, &vir); + break; + default: + break; + } break; case VSCSIBACK_OP_UPDATEDEV_STATE: @@ -1071,15 +1078,14 @@ static void scsiback_do_1lun_hotplug(struct vscsibk_info *info, int op, /* modify vscsi-devs/dev-x/state */ if (xenbus_printf(XBT_NIL, dev->nodename, state, "%d", XenbusStateConnected)) { - pr_err("xen-pvscsi: xenbus_printf error %s\n", - str); + pr_err("xenbus_printf error %s\n", str); scsiback_del_translation_entry(info, &vir); xenbus_printf(XBT_NIL, dev->nodename, state, "%d", XenbusStateClosed); } } break; - /*When it is necessary, processing is added here.*/ + /* When it is necessary, processing is added here. */ default: break; } @@ -1196,7 +1202,7 @@ static int scsiback_probe(struct xenbus_device *dev, struct vscsibk_info *info = kzalloc(sizeof(struct vscsibk_info), GFP_KERNEL); - DPRINTK("%p %d\n", dev, dev->otherend_id); + pr_debug("%s %p %d\n", __func__, dev, dev->otherend_id); if (!info) { xenbus_dev_fatal(dev, -ENOMEM, "allocating backend structure"); @@ -1227,7 +1233,7 @@ static int scsiback_probe(struct xenbus_device *dev, return 0; fail: - pr_warn("xen-pvscsi: %s failed\n", __func__); + pr_warn("%s failed\n", __func__); scsiback_remove(dev); return err; @@ -1432,7 +1438,7 @@ check_len: } snprintf(&tport->tport_name[0], VSCSI_NAMELEN, "%s", &name[off]); - pr_debug("xen-pvscsi: Allocated emulated Target %s Address: %s\n", + pr_debug("Allocated emulated Target %s Address: %s\n", scsiback_dump_proto_id(tport), name); return &tport->tport_wwn; @@ -1443,7 +1449,7 @@ static void scsiback_drop_tport(struct se_wwn *wwn) struct scsiback_tport *tport = container_of(wwn, struct scsiback_tport, tport_wwn); - pr_debug("xen-pvscsi: Deallocating emulated Target %s Address: %s\n", + pr_debug("Deallocating emulated Target %s Address: %s\n", scsiback_dump_proto_id(tport), tport->tport_name); kfree(tport); @@ -1470,8 +1476,8 @@ static u32 scsiback_tpg_get_inst_index(struct se_portal_group *se_tpg) static int scsiback_check_stop_free(struct se_cmd *se_cmd) { /* - * Do not release struct se_cmd's containing a valid TMR - * pointer. These will be released directly in scsiback_device_action() + * Do not release struct se_cmd's containing a valid TMR pointer. + * These will be released directly in scsiback_device_action() * with transport_generic_free_cmd(). */ if (se_cmd->se_cmd_flags & SCF_SCSI_TMR_CDB) @@ -1637,7 +1643,7 @@ static int scsiback_make_nexus(struct scsiback_tpg *tpg, return -ENOMEM; } /* - * Initialize the struct se_session pointer + * Initialize the struct se_session pointer */ tv_nexus->tvn_se_sess = transport_init_session(TARGET_PROT_NORMAL); if (IS_ERR(tv_nexus->tvn_se_sess)) { @@ -1705,7 +1711,7 @@ static int scsiback_drop_nexus(struct scsiback_tpg *tpg) return -EBUSY; } - pr_debug("xen-pvscsi: Removing I_T Nexus to emulated %s Initiator Port: %s\n", + pr_debug("Removing I_T Nexus to emulated %s Initiator Port: %s\n", scsiback_dump_proto_id(tpg->tport), tv_nexus->tvn_se_sess->se_node_acl->initiatorname); @@ -1751,7 +1757,7 @@ static ssize_t scsiback_tpg_store_nexus(struct se_portal_group *se_tpg, unsigned char i_port[VSCSI_NAMELEN], *ptr, *port_ptr; int ret; /* - * Shutdown the active I_T nexus if 'NULL' is passed.. + * Shutdown the active I_T nexus if 'NULL' is passed. */ if (!strncmp(page, "NULL", 4)) { ret = scsiback_drop_nexus(tpg); @@ -1922,7 +1928,7 @@ static void scsiback_drop_tpg(struct se_portal_group *se_tpg) */ scsiback_drop_nexus(tpg); /* - * Deregister the se_tpg from TCM.. + * Deregister the se_tpg from TCM. */ core_tpg_deregister(se_tpg); kfree(tpg); @@ -1992,7 +1998,7 @@ static int scsiback_register_configfs(void) struct target_fabric_configfs *fabric; int ret; - pr_debug("xen-pvscsi: fabric module %s on %s/%s on "UTS_RELEASE"\n", + pr_debug("fabric module %s on %s/%s on "UTS_RELEASE"\n", VSCSI_VERSION, utsname()->sysname, utsname()->machine); /* * Register the top level struct config_item_type with TCM core @@ -2029,7 +2035,7 @@ static int scsiback_register_configfs(void) * Setup our local pointer to *fabric */ scsiback_fabric_configfs = fabric; - pr_debug("xen-pvscsi: Set fabric -> scsiback_fabric_configfs\n"); + pr_debug("Set fabric -> scsiback_fabric_configfs\n"); return 0; }; @@ -2040,7 +2046,7 @@ static void scsiback_deregister_configfs(void) target_fabric_configfs_deregister(scsiback_fabric_configfs); scsiback_fabric_configfs = NULL; - pr_debug("xen-pvscsi: Cleared scsiback_fabric_configfs\n"); + pr_debug("Cleared scsiback_fabric_configfs\n"); }; static const struct xenbus_device_id scsiback_ids[] = { @@ -2091,7 +2097,7 @@ out_unregister_xenbus: xenbus_unregister_driver(&scsiback_driver); out_cache_destroy: kmem_cache_destroy(scsiback_cachep); - pr_err("xen-pvscsi: %s: error %d\n", __func__, ret); + pr_err("%s: error %d\n", __func__, ret); return ret; } diff --git a/drivers/xen/xenbus/xenbus_client.c b/drivers/xen/xenbus/xenbus_client.c index ca744102b666..96b2011d25f3 100644 --- a/drivers/xen/xenbus/xenbus_client.c +++ b/drivers/xen/xenbus/xenbus_client.c @@ -52,17 +52,25 @@ struct xenbus_map_node { struct list_head next; union { - struct vm_struct *area; /* PV */ - struct page *page; /* HVM */ + struct { + struct vm_struct *area; + } pv; + struct { + struct page *pages[XENBUS_MAX_RING_PAGES]; + void *addr; + } hvm; }; - grant_handle_t handle; + grant_handle_t handles[XENBUS_MAX_RING_PAGES]; + unsigned int nr_handles; }; static DEFINE_SPINLOCK(xenbus_valloc_lock); static LIST_HEAD(xenbus_valloc_pages); struct xenbus_ring_ops { - int (*map)(struct xenbus_device *dev, int gnt, void **vaddr); + int (*map)(struct xenbus_device *dev, + grant_ref_t *gnt_refs, unsigned int nr_grefs, + void **vaddr); int (*unmap)(struct xenbus_device *dev, void *vaddr); }; @@ -355,17 +363,39 @@ static void xenbus_switch_fatal(struct xenbus_device *dev, int depth, int err, /** * xenbus_grant_ring * @dev: xenbus device - * @ring_mfn: mfn of ring to grant - - * Grant access to the given @ring_mfn to the peer of the given device. Return - * a grant reference on success, or -errno on error. On error, the device will - * switch to XenbusStateClosing, and the error will be saved in the store. + * @vaddr: starting virtual address of the ring + * @nr_pages: number of pages to be granted + * @grefs: grant reference array to be filled in + * + * Grant access to the given @vaddr to the peer of the given device. + * Then fill in @grefs with grant references. Return 0 on success, or + * -errno on error. On error, the device will switch to + * XenbusStateClosing, and the error will be saved in the store. */ -int xenbus_grant_ring(struct xenbus_device *dev, unsigned long ring_mfn) +int xenbus_grant_ring(struct xenbus_device *dev, void *vaddr, + unsigned int nr_pages, grant_ref_t *grefs) { - int err = gnttab_grant_foreign_access(dev->otherend_id, ring_mfn, 0); - if (err < 0) - xenbus_dev_fatal(dev, err, "granting access to ring page"); + int err; + int i, j; + + for (i = 0; i < nr_pages; i++) { + unsigned long addr = (unsigned long)vaddr + + (PAGE_SIZE * i); + err = gnttab_grant_foreign_access(dev->otherend_id, + virt_to_mfn(addr), 0); + if (err < 0) { + xenbus_dev_fatal(dev, err, + "granting access to ring page"); + goto fail; + } + grefs[i] = err; + } + + return 0; + +fail: + for (j = 0; j < i; j++) + gnttab_end_foreign_access_ref(grefs[j], 0); return err; } EXPORT_SYMBOL_GPL(xenbus_grant_ring); @@ -419,62 +449,130 @@ EXPORT_SYMBOL_GPL(xenbus_free_evtchn); /** * xenbus_map_ring_valloc * @dev: xenbus device - * @gnt_ref: grant reference + * @gnt_refs: grant reference array + * @nr_grefs: number of grant references * @vaddr: pointer to address to be filled out by mapping * - * Based on Rusty Russell's skeleton driver's map_page. - * Map a page of memory into this domain from another domain's grant table. - * xenbus_map_ring_valloc allocates a page of virtual address space, maps the - * page to that address, and sets *vaddr to that address. - * Returns 0 on success, and GNTST_* (see xen/include/interface/grant_table.h) - * or -ENOMEM on error. If an error is returned, device will switch to + * Map @nr_grefs pages of memory into this domain from another + * domain's grant table. xenbus_map_ring_valloc allocates @nr_grefs + * pages of virtual address space, maps the pages to that address, and + * sets *vaddr to that address. Returns 0 on success, and GNTST_* + * (see xen/include/interface/grant_table.h) or -ENOMEM / -EINVAL on + * error. If an error is returned, device will switch to * XenbusStateClosing and the error message will be saved in XenStore. */ -int xenbus_map_ring_valloc(struct xenbus_device *dev, int gnt_ref, void **vaddr) +int xenbus_map_ring_valloc(struct xenbus_device *dev, grant_ref_t *gnt_refs, + unsigned int nr_grefs, void **vaddr) { - return ring_ops->map(dev, gnt_ref, vaddr); + return ring_ops->map(dev, gnt_refs, nr_grefs, vaddr); } EXPORT_SYMBOL_GPL(xenbus_map_ring_valloc); +/* N.B. sizeof(phys_addr_t) doesn't always equal to sizeof(unsigned + * long), e.g. 32-on-64. Caller is responsible for preparing the + * right array to feed into this function */ +static int __xenbus_map_ring(struct xenbus_device *dev, + grant_ref_t *gnt_refs, + unsigned int nr_grefs, + grant_handle_t *handles, + phys_addr_t *addrs, + unsigned int flags, + bool *leaked) +{ + struct gnttab_map_grant_ref map[XENBUS_MAX_RING_PAGES]; + struct gnttab_unmap_grant_ref unmap[XENBUS_MAX_RING_PAGES]; + int i, j; + int err = GNTST_okay; + + if (nr_grefs > XENBUS_MAX_RING_PAGES) + return -EINVAL; + + for (i = 0; i < nr_grefs; i++) { + memset(&map[i], 0, sizeof(map[i])); + gnttab_set_map_op(&map[i], addrs[i], flags, gnt_refs[i], + dev->otherend_id); + handles[i] = INVALID_GRANT_HANDLE; + } + + gnttab_batch_map(map, i); + + for (i = 0; i < nr_grefs; i++) { + if (map[i].status != GNTST_okay) { + err = map[i].status; + xenbus_dev_fatal(dev, map[i].status, + "mapping in shared page %d from domain %d", + gnt_refs[i], dev->otherend_id); + goto fail; + } else + handles[i] = map[i].handle; + } + + return GNTST_okay; + + fail: + for (i = j = 0; i < nr_grefs; i++) { + if (handles[i] != INVALID_GRANT_HANDLE) { + memset(&unmap[j], 0, sizeof(unmap[j])); + gnttab_set_unmap_op(&unmap[j], (phys_addr_t)addrs[i], + GNTMAP_host_map, handles[i]); + j++; + } + } + + if (HYPERVISOR_grant_table_op(GNTTABOP_unmap_grant_ref, unmap, j)) + BUG(); + + *leaked = false; + for (i = 0; i < j; i++) { + if (unmap[i].status != GNTST_okay) { + *leaked = true; + break; + } + } + + return err; +} + static int xenbus_map_ring_valloc_pv(struct xenbus_device *dev, - int gnt_ref, void **vaddr) + grant_ref_t *gnt_refs, + unsigned int nr_grefs, + void **vaddr) { - struct gnttab_map_grant_ref op = { - .flags = GNTMAP_host_map | GNTMAP_contains_pte, - .ref = gnt_ref, - .dom = dev->otherend_id, - }; struct xenbus_map_node *node; struct vm_struct *area; - pte_t *pte; + pte_t *ptes[XENBUS_MAX_RING_PAGES]; + phys_addr_t phys_addrs[XENBUS_MAX_RING_PAGES]; + int err = GNTST_okay; + int i; + bool leaked; *vaddr = NULL; + if (nr_grefs > XENBUS_MAX_RING_PAGES) + return -EINVAL; + node = kzalloc(sizeof(*node), GFP_KERNEL); if (!node) return -ENOMEM; - area = alloc_vm_area(PAGE_SIZE, &pte); + area = alloc_vm_area(PAGE_SIZE * nr_grefs, ptes); if (!area) { kfree(node); return -ENOMEM; } - op.host_addr = arbitrary_virt_to_machine(pte).maddr; + for (i = 0; i < nr_grefs; i++) + phys_addrs[i] = arbitrary_virt_to_machine(ptes[i]).maddr; - gnttab_batch_map(&op, 1); - - if (op.status != GNTST_okay) { - free_vm_area(area); - kfree(node); - xenbus_dev_fatal(dev, op.status, - "mapping in shared page %d from domain %d", - gnt_ref, dev->otherend_id); - return op.status; - } + err = __xenbus_map_ring(dev, gnt_refs, nr_grefs, node->handles, + phys_addrs, + GNTMAP_host_map | GNTMAP_contains_pte, + &leaked); + if (err) + goto failed; - node->handle = op.handle; - node->area = area; + node->nr_handles = nr_grefs; + node->pv.area = area; spin_lock(&xenbus_valloc_lock); list_add(&node->next, &xenbus_valloc_pages); @@ -482,14 +580,33 @@ static int xenbus_map_ring_valloc_pv(struct xenbus_device *dev, *vaddr = area->addr; return 0; + +failed: + if (!leaked) + free_vm_area(area); + else + pr_alert("leaking VM area %p size %u page(s)", area, nr_grefs); + + kfree(node); + return err; } static int xenbus_map_ring_valloc_hvm(struct xenbus_device *dev, - int gnt_ref, void **vaddr) + grant_ref_t *gnt_ref, + unsigned int nr_grefs, + void **vaddr) { struct xenbus_map_node *node; + int i; int err; void *addr; + bool leaked = false; + /* Why do we need two arrays? See comment of __xenbus_map_ring */ + phys_addr_t phys_addrs[XENBUS_MAX_RING_PAGES]; + unsigned long addrs[XENBUS_MAX_RING_PAGES]; + + if (nr_grefs > XENBUS_MAX_RING_PAGES) + return -EINVAL; *vaddr = NULL; @@ -497,15 +614,32 @@ static int xenbus_map_ring_valloc_hvm(struct xenbus_device *dev, if (!node) return -ENOMEM; - err = alloc_xenballooned_pages(1, &node->page, false /* lowmem */); + err = alloc_xenballooned_pages(nr_grefs, node->hvm.pages, + false /* lowmem */); if (err) goto out_err; - addr = pfn_to_kaddr(page_to_pfn(node->page)); + for (i = 0; i < nr_grefs; i++) { + unsigned long pfn = page_to_pfn(node->hvm.pages[i]); + phys_addrs[i] = (unsigned long)pfn_to_kaddr(pfn); + addrs[i] = (unsigned long)pfn_to_kaddr(pfn); + } + + err = __xenbus_map_ring(dev, gnt_ref, nr_grefs, node->handles, + phys_addrs, GNTMAP_host_map, &leaked); + node->nr_handles = nr_grefs; - err = xenbus_map_ring(dev, gnt_ref, &node->handle, addr); if (err) - goto out_err_free_ballooned_pages; + goto out_free_ballooned_pages; + + addr = vmap(node->hvm.pages, nr_grefs, VM_MAP | VM_IOREMAP, + PAGE_KERNEL); + if (!addr) { + err = -ENOMEM; + goto out_xenbus_unmap_ring; + } + + node->hvm.addr = addr; spin_lock(&xenbus_valloc_lock); list_add(&node->next, &xenbus_valloc_pages); @@ -514,8 +648,16 @@ static int xenbus_map_ring_valloc_hvm(struct xenbus_device *dev, *vaddr = addr; return 0; - out_err_free_ballooned_pages: - free_xenballooned_pages(1, &node->page); + out_xenbus_unmap_ring: + if (!leaked) + xenbus_unmap_ring(dev, node->handles, node->nr_handles, + addrs); + else + pr_alert("leaking %p size %u page(s)", + addr, nr_grefs); + out_free_ballooned_pages: + if (!leaked) + free_xenballooned_pages(nr_grefs, node->hvm.pages); out_err: kfree(node); return err; @@ -525,35 +667,37 @@ static int xenbus_map_ring_valloc_hvm(struct xenbus_device *dev, /** * xenbus_map_ring * @dev: xenbus device - * @gnt_ref: grant reference - * @handle: pointer to grant handle to be filled - * @vaddr: address to be mapped to + * @gnt_refs: grant reference array + * @nr_grefs: number of grant reference + * @handles: pointer to grant handle to be filled + * @vaddrs: addresses to be mapped to + * @leaked: fail to clean up a failed map, caller should not free vaddr * - * Map a page of memory into this domain from another domain's grant table. + * Map pages of memory into this domain from another domain's grant table. * xenbus_map_ring does not allocate the virtual address space (you must do - * this yourself!). It only maps in the page to the specified address. + * this yourself!). It only maps in the pages to the specified address. * Returns 0 on success, and GNTST_* (see xen/include/interface/grant_table.h) - * or -ENOMEM on error. If an error is returned, device will switch to - * XenbusStateClosing and the error message will be saved in XenStore. + * or -ENOMEM / -EINVAL on error. If an error is returned, device will switch to + * XenbusStateClosing and the first error message will be saved in XenStore. + * Further more if we fail to map the ring, caller should check @leaked. + * If @leaked is not zero it means xenbus_map_ring fails to clean up, caller + * should not free the address space of @vaddr. */ -int xenbus_map_ring(struct xenbus_device *dev, int gnt_ref, - grant_handle_t *handle, void *vaddr) +int xenbus_map_ring(struct xenbus_device *dev, grant_ref_t *gnt_refs, + unsigned int nr_grefs, grant_handle_t *handles, + unsigned long *vaddrs, bool *leaked) { - struct gnttab_map_grant_ref op; - - gnttab_set_map_op(&op, (unsigned long)vaddr, GNTMAP_host_map, gnt_ref, - dev->otherend_id); + phys_addr_t phys_addrs[XENBUS_MAX_RING_PAGES]; + int i; - gnttab_batch_map(&op, 1); + if (nr_grefs > XENBUS_MAX_RING_PAGES) + return -EINVAL; - if (op.status != GNTST_okay) { - xenbus_dev_fatal(dev, op.status, - "mapping in shared page %d from domain %d", - gnt_ref, dev->otherend_id); - } else - *handle = op.handle; + for (i = 0; i < nr_grefs; i++) + phys_addrs[i] = (unsigned long)vaddrs[i]; - return op.status; + return __xenbus_map_ring(dev, gnt_refs, nr_grefs, handles, + phys_addrs, GNTMAP_host_map, leaked); } EXPORT_SYMBOL_GPL(xenbus_map_ring); @@ -579,14 +723,15 @@ EXPORT_SYMBOL_GPL(xenbus_unmap_ring_vfree); static int xenbus_unmap_ring_vfree_pv(struct xenbus_device *dev, void *vaddr) { struct xenbus_map_node *node; - struct gnttab_unmap_grant_ref op = { - .host_addr = (unsigned long)vaddr, - }; + struct gnttab_unmap_grant_ref unmap[XENBUS_MAX_RING_PAGES]; unsigned int level; + int i; + bool leaked = false; + int err; spin_lock(&xenbus_valloc_lock); list_for_each_entry(node, &xenbus_valloc_pages, next) { - if (node->area->addr == vaddr) { + if (node->pv.area->addr == vaddr) { list_del(&node->next); goto found; } @@ -601,22 +746,41 @@ static int xenbus_unmap_ring_vfree_pv(struct xenbus_device *dev, void *vaddr) return GNTST_bad_virt_addr; } - op.handle = node->handle; - op.host_addr = arbitrary_virt_to_machine( - lookup_address((unsigned long)vaddr, &level)).maddr; + for (i = 0; i < node->nr_handles; i++) { + unsigned long addr; + + memset(&unmap[i], 0, sizeof(unmap[i])); + addr = (unsigned long)vaddr + (PAGE_SIZE * i); + unmap[i].host_addr = arbitrary_virt_to_machine( + lookup_address(addr, &level)).maddr; + unmap[i].dev_bus_addr = 0; + unmap[i].handle = node->handles[i]; + } - if (HYPERVISOR_grant_table_op(GNTTABOP_unmap_grant_ref, &op, 1)) + if (HYPERVISOR_grant_table_op(GNTTABOP_unmap_grant_ref, unmap, i)) BUG(); - if (op.status == GNTST_okay) - free_vm_area(node->area); + err = GNTST_okay; + leaked = false; + for (i = 0; i < node->nr_handles; i++) { + if (unmap[i].status != GNTST_okay) { + leaked = true; + xenbus_dev_error(dev, unmap[i].status, + "unmapping page at handle %d error %d", + node->handles[i], unmap[i].status); + err = unmap[i].status; + break; + } + } + + if (!leaked) + free_vm_area(node->pv.area); else - xenbus_dev_error(dev, op.status, - "unmapping page at handle %d error %d", - node->handle, op.status); + pr_alert("leaking VM area %p size %u page(s)", + node->pv.area, node->nr_handles); kfree(node); - return op.status; + return err; } static int xenbus_unmap_ring_vfree_hvm(struct xenbus_device *dev, void *vaddr) @@ -624,10 +788,12 @@ static int xenbus_unmap_ring_vfree_hvm(struct xenbus_device *dev, void *vaddr) int rv; struct xenbus_map_node *node; void *addr; + unsigned long addrs[XENBUS_MAX_RING_PAGES]; + int i; spin_lock(&xenbus_valloc_lock); list_for_each_entry(node, &xenbus_valloc_pages, next) { - addr = pfn_to_kaddr(page_to_pfn(node->page)); + addr = node->hvm.addr; if (addr == vaddr) { list_del(&node->next); goto found; @@ -643,12 +809,16 @@ static int xenbus_unmap_ring_vfree_hvm(struct xenbus_device *dev, void *vaddr) return GNTST_bad_virt_addr; } - rv = xenbus_unmap_ring(dev, node->handle, addr); + for (i = 0; i < node->nr_handles; i++) + addrs[i] = (unsigned long)pfn_to_kaddr(page_to_pfn(node->hvm.pages[i])); + rv = xenbus_unmap_ring(dev, node->handles, node->nr_handles, + addrs); if (!rv) - free_xenballooned_pages(1, &node->page); + vunmap(vaddr); else - WARN(1, "Leaking %p\n", vaddr); + WARN(1, "Leaking %p, size %u page(s)\n", vaddr, + node->nr_handles); kfree(node); return rv; @@ -657,29 +827,44 @@ static int xenbus_unmap_ring_vfree_hvm(struct xenbus_device *dev, void *vaddr) /** * xenbus_unmap_ring * @dev: xenbus device - * @handle: grant handle - * @vaddr: addr to unmap + * @handles: grant handle array + * @nr_handles: number of handles in the array + * @vaddrs: addresses to unmap * - * Unmap a page of memory in this domain that was imported from another domain. + * Unmap memory in this domain that was imported from another domain. * Returns 0 on success and returns GNTST_* on error * (see xen/include/interface/grant_table.h). */ int xenbus_unmap_ring(struct xenbus_device *dev, - grant_handle_t handle, void *vaddr) + grant_handle_t *handles, unsigned int nr_handles, + unsigned long *vaddrs) { - struct gnttab_unmap_grant_ref op; + struct gnttab_unmap_grant_ref unmap[XENBUS_MAX_RING_PAGES]; + int i; + int err; - gnttab_set_unmap_op(&op, (unsigned long)vaddr, GNTMAP_host_map, handle); + if (nr_handles > XENBUS_MAX_RING_PAGES) + return -EINVAL; - if (HYPERVISOR_grant_table_op(GNTTABOP_unmap_grant_ref, &op, 1)) + for (i = 0; i < nr_handles; i++) + gnttab_set_unmap_op(&unmap[i], vaddrs[i], + GNTMAP_host_map, handles[i]); + + if (HYPERVISOR_grant_table_op(GNTTABOP_unmap_grant_ref, unmap, i)) BUG(); - if (op.status != GNTST_okay) - xenbus_dev_error(dev, op.status, - "unmapping page at handle %d error %d", - handle, op.status); + err = GNTST_okay; + for (i = 0; i < nr_handles; i++) { + if (unmap[i].status != GNTST_okay) { + xenbus_dev_error(dev, unmap[i].status, + "unmapping page at handle %d error %d", + handles[i], unmap[i].status); + err = unmap[i].status; + break; + } + } - return op.status; + return err; } EXPORT_SYMBOL_GPL(xenbus_unmap_ring); diff --git a/drivers/xen/xlate_mmu.c b/drivers/xen/xlate_mmu.c new file mode 100644 index 000000000000..58a5389aec89 --- /dev/null +++ b/drivers/xen/xlate_mmu.c @@ -0,0 +1,143 @@ +/* + * MMU operations common to all auto-translated physmap guests. + * + * Copyright (C) 2015 Citrix Systems R&D Ltd. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License version 2 + * as published by the Free Software Foundation; or, when distributed + * separately from the Linux kernel or incorporated into other + * software packages, subject to the following license: + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this source file (the "Software"), to deal in the Software without + * restriction, including without limitation the rights to use, copy, modify, + * merge, publish, distribute, sublicense, and/or sell copies of the Software, + * and to permit persons to whom the Software is furnished to do so, subject to + * the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE + * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS + * IN THE SOFTWARE. + */ +#include <linux/kernel.h> +#include <linux/mm.h> + +#include <asm/xen/hypercall.h> +#include <asm/xen/hypervisor.h> + +#include <xen/xen.h> +#include <xen/page.h> +#include <xen/interface/xen.h> +#include <xen/interface/memory.h> + +/* map fgmfn of domid to lpfn in the current domain */ +static int map_foreign_page(unsigned long lpfn, unsigned long fgmfn, + unsigned int domid) +{ + int rc; + struct xen_add_to_physmap_range xatp = { + .domid = DOMID_SELF, + .foreign_domid = domid, + .size = 1, + .space = XENMAPSPACE_gmfn_foreign, + }; + xen_ulong_t idx = fgmfn; + xen_pfn_t gpfn = lpfn; + int err = 0; + + set_xen_guest_handle(xatp.idxs, &idx); + set_xen_guest_handle(xatp.gpfns, &gpfn); + set_xen_guest_handle(xatp.errs, &err); + + rc = HYPERVISOR_memory_op(XENMEM_add_to_physmap_range, &xatp); + return rc < 0 ? rc : err; +} + +struct remap_data { + xen_pfn_t *fgmfn; /* foreign domain's gmfn */ + pgprot_t prot; + domid_t domid; + struct vm_area_struct *vma; + int index; + struct page **pages; + struct xen_remap_mfn_info *info; + int *err_ptr; + int mapped; +}; + +static int remap_pte_fn(pte_t *ptep, pgtable_t token, unsigned long addr, + void *data) +{ + struct remap_data *info = data; + struct page *page = info->pages[info->index++]; + unsigned long pfn = page_to_pfn(page); + pte_t pte = pte_mkspecial(pfn_pte(pfn, info->prot)); + int rc; + + rc = map_foreign_page(pfn, *info->fgmfn, info->domid); + *info->err_ptr++ = rc; + if (!rc) { + set_pte_at(info->vma->vm_mm, addr, ptep, pte); + info->mapped++; + } + info->fgmfn++; + + return 0; +} + +int xen_xlate_remap_gfn_array(struct vm_area_struct *vma, + unsigned long addr, + xen_pfn_t *mfn, int nr, + int *err_ptr, pgprot_t prot, + unsigned domid, + struct page **pages) +{ + int err; + struct remap_data data; + unsigned long range = nr << PAGE_SHIFT; + + /* Kept here for the purpose of making sure code doesn't break + x86 PVOPS */ + BUG_ON(!((vma->vm_flags & (VM_PFNMAP | VM_IO)) == (VM_PFNMAP | VM_IO))); + + data.fgmfn = mfn; + data.prot = prot; + data.domid = domid; + data.vma = vma; + data.pages = pages; + data.index = 0; + data.err_ptr = err_ptr; + data.mapped = 0; + + err = apply_to_page_range(vma->vm_mm, addr, range, + remap_pte_fn, &data); + return err < 0 ? err : data.mapped; +} +EXPORT_SYMBOL_GPL(xen_xlate_remap_gfn_array); + +int xen_xlate_unmap_gfn_range(struct vm_area_struct *vma, + int nr, struct page **pages) +{ + int i; + + for (i = 0; i < nr; i++) { + struct xen_remove_from_physmap xrp; + unsigned long pfn; + + pfn = page_to_pfn(pages[i]); + + xrp.domid = DOMID_SELF; + xrp.gpfn = pfn; + (void)HYPERVISOR_memory_op(XENMEM_remove_from_physmap, &xrp); + } + return 0; +} +EXPORT_SYMBOL_GPL(xen_xlate_unmap_gfn_range); |