diff options
Diffstat (limited to 'drivers/xen')
| -rw-r--r-- | drivers/xen/Kconfig | 3 | ||||
| -rw-r--r-- | drivers/xen/Makefile | 7 | ||||
| -rw-r--r-- | drivers/xen/balloon.c | 5 | ||||
| -rw-r--r-- | drivers/xen/privcmd.c | 72 | ||||
| -rw-r--r-- | drivers/xen/xen-acpi-pad.c | 182 | ||||
| -rw-r--r-- | drivers/xen/xen-pciback/pci_stub.c | 118 | ||||
| -rw-r--r-- | drivers/xen/xenbus/xenbus_xs.c | 1 |
7 files changed, 326 insertions, 62 deletions
diff --git a/drivers/xen/Kconfig b/drivers/xen/Kconfig index 126d8ce591c..cabfa97f467 100644 --- a/drivers/xen/Kconfig +++ b/drivers/xen/Kconfig @@ -206,4 +206,7 @@ config XEN_MCE_LOG Allow kernel fetching MCE error from Xen platform and converting it into Linux mcelog format for mcelog tools +config XEN_HAVE_PVMMU + bool + endmenu diff --git a/drivers/xen/Makefile b/drivers/xen/Makefile index 74354708c6c..fb213cf81a7 100644 --- a/drivers/xen/Makefile +++ b/drivers/xen/Makefile @@ -1,9 +1,9 @@ ifneq ($(CONFIG_ARM),y) -obj-y += manage.o balloon.o +obj-y += manage.o obj-$(CONFIG_HOTPLUG_CPU) += cpu_hotplug.o endif obj-$(CONFIG_X86) += fallback.o -obj-y += grant-table.o features.o events.o +obj-y += grant-table.o features.o events.o balloon.o obj-y += xenbus/ nostackp := $(call cc-option, -fno-stack-protector) @@ -11,7 +11,8 @@ CFLAGS_features.o := $(nostackp) dom0-$(CONFIG_PCI) += pci.o dom0-$(CONFIG_USB_SUPPORT) += dbgp.o -dom0-$(CONFIG_ACPI) += acpi.o +dom0-$(CONFIG_ACPI) += acpi.o $(xen-pad-y) +xen-pad-$(CONFIG_X86) += xen-acpi-pad.o dom0-$(CONFIG_X86) += pcpu.o obj-$(CONFIG_XEN_DOM0) += $(dom0-y) obj-$(CONFIG_BLOCK) += biomerge.o diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c index d6886d90ccf..a56776dbe09 100644 --- a/drivers/xen/balloon.c +++ b/drivers/xen/balloon.c @@ -359,6 +359,7 @@ static enum bp_state increase_reservation(unsigned long nr_pages) set_phys_to_machine(pfn, frame_list[i]); +#ifdef CONFIG_XEN_HAVE_PVMMU /* Link back into the page tables if not highmem. */ if (xen_pv_domain() && !PageHighMem(page)) { int ret; @@ -368,6 +369,7 @@ static enum bp_state increase_reservation(unsigned long nr_pages) 0); BUG_ON(ret); } +#endif /* Relinquish the page back to the allocator. */ ClearPageReserved(page); @@ -416,13 +418,14 @@ static enum bp_state decrease_reservation(unsigned long nr_pages, gfp_t gfp) scrub_page(page); +#ifdef CONFIG_XEN_HAVE_PVMMU if (xen_pv_domain() && !PageHighMem(page)) { ret = HYPERVISOR_update_va_mapping( (unsigned long)__va(pfn << PAGE_SHIFT), __pte_ma(0), 0); BUG_ON(ret); } - +#endif } /* Ensure that ballooned highmem pages don't have kmaps. */ diff --git a/drivers/xen/privcmd.c b/drivers/xen/privcmd.c index 71f5c459b08..0bbbccbb1f1 100644 --- a/drivers/xen/privcmd.c +++ b/drivers/xen/privcmd.c @@ -33,11 +33,14 @@ #include <xen/features.h> #include <xen/page.h> #include <xen/xen-ops.h> +#include <xen/balloon.h> #include "privcmd.h" MODULE_LICENSE("GPL"); +#define PRIV_VMA_LOCKED ((void *)1) + #ifndef HAVE_ARCH_PRIVCMD_MMAP static int privcmd_enforce_singleshot_mapping(struct vm_area_struct *vma); #endif @@ -178,7 +181,7 @@ static int mmap_mfn_range(void *data, void *state) msg->va & PAGE_MASK, msg->mfn, msg->npages, vma->vm_page_prot, - st->domain); + st->domain, NULL); if (rc < 0) return rc; @@ -199,6 +202,10 @@ static long privcmd_ioctl_mmap(void __user *udata) if (!xen_initial_domain()) return -EPERM; + /* We only support privcmd_ioctl_mmap_batch for auto translated. */ + if (xen_feature(XENFEAT_auto_translated_physmap)) + return -ENOSYS; + if (copy_from_user(&mmapcmd, udata, sizeof(mmapcmd))) return -EFAULT; @@ -246,6 +253,7 @@ struct mmap_batch_state { domid_t domain; unsigned long va; struct vm_area_struct *vma; + int index; /* A tristate: * 0 for no errors * 1 if at least one error has happened (and no @@ -260,14 +268,24 @@ struct mmap_batch_state { xen_pfn_t __user *user_mfn; }; +/* 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) { 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; int ret; + if (xen_feature(XENFEAT_auto_translated_physmap)) + cur_page = pages[st->index++]; + ret = xen_remap_domain_mfn_range(st->vma, st->va & PAGE_MASK, *mfnp, 1, - st->vma->vm_page_prot, st->domain); + st->vma->vm_page_prot, st->domain, + &cur_page); /* Store error code for second pass. */ *(st->err++) = ret; @@ -303,6 +321,32 @@ static int mmap_return_errors_v1(void *data, void *state) return __put_user(*mfnp, st->user_mfn++); } +/* 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 + */ +static int alloc_empty_pages(struct vm_area_struct *vma, int numpgs) +{ + int rc; + struct page **pages; + + pages = kcalloc(numpgs, sizeof(pages[0]), GFP_KERNEL); + if (pages == NULL) + return -ENOMEM; + + rc = alloc_xenballooned_pages(numpgs, pages, 0); + if (rc != 0) { + pr_warn("%s Could not alloc %d pfns rc:%d\n", __func__, + numpgs, rc); + kfree(pages); + return -ENOMEM; + } + BUG_ON(vma->vm_private_data != PRIV_VMA_LOCKED); + vma->vm_private_data = pages; + + return 0; +} + static struct vm_operations_struct privcmd_vm_ops; static long privcmd_ioctl_mmap_batch(void __user *udata, int version) @@ -370,10 +414,18 @@ static long privcmd_ioctl_mmap_batch(void __user *udata, int version) ret = -EINVAL; goto out; } + if (xen_feature(XENFEAT_auto_translated_physmap)) { + ret = alloc_empty_pages(vma, m.num); + if (ret < 0) { + up_write(&mm->mmap_sem); + goto out; + } + } state.domain = m.dom; state.vma = vma; state.va = m.addr; + state.index = 0; state.global_error = 0; state.err = err_array; @@ -442,6 +494,19 @@ static long privcmd_ioctl(struct file *file, return ret; } +static void privcmd_close(struct vm_area_struct *vma) +{ + struct page **pages = vma->vm_private_data; + int numpgs = (vma->vm_end - vma->vm_start) >> PAGE_SHIFT; + + if (!xen_feature(XENFEAT_auto_translated_physmap || !numpgs || !pages)) + return; + + xen_unmap_domain_mfn_range(vma, numpgs, pages); + free_xenballooned_pages(numpgs, pages); + kfree(pages); +} + static int privcmd_fault(struct vm_area_struct *vma, struct vm_fault *vmf) { printk(KERN_DEBUG "privcmd_fault: vma=%p %lx-%lx, pgoff=%lx, uv=%p\n", @@ -452,6 +517,7 @@ static int privcmd_fault(struct vm_area_struct *vma, struct vm_fault *vmf) } static struct vm_operations_struct privcmd_vm_ops = { + .close = privcmd_close, .fault = privcmd_fault }; @@ -469,7 +535,7 @@ static int privcmd_mmap(struct file *file, struct vm_area_struct *vma) static int privcmd_enforce_singleshot_mapping(struct vm_area_struct *vma) { - return (xchg(&vma->vm_private_data, (void *)1) == NULL); + return !cmpxchg(&vma->vm_private_data, NULL, PRIV_VMA_LOCKED); } const struct file_operations xen_privcmd_fops = { diff --git a/drivers/xen/xen-acpi-pad.c b/drivers/xen/xen-acpi-pad.c new file mode 100644 index 00000000000..da39191e727 --- /dev/null +++ b/drivers/xen/xen-acpi-pad.c @@ -0,0 +1,182 @@ +/* + * xen-acpi-pad.c - Xen pad interface + * + * Copyright (c) 2012, Intel Corporation. + * Author: Liu, Jinsong <jinsong.liu@intel.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + */ + +#include <linux/kernel.h> +#include <linux/types.h> +#include <acpi/acpi_bus.h> +#include <acpi/acpi_drivers.h> +#include <asm/xen/hypercall.h> +#include <xen/interface/version.h> +#include <xen/xen-ops.h> + +#define ACPI_PROCESSOR_AGGREGATOR_CLASS "acpi_pad" +#define ACPI_PROCESSOR_AGGREGATOR_DEVICE_NAME "Processor Aggregator" +#define ACPI_PROCESSOR_AGGREGATOR_NOTIFY 0x80 +static DEFINE_MUTEX(xen_cpu_lock); + +static int xen_acpi_pad_idle_cpus(unsigned int idle_nums) +{ + struct xen_platform_op op; + + op.cmd = XENPF_core_parking; + op.u.core_parking.type = XEN_CORE_PARKING_SET; + op.u.core_parking.idle_nums = idle_nums; + + return HYPERVISOR_dom0_op(&op); +} + +static int xen_acpi_pad_idle_cpus_num(void) +{ + struct xen_platform_op op; + + op.cmd = XENPF_core_parking; + op.u.core_parking.type = XEN_CORE_PARKING_GET; + + return HYPERVISOR_dom0_op(&op) + ?: op.u.core_parking.idle_nums; +} + +/* + * Query firmware how many CPUs should be idle + * return -1 on failure + */ +static int acpi_pad_pur(acpi_handle handle) +{ + struct acpi_buffer buffer = {ACPI_ALLOCATE_BUFFER, NULL}; + union acpi_object *package; + int num = -1; + + if (ACPI_FAILURE(acpi_evaluate_object(handle, "_PUR", NULL, &buffer))) + return num; + + if (!buffer.length || !buffer.pointer) + return num; + + package = buffer.pointer; + + if (package->type == ACPI_TYPE_PACKAGE && + package->package.count == 2 && + package->package.elements[0].integer.value == 1) /* rev 1 */ + num = package->package.elements[1].integer.value; + + kfree(buffer.pointer); + return num; +} + +/* Notify firmware how many CPUs are idle */ +static void acpi_pad_ost(acpi_handle handle, int stat, + uint32_t idle_nums) +{ + union acpi_object params[3] = { + {.type = ACPI_TYPE_INTEGER,}, + {.type = ACPI_TYPE_INTEGER,}, + {.type = ACPI_TYPE_BUFFER,}, + }; + struct acpi_object_list arg_list = {3, params}; + + params[0].integer.value = ACPI_PROCESSOR_AGGREGATOR_NOTIFY; + params[1].integer.value = stat; + params[2].buffer.length = 4; + params[2].buffer.pointer = (void *)&idle_nums; + acpi_evaluate_object(handle, "_OST", &arg_list, NULL); +} + +static void acpi_pad_handle_notify(acpi_handle handle) +{ + int idle_nums; + + mutex_lock(&xen_cpu_lock); + idle_nums = acpi_pad_pur(handle); + if (idle_nums < 0) { + mutex_unlock(&xen_cpu_lock); + return; + } + + idle_nums = xen_acpi_pad_idle_cpus(idle_nums) + ?: xen_acpi_pad_idle_cpus_num(); + if (idle_nums >= 0) + acpi_pad_ost(handle, 0, idle_nums); + mutex_unlock(&xen_cpu_lock); +} + +static void acpi_pad_notify(acpi_handle handle, u32 event, + void *data) +{ + switch (event) { + case ACPI_PROCESSOR_AGGREGATOR_NOTIFY: + acpi_pad_handle_notify(handle); + break; + default: + pr_warn("Unsupported event [0x%x]\n", event); + break; + } +} + +static int acpi_pad_add(struct acpi_device *device) +{ + acpi_status status; + + strcpy(acpi_device_name(device), ACPI_PROCESSOR_AGGREGATOR_DEVICE_NAME); + strcpy(acpi_device_class(device), ACPI_PROCESSOR_AGGREGATOR_CLASS); + + status = acpi_install_notify_handler(device->handle, + ACPI_DEVICE_NOTIFY, acpi_pad_notify, device); + if (ACPI_FAILURE(status)) + return -ENODEV; + + return 0; +} + +static int acpi_pad_remove(struct acpi_device *device, + int type) +{ + mutex_lock(&xen_cpu_lock); + xen_acpi_pad_idle_cpus(0); + mutex_unlock(&xen_cpu_lock); + + acpi_remove_notify_handler(device->handle, + ACPI_DEVICE_NOTIFY, acpi_pad_notify); + return 0; +} + +static const struct acpi_device_id pad_device_ids[] = { + {"ACPI000C", 0}, + {"", 0}, +}; + +static struct acpi_driver acpi_pad_driver = { + .name = "processor_aggregator", + .class = ACPI_PROCESSOR_AGGREGATOR_CLASS, + .ids = pad_device_ids, + .ops = { + .add = acpi_pad_add, + .remove = acpi_pad_remove, + }, +}; + +static int __init xen_acpi_pad_init(void) +{ + /* Only DOM0 is responsible for Xen acpi pad */ + if (!xen_initial_domain()) + return -ENODEV; + + /* Only Xen4.2 or later support Xen acpi pad */ + if (!xen_running_on_version_or_later(4, 2)) + return -ENODEV; + + return acpi_bus_register_driver(&acpi_pad_driver); +} +subsys_initcall(xen_acpi_pad_init); diff --git a/drivers/xen/xen-pciback/pci_stub.c b/drivers/xen/xen-pciback/pci_stub.c index 68dcc59cd28..cd50d251998 100644 --- a/drivers/xen/xen-pciback/pci_stub.c +++ b/drivers/xen/xen-pciback/pci_stub.c @@ -142,7 +142,8 @@ static struct pcistub_device *pcistub_device_find(int domain, int bus, if (psdev->dev != NULL && domain == pci_domain_nr(psdev->dev->bus) && bus == psdev->dev->bus->number - && PCI_DEVFN(slot, func) == psdev->dev->devfn) { + && slot == PCI_SLOT(psdev->dev->devfn) + && func == PCI_FUNC(psdev->dev->devfn)) { pcistub_device_get(psdev); goto out; } @@ -191,7 +192,8 @@ struct pci_dev *pcistub_get_pci_dev_by_slot(struct xen_pcibk_device *pdev, if (psdev->dev != NULL && domain == pci_domain_nr(psdev->dev->bus) && bus == psdev->dev->bus->number - && PCI_DEVFN(slot, func) == psdev->dev->devfn) { + && slot == PCI_SLOT(psdev->dev->devfn) + && func == PCI_FUNC(psdev->dev->devfn)) { found_dev = pcistub_device_get_pci_dev(pdev, psdev); break; } @@ -897,42 +899,35 @@ static struct pci_driver xen_pcibk_pci_driver = { static inline int str_to_slot(const char *buf, int *domain, int *bus, int *slot, int *func) { - int err; - char wc = '*'; + int parsed = 0; - err = sscanf(buf, " %x:%x:%x.%x", domain, bus, slot, func); - switch (err) { + switch (sscanf(buf, " %x:%x:%x.%x %n", domain, bus, slot, func, + &parsed)) { case 3: *func = -1; - err = sscanf(buf, " %x:%x:%x.%c", domain, bus, slot, &wc); + sscanf(buf, " %x:%x:%x.* %n", domain, bus, slot, &parsed); break; case 2: *slot = *func = -1; - err = sscanf(buf, " %x:%x:*.%c", domain, bus, &wc); - if (err >= 2) - ++err; + sscanf(buf, " %x:%x:*.* %n", domain, bus, &parsed); break; } - if (err == 4 && wc == '*') + if (parsed && !buf[parsed]) return 0; - else if (err < 0) - return -EINVAL; /* try again without domain */ *domain = 0; - wc = '*'; - err = sscanf(buf, " %x:%x.%x", bus, slot, func); - switch (err) { + switch (sscanf(buf, " %x:%x.%x %n", bus, slot, func, &parsed)) { case 2: *func = -1; - err = sscanf(buf, " %x:%x.%c", bus, slot, &wc); + sscanf(buf, " %x:%x.* %n", bus, slot, &parsed); break; case 1: *slot = *func = -1; - err = sscanf(buf, " %x:*.%c", bus, &wc) + 1; + sscanf(buf, " %x:*.* %n", bus, &parsed); break; } - if (err == 3 && wc == '*') + if (parsed && !buf[parsed]) return 0; return -EINVAL; @@ -941,13 +936,20 @@ static inline int str_to_slot(const char *buf, int *domain, int *bus, static inline int str_to_quirk(const char *buf, int *domain, int *bus, int *slot, int *func, int *reg, int *size, int *mask) { - int err; + int parsed = 0; - err = - sscanf(buf, " %04x:%02x:%02x.%d-%08x:%1x:%08x", domain, bus, slot, - func, reg, size, mask); - if (err == 7) + sscanf(buf, " %x:%x:%x.%x-%x:%x:%x %n", domain, bus, slot, func, + reg, size, mask, &parsed); + if (parsed && !buf[parsed]) return 0; + + /* try again without domain */ + *domain = 0; + sscanf(buf, " %x:%x.%x-%x:%x:%x %n", bus, slot, func, reg, size, + mask, &parsed); + if (parsed && !buf[parsed]) + return 0; + return -EINVAL; } @@ -955,7 +957,7 @@ static int pcistub_device_id_add(int domain, int bus, int slot, int func) { struct pcistub_device_id *pci_dev_id; unsigned long flags; - int rc = 0; + int rc = 0, devfn = PCI_DEVFN(slot, func); if (slot < 0) { for (slot = 0; !rc && slot < 32; ++slot) @@ -969,13 +971,24 @@ static int pcistub_device_id_add(int domain, int bus, int slot, int func) return rc; } + if (( +#if !defined(MODULE) /* pci_domains_supported is not being exported */ \ + || !defined(CONFIG_PCI_DOMAINS) + !pci_domains_supported ? domain : +#endif + domain < 0 || domain > 0xffff) + || bus < 0 || bus > 0xff + || PCI_SLOT(devfn) != slot + || PCI_FUNC(devfn) != func) + return -EINVAL; + pci_dev_id = kmalloc(sizeof(*pci_dev_id), GFP_KERNEL); if (!pci_dev_id) return -ENOMEM; pci_dev_id->domain = domain; pci_dev_id->bus = bus; - pci_dev_id->devfn = PCI_DEVFN(slot, func); + pci_dev_id->devfn = devfn; pr_debug(DRV_NAME ": wants to seize %04x:%02x:%02x.%d\n", domain, bus, slot, func); @@ -1016,14 +1029,18 @@ static int pcistub_device_id_remove(int domain, int bus, int slot, int func) return err; } -static int pcistub_reg_add(int domain, int bus, int slot, int func, int reg, - int size, int mask) +static int pcistub_reg_add(int domain, int bus, int slot, int func, + unsigned int reg, unsigned int size, + unsigned int mask) { int err = 0; struct pcistub_device *psdev; struct pci_dev *dev; struct config_field *field; + if (reg > 0xfff || (size < 4 && (mask >> (size * 8)))) + return -EINVAL; + psdev = pcistub_device_find(domain, bus, slot, func); if (!psdev) { err = -ENODEV; @@ -1254,13 +1271,11 @@ static ssize_t permissive_add(struct device_driver *drv, const char *buf, int err; struct pcistub_device *psdev; struct xen_pcibk_dev_data *dev_data; + err = str_to_slot(buf, &domain, &bus, &slot, &func); if (err) goto out; - if (slot < 0 || func < 0) { - err = -EINVAL; - goto out; - } + psdev = pcistub_device_find(domain, bus, slot, func); if (!psdev) { err = -ENODEV; @@ -1339,8 +1354,6 @@ static int __init pcistub_init(void) if (pci_devs_to_hide && *pci_devs_to_hide) { do { - char wc = '*'; - parsed = 0; err = sscanf(pci_devs_to_hide + pos, @@ -1349,51 +1362,48 @@ static int __init pcistub_init(void) switch (err) { case 3: func = -1; - err = sscanf(pci_devs_to_hide + pos, - " (%x:%x:%x.%c) %n", - &domain, &bus, &slot, &wc, - &parsed); + sscanf(pci_devs_to_hide + pos, + " (%x:%x:%x.*) %n", + &domain, &bus, &slot, &parsed); break; case 2: slot = func = -1; - err = sscanf(pci_devs_to_hide + pos, - " (%x:%x:*.%c) %n", - &domain, &bus, &wc, &parsed) + 1; + sscanf(pci_devs_to_hide + pos, + " (%x:%x:*.*) %n", + &domain, &bus, &parsed); break; } - if (err != 4 || wc != '*') { + if (!parsed) { domain = 0; - wc = '*'; err = sscanf(pci_devs_to_hide + pos, " (%x:%x.%x) %n", &bus, &slot, &func, &parsed); switch (err) { case 2: func = -1; - err = sscanf(pci_devs_to_hide + pos, - " (%x:%x.%c) %n", - &bus, &slot, &wc, - &parsed); + sscanf(pci_devs_to_hide + pos, + " (%x:%x.*) %n", + &bus, &slot, &parsed); break; case 1: slot = func = -1; - err = sscanf(pci_devs_to_hide + pos, - " (%x:*.%c) %n", - &bus, &wc, &parsed) + 1; + sscanf(pci_devs_to_hide + pos, + " (%x:*.*) %n", + &bus, &parsed); break; } - if (err != 3 || wc != '*') - goto parse_error; } + if (parsed <= 0) + goto parse_error; + err = pcistub_device_id_add(domain, bus, slot, func); if (err) goto out; - /* if parsed<=0, we've reached the end of the string */ pos += parsed; - } while (parsed > 0 && pci_devs_to_hide[pos]); + } while (pci_devs_to_hide[pos]); } /* If we're the first PCI Device Driver to register, we're the diff --git a/drivers/xen/xenbus/xenbus_xs.c b/drivers/xen/xenbus/xenbus_xs.c index acedeabe589..88e677b0de7 100644 --- a/drivers/xen/xenbus/xenbus_xs.c +++ b/drivers/xen/xenbus/xenbus_xs.c @@ -48,7 +48,6 @@ #include <xen/xenbus.h> #include <xen/xen.h> #include "xenbus_comms.h" -#include <asm/xen/hypervisor.h> struct xs_stored_msg { struct list_head list; |