diff options
Diffstat (limited to 'drivers/xen')
| -rw-r--r-- | drivers/xen/Kconfig | 3 | ||||
| -rw-r--r-- | drivers/xen/Makefile | 2 | ||||
| -rw-r--r-- | drivers/xen/biomerge.c | 13 | ||||
| -rw-r--r-- | drivers/xen/events.c | 610 | ||||
| -rw-r--r-- | drivers/xen/pci.c | 117 | ||||
| -rw-r--r-- | drivers/xen/xenbus/xenbus_client.c | 2 | ||||
| -rw-r--r-- | drivers/xen/xenbus/xenbus_probe.c | 33 | ||||
| -rw-r--r-- | drivers/xen/xenfs/Makefile | 3 | ||||
| -rw-r--r-- | drivers/xen/xenfs/privcmd.c | 404 | ||||
| -rw-r--r-- | drivers/xen/xenfs/super.c | 103 | ||||
| -rw-r--r-- | drivers/xen/xenfs/xenfs.h | 3 | ||||
| -rw-r--r-- | drivers/xen/xenfs/xenstored.c | 68 |
12 files changed, 1295 insertions, 66 deletions
diff --git a/drivers/xen/Kconfig b/drivers/xen/Kconfig index 60d71e9abe9f..6e6180ccd726 100644 --- a/drivers/xen/Kconfig +++ b/drivers/xen/Kconfig @@ -74,6 +74,7 @@ config XEN_PLATFORM_PCI config SWIOTLB_XEN def_bool y - depends on SWIOTLB + depends on PCI + select SWIOTLB endmenu diff --git a/drivers/xen/Makefile b/drivers/xen/Makefile index fcaf838f54be..eb8a78d77d9d 100644 --- a/drivers/xen/Makefile +++ b/drivers/xen/Makefile @@ -4,6 +4,7 @@ obj-y += xenbus/ nostackp := $(call cc-option, -fno-stack-protector) CFLAGS_features.o := $(nostackp) +obj-$(CONFIG_BLOCK) += biomerge.o obj-$(CONFIG_HOTPLUG_CPU) += cpu_hotplug.o obj-$(CONFIG_XEN_XENCOMM) += xencomm.o obj-$(CONFIG_XEN_BALLOON) += balloon.o @@ -12,3 +13,4 @@ obj-$(CONFIG_XENFS) += xenfs/ obj-$(CONFIG_XEN_SYS_HYPERVISOR) += sys-hypervisor.o obj-$(CONFIG_XEN_PLATFORM_PCI) += platform-pci.o obj-$(CONFIG_SWIOTLB_XEN) += swiotlb-xen.o +obj-$(CONFIG_XEN_DOM0) += pci.o diff --git a/drivers/xen/biomerge.c b/drivers/xen/biomerge.c new file mode 100644 index 000000000000..ba6eda4b5143 --- /dev/null +++ b/drivers/xen/biomerge.c @@ -0,0 +1,13 @@ +#include <linux/bio.h> +#include <linux/io.h> +#include <xen/page.h> + +bool xen_biovec_phys_mergeable(const struct bio_vec *vec1, + const struct bio_vec *vec2) +{ + unsigned long mfn1 = pfn_to_mfn(page_to_pfn(vec1->bv_page)); + unsigned long mfn2 = pfn_to_mfn(page_to_pfn(vec2->bv_page)); + + return __BIOVEC_PHYS_MERGEABLE(vec1, vec2) && + ((mfn1 == mfn2) || ((mfn1+1) == mfn2)); +} diff --git a/drivers/xen/events.c b/drivers/xen/events.c index 7d24b0d94ed4..97612f548a8e 100644 --- a/drivers/xen/events.c +++ b/drivers/xen/events.c @@ -16,7 +16,7 @@ * (typically dom0). * 2. VIRQs, typically used for timers. These are per-cpu events. * 3. IPIs. - * 4. Hardware interrupts. Not supported at present. + * 4. PIRQs - Hardware interrupts. * * Jeremy Fitzhardinge <jeremy@xensource.com>, XenSource Inc, 2007 */ @@ -28,12 +28,16 @@ #include <linux/string.h> #include <linux/bootmem.h> #include <linux/slab.h> +#include <linux/irqnr.h> +#include <linux/pci.h> #include <asm/desc.h> #include <asm/ptrace.h> #include <asm/irq.h> #include <asm/idle.h> +#include <asm/io_apic.h> #include <asm/sync_bitops.h> +#include <asm/xen/pci.h> #include <asm/xen/hypercall.h> #include <asm/xen/hypervisor.h> @@ -73,7 +77,8 @@ enum xen_irq_type { * event channel - irq->event channel mapping * cpu - cpu this event channel is bound to * index - type-specific information: - * PIRQ - vector, with MSB being "needs EIO" + * PIRQ - vector, with MSB being "needs EIO", or physical IRQ of the HVM + * guest, or GSI (real passthrough IRQ) of the device. * VIRQ - virq number * IPI - IPI vector * EVTCHN - @@ -88,21 +93,30 @@ struct irq_info unsigned short virq; enum ipi_vector ipi; struct { + unsigned short pirq; unsigned short gsi; - unsigned short vector; + unsigned char vector; + unsigned char flags; } pirq; } u; }; +#define PIRQ_NEEDS_EOI (1 << 0) +#define PIRQ_SHAREABLE (1 << 1) -static struct irq_info irq_info[NR_IRQS]; +static struct irq_info *irq_info; +static int *pirq_to_irq; +static int nr_pirqs; -static int evtchn_to_irq[NR_EVENT_CHANNELS] = { - [0 ... NR_EVENT_CHANNELS-1] = -1 -}; +static int *evtchn_to_irq; struct cpu_evtchn_s { unsigned long bits[NR_EVENT_CHANNELS/BITS_PER_LONG]; }; -static struct cpu_evtchn_s *cpu_evtchn_mask_p; + +static __initdata struct cpu_evtchn_s init_evtchn_mask = { + .bits[0 ... (NR_EVENT_CHANNELS/BITS_PER_LONG)-1] = ~0ul, +}; +static struct cpu_evtchn_s *cpu_evtchn_mask_p = &init_evtchn_mask; + static inline unsigned long *cpu_evtchn_mask(int cpu) { return cpu_evtchn_mask_p[cpu].bits; @@ -113,6 +127,7 @@ static inline unsigned long *cpu_evtchn_mask(int cpu) static struct irq_chip xen_dynamic_chip; static struct irq_chip xen_percpu_chip; +static struct irq_chip xen_pirq_chip; /* Constructor for packed IRQ information. */ static struct irq_info mk_unbound_info(void) @@ -138,11 +153,12 @@ static struct irq_info mk_virq_info(unsigned short evtchn, unsigned short virq) .cpu = 0, .u.virq = virq }; } -static struct irq_info mk_pirq_info(unsigned short evtchn, +static struct irq_info mk_pirq_info(unsigned short evtchn, unsigned short pirq, unsigned short gsi, unsigned short vector) { return (struct irq_info) { .type = IRQT_PIRQ, .evtchn = evtchn, - .cpu = 0, .u.pirq = { .gsi = gsi, .vector = vector } }; + .cpu = 0, + .u.pirq = { .pirq = pirq, .gsi = gsi, .vector = vector } }; } /* @@ -184,6 +200,16 @@ static unsigned virq_from_irq(unsigned irq) return info->u.virq; } +static unsigned pirq_from_irq(unsigned irq) +{ + struct irq_info *info = info_for_irq(irq); + + BUG_ON(info == NULL); + BUG_ON(info->type != IRQT_PIRQ); + + return info->u.pirq.pirq; +} + static unsigned gsi_from_irq(unsigned irq) { struct irq_info *info = info_for_irq(irq); @@ -225,6 +251,15 @@ static unsigned int cpu_from_evtchn(unsigned int evtchn) return ret; } +static bool pirq_needs_eoi(unsigned irq) +{ + struct irq_info *info = info_for_irq(irq); + + BUG_ON(info->type != IRQT_PIRQ); + + return info->u.pirq.flags & PIRQ_NEEDS_EOI; +} + static inline unsigned long active_evtchns(unsigned int cpu, struct shared_info *sh, unsigned int idx) @@ -261,7 +296,7 @@ static void init_evtchn_cpu_bindings(void) } #endif - memset(cpu_evtchn_mask(0), ~0, sizeof(cpu_evtchn_mask(0))); + memset(cpu_evtchn_mask(0), ~0, sizeof(struct cpu_evtchn_s)); } static inline void clear_evtchn(int port) @@ -336,12 +371,40 @@ static void unmask_evtchn(int port) put_cpu(); } +static int get_nr_hw_irqs(void) +{ + int ret = 1; + +#ifdef CONFIG_X86_IO_APIC + ret = get_nr_irqs_gsi(); +#endif + + return ret; +} + +/* callers of this function should make sure that PHYSDEVOP_get_nr_pirqs + * succeeded otherwise nr_pirqs won't hold the right value */ +static int find_unbound_pirq(void) +{ + int i; + for (i = nr_pirqs-1; i >= 0; i--) { + if (pirq_to_irq[i] < 0) + return i; + } + return -1; +} + static int find_unbound_irq(void) { struct irq_data *data; int irq, res; + int start = get_nr_hw_irqs(); - for (irq = 0; irq < nr_irqs; irq++) { + if (start == nr_irqs) + goto no_irqs; + + /* nr_irqs is a magic value. Must not use it.*/ + for (irq = nr_irqs-1; irq > start; irq--) { data = irq_get_irq_data(irq); /* only 0->15 have init'd desc; handle irq > 16 */ if (!data) @@ -354,8 +417,8 @@ static int find_unbound_irq(void) return irq; } - if (irq == nr_irqs) - panic("No available IRQ to bind to: increase nr_irqs!\n"); + if (irq == start) + goto no_irqs; res = irq_alloc_desc_at(irq, 0); @@ -363,6 +426,357 @@ static int find_unbound_irq(void) return -1; return irq; + +no_irqs: + panic("No available IRQ to bind to: increase nr_irqs!\n"); +} + +static bool identity_mapped_irq(unsigned irq) +{ + /* identity map all the hardware irqs */ + return irq < get_nr_hw_irqs(); +} + +static void pirq_unmask_notify(int irq) +{ + struct physdev_eoi eoi = { .irq = pirq_from_irq(irq) }; + + if (unlikely(pirq_needs_eoi(irq))) { + int rc = HYPERVISOR_physdev_op(PHYSDEVOP_eoi, &eoi); + WARN_ON(rc); + } +} + +static void pirq_query_unmask(int irq) +{ + struct physdev_irq_status_query irq_status; + struct irq_info *info = info_for_irq(irq); + + BUG_ON(info->type != IRQT_PIRQ); + + irq_status.irq = pirq_from_irq(irq); + if (HYPERVISOR_physdev_op(PHYSDEVOP_irq_status_query, &irq_status)) + irq_status.flags = 0; + + info->u.pirq.flags &= ~PIRQ_NEEDS_EOI; + if (irq_status.flags & XENIRQSTAT_needs_eoi) + info->u.pirq.flags |= PIRQ_NEEDS_EOI; +} + +static bool probing_irq(int irq) +{ + struct irq_desc *desc = irq_to_desc(irq); + + return desc && desc->action == NULL; +} + +static unsigned int startup_pirq(unsigned int irq) +{ + struct evtchn_bind_pirq bind_pirq; + struct irq_info *info = info_for_irq(irq); + int evtchn = evtchn_from_irq(irq); + int rc; + + BUG_ON(info->type != IRQT_PIRQ); + + if (VALID_EVTCHN(evtchn)) + goto out; + + bind_pirq.pirq = pirq_from_irq(irq); + /* NB. We are happy to share unless we are probing. */ + bind_pirq.flags = info->u.pirq.flags & PIRQ_SHAREABLE ? + BIND_PIRQ__WILL_SHARE : 0; + rc = HYPERVISOR_event_channel_op(EVTCHNOP_bind_pirq, &bind_pirq); + if (rc != 0) { + if (!probing_irq(irq)) + printk(KERN_INFO "Failed to obtain physical IRQ %d\n", + irq); + return 0; + } + evtchn = bind_pirq.port; + + pirq_query_unmask(irq); + + evtchn_to_irq[evtchn] = irq; + bind_evtchn_to_cpu(evtchn, 0); + info->evtchn = evtchn; + +out: + unmask_evtchn(evtchn); + pirq_unmask_notify(irq); + + return 0; +} + +static void shutdown_pirq(unsigned int irq) +{ + struct evtchn_close close; + struct irq_info *info = info_for_irq(irq); + int evtchn = evtchn_from_irq(irq); + + BUG_ON(info->type != IRQT_PIRQ); + + if (!VALID_EVTCHN(evtchn)) + return; + + mask_evtchn(evtchn); + + close.port = evtchn; + if (HYPERVISOR_event_channel_op(EVTCHNOP_close, &close) != 0) + BUG(); + + bind_evtchn_to_cpu(evtchn, 0); + evtchn_to_irq[evtchn] = -1; + info->evtchn = 0; +} + +static void enable_pirq(unsigned int irq) +{ + startup_pirq(irq); +} + +static void disable_pirq(unsigned int irq) +{ +} + +static void ack_pirq(unsigned int irq) +{ + int evtchn = evtchn_from_irq(irq); + + move_native_irq(irq); + + if (VALID_EVTCHN(evtchn)) { + mask_evtchn(evtchn); + clear_evtchn(evtchn); + } +} + +static void end_pirq(unsigned int irq) +{ + int evtchn = evtchn_from_irq(irq); + struct irq_desc *desc = irq_to_desc(irq); + + if (WARN_ON(!desc)) + return; + + if ((desc->status & (IRQ_DISABLED|IRQ_PENDING)) == + (IRQ_DISABLED|IRQ_PENDING)) { + shutdown_pirq(irq); + } else if (VALID_EVTCHN(evtchn)) { + unmask_evtchn(evtchn); + pirq_unmask_notify(irq); + } +} + +static int find_irq_by_gsi(unsigned gsi) +{ + int irq; + + for (irq = 0; irq < nr_irqs; irq++) { + struct irq_info *info = info_for_irq(irq); + + if (info == NULL || info->type != IRQT_PIRQ) + continue; + + if (gsi_from_irq(irq) == gsi) + return irq; + } + + return -1; +} + +int xen_allocate_pirq(unsigned gsi, int shareable, char *name) +{ + return xen_map_pirq_gsi(gsi, gsi, shareable, name); +} + +/* xen_map_pirq_gsi might allocate irqs from the top down, as a + * consequence don't assume that the irq number returned has a low value + * or can be used as a pirq number unless you know otherwise. + * + * One notable exception is when xen_map_pirq_gsi is called passing an + * hardware gsi as argument, in that case the irq number returned + * matches the gsi number passed as second argument. + * + * Note: We don't assign an event channel until the irq actually started + * up. Return an existing irq if we've already got one for the gsi. + */ +int xen_map_pirq_gsi(unsigned pirq, unsigned gsi, int shareable, char *name) +{ + int irq = 0; + struct physdev_irq irq_op; + + spin_lock(&irq_mapping_update_lock); + + if ((pirq > nr_pirqs) || (gsi > nr_irqs)) { + printk(KERN_WARNING "xen_map_pirq_gsi: %s %s is incorrect!\n", + pirq > nr_pirqs ? "nr_pirqs" :"", + gsi > nr_irqs ? "nr_irqs" : ""); + goto out; + } + + irq = find_irq_by_gsi(gsi); + if (irq != -1) { + printk(KERN_INFO "xen_map_pirq_gsi: returning irq %d for gsi %u\n", + irq, gsi); + goto out; /* XXX need refcount? */ + } + + /* If we are a PV guest, we don't have GSIs (no ACPI passed). Therefore + * we are using the !xen_initial_domain() to drop in the function.*/ + if (identity_mapped_irq(gsi) || (!xen_initial_domain() && + xen_pv_domain())) { + irq = gsi; + irq_alloc_desc_at(irq, 0); + } else + irq = find_unbound_irq(); + + set_irq_chip_and_handler_name(irq, &xen_pirq_chip, + handle_level_irq, name); + + irq_op.irq = irq; + irq_op.vector = 0; + + /* Only the privileged domain can do this. For non-priv, the pcifront + * driver provides a PCI bus that does the call to do exactly + * this in the priv domain. */ + if (xen_initial_domain() && + HYPERVISOR_physdev_op(PHYSDEVOP_alloc_irq_vector, &irq_op)) { + irq_free_desc(irq); + irq = -ENOSPC; + goto out; + } + + irq_info[irq] = mk_pirq_info(0, pirq, gsi, irq_op.vector); + irq_info[irq].u.pirq.flags |= shareable ? PIRQ_SHAREABLE : 0; + pirq_to_irq[pirq] = irq; + +out: + spin_unlock(&irq_mapping_update_lock); + + return irq; +} + +#ifdef CONFIG_PCI_MSI +#include <linux/msi.h> +#include "../pci/msi.h" + +void xen_allocate_pirq_msi(char *name, int *irq, int *pirq) +{ + spin_lock(&irq_mapping_update_lock); + + *irq = find_unbound_irq(); + if (*irq == -1) + goto out; + + *pirq = find_unbound_pirq(); + if (*pirq == -1) + goto out; + + set_irq_chip_and_handler_name(*irq, &xen_pirq_chip, + handle_level_irq, name); + + irq_info[*irq] = mk_pirq_info(0, *pirq, 0, 0); + pirq_to_irq[*pirq] = *irq; + +out: + spin_unlock(&irq_mapping_update_lock); +} + +int xen_create_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc, int type) +{ + int irq = -1; + struct physdev_map_pirq map_irq; + int rc; + int pos; + u32 table_offset, bir; + + memset(&map_irq, 0, sizeof(map_irq)); + map_irq.domid = DOMID_SELF; + map_irq.type = MAP_PIRQ_TYPE_MSI; + map_irq.index = -1; + map_irq.pirq = -1; + map_irq.bus = dev->bus->number; + map_irq.devfn = dev->devfn; + + if (type == PCI_CAP_ID_MSIX) { + pos = pci_find_capability(dev, PCI_CAP_ID_MSIX); + + pci_read_config_dword(dev, msix_table_offset_reg(pos), + &table_offset); + bir = (u8)(table_offset & PCI_MSIX_FLAGS_BIRMASK); + + map_irq.table_base = pci_resource_start(dev, bir); + map_irq.entry_nr = msidesc->msi_attrib.entry_nr; + } + + spin_lock(&irq_mapping_update_lock); + + irq = find_unbound_irq(); + + if (irq == -1) + goto out; + + rc = HYPERVISOR_physdev_op(PHYSDEVOP_map_pirq, &map_irq); + if (rc) { + printk(KERN_WARNING "xen map irq failed %d\n", rc); + + irq_free_desc(irq); + + irq = -1; + goto out; + } + irq_info[irq] = mk_pirq_info(0, map_irq.pirq, 0, map_irq.index); + + set_irq_chip_and_handler_name(irq, &xen_pirq_chip, + handle_level_irq, + (type == PCI_CAP_ID_MSIX) ? "msi-x":"msi"); + +out: + spin_unlock(&irq_mapping_update_lock); + return irq; +} +#endif + +int xen_destroy_irq(int irq) +{ + struct irq_desc *desc; + struct physdev_unmap_pirq unmap_irq; + struct irq_info *info = info_for_irq(irq); + int rc = -ENOENT; + + spin_lock(&irq_mapping_update_lock); + + desc = irq_to_desc(irq); + if (!desc) + goto out; + + if (xen_initial_domain()) { + unmap_irq.pirq = info->u.pirq.gsi; + unmap_irq.domid = DOMID_SELF; + rc = HYPERVISOR_physdev_op(PHYSDEVOP_unmap_pirq, &unmap_irq); + if (rc) { + printk(KERN_WARNING "unmap irq failed %d\n", rc); + goto out; + } + } + irq_info[irq] = mk_unbound_info(); + + irq_free_desc(irq); + +out: + spin_unlock(&irq_mapping_update_lock); + return rc; +} + +int xen_vector_from_irq(unsigned irq) +{ + return vector_from_irq(irq); +} + +int xen_gsi_from_irq(unsigned irq) +{ + return gsi_from_irq(irq); } int bind_evtchn_to_irq(unsigned int evtchn) @@ -377,7 +791,7 @@ int bind_evtchn_to_irq(unsigned int evtchn) irq = find_unbound_irq(); set_irq_chip_and_handler_name(irq, &xen_dynamic_chip, - handle_edge_irq, "event"); + handle_fasteoi_irq, "event"); evtchn_to_irq[evtchn] = irq; irq_info[irq] = mk_evtchn_info(evtchn); @@ -425,7 +839,7 @@ static int bind_ipi_to_irq(unsigned int ipi, unsigned int cpu) } -static int bind_virq_to_irq(unsigned int virq, unsigned int cpu) +int bind_virq_to_irq(unsigned int virq, unsigned int cpu) { struct evtchn_bind_virq bind_virq; int evtchn, irq; @@ -435,6 +849,11 @@ static int bind_virq_to_irq(unsigned int virq, unsigned int cpu) irq = per_cpu(virq_to_irq, cpu)[virq]; if (irq == -1) { + irq = find_unbound_irq(); + + set_irq_chip_and_handler_name(irq, &xen_percpu_chip, + handle_percpu_irq, "virq"); + bind_virq.virq = virq; bind_virq.vcpu = cpu; if (HYPERVISOR_event_channel_op(EVTCHNOP_bind_virq, @@ -442,11 +861,6 @@ static int bind_virq_to_irq(unsigned int virq, unsigned int cpu) BUG(); evtchn = bind_virq.port; - irq = find_unbound_irq(); - - set_irq_chip_and_handler_name(irq, &xen_percpu_chip, - handle_percpu_irq, "virq"); - evtchn_to_irq[evtchn] = irq; irq_info[irq] = mk_virq_info(evtchn, virq); @@ -578,41 +992,75 @@ irqreturn_t xen_debug_interrupt(int irq, void *dev_id) { struct shared_info *sh = HYPERVISOR_shared_info; int cpu = smp_processor_id(); + unsigned long *cpu_evtchn = cpu_evtchn_mask(cpu); int i; unsigned long flags; static DEFINE_SPINLOCK(debug_lock); + struct vcpu_info *v; spin_lock_irqsave(&debug_lock, flags); - printk("vcpu %d\n ", cpu); + printk("\nvcpu %d\n ", cpu); for_each_online_cpu(i) { - struct vcpu_info *v = per_cpu(xen_vcpu, i); - printk("%d: masked=%d pending=%d event_sel %08lx\n ", i, - (get_irq_regs() && i == cpu) ? xen_irqs_disabled(get_irq_regs()) : v->evtchn_upcall_mask, - v->evtchn_upcall_pending, - v->evtchn_pending_sel); + int pending; + v = per_cpu(xen_vcpu, i); + pending = (get_irq_regs() && i == cpu) + ? xen_irqs_disabled(get_irq_regs()) + : v->evtchn_upcall_mask; + printk("%d: masked=%d pending=%d event_sel %0*lx\n ", i, + pending, v->evtchn_upcall_pending, + (int)(sizeof(v->evtchn_pending_sel)*2), + v->evtchn_pending_sel); + } + v = per_cpu(xen_vcpu, cpu); + + printk("\npending:\n "); + for (i = ARRAY_SIZE(sh->evtchn_pending)-1; i >= 0; i--) + printk("%0*lx%s", (int)sizeof(sh->evtchn_pending[0])*2, + sh->evtchn_pending[i], + i % 8 == 0 ? "\n " : " "); + printk("\nglobal mask:\n "); + for (i = ARRAY_SIZE(sh->evtchn_mask)-1; i >= 0; i--) + printk("%0*lx%s", + (int)(sizeof(sh->evtchn_mask[0])*2), + sh->evtchn_mask[i], + i % 8 == 0 ? "\n " : " "); + + printk("\nglobally unmasked:\n "); + for (i = ARRAY_SIZE(sh->evtchn_mask)-1; i >= 0; i--) + printk("%0*lx%s", (int)(sizeof(sh->evtchn_mask[0])*2), + sh->evtchn_pending[i] & ~sh->evtchn_mask[i], + i % 8 == 0 ? "\n " : " "); + + printk("\nlocal cpu%d mask:\n ", cpu); + for (i = (NR_EVENT_CHANNELS/BITS_PER_LONG)-1; i >= 0; i--) + printk("%0*lx%s", (int)(sizeof(cpu_evtchn[0])*2), + cpu_evtchn[i], + i % 8 == 0 ? "\n " : " "); + + printk("\nlocally unmasked:\n "); + for (i = ARRAY_SIZE(sh->evtchn_mask)-1; i >= 0; i--) { + unsigned long pending = sh->evtchn_pending[i] + & ~sh->evtchn_mask[i] + & cpu_evtchn[i]; + printk("%0*lx%s", (int)(sizeof(sh->evtchn_mask[0])*2), + pending, i % 8 == 0 ? "\n " : " "); } - printk("pending:\n "); - for(i = ARRAY_SIZE(sh->evtchn_pending)-1; i >= 0; i--) - printk("%08lx%s", sh->evtchn_pending[i], - i % 8 == 0 ? "\n " : " "); - printk("\nmasks:\n "); - for(i = ARRAY_SIZE(sh->evtchn_mask)-1; i >= 0; i--) - printk("%08lx%s", sh->evtchn_mask[i], - i % 8 == 0 ? "\n " : " "); - - printk("\nunmasked:\n "); - for(i = ARRAY_SIZE(sh->evtchn_mask)-1; i >= 0; i--) - printk("%08lx%s", sh->evtchn_pending[i] & ~sh->evtchn_mask[i], - i % 8 == 0 ? "\n " : " "); printk("\npending list:\n"); - for(i = 0; i < NR_EVENT_CHANNELS; i++) { + for (i = 0; i < NR_EVENT_CHANNELS; i++) { if (sync_test_bit(i, sh->evtchn_pending)) { - printk(" %d: event %d -> irq %d\n", + int word_idx = i / BITS_PER_LONG; + printk(" %d: event %d -> irq %d%s%s%s\n", cpu_from_evtchn(i), i, - evtchn_to_irq[i]); + evtchn_to_irq[i], + sync_test_bit(word_idx, &v->evtchn_pending_sel) + ? "" : " l2-clear", + !sync_test_bit(i, sh->evtchn_mask) + ? "" : " globally-masked", + sync_test_bit(i, cpu_evtchn) + ? "" : " locally-masked"); } } @@ -663,6 +1111,9 @@ static void __xen_evtchn_do_upcall(void) int irq = evtchn_to_irq[port]; struct irq_desc *desc; + mask_evtchn(port); + clear_evtchn(port); + if (irq != -1) { desc = irq_to_desc(irq); if (desc) @@ -800,10 +1251,10 @@ static void ack_dynirq(unsigned int irq) { int evtchn = evtchn_from_irq(irq); - move_native_irq(irq); + move_masked_irq(irq); if (VALID_EVTCHN(evtchn)) - clear_evtchn(evtchn); + unmask_evtchn(evtchn); } static int retrigger_dynirq(unsigned int irq) @@ -891,7 +1342,7 @@ void xen_clear_irq_pending(int irq) if (VALID_EVTCHN(evtchn)) clear_evtchn(evtchn); } - +EXPORT_SYMBOL(xen_clear_irq_pending); void xen_set_irq_pending(int irq) { int evtchn = evtchn_from_irq(irq); @@ -911,9 +1362,9 @@ bool xen_test_irq_pending(int irq) return ret; } -/* Poll waiting for an irq to become pending. In the usual case, the - irq will be disabled so it won't deliver an interrupt. */ -void xen_poll_irq(int irq) +/* Poll waiting for an irq to become pending with timeout. In the usual case, + * the irq will be disabled so it won't deliver an interrupt. */ +void xen_poll_irq_timeout(int irq, u64 timeout) { evtchn_port_t evtchn = evtchn_from_irq(irq); @@ -921,13 +1372,20 @@ void xen_poll_irq(int irq) struct sched_poll poll; poll.nr_ports = 1; - poll.timeout = 0; + poll.timeout = timeout; set_xen_guest_handle(poll.ports, &evtchn); if (HYPERVISOR_sched_op(SCHEDOP_poll, &poll) != 0) BUG(); } } +EXPORT_SYMBOL(xen_poll_irq_timeout); +/* Poll waiting for an irq to become pending. In the usual case, the + * irq will be disabled so it won't deliver an interrupt. */ +void xen_poll_irq(int irq) +{ + xen_poll_irq_timeout(irq, 0 /* no timeout */); +} void xen_irq_resume(void) { @@ -959,8 +1417,28 @@ static struct irq_chip xen_dynamic_chip __read_mostly = { .mask = disable_dynirq, .unmask = enable_dynirq, - .ack = ack_dynirq, + .eoi = ack_dynirq, + .set_affinity = set_affinity_irq, + .retrigger = retrigger_dynirq, +}; + +static struct irq_chip xen_pirq_chip __read_mostly = { + .name = "xen-pirq", + + .startup = startup_pirq, + .shutdown = shutdown_pirq, + + .enable = enable_pirq, + .unmask = enable_pirq, + + .disable = disable_pirq, + .mask = disable_pirq, + + .ack = ack_pirq, + .end = end_pirq, + .set_affinity = set_affinity_irq, + .retrigger = retrigger_dynirq, }; @@ -1014,11 +1492,32 @@ void xen_callback_vector(void) {} void __init xen_init_IRQ(void) { - int i; + int i, rc; + struct physdev_nr_pirqs op_nr_pirqs; cpu_evtchn_mask_p = kcalloc(nr_cpu_ids, sizeof(struct cpu_evtchn_s), GFP_KERNEL); - BUG_ON(cpu_evtchn_mask_p == NULL); + irq_info = kcalloc(nr_irqs, sizeof(*irq_info), GFP_KERNEL); + + rc = HYPERVISOR_physdev_op(PHYSDEVOP_get_nr_pirqs, &op_nr_pirqs); + if (rc < 0) { + nr_pirqs = nr_irqs; + if (rc != -ENOSYS) + printk(KERN_WARNING "PHYSDEVOP_get_nr_pirqs returned rc=%d\n", rc); + } else { + if (xen_pv_domain() && !xen_initial_domain()) + nr_pirqs = max((int)op_nr_pirqs.nr_pirqs, nr_irqs); + else + nr_pirqs = op_nr_pirqs.nr_pirqs; + } + pirq_to_irq = kcalloc(nr_pirqs, sizeof(*pirq_to_irq), GFP_KERNEL); + for (i = 0; i < nr_pirqs; i++) + pirq_to_irq[i] = -1; + + evtchn_to_irq = kcalloc(NR_EVENT_CHANNELS, sizeof(*evtchn_to_irq), + GFP_KERNEL); + for (i = 0; i < NR_EVENT_CHANNELS; i++) + evtchn_to_irq[i] = -1; init_evtchn_cpu_bindings(); @@ -1029,7 +1528,12 @@ void __init xen_init_IRQ(void) if (xen_hvm_domain()) { xen_callback_vector(); native_init_IRQ(); + /* pci_xen_hvm_init must be called after native_init_IRQ so that + * __acpi_register_gsi can point at the right function */ + pci_xen_hvm_init(); } else { irq_ctx_init(smp_processor_id()); + if (xen_initial_domain()) + xen_setup_pirqs(); } } diff --git a/drivers/xen/pci.c b/drivers/xen/pci.c new file mode 100644 index 000000000000..cef4bafc07dc --- /dev/null +++ b/drivers/xen/pci.c @@ -0,0 +1,117 @@ +/* + * Copyright (c) 2009, Intel Corporation. + * + * 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. + * + * You should have received a copy of the GNU General Public License along with + * this program; if not, write to the Free Software Foundation, Inc., 59 Temple + * Place - Suite 330, Boston, MA 02111-1307 USA. + * + * Author: Weidong Han <weidong.han@intel.com> + */ + +#include <linux/pci.h> +#include <xen/xen.h> +#include <xen/interface/physdev.h> +#include <xen/interface/xen.h> + +#include <asm/xen/hypervisor.h> +#include <asm/xen/hypercall.h> +#include "../pci/pci.h" + +static int xen_add_device(struct device *dev) +{ + int r; + struct pci_dev *pci_dev = to_pci_dev(dev); + +#ifdef CONFIG_PCI_IOV + if (pci_dev->is_virtfn) { + struct physdev_manage_pci_ext manage_pci_ext = { + .bus = pci_dev->bus->number, + .devfn = pci_dev->devfn, + .is_virtfn = 1, + .physfn.bus = pci_dev->physfn->bus->number, + .physfn.devfn = pci_dev->physfn->devfn, + }; + + r = HYPERVISOR_physdev_op(PHYSDEVOP_manage_pci_add_ext, + &manage_pci_ext); + } else +#endif + if (pci_ari_enabled(pci_dev->bus) && PCI_SLOT(pci_dev->devfn)) { + struct physdev_manage_pci_ext manage_pci_ext = { + .bus = pci_dev->bus->number, + .devfn = pci_dev->devfn, + .is_extfn = 1, + }; + + r = HYPERVISOR_physdev_op(PHYSDEVOP_manage_pci_add_ext, + &manage_pci_ext); + } else { + struct physdev_manage_pci manage_pci = { + .bus = pci_dev->bus->number, + .devfn = pci_dev->devfn, + }; + + r = HYPERVISOR_physdev_op(PHYSDEVOP_manage_pci_add, + &manage_pci); + } + + return r; +} + +static int xen_remove_device(struct device *dev) +{ + int r; + struct pci_dev *pci_dev = to_pci_dev(dev); + struct physdev_manage_pci manage_pci; + + manage_pci.bus = pci_dev->bus->number; + manage_pci.devfn = pci_dev->devfn; + + r = HYPERVISOR_physdev_op(PHYSDEVOP_manage_pci_remove, + &manage_pci); + + return r; +} + +static int xen_pci_notifier(struct notifier_block *nb, + unsigned long action, void *data) +{ + struct device *dev = data; + int r = 0; + + switch (action) { + case BUS_NOTIFY_ADD_DEVICE: + r = xen_add_device(dev); + break; + case BUS_NOTIFY_DEL_DEVICE: + r = xen_remove_device(dev); + break; + default: + break; + } + + return r; +} + +struct notifier_block device_nb = { + .notifier_call = xen_pci_notifier, +}; + +static int __init register_xen_pci_notifier(void) +{ + if (!xen_initial_domain()) + return 0; + + return bus_register_notifier(&pci_bus_type, &device_nb); +} + +arch_initcall(register_xen_pci_notifier); diff --git a/drivers/xen/xenbus/xenbus_client.c b/drivers/xen/xenbus/xenbus_client.c index 7e49527189b6..cdacf923e073 100644 --- a/drivers/xen/xenbus/xenbus_client.c +++ b/drivers/xen/xenbus/xenbus_client.c @@ -50,6 +50,8 @@ const char *xenbus_strstate(enum xenbus_state state) [ XenbusStateConnected ] = "Connected", [ XenbusStateClosing ] = "Closing", [ XenbusStateClosed ] = "Closed", + [XenbusStateReconfiguring] = "Reconfiguring", + [XenbusStateReconfigured] = "Reconfigured", }; return (state < ARRAY_SIZE(name)) ? name[state] : "INVALID"; } diff --git a/drivers/xen/xenbus/xenbus_probe.c b/drivers/xen/xenbus/xenbus_probe.c index d409495876f1..deb9c4ba3a93 100644 --- a/drivers/xen/xenbus/xenbus_probe.c +++ b/drivers/xen/xenbus/xenbus_probe.c @@ -64,9 +64,11 @@ int xen_store_evtchn; -EXPORT_SYMBOL(xen_store_evtchn); +EXPORT_SYMBOL_GPL(xen_store_evtchn); struct xenstore_domain_interface *xen_store_interface; +EXPORT_SYMBOL_GPL(xen_store_interface); + static unsigned long xen_store_mfn; static BLOCKING_NOTIFIER_HEAD(xenstore_chain); @@ -801,6 +803,7 @@ device_initcall(xenbus_probe_initcall); static int __init xenbus_init(void) { int err = 0; + unsigned long page = 0; DPRINTK(""); @@ -821,7 +824,31 @@ static int __init xenbus_init(void) * Domain0 doesn't have a store_evtchn or store_mfn yet. */ if (xen_initial_domain()) { - /* dom0 not yet supported */ + struct evtchn_alloc_unbound alloc_unbound; + + /* Allocate Xenstore page */ + page = get_zeroed_page(GFP_KERNEL); + if (!page) + goto out_error; + + xen_store_mfn = xen_start_info->store_mfn = + pfn_to_mfn(virt_to_phys((void *)page) >> + PAGE_SHIFT); + + /* Next allocate a local port which xenstored can bind to */ + alloc_unbound.dom = DOMID_SELF; + alloc_unbound.remote_dom = 0; + + err = HYPERVISOR_event_channel_op(EVTCHNOP_alloc_unbound, + &alloc_unbound); + if (err == -ENOSYS) + goto out_error; + + BUG_ON(err); + xen_store_evtchn = xen_start_info->store_evtchn = + alloc_unbound.port; + + xen_store_interface = mfn_to_virt(xen_store_mfn); } else { if (xen_hvm_domain()) { uint64_t v = 0; @@ -867,6 +894,8 @@ static int __init xenbus_init(void) bus_unregister(&xenbus_frontend.bus); out_error: + if (page != 0) + free_page(page); return err; } diff --git a/drivers/xen/xenfs/Makefile b/drivers/xen/xenfs/Makefile index 25275c3bbdff..4fde9440fe1f 100644 --- a/drivers/xen/xenfs/Makefile +++ b/drivers/xen/xenfs/Makefile @@ -1,3 +1,4 @@ obj-$(CONFIG_XENFS) += xenfs.o -xenfs-objs = super.o xenbus.o
\ No newline at end of file +xenfs-y = super.o xenbus.o privcmd.o +xenfs-$(CONFIG_XEN_DOM0) += xenstored.o diff --git a/drivers/xen/xenfs/privcmd.c b/drivers/xen/xenfs/privcmd.c new file mode 100644 index 000000000000..f80be7f6eb95 --- /dev/null +++ b/drivers/xen/xenfs/privcmd.c @@ -0,0 +1,404 @@ +/****************************************************************************** + * privcmd.c + * + * Interface to privileged domain-0 commands. + * + * Copyright (c) 2002-2004, K A Fraser, B Dragovic + */ + +#include <linux/kernel.h> +#include <linux/sched.h> +#include <linux/slab.h> +#include <linux/string.h> +#include <linux/errno.h> +#include <linux/mm.h> +#include <linux/mman.h> +#include <linux/uaccess.h> +#include <linux/swap.h> +#include <linux/smp_lock.h> +#include <linux/highmem.h> +#include <linux/pagemap.h> +#include <linux/seq_file.h> + +#include <asm/pgalloc.h> +#include <asm/pgtable.h> +#include <asm/tlb.h> +#include <asm/xen/hypervisor.h> +#include <asm/xen/hypercall.h> + +#include <xen/xen.h> +#include <xen/privcmd.h> +#include <xen/interface/xen.h> +#include <xen/features.h> +#include <xen/page.h> +#include <xen/xen-ops.h> + +#ifndef HAVE_ARCH_PRIVCMD_MMAP +static int privcmd_enforce_singleshot_mapping(struct vm_area_struct *vma); +#endif + +static long privcmd_ioctl_hypercall(void __user *udata) +{ + struct privcmd_hypercall hypercall; + long ret; + + if (copy_from_user(&hypercall, udata, sizeof(hypercall))) + return -EFAULT; + + ret = privcmd_call(hypercall.op, + hypercall.arg[0], hypercall.arg[1], + hypercall.arg[2], hypercall.arg[3], + hypercall.arg[4]); + + return ret; +} + +static void free_page_list(struct list_head *pages) +{ + struct page *p, *n; + + list_for_each_entry_safe(p, n, pages, lru) + __free_page(p); + + INIT_LIST_HEAD(pages); +} + +/* + * Given an array of items in userspace, return a list of pages + * containing the data. If copying fails, either because of memory + * allocation failure or a problem reading user memory, return an + * error code; its up to the caller to dispose of any partial list. + */ +static int gather_array(struct list_head *pagelist, + unsigned nelem, size_t size, + void __user *data) +{ + unsigned pageidx; + void *pagedata; + int ret; + + if (size > PAGE_SIZE) + return 0; + + pageidx = PAGE_SIZE; + pagedata = NULL; /* quiet, gcc */ + while (nelem--) { + if (pageidx > PAGE_SIZE-size) { + struct page *page = alloc_page(GFP_KERNEL); + + ret = -ENOMEM; + if (page == NULL) + goto fail; + + pagedata = page_address(page); + + list_add_tail(&page->lru, pagelist); + pageidx = 0; + } + + ret = -EFAULT; + if (copy_from_user(pagedata + pageidx, data, size)) + goto fail; + + data += size; + pageidx += size; + } + + ret = 0; + +fail: + return ret; +} + +/* + * Call function "fn" on each element of the array fragmented + * over a list of pages. + */ +static int traverse_pages(unsigned nelem, size_t size, + struct list_head *pos, + int (*fn)(void *data, void *state), + void *state) +{ + void *pagedata; + unsigned pageidx; + int ret = 0; + + BUG_ON(size > PAGE_SIZE); + + pageidx = PAGE_SIZE; + pagedata = NULL; /* hush, gcc */ + + while (nelem--) { + if (pageidx > PAGE_SIZE-size) { + struct page *page; + pos = pos->next; + page = list_entry(pos, struct page, lru); + pagedata = page_address(page); + pageidx = 0; + } + + ret = (*fn)(pagedata + pageidx, state); + if (ret) + break; + pageidx += size; + } + + return ret; +} + +struct mmap_mfn_state { + unsigned long va; + struct vm_area_struct *vma; + domid_t domain; +}; + +static int mmap_mfn_range(void *data, void *state) +{ + struct privcmd_mmap_entry *msg = data; + struct mmap_mfn_state *st = state; + struct vm_area_struct *vma = st->vma; + int rc; + + /* Do not allow range to wrap the address space. */ + if ((msg->npages > (LONG_MAX >> PAGE_SHIFT)) || + ((unsigned long)(msg->npages << PAGE_SHIFT) >= -st->va)) + return -EINVAL; + + /* Range chunks must be contiguous in va space. */ + if ((msg->va != st->va) || + ((msg->va+(msg->npages<<PAGE_SHIFT)) > vma->vm_end)) + return -EINVAL; + + rc = xen_remap_domain_mfn_range(vma, + msg->va & PAGE_MASK, + msg->mfn, msg->npages, + vma->vm_page_prot, + st->domain); + if (rc < 0) + return rc; + + st->va += msg->npages << PAGE_SHIFT; + + return 0; +} + +static long privcmd_ioctl_mmap(void __user *udata) +{ + struct privcmd_mmap mmapcmd; + struct mm_struct *mm = current->mm; + struct vm_area_struct *vma; + int rc; + LIST_HEAD(pagelist); + struct mmap_mfn_state state; + + if (!xen_initial_domain()) + return -EPERM; + + if (copy_from_user(&mmapcmd, udata, sizeof(mmapcmd))) + return -EFAULT; + + rc = gather_array(&pagelist, + mmapcmd.num, sizeof(struct privcmd_mmap_entry), + mmapcmd.entry); + + if (rc || list_empty(&pagelist)) + goto out; + + down_write(&mm->mmap_sem); + + { + struct page *page = list_first_entry(&pagelist, + struct page, lru); + struct privcmd_mmap_entry *msg = page_address(page); + + vma = find_vma(mm, msg->va); + rc = -EINVAL; + + if (!vma || (msg->va != vma->vm_start) || + !privcmd_enforce_singleshot_mapping(vma)) + goto out_up; + } + + state.va = vma->vm_start; + state.vma = vma; + state.domain = mmapcmd.dom; + + rc = traverse_pages(mmapcmd.num, sizeof(struct privcmd_mmap_entry), + &pagelist, + mmap_mfn_range, &state); + + +out_up: + up_write(&mm->mmap_sem); + +out: + free_page_list(&pagelist); + + return rc; +} + +struct mmap_batch_state { + domid_t domain; + unsigned long va; + struct vm_area_struct *vma; + int err; + + xen_pfn_t __user *user; +}; + +static int mmap_batch_fn(void *data, void *state) +{ + xen_pfn_t *mfnp = data; + struct mmap_batch_state *st = state; + + if (xen_remap_domain_mfn_range(st->vma, st->va & PAGE_MASK, *mfnp, 1, + st->vma->vm_page_prot, st->domain) < 0) { + *mfnp |= 0xf0000000U; + st->err++; + } + st->va += PAGE_SIZE; + + return 0; +} + +static int mmap_return_errors(void *data, void *state) +{ + xen_pfn_t *mfnp = data; + struct mmap_batch_state *st = state; + + put_user(*mfnp, st->user++); + + return 0; +} + +static struct vm_operations_struct privcmd_vm_ops; + +static long privcmd_ioctl_mmap_batch(void __user *udata) +{ + int ret; + struct privcmd_mmapbatch m; + struct mm_struct *mm = current->mm; + struct vm_area_struct *vma; + unsigned long nr_pages; + LIST_HEAD(pagelist); + struct mmap_batch_state state; + + if (!xen_initial_domain()) + return -EPERM; + + if (copy_from_user(&m, udata, sizeof(m))) + return -EFAULT; + + nr_pages = m.num; + if ((m.num <= 0) || (nr_pages > (LONG_MAX >> PAGE_SHIFT))) + return -EINVAL; + + ret = gather_array(&pagelist, m.num, sizeof(xen_pfn_t), + m.arr); + + if (ret || list_empty(&pagelist)) + goto out; + + down_write(&mm->mmap_sem); + + vma = find_vma(mm, m.addr); + ret = -EINVAL; + if (!vma || + vma->vm_ops != &privcmd_vm_ops || + (m.addr != vma->vm_start) || + ((m.addr + (nr_pages << PAGE_SHIFT)) != vma->vm_end) || + !privcmd_enforce_singleshot_mapping(vma)) { + up_write(&mm->mmap_sem); + goto out; + } + + state.domain = m.dom; + state.vma = vma; + state.va = m.addr; + state.err = 0; + + ret = traverse_pages(m.num, sizeof(xen_pfn_t), + &pagelist, mmap_batch_fn, &state); + + up_write(&mm->mmap_sem); + + if (state.err > 0) { + ret = 0; + + state.user = m.arr; + traverse_pages(m.num, sizeof(xen_pfn_t), + &pagelist, + mmap_return_errors, &state); + } + +out: + free_page_list(&pagelist); + + return ret; +} + +static long privcmd_ioctl(struct file *file, + unsigned int cmd, unsigned long data) +{ + int ret = -ENOSYS; + void __user *udata = (void __user *) data; + + switch (cmd) { + case IOCTL_PRIVCMD_HYPERCALL: + ret = privcmd_ioctl_hypercall(udata); + break; + + case IOCTL_PRIVCMD_MMAP: + ret = privcmd_ioctl_mmap(udata); + break; + + case IOCTL_PRIVCMD_MMAPBATCH: + ret = privcmd_ioctl_mmap_batch(udata); + break; + + default: + ret = -EINVAL; + break; + } + + return ret; +} + +#ifndef HAVE_ARCH_PRIVCMD_MMAP +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", + vma, vma->vm_start, vma->vm_end, + vmf->pgoff, vmf->virtual_address); + + return VM_FAULT_SIGBUS; +} + +static struct vm_operations_struct privcmd_vm_ops = { + .fault = privcmd_fault +}; + +static int privcmd_mmap(struct file *file, struct vm_area_struct *vma) +{ + /* Unsupported for auto-translate guests. */ + if (xen_feature(XENFEAT_auto_translated_physmap)) + return -ENOSYS; + + /* DONTCOPY is essential for Xen as copy_page_range is broken. */ + vma->vm_flags |= VM_RESERVED | VM_IO | VM_DONTCOPY; + vma->vm_ops = &privcmd_vm_ops; + vma->vm_private_data = NULL; + + return 0; +} + +static int privcmd_enforce_singleshot_mapping(struct vm_area_struct *vma) +{ + return (xchg(&vma->vm_private_data, (void *)1) == NULL); +} +#endif + +const struct file_operations privcmd_file_ops = { + .unlocked_ioctl = privcmd_ioctl, + .mmap = privcmd_mmap, +}; diff --git a/drivers/xen/xenfs/super.c b/drivers/xen/xenfs/super.c index bd96340063c1..f6339d11d59c 100644 --- a/drivers/xen/xenfs/super.c +++ b/drivers/xen/xenfs/super.c @@ -12,6 +12,8 @@ #include <linux/module.h> #include <linux/fs.h> #include <linux/magic.h> +#include <linux/mm.h> +#include <linux/backing-dev.h> #include <xen/xen.h> @@ -22,6 +24,62 @@ MODULE_DESCRIPTION("Xen filesystem"); MODULE_LICENSE("GPL"); +static int xenfs_set_page_dirty(struct page *page) +{ + return !TestSetPageDirty(page); +} + +static const struct address_space_operations xenfs_aops = { + .set_page_dirty = xenfs_set_page_dirty, +}; + +static struct backing_dev_info xenfs_backing_dev_info = { + .ra_pages = 0, /* No readahead */ + .capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK, +}; + +static struct inode *xenfs_make_inode(struct super_block *sb, int mode) +{ + struct inode *ret = new_inode(sb); + + if (ret) { + ret->i_mode = mode; + ret->i_mapping->a_ops = &xenfs_aops; + ret->i_mapping->backing_dev_info = &xenfs_backing_dev_info; + ret->i_uid = ret->i_gid = 0; + ret->i_blocks = 0; + ret->i_atime = ret->i_mtime = ret->i_ctime = CURRENT_TIME; + } + return ret; +} + +static struct dentry *xenfs_create_file(struct super_block *sb, + struct dentry *parent, + const char *name, + const struct file_operations *fops, + void *data, + int mode) +{ + struct dentry *dentry; + struct inode *inode; + + dentry = d_alloc_name(parent, name); + if (!dentry) + return NULL; + + inode = xenfs_make_inode(sb, S_IFREG | mode); + if (!inode) { + dput(dentry); + return NULL; + } + + inode->i_fop = fops; + inode->i_private = data; + + d_add(dentry, inode); + return dentry; +} + static ssize_t capabilities_read(struct file *file, char __user *buf, size_t size, loff_t *off) { @@ -44,33 +102,60 @@ static int xenfs_fill_super(struct super_block *sb, void *data, int silent) [1] = {}, { "xenbus", &xenbus_file_ops, S_IRUSR|S_IWUSR }, { "capabilities", &capabilities_file_ops, S_IRUGO }, + { "privcmd", &privcmd_file_ops, S_IRUSR|S_IWUSR }, {""}, }; + int rc; - return simple_fill_super(sb, XENFS_SUPER_MAGIC, xenfs_files); + rc = simple_fill_super(sb, XENFS_SUPER_MAGIC, xenfs_files); + if (rc < 0) + return rc; + + if (xen_initial_domain()) { + xenfs_create_file(sb, sb->s_root, "xsd_kva", + &xsd_kva_file_ops, NULL, S_IRUSR|S_IWUSR); + xenfs_create_file(sb, sb->s_root, "xsd_port", + &xsd_port_file_ops, NULL, S_IRUSR|S_IWUSR); + } + + return rc; } -static int xenfs_get_sb(struct file_system_type *fs_type, +static int xenfs_mount(struct file_system_type *fs_type, int flags, const char *dev_name, - void *data, struct vfsmount *mnt) + void *data) { - return get_sb_single(fs_type, flags, data, xenfs_fill_super, mnt); + return mount_single(fs_type, flags, data, xenfs_fill_super); } static struct file_system_type xenfs_type = { .owner = THIS_MODULE, .name = "xenfs", - .get_sb = xenfs_get_sb, + .mount = xenfs_mount, .kill_sb = kill_litter_super, }; static int __init xenfs_init(void) { - if (xen_domain()) - return register_filesystem(&xenfs_type); + int err; + if (!xen_domain()) { + printk(KERN_INFO "xenfs: not registering filesystem on non-xen platform\n"); + return 0; + } + + err = register_filesystem(&xenfs_type); + if (err) { + printk(KERN_ERR "xenfs: Unable to register filesystem!\n"); + goto out; + } + + err = bdi_init(&xenfs_backing_dev_info); + if (err) + unregister_filesystem(&xenfs_type); + + out: - printk(KERN_INFO "XENFS: not registering filesystem on non-xen platform\n"); - return 0; + return err; } static void __exit xenfs_exit(void) diff --git a/drivers/xen/xenfs/xenfs.h b/drivers/xen/xenfs/xenfs.h index 51f08b2d0bf1..b68aa6200003 100644 --- a/drivers/xen/xenfs/xenfs.h +++ b/drivers/xen/xenfs/xenfs.h @@ -2,5 +2,8 @@ #define _XENFS_XENBUS_H extern const struct file_operations xenbus_file_ops; +extern const struct file_operations privcmd_file_ops; +extern const struct file_operations xsd_kva_file_ops; +extern const struct file_operations xsd_port_file_ops; #endif /* _XENFS_XENBUS_H */ diff --git a/drivers/xen/xenfs/xenstored.c b/drivers/xen/xenfs/xenstored.c new file mode 100644 index 000000000000..fef20dbc6a5c --- /dev/null +++ b/drivers/xen/xenfs/xenstored.c @@ -0,0 +1,68 @@ +#include <linux/slab.h> +#include <linux/types.h> +#include <linux/mm.h> +#include <linux/fs.h> + +#include <xen/page.h> + +#include "xenfs.h" +#include "../xenbus/xenbus_comms.h" + +static ssize_t xsd_read(struct file *file, char __user *buf, + size_t size, loff_t *off) +{ + const char *str = (const char *)file->private_data; + return simple_read_from_buffer(buf, size, off, str, strlen(str)); +} + +static int xsd_release(struct inode *inode, struct file *file) +{ + kfree(file->private_data); + return 0; +} + +static int xsd_kva_open(struct inode *inode, struct file *file) +{ + file->private_data = (void *)kasprintf(GFP_KERNEL, "0x%p", + xen_store_interface); + if (!file->private_data) + return -ENOMEM; + return 0; +} + +static int xsd_kva_mmap(struct file *file, struct vm_area_struct *vma) +{ + size_t size = vma->vm_end - vma->vm_start; + + if ((size > PAGE_SIZE) || (vma->vm_pgoff != 0)) + return -EINVAL; + + if (remap_pfn_range(vma, vma->vm_start, + virt_to_pfn(xen_store_interface), + size, vma->vm_page_prot)) + return -EAGAIN; + + return 0; +} + +const struct file_operations xsd_kva_file_ops = { + .open = xsd_kva_open, + .mmap = xsd_kva_mmap, + .read = xsd_read, + .release = xsd_release, +}; + +static int xsd_port_open(struct inode *inode, struct file *file) +{ + file->private_data = (void *)kasprintf(GFP_KERNEL, "%d", + xen_store_evtchn); + if (!file->private_data) + return -ENOMEM; + return 0; +} + +const struct file_operations xsd_port_file_ops = { + .open = xsd_port_open, + .read = xsd_read, + .release = xsd_release, +}; |