diff options
Diffstat (limited to 'drivers')
112 files changed, 1569 insertions, 16593 deletions
diff --git a/drivers/Kconfig b/drivers/Kconfig index f4076d9e9902..08d4ae201597 100644 --- a/drivers/Kconfig +++ b/drivers/Kconfig @@ -90,8 +90,6 @@ source "drivers/dca/Kconfig" source "drivers/auxdisplay/Kconfig" -source "drivers/kvm/Kconfig" - source "drivers/uio/Kconfig" source "drivers/virtio/Kconfig" diff --git a/drivers/Makefile b/drivers/Makefile index 8cb37e3557d4..0ee9a8a4095e 100644 --- a/drivers/Makefile +++ b/drivers/Makefile @@ -38,7 +38,7 @@ obj-$(CONFIG_SCSI) += scsi/ obj-$(CONFIG_ATA) += ata/ obj-$(CONFIG_FUSION) += message/ obj-$(CONFIG_FIREWIRE) += firewire/ -obj-$(CONFIG_IEEE1394) += ieee1394/ +obj-y += ieee1394/ obj-$(CONFIG_UIO) += uio/ obj-y += cdrom/ obj-y += auxdisplay/ @@ -47,7 +47,6 @@ obj-$(CONFIG_SPI) += spi/ obj-$(CONFIG_PCCARD) += pcmcia/ obj-$(CONFIG_DIO) += dio/ obj-$(CONFIG_SBUS) += sbus/ -obj-$(CONFIG_KVM) += kvm/ obj-$(CONFIG_ZORRO) += zorro/ obj-$(CONFIG_MAC) += macintosh/ obj-$(CONFIG_ATA_OVER_ETH) += block/aoe/ @@ -73,7 +72,7 @@ obj-$(CONFIG_ISDN) += isdn/ obj-$(CONFIG_EDAC) += edac/ obj-$(CONFIG_MCA) += mca/ obj-$(CONFIG_EISA) += eisa/ -obj-$(CONFIG_LGUEST_GUEST) += lguest/ +obj-y += lguest/ obj-$(CONFIG_CPU_FREQ) += cpufreq/ obj-$(CONFIG_CPU_IDLE) += cpuidle/ obj-$(CONFIG_MMC) += mmc/ diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c index 2235f4e02d26..eb1f82f79153 100644 --- a/drivers/acpi/processor_idle.c +++ b/drivers/acpi/processor_idle.c @@ -357,6 +357,26 @@ int acpi_processor_resume(struct acpi_device * device) return 0; } +#if defined (CONFIG_GENERIC_TIME) && defined (CONFIG_X86_TSC) +static int tsc_halts_in_c(int state) +{ + switch (boot_cpu_data.x86_vendor) { + case X86_VENDOR_AMD: + /* + * AMD Fam10h TSC will tick in all + * C/P/S0/S1 states when this bit is set. + */ + if (boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) + return 0; + /*FALL THROUGH*/ + case X86_VENDOR_INTEL: + /* Several cases known where TSC halts in C2 too */ + default: + return state > ACPI_STATE_C1; + } +} +#endif + #ifndef CONFIG_CPU_IDLE static void acpi_processor_idle(void) { @@ -516,7 +536,8 @@ static void acpi_processor_idle(void) #if defined (CONFIG_GENERIC_TIME) && defined (CONFIG_X86_TSC) /* TSC halts in C2, so notify users */ - mark_tsc_unstable("possible TSC halt in C2"); + if (tsc_halts_in_c(ACPI_STATE_C2)) + mark_tsc_unstable("possible TSC halt in C2"); #endif /* Compute time (ticks) that we were actually asleep */ sleep_ticks = ticks_elapsed(t1, t2); @@ -534,6 +555,7 @@ static void acpi_processor_idle(void) break; case ACPI_STATE_C3: + acpi_unlazy_tlb(smp_processor_id()); /* * Must be done before busmaster disable as we might * need to access HPET ! @@ -579,7 +601,8 @@ static void acpi_processor_idle(void) #if defined (CONFIG_GENERIC_TIME) && defined (CONFIG_X86_TSC) /* TSC halts in C3, so notify users */ - mark_tsc_unstable("TSC halts in C3"); + if (tsc_halts_in_c(ACPI_STATE_C3)) + mark_tsc_unstable("TSC halts in C3"); #endif /* Compute time (ticks) that we were actually asleep */ sleep_ticks = ticks_elapsed(t1, t2); @@ -1423,6 +1446,7 @@ static int acpi_idle_enter_simple(struct cpuidle_device *dev, return 0; } + acpi_unlazy_tlb(smp_processor_id()); /* * Must be done before busmaster disable as we might need to * access HPET ! @@ -1443,7 +1467,8 @@ static int acpi_idle_enter_simple(struct cpuidle_device *dev, #if defined (CONFIG_GENERIC_TIME) && defined (CONFIG_X86_TSC) /* TSC could halt in idle, so notify users */ - mark_tsc_unstable("TSC halts in idle");; + if (tsc_halts_in_c(cx->type)) + mark_tsc_unstable("TSC halts in idle");; #endif sleep_ticks = ticks_elapsed(t1, t2); @@ -1554,7 +1579,8 @@ static int acpi_idle_enter_bm(struct cpuidle_device *dev, #if defined (CONFIG_GENERIC_TIME) && defined (CONFIG_X86_TSC) /* TSC could halt in idle, so notify users */ - mark_tsc_unstable("TSC halts in idle"); + if (tsc_halts_in_c(ACPI_STATE_C3)) + mark_tsc_unstable("TSC halts in idle"); #endif sleep_ticks = ticks_elapsed(t1, t2); /* Tell the scheduler how much we idled: */ diff --git a/drivers/base/bus.c b/drivers/base/bus.c index f484495b2ad1..055989e94799 100644 --- a/drivers/base/bus.c +++ b/drivers/base/bus.c @@ -163,15 +163,6 @@ static struct kset *bus_kset; #ifdef CONFIG_HOTPLUG /* Manually detach a device from its associated driver. */ -static int driver_helper(struct device *dev, void *data) -{ - const char *name = data; - - if (strcmp(name, dev->bus_id) == 0) - return 1; - return 0; -} - static ssize_t driver_unbind(struct device_driver *drv, const char *buf, size_t count) { @@ -179,7 +170,7 @@ static ssize_t driver_unbind(struct device_driver *drv, struct device *dev; int err = -ENODEV; - dev = bus_find_device(bus, NULL, (void *)buf, driver_helper); + dev = bus_find_device_by_name(bus, NULL, buf); if (dev && dev->driver == drv) { if (dev->parent) /* Needed for USB */ down(&dev->parent->sem); @@ -206,7 +197,7 @@ static ssize_t driver_bind(struct device_driver *drv, struct device *dev; int err = -ENODEV; - dev = bus_find_device(bus, NULL, (void *)buf, driver_helper); + dev = bus_find_device_by_name(bus, NULL, buf); if (dev && dev->driver == NULL) { if (dev->parent) /* Needed for USB */ down(&dev->parent->sem); @@ -250,7 +241,7 @@ static ssize_t store_drivers_probe(struct bus_type *bus, { struct device *dev; - dev = bus_find_device(bus, NULL, (void *)buf, driver_helper); + dev = bus_find_device_by_name(bus, NULL, buf); if (!dev) return -ENODEV; if (bus_rescan_devices_helper(dev, NULL) != 0) @@ -338,6 +329,32 @@ struct device *bus_find_device(struct bus_type *bus, } EXPORT_SYMBOL_GPL(bus_find_device); +static int match_name(struct device *dev, void *data) +{ + const char *name = data; + + if (strcmp(name, dev->bus_id) == 0) + return 1; + return 0; +} + +/** + * bus_find_device_by_name - device iterator for locating a particular device of a specific name + * @bus: bus type + * @start: Device to begin with + * @name: name of the device to match + * + * This is similar to the bus_find_device() function above, but it handles + * searching by a name automatically, no need to write another strcmp matching + * function. + */ +struct device *bus_find_device_by_name(struct bus_type *bus, + struct device *start, const char *name) +{ + return bus_find_device(bus, start, (void *)name, match_name); +} +EXPORT_SYMBOL_GPL(bus_find_device_by_name); + static struct device_driver *next_driver(struct klist_iter *i) { struct klist_node *n = klist_next(i); diff --git a/drivers/base/class.c b/drivers/base/class.c index 59cf35894cfc..9d915376c313 100644 --- a/drivers/base/class.c +++ b/drivers/base/class.c @@ -149,7 +149,7 @@ int class_register(struct class *cls) if (error) return error; -#ifdef CONFIG_SYSFS_DEPRECATED +#if defined(CONFIG_SYSFS_DEPRECATED) && defined(CONFIG_BLOCK) /* let the block class directory show up in the root of sysfs */ if (cls != &block_class) cls->subsys.kobj.kset = class_kset; @@ -863,7 +863,7 @@ EXPORT_SYMBOL_GPL(class_for_each_device); * The callback should return 0 if the device doesn't match and non-zero * if it does. If the callback returns non-zero, this function will * return to the caller and not iterate over any more devices. - + * * Note, you will need to drop the reference with put_device() after use. * * We hold class->sem in this function, so it can not be diff --git a/drivers/base/core.c b/drivers/base/core.c index edf3bbeb8d6a..b1727876182c 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -27,9 +27,17 @@ int (*platform_notify)(struct device *dev) = NULL; int (*platform_notify_remove)(struct device *dev) = NULL; -/* - * sysfs bindings for devices. - */ +#ifdef CONFIG_BLOCK +static inline int device_is_not_partition(struct device *dev) +{ + return !(dev->type == &part_type); +} +#else +static inline int device_is_not_partition(struct device *dev) +{ + return 1; +} +#endif /** * dev_driver_string - Return a device's driver name, if at all possible @@ -652,14 +660,14 @@ static int device_add_class_symlinks(struct device *dev) #ifdef CONFIG_SYSFS_DEPRECATED /* stacked class devices need a symlink in the class directory */ if (dev->kobj.parent != &dev->class->subsys.kobj && - dev->type != &part_type) { + device_is_not_partition(dev)) { error = sysfs_create_link(&dev->class->subsys.kobj, &dev->kobj, dev->bus_id); if (error) goto out_subsys; } - if (dev->parent && dev->type != &part_type) { + if (dev->parent && device_is_not_partition(dev)) { struct device *parent = dev->parent; char *class_name; @@ -688,11 +696,11 @@ static int device_add_class_symlinks(struct device *dev) return 0; out_device: - if (dev->parent && dev->type != &part_type) + if (dev->parent && device_is_not_partition(dev)) sysfs_remove_link(&dev->kobj, "device"); out_busid: if (dev->kobj.parent != &dev->class->subsys.kobj && - dev->type != &part_type) + device_is_not_partition(dev)) sysfs_remove_link(&dev->class->subsys.kobj, dev->bus_id); #else /* link in the class directory pointing to the device */ @@ -701,7 +709,7 @@ out_busid: if (error) goto out_subsys; - if (dev->parent && dev->type != &part_type) { + if (dev->parent && device_is_not_partition(dev)) { error = sysfs_create_link(&dev->kobj, &dev->parent->kobj, "device"); if (error) @@ -725,7 +733,7 @@ static void device_remove_class_symlinks(struct device *dev) return; #ifdef CONFIG_SYSFS_DEPRECATED - if (dev->parent && dev->type != &part_type) { + if (dev->parent && device_is_not_partition(dev)) { char *class_name; class_name = make_class_name(dev->class->name, &dev->kobj); @@ -737,10 +745,10 @@ static void device_remove_class_symlinks(struct device *dev) } if (dev->kobj.parent != &dev->class->subsys.kobj && - dev->type != &part_type) + device_is_not_partition(dev)) sysfs_remove_link(&dev->class->subsys.kobj, dev->bus_id); #else - if (dev->parent && dev->type != &part_type) + if (dev->parent && device_is_not_partition(dev)) sysfs_remove_link(&dev->kobj, "device"); sysfs_remove_link(&dev->class->subsys.kobj, dev->bus_id); diff --git a/drivers/block/cciss.c b/drivers/block/cciss.c index ef50068def88..855ce8e5efba 100644 --- a/drivers/block/cciss.c +++ b/drivers/block/cciss.c @@ -2524,7 +2524,6 @@ after_error_processing: resend_cciss_cmd(h, cmd); return; } - cmd->rq->data_len = 0; cmd->rq->completion_data = cmd; blk_complete_request(cmd->rq); } diff --git a/drivers/block/xsysace.c b/drivers/block/xsysace.c index 2c81465fd60c..78ebfffc77e3 100644 --- a/drivers/block/xsysace.c +++ b/drivers/block/xsysace.c @@ -483,7 +483,6 @@ static void ace_fsm_dostate(struct ace_device *ace) u32 status; u16 val; int count; - int i; #if defined(DEBUG) dev_dbg(ace->dev, "fsm_state=%i, id_req_count=%i\n", @@ -688,7 +687,6 @@ static void ace_fsm_dostate(struct ace_device *ace) } /* Transfer the next buffer */ - i = 16; if (ace->fsm_task == ACE_TASK_WRITE) ace->reg_ops->dataout(ace); else @@ -702,8 +700,8 @@ static void ace_fsm_dostate(struct ace_device *ace) } /* bio finished; is there another one? */ - i = ace->req->current_nr_sectors; - if (__blk_end_request(ace->req, 0, i)) { + if (__blk_end_request(ace->req, 0, + blk_rq_cur_bytes(ace->req))) { /* dev_dbg(ace->dev, "next block; h=%li c=%i\n", * ace->req->hard_nr_sectors, * ace->req->current_nr_sectors); diff --git a/drivers/char/agp/ali-agp.c b/drivers/char/agp/ali-agp.c index aa5ddb716ffb..1ffb381130c3 100644 --- a/drivers/char/agp/ali-agp.c +++ b/drivers/char/agp/ali-agp.c @@ -145,7 +145,6 @@ static void *m1541_alloc_page(struct agp_bridge_data *bridge) void *addr = agp_generic_alloc_page(agp_bridge); u32 temp; - global_flush_tlb(); if (!addr) return NULL; @@ -162,7 +161,6 @@ static void ali_destroy_page(void * addr, int flags) if (flags & AGP_PAGE_DESTROY_UNMAP) { global_cache_flush(); /* is this really needed? --hch */ agp_generic_destroy_page(addr, flags); - global_flush_tlb(); } else agp_generic_destroy_page(addr, flags); } diff --git a/drivers/char/agp/backend.c b/drivers/char/agp/backend.c index 832ded20fe70..2720882e66fe 100644 --- a/drivers/char/agp/backend.c +++ b/drivers/char/agp/backend.c @@ -147,7 +147,6 @@ static int agp_backend_initialize(struct agp_bridge_data *bridge) printk(KERN_ERR PFX "unable to get memory for scratch page.\n"); return -ENOMEM; } - flush_agp_mappings(); bridge->scratch_page_real = virt_to_gart(addr); bridge->scratch_page = @@ -191,7 +190,6 @@ err_out: if (bridge->driver->needs_scratch_page) { bridge->driver->agp_destroy_page(gart_to_virt(bridge->scratch_page_real), AGP_PAGE_DESTROY_UNMAP); - flush_agp_mappings(); bridge->driver->agp_destroy_page(gart_to_virt(bridge->scratch_page_real), AGP_PAGE_DESTROY_FREE); } @@ -219,7 +217,6 @@ static void agp_backend_cleanup(struct agp_bridge_data *bridge) bridge->driver->needs_scratch_page) { bridge->driver->agp_destroy_page(gart_to_virt(bridge->scratch_page_real), AGP_PAGE_DESTROY_UNMAP); - flush_agp_mappings(); bridge->driver->agp_destroy_page(gart_to_virt(bridge->scratch_page_real), AGP_PAGE_DESTROY_FREE); } diff --git a/drivers/char/agp/generic.c b/drivers/char/agp/generic.c index 64b2f6d7059d..1a4674ce0c71 100644 --- a/drivers/char/agp/generic.c +++ b/drivers/char/agp/generic.c @@ -197,7 +197,6 @@ void agp_free_memory(struct agp_memory *curr) for (i = 0; i < curr->page_count; i++) { curr->bridge->driver->agp_destroy_page(gart_to_virt(curr->memory[i]), AGP_PAGE_DESTROY_UNMAP); } - flush_agp_mappings(); for (i = 0; i < curr->page_count; i++) { curr->bridge->driver->agp_destroy_page(gart_to_virt(curr->memory[i]), AGP_PAGE_DESTROY_FREE); } @@ -267,8 +266,6 @@ struct agp_memory *agp_allocate_memory(struct agp_bridge_data *bridge, } new->bridge = bridge; - flush_agp_mappings(); - return new; } EXPORT_SYMBOL(agp_allocate_memory); diff --git a/drivers/char/agp/i460-agp.c b/drivers/char/agp/i460-agp.c index e72a83e2bad5..76f581c85a7d 100644 --- a/drivers/char/agp/i460-agp.c +++ b/drivers/char/agp/i460-agp.c @@ -527,7 +527,6 @@ static void *i460_alloc_page (struct agp_bridge_data *bridge) if (I460_IO_PAGE_SHIFT <= PAGE_SHIFT) { page = agp_generic_alloc_page(agp_bridge); - global_flush_tlb(); } else /* Returning NULL would cause problems */ /* AK: really dubious code. */ @@ -539,7 +538,6 @@ static void i460_destroy_page (void *page, int flags) { if (I460_IO_PAGE_SHIFT <= PAGE_SHIFT) { agp_generic_destroy_page(page, flags); - global_flush_tlb(); } } diff --git a/drivers/char/agp/intel-agp.c b/drivers/char/agp/intel-agp.c index 03eac1eb8e0f..189efb6ef970 100644 --- a/drivers/char/agp/intel-agp.c +++ b/drivers/char/agp/intel-agp.c @@ -210,13 +210,11 @@ static void *i8xx_alloc_pages(void) if (page == NULL) return NULL; - if (change_page_attr(page, 4, PAGE_KERNEL_NOCACHE) < 0) { - change_page_attr(page, 4, PAGE_KERNEL); - global_flush_tlb(); + if (set_pages_uc(page, 4) < 0) { + set_pages_wb(page, 4); __free_pages(page, 2); return NULL; } - global_flush_tlb(); get_page(page); atomic_inc(&agp_bridge->current_memory_agp); return page_address(page); @@ -230,8 +228,7 @@ static void i8xx_destroy_pages(void *addr) return; page = virt_to_page(addr); - change_page_attr(page, 4, PAGE_KERNEL); - global_flush_tlb(); + set_pages_wb(page, 4); put_page(page); __free_pages(page, 2); atomic_dec(&agp_bridge->current_memory_agp); @@ -341,7 +338,6 @@ static struct agp_memory *alloc_agpphysmem_i8xx(size_t pg_count, int type) switch (pg_count) { case 1: addr = agp_bridge->driver->agp_alloc_page(agp_bridge); - global_flush_tlb(); break; case 4: /* kludge to get 4 physical pages for ARGB cursor */ @@ -404,7 +400,6 @@ static void intel_i810_free_by_type(struct agp_memory *curr) else { agp_bridge->driver->agp_destroy_page(gart_to_virt(curr->memory[0]), AGP_PAGE_DESTROY_UNMAP); - global_flush_tlb(); agp_bridge->driver->agp_destroy_page(gart_to_virt(curr->memory[0]), AGP_PAGE_DESTROY_FREE); } diff --git a/drivers/char/hpet.c b/drivers/char/hpet.c index 4c16778e3f84..465ad35ed38f 100644 --- a/drivers/char/hpet.c +++ b/drivers/char/hpet.c @@ -600,63 +600,6 @@ static int hpet_is_known(struct hpet_data *hdp) return 0; } -EXPORT_SYMBOL(hpet_alloc); -EXPORT_SYMBOL(hpet_register); -EXPORT_SYMBOL(hpet_unregister); -EXPORT_SYMBOL(hpet_control); - -int hpet_register(struct hpet_task *tp, int periodic) -{ - unsigned int i; - u64 mask; - struct hpet_timer __iomem *timer; - struct hpet_dev *devp; - struct hpets *hpetp; - - switch (periodic) { - case 1: - mask = Tn_PER_INT_CAP_MASK; - break; - case 0: - mask = 0; - break; - default: - return -EINVAL; - } - - tp->ht_opaque = NULL; - - spin_lock_irq(&hpet_task_lock); - spin_lock(&hpet_lock); - - for (devp = NULL, hpetp = hpets; hpetp && !devp; hpetp = hpetp->hp_next) - for (timer = hpetp->hp_hpet->hpet_timers, i = 0; - i < hpetp->hp_ntimer; i++, timer++) { - if ((readq(&timer->hpet_config) & Tn_PER_INT_CAP_MASK) - != mask) - continue; - - devp = &hpetp->hp_dev[i]; - - if (devp->hd_flags & HPET_OPEN || devp->hd_task) { - devp = NULL; - continue; - } - - tp->ht_opaque = devp; - devp->hd_task = tp; - break; - } - - spin_unlock(&hpet_lock); - spin_unlock_irq(&hpet_task_lock); - - if (tp->ht_opaque) - return 0; - else - return -EBUSY; -} - static inline int hpet_tpcheck(struct hpet_task *tp) { struct hpet_dev *devp; @@ -706,24 +649,6 @@ int hpet_unregister(struct hpet_task *tp) return 0; } -int hpet_control(struct hpet_task *tp, unsigned int cmd, unsigned long arg) -{ - struct hpet_dev *devp; - int err; - - if ((err = hpet_tpcheck(tp))) - return err; - - spin_lock_irq(&hpet_lock); - devp = tp->ht_opaque; - if (devp->hd_task != tp) { - spin_unlock_irq(&hpet_lock); - return -ENXIO; - } - spin_unlock_irq(&hpet_lock); - return hpet_ioctl_common(devp, cmd, arg, 1); -} - static ctl_table hpet_table[] = { { .ctl_name = CTL_UNNUMBERED, @@ -806,14 +731,14 @@ static unsigned long hpet_calibrate(struct hpets *hpetp) int hpet_alloc(struct hpet_data *hdp) { - u64 cap, mcfg; + u64 cap, mcfg, hpet_config; struct hpet_dev *devp; - u32 i, ntimer; + u32 i, ntimer, irq; struct hpets *hpetp; size_t siz; struct hpet __iomem *hpet; static struct hpets *last = NULL; - unsigned long period; + unsigned long period, irq_bitmap; unsigned long long temp; /* @@ -840,11 +765,47 @@ int hpet_alloc(struct hpet_data *hdp) hpetp->hp_hpet_phys = hdp->hd_phys_address; hpetp->hp_ntimer = hdp->hd_nirqs; + hpet = hpetp->hp_hpet; - for (i = 0; i < hdp->hd_nirqs; i++) - hpetp->hp_dev[i].hd_hdwirq = hdp->hd_irq[i]; + /* Assign IRQs statically for legacy devices */ + hpetp->hp_dev[0].hd_hdwirq = hdp->hd_irq[0]; + hpetp->hp_dev[1].hd_hdwirq = hdp->hd_irq[1]; - hpet = hpetp->hp_hpet; + /* Assign IRQs dynamically for the others */ + for (i = 2, devp = &hpetp->hp_dev[2]; i < hdp->hd_nirqs; i++, devp++) { + struct hpet_timer __iomem *timer; + + timer = &hpet->hpet_timers[devp - hpetp->hp_dev]; + + /* Check if there's already an IRQ assigned to the timer */ + if (hdp->hd_irq[i]) { + hpetp->hp_dev[i].hd_hdwirq = hdp->hd_irq[i]; + continue; + } + + hpet_config = readq(&timer->hpet_config); + irq_bitmap = (hpet_config & Tn_INT_ROUTE_CAP_MASK) + >> Tn_INT_ROUTE_CAP_SHIFT; + if (!irq_bitmap) + irq = 0; /* No valid IRQ Assignable */ + else { + irq = find_first_bit(&irq_bitmap, 32); + do { + hpet_config |= irq << Tn_INT_ROUTE_CNF_SHIFT; + writeq(hpet_config, &timer->hpet_config); + + /* + * Verify whether we have written a valid + * IRQ number by reading it back again + */ + hpet_config = readq(&timer->hpet_config); + if (irq == (hpet_config & Tn_INT_ROUTE_CNF_MASK) + >> Tn_INT_ROUTE_CNF_SHIFT) + break; /* Success */ + } while ((irq = (find_next_bit(&irq_bitmap, 32, irq)))); + } + hpetp->hp_dev[i].hd_hdwirq = irq; + } cap = readq(&hpet->hpet_cap); @@ -875,7 +836,8 @@ int hpet_alloc(struct hpet_data *hdp) hpetp->hp_which, hdp->hd_phys_address, hpetp->hp_ntimer > 1 ? "s" : ""); for (i = 0; i < hpetp->hp_ntimer; i++) - printk("%s %d", i > 0 ? "," : "", hdp->hd_irq[i]); + printk("%s %d", i > 0 ? "," : "", + hpetp->hp_dev[i].hd_hdwirq); printk("\n"); printk(KERN_INFO "hpet%u: %u %d-bit timers, %Lu Hz\n", diff --git a/drivers/char/rtc.c b/drivers/char/rtc.c index 0c66b802736a..78b151c4d20f 100644 --- a/drivers/char/rtc.c +++ b/drivers/char/rtc.c @@ -1,5 +1,5 @@ /* - * Real Time Clock interface for Linux + * Real Time Clock interface for Linux * * Copyright (C) 1996 Paul Gortmaker * @@ -17,7 +17,7 @@ * has been received. If a RTC interrupt has already happened, * it will output an unsigned long and then block. The output value * contains the interrupt status in the low byte and the number of - * interrupts since the last read in the remaining high bytes. The + * interrupts since the last read in the remaining high bytes. The * /dev/rtc interface can also be used with the select(2) call. * * This program is free software; you can redistribute it and/or @@ -104,12 +104,14 @@ static int rtc_has_irq = 1; #ifndef CONFIG_HPET_EMULATE_RTC #define is_hpet_enabled() 0 -#define hpet_set_alarm_time(hrs, min, sec) 0 -#define hpet_set_periodic_freq(arg) 0 -#define hpet_mask_rtc_irq_bit(arg) 0 -#define hpet_set_rtc_irq_bit(arg) 0 -#define hpet_rtc_timer_init() do { } while (0) -#define hpet_rtc_dropped_irq() 0 +#define hpet_set_alarm_time(hrs, min, sec) 0 +#define hpet_set_periodic_freq(arg) 0 +#define hpet_mask_rtc_irq_bit(arg) 0 +#define hpet_set_rtc_irq_bit(arg) 0 +#define hpet_rtc_timer_init() do { } while (0) +#define hpet_rtc_dropped_irq() 0 +#define hpet_register_irq_handler(h) 0 +#define hpet_unregister_irq_handler(h) 0 #ifdef RTC_IRQ static irqreturn_t hpet_rtc_interrupt(int irq, void *dev_id) { @@ -147,7 +149,7 @@ static int rtc_ioctl(struct inode *inode, struct file *file, static unsigned int rtc_poll(struct file *file, poll_table *wait); #endif -static void get_rtc_alm_time (struct rtc_time *alm_tm); +static void get_rtc_alm_time(struct rtc_time *alm_tm); #ifdef RTC_IRQ static void set_rtc_irq_bit_locked(unsigned char bit); static void mask_rtc_irq_bit_locked(unsigned char bit); @@ -185,9 +187,9 @@ static int rtc_proc_open(struct inode *inode, struct file *file); * rtc_status but before mod_timer is called, which would then reenable the * timer (but you would need to have an awful timing before you'd trip on it) */ -static unsigned long rtc_status = 0; /* bitmapped status byte. */ -static unsigned long rtc_freq = 0; /* Current periodic IRQ rate */ -static unsigned long rtc_irq_data = 0; /* our output to the world */ +static unsigned long rtc_status; /* bitmapped status byte. */ +static unsigned long rtc_freq; /* Current periodic IRQ rate */ +static unsigned long rtc_irq_data; /* our output to the world */ static unsigned long rtc_max_user_freq = 64; /* > this, need CAP_SYS_RESOURCE */ #ifdef RTC_IRQ @@ -195,7 +197,7 @@ static unsigned long rtc_max_user_freq = 64; /* > this, need CAP_SYS_RESOURCE */ * rtc_task_lock nests inside rtc_lock. */ static DEFINE_SPINLOCK(rtc_task_lock); -static rtc_task_t *rtc_callback = NULL; +static rtc_task_t *rtc_callback; #endif /* @@ -205,7 +207,7 @@ static rtc_task_t *rtc_callback = NULL; static unsigned long epoch = 1900; /* year corresponding to 0x00 */ -static const unsigned char days_in_mo[] = +static const unsigned char days_in_mo[] = {0, 31, 28, 31, 30, 31, 30, 31, 31, 30, 31, 30, 31}; /* @@ -242,7 +244,7 @@ irqreturn_t rtc_interrupt(int irq, void *dev_id) * the last read in the remainder of rtc_irq_data. */ - spin_lock (&rtc_lock); + spin_lock(&rtc_lock); rtc_irq_data += 0x100; rtc_irq_data &= ~0xff; if (is_hpet_enabled()) { @@ -259,16 +261,16 @@ irqreturn_t rtc_interrupt(int irq, void *dev_id) if (rtc_status & RTC_TIMER_ON) mod_timer(&rtc_irq_timer, jiffies + HZ/rtc_freq + 2*HZ/100); - spin_unlock (&rtc_lock); + spin_unlock(&rtc_lock); /* Now do the rest of the actions */ spin_lock(&rtc_task_lock); if (rtc_callback) rtc_callback->func(rtc_callback->private_data); spin_unlock(&rtc_task_lock); - wake_up_interruptible(&rtc_wait); + wake_up_interruptible(&rtc_wait); - kill_fasync (&rtc_async_queue, SIGIO, POLL_IN); + kill_fasync(&rtc_async_queue, SIGIO, POLL_IN); return IRQ_HANDLED; } @@ -335,7 +337,7 @@ static ssize_t rtc_read(struct file *file, char __user *buf, DECLARE_WAITQUEUE(wait, current); unsigned long data; ssize_t retval; - + if (rtc_has_irq == 0) return -EIO; @@ -358,11 +360,11 @@ static ssize_t rtc_read(struct file *file, char __user *buf, * confusing. And no, xchg() is not the answer. */ __set_current_state(TASK_INTERRUPTIBLE); - - spin_lock_irq (&rtc_lock); + + spin_lock_irq(&rtc_lock); data = rtc_irq_data; rtc_irq_data = 0; - spin_unlock_irq (&rtc_lock); + spin_unlock_irq(&rtc_lock); if (data != 0) break; @@ -378,10 +380,13 @@ static ssize_t rtc_read(struct file *file, char __user *buf, schedule(); } while (1); - if (count == sizeof(unsigned int)) - retval = put_user(data, (unsigned int __user *)buf) ?: sizeof(int); - else - retval = put_user(data, (unsigned long __user *)buf) ?: sizeof(long); + if (count == sizeof(unsigned int)) { + retval = put_user(data, + (unsigned int __user *)buf) ?: sizeof(int); + } else { + retval = put_user(data, + (unsigned long __user *)buf) ?: sizeof(long); + } if (!retval) retval = count; out: @@ -394,7 +399,7 @@ static ssize_t rtc_read(struct file *file, char __user *buf, static int rtc_do_ioctl(unsigned int cmd, unsigned long arg, int kernel) { - struct rtc_time wtime; + struct rtc_time wtime; #ifdef RTC_IRQ if (rtc_has_irq == 0) { @@ -426,35 +431,41 @@ static int rtc_do_ioctl(unsigned int cmd, unsigned long arg, int kernel) } case RTC_PIE_OFF: /* Mask periodic int. enab. bit */ { - unsigned long flags; /* can be called from isr via rtc_control() */ - spin_lock_irqsave (&rtc_lock, flags); + /* can be called from isr via rtc_control() */ + unsigned long flags; + + spin_lock_irqsave(&rtc_lock, flags); mask_rtc_irq_bit_locked(RTC_PIE); if (rtc_status & RTC_TIMER_ON) { rtc_status &= ~RTC_TIMER_ON; del_timer(&rtc_irq_timer); } - spin_unlock_irqrestore (&rtc_lock, flags); + spin_unlock_irqrestore(&rtc_lock, flags); + return 0; } case RTC_PIE_ON: /* Allow periodic ints */ { - unsigned long flags; /* can be called from isr via rtc_control() */ + /* can be called from isr via rtc_control() */ + unsigned long flags; + /* * We don't really want Joe User enabling more * than 64Hz of interrupts on a multi-user machine. */ if (!kernel && (rtc_freq > rtc_max_user_freq) && - (!capable(CAP_SYS_RESOURCE))) + (!capable(CAP_SYS_RESOURCE))) return -EACCES; - spin_lock_irqsave (&rtc_lock, flags); + spin_lock_irqsave(&rtc_lock, flags); if (!(rtc_status & RTC_TIMER_ON)) { mod_timer(&rtc_irq_timer, jiffies + HZ/rtc_freq + 2*HZ/100); rtc_status |= RTC_TIMER_ON; } set_rtc_irq_bit_locked(RTC_PIE); - spin_unlock_irqrestore (&rtc_lock, flags); + spin_unlock_irqrestore(&rtc_lock, flags); + return 0; } case RTC_UIE_OFF: /* Mask ints from RTC updates. */ @@ -477,7 +488,7 @@ static int rtc_do_ioctl(unsigned int cmd, unsigned long arg, int kernel) */ memset(&wtime, 0, sizeof(struct rtc_time)); get_rtc_alm_time(&wtime); - break; + break; } case RTC_ALM_SET: /* Store a time into the alarm */ { @@ -505,16 +516,21 @@ static int rtc_do_ioctl(unsigned int cmd, unsigned long arg, int kernel) */ } if (!(CMOS_READ(RTC_CONTROL) & RTC_DM_BINARY) || - RTC_ALWAYS_BCD) - { - if (sec < 60) BIN_TO_BCD(sec); - else sec = 0xff; - - if (min < 60) BIN_TO_BCD(min); - else min = 0xff; - - if (hrs < 24) BIN_TO_BCD(hrs); - else hrs = 0xff; + RTC_ALWAYS_BCD) { + if (sec < 60) + BIN_TO_BCD(sec); + else + sec = 0xff; + + if (min < 60) + BIN_TO_BCD(min); + else + min = 0xff; + + if (hrs < 24) + BIN_TO_BCD(hrs); + else + hrs = 0xff; } CMOS_WRITE(hrs, RTC_HOURS_ALARM); CMOS_WRITE(min, RTC_MINUTES_ALARM); @@ -563,11 +579,12 @@ static int rtc_do_ioctl(unsigned int cmd, unsigned long arg, int kernel) if (day > (days_in_mo[mon] + ((mon == 2) && leap_yr))) return -EINVAL; - + if ((hrs >= 24) || (min >= 60) || (sec >= 60)) return -EINVAL; - if ((yrs -= epoch) > 255) /* They are unsigned */ + yrs -= epoch; + if (yrs > 255) /* They are unsigned */ return -EINVAL; spin_lock_irq(&rtc_lock); @@ -635,9 +652,10 @@ static int rtc_do_ioctl(unsigned int cmd, unsigned long arg, int kernel) { int tmp = 0; unsigned char val; - unsigned long flags; /* can be called from isr via rtc_control() */ + /* can be called from isr via rtc_control() */ + unsigned long flags; - /* + /* * The max we can do is 8192Hz. */ if ((arg < 2) || (arg > 8192)) @@ -646,7 +664,8 @@ static int rtc_do_ioctl(unsigned int cmd, unsigned long arg, int kernel) * We don't really want Joe User generating more * than 64Hz of interrupts on a multi-user machine. */ - if (!kernel && (arg > rtc_max_user_freq) && (!capable(CAP_SYS_RESOURCE))) + if (!kernel && (arg > rtc_max_user_freq) && + !capable(CAP_SYS_RESOURCE)) return -EACCES; while (arg > (1<<tmp)) @@ -674,11 +693,11 @@ static int rtc_do_ioctl(unsigned int cmd, unsigned long arg, int kernel) #endif case RTC_EPOCH_READ: /* Read the epoch. */ { - return put_user (epoch, (unsigned long __user *)arg); + return put_user(epoch, (unsigned long __user *)arg); } case RTC_EPOCH_SET: /* Set the epoch. */ { - /* + /* * There were no RTC clocks before 1900. */ if (arg < 1900) @@ -693,7 +712,8 @@ static int rtc_do_ioctl(unsigned int cmd, unsigned long arg, int kernel) default: return -ENOTTY; } - return copy_to_user((void __user *)arg, &wtime, sizeof wtime) ? -EFAULT : 0; + return copy_to_user((void __user *)arg, + &wtime, sizeof wtime) ? -EFAULT : 0; } static int rtc_ioctl(struct inode *inode, struct file *file, unsigned int cmd, @@ -712,26 +732,25 @@ static int rtc_ioctl(struct inode *inode, struct file *file, unsigned int cmd, * needed here. Or anywhere else in this driver. */ static int rtc_open(struct inode *inode, struct file *file) { - spin_lock_irq (&rtc_lock); + spin_lock_irq(&rtc_lock); - if(rtc_status & RTC_IS_OPEN) + if (rtc_status & RTC_IS_OPEN) goto out_busy; rtc_status |= RTC_IS_OPEN; rtc_irq_data = 0; - spin_unlock_irq (&rtc_lock); + spin_unlock_irq(&rtc_lock); return 0; out_busy: - spin_unlock_irq (&rtc_lock); + spin_unlock_irq(&rtc_lock); return -EBUSY; } -static int rtc_fasync (int fd, struct file *filp, int on) - +static int rtc_fasync(int fd, struct file *filp, int on) { - return fasync_helper (fd, filp, on, &rtc_async_queue); + return fasync_helper(fd, filp, on, &rtc_async_queue); } static int rtc_release(struct inode *inode, struct file *file) @@ -762,16 +781,16 @@ static int rtc_release(struct inode *inode, struct file *file) } spin_unlock_irq(&rtc_lock); - if (file->f_flags & FASYNC) { - rtc_fasync (-1, file, 0); - } + if (file->f_flags & FASYNC) + rtc_fasync(-1, file, 0); no_irq: #endif - spin_lock_irq (&rtc_lock); + spin_lock_irq(&rtc_lock); rtc_irq_data = 0; rtc_status &= ~RTC_IS_OPEN; - spin_unlock_irq (&rtc_lock); + spin_unlock_irq(&rtc_lock); + return 0; } @@ -786,9 +805,9 @@ static unsigned int rtc_poll(struct file *file, poll_table *wait) poll_wait(file, &rtc_wait, wait); - spin_lock_irq (&rtc_lock); + spin_lock_irq(&rtc_lock); l = rtc_irq_data; - spin_unlock_irq (&rtc_lock); + spin_unlock_irq(&rtc_lock); if (l != 0) return POLLIN | POLLRDNORM; @@ -796,14 +815,6 @@ static unsigned int rtc_poll(struct file *file, poll_table *wait) } #endif -/* - * exported stuffs - */ - -EXPORT_SYMBOL(rtc_register); -EXPORT_SYMBOL(rtc_unregister); -EXPORT_SYMBOL(rtc_control); - int rtc_register(rtc_task_t *task) { #ifndef RTC_IRQ @@ -829,6 +840,7 @@ int rtc_register(rtc_task_t *task) return 0; #endif } +EXPORT_SYMBOL(rtc_register); int rtc_unregister(rtc_task_t *task) { @@ -845,7 +857,7 @@ int rtc_unregister(rtc_task_t *task) return -ENXIO; } rtc_callback = NULL; - + /* disable controls */ if (!hpet_mask_rtc_irq_bit(RTC_PIE | RTC_AIE | RTC_UIE)) { tmp = CMOS_READ(RTC_CONTROL); @@ -865,6 +877,7 @@ int rtc_unregister(rtc_task_t *task) return 0; #endif } +EXPORT_SYMBOL(rtc_unregister); int rtc_control(rtc_task_t *task, unsigned int cmd, unsigned long arg) { @@ -883,7 +896,7 @@ int rtc_control(rtc_task_t *task, unsigned int cmd, unsigned long arg) return rtc_do_ioctl(cmd, arg, 1); #endif } - +EXPORT_SYMBOL(rtc_control); /* * The various file operations we support. @@ -910,11 +923,11 @@ static struct miscdevice rtc_dev = { #ifdef CONFIG_PROC_FS static const struct file_operations rtc_proc_fops = { - .owner = THIS_MODULE, - .open = rtc_proc_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, + .owner = THIS_MODULE, + .open = rtc_proc_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, }; #endif @@ -965,7 +978,7 @@ static int __init rtc_init(void) #ifdef CONFIG_SPARC32 for_each_ebus(ebus) { for_each_ebusdev(edev, ebus) { - if(strcmp(edev->prom_node->name, "rtc") == 0) { + if (strcmp(edev->prom_node->name, "rtc") == 0) { rtc_port = edev->resource[0].start; rtc_irq = edev->irqs[0]; goto found; @@ -986,7 +999,8 @@ found: * XXX Interrupt pin #7 in Espresso is shared between RTC and * PCI Slot 2 INTA# (and some INTx# in Slot 1). */ - if (request_irq(rtc_irq, rtc_interrupt, IRQF_SHARED, "rtc", (void *)&rtc_port)) { + if (request_irq(rtc_irq, rtc_interrupt, IRQF_SHARED, "rtc", + (void *)&rtc_port)) { rtc_has_irq = 0; printk(KERN_ERR "rtc: cannot register IRQ %d\n", rtc_irq); return -EIO; @@ -1015,16 +1029,26 @@ no_irq: #ifdef RTC_IRQ if (is_hpet_enabled()) { + int err; + rtc_int_handler_ptr = hpet_rtc_interrupt; + err = hpet_register_irq_handler(rtc_interrupt); + if (err != 0) { + printk(KERN_WARNING "hpet_register_irq_handler failed " + "in rtc_init()."); + return err; + } } else { rtc_int_handler_ptr = rtc_interrupt; } - if(request_irq(RTC_IRQ, rtc_int_handler_ptr, IRQF_DISABLED, "rtc", NULL)) { + if (request_irq(RTC_IRQ, rtc_int_handler_ptr, IRQF_DISABLED, + "rtc", NULL)) { /* Yeah right, seeing as irq 8 doesn't even hit the bus. */ rtc_has_irq = 0; printk(KERN_ERR "rtc: IRQ %d is not free.\n", RTC_IRQ); rtc_release_region(); + return -EIO; } hpet_rtc_timer_init(); @@ -1036,6 +1060,7 @@ no_irq: if (misc_register(&rtc_dev)) { #ifdef RTC_IRQ free_irq(RTC_IRQ, NULL); + hpet_unregister_irq_handler(rtc_interrupt); rtc_has_irq = 0; #endif rtc_release_region(); @@ -1052,21 +1077,21 @@ no_irq: #if defined(__alpha__) || defined(__mips__) rtc_freq = HZ; - + /* Each operating system on an Alpha uses its own epoch. Let's try to guess which one we are using now. */ - + if (rtc_is_updating() != 0) msleep(20); - + spin_lock_irq(&rtc_lock); year = CMOS_READ(RTC_YEAR); ctrl = CMOS_READ(RTC_CONTROL); spin_unlock_irq(&rtc_lock); - + if (!(ctrl & RTC_DM_BINARY) || RTC_ALWAYS_BCD) BCD_TO_BIN(year); /* This should never happen... */ - + if (year < 20) { epoch = 2000; guess = "SRM (post-2000)"; @@ -1087,7 +1112,8 @@ no_irq: #endif } if (guess) - printk(KERN_INFO "rtc: %s epoch (%lu) detected\n", guess, epoch); + printk(KERN_INFO "rtc: %s epoch (%lu) detected\n", + guess, epoch); #endif #ifdef RTC_IRQ if (rtc_has_irq == 0) @@ -1096,8 +1122,12 @@ no_irq: spin_lock_irq(&rtc_lock); rtc_freq = 1024; if (!hpet_set_periodic_freq(rtc_freq)) { - /* Initialize periodic freq. to CMOS reset default, which is 1024Hz */ - CMOS_WRITE(((CMOS_READ(RTC_FREQ_SELECT) & 0xF0) | 0x06), RTC_FREQ_SELECT); + /* + * Initialize periodic frequency to CMOS reset default, + * which is 1024Hz + */ + CMOS_WRITE(((CMOS_READ(RTC_FREQ_SELECT) & 0xF0) | 0x06), + RTC_FREQ_SELECT); } spin_unlock_irq(&rtc_lock); no_irq2: @@ -1110,20 +1140,22 @@ no_irq2: return 0; } -static void __exit rtc_exit (void) +static void __exit rtc_exit(void) { cleanup_sysctl(); - remove_proc_entry ("driver/rtc", NULL); + remove_proc_entry("driver/rtc", NULL); misc_deregister(&rtc_dev); #ifdef CONFIG_SPARC32 if (rtc_has_irq) - free_irq (rtc_irq, &rtc_port); + free_irq(rtc_irq, &rtc_port); #else rtc_release_region(); #ifdef RTC_IRQ - if (rtc_has_irq) - free_irq (RTC_IRQ, NULL); + if (rtc_has_irq) { + free_irq(RTC_IRQ, NULL); + hpet_unregister_irq_handler(hpet_rtc_interrupt); + } #endif #endif /* CONFIG_SPARC32 */ } @@ -1133,14 +1165,14 @@ module_exit(rtc_exit); #ifdef RTC_IRQ /* - * At IRQ rates >= 4096Hz, an interrupt may get lost altogether. + * At IRQ rates >= 4096Hz, an interrupt may get lost altogether. * (usually during an IDE disk interrupt, with IRQ unmasking off) * Since the interrupt handler doesn't get called, the IRQ status * byte doesn't get read, and the RTC stops generating interrupts. * A timer is set, and will call this function if/when that happens. * To get it out of this stalled state, we just read the status. * At least a jiffy of interrupts (rtc_freq/HZ) will have been lost. - * (You *really* shouldn't be trying to use a non-realtime system + * (You *really* shouldn't be trying to use a non-realtime system * for something that requires a steady > 1KHz signal anyways.) */ @@ -1148,7 +1180,7 @@ static void rtc_dropped_irq(unsigned long data) { unsigned long freq; - spin_lock_irq (&rtc_lock); + spin_lock_irq(&rtc_lock); if (hpet_rtc_dropped_irq()) { spin_unlock_irq(&rtc_lock); @@ -1167,13 +1199,15 @@ static void rtc_dropped_irq(unsigned long data) spin_unlock_irq(&rtc_lock); - if (printk_ratelimit()) - printk(KERN_WARNING "rtc: lost some interrupts at %ldHz.\n", freq); + if (printk_ratelimit()) { + printk(KERN_WARNING "rtc: lost some interrupts at %ldHz.\n", + freq); + } /* Now we have new data */ wake_up_interruptible(&rtc_wait); - kill_fasync (&rtc_async_queue, SIGIO, POLL_IN); + kill_fasync(&rtc_async_queue, SIGIO, POLL_IN); } #endif @@ -1277,7 +1311,7 @@ void rtc_get_rtc_time(struct rtc_time *rtc_tm) * can take just over 2ms. We wait 20ms. There is no need to * to poll-wait (up to 1s - eeccch) for the falling edge of RTC_UIP. * If you need to know *exactly* when a second has started, enable - * periodic update complete interrupts, (via ioctl) and then + * periodic update complete interrupts, (via ioctl) and then * immediately read /dev/rtc which will block until you get the IRQ. * Once the read clears, read the RTC time (again via ioctl). Easy. */ @@ -1307,8 +1341,7 @@ void rtc_get_rtc_time(struct rtc_time *rtc_tm) ctrl = CMOS_READ(RTC_CONTROL); spin_unlock_irqrestore(&rtc_lock, flags); - if (!(ctrl & RTC_DM_BINARY) || RTC_ALWAYS_BCD) - { + if (!(ctrl & RTC_DM_BINARY) || RTC_ALWAYS_BCD) { BCD_TO_BIN(rtc_tm->tm_sec); BCD_TO_BIN(rtc_tm->tm_min); BCD_TO_BIN(rtc_tm->tm_hour); @@ -1326,7 +1359,8 @@ void rtc_get_rtc_time(struct rtc_time *rtc_tm) * Account for differences between how the RTC uses the values * and how they are defined in a struct rtc_time; */ - if ((rtc_tm->tm_year += (epoch - 1900)) <= 69) + rtc_tm->tm_year += epoch - 1900; + if (rtc_tm->tm_year <= 69) rtc_tm->tm_year += 100; rtc_tm->tm_mon--; @@ -1347,8 +1381,7 @@ static void get_rtc_alm_time(struct rtc_time *alm_tm) ctrl = CMOS_READ(RTC_CONTROL); spin_unlock_irq(&rtc_lock); - if (!(ctrl & RTC_DM_BINARY) || RTC_ALWAYS_BCD) - { + if (!(ctrl & RTC_DM_BINARY) || RTC_ALWAYS_BCD) { BCD_TO_BIN(alm_tm->tm_sec); BCD_TO_BIN(alm_tm->tm_min); BCD_TO_BIN(alm_tm->tm_hour); diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 5efd5550f4ca..b730d6709529 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -1604,7 +1604,7 @@ static int __cpufreq_set_policy(struct cpufreq_policy *data, memcpy(&policy->cpuinfo, &data->cpuinfo, sizeof(struct cpufreq_cpuinfo)); - if (policy->min > data->min && policy->min > policy->max) { + if (policy->min > data->max || policy->max < data->min) { ret = -EINVAL; goto error_out; } diff --git a/drivers/firmware/dmi_scan.c b/drivers/firmware/dmi_scan.c index 5e596a7e3601..9008ed5ef4ce 100644 --- a/drivers/firmware/dmi_scan.c +++ b/drivers/firmware/dmi_scan.c @@ -8,6 +8,8 @@ #include <linux/slab.h> #include <asm/dmi.h> +static char dmi_empty_string[] = " "; + static char * __init dmi_string(const struct dmi_header *dm, u8 s) { const u8 *bp = ((u8 *) dm) + dm->length; @@ -21,11 +23,16 @@ static char * __init dmi_string(const struct dmi_header *dm, u8 s) } if (*bp != 0) { - str = dmi_alloc(strlen(bp) + 1); + size_t len = strlen(bp)+1; + size_t cmp_len = len > 8 ? 8 : len; + + if (!memcmp(bp, dmi_empty_string, cmp_len)) + return dmi_empty_string; + str = dmi_alloc(len); if (str != NULL) strcpy(str, bp); else - printk(KERN_ERR "dmi_string: out of memory.\n"); + printk(KERN_ERR "dmi_string: cannot allocate %Zu bytes.\n", len); } } @@ -175,12 +182,23 @@ static void __init dmi_save_devices(const struct dmi_header *dm) } } +static struct dmi_device empty_oem_string_dev = { + .name = dmi_empty_string, +}; + static void __init dmi_save_oem_strings_devices(const struct dmi_header *dm) { int i, count = *(u8 *)(dm + 1); struct dmi_device *dev; for (i = 1; i <= count; i++) { + char *devname = dmi_string(dm, i); + + if (!strcmp(devname, dmi_empty_string)) { + list_add(&empty_oem_string_dev.list, &dmi_devices); + continue; + } + dev = dmi_alloc(sizeof(*dev)); if (!dev) { printk(KERN_ERR @@ -189,7 +207,7 @@ static void __init dmi_save_oem_strings_devices(const struct dmi_header *dm) } dev->type = DMI_DEV_TYPE_OEM_STRING; - dev->name = dmi_string(dm, i); + dev->name = devname; dev->device_data = NULL; list_add(&dev->list, &dmi_devices); @@ -331,9 +349,11 @@ void __init dmi_scan_machine(void) rc = dmi_present(q); if (!rc) { dmi_available = 1; + dmi_iounmap(p, 0x10000); return; } } + dmi_iounmap(p, 0x10000); } out: printk(KERN_INFO "DMI not present or invalid.\n"); } diff --git a/drivers/ieee1394/Makefile b/drivers/ieee1394/Makefile index 489c133664d5..1f8153b57503 100644 --- a/drivers/ieee1394/Makefile +++ b/drivers/ieee1394/Makefile @@ -15,3 +15,4 @@ obj-$(CONFIG_IEEE1394_SBP2) += sbp2.o obj-$(CONFIG_IEEE1394_DV1394) += dv1394.o obj-$(CONFIG_IEEE1394_ETH1394) += eth1394.o +obj-$(CONFIG_PROVIDE_OHCI1394_DMA_INIT) += init_ohci1394_dma.o diff --git a/drivers/ieee1394/init_ohci1394_dma.c b/drivers/ieee1394/init_ohci1394_dma.c new file mode 100644 index 000000000000..ddaab6eb8ace --- /dev/null +++ b/drivers/ieee1394/init_ohci1394_dma.c @@ -0,0 +1,285 @@ +/* + * init_ohci1394_dma.c - Initializes physical DMA on all OHCI 1394 controllers + * + * Copyright (C) 2006-2007 Bernhard Kaindl <bk@suse.de> + * + * Derived from drivers/ieee1394/ohci1394.c and arch/x86/kernel/early-quirks.c + * this file has functions to: + * - scan the PCI very early on boot for all OHCI 1394-compliant controllers + * - reset and initialize them and make them join the IEEE1394 bus and + * - enable physical DMA on them to allow remote debugging + * + * All code and data is marked as __init and __initdata, respective as + * during boot, all OHCI1394 controllers may be claimed by the firewire + * stack and at this point, this code should not touch them anymore. + * + * To use physical DMA after the initialization of the firewire stack, + * be sure that the stack enables it and (re-)attach after the bus reset + * which may be caused by the firewire stack initialization. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that 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. + */ + +#include <linux/interrupt.h> /* for ohci1394.h */ +#include <linux/delay.h> +#include <linux/pci.h> /* for PCI defines */ +#include <linux/init_ohci1394_dma.h> +#include <asm/pci-direct.h> /* for direct PCI config space access */ +#include <asm/fixmap.h> + +#include "ieee1394_types.h" +#include "ohci1394.h" + +int __initdata init_ohci1394_dma_early; + +/* Reads a PHY register of an OHCI-1394 controller */ +static inline u8 __init get_phy_reg(struct ti_ohci *ohci, u8 addr) +{ + int i; + quadlet_t r; + + reg_write(ohci, OHCI1394_PhyControl, (addr << 8) | 0x00008000); + + for (i = 0; i < OHCI_LOOP_COUNT; i++) { + if (reg_read(ohci, OHCI1394_PhyControl) & 0x80000000) + break; + mdelay(1); + } + r = reg_read(ohci, OHCI1394_PhyControl); + + return (r & 0x00ff0000) >> 16; +} + +/* Writes to a PHY register of an OHCI-1394 controller */ +static inline void __init set_phy_reg(struct ti_ohci *ohci, u8 addr, u8 data) +{ + int i; + + reg_write(ohci, OHCI1394_PhyControl, (addr << 8) | data | 0x00004000); + + for (i = 0; i < OHCI_LOOP_COUNT; i++) { + u32 r = reg_read(ohci, OHCI1394_PhyControl); + if (!(r & 0x00004000)) + break; + mdelay(1); + } +} + +/* Resets an OHCI-1394 controller (for sane state before initialization) */ +static inline void __init init_ohci1394_soft_reset(struct ti_ohci *ohci) { + int i; + + reg_write(ohci, OHCI1394_HCControlSet, OHCI1394_HCControl_softReset); + + for (i = 0; i < OHCI_LOOP_COUNT; i++) { + if (!(reg_read(ohci, OHCI1394_HCControlSet) + & OHCI1394_HCControl_softReset)) + break; + mdelay(1); + } +} + +/* Basic OHCI-1394 register and port inititalization */ +static inline void __init init_ohci1394_initialize(struct ti_ohci *ohci) +{ + quadlet_t bus_options; + int num_ports, i; + + /* Put some defaults to these undefined bus options */ + bus_options = reg_read(ohci, OHCI1394_BusOptions); + bus_options |= 0x60000000; /* Enable CMC and ISC */ + bus_options &= ~0x00ff0000; /* XXX: Set cyc_clk_acc to zero for now */ + bus_options &= ~0x18000000; /* Disable PMC and BMC */ + reg_write(ohci, OHCI1394_BusOptions, bus_options); + + /* Set the bus number */ + reg_write(ohci, OHCI1394_NodeID, 0x0000ffc0); + + /* Enable posted writes */ + reg_write(ohci, OHCI1394_HCControlSet, + OHCI1394_HCControl_postedWriteEnable); + + /* Clear link control register */ + reg_write(ohci, OHCI1394_LinkControlClear, 0xffffffff); + + /* enable phys */ + reg_write(ohci, OHCI1394_LinkControlSet, + OHCI1394_LinkControl_RcvPhyPkt); + + /* Don't accept phy packets into AR request context */ + reg_write(ohci, OHCI1394_LinkControlClear, 0x00000400); + + /* Clear the Isochonouys interrupt masks */ + reg_write(ohci, OHCI1394_IsoRecvIntMaskClear, 0xffffffff); + reg_write(ohci, OHCI1394_IsoRecvIntEventClear, 0xffffffff); + reg_write(ohci, OHCI1394_IsoXmitIntMaskClear, 0xffffffff); + reg_write(ohci, OHCI1394_IsoXmitIntEventClear, 0xffffffff); + + /* Accept asyncronous transfer requests from all nodes for now */ + reg_write(ohci,OHCI1394_AsReqFilterHiSet, 0x80000000); + + /* Specify asyncronous transfer retries */ + reg_write(ohci, OHCI1394_ATRetries, + OHCI1394_MAX_AT_REQ_RETRIES | + (OHCI1394_MAX_AT_RESP_RETRIES<<4) | + (OHCI1394_MAX_PHYS_RESP_RETRIES<<8)); + + /* We don't want hardware swapping */ + reg_write(ohci, OHCI1394_HCControlClear, OHCI1394_HCControl_noByteSwap); + + /* Enable link */ + reg_write(ohci, OHCI1394_HCControlSet, OHCI1394_HCControl_linkEnable); + + /* If anything is connected to a port, make sure it is enabled */ + num_ports = get_phy_reg(ohci, 2) & 0xf; + for (i = 0; i < num_ports; i++) { + unsigned int status; + + set_phy_reg(ohci, 7, i); + status = get_phy_reg(ohci, 8); + + if (status & 0x20) + set_phy_reg(ohci, 8, status & ~1); + } +} + +/** + * init_ohci1394_wait_for_busresets - wait until bus resets are completed + * + * OHCI1394 initialization itself and any device going on- or offline + * and any cable issue cause a IEEE1394 bus reset. The OHCI1394 spec + * specifies that physical DMA is disabled on each bus reset and it + * has to be enabled after each bus reset when needed. We resort + * to polling here because on early boot, we have no interrupts. + */ +static inline void __init init_ohci1394_wait_for_busresets(struct ti_ohci *ohci) +{ + int i, events; + + for (i=0; i < 9; i++) { + mdelay(200); + events = reg_read(ohci, OHCI1394_IntEventSet); + if (events & OHCI1394_busReset) + reg_write(ohci, OHCI1394_IntEventClear, + OHCI1394_busReset); + } +} + +/** + * init_ohci1394_enable_physical_dma - Enable physical DMA for remote debugging + * This enables remote DMA access over IEEE1394 from every host for the low + * 4GB of address space. DMA accesses above 4GB are not available currently. + */ +static inline void __init init_ohci1394_enable_physical_dma(struct ti_ohci *hci) +{ + reg_write(hci, OHCI1394_PhyReqFilterHiSet, 0xffffffff); + reg_write(hci, OHCI1394_PhyReqFilterLoSet, 0xffffffff); + reg_write(hci, OHCI1394_PhyUpperBound, 0xffff0000); +} + +/** + * init_ohci1394_reset_and_init_dma - init controller and enable DMA + * This initializes the given controller and enables physical DMA engine in it. + */ +static inline void __init init_ohci1394_reset_and_init_dma(struct ti_ohci *ohci) +{ + /* Start off with a soft reset, clears everything to a sane state. */ + init_ohci1394_soft_reset(ohci); + + /* Accessing some registers without LPS enabled may cause lock up */ + reg_write(ohci, OHCI1394_HCControlSet, OHCI1394_HCControl_LPS); + + /* Disable and clear interrupts */ + reg_write(ohci, OHCI1394_IntEventClear, 0xffffffff); + reg_write(ohci, OHCI1394_IntMaskClear, 0xffffffff); + + mdelay(50); /* Wait 50msec to make sure we have full link enabled */ + + init_ohci1394_initialize(ohci); + /* + * The initialization causes at least one IEEE1394 bus reset. Enabling + * physical DMA only works *after* *all* bus resets have calmed down: + */ + init_ohci1394_wait_for_busresets(ohci); + + /* We had to wait and do this now if we want to debug early problems */ + init_ohci1394_enable_physical_dma(ohci); +} + +/** + * init_ohci1394_controller - Map the registers of the controller and init DMA + * This maps the registers of the specified controller and initializes it + */ +static inline void __init init_ohci1394_controller(int num, int slot, int func) +{ + unsigned long ohci_base; + struct ti_ohci ohci; + + printk(KERN_INFO "init_ohci1394_dma: initializing OHCI-1394" + " at %02x:%02x.%x\n", num, slot, func); + + ohci_base = read_pci_config(num, slot, func, PCI_BASE_ADDRESS_0+(0<<2)) + & PCI_BASE_ADDRESS_MEM_MASK; + + set_fixmap_nocache(FIX_OHCI1394_BASE, ohci_base); + + ohci.registers = (void *)fix_to_virt(FIX_OHCI1394_BASE); + + init_ohci1394_reset_and_init_dma(&ohci); +} + +/** + * debug_init_ohci1394_dma - scan for OHCI1394 controllers and init DMA on them + * Scans the whole PCI space for OHCI1394 controllers and inits DMA on them + */ +void __init init_ohci1394_dma_on_all_controllers(void) +{ + int num, slot, func; + + if (!early_pci_allowed()) + return; + + /* Poor man's PCI discovery, the only thing we can do at early boot */ + for (num = 0; num < 32; num++) { + for (slot = 0; slot < 32; slot++) { + for (func = 0; func < 8; func++) { + u32 class = read_pci_config(num,slot,func, + PCI_CLASS_REVISION); + if ((class == 0xffffffff)) + continue; /* No device at this func */ + + if (class>>8 != PCI_CLASS_SERIAL_FIREWIRE_OHCI) + continue; /* Not an OHCI-1394 device */ + + init_ohci1394_controller(num, slot, func); + break; /* Assume one controller per device */ + } + } + } + printk(KERN_INFO "init_ohci1394_dma: finished initializing OHCI DMA\n"); +} + +/** + * setup_init_ohci1394_early - enables early OHCI1394 DMA initialization + */ +static int __init setup_ohci1394_dma(char *opt) +{ + if (!strcmp(opt, "early")) + init_ohci1394_dma_early = 1; + return 0; +} + +/* passing ohci1394_dma=early on boot causes early OHCI1394 DMA initialization */ +early_param("ohci1394_dma", setup_ohci1394_dma); diff --git a/drivers/infiniband/ulp/srp/ib_srp.c b/drivers/infiniband/ulp/srp/ib_srp.c index f2d2c7e2c76b..195ce7c12319 100644 --- a/drivers/infiniband/ulp/srp/ib_srp.c +++ b/drivers/infiniband/ulp/srp/ib_srp.c @@ -1571,7 +1571,6 @@ static struct scsi_host_template srp_template = { .this_id = -1, .cmd_per_lun = SRP_SQ_SIZE, .use_clustering = ENABLE_CLUSTERING, - .use_sg_chaining = ENABLE_SG_CHAINING, .shost_attrs = srp_host_attrs }; diff --git a/drivers/input/mouse/pc110pad.c b/drivers/input/mouse/pc110pad.c index 8991ab0b4fe3..61cff8374e6c 100644 --- a/drivers/input/mouse/pc110pad.c +++ b/drivers/input/mouse/pc110pad.c @@ -39,6 +39,7 @@ #include <linux/init.h> #include <linux/interrupt.h> #include <linux/pci.h> +#include <linux/delay.h> #include <asm/io.h> #include <asm/irq.h> @@ -62,8 +63,10 @@ static irqreturn_t pc110pad_interrupt(int irq, void *ptr) int value = inb_p(pc110pad_io); int handshake = inb_p(pc110pad_io + 2); - outb_p(handshake | 1, pc110pad_io + 2); - outb_p(handshake & ~1, pc110pad_io + 2); + outb(handshake | 1, pc110pad_io + 2); + udelay(2); + outb(handshake & ~1, pc110pad_io + 2); + udelay(2); inb_p(0x64); pc110pad_data[pc110pad_count++] = value; diff --git a/drivers/kvm/Kconfig b/drivers/kvm/Kconfig deleted file mode 100644 index 656920636cb2..000000000000 --- a/drivers/kvm/Kconfig +++ /dev/null @@ -1,54 +0,0 @@ -# -# KVM configuration -# -menuconfig VIRTUALIZATION - bool "Virtualization" - depends on X86 - default y - ---help--- - Say Y here to get to see options for using your Linux host to run other - operating systems inside virtual machines (guests). - This option alone does not add any kernel code. - - If you say N, all options in this submenu will be skipped and disabled. - -if VIRTUALIZATION - -config KVM - tristate "Kernel-based Virtual Machine (KVM) support" - depends on X86 && EXPERIMENTAL - select PREEMPT_NOTIFIERS - select ANON_INODES - ---help--- - Support hosting fully virtualized guest machines using hardware - virtualization extensions. You will need a fairly recent - processor equipped with virtualization extensions. You will also - need to select one or more of the processor modules below. - - This module provides access to the hardware capabilities through - a character device node named /dev/kvm. - - To compile this as a module, choose M here: the module - will be called kvm. - - If unsure, say N. - -config KVM_INTEL - tristate "KVM for Intel processors support" - depends on KVM - ---help--- - Provides support for KVM on Intel processors equipped with the VT - extensions. - -config KVM_AMD - tristate "KVM for AMD processors support" - depends on KVM - ---help--- - Provides support for KVM on AMD processors equipped with the AMD-V - (SVM) extensions. - -# OK, it's a little counter-intuitive to do this, but it puts it neatly under -# the virtualization menu. -source drivers/lguest/Kconfig - -endif # VIRTUALIZATION diff --git a/drivers/kvm/Makefile b/drivers/kvm/Makefile deleted file mode 100644 index e5a8f4d3e973..000000000000 --- a/drivers/kvm/Makefile +++ /dev/null @@ -1,10 +0,0 @@ -# -# Makefile for Kernel-based Virtual Machine module -# - -kvm-objs := kvm_main.o mmu.o x86_emulate.o i8259.o irq.o lapic.o ioapic.o -obj-$(CONFIG_KVM) += kvm.o -kvm-intel-objs = vmx.o -obj-$(CONFIG_KVM_INTEL) += kvm-intel.o -kvm-amd-objs = svm.o -obj-$(CONFIG_KVM_AMD) += kvm-amd.o diff --git a/drivers/kvm/i8259.c b/drivers/kvm/i8259.c deleted file mode 100644 index a679157bc599..000000000000 --- a/drivers/kvm/i8259.c +++ /dev/null @@ -1,450 +0,0 @@ -/* - * 8259 interrupt controller emulation - * - * Copyright (c) 2003-2004 Fabrice Bellard - * Copyright (c) 2007 Intel Corporation - * - * Permission is hereby granted, free of charge, to any person obtaining a copy - * of this software and associated documentation files (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. - * Authors: - * Yaozu (Eddie) Dong <Eddie.dong@intel.com> - * Port from Qemu. - */ -#include <linux/mm.h> -#include "irq.h" - -/* - * set irq level. If an edge is detected, then the IRR is set to 1 - */ -static inline void pic_set_irq1(struct kvm_kpic_state *s, int irq, int level) -{ - int mask; - mask = 1 << irq; - if (s->elcr & mask) /* level triggered */ - if (level) { - s->irr |= mask; - s->last_irr |= mask; - } else { - s->irr &= ~mask; - s->last_irr &= ~mask; - } - else /* edge triggered */ - if (level) { - if ((s->last_irr & mask) == 0) - s->irr |= mask; - s->last_irr |= mask; - } else - s->last_irr &= ~mask; -} - -/* - * return the highest priority found in mask (highest = smallest - * number). Return 8 if no irq - */ -static inline int get_priority(struct kvm_kpic_state *s, int mask) -{ - int priority; - if (mask == 0) - return 8; - priority = 0; - while ((mask & (1 << ((priority + s->priority_add) & 7))) == 0) - priority++; - return priority; -} - -/* - * return the pic wanted interrupt. return -1 if none - */ -static int pic_get_irq(struct kvm_kpic_state *s) -{ - int mask, cur_priority, priority; - - mask = s->irr & ~s->imr; - priority = get_priority(s, mask); - if (priority == 8) - return -1; - /* - * compute current priority. If special fully nested mode on the - * master, the IRQ coming from the slave is not taken into account - * for the priority computation. - */ - mask = s->isr; - if (s->special_fully_nested_mode && s == &s->pics_state->pics[0]) - mask &= ~(1 << 2); - cur_priority = get_priority(s, mask); - if (priority < cur_priority) - /* - * higher priority found: an irq should be generated - */ - return (priority + s->priority_add) & 7; - else - return -1; -} - -/* - * raise irq to CPU if necessary. must be called every time the active - * irq may change - */ -static void pic_update_irq(struct kvm_pic *s) -{ - int irq2, irq; - - irq2 = pic_get_irq(&s->pics[1]); - if (irq2 >= 0) { - /* - * if irq request by slave pic, signal master PIC - */ - pic_set_irq1(&s->pics[0], 2, 1); - pic_set_irq1(&s->pics[0], 2, 0); - } - irq = pic_get_irq(&s->pics[0]); - if (irq >= 0) - s->irq_request(s->irq_request_opaque, 1); - else - s->irq_request(s->irq_request_opaque, 0); -} - -void kvm_pic_update_irq(struct kvm_pic *s) -{ - pic_update_irq(s); -} - -void kvm_pic_set_irq(void *opaque, int irq, int level) -{ - struct kvm_pic *s = opaque; - - pic_set_irq1(&s->pics[irq >> 3], irq & 7, level); - pic_update_irq(s); -} - -/* - * acknowledge interrupt 'irq' - */ -static inline void pic_intack(struct kvm_kpic_state *s, int irq) -{ - if (s->auto_eoi) { - if (s->rotate_on_auto_eoi) - s->priority_add = (irq + 1) & 7; - } else - s->isr |= (1 << irq); - /* - * We don't clear a level sensitive interrupt here - */ - if (!(s->elcr & (1 << irq))) - s->irr &= ~(1 << irq); -} - -int kvm_pic_read_irq(struct kvm_pic *s) -{ - int irq, irq2, intno; - - irq = pic_get_irq(&s->pics[0]); - if (irq >= 0) { - pic_intack(&s->pics[0], irq); - if (irq == 2) { - irq2 = pic_get_irq(&s->pics[1]); - if (irq2 >= 0) - pic_intack(&s->pics[1], irq2); - else - /* - * spurious IRQ on slave controller - */ - irq2 = 7; - intno = s->pics[1].irq_base + irq2; - irq = irq2 + 8; - } else - intno = s->pics[0].irq_base + irq; - } else { - /* - * spurious IRQ on host controller - */ - irq = 7; - intno = s->pics[0].irq_base + irq; - } - pic_update_irq(s); - - return intno; -} - -static void pic_reset(void *opaque) -{ - struct kvm_kpic_state *s = opaque; - - s->last_irr = 0; - s->irr = 0; - s->imr = 0; - s->isr = 0; - s->priority_add = 0; - s->irq_base = 0; - s->read_reg_select = 0; - s->poll = 0; - s->special_mask = 0; - s->init_state = 0; - s->auto_eoi = 0; - s->rotate_on_auto_eoi = 0; - s->special_fully_nested_mode = 0; - s->init4 = 0; -} - -static void pic_ioport_write(void *opaque, u32 addr, u32 val) -{ - struct kvm_kpic_state *s = opaque; - int priority, cmd, irq; - - addr &= 1; - if (addr == 0) { - if (val & 0x10) { - pic_reset(s); /* init */ - /* - * deassert a pending interrupt - */ - s->pics_state->irq_request(s->pics_state-> - irq_request_opaque, 0); - s->init_state = 1; - s->init4 = val & 1; - if (val & 0x02) - printk(KERN_ERR "single mode not supported"); - if (val & 0x08) - printk(KERN_ERR - "level sensitive irq not supported"); - } else if (val & 0x08) { - if (val & 0x04) - s->poll = 1; - if (val & 0x02) - s->read_reg_select = val & 1; - if (val & 0x40) - s->special_mask = (val >> 5) & 1; - } else { - cmd = val >> 5; - switch (cmd) { - case 0: - case 4: - s->rotate_on_auto_eoi = cmd >> 2; - break; - case 1: /* end of interrupt */ - case 5: - priority = get_priority(s, s->isr); - if (priority != 8) { - irq = (priority + s->priority_add) & 7; - s->isr &= ~(1 << irq); - if (cmd == 5) - s->priority_add = (irq + 1) & 7; - pic_update_irq(s->pics_state); - } - break; - case 3: - irq = val & 7; - s->isr &= ~(1 << irq); - pic_update_irq(s->pics_state); - break; - case 6: - s->priority_add = (val + 1) & 7; - pic_update_irq(s->pics_state); - break; - case 7: - irq = val & 7; - s->isr &= ~(1 << irq); - s->priority_add = (irq + 1) & 7; - pic_update_irq(s->pics_state); - break; - default: - break; /* no operation */ - } - } - } else - switch (s->init_state) { - case 0: /* normal mode */ - s->imr = val; - pic_update_irq(s->pics_state); - break; - case 1: - s->irq_base = val & 0xf8; - s->init_state = 2; - break; - case 2: - if (s->init4) - s->init_state = 3; - else - s->init_state = 0; - break; - case 3: - s->special_fully_nested_mode = (val >> 4) & 1; - s->auto_eoi = (val >> 1) & 1; - s->init_state = 0; - break; - } -} - -static u32 pic_poll_read(struct kvm_kpic_state *s, u32 addr1) -{ - int ret; - - ret = pic_get_irq(s); - if (ret >= 0) { - if (addr1 >> 7) { - s->pics_state->pics[0].isr &= ~(1 << 2); - s->pics_state->pics[0].irr &= ~(1 << 2); - } - s->irr &= ~(1 << ret); - s->isr &= ~(1 << ret); - if (addr1 >> 7 || ret != 2) - pic_update_irq(s->pics_state); - } else { - ret = 0x07; - pic_update_irq(s->pics_state); - } - - return ret; -} - -static u32 pic_ioport_read(void *opaque, u32 addr1) -{ - struct kvm_kpic_state *s = opaque; - unsigned int addr; - int ret; - - addr = addr1; - addr &= 1; - if (s->poll) { - ret = pic_poll_read(s, addr1); - s->poll = 0; - } else - if (addr == 0) - if (s->read_reg_select) - ret = s->isr; - else - ret = s->irr; - else - ret = s->imr; - return ret; -} - -static void elcr_ioport_write(void *opaque, u32 addr, u32 val) -{ - struct kvm_kpic_state *s = opaque; - s->elcr = val & s->elcr_mask; -} - -static u32 elcr_ioport_read(void *opaque, u32 addr1) -{ - struct kvm_kpic_state *s = opaque; - return s->elcr; -} - -static int picdev_in_range(struct kvm_io_device *this, gpa_t addr) -{ - switch (addr) { - case 0x20: - case 0x21: - case 0xa0: - case 0xa1: - case 0x4d0: - case 0x4d1: - return 1; - default: - return 0; - } -} - -static void picdev_write(struct kvm_io_device *this, - gpa_t addr, int len, const void *val) -{ - struct kvm_pic *s = this->private; - unsigned char data = *(unsigned char *)val; - - if (len != 1) { - if (printk_ratelimit()) - printk(KERN_ERR "PIC: non byte write\n"); - return; - } - switch (addr) { - case 0x20: - case 0x21: - case 0xa0: - case 0xa1: - pic_ioport_write(&s->pics[addr >> 7], addr, data); - break; - case 0x4d0: - case 0x4d1: - elcr_ioport_write(&s->pics[addr & 1], addr, data); - break; - } -} - -static void picdev_read(struct kvm_io_device *this, - gpa_t addr, int len, void *val) -{ - struct kvm_pic *s = this->private; - unsigned char data = 0; - - if (len != 1) { - if (printk_ratelimit()) - printk(KERN_ERR "PIC: non byte read\n"); - return; - } - switch (addr) { - case 0x20: - case 0x21: - case 0xa0: - case 0xa1: - data = pic_ioport_read(&s->pics[addr >> 7], addr); - break; - case 0x4d0: - case 0x4d1: - data = elcr_ioport_read(&s->pics[addr & 1], addr); - break; - } - *(unsigned char *)val = data; -} - -/* - * callback when PIC0 irq status changed - */ -static void pic_irq_request(void *opaque, int level) -{ - struct kvm *kvm = opaque; - struct kvm_vcpu *vcpu = kvm->vcpus[0]; - - pic_irqchip(kvm)->output = level; - if (vcpu) - kvm_vcpu_kick(vcpu); -} - -struct kvm_pic *kvm_create_pic(struct kvm *kvm) -{ - struct kvm_pic *s; - s = kzalloc(sizeof(struct kvm_pic), GFP_KERNEL); - if (!s) - return NULL; - s->pics[0].elcr_mask = 0xf8; - s->pics[1].elcr_mask = 0xde; - s->irq_request = pic_irq_request; - s->irq_request_opaque = kvm; - s->pics[0].pics_state = s; - s->pics[1].pics_state = s; - - /* - * Initialize PIO device - */ - s->dev.read = picdev_read; - s->dev.write = picdev_write; - s->dev.in_range = picdev_in_range; - s->dev.private = s; - kvm_io_bus_register_dev(&kvm->pio_bus, &s->dev); - return s; -} diff --git a/drivers/kvm/ioapic.c b/drivers/kvm/ioapic.c deleted file mode 100644 index c7992e667fdb..000000000000 --- a/drivers/kvm/ioapic.c +++ /dev/null @@ -1,388 +0,0 @@ -/* - * Copyright (C) 2001 MandrakeSoft S.A. - * - * MandrakeSoft S.A. - * 43, rue d'Aboukir - * 75002 Paris - France - * http://www.linux-mandrake.com/ - * http://www.mandrakesoft.com/ - * - * This library is free software; you can redistribute it and/or - * modify it under the terms of the GNU Lesser General Public - * License as published by the Free Software Foundation; either - * version 2 of the License, or (at your option) any later version. - * - * This library is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * Lesser General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public - * License along with this library; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - * - * Yunhong Jiang <yunhong.jiang@intel.com> - * Yaozu (Eddie) Dong <eddie.dong@intel.com> - * Based on Xen 3.1 code. - */ - -#include "kvm.h" -#include <linux/kvm.h> -#include <linux/mm.h> -#include <linux/highmem.h> -#include <linux/smp.h> -#include <linux/hrtimer.h> -#include <linux/io.h> -#include <asm/processor.h> -#include <asm/msr.h> -#include <asm/page.h> -#include <asm/current.h> -#include <asm/apicdef.h> -#include <asm/io_apic.h> -#include "irq.h" -/* #define ioapic_debug(fmt,arg...) printk(KERN_WARNING fmt,##arg) */ -#define ioapic_debug(fmt, arg...) -static void ioapic_deliver(struct kvm_ioapic *vioapic, int irq); - -static unsigned long ioapic_read_indirect(struct kvm_ioapic *ioapic, - unsigned long addr, - unsigned long length) -{ - unsigned long result = 0; - - switch (ioapic->ioregsel) { - case IOAPIC_REG_VERSION: - result = ((((IOAPIC_NUM_PINS - 1) & 0xff) << 16) - | (IOAPIC_VERSION_ID & 0xff)); - break; - - case IOAPIC_REG_APIC_ID: - case IOAPIC_REG_ARB_ID: - result = ((ioapic->id & 0xf) << 24); - break; - - default: - { - u32 redir_index = (ioapic->ioregsel - 0x10) >> 1; - u64 redir_content; - - ASSERT(redir_index < IOAPIC_NUM_PINS); - - redir_content = ioapic->redirtbl[redir_index].bits; - result = (ioapic->ioregsel & 0x1) ? - (redir_content >> 32) & 0xffffffff : - redir_content & 0xffffffff; - break; - } - } - - return result; -} - -static void ioapic_service(struct kvm_ioapic *ioapic, unsigned int idx) -{ - union ioapic_redir_entry *pent; - - pent = &ioapic->redirtbl[idx]; - - if (!pent->fields.mask) { - ioapic_deliver(ioapic, idx); - if (pent->fields.trig_mode == IOAPIC_LEVEL_TRIG) - pent->fields.remote_irr = 1; - } - if (!pent->fields.trig_mode) - ioapic->irr &= ~(1 << idx); -} - -static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val) -{ - unsigned index; - - switch (ioapic->ioregsel) { - case IOAPIC_REG_VERSION: - /* Writes are ignored. */ - break; - - case IOAPIC_REG_APIC_ID: - ioapic->id = (val >> 24) & 0xf; - break; - - case IOAPIC_REG_ARB_ID: - break; - - default: - index = (ioapic->ioregsel - 0x10) >> 1; - - ioapic_debug("change redir index %x val %x", index, val); - if (index >= IOAPIC_NUM_PINS) - return; - if (ioapic->ioregsel & 1) { - ioapic->redirtbl[index].bits &= 0xffffffff; - ioapic->redirtbl[index].bits |= (u64) val << 32; - } else { - ioapic->redirtbl[index].bits &= ~0xffffffffULL; - ioapic->redirtbl[index].bits |= (u32) val; - ioapic->redirtbl[index].fields.remote_irr = 0; - } - if (ioapic->irr & (1 << index)) - ioapic_service(ioapic, index); - break; - } -} - -static void ioapic_inj_irq(struct kvm_ioapic *ioapic, - struct kvm_lapic *target, - u8 vector, u8 trig_mode, u8 delivery_mode) -{ - ioapic_debug("irq %d trig %d deliv %d", vector, trig_mode, - delivery_mode); - - ASSERT((delivery_mode == dest_Fixed) || - (delivery_mode == dest_LowestPrio)); - - kvm_apic_set_irq(target, vector, trig_mode); -} - -static u32 ioapic_get_delivery_bitmask(struct kvm_ioapic *ioapic, u8 dest, - u8 dest_mode) -{ - u32 mask = 0; - int i; - struct kvm *kvm = ioapic->kvm; - struct kvm_vcpu *vcpu; - - ioapic_debug("dest %d dest_mode %d", dest, dest_mode); - - if (dest_mode == 0) { /* Physical mode. */ - if (dest == 0xFF) { /* Broadcast. */ - for (i = 0; i < KVM_MAX_VCPUS; ++i) - if (kvm->vcpus[i] && kvm->vcpus[i]->apic) - mask |= 1 << i; - return mask; - } - for (i = 0; i < KVM_MAX_VCPUS; ++i) { - vcpu = kvm->vcpus[i]; - if (!vcpu) - continue; - if (kvm_apic_match_physical_addr(vcpu->apic, dest)) { - if (vcpu->apic) - mask = 1 << i; - break; - } - } - } else if (dest != 0) /* Logical mode, MDA non-zero. */ - for (i = 0; i < KVM_MAX_VCPUS; ++i) { - vcpu = kvm->vcpus[i]; - if (!vcpu) - continue; - if (vcpu->apic && - kvm_apic_match_logical_addr(vcpu->apic, dest)) - mask |= 1 << vcpu->vcpu_id; - } - ioapic_debug("mask %x", mask); - return mask; -} - -static void ioapic_deliver(struct kvm_ioapic *ioapic, int irq) -{ - u8 dest = ioapic->redirtbl[irq].fields.dest_id; - u8 dest_mode = ioapic->redirtbl[irq].fields.dest_mode; - u8 delivery_mode = ioapic->redirtbl[irq].fields.delivery_mode; - u8 vector = ioapic->redirtbl[irq].fields.vector; - u8 trig_mode = ioapic->redirtbl[irq].fields.trig_mode; - u32 deliver_bitmask; - struct kvm_lapic *target; - struct kvm_vcpu *vcpu; - int vcpu_id; - - ioapic_debug("dest=%x dest_mode=%x delivery_mode=%x " - "vector=%x trig_mode=%x", - dest, dest_mode, delivery_mode, vector, trig_mode); - - deliver_bitmask = ioapic_get_delivery_bitmask(ioapic, dest, dest_mode); - if (!deliver_bitmask) { - ioapic_debug("no target on destination"); - return; - } - - switch (delivery_mode) { - case dest_LowestPrio: - target = - kvm_apic_round_robin(ioapic->kvm, vector, deliver_bitmask); - if (target != NULL) - ioapic_inj_irq(ioapic, target, vector, - trig_mode, delivery_mode); - else - ioapic_debug("null round robin: " - "mask=%x vector=%x delivery_mode=%x", - deliver_bitmask, vector, dest_LowestPrio); - break; - case dest_Fixed: - for (vcpu_id = 0; deliver_bitmask != 0; vcpu_id++) { - if (!(deliver_bitmask & (1 << vcpu_id))) - continue; - deliver_bitmask &= ~(1 << vcpu_id); - vcpu = ioapic->kvm->vcpus[vcpu_id]; - if (vcpu) { - target = vcpu->apic; - ioapic_inj_irq(ioapic, target, vector, - trig_mode, delivery_mode); - } - } - break; - - /* TODO: NMI */ - default: - printk(KERN_WARNING "Unsupported delivery mode %d\n", - delivery_mode); - break; - } -} - -void kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int level) -{ - u32 old_irr = ioapic->irr; - u32 mask = 1 << irq; - union ioapic_redir_entry entry; - - if (irq >= 0 && irq < IOAPIC_NUM_PINS) { - entry = ioapic->redirtbl[irq]; - level ^= entry.fields.polarity; - if (!level) - ioapic->irr &= ~mask; - else { - ioapic->irr |= mask; - if ((!entry.fields.trig_mode && old_irr != ioapic->irr) - || !entry.fields.remote_irr) - ioapic_service(ioapic, irq); - } - } -} - -static int get_eoi_gsi(struct kvm_ioapic *ioapic, int vector) -{ - int i; - - for (i = 0; i < IOAPIC_NUM_PINS; i++) - if (ioapic->redirtbl[i].fields.vector == vector) - return i; - return -1; -} - -void kvm_ioapic_update_eoi(struct kvm *kvm, int vector) -{ - struct kvm_ioapic *ioapic = kvm->vioapic; - union ioapic_redir_entry *ent; - int gsi; - - gsi = get_eoi_gsi(ioapic, vector); - if (gsi == -1) { - printk(KERN_WARNING "Can't find redir item for %d EOI\n", - vector); - return; - } - - ent = &ioapic->redirtbl[gsi]; - ASSERT(ent->fields.trig_mode == IOAPIC_LEVEL_TRIG); - - ent->fields.remote_irr = 0; - if (!ent->fields.mask && (ioapic->irr & (1 << gsi))) - ioapic_deliver(ioapic, gsi); -} - -static int ioapic_in_range(struct kvm_io_device *this, gpa_t addr) -{ - struct kvm_ioapic *ioapic = (struct kvm_ioapic *)this->private; - - return ((addr >= ioapic->base_address && - (addr < ioapic->base_address + IOAPIC_MEM_LENGTH))); -} - -static void ioapic_mmio_read(struct kvm_io_device *this, gpa_t addr, int len, - void *val) -{ - struct kvm_ioapic *ioapic = (struct kvm_ioapic *)this->private; - u32 result; - - ioapic_debug("addr %lx", (unsigned long)addr); - ASSERT(!(addr & 0xf)); /* check alignment */ - - addr &= 0xff; - switch (addr) { - case IOAPIC_REG_SELECT: - result = ioapic->ioregsel; - break; - - case IOAPIC_REG_WINDOW: - result = ioapic_read_indirect(ioapic, addr, len); - break; - - default: - result = 0; - break; - } - switch (len) { - case 8: - *(u64 *) val = result; - break; - case 1: - case 2: - case 4: - memcpy(val, (char *)&result, len); - break; - default: - printk(KERN_WARNING "ioapic: wrong length %d\n", len); - } -} - -static void ioapic_mmio_write(struct kvm_io_device *this, gpa_t addr, int len, - const void *val) -{ - struct kvm_ioapic *ioapic = (struct kvm_ioapic *)this->private; - u32 data; - - ioapic_debug("ioapic_mmio_write addr=%lx len=%d val=%p\n", - addr, len, val); - ASSERT(!(addr & 0xf)); /* check alignment */ - if (len == 4 || len == 8) - data = *(u32 *) val; - else { - printk(KERN_WARNING "ioapic: Unsupported size %d\n", len); - return; - } - - addr &= 0xff; - switch (addr) { - case IOAPIC_REG_SELECT: - ioapic->ioregsel = data; - break; - - case IOAPIC_REG_WINDOW: - ioapic_write_indirect(ioapic, data); - break; - - default: - break; - } -} - -int kvm_ioapic_init(struct kvm *kvm) -{ - struct kvm_ioapic *ioapic; - int i; - - ioapic = kzalloc(sizeof(struct kvm_ioapic), GFP_KERNEL); - if (!ioapic) - return -ENOMEM; - kvm->vioapic = ioapic; - for (i = 0; i < IOAPIC_NUM_PINS; i++) - ioapic->redirtbl[i].fields.mask = 1; - ioapic->base_address = IOAPIC_DEFAULT_BASE_ADDRESS; - ioapic->dev.read = ioapic_mmio_read; - ioapic->dev.write = ioapic_mmio_write; - ioapic->dev.in_range = ioapic_in_range; - ioapic->dev.private = ioapic; - ioapic->kvm = kvm; - kvm_io_bus_register_dev(&kvm->mmio_bus, &ioapic->dev); - return 0; -} diff --git a/drivers/kvm/irq.c b/drivers/kvm/irq.c deleted file mode 100644 index 7628c7ff628f..000000000000 --- a/drivers/kvm/irq.c +++ /dev/null @@ -1,98 +0,0 @@ -/* - * irq.c: API for in kernel interrupt controller - * Copyright (c) 2007, 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. - * Authors: - * Yaozu (Eddie) Dong <Eddie.dong@intel.com> - * - */ - -#include <linux/module.h> - -#include "kvm.h" -#include "irq.h" - -/* - * check if there is pending interrupt without - * intack. - */ -int kvm_cpu_has_interrupt(struct kvm_vcpu *v) -{ - struct kvm_pic *s; - - if (kvm_apic_has_interrupt(v) == -1) { /* LAPIC */ - if (kvm_apic_accept_pic_intr(v)) { - s = pic_irqchip(v->kvm); /* PIC */ - return s->output; - } else - return 0; - } - return 1; -} -EXPORT_SYMBOL_GPL(kvm_cpu_has_interrupt); - -/* - * Read pending interrupt vector and intack. - */ -int kvm_cpu_get_interrupt(struct kvm_vcpu *v) -{ - struct kvm_pic *s; - int vector; - - vector = kvm_get_apic_interrupt(v); /* APIC */ - if (vector == -1) { - if (kvm_apic_accept_pic_intr(v)) { - s = pic_irqchip(v->kvm); - s->output = 0; /* PIC */ - vector = kvm_pic_read_irq(s); - } - } - return vector; -} -EXPORT_SYMBOL_GPL(kvm_cpu_get_interrupt); - -static void vcpu_kick_intr(void *info) -{ -#ifdef DEBUG - struct kvm_vcpu *vcpu = (struct kvm_vcpu *)info; - printk(KERN_DEBUG "vcpu_kick_intr %p \n", vcpu); -#endif -} - -void kvm_vcpu_kick(struct kvm_vcpu *vcpu) -{ - int ipi_pcpu = vcpu->cpu; - - if (waitqueue_active(&vcpu->wq)) { - wake_up_interruptible(&vcpu->wq); - ++vcpu->stat.halt_wakeup; - } - if (vcpu->guest_mode) - smp_call_function_single(ipi_pcpu, vcpu_kick_intr, vcpu, 0, 0); -} - -void kvm_inject_pending_timer_irqs(struct kvm_vcpu *vcpu) -{ - kvm_inject_apic_timer_irqs(vcpu); - /* TODO: PIT, RTC etc. */ -} -EXPORT_SYMBOL_GPL(kvm_inject_pending_timer_irqs); - -void kvm_timer_intr_post(struct kvm_vcpu *vcpu, int vec) -{ - kvm_apic_timer_intr_post(vcpu, vec); - /* TODO: PIT, RTC etc. */ -} -EXPORT_SYMBOL_GPL(kvm_timer_intr_post); diff --git a/drivers/kvm/irq.h b/drivers/kvm/irq.h deleted file mode 100644 index 11fc014e2b30..000000000000 --- a/drivers/kvm/irq.h +++ /dev/null @@ -1,165 +0,0 @@ -/* - * irq.h: in kernel interrupt controller related definitions - * Copyright (c) 2007, 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. - * Authors: - * Yaozu (Eddie) Dong <Eddie.dong@intel.com> - * - */ - -#ifndef __IRQ_H -#define __IRQ_H - -#include "kvm.h" - -typedef void irq_request_func(void *opaque, int level); - -struct kvm_kpic_state { - u8 last_irr; /* edge detection */ - u8 irr; /* interrupt request register */ - u8 imr; /* interrupt mask register */ - u8 isr; /* interrupt service register */ - u8 priority_add; /* highest irq priority */ - u8 irq_base; - u8 read_reg_select; - u8 poll; - u8 special_mask; - u8 init_state; - u8 auto_eoi; - u8 rotate_on_auto_eoi; - u8 special_fully_nested_mode; - u8 init4; /* true if 4 byte init */ - u8 elcr; /* PIIX edge/trigger selection */ - u8 elcr_mask; - struct kvm_pic *pics_state; -}; - -struct kvm_pic { - struct kvm_kpic_state pics[2]; /* 0 is master pic, 1 is slave pic */ - irq_request_func *irq_request; - void *irq_request_opaque; - int output; /* intr from master PIC */ - struct kvm_io_device dev; -}; - -struct kvm_pic *kvm_create_pic(struct kvm *kvm); -void kvm_pic_set_irq(void *opaque, int irq, int level); -int kvm_pic_read_irq(struct kvm_pic *s); -int kvm_cpu_get_interrupt(struct kvm_vcpu *v); -int kvm_cpu_has_interrupt(struct kvm_vcpu *v); -void kvm_pic_update_irq(struct kvm_pic *s); - -#define IOAPIC_NUM_PINS KVM_IOAPIC_NUM_PINS -#define IOAPIC_VERSION_ID 0x11 /* IOAPIC version */ -#define IOAPIC_EDGE_TRIG 0 -#define IOAPIC_LEVEL_TRIG 1 - -#define IOAPIC_DEFAULT_BASE_ADDRESS 0xfec00000 -#define IOAPIC_MEM_LENGTH 0x100 - -/* Direct registers. */ -#define IOAPIC_REG_SELECT 0x00 -#define IOAPIC_REG_WINDOW 0x10 -#define IOAPIC_REG_EOI 0x40 /* IA64 IOSAPIC only */ - -/* Indirect registers. */ -#define IOAPIC_REG_APIC_ID 0x00 /* x86 IOAPIC only */ -#define IOAPIC_REG_VERSION 0x01 -#define IOAPIC_REG_ARB_ID 0x02 /* x86 IOAPIC only */ - -struct kvm_ioapic { - u64 base_address; - u32 ioregsel; - u32 id; - u32 irr; - u32 pad; - union ioapic_redir_entry { - u64 bits; - struct { - u8 vector; - u8 delivery_mode:3; - u8 dest_mode:1; - u8 delivery_status:1; - u8 polarity:1; - u8 remote_irr:1; - u8 trig_mode:1; - u8 mask:1; - u8 reserve:7; - u8 reserved[4]; - u8 dest_id; - } fields; - } redirtbl[IOAPIC_NUM_PINS]; - struct kvm_io_device dev; - struct kvm *kvm; -}; - -struct kvm_lapic { - unsigned long base_address; - struct kvm_io_device dev; - struct { - atomic_t pending; - s64 period; /* unit: ns */ - u32 divide_count; - ktime_t last_update; - struct hrtimer dev; - } timer; - struct kvm_vcpu *vcpu; - struct page *regs_page; - void *regs; -}; - -#ifdef DEBUG -#define ASSERT(x) \ -do { \ - if (!(x)) { \ - printk(KERN_EMERG "assertion failed %s: %d: %s\n", \ - __FILE__, __LINE__, #x); \ - BUG(); \ - } \ -} while (0) -#else -#define ASSERT(x) do { } while (0) -#endif - -void kvm_vcpu_kick(struct kvm_vcpu *vcpu); -int kvm_apic_has_interrupt(struct kvm_vcpu *vcpu); -int kvm_apic_accept_pic_intr(struct kvm_vcpu *vcpu); -int kvm_get_apic_interrupt(struct kvm_vcpu *vcpu); -int kvm_create_lapic(struct kvm_vcpu *vcpu); -void kvm_lapic_reset(struct kvm_vcpu *vcpu); -void kvm_free_apic(struct kvm_lapic *apic); -u64 kvm_lapic_get_cr8(struct kvm_vcpu *vcpu); -void kvm_lapic_set_tpr(struct kvm_vcpu *vcpu, unsigned long cr8); -void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value); -struct kvm_lapic *kvm_apic_round_robin(struct kvm *kvm, u8 vector, - unsigned long bitmap); -u64 kvm_get_apic_base(struct kvm_vcpu *vcpu); -void kvm_set_apic_base(struct kvm_vcpu *vcpu, u64 data); -int kvm_apic_match_physical_addr(struct kvm_lapic *apic, u16 dest); -void kvm_ioapic_update_eoi(struct kvm *kvm, int vector); -int kvm_apic_match_logical_addr(struct kvm_lapic *apic, u8 mda); -int kvm_apic_set_irq(struct kvm_lapic *apic, u8 vec, u8 trig); -void kvm_apic_post_state_restore(struct kvm_vcpu *vcpu); -int kvm_ioapic_init(struct kvm *kvm); -void kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int level); -int kvm_lapic_enabled(struct kvm_vcpu *vcpu); -int kvm_lapic_find_highest_irr(struct kvm_vcpu *vcpu); -void kvm_apic_timer_intr_post(struct kvm_vcpu *vcpu, int vec); -void kvm_timer_intr_post(struct kvm_vcpu *vcpu, int vec); -void kvm_inject_pending_timer_irqs(struct kvm_vcpu *vcpu); -void kvm_inject_apic_timer_irqs(struct kvm_vcpu *vcpu); -void kvm_migrate_apic_timer(struct kvm_vcpu *vcpu); - -#endif diff --git a/drivers/kvm/kvm.h b/drivers/kvm/kvm.h deleted file mode 100644 index 3b0bc4bda5f2..000000000000 --- a/drivers/kvm/kvm.h +++ /dev/null @@ -1,796 +0,0 @@ -#ifndef __KVM_H -#define __KVM_H - -/* - * This work is licensed under the terms of the GNU GPL, version 2. See - * the COPYING file in the top-level directory. - */ - -#include <linux/types.h> -#include <linux/list.h> -#include <linux/mutex.h> -#include <linux/spinlock.h> -#include <linux/signal.h> -#include <linux/sched.h> -#include <linux/mm.h> -#include <linux/preempt.h> -#include <asm/signal.h> - -#include <linux/kvm.h> -#include <linux/kvm_para.h> - -#define CR3_PAE_RESERVED_BITS ((X86_CR3_PWT | X86_CR3_PCD) - 1) -#define CR3_NONPAE_RESERVED_BITS ((PAGE_SIZE-1) & ~(X86_CR3_PWT | X86_CR3_PCD)) -#define CR3_L_MODE_RESERVED_BITS (CR3_NONPAE_RESERVED_BITS|0xFFFFFF0000000000ULL) - -#define KVM_GUEST_CR0_MASK \ - (X86_CR0_PG | X86_CR0_PE | X86_CR0_WP | X86_CR0_NE \ - | X86_CR0_NW | X86_CR0_CD) -#define KVM_VM_CR0_ALWAYS_ON \ - (X86_CR0_PG | X86_CR0_PE | X86_CR0_WP | X86_CR0_NE | X86_CR0_TS \ - | X86_CR0_MP) -#define KVM_GUEST_CR4_MASK \ - (X86_CR4_VME | X86_CR4_PSE | X86_CR4_PAE | X86_CR4_PGE | X86_CR4_VMXE) -#define KVM_PMODE_VM_CR4_ALWAYS_ON (X86_CR4_PAE | X86_CR4_VMXE) -#define KVM_RMODE_VM_CR4_ALWAYS_ON (X86_CR4_VME | X86_CR4_PAE | X86_CR4_VMXE) - -#define INVALID_PAGE (~(hpa_t)0) -#define UNMAPPED_GVA (~(gpa_t)0) - -#define KVM_MAX_VCPUS 4 -#define KVM_ALIAS_SLOTS 4 -#define KVM_MEMORY_SLOTS 8 -#define KVM_NUM_MMU_PAGES 1024 -#define KVM_MIN_FREE_MMU_PAGES 5 -#define KVM_REFILL_PAGES 25 -#define KVM_MAX_CPUID_ENTRIES 40 - -#define DE_VECTOR 0 -#define NM_VECTOR 7 -#define DF_VECTOR 8 -#define TS_VECTOR 10 -#define NP_VECTOR 11 -#define SS_VECTOR 12 -#define GP_VECTOR 13 -#define PF_VECTOR 14 - -#define SELECTOR_TI_MASK (1 << 2) -#define SELECTOR_RPL_MASK 0x03 - -#define IOPL_SHIFT 12 - -#define KVM_PIO_PAGE_OFFSET 1 - -/* - * vcpu->requests bit members - */ -#define KVM_TLB_FLUSH 0 - -/* - * Address types: - * - * gva - guest virtual address - * gpa - guest physical address - * gfn - guest frame number - * hva - host virtual address - * hpa - host physical address - * hfn - host frame number - */ - -typedef unsigned long gva_t; -typedef u64 gpa_t; -typedef unsigned long gfn_t; - -typedef unsigned long hva_t; -typedef u64 hpa_t; -typedef unsigned long hfn_t; - -#define NR_PTE_CHAIN_ENTRIES 5 - -struct kvm_pte_chain { - u64 *parent_ptes[NR_PTE_CHAIN_ENTRIES]; - struct hlist_node link; -}; - -/* - * kvm_mmu_page_role, below, is defined as: - * - * bits 0:3 - total guest paging levels (2-4, or zero for real mode) - * bits 4:7 - page table level for this shadow (1-4) - * bits 8:9 - page table quadrant for 2-level guests - * bit 16 - "metaphysical" - gfn is not a real page (huge page/real mode) - * bits 17:19 - "access" - the user, writable, and nx bits of a huge page pde - */ -union kvm_mmu_page_role { - unsigned word; - struct { - unsigned glevels : 4; - unsigned level : 4; - unsigned quadrant : 2; - unsigned pad_for_nice_hex_output : 6; - unsigned metaphysical : 1; - unsigned hugepage_access : 3; - }; -}; - -struct kvm_mmu_page { - struct list_head link; - struct hlist_node hash_link; - - /* - * The following two entries are used to key the shadow page in the - * hash table. - */ - gfn_t gfn; - union kvm_mmu_page_role role; - - u64 *spt; - unsigned long slot_bitmap; /* One bit set per slot which has memory - * in this shadow page. - */ - int multimapped; /* More than one parent_pte? */ - int root_count; /* Currently serving as active root */ - union { - u64 *parent_pte; /* !multimapped */ - struct hlist_head parent_ptes; /* multimapped, kvm_pte_chain */ - }; -}; - -struct kvm_vcpu; -extern struct kmem_cache *kvm_vcpu_cache; - -/* - * x86 supports 3 paging modes (4-level 64-bit, 3-level 64-bit, and 2-level - * 32-bit). The kvm_mmu structure abstracts the details of the current mmu - * mode. - */ -struct kvm_mmu { - void (*new_cr3)(struct kvm_vcpu *vcpu); - int (*page_fault)(struct kvm_vcpu *vcpu, gva_t gva, u32 err); - void (*free)(struct kvm_vcpu *vcpu); - gpa_t (*gva_to_gpa)(struct kvm_vcpu *vcpu, gva_t gva); - hpa_t root_hpa; - int root_level; - int shadow_root_level; - - u64 *pae_root; -}; - -#define KVM_NR_MEM_OBJS 20 - -struct kvm_mmu_memory_cache { - int nobjs; - void *objects[KVM_NR_MEM_OBJS]; -}; - -/* - * We don't want allocation failures within the mmu code, so we preallocate - * enough memory for a single page fault in a cache. - */ -struct kvm_guest_debug { - int enabled; - unsigned long bp[4]; - int singlestep; -}; - -enum { - VCPU_REGS_RAX = 0, - VCPU_REGS_RCX = 1, - VCPU_REGS_RDX = 2, - VCPU_REGS_RBX = 3, - VCPU_REGS_RSP = 4, - VCPU_REGS_RBP = 5, - VCPU_REGS_RSI = 6, - VCPU_REGS_RDI = 7, -#ifdef CONFIG_X86_64 - VCPU_REGS_R8 = 8, - VCPU_REGS_R9 = 9, - VCPU_REGS_R10 = 10, - VCPU_REGS_R11 = 11, - VCPU_REGS_R12 = 12, - VCPU_REGS_R13 = 13, - VCPU_REGS_R14 = 14, - VCPU_REGS_R15 = 15, -#endif - NR_VCPU_REGS -}; - -enum { - VCPU_SREG_CS, - VCPU_SREG_DS, - VCPU_SREG_ES, - VCPU_SREG_FS, - VCPU_SREG_GS, - VCPU_SREG_SS, - VCPU_SREG_TR, - VCPU_SREG_LDTR, -}; - -struct kvm_pio_request { - unsigned long count; - int cur_count; - struct page *guest_pages[2]; - unsigned guest_page_offset; - int in; - int port; - int size; - int string; - int down; - int rep; -}; - -struct kvm_stat { - u32 pf_fixed; - u32 pf_guest; - u32 tlb_flush; - u32 invlpg; - - u32 exits; - u32 io_exits; - u32 mmio_exits; - u32 signal_exits; - u32 irq_window_exits; - u32 halt_exits; - u32 halt_wakeup; - u32 request_irq_exits; - u32 irq_exits; - u32 light_exits; - u32 efer_reload; -}; - -struct kvm_io_device { - void (*read)(struct kvm_io_device *this, - gpa_t addr, - int len, - void *val); - void (*write)(struct kvm_io_device *this, - gpa_t addr, - int len, - const void *val); - int (*in_range)(struct kvm_io_device *this, gpa_t addr); - void (*destructor)(struct kvm_io_device *this); - - void *private; -}; - -static inline void kvm_iodevice_read(struct kvm_io_device *dev, - gpa_t addr, - int len, - void *val) -{ - dev->read(dev, addr, len, val); -} - -static inline void kvm_iodevice_write(struct kvm_io_device *dev, - gpa_t addr, - int len, - const void *val) -{ - dev->write(dev, addr, len, val); -} - -static inline int kvm_iodevice_inrange(struct kvm_io_device *dev, gpa_t addr) -{ - return dev->in_range(dev, addr); -} - -static inline void kvm_iodevice_destructor(struct kvm_io_device *dev) -{ - if (dev->destructor) - dev->destructor(dev); -} - -/* - * It would be nice to use something smarter than a linear search, TBD... - * Thankfully we dont expect many devices to register (famous last words :), - * so until then it will suffice. At least its abstracted so we can change - * in one place. - */ -struct kvm_io_bus { - int dev_count; -#define NR_IOBUS_DEVS 6 - struct kvm_io_device *devs[NR_IOBUS_DEVS]; -}; - -void kvm_io_bus_init(struct kvm_io_bus *bus); -void kvm_io_bus_destroy(struct kvm_io_bus *bus); -struct kvm_io_device *kvm_io_bus_find_dev(struct kvm_io_bus *bus, gpa_t addr); -void kvm_io_bus_register_dev(struct kvm_io_bus *bus, - struct kvm_io_device *dev); - -struct kvm_vcpu { - struct kvm *kvm; - struct preempt_notifier preempt_notifier; - int vcpu_id; - struct mutex mutex; - int cpu; - u64 host_tsc; - struct kvm_run *run; - int interrupt_window_open; - int guest_mode; - unsigned long requests; - unsigned long irq_summary; /* bit vector: 1 per word in irq_pending */ - DECLARE_BITMAP(irq_pending, KVM_NR_INTERRUPTS); - unsigned long regs[NR_VCPU_REGS]; /* for rsp: vcpu_load_rsp_rip() */ - unsigned long rip; /* needs vcpu_load_rsp_rip() */ - - unsigned long cr0; - unsigned long cr2; - unsigned long cr3; - gpa_t para_state_gpa; - struct page *para_state_page; - gpa_t hypercall_gpa; - unsigned long cr4; - unsigned long cr8; - u64 pdptrs[4]; /* pae */ - u64 shadow_efer; - u64 apic_base; - struct kvm_lapic *apic; /* kernel irqchip context */ -#define VCPU_MP_STATE_RUNNABLE 0 -#define VCPU_MP_STATE_UNINITIALIZED 1 -#define VCPU_MP_STATE_INIT_RECEIVED 2 -#define VCPU_MP_STATE_SIPI_RECEIVED 3 -#define VCPU_MP_STATE_HALTED 4 - int mp_state; - int sipi_vector; - u64 ia32_misc_enable_msr; - - struct kvm_mmu mmu; - - struct kvm_mmu_memory_cache mmu_pte_chain_cache; - struct kvm_mmu_memory_cache mmu_rmap_desc_cache; - struct kvm_mmu_memory_cache mmu_page_cache; - struct kvm_mmu_memory_cache mmu_page_header_cache; - - gfn_t last_pt_write_gfn; - int last_pt_write_count; - - struct kvm_guest_debug guest_debug; - - struct i387_fxsave_struct host_fx_image; - struct i387_fxsave_struct guest_fx_image; - int fpu_active; - int guest_fpu_loaded; - - int mmio_needed; - int mmio_read_completed; - int mmio_is_write; - int mmio_size; - unsigned char mmio_data[8]; - gpa_t mmio_phys_addr; - gva_t mmio_fault_cr2; - struct kvm_pio_request pio; - void *pio_data; - wait_queue_head_t wq; - - int sigset_active; - sigset_t sigset; - - struct kvm_stat stat; - - struct { - int active; - u8 save_iopl; - struct kvm_save_segment { - u16 selector; - unsigned long base; - u32 limit; - u32 ar; - } tr, es, ds, fs, gs; - } rmode; - int halt_request; /* real mode on Intel only */ - - int cpuid_nent; - struct kvm_cpuid_entry cpuid_entries[KVM_MAX_CPUID_ENTRIES]; -}; - -struct kvm_mem_alias { - gfn_t base_gfn; - unsigned long npages; - gfn_t target_gfn; -}; - -struct kvm_memory_slot { - gfn_t base_gfn; - unsigned long npages; - unsigned long flags; - struct page **phys_mem; - unsigned long *dirty_bitmap; -}; - -struct kvm { - struct mutex lock; /* protects everything except vcpus */ - int naliases; - struct kvm_mem_alias aliases[KVM_ALIAS_SLOTS]; - int nmemslots; - struct kvm_memory_slot memslots[KVM_MEMORY_SLOTS]; - /* - * Hash table of struct kvm_mmu_page. - */ - struct list_head active_mmu_pages; - int n_free_mmu_pages; - struct hlist_head mmu_page_hash[KVM_NUM_MMU_PAGES]; - struct kvm_vcpu *vcpus[KVM_MAX_VCPUS]; - unsigned long rmap_overflow; - struct list_head vm_list; - struct file *filp; - struct kvm_io_bus mmio_bus; - struct kvm_io_bus pio_bus; - struct kvm_pic *vpic; - struct kvm_ioapic *vioapic; - int round_robin_prev_vcpu; -}; - -static inline struct kvm_pic *pic_irqchip(struct kvm *kvm) -{ - return kvm->vpic; -} - -static inline struct kvm_ioapic *ioapic_irqchip(struct kvm *kvm) -{ - return kvm->vioapic; -} - -static inline int irqchip_in_kernel(struct kvm *kvm) -{ - return pic_irqchip(kvm) != 0; -} - -struct descriptor_table { - u16 limit; - unsigned long base; -} __attribute__((packed)); - -struct kvm_x86_ops { - int (*cpu_has_kvm_support)(void); /* __init */ - int (*disabled_by_bios)(void); /* __init */ - void (*hardware_enable)(void *dummy); /* __init */ - void (*hardware_disable)(void *dummy); - void (*check_processor_compatibility)(void *rtn); - int (*hardware_setup)(void); /* __init */ - void (*hardware_unsetup)(void); /* __exit */ - - /* Create, but do not attach this VCPU */ - struct kvm_vcpu *(*vcpu_create)(struct kvm *kvm, unsigned id); - void (*vcpu_free)(struct kvm_vcpu *vcpu); - void (*vcpu_reset)(struct kvm_vcpu *vcpu); - - void (*prepare_guest_switch)(struct kvm_vcpu *vcpu); - void (*vcpu_load)(struct kvm_vcpu *vcpu, int cpu); - void (*vcpu_put)(struct kvm_vcpu *vcpu); - void (*vcpu_decache)(struct kvm_vcpu *vcpu); - - int (*set_guest_debug)(struct kvm_vcpu *vcpu, - struct kvm_debug_guest *dbg); - void (*guest_debug_pre)(struct kvm_vcpu *vcpu); - int (*get_msr)(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata); - int (*set_msr)(struct kvm_vcpu *vcpu, u32 msr_index, u64 data); - u64 (*get_segment_base)(struct kvm_vcpu *vcpu, int seg); - void (*get_segment)(struct kvm_vcpu *vcpu, - struct kvm_segment *var, int seg); - void (*set_segment)(struct kvm_vcpu *vcpu, - struct kvm_segment *var, int seg); - void (*get_cs_db_l_bits)(struct kvm_vcpu *vcpu, int *db, int *l); - void (*decache_cr4_guest_bits)(struct kvm_vcpu *vcpu); - void (*set_cr0)(struct kvm_vcpu *vcpu, unsigned long cr0); - void (*set_cr3)(struct kvm_vcpu *vcpu, unsigned long cr3); - void (*set_cr4)(struct kvm_vcpu *vcpu, unsigned long cr4); - void (*set_efer)(struct kvm_vcpu *vcpu, u64 efer); - void (*get_idt)(struct kvm_vcpu *vcpu, struct descriptor_table *dt); - void (*set_idt)(struct kvm_vcpu *vcpu, struct descriptor_table *dt); - void (*get_gdt)(struct kvm_vcpu *vcpu, struct descriptor_table *dt); - void (*set_gdt)(struct kvm_vcpu *vcpu, struct descriptor_table *dt); - unsigned long (*get_dr)(struct kvm_vcpu *vcpu, int dr); - void (*set_dr)(struct kvm_vcpu *vcpu, int dr, unsigned long value, - int *exception); - void (*cache_regs)(struct kvm_vcpu *vcpu); - void (*decache_regs)(struct kvm_vcpu *vcpu); - unsigned long (*get_rflags)(struct kvm_vcpu *vcpu); - void (*set_rflags)(struct kvm_vcpu *vcpu, unsigned long rflags); - - void (*tlb_flush)(struct kvm_vcpu *vcpu); - void (*inject_page_fault)(struct kvm_vcpu *vcpu, - unsigned long addr, u32 err_code); - - void (*inject_gp)(struct kvm_vcpu *vcpu, unsigned err_code); - - void (*run)(struct kvm_vcpu *vcpu, struct kvm_run *run); - int (*handle_exit)(struct kvm_run *run, struct kvm_vcpu *vcpu); - void (*skip_emulated_instruction)(struct kvm_vcpu *vcpu); - void (*patch_hypercall)(struct kvm_vcpu *vcpu, - unsigned char *hypercall_addr); - int (*get_irq)(struct kvm_vcpu *vcpu); - void (*set_irq)(struct kvm_vcpu *vcpu, int vec); - void (*inject_pending_irq)(struct kvm_vcpu *vcpu); - void (*inject_pending_vectors)(struct kvm_vcpu *vcpu, - struct kvm_run *run); -}; - -extern struct kvm_x86_ops *kvm_x86_ops; - -/* The guest did something we don't support. */ -#define pr_unimpl(vcpu, fmt, ...) \ - do { \ - if (printk_ratelimit()) \ - printk(KERN_ERR "kvm: %i: cpu%i " fmt, \ - current->tgid, (vcpu)->vcpu_id , ## __VA_ARGS__); \ - } while(0) - -#define kvm_printf(kvm, fmt ...) printk(KERN_DEBUG fmt) -#define vcpu_printf(vcpu, fmt...) kvm_printf(vcpu->kvm, fmt) - -int kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id); -void kvm_vcpu_uninit(struct kvm_vcpu *vcpu); - -int kvm_init_x86(struct kvm_x86_ops *ops, unsigned int vcpu_size, - struct module *module); -void kvm_exit_x86(void); - -int kvm_mmu_module_init(void); -void kvm_mmu_module_exit(void); - -void kvm_mmu_destroy(struct kvm_vcpu *vcpu); -int kvm_mmu_create(struct kvm_vcpu *vcpu); -int kvm_mmu_setup(struct kvm_vcpu *vcpu); - -int kvm_mmu_reset_context(struct kvm_vcpu *vcpu); -void kvm_mmu_slot_remove_write_access(struct kvm *kvm, int slot); -void kvm_mmu_zap_all(struct kvm *kvm); - -hpa_t gpa_to_hpa(struct kvm_vcpu *vcpu, gpa_t gpa); -#define HPA_MSB ((sizeof(hpa_t) * 8) - 1) -#define HPA_ERR_MASK ((hpa_t)1 << HPA_MSB) -static inline int is_error_hpa(hpa_t hpa) { return hpa >> HPA_MSB; } -hpa_t gva_to_hpa(struct kvm_vcpu *vcpu, gva_t gva); -struct page *gva_to_page(struct kvm_vcpu *vcpu, gva_t gva); - -extern hpa_t bad_page_address; - -struct page *gfn_to_page(struct kvm *kvm, gfn_t gfn); -struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn); -void mark_page_dirty(struct kvm *kvm, gfn_t gfn); - -enum emulation_result { - EMULATE_DONE, /* no further processing */ - EMULATE_DO_MMIO, /* kvm_run filled with mmio request */ - EMULATE_FAIL, /* can't emulate this instruction */ -}; - -int emulate_instruction(struct kvm_vcpu *vcpu, struct kvm_run *run, - unsigned long cr2, u16 error_code); -void kvm_report_emulation_failure(struct kvm_vcpu *cvpu, const char *context); -void realmode_lgdt(struct kvm_vcpu *vcpu, u16 size, unsigned long address); -void realmode_lidt(struct kvm_vcpu *vcpu, u16 size, unsigned long address); -void realmode_lmsw(struct kvm_vcpu *vcpu, unsigned long msw, - unsigned long *rflags); - -unsigned long realmode_get_cr(struct kvm_vcpu *vcpu, int cr); -void realmode_set_cr(struct kvm_vcpu *vcpu, int cr, unsigned long value, - unsigned long *rflags); -int kvm_get_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *data); -int kvm_set_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data); - -struct x86_emulate_ctxt; - -int kvm_emulate_pio (struct kvm_vcpu *vcpu, struct kvm_run *run, int in, - int size, unsigned port); -int kvm_emulate_pio_string(struct kvm_vcpu *vcpu, struct kvm_run *run, int in, - int size, unsigned long count, int down, - gva_t address, int rep, unsigned port); -void kvm_emulate_cpuid(struct kvm_vcpu *vcpu); -int kvm_emulate_halt(struct kvm_vcpu *vcpu); -int emulate_invlpg(struct kvm_vcpu *vcpu, gva_t address); -int emulate_clts(struct kvm_vcpu *vcpu); -int emulator_get_dr(struct x86_emulate_ctxt* ctxt, int dr, - unsigned long *dest); -int emulator_set_dr(struct x86_emulate_ctxt *ctxt, int dr, - unsigned long value); - -void set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0); -void set_cr3(struct kvm_vcpu *vcpu, unsigned long cr0); -void set_cr4(struct kvm_vcpu *vcpu, unsigned long cr0); -void set_cr8(struct kvm_vcpu *vcpu, unsigned long cr0); -unsigned long get_cr8(struct kvm_vcpu *vcpu); -void lmsw(struct kvm_vcpu *vcpu, unsigned long msw); -void kvm_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l); - -int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata); -int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data); - -void fx_init(struct kvm_vcpu *vcpu); - -void kvm_resched(struct kvm_vcpu *vcpu); -void kvm_load_guest_fpu(struct kvm_vcpu *vcpu); -void kvm_put_guest_fpu(struct kvm_vcpu *vcpu); -void kvm_flush_remote_tlbs(struct kvm *kvm); - -int emulator_read_std(unsigned long addr, - void *val, - unsigned int bytes, - struct kvm_vcpu *vcpu); -int emulator_write_emulated(unsigned long addr, - const void *val, - unsigned int bytes, - struct kvm_vcpu *vcpu); - -unsigned long segment_base(u16 selector); - -void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, - const u8 *new, int bytes); -int kvm_mmu_unprotect_page_virt(struct kvm_vcpu *vcpu, gva_t gva); -void __kvm_mmu_free_some_pages(struct kvm_vcpu *vcpu); -int kvm_mmu_load(struct kvm_vcpu *vcpu); -void kvm_mmu_unload(struct kvm_vcpu *vcpu); - -int kvm_hypercall(struct kvm_vcpu *vcpu, struct kvm_run *run); - -static inline void kvm_guest_enter(void) -{ - current->flags |= PF_VCPU; -} - -static inline void kvm_guest_exit(void) -{ - current->flags &= ~PF_VCPU; -} - -static inline int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t gva, - u32 error_code) -{ - return vcpu->mmu.page_fault(vcpu, gva, error_code); -} - -static inline void kvm_mmu_free_some_pages(struct kvm_vcpu *vcpu) -{ - if (unlikely(vcpu->kvm->n_free_mmu_pages < KVM_MIN_FREE_MMU_PAGES)) - __kvm_mmu_free_some_pages(vcpu); -} - -static inline int kvm_mmu_reload(struct kvm_vcpu *vcpu) -{ - if (likely(vcpu->mmu.root_hpa != INVALID_PAGE)) - return 0; - - return kvm_mmu_load(vcpu); -} - -static inline int is_long_mode(struct kvm_vcpu *vcpu) -{ -#ifdef CONFIG_X86_64 - return vcpu->shadow_efer & EFER_LME; -#else - return 0; -#endif -} - -static inline int is_pae(struct kvm_vcpu *vcpu) -{ - return vcpu->cr4 & X86_CR4_PAE; -} - -static inline int is_pse(struct kvm_vcpu *vcpu) -{ - return vcpu->cr4 & X86_CR4_PSE; -} - -static inline int is_paging(struct kvm_vcpu *vcpu) -{ - return vcpu->cr0 & X86_CR0_PG; -} - -static inline int memslot_id(struct kvm *kvm, struct kvm_memory_slot *slot) -{ - return slot - kvm->memslots; -} - -static inline struct kvm_mmu_page *page_header(hpa_t shadow_page) -{ - struct page *page = pfn_to_page(shadow_page >> PAGE_SHIFT); - - return (struct kvm_mmu_page *)page_private(page); -} - -static inline u16 read_fs(void) -{ - u16 seg; - asm ("mov %%fs, %0" : "=g"(seg)); - return seg; -} - -static inline u16 read_gs(void) -{ - u16 seg; - asm ("mov %%gs, %0" : "=g"(seg)); - return seg; -} - -static inline u16 read_ldt(void) -{ - u16 ldt; - asm ("sldt %0" : "=g"(ldt)); - return ldt; -} - -static inline void load_fs(u16 sel) -{ - asm ("mov %0, %%fs" : : "rm"(sel)); -} - -static inline void load_gs(u16 sel) -{ - asm ("mov %0, %%gs" : : "rm"(sel)); -} - -#ifndef load_ldt -static inline void load_ldt(u16 sel) -{ - asm ("lldt %0" : : "rm"(sel)); -} -#endif - -static inline void get_idt(struct descriptor_table *table) -{ - asm ("sidt %0" : "=m"(*table)); -} - -static inline void get_gdt(struct descriptor_table *table) -{ - asm ("sgdt %0" : "=m"(*table)); -} - -static inline unsigned long read_tr_base(void) -{ - u16 tr; - asm ("str %0" : "=g"(tr)); - return segment_base(tr); -} - -#ifdef CONFIG_X86_64 -static inline unsigned long read_msr(unsigned long msr) -{ - u64 value; - - rdmsrl(msr, value); - return value; -} -#endif - -static inline void fx_save(struct i387_fxsave_struct *image) -{ - asm ("fxsave (%0)":: "r" (image)); -} - -static inline void fx_restore(struct i387_fxsave_struct *image) -{ - asm ("fxrstor (%0)":: "r" (image)); -} - -static inline void fpu_init(void) -{ - asm ("finit"); -} - -static inline u32 get_rdx_init_val(void) -{ - return 0x600; /* P6 family */ -} - -#define ASM_VMX_VMCLEAR_RAX ".byte 0x66, 0x0f, 0xc7, 0x30" -#define ASM_VMX_VMLAUNCH ".byte 0x0f, 0x01, 0xc2" -#define ASM_VMX_VMRESUME ".byte 0x0f, 0x01, 0xc3" -#define ASM_VMX_VMPTRLD_RAX ".byte 0x0f, 0xc7, 0x30" -#define ASM_VMX_VMREAD_RDX_RAX ".byte 0x0f, 0x78, 0xd0" -#define ASM_VMX_VMWRITE_RAX_RDX ".byte 0x0f, 0x79, 0xd0" -#define ASM_VMX_VMWRITE_RSP_RDX ".byte 0x0f, 0x79, 0xd4" -#define ASM_VMX_VMXOFF ".byte 0x0f, 0x01, 0xc4" -#define ASM_VMX_VMXON_RAX ".byte 0xf3, 0x0f, 0xc7, 0x30" - -#define MSR_IA32_TIME_STAMP_COUNTER 0x010 - -#define TSS_IOPB_BASE_OFFSET 0x66 -#define TSS_BASE_SIZE 0x68 -#define TSS_IOPB_SIZE (65536 / 8) -#define TSS_REDIRECTION_SIZE (256 / 8) -#define RMODE_TSS_SIZE (TSS_BASE_SIZE + TSS_REDIRECTION_SIZE + TSS_IOPB_SIZE + 1) - -#endif diff --git a/drivers/kvm/kvm_main.c b/drivers/kvm/kvm_main.c deleted file mode 100644 index c0f372f1d761..000000000000 --- a/drivers/kvm/kvm_main.c +++ /dev/null @@ -1,3628 +0,0 @@ -/* - * Kernel-based Virtual Machine driver for Linux - * - * This module enables machines with Intel VT-x extensions to run virtual - * machines without emulation or binary translation. - * - * Copyright (C) 2006 Qumranet, Inc. - * - * Authors: - * Avi Kivity <avi@qumranet.com> - * Yaniv Kamay <yaniv@qumranet.com> - * - * This work is licensed under the terms of the GNU GPL, version 2. See - * the COPYING file in the top-level directory. - * - */ - -#include "kvm.h" -#include "x86_emulate.h" -#include "segment_descriptor.h" -#include "irq.h" - -#include <linux/kvm.h> -#include <linux/module.h> -#include <linux/errno.h> -#include <linux/percpu.h> -#include <linux/gfp.h> -#include <linux/mm.h> -#include <linux/miscdevice.h> -#include <linux/vmalloc.h> -#include <linux/reboot.h> -#include <linux/debugfs.h> -#include <linux/highmem.h> -#include <linux/file.h> -#include <linux/sysdev.h> -#include <linux/cpu.h> -#include <linux/sched.h> -#include <linux/cpumask.h> -#include <linux/smp.h> -#include <linux/anon_inodes.h> -#include <linux/profile.h> - -#include <asm/processor.h> -#include <asm/msr.h> -#include <asm/io.h> -#include <asm/uaccess.h> -#include <asm/desc.h> - -MODULE_AUTHOR("Qumranet"); -MODULE_LICENSE("GPL"); - -static DEFINE_SPINLOCK(kvm_lock); -static LIST_HEAD(vm_list); - -static cpumask_t cpus_hardware_enabled; - -struct kvm_x86_ops *kvm_x86_ops; -struct kmem_cache *kvm_vcpu_cache; -EXPORT_SYMBOL_GPL(kvm_vcpu_cache); - -static __read_mostly struct preempt_ops kvm_preempt_ops; - -#define STAT_OFFSET(x) offsetof(struct kvm_vcpu, stat.x) - -static struct kvm_stats_debugfs_item { - const char *name; - int offset; - struct dentry *dentry; -} debugfs_entries[] = { - { "pf_fixed", STAT_OFFSET(pf_fixed) }, - { "pf_guest", STAT_OFFSET(pf_guest) }, - { "tlb_flush", STAT_OFFSET(tlb_flush) }, - { "invlpg", STAT_OFFSET(invlpg) }, - { "exits", STAT_OFFSET(exits) }, - { "io_exits", STAT_OFFSET(io_exits) }, - { "mmio_exits", STAT_OFFSET(mmio_exits) }, - { "signal_exits", STAT_OFFSET(signal_exits) }, - { "irq_window", STAT_OFFSET(irq_window_exits) }, - { "halt_exits", STAT_OFFSET(halt_exits) }, - { "halt_wakeup", STAT_OFFSET(halt_wakeup) }, - { "request_irq", STAT_OFFSET(request_irq_exits) }, - { "irq_exits", STAT_OFFSET(irq_exits) }, - { "light_exits", STAT_OFFSET(light_exits) }, - { "efer_reload", STAT_OFFSET(efer_reload) }, - { NULL } -}; - -static struct dentry *debugfs_dir; - -#define MAX_IO_MSRS 256 - -#define CR0_RESERVED_BITS \ - (~(unsigned long)(X86_CR0_PE | X86_CR0_MP | X86_CR0_EM | X86_CR0_TS \ - | X86_CR0_ET | X86_CR0_NE | X86_CR0_WP | X86_CR0_AM \ - | X86_CR0_NW | X86_CR0_CD | X86_CR0_PG)) -#define CR4_RESERVED_BITS \ - (~(unsigned long)(X86_CR4_VME | X86_CR4_PVI | X86_CR4_TSD | X86_CR4_DE\ - | X86_CR4_PSE | X86_CR4_PAE | X86_CR4_MCE \ - | X86_CR4_PGE | X86_CR4_PCE | X86_CR4_OSFXSR \ - | X86_CR4_OSXMMEXCPT | X86_CR4_VMXE)) - -#define CR8_RESERVED_BITS (~(unsigned long)X86_CR8_TPR) -#define EFER_RESERVED_BITS 0xfffffffffffff2fe - -#ifdef CONFIG_X86_64 -// LDT or TSS descriptor in the GDT. 16 bytes. -struct segment_descriptor_64 { - struct segment_descriptor s; - u32 base_higher; - u32 pad_zero; -}; - -#endif - -static long kvm_vcpu_ioctl(struct file *file, unsigned int ioctl, - unsigned long arg); - -unsigned long segment_base(u16 selector) -{ - struct descriptor_table gdt; - struct segment_descriptor *d; - unsigned long table_base; - typedef unsigned long ul; - unsigned long v; - - if (selector == 0) - return 0; - - asm ("sgdt %0" : "=m"(gdt)); - table_base = gdt.base; - - if (selector & 4) { /* from ldt */ - u16 ldt_selector; - - asm ("sldt %0" : "=g"(ldt_selector)); - table_base = segment_base(ldt_selector); - } - d = (struct segment_descriptor *)(table_base + (selector & ~7)); - v = d->base_low | ((ul)d->base_mid << 16) | ((ul)d->base_high << 24); -#ifdef CONFIG_X86_64 - if (d->system == 0 - && (d->type == 2 || d->type == 9 || d->type == 11)) - v |= ((ul)((struct segment_descriptor_64 *)d)->base_higher) << 32; -#endif - return v; -} -EXPORT_SYMBOL_GPL(segment_base); - -static inline int valid_vcpu(int n) -{ - return likely(n >= 0 && n < KVM_MAX_VCPUS); -} - -void kvm_load_guest_fpu(struct kvm_vcpu *vcpu) -{ - if (!vcpu->fpu_active || vcpu->guest_fpu_loaded) - return; - - vcpu->guest_fpu_loaded = 1; - fx_save(&vcpu->host_fx_image); - fx_restore(&vcpu->guest_fx_image); -} -EXPORT_SYMBOL_GPL(kvm_load_guest_fpu); - -void kvm_put_guest_fpu(struct kvm_vcpu *vcpu) -{ - if (!vcpu->guest_fpu_loaded) - return; - - vcpu->guest_fpu_loaded = 0; - fx_save(&vcpu->guest_fx_image); - fx_restore(&vcpu->host_fx_image); -} -EXPORT_SYMBOL_GPL(kvm_put_guest_fpu); - -/* - * Switches to specified vcpu, until a matching vcpu_put() - */ -static void vcpu_load(struct kvm_vcpu *vcpu) -{ - int cpu; - - mutex_lock(&vcpu->mutex); - cpu = get_cpu(); - preempt_notifier_register(&vcpu->preempt_notifier); - kvm_x86_ops->vcpu_load(vcpu, cpu); - put_cpu(); -} - -static void vcpu_put(struct kvm_vcpu *vcpu) -{ - preempt_disable(); - kvm_x86_ops->vcpu_put(vcpu); - preempt_notifier_unregister(&vcpu->preempt_notifier); - preempt_enable(); - mutex_unlock(&vcpu->mutex); -} - -static void ack_flush(void *_completed) -{ -} - -void kvm_flush_remote_tlbs(struct kvm *kvm) -{ - int i, cpu; - cpumask_t cpus; - struct kvm_vcpu *vcpu; - - cpus_clear(cpus); - for (i = 0; i < KVM_MAX_VCPUS; ++i) { - vcpu = kvm->vcpus[i]; - if (!vcpu) - continue; - if (test_and_set_bit(KVM_TLB_FLUSH, &vcpu->requests)) - continue; - cpu = vcpu->cpu; - if (cpu != -1 && cpu != raw_smp_processor_id()) - cpu_set(cpu, cpus); - } - smp_call_function_mask(cpus, ack_flush, NULL, 1); -} - -int kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id) -{ - struct page *page; - int r; - - mutex_init(&vcpu->mutex); - vcpu->cpu = -1; - vcpu->mmu.root_hpa = INVALID_PAGE; - vcpu->kvm = kvm; - vcpu->vcpu_id = id; - if (!irqchip_in_kernel(kvm) || id == 0) - vcpu->mp_state = VCPU_MP_STATE_RUNNABLE; - else - vcpu->mp_state = VCPU_MP_STATE_UNINITIALIZED; - init_waitqueue_head(&vcpu->wq); - - page = alloc_page(GFP_KERNEL | __GFP_ZERO); - if (!page) { - r = -ENOMEM; - goto fail; - } - vcpu->run = page_address(page); - - page = alloc_page(GFP_KERNEL | __GFP_ZERO); - if (!page) { - r = -ENOMEM; - goto fail_free_run; - } - vcpu->pio_data = page_address(page); - - r = kvm_mmu_create(vcpu); - if (r < 0) - goto fail_free_pio_data; - - return 0; - -fail_free_pio_data: - free_page((unsigned long)vcpu->pio_data); -fail_free_run: - free_page((unsigned long)vcpu->run); -fail: - return -ENOMEM; -} -EXPORT_SYMBOL_GPL(kvm_vcpu_init); - -void kvm_vcpu_uninit(struct kvm_vcpu *vcpu) -{ - kvm_mmu_destroy(vcpu); - if (vcpu->apic) - hrtimer_cancel(&vcpu->apic->timer.dev); - kvm_free_apic(vcpu->apic); - free_page((unsigned long)vcpu->pio_data); - free_page((unsigned long)vcpu->run); -} -EXPORT_SYMBOL_GPL(kvm_vcpu_uninit); - -static struct kvm *kvm_create_vm(void) -{ - struct kvm *kvm = kzalloc(sizeof(struct kvm), GFP_KERNEL); - - if (!kvm) - return ERR_PTR(-ENOMEM); - - kvm_io_bus_init(&kvm->pio_bus); - mutex_init(&kvm->lock); - INIT_LIST_HEAD(&kvm->active_mmu_pages); - kvm_io_bus_init(&kvm->mmio_bus); - spin_lock(&kvm_lock); - list_add(&kvm->vm_list, &vm_list); - spin_unlock(&kvm_lock); - return kvm; -} - -/* - * Free any memory in @free but not in @dont. - */ -static void kvm_free_physmem_slot(struct kvm_memory_slot *free, - struct kvm_memory_slot *dont) -{ - int i; - - if (!dont || free->phys_mem != dont->phys_mem) - if (free->phys_mem) { - for (i = 0; i < free->npages; ++i) - if (free->phys_mem[i]) - __free_page(free->phys_mem[i]); - vfree(free->phys_mem); - } - - if (!dont || free->dirty_bitmap != dont->dirty_bitmap) - vfree(free->dirty_bitmap); - - free->phys_mem = NULL; - free->npages = 0; - free->dirty_bitmap = NULL; -} - -static void kvm_free_physmem(struct kvm *kvm) -{ - int i; - - for (i = 0; i < kvm->nmemslots; ++i) - kvm_free_physmem_slot(&kvm->memslots[i], NULL); -} - -static void free_pio_guest_pages(struct kvm_vcpu *vcpu) -{ - int i; - - for (i = 0; i < ARRAY_SIZE(vcpu->pio.guest_pages); ++i) - if (vcpu->pio.guest_pages[i]) { - __free_page(vcpu->pio.guest_pages[i]); - vcpu->pio.guest_pages[i] = NULL; - } -} - -static void kvm_unload_vcpu_mmu(struct kvm_vcpu *vcpu) -{ - vcpu_load(vcpu); - kvm_mmu_unload(vcpu); - vcpu_put(vcpu); -} - -static void kvm_free_vcpus(struct kvm *kvm) -{ - unsigned int i; - - /* - * Unpin any mmu pages first. - */ - for (i = 0; i < KVM_MAX_VCPUS; ++i) - if (kvm->vcpus[i]) - kvm_unload_vcpu_mmu(kvm->vcpus[i]); - for (i = 0; i < KVM_MAX_VCPUS; ++i) { - if (kvm->vcpus[i]) { - kvm_x86_ops->vcpu_free(kvm->vcpus[i]); - kvm->vcpus[i] = NULL; - } - } - -} - -static void kvm_destroy_vm(struct kvm *kvm) -{ - spin_lock(&kvm_lock); - list_del(&kvm->vm_list); - spin_unlock(&kvm_lock); - kvm_io_bus_destroy(&kvm->pio_bus); - kvm_io_bus_destroy(&kvm->mmio_bus); - kfree(kvm->vpic); - kfree(kvm->vioapic); - kvm_free_vcpus(kvm); - kvm_free_physmem(kvm); - kfree(kvm); -} - -static int kvm_vm_release(struct inode *inode, struct file *filp) -{ - struct kvm *kvm = filp->private_data; - - kvm_destroy_vm(kvm); - return 0; -} - -static void inject_gp(struct kvm_vcpu *vcpu) -{ - kvm_x86_ops->inject_gp(vcpu, 0); -} - -/* - * Load the pae pdptrs. Return true is they are all valid. - */ -static int load_pdptrs(struct kvm_vcpu *vcpu, unsigned long cr3) -{ - gfn_t pdpt_gfn = cr3 >> PAGE_SHIFT; - unsigned offset = ((cr3 & (PAGE_SIZE-1)) >> 5) << 2; - int i; - u64 *pdpt; - int ret; - struct page *page; - u64 pdpte[ARRAY_SIZE(vcpu->pdptrs)]; - - mutex_lock(&vcpu->kvm->lock); - page = gfn_to_page(vcpu->kvm, pdpt_gfn); - if (!page) { - ret = 0; - goto out; - } - - pdpt = kmap_atomic(page, KM_USER0); - memcpy(pdpte, pdpt+offset, sizeof(pdpte)); - kunmap_atomic(pdpt, KM_USER0); - - for (i = 0; i < ARRAY_SIZE(pdpte); ++i) { - if ((pdpte[i] & 1) && (pdpte[i] & 0xfffffff0000001e6ull)) { - ret = 0; - goto out; - } - } - ret = 1; - - memcpy(vcpu->pdptrs, pdpte, sizeof(vcpu->pdptrs)); -out: - mutex_unlock(&vcpu->kvm->lock); - - return ret; -} - -void set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) -{ - if (cr0 & CR0_RESERVED_BITS) { - printk(KERN_DEBUG "set_cr0: 0x%lx #GP, reserved bits 0x%lx\n", - cr0, vcpu->cr0); - inject_gp(vcpu); - return; - } - - if ((cr0 & X86_CR0_NW) && !(cr0 & X86_CR0_CD)) { - printk(KERN_DEBUG "set_cr0: #GP, CD == 0 && NW == 1\n"); - inject_gp(vcpu); - return; - } - - if ((cr0 & X86_CR0_PG) && !(cr0 & X86_CR0_PE)) { - printk(KERN_DEBUG "set_cr0: #GP, set PG flag " - "and a clear PE flag\n"); - inject_gp(vcpu); - return; - } - - if (!is_paging(vcpu) && (cr0 & X86_CR0_PG)) { -#ifdef CONFIG_X86_64 - if ((vcpu->shadow_efer & EFER_LME)) { - int cs_db, cs_l; - - if (!is_pae(vcpu)) { - printk(KERN_DEBUG "set_cr0: #GP, start paging " - "in long mode while PAE is disabled\n"); - inject_gp(vcpu); - return; - } - kvm_x86_ops->get_cs_db_l_bits(vcpu, &cs_db, &cs_l); - if (cs_l) { - printk(KERN_DEBUG "set_cr0: #GP, start paging " - "in long mode while CS.L == 1\n"); - inject_gp(vcpu); - return; - - } - } else -#endif - if (is_pae(vcpu) && !load_pdptrs(vcpu, vcpu->cr3)) { - printk(KERN_DEBUG "set_cr0: #GP, pdptrs " - "reserved bits\n"); - inject_gp(vcpu); - return; - } - - } - - kvm_x86_ops->set_cr0(vcpu, cr0); - vcpu->cr0 = cr0; - - mutex_lock(&vcpu->kvm->lock); - kvm_mmu_reset_context(vcpu); - mutex_unlock(&vcpu->kvm->lock); - return; -} -EXPORT_SYMBOL_GPL(set_cr0); - -void lmsw(struct kvm_vcpu *vcpu, unsigned long msw) -{ - set_cr0(vcpu, (vcpu->cr0 & ~0x0ful) | (msw & 0x0f)); -} -EXPORT_SYMBOL_GPL(lmsw); - -void set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) -{ - if (cr4 & CR4_RESERVED_BITS) { - printk(KERN_DEBUG "set_cr4: #GP, reserved bits\n"); - inject_gp(vcpu); - return; - } - - if (is_long_mode(vcpu)) { - if (!(cr4 & X86_CR4_PAE)) { - printk(KERN_DEBUG "set_cr4: #GP, clearing PAE while " - "in long mode\n"); - inject_gp(vcpu); - return; - } - } else if (is_paging(vcpu) && !is_pae(vcpu) && (cr4 & X86_CR4_PAE) - && !load_pdptrs(vcpu, vcpu->cr3)) { - printk(KERN_DEBUG "set_cr4: #GP, pdptrs reserved bits\n"); - inject_gp(vcpu); - return; - } - - if (cr4 & X86_CR4_VMXE) { - printk(KERN_DEBUG "set_cr4: #GP, setting VMXE\n"); - inject_gp(vcpu); - return; - } - kvm_x86_ops->set_cr4(vcpu, cr4); - vcpu->cr4 = cr4; - mutex_lock(&vcpu->kvm->lock); - kvm_mmu_reset_context(vcpu); - mutex_unlock(&vcpu->kvm->lock); -} -EXPORT_SYMBOL_GPL(set_cr4); - -void set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) -{ - if (is_long_mode(vcpu)) { - if (cr3 & CR3_L_MODE_RESERVED_BITS) { - printk(KERN_DEBUG "set_cr3: #GP, reserved bits\n"); - inject_gp(vcpu); - return; - } - } else { - if (is_pae(vcpu)) { - if (cr3 & CR3_PAE_RESERVED_BITS) { - printk(KERN_DEBUG - "set_cr3: #GP, reserved bits\n"); - inject_gp(vcpu); - return; - } - if (is_paging(vcpu) && !load_pdptrs(vcpu, cr3)) { - printk(KERN_DEBUG "set_cr3: #GP, pdptrs " - "reserved bits\n"); - inject_gp(vcpu); - return; - } - } else { - if (cr3 & CR3_NONPAE_RESERVED_BITS) { - printk(KERN_DEBUG - "set_cr3: #GP, reserved bits\n"); - inject_gp(vcpu); - return; - } - } - } - - mutex_lock(&vcpu->kvm->lock); - /* - * Does the new cr3 value map to physical memory? (Note, we - * catch an invalid cr3 even in real-mode, because it would - * cause trouble later on when we turn on paging anyway.) - * - * A real CPU would silently accept an invalid cr3 and would - * attempt to use it - with largely undefined (and often hard - * to debug) behavior on the guest side. - */ - if (unlikely(!gfn_to_memslot(vcpu->kvm, cr3 >> PAGE_SHIFT))) - inject_gp(vcpu); - else { - vcpu->cr3 = cr3; - vcpu->mmu.new_cr3(vcpu); - } - mutex_unlock(&vcpu->kvm->lock); -} -EXPORT_SYMBOL_GPL(set_cr3); - -void set_cr8(struct kvm_vcpu *vcpu, unsigned long cr8) -{ - if (cr8 & CR8_RESERVED_BITS) { - printk(KERN_DEBUG "set_cr8: #GP, reserved bits 0x%lx\n", cr8); - inject_gp(vcpu); - return; - } - if (irqchip_in_kernel(vcpu->kvm)) - kvm_lapic_set_tpr(vcpu, cr8); - else - vcpu->cr8 = cr8; -} -EXPORT_SYMBOL_GPL(set_cr8); - -unsigned long get_cr8(struct kvm_vcpu *vcpu) -{ - if (irqchip_in_kernel(vcpu->kvm)) - return kvm_lapic_get_cr8(vcpu); - else - return vcpu->cr8; -} -EXPORT_SYMBOL_GPL(get_cr8); - -u64 kvm_get_apic_base(struct kvm_vcpu *vcpu) -{ - if (irqchip_in_kernel(vcpu->kvm)) - return vcpu->apic_base; - else - return vcpu->apic_base; -} -EXPORT_SYMBOL_GPL(kvm_get_apic_base); - -void kvm_set_apic_base(struct kvm_vcpu *vcpu, u64 data) -{ - /* TODO: reserve bits check */ - if (irqchip_in_kernel(vcpu->kvm)) - kvm_lapic_set_base(vcpu, data); - else - vcpu->apic_base = data; -} -EXPORT_SYMBOL_GPL(kvm_set_apic_base); - -void fx_init(struct kvm_vcpu *vcpu) -{ - unsigned after_mxcsr_mask; - - /* Initialize guest FPU by resetting ours and saving into guest's */ - preempt_disable(); - fx_save(&vcpu->host_fx_image); - fpu_init(); - fx_save(&vcpu->guest_fx_image); - fx_restore(&vcpu->host_fx_image); - preempt_enable(); - - vcpu->cr0 |= X86_CR0_ET; - after_mxcsr_mask = offsetof(struct i387_fxsave_struct, st_space); - vcpu->guest_fx_image.mxcsr = 0x1f80; - memset((void *)&vcpu->guest_fx_image + after_mxcsr_mask, - 0, sizeof(struct i387_fxsave_struct) - after_mxcsr_mask); -} -EXPORT_SYMBOL_GPL(fx_init); - -/* - * Allocate some memory and give it an address in the guest physical address - * space. - * - * Discontiguous memory is allowed, mostly for framebuffers. - */ -static int kvm_vm_ioctl_set_memory_region(struct kvm *kvm, - struct kvm_memory_region *mem) -{ - int r; - gfn_t base_gfn; - unsigned long npages; - unsigned long i; - struct kvm_memory_slot *memslot; - struct kvm_memory_slot old, new; - - r = -EINVAL; - /* General sanity checks */ - if (mem->memory_size & (PAGE_SIZE - 1)) - goto out; - if (mem->guest_phys_addr & (PAGE_SIZE - 1)) - goto out; - if (mem->slot >= KVM_MEMORY_SLOTS) - goto out; - if (mem->guest_phys_addr + mem->memory_size < mem->guest_phys_addr) - goto out; - - memslot = &kvm->memslots[mem->slot]; - base_gfn = mem->guest_phys_addr >> PAGE_SHIFT; - npages = mem->memory_size >> PAGE_SHIFT; - - if (!npages) - mem->flags &= ~KVM_MEM_LOG_DIRTY_PAGES; - - mutex_lock(&kvm->lock); - - new = old = *memslot; - - new.base_gfn = base_gfn; - new.npages = npages; - new.flags = mem->flags; - - /* Disallow changing a memory slot's size. */ - r = -EINVAL; - if (npages && old.npages && npages != old.npages) - goto out_unlock; - - /* Check for overlaps */ - r = -EEXIST; - for (i = 0; i < KVM_MEMORY_SLOTS; ++i) { - struct kvm_memory_slot *s = &kvm->memslots[i]; - - if (s == memslot) - continue; - if (!((base_gfn + npages <= s->base_gfn) || - (base_gfn >= s->base_gfn + s->npages))) - goto out_unlock; - } - - /* Deallocate if slot is being removed */ - if (!npages) - new.phys_mem = NULL; - - /* Free page dirty bitmap if unneeded */ - if (!(new.flags & KVM_MEM_LOG_DIRTY_PAGES)) - new.dirty_bitmap = NULL; - - r = -ENOMEM; - - /* Allocate if a slot is being created */ - if (npages && !new.phys_mem) { - new.phys_mem = vmalloc(npages * sizeof(struct page *)); - - if (!new.phys_mem) - goto out_unlock; - - memset(new.phys_mem, 0, npages * sizeof(struct page *)); - for (i = 0; i < npages; ++i) { - new.phys_mem[i] = alloc_page(GFP_HIGHUSER - | __GFP_ZERO); - if (!new.phys_mem[i]) - goto out_unlock; - set_page_private(new.phys_mem[i],0); - } - } - - /* Allocate page dirty bitmap if needed */ - if ((new.flags & KVM_MEM_LOG_DIRTY_PAGES) && !new.dirty_bitmap) { - unsigned dirty_bytes = ALIGN(npages, BITS_PER_LONG) / 8; - - new.dirty_bitmap = vmalloc(dirty_bytes); - if (!new.dirty_bitmap) - goto out_unlock; - memset(new.dirty_bitmap, 0, dirty_bytes); - } - - if (mem->slot >= kvm->nmemslots) - kvm->nmemslots = mem->slot + 1; - - *memslot = new; - - kvm_mmu_slot_remove_write_access(kvm, mem->slot); - kvm_flush_remote_tlbs(kvm); - - mutex_unlock(&kvm->lock); - - kvm_free_physmem_slot(&old, &new); - return 0; - -out_unlock: - mutex_unlock(&kvm->lock); - kvm_free_physmem_slot(&new, &old); -out: - return r; -} - -/* - * Get (and clear) the dirty memory log for a memory slot. - */ -static int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, - struct kvm_dirty_log *log) -{ - struct kvm_memory_slot *memslot; - int r, i; - int n; - unsigned long any = 0; - - mutex_lock(&kvm->lock); - - r = -EINVAL; - if (log->slot >= KVM_MEMORY_SLOTS) - goto out; - - memslot = &kvm->memslots[log->slot]; - r = -ENOENT; - if (!memslot->dirty_bitmap) - goto out; - - n = ALIGN(memslot->npages, BITS_PER_LONG) / 8; - - for (i = 0; !any && i < n/sizeof(long); ++i) - any = memslot->dirty_bitmap[i]; - - r = -EFAULT; - if (copy_to_user(log->dirty_bitmap, memslot->dirty_bitmap, n)) - goto out; - - /* If nothing is dirty, don't bother messing with page tables. */ - if (any) { - kvm_mmu_slot_remove_write_access(kvm, log->slot); - kvm_flush_remote_tlbs(kvm); - memset(memslot->dirty_bitmap, 0, n); - } - - r = 0; - -out: - mutex_unlock(&kvm->lock); - return r; -} - -/* - * Set a new alias region. Aliases map a portion of physical memory into - * another portion. This is useful for memory windows, for example the PC - * VGA region. - */ -static int kvm_vm_ioctl_set_memory_alias(struct kvm *kvm, - struct kvm_memory_alias *alias) -{ - int r, n; - struct kvm_mem_alias *p; - - r = -EINVAL; - /* General sanity checks */ - if (alias->memory_size & (PAGE_SIZE - 1)) - goto out; - if (alias->guest_phys_addr & (PAGE_SIZE - 1)) - goto out; - if (alias->slot >= KVM_ALIAS_SLOTS) - goto out; - if (alias->guest_phys_addr + alias->memory_size - < alias->guest_phys_addr) - goto out; - if (alias->target_phys_addr + alias->memory_size - < alias->target_phys_addr) - goto out; - - mutex_lock(&kvm->lock); - - p = &kvm->aliases[alias->slot]; - p->base_gfn = alias->guest_phys_addr >> PAGE_SHIFT; - p->npages = alias->memory_size >> PAGE_SHIFT; - p->target_gfn = alias->target_phys_addr >> PAGE_SHIFT; - - for (n = KVM_ALIAS_SLOTS; n > 0; --n) - if (kvm->aliases[n - 1].npages) - break; - kvm->naliases = n; - - kvm_mmu_zap_all(kvm); - - mutex_unlock(&kvm->lock); - - return 0; - -out: - return r; -} - -static int kvm_vm_ioctl_get_irqchip(struct kvm *kvm, struct kvm_irqchip *chip) -{ - int r; - - r = 0; - switch (chip->chip_id) { - case KVM_IRQCHIP_PIC_MASTER: - memcpy (&chip->chip.pic, - &pic_irqchip(kvm)->pics[0], - sizeof(struct kvm_pic_state)); - break; - case KVM_IRQCHIP_PIC_SLAVE: - memcpy (&chip->chip.pic, - &pic_irqchip(kvm)->pics[1], - sizeof(struct kvm_pic_state)); - break; - case KVM_IRQCHIP_IOAPIC: - memcpy (&chip->chip.ioapic, - ioapic_irqchip(kvm), - sizeof(struct kvm_ioapic_state)); - break; - default: - r = -EINVAL; - break; - } - return r; -} - -static int kvm_vm_ioctl_set_irqchip(struct kvm *kvm, struct kvm_irqchip *chip) -{ - int r; - - r = 0; - switch (chip->chip_id) { - case KVM_IRQCHIP_PIC_MASTER: - memcpy (&pic_irqchip(kvm)->pics[0], - &chip->chip.pic, - sizeof(struct kvm_pic_state)); - break; - case KVM_IRQCHIP_PIC_SLAVE: - memcpy (&pic_irqchip(kvm)->pics[1], - &chip->chip.pic, - sizeof(struct kvm_pic_state)); - break; - case KVM_IRQCHIP_IOAPIC: - memcpy (ioapic_irqchip(kvm), - &chip->chip.ioapic, - sizeof(struct kvm_ioapic_state)); - break; - default: - r = -EINVAL; - break; - } - kvm_pic_update_irq(pic_irqchip(kvm)); - return r; -} - -static gfn_t unalias_gfn(struct kvm *kvm, gfn_t gfn) -{ - int i; - struct kvm_mem_alias *alias; - - for (i = 0; i < kvm->naliases; ++i) { - alias = &kvm->aliases[i]; - if (gfn >= alias->base_gfn - && gfn < alias->base_gfn + alias->npages) - return alias->target_gfn + gfn - alias->base_gfn; - } - return gfn; -} - -static struct kvm_memory_slot *__gfn_to_memslot(struct kvm *kvm, gfn_t gfn) -{ - int i; - - for (i = 0; i < kvm->nmemslots; ++i) { - struct kvm_memory_slot *memslot = &kvm->memslots[i]; - - if (gfn >= memslot->base_gfn - && gfn < memslot->base_gfn + memslot->npages) - return memslot; - } - return NULL; -} - -struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn) -{ - gfn = unalias_gfn(kvm, gfn); - return __gfn_to_memslot(kvm, gfn); -} - -struct page *gfn_to_page(struct kvm *kvm, gfn_t gfn) -{ - struct kvm_memory_slot *slot; - - gfn = unalias_gfn(kvm, gfn); - slot = __gfn_to_memslot(kvm, gfn); - if (!slot) - return NULL; - return slot->phys_mem[gfn - slot->base_gfn]; -} -EXPORT_SYMBOL_GPL(gfn_to_page); - -/* WARNING: Does not work on aliased pages. */ -void mark_page_dirty(struct kvm *kvm, gfn_t gfn) -{ - struct kvm_memory_slot *memslot; - - memslot = __gfn_to_memslot(kvm, gfn); - if (memslot && memslot->dirty_bitmap) { - unsigned long rel_gfn = gfn - memslot->base_gfn; - - /* avoid RMW */ - if (!test_bit(rel_gfn, memslot->dirty_bitmap)) - set_bit(rel_gfn, memslot->dirty_bitmap); - } -} - -int emulator_read_std(unsigned long addr, - void *val, - unsigned int bytes, - struct kvm_vcpu *vcpu) -{ - void *data = val; - - while (bytes) { - gpa_t gpa = vcpu->mmu.gva_to_gpa(vcpu, addr); - unsigned offset = addr & (PAGE_SIZE-1); - unsigned tocopy = min(bytes, (unsigned)PAGE_SIZE - offset); - unsigned long pfn; - struct page *page; - void *page_virt; - - if (gpa == UNMAPPED_GVA) - return X86EMUL_PROPAGATE_FAULT; - pfn = gpa >> PAGE_SHIFT; - page = gfn_to_page(vcpu->kvm, pfn); - if (!page) - return X86EMUL_UNHANDLEABLE; - page_virt = kmap_atomic(page, KM_USER0); - - memcpy(data, page_virt + offset, tocopy); - - kunmap_atomic(page_virt, KM_USER0); - - bytes -= tocopy; - data += tocopy; - addr += tocopy; - } - - return X86EMUL_CONTINUE; -} -EXPORT_SYMBOL_GPL(emulator_read_std); - -static int emulator_write_std(unsigned long addr, - const void *val, - unsigned int bytes, - struct kvm_vcpu *vcpu) -{ - pr_unimpl(vcpu, "emulator_write_std: addr %lx n %d\n", addr, bytes); - return X86EMUL_UNHANDLEABLE; -} - -/* - * Only apic need an MMIO device hook, so shortcut now.. - */ -static struct kvm_io_device *vcpu_find_pervcpu_dev(struct kvm_vcpu *vcpu, - gpa_t addr) -{ - struct kvm_io_device *dev; - - if (vcpu->apic) { - dev = &vcpu->apic->dev; - if (dev->in_range(dev, addr)) - return dev; - } - return NULL; -} - -static struct kvm_io_device *vcpu_find_mmio_dev(struct kvm_vcpu *vcpu, - gpa_t addr) -{ - struct kvm_io_device *dev; - - dev = vcpu_find_pervcpu_dev(vcpu, addr); - if (dev == NULL) - dev = kvm_io_bus_find_dev(&vcpu->kvm->mmio_bus, addr); - return dev; -} - -static struct kvm_io_device *vcpu_find_pio_dev(struct kvm_vcpu *vcpu, - gpa_t addr) -{ - return kvm_io_bus_find_dev(&vcpu->kvm->pio_bus, addr); -} - -static int emulator_read_emulated(unsigned long addr, - void *val, - unsigned int bytes, - struct kvm_vcpu *vcpu) -{ - struct kvm_io_device *mmio_dev; - gpa_t gpa; - - if (vcpu->mmio_read_completed) { - memcpy(val, vcpu->mmio_data, bytes); - vcpu->mmio_read_completed = 0; - return X86EMUL_CONTINUE; - } else if (emulator_read_std(addr, val, bytes, vcpu) - == X86EMUL_CONTINUE) - return X86EMUL_CONTINUE; - - gpa = vcpu->mmu.gva_to_gpa(vcpu, addr); - if (gpa == UNMAPPED_GVA) - return X86EMUL_PROPAGATE_FAULT; - - /* - * Is this MMIO handled locally? - */ - mmio_dev = vcpu_find_mmio_dev(vcpu, gpa); - if (mmio_dev) { - kvm_iodevice_read(mmio_dev, gpa, bytes, val); - return X86EMUL_CONTINUE; - } - - vcpu->mmio_needed = 1; - vcpu->mmio_phys_addr = gpa; - vcpu->mmio_size = bytes; - vcpu->mmio_is_write = 0; - - return X86EMUL_UNHANDLEABLE; -} - -static int emulator_write_phys(struct kvm_vcpu *vcpu, gpa_t gpa, - const void *val, int bytes) -{ - struct page *page; - void *virt; - - if (((gpa + bytes - 1) >> PAGE_SHIFT) != (gpa >> PAGE_SHIFT)) - return 0; - page = gfn_to_page(vcpu->kvm, gpa >> PAGE_SHIFT); - if (!page) - return 0; - mark_page_dirty(vcpu->kvm, gpa >> PAGE_SHIFT); - virt = kmap_atomic(page, KM_USER0); - kvm_mmu_pte_write(vcpu, gpa, val, bytes); - memcpy(virt + offset_in_page(gpa), val, bytes); - kunmap_atomic(virt, KM_USER0); - return 1; -} - -static int emulator_write_emulated_onepage(unsigned long addr, - const void *val, - unsigned int bytes, - struct kvm_vcpu *vcpu) -{ - struct kvm_io_device *mmio_dev; - gpa_t gpa = vcpu->mmu.gva_to_gpa(vcpu, addr); - - if (gpa == UNMAPPED_GVA) { - kvm_x86_ops->inject_page_fault(vcpu, addr, 2); - return X86EMUL_PROPAGATE_FAULT; - } - - if (emulator_write_phys(vcpu, gpa, val, bytes)) - return X86EMUL_CONTINUE; - - /* - * Is this MMIO handled locally? - */ - mmio_dev = vcpu_find_mmio_dev(vcpu, gpa); - if (mmio_dev) { - kvm_iodevice_write(mmio_dev, gpa, bytes, val); - return X86EMUL_CONTINUE; - } - - vcpu->mmio_needed = 1; - vcpu->mmio_phys_addr = gpa; - vcpu->mmio_size = bytes; - vcpu->mmio_is_write = 1; - memcpy(vcpu->mmio_data, val, bytes); - - return X86EMUL_CONTINUE; -} - -int emulator_write_emulated(unsigned long addr, - const void *val, - unsigned int bytes, - struct kvm_vcpu *vcpu) -{ - /* Crossing a page boundary? */ - if (((addr + bytes - 1) ^ addr) & PAGE_MASK) { - int rc, now; - - now = -addr & ~PAGE_MASK; - rc = emulator_write_emulated_onepage(addr, val, now, vcpu); - if (rc != X86EMUL_CONTINUE) - return rc; - addr += now; - val += now; - bytes -= now; - } - return emulator_write_emulated_onepage(addr, val, bytes, vcpu); -} -EXPORT_SYMBOL_GPL(emulator_write_emulated); - -static int emulator_cmpxchg_emulated(unsigned long addr, - const void *old, - const void *new, - unsigned int bytes, - struct kvm_vcpu *vcpu) -{ - static int reported; - - if (!reported) { - reported = 1; - printk(KERN_WARNING "kvm: emulating exchange as write\n"); - } - return emulator_write_emulated(addr, new, bytes, vcpu); -} - -static unsigned long get_segment_base(struct kvm_vcpu *vcpu, int seg) -{ - return kvm_x86_ops->get_segment_base(vcpu, seg); -} - -int emulate_invlpg(struct kvm_vcpu *vcpu, gva_t address) -{ - return X86EMUL_CONTINUE; -} - -int emulate_clts(struct kvm_vcpu *vcpu) -{ - kvm_x86_ops->set_cr0(vcpu, vcpu->cr0 & ~X86_CR0_TS); - return X86EMUL_CONTINUE; -} - -int emulator_get_dr(struct x86_emulate_ctxt* ctxt, int dr, unsigned long *dest) -{ - struct kvm_vcpu *vcpu = ctxt->vcpu; - - switch (dr) { - case 0 ... 3: - *dest = kvm_x86_ops->get_dr(vcpu, dr); - return X86EMUL_CONTINUE; - default: - pr_unimpl(vcpu, "%s: unexpected dr %u\n", __FUNCTION__, dr); - return X86EMUL_UNHANDLEABLE; - } -} - -int emulator_set_dr(struct x86_emulate_ctxt *ctxt, int dr, unsigned long value) -{ - unsigned long mask = (ctxt->mode == X86EMUL_MODE_PROT64) ? ~0ULL : ~0U; - int exception; - - kvm_x86_ops->set_dr(ctxt->vcpu, dr, value & mask, &exception); - if (exception) { - /* FIXME: better handling */ - return X86EMUL_UNHANDLEABLE; - } - return X86EMUL_CONTINUE; -} - -void kvm_report_emulation_failure(struct kvm_vcpu *vcpu, const char *context) -{ - static int reported; - u8 opcodes[4]; - unsigned long rip = vcpu->rip; - unsigned long rip_linear; - - rip_linear = rip + get_segment_base(vcpu, VCPU_SREG_CS); - - if (reported) - return; - - emulator_read_std(rip_linear, (void *)opcodes, 4, vcpu); - - printk(KERN_ERR "emulation failed (%s) rip %lx %02x %02x %02x %02x\n", - context, rip, opcodes[0], opcodes[1], opcodes[2], opcodes[3]); - reported = 1; -} -EXPORT_SYMBOL_GPL(kvm_report_emulation_failure); - -struct x86_emulate_ops emulate_ops = { - .read_std = emulator_read_std, - .write_std = emulator_write_std, - .read_emulated = emulator_read_emulated, - .write_emulated = emulator_write_emulated, - .cmpxchg_emulated = emulator_cmpxchg_emulated, -}; - -int emulate_instruction(struct kvm_vcpu *vcpu, - struct kvm_run *run, - unsigned long cr2, - u16 error_code) -{ - struct x86_emulate_ctxt emulate_ctxt; - int r; - int cs_db, cs_l; - - vcpu->mmio_fault_cr2 = cr2; - kvm_x86_ops->cache_regs(vcpu); - - kvm_x86_ops->get_cs_db_l_bits(vcpu, &cs_db, &cs_l); - - emulate_ctxt.vcpu = vcpu; - emulate_ctxt.eflags = kvm_x86_ops->get_rflags(vcpu); - emulate_ctxt.cr2 = cr2; - emulate_ctxt.mode = (emulate_ctxt.eflags & X86_EFLAGS_VM) - ? X86EMUL_MODE_REAL : cs_l - ? X86EMUL_MODE_PROT64 : cs_db - ? X86EMUL_MODE_PROT32 : X86EMUL_MODE_PROT16; - - if (emulate_ctxt.mode == X86EMUL_MODE_PROT64) { - emulate_ctxt.cs_base = 0; - emulate_ctxt.ds_base = 0; - emulate_ctxt.es_base = 0; - emulate_ctxt.ss_base = 0; - } else { - emulate_ctxt.cs_base = get_segment_base(vcpu, VCPU_SREG_CS); - emulate_ctxt.ds_base = get_segment_base(vcpu, VCPU_SREG_DS); - emulate_ctxt.es_base = get_segment_base(vcpu, VCPU_SREG_ES); - emulate_ctxt.ss_base = get_segment_base(vcpu, VCPU_SREG_SS); - } - - emulate_ctxt.gs_base = get_segment_base(vcpu, VCPU_SREG_GS); - emulate_ctxt.fs_base = get_segment_base(vcpu, VCPU_SREG_FS); - - vcpu->mmio_is_write = 0; - vcpu->pio.string = 0; - r = x86_emulate_memop(&emulate_ctxt, &emulate_ops); - if (vcpu->pio.string) - return EMULATE_DO_MMIO; - - if ((r || vcpu->mmio_is_write) && run) { - run->exit_reason = KVM_EXIT_MMIO; - run->mmio.phys_addr = vcpu->mmio_phys_addr; - memcpy(run->mmio.data, vcpu->mmio_data, 8); - run->mmio.len = vcpu->mmio_size; - run->mmio.is_write = vcpu->mmio_is_write; - } - - if (r) { - if (kvm_mmu_unprotect_page_virt(vcpu, cr2)) - return EMULATE_DONE; - if (!vcpu->mmio_needed) { - kvm_report_emulation_failure(vcpu, "mmio"); - return EMULATE_FAIL; - } - return EMULATE_DO_MMIO; - } - - kvm_x86_ops->decache_regs(vcpu); - kvm_x86_ops->set_rflags(vcpu, emulate_ctxt.eflags); - - if (vcpu->mmio_is_write) { - vcpu->mmio_needed = 0; - return EMULATE_DO_MMIO; - } - - return EMULATE_DONE; -} -EXPORT_SYMBOL_GPL(emulate_instruction); - -/* - * The vCPU has executed a HLT instruction with in-kernel mode enabled. - */ -static void kvm_vcpu_block(struct kvm_vcpu *vcpu) -{ - DECLARE_WAITQUEUE(wait, current); - - add_wait_queue(&vcpu->wq, &wait); - - /* - * We will block until either an interrupt or a signal wakes us up - */ - while (!kvm_cpu_has_interrupt(vcpu) - && !signal_pending(current) - && vcpu->mp_state != VCPU_MP_STATE_RUNNABLE - && vcpu->mp_state != VCPU_MP_STATE_SIPI_RECEIVED) { - set_current_state(TASK_INTERRUPTIBLE); - vcpu_put(vcpu); - schedule(); - vcpu_load(vcpu); - } - - __set_current_state(TASK_RUNNING); - remove_wait_queue(&vcpu->wq, &wait); -} - -int kvm_emulate_halt(struct kvm_vcpu *vcpu) -{ - ++vcpu->stat.halt_exits; - if (irqchip_in_kernel(vcpu->kvm)) { - vcpu->mp_state = VCPU_MP_STATE_HALTED; - kvm_vcpu_block(vcpu); - if (vcpu->mp_state != VCPU_MP_STATE_RUNNABLE) - return -EINTR; - return 1; - } else { - vcpu->run->exit_reason = KVM_EXIT_HLT; - return 0; - } -} -EXPORT_SYMBOL_GPL(kvm_emulate_halt); - -int kvm_hypercall(struct kvm_vcpu *vcpu, struct kvm_run *run) -{ - unsigned long nr, a0, a1, a2, a3, a4, a5, ret; - - kvm_x86_ops->cache_regs(vcpu); - ret = -KVM_EINVAL; -#ifdef CONFIG_X86_64 - if (is_long_mode(vcpu)) { - nr = vcpu->regs[VCPU_REGS_RAX]; - a0 = vcpu->regs[VCPU_REGS_RDI]; - a1 = vcpu->regs[VCPU_REGS_RSI]; - a2 = vcpu->regs[VCPU_REGS_RDX]; - a3 = vcpu->regs[VCPU_REGS_RCX]; - a4 = vcpu->regs[VCPU_REGS_R8]; - a5 = vcpu->regs[VCPU_REGS_R9]; - } else -#endif - { - nr = vcpu->regs[VCPU_REGS_RBX] & -1u; - a0 = vcpu->regs[VCPU_REGS_RAX] & -1u; - a1 = vcpu->regs[VCPU_REGS_RCX] & -1u; - a2 = vcpu->regs[VCPU_REGS_RDX] & -1u; - a3 = vcpu->regs[VCPU_REGS_RSI] & -1u; - a4 = vcpu->regs[VCPU_REGS_RDI] & -1u; - a5 = vcpu->regs[VCPU_REGS_RBP] & -1u; - } - switch (nr) { - default: - run->hypercall.nr = nr; - run->hypercall.args[0] = a0; - run->hypercall.args[1] = a1; - run->hypercall.args[2] = a2; - run->hypercall.args[3] = a3; - run->hypercall.args[4] = a4; - run->hypercall.args[5] = a5; - run->hypercall.ret = ret; - run->hypercall.longmode = is_long_mode(vcpu); - kvm_x86_ops->decache_regs(vcpu); - return 0; - } - vcpu->regs[VCPU_REGS_RAX] = ret; - kvm_x86_ops->decache_regs(vcpu); - return 1; -} -EXPORT_SYMBOL_GPL(kvm_hypercall); - -static u64 mk_cr_64(u64 curr_cr, u32 new_val) -{ - return (curr_cr & ~((1ULL << 32) - 1)) | new_val; -} - -void realmode_lgdt(struct kvm_vcpu *vcpu, u16 limit, unsigned long base) -{ - struct descriptor_table dt = { limit, base }; - - kvm_x86_ops->set_gdt(vcpu, &dt); -} - -void realmode_lidt(struct kvm_vcpu *vcpu, u16 limit, unsigned long base) -{ - struct descriptor_table dt = { limit, base }; - - kvm_x86_ops->set_idt(vcpu, &dt); -} - -void realmode_lmsw(struct kvm_vcpu *vcpu, unsigned long msw, - unsigned long *rflags) -{ - lmsw(vcpu, msw); - *rflags = kvm_x86_ops->get_rflags(vcpu); -} - -unsigned long realmode_get_cr(struct kvm_vcpu *vcpu, int cr) -{ - kvm_x86_ops->decache_cr4_guest_bits(vcpu); - switch (cr) { - case 0: - return vcpu->cr0; - case 2: - return vcpu->cr2; - case 3: - return vcpu->cr3; - case 4: - return vcpu->cr4; - default: - vcpu_printf(vcpu, "%s: unexpected cr %u\n", __FUNCTION__, cr); - return 0; - } -} - -void realmode_set_cr(struct kvm_vcpu *vcpu, int cr, unsigned long val, - unsigned long *rflags) -{ - switch (cr) { - case 0: - set_cr0(vcpu, mk_cr_64(vcpu->cr0, val)); - *rflags = kvm_x86_ops->get_rflags(vcpu); - break; - case 2: - vcpu->cr2 = val; - break; - case 3: - set_cr3(vcpu, val); - break; - case 4: - set_cr4(vcpu, mk_cr_64(vcpu->cr4, val)); - break; - default: - vcpu_printf(vcpu, "%s: unexpected cr %u\n", __FUNCTION__, cr); - } -} - -/* - * Register the para guest with the host: - */ -static int vcpu_register_para(struct kvm_vcpu *vcpu, gpa_t para_state_gpa) -{ - struct kvm_vcpu_para_state *para_state; - hpa_t para_state_hpa, hypercall_hpa; - struct page *para_state_page; - unsigned char *hypercall; - gpa_t hypercall_gpa; - - printk(KERN_DEBUG "kvm: guest trying to enter paravirtual mode\n"); - printk(KERN_DEBUG ".... para_state_gpa: %08Lx\n", para_state_gpa); - - /* - * Needs to be page aligned: - */ - if (para_state_gpa != PAGE_ALIGN(para_state_gpa)) - goto err_gp; - - para_state_hpa = gpa_to_hpa(vcpu, para_state_gpa); - printk(KERN_DEBUG ".... para_state_hpa: %08Lx\n", para_state_hpa); - if (is_error_hpa(para_state_hpa)) - goto err_gp; - - mark_page_dirty(vcpu->kvm, para_state_gpa >> PAGE_SHIFT); - para_state_page = pfn_to_page(para_state_hpa >> PAGE_SHIFT); - para_state = kmap(para_state_page); - - printk(KERN_DEBUG ".... guest version: %d\n", para_state->guest_version); - printk(KERN_DEBUG ".... size: %d\n", para_state->size); - - para_state->host_version = KVM_PARA_API_VERSION; - /* - * We cannot support guests that try to register themselves - * with a newer API version than the host supports: - */ - if (para_state->guest_version > KVM_PARA_API_VERSION) { - para_state->ret = -KVM_EINVAL; - goto err_kunmap_skip; - } - - hypercall_gpa = para_state->hypercall_gpa; - hypercall_hpa = gpa_to_hpa(vcpu, hypercall_gpa); - printk(KERN_DEBUG ".... hypercall_hpa: %08Lx\n", hypercall_hpa); - if (is_error_hpa(hypercall_hpa)) { - para_state->ret = -KVM_EINVAL; - goto err_kunmap_skip; - } - - printk(KERN_DEBUG "kvm: para guest successfully registered.\n"); - vcpu->para_state_page = para_state_page; - vcpu->para_state_gpa = para_state_gpa; - vcpu->hypercall_gpa = hypercall_gpa; - - mark_page_dirty(vcpu->kvm, hypercall_gpa >> PAGE_SHIFT); - hypercall = kmap_atomic(pfn_to_page(hypercall_hpa >> PAGE_SHIFT), - KM_USER1) + (hypercall_hpa & ~PAGE_MASK); - kvm_x86_ops->patch_hypercall(vcpu, hypercall); - kunmap_atomic(hypercall, KM_USER1); - - para_state->ret = 0; -err_kunmap_skip: - kunmap(para_state_page); - return 0; -err_gp: - return 1; -} - -int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) -{ - u64 data; - - switch (msr) { - case 0xc0010010: /* SYSCFG */ - case 0xc0010015: /* HWCR */ - case MSR_IA32_PLATFORM_ID: - case MSR_IA32_P5_MC_ADDR: - case MSR_IA32_P5_MC_TYPE: - case MSR_IA32_MC0_CTL: - case MSR_IA32_MCG_STATUS: - case MSR_IA32_MCG_CAP: - case MSR_IA32_MC0_MISC: - case MSR_IA32_MC0_MISC+4: - case MSR_IA32_MC0_MISC+8: - case MSR_IA32_MC0_MISC+12: - case MSR_IA32_MC0_MISC+16: - case MSR_IA32_UCODE_REV: - case MSR_IA32_PERF_STATUS: - case MSR_IA32_EBL_CR_POWERON: - /* MTRR registers */ - case 0xfe: - case 0x200 ... 0x2ff: - data = 0; - break; - case 0xcd: /* fsb frequency */ - data = 3; - break; - case MSR_IA32_APICBASE: - data = kvm_get_apic_base(vcpu); - break; - case MSR_IA32_MISC_ENABLE: - data = vcpu->ia32_misc_enable_msr; - break; -#ifdef CONFIG_X86_64 - case MSR_EFER: - data = vcpu->shadow_efer; - break; -#endif - default: - pr_unimpl(vcpu, "unhandled rdmsr: 0x%x\n", msr); - return 1; - } - *pdata = data; - return 0; -} -EXPORT_SYMBOL_GPL(kvm_get_msr_common); - -/* - * Reads an msr value (of 'msr_index') into 'pdata'. - * Returns 0 on success, non-0 otherwise. - * Assumes vcpu_load() was already called. - */ -int kvm_get_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata) -{ - return kvm_x86_ops->get_msr(vcpu, msr_index, pdata); -} - -#ifdef CONFIG_X86_64 - -static void set_efer(struct kvm_vcpu *vcpu, u64 efer) -{ - if (efer & EFER_RESERVED_BITS) { - printk(KERN_DEBUG "set_efer: 0x%llx #GP, reserved bits\n", - efer); - inject_gp(vcpu); - return; - } - - if (is_paging(vcpu) - && (vcpu->shadow_efer & EFER_LME) != (efer & EFER_LME)) { - printk(KERN_DEBUG "set_efer: #GP, change LME while paging\n"); - inject_gp(vcpu); - return; - } - - kvm_x86_ops->set_efer(vcpu, efer); - - efer &= ~EFER_LMA; - efer |= vcpu->shadow_efer & EFER_LMA; - - vcpu->shadow_efer = efer; -} - -#endif - -int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data) -{ - switch (msr) { -#ifdef CONFIG_X86_64 - case MSR_EFER: - set_efer(vcpu, data); - break; -#endif - case MSR_IA32_MC0_STATUS: - pr_unimpl(vcpu, "%s: MSR_IA32_MC0_STATUS 0x%llx, nop\n", - __FUNCTION__, data); - break; - case MSR_IA32_MCG_STATUS: - pr_unimpl(vcpu, "%s: MSR_IA32_MCG_STATUS 0x%llx, nop\n", - __FUNCTION__, data); - break; - case MSR_IA32_UCODE_REV: - case MSR_IA32_UCODE_WRITE: - case 0x200 ... 0x2ff: /* MTRRs */ - break; - case MSR_IA32_APICBASE: - kvm_set_apic_base(vcpu, data); - break; - case MSR_IA32_MISC_ENABLE: - vcpu->ia32_misc_enable_msr = data; - break; - /* - * This is the 'probe whether the host is KVM' logic: - */ - case MSR_KVM_API_MAGIC: - return vcpu_register_para(vcpu, data); - - default: - pr_unimpl(vcpu, "unhandled wrmsr: 0x%x\n", msr); - return 1; - } - return 0; -} -EXPORT_SYMBOL_GPL(kvm_set_msr_common); - -/* - * Writes msr value into into the appropriate "register". - * Returns 0 on success, non-0 otherwise. - * Assumes vcpu_load() was already called. - */ -int kvm_set_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data) -{ - return kvm_x86_ops->set_msr(vcpu, msr_index, data); -} - -void kvm_resched(struct kvm_vcpu *vcpu) -{ - if (!need_resched()) - return; - cond_resched(); -} -EXPORT_SYMBOL_GPL(kvm_resched); - -void kvm_emulate_cpuid(struct kvm_vcpu *vcpu) -{ - int i; - u32 function; - struct kvm_cpuid_entry *e, *best; - - kvm_x86_ops->cache_regs(vcpu); - function = vcpu->regs[VCPU_REGS_RAX]; - vcpu->regs[VCPU_REGS_RAX] = 0; - vcpu->regs[VCPU_REGS_RBX] = 0; - vcpu->regs[VCPU_REGS_RCX] = 0; - vcpu->regs[VCPU_REGS_RDX] = 0; - best = NULL; - for (i = 0; i < vcpu->cpuid_nent; ++i) { - e = &vcpu->cpuid_entries[i]; - if (e->function == function) { - best = e; - break; - } - /* - * Both basic or both extended? - */ - if (((e->function ^ function) & 0x80000000) == 0) - if (!best || e->function > best->function) - best = e; - } - if (best) { - vcpu->regs[VCPU_REGS_RAX] = best->eax; - vcpu->regs[VCPU_REGS_RBX] = best->ebx; - vcpu->regs[VCPU_REGS_RCX] = best->ecx; - vcpu->regs[VCPU_REGS_RDX] = best->edx; - } - kvm_x86_ops->decache_regs(vcpu); - kvm_x86_ops->skip_emulated_instruction(vcpu); -} -EXPORT_SYMBOL_GPL(kvm_emulate_cpuid); - -static int pio_copy_data(struct kvm_vcpu *vcpu) -{ - void *p = vcpu->pio_data; - void *q; - unsigned bytes; - int nr_pages = vcpu->pio.guest_pages[1] ? 2 : 1; - - q = vmap(vcpu->pio.guest_pages, nr_pages, VM_READ|VM_WRITE, - PAGE_KERNEL); - if (!q) { - free_pio_guest_pages(vcpu); - return -ENOMEM; - } - q += vcpu->pio.guest_page_offset; - bytes = vcpu->pio.size * vcpu->pio.cur_count; - if (vcpu->pio.in) - memcpy(q, p, bytes); - else - memcpy(p, q, bytes); - q -= vcpu->pio.guest_page_offset; - vunmap(q); - free_pio_guest_pages(vcpu); - return 0; -} - -static int complete_pio(struct kvm_vcpu *vcpu) -{ - struct kvm_pio_request *io = &vcpu->pio; - long delta; - int r; - - kvm_x86_ops->cache_regs(vcpu); - - if (!io->string) { - if (io->in) - memcpy(&vcpu->regs[VCPU_REGS_RAX], vcpu->pio_data, - io->size); - } else { - if (io->in) { - r = pio_copy_data(vcpu); - if (r) { - kvm_x86_ops->cache_regs(vcpu); - return r; - } - } - - delta = 1; - if (io->rep) { - delta *= io->cur_count; - /* - * The size of the register should really depend on - * current address size. - */ - vcpu->regs[VCPU_REGS_RCX] -= delta; - } - if (io->down) - delta = -delta; - delta *= io->size; - if (io->in) - vcpu->regs[VCPU_REGS_RDI] += delta; - else - vcpu->regs[VCPU_REGS_RSI] += delta; - } - - kvm_x86_ops->decache_regs(vcpu); - - io->count -= io->cur_count; - io->cur_count = 0; - - return 0; -} - -static void kernel_pio(struct kvm_io_device *pio_dev, - struct kvm_vcpu *vcpu, - void *pd) -{ - /* TODO: String I/O for in kernel device */ - - mutex_lock(&vcpu->kvm->lock); - if (vcpu->pio.in) - kvm_iodevice_read(pio_dev, vcpu->pio.port, - vcpu->pio.size, - pd); - else - kvm_iodevice_write(pio_dev, vcpu->pio.port, - vcpu->pio.size, - pd); - mutex_unlock(&vcpu->kvm->lock); -} - -static void pio_string_write(struct kvm_io_device *pio_dev, - struct kvm_vcpu *vcpu) -{ - struct kvm_pio_request *io = &vcpu->pio; - void *pd = vcpu->pio_data; - int i; - - mutex_lock(&vcpu->kvm->lock); - for (i = 0; i < io->cur_count; i++) { - kvm_iodevice_write(pio_dev, io->port, - io->size, - pd); - pd += io->size; - } - mutex_unlock(&vcpu->kvm->lock); -} - -int kvm_emulate_pio (struct kvm_vcpu *vcpu, struct kvm_run *run, int in, - int size, unsigned port) -{ - struct kvm_io_device *pio_dev; - - vcpu->run->exit_reason = KVM_EXIT_IO; - vcpu->run->io.direction = in ? KVM_EXIT_IO_IN : KVM_EXIT_IO_OUT; - vcpu->run->io.size = vcpu->pio.size = size; - vcpu->run->io.data_offset = KVM_PIO_PAGE_OFFSET * PAGE_SIZE; - vcpu->run->io.count = vcpu->pio.count = vcpu->pio.cur_count = 1; - vcpu->run->io.port = vcpu->pio.port = port; - vcpu->pio.in = in; - vcpu->pio.string = 0; - vcpu->pio.down = 0; - vcpu->pio.guest_page_offset = 0; - vcpu->pio.rep = 0; - - kvm_x86_ops->cache_regs(vcpu); - memcpy(vcpu->pio_data, &vcpu->regs[VCPU_REGS_RAX], 4); - kvm_x86_ops->decache_regs(vcpu); - - kvm_x86_ops->skip_emulated_instruction(vcpu); - - pio_dev = vcpu_find_pio_dev(vcpu, port); - if (pio_dev) { - kernel_pio(pio_dev, vcpu, vcpu->pio_data); - complete_pio(vcpu); - return 1; - } - return 0; -} -EXPORT_SYMBOL_GPL(kvm_emulate_pio); - -int kvm_emulate_pio_string(struct kvm_vcpu *vcpu, struct kvm_run *run, int in, - int size, unsigned long count, int down, - gva_t address, int rep, unsigned port) -{ - unsigned now, in_page; - int i, ret = 0; - int nr_pages = 1; - struct page *page; - struct kvm_io_device *pio_dev; - - vcpu->run->exit_reason = KVM_EXIT_IO; - vcpu->run->io.direction = in ? KVM_EXIT_IO_IN : KVM_EXIT_IO_OUT; - vcpu->run->io.size = vcpu->pio.size = size; - vcpu->run->io.data_offset = KVM_PIO_PAGE_OFFSET * PAGE_SIZE; - vcpu->run->io.count = vcpu->pio.count = vcpu->pio.cur_count = count; - vcpu->run->io.port = vcpu->pio.port = port; - vcpu->pio.in = in; - vcpu->pio.string = 1; - vcpu->pio.down = down; - vcpu->pio.guest_page_offset = offset_in_page(address); - vcpu->pio.rep = rep; - - if (!count) { - kvm_x86_ops->skip_emulated_instruction(vcpu); - return 1; - } - - if (!down) - in_page = PAGE_SIZE - offset_in_page(address); - else - in_page = offset_in_page(address) + size; - now = min(count, (unsigned long)in_page / size); - if (!now) { - /* - * String I/O straddles page boundary. Pin two guest pages - * so that we satisfy atomicity constraints. Do just one - * transaction to avoid complexity. - */ - nr_pages = 2; - now = 1; - } - if (down) { - /* - * String I/O in reverse. Yuck. Kill the guest, fix later. - */ - pr_unimpl(vcpu, "guest string pio down\n"); - inject_gp(vcpu); - return 1; - } - vcpu->run->io.count = now; - vcpu->pio.cur_count = now; - - if (vcpu->pio.cur_count == vcpu->pio.count) - kvm_x86_ops->skip_emulated_instruction(vcpu); - - for (i = 0; i < nr_pages; ++i) { - mutex_lock(&vcpu->kvm->lock); - page = gva_to_page(vcpu, address + i * PAGE_SIZE); - if (page) - get_page(page); - vcpu->pio.guest_pages[i] = page; - mutex_unlock(&vcpu->kvm->lock); - if (!page) { - inject_gp(vcpu); - free_pio_guest_pages(vcpu); - return 1; - } - } - - pio_dev = vcpu_find_pio_dev(vcpu, port); - if (!vcpu->pio.in) { - /* string PIO write */ - ret = pio_copy_data(vcpu); - if (ret >= 0 && pio_dev) { - pio_string_write(pio_dev, vcpu); - complete_pio(vcpu); - if (vcpu->pio.count == 0) - ret = 1; - } - } else if (pio_dev) - pr_unimpl(vcpu, "no string pio read support yet, " - "port %x size %d count %ld\n", - port, size, count); - - return ret; -} -EXPORT_SYMBOL_GPL(kvm_emulate_pio_string); - -/* - * Check if userspace requested an interrupt window, and that the - * interrupt window is open. - * - * No need to exit to userspace if we already have an interrupt queued. - */ -static int dm_request_for_irq_injection(struct kvm_vcpu *vcpu, - struct kvm_run *kvm_run) -{ - return (!vcpu->irq_summary && - kvm_run->request_interrupt_window && - vcpu->interrupt_window_open && - (kvm_x86_ops->get_rflags(vcpu) & X86_EFLAGS_IF)); -} - -static void post_kvm_run_save(struct kvm_vcpu *vcpu, - struct kvm_run *kvm_run) -{ - kvm_run->if_flag = (kvm_x86_ops->get_rflags(vcpu) & X86_EFLAGS_IF) != 0; - kvm_run->cr8 = get_cr8(vcpu); - kvm_run->apic_base = kvm_get_apic_base(vcpu); - if (irqchip_in_kernel(vcpu->kvm)) - kvm_run->ready_for_interrupt_injection = 1; - else - kvm_run->ready_for_interrupt_injection = - (vcpu->interrupt_window_open && - vcpu->irq_summary == 0); -} - -static int __vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) -{ - int r; - - if (unlikely(vcpu->mp_state == VCPU_MP_STATE_SIPI_RECEIVED)) { - printk("vcpu %d received sipi with vector # %x\n", - vcpu->vcpu_id, vcpu->sipi_vector); - kvm_lapic_reset(vcpu); - kvm_x86_ops->vcpu_reset(vcpu); - vcpu->mp_state = VCPU_MP_STATE_RUNNABLE; - } - -preempted: - if (vcpu->guest_debug.enabled) - kvm_x86_ops->guest_debug_pre(vcpu); - -again: - r = kvm_mmu_reload(vcpu); - if (unlikely(r)) - goto out; - - preempt_disable(); - - kvm_x86_ops->prepare_guest_switch(vcpu); - kvm_load_guest_fpu(vcpu); - - local_irq_disable(); - - if (signal_pending(current)) { - local_irq_enable(); - preempt_enable(); - r = -EINTR; - kvm_run->exit_reason = KVM_EXIT_INTR; - ++vcpu->stat.signal_exits; - goto out; - } - - if (irqchip_in_kernel(vcpu->kvm)) - kvm_x86_ops->inject_pending_irq(vcpu); - else if (!vcpu->mmio_read_completed) - kvm_x86_ops->inject_pending_vectors(vcpu, kvm_run); - - vcpu->guest_mode = 1; - kvm_guest_enter(); - - if (vcpu->requests) - if (test_and_clear_bit(KVM_TLB_FLUSH, &vcpu->requests)) - kvm_x86_ops->tlb_flush(vcpu); - - kvm_x86_ops->run(vcpu, kvm_run); - - vcpu->guest_mode = 0; - local_irq_enable(); - - ++vcpu->stat.exits; - - /* - * We must have an instruction between local_irq_enable() and - * kvm_guest_exit(), so the timer interrupt isn't delayed by - * the interrupt shadow. The stat.exits increment will do nicely. - * But we need to prevent reordering, hence this barrier(): - */ - barrier(); - - kvm_guest_exit(); - - preempt_enable(); - - /* - * Profile KVM exit RIPs: - */ - if (unlikely(prof_on == KVM_PROFILING)) { - kvm_x86_ops->cache_regs(vcpu); - profile_hit(KVM_PROFILING, (void *)vcpu->rip); - } - - r = kvm_x86_ops->handle_exit(kvm_run, vcpu); - - if (r > 0) { - if (dm_request_for_irq_injection(vcpu, kvm_run)) { - r = -EINTR; - kvm_run->exit_reason = KVM_EXIT_INTR; - ++vcpu->stat.request_irq_exits; - goto out; - } - if (!need_resched()) { - ++vcpu->stat.light_exits; - goto again; - } - } - -out: - if (r > 0) { - kvm_resched(vcpu); - goto preempted; - } - - post_kvm_run_save(vcpu, kvm_run); - - return r; -} - - -static int kvm_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) -{ - int r; - sigset_t sigsaved; - - vcpu_load(vcpu); - - if (unlikely(vcpu->mp_state == VCPU_MP_STATE_UNINITIALIZED)) { - kvm_vcpu_block(vcpu); - vcpu_put(vcpu); - return -EAGAIN; - } - - if (vcpu->sigset_active) - sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved); - - /* re-sync apic's tpr */ - if (!irqchip_in_kernel(vcpu->kvm)) - set_cr8(vcpu, kvm_run->cr8); - - if (vcpu->pio.cur_count) { - r = complete_pio(vcpu); - if (r) - goto out; - } - - if (vcpu->mmio_needed) { - memcpy(vcpu->mmio_data, kvm_run->mmio.data, 8); - vcpu->mmio_read_completed = 1; - vcpu->mmio_needed = 0; - r = emulate_instruction(vcpu, kvm_run, - vcpu->mmio_fault_cr2, 0); - if (r == EMULATE_DO_MMIO) { - /* - * Read-modify-write. Back to userspace. - */ - r = 0; - goto out; - } - } - - if (kvm_run->exit_reason == KVM_EXIT_HYPERCALL) { - kvm_x86_ops->cache_regs(vcpu); - vcpu->regs[VCPU_REGS_RAX] = kvm_run->hypercall.ret; - kvm_x86_ops->decache_regs(vcpu); - } - - r = __vcpu_run(vcpu, kvm_run); - -out: - if (vcpu->sigset_active) - sigprocmask(SIG_SETMASK, &sigsaved, NULL); - - vcpu_put(vcpu); - return r; -} - -static int kvm_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, - struct kvm_regs *regs) -{ - vcpu_load(vcpu); - - kvm_x86_ops->cache_regs(vcpu); - - regs->rax = vcpu->regs[VCPU_REGS_RAX]; - regs->rbx = vcpu->regs[VCPU_REGS_RBX]; - regs->rcx = vcpu->regs[VCPU_REGS_RCX]; - regs->rdx = vcpu->regs[VCPU_REGS_RDX]; - regs->rsi = vcpu->regs[VCPU_REGS_RSI]; - regs->rdi = vcpu->regs[VCPU_REGS_RDI]; - regs->rsp = vcpu->regs[VCPU_REGS_RSP]; - regs->rbp = vcpu->regs[VCPU_REGS_RBP]; -#ifdef CONFIG_X86_64 - regs->r8 = vcpu->regs[VCPU_REGS_R8]; - regs->r9 = vcpu->regs[VCPU_REGS_R9]; - regs->r10 = vcpu->regs[VCPU_REGS_R10]; - regs->r11 = vcpu->regs[VCPU_REGS_R11]; - regs->r12 = vcpu->regs[VCPU_REGS_R12]; - regs->r13 = vcpu->regs[VCPU_REGS_R13]; - regs->r14 = vcpu->regs[VCPU_REGS_R14]; - regs->r15 = vcpu->regs[VCPU_REGS_R15]; -#endif - - regs->rip = vcpu->rip; - regs->rflags = kvm_x86_ops->get_rflags(vcpu); - - /* - * Don't leak debug flags in case they were set for guest debugging - */ - if (vcpu->guest_debug.enabled && vcpu->guest_debug.singlestep) - regs->rflags &= ~(X86_EFLAGS_TF | X86_EFLAGS_RF); - - vcpu_put(vcpu); - - return 0; -} - -static int kvm_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, - struct kvm_regs *regs) -{ - vcpu_load(vcpu); - - vcpu->regs[VCPU_REGS_RAX] = regs->rax; - vcpu->regs[VCPU_REGS_RBX] = regs->rbx; - vcpu->regs[VCPU_REGS_RCX] = regs->rcx; - vcpu->regs[VCPU_REGS_RDX] = regs->rdx; - vcpu->regs[VCPU_REGS_RSI] = regs->rsi; - vcpu->regs[VCPU_REGS_RDI] = regs->rdi; - vcpu->regs[VCPU_REGS_RSP] = regs->rsp; - vcpu->regs[VCPU_REGS_RBP] = regs->rbp; -#ifdef CONFIG_X86_64 - vcpu->regs[VCPU_REGS_R8] = regs->r8; - vcpu->regs[VCPU_REGS_R9] = regs->r9; - vcpu->regs[VCPU_REGS_R10] = regs->r10; - vcpu->regs[VCPU_REGS_R11] = regs->r11; - vcpu->regs[VCPU_REGS_R12] = regs->r12; - vcpu->regs[VCPU_REGS_R13] = regs->r13; - vcpu->regs[VCPU_REGS_R14] = regs->r14; - vcpu->regs[VCPU_REGS_R15] = regs->r15; -#endif - - vcpu->rip = regs->rip; - kvm_x86_ops->set_rflags(vcpu, regs->rflags); - - kvm_x86_ops->decache_regs(vcpu); - - vcpu_put(vcpu); - - return 0; -} - -static void get_segment(struct kvm_vcpu *vcpu, - struct kvm_segment *var, int seg) -{ - return kvm_x86_ops->get_segment(vcpu, var, seg); -} - -static int kvm_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu, - struct kvm_sregs *sregs) -{ - struct descriptor_table dt; - int pending_vec; - - vcpu_load(vcpu); - - get_segment(vcpu, &sregs->cs, VCPU_SREG_CS); - get_segment(vcpu, &sregs->ds, VCPU_SREG_DS); - get_segment(vcpu, &sregs->es, VCPU_SREG_ES); - get_segment(vcpu, &sregs->fs, VCPU_SREG_FS); - get_segment(vcpu, &sregs->gs, VCPU_SREG_GS); - get_segment(vcpu, &sregs->ss, VCPU_SREG_SS); - - get_segment(vcpu, &sregs->tr, VCPU_SREG_TR); - get_segment(vcpu, &sregs->ldt, VCPU_SREG_LDTR); - - kvm_x86_ops->get_idt(vcpu, &dt); - sregs->idt.limit = dt.limit; - sregs->idt.base = dt.base; - kvm_x86_ops->get_gdt(vcpu, &dt); - sregs->gdt.limit = dt.limit; - sregs->gdt.base = dt.base; - - kvm_x86_ops->decache_cr4_guest_bits(vcpu); - sregs->cr0 = vcpu->cr0; - sregs->cr2 = vcpu->cr2; - sregs->cr3 = vcpu->cr3; - sregs->cr4 = vcpu->cr4; - sregs->cr8 = get_cr8(vcpu); - sregs->efer = vcpu->shadow_efer; - sregs->apic_base = kvm_get_apic_base(vcpu); - - if (irqchip_in_kernel(vcpu->kvm)) { - memset(sregs->interrupt_bitmap, 0, - sizeof sregs->interrupt_bitmap); - pending_vec = kvm_x86_ops->get_irq(vcpu); - if (pending_vec >= 0) - set_bit(pending_vec, (unsigned long *)sregs->interrupt_bitmap); - } else - memcpy(sregs->interrupt_bitmap, vcpu->irq_pending, - sizeof sregs->interrupt_bitmap); - - vcpu_put(vcpu); - - return 0; -} - -static void set_segment(struct kvm_vcpu *vcpu, - struct kvm_segment *var, int seg) -{ - return kvm_x86_ops->set_segment(vcpu, var, seg); -} - -static int kvm_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, - struct kvm_sregs *sregs) -{ - int mmu_reset_needed = 0; - int i, pending_vec, max_bits; - struct descriptor_table dt; - - vcpu_load(vcpu); - - dt.limit = sregs->idt.limit; - dt.base = sregs->idt.base; - kvm_x86_ops->set_idt(vcpu, &dt); - dt.limit = sregs->gdt.limit; - dt.base = sregs->gdt.base; - kvm_x86_ops->set_gdt(vcpu, &dt); - - vcpu->cr2 = sregs->cr2; - mmu_reset_needed |= vcpu->cr3 != sregs->cr3; - vcpu->cr3 = sregs->cr3; - - set_cr8(vcpu, sregs->cr8); - - mmu_reset_needed |= vcpu->shadow_efer != sregs->efer; -#ifdef CONFIG_X86_64 - kvm_x86_ops->set_efer(vcpu, sregs->efer); -#endif - kvm_set_apic_base(vcpu, sregs->apic_base); - - kvm_x86_ops->decache_cr4_guest_bits(vcpu); - - mmu_reset_needed |= vcpu->cr0 != sregs->cr0; - vcpu->cr0 = sregs->cr0; - kvm_x86_ops->set_cr0(vcpu, sregs->cr0); - - mmu_reset_needed |= vcpu->cr4 != sregs->cr4; - kvm_x86_ops->set_cr4(vcpu, sregs->cr4); - if (!is_long_mode(vcpu) && is_pae(vcpu)) - load_pdptrs(vcpu, vcpu->cr3); - - if (mmu_reset_needed) - kvm_mmu_reset_context(vcpu); - - if (!irqchip_in_kernel(vcpu->kvm)) { - memcpy(vcpu->irq_pending, sregs->interrupt_bitmap, - sizeof vcpu->irq_pending); - vcpu->irq_summary = 0; - for (i = 0; i < ARRAY_SIZE(vcpu->irq_pending); ++i) - if (vcpu->irq_pending[i]) - __set_bit(i, &vcpu->irq_summary); - } else { - max_bits = (sizeof sregs->interrupt_bitmap) << 3; - pending_vec = find_first_bit( - (const unsigned long *)sregs->interrupt_bitmap, - max_bits); - /* Only pending external irq is handled here */ - if (pending_vec < max_bits) { - kvm_x86_ops->set_irq(vcpu, pending_vec); - printk("Set back pending irq %d\n", pending_vec); - } - } - - set_segment(vcpu, &sregs->cs, VCPU_SREG_CS); - set_segment(vcpu, &sregs->ds, VCPU_SREG_DS); - set_segment(vcpu, &sregs->es, VCPU_SREG_ES); - set_segment(vcpu, &sregs->fs, VCPU_SREG_FS); - set_segment(vcpu, &sregs->gs, VCPU_SREG_GS); - set_segment(vcpu, &sregs->ss, VCPU_SREG_SS); - - set_segment(vcpu, &sregs->tr, VCPU_SREG_TR); - set_segment(vcpu, &sregs->ldt, VCPU_SREG_LDTR); - - vcpu_put(vcpu); - - return 0; -} - -void kvm_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l) -{ - struct kvm_segment cs; - - get_segment(vcpu, &cs, VCPU_SREG_CS); - *db = cs.db; - *l = cs.l; -} -EXPORT_SYMBOL_GPL(kvm_get_cs_db_l_bits); - -/* - * List of msr numbers which we expose to userspace through KVM_GET_MSRS - * and KVM_SET_MSRS, and KVM_GET_MSR_INDEX_LIST. - * - * This list is modified at module load time to reflect the - * capabilities of the host cpu. - */ -static u32 msrs_to_save[] = { - MSR_IA32_SYSENTER_CS, MSR_IA32_SYSENTER_ESP, MSR_IA32_SYSENTER_EIP, - MSR_K6_STAR, -#ifdef CONFIG_X86_64 - MSR_CSTAR, MSR_KERNEL_GS_BASE, MSR_SYSCALL_MASK, MSR_LSTAR, -#endif - MSR_IA32_TIME_STAMP_COUNTER, -}; - -static unsigned num_msrs_to_save; - -static u32 emulated_msrs[] = { - MSR_IA32_MISC_ENABLE, -}; - -static __init void kvm_init_msr_list(void) -{ - u32 dummy[2]; - unsigned i, j; - - for (i = j = 0; i < ARRAY_SIZE(msrs_to_save); i++) { - if (rdmsr_safe(msrs_to_save[i], &dummy[0], &dummy[1]) < 0) - continue; - if (j < i) - msrs_to_save[j] = msrs_to_save[i]; - j++; - } - num_msrs_to_save = j; -} - -/* - * Adapt set_msr() to msr_io()'s calling convention - */ -static int do_set_msr(struct kvm_vcpu *vcpu, unsigned index, u64 *data) -{ - return kvm_set_msr(vcpu, index, *data); -} - -/* - * Read or write a bunch of msrs. All parameters are kernel addresses. - * - * @return number of msrs set successfully. - */ -static int __msr_io(struct kvm_vcpu *vcpu, struct kvm_msrs *msrs, - struct kvm_msr_entry *entries, - int (*do_msr)(struct kvm_vcpu *vcpu, - unsigned index, u64 *data)) -{ - int i; - - vcpu_load(vcpu); - - for (i = 0; i < msrs->nmsrs; ++i) - if (do_msr(vcpu, entries[i].index, &entries[i].data)) - break; - - vcpu_put(vcpu); - - return i; -} - -/* - * Read or write a bunch of msrs. Parameters are user addresses. - * - * @return number of msrs set successfully. - */ -static int msr_io(struct kvm_vcpu *vcpu, struct kvm_msrs __user *user_msrs, - int (*do_msr)(struct kvm_vcpu *vcpu, - unsigned index, u64 *data), - int writeback) -{ - struct kvm_msrs msrs; - struct kvm_msr_entry *entries; - int r, n; - unsigned size; - - r = -EFAULT; - if (copy_from_user(&msrs, user_msrs, sizeof msrs)) - goto out; - - r = -E2BIG; - if (msrs.nmsrs >= MAX_IO_MSRS) - goto out; - - r = -ENOMEM; - size = sizeof(struct kvm_msr_entry) * msrs.nmsrs; - entries = vmalloc(size); - if (!entries) - goto out; - - r = -EFAULT; - if (copy_from_user(entries, user_msrs->entries, size)) - goto out_free; - - r = n = __msr_io(vcpu, &msrs, entries, do_msr); - if (r < 0) - goto out_free; - - r = -EFAULT; - if (writeback && copy_to_user(user_msrs->entries, entries, size)) - goto out_free; - - r = n; - -out_free: - vfree(entries); -out: - return r; -} - -/* - * Translate a guest virtual address to a guest physical address. - */ -static int kvm_vcpu_ioctl_translate(struct kvm_vcpu *vcpu, - struct kvm_translation *tr) -{ - unsigned long vaddr = tr->linear_address; - gpa_t gpa; - - vcpu_load(vcpu); - mutex_lock(&vcpu->kvm->lock); - gpa = vcpu->mmu.gva_to_gpa(vcpu, vaddr); - tr->physical_address = gpa; - tr->valid = gpa != UNMAPPED_GVA; - tr->writeable = 1; - tr->usermode = 0; - mutex_unlock(&vcpu->kvm->lock); - vcpu_put(vcpu); - - return 0; -} - -static int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu, - struct kvm_interrupt *irq) -{ - if (irq->irq < 0 || irq->irq >= 256) - return -EINVAL; - if (irqchip_in_kernel(vcpu->kvm)) - return -ENXIO; - vcpu_load(vcpu); - - set_bit(irq->irq, vcpu->irq_pending); - set_bit(irq->irq / BITS_PER_LONG, &vcpu->irq_summary); - - vcpu_put(vcpu); - - return 0; -} - -static int kvm_vcpu_ioctl_debug_guest(struct kvm_vcpu *vcpu, - struct kvm_debug_guest *dbg) -{ - int r; - - vcpu_load(vcpu); - - r = kvm_x86_ops->set_guest_debug(vcpu, dbg); - - vcpu_put(vcpu); - - return r; -} - -static struct page *kvm_vcpu_nopage(struct vm_area_struct *vma, - unsigned long address, - int *type) -{ - struct kvm_vcpu *vcpu = vma->vm_file->private_data; - unsigned long pgoff; - struct page *page; - - pgoff = ((address - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff; - if (pgoff == 0) - page = virt_to_page(vcpu->run); - else if (pgoff == KVM_PIO_PAGE_OFFSET) - page = virt_to_page(vcpu->pio_data); - else - return NOPAGE_SIGBUS; - get_page(page); - if (type != NULL) - *type = VM_FAULT_MINOR; - - return page; -} - -static struct vm_operations_struct kvm_vcpu_vm_ops = { - .nopage = kvm_vcpu_nopage, -}; - -static int kvm_vcpu_mmap(struct file *file, struct vm_area_struct *vma) -{ - vma->vm_ops = &kvm_vcpu_vm_ops; - return 0; -} - -static int kvm_vcpu_release(struct inode *inode, struct file *filp) -{ - struct kvm_vcpu *vcpu = filp->private_data; - - fput(vcpu->kvm->filp); - return 0; -} - -static struct file_operations kvm_vcpu_fops = { - .release = kvm_vcpu_release, - .unlocked_ioctl = kvm_vcpu_ioctl, - .compat_ioctl = kvm_vcpu_ioctl, - .mmap = kvm_vcpu_mmap, -}; - -/* - * Allocates an inode for the vcpu. - */ -static int create_vcpu_fd(struct kvm_vcpu *vcpu) -{ - int fd, r; - struct inode *inode; - struct file *file; - - r = anon_inode_getfd(&fd, &inode, &file, - "kvm-vcpu", &kvm_vcpu_fops, vcpu); - if (r) - return r; - atomic_inc(&vcpu->kvm->filp->f_count); - return fd; -} - -/* - * Creates some virtual cpus. Good luck creating more than one. - */ -static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, int n) -{ - int r; - struct kvm_vcpu *vcpu; - - if (!valid_vcpu(n)) - return -EINVAL; - - vcpu = kvm_x86_ops->vcpu_create(kvm, n); - if (IS_ERR(vcpu)) - return PTR_ERR(vcpu); - - preempt_notifier_init(&vcpu->preempt_notifier, &kvm_preempt_ops); - - /* We do fxsave: this must be aligned. */ - BUG_ON((unsigned long)&vcpu->host_fx_image & 0xF); - - vcpu_load(vcpu); - r = kvm_mmu_setup(vcpu); - vcpu_put(vcpu); - if (r < 0) - goto free_vcpu; - - mutex_lock(&kvm->lock); - if (kvm->vcpus[n]) { - r = -EEXIST; - mutex_unlock(&kvm->lock); - goto mmu_unload; - } - kvm->vcpus[n] = vcpu; - mutex_unlock(&kvm->lock); - - /* Now it's all set up, let userspace reach it */ - r = create_vcpu_fd(vcpu); - if (r < 0) - goto unlink; - return r; - -unlink: - mutex_lock(&kvm->lock); - kvm->vcpus[n] = NULL; - mutex_unlock(&kvm->lock); - -mmu_unload: - vcpu_load(vcpu); - kvm_mmu_unload(vcpu); - vcpu_put(vcpu); - -free_vcpu: - kvm_x86_ops->vcpu_free(vcpu); - return r; -} - -static void cpuid_fix_nx_cap(struct kvm_vcpu *vcpu) -{ - u64 efer; - int i; - struct kvm_cpuid_entry *e, *entry; - - rdmsrl(MSR_EFER, efer); - entry = NULL; - for (i = 0; i < vcpu->cpuid_nent; ++i) { - e = &vcpu->cpuid_entries[i]; - if (e->function == 0x80000001) { - entry = e; - break; - } - } - if (entry && (entry->edx & (1 << 20)) && !(efer & EFER_NX)) { - entry->edx &= ~(1 << 20); - printk(KERN_INFO "kvm: guest NX capability removed\n"); - } -} - -static int kvm_vcpu_ioctl_set_cpuid(struct kvm_vcpu *vcpu, - struct kvm_cpuid *cpuid, - struct kvm_cpuid_entry __user *entries) -{ - int r; - - r = -E2BIG; - if (cpuid->nent > KVM_MAX_CPUID_ENTRIES) - goto out; - r = -EFAULT; - if (copy_from_user(&vcpu->cpuid_entries, entries, - cpuid->nent * sizeof(struct kvm_cpuid_entry))) - goto out; - vcpu->cpuid_nent = cpuid->nent; - cpuid_fix_nx_cap(vcpu); - return 0; - -out: - return r; -} - -static int kvm_vcpu_ioctl_set_sigmask(struct kvm_vcpu *vcpu, sigset_t *sigset) -{ - if (sigset) { - sigdelsetmask(sigset, sigmask(SIGKILL)|sigmask(SIGSTOP)); - vcpu->sigset_active = 1; - vcpu->sigset = *sigset; - } else - vcpu->sigset_active = 0; - return 0; -} - -/* - * fxsave fpu state. Taken from x86_64/processor.h. To be killed when - * we have asm/x86/processor.h - */ -struct fxsave { - u16 cwd; - u16 swd; - u16 twd; - u16 fop; - u64 rip; - u64 rdp; - u32 mxcsr; - u32 mxcsr_mask; - u32 st_space[32]; /* 8*16 bytes for each FP-reg = 128 bytes */ -#ifdef CONFIG_X86_64 - u32 xmm_space[64]; /* 16*16 bytes for each XMM-reg = 256 bytes */ -#else - u32 xmm_space[32]; /* 8*16 bytes for each XMM-reg = 128 bytes */ -#endif -}; - -static int kvm_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) -{ - struct fxsave *fxsave = (struct fxsave *)&vcpu->guest_fx_image; - - vcpu_load(vcpu); - - memcpy(fpu->fpr, fxsave->st_space, 128); - fpu->fcw = fxsave->cwd; - fpu->fsw = fxsave->swd; - fpu->ftwx = fxsave->twd; - fpu->last_opcode = fxsave->fop; - fpu->last_ip = fxsave->rip; - fpu->last_dp = fxsave->rdp; - memcpy(fpu->xmm, fxsave->xmm_space, sizeof fxsave->xmm_space); - - vcpu_put(vcpu); - - return 0; -} - -static int kvm_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) -{ - struct fxsave *fxsave = (struct fxsave *)&vcpu->guest_fx_image; - - vcpu_load(vcpu); - - memcpy(fxsave->st_space, fpu->fpr, 128); - fxsave->cwd = fpu->fcw; - fxsave->swd = fpu->fsw; - fxsave->twd = fpu->ftwx; - fxsave->fop = fpu->last_opcode; - fxsave->rip = fpu->last_ip; - fxsave->rdp = fpu->last_dp; - memcpy(fxsave->xmm_space, fpu->xmm, sizeof fxsave->xmm_space); - - vcpu_put(vcpu); - - return 0; -} - -static int kvm_vcpu_ioctl_get_lapic(struct kvm_vcpu *vcpu, - struct kvm_lapic_state *s) -{ - vcpu_load(vcpu); - memcpy(s->regs, vcpu->apic->regs, sizeof *s); - vcpu_put(vcpu); - - return 0; -} - -static int kvm_vcpu_ioctl_set_lapic(struct kvm_vcpu *vcpu, - struct kvm_lapic_state *s) -{ - vcpu_load(vcpu); - memcpy(vcpu->apic->regs, s->regs, sizeof *s); - kvm_apic_post_state_restore(vcpu); - vcpu_put(vcpu); - - return 0; -} - -static long kvm_vcpu_ioctl(struct file *filp, - unsigned int ioctl, unsigned long arg) -{ - struct kvm_vcpu *vcpu = filp->private_data; - void __user *argp = (void __user *)arg; - int r = -EINVAL; - - switch (ioctl) { - case KVM_RUN: - r = -EINVAL; - if (arg) - goto out; - r = kvm_vcpu_ioctl_run(vcpu, vcpu->run); - break; - case KVM_GET_REGS: { - struct kvm_regs kvm_regs; - - memset(&kvm_regs, 0, sizeof kvm_regs); - r = kvm_vcpu_ioctl_get_regs(vcpu, &kvm_regs); - if (r) - goto out; - r = -EFAULT; - if (copy_to_user(argp, &kvm_regs, sizeof kvm_regs)) - goto out; - r = 0; - break; - } - case KVM_SET_REGS: { - struct kvm_regs kvm_regs; - - r = -EFAULT; - if (copy_from_user(&kvm_regs, argp, sizeof kvm_regs)) - goto out; - r = kvm_vcpu_ioctl_set_regs(vcpu, &kvm_regs); - if (r) - goto out; - r = 0; - break; - } - case KVM_GET_SREGS: { - struct kvm_sregs kvm_sregs; - - memset(&kvm_sregs, 0, sizeof kvm_sregs); - r = kvm_vcpu_ioctl_get_sregs(vcpu, &kvm_sregs); - if (r) - goto out; - r = -EFAULT; - if (copy_to_user(argp, &kvm_sregs, sizeof kvm_sregs)) - goto out; - r = 0; - break; - } - case KVM_SET_SREGS: { - struct kvm_sregs kvm_sregs; - - r = -EFAULT; - if (copy_from_user(&kvm_sregs, argp, sizeof kvm_sregs)) - goto out; - r = kvm_vcpu_ioctl_set_sregs(vcpu, &kvm_sregs); - if (r) - goto out; - r = 0; - break; - } - case KVM_TRANSLATE: { - struct kvm_translation tr; - - r = -EFAULT; - if (copy_from_user(&tr, argp, sizeof tr)) - goto out; - r = kvm_vcpu_ioctl_translate(vcpu, &tr); - if (r) - goto out; - r = -EFAULT; - if (copy_to_user(argp, &tr, sizeof tr)) - goto out; - r = 0; - break; - } - case KVM_INTERRUPT: { - struct kvm_interrupt irq; - - r = -EFAULT; - if (copy_from_user(&irq, argp, sizeof irq)) - goto out; - r = kvm_vcpu_ioctl_interrupt(vcpu, &irq); - if (r) - goto out; - r = 0; - break; - } - case KVM_DEBUG_GUEST: { - struct kvm_debug_guest dbg; - - r = -EFAULT; - if (copy_from_user(&dbg, argp, sizeof dbg)) - goto out; - r = kvm_vcpu_ioctl_debug_guest(vcpu, &dbg); - if (r) - goto out; - r = 0; - break; - } - case KVM_GET_MSRS: - r = msr_io(vcpu, argp, kvm_get_msr, 1); - break; - case KVM_SET_MSRS: - r = msr_io(vcpu, argp, do_set_msr, 0); - break; - case KVM_SET_CPUID: { - struct kvm_cpuid __user *cpuid_arg = argp; - struct kvm_cpuid cpuid; - - r = -EFAULT; - if (copy_from_user(&cpuid, cpuid_arg, sizeof cpuid)) - goto out; - r = kvm_vcpu_ioctl_set_cpuid(vcpu, &cpuid, cpuid_arg->entries); - if (r) - goto out; - break; - } - case KVM_SET_SIGNAL_MASK: { - struct kvm_signal_mask __user *sigmask_arg = argp; - struct kvm_signal_mask kvm_sigmask; - sigset_t sigset, *p; - - p = NULL; - if (argp) { - r = -EFAULT; - if (copy_from_user(&kvm_sigmask, argp, - sizeof kvm_sigmask)) - goto out; - r = -EINVAL; - if (kvm_sigmask.len != sizeof sigset) - goto out; - r = -EFAULT; - if (copy_from_user(&sigset, sigmask_arg->sigset, - sizeof sigset)) - goto out; - p = &sigset; - } - r = kvm_vcpu_ioctl_set_sigmask(vcpu, &sigset); - break; - } - case KVM_GET_FPU: { - struct kvm_fpu fpu; - - memset(&fpu, 0, sizeof fpu); - r = kvm_vcpu_ioctl_get_fpu(vcpu, &fpu); - if (r) - goto out; - r = -EFAULT; - if (copy_to_user(argp, &fpu, sizeof fpu)) - goto out; - r = 0; - break; - } - case KVM_SET_FPU: { - struct kvm_fpu fpu; - - r = -EFAULT; - if (copy_from_user(&fpu, argp, sizeof fpu)) - goto out; - r = kvm_vcpu_ioctl_set_fpu(vcpu, &fpu); - if (r) - goto out; - r = 0; - break; - } - case KVM_GET_LAPIC: { - struct kvm_lapic_state lapic; - - memset(&lapic, 0, sizeof lapic); - r = kvm_vcpu_ioctl_get_lapic(vcpu, &lapic); - if (r) - goto out; - r = -EFAULT; - if (copy_to_user(argp, &lapic, sizeof lapic)) - goto out; - r = 0; - break; - } - case KVM_SET_LAPIC: { - struct kvm_lapic_state lapic; - - r = -EFAULT; - if (copy_from_user(&lapic, argp, sizeof lapic)) - goto out; - r = kvm_vcpu_ioctl_set_lapic(vcpu, &lapic);; - if (r) - goto out; - r = 0; - break; - } - default: - ; - } -out: - return r; -} - -static long kvm_vm_ioctl(struct file *filp, - unsigned int ioctl, unsigned long arg) -{ - struct kvm *kvm = filp->private_data; - void __user *argp = (void __user *)arg; - int r = -EINVAL; - - switch (ioctl) { - case KVM_CREATE_VCPU: - r = kvm_vm_ioctl_create_vcpu(kvm, arg); - if (r < 0) - goto out; - break; - case KVM_SET_MEMORY_REGION: { - struct kvm_memory_region kvm_mem; - - r = -EFAULT; - if (copy_from_user(&kvm_mem, argp, sizeof kvm_mem)) - goto out; - r = kvm_vm_ioctl_set_memory_region(kvm, &kvm_mem); - if (r) - goto out; - break; - } - case KVM_GET_DIRTY_LOG: { - struct kvm_dirty_log log; - - r = -EFAULT; - if (copy_from_user(&log, argp, sizeof log)) - goto out; - r = kvm_vm_ioctl_get_dirty_log(kvm, &log); - if (r) - goto out; - break; - } - case KVM_SET_MEMORY_ALIAS: { - struct kvm_memory_alias alias; - - r = -EFAULT; - if (copy_from_user(&alias, argp, sizeof alias)) - goto out; - r = kvm_vm_ioctl_set_memory_alias(kvm, &alias); - if (r) - goto out; - break; - } - case KVM_CREATE_IRQCHIP: - r = -ENOMEM; - kvm->vpic = kvm_create_pic(kvm); - if (kvm->vpic) { - r = kvm_ioapic_init(kvm); - if (r) { - kfree(kvm->vpic); - kvm->vpic = NULL; - goto out; - } - } - else - goto out; - break; - case KVM_IRQ_LINE: { - struct kvm_irq_level irq_event; - - r = -EFAULT; - if (copy_from_user(&irq_event, argp, sizeof irq_event)) - goto out; - if (irqchip_in_kernel(kvm)) { - mutex_lock(&kvm->lock); - if (irq_event.irq < 16) - kvm_pic_set_irq(pic_irqchip(kvm), - irq_event.irq, - irq_event.level); - kvm_ioapic_set_irq(kvm->vioapic, - irq_event.irq, - irq_event.level); - mutex_unlock(&kvm->lock); - r = 0; - } - break; - } - case KVM_GET_IRQCHIP: { - /* 0: PIC master, 1: PIC slave, 2: IOAPIC */ - struct kvm_irqchip chip; - - r = -EFAULT; - if (copy_from_user(&chip, argp, sizeof chip)) - goto out; - r = -ENXIO; - if (!irqchip_in_kernel(kvm)) - goto out; - r = kvm_vm_ioctl_get_irqchip(kvm, &chip); - if (r) - goto out; - r = -EFAULT; - if (copy_to_user(argp, &chip, sizeof chip)) - goto out; - r = 0; - break; - } - case KVM_SET_IRQCHIP: { - /* 0: PIC master, 1: PIC slave, 2: IOAPIC */ - struct kvm_irqchip chip; - - r = -EFAULT; - if (copy_from_user(&chip, argp, sizeof chip)) - goto out; - r = -ENXIO; - if (!irqchip_in_kernel(kvm)) - goto out; - r = kvm_vm_ioctl_set_irqchip(kvm, &chip); - if (r) - goto out; - r = 0; - break; - } - default: - ; - } -out: - return r; -} - -static struct page *kvm_vm_nopage(struct vm_area_struct *vma, - unsigned long address, - int *type) -{ - struct kvm *kvm = vma->vm_file->private_data; - unsigned long pgoff; - struct page *page; - - pgoff = ((address - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff; - page = gfn_to_page(kvm, pgoff); - if (!page) - return NOPAGE_SIGBUS; - get_page(page); - if (type != NULL) - *type = VM_FAULT_MINOR; - - return page; -} - -static struct vm_operations_struct kvm_vm_vm_ops = { - .nopage = kvm_vm_nopage, -}; - -static int kvm_vm_mmap(struct file *file, struct vm_area_struct *vma) -{ - vma->vm_ops = &kvm_vm_vm_ops; - return 0; -} - -static struct file_operations kvm_vm_fops = { - .release = kvm_vm_release, - .unlocked_ioctl = kvm_vm_ioctl, - .compat_ioctl = kvm_vm_ioctl, - .mmap = kvm_vm_mmap, -}; - -static int kvm_dev_ioctl_create_vm(void) -{ - int fd, r; - struct inode *inode; - struct file *file; - struct kvm *kvm; - - kvm = kvm_create_vm(); - if (IS_ERR(kvm)) - return PTR_ERR(kvm); - r = anon_inode_getfd(&fd, &inode, &file, "kvm-vm", &kvm_vm_fops, kvm); - if (r) { - kvm_destroy_vm(kvm); - return r; - } - - kvm->filp = file; - - return fd; -} - -static long kvm_dev_ioctl(struct file *filp, - unsigned int ioctl, unsigned long arg) -{ - void __user *argp = (void __user *)arg; - long r = -EINVAL; - - switch (ioctl) { - case KVM_GET_API_VERSION: - r = -EINVAL; - if (arg) - goto out; - r = KVM_API_VERSION; - break; - case KVM_CREATE_VM: - r = -EINVAL; - if (arg) - goto out; - r = kvm_dev_ioctl_create_vm(); - break; - case KVM_GET_MSR_INDEX_LIST: { - struct kvm_msr_list __user *user_msr_list = argp; - struct kvm_msr_list msr_list; - unsigned n; - - r = -EFAULT; - if (copy_from_user(&msr_list, user_msr_list, sizeof msr_list)) - goto out; - n = msr_list.nmsrs; - msr_list.nmsrs = num_msrs_to_save + ARRAY_SIZE(emulated_msrs); - if (copy_to_user(user_msr_list, &msr_list, sizeof msr_list)) - goto out; - r = -E2BIG; - if (n < num_msrs_to_save) - goto out; - r = -EFAULT; - if (copy_to_user(user_msr_list->indices, &msrs_to_save, - num_msrs_to_save * sizeof(u32))) - goto out; - if (copy_to_user(user_msr_list->indices - + num_msrs_to_save * sizeof(u32), - &emulated_msrs, - ARRAY_SIZE(emulated_msrs) * sizeof(u32))) - goto out; - r = 0; - break; - } - case KVM_CHECK_EXTENSION: { - int ext = (long)argp; - - switch (ext) { - case KVM_CAP_IRQCHIP: - case KVM_CAP_HLT: - r = 1; - break; - default: - r = 0; - break; - } - break; - } - case KVM_GET_VCPU_MMAP_SIZE: - r = -EINVAL; - if (arg) - goto out; - r = 2 * PAGE_SIZE; - break; - default: - ; - } -out: - return r; -} - -static struct file_operations kvm_chardev_ops = { - .unlocked_ioctl = kvm_dev_ioctl, - .compat_ioctl = kvm_dev_ioctl, -}; - -static struct miscdevice kvm_dev = { - KVM_MINOR, - "kvm", - &kvm_chardev_ops, -}; - -/* - * Make sure that a cpu that is being hot-unplugged does not have any vcpus - * cached on it. - */ -static void decache_vcpus_on_cpu(int cpu) -{ - struct kvm *vm; - struct kvm_vcpu *vcpu; - int i; - - spin_lock(&kvm_lock); - list_for_each_entry(vm, &vm_list, vm_list) - for (i = 0; i < KVM_MAX_VCPUS; ++i) { - vcpu = vm->vcpus[i]; - if (!vcpu) - continue; - /* - * If the vcpu is locked, then it is running on some - * other cpu and therefore it is not cached on the - * cpu in question. - * - * If it's not locked, check the last cpu it executed - * on. - */ - if (mutex_trylock(&vcpu->mutex)) { - if (vcpu->cpu == cpu) { - kvm_x86_ops->vcpu_decache(vcpu); - vcpu->cpu = -1; - } - mutex_unlock(&vcpu->mutex); - } - } - spin_unlock(&kvm_lock); -} - -static void hardware_enable(void *junk) -{ - int cpu = raw_smp_processor_id(); - - if (cpu_isset(cpu, cpus_hardware_enabled)) - return; - cpu_set(cpu, cpus_hardware_enabled); - kvm_x86_ops->hardware_enable(NULL); -} - -static void hardware_disable(void *junk) -{ - int cpu = raw_smp_processor_id(); - - if (!cpu_isset(cpu, cpus_hardware_enabled)) - return; - cpu_clear(cpu, cpus_hardware_enabled); - decache_vcpus_on_cpu(cpu); - kvm_x86_ops->hardware_disable(NULL); -} - -static int kvm_cpu_hotplug(struct notifier_block *notifier, unsigned long val, - void *v) -{ - int cpu = (long)v; - - switch (val) { - case CPU_DYING: - case CPU_DYING_FROZEN: - printk(KERN_INFO "kvm: disabling virtualization on CPU%d\n", - cpu); - hardware_disable(NULL); - break; - case CPU_UP_CANCELED: - case CPU_UP_CANCELED_FROZEN: - printk(KERN_INFO "kvm: disabling virtualization on CPU%d\n", - cpu); - smp_call_function_single(cpu, hardware_disable, NULL, 0, 1); - break; - case CPU_ONLINE: - case CPU_ONLINE_FROZEN: - printk(KERN_INFO "kvm: enabling virtualization on CPU%d\n", - cpu); - smp_call_function_single(cpu, hardware_enable, NULL, 0, 1); - break; - } - return NOTIFY_OK; -} - -static int kvm_reboot(struct notifier_block *notifier, unsigned long val, - void *v) -{ - if (val == SYS_RESTART) { - /* - * Some (well, at least mine) BIOSes hang on reboot if - * in vmx root mode. - */ - printk(KERN_INFO "kvm: exiting hardware virtualization\n"); - on_each_cpu(hardware_disable, NULL, 0, 1); - } - return NOTIFY_OK; -} - -static struct notifier_block kvm_reboot_notifier = { - .notifier_call = kvm_reboot, - .priority = 0, -}; - -void kvm_io_bus_init(struct kvm_io_bus *bus) -{ - memset(bus, 0, sizeof(*bus)); -} - -void kvm_io_bus_destroy(struct kvm_io_bus *bus) -{ - int i; - - for (i = 0; i < bus->dev_count; i++) { - struct kvm_io_device *pos = bus->devs[i]; - - kvm_iodevice_destructor(pos); - } -} - -struct kvm_io_device *kvm_io_bus_find_dev(struct kvm_io_bus *bus, gpa_t addr) -{ - int i; - - for (i = 0; i < bus->dev_count; i++) { - struct kvm_io_device *pos = bus->devs[i]; - - if (pos->in_range(pos, addr)) - return pos; - } - - return NULL; -} - -void kvm_io_bus_register_dev(struct kvm_io_bus *bus, struct kvm_io_device *dev) -{ - BUG_ON(bus->dev_count > (NR_IOBUS_DEVS-1)); - - bus->devs[bus->dev_count++] = dev; -} - -static struct notifier_block kvm_cpu_notifier = { - .notifier_call = kvm_cpu_hotplug, - .priority = 20, /* must be > scheduler priority */ -}; - -static u64 stat_get(void *_offset) -{ - unsigned offset = (long)_offset; - u64 total = 0; - struct kvm *kvm; - struct kvm_vcpu *vcpu; - int i; - - spin_lock(&kvm_lock); - list_for_each_entry(kvm, &vm_list, vm_list) - for (i = 0; i < KVM_MAX_VCPUS; ++i) { - vcpu = kvm->vcpus[i]; - if (vcpu) - total += *(u32 *)((void *)vcpu + offset); - } - spin_unlock(&kvm_lock); - return total; -} - -DEFINE_SIMPLE_ATTRIBUTE(stat_fops, stat_get, NULL, "%llu\n"); - -static __init void kvm_init_debug(void) -{ - struct kvm_stats_debugfs_item *p; - - debugfs_dir = debugfs_create_dir("kvm", NULL); - for (p = debugfs_entries; p->name; ++p) - p->dentry = debugfs_create_file(p->name, 0444, debugfs_dir, - (void *)(long)p->offset, - &stat_fops); -} - -static void kvm_exit_debug(void) -{ - struct kvm_stats_debugfs_item *p; - - for (p = debugfs_entries; p->name; ++p) - debugfs_remove(p->dentry); - debugfs_remove(debugfs_dir); -} - -static int kvm_suspend(struct sys_device *dev, pm_message_t state) -{ - hardware_disable(NULL); - return 0; -} - -static int kvm_resume(struct sys_device *dev) -{ - hardware_enable(NULL); - return 0; -} - -static struct sysdev_class kvm_sysdev_class = { - .name = "kvm", - .suspend = kvm_suspend, - .resume = kvm_resume, -}; - -static struct sys_device kvm_sysdev = { - .id = 0, - .cls = &kvm_sysdev_class, -}; - -hpa_t bad_page_address; - -static inline -struct kvm_vcpu *preempt_notifier_to_vcpu(struct preempt_notifier *pn) -{ - return container_of(pn, struct kvm_vcpu, preempt_notifier); -} - -static void kvm_sched_in(struct preempt_notifier *pn, int cpu) -{ - struct kvm_vcpu *vcpu = preempt_notifier_to_vcpu(pn); - - kvm_x86_ops->vcpu_load(vcpu, cpu); -} - -static void kvm_sched_out(struct preempt_notifier *pn, - struct task_struct *next) -{ - struct kvm_vcpu *vcpu = preempt_notifier_to_vcpu(pn); - - kvm_x86_ops->vcpu_put(vcpu); -} - -int kvm_init_x86(struct kvm_x86_ops *ops, unsigned int vcpu_size, - struct module *module) -{ - int r; - int cpu; - - if (kvm_x86_ops) { - printk(KERN_ERR "kvm: already loaded the other module\n"); - return -EEXIST; - } - - if (!ops->cpu_has_kvm_support()) { - printk(KERN_ERR "kvm: no hardware support\n"); - return -EOPNOTSUPP; - } - if (ops->disabled_by_bios()) { - printk(KERN_ERR "kvm: disabled by bios\n"); - return -EOPNOTSUPP; - } - - kvm_x86_ops = ops; - - r = kvm_x86_ops->hardware_setup(); - if (r < 0) - goto out; - - for_each_online_cpu(cpu) { - smp_call_function_single(cpu, - kvm_x86_ops->check_processor_compatibility, - &r, 0, 1); - if (r < 0) - goto out_free_0; - } - - on_each_cpu(hardware_enable, NULL, 0, 1); - r = register_cpu_notifier(&kvm_cpu_notifier); - if (r) - goto out_free_1; - register_reboot_notifier(&kvm_reboot_notifier); - - r = sysdev_class_register(&kvm_sysdev_class); - if (r) - goto out_free_2; - - r = sysdev_register(&kvm_sysdev); - if (r) - goto out_free_3; - - /* A kmem cache lets us meet the alignment requirements of fx_save. */ - kvm_vcpu_cache = kmem_cache_create("kvm_vcpu", vcpu_size, - __alignof__(struct kvm_vcpu), 0, 0); - if (!kvm_vcpu_cache) { - r = -ENOMEM; - goto out_free_4; - } - - kvm_chardev_ops.owner = module; - - r = misc_register(&kvm_dev); - if (r) { - printk (KERN_ERR "kvm: misc device register failed\n"); - goto out_free; - } - - kvm_preempt_ops.sched_in = kvm_sched_in; - kvm_preempt_ops.sched_out = kvm_sched_out; - - return r; - -out_free: - kmem_cache_destroy(kvm_vcpu_cache); -out_free_4: - sysdev_unregister(&kvm_sysdev); -out_free_3: - sysdev_class_unregister(&kvm_sysdev_class); -out_free_2: - unregister_reboot_notifier(&kvm_reboot_notifier); - unregister_cpu_notifier(&kvm_cpu_notifier); -out_free_1: - on_each_cpu(hardware_disable, NULL, 0, 1); -out_free_0: - kvm_x86_ops->hardware_unsetup(); -out: - kvm_x86_ops = NULL; - return r; -} - -void kvm_exit_x86(void) -{ - misc_deregister(&kvm_dev); - kmem_cache_destroy(kvm_vcpu_cache); - sysdev_unregister(&kvm_sysdev); - sysdev_class_unregister(&kvm_sysdev_class); - unregister_reboot_notifier(&kvm_reboot_notifier); - unregister_cpu_notifier(&kvm_cpu_notifier); - on_each_cpu(hardware_disable, NULL, 0, 1); - kvm_x86_ops->hardware_unsetup(); - kvm_x86_ops = NULL; -} - -static __init int kvm_init(void) -{ - static struct page *bad_page; - int r; - - r = kvm_mmu_module_init(); - if (r) - goto out4; - - kvm_init_debug(); - - kvm_init_msr_list(); - - if ((bad_page = alloc_page(GFP_KERNEL)) == NULL) { - r = -ENOMEM; - goto out; - } - - bad_page_address = page_to_pfn(bad_page) << PAGE_SHIFT; - memset(__va(bad_page_address), 0, PAGE_SIZE); - - return 0; - -out: - kvm_exit_debug(); - kvm_mmu_module_exit(); -out4: - return r; -} - -static __exit void kvm_exit(void) -{ - kvm_exit_debug(); - __free_page(pfn_to_page(bad_page_address >> PAGE_SHIFT)); - kvm_mmu_module_exit(); -} - -module_init(kvm_init) -module_exit(kvm_exit) - -EXPORT_SYMBOL_GPL(kvm_init_x86); -EXPORT_SYMBOL_GPL(kvm_exit_x86); diff --git a/drivers/kvm/kvm_svm.h b/drivers/kvm/kvm_svm.h deleted file mode 100644 index a0e415daef5b..000000000000 --- a/drivers/kvm/kvm_svm.h +++ /dev/null @@ -1,45 +0,0 @@ -#ifndef __KVM_SVM_H -#define __KVM_SVM_H - -#include <linux/kernel.h> -#include <linux/types.h> -#include <linux/list.h> -#include <asm/msr.h> - -#include "svm.h" -#include "kvm.h" - -static const u32 host_save_user_msrs[] = { -#ifdef CONFIG_X86_64 - MSR_STAR, MSR_LSTAR, MSR_CSTAR, MSR_SYSCALL_MASK, MSR_KERNEL_GS_BASE, - MSR_FS_BASE, -#endif - MSR_IA32_SYSENTER_CS, MSR_IA32_SYSENTER_ESP, MSR_IA32_SYSENTER_EIP, -}; - -#define NR_HOST_SAVE_USER_MSRS ARRAY_SIZE(host_save_user_msrs) -#define NUM_DB_REGS 4 - -struct kvm_vcpu; - -struct vcpu_svm { - struct kvm_vcpu vcpu; - struct vmcb *vmcb; - unsigned long vmcb_pa; - struct svm_cpu_data *svm_data; - uint64_t asid_generation; - - unsigned long db_regs[NUM_DB_REGS]; - - u64 next_rip; - - u64 host_user_msrs[NR_HOST_SAVE_USER_MSRS]; - u64 host_gs_base; - unsigned long host_cr2; - unsigned long host_db_regs[NUM_DB_REGS]; - unsigned long host_dr6; - unsigned long host_dr7; -}; - -#endif - diff --git a/drivers/kvm/lapic.c b/drivers/kvm/lapic.c deleted file mode 100644 index 238fcad3cece..000000000000 --- a/drivers/kvm/lapic.c +++ /dev/null @@ -1,1080 +0,0 @@ - -/* - * Local APIC virtualization - * - * Copyright (C) 2006 Qumranet, Inc. - * Copyright (C) 2007 Novell - * Copyright (C) 2007 Intel - * - * Authors: - * Dor Laor <dor.laor@qumranet.com> - * Gregory Haskins <ghaskins@novell.com> - * Yaozu (Eddie) Dong <eddie.dong@intel.com> - * - * Based on Xen 3.1 code, Copyright (c) 2004, Intel Corporation. - * - * This work is licensed under the terms of the GNU GPL, version 2. See - * the COPYING file in the top-level directory. - */ - -#include "kvm.h" -#include <linux/kvm.h> -#include <linux/mm.h> -#include <linux/highmem.h> -#include <linux/smp.h> -#include <linux/hrtimer.h> -#include <linux/io.h> -#include <linux/module.h> -#include <asm/processor.h> -#include <asm/msr.h> -#include <asm/page.h> -#include <asm/current.h> -#include <asm/apicdef.h> -#include <asm/atomic.h> -#include <asm/div64.h> -#include "irq.h" - -#define PRId64 "d" -#define PRIx64 "llx" -#define PRIu64 "u" -#define PRIo64 "o" - -#define APIC_BUS_CYCLE_NS 1 - -/* #define apic_debug(fmt,arg...) printk(KERN_WARNING fmt,##arg) */ -#define apic_debug(fmt, arg...) - -#define APIC_LVT_NUM 6 -/* 14 is the version for Xeon and Pentium 8.4.8*/ -#define APIC_VERSION (0x14UL | ((APIC_LVT_NUM - 1) << 16)) -#define LAPIC_MMIO_LENGTH (1 << 12) -/* followed define is not in apicdef.h */ -#define APIC_SHORT_MASK 0xc0000 -#define APIC_DEST_NOSHORT 0x0 -#define APIC_DEST_MASK 0x800 -#define MAX_APIC_VECTOR 256 - -#define VEC_POS(v) ((v) & (32 - 1)) -#define REG_POS(v) (((v) >> 5) << 4) -static inline u32 apic_get_reg(struct kvm_lapic *apic, int reg_off) -{ - return *((u32 *) (apic->regs + reg_off)); -} - -static inline void apic_set_reg(struct kvm_lapic *apic, int reg_off, u32 val) -{ - *((u32 *) (apic->regs + reg_off)) = val; -} - -static inline int apic_test_and_set_vector(int vec, void *bitmap) -{ - return test_and_set_bit(VEC_POS(vec), (bitmap) + REG_POS(vec)); -} - -static inline int apic_test_and_clear_vector(int vec, void *bitmap) -{ - return test_and_clear_bit(VEC_POS(vec), (bitmap) + REG_POS(vec)); -} - -static inline void apic_set_vector(int vec, void *bitmap) -{ - set_bit(VEC_POS(vec), (bitmap) + REG_POS(vec)); -} - -static inline void apic_clear_vector(int vec, void *bitmap) -{ - clear_bit(VEC_POS(vec), (bitmap) + REG_POS(vec)); -} - -static inline int apic_hw_enabled(struct kvm_lapic *apic) -{ - return (apic)->vcpu->apic_base & MSR_IA32_APICBASE_ENABLE; -} - -static inline int apic_sw_enabled(struct kvm_lapic *apic) -{ - return apic_get_reg(apic, APIC_SPIV) & APIC_SPIV_APIC_ENABLED; -} - -static inline int apic_enabled(struct kvm_lapic *apic) -{ - return apic_sw_enabled(apic) && apic_hw_enabled(apic); -} - -#define LVT_MASK \ - (APIC_LVT_MASKED | APIC_SEND_PENDING | APIC_VECTOR_MASK) - -#define LINT_MASK \ - (LVT_MASK | APIC_MODE_MASK | APIC_INPUT_POLARITY | \ - APIC_LVT_REMOTE_IRR | APIC_LVT_LEVEL_TRIGGER) - -static inline int kvm_apic_id(struct kvm_lapic *apic) -{ - return (apic_get_reg(apic, APIC_ID) >> 24) & 0xff; -} - -static inline int apic_lvt_enabled(struct kvm_lapic *apic, int lvt_type) -{ - return !(apic_get_reg(apic, lvt_type) & APIC_LVT_MASKED); -} - -static inline int apic_lvt_vector(struct kvm_lapic *apic, int lvt_type) -{ - return apic_get_reg(apic, lvt_type) & APIC_VECTOR_MASK; -} - -static inline int apic_lvtt_period(struct kvm_lapic *apic) -{ - return apic_get_reg(apic, APIC_LVTT) & APIC_LVT_TIMER_PERIODIC; -} - -static unsigned int apic_lvt_mask[APIC_LVT_NUM] = { - LVT_MASK | APIC_LVT_TIMER_PERIODIC, /* LVTT */ - LVT_MASK | APIC_MODE_MASK, /* LVTTHMR */ - LVT_MASK | APIC_MODE_MASK, /* LVTPC */ - LINT_MASK, LINT_MASK, /* LVT0-1 */ - LVT_MASK /* LVTERR */ -}; - -static int find_highest_vector(void *bitmap) -{ - u32 *word = bitmap; - int word_offset = MAX_APIC_VECTOR >> 5; - - while ((word_offset != 0) && (word[(--word_offset) << 2] == 0)) - continue; - - if (likely(!word_offset && !word[0])) - return -1; - else - return fls(word[word_offset << 2]) - 1 + (word_offset << 5); -} - -static inline int apic_test_and_set_irr(int vec, struct kvm_lapic *apic) -{ - return apic_test_and_set_vector(vec, apic->regs + APIC_IRR); -} - -static inline void apic_clear_irr(int vec, struct kvm_lapic *apic) -{ - apic_clear_vector(vec, apic->regs + APIC_IRR); -} - -static inline int apic_find_highest_irr(struct kvm_lapic *apic) -{ - int result; - - result = find_highest_vector(apic->regs + APIC_IRR); - ASSERT(result == -1 || result >= 16); - - return result; -} - -int kvm_lapic_find_highest_irr(struct kvm_vcpu *vcpu) -{ - struct kvm_lapic *apic = (struct kvm_lapic *)vcpu->apic; - int highest_irr; - - if (!apic) - return 0; - highest_irr = apic_find_highest_irr(apic); - - return highest_irr; -} -EXPORT_SYMBOL_GPL(kvm_lapic_find_highest_irr); - -int kvm_apic_set_irq(struct kvm_lapic *apic, u8 vec, u8 trig) -{ - if (!apic_test_and_set_irr(vec, apic)) { - /* a new pending irq is set in IRR */ - if (trig) - apic_set_vector(vec, apic->regs + APIC_TMR); - else - apic_clear_vector(vec, apic->regs + APIC_TMR); - kvm_vcpu_kick(apic->vcpu); - return 1; - } - return 0; -} - -static inline int apic_find_highest_isr(struct kvm_lapic *apic) -{ - int result; - - result = find_highest_vector(apic->regs + APIC_ISR); - ASSERT(result == -1 || result >= 16); - - return result; -} - -static void apic_update_ppr(struct kvm_lapic *apic) -{ - u32 tpr, isrv, ppr; - int isr; - - tpr = apic_get_reg(apic, APIC_TASKPRI); - isr = apic_find_highest_isr(apic); - isrv = (isr != -1) ? isr : 0; - - if ((tpr & 0xf0) >= (isrv & 0xf0)) - ppr = tpr & 0xff; - else - ppr = isrv & 0xf0; - - apic_debug("vlapic %p, ppr 0x%x, isr 0x%x, isrv 0x%x", - apic, ppr, isr, isrv); - - apic_set_reg(apic, APIC_PROCPRI, ppr); -} - -static void apic_set_tpr(struct kvm_lapic *apic, u32 tpr) -{ - apic_set_reg(apic, APIC_TASKPRI, tpr); - apic_update_ppr(apic); -} - -int kvm_apic_match_physical_addr(struct kvm_lapic *apic, u16 dest) -{ - return kvm_apic_id(apic) == dest; -} - -int kvm_apic_match_logical_addr(struct kvm_lapic *apic, u8 mda) -{ - int result = 0; - u8 logical_id; - - logical_id = GET_APIC_LOGICAL_ID(apic_get_reg(apic, APIC_LDR)); - - switch (apic_get_reg(apic, APIC_DFR)) { - case APIC_DFR_FLAT: - if (logical_id & mda) - result = 1; - break; - case APIC_DFR_CLUSTER: - if (((logical_id >> 4) == (mda >> 0x4)) - && (logical_id & mda & 0xf)) - result = 1; - break; - default: - printk(KERN_WARNING "Bad DFR vcpu %d: %08x\n", - apic->vcpu->vcpu_id, apic_get_reg(apic, APIC_DFR)); - break; - } - - return result; -} - -static int apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source, - int short_hand, int dest, int dest_mode) -{ - int result = 0; - struct kvm_lapic *target = vcpu->apic; - - apic_debug("target %p, source %p, dest 0x%x, " - "dest_mode 0x%x, short_hand 0x%x", - target, source, dest, dest_mode, short_hand); - - ASSERT(!target); - switch (short_hand) { - case APIC_DEST_NOSHORT: - if (dest_mode == 0) { - /* Physical mode. */ - if ((dest == 0xFF) || (dest == kvm_apic_id(target))) - result = 1; - } else - /* Logical mode. */ - result = kvm_apic_match_logical_addr(target, dest); - break; - case APIC_DEST_SELF: - if (target == source) - result = 1; - break; - case APIC_DEST_ALLINC: - result = 1; - break; - case APIC_DEST_ALLBUT: - if (target != source) - result = 1; - break; - default: - printk(KERN_WARNING "Bad dest shorthand value %x\n", - short_hand); - break; - } - - return result; -} - -/* - * Add a pending IRQ into lapic. - * Return 1 if successfully added and 0 if discarded. - */ -static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode, - int vector, int level, int trig_mode) -{ - int orig_irr, result = 0; - struct kvm_vcpu *vcpu = apic->vcpu; - - switch (delivery_mode) { - case APIC_DM_FIXED: - case APIC_DM_LOWEST: - /* FIXME add logic for vcpu on reset */ - if (unlikely(!apic_enabled(apic))) - break; - - orig_irr = apic_test_and_set_irr(vector, apic); - if (orig_irr && trig_mode) { - apic_debug("level trig mode repeatedly for vector %d", - vector); - break; - } - - if (trig_mode) { - apic_debug("level trig mode for vector %d", vector); - apic_set_vector(vector, apic->regs + APIC_TMR); - } else - apic_clear_vector(vector, apic->regs + APIC_TMR); - - if (vcpu->mp_state == VCPU_MP_STATE_RUNNABLE) - kvm_vcpu_kick(vcpu); - else if (vcpu->mp_state == VCPU_MP_STATE_HALTED) { - vcpu->mp_state = VCPU_MP_STATE_RUNNABLE; - if (waitqueue_active(&vcpu->wq)) - wake_up_interruptible(&vcpu->wq); - } - - result = (orig_irr == 0); - break; - - case APIC_DM_REMRD: - printk(KERN_DEBUG "Ignoring delivery mode 3\n"); - break; - - case APIC_DM_SMI: - printk(KERN_DEBUG "Ignoring guest SMI\n"); - break; - case APIC_DM_NMI: - printk(KERN_DEBUG "Ignoring guest NMI\n"); - break; - - case APIC_DM_INIT: - if (level) { - if (vcpu->mp_state == VCPU_MP_STATE_RUNNABLE) - printk(KERN_DEBUG - "INIT on a runnable vcpu %d\n", - vcpu->vcpu_id); - vcpu->mp_state = VCPU_MP_STATE_INIT_RECEIVED; - kvm_vcpu_kick(vcpu); - } else { - printk(KERN_DEBUG - "Ignoring de-assert INIT to vcpu %d\n", - vcpu->vcpu_id); - } - - break; - - case APIC_DM_STARTUP: - printk(KERN_DEBUG "SIPI to vcpu %d vector 0x%02x\n", - vcpu->vcpu_id, vector); - if (vcpu->mp_state == VCPU_MP_STATE_INIT_RECEIVED) { - vcpu->sipi_vector = vector; - vcpu->mp_state = VCPU_MP_STATE_SIPI_RECEIVED; - if (waitqueue_active(&vcpu->wq)) - wake_up_interruptible(&vcpu->wq); - } - break; - - default: - printk(KERN_ERR "TODO: unsupported delivery mode %x\n", - delivery_mode); - break; - } - return result; -} - -struct kvm_lapic *kvm_apic_round_robin(struct kvm *kvm, u8 vector, - unsigned long bitmap) -{ - int vcpu_id; - int last; - int next; - struct kvm_lapic *apic; - - last = kvm->round_robin_prev_vcpu; - next = last; - - do { - if (++next == KVM_MAX_VCPUS) - next = 0; - if (kvm->vcpus[next] == NULL || !test_bit(next, &bitmap)) - continue; - apic = kvm->vcpus[next]->apic; - if (apic && apic_enabled(apic)) - break; - apic = NULL; - } while (next != last); - kvm->round_robin_prev_vcpu = next; - - if (!apic) { - vcpu_id = ffs(bitmap) - 1; - if (vcpu_id < 0) { - vcpu_id = 0; - printk(KERN_DEBUG "vcpu not ready for apic_round_robin\n"); - } - apic = kvm->vcpus[vcpu_id]->apic; - } - - return apic; -} - -static void apic_set_eoi(struct kvm_lapic *apic) -{ - int vector = apic_find_highest_isr(apic); - - /* - * Not every write EOI will has corresponding ISR, - * one example is when Kernel check timer on setup_IO_APIC - */ - if (vector == -1) - return; - - apic_clear_vector(vector, apic->regs + APIC_ISR); - apic_update_ppr(apic); - - if (apic_test_and_clear_vector(vector, apic->regs + APIC_TMR)) - kvm_ioapic_update_eoi(apic->vcpu->kvm, vector); -} - -static void apic_send_ipi(struct kvm_lapic *apic) -{ - u32 icr_low = apic_get_reg(apic, APIC_ICR); - u32 icr_high = apic_get_reg(apic, APIC_ICR2); - - unsigned int dest = GET_APIC_DEST_FIELD(icr_high); - unsigned int short_hand = icr_low & APIC_SHORT_MASK; - unsigned int trig_mode = icr_low & APIC_INT_LEVELTRIG; - unsigned int level = icr_low & APIC_INT_ASSERT; - unsigned int dest_mode = icr_low & APIC_DEST_MASK; - unsigned int delivery_mode = icr_low & APIC_MODE_MASK; - unsigned int vector = icr_low & APIC_VECTOR_MASK; - - struct kvm_lapic *target; - struct kvm_vcpu *vcpu; - unsigned long lpr_map = 0; - int i; - - apic_debug("icr_high 0x%x, icr_low 0x%x, " - "short_hand 0x%x, dest 0x%x, trig_mode 0x%x, level 0x%x, " - "dest_mode 0x%x, delivery_mode 0x%x, vector 0x%x\n", - icr_high, icr_low, short_hand, dest, - trig_mode, level, dest_mode, delivery_mode, vector); - - for (i = 0; i < KVM_MAX_VCPUS; i++) { - vcpu = apic->vcpu->kvm->vcpus[i]; - if (!vcpu) - continue; - - if (vcpu->apic && - apic_match_dest(vcpu, apic, short_hand, dest, dest_mode)) { - if (delivery_mode == APIC_DM_LOWEST) - set_bit(vcpu->vcpu_id, &lpr_map); - else - __apic_accept_irq(vcpu->apic, delivery_mode, - vector, level, trig_mode); - } - } - - if (delivery_mode == APIC_DM_LOWEST) { - target = kvm_apic_round_robin(vcpu->kvm, vector, lpr_map); - if (target != NULL) - __apic_accept_irq(target, delivery_mode, - vector, level, trig_mode); - } -} - -static u32 apic_get_tmcct(struct kvm_lapic *apic) -{ - u64 counter_passed; - ktime_t passed, now; - u32 tmcct; - - ASSERT(apic != NULL); - - now = apic->timer.dev.base->get_time(); - tmcct = apic_get_reg(apic, APIC_TMICT); - - /* if initial count is 0, current count should also be 0 */ - if (tmcct == 0) - return 0; - - if (unlikely(ktime_to_ns(now) <= - ktime_to_ns(apic->timer.last_update))) { - /* Wrap around */ - passed = ktime_add(( { - (ktime_t) { - .tv64 = KTIME_MAX - - (apic->timer.last_update).tv64}; } - ), now); - apic_debug("time elapsed\n"); - } else - passed = ktime_sub(now, apic->timer.last_update); - - counter_passed = div64_64(ktime_to_ns(passed), - (APIC_BUS_CYCLE_NS * apic->timer.divide_count)); - - if (counter_passed > tmcct) { - if (unlikely(!apic_lvtt_period(apic))) { - /* one-shot timers stick at 0 until reset */ - tmcct = 0; - } else { - /* - * periodic timers reset to APIC_TMICT when they - * hit 0. The while loop simulates this happening N - * times. (counter_passed %= tmcct) would also work, - * but might be slower or not work on 32-bit?? - */ - while (counter_passed > tmcct) - counter_passed -= tmcct; - tmcct -= counter_passed; - } - } else { - tmcct -= counter_passed; - } - - return tmcct; -} - -static u32 __apic_read(struct kvm_lapic *apic, unsigned int offset) -{ - u32 val = 0; - - if (offset >= LAPIC_MMIO_LENGTH) - return 0; - - switch (offset) { - case APIC_ARBPRI: - printk(KERN_WARNING "Access APIC ARBPRI register " - "which is for P6\n"); - break; - - case APIC_TMCCT: /* Timer CCR */ - val = apic_get_tmcct(apic); - break; - - default: - apic_update_ppr(apic); - val = apic_get_reg(apic, offset); - break; - } - - return val; -} - -static void apic_mmio_read(struct kvm_io_device *this, - gpa_t address, int len, void *data) -{ - struct kvm_lapic *apic = (struct kvm_lapic *)this->private; - unsigned int offset = address - apic->base_address; - unsigned char alignment = offset & 0xf; - u32 result; - - if ((alignment + len) > 4) { - printk(KERN_ERR "KVM_APIC_READ: alignment error %lx %d", - (unsigned long)address, len); - return; - } - result = __apic_read(apic, offset & ~0xf); - - switch (len) { - case 1: - case 2: - case 4: - memcpy(data, (char *)&result + alignment, len); - break; - default: - printk(KERN_ERR "Local APIC read with len = %x, " - "should be 1,2, or 4 instead\n", len); - break; - } -} - -static void update_divide_count(struct kvm_lapic *apic) -{ - u32 tmp1, tmp2, tdcr; - - tdcr = apic_get_reg(apic, APIC_TDCR); - tmp1 = tdcr & 0xf; - tmp2 = ((tmp1 & 0x3) | ((tmp1 & 0x8) >> 1)) + 1; - apic->timer.divide_count = 0x1 << (tmp2 & 0x7); - - apic_debug("timer divide count is 0x%x\n", - apic->timer.divide_count); -} - -static void start_apic_timer(struct kvm_lapic *apic) -{ - ktime_t now = apic->timer.dev.base->get_time(); - - apic->timer.last_update = now; - - apic->timer.period = apic_get_reg(apic, APIC_TMICT) * - APIC_BUS_CYCLE_NS * apic->timer.divide_count; - atomic_set(&apic->timer.pending, 0); - hrtimer_start(&apic->timer.dev, - ktime_add_ns(now, apic->timer.period), - HRTIMER_MODE_ABS); - - apic_debug("%s: bus cycle is %" PRId64 "ns, now 0x%016" - PRIx64 ", " - "timer initial count 0x%x, period %lldns, " - "expire @ 0x%016" PRIx64 ".\n", __FUNCTION__, - APIC_BUS_CYCLE_NS, ktime_to_ns(now), - apic_get_reg(apic, APIC_TMICT), - apic->timer.period, - ktime_to_ns(ktime_add_ns(now, - apic->timer.period))); -} - -static void apic_mmio_write(struct kvm_io_device *this, - gpa_t address, int len, const void *data) -{ - struct kvm_lapic *apic = (struct kvm_lapic *)this->private; - unsigned int offset = address - apic->base_address; - unsigned char alignment = offset & 0xf; - u32 val; - - /* - * APIC register must be aligned on 128-bits boundary. - * 32/64/128 bits registers must be accessed thru 32 bits. - * Refer SDM 8.4.1 - */ - if (len != 4 || alignment) { - if (printk_ratelimit()) - printk(KERN_ERR "apic write: bad size=%d %lx\n", - len, (long)address); - return; - } - - val = *(u32 *) data; - - /* too common printing */ - if (offset != APIC_EOI) - apic_debug("%s: offset 0x%x with length 0x%x, and value is " - "0x%x\n", __FUNCTION__, offset, len, val); - - offset &= 0xff0; - - switch (offset) { - case APIC_ID: /* Local APIC ID */ - apic_set_reg(apic, APIC_ID, val); - break; - - case APIC_TASKPRI: - apic_set_tpr(apic, val & 0xff); - break; - - case APIC_EOI: - apic_set_eoi(apic); - break; - - case APIC_LDR: - apic_set_reg(apic, APIC_LDR, val & APIC_LDR_MASK); - break; - - case APIC_DFR: - apic_set_reg(apic, APIC_DFR, val | 0x0FFFFFFF); - break; - - case APIC_SPIV: - apic_set_reg(apic, APIC_SPIV, val & 0x3ff); - if (!(val & APIC_SPIV_APIC_ENABLED)) { - int i; - u32 lvt_val; - - for (i = 0; i < APIC_LVT_NUM; i++) { - lvt_val = apic_get_reg(apic, - APIC_LVTT + 0x10 * i); - apic_set_reg(apic, APIC_LVTT + 0x10 * i, - lvt_val | APIC_LVT_MASKED); - } - atomic_set(&apic->timer.pending, 0); - - } - break; - - case APIC_ICR: - /* No delay here, so we always clear the pending bit */ - apic_set_reg(apic, APIC_ICR, val & ~(1 << 12)); - apic_send_ipi(apic); - break; - - case APIC_ICR2: - apic_set_reg(apic, APIC_ICR2, val & 0xff000000); - break; - - case APIC_LVTT: - case APIC_LVTTHMR: - case APIC_LVTPC: - case APIC_LVT0: - case APIC_LVT1: - case APIC_LVTERR: - /* TODO: Check vector */ - if (!apic_sw_enabled(apic)) - val |= APIC_LVT_MASKED; - - val &= apic_lvt_mask[(offset - APIC_LVTT) >> 4]; - apic_set_reg(apic, offset, val); - - break; - - case APIC_TMICT: - hrtimer_cancel(&apic->timer.dev); - apic_set_reg(apic, APIC_TMICT, val); - start_apic_timer(apic); - return; - - case APIC_TDCR: - if (val & 4) - printk(KERN_ERR "KVM_WRITE:TDCR %x\n", val); - apic_set_reg(apic, APIC_TDCR, val); - update_divide_count(apic); - break; - - default: - apic_debug("Local APIC Write to read-only register %x\n", - offset); - break; - } - -} - -static int apic_mmio_range(struct kvm_io_device *this, gpa_t addr) -{ - struct kvm_lapic *apic = (struct kvm_lapic *)this->private; - int ret = 0; - - - if (apic_hw_enabled(apic) && - (addr >= apic->base_address) && - (addr < (apic->base_address + LAPIC_MMIO_LENGTH))) - ret = 1; - - return ret; -} - -void kvm_free_apic(struct kvm_lapic *apic) -{ - if (!apic) - return; - - hrtimer_cancel(&apic->timer.dev); - - if (apic->regs_page) { - __free_page(apic->regs_page); - apic->regs_page = 0; - } - - kfree(apic); -} - -/* - *---------------------------------------------------------------------- - * LAPIC interface - *---------------------------------------------------------------------- - */ - -void kvm_lapic_set_tpr(struct kvm_vcpu *vcpu, unsigned long cr8) -{ - struct kvm_lapic *apic = (struct kvm_lapic *)vcpu->apic; - - if (!apic) - return; - apic_set_tpr(apic, ((cr8 & 0x0f) << 4)); -} - -u64 kvm_lapic_get_cr8(struct kvm_vcpu *vcpu) -{ - struct kvm_lapic *apic = (struct kvm_lapic *)vcpu->apic; - u64 tpr; - - if (!apic) - return 0; - tpr = (u64) apic_get_reg(apic, APIC_TASKPRI); - - return (tpr & 0xf0) >> 4; -} -EXPORT_SYMBOL_GPL(kvm_lapic_get_cr8); - -void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value) -{ - struct kvm_lapic *apic = (struct kvm_lapic *)vcpu->apic; - - if (!apic) { - value |= MSR_IA32_APICBASE_BSP; - vcpu->apic_base = value; - return; - } - if (apic->vcpu->vcpu_id) - value &= ~MSR_IA32_APICBASE_BSP; - - vcpu->apic_base = value; - apic->base_address = apic->vcpu->apic_base & - MSR_IA32_APICBASE_BASE; - - /* with FSB delivery interrupt, we can restart APIC functionality */ - apic_debug("apic base msr is 0x%016" PRIx64 ", and base address is " - "0x%lx.\n", apic->apic_base, apic->base_address); - -} - -u64 kvm_lapic_get_base(struct kvm_vcpu *vcpu) -{ - return vcpu->apic_base; -} -EXPORT_SYMBOL_GPL(kvm_lapic_get_base); - -void kvm_lapic_reset(struct kvm_vcpu *vcpu) -{ - struct kvm_lapic *apic; - int i; - - apic_debug("%s\n", __FUNCTION__); - - ASSERT(vcpu); - apic = vcpu->apic; - ASSERT(apic != NULL); - - /* Stop the timer in case it's a reset to an active apic */ - hrtimer_cancel(&apic->timer.dev); - - apic_set_reg(apic, APIC_ID, vcpu->vcpu_id << 24); - apic_set_reg(apic, APIC_LVR, APIC_VERSION); - - for (i = 0; i < APIC_LVT_NUM; i++) - apic_set_reg(apic, APIC_LVTT + 0x10 * i, APIC_LVT_MASKED); - apic_set_reg(apic, APIC_LVT0, - SET_APIC_DELIVERY_MODE(0, APIC_MODE_EXTINT)); - - apic_set_reg(apic, APIC_DFR, 0xffffffffU); - apic_set_reg(apic, APIC_SPIV, 0xff); - apic_set_reg(apic, APIC_TASKPRI, 0); - apic_set_reg(apic, APIC_LDR, 0); - apic_set_reg(apic, APIC_ESR, 0); - apic_set_reg(apic, APIC_ICR, 0); - apic_set_reg(apic, APIC_ICR2, 0); - apic_set_reg(apic, APIC_TDCR, 0); - apic_set_reg(apic, APIC_TMICT, 0); - for (i = 0; i < 8; i++) { - apic_set_reg(apic, APIC_IRR + 0x10 * i, 0); - apic_set_reg(apic, APIC_ISR + 0x10 * i, 0); - apic_set_reg(apic, APIC_TMR + 0x10 * i, 0); - } - update_divide_count(apic); - atomic_set(&apic->timer.pending, 0); - if (vcpu->vcpu_id == 0) - vcpu->apic_base |= MSR_IA32_APICBASE_BSP; - apic_update_ppr(apic); - - apic_debug(KERN_INFO "%s: vcpu=%p, id=%d, base_msr=" - "0x%016" PRIx64 ", base_address=0x%0lx.\n", __FUNCTION__, - vcpu, kvm_apic_id(apic), - vcpu->apic_base, apic->base_address); -} -EXPORT_SYMBOL_GPL(kvm_lapic_reset); - -int kvm_lapic_enabled(struct kvm_vcpu *vcpu) -{ - struct kvm_lapic *apic = (struct kvm_lapic *)vcpu->apic; - int ret = 0; - - if (!apic) - return 0; - ret = apic_enabled(apic); - - return ret; -} -EXPORT_SYMBOL_GPL(kvm_lapic_enabled); - -/* - *---------------------------------------------------------------------- - * timer interface - *---------------------------------------------------------------------- - */ - -/* TODO: make sure __apic_timer_fn runs in current pCPU */ -static int __apic_timer_fn(struct kvm_lapic *apic) -{ - int result = 0; - wait_queue_head_t *q = &apic->vcpu->wq; - - atomic_inc(&apic->timer.pending); - if (waitqueue_active(q)) - { - apic->vcpu->mp_state = VCPU_MP_STATE_RUNNABLE; - wake_up_interruptible(q); - } - if (apic_lvtt_period(apic)) { - result = 1; - apic->timer.dev.expires = ktime_add_ns( - apic->timer.dev.expires, - apic->timer.period); - } - return result; -} - -static int __inject_apic_timer_irq(struct kvm_lapic *apic) -{ - int vector; - - vector = apic_lvt_vector(apic, APIC_LVTT); - return __apic_accept_irq(apic, APIC_DM_FIXED, vector, 1, 0); -} - -static enum hrtimer_restart apic_timer_fn(struct hrtimer *data) -{ - struct kvm_lapic *apic; - int restart_timer = 0; - - apic = container_of(data, struct kvm_lapic, timer.dev); - - restart_timer = __apic_timer_fn(apic); - - if (restart_timer) - return HRTIMER_RESTART; - else - return HRTIMER_NORESTART; -} - -int kvm_create_lapic(struct kvm_vcpu *vcpu) -{ - struct kvm_lapic *apic; - - ASSERT(vcpu != NULL); - apic_debug("apic_init %d\n", vcpu->vcpu_id); - - apic = kzalloc(sizeof(*apic), GFP_KERNEL); - if (!apic) - goto nomem; - - vcpu->apic = apic; - - apic->regs_page = alloc_page(GFP_KERNEL); - if (apic->regs_page == NULL) { - printk(KERN_ERR "malloc apic regs error for vcpu %x\n", - vcpu->vcpu_id); - goto nomem; - } - apic->regs = page_address(apic->regs_page); - memset(apic->regs, 0, PAGE_SIZE); - apic->vcpu = vcpu; - - hrtimer_init(&apic->timer.dev, CLOCK_MONOTONIC, HRTIMER_MODE_ABS); - apic->timer.dev.function = apic_timer_fn; - apic->base_address = APIC_DEFAULT_PHYS_BASE; - vcpu->apic_base = APIC_DEFAULT_PHYS_BASE; - - kvm_lapic_reset(vcpu); - apic->dev.read = apic_mmio_read; - apic->dev.write = apic_mmio_write; - apic->dev.in_range = apic_mmio_range; - apic->dev.private = apic; - - return 0; -nomem: - kvm_free_apic(apic); - return -ENOMEM; -} -EXPORT_SYMBOL_GPL(kvm_create_lapic); - -int kvm_apic_has_interrupt(struct kvm_vcpu *vcpu) -{ - struct kvm_lapic *apic = vcpu->apic; - int highest_irr; - - if (!apic || !apic_enabled(apic)) - return -1; - - apic_update_ppr(apic); - highest_irr = apic_find_highest_irr(apic); - if ((highest_irr == -1) || - ((highest_irr & 0xF0) <= apic_get_reg(apic, APIC_PROCPRI))) - return -1; - return highest_irr; -} - -int kvm_apic_accept_pic_intr(struct kvm_vcpu *vcpu) -{ - u32 lvt0 = apic_get_reg(vcpu->apic, APIC_LVT0); - int r = 0; - - if (vcpu->vcpu_id == 0) { - if (!apic_hw_enabled(vcpu->apic)) - r = 1; - if ((lvt0 & APIC_LVT_MASKED) == 0 && - GET_APIC_DELIVERY_MODE(lvt0) == APIC_MODE_EXTINT) - r = 1; - } - return r; -} - -void kvm_inject_apic_timer_irqs(struct kvm_vcpu *vcpu) -{ - struct kvm_lapic *apic = vcpu->apic; - - if (apic && apic_lvt_enabled(apic, APIC_LVTT) && - atomic_read(&apic->timer.pending) > 0) { - if (__inject_apic_timer_irq(apic)) - atomic_dec(&apic->timer.pending); - } -} - -void kvm_apic_timer_intr_post(struct kvm_vcpu *vcpu, int vec) -{ - struct kvm_lapic *apic = vcpu->apic; - - if (apic && apic_lvt_vector(apic, APIC_LVTT) == vec) - apic->timer.last_update = ktime_add_ns( - apic->timer.last_update, - apic->timer.period); -} - -int kvm_get_apic_interrupt(struct kvm_vcpu *vcpu) -{ - int vector = kvm_apic_has_interrupt(vcpu); - struct kvm_lapic *apic = vcpu->apic; - - if (vector == -1) - return -1; - - apic_set_vector(vector, apic->regs + APIC_ISR); - apic_update_ppr(apic); - apic_clear_irr(vector, apic); - return vector; -} - -void kvm_apic_post_state_restore(struct kvm_vcpu *vcpu) -{ - struct kvm_lapic *apic = vcpu->apic; - - apic->base_address = vcpu->apic_base & - MSR_IA32_APICBASE_BASE; - apic_set_reg(apic, APIC_LVR, APIC_VERSION); - apic_update_ppr(apic); - hrtimer_cancel(&apic->timer.dev); - update_divide_count(apic); - start_apic_timer(apic); -} - -void kvm_migrate_apic_timer(struct kvm_vcpu *vcpu) -{ - struct kvm_lapic *apic = vcpu->apic; - struct hrtimer *timer; - - if (!apic) - return; - - timer = &apic->timer.dev; - if (hrtimer_cancel(timer)) - hrtimer_start(timer, timer->expires, HRTIMER_MODE_ABS); -} -EXPORT_SYMBOL_GPL(kvm_migrate_apic_timer); diff --git a/drivers/kvm/mmu.c b/drivers/kvm/mmu.c deleted file mode 100644 index feb5ac986c5d..000000000000 --- a/drivers/kvm/mmu.c +++ /dev/null @@ -1,1498 +0,0 @@ -/* - * Kernel-based Virtual Machine driver for Linux - * - * This module enables machines with Intel VT-x extensions to run virtual - * machines without emulation or binary translation. - * - * MMU support - * - * Copyright (C) 2006 Qumranet, Inc. - * - * Authors: - * Yaniv Kamay <yaniv@qumranet.com> - * Avi Kivity <avi@qumranet.com> - * - * This work is licensed under the terms of the GNU GPL, version 2. See - * the COPYING file in the top-level directory. - * - */ - -#include "vmx.h" -#include "kvm.h" - -#include <linux/types.h> -#include <linux/string.h> -#include <linux/mm.h> -#include <linux/highmem.h> -#include <linux/module.h> - -#include <asm/page.h> -#include <asm/cmpxchg.h> - -#undef MMU_DEBUG - -#undef AUDIT - -#ifdef AUDIT -static void kvm_mmu_audit(struct kvm_vcpu *vcpu, const char *msg); -#else -static void kvm_mmu_audit(struct kvm_vcpu *vcpu, const char *msg) {} -#endif - -#ifdef MMU_DEBUG - -#define pgprintk(x...) do { if (dbg) printk(x); } while (0) -#define rmap_printk(x...) do { if (dbg) printk(x); } while (0) - -#else - -#define pgprintk(x...) do { } while (0) -#define rmap_printk(x...) do { } while (0) - -#endif - -#if defined(MMU_DEBUG) || defined(AUDIT) -static int dbg = 1; -#endif - -#ifndef MMU_DEBUG -#define ASSERT(x) do { } while (0) -#else -#define ASSERT(x) \ - if (!(x)) { \ - printk(KERN_WARNING "assertion failed %s:%d: %s\n", \ - __FILE__, __LINE__, #x); \ - } -#endif - -#define PT64_PT_BITS 9 -#define PT64_ENT_PER_PAGE (1 << PT64_PT_BITS) -#define PT32_PT_BITS 10 -#define PT32_ENT_PER_PAGE (1 << PT32_PT_BITS) - -#define PT_WRITABLE_SHIFT 1 - -#define PT_PRESENT_MASK (1ULL << 0) -#define PT_WRITABLE_MASK (1ULL << PT_WRITABLE_SHIFT) -#define PT_USER_MASK (1ULL << 2) -#define PT_PWT_MASK (1ULL << 3) -#define PT_PCD_MASK (1ULL << 4) -#define PT_ACCESSED_MASK (1ULL << 5) -#define PT_DIRTY_MASK (1ULL << 6) -#define PT_PAGE_SIZE_MASK (1ULL << 7) -#define PT_PAT_MASK (1ULL << 7) -#define PT_GLOBAL_MASK (1ULL << 8) -#define PT64_NX_MASK (1ULL << 63) - -#define PT_PAT_SHIFT 7 -#define PT_DIR_PAT_SHIFT 12 -#define PT_DIR_PAT_MASK (1ULL << PT_DIR_PAT_SHIFT) - -#define PT32_DIR_PSE36_SIZE 4 -#define PT32_DIR_PSE36_SHIFT 13 -#define PT32_DIR_PSE36_MASK (((1ULL << PT32_DIR_PSE36_SIZE) - 1) << PT32_DIR_PSE36_SHIFT) - - -#define PT_FIRST_AVAIL_BITS_SHIFT 9 -#define PT64_SECOND_AVAIL_BITS_SHIFT 52 - -#define PT_SHADOW_IO_MARK (1ULL << PT_FIRST_AVAIL_BITS_SHIFT) - -#define VALID_PAGE(x) ((x) != INVALID_PAGE) - -#define PT64_LEVEL_BITS 9 - -#define PT64_LEVEL_SHIFT(level) \ - ( PAGE_SHIFT + (level - 1) * PT64_LEVEL_BITS ) - -#define PT64_LEVEL_MASK(level) \ - (((1ULL << PT64_LEVEL_BITS) - 1) << PT64_LEVEL_SHIFT(level)) - -#define PT64_INDEX(address, level)\ - (((address) >> PT64_LEVEL_SHIFT(level)) & ((1 << PT64_LEVEL_BITS) - 1)) - - -#define PT32_LEVEL_BITS 10 - -#define PT32_LEVEL_SHIFT(level) \ - ( PAGE_SHIFT + (level - 1) * PT32_LEVEL_BITS ) - -#define PT32_LEVEL_MASK(level) \ - (((1ULL << PT32_LEVEL_BITS) - 1) << PT32_LEVEL_SHIFT(level)) - -#define PT32_INDEX(address, level)\ - (((address) >> PT32_LEVEL_SHIFT(level)) & ((1 << PT32_LEVEL_BITS) - 1)) - - -#define PT64_BASE_ADDR_MASK (((1ULL << 52) - 1) & ~(u64)(PAGE_SIZE-1)) -#define PT64_DIR_BASE_ADDR_MASK \ - (PT64_BASE_ADDR_MASK & ~((1ULL << (PAGE_SHIFT + PT64_LEVEL_BITS)) - 1)) - -#define PT32_BASE_ADDR_MASK PAGE_MASK -#define PT32_DIR_BASE_ADDR_MASK \ - (PAGE_MASK & ~((1ULL << (PAGE_SHIFT + PT32_LEVEL_BITS)) - 1)) - - -#define PFERR_PRESENT_MASK (1U << 0) -#define PFERR_WRITE_MASK (1U << 1) -#define PFERR_USER_MASK (1U << 2) -#define PFERR_FETCH_MASK (1U << 4) - -#define PT64_ROOT_LEVEL 4 -#define PT32_ROOT_LEVEL 2 -#define PT32E_ROOT_LEVEL 3 - -#define PT_DIRECTORY_LEVEL 2 -#define PT_PAGE_TABLE_LEVEL 1 - -#define RMAP_EXT 4 - -struct kvm_rmap_desc { - u64 *shadow_ptes[RMAP_EXT]; - struct kvm_rmap_desc *more; -}; - -static struct kmem_cache *pte_chain_cache; -static struct kmem_cache *rmap_desc_cache; -static struct kmem_cache *mmu_page_header_cache; - -static int is_write_protection(struct kvm_vcpu *vcpu) -{ - return vcpu->cr0 & X86_CR0_WP; -} - -static int is_cpuid_PSE36(void) -{ - return 1; -} - -static int is_nx(struct kvm_vcpu *vcpu) -{ - return vcpu->shadow_efer & EFER_NX; -} - -static int is_present_pte(unsigned long pte) -{ - return pte & PT_PRESENT_MASK; -} - -static int is_writeble_pte(unsigned long pte) -{ - return pte & PT_WRITABLE_MASK; -} - -static int is_io_pte(unsigned long pte) -{ - return pte & PT_SHADOW_IO_MARK; -} - -static int is_rmap_pte(u64 pte) -{ - return (pte & (PT_WRITABLE_MASK | PT_PRESENT_MASK)) - == (PT_WRITABLE_MASK | PT_PRESENT_MASK); -} - -static void set_shadow_pte(u64 *sptep, u64 spte) -{ -#ifdef CONFIG_X86_64 - set_64bit((unsigned long *)sptep, spte); -#else - set_64bit((unsigned long long *)sptep, spte); -#endif -} - -static int mmu_topup_memory_cache(struct kvm_mmu_memory_cache *cache, - struct kmem_cache *base_cache, int min) -{ - void *obj; - - if (cache->nobjs >= min) - return 0; - while (cache->nobjs < ARRAY_SIZE(cache->objects)) { - obj = kmem_cache_zalloc(base_cache, GFP_KERNEL); - if (!obj) - return -ENOMEM; - cache->objects[cache->nobjs++] = obj; - } - return 0; -} - -static void mmu_free_memory_cache(struct kvm_mmu_memory_cache *mc) -{ - while (mc->nobjs) - kfree(mc->objects[--mc->nobjs]); -} - -static int mmu_topup_memory_cache_page(struct kvm_mmu_memory_cache *cache, - int min) -{ - struct page *page; - - if (cache->nobjs >= min) - return 0; - while (cache->nobjs < ARRAY_SIZE(cache->objects)) { - page = alloc_page(GFP_KERNEL); - if (!page) - return -ENOMEM; - set_page_private(page, 0); - cache->objects[cache->nobjs++] = page_address(page); - } - return 0; -} - -static void mmu_free_memory_cache_page(struct kvm_mmu_memory_cache *mc) -{ - while (mc->nobjs) - free_page((unsigned long)mc->objects[--mc->nobjs]); -} - -static int mmu_topup_memory_caches(struct kvm_vcpu *vcpu) -{ - int r; - - kvm_mmu_free_some_pages(vcpu); - r = mmu_topup_memory_cache(&vcpu->mmu_pte_chain_cache, - pte_chain_cache, 4); - if (r) - goto out; - r = mmu_topup_memory_cache(&vcpu->mmu_rmap_desc_cache, - rmap_desc_cache, 1); - if (r) - goto out; - r = mmu_topup_memory_cache_page(&vcpu->mmu_page_cache, 4); - if (r) - goto out; - r = mmu_topup_memory_cache(&vcpu->mmu_page_header_cache, - mmu_page_header_cache, 4); -out: - return r; -} - -static void mmu_free_memory_caches(struct kvm_vcpu *vcpu) -{ - mmu_free_memory_cache(&vcpu->mmu_pte_chain_cache); - mmu_free_memory_cache(&vcpu->mmu_rmap_desc_cache); - mmu_free_memory_cache_page(&vcpu->mmu_page_cache); - mmu_free_memory_cache(&vcpu->mmu_page_header_cache); -} - -static void *mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc, - size_t size) -{ - void *p; - - BUG_ON(!mc->nobjs); - p = mc->objects[--mc->nobjs]; - memset(p, 0, size); - return p; -} - -static struct kvm_pte_chain *mmu_alloc_pte_chain(struct kvm_vcpu *vcpu) -{ - return mmu_memory_cache_alloc(&vcpu->mmu_pte_chain_cache, - sizeof(struct kvm_pte_chain)); -} - -static void mmu_free_pte_chain(struct kvm_pte_chain *pc) -{ - kfree(pc); -} - -static struct kvm_rmap_desc *mmu_alloc_rmap_desc(struct kvm_vcpu *vcpu) -{ - return mmu_memory_cache_alloc(&vcpu->mmu_rmap_desc_cache, - sizeof(struct kvm_rmap_desc)); -} - -static void mmu_free_rmap_desc(struct kvm_rmap_desc *rd) -{ - kfree(rd); -} - -/* - * Reverse mapping data structures: - * - * If page->private bit zero is zero, then page->private points to the - * shadow page table entry that points to page_address(page). - * - * If page->private bit zero is one, (then page->private & ~1) points - * to a struct kvm_rmap_desc containing more mappings. - */ -static void rmap_add(struct kvm_vcpu *vcpu, u64 *spte) -{ - struct page *page; - struct kvm_rmap_desc *desc; - int i; - - if (!is_rmap_pte(*spte)) - return; - page = pfn_to_page((*spte & PT64_BASE_ADDR_MASK) >> PAGE_SHIFT); - if (!page_private(page)) { - rmap_printk("rmap_add: %p %llx 0->1\n", spte, *spte); - set_page_private(page,(unsigned long)spte); - } else if (!(page_private(page) & 1)) { - rmap_printk("rmap_add: %p %llx 1->many\n", spte, *spte); - desc = mmu_alloc_rmap_desc(vcpu); - desc->shadow_ptes[0] = (u64 *)page_private(page); - desc->shadow_ptes[1] = spte; - set_page_private(page,(unsigned long)desc | 1); - } else { - rmap_printk("rmap_add: %p %llx many->many\n", spte, *spte); - desc = (struct kvm_rmap_desc *)(page_private(page) & ~1ul); - while (desc->shadow_ptes[RMAP_EXT-1] && desc->more) - desc = desc->more; - if (desc->shadow_ptes[RMAP_EXT-1]) { - desc->more = mmu_alloc_rmap_desc(vcpu); - desc = desc->more; - } - for (i = 0; desc->shadow_ptes[i]; ++i) - ; - desc->shadow_ptes[i] = spte; - } -} - -static void rmap_desc_remove_entry(struct page *page, - struct kvm_rmap_desc *desc, - int i, - struct kvm_rmap_desc *prev_desc) -{ - int j; - - for (j = RMAP_EXT - 1; !desc->shadow_ptes[j] && j > i; --j) - ; - desc->shadow_ptes[i] = desc->shadow_ptes[j]; - desc->shadow_ptes[j] = NULL; - if (j != 0) - return; - if (!prev_desc && !desc->more) - set_page_private(page,(unsigned long)desc->shadow_ptes[0]); - else - if (prev_desc) - prev_desc->more = desc->more; - else - set_page_private(page,(unsigned long)desc->more | 1); - mmu_free_rmap_desc(desc); -} - -static void rmap_remove(u64 *spte) -{ - struct page *page; - struct kvm_rmap_desc *desc; - struct kvm_rmap_desc *prev_desc; - int i; - - if (!is_rmap_pte(*spte)) - return; - page = pfn_to_page((*spte & PT64_BASE_ADDR_MASK) >> PAGE_SHIFT); - if (!page_private(page)) { - printk(KERN_ERR "rmap_remove: %p %llx 0->BUG\n", spte, *spte); - BUG(); - } else if (!(page_private(page) & 1)) { - rmap_printk("rmap_remove: %p %llx 1->0\n", spte, *spte); - if ((u64 *)page_private(page) != spte) { - printk(KERN_ERR "rmap_remove: %p %llx 1->BUG\n", - spte, *spte); - BUG(); - } - set_page_private(page,0); - } else { - rmap_printk("rmap_remove: %p %llx many->many\n", spte, *spte); - desc = (struct kvm_rmap_desc *)(page_private(page) & ~1ul); - prev_desc = NULL; - while (desc) { - for (i = 0; i < RMAP_EXT && desc->shadow_ptes[i]; ++i) - if (desc->shadow_ptes[i] == spte) { - rmap_desc_remove_entry(page, - desc, i, - prev_desc); - return; - } - prev_desc = desc; - desc = desc->more; - } - BUG(); - } -} - -static void rmap_write_protect(struct kvm_vcpu *vcpu, u64 gfn) -{ - struct kvm *kvm = vcpu->kvm; - struct page *page; - struct kvm_rmap_desc *desc; - u64 *spte; - - page = gfn_to_page(kvm, gfn); - BUG_ON(!page); - - while (page_private(page)) { - if (!(page_private(page) & 1)) - spte = (u64 *)page_private(page); - else { - desc = (struct kvm_rmap_desc *)(page_private(page) & ~1ul); - spte = desc->shadow_ptes[0]; - } - BUG_ON(!spte); - BUG_ON((*spte & PT64_BASE_ADDR_MASK) >> PAGE_SHIFT - != page_to_pfn(page)); - BUG_ON(!(*spte & PT_PRESENT_MASK)); - BUG_ON(!(*spte & PT_WRITABLE_MASK)); - rmap_printk("rmap_write_protect: spte %p %llx\n", spte, *spte); - rmap_remove(spte); - set_shadow_pte(spte, *spte & ~PT_WRITABLE_MASK); - kvm_flush_remote_tlbs(vcpu->kvm); - } -} - -#ifdef MMU_DEBUG -static int is_empty_shadow_page(u64 *spt) -{ - u64 *pos; - u64 *end; - - for (pos = spt, end = pos + PAGE_SIZE / sizeof(u64); pos != end; pos++) - if (*pos != 0) { - printk(KERN_ERR "%s: %p %llx\n", __FUNCTION__, - pos, *pos); - return 0; - } - return 1; -} -#endif - -static void kvm_mmu_free_page(struct kvm *kvm, - struct kvm_mmu_page *page_head) -{ - ASSERT(is_empty_shadow_page(page_head->spt)); - list_del(&page_head->link); - __free_page(virt_to_page(page_head->spt)); - kfree(page_head); - ++kvm->n_free_mmu_pages; -} - -static unsigned kvm_page_table_hashfn(gfn_t gfn) -{ - return gfn; -} - -static struct kvm_mmu_page *kvm_mmu_alloc_page(struct kvm_vcpu *vcpu, - u64 *parent_pte) -{ - struct kvm_mmu_page *page; - - if (!vcpu->kvm->n_free_mmu_pages) - return NULL; - - page = mmu_memory_cache_alloc(&vcpu->mmu_page_header_cache, - sizeof *page); - page->spt = mmu_memory_cache_alloc(&vcpu->mmu_page_cache, PAGE_SIZE); - set_page_private(virt_to_page(page->spt), (unsigned long)page); - list_add(&page->link, &vcpu->kvm->active_mmu_pages); - ASSERT(is_empty_shadow_page(page->spt)); - page->slot_bitmap = 0; - page->multimapped = 0; - page->parent_pte = parent_pte; - --vcpu->kvm->n_free_mmu_pages; - return page; -} - -static void mmu_page_add_parent_pte(struct kvm_vcpu *vcpu, - struct kvm_mmu_page *page, u64 *parent_pte) -{ - struct kvm_pte_chain *pte_chain; - struct hlist_node *node; - int i; - - if (!parent_pte) - return; - if (!page->multimapped) { - u64 *old = page->parent_pte; - - if (!old) { - page->parent_pte = parent_pte; - return; - } - page->multimapped = 1; - pte_chain = mmu_alloc_pte_chain(vcpu); - INIT_HLIST_HEAD(&page->parent_ptes); - hlist_add_head(&pte_chain->link, &page->parent_ptes); - pte_chain->parent_ptes[0] = old; - } - hlist_for_each_entry(pte_chain, node, &page->parent_ptes, link) { - if (pte_chain->parent_ptes[NR_PTE_CHAIN_ENTRIES-1]) - continue; - for (i = 0; i < NR_PTE_CHAIN_ENTRIES; ++i) - if (!pte_chain->parent_ptes[i]) { - pte_chain->parent_ptes[i] = parent_pte; - return; - } - } - pte_chain = mmu_alloc_pte_chain(vcpu); - BUG_ON(!pte_chain); - hlist_add_head(&pte_chain->link, &page->parent_ptes); - pte_chain->parent_ptes[0] = parent_pte; -} - -static void mmu_page_remove_parent_pte(struct kvm_mmu_page *page, - u64 *parent_pte) -{ - struct kvm_pte_chain *pte_chain; - struct hlist_node *node; - int i; - - if (!page->multimapped) { - BUG_ON(page->parent_pte != parent_pte); - page->parent_pte = NULL; - return; - } - hlist_for_each_entry(pte_chain, node, &page->parent_ptes, link) - for (i = 0; i < NR_PTE_CHAIN_ENTRIES; ++i) { - if (!pte_chain->parent_ptes[i]) - break; - if (pte_chain->parent_ptes[i] != parent_pte) - continue; - while (i + 1 < NR_PTE_CHAIN_ENTRIES - && pte_chain->parent_ptes[i + 1]) { - pte_chain->parent_ptes[i] - = pte_chain->parent_ptes[i + 1]; - ++i; - } - pte_chain->parent_ptes[i] = NULL; - if (i == 0) { - hlist_del(&pte_chain->link); - mmu_free_pte_chain(pte_chain); - if (hlist_empty(&page->parent_ptes)) { - page->multimapped = 0; - page->parent_pte = NULL; - } - } - return; - } - BUG(); -} - -static struct kvm_mmu_page *kvm_mmu_lookup_page(struct kvm_vcpu *vcpu, - gfn_t gfn) -{ - unsigned index; - struct hlist_head *bucket; - struct kvm_mmu_page *page; - struct hlist_node *node; - - pgprintk("%s: looking for gfn %lx\n", __FUNCTION__, gfn); - index = kvm_page_table_hashfn(gfn) % KVM_NUM_MMU_PAGES; - bucket = &vcpu->kvm->mmu_page_hash[index]; - hlist_for_each_entry(page, node, bucket, hash_link) - if (page->gfn == gfn && !page->role.metaphysical) { - pgprintk("%s: found role %x\n", - __FUNCTION__, page->role.word); - return page; - } - return NULL; -} - -static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu, - gfn_t gfn, - gva_t gaddr, - unsigned level, - int metaphysical, - unsigned hugepage_access, - u64 *parent_pte) -{ - union kvm_mmu_page_role role; - unsigned index; - unsigned quadrant; - struct hlist_head *bucket; - struct kvm_mmu_page *page; - struct hlist_node *node; - - role.word = 0; - role.glevels = vcpu->mmu.root_level; - role.level = level; - role.metaphysical = metaphysical; - role.hugepage_access = hugepage_access; - if (vcpu->mmu.root_level <= PT32_ROOT_LEVEL) { - quadrant = gaddr >> (PAGE_SHIFT + (PT64_PT_BITS * level)); - quadrant &= (1 << ((PT32_PT_BITS - PT64_PT_BITS) * level)) - 1; - role.quadrant = quadrant; - } - pgprintk("%s: looking gfn %lx role %x\n", __FUNCTION__, - gfn, role.word); - index = kvm_page_table_hashfn(gfn) % KVM_NUM_MMU_PAGES; - bucket = &vcpu->kvm->mmu_page_hash[index]; - hlist_for_each_entry(page, node, bucket, hash_link) - if (page->gfn == gfn && page->role.word == role.word) { - mmu_page_add_parent_pte(vcpu, page, parent_pte); - pgprintk("%s: found\n", __FUNCTION__); - return page; - } - page = kvm_mmu_alloc_page(vcpu, parent_pte); - if (!page) - return page; - pgprintk("%s: adding gfn %lx role %x\n", __FUNCTION__, gfn, role.word); - page->gfn = gfn; - page->role = role; - hlist_add_head(&page->hash_link, bucket); - if (!metaphysical) - rmap_write_protect(vcpu, gfn); - return page; -} - -static void kvm_mmu_page_unlink_children(struct kvm *kvm, - struct kvm_mmu_page *page) -{ - unsigned i; - u64 *pt; - u64 ent; - - pt = page->spt; - - if (page->role.level == PT_PAGE_TABLE_LEVEL) { - for (i = 0; i < PT64_ENT_PER_PAGE; ++i) { - if (pt[i] & PT_PRESENT_MASK) - rmap_remove(&pt[i]); - pt[i] = 0; - } - kvm_flush_remote_tlbs(kvm); - return; - } - - for (i = 0; i < PT64_ENT_PER_PAGE; ++i) { - ent = pt[i]; - - pt[i] = 0; - if (!(ent & PT_PRESENT_MASK)) - continue; - ent &= PT64_BASE_ADDR_MASK; - mmu_page_remove_parent_pte(page_header(ent), &pt[i]); - } - kvm_flush_remote_tlbs(kvm); -} - -static void kvm_mmu_put_page(struct kvm_mmu_page *page, - u64 *parent_pte) -{ - mmu_page_remove_parent_pte(page, parent_pte); -} - -static void kvm_mmu_zap_page(struct kvm *kvm, - struct kvm_mmu_page *page) -{ - u64 *parent_pte; - - while (page->multimapped || page->parent_pte) { - if (!page->multimapped) - parent_pte = page->parent_pte; - else { - struct kvm_pte_chain *chain; - - chain = container_of(page->parent_ptes.first, - struct kvm_pte_chain, link); - parent_pte = chain->parent_ptes[0]; - } - BUG_ON(!parent_pte); - kvm_mmu_put_page(page, parent_pte); - set_shadow_pte(parent_pte, 0); - } - kvm_mmu_page_unlink_children(kvm, page); - if (!page->root_count) { - hlist_del(&page->hash_link); - kvm_mmu_free_page(kvm, page); - } else - list_move(&page->link, &kvm->active_mmu_pages); -} - -static int kvm_mmu_unprotect_page(struct kvm_vcpu *vcpu, gfn_t gfn) -{ - unsigned index; - struct hlist_head *bucket; - struct kvm_mmu_page *page; - struct hlist_node *node, *n; - int r; - - pgprintk("%s: looking for gfn %lx\n", __FUNCTION__, gfn); - r = 0; - index = kvm_page_table_hashfn(gfn) % KVM_NUM_MMU_PAGES; - bucket = &vcpu->kvm->mmu_page_hash[index]; - hlist_for_each_entry_safe(page, node, n, bucket, hash_link) - if (page->gfn == gfn && !page->role.metaphysical) { - pgprintk("%s: gfn %lx role %x\n", __FUNCTION__, gfn, - page->role.word); - kvm_mmu_zap_page(vcpu->kvm, page); - r = 1; - } - return r; -} - -static void mmu_unshadow(struct kvm_vcpu *vcpu, gfn_t gfn) -{ - struct kvm_mmu_page *page; - - while ((page = kvm_mmu_lookup_page(vcpu, gfn)) != NULL) { - pgprintk("%s: zap %lx %x\n", - __FUNCTION__, gfn, page->role.word); - kvm_mmu_zap_page(vcpu->kvm, page); - } -} - -static void page_header_update_slot(struct kvm *kvm, void *pte, gpa_t gpa) -{ - int slot = memslot_id(kvm, gfn_to_memslot(kvm, gpa >> PAGE_SHIFT)); - struct kvm_mmu_page *page_head = page_header(__pa(pte)); - - __set_bit(slot, &page_head->slot_bitmap); -} - -hpa_t safe_gpa_to_hpa(struct kvm_vcpu *vcpu, gpa_t gpa) -{ - hpa_t hpa = gpa_to_hpa(vcpu, gpa); - - return is_error_hpa(hpa) ? bad_page_address | (gpa & ~PAGE_MASK): hpa; -} - -hpa_t gpa_to_hpa(struct kvm_vcpu *vcpu, gpa_t gpa) -{ - struct page *page; - - ASSERT((gpa & HPA_ERR_MASK) == 0); - page = gfn_to_page(vcpu->kvm, gpa >> PAGE_SHIFT); - if (!page) - return gpa | HPA_ERR_MASK; - return ((hpa_t)page_to_pfn(page) << PAGE_SHIFT) - | (gpa & (PAGE_SIZE-1)); -} - -hpa_t gva_to_hpa(struct kvm_vcpu *vcpu, gva_t gva) -{ - gpa_t gpa = vcpu->mmu.gva_to_gpa(vcpu, gva); - - if (gpa == UNMAPPED_GVA) - return UNMAPPED_GVA; - return gpa_to_hpa(vcpu, gpa); -} - -struct page *gva_to_page(struct kvm_vcpu *vcpu, gva_t gva) -{ - gpa_t gpa = vcpu->mmu.gva_to_gpa(vcpu, gva); - - if (gpa == UNMAPPED_GVA) - return NULL; - return pfn_to_page(gpa_to_hpa(vcpu, gpa) >> PAGE_SHIFT); -} - -static void nonpaging_new_cr3(struct kvm_vcpu *vcpu) -{ -} - -static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, hpa_t p) -{ - int level = PT32E_ROOT_LEVEL; - hpa_t table_addr = vcpu->mmu.root_hpa; - - for (; ; level--) { - u32 index = PT64_INDEX(v, level); - u64 *table; - u64 pte; - - ASSERT(VALID_PAGE(table_addr)); - table = __va(table_addr); - - if (level == 1) { - pte = table[index]; - if (is_present_pte(pte) && is_writeble_pte(pte)) - return 0; - mark_page_dirty(vcpu->kvm, v >> PAGE_SHIFT); - page_header_update_slot(vcpu->kvm, table, v); - table[index] = p | PT_PRESENT_MASK | PT_WRITABLE_MASK | - PT_USER_MASK; - rmap_add(vcpu, &table[index]); - return 0; - } - - if (table[index] == 0) { - struct kvm_mmu_page *new_table; - gfn_t pseudo_gfn; - - pseudo_gfn = (v & PT64_DIR_BASE_ADDR_MASK) - >> PAGE_SHIFT; - new_table = kvm_mmu_get_page(vcpu, pseudo_gfn, - v, level - 1, - 1, 0, &table[index]); - if (!new_table) { - pgprintk("nonpaging_map: ENOMEM\n"); - return -ENOMEM; - } - - table[index] = __pa(new_table->spt) | PT_PRESENT_MASK - | PT_WRITABLE_MASK | PT_USER_MASK; - } - table_addr = table[index] & PT64_BASE_ADDR_MASK; - } -} - -static void mmu_free_roots(struct kvm_vcpu *vcpu) -{ - int i; - struct kvm_mmu_page *page; - - if (!VALID_PAGE(vcpu->mmu.root_hpa)) - return; -#ifdef CONFIG_X86_64 - if (vcpu->mmu.shadow_root_level == PT64_ROOT_LEVEL) { - hpa_t root = vcpu->mmu.root_hpa; - - page = page_header(root); - --page->root_count; - vcpu->mmu.root_hpa = INVALID_PAGE; - return; - } -#endif - for (i = 0; i < 4; ++i) { - hpa_t root = vcpu->mmu.pae_root[i]; - - if (root) { - root &= PT64_BASE_ADDR_MASK; - page = page_header(root); - --page->root_count; - } - vcpu->mmu.pae_root[i] = INVALID_PAGE; - } - vcpu->mmu.root_hpa = INVALID_PAGE; -} - -static void mmu_alloc_roots(struct kvm_vcpu *vcpu) -{ - int i; - gfn_t root_gfn; - struct kvm_mmu_page *page; - - root_gfn = vcpu->cr3 >> PAGE_SHIFT; - -#ifdef CONFIG_X86_64 - if (vcpu->mmu.shadow_root_level == PT64_ROOT_LEVEL) { - hpa_t root = vcpu->mmu.root_hpa; - - ASSERT(!VALID_PAGE(root)); - page = kvm_mmu_get_page(vcpu, root_gfn, 0, - PT64_ROOT_LEVEL, 0, 0, NULL); - root = __pa(page->spt); - ++page->root_count; - vcpu->mmu.root_hpa = root; - return; - } -#endif - for (i = 0; i < 4; ++i) { - hpa_t root = vcpu->mmu.pae_root[i]; - - ASSERT(!VALID_PAGE(root)); - if (vcpu->mmu.root_level == PT32E_ROOT_LEVEL) { - if (!is_present_pte(vcpu->pdptrs[i])) { - vcpu->mmu.pae_root[i] = 0; - continue; - } - root_gfn = vcpu->pdptrs[i] >> PAGE_SHIFT; - } else if (vcpu->mmu.root_level == 0) - root_gfn = 0; - page = kvm_mmu_get_page(vcpu, root_gfn, i << 30, - PT32_ROOT_LEVEL, !is_paging(vcpu), - 0, NULL); - root = __pa(page->spt); - ++page->root_count; - vcpu->mmu.pae_root[i] = root | PT_PRESENT_MASK; - } - vcpu->mmu.root_hpa = __pa(vcpu->mmu.pae_root); -} - -static gpa_t nonpaging_gva_to_gpa(struct kvm_vcpu *vcpu, gva_t vaddr) -{ - return vaddr; -} - -static int nonpaging_page_fault(struct kvm_vcpu *vcpu, gva_t gva, - u32 error_code) -{ - gpa_t addr = gva; - hpa_t paddr; - int r; - - r = mmu_topup_memory_caches(vcpu); - if (r) - return r; - - ASSERT(vcpu); - ASSERT(VALID_PAGE(vcpu->mmu.root_hpa)); - - - paddr = gpa_to_hpa(vcpu , addr & PT64_BASE_ADDR_MASK); - - if (is_error_hpa(paddr)) - return 1; - - return nonpaging_map(vcpu, addr & PAGE_MASK, paddr); -} - -static void nonpaging_free(struct kvm_vcpu *vcpu) -{ - mmu_free_roots(vcpu); -} - -static int nonpaging_init_context(struct kvm_vcpu *vcpu) -{ - struct kvm_mmu *context = &vcpu->mmu; - - context->new_cr3 = nonpaging_new_cr3; - context->page_fault = nonpaging_page_fault; - context->gva_to_gpa = nonpaging_gva_to_gpa; - context->free = nonpaging_free; - context->root_level = 0; - context->shadow_root_level = PT32E_ROOT_LEVEL; - context->root_hpa = INVALID_PAGE; - return 0; -} - -static void kvm_mmu_flush_tlb(struct kvm_vcpu *vcpu) -{ - ++vcpu->stat.tlb_flush; - kvm_x86_ops->tlb_flush(vcpu); -} - -static void paging_new_cr3(struct kvm_vcpu *vcpu) -{ - pgprintk("%s: cr3 %lx\n", __FUNCTION__, vcpu->cr3); - mmu_free_roots(vcpu); -} - -static void inject_page_fault(struct kvm_vcpu *vcpu, - u64 addr, - u32 err_code) -{ - kvm_x86_ops->inject_page_fault(vcpu, addr, err_code); -} - -static void paging_free(struct kvm_vcpu *vcpu) -{ - nonpaging_free(vcpu); -} - -#define PTTYPE 64 -#include "paging_tmpl.h" -#undef PTTYPE - -#define PTTYPE 32 -#include "paging_tmpl.h" -#undef PTTYPE - -static int paging64_init_context_common(struct kvm_vcpu *vcpu, int level) -{ - struct kvm_mmu *context = &vcpu->mmu; - - ASSERT(is_pae(vcpu)); - context->new_cr3 = paging_new_cr3; - context->page_fault = paging64_page_fault; - context->gva_to_gpa = paging64_gva_to_gpa; - context->free = paging_free; - context->root_level = level; - context->shadow_root_level = level; - context->root_hpa = INVALID_PAGE; - return 0; -} - -static int paging64_init_context(struct kvm_vcpu *vcpu) -{ - return paging64_init_context_common(vcpu, PT64_ROOT_LEVEL); -} - -static int paging32_init_context(struct kvm_vcpu *vcpu) -{ - struct kvm_mmu *context = &vcpu->mmu; - - context->new_cr3 = paging_new_cr3; - context->page_fault = paging32_page_fault; - context->gva_to_gpa = paging32_gva_to_gpa; - context->free = paging_free; - context->root_level = PT32_ROOT_LEVEL; - context->shadow_root_level = PT32E_ROOT_LEVEL; - context->root_hpa = INVALID_PAGE; - return 0; -} - -static int paging32E_init_context(struct kvm_vcpu *vcpu) -{ - return paging64_init_context_common(vcpu, PT32E_ROOT_LEVEL); -} - -static int init_kvm_mmu(struct kvm_vcpu *vcpu) -{ - ASSERT(vcpu); - ASSERT(!VALID_PAGE(vcpu->mmu.root_hpa)); - - if (!is_paging(vcpu)) - return nonpaging_init_context(vcpu); - else if (is_long_mode(vcpu)) - return paging64_init_context(vcpu); - else if (is_pae(vcpu)) - return paging32E_init_context(vcpu); - else - return paging32_init_context(vcpu); -} - -static void destroy_kvm_mmu(struct kvm_vcpu *vcpu) -{ - ASSERT(vcpu); - if (VALID_PAGE(vcpu->mmu.root_hpa)) { - vcpu->mmu.free(vcpu); - vcpu->mmu.root_hpa = INVALID_PAGE; - } -} - -int kvm_mmu_reset_context(struct kvm_vcpu *vcpu) -{ - destroy_kvm_mmu(vcpu); - return init_kvm_mmu(vcpu); -} -EXPORT_SYMBOL_GPL(kvm_mmu_reset_context); - -int kvm_mmu_load(struct kvm_vcpu *vcpu) -{ - int r; - - mutex_lock(&vcpu->kvm->lock); - r = mmu_topup_memory_caches(vcpu); - if (r) - goto out; - mmu_alloc_roots(vcpu); - kvm_x86_ops->set_cr3(vcpu, vcpu->mmu.root_hpa); - kvm_mmu_flush_tlb(vcpu); -out: - mutex_unlock(&vcpu->kvm->lock); - return r; -} -EXPORT_SYMBOL_GPL(kvm_mmu_load); - -void kvm_mmu_unload(struct kvm_vcpu *vcpu) -{ - mmu_free_roots(vcpu); -} - -static void mmu_pte_write_zap_pte(struct kvm_vcpu *vcpu, - struct kvm_mmu_page *page, - u64 *spte) -{ - u64 pte; - struct kvm_mmu_page *child; - - pte = *spte; - if (is_present_pte(pte)) { - if (page->role.level == PT_PAGE_TABLE_LEVEL) - rmap_remove(spte); - else { - child = page_header(pte & PT64_BASE_ADDR_MASK); - mmu_page_remove_parent_pte(child, spte); - } - } - set_shadow_pte(spte, 0); - kvm_flush_remote_tlbs(vcpu->kvm); -} - -static void mmu_pte_write_new_pte(struct kvm_vcpu *vcpu, - struct kvm_mmu_page *page, - u64 *spte, - const void *new, int bytes) -{ - if (page->role.level != PT_PAGE_TABLE_LEVEL) - return; - - if (page->role.glevels == PT32_ROOT_LEVEL) - paging32_update_pte(vcpu, page, spte, new, bytes); - else - paging64_update_pte(vcpu, page, spte, new, bytes); -} - -void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, - const u8 *new, int bytes) -{ - gfn_t gfn = gpa >> PAGE_SHIFT; - struct kvm_mmu_page *page; - struct hlist_node *node, *n; - struct hlist_head *bucket; - unsigned index; - u64 *spte; - unsigned offset = offset_in_page(gpa); - unsigned pte_size; - unsigned page_offset; - unsigned misaligned; - unsigned quadrant; - int level; - int flooded = 0; - int npte; - - pgprintk("%s: gpa %llx bytes %d\n", __FUNCTION__, gpa, bytes); - if (gfn == vcpu->last_pt_write_gfn) { - ++vcpu->last_pt_write_count; - if (vcpu->last_pt_write_count >= 3) - flooded = 1; - } else { - vcpu->last_pt_write_gfn = gfn; - vcpu->last_pt_write_count = 1; - } - index = kvm_page_table_hashfn(gfn) % KVM_NUM_MMU_PAGES; - bucket = &vcpu->kvm->mmu_page_hash[index]; - hlist_for_each_entry_safe(page, node, n, bucket, hash_link) { - if (page->gfn != gfn || page->role.metaphysical) - continue; - pte_size = page->role.glevels == PT32_ROOT_LEVEL ? 4 : 8; - misaligned = (offset ^ (offset + bytes - 1)) & ~(pte_size - 1); - misaligned |= bytes < 4; - if (misaligned || flooded) { - /* - * Misaligned accesses are too much trouble to fix - * up; also, they usually indicate a page is not used - * as a page table. - * - * If we're seeing too many writes to a page, - * it may no longer be a page table, or we may be - * forking, in which case it is better to unmap the - * page. - */ - pgprintk("misaligned: gpa %llx bytes %d role %x\n", - gpa, bytes, page->role.word); - kvm_mmu_zap_page(vcpu->kvm, page); - continue; - } - page_offset = offset; - level = page->role.level; - npte = 1; - if (page->role.glevels == PT32_ROOT_LEVEL) { - page_offset <<= 1; /* 32->64 */ - /* - * A 32-bit pde maps 4MB while the shadow pdes map - * only 2MB. So we need to double the offset again - * and zap two pdes instead of one. - */ - if (level == PT32_ROOT_LEVEL) { - page_offset &= ~7; /* kill rounding error */ - page_offset <<= 1; - npte = 2; - } - quadrant = page_offset >> PAGE_SHIFT; - page_offset &= ~PAGE_MASK; - if (quadrant != page->role.quadrant) - continue; - } - spte = &page->spt[page_offset / sizeof(*spte)]; - while (npte--) { - mmu_pte_write_zap_pte(vcpu, page, spte); - mmu_pte_write_new_pte(vcpu, page, spte, new, bytes); - ++spte; - } - } -} - -int kvm_mmu_unprotect_page_virt(struct kvm_vcpu *vcpu, gva_t gva) -{ - gpa_t gpa = vcpu->mmu.gva_to_gpa(vcpu, gva); - - return kvm_mmu_unprotect_page(vcpu, gpa >> PAGE_SHIFT); -} - -void __kvm_mmu_free_some_pages(struct kvm_vcpu *vcpu) -{ - while (vcpu->kvm->n_free_mmu_pages < KVM_REFILL_PAGES) { - struct kvm_mmu_page *page; - - page = container_of(vcpu->kvm->active_mmu_pages.prev, - struct kvm_mmu_page, link); - kvm_mmu_zap_page(vcpu->kvm, page); - } -} - -static void free_mmu_pages(struct kvm_vcpu *vcpu) -{ - struct kvm_mmu_page *page; - - while (!list_empty(&vcpu->kvm->active_mmu_pages)) { - page = container_of(vcpu->kvm->active_mmu_pages.next, - struct kvm_mmu_page, link); - kvm_mmu_zap_page(vcpu->kvm, page); - } - free_page((unsigned long)vcpu->mmu.pae_root); -} - -static int alloc_mmu_pages(struct kvm_vcpu *vcpu) -{ - struct page *page; - int i; - - ASSERT(vcpu); - - vcpu->kvm->n_free_mmu_pages = KVM_NUM_MMU_PAGES; - - /* - * When emulating 32-bit mode, cr3 is only 32 bits even on x86_64. - * Therefore we need to allocate shadow page tables in the first - * 4GB of memory, which happens to fit the DMA32 zone. - */ - page = alloc_page(GFP_KERNEL | __GFP_DMA32); - if (!page) - goto error_1; - vcpu->mmu.pae_root = page_address(page); - for (i = 0; i < 4; ++i) - vcpu->mmu.pae_root[i] = INVALID_PAGE; - - return 0; - -error_1: - free_mmu_pages(vcpu); - return -ENOMEM; -} - -int kvm_mmu_create(struct kvm_vcpu *vcpu) -{ - ASSERT(vcpu); - ASSERT(!VALID_PAGE(vcpu->mmu.root_hpa)); - - return alloc_mmu_pages(vcpu); -} - -int kvm_mmu_setup(struct kvm_vcpu *vcpu) -{ - ASSERT(vcpu); - ASSERT(!VALID_PAGE(vcpu->mmu.root_hpa)); - - return init_kvm_mmu(vcpu); -} - -void kvm_mmu_destroy(struct kvm_vcpu *vcpu) -{ - ASSERT(vcpu); - - destroy_kvm_mmu(vcpu); - free_mmu_pages(vcpu); - mmu_free_memory_caches(vcpu); -} - -void kvm_mmu_slot_remove_write_access(struct kvm *kvm, int slot) -{ - struct kvm_mmu_page *page; - - list_for_each_entry(page, &kvm->active_mmu_pages, link) { - int i; - u64 *pt; - - if (!test_bit(slot, &page->slot_bitmap)) - continue; - - pt = page->spt; - for (i = 0; i < PT64_ENT_PER_PAGE; ++i) - /* avoid RMW */ - if (pt[i] & PT_WRITABLE_MASK) { - rmap_remove(&pt[i]); - pt[i] &= ~PT_WRITABLE_MASK; - } - } -} - -void kvm_mmu_zap_all(struct kvm *kvm) -{ - struct kvm_mmu_page *page, *node; - - list_for_each_entry_safe(page, node, &kvm->active_mmu_pages, link) - kvm_mmu_zap_page(kvm, page); - - kvm_flush_remote_tlbs(kvm); -} - -void kvm_mmu_module_exit(void) -{ - if (pte_chain_cache) - kmem_cache_destroy(pte_chain_cache); - if (rmap_desc_cache) - kmem_cache_destroy(rmap_desc_cache); - if (mmu_page_header_cache) - kmem_cache_destroy(mmu_page_header_cache); -} - -int kvm_mmu_module_init(void) -{ - pte_chain_cache = kmem_cache_create("kvm_pte_chain", - sizeof(struct kvm_pte_chain), - 0, 0, NULL); - if (!pte_chain_cache) - goto nomem; - rmap_desc_cache = kmem_cache_create("kvm_rmap_desc", - sizeof(struct kvm_rmap_desc), - 0, 0, NULL); - if (!rmap_desc_cache) - goto nomem; - - mmu_page_header_cache = kmem_cache_create("kvm_mmu_page_header", - sizeof(struct kvm_mmu_page), - 0, 0, NULL); - if (!mmu_page_header_cache) - goto nomem; - - return 0; - -nomem: - kvm_mmu_module_exit(); - return -ENOMEM; -} - -#ifdef AUDIT - -static const char *audit_msg; - -static gva_t canonicalize(gva_t gva) -{ -#ifdef CONFIG_X86_64 - gva = (long long)(gva << 16) >> 16; -#endif - return gva; -} - -static void audit_mappings_page(struct kvm_vcpu *vcpu, u64 page_pte, - gva_t va, int level) -{ - u64 *pt = __va(page_pte & PT64_BASE_ADDR_MASK); - int i; - gva_t va_delta = 1ul << (PAGE_SHIFT + 9 * (level - 1)); - - for (i = 0; i < PT64_ENT_PER_PAGE; ++i, va += va_delta) { - u64 ent = pt[i]; - - if (!(ent & PT_PRESENT_MASK)) - continue; - - va = canonicalize(va); - if (level > 1) - audit_mappings_page(vcpu, ent, va, level - 1); - else { - gpa_t gpa = vcpu->mmu.gva_to_gpa(vcpu, va); - hpa_t hpa = gpa_to_hpa(vcpu, gpa); - - if ((ent & PT_PRESENT_MASK) - && (ent & PT64_BASE_ADDR_MASK) != hpa) - printk(KERN_ERR "audit error: (%s) levels %d" - " gva %lx gpa %llx hpa %llx ent %llx\n", - audit_msg, vcpu->mmu.root_level, - va, gpa, hpa, ent); - } - } -} - -static void audit_mappings(struct kvm_vcpu *vcpu) -{ - unsigned i; - - if (vcpu->mmu.root_level == 4) - audit_mappings_page(vcpu, vcpu->mmu.root_hpa, 0, 4); - else - for (i = 0; i < 4; ++i) - if (vcpu->mmu.pae_root[i] & PT_PRESENT_MASK) - audit_mappings_page(vcpu, - vcpu->mmu.pae_root[i], - i << 30, - 2); -} - -static int count_rmaps(struct kvm_vcpu *vcpu) -{ - int nmaps = 0; - int i, j, k; - - for (i = 0; i < KVM_MEMORY_SLOTS; ++i) { - struct kvm_memory_slot *m = &vcpu->kvm->memslots[i]; - struct kvm_rmap_desc *d; - - for (j = 0; j < m->npages; ++j) { - struct page *page = m->phys_mem[j]; - - if (!page->private) - continue; - if (!(page->private & 1)) { - ++nmaps; - continue; - } - d = (struct kvm_rmap_desc *)(page->private & ~1ul); - while (d) { - for (k = 0; k < RMAP_EXT; ++k) - if (d->shadow_ptes[k]) - ++nmaps; - else - break; - d = d->more; - } - } - } - return nmaps; -} - -static int count_writable_mappings(struct kvm_vcpu *vcpu) -{ - int nmaps = 0; - struct kvm_mmu_page *page; - int i; - - list_for_each_entry(page, &vcpu->kvm->active_mmu_pages, link) { - u64 *pt = page->spt; - - if (page->role.level != PT_PAGE_TABLE_LEVEL) - continue; - - for (i = 0; i < PT64_ENT_PER_PAGE; ++i) { - u64 ent = pt[i]; - - if (!(ent & PT_PRESENT_MASK)) - continue; - if (!(ent & PT_WRITABLE_MASK)) - continue; - ++nmaps; - } - } - return nmaps; -} - -static void audit_rmap(struct kvm_vcpu *vcpu) -{ - int n_rmap = count_rmaps(vcpu); - int n_actual = count_writable_mappings(vcpu); - - if (n_rmap != n_actual) - printk(KERN_ERR "%s: (%s) rmap %d actual %d\n", - __FUNCTION__, audit_msg, n_rmap, n_actual); -} - -static void audit_write_protection(struct kvm_vcpu *vcpu) -{ - struct kvm_mmu_page *page; - - list_for_each_entry(page, &vcpu->kvm->active_mmu_pages, link) { - hfn_t hfn; - struct page *pg; - - if (page->role.metaphysical) - continue; - - hfn = gpa_to_hpa(vcpu, (gpa_t)page->gfn << PAGE_SHIFT) - >> PAGE_SHIFT; - pg = pfn_to_page(hfn); - if (pg->private) - printk(KERN_ERR "%s: (%s) shadow page has writable" - " mappings: gfn %lx role %x\n", - __FUNCTION__, audit_msg, page->gfn, - page->role.word); - } -} - -static void kvm_mmu_audit(struct kvm_vcpu *vcpu, const char *msg) -{ - int olddbg = dbg; - - dbg = 0; - audit_msg = msg; - audit_rmap(vcpu); - audit_write_protection(vcpu); - audit_mappings(vcpu); - dbg = olddbg; -} - -#endif diff --git a/drivers/kvm/paging_tmpl.h b/drivers/kvm/paging_tmpl.h deleted file mode 100644 index 6b094b44f8fb..000000000000 --- a/drivers/kvm/paging_tmpl.h +++ /dev/null @@ -1,511 +0,0 @@ -/* - * Kernel-based Virtual Machine driver for Linux - * - * This module enables machines with Intel VT-x extensions to run virtual - * machines without emulation or binary translation. - * - * MMU support - * - * Copyright (C) 2006 Qumranet, Inc. - * - * Authors: - * Yaniv Kamay <yaniv@qumranet.com> - * Avi Kivity <avi@qumranet.com> - * - * This work is licensed under the terms of the GNU GPL, version 2. See - * the COPYING file in the top-level directory. - * - */ - -/* - * We need the mmu code to access both 32-bit and 64-bit guest ptes, - * so the code in this file is compiled twice, once per pte size. - */ - -#if PTTYPE == 64 - #define pt_element_t u64 - #define guest_walker guest_walker64 - #define FNAME(name) paging##64_##name - #define PT_BASE_ADDR_MASK PT64_BASE_ADDR_MASK - #define PT_DIR_BASE_ADDR_MASK PT64_DIR_BASE_ADDR_MASK - #define PT_INDEX(addr, level) PT64_INDEX(addr, level) - #define SHADOW_PT_INDEX(addr, level) PT64_INDEX(addr, level) - #define PT_LEVEL_MASK(level) PT64_LEVEL_MASK(level) - #ifdef CONFIG_X86_64 - #define PT_MAX_FULL_LEVELS 4 - #else - #define PT_MAX_FULL_LEVELS 2 - #endif -#elif PTTYPE == 32 - #define pt_element_t u32 - #define guest_walker guest_walker32 - #define FNAME(name) paging##32_##name - #define PT_BASE_ADDR_MASK PT32_BASE_ADDR_MASK - #define PT_DIR_BASE_ADDR_MASK PT32_DIR_BASE_ADDR_MASK - #define PT_INDEX(addr, level) PT32_INDEX(addr, level) - #define SHADOW_PT_INDEX(addr, level) PT64_INDEX(addr, level) - #define PT_LEVEL_MASK(level) PT32_LEVEL_MASK(level) - #define PT_MAX_FULL_LEVELS 2 -#else - #error Invalid PTTYPE value -#endif - -/* - * The guest_walker structure emulates the behavior of the hardware page - * table walker. - */ -struct guest_walker { - int level; - gfn_t table_gfn[PT_MAX_FULL_LEVELS]; - pt_element_t *table; - pt_element_t pte; - pt_element_t *ptep; - struct page *page; - int index; - pt_element_t inherited_ar; - gfn_t gfn; - u32 error_code; -}; - -/* - * Fetch a guest pte for a guest virtual address - */ -static int FNAME(walk_addr)(struct guest_walker *walker, - struct kvm_vcpu *vcpu, gva_t addr, - int write_fault, int user_fault, int fetch_fault) -{ - hpa_t hpa; - struct kvm_memory_slot *slot; - pt_element_t *ptep; - pt_element_t root; - gfn_t table_gfn; - - pgprintk("%s: addr %lx\n", __FUNCTION__, addr); - walker->level = vcpu->mmu.root_level; - walker->table = NULL; - walker->page = NULL; - walker->ptep = NULL; - root = vcpu->cr3; -#if PTTYPE == 64 - if (!is_long_mode(vcpu)) { - walker->ptep = &vcpu->pdptrs[(addr >> 30) & 3]; - root = *walker->ptep; - walker->pte = root; - if (!(root & PT_PRESENT_MASK)) - goto not_present; - --walker->level; - } -#endif - table_gfn = (root & PT64_BASE_ADDR_MASK) >> PAGE_SHIFT; - walker->table_gfn[walker->level - 1] = table_gfn; - pgprintk("%s: table_gfn[%d] %lx\n", __FUNCTION__, - walker->level - 1, table_gfn); - slot = gfn_to_memslot(vcpu->kvm, table_gfn); - hpa = safe_gpa_to_hpa(vcpu, root & PT64_BASE_ADDR_MASK); - walker->page = pfn_to_page(hpa >> PAGE_SHIFT); - walker->table = kmap_atomic(walker->page, KM_USER0); - - ASSERT((!is_long_mode(vcpu) && is_pae(vcpu)) || - (vcpu->cr3 & CR3_NONPAE_RESERVED_BITS) == 0); - - walker->inherited_ar = PT_USER_MASK | PT_WRITABLE_MASK; - - for (;;) { - int index = PT_INDEX(addr, walker->level); - hpa_t paddr; - - ptep = &walker->table[index]; - walker->index = index; - ASSERT(((unsigned long)walker->table & PAGE_MASK) == - ((unsigned long)ptep & PAGE_MASK)); - - if (!is_present_pte(*ptep)) - goto not_present; - - if (write_fault && !is_writeble_pte(*ptep)) - if (user_fault || is_write_protection(vcpu)) - goto access_error; - - if (user_fault && !(*ptep & PT_USER_MASK)) - goto access_error; - -#if PTTYPE == 64 - if (fetch_fault && is_nx(vcpu) && (*ptep & PT64_NX_MASK)) - goto access_error; -#endif - - if (!(*ptep & PT_ACCESSED_MASK)) { - mark_page_dirty(vcpu->kvm, table_gfn); - *ptep |= PT_ACCESSED_MASK; - } - - if (walker->level == PT_PAGE_TABLE_LEVEL) { - walker->gfn = (*ptep & PT_BASE_ADDR_MASK) - >> PAGE_SHIFT; - break; - } - - if (walker->level == PT_DIRECTORY_LEVEL - && (*ptep & PT_PAGE_SIZE_MASK) - && (PTTYPE == 64 || is_pse(vcpu))) { - walker->gfn = (*ptep & PT_DIR_BASE_ADDR_MASK) - >> PAGE_SHIFT; - walker->gfn += PT_INDEX(addr, PT_PAGE_TABLE_LEVEL); - break; - } - - walker->inherited_ar &= walker->table[index]; - table_gfn = (*ptep & PT_BASE_ADDR_MASK) >> PAGE_SHIFT; - kunmap_atomic(walker->table, KM_USER0); - paddr = safe_gpa_to_hpa(vcpu, table_gfn << PAGE_SHIFT); - walker->page = pfn_to_page(paddr >> PAGE_SHIFT); - walker->table = kmap_atomic(walker->page, KM_USER0); - --walker->level; - walker->table_gfn[walker->level - 1 ] = table_gfn; - pgprintk("%s: table_gfn[%d] %lx\n", __FUNCTION__, - walker->level - 1, table_gfn); - } - walker->pte = *ptep; - if (walker->page) - walker->ptep = NULL; - if (walker->table) - kunmap_atomic(walker->table, KM_USER0); - pgprintk("%s: pte %llx\n", __FUNCTION__, (u64)*ptep); - return 1; - -not_present: - walker->error_code = 0; - goto err; - -access_error: - walker->error_code = PFERR_PRESENT_MASK; - -err: - if (write_fault) - walker->error_code |= PFERR_WRITE_MASK; - if (user_fault) - walker->error_code |= PFERR_USER_MASK; - if (fetch_fault) - walker->error_code |= PFERR_FETCH_MASK; - if (walker->table) - kunmap_atomic(walker->table, KM_USER0); - return 0; -} - -static void FNAME(mark_pagetable_dirty)(struct kvm *kvm, - struct guest_walker *walker) -{ - mark_page_dirty(kvm, walker->table_gfn[walker->level - 1]); -} - -static void FNAME(set_pte_common)(struct kvm_vcpu *vcpu, - u64 *shadow_pte, - gpa_t gaddr, - pt_element_t gpte, - u64 access_bits, - int user_fault, - int write_fault, - int *ptwrite, - struct guest_walker *walker, - gfn_t gfn) -{ - hpa_t paddr; - int dirty = gpte & PT_DIRTY_MASK; - u64 spte = *shadow_pte; - int was_rmapped = is_rmap_pte(spte); - - pgprintk("%s: spte %llx gpte %llx access %llx write_fault %d" - " user_fault %d gfn %lx\n", - __FUNCTION__, spte, (u64)gpte, access_bits, - write_fault, user_fault, gfn); - - if (write_fault && !dirty) { - pt_element_t *guest_ent, *tmp = NULL; - - if (walker->ptep) - guest_ent = walker->ptep; - else { - tmp = kmap_atomic(walker->page, KM_USER0); - guest_ent = &tmp[walker->index]; - } - - *guest_ent |= PT_DIRTY_MASK; - if (!walker->ptep) - kunmap_atomic(tmp, KM_USER0); - dirty = 1; - FNAME(mark_pagetable_dirty)(vcpu->kvm, walker); - } - - spte |= PT_PRESENT_MASK | PT_ACCESSED_MASK | PT_DIRTY_MASK; - spte |= gpte & PT64_NX_MASK; - if (!dirty) - access_bits &= ~PT_WRITABLE_MASK; - - paddr = gpa_to_hpa(vcpu, gaddr & PT64_BASE_ADDR_MASK); - - spte |= PT_PRESENT_MASK; - if (access_bits & PT_USER_MASK) - spte |= PT_USER_MASK; - - if (is_error_hpa(paddr)) { - spte |= gaddr; - spte |= PT_SHADOW_IO_MARK; - spte &= ~PT_PRESENT_MASK; - set_shadow_pte(shadow_pte, spte); - return; - } - - spte |= paddr; - - if ((access_bits & PT_WRITABLE_MASK) - || (write_fault && !is_write_protection(vcpu) && !user_fault)) { - struct kvm_mmu_page *shadow; - - spte |= PT_WRITABLE_MASK; - if (user_fault) { - mmu_unshadow(vcpu, gfn); - goto unshadowed; - } - - shadow = kvm_mmu_lookup_page(vcpu, gfn); - if (shadow) { - pgprintk("%s: found shadow page for %lx, marking ro\n", - __FUNCTION__, gfn); - access_bits &= ~PT_WRITABLE_MASK; - if (is_writeble_pte(spte)) { - spte &= ~PT_WRITABLE_MASK; - kvm_x86_ops->tlb_flush(vcpu); - } - if (write_fault) - *ptwrite = 1; - } - } - -unshadowed: - - if (access_bits & PT_WRITABLE_MASK) - mark_page_dirty(vcpu->kvm, gaddr >> PAGE_SHIFT); - - set_shadow_pte(shadow_pte, spte); - page_header_update_slot(vcpu->kvm, shadow_pte, gaddr); - if (!was_rmapped) - rmap_add(vcpu, shadow_pte); -} - -static void FNAME(set_pte)(struct kvm_vcpu *vcpu, pt_element_t gpte, - u64 *shadow_pte, u64 access_bits, - int user_fault, int write_fault, int *ptwrite, - struct guest_walker *walker, gfn_t gfn) -{ - access_bits &= gpte; - FNAME(set_pte_common)(vcpu, shadow_pte, gpte & PT_BASE_ADDR_MASK, - gpte, access_bits, user_fault, write_fault, - ptwrite, walker, gfn); -} - -static void FNAME(update_pte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *page, - u64 *spte, const void *pte, int bytes) -{ - pt_element_t gpte; - - if (bytes < sizeof(pt_element_t)) - return; - gpte = *(const pt_element_t *)pte; - if (~gpte & (PT_PRESENT_MASK | PT_ACCESSED_MASK)) - return; - pgprintk("%s: gpte %llx spte %p\n", __FUNCTION__, (u64)gpte, spte); - FNAME(set_pte)(vcpu, gpte, spte, PT_USER_MASK | PT_WRITABLE_MASK, 0, - 0, NULL, NULL, - (gpte & PT_BASE_ADDR_MASK) >> PAGE_SHIFT); -} - -static void FNAME(set_pde)(struct kvm_vcpu *vcpu, pt_element_t gpde, - u64 *shadow_pte, u64 access_bits, - int user_fault, int write_fault, int *ptwrite, - struct guest_walker *walker, gfn_t gfn) -{ - gpa_t gaddr; - - access_bits &= gpde; - gaddr = (gpa_t)gfn << PAGE_SHIFT; - if (PTTYPE == 32 && is_cpuid_PSE36()) - gaddr |= (gpde & PT32_DIR_PSE36_MASK) << - (32 - PT32_DIR_PSE36_SHIFT); - FNAME(set_pte_common)(vcpu, shadow_pte, gaddr, - gpde, access_bits, user_fault, write_fault, - ptwrite, walker, gfn); -} - -/* - * Fetch a shadow pte for a specific level in the paging hierarchy. - */ -static u64 *FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr, - struct guest_walker *walker, - int user_fault, int write_fault, int *ptwrite) -{ - hpa_t shadow_addr; - int level; - u64 *shadow_ent; - u64 *prev_shadow_ent = NULL; - - if (!is_present_pte(walker->pte)) - return NULL; - - shadow_addr = vcpu->mmu.root_hpa; - level = vcpu->mmu.shadow_root_level; - if (level == PT32E_ROOT_LEVEL) { - shadow_addr = vcpu->mmu.pae_root[(addr >> 30) & 3]; - shadow_addr &= PT64_BASE_ADDR_MASK; - --level; - } - - for (; ; level--) { - u32 index = SHADOW_PT_INDEX(addr, level); - struct kvm_mmu_page *shadow_page; - u64 shadow_pte; - int metaphysical; - gfn_t table_gfn; - unsigned hugepage_access = 0; - - shadow_ent = ((u64 *)__va(shadow_addr)) + index; - if (is_present_pte(*shadow_ent) || is_io_pte(*shadow_ent)) { - if (level == PT_PAGE_TABLE_LEVEL) - break; - shadow_addr = *shadow_ent & PT64_BASE_ADDR_MASK; - prev_shadow_ent = shadow_ent; - continue; - } - - if (level == PT_PAGE_TABLE_LEVEL) - break; - - if (level - 1 == PT_PAGE_TABLE_LEVEL - && walker->level == PT_DIRECTORY_LEVEL) { - metaphysical = 1; - hugepage_access = walker->pte; - hugepage_access &= PT_USER_MASK | PT_WRITABLE_MASK; - if (walker->pte & PT64_NX_MASK) - hugepage_access |= (1 << 2); - hugepage_access >>= PT_WRITABLE_SHIFT; - table_gfn = (walker->pte & PT_BASE_ADDR_MASK) - >> PAGE_SHIFT; - } else { - metaphysical = 0; - table_gfn = walker->table_gfn[level - 2]; - } - shadow_page = kvm_mmu_get_page(vcpu, table_gfn, addr, level-1, - metaphysical, hugepage_access, - shadow_ent); - shadow_addr = __pa(shadow_page->spt); - shadow_pte = shadow_addr | PT_PRESENT_MASK | PT_ACCESSED_MASK - | PT_WRITABLE_MASK | PT_USER_MASK; - *shadow_ent = shadow_pte; - prev_shadow_ent = shadow_ent; - } - - if (walker->level == PT_DIRECTORY_LEVEL) { - FNAME(set_pde)(vcpu, walker->pte, shadow_ent, - walker->inherited_ar, user_fault, write_fault, - ptwrite, walker, walker->gfn); - } else { - ASSERT(walker->level == PT_PAGE_TABLE_LEVEL); - FNAME(set_pte)(vcpu, walker->pte, shadow_ent, - walker->inherited_ar, user_fault, write_fault, - ptwrite, walker, walker->gfn); - } - return shadow_ent; -} - -/* - * Page fault handler. There are several causes for a page fault: - * - there is no shadow pte for the guest pte - * - write access through a shadow pte marked read only so that we can set - * the dirty bit - * - write access to a shadow pte marked read only so we can update the page - * dirty bitmap, when userspace requests it - * - mmio access; in this case we will never install a present shadow pte - * - normal guest page fault due to the guest pte marked not present, not - * writable, or not executable - * - * Returns: 1 if we need to emulate the instruction, 0 otherwise, or - * a negative value on error. - */ -static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, - u32 error_code) -{ - int write_fault = error_code & PFERR_WRITE_MASK; - int user_fault = error_code & PFERR_USER_MASK; - int fetch_fault = error_code & PFERR_FETCH_MASK; - struct guest_walker walker; - u64 *shadow_pte; - int write_pt = 0; - int r; - - pgprintk("%s: addr %lx err %x\n", __FUNCTION__, addr, error_code); - kvm_mmu_audit(vcpu, "pre page fault"); - - r = mmu_topup_memory_caches(vcpu); - if (r) - return r; - - /* - * Look up the shadow pte for the faulting address. - */ - r = FNAME(walk_addr)(&walker, vcpu, addr, write_fault, user_fault, - fetch_fault); - - /* - * The page is not mapped by the guest. Let the guest handle it. - */ - if (!r) { - pgprintk("%s: guest page fault\n", __FUNCTION__); - inject_page_fault(vcpu, addr, walker.error_code); - vcpu->last_pt_write_count = 0; /* reset fork detector */ - return 0; - } - - shadow_pte = FNAME(fetch)(vcpu, addr, &walker, user_fault, write_fault, - &write_pt); - pgprintk("%s: shadow pte %p %llx ptwrite %d\n", __FUNCTION__, - shadow_pte, *shadow_pte, write_pt); - - if (!write_pt) - vcpu->last_pt_write_count = 0; /* reset fork detector */ - - /* - * mmio: emulate if accessible, otherwise its a guest fault. - */ - if (is_io_pte(*shadow_pte)) - return 1; - - ++vcpu->stat.pf_fixed; - kvm_mmu_audit(vcpu, "post page fault (fixed)"); - - return write_pt; -} - -static gpa_t FNAME(gva_to_gpa)(struct kvm_vcpu *vcpu, gva_t vaddr) -{ - struct guest_walker walker; - gpa_t gpa = UNMAPPED_GVA; - int r; - - r = FNAME(walk_addr)(&walker, vcpu, vaddr, 0, 0, 0); - - if (r) { - gpa = (gpa_t)walker.gfn << PAGE_SHIFT; - gpa |= vaddr & ~PAGE_MASK; - } - - return gpa; -} - -#undef pt_element_t -#undef guest_walker -#undef FNAME -#undef PT_BASE_ADDR_MASK -#undef PT_INDEX -#undef SHADOW_PT_INDEX -#undef PT_LEVEL_MASK -#undef PT_DIR_BASE_ADDR_MASK -#undef PT_MAX_FULL_LEVELS diff --git a/drivers/kvm/segment_descriptor.h b/drivers/kvm/segment_descriptor.h deleted file mode 100644 index 71fdf458619a..000000000000 --- a/drivers/kvm/segment_descriptor.h +++ /dev/null @@ -1,17 +0,0 @@ -struct segment_descriptor { - u16 limit_low; - u16 base_low; - u8 base_mid; - u8 type : 4; - u8 system : 1; - u8 dpl : 2; - u8 present : 1; - u8 limit_high : 4; - u8 avl : 1; - u8 long_mode : 1; - u8 default_op : 1; - u8 granularity : 1; - u8 base_high; -} __attribute__((packed)); - - diff --git a/drivers/kvm/svm.c b/drivers/kvm/svm.c deleted file mode 100644 index 4e04e49a2f1c..000000000000 --- a/drivers/kvm/svm.c +++ /dev/null @@ -1,1754 +0,0 @@ -/* - * Kernel-based Virtual Machine driver for Linux - * - * AMD SVM support - * - * Copyright (C) 2006 Qumranet, Inc. - * - * Authors: - * Yaniv Kamay <yaniv@qumranet.com> - * Avi Kivity <avi@qumranet.com> - * - * This work is licensed under the terms of the GNU GPL, version 2. See - * the COPYING file in the top-level directory. - * - */ - -#include "kvm_svm.h" -#include "x86_emulate.h" -#include "irq.h" - -#include <linux/module.h> -#include <linux/kernel.h> -#include <linux/vmalloc.h> -#include <linux/highmem.h> -#include <linux/sched.h> - -#include <asm/desc.h> - -MODULE_AUTHOR("Qumranet"); -MODULE_LICENSE("GPL"); - -#define IOPM_ALLOC_ORDER 2 -#define MSRPM_ALLOC_ORDER 1 - -#define DB_VECTOR 1 -#define UD_VECTOR 6 -#define GP_VECTOR 13 - -#define DR7_GD_MASK (1 << 13) -#define DR6_BD_MASK (1 << 13) - -#define SEG_TYPE_LDT 2 -#define SEG_TYPE_BUSY_TSS16 3 - -#define KVM_EFER_LMA (1 << 10) -#define KVM_EFER_LME (1 << 8) - -#define SVM_FEATURE_NPT (1 << 0) -#define SVM_FEATURE_LBRV (1 << 1) -#define SVM_DEATURE_SVML (1 << 2) - -static void kvm_reput_irq(struct vcpu_svm *svm); - -static inline struct vcpu_svm *to_svm(struct kvm_vcpu *vcpu) -{ - return container_of(vcpu, struct vcpu_svm, vcpu); -} - -unsigned long iopm_base; -unsigned long msrpm_base; - -struct kvm_ldttss_desc { - u16 limit0; - u16 base0; - unsigned base1 : 8, type : 5, dpl : 2, p : 1; - unsigned limit1 : 4, zero0 : 3, g : 1, base2 : 8; - u32 base3; - u32 zero1; -} __attribute__((packed)); - -struct svm_cpu_data { - int cpu; - - u64 asid_generation; - u32 max_asid; - u32 next_asid; - struct kvm_ldttss_desc *tss_desc; - - struct page *save_area; -}; - -static DEFINE_PER_CPU(struct svm_cpu_data *, svm_data); -static uint32_t svm_features; - -struct svm_init_data { - int cpu; - int r; -}; - -static u32 msrpm_ranges[] = {0, 0xc0000000, 0xc0010000}; - -#define NUM_MSR_MAPS ARRAY_SIZE(msrpm_ranges) -#define MSRS_RANGE_SIZE 2048 -#define MSRS_IN_RANGE (MSRS_RANGE_SIZE * 8 / 2) - -#define MAX_INST_SIZE 15 - -static inline u32 svm_has(u32 feat) -{ - return svm_features & feat; -} - -static inline u8 pop_irq(struct kvm_vcpu *vcpu) -{ - int word_index = __ffs(vcpu->irq_summary); - int bit_index = __ffs(vcpu->irq_pending[word_index]); - int irq = word_index * BITS_PER_LONG + bit_index; - - clear_bit(bit_index, &vcpu->irq_pending[word_index]); - if (!vcpu->irq_pending[word_index]) - clear_bit(word_index, &vcpu->irq_summary); - return irq; -} - -static inline void push_irq(struct kvm_vcpu *vcpu, u8 irq) -{ - set_bit(irq, vcpu->irq_pending); - set_bit(irq / BITS_PER_LONG, &vcpu->irq_summary); -} - -static inline void clgi(void) -{ - asm volatile (SVM_CLGI); -} - -static inline void stgi(void) -{ - asm volatile (SVM_STGI); -} - -static inline void invlpga(unsigned long addr, u32 asid) -{ - asm volatile (SVM_INVLPGA :: "a"(addr), "c"(asid)); -} - -static inline unsigned long kvm_read_cr2(void) -{ - unsigned long cr2; - - asm volatile ("mov %%cr2, %0" : "=r" (cr2)); - return cr2; -} - -static inline void kvm_write_cr2(unsigned long val) -{ - asm volatile ("mov %0, %%cr2" :: "r" (val)); -} - -static inline unsigned long read_dr6(void) -{ - unsigned long dr6; - - asm volatile ("mov %%dr6, %0" : "=r" (dr6)); - return dr6; -} - -static inline void write_dr6(unsigned long val) -{ - asm volatile ("mov %0, %%dr6" :: "r" (val)); -} - -static inline unsigned long read_dr7(void) -{ - unsigned long dr7; - - asm volatile ("mov %%dr7, %0" : "=r" (dr7)); - return dr7; -} - -static inline void write_dr7(unsigned long val) -{ - asm volatile ("mov %0, %%dr7" :: "r" (val)); -} - -static inline void force_new_asid(struct kvm_vcpu *vcpu) -{ - to_svm(vcpu)->asid_generation--; -} - -static inline void flush_guest_tlb(struct kvm_vcpu *vcpu) -{ - force_new_asid(vcpu); -} - -static void svm_set_efer(struct kvm_vcpu *vcpu, u64 efer) -{ - if (!(efer & KVM_EFER_LMA)) - efer &= ~KVM_EFER_LME; - - to_svm(vcpu)->vmcb->save.efer = efer | MSR_EFER_SVME_MASK; - vcpu->shadow_efer = efer; -} - -static void svm_inject_gp(struct kvm_vcpu *vcpu, unsigned error_code) -{ - struct vcpu_svm *svm = to_svm(vcpu); - - svm->vmcb->control.event_inj = SVM_EVTINJ_VALID | - SVM_EVTINJ_VALID_ERR | - SVM_EVTINJ_TYPE_EXEPT | - GP_VECTOR; - svm->vmcb->control.event_inj_err = error_code; -} - -static void inject_ud(struct kvm_vcpu *vcpu) -{ - to_svm(vcpu)->vmcb->control.event_inj = SVM_EVTINJ_VALID | - SVM_EVTINJ_TYPE_EXEPT | - UD_VECTOR; -} - -static int is_page_fault(uint32_t info) -{ - info &= SVM_EVTINJ_VEC_MASK | SVM_EVTINJ_TYPE_MASK | SVM_EVTINJ_VALID; - return info == (PF_VECTOR | SVM_EVTINJ_VALID | SVM_EVTINJ_TYPE_EXEPT); -} - -static int is_external_interrupt(u32 info) -{ - info &= SVM_EVTINJ_TYPE_MASK | SVM_EVTINJ_VALID; - return info == (SVM_EVTINJ_VALID | SVM_EVTINJ_TYPE_INTR); -} - -static void skip_emulated_instruction(struct kvm_vcpu *vcpu) -{ - struct vcpu_svm *svm = to_svm(vcpu); - - if (!svm->next_rip) { - printk(KERN_DEBUG "%s: NOP\n", __FUNCTION__); - return; - } - if (svm->next_rip - svm->vmcb->save.rip > MAX_INST_SIZE) { - printk(KERN_ERR "%s: ip 0x%llx next 0x%llx\n", - __FUNCTION__, - svm->vmcb->save.rip, - svm->next_rip); - } - - vcpu->rip = svm->vmcb->save.rip = svm->next_rip; - svm->vmcb->control.int_state &= ~SVM_INTERRUPT_SHADOW_MASK; - - vcpu->interrupt_window_open = 1; -} - -static int has_svm(void) -{ - uint32_t eax, ebx, ecx, edx; - - if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD) { - printk(KERN_INFO "has_svm: not amd\n"); - return 0; - } - - cpuid(0x80000000, &eax, &ebx, &ecx, &edx); - if (eax < SVM_CPUID_FUNC) { - printk(KERN_INFO "has_svm: can't execute cpuid_8000000a\n"); - return 0; - } - - cpuid(0x80000001, &eax, &ebx, &ecx, &edx); - if (!(ecx & (1 << SVM_CPUID_FEATURE_SHIFT))) { - printk(KERN_DEBUG "has_svm: svm not available\n"); - return 0; - } - return 1; -} - -static void svm_hardware_disable(void *garbage) -{ - struct svm_cpu_data *svm_data - = per_cpu(svm_data, raw_smp_processor_id()); - - if (svm_data) { - uint64_t efer; - - wrmsrl(MSR_VM_HSAVE_PA, 0); - rdmsrl(MSR_EFER, efer); - wrmsrl(MSR_EFER, efer & ~MSR_EFER_SVME_MASK); - per_cpu(svm_data, raw_smp_processor_id()) = NULL; - __free_page(svm_data->save_area); - kfree(svm_data); - } -} - -static void svm_hardware_enable(void *garbage) -{ - - struct svm_cpu_data *svm_data; - uint64_t efer; -#ifdef CONFIG_X86_64 - struct desc_ptr gdt_descr; -#else - struct Xgt_desc_struct gdt_descr; -#endif - struct desc_struct *gdt; - int me = raw_smp_processor_id(); - - if (!has_svm()) { - printk(KERN_ERR "svm_cpu_init: err EOPNOTSUPP on %d\n", me); - return; - } - svm_data = per_cpu(svm_data, me); - - if (!svm_data) { - printk(KERN_ERR "svm_cpu_init: svm_data is NULL on %d\n", - me); - return; - } - - svm_data->asid_generation = 1; - svm_data->max_asid = cpuid_ebx(SVM_CPUID_FUNC) - 1; - svm_data->next_asid = svm_data->max_asid + 1; - svm_features = cpuid_edx(SVM_CPUID_FUNC); - - asm volatile ( "sgdt %0" : "=m"(gdt_descr) ); - gdt = (struct desc_struct *)gdt_descr.address; - svm_data->tss_desc = (struct kvm_ldttss_desc *)(gdt + GDT_ENTRY_TSS); - - rdmsrl(MSR_EFER, efer); - wrmsrl(MSR_EFER, efer | MSR_EFER_SVME_MASK); - - wrmsrl(MSR_VM_HSAVE_PA, - page_to_pfn(svm_data->save_area) << PAGE_SHIFT); -} - -static int svm_cpu_init(int cpu) -{ - struct svm_cpu_data *svm_data; - int r; - - svm_data = kzalloc(sizeof(struct svm_cpu_data), GFP_KERNEL); - if (!svm_data) - return -ENOMEM; - svm_data->cpu = cpu; - svm_data->save_area = alloc_page(GFP_KERNEL); - r = -ENOMEM; - if (!svm_data->save_area) - goto err_1; - - per_cpu(svm_data, cpu) = svm_data; - - return 0; - -err_1: - kfree(svm_data); - return r; - -} - -static void set_msr_interception(u32 *msrpm, unsigned msr, - int read, int write) -{ - int i; - - for (i = 0; i < NUM_MSR_MAPS; i++) { - if (msr >= msrpm_ranges[i] && - msr < msrpm_ranges[i] + MSRS_IN_RANGE) { - u32 msr_offset = (i * MSRS_IN_RANGE + msr - - msrpm_ranges[i]) * 2; - - u32 *base = msrpm + (msr_offset / 32); - u32 msr_shift = msr_offset % 32; - u32 mask = ((write) ? 0 : 2) | ((read) ? 0 : 1); - *base = (*base & ~(0x3 << msr_shift)) | - (mask << msr_shift); - return; - } - } - BUG(); -} - -static __init int svm_hardware_setup(void) -{ - int cpu; - struct page *iopm_pages; - struct page *msrpm_pages; - void *iopm_va, *msrpm_va; - int r; - - iopm_pages = alloc_pages(GFP_KERNEL, IOPM_ALLOC_ORDER); - - if (!iopm_pages) - return -ENOMEM; - - iopm_va = page_address(iopm_pages); - memset(iopm_va, 0xff, PAGE_SIZE * (1 << IOPM_ALLOC_ORDER)); - clear_bit(0x80, iopm_va); /* allow direct access to PC debug port */ - iopm_base = page_to_pfn(iopm_pages) << PAGE_SHIFT; - - - msrpm_pages = alloc_pages(GFP_KERNEL, MSRPM_ALLOC_ORDER); - - r = -ENOMEM; - if (!msrpm_pages) - goto err_1; - - msrpm_va = page_address(msrpm_pages); - memset(msrpm_va, 0xff, PAGE_SIZE * (1 << MSRPM_ALLOC_ORDER)); - msrpm_base = page_to_pfn(msrpm_pages) << PAGE_SHIFT; - -#ifdef CONFIG_X86_64 - set_msr_interception(msrpm_va, MSR_GS_BASE, 1, 1); - set_msr_interception(msrpm_va, MSR_FS_BASE, 1, 1); - set_msr_interception(msrpm_va, MSR_KERNEL_GS_BASE, 1, 1); - set_msr_interception(msrpm_va, MSR_LSTAR, 1, 1); - set_msr_interception(msrpm_va, MSR_CSTAR, 1, 1); - set_msr_interception(msrpm_va, MSR_SYSCALL_MASK, 1, 1); -#endif - set_msr_interception(msrpm_va, MSR_K6_STAR, 1, 1); - set_msr_interception(msrpm_va, MSR_IA32_SYSENTER_CS, 1, 1); - set_msr_interception(msrpm_va, MSR_IA32_SYSENTER_ESP, 1, 1); - set_msr_interception(msrpm_va, MSR_IA32_SYSENTER_EIP, 1, 1); - - for_each_online_cpu(cpu) { - r = svm_cpu_init(cpu); - if (r) - goto err_2; - } - return 0; - -err_2: - __free_pages(msrpm_pages, MSRPM_ALLOC_ORDER); - msrpm_base = 0; -err_1: - __free_pages(iopm_pages, IOPM_ALLOC_ORDER); - iopm_base = 0; - return r; -} - -static __exit void svm_hardware_unsetup(void) -{ - __free_pages(pfn_to_page(msrpm_base >> PAGE_SHIFT), MSRPM_ALLOC_ORDER); - __free_pages(pfn_to_page(iopm_base >> PAGE_SHIFT), IOPM_ALLOC_ORDER); - iopm_base = msrpm_base = 0; -} - -static void init_seg(struct vmcb_seg *seg) -{ - seg->selector = 0; - seg->attrib = SVM_SELECTOR_P_MASK | SVM_SELECTOR_S_MASK | - SVM_SELECTOR_WRITE_MASK; /* Read/Write Data Segment */ - seg->limit = 0xffff; - seg->base = 0; -} - -static void init_sys_seg(struct vmcb_seg *seg, uint32_t type) -{ - seg->selector = 0; - seg->attrib = SVM_SELECTOR_P_MASK | type; - seg->limit = 0xffff; - seg->base = 0; -} - -static void init_vmcb(struct vmcb *vmcb) -{ - struct vmcb_control_area *control = &vmcb->control; - struct vmcb_save_area *save = &vmcb->save; - - control->intercept_cr_read = INTERCEPT_CR0_MASK | - INTERCEPT_CR3_MASK | - INTERCEPT_CR4_MASK; - - control->intercept_cr_write = INTERCEPT_CR0_MASK | - INTERCEPT_CR3_MASK | - INTERCEPT_CR4_MASK; - - control->intercept_dr_read = INTERCEPT_DR0_MASK | - INTERCEPT_DR1_MASK | - INTERCEPT_DR2_MASK | - INTERCEPT_DR3_MASK; - - control->intercept_dr_write = INTERCEPT_DR0_MASK | - INTERCEPT_DR1_MASK | - INTERCEPT_DR2_MASK | - INTERCEPT_DR3_MASK | - INTERCEPT_DR5_MASK | - INTERCEPT_DR7_MASK; - - control->intercept_exceptions = 1 << PF_VECTOR; - - - control->intercept = (1ULL << INTERCEPT_INTR) | - (1ULL << INTERCEPT_NMI) | - (1ULL << INTERCEPT_SMI) | - /* - * selective cr0 intercept bug? - * 0: 0f 22 d8 mov %eax,%cr3 - * 3: 0f 20 c0 mov %cr0,%eax - * 6: 0d 00 00 00 80 or $0x80000000,%eax - * b: 0f 22 c0 mov %eax,%cr0 - * set cr3 ->interception - * get cr0 ->interception - * set cr0 -> no interception - */ - /* (1ULL << INTERCEPT_SELECTIVE_CR0) | */ - (1ULL << INTERCEPT_CPUID) | - (1ULL << INTERCEPT_INVD) | - (1ULL << INTERCEPT_HLT) | - (1ULL << INTERCEPT_INVLPGA) | - (1ULL << INTERCEPT_IOIO_PROT) | - (1ULL << INTERCEPT_MSR_PROT) | - (1ULL << INTERCEPT_TASK_SWITCH) | - (1ULL << INTERCEPT_SHUTDOWN) | - (1ULL << INTERCEPT_VMRUN) | - (1ULL << INTERCEPT_VMMCALL) | - (1ULL << INTERCEPT_VMLOAD) | - (1ULL << INTERCEPT_VMSAVE) | - (1ULL << INTERCEPT_STGI) | - (1ULL << INTERCEPT_CLGI) | - (1ULL << INTERCEPT_SKINIT) | - (1ULL << INTERCEPT_WBINVD) | - (1ULL << INTERCEPT_MONITOR) | - (1ULL << INTERCEPT_MWAIT); - - control->iopm_base_pa = iopm_base; - control->msrpm_base_pa = msrpm_base; - control->tsc_offset = 0; - control->int_ctl = V_INTR_MASKING_MASK; - - init_seg(&save->es); - init_seg(&save->ss); - init_seg(&save->ds); - init_seg(&save->fs); - init_seg(&save->gs); - - save->cs.selector = 0xf000; - /* Executable/Readable Code Segment */ - save->cs.attrib = SVM_SELECTOR_READ_MASK | SVM_SELECTOR_P_MASK | - SVM_SELECTOR_S_MASK | SVM_SELECTOR_CODE_MASK; - save->cs.limit = 0xffff; - /* - * cs.base should really be 0xffff0000, but vmx can't handle that, so - * be consistent with it. - * - * Replace when we have real mode working for vmx. - */ - save->cs.base = 0xf0000; - - save->gdtr.limit = 0xffff; - save->idtr.limit = 0xffff; - - init_sys_seg(&save->ldtr, SEG_TYPE_LDT); - init_sys_seg(&save->tr, SEG_TYPE_BUSY_TSS16); - - save->efer = MSR_EFER_SVME_MASK; - - save->dr6 = 0xffff0ff0; - save->dr7 = 0x400; - save->rflags = 2; - save->rip = 0x0000fff0; - - /* - * cr0 val on cpu init should be 0x60000010, we enable cpu - * cache by default. the orderly way is to enable cache in bios. - */ - save->cr0 = 0x00000010 | X86_CR0_PG | X86_CR0_WP; - save->cr4 = X86_CR4_PAE; - /* rdx = ?? */ -} - -static void svm_vcpu_reset(struct kvm_vcpu *vcpu) -{ - struct vcpu_svm *svm = to_svm(vcpu); - - init_vmcb(svm->vmcb); - - if (vcpu->vcpu_id != 0) { - svm->vmcb->save.rip = 0; - svm->vmcb->save.cs.base = svm->vcpu.sipi_vector << 12; - svm->vmcb->save.cs.selector = svm->vcpu.sipi_vector << 8; - } -} - -static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id) -{ - struct vcpu_svm *svm; - struct page *page; - int err; - - svm = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL); - if (!svm) { - err = -ENOMEM; - goto out; - } - - err = kvm_vcpu_init(&svm->vcpu, kvm, id); - if (err) - goto free_svm; - - if (irqchip_in_kernel(kvm)) { - err = kvm_create_lapic(&svm->vcpu); - if (err < 0) - goto free_svm; - } - - page = alloc_page(GFP_KERNEL); - if (!page) { - err = -ENOMEM; - goto uninit; - } - - svm->vmcb = page_address(page); - clear_page(svm->vmcb); - svm->vmcb_pa = page_to_pfn(page) << PAGE_SHIFT; - svm->asid_generation = 0; - memset(svm->db_regs, 0, sizeof(svm->db_regs)); - init_vmcb(svm->vmcb); - - fx_init(&svm->vcpu); - svm->vcpu.fpu_active = 1; - svm->vcpu.apic_base = 0xfee00000 | MSR_IA32_APICBASE_ENABLE; - if (svm->vcpu.vcpu_id == 0) - svm->vcpu.apic_base |= MSR_IA32_APICBASE_BSP; - - return &svm->vcpu; - -uninit: - kvm_vcpu_uninit(&svm->vcpu); -free_svm: - kmem_cache_free(kvm_vcpu_cache, svm); -out: - return ERR_PTR(err); -} - -static void svm_free_vcpu(struct kvm_vcpu *vcpu) -{ - struct vcpu_svm *svm = to_svm(vcpu); - - __free_page(pfn_to_page(svm->vmcb_pa >> PAGE_SHIFT)); - kvm_vcpu_uninit(vcpu); - kmem_cache_free(kvm_vcpu_cache, svm); -} - -static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu) -{ - struct vcpu_svm *svm = to_svm(vcpu); - int i; - - if (unlikely(cpu != vcpu->cpu)) { - u64 tsc_this, delta; - - /* - * Make sure that the guest sees a monotonically - * increasing TSC. - */ - rdtscll(tsc_this); - delta = vcpu->host_tsc - tsc_this; - svm->vmcb->control.tsc_offset += delta; - vcpu->cpu = cpu; - kvm_migrate_apic_timer(vcpu); - } - - for (i = 0; i < NR_HOST_SAVE_USER_MSRS; i++) - rdmsrl(host_save_user_msrs[i], svm->host_user_msrs[i]); -} - -static void svm_vcpu_put(struct kvm_vcpu *vcpu) -{ - struct vcpu_svm *svm = to_svm(vcpu); - int i; - - for (i = 0; i < NR_HOST_SAVE_USER_MSRS; i++) - wrmsrl(host_save_user_msrs[i], svm->host_user_msrs[i]); - - rdtscll(vcpu->host_tsc); - kvm_put_guest_fpu(vcpu); -} - -static void svm_vcpu_decache(struct kvm_vcpu *vcpu) -{ -} - -static void svm_cache_regs(struct kvm_vcpu *vcpu) -{ - struct vcpu_svm *svm = to_svm(vcpu); - - vcpu->regs[VCPU_REGS_RAX] = svm->vmcb->save.rax; - vcpu->regs[VCPU_REGS_RSP] = svm->vmcb->save.rsp; - vcpu->rip = svm->vmcb->save.rip; -} - -static void svm_decache_regs(struct kvm_vcpu *vcpu) -{ - struct vcpu_svm *svm = to_svm(vcpu); - svm->vmcb->save.rax = vcpu->regs[VCPU_REGS_RAX]; - svm->vmcb->save.rsp = vcpu->regs[VCPU_REGS_RSP]; - svm->vmcb->save.rip = vcpu->rip; -} - -static unsigned long svm_get_rflags(struct kvm_vcpu *vcpu) -{ - return to_svm(vcpu)->vmcb->save.rflags; -} - -static void svm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags) -{ - to_svm(vcpu)->vmcb->save.rflags = rflags; -} - -static struct vmcb_seg *svm_seg(struct kvm_vcpu *vcpu, int seg) -{ - struct vmcb_save_area *save = &to_svm(vcpu)->vmcb->save; - - switch (seg) { - case VCPU_SREG_CS: return &save->cs; - case VCPU_SREG_DS: return &save->ds; - case VCPU_SREG_ES: return &save->es; - case VCPU_SREG_FS: return &save->fs; - case VCPU_SREG_GS: return &save->gs; - case VCPU_SREG_SS: return &save->ss; - case VCPU_SREG_TR: return &save->tr; - case VCPU_SREG_LDTR: return &save->ldtr; - } - BUG(); - return NULL; -} - -static u64 svm_get_segment_base(struct kvm_vcpu *vcpu, int seg) -{ - struct vmcb_seg *s = svm_seg(vcpu, seg); - - return s->base; -} - -static void svm_get_segment(struct kvm_vcpu *vcpu, - struct kvm_segment *var, int seg) -{ - struct vmcb_seg *s = svm_seg(vcpu, seg); - - var->base = s->base; - var->limit = s->limit; - var->selector = s->selector; - var->type = s->attrib & SVM_SELECTOR_TYPE_MASK; - var->s = (s->attrib >> SVM_SELECTOR_S_SHIFT) & 1; - var->dpl = (s->attrib >> SVM_SELECTOR_DPL_SHIFT) & 3; - var->present = (s->attrib >> SVM_SELECTOR_P_SHIFT) & 1; - var->avl = (s->attrib >> SVM_SELECTOR_AVL_SHIFT) & 1; - var->l = (s->attrib >> SVM_SELECTOR_L_SHIFT) & 1; - var->db = (s->attrib >> SVM_SELECTOR_DB_SHIFT) & 1; - var->g = (s->attrib >> SVM_SELECTOR_G_SHIFT) & 1; - var->unusable = !var->present; -} - -static void svm_get_idt(struct kvm_vcpu *vcpu, struct descriptor_table *dt) -{ - struct vcpu_svm *svm = to_svm(vcpu); - - dt->limit = svm->vmcb->save.idtr.limit; - dt->base = svm->vmcb->save.idtr.base; -} - -static void svm_set_idt(struct kvm_vcpu *vcpu, struct descriptor_table *dt) -{ - struct vcpu_svm *svm = to_svm(vcpu); - - svm->vmcb->save.idtr.limit = dt->limit; - svm->vmcb->save.idtr.base = dt->base ; -} - -static void svm_get_gdt(struct kvm_vcpu *vcpu, struct descriptor_table *dt) -{ - struct vcpu_svm *svm = to_svm(vcpu); - - dt->limit = svm->vmcb->save.gdtr.limit; - dt->base = svm->vmcb->save.gdtr.base; -} - -static void svm_set_gdt(struct kvm_vcpu *vcpu, struct descriptor_table *dt) -{ - struct vcpu_svm *svm = to_svm(vcpu); - - svm->vmcb->save.gdtr.limit = dt->limit; - svm->vmcb->save.gdtr.base = dt->base ; -} - -static void svm_decache_cr4_guest_bits(struct kvm_vcpu *vcpu) -{ -} - -static void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) -{ - struct vcpu_svm *svm = to_svm(vcpu); - -#ifdef CONFIG_X86_64 - if (vcpu->shadow_efer & KVM_EFER_LME) { - if (!is_paging(vcpu) && (cr0 & X86_CR0_PG)) { - vcpu->shadow_efer |= KVM_EFER_LMA; - svm->vmcb->save.efer |= KVM_EFER_LMA | KVM_EFER_LME; - } - - if (is_paging(vcpu) && !(cr0 & X86_CR0_PG) ) { - vcpu->shadow_efer &= ~KVM_EFER_LMA; - svm->vmcb->save.efer &= ~(KVM_EFER_LMA | KVM_EFER_LME); - } - } -#endif - if ((vcpu->cr0 & X86_CR0_TS) && !(cr0 & X86_CR0_TS)) { - svm->vmcb->control.intercept_exceptions &= ~(1 << NM_VECTOR); - vcpu->fpu_active = 1; - } - - vcpu->cr0 = cr0; - cr0 |= X86_CR0_PG | X86_CR0_WP; - cr0 &= ~(X86_CR0_CD | X86_CR0_NW); - svm->vmcb->save.cr0 = cr0; -} - -static void svm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) -{ - vcpu->cr4 = cr4; - to_svm(vcpu)->vmcb->save.cr4 = cr4 | X86_CR4_PAE; -} - -static void svm_set_segment(struct kvm_vcpu *vcpu, - struct kvm_segment *var, int seg) -{ - struct vcpu_svm *svm = to_svm(vcpu); - struct vmcb_seg *s = svm_seg(vcpu, seg); - - s->base = var->base; - s->limit = var->limit; - s->selector = var->selector; - if (var->unusable) - s->attrib = 0; - else { - s->attrib = (var->type & SVM_SELECTOR_TYPE_MASK); - s->attrib |= (var->s & 1) << SVM_SELECTOR_S_SHIFT; - s->attrib |= (var->dpl & 3) << SVM_SELECTOR_DPL_SHIFT; - s->attrib |= (var->present & 1) << SVM_SELECTOR_P_SHIFT; - s->attrib |= (var->avl & 1) << SVM_SELECTOR_AVL_SHIFT; - s->attrib |= (var->l & 1) << SVM_SELECTOR_L_SHIFT; - s->attrib |= (var->db & 1) << SVM_SELECTOR_DB_SHIFT; - s->attrib |= (var->g & 1) << SVM_SELECTOR_G_SHIFT; - } - if (seg == VCPU_SREG_CS) - svm->vmcb->save.cpl - = (svm->vmcb->save.cs.attrib - >> SVM_SELECTOR_DPL_SHIFT) & 3; - -} - -/* FIXME: - - svm(vcpu)->vmcb->control.int_ctl &= ~V_TPR_MASK; - svm(vcpu)->vmcb->control.int_ctl |= (sregs->cr8 & V_TPR_MASK); - -*/ - -static int svm_guest_debug(struct kvm_vcpu *vcpu, struct kvm_debug_guest *dbg) -{ - return -EOPNOTSUPP; -} - -static int svm_get_irq(struct kvm_vcpu *vcpu) -{ - struct vcpu_svm *svm = to_svm(vcpu); - u32 exit_int_info = svm->vmcb->control.exit_int_info; - - if (is_external_interrupt(exit_int_info)) - return exit_int_info & SVM_EVTINJ_VEC_MASK; - return -1; -} - -static void load_host_msrs(struct kvm_vcpu *vcpu) -{ -#ifdef CONFIG_X86_64 - wrmsrl(MSR_GS_BASE, to_svm(vcpu)->host_gs_base); -#endif -} - -static void save_host_msrs(struct kvm_vcpu *vcpu) -{ -#ifdef CONFIG_X86_64 - rdmsrl(MSR_GS_BASE, to_svm(vcpu)->host_gs_base); -#endif -} - -static void new_asid(struct vcpu_svm *svm, struct svm_cpu_data *svm_data) -{ - if (svm_data->next_asid > svm_data->max_asid) { - ++svm_data->asid_generation; - svm_data->next_asid = 1; - svm->vmcb->control.tlb_ctl = TLB_CONTROL_FLUSH_ALL_ASID; - } - - svm->vcpu.cpu = svm_data->cpu; - svm->asid_generation = svm_data->asid_generation; - svm->vmcb->control.asid = svm_data->next_asid++; -} - -static unsigned long svm_get_dr(struct kvm_vcpu *vcpu, int dr) -{ - return to_svm(vcpu)->db_regs[dr]; -} - -static void svm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long value, - int *exception) -{ - struct vcpu_svm *svm = to_svm(vcpu); - - *exception = 0; - - if (svm->vmcb->save.dr7 & DR7_GD_MASK) { - svm->vmcb->save.dr7 &= ~DR7_GD_MASK; - svm->vmcb->save.dr6 |= DR6_BD_MASK; - *exception = DB_VECTOR; - return; - } - - switch (dr) { - case 0 ... 3: - svm->db_regs[dr] = value; - return; - case 4 ... 5: - if (vcpu->cr4 & X86_CR4_DE) { - *exception = UD_VECTOR; - return; - } - case 7: { - if (value & ~((1ULL << 32) - 1)) { - *exception = GP_VECTOR; - return; - } - svm->vmcb->save.dr7 = value; - return; - } - default: - printk(KERN_DEBUG "%s: unexpected dr %u\n", - __FUNCTION__, dr); - *exception = UD_VECTOR; - return; - } -} - -static int pf_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) -{ - u32 exit_int_info = svm->vmcb->control.exit_int_info; - struct kvm *kvm = svm->vcpu.kvm; - u64 fault_address; - u32 error_code; - enum emulation_result er; - int r; - - if (!irqchip_in_kernel(kvm) && - is_external_interrupt(exit_int_info)) - push_irq(&svm->vcpu, exit_int_info & SVM_EVTINJ_VEC_MASK); - - mutex_lock(&kvm->lock); - - fault_address = svm->vmcb->control.exit_info_2; - error_code = svm->vmcb->control.exit_info_1; - r = kvm_mmu_page_fault(&svm->vcpu, fault_address, error_code); - if (r < 0) { - mutex_unlock(&kvm->lock); - return r; - } - if (!r) { - mutex_unlock(&kvm->lock); - return 1; - } - er = emulate_instruction(&svm->vcpu, kvm_run, fault_address, - error_code); - mutex_unlock(&kvm->lock); - - switch (er) { - case EMULATE_DONE: - return 1; - case EMULATE_DO_MMIO: - ++svm->vcpu.stat.mmio_exits; - return 0; - case EMULATE_FAIL: - kvm_report_emulation_failure(&svm->vcpu, "pagetable"); - break; - default: - BUG(); - } - - kvm_run->exit_reason = KVM_EXIT_UNKNOWN; - return 0; -} - -static int nm_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) -{ - svm->vmcb->control.intercept_exceptions &= ~(1 << NM_VECTOR); - if (!(svm->vcpu.cr0 & X86_CR0_TS)) - svm->vmcb->save.cr0 &= ~X86_CR0_TS; - svm->vcpu.fpu_active = 1; - - return 1; -} - -static int shutdown_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) -{ - /* - * VMCB is undefined after a SHUTDOWN intercept - * so reinitialize it. - */ - clear_page(svm->vmcb); - init_vmcb(svm->vmcb); - - kvm_run->exit_reason = KVM_EXIT_SHUTDOWN; - return 0; -} - -static int io_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) -{ - u32 io_info = svm->vmcb->control.exit_info_1; //address size bug? - int size, down, in, string, rep; - unsigned port; - - ++svm->vcpu.stat.io_exits; - - svm->next_rip = svm->vmcb->control.exit_info_2; - - string = (io_info & SVM_IOIO_STR_MASK) != 0; - - if (string) { - if (emulate_instruction(&svm->vcpu, kvm_run, 0, 0) == EMULATE_DO_MMIO) - return 0; - return 1; - } - - in = (io_info & SVM_IOIO_TYPE_MASK) != 0; - port = io_info >> 16; - size = (io_info & SVM_IOIO_SIZE_MASK) >> SVM_IOIO_SIZE_SHIFT; - rep = (io_info & SVM_IOIO_REP_MASK) != 0; - down = (svm->vmcb->save.rflags & X86_EFLAGS_DF) != 0; - - return kvm_emulate_pio(&svm->vcpu, kvm_run, in, size, port); -} - -static int nop_on_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) -{ - return 1; -} - -static int halt_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) -{ - svm->next_rip = svm->vmcb->save.rip + 1; - skip_emulated_instruction(&svm->vcpu); - return kvm_emulate_halt(&svm->vcpu); -} - -static int vmmcall_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) -{ - svm->next_rip = svm->vmcb->save.rip + 3; - skip_emulated_instruction(&svm->vcpu); - return kvm_hypercall(&svm->vcpu, kvm_run); -} - -static int invalid_op_interception(struct vcpu_svm *svm, - struct kvm_run *kvm_run) -{ - inject_ud(&svm->vcpu); - return 1; -} - -static int task_switch_interception(struct vcpu_svm *svm, - struct kvm_run *kvm_run) -{ - pr_unimpl(&svm->vcpu, "%s: task switch is unsupported\n", __FUNCTION__); - kvm_run->exit_reason = KVM_EXIT_UNKNOWN; - return 0; -} - -static int cpuid_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) -{ - svm->next_rip = svm->vmcb->save.rip + 2; - kvm_emulate_cpuid(&svm->vcpu); - return 1; -} - -static int emulate_on_interception(struct vcpu_svm *svm, - struct kvm_run *kvm_run) -{ - if (emulate_instruction(&svm->vcpu, NULL, 0, 0) != EMULATE_DONE) - pr_unimpl(&svm->vcpu, "%s: failed\n", __FUNCTION__); - return 1; -} - -static int svm_get_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 *data) -{ - struct vcpu_svm *svm = to_svm(vcpu); - - switch (ecx) { - case MSR_IA32_TIME_STAMP_COUNTER: { - u64 tsc; - - rdtscll(tsc); - *data = svm->vmcb->control.tsc_offset + tsc; - break; - } - case MSR_K6_STAR: - *data = svm->vmcb->save.star; - break; -#ifdef CONFIG_X86_64 - case MSR_LSTAR: - *data = svm->vmcb->save.lstar; - break; - case MSR_CSTAR: - *data = svm->vmcb->save.cstar; - break; - case MSR_KERNEL_GS_BASE: - *data = svm->vmcb->save.kernel_gs_base; - break; - case MSR_SYSCALL_MASK: - *data = svm->vmcb->save.sfmask; - break; -#endif - case MSR_IA32_SYSENTER_CS: - *data = svm->vmcb->save.sysenter_cs; - break; - case MSR_IA32_SYSENTER_EIP: - *data = svm->vmcb->save.sysenter_eip; - break; - case MSR_IA32_SYSENTER_ESP: - *data = svm->vmcb->save.sysenter_esp; - break; - default: - return kvm_get_msr_common(vcpu, ecx, data); - } - return 0; -} - -static int rdmsr_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) -{ - u32 ecx = svm->vcpu.regs[VCPU_REGS_RCX]; - u64 data; - - if (svm_get_msr(&svm->vcpu, ecx, &data)) - svm_inject_gp(&svm->vcpu, 0); - else { - svm->vmcb->save.rax = data & 0xffffffff; - svm->vcpu.regs[VCPU_REGS_RDX] = data >> 32; - svm->next_rip = svm->vmcb->save.rip + 2; - skip_emulated_instruction(&svm->vcpu); - } - return 1; -} - -static int svm_set_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 data) -{ - struct vcpu_svm *svm = to_svm(vcpu); - - switch (ecx) { - case MSR_IA32_TIME_STAMP_COUNTER: { - u64 tsc; - - rdtscll(tsc); - svm->vmcb->control.tsc_offset = data - tsc; - break; - } - case MSR_K6_STAR: - svm->vmcb->save.star = data; - break; -#ifdef CONFIG_X86_64 - case MSR_LSTAR: - svm->vmcb->save.lstar = data; - break; - case MSR_CSTAR: - svm->vmcb->save.cstar = data; - break; - case MSR_KERNEL_GS_BASE: - svm->vmcb->save.kernel_gs_base = data; - break; - case MSR_SYSCALL_MASK: - svm->vmcb->save.sfmask = data; - break; -#endif - case MSR_IA32_SYSENTER_CS: - svm->vmcb->save.sysenter_cs = data; - break; - case MSR_IA32_SYSENTER_EIP: - svm->vmcb->save.sysenter_eip = data; - break; - case MSR_IA32_SYSENTER_ESP: - svm->vmcb->save.sysenter_esp = data; - break; - default: - return kvm_set_msr_common(vcpu, ecx, data); - } - return 0; -} - -static int wrmsr_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) -{ - u32 ecx = svm->vcpu.regs[VCPU_REGS_RCX]; - u64 data = (svm->vmcb->save.rax & -1u) - | ((u64)(svm->vcpu.regs[VCPU_REGS_RDX] & -1u) << 32); - svm->next_rip = svm->vmcb->save.rip + 2; - if (svm_set_msr(&svm->vcpu, ecx, data)) - svm_inject_gp(&svm->vcpu, 0); - else - skip_emulated_instruction(&svm->vcpu); - return 1; -} - -static int msr_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) -{ - if (svm->vmcb->control.exit_info_1) - return wrmsr_interception(svm, kvm_run); - else - return rdmsr_interception(svm, kvm_run); -} - -static int interrupt_window_interception(struct vcpu_svm *svm, - struct kvm_run *kvm_run) -{ - svm->vmcb->control.intercept &= ~(1ULL << INTERCEPT_VINTR); - svm->vmcb->control.int_ctl &= ~V_IRQ_MASK; - /* - * If the user space waits to inject interrupts, exit as soon as - * possible - */ - if (kvm_run->request_interrupt_window && - !svm->vcpu.irq_summary) { - ++svm->vcpu.stat.irq_window_exits; - kvm_run->exit_reason = KVM_EXIT_IRQ_WINDOW_OPEN; - return 0; - } - - return 1; -} - -static int (*svm_exit_handlers[])(struct vcpu_svm *svm, - struct kvm_run *kvm_run) = { - [SVM_EXIT_READ_CR0] = emulate_on_interception, - [SVM_EXIT_READ_CR3] = emulate_on_interception, - [SVM_EXIT_READ_CR4] = emulate_on_interception, - /* for now: */ - [SVM_EXIT_WRITE_CR0] = emulate_on_interception, - [SVM_EXIT_WRITE_CR3] = emulate_on_interception, - [SVM_EXIT_WRITE_CR4] = emulate_on_interception, - [SVM_EXIT_READ_DR0] = emulate_on_interception, - [SVM_EXIT_READ_DR1] = emulate_on_interception, - [SVM_EXIT_READ_DR2] = emulate_on_interception, - [SVM_EXIT_READ_DR3] = emulate_on_interception, - [SVM_EXIT_WRITE_DR0] = emulate_on_interception, - [SVM_EXIT_WRITE_DR1] = emulate_on_interception, - [SVM_EXIT_WRITE_DR2] = emulate_on_interception, - [SVM_EXIT_WRITE_DR3] = emulate_on_interception, - [SVM_EXIT_WRITE_DR5] = emulate_on_interception, - [SVM_EXIT_WRITE_DR7] = emulate_on_interception, - [SVM_EXIT_EXCP_BASE + PF_VECTOR] = pf_interception, - [SVM_EXIT_EXCP_BASE + NM_VECTOR] = nm_interception, - [SVM_EXIT_INTR] = nop_on_interception, - [SVM_EXIT_NMI] = nop_on_interception, - [SVM_EXIT_SMI] = nop_on_interception, - [SVM_EXIT_INIT] = nop_on_interception, - [SVM_EXIT_VINTR] = interrupt_window_interception, - /* [SVM_EXIT_CR0_SEL_WRITE] = emulate_on_interception, */ - [SVM_EXIT_CPUID] = cpuid_interception, - [SVM_EXIT_INVD] = emulate_on_interception, - [SVM_EXIT_HLT] = halt_interception, - [SVM_EXIT_INVLPG] = emulate_on_interception, - [SVM_EXIT_INVLPGA] = invalid_op_interception, - [SVM_EXIT_IOIO] = io_interception, - [SVM_EXIT_MSR] = msr_interception, - [SVM_EXIT_TASK_SWITCH] = task_switch_interception, - [SVM_EXIT_SHUTDOWN] = shutdown_interception, - [SVM_EXIT_VMRUN] = invalid_op_interception, - [SVM_EXIT_VMMCALL] = vmmcall_interception, - [SVM_EXIT_VMLOAD] = invalid_op_interception, - [SVM_EXIT_VMSAVE] = invalid_op_interception, - [SVM_EXIT_STGI] = invalid_op_interception, - [SVM_EXIT_CLGI] = invalid_op_interception, - [SVM_EXIT_SKINIT] = invalid_op_interception, - [SVM_EXIT_WBINVD] = emulate_on_interception, - [SVM_EXIT_MONITOR] = invalid_op_interception, - [SVM_EXIT_MWAIT] = invalid_op_interception, -}; - - -static int handle_exit(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) -{ - struct vcpu_svm *svm = to_svm(vcpu); - u32 exit_code = svm->vmcb->control.exit_code; - - kvm_reput_irq(svm); - - if (svm->vmcb->control.exit_code == SVM_EXIT_ERR) { - kvm_run->exit_reason = KVM_EXIT_FAIL_ENTRY; - kvm_run->fail_entry.hardware_entry_failure_reason - = svm->vmcb->control.exit_code; - return 0; - } - - if (is_external_interrupt(svm->vmcb->control.exit_int_info) && - exit_code != SVM_EXIT_EXCP_BASE + PF_VECTOR) - printk(KERN_ERR "%s: unexpected exit_ini_info 0x%x " - "exit_code 0x%x\n", - __FUNCTION__, svm->vmcb->control.exit_int_info, - exit_code); - - if (exit_code >= ARRAY_SIZE(svm_exit_handlers) - || svm_exit_handlers[exit_code] == 0) { - kvm_run->exit_reason = KVM_EXIT_UNKNOWN; - kvm_run->hw.hardware_exit_reason = exit_code; - return 0; - } - - return svm_exit_handlers[exit_code](svm, kvm_run); -} - -static void reload_tss(struct kvm_vcpu *vcpu) -{ - int cpu = raw_smp_processor_id(); - - struct svm_cpu_data *svm_data = per_cpu(svm_data, cpu); - svm_data->tss_desc->type = 9; //available 32/64-bit TSS - load_TR_desc(); -} - -static void pre_svm_run(struct vcpu_svm *svm) -{ - int cpu = raw_smp_processor_id(); - - struct svm_cpu_data *svm_data = per_cpu(svm_data, cpu); - - svm->vmcb->control.tlb_ctl = TLB_CONTROL_DO_NOTHING; - if (svm->vcpu.cpu != cpu || - svm->asid_generation != svm_data->asid_generation) - new_asid(svm, svm_data); -} - - -static inline void svm_inject_irq(struct vcpu_svm *svm, int irq) -{ - struct vmcb_control_area *control; - - control = &svm->vmcb->control; - control->int_vector = irq; - control->int_ctl &= ~V_INTR_PRIO_MASK; - control->int_ctl |= V_IRQ_MASK | - ((/*control->int_vector >> 4*/ 0xf) << V_INTR_PRIO_SHIFT); -} - -static void svm_set_irq(struct kvm_vcpu *vcpu, int irq) -{ - struct vcpu_svm *svm = to_svm(vcpu); - - svm_inject_irq(svm, irq); -} - -static void svm_intr_assist(struct kvm_vcpu *vcpu) -{ - struct vcpu_svm *svm = to_svm(vcpu); - struct vmcb *vmcb = svm->vmcb; - int intr_vector = -1; - - kvm_inject_pending_timer_irqs(vcpu); - if ((vmcb->control.exit_int_info & SVM_EVTINJ_VALID) && - ((vmcb->control.exit_int_info & SVM_EVTINJ_TYPE_MASK) == 0)) { - intr_vector = vmcb->control.exit_int_info & - SVM_EVTINJ_VEC_MASK; - vmcb->control.exit_int_info = 0; - svm_inject_irq(svm, intr_vector); - return; - } - - if (vmcb->control.int_ctl & V_IRQ_MASK) - return; - - if (!kvm_cpu_has_interrupt(vcpu)) - return; - - if (!(vmcb->save.rflags & X86_EFLAGS_IF) || - (vmcb->control.int_state & SVM_INTERRUPT_SHADOW_MASK) || - (vmcb->control.event_inj & SVM_EVTINJ_VALID)) { - /* unable to deliver irq, set pending irq */ - vmcb->control.intercept |= (1ULL << INTERCEPT_VINTR); - svm_inject_irq(svm, 0x0); - return; - } - /* Okay, we can deliver the interrupt: grab it and update PIC state. */ - intr_vector = kvm_cpu_get_interrupt(vcpu); - svm_inject_irq(svm, intr_vector); - kvm_timer_intr_post(vcpu, intr_vector); -} - -static void kvm_reput_irq(struct vcpu_svm *svm) -{ - struct vmcb_control_area *control = &svm->vmcb->control; - - if ((control->int_ctl & V_IRQ_MASK) - && !irqchip_in_kernel(svm->vcpu.kvm)) { - control->int_ctl &= ~V_IRQ_MASK; - push_irq(&svm->vcpu, control->int_vector); - } - - svm->vcpu.interrupt_window_open = - !(control->int_state & SVM_INTERRUPT_SHADOW_MASK); -} - -static void svm_do_inject_vector(struct vcpu_svm *svm) -{ - struct kvm_vcpu *vcpu = &svm->vcpu; - int word_index = __ffs(vcpu->irq_summary); - int bit_index = __ffs(vcpu->irq_pending[word_index]); - int irq = word_index * BITS_PER_LONG + bit_index; - - clear_bit(bit_index, &vcpu->irq_pending[word_index]); - if (!vcpu->irq_pending[word_index]) - clear_bit(word_index, &vcpu->irq_summary); - svm_inject_irq(svm, irq); -} - -static void do_interrupt_requests(struct kvm_vcpu *vcpu, - struct kvm_run *kvm_run) -{ - struct vcpu_svm *svm = to_svm(vcpu); - struct vmcb_control_area *control = &svm->vmcb->control; - - svm->vcpu.interrupt_window_open = - (!(control->int_state & SVM_INTERRUPT_SHADOW_MASK) && - (svm->vmcb->save.rflags & X86_EFLAGS_IF)); - - if (svm->vcpu.interrupt_window_open && svm->vcpu.irq_summary) - /* - * If interrupts enabled, and not blocked by sti or mov ss. Good. - */ - svm_do_inject_vector(svm); - - /* - * Interrupts blocked. Wait for unblock. - */ - if (!svm->vcpu.interrupt_window_open && - (svm->vcpu.irq_summary || kvm_run->request_interrupt_window)) { - control->intercept |= 1ULL << INTERCEPT_VINTR; - } else - control->intercept &= ~(1ULL << INTERCEPT_VINTR); -} - -static void save_db_regs(unsigned long *db_regs) -{ - asm volatile ("mov %%dr0, %0" : "=r"(db_regs[0])); - asm volatile ("mov %%dr1, %0" : "=r"(db_regs[1])); - asm volatile ("mov %%dr2, %0" : "=r"(db_regs[2])); - asm volatile ("mov %%dr3, %0" : "=r"(db_regs[3])); -} - -static void load_db_regs(unsigned long *db_regs) -{ - asm volatile ("mov %0, %%dr0" : : "r"(db_regs[0])); - asm volatile ("mov %0, %%dr1" : : "r"(db_regs[1])); - asm volatile ("mov %0, %%dr2" : : "r"(db_regs[2])); - asm volatile ("mov %0, %%dr3" : : "r"(db_regs[3])); -} - -static void svm_flush_tlb(struct kvm_vcpu *vcpu) -{ - force_new_asid(vcpu); -} - -static void svm_prepare_guest_switch(struct kvm_vcpu *vcpu) -{ -} - -static void svm_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) -{ - struct vcpu_svm *svm = to_svm(vcpu); - u16 fs_selector; - u16 gs_selector; - u16 ldt_selector; - - pre_svm_run(svm); - - save_host_msrs(vcpu); - fs_selector = read_fs(); - gs_selector = read_gs(); - ldt_selector = read_ldt(); - svm->host_cr2 = kvm_read_cr2(); - svm->host_dr6 = read_dr6(); - svm->host_dr7 = read_dr7(); - svm->vmcb->save.cr2 = vcpu->cr2; - - if (svm->vmcb->save.dr7 & 0xff) { - write_dr7(0); - save_db_regs(svm->host_db_regs); - load_db_regs(svm->db_regs); - } - - clgi(); - - local_irq_enable(); - - asm volatile ( -#ifdef CONFIG_X86_64 - "push %%rbx; push %%rcx; push %%rdx;" - "push %%rsi; push %%rdi; push %%rbp;" - "push %%r8; push %%r9; push %%r10; push %%r11;" - "push %%r12; push %%r13; push %%r14; push %%r15;" -#else - "push %%ebx; push %%ecx; push %%edx;" - "push %%esi; push %%edi; push %%ebp;" -#endif - -#ifdef CONFIG_X86_64 - "mov %c[rbx](%[svm]), %%rbx \n\t" - "mov %c[rcx](%[svm]), %%rcx \n\t" - "mov %c[rdx](%[svm]), %%rdx \n\t" - "mov %c[rsi](%[svm]), %%rsi \n\t" - "mov %c[rdi](%[svm]), %%rdi \n\t" - "mov %c[rbp](%[svm]), %%rbp \n\t" - "mov %c[r8](%[svm]), %%r8 \n\t" - "mov %c[r9](%[svm]), %%r9 \n\t" - "mov %c[r10](%[svm]), %%r10 \n\t" - "mov %c[r11](%[svm]), %%r11 \n\t" - "mov %c[r12](%[svm]), %%r12 \n\t" - "mov %c[r13](%[svm]), %%r13 \n\t" - "mov %c[r14](%[svm]), %%r14 \n\t" - "mov %c[r15](%[svm]), %%r15 \n\t" -#else - "mov %c[rbx](%[svm]), %%ebx \n\t" - "mov %c[rcx](%[svm]), %%ecx \n\t" - "mov %c[rdx](%[svm]), %%edx \n\t" - "mov %c[rsi](%[svm]), %%esi \n\t" - "mov %c[rdi](%[svm]), %%edi \n\t" - "mov %c[rbp](%[svm]), %%ebp \n\t" -#endif - -#ifdef CONFIG_X86_64 - /* Enter guest mode */ - "push %%rax \n\t" - "mov %c[vmcb](%[svm]), %%rax \n\t" - SVM_VMLOAD "\n\t" - SVM_VMRUN "\n\t" - SVM_VMSAVE "\n\t" - "pop %%rax \n\t" -#else - /* Enter guest mode */ - "push %%eax \n\t" - "mov %c[vmcb](%[svm]), %%eax \n\t" - SVM_VMLOAD "\n\t" - SVM_VMRUN "\n\t" - SVM_VMSAVE "\n\t" - "pop %%eax \n\t" -#endif - - /* Save guest registers, load host registers */ -#ifdef CONFIG_X86_64 - "mov %%rbx, %c[rbx](%[svm]) \n\t" - "mov %%rcx, %c[rcx](%[svm]) \n\t" - "mov %%rdx, %c[rdx](%[svm]) \n\t" - "mov %%rsi, %c[rsi](%[svm]) \n\t" - "mov %%rdi, %c[rdi](%[svm]) \n\t" - "mov %%rbp, %c[rbp](%[svm]) \n\t" - "mov %%r8, %c[r8](%[svm]) \n\t" - "mov %%r9, %c[r9](%[svm]) \n\t" - "mov %%r10, %c[r10](%[svm]) \n\t" - "mov %%r11, %c[r11](%[svm]) \n\t" - "mov %%r12, %c[r12](%[svm]) \n\t" - "mov %%r13, %c[r13](%[svm]) \n\t" - "mov %%r14, %c[r14](%[svm]) \n\t" - "mov %%r15, %c[r15](%[svm]) \n\t" - - "pop %%r15; pop %%r14; pop %%r13; pop %%r12;" - "pop %%r11; pop %%r10; pop %%r9; pop %%r8;" - "pop %%rbp; pop %%rdi; pop %%rsi;" - "pop %%rdx; pop %%rcx; pop %%rbx; \n\t" -#else - "mov %%ebx, %c[rbx](%[svm]) \n\t" - "mov %%ecx, %c[rcx](%[svm]) \n\t" - "mov %%edx, %c[rdx](%[svm]) \n\t" - "mov %%esi, %c[rsi](%[svm]) \n\t" - "mov %%edi, %c[rdi](%[svm]) \n\t" - "mov %%ebp, %c[rbp](%[svm]) \n\t" - - "pop %%ebp; pop %%edi; pop %%esi;" - "pop %%edx; pop %%ecx; pop %%ebx; \n\t" -#endif - : - : [svm]"a"(svm), - [vmcb]"i"(offsetof(struct vcpu_svm, vmcb_pa)), - [rbx]"i"(offsetof(struct vcpu_svm,vcpu.regs[VCPU_REGS_RBX])), - [rcx]"i"(offsetof(struct vcpu_svm,vcpu.regs[VCPU_REGS_RCX])), - [rdx]"i"(offsetof(struct vcpu_svm,vcpu.regs[VCPU_REGS_RDX])), - [rsi]"i"(offsetof(struct vcpu_svm,vcpu.regs[VCPU_REGS_RSI])), - [rdi]"i"(offsetof(struct vcpu_svm,vcpu.regs[VCPU_REGS_RDI])), - [rbp]"i"(offsetof(struct vcpu_svm,vcpu.regs[VCPU_REGS_RBP])) -#ifdef CONFIG_X86_64 - ,[r8 ]"i"(offsetof(struct vcpu_svm,vcpu.regs[VCPU_REGS_R8])), - [r9 ]"i"(offsetof(struct vcpu_svm,vcpu.regs[VCPU_REGS_R9 ])), - [r10]"i"(offsetof(struct vcpu_svm,vcpu.regs[VCPU_REGS_R10])), - [r11]"i"(offsetof(struct vcpu_svm,vcpu.regs[VCPU_REGS_R11])), - [r12]"i"(offsetof(struct vcpu_svm,vcpu.regs[VCPU_REGS_R12])), - [r13]"i"(offsetof(struct vcpu_svm,vcpu.regs[VCPU_REGS_R13])), - [r14]"i"(offsetof(struct vcpu_svm,vcpu.regs[VCPU_REGS_R14])), - [r15]"i"(offsetof(struct vcpu_svm,vcpu.regs[VCPU_REGS_R15])) -#endif - : "cc", "memory" ); - - if ((svm->vmcb->save.dr7 & 0xff)) - load_db_regs(svm->host_db_regs); - - vcpu->cr2 = svm->vmcb->save.cr2; - - write_dr6(svm->host_dr6); - write_dr7(svm->host_dr7); - kvm_write_cr2(svm->host_cr2); - - load_fs(fs_selector); - load_gs(gs_selector); - load_ldt(ldt_selector); - load_host_msrs(vcpu); - - reload_tss(vcpu); - - local_irq_disable(); - - stgi(); - - svm->next_rip = 0; -} - -static void svm_set_cr3(struct kvm_vcpu *vcpu, unsigned long root) -{ - struct vcpu_svm *svm = to_svm(vcpu); - - svm->vmcb->save.cr3 = root; - force_new_asid(vcpu); - - if (vcpu->fpu_active) { - svm->vmcb->control.intercept_exceptions |= (1 << NM_VECTOR); - svm->vmcb->save.cr0 |= X86_CR0_TS; - vcpu->fpu_active = 0; - } -} - -static void svm_inject_page_fault(struct kvm_vcpu *vcpu, - unsigned long addr, - uint32_t err_code) -{ - struct vcpu_svm *svm = to_svm(vcpu); - uint32_t exit_int_info = svm->vmcb->control.exit_int_info; - - ++vcpu->stat.pf_guest; - - if (is_page_fault(exit_int_info)) { - - svm->vmcb->control.event_inj_err = 0; - svm->vmcb->control.event_inj = SVM_EVTINJ_VALID | - SVM_EVTINJ_VALID_ERR | - SVM_EVTINJ_TYPE_EXEPT | - DF_VECTOR; - return; - } - vcpu->cr2 = addr; - svm->vmcb->save.cr2 = addr; - svm->vmcb->control.event_inj = SVM_EVTINJ_VALID | - SVM_EVTINJ_VALID_ERR | - SVM_EVTINJ_TYPE_EXEPT | - PF_VECTOR; - svm->vmcb->control.event_inj_err = err_code; -} - - -static int is_disabled(void) -{ - u64 vm_cr; - - rdmsrl(MSR_VM_CR, vm_cr); - if (vm_cr & (1 << SVM_VM_CR_SVM_DISABLE)) - return 1; - - return 0; -} - -static void -svm_patch_hypercall(struct kvm_vcpu *vcpu, unsigned char *hypercall) -{ - /* - * Patch in the VMMCALL instruction: - */ - hypercall[0] = 0x0f; - hypercall[1] = 0x01; - hypercall[2] = 0xd9; - hypercall[3] = 0xc3; -} - -static void svm_check_processor_compat(void *rtn) -{ - *(int *)rtn = 0; -} - -static struct kvm_x86_ops svm_x86_ops = { - .cpu_has_kvm_support = has_svm, - .disabled_by_bios = is_disabled, - .hardware_setup = svm_hardware_setup, - .hardware_unsetup = svm_hardware_unsetup, - .check_processor_compatibility = svm_check_processor_compat, - .hardware_enable = svm_hardware_enable, - .hardware_disable = svm_hardware_disable, - - .vcpu_create = svm_create_vcpu, - .vcpu_free = svm_free_vcpu, - .vcpu_reset = svm_vcpu_reset, - - .prepare_guest_switch = svm_prepare_guest_switch, - .vcpu_load = svm_vcpu_load, - .vcpu_put = svm_vcpu_put, - .vcpu_decache = svm_vcpu_decache, - - .set_guest_debug = svm_guest_debug, - .get_msr = svm_get_msr, - .set_msr = svm_set_msr, - .get_segment_base = svm_get_segment_base, - .get_segment = svm_get_segment, - .set_segment = svm_set_segment, - .get_cs_db_l_bits = kvm_get_cs_db_l_bits, - .decache_cr4_guest_bits = svm_decache_cr4_guest_bits, - .set_cr0 = svm_set_cr0, - .set_cr3 = svm_set_cr3, - .set_cr4 = svm_set_cr4, - .set_efer = svm_set_efer, - .get_idt = svm_get_idt, - .set_idt = svm_set_idt, - .get_gdt = svm_get_gdt, - .set_gdt = svm_set_gdt, - .get_dr = svm_get_dr, - .set_dr = svm_set_dr, - .cache_regs = svm_cache_regs, - .decache_regs = svm_decache_regs, - .get_rflags = svm_get_rflags, - .set_rflags = svm_set_rflags, - - .tlb_flush = svm_flush_tlb, - .inject_page_fault = svm_inject_page_fault, - - .inject_gp = svm_inject_gp, - - .run = svm_vcpu_run, - .handle_exit = handle_exit, - .skip_emulated_instruction = skip_emulated_instruction, - .patch_hypercall = svm_patch_hypercall, - .get_irq = svm_get_irq, - .set_irq = svm_set_irq, - .inject_pending_irq = svm_intr_assist, - .inject_pending_vectors = do_interrupt_requests, -}; - -static int __init svm_init(void) -{ - return kvm_init_x86(&svm_x86_ops, sizeof(struct vcpu_svm), - THIS_MODULE); -} - -static void __exit svm_exit(void) -{ - kvm_exit_x86(); -} - -module_init(svm_init) -module_exit(svm_exit) diff --git a/drivers/kvm/svm.h b/drivers/kvm/svm.h deleted file mode 100644 index 3b1b0f35b6cb..000000000000 --- a/drivers/kvm/svm.h +++ /dev/null @@ -1,324 +0,0 @@ -#ifndef __SVM_H -#define __SVM_H - -enum { - INTERCEPT_INTR, - INTERCEPT_NMI, - INTERCEPT_SMI, - INTERCEPT_INIT, - INTERCEPT_VINTR, - INTERCEPT_SELECTIVE_CR0, - INTERCEPT_STORE_IDTR, - INTERCEPT_STORE_GDTR, - INTERCEPT_STORE_LDTR, - INTERCEPT_STORE_TR, - INTERCEPT_LOAD_IDTR, - INTERCEPT_LOAD_GDTR, - INTERCEPT_LOAD_LDTR, - INTERCEPT_LOAD_TR, - INTERCEPT_RDTSC, - INTERCEPT_RDPMC, - INTERCEPT_PUSHF, - INTERCEPT_POPF, - INTERCEPT_CPUID, - INTERCEPT_RSM, - INTERCEPT_IRET, - INTERCEPT_INTn, - INTERCEPT_INVD, - INTERCEPT_PAUSE, - INTERCEPT_HLT, - INTERCEPT_INVLPG, - INTERCEPT_INVLPGA, - INTERCEPT_IOIO_PROT, - INTERCEPT_MSR_PROT, - INTERCEPT_TASK_SWITCH, - INTERCEPT_FERR_FREEZE, - INTERCEPT_SHUTDOWN, - INTERCEPT_VMRUN, - INTERCEPT_VMMCALL, - INTERCEPT_VMLOAD, - INTERCEPT_VMSAVE, - INTERCEPT_STGI, - INTERCEPT_CLGI, - INTERCEPT_SKINIT, - INTERCEPT_RDTSCP, - INTERCEPT_ICEBP, - INTERCEPT_WBINVD, - INTERCEPT_MONITOR, - INTERCEPT_MWAIT, - INTERCEPT_MWAIT_COND, -}; - - -struct __attribute__ ((__packed__)) vmcb_control_area { - u16 intercept_cr_read; - u16 intercept_cr_write; - u16 intercept_dr_read; - u16 intercept_dr_write; - u32 intercept_exceptions; - u64 intercept; - u8 reserved_1[44]; - u64 iopm_base_pa; - u64 msrpm_base_pa; - u64 tsc_offset; - u32 asid; - u8 tlb_ctl; - u8 reserved_2[3]; - u32 int_ctl; - u32 int_vector; - u32 int_state; - u8 reserved_3[4]; - u32 exit_code; - u32 exit_code_hi; - u64 exit_info_1; - u64 exit_info_2; - u32 exit_int_info; - u32 exit_int_info_err; - u64 nested_ctl; - u8 reserved_4[16]; - u32 event_inj; - u32 event_inj_err; - u64 nested_cr3; - u64 lbr_ctl; - u8 reserved_5[832]; -}; - - -#define TLB_CONTROL_DO_NOTHING 0 -#define TLB_CONTROL_FLUSH_ALL_ASID 1 - -#define V_TPR_MASK 0x0f - -#define V_IRQ_SHIFT 8 -#define V_IRQ_MASK (1 << V_IRQ_SHIFT) - -#define V_INTR_PRIO_SHIFT 16 -#define V_INTR_PRIO_MASK (0x0f << V_INTR_PRIO_SHIFT) - -#define V_IGN_TPR_SHIFT 20 -#define V_IGN_TPR_MASK (1 << V_IGN_TPR_SHIFT) - -#define V_INTR_MASKING_SHIFT 24 -#define V_INTR_MASKING_MASK (1 << V_INTR_MASKING_SHIFT) - -#define SVM_INTERRUPT_SHADOW_MASK 1 - -#define SVM_IOIO_STR_SHIFT 2 -#define SVM_IOIO_REP_SHIFT 3 -#define SVM_IOIO_SIZE_SHIFT 4 -#define SVM_IOIO_ASIZE_SHIFT 7 - -#define SVM_IOIO_TYPE_MASK 1 -#define SVM_IOIO_STR_MASK (1 << SVM_IOIO_STR_SHIFT) -#define SVM_IOIO_REP_MASK (1 << SVM_IOIO_REP_SHIFT) -#define SVM_IOIO_SIZE_MASK (7 << SVM_IOIO_SIZE_SHIFT) -#define SVM_IOIO_ASIZE_MASK (7 << SVM_IOIO_ASIZE_SHIFT) - -struct __attribute__ ((__packed__)) vmcb_seg { - u16 selector; - u16 attrib; - u32 limit; - u64 base; -}; - -struct __attribute__ ((__packed__)) vmcb_save_area { - struct vmcb_seg es; - struct vmcb_seg cs; - struct vmcb_seg ss; - struct vmcb_seg ds; - struct vmcb_seg fs; - struct vmcb_seg gs; - struct vmcb_seg gdtr; - struct vmcb_seg ldtr; - struct vmcb_seg idtr; - struct vmcb_seg tr; - u8 reserved_1[43]; - u8 cpl; - u8 reserved_2[4]; - u64 efer; - u8 reserved_3[112]; - u64 cr4; - u64 cr3; - u64 cr0; - u64 dr7; - u64 dr6; - u64 rflags; - u64 rip; - u8 reserved_4[88]; - u64 rsp; - u8 reserved_5[24]; - u64 rax; - u64 star; - u64 lstar; - u64 cstar; - u64 sfmask; - u64 kernel_gs_base; - u64 sysenter_cs; - u64 sysenter_esp; - u64 sysenter_eip; - u64 cr2; - u8 reserved_6[32]; - u64 g_pat; - u64 dbgctl; - u64 br_from; - u64 br_to; - u64 last_excp_from; - u64 last_excp_to; -}; - -struct __attribute__ ((__packed__)) vmcb { - struct vmcb_control_area control; - struct vmcb_save_area save; -}; - -#define SVM_CPUID_FEATURE_SHIFT 2 -#define SVM_CPUID_FUNC 0x8000000a - -#define MSR_EFER_SVME_MASK (1ULL << 12) -#define MSR_VM_CR 0xc0010114 -#define MSR_VM_HSAVE_PA 0xc0010117ULL - -#define SVM_VM_CR_SVM_DISABLE 4 - -#define SVM_SELECTOR_S_SHIFT 4 -#define SVM_SELECTOR_DPL_SHIFT 5 -#define SVM_SELECTOR_P_SHIFT 7 -#define SVM_SELECTOR_AVL_SHIFT 8 -#define SVM_SELECTOR_L_SHIFT 9 -#define SVM_SELECTOR_DB_SHIFT 10 -#define SVM_SELECTOR_G_SHIFT 11 - -#define SVM_SELECTOR_TYPE_MASK (0xf) -#define SVM_SELECTOR_S_MASK (1 << SVM_SELECTOR_S_SHIFT) -#define SVM_SELECTOR_DPL_MASK (3 << SVM_SELECTOR_DPL_SHIFT) -#define SVM_SELECTOR_P_MASK (1 << SVM_SELECTOR_P_SHIFT) -#define SVM_SELECTOR_AVL_MASK (1 << SVM_SELECTOR_AVL_SHIFT) -#define SVM_SELECTOR_L_MASK (1 << SVM_SELECTOR_L_SHIFT) -#define SVM_SELECTOR_DB_MASK (1 << SVM_SELECTOR_DB_SHIFT) -#define SVM_SELECTOR_G_MASK (1 << SVM_SELECTOR_G_SHIFT) - -#define SVM_SELECTOR_WRITE_MASK (1 << 1) -#define SVM_SELECTOR_READ_MASK SVM_SELECTOR_WRITE_MASK -#define SVM_SELECTOR_CODE_MASK (1 << 3) - -#define INTERCEPT_CR0_MASK 1 -#define INTERCEPT_CR3_MASK (1 << 3) -#define INTERCEPT_CR4_MASK (1 << 4) - -#define INTERCEPT_DR0_MASK 1 -#define INTERCEPT_DR1_MASK (1 << 1) -#define INTERCEPT_DR2_MASK (1 << 2) -#define INTERCEPT_DR3_MASK (1 << 3) -#define INTERCEPT_DR4_MASK (1 << 4) -#define INTERCEPT_DR5_MASK (1 << 5) -#define INTERCEPT_DR6_MASK (1 << 6) -#define INTERCEPT_DR7_MASK (1 << 7) - -#define SVM_EVTINJ_VEC_MASK 0xff - -#define SVM_EVTINJ_TYPE_SHIFT 8 -#define SVM_EVTINJ_TYPE_MASK (7 << SVM_EVTINJ_TYPE_SHIFT) - -#define SVM_EVTINJ_TYPE_INTR (0 << SVM_EVTINJ_TYPE_SHIFT) -#define SVM_EVTINJ_TYPE_NMI (2 << SVM_EVTINJ_TYPE_SHIFT) -#define SVM_EVTINJ_TYPE_EXEPT (3 << SVM_EVTINJ_TYPE_SHIFT) -#define SVM_EVTINJ_TYPE_SOFT (4 << SVM_EVTINJ_TYPE_SHIFT) - -#define SVM_EVTINJ_VALID (1 << 31) -#define SVM_EVTINJ_VALID_ERR (1 << 11) - -#define SVM_EXITINTINFO_VEC_MASK SVM_EVTINJ_VEC_MASK - -#define SVM_EXITINTINFO_TYPE_INTR SVM_EVTINJ_TYPE_INTR -#define SVM_EXITINTINFO_TYPE_NMI SVM_EVTINJ_TYPE_NMI -#define SVM_EXITINTINFO_TYPE_EXEPT SVM_EVTINJ_TYPE_EXEPT -#define SVM_EXITINTINFO_TYPE_SOFT SVM_EVTINJ_TYPE_SOFT - -#define SVM_EXITINTINFO_VALID SVM_EVTINJ_VALID -#define SVM_EXITINTINFO_VALID_ERR SVM_EVTINJ_VALID_ERR - -#define SVM_EXIT_READ_CR0 0x000 -#define SVM_EXIT_READ_CR3 0x003 -#define SVM_EXIT_READ_CR4 0x004 -#define SVM_EXIT_READ_CR8 0x008 -#define SVM_EXIT_WRITE_CR0 0x010 -#define SVM_EXIT_WRITE_CR3 0x013 -#define SVM_EXIT_WRITE_CR4 0x014 -#define SVM_EXIT_WRITE_CR8 0x018 -#define SVM_EXIT_READ_DR0 0x020 -#define SVM_EXIT_READ_DR1 0x021 -#define SVM_EXIT_READ_DR2 0x022 -#define SVM_EXIT_READ_DR3 0x023 -#define SVM_EXIT_READ_DR4 0x024 -#define SVM_EXIT_READ_DR5 0x025 -#define SVM_EXIT_READ_DR6 0x026 -#define SVM_EXIT_READ_DR7 0x027 -#define SVM_EXIT_WRITE_DR0 0x030 -#define SVM_EXIT_WRITE_DR1 0x031 -#define SVM_EXIT_WRITE_DR2 0x032 -#define SVM_EXIT_WRITE_DR3 0x033 -#define SVM_EXIT_WRITE_DR4 0x034 -#define SVM_EXIT_WRITE_DR5 0x035 -#define SVM_EXIT_WRITE_DR6 0x036 -#define SVM_EXIT_WRITE_DR7 0x037 -#define SVM_EXIT_EXCP_BASE 0x040 -#define SVM_EXIT_INTR 0x060 -#define SVM_EXIT_NMI 0x061 -#define SVM_EXIT_SMI 0x062 -#define SVM_EXIT_INIT 0x063 -#define SVM_EXIT_VINTR 0x064 -#define SVM_EXIT_CR0_SEL_WRITE 0x065 -#define SVM_EXIT_IDTR_READ 0x066 -#define SVM_EXIT_GDTR_READ 0x067 -#define SVM_EXIT_LDTR_READ 0x068 -#define SVM_EXIT_TR_READ 0x069 -#define SVM_EXIT_IDTR_WRITE 0x06a -#define SVM_EXIT_GDTR_WRITE 0x06b -#define SVM_EXIT_LDTR_WRITE 0x06c -#define SVM_EXIT_TR_WRITE 0x06d -#define SVM_EXIT_RDTSC 0x06e -#define SVM_EXIT_RDPMC 0x06f -#define SVM_EXIT_PUSHF 0x070 -#define SVM_EXIT_POPF 0x071 -#define SVM_EXIT_CPUID 0x072 -#define SVM_EXIT_RSM 0x073 -#define SVM_EXIT_IRET 0x074 -#define SVM_EXIT_SWINT 0x075 -#define SVM_EXIT_INVD 0x076 -#define SVM_EXIT_PAUSE 0x077 -#define SVM_EXIT_HLT 0x078 -#define SVM_EXIT_INVLPG 0x079 -#define SVM_EXIT_INVLPGA 0x07a -#define SVM_EXIT_IOIO 0x07b -#define SVM_EXIT_MSR 0x07c -#define SVM_EXIT_TASK_SWITCH 0x07d -#define SVM_EXIT_FERR_FREEZE 0x07e -#define SVM_EXIT_SHUTDOWN 0x07f -#define SVM_EXIT_VMRUN 0x080 -#define SVM_EXIT_VMMCALL 0x081 -#define SVM_EXIT_VMLOAD 0x082 -#define SVM_EXIT_VMSAVE 0x083 -#define SVM_EXIT_STGI 0x084 -#define SVM_EXIT_CLGI 0x085 -#define SVM_EXIT_SKINIT 0x086 -#define SVM_EXIT_RDTSCP 0x087 -#define SVM_EXIT_ICEBP 0x088 -#define SVM_EXIT_WBINVD 0x089 -#define SVM_EXIT_MONITOR 0x08a -#define SVM_EXIT_MWAIT 0x08b -#define SVM_EXIT_MWAIT_COND 0x08c -#define SVM_EXIT_NPF 0x400 - -#define SVM_EXIT_ERR -1 - -#define SVM_CR0_SELECTIVE_MASK (1 << 3 | 1) // TS and MP - -#define SVM_VMLOAD ".byte 0x0f, 0x01, 0xda" -#define SVM_VMRUN ".byte 0x0f, 0x01, 0xd8" -#define SVM_VMSAVE ".byte 0x0f, 0x01, 0xdb" -#define SVM_CLGI ".byte 0x0f, 0x01, 0xdd" -#define SVM_STGI ".byte 0x0f, 0x01, 0xdc" -#define SVM_INVLPGA ".byte 0x0f, 0x01, 0xdf" - -#endif - diff --git a/drivers/kvm/vmx.c b/drivers/kvm/vmx.c deleted file mode 100644 index bb56ae3f89b6..000000000000 --- a/drivers/kvm/vmx.c +++ /dev/null @@ -1,2566 +0,0 @@ -/* - * Kernel-based Virtual Machine driver for Linux - * - * This module enables machines with Intel VT-x extensions to run virtual - * machines without emulation or binary translation. - * - * Copyright (C) 2006 Qumranet, Inc. - * - * Authors: - * Avi Kivity <avi@qumranet.com> - * Yaniv Kamay <yaniv@qumranet.com> - * - * This work is licensed under the terms of the GNU GPL, version 2. See - * the COPYING file in the top-level directory. - * - */ - -#include "kvm.h" -#include "x86_emulate.h" -#include "irq.h" -#include "vmx.h" -#include "segment_descriptor.h" - -#include <linux/module.h> -#include <linux/kernel.h> -#include <linux/mm.h> -#include <linux/highmem.h> -#include <linux/sched.h> - -#include <asm/io.h> -#include <asm/desc.h> - -MODULE_AUTHOR("Qumranet"); -MODULE_LICENSE("GPL"); - -struct vmcs { - u32 revision_id; - u32 abort; - char data[0]; -}; - -struct vcpu_vmx { - struct kvm_vcpu vcpu; - int launched; - u8 fail; - struct kvm_msr_entry *guest_msrs; - struct kvm_msr_entry *host_msrs; - int nmsrs; - int save_nmsrs; - int msr_offset_efer; -#ifdef CONFIG_X86_64 - int msr_offset_kernel_gs_base; -#endif - struct vmcs *vmcs; - struct { - int loaded; - u16 fs_sel, gs_sel, ldt_sel; - int gs_ldt_reload_needed; - int fs_reload_needed; - }host_state; - -}; - -static inline struct vcpu_vmx *to_vmx(struct kvm_vcpu *vcpu) -{ - return container_of(vcpu, struct vcpu_vmx, vcpu); -} - -static int init_rmode_tss(struct kvm *kvm); - -static DEFINE_PER_CPU(struct vmcs *, vmxarea); -static DEFINE_PER_CPU(struct vmcs *, current_vmcs); - -static struct page *vmx_io_bitmap_a; -static struct page *vmx_io_bitmap_b; - -#define EFER_SAVE_RESTORE_BITS ((u64)EFER_SCE) - -static struct vmcs_config { - int size; - int order; - u32 revision_id; - u32 pin_based_exec_ctrl; - u32 cpu_based_exec_ctrl; - u32 vmexit_ctrl; - u32 vmentry_ctrl; -} vmcs_config; - -#define VMX_SEGMENT_FIELD(seg) \ - [VCPU_SREG_##seg] = { \ - .selector = GUEST_##seg##_SELECTOR, \ - .base = GUEST_##seg##_BASE, \ - .limit = GUEST_##seg##_LIMIT, \ - .ar_bytes = GUEST_##seg##_AR_BYTES, \ - } - -static struct kvm_vmx_segment_field { - unsigned selector; - unsigned base; - unsigned limit; - unsigned ar_bytes; -} kvm_vmx_segment_fields[] = { - VMX_SEGMENT_FIELD(CS), - VMX_SEGMENT_FIELD(DS), - VMX_SEGMENT_FIELD(ES), - VMX_SEGMENT_FIELD(FS), - VMX_SEGMENT_FIELD(GS), - VMX_SEGMENT_FIELD(SS), - VMX_SEGMENT_FIELD(TR), - VMX_SEGMENT_FIELD(LDTR), -}; - -/* - * Keep MSR_K6_STAR at the end, as setup_msrs() will try to optimize it - * away by decrementing the array size. - */ -static const u32 vmx_msr_index[] = { -#ifdef CONFIG_X86_64 - MSR_SYSCALL_MASK, MSR_LSTAR, MSR_CSTAR, MSR_KERNEL_GS_BASE, -#endif - MSR_EFER, MSR_K6_STAR, -}; -#define NR_VMX_MSR ARRAY_SIZE(vmx_msr_index) - -static void load_msrs(struct kvm_msr_entry *e, int n) -{ - int i; - - for (i = 0; i < n; ++i) - wrmsrl(e[i].index, e[i].data); -} - -static void save_msrs(struct kvm_msr_entry *e, int n) -{ - int i; - - for (i = 0; i < n; ++i) - rdmsrl(e[i].index, e[i].data); -} - -static inline u64 msr_efer_save_restore_bits(struct kvm_msr_entry msr) -{ - return (u64)msr.data & EFER_SAVE_RESTORE_BITS; -} - -static inline int msr_efer_need_save_restore(struct vcpu_vmx *vmx) -{ - int efer_offset = vmx->msr_offset_efer; - return msr_efer_save_restore_bits(vmx->host_msrs[efer_offset]) != - msr_efer_save_restore_bits(vmx->guest_msrs[efer_offset]); -} - -static inline int is_page_fault(u32 intr_info) -{ - return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK | - INTR_INFO_VALID_MASK)) == - (INTR_TYPE_EXCEPTION | PF_VECTOR | INTR_INFO_VALID_MASK); -} - -static inline int is_no_device(u32 intr_info) -{ - return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK | - INTR_INFO_VALID_MASK)) == - (INTR_TYPE_EXCEPTION | NM_VECTOR | INTR_INFO_VALID_MASK); -} - -static inline int is_external_interrupt(u32 intr_info) -{ - return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VALID_MASK)) - == (INTR_TYPE_EXT_INTR | INTR_INFO_VALID_MASK); -} - -static inline int cpu_has_vmx_tpr_shadow(void) -{ - return (vmcs_config.cpu_based_exec_ctrl & CPU_BASED_TPR_SHADOW); -} - -static inline int vm_need_tpr_shadow(struct kvm *kvm) -{ - return ((cpu_has_vmx_tpr_shadow()) && (irqchip_in_kernel(kvm))); -} - -static int __find_msr_index(struct vcpu_vmx *vmx, u32 msr) -{ - int i; - - for (i = 0; i < vmx->nmsrs; ++i) - if (vmx->guest_msrs[i].index == msr) - return i; - return -1; -} - -static struct kvm_msr_entry *find_msr_entry(struct vcpu_vmx *vmx, u32 msr) -{ - int i; - - i = __find_msr_index(vmx, msr); - if (i >= 0) - return &vmx->guest_msrs[i]; - return NULL; -} - -static void vmcs_clear(struct vmcs *vmcs) -{ - u64 phys_addr = __pa(vmcs); - u8 error; - - asm volatile (ASM_VMX_VMCLEAR_RAX "; setna %0" - : "=g"(error) : "a"(&phys_addr), "m"(phys_addr) - : "cc", "memory"); - if (error) - printk(KERN_ERR "kvm: vmclear fail: %p/%llx\n", - vmcs, phys_addr); -} - -static void __vcpu_clear(void *arg) -{ - struct vcpu_vmx *vmx = arg; - int cpu = raw_smp_processor_id(); - - if (vmx->vcpu.cpu == cpu) - vmcs_clear(vmx->vmcs); - if (per_cpu(current_vmcs, cpu) == vmx->vmcs) - per_cpu(current_vmcs, cpu) = NULL; - rdtscll(vmx->vcpu.host_tsc); -} - -static void vcpu_clear(struct vcpu_vmx *vmx) -{ - if (vmx->vcpu.cpu != raw_smp_processor_id() && vmx->vcpu.cpu != -1) - smp_call_function_single(vmx->vcpu.cpu, __vcpu_clear, - vmx, 0, 1); - else - __vcpu_clear(vmx); - vmx->launched = 0; -} - -static unsigned long vmcs_readl(unsigned long field) -{ - unsigned long value; - - asm volatile (ASM_VMX_VMREAD_RDX_RAX - : "=a"(value) : "d"(field) : "cc"); - return value; -} - -static u16 vmcs_read16(unsigned long field) -{ - return vmcs_readl(field); -} - -static u32 vmcs_read32(unsigned long field) -{ - return vmcs_readl(field); -} - -static u64 vmcs_read64(unsigned long field) -{ -#ifdef CONFIG_X86_64 - return vmcs_readl(field); -#else - return vmcs_readl(field) | ((u64)vmcs_readl(field+1) << 32); -#endif -} - -static noinline void vmwrite_error(unsigned long field, unsigned long value) -{ - printk(KERN_ERR "vmwrite error: reg %lx value %lx (err %d)\n", - field, value, vmcs_read32(VM_INSTRUCTION_ERROR)); - dump_stack(); -} - -static void vmcs_writel(unsigned long field, unsigned long value) -{ - u8 error; - - asm volatile (ASM_VMX_VMWRITE_RAX_RDX "; setna %0" - : "=q"(error) : "a"(value), "d"(field) : "cc" ); - if (unlikely(error)) - vmwrite_error(field, value); -} - -static void vmcs_write16(unsigned long field, u16 value) -{ - vmcs_writel(field, value); -} - -static void vmcs_write32(unsigned long field, u32 value) -{ - vmcs_writel(field, value); -} - -static void vmcs_write64(unsigned long field, u64 value) -{ -#ifdef CONFIG_X86_64 - vmcs_writel(field, value); -#else - vmcs_writel(field, value); - asm volatile (""); - vmcs_writel(field+1, value >> 32); -#endif -} - -static void vmcs_clear_bits(unsigned long field, u32 mask) -{ - vmcs_writel(field, vmcs_readl(field) & ~mask); -} - -static void vmcs_set_bits(unsigned long field, u32 mask) -{ - vmcs_writel(field, vmcs_readl(field) | mask); -} - -static void update_exception_bitmap(struct kvm_vcpu *vcpu) -{ - u32 eb; - - eb = 1u << PF_VECTOR; - if (!vcpu->fpu_active) - eb |= 1u << NM_VECTOR; - if (vcpu->guest_debug.enabled) - eb |= 1u << 1; - if (vcpu->rmode.active) - eb = ~0; - vmcs_write32(EXCEPTION_BITMAP, eb); -} - -static void reload_tss(void) -{ -#ifndef CONFIG_X86_64 - - /* - * VT restores TR but not its size. Useless. - */ - struct descriptor_table gdt; - struct segment_descriptor *descs; - - get_gdt(&gdt); - descs = (void *)gdt.base; - descs[GDT_ENTRY_TSS].type = 9; /* available TSS */ - load_TR_desc(); -#endif -} - -static void load_transition_efer(struct vcpu_vmx *vmx) -{ - u64 trans_efer; - int efer_offset = vmx->msr_offset_efer; - - trans_efer = vmx->host_msrs[efer_offset].data; - trans_efer &= ~EFER_SAVE_RESTORE_BITS; - trans_efer |= msr_efer_save_restore_bits(vmx->guest_msrs[efer_offset]); - wrmsrl(MSR_EFER, trans_efer); - vmx->vcpu.stat.efer_reload++; -} - -static void vmx_save_host_state(struct kvm_vcpu *vcpu) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - - if (vmx->host_state.loaded) - return; - - vmx->host_state.loaded = 1; - /* - * Set host fs and gs selectors. Unfortunately, 22.2.3 does not - * allow segment selectors with cpl > 0 or ti == 1. - */ - vmx->host_state.ldt_sel = read_ldt(); - vmx->host_state.gs_ldt_reload_needed = vmx->host_state.ldt_sel; - vmx->host_state.fs_sel = read_fs(); - if (!(vmx->host_state.fs_sel & 7)) { - vmcs_write16(HOST_FS_SELECTOR, vmx->host_state.fs_sel); - vmx->host_state.fs_reload_needed = 0; - } else { - vmcs_write16(HOST_FS_SELECTOR, 0); - vmx->host_state.fs_reload_needed = 1; - } - vmx->host_state.gs_sel = read_gs(); - if (!(vmx->host_state.gs_sel & 7)) - vmcs_write16(HOST_GS_SELECTOR, vmx->host_state.gs_sel); - else { - vmcs_write16(HOST_GS_SELECTOR, 0); - vmx->host_state.gs_ldt_reload_needed = 1; - } - -#ifdef CONFIG_X86_64 - vmcs_writel(HOST_FS_BASE, read_msr(MSR_FS_BASE)); - vmcs_writel(HOST_GS_BASE, read_msr(MSR_GS_BASE)); -#else - vmcs_writel(HOST_FS_BASE, segment_base(vmx->host_state.fs_sel)); - vmcs_writel(HOST_GS_BASE, segment_base(vmx->host_state.gs_sel)); -#endif - -#ifdef CONFIG_X86_64 - if (is_long_mode(&vmx->vcpu)) { - save_msrs(vmx->host_msrs + - vmx->msr_offset_kernel_gs_base, 1); - } -#endif - load_msrs(vmx->guest_msrs, vmx->save_nmsrs); - if (msr_efer_need_save_restore(vmx)) - load_transition_efer(vmx); -} - -static void vmx_load_host_state(struct vcpu_vmx *vmx) -{ - unsigned long flags; - - if (!vmx->host_state.loaded) - return; - - vmx->host_state.loaded = 0; - if (vmx->host_state.fs_reload_needed) - load_fs(vmx->host_state.fs_sel); - if (vmx->host_state.gs_ldt_reload_needed) { - load_ldt(vmx->host_state.ldt_sel); - /* - * If we have to reload gs, we must take care to - * preserve our gs base. - */ - local_irq_save(flags); - load_gs(vmx->host_state.gs_sel); -#ifdef CONFIG_X86_64 - wrmsrl(MSR_GS_BASE, vmcs_readl(HOST_GS_BASE)); -#endif - local_irq_restore(flags); - } - reload_tss(); - save_msrs(vmx->guest_msrs, vmx->save_nmsrs); - load_msrs(vmx->host_msrs, vmx->save_nmsrs); - if (msr_efer_need_save_restore(vmx)) - load_msrs(vmx->host_msrs + vmx->msr_offset_efer, 1); -} - -/* - * Switches to specified vcpu, until a matching vcpu_put(), but assumes - * vcpu mutex is already taken. - */ -static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - u64 phys_addr = __pa(vmx->vmcs); - u64 tsc_this, delta; - - if (vcpu->cpu != cpu) { - vcpu_clear(vmx); - kvm_migrate_apic_timer(vcpu); - } - - if (per_cpu(current_vmcs, cpu) != vmx->vmcs) { - u8 error; - - per_cpu(current_vmcs, cpu) = vmx->vmcs; - asm volatile (ASM_VMX_VMPTRLD_RAX "; setna %0" - : "=g"(error) : "a"(&phys_addr), "m"(phys_addr) - : "cc"); - if (error) - printk(KERN_ERR "kvm: vmptrld %p/%llx fail\n", - vmx->vmcs, phys_addr); - } - - if (vcpu->cpu != cpu) { - struct descriptor_table dt; - unsigned long sysenter_esp; - - vcpu->cpu = cpu; - /* - * Linux uses per-cpu TSS and GDT, so set these when switching - * processors. - */ - vmcs_writel(HOST_TR_BASE, read_tr_base()); /* 22.2.4 */ - get_gdt(&dt); - vmcs_writel(HOST_GDTR_BASE, dt.base); /* 22.2.4 */ - - rdmsrl(MSR_IA32_SYSENTER_ESP, sysenter_esp); - vmcs_writel(HOST_IA32_SYSENTER_ESP, sysenter_esp); /* 22.2.3 */ - - /* - * Make sure the time stamp counter is monotonous. - */ - rdtscll(tsc_this); - delta = vcpu->host_tsc - tsc_this; - vmcs_write64(TSC_OFFSET, vmcs_read64(TSC_OFFSET) + delta); - } -} - -static void vmx_vcpu_put(struct kvm_vcpu *vcpu) -{ - vmx_load_host_state(to_vmx(vcpu)); - kvm_put_guest_fpu(vcpu); -} - -static void vmx_fpu_activate(struct kvm_vcpu *vcpu) -{ - if (vcpu->fpu_active) - return; - vcpu->fpu_active = 1; - vmcs_clear_bits(GUEST_CR0, X86_CR0_TS); - if (vcpu->cr0 & X86_CR0_TS) - vmcs_set_bits(GUEST_CR0, X86_CR0_TS); - update_exception_bitmap(vcpu); -} - -static void vmx_fpu_deactivate(struct kvm_vcpu *vcpu) -{ - if (!vcpu->fpu_active) - return; - vcpu->fpu_active = 0; - vmcs_set_bits(GUEST_CR0, X86_CR0_TS); - update_exception_bitmap(vcpu); -} - -static void vmx_vcpu_decache(struct kvm_vcpu *vcpu) -{ - vcpu_clear(to_vmx(vcpu)); -} - -static unsigned long vmx_get_rflags(struct kvm_vcpu *vcpu) -{ - return vmcs_readl(GUEST_RFLAGS); -} - -static void vmx_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags) -{ - if (vcpu->rmode.active) - rflags |= IOPL_MASK | X86_EFLAGS_VM; - vmcs_writel(GUEST_RFLAGS, rflags); -} - -static void skip_emulated_instruction(struct kvm_vcpu *vcpu) -{ - unsigned long rip; - u32 interruptibility; - - rip = vmcs_readl(GUEST_RIP); - rip += vmcs_read32(VM_EXIT_INSTRUCTION_LEN); - vmcs_writel(GUEST_RIP, rip); - - /* - * We emulated an instruction, so temporary interrupt blocking - * should be removed, if set. - */ - interruptibility = vmcs_read32(GUEST_INTERRUPTIBILITY_INFO); - if (interruptibility & 3) - vmcs_write32(GUEST_INTERRUPTIBILITY_INFO, - interruptibility & ~3); - vcpu->interrupt_window_open = 1; -} - -static void vmx_inject_gp(struct kvm_vcpu *vcpu, unsigned error_code) -{ - printk(KERN_DEBUG "inject_general_protection: rip 0x%lx\n", - vmcs_readl(GUEST_RIP)); - vmcs_write32(VM_ENTRY_EXCEPTION_ERROR_CODE, error_code); - vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, - GP_VECTOR | - INTR_TYPE_EXCEPTION | - INTR_INFO_DELIEVER_CODE_MASK | - INTR_INFO_VALID_MASK); -} - -/* - * Swap MSR entry in host/guest MSR entry array. - */ -#ifdef CONFIG_X86_64 -static void move_msr_up(struct vcpu_vmx *vmx, int from, int to) -{ - struct kvm_msr_entry tmp; - - tmp = vmx->guest_msrs[to]; - vmx->guest_msrs[to] = vmx->guest_msrs[from]; - vmx->guest_msrs[from] = tmp; - tmp = vmx->host_msrs[to]; - vmx->host_msrs[to] = vmx->host_msrs[from]; - vmx->host_msrs[from] = tmp; -} -#endif - -/* - * Set up the vmcs to automatically save and restore system - * msrs. Don't touch the 64-bit msrs if the guest is in legacy - * mode, as fiddling with msrs is very expensive. - */ -static void setup_msrs(struct vcpu_vmx *vmx) -{ - int save_nmsrs; - - save_nmsrs = 0; -#ifdef CONFIG_X86_64 - if (is_long_mode(&vmx->vcpu)) { - int index; - - index = __find_msr_index(vmx, MSR_SYSCALL_MASK); - if (index >= 0) - move_msr_up(vmx, index, save_nmsrs++); - index = __find_msr_index(vmx, MSR_LSTAR); - if (index >= 0) - move_msr_up(vmx, index, save_nmsrs++); - index = __find_msr_index(vmx, MSR_CSTAR); - if (index >= 0) - move_msr_up(vmx, index, save_nmsrs++); - index = __find_msr_index(vmx, MSR_KERNEL_GS_BASE); - if (index >= 0) - move_msr_up(vmx, index, save_nmsrs++); - /* - * MSR_K6_STAR is only needed on long mode guests, and only - * if efer.sce is enabled. - */ - index = __find_msr_index(vmx, MSR_K6_STAR); - if ((index >= 0) && (vmx->vcpu.shadow_efer & EFER_SCE)) - move_msr_up(vmx, index, save_nmsrs++); - } -#endif - vmx->save_nmsrs = save_nmsrs; - -#ifdef CONFIG_X86_64 - vmx->msr_offset_kernel_gs_base = - __find_msr_index(vmx, MSR_KERNEL_GS_BASE); -#endif - vmx->msr_offset_efer = __find_msr_index(vmx, MSR_EFER); -} - -/* - * reads and returns guest's timestamp counter "register" - * guest_tsc = host_tsc + tsc_offset -- 21.3 - */ -static u64 guest_read_tsc(void) -{ - u64 host_tsc, tsc_offset; - - rdtscll(host_tsc); - tsc_offset = vmcs_read64(TSC_OFFSET); - return host_tsc + tsc_offset; -} - -/* - * writes 'guest_tsc' into guest's timestamp counter "register" - * guest_tsc = host_tsc + tsc_offset ==> tsc_offset = guest_tsc - host_tsc - */ -static void guest_write_tsc(u64 guest_tsc) -{ - u64 host_tsc; - - rdtscll(host_tsc); - vmcs_write64(TSC_OFFSET, guest_tsc - host_tsc); -} - -/* - * Reads an msr value (of 'msr_index') into 'pdata'. - * Returns 0 on success, non-0 otherwise. - * Assumes vcpu_load() was already called. - */ -static int vmx_get_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata) -{ - u64 data; - struct kvm_msr_entry *msr; - - if (!pdata) { - printk(KERN_ERR "BUG: get_msr called with NULL pdata\n"); - return -EINVAL; - } - - switch (msr_index) { -#ifdef CONFIG_X86_64 - case MSR_FS_BASE: - data = vmcs_readl(GUEST_FS_BASE); - break; - case MSR_GS_BASE: - data = vmcs_readl(GUEST_GS_BASE); - break; - case MSR_EFER: - return kvm_get_msr_common(vcpu, msr_index, pdata); -#endif - case MSR_IA32_TIME_STAMP_COUNTER: - data = guest_read_tsc(); - break; - case MSR_IA32_SYSENTER_CS: - data = vmcs_read32(GUEST_SYSENTER_CS); - break; - case MSR_IA32_SYSENTER_EIP: - data = vmcs_readl(GUEST_SYSENTER_EIP); - break; - case MSR_IA32_SYSENTER_ESP: - data = vmcs_readl(GUEST_SYSENTER_ESP); - break; - default: - msr = find_msr_entry(to_vmx(vcpu), msr_index); - if (msr) { - data = msr->data; - break; - } - return kvm_get_msr_common(vcpu, msr_index, pdata); - } - - *pdata = data; - return 0; -} - -/* - * Writes msr value into into the appropriate "register". - * Returns 0 on success, non-0 otherwise. - * Assumes vcpu_load() was already called. - */ -static int vmx_set_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - struct kvm_msr_entry *msr; - int ret = 0; - - switch (msr_index) { -#ifdef CONFIG_X86_64 - case MSR_EFER: - ret = kvm_set_msr_common(vcpu, msr_index, data); - if (vmx->host_state.loaded) - load_transition_efer(vmx); - break; - case MSR_FS_BASE: - vmcs_writel(GUEST_FS_BASE, data); - break; - case MSR_GS_BASE: - vmcs_writel(GUEST_GS_BASE, data); - break; -#endif - case MSR_IA32_SYSENTER_CS: - vmcs_write32(GUEST_SYSENTER_CS, data); - break; - case MSR_IA32_SYSENTER_EIP: - vmcs_writel(GUEST_SYSENTER_EIP, data); - break; - case MSR_IA32_SYSENTER_ESP: - vmcs_writel(GUEST_SYSENTER_ESP, data); - break; - case MSR_IA32_TIME_STAMP_COUNTER: - guest_write_tsc(data); - break; - default: - msr = find_msr_entry(vmx, msr_index); - if (msr) { - msr->data = data; - if (vmx->host_state.loaded) - load_msrs(vmx->guest_msrs, vmx->save_nmsrs); - break; - } - ret = kvm_set_msr_common(vcpu, msr_index, data); - } - - return ret; -} - -/* - * Sync the rsp and rip registers into the vcpu structure. This allows - * registers to be accessed by indexing vcpu->regs. - */ -static void vcpu_load_rsp_rip(struct kvm_vcpu *vcpu) -{ - vcpu->regs[VCPU_REGS_RSP] = vmcs_readl(GUEST_RSP); - vcpu->rip = vmcs_readl(GUEST_RIP); -} - -/* - * Syncs rsp and rip back into the vmcs. Should be called after possible - * modification. - */ -static void vcpu_put_rsp_rip(struct kvm_vcpu *vcpu) -{ - vmcs_writel(GUEST_RSP, vcpu->regs[VCPU_REGS_RSP]); - vmcs_writel(GUEST_RIP, vcpu->rip); -} - -static int set_guest_debug(struct kvm_vcpu *vcpu, struct kvm_debug_guest *dbg) -{ - unsigned long dr7 = 0x400; - int old_singlestep; - - old_singlestep = vcpu->guest_debug.singlestep; - - vcpu->guest_debug.enabled = dbg->enabled; - if (vcpu->guest_debug.enabled) { - int i; - - dr7 |= 0x200; /* exact */ - for (i = 0; i < 4; ++i) { - if (!dbg->breakpoints[i].enabled) - continue; - vcpu->guest_debug.bp[i] = dbg->breakpoints[i].address; - dr7 |= 2 << (i*2); /* global enable */ - dr7 |= 0 << (i*4+16); /* execution breakpoint */ - } - - vcpu->guest_debug.singlestep = dbg->singlestep; - } else - vcpu->guest_debug.singlestep = 0; - - if (old_singlestep && !vcpu->guest_debug.singlestep) { - unsigned long flags; - - flags = vmcs_readl(GUEST_RFLAGS); - flags &= ~(X86_EFLAGS_TF | X86_EFLAGS_RF); - vmcs_writel(GUEST_RFLAGS, flags); - } - - update_exception_bitmap(vcpu); - vmcs_writel(GUEST_DR7, dr7); - - return 0; -} - -static int vmx_get_irq(struct kvm_vcpu *vcpu) -{ - u32 idtv_info_field; - - idtv_info_field = vmcs_read32(IDT_VECTORING_INFO_FIELD); - if (idtv_info_field & INTR_INFO_VALID_MASK) { - if (is_external_interrupt(idtv_info_field)) - return idtv_info_field & VECTORING_INFO_VECTOR_MASK; - else - printk("pending exception: not handled yet\n"); - } - return -1; -} - -static __init int cpu_has_kvm_support(void) -{ - unsigned long ecx = cpuid_ecx(1); - return test_bit(5, &ecx); /* CPUID.1:ECX.VMX[bit 5] -> VT */ -} - -static __init int vmx_disabled_by_bios(void) -{ - u64 msr; - - rdmsrl(MSR_IA32_FEATURE_CONTROL, msr); - return (msr & (MSR_IA32_FEATURE_CONTROL_LOCKED | - MSR_IA32_FEATURE_CONTROL_VMXON_ENABLED)) - == MSR_IA32_FEATURE_CONTROL_LOCKED; - /* locked but not enabled */ -} - -static void hardware_enable(void *garbage) -{ - int cpu = raw_smp_processor_id(); - u64 phys_addr = __pa(per_cpu(vmxarea, cpu)); - u64 old; - - rdmsrl(MSR_IA32_FEATURE_CONTROL, old); - if ((old & (MSR_IA32_FEATURE_CONTROL_LOCKED | - MSR_IA32_FEATURE_CONTROL_VMXON_ENABLED)) - != (MSR_IA32_FEATURE_CONTROL_LOCKED | - MSR_IA32_FEATURE_CONTROL_VMXON_ENABLED)) - /* enable and lock */ - wrmsrl(MSR_IA32_FEATURE_CONTROL, old | - MSR_IA32_FEATURE_CONTROL_LOCKED | - MSR_IA32_FEATURE_CONTROL_VMXON_ENABLED); - write_cr4(read_cr4() | X86_CR4_VMXE); /* FIXME: not cpu hotplug safe */ - asm volatile (ASM_VMX_VMXON_RAX : : "a"(&phys_addr), "m"(phys_addr) - : "memory", "cc"); -} - -static void hardware_disable(void *garbage) -{ - asm volatile (ASM_VMX_VMXOFF : : : "cc"); -} - -static __init int adjust_vmx_controls(u32 ctl_min, u32 ctl_opt, - u32 msr, u32* result) -{ - u32 vmx_msr_low, vmx_msr_high; - u32 ctl = ctl_min | ctl_opt; - - rdmsr(msr, vmx_msr_low, vmx_msr_high); - - ctl &= vmx_msr_high; /* bit == 0 in high word ==> must be zero */ - ctl |= vmx_msr_low; /* bit == 1 in low word ==> must be one */ - - /* Ensure minimum (required) set of control bits are supported. */ - if (ctl_min & ~ctl) - return -EIO; - - *result = ctl; - return 0; -} - -static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf) -{ - u32 vmx_msr_low, vmx_msr_high; - u32 min, opt; - u32 _pin_based_exec_control = 0; - u32 _cpu_based_exec_control = 0; - u32 _vmexit_control = 0; - u32 _vmentry_control = 0; - - min = PIN_BASED_EXT_INTR_MASK | PIN_BASED_NMI_EXITING; - opt = 0; - if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_PINBASED_CTLS, - &_pin_based_exec_control) < 0) - return -EIO; - - min = CPU_BASED_HLT_EXITING | -#ifdef CONFIG_X86_64 - CPU_BASED_CR8_LOAD_EXITING | - CPU_BASED_CR8_STORE_EXITING | -#endif - CPU_BASED_USE_IO_BITMAPS | - CPU_BASED_MOV_DR_EXITING | - CPU_BASED_USE_TSC_OFFSETING; -#ifdef CONFIG_X86_64 - opt = CPU_BASED_TPR_SHADOW; -#else - opt = 0; -#endif - if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_PROCBASED_CTLS, - &_cpu_based_exec_control) < 0) - return -EIO; -#ifdef CONFIG_X86_64 - if ((_cpu_based_exec_control & CPU_BASED_TPR_SHADOW)) - _cpu_based_exec_control &= ~CPU_BASED_CR8_LOAD_EXITING & - ~CPU_BASED_CR8_STORE_EXITING; -#endif - - min = 0; -#ifdef CONFIG_X86_64 - min |= VM_EXIT_HOST_ADDR_SPACE_SIZE; -#endif - opt = 0; - if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_EXIT_CTLS, - &_vmexit_control) < 0) - return -EIO; - - min = opt = 0; - if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_ENTRY_CTLS, - &_vmentry_control) < 0) - return -EIO; - - rdmsr(MSR_IA32_VMX_BASIC, vmx_msr_low, vmx_msr_high); - - /* IA-32 SDM Vol 3B: VMCS size is never greater than 4kB. */ - if ((vmx_msr_high & 0x1fff) > PAGE_SIZE) - return -EIO; - -#ifdef CONFIG_X86_64 - /* IA-32 SDM Vol 3B: 64-bit CPUs always have VMX_BASIC_MSR[48]==0. */ - if (vmx_msr_high & (1u<<16)) - return -EIO; -#endif - - /* Require Write-Back (WB) memory type for VMCS accesses. */ - if (((vmx_msr_high >> 18) & 15) != 6) - return -EIO; - - vmcs_conf->size = vmx_msr_high & 0x1fff; - vmcs_conf->order = get_order(vmcs_config.size); - vmcs_conf->revision_id = vmx_msr_low; - - vmcs_conf->pin_based_exec_ctrl = _pin_based_exec_control; - vmcs_conf->cpu_based_exec_ctrl = _cpu_based_exec_control; - vmcs_conf->vmexit_ctrl = _vmexit_control; - vmcs_conf->vmentry_ctrl = _vmentry_control; - - return 0; -} - -static struct vmcs *alloc_vmcs_cpu(int cpu) -{ - int node = cpu_to_node(cpu); - struct page *pages; - struct vmcs *vmcs; - - pages = alloc_pages_node(node, GFP_KERNEL, vmcs_config.order); - if (!pages) - return NULL; - vmcs = page_address(pages); - memset(vmcs, 0, vmcs_config.size); - vmcs->revision_id = vmcs_config.revision_id; /* vmcs revision id */ - return vmcs; -} - -static struct vmcs *alloc_vmcs(void) -{ - return alloc_vmcs_cpu(raw_smp_processor_id()); -} - -static void free_vmcs(struct vmcs *vmcs) -{ - free_pages((unsigned long)vmcs, vmcs_config.order); -} - -static void free_kvm_area(void) -{ - int cpu; - - for_each_online_cpu(cpu) - free_vmcs(per_cpu(vmxarea, cpu)); -} - -static __init int alloc_kvm_area(void) -{ - int cpu; - - for_each_online_cpu(cpu) { - struct vmcs *vmcs; - - vmcs = alloc_vmcs_cpu(cpu); - if (!vmcs) { - free_kvm_area(); - return -ENOMEM; - } - - per_cpu(vmxarea, cpu) = vmcs; - } - return 0; -} - -static __init int hardware_setup(void) -{ - if (setup_vmcs_config(&vmcs_config) < 0) - return -EIO; - return alloc_kvm_area(); -} - -static __exit void hardware_unsetup(void) -{ - free_kvm_area(); -} - -static void fix_pmode_dataseg(int seg, struct kvm_save_segment *save) -{ - struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg]; - - if (vmcs_readl(sf->base) == save->base && (save->base & AR_S_MASK)) { - vmcs_write16(sf->selector, save->selector); - vmcs_writel(sf->base, save->base); - vmcs_write32(sf->limit, save->limit); - vmcs_write32(sf->ar_bytes, save->ar); - } else { - u32 dpl = (vmcs_read16(sf->selector) & SELECTOR_RPL_MASK) - << AR_DPL_SHIFT; - vmcs_write32(sf->ar_bytes, 0x93 | dpl); - } -} - -static void enter_pmode(struct kvm_vcpu *vcpu) -{ - unsigned long flags; - - vcpu->rmode.active = 0; - - vmcs_writel(GUEST_TR_BASE, vcpu->rmode.tr.base); - vmcs_write32(GUEST_TR_LIMIT, vcpu->rmode.tr.limit); - vmcs_write32(GUEST_TR_AR_BYTES, vcpu->rmode.tr.ar); - - flags = vmcs_readl(GUEST_RFLAGS); - flags &= ~(IOPL_MASK | X86_EFLAGS_VM); - flags |= (vcpu->rmode.save_iopl << IOPL_SHIFT); - vmcs_writel(GUEST_RFLAGS, flags); - - vmcs_writel(GUEST_CR4, (vmcs_readl(GUEST_CR4) & ~X86_CR4_VME) | - (vmcs_readl(CR4_READ_SHADOW) & X86_CR4_VME)); - - update_exception_bitmap(vcpu); - - fix_pmode_dataseg(VCPU_SREG_ES, &vcpu->rmode.es); - fix_pmode_dataseg(VCPU_SREG_DS, &vcpu->rmode.ds); - fix_pmode_dataseg(VCPU_SREG_GS, &vcpu->rmode.gs); - fix_pmode_dataseg(VCPU_SREG_FS, &vcpu->rmode.fs); - - vmcs_write16(GUEST_SS_SELECTOR, 0); - vmcs_write32(GUEST_SS_AR_BYTES, 0x93); - - vmcs_write16(GUEST_CS_SELECTOR, - vmcs_read16(GUEST_CS_SELECTOR) & ~SELECTOR_RPL_MASK); - vmcs_write32(GUEST_CS_AR_BYTES, 0x9b); -} - -static gva_t rmode_tss_base(struct kvm* kvm) -{ - gfn_t base_gfn = kvm->memslots[0].base_gfn + kvm->memslots[0].npages - 3; - return base_gfn << PAGE_SHIFT; -} - -static void fix_rmode_seg(int seg, struct kvm_save_segment *save) -{ - struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg]; - - save->selector = vmcs_read16(sf->selector); - save->base = vmcs_readl(sf->base); - save->limit = vmcs_read32(sf->limit); - save->ar = vmcs_read32(sf->ar_bytes); - vmcs_write16(sf->selector, vmcs_readl(sf->base) >> 4); - vmcs_write32(sf->limit, 0xffff); - vmcs_write32(sf->ar_bytes, 0xf3); -} - -static void enter_rmode(struct kvm_vcpu *vcpu) -{ - unsigned long flags; - - vcpu->rmode.active = 1; - - vcpu->rmode.tr.base = vmcs_readl(GUEST_TR_BASE); - vmcs_writel(GUEST_TR_BASE, rmode_tss_base(vcpu->kvm)); - - vcpu->rmode.tr.limit = vmcs_read32(GUEST_TR_LIMIT); - vmcs_write32(GUEST_TR_LIMIT, RMODE_TSS_SIZE - 1); - - vcpu->rmode.tr.ar = vmcs_read32(GUEST_TR_AR_BYTES); - vmcs_write32(GUEST_TR_AR_BYTES, 0x008b); - - flags = vmcs_readl(GUEST_RFLAGS); - vcpu->rmode.save_iopl = (flags & IOPL_MASK) >> IOPL_SHIFT; - - flags |= IOPL_MASK | X86_EFLAGS_VM; - - vmcs_writel(GUEST_RFLAGS, flags); - vmcs_writel(GUEST_CR4, vmcs_readl(GUEST_CR4) | X86_CR4_VME); - update_exception_bitmap(vcpu); - - vmcs_write16(GUEST_SS_SELECTOR, vmcs_readl(GUEST_SS_BASE) >> 4); - vmcs_write32(GUEST_SS_LIMIT, 0xffff); - vmcs_write32(GUEST_SS_AR_BYTES, 0xf3); - - vmcs_write32(GUEST_CS_AR_BYTES, 0xf3); - vmcs_write32(GUEST_CS_LIMIT, 0xffff); - if (vmcs_readl(GUEST_CS_BASE) == 0xffff0000) - vmcs_writel(GUEST_CS_BASE, 0xf0000); - vmcs_write16(GUEST_CS_SELECTOR, vmcs_readl(GUEST_CS_BASE) >> 4); - - fix_rmode_seg(VCPU_SREG_ES, &vcpu->rmode.es); - fix_rmode_seg(VCPU_SREG_DS, &vcpu->rmode.ds); - fix_rmode_seg(VCPU_SREG_GS, &vcpu->rmode.gs); - fix_rmode_seg(VCPU_SREG_FS, &vcpu->rmode.fs); - - kvm_mmu_reset_context(vcpu); - init_rmode_tss(vcpu->kvm); -} - -#ifdef CONFIG_X86_64 - -static void enter_lmode(struct kvm_vcpu *vcpu) -{ - u32 guest_tr_ar; - - guest_tr_ar = vmcs_read32(GUEST_TR_AR_BYTES); - if ((guest_tr_ar & AR_TYPE_MASK) != AR_TYPE_BUSY_64_TSS) { - printk(KERN_DEBUG "%s: tss fixup for long mode. \n", - __FUNCTION__); - vmcs_write32(GUEST_TR_AR_BYTES, - (guest_tr_ar & ~AR_TYPE_MASK) - | AR_TYPE_BUSY_64_TSS); - } - - vcpu->shadow_efer |= EFER_LMA; - - find_msr_entry(to_vmx(vcpu), MSR_EFER)->data |= EFER_LMA | EFER_LME; - vmcs_write32(VM_ENTRY_CONTROLS, - vmcs_read32(VM_ENTRY_CONTROLS) - | VM_ENTRY_IA32E_MODE); -} - -static void exit_lmode(struct kvm_vcpu *vcpu) -{ - vcpu->shadow_efer &= ~EFER_LMA; - - vmcs_write32(VM_ENTRY_CONTROLS, - vmcs_read32(VM_ENTRY_CONTROLS) - & ~VM_ENTRY_IA32E_MODE); -} - -#endif - -static void vmx_decache_cr4_guest_bits(struct kvm_vcpu *vcpu) -{ - vcpu->cr4 &= KVM_GUEST_CR4_MASK; - vcpu->cr4 |= vmcs_readl(GUEST_CR4) & ~KVM_GUEST_CR4_MASK; -} - -static void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) -{ - vmx_fpu_deactivate(vcpu); - - if (vcpu->rmode.active && (cr0 & X86_CR0_PE)) - enter_pmode(vcpu); - - if (!vcpu->rmode.active && !(cr0 & X86_CR0_PE)) - enter_rmode(vcpu); - -#ifdef CONFIG_X86_64 - if (vcpu->shadow_efer & EFER_LME) { - if (!is_paging(vcpu) && (cr0 & X86_CR0_PG)) - enter_lmode(vcpu); - if (is_paging(vcpu) && !(cr0 & X86_CR0_PG)) - exit_lmode(vcpu); - } -#endif - - vmcs_writel(CR0_READ_SHADOW, cr0); - vmcs_writel(GUEST_CR0, - (cr0 & ~KVM_GUEST_CR0_MASK) | KVM_VM_CR0_ALWAYS_ON); - vcpu->cr0 = cr0; - - if (!(cr0 & X86_CR0_TS) || !(cr0 & X86_CR0_PE)) - vmx_fpu_activate(vcpu); -} - -static void vmx_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) -{ - vmcs_writel(GUEST_CR3, cr3); - if (vcpu->cr0 & X86_CR0_PE) - vmx_fpu_deactivate(vcpu); -} - -static void vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) -{ - vmcs_writel(CR4_READ_SHADOW, cr4); - vmcs_writel(GUEST_CR4, cr4 | (vcpu->rmode.active ? - KVM_RMODE_VM_CR4_ALWAYS_ON : KVM_PMODE_VM_CR4_ALWAYS_ON)); - vcpu->cr4 = cr4; -} - -#ifdef CONFIG_X86_64 - -static void vmx_set_efer(struct kvm_vcpu *vcpu, u64 efer) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - struct kvm_msr_entry *msr = find_msr_entry(vmx, MSR_EFER); - - vcpu->shadow_efer = efer; - if (efer & EFER_LMA) { - vmcs_write32(VM_ENTRY_CONTROLS, - vmcs_read32(VM_ENTRY_CONTROLS) | - VM_ENTRY_IA32E_MODE); - msr->data = efer; - - } else { - vmcs_write32(VM_ENTRY_CONTROLS, - vmcs_read32(VM_ENTRY_CONTROLS) & - ~VM_ENTRY_IA32E_MODE); - - msr->data = efer & ~EFER_LME; - } - setup_msrs(vmx); -} - -#endif - -static u64 vmx_get_segment_base(struct kvm_vcpu *vcpu, int seg) -{ - struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg]; - - return vmcs_readl(sf->base); -} - -static void vmx_get_segment(struct kvm_vcpu *vcpu, - struct kvm_segment *var, int seg) -{ - struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg]; - u32 ar; - - var->base = vmcs_readl(sf->base); - var->limit = vmcs_read32(sf->limit); - var->selector = vmcs_read16(sf->selector); - ar = vmcs_read32(sf->ar_bytes); - if (ar & AR_UNUSABLE_MASK) - ar = 0; - var->type = ar & 15; - var->s = (ar >> 4) & 1; - var->dpl = (ar >> 5) & 3; - var->present = (ar >> 7) & 1; - var->avl = (ar >> 12) & 1; - var->l = (ar >> 13) & 1; - var->db = (ar >> 14) & 1; - var->g = (ar >> 15) & 1; - var->unusable = (ar >> 16) & 1; -} - -static u32 vmx_segment_access_rights(struct kvm_segment *var) -{ - u32 ar; - - if (var->unusable) - ar = 1 << 16; - else { - ar = var->type & 15; - ar |= (var->s & 1) << 4; - ar |= (var->dpl & 3) << 5; - ar |= (var->present & 1) << 7; - ar |= (var->avl & 1) << 12; - ar |= (var->l & 1) << 13; - ar |= (var->db & 1) << 14; - ar |= (var->g & 1) << 15; - } - if (ar == 0) /* a 0 value means unusable */ - ar = AR_UNUSABLE_MASK; - - return ar; -} - -static void vmx_set_segment(struct kvm_vcpu *vcpu, - struct kvm_segment *var, int seg) -{ - struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg]; - u32 ar; - - if (vcpu->rmode.active && seg == VCPU_SREG_TR) { - vcpu->rmode.tr.selector = var->selector; - vcpu->rmode.tr.base = var->base; - vcpu->rmode.tr.limit = var->limit; - vcpu->rmode.tr.ar = vmx_segment_access_rights(var); - return; - } - vmcs_writel(sf->base, var->base); - vmcs_write32(sf->limit, var->limit); - vmcs_write16(sf->selector, var->selector); - if (vcpu->rmode.active && var->s) { - /* - * Hack real-mode segments into vm86 compatibility. - */ - if (var->base == 0xffff0000 && var->selector == 0xf000) - vmcs_writel(sf->base, 0xf0000); - ar = 0xf3; - } else - ar = vmx_segment_access_rights(var); - vmcs_write32(sf->ar_bytes, ar); -} - -static void vmx_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l) -{ - u32 ar = vmcs_read32(GUEST_CS_AR_BYTES); - - *db = (ar >> 14) & 1; - *l = (ar >> 13) & 1; -} - -static void vmx_get_idt(struct kvm_vcpu *vcpu, struct descriptor_table *dt) -{ - dt->limit = vmcs_read32(GUEST_IDTR_LIMIT); - dt->base = vmcs_readl(GUEST_IDTR_BASE); -} - -static void vmx_set_idt(struct kvm_vcpu *vcpu, struct descriptor_table *dt) -{ - vmcs_write32(GUEST_IDTR_LIMIT, dt->limit); - vmcs_writel(GUEST_IDTR_BASE, dt->base); -} - -static void vmx_get_gdt(struct kvm_vcpu *vcpu, struct descriptor_table *dt) -{ - dt->limit = vmcs_read32(GUEST_GDTR_LIMIT); - dt->base = vmcs_readl(GUEST_GDTR_BASE); -} - -static void vmx_set_gdt(struct kvm_vcpu *vcpu, struct descriptor_table *dt) -{ - vmcs_write32(GUEST_GDTR_LIMIT, dt->limit); - vmcs_writel(GUEST_GDTR_BASE, dt->base); -} - -static int init_rmode_tss(struct kvm* kvm) -{ - struct page *p1, *p2, *p3; - gfn_t fn = rmode_tss_base(kvm) >> PAGE_SHIFT; - char *page; - - p1 = gfn_to_page(kvm, fn++); - p2 = gfn_to_page(kvm, fn++); - p3 = gfn_to_page(kvm, fn); - - if (!p1 || !p2 || !p3) { - kvm_printf(kvm,"%s: gfn_to_page failed\n", __FUNCTION__); - return 0; - } - - page = kmap_atomic(p1, KM_USER0); - clear_page(page); - *(u16*)(page + 0x66) = TSS_BASE_SIZE + TSS_REDIRECTION_SIZE; - kunmap_atomic(page, KM_USER0); - - page = kmap_atomic(p2, KM_USER0); - clear_page(page); - kunmap_atomic(page, KM_USER0); - - page = kmap_atomic(p3, KM_USER0); - clear_page(page); - *(page + RMODE_TSS_SIZE - 2 * PAGE_SIZE - 1) = ~0; - kunmap_atomic(page, KM_USER0); - - return 1; -} - -static void seg_setup(int seg) -{ - struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg]; - - vmcs_write16(sf->selector, 0); - vmcs_writel(sf->base, 0); - vmcs_write32(sf->limit, 0xffff); - vmcs_write32(sf->ar_bytes, 0x93); -} - -/* - * Sets up the vmcs for emulated real mode. - */ -static int vmx_vcpu_setup(struct vcpu_vmx *vmx) -{ - u32 host_sysenter_cs; - u32 junk; - unsigned long a; - struct descriptor_table dt; - int i; - int ret = 0; - unsigned long kvm_vmx_return; - u64 msr; - u32 exec_control; - - if (!init_rmode_tss(vmx->vcpu.kvm)) { - ret = -ENOMEM; - goto out; - } - - vmx->vcpu.rmode.active = 0; - - vmx->vcpu.regs[VCPU_REGS_RDX] = get_rdx_init_val(); - set_cr8(&vmx->vcpu, 0); - msr = 0xfee00000 | MSR_IA32_APICBASE_ENABLE; - if (vmx->vcpu.vcpu_id == 0) - msr |= MSR_IA32_APICBASE_BSP; - kvm_set_apic_base(&vmx->vcpu, msr); - - fx_init(&vmx->vcpu); - - /* - * GUEST_CS_BASE should really be 0xffff0000, but VT vm86 mode - * insists on having GUEST_CS_BASE == GUEST_CS_SELECTOR << 4. Sigh. - */ - if (vmx->vcpu.vcpu_id == 0) { - vmcs_write16(GUEST_CS_SELECTOR, 0xf000); - vmcs_writel(GUEST_CS_BASE, 0x000f0000); - } else { - vmcs_write16(GUEST_CS_SELECTOR, vmx->vcpu.sipi_vector << 8); - vmcs_writel(GUEST_CS_BASE, vmx->vcpu.sipi_vector << 12); - } - vmcs_write32(GUEST_CS_LIMIT, 0xffff); - vmcs_write32(GUEST_CS_AR_BYTES, 0x9b); - - seg_setup(VCPU_SREG_DS); - seg_setup(VCPU_SREG_ES); - seg_setup(VCPU_SREG_FS); - seg_setup(VCPU_SREG_GS); - seg_setup(VCPU_SREG_SS); - - vmcs_write16(GUEST_TR_SELECTOR, 0); - vmcs_writel(GUEST_TR_BASE, 0); - vmcs_write32(GUEST_TR_LIMIT, 0xffff); - vmcs_write32(GUEST_TR_AR_BYTES, 0x008b); - - vmcs_write16(GUEST_LDTR_SELECTOR, 0); - vmcs_writel(GUEST_LDTR_BASE, 0); - vmcs_write32(GUEST_LDTR_LIMIT, 0xffff); - vmcs_write32(GUEST_LDTR_AR_BYTES, 0x00082); - - vmcs_write32(GUEST_SYSENTER_CS, 0); - vmcs_writel(GUEST_SYSENTER_ESP, 0); - vmcs_writel(GUEST_SYSENTER_EIP, 0); - - vmcs_writel(GUEST_RFLAGS, 0x02); - if (vmx->vcpu.vcpu_id == 0) - vmcs_writel(GUEST_RIP, 0xfff0); - else - vmcs_writel(GUEST_RIP, 0); - vmcs_writel(GUEST_RSP, 0); - - //todo: dr0 = dr1 = dr2 = dr3 = 0; dr6 = 0xffff0ff0 - vmcs_writel(GUEST_DR7, 0x400); - - vmcs_writel(GUEST_GDTR_BASE, 0); - vmcs_write32(GUEST_GDTR_LIMIT, 0xffff); - - vmcs_writel(GUEST_IDTR_BASE, 0); - vmcs_write32(GUEST_IDTR_LIMIT, 0xffff); - - vmcs_write32(GUEST_ACTIVITY_STATE, 0); - vmcs_write32(GUEST_INTERRUPTIBILITY_INFO, 0); - vmcs_write32(GUEST_PENDING_DBG_EXCEPTIONS, 0); - - /* I/O */ - vmcs_write64(IO_BITMAP_A, page_to_phys(vmx_io_bitmap_a)); - vmcs_write64(IO_BITMAP_B, page_to_phys(vmx_io_bitmap_b)); - - guest_write_tsc(0); - - vmcs_write64(VMCS_LINK_POINTER, -1ull); /* 22.3.1.5 */ - - /* Special registers */ - vmcs_write64(GUEST_IA32_DEBUGCTL, 0); - - /* Control */ - vmcs_write32(PIN_BASED_VM_EXEC_CONTROL, - vmcs_config.pin_based_exec_ctrl); - - exec_control = vmcs_config.cpu_based_exec_ctrl; - if (!vm_need_tpr_shadow(vmx->vcpu.kvm)) { - exec_control &= ~CPU_BASED_TPR_SHADOW; -#ifdef CONFIG_X86_64 - exec_control |= CPU_BASED_CR8_STORE_EXITING | - CPU_BASED_CR8_LOAD_EXITING; -#endif - } - vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, exec_control); - - vmcs_write32(PAGE_FAULT_ERROR_CODE_MASK, 0); - vmcs_write32(PAGE_FAULT_ERROR_CODE_MATCH, 0); - vmcs_write32(CR3_TARGET_COUNT, 0); /* 22.2.1 */ - - vmcs_writel(HOST_CR0, read_cr0()); /* 22.2.3 */ - vmcs_writel(HOST_CR4, read_cr4()); /* 22.2.3, 22.2.5 */ - vmcs_writel(HOST_CR3, read_cr3()); /* 22.2.3 FIXME: shadow tables */ - - vmcs_write16(HOST_CS_SELECTOR, __KERNEL_CS); /* 22.2.4 */ - vmcs_write16(HOST_DS_SELECTOR, __KERNEL_DS); /* 22.2.4 */ - vmcs_write16(HOST_ES_SELECTOR, __KERNEL_DS); /* 22.2.4 */ - vmcs_write16(HOST_FS_SELECTOR, read_fs()); /* 22.2.4 */ - vmcs_write16(HOST_GS_SELECTOR, read_gs()); /* 22.2.4 */ - vmcs_write16(HOST_SS_SELECTOR, __KERNEL_DS); /* 22.2.4 */ -#ifdef CONFIG_X86_64 - rdmsrl(MSR_FS_BASE, a); - vmcs_writel(HOST_FS_BASE, a); /* 22.2.4 */ - rdmsrl(MSR_GS_BASE, a); - vmcs_writel(HOST_GS_BASE, a); /* 22.2.4 */ -#else - vmcs_writel(HOST_FS_BASE, 0); /* 22.2.4 */ - vmcs_writel(HOST_GS_BASE, 0); /* 22.2.4 */ -#endif - - vmcs_write16(HOST_TR_SELECTOR, GDT_ENTRY_TSS*8); /* 22.2.4 */ - - get_idt(&dt); - vmcs_writel(HOST_IDTR_BASE, dt.base); /* 22.2.4 */ - - asm ("mov $.Lkvm_vmx_return, %0" : "=r"(kvm_vmx_return)); - vmcs_writel(HOST_RIP, kvm_vmx_return); /* 22.2.5 */ - vmcs_write32(VM_EXIT_MSR_STORE_COUNT, 0); - vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, 0); - vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, 0); - - rdmsr(MSR_IA32_SYSENTER_CS, host_sysenter_cs, junk); - vmcs_write32(HOST_IA32_SYSENTER_CS, host_sysenter_cs); - rdmsrl(MSR_IA32_SYSENTER_ESP, a); - vmcs_writel(HOST_IA32_SYSENTER_ESP, a); /* 22.2.3 */ - rdmsrl(MSR_IA32_SYSENTER_EIP, a); - vmcs_writel(HOST_IA32_SYSENTER_EIP, a); /* 22.2.3 */ - - for (i = 0; i < NR_VMX_MSR; ++i) { - u32 index = vmx_msr_index[i]; - u32 data_low, data_high; - u64 data; - int j = vmx->nmsrs; - - if (rdmsr_safe(index, &data_low, &data_high) < 0) - continue; - if (wrmsr_safe(index, data_low, data_high) < 0) - continue; - data = data_low | ((u64)data_high << 32); - vmx->host_msrs[j].index = index; - vmx->host_msrs[j].reserved = 0; - vmx->host_msrs[j].data = data; - vmx->guest_msrs[j] = vmx->host_msrs[j]; - ++vmx->nmsrs; - } - - setup_msrs(vmx); - - vmcs_write32(VM_EXIT_CONTROLS, vmcs_config.vmexit_ctrl); - - /* 22.2.1, 20.8.1 */ - vmcs_write32(VM_ENTRY_CONTROLS, vmcs_config.vmentry_ctrl); - - vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, 0); /* 22.2.1 */ - -#ifdef CONFIG_X86_64 - vmcs_write64(VIRTUAL_APIC_PAGE_ADDR, 0); - if (vm_need_tpr_shadow(vmx->vcpu.kvm)) - vmcs_write64(VIRTUAL_APIC_PAGE_ADDR, - page_to_phys(vmx->vcpu.apic->regs_page)); - vmcs_write32(TPR_THRESHOLD, 0); -#endif - - vmcs_writel(CR0_GUEST_HOST_MASK, ~0UL); - vmcs_writel(CR4_GUEST_HOST_MASK, KVM_GUEST_CR4_MASK); - - vmx->vcpu.cr0 = 0x60000010; - vmx_set_cr0(&vmx->vcpu, vmx->vcpu.cr0); // enter rmode - vmx_set_cr4(&vmx->vcpu, 0); -#ifdef CONFIG_X86_64 - vmx_set_efer(&vmx->vcpu, 0); -#endif - vmx_fpu_activate(&vmx->vcpu); - update_exception_bitmap(&vmx->vcpu); - - return 0; - -out: - return ret; -} - -static void vmx_vcpu_reset(struct kvm_vcpu *vcpu) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - - vmx_vcpu_setup(vmx); -} - -static void inject_rmode_irq(struct kvm_vcpu *vcpu, int irq) -{ - u16 ent[2]; - u16 cs; - u16 ip; - unsigned long flags; - unsigned long ss_base = vmcs_readl(GUEST_SS_BASE); - u16 sp = vmcs_readl(GUEST_RSP); - u32 ss_limit = vmcs_read32(GUEST_SS_LIMIT); - - if (sp > ss_limit || sp < 6 ) { - vcpu_printf(vcpu, "%s: #SS, rsp 0x%lx ss 0x%lx limit 0x%x\n", - __FUNCTION__, - vmcs_readl(GUEST_RSP), - vmcs_readl(GUEST_SS_BASE), - vmcs_read32(GUEST_SS_LIMIT)); - return; - } - - if (emulator_read_std(irq * sizeof(ent), &ent, sizeof(ent), vcpu) != - X86EMUL_CONTINUE) { - vcpu_printf(vcpu, "%s: read guest err\n", __FUNCTION__); - return; - } - - flags = vmcs_readl(GUEST_RFLAGS); - cs = vmcs_readl(GUEST_CS_BASE) >> 4; - ip = vmcs_readl(GUEST_RIP); - - - if (emulator_write_emulated(ss_base + sp - 2, &flags, 2, vcpu) != X86EMUL_CONTINUE || - emulator_write_emulated(ss_base + sp - 4, &cs, 2, vcpu) != X86EMUL_CONTINUE || - emulator_write_emulated(ss_base + sp - 6, &ip, 2, vcpu) != X86EMUL_CONTINUE) { - vcpu_printf(vcpu, "%s: write guest err\n", __FUNCTION__); - return; - } - - vmcs_writel(GUEST_RFLAGS, flags & - ~( X86_EFLAGS_IF | X86_EFLAGS_AC | X86_EFLAGS_TF)); - vmcs_write16(GUEST_CS_SELECTOR, ent[1]) ; - vmcs_writel(GUEST_CS_BASE, ent[1] << 4); - vmcs_writel(GUEST_RIP, ent[0]); - vmcs_writel(GUEST_RSP, (vmcs_readl(GUEST_RSP) & ~0xffff) | (sp - 6)); -} - -static void vmx_inject_irq(struct kvm_vcpu *vcpu, int irq) -{ - if (vcpu->rmode.active) { - inject_rmode_irq(vcpu, irq); - return; - } - vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, - irq | INTR_TYPE_EXT_INTR | INTR_INFO_VALID_MASK); -} - -static void kvm_do_inject_irq(struct kvm_vcpu *vcpu) -{ - int word_index = __ffs(vcpu->irq_summary); - int bit_index = __ffs(vcpu->irq_pending[word_index]); - int irq = word_index * BITS_PER_LONG + bit_index; - - clear_bit(bit_index, &vcpu->irq_pending[word_index]); - if (!vcpu->irq_pending[word_index]) - clear_bit(word_index, &vcpu->irq_summary); - vmx_inject_irq(vcpu, irq); -} - - -static void do_interrupt_requests(struct kvm_vcpu *vcpu, - struct kvm_run *kvm_run) -{ - u32 cpu_based_vm_exec_control; - - vcpu->interrupt_window_open = - ((vmcs_readl(GUEST_RFLAGS) & X86_EFLAGS_IF) && - (vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & 3) == 0); - - if (vcpu->interrupt_window_open && - vcpu->irq_summary && - !(vmcs_read32(VM_ENTRY_INTR_INFO_FIELD) & INTR_INFO_VALID_MASK)) - /* - * If interrupts enabled, and not blocked by sti or mov ss. Good. - */ - kvm_do_inject_irq(vcpu); - - cpu_based_vm_exec_control = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL); - if (!vcpu->interrupt_window_open && - (vcpu->irq_summary || kvm_run->request_interrupt_window)) - /* - * Interrupts blocked. Wait for unblock. - */ - cpu_based_vm_exec_control |= CPU_BASED_VIRTUAL_INTR_PENDING; - else - cpu_based_vm_exec_control &= ~CPU_BASED_VIRTUAL_INTR_PENDING; - vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, cpu_based_vm_exec_control); -} - -static void kvm_guest_debug_pre(struct kvm_vcpu *vcpu) -{ - struct kvm_guest_debug *dbg = &vcpu->guest_debug; - - set_debugreg(dbg->bp[0], 0); - set_debugreg(dbg->bp[1], 1); - set_debugreg(dbg->bp[2], 2); - set_debugreg(dbg->bp[3], 3); - - if (dbg->singlestep) { - unsigned long flags; - - flags = vmcs_readl(GUEST_RFLAGS); - flags |= X86_EFLAGS_TF | X86_EFLAGS_RF; - vmcs_writel(GUEST_RFLAGS, flags); - } -} - -static int handle_rmode_exception(struct kvm_vcpu *vcpu, - int vec, u32 err_code) -{ - if (!vcpu->rmode.active) - return 0; - - /* - * Instruction with address size override prefix opcode 0x67 - * Cause the #SS fault with 0 error code in VM86 mode. - */ - if (((vec == GP_VECTOR) || (vec == SS_VECTOR)) && err_code == 0) - if (emulate_instruction(vcpu, NULL, 0, 0) == EMULATE_DONE) - return 1; - return 0; -} - -static int handle_exception(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) -{ - u32 intr_info, error_code; - unsigned long cr2, rip; - u32 vect_info; - enum emulation_result er; - int r; - - vect_info = vmcs_read32(IDT_VECTORING_INFO_FIELD); - intr_info = vmcs_read32(VM_EXIT_INTR_INFO); - - if ((vect_info & VECTORING_INFO_VALID_MASK) && - !is_page_fault(intr_info)) { - printk(KERN_ERR "%s: unexpected, vectoring info 0x%x " - "intr info 0x%x\n", __FUNCTION__, vect_info, intr_info); - } - - if (!irqchip_in_kernel(vcpu->kvm) && is_external_interrupt(vect_info)) { - int irq = vect_info & VECTORING_INFO_VECTOR_MASK; - set_bit(irq, vcpu->irq_pending); - set_bit(irq / BITS_PER_LONG, &vcpu->irq_summary); - } - - if ((intr_info & INTR_INFO_INTR_TYPE_MASK) == 0x200) /* nmi */ - return 1; /* already handled by vmx_vcpu_run() */ - - if (is_no_device(intr_info)) { - vmx_fpu_activate(vcpu); - return 1; - } - - error_code = 0; - rip = vmcs_readl(GUEST_RIP); - if (intr_info & INTR_INFO_DELIEVER_CODE_MASK) - error_code = vmcs_read32(VM_EXIT_INTR_ERROR_CODE); - if (is_page_fault(intr_info)) { - cr2 = vmcs_readl(EXIT_QUALIFICATION); - - mutex_lock(&vcpu->kvm->lock); - r = kvm_mmu_page_fault(vcpu, cr2, error_code); - if (r < 0) { - mutex_unlock(&vcpu->kvm->lock); - return r; - } - if (!r) { - mutex_unlock(&vcpu->kvm->lock); - return 1; - } - - er = emulate_instruction(vcpu, kvm_run, cr2, error_code); - mutex_unlock(&vcpu->kvm->lock); - - switch (er) { - case EMULATE_DONE: - return 1; - case EMULATE_DO_MMIO: - ++vcpu->stat.mmio_exits; - return 0; - case EMULATE_FAIL: - kvm_report_emulation_failure(vcpu, "pagetable"); - break; - default: - BUG(); - } - } - - if (vcpu->rmode.active && - handle_rmode_exception(vcpu, intr_info & INTR_INFO_VECTOR_MASK, - error_code)) { - if (vcpu->halt_request) { - vcpu->halt_request = 0; - return kvm_emulate_halt(vcpu); - } - return 1; - } - - if ((intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK)) == (INTR_TYPE_EXCEPTION | 1)) { - kvm_run->exit_reason = KVM_EXIT_DEBUG; - return 0; - } - kvm_run->exit_reason = KVM_EXIT_EXCEPTION; - kvm_run->ex.exception = intr_info & INTR_INFO_VECTOR_MASK; - kvm_run->ex.error_code = error_code; - return 0; -} - -static int handle_external_interrupt(struct kvm_vcpu *vcpu, - struct kvm_run *kvm_run) -{ - ++vcpu->stat.irq_exits; - return 1; -} - -static int handle_triple_fault(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) -{ - kvm_run->exit_reason = KVM_EXIT_SHUTDOWN; - return 0; -} - -static int handle_io(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) -{ - unsigned long exit_qualification; - int size, down, in, string, rep; - unsigned port; - - ++vcpu->stat.io_exits; - exit_qualification = vmcs_readl(EXIT_QUALIFICATION); - string = (exit_qualification & 16) != 0; - - if (string) { - if (emulate_instruction(vcpu, kvm_run, 0, 0) == EMULATE_DO_MMIO) - return 0; - return 1; - } - - size = (exit_qualification & 7) + 1; - in = (exit_qualification & 8) != 0; - down = (vmcs_readl(GUEST_RFLAGS) & X86_EFLAGS_DF) != 0; - rep = (exit_qualification & 32) != 0; - port = exit_qualification >> 16; - - return kvm_emulate_pio(vcpu, kvm_run, in, size, port); -} - -static void -vmx_patch_hypercall(struct kvm_vcpu *vcpu, unsigned char *hypercall) -{ - /* - * Patch in the VMCALL instruction: - */ - hypercall[0] = 0x0f; - hypercall[1] = 0x01; - hypercall[2] = 0xc1; - hypercall[3] = 0xc3; -} - -static int handle_cr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) -{ - unsigned long exit_qualification; - int cr; - int reg; - - exit_qualification = vmcs_readl(EXIT_QUALIFICATION); - cr = exit_qualification & 15; - reg = (exit_qualification >> 8) & 15; - switch ((exit_qualification >> 4) & 3) { - case 0: /* mov to cr */ - switch (cr) { - case 0: - vcpu_load_rsp_rip(vcpu); - set_cr0(vcpu, vcpu->regs[reg]); - skip_emulated_instruction(vcpu); - return 1; - case 3: - vcpu_load_rsp_rip(vcpu); - set_cr3(vcpu, vcpu->regs[reg]); - skip_emulated_instruction(vcpu); - return 1; - case 4: - vcpu_load_rsp_rip(vcpu); - set_cr4(vcpu, vcpu->regs[reg]); - skip_emulated_instruction(vcpu); - return 1; - case 8: - vcpu_load_rsp_rip(vcpu); - set_cr8(vcpu, vcpu->regs[reg]); - skip_emulated_instruction(vcpu); - kvm_run->exit_reason = KVM_EXIT_SET_TPR; - return 0; - }; - break; - case 2: /* clts */ - vcpu_load_rsp_rip(vcpu); - vmx_fpu_deactivate(vcpu); - vcpu->cr0 &= ~X86_CR0_TS; - vmcs_writel(CR0_READ_SHADOW, vcpu->cr0); - vmx_fpu_activate(vcpu); - skip_emulated_instruction(vcpu); - return 1; - case 1: /*mov from cr*/ - switch (cr) { - case 3: - vcpu_load_rsp_rip(vcpu); - vcpu->regs[reg] = vcpu->cr3; - vcpu_put_rsp_rip(vcpu); - skip_emulated_instruction(vcpu); - return 1; - case 8: - vcpu_load_rsp_rip(vcpu); - vcpu->regs[reg] = get_cr8(vcpu); - vcpu_put_rsp_rip(vcpu); - skip_emulated_instruction(vcpu); - return 1; - } - break; - case 3: /* lmsw */ - lmsw(vcpu, (exit_qualification >> LMSW_SOURCE_DATA_SHIFT) & 0x0f); - - skip_emulated_instruction(vcpu); - return 1; - default: - break; - } - kvm_run->exit_reason = 0; - pr_unimpl(vcpu, "unhandled control register: op %d cr %d\n", - (int)(exit_qualification >> 4) & 3, cr); - return 0; -} - -static int handle_dr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) -{ - unsigned long exit_qualification; - unsigned long val; - int dr, reg; - - /* - * FIXME: this code assumes the host is debugging the guest. - * need to deal with guest debugging itself too. - */ - exit_qualification = vmcs_readl(EXIT_QUALIFICATION); - dr = exit_qualification & 7; - reg = (exit_qualification >> 8) & 15; - vcpu_load_rsp_rip(vcpu); - if (exit_qualification & 16) { - /* mov from dr */ - switch (dr) { - case 6: - val = 0xffff0ff0; - break; - case 7: - val = 0x400; - break; - default: - val = 0; - } - vcpu->regs[reg] = val; - } else { - /* mov to dr */ - } - vcpu_put_rsp_rip(vcpu); - skip_emulated_instruction(vcpu); - return 1; -} - -static int handle_cpuid(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) -{ - kvm_emulate_cpuid(vcpu); - return 1; -} - -static int handle_rdmsr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) -{ - u32 ecx = vcpu->regs[VCPU_REGS_RCX]; - u64 data; - - if (vmx_get_msr(vcpu, ecx, &data)) { - vmx_inject_gp(vcpu, 0); - return 1; - } - - /* FIXME: handling of bits 32:63 of rax, rdx */ - vcpu->regs[VCPU_REGS_RAX] = data & -1u; - vcpu->regs[VCPU_REGS_RDX] = (data >> 32) & -1u; - skip_emulated_instruction(vcpu); - return 1; -} - -static int handle_wrmsr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) -{ - u32 ecx = vcpu->regs[VCPU_REGS_RCX]; - u64 data = (vcpu->regs[VCPU_REGS_RAX] & -1u) - | ((u64)(vcpu->regs[VCPU_REGS_RDX] & -1u) << 32); - - if (vmx_set_msr(vcpu, ecx, data) != 0) { - vmx_inject_gp(vcpu, 0); - return 1; - } - - skip_emulated_instruction(vcpu); - return 1; -} - -static int handle_tpr_below_threshold(struct kvm_vcpu *vcpu, - struct kvm_run *kvm_run) -{ - return 1; -} - -static int handle_interrupt_window(struct kvm_vcpu *vcpu, - struct kvm_run *kvm_run) -{ - u32 cpu_based_vm_exec_control; - - /* clear pending irq */ - cpu_based_vm_exec_control = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL); - cpu_based_vm_exec_control &= ~CPU_BASED_VIRTUAL_INTR_PENDING; - vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, cpu_based_vm_exec_control); - /* - * If the user space waits to inject interrupts, exit as soon as - * possible - */ - if (kvm_run->request_interrupt_window && - !vcpu->irq_summary) { - kvm_run->exit_reason = KVM_EXIT_IRQ_WINDOW_OPEN; - ++vcpu->stat.irq_window_exits; - return 0; - } - return 1; -} - -static int handle_halt(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) -{ - skip_emulated_instruction(vcpu); - return kvm_emulate_halt(vcpu); -} - -static int handle_vmcall(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) -{ - skip_emulated_instruction(vcpu); - return kvm_hypercall(vcpu, kvm_run); -} - -/* - * The exit handlers return 1 if the exit was handled fully and guest execution - * may resume. Otherwise they set the kvm_run parameter to indicate what needs - * to be done to userspace and return 0. - */ -static int (*kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu, - struct kvm_run *kvm_run) = { - [EXIT_REASON_EXCEPTION_NMI] = handle_exception, - [EXIT_REASON_EXTERNAL_INTERRUPT] = handle_external_interrupt, - [EXIT_REASON_TRIPLE_FAULT] = handle_triple_fault, - [EXIT_REASON_IO_INSTRUCTION] = handle_io, - [EXIT_REASON_CR_ACCESS] = handle_cr, - [EXIT_REASON_DR_ACCESS] = handle_dr, - [EXIT_REASON_CPUID] = handle_cpuid, - [EXIT_REASON_MSR_READ] = handle_rdmsr, - [EXIT_REASON_MSR_WRITE] = handle_wrmsr, - [EXIT_REASON_PENDING_INTERRUPT] = handle_interrupt_window, - [EXIT_REASON_HLT] = handle_halt, - [EXIT_REASON_VMCALL] = handle_vmcall, - [EXIT_REASON_TPR_BELOW_THRESHOLD] = handle_tpr_below_threshold -}; - -static const int kvm_vmx_max_exit_handlers = - ARRAY_SIZE(kvm_vmx_exit_handlers); - -/* - * The guest has exited. See if we can fix it or if we need userspace - * assistance. - */ -static int kvm_handle_exit(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) -{ - u32 vectoring_info = vmcs_read32(IDT_VECTORING_INFO_FIELD); - u32 exit_reason = vmcs_read32(VM_EXIT_REASON); - struct vcpu_vmx *vmx = to_vmx(vcpu); - - if (unlikely(vmx->fail)) { - kvm_run->exit_reason = KVM_EXIT_FAIL_ENTRY; - kvm_run->fail_entry.hardware_entry_failure_reason - = vmcs_read32(VM_INSTRUCTION_ERROR); - return 0; - } - - if ( (vectoring_info & VECTORING_INFO_VALID_MASK) && - exit_reason != EXIT_REASON_EXCEPTION_NMI ) - printk(KERN_WARNING "%s: unexpected, valid vectoring info and " - "exit reason is 0x%x\n", __FUNCTION__, exit_reason); - if (exit_reason < kvm_vmx_max_exit_handlers - && kvm_vmx_exit_handlers[exit_reason]) - return kvm_vmx_exit_handlers[exit_reason](vcpu, kvm_run); - else { - kvm_run->exit_reason = KVM_EXIT_UNKNOWN; - kvm_run->hw.hardware_exit_reason = exit_reason; - } - return 0; -} - -static void vmx_flush_tlb(struct kvm_vcpu *vcpu) -{ -} - -static void update_tpr_threshold(struct kvm_vcpu *vcpu) -{ - int max_irr, tpr; - - if (!vm_need_tpr_shadow(vcpu->kvm)) - return; - - if (!kvm_lapic_enabled(vcpu) || - ((max_irr = kvm_lapic_find_highest_irr(vcpu)) == -1)) { - vmcs_write32(TPR_THRESHOLD, 0); - return; - } - - tpr = (kvm_lapic_get_cr8(vcpu) & 0x0f) << 4; - vmcs_write32(TPR_THRESHOLD, (max_irr > tpr) ? tpr >> 4 : max_irr >> 4); -} - -static void enable_irq_window(struct kvm_vcpu *vcpu) -{ - u32 cpu_based_vm_exec_control; - - cpu_based_vm_exec_control = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL); - cpu_based_vm_exec_control |= CPU_BASED_VIRTUAL_INTR_PENDING; - vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, cpu_based_vm_exec_control); -} - -static void vmx_intr_assist(struct kvm_vcpu *vcpu) -{ - u32 idtv_info_field, intr_info_field; - int has_ext_irq, interrupt_window_open; - int vector; - - kvm_inject_pending_timer_irqs(vcpu); - update_tpr_threshold(vcpu); - - has_ext_irq = kvm_cpu_has_interrupt(vcpu); - intr_info_field = vmcs_read32(VM_ENTRY_INTR_INFO_FIELD); - idtv_info_field = vmcs_read32(IDT_VECTORING_INFO_FIELD); - if (intr_info_field & INTR_INFO_VALID_MASK) { - if (idtv_info_field & INTR_INFO_VALID_MASK) { - /* TODO: fault when IDT_Vectoring */ - printk(KERN_ERR "Fault when IDT_Vectoring\n"); - } - if (has_ext_irq) - enable_irq_window(vcpu); - return; - } - if (unlikely(idtv_info_field & INTR_INFO_VALID_MASK)) { - vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, idtv_info_field); - vmcs_write32(VM_ENTRY_INSTRUCTION_LEN, - vmcs_read32(VM_EXIT_INSTRUCTION_LEN)); - - if (unlikely(idtv_info_field & INTR_INFO_DELIEVER_CODE_MASK)) - vmcs_write32(VM_ENTRY_EXCEPTION_ERROR_CODE, - vmcs_read32(IDT_VECTORING_ERROR_CODE)); - if (unlikely(has_ext_irq)) - enable_irq_window(vcpu); - return; - } - if (!has_ext_irq) - return; - interrupt_window_open = - ((vmcs_readl(GUEST_RFLAGS) & X86_EFLAGS_IF) && - (vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & 3) == 0); - if (interrupt_window_open) { - vector = kvm_cpu_get_interrupt(vcpu); - vmx_inject_irq(vcpu, vector); - kvm_timer_intr_post(vcpu, vector); - } else - enable_irq_window(vcpu); -} - -static void vmx_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - u32 intr_info; - - /* - * Loading guest fpu may have cleared host cr0.ts - */ - vmcs_writel(HOST_CR0, read_cr0()); - - asm ( - /* Store host registers */ -#ifdef CONFIG_X86_64 - "push %%rax; push %%rbx; push %%rdx;" - "push %%rsi; push %%rdi; push %%rbp;" - "push %%r8; push %%r9; push %%r10; push %%r11;" - "push %%r12; push %%r13; push %%r14; push %%r15;" - "push %%rcx \n\t" - ASM_VMX_VMWRITE_RSP_RDX "\n\t" -#else - "pusha; push %%ecx \n\t" - ASM_VMX_VMWRITE_RSP_RDX "\n\t" -#endif - /* Check if vmlaunch of vmresume is needed */ - "cmp $0, %1 \n\t" - /* Load guest registers. Don't clobber flags. */ -#ifdef CONFIG_X86_64 - "mov %c[cr2](%3), %%rax \n\t" - "mov %%rax, %%cr2 \n\t" - "mov %c[rax](%3), %%rax \n\t" - "mov %c[rbx](%3), %%rbx \n\t" - "mov %c[rdx](%3), %%rdx \n\t" - "mov %c[rsi](%3), %%rsi \n\t" - "mov %c[rdi](%3), %%rdi \n\t" - "mov %c[rbp](%3), %%rbp \n\t" - "mov %c[r8](%3), %%r8 \n\t" - "mov %c[r9](%3), %%r9 \n\t" - "mov %c[r10](%3), %%r10 \n\t" - "mov %c[r11](%3), %%r11 \n\t" - "mov %c[r12](%3), %%r12 \n\t" - "mov %c[r13](%3), %%r13 \n\t" - "mov %c[r14](%3), %%r14 \n\t" - "mov %c[r15](%3), %%r15 \n\t" - "mov %c[rcx](%3), %%rcx \n\t" /* kills %3 (rcx) */ -#else - "mov %c[cr2](%3), %%eax \n\t" - "mov %%eax, %%cr2 \n\t" - "mov %c[rax](%3), %%eax \n\t" - "mov %c[rbx](%3), %%ebx \n\t" - "mov %c[rdx](%3), %%edx \n\t" - "mov %c[rsi](%3), %%esi \n\t" - "mov %c[rdi](%3), %%edi \n\t" - "mov %c[rbp](%3), %%ebp \n\t" - "mov %c[rcx](%3), %%ecx \n\t" /* kills %3 (ecx) */ -#endif - /* Enter guest mode */ - "jne .Llaunched \n\t" - ASM_VMX_VMLAUNCH "\n\t" - "jmp .Lkvm_vmx_return \n\t" - ".Llaunched: " ASM_VMX_VMRESUME "\n\t" - ".Lkvm_vmx_return: " - /* Save guest registers, load host registers, keep flags */ -#ifdef CONFIG_X86_64 - "xchg %3, (%%rsp) \n\t" - "mov %%rax, %c[rax](%3) \n\t" - "mov %%rbx, %c[rbx](%3) \n\t" - "pushq (%%rsp); popq %c[rcx](%3) \n\t" - "mov %%rdx, %c[rdx](%3) \n\t" - "mov %%rsi, %c[rsi](%3) \n\t" - "mov %%rdi, %c[rdi](%3) \n\t" - "mov %%rbp, %c[rbp](%3) \n\t" - "mov %%r8, %c[r8](%3) \n\t" - "mov %%r9, %c[r9](%3) \n\t" - "mov %%r10, %c[r10](%3) \n\t" - "mov %%r11, %c[r11](%3) \n\t" - "mov %%r12, %c[r12](%3) \n\t" - "mov %%r13, %c[r13](%3) \n\t" - "mov %%r14, %c[r14](%3) \n\t" - "mov %%r15, %c[r15](%3) \n\t" - "mov %%cr2, %%rax \n\t" - "mov %%rax, %c[cr2](%3) \n\t" - "mov (%%rsp), %3 \n\t" - - "pop %%rcx; pop %%r15; pop %%r14; pop %%r13; pop %%r12;" - "pop %%r11; pop %%r10; pop %%r9; pop %%r8;" - "pop %%rbp; pop %%rdi; pop %%rsi;" - "pop %%rdx; pop %%rbx; pop %%rax \n\t" -#else - "xchg %3, (%%esp) \n\t" - "mov %%eax, %c[rax](%3) \n\t" - "mov %%ebx, %c[rbx](%3) \n\t" - "pushl (%%esp); popl %c[rcx](%3) \n\t" - "mov %%edx, %c[rdx](%3) \n\t" - "mov %%esi, %c[rsi](%3) \n\t" - "mov %%edi, %c[rdi](%3) \n\t" - "mov %%ebp, %c[rbp](%3) \n\t" - "mov %%cr2, %%eax \n\t" - "mov %%eax, %c[cr2](%3) \n\t" - "mov (%%esp), %3 \n\t" - - "pop %%ecx; popa \n\t" -#endif - "setbe %0 \n\t" - : "=q" (vmx->fail) - : "r"(vmx->launched), "d"((unsigned long)HOST_RSP), - "c"(vcpu), - [rax]"i"(offsetof(struct kvm_vcpu, regs[VCPU_REGS_RAX])), - [rbx]"i"(offsetof(struct kvm_vcpu, regs[VCPU_REGS_RBX])), - [rcx]"i"(offsetof(struct kvm_vcpu, regs[VCPU_REGS_RCX])), - [rdx]"i"(offsetof(struct kvm_vcpu, regs[VCPU_REGS_RDX])), - [rsi]"i"(offsetof(struct kvm_vcpu, regs[VCPU_REGS_RSI])), - [rdi]"i"(offsetof(struct kvm_vcpu, regs[VCPU_REGS_RDI])), - [rbp]"i"(offsetof(struct kvm_vcpu, regs[VCPU_REGS_RBP])), -#ifdef CONFIG_X86_64 - [r8 ]"i"(offsetof(struct kvm_vcpu, regs[VCPU_REGS_R8 ])), - [r9 ]"i"(offsetof(struct kvm_vcpu, regs[VCPU_REGS_R9 ])), - [r10]"i"(offsetof(struct kvm_vcpu, regs[VCPU_REGS_R10])), - [r11]"i"(offsetof(struct kvm_vcpu, regs[VCPU_REGS_R11])), - [r12]"i"(offsetof(struct kvm_vcpu, regs[VCPU_REGS_R12])), - [r13]"i"(offsetof(struct kvm_vcpu, regs[VCPU_REGS_R13])), - [r14]"i"(offsetof(struct kvm_vcpu, regs[VCPU_REGS_R14])), - [r15]"i"(offsetof(struct kvm_vcpu, regs[VCPU_REGS_R15])), -#endif - [cr2]"i"(offsetof(struct kvm_vcpu, cr2)) - : "cc", "memory" ); - - vcpu->interrupt_window_open = (vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & 3) == 0; - - asm ("mov %0, %%ds; mov %0, %%es" : : "r"(__USER_DS)); - vmx->launched = 1; - - intr_info = vmcs_read32(VM_EXIT_INTR_INFO); - - /* We need to handle NMIs before interrupts are enabled */ - if ((intr_info & INTR_INFO_INTR_TYPE_MASK) == 0x200) /* nmi */ - asm("int $2"); -} - -static void vmx_inject_page_fault(struct kvm_vcpu *vcpu, - unsigned long addr, - u32 err_code) -{ - u32 vect_info = vmcs_read32(IDT_VECTORING_INFO_FIELD); - - ++vcpu->stat.pf_guest; - - if (is_page_fault(vect_info)) { - printk(KERN_DEBUG "inject_page_fault: " - "double fault 0x%lx @ 0x%lx\n", - addr, vmcs_readl(GUEST_RIP)); - vmcs_write32(VM_ENTRY_EXCEPTION_ERROR_CODE, 0); - vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, - DF_VECTOR | - INTR_TYPE_EXCEPTION | - INTR_INFO_DELIEVER_CODE_MASK | - INTR_INFO_VALID_MASK); - return; - } - vcpu->cr2 = addr; - vmcs_write32(VM_ENTRY_EXCEPTION_ERROR_CODE, err_code); - vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, - PF_VECTOR | - INTR_TYPE_EXCEPTION | - INTR_INFO_DELIEVER_CODE_MASK | - INTR_INFO_VALID_MASK); - -} - -static void vmx_free_vmcs(struct kvm_vcpu *vcpu) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - - if (vmx->vmcs) { - on_each_cpu(__vcpu_clear, vmx, 0, 1); - free_vmcs(vmx->vmcs); - vmx->vmcs = NULL; - } -} - -static void vmx_free_vcpu(struct kvm_vcpu *vcpu) -{ - struct vcpu_vmx *vmx = to_vmx(vcpu); - - vmx_free_vmcs(vcpu); - kfree(vmx->host_msrs); - kfree(vmx->guest_msrs); - kvm_vcpu_uninit(vcpu); - kmem_cache_free(kvm_vcpu_cache, vmx); -} - -static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) -{ - int err; - struct vcpu_vmx *vmx = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL); - int cpu; - - if (!vmx) - return ERR_PTR(-ENOMEM); - - err = kvm_vcpu_init(&vmx->vcpu, kvm, id); - if (err) - goto free_vcpu; - - if (irqchip_in_kernel(kvm)) { - err = kvm_create_lapic(&vmx->vcpu); - if (err < 0) - goto free_vcpu; - } - - vmx->guest_msrs = kmalloc(PAGE_SIZE, GFP_KERNEL); - if (!vmx->guest_msrs) { - err = -ENOMEM; - goto uninit_vcpu; - } - - vmx->host_msrs = kmalloc(PAGE_SIZE, GFP_KERNEL); - if (!vmx->host_msrs) - goto free_guest_msrs; - - vmx->vmcs = alloc_vmcs(); - if (!vmx->vmcs) - goto free_msrs; - - vmcs_clear(vmx->vmcs); - - cpu = get_cpu(); - vmx_vcpu_load(&vmx->vcpu, cpu); - err = vmx_vcpu_setup(vmx); - vmx_vcpu_put(&vmx->vcpu); - put_cpu(); - if (err) - goto free_vmcs; - - return &vmx->vcpu; - -free_vmcs: - free_vmcs(vmx->vmcs); -free_msrs: - kfree(vmx->host_msrs); -free_guest_msrs: - kfree(vmx->guest_msrs); -uninit_vcpu: - kvm_vcpu_uninit(&vmx->vcpu); -free_vcpu: - kmem_cache_free(kvm_vcpu_cache, vmx); - return ERR_PTR(err); -} - -static void __init vmx_check_processor_compat(void *rtn) -{ - struct vmcs_config vmcs_conf; - - *(int *)rtn = 0; - if (setup_vmcs_config(&vmcs_conf) < 0) - *(int *)rtn = -EIO; - if (memcmp(&vmcs_config, &vmcs_conf, sizeof(struct vmcs_config)) != 0) { - printk(KERN_ERR "kvm: CPU %d feature inconsistency!\n", - smp_processor_id()); - *(int *)rtn = -EIO; - } -} - -static struct kvm_x86_ops vmx_x86_ops = { - .cpu_has_kvm_support = cpu_has_kvm_support, - .disabled_by_bios = vmx_disabled_by_bios, - .hardware_setup = hardware_setup, - .hardware_unsetup = hardware_unsetup, - .check_processor_compatibility = vmx_check_processor_compat, - .hardware_enable = hardware_enable, - .hardware_disable = hardware_disable, - - .vcpu_create = vmx_create_vcpu, - .vcpu_free = vmx_free_vcpu, - .vcpu_reset = vmx_vcpu_reset, - - .prepare_guest_switch = vmx_save_host_state, - .vcpu_load = vmx_vcpu_load, - .vcpu_put = vmx_vcpu_put, - .vcpu_decache = vmx_vcpu_decache, - - .set_guest_debug = set_guest_debug, - .guest_debug_pre = kvm_guest_debug_pre, - .get_msr = vmx_get_msr, - .set_msr = vmx_set_msr, - .get_segment_base = vmx_get_segment_base, - .get_segment = vmx_get_segment, - .set_segment = vmx_set_segment, - .get_cs_db_l_bits = vmx_get_cs_db_l_bits, - .decache_cr4_guest_bits = vmx_decache_cr4_guest_bits, - .set_cr0 = vmx_set_cr0, - .set_cr3 = vmx_set_cr3, - .set_cr4 = vmx_set_cr4, -#ifdef CONFIG_X86_64 - .set_efer = vmx_set_efer, -#endif - .get_idt = vmx_get_idt, - .set_idt = vmx_set_idt, - .get_gdt = vmx_get_gdt, - .set_gdt = vmx_set_gdt, - .cache_regs = vcpu_load_rsp_rip, - .decache_regs = vcpu_put_rsp_rip, - .get_rflags = vmx_get_rflags, - .set_rflags = vmx_set_rflags, - - .tlb_flush = vmx_flush_tlb, - .inject_page_fault = vmx_inject_page_fault, - - .inject_gp = vmx_inject_gp, - - .run = vmx_vcpu_run, - .handle_exit = kvm_handle_exit, - .skip_emulated_instruction = skip_emulated_instruction, - .patch_hypercall = vmx_patch_hypercall, - .get_irq = vmx_get_irq, - .set_irq = vmx_inject_irq, - .inject_pending_irq = vmx_intr_assist, - .inject_pending_vectors = do_interrupt_requests, -}; - -static int __init vmx_init(void) -{ - void *iova; - int r; - - vmx_io_bitmap_a = alloc_page(GFP_KERNEL | __GFP_HIGHMEM); - if (!vmx_io_bitmap_a) - return -ENOMEM; - - vmx_io_bitmap_b = alloc_page(GFP_KERNEL | __GFP_HIGHMEM); - if (!vmx_io_bitmap_b) { - r = -ENOMEM; - goto out; - } - - /* - * Allow direct access to the PC debug port (it is often used for I/O - * delays, but the vmexits simply slow things down). - */ - iova = kmap(vmx_io_bitmap_a); - memset(iova, 0xff, PAGE_SIZE); - clear_bit(0x80, iova); - kunmap(vmx_io_bitmap_a); - - iova = kmap(vmx_io_bitmap_b); - memset(iova, 0xff, PAGE_SIZE); - kunmap(vmx_io_bitmap_b); - - r = kvm_init_x86(&vmx_x86_ops, sizeof(struct vcpu_vmx), THIS_MODULE); - if (r) - goto out1; - - return 0; - -out1: - __free_page(vmx_io_bitmap_b); -out: - __free_page(vmx_io_bitmap_a); - return r; -} - -static void __exit vmx_exit(void) -{ - __free_page(vmx_io_bitmap_b); - __free_page(vmx_io_bitmap_a); - - kvm_exit_x86(); -} - -module_init(vmx_init) -module_exit(vmx_exit) diff --git a/drivers/kvm/vmx.h b/drivers/kvm/vmx.h deleted file mode 100644 index fd4e14666088..000000000000 --- a/drivers/kvm/vmx.h +++ /dev/null @@ -1,310 +0,0 @@ -#ifndef VMX_H -#define VMX_H - -/* - * vmx.h: VMX Architecture related definitions - * Copyright (c) 2004, 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. - * - * A few random additions are: - * Copyright (C) 2006 Qumranet - * Avi Kivity <avi@qumranet.com> - * Yaniv Kamay <yaniv@qumranet.com> - * - */ - -#define CPU_BASED_VIRTUAL_INTR_PENDING 0x00000004 -#define CPU_BASED_USE_TSC_OFFSETING 0x00000008 -#define CPU_BASED_HLT_EXITING 0x00000080 -#define CPU_BASED_INVLPG_EXITING 0x00000200 -#define CPU_BASED_MWAIT_EXITING 0x00000400 -#define CPU_BASED_RDPMC_EXITING 0x00000800 -#define CPU_BASED_RDTSC_EXITING 0x00001000 -#define CPU_BASED_CR8_LOAD_EXITING 0x00080000 -#define CPU_BASED_CR8_STORE_EXITING 0x00100000 -#define CPU_BASED_TPR_SHADOW 0x00200000 -#define CPU_BASED_MOV_DR_EXITING 0x00800000 -#define CPU_BASED_UNCOND_IO_EXITING 0x01000000 -#define CPU_BASED_USE_IO_BITMAPS 0x02000000 -#define CPU_BASED_USE_MSR_BITMAPS 0x10000000 -#define CPU_BASED_MONITOR_EXITING 0x20000000 -#define CPU_BASED_PAUSE_EXITING 0x40000000 -#define CPU_BASED_ACTIVATE_SECONDARY_CONTROLS 0x80000000 - -#define PIN_BASED_EXT_INTR_MASK 0x00000001 -#define PIN_BASED_NMI_EXITING 0x00000008 -#define PIN_BASED_VIRTUAL_NMIS 0x00000020 - -#define VM_EXIT_HOST_ADDR_SPACE_SIZE 0x00000200 -#define VM_EXIT_ACK_INTR_ON_EXIT 0x00008000 - -#define VM_ENTRY_IA32E_MODE 0x00000200 -#define VM_ENTRY_SMM 0x00000400 -#define VM_ENTRY_DEACT_DUAL_MONITOR 0x00000800 - -#define SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES 0x00000001 - -/* VMCS Encodings */ -enum vmcs_field { - GUEST_ES_SELECTOR = 0x00000800, - GUEST_CS_SELECTOR = 0x00000802, - GUEST_SS_SELECTOR = 0x00000804, - GUEST_DS_SELECTOR = 0x00000806, - GUEST_FS_SELECTOR = 0x00000808, - GUEST_GS_SELECTOR = 0x0000080a, - GUEST_LDTR_SELECTOR = 0x0000080c, - GUEST_TR_SELECTOR = 0x0000080e, - HOST_ES_SELECTOR = 0x00000c00, - HOST_CS_SELECTOR = 0x00000c02, - HOST_SS_SELECTOR = 0x00000c04, - HOST_DS_SELECTOR = 0x00000c06, - HOST_FS_SELECTOR = 0x00000c08, - HOST_GS_SELECTOR = 0x00000c0a, - HOST_TR_SELECTOR = 0x00000c0c, - IO_BITMAP_A = 0x00002000, - IO_BITMAP_A_HIGH = 0x00002001, - IO_BITMAP_B = 0x00002002, - IO_BITMAP_B_HIGH = 0x00002003, - MSR_BITMAP = 0x00002004, - MSR_BITMAP_HIGH = 0x00002005, - VM_EXIT_MSR_STORE_ADDR = 0x00002006, - VM_EXIT_MSR_STORE_ADDR_HIGH = 0x00002007, - VM_EXIT_MSR_LOAD_ADDR = 0x00002008, - VM_EXIT_MSR_LOAD_ADDR_HIGH = 0x00002009, - VM_ENTRY_MSR_LOAD_ADDR = 0x0000200a, - VM_ENTRY_MSR_LOAD_ADDR_HIGH = 0x0000200b, - TSC_OFFSET = 0x00002010, - TSC_OFFSET_HIGH = 0x00002011, - VIRTUAL_APIC_PAGE_ADDR = 0x00002012, - VIRTUAL_APIC_PAGE_ADDR_HIGH = 0x00002013, - VMCS_LINK_POINTER = 0x00002800, - VMCS_LINK_POINTER_HIGH = 0x00002801, - GUEST_IA32_DEBUGCTL = 0x00002802, - GUEST_IA32_DEBUGCTL_HIGH = 0x00002803, - PIN_BASED_VM_EXEC_CONTROL = 0x00004000, - CPU_BASED_VM_EXEC_CONTROL = 0x00004002, - EXCEPTION_BITMAP = 0x00004004, - PAGE_FAULT_ERROR_CODE_MASK = 0x00004006, - PAGE_FAULT_ERROR_CODE_MATCH = 0x00004008, - CR3_TARGET_COUNT = 0x0000400a, - VM_EXIT_CONTROLS = 0x0000400c, - VM_EXIT_MSR_STORE_COUNT = 0x0000400e, - VM_EXIT_MSR_LOAD_COUNT = 0x00004010, - VM_ENTRY_CONTROLS = 0x00004012, - VM_ENTRY_MSR_LOAD_COUNT = 0x00004014, - VM_ENTRY_INTR_INFO_FIELD = 0x00004016, - VM_ENTRY_EXCEPTION_ERROR_CODE = 0x00004018, - VM_ENTRY_INSTRUCTION_LEN = 0x0000401a, - TPR_THRESHOLD = 0x0000401c, - SECONDARY_VM_EXEC_CONTROL = 0x0000401e, - VM_INSTRUCTION_ERROR = 0x00004400, - VM_EXIT_REASON = 0x00004402, - VM_EXIT_INTR_INFO = 0x00004404, - VM_EXIT_INTR_ERROR_CODE = 0x00004406, - IDT_VECTORING_INFO_FIELD = 0x00004408, - IDT_VECTORING_ERROR_CODE = 0x0000440a, - VM_EXIT_INSTRUCTION_LEN = 0x0000440c, - VMX_INSTRUCTION_INFO = 0x0000440e, - GUEST_ES_LIMIT = 0x00004800, - GUEST_CS_LIMIT = 0x00004802, - GUEST_SS_LIMIT = 0x00004804, - GUEST_DS_LIMIT = 0x00004806, - GUEST_FS_LIMIT = 0x00004808, - GUEST_GS_LIMIT = 0x0000480a, - GUEST_LDTR_LIMIT = 0x0000480c, - GUEST_TR_LIMIT = 0x0000480e, - GUEST_GDTR_LIMIT = 0x00004810, - GUEST_IDTR_LIMIT = 0x00004812, - GUEST_ES_AR_BYTES = 0x00004814, - GUEST_CS_AR_BYTES = 0x00004816, - GUEST_SS_AR_BYTES = 0x00004818, - GUEST_DS_AR_BYTES = 0x0000481a, - GUEST_FS_AR_BYTES = 0x0000481c, - GUEST_GS_AR_BYTES = 0x0000481e, - GUEST_LDTR_AR_BYTES = 0x00004820, - GUEST_TR_AR_BYTES = 0x00004822, - GUEST_INTERRUPTIBILITY_INFO = 0x00004824, - GUEST_ACTIVITY_STATE = 0X00004826, - GUEST_SYSENTER_CS = 0x0000482A, - HOST_IA32_SYSENTER_CS = 0x00004c00, - CR0_GUEST_HOST_MASK = 0x00006000, - CR4_GUEST_HOST_MASK = 0x00006002, - CR0_READ_SHADOW = 0x00006004, - CR4_READ_SHADOW = 0x00006006, - CR3_TARGET_VALUE0 = 0x00006008, - CR3_TARGET_VALUE1 = 0x0000600a, - CR3_TARGET_VALUE2 = 0x0000600c, - CR3_TARGET_VALUE3 = 0x0000600e, - EXIT_QUALIFICATION = 0x00006400, - GUEST_LINEAR_ADDRESS = 0x0000640a, - GUEST_CR0 = 0x00006800, - GUEST_CR3 = 0x00006802, - GUEST_CR4 = 0x00006804, - GUEST_ES_BASE = 0x00006806, - GUEST_CS_BASE = 0x00006808, - GUEST_SS_BASE = 0x0000680a, - GUEST_DS_BASE = 0x0000680c, - GUEST_FS_BASE = 0x0000680e, - GUEST_GS_BASE = 0x00006810, - GUEST_LDTR_BASE = 0x00006812, - GUEST_TR_BASE = 0x00006814, - GUEST_GDTR_BASE = 0x00006816, - GUEST_IDTR_BASE = 0x00006818, - GUEST_DR7 = 0x0000681a, - GUEST_RSP = 0x0000681c, - GUEST_RIP = 0x0000681e, - GUEST_RFLAGS = 0x00006820, - GUEST_PENDING_DBG_EXCEPTIONS = 0x00006822, - GUEST_SYSENTER_ESP = 0x00006824, - GUEST_SYSENTER_EIP = 0x00006826, - HOST_CR0 = 0x00006c00, - HOST_CR3 = 0x00006c02, - HOST_CR4 = 0x00006c04, - HOST_FS_BASE = 0x00006c06, - HOST_GS_BASE = 0x00006c08, - HOST_TR_BASE = 0x00006c0a, - HOST_GDTR_BASE = 0x00006c0c, - HOST_IDTR_BASE = 0x00006c0e, - HOST_IA32_SYSENTER_ESP = 0x00006c10, - HOST_IA32_SYSENTER_EIP = 0x00006c12, - HOST_RSP = 0x00006c14, - HOST_RIP = 0x00006c16, -}; - -#define VMX_EXIT_REASONS_FAILED_VMENTRY 0x80000000 - -#define EXIT_REASON_EXCEPTION_NMI 0 -#define EXIT_REASON_EXTERNAL_INTERRUPT 1 -#define EXIT_REASON_TRIPLE_FAULT 2 - -#define EXIT_REASON_PENDING_INTERRUPT 7 - -#define EXIT_REASON_TASK_SWITCH 9 -#define EXIT_REASON_CPUID 10 -#define EXIT_REASON_HLT 12 -#define EXIT_REASON_INVLPG 14 -#define EXIT_REASON_RDPMC 15 -#define EXIT_REASON_RDTSC 16 -#define EXIT_REASON_VMCALL 18 -#define EXIT_REASON_VMCLEAR 19 -#define EXIT_REASON_VMLAUNCH 20 -#define EXIT_REASON_VMPTRLD 21 -#define EXIT_REASON_VMPTRST 22 -#define EXIT_REASON_VMREAD 23 -#define EXIT_REASON_VMRESUME 24 -#define EXIT_REASON_VMWRITE 25 -#define EXIT_REASON_VMOFF 26 -#define EXIT_REASON_VMON 27 -#define EXIT_REASON_CR_ACCESS 28 -#define EXIT_REASON_DR_ACCESS 29 -#define EXIT_REASON_IO_INSTRUCTION 30 -#define EXIT_REASON_MSR_READ 31 -#define EXIT_REASON_MSR_WRITE 32 -#define EXIT_REASON_MWAIT_INSTRUCTION 36 -#define EXIT_REASON_TPR_BELOW_THRESHOLD 43 - -/* - * Interruption-information format - */ -#define INTR_INFO_VECTOR_MASK 0xff /* 7:0 */ -#define INTR_INFO_INTR_TYPE_MASK 0x700 /* 10:8 */ -#define INTR_INFO_DELIEVER_CODE_MASK 0x800 /* 11 */ -#define INTR_INFO_VALID_MASK 0x80000000 /* 31 */ - -#define VECTORING_INFO_VECTOR_MASK INTR_INFO_VECTOR_MASK -#define VECTORING_INFO_TYPE_MASK INTR_INFO_INTR_TYPE_MASK -#define VECTORING_INFO_DELIEVER_CODE_MASK INTR_INFO_DELIEVER_CODE_MASK -#define VECTORING_INFO_VALID_MASK INTR_INFO_VALID_MASK - -#define INTR_TYPE_EXT_INTR (0 << 8) /* external interrupt */ -#define INTR_TYPE_EXCEPTION (3 << 8) /* processor exception */ - -/* - * Exit Qualifications for MOV for Control Register Access - */ -#define CONTROL_REG_ACCESS_NUM 0x7 /* 2:0, number of control register */ -#define CONTROL_REG_ACCESS_TYPE 0x30 /* 5:4, access type */ -#define CONTROL_REG_ACCESS_REG 0xf00 /* 10:8, general purpose register */ -#define LMSW_SOURCE_DATA_SHIFT 16 -#define LMSW_SOURCE_DATA (0xFFFF << LMSW_SOURCE_DATA_SHIFT) /* 16:31 lmsw source */ -#define REG_EAX (0 << 8) -#define REG_ECX (1 << 8) -#define REG_EDX (2 << 8) -#define REG_EBX (3 << 8) -#define REG_ESP (4 << 8) -#define REG_EBP (5 << 8) -#define REG_ESI (6 << 8) -#define REG_EDI (7 << 8) -#define REG_R8 (8 << 8) -#define REG_R9 (9 << 8) -#define REG_R10 (10 << 8) -#define REG_R11 (11 << 8) -#define REG_R12 (12 << 8) -#define REG_R13 (13 << 8) -#define REG_R14 (14 << 8) -#define REG_R15 (15 << 8) - -/* - * Exit Qualifications for MOV for Debug Register Access - */ -#define DEBUG_REG_ACCESS_NUM 0x7 /* 2:0, number of debug register */ -#define DEBUG_REG_ACCESS_TYPE 0x10 /* 4, direction of access */ -#define TYPE_MOV_TO_DR (0 << 4) -#define TYPE_MOV_FROM_DR (1 << 4) -#define DEBUG_REG_ACCESS_REG 0xf00 /* 11:8, general purpose register */ - - -/* segment AR */ -#define SEGMENT_AR_L_MASK (1 << 13) - -#define AR_TYPE_ACCESSES_MASK 1 -#define AR_TYPE_READABLE_MASK (1 << 1) -#define AR_TYPE_WRITEABLE_MASK (1 << 2) -#define AR_TYPE_CODE_MASK (1 << 3) -#define AR_TYPE_MASK 0x0f -#define AR_TYPE_BUSY_64_TSS 11 -#define AR_TYPE_BUSY_32_TSS 11 -#define AR_TYPE_BUSY_16_TSS 3 -#define AR_TYPE_LDT 2 - -#define AR_UNUSABLE_MASK (1 << 16) -#define AR_S_MASK (1 << 4) -#define AR_P_MASK (1 << 7) -#define AR_L_MASK (1 << 13) -#define AR_DB_MASK (1 << 14) -#define AR_G_MASK (1 << 15) -#define AR_DPL_SHIFT 5 -#define AR_DPL(ar) (((ar) >> AR_DPL_SHIFT) & 3) - -#define AR_RESERVD_MASK 0xfffe0f00 - -#define MSR_IA32_VMX_BASIC 0x480 -#define MSR_IA32_VMX_PINBASED_CTLS 0x481 -#define MSR_IA32_VMX_PROCBASED_CTLS 0x482 -#define MSR_IA32_VMX_EXIT_CTLS 0x483 -#define MSR_IA32_VMX_ENTRY_CTLS 0x484 -#define MSR_IA32_VMX_MISC 0x485 -#define MSR_IA32_VMX_CR0_FIXED0 0x486 -#define MSR_IA32_VMX_CR0_FIXED1 0x487 -#define MSR_IA32_VMX_CR4_FIXED0 0x488 -#define MSR_IA32_VMX_CR4_FIXED1 0x489 -#define MSR_IA32_VMX_VMCS_ENUM 0x48a -#define MSR_IA32_VMX_PROCBASED_CTLS2 0x48b - -#define MSR_IA32_FEATURE_CONTROL 0x3a -#define MSR_IA32_FEATURE_CONTROL_LOCKED 0x1 -#define MSR_IA32_FEATURE_CONTROL_VMXON_ENABLED 0x4 - -#endif diff --git a/drivers/kvm/x86_emulate.c b/drivers/kvm/x86_emulate.c deleted file mode 100644 index bd46de6bf891..000000000000 --- a/drivers/kvm/x86_emulate.c +++ /dev/null @@ -1,1662 +0,0 @@ -/****************************************************************************** - * x86_emulate.c - * - * Generic x86 (32-bit and 64-bit) instruction decoder and emulator. - * - * Copyright (c) 2005 Keir Fraser - * - * Linux coding style, mod r/m decoder, segment base fixes, real-mode - * privileged instructions: - * - * Copyright (C) 2006 Qumranet - * - * Avi Kivity <avi@qumranet.com> - * Yaniv Kamay <yaniv@qumranet.com> - * - * This work is licensed under the terms of the GNU GPL, version 2. See - * the COPYING file in the top-level directory. - * - * From: xen-unstable 10676:af9809f51f81a3c43f276f00c81a52ef558afda4 - */ - -#ifndef __KERNEL__ -#include <stdio.h> -#include <stdint.h> -#include <public/xen.h> -#define DPRINTF(_f, _a ...) printf( _f , ## _a ) -#else -#include "kvm.h" -#define DPRINTF(x...) do {} while (0) -#endif -#include "x86_emulate.h" -#include <linux/module.h> - -/* - * Opcode effective-address decode tables. - * Note that we only emulate instructions that have at least one memory - * operand (excluding implicit stack references). We assume that stack - * references and instruction fetches will never occur in special memory - * areas that require emulation. So, for example, 'mov <imm>,<reg>' need - * not be handled. - */ - -/* Operand sizes: 8-bit operands or specified/overridden size. */ -#define ByteOp (1<<0) /* 8-bit operands. */ -/* Destination operand type. */ -#define ImplicitOps (1<<1) /* Implicit in opcode. No generic decode. */ -#define DstReg (2<<1) /* Register operand. */ -#define DstMem (3<<1) /* Memory operand. */ -#define DstMask (3<<1) -/* Source operand type. */ -#define SrcNone (0<<3) /* No source operand. */ -#define SrcImplicit (0<<3) /* Source operand is implicit in the opcode. */ -#define SrcReg (1<<3) /* Register operand. */ -#define SrcMem (2<<3) /* Memory operand. */ -#define SrcMem16 (3<<3) /* Memory operand (16-bit). */ -#define SrcMem32 (4<<3) /* Memory operand (32-bit). */ -#define SrcImm (5<<3) /* Immediate operand. */ -#define SrcImmByte (6<<3) /* 8-bit sign-extended immediate operand. */ -#define SrcMask (7<<3) -/* Generic ModRM decode. */ -#define ModRM (1<<6) -/* Destination is only written; never read. */ -#define Mov (1<<7) -#define BitOp (1<<8) - -static u8 opcode_table[256] = { - /* 0x00 - 0x07 */ - ByteOp | DstMem | SrcReg | ModRM, DstMem | SrcReg | ModRM, - ByteOp | DstReg | SrcMem | ModRM, DstReg | SrcMem | ModRM, - 0, 0, 0, 0, - /* 0x08 - 0x0F */ - ByteOp | DstMem | SrcReg | ModRM, DstMem | SrcReg | ModRM, - ByteOp | DstReg | SrcMem | ModRM, DstReg | SrcMem | ModRM, - 0, 0, 0, 0, - /* 0x10 - 0x17 */ - ByteOp | DstMem | SrcReg | ModRM, DstMem | SrcReg | ModRM, - ByteOp | DstReg | SrcMem | ModRM, DstReg | SrcMem | ModRM, - 0, 0, 0, 0, - /* 0x18 - 0x1F */ - ByteOp | DstMem | SrcReg | ModRM, DstMem | SrcReg | ModRM, - ByteOp | DstReg | SrcMem | ModRM, DstReg | SrcMem | ModRM, - 0, 0, 0, 0, - /* 0x20 - 0x27 */ - ByteOp | DstMem | SrcReg | ModRM, DstMem | SrcReg | ModRM, - ByteOp | DstReg | SrcMem | ModRM, DstReg | SrcMem | ModRM, - SrcImmByte, SrcImm, 0, 0, - /* 0x28 - 0x2F */ - ByteOp | DstMem | SrcReg | ModRM, DstMem | SrcReg | ModRM, - ByteOp | DstReg | SrcMem | ModRM, DstReg | SrcMem | ModRM, - 0, 0, 0, 0, - /* 0x30 - 0x37 */ - ByteOp | DstMem | SrcReg | ModRM, DstMem | SrcReg | ModRM, - ByteOp | DstReg | SrcMem | ModRM, DstReg | SrcMem | ModRM, - 0, 0, 0, 0, - /* 0x38 - 0x3F */ - ByteOp | DstMem | SrcReg | ModRM, DstMem | SrcReg | ModRM, - ByteOp | DstReg | SrcMem | ModRM, DstReg | SrcMem | ModRM, - 0, 0, 0, 0, - /* 0x40 - 0x4F */ - 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, - /* 0x50 - 0x57 */ - ImplicitOps, ImplicitOps, ImplicitOps, ImplicitOps, - ImplicitOps, ImplicitOps, ImplicitOps, ImplicitOps, - /* 0x58 - 0x5F */ - ImplicitOps, ImplicitOps, ImplicitOps, ImplicitOps, - ImplicitOps, ImplicitOps, ImplicitOps, ImplicitOps, - /* 0x60 - 0x67 */ - 0, 0, 0, DstReg | SrcMem32 | ModRM | Mov /* movsxd (x86/64) */ , - 0, 0, 0, 0, - /* 0x68 - 0x6F */ - 0, 0, ImplicitOps|Mov, 0, - SrcNone | ByteOp | ImplicitOps, SrcNone | ImplicitOps, /* insb, insw/insd */ - SrcNone | ByteOp | ImplicitOps, SrcNone | ImplicitOps, /* outsb, outsw/outsd */ - /* 0x70 - 0x77 */ - ImplicitOps, ImplicitOps, ImplicitOps, ImplicitOps, - ImplicitOps, ImplicitOps, ImplicitOps, ImplicitOps, - /* 0x78 - 0x7F */ - ImplicitOps, ImplicitOps, ImplicitOps, ImplicitOps, - ImplicitOps, ImplicitOps, ImplicitOps, ImplicitOps, - /* 0x80 - 0x87 */ - ByteOp | DstMem | SrcImm | ModRM, DstMem | SrcImm | ModRM, - ByteOp | DstMem | SrcImm | ModRM, DstMem | SrcImmByte | ModRM, - ByteOp | DstMem | SrcReg | ModRM, DstMem | SrcReg | ModRM, - ByteOp | DstMem | SrcReg | ModRM, DstMem | SrcReg | ModRM, - /* 0x88 - 0x8F */ - ByteOp | DstMem | SrcReg | ModRM | Mov, DstMem | SrcReg | ModRM | Mov, - ByteOp | DstReg | SrcMem | ModRM | Mov, DstReg | SrcMem | ModRM | Mov, - 0, ModRM | DstReg, 0, DstMem | SrcNone | ModRM | Mov, - /* 0x90 - 0x9F */ - 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, ImplicitOps, ImplicitOps, 0, 0, - /* 0xA0 - 0xA7 */ - ByteOp | DstReg | SrcMem | Mov, DstReg | SrcMem | Mov, - ByteOp | DstMem | SrcReg | Mov, DstMem | SrcReg | Mov, - ByteOp | ImplicitOps | Mov, ImplicitOps | Mov, - ByteOp | ImplicitOps, ImplicitOps, - /* 0xA8 - 0xAF */ - 0, 0, ByteOp | ImplicitOps | Mov, ImplicitOps | Mov, - ByteOp | ImplicitOps | Mov, ImplicitOps | Mov, - ByteOp | ImplicitOps, ImplicitOps, - /* 0xB0 - 0xBF */ - 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, - /* 0xC0 - 0xC7 */ - ByteOp | DstMem | SrcImm | ModRM, DstMem | SrcImmByte | ModRM, - 0, ImplicitOps, 0, 0, - ByteOp | DstMem | SrcImm | ModRM | Mov, DstMem | SrcImm | ModRM | Mov, - /* 0xC8 - 0xCF */ - 0, 0, 0, 0, 0, 0, 0, 0, - /* 0xD0 - 0xD7 */ - ByteOp | DstMem | SrcImplicit | ModRM, DstMem | SrcImplicit | ModRM, - ByteOp | DstMem | SrcImplicit | ModRM, DstMem | SrcImplicit | ModRM, - 0, 0, 0, 0, - /* 0xD8 - 0xDF */ - 0, 0, 0, 0, 0, 0, 0, 0, - /* 0xE0 - 0xE7 */ - 0, 0, 0, 0, 0, 0, 0, 0, - /* 0xE8 - 0xEF */ - ImplicitOps, SrcImm|ImplicitOps, 0, SrcImmByte|ImplicitOps, 0, 0, 0, 0, - /* 0xF0 - 0xF7 */ - 0, 0, 0, 0, - ImplicitOps, 0, - ByteOp | DstMem | SrcNone | ModRM, DstMem | SrcNone | ModRM, - /* 0xF8 - 0xFF */ - 0, 0, 0, 0, - 0, 0, ByteOp | DstMem | SrcNone | ModRM, DstMem | SrcNone | ModRM -}; - -static u16 twobyte_table[256] = { - /* 0x00 - 0x0F */ - 0, SrcMem | ModRM | DstReg, 0, 0, 0, 0, ImplicitOps, 0, - ImplicitOps, ImplicitOps, 0, 0, 0, ImplicitOps | ModRM, 0, 0, - /* 0x10 - 0x1F */ - 0, 0, 0, 0, 0, 0, 0, 0, ImplicitOps | ModRM, 0, 0, 0, 0, 0, 0, 0, - /* 0x20 - 0x2F */ - ModRM | ImplicitOps, ModRM, ModRM | ImplicitOps, ModRM, 0, 0, 0, 0, - 0, 0, 0, 0, 0, 0, 0, 0, - /* 0x30 - 0x3F */ - ImplicitOps, 0, ImplicitOps, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, - /* 0x40 - 0x47 */ - DstReg | SrcMem | ModRM | Mov, DstReg | SrcMem | ModRM | Mov, - DstReg | SrcMem | ModRM | Mov, DstReg | SrcMem | ModRM | Mov, - DstReg | SrcMem | ModRM | Mov, DstReg | SrcMem | ModRM | Mov, - DstReg | SrcMem | ModRM | Mov, DstReg | SrcMem | ModRM | Mov, - /* 0x48 - 0x4F */ - DstReg | SrcMem | ModRM | Mov, DstReg | SrcMem | ModRM | Mov, - DstReg | SrcMem | ModRM | Mov, DstReg | SrcMem | ModRM | Mov, - DstReg | SrcMem | ModRM | Mov, DstReg | SrcMem | ModRM | Mov, - DstReg | SrcMem | ModRM | Mov, DstReg | SrcMem | ModRM | Mov, - /* 0x50 - 0x5F */ - 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, - /* 0x60 - 0x6F */ - 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, - /* 0x70 - 0x7F */ - 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, - /* 0x80 - 0x8F */ - ImplicitOps, ImplicitOps, ImplicitOps, ImplicitOps, - ImplicitOps, ImplicitOps, ImplicitOps, ImplicitOps, - ImplicitOps, ImplicitOps, ImplicitOps, ImplicitOps, - ImplicitOps, ImplicitOps, ImplicitOps, ImplicitOps, - /* 0x90 - 0x9F */ - 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, - /* 0xA0 - 0xA7 */ - 0, 0, 0, DstMem | SrcReg | ModRM | BitOp, 0, 0, 0, 0, - /* 0xA8 - 0xAF */ - 0, 0, 0, DstMem | SrcReg | ModRM | BitOp, 0, 0, 0, 0, - /* 0xB0 - 0xB7 */ - ByteOp | DstMem | SrcReg | ModRM, DstMem | SrcReg | ModRM, 0, - DstMem | SrcReg | ModRM | BitOp, - 0, 0, ByteOp | DstReg | SrcMem | ModRM | Mov, - DstReg | SrcMem16 | ModRM | Mov, - /* 0xB8 - 0xBF */ - 0, 0, DstMem | SrcImmByte | ModRM, DstMem | SrcReg | ModRM | BitOp, - 0, 0, ByteOp | DstReg | SrcMem | ModRM | Mov, - DstReg | SrcMem16 | ModRM | Mov, - /* 0xC0 - 0xCF */ - 0, 0, 0, DstMem | SrcReg | ModRM | Mov, 0, 0, 0, ImplicitOps | ModRM, - 0, 0, 0, 0, 0, 0, 0, 0, - /* 0xD0 - 0xDF */ - 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, - /* 0xE0 - 0xEF */ - 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, - /* 0xF0 - 0xFF */ - 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 -}; - -/* Type, address-of, and value of an instruction's operand. */ -struct operand { - enum { OP_REG, OP_MEM, OP_IMM } type; - unsigned int bytes; - unsigned long val, orig_val, *ptr; -}; - -/* EFLAGS bit definitions. */ -#define EFLG_OF (1<<11) -#define EFLG_DF (1<<10) -#define EFLG_SF (1<<7) -#define EFLG_ZF (1<<6) -#define EFLG_AF (1<<4) -#define EFLG_PF (1<<2) -#define EFLG_CF (1<<0) - -/* - * Instruction emulation: - * Most instructions are emulated directly via a fragment of inline assembly - * code. This allows us to save/restore EFLAGS and thus very easily pick up - * any modified flags. - */ - -#if defined(CONFIG_X86_64) -#define _LO32 "k" /* force 32-bit operand */ -#define _STK "%%rsp" /* stack pointer */ -#elif defined(__i386__) -#define _LO32 "" /* force 32-bit operand */ -#define _STK "%%esp" /* stack pointer */ -#endif - -/* - * These EFLAGS bits are restored from saved value during emulation, and - * any changes are written back to the saved value after emulation. - */ -#define EFLAGS_MASK (EFLG_OF|EFLG_SF|EFLG_ZF|EFLG_AF|EFLG_PF|EFLG_CF) - -/* Before executing instruction: restore necessary bits in EFLAGS. */ -#define _PRE_EFLAGS(_sav, _msk, _tmp) \ - /* EFLAGS = (_sav & _msk) | (EFLAGS & ~_msk); */ \ - "push %"_sav"; " \ - "movl %"_msk",%"_LO32 _tmp"; " \ - "andl %"_LO32 _tmp",("_STK"); " \ - "pushf; " \ - "notl %"_LO32 _tmp"; " \ - "andl %"_LO32 _tmp",("_STK"); " \ - "pop %"_tmp"; " \ - "orl %"_LO32 _tmp",("_STK"); " \ - "popf; " \ - /* _sav &= ~msk; */ \ - "movl %"_msk",%"_LO32 _tmp"; " \ - "notl %"_LO32 _tmp"; " \ - "andl %"_LO32 _tmp",%"_sav"; " - -/* After executing instruction: write-back necessary bits in EFLAGS. */ -#define _POST_EFLAGS(_sav, _msk, _tmp) \ - /* _sav |= EFLAGS & _msk; */ \ - "pushf; " \ - "pop %"_tmp"; " \ - "andl %"_msk",%"_LO32 _tmp"; " \ - "orl %"_LO32 _tmp",%"_sav"; " - -/* Raw emulation: instruction has two explicit operands. */ -#define __emulate_2op_nobyte(_op,_src,_dst,_eflags,_wx,_wy,_lx,_ly,_qx,_qy) \ - do { \ - unsigned long _tmp; \ - \ - switch ((_dst).bytes) { \ - case 2: \ - __asm__ __volatile__ ( \ - _PRE_EFLAGS("0","4","2") \ - _op"w %"_wx"3,%1; " \ - _POST_EFLAGS("0","4","2") \ - : "=m" (_eflags), "=m" ((_dst).val), \ - "=&r" (_tmp) \ - : _wy ((_src).val), "i" (EFLAGS_MASK) ); \ - break; \ - case 4: \ - __asm__ __volatile__ ( \ - _PRE_EFLAGS("0","4","2") \ - _op"l %"_lx"3,%1; " \ - _POST_EFLAGS("0","4","2") \ - : "=m" (_eflags), "=m" ((_dst).val), \ - "=&r" (_tmp) \ - : _ly ((_src).val), "i" (EFLAGS_MASK) ); \ - break; \ - case 8: \ - __emulate_2op_8byte(_op, _src, _dst, \ - _eflags, _qx, _qy); \ - break; \ - } \ - } while (0) - -#define __emulate_2op(_op,_src,_dst,_eflags,_bx,_by,_wx,_wy,_lx,_ly,_qx,_qy) \ - do { \ - unsigned long _tmp; \ - switch ( (_dst).bytes ) \ - { \ - case 1: \ - __asm__ __volatile__ ( \ - _PRE_EFLAGS("0","4","2") \ - _op"b %"_bx"3,%1; " \ - _POST_EFLAGS("0","4","2") \ - : "=m" (_eflags), "=m" ((_dst).val), \ - "=&r" (_tmp) \ - : _by ((_src).val), "i" (EFLAGS_MASK) ); \ - break; \ - default: \ - __emulate_2op_nobyte(_op, _src, _dst, _eflags, \ - _wx, _wy, _lx, _ly, _qx, _qy); \ - break; \ - } \ - } while (0) - -/* Source operand is byte-sized and may be restricted to just %cl. */ -#define emulate_2op_SrcB(_op, _src, _dst, _eflags) \ - __emulate_2op(_op, _src, _dst, _eflags, \ - "b", "c", "b", "c", "b", "c", "b", "c") - -/* Source operand is byte, word, long or quad sized. */ -#define emulate_2op_SrcV(_op, _src, _dst, _eflags) \ - __emulate_2op(_op, _src, _dst, _eflags, \ - "b", "q", "w", "r", _LO32, "r", "", "r") - -/* Source operand is word, long or quad sized. */ -#define emulate_2op_SrcV_nobyte(_op, _src, _dst, _eflags) \ - __emulate_2op_nobyte(_op, _src, _dst, _eflags, \ - "w", "r", _LO32, "r", "", "r") - -/* Instruction has only one explicit operand (no source operand). */ -#define emulate_1op(_op, _dst, _eflags) \ - do { \ - unsigned long _tmp; \ - \ - switch ( (_dst).bytes ) \ - { \ - case 1: \ - __asm__ __volatile__ ( \ - _PRE_EFLAGS("0","3","2") \ - _op"b %1; " \ - _POST_EFLAGS("0","3","2") \ - : "=m" (_eflags), "=m" ((_dst).val), \ - "=&r" (_tmp) \ - : "i" (EFLAGS_MASK) ); \ - break; \ - case 2: \ - __asm__ __volatile__ ( \ - _PRE_EFLAGS("0","3","2") \ - _op"w %1; " \ - _POST_EFLAGS("0","3","2") \ - : "=m" (_eflags), "=m" ((_dst).val), \ - "=&r" (_tmp) \ - : "i" (EFLAGS_MASK) ); \ - break; \ - case 4: \ - __asm__ __volatile__ ( \ - _PRE_EFLAGS("0","3","2") \ - _op"l %1; " \ - _POST_EFLAGS("0","3","2") \ - : "=m" (_eflags), "=m" ((_dst).val), \ - "=&r" (_tmp) \ - : "i" (EFLAGS_MASK) ); \ - break; \ - case 8: \ - __emulate_1op_8byte(_op, _dst, _eflags); \ - break; \ - } \ - } while (0) - -/* Emulate an instruction with quadword operands (x86/64 only). */ -#if defined(CONFIG_X86_64) -#define __emulate_2op_8byte(_op, _src, _dst, _eflags, _qx, _qy) \ - do { \ - __asm__ __volatile__ ( \ - _PRE_EFLAGS("0","4","2") \ - _op"q %"_qx"3,%1; " \ - _POST_EFLAGS("0","4","2") \ - : "=m" (_eflags), "=m" ((_dst).val), "=&r" (_tmp) \ - : _qy ((_src).val), "i" (EFLAGS_MASK) ); \ - } while (0) - -#define __emulate_1op_8byte(_op, _dst, _eflags) \ - do { \ - __asm__ __volatile__ ( \ - _PRE_EFLAGS("0","3","2") \ - _op"q %1; " \ - _POST_EFLAGS("0","3","2") \ - : "=m" (_eflags), "=m" ((_dst).val), "=&r" (_tmp) \ - : "i" (EFLAGS_MASK) ); \ - } while (0) - -#elif defined(__i386__) -#define __emulate_2op_8byte(_op, _src, _dst, _eflags, _qx, _qy) -#define __emulate_1op_8byte(_op, _dst, _eflags) -#endif /* __i386__ */ - -/* Fetch next part of the instruction being emulated. */ -#define insn_fetch(_type, _size, _eip) \ -({ unsigned long _x; \ - rc = ops->read_std((unsigned long)(_eip) + ctxt->cs_base, &_x, \ - (_size), ctxt->vcpu); \ - if ( rc != 0 ) \ - goto done; \ - (_eip) += (_size); \ - (_type)_x; \ -}) - -/* Access/update address held in a register, based on addressing mode. */ -#define address_mask(reg) \ - ((ad_bytes == sizeof(unsigned long)) ? \ - (reg) : ((reg) & ((1UL << (ad_bytes << 3)) - 1))) -#define register_address(base, reg) \ - ((base) + address_mask(reg)) -#define register_address_increment(reg, inc) \ - do { \ - /* signed type ensures sign extension to long */ \ - int _inc = (inc); \ - if ( ad_bytes == sizeof(unsigned long) ) \ - (reg) += _inc; \ - else \ - (reg) = ((reg) & ~((1UL << (ad_bytes << 3)) - 1)) | \ - (((reg) + _inc) & ((1UL << (ad_bytes << 3)) - 1)); \ - } while (0) - -#define JMP_REL(rel) \ - do { \ - register_address_increment(_eip, rel); \ - } while (0) - -/* - * Given the 'reg' portion of a ModRM byte, and a register block, return a - * pointer into the block that addresses the relevant register. - * @highbyte_regs specifies whether to decode AH,CH,DH,BH. - */ -static void *decode_register(u8 modrm_reg, unsigned long *regs, - int highbyte_regs) -{ - void *p; - - p = ®s[modrm_reg]; - if (highbyte_regs && modrm_reg >= 4 && modrm_reg < 8) - p = (unsigned char *)®s[modrm_reg & 3] + 1; - return p; -} - -static int read_descriptor(struct x86_emulate_ctxt *ctxt, - struct x86_emulate_ops *ops, - void *ptr, - u16 *size, unsigned long *address, int op_bytes) -{ - int rc; - - if (op_bytes == 2) - op_bytes = 3; - *address = 0; - rc = ops->read_std((unsigned long)ptr, (unsigned long *)size, 2, - ctxt->vcpu); - if (rc) - return rc; - rc = ops->read_std((unsigned long)ptr + 2, address, op_bytes, - ctxt->vcpu); - return rc; -} - -static int test_cc(unsigned int condition, unsigned int flags) -{ - int rc = 0; - - switch ((condition & 15) >> 1) { - case 0: /* o */ - rc |= (flags & EFLG_OF); - break; - case 1: /* b/c/nae */ - rc |= (flags & EFLG_CF); - break; - case 2: /* z/e */ - rc |= (flags & EFLG_ZF); - break; - case 3: /* be/na */ - rc |= (flags & (EFLG_CF|EFLG_ZF)); - break; - case 4: /* s */ - rc |= (flags & EFLG_SF); - break; - case 5: /* p/pe */ - rc |= (flags & EFLG_PF); - break; - case 7: /* le/ng */ - rc |= (flags & EFLG_ZF); - /* fall through */ - case 6: /* l/nge */ - rc |= (!(flags & EFLG_SF) != !(flags & EFLG_OF)); - break; - } - - /* Odd condition identifiers (lsb == 1) have inverted sense. */ - return (!!rc ^ (condition & 1)); -} - -int -x86_emulate_memop(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops) -{ - unsigned d; - u8 b, sib, twobyte = 0, rex_prefix = 0; - u8 modrm, modrm_mod = 0, modrm_reg = 0, modrm_rm = 0; - unsigned long *override_base = NULL; - unsigned int op_bytes, ad_bytes, lock_prefix = 0, rep_prefix = 0, i; - int rc = 0; - struct operand src, dst; - unsigned long cr2 = ctxt->cr2; - int mode = ctxt->mode; - unsigned long modrm_ea; - int use_modrm_ea, index_reg = 0, base_reg = 0, scale, rip_relative = 0; - int no_wb = 0; - u64 msr_data; - - /* Shadow copy of register state. Committed on successful emulation. */ - unsigned long _regs[NR_VCPU_REGS]; - unsigned long _eip = ctxt->vcpu->rip, _eflags = ctxt->eflags; - unsigned long modrm_val = 0; - - memcpy(_regs, ctxt->vcpu->regs, sizeof _regs); - - switch (mode) { - case X86EMUL_MODE_REAL: - case X86EMUL_MODE_PROT16: - op_bytes = ad_bytes = 2; - break; - case X86EMUL_MODE_PROT32: - op_bytes = ad_bytes = 4; - break; -#ifdef CONFIG_X86_64 - case X86EMUL_MODE_PROT64: - op_bytes = 4; - ad_bytes = 8; - break; -#endif - default: - return -1; - } - - /* Legacy prefixes. */ - for (i = 0; i < 8; i++) { - switch (b = insn_fetch(u8, 1, _eip)) { - case 0x66: /* operand-size override */ - op_bytes ^= 6; /* switch between 2/4 bytes */ - break; - case 0x67: /* address-size override */ - if (mode == X86EMUL_MODE_PROT64) - ad_bytes ^= 12; /* switch between 4/8 bytes */ - else - ad_bytes ^= 6; /* switch between 2/4 bytes */ - break; - case 0x2e: /* CS override */ - override_base = &ctxt->cs_base; - break; - case 0x3e: /* DS override */ - override_base = &ctxt->ds_base; - break; - case 0x26: /* ES override */ - override_base = &ctxt->es_base; - break; - case 0x64: /* FS override */ - override_base = &ctxt->fs_base; - break; - case 0x65: /* GS override */ - override_base = &ctxt->gs_base; - break; - case 0x36: /* SS override */ - override_base = &ctxt->ss_base; - break; - case 0xf0: /* LOCK */ - lock_prefix = 1; - break; - case 0xf2: /* REPNE/REPNZ */ - case 0xf3: /* REP/REPE/REPZ */ - rep_prefix = 1; - break; - default: - goto done_prefixes; - } - } - -done_prefixes: - - /* REX prefix. */ - if ((mode == X86EMUL_MODE_PROT64) && ((b & 0xf0) == 0x40)) { - rex_prefix = b; - if (b & 8) - op_bytes = 8; /* REX.W */ - modrm_reg = (b & 4) << 1; /* REX.R */ - index_reg = (b & 2) << 2; /* REX.X */ - modrm_rm = base_reg = (b & 1) << 3; /* REG.B */ - b = insn_fetch(u8, 1, _eip); - } - - /* Opcode byte(s). */ - d = opcode_table[b]; - if (d == 0) { - /* Two-byte opcode? */ - if (b == 0x0f) { - twobyte = 1; - b = insn_fetch(u8, 1, _eip); - d = twobyte_table[b]; - } - - /* Unrecognised? */ - if (d == 0) - goto cannot_emulate; - } - - /* ModRM and SIB bytes. */ - if (d & ModRM) { - modrm = insn_fetch(u8, 1, _eip); - modrm_mod |= (modrm & 0xc0) >> 6; - modrm_reg |= (modrm & 0x38) >> 3; - modrm_rm |= (modrm & 0x07); - modrm_ea = 0; - use_modrm_ea = 1; - - if (modrm_mod == 3) { - modrm_val = *(unsigned long *) - decode_register(modrm_rm, _regs, d & ByteOp); - goto modrm_done; - } - - if (ad_bytes == 2) { - unsigned bx = _regs[VCPU_REGS_RBX]; - unsigned bp = _regs[VCPU_REGS_RBP]; - unsigned si = _regs[VCPU_REGS_RSI]; - unsigned di = _regs[VCPU_REGS_RDI]; - - /* 16-bit ModR/M decode. */ - switch (modrm_mod) { - case 0: - if (modrm_rm == 6) - modrm_ea += insn_fetch(u16, 2, _eip); - break; - case 1: - modrm_ea += insn_fetch(s8, 1, _eip); - break; - case 2: - modrm_ea += insn_fetch(u16, 2, _eip); - break; - } - switch (modrm_rm) { - case 0: - modrm_ea += bx + si; - break; - case 1: - modrm_ea += bx + di; - break; - case 2: - modrm_ea += bp + si; - break; - case 3: - modrm_ea += bp + di; - break; - case 4: - modrm_ea += si; - break; - case 5: - modrm_ea += di; - break; - case 6: - if (modrm_mod != 0) - modrm_ea += bp; - break; - case 7: - modrm_ea += bx; - break; - } - if (modrm_rm == 2 || modrm_rm == 3 || - (modrm_rm == 6 && modrm_mod != 0)) - if (!override_base) - override_base = &ctxt->ss_base; - modrm_ea = (u16)modrm_ea; - } else { - /* 32/64-bit ModR/M decode. */ - switch (modrm_rm) { - case 4: - case 12: - sib = insn_fetch(u8, 1, _eip); - index_reg |= (sib >> 3) & 7; - base_reg |= sib & 7; - scale = sib >> 6; - - switch (base_reg) { - case 5: - if (modrm_mod != 0) - modrm_ea += _regs[base_reg]; - else - modrm_ea += insn_fetch(s32, 4, _eip); - break; - default: - modrm_ea += _regs[base_reg]; - } - switch (index_reg) { - case 4: - break; - default: - modrm_ea += _regs[index_reg] << scale; - - } - break; - case 5: - if (modrm_mod != 0) - modrm_ea += _regs[modrm_rm]; - else if (mode == X86EMUL_MODE_PROT64) - rip_relative = 1; - break; - default: - modrm_ea += _regs[modrm_rm]; - break; - } - switch (modrm_mod) { - case 0: - if (modrm_rm == 5) - modrm_ea += insn_fetch(s32, 4, _eip); - break; - case 1: - modrm_ea += insn_fetch(s8, 1, _eip); - break; - case 2: - modrm_ea += insn_fetch(s32, 4, _eip); - break; - } - } - if (!override_base) - override_base = &ctxt->ds_base; - if (mode == X86EMUL_MODE_PROT64 && - override_base != &ctxt->fs_base && - override_base != &ctxt->gs_base) - override_base = NULL; - - if (override_base) - modrm_ea += *override_base; - - if (rip_relative) { - modrm_ea += _eip; - switch (d & SrcMask) { - case SrcImmByte: - modrm_ea += 1; - break; - case SrcImm: - if (d & ByteOp) - modrm_ea += 1; - else - if (op_bytes == 8) - modrm_ea += 4; - else - modrm_ea += op_bytes; - } - } - if (ad_bytes != 8) - modrm_ea = (u32)modrm_ea; - cr2 = modrm_ea; - modrm_done: - ; - } - - /* - * Decode and fetch the source operand: register, memory - * or immediate. - */ - switch (d & SrcMask) { - case SrcNone: - break; - case SrcReg: - src.type = OP_REG; - if (d & ByteOp) { - src.ptr = decode_register(modrm_reg, _regs, - (rex_prefix == 0)); - src.val = src.orig_val = *(u8 *) src.ptr; - src.bytes = 1; - } else { - src.ptr = decode_register(modrm_reg, _regs, 0); - switch ((src.bytes = op_bytes)) { - case 2: - src.val = src.orig_val = *(u16 *) src.ptr; - break; - case 4: - src.val = src.orig_val = *(u32 *) src.ptr; - break; - case 8: - src.val = src.orig_val = *(u64 *) src.ptr; - break; - } - } - break; - case SrcMem16: - src.bytes = 2; - goto srcmem_common; - case SrcMem32: - src.bytes = 4; - goto srcmem_common; - case SrcMem: - src.bytes = (d & ByteOp) ? 1 : op_bytes; - /* Don't fetch the address for invlpg: it could be unmapped. */ - if (twobyte && b == 0x01 && modrm_reg == 7) - break; - srcmem_common: - /* - * For instructions with a ModR/M byte, switch to register - * access if Mod = 3. - */ - if ((d & ModRM) && modrm_mod == 3) { - src.type = OP_REG; - break; - } - src.type = OP_MEM; - src.ptr = (unsigned long *)cr2; - src.val = 0; - if ((rc = ops->read_emulated((unsigned long)src.ptr, - &src.val, src.bytes, ctxt->vcpu)) != 0) - goto done; - src.orig_val = src.val; - break; - case SrcImm: - src.type = OP_IMM; - src.ptr = (unsigned long *)_eip; - src.bytes = (d & ByteOp) ? 1 : op_bytes; - if (src.bytes == 8) - src.bytes = 4; - /* NB. Immediates are sign-extended as necessary. */ - switch (src.bytes) { - case 1: - src.val = insn_fetch(s8, 1, _eip); - break; - case 2: - src.val = insn_fetch(s16, 2, _eip); - break; - case 4: - src.val = insn_fetch(s32, 4, _eip); - break; - } - break; - case SrcImmByte: - src.type = OP_IMM; - src.ptr = (unsigned long *)_eip; - src.bytes = 1; - src.val = insn_fetch(s8, 1, _eip); - break; - } - - /* Decode and fetch the destination operand: register or memory. */ - switch (d & DstMask) { - case ImplicitOps: - /* Special instructions do their own operand decoding. */ - goto special_insn; - case DstReg: - dst.type = OP_REG; - if ((d & ByteOp) - && !(twobyte && (b == 0xb6 || b == 0xb7))) { - dst.ptr = decode_register(modrm_reg, _regs, - (rex_prefix == 0)); - dst.val = *(u8 *) dst.ptr; - dst.bytes = 1; - } else { - dst.ptr = decode_register(modrm_reg, _regs, 0); - switch ((dst.bytes = op_bytes)) { - case 2: - dst.val = *(u16 *)dst.ptr; - break; - case 4: - dst.val = *(u32 *)dst.ptr; - break; - case 8: - dst.val = *(u64 *)dst.ptr; - break; - } - } - break; - case DstMem: - dst.type = OP_MEM; - dst.ptr = (unsigned long *)cr2; - dst.bytes = (d & ByteOp) ? 1 : op_bytes; - dst.val = 0; - /* - * For instructions with a ModR/M byte, switch to register - * access if Mod = 3. - */ - if ((d & ModRM) && modrm_mod == 3) { - dst.type = OP_REG; - break; - } - if (d & BitOp) { - unsigned long mask = ~(dst.bytes * 8 - 1); - - dst.ptr = (void *)dst.ptr + (src.val & mask) / 8; - } - if (!(d & Mov) && /* optimisation - avoid slow emulated read */ - ((rc = ops->read_emulated((unsigned long)dst.ptr, - &dst.val, dst.bytes, ctxt->vcpu)) != 0)) - goto done; - break; - } - dst.orig_val = dst.val; - - if (twobyte) - goto twobyte_insn; - - switch (b) { - case 0x00 ... 0x05: - add: /* add */ - emulate_2op_SrcV("add", src, dst, _eflags); - break; - case 0x08 ... 0x0d: - or: /* or */ - emulate_2op_SrcV("or", src, dst, _eflags); - break; - case 0x10 ... 0x15: - adc: /* adc */ - emulate_2op_SrcV("adc", src, dst, _eflags); - break; - case 0x18 ... 0x1d: - sbb: /* sbb */ - emulate_2op_SrcV("sbb", src, dst, _eflags); - break; - case 0x20 ... 0x23: - and: /* and */ - emulate_2op_SrcV("and", src, dst, _eflags); - break; - case 0x24: /* and al imm8 */ - dst.type = OP_REG; - dst.ptr = &_regs[VCPU_REGS_RAX]; - dst.val = *(u8 *)dst.ptr; - dst.bytes = 1; - dst.orig_val = dst.val; - goto and; - case 0x25: /* and ax imm16, or eax imm32 */ - dst.type = OP_REG; - dst.bytes = op_bytes; - dst.ptr = &_regs[VCPU_REGS_RAX]; - if (op_bytes == 2) - dst.val = *(u16 *)dst.ptr; - else - dst.val = *(u32 *)dst.ptr; - dst.orig_val = dst.val; - goto and; - case 0x28 ... 0x2d: - sub: /* sub */ - emulate_2op_SrcV("sub", src, dst, _eflags); - break; - case 0x30 ... 0x35: - xor: /* xor */ - emulate_2op_SrcV("xor", src, dst, _eflags); - break; - case 0x38 ... 0x3d: - cmp: /* cmp */ - emulate_2op_SrcV("cmp", src, dst, _eflags); - break; - case 0x63: /* movsxd */ - if (mode != X86EMUL_MODE_PROT64) - goto cannot_emulate; - dst.val = (s32) src.val; - break; - case 0x80 ... 0x83: /* Grp1 */ - switch (modrm_reg) { - case 0: - goto add; - case 1: - goto or; - case 2: - goto adc; - case 3: - goto sbb; - case 4: - goto and; - case 5: - goto sub; - case 6: - goto xor; - case 7: - goto cmp; - } - break; - case 0x84 ... 0x85: - test: /* test */ - emulate_2op_SrcV("test", src, dst, _eflags); - break; - case 0x86 ... 0x87: /* xchg */ - /* Write back the register source. */ - switch (dst.bytes) { - case 1: - *(u8 *) src.ptr = (u8) dst.val; - break; - case 2: - *(u16 *) src.ptr = (u16) dst.val; - break; - case 4: - *src.ptr = (u32) dst.val; - break; /* 64b reg: zero-extend */ - case 8: - *src.ptr = dst.val; - break; - } - /* - * Write back the memory destination with implicit LOCK - * prefix. - */ - dst.val = src.val; - lock_prefix = 1; - break; - case 0x88 ... 0x8b: /* mov */ - goto mov; - case 0x8d: /* lea r16/r32, m */ - dst.val = modrm_val; - break; - case 0x8f: /* pop (sole member of Grp1a) */ - /* 64-bit mode: POP always pops a 64-bit operand. */ - if (mode == X86EMUL_MODE_PROT64) - dst.bytes = 8; - if ((rc = ops->read_std(register_address(ctxt->ss_base, - _regs[VCPU_REGS_RSP]), - &dst.val, dst.bytes, ctxt->vcpu)) != 0) - goto done; - register_address_increment(_regs[VCPU_REGS_RSP], dst.bytes); - break; - case 0xa0 ... 0xa1: /* mov */ - dst.ptr = (unsigned long *)&_regs[VCPU_REGS_RAX]; - dst.val = src.val; - _eip += ad_bytes; /* skip src displacement */ - break; - case 0xa2 ... 0xa3: /* mov */ - dst.val = (unsigned long)_regs[VCPU_REGS_RAX]; - _eip += ad_bytes; /* skip dst displacement */ - break; - case 0xc0 ... 0xc1: - grp2: /* Grp2 */ - switch (modrm_reg) { - case 0: /* rol */ - emulate_2op_SrcB("rol", src, dst, _eflags); - break; - case 1: /* ror */ - emulate_2op_SrcB("ror", src, dst, _eflags); - break; - case 2: /* rcl */ - emulate_2op_SrcB("rcl", src, dst, _eflags); - break; - case 3: /* rcr */ - emulate_2op_SrcB("rcr", src, dst, _eflags); - break; - case 4: /* sal/shl */ - case 6: /* sal/shl */ - emulate_2op_SrcB("sal", src, dst, _eflags); - break; - case 5: /* shr */ - emulate_2op_SrcB("shr", src, dst, _eflags); - break; - case 7: /* sar */ - emulate_2op_SrcB("sar", src, dst, _eflags); - break; - } - break; - case 0xc6 ... 0xc7: /* mov (sole member of Grp11) */ - mov: - dst.val = src.val; - break; - case 0xd0 ... 0xd1: /* Grp2 */ - src.val = 1; - goto grp2; - case 0xd2 ... 0xd3: /* Grp2 */ - src.val = _regs[VCPU_REGS_RCX]; - goto grp2; - case 0xf6 ... 0xf7: /* Grp3 */ - switch (modrm_reg) { - case 0 ... 1: /* test */ - /* - * Special case in Grp3: test has an immediate - * source operand. - */ - src.type = OP_IMM; - src.ptr = (unsigned long *)_eip; - src.bytes = (d & ByteOp) ? 1 : op_bytes; - if (src.bytes == 8) - src.bytes = 4; - switch (src.bytes) { - case 1: - src.val = insn_fetch(s8, 1, _eip); - break; - case 2: - src.val = insn_fetch(s16, 2, _eip); - break; - case 4: - src.val = insn_fetch(s32, 4, _eip); - break; - } - goto test; - case 2: /* not */ - dst.val = ~dst.val; - break; - case 3: /* neg */ - emulate_1op("neg", dst, _eflags); - break; - default: - goto cannot_emulate; - } - break; - case 0xfe ... 0xff: /* Grp4/Grp5 */ - switch (modrm_reg) { - case 0: /* inc */ - emulate_1op("inc", dst, _eflags); - break; - case 1: /* dec */ - emulate_1op("dec", dst, _eflags); - break; - case 4: /* jmp abs */ - if (b == 0xff) - _eip = dst.val; - else - goto cannot_emulate; - break; - case 6: /* push */ - /* 64-bit mode: PUSH always pushes a 64-bit operand. */ - if (mode == X86EMUL_MODE_PROT64) { - dst.bytes = 8; - if ((rc = ops->read_std((unsigned long)dst.ptr, - &dst.val, 8, - ctxt->vcpu)) != 0) - goto done; - } - register_address_increment(_regs[VCPU_REGS_RSP], - -dst.bytes); - if ((rc = ops->write_emulated( - register_address(ctxt->ss_base, - _regs[VCPU_REGS_RSP]), - &dst.val, dst.bytes, ctxt->vcpu)) != 0) - goto done; - no_wb = 1; - break; - default: - goto cannot_emulate; - } - break; - } - -writeback: - if (!no_wb) { - switch (dst.type) { - case OP_REG: - /* The 4-byte case *is* correct: in 64-bit mode we zero-extend. */ - switch (dst.bytes) { - case 1: - *(u8 *)dst.ptr = (u8)dst.val; - break; - case 2: - *(u16 *)dst.ptr = (u16)dst.val; - break; - case 4: - *dst.ptr = (u32)dst.val; - break; /* 64b: zero-ext */ - case 8: - *dst.ptr = dst.val; - break; - } - break; - case OP_MEM: - if (lock_prefix) - rc = ops->cmpxchg_emulated((unsigned long)dst. - ptr, &dst.orig_val, - &dst.val, dst.bytes, - ctxt->vcpu); - else - rc = ops->write_emulated((unsigned long)dst.ptr, - &dst.val, dst.bytes, - ctxt->vcpu); - if (rc != 0) - goto done; - default: - break; - } - } - - /* Commit shadow register state. */ - memcpy(ctxt->vcpu->regs, _regs, sizeof _regs); - ctxt->eflags = _eflags; - ctxt->vcpu->rip = _eip; - -done: - return (rc == X86EMUL_UNHANDLEABLE) ? -1 : 0; - -special_insn: - if (twobyte) - goto twobyte_special_insn; - switch(b) { - case 0x50 ... 0x57: /* push reg */ - if (op_bytes == 2) - src.val = (u16) _regs[b & 0x7]; - else - src.val = (u32) _regs[b & 0x7]; - dst.type = OP_MEM; - dst.bytes = op_bytes; - dst.val = src.val; - register_address_increment(_regs[VCPU_REGS_RSP], -op_bytes); - dst.ptr = (void *) register_address( - ctxt->ss_base, _regs[VCPU_REGS_RSP]); - break; - case 0x58 ... 0x5f: /* pop reg */ - dst.ptr = (unsigned long *)&_regs[b & 0x7]; - pop_instruction: - if ((rc = ops->read_std(register_address(ctxt->ss_base, - _regs[VCPU_REGS_RSP]), dst.ptr, op_bytes, ctxt->vcpu)) - != 0) - goto done; - - register_address_increment(_regs[VCPU_REGS_RSP], op_bytes); - no_wb = 1; /* Disable writeback. */ - break; - case 0x6a: /* push imm8 */ - src.val = 0L; - src.val = insn_fetch(s8, 1, _eip); - push: - dst.type = OP_MEM; - dst.bytes = op_bytes; - dst.val = src.val; - register_address_increment(_regs[VCPU_REGS_RSP], -op_bytes); - dst.ptr = (void *) register_address(ctxt->ss_base, - _regs[VCPU_REGS_RSP]); - break; - case 0x6c: /* insb */ - case 0x6d: /* insw/insd */ - if (kvm_emulate_pio_string(ctxt->vcpu, NULL, - 1, /* in */ - (d & ByteOp) ? 1 : op_bytes, /* size */ - rep_prefix ? - address_mask(_regs[VCPU_REGS_RCX]) : 1, /* count */ - (_eflags & EFLG_DF), /* down */ - register_address(ctxt->es_base, - _regs[VCPU_REGS_RDI]), /* address */ - rep_prefix, - _regs[VCPU_REGS_RDX] /* port */ - ) == 0) - return -1; - return 0; - case 0x6e: /* outsb */ - case 0x6f: /* outsw/outsd */ - if (kvm_emulate_pio_string(ctxt->vcpu, NULL, - 0, /* in */ - (d & ByteOp) ? 1 : op_bytes, /* size */ - rep_prefix ? - address_mask(_regs[VCPU_REGS_RCX]) : 1, /* count */ - (_eflags & EFLG_DF), /* down */ - register_address(override_base ? - *override_base : ctxt->ds_base, - _regs[VCPU_REGS_RSI]), /* address */ - rep_prefix, - _regs[VCPU_REGS_RDX] /* port */ - ) == 0) - return -1; - return 0; - case 0x70 ... 0x7f: /* jcc (short) */ { - int rel = insn_fetch(s8, 1, _eip); - - if (test_cc(b, _eflags)) - JMP_REL(rel); - break; - } - case 0x9c: /* pushf */ - src.val = (unsigned long) _eflags; - goto push; - case 0x9d: /* popf */ - dst.ptr = (unsigned long *) &_eflags; - goto pop_instruction; - case 0xc3: /* ret */ - dst.ptr = &_eip; - goto pop_instruction; - case 0xf4: /* hlt */ - ctxt->vcpu->halt_request = 1; - goto done; - } - if (rep_prefix) { - if (_regs[VCPU_REGS_RCX] == 0) { - ctxt->vcpu->rip = _eip; - goto done; - } - _regs[VCPU_REGS_RCX]--; - _eip = ctxt->vcpu->rip; - } - switch (b) { - case 0xa4 ... 0xa5: /* movs */ - dst.type = OP_MEM; - dst.bytes = (d & ByteOp) ? 1 : op_bytes; - dst.ptr = (unsigned long *)register_address(ctxt->es_base, - _regs[VCPU_REGS_RDI]); - if ((rc = ops->read_emulated(register_address( - override_base ? *override_base : ctxt->ds_base, - _regs[VCPU_REGS_RSI]), &dst.val, dst.bytes, ctxt->vcpu)) != 0) - goto done; - register_address_increment(_regs[VCPU_REGS_RSI], - (_eflags & EFLG_DF) ? -dst.bytes : dst.bytes); - register_address_increment(_regs[VCPU_REGS_RDI], - (_eflags & EFLG_DF) ? -dst.bytes : dst.bytes); - break; - case 0xa6 ... 0xa7: /* cmps */ - DPRINTF("Urk! I don't handle CMPS.\n"); - goto cannot_emulate; - case 0xaa ... 0xab: /* stos */ - dst.type = OP_MEM; - dst.bytes = (d & ByteOp) ? 1 : op_bytes; - dst.ptr = (unsigned long *)cr2; - dst.val = _regs[VCPU_REGS_RAX]; - register_address_increment(_regs[VCPU_REGS_RDI], - (_eflags & EFLG_DF) ? -dst.bytes : dst.bytes); - break; - case 0xac ... 0xad: /* lods */ - dst.type = OP_REG; - dst.bytes = (d & ByteOp) ? 1 : op_bytes; - dst.ptr = (unsigned long *)&_regs[VCPU_REGS_RAX]; - if ((rc = ops->read_emulated(cr2, &dst.val, dst.bytes, - ctxt->vcpu)) != 0) - goto done; - register_address_increment(_regs[VCPU_REGS_RSI], - (_eflags & EFLG_DF) ? -dst.bytes : dst.bytes); - break; - case 0xae ... 0xaf: /* scas */ - DPRINTF("Urk! I don't handle SCAS.\n"); - goto cannot_emulate; - case 0xe8: /* call (near) */ { - long int rel; - switch (op_bytes) { - case 2: - rel = insn_fetch(s16, 2, _eip); - break; - case 4: - rel = insn_fetch(s32, 4, _eip); - break; - case 8: - rel = insn_fetch(s64, 8, _eip); - break; - default: - DPRINTF("Call: Invalid op_bytes\n"); - goto cannot_emulate; - } - src.val = (unsigned long) _eip; - JMP_REL(rel); - op_bytes = ad_bytes; - goto push; - } - case 0xe9: /* jmp rel */ - case 0xeb: /* jmp rel short */ - JMP_REL(src.val); - no_wb = 1; /* Disable writeback. */ - break; - - - } - goto writeback; - -twobyte_insn: - switch (b) { - case 0x01: /* lgdt, lidt, lmsw */ - /* Disable writeback. */ - no_wb = 1; - switch (modrm_reg) { - u16 size; - unsigned long address; - - case 2: /* lgdt */ - rc = read_descriptor(ctxt, ops, src.ptr, - &size, &address, op_bytes); - if (rc) - goto done; - realmode_lgdt(ctxt->vcpu, size, address); - break; - case 3: /* lidt */ - rc = read_descriptor(ctxt, ops, src.ptr, - &size, &address, op_bytes); - if (rc) - goto done; - realmode_lidt(ctxt->vcpu, size, address); - break; - case 4: /* smsw */ - if (modrm_mod != 3) - goto cannot_emulate; - *(u16 *)&_regs[modrm_rm] - = realmode_get_cr(ctxt->vcpu, 0); - break; - case 6: /* lmsw */ - if (modrm_mod != 3) - goto cannot_emulate; - realmode_lmsw(ctxt->vcpu, (u16)modrm_val, &_eflags); - break; - case 7: /* invlpg*/ - emulate_invlpg(ctxt->vcpu, cr2); - break; - default: - goto cannot_emulate; - } - break; - case 0x21: /* mov from dr to reg */ - no_wb = 1; - if (modrm_mod != 3) - goto cannot_emulate; - rc = emulator_get_dr(ctxt, modrm_reg, &_regs[modrm_rm]); - break; - case 0x23: /* mov from reg to dr */ - no_wb = 1; - if (modrm_mod != 3) - goto cannot_emulate; - rc = emulator_set_dr(ctxt, modrm_reg, _regs[modrm_rm]); - break; - case 0x40 ... 0x4f: /* cmov */ - dst.val = dst.orig_val = src.val; - no_wb = 1; - /* - * First, assume we're decoding an even cmov opcode - * (lsb == 0). - */ - switch ((b & 15) >> 1) { - case 0: /* cmovo */ - no_wb = (_eflags & EFLG_OF) ? 0 : 1; - break; - case 1: /* cmovb/cmovc/cmovnae */ - no_wb = (_eflags & EFLG_CF) ? 0 : 1; - break; - case 2: /* cmovz/cmove */ - no_wb = (_eflags & EFLG_ZF) ? 0 : 1; - break; - case 3: /* cmovbe/cmovna */ - no_wb = (_eflags & (EFLG_CF | EFLG_ZF)) ? 0 : 1; - break; - case 4: /* cmovs */ - no_wb = (_eflags & EFLG_SF) ? 0 : 1; - break; - case 5: /* cmovp/cmovpe */ - no_wb = (_eflags & EFLG_PF) ? 0 : 1; - break; - case 7: /* cmovle/cmovng */ - no_wb = (_eflags & EFLG_ZF) ? 0 : 1; - /* fall through */ - case 6: /* cmovl/cmovnge */ - no_wb &= (!(_eflags & EFLG_SF) != - !(_eflags & EFLG_OF)) ? 0 : 1; - break; - } - /* Odd cmov opcodes (lsb == 1) have inverted sense. */ - no_wb ^= b & 1; - break; - case 0xa3: - bt: /* bt */ - src.val &= (dst.bytes << 3) - 1; /* only subword offset */ - emulate_2op_SrcV_nobyte("bt", src, dst, _eflags); - break; - case 0xab: - bts: /* bts */ - src.val &= (dst.bytes << 3) - 1; /* only subword offset */ - emulate_2op_SrcV_nobyte("bts", src, dst, _eflags); - break; - case 0xb0 ... 0xb1: /* cmpxchg */ - /* - * Save real source value, then compare EAX against - * destination. - */ - src.orig_val = src.val; - src.val = _regs[VCPU_REGS_RAX]; - emulate_2op_SrcV("cmp", src, dst, _eflags); - if (_eflags & EFLG_ZF) { - /* Success: write back to memory. */ - dst.val = src.orig_val; - } else { - /* Failure: write the value we saw to EAX. */ - dst.type = OP_REG; - dst.ptr = (unsigned long *)&_regs[VCPU_REGS_RAX]; - } - break; - case 0xb3: - btr: /* btr */ - src.val &= (dst.bytes << 3) - 1; /* only subword offset */ - emulate_2op_SrcV_nobyte("btr", src, dst, _eflags); - break; - case 0xb6 ... 0xb7: /* movzx */ - dst.bytes = op_bytes; - dst.val = (d & ByteOp) ? (u8) src.val : (u16) src.val; - break; - case 0xba: /* Grp8 */ - switch (modrm_reg & 3) { - case 0: - goto bt; - case 1: - goto bts; - case 2: - goto btr; - case 3: - goto btc; - } - break; - case 0xbb: - btc: /* btc */ - src.val &= (dst.bytes << 3) - 1; /* only subword offset */ - emulate_2op_SrcV_nobyte("btc", src, dst, _eflags); - break; - case 0xbe ... 0xbf: /* movsx */ - dst.bytes = op_bytes; - dst.val = (d & ByteOp) ? (s8) src.val : (s16) src.val; - break; - case 0xc3: /* movnti */ - dst.bytes = op_bytes; - dst.val = (op_bytes == 4) ? (u32) src.val : (u64) src.val; - break; - } - goto writeback; - -twobyte_special_insn: - /* Disable writeback. */ - no_wb = 1; - switch (b) { - case 0x06: - emulate_clts(ctxt->vcpu); - break; - case 0x08: /* invd */ - break; - case 0x09: /* wbinvd */ - break; - case 0x0d: /* GrpP (prefetch) */ - case 0x18: /* Grp16 (prefetch/nop) */ - break; - case 0x20: /* mov cr, reg */ - if (modrm_mod != 3) - goto cannot_emulate; - _regs[modrm_rm] = realmode_get_cr(ctxt->vcpu, modrm_reg); - break; - case 0x22: /* mov reg, cr */ - if (modrm_mod != 3) - goto cannot_emulate; - realmode_set_cr(ctxt->vcpu, modrm_reg, modrm_val, &_eflags); - break; - case 0x30: - /* wrmsr */ - msr_data = (u32)_regs[VCPU_REGS_RAX] - | ((u64)_regs[VCPU_REGS_RDX] << 32); - rc = kvm_set_msr(ctxt->vcpu, _regs[VCPU_REGS_RCX], msr_data); - if (rc) { - kvm_x86_ops->inject_gp(ctxt->vcpu, 0); - _eip = ctxt->vcpu->rip; - } - rc = X86EMUL_CONTINUE; - break; - case 0x32: - /* rdmsr */ - rc = kvm_get_msr(ctxt->vcpu, _regs[VCPU_REGS_RCX], &msr_data); - if (rc) { - kvm_x86_ops->inject_gp(ctxt->vcpu, 0); - _eip = ctxt->vcpu->rip; - } else { - _regs[VCPU_REGS_RAX] = (u32)msr_data; - _regs[VCPU_REGS_RDX] = msr_data >> 32; - } - rc = X86EMUL_CONTINUE; - break; - case 0x80 ... 0x8f: /* jnz rel, etc*/ { - long int rel; - - switch (op_bytes) { - case 2: - rel = insn_fetch(s16, 2, _eip); - break; - case 4: - rel = insn_fetch(s32, 4, _eip); - break; - case 8: - rel = insn_fetch(s64, 8, _eip); - break; - default: - DPRINTF("jnz: Invalid op_bytes\n"); - goto cannot_emulate; - } - if (test_cc(b, _eflags)) - JMP_REL(rel); - break; - } - case 0xc7: /* Grp9 (cmpxchg8b) */ - { - u64 old, new; - if ((rc = ops->read_emulated(cr2, &old, 8, ctxt->vcpu)) - != 0) - goto done; - if (((u32) (old >> 0) != (u32) _regs[VCPU_REGS_RAX]) || - ((u32) (old >> 32) != (u32) _regs[VCPU_REGS_RDX])) { - _regs[VCPU_REGS_RAX] = (u32) (old >> 0); - _regs[VCPU_REGS_RDX] = (u32) (old >> 32); - _eflags &= ~EFLG_ZF; - } else { - new = ((u64)_regs[VCPU_REGS_RCX] << 32) - | (u32) _regs[VCPU_REGS_RBX]; - if ((rc = ops->cmpxchg_emulated(cr2, &old, - &new, 8, ctxt->vcpu)) != 0) - goto done; - _eflags |= EFLG_ZF; - } - break; - } - } - goto writeback; - -cannot_emulate: - DPRINTF("Cannot emulate %02x\n", b); - return -1; -} - -#ifdef __XEN__ - -#include <asm/mm.h> -#include <asm/uaccess.h> - -int -x86_emulate_read_std(unsigned long addr, - unsigned long *val, - unsigned int bytes, struct x86_emulate_ctxt *ctxt) -{ - unsigned int rc; - - *val = 0; - - if ((rc = copy_from_user((void *)val, (void *)addr, bytes)) != 0) { - propagate_page_fault(addr + bytes - rc, 0); /* read fault */ - return X86EMUL_PROPAGATE_FAULT; - } - - return X86EMUL_CONTINUE; -} - -int -x86_emulate_write_std(unsigned long addr, - unsigned long val, - unsigned int bytes, struct x86_emulate_ctxt *ctxt) -{ - unsigned int rc; - - if ((rc = copy_to_user((void *)addr, (void *)&val, bytes)) != 0) { - propagate_page_fault(addr + bytes - rc, PGERR_write_access); - return X86EMUL_PROPAGATE_FAULT; - } - - return X86EMUL_CONTINUE; -} - -#endif diff --git a/drivers/kvm/x86_emulate.h b/drivers/kvm/x86_emulate.h deleted file mode 100644 index 92c73aa7f9ac..000000000000 --- a/drivers/kvm/x86_emulate.h +++ /dev/null @@ -1,155 +0,0 @@ -/****************************************************************************** - * x86_emulate.h - * - * Generic x86 (32-bit and 64-bit) instruction decoder and emulator. - * - * Copyright (c) 2005 Keir Fraser - * - * From: xen-unstable 10676:af9809f51f81a3c43f276f00c81a52ef558afda4 - */ - -#ifndef __X86_EMULATE_H__ -#define __X86_EMULATE_H__ - -struct x86_emulate_ctxt; - -/* - * x86_emulate_ops: - * - * These operations represent the instruction emulator's interface to memory. - * There are two categories of operation: those that act on ordinary memory - * regions (*_std), and those that act on memory regions known to require - * special treatment or emulation (*_emulated). - * - * The emulator assumes that an instruction accesses only one 'emulated memory' - * location, that this location is the given linear faulting address (cr2), and - * that this is one of the instruction's data operands. Instruction fetches and - * stack operations are assumed never to access emulated memory. The emulator - * automatically deduces which operand of a string-move operation is accessing - * emulated memory, and assumes that the other operand accesses normal memory. - * - * NOTES: - * 1. The emulator isn't very smart about emulated vs. standard memory. - * 'Emulated memory' access addresses should be checked for sanity. - * 'Normal memory' accesses may fault, and the caller must arrange to - * detect and handle reentrancy into the emulator via recursive faults. - * Accesses may be unaligned and may cross page boundaries. - * 2. If the access fails (cannot emulate, or a standard access faults) then - * it is up to the memop to propagate the fault to the guest VM via - * some out-of-band mechanism, unknown to the emulator. The memop signals - * failure by returning X86EMUL_PROPAGATE_FAULT to the emulator, which will - * then immediately bail. - * 3. Valid access sizes are 1, 2, 4 and 8 bytes. On x86/32 systems only - * cmpxchg8b_emulated need support 8-byte accesses. - * 4. The emulator cannot handle 64-bit mode emulation on an x86/32 system. - */ -/* Access completed successfully: continue emulation as normal. */ -#define X86EMUL_CONTINUE 0 -/* Access is unhandleable: bail from emulation and return error to caller. */ -#define X86EMUL_UNHANDLEABLE 1 -/* Terminate emulation but return success to the caller. */ -#define X86EMUL_PROPAGATE_FAULT 2 /* propagate a generated fault to guest */ -#define X86EMUL_RETRY_INSTR 2 /* retry the instruction for some reason */ -#define X86EMUL_CMPXCHG_FAILED 2 /* cmpxchg did not see expected value */ -struct x86_emulate_ops { - /* - * read_std: Read bytes of standard (non-emulated/special) memory. - * Used for instruction fetch, stack operations, and others. - * @addr: [IN ] Linear address from which to read. - * @val: [OUT] Value read from memory, zero-extended to 'u_long'. - * @bytes: [IN ] Number of bytes to read from memory. - */ - int (*read_std)(unsigned long addr, void *val, - unsigned int bytes, struct kvm_vcpu *vcpu); - - /* - * write_std: Write bytes of standard (non-emulated/special) memory. - * Used for stack operations, and others. - * @addr: [IN ] Linear address to which to write. - * @val: [IN ] Value to write to memory (low-order bytes used as - * required). - * @bytes: [IN ] Number of bytes to write to memory. - */ - int (*write_std)(unsigned long addr, const void *val, - unsigned int bytes, struct kvm_vcpu *vcpu); - - /* - * read_emulated: Read bytes from emulated/special memory area. - * @addr: [IN ] Linear address from which to read. - * @val: [OUT] Value read from memory, zero-extended to 'u_long'. - * @bytes: [IN ] Number of bytes to read from memory. - */ - int (*read_emulated) (unsigned long addr, - void *val, - unsigned int bytes, - struct kvm_vcpu *vcpu); - - /* - * write_emulated: Read bytes from emulated/special memory area. - * @addr: [IN ] Linear address to which to write. - * @val: [IN ] Value to write to memory (low-order bytes used as - * required). - * @bytes: [IN ] Number of bytes to write to memory. - */ - int (*write_emulated) (unsigned long addr, - const void *val, - unsigned int bytes, - struct kvm_vcpu *vcpu); - - /* - * cmpxchg_emulated: Emulate an atomic (LOCKed) CMPXCHG operation on an - * emulated/special memory area. - * @addr: [IN ] Linear address to access. - * @old: [IN ] Value expected to be current at @addr. - * @new: [IN ] Value to write to @addr. - * @bytes: [IN ] Number of bytes to access using CMPXCHG. - */ - int (*cmpxchg_emulated) (unsigned long addr, - const void *old, - const void *new, - unsigned int bytes, - struct kvm_vcpu *vcpu); - -}; - -struct x86_emulate_ctxt { - /* Register state before/after emulation. */ - struct kvm_vcpu *vcpu; - - /* Linear faulting address (if emulating a page-faulting instruction). */ - unsigned long eflags; - unsigned long cr2; - - /* Emulated execution mode, represented by an X86EMUL_MODE value. */ - int mode; - - unsigned long cs_base; - unsigned long ds_base; - unsigned long es_base; - unsigned long ss_base; - unsigned long gs_base; - unsigned long fs_base; -}; - -/* Execution mode, passed to the emulator. */ -#define X86EMUL_MODE_REAL 0 /* Real mode. */ -#define X86EMUL_MODE_PROT16 2 /* 16-bit protected mode. */ -#define X86EMUL_MODE_PROT32 4 /* 32-bit protected mode. */ -#define X86EMUL_MODE_PROT64 8 /* 64-bit (long) mode. */ - -/* Host execution mode. */ -#if defined(__i386__) -#define X86EMUL_MODE_HOST X86EMUL_MODE_PROT32 -#elif defined(CONFIG_X86_64) -#define X86EMUL_MODE_HOST X86EMUL_MODE_PROT64 -#endif - -/* - * x86_emulate_memop: Emulate an instruction that faulted attempting to - * read/write a 'special' memory area. - * Returns -1 on failure, 0 on success. - */ -int x86_emulate_memop(struct x86_emulate_ctxt *ctxt, - struct x86_emulate_ops *ops); - -#endif /* __X86_EMULATE_H__ */ diff --git a/drivers/lguest/core.c b/drivers/lguest/core.c index cb4c67025d52..7743d73768df 100644 --- a/drivers/lguest/core.c +++ b/drivers/lguest/core.c @@ -151,43 +151,43 @@ int lguest_address_ok(const struct lguest *lg, /* This routine copies memory from the Guest. Here we can see how useful the * kill_lguest() routine we met in the Launcher can be: we return a random * value (all zeroes) instead of needing to return an error. */ -void __lgread(struct lguest *lg, void *b, unsigned long addr, unsigned bytes) +void __lgread(struct lg_cpu *cpu, void *b, unsigned long addr, unsigned bytes) { - if (!lguest_address_ok(lg, addr, bytes) - || copy_from_user(b, lg->mem_base + addr, bytes) != 0) { + if (!lguest_address_ok(cpu->lg, addr, bytes) + || copy_from_user(b, cpu->lg->mem_base + addr, bytes) != 0) { /* copy_from_user should do this, but as we rely on it... */ memset(b, 0, bytes); - kill_guest(lg, "bad read address %#lx len %u", addr, bytes); + kill_guest(cpu, "bad read address %#lx len %u", addr, bytes); } } /* This is the write (copy into guest) version. */ -void __lgwrite(struct lguest *lg, unsigned long addr, const void *b, +void __lgwrite(struct lg_cpu *cpu, unsigned long addr, const void *b, unsigned bytes) { - if (!lguest_address_ok(lg, addr, bytes) - || copy_to_user(lg->mem_base + addr, b, bytes) != 0) - kill_guest(lg, "bad write address %#lx len %u", addr, bytes); + if (!lguest_address_ok(cpu->lg, addr, bytes) + || copy_to_user(cpu->lg->mem_base + addr, b, bytes) != 0) + kill_guest(cpu, "bad write address %#lx len %u", addr, bytes); } /*:*/ /*H:030 Let's jump straight to the the main loop which runs the Guest. * Remember, this is called by the Launcher reading /dev/lguest, and we keep * going around and around until something interesting happens. */ -int run_guest(struct lguest *lg, unsigned long __user *user) +int run_guest(struct lg_cpu *cpu, unsigned long __user *user) { /* We stop running once the Guest is dead. */ - while (!lg->dead) { + while (!cpu->lg->dead) { /* First we run any hypercalls the Guest wants done. */ - if (lg->hcall) - do_hypercalls(lg); + if (cpu->hcall) + do_hypercalls(cpu); /* It's possible the Guest did a NOTIFY hypercall to the * Launcher, in which case we return from the read() now. */ - if (lg->pending_notify) { - if (put_user(lg->pending_notify, user)) + if (cpu->pending_notify) { + if (put_user(cpu->pending_notify, user)) return -EFAULT; - return sizeof(lg->pending_notify); + return sizeof(cpu->pending_notify); } /* Check for signals */ @@ -195,13 +195,13 @@ int run_guest(struct lguest *lg, unsigned long __user *user) return -ERESTARTSYS; /* If Waker set break_out, return to Launcher. */ - if (lg->break_out) + if (cpu->break_out) return -EAGAIN; /* Check if there are any interrupts which can be delivered * now: if so, this sets up the hander to be executed when we * next run the Guest. */ - maybe_do_interrupt(lg); + maybe_do_interrupt(cpu); /* All long-lived kernel loops need to check with this horrible * thing called the freezer. If the Host is trying to suspend, @@ -210,12 +210,12 @@ int run_guest(struct lguest *lg, unsigned long __user *user) /* Just make absolutely sure the Guest is still alive. One of * those hypercalls could have been fatal, for example. */ - if (lg->dead) + if (cpu->lg->dead) break; /* If the Guest asked to be stopped, we sleep. The Guest's * clock timer or LHCALL_BREAK from the Waker will wake us. */ - if (lg->halted) { + if (cpu->halted) { set_current_state(TASK_INTERRUPTIBLE); schedule(); continue; @@ -226,15 +226,17 @@ int run_guest(struct lguest *lg, unsigned long __user *user) local_irq_disable(); /* Actually run the Guest until something happens. */ - lguest_arch_run_guest(lg); + lguest_arch_run_guest(cpu); /* Now we're ready to be interrupted or moved to other CPUs */ local_irq_enable(); /* Now we deal with whatever happened to the Guest. */ - lguest_arch_handle_trap(lg); + lguest_arch_handle_trap(cpu); } + if (cpu->lg->dead == ERR_PTR(-ERESTART)) + return -ERESTART; /* The Guest is dead => "No such file or directory" */ return -ENOENT; } @@ -253,7 +255,7 @@ static int __init init(void) /* Lguest can't run under Xen, VMI or itself. It does Tricky Stuff. */ if (paravirt_enabled()) { - printk("lguest is afraid of %s\n", pv_info.name); + printk("lguest is afraid of being a guest\n"); return -EPERM; } diff --git a/drivers/lguest/hypercalls.c b/drivers/lguest/hypercalls.c index b478affe8f91..0f2cb4fd7c69 100644 --- a/drivers/lguest/hypercalls.c +++ b/drivers/lguest/hypercalls.c @@ -23,13 +23,14 @@ #include <linux/uaccess.h> #include <linux/syscalls.h> #include <linux/mm.h> +#include <linux/ktime.h> #include <asm/page.h> #include <asm/pgtable.h> #include "lg.h" /*H:120 This is the core hypercall routine: where the Guest gets what it wants. * Or gets killed. Or, in the case of LHCALL_CRASH, both. */ -static void do_hcall(struct lguest *lg, struct hcall_args *args) +static void do_hcall(struct lg_cpu *cpu, struct hcall_args *args) { switch (args->arg0) { case LHCALL_FLUSH_ASYNC: @@ -39,60 +40,62 @@ static void do_hcall(struct lguest *lg, struct hcall_args *args) case LHCALL_LGUEST_INIT: /* You can't get here unless you're already initialized. Don't * do that. */ - kill_guest(lg, "already have lguest_data"); + kill_guest(cpu, "already have lguest_data"); break; - case LHCALL_CRASH: { - /* Crash is such a trivial hypercall that we do it in four + case LHCALL_SHUTDOWN: { + /* Shutdown is such a trivial hypercall that we do it in four * lines right here. */ char msg[128]; /* If the lgread fails, it will call kill_guest() itself; the * kill_guest() with the message will be ignored. */ - __lgread(lg, msg, args->arg1, sizeof(msg)); + __lgread(cpu, msg, args->arg1, sizeof(msg)); msg[sizeof(msg)-1] = '\0'; - kill_guest(lg, "CRASH: %s", msg); + kill_guest(cpu, "CRASH: %s", msg); + if (args->arg2 == LGUEST_SHUTDOWN_RESTART) + cpu->lg->dead = ERR_PTR(-ERESTART); break; } case LHCALL_FLUSH_TLB: /* FLUSH_TLB comes in two flavors, depending on the * argument: */ if (args->arg1) - guest_pagetable_clear_all(lg); + guest_pagetable_clear_all(cpu); else - guest_pagetable_flush_user(lg); + guest_pagetable_flush_user(cpu); break; /* All these calls simply pass the arguments through to the right * routines. */ case LHCALL_NEW_PGTABLE: - guest_new_pagetable(lg, args->arg1); + guest_new_pagetable(cpu, args->arg1); break; case LHCALL_SET_STACK: - guest_set_stack(lg, args->arg1, args->arg2, args->arg3); + guest_set_stack(cpu, args->arg1, args->arg2, args->arg3); break; case LHCALL_SET_PTE: - guest_set_pte(lg, args->arg1, args->arg2, __pte(args->arg3)); + guest_set_pte(cpu, args->arg1, args->arg2, __pte(args->arg3)); break; case LHCALL_SET_PMD: - guest_set_pmd(lg, args->arg1, args->arg2); + guest_set_pmd(cpu->lg, args->arg1, args->arg2); break; case LHCALL_SET_CLOCKEVENT: - guest_set_clockevent(lg, args->arg1); + guest_set_clockevent(cpu, args->arg1); break; case LHCALL_TS: /* This sets the TS flag, as we saw used in run_guest(). */ - lg->ts = args->arg1; + cpu->ts = args->arg1; break; case LHCALL_HALT: /* Similarly, this sets the halted flag for run_guest(). */ - lg->halted = 1; + cpu->halted = 1; break; case LHCALL_NOTIFY: - lg->pending_notify = args->arg1; + cpu->pending_notify = args->arg1; break; default: /* It should be an architecture-specific hypercall. */ - if (lguest_arch_do_hcall(lg, args)) - kill_guest(lg, "Bad hypercall %li\n", args->arg0); + if (lguest_arch_do_hcall(cpu, args)) + kill_guest(cpu, "Bad hypercall %li\n", args->arg0); } } /*:*/ @@ -104,13 +107,13 @@ static void do_hcall(struct lguest *lg, struct hcall_args *args) * Guest put them in the ring, but we also promise the Guest that they will * happen before any normal hypercall (which is why we check this before * checking for a normal hcall). */ -static void do_async_hcalls(struct lguest *lg) +static void do_async_hcalls(struct lg_cpu *cpu) { unsigned int i; u8 st[LHCALL_RING_SIZE]; /* For simplicity, we copy the entire call status array in at once. */ - if (copy_from_user(&st, &lg->lguest_data->hcall_status, sizeof(st))) + if (copy_from_user(&st, &cpu->lg->lguest_data->hcall_status, sizeof(st))) return; /* We process "struct lguest_data"s hcalls[] ring once. */ @@ -119,7 +122,7 @@ static void do_async_hcalls(struct lguest *lg) /* We remember where we were up to from last time. This makes * sure that the hypercalls are done in the order the Guest * places them in the ring. */ - unsigned int n = lg->next_hcall; + unsigned int n = cpu->next_hcall; /* 0xFF means there's no call here (yet). */ if (st[n] == 0xFF) @@ -127,65 +130,65 @@ static void do_async_hcalls(struct lguest *lg) /* OK, we have hypercall. Increment the "next_hcall" cursor, * and wrap back to 0 if we reach the end. */ - if (++lg->next_hcall == LHCALL_RING_SIZE) - lg->next_hcall = 0; + if (++cpu->next_hcall == LHCALL_RING_SIZE) + cpu->next_hcall = 0; /* Copy the hypercall arguments into a local copy of * the hcall_args struct. */ - if (copy_from_user(&args, &lg->lguest_data->hcalls[n], + if (copy_from_user(&args, &cpu->lg->lguest_data->hcalls[n], sizeof(struct hcall_args))) { - kill_guest(lg, "Fetching async hypercalls"); + kill_guest(cpu, "Fetching async hypercalls"); break; } /* Do the hypercall, same as a normal one. */ - do_hcall(lg, &args); + do_hcall(cpu, &args); /* Mark the hypercall done. */ - if (put_user(0xFF, &lg->lguest_data->hcall_status[n])) { - kill_guest(lg, "Writing result for async hypercall"); + if (put_user(0xFF, &cpu->lg->lguest_data->hcall_status[n])) { + kill_guest(cpu, "Writing result for async hypercall"); break; } /* Stop doing hypercalls if they want to notify the Launcher: * it needs to service this first. */ - if (lg->pending_notify) + if (cpu->pending_notify) break; } } /* Last of all, we look at what happens first of all. The very first time the * Guest makes a hypercall, we end up here to set things up: */ -static void initialize(struct lguest *lg) +static void initialize(struct lg_cpu *cpu) { /* You can't do anything until you're initialized. The Guest knows the * rules, so we're unforgiving here. */ - if (lg->hcall->arg0 != LHCALL_LGUEST_INIT) { - kill_guest(lg, "hypercall %li before INIT", lg->hcall->arg0); + if (cpu->hcall->arg0 != LHCALL_LGUEST_INIT) { + kill_guest(cpu, "hypercall %li before INIT", cpu->hcall->arg0); return; } - if (lguest_arch_init_hypercalls(lg)) - kill_guest(lg, "bad guest page %p", lg->lguest_data); + if (lguest_arch_init_hypercalls(cpu)) + kill_guest(cpu, "bad guest page %p", cpu->lg->lguest_data); /* The Guest tells us where we're not to deliver interrupts by putting * the range of addresses into "struct lguest_data". */ - if (get_user(lg->noirq_start, &lg->lguest_data->noirq_start) - || get_user(lg->noirq_end, &lg->lguest_data->noirq_end)) - kill_guest(lg, "bad guest page %p", lg->lguest_data); + if (get_user(cpu->lg->noirq_start, &cpu->lg->lguest_data->noirq_start) + || get_user(cpu->lg->noirq_end, &cpu->lg->lguest_data->noirq_end)) + kill_guest(cpu, "bad guest page %p", cpu->lg->lguest_data); /* We write the current time into the Guest's data page once so it can * set its clock. */ - write_timestamp(lg); + write_timestamp(cpu); /* page_tables.c will also do some setup. */ - page_table_guest_data_init(lg); + page_table_guest_data_init(cpu); /* This is the one case where the above accesses might have been the * first write to a Guest page. This may have caused a copy-on-write * fault, but the old page might be (read-only) in the Guest * pagetable. */ - guest_pagetable_clear_all(lg); + guest_pagetable_clear_all(cpu); } /*H:100 @@ -194,27 +197,27 @@ static void initialize(struct lguest *lg) * Remember from the Guest, hypercalls come in two flavors: normal and * asynchronous. This file handles both of types. */ -void do_hypercalls(struct lguest *lg) +void do_hypercalls(struct lg_cpu *cpu) { /* Not initialized yet? This hypercall must do it. */ - if (unlikely(!lg->lguest_data)) { + if (unlikely(!cpu->lg->lguest_data)) { /* Set up the "struct lguest_data" */ - initialize(lg); + initialize(cpu); /* Hcall is done. */ - lg->hcall = NULL; + cpu->hcall = NULL; return; } /* The Guest has initialized. * * Look in the hypercall ring for the async hypercalls: */ - do_async_hcalls(lg); + do_async_hcalls(cpu); /* If we stopped reading the hypercall ring because the Guest did a * NOTIFY to the Launcher, we want to return now. Otherwise we do * the hypercall. */ - if (!lg->pending_notify) { - do_hcall(lg, lg->hcall); + if (!cpu->pending_notify) { + do_hcall(cpu, cpu->hcall); /* Tricky point: we reset the hcall pointer to mark the * hypercall as "done". We use the hcall pointer rather than * the trap number to indicate a hypercall is pending. @@ -225,16 +228,17 @@ void do_hypercalls(struct lguest *lg) * Launcher, the run_guest() loop will exit without running the * Guest. When it comes back it would try to re-run the * hypercall. */ - lg->hcall = NULL; + cpu->hcall = NULL; } } /* This routine supplies the Guest with time: it's used for wallclock time at * initial boot and as a rough time source if the TSC isn't available. */ -void write_timestamp(struct lguest *lg) +void write_timestamp(struct lg_cpu *cpu) { struct timespec now; ktime_get_real_ts(&now); - if (copy_to_user(&lg->lguest_data->time, &now, sizeof(struct timespec))) - kill_guest(lg, "Writing timestamp"); + if (copy_to_user(&cpu->lg->lguest_data->time, + &now, sizeof(struct timespec))) + kill_guest(cpu, "Writing timestamp"); } diff --git a/drivers/lguest/interrupts_and_traps.c b/drivers/lguest/interrupts_and_traps.c index 2b66f79c208b..32e97c1858e5 100644 --- a/drivers/lguest/interrupts_and_traps.c +++ b/drivers/lguest/interrupts_and_traps.c @@ -41,11 +41,11 @@ static int idt_present(u32 lo, u32 hi) /* We need a helper to "push" a value onto the Guest's stack, since that's a * big part of what delivering an interrupt does. */ -static void push_guest_stack(struct lguest *lg, unsigned long *gstack, u32 val) +static void push_guest_stack(struct lg_cpu *cpu, unsigned long *gstack, u32 val) { /* Stack grows upwards: move stack then write value. */ *gstack -= 4; - lgwrite(lg, *gstack, u32, val); + lgwrite(cpu, *gstack, u32, val); } /*H:210 The set_guest_interrupt() routine actually delivers the interrupt or @@ -60,7 +60,7 @@ static void push_guest_stack(struct lguest *lg, unsigned long *gstack, u32 val) * We set up the stack just like the CPU does for a real interrupt, so it's * identical for the Guest (and the standard "iret" instruction will undo * it). */ -static void set_guest_interrupt(struct lguest *lg, u32 lo, u32 hi, int has_err) +static void set_guest_interrupt(struct lg_cpu *cpu, u32 lo, u32 hi, int has_err) { unsigned long gstack, origstack; u32 eflags, ss, irq_enable; @@ -69,59 +69,59 @@ static void set_guest_interrupt(struct lguest *lg, u32 lo, u32 hi, int has_err) /* There are two cases for interrupts: one where the Guest is already * in the kernel, and a more complex one where the Guest is in * userspace. We check the privilege level to find out. */ - if ((lg->regs->ss&0x3) != GUEST_PL) { + if ((cpu->regs->ss&0x3) != GUEST_PL) { /* The Guest told us their kernel stack with the SET_STACK * hypercall: both the virtual address and the segment */ - virtstack = lg->esp1; - ss = lg->ss1; + virtstack = cpu->esp1; + ss = cpu->ss1; - origstack = gstack = guest_pa(lg, virtstack); + origstack = gstack = guest_pa(cpu, virtstack); /* We push the old stack segment and pointer onto the new * stack: when the Guest does an "iret" back from the interrupt * handler the CPU will notice they're dropping privilege * levels and expect these here. */ - push_guest_stack(lg, &gstack, lg->regs->ss); - push_guest_stack(lg, &gstack, lg->regs->esp); + push_guest_stack(cpu, &gstack, cpu->regs->ss); + push_guest_stack(cpu, &gstack, cpu->regs->esp); } else { /* We're staying on the same Guest (kernel) stack. */ - virtstack = lg->regs->esp; - ss = lg->regs->ss; + virtstack = cpu->regs->esp; + ss = cpu->regs->ss; - origstack = gstack = guest_pa(lg, virtstack); + origstack = gstack = guest_pa(cpu, virtstack); } /* Remember that we never let the Guest actually disable interrupts, so * the "Interrupt Flag" bit is always set. We copy that bit from the * Guest's "irq_enabled" field into the eflags word: we saw the Guest * copy it back in "lguest_iret". */ - eflags = lg->regs->eflags; - if (get_user(irq_enable, &lg->lguest_data->irq_enabled) == 0 + eflags = cpu->regs->eflags; + if (get_user(irq_enable, &cpu->lg->lguest_data->irq_enabled) == 0 && !(irq_enable & X86_EFLAGS_IF)) eflags &= ~X86_EFLAGS_IF; /* An interrupt is expected to push three things on the stack: the old * "eflags" word, the old code segment, and the old instruction * pointer. */ - push_guest_stack(lg, &gstack, eflags); - push_guest_stack(lg, &gstack, lg->regs->cs); - push_guest_stack(lg, &gstack, lg->regs->eip); + push_guest_stack(cpu, &gstack, eflags); + push_guest_stack(cpu, &gstack, cpu->regs->cs); + push_guest_stack(cpu, &gstack, cpu->regs->eip); /* For the six traps which supply an error code, we push that, too. */ if (has_err) - push_guest_stack(lg, &gstack, lg->regs->errcode); + push_guest_stack(cpu, &gstack, cpu->regs->errcode); /* Now we've pushed all the old state, we change the stack, the code * segment and the address to execute. */ - lg->regs->ss = ss; - lg->regs->esp = virtstack + (gstack - origstack); - lg->regs->cs = (__KERNEL_CS|GUEST_PL); - lg->regs->eip = idt_address(lo, hi); + cpu->regs->ss = ss; + cpu->regs->esp = virtstack + (gstack - origstack); + cpu->regs->cs = (__KERNEL_CS|GUEST_PL); + cpu->regs->eip = idt_address(lo, hi); /* There are two kinds of interrupt handlers: 0xE is an "interrupt * gate" which expects interrupts to be disabled on entry. */ if (idt_type(lo, hi) == 0xE) - if (put_user(0, &lg->lguest_data->irq_enabled)) - kill_guest(lg, "Disabling interrupts"); + if (put_user(0, &cpu->lg->lguest_data->irq_enabled)) + kill_guest(cpu, "Disabling interrupts"); } /*H:205 @@ -129,23 +129,23 @@ static void set_guest_interrupt(struct lguest *lg, u32 lo, u32 hi, int has_err) * * maybe_do_interrupt() gets called before every entry to the Guest, to see if * we should divert the Guest to running an interrupt handler. */ -void maybe_do_interrupt(struct lguest *lg) +void maybe_do_interrupt(struct lg_cpu *cpu) { unsigned int irq; DECLARE_BITMAP(blk, LGUEST_IRQS); struct desc_struct *idt; /* If the Guest hasn't even initialized yet, we can do nothing. */ - if (!lg->lguest_data) + if (!cpu->lg->lguest_data) return; /* Take our "irqs_pending" array and remove any interrupts the Guest * wants blocked: the result ends up in "blk". */ - if (copy_from_user(&blk, lg->lguest_data->blocked_interrupts, + if (copy_from_user(&blk, cpu->lg->lguest_data->blocked_interrupts, sizeof(blk))) return; - bitmap_andnot(blk, lg->irqs_pending, blk, LGUEST_IRQS); + bitmap_andnot(blk, cpu->irqs_pending, blk, LGUEST_IRQS); /* Find the first interrupt. */ irq = find_first_bit(blk, LGUEST_IRQS); @@ -155,19 +155,20 @@ void maybe_do_interrupt(struct lguest *lg) /* They may be in the middle of an iret, where they asked us never to * deliver interrupts. */ - if (lg->regs->eip >= lg->noirq_start && lg->regs->eip < lg->noirq_end) + if (cpu->regs->eip >= cpu->lg->noirq_start && + (cpu->regs->eip < cpu->lg->noirq_end)) return; /* If they're halted, interrupts restart them. */ - if (lg->halted) { + if (cpu->halted) { /* Re-enable interrupts. */ - if (put_user(X86_EFLAGS_IF, &lg->lguest_data->irq_enabled)) - kill_guest(lg, "Re-enabling interrupts"); - lg->halted = 0; + if (put_user(X86_EFLAGS_IF, &cpu->lg->lguest_data->irq_enabled)) + kill_guest(cpu, "Re-enabling interrupts"); + cpu->halted = 0; } else { /* Otherwise we check if they have interrupts disabled. */ u32 irq_enabled; - if (get_user(irq_enabled, &lg->lguest_data->irq_enabled)) + if (get_user(irq_enabled, &cpu->lg->lguest_data->irq_enabled)) irq_enabled = 0; if (!irq_enabled) return; @@ -176,15 +177,15 @@ void maybe_do_interrupt(struct lguest *lg) /* Look at the IDT entry the Guest gave us for this interrupt. The * first 32 (FIRST_EXTERNAL_VECTOR) entries are for traps, so we skip * over them. */ - idt = &lg->arch.idt[FIRST_EXTERNAL_VECTOR+irq]; + idt = &cpu->arch.idt[FIRST_EXTERNAL_VECTOR+irq]; /* If they don't have a handler (yet?), we just ignore it */ if (idt_present(idt->a, idt->b)) { /* OK, mark it no longer pending and deliver it. */ - clear_bit(irq, lg->irqs_pending); + clear_bit(irq, cpu->irqs_pending); /* set_guest_interrupt() takes the interrupt descriptor and a * flag to say whether this interrupt pushes an error code onto * the stack as well: virtual interrupts never do. */ - set_guest_interrupt(lg, idt->a, idt->b, 0); + set_guest_interrupt(cpu, idt->a, idt->b, 0); } /* Every time we deliver an interrupt, we update the timestamp in the @@ -192,7 +193,7 @@ void maybe_do_interrupt(struct lguest *lg) * did this more often, but it can actually be quite slow: doing it * here is a compromise which means at least it gets updated every * timer interrupt. */ - write_timestamp(lg); + write_timestamp(cpu); } /*:*/ @@ -245,19 +246,19 @@ static int has_err(unsigned int trap) } /* deliver_trap() returns true if it could deliver the trap. */ -int deliver_trap(struct lguest *lg, unsigned int num) +int deliver_trap(struct lg_cpu *cpu, unsigned int num) { /* Trap numbers are always 8 bit, but we set an impossible trap number * for traps inside the Switcher, so check that here. */ - if (num >= ARRAY_SIZE(lg->arch.idt)) + if (num >= ARRAY_SIZE(cpu->arch.idt)) return 0; /* Early on the Guest hasn't set the IDT entries (or maybe it put a * bogus one in): if we fail here, the Guest will be killed. */ - if (!idt_present(lg->arch.idt[num].a, lg->arch.idt[num].b)) + if (!idt_present(cpu->arch.idt[num].a, cpu->arch.idt[num].b)) return 0; - set_guest_interrupt(lg, lg->arch.idt[num].a, lg->arch.idt[num].b, - has_err(num)); + set_guest_interrupt(cpu, cpu->arch.idt[num].a, + cpu->arch.idt[num].b, has_err(num)); return 1; } @@ -309,18 +310,18 @@ static int direct_trap(unsigned int num) * the Guest. * * Which is deeply unfair, because (literally!) it wasn't the Guests' fault. */ -void pin_stack_pages(struct lguest *lg) +void pin_stack_pages(struct lg_cpu *cpu) { unsigned int i; /* Depending on the CONFIG_4KSTACKS option, the Guest can have one or * two pages of stack space. */ - for (i = 0; i < lg->stack_pages; i++) + for (i = 0; i < cpu->lg->stack_pages; i++) /* The stack grows *upwards*, so the address we're given is the * start of the page after the kernel stack. Subtract one to * get back onto the first stack page, and keep subtracting to * get to the rest of the stack pages. */ - pin_page(lg, lg->esp1 - 1 - i * PAGE_SIZE); + pin_page(cpu, cpu->esp1 - 1 - i * PAGE_SIZE); } /* Direct traps also mean that we need to know whenever the Guest wants to use @@ -331,21 +332,21 @@ void pin_stack_pages(struct lguest *lg) * * In Linux each process has its own kernel stack, so this happens a lot: we * change stacks on each context switch. */ -void guest_set_stack(struct lguest *lg, u32 seg, u32 esp, unsigned int pages) +void guest_set_stack(struct lg_cpu *cpu, u32 seg, u32 esp, unsigned int pages) { /* You are not allowed have a stack segment with privilege level 0: bad * Guest! */ if ((seg & 0x3) != GUEST_PL) - kill_guest(lg, "bad stack segment %i", seg); + kill_guest(cpu, "bad stack segment %i", seg); /* We only expect one or two stack pages. */ if (pages > 2) - kill_guest(lg, "bad stack pages %u", pages); + kill_guest(cpu, "bad stack pages %u", pages); /* Save where the stack is, and how many pages */ - lg->ss1 = seg; - lg->esp1 = esp; - lg->stack_pages = pages; + cpu->ss1 = seg; + cpu->esp1 = esp; + cpu->lg->stack_pages = pages; /* Make sure the new stack pages are mapped */ - pin_stack_pages(lg); + pin_stack_pages(cpu); } /* All this reference to mapping stacks leads us neatly into the other complex @@ -353,7 +354,7 @@ void guest_set_stack(struct lguest *lg, u32 seg, u32 esp, unsigned int pages) /*H:235 This is the routine which actually checks the Guest's IDT entry and * transfers it into the entry in "struct lguest": */ -static void set_trap(struct lguest *lg, struct desc_struct *trap, +static void set_trap(struct lg_cpu *cpu, struct desc_struct *trap, unsigned int num, u32 lo, u32 hi) { u8 type = idt_type(lo, hi); @@ -366,7 +367,7 @@ static void set_trap(struct lguest *lg, struct desc_struct *trap, /* We only support interrupt and trap gates. */ if (type != 0xE && type != 0xF) - kill_guest(lg, "bad IDT type %i", type); + kill_guest(cpu, "bad IDT type %i", type); /* We only copy the handler address, present bit, privilege level and * type. The privilege level controls where the trap can be triggered @@ -383,7 +384,7 @@ static void set_trap(struct lguest *lg, struct desc_struct *trap, * * We saw the Guest setting Interrupt Descriptor Table (IDT) entries with the * LHCALL_LOAD_IDT_ENTRY hypercall before: that comes here. */ -void load_guest_idt_entry(struct lguest *lg, unsigned int num, u32 lo, u32 hi) +void load_guest_idt_entry(struct lg_cpu *cpu, unsigned int num, u32 lo, u32 hi) { /* Guest never handles: NMI, doublefault, spurious interrupt or * hypercall. We ignore when it tries to set them. */ @@ -392,13 +393,13 @@ void load_guest_idt_entry(struct lguest *lg, unsigned int num, u32 lo, u32 hi) /* Mark the IDT as changed: next time the Guest runs we'll know we have * to copy this again. */ - lg->changed |= CHANGED_IDT; + cpu->changed |= CHANGED_IDT; /* Check that the Guest doesn't try to step outside the bounds. */ - if (num >= ARRAY_SIZE(lg->arch.idt)) - kill_guest(lg, "Setting idt entry %u", num); + if (num >= ARRAY_SIZE(cpu->arch.idt)) + kill_guest(cpu, "Setting idt entry %u", num); else - set_trap(lg, &lg->arch.idt[num], num, lo, hi); + set_trap(cpu, &cpu->arch.idt[num], num, lo, hi); } /* The default entry for each interrupt points into the Switcher routines which @@ -434,14 +435,14 @@ void setup_default_idt_entries(struct lguest_ro_state *state, /*H:240 We don't use the IDT entries in the "struct lguest" directly, instead * we copy them into the IDT which we've set up for Guests on this CPU, just * before we run the Guest. This routine does that copy. */ -void copy_traps(const struct lguest *lg, struct desc_struct *idt, +void copy_traps(const struct lg_cpu *cpu, struct desc_struct *idt, const unsigned long *def) { unsigned int i; /* We can simply copy the direct traps, otherwise we use the default * ones in the Switcher: they will return to the Host. */ - for (i = 0; i < ARRAY_SIZE(lg->arch.idt); i++) { + for (i = 0; i < ARRAY_SIZE(cpu->arch.idt); i++) { /* If no Guest can ever override this trap, leave it alone. */ if (!direct_trap(i)) continue; @@ -450,8 +451,8 @@ void copy_traps(const struct lguest *lg, struct desc_struct *idt, * Interrupt gates (type 14) disable interrupts as they are * entered, which we never let the Guest do. Not present * entries (type 0x0) also can't go direct, of course. */ - if (idt_type(lg->arch.idt[i].a, lg->arch.idt[i].b) == 0xF) - idt[i] = lg->arch.idt[i]; + if (idt_type(cpu->arch.idt[i].a, cpu->arch.idt[i].b) == 0xF) + idt[i] = cpu->arch.idt[i]; else /* Reset it to the default. */ default_idt_entry(&idt[i], i, def[i]); @@ -470,13 +471,13 @@ void copy_traps(const struct lguest *lg, struct desc_struct *idt, * infrastructure to set a callback at that time. * * 0 means "turn off the clock". */ -void guest_set_clockevent(struct lguest *lg, unsigned long delta) +void guest_set_clockevent(struct lg_cpu *cpu, unsigned long delta) { ktime_t expires; if (unlikely(delta == 0)) { /* Clock event device is shutting down. */ - hrtimer_cancel(&lg->hrt); + hrtimer_cancel(&cpu->hrt); return; } @@ -484,25 +485,25 @@ void guest_set_clockevent(struct lguest *lg, unsigned long delta) * all the time between now and the timer interrupt it asked for. This * is almost always the right thing to do. */ expires = ktime_add_ns(ktime_get_real(), delta); - hrtimer_start(&lg->hrt, expires, HRTIMER_MODE_ABS); + hrtimer_start(&cpu->hrt, expires, HRTIMER_MODE_ABS); } /* This is the function called when the Guest's timer expires. */ static enum hrtimer_restart clockdev_fn(struct hrtimer *timer) { - struct lguest *lg = container_of(timer, struct lguest, hrt); + struct lg_cpu *cpu = container_of(timer, struct lg_cpu, hrt); /* Remember the first interrupt is the timer interrupt. */ - set_bit(0, lg->irqs_pending); + set_bit(0, cpu->irqs_pending); /* If the Guest is actually stopped, we need to wake it up. */ - if (lg->halted) - wake_up_process(lg->tsk); + if (cpu->halted) + wake_up_process(cpu->tsk); return HRTIMER_NORESTART; } /* This sets up the timer for this Guest. */ -void init_clockdev(struct lguest *lg) +void init_clockdev(struct lg_cpu *cpu) { - hrtimer_init(&lg->hrt, CLOCK_REALTIME, HRTIMER_MODE_ABS); - lg->hrt.function = clockdev_fn; + hrtimer_init(&cpu->hrt, CLOCK_REALTIME, HRTIMER_MODE_ABS); + cpu->hrt.function = clockdev_fn; } diff --git a/drivers/lguest/lg.h b/drivers/lguest/lg.h index 86924891b5eb..2337e1a06f02 100644 --- a/drivers/lguest/lg.h +++ b/drivers/lguest/lg.h @@ -8,6 +8,7 @@ #include <linux/lguest.h> #include <linux/lguest_launcher.h> #include <linux/wait.h> +#include <linux/hrtimer.h> #include <linux/err.h> #include <asm/semaphore.h> @@ -38,58 +39,72 @@ struct lguest_pages #define CHANGED_GDT_TLS 4 /* Actually a subset of CHANGED_GDT */ #define CHANGED_ALL 3 -/* The private info the thread maintains about the guest. */ -struct lguest -{ - /* At end of a page shared mapped over lguest_pages in guest. */ - unsigned long regs_page; - struct lguest_regs *regs; - struct lguest_data __user *lguest_data; +struct lguest; + +struct lg_cpu { + unsigned int id; + struct lguest *lg; struct task_struct *tsk; struct mm_struct *mm; /* == tsk->mm, but that becomes NULL on exit */ - u32 pfn_limit; - /* This provides the offset to the base of guest-physical - * memory in the Launcher. */ - void __user *mem_base; - unsigned long kernel_address; + u32 cr2; - int halted; int ts; - u32 next_hcall; u32 esp1; u8 ss1; + /* Bitmap of what has changed: see CHANGED_* above. */ + int changed; + + unsigned long pending_notify; /* pfn from LHCALL_NOTIFY */ + + /* At end of a page shared mapped over lguest_pages in guest. */ + unsigned long regs_page; + struct lguest_regs *regs; + + struct lguest_pages *last_pages; + + int cpu_pgd; /* which pgd this cpu is currently using */ + /* If a hypercall was asked for, this points to the arguments. */ struct hcall_args *hcall; + u32 next_hcall; + + /* Virtual clock device */ + struct hrtimer hrt; /* Do we need to stop what we're doing and return to userspace? */ int break_out; wait_queue_head_t break_wq; + int halted; - /* Bitmap of what has changed: see CHANGED_* above. */ - int changed; - struct lguest_pages *last_pages; + /* Pending virtual interrupts */ + DECLARE_BITMAP(irqs_pending, LGUEST_IRQS); + + struct lg_cpu_arch arch; +}; + +/* The private info the thread maintains about the guest. */ +struct lguest +{ + struct lguest_data __user *lguest_data; + struct lg_cpu cpus[NR_CPUS]; + unsigned int nr_cpus; + + u32 pfn_limit; + /* This provides the offset to the base of guest-physical + * memory in the Launcher. */ + void __user *mem_base; + unsigned long kernel_address; - /* We keep a small number of these. */ - u32 pgdidx; struct pgdir pgdirs[4]; unsigned long noirq_start, noirq_end; - unsigned long pending_notify; /* pfn from LHCALL_NOTIFY */ unsigned int stack_pages; u32 tsc_khz; /* Dead? */ const char *dead; - - struct lguest_arch arch; - - /* Virtual clock device */ - struct hrtimer hrt; - - /* Pending virtual interrupts */ - DECLARE_BITMAP(irqs_pending, LGUEST_IRQS); }; extern struct mutex lguest_lock; @@ -97,26 +112,26 @@ extern struct mutex lguest_lock; /* core.c: */ int lguest_address_ok(const struct lguest *lg, unsigned long addr, unsigned long len); -void __lgread(struct lguest *, void *, unsigned long, unsigned); -void __lgwrite(struct lguest *, unsigned long, const void *, unsigned); +void __lgread(struct lg_cpu *, void *, unsigned long, unsigned); +void __lgwrite(struct lg_cpu *, unsigned long, const void *, unsigned); /*H:035 Using memory-copy operations like that is usually inconvient, so we * have the following helper macros which read and write a specific type (often * an unsigned long). * * This reads into a variable of the given type then returns that. */ -#define lgread(lg, addr, type) \ - ({ type _v; __lgread((lg), &_v, (addr), sizeof(_v)); _v; }) +#define lgread(cpu, addr, type) \ + ({ type _v; __lgread((cpu), &_v, (addr), sizeof(_v)); _v; }) /* This checks that the variable is of the given type, then writes it out. */ -#define lgwrite(lg, addr, type, val) \ +#define lgwrite(cpu, addr, type, val) \ do { \ typecheck(type, val); \ - __lgwrite((lg), (addr), &(val), sizeof(val)); \ + __lgwrite((cpu), (addr), &(val), sizeof(val)); \ } while(0) /* (end of memory access helper routines) :*/ -int run_guest(struct lguest *lg, unsigned long __user *user); +int run_guest(struct lg_cpu *cpu, unsigned long __user *user); /* Helper macros to obtain the first 12 or the last 20 bits, this is only the * first step in the migration to the kernel types. pte_pfn is already defined @@ -126,52 +141,53 @@ int run_guest(struct lguest *lg, unsigned long __user *user); #define pgd_pfn(x) (pgd_val(x) >> PAGE_SHIFT) /* interrupts_and_traps.c: */ -void maybe_do_interrupt(struct lguest *lg); -int deliver_trap(struct lguest *lg, unsigned int num); -void load_guest_idt_entry(struct lguest *lg, unsigned int i, u32 low, u32 hi); -void guest_set_stack(struct lguest *lg, u32 seg, u32 esp, unsigned int pages); -void pin_stack_pages(struct lguest *lg); +void maybe_do_interrupt(struct lg_cpu *cpu); +int deliver_trap(struct lg_cpu *cpu, unsigned int num); +void load_guest_idt_entry(struct lg_cpu *cpu, unsigned int i, + u32 low, u32 hi); +void guest_set_stack(struct lg_cpu *cpu, u32 seg, u32 esp, unsigned int pages); +void pin_stack_pages(struct lg_cpu *cpu); void setup_default_idt_entries(struct lguest_ro_state *state, const unsigned long *def); -void copy_traps(const struct lguest *lg, struct desc_struct *idt, +void copy_traps(const struct lg_cpu *cpu, struct desc_struct *idt, const unsigned long *def); -void guest_set_clockevent(struct lguest *lg, unsigned long delta); -void init_clockdev(struct lguest *lg); +void guest_set_clockevent(struct lg_cpu *cpu, unsigned long delta); +void init_clockdev(struct lg_cpu *cpu); bool check_syscall_vector(struct lguest *lg); int init_interrupts(void); void free_interrupts(void); /* segments.c: */ void setup_default_gdt_entries(struct lguest_ro_state *state); -void setup_guest_gdt(struct lguest *lg); -void load_guest_gdt(struct lguest *lg, unsigned long table, u32 num); -void guest_load_tls(struct lguest *lg, unsigned long tls_array); -void copy_gdt(const struct lguest *lg, struct desc_struct *gdt); -void copy_gdt_tls(const struct lguest *lg, struct desc_struct *gdt); +void setup_guest_gdt(struct lg_cpu *cpu); +void load_guest_gdt(struct lg_cpu *cpu, unsigned long table, u32 num); +void guest_load_tls(struct lg_cpu *cpu, unsigned long tls_array); +void copy_gdt(const struct lg_cpu *cpu, struct desc_struct *gdt); +void copy_gdt_tls(const struct lg_cpu *cpu, struct desc_struct *gdt); /* page_tables.c: */ int init_guest_pagetable(struct lguest *lg, unsigned long pgtable); void free_guest_pagetable(struct lguest *lg); -void guest_new_pagetable(struct lguest *lg, unsigned long pgtable); +void guest_new_pagetable(struct lg_cpu *cpu, unsigned long pgtable); void guest_set_pmd(struct lguest *lg, unsigned long gpgdir, u32 i); -void guest_pagetable_clear_all(struct lguest *lg); -void guest_pagetable_flush_user(struct lguest *lg); -void guest_set_pte(struct lguest *lg, unsigned long gpgdir, +void guest_pagetable_clear_all(struct lg_cpu *cpu); +void guest_pagetable_flush_user(struct lg_cpu *cpu); +void guest_set_pte(struct lg_cpu *cpu, unsigned long gpgdir, unsigned long vaddr, pte_t val); -void map_switcher_in_guest(struct lguest *lg, struct lguest_pages *pages); -int demand_page(struct lguest *info, unsigned long cr2, int errcode); -void pin_page(struct lguest *lg, unsigned long vaddr); -unsigned long guest_pa(struct lguest *lg, unsigned long vaddr); -void page_table_guest_data_init(struct lguest *lg); +void map_switcher_in_guest(struct lg_cpu *cpu, struct lguest_pages *pages); +int demand_page(struct lg_cpu *cpu, unsigned long cr2, int errcode); +void pin_page(struct lg_cpu *cpu, unsigned long vaddr); +unsigned long guest_pa(struct lg_cpu *cpu, unsigned long vaddr); +void page_table_guest_data_init(struct lg_cpu *cpu); /* <arch>/core.c: */ void lguest_arch_host_init(void); void lguest_arch_host_fini(void); -void lguest_arch_run_guest(struct lguest *lg); -void lguest_arch_handle_trap(struct lguest *lg); -int lguest_arch_init_hypercalls(struct lguest *lg); -int lguest_arch_do_hcall(struct lguest *lg, struct hcall_args *args); -void lguest_arch_setup_regs(struct lguest *lg, unsigned long start); +void lguest_arch_run_guest(struct lg_cpu *cpu); +void lguest_arch_handle_trap(struct lg_cpu *cpu); +int lguest_arch_init_hypercalls(struct lg_cpu *cpu); +int lguest_arch_do_hcall(struct lg_cpu *cpu, struct hcall_args *args); +void lguest_arch_setup_regs(struct lg_cpu *cpu, unsigned long start); /* <arch>/switcher.S: */ extern char start_switcher_text[], end_switcher_text[], switch_to_guest[]; @@ -181,8 +197,8 @@ int lguest_device_init(void); void lguest_device_remove(void); /* hypercalls.c: */ -void do_hypercalls(struct lguest *lg); -void write_timestamp(struct lguest *lg); +void do_hypercalls(struct lg_cpu *cpu); +void write_timestamp(struct lg_cpu *cpu); /*L:035 * Let's step aside for the moment, to study one important routine that's used @@ -208,12 +224,12 @@ void write_timestamp(struct lguest *lg); * Like any macro which uses an "if", it is safely wrapped in a run-once "do { * } while(0)". */ -#define kill_guest(lg, fmt...) \ +#define kill_guest(cpu, fmt...) \ do { \ - if (!(lg)->dead) { \ - (lg)->dead = kasprintf(GFP_ATOMIC, fmt); \ - if (!(lg)->dead) \ - (lg)->dead = ERR_PTR(-ENOMEM); \ + if (!(cpu)->lg->dead) { \ + (cpu)->lg->dead = kasprintf(GFP_ATOMIC, fmt); \ + if (!(cpu)->lg->dead) \ + (cpu)->lg->dead = ERR_PTR(-ENOMEM); \ } \ } while(0) /* (End of aside) :*/ diff --git a/drivers/lguest/lguest_user.c b/drivers/lguest/lguest_user.c index 3b92a61ba8d2..85d42d3d01a9 100644 --- a/drivers/lguest/lguest_user.c +++ b/drivers/lguest/lguest_user.c @@ -6,6 +6,7 @@ #include <linux/uaccess.h> #include <linux/miscdevice.h> #include <linux/fs.h> +#include <linux/sched.h> #include "lg.h" /*L:055 When something happens, the Waker process needs a way to stop the @@ -13,7 +14,7 @@ * LHREQ_BREAK and the value "1" to /dev/lguest to do this. Once the Launcher * has done whatever needs attention, it writes LHREQ_BREAK and "0" to release * the Waker. */ -static int break_guest_out(struct lguest *lg, const unsigned long __user *input) +static int break_guest_out(struct lg_cpu *cpu, const unsigned long __user*input) { unsigned long on; @@ -22,21 +23,21 @@ static int break_guest_out(struct lguest *lg, const unsigned long __user *input) return -EFAULT; if (on) { - lg->break_out = 1; + cpu->break_out = 1; /* Pop it out of the Guest (may be running on different CPU) */ - wake_up_process(lg->tsk); + wake_up_process(cpu->tsk); /* Wait for them to reset it */ - return wait_event_interruptible(lg->break_wq, !lg->break_out); + return wait_event_interruptible(cpu->break_wq, !cpu->break_out); } else { - lg->break_out = 0; - wake_up(&lg->break_wq); + cpu->break_out = 0; + wake_up(&cpu->break_wq); return 0; } } /*L:050 Sending an interrupt is done by writing LHREQ_IRQ and an interrupt * number to /dev/lguest. */ -static int user_send_irq(struct lguest *lg, const unsigned long __user *input) +static int user_send_irq(struct lg_cpu *cpu, const unsigned long __user *input) { unsigned long irq; @@ -46,7 +47,7 @@ static int user_send_irq(struct lguest *lg, const unsigned long __user *input) return -EINVAL; /* Next time the Guest runs, the core code will see if it can deliver * this interrupt. */ - set_bit(irq, lg->irqs_pending); + set_bit(irq, cpu->irqs_pending); return 0; } @@ -55,13 +56,21 @@ static int user_send_irq(struct lguest *lg, const unsigned long __user *input) static ssize_t read(struct file *file, char __user *user, size_t size,loff_t*o) { struct lguest *lg = file->private_data; + struct lg_cpu *cpu; + unsigned int cpu_id = *o; /* You must write LHREQ_INITIALIZE first! */ if (!lg) return -EINVAL; + /* Watch out for arbitrary vcpu indexes! */ + if (cpu_id >= lg->nr_cpus) + return -EINVAL; + + cpu = &lg->cpus[cpu_id]; + /* If you're not the task which owns the Guest, go away. */ - if (current != lg->tsk) + if (current != cpu->tsk) return -EPERM; /* If the guest is already dead, we indicate why */ @@ -81,11 +90,53 @@ static ssize_t read(struct file *file, char __user *user, size_t size,loff_t*o) /* If we returned from read() last time because the Guest notified, * clear the flag. */ - if (lg->pending_notify) - lg->pending_notify = 0; + if (cpu->pending_notify) + cpu->pending_notify = 0; /* Run the Guest until something interesting happens. */ - return run_guest(lg, (unsigned long __user *)user); + return run_guest(cpu, (unsigned long __user *)user); +} + +static int lg_cpu_start(struct lg_cpu *cpu, unsigned id, unsigned long start_ip) +{ + if (id >= NR_CPUS) + return -EINVAL; + + cpu->id = id; + cpu->lg = container_of((cpu - id), struct lguest, cpus[0]); + cpu->lg->nr_cpus++; + init_clockdev(cpu); + + /* We need a complete page for the Guest registers: they are accessible + * to the Guest and we can only grant it access to whole pages. */ + cpu->regs_page = get_zeroed_page(GFP_KERNEL); + if (!cpu->regs_page) + return -ENOMEM; + + /* We actually put the registers at the bottom of the page. */ + cpu->regs = (void *)cpu->regs_page + PAGE_SIZE - sizeof(*cpu->regs); + + /* Now we initialize the Guest's registers, handing it the start + * address. */ + lguest_arch_setup_regs(cpu, start_ip); + + /* Initialize the queue for the waker to wait on */ + init_waitqueue_head(&cpu->break_wq); + + /* We keep a pointer to the Launcher task (ie. current task) for when + * other Guests want to wake this one (inter-Guest I/O). */ + cpu->tsk = current; + + /* We need to keep a pointer to the Launcher's memory map, because if + * the Launcher dies we need to clean it up. If we don't keep a + * reference, it is destroyed before close() is called. */ + cpu->mm = get_task_mm(cpu->tsk); + + /* We remember which CPU's pages this Guest used last, for optimization + * when the same Guest runs on the same CPU twice. */ + cpu->last_pages = NULL; + + return 0; } /*L:020 The initialization write supplies 4 pointer sized (32 or 64 bit) @@ -134,15 +185,10 @@ static int initialize(struct file *file, const unsigned long __user *input) lg->mem_base = (void __user *)(long)args[0]; lg->pfn_limit = args[1]; - /* We need a complete page for the Guest registers: they are accessible - * to the Guest and we can only grant it access to whole pages. */ - lg->regs_page = get_zeroed_page(GFP_KERNEL); - if (!lg->regs_page) { - err = -ENOMEM; + /* This is the first cpu */ + err = lg_cpu_start(&lg->cpus[0], 0, args[3]); + if (err) goto release_guest; - } - /* We actually put the registers at the bottom of the page. */ - lg->regs = (void *)lg->regs_page + PAGE_SIZE - sizeof(*lg->regs); /* Initialize the Guest's shadow page tables, using the toplevel * address the Launcher gave us. This allocates memory, so can @@ -151,28 +197,6 @@ static int initialize(struct file *file, const unsigned long __user *input) if (err) goto free_regs; - /* Now we initialize the Guest's registers, handing it the start - * address. */ - lguest_arch_setup_regs(lg, args[3]); - - /* The timer for lguest's clock needs initialization. */ - init_clockdev(lg); - - /* We keep a pointer to the Launcher task (ie. current task) for when - * other Guests want to wake this one (inter-Guest I/O). */ - lg->tsk = current; - /* We need to keep a pointer to the Launcher's memory map, because if - * the Launcher dies we need to clean it up. If we don't keep a - * reference, it is destroyed before close() is called. */ - lg->mm = get_task_mm(lg->tsk); - - /* Initialize the queue for the waker to wait on */ - init_waitqueue_head(&lg->break_wq); - - /* We remember which CPU's pages this Guest used last, for optimization - * when the same Guest runs on the same CPU twice. */ - lg->last_pages = NULL; - /* We keep our "struct lguest" in the file's private_data. */ file->private_data = lg; @@ -182,7 +206,8 @@ static int initialize(struct file *file, const unsigned long __user *input) return sizeof(args); free_regs: - free_page(lg->regs_page); + /* FIXME: This should be in free_vcpu */ + free_page(lg->cpus[0].regs_page); release_guest: kfree(lg); unlock: @@ -202,30 +227,37 @@ static ssize_t write(struct file *file, const char __user *in, struct lguest *lg = file->private_data; const unsigned long __user *input = (const unsigned long __user *)in; unsigned long req; + struct lg_cpu *uninitialized_var(cpu); + unsigned int cpu_id = *off; if (get_user(req, input) != 0) return -EFAULT; input++; /* If you haven't initialized, you must do that first. */ - if (req != LHREQ_INITIALIZE && !lg) - return -EINVAL; + if (req != LHREQ_INITIALIZE) { + if (!lg || (cpu_id >= lg->nr_cpus)) + return -EINVAL; + cpu = &lg->cpus[cpu_id]; + if (!cpu) + return -EINVAL; + } /* Once the Guest is dead, all you can do is read() why it died. */ if (lg && lg->dead) return -ENOENT; /* If you're not the task which owns the Guest, you can only break */ - if (lg && current != lg->tsk && req != LHREQ_BREAK) + if (lg && current != cpu->tsk && req != LHREQ_BREAK) return -EPERM; switch (req) { case LHREQ_INITIALIZE: return initialize(file, input); case LHREQ_IRQ: - return user_send_irq(lg, input); + return user_send_irq(cpu, input); case LHREQ_BREAK: - return break_guest_out(lg, input); + return break_guest_out(cpu, input); default: return -EINVAL; } @@ -241,6 +273,7 @@ static ssize_t write(struct file *file, const char __user *in, static int close(struct inode *inode, struct file *file) { struct lguest *lg = file->private_data; + unsigned int i; /* If we never successfully initialized, there's nothing to clean up */ if (!lg) @@ -249,19 +282,23 @@ static int close(struct inode *inode, struct file *file) /* We need the big lock, to protect from inter-guest I/O and other * Launchers initializing guests. */ mutex_lock(&lguest_lock); - /* Cancels the hrtimer set via LHCALL_SET_CLOCKEVENT. */ - hrtimer_cancel(&lg->hrt); + /* Free up the shadow page tables for the Guest. */ free_guest_pagetable(lg); - /* Now all the memory cleanups are done, it's safe to release the - * Launcher's memory management structure. */ - mmput(lg->mm); + + for (i = 0; i < lg->nr_cpus; i++) { + /* Cancels the hrtimer set via LHCALL_SET_CLOCKEVENT. */ + hrtimer_cancel(&lg->cpus[i].hrt); + /* We can free up the register page we allocated. */ + free_page(lg->cpus[i].regs_page); + /* Now all the memory cleanups are done, it's safe to release + * the Launcher's memory management structure. */ + mmput(lg->cpus[i].mm); + } /* If lg->dead doesn't contain an error code it will be NULL or a * kmalloc()ed string, either of which is ok to hand to kfree(). */ if (!IS_ERR(lg->dead)) kfree(lg->dead); - /* We can free up the register page we allocated. */ - free_page(lg->regs_page); /* We clear the entire structure, which also marks it as free for the * next user. */ memset(lg, 0, sizeof(*lg)); diff --git a/drivers/lguest/page_tables.c b/drivers/lguest/page_tables.c index fffabb327157..74b4cf2a6c41 100644 --- a/drivers/lguest/page_tables.c +++ b/drivers/lguest/page_tables.c @@ -68,23 +68,23 @@ static DEFINE_PER_CPU(pte_t *, switcher_pte_pages); * page directory entry (PGD) for that address. Since we keep track of several * page tables, the "i" argument tells us which one we're interested in (it's * usually the current one). */ -static pgd_t *spgd_addr(struct lguest *lg, u32 i, unsigned long vaddr) +static pgd_t *spgd_addr(struct lg_cpu *cpu, u32 i, unsigned long vaddr) { unsigned int index = pgd_index(vaddr); /* We kill any Guest trying to touch the Switcher addresses. */ if (index >= SWITCHER_PGD_INDEX) { - kill_guest(lg, "attempt to access switcher pages"); + kill_guest(cpu, "attempt to access switcher pages"); index = 0; } /* Return a pointer index'th pgd entry for the i'th page table. */ - return &lg->pgdirs[i].pgdir[index]; + return &cpu->lg->pgdirs[i].pgdir[index]; } /* This routine then takes the page directory entry returned above, which * contains the address of the page table entry (PTE) page. It then returns a * pointer to the PTE entry for the given address. */ -static pte_t *spte_addr(struct lguest *lg, pgd_t spgd, unsigned long vaddr) +static pte_t *spte_addr(pgd_t spgd, unsigned long vaddr) { pte_t *page = __va(pgd_pfn(spgd) << PAGE_SHIFT); /* You should never call this if the PGD entry wasn't valid */ @@ -94,14 +94,13 @@ static pte_t *spte_addr(struct lguest *lg, pgd_t spgd, unsigned long vaddr) /* These two functions just like the above two, except they access the Guest * page tables. Hence they return a Guest address. */ -static unsigned long gpgd_addr(struct lguest *lg, unsigned long vaddr) +static unsigned long gpgd_addr(struct lg_cpu *cpu, unsigned long vaddr) { unsigned int index = vaddr >> (PGDIR_SHIFT); - return lg->pgdirs[lg->pgdidx].gpgdir + index * sizeof(pgd_t); + return cpu->lg->pgdirs[cpu->cpu_pgd].gpgdir + index * sizeof(pgd_t); } -static unsigned long gpte_addr(struct lguest *lg, - pgd_t gpgd, unsigned long vaddr) +static unsigned long gpte_addr(pgd_t gpgd, unsigned long vaddr) { unsigned long gpage = pgd_pfn(gpgd) << PAGE_SHIFT; BUG_ON(!(pgd_flags(gpgd) & _PAGE_PRESENT)); @@ -138,7 +137,7 @@ static unsigned long get_pfn(unsigned long virtpfn, int write) * entry can be a little tricky. The flags are (almost) the same, but the * Guest PTE contains a virtual page number: the CPU needs the real page * number. */ -static pte_t gpte_to_spte(struct lguest *lg, pte_t gpte, int write) +static pte_t gpte_to_spte(struct lg_cpu *cpu, pte_t gpte, int write) { unsigned long pfn, base, flags; @@ -149,7 +148,7 @@ static pte_t gpte_to_spte(struct lguest *lg, pte_t gpte, int write) flags = (pte_flags(gpte) & ~_PAGE_GLOBAL); /* The Guest's pages are offset inside the Launcher. */ - base = (unsigned long)lg->mem_base / PAGE_SIZE; + base = (unsigned long)cpu->lg->mem_base / PAGE_SIZE; /* We need a temporary "unsigned long" variable to hold the answer from * get_pfn(), because it returns 0xFFFFFFFF on failure, which wouldn't @@ -157,7 +156,7 @@ static pte_t gpte_to_spte(struct lguest *lg, pte_t gpte, int write) * page, given the virtual number. */ pfn = get_pfn(base + pte_pfn(gpte), write); if (pfn == -1UL) { - kill_guest(lg, "failed to get page %lu", pte_pfn(gpte)); + kill_guest(cpu, "failed to get page %lu", pte_pfn(gpte)); /* When we destroy the Guest, we'll go through the shadow page * tables and release_pte() them. Make sure we don't think * this one is valid! */ @@ -177,17 +176,18 @@ static void release_pte(pte_t pte) } /*:*/ -static void check_gpte(struct lguest *lg, pte_t gpte) +static void check_gpte(struct lg_cpu *cpu, pte_t gpte) { if ((pte_flags(gpte) & (_PAGE_PWT|_PAGE_PSE)) - || pte_pfn(gpte) >= lg->pfn_limit) - kill_guest(lg, "bad page table entry"); + || pte_pfn(gpte) >= cpu->lg->pfn_limit) + kill_guest(cpu, "bad page table entry"); } -static void check_gpgd(struct lguest *lg, pgd_t gpgd) +static void check_gpgd(struct lg_cpu *cpu, pgd_t gpgd) { - if ((pgd_flags(gpgd) & ~_PAGE_TABLE) || pgd_pfn(gpgd) >= lg->pfn_limit) - kill_guest(lg, "bad page directory entry"); + if ((pgd_flags(gpgd) & ~_PAGE_TABLE) || + (pgd_pfn(gpgd) >= cpu->lg->pfn_limit)) + kill_guest(cpu, "bad page directory entry"); } /*H:330 @@ -200,7 +200,7 @@ static void check_gpgd(struct lguest *lg, pgd_t gpgd) * * If we fixed up the fault (ie. we mapped the address), this routine returns * true. Otherwise, it was a real fault and we need to tell the Guest. */ -int demand_page(struct lguest *lg, unsigned long vaddr, int errcode) +int demand_page(struct lg_cpu *cpu, unsigned long vaddr, int errcode) { pgd_t gpgd; pgd_t *spgd; @@ -209,24 +209,24 @@ int demand_page(struct lguest *lg, unsigned long vaddr, int errcode) pte_t *spte; /* First step: get the top-level Guest page table entry. */ - gpgd = lgread(lg, gpgd_addr(lg, vaddr), pgd_t); + gpgd = lgread(cpu, gpgd_addr(cpu, vaddr), pgd_t); /* Toplevel not present? We can't map it in. */ if (!(pgd_flags(gpgd) & _PAGE_PRESENT)) return 0; /* Now look at the matching shadow entry. */ - spgd = spgd_addr(lg, lg->pgdidx, vaddr); + spgd = spgd_addr(cpu, cpu->cpu_pgd, vaddr); if (!(pgd_flags(*spgd) & _PAGE_PRESENT)) { /* No shadow entry: allocate a new shadow PTE page. */ unsigned long ptepage = get_zeroed_page(GFP_KERNEL); /* This is not really the Guest's fault, but killing it is * simple for this corner case. */ if (!ptepage) { - kill_guest(lg, "out of memory allocating pte page"); + kill_guest(cpu, "out of memory allocating pte page"); return 0; } /* We check that the Guest pgd is OK. */ - check_gpgd(lg, gpgd); + check_gpgd(cpu, gpgd); /* And we copy the flags to the shadow PGD entry. The page * number in the shadow PGD is the page we just allocated. */ *spgd = __pgd(__pa(ptepage) | pgd_flags(gpgd)); @@ -234,8 +234,8 @@ int demand_page(struct lguest *lg, unsigned long vaddr, int errcode) /* OK, now we look at the lower level in the Guest page table: keep its * address, because we might update it later. */ - gpte_ptr = gpte_addr(lg, gpgd, vaddr); - gpte = lgread(lg, gpte_ptr, pte_t); + gpte_ptr = gpte_addr(gpgd, vaddr); + gpte = lgread(cpu, gpte_ptr, pte_t); /* If this page isn't in the Guest page tables, we can't page it in. */ if (!(pte_flags(gpte) & _PAGE_PRESENT)) @@ -252,7 +252,7 @@ int demand_page(struct lguest *lg, unsigned long vaddr, int errcode) /* Check that the Guest PTE flags are OK, and the page number is below * the pfn_limit (ie. not mapping the Launcher binary). */ - check_gpte(lg, gpte); + check_gpte(cpu, gpte); /* Add the _PAGE_ACCESSED and (for a write) _PAGE_DIRTY flag */ gpte = pte_mkyoung(gpte); @@ -260,7 +260,7 @@ int demand_page(struct lguest *lg, unsigned long vaddr, int errcode) gpte = pte_mkdirty(gpte); /* Get the pointer to the shadow PTE entry we're going to set. */ - spte = spte_addr(lg, *spgd, vaddr); + spte = spte_addr(*spgd, vaddr); /* If there was a valid shadow PTE entry here before, we release it. * This can happen with a write to a previously read-only entry. */ release_pte(*spte); @@ -268,17 +268,17 @@ int demand_page(struct lguest *lg, unsigned long vaddr, int errcode) /* If this is a write, we insist that the Guest page is writable (the * final arg to gpte_to_spte()). */ if (pte_dirty(gpte)) - *spte = gpte_to_spte(lg, gpte, 1); + *spte = gpte_to_spte(cpu, gpte, 1); else /* If this is a read, don't set the "writable" bit in the page * table entry, even if the Guest says it's writable. That way * we will come back here when a write does actually occur, so * we can update the Guest's _PAGE_DIRTY flag. */ - *spte = gpte_to_spte(lg, pte_wrprotect(gpte), 0); + *spte = gpte_to_spte(cpu, pte_wrprotect(gpte), 0); /* Finally, we write the Guest PTE entry back: we've set the * _PAGE_ACCESSED and maybe the _PAGE_DIRTY flags. */ - lgwrite(lg, gpte_ptr, pte_t, gpte); + lgwrite(cpu, gpte_ptr, pte_t, gpte); /* The fault is fixed, the page table is populated, the mapping * manipulated, the result returned and the code complete. A small @@ -297,19 +297,19 @@ int demand_page(struct lguest *lg, unsigned long vaddr, int errcode) * * This is a quick version which answers the question: is this virtual address * mapped by the shadow page tables, and is it writable? */ -static int page_writable(struct lguest *lg, unsigned long vaddr) +static int page_writable(struct lg_cpu *cpu, unsigned long vaddr) { pgd_t *spgd; unsigned long flags; /* Look at the current top level entry: is it present? */ - spgd = spgd_addr(lg, lg->pgdidx, vaddr); + spgd = spgd_addr(cpu, cpu->cpu_pgd, vaddr); if (!(pgd_flags(*spgd) & _PAGE_PRESENT)) return 0; /* Check the flags on the pte entry itself: it must be present and * writable. */ - flags = pte_flags(*(spte_addr(lg, *spgd, vaddr))); + flags = pte_flags(*(spte_addr(*spgd, vaddr))); return (flags & (_PAGE_PRESENT|_PAGE_RW)) == (_PAGE_PRESENT|_PAGE_RW); } @@ -317,10 +317,10 @@ static int page_writable(struct lguest *lg, unsigned long vaddr) /* So, when pin_stack_pages() asks us to pin a page, we check if it's already * in the page tables, and if not, we call demand_page() with error code 2 * (meaning "write"). */ -void pin_page(struct lguest *lg, unsigned long vaddr) +void pin_page(struct lg_cpu *cpu, unsigned long vaddr) { - if (!page_writable(lg, vaddr) && !demand_page(lg, vaddr, 2)) - kill_guest(lg, "bad stack page %#lx", vaddr); + if (!page_writable(cpu, vaddr) && !demand_page(cpu, vaddr, 2)) + kill_guest(cpu, "bad stack page %#lx", vaddr); } /*H:450 If we chase down the release_pgd() code, it looks like this: */ @@ -358,28 +358,28 @@ static void flush_user_mappings(struct lguest *lg, int idx) * * The Guest has a hypercall to throw away the page tables: it's used when a * large number of mappings have been changed. */ -void guest_pagetable_flush_user(struct lguest *lg) +void guest_pagetable_flush_user(struct lg_cpu *cpu) { /* Drop the userspace part of the current page table. */ - flush_user_mappings(lg, lg->pgdidx); + flush_user_mappings(cpu->lg, cpu->cpu_pgd); } /*:*/ /* We walk down the guest page tables to get a guest-physical address */ -unsigned long guest_pa(struct lguest *lg, unsigned long vaddr) +unsigned long guest_pa(struct lg_cpu *cpu, unsigned long vaddr) { pgd_t gpgd; pte_t gpte; /* First step: get the top-level Guest page table entry. */ - gpgd = lgread(lg, gpgd_addr(lg, vaddr), pgd_t); + gpgd = lgread(cpu, gpgd_addr(cpu, vaddr), pgd_t); /* Toplevel not present? We can't map it in. */ if (!(pgd_flags(gpgd) & _PAGE_PRESENT)) - kill_guest(lg, "Bad address %#lx", vaddr); + kill_guest(cpu, "Bad address %#lx", vaddr); - gpte = lgread(lg, gpte_addr(lg, gpgd, vaddr), pte_t); + gpte = lgread(cpu, gpte_addr(gpgd, vaddr), pte_t); if (!(pte_flags(gpte) & _PAGE_PRESENT)) - kill_guest(lg, "Bad address %#lx", vaddr); + kill_guest(cpu, "Bad address %#lx", vaddr); return pte_pfn(gpte) * PAGE_SIZE | (vaddr & ~PAGE_MASK); } @@ -399,7 +399,7 @@ static unsigned int find_pgdir(struct lguest *lg, unsigned long pgtable) /*H:435 And this is us, creating the new page directory. If we really do * allocate a new one (and so the kernel parts are not there), we set * blank_pgdir. */ -static unsigned int new_pgdir(struct lguest *lg, +static unsigned int new_pgdir(struct lg_cpu *cpu, unsigned long gpgdir, int *blank_pgdir) { @@ -407,22 +407,23 @@ static unsigned int new_pgdir(struct lguest *lg, /* We pick one entry at random to throw out. Choosing the Least * Recently Used might be better, but this is easy. */ - next = random32() % ARRAY_SIZE(lg->pgdirs); + next = random32() % ARRAY_SIZE(cpu->lg->pgdirs); /* If it's never been allocated at all before, try now. */ - if (!lg->pgdirs[next].pgdir) { - lg->pgdirs[next].pgdir = (pgd_t *)get_zeroed_page(GFP_KERNEL); + if (!cpu->lg->pgdirs[next].pgdir) { + cpu->lg->pgdirs[next].pgdir = + (pgd_t *)get_zeroed_page(GFP_KERNEL); /* If the allocation fails, just keep using the one we have */ - if (!lg->pgdirs[next].pgdir) - next = lg->pgdidx; + if (!cpu->lg->pgdirs[next].pgdir) + next = cpu->cpu_pgd; else /* This is a blank page, so there are no kernel * mappings: caller must map the stack! */ *blank_pgdir = 1; } /* Record which Guest toplevel this shadows. */ - lg->pgdirs[next].gpgdir = gpgdir; + cpu->lg->pgdirs[next].gpgdir = gpgdir; /* Release all the non-kernel mappings. */ - flush_user_mappings(lg, next); + flush_user_mappings(cpu->lg, next); return next; } @@ -432,21 +433,21 @@ static unsigned int new_pgdir(struct lguest *lg, * Now we've seen all the page table setting and manipulation, let's see what * what happens when the Guest changes page tables (ie. changes the top-level * pgdir). This occurs on almost every context switch. */ -void guest_new_pagetable(struct lguest *lg, unsigned long pgtable) +void guest_new_pagetable(struct lg_cpu *cpu, unsigned long pgtable) { int newpgdir, repin = 0; /* Look to see if we have this one already. */ - newpgdir = find_pgdir(lg, pgtable); + newpgdir = find_pgdir(cpu->lg, pgtable); /* If not, we allocate or mug an existing one: if it's a fresh one, * repin gets set to 1. */ - if (newpgdir == ARRAY_SIZE(lg->pgdirs)) - newpgdir = new_pgdir(lg, pgtable, &repin); + if (newpgdir == ARRAY_SIZE(cpu->lg->pgdirs)) + newpgdir = new_pgdir(cpu, pgtable, &repin); /* Change the current pgd index to the new one. */ - lg->pgdidx = newpgdir; + cpu->cpu_pgd = newpgdir; /* If it was completely blank, we map in the Guest kernel stack */ if (repin) - pin_stack_pages(lg); + pin_stack_pages(cpu); } /*H:470 Finally, a routine which throws away everything: all PGD entries in all @@ -468,11 +469,11 @@ static void release_all_pagetables(struct lguest *lg) * mapping. Since kernel mappings are in every page table, it's easiest to * throw them all away. This traps the Guest in amber for a while as * everything faults back in, but it's rare. */ -void guest_pagetable_clear_all(struct lguest *lg) +void guest_pagetable_clear_all(struct lg_cpu *cpu) { - release_all_pagetables(lg); + release_all_pagetables(cpu->lg); /* We need the Guest kernel stack mapped again. */ - pin_stack_pages(lg); + pin_stack_pages(cpu); } /*:*/ /*M:009 Since we throw away all mappings when a kernel mapping changes, our @@ -497,24 +498,24 @@ void guest_pagetable_clear_all(struct lguest *lg) * _PAGE_ACCESSED then we can put a read-only PTE entry in immediately, and if * they set _PAGE_DIRTY then we can put a writable PTE entry in immediately. */ -static void do_set_pte(struct lguest *lg, int idx, +static void do_set_pte(struct lg_cpu *cpu, int idx, unsigned long vaddr, pte_t gpte) { /* Look up the matching shadow page directory entry. */ - pgd_t *spgd = spgd_addr(lg, idx, vaddr); + pgd_t *spgd = spgd_addr(cpu, idx, vaddr); /* If the top level isn't present, there's no entry to update. */ if (pgd_flags(*spgd) & _PAGE_PRESENT) { /* Otherwise, we start by releasing the existing entry. */ - pte_t *spte = spte_addr(lg, *spgd, vaddr); + pte_t *spte = spte_addr(*spgd, vaddr); release_pte(*spte); /* If they're setting this entry as dirty or accessed, we might * as well put that entry they've given us in now. This shaves * 10% off a copy-on-write micro-benchmark. */ if (pte_flags(gpte) & (_PAGE_DIRTY | _PAGE_ACCESSED)) { - check_gpte(lg, gpte); - *spte = gpte_to_spte(lg, gpte, + check_gpte(cpu, gpte); + *spte = gpte_to_spte(cpu, gpte, pte_flags(gpte) & _PAGE_DIRTY); } else /* Otherwise kill it and we can demand_page() it in @@ -533,22 +534,22 @@ static void do_set_pte(struct lguest *lg, int idx, * * The benefit is that when we have to track a new page table, we can copy keep * all the kernel mappings. This speeds up context switch immensely. */ -void guest_set_pte(struct lguest *lg, +void guest_set_pte(struct lg_cpu *cpu, unsigned long gpgdir, unsigned long vaddr, pte_t gpte) { /* Kernel mappings must be changed on all top levels. Slow, but * doesn't happen often. */ - if (vaddr >= lg->kernel_address) { + if (vaddr >= cpu->lg->kernel_address) { unsigned int i; - for (i = 0; i < ARRAY_SIZE(lg->pgdirs); i++) - if (lg->pgdirs[i].pgdir) - do_set_pte(lg, i, vaddr, gpte); + for (i = 0; i < ARRAY_SIZE(cpu->lg->pgdirs); i++) + if (cpu->lg->pgdirs[i].pgdir) + do_set_pte(cpu, i, vaddr, gpte); } else { /* Is this page table one we have a shadow for? */ - int pgdir = find_pgdir(lg, gpgdir); - if (pgdir != ARRAY_SIZE(lg->pgdirs)) + int pgdir = find_pgdir(cpu->lg, gpgdir); + if (pgdir != ARRAY_SIZE(cpu->lg->pgdirs)) /* If so, do the update. */ - do_set_pte(lg, pgdir, vaddr, gpte); + do_set_pte(cpu, pgdir, vaddr, gpte); } } @@ -590,30 +591,32 @@ int init_guest_pagetable(struct lguest *lg, unsigned long pgtable) { /* We start on the first shadow page table, and give it a blank PGD * page. */ - lg->pgdidx = 0; - lg->pgdirs[lg->pgdidx].gpgdir = pgtable; - lg->pgdirs[lg->pgdidx].pgdir = (pgd_t*)get_zeroed_page(GFP_KERNEL); - if (!lg->pgdirs[lg->pgdidx].pgdir) + lg->pgdirs[0].gpgdir = pgtable; + lg->pgdirs[0].pgdir = (pgd_t *)get_zeroed_page(GFP_KERNEL); + if (!lg->pgdirs[0].pgdir) return -ENOMEM; + lg->cpus[0].cpu_pgd = 0; return 0; } /* When the Guest calls LHCALL_LGUEST_INIT we do more setup. */ -void page_table_guest_data_init(struct lguest *lg) +void page_table_guest_data_init(struct lg_cpu *cpu) { /* We get the kernel address: above this is all kernel memory. */ - if (get_user(lg->kernel_address, &lg->lguest_data->kernel_address) + if (get_user(cpu->lg->kernel_address, + &cpu->lg->lguest_data->kernel_address) /* We tell the Guest that it can't use the top 4MB of virtual * addresses used by the Switcher. */ - || put_user(4U*1024*1024, &lg->lguest_data->reserve_mem) - || put_user(lg->pgdirs[lg->pgdidx].gpgdir,&lg->lguest_data->pgdir)) - kill_guest(lg, "bad guest page %p", lg->lguest_data); + || put_user(4U*1024*1024, &cpu->lg->lguest_data->reserve_mem) + || put_user(cpu->lg->pgdirs[0].gpgdir, &cpu->lg->lguest_data->pgdir)) + kill_guest(cpu, "bad guest page %p", cpu->lg->lguest_data); /* In flush_user_mappings() we loop from 0 to * "pgd_index(lg->kernel_address)". This assumes it won't hit the * Switcher mappings, so check that now. */ - if (pgd_index(lg->kernel_address) >= SWITCHER_PGD_INDEX) - kill_guest(lg, "bad kernel address %#lx", lg->kernel_address); + if (pgd_index(cpu->lg->kernel_address) >= SWITCHER_PGD_INDEX) + kill_guest(cpu, "bad kernel address %#lx", + cpu->lg->kernel_address); } /* When a Guest dies, our cleanup is fairly simple. */ @@ -634,17 +637,18 @@ void free_guest_pagetable(struct lguest *lg) * Guest (and not the pages for other CPUs). We have the appropriate PTE pages * for each CPU already set up, we just need to hook them in now we know which * Guest is about to run on this CPU. */ -void map_switcher_in_guest(struct lguest *lg, struct lguest_pages *pages) +void map_switcher_in_guest(struct lg_cpu *cpu, struct lguest_pages *pages) { pte_t *switcher_pte_page = __get_cpu_var(switcher_pte_pages); pgd_t switcher_pgd; pte_t regs_pte; + unsigned long pfn; /* Make the last PGD entry for this Guest point to the Switcher's PTE * page for this CPU (with appropriate flags). */ - switcher_pgd = __pgd(__pa(switcher_pte_page) | _PAGE_KERNEL); + switcher_pgd = __pgd(__pa(switcher_pte_page) | __PAGE_KERNEL); - lg->pgdirs[lg->pgdidx].pgdir[SWITCHER_PGD_INDEX] = switcher_pgd; + cpu->lg->pgdirs[cpu->cpu_pgd].pgdir[SWITCHER_PGD_INDEX] = switcher_pgd; /* We also change the Switcher PTE page. When we're running the Guest, * we want the Guest's "regs" page to appear where the first Switcher @@ -653,7 +657,8 @@ void map_switcher_in_guest(struct lguest *lg, struct lguest_pages *pages) * CPU's "struct lguest_pages": if we make sure the Guest's register * page is already mapped there, we don't have to copy them out * again. */ - regs_pte = pfn_pte (__pa(lg->regs_page) >> PAGE_SHIFT, __pgprot(_PAGE_KERNEL)); + pfn = __pa(cpu->regs_page) >> PAGE_SHIFT; + regs_pte = pfn_pte(pfn, __pgprot(__PAGE_KERNEL)); switcher_pte_page[(unsigned long)pages/PAGE_SIZE%PTRS_PER_PTE] = regs_pte; } /*:*/ diff --git a/drivers/lguest/segments.c b/drivers/lguest/segments.c index 9e189cbec7dd..ec6aa3f1c36b 100644 --- a/drivers/lguest/segments.c +++ b/drivers/lguest/segments.c @@ -58,7 +58,7 @@ static int ignored_gdt(unsigned int num) * Protection Fault in the Switcher when it restores a Guest segment register * which tries to use that entry. Then we kill the Guest for causing such a * mess: the message will be "unhandled trap 256". */ -static void fixup_gdt_table(struct lguest *lg, unsigned start, unsigned end) +static void fixup_gdt_table(struct lg_cpu *cpu, unsigned start, unsigned end) { unsigned int i; @@ -71,14 +71,14 @@ static void fixup_gdt_table(struct lguest *lg, unsigned start, unsigned end) /* Segment descriptors contain a privilege level: the Guest is * sometimes careless and leaves this as 0, even though it's * running at privilege level 1. If so, we fix it here. */ - if ((lg->arch.gdt[i].b & 0x00006000) == 0) - lg->arch.gdt[i].b |= (GUEST_PL << 13); + if ((cpu->arch.gdt[i].b & 0x00006000) == 0) + cpu->arch.gdt[i].b |= (GUEST_PL << 13); /* Each descriptor has an "accessed" bit. If we don't set it * now, the CPU will try to set it when the Guest first loads * that entry into a segment register. But the GDT isn't * writable by the Guest, so bad things can happen. */ - lg->arch.gdt[i].b |= 0x00000100; + cpu->arch.gdt[i].b |= 0x00000100; } } @@ -109,31 +109,31 @@ void setup_default_gdt_entries(struct lguest_ro_state *state) /* This routine sets up the initial Guest GDT for booting. All entries start * as 0 (unusable). */ -void setup_guest_gdt(struct lguest *lg) +void setup_guest_gdt(struct lg_cpu *cpu) { /* Start with full 0-4G segments... */ - lg->arch.gdt[GDT_ENTRY_KERNEL_CS] = FULL_EXEC_SEGMENT; - lg->arch.gdt[GDT_ENTRY_KERNEL_DS] = FULL_SEGMENT; + cpu->arch.gdt[GDT_ENTRY_KERNEL_CS] = FULL_EXEC_SEGMENT; + cpu->arch.gdt[GDT_ENTRY_KERNEL_DS] = FULL_SEGMENT; /* ...except the Guest is allowed to use them, so set the privilege * level appropriately in the flags. */ - lg->arch.gdt[GDT_ENTRY_KERNEL_CS].b |= (GUEST_PL << 13); - lg->arch.gdt[GDT_ENTRY_KERNEL_DS].b |= (GUEST_PL << 13); + cpu->arch.gdt[GDT_ENTRY_KERNEL_CS].b |= (GUEST_PL << 13); + cpu->arch.gdt[GDT_ENTRY_KERNEL_DS].b |= (GUEST_PL << 13); } /*H:650 An optimization of copy_gdt(), for just the three "thead-local storage" * entries. */ -void copy_gdt_tls(const struct lguest *lg, struct desc_struct *gdt) +void copy_gdt_tls(const struct lg_cpu *cpu, struct desc_struct *gdt) { unsigned int i; for (i = GDT_ENTRY_TLS_MIN; i <= GDT_ENTRY_TLS_MAX; i++) - gdt[i] = lg->arch.gdt[i]; + gdt[i] = cpu->arch.gdt[i]; } /*H:640 When the Guest is run on a different CPU, or the GDT entries have * changed, copy_gdt() is called to copy the Guest's GDT entries across to this * CPU's GDT. */ -void copy_gdt(const struct lguest *lg, struct desc_struct *gdt) +void copy_gdt(const struct lg_cpu *cpu, struct desc_struct *gdt) { unsigned int i; @@ -141,38 +141,38 @@ void copy_gdt(const struct lguest *lg, struct desc_struct *gdt) * replaced. See ignored_gdt() above. */ for (i = 0; i < GDT_ENTRIES; i++) if (!ignored_gdt(i)) - gdt[i] = lg->arch.gdt[i]; + gdt[i] = cpu->arch.gdt[i]; } /*H:620 This is where the Guest asks us to load a new GDT (LHCALL_LOAD_GDT). * We copy it from the Guest and tweak the entries. */ -void load_guest_gdt(struct lguest *lg, unsigned long table, u32 num) +void load_guest_gdt(struct lg_cpu *cpu, unsigned long table, u32 num) { /* We assume the Guest has the same number of GDT entries as the * Host, otherwise we'd have to dynamically allocate the Guest GDT. */ - if (num > ARRAY_SIZE(lg->arch.gdt)) - kill_guest(lg, "too many gdt entries %i", num); + if (num > ARRAY_SIZE(cpu->arch.gdt)) + kill_guest(cpu, "too many gdt entries %i", num); /* We read the whole thing in, then fix it up. */ - __lgread(lg, lg->arch.gdt, table, num * sizeof(lg->arch.gdt[0])); - fixup_gdt_table(lg, 0, ARRAY_SIZE(lg->arch.gdt)); + __lgread(cpu, cpu->arch.gdt, table, num * sizeof(cpu->arch.gdt[0])); + fixup_gdt_table(cpu, 0, ARRAY_SIZE(cpu->arch.gdt)); /* Mark that the GDT changed so the core knows it has to copy it again, * even if the Guest is run on the same CPU. */ - lg->changed |= CHANGED_GDT; + cpu->changed |= CHANGED_GDT; } /* This is the fast-track version for just changing the three TLS entries. * Remember that this happens on every context switch, so it's worth * optimizing. But wouldn't it be neater to have a single hypercall to cover * both cases? */ -void guest_load_tls(struct lguest *lg, unsigned long gtls) +void guest_load_tls(struct lg_cpu *cpu, unsigned long gtls) { - struct desc_struct *tls = &lg->arch.gdt[GDT_ENTRY_TLS_MIN]; + struct desc_struct *tls = &cpu->arch.gdt[GDT_ENTRY_TLS_MIN]; - __lgread(lg, tls, gtls, sizeof(*tls)*GDT_ENTRY_TLS_ENTRIES); - fixup_gdt_table(lg, GDT_ENTRY_TLS_MIN, GDT_ENTRY_TLS_MAX+1); + __lgread(cpu, tls, gtls, sizeof(*tls)*GDT_ENTRY_TLS_ENTRIES); + fixup_gdt_table(cpu, GDT_ENTRY_TLS_MIN, GDT_ENTRY_TLS_MAX+1); /* Note that just the TLS entries have changed. */ - lg->changed |= CHANGED_GDT_TLS; + cpu->changed |= CHANGED_GDT_TLS; } /*:*/ diff --git a/drivers/lguest/x86/core.c b/drivers/lguest/x86/core.c index 96d0fd07c57d..61f2f8eb8cad 100644 --- a/drivers/lguest/x86/core.c +++ b/drivers/lguest/x86/core.c @@ -60,7 +60,7 @@ static struct lguest_pages *lguest_pages(unsigned int cpu) (SWITCHER_ADDR + SHARED_SWITCHER_PAGES*PAGE_SIZE))[cpu]); } -static DEFINE_PER_CPU(struct lguest *, last_guest); +static DEFINE_PER_CPU(struct lg_cpu *, last_cpu); /*S:010 * We approach the Switcher. @@ -73,16 +73,16 @@ static DEFINE_PER_CPU(struct lguest *, last_guest); * since it last ran. We saw this set in interrupts_and_traps.c and * segments.c. */ -static void copy_in_guest_info(struct lguest *lg, struct lguest_pages *pages) +static void copy_in_guest_info(struct lg_cpu *cpu, struct lguest_pages *pages) { /* Copying all this data can be quite expensive. We usually run the * same Guest we ran last time (and that Guest hasn't run anywhere else * meanwhile). If that's not the case, we pretend everything in the * Guest has changed. */ - if (__get_cpu_var(last_guest) != lg || lg->last_pages != pages) { - __get_cpu_var(last_guest) = lg; - lg->last_pages = pages; - lg->changed = CHANGED_ALL; + if (__get_cpu_var(last_cpu) != cpu || cpu->last_pages != pages) { + __get_cpu_var(last_cpu) = cpu; + cpu->last_pages = pages; + cpu->changed = CHANGED_ALL; } /* These copies are pretty cheap, so we do them unconditionally: */ @@ -90,42 +90,42 @@ static void copy_in_guest_info(struct lguest *lg, struct lguest_pages *pages) pages->state.host_cr3 = __pa(current->mm->pgd); /* Set up the Guest's page tables to see this CPU's pages (and no * other CPU's pages). */ - map_switcher_in_guest(lg, pages); + map_switcher_in_guest(cpu, pages); /* Set up the two "TSS" members which tell the CPU what stack to use * for traps which do directly into the Guest (ie. traps at privilege * level 1). */ - pages->state.guest_tss.esp1 = lg->esp1; - pages->state.guest_tss.ss1 = lg->ss1; + pages->state.guest_tss.esp1 = cpu->esp1; + pages->state.guest_tss.ss1 = cpu->ss1; /* Copy direct-to-Guest trap entries. */ - if (lg->changed & CHANGED_IDT) - copy_traps(lg, pages->state.guest_idt, default_idt_entries); + if (cpu->changed & CHANGED_IDT) + copy_traps(cpu, pages->state.guest_idt, default_idt_entries); /* Copy all GDT entries which the Guest can change. */ - if (lg->changed & CHANGED_GDT) - copy_gdt(lg, pages->state.guest_gdt); + if (cpu->changed & CHANGED_GDT) + copy_gdt(cpu, pages->state.guest_gdt); /* If only the TLS entries have changed, copy them. */ - else if (lg->changed & CHANGED_GDT_TLS) - copy_gdt_tls(lg, pages->state.guest_gdt); + else if (cpu->changed & CHANGED_GDT_TLS) + copy_gdt_tls(cpu, pages->state.guest_gdt); /* Mark the Guest as unchanged for next time. */ - lg->changed = 0; + cpu->changed = 0; } /* Finally: the code to actually call into the Switcher to run the Guest. */ -static void run_guest_once(struct lguest *lg, struct lguest_pages *pages) +static void run_guest_once(struct lg_cpu *cpu, struct lguest_pages *pages) { /* This is a dummy value we need for GCC's sake. */ unsigned int clobber; /* Copy the guest-specific information into this CPU's "struct * lguest_pages". */ - copy_in_guest_info(lg, pages); + copy_in_guest_info(cpu, pages); /* Set the trap number to 256 (impossible value). If we fault while * switching to the Guest (bad segment registers or bug), this will * cause us to abort the Guest. */ - lg->regs->trapnum = 256; + cpu->regs->trapnum = 256; /* Now: we push the "eflags" register on the stack, then do an "lcall". * This is how we change from using the kernel code segment to using @@ -143,7 +143,7 @@ static void run_guest_once(struct lguest *lg, struct lguest_pages *pages) * 0-th argument above, ie "a"). %ebx contains the * physical address of the Guest's top-level page * directory. */ - : "0"(pages), "1"(__pa(lg->pgdirs[lg->pgdidx].pgdir)) + : "0"(pages), "1"(__pa(cpu->lg->pgdirs[cpu->cpu_pgd].pgdir)) /* We tell gcc that all these registers could change, * which means we don't have to save and restore them in * the Switcher. */ @@ -161,12 +161,12 @@ static void run_guest_once(struct lguest *lg, struct lguest_pages *pages) /*H:040 This is the i386-specific code to setup and run the Guest. Interrupts * are disabled: we own the CPU. */ -void lguest_arch_run_guest(struct lguest *lg) +void lguest_arch_run_guest(struct lg_cpu *cpu) { /* Remember the awfully-named TS bit? If the Guest has asked to set it * we set it now, so we can trap and pass that trap to the Guest if it * uses the FPU. */ - if (lg->ts) + if (cpu->ts) lguest_set_ts(); /* SYSENTER is an optimized way of doing system calls. We can't allow @@ -180,7 +180,7 @@ void lguest_arch_run_guest(struct lguest *lg) /* Now we actually run the Guest. It will return when something * interesting happens, and we can examine its registers to see what it * was doing. */ - run_guest_once(lg, lguest_pages(raw_smp_processor_id())); + run_guest_once(cpu, lguest_pages(raw_smp_processor_id())); /* Note that the "regs" pointer contains two extra entries which are * not really registers: a trap number which says what interrupt or @@ -191,11 +191,11 @@ void lguest_arch_run_guest(struct lguest *lg) * bad virtual address. We have to grab this now, because once we * re-enable interrupts an interrupt could fault and thus overwrite * cr2, or we could even move off to a different CPU. */ - if (lg->regs->trapnum == 14) - lg->arch.last_pagefault = read_cr2(); + if (cpu->regs->trapnum == 14) + cpu->arch.last_pagefault = read_cr2(); /* Similarly, if we took a trap because the Guest used the FPU, * we have to restore the FPU it expects to see. */ - else if (lg->regs->trapnum == 7) + else if (cpu->regs->trapnum == 7) math_state_restore(); /* Restore SYSENTER if it's supposed to be on. */ @@ -214,22 +214,22 @@ void lguest_arch_run_guest(struct lguest *lg) * When the Guest uses one of these instructions, we get a trap (General * Protection Fault) and come here. We see if it's one of those troublesome * instructions and skip over it. We return true if we did. */ -static int emulate_insn(struct lguest *lg) +static int emulate_insn(struct lg_cpu *cpu) { u8 insn; unsigned int insnlen = 0, in = 0, shift = 0; /* The eip contains the *virtual* address of the Guest's instruction: * guest_pa just subtracts the Guest's page_offset. */ - unsigned long physaddr = guest_pa(lg, lg->regs->eip); + unsigned long physaddr = guest_pa(cpu, cpu->regs->eip); /* This must be the Guest kernel trying to do something, not userspace! * The bottom two bits of the CS segment register are the privilege * level. */ - if ((lg->regs->cs & 3) != GUEST_PL) + if ((cpu->regs->cs & 3) != GUEST_PL) return 0; /* Decoding x86 instructions is icky. */ - insn = lgread(lg, physaddr, u8); + insn = lgread(cpu, physaddr, u8); /* 0x66 is an "operand prefix". It means it's using the upper 16 bits of the eax register. */ @@ -237,7 +237,7 @@ static int emulate_insn(struct lguest *lg) shift = 16; /* The instruction is 1 byte so far, read the next byte. */ insnlen = 1; - insn = lgread(lg, physaddr + insnlen, u8); + insn = lgread(cpu, physaddr + insnlen, u8); } /* We can ignore the lower bit for the moment and decode the 4 opcodes @@ -268,26 +268,26 @@ static int emulate_insn(struct lguest *lg) if (in) { /* Lower bit tells is whether it's a 16 or 32 bit access */ if (insn & 0x1) - lg->regs->eax = 0xFFFFFFFF; + cpu->regs->eax = 0xFFFFFFFF; else - lg->regs->eax |= (0xFFFF << shift); + cpu->regs->eax |= (0xFFFF << shift); } /* Finally, we've "done" the instruction, so move past it. */ - lg->regs->eip += insnlen; + cpu->regs->eip += insnlen; /* Success! */ return 1; } /*H:050 Once we've re-enabled interrupts, we look at why the Guest exited. */ -void lguest_arch_handle_trap(struct lguest *lg) +void lguest_arch_handle_trap(struct lg_cpu *cpu) { - switch (lg->regs->trapnum) { + switch (cpu->regs->trapnum) { case 13: /* We've intercepted a General Protection Fault. */ /* Check if this was one of those annoying IN or OUT * instructions which we need to emulate. If so, we just go * back into the Guest after we've done it. */ - if (lg->regs->errcode == 0) { - if (emulate_insn(lg)) + if (cpu->regs->errcode == 0) { + if (emulate_insn(cpu)) return; } break; @@ -301,7 +301,8 @@ void lguest_arch_handle_trap(struct lguest *lg) * * The errcode tells whether this was a read or a write, and * whether kernel or userspace code. */ - if (demand_page(lg, lg->arch.last_pagefault, lg->regs->errcode)) + if (demand_page(cpu, cpu->arch.last_pagefault, + cpu->regs->errcode)) return; /* OK, it's really not there (or not OK): the Guest needs to @@ -311,15 +312,16 @@ void lguest_arch_handle_trap(struct lguest *lg) * Note that if the Guest were really messed up, this could * happen before it's done the LHCALL_LGUEST_INIT hypercall, so * lg->lguest_data could be NULL */ - if (lg->lguest_data && - put_user(lg->arch.last_pagefault, &lg->lguest_data->cr2)) - kill_guest(lg, "Writing cr2"); + if (cpu->lg->lguest_data && + put_user(cpu->arch.last_pagefault, + &cpu->lg->lguest_data->cr2)) + kill_guest(cpu, "Writing cr2"); break; case 7: /* We've intercepted a Device Not Available fault. */ /* If the Guest doesn't want to know, we already restored the * Floating Point Unit, so we just continue without telling * it. */ - if (!lg->ts) + if (!cpu->ts) return; break; case 32 ... 255: @@ -332,19 +334,19 @@ void lguest_arch_handle_trap(struct lguest *lg) case LGUEST_TRAP_ENTRY: /* Our 'struct hcall_args' maps directly over our regs: we set * up the pointer now to indicate a hypercall is pending. */ - lg->hcall = (struct hcall_args *)lg->regs; + cpu->hcall = (struct hcall_args *)cpu->regs; return; } /* We didn't handle the trap, so it needs to go to the Guest. */ - if (!deliver_trap(lg, lg->regs->trapnum)) + if (!deliver_trap(cpu, cpu->regs->trapnum)) /* If the Guest doesn't have a handler (either it hasn't * registered any yet, or it's one of the faults we don't let * it handle), it dies with a cryptic error message. */ - kill_guest(lg, "unhandled trap %li at %#lx (%#lx)", - lg->regs->trapnum, lg->regs->eip, - lg->regs->trapnum == 14 ? lg->arch.last_pagefault - : lg->regs->errcode); + kill_guest(cpu, "unhandled trap %li at %#lx (%#lx)", + cpu->regs->trapnum, cpu->regs->eip, + cpu->regs->trapnum == 14 ? cpu->arch.last_pagefault + : cpu->regs->errcode); } /* Now we can look at each of the routines this calls, in increasing order of @@ -416,7 +418,7 @@ void __init lguest_arch_host_init(void) /* We know where we want the stack to be when the Guest enters * the switcher: in pages->regs. The stack grows upwards, so * we start it at the end of that structure. */ - state->guest_tss.esp0 = (long)(&pages->regs + 1); + state->guest_tss.sp0 = (long)(&pages->regs + 1); /* And this is the GDT entry to use for the stack: we keep a * couple of special LGUEST entries. */ state->guest_tss.ss0 = LGUEST_DS; @@ -487,17 +489,17 @@ void __exit lguest_arch_host_fini(void) /*H:122 The i386-specific hypercalls simply farm out to the right functions. */ -int lguest_arch_do_hcall(struct lguest *lg, struct hcall_args *args) +int lguest_arch_do_hcall(struct lg_cpu *cpu, struct hcall_args *args) { switch (args->arg0) { case LHCALL_LOAD_GDT: - load_guest_gdt(lg, args->arg1, args->arg2); + load_guest_gdt(cpu, args->arg1, args->arg2); break; case LHCALL_LOAD_IDT_ENTRY: - load_guest_idt_entry(lg, args->arg1, args->arg2, args->arg3); + load_guest_idt_entry(cpu, args->arg1, args->arg2, args->arg3); break; case LHCALL_LOAD_TLS: - guest_load_tls(lg, args->arg1); + guest_load_tls(cpu, args->arg1); break; default: /* Bad Guest. Bad! */ @@ -507,13 +509,14 @@ int lguest_arch_do_hcall(struct lguest *lg, struct hcall_args *args) } /*H:126 i386-specific hypercall initialization: */ -int lguest_arch_init_hypercalls(struct lguest *lg) +int lguest_arch_init_hypercalls(struct lg_cpu *cpu) { u32 tsc_speed; /* The pointer to the Guest's "struct lguest_data" is the only * argument. We check that address now. */ - if (!lguest_address_ok(lg, lg->hcall->arg1, sizeof(*lg->lguest_data))) + if (!lguest_address_ok(cpu->lg, cpu->hcall->arg1, + sizeof(*cpu->lg->lguest_data))) return -EFAULT; /* Having checked it, we simply set lg->lguest_data to point straight @@ -521,7 +524,7 @@ int lguest_arch_init_hypercalls(struct lguest *lg) * copy_to_user/from_user from now on, instead of lgread/write. I put * this in to show that I'm not immune to writing stupid * optimizations. */ - lg->lguest_data = lg->mem_base + lg->hcall->arg1; + cpu->lg->lguest_data = cpu->lg->mem_base + cpu->hcall->arg1; /* We insist that the Time Stamp Counter exist and doesn't change with * cpu frequency. Some devious chip manufacturers decided that TSC @@ -534,12 +537,12 @@ int lguest_arch_init_hypercalls(struct lguest *lg) tsc_speed = tsc_khz; else tsc_speed = 0; - if (put_user(tsc_speed, &lg->lguest_data->tsc_khz)) + if (put_user(tsc_speed, &cpu->lg->lguest_data->tsc_khz)) return -EFAULT; /* The interrupt code might not like the system call vector. */ - if (!check_syscall_vector(lg)) - kill_guest(lg, "bad syscall vector"); + if (!check_syscall_vector(cpu->lg)) + kill_guest(cpu, "bad syscall vector"); return 0; } @@ -548,9 +551,9 @@ int lguest_arch_init_hypercalls(struct lguest *lg) * * Most of the Guest's registers are left alone: we used get_zeroed_page() to * allocate the structure, so they will be 0. */ -void lguest_arch_setup_regs(struct lguest *lg, unsigned long start) +void lguest_arch_setup_regs(struct lg_cpu *cpu, unsigned long start) { - struct lguest_regs *regs = lg->regs; + struct lguest_regs *regs = cpu->regs; /* There are four "segment" registers which the Guest needs to boot: * The "code segment" register (cs) refers to the kernel code segment @@ -577,5 +580,5 @@ void lguest_arch_setup_regs(struct lguest *lg, unsigned long start) /* There are a couple of GDT entries the Guest expects when first * booting. */ - setup_guest_gdt(lg); + setup_guest_gdt(cpu); } diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig index af40ff434def..6c575403bd39 100644 --- a/drivers/net/Kconfig +++ b/drivers/net/Kconfig @@ -2009,6 +2009,9 @@ config E1000E To compile this driver as a module, choose M here. The module will be called e1000e. +config E1000E_ENABLED + def_bool E1000E != n + config IP1000 tristate "IP1000 Gigabit Ethernet support" depends on PCI && EXPERIMENTAL diff --git a/drivers/net/e1000/e1000_main.c b/drivers/net/e1000/e1000_main.c index 7f5b2ae70d5d..8c87940a9ce8 100644 --- a/drivers/net/e1000/e1000_main.c +++ b/drivers/net/e1000/e1000_main.c @@ -47,6 +47,12 @@ static const char e1000_copyright[] = "Copyright (c) 1999-2006 Intel Corporation * Macro expands to... * {PCI_DEVICE(PCI_VENDOR_ID_INTEL, device_id)} */ +#ifdef CONFIG_E1000E_ENABLED + #define PCIE(x) +#else + #define PCIE(x) x, +#endif + static struct pci_device_id e1000_pci_tbl[] = { INTEL_E1000_ETHERNET_DEVICE(0x1000), INTEL_E1000_ETHERNET_DEVICE(0x1001), @@ -73,6 +79,14 @@ static struct pci_device_id e1000_pci_tbl[] = { INTEL_E1000_ETHERNET_DEVICE(0x1026), INTEL_E1000_ETHERNET_DEVICE(0x1027), INTEL_E1000_ETHERNET_DEVICE(0x1028), +PCIE( INTEL_E1000_ETHERNET_DEVICE(0x1049)) +PCIE( INTEL_E1000_ETHERNET_DEVICE(0x104A)) +PCIE( INTEL_E1000_ETHERNET_DEVICE(0x104B)) +PCIE( INTEL_E1000_ETHERNET_DEVICE(0x104C)) +PCIE( INTEL_E1000_ETHERNET_DEVICE(0x104D)) +PCIE( INTEL_E1000_ETHERNET_DEVICE(0x105E)) +PCIE( INTEL_E1000_ETHERNET_DEVICE(0x105F)) +PCIE( INTEL_E1000_ETHERNET_DEVICE(0x1060)) INTEL_E1000_ETHERNET_DEVICE(0x1075), INTEL_E1000_ETHERNET_DEVICE(0x1076), INTEL_E1000_ETHERNET_DEVICE(0x1077), @@ -81,9 +95,28 @@ static struct pci_device_id e1000_pci_tbl[] = { INTEL_E1000_ETHERNET_DEVICE(0x107A), INTEL_E1000_ETHERNET_DEVICE(0x107B), INTEL_E1000_ETHERNET_DEVICE(0x107C), +PCIE( INTEL_E1000_ETHERNET_DEVICE(0x107D)) +PCIE( INTEL_E1000_ETHERNET_DEVICE(0x107E)) +PCIE( INTEL_E1000_ETHERNET_DEVICE(0x107F)) INTEL_E1000_ETHERNET_DEVICE(0x108A), +PCIE( INTEL_E1000_ETHERNET_DEVICE(0x108B)) +PCIE( INTEL_E1000_ETHERNET_DEVICE(0x108C)) +PCIE( INTEL_E1000_ETHERNET_DEVICE(0x1096)) +PCIE( INTEL_E1000_ETHERNET_DEVICE(0x1098)) INTEL_E1000_ETHERNET_DEVICE(0x1099), +PCIE( INTEL_E1000_ETHERNET_DEVICE(0x109A)) +PCIE( INTEL_E1000_ETHERNET_DEVICE(0x10A4)) +PCIE( INTEL_E1000_ETHERNET_DEVICE(0x10A5)) INTEL_E1000_ETHERNET_DEVICE(0x10B5), +PCIE( INTEL_E1000_ETHERNET_DEVICE(0x10B9)) +PCIE( INTEL_E1000_ETHERNET_DEVICE(0x10BA)) +PCIE( INTEL_E1000_ETHERNET_DEVICE(0x10BB)) +PCIE( INTEL_E1000_ETHERNET_DEVICE(0x10BC)) +PCIE( INTEL_E1000_ETHERNET_DEVICE(0x10C4)) +PCIE( INTEL_E1000_ETHERNET_DEVICE(0x10C5)) +PCIE( INTEL_E1000_ETHERNET_DEVICE(0x10D5)) +PCIE( INTEL_E1000_ETHERNET_DEVICE(0x10D9)) +PCIE( INTEL_E1000_ETHERNET_DEVICE(0x10DA)) /* required last entry */ {0,} }; diff --git a/drivers/pnp/pnpbios/bioscalls.c b/drivers/pnp/pnpbios/bioscalls.c index 5dba68fe33f5..a8364d815222 100644 --- a/drivers/pnp/pnpbios/bioscalls.c +++ b/drivers/pnp/pnpbios/bioscalls.c @@ -61,7 +61,7 @@ set_base(gdt[(selname) >> 3], (u32)(address)); \ set_limit(gdt[(selname) >> 3], size); \ } while(0) -static struct desc_struct bad_bios_desc = { 0, 0x00409200 }; +static struct desc_struct bad_bios_desc; /* * At some point we want to use this stack frame pointer to unwind @@ -477,6 +477,9 @@ void pnpbios_calls_init(union pnp_bios_install_struct *header) pnp_bios_callpoint.offset = header->fields.pm16offset; pnp_bios_callpoint.segment = PNP_CS16; + bad_bios_desc.a = 0; + bad_bios_desc.b = 0x00409200; + set_base(bad_bios_desc, __va((unsigned long)0x40 << 4)); _set_limit((char *)&bad_bios_desc, 4095 - (0x40 << 4)); for (i = 0; i < NR_CPUS; i++) { diff --git a/drivers/s390/scsi/zfcp_fsf.c b/drivers/s390/scsi/zfcp_fsf.c index e45f85f7c7ed..0dff05840ee2 100644 --- a/drivers/s390/scsi/zfcp_fsf.c +++ b/drivers/s390/scsi/zfcp_fsf.c @@ -4224,10 +4224,10 @@ zfcp_fsf_send_fcp_command_task_handler(struct zfcp_fsf_req *fsf_req) ZFCP_LOG_TRACE("%i bytes sense data provided by FCP\n", fcp_rsp_iu->fcp_sns_len); - memcpy(&scpnt->sense_buffer, + memcpy(scpnt->sense_buffer, zfcp_get_fcp_sns_info_ptr(fcp_rsp_iu), sns_len); ZFCP_HEX_DUMP(ZFCP_LOG_LEVEL_TRACE, - (void *) &scpnt->sense_buffer, sns_len); + (void *)scpnt->sense_buffer, sns_len); } /* check for overrun */ diff --git a/drivers/scsi/3w-9xxx.c b/drivers/scsi/3w-9xxx.c index 1c244832c6c8..b4912d1cee2a 100644 --- a/drivers/scsi/3w-9xxx.c +++ b/drivers/scsi/3w-9xxx.c @@ -1990,7 +1990,6 @@ static struct scsi_host_template driver_template = { .max_sectors = TW_MAX_SECTORS, .cmd_per_lun = TW_MAX_CMDS_PER_LUN, .use_clustering = ENABLE_CLUSTERING, - .use_sg_chaining = ENABLE_SG_CHAINING, .shost_attrs = twa_host_attrs, .emulated = 1 }; diff --git a/drivers/scsi/3w-xxxx.c b/drivers/scsi/3w-xxxx.c index 59716ebeb10c..d09532162217 100644 --- a/drivers/scsi/3w-xxxx.c +++ b/drivers/scsi/3w-xxxx.c @@ -2261,7 +2261,6 @@ static struct scsi_host_template driver_template = { .max_sectors = TW_MAX_SECTORS, .cmd_per_lun = TW_MAX_CMDS_PER_LUN, .use_clustering = ENABLE_CLUSTERING, - .use_sg_chaining = ENABLE_SG_CHAINING, .shost_attrs = tw_host_attrs, .emulated = 1 }; diff --git a/drivers/scsi/BusLogic.c b/drivers/scsi/BusLogic.c index ead47c143ce0..4d3ebb1af490 100644 --- a/drivers/scsi/BusLogic.c +++ b/drivers/scsi/BusLogic.c @@ -3575,7 +3575,6 @@ static struct scsi_host_template Bus_Logic_template = { .unchecked_isa_dma = 1, .max_sectors = 128, .use_clustering = ENABLE_CLUSTERING, - .use_sg_chaining = ENABLE_SG_CHAINING, }; /* diff --git a/drivers/scsi/Kconfig b/drivers/scsi/Kconfig index 3e161cd66463..14fc7f39e83e 100644 --- a/drivers/scsi/Kconfig +++ b/drivers/scsi/Kconfig @@ -345,7 +345,7 @@ config ISCSI_TCP config SGIWD93_SCSI tristate "SGI WD93C93 SCSI Driver" - depends on SGI_IP22 && SCSI + depends on SGI_HAS_WD93 && SCSI help If you have a Western Digital WD93 SCSI controller on an SGI MIPS system, say Y. Otherwise, say N. diff --git a/drivers/scsi/NCR53c406a.c b/drivers/scsi/NCR53c406a.c index 137d065db3da..6961f78742ae 100644 --- a/drivers/scsi/NCR53c406a.c +++ b/drivers/scsi/NCR53c406a.c @@ -1065,7 +1065,6 @@ static struct scsi_host_template driver_template = .cmd_per_lun = 1 /* commands per lun */, .unchecked_isa_dma = 1 /* unchecked_isa_dma */, .use_clustering = ENABLE_CLUSTERING, - .use_sg_chaining = ENABLE_SG_CHAINING, }; #include "scsi_module.c" diff --git a/drivers/scsi/a100u2w.c b/drivers/scsi/a100u2w.c index d3a6d15fb77a..f608d4a1d6da 100644 --- a/drivers/scsi/a100u2w.c +++ b/drivers/scsi/a100u2w.c @@ -1071,7 +1071,6 @@ static struct scsi_host_template inia100_template = { .sg_tablesize = SG_ALL, .cmd_per_lun = 1, .use_clustering = ENABLE_CLUSTERING, - .use_sg_chaining = ENABLE_SG_CHAINING, }; static int __devinit inia100_probe_one(struct pci_dev *pdev, diff --git a/drivers/scsi/aacraid/commctrl.c b/drivers/scsi/aacraid/commctrl.c index 851a7e599c50..f8afa358b6b6 100644 --- a/drivers/scsi/aacraid/commctrl.c +++ b/drivers/scsi/aacraid/commctrl.c @@ -243,7 +243,6 @@ static int next_getadapter_fib(struct aac_dev * dev, void __user *arg) * Search the list of AdapterFibContext addresses on the adapter * to be sure this is a valid address */ - spin_lock_irqsave(&dev->fib_lock, flags); entry = dev->fib_list.next; fibctx = NULL; @@ -252,25 +251,24 @@ static int next_getadapter_fib(struct aac_dev * dev, void __user *arg) /* * Extract the AdapterFibContext from the Input parameters. */ - if (fibctx->unique == f.fibctx) { /* We found a winner */ + if (fibctx->unique == f.fibctx) { /* We found a winner */ break; } entry = entry->next; fibctx = NULL; } if (!fibctx) { - spin_unlock_irqrestore(&dev->fib_lock, flags); dprintk ((KERN_INFO "Fib Context not found\n")); return -EINVAL; } if((fibctx->type != FSAFS_NTC_GET_ADAPTER_FIB_CONTEXT) || (fibctx->size != sizeof(struct aac_fib_context))) { - spin_unlock_irqrestore(&dev->fib_lock, flags); dprintk ((KERN_INFO "Fib Context corrupt?\n")); return -EINVAL; } status = 0; + spin_lock_irqsave(&dev->fib_lock, flags); /* * If there are no fibs to send back, then either wait or return * -EAGAIN @@ -328,9 +326,7 @@ return_fib: int aac_close_fib_context(struct aac_dev * dev, struct aac_fib_context * fibctx) { struct fib *fib; - unsigned long flags; - spin_lock_irqsave(&dev->fib_lock, flags); /* * First free any FIBs that have not been consumed. */ @@ -353,7 +349,6 @@ int aac_close_fib_context(struct aac_dev * dev, struct aac_fib_context * fibctx) * Remove the Context from the AdapterFibContext List */ list_del(&fibctx->next); - spin_unlock_irqrestore(&dev->fib_lock, flags); /* * Invalidate context */ @@ -419,8 +414,8 @@ static int close_getadapter_fib(struct aac_dev * dev, void __user *arg) * @arg: ioctl arguments * * This routine returns the driver version. - * Under Linux, there have been no version incompatibilities, so this is - * simple! + * Under Linux, there have been no version incompatibilities, so this is + * simple! */ static int check_revision(struct aac_dev *dev, void __user *arg) @@ -468,7 +463,7 @@ static int aac_send_raw_srb(struct aac_dev* dev, void __user * arg) u32 data_dir; void __user *sg_user[32]; void *sg_list[32]; - u32 sg_indx = 0; + u32 sg_indx = 0; u32 byte_count = 0; u32 actual_fibsize64, actual_fibsize = 0; int i; @@ -522,11 +517,11 @@ static int aac_send_raw_srb(struct aac_dev* dev, void __user * arg) // Fix up srb for endian and force some values srbcmd->function = cpu_to_le32(SRBF_ExecuteScsi); // Force this - srbcmd->channel = cpu_to_le32(user_srbcmd->channel); + srbcmd->channel = cpu_to_le32(user_srbcmd->channel); srbcmd->id = cpu_to_le32(user_srbcmd->id); - srbcmd->lun = cpu_to_le32(user_srbcmd->lun); - srbcmd->timeout = cpu_to_le32(user_srbcmd->timeout); - srbcmd->flags = cpu_to_le32(flags); + srbcmd->lun = cpu_to_le32(user_srbcmd->lun); + srbcmd->timeout = cpu_to_le32(user_srbcmd->timeout); + srbcmd->flags = cpu_to_le32(flags); srbcmd->retry_limit = 0; // Obsolete parameter srbcmd->cdb_size = cpu_to_le32(user_srbcmd->cdb_size); memcpy(srbcmd->cdb, user_srbcmd->cdb, sizeof(srbcmd->cdb)); @@ -791,9 +786,9 @@ static int aac_get_pci_info(struct aac_dev* dev, void __user *arg) pci_info.bus = dev->pdev->bus->number; pci_info.slot = PCI_SLOT(dev->pdev->devfn); - if (copy_to_user(arg, &pci_info, sizeof(struct aac_pci_info))) { - dprintk((KERN_DEBUG "aacraid: Could not copy pci info\n")); - return -EFAULT; + if (copy_to_user(arg, &pci_info, sizeof(struct aac_pci_info))) { + dprintk((KERN_DEBUG "aacraid: Could not copy pci info\n")); + return -EFAULT; } return 0; } diff --git a/drivers/scsi/aacraid/linit.c b/drivers/scsi/aacraid/linit.c index 61be22774e99..0e8267c1e915 100644 --- a/drivers/scsi/aacraid/linit.c +++ b/drivers/scsi/aacraid/linit.c @@ -1032,7 +1032,6 @@ static struct scsi_host_template aac_driver_template = { .cmd_per_lun = AAC_NUM_IO_FIB, #endif .use_clustering = ENABLE_CLUSTERING, - .use_sg_chaining = ENABLE_SG_CHAINING, .emulated = 1, }; diff --git a/drivers/scsi/aha1740.c b/drivers/scsi/aha1740.c index be58a0b097c7..7c45d88a205b 100644 --- a/drivers/scsi/aha1740.c +++ b/drivers/scsi/aha1740.c @@ -563,7 +563,6 @@ static struct scsi_host_template aha1740_template = { .sg_tablesize = AHA1740_SCATTER, .cmd_per_lun = AHA1740_CMDLUN, .use_clustering = ENABLE_CLUSTERING, - .use_sg_chaining = ENABLE_SG_CHAINING, .eh_abort_handler = aha1740_eh_abort_handler, }; diff --git a/drivers/scsi/aic7xxx/aic79xx.h b/drivers/scsi/aic7xxx/aic79xx.h index ce638aa6005a..2f00467b6b8c 100644 --- a/drivers/scsi/aic7xxx/aic79xx.h +++ b/drivers/scsi/aic7xxx/aic79xx.h @@ -1340,8 +1340,10 @@ struct ahd_pci_identity *ahd_find_pci_device(ahd_dev_softc_t); int ahd_pci_config(struct ahd_softc *, struct ahd_pci_identity *); int ahd_pci_test_register_access(struct ahd_softc *); +#ifdef CONFIG_PM void ahd_pci_suspend(struct ahd_softc *); void ahd_pci_resume(struct ahd_softc *); +#endif /************************** SCB and SCB queue management **********************/ void ahd_qinfifo_requeue_tail(struct ahd_softc *ahd, @@ -1352,8 +1354,10 @@ struct ahd_softc *ahd_alloc(void *platform_arg, char *name); int ahd_softc_init(struct ahd_softc *); void ahd_controller_info(struct ahd_softc *ahd, char *buf); int ahd_init(struct ahd_softc *ahd); +#ifdef CONFIG_PM int ahd_suspend(struct ahd_softc *ahd); void ahd_resume(struct ahd_softc *ahd); +#endif int ahd_default_config(struct ahd_softc *ahd); int ahd_parse_vpddata(struct ahd_softc *ahd, struct vpd_config *vpd); @@ -1361,7 +1365,6 @@ int ahd_parse_cfgdata(struct ahd_softc *ahd, struct seeprom_config *sc); void ahd_intr_enable(struct ahd_softc *ahd, int enable); void ahd_pause_and_flushwork(struct ahd_softc *ahd); -int ahd_suspend(struct ahd_softc *ahd); void ahd_set_unit(struct ahd_softc *, int); void ahd_set_name(struct ahd_softc *, char *); struct scb *ahd_get_scb(struct ahd_softc *ahd, u_int col_idx); diff --git a/drivers/scsi/aic7xxx/aic79xx_core.c b/drivers/scsi/aic7xxx/aic79xx_core.c index a7dd8cdda472..ade0fb8fbdb2 100644 --- a/drivers/scsi/aic7xxx/aic79xx_core.c +++ b/drivers/scsi/aic7xxx/aic79xx_core.c @@ -7175,6 +7175,7 @@ ahd_pause_and_flushwork(struct ahd_softc *ahd) ahd->flags &= ~AHD_ALL_INTERRUPTS; } +#ifdef CONFIG_PM int ahd_suspend(struct ahd_softc *ahd) { @@ -7197,6 +7198,7 @@ ahd_resume(struct ahd_softc *ahd) ahd_intr_enable(ahd, TRUE); ahd_restart(ahd); } +#endif /************************** Busy Target Table *********************************/ /* diff --git a/drivers/scsi/aic7xxx/aic79xx_osm.c b/drivers/scsi/aic7xxx/aic79xx_osm.c index 0e4708fd43c8..014654792901 100644 --- a/drivers/scsi/aic7xxx/aic79xx_osm.c +++ b/drivers/scsi/aic7xxx/aic79xx_osm.c @@ -766,7 +766,6 @@ struct scsi_host_template aic79xx_driver_template = { .max_sectors = 8192, .cmd_per_lun = 2, .use_clustering = ENABLE_CLUSTERING, - .use_sg_chaining = ENABLE_SG_CHAINING, .slave_alloc = ahd_linux_slave_alloc, .slave_configure = ahd_linux_slave_configure, .target_alloc = ahd_linux_target_alloc, @@ -1922,7 +1921,7 @@ ahd_linux_queue_cmd_complete(struct ahd_softc *ahd, struct scsi_cmnd *cmd) struct scsi_sense_data *sense; sense = (struct scsi_sense_data *) - &cmd->sense_buffer; + cmd->sense_buffer; if (sense->extra_len >= 5 && (sense->add_sense_code == 0x47 || sense->add_sense_code == 0x48)) diff --git a/drivers/scsi/aic7xxx/aic79xx_osm_pci.c b/drivers/scsi/aic7xxx/aic79xx_osm_pci.c index 66f0259edb69..4150c8a8fdc2 100644 --- a/drivers/scsi/aic7xxx/aic79xx_osm_pci.c +++ b/drivers/scsi/aic7xxx/aic79xx_osm_pci.c @@ -43,17 +43,6 @@ #include "aic79xx_inline.h" #include "aic79xx_pci.h" -static int ahd_linux_pci_dev_probe(struct pci_dev *pdev, - const struct pci_device_id *ent); -static int ahd_linux_pci_reserve_io_regions(struct ahd_softc *ahd, - u_long *base, u_long *base2); -static int ahd_linux_pci_reserve_mem_region(struct ahd_softc *ahd, - u_long *bus_addr, - uint8_t __iomem **maddr); -static int ahd_linux_pci_dev_suspend(struct pci_dev *pdev, pm_message_t mesg); -static int ahd_linux_pci_dev_resume(struct pci_dev *pdev); -static void ahd_linux_pci_dev_remove(struct pci_dev *pdev); - /* Define the macro locally since it's different for different class of chips. */ #define ID(x) \ @@ -85,17 +74,7 @@ static struct pci_device_id ahd_linux_pci_id_table[] = { MODULE_DEVICE_TABLE(pci, ahd_linux_pci_id_table); -static struct pci_driver aic79xx_pci_driver = { - .name = "aic79xx", - .probe = ahd_linux_pci_dev_probe, #ifdef CONFIG_PM - .suspend = ahd_linux_pci_dev_suspend, - .resume = ahd_linux_pci_dev_resume, -#endif - .remove = ahd_linux_pci_dev_remove, - .id_table = ahd_linux_pci_id_table -}; - static int ahd_linux_pci_dev_suspend(struct pci_dev *pdev, pm_message_t mesg) { @@ -139,6 +118,7 @@ ahd_linux_pci_dev_resume(struct pci_dev *pdev) return rc; } +#endif static void ahd_linux_pci_dev_remove(struct pci_dev *pdev) @@ -245,6 +225,17 @@ ahd_linux_pci_dev_probe(struct pci_dev *pdev, const struct pci_device_id *ent) return (0); } +static struct pci_driver aic79xx_pci_driver = { + .name = "aic79xx", + .probe = ahd_linux_pci_dev_probe, +#ifdef CONFIG_PM + .suspend = ahd_linux_pci_dev_suspend, + .resume = ahd_linux_pci_dev_resume, +#endif + .remove = ahd_linux_pci_dev_remove, + .id_table = ahd_linux_pci_id_table +}; + int ahd_linux_pci_init(void) { diff --git a/drivers/scsi/aic7xxx/aic79xx_pci.c b/drivers/scsi/aic7xxx/aic79xx_pci.c index 7a203a90601a..df853676e66a 100644 --- a/drivers/scsi/aic7xxx/aic79xx_pci.c +++ b/drivers/scsi/aic7xxx/aic79xx_pci.c @@ -389,6 +389,7 @@ ahd_pci_config(struct ahd_softc *ahd, struct ahd_pci_identity *entry) return error; } +#ifdef CONFIG_PM void ahd_pci_suspend(struct ahd_softc *ahd) { @@ -415,6 +416,7 @@ ahd_pci_resume(struct ahd_softc *ahd) ahd_pci_write_config(ahd->dev_softc, CSIZE_LATTIME, ahd->suspend_state.pci_state.csize_lattime, /*bytes*/1); } +#endif /* * Perform some simple tests that should catch situations where diff --git a/drivers/scsi/aic7xxx/aic7xxx.h b/drivers/scsi/aic7xxx/aic7xxx.h index 3d4e42d90452..c0344e617651 100644 --- a/drivers/scsi/aic7xxx/aic7xxx.h +++ b/drivers/scsi/aic7xxx/aic7xxx.h @@ -1143,7 +1143,9 @@ struct ahc_pci_identity *ahc_find_pci_device(ahc_dev_softc_t); int ahc_pci_config(struct ahc_softc *, struct ahc_pci_identity *); int ahc_pci_test_register_access(struct ahc_softc *); +#ifdef CONFIG_PM void ahc_pci_resume(struct ahc_softc *ahc); +#endif /*************************** EISA/VL Front End ********************************/ struct aic7770_identity *aic7770_find_device(uint32_t); @@ -1170,8 +1172,10 @@ int ahc_chip_init(struct ahc_softc *ahc); int ahc_init(struct ahc_softc *ahc); void ahc_intr_enable(struct ahc_softc *ahc, int enable); void ahc_pause_and_flushwork(struct ahc_softc *ahc); +#ifdef CONFIG_PM int ahc_suspend(struct ahc_softc *ahc); int ahc_resume(struct ahc_softc *ahc); +#endif void ahc_set_unit(struct ahc_softc *, int); void ahc_set_name(struct ahc_softc *, char *); void ahc_alloc_scbs(struct ahc_softc *ahc); diff --git a/drivers/scsi/aic7xxx/aic7xxx_core.c b/drivers/scsi/aic7xxx/aic7xxx_core.c index f350b5e89e76..6d2ae641273c 100644 --- a/drivers/scsi/aic7xxx/aic7xxx_core.c +++ b/drivers/scsi/aic7xxx/aic7xxx_core.c @@ -5078,6 +5078,7 @@ ahc_pause_and_flushwork(struct ahc_softc *ahc) ahc->flags &= ~AHC_ALL_INTERRUPTS; } +#ifdef CONFIG_PM int ahc_suspend(struct ahc_softc *ahc) { @@ -5113,7 +5114,7 @@ ahc_resume(struct ahc_softc *ahc) ahc_restart(ahc); return (0); } - +#endif /************************** Busy Target Table *********************************/ /* * Return the untagged transaction id for a given target/channel lun. diff --git a/drivers/scsi/aic7xxx/aic7xxx_osm.c b/drivers/scsi/aic7xxx/aic7xxx_osm.c index e310e414067f..99a3b33a3233 100644 --- a/drivers/scsi/aic7xxx/aic7xxx_osm.c +++ b/drivers/scsi/aic7xxx/aic7xxx_osm.c @@ -747,7 +747,6 @@ struct scsi_host_template aic7xxx_driver_template = { .max_sectors = 8192, .cmd_per_lun = 2, .use_clustering = ENABLE_CLUSTERING, - .use_sg_chaining = ENABLE_SG_CHAINING, .slave_alloc = ahc_linux_slave_alloc, .slave_configure = ahc_linux_slave_configure, .target_alloc = ahc_linux_target_alloc, @@ -1658,9 +1657,12 @@ ahc_done(struct ahc_softc *ahc, struct scb *scb) untagged_q = &(ahc->untagged_queues[target_offset]); TAILQ_REMOVE(untagged_q, scb, links.tqe); BUG_ON(!TAILQ_EMPTY(untagged_q)); - } - - if ((scb->flags & SCB_ACTIVE) == 0) { + } else if ((scb->flags & SCB_ACTIVE) == 0) { + /* + * Transactions aborted from the untagged queue may + * not have been dispatched to the controller, so + * only check the SCB_ACTIVE flag for tagged transactions. + */ printf("SCB %d done'd twice\n", scb->hscb->tag); ahc_dump_card_state(ahc); panic("Stopping for safety"); diff --git a/drivers/scsi/aic7xxx/aic7xxx_osm_pci.c b/drivers/scsi/aic7xxx/aic7xxx_osm_pci.c index 4488946cff2e..dd6e21d6f1dd 100644 --- a/drivers/scsi/aic7xxx/aic7xxx_osm_pci.c +++ b/drivers/scsi/aic7xxx/aic7xxx_osm_pci.c @@ -42,17 +42,6 @@ #include "aic7xxx_osm.h" #include "aic7xxx_pci.h" -static int ahc_linux_pci_dev_probe(struct pci_dev *pdev, - const struct pci_device_id *ent); -static int ahc_linux_pci_reserve_io_region(struct ahc_softc *ahc, - u_long *base); -static int ahc_linux_pci_reserve_mem_region(struct ahc_softc *ahc, - u_long *bus_addr, - uint8_t __iomem **maddr); -static int ahc_linux_pci_dev_suspend(struct pci_dev *pdev, pm_message_t mesg); -static int ahc_linux_pci_dev_resume(struct pci_dev *pdev); -static void ahc_linux_pci_dev_remove(struct pci_dev *pdev); - /* Define the macro locally since it's different for different class of chips. */ #define ID(x) ID_C(x, PCI_CLASS_STORAGE_SCSI) @@ -132,17 +121,7 @@ static struct pci_device_id ahc_linux_pci_id_table[] = { MODULE_DEVICE_TABLE(pci, ahc_linux_pci_id_table); -static struct pci_driver aic7xxx_pci_driver = { - .name = "aic7xxx", - .probe = ahc_linux_pci_dev_probe, #ifdef CONFIG_PM - .suspend = ahc_linux_pci_dev_suspend, - .resume = ahc_linux_pci_dev_resume, -#endif - .remove = ahc_linux_pci_dev_remove, - .id_table = ahc_linux_pci_id_table -}; - static int ahc_linux_pci_dev_suspend(struct pci_dev *pdev, pm_message_t mesg) { @@ -182,6 +161,7 @@ ahc_linux_pci_dev_resume(struct pci_dev *pdev) return (ahc_resume(ahc)); } +#endif static void ahc_linux_pci_dev_remove(struct pci_dev *pdev) @@ -289,6 +269,17 @@ ahc_linux_pci_dev_probe(struct pci_dev *pdev, const struct pci_device_id *ent) return (0); } +static struct pci_driver aic7xxx_pci_driver = { + .name = "aic7xxx", + .probe = ahc_linux_pci_dev_probe, +#ifdef CONFIG_PM + .suspend = ahc_linux_pci_dev_suspend, + .resume = ahc_linux_pci_dev_resume, +#endif + .remove = ahc_linux_pci_dev_remove, + .id_table = ahc_linux_pci_id_table +}; + int ahc_linux_pci_init(void) { diff --git a/drivers/scsi/aic7xxx/aic7xxx_pci.c b/drivers/scsi/aic7xxx/aic7xxx_pci.c index ae35937b8055..56848f41e4f9 100644 --- a/drivers/scsi/aic7xxx/aic7xxx_pci.c +++ b/drivers/scsi/aic7xxx/aic7xxx_pci.c @@ -2020,6 +2020,7 @@ ahc_pci_chip_init(struct ahc_softc *ahc) return (ahc_chip_init(ahc)); } +#ifdef CONFIG_PM void ahc_pci_resume(struct ahc_softc *ahc) { @@ -2051,6 +2052,7 @@ ahc_pci_resume(struct ahc_softc *ahc) ahc_release_seeprom(&sd); } } +#endif static int ahc_aic785X_setup(struct ahc_softc *ahc) diff --git a/drivers/scsi/aic7xxx_old.c b/drivers/scsi/aic7xxx_old.c index bcb0b870320c..3bfd9296bbfa 100644 --- a/drivers/scsi/aic7xxx_old.c +++ b/drivers/scsi/aic7xxx_old.c @@ -11141,7 +11141,6 @@ static struct scsi_host_template driver_template = { .max_sectors = 2048, .cmd_per_lun = 3, .use_clustering = ENABLE_CLUSTERING, - .use_sg_chaining = ENABLE_SG_CHAINING, }; #include "scsi_module.c" diff --git a/drivers/scsi/arcmsr/arcmsr_hba.c b/drivers/scsi/arcmsr/arcmsr_hba.c index d80dba913a75..f4a202e8df26 100644 --- a/drivers/scsi/arcmsr/arcmsr_hba.c +++ b/drivers/scsi/arcmsr/arcmsr_hba.c @@ -122,7 +122,6 @@ static struct scsi_host_template arcmsr_scsi_host_template = { .max_sectors = ARCMSR_MAX_XFER_SECTORS, .cmd_per_lun = ARCMSR_MAX_CMD_PERLUN, .use_clustering = ENABLE_CLUSTERING, - .use_sg_chaining = ENABLE_SG_CHAINING, .shost_attrs = arcmsr_host_attrs, }; #ifdef CONFIG_SCSI_ARCMSR_AER diff --git a/drivers/scsi/dc395x.c b/drivers/scsi/dc395x.c index f93c73c0ba53..22ef3716e786 100644 --- a/drivers/scsi/dc395x.c +++ b/drivers/scsi/dc395x.c @@ -4763,7 +4763,6 @@ static struct scsi_host_template dc395x_driver_template = { .eh_bus_reset_handler = dc395x_eh_bus_reset, .unchecked_isa_dma = 0, .use_clustering = DISABLE_CLUSTERING, - .use_sg_chaining = ENABLE_SG_CHAINING, }; diff --git a/drivers/scsi/dpt_i2o.c b/drivers/scsi/dpt_i2o.c index 19cce125124c..c9dd8392aab2 100644 --- a/drivers/scsi/dpt_i2o.c +++ b/drivers/scsi/dpt_i2o.c @@ -3340,7 +3340,6 @@ static struct scsi_host_template driver_template = { .this_id = 7, .cmd_per_lun = 1, .use_clustering = ENABLE_CLUSTERING, - .use_sg_chaining = ENABLE_SG_CHAINING, }; #include "scsi_module.c" MODULE_LICENSE("GPL"); diff --git a/drivers/scsi/eata.c b/drivers/scsi/eata.c index 05163cefec12..8be3d76656fa 100644 --- a/drivers/scsi/eata.c +++ b/drivers/scsi/eata.c @@ -524,7 +524,6 @@ static struct scsi_host_template driver_template = { .this_id = 7, .unchecked_isa_dma = 1, .use_clustering = ENABLE_CLUSTERING, - .use_sg_chaining = ENABLE_SG_CHAINING, }; #if !defined(__BIG_ENDIAN_BITFIELD) && !defined(__LITTLE_ENDIAN_BITFIELD) diff --git a/drivers/scsi/hosts.c b/drivers/scsi/hosts.c index 5ea1f986220c..880c78bff0e1 100644 --- a/drivers/scsi/hosts.c +++ b/drivers/scsi/hosts.c @@ -342,7 +342,6 @@ struct Scsi_Host *scsi_host_alloc(struct scsi_host_template *sht, int privsize) shost->use_clustering = sht->use_clustering; shost->ordered_tag = sht->ordered_tag; shost->active_mode = sht->supported_mode; - shost->use_sg_chaining = sht->use_sg_chaining; if (sht->supported_mode == MODE_UNKNOWN) /* means we didn't set it ... default to INITIATOR */ diff --git a/drivers/scsi/hptiop.c b/drivers/scsi/hptiop.c index e7b2f3575ce9..ff149ad6bc4e 100644 --- a/drivers/scsi/hptiop.c +++ b/drivers/scsi/hptiop.c @@ -573,7 +573,7 @@ static void hptiop_finish_scsi_req(struct hptiop_hba *hba, u32 tag, scsi_set_resid(scp, scsi_bufflen(scp) - le32_to_cpu(req->dataxfer_length)); scp->result = SAM_STAT_CHECK_CONDITION; - memcpy(&scp->sense_buffer, &req->sg_list, + memcpy(scp->sense_buffer, &req->sg_list, min_t(size_t, SCSI_SENSE_BUFFERSIZE, le32_to_cpu(req->dataxfer_length))); break; @@ -906,7 +906,6 @@ static struct scsi_host_template driver_template = { .unchecked_isa_dma = 0, .emulated = 0, .use_clustering = ENABLE_CLUSTERING, - .use_sg_chaining = ENABLE_SG_CHAINING, .proc_name = driver_name, .shost_attrs = hptiop_attrs, .this_id = -1, diff --git a/drivers/scsi/ibmmca.c b/drivers/scsi/ibmmca.c index db004a450732..4d15a62914e9 100644 --- a/drivers/scsi/ibmmca.c +++ b/drivers/scsi/ibmmca.c @@ -1501,7 +1501,6 @@ static struct scsi_host_template ibmmca_driver_template = { .sg_tablesize = 16, .cmd_per_lun = 1, .use_clustering = ENABLE_CLUSTERING, - .use_sg_chaining = ENABLE_SG_CHAINING, }; static int ibmmca_probe(struct device *dev) diff --git a/drivers/scsi/ibmvscsi/ibmvscsi.c b/drivers/scsi/ibmvscsi/ibmvscsi.c index 30819012898f..78d46a900bb5 100644 --- a/drivers/scsi/ibmvscsi/ibmvscsi.c +++ b/drivers/scsi/ibmvscsi/ibmvscsi.c @@ -1600,7 +1600,6 @@ static struct scsi_host_template driver_template = { .this_id = -1, .sg_tablesize = SG_ALL, .use_clustering = ENABLE_CLUSTERING, - .use_sg_chaining = ENABLE_SG_CHAINING, .shost_attrs = ibmvscsi_attrs, }; diff --git a/drivers/scsi/initio.c b/drivers/scsi/initio.c index a10a5c74b48d..0cc8868ea35d 100644 --- a/drivers/scsi/initio.c +++ b/drivers/scsi/initio.c @@ -2833,7 +2833,6 @@ static struct scsi_host_template initio_template = { .sg_tablesize = SG_ALL, .cmd_per_lun = 1, .use_clustering = ENABLE_CLUSTERING, - .use_sg_chaining = ENABLE_SG_CHAINING, }; static int initio_probe_one(struct pci_dev *pdev, diff --git a/drivers/scsi/iscsi_tcp.c b/drivers/scsi/iscsi_tcp.c index e5be5fd4ef58..b6f99dfbb038 100644 --- a/drivers/scsi/iscsi_tcp.c +++ b/drivers/scsi/iscsi_tcp.c @@ -1933,7 +1933,6 @@ static struct scsi_host_template iscsi_sht = { .eh_device_reset_handler= iscsi_eh_device_reset, .eh_host_reset_handler = iscsi_eh_host_reset, .use_clustering = DISABLE_CLUSTERING, - .use_sg_chaining = ENABLE_SG_CHAINING, .slave_configure = iscsi_tcp_slave_configure, .proc_name = "iscsi_tcp", .this_id = -1, diff --git a/drivers/scsi/libsrp.c b/drivers/scsi/libsrp.c index 5cff0204227d..6d6a76e65a6c 100644 --- a/drivers/scsi/libsrp.c +++ b/drivers/scsi/libsrp.c @@ -426,8 +426,8 @@ int srp_cmd_queue(struct Scsi_Host *shost, struct srp_cmd *cmd, void *info, sc->SCp.ptr = info; memcpy(sc->cmnd, cmd->cdb, MAX_COMMAND_SIZE); - sc->request_bufflen = len; - sc->request_buffer = (void *) (unsigned long) addr; + sc->sdb.length = len; + sc->sdb.table.sgl = (void *) (unsigned long) addr; sc->tag = tag; err = scsi_tgt_queue_command(sc, itn_id, (struct scsi_lun *)&cmd->lun, cmd->tag); diff --git a/drivers/scsi/lpfc/lpfc_scsi.c b/drivers/scsi/lpfc/lpfc_scsi.c index 6483c62730b3..fc5c3a42b05a 100644 --- a/drivers/scsi/lpfc/lpfc_scsi.c +++ b/drivers/scsi/lpfc/lpfc_scsi.c @@ -1459,7 +1459,6 @@ struct scsi_host_template lpfc_template = { .scan_finished = lpfc_scan_finished, .this_id = -1, .sg_tablesize = LPFC_DEFAULT_SG_SEG_CNT, - .use_sg_chaining = ENABLE_SG_CHAINING, .cmd_per_lun = LPFC_CMD_PER_LUN, .use_clustering = ENABLE_CLUSTERING, .shost_attrs = lpfc_hba_attrs, @@ -1482,7 +1481,6 @@ struct scsi_host_template lpfc_vport_template = { .sg_tablesize = LPFC_DEFAULT_SG_SEG_CNT, .cmd_per_lun = LPFC_CMD_PER_LUN, .use_clustering = ENABLE_CLUSTERING, - .use_sg_chaining = ENABLE_SG_CHAINING, .shost_attrs = lpfc_vport_attrs, .max_sectors = 0xFFFF, }; diff --git a/drivers/scsi/mac53c94.c b/drivers/scsi/mac53c94.c index a035001f4438..b12ad7c7c673 100644 --- a/drivers/scsi/mac53c94.c +++ b/drivers/scsi/mac53c94.c @@ -402,7 +402,6 @@ static struct scsi_host_template mac53c94_template = { .sg_tablesize = SG_ALL, .cmd_per_lun = 1, .use_clustering = DISABLE_CLUSTERING, - .use_sg_chaining = ENABLE_SG_CHAINING, }; static int mac53c94_probe(struct macio_dev *mdev, const struct of_device_id *match) diff --git a/drivers/scsi/megaraid.c b/drivers/scsi/megaraid.c index 765c24d2bc38..4d59ae8491a4 100644 --- a/drivers/scsi/megaraid.c +++ b/drivers/scsi/megaraid.c @@ -4490,7 +4490,6 @@ static struct scsi_host_template megaraid_template = { .sg_tablesize = MAX_SGLIST, .cmd_per_lun = DEF_CMD_PER_LUN, .use_clustering = ENABLE_CLUSTERING, - .use_sg_chaining = ENABLE_SG_CHAINING, .eh_abort_handler = megaraid_abort, .eh_device_reset_handler = megaraid_reset, .eh_bus_reset_handler = megaraid_reset, diff --git a/drivers/scsi/megaraid/megaraid_mbox.c b/drivers/scsi/megaraid/megaraid_mbox.c index 24e32e446e76..6db77c00e3ee 100644 --- a/drivers/scsi/megaraid/megaraid_mbox.c +++ b/drivers/scsi/megaraid/megaraid_mbox.c @@ -361,7 +361,6 @@ static struct scsi_host_template megaraid_template_g = { .eh_host_reset_handler = megaraid_reset_handler, .change_queue_depth = megaraid_change_queue_depth, .use_clustering = ENABLE_CLUSTERING, - .use_sg_chaining = ENABLE_SG_CHAINING, .sdev_attrs = megaraid_sdev_attrs, .shost_attrs = megaraid_shost_attrs, }; diff --git a/drivers/scsi/megaraid/megaraid_sas.c b/drivers/scsi/megaraid/megaraid_sas.c index d7ec921865c4..672c759ac24d 100644 --- a/drivers/scsi/megaraid/megaraid_sas.c +++ b/drivers/scsi/megaraid/megaraid_sas.c @@ -1192,7 +1192,6 @@ static struct scsi_host_template megasas_template = { .eh_timed_out = megasas_reset_timer, .bios_param = megasas_bios_param, .use_clustering = ENABLE_CLUSTERING, - .use_sg_chaining = ENABLE_SG_CHAINING, }; /** diff --git a/drivers/scsi/mesh.c b/drivers/scsi/mesh.c index 7470ff39ab22..651d09b08f2a 100644 --- a/drivers/scsi/mesh.c +++ b/drivers/scsi/mesh.c @@ -1843,7 +1843,6 @@ static struct scsi_host_template mesh_template = { .sg_tablesize = SG_ALL, .cmd_per_lun = 2, .use_clustering = DISABLE_CLUSTERING, - .use_sg_chaining = ENABLE_SG_CHAINING, }; static int mesh_probe(struct macio_dev *mdev, const struct of_device_id *match) diff --git a/drivers/scsi/ncr53c8xx.c b/drivers/scsi/ncr53c8xx.c index c02771aa6c9b..c5ebf018b378 100644 --- a/drivers/scsi/ncr53c8xx.c +++ b/drivers/scsi/ncr53c8xx.c @@ -4967,7 +4967,7 @@ void ncr_complete (struct ncb *np, struct ccb *cp) sizeof(cp->sense_buf))); if (DEBUG_FLAGS & (DEBUG_RESULT|DEBUG_TINY)) { - u_char * p = (u_char*) & cmd->sense_buffer; + u_char *p = cmd->sense_buffer; int i; PRINT_ADDR(cmd, "sense data:"); for (i=0; i<14; i++) printk (" %x", *p++); diff --git a/drivers/scsi/nsp32.c b/drivers/scsi/nsp32.c index 28161dc95e0d..7fed35372150 100644 --- a/drivers/scsi/nsp32.c +++ b/drivers/scsi/nsp32.c @@ -281,7 +281,6 @@ static struct scsi_host_template nsp32_template = { .cmd_per_lun = 1, .this_id = NSP32_HOST_SCSIID, .use_clustering = DISABLE_CLUSTERING, - .use_sg_chaining = ENABLE_SG_CHAINING, .eh_abort_handler = nsp32_eh_abort, .eh_bus_reset_handler = nsp32_eh_bus_reset, .eh_host_reset_handler = nsp32_eh_host_reset, diff --git a/drivers/scsi/pcmcia/sym53c500_cs.c b/drivers/scsi/pcmcia/sym53c500_cs.c index 969b9387a0c3..3454a5714749 100644 --- a/drivers/scsi/pcmcia/sym53c500_cs.c +++ b/drivers/scsi/pcmcia/sym53c500_cs.c @@ -692,7 +692,6 @@ static struct scsi_host_template sym53c500_driver_template = { .sg_tablesize = 32, .cmd_per_lun = 1, .use_clustering = ENABLE_CLUSTERING, - .use_sg_chaining = ENABLE_SG_CHAINING, .shost_attrs = SYM53C500_shost_attrs }; diff --git a/drivers/scsi/qla1280.c b/drivers/scsi/qla1280.c index c94906abfee3..68c0d09ffe78 100644 --- a/drivers/scsi/qla1280.c +++ b/drivers/scsi/qla1280.c @@ -4204,7 +4204,6 @@ static struct scsi_host_template qla1280_driver_template = { .sg_tablesize = SG_ALL, .cmd_per_lun = 1, .use_clustering = ENABLE_CLUSTERING, - .use_sg_chaining = ENABLE_SG_CHAINING, }; diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c index aba1e6d48066..3954ed2d7b51 100644 --- a/drivers/scsi/qla2xxx/qla_os.c +++ b/drivers/scsi/qla2xxx/qla_os.c @@ -131,7 +131,6 @@ static struct scsi_host_template qla2x00_driver_template = { .this_id = -1, .cmd_per_lun = 3, .use_clustering = ENABLE_CLUSTERING, - .use_sg_chaining = ENABLE_SG_CHAINING, .sg_tablesize = SG_ALL, /* @@ -163,7 +162,6 @@ struct scsi_host_template qla24xx_driver_template = { .this_id = -1, .cmd_per_lun = 3, .use_clustering = ENABLE_CLUSTERING, - .use_sg_chaining = ENABLE_SG_CHAINING, .sg_tablesize = SG_ALL, .max_sectors = 0xFFFF, diff --git a/drivers/scsi/qla4xxx/ql4_os.c b/drivers/scsi/qla4xxx/ql4_os.c index d3f86646cb08..2e2b9fedffcc 100644 --- a/drivers/scsi/qla4xxx/ql4_os.c +++ b/drivers/scsi/qla4xxx/ql4_os.c @@ -94,7 +94,6 @@ static struct scsi_host_template qla4xxx_driver_template = { .this_id = -1, .cmd_per_lun = 3, .use_clustering = ENABLE_CLUSTERING, - .use_sg_chaining = ENABLE_SG_CHAINING, .sg_tablesize = SG_ALL, .max_sectors = 0xFFFF, diff --git a/drivers/scsi/qlogicfas.c b/drivers/scsi/qlogicfas.c index 1769f965eedf..1e874f1fb5c6 100644 --- a/drivers/scsi/qlogicfas.c +++ b/drivers/scsi/qlogicfas.c @@ -197,7 +197,6 @@ static struct scsi_host_template qlogicfas_driver_template = { .sg_tablesize = SG_ALL, .cmd_per_lun = 1, .use_clustering = DISABLE_CLUSTERING, - .use_sg_chaining = ENABLE_SG_CHAINING, }; static __init int qlogicfas_init(void) diff --git a/drivers/scsi/scsi.c b/drivers/scsi/scsi.c index 1a9fba6a9f92..b35d19472caa 100644 --- a/drivers/scsi/scsi.c +++ b/drivers/scsi/scsi.c @@ -757,7 +757,7 @@ void scsi_finish_command(struct scsi_cmnd *cmd) "Notifying upper driver of completion " "(result %x)\n", cmd->result)); - good_bytes = cmd->request_bufflen; + good_bytes = scsi_bufflen(cmd); if (cmd->request->cmd_type != REQ_TYPE_BLOCK_PC) { drv = scsi_cmd_to_driver(cmd); if (drv->done) diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c index 82c06f0a9d02..1541c174937a 100644 --- a/drivers/scsi/scsi_debug.c +++ b/drivers/scsi/scsi_debug.c @@ -280,6 +280,8 @@ static int resp_write(struct scsi_cmnd * SCpnt, unsigned long long lba, unsigned int num, struct sdebug_dev_info * devip); static int resp_report_luns(struct scsi_cmnd * SCpnt, struct sdebug_dev_info * devip); +static int resp_xdwriteread(struct scsi_cmnd *scp, unsigned long long lba, + unsigned int num, struct sdebug_dev_info *devip); static int fill_from_dev_buffer(struct scsi_cmnd * scp, unsigned char * arr, int arr_len); static int fetch_to_dev_buffer(struct scsi_cmnd * scp, unsigned char * arr, @@ -311,12 +313,48 @@ static void sdebug_max_tgts_luns(void); static struct device pseudo_primary; static struct bus_type pseudo_lld_bus; +static void get_data_transfer_info(unsigned char *cmd, + unsigned long long *lba, unsigned int *num) +{ + int i; + + switch (*cmd) { + case WRITE_16: + case READ_16: + for (*lba = 0, i = 0; i < 8; ++i) { + if (i > 0) + *lba <<= 8; + *lba += cmd[2 + i]; + } + *num = cmd[13] + (cmd[12] << 8) + + (cmd[11] << 16) + (cmd[10] << 24); + break; + case WRITE_12: + case READ_12: + *lba = cmd[5] + (cmd[4] << 8) + (cmd[3] << 16) + (cmd[2] << 24); + *num = cmd[9] + (cmd[8] << 8) + (cmd[7] << 16) + (cmd[6] << 24); + break; + case WRITE_10: + case READ_10: + case XDWRITEREAD_10: + *lba = cmd[5] + (cmd[4] << 8) + (cmd[3] << 16) + (cmd[2] << 24); + *num = cmd[8] + (cmd[7] << 8); + break; + case WRITE_6: + case READ_6: + *lba = cmd[3] + (cmd[2] << 8) + ((cmd[1] & 0x1f) << 16); + *num = (0 == cmd[4]) ? 256 : cmd[4]; + break; + default: + break; + } +} static int scsi_debug_queuecommand(struct scsi_cmnd * SCpnt, done_funct_t done) { unsigned char *cmd = (unsigned char *) SCpnt->cmnd; - int len, k, j; + int len, k; unsigned int num; unsigned long long lba; int errsts = 0; @@ -452,28 +490,7 @@ int scsi_debug_queuecommand(struct scsi_cmnd * SCpnt, done_funct_t done) break; if (scsi_debug_fake_rw) break; - if ((*cmd) == READ_16) { - for (lba = 0, j = 0; j < 8; ++j) { - if (j > 0) - lba <<= 8; - lba += cmd[2 + j]; - } - num = cmd[13] + (cmd[12] << 8) + - (cmd[11] << 16) + (cmd[10] << 24); - } else if ((*cmd) == READ_12) { - lba = cmd[5] + (cmd[4] << 8) + - (cmd[3] << 16) + (cmd[2] << 24); - num = cmd[9] + (cmd[8] << 8) + - (cmd[7] << 16) + (cmd[6] << 24); - } else if ((*cmd) == READ_10) { - lba = cmd[5] + (cmd[4] << 8) + - (cmd[3] << 16) + (cmd[2] << 24); - num = cmd[8] + (cmd[7] << 8); - } else { /* READ (6) */ - lba = cmd[3] + (cmd[2] << 8) + - ((cmd[1] & 0x1f) << 16); - num = (0 == cmd[4]) ? 256 : cmd[4]; - } + get_data_transfer_info(cmd, &lba, &num); errsts = resp_read(SCpnt, lba, num, devip); if (inj_recovered && (0 == errsts)) { mk_sense_buffer(devip, RECOVERED_ERROR, @@ -500,28 +517,7 @@ int scsi_debug_queuecommand(struct scsi_cmnd * SCpnt, done_funct_t done) break; if (scsi_debug_fake_rw) break; - if ((*cmd) == WRITE_16) { - for (lba = 0, j = 0; j < 8; ++j) { - if (j > 0) - lba <<= 8; - lba += cmd[2 + j]; - } - num = cmd[13] + (cmd[12] << 8) + - (cmd[11] << 16) + (cmd[10] << 24); - } else if ((*cmd) == WRITE_12) { - lba = cmd[5] + (cmd[4] << 8) + - (cmd[3] << 16) + (cmd[2] << 24); - num = cmd[9] + (cmd[8] << 8) + - (cmd[7] << 16) + (cmd[6] << 24); - } else if ((*cmd) == WRITE_10) { - lba = cmd[5] + (cmd[4] << 8) + - (cmd[3] << 16) + (cmd[2] << 24); - num = cmd[8] + (cmd[7] << 8); - } else { /* WRITE (6) */ - lba = cmd[3] + (cmd[2] << 8) + - ((cmd[1] & 0x1f) << 16); - num = (0 == cmd[4]) ? 256 : cmd[4]; - } + get_data_transfer_info(cmd, &lba, &num); errsts = resp_write(SCpnt, lba, num, devip); if (inj_recovered && (0 == errsts)) { mk_sense_buffer(devip, RECOVERED_ERROR, @@ -549,6 +545,28 @@ int scsi_debug_queuecommand(struct scsi_cmnd * SCpnt, done_funct_t done) case WRITE_BUFFER: errsts = check_readiness(SCpnt, 1, devip); break; + case XDWRITEREAD_10: + if (!scsi_bidi_cmnd(SCpnt)) { + mk_sense_buffer(devip, ILLEGAL_REQUEST, + INVALID_FIELD_IN_CDB, 0); + errsts = check_condition_result; + break; + } + + errsts = check_readiness(SCpnt, 0, devip); + if (errsts) + break; + if (scsi_debug_fake_rw) + break; + get_data_transfer_info(cmd, &lba, &num); + errsts = resp_read(SCpnt, lba, num, devip); + if (errsts) + break; + errsts = resp_write(SCpnt, lba, num, devip); + if (errsts) + break; + errsts = resp_xdwriteread(SCpnt, lba, num, devip); + break; default: if (SCSI_DEBUG_OPT_NOISE & scsi_debug_opts) printk(KERN_INFO "scsi_debug: Opcode: 0x%x not " @@ -601,18 +619,18 @@ static int fill_from_dev_buffer(struct scsi_cmnd * scp, unsigned char * arr, int k, req_len, act_len, len, active; void * kaddr; void * kaddr_off; - struct scatterlist * sg; + struct scatterlist *sg; + struct scsi_data_buffer *sdb = scsi_in(scp); - if (0 == scsi_bufflen(scp)) + if (!sdb->length) return 0; - if (NULL == scsi_sglist(scp)) + if (!sdb->table.sgl) return (DID_ERROR << 16); - if (! ((scp->sc_data_direction == DMA_BIDIRECTIONAL) || - (scp->sc_data_direction == DMA_FROM_DEVICE))) + if (!(scsi_bidi_cmnd(scp) || scp->sc_data_direction == DMA_FROM_DEVICE)) return (DID_ERROR << 16); active = 1; req_len = act_len = 0; - scsi_for_each_sg(scp, sg, scsi_sg_count(scp), k) { + for_each_sg(sdb->table.sgl, sg, sdb->table.nents, k) { if (active) { kaddr = (unsigned char *) kmap_atomic(sg_page(sg), KM_USER0); @@ -630,10 +648,10 @@ static int fill_from_dev_buffer(struct scsi_cmnd * scp, unsigned char * arr, } req_len += sg->length; } - if (scsi_get_resid(scp)) - scsi_set_resid(scp, scsi_get_resid(scp) - act_len); + if (sdb->resid) + sdb->resid -= act_len; else - scsi_set_resid(scp, req_len - act_len); + sdb->resid = req_len - act_len; return 0; } @@ -650,8 +668,7 @@ static int fetch_to_dev_buffer(struct scsi_cmnd * scp, unsigned char * arr, return 0; if (NULL == scsi_sglist(scp)) return -1; - if (! ((scp->sc_data_direction == DMA_BIDIRECTIONAL) || - (scp->sc_data_direction == DMA_TO_DEVICE))) + if (!(scsi_bidi_cmnd(scp) || scp->sc_data_direction == DMA_TO_DEVICE)) return -1; req_len = fin = 0; scsi_for_each_sg(scp, sg, scsi_sg_count(scp), k) { @@ -1956,6 +1973,50 @@ static int resp_report_luns(struct scsi_cmnd * scp, min((int)alloc_len, SDEBUG_RLUN_ARR_SZ)); } +static int resp_xdwriteread(struct scsi_cmnd *scp, unsigned long long lba, + unsigned int num, struct sdebug_dev_info *devip) +{ + int i, j, ret = -1; + unsigned char *kaddr, *buf; + unsigned int offset; + struct scatterlist *sg; + struct scsi_data_buffer *sdb = scsi_in(scp); + + /* better not to use temporary buffer. */ + buf = kmalloc(scsi_bufflen(scp), GFP_ATOMIC); + if (!buf) + return ret; + + offset = 0; + scsi_for_each_sg(scp, sg, scsi_sg_count(scp), i) { + kaddr = (unsigned char *)kmap_atomic(sg_page(sg), KM_USER0); + if (!kaddr) + goto out; + + memcpy(buf + offset, kaddr + sg->offset, sg->length); + offset += sg->length; + kunmap_atomic(kaddr, KM_USER0); + } + + offset = 0; + for_each_sg(sdb->table.sgl, sg, sdb->table.nents, i) { + kaddr = (unsigned char *)kmap_atomic(sg_page(sg), KM_USER0); + if (!kaddr) + goto out; + + for (j = 0; j < sg->length; j++) + *(kaddr + sg->offset + j) ^= *(buf + offset + j); + + offset += sg->length; + kunmap_atomic(kaddr, KM_USER0); + } + ret = 0; +out: + kfree(buf); + + return ret; +} + /* When timer goes off this function is called. */ static void timer_intr_handler(unsigned long indx) { @@ -1989,6 +2050,7 @@ static int scsi_debug_slave_alloc(struct scsi_device * sdp) if (SCSI_DEBUG_OPT_NOISE & scsi_debug_opts) printk(KERN_INFO "scsi_debug: slave_alloc <%u %u %u %u>\n", sdp->host->host_no, sdp->channel, sdp->id, sdp->lun); + set_bit(QUEUE_FLAG_BIDI, &sdp->request_queue->queue_flags); return 0; } diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c index 547e85aa414f..045a0868fc7b 100644 --- a/drivers/scsi/scsi_error.c +++ b/drivers/scsi/scsi_error.c @@ -617,29 +617,27 @@ void scsi_eh_prep_cmnd(struct scsi_cmnd *scmd, struct scsi_eh_save *ses, ses->cmd_len = scmd->cmd_len; memcpy(ses->cmnd, scmd->cmnd, sizeof(scmd->cmnd)); ses->data_direction = scmd->sc_data_direction; - ses->bufflen = scmd->request_bufflen; - ses->buffer = scmd->request_buffer; - ses->use_sg = scmd->use_sg; - ses->resid = scmd->resid; + ses->sdb = scmd->sdb; + ses->next_rq = scmd->request->next_rq; ses->result = scmd->result; + memset(&scmd->sdb, 0, sizeof(scmd->sdb)); + scmd->request->next_rq = NULL; + if (sense_bytes) { - scmd->request_bufflen = min_t(unsigned, - SCSI_SENSE_BUFFERSIZE, sense_bytes); + scmd->sdb.length = min_t(unsigned, SCSI_SENSE_BUFFERSIZE, + sense_bytes); sg_init_one(&ses->sense_sgl, scmd->sense_buffer, - scmd->request_bufflen); - scmd->request_buffer = &ses->sense_sgl; + scmd->sdb.length); + scmd->sdb.table.sgl = &ses->sense_sgl; scmd->sc_data_direction = DMA_FROM_DEVICE; - scmd->use_sg = 1; + scmd->sdb.table.nents = 1; memset(scmd->cmnd, 0, sizeof(scmd->cmnd)); scmd->cmnd[0] = REQUEST_SENSE; - scmd->cmnd[4] = scmd->request_bufflen; + scmd->cmnd[4] = scmd->sdb.length; scmd->cmd_len = COMMAND_SIZE(scmd->cmnd[0]); } else { - scmd->request_buffer = NULL; - scmd->request_bufflen = 0; scmd->sc_data_direction = DMA_NONE; - scmd->use_sg = 0; if (cmnd) { memset(scmd->cmnd, 0, sizeof(scmd->cmnd)); memcpy(scmd->cmnd, cmnd, cmnd_size); @@ -676,10 +674,8 @@ void scsi_eh_restore_cmnd(struct scsi_cmnd* scmd, struct scsi_eh_save *ses) scmd->cmd_len = ses->cmd_len; memcpy(scmd->cmnd, ses->cmnd, sizeof(scmd->cmnd)); scmd->sc_data_direction = ses->data_direction; - scmd->request_bufflen = ses->bufflen; - scmd->request_buffer = ses->buffer; - scmd->use_sg = ses->use_sg; - scmd->resid = ses->resid; + scmd->sdb = ses->sdb; + scmd->request->next_rq = ses->next_rq; scmd->result = ses->result; } EXPORT_SYMBOL(scsi_eh_restore_cmnd); @@ -1700,8 +1696,7 @@ scsi_reset_provider(struct scsi_device *dev, int flag) memset(&scmd->cmnd, '\0', sizeof(scmd->cmnd)); scmd->scsi_done = scsi_reset_provider_done_command; - scmd->request_buffer = NULL; - scmd->request_bufflen = 0; + memset(&scmd->sdb, 0, sizeof(scmd->sdb)); scmd->cmd_len = 0; diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index 7c4c889c5221..b12fb310e399 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -8,6 +8,7 @@ */ #include <linux/bio.h> +#include <linux/bitops.h> #include <linux/blkdev.h> #include <linux/completion.h> #include <linux/kernel.h> @@ -34,13 +35,6 @@ #define SG_MEMPOOL_NR ARRAY_SIZE(scsi_sg_pools) #define SG_MEMPOOL_SIZE 2 -/* - * The maximum number of SG segments that we will put inside a scatterlist - * (unless chaining is used). Should ideally fit inside a single page, to - * avoid a higher order allocation. - */ -#define SCSI_MAX_SG_SEGMENTS 128 - struct scsi_host_sg_pool { size_t size; char *name; @@ -48,22 +42,31 @@ struct scsi_host_sg_pool { mempool_t *pool; }; -#define SP(x) { x, "sgpool-" #x } +#define SP(x) { x, "sgpool-" __stringify(x) } +#if (SCSI_MAX_SG_SEGMENTS < 32) +#error SCSI_MAX_SG_SEGMENTS is too small (must be 32 or greater) +#endif static struct scsi_host_sg_pool scsi_sg_pools[] = { SP(8), SP(16), -#if (SCSI_MAX_SG_SEGMENTS > 16) - SP(32), #if (SCSI_MAX_SG_SEGMENTS > 32) - SP(64), + SP(32), #if (SCSI_MAX_SG_SEGMENTS > 64) + SP(64), +#if (SCSI_MAX_SG_SEGMENTS > 128) SP(128), +#if (SCSI_MAX_SG_SEGMENTS > 256) +#error SCSI_MAX_SG_SEGMENTS is too large (256 MAX) +#endif #endif #endif #endif + SP(SCSI_MAX_SG_SEGMENTS) }; #undef SP +static struct kmem_cache *scsi_bidi_sdb_cache; + static void scsi_run_queue(struct request_queue *q); /* @@ -440,7 +443,7 @@ EXPORT_SYMBOL_GPL(scsi_execute_async); static void scsi_init_cmd_errh(struct scsi_cmnd *cmd) { cmd->serial_number = 0; - cmd->resid = 0; + scsi_set_resid(cmd, 0); memset(cmd->sense_buffer, 0, SCSI_SENSE_BUFFERSIZE); if (cmd->cmd_len == 0) cmd->cmd_len = COMMAND_SIZE(cmd->cmnd[0]); @@ -690,42 +693,16 @@ static struct scsi_cmnd *scsi_end_request(struct scsi_cmnd *cmd, int error, return NULL; } -/* - * Like SCSI_MAX_SG_SEGMENTS, but for archs that have sg chaining. This limit - * is totally arbitrary, a setting of 2048 will get you at least 8mb ios. - */ -#define SCSI_MAX_SG_CHAIN_SEGMENTS 2048 - static inline unsigned int scsi_sgtable_index(unsigned short nents) { unsigned int index; - switch (nents) { - case 1 ... 8: + BUG_ON(nents > SCSI_MAX_SG_SEGMENTS); + + if (nents <= 8) index = 0; - break; - case 9 ... 16: - index = 1; - break; -#if (SCSI_MAX_SG_SEGMENTS > 16) - case 17 ... 32: - index = 2; - break; -#if (SCSI_MAX_SG_SEGMENTS > 32) - case 33 ... 64: - index = 3; - break; -#if (SCSI_MAX_SG_SEGMENTS > 64) - case 65 ... 128: - index = 4; - break; -#endif -#endif -#endif - default: - printk(KERN_ERR "scsi: bad segment count=%d\n", nents); - BUG(); - } + else + index = get_count_order(nents) - 3; return index; } @@ -746,31 +723,27 @@ static struct scatterlist *scsi_sg_alloc(unsigned int nents, gfp_t gfp_mask) return mempool_alloc(sgp->pool, gfp_mask); } -int scsi_alloc_sgtable(struct scsi_cmnd *cmd, gfp_t gfp_mask) +static int scsi_alloc_sgtable(struct scsi_data_buffer *sdb, int nents, + gfp_t gfp_mask) { int ret; - BUG_ON(!cmd->use_sg); + BUG_ON(!nents); - ret = __sg_alloc_table(&cmd->sg_table, cmd->use_sg, - SCSI_MAX_SG_SEGMENTS, gfp_mask, scsi_sg_alloc); + ret = __sg_alloc_table(&sdb->table, nents, SCSI_MAX_SG_SEGMENTS, + gfp_mask, scsi_sg_alloc); if (unlikely(ret)) - __sg_free_table(&cmd->sg_table, SCSI_MAX_SG_SEGMENTS, + __sg_free_table(&sdb->table, SCSI_MAX_SG_SEGMENTS, scsi_sg_free); - cmd->request_buffer = cmd->sg_table.sgl; return ret; } -EXPORT_SYMBOL(scsi_alloc_sgtable); - -void scsi_free_sgtable(struct scsi_cmnd *cmd) +static void scsi_free_sgtable(struct scsi_data_buffer *sdb) { - __sg_free_table(&cmd->sg_table, SCSI_MAX_SG_SEGMENTS, scsi_sg_free); + __sg_free_table(&sdb->table, SCSI_MAX_SG_SEGMENTS, scsi_sg_free); } -EXPORT_SYMBOL(scsi_free_sgtable); - /* * Function: scsi_release_buffers() * @@ -788,17 +761,49 @@ EXPORT_SYMBOL(scsi_free_sgtable); * the scatter-gather table, and potentially any bounce * buffers. */ -static void scsi_release_buffers(struct scsi_cmnd *cmd) +void scsi_release_buffers(struct scsi_cmnd *cmd) +{ + if (cmd->sdb.table.nents) + scsi_free_sgtable(&cmd->sdb); + + memset(&cmd->sdb, 0, sizeof(cmd->sdb)); + + if (scsi_bidi_cmnd(cmd)) { + struct scsi_data_buffer *bidi_sdb = + cmd->request->next_rq->special; + scsi_free_sgtable(bidi_sdb); + kmem_cache_free(scsi_bidi_sdb_cache, bidi_sdb); + cmd->request->next_rq->special = NULL; + } +} +EXPORT_SYMBOL(scsi_release_buffers); + +/* + * Bidi commands Must be complete as a whole, both sides at once. + * If part of the bytes were written and lld returned + * scsi_in()->resid and/or scsi_out()->resid this information will be left + * in req->data_len and req->next_rq->data_len. The upper-layer driver can + * decide what to do with this information. + */ +void scsi_end_bidi_request(struct scsi_cmnd *cmd) { - if (cmd->use_sg) - scsi_free_sgtable(cmd); + struct request *req = cmd->request; + unsigned int dlen = req->data_len; + unsigned int next_dlen = req->next_rq->data_len; + + req->data_len = scsi_out(cmd)->resid; + req->next_rq->data_len = scsi_in(cmd)->resid; + + /* The req and req->next_rq have not been completed */ + BUG_ON(blk_end_bidi_request(req, 0, dlen, next_dlen)); + + scsi_release_buffers(cmd); /* - * Zero these out. They now point to freed memory, and it is - * dangerous to hang onto the pointers. + * This will goose the queue request function at the end, so we don't + * need to worry about launching another command. */ - cmd->request_buffer = NULL; - cmd->request_bufflen = 0; + scsi_next_command(cmd); } /* @@ -832,7 +837,7 @@ static void scsi_release_buffers(struct scsi_cmnd *cmd) void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes) { int result = cmd->result; - int this_count = cmd->request_bufflen; + int this_count = scsi_bufflen(cmd); struct request_queue *q = cmd->device->request_queue; struct request *req = cmd->request; int clear_errors = 1; @@ -840,8 +845,6 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes) int sense_valid = 0; int sense_deferred = 0; - scsi_release_buffers(cmd); - if (result) { sense_valid = scsi_command_normalize_sense(cmd, &sshdr); if (sense_valid) @@ -864,9 +867,17 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes) req->sense_len = len; } } - req->data_len = cmd->resid; + if (scsi_bidi_cmnd(cmd)) { + /* will also release_buffers */ + scsi_end_bidi_request(cmd); + return; + } + req->data_len = scsi_get_resid(cmd); } + BUG_ON(blk_bidi_rq(req)); /* bidi not support for !blk_pc_request yet */ + scsi_release_buffers(cmd); + /* * Next deal with any sectors which we were able to correctly * handle. @@ -874,7 +885,6 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes) SCSI_LOG_HLCOMPLETE(1, printk("%ld sectors total, " "%d bytes done.\n", req->nr_sectors, good_bytes)); - SCSI_LOG_HLCOMPLETE(1, printk("use_sg is %d\n", cmd->use_sg)); if (clear_errors) req->errors = 0; @@ -991,52 +1001,80 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes) scsi_end_request(cmd, -EIO, this_count, !result); } -/* - * Function: scsi_init_io() - * - * Purpose: SCSI I/O initialize function. - * - * Arguments: cmd - Command descriptor we wish to initialize - * - * Returns: 0 on success - * BLKPREP_DEFER if the failure is retryable - */ -static int scsi_init_io(struct scsi_cmnd *cmd) +static int scsi_init_sgtable(struct request *req, struct scsi_data_buffer *sdb, + gfp_t gfp_mask) { - struct request *req = cmd->request; - int count; - - /* - * We used to not use scatter-gather for single segment request, - * but now we do (it makes highmem I/O easier to support without - * kmapping pages) - */ - cmd->use_sg = req->nr_phys_segments; + int count; /* * If sg table allocation fails, requeue request later. */ - if (unlikely(scsi_alloc_sgtable(cmd, GFP_ATOMIC))) { - scsi_unprep_request(req); + if (unlikely(scsi_alloc_sgtable(sdb, req->nr_phys_segments, + gfp_mask))) { return BLKPREP_DEFER; } req->buffer = NULL; if (blk_pc_request(req)) - cmd->request_bufflen = req->data_len; + sdb->length = req->data_len; else - cmd->request_bufflen = req->nr_sectors << 9; + sdb->length = req->nr_sectors << 9; /* * Next, walk the list, and fill in the addresses and sizes of * each segment. */ - count = blk_rq_map_sg(req->q, req, cmd->request_buffer); - BUG_ON(count > cmd->use_sg); - cmd->use_sg = count; + count = blk_rq_map_sg(req->q, req, sdb->table.sgl); + BUG_ON(count > sdb->table.nents); + sdb->table.nents = count; return BLKPREP_OK; } +/* + * Function: scsi_init_io() + * + * Purpose: SCSI I/O initialize function. + * + * Arguments: cmd - Command descriptor we wish to initialize + * + * Returns: 0 on success + * BLKPREP_DEFER if the failure is retryable + * BLKPREP_KILL if the failure is fatal + */ +int scsi_init_io(struct scsi_cmnd *cmd, gfp_t gfp_mask) +{ + int error = scsi_init_sgtable(cmd->request, &cmd->sdb, gfp_mask); + if (error) + goto err_exit; + + if (blk_bidi_rq(cmd->request)) { + struct scsi_data_buffer *bidi_sdb = kmem_cache_zalloc( + scsi_bidi_sdb_cache, GFP_ATOMIC); + if (!bidi_sdb) { + error = BLKPREP_DEFER; + goto err_exit; + } + + cmd->request->next_rq->special = bidi_sdb; + error = scsi_init_sgtable(cmd->request->next_rq, bidi_sdb, + GFP_ATOMIC); + if (error) + goto err_exit; + } + + return BLKPREP_OK ; + +err_exit: + scsi_release_buffers(cmd); + if (error == BLKPREP_KILL) + scsi_put_command(cmd); + else /* BLKPREP_DEFER */ + scsi_unprep_request(cmd->request); + + return error; +} +EXPORT_SYMBOL(scsi_init_io); + static struct scsi_cmnd *scsi_get_cmd_from_req(struct scsi_device *sdev, struct request *req) { @@ -1081,16 +1119,14 @@ int scsi_setup_blk_pc_cmnd(struct scsi_device *sdev, struct request *req) BUG_ON(!req->nr_phys_segments); - ret = scsi_init_io(cmd); + ret = scsi_init_io(cmd, GFP_ATOMIC); if (unlikely(ret)) return ret; } else { BUG_ON(req->data_len); BUG_ON(req->data); - cmd->request_bufflen = 0; - cmd->request_buffer = NULL; - cmd->use_sg = 0; + memset(&cmd->sdb, 0, sizeof(cmd->sdb)); req->buffer = NULL; } @@ -1132,7 +1168,7 @@ int scsi_setup_fs_cmnd(struct scsi_device *sdev, struct request *req) if (unlikely(!cmd)) return BLKPREP_DEFER; - return scsi_init_io(cmd); + return scsi_init_io(cmd, GFP_ATOMIC); } EXPORT_SYMBOL(scsi_setup_fs_cmnd); @@ -1542,20 +1578,7 @@ struct request_queue *__scsi_alloc_queue(struct Scsi_Host *shost, * this limit is imposed by hardware restrictions */ blk_queue_max_hw_segments(q, shost->sg_tablesize); - - /* - * In the future, sg chaining support will be mandatory and this - * ifdef can then go away. Right now we don't have all archs - * converted, so better keep it safe. - */ -#ifdef ARCH_HAS_SG_CHAIN - if (shost->use_sg_chaining) - blk_queue_max_phys_segments(q, SCSI_MAX_SG_CHAIN_SEGMENTS); - else - blk_queue_max_phys_segments(q, SCSI_MAX_SG_SEGMENTS); -#else - blk_queue_max_phys_segments(q, SCSI_MAX_SG_SEGMENTS); -#endif + blk_queue_max_phys_segments(q, SCSI_MAX_SG_CHAIN_SEGMENTS); blk_queue_max_sectors(q, shost->max_sectors); blk_queue_bounce_limit(q, scsi_calculate_bounce_limit(shost)); @@ -1654,6 +1677,14 @@ int __init scsi_init_queue(void) return -ENOMEM; } + scsi_bidi_sdb_cache = kmem_cache_create("scsi_bidi_sdb", + sizeof(struct scsi_data_buffer), + 0, 0, NULL); + if (!scsi_bidi_sdb_cache) { + printk(KERN_ERR "SCSI: can't init scsi bidi sdb cache\n"); + goto cleanup_io_context; + } + for (i = 0; i < SG_MEMPOOL_NR; i++) { struct scsi_host_sg_pool *sgp = scsi_sg_pools + i; int size = sgp->size * sizeof(struct scatterlist); @@ -1663,6 +1694,7 @@ int __init scsi_init_queue(void) if (!sgp->slab) { printk(KERN_ERR "SCSI: can't init sg slab %s\n", sgp->name); + goto cleanup_bidi_sdb; } sgp->pool = mempool_create_slab_pool(SG_MEMPOOL_SIZE, @@ -1670,10 +1702,25 @@ int __init scsi_init_queue(void) if (!sgp->pool) { printk(KERN_ERR "SCSI: can't init sg mempool %s\n", sgp->name); + goto cleanup_bidi_sdb; } } return 0; + +cleanup_bidi_sdb: + for (i = 0; i < SG_MEMPOOL_NR; i++) { + struct scsi_host_sg_pool *sgp = scsi_sg_pools + i; + if (sgp->pool) + mempool_destroy(sgp->pool); + if (sgp->slab) + kmem_cache_destroy(sgp->slab); + } + kmem_cache_destroy(scsi_bidi_sdb_cache); +cleanup_io_context: + kmem_cache_destroy(scsi_io_context_cache); + + return -ENOMEM; } void scsi_exit_queue(void) @@ -1681,6 +1728,7 @@ void scsi_exit_queue(void) int i; kmem_cache_destroy(scsi_io_context_cache); + kmem_cache_destroy(scsi_bidi_sdb_cache); for (i = 0; i < SG_MEMPOOL_NR; i++) { struct scsi_host_sg_pool *sgp = scsi_sg_pools + i; diff --git a/drivers/scsi/scsi_tgt_lib.c b/drivers/scsi/scsi_tgt_lib.c index 01e03f3f6ffa..91630baea532 100644 --- a/drivers/scsi/scsi_tgt_lib.c +++ b/drivers/scsi/scsi_tgt_lib.c @@ -331,8 +331,7 @@ static void scsi_tgt_cmd_done(struct scsi_cmnd *cmd) scsi_tgt_uspace_send_status(cmd, tcmd->itn_id, tcmd->tag); - if (scsi_sglist(cmd)) - scsi_free_sgtable(cmd); + scsi_release_buffers(cmd); queue_work(scsi_tgtd, &tcmd->work); } @@ -353,25 +352,6 @@ static int scsi_tgt_transfer_response(struct scsi_cmnd *cmd) return 0; } -static int scsi_tgt_init_cmd(struct scsi_cmnd *cmd, gfp_t gfp_mask) -{ - struct request *rq = cmd->request; - int count; - - cmd->use_sg = rq->nr_phys_segments; - if (scsi_alloc_sgtable(cmd, gfp_mask)) - return -ENOMEM; - - cmd->request_bufflen = rq->data_len; - - dprintk("cmd %p cnt %d %lu\n", cmd, scsi_sg_count(cmd), - rq_data_dir(rq)); - count = blk_rq_map_sg(rq->q, rq, scsi_sglist(cmd)); - BUG_ON(count > cmd->use_sg); - cmd->use_sg = count; - return 0; -} - /* TODO: test this crap and replace bio_map_user with new interface maybe */ static int scsi_map_user_pages(struct scsi_tgt_cmd *tcmd, struct scsi_cmnd *cmd, unsigned long uaddr, unsigned int len, int rw) @@ -397,9 +377,11 @@ static int scsi_map_user_pages(struct scsi_tgt_cmd *tcmd, struct scsi_cmnd *cmd, } tcmd->bio = rq->bio; - err = scsi_tgt_init_cmd(cmd, GFP_KERNEL); - if (err) + err = scsi_init_io(cmd, GFP_KERNEL); + if (err) { + scsi_release_buffers(cmd); goto unmap_rq; + } return 0; diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index 24eba3118b5a..51a5557f42dd 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -519,7 +519,7 @@ static int sd_prep_fn(struct request_queue *q, struct request *rq) SCpnt->cmnd[4] = (unsigned char) this_count; SCpnt->cmnd[5] = 0; } - SCpnt->request_bufflen = this_count * sdp->sector_size; + SCpnt->sdb.length = this_count * sdp->sector_size; /* * We shouldn't disconnect in the middle of a sector, so with a dumb @@ -926,7 +926,7 @@ static struct block_device_operations sd_fops = { static int sd_done(struct scsi_cmnd *SCpnt) { int result = SCpnt->result; - unsigned int xfer_size = SCpnt->request_bufflen; + unsigned int xfer_size = scsi_bufflen(SCpnt); unsigned int good_bytes = result ? 0 : xfer_size; u64 start_lba = SCpnt->request->sector; u64 bad_lba; diff --git a/drivers/scsi/sgiwd93.c b/drivers/scsi/sgiwd93.c index d4ebe8c67ba9..26cfc56c7091 100644 --- a/drivers/scsi/sgiwd93.c +++ b/drivers/scsi/sgiwd93.c @@ -33,10 +33,9 @@ struct ip22_hostdata { struct WD33C93_hostdata wh; - struct hpc_data { - dma_addr_t dma; - void *cpu; - } hd; + dma_addr_t dma; + void *cpu; + struct device *dev; }; #define host_to_hostdata(host) ((struct ip22_hostdata *)((host)->hostdata)) @@ -46,6 +45,11 @@ struct hpc_chunk { u32 _padding; /* align to quadword boundary */ }; +/* space for hpc dma descriptors */ +#define HPC_DMA_SIZE PAGE_SIZE + +#define DMA_DIR(d) ((d == DATA_OUT_DIR) ? DMA_TO_DEVICE : DMA_FROM_DEVICE) + static irqreturn_t sgiwd93_intr(int irq, void *dev_id) { struct Scsi_Host * host = dev_id; @@ -59,15 +63,17 @@ static irqreturn_t sgiwd93_intr(int irq, void *dev_id) } static inline -void fill_hpc_entries(struct hpc_chunk *hcp, struct scsi_cmnd *cmd, int datainp) +void fill_hpc_entries(struct ip22_hostdata *hd, struct scsi_cmnd *cmd, int din) { unsigned long len = cmd->SCp.this_residual; void *addr = cmd->SCp.ptr; dma_addr_t physaddr; unsigned long count; + struct hpc_chunk *hcp; - physaddr = dma_map_single(NULL, addr, len, cmd->sc_data_direction); + physaddr = dma_map_single(hd->dev, addr, len, DMA_DIR(din)); cmd->SCp.dma_handle = physaddr; + hcp = hd->cpu; while (len) { /* @@ -89,6 +95,9 @@ void fill_hpc_entries(struct hpc_chunk *hcp, struct scsi_cmnd *cmd, int datainp) */ hcp->desc.pbuf = 0; hcp->desc.cntinfo = HPCDMA_EOX; + dma_cache_sync(hd->dev, hd->cpu, + (unsigned long)(hcp + 1) - (unsigned long)hd->cpu, + DMA_TO_DEVICE); } static int dma_setup(struct scsi_cmnd *cmd, int datainp) @@ -96,9 +105,8 @@ static int dma_setup(struct scsi_cmnd *cmd, int datainp) struct ip22_hostdata *hdata = host_to_hostdata(cmd->device->host); struct hpc3_scsiregs *hregs = (struct hpc3_scsiregs *) cmd->device->host->base; - struct hpc_chunk *hcp = (struct hpc_chunk *) hdata->hd.cpu; - pr_debug("dma_setup: datainp<%d> hcp<%p> ", datainp, hcp); + pr_debug("dma_setup: datainp<%d> hcp<%p> ", datainp, hdata->cpu); hdata->wh.dma_dir = datainp; @@ -111,12 +119,12 @@ static int dma_setup(struct scsi_cmnd *cmd, int datainp) if (cmd->SCp.ptr == NULL || cmd->SCp.this_residual == 0) return 1; - fill_hpc_entries(hcp, cmd, datainp); + fill_hpc_entries(hdata, cmd, datainp); pr_debug(" HPCGO\n"); /* Start up the HPC. */ - hregs->ndptr = hdata->hd.dma; + hregs->ndptr = hdata->dma; if (datainp) hregs->ctrl = HPC3_SCTRL_ACTIVE; else @@ -134,6 +142,9 @@ static void dma_stop(struct Scsi_Host *instance, struct scsi_cmnd *SCpnt, if (!SCpnt) return; + if (SCpnt->SCp.ptr == NULL || SCpnt->SCp.this_residual == 0) + return; + hregs = (struct hpc3_scsiregs *) SCpnt->device->host->base; pr_debug("dma_stop: status<%d> ", status); @@ -145,8 +156,9 @@ static void dma_stop(struct Scsi_Host *instance, struct scsi_cmnd *SCpnt, barrier(); } hregs->ctrl = 0; - dma_unmap_single(NULL, SCpnt->SCp.dma_handle, SCpnt->SCp.this_residual, - SCpnt->sc_data_direction); + dma_unmap_single(hdata->dev, SCpnt->SCp.dma_handle, + SCpnt->SCp.this_residual, + DMA_DIR(hdata->wh.dma_dir)); pr_debug("\n"); } @@ -161,22 +173,23 @@ void sgiwd93_reset(unsigned long base) } EXPORT_SYMBOL_GPL(sgiwd93_reset); -static inline void init_hpc_chain(struct hpc_data *hd) +static inline void init_hpc_chain(struct ip22_hostdata *hdata) { - struct hpc_chunk *hcp = (struct hpc_chunk *) hd->cpu; - struct hpc_chunk *dma = (struct hpc_chunk *) hd->dma; + struct hpc_chunk *hcp = (struct hpc_chunk *)hdata->cpu; + dma_addr_t dma = hdata->dma; unsigned long start, end; start = (unsigned long) hcp; - end = start + PAGE_SIZE; + end = start + HPC_DMA_SIZE; while (start < end) { - hcp->desc.pnext = (u32) (dma + 1); + hcp->desc.pnext = (u32) (dma + sizeof(struct hpc_chunk)); hcp->desc.cntinfo = HPCDMA_EOX; - hcp++; dma++; + hcp++; + dma += sizeof(struct hpc_chunk); start += sizeof(struct hpc_chunk); }; hcp--; - hcp->desc.pnext = hd->dma; + hcp->desc.pnext = hdata->dma; } static int sgiwd93_bus_reset(struct scsi_cmnd *cmd) @@ -235,16 +248,17 @@ static int __init sgiwd93_probe(struct platform_device *pdev) host->irq = irq; hdata = host_to_hostdata(host); - hdata->hd.cpu = dma_alloc_coherent(&pdev->dev, PAGE_SIZE, - &hdata->hd.dma, GFP_KERNEL); - if (!hdata->hd.cpu) { + hdata->dev = &pdev->dev; + hdata->cpu = dma_alloc_noncoherent(&pdev->dev, HPC_DMA_SIZE, + &hdata->dma, GFP_KERNEL); + if (!hdata->cpu) { printk(KERN_WARNING "sgiwd93: Could not allocate memory for " "host %d buffer.\n", unit); err = -ENOMEM; goto out_put; } - init_hpc_chain(&hdata->hd); + init_hpc_chain(hdata); regs.SASR = wdregs + 3; regs.SCMD = wdregs + 7; @@ -274,7 +288,7 @@ static int __init sgiwd93_probe(struct platform_device *pdev) out_irq: free_irq(irq, host); out_free: - dma_free_coherent(NULL, PAGE_SIZE, hdata->hd.cpu, hdata->hd.dma); + dma_free_noncoherent(&pdev->dev, HPC_DMA_SIZE, hdata->cpu, hdata->dma); out_put: scsi_host_put(host); out: @@ -290,7 +304,7 @@ static void __exit sgiwd93_remove(struct platform_device *pdev) scsi_remove_host(host); free_irq(pd->irq, host); - dma_free_coherent(&pdev->dev, PAGE_SIZE, hdata->hd.cpu, hdata->hd.dma); + dma_free_noncoherent(&pdev->dev, HPC_DMA_SIZE, hdata->cpu, hdata->dma); scsi_host_put(host); } diff --git a/drivers/scsi/sr.c b/drivers/scsi/sr.c index 1fcee16fa36d..50ba49250203 100644 --- a/drivers/scsi/sr.c +++ b/drivers/scsi/sr.c @@ -231,7 +231,7 @@ out: static int sr_done(struct scsi_cmnd *SCpnt) { int result = SCpnt->result; - int this_count = SCpnt->request_bufflen; + int this_count = scsi_bufflen(SCpnt); int good_bytes = (result == 0 ? this_count : 0); int block_sectors = 0; long error_sector; @@ -379,17 +379,18 @@ static int sr_prep_fn(struct request_queue *q, struct request *rq) } { - struct scatterlist *sg = SCpnt->request_buffer; - int i, size = 0; - for (i = 0; i < SCpnt->use_sg; i++) - size += sg[i].length; + struct scatterlist *sg; + int i, size = 0, sg_count = scsi_sg_count(SCpnt); - if (size != SCpnt->request_bufflen && SCpnt->use_sg) { + scsi_for_each_sg(SCpnt, sg, sg_count, i) + size += sg->length; + + if (size != scsi_bufflen(SCpnt)) { scmd_printk(KERN_ERR, SCpnt, "mismatch count %d, bytes %d\n", - size, SCpnt->request_bufflen); - if (SCpnt->request_bufflen > size) - SCpnt->request_bufflen = size; + size, scsi_bufflen(SCpnt)); + if (scsi_bufflen(SCpnt) > size) + SCpnt->sdb.length = size; } } @@ -397,12 +398,12 @@ static int sr_prep_fn(struct request_queue *q, struct request *rq) * request doesn't start on hw block boundary, add scatter pads */ if (((unsigned int)rq->sector % (s_size >> 9)) || - (SCpnt->request_bufflen % s_size)) { + (scsi_bufflen(SCpnt) % s_size)) { scmd_printk(KERN_NOTICE, SCpnt, "unaligned transfer\n"); goto out; } - this_count = (SCpnt->request_bufflen >> 9) / (s_size >> 9); + this_count = (scsi_bufflen(SCpnt) >> 9) / (s_size >> 9); SCSI_LOG_HLQUEUE(2, printk("%s : %s %d/%ld 512 byte blocks.\n", @@ -416,7 +417,7 @@ static int sr_prep_fn(struct request_queue *q, struct request *rq) if (this_count > 0xffff) { this_count = 0xffff; - SCpnt->request_bufflen = this_count * s_size; + SCpnt->sdb.length = this_count * s_size; } SCpnt->cmnd[2] = (unsigned char) (block >> 24) & 0xff; diff --git a/drivers/scsi/stex.c b/drivers/scsi/stex.c index e3fab3a6aed7..72f6d8015358 100644 --- a/drivers/scsi/stex.c +++ b/drivers/scsi/stex.c @@ -1123,7 +1123,6 @@ static struct scsi_host_template driver_template = { .this_id = -1, .sg_tablesize = ST_MAX_SG, .cmd_per_lun = ST_CMD_PER_LUN, - .use_sg_chaining = ENABLE_SG_CHAINING, }; static int stex_set_dma_mask(struct pci_dev * pdev) diff --git a/drivers/scsi/sym53c416.c b/drivers/scsi/sym53c416.c index 1f6fd1680335..6325901e5093 100644 --- a/drivers/scsi/sym53c416.c +++ b/drivers/scsi/sym53c416.c @@ -840,6 +840,5 @@ static struct scsi_host_template driver_template = { .cmd_per_lun = 1, .unchecked_isa_dma = 1, .use_clustering = ENABLE_CLUSTERING, - .use_sg_chaining = ENABLE_SG_CHAINING, }; #include "scsi_module.c" diff --git a/drivers/scsi/sym53c8xx_2/sym_glue.c b/drivers/scsi/sym53c8xx_2/sym_glue.c index 21e926dcdab0..d39107b7669b 100644 --- a/drivers/scsi/sym53c8xx_2/sym_glue.c +++ b/drivers/scsi/sym53c8xx_2/sym_glue.c @@ -207,7 +207,7 @@ void sym_set_cam_result_error(struct sym_hcb *np, struct sym_ccb *cp, int resid) /* * Bounce back the sense data to user. */ - memset(&cmd->sense_buffer, 0, SCSI_SENSE_BUFFERSIZE); + memset(cmd->sense_buffer, 0, SCSI_SENSE_BUFFERSIZE); memcpy(cmd->sense_buffer, cp->sns_bbuf, min(SCSI_SENSE_BUFFERSIZE, SYM_SNS_BBUF_LEN)); #if 0 @@ -1681,7 +1681,6 @@ static struct scsi_host_template sym2_template = { .eh_host_reset_handler = sym53c8xx_eh_host_reset_handler, .this_id = 7, .use_clustering = ENABLE_CLUSTERING, - .use_sg_chaining = ENABLE_SG_CHAINING, .max_sectors = 0xFFFF, #ifdef SYM_LINUX_PROC_INFO_SUPPORT .proc_info = sym53c8xx_proc_info, diff --git a/drivers/scsi/u14-34f.c b/drivers/scsi/u14-34f.c index 4bc5407f9695..662c00451be4 100644 --- a/drivers/scsi/u14-34f.c +++ b/drivers/scsi/u14-34f.c @@ -451,7 +451,6 @@ static struct scsi_host_template driver_template = { .this_id = 7, .unchecked_isa_dma = 1, .use_clustering = ENABLE_CLUSTERING, - .use_sg_chaining = ENABLE_SG_CHAINING, }; #if !defined(__BIG_ENDIAN_BITFIELD) && !defined(__LITTLE_ENDIAN_BITFIELD) diff --git a/drivers/scsi/ultrastor.c b/drivers/scsi/ultrastor.c index 75eca6b22db5..f385dce8dfbe 100644 --- a/drivers/scsi/ultrastor.c +++ b/drivers/scsi/ultrastor.c @@ -1204,6 +1204,5 @@ static struct scsi_host_template driver_template = { .cmd_per_lun = ULTRASTOR_MAX_CMDS_PER_LUN, .unchecked_isa_dma = 1, .use_clustering = ENABLE_CLUSTERING, - .use_sg_chaining = ENABLE_SG_CHAINING, }; #include "scsi_module.c" diff --git a/drivers/scsi/wd7000.c b/drivers/scsi/wd7000.c index b4304ae78527..c975c01b3a02 100644 --- a/drivers/scsi/wd7000.c +++ b/drivers/scsi/wd7000.c @@ -1671,7 +1671,6 @@ static struct scsi_host_template driver_template = { .cmd_per_lun = 1, .unchecked_isa_dma = 1, .use_clustering = ENABLE_CLUSTERING, - .use_sg_chaining = ENABLE_SG_CHAINING, }; #include "scsi_module.c" diff --git a/drivers/usb/storage/isd200.c b/drivers/usb/storage/isd200.c index 178e8c2a8a2f..0db488624ab1 100644 --- a/drivers/usb/storage/isd200.c +++ b/drivers/usb/storage/isd200.c @@ -415,14 +415,14 @@ static void isd200_set_srb(struct isd200_info *info, sg_init_one(&info->sg, buff, bufflen); srb->sc_data_direction = dir; - srb->request_buffer = buff ? &info->sg : NULL; - srb->request_bufflen = bufflen; - srb->use_sg = buff ? 1 : 0; + srb->sdb.table.sgl = buff ? &info->sg : NULL; + srb->sdb.length = bufflen; + srb->sdb.table.nents = buff ? 1 : 0; } static void isd200_srb_set_bufflen(struct scsi_cmnd *srb, unsigned bufflen) { - srb->request_bufflen = bufflen; + srb->sdb.length = bufflen; } diff --git a/drivers/video/vermilion/vermilion.c b/drivers/video/vermilion/vermilion.c index c31f549ebea0..1c656667b937 100644 --- a/drivers/video/vermilion/vermilion.c +++ b/drivers/video/vermilion/vermilion.c @@ -88,9 +88,7 @@ static int vmlfb_alloc_vram_area(struct vram_area *va, unsigned max_order, { gfp_t flags; unsigned long i; - pgprot_t wc_pageprot; - wc_pageprot = PAGE_KERNEL_NOCACHE; max_order++; do { /* @@ -126,14 +124,8 @@ static int vmlfb_alloc_vram_area(struct vram_area *va, unsigned max_order, /* * Change caching policy of the linear kernel map to avoid * mapping type conflicts with user-space mappings. - * The first global_flush_tlb() is really only there to do a global - * wbinvd(). */ - - global_flush_tlb(); - change_page_attr(virt_to_page(va->logical), va->size >> PAGE_SHIFT, - wc_pageprot); - global_flush_tlb(); + set_pages_uc(virt_to_page(va->logical), va->size >> PAGE_SHIFT); printk(KERN_DEBUG MODULE_NAME ": Allocated %ld bytes vram area at 0x%08lx\n", @@ -157,9 +149,8 @@ static void vmlfb_free_vram_area(struct vram_area *va) * Reset the linear kernel map caching policy. */ - change_page_attr(virt_to_page(va->logical), - va->size >> PAGE_SHIFT, PAGE_KERNEL); - global_flush_tlb(); + set_pages_wb(virt_to_page(va->logical), + va->size >> PAGE_SHIFT); /* * Decrease the usage count on the pages we've used |