diff options
Diffstat (limited to 'drivers/lguest')
| -rw-r--r-- | drivers/lguest/Kconfig | 2 | ||||
| -rw-r--r-- | drivers/lguest/core.c | 1 | ||||
| -rw-r--r-- | drivers/lguest/interrupts_and_traps.c | 24 | ||||
| -rw-r--r-- | drivers/lguest/lg.h | 1 | ||||
| -rw-r--r-- | drivers/lguest/lguest_device.c | 39 | ||||
| -rw-r--r-- | drivers/lguest/x86/core.c | 23 |
6 files changed, 51 insertions, 39 deletions
diff --git a/drivers/lguest/Kconfig b/drivers/lguest/Kconfig index 6b8dbb9ba73..76f2b36881c 100644 --- a/drivers/lguest/Kconfig +++ b/drivers/lguest/Kconfig @@ -1,6 +1,6 @@ config LGUEST tristate "Linux hypervisor example code" - depends on X86_32 && EXPERIMENTAL && !X86_PAE && FUTEX && !(X86_VISWS || X86_VOYAGER) + depends on X86_32 && EXPERIMENTAL && !X86_PAE && FUTEX && !X86_VOYAGER select HVC_DRIVER ---help--- This is a very simple module which allows you to run diff --git a/drivers/lguest/core.c b/drivers/lguest/core.c index 5eea4356d70..90663e01a56 100644 --- a/drivers/lguest/core.c +++ b/drivers/lguest/core.c @@ -135,6 +135,7 @@ static void unmap_switcher(void) /* Now we just need to free the pages we copied the switcher into */ for (i = 0; i < TOTAL_SWITCHER_PAGES; i++) __free_pages(switcher_page[i], 0); + kfree(switcher_page); } /*H:032 diff --git a/drivers/lguest/interrupts_and_traps.c b/drivers/lguest/interrupts_and_traps.c index 0414ddf8758..a1039068f95 100644 --- a/drivers/lguest/interrupts_and_traps.c +++ b/drivers/lguest/interrupts_and_traps.c @@ -406,7 +406,8 @@ void load_guest_idt_entry(struct lg_cpu *cpu, unsigned int num, u32 lo, u32 hi) * deliver_trap() to bounce it back into the Guest. */ static void default_idt_entry(struct desc_struct *idt, int trap, - const unsigned long handler) + const unsigned long handler, + const struct desc_struct *base) { /* A present interrupt gate. */ u32 flags = 0x8e00; @@ -415,6 +416,10 @@ static void default_idt_entry(struct desc_struct *idt, * the Guest to use the "int" instruction to trigger it. */ if (trap == LGUEST_TRAP_ENTRY) flags |= (GUEST_PL << 13); + else if (base) + /* Copy priv. level from what Guest asked for. This allows + * debug (int 3) traps from Guest userspace, for example. */ + flags |= (base->b & 0x6000); /* Now pack it into the IDT entry in its weird format. */ idt->a = (LGUEST_CS<<16) | (handler&0x0000FFFF); @@ -428,7 +433,7 @@ void setup_default_idt_entries(struct lguest_ro_state *state, unsigned int i; for (i = 0; i < ARRAY_SIZE(state->guest_idt); i++) - default_idt_entry(&state->guest_idt[i], i, def[i]); + default_idt_entry(&state->guest_idt[i], i, def[i], NULL); } /*H:240 We don't use the IDT entries in the "struct lguest" directly, instead @@ -442,6 +447,8 @@ void copy_traps(const struct lg_cpu *cpu, struct desc_struct *idt, /* 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(cpu->arch.idt); i++) { + const struct desc_struct *gidt = &cpu->arch.idt[i]; + /* If no Guest can ever override this trap, leave it alone. */ if (!direct_trap(i)) continue; @@ -449,12 +456,15 @@ void copy_traps(const struct lg_cpu *cpu, struct desc_struct *idt, /* Only trap gates (type 15) can go direct to the Guest. * 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(cpu->arch.idt[i].a, cpu->arch.idt[i].b) == 0xF) - idt[i] = cpu->arch.idt[i]; + * entries (type 0x0) also can't go direct, of course. + * + * If it can't go direct, we still need to copy the priv. level: + * they might want to give userspace access to a software + * interrupt. */ + if (idt_type(gidt->a, gidt->b) == 0xF) + idt[i] = *gidt; else - /* Reset it to the default. */ - default_idt_entry(&idt[i], i, def[i]); + default_idt_entry(&idt[i], i, def[i], gidt); } } diff --git a/drivers/lguest/lg.h b/drivers/lguest/lg.h index 005bd045d2e..5faefeaf679 100644 --- a/drivers/lguest/lg.h +++ b/drivers/lguest/lg.h @@ -136,7 +136,6 @@ int run_guest(struct lg_cpu *cpu, unsigned long __user *user); * first step in the migration to the kernel types. pte_pfn is already defined * in the kernel. */ #define pgd_flags(x) (pgd_val(x) & ~PAGE_MASK) -#define pte_flags(x) (pte_val(x) & ~PAGE_MASK) #define pgd_pfn(x) (pgd_val(x) >> PAGE_SHIFT) /* interrupts_and_traps.c: */ diff --git a/drivers/lguest/lguest_device.c b/drivers/lguest/lguest_device.c index 8080249957a..37344aaee22 100644 --- a/drivers/lguest/lguest_device.c +++ b/drivers/lguest/lguest_device.c @@ -20,14 +20,11 @@ /* The pointer to our (page) of device descriptions. */ static void *lguest_devices; -/* Unique numbering for lguest devices. */ -static unsigned int dev_index; - /* For Guests, device memory can be used as normal memory, so we cast away the * __iomem to quieten sparse. */ static inline void *lguest_map(unsigned long phys_addr, unsigned long pages) { - return (__force void *)ioremap(phys_addr, PAGE_SIZE*pages); + return (__force void *)ioremap_cache(phys_addr, PAGE_SIZE*pages); } static inline void lguest_unmap(void *addr) @@ -101,16 +98,20 @@ static u32 lg_get_features(struct virtio_device *vdev) return features; } -static void lg_set_features(struct virtio_device *vdev, u32 features) +static void lg_finalize_features(struct virtio_device *vdev) { - unsigned int i; + unsigned int i, bits; struct lguest_device_desc *desc = to_lgdev(vdev)->desc; /* Second half of bitmap is features we accept. */ u8 *out_features = lg_features(desc) + desc->feature_len; + /* Give virtio_ring a chance to accept features. */ + vring_transport_features(vdev); + memset(out_features, 0, desc->feature_len); - for (i = 0; i < min(desc->feature_len * 8, 32); i++) { - if (features & (1 << i)) + bits = min_t(unsigned, desc->feature_len, sizeof(vdev->features)) * 8; + for (i = 0; i < bits; i++) { + if (test_bit(i, vdev->features)) out_features[i / 8] |= (1 << (i % 8)); } } @@ -300,7 +301,7 @@ static void lg_del_vq(struct virtqueue *vq) /* The ops structure which hooks everything together. */ static struct virtio_config_ops lguest_config_ops = { .get_features = lg_get_features, - .set_features = lg_set_features, + .finalize_features = lg_finalize_features, .get = lg_get, .set = lg_set, .get_status = lg_get_status, @@ -325,8 +326,10 @@ static struct device lguest_root = { * As Andrew Tridgell says, "Untested code is buggy code". * * It's worth reading this carefully: we start with a pointer to the new device - * descriptor in the "lguest_devices" page. */ -static void add_lguest_device(struct lguest_device_desc *d) + * descriptor in the "lguest_devices" page, and the offset into the device + * descriptor page so we can uniquely identify it if things go badly wrong. */ +static void add_lguest_device(struct lguest_device_desc *d, + unsigned int offset) { struct lguest_device *ldev; @@ -334,18 +337,14 @@ static void add_lguest_device(struct lguest_device_desc *d) * it. */ ldev = kzalloc(sizeof(*ldev), GFP_KERNEL); if (!ldev) { - printk(KERN_EMERG "Cannot allocate lguest dev %u\n", - dev_index++); + printk(KERN_EMERG "Cannot allocate lguest dev %u type %u\n", + offset, d->type); return; } /* This devices' parent is the lguest/ dir. */ ldev->vdev.dev.parent = &lguest_root; /* We have a unique device index thanks to the dev_index counter. */ - ldev->vdev.index = dev_index++; - /* The device type comes straight from the descriptor. There's also a - * device vendor field in the virtio_device struct, which we leave as - * 0. */ ldev->vdev.id.device = d->type; /* We have a simple set of routines for querying the device's * configuration information and setting its status. */ @@ -357,8 +356,8 @@ static void add_lguest_device(struct lguest_device_desc *d) * virtio_device and calls device_register(). This makes the bus * infrastructure look for a matching driver. */ if (register_virtio_device(&ldev->vdev) != 0) { - printk(KERN_ERR "Failed to register lguest device %u\n", - ldev->vdev.index); + printk(KERN_ERR "Failed to register lguest dev %u type %u\n", + offset, d->type); kfree(ldev); } } @@ -379,7 +378,7 @@ static void scan_devices(void) break; printk("Device at %i has size %u\n", i, desc_size(d)); - add_lguest_device(d); + add_lguest_device(d, i); } } diff --git a/drivers/lguest/x86/core.c b/drivers/lguest/x86/core.c index 5126d5d9ea0..bf7942327bd 100644 --- a/drivers/lguest/x86/core.c +++ b/drivers/lguest/x86/core.c @@ -176,7 +176,7 @@ void lguest_arch_run_guest(struct lg_cpu *cpu) * we set it now, so we can trap and pass that trap to the Guest if it * uses the FPU. */ if (cpu->ts) - lguest_set_ts(); + unlazy_fpu(current); /* SYSENTER is an optimized way of doing system calls. We can't allow * it because it always jumps to privilege level 0. A normal Guest @@ -196,6 +196,10 @@ void lguest_arch_run_guest(struct lg_cpu *cpu) * trap made the switcher code come back, and an error code which some * traps set. */ + /* Restore SYSENTER if it's supposed to be on. */ + if (boot_cpu_has(X86_FEATURE_SEP)) + wrmsr(MSR_IA32_SYSENTER_CS, __KERNEL_CS, 0); + /* If the Guest page faulted, then the cr2 register will tell us the * bad virtual address. We have to grab this now, because once we * re-enable interrupts an interrupt could fault and thus overwrite @@ -203,13 +207,12 @@ void lguest_arch_run_guest(struct lg_cpu *cpu) 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. */ + * we have to restore the FPU it expects to see. + * math_state_restore() may sleep and we may even move off to + * a different CPU. So all the critical stuff should be done + * before this. */ else if (cpu->regs->trapnum == 7) math_state_restore(); - - /* Restore SYSENTER if it's supposed to be on. */ - if (boot_cpu_has(X86_FEATURE_SEP)) - wrmsr(MSR_IA32_SYSENTER_CS, __KERNEL_CS, 0); } /*H:130 Now we've examined the hypercall code; our Guest can make requests. @@ -475,9 +478,9 @@ void __init lguest_arch_host_init(void) cpu_had_pge = 1; /* adjust_pge is a helper function which sets or unsets the PGE * bit on its CPU, depending on the argument (0 == unset). */ - on_each_cpu(adjust_pge, (void *)0, 0, 1); + on_each_cpu(adjust_pge, (void *)0, 1); /* Turn off the feature in the global feature set. */ - clear_bit(X86_FEATURE_PGE, boot_cpu_data.x86_capability); + clear_cpu_cap(&boot_cpu_data, X86_FEATURE_PGE); } put_online_cpus(); }; @@ -488,9 +491,9 @@ void __exit lguest_arch_host_fini(void) /* If we had PGE before we started, turn it back on now. */ get_online_cpus(); if (cpu_had_pge) { - set_bit(X86_FEATURE_PGE, boot_cpu_data.x86_capability); + set_cpu_cap(&boot_cpu_data, X86_FEATURE_PGE); /* adjust_pge's argument "1" means set PGE. */ - on_each_cpu(adjust_pge, (void *)1, 0, 1); + on_each_cpu(adjust_pge, (void *)1, 1); } put_online_cpus(); } |