summaryrefslogtreecommitdiff
path: root/virt
diff options
context:
space:
mode:
Diffstat (limited to 'virt')
-rw-r--r--virt/kvm/arm/vgic.c744
-rw-r--r--virt/kvm/assigned-dev.c2
-rw-r--r--virt/kvm/async_pf.c4
-rw-r--r--virt/kvm/eventfd.c4
-rw-r--r--virt/kvm/ioapic.c46
-rw-r--r--virt/kvm/ioapic.h2
-rw-r--r--virt/kvm/iommu.c4
-rw-r--r--virt/kvm/kvm_main.c192
-rw-r--r--virt/kvm/vfio.c22
-rw-r--r--virt/kvm/vfio.h13
10 files changed, 782 insertions, 251 deletions
diff --git a/virt/kvm/arm/vgic.c b/virt/kvm/arm/vgic.c
index 73eba793b17f..862967852d5a 100644
--- a/virt/kvm/arm/vgic.c
+++ b/virt/kvm/arm/vgic.c
@@ -36,21 +36,22 @@
* How the whole thing works (courtesy of Christoffer Dall):
*
* - At any time, the dist->irq_pending_on_cpu is the oracle that knows if
- * something is pending
- * - VGIC pending interrupts are stored on the vgic.irq_state vgic
- * bitmap (this bitmap is updated by both user land ioctls and guest
- * mmio ops, and other in-kernel peripherals such as the
- * arch. timers) and indicate the 'wire' state.
+ * something is pending on the CPU interface.
+ * - Interrupts that are pending on the distributor are stored on the
+ * vgic.irq_pending vgic bitmap (this bitmap is updated by both user land
+ * ioctls and guest mmio ops, and other in-kernel peripherals such as the
+ * arch. timers).
* - Every time the bitmap changes, the irq_pending_on_cpu oracle is
* recalculated
* - To calculate the oracle, we need info for each cpu from
* compute_pending_for_cpu, which considers:
- * - PPI: dist->irq_state & dist->irq_enable
- * - SPI: dist->irq_state & dist->irq_enable & dist->irq_spi_target
- * - irq_spi_target is a 'formatted' version of the GICD_ICFGR
+ * - PPI: dist->irq_pending & dist->irq_enable
+ * - SPI: dist->irq_pending & dist->irq_enable & dist->irq_spi_target
+ * - irq_spi_target is a 'formatted' version of the GICD_ITARGETSRn
* registers, stored on each vcpu. We only keep one bit of
* information per interrupt, making sure that only one vcpu can
* accept the interrupt.
+ * - If any of the above state changes, we must recalculate the oracle.
* - The same is true when injecting an interrupt, except that we only
* consider a single interrupt at a time. The irq_spi_cpu array
* contains the target CPU for each SPI.
@@ -60,13 +61,18 @@
* the 'line' again. This is achieved as such:
*
* - When a level interrupt is moved onto a vcpu, the corresponding
- * bit in irq_active is set. As long as this bit is set, the line
+ * bit in irq_queued is set. As long as this bit is set, the line
* will be ignored for further interrupts. The interrupt is injected
* into the vcpu with the GICH_LR_EOI bit set (generate a
* maintenance interrupt on EOI).
* - When the interrupt is EOIed, the maintenance interrupt fires,
- * and clears the corresponding bit in irq_active. This allow the
+ * and clears the corresponding bit in irq_queued. This allows the
* interrupt line to be sampled again.
+ * - Note that level-triggered interrupts can also be set to pending from
+ * writes to GICD_ISPENDRn and lowering the external input line does not
+ * cause the interrupt to become inactive in such a situation.
+ * Conversely, writes to GICD_ICPENDRn do not cause the interrupt to become
+ * inactive as long as the external input line is held high.
*/
#define VGIC_ADDR_UNDEF (-1)
@@ -89,6 +95,7 @@ static void vgic_retire_disabled_irqs(struct kvm_vcpu *vcpu);
static void vgic_retire_lr(int lr_nr, int irq, struct kvm_vcpu *vcpu);
static void vgic_update_state(struct kvm *kvm);
static void vgic_kick_vcpus(struct kvm *kvm);
+static u8 *vgic_get_sgi_sources(struct vgic_dist *dist, int vcpu_id, int sgi);
static void vgic_dispatch_sgi(struct kvm_vcpu *vcpu, u32 reg);
static struct vgic_lr vgic_get_lr(const struct kvm_vcpu *vcpu, int lr);
static void vgic_set_lr(struct kvm_vcpu *vcpu, int lr, struct vgic_lr lr_desc);
@@ -99,10 +106,8 @@ static const struct vgic_ops *vgic_ops;
static const struct vgic_params *vgic;
/*
- * struct vgic_bitmap contains unions that provide two views of
- * the same data. In one case it is an array of registers of
- * u32's, and in the other case it is a bitmap of unsigned
- * longs.
+ * struct vgic_bitmap contains a bitmap made of unsigned longs, but
+ * extracts u32s out of them.
*
* This does not work on 64-bit BE systems, because the bitmap access
* will store two consecutive 32-bit words with the higher-addressed
@@ -118,23 +123,45 @@ static const struct vgic_params *vgic;
#define REG_OFFSET_SWIZZLE 0
#endif
+static int vgic_init_bitmap(struct vgic_bitmap *b, int nr_cpus, int nr_irqs)
+{
+ int nr_longs;
+
+ nr_longs = nr_cpus + BITS_TO_LONGS(nr_irqs - VGIC_NR_PRIVATE_IRQS);
+
+ b->private = kzalloc(sizeof(unsigned long) * nr_longs, GFP_KERNEL);
+ if (!b->private)
+ return -ENOMEM;
+
+ b->shared = b->private + nr_cpus;
+
+ return 0;
+}
+
+static void vgic_free_bitmap(struct vgic_bitmap *b)
+{
+ kfree(b->private);
+ b->private = NULL;
+ b->shared = NULL;
+}
+
static u32 *vgic_bitmap_get_reg(struct vgic_bitmap *x,
int cpuid, u32 offset)
{
offset >>= 2;
if (!offset)
- return x->percpu[cpuid].reg + (offset ^ REG_OFFSET_SWIZZLE);
+ return (u32 *)(x->private + cpuid) + REG_OFFSET_SWIZZLE;
else
- return x->shared.reg + ((offset - 1) ^ REG_OFFSET_SWIZZLE);
+ return (u32 *)(x->shared) + ((offset - 1) ^ REG_OFFSET_SWIZZLE);
}
static int vgic_bitmap_get_irq_val(struct vgic_bitmap *x,
int cpuid, int irq)
{
if (irq < VGIC_NR_PRIVATE_IRQS)
- return test_bit(irq, x->percpu[cpuid].reg_ul);
+ return test_bit(irq, x->private + cpuid);
- return test_bit(irq - VGIC_NR_PRIVATE_IRQS, x->shared.reg_ul);
+ return test_bit(irq - VGIC_NR_PRIVATE_IRQS, x->shared);
}
static void vgic_bitmap_set_irq_val(struct vgic_bitmap *x, int cpuid,
@@ -143,9 +170,9 @@ static void vgic_bitmap_set_irq_val(struct vgic_bitmap *x, int cpuid,
unsigned long *reg;
if (irq < VGIC_NR_PRIVATE_IRQS) {
- reg = x->percpu[cpuid].reg_ul;
+ reg = x->private + cpuid;
} else {
- reg = x->shared.reg_ul;
+ reg = x->shared;
irq -= VGIC_NR_PRIVATE_IRQS;
}
@@ -157,24 +184,49 @@ static void vgic_bitmap_set_irq_val(struct vgic_bitmap *x, int cpuid,
static unsigned long *vgic_bitmap_get_cpu_map(struct vgic_bitmap *x, int cpuid)
{
- if (unlikely(cpuid >= VGIC_MAX_CPUS))
- return NULL;
- return x->percpu[cpuid].reg_ul;
+ return x->private + cpuid;
}
static unsigned long *vgic_bitmap_get_shared_map(struct vgic_bitmap *x)
{
- return x->shared.reg_ul;
+ return x->shared;
+}
+
+static int vgic_init_bytemap(struct vgic_bytemap *x, int nr_cpus, int nr_irqs)
+{
+ int size;
+
+ size = nr_cpus * VGIC_NR_PRIVATE_IRQS;
+ size += nr_irqs - VGIC_NR_PRIVATE_IRQS;
+
+ x->private = kzalloc(size, GFP_KERNEL);
+ if (!x->private)
+ return -ENOMEM;
+
+ x->shared = x->private + nr_cpus * VGIC_NR_PRIVATE_IRQS / sizeof(u32);
+ return 0;
+}
+
+static void vgic_free_bytemap(struct vgic_bytemap *b)
+{
+ kfree(b->private);
+ b->private = NULL;
+ b->shared = NULL;
}
static u32 *vgic_bytemap_get_reg(struct vgic_bytemap *x, int cpuid, u32 offset)
{
- offset >>= 2;
- BUG_ON(offset > (VGIC_NR_IRQS / 4));
- if (offset < 8)
- return x->percpu[cpuid] + offset;
- else
- return x->shared + offset - 8;
+ u32 *reg;
+
+ if (offset < VGIC_NR_PRIVATE_IRQS) {
+ reg = x->private;
+ offset += cpuid * VGIC_NR_PRIVATE_IRQS;
+ } else {
+ reg = x->shared;
+ offset -= VGIC_NR_PRIVATE_IRQS;
+ }
+
+ return reg + (offset / sizeof(u32));
}
#define VGIC_CFG_LEVEL 0
@@ -196,46 +248,81 @@ static int vgic_irq_is_enabled(struct kvm_vcpu *vcpu, int irq)
return vgic_bitmap_get_irq_val(&dist->irq_enabled, vcpu->vcpu_id, irq);
}
-static int vgic_irq_is_active(struct kvm_vcpu *vcpu, int irq)
+static int vgic_irq_is_queued(struct kvm_vcpu *vcpu, int irq)
+{
+ struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
+
+ return vgic_bitmap_get_irq_val(&dist->irq_queued, vcpu->vcpu_id, irq);
+}
+
+static void vgic_irq_set_queued(struct kvm_vcpu *vcpu, int irq)
+{
+ struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
+
+ vgic_bitmap_set_irq_val(&dist->irq_queued, vcpu->vcpu_id, irq, 1);
+}
+
+static void vgic_irq_clear_queued(struct kvm_vcpu *vcpu, int irq)
+{
+ struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
+
+ vgic_bitmap_set_irq_val(&dist->irq_queued, vcpu->vcpu_id, irq, 0);
+}
+
+static int vgic_dist_irq_get_level(struct kvm_vcpu *vcpu, int irq)
{
struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
- return vgic_bitmap_get_irq_val(&dist->irq_active, vcpu->vcpu_id, irq);
+ return vgic_bitmap_get_irq_val(&dist->irq_level, vcpu->vcpu_id, irq);
}
-static void vgic_irq_set_active(struct kvm_vcpu *vcpu, int irq)
+static void vgic_dist_irq_set_level(struct kvm_vcpu *vcpu, int irq)
{
struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
- vgic_bitmap_set_irq_val(&dist->irq_active, vcpu->vcpu_id, irq, 1);
+ vgic_bitmap_set_irq_val(&dist->irq_level, vcpu->vcpu_id, irq, 1);
}
-static void vgic_irq_clear_active(struct kvm_vcpu *vcpu, int irq)
+static void vgic_dist_irq_clear_level(struct kvm_vcpu *vcpu, int irq)
{
struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
- vgic_bitmap_set_irq_val(&dist->irq_active, vcpu->vcpu_id, irq, 0);
+ vgic_bitmap_set_irq_val(&dist->irq_level, vcpu->vcpu_id, irq, 0);
+}
+
+static int vgic_dist_irq_soft_pend(struct kvm_vcpu *vcpu, int irq)
+{
+ struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
+
+ return vgic_bitmap_get_irq_val(&dist->irq_soft_pend, vcpu->vcpu_id, irq);
+}
+
+static void vgic_dist_irq_clear_soft_pend(struct kvm_vcpu *vcpu, int irq)
+{
+ struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
+
+ vgic_bitmap_set_irq_val(&dist->irq_soft_pend, vcpu->vcpu_id, irq, 0);
}
static int vgic_dist_irq_is_pending(struct kvm_vcpu *vcpu, int irq)
{
struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
- return vgic_bitmap_get_irq_val(&dist->irq_state, vcpu->vcpu_id, irq);
+ return vgic_bitmap_get_irq_val(&dist->irq_pending, vcpu->vcpu_id, irq);
}
-static void vgic_dist_irq_set(struct kvm_vcpu *vcpu, int irq)
+static void vgic_dist_irq_set_pending(struct kvm_vcpu *vcpu, int irq)
{
struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
- vgic_bitmap_set_irq_val(&dist->irq_state, vcpu->vcpu_id, irq, 1);
+ vgic_bitmap_set_irq_val(&dist->irq_pending, vcpu->vcpu_id, irq, 1);
}
-static void vgic_dist_irq_clear(struct kvm_vcpu *vcpu, int irq)
+static void vgic_dist_irq_clear_pending(struct kvm_vcpu *vcpu, int irq)
{
struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
- vgic_bitmap_set_irq_val(&dist->irq_state, vcpu->vcpu_id, irq, 0);
+ vgic_bitmap_set_irq_val(&dist->irq_pending, vcpu->vcpu_id, irq, 0);
}
static void vgic_cpu_irq_set(struct kvm_vcpu *vcpu, int irq)
@@ -256,6 +343,11 @@ static void vgic_cpu_irq_clear(struct kvm_vcpu *vcpu, int irq)
vcpu->arch.vgic_cpu.pending_shared);
}
+static bool vgic_can_sample_irq(struct kvm_vcpu *vcpu, int irq)
+{
+ return vgic_irq_is_edge(vcpu, irq) || !vgic_irq_is_queued(vcpu, irq);
+}
+
static u32 mmio_data_read(struct kvm_exit_mmio *mmio, u32 mask)
{
return le32_to_cpu(*((u32 *)mmio->data)) & mask;
@@ -347,7 +439,7 @@ static bool handle_mmio_misc(struct kvm_vcpu *vcpu,
case 4: /* GICD_TYPER */
reg = (atomic_read(&vcpu->kvm->online_vcpus) - 1) << 5;
- reg |= (VGIC_NR_IRQS >> 5) - 1;
+ reg |= (vcpu->kvm->arch.vgic.nr_irqs >> 5) - 1;
vgic_reg_access(mmio, &reg, word_offset,
ACCESS_READ_VALUE | ACCESS_WRITE_IGNORED);
break;
@@ -409,11 +501,33 @@ static bool handle_mmio_set_pending_reg(struct kvm_vcpu *vcpu,
struct kvm_exit_mmio *mmio,
phys_addr_t offset)
{
- u32 *reg = vgic_bitmap_get_reg(&vcpu->kvm->arch.vgic.irq_state,
- vcpu->vcpu_id, offset);
+ u32 *reg, orig;
+ u32 level_mask;
+ struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
+
+ reg = vgic_bitmap_get_reg(&dist->irq_cfg, vcpu->vcpu_id, offset);
+ level_mask = (~(*reg));
+
+ /* Mark both level and edge triggered irqs as pending */
+ reg = vgic_bitmap_get_reg(&dist->irq_pending, vcpu->vcpu_id, offset);
+ orig = *reg;
vgic_reg_access(mmio, reg, offset,
ACCESS_READ_VALUE | ACCESS_WRITE_SETBIT);
+
if (mmio->is_write) {
+ /* Set the soft-pending flag only for level-triggered irqs */
+ reg = vgic_bitmap_get_reg(&dist->irq_soft_pend,
+ vcpu->vcpu_id, offset);
+ vgic_reg_access(mmio, reg, offset,
+ ACCESS_READ_VALUE | ACCESS_WRITE_SETBIT);
+ *reg &= level_mask;
+
+ /* Ignore writes to SGIs */
+ if (offset < 2) {
+ *reg &= ~0xffff;
+ *reg |= orig & 0xffff;
+ }
+
vgic_update_state(vcpu->kvm);
return true;
}
@@ -425,11 +539,34 @@ static bool handle_mmio_clear_pending_reg(struct kvm_vcpu *vcpu,
struct kvm_exit_mmio *mmio,
phys_addr_t offset)
{
- u32 *reg = vgic_bitmap_get_reg(&vcpu->kvm->arch.vgic.irq_state,
- vcpu->vcpu_id, offset);
+ u32 *level_active;
+ u32 *reg, orig;
+ struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
+
+ reg = vgic_bitmap_get_reg(&dist->irq_pending, vcpu->vcpu_id, offset);
+ orig = *reg;
vgic_reg_access(mmio, reg, offset,
ACCESS_READ_VALUE | ACCESS_WRITE_CLEARBIT);
if (mmio->is_write) {
+ /* Re-set level triggered level-active interrupts */
+ level_active = vgic_bitmap_get_reg(&dist->irq_level,
+ vcpu->vcpu_id, offset);
+ reg = vgic_bitmap_get_reg(&dist->irq_pending,
+ vcpu->vcpu_id, offset);
+ *reg |= *level_active;
+
+ /* Ignore writes to SGIs */
+ if (offset < 2) {
+ *reg &= ~0xffff;
+ *reg |= orig & 0xffff;
+ }
+
+ /* Clear soft-pending flags */
+ reg = vgic_bitmap_get_reg(&dist->irq_soft_pend,
+ vcpu->vcpu_id, offset);
+ vgic_reg_access(mmio, reg, offset,
+ ACCESS_READ_VALUE | ACCESS_WRITE_CLEARBIT);
+
vgic_update_state(vcpu->kvm);
return true;
}
@@ -651,9 +788,9 @@ static void vgic_unqueue_irqs(struct kvm_vcpu *vcpu)
* is fine, then we are only setting a few bits that were
* already set.
*/
- vgic_dist_irq_set(vcpu, lr.irq);
+ vgic_dist_irq_set_pending(vcpu, lr.irq);
if (lr.irq < VGIC_NR_SGIS)
- dist->irq_sgi_sources[vcpu_id][lr.irq] |= 1 << lr.source;
+ *vgic_get_sgi_sources(dist, vcpu_id, lr.irq) |= 1 << lr.source;
lr.state &= ~LR_STATE_PENDING;
vgic_set_lr(vcpu, i, lr);
@@ -662,8 +799,10 @@ static void vgic_unqueue_irqs(struct kvm_vcpu *vcpu)
* active), then the LR does not hold any useful info and can
* be marked as free for other use.
*/
- if (!(lr.state & LR_STATE_MASK))
+ if (!(lr.state & LR_STATE_MASK)) {
vgic_retire_lr(i, lr.irq, vcpu);
+ vgic_irq_clear_queued(vcpu, lr.irq);
+ }
/* Finally update the VGIC state. */
vgic_update_state(vcpu->kvm);
@@ -677,7 +816,7 @@ static bool read_set_clear_sgi_pend_reg(struct kvm_vcpu *vcpu,
{
struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
int sgi;
- int min_sgi = (offset & ~0x3) * 4;
+ int min_sgi = (offset & ~0x3);
int max_sgi = min_sgi + 3;
int vcpu_id = vcpu->vcpu_id;
u32 reg = 0;
@@ -685,7 +824,7 @@ static bool read_set_clear_sgi_pend_reg(struct kvm_vcpu *vcpu,
/* Copy source SGIs from distributor side */
for (sgi = min_sgi; sgi <= max_sgi; sgi++) {
int shift = 8 * (sgi - min_sgi);
- reg |= (u32)dist->irq_sgi_sources[vcpu_id][sgi] << shift;
+ reg |= ((u32)*vgic_get_sgi_sources(dist, vcpu_id, sgi)) << shift;
}
mmio_data_write(mmio, ~0, reg);
@@ -698,7 +837,7 @@ static bool write_set_clear_sgi_pend_reg(struct kvm_vcpu *vcpu,
{
struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
int sgi;
- int min_sgi = (offset & ~0x3) * 4;
+ int min_sgi = (offset & ~0x3);
int max_sgi = min_sgi + 3;
int vcpu_id = vcpu->vcpu_id;
u32 reg;
@@ -709,14 +848,15 @@ static bool write_set_clear_sgi_pend_reg(struct kvm_vcpu *vcpu,
/* Clear pending SGIs on the distributor */
for (sgi = min_sgi; sgi <= max_sgi; sgi++) {
u8 mask = reg >> (8 * (sgi - min_sgi));
+ u8 *src = vgic_get_sgi_sources(dist, vcpu_id, sgi);
if (set) {
- if ((dist->irq_sgi_sources[vcpu_id][sgi] & mask) != mask)
+ if ((*src & mask) != mask)
updated = true;
- dist->irq_sgi_sources[vcpu_id][sgi] |= mask;
+ *src |= mask;
} else {
- if (dist->irq_sgi_sources[vcpu_id][sgi] & mask)
+ if (*src & mask)
updated = true;
- dist->irq_sgi_sources[vcpu_id][sgi] &= ~mask;
+ *src &= ~mask;
}
}
@@ -755,6 +895,7 @@ static bool handle_mmio_sgi_clear(struct kvm_vcpu *vcpu,
struct mmio_range {
phys_addr_t base;
unsigned long len;
+ int bits_per_irq;
bool (*handle_mmio)(struct kvm_vcpu *vcpu, struct kvm_exit_mmio *mmio,
phys_addr_t offset);
};
@@ -763,56 +904,67 @@ static const struct mmio_range vgic_dist_ranges[] = {
{
.base = GIC_DIST_CTRL,
.len = 12,
+ .bits_per_irq = 0,
.handle_mmio = handle_mmio_misc,
},
{
.base = GIC_DIST_IGROUP,
- .len = VGIC_NR_IRQS / 8,
+ .len = VGIC_MAX_IRQS / 8,
+ .bits_per_irq = 1,
.handle_mmio = handle_mmio_raz_wi,
},
{
.base = GIC_DIST_ENABLE_SET,
- .len = VGIC_NR_IRQS / 8,
+ .len = VGIC_MAX_IRQS / 8,
+ .bits_per_irq = 1,
.handle_mmio = handle_mmio_set_enable_reg,
},
{
.base = GIC_DIST_ENABLE_CLEAR,
- .len = VGIC_NR_IRQS / 8,
+ .len = VGIC_MAX_IRQS / 8,
+ .bits_per_irq = 1,
.handle_mmio = handle_mmio_clear_enable_reg,
},
{
.base = GIC_DIST_PENDING_SET,
- .len = VGIC_NR_IRQS / 8,
+ .len = VGIC_MAX_IRQS / 8,
+ .bits_per_irq = 1,
.handle_mmio = handle_mmio_set_pending_reg,
},
{
.base = GIC_DIST_PENDING_CLEAR,
- .len = VGIC_NR_IRQS / 8,
+ .len = VGIC_MAX_IRQS / 8,
+ .bits_per_irq = 1,
.handle_mmio = handle_mmio_clear_pending_reg,
},
{
.base = GIC_DIST_ACTIVE_SET,
- .len = VGIC_NR_IRQS / 8,
+ .len = VGIC_MAX_IRQS / 8,
+ .bits_per_irq = 1,
.handle_mmio = handle_mmio_raz_wi,
},
{
.base = GIC_DIST_ACTIVE_CLEAR,
- .len = VGIC_NR_IRQS / 8,
+ .len = VGIC_MAX_IRQS / 8,
+ .bits_per_irq = 1,
.handle_mmio = handle_mmio_raz_wi,
},
{
.base = GIC_DIST_PRI,
- .len = VGIC_NR_IRQS,
+ .len = VGIC_MAX_IRQS,
+ .bits_per_irq = 8,
.handle_mmio = handle_mmio_priority_reg,
},
{
.base = GIC_DIST_TARGET,
- .len = VGIC_NR_IRQS,
+ .len = VGIC_MAX_IRQS,
+ .bits_per_irq = 8,
.handle_mmio = handle_mmio_target_reg,
},
{
.base = GIC_DIST_CONFIG,
- .len = VGIC_NR_IRQS / 4,
+ .len = VGIC_MAX_IRQS / 4,
+ .bits_per_irq = 2,
.handle_mmio = handle_mmio_cfg_reg,
},
{
@@ -850,6 +1002,22 @@ struct mmio_range *find_matching_range(const struct mmio_range *ranges,
return NULL;
}
+static bool vgic_validate_access(const struct vgic_dist *dist,
+ const struct mmio_range *range,
+ unsigned long offset)
+{
+ int irq;
+
+ if (!range->bits_per_irq)
+ return true; /* Not an irq-based access */
+
+ irq = offset * 8 / range->bits_per_irq;
+ if (irq >= dist->nr_irqs)
+ return false;
+
+ return true;
+}
+
/**
* vgic_handle_mmio - handle an in-kernel MMIO access
* @vcpu: pointer to the vcpu performing the access
@@ -889,7 +1057,13 @@ bool vgic_handle_mmio(struct kvm_vcpu *vcpu, struct kvm_run *run,
spin_lock(&vcpu->kvm->arch.vgic.lock);
offset = mmio->phys_addr - range->base - base;
- updated_state = range->handle_mmio(vcpu, mmio, offset);
+ if (vgic_validate_access(dist, range, offset)) {
+ updated_state = range->handle_mmio(vcpu, mmio, offset);
+ } else {
+ vgic_reg_access(mmio, NULL, offset,
+ ACCESS_READ_RAZ | ACCESS_WRITE_IGNORED);
+ updated_state = false;
+ }
spin_unlock(&vcpu->kvm->arch.vgic.lock);
kvm_prepare_mmio(run, mmio);
kvm_handle_mmio_return(vcpu, run);
@@ -900,6 +1074,11 @@ bool vgic_handle_mmio(struct kvm_vcpu *vcpu, struct kvm_run *run,
return true;
}
+static u8 *vgic_get_sgi_sources(struct vgic_dist *dist, int vcpu_id, int sgi)
+{
+ return dist->irq_sgi_sources + vcpu_id * VGIC_NR_SGIS + sgi;
+}
+
static void vgic_dispatch_sgi(struct kvm_vcpu *vcpu, u32 reg)
{
struct kvm *kvm = vcpu->kvm;
@@ -932,8 +1111,8 @@ static void vgic_dispatch_sgi(struct kvm_vcpu *vcpu, u32 reg)
kvm_for_each_vcpu(c, vcpu, kvm) {
if (target_cpus & 1) {
/* Flag the SGI as pending */
- vgic_dist_irq_set(vcpu, sgi);
- dist->irq_sgi_sources[c][sgi] |= 1 << vcpu_id;
+ vgic_dist_irq_set_pending(vcpu, sgi);
+ *vgic_get_sgi_sources(dist, c, sgi) |= 1 << vcpu_id;
kvm_debug("SGI%d from CPU%d to CPU%d\n", sgi, vcpu_id, c);
}
@@ -941,32 +1120,38 @@ static void vgic_dispatch_sgi(struct kvm_vcpu *vcpu, u32 reg)
}
}
+static int vgic_nr_shared_irqs(struct vgic_dist *dist)
+{
+ return dist->nr_irqs - VGIC_NR_PRIVATE_IRQS;
+}
+
static int compute_pending_for_cpu(struct kvm_vcpu *vcpu)
{
struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
unsigned long *pending, *enabled, *pend_percpu, *pend_shared;
unsigned long pending_private, pending_shared;
+ int nr_shared = vgic_nr_shared_irqs(dist);
int vcpu_id;
vcpu_id = vcpu->vcpu_id;
pend_percpu = vcpu->arch.vgic_cpu.pending_percpu;
pend_shared = vcpu->arch.vgic_cpu.pending_shared;
- pending = vgic_bitmap_get_cpu_map(&dist->irq_state, vcpu_id);
+ pending = vgic_bitmap_get_cpu_map(&dist->irq_pending, vcpu_id);
enabled = vgic_bitmap_get_cpu_map(&dist->irq_enabled, vcpu_id);
bitmap_and(pend_percpu, pending, enabled, VGIC_NR_PRIVATE_IRQS);
- pending = vgic_bitmap_get_shared_map(&dist->irq_state);
+ pending = vgic_bitmap_get_shared_map(&dist->irq_pending);
enabled = vgic_bitmap_get_shared_map(&dist->irq_enabled);
- bitmap_and(pend_shared, pending, enabled, VGIC_NR_SHARED_IRQS);
+ bitmap_and(pend_shared, pending, enabled, nr_shared);
bitmap_and(pend_shared, pend_shared,
vgic_bitmap_get_shared_map(&dist->irq_spi_target[vcpu_id]),
- VGIC_NR_SHARED_IRQS);
+ nr_shared);
pending_private = find_first_bit(pend_percpu, VGIC_NR_PRIVATE_IRQS);
- pending_shared = find_first_bit(pend_shared, VGIC_NR_SHARED_IRQS);
+ pending_shared = find_first_bit(pend_shared, nr_shared);
return (pending_private < VGIC_NR_PRIVATE_IRQS ||
- pending_shared < VGIC_NR_SHARED_IRQS);
+ pending_shared < vgic_nr_shared_irqs(dist));
}
/*
@@ -980,14 +1165,14 @@ static void vgic_update_state(struct kvm *kvm)
int c;
if (!dist->enabled) {
- set_bit(0, &dist->irq_pending_on_cpu);
+ set_bit(0, dist->irq_pending_on_cpu);
return;
}
kvm_for_each_vcpu(c, vcpu, kvm) {
if (compute_pending_for_cpu(vcpu)) {
pr_debug("CPU%d has pending interrupts\n", c);
- set_bit(c, &dist->irq_pending_on_cpu);
+ set_bit(c, dist->irq_pending_on_cpu);
}
}
}
@@ -1079,8 +1264,8 @@ static void vgic_retire_disabled_irqs(struct kvm_vcpu *vcpu)
if (!vgic_irq_is_enabled(vcpu, vlr.irq)) {
vgic_retire_lr(lr, vlr.irq, vcpu);
- if (vgic_irq_is_active(vcpu, vlr.irq))
- vgic_irq_clear_active(vcpu, vlr.irq);
+ if (vgic_irq_is_queued(vcpu, vlr.irq))
+ vgic_irq_clear_queued(vcpu, vlr.irq);
}
}
}
@@ -1092,13 +1277,14 @@ static void vgic_retire_disabled_irqs(struct kvm_vcpu *vcpu)
static bool vgic_queue_irq(struct kvm_vcpu *vcpu, u8 sgi_source_id, int irq)
{
struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
+ struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
struct vgic_lr vlr;
int lr;
/* Sanitize the input... */
BUG_ON(sgi_source_id & ~7);
BUG_ON(sgi_source_id && irq >= VGIC_NR_SGIS);
- BUG_ON(irq >= VGIC_NR_IRQS);
+ BUG_ON(irq >= dist->nr_irqs);
kvm_debug("Queue IRQ%d\n", irq);
@@ -1144,14 +1330,14 @@ static bool vgic_queue_sgi(struct kvm_vcpu *vcpu, int irq)
int vcpu_id = vcpu->vcpu_id;
int c;
- sources = dist->irq_sgi_sources[vcpu_id][irq];
+ sources = *vgic_get_sgi_sources(dist, vcpu_id, irq);
- for_each_set_bit(c, &sources, VGIC_MAX_CPUS) {
+ for_each_set_bit(c, &sources, dist->nr_cpus) {
if (vgic_queue_irq(vcpu, c, irq))
clear_bit(c, &sources);
}
- dist->irq_sgi_sources[vcpu_id][irq] = sources;
+ *vgic_get_sgi_sources(dist, vcpu_id, irq) = sources;
/*
* If the sources bitmap has been cleared it means that we
@@ -1160,7 +1346,7 @@ static bool vgic_queue_sgi(struct kvm_vcpu *vcpu, int irq)
* our emulated gic and can get rid of them.
*/
if (!sources) {
- vgic_dist_irq_clear(vcpu, irq);
+ vgic_dist_irq_clear_pending(vcpu, irq);
vgic_cpu_irq_clear(vcpu, irq);
return true;
}
@@ -1170,15 +1356,15 @@ static bool vgic_queue_sgi(struct kvm_vcpu *vcpu, int irq)
static bool vgic_queue_hwirq(struct kvm_vcpu *vcpu, int irq)
{
- if (vgic_irq_is_active(vcpu, irq))
+ if (!vgic_can_sample_irq(vcpu, irq))
return true; /* level interrupt, already queued */
if (vgic_queue_irq(vcpu, 0, irq)) {
if (vgic_irq_is_edge(vcpu, irq)) {
- vgic_dist_irq_clear(vcpu, irq);
+ vgic_dist_irq_clear_pending(vcpu, irq);
vgic_cpu_irq_clear(vcpu, irq);
} else {
- vgic_irq_set_active(vcpu, irq);
+ vgic_irq_set_queued(vcpu, irq);
}
return true;
@@ -1223,7 +1409,7 @@ static void __kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu)
}
/* SPIs */
- for_each_set_bit(i, vgic_cpu->pending_shared, VGIC_NR_SHARED_IRQS) {
+ for_each_set_bit(i, vgic_cpu->pending_shared, vgic_nr_shared_irqs(dist)) {
if (!vgic_queue_hwirq(vcpu, i + VGIC_NR_PRIVATE_IRQS))
overflow = 1;
}
@@ -1239,7 +1425,7 @@ epilog:
* us. Claim we don't have anything pending. We'll
* adjust that if needed while exiting.
*/
- clear_bit(vcpu_id, &dist->irq_pending_on_cpu);
+ clear_bit(vcpu_id, dist->irq_pending_on_cpu);
}
}
@@ -1261,17 +1447,32 @@ static bool vgic_process_maintenance(struct kvm_vcpu *vcpu)
for_each_set_bit(lr, eisr_ptr, vgic->nr_lr) {
struct vgic_lr vlr = vgic_get_lr(vcpu, lr);
+ WARN_ON(vgic_irq_is_edge(vcpu, vlr.irq));
- vgic_irq_clear_active(vcpu, vlr.irq);
+ vgic_irq_clear_queued(vcpu, vlr.irq);
WARN_ON(vlr.state & LR_STATE_MASK);
vlr.state = 0;
vgic_set_lr(vcpu, lr, vlr);
+ /*
+ * If the IRQ was EOIed it was also ACKed and we we
+ * therefore assume we can clear the soft pending
+ * state (should it had been set) for this interrupt.
+ *
+ * Note: if the IRQ soft pending state was set after
+ * the IRQ was acked, it actually shouldn't be
+ * cleared, but we have no way of knowing that unless
+ * we start trapping ACKs when the soft-pending state
+ * is set.
+ */
+ vgic_dist_irq_clear_soft_pend(vcpu, vlr.irq);
+
/* Any additional pending interrupt? */
- if (vgic_dist_irq_is_pending(vcpu, vlr.irq)) {
+ if (vgic_dist_irq_get_level(vcpu, vlr.irq)) {
vgic_cpu_irq_set(vcpu, vlr.irq);
level_pending = true;
} else {
+ vgic_dist_irq_clear_pending(vcpu, vlr.irq);
vgic_cpu_irq_clear(vcpu, vlr.irq);
}
@@ -1315,14 +1516,14 @@ static void __kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu)
vlr = vgic_get_lr(vcpu, lr);
- BUG_ON(vlr.irq >= VGIC_NR_IRQS);
+ BUG_ON(vlr.irq >= dist->nr_irqs);
vgic_cpu->vgic_irq_lr_map[vlr.irq] = LR_EMPTY;
}
/* Check if we still have something up our sleeve... */
pending = find_first_zero_bit(elrsr_ptr, vgic->nr_lr);
if (level_pending || pending < vgic->nr_lr)
- set_bit(vcpu->vcpu_id, &dist->irq_pending_on_cpu);
+ set_bit(vcpu->vcpu_id, dist->irq_pending_on_cpu);
}
void kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu)
@@ -1356,7 +1557,7 @@ int kvm_vgic_vcpu_pending_irq(struct kvm_vcpu *vcpu)
if (!irqchip_in_kernel(vcpu->kvm))
return 0;
- return test_bit(vcpu->vcpu_id, &dist->irq_pending_on_cpu);
+ return test_bit(vcpu->vcpu_id, dist->irq_pending_on_cpu);
}
static void vgic_kick_vcpus(struct kvm *kvm)
@@ -1376,34 +1577,36 @@ static void vgic_kick_vcpus(struct kvm *kvm)
static int vgic_validate_injection(struct kvm_vcpu *vcpu, int irq, int level)
{
- int is_edge = vgic_irq_is_edge(vcpu, irq);
- int state = vgic_dist_irq_is_pending(vcpu, irq);
+ int edge_triggered = vgic_irq_is_edge(vcpu, irq);
/*
* Only inject an interrupt if:
* - edge triggered and we have a rising edge
* - level triggered and we change level
*/
- if (is_edge)
+ if (edge_triggered) {
+ int state = vgic_dist_irq_is_pending(vcpu, irq);
return level > state;
- else
+ } else {
+ int state = vgic_dist_irq_get_level(vcpu, irq);
return level != state;
+ }
}
-static bool vgic_update_irq_state(struct kvm *kvm, int cpuid,
+static bool vgic_update_irq_pending(struct kvm *kvm, int cpuid,
unsigned int irq_num, bool level)
{
struct vgic_dist *dist = &kvm->arch.vgic;
struct kvm_vcpu *vcpu;
- int is_edge, is_level;
+ int edge_triggered, level_triggered;
int enabled;
bool ret = true;
spin_lock(&dist->lock);
vcpu = kvm_get_vcpu(kvm, cpuid);
- is_edge = vgic_irq_is_edge(vcpu, irq_num);
- is_level = !is_edge;
+ edge_triggered = vgic_irq_is_edge(vcpu, irq_num);
+ level_triggered = !edge_triggered;
if (!vgic_validate_injection(vcpu, irq_num, level)) {
ret = false;
@@ -1417,10 +1620,19 @@ static bool vgic_update_irq_state(struct kvm *kvm, int cpuid,
kvm_debug("Inject IRQ%d level %d CPU%d\n", irq_num, level, cpuid);
- if (level)
- vgic_dist_irq_set(vcpu, irq_num);
- else
- vgic_dist_irq_clear(vcpu, irq_num);
+ if (level) {
+ if (level_triggered)
+ vgic_dist_irq_set_level(vcpu, irq_num);
+ vgic_dist_irq_set_pending(vcpu, irq_num);
+ } else {
+ if (level_triggered) {
+ vgic_dist_irq_clear_level(vcpu, irq_num);
+ if (!vgic_dist_irq_soft_pend(vcpu, irq_num))
+ vgic_dist_irq_clear_pending(vcpu, irq_num);
+ } else {
+ vgic_dist_irq_clear_pending(vcpu, irq_num);
+ }
+ }
enabled = vgic_irq_is_enabled(vcpu, irq_num);
@@ -1429,7 +1641,7 @@ static bool vgic_update_irq_state(struct kvm *kvm, int cpuid,
goto out;
}
- if (is_level && vgic_irq_is_active(vcpu, irq_num)) {
+ if (!vgic_can_sample_irq(vcpu, irq_num)) {
/*
* Level interrupt in progress, will be picked up
* when EOId.
@@ -1440,7 +1652,7 @@ static bool vgic_update_irq_state(struct kvm *kvm, int cpuid,
if (level) {
vgic_cpu_irq_set(vcpu, irq_num);
- set_bit(cpuid, &dist->irq_pending_on_cpu);
+ set_bit(cpuid, dist->irq_pending_on_cpu);
}
out:
@@ -1466,7 +1678,8 @@ out:
int kvm_vgic_inject_irq(struct kvm *kvm, int cpuid, unsigned int irq_num,
bool level)
{
- if (vgic_update_irq_state(kvm, cpuid, irq_num, level))
+ if (likely(vgic_initialized(kvm)) &&
+ vgic_update_irq_pending(kvm, cpuid, irq_num, level))
vgic_kick_vcpus(kvm);
return 0;
@@ -1483,6 +1696,32 @@ static irqreturn_t vgic_maintenance_handler(int irq, void *data)
return IRQ_HANDLED;
}
+void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu)
+{
+ struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
+
+ kfree(vgic_cpu->pending_shared);
+ kfree(vgic_cpu->vgic_irq_lr_map);
+ vgic_cpu->pending_shared = NULL;
+ vgic_cpu->vgic_irq_lr_map = NULL;
+}
+
+static int vgic_vcpu_init_maps(struct kvm_vcpu *vcpu, int nr_irqs)
+{
+ struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
+
+ int sz = (nr_irqs - VGIC_NR_PRIVATE_IRQS) / 8;
+ vgic_cpu->pending_shared = kzalloc(sz, GFP_KERNEL);
+ vgic_cpu->vgic_irq_lr_map = kzalloc(nr_irqs, GFP_KERNEL);
+
+ if (!vgic_cpu->pending_shared || !vgic_cpu->vgic_irq_lr_map) {
+ kvm_vgic_vcpu_destroy(vcpu);
+ return -ENOMEM;
+ }
+
+ return 0;
+}
+
/**
* kvm_vgic_vcpu_init - Initialize per-vcpu VGIC state
* @vcpu: pointer to the vcpu struct
@@ -1490,16 +1729,13 @@ static irqreturn_t vgic_maintenance_handler(int irq, void *data)
* Initialize the vgic_cpu struct and vgic_dist struct fields pertaining to
* this vcpu and enable the VGIC for this VCPU
*/
-int kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu)
+static void kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu)
{
struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
int i;
- if (vcpu->vcpu_id >= VGIC_MAX_CPUS)
- return -EBUSY;
-
- for (i = 0; i < VGIC_NR_IRQS; i++) {
+ for (i = 0; i < dist->nr_irqs; i++) {
if (i < VGIC_NR_PPIS)
vgic_bitmap_set_irq_val(&dist->irq_enabled,
vcpu->vcpu_id, i, 1);
@@ -1518,84 +1754,112 @@ int kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu)
vgic_cpu->nr_lr = vgic->nr_lr;
vgic_enable(vcpu);
-
- return 0;
}
-static void vgic_init_maintenance_interrupt(void *info)
+void kvm_vgic_destroy(struct kvm *kvm)
{
- enable_percpu_irq(vgic->maint_irq, 0);
+ struct vgic_dist *dist = &kvm->arch.vgic;
+ struct kvm_vcpu *vcpu;
+ int i;
+
+ kvm_for_each_vcpu(i, vcpu, kvm)
+ kvm_vgic_vcpu_destroy(vcpu);
+
+ vgic_free_bitmap(&dist->irq_enabled);
+ vgic_free_bitmap(&dist->irq_level);
+ vgic_free_bitmap(&dist->irq_pending);
+ vgic_free_bitmap(&dist->irq_soft_pend);
+ vgic_free_bitmap(&dist->irq_queued);
+ vgic_free_bitmap(&dist->irq_cfg);
+ vgic_free_bytemap(&dist->irq_priority);
+ if (dist->irq_spi_target) {
+ for (i = 0; i < dist->nr_cpus; i++)
+ vgic_free_bitmap(&dist->irq_spi_target[i]);
+ }
+ kfree(dist->irq_sgi_sources);
+ kfree(dist->irq_spi_cpu);
+ kfree(dist->irq_spi_target);
+ kfree(dist->irq_pending_on_cpu);
+ dist->irq_sgi_sources = NULL;
+ dist->irq_spi_cpu = NULL;
+ dist->irq_spi_target = NULL;
+ dist->irq_pending_on_cpu = NULL;
}
-static int vgic_cpu_notify(struct notifier_block *self,
- unsigned long action, void *cpu)
+/*
+ * Allocate and initialize the various data structures. Must be called
+ * with kvm->lock held!
+ */
+static int vgic_init_maps(struct kvm *kvm)
{
- switch (action) {
- case CPU_STARTING:
- case CPU_STARTING_FROZEN:
- vgic_init_maintenance_interrupt(NULL);
- break;
- case CPU_DYING:
- case CPU_DYING_FROZEN:
- disable_percpu_irq(vgic->maint_irq);
- break;
- }
+ struct vgic_dist *dist = &kvm->arch.vgic;
+ struct kvm_vcpu *vcpu;
+ int nr_cpus, nr_irqs;
+ int ret, i;
- return NOTIFY_OK;
-}
+ if (dist->nr_cpus) /* Already allocated */
+ return 0;
-static struct notifier_block vgic_cpu_nb = {
- .notifier_call = vgic_cpu_notify,
-};
+ nr_cpus = dist->nr_cpus = atomic_read(&kvm->online_vcpus);
+ if (!nr_cpus) /* No vcpus? Can't be good... */
+ return -EINVAL;
-static const struct of_device_id vgic_ids[] = {
- { .compatible = "arm,cortex-a15-gic", .data = vgic_v2_probe, },
- { .compatible = "arm,gic-v3", .data = vgic_v3_probe, },
- {},
-};
+ /*
+ * If nobody configured the number of interrupts, use the
+ * legacy one.
+ */
+ if (!dist->nr_irqs)
+ dist->nr_irqs = VGIC_NR_IRQS_LEGACY;
-int kvm_vgic_hyp_init(void)
-{
- const struct of_device_id *matched_id;
- int (*vgic_probe)(struct device_node *,const struct vgic_ops **,
- const struct vgic_params **);
- struct device_node *vgic_node;
- int ret;
+ nr_irqs = dist->nr_irqs;
- vgic_node = of_find_matching_node_and_match(NULL,
- vgic_ids, &matched_id);
- if (!vgic_node) {
- kvm_err("error: no compatible GIC node found\n");
- return -ENODEV;
- }
+ ret = vgic_init_bitmap(&dist->irq_enabled, nr_cpus, nr_irqs);
+ ret |= vgic_init_bitmap(&dist->irq_level, nr_cpus, nr_irqs);
+ ret |= vgic_init_bitmap(&dist->irq_pending, nr_cpus, nr_irqs);
+ ret |= vgic_init_bitmap(&dist->irq_soft_pend, nr_cpus, nr_irqs);
+ ret |= vgic_init_bitmap(&dist->irq_queued, nr_cpus, nr_irqs);
+ ret |= vgic_init_bitmap(&dist->irq_cfg, nr_cpus, nr_irqs);
+ ret |= vgic_init_bytemap(&dist->irq_priority, nr_cpus, nr_irqs);
- vgic_probe = matched_id->data;
- ret = vgic_probe(vgic_node, &vgic_ops, &vgic);
if (ret)
- return ret;
+ goto out;
- ret = request_percpu_irq(vgic->maint_irq, vgic_maintenance_handler,
- "vgic", kvm_get_running_vcpus());
- if (ret) {
- kvm_err("Cannot register interrupt %d\n", vgic->maint_irq);
- return ret;
+ dist->irq_sgi_sources = kzalloc(nr_cpus * VGIC_NR_SGIS, GFP_KERNEL);
+ dist->irq_spi_cpu = kzalloc(nr_irqs - VGIC_NR_PRIVATE_IRQS, GFP_KERNEL);
+ dist->irq_spi_target = kzalloc(sizeof(*dist->irq_spi_target) * nr_cpus,
+ GFP_KERNEL);
+ dist->irq_pending_on_cpu = kzalloc(BITS_TO_LONGS(nr_cpus) * sizeof(long),
+ GFP_KERNEL);
+ if (!dist->irq_sgi_sources ||
+ !dist->irq_spi_cpu ||
+ !dist->irq_spi_target ||
+ !dist->irq_pending_on_cpu) {
+ ret = -ENOMEM;
+ goto out;
}
- ret = __register_cpu_notifier(&vgic_cpu_nb);
- if (ret) {
- kvm_err("Cannot register vgic CPU notifier\n");
- goto out_free_irq;
- }
+ for (i = 0; i < nr_cpus; i++)
+ ret |= vgic_init_bitmap(&dist->irq_spi_target[i],
+ nr_cpus, nr_irqs);
- /* Callback into for arch code for setup */
- vgic_arch_setup(vgic);
+ if (ret)
+ goto out;
- on_each_cpu(vgic_init_maintenance_interrupt, NULL, 1);
+ kvm_for_each_vcpu(i, vcpu, kvm) {
+ ret = vgic_vcpu_init_maps(vcpu, nr_irqs);
+ if (ret) {
+ kvm_err("VGIC: Failed to allocate vcpu memory\n");
+ break;
+ }
+ }
- return 0;
+ for (i = VGIC_NR_PRIVATE_IRQS; i < dist->nr_irqs; i += 4)
+ vgic_set_target_reg(kvm, 0, i);
+
+out:
+ if (ret)
+ kvm_vgic_destroy(kvm);
-out_free_irq:
- free_percpu_irq(vgic->maint_irq, kvm_get_running_vcpus());
return ret;
}
@@ -1610,6 +1874,7 @@ out_free_irq:
*/
int kvm_vgic_init(struct kvm *kvm)
{
+ struct kvm_vcpu *vcpu;
int ret = 0, i;
if (!irqchip_in_kernel(kvm))
@@ -1627,6 +1892,12 @@ int kvm_vgic_init(struct kvm *kvm)
goto out;
}
+ ret = vgic_init_maps(kvm);
+ if (ret) {
+ kvm_err("Unable to allocate maps\n");
+ goto out;
+ }
+
ret = kvm_phys_addr_ioremap(kvm, kvm->arch.vgic.vgic_cpu_base,
vgic->vcpu_base, KVM_VGIC_V2_CPU_SIZE);
if (ret) {
@@ -1634,11 +1905,13 @@ int kvm_vgic_init(struct kvm *kvm)
goto out;
}
- for (i = VGIC_NR_PRIVATE_IRQS; i < VGIC_NR_IRQS; i += 4)
- vgic_set_target_reg(kvm, 0, i);
+ kvm_for_each_vcpu(i, vcpu, kvm)
+ kvm_vgic_vcpu_init(vcpu);
kvm->arch.vgic.ready = true;
out:
+ if (ret)
+ kvm_vgic_destroy(kvm);
mutex_unlock(&kvm->lock);
return ret;
}
@@ -1690,7 +1963,7 @@ out:
return ret;
}
-static bool vgic_ioaddr_overlap(struct kvm *kvm)
+static int vgic_ioaddr_overlap(struct kvm *kvm)
{
phys_addr_t dist = kvm->arch.vgic.vgic_dist_base;
phys_addr_t cpu = kvm->arch.vgic.vgic_cpu_base;
@@ -1879,6 +2152,10 @@ static int vgic_attr_regs_access(struct kvm_device *dev,
mutex_lock(&dev->kvm->lock);
+ ret = vgic_init_maps(dev->kvm);
+ if (ret)
+ goto out;
+
if (cpuid >= atomic_read(&dev->kvm->online_vcpus)) {
ret = -EINVAL;
goto out;
@@ -1976,6 +2253,36 @@ static int vgic_set_attr(struct kvm_device *dev, struct kvm_device_attr *attr)
return vgic_attr_regs_access(dev, attr, &reg, true);
}
+ case KVM_DEV_ARM_VGIC_GRP_NR_IRQS: {
+ u32 __user *uaddr = (u32 __user *)(long)attr->addr;
+ u32 val;
+ int ret = 0;
+
+ if (get_user(val, uaddr))
+ return -EFAULT;
+
+ /*
+ * We require:
+ * - at least 32 SPIs on top of the 16 SGIs and 16 PPIs
+ * - at most 1024 interrupts
+ * - a multiple of 32 interrupts
+ */
+ if (val < (VGIC_NR_PRIVATE_IRQS + 32) ||
+ val > VGIC_MAX_IRQS ||
+ (val & 31))
+ return -EINVAL;
+
+ mutex_lock(&dev->kvm->lock);
+
+ if (vgic_initialized(dev->kvm) || dev->kvm->arch.vgic.nr_irqs)
+ ret = -EBUSY;
+ else
+ dev->kvm->arch.vgic.nr_irqs = val;
+
+ mutex_unlock(&dev->kvm->lock);
+
+ return ret;
+ }
}
@@ -2012,6 +2319,11 @@ static int vgic_get_attr(struct kvm_device *dev, struct kvm_device_attr *attr)
r = put_user(reg, uaddr);
break;
}
+ case KVM_DEV_ARM_VGIC_GRP_NR_IRQS: {
+ u32 __user *uaddr = (u32 __user *)(long)attr->addr;
+ r = put_user(dev->kvm->arch.vgic.nr_irqs, uaddr);
+ break;
+ }
}
@@ -2048,6 +2360,8 @@ static int vgic_has_attr(struct kvm_device *dev, struct kvm_device_attr *attr)
case KVM_DEV_ARM_VGIC_GRP_CPU_REGS:
offset = attr->attr & KVM_DEV_ARM_VGIC_OFFSET_MASK;
return vgic_has_attr_regs(vgic_cpu_ranges, offset);
+ case KVM_DEV_ARM_VGIC_GRP_NR_IRQS:
+ return 0;
}
return -ENXIO;
}
@@ -2062,7 +2376,7 @@ static int vgic_create(struct kvm_device *dev, u32 type)
return kvm_vgic_create(dev->kvm);
}
-struct kvm_device_ops kvm_arm_vgic_v2_ops = {
+static struct kvm_device_ops kvm_arm_vgic_v2_ops = {
.name = "kvm-arm-vgic",
.create = vgic_create,
.destroy = vgic_destroy,
@@ -2070,3 +2384,81 @@ struct kvm_device_ops kvm_arm_vgic_v2_ops = {
.get_attr = vgic_get_attr,
.has_attr = vgic_has_attr,
};
+
+static void vgic_init_maintenance_interrupt(void *info)
+{
+ enable_percpu_irq(vgic->maint_irq, 0);
+}
+
+static int vgic_cpu_notify(struct notifier_block *self,
+ unsigned long action, void *cpu)
+{
+ switch (action) {
+ case CPU_STARTING:
+ case CPU_STARTING_FROZEN:
+ vgic_init_maintenance_interrupt(NULL);
+ break;
+ case CPU_DYING:
+ case CPU_DYING_FROZEN:
+ disable_percpu_irq(vgic->maint_irq);
+ break;
+ }
+
+ return NOTIFY_OK;
+}
+
+static struct notifier_block vgic_cpu_nb = {
+ .notifier_call = vgic_cpu_notify,
+};
+
+static const struct of_device_id vgic_ids[] = {
+ { .compatible = "arm,cortex-a15-gic", .data = vgic_v2_probe, },
+ { .compatible = "arm,gic-v3", .data = vgic_v3_probe, },
+ {},
+};
+
+int kvm_vgic_hyp_init(void)
+{
+ const struct of_device_id *matched_id;
+ const int (*vgic_probe)(struct device_node *,const struct vgic_ops **,
+ const struct vgic_params **);
+ struct device_node *vgic_node;
+ int ret;
+
+ vgic_node = of_find_matching_node_and_match(NULL,
+ vgic_ids, &matched_id);
+ if (!vgic_node) {
+ kvm_err("error: no compatible GIC node found\n");
+ return -ENODEV;
+ }
+
+ vgic_probe = matched_id->data;
+ ret = vgic_probe(vgic_node, &vgic_ops, &vgic);
+ if (ret)
+ return ret;
+
+ ret = request_percpu_irq(vgic->maint_irq, vgic_maintenance_handler,
+ "vgic", kvm_get_running_vcpus());
+ if (ret) {
+ kvm_err("Cannot register interrupt %d\n", vgic->maint_irq);
+ return ret;
+ }
+
+ ret = __register_cpu_notifier(&vgic_cpu_nb);
+ if (ret) {
+ kvm_err("Cannot register vgic CPU notifier\n");
+ goto out_free_irq;
+ }
+
+ /* Callback into for arch code for setup */
+ vgic_arch_setup(vgic);
+
+ on_each_cpu(vgic_init_maintenance_interrupt, NULL, 1);
+
+ return kvm_register_device_ops(&kvm_arm_vgic_v2_ops,
+ KVM_DEV_TYPE_ARM_VGIC_V2);
+
+out_free_irq:
+ free_percpu_irq(vgic->maint_irq, kvm_get_running_vcpus());
+ return ret;
+}
diff --git a/virt/kvm/assigned-dev.c b/virt/kvm/assigned-dev.c
index 5819a2708d7e..e05000e200d2 100644
--- a/virt/kvm/assigned-dev.c
+++ b/virt/kvm/assigned-dev.c
@@ -302,7 +302,7 @@ static void kvm_free_assigned_device(struct kvm *kvm,
else
pci_restore_state(assigned_dev->dev);
- assigned_dev->dev->dev_flags &= ~PCI_DEV_FLAGS_ASSIGNED;
+ pci_clear_dev_assigned(assigned_dev->dev);
pci_release_regions(assigned_dev->dev);
pci_disable_device(assigned_dev->dev);
diff --git a/virt/kvm/async_pf.c b/virt/kvm/async_pf.c
index d6a3d0993d88..5ff7f7f2689a 100644
--- a/virt/kvm/async_pf.c
+++ b/virt/kvm/async_pf.c
@@ -80,9 +80,7 @@ static void async_pf_execute(struct work_struct *work)
might_sleep();
- down_read(&mm->mmap_sem);
- get_user_pages(NULL, mm, addr, 1, 1, 0, NULL, NULL);
- up_read(&mm->mmap_sem);
+ kvm_get_user_page_io(NULL, mm, addr, 1, NULL);
kvm_async_page_present_sync(vcpu, apf);
spin_lock(&vcpu->async_pf.lock);
diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c
index 3c5981c87c3f..b0fb390943c6 100644
--- a/virt/kvm/eventfd.c
+++ b/virt/kvm/eventfd.c
@@ -36,7 +36,9 @@
#include <linux/seqlock.h>
#include <trace/events/kvm.h>
-#include "irq.h"
+#ifdef __KVM_HAVE_IOAPIC
+#include "ioapic.h"
+#endif
#include "iodev.h"
#ifdef CONFIG_HAVE_KVM_IRQFD
diff --git a/virt/kvm/ioapic.c b/virt/kvm/ioapic.c
index e8ce34c9db32..0ba4057d271b 100644
--- a/virt/kvm/ioapic.c
+++ b/virt/kvm/ioapic.c
@@ -405,6 +405,26 @@ void kvm_ioapic_clear_all(struct kvm_ioapic *ioapic, int irq_source_id)
spin_unlock(&ioapic->lock);
}
+static void kvm_ioapic_eoi_inject_work(struct work_struct *work)
+{
+ int i;
+ struct kvm_ioapic *ioapic = container_of(work, struct kvm_ioapic,
+ eoi_inject.work);
+ spin_lock(&ioapic->lock);
+ for (i = 0; i < IOAPIC_NUM_PINS; i++) {
+ union kvm_ioapic_redirect_entry *ent = &ioapic->redirtbl[i];
+
+ if (ent->fields.trig_mode != IOAPIC_LEVEL_TRIG)
+ continue;
+
+ if (ioapic->irr & (1 << i) && !ent->fields.remote_irr)
+ ioapic_service(ioapic, i, false);
+ }
+ spin_unlock(&ioapic->lock);
+}
+
+#define IOAPIC_SUCCESSIVE_IRQ_MAX_COUNT 10000
+
static void __kvm_ioapic_update_eoi(struct kvm_vcpu *vcpu,
struct kvm_ioapic *ioapic, int vector, int trigger_mode)
{
@@ -435,8 +455,26 @@ static void __kvm_ioapic_update_eoi(struct kvm_vcpu *vcpu,
ASSERT(ent->fields.trig_mode == IOAPIC_LEVEL_TRIG);
ent->fields.remote_irr = 0;
- if (ioapic->irr & (1 << i))
- ioapic_service(ioapic, i, false);
+ if (!ent->fields.mask && (ioapic->irr & (1 << i))) {
+ ++ioapic->irq_eoi[i];
+ if (ioapic->irq_eoi[i] == IOAPIC_SUCCESSIVE_IRQ_MAX_COUNT) {
+ /*
+ * Real hardware does not deliver the interrupt
+ * immediately during eoi broadcast, and this
+ * lets a buggy guest make slow progress
+ * even if it does not correctly handle a
+ * level-triggered interrupt. Emulate this
+ * behavior if we detect an interrupt storm.
+ */
+ schedule_delayed_work(&ioapic->eoi_inject, HZ / 100);
+ ioapic->irq_eoi[i] = 0;
+ trace_kvm_ioapic_delayed_eoi_inj(ent->bits);
+ } else {
+ ioapic_service(ioapic, i, false);
+ }
+ } else {
+ ioapic->irq_eoi[i] = 0;
+ }
}
}
@@ -565,12 +603,14 @@ static void kvm_ioapic_reset(struct kvm_ioapic *ioapic)
{
int i;
+ cancel_delayed_work_sync(&ioapic->eoi_inject);
for (i = 0; i < IOAPIC_NUM_PINS; i++)
ioapic->redirtbl[i].fields.mask = 1;
ioapic->base_address = IOAPIC_DEFAULT_BASE_ADDRESS;
ioapic->ioregsel = 0;
ioapic->irr = 0;
ioapic->id = 0;
+ memset(ioapic->irq_eoi, 0x00, IOAPIC_NUM_PINS);
rtc_irq_eoi_tracking_reset(ioapic);
update_handled_vectors(ioapic);
}
@@ -589,6 +629,7 @@ int kvm_ioapic_init(struct kvm *kvm)
if (!ioapic)
return -ENOMEM;
spin_lock_init(&ioapic->lock);
+ INIT_DELAYED_WORK(&ioapic->eoi_inject, kvm_ioapic_eoi_inject_work);
kvm->arch.vioapic = ioapic;
kvm_ioapic_reset(ioapic);
kvm_iodevice_init(&ioapic->dev, &ioapic_mmio_ops);
@@ -609,6 +650,7 @@ void kvm_ioapic_destroy(struct kvm *kvm)
{
struct kvm_ioapic *ioapic = kvm->arch.vioapic;
+ cancel_delayed_work_sync(&ioapic->eoi_inject);
if (ioapic) {
kvm_io_bus_unregister_dev(kvm, KVM_MMIO_BUS, &ioapic->dev);
kvm->arch.vioapic = NULL;
diff --git a/virt/kvm/ioapic.h b/virt/kvm/ioapic.h
index 90d43e95dcf8..e23b70634f1e 100644
--- a/virt/kvm/ioapic.h
+++ b/virt/kvm/ioapic.h
@@ -59,6 +59,8 @@ struct kvm_ioapic {
spinlock_t lock;
DECLARE_BITMAP(handled_vectors, 256);
struct rtc_status rtc_status;
+ struct delayed_work eoi_inject;
+ u32 irq_eoi[IOAPIC_NUM_PINS];
};
#ifdef DEBUG
diff --git a/virt/kvm/iommu.c b/virt/kvm/iommu.c
index 45ee080573f4..e51d9f9b995f 100644
--- a/virt/kvm/iommu.c
+++ b/virt/kvm/iommu.c
@@ -202,7 +202,7 @@ int kvm_assign_device(struct kvm *kvm,
goto out_unmap;
}
- pdev->dev_flags |= PCI_DEV_FLAGS_ASSIGNED;
+ pci_set_dev_assigned(pdev);
dev_info(&pdev->dev, "kvm assign device\n");
@@ -228,7 +228,7 @@ int kvm_deassign_device(struct kvm *kvm,
iommu_detach_device(domain, &pdev->dev);
- pdev->dev_flags &= ~PCI_DEV_FLAGS_ASSIGNED;
+ pci_clear_dev_assigned(pdev);
dev_info(&pdev->dev, "kvm deassign device\n");
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 95519bc959ed..384eaa7b02fa 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -52,11 +52,13 @@
#include <asm/processor.h>
#include <asm/io.h>
+#include <asm/ioctl.h>
#include <asm/uaccess.h>
#include <asm/pgtable.h>
#include "coalesced_mmio.h"
#include "async_pf.h"
+#include "vfio.h"
#define CREATE_TRACE_POINTS
#include <trace/events/kvm.h>
@@ -95,8 +97,6 @@ static int hardware_enable_all(void);
static void hardware_disable_all(void);
static void kvm_io_bus_destroy(struct kvm_io_bus *bus);
-static void update_memslots(struct kvm_memslots *slots,
- struct kvm_memory_slot *new, u64 last_generation);
static void kvm_release_pfn_dirty(pfn_t pfn);
static void mark_page_dirty_in_slot(struct kvm *kvm,
@@ -129,7 +129,8 @@ int vcpu_load(struct kvm_vcpu *vcpu)
struct pid *oldpid = vcpu->pid;
struct pid *newpid = get_task_pid(current, PIDTYPE_PID);
rcu_assign_pointer(vcpu->pid, newpid);
- synchronize_rcu();
+ if (oldpid)
+ synchronize_rcu();
put_pid(oldpid);
}
cpu = get_cpu();
@@ -152,7 +153,7 @@ static void ack_flush(void *_completed)
{
}
-static bool make_all_cpus_request(struct kvm *kvm, unsigned int req)
+bool kvm_make_all_cpus_request(struct kvm *kvm, unsigned int req)
{
int i, cpu, me;
cpumask_var_t cpus;
@@ -189,7 +190,7 @@ void kvm_flush_remote_tlbs(struct kvm *kvm)
long dirty_count = kvm->tlbs_dirty;
smp_mb();
- if (make_all_cpus_request(kvm, KVM_REQ_TLB_FLUSH))
+ if (kvm_make_all_cpus_request(kvm, KVM_REQ_TLB_FLUSH))
++kvm->stat.remote_tlb_flush;
cmpxchg(&kvm->tlbs_dirty, dirty_count, 0);
}
@@ -197,17 +198,17 @@ EXPORT_SYMBOL_GPL(kvm_flush_remote_tlbs);
void kvm_reload_remote_mmus(struct kvm *kvm)
{
- make_all_cpus_request(kvm, KVM_REQ_MMU_RELOAD);
+ kvm_make_all_cpus_request(kvm, KVM_REQ_MMU_RELOAD);
}
void kvm_make_mclock_inprogress_request(struct kvm *kvm)
{
- make_all_cpus_request(kvm, KVM_REQ_MCLOCK_INPROGRESS);
+ kvm_make_all_cpus_request(kvm, KVM_REQ_MCLOCK_INPROGRESS);
}
void kvm_make_scan_ioapic_request(struct kvm *kvm)
{
- make_all_cpus_request(kvm, KVM_REQ_SCAN_IOAPIC);
+ kvm_make_all_cpus_request(kvm, KVM_REQ_SCAN_IOAPIC);
}
int kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id)
@@ -295,6 +296,9 @@ static void kvm_mmu_notifier_invalidate_page(struct mmu_notifier *mn,
kvm_flush_remote_tlbs(kvm);
spin_unlock(&kvm->mmu_lock);
+
+ kvm_arch_mmu_notifier_invalidate_page(kvm, address);
+
srcu_read_unlock(&kvm->srcu, idx);
}
@@ -368,7 +372,8 @@ static void kvm_mmu_notifier_invalidate_range_end(struct mmu_notifier *mn,
static int kvm_mmu_notifier_clear_flush_young(struct mmu_notifier *mn,
struct mm_struct *mm,
- unsigned long address)
+ unsigned long start,
+ unsigned long end)
{
struct kvm *kvm = mmu_notifier_to_kvm(mn);
int young, idx;
@@ -376,7 +381,7 @@ static int kvm_mmu_notifier_clear_flush_young(struct mmu_notifier *mn,
idx = srcu_read_lock(&kvm->srcu);
spin_lock(&kvm->mmu_lock);
- young = kvm_age_hva(kvm, address);
+ young = kvm_age_hva(kvm, start, end);
if (young)
kvm_flush_remote_tlbs(kvm);
@@ -476,6 +481,13 @@ static struct kvm *kvm_create_vm(unsigned long type)
kvm->memslots = kzalloc(sizeof(struct kvm_memslots), GFP_KERNEL);
if (!kvm->memslots)
goto out_err_no_srcu;
+
+ /*
+ * Init kvm generation close to the maximum to easily test the
+ * code of handling generation number wrap-around.
+ */
+ kvm->memslots->generation = -150;
+
kvm_init_memslots_id(kvm);
if (init_srcu_struct(&kvm->srcu))
goto out_err_no_srcu;
@@ -687,8 +699,7 @@ static void sort_memslots(struct kvm_memslots *slots)
}
static void update_memslots(struct kvm_memslots *slots,
- struct kvm_memory_slot *new,
- u64 last_generation)
+ struct kvm_memory_slot *new)
{
if (new) {
int id = new->id;
@@ -699,15 +710,13 @@ static void update_memslots(struct kvm_memslots *slots,
if (new->npages != npages)
sort_memslots(slots);
}
-
- slots->generation = last_generation + 1;
}
static int check_memory_region_flags(struct kvm_userspace_memory_region *mem)
{
u32 valid_flags = KVM_MEM_LOG_DIRTY_PAGES;
-#ifdef KVM_CAP_READONLY_MEM
+#ifdef __KVM_HAVE_READONLY_MEM
valid_flags |= KVM_MEM_READONLY;
#endif
@@ -722,10 +731,24 @@ static struct kvm_memslots *install_new_memslots(struct kvm *kvm,
{
struct kvm_memslots *old_memslots = kvm->memslots;
- update_memslots(slots, new, kvm->memslots->generation);
+ /*
+ * Set the low bit in the generation, which disables SPTE caching
+ * until the end of synchronize_srcu_expedited.
+ */
+ WARN_ON(old_memslots->generation & 1);
+ slots->generation = old_memslots->generation + 1;
+
+ update_memslots(slots, new);
rcu_assign_pointer(kvm->memslots, slots);
synchronize_srcu_expedited(&kvm->srcu);
+ /*
+ * Increment the new memslot generation a second time. This prevents
+ * vm exits that race with memslot updates from caching a memslot
+ * generation that will (potentially) be valid forever.
+ */
+ slots->generation++;
+
kvm_arch_memslots_updated(kvm);
return old_memslots;
@@ -776,7 +799,6 @@ int __kvm_set_memory_region(struct kvm *kvm,
base_gfn = mem->guest_phys_addr >> PAGE_SHIFT;
npages = mem->memory_size >> PAGE_SHIFT;
- r = -EINVAL;
if (npages > KVM_MEM_MAX_NR_PAGES)
goto out;
@@ -790,7 +812,6 @@ int __kvm_set_memory_region(struct kvm *kvm,
new.npages = npages;
new.flags = mem->flags;
- r = -EINVAL;
if (npages) {
if (!old.npages)
change = KVM_MR_CREATE;
@@ -846,7 +867,6 @@ int __kvm_set_memory_region(struct kvm *kvm,
}
if ((change == KVM_MR_DELETE) || (change == KVM_MR_MOVE)) {
- r = -ENOMEM;
slots = kmemdup(kvm->memslots, sizeof(struct kvm_memslots),
GFP_KERNEL);
if (!slots)
@@ -1075,9 +1095,9 @@ EXPORT_SYMBOL_GPL(gfn_to_hva);
* If writable is set to false, the hva returned by this function is only
* allowed to be read.
*/
-unsigned long gfn_to_hva_prot(struct kvm *kvm, gfn_t gfn, bool *writable)
+unsigned long gfn_to_hva_memslot_prot(struct kvm_memory_slot *slot,
+ gfn_t gfn, bool *writable)
{
- struct kvm_memory_slot *slot = gfn_to_memslot(kvm, gfn);
unsigned long hva = __gfn_to_hva_many(slot, gfn, NULL, false);
if (!kvm_is_error_hva(hva) && writable)
@@ -1086,6 +1106,13 @@ unsigned long gfn_to_hva_prot(struct kvm *kvm, gfn_t gfn, bool *writable)
return hva;
}
+unsigned long gfn_to_hva_prot(struct kvm *kvm, gfn_t gfn, bool *writable)
+{
+ struct kvm_memory_slot *slot = gfn_to_memslot(kvm, gfn);
+
+ return gfn_to_hva_memslot_prot(slot, gfn, writable);
+}
+
static int kvm_read_hva(void *data, void __user *hva, int len)
{
return __copy_from_user(data, hva, len);
@@ -1107,6 +1134,43 @@ static int get_user_page_nowait(struct task_struct *tsk, struct mm_struct *mm,
return __get_user_pages(tsk, mm, start, 1, flags, page, NULL, NULL);
}
+int kvm_get_user_page_io(struct task_struct *tsk, struct mm_struct *mm,
+ unsigned long addr, bool write_fault,
+ struct page **pagep)
+{
+ int npages;
+ int locked = 1;
+ int flags = FOLL_TOUCH | FOLL_HWPOISON |
+ (pagep ? FOLL_GET : 0) |
+ (write_fault ? FOLL_WRITE : 0);
+
+ /*
+ * If retrying the fault, we get here *not* having allowed the filemap
+ * to wait on the page lock. We should now allow waiting on the IO with
+ * the mmap semaphore released.
+ */
+ down_read(&mm->mmap_sem);
+ npages = __get_user_pages(tsk, mm, addr, 1, flags, pagep, NULL,
+ &locked);
+ if (!locked) {
+ VM_BUG_ON(npages);
+
+ if (!pagep)
+ return 0;
+
+ /*
+ * The previous call has now waited on the IO. Now we can
+ * retry and complete. Pass TRIED to ensure we do not re
+ * schedule async IO (see e.g. filemap_fault).
+ */
+ down_read(&mm->mmap_sem);
+ npages = __get_user_pages(tsk, mm, addr, 1, flags | FOLL_TRIED,
+ pagep, NULL, NULL);
+ }
+ up_read(&mm->mmap_sem);
+ return npages;
+}
+
static inline int check_user_page_hwpoison(unsigned long addr)
{
int rc, flags = FOLL_TOUCH | FOLL_HWPOISON | FOLL_WRITE;
@@ -1169,9 +1233,15 @@ static int hva_to_pfn_slow(unsigned long addr, bool *async, bool write_fault,
npages = get_user_page_nowait(current, current->mm,
addr, write_fault, page);
up_read(&current->mm->mmap_sem);
- } else
- npages = get_user_pages_fast(addr, 1, write_fault,
- page);
+ } else {
+ /*
+ * By now we have tried gup_fast, and possibly async_pf, and we
+ * are certainly not atomic. Time to retry the gup, allowing
+ * mmap semaphore to be relinquished in the case of IO.
+ */
+ npages = kvm_get_user_page_io(current, current->mm, addr,
+ write_fault, page);
+ }
if (npages != 1)
return npages;
@@ -1768,8 +1838,7 @@ static bool kvm_vcpu_eligible_for_directed_yield(struct kvm_vcpu *vcpu)
bool eligible;
eligible = !vcpu->spin_loop.in_spin_loop ||
- (vcpu->spin_loop.in_spin_loop &&
- vcpu->spin_loop.dy_eligible);
+ vcpu->spin_loop.dy_eligible;
if (vcpu->spin_loop.in_spin_loop)
kvm_vcpu_set_dy_eligible(vcpu, !vcpu->spin_loop.dy_eligible);
@@ -1975,6 +2044,9 @@ static long kvm_vcpu_ioctl(struct file *filp,
if (vcpu->kvm->mm != current->mm)
return -EIO;
+ if (unlikely(_IOC_TYPE(ioctl) != KVMIO))
+ return -EINVAL;
+
#if defined(CONFIG_S390) || defined(CONFIG_PPC) || defined(CONFIG_MIPS)
/*
* Special cases: vcpu ioctls that are asynchronous to vcpu execution,
@@ -2259,6 +2331,29 @@ struct kvm_device *kvm_device_from_filp(struct file *filp)
return filp->private_data;
}
+static struct kvm_device_ops *kvm_device_ops_table[KVM_DEV_TYPE_MAX] = {
+#ifdef CONFIG_KVM_MPIC
+ [KVM_DEV_TYPE_FSL_MPIC_20] = &kvm_mpic_ops,
+ [KVM_DEV_TYPE_FSL_MPIC_42] = &kvm_mpic_ops,
+#endif
+
+#ifdef CONFIG_KVM_XICS
+ [KVM_DEV_TYPE_XICS] = &kvm_xics_ops,
+#endif
+};
+
+int kvm_register_device_ops(struct kvm_device_ops *ops, u32 type)
+{
+ if (type >= ARRAY_SIZE(kvm_device_ops_table))
+ return -ENOSPC;
+
+ if (kvm_device_ops_table[type] != NULL)
+ return -EEXIST;
+
+ kvm_device_ops_table[type] = ops;
+ return 0;
+}
+
static int kvm_ioctl_create_device(struct kvm *kvm,
struct kvm_create_device *cd)
{
@@ -2267,36 +2362,12 @@ static int kvm_ioctl_create_device(struct kvm *kvm,
bool test = cd->flags & KVM_CREATE_DEVICE_TEST;
int ret;
- switch (cd->type) {
-#ifdef CONFIG_KVM_MPIC
- case KVM_DEV_TYPE_FSL_MPIC_20:
- case KVM_DEV_TYPE_FSL_MPIC_42:
- ops = &kvm_mpic_ops;
- break;
-#endif
-#ifdef CONFIG_KVM_XICS
- case KVM_DEV_TYPE_XICS:
- ops = &kvm_xics_ops;
- break;
-#endif
-#ifdef CONFIG_KVM_VFIO
- case KVM_DEV_TYPE_VFIO:
- ops = &kvm_vfio_ops;
- break;
-#endif
-#ifdef CONFIG_KVM_ARM_VGIC
- case KVM_DEV_TYPE_ARM_VGIC_V2:
- ops = &kvm_arm_vgic_v2_ops;
- break;
-#endif
-#ifdef CONFIG_S390
- case KVM_DEV_TYPE_FLIC:
- ops = &kvm_flic_ops;
- break;
-#endif
- default:
+ if (cd->type >= ARRAY_SIZE(kvm_device_ops_table))
+ return -ENODEV;
+
+ ops = kvm_device_ops_table[cd->type];
+ if (ops == NULL)
return -ENODEV;
- }
if (test)
return 0;
@@ -2611,7 +2682,6 @@ static long kvm_dev_ioctl(struct file *filp,
switch (ioctl) {
case KVM_GET_API_VERSION:
- r = -EINVAL;
if (arg)
goto out;
r = KVM_API_VERSION;
@@ -2623,7 +2693,6 @@ static long kvm_dev_ioctl(struct file *filp,
r = kvm_vm_ioctl_check_extension_generic(NULL, arg);
break;
case KVM_GET_VCPU_MMAP_SIZE:
- r = -EINVAL;
if (arg)
goto out;
r = PAGE_SIZE; /* struct kvm_run */
@@ -2668,7 +2737,7 @@ static void hardware_enable_nolock(void *junk)
cpumask_set_cpu(cpu, cpus_hardware_enabled);
- r = kvm_arch_hardware_enable(NULL);
+ r = kvm_arch_hardware_enable();
if (r) {
cpumask_clear_cpu(cpu, cpus_hardware_enabled);
@@ -2693,7 +2762,7 @@ static void hardware_disable_nolock(void *junk)
if (!cpumask_test_cpu(cpu, cpus_hardware_enabled))
return;
cpumask_clear_cpu(cpu, cpus_hardware_enabled);
- kvm_arch_hardware_disable(NULL);
+ kvm_arch_hardware_disable();
}
static void hardware_disable(void)
@@ -3123,6 +3192,8 @@ static void kvm_sched_in(struct preempt_notifier *pn, int cpu)
if (vcpu->preempted)
vcpu->preempted = false;
+ kvm_arch_sched_in(vcpu, cpu);
+
kvm_arch_vcpu_load(vcpu, cpu);
}
@@ -3214,6 +3285,9 @@ int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align,
goto out_undebugfs;
}
+ r = kvm_vfio_ops_init();
+ WARN_ON(r);
+
return 0;
out_undebugfs:
diff --git a/virt/kvm/vfio.c b/virt/kvm/vfio.c
index ba1a93f935c7..281e7cf2b8e5 100644
--- a/virt/kvm/vfio.c
+++ b/virt/kvm/vfio.c
@@ -18,6 +18,7 @@
#include <linux/slab.h>
#include <linux/uaccess.h>
#include <linux/vfio.h>
+#include "vfio.h"
struct kvm_vfio_group {
struct list_head node;
@@ -246,6 +247,16 @@ static void kvm_vfio_destroy(struct kvm_device *dev)
kfree(dev); /* alloc by kvm_ioctl_create_device, free by .destroy */
}
+static int kvm_vfio_create(struct kvm_device *dev, u32 type);
+
+static struct kvm_device_ops kvm_vfio_ops = {
+ .name = "kvm-vfio",
+ .create = kvm_vfio_create,
+ .destroy = kvm_vfio_destroy,
+ .set_attr = kvm_vfio_set_attr,
+ .has_attr = kvm_vfio_has_attr,
+};
+
static int kvm_vfio_create(struct kvm_device *dev, u32 type)
{
struct kvm_device *tmp;
@@ -268,10 +279,7 @@ static int kvm_vfio_create(struct kvm_device *dev, u32 type)
return 0;
}
-struct kvm_device_ops kvm_vfio_ops = {
- .name = "kvm-vfio",
- .create = kvm_vfio_create,
- .destroy = kvm_vfio_destroy,
- .set_attr = kvm_vfio_set_attr,
- .has_attr = kvm_vfio_has_attr,
-};
+int kvm_vfio_ops_init(void)
+{
+ return kvm_register_device_ops(&kvm_vfio_ops, KVM_DEV_TYPE_VFIO);
+}
diff --git a/virt/kvm/vfio.h b/virt/kvm/vfio.h
new file mode 100644
index 000000000000..92eac75d6b62
--- /dev/null
+++ b/virt/kvm/vfio.h
@@ -0,0 +1,13 @@
+#ifndef __KVM_VFIO_H
+#define __KVM_VFIO_H
+
+#ifdef CONFIG_KVM_VFIO
+int kvm_vfio_ops_init(void);
+#else
+static inline int kvm_vfio_ops_init(void)
+{
+ return 0;
+}
+#endif
+
+#endif