aboutsummaryrefslogtreecommitdiff
path: root/virt
diff options
context:
space:
mode:
Diffstat (limited to 'virt')
-rw-r--r--virt/kvm/Kconfig5
-rw-r--r--virt/kvm/arm/arm.c36
-rw-r--r--virt/kvm/arm/mmu.c3
-rw-r--r--virt/kvm/arm/psci.c18
-rw-r--r--virt/kvm/arm/vgic/vgic-debug.c22
-rw-r--r--virt/kvm/arm/vgic/vgic-init.c102
-rw-r--r--virt/kvm/arm/vgic/vgic-its.c34
-rw-r--r--virt/kvm/arm/vgic/vgic-kvm-device.c53
-rw-r--r--virt/kvm/arm/vgic/vgic-mmio-v3.c112
-rw-r--r--virt/kvm/arm/vgic/vgic-mmio.c10
-rw-r--r--virt/kvm/arm/vgic/vgic-v2.c38
-rw-r--r--virt/kvm/arm/vgic/vgic-v3.c157
-rw-r--r--virt/kvm/arm/vgic/vgic-v4.c2
-rw-r--r--virt/kvm/arm/vgic/vgic.c52
-rw-r--r--virt/kvm/arm/vgic/vgic.h60
-rw-r--r--virt/kvm/eventfd.c2
-rw-r--r--virt/kvm/kvm_main.c105
17 files changed, 560 insertions, 251 deletions
diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig
index cca7e065a075..ea434ddc8499 100644
--- a/virt/kvm/Kconfig
+++ b/virt/kvm/Kconfig
@@ -47,10 +47,13 @@ config KVM_GENERIC_DIRTYLOG_READ_PROTECT
config KVM_COMPAT
def_bool y
- depends on KVM && COMPAT && !S390
+ depends on KVM && COMPAT && !(S390 || ARM64)
config HAVE_KVM_IRQ_BYPASS
bool
config HAVE_KVM_VCPU_ASYNC_IOCTL
bool
+
+config HAVE_KVM_VCPU_RUN_PID_CHANGE
+ bool
diff --git a/virt/kvm/arm/arm.c b/virt/kvm/arm/arm.c
index a4c1b76240df..04e554cae3a2 100644
--- a/virt/kvm/arm/arm.c
+++ b/virt/kvm/arm/arm.c
@@ -16,6 +16,7 @@
* Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
*/
+#include <linux/bug.h>
#include <linux/cpu_pm.h>
#include <linux/errno.h>
#include <linux/err.h>
@@ -41,6 +42,7 @@
#include <asm/mman.h>
#include <asm/tlbflush.h>
#include <asm/cacheflush.h>
+#include <asm/cpufeature.h>
#include <asm/virt.h>
#include <asm/kvm_arm.h>
#include <asm/kvm_asm.h>
@@ -163,7 +165,7 @@ int kvm_arch_create_vcpu_debugfs(struct kvm_vcpu *vcpu)
return 0;
}
-int kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf)
+vm_fault_t kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf)
{
return VM_FAULT_SIGBUS;
}
@@ -249,6 +251,21 @@ long kvm_arch_dev_ioctl(struct file *filp,
return -EINVAL;
}
+struct kvm *kvm_arch_alloc_vm(void)
+{
+ if (!has_vhe())
+ return kzalloc(sizeof(struct kvm), GFP_KERNEL);
+
+ return vzalloc(sizeof(struct kvm));
+}
+
+void kvm_arch_free_vm(struct kvm *kvm)
+{
+ if (!has_vhe())
+ kfree(kvm);
+ else
+ vfree(kvm);
+}
struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id)
{
@@ -290,7 +307,6 @@ out:
void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu)
{
- kvm_vgic_vcpu_early_init(vcpu);
}
void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu)
@@ -363,10 +379,12 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
kvm_vgic_load(vcpu);
kvm_timer_vcpu_load(vcpu);
kvm_vcpu_load_sysregs(vcpu);
+ kvm_arch_vcpu_load_fp(vcpu);
}
void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
{
+ kvm_arch_vcpu_put_fp(vcpu);
kvm_vcpu_put_sysregs(vcpu);
kvm_timer_vcpu_put(vcpu);
kvm_vgic_put(vcpu);
@@ -678,9 +696,6 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
*/
preempt_disable();
- /* Flush FP/SIMD state that can't survive guest entry/exit */
- kvm_fpsimd_flush_cpu_state();
-
kvm_pmu_flush_hwstate(vcpu);
local_irq_disable();
@@ -778,6 +793,8 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
if (static_branch_unlikely(&userspace_irqchip_in_use))
kvm_timer_sync_hwstate(vcpu);
+ kvm_arch_vcpu_ctxsync_fp(vcpu);
+
/*
* We may have taken a host interrupt in HYP mode (ie
* while executing the guest). This interrupt is still
@@ -1490,6 +1507,10 @@ static int init_hyp_mode(void)
}
}
+ err = hyp_map_aux_data();
+ if (err)
+ kvm_err("Cannot map host auxilary data: %d\n", err);
+
return 0;
out_err:
@@ -1570,6 +1591,11 @@ int kvm_arch_init(void *opaque)
return -ENODEV;
}
+ if (!kvm_arch_check_sve_has_vhe()) {
+ kvm_pr_unimpl("SVE system without VHE unsupported. Broken cpu?");
+ return -ENODEV;
+ }
+
for_each_online_cpu(cpu) {
smp_call_function_single(cpu, check_kvm_target_cpu, &ret, 1);
if (ret < 0) {
diff --git a/virt/kvm/arm/mmu.c b/virt/kvm/arm/mmu.c
index 7f6a944db23d..1d90d79706bd 100644
--- a/virt/kvm/arm/mmu.c
+++ b/virt/kvm/arm/mmu.c
@@ -297,6 +297,8 @@ static void unmap_stage2_range(struct kvm *kvm, phys_addr_t start, u64 size)
phys_addr_t next;
assert_spin_locked(&kvm->mmu_lock);
+ WARN_ON(size & ~PAGE_MASK);
+
pgd = kvm->arch.pgd + stage2_pgd_index(addr);
do {
/*
@@ -1401,6 +1403,7 @@ static void kvm_send_hwpoison_signal(unsigned long address,
{
siginfo_t info;
+ clear_siginfo(&info);
info.si_signo = SIGBUS;
info.si_errno = 0;
info.si_code = BUS_MCEERR_AR;
diff --git a/virt/kvm/arm/psci.c b/virt/kvm/arm/psci.c
index c4762bef13c6..c95ab4c5a475 100644
--- a/virt/kvm/arm/psci.c
+++ b/virt/kvm/arm/psci.c
@@ -405,7 +405,7 @@ static int kvm_psci_call(struct kvm_vcpu *vcpu)
int kvm_hvc_call_handler(struct kvm_vcpu *vcpu)
{
u32 func_id = smccc_get_function(vcpu);
- u32 val = PSCI_RET_NOT_SUPPORTED;
+ u32 val = SMCCC_RET_NOT_SUPPORTED;
u32 feature;
switch (func_id) {
@@ -417,7 +417,21 @@ int kvm_hvc_call_handler(struct kvm_vcpu *vcpu)
switch(feature) {
case ARM_SMCCC_ARCH_WORKAROUND_1:
if (kvm_arm_harden_branch_predictor())
- val = 0;
+ val = SMCCC_RET_SUCCESS;
+ break;
+ case ARM_SMCCC_ARCH_WORKAROUND_2:
+ switch (kvm_arm_have_ssbd()) {
+ case KVM_SSBD_FORCE_DISABLE:
+ case KVM_SSBD_UNKNOWN:
+ break;
+ case KVM_SSBD_KERNEL:
+ val = SMCCC_RET_SUCCESS;
+ break;
+ case KVM_SSBD_FORCE_ENABLE:
+ case KVM_SSBD_MITIGATED:
+ val = SMCCC_RET_NOT_REQUIRED;
+ break;
+ }
break;
}
break;
diff --git a/virt/kvm/arm/vgic/vgic-debug.c b/virt/kvm/arm/vgic/vgic-debug.c
index 10b38178cff2..c589d4c2b478 100644
--- a/virt/kvm/arm/vgic/vgic-debug.c
+++ b/virt/kvm/arm/vgic/vgic-debug.c
@@ -211,6 +211,7 @@ static int vgic_debug_show(struct seq_file *s, void *v)
struct vgic_state_iter *iter = (struct vgic_state_iter *)v;
struct vgic_irq *irq;
struct kvm_vcpu *vcpu = NULL;
+ unsigned long flags;
if (iter->dist_id == 0) {
print_dist_state(s, &kvm->arch.vgic);
@@ -227,9 +228,9 @@ static int vgic_debug_show(struct seq_file *s, void *v)
irq = &kvm->arch.vgic.spis[iter->intid - VGIC_NR_PRIVATE_IRQS];
}
- spin_lock(&irq->irq_lock);
+ spin_lock_irqsave(&irq->irq_lock, flags);
print_irq_state(s, irq, vcpu);
- spin_unlock(&irq->irq_lock);
+ spin_unlock_irqrestore(&irq->irq_lock, flags);
return 0;
}
@@ -263,21 +264,12 @@ static const struct file_operations vgic_debug_fops = {
.release = seq_release
};
-int vgic_debug_init(struct kvm *kvm)
+void vgic_debug_init(struct kvm *kvm)
{
- if (!kvm->debugfs_dentry)
- return -ENOENT;
-
- if (!debugfs_create_file("vgic-state", 0444,
- kvm->debugfs_dentry,
- kvm,
- &vgic_debug_fops))
- return -ENOMEM;
-
- return 0;
+ debugfs_create_file("vgic-state", 0444, kvm->debugfs_dentry, kvm,
+ &vgic_debug_fops);
}
-int vgic_debug_destroy(struct kvm *kvm)
+void vgic_debug_destroy(struct kvm *kvm)
{
- return 0;
}
diff --git a/virt/kvm/arm/vgic/vgic-init.c b/virt/kvm/arm/vgic/vgic-init.c
index 68378fe17a0e..2673efce65f3 100644
--- a/virt/kvm/arm/vgic/vgic-init.c
+++ b/virt/kvm/arm/vgic/vgic-init.c
@@ -44,7 +44,7 @@
*
* CPU Interface:
*
- * - kvm_vgic_vcpu_early_init(): initialization of static data that
+ * - kvm_vgic_vcpu_init(): initialization of static data that
* doesn't depend on any sizing information or emulation type. No
* allocation is allowed there.
*/
@@ -67,46 +67,6 @@ void kvm_vgic_early_init(struct kvm *kvm)
spin_lock_init(&dist->lpi_list_lock);
}
-/**
- * kvm_vgic_vcpu_early_init() - Initialize static VGIC VCPU data structures
- * @vcpu: The VCPU whose VGIC data structures whould be initialized
- *
- * Only do initialization, but do not actually enable the VGIC CPU interface
- * yet.
- */
-void kvm_vgic_vcpu_early_init(struct kvm_vcpu *vcpu)
-{
- struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
- int i;
-
- INIT_LIST_HEAD(&vgic_cpu->ap_list_head);
- spin_lock_init(&vgic_cpu->ap_list_lock);
-
- /*
- * Enable and configure all SGIs to be edge-triggered and
- * configure all PPIs as level-triggered.
- */
- for (i = 0; i < VGIC_NR_PRIVATE_IRQS; i++) {
- struct vgic_irq *irq = &vgic_cpu->private_irqs[i];
-
- INIT_LIST_HEAD(&irq->ap_list);
- spin_lock_init(&irq->irq_lock);
- irq->intid = i;
- irq->vcpu = NULL;
- irq->target_vcpu = vcpu;
- irq->targets = 1U << vcpu->vcpu_id;
- kref_init(&irq->refcount);
- if (vgic_irq_is_sgi(i)) {
- /* SGIs */
- irq->enabled = 1;
- irq->config = VGIC_CONFIG_EDGE;
- } else {
- /* PPIs */
- irq->config = VGIC_CONFIG_LEVEL;
- }
- }
-}
-
/* CREATION */
/**
@@ -167,8 +127,11 @@ int kvm_vgic_create(struct kvm *kvm, u32 type)
kvm->arch.vgic.vgic_model = type;
kvm->arch.vgic.vgic_dist_base = VGIC_ADDR_UNDEF;
- kvm->arch.vgic.vgic_cpu_base = VGIC_ADDR_UNDEF;
- kvm->arch.vgic.vgic_redist_base = VGIC_ADDR_UNDEF;
+
+ if (type == KVM_DEV_TYPE_ARM_VGIC_V2)
+ kvm->arch.vgic.vgic_cpu_base = VGIC_ADDR_UNDEF;
+ else
+ INIT_LIST_HEAD(&kvm->arch.vgic.rd_regions);
out_unlock:
for (; vcpu_lock_idx >= 0; vcpu_lock_idx--) {
@@ -221,13 +184,50 @@ static int kvm_vgic_dist_init(struct kvm *kvm, unsigned int nr_spis)
}
/**
- * kvm_vgic_vcpu_init() - Register VCPU-specific KVM iodevs
+ * kvm_vgic_vcpu_init() - Initialize static VGIC VCPU data
+ * structures and register VCPU-specific KVM iodevs
+ *
* @vcpu: pointer to the VCPU being created and initialized
+ *
+ * Only do initialization, but do not actually enable the
+ * VGIC CPU interface
*/
int kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu)
{
- int ret = 0;
+ struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
+ int ret = 0;
+ int i;
+
+ vgic_cpu->rd_iodev.base_addr = VGIC_ADDR_UNDEF;
+ vgic_cpu->sgi_iodev.base_addr = VGIC_ADDR_UNDEF;
+
+ INIT_LIST_HEAD(&vgic_cpu->ap_list_head);
+ spin_lock_init(&vgic_cpu->ap_list_lock);
+
+ /*
+ * Enable and configure all SGIs to be edge-triggered and
+ * configure all PPIs as level-triggered.
+ */
+ for (i = 0; i < VGIC_NR_PRIVATE_IRQS; i++) {
+ struct vgic_irq *irq = &vgic_cpu->private_irqs[i];
+
+ INIT_LIST_HEAD(&irq->ap_list);
+ spin_lock_init(&irq->irq_lock);
+ irq->intid = i;
+ irq->vcpu = NULL;
+ irq->target_vcpu = vcpu;
+ irq->targets = 1U << vcpu->vcpu_id;
+ kref_init(&irq->refcount);
+ if (vgic_irq_is_sgi(i)) {
+ /* SGIs */
+ irq->enabled = 1;
+ irq->config = VGIC_CONFIG_EDGE;
+ } else {
+ /* PPIs */
+ irq->config = VGIC_CONFIG_LEVEL;
+ }
+ }
if (!irqchip_in_kernel(vcpu->kvm))
return 0;
@@ -303,13 +303,23 @@ out:
static void kvm_vgic_dist_destroy(struct kvm *kvm)
{
struct vgic_dist *dist = &kvm->arch.vgic;
+ struct vgic_redist_region *rdreg, *next;
dist->ready = false;
dist->initialized = false;
kfree(dist->spis);
+ dist->spis = NULL;
dist->nr_spis = 0;
+ if (kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3) {
+ list_for_each_entry_safe(rdreg, next, &dist->rd_regions, list) {
+ list_del(&rdreg->list);
+ kfree(rdreg);
+ }
+ INIT_LIST_HEAD(&dist->rd_regions);
+ }
+
if (vgic_supports_direct_msis(kvm))
vgic_v4_teardown(kvm);
}
@@ -423,7 +433,7 @@ static irqreturn_t vgic_maintenance_handler(int irq, void *data)
* We cannot rely on the vgic maintenance interrupt to be
* delivered synchronously. This means we can only use it to
* exit the VM, and we perform the handling of EOIed
- * interrupts on the exit path (see vgic_process_maintenance).
+ * interrupts on the exit path (see vgic_fold_lr_state).
*/
return IRQ_HANDLED;
}
diff --git a/virt/kvm/arm/vgic/vgic-its.c b/virt/kvm/arm/vgic/vgic-its.c
index a8f07243aa9f..4ed79c939fb4 100644
--- a/virt/kvm/arm/vgic/vgic-its.c
+++ b/virt/kvm/arm/vgic/vgic-its.c
@@ -52,6 +52,7 @@ static struct vgic_irq *vgic_add_lpi(struct kvm *kvm, u32 intid,
{
struct vgic_dist *dist = &kvm->arch.vgic;
struct vgic_irq *irq = vgic_get_irq(kvm, NULL, intid), *oldirq;
+ unsigned long flags;
int ret;
/* In this case there is no put, since we keep the reference. */
@@ -71,7 +72,7 @@ static struct vgic_irq *vgic_add_lpi(struct kvm *kvm, u32 intid,
irq->intid = intid;
irq->target_vcpu = vcpu;
- spin_lock(&dist->lpi_list_lock);
+ spin_lock_irqsave(&dist->lpi_list_lock, flags);
/*
* There could be a race with another vgic_add_lpi(), so we need to
@@ -99,7 +100,7 @@ static struct vgic_irq *vgic_add_lpi(struct kvm *kvm, u32 intid,
dist->lpi_list_count++;
out_unlock:
- spin_unlock(&dist->lpi_list_lock);
+ spin_unlock_irqrestore(&dist->lpi_list_lock, flags);
/*
* We "cache" the configuration table entries in our struct vgic_irq's.
@@ -280,8 +281,8 @@ static int update_lpi_config(struct kvm *kvm, struct vgic_irq *irq,
int ret;
unsigned long flags;
- ret = kvm_read_guest(kvm, propbase + irq->intid - GIC_LPI_OFFSET,
- &prop, 1);
+ ret = kvm_read_guest_lock(kvm, propbase + irq->intid - GIC_LPI_OFFSET,
+ &prop, 1);
if (ret)
return ret;
@@ -315,6 +316,7 @@ static int vgic_copy_lpi_list(struct kvm_vcpu *vcpu, u32 **intid_ptr)
{
struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
struct vgic_irq *irq;
+ unsigned long flags;
u32 *intids;
int irq_count, i = 0;
@@ -330,7 +332,7 @@ static int vgic_copy_lpi_list(struct kvm_vcpu *vcpu, u32 **intid_ptr)
if (!intids)
return -ENOMEM;
- spin_lock(&dist->lpi_list_lock);
+ spin_lock_irqsave(&dist->lpi_list_lock, flags);
list_for_each_entry(irq, &dist->lpi_list_head, lpi_list) {
if (i == irq_count)
break;
@@ -339,7 +341,7 @@ static int vgic_copy_lpi_list(struct kvm_vcpu *vcpu, u32 **intid_ptr)
continue;
intids[i++] = irq->intid;
}
- spin_unlock(&dist->lpi_list_lock);
+ spin_unlock_irqrestore(&dist->lpi_list_lock, flags);
*intid_ptr = intids;
return i;
@@ -348,10 +350,11 @@ static int vgic_copy_lpi_list(struct kvm_vcpu *vcpu, u32 **intid_ptr)
static int update_affinity(struct vgic_irq *irq, struct kvm_vcpu *vcpu)
{
int ret = 0;
+ unsigned long flags;
- spin_lock(&irq->irq_lock);
+ spin_lock_irqsave(&irq->irq_lock, flags);
irq->target_vcpu = vcpu;
- spin_unlock(&irq->irq_lock);
+ spin_unlock_irqrestore(&irq->irq_lock, flags);
if (irq->hw) {
struct its_vlpi_map map;
@@ -441,8 +444,9 @@ static int its_sync_lpi_pending_table(struct kvm_vcpu *vcpu)
* this very same byte in the last iteration. Reuse that.
*/
if (byte_offset != last_byte_offset) {
- ret = kvm_read_guest(vcpu->kvm, pendbase + byte_offset,
- &pendmask, 1);
+ ret = kvm_read_guest_lock(vcpu->kvm,
+ pendbase + byte_offset,
+ &pendmask, 1);
if (ret) {
kfree(intids);
return ret;
@@ -786,7 +790,7 @@ static bool vgic_its_check_id(struct vgic_its *its, u64 baser, u32 id,
return false;
/* Each 1st level entry is represented by a 64-bit value. */
- if (kvm_read_guest(its->dev->kvm,
+ if (kvm_read_guest_lock(its->dev->kvm,
BASER_ADDRESS(baser) + index * sizeof(indirect_ptr),
&indirect_ptr, sizeof(indirect_ptr)))
return false;
@@ -1367,8 +1371,8 @@ static void vgic_its_process_commands(struct kvm *kvm, struct vgic_its *its)
cbaser = CBASER_ADDRESS(its->cbaser);
while (its->cwriter != its->creadr) {
- int ret = kvm_read_guest(kvm, cbaser + its->creadr,
- cmd_buf, ITS_CMD_SIZE);
+ int ret = kvm_read_guest_lock(kvm, cbaser + its->creadr,
+ cmd_buf, ITS_CMD_SIZE);
/*
* If kvm_read_guest() fails, this could be due to the guest
* programming a bogus value in CBASER or something else going
@@ -1893,7 +1897,7 @@ static int scan_its_table(struct vgic_its *its, gpa_t base, int size, int esz,
int next_offset;
size_t byte_offset;
- ret = kvm_read_guest(kvm, gpa, entry, esz);
+ ret = kvm_read_guest_lock(kvm, gpa, entry, esz);
if (ret)
return ret;
@@ -2263,7 +2267,7 @@ static int vgic_its_restore_cte(struct vgic_its *its, gpa_t gpa, int esz)
int ret;
BUG_ON(esz > sizeof(val));
- ret = kvm_read_guest(kvm, gpa, &val, esz);
+ ret = kvm_read_guest_lock(kvm, gpa, &val, esz);
if (ret)
return ret;
val = le64_to_cpu(val);
diff --git a/virt/kvm/arm/vgic/vgic-kvm-device.c b/virt/kvm/arm/vgic/vgic-kvm-device.c
index 10ae6f394b71..6ada2432e37c 100644
--- a/virt/kvm/arm/vgic/vgic-kvm-device.c
+++ b/virt/kvm/arm/vgic/vgic-kvm-device.c
@@ -66,6 +66,7 @@ int kvm_vgic_addr(struct kvm *kvm, unsigned long type, u64 *addr, bool write)
int r = 0;
struct vgic_dist *vgic = &kvm->arch.vgic;
phys_addr_t *addr_ptr, alignment;
+ u64 undef_value = VGIC_ADDR_UNDEF;
mutex_lock(&kvm->lock);
switch (type) {
@@ -84,16 +85,61 @@ int kvm_vgic_addr(struct kvm *kvm, unsigned long type, u64 *addr, bool write)
addr_ptr = &vgic->vgic_dist_base;
alignment = SZ_64K;
break;
- case KVM_VGIC_V3_ADDR_TYPE_REDIST:
+ case KVM_VGIC_V3_ADDR_TYPE_REDIST: {
+ struct vgic_redist_region *rdreg;
+
r = vgic_check_type(kvm, KVM_DEV_TYPE_ARM_VGIC_V3);
if (r)
break;
if (write) {
- r = vgic_v3_set_redist_base(kvm, *addr);
+ r = vgic_v3_set_redist_base(kvm, 0, *addr, 0);
goto out;
}
- addr_ptr = &vgic->vgic_redist_base;
+ rdreg = list_first_entry(&vgic->rd_regions,
+ struct vgic_redist_region, list);
+ if (!rdreg)
+ addr_ptr = &undef_value;
+ else
+ addr_ptr = &rdreg->base;
break;
+ }
+ case KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION:
+ {
+ struct vgic_redist_region *rdreg;
+ u8 index;
+
+ r = vgic_check_type(kvm, KVM_DEV_TYPE_ARM_VGIC_V3);
+ if (r)
+ break;
+
+ index = *addr & KVM_VGIC_V3_RDIST_INDEX_MASK;
+
+ if (write) {
+ gpa_t base = *addr & KVM_VGIC_V3_RDIST_BASE_MASK;
+ u32 count = (*addr & KVM_VGIC_V3_RDIST_COUNT_MASK)
+ >> KVM_VGIC_V3_RDIST_COUNT_SHIFT;
+ u8 flags = (*addr & KVM_VGIC_V3_RDIST_FLAGS_MASK)
+ >> KVM_VGIC_V3_RDIST_FLAGS_SHIFT;
+
+ if (!count || flags)
+ r = -EINVAL;
+ else
+ r = vgic_v3_set_redist_base(kvm, index,
+ base, count);
+ goto out;
+ }
+
+ rdreg = vgic_v3_rdist_region_from_index(kvm, index);
+ if (!rdreg) {
+ r = -ENOENT;
+ goto out;
+ }
+
+ *addr = index;
+ *addr |= rdreg->base;
+ *addr |= (u64)rdreg->count << KVM_VGIC_V3_RDIST_COUNT_SHIFT;
+ goto out;
+ }
default:
r = -ENODEV;
}
@@ -665,6 +711,7 @@ static int vgic_v3_has_attr(struct kvm_device *dev,
switch (attr->attr) {
case KVM_VGIC_V3_ADDR_TYPE_DIST:
case KVM_VGIC_V3_ADDR_TYPE_REDIST:
+ case KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION:
return 0;
}
break;
diff --git a/virt/kvm/arm/vgic/vgic-mmio-v3.c b/virt/kvm/arm/vgic/vgic-mmio-v3.c
index 671fe81f8e1d..287784095b5b 100644
--- a/virt/kvm/arm/vgic/vgic-mmio-v3.c
+++ b/virt/kvm/arm/vgic/vgic-mmio-v3.c
@@ -184,12 +184,17 @@ static unsigned long vgic_mmio_read_v3r_typer(struct kvm_vcpu *vcpu,
gpa_t addr, unsigned int len)
{
unsigned long mpidr = kvm_vcpu_get_mpidr_aff(vcpu);
+ struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
+ struct vgic_redist_region *rdreg = vgic_cpu->rdreg;
int target_vcpu_id = vcpu->vcpu_id;
+ gpa_t last_rdist_typer = rdreg->base + GICR_TYPER +
+ (rdreg->free_index - 1) * KVM_VGIC_V3_REDIST_SIZE;
u64 value;
value = (u64)(mpidr & GENMASK(23, 0)) << 32;
value |= ((target_vcpu_id & 0xffff) << 8);
- if (target_vcpu_id == atomic_read(&vcpu->kvm->online_vcpus) - 1)
+
+ if (addr == last_rdist_typer)
value |= GICR_TYPER_LAST;
if (vgic_has_its(vcpu->kvm))
value |= GICR_TYPER_PLPIS;
@@ -580,24 +585,32 @@ int vgic_register_redist_iodev(struct kvm_vcpu *vcpu)
{
struct kvm *kvm = vcpu->kvm;
struct vgic_dist *vgic = &kvm->arch.vgic;
+ struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
struct vgic_io_device *rd_dev = &vcpu->arch.vgic_cpu.rd_iodev;
struct vgic_io_device *sgi_dev = &vcpu->arch.vgic_cpu.sgi_iodev;
+ struct vgic_redist_region *rdreg;
gpa_t rd_base, sgi_base;
int ret;
+ if (!IS_VGIC_ADDR_UNDEF(vgic_cpu->rd_iodev.base_addr))
+ return 0;
+
/*
* We may be creating VCPUs before having set the base address for the
* redistributor region, in which case we will come back to this
* function for all VCPUs when the base address is set. Just return
* without doing any work for now.
*/
- if (IS_VGIC_ADDR_UNDEF(vgic->vgic_redist_base))
+ rdreg = vgic_v3_rdist_free_slot(&vgic->rd_regions);
+ if (!rdreg)
return 0;
if (!vgic_v3_check_base(kvm))
return -EINVAL;
- rd_base = vgic->vgic_redist_base + vgic->vgic_redist_free_offset;
+ vgic_cpu->rdreg = rdreg;
+
+ rd_base = rdreg->base + rdreg->free_index * KVM_VGIC_V3_REDIST_SIZE;
sgi_base = rd_base + SZ_64K;
kvm_iodevice_init(&rd_dev->dev, &kvm_io_gic_ops);
@@ -631,7 +644,7 @@ int vgic_register_redist_iodev(struct kvm_vcpu *vcpu)
goto out;
}
- vgic->vgic_redist_free_offset += 2 * SZ_64K;
+ rdreg->free_index++;
out:
mutex_unlock(&kvm->slots_lock);
return ret;
@@ -670,23 +683,96 @@ static int vgic_register_all_redist_iodevs(struct kvm *kvm)
return ret;
}
-int vgic_v3_set_redist_base(struct kvm *kvm, u64 addr)
+/**
+ * vgic_v3_insert_redist_region - Insert a new redistributor region
+ *
+ * Performs various checks before inserting the rdist region in the list.
+ * Those tests depend on whether the size of the rdist region is known
+ * (ie. count != 0). The list is sorted by rdist region index.
+ *
+ * @kvm: kvm handle
+ * @index: redist region index
+ * @base: base of the new rdist region
+ * @count: number of redistributors the region is made of (0 in the old style
+ * single region, whose size is induced from the number of vcpus)
+ *
+ * Return 0 on success, < 0 otherwise
+ */
+static int vgic_v3_insert_redist_region(struct kvm *kvm, uint32_t index,
+ gpa_t base, uint32_t count)
{
- struct vgic_dist *vgic = &kvm->arch.vgic;
+ struct vgic_dist *d = &kvm->arch.vgic;
+ struct vgic_redist_region *rdreg;
+ struct list_head *rd_regions = &d->rd_regions;
+ size_t size = count * KVM_VGIC_V3_REDIST_SIZE;
int ret;
- /* vgic_check_ioaddr makes sure we don't do this twice */
- ret = vgic_check_ioaddr(kvm, &vgic->vgic_redist_base, addr, SZ_64K);
- if (ret)
- return ret;
+ /* single rdist region already set ?*/
+ if (!count && !list_empty(rd_regions))
+ return -EINVAL;
- vgic->vgic_redist_base = addr;
- if (!vgic_v3_check_base(kvm)) {
- vgic->vgic_redist_base = VGIC_ADDR_UNDEF;
+ /* cross the end of memory ? */
+ if (base + size < base)
return -EINVAL;
+
+ if (list_empty(rd_regions)) {
+ if (index != 0)
+ return -EINVAL;
+ } else {
+ rdreg = list_last_entry(rd_regions,
+ struct vgic_redist_region, list);
+ if (index != rdreg->index + 1)
+ return -EINVAL;
+
+ /* Cannot add an explicitly sized regions after legacy region */
+ if (!rdreg->count)
+ return -EINVAL;
}
/*
+ * For legacy single-region redistributor regions (!count),
+ * check that the redistributor region does not overlap with the
+ * distributor's address space.
+ */
+ if (!count && !IS_VGIC_ADDR_UNDEF(d->vgic_dist_base) &&
+ vgic_dist_overlap(kvm, base, size))
+ return -EINVAL;
+
+ /* collision with any other rdist region? */
+ if (vgic_v3_rdist_overlap(kvm, base, size))
+ return -EINVAL;
+
+ rdreg = kzalloc(sizeof(*rdreg), GFP_KERNEL);
+ if (!rdreg)
+ return -ENOMEM;
+
+ rdreg->base = VGIC_ADDR_UNDEF;
+
+ ret = vgic_check_ioaddr(kvm, &rdreg->base, base, SZ_64K);
+ if (ret)
+ goto free;
+
+ rdreg->base = base;
+ rdreg->count = count;
+ rdreg->free_index = 0;
+ rdreg->index = index;
+
+ list_add_tail(&rdreg->list, rd_regions);
+ return 0;
+free:
+ kfree(rdreg);
+ return ret;
+}
+
+int vgic_v3_set_redist_base(struct kvm *kvm, u32 index, u64 addr, u32 count)
+{
+ int ret;
+
+ ret = vgic_v3_insert_redist_region(kvm, index, addr, count);
+ if (ret)
+ return ret;
+
+ /*
* Register iodevs for each existing VCPU. Adding more VCPUs
* afterwards will register the iodevs when needed.
*/
diff --git a/virt/kvm/arm/vgic/vgic-mmio.c b/virt/kvm/arm/vgic/vgic-mmio.c
index dbe99d635c80..ff9655cfeb2f 100644
--- a/virt/kvm/arm/vgic/vgic-mmio.c
+++ b/virt/kvm/arm/vgic/vgic-mmio.c
@@ -289,10 +289,16 @@ static void vgic_mmio_change_active(struct kvm_vcpu *vcpu, struct vgic_irq *irq,
irq->vcpu->cpu != -1) /* VCPU thread is running */
cond_resched_lock(&irq->irq_lock);
- if (irq->hw)
+ if (irq->hw) {
vgic_hw_irq_change_active(vcpu, irq, active, !requester_vcpu);
- else
+ } else {
+ u32 model = vcpu->kvm->arch.vgic.vgic_model;
+
irq->active = active;
+ if (model == KVM_DEV_TYPE_ARM_VGIC_V2 &&
+ active && vgic_irq_is_sgi(irq->intid))
+ irq->active_source = requester_vcpu->vcpu_id;
+ }
if (irq->active)
vgic_queue_irq_unlock(vcpu->kvm, irq, flags);
diff --git a/virt/kvm/arm/vgic/vgic-v2.c b/virt/kvm/arm/vgic/vgic-v2.c
index 45aa433f018f..a5f2e44f1c33 100644
--- a/virt/kvm/arm/vgic/vgic-v2.c
+++ b/virt/kvm/arm/vgic/vgic-v2.c
@@ -37,13 +37,6 @@ void vgic_v2_init_lrs(void)
vgic_v2_write_lr(i, 0);
}
-void vgic_v2_set_npie(struct kvm_vcpu *vcpu)
-{
- struct vgic_v2_cpu_if *cpuif = &vcpu->arch.vgic_cpu.vgic_v2;
-
- cpuif->vgic_hcr |= GICH_HCR_NPIE;
-}
-
void vgic_v2_set_underflow(struct kvm_vcpu *vcpu)
{
struct vgic_v2_cpu_if *cpuif = &vcpu->arch.vgic_cpu.vgic_v2;
@@ -71,13 +64,18 @@ void vgic_v2_fold_lr_state(struct kvm_vcpu *vcpu)
int lr;
unsigned long flags;
- cpuif->vgic_hcr &= ~(GICH_HCR_UIE | GICH_HCR_NPIE);
+ cpuif->vgic_hcr &= ~GICH_HCR_UIE;
for (lr = 0; lr < vgic_cpu->used_lrs; lr++) {
u32 val = cpuif->vgic_lr[lr];
- u32 intid = val & GICH_LR_VIRTUALID;
+ u32 cpuid, intid = val & GICH_LR_VIRTUALID;
struct vgic_irq *irq;
+ /* Extract the source vCPU id from the LR */
+ cpuid = val & GICH_LR_PHYSID_CPUID;
+ cpuid >>= GICH_LR_PHYSID_CPUID_SHIFT;
+ cpuid &= 7;
+
/* Notify fds when the guest EOI'ed a level-triggered SPI */
if (lr_signals_eoi_mi(val) && vgic_valid_spi(vcpu->kvm, intid))
kvm_notify_acked_irq(vcpu->kvm, 0,
@@ -90,17 +88,16 @@ void vgic_v2_fold_lr_state(struct kvm_vcpu *vcpu)
/* Always preserve the active bit */
irq->active = !!(val & GICH_LR_ACTIVE_BIT);
+ if (irq->active && vgic_irq_is_sgi(intid))
+ irq->active_source = cpuid;
+
/* Edge is the only case where we preserve the pending bit */
if (irq->config == VGIC_CONFIG_EDGE &&
(val & GICH_LR_PENDING_BIT)) {
irq->pending_latch = true;
- if (vgic_irq_is_sgi(intid)) {
- u32 cpuid = val & GICH_LR_PHYSID_CPUID;
-
- cpuid >>= GICH_LR_PHYSID_CPUID_SHIFT;
+ if (vgic_irq_is_sgi(intid))
irq->source |= (1 << cpuid);
- }
}
/*
@@ -152,8 +149,15 @@ void vgic_v2_populate_lr(struct kvm_vcpu *vcpu, struct vgic_irq *irq, int lr)
u32 val = irq->intid;
bool allow_pending = true;
- if (irq->active)
+ if (irq->active) {
val |= GICH_LR_ACTIVE_BIT;
+ if (vgic_irq_is_sgi(irq->intid))
+ val |= irq->active_source << GICH_LR_PHYSID_CPUID_SHIFT;
+ if (vgic_irq_is_multi_sgi(irq)) {
+ allow_pending = false;
+ val |= GICH_LR_EOI;
+ }
+ }
if (irq->hw) {
val |= GICH_LR_HW;
@@ -190,8 +194,10 @@ void vgic_v2_populate_lr(struct kvm_vcpu *vcpu, struct vgic_irq *irq, int lr)
BUG_ON(!src);
val |= (src - 1) << GICH_LR_PHYSID_CPUID_SHIFT;
irq->source &= ~(1 << (src - 1));
- if (irq->source)
+ if (irq->source) {
irq->pending_latch = true;
+ val |= GICH_LR_EOI;
+ }
}
}
diff --git a/virt/kvm/arm/vgic/vgic-v3.c b/virt/kvm/arm/vgic/vgic-v3.c
index 8195f52ae6f0..cdce653e3c47 100644
--- a/virt/kvm/arm/vgic/vgic-v3.c
+++ b/virt/kvm/arm/vgic/vgic-v3.c
@@ -27,13 +27,6 @@ static bool group1_trap;
static bool common_trap;
static bool gicv4_enable;
-void vgic_v3_set_npie(struct kvm_vcpu *vcpu)
-{
- struct vgic_v3_cpu_if *cpuif = &vcpu->arch.vgic_cpu.vgic_v3;
-
- cpuif->vgic_hcr |= ICH_HCR_NPIE;
-}
-
void vgic_v3_set_underflow(struct kvm_vcpu *vcpu)
{
struct vgic_v3_cpu_if *cpuif = &vcpu->arch.vgic_cpu.vgic_v3;
@@ -55,17 +48,23 @@ void vgic_v3_fold_lr_state(struct kvm_vcpu *vcpu)
int lr;
unsigned long flags;
- cpuif->vgic_hcr &= ~(ICH_HCR_UIE | ICH_HCR_NPIE);
+ cpuif->vgic_hcr &= ~ICH_HCR_UIE;
for (lr = 0; lr < vgic_cpu->used_lrs; lr++) {
u64 val = cpuif->vgic_lr[lr];
- u32 intid;
+ u32 intid, cpuid;
struct vgic_irq *irq;
+ bool is_v2_sgi = false;
+
+ cpuid = val & GICH_LR_PHYSID_CPUID;
+ cpuid >>= GICH_LR_PHYSID_CPUID_SHIFT;
- if (model == KVM_DEV_TYPE_ARM_VGIC_V3)
+ if (model == KVM_DEV_TYPE_ARM_VGIC_V3) {
intid = val & ICH_LR_VIRTUAL_ID_MASK;
- else
+ } else {
intid = val & GICH_LR_VIRTUALID;
+ is_v2_sgi = vgic_irq_is_sgi(intid);
+ }
/* Notify fds when the guest EOI'ed a level-triggered IRQ */
if (lr_signals_eoi_mi(val) && vgic_valid_spi(vcpu->kvm, intid))
@@ -81,18 +80,16 @@ void vgic_v3_fold_lr_state(struct kvm_vcpu *vcpu)
/* Always preserve the active bit */
irq->active = !!(val & ICH_LR_ACTIVE_BIT);
+ if (irq->active && is_v2_sgi)
+ irq->active_source = cpuid;
+
/* Edge is the only case where we preserve the pending bit */
if (irq->config == VGIC_CONFIG_EDGE &&
(val & ICH_LR_PENDING_BIT)) {
irq->pending_latch = true;
- if (vgic_irq_is_sgi(intid) &&
- model == KVM_DEV_TYPE_ARM_VGIC_V2) {
- u32 cpuid = val & GICH_LR_PHYSID_CPUID;
-
- cpuid >>= GICH_LR_PHYSID_CPUID_SHIFT;
+ if (is_v2_sgi)
irq->source |= (1 << cpuid);
- }
}
/*
@@ -133,10 +130,20 @@ void vgic_v3_populate_lr(struct kvm_vcpu *vcpu, struct vgic_irq *irq, int lr)
{
u32 model = vcpu->kvm->arch.vgic.vgic_model;
u64 val = irq->intid;
- bool allow_pending = true;
+ bool allow_pending = true, is_v2_sgi;
+
+ is_v2_sgi = (vgic_irq_is_sgi(irq->intid) &&
+ model == KVM_DEV_TYPE_ARM_VGIC_V2);
- if (irq->active)
+ if (irq->active) {
val |= ICH_LR_ACTIVE_BIT;
+ if (is_v2_sgi)
+ val |= irq->active_source << GICH_LR_PHYSID_CPUID_SHIFT;
+ if (vgic_irq_is_multi_sgi(irq)) {
+ allow_pending = false;
+ val |= ICH_LR_EOI;
+ }
+ }
if (irq->hw) {
val |= ICH_LR_HW;
@@ -174,8 +181,10 @@ void vgic_v3_populate_lr(struct kvm_vcpu *vcpu, struct vgic_irq *irq, int lr)
BUG_ON(!src);
val |= (src - 1) << GICH_LR_PHYSID_CPUID_SHIFT;
irq->source &= ~(1 << (src - 1));
- if (irq->source)
+ if (irq->source) {
irq->pending_latch = true;
+ val |= ICH_LR_EOI;
+ }
}
}
@@ -335,7 +344,7 @@ retry:
bit_nr = irq->intid % BITS_PER_BYTE;
ptr = pendbase + byte_offset;
- ret = kvm_read_guest(kvm, ptr, &val, 1);
+ ret = kvm_read_guest_lock(kvm, ptr, &val, 1);
if (ret)
return ret;
@@ -388,7 +397,7 @@ int vgic_v3_save_pending_tables(struct kvm *kvm)
ptr = pendbase + byte_offset;
if (byte_offset != last_byte_offset) {
- ret = kvm_read_guest(kvm, ptr, &val, 1);
+ ret = kvm_read_guest_lock(kvm, ptr, &val, 1);
if (ret)
return ret;
last_byte_offset = byte_offset;
@@ -410,6 +419,29 @@ int vgic_v3_save_pending_tables(struct kvm *kvm)
return 0;
}
+/**
+ * vgic_v3_rdist_overlap - check if a region overlaps with any
+ * existing redistributor region
+ *
+ * @kvm: kvm handle
+ * @base: base of the region
+ * @size: size of region
+ *
+ * Return: true if there is an overlap
+ */
+bool vgic_v3_rdist_overlap(struct kvm *kvm, gpa_t base, size_t size)
+{
+ struct vgic_dist *d = &kvm->arch.vgic;
+ struct vgic_redist_region *rdreg;
+
+ list_for_each_entry(rdreg, &d->rd_regions, list) {
+ if ((base + size > rdreg->base) &&
+ (base < rdreg->base + vgic_v3_rd_region_size(kvm, rdreg)))
+ return true;
+ }
+ return false;
+}
+
/*
* Check for overlapping regions and for regions crossing the end of memory
* for base addresses which have already been set.
@@ -417,41 +449,83 @@ int vgic_v3_save_pending_tables(struct kvm *kvm)
bool vgic_v3_check_base(struct kvm *kvm)
{
struct vgic_dist *d = &kvm->arch.vgic;
- gpa_t redist_size = KVM_VGIC_V3_REDIST_SIZE;
-
- redist_size *= atomic_read(&kvm->online_vcpus);
+ struct vgic_redist_region *rdreg;
if (!IS_VGIC_ADDR_UNDEF(d->vgic_dist_base) &&
d->vgic_dist_base + KVM_VGIC_V3_DIST_SIZE < d->vgic_dist_base)
return false;
- if (!IS_VGIC_ADDR_UNDEF(d->vgic_redist_base) &&
- d->vgic_redist_base + redist_size < d->vgic_redist_base)
- return false;
+ list_for_each_entry(rdreg, &d->rd_regions, list) {
+ if (rdreg->base + vgic_v3_rd_region_size(kvm, rdreg) <
+ rdreg->base)
+ return false;
+ }
- /* Both base addresses must be set to check if they overlap */
- if (IS_VGIC_ADDR_UNDEF(d->vgic_dist_base) ||
- IS_VGIC_ADDR_UNDEF(d->vgic_redist_base))
+ if (IS_VGIC_ADDR_UNDEF(d->vgic_dist_base))
return true;
- if (d->vgic_dist_base + KVM_VGIC_V3_DIST_SIZE <= d->vgic_redist_base)
- return true;
- if (d->vgic_redist_base + redist_size <= d->vgic_dist_base)
- return true;
+ return !vgic_v3_rdist_overlap(kvm, d->vgic_dist_base,
+ KVM_VGIC_V3_DIST_SIZE);
+}
- return false;
+/**
+ * vgic_v3_rdist_free_slot - Look up registered rdist regions and identify one
+ * which has free space to put a new rdist region.
+ *
+ * @rd_regions: redistributor region list head
+ *
+ * A redistributor regions maps n redistributors, n = region size / (2 x 64kB).
+ * Stride between redistributors is 0 and regions are filled in the index order.
+ *
+ * Return: the redist region handle, if any, that has space to map a new rdist
+ * region.
+ */
+struct vgic_redist_region *vgic_v3_rdist_free_slot(struct list_head *rd_regions)
+{
+ struct vgic_redist_region *rdreg;
+
+ list_for_each_entry(rdreg, rd_regions, list) {
+ if (!vgic_v3_redist_region_full(rdreg))
+ return rdreg;
+ }
+ return NULL;
}
+struct vgic_redist_region *vgic_v3_rdist_region_from_index(struct kvm *kvm,
+ u32 index)
+{
+ struct list_head *rd_regions = &kvm->arch.vgic.rd_regions;
+ struct vgic_redist_region *rdreg;
+
+ list_for_each_entry(rdreg, rd_regions, list) {
+ if (rdreg->index == index)
+ return rdreg;
+ }
+ return NULL;
+}
+
+
int vgic_v3_map_resources(struct kvm *kvm)
{
- int ret = 0;
struct vgic_dist *dist = &kvm->arch.vgic;
+ struct kvm_vcpu *vcpu;
+ int ret = 0;
+ int c;
if (vgic_ready(kvm))
goto out;
- if (IS_VGIC_ADDR_UNDEF(dist->vgic_dist_base) ||
- IS_VGIC_ADDR_UNDEF(dist->vgic_redist_base)) {
+ kvm_for_each_vcpu(c, vcpu, kvm) {
+ struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
+
+ if (IS_VGIC_ADDR_UNDEF(vgic_cpu->rd_iodev.base_addr)) {
+ kvm_debug("vcpu %d redistributor base not set\n", c);
+ ret = -ENXIO;
+ goto out;
+ }
+ }
+
+ if (IS_VGIC_ADDR_UNDEF(dist->vgic_dist_base)) {
kvm_err("Need to set vgic distributor addresses first\n");
ret = -ENXIO;
goto out;
@@ -543,11 +617,6 @@ int vgic_v3_probe(const struct gic_kvm_info *info)
pr_warn("GICV physical address 0x%llx not page aligned\n",
(unsigned long long)info->vcpu.start);
kvm_vgic_global_state.vcpu_base = 0;
- } else if (!PAGE_ALIGNED(resource_size(&info->vcpu))) {
- pr_warn("GICV size 0x%llx not a multiple of page size 0x%lx\n",
- (unsigned long long)resource_size(&info->vcpu),
- PAGE_SIZE);
- kvm_vgic_global_state.vcpu_base = 0;
} else {
kvm_vgic_global_state.vcpu_base = info->vcpu.start;
kvm_vgic_global_state.can_emulate_gicv2 = true;
diff --git a/virt/kvm/arm/vgic/vgic-v4.c b/virt/kvm/arm/vgic/vgic-v4.c
index bc4265154bac..1ed5f2286b8e 100644
--- a/virt/kvm/arm/vgic/vgic-v4.c
+++ b/virt/kvm/arm/vgic/vgic-v4.c
@@ -126,7 +126,7 @@ int vgic_v4_init(struct kvm *kvm)
nr_vcpus = atomic_read(&kvm->online_vcpus);
- dist->its_vm.vpes = kzalloc(sizeof(*dist->its_vm.vpes) * nr_vcpus,
+ dist->its_vm.vpes = kcalloc(nr_vcpus, sizeof(*dist->its_vm.vpes),
GFP_KERNEL);
if (!dist->its_vm.vpes)
return -ENOMEM;
diff --git a/virt/kvm/arm/vgic/vgic.c b/virt/kvm/arm/vgic/vgic.c
index 702936cbe173..33c8325c8f35 100644
--- a/virt/kvm/arm/vgic/vgic.c
+++ b/virt/kvm/arm/vgic/vgic.c
@@ -43,9 +43,13 @@ struct vgic_global kvm_vgic_global_state __ro_after_init = {
* kvm->lock (mutex)
* its->cmd_lock (mutex)
* its->its_lock (mutex)
- * vgic_cpu->ap_list_lock
- * kvm->lpi_list_lock
- * vgic_irq->irq_lock
+ * vgic_cpu->ap_list_lock must be taken with IRQs disabled
+ * kvm->lpi_list_lock must be taken with IRQs disabled
+ * vgic_irq->irq_lock must be taken with IRQs disabled
+ *
+ * As the ap_list_lock might be taken from the timer interrupt handler,
+ * we have to disable IRQs before taking this lock and everything lower
+ * than it.
*
* If you need to take multiple locks, always take the upper lock first,
* then the lower ones, e.g. first take the its_lock, then the irq_lock.
@@ -72,8 +76,9 @@ static struct vgic_irq *vgic_get_lpi(struct kvm *kvm, u32 intid)
{
struct vgic_dist *dist = &kvm->arch.vgic;
struct vgic_irq *irq = NULL;
+ unsigned long flags;
- spin_lock(&dist->lpi_list_lock);
+ spin_lock_irqsave(&dist->lpi_list_lock, flags);
list_for_each_entry(irq, &dist->lpi_list_head, lpi_list) {
if (irq->intid != intid)
@@ -89,7 +94,7 @@ static struct vgic_irq *vgic_get_lpi(struct kvm *kvm, u32 intid)
irq = NULL;
out_unlock:
- spin_unlock(&dist->lpi_list_lock);
+ spin_unlock_irqrestore(&dist->lpi_list_lock, flags);
return irq;
}
@@ -134,19 +139,20 @@ static void vgic_irq_release(struct kref *ref)
void vgic_put_irq(struct kvm *kvm, struct vgic_irq *irq)
{
struct vgic_dist *dist = &kvm->arch.vgic;
+ unsigned long flags;
if (irq->intid < VGIC_MIN_LPI)
return;
- spin_lock(&dist->lpi_list_lock);
+ spin_lock_irqsave(&dist->lpi_list_lock, flags);
if (!kref_put(&irq->refcount, vgic_irq_release)) {
- spin_unlock(&dist->lpi_list_lock);
+ spin_unlock_irqrestore(&dist->lpi_list_lock, flags);
return;
};
list_del(&irq->lpi_list);
dist->lpi_list_count--;
- spin_unlock(&dist->lpi_list_lock);
+ spin_unlock_irqrestore(&dist->lpi_list_lock, flags);
kfree(irq);
}
@@ -725,14 +731,6 @@ static inline void vgic_set_underflow(struct kvm_vcpu *vcpu)
vgic_v3_set_underflow(vcpu);
}
-static inline void vgic_set_npie(struct kvm_vcpu *vcpu)
-{
- if (kvm_vgic_global_state.type == VGIC_V2)
- vgic_v2_set_npie(vcpu);
- else
- vgic_v3_set_npie(vcpu);
-}
-
/* Requires the ap_list_lock to be held. */
static int compute_ap_list_depth(struct kvm_vcpu *vcpu,
bool *multi_sgi)
@@ -746,17 +744,15 @@ static int compute_ap_list_depth(struct kvm_vcpu *vcpu,
DEBUG_SPINLOCK_BUG_ON(!spin_is_locked(&vgic_cpu->ap_list_lock));
list_for_each_entry(irq, &vgic_cpu->ap_list_head, ap_list) {
+ int w;
+
spin_lock(&irq->irq_lock);
/* GICv2 SGIs can count for more than one... */
- if (vgic_irq_is_sgi(irq->intid) && irq->source) {
- int w = hweight8(irq->source);
-
- count += w;
- *multi_sgi |= (w > 1);
- } else {
- count++;
- }
+ w = vgic_irq_get_lr_count(irq);
spin_unlock(&irq->irq_lock);
+
+ count += w;
+ *multi_sgi |= (w > 1);
}
return count;
}
@@ -767,7 +763,6 @@ static void vgic_flush_lr_state(struct kvm_vcpu *vcpu)
struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
struct vgic_irq *irq;
int count;
- bool npie = false;
bool multi_sgi;
u8 prio = 0xff;
@@ -797,10 +792,8 @@ static void vgic_flush_lr_state(struct kvm_vcpu *vcpu)
if (likely(vgic_target_oracle(irq) == vcpu)) {
vgic_populate_lr(vcpu, irq, count++);
- if (irq->source) {
- npie = true;
+ if (irq->source)
prio = irq->priority;
- }
}
spin_unlock(&irq->irq_lock);
@@ -813,9 +806,6 @@ static void vgic_flush_lr_state(struct kvm_vcpu *vcpu)
}
}
- if (npie)
- vgic_set_npie(vcpu);
-
vcpu->arch.vgic_cpu.used_lrs = count;
/* Nuke remaining LRs */
diff --git a/virt/kvm/arm/vgic/vgic.h b/virt/kvm/arm/vgic/vgic.h
index 830e815748a0..ead00b2072b2 100644
--- a/virt/kvm/arm/vgic/vgic.h
+++ b/virt/kvm/arm/vgic/vgic.h
@@ -96,6 +96,13 @@
/* we only support 64 kB translation table page size */
#define KVM_ITS_L1E_ADDR_MASK GENMASK_ULL(51, 16)
+#define KVM_VGIC_V3_RDIST_INDEX_MASK GENMASK_ULL(11, 0)
+#define KVM_VGIC_V3_RDIST_FLAGS_MASK GENMASK_ULL(15, 12)
+#define KVM_VGIC_V3_RDIST_FLAGS_SHIFT 12
+#define KVM_VGIC_V3_RDIST_BASE_MASK GENMASK_ULL(51, 16)
+#define KVM_VGIC_V3_RDIST_COUNT_MASK GENMASK_ULL(63, 52)
+#define KVM_VGIC_V3_RDIST_COUNT_SHIFT 52
+
/* Requires the irq_lock to be held by the caller. */
static inline bool irq_is_pending(struct vgic_irq *irq)
{
@@ -110,6 +117,20 @@ static inline bool vgic_irq_is_mapped_level(struct vgic_irq *irq)
return irq->config == VGIC_CONFIG_LEVEL && irq->hw;
}
+static inline int vgic_irq_get_lr_count(struct vgic_irq *irq)
+{
+ /* Account for the active state as an interrupt */
+ if (vgic_irq_is_sgi(irq->intid) && irq->source)
+ return hweight8(irq->source) + irq->active;
+
+ return irq_is_pending(irq) || irq->active;
+}
+
+static inline bool vgic_irq_is_multi_sgi(struct vgic_irq *irq)
+{
+ return vgic_irq_get_lr_count(irq) > 1;
+}
+
/*
* This struct provides an intermediate representation of the fields contained
* in the GICH_VMCR and ICH_VMCR registers, such that code exporting the GIC
@@ -201,7 +222,7 @@ int vgic_v3_probe(const struct gic_kvm_info *info);
int vgic_v3_map_resources(struct kvm *kvm);
int vgic_v3_lpi_sync_pending_status(struct kvm *kvm, struct vgic_irq *irq);
int vgic_v3_save_pending_tables(struct kvm *kvm);
-int vgic_v3_set_redist_base(struct kvm *kvm, u64 addr);
+int vgic_v3_set_redist_base(struct kvm *kvm, u32 index, u64 addr, u32 count);
int vgic_register_redist_iodev(struct kvm_vcpu *vcpu);
bool vgic_v3_check_base(struct kvm *kvm);
@@ -229,8 +250,8 @@ void vgic_get_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr);
int vgic_lazy_init(struct kvm *kvm);
int vgic_init(struct kvm *kvm);
-int vgic_debug_init(struct kvm *kvm);
-int vgic_debug_destroy(struct kvm *kvm);
+void vgic_debug_init(struct kvm *kvm);
+void vgic_debug_destroy(struct kvm *kvm);
bool lock_all_vcpus(struct kvm *kvm);
void unlock_all_vcpus(struct kvm *kvm);
@@ -251,6 +272,39 @@ static inline int vgic_v3_max_apr_idx(struct kvm_vcpu *vcpu)
}
}
+static inline bool
+vgic_v3_redist_region_full(struct vgic_redist_region *region)
+{
+ if (!region->count)
+ return false;
+
+ return (region->free_index >= region->count);
+}
+
+struct vgic_redist_region *vgic_v3_rdist_free_slot(struct list_head *rdregs);
+
+static inline size_t
+vgic_v3_rd_region_size(struct kvm *kvm, struct vgic_redist_region *rdreg)
+{
+ if (!rdreg->count)
+ return atomic_read(&kvm->online_vcpus) * KVM_VGIC_V3_REDIST_SIZE;
+ else
+ return rdreg->count * KVM_VGIC_V3_REDIST_SIZE;
+}
+
+struct vgic_redist_region *vgic_v3_rdist_region_from_index(struct kvm *kvm,
+ u32 index);
+
+bool vgic_v3_rdist_overlap(struct kvm *kvm, gpa_t base, size_t size);
+
+static inline bool vgic_dist_overlap(struct kvm *kvm, gpa_t base, size_t size)
+{
+ struct vgic_dist *d = &kvm->arch.vgic;
+
+ return (base + size > d->vgic_dist_base) &&
+ (base < d->vgic_dist_base + KVM_VGIC_V3_DIST_SIZE);
+}
+
int vgic_its_resolve_lpi(struct kvm *kvm, struct vgic_its *its,
u32 devid, u32 eventid, struct vgic_irq **irq);
struct vgic_its *vgic_msi_to_its(struct kvm *kvm, struct kvm_msi *msi);
diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c
index 6e865e8b5b10..90d30fbe95ae 100644
--- a/virt/kvm/eventfd.c
+++ b/virt/kvm/eventfd.c
@@ -397,7 +397,7 @@ kvm_irqfd_assign(struct kvm *kvm, struct kvm_irqfd *args)
* Check if there was an event already pending on the eventfd
* before we registered, and trigger it as if we didn't miss it.
*/
- events = f.file->f_op->poll(f.file, &irqfd->pt);
+ events = vfs_poll(f.file, &irqfd->pt);
if (events & EPOLLIN)
schedule_work(&irqfd->inject);
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index c7b2e927f699..8b47507faab5 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -116,6 +116,11 @@ static long kvm_vcpu_ioctl(struct file *file, unsigned int ioctl,
#ifdef CONFIG_KVM_COMPAT
static long kvm_vcpu_compat_ioctl(struct file *file, unsigned int ioctl,
unsigned long arg);
+#define KVM_COMPAT(c) .compat_ioctl = (c)
+#else
+static long kvm_no_compat_ioctl(struct file *file, unsigned int ioctl,
+ unsigned long arg) { return -EINVAL; }
+#define KVM_COMPAT(c) .compat_ioctl = kvm_no_compat_ioctl
#endif
static int hardware_enable_all(void);
static void hardware_disable_all(void);
@@ -203,29 +208,47 @@ static inline bool kvm_kick_many_cpus(const struct cpumask *cpus, bool wait)
return true;
}
-bool kvm_make_all_cpus_request(struct kvm *kvm, unsigned int req)
+bool kvm_make_vcpus_request_mask(struct kvm *kvm, unsigned int req,
+ unsigned long *vcpu_bitmap, cpumask_var_t tmp)
{
int i, cpu, me;
- cpumask_var_t cpus;
- bool called;
struct kvm_vcpu *vcpu;
-
- zalloc_cpumask_var(&cpus, GFP_ATOMIC);
+ bool called;
me = get_cpu();
+
kvm_for_each_vcpu(i, vcpu, kvm) {
+ if (!test_bit(i, vcpu_bitmap))
+ continue;
+
kvm_make_request(req, vcpu);
cpu = vcpu->cpu;
if (!(req & KVM_REQUEST_NO_WAKEUP) && kvm_vcpu_wake_up(vcpu))
continue;
- if (cpus != NULL && cpu != -1 && cpu != me &&
+ if (tmp != NULL && cpu != -1 && cpu != me &&
kvm_request_needs_ipi(vcpu, req))
- __cpumask_set_cpu(cpu, cpus);
+ __cpumask_set_cpu(cpu, tmp);
}
- called = kvm_kick_many_cpus(cpus, !!(req & KVM_REQUEST_WAIT));
+
+ called = kvm_kick_many_cpus(tmp, !!(req & KVM_REQUEST_WAIT));
put_cpu();
+
+ return called;
+}
+
+bool kvm_make_all_cpus_request(struct kvm *kvm, unsigned int req)
+{
+ cpumask_var_t cpus;
+ bool called;
+ static unsigned long vcpu_bitmap[BITS_TO_LONGS(KVM_MAX_VCPUS)]
+ = {[0 ... BITS_TO_LONGS(KVM_MAX_VCPUS)-1] = ULONG_MAX};
+
+ zalloc_cpumask_var(&cpus, GFP_ATOMIC);
+
+ called = kvm_make_vcpus_request_mask(kvm, req, vcpu_bitmap, cpus);
+
free_cpumask_var(cpus);
return called;
}
@@ -572,10 +595,7 @@ static int kvm_create_vm_debugfs(struct kvm *kvm, int fd)
return 0;
snprintf(dir_name, sizeof(dir_name), "%d-%d", task_pid_nr(current), fd);
- kvm->debugfs_dentry = debugfs_create_dir(dir_name,
- kvm_debugfs_dir);
- if (!kvm->debugfs_dentry)
- return -ENOMEM;
+ kvm->debugfs_dentry = debugfs_create_dir(dir_name, kvm_debugfs_dir);
kvm->debugfs_stat_data = kcalloc(kvm_debugfs_num_entries,
sizeof(*kvm->debugfs_stat_data),
@@ -591,11 +611,8 @@ static int kvm_create_vm_debugfs(struct kvm *kvm, int fd)
stat_data->kvm = kvm;
stat_data->offset = p->offset;
kvm->debugfs_stat_data[p - debugfs_entries] = stat_data;
- if (!debugfs_create_file(p->name, 0644,
- kvm->debugfs_dentry,
- stat_data,
- stat_fops_per_vm[p->kind]))
- return -ENOMEM;
+ debugfs_create_file(p->name, 0644, kvm->debugfs_dentry,
+ stat_data, stat_fops_per_vm[p->kind]);
}
return 0;
}
@@ -2340,7 +2357,7 @@ void kvm_vcpu_on_spin(struct kvm_vcpu *me, bool yield_to_kernel_mode)
}
EXPORT_SYMBOL_GPL(kvm_vcpu_on_spin);
-static int kvm_vcpu_fault(struct vm_fault *vmf)
+static vm_fault_t kvm_vcpu_fault(struct vm_fault *vmf)
{
struct kvm_vcpu *vcpu = vmf->vma->vm_file->private_data;
struct page *page;
@@ -2384,11 +2401,9 @@ static int kvm_vcpu_release(struct inode *inode, struct file *filp)
static struct file_operations kvm_vcpu_fops = {
.release = kvm_vcpu_release,
.unlocked_ioctl = kvm_vcpu_ioctl,
-#ifdef CONFIG_KVM_COMPAT
- .compat_ioctl = kvm_vcpu_compat_ioctl,
-#endif
.mmap = kvm_vcpu_mmap,
.llseek = noop_llseek,
+ KVM_COMPAT(kvm_vcpu_compat_ioctl),
};
/*
@@ -2550,8 +2565,13 @@ static long kvm_vcpu_ioctl(struct file *filp,
oldpid = rcu_access_pointer(vcpu->pid);
if (unlikely(oldpid != current->pids[PIDTYPE_PID].pid)) {
/* The thread running this VCPU changed. */
- struct pid *newpid = get_task_pid(current, PIDTYPE_PID);
+ struct pid *newpid;
+ r = kvm_arch_vcpu_run_pid_change(vcpu);
+ if (r)
+ break;
+
+ newpid = get_task_pid(current, PIDTYPE_PID);
rcu_assign_pointer(vcpu->pid, newpid);
if (oldpid)
synchronize_rcu();
@@ -2807,10 +2827,8 @@ static int kvm_device_release(struct inode *inode, struct file *filp)
static const struct file_operations kvm_device_fops = {
.unlocked_ioctl = kvm_device_ioctl,
-#ifdef CONFIG_KVM_COMPAT
- .compat_ioctl = kvm_device_ioctl,
-#endif
.release = kvm_device_release,
+ KVM_COMPAT(kvm_device_ioctl),
};
struct kvm_device *kvm_device_from_filp(struct file *filp)
@@ -3059,7 +3077,8 @@ static long kvm_vm_ioctl(struct file *filp,
goto out;
if (routing.nr) {
r = -ENOMEM;
- entries = vmalloc(routing.nr * sizeof(*entries));
+ entries = vmalloc(array_size(sizeof(*entries),
+ routing.nr));
if (!entries)
goto out;
r = -EFAULT;
@@ -3147,10 +3166,8 @@ static long kvm_vm_compat_ioctl(struct file *filp,
static struct file_operations kvm_vm_fops = {
.release = kvm_vm_release,
.unlocked_ioctl = kvm_vm_ioctl,
-#ifdef CONFIG_KVM_COMPAT
- .compat_ioctl = kvm_vm_compat_ioctl,
-#endif
.llseek = noop_llseek,
+ KVM_COMPAT(kvm_vm_compat_ioctl),
};
static int kvm_dev_ioctl_create_vm(unsigned long type)
@@ -3241,8 +3258,8 @@ out:
static struct file_operations kvm_chardev_ops = {
.unlocked_ioctl = kvm_dev_ioctl,
- .compat_ioctl = kvm_dev_ioctl,
.llseek = noop_llseek,
+ KVM_COMPAT(kvm_dev_ioctl),
};
static struct miscdevice kvm_dev = {
@@ -3896,29 +3913,18 @@ static void kvm_uevent_notify_change(unsigned int type, struct kvm *kvm)
kfree(env);
}
-static int kvm_init_debug(void)
+static void kvm_init_debug(void)
{
- int r = -EEXIST;
struct kvm_stats_debugfs_item *p;
kvm_debugfs_dir = debugfs_create_dir("kvm", NULL);
- if (kvm_debugfs_dir == NULL)
- goto out;
kvm_debugfs_num_entries = 0;
for (p = debugfs_entries; p->name; ++p, kvm_debugfs_num_entries++) {
- if (!debugfs_create_file(p->name, 0644, kvm_debugfs_dir,
- (void *)(long)p->offset,
- stat_fops[p->kind]))
- goto out_dir;
+ debugfs_create_file(p->name, 0644, kvm_debugfs_dir,
+ (void *)(long)p->offset,
+ stat_fops[p->kind]);
}
-
- return 0;
-
-out_dir:
- debugfs_remove_recursive(kvm_debugfs_dir);
-out:
- return r;
}
static int kvm_suspend(void)
@@ -4046,20 +4052,13 @@ int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align,
kvm_preempt_ops.sched_in = kvm_sched_in;
kvm_preempt_ops.sched_out = kvm_sched_out;
- r = kvm_init_debug();
- if (r) {
- pr_err("kvm: create debugfs files failed\n");
- goto out_undebugfs;
- }
+ kvm_init_debug();
r = kvm_vfio_ops_init();
WARN_ON(r);
return 0;
-out_undebugfs:
- unregister_syscore_ops(&kvm_syscore_ops);
- misc_deregister(&kvm_dev);
out_unreg:
kvm_async_pf_deinit();
out_free:
Powered by cgit, Gruvboxed by Blaster4385.