summaryrefslogtreecommitdiffstats
path: root/virt/kvm
diff options
context:
space:
mode:
Diffstat (limited to 'virt/kvm')
-rw-r--r--virt/kvm/assigned-dev.c1
-rw-r--r--virt/kvm/coalesced_mmio.c1
-rw-r--r--virt/kvm/eventfd.c1
-rw-r--r--virt/kvm/ioapic.c31
-rw-r--r--virt/kvm/ioapic.h2
-rw-r--r--virt/kvm/iommu.c113
-rw-r--r--virt/kvm/irq_comm.c1
-rw-r--r--virt/kvm/kvm_main.c19
8 files changed, 125 insertions, 44 deletions
diff --git a/virt/kvm/assigned-dev.c b/virt/kvm/assigned-dev.c
index 057e2cca6af5..02ff2b19dbe2 100644
--- a/virt/kvm/assigned-dev.c
+++ b/virt/kvm/assigned-dev.c
@@ -16,6 +16,7 @@
#include <linux/spinlock.h>
#include <linux/pci.h>
#include <linux/interrupt.h>
+#include <linux/slab.h>
#include "irq.h"
static struct kvm_assigned_dev_kernel *kvm_find_assigned_dev(struct list_head *head,
diff --git a/virt/kvm/coalesced_mmio.c b/virt/kvm/coalesced_mmio.c
index 5169736377a3..36e258029649 100644
--- a/virt/kvm/coalesced_mmio.c
+++ b/virt/kvm/coalesced_mmio.c
@@ -10,6 +10,7 @@
#include "iodev.h"
#include <linux/kvm_host.h>
+#include <linux/slab.h>
#include <linux/kvm.h>
#include "coalesced_mmio.h"
diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c
index 7016319b1ec0..b81f0ebbaaad 100644
--- a/virt/kvm/eventfd.c
+++ b/virt/kvm/eventfd.c
@@ -30,6 +30,7 @@
#include <linux/list.h>
#include <linux/eventfd.h>
#include <linux/kernel.h>
+#include <linux/slab.h>
#include "iodev.h"
diff --git a/virt/kvm/ioapic.c b/virt/kvm/ioapic.c
index 3db15a807f80..7c79c1d76d0c 100644
--- a/virt/kvm/ioapic.c
+++ b/virt/kvm/ioapic.c
@@ -33,6 +33,7 @@
#include <linux/smp.h>
#include <linux/hrtimer.h>
#include <linux/io.h>
+#include <linux/slab.h>
#include <asm/processor.h>
#include <asm/page.h>
#include <asm/current.h>
@@ -196,7 +197,7 @@ int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int level)
union kvm_ioapic_redirect_entry entry;
int ret = 1;
- mutex_lock(&ioapic->lock);
+ spin_lock(&ioapic->lock);
if (irq >= 0 && irq < IOAPIC_NUM_PINS) {
entry = ioapic->redirtbl[irq];
level ^= entry.fields.polarity;
@@ -213,7 +214,7 @@ int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int level)
}
trace_kvm_ioapic_set_irq(entry.bits, irq, ret == 0);
}
- mutex_unlock(&ioapic->lock);
+ spin_unlock(&ioapic->lock);
return ret;
}
@@ -237,9 +238,9 @@ static void __kvm_ioapic_update_eoi(struct kvm_ioapic *ioapic, int vector,
* is dropped it will be put into irr and will be delivered
* after ack notifier returns.
*/
- mutex_unlock(&ioapic->lock);
+ spin_unlock(&ioapic->lock);
kvm_notify_acked_irq(ioapic->kvm, KVM_IRQCHIP_IOAPIC, i);
- mutex_lock(&ioapic->lock);
+ spin_lock(&ioapic->lock);
if (trigger_mode != IOAPIC_LEVEL_TRIG)
continue;
@@ -258,9 +259,9 @@ void kvm_ioapic_update_eoi(struct kvm *kvm, int vector, int trigger_mode)
smp_rmb();
if (!test_bit(vector, ioapic->handled_vectors))
return;
- mutex_lock(&ioapic->lock);
+ spin_lock(&ioapic->lock);
__kvm_ioapic_update_eoi(ioapic, vector, trigger_mode);
- mutex_unlock(&ioapic->lock);
+ spin_unlock(&ioapic->lock);
}
static inline struct kvm_ioapic *to_ioapic(struct kvm_io_device *dev)
@@ -286,7 +287,7 @@ static int ioapic_mmio_read(struct kvm_io_device *this, gpa_t addr, int len,
ASSERT(!(addr & 0xf)); /* check alignment */
addr &= 0xff;
- mutex_lock(&ioapic->lock);
+ spin_lock(&ioapic->lock);
switch (addr) {
case IOAPIC_REG_SELECT:
result = ioapic->ioregsel;
@@ -300,7 +301,7 @@ static int ioapic_mmio_read(struct kvm_io_device *this, gpa_t addr, int len,
result = 0;
break;
}
- mutex_unlock(&ioapic->lock);
+ spin_unlock(&ioapic->lock);
switch (len) {
case 8:
@@ -337,7 +338,7 @@ static int ioapic_mmio_write(struct kvm_io_device *this, gpa_t addr, int len,
}
addr &= 0xff;
- mutex_lock(&ioapic->lock);
+ spin_lock(&ioapic->lock);
switch (addr) {
case IOAPIC_REG_SELECT:
ioapic->ioregsel = data;
@@ -355,7 +356,7 @@ static int ioapic_mmio_write(struct kvm_io_device *this, gpa_t addr, int len,
default:
break;
}
- mutex_unlock(&ioapic->lock);
+ spin_unlock(&ioapic->lock);
return 0;
}
@@ -385,7 +386,7 @@ int kvm_ioapic_init(struct kvm *kvm)
ioapic = kzalloc(sizeof(struct kvm_ioapic), GFP_KERNEL);
if (!ioapic)
return -ENOMEM;
- mutex_init(&ioapic->lock);
+ spin_lock_init(&ioapic->lock);
kvm->arch.vioapic = ioapic;
kvm_ioapic_reset(ioapic);
kvm_iodevice_init(&ioapic->dev, &ioapic_mmio_ops);
@@ -418,9 +419,9 @@ int kvm_get_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state)
if (!ioapic)
return -EINVAL;
- mutex_lock(&ioapic->lock);
+ spin_lock(&ioapic->lock);
memcpy(state, ioapic, sizeof(struct kvm_ioapic_state));
- mutex_unlock(&ioapic->lock);
+ spin_unlock(&ioapic->lock);
return 0;
}
@@ -430,9 +431,9 @@ int kvm_set_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state)
if (!ioapic)
return -EINVAL;
- mutex_lock(&ioapic->lock);
+ spin_lock(&ioapic->lock);
memcpy(ioapic, state, sizeof(struct kvm_ioapic_state));
update_handled_vectors(ioapic);
- mutex_unlock(&ioapic->lock);
+ spin_unlock(&ioapic->lock);
return 0;
}
diff --git a/virt/kvm/ioapic.h b/virt/kvm/ioapic.h
index 8a751b78a430..0b190c34ccc3 100644
--- a/virt/kvm/ioapic.h
+++ b/virt/kvm/ioapic.h
@@ -45,7 +45,7 @@ struct kvm_ioapic {
struct kvm_io_device dev;
struct kvm *kvm;
void (*ack_notifier)(void *opaque, int irq);
- struct mutex lock;
+ spinlock_t lock;
DECLARE_BITMAP(handled_vectors, 256);
};
diff --git a/virt/kvm/iommu.c b/virt/kvm/iommu.c
index 80fd3ad3b2de..11692b9e8830 100644
--- a/virt/kvm/iommu.c
+++ b/virt/kvm/iommu.c
@@ -32,12 +32,30 @@ static int kvm_iommu_unmap_memslots(struct kvm *kvm);
static void kvm_iommu_put_pages(struct kvm *kvm,
gfn_t base_gfn, unsigned long npages);
+static pfn_t kvm_pin_pages(struct kvm *kvm, struct kvm_memory_slot *slot,
+ gfn_t gfn, unsigned long size)
+{
+ gfn_t end_gfn;
+ pfn_t pfn;
+
+ pfn = gfn_to_pfn_memslot(kvm, slot, gfn);
+ end_gfn = gfn + (size >> PAGE_SHIFT);
+ gfn += 1;
+
+ if (is_error_pfn(pfn))
+ return pfn;
+
+ while (gfn < end_gfn)
+ gfn_to_pfn_memslot(kvm, slot, gfn++);
+
+ return pfn;
+}
+
int kvm_iommu_map_pages(struct kvm *kvm, struct kvm_memory_slot *slot)
{
- gfn_t gfn = slot->base_gfn;
- unsigned long npages = slot->npages;
+ gfn_t gfn, end_gfn;
pfn_t pfn;
- int i, r = 0;
+ int r = 0;
struct iommu_domain *domain = kvm->arch.iommu_domain;
int flags;
@@ -45,31 +63,62 @@ int kvm_iommu_map_pages(struct kvm *kvm, struct kvm_memory_slot *slot)
if (!domain)
return 0;
+ gfn = slot->base_gfn;
+ end_gfn = gfn + slot->npages;
+
flags = IOMMU_READ | IOMMU_WRITE;
if (kvm->arch.iommu_flags & KVM_IOMMU_CACHE_COHERENCY)
flags |= IOMMU_CACHE;
- for (i = 0; i < npages; i++) {
- /* check if already mapped */
- if (iommu_iova_to_phys(domain, gfn_to_gpa(gfn)))
+
+ while (gfn < end_gfn) {
+ unsigned long page_size;
+
+ /* Check if already mapped */
+ if (iommu_iova_to_phys(domain, gfn_to_gpa(gfn))) {
+ gfn += 1;
+ continue;
+ }
+
+ /* Get the page size we could use to map */
+ page_size = kvm_host_page_size(kvm, gfn);
+
+ /* Make sure the page_size does not exceed the memslot */
+ while ((gfn + (page_size >> PAGE_SHIFT)) > end_gfn)
+ page_size >>= 1;
+
+ /* Make sure gfn is aligned to the page size we want to map */
+ while ((gfn << PAGE_SHIFT) & (page_size - 1))
+ page_size >>= 1;
+
+ /*
+ * Pin all pages we are about to map in memory. This is
+ * important because we unmap and unpin in 4kb steps later.
+ */
+ pfn = kvm_pin_pages(kvm, slot, gfn, page_size);
+ if (is_error_pfn(pfn)) {
+ gfn += 1;
continue;
+ }
- pfn = gfn_to_pfn_memslot(kvm, slot, gfn);
- r = iommu_map_range(domain,
- gfn_to_gpa(gfn),
- pfn_to_hpa(pfn),
- PAGE_SIZE, flags);
+ /* Map into IO address space */
+ r = iommu_map(domain, gfn_to_gpa(gfn), pfn_to_hpa(pfn),
+ get_order(page_size), flags);
if (r) {
printk(KERN_ERR "kvm_iommu_map_address:"
"iommu failed to map pfn=%lx\n", pfn);
goto unmap_pages;
}
- gfn++;
+
+ gfn += page_size >> PAGE_SHIFT;
+
+
}
+
return 0;
unmap_pages:
- kvm_iommu_put_pages(kvm, slot->base_gfn, i);
+ kvm_iommu_put_pages(kvm, slot->base_gfn, gfn);
return r;
}
@@ -189,27 +238,47 @@ out_unmap:
return r;
}
+static void kvm_unpin_pages(struct kvm *kvm, pfn_t pfn, unsigned long npages)
+{
+ unsigned long i;
+
+ for (i = 0; i < npages; ++i)
+ kvm_release_pfn_clean(pfn + i);
+}
+
static void kvm_iommu_put_pages(struct kvm *kvm,
gfn_t base_gfn, unsigned long npages)
{
- gfn_t gfn = base_gfn;
+ struct iommu_domain *domain;
+ gfn_t end_gfn, gfn;
pfn_t pfn;
- struct iommu_domain *domain = kvm->arch.iommu_domain;
- unsigned long i;
u64 phys;
+ domain = kvm->arch.iommu_domain;
+ end_gfn = base_gfn + npages;
+ gfn = base_gfn;
+
/* check if iommu exists and in use */
if (!domain)
return;
- for (i = 0; i < npages; i++) {
+ while (gfn < end_gfn) {
+ unsigned long unmap_pages;
+ int order;
+
+ /* Get physical address */
phys = iommu_iova_to_phys(domain, gfn_to_gpa(gfn));
- pfn = phys >> PAGE_SHIFT;
- kvm_release_pfn_clean(pfn);
- gfn++;
- }
+ pfn = phys >> PAGE_SHIFT;
+
+ /* Unmap address from IO address space */
+ order = iommu_unmap(domain, gfn_to_gpa(gfn), PAGE_SIZE);
+ unmap_pages = 1ULL << order;
- iommu_unmap_range(domain, gfn_to_gpa(base_gfn), PAGE_SIZE * npages);
+ /* Unpin all pages we just unmapped to not leak any memory */
+ kvm_unpin_pages(kvm, pfn, unmap_pages);
+
+ gfn += unmap_pages;
+ }
}
static int kvm_iommu_unmap_memslots(struct kvm *kvm)
diff --git a/virt/kvm/irq_comm.c b/virt/kvm/irq_comm.c
index 9fd5b3ebc517..a0e88809e45e 100644
--- a/virt/kvm/irq_comm.c
+++ b/virt/kvm/irq_comm.c
@@ -20,6 +20,7 @@
*/
#include <linux/kvm_host.h>
+#include <linux/slab.h>
#include <trace/events/kvm.h>
#include <asm/msidef.h>
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 548f9253c195..c82ae2492634 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -22,7 +22,6 @@
#include <linux/module.h>
#include <linux/errno.h>
#include <linux/percpu.h>
-#include <linux/gfp.h>
#include <linux/mm.h>
#include <linux/miscdevice.h>
#include <linux/vmalloc.h>
@@ -46,6 +45,7 @@
#include <linux/compat.h>
#include <linux/srcu.h>
#include <linux/hugetlb.h>
+#include <linux/slab.h>
#include <asm/processor.h>
#include <asm/io.h>
@@ -341,7 +341,11 @@ static void kvm_mmu_notifier_release(struct mmu_notifier *mn,
struct mm_struct *mm)
{
struct kvm *kvm = mmu_notifier_to_kvm(mn);
+ int idx;
+
+ idx = srcu_read_lock(&kvm->srcu);
kvm_arch_flush_shadow(kvm);
+ srcu_read_unlock(&kvm->srcu, idx);
}
static const struct mmu_notifier_ops kvm_mmu_notifier_ops = {
@@ -648,7 +652,7 @@ skip_lpage:
/* Allocate page dirty bitmap if needed */
if ((new.flags & KVM_MEM_LOG_DIRTY_PAGES) && !new.dirty_bitmap) {
- unsigned dirty_bytes = ALIGN(npages, BITS_PER_LONG) / 8;
+ unsigned long dirty_bytes = kvm_dirty_bitmap_bytes(&new);
new.dirty_bitmap = vmalloc(dirty_bytes);
if (!new.dirty_bitmap)
@@ -768,7 +772,7 @@ int kvm_get_dirty_log(struct kvm *kvm,
{
struct kvm_memory_slot *memslot;
int r, i;
- int n;
+ unsigned long n;
unsigned long any = 0;
r = -EINVAL;
@@ -780,7 +784,7 @@ int kvm_get_dirty_log(struct kvm *kvm,
if (!memslot->dirty_bitmap)
goto out;
- n = ALIGN(memslot->npages, BITS_PER_LONG) / 8;
+ n = kvm_dirty_bitmap_bytes(memslot);
for (i = 0; !any && i < n/sizeof(long); ++i)
any = memslot->dirty_bitmap[i];
@@ -1186,10 +1190,13 @@ void mark_page_dirty(struct kvm *kvm, gfn_t gfn)
memslot = gfn_to_memslot_unaliased(kvm, gfn);
if (memslot && memslot->dirty_bitmap) {
unsigned long rel_gfn = gfn - memslot->base_gfn;
+ unsigned long *p = memslot->dirty_bitmap +
+ rel_gfn / BITS_PER_LONG;
+ int offset = rel_gfn % BITS_PER_LONG;
/* avoid RMW */
- if (!generic_test_le_bit(rel_gfn, memslot->dirty_bitmap))
- generic___set_le_bit(rel_gfn, memslot->dirty_bitmap);
+ if (!generic_test_le_bit(offset, p))
+ generic___set_le_bit(offset, p);
}
}
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-20 13:31:04 +0100