[070/126] KVM: Allow cross page reads and writes from cached translations.

From: Steven Rostedt
Date: Tue May 07 2013 - 00:31:18 EST


3.6.11.3 stable review patch.
If anyone has any objections, please let me know.

------------------

From: Andrew Honig <ahonig@xxxxxxxxxx>

[ Upstream commit 8f964525a121f2ff2df948dac908dcc65be21b5b ]

This patch adds support for kvm_gfn_to_hva_cache_init functions for
reads and writes that will cross a page. If the range falls within
the same memslot, then this will be a fast operation. If the range
is split between two memslots, then the slower kvm_read_guest and
kvm_write_guest are used.

Tested: Test against kvm_clock unit tests.

Signed-off-by: Andrew Honig <ahonig@xxxxxxxxxx>
Signed-off-by: Gleb Natapov <gleb@xxxxxxxxxx>
Signed-off-by: Steven Rostedt <rostedt@xxxxxxxxxxx>
---
arch/x86/kvm/lapic.c | 2 +-
arch/x86/kvm/x86.c | 13 ++++++-------
include/linux/kvm_host.h | 2 +-
include/linux/kvm_types.h | 1 +
virt/kvm/kvm_main.c | 47 +++++++++++++++++++++++++++++++++++----------
5 files changed, 46 insertions(+), 19 deletions(-)

diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index ce87878..f0ecc92 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1574,5 +1574,5 @@ int kvm_lapic_enable_pv_eoi(struct kvm_vcpu *vcpu, u64 data)
if (!pv_eoi_enabled(vcpu))
return 0;
return kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.pv_eoi.data,
- addr);
+ addr, sizeof(u8));
}
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 2bf95c0..f7a361f 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1510,7 +1510,8 @@ static int kvm_pv_enable_async_pf(struct kvm_vcpu *vcpu, u64 data)
return 0;
}

- if (kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.apf.data, gpa))
+ if (kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.apf.data, gpa,
+ sizeof(u32)))
return 1;

vcpu->arch.apf.send_user_only = !(data & KVM_ASYNC_PF_SEND_ALWAYS);
@@ -1627,12 +1628,9 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data)

gpa_offset = data & ~(PAGE_MASK | 1);

- /* Check that the address is 32-byte aligned. */
- if (gpa_offset & (sizeof(struct pvclock_vcpu_time_info) - 1))
- break;
-
if (kvm_gfn_to_hva_cache_init(vcpu->kvm,
- &vcpu->arch.pv_time, data & ~1ULL))
+ &vcpu->arch.pv_time, data & ~1ULL,
+ sizeof(struct pvclock_vcpu_time_info)))
vcpu->arch.pv_time_enabled = false;
else
vcpu->arch.pv_time_enabled = true;
@@ -1651,7 +1649,8 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data)
return 1;

if (kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.st.stime,
- data & KVM_STEAL_VALID_BITS))
+ data & KVM_STEAL_VALID_BITS,
+ sizeof(struct kvm_steal_time)))
return 1;

vcpu->arch.st.msr_val = data;
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index b70b48b..5a0fa66 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -456,7 +456,7 @@ int kvm_write_guest(struct kvm *kvm, gpa_t gpa, const void *data,
int kvm_write_guest_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
void *data, unsigned long len);
int kvm_gfn_to_hva_cache_init(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
- gpa_t gpa);
+ gpa_t gpa, unsigned long len);
int kvm_clear_guest_page(struct kvm *kvm, gfn_t gfn, int offset, int len);
int kvm_clear_guest(struct kvm *kvm, gpa_t gpa, unsigned long len);
struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn);
diff --git a/include/linux/kvm_types.h b/include/linux/kvm_types.h
index fa7cc72..b0bcce0 100644
--- a/include/linux/kvm_types.h
+++ b/include/linux/kvm_types.h
@@ -71,6 +71,7 @@ struct gfn_to_hva_cache {
u64 generation;
gpa_t gpa;
unsigned long hva;
+ unsigned long len;
struct kvm_memory_slot *memslot;
};

diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index d617f69..f555d95 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -1393,21 +1393,38 @@ int kvm_write_guest(struct kvm *kvm, gpa_t gpa, const void *data,
}

int kvm_gfn_to_hva_cache_init(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
- gpa_t gpa)
+ gpa_t gpa, unsigned long len)
{
struct kvm_memslots *slots = kvm_memslots(kvm);
int offset = offset_in_page(gpa);
- gfn_t gfn = gpa >> PAGE_SHIFT;
+ gfn_t start_gfn = gpa >> PAGE_SHIFT;
+ gfn_t end_gfn = (gpa + len - 1) >> PAGE_SHIFT;
+ gfn_t nr_pages_needed = end_gfn - start_gfn + 1;
+ gfn_t nr_pages_avail;

ghc->gpa = gpa;
ghc->generation = slots->generation;
- ghc->memslot = gfn_to_memslot(kvm, gfn);
- ghc->hva = gfn_to_hva_many(ghc->memslot, gfn, NULL);
- if (!kvm_is_error_hva(ghc->hva))
+ ghc->len = len;
+ ghc->memslot = gfn_to_memslot(kvm, start_gfn);
+ ghc->hva = gfn_to_hva_many(ghc->memslot, start_gfn, &nr_pages_avail);
+ if (!kvm_is_error_hva(ghc->hva) && nr_pages_avail >= nr_pages_needed) {
ghc->hva += offset;
- else
- return -EFAULT;
-
+ } else {
+ /*
+ * If the requested region crosses two memslots, we still
+ * verify that the entire region is valid here.
+ */
+ while (start_gfn <= end_gfn) {
+ ghc->memslot = gfn_to_memslot(kvm, start_gfn);
+ ghc->hva = gfn_to_hva_many(ghc->memslot, start_gfn,
+ &nr_pages_avail);
+ if (kvm_is_error_hva(ghc->hva))
+ return -EFAULT;
+ start_gfn += nr_pages_avail;
+ }
+ /* Use the slow path for cross page reads and writes. */
+ ghc->memslot = NULL;
+ }
return 0;
}
EXPORT_SYMBOL_GPL(kvm_gfn_to_hva_cache_init);
@@ -1418,8 +1435,13 @@ int kvm_write_guest_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
struct kvm_memslots *slots = kvm_memslots(kvm);
int r;

+ BUG_ON(len > ghc->len);
+
if (slots->generation != ghc->generation)
- kvm_gfn_to_hva_cache_init(kvm, ghc, ghc->gpa);
+ kvm_gfn_to_hva_cache_init(kvm, ghc, ghc->gpa, ghc->len);
+
+ if (unlikely(!ghc->memslot))
+ return kvm_write_guest(kvm, ghc->gpa, data, len);

if (kvm_is_error_hva(ghc->hva))
return -EFAULT;
@@ -1439,8 +1461,13 @@ int kvm_read_guest_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
struct kvm_memslots *slots = kvm_memslots(kvm);
int r;

+ BUG_ON(len > ghc->len);
+
if (slots->generation != ghc->generation)
- kvm_gfn_to_hva_cache_init(kvm, ghc, ghc->gpa);
+ kvm_gfn_to_hva_cache_init(kvm, ghc, ghc->gpa, ghc->len);
+
+ if (unlikely(!ghc->memslot))
+ return kvm_read_guest(kvm, ghc->gpa, data, len);

if (kvm_is_error_hva(ghc->hva))
return -EFAULT;
--
1.7.10.4


--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/