* [PATCH 1/3] KVM: PPC: Book3S HV: Take the SRCU read lock before looking up memslots
2012-09-11 23:26 [PATCH 0/3] KVM: PPC: Memslot handling improvements Paul Mackerras
@ 2012-09-11 23:27 ` Paul Mackerras
2012-09-11 23:27 ` [PATCH 2/3] KVM: PPC: Move kvm->arch.slot_phys into memslot.arch Paul Mackerras
` (2 subsequent siblings)
3 siblings, 0 replies; 5+ messages in thread
From: Paul Mackerras @ 2012-09-11 23:27 UTC (permalink / raw)
To: Alexander Graf; +Cc: kvm-ppc, kvm
The generic KVM code uses SRCU (sleeping RCU) to protect accesses
to the memslots data structures against updates due to userspace
adding, modifying or removing memory slots. We need to do that too,
both to avoid accessing stale copies of the memslots and to avoid
lockdep warnings. This therefore adds srcu_read_lock/unlock pairs
around code that accesses and uses memslots.
Since the real-mode handlers for H_ENTER, H_REMOVE and H_BULK_REMOVE
need to access the memslots, and we don't want to call the SRCU code
in real mode (since we have no assurance that it would only access
the linear mapping), we hold the SRCU read lock for the VM while
in the guest. This does mean that adding or removing memory slots
while some vcpus are executing in the guest will block for up to
two jiffies. This tradeoff is acceptable since adding/removing
memory slots only happens rarely, while H_ENTER/H_REMOVE/H_BULK_REMOVE
are performance-critical hot paths.
Signed-off-by: Paul Mackerras <paulus@samba.org>
---
arch/powerpc/kvm/book3s_64_mmu_hv.c | 17 +++++++++++++----
arch/powerpc/kvm/book3s_hv.c | 27 +++++++++++++++++++++++----
2 files changed, 36 insertions(+), 8 deletions(-)
diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c
index d95d113..0f031c0 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_hv.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c
@@ -24,6 +24,7 @@
#include <linux/slab.h>
#include <linux/hugetlb.h>
#include <linux/vmalloc.h>
+#include <linux/srcu.h>
#include <asm/tlbflush.h>
#include <asm/kvm_ppc.h>
@@ -1057,20 +1058,22 @@ void *kvmppc_pin_guest_page(struct kvm *kvm, unsigned long gpa,
unsigned long hva, psize, offset;
unsigned long pa;
unsigned long *physp;
+ int srcu_idx;
+ srcu_idx = srcu_read_lock(&kvm->srcu);
memslot = gfn_to_memslot(kvm, gfn);
if (!memslot || (memslot->flags & KVM_MEMSLOT_INVALID))
- return NULL;
+ goto err;
if (!kvm->arch.using_mmu_notifiers) {
physp = kvm->arch.slot_phys[memslot->id];
if (!physp)
- return NULL;
+ goto err;
physp += gfn - memslot->base_gfn;
pa = *physp;
if (!pa) {
if (kvmppc_get_guest_page(kvm, gfn, memslot,
PAGE_SIZE) < 0)
- return NULL;
+ goto err;
pa = *physp;
}
page = pfn_to_page(pa >> PAGE_SHIFT);
@@ -1079,9 +1082,11 @@ void *kvmppc_pin_guest_page(struct kvm *kvm, unsigned long gpa,
hva = gfn_to_hva_memslot(memslot, gfn);
npages = get_user_pages_fast(hva, 1, 1, pages);
if (npages < 1)
- return NULL;
+ goto err;
page = pages[0];
}
+ srcu_read_unlock(&kvm->srcu, srcu_idx);
+
psize = PAGE_SIZE;
if (PageHuge(page)) {
page = compound_head(page);
@@ -1091,6 +1096,10 @@ void *kvmppc_pin_guest_page(struct kvm *kvm, unsigned long gpa,
if (nb_ret)
*nb_ret = psize - offset;
return page_address(page) + offset;
+
+ err:
+ srcu_read_unlock(&kvm->srcu, srcu_idx);
+ return NULL;
}
void kvmppc_unpin_guest_page(struct kvm *kvm, void *va)
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 83e929e..48b0d4a 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -30,6 +30,7 @@
#include <linux/cpumask.h>
#include <linux/spinlock.h>
#include <linux/page-flags.h>
+#include <linux/srcu.h>
#include <asm/reg.h>
#include <asm/cputable.h>
@@ -366,13 +367,16 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
unsigned long req = kvmppc_get_gpr(vcpu, 3);
unsigned long target, ret = H_SUCCESS;
struct kvm_vcpu *tvcpu;
+ int idx;
switch (req) {
case H_ENTER:
+ idx = srcu_read_lock(&vcpu->kvm->srcu);
ret = kvmppc_virtmode_h_enter(vcpu, kvmppc_get_gpr(vcpu, 4),
kvmppc_get_gpr(vcpu, 5),
kvmppc_get_gpr(vcpu, 6),
kvmppc_get_gpr(vcpu, 7));
+ srcu_read_unlock(&vcpu->kvm->srcu, idx);
break;
case H_CEDE:
break;
@@ -411,6 +415,7 @@ static int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
struct task_struct *tsk)
{
int r = RESUME_HOST;
+ int srcu_idx;
vcpu->stat.sum_exits++;
@@ -470,12 +475,16 @@ static int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
* have been handled already.
*/
case BOOK3S_INTERRUPT_H_DATA_STORAGE:
+ srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
r = kvmppc_book3s_hv_page_fault(run, vcpu,
vcpu->arch.fault_dar, vcpu->arch.fault_dsisr);
+ srcu_read_unlock(&vcpu->kvm->srcu, srcu_idx);
break;
case BOOK3S_INTERRUPT_H_INST_STORAGE:
+ srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
r = kvmppc_book3s_hv_page_fault(run, vcpu,
kvmppc_get_pc(vcpu), 0);
+ srcu_read_unlock(&vcpu->kvm->srcu, srcu_idx);
break;
/*
* This occurs if the guest executes an illegal instruction.
@@ -820,6 +829,7 @@ static int kvmppc_run_core(struct kvmppc_vcore *vc)
long ret;
u64 now;
int ptid, i, need_vpa_update;
+ int srcu_idx;
/* don't start if any threads have a signal pending */
need_vpa_update = 0;
@@ -898,6 +908,9 @@ static int kvmppc_run_core(struct kvmppc_vcore *vc)
spin_unlock(&vc->lock);
kvm_guest_enter();
+
+ srcu_idx = srcu_read_lock(&vcpu0->kvm->srcu);
+
__kvmppc_vcore_entry(NULL, vcpu0);
for (i = 0; i < threads_per_core; ++i)
kvmppc_release_hwthread(vc->pcpu + i);
@@ -913,6 +926,8 @@ static int kvmppc_run_core(struct kvmppc_vcore *vc)
vc->vcore_state = VCORE_EXITING;
spin_unlock(&vc->lock);
+ srcu_read_unlock(&vcpu0->kvm->srcu, srcu_idx);
+
/* make sure updates to secondary vcpu structs are visible now */
smp_mb();
kvm_guest_exit();
@@ -1362,6 +1377,7 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu)
unsigned long rmls;
unsigned long *physp;
unsigned long i, npages;
+ int srcu_idx;
mutex_lock(&kvm->lock);
if (kvm->arch.rma_setup_done)
@@ -1377,12 +1393,13 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu)
}
/* Look up the memslot for guest physical address 0 */
+ srcu_idx = srcu_read_lock(&kvm->srcu);
memslot = gfn_to_memslot(kvm, 0);
/* We must have some memory at 0 by now */
err = -EINVAL;
if (!memslot || (memslot->flags & KVM_MEMSLOT_INVALID))
- goto out;
+ goto out_srcu;
/* Look up the VMA for the start of this memory slot */
hva = memslot->userspace_addr;
@@ -1406,14 +1423,14 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu)
err = -EPERM;
if (cpu_has_feature(CPU_FTR_ARCH_201)) {
pr_err("KVM: CPU requires an RMO\n");
- goto out;
+ goto out_srcu;
}
/* We can handle 4k, 64k or 16M pages in the VRMA */
err = -EINVAL;
if (!(psize = 0x1000 || psize = 0x10000 ||
psize = 0x1000000))
- goto out;
+ goto out_srcu;
/* Update VRMASD field in the LPCR */
senc = slb_pgsize_encoding(psize);
@@ -1436,7 +1453,7 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu)
err = -EINVAL;
if (rmls < 0) {
pr_err("KVM: Can't use RMA of 0x%lx bytes\n", rma_size);
- goto out;
+ goto out_srcu;
}
atomic_inc(&ri->use_count);
kvm->arch.rma = ri;
@@ -1476,6 +1493,8 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu)
smp_wmb();
kvm->arch.rma_setup_done = 1;
err = 0;
+ out_srcu:
+ srcu_read_unlock(&kvm->srcu, srcu_idx);
out:
mutex_unlock(&kvm->lock);
return err;
--
1.7.10.rc3.219.g53414
^ permalink raw reply related [flat|nested] 5+ messages in thread* [PATCH 2/3] KVM: PPC: Move kvm->arch.slot_phys into memslot.arch
2012-09-11 23:26 [PATCH 0/3] KVM: PPC: Memslot handling improvements Paul Mackerras
2012-09-11 23:27 ` [PATCH 1/3] KVM: PPC: Book3S HV: Take the SRCU read lock before looking up memslots Paul Mackerras
@ 2012-09-11 23:27 ` Paul Mackerras
2012-09-11 23:28 ` [PATCH 3/3] KVM: PPC: Book3S HV: Handle memory slot deletion and modification correctly Paul Mackerras
2012-09-13 16:43 ` [PATCH 0/3] KVM: PPC: Memslot handling improvements Alexander Graf
3 siblings, 0 replies; 5+ messages in thread
From: Paul Mackerras @ 2012-09-11 23:27 UTC (permalink / raw)
To: Alexander Graf; +Cc: kvm-ppc, kvm
Now that we have an architecture-specific field in the kvm_memory_slot
structure, we can use it to store the array of page physical addresses
that we need for Book3S HV KVM on PPC970 processors. This reduces the
size of struct kvm_arch for Book3S HV, and also reduces the size of
struct kvm_arch_memory_slot for other PPC KVM variants since the fields
in it are now only compiled in for Book3S HV.
This necessitates making the kvm_arch_create_memslot and
kvm_arch_free_memslot operations specific to each PPC KVM variant.
That in turn means that we now don't allocate the rmap arrays on
Book3S PR and Book E.
Since we now unpin pages and free the slot_phys array in
kvmppc_core_free_memslot, we no longer need to do it in
kvmppc_core_destroy_vm, since the generic code takes care to free
all the memslots when destroying a VM.
We now need the new memslot to be passed in to
kvmppc_core_prepare_memory_region, since we need to initialize its
arch.slot_phys member on Book3S HV.
Signed-off-by: Paul Mackerras <paulus@samba.org>
---
arch/powerpc/include/asm/kvm_host.h | 9 +--
arch/powerpc/include/asm/kvm_ppc.h | 5 ++
arch/powerpc/kvm/book3s_64_mmu_hv.c | 6 +-
arch/powerpc/kvm/book3s_hv.c | 104 ++++++++++++++++++++---------------
arch/powerpc/kvm/book3s_hv_rm_mmu.c | 2 +-
arch/powerpc/kvm/book3s_pr.c | 12 ++++
arch/powerpc/kvm/booke.c | 12 ++++
arch/powerpc/kvm/powerpc.c | 13 +----
8 files changed, 102 insertions(+), 61 deletions(-)
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 28e8f5e..b102ff6 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -204,7 +204,7 @@ struct revmap_entry {
};
/*
- * We use the top bit of each memslot->rmap entry as a lock bit,
+ * We use the top bit of each memslot->arch.rmap entry as a lock bit,
* and bit 32 as a present flag. The bottom 32 bits are the
* index in the guest HPT of a HPTE that points to the page.
*/
@@ -215,14 +215,17 @@ struct revmap_entry {
#define KVMPPC_RMAP_PRESENT 0x100000000ul
#define KVMPPC_RMAP_INDEX 0xfffffffful
-/* Low-order bits in kvm->arch.slot_phys[][] */
+/* Low-order bits in memslot->arch.slot_phys[] */
#define KVMPPC_PAGE_ORDER_MASK 0x1f
#define KVMPPC_PAGE_NO_CACHE HPTE_R_I /* 0x20 */
#define KVMPPC_PAGE_WRITETHRU HPTE_R_W /* 0x40 */
#define KVMPPC_GOT_PAGE 0x80
struct kvm_arch_memory_slot {
+#ifdef CONFIG_KVM_BOOK3S_64_HV
unsigned long *rmap;
+ unsigned long *slot_phys;
+#endif /* CONFIG_KVM_BOOK3S_64_HV */
};
struct kvm_arch {
@@ -246,8 +249,6 @@ struct kvm_arch {
unsigned long hpt_npte;
unsigned long hpt_mask;
spinlock_t slot_phys_lock;
- unsigned long *slot_phys[KVM_MEM_SLOTS_NUM];
- int slot_npages[KVM_MEM_SLOTS_NUM];
unsigned short last_vcpu[NR_CPUS];
struct kvmppc_vcore *vcores[KVM_MAX_VCORES];
struct kvmppc_linear_info *hpt_li;
diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index e006f0b..1cde8a1c 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -139,7 +139,12 @@ extern struct kvmppc_linear_info *kvm_alloc_hpt(void);
extern void kvm_release_hpt(struct kvmppc_linear_info *li);
extern int kvmppc_core_init_vm(struct kvm *kvm);
extern void kvmppc_core_destroy_vm(struct kvm *kvm);
+extern void kvmppc_core_free_memslot(struct kvm_memory_slot *free,
+ struct kvm_memory_slot *dont);
+extern int kvmppc_core_create_memslot(struct kvm_memory_slot *slot,
+ unsigned long npages);
extern int kvmppc_core_prepare_memory_region(struct kvm *kvm,
+ struct kvm_memory_slot *memslot,
struct kvm_userspace_memory_region *mem);
extern void kvmppc_core_commit_memory_region(struct kvm *kvm,
struct kvm_userspace_memory_region *mem);
diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c
index 0f031c0..a389cc6 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_hv.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c
@@ -261,7 +261,7 @@ static void kvmppc_mmu_book3s_64_hv_reset_msr(struct kvm_vcpu *vcpu)
/*
* This is called to get a reference to a guest page if there isn't
- * one already in the kvm->arch.slot_phys[][] arrays.
+ * one already in the memslot->arch.slot_phys[] array.
*/
static long kvmppc_get_guest_page(struct kvm *kvm, unsigned long gfn,
struct kvm_memory_slot *memslot,
@@ -276,7 +276,7 @@ static long kvmppc_get_guest_page(struct kvm *kvm, unsigned long gfn,
struct vm_area_struct *vma;
unsigned long pfn, i, npages;
- physp = kvm->arch.slot_phys[memslot->id];
+ physp = memslot->arch.slot_phys;
if (!physp)
return -EINVAL;
if (physp[gfn - memslot->base_gfn])
@@ -1065,7 +1065,7 @@ void *kvmppc_pin_guest_page(struct kvm *kvm, unsigned long gpa,
if (!memslot || (memslot->flags & KVM_MEMSLOT_INVALID))
goto err;
if (!kvm->arch.using_mmu_notifiers) {
- physp = kvm->arch.slot_phys[memslot->id];
+ physp = memslot->arch.slot_phys;
if (!physp)
goto err;
physp += gfn - memslot->base_gfn;
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 48b0d4a..817837d 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -1314,48 +1314,67 @@ static unsigned long slb_pgsize_encoding(unsigned long psize)
return senc;
}
-int kvmppc_core_prepare_memory_region(struct kvm *kvm,
- struct kvm_userspace_memory_region *mem)
+static void unpin_slot(struct kvm_memory_slot *memslot)
{
- unsigned long npages;
- unsigned long *phys;
+ unsigned long *physp;
+ unsigned long j, npages, pfn;
+ struct page *page;
- /* Allocate a slot_phys array */
- phys = kvm->arch.slot_phys[mem->slot];
- if (!kvm->arch.using_mmu_notifiers && !phys) {
- npages = mem->memory_size >> PAGE_SHIFT;
- phys = vzalloc(npages * sizeof(unsigned long));
- if (!phys)
- return -ENOMEM;
- kvm->arch.slot_phys[mem->slot] = phys;
- kvm->arch.slot_npages[mem->slot] = npages;
+ physp = memslot->arch.slot_phys;
+ npages = memslot->npages;
+ if (!physp)
+ return;
+ for (j = 0; j < npages; j++) {
+ if (!(physp[j] & KVMPPC_GOT_PAGE))
+ continue;
+ pfn = physp[j] >> PAGE_SHIFT;
+ page = pfn_to_page(pfn);
+ SetPageDirty(page);
+ put_page(page);
+ }
+}
+
+void kvmppc_core_free_memslot(struct kvm_memory_slot *free,
+ struct kvm_memory_slot *dont)
+{
+ if (!dont || free->arch.rmap != dont->arch.rmap) {
+ vfree(free->arch.rmap);
+ free->arch.rmap = NULL;
}
+ if (!dont || free->arch.slot_phys != dont->arch.slot_phys) {
+ unpin_slot(free);
+ vfree(free->arch.slot_phys);
+ free->arch.slot_phys = NULL;
+ }
+}
+
+int kvmppc_core_create_memslot(struct kvm_memory_slot *slot,
+ unsigned long npages)
+{
+ slot->arch.rmap = vzalloc(npages * sizeof(*slot->arch.rmap));
+ if (!slot->arch.rmap)
+ return -ENOMEM;
+ slot->arch.slot_phys = NULL;
return 0;
}
-static void unpin_slot(struct kvm *kvm, int slot_id)
+int kvmppc_core_prepare_memory_region(struct kvm *kvm,
+ struct kvm_memory_slot *memslot,
+ struct kvm_userspace_memory_region *mem)
{
- unsigned long *physp;
- unsigned long j, npages, pfn;
- struct page *page;
+ unsigned long *phys;
- physp = kvm->arch.slot_phys[slot_id];
- npages = kvm->arch.slot_npages[slot_id];
- if (physp) {
- spin_lock(&kvm->arch.slot_phys_lock);
- for (j = 0; j < npages; j++) {
- if (!(physp[j] & KVMPPC_GOT_PAGE))
- continue;
- pfn = physp[j] >> PAGE_SHIFT;
- page = pfn_to_page(pfn);
- SetPageDirty(page);
- put_page(page);
- }
- kvm->arch.slot_phys[slot_id] = NULL;
- spin_unlock(&kvm->arch.slot_phys_lock);
- vfree(physp);
+ /* Allocate a slot_phys array if needed */
+ phys = memslot->arch.slot_phys;
+ if (!kvm->arch.using_mmu_notifiers && !phys && memslot->npages) {
+ phys = vzalloc(memslot->npages * sizeof(unsigned long));
+ if (!phys)
+ return -ENOMEM;
+ memslot->arch.slot_phys = phys;
}
+
+ return 0;
}
void kvmppc_core_commit_memory_region(struct kvm *kvm,
@@ -1482,11 +1501,16 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu)
/* Initialize phys addrs of pages in RMO */
npages = ri->npages;
porder = __ilog2(npages);
- physp = kvm->arch.slot_phys[memslot->id];
- spin_lock(&kvm->arch.slot_phys_lock);
- for (i = 0; i < npages; ++i)
- physp[i] = ((ri->base_pfn + i) << PAGE_SHIFT) + porder;
- spin_unlock(&kvm->arch.slot_phys_lock);
+ physp = memslot->arch.slot_phys;
+ if (physp) {
+ if (npages > memslot->npages)
+ npages = memslot->npages;
+ spin_lock(&kvm->arch.slot_phys_lock);
+ for (i = 0; i < npages; ++i)
+ physp[i] = ((ri->base_pfn + i) << PAGE_SHIFT) +
+ porder;
+ spin_unlock(&kvm->arch.slot_phys_lock);
+ }
}
/* Order updates to kvm->arch.lpcr etc. vs. rma_setup_done */
@@ -1547,12 +1571,6 @@ int kvmppc_core_init_vm(struct kvm *kvm)
void kvmppc_core_destroy_vm(struct kvm *kvm)
{
- unsigned long i;
-
- if (!kvm->arch.using_mmu_notifiers)
- for (i = 0; i < KVM_MEM_SLOTS_NUM; i++)
- unpin_slot(kvm, i);
-
if (kvm->arch.rma) {
kvm_release_rma(kvm->arch.rma);
kvm->arch.rma = NULL;
diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
index fb0e821..63eb94e 100644
--- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c
+++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
@@ -183,7 +183,7 @@ long kvmppc_h_enter(struct kvm_vcpu *vcpu, unsigned long flags,
rmap = &memslot->arch.rmap[slot_fn];
if (!kvm->arch.using_mmu_notifiers) {
- physp = kvm->arch.slot_phys[memslot->id];
+ physp = memslot->arch.slot_phys;
if (!physp)
return H_PARAMETER;
physp += slot_fn;
diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c
index 05c28f5..53f65a2 100644
--- a/arch/powerpc/kvm/book3s_pr.c
+++ b/arch/powerpc/kvm/book3s_pr.c
@@ -1181,7 +1181,19 @@ int kvm_vm_ioctl_get_smmu_info(struct kvm *kvm, struct kvm_ppc_smmu_info *info)
}
#endif /* CONFIG_PPC64 */
+void kvmppc_core_free_memslot(struct kvm_memory_slot *free,
+ struct kvm_memory_slot *dont)
+{
+}
+
+int kvmppc_core_create_memslot(struct kvm_memory_slot *slot,
+ unsigned long npages)
+{
+ return 0;
+}
+
int kvmppc_core_prepare_memory_region(struct kvm *kvm,
+ struct kvm_memory_slot *memslot,
struct kvm_userspace_memory_region *mem)
{
return 0;
diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index d25a097..0e66b46 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -1253,7 +1253,19 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log)
return -ENOTSUPP;
}
+void kvmppc_core_free_memslot(struct kvm_memory_slot *free,
+ struct kvm_memory_slot *dont)
+{
+}
+
+int kvmppc_core_create_memslot(struct kvm_memory_slot *slot,
+ unsigned long npages)
+{
+ return 0;
+}
+
int kvmppc_core_prepare_memory_region(struct kvm *kvm,
+ struct kvm_memory_slot *memslot,
struct kvm_userspace_memory_region *mem)
{
return 0;
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 4d213b8..3a29f29 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -302,19 +302,12 @@ long kvm_arch_dev_ioctl(struct file *filp,
void kvm_arch_free_memslot(struct kvm_memory_slot *free,
struct kvm_memory_slot *dont)
{
- if (!dont || free->arch.rmap != dont->arch.rmap) {
- vfree(free->arch.rmap);
- free->arch.rmap = NULL;
- }
+ kvmppc_core_free_memslot(free, dont);
}
int kvm_arch_create_memslot(struct kvm_memory_slot *slot, unsigned long npages)
{
- slot->arch.rmap = vzalloc(npages * sizeof(*slot->arch.rmap));
- if (!slot->arch.rmap)
- return -ENOMEM;
-
- return 0;
+ return kvmppc_core_create_memslot(slot, npages);
}
int kvm_arch_prepare_memory_region(struct kvm *kvm,
@@ -323,7 +316,7 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
struct kvm_userspace_memory_region *mem,
int user_alloc)
{
- return kvmppc_core_prepare_memory_region(kvm, mem);
+ return kvmppc_core_prepare_memory_region(kvm, memslot, mem);
}
void kvm_arch_commit_memory_region(struct kvm *kvm,
--
1.7.10.rc3.219.g53414
^ permalink raw reply related [flat|nested] 5+ messages in thread* [PATCH 3/3] KVM: PPC: Book3S HV: Handle memory slot deletion and modification correctly
2012-09-11 23:26 [PATCH 0/3] KVM: PPC: Memslot handling improvements Paul Mackerras
2012-09-11 23:27 ` [PATCH 1/3] KVM: PPC: Book3S HV: Take the SRCU read lock before looking up memslots Paul Mackerras
2012-09-11 23:27 ` [PATCH 2/3] KVM: PPC: Move kvm->arch.slot_phys into memslot.arch Paul Mackerras
@ 2012-09-11 23:28 ` Paul Mackerras
2012-09-13 16:43 ` [PATCH 0/3] KVM: PPC: Memslot handling improvements Alexander Graf
3 siblings, 0 replies; 5+ messages in thread
From: Paul Mackerras @ 2012-09-11 23:28 UTC (permalink / raw)
To: Alexander Graf; +Cc: kvm-ppc, kvm
This adds an implementation of kvm_arch_flush_shadow_memslot for
Book3S HV, and arranges for kvmppc_core_commit_memory_region to
flush the dirty log when modifying an existing slot. With this,
we can handle deletion and modification of memory slots.
kvm_arch_flush_shadow_memslot calls kvmppc_core_flush_memslot, which
on Book3S HV now traverses the reverse map chains to remove any HPT
(hashed page table) entries referring to pages in the memslot. This
gets called by generic code whenever deleting a memslot or changing
the guest physical address for a memslot.
We flush the dirty log in kvmppc_core_commit_memory_region for
consistency with what x86 does. We only need to flush when an
existing memslot is being modified, because for a new memslot the
rmap array (which stores the dirty bits) is all zero, meaning that
every page is considered clean already, and when deleting a memslot
we obviously don't care about the dirty bits any more.
Signed-off-by: Paul Mackerras <paulus@samba.org>
---
arch/powerpc/include/asm/kvm_book3s.h | 2 +-
arch/powerpc/include/asm/kvm_ppc.h | 5 ++++-
arch/powerpc/kvm/book3s_64_mmu_hv.c | 33 ++++++++++++++++++++++++++++-----
arch/powerpc/kvm/book3s_hv.c | 18 ++++++++++++++++--
arch/powerpc/kvm/book3s_hv_rm_mmu.c | 2 +-
arch/powerpc/kvm/book3s_pr.c | 7 ++++++-
arch/powerpc/kvm/booke.c | 7 ++++++-
arch/powerpc/kvm/powerpc.c | 3 ++-
8 files changed, 64 insertions(+), 13 deletions(-)
diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h
index f0e0c6a..ab73800 100644
--- a/arch/powerpc/include/asm/kvm_book3s.h
+++ b/arch/powerpc/include/asm/kvm_book3s.h
@@ -160,7 +160,7 @@ extern long kvmppc_virtmode_h_enter(struct kvm_vcpu *vcpu, unsigned long flags,
extern long kvmppc_h_enter(struct kvm_vcpu *vcpu, unsigned long flags,
long pte_index, unsigned long pteh, unsigned long ptel);
extern long kvmppc_hv_get_dirty_log(struct kvm *kvm,
- struct kvm_memory_slot *memslot);
+ struct kvm_memory_slot *memslot, unsigned long *map);
extern void kvmppc_entry_trampoline(void);
extern void kvmppc_hv_entry_trampoline(void);
diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index 1cde8a1c..4f390cb 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -147,9 +147,12 @@ extern int kvmppc_core_prepare_memory_region(struct kvm *kvm,
struct kvm_memory_slot *memslot,
struct kvm_userspace_memory_region *mem);
extern void kvmppc_core_commit_memory_region(struct kvm *kvm,
- struct kvm_userspace_memory_region *mem);
+ struct kvm_userspace_memory_region *mem,
+ struct kvm_memory_slot old);
extern int kvm_vm_ioctl_get_smmu_info(struct kvm *kvm,
struct kvm_ppc_smmu_info *info);
+extern void kvmppc_core_flush_memslot(struct kvm *kvm,
+ struct kvm_memory_slot *memslot);
extern int kvmppc_bookehv_init(void);
extern void kvmppc_bookehv_exit(void);
diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c
index a389cc6..f598366 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_hv.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c
@@ -851,7 +851,8 @@ static int kvm_unmap_rmapp(struct kvm *kvm, unsigned long *rmapp,
psize = hpte_page_size(hptep[0], ptel);
if ((hptep[0] & HPTE_V_VALID) &&
hpte_rpn(ptel, psize) = gfn) {
- hptep[0] |= HPTE_V_ABSENT;
+ if (kvm->arch.using_mmu_notifiers)
+ hptep[0] |= HPTE_V_ABSENT;
kvmppc_invalidate_hpte(kvm, hptep, i);
/* Harvest R and C */
rcbits = hptep[1] & (HPTE_R_R | HPTE_R_C);
@@ -878,6 +879,28 @@ int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end)
return 0;
}
+void kvmppc_core_flush_memslot(struct kvm *kvm, struct kvm_memory_slot *memslot)
+{
+ unsigned long *rmapp;
+ unsigned long gfn;
+ unsigned long n;
+
+ rmapp = memslot->arch.rmap;
+ gfn = memslot->base_gfn;
+ for (n = memslot->npages; n; --n) {
+ /*
+ * Testing the present bit without locking is OK because
+ * the memslot has been marked invalid already, and hence
+ * no new HPTEs referencing this page can be created,
+ * thus the present bit can't go from 0 to 1.
+ */
+ if (*rmapp & KVMPPC_RMAP_PRESENT)
+ kvm_unmap_rmapp(kvm, rmapp, gfn);
+ ++rmapp;
+ ++gfn;
+ }
+}
+
static int kvm_age_rmapp(struct kvm *kvm, unsigned long *rmapp,
unsigned long gfn)
{
@@ -1031,16 +1054,16 @@ static int kvm_test_clear_dirty(struct kvm *kvm, unsigned long *rmapp)
return ret;
}
-long kvmppc_hv_get_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot)
+long kvmppc_hv_get_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot,
+ unsigned long *map)
{
unsigned long i;
- unsigned long *rmapp, *map;
+ unsigned long *rmapp;
preempt_disable();
rmapp = memslot->arch.rmap;
- map = memslot->dirty_bitmap;
for (i = 0; i < memslot->npages; ++i) {
- if (kvm_test_clear_dirty(kvm, rmapp))
+ if (kvm_test_clear_dirty(kvm, rmapp) && map)
__set_bit_le(i, map);
++rmapp;
}
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 817837d..38c7f1b 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -1288,7 +1288,7 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log)
n = kvm_dirty_bitmap_bytes(memslot);
memset(memslot->dirty_bitmap, 0, n);
- r = kvmppc_hv_get_dirty_log(kvm, memslot);
+ r = kvmppc_hv_get_dirty_log(kvm, memslot, memslot->dirty_bitmap);
if (r)
goto out;
@@ -1378,8 +1378,22 @@ int kvmppc_core_prepare_memory_region(struct kvm *kvm,
}
void kvmppc_core_commit_memory_region(struct kvm *kvm,
- struct kvm_userspace_memory_region *mem)
+ struct kvm_userspace_memory_region *mem,
+ struct kvm_memory_slot old)
{
+ unsigned long npages = mem->memory_size >> PAGE_SHIFT;
+ struct kvm_memory_slot *memslot;
+
+ if (npages && old.npages) {
+ /*
+ * If modifying a memslot, reset all the rmap dirty bits.
+ * If this is a new memslot, we don't need to do anything
+ * since the rmap array starts out as all zeroes,
+ * i.e. no pages are dirty.
+ */
+ memslot = id_to_memslot(kvm->memslots, mem->slot);
+ kvmppc_hv_get_dirty_log(kvm, memslot, NULL);
+ }
}
static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu)
diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
index 63eb94e..9955216 100644
--- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c
+++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
@@ -81,7 +81,7 @@ static void remove_revmap_chain(struct kvm *kvm, long pte_index,
ptel = rev->guest_rpte |= rcbits;
gfn = hpte_rpn(ptel, hpte_page_size(hpte_v, ptel));
memslot = __gfn_to_memslot(kvm_memslots(kvm), gfn);
- if (!memslot || (memslot->flags & KVM_MEMSLOT_INVALID))
+ if (!memslot)
return;
rmap = real_vmalloc_addr(&memslot->arch.rmap[gfn - memslot->base_gfn]);
diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c
index 53f65a2..016e1ed 100644
--- a/arch/powerpc/kvm/book3s_pr.c
+++ b/arch/powerpc/kvm/book3s_pr.c
@@ -1200,7 +1200,12 @@ int kvmppc_core_prepare_memory_region(struct kvm *kvm,
}
void kvmppc_core_commit_memory_region(struct kvm *kvm,
- struct kvm_userspace_memory_region *mem)
+ struct kvm_userspace_memory_region *mem,
+ struct kvm_memory_slot old)
+{
+}
+
+void kvmppc_core_flush_memslot(struct kvm *kvm, struct kvm_memory_slot *memslot)
{
}
diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index 0e66b46..c91f8be 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -1272,7 +1272,12 @@ int kvmppc_core_prepare_memory_region(struct kvm *kvm,
}
void kvmppc_core_commit_memory_region(struct kvm *kvm,
- struct kvm_userspace_memory_region *mem)
+ struct kvm_userspace_memory_region *mem,
+ struct kvm_memory_slot old)
+{
+}
+
+void kvmppc_core_flush_memslot(struct kvm *kvm, struct kvm_memory_slot *memslot)
{
}
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 3a29f29..229627e 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -324,7 +324,7 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
struct kvm_memory_slot old,
int user_alloc)
{
- kvmppc_core_commit_memory_region(kvm, mem);
+ kvmppc_core_commit_memory_region(kvm, mem, old);
}
void kvm_arch_flush_shadow_all(struct kvm *kvm)
@@ -334,6 +334,7 @@ void kvm_arch_flush_shadow_all(struct kvm *kvm)
void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
struct kvm_memory_slot *slot)
{
+ kvmppc_core_flush_memslot(kvm, slot);
}
struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id)
--
1.7.10.rc3.219.g53414
^ permalink raw reply related [flat|nested] 5+ messages in thread* Re: [PATCH 0/3] KVM: PPC: Memslot handling improvements
2012-09-11 23:26 [PATCH 0/3] KVM: PPC: Memslot handling improvements Paul Mackerras
` (2 preceding siblings ...)
2012-09-11 23:28 ` [PATCH 3/3] KVM: PPC: Book3S HV: Handle memory slot deletion and modification correctly Paul Mackerras
@ 2012-09-13 16:43 ` Alexander Graf
3 siblings, 0 replies; 5+ messages in thread
From: Alexander Graf @ 2012-09-13 16:43 UTC (permalink / raw)
To: Paul Mackerras; +Cc: kvm-ppc, kvm
On 09/12/2012 01:26 AM, Paul Mackerras wrote:
> This series of 3 patches fixes up the memslot handling for Book3S HV
> style KVM on powerpc, making slot deletion and modification work and
> making sure we have the appropriate SRCU synchronization against
> updates.
>
> The series is against the next branch of the kvm tree. These patches
> have all been posted before, but I am reposting them now because
> Marcelo's patches that are a prerequisite for the third patch
> (2df72e9bc4, "KVM: split kvm_arch_flush_shadow" and 12d6e7538e, "KVM:
> perform an invalid memslot step for gpa base change") have now gone
> into the kvm next branch.
Thanks, applied all to kvm-ppc-next.
Alex
^ permalink raw reply [flat|nested] 5+ messages in thread