* [PATCH 19/20] KVM: PPC: Book3S HV: Don't use compound_order to determine host mapping size
[not found] <20190308163505.13021-1-leonardo@linux.ibm.com>
@ 2019-03-08 16:35 ` Leonardo Bras
0 siblings, 0 replies; 2+ messages in thread
From: Leonardo Bras @ 2019-03-08 16:35 UTC (permalink / raw)
To: kernel-team
Cc: Aneesh Kumar K.V, kvm-ppc, Nicholas Piggin, linuxppc-dev,
David Gibson
From: Nicholas Piggin <npiggin@gmail.com>
THP paths can defer splitting compound pages until after the actual
remap and TLB flushes to split a huge PMD/PUD. This causes radix
partition scope page table mappings to get out of synch with the host
qemu page table mappings.
This results in random memory corruption in the guest when running
with THP. The easiest way to reproduce is use KVM balloon to free up
a lot of memory in the guest and then shrink the balloon to give the
memory back, while some work is being done in the guest.
Cc: David Gibson <david@gibson.dropbear.id.au>
Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com>
Cc: kvm-ppc@vger.kernel.org
Cc: linuxppc-dev@lists.ozlabs.org
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
---
arch/powerpc/kvm/book3s_64_mmu_radix.c | 91 +++++++++++---------------
1 file changed, 37 insertions(+), 54 deletions(-)
diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c
index 7efc42538ccf..ae023d2256ef 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_radix.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c
@@ -538,8 +538,8 @@ int kvmppc_book3s_radix_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
unsigned long ea, unsigned long dsisr)
{
struct kvm *kvm = vcpu->kvm;
- unsigned long mmu_seq, pte_size;
- unsigned long gpa, gfn, hva, pfn;
+ unsigned long mmu_seq;
+ unsigned long gpa, gfn, hva;
struct kvm_memory_slot *memslot;
struct page *page = NULL;
long ret;
@@ -636,9 +636,10 @@ int kvmppc_book3s_radix_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
*/
hva = gfn_to_hva_memslot(memslot, gfn);
if (upgrade_p && __get_user_pages_fast(hva, 1, 1, &page) == 1) {
- pfn = page_to_pfn(page);
upgrade_write = true;
} else {
+ unsigned long pfn;
+
/* Call KVM generic code to do the slow-path check */
pfn = __gfn_to_pfn_memslot(memslot, gfn, false, NULL,
writing, upgrade_p);
@@ -652,63 +653,45 @@ int kvmppc_book3s_radix_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
}
}
- /* See if we can insert a 1GB or 2MB large PTE here */
- level = 0;
- if (page && PageCompound(page)) {
- pte_size = PAGE_SIZE << compound_order(compound_head(page));
- if (pte_size >= PUD_SIZE &&
- (gpa & (PUD_SIZE - PAGE_SIZE)) ==
- (hva & (PUD_SIZE - PAGE_SIZE))) {
- level = 2;
- pfn &= ~((PUD_SIZE >> PAGE_SHIFT) - 1);
- } else if (pte_size >= PMD_SIZE &&
- (gpa & (PMD_SIZE - PAGE_SIZE)) ==
- (hva & (PMD_SIZE - PAGE_SIZE))) {
- level = 1;
- pfn &= ~((PMD_SIZE >> PAGE_SHIFT) - 1);
- }
- }
-
/*
- * Compute the PTE value that we need to insert.
+ * Read the PTE from the process' radix tree and use that
+ * so we get the shift and attribute bits.
*/
- if (page) {
- pgflags = _PAGE_READ | _PAGE_EXEC | _PAGE_PRESENT | _PAGE_PTE |
- _PAGE_ACCESSED;
- if (writing || upgrade_write)
- pgflags |= _PAGE_WRITE | _PAGE_DIRTY;
- pte = pfn_pte(pfn, __pgprot(pgflags));
+ local_irq_disable();
+ ptep = __find_linux_pte(vcpu->arch.pgdir, hva, NULL, &shift);
+ pte = *ptep;
+ local_irq_enable();
+
+ /* Get pte level from shift/size */
+ if (shift == PUD_SHIFT &&
+ (gpa & (PUD_SIZE - PAGE_SIZE)) ==
+ (hva & (PUD_SIZE - PAGE_SIZE))) {
+ level = 2;
+ } else if (shift == PMD_SHIFT &&
+ (gpa & (PMD_SIZE - PAGE_SIZE)) ==
+ (hva & (PMD_SIZE - PAGE_SIZE))) {
+ level = 1;
} else {
- /*
- * Read the PTE from the process' radix tree and use that
- * so we get the attribute bits.
- */
- local_irq_disable();
- ptep = __find_linux_pte(vcpu->arch.pgdir, hva, NULL, &shift);
- pte = *ptep;
- local_irq_enable();
- if (shift == PUD_SHIFT &&
- (gpa & (PUD_SIZE - PAGE_SIZE)) ==
- (hva & (PUD_SIZE - PAGE_SIZE))) {
- level = 2;
- } else if (shift == PMD_SHIFT &&
- (gpa & (PMD_SIZE - PAGE_SIZE)) ==
- (hva & (PMD_SIZE - PAGE_SIZE))) {
- level = 1;
- } else if (shift && shift != PAGE_SHIFT) {
- /* Adjust PFN */
- unsigned long mask = (1ul << shift) - PAGE_SIZE;
- pte = __pte(pte_val(pte) | (hva & mask));
- }
- pte = __pte(pte_val(pte) | _PAGE_EXEC | _PAGE_ACCESSED);
- if (writing || upgrade_write) {
- if (pte_val(pte) & _PAGE_WRITE)
- pte = __pte(pte_val(pte) | _PAGE_DIRTY);
- } else {
- pte = __pte(pte_val(pte) & ~(_PAGE_WRITE | _PAGE_DIRTY));
+ level = 0;
+ if (shift > PAGE_SHIFT) {
+ /*
+ * If the pte maps more than one page, bring over
+ * bits from the virtual address to get the real
+ * address of the specific single page we want.
+ */
+ unsigned long rpnmask = (1ul << shift) - PAGE_SIZE;
+ pte = __pte(pte_val(pte) | (hva & rpnmask));
}
}
+ pte = __pte(pte_val(pte) | _PAGE_EXEC | _PAGE_ACCESSED);
+ if (writing || upgrade_write) {
+ if (pte_val(pte) & _PAGE_WRITE)
+ pte = __pte(pte_val(pte) | _PAGE_DIRTY);
+ } else {
+ pte = __pte(pte_val(pte) & ~(_PAGE_WRITE | _PAGE_DIRTY));
+ }
+
/* Allocate space in the tree and write the PTE */
ret = kvmppc_create_pte(kvm, pte, gpa, level, mmu_seq);
--
2.20.1
^ permalink raw reply related [flat|nested] 2+ messages in thread
* [PATCH 19/20] KVM: PPC: Book3S HV: Don't use compound_order to determine host mapping size
[not found] <20190311165051.1149-1-leonardo@linux.ibm.com>
@ 2019-03-11 16:50 ` Leonardo Bras
0 siblings, 0 replies; 2+ messages in thread
From: Leonardo Bras @ 2019-03-11 16:50 UTC (permalink / raw)
To: kernel-team
Cc: Aneesh Kumar K.V, kvm-ppc, Nicholas Piggin, Leonardo Bras,
linuxppc-dev, David Gibson
From: Nicholas Piggin <npiggin@gmail.com>
THP paths can defer splitting compound pages until after the actual
remap and TLB flushes to split a huge PMD/PUD. This causes radix
partition scope page table mappings to get out of synch with the host
qemu page table mappings.
This results in random memory corruption in the guest when running
with THP. The easiest way to reproduce is use KVM balloon to free up
a lot of memory in the guest and then shrink the balloon to give the
memory back, while some work is being done in the guest.
Cc: David Gibson <david@gibson.dropbear.id.au>
Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com>
Cc: kvm-ppc@vger.kernel.org
Cc: linuxppc-dev@lists.ozlabs.org
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
Signed-off-by: Leonardo Bras <leonardo@linux.ibm.com>
---
arch/powerpc/kvm/book3s_64_mmu_radix.c | 91 +++++++++++---------------
1 file changed, 37 insertions(+), 54 deletions(-)
diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c
index 7efc42538ccf..ae023d2256ef 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_radix.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c
@@ -538,8 +538,8 @@ int kvmppc_book3s_radix_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
unsigned long ea, unsigned long dsisr)
{
struct kvm *kvm = vcpu->kvm;
- unsigned long mmu_seq, pte_size;
- unsigned long gpa, gfn, hva, pfn;
+ unsigned long mmu_seq;
+ unsigned long gpa, gfn, hva;
struct kvm_memory_slot *memslot;
struct page *page = NULL;
long ret;
@@ -636,9 +636,10 @@ int kvmppc_book3s_radix_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
*/
hva = gfn_to_hva_memslot(memslot, gfn);
if (upgrade_p && __get_user_pages_fast(hva, 1, 1, &page) == 1) {
- pfn = page_to_pfn(page);
upgrade_write = true;
} else {
+ unsigned long pfn;
+
/* Call KVM generic code to do the slow-path check */
pfn = __gfn_to_pfn_memslot(memslot, gfn, false, NULL,
writing, upgrade_p);
@@ -652,63 +653,45 @@ int kvmppc_book3s_radix_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
}
}
- /* See if we can insert a 1GB or 2MB large PTE here */
- level = 0;
- if (page && PageCompound(page)) {
- pte_size = PAGE_SIZE << compound_order(compound_head(page));
- if (pte_size >= PUD_SIZE &&
- (gpa & (PUD_SIZE - PAGE_SIZE)) ==
- (hva & (PUD_SIZE - PAGE_SIZE))) {
- level = 2;
- pfn &= ~((PUD_SIZE >> PAGE_SHIFT) - 1);
- } else if (pte_size >= PMD_SIZE &&
- (gpa & (PMD_SIZE - PAGE_SIZE)) ==
- (hva & (PMD_SIZE - PAGE_SIZE))) {
- level = 1;
- pfn &= ~((PMD_SIZE >> PAGE_SHIFT) - 1);
- }
- }
-
/*
- * Compute the PTE value that we need to insert.
+ * Read the PTE from the process' radix tree and use that
+ * so we get the shift and attribute bits.
*/
- if (page) {
- pgflags = _PAGE_READ | _PAGE_EXEC | _PAGE_PRESENT | _PAGE_PTE |
- _PAGE_ACCESSED;
- if (writing || upgrade_write)
- pgflags |= _PAGE_WRITE | _PAGE_DIRTY;
- pte = pfn_pte(pfn, __pgprot(pgflags));
+ local_irq_disable();
+ ptep = __find_linux_pte(vcpu->arch.pgdir, hva, NULL, &shift);
+ pte = *ptep;
+ local_irq_enable();
+
+ /* Get pte level from shift/size */
+ if (shift == PUD_SHIFT &&
+ (gpa & (PUD_SIZE - PAGE_SIZE)) ==
+ (hva & (PUD_SIZE - PAGE_SIZE))) {
+ level = 2;
+ } else if (shift == PMD_SHIFT &&
+ (gpa & (PMD_SIZE - PAGE_SIZE)) ==
+ (hva & (PMD_SIZE - PAGE_SIZE))) {
+ level = 1;
} else {
- /*
- * Read the PTE from the process' radix tree and use that
- * so we get the attribute bits.
- */
- local_irq_disable();
- ptep = __find_linux_pte(vcpu->arch.pgdir, hva, NULL, &shift);
- pte = *ptep;
- local_irq_enable();
- if (shift == PUD_SHIFT &&
- (gpa & (PUD_SIZE - PAGE_SIZE)) ==
- (hva & (PUD_SIZE - PAGE_SIZE))) {
- level = 2;
- } else if (shift == PMD_SHIFT &&
- (gpa & (PMD_SIZE - PAGE_SIZE)) ==
- (hva & (PMD_SIZE - PAGE_SIZE))) {
- level = 1;
- } else if (shift && shift != PAGE_SHIFT) {
- /* Adjust PFN */
- unsigned long mask = (1ul << shift) - PAGE_SIZE;
- pte = __pte(pte_val(pte) | (hva & mask));
- }
- pte = __pte(pte_val(pte) | _PAGE_EXEC | _PAGE_ACCESSED);
- if (writing || upgrade_write) {
- if (pte_val(pte) & _PAGE_WRITE)
- pte = __pte(pte_val(pte) | _PAGE_DIRTY);
- } else {
- pte = __pte(pte_val(pte) & ~(_PAGE_WRITE | _PAGE_DIRTY));
+ level = 0;
+ if (shift > PAGE_SHIFT) {
+ /*
+ * If the pte maps more than one page, bring over
+ * bits from the virtual address to get the real
+ * address of the specific single page we want.
+ */
+ unsigned long rpnmask = (1ul << shift) - PAGE_SIZE;
+ pte = __pte(pte_val(pte) | (hva & rpnmask));
}
}
+ pte = __pte(pte_val(pte) | _PAGE_EXEC | _PAGE_ACCESSED);
+ if (writing || upgrade_write) {
+ if (pte_val(pte) & _PAGE_WRITE)
+ pte = __pte(pte_val(pte) | _PAGE_DIRTY);
+ } else {
+ pte = __pte(pte_val(pte) & ~(_PAGE_WRITE | _PAGE_DIRTY));
+ }
+
/* Allocate space in the tree and write the PTE */
ret = kvmppc_create_pte(kvm, pte, gpa, level, mmu_seq);
--
2.20.1
^ permalink raw reply related [flat|nested] 2+ messages in thread
end of thread, other threads:[~2019-03-11 16:53 UTC | newest]
Thread overview: 2+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
[not found] <20190308163505.13021-1-leonardo@linux.ibm.com>
2019-03-08 16:35 ` [PATCH 19/20] KVM: PPC: Book3S HV: Don't use compound_order to determine host mapping size Leonardo Bras
[not found] <20190311165051.1149-1-leonardo@linux.ibm.com>
2019-03-11 16:50 ` Leonardo Bras
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).