[PATCH v3 09/11] powerpc/kvm/book3s_64: Applies counting method to monitor lockless pgtbl walks

From: Leonardo Bras
Date: Tue Sep 24 2019 - 17:26:22 EST


Applies the counting-based method for monitoring all book3s_64-related
functions that do lockless pagetable walks.

Signed-off-by: Leonardo Bras <leonardo@xxxxxxxxxxxxx>
---
arch/powerpc/kvm/book3s_64_mmu_hv.c | 2 ++
arch/powerpc/kvm/book3s_64_mmu_radix.c | 20 ++++++++++++++++++--
arch/powerpc/kvm/book3s_64_vio_hv.c | 4 ++++
3 files changed, 24 insertions(+), 2 deletions(-)

diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c
index 9a75f0e1933b..fcd3dad1297f 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_hv.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c
@@ -620,6 +620,7 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
* We need to protect against page table destruction
* hugepage split and collapse.
*/
+ start_lockless_pgtbl_walk(kvm->mm);
local_irq_save(flags);
ptep = find_current_mm_pte(current->mm->pgd,
hva, NULL, NULL);
@@ -629,6 +630,7 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
write_ok = 1;
}
local_irq_restore(flags);
+ end_lockless_pgtbl_walk(kvm->mm);
}
}

diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c
index 2d415c36a61d..d46f8258d8d6 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_radix.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c
@@ -741,6 +741,7 @@ bool kvmppc_hv_handle_set_rc(struct kvm *kvm, pgd_t *pgtable, bool writing,
unsigned long pgflags;
unsigned int shift;
pte_t *ptep;
+ bool ret = false;

/*
* Need to set an R or C bit in the 2nd-level tables;
@@ -755,12 +756,14 @@ bool kvmppc_hv_handle_set_rc(struct kvm *kvm, pgd_t *pgtable, bool writing,
* We can do this without disabling irq because the Linux MM
* subsystem doesn't do THP splits and collapses on this tree.
*/
+ start_lockless_pgtbl_walk(kvm->mm);
ptep = __find_linux_pte(pgtable, gpa, NULL, &shift);
if (ptep && pte_present(*ptep) && (!writing || pte_write(*ptep))) {
kvmppc_radix_update_pte(kvm, ptep, 0, pgflags, gpa, shift);
- return true;
+ ret = true;
}
- return false;
+ end_lockless_pgtbl_walk(kvm->mm);
+ return ret;
}

int kvmppc_book3s_instantiate_page(struct kvm_vcpu *vcpu,
@@ -813,6 +816,7 @@ int kvmppc_book3s_instantiate_page(struct kvm_vcpu *vcpu,
* Read the PTE from the process' radix tree and use that
* so we get the shift and attribute bits.
*/
+ start_lockless_pgtbl_walk(kvm->mm);
local_irq_disable();
ptep = __find_linux_pte(vcpu->arch.pgdir, hva, NULL, &shift);
/*
@@ -821,12 +825,14 @@ int kvmppc_book3s_instantiate_page(struct kvm_vcpu *vcpu,
*/
if (!ptep) {
local_irq_enable();
+ end_lockless_pgtbl_walk(kvm->mm);
if (page)
put_page(page);
return RESUME_GUEST;
}
pte = *ptep;
local_irq_enable();
+ end_lockless_pgtbl_walk(kvm->mm);

/* If we're logging dirty pages, always map single pages */
large_enable = !(memslot->flags & KVM_MEM_LOG_DIRTY_PAGES);
@@ -972,10 +978,12 @@ int kvm_unmap_radix(struct kvm *kvm, struct kvm_memory_slot *memslot,
unsigned long gpa = gfn << PAGE_SHIFT;
unsigned int shift;

+ start_lockless_pgtbl_walk(kvm->mm);
ptep = __find_linux_pte(kvm->arch.pgtable, gpa, NULL, &shift);
if (ptep && pte_present(*ptep))
kvmppc_unmap_pte(kvm, ptep, gpa, shift, memslot,
kvm->arch.lpid);
+ end_lockless_pgtbl_walk(kvm->mm);
return 0;
}

@@ -989,6 +997,7 @@ int kvm_age_radix(struct kvm *kvm, struct kvm_memory_slot *memslot,
int ref = 0;
unsigned long old, *rmapp;

+ start_lockless_pgtbl_walk(kvm->mm);
ptep = __find_linux_pte(kvm->arch.pgtable, gpa, NULL, &shift);
if (ptep && pte_present(*ptep) && pte_young(*ptep)) {
old = kvmppc_radix_update_pte(kvm, ptep, _PAGE_ACCESSED, 0,
@@ -1001,6 +1010,7 @@ int kvm_age_radix(struct kvm *kvm, struct kvm_memory_slot *memslot,
1UL << shift);
ref = 1;
}
+ end_lockless_pgtbl_walk(kvm->mm);
return ref;
}

@@ -1013,9 +1023,11 @@ int kvm_test_age_radix(struct kvm *kvm, struct kvm_memory_slot *memslot,
unsigned int shift;
int ref = 0;

+ start_lockless_pgtbl_walk(kvm->mm);
ptep = __find_linux_pte(kvm->arch.pgtable, gpa, NULL, &shift);
if (ptep && pte_present(*ptep) && pte_young(*ptep))
ref = 1;
+ end_lockless_pgtbl_walk(kvm->mm);
return ref;
}

@@ -1030,6 +1042,7 @@ static int kvm_radix_test_clear_dirty(struct kvm *kvm,
int ret = 0;
unsigned long old, *rmapp;

+ start_lockless_pgtbl_walk(kvm->mm);
ptep = __find_linux_pte(kvm->arch.pgtable, gpa, NULL, &shift);
if (ptep && pte_present(*ptep) && pte_dirty(*ptep)) {
ret = 1;
@@ -1046,6 +1059,7 @@ static int kvm_radix_test_clear_dirty(struct kvm *kvm,
1UL << shift);
spin_unlock(&kvm->mmu_lock);
}
+ end_lockless_pgtbl_walk(kvm->mm);
return ret;
}

@@ -1084,6 +1098,7 @@ void kvmppc_radix_flush_memslot(struct kvm *kvm,

gpa = memslot->base_gfn << PAGE_SHIFT;
spin_lock(&kvm->mmu_lock);
+ start_lockless_pgtbl_walk(kvm->mm);
for (n = memslot->npages; n; --n) {
ptep = __find_linux_pte(kvm->arch.pgtable, gpa, NULL, &shift);
if (ptep && pte_present(*ptep))
@@ -1091,6 +1106,7 @@ void kvmppc_radix_flush_memslot(struct kvm *kvm,
kvm->arch.lpid);
gpa += PAGE_SIZE;
}
+ end_lockless_pgtbl_walk(kvm->mm);
spin_unlock(&kvm->mmu_lock);
}

diff --git a/arch/powerpc/kvm/book3s_64_vio_hv.c b/arch/powerpc/kvm/book3s_64_vio_hv.c
index b4f20f13b860..d7ea44f28993 100644
--- a/arch/powerpc/kvm/book3s_64_vio_hv.c
+++ b/arch/powerpc/kvm/book3s_64_vio_hv.c
@@ -431,6 +431,7 @@ long kvmppc_rm_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
static long kvmppc_rm_ua_to_hpa(struct kvm_vcpu *vcpu,
unsigned long ua, unsigned long *phpa)
{
+ struct kvm *kvm = vcpu->kvm;
pte_t *ptep, pte;
unsigned shift = 0;

@@ -443,10 +444,13 @@ static long kvmppc_rm_ua_to_hpa(struct kvm_vcpu *vcpu,
* to exit which will agains result in the below page table walk
* to finish.
*/
+
+ start_lockless_pgtbl_walk(kvm->mm);
ptep = __find_linux_pte(vcpu->arch.pgdir, ua, NULL, &shift);
if (!ptep || !pte_present(*ptep))
return -ENXIO;
pte = *ptep;
+ end_lockless_pgtbl_walk(kvm->mm);

if (!shift)
shift = PAGE_SHIFT;
--
2.20.1