@@ -199,7 +199,6 @@ static int kvmppc_create_pte(struct kvm *kvm, pte_t pte, unsigned long gpa,
pud_t *pud, *new_pud = NULL;
pmd_t *pmd, *new_pmd = NULL;
pte_t *ptep, *new_ptep = NULL;
- unsigned long old;
int ret;
/* Traverse the guest's 2nd-level tree, allocate new levels needed */
@@ -243,6 +242,7 @@ static int kvmppc_create_pte(struct kvm *kvm, pte_t pte, unsigned long gpa,
pmd = pmd_offset(pud, gpa);
if (pmd_is_leaf(*pmd)) {
unsigned long lgpa = gpa & PMD_MASK;
+ pte_t old_pte = *pmdp_ptep(pmd);
/*
* If we raced with another CPU which has just put
@@ -252,18 +252,22 @@ static int kvmppc_create_pte(struct kvm *kvm, pte_t pte, unsigned long gpa,
ret = -EAGAIN;
goto out_unlock;
}
- /* Valid 2MB page here already, remove it */
- old = kvmppc_radix_update_pte(kvm, pmdp_ptep(pmd),
- ~0UL, 0, lgpa, PMD_SHIFT);
- kvmppc_radix_tlbie_page(kvm, lgpa, PMD_SHIFT);
- if (old & _PAGE_DIRTY) {
- unsigned long gfn = lgpa >> PAGE_SHIFT;
- struct kvm_memory_slot *memslot;
- memslot = gfn_to_memslot(kvm, gfn);
- if (memslot && memslot->dirty_bitmap)
- kvmppc_update_dirty_map(memslot,
- gfn, PMD_SIZE);
+
+ /* PTE was previously valid, so update it */
+ if (pte_val(old_pte) == pte_val(pte)) {
+ ret = -EAGAIN;
+ goto out_unlock;
}
+
+ /* Make sure we're weren't trying to take bits away */
+ WARN_ON_ONCE(pte_pfn(old_pte) != pte_pfn(pte));
+ WARN_ON_ONCE((pte_val(old_pte) & ~pte_val(pte)) &
+ (_PAGE_PRESENT | _PAGE_READ | _PAGE_WRITE));
+
+ kvmppc_radix_update_pte(kvm, pmdp_ptep(pmd),
+ 0, pte_val(pte), lgpa, PMD_SHIFT);
+ ret = 0;
+ goto out_unlock;
} else if (level == 1 && !pmd_none(*pmd)) {
/*
* There's a page table page here, but we wanted
@@ -274,6 +278,8 @@ static int kvmppc_create_pte(struct kvm *kvm, pte_t pte, unsigned long gpa,
goto out_unlock;
}
if (level == 0) {
+ pte_t old_pte;
+
if (pmd_none(*pmd)) {
if (!new_ptep)
goto out_unlock;
@@ -281,13 +287,21 @@ static int kvmppc_create_pte(struct kvm *kvm, pte_t pte, unsigned long gpa,
new_ptep = NULL;
}
ptep = pte_offset_kernel(pmd, gpa);
- if (pte_present(*ptep)) {
- /* PTE was previously valid, so invalidate it */
- old = kvmppc_radix_update_pte(kvm, ptep, _PAGE_PRESENT,
- 0, gpa, 0);
- kvmppc_radix_tlbie_page(kvm, gpa, 0);
- if (old & _PAGE_DIRTY)
- mark_page_dirty(kvm, gpa >> PAGE_SHIFT);
+ old_pte = *ptep;
+ if (pte_present(old_pte)) {
+ /* PTE was previously valid, so update it */
+ if (pte_val(old_pte) == pte_val(pte)) {
+ ret = -EAGAIN;
+ goto out_unlock;
+ }
+
+ /* Make sure we're weren't trying to take bits away */
+ WARN_ON_ONCE(pte_pfn(old_pte) != pte_pfn(pte));
+ WARN_ON_ONCE((pte_val(old_pte) & ~pte_val(pte)) &
+ (_PAGE_PRESENT | _PAGE_READ | _PAGE_WRITE));
+
+ kvmppc_radix_update_pte(kvm, ptep, 0,
+ pte_val(pte), gpa, 0);
}
kvmppc_radix_set_pte_at(kvm, gpa, ptep, pte);
} else {
When running a SMP radix guest, KVM can get into page fault / tlbie storms -- hundreds of thousands to the same address from different threads -- due to partition scoped page faults invalidating the page table entry if it was found to be already set up by a racing CPU. What can happen is that guest threads can hit page faults for the same addresses, this can happen when KSM or THP takes out a commonly used page. gRA zero (the interrupt vectors and important kernel text) was a common one. Multiple CPUs will page fault and contend on the same lock, when one CPU sets up the page table and releases the lock, the next will find the new entry and invalidate it before installing its own, which causes other page faults which invalidate that entry, etc. The solution to this is to avoid invalidating the entry or flushing TLBs in case of a race. The pte may still need bits updated, but those are to add R/C or relax access restrictions so no flush is required. This solves the page fault / tlbie storms. Signed-off-by: Nicholas Piggin <npiggin@gmail.com> --- arch/powerpc/kvm/book3s_64_mmu_radix.c | 52 ++++++++++++++++---------- 1 file changed, 33 insertions(+), 19 deletions(-)