summaryrefslogtreecommitdiff
path: root/arch/powerpc/kvm/book3s_hv_rm_mmu.c
diff options
context:
space:
mode:
Diffstat (limited to 'arch/powerpc/kvm/book3s_hv_rm_mmu.c')
-rw-r--r--arch/powerpc/kvm/book3s_hv_rm_mmu.c111
1 files changed, 56 insertions, 55 deletions
diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
index 625407e4d3b0..b027a89737b6 100644
--- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c
+++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
@@ -26,11 +26,14 @@ static void *real_vmalloc_addr(void *x)
{
unsigned long addr = (unsigned long) x;
pte_t *p;
-
- p = find_linux_pte_or_hugepte(swapper_pg_dir, addr, NULL);
+ /*
+ * assume we don't have huge pages in vmalloc space...
+ * So don't worry about THP collapse/split. Called
+ * Only in realmode, hence won't need irq_save/restore.
+ */
+ p = __find_linux_pte_or_hugepte(swapper_pg_dir, addr, NULL);
if (!p || !pte_present(*p))
return NULL;
- /* assume we don't have huge pages in vmalloc space... */
addr = (pte_pfn(*p) << PAGE_SHIFT) | (addr & ~PAGE_MASK);
return __va(addr);
}
@@ -131,31 +134,6 @@ static void remove_revmap_chain(struct kvm *kvm, long pte_index,
unlock_rmap(rmap);
}
-static pte_t lookup_linux_pte_and_update(pgd_t *pgdir, unsigned long hva,
- int writing, unsigned long *pte_sizep)
-{
- pte_t *ptep;
- unsigned long ps = *pte_sizep;
- unsigned int hugepage_shift;
-
- ptep = find_linux_pte_or_hugepte(pgdir, hva, &hugepage_shift);
- if (!ptep)
- return __pte(0);
- if (hugepage_shift)
- *pte_sizep = 1ul << hugepage_shift;
- else
- *pte_sizep = PAGE_SIZE;
- if (ps > *pte_sizep)
- return __pte(0);
- return kvmppc_read_update_linux_pte(ptep, writing, hugepage_shift);
-}
-
-static inline void unlock_hpte(__be64 *hpte, unsigned long hpte_v)
-{
- asm volatile(PPC_RELEASE_BARRIER "" : : : "memory");
- hpte[0] = cpu_to_be64(hpte_v);
-}
-
long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags,
long pte_index, unsigned long pteh, unsigned long ptel,
pgd_t *pgdir, bool realmode, unsigned long *pte_idx_ret)
@@ -166,13 +144,13 @@ long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags,
struct revmap_entry *rev;
unsigned long g_ptel;
struct kvm_memory_slot *memslot;
- unsigned long pte_size;
+ unsigned hpage_shift;
unsigned long is_io;
unsigned long *rmap;
- pte_t pte;
+ pte_t *ptep;
unsigned int writing;
unsigned long mmu_seq;
- unsigned long rcbits;
+ unsigned long rcbits, irq_flags = 0;
psize = hpte_page_size(pteh, ptel);
if (!psize)
@@ -208,22 +186,46 @@ long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags,
/* Translate to host virtual address */
hva = __gfn_to_hva_memslot(memslot, gfn);
-
- /* Look up the Linux PTE for the backing page */
- pte_size = psize;
- pte = lookup_linux_pte_and_update(pgdir, hva, writing, &pte_size);
- if (pte_present(pte) && !pte_protnone(pte)) {
- if (writing && !pte_write(pte))
- /* make the actual HPTE be read-only */
- ptel = hpte_make_readonly(ptel);
- is_io = hpte_cache_bits(pte_val(pte));
- pa = pte_pfn(pte) << PAGE_SHIFT;
- pa |= hva & (pte_size - 1);
- pa |= gpa & ~PAGE_MASK;
+ /*
+ * If we had a page table table change after lookup, we would
+ * retry via mmu_notifier_retry.
+ */
+ if (realmode)
+ ptep = __find_linux_pte_or_hugepte(pgdir, hva, &hpage_shift);
+ else {
+ local_irq_save(irq_flags);
+ ptep = find_linux_pte_or_hugepte(pgdir, hva, &hpage_shift);
}
+ if (ptep) {
+ pte_t pte;
+ unsigned int host_pte_size;
- if (pte_size < psize)
- return H_PARAMETER;
+ if (hpage_shift)
+ host_pte_size = 1ul << hpage_shift;
+ else
+ host_pte_size = PAGE_SIZE;
+ /*
+ * We should always find the guest page size
+ * to <= host page size, if host is using hugepage
+ */
+ if (host_pte_size < psize) {
+ if (!realmode)
+ local_irq_restore(flags);
+ return H_PARAMETER;
+ }
+ pte = kvmppc_read_update_linux_pte(ptep, writing);
+ if (pte_present(pte) && !pte_protnone(pte)) {
+ if (writing && !pte_write(pte))
+ /* make the actual HPTE be read-only */
+ ptel = hpte_make_readonly(ptel);
+ is_io = hpte_cache_bits(pte_val(pte));
+ pa = pte_pfn(pte) << PAGE_SHIFT;
+ pa |= hva & (host_pte_size - 1);
+ pa |= gpa & ~PAGE_MASK;
+ }
+ }
+ if (!realmode)
+ local_irq_restore(irq_flags);
ptel &= ~(HPTE_R_PP0 - psize);
ptel |= pa;
@@ -271,10 +273,10 @@ long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags,
u64 pte;
while (!try_lock_hpte(hpte, HPTE_V_HVLOCK))
cpu_relax();
- pte = be64_to_cpu(*hpte);
+ pte = be64_to_cpu(hpte[0]);
if (!(pte & (HPTE_V_VALID | HPTE_V_ABSENT)))
break;
- *hpte &= ~cpu_to_be64(HPTE_V_HVLOCK);
+ __unlock_hpte(hpte, pte);
hpte += 2;
}
if (i == 8)
@@ -290,9 +292,9 @@ long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags,
while (!try_lock_hpte(hpte, HPTE_V_HVLOCK))
cpu_relax();
- pte = be64_to_cpu(*hpte);
+ pte = be64_to_cpu(hpte[0]);
if (pte & (HPTE_V_VALID | HPTE_V_ABSENT)) {
- *hpte &= ~cpu_to_be64(HPTE_V_HVLOCK);
+ __unlock_hpte(hpte, pte);
return H_PTEG_FULL;
}
}
@@ -331,7 +333,7 @@ long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags,
/* Write the first HPTE dword, unlocking the HPTE and making it valid */
eieio();
- hpte[0] = cpu_to_be64(pteh);
+ __unlock_hpte(hpte, pteh);
asm volatile("ptesync" : : : "memory");
*pte_idx_ret = pte_index;
@@ -412,7 +414,7 @@ long kvmppc_do_h_remove(struct kvm *kvm, unsigned long flags,
if ((pte & (HPTE_V_ABSENT | HPTE_V_VALID)) == 0 ||
((flags & H_AVPN) && (pte & ~0x7fUL) != avpn) ||
((flags & H_ANDCOND) && (pte & avpn) != 0)) {
- hpte[0] &= ~cpu_to_be64(HPTE_V_HVLOCK);
+ __unlock_hpte(hpte, pte);
return H_NOT_FOUND;
}
@@ -548,7 +550,7 @@ long kvmppc_h_bulk_remove(struct kvm_vcpu *vcpu)
be64_to_cpu(hp[0]), be64_to_cpu(hp[1]));
rcbits = rev->guest_rpte & (HPTE_R_R|HPTE_R_C);
args[j] |= rcbits << (56 - 5);
- hp[0] = 0;
+ __unlock_hpte(hp, 0);
}
}
@@ -574,7 +576,7 @@ long kvmppc_h_protect(struct kvm_vcpu *vcpu, unsigned long flags,
pte = be64_to_cpu(hpte[0]);
if ((pte & (HPTE_V_ABSENT | HPTE_V_VALID)) == 0 ||
((flags & H_AVPN) && (pte & ~0x7fUL) != avpn)) {
- hpte[0] &= ~cpu_to_be64(HPTE_V_HVLOCK);
+ __unlock_hpte(hpte, pte);
return H_NOT_FOUND;
}
@@ -755,8 +757,7 @@ long kvmppc_hv_find_lock_hpte(struct kvm *kvm, gva_t eaddr, unsigned long slb_v,
/* Return with the HPTE still locked */
return (hash << 3) + (i >> 1);
- /* Unlock and move on */
- hpte[i] = cpu_to_be64(v);
+ __unlock_hpte(&hpte[i], v);
}
if (val & HPTE_V_SECONDARY)
generated by cgit v1.2.3 (git 2.39.0) at 2024-12-20 10:56:57 +0300