bool writing, bool *writable);
extern void kvmppc_add_revmap_chain(struct kvm *kvm, struct revmap_entry *rev,
unsigned long *rmap, long pte_index, int realmode);
-extern void kvmppc_update_rmap_change(unsigned long *rmap, unsigned long psize);
+extern void kvmppc_update_dirty_map(struct kvm_memory_slot *memslot,
+ unsigned long gfn, unsigned long psize);
extern void kvmppc_invalidate_hpte(struct kvm *kvm, __be64 *hptep,
unsigned long pte_index);
void kvmppc_clear_ref_hpte(struct kvm *kvm, __be64 *hptep,
#ifndef __ASM_KVM_BOOK3S_64_H__
#define __ASM_KVM_BOOK3S_64_H__
+#include <linux/string.h>
+#include <asm/bitops.h>
#include <asm/book3s/64/mmu-hash.h>
/* Power architecture requires HPT is at least 256kiB, at most 64TiB */
return (1UL << (hpt->order - 7)) - 1;
}
+/* Set bits in a dirty bitmap, which is in LE format */
+static inline void set_dirty_bits(unsigned long *map, unsigned long i,
+ unsigned long npages)
+{
+
+ if (npages >= 8)
+ memset((char *)map + i / 8, 0xff, npages / 8);
+ else
+ for (; npages; ++i, --npages)
+ __set_bit_le(i, map);
+}
+
+static inline void set_dirty_bits_atomic(unsigned long *map, unsigned long i,
+ unsigned long npages)
+{
+ if (npages >= 8)
+ memset((char *)map + i / 8, 0xff, npages / 8);
+ else
+ for (; npages; ++i, --npages)
+ set_bit_le(i, map);
+}
+
#endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */
#endif /* __ASM_KVM_BOOK3S_64_H__ */
*/
#define KVMPPC_RMAP_LOCK_BIT 63
#define KVMPPC_RMAP_RC_SHIFT 32
-#define KVMPPC_RMAP_CHG_SHIFT 48
#define KVMPPC_RMAP_REFERENCED (HPTE_R_R << KVMPPC_RMAP_RC_SHIFT)
-#define KVMPPC_RMAP_CHANGED (HPTE_R_C << KVMPPC_RMAP_RC_SHIFT)
-#define KVMPPC_RMAP_CHG_ORDER (0x3ful << KVMPPC_RMAP_CHG_SHIFT)
#define KVMPPC_RMAP_PRESENT 0x100000000ul
#define KVMPPC_RMAP_INDEX 0xfffffffful
/* Must be called with both HPTE and rmap locked */
static void kvmppc_unmap_hpte(struct kvm *kvm, unsigned long i,
+ struct kvm_memory_slot *memslot,
unsigned long *rmapp, unsigned long gfn)
{
__be64 *hptep = (__be64 *) (kvm->arch.hpt.virt + (i << 4));
/* Harvest R and C */
rcbits = be64_to_cpu(hptep[1]) & (HPTE_R_R | HPTE_R_C);
*rmapp |= rcbits << KVMPPC_RMAP_RC_SHIFT;
- if (rcbits & HPTE_R_C)
- kvmppc_update_rmap_change(rmapp, psize);
+ if ((rcbits & HPTE_R_C) && memslot->dirty_bitmap)
+ kvmppc_update_dirty_map(memslot, gfn, psize);
if (rcbits & ~rev[i].guest_rpte) {
rev[i].guest_rpte = ptel | rcbits;
note_hpte_modification(kvm, &rev[i]);
continue;
}
- kvmppc_unmap_hpte(kvm, i, rmapp, gfn);
+ kvmppc_unmap_hpte(kvm, i, memslot, rmapp, gfn);
unlock_rmap(rmapp);
__unlock_hpte(hptep, be64_to_cpu(hptep[0]));
}
retry:
lock_rmap(rmapp);
- if (*rmapp & KVMPPC_RMAP_CHANGED) {
- long change_order = (*rmapp & KVMPPC_RMAP_CHG_ORDER)
- >> KVMPPC_RMAP_CHG_SHIFT;
- *rmapp &= ~(KVMPPC_RMAP_CHANGED | KVMPPC_RMAP_CHG_ORDER);
- npages_dirty = 1;
- if (change_order > PAGE_SHIFT)
- npages_dirty = 1ul << (change_order - PAGE_SHIFT);
- }
if (!(*rmapp & KVMPPC_RMAP_PRESENT)) {
unlock_rmap(rmapp);
return npages_dirty;
long kvmppc_hv_get_dirty_log_hpt(struct kvm *kvm,
struct kvm_memory_slot *memslot, unsigned long *map)
{
- unsigned long i, j;
+ unsigned long i;
unsigned long *rmapp;
preempt_disable();
* since we always put huge-page HPTEs in the rmap chain
* corresponding to their page base address.
*/
- if (npages && map)
- for (j = i; npages; ++j, --npages)
- __set_bit_le(j, map);
+ if (npages)
+ set_dirty_bits(map, i, npages);
++rmapp;
}
preempt_enable();
struct page *page = virt_to_page(va);
struct kvm_memory_slot *memslot;
unsigned long gfn;
- unsigned long *rmap;
int srcu_idx;
put_page(page);
if (!dirty)
return;
- /* We need to mark this page dirty in the rmap chain */
+ /* We need to mark this page dirty in the memslot dirty_bitmap, if any */
gfn = gpa >> PAGE_SHIFT;
srcu_idx = srcu_read_lock(&kvm->srcu);
memslot = gfn_to_memslot(kvm, gfn);
- if (memslot) {
- if (!kvm_is_radix(kvm)) {
- rmap = &memslot->arch.rmap[gfn - memslot->base_gfn];
- lock_rmap(rmap);
- *rmap |= KVMPPC_RMAP_CHANGED;
- unlock_rmap(rmap);
- } else if (memslot->dirty_bitmap) {
- mark_page_dirty(kvm, gfn);
- }
- }
+ if (memslot && memslot->dirty_bitmap)
+ set_bit_le(gfn - memslot->base_gfn, memslot->dirty_bitmap);
srcu_read_unlock(&kvm->srcu, srcu_idx);
}
rmapp = &memslot->arch.rmap[gfn - memslot->base_gfn];
lock_rmap(rmapp);
- kvmppc_unmap_hpte(kvm, idx, rmapp, gfn);
+ kvmppc_unmap_hpte(kvm, idx, memslot, rmapp, gfn);
unlock_rmap(rmapp);
}
return ret;
}
-static void mark_pages_dirty(struct kvm *kvm, struct kvm_memory_slot *memslot,
- unsigned long gfn, unsigned int order)
-{
- unsigned long i, limit;
- unsigned long *dp;
-
- if (!memslot->dirty_bitmap)
- return;
- limit = 1ul << order;
- if (limit < BITS_PER_LONG) {
- for (i = 0; i < limit; ++i)
- mark_page_dirty(kvm, gfn + i);
- return;
- }
- dp = memslot->dirty_bitmap + (gfn - memslot->base_gfn);
- limit /= BITS_PER_LONG;
- for (i = 0; i < limit; ++i)
- *dp++ = ~0ul;
-}
-
/* Called with kvm->lock held */
int kvm_unmap_radix(struct kvm *kvm, struct kvm_memory_slot *memslot,
unsigned long gfn)
old = kvmppc_radix_update_pte(kvm, ptep, _PAGE_PRESENT, 0,
gpa, shift);
kvmppc_radix_tlbie_page(kvm, gpa, shift);
- if (old & _PAGE_DIRTY) {
- if (!shift)
- mark_page_dirty(kvm, gfn);
- else
- mark_pages_dirty(kvm, memslot,
- gfn, shift - PAGE_SHIFT);
+ if ((old & _PAGE_DIRTY) && memslot->dirty_bitmap) {
+ unsigned long npages = 1;
+ if (shift)
+ npages = 1ul << (shift - PAGE_SHIFT);
+ kvmppc_update_dirty_map(memslot, gfn, npages);
}
}
return 0;
struct kvm_memory_slot *memslot, unsigned long *map)
{
unsigned long i, j;
- unsigned long n, *p;
int npages;
- /*
- * Radix accumulates dirty bits in the first half of the
- * memslot's dirty_bitmap area, for when pages are paged
- * out or modified by the host directly. Pick up these
- * bits and add them to the map.
- */
- n = kvm_dirty_bitmap_bytes(memslot) / sizeof(long);
- p = memslot->dirty_bitmap;
- for (i = 0; i < n; ++i)
- map[i] |= xchg(&p[i], 0);
-
for (i = 0; i < memslot->npages; i = j) {
npages = kvm_radix_test_clear_dirty(kvm, memslot, i);
* real address, if npages > 1 we can skip to i + npages.
*/
j = i + 1;
- if (npages)
- for (j = i; npages; ++j, --npages)
- __set_bit_le(j, map);
+ if (npages) {
+ set_dirty_bits(map, i, npages);
+ i = j + npages;
+ }
}
return 0;
}
struct kvm_memory_slot *memslot;
int i, r;
unsigned long n;
- unsigned long *buf;
+ unsigned long *buf, *p;
struct kvm_vcpu *vcpu;
mutex_lock(&kvm->slots_lock);
goto out;
/*
- * Use second half of bitmap area because radix accumulates
- * bits in the first half.
+ * Use second half of bitmap area because both HPT and radix
+ * accumulate bits in the first half.
*/
n = kvm_dirty_bitmap_bytes(memslot);
buf = memslot->dirty_bitmap + n / sizeof(long);
if (r)
goto out;
+ /*
+ * We accumulate dirty bits in the first half of the
+ * memslot's dirty_bitmap area, for when pages are paged
+ * out or modified by the host directly. Pick up these
+ * bits and add them to the map.
+ */
+ p = memslot->dirty_bitmap;
+ for (i = 0; i < n / sizeof(long); ++i)
+ buf[i] |= xchg(&p[i], 0);
+
/* Harvest dirty bits from VPA and DTL updates */
/* Note: we never modify the SLB shadow buffer areas */
kvm_for_each_vcpu(i, vcpu, kvm) {
const struct kvm_memory_slot *new)
{
unsigned long npages = mem->memory_size >> PAGE_SHIFT;
- struct kvm_memslots *slots;
- struct kvm_memory_slot *memslot;
/*
* If we are making a new memslot, it might make
*/
if (npages)
atomic64_inc(&kvm->arch.mmio_update);
-
- if (npages && old->npages && !kvm_is_radix(kvm)) {
- /*
- * 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.
- */
- slots = kvm_memslots(kvm);
- memslot = id_to_memslot(slots, mem->slot);
- kvmppc_hv_get_dirty_log_hpt(kvm, memslot, NULL);
- }
}
/*
}
EXPORT_SYMBOL_GPL(kvmppc_add_revmap_chain);
-/* Update the changed page order field of an rmap entry */
-void kvmppc_update_rmap_change(unsigned long *rmap, unsigned long psize)
+/* Update the dirty bitmap of a memslot */
+void kvmppc_update_dirty_map(struct kvm_memory_slot *memslot,
+ unsigned long gfn, unsigned long psize)
{
- unsigned long order;
+ unsigned long npages;
- if (!psize)
+ if (!psize || !memslot->dirty_bitmap)
return;
- order = ilog2(psize);
- order <<= KVMPPC_RMAP_CHG_SHIFT;
- if (order > (*rmap & KVMPPC_RMAP_CHG_ORDER))
- *rmap = (*rmap & ~KVMPPC_RMAP_CHG_ORDER) | order;
+ npages = (psize + PAGE_SIZE - 1) / PAGE_SIZE;
+ gfn -= memslot->base_gfn;
+ set_dirty_bits_atomic(memslot->dirty_bitmap, gfn, npages);
+}
+EXPORT_SYMBOL_GPL(kvmppc_update_dirty_map);
+
+static void kvmppc_set_dirty_from_hpte(struct kvm *kvm,
+ unsigned long hpte_v, unsigned long hpte_gr)
+{
+ struct kvm_memory_slot *memslot;
+ unsigned long gfn;
+ unsigned long psize;
+
+ psize = kvmppc_actual_pgsz(hpte_v, hpte_gr);
+ gfn = hpte_rpn(hpte_gr, psize);
+ memslot = __gfn_to_memslot(kvm_memslots_raw(kvm), gfn);
+ if (memslot && memslot->dirty_bitmap)
+ kvmppc_update_dirty_map(memslot, gfn, psize);
}
-EXPORT_SYMBOL_GPL(kvmppc_update_rmap_change);
/* Returns a pointer to the revmap entry for the page mapped by a HPTE */
static unsigned long *revmap_for_hpte(struct kvm *kvm, unsigned long hpte_v,
- unsigned long hpte_gr)
+ unsigned long hpte_gr,
+ struct kvm_memory_slot **memslotp,
+ unsigned long *gfnp)
{
struct kvm_memory_slot *memslot;
unsigned long *rmap;
gfn = hpte_rpn(hpte_gr, kvmppc_actual_pgsz(hpte_v, hpte_gr));
memslot = __gfn_to_memslot(kvm_memslots_raw(kvm), gfn);
+ if (memslotp)
+ *memslotp = memslot;
+ if (gfnp)
+ *gfnp = gfn;
if (!memslot)
return NULL;
unsigned long ptel, head;
unsigned long *rmap;
unsigned long rcbits;
+ struct kvm_memory_slot *memslot;
+ unsigned long gfn;
rcbits = hpte_r & (HPTE_R_R | HPTE_R_C);
ptel = rev->guest_rpte |= rcbits;
- rmap = revmap_for_hpte(kvm, hpte_v, ptel);
+ rmap = revmap_for_hpte(kvm, hpte_v, ptel, &memslot, &gfn);
if (!rmap)
return;
lock_rmap(rmap);
}
*rmap |= rcbits << KVMPPC_RMAP_RC_SHIFT;
if (rcbits & HPTE_R_C)
- kvmppc_update_rmap_change(rmap,
- kvmppc_actual_pgsz(hpte_v, hpte_r));
+ kvmppc_update_dirty_map(memslot, gfn,
+ kvmppc_actual_pgsz(hpte_v, hpte_r));
unlock_rmap(rmap);
}
gr |= r & (HPTE_R_R | HPTE_R_C);
if (r & HPTE_R_R) {
kvmppc_clear_ref_hpte(kvm, hpte, pte_index);
- rmap = revmap_for_hpte(kvm, v, gr);
+ rmap = revmap_for_hpte(kvm, v, gr, NULL, NULL);
if (rmap) {
lock_rmap(rmap);
*rmap |= KVMPPC_RMAP_REFERENCED;
__be64 *hpte;
unsigned long v, r, gr;
struct revmap_entry *rev;
- unsigned long *rmap;
long ret = H_NOT_FOUND;
if (kvm_is_radix(kvm))
r = be64_to_cpu(hpte[1]);
gr |= r & (HPTE_R_R | HPTE_R_C);
if (r & HPTE_R_C) {
- unsigned long psize = kvmppc_actual_pgsz(v, r);
hpte[1] = cpu_to_be64(r & ~HPTE_R_C);
eieio();
- rmap = revmap_for_hpte(kvm, v, gr);
- if (rmap) {
- lock_rmap(rmap);
- *rmap |= KVMPPC_RMAP_CHANGED;
- kvmppc_update_rmap_change(rmap, psize);
- unlock_rmap(rmap);
- }
+ kvmppc_set_dirty_from_hpte(kvm, v, gr);
}
}
vcpu->arch.gpr[4] = gr;