public inbox for kvm@vger.kernel.org
 help / color / mirror / Atom feed
From: Alexander Graf <agraf@suse.de>
To: kvm-ppc@vger.kernel.org
Cc: kvm list <kvm@vger.kernel.org>, Avi Kivity <avi@redhat.com>,
	Marcelo Tosatti <mtosatti@redhat.com>,
	Paul Mackerras <paulus@samba.org>
Subject: [PATCH 45/52] KVM: PPC: Book3s HV: Implement get_dirty_log using hardware changed bit
Date: Fri, 13 Jan 2012 15:31:48 +0100	[thread overview]
Message-ID: <1326465115-5976-46-git-send-email-agraf@suse.de> (raw)
In-Reply-To: <1326465115-5976-1-git-send-email-agraf@suse.de>

From: Paul Mackerras <paulus@samba.org>

This changes the implementation of kvm_vm_ioctl_get_dirty_log() for
Book3s HV guests to use the hardware C (changed) bits in the guest
hashed page table.  Since this makes the implementation quite different
from the Book3s PR case, this moves the existing implementation from
book3s.c to book3s_pr.c and creates a new implementation in book3s_hv.c.
That implementation calls kvmppc_hv_get_dirty_log() to do the actual
work by calling kvm_test_clear_dirty on each page.  It iterates over
the HPTEs, clearing the C bit if set, and returns 1 if any C bit was
set (including the saved C bit in the rmap entry).

Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/include/asm/kvm_book3s.h |    2 +
 arch/powerpc/kvm/book3s.c             |   39 ------------------
 arch/powerpc/kvm/book3s_64_mmu_hv.c   |   69 +++++++++++++++++++++++++++++++++
 arch/powerpc/kvm/book3s_hv.c          |   37 +++++++++++++++++
 arch/powerpc/kvm/book3s_pr.c          |   39 ++++++++++++++++++
 5 files changed, 147 insertions(+), 39 deletions(-)

diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h
index 33fdc09..3c3edee 100644
--- a/arch/powerpc/include/asm/kvm_book3s.h
+++ b/arch/powerpc/include/asm/kvm_book3s.h
@@ -156,6 +156,8 @@ extern long kvmppc_virtmode_h_enter(struct kvm_vcpu *vcpu, unsigned long flags,
 			long pte_index, unsigned long pteh, unsigned long ptel);
 extern long kvmppc_h_enter(struct kvm_vcpu *vcpu, unsigned long flags,
 			long pte_index, unsigned long pteh, unsigned long ptel);
+extern long kvmppc_hv_get_dirty_log(struct kvm *kvm,
+			struct kvm_memory_slot *memslot);
 
 extern void kvmppc_entry_trampoline(void);
 extern void kvmppc_hv_entry_trampoline(void);
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index 6bf7e05..7d54f4e 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -477,45 +477,6 @@ int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu,
 	return 0;
 }
 
-/*
- * Get (and clear) the dirty memory log for a memory slot.
- */
-int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm,
-				      struct kvm_dirty_log *log)
-{
-	struct kvm_memory_slot *memslot;
-	struct kvm_vcpu *vcpu;
-	ulong ga, ga_end;
-	int is_dirty = 0;
-	int r;
-	unsigned long n;
-
-	mutex_lock(&kvm->slots_lock);
-
-	r = kvm_get_dirty_log(kvm, log, &is_dirty);
-	if (r)
-		goto out;
-
-	/* If nothing is dirty, don't bother messing with page tables. */
-	if (is_dirty) {
-		memslot = id_to_memslot(kvm->memslots, log->slot);
-
-		ga = memslot->base_gfn << PAGE_SHIFT;
-		ga_end = ga + (memslot->npages << PAGE_SHIFT);
-
-		kvm_for_each_vcpu(n, vcpu, kvm)
-			kvmppc_mmu_pte_pflush(vcpu, ga, ga_end);
-
-		n = kvm_dirty_bitmap_bytes(memslot);
-		memset(memslot->dirty_bitmap, 0, n);
-	}
-
-	r = 0;
-out:
-	mutex_unlock(&kvm->slots_lock);
-	return r;
-}
-
 void kvmppc_decrementer_func(unsigned long data)
 {
 	struct kvm_vcpu *vcpu = (struct kvm_vcpu *)data;
diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c
index 926e2b9..783cd35 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_hv.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c
@@ -870,6 +870,75 @@ void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte)
 	kvm_handle_hva(kvm, hva, kvm_unmap_rmapp);
 }
 
+static int kvm_test_clear_dirty(struct kvm *kvm, unsigned long *rmapp)
+{
+	struct revmap_entry *rev = kvm->arch.revmap;
+	unsigned long head, i, j;
+	unsigned long *hptep;
+	int ret = 0;
+
+ retry:
+	lock_rmap(rmapp);
+	if (*rmapp & KVMPPC_RMAP_CHANGED) {
+		*rmapp &= ~KVMPPC_RMAP_CHANGED;
+		ret = 1;
+	}
+	if (!(*rmapp & KVMPPC_RMAP_PRESENT)) {
+		unlock_rmap(rmapp);
+		return ret;
+	}
+
+	i = head = *rmapp & KVMPPC_RMAP_INDEX;
+	do {
+		hptep = (unsigned long *) (kvm->arch.hpt_virt + (i << 4));
+		j = rev[i].forw;
+
+		if (!(hptep[1] & HPTE_R_C))
+			continue;
+
+		if (!try_lock_hpte(hptep, HPTE_V_HVLOCK)) {
+			/* unlock rmap before spinning on the HPTE lock */
+			unlock_rmap(rmapp);
+			while (hptep[0] & HPTE_V_HVLOCK)
+				cpu_relax();
+			goto retry;
+		}
+
+		/* Now check and modify the HPTE */
+		if ((hptep[0] & HPTE_V_VALID) && (hptep[1] & HPTE_R_C)) {
+			/* need to make it temporarily absent to clear C */
+			hptep[0] |= HPTE_V_ABSENT;
+			kvmppc_invalidate_hpte(kvm, hptep, i);
+			hptep[1] &= ~HPTE_R_C;
+			eieio();
+			hptep[0] = (hptep[0] & ~HPTE_V_ABSENT) | HPTE_V_VALID;
+			rev[i].guest_rpte |= HPTE_R_C;
+			ret = 1;
+		}
+		hptep[0] &= ~HPTE_V_HVLOCK;
+	} while ((i = j) != head);
+
+	unlock_rmap(rmapp);
+	return ret;
+}
+
+long kvmppc_hv_get_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot)
+{
+	unsigned long i;
+	unsigned long *rmapp, *map;
+
+	preempt_disable();
+	rmapp = memslot->rmap;
+	map = memslot->dirty_bitmap;
+	for (i = 0; i < memslot->npages; ++i) {
+		if (kvm_test_clear_dirty(kvm, rmapp))
+			__set_bit_le(i, map);
+		++rmapp;
+	}
+	preempt_enable();
+	return 0;
+}
+
 void *kvmppc_pin_guest_page(struct kvm *kvm, unsigned long gpa,
 			    unsigned long *nb_ret)
 {
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 86c4191..0f1ddf0 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -1072,6 +1072,43 @@ long kvm_vm_ioctl_allocate_rma(struct kvm *kvm, struct kvm_allocate_rma *ret)
 	return fd;
 }
 
+/*
+ * Get (and clear) the dirty memory log for a memory slot.
+ */
+int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log)
+{
+	struct kvm_memory_slot *memslot;
+	int r;
+	unsigned long n;
+
+	mutex_lock(&kvm->slots_lock);
+
+	r = -EINVAL;
+	if (log->slot >= KVM_MEMORY_SLOTS)
+		goto out;
+
+	memslot = id_to_memslot(kvm->memslots, log->slot);
+	r = -ENOENT;
+	if (!memslot->dirty_bitmap)
+		goto out;
+
+	n = kvm_dirty_bitmap_bytes(memslot);
+	memset(memslot->dirty_bitmap, 0, n);
+
+	r = kvmppc_hv_get_dirty_log(kvm, memslot);
+	if (r)
+		goto out;
+
+	r = -EFAULT;
+	if (copy_to_user(log->dirty_bitmap, memslot->dirty_bitmap, n))
+		goto out;
+
+	r = 0;
+out:
+	mutex_unlock(&kvm->slots_lock);
+	return r;
+}
+
 static unsigned long slb_pgsize_encoding(unsigned long psize)
 {
 	unsigned long senc = 0;
diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c
index 2da6704..c193625 100644
--- a/arch/powerpc/kvm/book3s_pr.c
+++ b/arch/powerpc/kvm/book3s_pr.c
@@ -1056,6 +1056,45 @@ out:
 	return ret;
 }
 
+/*
+ * Get (and clear) the dirty memory log for a memory slot.
+ */
+int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm,
+				      struct kvm_dirty_log *log)
+{
+	struct kvm_memory_slot *memslot;
+	struct kvm_vcpu *vcpu;
+	ulong ga, ga_end;
+	int is_dirty = 0;
+	int r;
+	unsigned long n;
+
+	mutex_lock(&kvm->slots_lock);
+
+	r = kvm_get_dirty_log(kvm, log, &is_dirty);
+	if (r)
+		goto out;
+
+	/* If nothing is dirty, don't bother messing with page tables. */
+	if (is_dirty) {
+		memslot = id_to_memslot(kvm->memslots, log->slot);
+
+		ga = memslot->base_gfn << PAGE_SHIFT;
+		ga_end = ga + (memslot->npages << PAGE_SHIFT);
+
+		kvm_for_each_vcpu(n, vcpu, kvm)
+			kvmppc_mmu_pte_pflush(vcpu, ga, ga_end);
+
+		n = kvm_dirty_bitmap_bytes(memslot);
+		memset(memslot->dirty_bitmap, 0, n);
+	}
+
+	r = 0;
+out:
+	mutex_unlock(&kvm->slots_lock);
+	return r;
+}
+
 int kvmppc_core_prepare_memory_region(struct kvm *kvm,
 				      struct kvm_userspace_memory_region *mem)
 {
-- 
1.6.0.2

  parent reply	other threads:[~2012-01-13 14:31 UTC|newest]

Thread overview: 54+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2012-01-13 14:31 [PULL 00/52] ppc patch queue 2012-01-13 Alexander Graf
2012-01-13 14:31 ` [PATCH 01/52] KVM: PPC: e500: don't translate gfn to pfn with preemption disabled Alexander Graf
2012-01-13 14:31 ` [PATCH 02/52] KVM: PPC: e500: Eliminate preempt_disable in local_sid_destroy_all Alexander Graf
2012-01-13 14:31 ` [PATCH 03/52] KVM: PPC: e500: clear up confusion between host and guest entries Alexander Graf
2012-01-13 14:31 ` [PATCH 04/52] KVM: PPC: e500: MMU API Alexander Graf
2012-01-13 14:31 ` [PATCH 05/52] KVM: PPC: e500: tlbsx: fix tlb0 esel Alexander Graf
2012-01-13 14:31 ` [PATCH 06/52] KVM: PPC: e500: Don't hardcode PIR=0 Alexander Graf
2012-01-13 14:31 ` [PATCH 07/52] KVM: PPC: E500: Support hugetlbfs Alexander Graf
2012-01-13 14:31 ` [PATCH 08/52] PPC: Fix race in mtmsr paravirt implementation Alexander Graf
2012-01-13 14:31 ` [PATCH 09/52] Fix DEC truncation for greater than 0xffff_ffff/1000 Alexander Graf
2012-01-13 14:31 ` [PATCH 10/52] KVM: booke: Do Not start decrementer when SPRN_DEC set 0 Alexander Graf
2012-01-13 14:31 ` [PATCH 11/52] KVM: PPC: booke: check for signals in kvmppc_vcpu_run Alexander Graf
2012-01-13 14:31 ` [PATCH 12/52] KVM: PPC: Rename deliver_interrupts to prepare_to_enter Alexander Graf
2012-01-13 14:31 ` [PATCH 13/52] KVM: PPC: Move prepare_to_enter call site into subarch code Alexander Graf
2012-01-13 14:31 ` [PATCH 14/52] KVM: PPC: booke: Check for MSR[WE] in prepare_to_enter Alexander Graf
2012-01-13 14:31 ` [PATCH 15/52] KVM: PPC: booke: Fix int_pending calculation for MSR[EE] paravirt Alexander Graf
2012-01-13 14:31 ` [PATCH 16/52] KVM: PPC: booke: Paravirtualize wrtee Alexander Graf
2012-01-13 14:31 ` [PATCH 17/52] KVM: PPC: Paravirtualize SPRG4-7, ESR, PIR, MASn Alexander Graf
2012-01-13 14:31 ` [PATCH 18/52] KVM: PPC: booke: Improve timer register emulation Alexander Graf
2012-01-13 14:31 ` [PATCH 19/52] KVM: PPC: Book3s: PR: Disable preemption in vcpu_run Alexander Graf
2012-01-13 14:31 ` [PATCH 20/52] KVM: PPC: Book3s: PR: No irq_disable " Alexander Graf
2012-01-13 14:31 ` [PATCH 21/52] KVM: PPC: Use get/set for to_svcpu to help preemption Alexander Graf
2012-01-13 14:31 ` [PATCH 22/52] KVM: PPC: align vcpu_kick with x86 Alexander Graf
2012-01-13 14:31 ` [PATCH 23/52] KVM: PPC: Book3S: PR: Fix signal check race Alexander Graf
2012-01-13 14:31 ` [PATCH 24/52] KVM: PPC: e500: Fix TLBnCFG in KVM_CONFIG_TLB Alexander Graf
2012-01-13 14:31 ` [PATCH 25/52] KVM: PPC: e500: use hardware hint when loading TLB0 entries Alexander Graf
2012-01-13 14:31 ` [PATCH 26/52] KVM: PPC: Avoid patching paravirt template code Alexander Graf
2012-01-13 14:31 ` [PATCH 27/52] KVM: PPC: Make wakeups work again for Book3S HV guests Alexander Graf
2012-01-13 14:31 ` [PATCH 28/52] KVM: PPC: Keep a record of HV guest view of hashed page table entries Alexander Graf
2012-01-13 14:31 ` [PATCH 29/52] KVM: PPC: Keep page physical addresses in per-slot arrays Alexander Graf
2012-01-13 14:31 ` [PATCH 30/52] KVM: PPC: Add an interface for pinning guest pages in Book3s HV guests Alexander Graf
2012-01-13 14:31 ` [PATCH 31/52] KVM: PPC: Make the H_ENTER hcall more reliable Alexander Graf
2012-01-13 14:31 ` [PATCH 32/52] KVM: PPC: Only get pages when actually needed, not in prepare_memory_region() Alexander Graf
2012-01-13 14:31 ` [PATCH 33/52] KVM: PPC: Allow use of small pages to back Book3S HV guests Alexander Graf
2012-01-13 14:31 ` [PATCH 34/52] KVM: PPC: Allow I/O mappings in memory slots Alexander Graf
2012-01-13 14:31 ` [PATCH 35/52] KVM: PPC: Maintain a doubly-linked list of guest HPTEs for each gfn Alexander Graf
2012-01-13 14:31 ` [PATCH 36/52] KVM: PPC: Implement MMIO emulation support for Book3S HV guests Alexander Graf
2012-01-13 14:31 ` [PATCH 37/52] KVM: PPC: Implement MMU notifiers " Alexander Graf
2012-01-13 14:31 ` [PATCH 38/52] KVM: Add barriers to allow mmu_notifier_retry to be used locklessly Alexander Graf
2012-01-13 14:31 ` [PATCH 39/52] KVM: PPC: Allow for read-only pages backing a Book3S HV guest Alexander Graf
2012-01-13 14:31 ` [PATCH 40/52] KVM: PPC: Fix vcpu_create dereference before validity check Alexander Graf
2012-01-13 14:31 ` [PATCH 41/52] KVM: PPC: Add KVM_CAP_NR_VCPUS and KVM_CAP_MAX_VCPUS Alexander Graf
2012-01-13 14:31 ` [PATCH 42/52] KVM: PPC: Book3S HV: Keep HPTE locked when invalidating Alexander Graf
2012-01-13 14:31 ` [PATCH 43/52] KVM: PPC: Book3s HV: Maintain separate guest and host views of R and C bits Alexander Graf
2012-01-13 14:31 ` [PATCH 44/52] KVM: PPC: Book3S HV: Use the hardware referenced bit for kvm_age_hva Alexander Graf
2012-01-13 14:31 ` Alexander Graf [this message]
2012-01-13 14:31 ` [PATCH 46/52] KVM: PPC: booke: Add booke206 TLB trace Alexander Graf
2012-01-13 14:31 ` [PATCH 47/52] KVM: PPC: Use the vcpu kmem_cache when allocating new VCPUs Alexander Graf
2012-01-13 14:31 ` [PATCH 48/52] KVM: PPC: Add generic single register ioctls Alexander Graf
2012-01-13 14:31 ` [PATCH 49/52] KVM: PPC: Add support for explicit HIOR setting Alexander Graf
2012-01-13 14:31 ` [PATCH 50/52] KVM: PPC: Move kvm_vcpu_ioctl_[gs]et_one_reg down to platform-specific code Alexander Graf
2012-01-13 14:31 ` [PATCH 51/52] KVM: PPC: Rename MMIO register identifiers Alexander Graf
2012-01-13 14:31 ` [PATCH 52/52] KVM: PPC: refer to paravirt docs in header file Alexander Graf
2012-01-16 10:55 ` [PULL 00/52] ppc patch queue 2012-01-13 Marcelo Tosatti

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=1326465115-5976-46-git-send-email-agraf@suse.de \
    --to=agraf@suse.de \
    --cc=avi@redhat.com \
    --cc=kvm-ppc@vger.kernel.org \
    --cc=kvm@vger.kernel.org \
    --cc=mtosatti@redhat.com \
    --cc=paulus@samba.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox