[PATCH RFC 0/2] KVM: remove host and guest pv mmu support

[PATCH RFC 0/2] KVM: remove host and guest pv mmu support

[Chris Wright]

This feature hasn't been in use for some years now.  The host side bits
are deprecated for almost a year.  The guest side would only get used
on old hosts, and it's slower than shadow or hw assisted paging.

Time to remove it.

 Documentation/feature-removal-schedule.txt |    9 --
 arch/x86/include/asm/kvm_host.h            |   13 --
 arch/x86/kernel/kvm.c                      |  181 ----------------------------
 arch/x86/kvm/mmu.c                         |  135 ---------------------
 arch/x86/kvm/x86.c                         |   12 --
 5 files changed, 0 insertions(+), 350 deletions(-)

[PATCH RFC 1/2] KVM Guest: remove KVM guest pv mmu support

[Chris Wright]

This has not been used for some years now.  It's time to remove it.
Will also make some pv patching improvements easier.

Signed-off-by: Chris Wright <chrisw@redhat.com>
---
 arch/x86/kernel/kvm.c |  181 -------------------------------------------------
 1 files changed, 0 insertions(+), 181 deletions(-)

diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index a9c2116..f0c6fd6 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -39,8 +39,6 @@
 #include <asm/desc.h>
 #include <asm/tlbflush.h>
 
-#define MMU_QUEUE_SIZE 1024
-
 static int kvmapf = 1;
 
 static int parse_no_kvmapf(char *arg)
@@ -60,21 +58,10 @@ static int parse_no_stealacc(char *arg)
 
 early_param("no-steal-acc", parse_no_stealacc);
 
-struct kvm_para_state {
-	u8 mmu_queue[MMU_QUEUE_SIZE];
-	int mmu_queue_len;
-};
-
-static DEFINE_PER_CPU(struct kvm_para_state, para_state);
 static DEFINE_PER_CPU(struct kvm_vcpu_pv_apf_data, apf_reason) __aligned(64);
 static DEFINE_PER_CPU(struct kvm_steal_time, steal_time) __aligned(64);
 static int has_steal_clock = 0;
 
-static struct kvm_para_state *kvm_para_state(void)
-{
-	return &per_cpu(para_state, raw_smp_processor_id());
-}
-
 /*
  * No need for any "IO delay" on KVM
  */
@@ -271,151 +258,6 @@ do_async_page_fault(struct pt_regs *regs, unsigned long error_code)
 	}
 }
 
-static void kvm_mmu_op(void *buffer, unsigned len)
-{
-	int r;
-	unsigned long a1, a2;
-
-	do {
-		a1 = __pa(buffer);
-		a2 = 0;   /* on i386 __pa() always returns <4G */
-		r = kvm_hypercall3(KVM_HC_MMU_OP, len, a1, a2);
-		buffer += r;
-		len -= r;
-	} while (len);
-}
-
-static void mmu_queue_flush(struct kvm_para_state *state)
-{
-	if (state->mmu_queue_len) {
-		kvm_mmu_op(state->mmu_queue, state->mmu_queue_len);
-		state->mmu_queue_len = 0;
-	}
-}
-
-static void kvm_deferred_mmu_op(void *buffer, int len)
-{
-	struct kvm_para_state *state = kvm_para_state();
-
-	if (paravirt_get_lazy_mode() != PARAVIRT_LAZY_MMU) {
-		kvm_mmu_op(buffer, len);
-		return;
-	}
-	if (state->mmu_queue_len + len > sizeof state->mmu_queue)
-		mmu_queue_flush(state);
-	memcpy(state->mmu_queue + state->mmu_queue_len, buffer, len);
-	state->mmu_queue_len += len;
-}
-
-static void kvm_mmu_write(void *dest, u64 val)
-{
-	__u64 pte_phys;
-	struct kvm_mmu_op_write_pte wpte;
-
-#ifdef CONFIG_HIGHPTE
-	struct page *page;
-	unsigned long dst = (unsigned long) dest;
-
-	page = kmap_atomic_to_page(dest);
-	pte_phys = page_to_pfn(page);
-	pte_phys <<= PAGE_SHIFT;
-	pte_phys += (dst & ~(PAGE_MASK));
-#else
-	pte_phys = (unsigned long)__pa(dest);
-#endif
-	wpte.header.op = KVM_MMU_OP_WRITE_PTE;
-	wpte.pte_val = val;
-	wpte.pte_phys = pte_phys;
-
-	kvm_deferred_mmu_op(&wpte, sizeof wpte);
-}
-
-/*
- * We only need to hook operations that are MMU writes.  We hook these so that
- * we can use lazy MMU mode to batch these operations.  We could probably
- * improve the performance of the host code if we used some of the information
- * here to simplify processing of batched writes.
- */
-static void kvm_set_pte(pte_t *ptep, pte_t pte)
-{
-	kvm_mmu_write(ptep, pte_val(pte));
-}
-
-static void kvm_set_pte_at(struct mm_struct *mm, unsigned long addr,
-			   pte_t *ptep, pte_t pte)
-{
-	kvm_mmu_write(ptep, pte_val(pte));
-}
-
-static void kvm_set_pmd(pmd_t *pmdp, pmd_t pmd)
-{
-	kvm_mmu_write(pmdp, pmd_val(pmd));
-}
-
-#if PAGETABLE_LEVELS >= 3
-#ifdef CONFIG_X86_PAE
-static void kvm_set_pte_atomic(pte_t *ptep, pte_t pte)
-{
-	kvm_mmu_write(ptep, pte_val(pte));
-}
-
-static void kvm_pte_clear(struct mm_struct *mm,
-			  unsigned long addr, pte_t *ptep)
-{
-	kvm_mmu_write(ptep, 0);
-}
-
-static void kvm_pmd_clear(pmd_t *pmdp)
-{
-	kvm_mmu_write(pmdp, 0);
-}
-#endif
-
-static void kvm_set_pud(pud_t *pudp, pud_t pud)
-{
-	kvm_mmu_write(pudp, pud_val(pud));
-}
-
-#if PAGETABLE_LEVELS == 4
-static void kvm_set_pgd(pgd_t *pgdp, pgd_t pgd)
-{
-	kvm_mmu_write(pgdp, pgd_val(pgd));
-}
-#endif
-#endif /* PAGETABLE_LEVELS >= 3 */
-
-static void kvm_flush_tlb(void)
-{
-	struct kvm_mmu_op_flush_tlb ftlb = {
-		.header.op = KVM_MMU_OP_FLUSH_TLB,
-	};
-
-	kvm_deferred_mmu_op(&ftlb, sizeof ftlb);
-}
-
-static void kvm_release_pt(unsigned long pfn)
-{
-	struct kvm_mmu_op_release_pt rpt = {
-		.header.op = KVM_MMU_OP_RELEASE_PT,
-		.pt_phys = (u64)pfn << PAGE_SHIFT,
-	};
-
-	kvm_mmu_op(&rpt, sizeof rpt);
-}
-
-static void kvm_enter_lazy_mmu(void)
-{
-	paravirt_enter_lazy_mmu();
-}
-
-static void kvm_leave_lazy_mmu(void)
-{
-	struct kvm_para_state *state = kvm_para_state();
-
-	mmu_queue_flush(state);
-	paravirt_leave_lazy_mmu();
-}
-
 static void __init paravirt_ops_setup(void)
 {
 	pv_info.name = "KVM";
@@ -424,29 +266,6 @@ static void __init paravirt_ops_setup(void)
 	if (kvm_para_has_feature(KVM_FEATURE_NOP_IO_DELAY))
 		pv_cpu_ops.io_delay = kvm_io_delay;
 
-	if (kvm_para_has_feature(KVM_FEATURE_MMU_OP)) {
-		pv_mmu_ops.set_pte = kvm_set_pte;
-		pv_mmu_ops.set_pte_at = kvm_set_pte_at;
-		pv_mmu_ops.set_pmd = kvm_set_pmd;
-#if PAGETABLE_LEVELS >= 3
-#ifdef CONFIG_X86_PAE
-		pv_mmu_ops.set_pte_atomic = kvm_set_pte_atomic;
-		pv_mmu_ops.pte_clear = kvm_pte_clear;
-		pv_mmu_ops.pmd_clear = kvm_pmd_clear;
-#endif
-		pv_mmu_ops.set_pud = kvm_set_pud;
-#if PAGETABLE_LEVELS == 4
-		pv_mmu_ops.set_pgd = kvm_set_pgd;
-#endif
-#endif
-		pv_mmu_ops.flush_tlb_user = kvm_flush_tlb;
-		pv_mmu_ops.release_pte = kvm_release_pt;
-		pv_mmu_ops.release_pmd = kvm_release_pt;
-		pv_mmu_ops.release_pud = kvm_release_pt;
-
-		pv_mmu_ops.lazy_mode.enter = kvm_enter_lazy_mmu;
-		pv_mmu_ops.lazy_mode.leave = kvm_leave_lazy_mmu;
-	}
 #ifdef CONFIG_X86_IO_APIC
 	no_timer_check = 1;
 #endif

[PATCH RFC 2/2] KVM: remove KVM host pv mmu support

[Chris Wright]

The host side pv mmu support has been marked for feature removal in
January 2011.  It's not in use, is slower than shadow or hardware
assisted paging, and a maintenance burden.  It's October 2011, time to
remove it.

Signed-off-by: Chris Wright <chrisw@redhat.com>
---
 Documentation/feature-removal-schedule.txt |    9 --
 arch/x86/include/asm/kvm_host.h            |   13 ---
 arch/x86/kvm/mmu.c                         |  135 ----------------------------
 arch/x86/kvm/x86.c                         |   12 ---
 4 files changed, 0 insertions(+), 169 deletions(-)

diff --git a/Documentation/feature-removal-schedule.txt b/Documentation/feature-removal-schedule.txt
index 4dc4654..75f88a5 100644
--- a/Documentation/feature-removal-schedule.txt
+++ b/Documentation/feature-removal-schedule.txt
@@ -397,15 +397,6 @@ Who: 	anybody or Florian Mickler <florian@mickler.org>
 
 ----------------------------
 
-What:	KVM paravirt mmu host support
-When:	January 2011
-Why:	The paravirt mmu host support is slower than non-paravirt mmu, both
-	on newer and older hardware.  It is already not exposed to the guest,
-	and kept only for live migration purposes.
-Who:	Avi Kivity <avi@redhat.com>
-
-----------------------------
-
 What:	iwlwifi 50XX module parameters
 When:	3.0
 Why:	The "..50" modules parameters were used to configure 5000 series and
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index dd51c83..8c9ce69 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -241,13 +241,6 @@ struct kvm_mmu_page {
 	struct rcu_head rcu;
 };
 
-struct kvm_pv_mmu_op_buffer {
-	void *ptr;
-	unsigned len;
-	unsigned processed;
-	char buf[512] __aligned(sizeof(long));
-};
-
 struct kvm_pio_request {
 	unsigned long count;
 	int in;
@@ -343,10 +336,6 @@ struct kvm_vcpu_arch {
 	 */
 	struct kvm_mmu *walk_mmu;
 
-	/* only needed in kvm_pv_mmu_op() path, but it's hot so
-	 * put it here to avoid allocation */
-	struct kvm_pv_mmu_op_buffer mmu_op_buffer;
-
 	struct kvm_mmu_memory_cache mmu_pte_list_desc_cache;
 	struct kvm_mmu_memory_cache mmu_page_cache;
 	struct kvm_mmu_memory_cache mmu_page_header_cache;
@@ -666,8 +655,6 @@ int load_pdptrs(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned long cr3);
 
 int emulator_write_phys(struct kvm_vcpu *vcpu, gpa_t gpa,
 			  const void *val, int bytes);
-int kvm_pv_mmu_op(struct kvm_vcpu *vcpu, unsigned long bytes,
-		  gpa_t addr, unsigned long *ret);
 u8 kvm_get_guest_memory_type(struct kvm_vcpu *vcpu, gfn_t gfn);
 
 extern bool tdp_enabled;
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 8e8da79..0a45bc1 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -2005,20 +2005,6 @@ static int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn)
 	return r;
 }
 
-static void mmu_unshadow(struct kvm *kvm, gfn_t gfn)
-{
-	struct kvm_mmu_page *sp;
-	struct hlist_node *node;
-	LIST_HEAD(invalid_list);
-
-	for_each_gfn_indirect_valid_sp(kvm, sp, gfn, node) {
-		pgprintk("%s: zap %llx %x\n",
-			 __func__, gfn, sp->role.word);
-		kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list);
-	}
-	kvm_mmu_commit_zap_page(kvm, &invalid_list);
-}
-
 static void page_header_update_slot(struct kvm *kvm, void *pte, gfn_t gfn)
 {
 	int slot = memslot_id(kvm, gfn);
@@ -3958,127 +3944,6 @@ unsigned int kvm_mmu_calculate_mmu_pages(struct kvm *kvm)
 	return nr_mmu_pages;
 }
 
-static void *pv_mmu_peek_buffer(struct kvm_pv_mmu_op_buffer *buffer,
-				unsigned len)
-{
-	if (len > buffer->len)
-		return NULL;
-	return buffer->ptr;
-}
-
-static void *pv_mmu_read_buffer(struct kvm_pv_mmu_op_buffer *buffer,
-				unsigned len)
-{
-	void *ret;
-
-	ret = pv_mmu_peek_buffer(buffer, len);
-	if (!ret)
-		return ret;
-	buffer->ptr += len;
-	buffer->len -= len;
-	buffer->processed += len;
-	return ret;
-}
-
-static int kvm_pv_mmu_write(struct kvm_vcpu *vcpu,
-			     gpa_t addr, gpa_t value)
-{
-	int bytes = 8;
-	int r;
-
-	if (!is_long_mode(vcpu) && !is_pae(vcpu))
-		bytes = 4;
-
-	r = mmu_topup_memory_caches(vcpu);
-	if (r)
-		return r;
-
-	if (!emulator_write_phys(vcpu, addr, &value, bytes))
-		return -EFAULT;
-
-	return 1;
-}
-
-static int kvm_pv_mmu_flush_tlb(struct kvm_vcpu *vcpu)
-{
-	(void)kvm_set_cr3(vcpu, kvm_read_cr3(vcpu));
-	return 1;
-}
-
-static int kvm_pv_mmu_release_pt(struct kvm_vcpu *vcpu, gpa_t addr)
-{
-	spin_lock(&vcpu->kvm->mmu_lock);
-	mmu_unshadow(vcpu->kvm, addr >> PAGE_SHIFT);
-	spin_unlock(&vcpu->kvm->mmu_lock);
-	return 1;
-}
-
-static int kvm_pv_mmu_op_one(struct kvm_vcpu *vcpu,
-			     struct kvm_pv_mmu_op_buffer *buffer)
-{
-	struct kvm_mmu_op_header *header;
-
-	header = pv_mmu_peek_buffer(buffer, sizeof *header);
-	if (!header)
-		return 0;
-	switch (header->op) {
-	case KVM_MMU_OP_WRITE_PTE: {
-		struct kvm_mmu_op_write_pte *wpte;
-
-		wpte = pv_mmu_read_buffer(buffer, sizeof *wpte);
-		if (!wpte)
-			return 0;
-		return kvm_pv_mmu_write(vcpu, wpte->pte_phys,
-					wpte->pte_val);
-	}
-	case KVM_MMU_OP_FLUSH_TLB: {
-		struct kvm_mmu_op_flush_tlb *ftlb;
-
-		ftlb = pv_mmu_read_buffer(buffer, sizeof *ftlb);
-		if (!ftlb)
-			return 0;
-		return kvm_pv_mmu_flush_tlb(vcpu);
-	}
-	case KVM_MMU_OP_RELEASE_PT: {
-		struct kvm_mmu_op_release_pt *rpt;
-
-		rpt = pv_mmu_read_buffer(buffer, sizeof *rpt);
-		if (!rpt)
-			return 0;
-		return kvm_pv_mmu_release_pt(vcpu, rpt->pt_phys);
-	}
-	default: return 0;
-	}
-}
-
-int kvm_pv_mmu_op(struct kvm_vcpu *vcpu, unsigned long bytes,
-		  gpa_t addr, unsigned long *ret)
-{
-	int r;
-	struct kvm_pv_mmu_op_buffer *buffer = &vcpu->arch.mmu_op_buffer;
-
-	buffer->ptr = buffer->buf;
-	buffer->len = min_t(unsigned long, bytes, sizeof buffer->buf);
-	buffer->processed = 0;
-
-	r = kvm_read_guest(vcpu->kvm, addr, buffer->buf, buffer->len);
-	if (r)
-		goto out;
-
-	while (buffer->len) {
-		r = kvm_pv_mmu_op_one(vcpu, buffer);
-		if (r < 0)
-			goto out;
-		if (r == 0)
-			break;
-	}
-
-	r = 1;
-out:
-	*ret = buffer->processed;
-	return r;
-}
-
 int kvm_mmu_get_spte_hierarchy(struct kvm_vcpu *vcpu, u64 addr, u64 sptes[4])
 {
 	struct kvm_shadow_walk_iterator iterator;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 84a28ea..10b74f7 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -5160,15 +5160,6 @@ int kvm_emulate_halt(struct kvm_vcpu *vcpu)
 }
 EXPORT_SYMBOL_GPL(kvm_emulate_halt);
 
-static inline gpa_t hc_gpa(struct kvm_vcpu *vcpu, unsigned long a0,
-			   unsigned long a1)
-{
-	if (is_long_mode(vcpu))
-		return a0;
-	else
-		return a0 | ((gpa_t)a1 << 32);
-}
-
 int kvm_hv_hypercall(struct kvm_vcpu *vcpu)
 {
 	u64 param, ingpa, outgpa, ret;
@@ -5264,9 +5255,6 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
 	case KVM_HC_VAPIC_POLL_IRQ:
 		ret = 0;
 		break;
-	case KVM_HC_MMU_OP:
-		r = kvm_pv_mmu_op(vcpu, a0, hc_gpa(vcpu, a1, a2), &ret);
-		break;
 	default:
 		ret = -KVM_ENOSYS;
 		break;
-- 
1.7.1

Re: [PATCH RFC 0/2] KVM: remove host and guest pv mmu support

[Marcelo Tosatti]

On Thu, Oct 20, 2011 at 05:44:23PM -0700, Chris Wright wrote:
> This feature hasn't been in use for some years now.  The host side bits
> are deprecated for almost a year.  The guest side would only get used
> on old hosts, and it's slower than shadow or hw assisted paging.
> 
> Time to remove it.
> 
>  Documentation/feature-removal-schedule.txt |    9 --
>  arch/x86/include/asm/kvm_host.h            |   13 --
>  arch/x86/kernel/kvm.c                      |  181 ----------------------------
>  arch/x86/kvm/mmu.c                         |  135 ---------------------
>  arch/x86/kvm/x86.c                         |   12 --
>  5 files changed, 0 insertions(+), 350 deletions(-)

Looks good to me. 

Re: [PATCH RFC 0/2] KVM: remove host and guest pv mmu support

[Marcelo Tosatti]

On Thu, Oct 20, 2011 at 05:44:23PM -0700, Chris Wright wrote:
> This feature hasn't been in use for some years now.  The host side bits
> are deprecated for almost a year.  The guest side would only get used
> on old hosts, and it's slower than shadow or hw assisted paging.
> 
> Time to remove it.

Please rebase.

[PATCH v2 0/2] KVM: remove host and guest pv mmu support

[Chris Wright]

This feature hasn't been in use for some years now.  The host side bits
are deprecated for almost a year.  The guest side would only get used
on old hosts, and it's slower than shadow or hw assisted paging.

Time to remove it.

Chris Wright (2):
      KVM Guest: remove KVM guest pv mmu support
      KVM: remove KVM host pv mmu support

 Documentation/feature-removal-schedule.txt |    9 --
 arch/x86/include/asm/kvm_host.h            |   13 --
 arch/x86/kernel/kvm.c                      |  181 ----------------------------
 arch/x86/kvm/mmu.c                         |  135 ---------------------
 arch/x86/kvm/x86.c                         |   12 --
 5 files changed, 0 insertions(+), 350 deletions(-)


Changes since RFC:

- v2 rebase to b796a09c

thanks,
-chris

[PATCH v2 1/2] KVM Guest: remove KVM guest pv mmu support

[Chris Wright]

This has not been used for some years now.  It's time to remove it.

Signed-off-by: Chris Wright <chrisw@redhat.com>
---

- v2 rebase to b796a09c

 arch/x86/kernel/kvm.c |  181 -------------------------------------------------
 1 files changed, 0 insertions(+), 181 deletions(-)

diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index a9c2116..f0c6fd6 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -39,8 +39,6 @@
 #include <asm/desc.h>
 #include <asm/tlbflush.h>
 
-#define MMU_QUEUE_SIZE 1024
-
 static int kvmapf = 1;
 
 static int parse_no_kvmapf(char *arg)
@@ -60,21 +58,10 @@ static int parse_no_stealacc(char *arg)
 
 early_param("no-steal-acc", parse_no_stealacc);
 
-struct kvm_para_state {
-	u8 mmu_queue[MMU_QUEUE_SIZE];
-	int mmu_queue_len;
-};
-
-static DEFINE_PER_CPU(struct kvm_para_state, para_state);
 static DEFINE_PER_CPU(struct kvm_vcpu_pv_apf_data, apf_reason) __aligned(64);
 static DEFINE_PER_CPU(struct kvm_steal_time, steal_time) __aligned(64);
 static int has_steal_clock = 0;
 
-static struct kvm_para_state *kvm_para_state(void)
-{
-	return &per_cpu(para_state, raw_smp_processor_id());
-}
-
 /*
  * No need for any "IO delay" on KVM
  */
@@ -271,151 +258,6 @@ do_async_page_fault(struct pt_regs *regs, unsigned long error_code)
 	}
 }
 
-static void kvm_mmu_op(void *buffer, unsigned len)
-{
-	int r;
-	unsigned long a1, a2;
-
-	do {
-		a1 = __pa(buffer);
-		a2 = 0;   /* on i386 __pa() always returns <4G */
-		r = kvm_hypercall3(KVM_HC_MMU_OP, len, a1, a2);
-		buffer += r;
-		len -= r;
-	} while (len);
-}
-
-static void mmu_queue_flush(struct kvm_para_state *state)
-{
-	if (state->mmu_queue_len) {
-		kvm_mmu_op(state->mmu_queue, state->mmu_queue_len);
-		state->mmu_queue_len = 0;
-	}
-}
-
-static void kvm_deferred_mmu_op(void *buffer, int len)
-{
-	struct kvm_para_state *state = kvm_para_state();
-
-	if (paravirt_get_lazy_mode() != PARAVIRT_LAZY_MMU) {
-		kvm_mmu_op(buffer, len);
-		return;
-	}
-	if (state->mmu_queue_len + len > sizeof state->mmu_queue)
-		mmu_queue_flush(state);
-	memcpy(state->mmu_queue + state->mmu_queue_len, buffer, len);
-	state->mmu_queue_len += len;
-}
-
-static void kvm_mmu_write(void *dest, u64 val)
-{
-	__u64 pte_phys;
-	struct kvm_mmu_op_write_pte wpte;
-
-#ifdef CONFIG_HIGHPTE
-	struct page *page;
-	unsigned long dst = (unsigned long) dest;
-
-	page = kmap_atomic_to_page(dest);
-	pte_phys = page_to_pfn(page);
-	pte_phys <<= PAGE_SHIFT;
-	pte_phys += (dst & ~(PAGE_MASK));
-#else
-	pte_phys = (unsigned long)__pa(dest);
-#endif
-	wpte.header.op = KVM_MMU_OP_WRITE_PTE;
-	wpte.pte_val = val;
-	wpte.pte_phys = pte_phys;
-
-	kvm_deferred_mmu_op(&wpte, sizeof wpte);
-}
-
-/*
- * We only need to hook operations that are MMU writes.  We hook these so that
- * we can use lazy MMU mode to batch these operations.  We could probably
- * improve the performance of the host code if we used some of the information
- * here to simplify processing of batched writes.
- */
-static void kvm_set_pte(pte_t *ptep, pte_t pte)
-{
-	kvm_mmu_write(ptep, pte_val(pte));
-}
-
-static void kvm_set_pte_at(struct mm_struct *mm, unsigned long addr,
-			   pte_t *ptep, pte_t pte)
-{
-	kvm_mmu_write(ptep, pte_val(pte));
-}
-
-static void kvm_set_pmd(pmd_t *pmdp, pmd_t pmd)
-{
-	kvm_mmu_write(pmdp, pmd_val(pmd));
-}
-
-#if PAGETABLE_LEVELS >= 3
-#ifdef CONFIG_X86_PAE
-static void kvm_set_pte_atomic(pte_t *ptep, pte_t pte)
-{
-	kvm_mmu_write(ptep, pte_val(pte));
-}
-
-static void kvm_pte_clear(struct mm_struct *mm,
-			  unsigned long addr, pte_t *ptep)
-{
-	kvm_mmu_write(ptep, 0);
-}
-
-static void kvm_pmd_clear(pmd_t *pmdp)
-{
-	kvm_mmu_write(pmdp, 0);
-}
-#endif
-
-static void kvm_set_pud(pud_t *pudp, pud_t pud)
-{
-	kvm_mmu_write(pudp, pud_val(pud));
-}
-
-#if PAGETABLE_LEVELS == 4
-static void kvm_set_pgd(pgd_t *pgdp, pgd_t pgd)
-{
-	kvm_mmu_write(pgdp, pgd_val(pgd));
-}
-#endif
-#endif /* PAGETABLE_LEVELS >= 3 */
-
-static void kvm_flush_tlb(void)
-{
-	struct kvm_mmu_op_flush_tlb ftlb = {
-		.header.op = KVM_MMU_OP_FLUSH_TLB,
-	};
-
-	kvm_deferred_mmu_op(&ftlb, sizeof ftlb);
-}
-
-static void kvm_release_pt(unsigned long pfn)
-{
-	struct kvm_mmu_op_release_pt rpt = {
-		.header.op = KVM_MMU_OP_RELEASE_PT,
-		.pt_phys = (u64)pfn << PAGE_SHIFT,
-	};
-
-	kvm_mmu_op(&rpt, sizeof rpt);
-}
-
-static void kvm_enter_lazy_mmu(void)
-{
-	paravirt_enter_lazy_mmu();
-}
-
-static void kvm_leave_lazy_mmu(void)
-{
-	struct kvm_para_state *state = kvm_para_state();
-
-	mmu_queue_flush(state);
-	paravirt_leave_lazy_mmu();
-}
-
 static void __init paravirt_ops_setup(void)
 {
 	pv_info.name = "KVM";
@@ -424,29 +266,6 @@ static void __init paravirt_ops_setup(void)
 	if (kvm_para_has_feature(KVM_FEATURE_NOP_IO_DELAY))
 		pv_cpu_ops.io_delay = kvm_io_delay;
 
-	if (kvm_para_has_feature(KVM_FEATURE_MMU_OP)) {
-		pv_mmu_ops.set_pte = kvm_set_pte;
-		pv_mmu_ops.set_pte_at = kvm_set_pte_at;
-		pv_mmu_ops.set_pmd = kvm_set_pmd;
-#if PAGETABLE_LEVELS >= 3
-#ifdef CONFIG_X86_PAE
-		pv_mmu_ops.set_pte_atomic = kvm_set_pte_atomic;
-		pv_mmu_ops.pte_clear = kvm_pte_clear;
-		pv_mmu_ops.pmd_clear = kvm_pmd_clear;
-#endif
-		pv_mmu_ops.set_pud = kvm_set_pud;
-#if PAGETABLE_LEVELS == 4
-		pv_mmu_ops.set_pgd = kvm_set_pgd;
-#endif
-#endif
-		pv_mmu_ops.flush_tlb_user = kvm_flush_tlb;
-		pv_mmu_ops.release_pte = kvm_release_pt;
-		pv_mmu_ops.release_pmd = kvm_release_pt;
-		pv_mmu_ops.release_pud = kvm_release_pt;
-
-		pv_mmu_ops.lazy_mode.enter = kvm_enter_lazy_mmu;
-		pv_mmu_ops.lazy_mode.leave = kvm_leave_lazy_mmu;
-	}
 #ifdef CONFIG_X86_IO_APIC
 	no_timer_check = 1;
 #endif

[PATCH v2 2/2] KVM: remove KVM host pv mmu support

[Chris Wright]

The host side pv mmu support has been marked for feature removal in
January 2011.  It's not in use, is slower than shadow or hardware
assisted paging, and a maintenance burden.  It's November 2011, time to
remove it.

Signed-off-by: Chris Wright <chrisw@redhat.com>
---

- v2 rebase to b796a09c

 Documentation/feature-removal-schedule.txt |    9 --
 arch/x86/include/asm/kvm_host.h            |   13 ---
 arch/x86/kvm/mmu.c                         |  135 ----------------------------
 arch/x86/kvm/x86.c                         |   12 ---
 4 files changed, 0 insertions(+), 169 deletions(-)

diff --git a/Documentation/feature-removal-schedule.txt b/Documentation/feature-removal-schedule.txt
index d5ac362..877f897 100644
--- a/Documentation/feature-removal-schedule.txt
+++ b/Documentation/feature-removal-schedule.txt
@@ -397,15 +397,6 @@ Who: 	anybody or Florian Mickler <florian@mickler.org>
 
 ----------------------------
 
-What:	KVM paravirt mmu host support
-When:	January 2011
-Why:	The paravirt mmu host support is slower than non-paravirt mmu, both
-	on newer and older hardware.  It is already not exposed to the guest,
-	and kept only for live migration purposes.
-Who:	Avi Kivity <avi@redhat.com>
-
-----------------------------
-
 What:	iwlwifi 50XX module parameters
 When:	3.0
 Why:	The "..50" modules parameters were used to configure 5000 series and
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index c1f19de..6d83264 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -244,13 +244,6 @@ struct kvm_mmu_page {
 	struct rcu_head rcu;
 };
 
-struct kvm_pv_mmu_op_buffer {
-	void *ptr;
-	unsigned len;
-	unsigned processed;
-	char buf[512] __aligned(sizeof(long));
-};
-
 struct kvm_pio_request {
 	unsigned long count;
 	int in;
@@ -347,10 +340,6 @@ struct kvm_vcpu_arch {
 	 */
 	struct kvm_mmu *walk_mmu;
 
-	/* only needed in kvm_pv_mmu_op() path, but it's hot so
-	 * put it here to avoid allocation */
-	struct kvm_pv_mmu_op_buffer mmu_op_buffer;
-
 	struct kvm_mmu_memory_cache mmu_pte_list_desc_cache;
 	struct kvm_mmu_memory_cache mmu_page_cache;
 	struct kvm_mmu_memory_cache mmu_page_header_cache;
@@ -667,8 +656,6 @@ int load_pdptrs(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned long cr3);
 
 int emulator_write_phys(struct kvm_vcpu *vcpu, gpa_t gpa,
 			  const void *val, int bytes);
-int kvm_pv_mmu_op(struct kvm_vcpu *vcpu, unsigned long bytes,
-		  gpa_t addr, unsigned long *ret);
 u8 kvm_get_guest_memory_type(struct kvm_vcpu *vcpu, gfn_t gfn);
 
 extern bool tdp_enabled;
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index e9534ce..a9b3a32 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -2028,20 +2028,6 @@ int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn)
 }
 EXPORT_SYMBOL_GPL(kvm_mmu_unprotect_page);
 
-static void mmu_unshadow(struct kvm *kvm, gfn_t gfn)
-{
-	struct kvm_mmu_page *sp;
-	struct hlist_node *node;
-	LIST_HEAD(invalid_list);
-
-	for_each_gfn_indirect_valid_sp(kvm, sp, gfn, node) {
-		pgprintk("%s: zap %llx %x\n",
-			 __func__, gfn, sp->role.word);
-		kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list);
-	}
-	kvm_mmu_commit_zap_page(kvm, &invalid_list);
-}
-
 static void page_header_update_slot(struct kvm *kvm, void *pte, gfn_t gfn)
 {
 	int slot = memslot_id(kvm, gfn);
@@ -4004,127 +3990,6 @@ unsigned int kvm_mmu_calculate_mmu_pages(struct kvm *kvm)
 	return nr_mmu_pages;
 }
 
-static void *pv_mmu_peek_buffer(struct kvm_pv_mmu_op_buffer *buffer,
-				unsigned len)
-{
-	if (len > buffer->len)
-		return NULL;
-	return buffer->ptr;
-}
-
-static void *pv_mmu_read_buffer(struct kvm_pv_mmu_op_buffer *buffer,
-				unsigned len)
-{
-	void *ret;
-
-	ret = pv_mmu_peek_buffer(buffer, len);
-	if (!ret)
-		return ret;
-	buffer->ptr += len;
-	buffer->len -= len;
-	buffer->processed += len;
-	return ret;
-}
-
-static int kvm_pv_mmu_write(struct kvm_vcpu *vcpu,
-			     gpa_t addr, gpa_t value)
-{
-	int bytes = 8;
-	int r;
-
-	if (!is_long_mode(vcpu) && !is_pae(vcpu))
-		bytes = 4;
-
-	r = mmu_topup_memory_caches(vcpu);
-	if (r)
-		return r;
-
-	if (!emulator_write_phys(vcpu, addr, &value, bytes))
-		return -EFAULT;
-
-	return 1;
-}
-
-static int kvm_pv_mmu_flush_tlb(struct kvm_vcpu *vcpu)
-{
-	(void)kvm_set_cr3(vcpu, kvm_read_cr3(vcpu));
-	return 1;
-}
-
-static int kvm_pv_mmu_release_pt(struct kvm_vcpu *vcpu, gpa_t addr)
-{
-	spin_lock(&vcpu->kvm->mmu_lock);
-	mmu_unshadow(vcpu->kvm, addr >> PAGE_SHIFT);
-	spin_unlock(&vcpu->kvm->mmu_lock);
-	return 1;
-}
-
-static int kvm_pv_mmu_op_one(struct kvm_vcpu *vcpu,
-			     struct kvm_pv_mmu_op_buffer *buffer)
-{
-	struct kvm_mmu_op_header *header;
-
-	header = pv_mmu_peek_buffer(buffer, sizeof *header);
-	if (!header)
-		return 0;
-	switch (header->op) {
-	case KVM_MMU_OP_WRITE_PTE: {
-		struct kvm_mmu_op_write_pte *wpte;
-
-		wpte = pv_mmu_read_buffer(buffer, sizeof *wpte);
-		if (!wpte)
-			return 0;
-		return kvm_pv_mmu_write(vcpu, wpte->pte_phys,
-					wpte->pte_val);
-	}
-	case KVM_MMU_OP_FLUSH_TLB: {
-		struct kvm_mmu_op_flush_tlb *ftlb;
-
-		ftlb = pv_mmu_read_buffer(buffer, sizeof *ftlb);
-		if (!ftlb)
-			return 0;
-		return kvm_pv_mmu_flush_tlb(vcpu);
-	}
-	case KVM_MMU_OP_RELEASE_PT: {
-		struct kvm_mmu_op_release_pt *rpt;
-
-		rpt = pv_mmu_read_buffer(buffer, sizeof *rpt);
-		if (!rpt)
-			return 0;
-		return kvm_pv_mmu_release_pt(vcpu, rpt->pt_phys);
-	}
-	default: return 0;
-	}
-}
-
-int kvm_pv_mmu_op(struct kvm_vcpu *vcpu, unsigned long bytes,
-		  gpa_t addr, unsigned long *ret)
-{
-	int r;
-	struct kvm_pv_mmu_op_buffer *buffer = &vcpu->arch.mmu_op_buffer;
-
-	buffer->ptr = buffer->buf;
-	buffer->len = min_t(unsigned long, bytes, sizeof buffer->buf);
-	buffer->processed = 0;
-
-	r = kvm_read_guest(vcpu->kvm, addr, buffer->buf, buffer->len);
-	if (r)
-		goto out;
-
-	while (buffer->len) {
-		r = kvm_pv_mmu_op_one(vcpu, buffer);
-		if (r < 0)
-			goto out;
-		if (r == 0)
-			break;
-	}
-
-	r = 1;
-out:
-	*ret = buffer->processed;
-	return r;
-}
-
 int kvm_mmu_get_spte_hierarchy(struct kvm_vcpu *vcpu, u64 addr, u64 sptes[4])
 {
 	struct kvm_shadow_walk_iterator iterator;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 2b1c526..3fb9757 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -5273,15 +5273,6 @@ int kvm_emulate_halt(struct kvm_vcpu *vcpu)
 }
 EXPORT_SYMBOL_GPL(kvm_emulate_halt);
 
-static inline gpa_t hc_gpa(struct kvm_vcpu *vcpu, unsigned long a0,
-			   unsigned long a1)
-{
-	if (is_long_mode(vcpu))
-		return a0;
-	else
-		return a0 | ((gpa_t)a1 << 32);
-}
-
 int kvm_hv_hypercall(struct kvm_vcpu *vcpu)
 {
 	u64 param, ingpa, outgpa, ret;
@@ -5377,9 +5368,6 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
 	case KVM_HC_VAPIC_POLL_IRQ:
 		ret = 0;
 		break;
-	case KVM_HC_MMU_OP:
-		r = kvm_pv_mmu_op(vcpu, a0, hc_gpa(vcpu, a1, a2), &ret);
-		break;
 	default:
 		ret = -KVM_ENOSYS;
 		break;

Re: [PATCH v2 0/2] KVM: remove host and guest pv mmu support

[Avi Kivity]

On 11/02/2011 02:25 AM, Chris Wright wrote:
> This feature hasn't been in use for some years now.  The host side bits
> are deprecated for almost a year.  The guest side would only get used
> on old hosts, and it's slower than shadow or hw assisted paging.
>
> Time to remove it.
>
> Chris Wright (2):
>       KVM Guest: remove KVM guest pv mmu support
>       KVM: remove KVM host pv mmu support
>
>  Documentation/feature-removal-schedule.txt |    9 --
>  arch/x86/include/asm/kvm_host.h            |   13 --
>  arch/x86/kernel/kvm.c                      |  181 ----------------------------
>  arch/x86/kvm/mmu.c                         |  135 ---------------------
>  arch/x86/kvm/x86.c                         |   12 --
>  5 files changed, 0 insertions(+), 350 deletions(-)
>
>

Thanks, applied.

-- 
error compiling committee.c: too many arguments to function