It is unnecessary to keep shadow tlb.
first, shadow tlb keep fixed value in shadow, which make things unflexible.
second, remove shadow tlb can save a lot memory.
This patch remove shadow tlb and caculate the shadow tlb entry value
before we write it to hardware.
Also we use new struct tlbe_ref to trace the relation
between guest tlb entry and page.
Signed-off-by: Liu Yu <yu.liu@xxxxxxxxxxxxx>
---
arch/powerpc/include/asm/kvm_e500.h | 7 +-
arch/powerpc/kvm/e500_tlb.c | 287 +++++++++++++----------------------
2 files changed, 108 insertions(+), 186 deletions(-)
diff --git a/arch/powerpc/include/asm/kvm_e500.h b/arch/powerpc/include/asm/kvm_e500.h
index 7fea26f..cb785f9 100644
--- a/arch/powerpc/include/asm/kvm_e500.h
+++ b/arch/powerpc/include/asm/kvm_e500.h
@@ -29,13 +29,18 @@ struct tlbe{
u32 mas7;
};
+struct tlbe_ref {
+ struct page *page;
+ struct tlbe *gtlbe;
+};
+
struct kvmppc_vcpu_e500 {
/* Unmodified copy of the guest's TLB. */
struct tlbe *guest_tlb[E500_TLB_NUM];
/* TLB that's actually used when the guest is running. */
struct tlbe *shadow_tlb[E500_TLB_NUM];
/* Pages which are referenced in the shadow TLB. */
- struct page **shadow_pages[E500_TLB_NUM];
+ struct tlbe_ref *shadow_refs[E500_TLB_NUM];
unsigned int guest_tlb_size[E500_TLB_NUM];
unsigned int shadow_tlb_size[E500_TLB_NUM];
diff --git a/arch/powerpc/kvm/e500_tlb.c b/arch/powerpc/kvm/e500_tlb.c
index f11ca0f..0b657af 100644
--- a/arch/powerpc/kvm/e500_tlb.c
+++ b/arch/powerpc/kvm/e500_tlb.c
@@ -1,5 +1,5 @@
/*
- * Copyright (C) 2008 Freescale Semiconductor, Inc. All rights reserved.
+ * Copyright (C) 2008, 2010 Freescale Semiconductor, Inc. All rights reserved.
*
* Author: Yu Liu, yu.liu@xxxxxxxxxxxxx
*
@@ -48,17 +48,6 @@ void kvmppc_dump_tlbs(struct kvm_vcpu *vcpu)
tlbe->mas3, tlbe->mas7);
}
}
-
- for (tlbsel = 0; tlbsel < 2; tlbsel++) {
- printk("Shadow TLB%d:\n", tlbsel);
- for (i = 0; i < vcpu_e500->shadow_tlb_size[tlbsel]; i++) {
- tlbe = &vcpu_e500->shadow_tlb[tlbsel][i];
- if (tlbe->mas1 & MAS1_VALID)
- printk(" S[%d][%3d] | %08X | %08X | %08X | %08X |\n",
- tlbsel, i, tlbe->mas1, tlbe->mas2,
- tlbe->mas3, tlbe->mas7);
- }
- }
}
static inline unsigned int tlb0_get_next_victim(
@@ -121,10 +110,8 @@ static inline void __write_host_tlbe(struct tlbe *stlbe)
}
static inline void write_host_tlbe(struct kvmppc_vcpu_e500 *vcpu_e500,
- int tlbsel, int esel)
+ int tlbsel, int esel, struct tlbe *stlbe)
{
- struct tlbe *stlbe = &vcpu_e500->shadow_tlb[tlbsel][esel];
-
local_irq_disable();
if (tlbsel == 0) {
__write_host_tlbe(stlbe);
@@ -139,28 +126,12 @@ static inline void write_host_tlbe(struct kvmppc_vcpu_e500 *vcpu_e500,
mtspr(SPRN_MAS0, mas0);
}
local_irq_enable();
+ trace_kvm_stlb_write(index_of(tlbsel, esel), stlbe->mas1, stlbe->mas2,
+ stlbe->mas3, stlbe->mas7);
}
void kvmppc_e500_tlb_load(struct kvm_vcpu *vcpu, int cpu)
{
- struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
- int i;
- unsigned register mas0;
-
- /* Load all valid TLB1 entries to reduce guest tlb miss fault */
- local_irq_disable();
- mas0 = mfspr(SPRN_MAS0);
- for (i = 0; i < tlb1_max_shadow_size(); i++) {
- struct tlbe *stlbe = &vcpu_e500->shadow_tlb[1][i];
-
- if (get_tlb_v(stlbe)) {
- mtspr(SPRN_MAS0, MAS0_TLBSEL(1)
- | MAS0_ESEL(to_htlb1_esel(i)));
- __write_host_tlbe(stlbe);
- }
- }
- mtspr(SPRN_MAS0, mas0);
- local_irq_enable();
}
void kvmppc_e500_tlb_put(struct kvm_vcpu *vcpu)
@@ -202,16 +173,19 @@ static int kvmppc_e500_tlb_index(struct kvmppc_vcpu_e500 *vcpu_e500,
}
static void kvmppc_e500_shadow_release(struct kvmppc_vcpu_e500 *vcpu_e500,
- int tlbsel, int esel)
+ int stlbsel, int sesel)
{
- struct tlbe *stlbe = &vcpu_e500->shadow_tlb[tlbsel][esel];
- struct page *page = vcpu_e500->shadow_pages[tlbsel][esel];
+ struct tlbe_ref *ref;
+ struct page *page;
+
+ ref = &vcpu_e500->shadow_refs[stlbsel][sesel];
+ page = ref->page;
if (page) {
- vcpu_e500->shadow_pages[tlbsel][esel] = NULL;
+ ref->page = NULL;
- if (get_tlb_v(stlbe)) {
- if (tlbe_is_writable(stlbe))
+ if (get_tlb_v(ref->gtlbe)) {
+ if (tlbe_is_writable(ref->gtlbe))
kvm_release_page_dirty(page);
else
kvm_release_page_clean(page);
@@ -219,46 +193,19 @@ static void kvmppc_e500_shadow_release(struct kvmppc_vcpu_e500 *vcpu_e500,
}
}
-static void kvmppc_e500_stlbe_invalidate(struct kvmppc_vcpu_e500 *vcpu_e500,
- int tlbsel, int esel)
-{
- struct tlbe *stlbe = &vcpu_e500->shadow_tlb[tlbsel][esel];
-
- kvmppc_e500_shadow_release(vcpu_e500, tlbsel, esel);
- stlbe->mas1 = 0;
- /* XXX doesn't compile */
-#if 0
- trace_kvm_stlb_inval(index_of(tlbsel, esel), stlbe->mas1, stlbe->mas2,
- stlbe->mas3, stlbe->mas7);
-#endif
-}
-
static void kvmppc_e500_tlb1_invalidate(struct kvmppc_vcpu_e500 *vcpu_e500,
- gva_t eaddr, gva_t eend, u32 tid)
+ int esel)
{
- unsigned int pid = tid & 0xff;
+ struct tlbe stlbe;
unsigned int i;
- /* XXX Replace loop with fancy data structures. */
- for (i = 0; i < vcpu_e500->guest_tlb_size[1]; i++) {
- struct tlbe *stlbe = &vcpu_e500->shadow_tlb[1][i];
- unsigned int tid;
-
- if (!get_tlb_v(stlbe))
- continue;
-
- if (eend < get_tlb_eaddr(stlbe))
- continue;
-
- if (eaddr > get_tlb_end(stlbe))
- continue;
-
- tid = get_tlb_tid(stlbe);
- if (tid && (tid != pid))
- continue;
+ stlbe.mas1 = 0;
+ for (i = 0; i < KVM_E500_TLB1_SIZE; i++) {
+ struct tlbe_ref *ref =
+ &vcpu_e500->shadow_refs[1][i];
- kvmppc_e500_stlbe_invalidate(vcpu_e500, 1, i);
- write_host_tlbe(vcpu_e500, 1, i);
+ if (ref->gtlbe == &vcpu_e500->guest_tlb[1][esel])
+ write_host_tlbe(vcpu_e500, 1, i, &stlbe);
}
}
@@ -289,14 +236,29 @@ static inline void kvmppc_e500_deliver_tlb_miss(struct kvm_vcpu *vcpu,
vcpu_e500->mas7 = 0;
}
+static inline void kvmppc_e500_setup_stlbe(struct kvmppc_vcpu_e500 *vcpu_e500,
+ struct tlbe *gtlbe, struct tlbe_ref *ref,
+ u64 gvaddr, struct tlbe *stlbe)
+{
+ hpa_t hpaddr = page_to_phys(ref->page);
+
+ /* Force TS=1 IPROT=0 TSIZE=4KB for all guest mappings. */
+ stlbe->mas1 = MAS1_TSIZE(BOOK3E_PAGESZ_4K)
+ | MAS1_TID(get_tlb_tid(gtlbe)) | MAS1_TS | MAS1_VALID;
+ stlbe->mas2 = (gvaddr & MAS2_EPN)
+ | e500_shadow_mas2_attrib(gtlbe->mas2,
+ vcpu_e500->vcpu.arch.msr & MSR_PR);
+ stlbe->mas3 = (hpaddr & MAS3_RPN)
+ | e500_shadow_mas3_attrib(gtlbe->mas3,
+ vcpu_e500->vcpu.arch.msr & MSR_PR);
+ stlbe->mas7 = (hpaddr >> 32) & MAS7_RPN;
+}
+
static inline void kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500,
- u64 gvaddr, gfn_t gfn, struct tlbe *gtlbe, int tlbsel, int esel)
+ gfn_t gfn, struct tlbe *gtlbe, int stlbsel, int sesel)
{
struct page *new_page;
- struct tlbe *stlbe;
- hpa_t hpaddr;
-
- stlbe = &vcpu_e500->shadow_tlb[tlbsel][esel];
+ struct tlbe_ref *ref;
/* Get reference to new page. */
new_page = gfn_to_page(vcpu_e500->vcpu.kvm, gfn);
@@ -305,39 +267,24 @@ static inline void kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500,
kvm_release_page_clean(new_page);
return;
}
- hpaddr = page_to_phys(new_page);
/* Drop reference to old page. */
- kvmppc_e500_shadow_release(vcpu_e500, tlbsel, esel);
-
- vcpu_e500->shadow_pages[tlbsel][esel] = new_page;
+ kvmppc_e500_shadow_release(vcpu_e500, stlbsel, sesel);
- /* Force TS=1 IPROT=0 TSIZE=4KB for all guest mappings. */
- stlbe->mas1 = MAS1_TSIZE(BOOK3E_PAGESZ_4K)
- | MAS1_TID(get_tlb_tid(gtlbe)) | MAS1_TS | MAS1_VALID;
- stlbe->mas2 = (gvaddr & MAS2_EPN)
- | e500_shadow_mas2_attrib(gtlbe->mas2,
- vcpu_e500->vcpu.arch.msr & MSR_PR);
- stlbe->mas3 = (hpaddr & MAS3_RPN)
- | e500_shadow_mas3_attrib(gtlbe->mas3,
- vcpu_e500->vcpu.arch.msr & MSR_PR);
- stlbe->mas7 = (hpaddr >> 32) & MAS7_RPN;
-
- trace_kvm_stlb_write(index_of(tlbsel, esel), stlbe->mas1, stlbe->mas2,
- stlbe->mas3, stlbe->mas7);
+ ref = &vcpu_e500->shadow_refs[stlbsel][sesel];
+ ref->page = new_page;
+ ref->gtlbe = gtlbe;
}
/* XXX only map the one-one case, for now use TLB0 */
-static int kvmppc_e500_stlbe_map(struct kvmppc_vcpu_e500 *vcpu_e500,
- int tlbsel, int esel)
+static int kvmppc_e500_tlb0_map(struct kvmppc_vcpu_e500 *vcpu_e500, int esel)
{
struct tlbe *gtlbe;
- gtlbe = &vcpu_e500->guest_tlb[tlbsel][esel];
+ gtlbe = &vcpu_e500->guest_tlb[0][esel];
- kvmppc_e500_shadow_map(vcpu_e500, get_tlb_eaddr(gtlbe),
- get_tlb_raddr(gtlbe) >> PAGE_SHIFT,
- gtlbe, tlbsel, esel);
+ kvmppc_e500_shadow_map(vcpu_e500, get_tlb_raddr(gtlbe) >> PAGE_SHIFT,
+ gtlbe, 0, esel);
return esel;
}
@@ -355,7 +302,7 @@ static int kvmppc_e500_tlb1_map(struct kvmppc_vcpu_e500 *vcpu_e500,
if (unlikely(vcpu_e500->guest_tlb_nv[1] >= tlb1_max_shadow_size()))
vcpu_e500->guest_tlb_nv[1] = 0;
- kvmppc_e500_shadow_map(vcpu_e500, gvaddr, gfn, gtlbe, 1, victim);
+ kvmppc_e500_shadow_map(vcpu_e500, gfn, gtlbe, 1, victim);
return victim;
}
@@ -366,33 +313,19 @@ static int kvmppc_e500_tlb1_map(struct kvmppc_vcpu_e500 *vcpu_e500,
void kvmppc_mmu_priv_switch(struct kvm_vcpu *vcpu, int usermode)
{
if (usermode) {
- struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
- int i;
-
- /* XXX Replace loop with fancy data structures. */
- for (i = 0; i < tlb1_max_shadow_size(); i++)
- kvmppc_e500_stlbe_invalidate(vcpu_e500, 1, i);
-
_tlbil_all();
}
}
-static int kvmppc_e500_gtlbe_invalidate(struct kvmppc_vcpu_e500 *vcpu_e500,
- int tlbsel, int esel)
+static inline int kvmppc_e500_gtlbe_invalidate(
+ struct kvmppc_vcpu_e500 *vcpu_e500,
+ int tlbsel, int esel)
{
struct tlbe *gtlbe = &vcpu_e500->guest_tlb[tlbsel][esel];
if (unlikely(get_tlb_iprot(gtlbe)))
return -1;
- if (tlbsel == 1) {
- kvmppc_e500_tlb1_invalidate(vcpu_e500, get_tlb_eaddr(gtlbe),
- get_tlb_end(gtlbe),
- get_tlb_tid(gtlbe));
- } else {
- kvmppc_e500_stlbe_invalidate(vcpu_e500, tlbsel, esel);
- }
-
gtlbe->mas1 = 0;
return 0;
@@ -515,23 +448,16 @@ int kvmppc_e500_emul_tlbsx(struct kvm_vcpu *vcpu, int rb)
int kvmppc_e500_emul_tlbwe(struct kvm_vcpu *vcpu)
{
struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
- u64 eaddr;
- u64 raddr;
- u32 tid;
struct tlbe *gtlbe;
- int tlbsel, esel, stlbsel, sesel;
+ int tlbsel, esel;
tlbsel = get_tlb_tlbsel(vcpu_e500);
esel = get_tlb_esel(vcpu_e500, tlbsel);
gtlbe = &vcpu_e500->guest_tlb[tlbsel][esel];
- if (get_tlb_v(gtlbe) && tlbsel == 1) {
- eaddr = get_tlb_eaddr(gtlbe);
- tid = get_tlb_tid(gtlbe);
- kvmppc_e500_tlb1_invalidate(vcpu_e500, eaddr,
- get_tlb_end(gtlbe), tid);
- }
+ if (get_tlb_v(gtlbe) && tlbsel == 1)
+ kvmppc_e500_tlb1_invalidate(vcpu_e500, esel);
gtlbe->mas1 = vcpu_e500->mas1;
gtlbe->mas2 = vcpu_e500->mas2;
@@ -543,35 +469,37 @@ int kvmppc_e500_emul_tlbwe(struct kvm_vcpu *vcpu)
/* Invalidate shadow mappings for the about-to-be-clobbered TLBE. */
if (tlbe_is_host_safe(vcpu, gtlbe)) {
+ struct tlbe stlbe;
+ int stlbsel, sesel;
+ struct tlbe_ref *ref;
+ u64 eaddr;
+
switch (tlbsel) {
case 0:
/* TLB0 */
gtlbe->mas1 &= ~MAS1_TSIZE(~0);
gtlbe->mas1 |= MAS1_TSIZE(BOOK3E_PAGESZ_4K);
+ eaddr = get_tlb_eaddr(gtlbe);
stlbsel = 0;
- sesel = kvmppc_e500_stlbe_map(vcpu_e500, 0, esel);
+ sesel = kvmppc_e500_tlb0_map(vcpu_e500, esel);
+
+ ref = &vcpu_e500->shadow_refs[stlbsel][sesel];
+
+ kvmppc_e500_setup_stlbe(vcpu_e500, gtlbe,
+ ref, eaddr, &stlbe);
+ write_host_tlbe(vcpu_e500, stlbsel, sesel, &stlbe);
break;
case 1:
- /* TLB1 */
- eaddr = get_tlb_eaddr(gtlbe);
- raddr = get_tlb_raddr(gtlbe);
-
- /* Create a 4KB mapping on the host.
- * If the guest wanted a large page,
- * only the first 4KB is mapped here and the rest
- * are mapped on the fly. */
- stlbsel = 1;
- sesel = kvmppc_e500_tlb1_map(vcpu_e500, eaddr,
- raddr >> PAGE_SHIFT, gtlbe);
+ /* Large page breaks into 4KB pages.
+ * And all these 4KB pages will be mapped on the fly. */
break;
default:
BUG();
}
- write_host_tlbe(vcpu_e500, stlbsel, sesel);
}
return EMULATE_DONE;
@@ -618,25 +546,20 @@ gpa_t kvmppc_mmu_xlate(struct kvm_vcpu *vcpu, unsigned int index,
void kvmppc_mmu_destroy(struct kvm_vcpu *vcpu)
{
- struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
- int tlbsel, i;
-
- for (tlbsel = 0; tlbsel < 2; tlbsel++)
- for (i = 0; i < vcpu_e500->guest_tlb_size[tlbsel]; i++)
- kvmppc_e500_shadow_release(vcpu_e500, tlbsel, i);
-
- /* discard all guest mapping */
- _tlbil_all();
}
void kvmppc_mmu_map(struct kvm_vcpu *vcpu, u64 eaddr, gpa_t gpaddr,
unsigned int index)
{
struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
+ struct tlbe_ref *ref;
+ struct tlbe *gtlbe, stlbe;
int tlbsel = tlbsel_of(index);
int esel = esel_of(index);
int stlbsel, sesel;
+ gtlbe = &vcpu_e500->guest_tlb[tlbsel][esel];
+
switch (tlbsel) {
case 0:
stlbsel = 0;
@@ -645,8 +568,6 @@ void kvmppc_mmu_map(struct kvm_vcpu *vcpu, u64 eaddr, gpa_t gpaddr,
case 1: {
gfn_t gfn = gpaddr >> PAGE_SHIFT;
- struct tlbe *gtlbe
- = &vcpu_e500->guest_tlb[tlbsel][esel];
stlbsel = 1;
sesel = kvmppc_e500_tlb1_map(vcpu_e500, eaddr, gfn, gtlbe);
@@ -657,7 +578,11 @@ void kvmppc_mmu_map(struct kvm_vcpu *vcpu, u64 eaddr, gpa_t gpaddr,
BUG();
break;
}
- write_host_tlbe(vcpu_e500, stlbsel, sesel);
+
+ ref = &vcpu_e500->shadow_refs[stlbsel][sesel];
+
+ kvmppc_e500_setup_stlbe(vcpu_e500, gtlbe, ref, eaddr, &stlbe);
+ write_host_tlbe(vcpu_e500, stlbsel, sesel, &stlbe);
}
int kvmppc_e500_tlb_search(struct kvm_vcpu *vcpu,
@@ -704,33 +629,21 @@ int kvmppc_e500_tlb_init(struct kvmppc_vcpu_e500 *vcpu_e500)
if (vcpu_e500->guest_tlb[0] == NULL)
goto err_out;
- vcpu_e500->shadow_tlb_size[0] = KVM_E500_TLB0_SIZE;
- vcpu_e500->shadow_tlb[0] =
- kzalloc(sizeof(struct tlbe) * KVM_E500_TLB0_SIZE, GFP_KERNEL);
- if (vcpu_e500->shadow_tlb[0] == NULL)
- goto err_out_guest0;
-
vcpu_e500->guest_tlb_size[1] = KVM_E500_TLB1_SIZE;
vcpu_e500->guest_tlb[1] =
kzalloc(sizeof(struct tlbe) * KVM_E500_TLB1_SIZE, GFP_KERNEL);
if (vcpu_e500->guest_tlb[1] == NULL)
- goto err_out_shadow0;
+ goto err_out_guest0;
- vcpu_e500->shadow_tlb_size[1] = tlb1_entry_num;
- vcpu_e500->shadow_tlb[1] =
- kzalloc(sizeof(struct tlbe) * tlb1_entry_num, GFP_KERNEL);
- if (vcpu_e500->shadow_tlb[1] == NULL)
+ vcpu_e500->shadow_refs[0] = (struct tlbe_ref *)
+ kzalloc(sizeof(struct tlbe_ref) * KVM_E500_TLB0_SIZE, GFP_KERNEL);
+ if (vcpu_e500->shadow_refs[0] == NULL)
goto err_out_guest1;
- vcpu_e500->shadow_pages[0] = (struct page **)
- kzalloc(sizeof(struct page *) * KVM_E500_TLB0_SIZE, GFP_KERNEL);
- if (vcpu_e500->shadow_pages[0] == NULL)
- goto err_out_shadow1;
-
- vcpu_e500->shadow_pages[1] = (struct page **)
- kzalloc(sizeof(struct page *) * tlb1_entry_num, GFP_KERNEL);
- if (vcpu_e500->shadow_pages[1] == NULL)
- goto err_out_page0;
+ vcpu_e500->shadow_refs[1] = (struct tlbe_ref *)
+ kzalloc(sizeof(struct tlbe_ref) * KVM_E500_TLB1_SIZE, GFP_KERNEL);
+ if (vcpu_e500->shadow_refs[1] == NULL)
+ goto err_out_ref0;
/* Init TLB configuration register */
vcpu_e500->tlb0cfg = mfspr(SPRN_TLB0CFG) & ~0xfffUL;
@@ -740,14 +653,10 @@ int kvmppc_e500_tlb_init(struct kvmppc_vcpu_e500 *vcpu_e500)
return 0;
-err_out_page0:
- kfree(vcpu_e500->shadow_pages[0]);
-err_out_shadow1:
- kfree(vcpu_e500->shadow_tlb[1]);
+err_out_ref0:
+ kfree(vcpu_e500->shadow_refs[0]);
err_out_guest1:
kfree(vcpu_e500->guest_tlb[1]);
-err_out_shadow0:
- kfree(vcpu_e500->shadow_tlb[0]);
err_out_guest0:
kfree(vcpu_e500->guest_tlb[0]);
err_out:
@@ -756,10 +665,18 @@ err_out:
void kvmppc_e500_tlb_uninit(struct kvmppc_vcpu_e500 *vcpu_e500)
{
- kfree(vcpu_e500->shadow_pages[1]);
- kfree(vcpu_e500->shadow_pages[0]);
- kfree(vcpu_e500->shadow_tlb[1]);
+ int stlbsel, i;
+
+ /* release all pages */
+ for (stlbsel = 0; stlbsel < 2; stlbsel++)
+ for (i = 0; i < vcpu_e500->guest_tlb_size[stlbsel]; i++)
+ kvmppc_e500_shadow_release(vcpu_e500, stlbsel, i);
+
+ /* discard all guest mapping */
+ _tlbil_all();
+
+ kfree(vcpu_e500->shadow_refs[1]);
+ kfree(vcpu_e500->shadow_refs[0]);
kfree(vcpu_e500->guest_tlb[1]);
- kfree(vcpu_e500->shadow_tlb[0]);
kfree(vcpu_e500->guest_tlb[0]);
}
--
1.6.4
--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
