KVM: PPC: Book3S PR: Use 64k host pages where possible

Currently, PR KVM uses 4k pages for the host-side mappings of guest
memory, regardless of the host page size.  When the host page size is
64kB, we might as well use 64k host page mappings for guest mappings
of 64kB and larger pages and for guest real-mode mappings.  However,
the magic page has to remain a 4k page.

To implement this, we first add another flag bit to the guest VSID
values we use, to indicate that this segment is one where host pages
should be mapped using 64k pages.  For segments with this bit set
we set the bits in the shadow SLB entry to indicate a 64k base page
size.  When faulting in host HPTEs for this segment, we make them
64k HPTEs instead of 4k.  We record the pagesize in struct hpte_cache
for use when invalidating the HPTE.

For now we restrict the segment containing the magic page (if any) to
4k pages.  It should be possible to lift this restriction in future
by ensuring that the magic 4k page is appropriately positioned within
a host 64k page.

Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>

diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h
index 1d4a1202e2d5c7024475820bb1182bcc1071961a..6bf20b4a28413f79343dfeb0eb22d552b12ee36d 100644 (file)
--- a/arch/powerpc/include/asm/kvm_book3s.h
+++ b/arch/powerpc/include/asm/kvm_book3s.h
@@ -66,6 +66,7 @@ struct hpte_cache {
        u64 pfn;
        ulong slot;
        struct kvmppc_pte pte;
+       int pagesize;
 };
 
 struct kvmppc_vcpu_book3s {
@@ -113,8 +114,9 @@ struct kvmppc_vcpu_book3s {
 #define CONTEXT_GUEST          1
 #define CONTEXT_GUEST_END      2
 
-#define VSID_REAL      0x0fffffffffc00000ULL
-#define VSID_BAT       0x0fffffffffb00000ULL
+#define VSID_REAL      0x07ffffffffc00000ULL
+#define VSID_BAT       0x07ffffffffb00000ULL
+#define VSID_64K       0x0800000000000000ULL
 #define VSID_1T                0x1000000000000000ULL
 #define VSID_REAL_DR   0x2000000000000000ULL
 #define VSID_REAL_IR   0x4000000000000000ULL

diff --git a/arch/powerpc/kvm/book3s_32_mmu.c b/arch/powerpc/kvm/book3s_32_mmu.c
index c8cefdd15fd8a2fa03661511e3ca6d2d7c730877..af045533e685da79c3c28d8aa52727288f6a87aa 100644 (file)
--- a/arch/powerpc/kvm/book3s_32_mmu.c
+++ b/arch/powerpc/kvm/book3s_32_mmu.c
@@ -308,6 +308,7 @@ static int kvmppc_mmu_book3s_32_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
        ulong mp_ea = vcpu->arch.magic_page_ea;
 
        pte->eaddr = eaddr;
+       pte->page_size = MMU_PAGE_4K;
 
        /* Magic page override */
        if (unlikely(mp_ea) &&

diff --git a/arch/powerpc/kvm/book3s_64_mmu.c b/arch/powerpc/kvm/book3s_64_mmu.c
index 8277264a0bc5526aa497474b86c5e94dd5c5d826..ffcde01cb995bf47e579244e49af7ea5c8d846a0 100644 (file)
--- a/arch/powerpc/kvm/book3s_64_mmu.c
+++ b/arch/powerpc/kvm/book3s_64_mmu.c
@@ -542,6 +542,16 @@ static void kvmppc_mmu_book3s_64_tlbie(struct kvm_vcpu *vcpu, ulong va,
        kvmppc_mmu_pte_vflush(vcpu, va >> 12, mask);
 }
 
+#ifdef CONFIG_PPC_64K_PAGES
+static int segment_contains_magic_page(struct kvm_vcpu *vcpu, ulong esid)
+{
+       ulong mp_ea = vcpu->arch.magic_page_ea;
+
+       return mp_ea && !(vcpu->arch.shared->msr & MSR_PR) &&
+               (mp_ea >> SID_SHIFT) == esid;
+}
+#endif
+
 static int kvmppc_mmu_book3s_64_esid_to_vsid(struct kvm_vcpu *vcpu, ulong esid,
                                             u64 *vsid)
 {
@@ -549,11 +559,13 @@ static int kvmppc_mmu_book3s_64_esid_to_vsid(struct kvm_vcpu *vcpu, ulong esid,
        struct kvmppc_slb *slb;
        u64 gvsid = esid;
        ulong mp_ea = vcpu->arch.magic_page_ea;
+       int pagesize = MMU_PAGE_64K;
 
        if (vcpu->arch.shared->msr & (MSR_DR|MSR_IR)) {
                slb = kvmppc_mmu_book3s_64_find_slbe(vcpu, ea);
                if (slb) {
                        gvsid = slb->vsid;
+                       pagesize = slb->base_page_size;
                        if (slb->tb) {
                                gvsid <<= SID_SHIFT_1T - SID_SHIFT;
                                gvsid |= esid & ((1ul << (SID_SHIFT_1T - SID_SHIFT)) - 1);
@@ -564,28 +576,41 @@ static int kvmppc_mmu_book3s_64_esid_to_vsid(struct kvm_vcpu *vcpu, ulong esid,
 
        switch (vcpu->arch.shared->msr & (MSR_DR|MSR_IR)) {
        case 0:
-               *vsid = VSID_REAL | esid;
+               gvsid = VSID_REAL | esid;
                break;
        case MSR_IR:
-               *vsid = VSID_REAL_IR | gvsid;
+               gvsid |= VSID_REAL_IR;
                break;
        case MSR_DR:
-               *vsid = VSID_REAL_DR | gvsid;
+               gvsid |= VSID_REAL_DR;
                break;
        case MSR_DR|MSR_IR:
                if (!slb)
                        goto no_slb;
 
-               *vsid = gvsid;
                break;
        default:
                BUG();
                break;
        }
 
+#ifdef CONFIG_PPC_64K_PAGES
+       /*
+        * Mark this as a 64k segment if the host is using
+        * 64k pages, the host MMU supports 64k pages and
+        * the guest segment page size is >= 64k,
+        * but not if this segment contains the magic page.
+        */
+       if (pagesize >= MMU_PAGE_64K &&
+           mmu_psize_defs[MMU_PAGE_64K].shift &&
+           !segment_contains_magic_page(vcpu, esid))
+               gvsid |= VSID_64K;
+#endif
+
        if (vcpu->arch.shared->msr & MSR_PR)
-               *vsid |= VSID_PR;
+               gvsid |= VSID_PR;
 
+       *vsid = gvsid;
        return 0;
 
 no_slb:

diff --git a/arch/powerpc/kvm/book3s_64_mmu_host.c b/arch/powerpc/kvm/book3s_64_mmu_host.c
index e5240524bf6c8aa8bbfc90cdadf5849d587e4d0b..6bda504ceda7cdd1093cc4b229e09c1d3aa6d937 100644 (file)
--- a/arch/powerpc/kvm/book3s_64_mmu_host.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_host.c
@@ -34,7 +34,7 @@
 void kvmppc_mmu_invalidate_pte(struct kvm_vcpu *vcpu, struct hpte_cache *pte)
 {
        ppc_md.hpte_invalidate(pte->slot, pte->host_vpn,
-                              MMU_PAGE_4K, MMU_PAGE_4K, MMU_SEGSIZE_256M,
+                              pte->pagesize, pte->pagesize, MMU_SEGSIZE_256M,
                               false);
 }
 
@@ -90,6 +90,7 @@ int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *orig_pte)
        int attempt = 0;
        struct kvmppc_sid_map *map;
        int r = 0;
+       int hpsize = MMU_PAGE_4K;
 
        /* Get host physical address for gpa */
        hpaddr = kvmppc_gfn_to_pfn(vcpu, orig_pte->raddr >> PAGE_SHIFT);
@@ -99,7 +100,6 @@ int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *orig_pte)
                goto out;
        }
        hpaddr <<= PAGE_SHIFT;
-       hpaddr |= orig_pte->raddr & (~0xfffULL & ~PAGE_MASK);
 
        /* and write the mapping ea -> hpa into the pt */
        vcpu->arch.mmu.esid_to_vsid(vcpu, orig_pte->eaddr >> SID_SHIFT, &vsid);
@@ -117,8 +117,7 @@ int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *orig_pte)
                goto out;
        }
 
-       vsid = map->host_vsid;
-       vpn = hpt_vpn(orig_pte->eaddr, vsid, MMU_SEGSIZE_256M);
+       vpn = hpt_vpn(orig_pte->eaddr, map->host_vsid, MMU_SEGSIZE_256M);
 
        if (!orig_pte->may_write)
                rflags |= HPTE_R_PP;
@@ -130,7 +129,16 @@ int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *orig_pte)
        else
                kvmppc_mmu_flush_icache(hpaddr >> PAGE_SHIFT);
 
-       hash = hpt_hash(vpn, PTE_SIZE, MMU_SEGSIZE_256M);
+       /*
+        * Use 64K pages if possible; otherwise, on 64K page kernels,
+        * we need to transfer 4 more bits from guest real to host real addr.
+        */
+       if (vsid & VSID_64K)
+               hpsize = MMU_PAGE_64K;
+       else
+               hpaddr |= orig_pte->raddr & (~0xfffULL & ~PAGE_MASK);
+
+       hash = hpt_hash(vpn, mmu_psize_defs[hpsize].shift, MMU_SEGSIZE_256M);
 
 map_again:
        hpteg = ((hash & htab_hash_mask) * HPTES_PER_GROUP);
@@ -143,7 +151,7 @@ map_again:
                }
 
        ret = ppc_md.hpte_insert(hpteg, vpn, hpaddr, rflags, vflags,
-                                MMU_PAGE_4K, MMU_PAGE_4K, MMU_SEGSIZE_256M);
+                                hpsize, hpsize, MMU_SEGSIZE_256M);
 
        if (ret < 0) {
                /* If we couldn't map a primary PTE, try a secondary */
@@ -168,6 +176,7 @@ map_again:
                pte->host_vpn = vpn;
                pte->pte = *orig_pte;
                pte->pfn = hpaddr >> PAGE_SHIFT;
+               pte->pagesize = hpsize;
 
                kvmppc_mmu_hpte_cache_map(vcpu, pte);
        }
@@ -291,6 +300,12 @@ int kvmppc_mmu_map_segment(struct kvm_vcpu *vcpu, ulong eaddr)
        slb_vsid &= ~SLB_VSID_KP;
        slb_esid |= slb_index;
 
+#ifdef CONFIG_PPC_64K_PAGES
+       /* Set host segment base page size to 64K if possible */
+       if (gvsid & VSID_64K)
+               slb_vsid |= mmu_psize_defs[MMU_PAGE_64K].sllp;
+#endif
+
        svcpu->slb[slb_index].esid = slb_esid;
        svcpu->slb[slb_index].vsid = slb_vsid;
 

diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c
index 6cc99583ed39711c903bdf800d3434d461ca1aee..e9e8c748e673484ec4e2819b9a08e8af4afc10eb 100644 (file)
--- a/arch/powerpc/kvm/book3s_pr.c
+++ b/arch/powerpc/kvm/book3s_pr.c
@@ -422,6 +422,7 @@ int kvmppc_handle_pagefault(struct kvm_run *run, struct kvm_vcpu *vcpu,
                pte.raddr = eaddr & KVM_PAM;
                pte.eaddr = eaddr;
                pte.vpage = eaddr >> 12;
+               pte.page_size = MMU_PAGE_64K;
        }
 
        switch (vcpu->arch.shared->msr & (MSR_DR|MSR_IR)) {