aboutsummaryrefslogtreecommitdiffstats
path: root/arch/powerpc/kvm/book3s_hv_rm_mmu.c
diff options
context:
space:
mode:
Diffstat (limited to 'arch/powerpc/kvm/book3s_hv_rm_mmu.c')
-rw-r--r--arch/powerpc/kvm/book3s_hv_rm_mmu.c835
1 files changed, 657 insertions, 178 deletions
diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
index bacb0cfa3602..def880aea63a 100644
--- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c
+++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
@@ -11,6 +11,7 @@
#include <linux/kvm.h>
#include <linux/kvm_host.h>
#include <linux/hugetlb.h>
+#include <linux/module.h>
#include <asm/tlbflush.h>
#include <asm/kvm_ppc.h>
@@ -20,95 +21,307 @@
#include <asm/synch.h>
#include <asm/ppc-opcode.h>
-/* For now use fixed-size 16MB page table */
-#define HPT_ORDER 24
-#define HPT_NPTEG (1ul << (HPT_ORDER - 7)) /* 128B per pteg */
-#define HPT_HASH_MASK (HPT_NPTEG - 1)
+/* Translate address of a vmalloc'd thing to a linear map address */
+static void *real_vmalloc_addr(void *x)
+{
+ unsigned long addr = (unsigned long) x;
+ pte_t *p;
-#define HPTE_V_HVLOCK 0x40UL
+ p = find_linux_pte(swapper_pg_dir, addr);
+ if (!p || !pte_present(*p))
+ return NULL;
+ /* assume we don't have huge pages in vmalloc space... */
+ addr = (pte_pfn(*p) << PAGE_SHIFT) | (addr & ~PAGE_MASK);
+ return __va(addr);
+}
-static inline long lock_hpte(unsigned long *hpte, unsigned long bits)
+/*
+ * Add this HPTE into the chain for the real page.
+ * Must be called with the chain locked; it unlocks the chain.
+ */
+void kvmppc_add_revmap_chain(struct kvm *kvm, struct revmap_entry *rev,
+ unsigned long *rmap, long pte_index, int realmode)
{
- unsigned long tmp, old;
+ struct revmap_entry *head, *tail;
+ unsigned long i;
- asm volatile(" ldarx %0,0,%2\n"
- " and. %1,%0,%3\n"
- " bne 2f\n"
- " ori %0,%0,%4\n"
- " stdcx. %0,0,%2\n"
- " beq+ 2f\n"
- " li %1,%3\n"
- "2: isync"
- : "=&r" (tmp), "=&r" (old)
- : "r" (hpte), "r" (bits), "i" (HPTE_V_HVLOCK)
- : "cc", "memory");
- return old == 0;
+ if (*rmap & KVMPPC_RMAP_PRESENT) {
+ i = *rmap & KVMPPC_RMAP_INDEX;
+ head = &kvm->arch.revmap[i];
+ if (realmode)
+ head = real_vmalloc_addr(head);
+ tail = &kvm->arch.revmap[head->back];
+ if (realmode)
+ tail = real_vmalloc_addr(tail);
+ rev->forw = i;
+ rev->back = head->back;
+ tail->forw = pte_index;
+ head->back = pte_index;
+ } else {
+ rev->forw = rev->back = pte_index;
+ i = pte_index;
+ }
+ smp_wmb();
+ *rmap = i | KVMPPC_RMAP_REFERENCED | KVMPPC_RMAP_PRESENT; /* unlock */
+}
+EXPORT_SYMBOL_GPL(kvmppc_add_revmap_chain);
+
+/* Remove this HPTE from the chain for a real page */
+static void remove_revmap_chain(struct kvm *kvm, long pte_index,
+ struct revmap_entry *rev,
+ unsigned long hpte_v, unsigned long hpte_r)
+{
+ struct revmap_entry *next, *prev;
+ unsigned long gfn, ptel, head;
+ struct kvm_memory_slot *memslot;
+ unsigned long *rmap;
+ unsigned long rcbits;
+
+ rcbits = hpte_r & (HPTE_R_R | HPTE_R_C);
+ ptel = rev->guest_rpte |= rcbits;
+ gfn = hpte_rpn(ptel, hpte_page_size(hpte_v, ptel));
+ memslot = __gfn_to_memslot(kvm_memslots(kvm), gfn);
+ if (!memslot || (memslot->flags & KVM_MEMSLOT_INVALID))
+ return;
+
+ rmap = real_vmalloc_addr(&memslot->rmap[gfn - memslot->base_gfn]);
+ lock_rmap(rmap);
+
+ head = *rmap & KVMPPC_RMAP_INDEX;
+ next = real_vmalloc_addr(&kvm->arch.revmap[rev->forw]);
+ prev = real_vmalloc_addr(&kvm->arch.revmap[rev->back]);
+ next->back = rev->back;
+ prev->forw = rev->forw;
+ if (head == pte_index) {
+ head = rev->forw;
+ if (head == pte_index)
+ *rmap &= ~(KVMPPC_RMAP_PRESENT | KVMPPC_RMAP_INDEX);
+ else
+ *rmap = (*rmap & ~KVMPPC_RMAP_INDEX) | head;
+ }
+ *rmap |= rcbits << KVMPPC_RMAP_RC_SHIFT;
+ unlock_rmap(rmap);
+}
+
+static pte_t lookup_linux_pte(struct kvm_vcpu *vcpu, unsigned long hva,
+ int writing, unsigned long *pte_sizep)
+{
+ pte_t *ptep;
+ unsigned long ps = *pte_sizep;
+ unsigned int shift;
+
+ ptep = find_linux_pte_or_hugepte(vcpu->arch.pgdir, hva, &shift);
+ if (!ptep)
+ return __pte(0);
+ if (shift)
+ *pte_sizep = 1ul << shift;
+ else
+ *pte_sizep = PAGE_SIZE;
+ if (ps > *pte_sizep)
+ return __pte(0);
+ if (!pte_present(*ptep))
+ return __pte(0);
+ return kvmppc_read_update_linux_pte(ptep, writing);
+}
+
+static inline void unlock_hpte(unsigned long *hpte, unsigned long hpte_v)
+{
+ asm volatile(PPC_RELEASE_BARRIER "" : : : "memory");
+ hpte[0] = hpte_v;
}
long kvmppc_h_enter(struct kvm_vcpu *vcpu, unsigned long flags,
long pte_index, unsigned long pteh, unsigned long ptel)
{
- unsigned long porder;
struct kvm *kvm = vcpu->kvm;
- unsigned long i, lpn, pa;
+ unsigned long i, pa, gpa, gfn, psize;
+ unsigned long slot_fn, hva;
unsigned long *hpte;
+ struct revmap_entry *rev;
+ unsigned long g_ptel = ptel;
+ struct kvm_memory_slot *memslot;
+ unsigned long *physp, pte_size;
+ unsigned long is_io;
+ unsigned long *rmap;
+ pte_t pte;
+ unsigned int writing;
+ unsigned long mmu_seq;
+ unsigned long rcbits;
+ bool realmode = vcpu->arch.vcore->vcore_state == VCORE_RUNNING;
- /* only handle 4k, 64k and 16M pages for now */
- porder = 12;
- if (pteh & HPTE_V_LARGE) {
- if (cpu_has_feature(CPU_FTR_ARCH_206) &&
- (ptel & 0xf000) == 0x1000) {
- /* 64k page */
- porder = 16;
- } else if ((ptel & 0xff000) == 0) {
- /* 16M page */
- porder = 24;
- /* lowest AVA bit must be 0 for 16M pages */
- if (pteh & 0x80)
- return H_PARAMETER;
- } else
+ psize = hpte_page_size(pteh, ptel);
+ if (!psize)
+ return H_PARAMETER;
+ writing = hpte_is_writable(ptel);
+ pteh &= ~(HPTE_V_HVLOCK | HPTE_V_ABSENT | HPTE_V_VALID);
+
+ /* used later to detect if we might have been invalidated */
+ mmu_seq = kvm->mmu_notifier_seq;
+ smp_rmb();
+
+ /* Find the memslot (if any) for this address */
+ gpa = (ptel & HPTE_R_RPN) & ~(psize - 1);
+ gfn = gpa >> PAGE_SHIFT;
+ memslot = __gfn_to_memslot(kvm_memslots(kvm), gfn);
+ pa = 0;
+ is_io = ~0ul;
+ rmap = NULL;
+ if (!(memslot && !(memslot->flags & KVM_MEMSLOT_INVALID))) {
+ /* PPC970 can't do emulated MMIO */
+ if (!cpu_has_feature(CPU_FTR_ARCH_206))
return H_PARAMETER;
+ /* Emulated MMIO - mark this with key=31 */
+ pteh |= HPTE_V_ABSENT;
+ ptel |= HPTE_R_KEY_HI | HPTE_R_KEY_LO;
+ goto do_insert;
}
- lpn = (ptel & HPTE_R_RPN) >> kvm->arch.ram_porder;
- if (lpn >= kvm->arch.ram_npages || porder > kvm->arch.ram_porder)
- return H_PARAMETER;
- pa = kvm->arch.ram_pginfo[lpn].pfn << PAGE_SHIFT;
- if (!pa)
+
+ /* Check if the requested page fits entirely in the memslot. */
+ if (!slot_is_aligned(memslot, psize))
return H_PARAMETER;
- /* Check WIMG */
- if ((ptel & HPTE_R_WIMG) != HPTE_R_M &&
- (ptel & HPTE_R_WIMG) != (HPTE_R_W | HPTE_R_I | HPTE_R_M))
+ slot_fn = gfn - memslot->base_gfn;
+ rmap = &memslot->rmap[slot_fn];
+
+ if (!kvm->arch.using_mmu_notifiers) {
+ physp = kvm->arch.slot_phys[memslot->id];
+ if (!physp)
+ return H_PARAMETER;
+ physp += slot_fn;
+ if (realmode)
+ physp = real_vmalloc_addr(physp);
+ pa = *physp;
+ if (!pa)
+ return H_TOO_HARD;
+ is_io = pa & (HPTE_R_I | HPTE_R_W);
+ pte_size = PAGE_SIZE << (pa & KVMPPC_PAGE_ORDER_MASK);
+ pa &= PAGE_MASK;
+ } else {
+ /* Translate to host virtual address */
+ hva = gfn_to_hva_memslot(memslot, gfn);
+
+ /* Look up the Linux PTE for the backing page */
+ pte_size = psize;
+ pte = lookup_linux_pte(vcpu, hva, writing, &pte_size);
+ if (pte_present(pte)) {
+ if (writing && !pte_write(pte))
+ /* make the actual HPTE be read-only */
+ ptel = hpte_make_readonly(ptel);
+ is_io = hpte_cache_bits(pte_val(pte));
+ pa = pte_pfn(pte) << PAGE_SHIFT;
+ }
+ }
+ if (pte_size < psize)
return H_PARAMETER;
- pteh &= ~0x60UL;
- ptel &= ~(HPTE_R_PP0 - kvm->arch.ram_psize);
+ if (pa && pte_size > psize)
+ pa |= gpa & (pte_size - 1);
+
+ ptel &= ~(HPTE_R_PP0 - psize);
ptel |= pa;
- if (pte_index >= (HPT_NPTEG << 3))
+
+ if (pa)
+ pteh |= HPTE_V_VALID;
+ else
+ pteh |= HPTE_V_ABSENT;
+
+ /* Check WIMG */
+ if (is_io != ~0ul && !hpte_cache_flags_ok(ptel, is_io)) {
+ if (is_io)
+ return H_PARAMETER;
+ /*
+ * Allow guest to map emulated device memory as
+ * uncacheable, but actually make it cacheable.
+ */
+ ptel &= ~(HPTE_R_W|HPTE_R_I|HPTE_R_G);
+ ptel |= HPTE_R_M;
+ }
+
+ /* Find and lock the HPTEG slot to use */
+ do_insert:
+ if (pte_index >= HPT_NPTE)
return H_PARAMETER;
if (likely((flags & H_EXACT) == 0)) {
pte_index &= ~7UL;
hpte = (unsigned long *)(kvm->arch.hpt_virt + (pte_index << 4));
- for (i = 0; ; ++i) {
- if (i == 8)
- return H_PTEG_FULL;
+ for (i = 0; i < 8; ++i) {
if ((*hpte & HPTE_V_VALID) == 0 &&
- lock_hpte(hpte, HPTE_V_HVLOCK | HPTE_V_VALID))
+ try_lock_hpte(hpte, HPTE_V_HVLOCK | HPTE_V_VALID |
+ HPTE_V_ABSENT))
break;
hpte += 2;
}
+ if (i == 8) {
+ /*
+ * Since try_lock_hpte doesn't retry (not even stdcx.
+ * failures), it could be that there is a free slot
+ * but we transiently failed to lock it. Try again,
+ * actually locking each slot and checking it.
+ */
+ hpte -= 16;
+ for (i = 0; i < 8; ++i) {
+ while (!try_lock_hpte(hpte, HPTE_V_HVLOCK))
+ cpu_relax();
+ if (!(*hpte & (HPTE_V_VALID | HPTE_V_ABSENT)))
+ break;
+ *hpte &= ~HPTE_V_HVLOCK;
+ hpte += 2;
+ }
+ if (i == 8)
+ return H_PTEG_FULL;
+ }
+ pte_index += i;
} else {
- i = 0;
hpte = (unsigned long *)(kvm->arch.hpt_virt + (pte_index << 4));
- if (!lock_hpte(hpte, HPTE_V_HVLOCK | HPTE_V_VALID))
- return H_PTEG_FULL;
+ if (!try_lock_hpte(hpte, HPTE_V_HVLOCK | HPTE_V_VALID |
+ HPTE_V_ABSENT)) {
+ /* Lock the slot and check again */
+ while (!try_lock_hpte(hpte, HPTE_V_HVLOCK))
+ cpu_relax();
+ if (*hpte & (HPTE_V_VALID | HPTE_V_ABSENT)) {
+ *hpte &= ~HPTE_V_HVLOCK;
+ return H_PTEG_FULL;
+ }
+ }
}
+
+ /* Save away the guest's idea of the second HPTE dword */
+ rev = &kvm->arch.revmap[pte_index];
+ if (realmode)
+ rev = real_vmalloc_addr(rev);
+ if (rev)
+ rev->guest_rpte = g_ptel;
+
+ /* Link HPTE into reverse-map chain */
+ if (pteh & HPTE_V_VALID) {
+ if (realmode)
+ rmap = real_vmalloc_addr(rmap);
+ lock_rmap(rmap);
+ /* Check for pending invalidations under the rmap chain lock */
+ if (kvm->arch.using_mmu_notifiers &&
+ mmu_notifier_retry(vcpu, mmu_seq)) {
+ /* inval in progress, write a non-present HPTE */
+ pteh |= HPTE_V_ABSENT;
+ pteh &= ~HPTE_V_VALID;
+ unlock_rmap(rmap);
+ } else {
+ kvmppc_add_revmap_chain(kvm, rev, rmap, pte_index,
+ realmode);
+ /* Only set R/C in real HPTE if already set in *rmap */
+ rcbits = *rmap >> KVMPPC_RMAP_RC_SHIFT;
+ ptel &= rcbits | ~(HPTE_R_R | HPTE_R_C);
+ }
+ }
+
hpte[1] = ptel;
+
+ /* Write the first HPTE dword, unlocking the HPTE and making it valid */
eieio();
hpte[0] = pteh;
asm volatile("ptesync" : : : "memory");
- atomic_inc(&kvm->arch.ram_pginfo[lpn].refcnt);
- vcpu->arch.gpr[4] = pte_index + i;
+
+ vcpu->arch.gpr[4] = pte_index;
return H_SUCCESS;
}
+EXPORT_SYMBOL_GPL(kvmppc_h_enter);
#define LOCK_TOKEN (*(u32 *)(&get_paca()->lock_token))
@@ -137,37 +350,46 @@ long kvmppc_h_remove(struct kvm_vcpu *vcpu, unsigned long flags,
struct kvm *kvm = vcpu->kvm;
unsigned long *hpte;
unsigned long v, r, rb;
+ struct revmap_entry *rev;
- if (pte_index >= (HPT_NPTEG << 3))
+ if (pte_index >= HPT_NPTE)
return H_PARAMETER;
hpte = (unsigned long *)(kvm->arch.hpt_virt + (pte_index << 4));
- while (!lock_hpte(hpte, HPTE_V_HVLOCK))
+ while (!try_lock_hpte(hpte, HPTE_V_HVLOCK))
cpu_relax();
- if ((hpte[0] & HPTE_V_VALID) == 0 ||
+ if ((hpte[0] & (HPTE_V_ABSENT | HPTE_V_VALID)) == 0 ||
((flags & H_AVPN) && (hpte[0] & ~0x7fUL) != avpn) ||
((flags & H_ANDCOND) && (hpte[0] & avpn) != 0)) {
hpte[0] &= ~HPTE_V_HVLOCK;
return H_NOT_FOUND;
}
- if (atomic_read(&kvm->online_vcpus) == 1)
- flags |= H_LOCAL;
- vcpu->arch.gpr[4] = v = hpte[0] & ~HPTE_V_HVLOCK;
- vcpu->arch.gpr[5] = r = hpte[1];
- rb = compute_tlbie_rb(v, r, pte_index);
- hpte[0] = 0;
- if (!(flags & H_LOCAL)) {
- while(!try_lock_tlbie(&kvm->arch.tlbie_lock))
- cpu_relax();
- asm volatile("ptesync" : : : "memory");
- asm volatile(PPC_TLBIE(%1,%0)"; eieio; tlbsync"
- : : "r" (rb), "r" (kvm->arch.lpid));
- asm volatile("ptesync" : : : "memory");
- kvm->arch.tlbie_lock = 0;
- } else {
- asm volatile("ptesync" : : : "memory");
- asm volatile("tlbiel %0" : : "r" (rb));
- asm volatile("ptesync" : : : "memory");
+
+ rev = real_vmalloc_addr(&kvm->arch.revmap[pte_index]);
+ v = hpte[0] & ~HPTE_V_HVLOCK;
+ if (v & HPTE_V_VALID) {
+ hpte[0] &= ~HPTE_V_VALID;
+ rb = compute_tlbie_rb(v, hpte[1], pte_index);
+ if (!(flags & H_LOCAL) && atomic_read(&kvm->online_vcpus) > 1) {
+ while (!try_lock_tlbie(&kvm->arch.tlbie_lock))
+ cpu_relax();
+ asm volatile("ptesync" : : : "memory");
+ asm volatile(PPC_TLBIE(%1,%0)"; eieio; tlbsync"
+ : : "r" (rb), "r" (kvm->arch.lpid));
+ asm volatile("ptesync" : : : "memory");
+ kvm->arch.tlbie_lock = 0;
+ } else {
+ asm volatile("ptesync" : : : "memory");
+ asm volatile("tlbiel %0" : : "r" (rb));
+ asm volatile("ptesync" : : : "memory");
+ }
+ /* Read PTE low word after tlbie to get final R/C values */
+ remove_revmap_chain(kvm, pte_index, rev, v, hpte[1]);
}
+ r = rev->guest_rpte;
+ unlock_hpte(hpte, 0);
+
+ vcpu->arch.gpr[4] = v;
+ vcpu->arch.gpr[5] = r;
return H_SUCCESS;
}
@@ -175,78 +397,117 @@ long kvmppc_h_bulk_remove(struct kvm_vcpu *vcpu)
{
struct kvm *kvm = vcpu->kvm;
unsigned long *args = &vcpu->arch.gpr[4];
- unsigned long *hp, tlbrb[4];
- long int i, found;
- long int n_inval = 0;
- unsigned long flags, req, pte_index;
+ unsigned long *hp, *hptes[4], tlbrb[4];
+ long int i, j, k, n, found, indexes[4];
+ unsigned long flags, req, pte_index, rcbits;
long int local = 0;
long int ret = H_SUCCESS;
+ struct revmap_entry *rev, *revs[4];
if (atomic_read(&kvm->online_vcpus) == 1)
local = 1;
- for (i = 0; i < 4; ++i) {
- pte_index = args[i * 2];
- flags = pte_index >> 56;
- pte_index &= ((1ul << 56) - 1);
- req = flags >> 6;
- flags &= 3;
- if (req == 3)
- break;
- if (req != 1 || flags == 3 ||
- pte_index >= (HPT_NPTEG << 3)) {
- /* parameter error */
- args[i * 2] = ((0xa0 | flags) << 56) + pte_index;
- ret = H_PARAMETER;
- break;
- }
- hp = (unsigned long *)(kvm->arch.hpt_virt + (pte_index << 4));
- while (!lock_hpte(hp, HPTE_V_HVLOCK))
- cpu_relax();
- found = 0;
- if (hp[0] & HPTE_V_VALID) {
- switch (flags & 3) {
- case 0: /* absolute */
- found = 1;
+ for (i = 0; i < 4 && ret == H_SUCCESS; ) {
+ n = 0;
+ for (; i < 4; ++i) {
+ j = i * 2;
+ pte_index = args[j];
+ flags = pte_index >> 56;
+ pte_index &= ((1ul << 56) - 1);
+ req = flags >> 6;
+ flags &= 3;
+ if (req == 3) { /* no more requests */
+ i = 4;
break;
- case 1: /* andcond */
- if (!(hp[0] & args[i * 2 + 1]))
- found = 1;
+ }
+ if (req != 1 || flags == 3 || pte_index >= HPT_NPTE) {
+ /* parameter error */
+ args[j] = ((0xa0 | flags) << 56) + pte_index;
+ ret = H_PARAMETER;
break;
- case 2: /* AVPN */
- if ((hp[0] & ~0x7fUL) == args[i * 2 + 1])
+ }
+ hp = (unsigned long *)
+ (kvm->arch.hpt_virt + (pte_index << 4));
+ /* to avoid deadlock, don't spin except for first */
+ if (!try_lock_hpte(hp, HPTE_V_HVLOCK)) {
+ if (n)
+ break;
+ while (!try_lock_hpte(hp, HPTE_V_HVLOCK))
+ cpu_relax();
+ }
+ found = 0;
+ if (hp[0] & (HPTE_V_ABSENT | HPTE_V_VALID)) {
+ switch (flags & 3) {
+ case 0: /* absolute */
found = 1;
- break;
+ break;
+ case 1: /* andcond */
+ if (!(hp[0] & args[j + 1]))
+ found = 1;
+ break;
+ case 2: /* AVPN */
+ if ((hp[0] & ~0x7fUL) == args[j + 1])
+ found = 1;
+ break;
+ }
+ }
+ if (!found) {
+ hp[0] &= ~HPTE_V_HVLOCK;
+ args[j] = ((0x90 | flags) << 56) + pte_index;
+ continue;
}
+
+ args[j] = ((0x80 | flags) << 56) + pte_index;
+ rev = real_vmalloc_addr(&kvm->arch.revmap[pte_index]);
+
+ if (!(hp[0] & HPTE_V_VALID)) {
+ /* insert R and C bits from PTE */
+ rcbits = rev->guest_rpte & (HPTE_R_R|HPTE_R_C);
+ args[j] |= rcbits << (56 - 5);
+ continue;
+ }
+
+ hp[0] &= ~HPTE_V_VALID; /* leave it locked */
+ tlbrb[n] = compute_tlbie_rb(hp[0], hp[1], pte_index);
+ indexes[n] = j;
+ hptes[n] = hp;
+ revs[n] = rev;
+ ++n;
+ }
+
+ if (!n)
+ break;
+
+ /* Now that we've collected a batch, do the tlbies */
+ if (!local) {
+ while(!try_lock_tlbie(&kvm->arch.tlbie_lock))
+ cpu_relax();
+ asm volatile("ptesync" : : : "memory");
+ for (k = 0; k < n; ++k)
+ asm volatile(PPC_TLBIE(%1,%0) : :
+ "r" (tlbrb[k]),
+ "r" (kvm->arch.lpid));
+ asm volatile("eieio; tlbsync; ptesync" : : : "memory");
+ kvm->arch.tlbie_lock = 0;
+ } else {
+ asm volatile("ptesync" : : : "memory");
+ for (k = 0; k < n; ++k)
+ asm volatile("tlbiel %0" : : "r" (tlbrb[k]));
+ asm volatile("ptesync" : : : "memory");
}
- if (!found) {
- hp[0] &= ~HPTE_V_HVLOCK;
- args[i * 2] = ((0x90 | flags) << 56) + pte_index;
- continue;
+
+ /* Read PTE low words after tlbie to get final R/C values */
+ for (k = 0; k < n; ++k) {
+ j = indexes[k];
+ pte_index = args[j] & ((1ul << 56) - 1);
+ hp = hptes[k];
+ rev = revs[k];
+ remove_revmap_chain(kvm, pte_index, rev, hp[0], hp[1]);
+ rcbits = rev->guest_rpte & (HPTE_R_R|HPTE_R_C);
+ args[j] |= rcbits << (56 - 5);
+ hp[0] = 0;
}
- /* insert R and C bits from PTE */
- flags |= (hp[1] >> 5) & 0x0c;
- args[i * 2] = ((0x80 | flags) << 56) + pte_index;
- tlbrb[n_inval++] = compute_tlbie_rb(hp[0], hp[1], pte_index);
- hp[0] = 0;
- }
- if (n_inval == 0)
- return ret;
-
- if (!local) {
- while(!try_lock_tlbie(&kvm->arch.tlbie_lock))
- cpu_relax();
- asm volatile("ptesync" : : : "memory");
- for (i = 0; i < n_inval; ++i)
- asm volatile(PPC_TLBIE(%1,%0)
- : : "r" (tlbrb[i]), "r" (kvm->arch.lpid));
- asm volatile("eieio; tlbsync; ptesync" : : : "memory");
- kvm->arch.tlbie_lock = 0;
- } else {
- asm volatile("ptesync" : : : "memory");
- for (i = 0; i < n_inval; ++i)
- asm volatile("tlbiel %0" : : "r" (tlbrb[i]));
- asm volatile("ptesync" : : : "memory");
}
+
return ret;
}
@@ -256,40 +517,55 @@ long kvmppc_h_protect(struct kvm_vcpu *vcpu, unsigned long flags,
{
struct kvm *kvm = vcpu->kvm;
unsigned long *hpte;
- unsigned long v, r, rb;
+ struct revmap_entry *rev;
+ unsigned long v, r, rb, mask, bits;
- if (pte_index >= (HPT_NPTEG << 3))
+ if (pte_index >= HPT_NPTE)
return H_PARAMETER;
+
hpte = (unsigned long *)(kvm->arch.hpt_virt + (pte_index << 4));
- while (!lock_hpte(hpte, HPTE_V_HVLOCK))
+ while (!try_lock_hpte(hpte, HPTE_V_HVLOCK))
cpu_relax();
- if ((hpte[0] & HPTE_V_VALID) == 0 ||
+ if ((hpte[0] & (HPTE_V_ABSENT | HPTE_V_VALID)) == 0 ||
((flags & H_AVPN) && (hpte[0] & ~0x7fUL) != avpn)) {
hpte[0] &= ~HPTE_V_HVLOCK;
return H_NOT_FOUND;
}
+
if (atomic_read(&kvm->online_vcpus) == 1)
flags |= H_LOCAL;
v = hpte[0];
- r = hpte[1] & ~(HPTE_R_PP0 | HPTE_R_PP | HPTE_R_N |
- HPTE_R_KEY_HI | HPTE_R_KEY_LO);
- r |= (flags << 55) & HPTE_R_PP0;
- r |= (flags << 48) & HPTE_R_KEY_HI;
- r |= flags & (HPTE_R_PP | HPTE_R_N | HPTE_R_KEY_LO);
- rb = compute_tlbie_rb(v, r, pte_index);
- hpte[0] = v & ~HPTE_V_VALID;
- if (!(flags & H_LOCAL)) {
- while(!try_lock_tlbie(&kvm->arch.tlbie_lock))
- cpu_relax();
- asm volatile("ptesync" : : : "memory");
- asm volatile(PPC_TLBIE(%1,%0)"; eieio; tlbsync"
- : : "r" (rb), "r" (kvm->arch.lpid));
- asm volatile("ptesync" : : : "memory");
- kvm->arch.tlbie_lock = 0;
- } else {
- asm volatile("ptesync" : : : "memory");
- asm volatile("tlbiel %0" : : "r" (rb));
- asm volatile("ptesync" : : : "memory");
+ bits = (flags << 55) & HPTE_R_PP0;
+ bits |= (flags << 48) & HPTE_R_KEY_HI;
+ bits |= flags & (HPTE_R_PP | HPTE_R_N | HPTE_R_KEY_LO);
+
+ /* Update guest view of 2nd HPTE dword */
+ mask = HPTE_R_PP0 | HPTE_R_PP | HPTE_R_N |
+ HPTE_R_KEY_HI | HPTE_R_KEY_LO;
+ rev = real_vmalloc_addr(&kvm->arch.revmap[pte_index]);
+ if (rev) {
+ r = (rev->guest_rpte & ~mask) | bits;
+ rev->guest_rpte = r;
+ }
+ r = (hpte[1] & ~mask) | bits;
+
+ /* Update HPTE */
+ if (v & HPTE_V_VALID) {
+ rb = compute_tlbie_rb(v, r, pte_index);
+ hpte[0] = v & ~HPTE_V_VALID;
+ if (!(flags & H_LOCAL)) {
+ while(!try_lock_tlbie(&kvm->arch.tlbie_lock))
+ cpu_relax();
+ asm volatile("ptesync" : : : "memory");
+ asm volatile(PPC_TLBIE(%1,%0)"; eieio; tlbsync"
+ : : "r" (rb), "r" (kvm->arch.lpid));
+ asm volatile("ptesync" : : : "memory");
+ kvm->arch.tlbie_lock = 0;
+ } else {
+ asm volatile("ptesync" : : : "memory");
+ asm volatile("tlbiel %0" : : "r" (rb));
+ asm volatile("ptesync" : : : "memory");
+ }
}
hpte[1] = r;
eieio();
@@ -298,40 +574,243 @@ long kvmppc_h_protect(struct kvm_vcpu *vcpu, unsigned long flags,
return H_SUCCESS;
}
-static unsigned long reverse_xlate(struct kvm *kvm, unsigned long realaddr)
-{
- long int i;
- unsigned long offset, rpn;
-
- offset = realaddr & (kvm->arch.ram_psize - 1);
- rpn = (realaddr - offset) >> PAGE_SHIFT;
- for (i = 0; i < kvm->arch.ram_npages; ++i)
- if (rpn == kvm->arch.ram_pginfo[i].pfn)
- return (i << PAGE_SHIFT) + offset;
- return HPTE_R_RPN; /* all 1s in the RPN field */
-}
-
long kvmppc_h_read(struct kvm_vcpu *vcpu, unsigned long flags,
unsigned long pte_index)
{
struct kvm *kvm = vcpu->kvm;
- unsigned long *hpte, r;
+ unsigned long *hpte, v, r;
int i, n = 1;
+ struct revmap_entry *rev = NULL;
- if (pte_index >= (HPT_NPTEG << 3))
+ if (pte_index >= HPT_NPTE)
return H_PARAMETER;
if (flags & H_READ_4) {
pte_index &= ~3;
n = 4;
}
+ rev = real_vmalloc_addr(&kvm->arch.revmap[pte_index]);
for (i = 0; i < n; ++i, ++pte_index) {
hpte = (unsigned long *)(kvm->arch.hpt_virt + (pte_index << 4));
+ v = hpte[0] & ~HPTE_V_HVLOCK;
r = hpte[1];
- if ((flags & H_R_XLATE) && (hpte[0] & HPTE_V_VALID))
- r = reverse_xlate(kvm, r & HPTE_R_RPN) |
- (r & ~HPTE_R_RPN);
- vcpu->arch.gpr[4 + i * 2] = hpte[0];
+ if (v & HPTE_V_ABSENT) {
+ v &= ~HPTE_V_ABSENT;
+ v |= HPTE_V_VALID;
+ }
+ if (v & HPTE_V_VALID)
+ r = rev[i].guest_rpte | (r & (HPTE_R_R | HPTE_R_C));
+ vcpu->arch.gpr[4 + i * 2] = v;
vcpu->arch.gpr[5 + i * 2] = r;
}
return H_SUCCESS;
}
+
+void kvmppc_invalidate_hpte(struct kvm *kvm, unsigned long *hptep,
+ unsigned long pte_index)
+{
+ unsigned long rb;
+
+ hptep[0] &= ~HPTE_V_VALID;
+ rb = compute_tlbie_rb(hptep[0], hptep[1], pte_index);
+ while (!try_lock_tlbie(&kvm->arch.tlbie_lock))
+ cpu_relax();
+ asm volatile("ptesync" : : : "memory");
+ asm volatile(PPC_TLBIE(%1,%0)"; eieio; tlbsync"
+ : : "r" (rb), "r" (kvm->arch.lpid));
+ asm volatile("ptesync" : : : "memory");
+ kvm->arch.tlbie_lock = 0;
+}
+EXPORT_SYMBOL_GPL(kvmppc_invalidate_hpte);
+
+void kvmppc_clear_ref_hpte(struct kvm *kvm, unsigned long *hptep,
+ unsigned long pte_index)
+{
+ unsigned long rb;
+ unsigned char rbyte;
+
+ rb = compute_tlbie_rb(hptep[0], hptep[1], pte_index);
+ rbyte = (hptep[1] & ~HPTE_R_R) >> 8;
+ /* modify only the second-last byte, which contains the ref bit */
+ *((char *)hptep + 14) = rbyte;
+ while (!try_lock_tlbie(&kvm->arch.tlbie_lock))
+ cpu_relax();
+ asm volatile(PPC_TLBIE(%1,%0)"; eieio; tlbsync"
+ : : "r" (rb), "r" (kvm->arch.lpid));
+ asm volatile("ptesync" : : : "memory");
+ kvm->arch.tlbie_lock = 0;
+}
+EXPORT_SYMBOL_GPL(kvmppc_clear_ref_hpte);
+
+static int slb_base_page_shift[4] = {
+ 24, /* 16M */
+ 16, /* 64k */
+ 34, /* 16G */
+ 20, /* 1M, unsupported */
+};
+
+long kvmppc_hv_find_lock_hpte(struct kvm *kvm, gva_t eaddr, unsigned long slb_v,
+ unsigned long valid)
+{
+ unsigned int i;
+ unsigned int pshift;
+ unsigned long somask;
+ unsigned long vsid, hash;
+ unsigned long avpn;
+ unsigned long *hpte;
+ unsigned long mask, val;
+ unsigned long v, r;
+
+ /* Get page shift, work out hash and AVPN etc. */
+ mask = SLB_VSID_B | HPTE_V_AVPN | HPTE_V_SECONDARY;
+ val = 0;
+ pshift = 12;
+ if (slb_v & SLB_VSID_L) {
+ mask |= HPTE_V_LARGE;
+ val |= HPTE_V_LARGE;
+ pshift = slb_base_page_shift[(slb_v & SLB_VSID_LP) >> 4];
+ }
+ if (slb_v & SLB_VSID_B_1T) {
+ somask = (1UL << 40) - 1;
+ vsid = (slb_v & ~SLB_VSID_B) >> SLB_VSID_SHIFT_1T;
+ vsid ^= vsid << 25;
+ } else {
+ somask = (1UL << 28) - 1;
+ vsid = (slb_v & ~SLB_VSID_B) >> SLB_VSID_SHIFT;
+ }
+ hash = (vsid ^ ((eaddr & somask) >> pshift)) & HPT_HASH_MASK;
+ avpn = slb_v & ~(somask >> 16); /* also includes B */
+ avpn |= (eaddr & somask) >> 16;
+
+ if (pshift >= 24)
+ avpn &= ~((1UL << (pshift - 16)) - 1);
+ else
+ avpn &= ~0x7fUL;
+ val |= avpn;
+
+ for (;;) {
+ hpte = (unsigned long *)(kvm->arch.hpt_virt + (hash << 7));
+
+ for (i = 0; i < 16; i += 2) {
+ /* Read the PTE racily */
+ v = hpte[i] & ~HPTE_V_HVLOCK;
+
+ /* Check valid/absent, hash, segment size and AVPN */
+ if (!(v & valid) || (v & mask) != val)
+ continue;
+
+ /* Lock the PTE and read it under the lock */
+ while (!try_lock_hpte(&hpte[i], HPTE_V_HVLOCK))
+ cpu_relax();
+ v = hpte[i] & ~HPTE_V_HVLOCK;
+ r = hpte[i+1];
+
+ /*
+ * Check the HPTE again, including large page size
+ * Since we don't currently allow any MPSS (mixed
+ * page-size segment) page sizes, it is sufficient
+ * to check against the actual page size.
+ */
+ if ((v & valid) && (v & mask) == val &&
+ hpte_page_size(v, r) == (1ul << pshift))
+ /* Return with the HPTE still locked */
+ return (hash << 3) + (i >> 1);
+
+ /* Unlock and move on */
+ hpte[i] = v;
+ }
+
+ if (val & HPTE_V_SECONDARY)
+ break;
+ val |= HPTE_V_SECONDARY;
+ hash = hash ^ HPT_HASH_MASK;
+ }
+ return -1;
+}
+EXPORT_SYMBOL(kvmppc_hv_find_lock_hpte);
+
+/*
+ * Called in real mode to check whether an HPTE not found fault
+ * is due to accessing a paged-out page or an emulated MMIO page,
+ * or if a protection fault is due to accessing a page that the
+ * guest wanted read/write access to but which we made read-only.
+ * Returns a possibly modified status (DSISR) value if not
+ * (i.e. pass the interrupt to the guest),
+ * -1 to pass the fault up to host kernel mode code, -2 to do that
+ * and also load the instruction word (for MMIO emulation),
+ * or 0 if we should make the guest retry the access.
+ */
+long kvmppc_hpte_hv_fault(struct kvm_vcpu *vcpu, unsigned long addr,
+ unsigned long slb_v, unsigned int status, bool data)
+{
+ struct kvm *kvm = vcpu->kvm;
+ long int index;
+ unsigned long v, r, gr;
+ unsigned long *hpte;
+ unsigned long valid;
+ struct revmap_entry *rev;
+ unsigned long pp, key;
+
+ /* For protection fault, expect to find a valid HPTE */
+ valid = HPTE_V_VALID;
+ if (status & DSISR_NOHPTE)
+ valid |= HPTE_V_ABSENT;
+
+ index = kvmppc_hv_find_lock_hpte(kvm, addr, slb_v, valid);
+ if (index < 0) {
+ if (status & DSISR_NOHPTE)
+ return status; /* there really was no HPTE */
+ return 0; /* for prot fault, HPTE disappeared */
+ }
+ hpte = (unsigned long *)(kvm->arch.hpt_virt + (index << 4));
+ v = hpte[0] & ~HPTE_V_HVLOCK;
+ r = hpte[1];
+ rev = real_vmalloc_addr(&kvm->arch.revmap[index]);
+ gr = rev->guest_rpte;
+
+ unlock_hpte(hpte, v);
+
+ /* For not found, if the HPTE is valid by now, retry the instruction */
+ if ((status & DSISR_NOHPTE) && (v & HPTE_V_VALID))
+ return 0;
+
+ /* Check access permissions to the page */
+ pp = gr & (HPTE_R_PP0 | HPTE_R_PP);
+ key = (vcpu->arch.shregs.msr & MSR_PR) ? SLB_VSID_KP : SLB_VSID_KS;
+ status &= ~DSISR_NOHPTE; /* DSISR_NOHPTE == SRR1_ISI_NOPT */
+ if (!data) {
+ if (gr & (HPTE_R_N | HPTE_R_G))
+ return status | SRR1_ISI_N_OR_G;
+ if (!hpte_read_permission(pp, slb_v & key))
+ return status | SRR1_ISI_PROT;
+ } else if (status & DSISR_ISSTORE) {
+ /* check write permission */
+ if (!hpte_write_permission(pp, slb_v & key))
+ return status | DSISR_PROTFAULT;
+ } else {
+ if (!hpte_read_permission(pp, slb_v & key))
+ return status | DSISR_PROTFAULT;
+ }
+
+ /* Check storage key, if applicable */
+ if (data && (vcpu->arch.shregs.msr & MSR_DR)) {
+ unsigned int perm = hpte_get_skey_perm(gr, vcpu->arch.amr);
+ if (status & DSISR_ISSTORE)
+ perm >>= 1;
+ if (perm & 1)
+ return status | DSISR_KEYFAULT;
+ }
+
+ /* Save HPTE info for virtual-mode handler */
+ vcpu->arch.pgfault_addr = addr;
+ vcpu->arch.pgfault_index = index;
+ vcpu->arch.pgfault_hpte[0] = v;
+ vcpu->arch.pgfault_hpte[1] = r;
+
+ /* Check the storage key to see if it is possibly emulated MMIO */
+ if (data && (vcpu->arch.shregs.msr & MSR_IR) &&
+ (r & (HPTE_R_KEY_HI | HPTE_R_KEY_LO)) ==
+ (HPTE_R_KEY_HI | HPTE_R_KEY_LO))
+ return -2; /* MMIO emulation - load instr word */
+
+ return -1; /* send fault up to host kernel mode */
+}
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.