KVM: PPC: Book3S HV: Make virtual processor area registration more robust

The PAPR API allows three sorts of per-virtual-processor areas to be
registered (VPA, SLB shadow buffer, and dispatch trace log), and
furthermore, these can be registered and unregistered for another
virtual CPU.  Currently we just update the vcpu fields pointing to
these areas at the time of registration or unregistration.  If this
is done on another vcpu, there is the possibility that the target vcpu
is using those fields at the time and could end up using a bogus
pointer and corrupting memory.

This fixes the race by making the target cpu itself do the update, so
we can be sure that the update happens at a time when the fields
aren't being used.  Each area now has a struct kvmppc_vpa which is
used to manage these updates.  There is also a spinlock which protects
access to all of the kvmppc_vpa structs, other than to the pinned_addr
fields.  (We could have just taken the spinlock when using the vpa,
slb_shadow or dtl fields, but that would mean taking the spinlock on
every guest entry and exit.)

This also changes 'struct dtl' (which was undefined) to 'struct dtl_entry',
which is what the rest of the kernel uses.

Thanks to Michael Ellerman <michael@ellerman.id.au> for pointing out
the need to initialize vcpu->arch.vpa_update_lock.

Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>

4 files changed, 190 insertions, 76 deletions

diff --git a/arch/powerpc/include/asm/hvcall.h b/arch/powerpc/include/asm/hvcall.h
index 1c324ff55ea8..318bac9f8752 100644
--- a/arch/powerpc/include/asm/hvcall.h
+++ b/arch/powerpc/include/asm/hvcall.h
@@ -114,6 +114,16 @@
 #define H_PP1                   (1UL<<(63-62))
 #define H_PP2                   (1UL<<(63-63))
 
+/* Flags for H_REGISTER_VPA subfunction field */
+#define H_VPA_FUNC_SHIFT        (63-18) /* Bit posn of subfunction code */
+#define H_VPA_FUNC_MASK         7UL
+#define H_VPA_REG_VPA           1UL     /* Register Virtual Processor Area */
+#define H_VPA_REG_DTL           2UL     /* Register Dispatch Trace Log */
+#define H_VPA_REG_SLB           3UL     /* Register SLB shadow buffer */
+#define H_VPA_DEREG_VPA         5UL     /* Deregister Virtual Processor Area */
+#define H_VPA_DEREG_DTL         6UL     /* Deregister Dispatch Trace Log */
+#define H_VPA_DEREG_SLB         7UL     /* Deregister SLB shadow buffer */
+
 /* VASI States */
 #define H_VASI_INVALID          0
 #define H_VASI_ENABLED          1
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 97ecdaf82956..93ffd8dd8554 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -82,7 +82,7 @@ struct kvm_vcpu;
 
 struct lppaca;
 struct slb_shadow;
-struct dtl;
+struct dtl_entry;
 
 struct kvm_vm_stat {
         u32 remote_tlb_flush;
@@ -279,6 +279,19 @@ struct kvmppc_vcore {
 #define VCORE_EXITING   2
 #define VCORE_SLEEPING  3
 
+/*
+ * Struct used to manage memory for a virtual processor area
+ * registered by a PAPR guest.  There are three types of area
+ * that a guest can register.
+ */
+struct kvmppc_vpa {
+        void *pinned_addr;      /* Address in kernel linear mapping */
+        void *pinned_end;       /* End of region */
+        unsigned long next_gpa; /* Guest phys addr for update */
+        unsigned long len;      /* Number of bytes required */
+        u8 update_pending;      /* 1 => update pinned_addr from next_gpa */
+};
+
 struct kvmppc_pte {
         ulong eaddr;
         u64 vpage;
@@ -473,11 +486,6 @@ struct kvm_vcpu_arch {
         u8 prodded;
         u32 last_inst;
 
-        struct lppaca *vpa;
-        struct slb_shadow *slb_shadow;
-        struct dtl *dtl;
-        struct dtl *dtl_end;
-
         wait_queue_head_t *wqp;
         struct kvmppc_vcore *vcore;
         int ret;
@@ -502,6 +510,13 @@ struct kvm_vcpu_arch {
         struct task_struct *run_task;
         struct kvm_run *kvm_run;
         pgd_t *pgdir;
+
+        spinlock_t vpa_update_lock;
+        struct kvmppc_vpa vpa;
+        struct kvmppc_vpa dtl;
+        struct dtl_entry *dtl_ptr;
+        unsigned long dtl_index;
+        struct kvmppc_vpa slb_shadow;
 #endif
 };
 
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 2abcf7d4b29c..502e038f8c8a 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -466,7 +466,7 @@ int main(void)
         DEFINE(VCPU_PENDING_EXC, offsetof(struct kvm_vcpu, arch.pending_exceptions));
         DEFINE(VCPU_CEDED, offsetof(struct kvm_vcpu, arch.ceded));
         DEFINE(VCPU_PRODDED, offsetof(struct kvm_vcpu, arch.prodded));
-        DEFINE(VCPU_VPA, offsetof(struct kvm_vcpu, arch.vpa));
+        DEFINE(VCPU_VPA, offsetof(struct kvm_vcpu, arch.vpa.pinned_addr));
         DEFINE(VCPU_MMCR, offsetof(struct kvm_vcpu, arch.mmcr));
         DEFINE(VCPU_PMC, offsetof(struct kvm_vcpu, arch.pmc));
         DEFINE(VCPU_SLB, offsetof(struct kvm_vcpu, arch.slb));
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index e87f6196d222..2444a9ce781f 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -134,6 +134,22 @@ static void init_vpa(struct kvm_vcpu *vcpu, struct lppaca *vpa)
         vpa->yield_count = 1;
 }
 
+/* Length for a per-processor buffer is passed in at offset 4 in the buffer */
+struct reg_vpa {
+        u32 dummy;
+        union {
+                u16 hword;
+                u32 word;
+        } length;
+};
+
+static int vpa_is_registered(struct kvmppc_vpa *vpap)
+{
+        if (vpap->update_pending)
+                return vpap->next_gpa != 0;
+        return vpap->pinned_addr != NULL;
+}
+
 static unsigned long do_h_register_vpa(struct kvm_vcpu *vcpu,
                                        unsigned long flags,
                                        unsigned long vcpuid, unsigned long vpa)
@@ -142,88 +158,153 @@ static unsigned long do_h_register_vpa(struct kvm_vcpu *vcpu,
         unsigned long len, nb;
         void *va;
         struct kvm_vcpu *tvcpu;
-        int err = H_PARAMETER;
+        int err;
+        int subfunc;
+        struct kvmppc_vpa *vpap;
 
         tvcpu = kvmppc_find_vcpu(kvm, vcpuid);
         if (!tvcpu)
                 return H_PARAMETER;
 
-        flags >>= 63 - 18;
-        flags &= 7;
-        if (flags == 0 || flags == 4)
-                return H_PARAMETER;
-        if (flags < 4) {
-                if (vpa & 0x7f)
+        subfunc = (flags >> H_VPA_FUNC_SHIFT) & H_VPA_FUNC_MASK;
+        if (subfunc == H_VPA_REG_VPA || subfunc == H_VPA_REG_DTL ||
+            subfunc == H_VPA_REG_SLB) {
+                /* Registering new area - address must be cache-line aligned */
+                if ((vpa & (L1_CACHE_BYTES - 1)) || !vpa)
                         return H_PARAMETER;
-                if (flags >= 2 && !tvcpu->arch.vpa)
-                        return H_RESOURCE;
-                /* registering new area; convert logical addr to real */
+
+                /* convert logical addr to kernel addr and read length */
                 va = kvmppc_pin_guest_page(kvm, vpa, &nb);
                 if (va == NULL)
                         return H_PARAMETER;
-                if (flags <= 1)
-                        len = *(unsigned short *)(va + 4);
+                if (subfunc == H_VPA_REG_VPA)
+                        len = ((struct reg_vpa *)va)->length.hword;
                 else
-                        len = *(unsigned int *)(va + 4);
-                if (len > nb)
-                        goto out_unpin;
-                switch (flags) {
-                case 1:         /* register VPA */
-                        if (len < 640)
+                        len = ((struct reg_vpa *)va)->length.word;
+                kvmppc_unpin_guest_page(kvm, va);
+
+                /* Check length */
+                if (len > nb || len < sizeof(struct reg_vpa))
+                        return H_PARAMETER;