[RFC PATCH v4 31/47] hw/xen: Implement EVTCHNOP_unmask

[David Woodhouse <dwmw2@infradead.org>]

From: David Woodhouse <dwmw@amazon.co.uk>

This finally comes with a mechanism for actually injecting events into
the guest vCPU, with all the atomic-test-and-set that's involved in
setting the bit in the shinfo, then the index in the vcpu_info, and
injecting either the lapic vector as MSI, or letting KVM inject the
bare vector.

Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
---
 hw/i386/kvm/xen_evtchn.c  | 220 ++++++++++++++++++++++++++++++++++++++
 hw/i386/kvm/xen_evtchn.h  |   2 +
 target/i386/kvm/xen-emu.c |  12 +++
 3 files changed, 234 insertions(+)

diff --git a/hw/i386/kvm/xen_evtchn.c b/hw/i386/kvm/xen_evtchn.c
index 3ccf72d78b..a3ad2ddb55 100644
--- a/hw/i386/kvm/xen_evtchn.c
+++ b/hw/i386/kvm/xen_evtchn.c
@@ -21,6 +21,7 @@
 
 #include "hw/sysbus.h"
 #include "hw/xen/xen.h"
+
 #include "xen_evtchn.h"
 #include "xen_overlay.h"
 
@@ -40,6 +41,41 @@ typedef struct XenEvtchnPort {
     uint16_t type_val;  /* pirq# / virq# / remote port according to type */
 } XenEvtchnPort;
 
+/* 32-bit compatibility definitions, also used natively in 32-bit build */
+struct compat_arch_vcpu_info {
+    unsigned int cr2;
+    unsigned int pad[5];
+};
+
+struct compat_vcpu_info {
+    uint8_t evtchn_upcall_pending;
+    uint8_t evtchn_upcall_mask;
+    uint16_t pad;
+    uint32_t evtchn_pending_sel;
+    struct compat_arch_vcpu_info arch;
+    struct vcpu_time_info time;
+}; /* 64 bytes (x86) */
+
+struct compat_arch_shared_info {
+    unsigned int max_pfn;
+    unsigned int pfn_to_mfn_frame_list_list;
+    unsigned int nmi_reason;
+    unsigned int p2m_cr3;
+    unsigned int p2m_vaddr;
+    unsigned int p2m_generation;
+    uint32_t wc_sec_hi;
+};
+
+struct compat_shared_info {
+    struct compat_vcpu_info vcpu_info[XEN_LEGACY_MAX_VCPUS];
+    uint32_t evtchn_pending[32];
+    uint32_t evtchn_mask[32];
+    uint32_t wc_version;      /* Version counter: see vcpu_time_info_t. */
+    uint32_t wc_sec;
+    uint32_t wc_nsec;
+    struct compat_arch_shared_info arch;
+};
+
 #define COMPAT_EVTCHN_2L_NR_CHANNELS            1024
 
 /*
@@ -183,6 +219,22 @@ int xen_evtchn_set_callback_param(uint64_t param)
     return ret;
 }
 
+static void inject_callback(XenEvtchnState *s, uint32_t vcpu)
+{
+    int type = s->callback_param >> CALLBACK_VIA_TYPE_SHIFT;
+
+    if (kvm_xen_inject_vcpu_callback_vector(vcpu, type)) {
+        return;
+    }
+
+    /* GSI or PCI_INTX delivery is only for events on vCPU 0 */
+    if (vcpu) {
+        return;
+    }
+
+    /* ... and isn't implemented yet. */
+}
+
 static bool valid_port(evtchn_port_t port)
 {
     if (!port) {
@@ -253,6 +305,152 @@ int xen_evtchn_status_op(struct evtchn_status *status)
     return 0;
 }
 
+/*
+ * Never thought I'd hear myself say this, but C++ templates would be
+ * kind of nice here.
+ *
+ * template<class T> static int do_unmask_port(T *shinfo, ...);
+ */
+static int do_unmask_port_lm(XenEvtchnState *s, evtchn_port_t port,
+                             bool do_unmask, struct shared_info *shinfo,
+                             struct vcpu_info *vcpu_info)
+{
+    const int bits_per_word = BITS_PER_BYTE * sizeof(shinfo->evtchn_pending[0]);
+    typeof(shinfo->evtchn_pending[0]) mask;
+    int idx = port / bits_per_word;
+    int offset = port % bits_per_word;
+
+    mask = 1UL << offset;
+
+    if (idx >= bits_per_word) {
+        return -EINVAL;
+    }
+
+    if (do_unmask) {
+        /*
+         * If this is a true unmask operation, clear the mask bit. If
+         * it was already unmasked, we have nothing further to do.
+         */
+        if (!((qatomic_fetch_and(&shinfo->evtchn_mask[idx], ~mask) & mask))) {
+            return 0;
+        }
+    } else {
+        /*
+         * This is a pseudo-unmask for affinity changes. We don't
+         * change the mask bit, and if it's *masked* we have nothing
+         * else to do.
+         */
+        if (qatomic_fetch_or(&shinfo->evtchn_mask[idx], 0) & mask) {
+            return 0;
+        }
+    }
+
+    /* If the event was not pending, we're done. */
+    if (!(qatomic_fetch_or(&shinfo->evtchn_pending[idx], 0) & mask)) {
+        return 0;
+    }
+
+    /* Now on to the vcpu_info evtchn_pending_sel index... */
+    mask = 1UL << idx;
+
+    /* If a port in this word was already pending for this vCPU, all done. */
+    if (qatomic_fetch_or(&vcpu_info->evtchn_pending_sel, mask) & mask) {
+        return 0;
+    }
+
+    /* Set evtchn_upcall_pending for this vCPU */
+    if (qatomic_fetch_or(&vcpu_info->evtchn_upcall_pending, 1)) {
+        return 0;
+    }
+
+    inject_callback(s, s->port_table[port].vcpu);
+
+    return 0;
+}
+
+static int do_unmask_port_compat(XenEvtchnState *s, evtchn_port_t port,
+                                 bool do_unmask,
+                                 struct compat_shared_info *shinfo,
+                                 struct compat_vcpu_info *vcpu_info)
+{
+    const int bits_per_word = BITS_PER_BYTE * sizeof(shinfo->evtchn_pending[0]);
+    typeof(shinfo->evtchn_pending[0]) mask;
+    int idx = port / bits_per_word;
+    int offset = port % bits_per_word;
+
+    mask = 1UL << offset;
+
+    if (idx >= bits_per_word) {
+        return -EINVAL;
+    }
+
+    if (do_unmask) {
+        /*
+         * If this is a true unmask operation, clear the mask bit. If
+         * it was already unmasked, we have nothing further to do.
+         */
+        if (!((qatomic_fetch_and(&shinfo->evtchn_mask[idx], ~mask) & mask))) {
+            return 0;
+        }
+    } else {
+        /*
+         * This is a pseudo-unmask for affinity changes. We don't
+         * change the mask bit, and if it's *masked* we have nothing
+         * else to do.
+         */
+        if (qatomic_fetch_or(&shinfo->evtchn_mask[idx], 0) & mask) {
+            return 0;
+        }
+    }
+
+    /* If the event was not pending, we're done. */
+    if (!(qatomic_fetch_or(&shinfo->evtchn_pending[idx], 0) & mask)) {
+        return 0;
+    }
+
+    /* Now on to the vcpu_info evtchn_pending_sel index... */
+    mask = 1UL << idx;
+
+    /* If a port in this word was already pending for this vCPU, all done. */
+    if (qatomic_fetch_or(&vcpu_info->evtchn_pending_sel, mask) & mask) {
+        return 0;
+    }
+
+    /* Set evtchn_upcall_pending for this vCPU */
+    if (qatomic_fetch_or(&vcpu_info->evtchn_upcall_pending, 1)) {
+        return 0;
+    }
+
+    inject_callback(s, s->port_table[port].vcpu);
+
+    return 0;
+}
+
+static int unmask_port(XenEvtchnState *s, evtchn_port_t port, bool do_unmask)
+{
+    void *vcpu_info, *shinfo;
+
+    if (s->port_table[port].type == EVTCHNSTAT_closed) {
+        return -EINVAL;
+    }
+
+    shinfo = xen_overlay_get_shinfo_ptr();
+    if (!shinfo) {
+        return -ENOTSUP;
+    }
+
+    vcpu_info = kvm_xen_get_vcpu_info_hva(s->port_table[port].vcpu);
+    if (!vcpu_info) {
+        return -EINVAL;
+    }
+
+    if (xen_is_long_mode()) {
+        return do_unmask_port_lm(s, port, do_unmask, shinfo, vcpu_info);
+    } else {
+        return do_unmask_port_compat(s, port, do_unmask, shinfo, vcpu_info);
+    }
+}
+
 static void free_port(XenEvtchnState *s, evtchn_port_t port)
 {
     s->port_table[port].type = EVTCHNSTAT_closed;
@@ -303,3 +501,25 @@ int xen_evtchn_close_op(struct evtchn_close *close)
 
     return ret;
 }
+
+int xen_evtchn_unmask_op(struct evtchn_unmask *unmask)
+{
+    XenEvtchnState *s = xen_evtchn_singleton;
+    int ret;
+
+    if (!s) {
+        return -ENOTSUP;
+    }
+
+    if (!valid_port(unmask->port)) {
+        return -EINVAL;
+    }
+
+    qemu_mutex_lock(&s->port_lock);
+
+    ret = unmask_port(s, unmask->port, true);
+
+    qemu_mutex_unlock(&s->port_lock);
+
+    return ret;
+}
diff --git a/hw/i386/kvm/xen_evtchn.h b/hw/i386/kvm/xen_evtchn.h
index cb3924941a..69c6b0d743 100644
--- a/hw/i386/kvm/xen_evtchn.h
+++ b/hw/i386/kvm/xen_evtchn.h
@@ -17,7 +17,9 @@ int xen_evtchn_set_callback_param(uint64_t param);
 
 struct evtchn_status;
 struct evtchn_close;
+struct evtchn_unmask;
 int xen_evtchn_status_op(struct evtchn_status *status);
 int xen_evtchn_close_op(struct evtchn_close *close);
+int xen_evtchn_unmask_op(struct evtchn_unmask *unmask);
 
 #endif /* QEMU_XEN_EVTCHN_H */
diff --git a/target/i386/kvm/xen-emu.c b/target/i386/kvm/xen-emu.c
index a81dbf5b63..c218696fe4 100644
--- a/target/i386/kvm/xen-emu.c
+++ b/target/i386/kvm/xen-emu.c
@@ -802,6 +802,18 @@ static bool kvm_xen_hcall_evtchn_op(struct kvm_xen_exit *exit, X86CPU *cpu,
         err = xen_evtchn_close_op(&close);
         break;
     }
+    case EVTCHNOP_unmask: {
+        struct evtchn_unmask unmask;
+
+        qemu_build_assert(sizeof(unmask) == 4);
+        if (kvm_copy_from_gva(cs, arg, &unmask, sizeof(unmask))) {
+            err = -EFAULT;
+            break;
+        }
+
+        err = xen_evtchn_unmask_op(&unmask);
+        break;
+    }
     default:
         return false;
     }
-- 
2.35.3