Merge tag 'for-upstream' of https://gitlab.com/bonzini/qemu into staging

* tcg/s390x: Fix for TSTEQ/TSTNE
* target/i386: Fixes for IN and OUT with REX prefix
* target/i386: New CPUID features and logic fixes
* target/i386: Add support save/load HWCR MSR
* target/i386: Move more instructions to new decoder; separate decoding
  and IR generation
* target/i386/tcg: Use DPL-level accesses for interrupts and call gates
* accel/kvm: perform capability checks on VM file descriptor when necessary
* accel/kvm: dynamically sized kvm memslots array
* target/i386: fixes for Hyper-V
* docs/system: Add recommendations to Hyper-V enlightenments doc

# -----BEGIN PGP SIGNATURE-----
#
# iQFIBAABCAAyFiEE8TM4V0tmI4mGbHaCv/vSX3jHroMFAmcRTIoUHHBib256aW5p
# QHJlZGhhdC5jb20ACgkQv/vSX3jHroMCewf8DnZbz7/0beql2YycrdPJZ3xnmfWW
# JenWKIThKHGWRTW2ODsac21n0TNXE0vsOYjw/Z/dNLO+72sLcqvmEB18+dpHAD2J
# ltb8OvuROc3nn64OEi08qIj7JYLmJ/osroI+6NnZrCOHo8nCirXoCHB7ZPqAE7/n
# yDnownWaduXmXt3+Vs1mpqlBklcClxaURDDEQ8CGsxjC3jW03cno6opJPZpJqk0t
# 6aX92vX+3lNhIlije3QESsDX0cP1CFnQmQlNNg/xzk+ZQO+vSRrPV+A/N9xf8m1b
# HiaCrlBWYef/sLgOHziOSrJV5/N8W0GDEVYDmpEswHE81BZxrOTZLxqzWw==
# =qwfc
# -----END PGP SIGNATURE-----
# gpg: Signature made Thu 17 Oct 2024 18:42:34 BST
# gpg:                using RSA key F13338574B662389866C7682BFFBD25F78C7AE83
# gpg:                issuer "pbonzini@redhat.com"
# gpg: Good signature from "Paolo Bonzini <bonzini@gnu.org>" [full]
# gpg:                 aka "Paolo Bonzini <pbonzini@redhat.com>" [full]
# Primary key fingerprint: 46F5 9FBD 57D6 12E7 BFD4  E2F7 7E15 100C CD36 69B1
#      Subkey fingerprint: F133 3857 4B66 2389 866C  7682 BFFB D25F 78C7 AE83

* tag 'for-upstream' of https://gitlab.com/bonzini/qemu: (26 commits)
  target/i386: Use only 16 and 32-bit operands for IN/OUT
  accel/kvm: check for KVM_CAP_MEMORY_ATTRIBUTES on vm
  accel/kvm: check for KVM_CAP_MULTI_ADDRESS_SPACE on vm
  accel/kvm: check for KVM_CAP_READONLY_MEM on VM
  target/i386/tcg: Use DPL-level accesses for interrupts and call gates
  KVM: Rename KVMState->nr_slots to nr_slots_max
  KVM: Rename KVMMemoryListener.nr_used_slots to nr_slots_used
  KVM: Define KVM_MEMSLOTS_NUM_MAX_DEFAULT
  KVM: Dynamic sized kvm memslots array
  target/i386: assert that cc_op* and pc_save are preserved
  target/i386: list instructions still in translate.c
  target/i386: do not check PREFIX_LOCK in old-style decoder
  target/i386: convert CMPXCHG8B/CMPXCHG16B to new decoder
  target/i386: decode address before going back to translate.c
  target/i386: convert bit test instructions to new decoder
  tcg/s390x: fix constraint for 32-bit TSTEQ/TSTNE
  docs/system: Add recommendations to Hyper-V enlightenments doc
  target/i386: Make sure SynIC state is really updated before KVM_RUN
  target/i386: Exclude 'hv-syndbg' from 'hv-passthrough'
  target/i386: Fix conditional CONFIG_SYNDBG enablement
  ...

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

1 files changed, 95 insertions, 36 deletions

diff --git a/accel/kvm/kvm-all.c b/accel/kvm/kvm-all.c
index 905fb844e4..801cff16a5 100644
--- a/accel/kvm/kvm-all.c
+++ b/accel/kvm/kvm-all.c
@@ -69,6 +69,11 @@
 #define KVM_GUESTDBG_BLOCKIRQ 0
 #endif
 
+/* Default num of memslots to be allocated when VM starts */
+#define  KVM_MEMSLOTS_NR_ALLOC_DEFAULT                      16
+/* Default max allowed memslots if kernel reported nothing */
+#define  KVM_MEMSLOTS_NR_MAX_DEFAULT                        32
+
 struct KVMParkedVcpu {
     unsigned long vcpu_id;
     int kvm_fd;
@@ -165,11 +170,62 @@ void kvm_resample_fd_notify(int gsi)
     }
 }
 
+/**
+ * kvm_slots_grow(): Grow the slots[] array in the KVMMemoryListener
+ *
+ * @kml: The KVMMemoryListener* to grow the slots[] array
+ * @nr_slots_new: The new size of slots[] array
+ *
+ * Returns: True if the array grows larger, false otherwise.
+ */
+static bool kvm_slots_grow(KVMMemoryListener *kml, unsigned int nr_slots_new)
+{
+    unsigned int i, cur = kml->nr_slots_allocated;
+    KVMSlot *slots;
+
+    if (nr_slots_new > kvm_state->nr_slots_max) {
+        nr_slots_new = kvm_state->nr_slots_max;
+    }
+
+    if (cur >= nr_slots_new) {
+        /* Big enough, no need to grow, or we reached max */
+        return false;
+    }
+
+    if (cur == 0) {
+        slots = g_new0(KVMSlot, nr_slots_new);
+    } else {
+        assert(kml->slots);
+        slots = g_renew(KVMSlot, kml->slots, nr_slots_new);
+        /*
+         * g_renew() doesn't initialize extended buffers, however kvm
+         * memslots require fields to be zero-initialized. E.g. pointers,
+         * memory_size field, etc.
+         */
+        memset(&slots[cur], 0x0, sizeof(slots[0]) * (nr_slots_new - cur));
+    }
+
+    for (i = cur; i < nr_slots_new; i++) {
+        slots[i].slot = i;
+    }
+
+    kml->slots = slots;
+    kml->nr_slots_allocated = nr_slots_new;
+    trace_kvm_slots_grow(cur, nr_slots_new);
+
+    return true;
+}
+
+static bool kvm_slots_double(KVMMemoryListener *kml)
+{
+    return kvm_slots_grow(kml, kml->nr_slots_allocated * 2);
+}
+
 unsigned int kvm_get_max_memslots(void)
 {
     KVMState *s = KVM_STATE(current_accel());
 
-    return s->nr_slots;
+    return s->nr_slots_max;
 }
 
 unsigned int kvm_get_free_memslots(void)
@@ -183,25 +239,36 @@ unsigned int kvm_get_free_memslots(void)
         if (!s->as[i].ml) {
             continue;
         }
-        used_slots = MAX(used_slots, s->as[i].ml->nr_used_slots);
+        used_slots = MAX(used_slots, s->as[i].ml->nr_slots_used);
     }
     kvm_slots_unlock();
 
-    return s->nr_slots - used_slots;
+    return s->nr_slots_max - used_slots;
 }
 
 /* Called with KVMMemoryListener.slots_lock held */
 static KVMSlot *kvm_get_free_slot(KVMMemoryListener *kml)
 {
-    KVMState *s = kvm_state;
+    unsigned int n;
     int i;
 
-    for (i = 0; i < s->nr_slots; i++) {
+    for (i = 0; i < kml->nr_slots_allocated; i++) {
         if (kml->slots[i].memory_size == 0) {
             return &kml->slots[i];
         }
     }
 
+    /*
+     * If no free slots, try to grow first by doubling.  Cache the old size
+     * here to avoid another round of search: if the grow succeeded, it
+     * means slots[] now must have the existing "n" slots occupied,
+     * followed by one or more free slots starting from slots[n].
+     */
+    n = kml->nr_slots_allocated;
+    if (kvm_slots_double(kml)) {
+        return &kml->slots[n];
+    }
+
     return NULL;
 }
 
@@ -222,10 +289,9 @@ static KVMSlot *kvm_lookup_matching_slot(KVMMemoryListener *kml,
                                          hwaddr start_addr,
                                          hwaddr size)
 {
-    KVMState *s = kvm_state;
     int i;
 
-    for (i = 0; i < s->nr_slots; i++) {
+    for (i = 0; i < kml->nr_slots_allocated; i++) {
         KVMSlot *mem = &kml->slots[i];
 
         if (start_addr == mem->start_addr && size == mem->memory_size) {
@@ -267,7 +333,7 @@ int kvm_physical_memory_addr_from_host(KVMState *s, void *ram,
     int i, ret = 0;
 
     kvm_slots_lock();
-    for (i = 0; i < s->nr_slots; i++) {
+    for (i = 0; i < kml->nr_slots_allocated; i++) {
         KVMSlot *mem = &kml->slots[i];
 
         if (ram >= mem->ram && ram < mem->ram + mem->memory_size) {
@@ -1071,7 +1137,7 @@ static int kvm_physical_log_clear(KVMMemoryListener *kml,
 
     kvm_slots_lock();
 
-    for (i = 0; i < s->nr_slots; i++) {
+    for (i = 0; i < kml->nr_slots_allocated; i++) {
         mem = &kml->slots[i];
         /* Discard slots that are empty or do not overlap the section */
         if (!mem->memory_size ||
@@ -1450,7 +1516,7 @@ static void kvm_set_phys_mem(KVMMemoryListener *kml,
             }
             start_addr += slot_size;
             size -= slot_size;
-            kml->nr_used_slots--;
+            kml->nr_slots_used--;
         } while (size);
         return;
     }
@@ -1489,7 +1555,7 @@ static void kvm_set_phys_mem(KVMMemoryListener *kml,
         ram_start_offset += slot_size;
         ram += slot_size;
         size -= slot_size;
-        kml->nr_used_slots++;
+        kml->nr_slots_used++;
     } while (size);
 }
 
@@ -1715,12 +1781,8 @@ static void kvm_log_sync_global(MemoryListener *l, bool last_stage)
     /* Flush all kernel dirty addresses into KVMSlot dirty bitmap */
     kvm_dirty_ring_flush();
 
-    /*
-     * TODO: make this faster when nr_slots is big while there are
-     * only a few used slots (small VMs).
-     */
     kvm_slots_lock();
-    for (i = 0; i < s->nr_slots; i++) {
+    for (i = 0; i < kml->nr_slots_allocated; i++) {
         mem = &kml->slots[i];
         if (mem->memory_size && mem->flags & KVM_MEM_LOG_DIRTY_PAGES) {
             kvm_slot_sync_dirty_pages(mem);
@@ -1835,12 +1897,9 @@ void kvm_memory_listener_register(KVMState *s, KVMMemoryListener *kml,
 {
     int i;
 
-    kml->slots = g_new0(KVMSlot, s->nr_slots);
     kml->as_id = as_id;
 
-    for (i = 0; i < s->nr_slots; i++) {
-        kml->slots[i].slot = i;
-    }
+    kvm_slots_grow(kml, KVM_MEMSLOTS_NR_ALLOC_DEFAULT);
 
     QSIMPLEQ_INIT(&kml->transaction_add);
     QSIMPLEQ_INIT(&kml->transaction_del);
@@ -2545,26 +2604,14 @@ static int kvm_init(MachineState *ms)
         goto err;
     }
 
-    kvm_supported_memory_attributes = kvm_check_extension(s, KVM_CAP_MEMORY_ATTRIBUTES);
-    kvm_guest_memfd_supported =
-        kvm_check_extension(s, KVM_CAP_GUEST_MEMFD) &&
-        kvm_check_extension(s, KVM_CAP_USER_MEMORY2) &&
-        (kvm_supported_memory_attributes & KVM_MEMORY_ATTRIBUTE_PRIVATE);
-
     kvm_immediate_exit = kvm_check_extension(s, KVM_CAP_IMMEDIATE_EXIT);
-    s->nr_slots = kvm_check_extension(s, KVM_CAP_NR_MEMSLOTS);
+    s->nr_slots_max = kvm_check_extension(s, KVM_CAP_NR_MEMSLOTS);
 
     /* If unspecified, use the default value */
-    if (!s->nr_slots) {
-        s->nr_slots = 32;
+    if (!s->nr_slots_max) {
+        s->nr_slots_max = KVM_MEMSLOTS_NR_MAX_DEFAULT;
     }
 
-    s->nr_as = kvm_check_extension(s, KVM_CAP_MULTI_ADDRESS_SPACE);
-    if (s->nr_as <= 1) {
-        s->nr_as = 1;
-    }
-    s->as = g_new0(struct KVMAs, s->nr_as);
-
     type = find_kvm_machine_type(ms);
     if (type < 0) {
         ret = -EINVAL;
@@ -2578,6 +2625,12 @@ static int kvm_init(MachineState *ms)
 
     s->vmfd = ret;
 
+    s->nr_as = kvm_vm_check_extension(s, KVM_CAP_MULTI_ADDRESS_SPACE);
+    if (s->nr_as <= 1) {
+        s->nr_as = 1;
+    }
+    s->as = g_new0(struct KVMAs, s->nr_as);
+
     /* check the vcpu limits */
     soft_vcpus_limit = kvm_recommended_vcpus(s);
     hard_vcpus_limit = kvm_max_vcpus(s);
@@ -2630,7 +2683,7 @@ static int kvm_init(MachineState *ms)
     }
 
     kvm_readonly_mem_allowed =
-        (kvm_check_extension(s, KVM_CAP_READONLY_MEM) > 0);
+        (kvm_vm_check_extension(s, KVM_CAP_READONLY_MEM) > 0);
 
     kvm_resamplefds_allowed =
         (kvm_check_extension(s, KVM_CAP_IRQFD_RESAMPLE) > 0);
@@ -2664,6 +2717,12 @@ static int kvm_init(MachineState *ms)
         goto err;
     }
 
+    kvm_supported_memory_attributes = kvm_vm_check_extension(s, KVM_CAP_MEMORY_ATTRIBUTES);
+    kvm_guest_memfd_supported =
+        kvm_check_extension(s, KVM_CAP_GUEST_MEMFD) &&
+        kvm_check_extension(s, KVM_CAP_USER_MEMORY2) &&
+        (kvm_supported_memory_attributes & KVM_MEMORY_ATTRIBUTE_PRIVATE);
+
     if (s->kernel_irqchip_split == ON_OFF_AUTO_AUTO) {
         s->kernel_irqchip_split = mc->default_kernel_irqchip_split ? ON_OFF_AUTO_ON : ON_OFF_AUTO_OFF;
     }