Merge tag 'exec-20241220' of https://github.com/philmd/qemu into staging

Accel & Exec patch queue

- Ignore writes to CNTP_CTL_EL0 on HVF ARM (Alexander)
- Add '-d invalid_mem' logging option (Zoltan)
- Create QOM containers explicitly (Peter)
- Rename sysemu/ -> system/ (Philippe)
- Re-orderning of include/exec/ headers (Philippe)
  Move a lot of declarations from these legacy mixed bag headers:
    . "exec/cpu-all.h"
    . "exec/cpu-common.h"
    . "exec/cpu-defs.h"
    . "exec/exec-all.h"
    . "exec/translate-all"
  to these more specific ones:
    . "exec/page-protection.h"
    . "exec/translation-block.h"
    . "user/cpu_loop.h"
    . "user/guest-host.h"
    . "user/page-protection.h"

 # -----BEGIN PGP SIGNATURE-----
 #
 # iQIzBAABCAAdFiEE+qvnXhKRciHc/Wuy4+MsLN6twN4FAmdlnyAACgkQ4+MsLN6t
 # wN6mBw//QFWi7CrU+bb8KMM53kOU9C507tjn99LLGFb5or73/umDsw6eo/b8DHBt
 # KIwGLgATel42oojKfNKavtAzLK5rOrywpboPDpa3SNeF1onW+99NGJ52LQUqIX6K
 # A6bS0fPdGG9ZzEuPpbjDXlp++0yhDcdSgZsS42fEsT7Dyj5gzJYlqpqhiXGqpsn8
 # 4Y0UMxSL21K3HEexlzw2hsoOBFA3tUm2ujNDhNkt8QASr85yQVLCypABJnuoe///
 # 5Ojl5wTBeDwhANET0rhwHK8eIYaNboiM9fHopJYhvyw1bz6yAu9jQwzF/MrL3s/r
 # xa4OBHBy5mq2hQV9Shcl3UfCQdk/vDaYaWpgzJGX8stgMGYfnfej1SIl8haJIfcl
 # VMX8/jEFdYbjhO4AeGRYcBzWjEJymkDJZoiSWp2NuEDi6jqIW+7yW1q0Rnlg9lay
 # ShAqLK5Pv4zUw3t0Jy3qv9KSW8sbs6PQxtzXjk8p97rTf76BJ2pF8sv1tVzmsidP
 # 9L92Hv5O34IqzBu2oATOUZYJk89YGmTIUSLkpT7asJZpBLwNM2qLp5jO00WVU0Sd
 # +kAn324guYPkko/TVnjC/AY7CMu55EOtD9NU35k3mUAnxXT9oDUeL4NlYtfgrJx6
 # x1Nzr2FkS68+wlPAFKNSSU5lTjsjNaFM0bIJ4LCNtenJVP+SnRo=
 # =cjz8
 # -----END PGP SIGNATURE-----
 # gpg: Signature made Fri 20 Dec 2024 11:45:20 EST
 # gpg:                using RSA key FAABE75E12917221DCFD6BB2E3E32C2CDEADC0DE
 # gpg: Good signature from "Philippe Mathieu-Daudé (F4BUG) <f4bug@amsat.org>" [unknown]
 # gpg: WARNING: This key is not certified with a trusted signature!
 # gpg:          There is no indication that the signature belongs to the owner.
 # Primary key fingerprint: FAAB E75E 1291 7221 DCFD  6BB2 E3E3 2C2C DEAD C0DE

* tag 'exec-20241220' of https://github.com/philmd/qemu: (59 commits)
  util/qemu-timer: fix indentation
  meson: Do not define CONFIG_DEVICES on user emulation
  system/accel-ops: Remove unnecessary 'exec/cpu-common.h' header
  system/numa: Remove unnecessary 'exec/cpu-common.h' header
  hw/xen: Remove unnecessary 'exec/cpu-common.h' header
  target/mips: Drop left-over comment about Jazz machine
  target/mips: Remove tswap() calls in semihosting uhi_fstat_cb()
  target/xtensa: Remove tswap() calls in semihosting simcall() helper
  accel/tcg: Un-inline translator_is_same_page()
  accel/tcg: Include missing 'exec/translation-block.h' header
  accel/tcg: Move tcg_cflags_has/set() to 'exec/translation-block.h'
  accel/tcg: Restrict curr_cflags() declaration to 'internal-common.h'
  qemu/coroutine: Include missing 'qemu/atomic.h' header
  exec/translation-block: Include missing 'qemu/atomic.h' header
  accel/tcg: Declare cpu_loop_exit_requested() in 'exec/cpu-common.h'
  exec/cpu-all: Include 'cpu.h' earlier so MMU_USER_IDX is always defined
  target/sparc: Move sparc_restore_state_to_opc() to cpu.c
  target/sparc: Uninline cpu_get_tb_cpu_state()
  target/loongarch: Declare loongarch_cpu_dump_state() locally
  user: Move various declarations out of 'exec/exec-all.h'
  ...

Conflicts:
	hw/char/riscv_htif.c
	hw/intc/riscv_aplic.c
	target/s390x/cpu.c

	Apply sysemu header path changes to not in the pull request.

Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>

1 files changed, 187 insertions, 0 deletions

diff --git a/include/system/kvm_int.h b/include/system/kvm_int.h
new file mode 100644
index 0000000000..4de6106869
--- /dev/null
+++ b/include/system/kvm_int.h
@@ -0,0 +1,187 @@
+/*
+ * Internal definitions for a target's KVM support
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ *
+ */
+
+#ifndef QEMU_KVM_INT_H
+#define QEMU_KVM_INT_H
+
+#include "exec/memory.h"
+#include "qapi/qapi-types-common.h"
+#include "qemu/accel.h"
+#include "qemu/queue.h"
+#include "system/kvm.h"
+#include "hw/boards.h"
+#include "hw/i386/topology.h"
+#include "io/channel-socket.h"
+
+typedef struct KVMSlot
+{
+    hwaddr start_addr;
+    ram_addr_t memory_size;
+    void *ram;
+    int slot;
+    int flags;
+    int old_flags;
+    /* Dirty bitmap cache for the slot */
+    unsigned long *dirty_bmap;
+    unsigned long dirty_bmap_size;
+    /* Cache of the address space ID */
+    int as_id;
+    /* Cache of the offset in ram address space */
+    ram_addr_t ram_start_offset;
+    int guest_memfd;
+    hwaddr guest_memfd_offset;
+} KVMSlot;
+
+typedef struct KVMMemoryUpdate {
+    QSIMPLEQ_ENTRY(KVMMemoryUpdate) next;
+    MemoryRegionSection section;
+} KVMMemoryUpdate;
+
+typedef struct KVMMemoryListener {
+    MemoryListener listener;
+    KVMSlot *slots;
+    unsigned int nr_slots_used;
+    unsigned int nr_slots_allocated;
+    int as_id;
+    QSIMPLEQ_HEAD(, KVMMemoryUpdate) transaction_add;
+    QSIMPLEQ_HEAD(, KVMMemoryUpdate) transaction_del;
+} KVMMemoryListener;
+
+#define KVM_MSI_HASHTAB_SIZE    256
+
+typedef struct KVMHostTopoInfo {
+    /* Number of package on the Host */
+    unsigned int maxpkgs;
+    /* Number of cpus on the Host */
+    unsigned int maxcpus;
+    /* Number of cpus on each different package */
+    unsigned int *pkg_cpu_count;
+    /* Each package can have different maxticks */
+    unsigned int *maxticks;
+} KVMHostTopoInfo;
+
+struct KVMMsrEnergy {
+    pid_t pid;
+    bool enable;
+    char *socket_path;
+    QIOChannelSocket *sioc;
+    QemuThread msr_thr;
+    unsigned int guest_vcpus;
+    unsigned int guest_vsockets;
+    X86CPUTopoInfo guest_topo_info;
+    KVMHostTopoInfo host_topo;
+    const CPUArchIdList *guest_cpu_list;
+    uint64_t *msr_value;
+    uint64_t msr_unit;
+    uint64_t msr_limit;
+    uint64_t msr_info;
+};
+
+enum KVMDirtyRingReaperState {
+    KVM_DIRTY_RING_REAPER_NONE = 0,
+    /* The reaper is sleeping */
+    KVM_DIRTY_RING_REAPER_WAIT,
+    /* The reaper is reaping for dirty pages */
+    KVM_DIRTY_RING_REAPER_REAPING,
+};
+
+/*
+ * KVM reaper instance, responsible for collecting the KVM dirty bits
+ * via the dirty ring.
+ */
+struct KVMDirtyRingReaper {
+    /* The reaper thread */
+    QemuThread reaper_thr;
+    volatile uint64_t reaper_iteration; /* iteration number of reaper thr */
+    volatile enum KVMDirtyRingReaperState reaper_state; /* reap thr state */
+};
+struct KVMState
+{
+    AccelState parent_obj;
+    /* Max number of KVM slots supported */
+    int nr_slots_max;
+    int fd;
+    int vmfd;
+    int coalesced_mmio;
+    int coalesced_pio;
+    struct kvm_coalesced_mmio_ring *coalesced_mmio_ring;
+    bool coalesced_flush_in_progress;
+    int vcpu_events;
+#ifdef TARGET_KVM_HAVE_GUEST_DEBUG
+    QTAILQ_HEAD(, kvm_sw_breakpoint) kvm_sw_breakpoints;
+#endif
+    int max_nested_state_len;
+    int kvm_shadow_mem;
+    bool kernel_irqchip_allowed;
+    bool kernel_irqchip_required;
+    OnOffAuto kernel_irqchip_split;
+    bool sync_mmu;
+    bool guest_state_protected;
+    uint64_t manual_dirty_log_protect;
+    /*
+     * Older POSIX says that ioctl numbers are signed int, but in
+     * practice they are not. (Newer POSIX doesn't specify ioctl
+     * at all.) Linux, glibc and *BSD all treat ioctl numbers as
+     * unsigned, and real-world ioctl values like KVM_GET_XSAVE have
+     * bit 31 set, which means that passing them via an 'int' will
+     * result in sign-extension when they get converted back to the
+     * 'unsigned long' which the ioctl() prototype uses. Luckily Linux
+     * always treats the argument as an unsigned 32-bit int, so any
+     * possible sign-extension is deliberately ignored, but for
+     * consistency we keep to the same type that glibc is using.
+     */
+    unsigned long irq_set_ioctl;
+    unsigned int sigmask_len;
+    GHashTable *gsimap;
+#ifdef KVM_CAP_IRQ_ROUTING
+    struct kvm_irq_routing *irq_routes;
+    int nr_allocated_irq_routes;
+    unsigned long *used_gsi_bitmap;
+    unsigned int gsi_count;
+#endif
+    KVMMemoryListener memory_listener;
+    QLIST_HEAD(, KVMParkedVcpu) kvm_parked_vcpus;
+
+    /* For "info mtree -f" to tell if an MR is registered in KVM */
+    int nr_as;
+    struct KVMAs {
+        KVMMemoryListener *ml;
+        AddressSpace *as;
+    } *as;
+    uint64_t kvm_dirty_ring_bytes;  /* Size of the per-vcpu dirty ring */
+    uint32_t kvm_dirty_ring_size;   /* Number of dirty GFNs per ring */
+    bool kvm_dirty_ring_with_bitmap;
+    uint64_t kvm_eager_split_size;  /* Eager Page Splitting chunk size */
+    struct KVMDirtyRingReaper reaper;
+    struct KVMMsrEnergy msr_energy;
+    NotifyVmexitOption notify_vmexit;
+    uint32_t notify_window;
+    uint32_t xen_version;
+    uint32_t xen_caps;
+    uint16_t xen_gnttab_max_frames;
+    uint16_t xen_evtchn_max_pirq;
+    char *device;
+};
+
+void kvm_memory_listener_register(KVMState *s, KVMMemoryListener *kml,
+                                  AddressSpace *as, int as_id, const char *name);
+
+void kvm_set_max_memslot_size(hwaddr max_slot_size);
+
+/**
+ * kvm_hwpoison_page_add:
+ *
+ * Parameters:
+ *  @ram_addr: the address in the RAM for the poisoned page
+ *
+ * Add a poisoned page to the list
+ *
+ * Return: None.
+ */
+void kvm_hwpoison_page_add(ram_addr_t ram_addr);
+#endif