hpet: make main counter read lock-less

Make access to main HPET counter lock-less.

In unlikely event of an update in progress, readers will busy wait
untill update is finished.

As result micro benchmark of concurrent reading of HPET counter
with large number of vCPU shows over 80% better (less) latency.

Signed-off-by: Igor Mammedov <imammedo@redhat.com>
Reviewed-by: Peter Xu <peterx@redhat.com>
Link: https://lore.kernel.org/r/20250814160600.2327672-6-imammedo@redhat.com
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

1 files changed, 20 insertions, 6 deletions

diff --git a/hw/timer/hpet.c b/hw/timer/hpet.c
index c776afc0f2..789a31d0a0 100644
--- a/hw/timer/hpet.c
+++ b/hw/timer/hpet.c
@@ -39,6 +39,7 @@
 #include "system/address-spaces.h"
 #include "qom/object.h"
 #include "qemu/lockable.h"
+#include "qemu/seqlock.h"
 #include "trace.h"
 
 struct hpet_fw_config hpet_fw_cfg = {.count = UINT8_MAX};
@@ -74,6 +75,7 @@ struct HPETState {
     MemoryRegion iomem;
     uint64_t hpet_offset;
     bool hpet_offset_saved;
+    QemuSeqLock state_version;
     qemu_irq irqs[HPET_NUM_IRQ_ROUTES];
     uint32_t flags;
     uint8_t rtc_irq_level;
@@ -430,17 +432,25 @@ static uint64_t hpet_ram_read(void *opaque, hwaddr addr,
     trace_hpet_ram_read(addr);
     addr &= ~4;
 
-    QEMU_LOCK_GUARD(&s->lock);
     if (addr == HPET_COUNTER) {
-        if (hpet_enabled(s)) {
-            cur_tick = hpet_get_ticks(s);
-        } else {
-            cur_tick = s->hpet_counter;
-        }
+        unsigned version;
+
+        /*
+         * Write update is rare, so busywait here is unlikely to happen
+         */
+        do {
+            version = seqlock_read_begin(&s->state_version);
+            if (unlikely(!hpet_enabled(s))) {
+                cur_tick = s->hpet_counter;
+            } else {
+                cur_tick = hpet_get_ticks(s);
+            }
+        } while (seqlock_read_retry(&s->state_version, version));
         trace_hpet_ram_read_reading_counter(addr & 4, cur_tick);
         return cur_tick >> shift;
     }
 
+    QEMU_LOCK_GUARD(&s->lock);
     /*address range of all global regs*/
     if (addr <= 0xff) {
         switch (addr) {
@@ -500,6 +510,7 @@ static void hpet_ram_write(void *opaque, hwaddr addr,
             old_val = s->config;
             new_val = deposit64(old_val, shift, len, value);
             new_val = hpet_fixup_reg(new_val, old_val, HPET_CFG_WRITE_MASK);
+            seqlock_write_begin(&s->state_version);
             s->config = new_val;
             if (activating_bit(old_val, new_val, HPET_CFG_ENABLE)) {
                 /* Enable main counter and interrupt generation. */
@@ -518,6 +529,8 @@ static void hpet_ram_write(void *opaque, hwaddr addr,
                     hpet_del_timer(&s->timer[i]);
                 }
             }
+            seqlock_write_end(&s->state_version);
+
             /* i8254 and RTC output pins are disabled
              * when HPET is in legacy mode */
             if (activating_bit(old_val, new_val, HPET_CFG_LEGACY)) {
@@ -686,6 +699,7 @@ static void hpet_init(Object *obj)
     HPETState *s = HPET(obj);
 
     qemu_mutex_init(&s->lock);
+    seqlock_init(&s->state_version);
     /* HPET Area */
     memory_region_init_io(&s->iomem, obj, &hpet_ram_ops, s, "hpet", HPET_LEN);
     memory_region_enable_lockless_io(&s->iomem);