[PATCH 2/3] softmmu: Use async_run_on_cpu in tcg_commit

[Richard Henderson <richard.henderson@linaro.org>]

After system startup, run the update to memory_dispatch
and the tlb_flush on the cpu.  This eliminates a race,
wherein a running cpu sees the memory_dispatch change
but has not yet seen the tlb_flush.

Since the update now happens on the cpu, we need not use
qatomic_rcu_read to protect the read of memory_dispatch.

Resolves: https://gitlab.com/qemu-project/qemu/-/issues/1826
Resolves: https://gitlab.com/qemu-project/qemu/-/issues/1834
Resolves: https://gitlab.com/qemu-project/qemu/-/issues/1846
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
 softmmu/physmem.c | 40 +++++++++++++++++++++++++++++-----------
 1 file changed, 29 insertions(+), 11 deletions(-)

diff --git a/softmmu/physmem.c b/softmmu/physmem.c
index 7597dc1c39..18277ddd67 100644
--- a/softmmu/physmem.c
+++ b/softmmu/physmem.c
@@ -680,8 +680,7 @@ address_space_translate_for_iotlb(CPUState *cpu, int asidx, hwaddr orig_addr,
     IOMMUTLBEntry iotlb;
     int iommu_idx;
     hwaddr addr = orig_addr;
-    AddressSpaceDispatch *d =
-        qatomic_rcu_read(&cpu->cpu_ases[asidx].memory_dispatch);
+    AddressSpaceDispatch *d = cpu->cpu_ases[asidx].memory_dispatch;
 
     for (;;) {
         section = address_space_translate_internal(d, addr, &addr, plen, false);
@@ -2412,7 +2411,7 @@ MemoryRegionSection *iotlb_to_section(CPUState *cpu,
 {
     int asidx = cpu_asidx_from_attrs(cpu, attrs);
     CPUAddressSpace *cpuas = &cpu->cpu_ases[asidx];
-    AddressSpaceDispatch *d = qatomic_rcu_read(&cpuas->memory_dispatch);
+    AddressSpaceDispatch *d = cpuas->memory_dispatch;
     int section_index = index & ~TARGET_PAGE_MASK;
     MemoryRegionSection *ret;
 
@@ -2487,23 +2486,42 @@ static void tcg_log_global_after_sync(MemoryListener *listener)
     }
 }
 
+static void tcg_commit_cpu(CPUState *cpu, run_on_cpu_data data)
+{
+    CPUAddressSpace *cpuas = data.host_ptr;
+
+    cpuas->memory_dispatch = address_space_to_dispatch(cpuas->as);
+    tlb_flush(cpu);
+}
+
 static void tcg_commit(MemoryListener *listener)
 {
     CPUAddressSpace *cpuas;
-    AddressSpaceDispatch *d;
+    CPUState *cpu;
 
     assert(tcg_enabled());
     /* since each CPU stores ram addresses in its TLB cache, we must
        reset the modified entries */
     cpuas = container_of(listener, CPUAddressSpace, tcg_as_listener);
-    cpu_reloading_memory_map();
-    /* The CPU and TLB are protected by the iothread lock.
-     * We reload the dispatch pointer now because cpu_reloading_memory_map()
-     * may have split the RCU critical section.
+    cpu = cpuas->cpu;
+
+    /*
+     * Defer changes to as->memory_dispatch until the cpu is quiescent.
+     * Otherwise we race between (1) other cpu threads and (2) ongoing
+     * i/o for the current cpu thread, with data cached by mmu_lookup().
+     *
+     * In addition, queueing the work function will kick the cpu back to
+     * the main loop, which will end the RCU critical section and reclaim
+     * the memory data structures.
+     *
+     * That said, the listener is also called during realize, before
+     * all of the tcg machinery for run-on is initialized: thus halt_cond.
      */
-    d = address_space_to_dispatch(cpuas->as);
-    qatomic_rcu_set(&cpuas->memory_dispatch, d);
-    tlb_flush(cpuas->cpu);
+    if (cpu->halt_cond) {
+        async_run_on_cpu(cpu, tcg_commit_cpu, RUN_ON_CPU_HOST_PTR(cpuas));
+    } else {
+        tcg_commit_cpu(cpu, RUN_ON_CPU_HOST_PTR(cpuas));
+    }
 }
 
 static void memory_map_init(void)
-- 
2.34.1