exec: Adjust notdirty tracing

The memory_region_tb_read tracepoint is unreachable, since notdirty
is supposed to apply only to writes.  The memory_region_tb_write
tracepoint is mis-named, because notdirty is not only used for TB
invalidation.  It is also used for e.g. VGA RAM updates and migration.

Replace memory_region_tb_write with memory_notdirty_write_access,
and place it in memory_notdirty_write_prepare where it can catch
all of the instances.  Add memory_notdirty_set_dirty to log when
we no longer intercept writes to a page.

Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com>
Reviewed-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

exec.c

@@ -2755,6 +2755,8 @@ void memory_notdirty_write_prepare(NotDirtyInfo *ndi,
     ndi->size = size;
     ndi->pages = NULL;
 
+    trace_memory_notdirty_write_access(mem_vaddr, ram_addr, size);
+
     assert(tcg_enabled());
     if (!cpu_physical_memory_get_dirty_flag(ram_addr, DIRTY_MEMORY_CODE)) {
         ndi->pages = page_collection_lock(ram_addr, ram_addr + size);
@@ -2779,6 +2781,7 @@ void memory_notdirty_write_complete(NotDirtyInfo *ndi)
     /* we remove the notdirty callback only if the code has been
        flushed */
     if (!cpu_physical_memory_is_clean(ndi->ram_addr)) {
+        trace_memory_notdirty_set_dirty(ndi->mem_vaddr);
         tlb_set_dirty(ndi->cpu, ndi->mem_vaddr);
     }
 }

memory.c

@@ -438,7 +438,6 @@ static MemTxResult  memory_region_read_accessor(MemoryRegion *mr,
         /* Accesses to code which has previously been translated into a TB show
          * up in the MMIO path, as accesses to the io_mem_notdirty
          * MemoryRegion. */
-        trace_memory_region_tb_read(get_cpu_index(), addr, tmp, size);
     } else if (TRACE_MEMORY_REGION_OPS_READ_ENABLED) {
         hwaddr abs_addr = memory_region_to_absolute_addr(mr, addr);
         trace_memory_region_ops_read(get_cpu_index(), mr, abs_addr, tmp, size);
@@ -465,7 +464,6 @@ static MemTxResult memory_region_read_with_attrs_accessor(MemoryRegion *mr,
         /* Accesses to code which has previously been translated into a TB show
          * up in the MMIO path, as accesses to the io_mem_notdirty
          * MemoryRegion. */
-        trace_memory_region_tb_read(get_cpu_index(), addr, tmp, size);
     } else if (TRACE_MEMORY_REGION_OPS_READ_ENABLED) {
         hwaddr abs_addr = memory_region_to_absolute_addr(mr, addr);
         trace_memory_region_ops_read(get_cpu_index(), mr, abs_addr, tmp, size);
@@ -490,7 +488,6 @@ static MemTxResult memory_region_write_accessor(MemoryRegion *mr,
         /* Accesses to code which has previously been translated into a TB show
          * up in the MMIO path, as accesses to the io_mem_notdirty
          * MemoryRegion. */
-        trace_memory_region_tb_write(get_cpu_index(), addr, tmp, size);
     } else if (TRACE_MEMORY_REGION_OPS_WRITE_ENABLED) {
         hwaddr abs_addr = memory_region_to_absolute_addr(mr, addr);
         trace_memory_region_ops_write(get_cpu_index(), mr, abs_addr, tmp, size);
@@ -515,7 +512,6 @@ static MemTxResult memory_region_write_with_attrs_accessor(MemoryRegion *mr,
         /* Accesses to code which has previously been translated into a TB show
          * up in the MMIO path, as accesses to the io_mem_notdirty
          * MemoryRegion. */
-        trace_memory_region_tb_write(get_cpu_index(), addr, tmp, size);
     } else if (TRACE_MEMORY_REGION_OPS_WRITE_ENABLED) {
         hwaddr abs_addr = memory_region_to_absolute_addr(mr, addr);
         trace_memory_region_ops_write(get_cpu_index(), mr, abs_addr, tmp, size);

trace-events

@@ -52,14 +52,14 @@ dma_map_wait(void *dbs) "dbs=%p"
 find_ram_offset(uint64_t size, uint64_t offset) "size: 0x%" PRIx64 " @ 0x%" PRIx64
 find_ram_offset_loop(uint64_t size, uint64_t candidate, uint64_t offset, uint64_t next, uint64_t mingap) "trying size: 0x%" PRIx64 " @ 0x%" PRIx64 ", offset: 0x%" PRIx64" next: 0x%" PRIx64 " mingap: 0x%" PRIx64
 ram_block_discard_range(const char *rbname, void *hva, size_t length, bool need_madvise, bool need_fallocate, int ret) "%s@%p + 0x%zx: madvise: %d fallocate: %d ret: %d"
+memory_notdirty_write_access(uint64_t vaddr, uint64_t ram_addr, unsigned size) "0x%" PRIx64 " ram_addr 0x%" PRIx64 " size %u"
+memory_notdirty_set_dirty(uint64_t vaddr) "0x%" PRIx64
 
 # memory.c
 memory_region_ops_read(int cpu_index, void *mr, uint64_t addr, uint64_t value, unsigned size) "cpu %d mr %p addr 0x%"PRIx64" value 0x%"PRIx64" size %u"
 memory_region_ops_write(int cpu_index, void *mr, uint64_t addr, uint64_t value, unsigned size) "cpu %d mr %p addr 0x%"PRIx64" value 0x%"PRIx64" size %u"
 memory_region_subpage_read(int cpu_index, void *mr, uint64_t offset, uint64_t value, unsigned size) "cpu %d mr %p offset 0x%"PRIx64" value 0x%"PRIx64" size %u"
 memory_region_subpage_write(int cpu_index, void *mr, uint64_t offset, uint64_t value, unsigned size) "cpu %d mr %p offset 0x%"PRIx64" value 0x%"PRIx64" size %u"
-memory_region_tb_read(int cpu_index, uint64_t addr, uint64_t value, unsigned size) "cpu %d addr 0x%"PRIx64" value 0x%"PRIx64" size %u"
-memory_region_tb_write(int cpu_index, uint64_t addr, uint64_t value, unsigned size) "cpu %d addr 0x%"PRIx64" value 0x%"PRIx64" size %u"
 memory_region_ram_device_read(int cpu_index, void *mr, uint64_t addr, uint64_t value, unsigned size) "cpu %d mr %p addr 0x%"PRIx64" value 0x%"PRIx64" size %u"
 memory_region_ram_device_write(int cpu_index, void *mr, uint64_t addr, uint64_t value, unsigned size) "cpu %d mr %p addr 0x%"PRIx64" value 0x%"PRIx64" size %u"
 flatview_new(void *view, void *root) "%p (root %p)"