system/physmem: handle hugetlb correctly in qemu_ram_remap()

The list of hwpoison pages used to remap the memory on reset
is based on the backend real page size.
To correctly handle hugetlb, we must mmap(MAP_FIXED) a complete
hugetlb page; hugetlb pages cannot be partially mapped.

Signed-off-by: William Roche <william.roche@oracle.com>
Co-developed-by: David Hildenbrand <david@redhat.com>
Acked-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Peter Xu <peterx@redhat.com>
Link: https://lore.kernel.org/r/20250211212707.302391-2-william.roche@oracle.com
Signed-off-by: Peter Xu <peterx@redhat.com>

accel/kvm/kvm-all.c

@@ -1288,7 +1288,7 @@ static void kvm_unpoison_all(void *param)
 
     QLIST_FOREACH_SAFE(page, &hwpoison_page_list, list, next_page) {
         QLIST_REMOVE(page, list);
-        qemu_ram_remap(page->ram_addr, TARGET_PAGE_SIZE);
+        qemu_ram_remap(page->ram_addr);
         g_free(page);
     }
 }

include/exec/cpu-common.h

@@ -67,7 +67,7 @@ typedef uintptr_t ram_addr_t;
 
 /* memory API */
 
-void qemu_ram_remap(ram_addr_t addr, ram_addr_t length);
+void qemu_ram_remap(ram_addr_t addr);
 /* This should not be used by devices.  */
 ram_addr_t qemu_ram_addr_from_host(void *ptr);
 ram_addr_t qemu_ram_addr_from_host_nofail(void *ptr);

system/physmem.c

@@ -2275,17 +2275,35 @@ void qemu_ram_free(RAMBlock *block)
 }
 
 #ifndef _WIN32
-void qemu_ram_remap(ram_addr_t addr, ram_addr_t length)
+/*
+ * qemu_ram_remap - remap a single RAM page
+ *
+ * @addr: address in ram_addr_t address space.
+ *
+ * This function will try remapping a single page of guest RAM identified by
+ * @addr, essentially discarding memory to recover from previously poisoned
+ * memory (MCE). The page size depends on the RAMBlock (i.e., hugetlb). @addr
+ * does not have to point at the start of the page.
+ *
+ * This function is only to be used during system resets; it will kill the
+ * VM if remapping failed.
+ */
+void qemu_ram_remap(ram_addr_t addr)
 {
     RAMBlock *block;
-    ram_addr_t offset;
+    uint64_t offset;
     int flags;
     void *area, *vaddr;
     int prot;
+    size_t page_size;
 
     RAMBLOCK_FOREACH(block) {
         offset = addr - block->offset;
         if (offset < block->max_length) {
+            /* Respect the pagesize of our RAMBlock */
+            page_size = qemu_ram_pagesize(block);
+            offset = QEMU_ALIGN_DOWN(offset, page_size);
+
             vaddr = ramblock_ptr(block, offset);
             if (block->flags & RAM_PREALLOC) {
                 ;
@@ -2299,21 +2317,23 @@ void qemu_ram_remap(ram_addr_t addr, ram_addr_t length)
                 prot = PROT_READ;
                 prot |= block->flags & RAM_READONLY ? 0 : PROT_WRITE;
                 if (block->fd >= 0) {
-                    area = mmap(vaddr, length, prot, flags, block->fd,
+                    area = mmap(vaddr, page_size, prot, flags, block->fd,
                                 offset + block->fd_offset);
                 } else {
                     flags |= MAP_ANONYMOUS;
-                    area = mmap(vaddr, length, prot, flags, -1, 0);
+                    area = mmap(vaddr, page_size, prot, flags, -1, 0);
                 }
                 if (area != vaddr) {
-                    error_report("Could not remap addr: "
-                                 RAM_ADDR_FMT "@" RAM_ADDR_FMT "",
-                                 length, addr);
+                    error_report("Could not remap RAM %s:%" PRIx64 "+%" PRIx64
+                                 " +%zx", block->idstr, offset,
+                                 block->fd_offset, page_size);
                     exit(1);
                 }
-                memory_try_enable_merging(vaddr, length);
-                qemu_ram_setup_dump(vaddr, length);
+                memory_try_enable_merging(vaddr, page_size);
+                qemu_ram_setup_dump(vaddr, page_size);
             }
+
+            break;
         }
     }
 }