[PATCH v5 1/6] system/physmem: handle hugetlb correctly in qemu_ram_remap()

["“William Roche" <william.roche@oracle.com>]

From: William Roche <william.roche@oracle.com>

The list of hwpoison pages used to remap the memory on reset
is based on the backend real page size. When dealing with
hugepages, we create a single entry for the entire page.

To correctly handle hugetlb, we must mmap(MAP_FIXED) a complete
hugetlb page; hugetlb pages cannot be partially mapped.

Co-developed-by: David Hildenbrand <david@redhat.com>
Signed-off-by: William Roche <william.roche@oracle.com>
---
 accel/kvm/kvm-all.c       |  6 +++++-
 include/exec/cpu-common.h |  3 ++-
 system/physmem.c          | 32 ++++++++++++++++++++++++++------
 3 files changed, 33 insertions(+), 8 deletions(-)

diff --git a/accel/kvm/kvm-all.c b/accel/kvm/kvm-all.c
index c65b790433..4f2abd5774 100644
--- a/accel/kvm/kvm-all.c
+++ b/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);
     }
 }
@@ -1296,6 +1296,10 @@ static void kvm_unpoison_all(void *param)
 void kvm_hwpoison_page_add(ram_addr_t ram_addr)
 {
     HWPoisonPage *page;
+    size_t page_size = qemu_ram_pagesize_from_addr(ram_addr);
+
+    if (page_size > TARGET_PAGE_SIZE)
+        ram_addr = QEMU_ALIGN_DOWN(ram_addr, page_size);
 
     QLIST_FOREACH(page, &hwpoison_page_list, list) {
         if (page->ram_addr == ram_addr) {
diff --git a/include/exec/cpu-common.h b/include/exec/cpu-common.h
index b1d76d6985..dbdf22fded 100644
--- a/include/exec/cpu-common.h
+++ b/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);
@@ -108,6 +108,7 @@ bool qemu_ram_is_named_file(RAMBlock *rb);
 int qemu_ram_get_fd(RAMBlock *rb);
 
 size_t qemu_ram_pagesize(RAMBlock *block);
+size_t qemu_ram_pagesize_from_addr(ram_addr_t addr);
 size_t qemu_ram_pagesize_largest(void);
 
 /**
diff --git a/system/physmem.c b/system/physmem.c
index c76503aea8..7a87548f99 100644
--- a/system/physmem.c
+++ b/system/physmem.c
@@ -1665,6 +1665,19 @@ size_t qemu_ram_pagesize(RAMBlock *rb)
     return rb->page_size;
 }
 
+/* Return backend real page size used for the given ram_addr */
+size_t qemu_ram_pagesize_from_addr(ram_addr_t addr)
+{
+    RAMBlock *rb;
+
+    RCU_READ_LOCK_GUARD();
+    rb =  qemu_get_ram_block(addr);
+    if (!rb) {
+        return TARGET_PAGE_SIZE;
+    }
+    return qemu_ram_pagesize(rb);
+}
+
 /* Returns the largest size of page in use */
 size_t qemu_ram_pagesize_largest(void)
 {
@@ -2167,17 +2180,22 @@ void qemu_ram_free(RAMBlock *block)
 }
 
 #ifndef _WIN32
-void qemu_ram_remap(ram_addr_t addr, ram_addr_t length)
+void qemu_ram_remap(ram_addr_t addr)
 {
     RAMBlock *block;
     ram_addr_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) {
                 ;
@@ -2191,21 +2209,23 @@ 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);
+                                 page_size, addr);
                     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;
         }
     }
 }
-- 
2.43.5