[Qemu-devel] [RFC 1/2] Add qemu_ram_remap

[Huang Ying <ying.huang@intel.com>]

qemu_ram_remap() unmaps the specified RAM pages, then re-maps these
pages again.  This is used by KVM HWPoison support to clear HWPoisoned
page tables across guest rebooting, so that a new page may be
allocated later to recover the memory error.

Signed-off-by: Huang Ying <ying.huang@intel.com>
---
 cpu-all.h    |    4 +++
 cpu-common.h |    1 
 exec.c       |   61 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++-
 3 files changed, 65 insertions(+), 1 deletion(-)

--- a/cpu-all.h
+++ b/cpu-all.h
@@ -861,10 +861,14 @@ target_phys_addr_t cpu_get_phys_page_deb
 extern int phys_ram_fd;
 extern ram_addr_t ram_size;
 
+/* RAM is pre-allocated and passed into qemu_ram_alloc_from_ptr */
+#define RAM_PREALLOC_MASK	(1 << 0)
+
 typedef struct RAMBlock {
     uint8_t *host;
     ram_addr_t offset;
     ram_addr_t length;
+    uint32_t flags;
     char idstr[256];
     QLIST_ENTRY(RAMBlock) next;
 #if defined(__linux__) && !defined(TARGET_S390X)
--- a/exec.c
+++ b/exec.c
@@ -2845,6 +2845,7 @@ ram_addr_t qemu_ram_alloc_from_ptr(Devic
 
     if (host) {
         new_block->host = host;
+        new_block->flags |= RAM_PREALLOC_MASK;
     } else {
         if (mem_path) {
 #if defined (__linux__) && !defined(TARGET_S390X)
@@ -2911,7 +2912,9 @@ void qemu_ram_free(ram_addr_t addr)
     QLIST_FOREACH(block, &ram_list.blocks, next) {
         if (addr == block->offset) {
             QLIST_REMOVE(block, next);
-            if (mem_path) {
+            if (block->flags & RAM_PREALLOC_MASK)
+                ;
+            else if (mem_path) {
 #if defined (__linux__) && !defined(TARGET_S390X)
                 if (block->fd) {
                     munmap(block->host, block->length);
@@ -2934,6 +2937,62 @@ void qemu_ram_free(ram_addr_t addr)
 
 }
 
+void qemu_ram_remap(ram_addr_t addr, ram_addr_t length)
+{
+    RAMBlock *block;
+    ram_addr_t offset;
+    int flags;
+    void *area, *vaddr;
+
+    QLIST_FOREACH(block, &ram_list.blocks, next) {
+        offset = addr - block->offset;
+        if (offset < block->length) {
+            vaddr = block->host + offset;
+            if (block->flags & RAM_PREALLOC_MASK)
+                ;
+            else {
+                flags = MAP_FIXED;
+                munmap(vaddr, length);
+                if (mem_path) {
+#if defined (__linux__) && !defined(TARGET_S390X)
+                    if (block->fd) {
+#ifdef MAP_POPULATE
+                        flags |= mem_prealloc ? MAP_POPULATE | MAP_SHARED :
+                            MAP_PRIVATE;
+#else
+                        flags |= MAP_PRIVATE;
+#endif
+                        area = mmap(vaddr, length, PROT_READ | PROT_WRITE,
+                                    flags, block->fd, offset);
+                    } else {
+                        flags |= MAP_PRIVATE | MAP_ANONYMOUS;
+                        area = mmap(vaddr, length, PROT_READ | PROT_WRITE,
+                                    flags, -1, 0);
+                    }
+#endif
+                } else {
+#if defined(TARGET_S390X) && defined(CONFIG_KVM)
+                    flags |= MAP_SHARED | MAP_ANONYMOUS;
+                    area = mmap(vaddr, length, PROT_EXEC|PROT_READ|PROT_WRITE,
+                                flags, -1, 0);
+#else
+                    flags |= MAP_PRIVATE | MAP_ANONYMOUS;
+                    area = mmap(vaddr, length, PROT_READ | PROT_WRITE,
+                                flags, -1, 0);
+#endif
+                }
+                if (area != vaddr) {
+                    fprintf(stderr, "Could not remap addr: %lx@%lx\n",
+                            length, addr);
+                    exit(1);
+                }
+                qemu_madvise(vaddr, length, QEMU_MADV_MERGEABLE);
+            }
+            return;
+        }
+    }
+}
+
 /* Return a host pointer to ram allocated with qemu_ram_alloc.
    With the exception of the softmmu code in this file, this should
    only be used for local memory (e.g. video ram) that the device owns,
--- a/cpu-common.h
+++ b/cpu-common.h
@@ -45,6 +45,7 @@ ram_addr_t qemu_ram_alloc_from_ptr(Devic
 ram_addr_t qemu_ram_alloc(DeviceState *dev, const char *name, ram_addr_t size);
 void qemu_ram_unmap(ram_addr_t addr);
 void qemu_ram_free(ram_addr_t addr);
+void qemu_ram_remap(ram_addr_t addr, ram_addr_t length);
 /* This should only be used for ram local to a device.  */
 void *qemu_get_ram_ptr(ram_addr_t addr);
 /* This should not be used by devices.  */