[Qemu-devel] [PATCH v3 12/14] kvm: add support to sync the page encryption state bitmap

[Singh, Brijesh]

The SEV VMs have concept of private and shared memory. The private memory
is encrypted with guest-specific key, while shared memory may be encrypted
with hyperivosr key. The KVM_GET_PAGE_ENC_BITMAP can be used to get a
bitmap indicating whether the guest page is private or shared. A private
page must be transmitted using the SEV migration commands.

Add a cpu_physical_memory_sync_encrypted_bitmap() which can be used to get
the page encryption bitmap for a given memory region.

The page encryption bitmap is not exactly same as dirty bitmap. The page
encryption bitmap is a purely a matter of state about the page is encrypted
or not. To avoid some confusion we clone few functions for clarity.

Signed-off-by: Brijesh Singh <address@hidden>
---
 accel/kvm/kvm-all.c     |  37 ++++++++
 include/exec/ram_addr.h | 199 ++++++++++++++++++++++++++++++++++++++++
 include/exec/ramlist.h  |   3 +-
 migration/ram.c         |  17 ++++
 4 files changed, 255 insertions(+), 1 deletion(-)

diff --git a/accel/kvm/kvm-all.c b/accel/kvm/kvm-all.c
index f4d136b022..d942e10896 100644
--- a/accel/kvm/kvm-all.c
+++ b/accel/kvm/kvm-all.c
@@ -560,6 +560,36 @@ static int 
kvm_get_dirty_pages_log_range(MemoryRegionSection *section,
 
 #define ALIGN(x, y)  (((x)+(y)-1) & ~((y)-1))
 
+/* sync page_enc bitmap */
+static int kvm_sync_page_enc_bitmap(KVMMemoryListener *kml,
+                                    MemoryRegionSection *section,
+                                    KVMSlot *mem)
+{
+    unsigned long size;
+    KVMState *s = kvm_state;
+    struct kvm_page_enc_bitmap e = {};
+    ram_addr_t pages = int128_get64(section->size) / getpagesize();
+    ram_addr_t start = section->offset_within_region +
+                       memory_region_get_ram_addr(section->mr);
+
+    size = ALIGN(((mem->memory_size) >> TARGET_PAGE_BITS), 64) / 8;
+    e.enc_bitmap = g_malloc0(size);
+    e.start_gfn = mem->start_addr >> TARGET_PAGE_BITS;
+    e.num_pages = pages;
+    if (kvm_vm_ioctl(s, KVM_GET_PAGE_ENC_BITMAP, &e) == -1) {
+        DPRINTF("KVM_GET_PAGE_ENC_BITMAP ioctl failed %d\n", errno);
+        g_free(e.enc_bitmap);
+        return 1;
+    }
+
+    cpu_physical_memory_set_encrypted_lebitmap(e.enc_bitmap,
+                                               start, pages);
+
+    g_free(e.enc_bitmap);
+
+    return 0;
+}
+
 /**
  * kvm_physical_sync_dirty_bitmap - Sync dirty bitmap from kernel space
  *
@@ -616,6 +646,13 @@ static int 
kvm_physical_sync_dirty_bitmap(KVMMemoryListener *kml,
         }
 
         kvm_get_dirty_pages_log_range(section, d.dirty_bitmap);
+
+        if (kvm_memcrypt_enabled() &&
+            kvm_sync_page_enc_bitmap(kml, section, mem)) {
+            g_free(d.dirty_bitmap);
+            return -1;
+        }
+
     }
 out:
     return ret;
diff --git a/include/exec/ram_addr.h b/include/exec/ram_addr.h
index b7b2e60ff6..6dbeac6567 100644
--- a/include/exec/ram_addr.h
+++ b/include/exec/ram_addr.h
@@ -67,6 +67,8 @@ struct RAMBlock {
      */
     unsigned long *clear_bmap;
     uint8_t clear_bmap_shift;
+    /* bitmap of page encryption state for an encrypted guest */
+    unsigned long *encbmap;
 };
 
 /**
@@ -323,6 +325,60 @@ static inline void 
cpu_physical_memory_set_dirty_flag(ram_addr_t addr,
     rcu_read_unlock();
 }
 
+static inline void cpu_physical_memory_set_encrypted_range(ram_addr_t start,
+                                                           ram_addr_t length,
+                                                           unsigned long val)
+{
+    unsigned long page;
+    unsigned long * const *src;
+
+    page = start >> TARGET_PAGE_BITS;
+
+    rcu_read_lock();
+
+    src = atomic_rcu_read(
+            &ram_list.dirty_memory[DIRTY_MEMORY_ENCRYPTED])->blocks;
+
+    if (length) {
+        unsigned long idx = page / DIRTY_MEMORY_BLOCK_SIZE;
+        unsigned long offset = page % DIRTY_MEMORY_BLOCK_SIZE;
+        int m = (start) & (BITS_PER_LONG - 1);
+        int n = MIN(length, BITS_PER_LONG - m);
+        unsigned long old_val = atomic_read(&src[idx][BIT_WORD(offset)]);
+        unsigned long mask;
+
+        mask = (~0UL >> n);
+        mask = mask << m;
+
+        old_val &= ~mask;
+        val &= mask;
+
+        atomic_xchg(&src[idx][BIT_WORD(offset)], old_val | val);
+        page += n;
+        length -= n;
+    }
+
+    /* remaining bits */
+    if (length) {
+        unsigned long idx = page / DIRTY_MEMORY_BLOCK_SIZE;
+        unsigned long offset = page % DIRTY_MEMORY_BLOCK_SIZE;
+        int m = (start) & (BITS_PER_LONG - 1);
+        int n = MIN(length, BITS_PER_LONG - m);
+        unsigned long old_val = atomic_read(&src[idx][BIT_WORD(offset)]);
+        unsigned long mask;
+
+        mask = (~0UL >> n);
+        mask = mask << m;
+
+        old_val &= ~mask;
+        val &= mask;
+
+        atomic_xchg(&src[idx][BIT_WORD(offset)], old_val | val);
+    }
+
+    rcu_read_unlock();
+}
+
 static inline void cpu_physical_memory_set_dirty_range(ram_addr_t start,
                                                        ram_addr_t length,
                                                        uint8_t mask)
@@ -376,6 +432,62 @@ static inline void 
cpu_physical_memory_set_dirty_range(ram_addr_t start,
 }
 
 #if !defined(_WIN32)
+static inline void cpu_physical_memory_set_encrypted_lebitmap(
+                                                        unsigned long *bitmap,
+                                                        ram_addr_t start,
+                                                        ram_addr_t pages)
+{
+    unsigned long i;
+    unsigned long hpratio = getpagesize() / TARGET_PAGE_SIZE;
+    unsigned long page = BIT_WORD(start >> TARGET_PAGE_BITS);
+
+    /* start address is aligned at the start of a word? */
+    if ((((page * BITS_PER_LONG) << TARGET_PAGE_BITS) == start) &&
+        (hpratio == 1)) {
+        unsigned long **blocks[DIRTY_MEMORY_NUM];
+        unsigned long idx;
+        unsigned long offset;
+        long k;
+        long nr = BITS_TO_LONGS(pages);
+
+        idx = (start >> TARGET_PAGE_BITS) / DIRTY_MEMORY_BLOCK_SIZE;
+        offset = BIT_WORD((start >> TARGET_PAGE_BITS) %
+                          DIRTY_MEMORY_BLOCK_SIZE);
+
+        rcu_read_lock();
+
+        for (i = 0; i < DIRTY_MEMORY_NUM; i++) {
+            blocks[i] = atomic_rcu_read(&ram_list.dirty_memory[i])->blocks;
+        }
+
+        for (k = 0; k < nr; k++) {
+            if (bitmap[k]) {
+                unsigned long temp = leul_to_cpu(bitmap[k]);
+
+                atomic_xchg(&blocks[DIRTY_MEMORY_ENCRYPTED][idx][offset], 
temp);
+            }
+
+            if (++offset >= BITS_TO_LONGS(DIRTY_MEMORY_BLOCK_SIZE)) {
+                offset = 0;
+                idx++;
+            }
+        }
+
+        rcu_read_unlock();
+    } else {
+        i = 0;
+        while (pages > 0) {
+            unsigned long len = MIN(pages, BITS_PER_LONG);
+
+            cpu_physical_memory_set_encrypted_range(start, len,
+                            leul_to_cpu(bitmap[i]));
+            start += len;
+            i++;
+            pages -= len;
+        }
+    }
+}
+
 static inline void cpu_physical_memory_set_dirty_lebitmap(unsigned long 
*bitmap,
                                                           ram_addr_t start,
                                                           ram_addr_t pages)
@@ -478,6 +590,8 @@ static inline void 
cpu_physical_memory_clear_dirty_range(ram_addr_t start,
     cpu_physical_memory_test_and_clear_dirty(start, length, 
DIRTY_MEMORY_MIGRATION);
     cpu_physical_memory_test_and_clear_dirty(start, length, DIRTY_MEMORY_VGA);
     cpu_physical_memory_test_and_clear_dirty(start, length, DIRTY_MEMORY_CODE);
+    cpu_physical_memory_test_and_clear_dirty(start, length,
+                                             DIRTY_MEMORY_ENCRYPTED);
 }
 
 
@@ -556,5 +670,90 @@ uint64_t cpu_physical_memory_sync_dirty_bitmap(RAMBlock 
*rb,
 
     return num_dirty;
 }
+
+static inline bool cpu_physical_memory_test_encrypted(ram_addr_t start,
+                                                      ram_addr_t length)
+{
+    unsigned long end, page;
+    bool enc = false;
+    unsigned long * const *src;
+
+    if (length == 0) {
+        return enc;
+    }
+
+    end = TARGET_PAGE_ALIGN(start + length) >> TARGET_PAGE_BITS;
+    page = start >> TARGET_PAGE_BITS;
+
+    rcu_read_lock();
+
+    src = atomic_rcu_read(
+            &ram_list.dirty_memory[DIRTY_MEMORY_ENCRYPTED])->blocks;
+
+    while (page < end) {
+        unsigned long idx = page / DIRTY_MEMORY_BLOCK_SIZE;
+        unsigned long offset = page % DIRTY_MEMORY_BLOCK_SIZE;
+        unsigned long num = MIN(end - page, DIRTY_MEMORY_BLOCK_SIZE - offset);
+
+        enc |= atomic_read(&src[idx][BIT_WORD(offset)]);
+        page += num;
+    }
+
+    rcu_read_unlock();
+
+    return enc;
+}
+
+static inline
+void cpu_physical_memory_sync_encrypted_bitmap(RAMBlock *rb,
+                                               ram_addr_t start,
+                                               ram_addr_t length)
+{
+    ram_addr_t addr;
+    unsigned long word = BIT_WORD((start + rb->offset) >> TARGET_PAGE_BITS);
+    unsigned long *dest = rb->encbmap;
+
+    /* start address and length is aligned at the start of a word? */
+    if (((word * BITS_PER_LONG) << TARGET_PAGE_BITS) ==
+         (start + rb->offset) &&
+        !(length & ((BITS_PER_LONG << TARGET_PAGE_BITS) - 1))) {
+        int k;
+        int nr = BITS_TO_LONGS(length >> TARGET_PAGE_BITS);
+        unsigned long * const *src;
+        unsigned long idx = (word * BITS_PER_LONG) / DIRTY_MEMORY_BLOCK_SIZE;
+        unsigned long offset = BIT_WORD((word * BITS_PER_LONG) %
+                                        DIRTY_MEMORY_BLOCK_SIZE);
+        unsigned long page = BIT_WORD(start >> TARGET_PAGE_BITS);
+
+        rcu_read_lock();
+
+        src = atomic_rcu_read(
+                &ram_list.dirty_memory[DIRTY_MEMORY_ENCRYPTED])->blocks;
+
+        for (k = page; k < page + nr; k++) {
+            unsigned long bits = atomic_read(&src[idx][offset]);
+            dest[k] = bits;
+
+            if (++offset >= BITS_TO_LONGS(DIRTY_MEMORY_BLOCK_SIZE)) {
+                offset = 0;
+                idx++;
+            }
+        }
+
+        rcu_read_unlock();
+    } else {
+        ram_addr_t offset = rb->offset;
+
+        for (addr = 0; addr < length; addr += TARGET_PAGE_SIZE) {
+            long k = (start + addr) >> TARGET_PAGE_BITS;
+            if (cpu_physical_memory_test_encrypted(start + addr + offset,
+                                                   TARGET_PAGE_SIZE)) {
+                set_bit(k, dest);
+            } else {
+                clear_bit(k, dest);
+            }
+        }
+    }
+}
 #endif
 #endif
diff --git a/include/exec/ramlist.h b/include/exec/ramlist.h
index bc4faa1b00..2a5eab8b11 100644
--- a/include/exec/ramlist.h
+++ b/include/exec/ramlist.h
@@ -11,7 +11,8 @@ typedef struct RAMBlockNotifier RAMBlockNotifier;
 #define DIRTY_MEMORY_VGA       0
 #define DIRTY_MEMORY_CODE      1
 #define DIRTY_MEMORY_MIGRATION 2
-#define DIRTY_MEMORY_NUM       3        /* num of dirty bits */
+#define DIRTY_MEMORY_ENCRYPTED 3
+#define DIRTY_MEMORY_NUM       4        /* num of dirty bits */
 
 /* The dirty memory bitmap is split into fixed-size blocks to allow growth
  * under RCU.  The bitmap for a block can be accessed as follows:
diff --git a/migration/ram.c b/migration/ram.c
index 889148dd84..57c707525b 100644
--- a/migration/ram.c
+++ b/migration/ram.c
@@ -57,6 +57,7 @@
 #include "qemu/uuid.h"
 #include "savevm.h"
 #include "qemu/iov.h"
+#include "hw/boards.h"
 
 /***********************************************************/
 /* ram save/restore */
@@ -700,6 +701,13 @@ typedef struct {
     QemuSemaphore sem_sync;
 } MultiFDRecvParams;
 
+static inline bool memcrypt_enabled(void)
+{
+    MachineState *ms = MACHINE(qdev_get_machine());
+
+    return machine_memory_encryption_enabled(ms);
+}
+
 static int multifd_send_initial_packet(MultiFDSendParams *p, Error **errp)
 {
     MultiFDInit_t msg;
@@ -1754,6 +1762,9 @@ static void migration_bitmap_sync_range(RAMState *rs, 
RAMBlock *rb,
     rs->migration_dirty_pages +=
         cpu_physical_memory_sync_dirty_bitmap(rb, 0, length,
                                               &rs->num_dirty_pages_period);
+    if (memcrypt_enabled()) {
+        cpu_physical_memory_sync_encrypted_bitmap(rb, 0, length);
+    }
 }
 
 /**
@@ -2768,6 +2779,8 @@ static void ram_save_cleanup(void *opaque)
         block->bmap = NULL;
         g_free(block->unsentmap);
         block->unsentmap = NULL;
+        g_free(block->encbmap);
+        block->encbmap = NULL;
     }
 
     xbzrle_cleanup();
@@ -3310,6 +3323,10 @@ static void ram_list_init_bitmaps(void)
                 block->unsentmap = bitmap_new(pages);
                 bitmap_set(block->unsentmap, 0, pages);
             }
+            if (memcrypt_enabled()) {
+                block->encbmap = bitmap_new(pages);
+                bitmap_set(block->encbmap, 0, pages);
+            }
         }
     }
 }
-- 
2.17.1