ahci: Update byte count after DMA completion

Currently, DMA read/write operations neglect to update
the byte count after a successful transfer like ATAPI
DMA read or PIO read/write operations do.

We correct this oversight by adding another callback into
the IDEDMAOps structure. The commit callback is called
whenever we are cleaning up a scatter-gather list.
AHCI can register this callback in order to update post-
transfer information such as byte count updates.

We use this callback in AHCI to consolidate where we delete
the SGlist as generated from the PRDT, as well as update the
byte count after the transfer is complete.

The QEMUSGList structure has an init flag added to it in order
to make qemu_sglist_destroy a nop if it is called when
there is no sglist, which simplifies cleanup and error paths.

This patch fixes several AHCI problems, notably Non-NCQ modes
of operation for Windows 7 as well as Hibernate support for Windows 7.

Signed-off-by: John Snow <jsnow@redhat.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Tested-by: Michael S. Tsirkin <mst@redhat.com>
Message-id: 1412204151-18117-3-git-send-email-jsnow@redhat.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>

3 files changed, 40 insertions, 14 deletions

diff --git a/hw/ide/ahci.c b/hw/ide/ahci.c
index 03df4623e9..d80ddd2d0a 100644
--- a/hw/ide/ahci.c
+++ b/hw/ide/ahci.c
@@ -49,6 +49,9 @@ static int handle_cmd(AHCIState *s,int port,int slot);
 static void ahci_reset_port(AHCIState *s, int port);
 static void ahci_write_fis_d2h(AHCIDevice *ad, uint8_t *cmd_fis);
 static void ahci_init_d2h(AHCIDevice *ad);
+static int ahci_dma_prepare_buf(IDEDMA *dma, int is_write);
+static void ahci_commit_buf(IDEDMA *dma, uint32_t tx_bytes);
+
 
 static uint32_t  ahci_port_read(AHCIState *s, int port, int offset)
 {
@@ -1105,16 +1108,12 @@ static void ahci_start_transfer(IDEDMA *dma)
         }
     }
 
-    /* update number of transferred bytes */
-    ad->cur_cmd->status = cpu_to_le32(le32_to_cpu(ad->cur_cmd->status) + size);
-
 out:
     /* declare that we processed everything */
     s->data_ptr = s->data_end;
 
-    if (has_sglist) {
-        qemu_sglist_destroy(&s->sg);
-    }
+    /* Update number of transferred bytes, destroy sglist */
+    ahci_commit_buf(dma, size);
 
     s->end_transfer_func(s);
 
@@ -1135,6 +1134,11 @@ static void ahci_start_dma(IDEDMA *dma, IDEState *s,
     dma_cb(s, 0);
 }
 
+/**
+ * Called in DMA R/W chains to read the PRDT, utilizing ahci_populate_sglist.
+ * Not currently invoked by PIO R/W chains,
+ * which invoke ahci_populate_sglist via ahci_start_transfer.
+ */
 static int ahci_dma_prepare_buf(IDEDMA *dma, int is_write)
 {
     AHCIDevice *ad = DO_UPCAST(AHCIDevice, dma, dma);
@@ -1147,6 +1151,24 @@ static int ahci_dma_prepare_buf(IDEDMA *dma, int is_write)
     return s->io_buffer_size != 0;
 }
 
+/**
+ * Destroys the scatter-gather list,
+ * and updates the command header with a bytes-read value.
+ * called explicitly via ahci_dma_rw_buf (ATAPI DMA),
+ * and ahci_start_transfer (PIO R/W),
+ * and called via callback from ide_dma_cb for DMA R/W paths.
+ */
+static void ahci_commit_buf(IDEDMA *dma, uint32_t tx_bytes)
+{
+    AHCIDevice *ad = DO_UPCAST(AHCIDevice, dma, dma);
+    IDEState *s = &ad->port.ifs[0];
+
+    tx_bytes += le32_to_cpu(ad->cur_cmd->status);
+    ad->cur_cmd->status = cpu_to_le32(tx_bytes);
+
+    qemu_sglist_destroy(&s->sg);
+}
+
 static int ahci_dma_rw_buf(IDEDMA *dma, int is_write)
 {
     AHCIDevice *ad = DO_UPCAST(AHCIDevice, dma, dma);
@@ -1164,11 +1186,9 @@ static int ahci_dma_rw_buf(IDEDMA *dma, int is_write)
         dma_buf_write(p, l, &s->sg);
     }
 
-    /* free sglist that was created in ahci_populate_sglist() */
-    qemu_sglist_destroy(&s->sg);
+    /* free sglist, update byte count */
+    ahci_commit_buf(dma, l);
 
-    /* update number of transferred bytes */
-    ad->cur_cmd->status = cpu_to_le32(le32_to_cpu(ad->cur_cmd->status) + l);
     s->io_buffer_index += l;
     s->io_buffer_offset += l;
 
@@ -1211,6 +1231,7 @@ static const IDEDMAOps ahci_dma_ops = {
     .start_dma = ahci_start_dma,
     .start_transfer = ahci_start_transfer,
     .prepare_buf = ahci_dma_prepare_buf,
+    .commit_buf = ahci_commit_buf,
     .rw_buf = ahci_dma_rw_buf,
     .set_unit = ahci_dma_set_unit,
     .cmd_done = ahci_cmd_done,
diff --git a/hw/ide/core.c b/hw/ide/core.c
index 44e3d502d4..d316ccf961 100644
--- a/hw/ide/core.c
+++ b/hw/ide/core.c
@@ -634,8 +634,11 @@ void ide_sector_read(IDEState *s)
                                  ide_sector_read_cb, s);
 }
 
-static void dma_buf_commit(IDEState *s)
+static void dma_buf_commit(IDEState *s, uint32_t tx_bytes)
 {
+    if (s->bus->dma->ops->commit_buf) {
+        s->bus->dma->ops->commit_buf(s->bus->dma, tx_bytes);
+    }
     qemu_sglist_destroy(&s->sg);
 }
 
@@ -650,6 +653,7 @@ void ide_set_inactive(IDEState *s, bool more)
 
 void ide_dma_error(IDEState *s)
 {
+    dma_buf_commit(s, 0);
     ide_abort_command(s);
     ide_set_inactive(s, false);
     ide_set_irq(s->bus);
@@ -665,7 +669,6 @@ static int ide_handle_rw_error(IDEState *s, int error, int op)
         s->bus->error_status = op;
     } else if (action == BLOCK_ERROR_ACTION_REPORT) {
         if (op & IDE_RETRY_DMA) {
-            dma_buf_commit(s);
             ide_dma_error(s);
         } else {
             ide_rw_error(s);
@@ -709,7 +712,8 @@ void ide_dma_cb(void *opaque, int ret)
 
     sector_num = ide_get_sector(s);
     if (n > 0) {
-        dma_buf_commit(s);
+        assert(s->io_buffer_size == s->sg.size);
+        dma_buf_commit(s, s->io_buffer_size);
         sector_num += n;
         ide_set_sector(s, sector_num);
         s->nsector -= n;
@@ -740,7 +744,6 @@ void ide_dma_cb(void *opaque, int ret)
 
     if ((s->dma_cmd == IDE_DMA_READ || s->dma_cmd == IDE_DMA_WRITE) &&
         !ide_sect_range_ok(s, sector_num, n)) {
-        dma_buf_commit(s);
         ide_dma_error(s);
         return;
     }
diff --git a/hw/ide/internal.h b/hw/ide/internal.h
index 68ac610d6f..907493d0f8 100644
--- a/hw/ide/internal.h
+++ b/hw/ide/internal.h
@@ -322,6 +322,7 @@ typedef void EndTransferFunc(IDEState *);
 typedef void DMAStartFunc(IDEDMA *, IDEState *, BlockCompletionFunc *);
 typedef void DMAVoidFunc(IDEDMA *);
 typedef int DMAIntFunc(IDEDMA *, int);
+typedef void DMAu32Func(IDEDMA *, uint32_t);
 typedef void DMAStopFunc(IDEDMA *, bool);
 typedef void DMARestartFunc(void *, int, RunState);
 
@@ -430,6 +431,7 @@ struct IDEDMAOps {
     DMAStartFunc *start_dma;
     DMAVoidFunc *start_transfer;
     DMAIntFunc *prepare_buf;
+    DMAu32Func *commit_buf;
     DMAIntFunc *rw_buf;
     DMAIntFunc *set_unit;
     DMAStopFunc *set_inactive;