[Qemu-devel] [PATCH v4 2/3] block/nvme: support larger that 512 bytes sector devices

[Maxim Levitsky <mlevitsk@redhat.com>]

Currently the driver hardcodes the sector size to 512,
and doesn't check the underlying device. Fix that.

Also fail if underlying nvme device is formatted with metadata
as this needs special support.

Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>
---
 block/nvme.c | 45 ++++++++++++++++++++++++++++++++++++++++-----
 1 file changed, 40 insertions(+), 5 deletions(-)

diff --git a/block/nvme.c b/block/nvme.c
index 82fdefccd6..35ce10dc79 100644
--- a/block/nvme.c
+++ b/block/nvme.c
@@ -102,8 +102,11 @@ typedef struct {
     size_t doorbell_scale;
     bool write_cache_supported;
     EventNotifier irq_notifier;
+
     uint64_t nsze; /* Namespace size reported by identify command */
     int nsid;      /* The namespace id to read/write data. */
+    size_t blkshift;
+
     uint64_t max_transfer;
     bool plugged;
 
@@ -418,8 +421,9 @@ static void nvme_identify(BlockDriverState *bs, int namespace, Error **errp)
     BDRVNVMeState *s = bs->opaque;
     NvmeIdCtrl *idctrl;
     NvmeIdNs *idns;
+    NvmeLBAF *lbaf;
     uint8_t *resp;
-    int r;
+    int r, hwsect_size;
     uint64_t iova;
     NvmeCmd cmd = {
         .opcode = NVME_ADM_CMD_IDENTIFY,
@@ -466,7 +470,22 @@ static void nvme_identify(BlockDriverState *bs, int namespace, Error **errp)
     }
 
     s->nsze = le64_to_cpu(idns->nsze);
+    lbaf = &idns->lbaf[NVME_ID_NS_FLBAS_INDEX(idns->flbas)];
+
+    if (lbaf->ms) {
+        error_setg(errp, "Namespaces with metadata are not yet supported");
+        goto out;
+    }
+
+    hwsect_size = 1 << lbaf->ds;
+
+    if (hwsect_size < BDRV_SECTOR_SIZE || hwsect_size > s->page_size) {
+        error_setg(errp, "Namespace has unsupported block size (%d)",
+                hwsect_size);
+        goto out;
+    }
 
+    s->blkshift = lbaf->ds;
 out:
     qemu_vfio_dma_unmap(s->vfio, resp);
     qemu_vfree(resp);
@@ -785,8 +804,22 @@ fail:
 static int64_t nvme_getlength(BlockDriverState *bs)
 {
     BDRVNVMeState *s = bs->opaque;
+    return s->nsze << s->blkshift;
+}
 
-    return s->nsze << BDRV_SECTOR_BITS;
+static int64_t nvme_get_blocksize(BlockDriverState *bs)
+{
+    BDRVNVMeState *s = bs->opaque;
+    assert(s->blkshift >= BDRV_SECTOR_BITS);
+    return 1 << s->blkshift;
+}
+
+static int nvme_probe_blocksizes(BlockDriverState *bs, BlockSizes *bsz)
+{
+    int64_t blocksize = nvme_get_blocksize(bs);
+    bsz->phys = blocksize;
+    bsz->log = blocksize;
+    return 0;
 }
 
 /* Called with s->dma_map_lock */
@@ -917,13 +950,14 @@ static coroutine_fn int nvme_co_prw_aligned(BlockDriverState *bs,
     BDRVNVMeState *s = bs->opaque;
     NVMeQueuePair *ioq = s->queues[1];
     NVMeRequest *req;
-    uint32_t cdw12 = (((bytes >> BDRV_SECTOR_BITS) - 1) & 0xFFFF) |
+
+    uint32_t cdw12 = (((bytes >> s->blkshift) - 1) & 0xFFFF) |
                        (flags & BDRV_REQ_FUA ? 1 << 30 : 0);
     NvmeCmd cmd = {
         .opcode = is_write ? NVME_CMD_WRITE : NVME_CMD_READ,
         .nsid = cpu_to_le32(s->nsid),
-        .cdw10 = cpu_to_le32((offset >> BDRV_SECTOR_BITS) & 0xFFFFFFFF),
-        .cdw11 = cpu_to_le32(((offset >> BDRV_SECTOR_BITS) >> 32) & 0xFFFFFFFF),
+        .cdw10 = cpu_to_le32((offset >> s->blkshift) & 0xFFFFFFFF),
+        .cdw11 = cpu_to_le32(((offset >> s->blkshift) >> 32) & 0xFFFFFFFF),
         .cdw12 = cpu_to_le32(cdw12),
     };
     NVMeCoData data = {
@@ -1154,6 +1188,7 @@ static BlockDriver bdrv_nvme = {
     .bdrv_file_open           = nvme_file_open,
     .bdrv_close               = nvme_close,
     .bdrv_getlength           = nvme_getlength,
+    .bdrv_probe_blocksizes    = nvme_probe_blocksizes,
 
     .bdrv_co_preadv           = nvme_co_preadv,
     .bdrv_co_pwritev          = nvme_co_pwritev,
-- 
2.17.2