Merge remote-tracking branch 'kwolf/tags/for-upstream' into staging

Block layer patches

# gpg: Signature made Thu 11 May 2017 10:31:37 AM EDT
# gpg:                using RSA key 0x7F09B272C88F2FD6
# gpg: Good signature from "Kevin Wolf <kwolf@redhat.com>"
# Primary key fingerprint: DC3D EB15 9A9A F95D 3D74  56FE 7F09 B272 C88F 2FD6

* kwolf/tags/for-upstream: (58 commits)
  MAINTAINERS: Add qemu-progress to the block layer
  qcow2: Discard/zero clusters by byte count
  qcow2: Assert that cluster operations are aligned
  qcow2: Optimize write zero of unaligned tail cluster
  iotests: Add test 179 to cover write zeroes with unmap
  iotests: Improve _filter_qemu_img_map
  qcow2: Optimize zero_single_l2() to minimize L2 churn
  qcow2: Make distinction between zero cluster types obvious
  qcow2: Name typedef for cluster type
  qcow2: Correctly report status of preallocated zero clusters
  block: Update comments on BDRV_BLOCK_* meanings
  qcow2: Use consistent switch indentation
  qcow2: Nicer variable names in qcow2_update_snapshot_refcount()
  tests: Add coverage for recent block geometry fixes
  blkdebug: Add ability to override unmap geometries
  blkdebug: Simplify override logic
  blkdebug: Add pass-through write_zero and discard support
  blkdebug: Refactor error injection
  blkdebug: Sanity check block layer guarantees
  qemu-io: Switch 'map' output to byte-based reporting
  ...

Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>

2 files changed, 27 insertions, 0 deletions

diff --git a/hw/block/nvme.c b/hw/block/nvme.c
index ae303d4..7428db9 100644
--- a/hw/block/nvme.c
+++ b/hw/block/nvme.c
@@ -227,6 +227,29 @@ static uint16_t nvme_flush(NvmeCtrl *n, NvmeNamespace *ns, NvmeCmd *cmd,
     return NVME_NO_COMPLETE;
 }
 
+static uint16_t nvme_write_zeros(NvmeCtrl *n, NvmeNamespace *ns, NvmeCmd *cmd,
+    NvmeRequest *req)
+{
+    NvmeRwCmd *rw = (NvmeRwCmd *)cmd;
+    const uint8_t lba_index = NVME_ID_NS_FLBAS_INDEX(ns->id_ns.flbas);
+    const uint8_t data_shift = ns->id_ns.lbaf[lba_index].ds;
+    uint64_t slba = le64_to_cpu(rw->slba);
+    uint32_t nlb  = le16_to_cpu(rw->nlb) + 1;
+    uint64_t aio_slba = slba << (data_shift - BDRV_SECTOR_BITS);
+    uint32_t aio_nlb = nlb << (data_shift - BDRV_SECTOR_BITS);
+
+    if (slba + nlb > ns->id_ns.nsze) {
+        return NVME_LBA_RANGE | NVME_DNR;
+    }
+
+    req->has_sg = false;
+    block_acct_start(blk_get_stats(n->conf.blk), &req->acct, 0,
+                     BLOCK_ACCT_WRITE);
+    req->aiocb = blk_aio_pwrite_zeroes(n->conf.blk, aio_slba, aio_nlb,
+                                        BDRV_REQ_MAY_UNMAP, nvme_rw_cb, req);
+    return NVME_NO_COMPLETE;
+}
+
 static uint16_t nvme_rw(NvmeCtrl *n, NvmeNamespace *ns, NvmeCmd *cmd,
     NvmeRequest *req)
 {
@@ -279,6 +302,8 @@ static uint16_t nvme_io_cmd(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
     switch (cmd->opcode) {
     case NVME_CMD_FLUSH:
         return nvme_flush(n, ns, cmd, req);
+    case NVME_CMD_WRITE_ZEROS:
+        return nvme_write_zeros(n, ns, cmd, req);
     case NVME_CMD_WRITE:
     case NVME_CMD_READ:
         return nvme_rw(n, ns, cmd, req);
@@ -895,6 +920,7 @@ static int nvme_init(PCIDevice *pci_dev)
     id->sqes = (0x6 << 4) | 0x6;
     id->cqes = (0x4 << 4) | 0x4;
     id->nn = cpu_to_le32(n->num_namespaces);
+    id->oncs = cpu_to_le16(NVME_ONCS_WRITE_ZEROS);
     id->psd[0].mp = cpu_to_le16(0x9c4);
     id->psd[0].enlat = cpu_to_le32(0x10);
     id->psd[0].exlat = cpu_to_le32(0x4);
diff --git a/hw/block/nvme.h b/hw/block/nvme.h
index 8fb0c10..a0d1564 100644
--- a/hw/block/nvme.h
+++ b/hw/block/nvme.h
@@ -179,6 +179,7 @@ enum NvmeIoCommands {
     NVME_CMD_READ               = 0x02,
     NVME_CMD_WRITE_UNCOR        = 0x04,
     NVME_CMD_COMPARE            = 0x05,
+    NVME_CMD_WRITE_ZEROS        = 0x08,
     NVME_CMD_DSM                = 0x09,
 };