Include qemu/main-loop.h less

[qemu.git] / block / nvme.c

diff --git a/block/nvme.c b/block/nvme.c
index 73ed5fa75f2e6c8833a9b7c09e8bcce93c9b8eee..5be3a39b632ec327406c730c3a7dad164c38ddda 100644 (file)
--- a/block/nvme.c
+++ b/block/nvme.c
@@ -17,6 +17,7 @@
 #include "qapi/qmp/qdict.h"
 #include "qapi/qmp/qstring.h"
 #include "qemu/error-report.h"
+#include "qemu/main-loop.h"
 #include "qemu/module.h"
 #include "qemu/cutils.h"
 #include "qemu/option.h"
@@ -102,8 +103,11 @@ 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. */
+    int blkshift;
+
     uint64_t max_transfer;
     bool plugged;
 
@@ -217,7 +221,7 @@ static NVMeQueuePair *nvme_create_queue_pair(BlockDriverState *bs,
         error_propagate(errp, local_err);
         goto fail;
     }
-    q->cq.doorbell = &s->regs->doorbells[idx * 2 * s->doorbell_scale + 1];
+    q->cq.doorbell = &s->regs->doorbells[(idx * 2 + 1) * s->doorbell_scale];
 
     return q;
 fail:
@@ -315,7 +319,7 @@ static bool nvme_process_completion(BDRVNVMeState *s, NVMeQueuePair *q)
     while (q->inflight) {
         int16_t cid;
         c = (NvmeCqe *)&q->cq.queue[q->cq.head * NVME_CQ_ENTRY_BYTES];
-        if (!c->cid || (le16_to_cpu(c->status) & 0x1) == q->cq_phase) {
+        if ((le16_to_cpu(c->status) & 0x1) == q->cq_phase) {
             break;
         }
         q->cq.head = (q->cq.head + 1) % NVME_QUEUE_SIZE;
@@ -339,10 +343,7 @@ static bool nvme_process_completion(BDRVNVMeState *s, NVMeQueuePair *q)
         qemu_mutex_unlock(&q->lock);
         req.cb(req.opaque, nvme_translate_error(c));
         qemu_mutex_lock(&q->lock);
-        c->cid = cpu_to_le16(0);
         q->inflight--;
-        /* Flip Phase Tag bit. */
-        c->status = cpu_to_le16(le16_to_cpu(c->status) ^ 0x1);
         progress = true;
     }
     if (progress) {
@@ -418,6 +419,7 @@ 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;
     uint64_t iova;
@@ -466,7 +468,22 @@ 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;
+    }
 
+    if (lbaf->ds < BDRV_SECTOR_BITS || lbaf->ds > 12 ||
+        (1 << lbaf->ds) > s->page_size)
+    {
+        error_setg(errp, "Namespace has unsupported block size (2^%d)",
+                   lbaf->ds);
+        goto out;
+    }
+
+    s->blkshift = lbaf->ds;
 out:
     qemu_vfio_dma_unmap(s->vfio, resp);
     qemu_vfree(resp);
@@ -613,12 +630,12 @@ static int nvme_init(BlockDriverState *bs, const char *device, int namespace,
 
     /* Set up admin queue. */
     s->queues = g_new(NVMeQueuePair *, 1);
-    s->nr_queues = 1;
     s->queues[0] = nvme_create_queue_pair(bs, 0, NVME_QUEUE_SIZE, errp);
     if (!s->queues[0]) {
         ret = -EINVAL;
         goto out;
     }
+    s->nr_queues = 1;
     QEMU_BUILD_BUG_ON(NVME_QUEUE_SIZE & 0xF000);
     s->regs->aqa = cpu_to_le32((NVME_QUEUE_SIZE << 16) | NVME_QUEUE_SIZE);
     s->regs->asq = cpu_to_le64(s->queues[0]->sq.iova);
@@ -785,8 +802,22 @@ fail:
 static int64_t nvme_getlength(BlockDriverState *bs)
 {
     BDRVNVMeState *s = bs->opaque;
+    return s->nsze << s->blkshift;
+}
 
-    return s->nsze << BDRV_SECTOR_BITS;
+static uint32_t nvme_get_blocksize(BlockDriverState *bs)
+{
+    BDRVNVMeState *s = bs->opaque;
+    assert(s->blkshift >= BDRV_SECTOR_BITS && s->blkshift <= 12);
+    return UINT32_C(1) << s->blkshift;
+}
+
+static int nvme_probe_blocksizes(BlockDriverState *bs, BlockSizes *bsz)
+{
+    uint32_t blocksize = nvme_get_blocksize(bs);
+    bsz->phys = blocksize;
+    bsz->log = blocksize;
+    return 0;
 }
 
 /* Called with s->dma_map_lock */
@@ -917,13 +948,14 @@ 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 +1186,7 @@ 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,