hw/block/nvme: add check for mdts

Add 'mdts' device parameter to control the Maximum Data Transfer Size of
the controller and check that it is respected.

Signed-off-by: Klaus Jensen <k.jensen@samsung.com>
Reviewed-by: Maxim Levitsky <mlevitsk@redhat.com>
Reviewed-by: Minwoo Im <minwoo.im.dev@gmail.com>

3 files changed, 31 insertions, 1 deletions

diff --git a/hw/block/nvme.c b/hw/block/nvme.c
index 8dade3e..30b42e2 100644
--- a/hw/block/nvme.c
+++ b/hw/block/nvme.c
@@ -21,7 +21,8 @@
  *              cmb_size_mb=<cmb_size_mb[optional]>, \
  *              [pmrdev=<mem_backend_file_id>,] \
  *              max_ioqpairs=<N[optional]>, \
- *              aerl=<N[optional]>, aer_max_queued=<N[optional]>
+ *              aerl=<N[optional]>, aer_max_queued=<N[optional]>, \
+ *              mdts=<N[optional]>
  *
  * Note cmb_size_mb denotes size of CMB in MB. CMB is assumed to be at
  * offset 0 in BAR2 and supports only WDS, RDS and SQS for now.
@@ -570,6 +571,17 @@ static void nvme_clear_events(NvmeCtrl *n, uint8_t event_type)
     }
 }
 
+static inline uint16_t nvme_check_mdts(NvmeCtrl *n, size_t len)
+{
+    uint8_t mdts = n->params.mdts;
+
+    if (mdts && len > n->page_size << mdts) {
+        return NVME_INVALID_FIELD | NVME_DNR;
+    }
+
+    return NVME_SUCCESS;
+}
+
 static inline uint16_t nvme_check_bounds(NvmeCtrl *n, NvmeNamespace *ns,
                                          uint64_t slba, uint32_t nlb)
 {
@@ -663,6 +675,13 @@ static uint16_t nvme_rw(NvmeCtrl *n, NvmeNamespace *ns, NvmeCmd *cmd,
 
     trace_pci_nvme_rw(is_write ? "write" : "read", nlb, data_size, slba);
 
+    status = nvme_check_mdts(n, data_size);
+    if (status) {
+        trace_pci_nvme_err_mdts(nvme_cid(req), data_size);
+        block_acct_invalid(blk_get_stats(n->conf.blk), acct);
+        return status;
+    }
+
     status = nvme_check_bounds(n, ns, slba, nlb);
     if (status) {
         trace_pci_nvme_err_invalid_lba_range(slba, nlb, ns->id_ns.nsze);
@@ -956,6 +975,7 @@ static uint16_t nvme_get_log(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
     uint32_t numdl, numdu;
     uint64_t off, lpol, lpou;
     size_t   len;
+    uint16_t status;
 
     numdl = (dw10 >> 16);
     numdu = (dw11 & 0xffff);
@@ -971,6 +991,12 @@ static uint16_t nvme_get_log(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
 
     trace_pci_nvme_get_log(nvme_cid(req), lid, lsp, rae, len, off);
 
+    status = nvme_check_mdts(n, len);
+    if (status) {
+        trace_pci_nvme_err_mdts(nvme_cid(req), len);
+        return status;
+    }
+
     switch (lid) {
     case NVME_LOG_ERROR_INFO:
         return nvme_error_info(n, cmd, rae, len, off, req);
@@ -2299,6 +2325,7 @@ static void nvme_init_ctrl(NvmeCtrl *n, PCIDevice *pci_dev)
     id->ieee[0] = 0x00;
     id->ieee[1] = 0x02;
     id->ieee[2] = 0xb3;
+    id->mdts = n->params.mdts;
     id->ver = cpu_to_le32(NVME_SPEC_VER);
     id->oacs = cpu_to_le16(0);
 
@@ -2418,6 +2445,7 @@ static Property nvme_props[] = {
     DEFINE_PROP_UINT16("msix_qsize", NvmeCtrl, params.msix_qsize, 65),
     DEFINE_PROP_UINT8("aerl", NvmeCtrl, params.aerl, 3),
     DEFINE_PROP_UINT32("aer_max_queued", NvmeCtrl, params.aer_max_queued, 64),
+    DEFINE_PROP_UINT8("mdts", NvmeCtrl, params.mdts, 7),
     DEFINE_PROP_END_OF_LIST(),
 };
 
diff --git a/hw/block/nvme.h b/hw/block/nvme.h
index 5519b5c..137cd8c 100644
--- a/hw/block/nvme.h
+++ b/hw/block/nvme.h
@@ -11,6 +11,7 @@ typedef struct NvmeParams {
     uint32_t cmb_size_mb;
     uint8_t  aerl;
     uint32_t aer_max_queued;
+    uint8_t  mdts;
 } NvmeParams;
 
 typedef struct NvmeAsyncEvent {
diff --git a/hw/block/trace-events b/hw/block/trace-events
index f20c59a..72cf2d1 100644
--- a/hw/block/trace-events
+++ b/hw/block/trace-events
@@ -85,6 +85,7 @@ pci_nvme_mmio_shutdown_set(void) "shutdown bit set"
 pci_nvme_mmio_shutdown_cleared(void) "shutdown bit cleared"
 
 # nvme traces for error conditions
+pci_nvme_err_mdts(uint16_t cid, size_t len) "cid %"PRIu16" len %zu"
 pci_nvme_err_invalid_dma(void) "PRP/SGL is too small for transfer size"
 pci_nvme_err_invalid_prplist_ent(uint64_t prplist) "PRP list entry is null or not page aligned: 0x%"PRIx64""
 pci_nvme_err_invalid_prp2_align(uint64_t prp2) "PRP2 is not page aligned: 0x%"PRIx64""