Skip to contentSkip to conversation

nvme: refactoring and cleanups

PATCH Superseded Klaus Jensen 3 participants 33 messages Apr 15, 2020

v1 of 7 Superseded Latest is v7 →

lore
Share & tools
lore
#1 lore raw

PATCH 1/16 nvme: fix pci doorbell size calculation

In reply to Klaus Jensen

From: Klaus Jensen <[email protected]>

The size of the BAR is 0x1000 (main registers) + 8 bytes for each queue. Currently, the size of the BAR is calculated like so:

    n->reg_size = pow2ceil(0x1004 + 2 * (n->params.num_queues + 1) * 4);

Since the 'num_queues' parameter already accounts for the admin queue, this should in any case not need to be incremented by one. Also, the size should be initialized to (0x1000).

    n->reg_size = pow2ceil(0x1000 + 2 * n->params.num_queues * 4);

This, with the default value of num_queues (64), we will set aside room for 1 admin queue and 63 I/O queues (4 bytes per doorbell, 2 doorbells per queue).

---
 hw/block/nvme.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
hw/block/nvme.c +1 -1
index d28335cbf377..77f9c151a665 100644
@@ -1345,7 +1345,7 @@ static void nvme_realize(PCIDevice *pci_dev, Error **errp)
     pcie_endpoint_cap_init(pci_dev, 0x80);
 
     n->num_namespaces = 1;
-    n->reg_size = pow2ceil(0x1004 + 2 * (n->num_queues + 1) * 4);
+    n->reg_size = pow2ceil(0x1000 + 2 * n->num_queues * 4);
     n->ns_size = bs_size / (uint64_t)n->num_namespaces;
 
     n->namespaces = g_new0(NvmeNamespace, n->num_namespaces);
Signature · 1 line
2.26.0
#7 lore raw

PATCH 5/16 nvme: use constants in identify

In reply to Klaus Jensen

From: Klaus Jensen <[email protected]>

---
 hw/block/nvme.c      | 8 ++++----
 include/block/nvme.h | 8 ++++++++
 2 files changed, 12 insertions(+), 4 deletions(-)
hw/block/nvme.c +4 -4
index 7ddfe8a21b03..12f97aed0c15 100644
@@ -679,7 +679,7 @@ static uint16_t nvme_identify_ns(NvmeCtrl *n, NvmeIdentify *c)
 
 static uint16_t nvme_identify_nslist(NvmeCtrl *n, NvmeIdentify *c)
 {
-    static const int data_len = 4 * KiB;
+    static const int data_len = NVME_IDENTIFY_DATA_SIZE;
     uint32_t min_nsid = le32_to_cpu(c->nsid);
     uint64_t prp1 = le64_to_cpu(c->prp1);
     uint64_t prp2 = le64_to_cpu(c->prp2);
@@ -709,11 +709,11 @@ static uint16_t nvme_identify(NvmeCtrl *n, NvmeCmd *cmd)
     NvmeIdentify *c = (NvmeIdentify *)cmd;
 
     switch (le32_to_cpu(c->cns)) {
-    case 0x00:
+    case NVME_ID_CNS_NS:
         return nvme_identify_ns(n, c);
-    case 0x01:
+    case NVME_ID_CNS_CTRL:
         return nvme_identify_ctrl(n, c);
-    case 0x02:
+    case NVME_ID_CNS_NS_ACTIVE_LIST:
         return nvme_identify_nslist(n, c);
     default:
         trace_nvme_dev_err_invalid_identify_cns(le32_to_cpu(c->cns));
include/block/nvme.h +8 -0
index 8fb941c6537c..c2fd01cf2f1d 100644
@@ -533,6 +533,14 @@ typedef struct NvmePSD {
     uint8_t     resv[16];
 } NvmePSD;
 
+#define NVME_IDENTIFY_DATA_SIZE 4096
+
+enum {
+    NVME_ID_CNS_NS             = 0x0,
+    NVME_ID_CNS_CTRL           = 0x1,
+    NVME_ID_CNS_NS_ACTIVE_LIST = 0x2,
+};
+
 typedef struct NvmeIdCtrl {
     uint16_t    vid;
     uint16_t    ssvid;
Signature · 1 line
2.26.0
#5 lore raw

PATCH 3/16 nvme: remove superfluous breaks

In reply to Klaus Jensen

From: Klaus Jensen <[email protected]>

These break statements was left over when commit 3036a626e9ef ("nvme:
add Get/Set Feature Timestamp support") was merged.

---
 hw/block/nvme.c | 4 ----
 1 file changed, 4 deletions(-)
hw/block/nvme.c +0 -4
index 316cfc4d36e0..0023876090ef 100644
@@ -788,7 +788,6 @@ static uint16_t nvme_get_feature(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
         break;
     case NVME_TIMESTAMP:
         return nvme_get_feature_timestamp(n, cmd);
-        break;
     default:
         trace_nvme_dev_err_invalid_getfeat(dw10);
         return NVME_INVALID_FIELD | NVME_DNR;
@@ -832,11 +831,8 @@ static uint16_t nvme_set_feature(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
         req->cqe.result =
             cpu_to_le32((n->num_queues - 2) | ((n->num_queues - 2) << 16));
         break;
-
     case NVME_TIMESTAMP:
         return nvme_set_feature_timestamp(n, cmd);
-        break;
-
     default:
         trace_nvme_dev_err_invalid_setfeat(dw10);
         return NVME_INVALID_FIELD | NVME_DNR;
Signature · 1 line
2.26.0
#9 lore raw

PATCH 7/16 nvme: add max_ioqpairs device parameter

In reply to Klaus Jensen

From: Klaus Jensen <[email protected]>

The num_queues device paramater has a slightly confusing meaning because it accounts for the admin queue pair which is not really optional. Secondly, it is really a maximum value of queues allowed.

Add a new max_ioqpairs parameter that only accounts for I/O queue pairs, but keep num_queues for compatibility.

---
 hw/block/nvme.c | 46 ++++++++++++++++++++++++++++------------------
 hw/block/nvme.h |  4 +++-
 2 files changed, 31 insertions(+), 19 deletions(-)
hw/block/nvme.c +28 -18
index 287e1e49c0bf..9383d2cb0b38 100644
@@ -19,7 +19,7 @@
  *      -drive file=<file>,if=none,id=<drive_id>
  *      -device nvme,drive=<drive_id>,serial=<serial>,id=<id[optional]>, \
  *              cmb_size_mb=<cmb_size_mb[optional]>, \
- *              num_queues=<N[optional]>
+ *              max_ioqpairs=<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.
@@ -27,6 +27,7 @@
 
 #include "qemu/osdep.h"
 #include "qemu/units.h"
+#include "qemu/error-report.h"
 #include "hw/block/block.h"
 #include "hw/pci/msix.h"
 #include "hw/pci/pci.h"
@@ -72,12 +73,12 @@ static void nvme_addr_read(NvmeCtrl *n, hwaddr addr, void *buf, int size)
 
 static int nvme_check_sqid(NvmeCtrl *n, uint16_t sqid)
 {
-    return sqid < n->params.num_queues && n->sq[sqid] != NULL ? 0 : -1;
+    return sqid < n->params.max_ioqpairs + 1 && n->sq[sqid] != NULL ? 0 : -1;
 }
 
 static int nvme_check_cqid(NvmeCtrl *n, uint16_t cqid)
 {
-    return cqid < n->params.num_queues && n->cq[cqid] != NULL ? 0 : -1;
+    return cqid < n->params.max_ioqpairs + 1 && n->cq[cqid] != NULL ? 0 : -1;
 }
 
 static void nvme_inc_cq_tail(NvmeCQueue *cq)
@@ -639,7 +640,7 @@ static uint16_t nvme_create_cq(NvmeCtrl *n, NvmeCmd *cmd)
         trace_nvme_dev_err_invalid_create_cq_addr(prp1);
         return NVME_INVALID_FIELD | NVME_DNR;
     }
-    if (unlikely(vector > n->params.num_queues)) {
+    if (unlikely(vector > n->params.max_ioqpairs + 1)) {
         trace_nvme_dev_err_invalid_create_cq_vector(vector);
         return NVME_INVALID_IRQ_VECTOR | NVME_DNR;
     }
@@ -791,8 +792,8 @@ static uint16_t nvme_get_feature(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
         trace_nvme_dev_getfeat_vwcache(result ? "enabled" : "disabled");
         break;
     case NVME_NUMBER_OF_QUEUES:
-        result = cpu_to_le32((n->params.num_queues - 2) |
-                             ((n->params.num_queues - 2) << 16));
+        result = cpu_to_le32((n->params.max_ioqpairs - 1) |
+                             ((n->params.max_ioqpairs - 1) << 16));
         trace_nvme_dev_getfeat_numq(result);
         break;
     case NVME_TIMESTAMP:
@@ -836,10 +837,10 @@ static uint16_t nvme_set_feature(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
     case NVME_NUMBER_OF_QUEUES:
         trace_nvme_dev_setfeat_numq((dw11 & 0xFFFF) + 1,
                                     ((dw11 >> 16) & 0xFFFF) + 1,
-                                    n->params.num_queues - 1,
-                                    n->params.num_queues - 1);
-        req->cqe.result = cpu_to_le32((n->params.num_queues - 2) |
-                                      ((n->params.num_queues - 2) << 16));
+                                    n->params.max_ioqpairs,
+                                    n->params.max_ioqpairs);
+        req->cqe.result = cpu_to_le32((n->params.max_ioqpairs - 1) |
+                                      ((n->params.max_ioqpairs - 1) << 16));
         break;
     case NVME_TIMESTAMP:
         return nvme_set_feature_timestamp(n, cmd);
@@ -910,12 +911,12 @@ static void nvme_clear_ctrl(NvmeCtrl *n)
 
     blk_drain(n->conf.blk);
 
-    for (i = 0; i < n->params.num_queues; i++) {
+    for (i = 0; i < n->params.max_ioqpairs + 1; i++) {
         if (n->sq[i] != NULL) {
             nvme_free_sq(n->sq[i], n);
         }
     }
-    for (i = 0; i < n->params.num_queues; i++) {
+    for (i = 0; i < n->params.max_ioqpairs + 1; i++) {
         if (n->cq[i] != NULL) {
             nvme_free_cq(n->cq[i], n);
         }
@@ -1316,8 +1317,17 @@ static void nvme_realize(PCIDevice *pci_dev, Error **errp)
     int64_t bs_size;
     uint8_t *pci_conf;
 
-    if (!n->params.num_queues) {
-        error_setg(errp, "num_queues can't be zero");
+    if (n->params.num_queues) {
+        warn_report("num_queues is deprecated; please use max_ioqpairs "
+                    "instead");
+
+        n->params.max_ioqpairs = n->params.num_queues - 1;
+    }
+
+    if (n->params.max_ioqpairs < 1 ||
+        n->params.max_ioqpairs > PCI_MSIX_FLAGS_QSIZE) {
+        error_setg(errp, "max_ioqpairs must be between 1 and %d",
+                   PCI_MSIX_FLAGS_QSIZE);
         return;
     }
 
@@ -1349,19 +1359,19 @@ static void nvme_realize(PCIDevice *pci_dev, Error **errp)
     pcie_endpoint_cap_init(pci_dev, 0x80);
 
     n->num_namespaces = 1;
-    n->reg_size = pow2ceil(0x1000 + 2 * n->params.num_queues * 4);
+    n->reg_size = pow2ceil(0x1008 + 2 * (n->params.max_ioqpairs) * 4);
     n->ns_size = bs_size / (uint64_t)n->num_namespaces;
 
     n->namespaces = g_new0(NvmeNamespace, n->num_namespaces);
-    n->sq = g_new0(NvmeSQueue *, n->params.num_queues);
-    n->cq = g_new0(NvmeCQueue *, n->params.num_queues);
+    n->sq = g_new0(NvmeSQueue *, n->params.max_ioqpairs + 1);
+    n->cq = g_new0(NvmeCQueue *, n->params.max_ioqpairs + 1);
 
     memory_region_init_io(&n->iomem, OBJECT(n), &nvme_mmio_ops, n,
                           "nvme", n->reg_size);
     pci_register_bar(pci_dev, 0,
         PCI_BASE_ADDRESS_SPACE_MEMORY | PCI_BASE_ADDRESS_MEM_TYPE_64,
         &n->iomem);
-    msix_init_exclusive_bar(pci_dev, n->params.num_queues, 4, NULL);
+    msix_init_exclusive_bar(pci_dev, n->params.max_ioqpairs + 1, 4, NULL);
 
     id->vid = cpu_to_le16(pci_get_word(pci_conf + PCI_VENDOR_ID));
     id->ssvid = cpu_to_le16(pci_get_word(pci_conf + PCI_SUBSYSTEM_VENDOR_ID));
hw/block/nvme.h +3 -1
index 9957c4a200e2..98f5b9479244 100644
@@ -6,11 +6,13 @@
 #define DEFINE_NVME_PROPERTIES(_state, _props) \
     DEFINE_PROP_STRING("serial", _state, _props.serial), \
     DEFINE_PROP_UINT32("cmb_size_mb", _state, _props.cmb_size_mb, 0), \
-    DEFINE_PROP_UINT32("num_queues", _state, _props.num_queues, 64)
+    DEFINE_PROP_UINT32("num_queues", _state, _props.num_queues, 0), \
+    DEFINE_PROP_UINT32("max_ioqpairs", _state, _props.max_ioqpairs, 64)
 
 typedef struct NvmeParams {
     char     *serial;
     uint32_t num_queues;
+    uint32_t max_ioqpairs;
     uint32_t cmb_size_mb;
 } NvmeParams;
 
Signature · 1 line
2.26.0
#0 lore raw

cover nvme: refactoring and cleanups

From: Klaus Jensen <[email protected]>

Philippe suggested that I split up this already way too huge series (more than 50 patches now), so here goes.

The first patch in this series fixes a small bug in the pci doorbell size calculation. Please consider cherry-picking this.

The rest are refactorings. The "nvme: add max_ioqpairs device parameter" introduces the 'max_ioqpairs' device parameter, the meaning of which should be more intuitive than the existing 'num_queues' parameter.

Klaus Jensen (16):
nvme: fix pci doorbell size calculation
nvme: rename trace events to nvme_dev
nvme: remove superfluous breaks
nvme: move device parameters to separate struct
nvme: use constants in identify
nvme: refactor nvme_addr_read
nvme: add max_ioqpairs device parameter
nvme: remove redundant cmbloc/cmbsz members
nvme: factor out property/constraint checks
nvme: factor out device state setup
nvme: factor out block backend setup
nvme: add namespace helpers
nvme: factor out namespace setup
nvme: factor out pci setup
nvme: factor out cmb setup
nvme: factor out controller identify setup

 hw/block/nvme.c       | 436 ++++++++++++++++++++++++------------------
 hw/block/nvme.h       |  36 +++-
 hw/block/trace-events | 172 ++++++++---------
 include/block/nvme.h  |   8 +
 4 files changed, 373 insertions(+), 279 deletions(-)
Signature · 1 line
2.26.0
#12 lore raw

PATCH 9/16 nvme: factor out property/constraint checks

From: Klaus Jensen <[email protected]>

---
 hw/block/nvme.c | 52 ++++++++++++++++++++++++++++++-------------------
 1 file changed, 32 insertions(+), 20 deletions(-)
hw/block/nvme.c +32 -20
index ea613213bd57..635292d6fac4 100644
@@ -1308,6 +1308,37 @@ static const MemoryRegionOps nvme_cmb_ops = {
     },
 };
 
+static int nvme_check_constraints(NvmeCtrl *n, Error **errp)
+{
+    NvmeParams *params = &n->params;
+
+    if (params->num_queues) {
+        warn_report("num_queues is deprecated; please use max_ioqpairs "
+                    "instead");
+
+        params->max_ioqpairs = params->num_queues - 1;
+    }
+
+    if (params->max_ioqpairs < 1 ||
+        params->max_ioqpairs > PCI_MSIX_FLAGS_QSIZE) {
+        error_setg(errp, "max_ioqpairs must be between 1 and %d",
+                   PCI_MSIX_FLAGS_QSIZE);
+        return -1;
+    }
+
+    if (!n->conf.blk) {
+        error_setg(errp, "drive property not set");
+        return -1;
+    }
+
+    if (!params->serial) {
+        error_setg(errp, "serial property not set");
+        return -1;
+    }
+
+    return 0;
+}
+
 static void nvme_realize(PCIDevice *pci_dev, Error **errp)
 {
     NvmeCtrl *n = NVME(pci_dev);
@@ -1317,22 +1348,7 @@ static void nvme_realize(PCIDevice *pci_dev, Error **errp)
     int64_t bs_size;
     uint8_t *pci_conf;
 
-    if (n->params.num_queues) {
-        warn_report("num_queues is deprecated; please use max_ioqpairs "
-                    "instead");
-
-        n->params.max_ioqpairs = n->params.num_queues - 1;
-    }
-
-    if (n->params.max_ioqpairs < 1 ||
-        n->params.max_ioqpairs > PCI_MSIX_FLAGS_QSIZE) {
-        error_setg(errp, "max_ioqpairs must be between 1 and %d",
-                   PCI_MSIX_FLAGS_QSIZE);
-        return;
-    }
-
-    if (!n->conf.blk) {
-        error_setg(errp, "drive property not set");
+    if (nvme_check_constraints(n, errp)) {
         return;
     }
 
@@ -1342,10 +1358,6 @@ static void nvme_realize(PCIDevice *pci_dev, Error **errp)
         return;
     }
 
-    if (!n->params.serial) {
-        error_setg(errp, "serial property not set");
-        return;
-    }
     blkconf_blocksizes(&n->conf);
     if (!blkconf_apply_backend_options(&n->conf, blk_is_read_only(n->conf.blk),
                                        false, errp)) {
Signature · 1 line
2.26.0
#30 lore raw

PATCH 16/16 nvme: factor out controller identify setup

In reply to Klaus Jensen

From: Klaus Jensen <[email protected]>

---
 hw/block/nvme.c | 42 ++++++++++++++++++++++++------------------
 1 file changed, 24 insertions(+), 18 deletions(-)
hw/block/nvme.c +24 -18
index 7387cf409f96..d1566b56381d 100644
@@ -1428,27 +1428,11 @@ static void nvme_init_pci(NvmeCtrl *n, PCIDevice *pci_dev)
     }
 }
 
-static void nvme_realize(PCIDevice *pci_dev, Error **errp)
+static void nvme_init_ctrl(NvmeCtrl *n, PCIDevice *pci_dev)
 {
-    NvmeCtrl *n = NVME(pci_dev);
     NvmeIdCtrl *id = &n->id_ctrl;
+    uint8_t *pci_conf = pci_dev->config;
 
-    int i;
-    uint8_t *pci_conf;
-
-    if (nvme_check_constraints(n, errp)) {
-        return;
-    }
-
-    nvme_init_state(n);
-
-    if (nvme_init_blk(n, errp)) {
-        return;
-    }
-
-    nvme_init_pci(n, pci_dev);
-
-    pci_conf = pci_dev->config;
     id->vid = cpu_to_le16(pci_get_word(pci_conf + PCI_VENDOR_ID));
     id->ssvid = cpu_to_le16(pci_get_word(pci_conf + PCI_SUBSYSTEM_VENDOR_ID));
     strpadcpy((char *)id->mn, sizeof(id->mn), "QEMU NVMe Ctrl", ' ');
@@ -1482,6 +1466,28 @@ static void nvme_realize(PCIDevice *pci_dev, Error **errp)
     n->bar.vs = 0x00010200;
     n->bar.intmc = n->bar.intms = 0;
 
+
+}
+
+static void nvme_realize(PCIDevice *pci_dev, Error **errp)
+{
+    NvmeCtrl *n = NVME(pci_dev);
+
+    int i;
+
+    if (nvme_check_constraints(n, errp)) {
+        return;
+    }
+
+    nvme_init_state(n);
+
+    if (nvme_init_blk(n, errp)) {
+        return;
+    }
+
+    nvme_init_pci(n, pci_dev);
+    nvme_init_ctrl(n, pci_dev);
+
     for (i = 0; i < n->num_namespaces; i++) {
         if (nvme_init_namespace(n, &n->namespaces[i], errp)) {
             return;
Signature · 1 line
2.26.0
#6 lore raw

PATCH 4/16 nvme: move device parameters to separate struct

In reply to Klaus Jensen

From: Klaus Jensen <[email protected]>

Move device configuration parameters to separate struct to make it explicit what is configurable and what is set internally.

---
 hw/block/nvme.c | 44 ++++++++++++++++++++++----------------------
 hw/block/nvme.h | 16 +++++++++++++---
 2 files changed, 35 insertions(+), 25 deletions(-)
hw/block/nvme.c +22 -22
index 0023876090ef..7ddfe8a21b03 100644
@@ -64,12 +64,12 @@ static void nvme_addr_read(NvmeCtrl *n, hwaddr addr, void *buf, int size)
 
 static int nvme_check_sqid(NvmeCtrl *n, uint16_t sqid)
 {
-    return sqid < n->num_queues && n->sq[sqid] != NULL ? 0 : -1;
+    return sqid < n->params.num_queues && n->sq[sqid] != NULL ? 0 : -1;
 }
 
 static int nvme_check_cqid(NvmeCtrl *n, uint16_t cqid)
 {
-    return cqid < n->num_queues && n->cq[cqid] != NULL ? 0 : -1;
+    return cqid < n->params.num_queues && n->cq[cqid] != NULL ? 0 : -1;
 }
 
 static void nvme_inc_cq_tail(NvmeCQueue *cq)
@@ -631,7 +631,7 @@ static uint16_t nvme_create_cq(NvmeCtrl *n, NvmeCmd *cmd)
         trace_nvme_dev_err_invalid_create_cq_addr(prp1);
         return NVME_INVALID_FIELD | NVME_DNR;
     }
-    if (unlikely(vector > n->num_queues)) {
+    if (unlikely(vector > n->params.num_queues)) {
         trace_nvme_dev_err_invalid_create_cq_vector(vector);
         return NVME_INVALID_IRQ_VECTOR | NVME_DNR;
     }
@@ -783,7 +783,8 @@ static uint16_t nvme_get_feature(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
         trace_nvme_dev_getfeat_vwcache(result ? "enabled" : "disabled");
         break;
     case NVME_NUMBER_OF_QUEUES:
-        result = cpu_to_le32((n->num_queues - 2) | ((n->num_queues - 2) << 16));
+        result = cpu_to_le32((n->params.num_queues - 2) |
+                             ((n->params.num_queues - 2) << 16));
         trace_nvme_dev_getfeat_numq(result);
         break;
     case NVME_TIMESTAMP:
@@ -827,9 +828,10 @@ static uint16_t nvme_set_feature(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
     case NVME_NUMBER_OF_QUEUES:
         trace_nvme_dev_setfeat_numq((dw11 & 0xFFFF) + 1,
                                     ((dw11 >> 16) & 0xFFFF) + 1,
-                                    n->num_queues - 1, n->num_queues - 1);
-        req->cqe.result =
-            cpu_to_le32((n->num_queues - 2) | ((n->num_queues - 2) << 16));
+                                    n->params.num_queues - 1,
+                                    n->params.num_queues - 1);
+        req->cqe.result = cpu_to_le32((n->params.num_queues - 2) |
+                                      ((n->params.num_queues - 2) << 16));
         break;
     case NVME_TIMESTAMP:
         return nvme_set_feature_timestamp(n, cmd);
@@ -900,12 +902,12 @@ static void nvme_clear_ctrl(NvmeCtrl *n)
 
     blk_drain(n->conf.blk);
 
-    for (i = 0; i < n->num_queues; i++) {
+    for (i = 0; i < n->params.num_queues; i++) {
         if (n->sq[i] != NULL) {
             nvme_free_sq(n->sq[i], n);
         }
     }
-    for (i = 0; i < n->num_queues; i++) {
+    for (i = 0; i < n->params.num_queues; i++) {
         if (n->cq[i] != NULL) {
             nvme_free_cq(n->cq[i], n);
         }
@@ -1306,7 +1308,7 @@ static void nvme_realize(PCIDevice *pci_dev, Error **errp)
     int64_t bs_size;
     uint8_t *pci_conf;
 
-    if (!n->num_queues) {
+    if (!n->params.num_queues) {
         error_setg(errp, "num_queues can't be zero");
         return;
     }
@@ -1322,7 +1324,7 @@ static void nvme_realize(PCIDevice *pci_dev, Error **errp)
         return;
     }
 
-    if (!n->serial) {
+    if (!n->params.serial) {
         error_setg(errp, "serial property not set");
         return;
     }
@@ -1339,25 +1341,25 @@ static void nvme_realize(PCIDevice *pci_dev, Error **errp)
     pcie_endpoint_cap_init(pci_dev, 0x80);
 
     n->num_namespaces = 1;
-    n->reg_size = pow2ceil(0x1000 + 2 * n->num_queues * 4);
+    n->reg_size = pow2ceil(0x1000 + 2 * n->params.num_queues * 4);
     n->ns_size = bs_size / (uint64_t)n->num_namespaces;
 
     n->namespaces = g_new0(NvmeNamespace, n->num_namespaces);
-    n->sq = g_new0(NvmeSQueue *, n->num_queues);
-    n->cq = g_new0(NvmeCQueue *, n->num_queues);
+    n->sq = g_new0(NvmeSQueue *, n->params.num_queues);
+    n->cq = g_new0(NvmeCQueue *, n->params.num_queues);
 
     memory_region_init_io(&n->iomem, OBJECT(n), &nvme_mmio_ops, n,
                           "nvme", n->reg_size);
     pci_register_bar(pci_dev, 0,
         PCI_BASE_ADDRESS_SPACE_MEMORY | PCI_BASE_ADDRESS_MEM_TYPE_64,
         &n->iomem);
-    msix_init_exclusive_bar(pci_dev, n->num_queues, 4, NULL);
+    msix_init_exclusive_bar(pci_dev, n->params.num_queues, 4, NULL);
 
     id->vid = cpu_to_le16(pci_get_word(pci_conf + PCI_VENDOR_ID));
     id->ssvid = cpu_to_le16(pci_get_word(pci_conf + PCI_SUBSYSTEM_VENDOR_ID));
     strpadcpy((char *)id->mn, sizeof(id->mn), "QEMU NVMe Ctrl", ' ');
     strpadcpy((char *)id->fr, sizeof(id->fr), "1.0", ' ');
-    strpadcpy((char *)id->sn, sizeof(id->sn), n->serial, ' ');
+    strpadcpy((char *)id->sn, sizeof(id->sn), n->params.serial, ' ');
     id->rab = 6;
     id->ieee[0] = 0x00;
     id->ieee[1] = 0x02;
@@ -1386,7 +1388,7 @@ static void nvme_realize(PCIDevice *pci_dev, Error **errp)
     n->bar.vs = 0x00010200;
     n->bar.intmc = n->bar.intms = 0;
 
-    if (n->cmb_size_mb) {
+    if (n->params.cmb_size_mb) {
 
         NVME_CMBLOC_SET_BIR(n->bar.cmbloc, 2);
         NVME_CMBLOC_SET_OFST(n->bar.cmbloc, 0);
@@ -1397,7 +1399,7 @@ static void nvme_realize(PCIDevice *pci_dev, Error **errp)
         NVME_CMBSZ_SET_RDS(n->bar.cmbsz, 1);
         NVME_CMBSZ_SET_WDS(n->bar.cmbsz, 1);
         NVME_CMBSZ_SET_SZU(n->bar.cmbsz, 2); /* MBs */
-        NVME_CMBSZ_SET_SZ(n->bar.cmbsz, n->cmb_size_mb);
+        NVME_CMBSZ_SET_SZ(n->bar.cmbsz, n->params.cmb_size_mb);
 
         n->cmbloc = n->bar.cmbloc;
         n->cmbsz = n->bar.cmbsz;
@@ -1436,7 +1438,7 @@ static void nvme_exit(PCIDevice *pci_dev)
     g_free(n->cq);
     g_free(n->sq);
 
-    if (n->cmb_size_mb) {
+    if (n->params.cmb_size_mb) {
         g_free(n->cmbuf);
     }
     msix_uninit_exclusive_bar(pci_dev);
@@ -1444,9 +1446,7 @@ static void nvme_exit(PCIDevice *pci_dev)
 
 static Property nvme_props[] = {
     DEFINE_BLOCK_PROPERTIES(NvmeCtrl, conf),
-    DEFINE_PROP_STRING("serial", NvmeCtrl, serial),
-    DEFINE_PROP_UINT32("cmb_size_mb", NvmeCtrl, cmb_size_mb, 0),
-    DEFINE_PROP_UINT32("num_queues", NvmeCtrl, num_queues, 64),
+    DEFINE_NVME_PROPERTIES(NvmeCtrl, params),
     DEFINE_PROP_END_OF_LIST(),
 };
 
hw/block/nvme.h +13 -3
index 557194ee1954..9957c4a200e2 100644
@@ -1,7 +1,19 @@
 #ifndef HW_NVME_H
 #define HW_NVME_H
+
 #include "block/nvme.h"
 
+#define DEFINE_NVME_PROPERTIES(_state, _props) \
+    DEFINE_PROP_STRING("serial", _state, _props.serial), \
+    DEFINE_PROP_UINT32("cmb_size_mb", _state, _props.cmb_size_mb, 0), \
+    DEFINE_PROP_UINT32("num_queues", _state, _props.num_queues, 64)
+
+typedef struct NvmeParams {
+    char     *serial;
+    uint32_t num_queues;
+    uint32_t cmb_size_mb;
+} NvmeParams;
+
 typedef struct NvmeAsyncEvent {
     QSIMPLEQ_ENTRY(NvmeAsyncEvent) entry;
     NvmeAerResult result;
@@ -63,6 +75,7 @@ typedef struct NvmeCtrl {
     MemoryRegion ctrl_mem;
     NvmeBar      bar;
     BlockConf    conf;
+    NvmeParams   params;
 
     uint32_t    page_size;
     uint16_t    page_bits;
@@ -71,10 +84,8 @@ typedef struct NvmeCtrl {
     uint16_t    sqe_size;
     uint32_t    reg_size;
     uint32_t    num_namespaces;
-    uint32_t    num_queues;
     uint32_t    max_q_ents;
     uint64_t    ns_size;
-    uint32_t    cmb_size_mb;
     uint32_t    cmbsz;
     uint32_t    cmbloc;
     uint8_t     *cmbuf;
@@ -82,7 +93,6 @@ typedef struct NvmeCtrl {
     uint64_t    host_timestamp;                 /* Timestamp sent by the host */
     uint64_t    timestamp_set_qemu_clock_ms;    /* QEMU clock time */
 
-    char            *serial;
     NvmeNamespace   *namespaces;
     NvmeSQueue      **sq;
     NvmeCQueue      **cq;
Signature · 1 line
2.26.0
#8 lore raw

PATCH 6/16 nvme: refactor nvme_addr_read

In reply to Klaus Jensen

From: Klaus Jensen <[email protected]>

Pull the controller memory buffer check to its own function. The check will be used on its own in later patches.

---
 hw/block/nvme.c | 16 ++++++++++++----
 1 file changed, 12 insertions(+), 4 deletions(-)
hw/block/nvme.c +12 -4
index 12f97aed0c15..287e1e49c0bf 100644
@@ -52,14 +52,22 @@
 
 static void nvme_process_sq(void *opaque);
 
+static bool nvme_addr_is_cmb(NvmeCtrl *n, hwaddr addr)
+{
+    hwaddr low = n->ctrl_mem.addr;
+    hwaddr hi  = n->ctrl_mem.addr + int128_get64(n->ctrl_mem.size);
+
+    return addr >= low && addr < hi;
+}
+
 static void nvme_addr_read(NvmeCtrl *n, hwaddr addr, void *buf, int size)
 {
-    if (n->cmbsz && addr >= n->ctrl_mem.addr &&
-                addr < (n->ctrl_mem.addr + int128_get64(n->ctrl_mem.size))) {
+    if (n->cmbsz && nvme_addr_is_cmb(n, addr)) {
         memcpy(buf, (void *)&n->cmbuf[addr - n->ctrl_mem.addr], size);
-    } else {
-        pci_dma_read(&n->parent_obj, addr, buf, size);
+        return;
     }
+
+    pci_dma_read(&n->parent_obj, addr, buf, size);
 }
 
 static int nvme_check_sqid(NvmeCtrl *n, uint16_t sqid)
Signature · 1 line
2.26.0
#3 lore raw

PATCH 2/16 nvme: rename trace events to nvme_dev

In reply to Klaus Jensen

From: Klaus Jensen <[email protected]>

Change the prefix of all nvme device related trace events to 'nvme_dev' to not clash with trace events from the nvme block driver.

---
 hw/block/nvme.c       | 190 +++++++++++++++++++++---------------------
 hw/block/trace-events | 172 +++++++++++++++++++-------------------
 2 files changed, 180 insertions(+), 182 deletions(-)
hw/block/nvme.c +94 -96
index 77f9c151a665..316cfc4d36e0 100644
@@ -112,16 +112,16 @@ static void nvme_irq_assert(NvmeCtrl *n, NvmeCQueue *cq)
 {
     if (cq->irq_enabled) {
         if (msix_enabled(&(n->parent_obj))) {
-            trace_nvme_irq_msix(cq->vector);
+            trace_nvme_dev_irq_msix(cq->vector);
             msix_notify(&(n->parent_obj), cq->vector);
         } else {
-            trace_nvme_irq_pin();
+            trace_nvme_dev_irq_pin();
             assert(cq->cqid < 64);
             n->irq_status |= 1 << cq->cqid;
             nvme_irq_check(n);
         }
     } else {
-        trace_nvme_irq_masked();
+        trace_nvme_dev_irq_masked();
     }
 }
 
@@ -146,7 +146,7 @@ static uint16_t nvme_map_prp(QEMUSGList *qsg, QEMUIOVector *iov, uint64_t prp1,
     int num_prps = (len >> n->page_bits) + 1;
 
     if (unlikely(!prp1)) {
-        trace_nvme_err_invalid_prp();
+        trace_nvme_dev_err_invalid_prp();
         return NVME_INVALID_FIELD | NVME_DNR;
     } else if (n->cmbsz && prp1 >= n->ctrl_mem.addr &&
                prp1 < n->ctrl_mem.addr + int128_get64(n->ctrl_mem.size)) {
@@ -160,7 +160,7 @@ static uint16_t nvme_map_prp(QEMUSGList *qsg, QEMUIOVector *iov, uint64_t prp1,
     len -= trans_len;
     if (len) {
         if (unlikely(!prp2)) {
-            trace_nvme_err_invalid_prp2_missing();
+            trace_nvme_dev_err_invalid_prp2_missing();
             goto unmap;
         }
         if (len > n->page_size) {
@@ -176,7 +176,7 @@ static uint16_t nvme_map_prp(QEMUSGList *qsg, QEMUIOVector *iov, uint64_t prp1,
 
                 if (i == n->max_prp_ents - 1 && len > n->page_size) {
                     if (unlikely(!prp_ent || prp_ent & (n->page_size - 1))) {
-                        trace_nvme_err_invalid_prplist_ent(prp_ent);
+                        trace_nvme_dev_err_invalid_prplist_ent(prp_ent);
                         goto unmap;
                     }
 
@@ -189,7 +189,7 @@ static uint16_t nvme_map_prp(QEMUSGList *qsg, QEMUIOVector *iov, uint64_t prp1,
                 }
 
                 if (unlikely(!prp_ent || prp_ent & (n->page_size - 1))) {
-                    trace_nvme_err_invalid_prplist_ent(prp_ent);
+                    trace_nvme_dev_err_invalid_prplist_ent(prp_ent);
                     goto unmap;
                 }
 
@@ -204,7 +204,7 @@ static uint16_t nvme_map_prp(QEMUSGList *qsg, QEMUIOVector *iov, uint64_t prp1,
             }
         } else {
             if (unlikely(prp2 & (n->page_size - 1))) {
-                trace_nvme_err_invalid_prp2_align(prp2);
+                trace_nvme_dev_err_invalid_prp2_align(prp2);
                 goto unmap;
             }
             if (qsg->nsg) {
@@ -252,20 +252,20 @@ static uint16_t nvme_dma_read_prp(NvmeCtrl *n, uint8_t *ptr, uint32_t len,
     QEMUIOVector iov;
     uint16_t status = NVME_SUCCESS;
 
-    trace_nvme_dma_read(prp1, prp2);
+    trace_nvme_dev_dma_read(prp1, prp2);
 
     if (nvme_map_prp(&qsg, &iov, prp1, prp2, len, n)) {
         return NVME_INVALID_FIELD | NVME_DNR;
     }
     if (qsg.nsg > 0) {
         if (unlikely(dma_buf_read(ptr, len, &qsg))) {
-            trace_nvme_err_invalid_dma();
+            trace_nvme_dev_err_invalid_dma();
             status = NVME_INVALID_FIELD | NVME_DNR;
         }
         qemu_sglist_destroy(&qsg);
     } else {
         if (unlikely(qemu_iovec_from_buf(&iov, 0, ptr, len) != len)) {
-            trace_nvme_err_invalid_dma();
+            trace_nvme_dev_err_invalid_dma();
             status = NVME_INVALID_FIELD | NVME_DNR;
         }
         qemu_iovec_destroy(&iov);
@@ -354,7 +354,7 @@ static uint16_t nvme_write_zeros(NvmeCtrl *n, NvmeNamespace *ns, NvmeCmd *cmd,
     uint32_t count = nlb << data_shift;
 
     if (unlikely(slba + nlb > ns->id_ns.nsze)) {
-        trace_nvme_err_invalid_lba_range(slba, nlb, ns->id_ns.nsze);
+        trace_nvme_dev_err_invalid_lba_range(slba, nlb, ns->id_ns.nsze);
         return NVME_LBA_RANGE | NVME_DNR;
     }
 
@@ -382,11 +382,11 @@ static uint16_t nvme_rw(NvmeCtrl *n, NvmeNamespace *ns, NvmeCmd *cmd,
     int is_write = rw->opcode == NVME_CMD_WRITE ? 1 : 0;
     enum BlockAcctType acct = is_write ? BLOCK_ACCT_WRITE : BLOCK_ACCT_READ;
 
-    trace_nvme_rw(is_write ? "write" : "read", nlb, data_size, slba);
+    trace_nvme_dev_rw(is_write ? "write" : "read", nlb, data_size, slba);
 
     if (unlikely((slba + nlb) > ns->id_ns.nsze)) {
         block_acct_invalid(blk_get_stats(n->conf.blk), acct);
-        trace_nvme_err_invalid_lba_range(slba, nlb, ns->id_ns.nsze);
+        trace_nvme_dev_err_invalid_lba_range(slba, nlb, ns->id_ns.nsze);
         return NVME_LBA_RANGE | NVME_DNR;
     }
 
@@ -421,7 +421,7 @@ static uint16_t nvme_io_cmd(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
     uint32_t nsid = le32_to_cpu(cmd->nsid);
 
     if (unlikely(nsid == 0 || nsid > n->num_namespaces)) {
-        trace_nvme_err_invalid_ns(nsid, n->num_namespaces);
+        trace_nvme_dev_err_invalid_ns(nsid, n->num_namespaces);
         return NVME_INVALID_NSID | NVME_DNR;
     }
 
@@ -435,7 +435,7 @@ static uint16_t nvme_io_cmd(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
     case NVME_CMD_READ:
         return nvme_rw(n, ns, cmd, req);
     default:
-        trace_nvme_err_invalid_opc(cmd->opcode);
+        trace_nvme_dev_err_invalid_opc(cmd->opcode);
         return NVME_INVALID_OPCODE | NVME_DNR;
     }
 }
@@ -460,11 +460,11 @@ static uint16_t nvme_del_sq(NvmeCtrl *n, NvmeCmd *cmd)
     uint16_t qid = le16_to_cpu(c->qid);
 
     if (unlikely(!qid || nvme_check_sqid(n, qid))) {
-        trace_nvme_err_invalid_del_sq(qid);
+        trace_nvme_dev_err_invalid_del_sq(qid);
         return NVME_INVALID_QID | NVME_DNR;
     }
 
-    trace_nvme_del_sq(qid);
+    trace_nvme_dev_del_sq(qid);
 
     sq = n->sq[qid];
     while (!QTAILQ_EMPTY(&sq->out_req_list)) {
@@ -528,26 +528,26 @@ static uint16_t nvme_create_sq(NvmeCtrl *n, NvmeCmd *cmd)
     uint16_t qflags = le16_to_cpu(c->sq_flags);
     uint64_t prp1 = le64_to_cpu(c->prp1);
 
-    trace_nvme_create_sq(prp1, sqid, cqid, qsize, qflags);
+    trace_nvme_dev_create_sq(prp1, sqid, cqid, qsize, qflags);
 
     if (unlikely(!cqid || nvme_check_cqid(n, cqid))) {
-        trace_nvme_err_invalid_create_sq_cqid(cqid);
+        trace_nvme_dev_err_invalid_create_sq_cqid(cqid);
         return NVME_INVALID_CQID | NVME_DNR;
     }
     if (unlikely(!sqid || !nvme_check_sqid(n, sqid))) {
-        trace_nvme_err_invalid_create_sq_sqid(sqid);
+        trace_nvme_dev_err_invalid_create_sq_sqid(sqid);
         return NVME_INVALID_QID | NVME_DNR;
     }
     if (unlikely(!qsize || qsize > NVME_CAP_MQES(n->bar.cap))) {
-        trace_nvme_err_invalid_create_sq_size(qsize);
+        trace_nvme_dev_err_invalid_create_sq_size(qsize);
         return NVME_MAX_QSIZE_EXCEEDED | NVME_DNR;
     }
     if (unlikely(!prp1 || prp1 & (n->page_size - 1))) {
-        trace_nvme_err_invalid_create_sq_addr(prp1);
+        trace_nvme_dev_err_invalid_create_sq_addr(prp1);
         return NVME_INVALID_FIELD | NVME_DNR;
     }
     if (unlikely(!(NVME_SQ_FLAGS_PC(qflags)))) {
-        trace_nvme_err_invalid_create_sq_qflags(NVME_SQ_FLAGS_PC(qflags));
+        trace_nvme_dev_err_invalid_create_sq_qflags(NVME_SQ_FLAGS_PC(qflags));
         return NVME_INVALID_FIELD | NVME_DNR;
     }
     sq = g_malloc0(sizeof(*sq));
@@ -573,17 +573,17 @@ static uint16_t nvme_del_cq(NvmeCtrl *n, NvmeCmd *cmd)
     uint16_t qid = le16_to_cpu(c->qid);
 
     if (unlikely(!qid || nvme_check_cqid(n, qid))) {
-        trace_nvme_err_invalid_del_cq_cqid(qid);
+        trace_nvme_dev_err_invalid_del_cq_cqid(qid);
         return NVME_INVALID_CQID | NVME_DNR;
     }
 
     cq = n->cq[qid];
     if (unlikely(!QTAILQ_EMPTY(&cq->sq_list))) {
-        trace_nvme_err_invalid_del_cq_notempty(qid);
+        trace_nvme_dev_err_invalid_del_cq_notempty(qid);
         return NVME_INVALID_QUEUE_DEL;
     }
     nvme_irq_deassert(n, cq);
-    trace_nvme_del_cq(qid);
+    trace_nvme_dev_del_cq(qid);
     nvme_free_cq(cq, n);
     return NVME_SUCCESS;
 }
@@ -616,27 +616,27 @@ static uint16_t nvme_create_cq(NvmeCtrl *n, NvmeCmd *cmd)
     uint16_t qflags = le16_to_cpu(c->cq_flags);
     uint64_t prp1 = le64_to_cpu(c->prp1);
 
-    trace_nvme_create_cq(prp1, cqid, vector, qsize, qflags,
-                         NVME_CQ_FLAGS_IEN(qflags) != 0);
+    trace_nvme_dev_create_cq(prp1, cqid, vector, qsize, qflags,
+                             NVME_CQ_FLAGS_IEN(qflags) != 0);
 
     if (unlikely(!cqid || !nvme_check_cqid(n, cqid))) {
-        trace_nvme_err_invalid_create_cq_cqid(cqid);
+        trace_nvme_dev_err_invalid_create_cq_cqid(cqid);
         return NVME_INVALID_CQID | NVME_DNR;
     }
     if (unlikely(!qsize || qsize > NVME_CAP_MQES(n->bar.cap))) {
-        trace_nvme_err_invalid_create_cq_size(qsize);
+        trace_nvme_dev_err_invalid_create_cq_size(qsize);
         return NVME_MAX_QSIZE_EXCEEDED | NVME_DNR;
     }
     if (unlikely(!prp1)) {
-        trace_nvme_err_invalid_create_cq_addr(prp1);
+        trace_nvme_dev_err_invalid_create_cq_addr(prp1);
         return NVME_INVALID_FIELD | NVME_DNR;
     }
     if (unlikely(vector > n->num_queues)) {
-        trace_nvme_err_invalid_create_cq_vector(vector);
+        trace_nvme_dev_err_invalid_create_cq_vector(vector);
         return NVME_INVALID_IRQ_VECTOR | NVME_DNR;
     }
     if (unlikely(!(NVME_CQ_FLAGS_PC(qflags)))) {
-        trace_nvme_err_invalid_create_cq_qflags(NVME_CQ_FLAGS_PC(qflags));
+        trace_nvme_dev_err_invalid_create_cq_qflags(NVME_CQ_FLAGS_PC(qflags));
         return NVME_INVALID_FIELD | NVME_DNR;
     }
 
@@ -651,7 +651,7 @@ static uint16_t nvme_identify_ctrl(NvmeCtrl *n, NvmeIdentify *c)
     uint64_t prp1 = le64_to_cpu(c->prp1);
     uint64_t prp2 = le64_to_cpu(c->prp2);
 
-    trace_nvme_identify_ctrl();
+    trace_nvme_dev_identify_ctrl();
 
     return nvme_dma_read_prp(n, (uint8_t *)&n->id_ctrl, sizeof(n->id_ctrl),
         prp1, prp2);
@@ -664,10 +664,10 @@ static uint16_t nvme_identify_ns(NvmeCtrl *n, NvmeIdentify *c)
     uint64_t prp1 = le64_to_cpu(c->prp1);
     uint64_t prp2 = le64_to_cpu(c->prp2);
 
-    trace_nvme_identify_ns(nsid);
+    trace_nvme_dev_identify_ns(nsid);
 
     if (unlikely(nsid == 0 || nsid > n->num_namespaces)) {
-        trace_nvme_err_invalid_ns(nsid, n->num_namespaces);
+        trace_nvme_dev_err_invalid_ns(nsid, n->num_namespaces);
         return NVME_INVALID_NSID | NVME_DNR;
     }
 
@@ -687,7 +687,7 @@ static uint16_t nvme_identify_nslist(NvmeCtrl *n, NvmeIdentify *c)
     uint16_t ret;
     int i, j = 0;
 
-    trace_nvme_identify_nslist(min_nsid);
+    trace_nvme_dev_identify_nslist(min_nsid);
 
     list = g_malloc0(data_len);
     for (i = 0; i < n->num_namespaces; i++) {
@@ -716,14 +716,14 @@ static uint16_t nvme_identify(NvmeCtrl *n, NvmeCmd *cmd)
     case 0x02:
         return nvme_identify_nslist(n, c);
     default:
-        trace_nvme_err_invalid_identify_cns(le32_to_cpu(c->cns));
+        trace_nvme_dev_err_invalid_identify_cns(le32_to_cpu(c->cns));
         return NVME_INVALID_FIELD | NVME_DNR;
     }
 }
 
 static inline void nvme_set_timestamp(NvmeCtrl *n, uint64_t ts)
 {
-    trace_nvme_setfeat_timestamp(ts);
+    trace_nvme_dev_setfeat_timestamp(ts);
 
     n->host_timestamp = le64_to_cpu(ts);
     n->timestamp_set_qemu_clock_ms = qemu_clock_get_ms(QEMU_CLOCK_VIRTUAL);
@@ -756,7 +756,7 @@ static inline uint64_t nvme_get_timestamp(const NvmeCtrl *n)
     /* If the host timestamp is non-zero, set the timestamp origin */
     ts.origin = n->host_timestamp ? 0x01 : 0x00;
 
-    trace_nvme_getfeat_timestamp(ts.all);
+    trace_nvme_dev_getfeat_timestamp(ts.all);
 
     return cpu_to_le64(ts.all);
 }
@@ -780,17 +780,17 @@ static uint16_t nvme_get_feature(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
     switch (dw10) {
     case NVME_VOLATILE_WRITE_CACHE:
         result = blk_enable_write_cache(n->conf.blk);
-        trace_nvme_getfeat_vwcache(result ? "enabled" : "disabled");
+        trace_nvme_dev_getfeat_vwcache(result ? "enabled" : "disabled");
         break;
     case NVME_NUMBER_OF_QUEUES:
         result = cpu_to_le32((n->num_queues - 2) | ((n->num_queues - 2) << 16));
-        trace_nvme_getfeat_numq(result);
+        trace_nvme_dev_getfeat_numq(result);
         break;
     case NVME_TIMESTAMP:
         return nvme_get_feature_timestamp(n, cmd);
         break;
     default:
-        trace_nvme_err_invalid_getfeat(dw10);
+        trace_nvme_dev_err_invalid_getfeat(dw10);
         return NVME_INVALID_FIELD | NVME_DNR;
     }
 
@@ -826,9 +826,9 @@ static uint16_t nvme_set_feature(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
         blk_set_enable_write_cache(n->conf.blk, dw11 & 1);
         break;
     case NVME_NUMBER_OF_QUEUES:
-        trace_nvme_setfeat_numq((dw11 & 0xFFFF) + 1,
-                                ((dw11 >> 16) & 0xFFFF) + 1,
-                                n->num_queues - 1, n->num_queues - 1);
+        trace_nvme_dev_setfeat_numq((dw11 & 0xFFFF) + 1,
+                                    ((dw11 >> 16) & 0xFFFF) + 1,
+                                    n->num_queues - 1, n->num_queues - 1);
         req->cqe.result =
             cpu_to_le32((n->num_queues - 2) | ((n->num_queues - 2) << 16));
         break;
@@ -838,7 +838,7 @@ static uint16_t nvme_set_feature(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
         break;
 
     default:
-        trace_nvme_err_invalid_setfeat(dw10);
+        trace_nvme_dev_err_invalid_setfeat(dw10);
         return NVME_INVALID_FIELD | NVME_DNR;
     }
     return NVME_SUCCESS;
@@ -862,7 +862,7 @@ static uint16_t nvme_admin_cmd(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
     case NVME_ADM_CMD_GET_FEATURES:
         return nvme_get_feature(n, cmd, req);
     default:
-        trace_nvme_err_invalid_admin_opc(cmd->opcode);
+        trace_nvme_dev_err_invalid_admin_opc(cmd->opcode);
         return NVME_INVALID_OPCODE | NVME_DNR;
     }
 }
@@ -925,77 +925,77 @@ static int nvme_start_ctrl(NvmeCtrl *n)
     uint32_t page_size = 1 << page_bits;
 
     if (unlikely(n->cq[0])) {
-        trace_nvme_err_startfail_cq();
+        trace_nvme_dev_err_startfail_cq();
         return -1;
     }
     if (unlikely(n->sq[0])) {
-        trace_nvme_err_startfail_sq();
+        trace_nvme_dev_err_startfail_sq();
         return -1;
     }
     if (unlikely(!n->bar.asq)) {
-        trace_nvme_err_startfail_nbarasq();
+        trace_nvme_dev_err_startfail_nbarasq();
         return -1;
     }
     if (unlikely(!n->bar.acq)) {
-        trace_nvme_err_startfail_nbaracq();
+        trace_nvme_dev_err_startfail_nbaracq();
         return -1;
     }
     if (unlikely(n->bar.asq & (page_size - 1))) {
-        trace_nvme_err_startfail_asq_misaligned(n->bar.asq);
+        trace_nvme_dev_err_startfail_asq_misaligned(n->bar.asq);
         return -1;
     }
     if (unlikely(n->bar.acq & (page_size - 1))) {
-        trace_nvme_err_startfail_acq_misaligned(n->bar.acq);
+        trace_nvme_dev_err_startfail_acq_misaligned(n->bar.acq);
         return -1;
     }
     if (unlikely(NVME_CC_MPS(n->bar.cc) <
                  NVME_CAP_MPSMIN(n->bar.cap))) {
-        trace_nvme_err_startfail_page_too_small(
+        trace_nvme_dev_err_startfail_page_too_small(
                     NVME_CC_MPS(n->bar.cc),
                     NVME_CAP_MPSMIN(n->bar.cap));
         return -1;
     }
     if (unlikely(NVME_CC_MPS(n->bar.cc) >
                  NVME_CAP_MPSMAX(n->bar.cap))) {
-        trace_nvme_err_startfail_page_too_large(
+        trace_nvme_dev_err_startfail_page_too_large(
                     NVME_CC_MPS(n->bar.cc),
                     NVME_CAP_MPSMAX(n->bar.cap));
         return -1;
     }
     if (unlikely(NVME_CC_IOCQES(n->bar.cc) <
                  NVME_CTRL_CQES_MIN(n->id_ctrl.cqes))) {
-        trace_nvme_err_startfail_cqent_too_small(
+        trace_nvme_dev_err_startfail_cqent_too_small(
                     NVME_CC_IOCQES(n->bar.cc),
                     NVME_CTRL_CQES_MIN(n->bar.cap));
         return -1;
     }
     if (unlikely(NVME_CC_IOCQES(n->bar.cc) >
                  NVME_CTRL_CQES_MAX(n->id_ctrl.cqes))) {
-        trace_nvme_err_startfail_cqent_too_large(
+        trace_nvme_dev_err_startfail_cqent_too_large(
                     NVME_CC_IOCQES(n->bar.cc),
                     NVME_CTRL_CQES_MAX(n->bar.cap));
         return -1;
     }
     if (unlikely(NVME_CC_IOSQES(n->bar.cc) <
                  NVME_CTRL_SQES_MIN(n->id_ctrl.sqes))) {
-        trace_nvme_err_startfail_sqent_too_small(
+        trace_nvme_dev_err_startfail_sqent_too_small(
                     NVME_CC_IOSQES(n->bar.cc),
                     NVME_CTRL_SQES_MIN(n->bar.cap));
         return -1;
     }
     if (unlikely(NVME_CC_IOSQES(n->bar.cc) >
                  NVME_CTRL_SQES_MAX(n->id_ctrl.sqes))) {
-        trace_nvme_err_startfail_sqent_too_large(
+        trace_nvme_dev_err_startfail_sqent_too_large(
                     NVME_CC_IOSQES(n->bar.cc),
                     NVME_CTRL_SQES_MAX(n->bar.cap));
         return -1;
     }
     if (unlikely(!NVME_AQA_ASQS(n->bar.aqa))) {
-        trace_nvme_err_startfail_asqent_sz_zero();
+        trace_nvme_dev_err_startfail_asqent_sz_zero();
         return -1;
     }
     if (unlikely(!NVME_AQA_ACQS(n->bar.aqa))) {
-        trace_nvme_err_startfail_acqent_sz_zero();
+        trace_nvme_dev_err_startfail_acqent_sz_zero();
         return -1;
     }
 
@@ -1018,14 +1018,14 @@ static void nvme_write_bar(NvmeCtrl *n, hwaddr offset, uint64_t data,
     unsigned size)
 {
     if (unlikely(offset & (sizeof(uint32_t) - 1))) {
-        NVME_GUEST_ERR(nvme_ub_mmiowr_misaligned32,
+        NVME_GUEST_ERR(nvme_dev_ub_mmiowr_misaligned32,
                        "MMIO write not 32-bit aligned,"
                        " offset=0x%"PRIx64"", offset);
         /* should be ignored, fall through for now */
     }
 
     if (unlikely(size < sizeof(uint32_t))) {
-        NVME_GUEST_ERR(nvme_ub_mmiowr_toosmall,
+        NVME_GUEST_ERR(nvme_dev_ub_mmiowr_toosmall,
                        "MMIO write smaller than 32-bits,"
                        " offset=0x%"PRIx64", size=%u",
                        offset, size);
@@ -1035,32 +1035,30 @@ static void nvme_write_bar(NvmeCtrl *n, hwaddr offset, uint64_t data,
     switch (offset) {
     case 0xc:   /* INTMS */
         if (unlikely(msix_enabled(&(n->parent_obj)))) {
-            NVME_GUEST_ERR(nvme_ub_mmiowr_intmask_with_msix,
+            NVME_GUEST_ERR(nvme_dev_ub_mmiowr_intmask_with_msix,
                            "undefined access to interrupt mask set"
                            " when MSI-X is enabled");
             /* should be ignored, fall through for now */
         }
         n->bar.intms |= data & 0xffffffff;
         n->bar.intmc = n->bar.intms;
-        trace_nvme_mmio_intm_set(data & 0xffffffff,
-                                 n->bar.intmc);
+        trace_nvme_dev_mmio_intm_set(data & 0xffffffff, n->bar.intmc);
         nvme_irq_check(n);
         break;
     case 0x10:  /* INTMC */
         if (unlikely(msix_enabled(&(n->parent_obj)))) {
-            NVME_GUEST_ERR(nvme_ub_mmiowr_intmask_with_msix,
+            NVME_GUEST_ERR(nvme_dev_ub_mmiowr_intmask_with_msix,
                            "undefined access to interrupt mask clr"
                            " when MSI-X is enabled");
             /* should be ignored, fall through for now */
         }
         n->bar.intms &= ~(data & 0xffffffff);
         n->bar.intmc = n->bar.intms;
-        trace_nvme_mmio_intm_clr(data & 0xffffffff,
-                                 n->bar.intmc);
+        trace_nvme_dev_mmio_intm_clr(data & 0xffffffff, n->bar.intmc);
         nvme_irq_check(n);
         break;
     case 0x14:  /* CC */
-        trace_nvme_mmio_cfg(data & 0xffffffff);
+        trace_nvme_dev_mmio_cfg(data & 0xffffffff);
         /* Windows first sends data, then sends enable bit */
         if (!NVME_CC_EN(data) && !NVME_CC_EN(n->bar.cc) &&
             !NVME_CC_SHN(data) && !NVME_CC_SHN(n->bar.cc))
@@ -1071,42 +1069,42 @@ static void nvme_write_bar(NvmeCtrl *n, hwaddr offset, uint64_t data,
         if (NVME_CC_EN(data) && !NVME_CC_EN(n->bar.cc)) {
             n->bar.cc = data;
             if (unlikely(nvme_start_ctrl(n))) {
-                trace_nvme_err_startfail();
+                trace_nvme_dev_err_startfail();
                 n->bar.csts = NVME_CSTS_FAILED;
             } else {
-                trace_nvme_mmio_start_success();
+                trace_nvme_dev_mmio_start_success();
                 n->bar.csts = NVME_CSTS_READY;
             }
         } else if (!NVME_CC_EN(data) && NVME_CC_EN(n->bar.cc)) {
-            trace_nvme_mmio_stopped();
+            trace_nvme_dev_mmio_stopped();
             nvme_clear_ctrl(n);
             n->bar.csts &= ~NVME_CSTS_READY;
         }
         if (NVME_CC_SHN(data) && !(NVME_CC_SHN(n->bar.cc))) {
-            trace_nvme_mmio_shutdown_set();
+            trace_nvme_dev_mmio_shutdown_set();
             nvme_clear_ctrl(n);
             n->bar.cc = data;
             n->bar.csts |= NVME_CSTS_SHST_COMPLETE;
         } else if (!NVME_CC_SHN(data) && NVME_CC_SHN(n->bar.cc)) {
-            trace_nvme_mmio_shutdown_cleared();
+            trace_nvme_dev_mmio_shutdown_cleared();
             n->bar.csts &= ~NVME_CSTS_SHST_COMPLETE;
             n->bar.cc = data;
         }
         break;
     case 0x1C:  /* CSTS */
         if (data & (1 << 4)) {
-            NVME_GUEST_ERR(nvme_ub_mmiowr_ssreset_w1c_unsupported,
+            NVME_GUEST_ERR(nvme_dev_ub_mmiowr_ssreset_w1c_unsupported,
                            "attempted to W1C CSTS.NSSRO"
                            " but CAP.NSSRS is zero (not supported)");
         } else if (data != 0) {
-            NVME_GUEST_ERR(nvme_ub_mmiowr_ro_csts,
+            NVME_GUEST_ERR(nvme_dev_ub_mmiowr_ro_csts,
                            "attempted to set a read only bit"
                            " of controller status");
         }
         break;
     case 0x20:  /* NSSR */
         if (data == 0x4E564D65) {
-            trace_nvme_ub_mmiowr_ssreset_unsupported();
+            trace_nvme_dev_ub_mmiowr_ssreset_unsupported();
         } else {
             /* The spec says that writes of other values have no effect */
             return;
@@ -1114,35 +1112,35 @@ static void nvme_write_bar(NvmeCtrl *n, hwaddr offset, uint64_t data,
         break;
     case 0x24:  /* AQA */
         n->bar.aqa = data & 0xffffffff;
-        trace_nvme_mmio_aqattr(data & 0xffffffff);
+        trace_nvme_dev_mmio_aqattr(data & 0xffffffff);
         break;
     case 0x28:  /* ASQ */
         n->bar.asq = data;
-        trace_nvme_mmio_asqaddr(data);
+        trace_nvme_dev_mmio_asqaddr(data);
         break;
     case 0x2c:  /* ASQ hi */
         n->bar.asq |= data << 32;
-        trace_nvme_mmio_asqaddr_hi(data, n->bar.asq);
+        trace_nvme_dev_mmio_asqaddr_hi(data, n->bar.asq);
         break;
     case 0x30:  /* ACQ */
-        trace_nvme_mmio_acqaddr(data);
+        trace_nvme_dev_mmio_acqaddr(data);
         n->bar.acq = data;
         break;
     case 0x34:  /* ACQ hi */
         n->bar.acq |= data << 32;
-        trace_nvme_mmio_acqaddr_hi(data, n->bar.acq);
+        trace_nvme_dev_mmio_acqaddr_hi(data, n->bar.acq);
         break;
     case 0x38:  /* CMBLOC */
-        NVME_GUEST_ERR(nvme_ub_mmiowr_cmbloc_reserved,
+        NVME_GUEST_ERR(nvme_dev_ub_mmiowr_cmbloc_reserved,
                        "invalid write to reserved CMBLOC"
                        " when CMBSZ is zero, ignored");
         return;
     case 0x3C:  /* CMBSZ */
-        NVME_GUEST_ERR(nvme_ub_mmiowr_cmbsz_readonly,
+        NVME_GUEST_ERR(nvme_dev_ub_mmiowr_cmbsz_readonly,
                        "invalid write to read only CMBSZ, ignored");
         return;
     default:
-        NVME_GUEST_ERR(nvme_ub_mmiowr_invalid,
+        NVME_GUEST_ERR(nvme_dev_ub_mmiowr_invalid,
                        "invalid MMIO write,"
                        " offset=0x%"PRIx64", data=%"PRIx64"",
                        offset, data);
@@ -1157,12 +1155,12 @@ static uint64_t nvme_mmio_read(void *opaque, hwaddr addr, unsigned size)
     uint64_t val = 0;
 
     if (unlikely(addr & (sizeof(uint32_t) - 1))) {
-        NVME_GUEST_ERR(nvme_ub_mmiord_misaligned32,
+        NVME_GUEST_ERR(nvme_dev_ub_mmiord_misaligned32,
                        "MMIO read not 32-bit aligned,"
                        " offset=0x%"PRIx64"", addr);
         /* should RAZ, fall through for now */
     } else if (unlikely(size < sizeof(uint32_t))) {
-        NVME_GUEST_ERR(nvme_ub_mmiord_toosmall,
+        NVME_GUEST_ERR(nvme_dev_ub_mmiord_toosmall,
                        "MMIO read smaller than 32-bits,"
                        " offset=0x%"PRIx64"", addr);
         /* should RAZ, fall through for now */
@@ -1171,7 +1169,7 @@ static uint64_t nvme_mmio_read(void *opaque, hwaddr addr, unsigned size)
     if (addr < sizeof(n->bar)) {
         memcpy(&val, ptr + addr, size);
     } else {
-        NVME_GUEST_ERR(nvme_ub_mmiord_invalid_ofs,
+        NVME_GUEST_ERR(nvme_dev_ub_mmiord_invalid_ofs,
                        "MMIO read beyond last register,"
                        " offset=0x%"PRIx64", returning 0", addr);
     }
@@ -1184,7 +1182,7 @@ static void nvme_process_db(NvmeCtrl *n, hwaddr addr, int val)
     uint32_t qid;
 
     if (unlikely(addr & ((1 << 2) - 1))) {
-        NVME_GUEST_ERR(nvme_ub_db_wr_misaligned,
+        NVME_GUEST_ERR(nvme_dev_ub_db_wr_misaligned,
                        "doorbell write not 32-bit aligned,"
                        " offset=0x%"PRIx64", ignoring", addr);
         return;
@@ -1199,7 +1197,7 @@ static void nvme_process_db(NvmeCtrl *n, hwaddr addr, int val)
 
         qid = (addr - (0x1000 + (1 << 2))) >> 3;
         if (unlikely(nvme_check_cqid(n, qid))) {
-            NVME_GUEST_ERR(nvme_ub_db_wr_invalid_cq,
+            NVME_GUEST_ERR(nvme_dev_ub_db_wr_invalid_cq,
                            "completion queue doorbell write"
                            " for nonexistent queue,"
                            " sqid=%"PRIu32", ignoring", qid);
@@ -1208,7 +1206,7 @@ static void nvme_process_db(NvmeCtrl *n, hwaddr addr, int val)
 
         cq = n->cq[qid];
         if (unlikely(new_head >= cq->size)) {
-            NVME_GUEST_ERR(nvme_ub_db_wr_invalid_cqhead,
+            NVME_GUEST_ERR(nvme_dev_ub_db_wr_invalid_cqhead,
                            "completion queue doorbell write value"
                            " beyond queue size, sqid=%"PRIu32","
                            " new_head=%"PRIu16", ignoring",
@@ -1237,7 +1235,7 @@ static void nvme_process_db(NvmeCtrl *n, hwaddr addr, int val)
 
         qid = (addr - 0x1000) >> 3;
         if (unlikely(nvme_check_sqid(n, qid))) {
-            NVME_GUEST_ERR(nvme_ub_db_wr_invalid_sq,
+            NVME_GUEST_ERR(nvme_dev_ub_db_wr_invalid_sq,
                            "submission queue doorbell write"
                            " for nonexistent queue,"
                            " sqid=%"PRIu32", ignoring", qid);
@@ -1246,7 +1244,7 @@ static void nvme_process_db(NvmeCtrl *n, hwaddr addr, int val)
 
         sq = n->sq[qid];
         if (unlikely(new_tail >= sq->size)) {
-            NVME_GUEST_ERR(nvme_ub_db_wr_invalid_sqtail,
+            NVME_GUEST_ERR(nvme_dev_ub_db_wr_invalid_sqtail,
                            "submission queue doorbell write value"
                            " beyond queue size, sqid=%"PRIu32","
                            " new_tail=%"PRIu16", ignoring",
hw/block/trace-events +86 -86

182 lines not on this page · raw message

Signature · 1 line
2.26.0
#14 lore raw

PATCH 10/16 nvme: factor out device state setup

In reply to Klaus Jensen

From: Klaus Jensen <[email protected]>

---
 hw/block/nvme.c | 17 +++++++++++------
 1 file changed, 11 insertions(+), 6 deletions(-)
hw/block/nvme.c +11 -6
index 635292d6fac4..e67f578fbf79 100644
@@ -1339,6 +1339,15 @@ static int nvme_check_constraints(NvmeCtrl *n, Error **errp)
     return 0;
 }
 
+static void nvme_init_state(NvmeCtrl *n)
+{
+    n->num_namespaces = 1;
+    n->reg_size = pow2ceil(0x1008 + 2 * (n->params.max_ioqpairs) * 4);
+    n->namespaces = g_new0(NvmeNamespace, n->num_namespaces);
+    n->sq = g_new0(NvmeSQueue *, n->params.max_ioqpairs + 1);
+    n->cq = g_new0(NvmeCQueue *, n->params.max_ioqpairs + 1);
+}
+
 static void nvme_realize(PCIDevice *pci_dev, Error **errp)
 {
     NvmeCtrl *n = NVME(pci_dev);
@@ -1352,6 +1361,8 @@ static void nvme_realize(PCIDevice *pci_dev, Error **errp)
         return;
     }
 
+    nvme_init_state(n);
+
     bs_size = blk_getlength(n->conf.blk);
     if (bs_size < 0) {
         error_setg(errp, "could not get backing file size");
@@ -1370,14 +1381,8 @@ static void nvme_realize(PCIDevice *pci_dev, Error **errp)
     pci_config_set_class(pci_dev->config, PCI_CLASS_STORAGE_EXPRESS);
     pcie_endpoint_cap_init(pci_dev, 0x80);
 
-    n->num_namespaces = 1;
-    n->reg_size = pow2ceil(0x1008 + 2 * (n->params.max_ioqpairs) * 4);
     n->ns_size = bs_size / (uint64_t)n->num_namespaces;
 
-    n->namespaces = g_new0(NvmeNamespace, n->num_namespaces);
-    n->sq = g_new0(NvmeSQueue *, n->params.max_ioqpairs + 1);
-    n->cq = g_new0(NvmeCQueue *, n->params.max_ioqpairs + 1);
-
     memory_region_init_io(&n->iomem, OBJECT(n), &nvme_mmio_ops, n,
                           "nvme", n->reg_size);
     pci_register_bar(pci_dev, 0,
Signature · 1 line
2.26.0
#16 lore raw

PATCH 11/16 nvme: factor out block backend setup

In reply to Klaus Jensen

From: Klaus Jensen <[email protected]>

---
 hw/block/nvme.c | 15 ++++++++++++---
 1 file changed, 12 insertions(+), 3 deletions(-)
hw/block/nvme.c +12 -3
index e67f578fbf79..f0989cbb4335 100644
@@ -1348,6 +1348,17 @@ static void nvme_init_state(NvmeCtrl *n)
     n->cq = g_new0(NvmeCQueue *, n->params.max_ioqpairs + 1);
 }
 
+static int nvme_init_blk(NvmeCtrl *n, Error **errp)
+{
+    blkconf_blocksizes(&n->conf);
+    if (!blkconf_apply_backend_options(&n->conf, blk_is_read_only(n->conf.blk),
+                                       false, errp)) {
+        return -1;
+    }
+
+    return 0;
+}
+
 static void nvme_realize(PCIDevice *pci_dev, Error **errp)
 {
     NvmeCtrl *n = NVME(pci_dev);
@@ -1369,9 +1380,7 @@ static void nvme_realize(PCIDevice *pci_dev, Error **errp)
         return;
     }
 
-    blkconf_blocksizes(&n->conf);
-    if (!blkconf_apply_backend_options(&n->conf, blk_is_read_only(n->conf.blk),
-                                       false, errp)) {
+    if (nvme_init_blk(n, errp)) {
         return;
     }
 
Signature · 1 line
2.26.0
#11 lore raw

PATCH 8/16 nvme: remove redundant cmbloc/cmbsz members

In reply to Klaus Jensen

From: Klaus Jensen <[email protected]>

---
 hw/block/nvme.c | 7 ++-----
 hw/block/nvme.h | 2 --
 2 files changed, 2 insertions(+), 7 deletions(-)
hw/block/nvme.c +2 -5
index 9383d2cb0b38..ea613213bd57 100644
@@ -63,7 +63,7 @@ static bool nvme_addr_is_cmb(NvmeCtrl *n, hwaddr addr)
 
 static void nvme_addr_read(NvmeCtrl *n, hwaddr addr, void *buf, int size)
 {
-    if (n->cmbsz && nvme_addr_is_cmb(n, addr)) {
+    if (n->bar.cmbsz && nvme_addr_is_cmb(n, addr)) {
         memcpy(buf, (void *)&n->cmbuf[addr - n->ctrl_mem.addr], size);
         return;
     }
@@ -157,7 +157,7 @@ static uint16_t nvme_map_prp(QEMUSGList *qsg, QEMUIOVector *iov, uint64_t prp1,
     if (unlikely(!prp1)) {
         trace_nvme_dev_err_invalid_prp();
         return NVME_INVALID_FIELD | NVME_DNR;
-    } else if (n->cmbsz && prp1 >= n->ctrl_mem.addr &&
+    } else if (n->bar.cmbsz && prp1 >= n->ctrl_mem.addr &&
                prp1 < n->ctrl_mem.addr + int128_get64(n->ctrl_mem.size)) {
         qsg->nsg = 0;
         qemu_iovec_init(iov, num_prps);
@@ -1419,9 +1419,6 @@ static void nvme_realize(PCIDevice *pci_dev, Error **errp)
         NVME_CMBSZ_SET_SZU(n->bar.cmbsz, 2); /* MBs */
         NVME_CMBSZ_SET_SZ(n->bar.cmbsz, n->params.cmb_size_mb);
 
-        n->cmbloc = n->bar.cmbloc;
-        n->cmbsz = n->bar.cmbsz;
-
         n->cmbuf = g_malloc0(NVME_CMBSZ_GETSIZE(n->bar.cmbsz));
         memory_region_init_io(&n->ctrl_mem, OBJECT(n), &nvme_cmb_ops, n,
                               "nvme-cmb", NVME_CMBSZ_GETSIZE(n->bar.cmbsz));
hw/block/nvme.h +0 -2
index 98f5b9479244..ad1786953be9 100644
@@ -88,8 +88,6 @@ typedef struct NvmeCtrl {
     uint32_t    num_namespaces;
     uint32_t    max_q_ents;
     uint64_t    ns_size;
-    uint32_t    cmbsz;
-    uint32_t    cmbloc;
     uint8_t     *cmbuf;
     uint64_t    irq_status;
     uint64_t    host_timestamp;                 /* Timestamp sent by the host */
Signature · 1 line
2.26.0
#20 lore raw

PATCH 12/16 nvme: add namespace helpers

In reply to Klaus Jensen

From: Klaus Jensen <[email protected]>

Introduce some small helpers to make the next patches easier on the eye.

---
 hw/block/nvme.h | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)
hw/block/nvme.h +16 -0
index ad1786953be9..d9900bed957c 100644
@@ -67,6 +67,17 @@ typedef struct NvmeNamespace {
     NvmeIdNs        id_ns;
 } NvmeNamespace;
 
+static inline NvmeLBAF *nvme_ns_lbaf(NvmeNamespace *ns)
+{
+    NvmeIdNs *id_ns = &ns->id_ns;
+    return &id_ns->lbaf[NVME_ID_NS_FLBAS_INDEX(id_ns->flbas)];
+}
+
+static inline uint8_t nvme_ns_lbads(NvmeNamespace *ns)
+{
+    return nvme_ns_lbaf(ns)->ds;
+}
+
 #define TYPE_NVME "nvme"
 #define NVME(obj) \
         OBJECT_CHECK(NvmeCtrl, (obj), TYPE_NVME)
@@ -101,4 +112,9 @@ typedef struct NvmeCtrl {
     NvmeIdCtrl      id_ctrl;
 } NvmeCtrl;
 
+static inline uint64_t nvme_ns_nlbas(NvmeCtrl *n, NvmeNamespace *ns)
+{
+    return n->ns_size >> nvme_ns_lbads(ns);
+}
+
 #endif /* HW_NVME_H */
Signature · 1 line
2.26.0
#26 lore raw

PATCH 14/16 nvme: factor out pci setup

In reply to Klaus Jensen

From: Klaus Jensen <[email protected]>

---
 hw/block/nvme.c | 32 ++++++++++++++++++++------------
 1 file changed, 20 insertions(+), 12 deletions(-)
hw/block/nvme.c +20 -12
index 08f7ae0a48b3..16d01af53a07 100644
@@ -1382,6 +1382,24 @@ static int nvme_init_namespace(NvmeCtrl *n, NvmeNamespace *ns, Error **errp)
     return 0;
 }
 
+static void nvme_init_pci(NvmeCtrl *n, PCIDevice *pci_dev)
+{
+    uint8_t *pci_conf = pci_dev->config;
+
+    pci_conf[PCI_INTERRUPT_PIN] = 1;
+    pci_config_set_prog_interface(pci_conf, 0x2);
+    pci_config_set_vendor_id(pci_conf, PCI_VENDOR_ID_INTEL);
+    pci_config_set_device_id(pci_conf, 0x5845);
+    pci_config_set_class(pci_conf, PCI_CLASS_STORAGE_EXPRESS);
+    pcie_endpoint_cap_init(pci_dev, 0x80);
+
+    memory_region_init_io(&n->iomem, OBJECT(n), &nvme_mmio_ops, n, "nvme",
+                          n->reg_size);
+    pci_register_bar(pci_dev, 0, PCI_BASE_ADDRESS_SPACE_MEMORY |
+                     PCI_BASE_ADDRESS_MEM_TYPE_64, &n->iomem);
+    msix_init_exclusive_bar(pci_dev, n->params.max_ioqpairs + 1, 4, NULL);
+}
+
 static void nvme_realize(PCIDevice *pci_dev, Error **errp)
 {
     NvmeCtrl *n = NVME(pci_dev);
@@ -1400,19 +1418,9 @@ static void nvme_realize(PCIDevice *pci_dev, Error **errp)
         return;
     }
 
+    nvme_init_pci(n, pci_dev);
+
     pci_conf = pci_dev->config;
-    pci_conf[PCI_INTERRUPT_PIN] = 1;
-    pci_config_set_prog_interface(pci_dev->config, 0x2);
-    pci_config_set_class(pci_dev->config, PCI_CLASS_STORAGE_EXPRESS);
-    pcie_endpoint_cap_init(pci_dev, 0x80);
-
-    memory_region_init_io(&n->iomem, OBJECT(n), &nvme_mmio_ops, n,
-                          "nvme", n->reg_size);
-    pci_register_bar(pci_dev, 0,
-        PCI_BASE_ADDRESS_SPACE_MEMORY | PCI_BASE_ADDRESS_MEM_TYPE_64,
-        &n->iomem);
-    msix_init_exclusive_bar(pci_dev, n->params.max_ioqpairs + 1, 4, NULL);
-
     id->vid = cpu_to_le16(pci_get_word(pci_conf + PCI_VENDOR_ID));
     id->ssvid = cpu_to_le16(pci_get_word(pci_conf + PCI_SUBSYSTEM_VENDOR_ID));
     strpadcpy((char *)id->mn, sizeof(id->mn), "QEMU NVMe Ctrl", ' ');
Signature · 1 line
2.26.0
#23 lore raw

Re: [PATCH 13/16] nvme: factor out namespace setup

In reply to Klaus Jensen
Quoted 62 lines · Klaus Jensen

From: Klaus Jensen <[email protected]>

---
  hw/block/nvme.c | 47 ++++++++++++++++++++++++++---------------------
  1 file changed, 26 insertions(+), 21 deletions(-)
hw/block/nvme.c +23 -7
index f0989cbb4335..08f7ae0a48b3 100644
@@ -1359,13 +1359,35 @@ static int nvme_init_blk(NvmeCtrl *n, Error **errp)
      return 0;
  }
 
+static int nvme_init_namespace(NvmeCtrl *n, NvmeNamespace *ns, Error **errp)
+{
+    int64_t bs_size;
+    NvmeIdNs *id_ns = &ns->id_ns;
+
+    bs_size = blk_getlength(n->conf.blk);
+    if (bs_size < 0) {
+        error_setg_errno(errp, -bs_size, "could not get backing file size");
+        return -1;
+    }
+
+    n->ns_size = bs_size;
+
+    id_ns->lbaf[0].ds = BDRV_SECTOR_BITS;
+    id_ns->nsze = cpu_to_le64(nvme_ns_nlbas(n, ns));
+
+    /* no thin provisioning */
+    id_ns->ncap = id_ns->nsze;
+    id_ns->nuse = id_ns->ncap;
+
+    return 0;
+}
+
  static void nvme_realize(PCIDevice *pci_dev, Error **errp)
  {
      NvmeCtrl *n = NVME(pci_dev);
      NvmeIdCtrl *id = &n->id_ctrl;
 
      int i;
-    int64_t bs_size;
      uint8_t *pci_conf;
 
      if (nvme_check_constraints(n, errp)) {
@@ -1374,12 +1396,6 @@ static void nvme_realize(PCIDevice *pci_dev, Error **errp)
 
      nvme_init_state(n);
 
-    bs_size = blk_getlength(n->conf.blk);
-    if (bs_size < 0) {
-        error_setg(errp, "could not get backing file size");
-        return;
-    }
-
      if (nvme_init_blk(n, errp)) {
          return;
      }

hw/block/nvme.c static void nvme_realize(PCIDevice *pci_dev, Error **errp) · line 1393

Quoted 4 lines
hw/block/nvme.c +0 -1
@@ -1390,8 +1406,6 @@ static void nvme_realize(PCIDevice *pci_dev, Error **errp)
      pci_config_set_class(pci_dev->config, PCI_CLASS_STORAGE_EXPRESS);
      pcie_endpoint_cap_init(pci_dev, 0x80);
 
-    n->ns_size = bs_size / (uint64_t)n->num_namespaces;

I'm not sure this line belong to this patch.

Quoted 27 lines
hw/block/nvme.c +3 -13
-
      memory_region_init_io(&n->iomem, OBJECT(n), &nvme_mmio_ops, n,
                            "nvme", n->reg_size);
      pci_register_bar(pci_dev, 0,
@@ -1455,18 +1469,9 @@ static void nvme_realize(PCIDevice *pci_dev, Error **errp)
      }
 
      for (i = 0; i < n->num_namespaces; i++) {
-        NvmeNamespace *ns = &n->namespaces[i];
-        NvmeIdNs *id_ns = &ns->id_ns;
-        id_ns->nsfeat = 0;
-        id_ns->nlbaf = 0;
-        id_ns->flbas = 0;
-        id_ns->mc = 0;
-        id_ns->dpc = 0;
-        id_ns->dps = 0;
-        id_ns->lbaf[0].ds = BDRV_SECTOR_BITS;
-        id_ns->ncap  = id_ns->nuse = id_ns->nsze =
-            cpu_to_le64(n->ns_size >>
-                id_ns->lbaf[NVME_ID_NS_FLBAS_INDEX(ns->id_ns.flbas)].ds);
+        if (nvme_init_namespace(n, &n->namespaces[i], errp)) {
+            return;
+        }
      }
  }
 
#28 lore raw

PATCH 15/16 nvme: factor out cmb setup

In reply to Klaus Jensen

From: Klaus Jensen <[email protected]>

---
 hw/block/nvme.c | 50 +++++++++++++++++++++++++++----------------------
 1 file changed, 28 insertions(+), 22 deletions(-)
hw/block/nvme.c +28 -22
index 16d01af53a07..7387cf409f96 100644
@@ -44,6 +44,8 @@
 #include "trace.h"
 #include "nvme.h"
 
+#define NVME_CMB_BIR 2
+
 #define NVME_GUEST_ERR(trace, fmt, ...) \
     do { \
         (trace_##trace)(__VA_ARGS__); \
@@ -1382,6 +1384,28 @@ static int nvme_init_namespace(NvmeCtrl *n, NvmeNamespace *ns, Error **errp)
     return 0;
 }
 
+static void nvme_init_cmb(NvmeCtrl *n, PCIDevice *pci_dev)
+{
+    NVME_CMBLOC_SET_BIR(n->bar.cmbloc, NVME_CMB_BIR);
+    NVME_CMBLOC_SET_OFST(n->bar.cmbloc, 0);
+
+    NVME_CMBSZ_SET_SQS(n->bar.cmbsz, 1);
+    NVME_CMBSZ_SET_CQS(n->bar.cmbsz, 0);
+    NVME_CMBSZ_SET_LISTS(n->bar.cmbsz, 0);
+    NVME_CMBSZ_SET_RDS(n->bar.cmbsz, 1);
+    NVME_CMBSZ_SET_WDS(n->bar.cmbsz, 1);
+    NVME_CMBSZ_SET_SZU(n->bar.cmbsz, 2);
+    NVME_CMBSZ_SET_SZ(n->bar.cmbsz, n->params.cmb_size_mb);
+
+    n->cmbuf = g_malloc0(NVME_CMBSZ_GETSIZE(n->bar.cmbsz));
+    memory_region_init_io(&n->ctrl_mem, OBJECT(n), &nvme_cmb_ops, n,
+                          "nvme-cmb", NVME_CMBSZ_GETSIZE(n->bar.cmbsz));
+    pci_register_bar(pci_dev, NVME_CMBLOC_BIR(n->bar.cmbloc),
+                     PCI_BASE_ADDRESS_SPACE_MEMORY |
+                     PCI_BASE_ADDRESS_MEM_TYPE_64 |
+                     PCI_BASE_ADDRESS_MEM_PREFETCH, &n->ctrl_mem);
+}
+
 static void nvme_init_pci(NvmeCtrl *n, PCIDevice *pci_dev)
 {
     uint8_t *pci_conf = pci_dev->config;
@@ -1398,6 +1422,10 @@ static void nvme_init_pci(NvmeCtrl *n, PCIDevice *pci_dev)
     pci_register_bar(pci_dev, 0, PCI_BASE_ADDRESS_SPACE_MEMORY |
                      PCI_BASE_ADDRESS_MEM_TYPE_64, &n->iomem);
     msix_init_exclusive_bar(pci_dev, n->params.max_ioqpairs + 1, 4, NULL);
+
+    if (n->params.cmb_size_mb) {
+        nvme_init_cmb(n, pci_dev);
+    }
 }
 
 static void nvme_realize(PCIDevice *pci_dev, Error **errp)
@@ -1454,28 +1482,6 @@ static void nvme_realize(PCIDevice *pci_dev, Error **errp)
     n->bar.vs = 0x00010200;
     n->bar.intmc = n->bar.intms = 0;
 
-    if (n->params.cmb_size_mb) {
-
-        NVME_CMBLOC_SET_BIR(n->bar.cmbloc, 2);
-        NVME_CMBLOC_SET_OFST(n->bar.cmbloc, 0);
-
-        NVME_CMBSZ_SET_SQS(n->bar.cmbsz, 1);
-        NVME_CMBSZ_SET_CQS(n->bar.cmbsz, 0);
-        NVME_CMBSZ_SET_LISTS(n->bar.cmbsz, 0);
-        NVME_CMBSZ_SET_RDS(n->bar.cmbsz, 1);
-        NVME_CMBSZ_SET_WDS(n->bar.cmbsz, 1);
-        NVME_CMBSZ_SET_SZU(n->bar.cmbsz, 2); /* MBs */
-        NVME_CMBSZ_SET_SZ(n->bar.cmbsz, n->params.cmb_size_mb);
-
-        n->cmbuf = g_malloc0(NVME_CMBSZ_GETSIZE(n->bar.cmbsz));
-        memory_region_init_io(&n->ctrl_mem, OBJECT(n), &nvme_cmb_ops, n,
-                              "nvme-cmb", NVME_CMBSZ_GETSIZE(n->bar.cmbsz));
-        pci_register_bar(pci_dev, NVME_CMBLOC_BIR(n->bar.cmbloc),
-            PCI_BASE_ADDRESS_SPACE_MEMORY | PCI_BASE_ADDRESS_MEM_TYPE_64 |
-            PCI_BASE_ADDRESS_MEM_PREFETCH, &n->ctrl_mem);
-
-    }
-
     for (i = 0; i < n->num_namespaces; i++) {
         if (nvme_init_namespace(n, &n->namespaces[i], errp)) {
             return;
Signature · 1 line
2.26.0
#22 lore raw

PATCH 13/16 nvme: factor out namespace setup

In reply to Klaus Jensen

From: Klaus Jensen <[email protected]>

---
 hw/block/nvme.c | 47 ++++++++++++++++++++++++++---------------------
 1 file changed, 26 insertions(+), 21 deletions(-)
hw/block/nvme.c +26 -21
index f0989cbb4335..08f7ae0a48b3 100644
@@ -1359,13 +1359,35 @@ static int nvme_init_blk(NvmeCtrl *n, Error **errp)
     return 0;
 }
 
+static int nvme_init_namespace(NvmeCtrl *n, NvmeNamespace *ns, Error **errp)
+{
+    int64_t bs_size;
+    NvmeIdNs *id_ns = &ns->id_ns;
+
+    bs_size = blk_getlength(n->conf.blk);
+    if (bs_size < 0) {
+        error_setg_errno(errp, -bs_size, "could not get backing file size");
+        return -1;
+    }
+
+    n->ns_size = bs_size;
+
+    id_ns->lbaf[0].ds = BDRV_SECTOR_BITS;
+    id_ns->nsze = cpu_to_le64(nvme_ns_nlbas(n, ns));
+
+    /* no thin provisioning */
+    id_ns->ncap = id_ns->nsze;
+    id_ns->nuse = id_ns->ncap;
+
+    return 0;
+}
+
 static void nvme_realize(PCIDevice *pci_dev, Error **errp)
 {
     NvmeCtrl *n = NVME(pci_dev);
     NvmeIdCtrl *id = &n->id_ctrl;
 
     int i;
-    int64_t bs_size;
     uint8_t *pci_conf;
 
     if (nvme_check_constraints(n, errp)) {
@@ -1374,12 +1396,6 @@ static void nvme_realize(PCIDevice *pci_dev, Error **errp)
 
     nvme_init_state(n);
 
-    bs_size = blk_getlength(n->conf.blk);
-    if (bs_size < 0) {
-        error_setg(errp, "could not get backing file size");
-        return;
-    }
-
     if (nvme_init_blk(n, errp)) {
         return;
     }
@@ -1390,8 +1406,6 @@ static void nvme_realize(PCIDevice *pci_dev, Error **errp)
     pci_config_set_class(pci_dev->config, PCI_CLASS_STORAGE_EXPRESS);
     pcie_endpoint_cap_init(pci_dev, 0x80);
 
-    n->ns_size = bs_size / (uint64_t)n->num_namespaces;
-
     memory_region_init_io(&n->iomem, OBJECT(n), &nvme_mmio_ops, n,
                           "nvme", n->reg_size);
     pci_register_bar(pci_dev, 0,
@@ -1455,18 +1469,9 @@ static void nvme_realize(PCIDevice *pci_dev, Error **errp)
     }
 
     for (i = 0; i < n->num_namespaces; i++) {
-        NvmeNamespace *ns = &n->namespaces[i];
-        NvmeIdNs *id_ns = &ns->id_ns;
-        id_ns->nsfeat = 0;
-        id_ns->nlbaf = 0;
-        id_ns->flbas = 0;
-        id_ns->mc = 0;
-        id_ns->dpc = 0;
-        id_ns->dps = 0;
-        id_ns->lbaf[0].ds = BDRV_SECTOR_BITS;
-        id_ns->ncap  = id_ns->nuse = id_ns->nsze =
-            cpu_to_le64(n->ns_size >>
-                id_ns->lbaf[NVME_ID_NS_FLBAS_INDEX(ns->id_ns.flbas)].ds);
+        if (nvme_init_namespace(n, &n->namespaces[i], errp)) {
+            return;
+        }
     }
 }
 
Signature · 1 line
2.26.0
#21 lore raw

Re: [PATCH 12/16] nvme: add namespace helpers

In reply to Klaus Jensen
Quoted 33 lines · Klaus Jensen

From: Klaus Jensen <[email protected]>

Introduce some small helpers to make the next patches easier on the eye.

---
  hw/block/nvme.h | 16 ++++++++++++++++
  1 file changed, 16 insertions(+)
hw/block/nvme.h +11 -0
index ad1786953be9..d9900bed957c 100644
@@ -67,6 +67,17 @@ typedef struct NvmeNamespace {
      NvmeIdNs        id_ns;
  } NvmeNamespace;
 
+static inline NvmeLBAF *nvme_ns_lbaf(NvmeNamespace *ns)
+{
+    NvmeIdNs *id_ns = &ns->id_ns;
+    return &id_ns->lbaf[NVME_ID_NS_FLBAS_INDEX(id_ns->flbas)];
+}
+
+static inline uint8_t nvme_ns_lbads(NvmeNamespace *ns)
+{
+    return nvme_ns_lbaf(ns)->ds;
+}
+
  #define TYPE_NVME "nvme"
  #define NVME(obj) \
          OBJECT_CHECK(NvmeCtrl, (obj), TYPE_NVME)

hw/block/nvme.h typedef struct NvmeCtrl { · line 120

Quoted 9 lines
hw/block/nvme.h +5 -0
@@ -101,4 +112,9 @@ typedef struct NvmeCtrl {
      NvmeIdCtrl      id_ctrl;
  } NvmeCtrl;
 
+static inline uint64_t nvme_ns_nlbas(NvmeCtrl *n, NvmeNamespace *ns)
+{
+    return n->ns_size >> nvme_ns_lbads(ns);
+}
+
  #endif /* HW_NVME_H */

Personally I'd use it directly in the same patch, this is one more hunk:

@@ -1455,18 +1469,9 @@ static void nvme_realize(PCIDevice *pci_dev, Error **errp) [...]
- id_ns->ncap = id_ns->nuse = id_ns->nsze =
- cpu_to_le64(n->ns_size >>
- id_ns->lbaf[NVME_ID_NS_FLBAS_INDEX(ns->id_ns.flbas)].ds);
+ cpu_to_le64(nvme_ns_nlbas(n, ns));

Reviewed-by on v1 15/16
#29 lore raw

Re: [PATCH 15/16] nvme: factor out cmb setup

In reply to Klaus Jensen
Quoted 25 lines · Klaus Jensen

From: Klaus Jensen <[email protected]>

---
  hw/block/nvme.c | 50 +++++++++++++++++++++++++++----------------------
  1 file changed, 28 insertions(+), 22 deletions(-)
hw/block/nvme.c +3 -0
index 16d01af53a07..7387cf409f96 100644
@@ -44,6 +44,8 @@
  #include "trace.h"
  #include "nvme.h"
 
+#define NVME_CMB_BIR 2
+
  #define NVME_GUEST_ERR(trace, fmt, ...) \
      do { \
          (trace_##trace)(__VA_ARGS__); \
@@ -1382,6 +1384,28 @@ static int nvme_init_namespace(NvmeCtrl *n, NvmeNamespace *ns, Error **errp)
      return 0;
  }
 
+static void nvme_init_cmb(NvmeCtrl *n, PCIDevice *pci_dev)

hw/block/nvme.c static int nvme_init_namespace(NvmeCtrl *n, NvmeNamespace *ns, Error **errp) · line 1397

Quoted 10 lines
hw/block/nvme.c +10 -0
+{
+    NVME_CMBLOC_SET_BIR(n->bar.cmbloc, NVME_CMB_BIR);
+    NVME_CMBLOC_SET_OFST(n->bar.cmbloc, 0);
+
+    NVME_CMBSZ_SET_SQS(n->bar.cmbsz, 1);
+    NVME_CMBSZ_SET_CQS(n->bar.cmbsz, 0);
+    NVME_CMBSZ_SET_LISTS(n->bar.cmbsz, 0);
+    NVME_CMBSZ_SET_RDS(n->bar.cmbsz, 1);
+    NVME_CMBSZ_SET_WDS(n->bar.cmbsz, 1);
+    NVME_CMBSZ_SET_SZU(n->bar.cmbsz, 2);

We lost the /* MBs */ comment, otherwise:

Quoted 55 lines
hw/block/nvme.c +15 -22
+    NVME_CMBSZ_SET_SZ(n->bar.cmbsz, n->params.cmb_size_mb);
+
+    n->cmbuf = g_malloc0(NVME_CMBSZ_GETSIZE(n->bar.cmbsz));
+    memory_region_init_io(&n->ctrl_mem, OBJECT(n), &nvme_cmb_ops, n,
+                          "nvme-cmb", NVME_CMBSZ_GETSIZE(n->bar.cmbsz));
+    pci_register_bar(pci_dev, NVME_CMBLOC_BIR(n->bar.cmbloc),
+                     PCI_BASE_ADDRESS_SPACE_MEMORY |
+                     PCI_BASE_ADDRESS_MEM_TYPE_64 |
+                     PCI_BASE_ADDRESS_MEM_PREFETCH, &n->ctrl_mem);
+}
+
  static void nvme_init_pci(NvmeCtrl *n, PCIDevice *pci_dev)
  {
      uint8_t *pci_conf = pci_dev->config;
@@ -1398,6 +1422,10 @@ static void nvme_init_pci(NvmeCtrl *n, PCIDevice *pci_dev)
      pci_register_bar(pci_dev, 0, PCI_BASE_ADDRESS_SPACE_MEMORY |
                       PCI_BASE_ADDRESS_MEM_TYPE_64, &n->iomem);
      msix_init_exclusive_bar(pci_dev, n->params.max_ioqpairs + 1, 4, NULL);
+
+    if (n->params.cmb_size_mb) {
+        nvme_init_cmb(n, pci_dev);
+    }
  }
 
  static void nvme_realize(PCIDevice *pci_dev, Error **errp)
@@ -1454,28 +1482,6 @@ static void nvme_realize(PCIDevice *pci_dev, Error **errp)
      n->bar.vs = 0x00010200;
      n->bar.intmc = n->bar.intms = 0;
 
-    if (n->params.cmb_size_mb) {
-
-        NVME_CMBLOC_SET_BIR(n->bar.cmbloc, 2);
-        NVME_CMBLOC_SET_OFST(n->bar.cmbloc, 0);
-
-        NVME_CMBSZ_SET_SQS(n->bar.cmbsz, 1);
-        NVME_CMBSZ_SET_CQS(n->bar.cmbsz, 0);
-        NVME_CMBSZ_SET_LISTS(n->bar.cmbsz, 0);
-        NVME_CMBSZ_SET_RDS(n->bar.cmbsz, 1);
-        NVME_CMBSZ_SET_WDS(n->bar.cmbsz, 1);
-        NVME_CMBSZ_SET_SZU(n->bar.cmbsz, 2); /* MBs */
-        NVME_CMBSZ_SET_SZ(n->bar.cmbsz, n->params.cmb_size_mb);
-
-        n->cmbuf = g_malloc0(NVME_CMBSZ_GETSIZE(n->bar.cmbsz));
-        memory_region_init_io(&n->ctrl_mem, OBJECT(n), &nvme_cmb_ops, n,
-                              "nvme-cmb", NVME_CMBSZ_GETSIZE(n->bar.cmbsz));
-        pci_register_bar(pci_dev, NVME_CMBLOC_BIR(n->bar.cmbloc),
-            PCI_BASE_ADDRESS_SPACE_MEMORY | PCI_BASE_ADDRESS_MEM_TYPE_64 |
-            PCI_BASE_ADDRESS_MEM_PREFETCH, &n->ctrl_mem);
-
-    }
-
      for (i = 0; i < n->num_namespaces; i++) {
          if (nvme_init_namespace(n, &n->namespaces[i], errp)) {
              return;
#27 lore raw

Re: [PATCH 14/16] nvme: factor out pci setup

In reply to Klaus Jensen
Quoted 12 lines · Klaus Jensen

From: Klaus Jensen <[email protected]>

---
  hw/block/nvme.c | 32 ++++++++++++++++++++------------
  1 file changed, 20 insertions(+), 12 deletions(-)
hw/block/nvme.c +0 -0
index 08f7ae0a48b3..16d01af53a07 100644

hw/block/nvme.c static int nvme_init_namespace(NvmeCtrl *n, NvmeNamespace *ns, Error **errp) · line 1390

Quoted 9 lines
hw/block/nvme.c +6 -0
@@ -1382,6 +1382,24 @@ static int nvme_init_namespace(NvmeCtrl *n, NvmeNamespace *ns, Error **errp)
      return 0;
  }
 
+static void nvme_init_pci(NvmeCtrl *n, PCIDevice *pci_dev)
+{
+    uint8_t *pci_conf = pci_dev->config;
+
+    pci_conf[PCI_INTERRUPT_PIN] = 1;
+    pci_config_set_prog_interface(pci_conf, 0x2);

<--

hw/block/nvme.c static int nvme_init_namespace(NvmeCtrl *n, NvmeNamespace *ns, Error **errp) · line 1392

Quoted 2 lines
hw/block/nvme.c +2 -0
+    pci_config_set_vendor_id(pci_conf, PCI_VENDOR_ID_INTEL);
+    pci_config_set_device_id(pci_conf, 0x5845);

-->

This is new. Already inherited by nvme_class_init().

Quoted 36 lines
hw/block/nvme.c +12 -12
+    pci_config_set_class(pci_conf, PCI_CLASS_STORAGE_EXPRESS);
+    pcie_endpoint_cap_init(pci_dev, 0x80);
+
+    memory_region_init_io(&n->iomem, OBJECT(n), &nvme_mmio_ops, n, "nvme",
+                          n->reg_size);
+    pci_register_bar(pci_dev, 0, PCI_BASE_ADDRESS_SPACE_MEMORY |
+                     PCI_BASE_ADDRESS_MEM_TYPE_64, &n->iomem);
+    msix_init_exclusive_bar(pci_dev, n->params.max_ioqpairs + 1, 4, NULL);
+}
+
  static void nvme_realize(PCIDevice *pci_dev, Error **errp)
  {
      NvmeCtrl *n = NVME(pci_dev);
@@ -1400,19 +1418,9 @@ static void nvme_realize(PCIDevice *pci_dev, Error **errp)
          return;
      }
 
+    nvme_init_pci(n, pci_dev);
+
      pci_conf = pci_dev->config;
-    pci_conf[PCI_INTERRUPT_PIN] = 1;
-    pci_config_set_prog_interface(pci_dev->config, 0x2);
-    pci_config_set_class(pci_dev->config, PCI_CLASS_STORAGE_EXPRESS);
-    pcie_endpoint_cap_init(pci_dev, 0x80);
-
-    memory_region_init_io(&n->iomem, OBJECT(n), &nvme_mmio_ops, n,
-                          "nvme", n->reg_size);
-    pci_register_bar(pci_dev, 0,
-        PCI_BASE_ADDRESS_SPACE_MEMORY | PCI_BASE_ADDRESS_MEM_TYPE_64,
-        &n->iomem);
-    msix_init_exclusive_bar(pci_dev, n->params.max_ioqpairs + 1, 4, NULL);
-
      id->vid = cpu_to_le16(pci_get_word(pci_conf + PCI_VENDOR_ID));
      id->ssvid = cpu_to_le16(pci_get_word(pci_conf + PCI_SUBSYSTEM_VENDOR_ID));
      strpadcpy((char *)id->mn, sizeof(id->mn), "QEMU NVMe Ctrl", ' ');
Reviewed-by on v1 11/16
#17 lore raw

Re: [PATCH 11/16] nvme: factor out block backend setup

In reply to Klaus Jensen
Quoted 14 lines · Klaus Jensen

From: Klaus Jensen <[email protected]>

---
  hw/block/nvme.c | 15 ++++++++++++---
  1 file changed, 12 insertions(+), 3 deletions(-)
hw/block/nvme.c +0 -0
index e67f578fbf79..f0989cbb4335 100644
@@ -1348,6 +1348,17 @@ static void nvme_init_state(NvmeCtrl *n)
      n->cq = g_new0(NvmeCQueue *, n->params.max_ioqpairs + 1);
  }

hw/block/nvme.c static void nvme_init_state(NvmeCtrl *n) · line 1359

Quoted 10 lines
hw/block/nvme.c +9 -0
 
+static int nvme_init_blk(NvmeCtrl *n, Error **errp)
+{
+    blkconf_blocksizes(&n->conf);
+    if (!blkconf_apply_backend_options(&n->conf, blk_is_read_only(n->conf.blk),
+                                       false, errp)) {
+        return -1;
+    }
+
+    return 0;

I'm not sure this is a correct usage of the 'propagating errors' API (see CODING_STYLE.rst and include/qapi/error.h), I'd expect this function to return void, and use a local_error & error_propagate() in nvme_realize().

However this works, so:

Quoted 17 lines
hw/block/nvme.c +3 -3
+}
+
  static void nvme_realize(PCIDevice *pci_dev, Error **errp)
  {
      NvmeCtrl *n = NVME(pci_dev);
@@ -1369,9 +1380,7 @@ static void nvme_realize(PCIDevice *pci_dev, Error **errp)
          return;
      }
 
-    blkconf_blocksizes(&n->conf);
-    if (!blkconf_apply_backend_options(&n->conf, blk_is_read_only(n->conf.blk),
-                                       false, errp)) {
+    if (nvme_init_blk(n, errp)) {
          return;
      }
 
#24 lore raw

Re: [PATCH 13/16] nvme: factor out namespace setup

In reply to Philippe Mathieu-Daudé
Quoted 55 lines · Philippe Mathieu-Daudé
Quoted 54 lines · Klaus Jensen

From: Klaus Jensen <[email protected]>

---
  hw/block/nvme.c | 47 ++++++++++++++++++++++++++---------------------
  1 file changed, 26 insertions(+), 21 deletions(-)
hw/block/nvme.c +23 -7
index f0989cbb4335..08f7ae0a48b3 100644
@@ -1359,13 +1359,35 @@ static int nvme_init_blk(NvmeCtrl *n, Error **errp)
      return 0;
  }
+static int nvme_init_namespace(NvmeCtrl *n, NvmeNamespace *ns, Error **errp)
+{
+    int64_t bs_size;
+    NvmeIdNs *id_ns = &ns->id_ns;
+
+    bs_size = blk_getlength(n->conf.blk);
+    if (bs_size < 0) {
+        error_setg_errno(errp, -bs_size, "could not get backing file size");
+        return -1;
+    }
+
+    n->ns_size = bs_size;
+
+    id_ns->lbaf[0].ds = BDRV_SECTOR_BITS;
+    id_ns->nsze = cpu_to_le64(nvme_ns_nlbas(n, ns));
+
+    /* no thin provisioning */
+    id_ns->ncap = id_ns->nsze;
+    id_ns->nuse = id_ns->ncap;
+
+    return 0;
+}
+
  static void nvme_realize(PCIDevice *pci_dev, Error **errp)
  {
      NvmeCtrl *n = NVME(pci_dev);
      NvmeIdCtrl *id = &n->id_ctrl;
      int i;
-    int64_t bs_size;
      uint8_t *pci_conf;
      if (nvme_check_constraints(n, errp)) {
@@ -1374,12 +1396,6 @@ static void nvme_realize(PCIDevice *pci_dev, Error **errp)
      nvme_init_state(n);
-    bs_size = blk_getlength(n->conf.blk);
-    if (bs_size < 0) {
-        error_setg(errp, "could not get backing file size");
-        return;
-    }
-
      if (nvme_init_blk(n, errp)) {
Quoted 9 lines

hw/block/nvme.c static void nvme_realize(PCIDevice *pci_dev, Error **errp) · line 1392

Quoted 6 lines
hw/block/nvme.c +0 -1
          return;
      }
@@ -1390,8 +1406,6 @@ static void nvme_realize(PCIDevice *pci_dev, Error **errp)
      pci_config_set_class(pci_dev->config, PCI_CLASS_STORAGE_EXPRESS);
      pcie_endpoint_cap_init(pci_dev, 0x80);
-    n->ns_size = bs_size / (uint64_t)n->num_namespaces;

I'm not sure this line belong to this patch.

It does. It is already there in the middle of the realize function. It is moved to nvme_init_namespace as

  n->ns_size = bs_size;

since only a single namespace can be configured anyway. I will remove the for-loop that initializes multiple namespaces as well.

Reviewed-by on v1 10/16
#15 lore raw

Re: [PATCH 10/16] nvme: factor out device state setup

In reply to Klaus Jensen
Quoted 42 lines · Klaus Jensen

From: Klaus Jensen <[email protected]>

---
  hw/block/nvme.c | 17 +++++++++++------
  1 file changed, 11 insertions(+), 6 deletions(-)
hw/block/nvme.c +11 -1
index 635292d6fac4..e67f578fbf79 100644
@@ -1339,6 +1339,15 @@ static int nvme_check_constraints(NvmeCtrl *n, Error **errp)
      return 0;
  }
 
+static void nvme_init_state(NvmeCtrl *n)
+{
+    n->num_namespaces = 1;
+    n->reg_size = pow2ceil(0x1008 + 2 * (n->params.max_ioqpairs) * 4);
+    n->namespaces = g_new0(NvmeNamespace, n->num_namespaces);
+    n->sq = g_new0(NvmeSQueue *, n->params.max_ioqpairs + 1);
+    n->cq = g_new0(NvmeCQueue *, n->params.max_ioqpairs + 1);
+}
+
  static void nvme_realize(PCIDevice *pci_dev, Error **errp)
  {
      NvmeCtrl *n = NVME(pci_dev);
@@ -1352,6 +1361,8 @@ static void nvme_realize(PCIDevice *pci_dev, Error **errp)
          return;
      }
 
+    nvme_init_state(n);
+
      bs_size = blk_getlength(n->conf.blk);
      if (bs_size < 0) {
          error_setg(errp, "could not get backing file size");
@@ -1370,14 +1381,8 @@ static void nvme_realize(PCIDevice *pci_dev, Error **errp)
      pci_config_set_class(pci_dev->config, PCI_CLASS_STORAGE_EXPRESS);
      pcie_endpoint_cap_init(pci_dev, 0x80);
 
-    n->num_namespaces = 1;

hw/block/nvme.c static void nvme_realize(PCIDevice *pci_dev, Error **errp) · line 1388

Quoted 10 lines
hw/block/nvme.c +0 -5
-    n->reg_size = pow2ceil(0x1008 + 2 * (n->params.max_ioqpairs) * 4);
      n->ns_size = bs_size / (uint64_t)n->num_namespaces;
 
-    n->namespaces = g_new0(NvmeNamespace, n->num_namespaces);
-    n->sq = g_new0(NvmeSQueue *, n->params.max_ioqpairs + 1);
-    n->cq = g_new0(NvmeCQueue *, n->params.max_ioqpairs + 1);
-
      memory_region_init_io(&n->iomem, OBJECT(n), &nvme_mmio_ops, n,
                            "nvme", n->reg_size);
      pci_register_bar(pci_dev, 0,
Reviewed-by on v1 9/16
#13 lore raw

Re: [PATCH 09/16] nvme: factor out property/constraint checks

In reply to Klaus Jensen
Quoted 34 lines · Klaus Jensen

From: Klaus Jensen <[email protected]>

---
  hw/block/nvme.c | 52 ++++++++++++++++++++++++++++++-------------------
  1 file changed, 32 insertions(+), 20 deletions(-)
hw/block/nvme.c +19 -0
index ea613213bd57..635292d6fac4 100644
@@ -1308,6 +1308,37 @@ static const MemoryRegionOps nvme_cmb_ops = {
      },
  };
 
+static int nvme_check_constraints(NvmeCtrl *n, Error **errp)
+{
+    NvmeParams *params = &n->params;
+
+    if (params->num_queues) {
+        warn_report("num_queues is deprecated; please use max_ioqpairs "
+                    "instead");
+
+        params->max_ioqpairs = params->num_queues - 1;
+    }
+
+    if (params->max_ioqpairs < 1 ||
+        params->max_ioqpairs > PCI_MSIX_FLAGS_QSIZE) {
+        error_setg(errp, "max_ioqpairs must be between 1 and %d",
+                   PCI_MSIX_FLAGS_QSIZE);
+        return -1;
+    }
+
+    if (!n->conf.blk) {

hw/block/nvme.c static const MemoryRegionOps nvme_cmb_ops = { · line 1339

Quoted 10 lines
hw/block/nvme.c +10 -0
+        error_setg(errp, "drive property not set");
+        return -1;
+    }
+
+    if (!params->serial) {
+        error_setg(errp, "serial property not set");
+        return -1;
+    }
+
+    return 0;

Similar comment than nvme_init_blk(), I'd expect this function to return void, and use a local_error & error_propagate() in nvme_realize().

Quoted 41 lines
hw/block/nvme.c +3 -20
+}
+
  static void nvme_realize(PCIDevice *pci_dev, Error **errp)
  {
      NvmeCtrl *n = NVME(pci_dev);
@@ -1317,22 +1348,7 @@ static void nvme_realize(PCIDevice *pci_dev, Error **errp)
      int64_t bs_size;
      uint8_t *pci_conf;
 
-    if (n->params.num_queues) {
-        warn_report("num_queues is deprecated; please use max_ioqpairs "
-                    "instead");
-
-        n->params.max_ioqpairs = n->params.num_queues - 1;
-    }
-
-    if (n->params.max_ioqpairs < 1 ||
-        n->params.max_ioqpairs > PCI_MSIX_FLAGS_QSIZE) {
-        error_setg(errp, "max_ioqpairs must be between 1 and %d",
-                   PCI_MSIX_FLAGS_QSIZE);
-        return;
-    }
-
-    if (!n->conf.blk) {
-        error_setg(errp, "drive property not set");
+    if (nvme_check_constraints(n, errp)) {
          return;
      }
 
@@ -1342,10 +1358,6 @@ static void nvme_realize(PCIDevice *pci_dev, Error **errp)
          return;
      }
 
-    if (!n->params.serial) {
-        error_setg(errp, "serial property not set");
-        return;
-    }
      blkconf_blocksizes(&n->conf);
      if (!blkconf_apply_backend_options(&n->conf, blk_is_read_only(n->conf.blk),
                                         false, errp)) {
#25 lore raw

Re: [PATCH 13/16] nvme: factor out namespace setup

In reply to Klaus Birkelund Jensen
Quoted 5 lines · Klaus Birkelund Jensen
Quoted 3 lines · Philippe Mathieu-Daudé

I'm not sure this line belong to this patch.

Quoted 7 lines

It does. It is already there in the middle of the realize function. It is moved to nvme_init_namespace as

  n->ns_size = bs_size;

since only a single namespace can be configured anyway. I will remove the for-loop that initializes multiple namespaces as well.

I'm gonna backtrack on that. Removing that for loop is just noise I think.

Reviewed-by on v1 7/16
#10 lore raw

Re: [PATCH 07/16] nvme: add max_ioqpairs device parameter

In reply to Klaus Jensen
Quoted 151 lines · Klaus Jensen

From: Klaus Jensen <[email protected]>

The num_queues device paramater has a slightly confusing meaning because it accounts for the admin queue pair which is not really optional. Secondly, it is really a maximum value of queues allowed.

Add a new max_ioqpairs parameter that only accounts for I/O queue pairs, but keep num_queues for compatibility.

---
  hw/block/nvme.c | 46 ++++++++++++++++++++++++++++------------------
  hw/block/nvme.h |  4 +++-
  2 files changed, 31 insertions(+), 19 deletions(-)
hw/block/nvme.c +28 -18
index 287e1e49c0bf..9383d2cb0b38 100644
@@ -19,7 +19,7 @@
   *      -drive file=<file>,if=none,id=<drive_id>
   *      -device nvme,drive=<drive_id>,serial=<serial>,id=<id[optional]>, \
   *              cmb_size_mb=<cmb_size_mb[optional]>, \
- *              num_queues=<N[optional]>
+ *              max_ioqpairs=<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.
@@ -27,6 +27,7 @@
 
  #include "qemu/osdep.h"
  #include "qemu/units.h"
+#include "qemu/error-report.h"
  #include "hw/block/block.h"
  #include "hw/pci/msix.h"
  #include "hw/pci/pci.h"
@@ -72,12 +73,12 @@ static void nvme_addr_read(NvmeCtrl *n, hwaddr addr, void *buf, int size)
 
  static int nvme_check_sqid(NvmeCtrl *n, uint16_t sqid)
  {
-    return sqid < n->params.num_queues && n->sq[sqid] != NULL ? 0 : -1;
+    return sqid < n->params.max_ioqpairs + 1 && n->sq[sqid] != NULL ? 0 : -1;
  }
 
  static int nvme_check_cqid(NvmeCtrl *n, uint16_t cqid)
  {
-    return cqid < n->params.num_queues && n->cq[cqid] != NULL ? 0 : -1;
+    return cqid < n->params.max_ioqpairs + 1 && n->cq[cqid] != NULL ? 0 : -1;
  }
 
  static void nvme_inc_cq_tail(NvmeCQueue *cq)
@@ -639,7 +640,7 @@ static uint16_t nvme_create_cq(NvmeCtrl *n, NvmeCmd *cmd)
          trace_nvme_dev_err_invalid_create_cq_addr(prp1);
          return NVME_INVALID_FIELD | NVME_DNR;
      }
-    if (unlikely(vector > n->params.num_queues)) {
+    if (unlikely(vector > n->params.max_ioqpairs + 1)) {
          trace_nvme_dev_err_invalid_create_cq_vector(vector);
          return NVME_INVALID_IRQ_VECTOR | NVME_DNR;
      }
@@ -791,8 +792,8 @@ static uint16_t nvme_get_feature(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
          trace_nvme_dev_getfeat_vwcache(result ? "enabled" : "disabled");
          break;
      case NVME_NUMBER_OF_QUEUES:
-        result = cpu_to_le32((n->params.num_queues - 2) |
-                             ((n->params.num_queues - 2) << 16));
+        result = cpu_to_le32((n->params.max_ioqpairs - 1) |
+                             ((n->params.max_ioqpairs - 1) << 16));
          trace_nvme_dev_getfeat_numq(result);
          break;
      case NVME_TIMESTAMP:
@@ -836,10 +837,10 @@ static uint16_t nvme_set_feature(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
      case NVME_NUMBER_OF_QUEUES:
          trace_nvme_dev_setfeat_numq((dw11 & 0xFFFF) + 1,
                                      ((dw11 >> 16) & 0xFFFF) + 1,
-                                    n->params.num_queues - 1,
-                                    n->params.num_queues - 1);
-        req->cqe.result = cpu_to_le32((n->params.num_queues - 2) |
-                                      ((n->params.num_queues - 2) << 16));
+                                    n->params.max_ioqpairs,
+                                    n->params.max_ioqpairs);
+        req->cqe.result = cpu_to_le32((n->params.max_ioqpairs - 1) |
+                                      ((n->params.max_ioqpairs - 1) << 16));
          break;
      case NVME_TIMESTAMP:
          return nvme_set_feature_timestamp(n, cmd);
@@ -910,12 +911,12 @@ static void nvme_clear_ctrl(NvmeCtrl *n)
 
      blk_drain(n->conf.blk);
 
-    for (i = 0; i < n->params.num_queues; i++) {
+    for (i = 0; i < n->params.max_ioqpairs + 1; i++) {
          if (n->sq[i] != NULL) {
              nvme_free_sq(n->sq[i], n);
          }
      }
-    for (i = 0; i < n->params.num_queues; i++) {
+    for (i = 0; i < n->params.max_ioqpairs + 1; i++) {
          if (n->cq[i] != NULL) {
              nvme_free_cq(n->cq[i], n);
          }
@@ -1316,8 +1317,17 @@ static void nvme_realize(PCIDevice *pci_dev, Error **errp)
      int64_t bs_size;
      uint8_t *pci_conf;
 
-    if (!n->params.num_queues) {
-        error_setg(errp, "num_queues can't be zero");
+    if (n->params.num_queues) {
+        warn_report("num_queues is deprecated; please use max_ioqpairs "
+                    "instead");
+
+        n->params.max_ioqpairs = n->params.num_queues - 1;
+    }
+
+    if (n->params.max_ioqpairs < 1 ||
+        n->params.max_ioqpairs > PCI_MSIX_FLAGS_QSIZE) {
+        error_setg(errp, "max_ioqpairs must be between 1 and %d",
+                   PCI_MSIX_FLAGS_QSIZE);
          return;
      }
 
@@ -1349,19 +1359,19 @@ static void nvme_realize(PCIDevice *pci_dev, Error **errp)
      pcie_endpoint_cap_init(pci_dev, 0x80);
 
      n->num_namespaces = 1;
-    n->reg_size = pow2ceil(0x1000 + 2 * n->params.num_queues * 4);
+    n->reg_size = pow2ceil(0x1008 + 2 * (n->params.max_ioqpairs) * 4);
      n->ns_size = bs_size / (uint64_t)n->num_namespaces;
 
      n->namespaces = g_new0(NvmeNamespace, n->num_namespaces);
-    n->sq = g_new0(NvmeSQueue *, n->params.num_queues);
-    n->cq = g_new0(NvmeCQueue *, n->params.num_queues);
+    n->sq = g_new0(NvmeSQueue *, n->params.max_ioqpairs + 1);
+    n->cq = g_new0(NvmeCQueue *, n->params.max_ioqpairs + 1);
 
      memory_region_init_io(&n->iomem, OBJECT(n), &nvme_mmio_ops, n,
                            "nvme", n->reg_size);
      pci_register_bar(pci_dev, 0,
          PCI_BASE_ADDRESS_SPACE_MEMORY | PCI_BASE_ADDRESS_MEM_TYPE_64,
          &n->iomem);
-    msix_init_exclusive_bar(pci_dev, n->params.num_queues, 4, NULL);
+    msix_init_exclusive_bar(pci_dev, n->params.max_ioqpairs + 1, 4, NULL);
 
      id->vid = cpu_to_le16(pci_get_word(pci_conf + PCI_VENDOR_ID));
      id->ssvid = cpu_to_le16(pci_get_word(pci_conf + PCI_SUBSYSTEM_VENDOR_ID));
hw/block/nvme.h +0 -0
index 9957c4a200e2..98f5b9479244 100644

hw/block/nvme.h line 14

Quoted 10 lines
hw/block/nvme.h +2 -1
@@ -6,11 +6,13 @@
  #define DEFINE_NVME_PROPERTIES(_state, _props) \
      DEFINE_PROP_STRING("serial", _state, _props.serial), \
      DEFINE_PROP_UINT32("cmb_size_mb", _state, _props.cmb_size_mb, 0), \
-    DEFINE_PROP_UINT32("num_queues", _state, _props.num_queues, 64)
+    DEFINE_PROP_UINT32("num_queues", _state, _props.num_queues, 0), \
+    DEFINE_PROP_UINT32("max_ioqpairs", _state, _props.max_ioqpairs, 64)
 
  typedef struct NvmeParams {
      char     *serial;
      uint32_t num_queues;

I'm tempted to rename it 'deprecated_num_queues' ... Can you add a comment such /* deprecated since 5.0 */?

Quoted 5 lines
hw/block/nvme.h +1 -0
+    uint32_t max_ioqpairs;
      uint32_t cmb_size_mb;
  } NvmeParams;
 
#18 lore raw

Re: [PATCH 11/16] nvme: factor out block backend setup

In reply to Philippe Mathieu-Daudé
Quoted 29 lines · Philippe Mathieu-Daudé
Quoted 13 lines · Klaus Jensen

From: Klaus Jensen <[email protected]>

---
  hw/block/nvme.c | 15 ++++++++++++---
  1 file changed, 12 insertions(+), 3 deletions(-)
hw/block/nvme.c +0 -0
index e67f578fbf79..f0989cbb4335 100644
@@ -1348,6 +1348,17 @@ static void nvme_init_state(NvmeCtrl *n)
      n->cq = g_new0(NvmeCQueue *, n->params.max_ioqpairs + 1);

hw/block/nvme.c static void nvme_init_state(NvmeCtrl *n) · line 1358

Quoted 10 lines
hw/block/nvme.c +9 -0
  }
+static int nvme_init_blk(NvmeCtrl *n, Error **errp)
+{
+    blkconf_blocksizes(&n->conf);
+    if (!blkconf_apply_backend_options(&n->conf, blk_is_read_only(n->conf.blk),
+                                       false, errp)) {
+        return -1;
+    }
+
+    return 0;

I'm not sure this is a correct usage of the 'propagating errors' API (see CODING_STYLE.rst and include/qapi/error.h), I'd expect this function to return void, and use a local_error & error_propagate() in nvme_realize().

Quoted 3 lines

However this works, so:

So, I get that and did use the propagate functionality earlier. But I still used the int return. I'm not sure about the style if returning void - should I check if errp is now non-NULL? Point is that I need to return early since the later calls could fail if previous calls did not complete successfully.

Reviewed-by on v1 16/16
#31 lore raw

Re: [PATCH 16/16] nvme: factor out controller identify setup

In reply to Klaus Jensen
Quoted 6 lines · Klaus Jensen

From: Klaus Jensen <[email protected]>

---
  hw/block/nvme.c | 42 ++++++++++++++++++++++++------------------
  1 file changed, 24 insertions(+), 18 deletions(-)

The review is trivial using 'git-diff -W'.

Quoted 65 lines
hw/block/nvme.c +24 -18
index 7387cf409f96..d1566b56381d 100644
@@ -1428,27 +1428,11 @@ static void nvme_init_pci(NvmeCtrl *n, PCIDevice *pci_dev)
      }
  }
 
-static void nvme_realize(PCIDevice *pci_dev, Error **errp)
+static void nvme_init_ctrl(NvmeCtrl *n, PCIDevice *pci_dev)
  {
-    NvmeCtrl *n = NVME(pci_dev);
      NvmeIdCtrl *id = &n->id_ctrl;
+    uint8_t *pci_conf = pci_dev->config;
 
-    int i;
-    uint8_t *pci_conf;
-
-    if (nvme_check_constraints(n, errp)) {
-        return;
-    }
-
-    nvme_init_state(n);
-
-    if (nvme_init_blk(n, errp)) {
-        return;
-    }
-
-    nvme_init_pci(n, pci_dev);
-
-    pci_conf = pci_dev->config;
      id->vid = cpu_to_le16(pci_get_word(pci_conf + PCI_VENDOR_ID));
      id->ssvid = cpu_to_le16(pci_get_word(pci_conf + PCI_SUBSYSTEM_VENDOR_ID));
      strpadcpy((char *)id->mn, sizeof(id->mn), "QEMU NVMe Ctrl", ' ');
@@ -1482,6 +1466,28 @@ static void nvme_realize(PCIDevice *pci_dev, Error **errp)
      n->bar.vs = 0x00010200;
      n->bar.intmc = n->bar.intms = 0;
 
+
+}
+
+static void nvme_realize(PCIDevice *pci_dev, Error **errp)
+{
+    NvmeCtrl *n = NVME(pci_dev);
+
+    int i;
+
+    if (nvme_check_constraints(n, errp)) {
+        return;
+    }
+
+    nvme_init_state(n);
+
+    if (nvme_init_blk(n, errp)) {
+        return;
+    }
+
+    nvme_init_pci(n, pci_dev);
+    nvme_init_ctrl(n, pci_dev);
+
      for (i = 0; i < n->num_namespaces; i++) {
          if (nvme_init_namespace(n, &n->namespaces[i], errp)) {
              return;
#19 lore raw

Re: [PATCH 11/16] nvme: factor out block backend setup

In reply to Klaus Birkelund Jensen
Quoted 34 lines · Klaus Birkelund Jensen
Quoted 29 lines · Philippe Mathieu-Daudé
Quoted 13 lines · Klaus Jensen

From: Klaus Jensen <[email protected]>

---
  hw/block/nvme.c | 15 ++++++++++++---
  1 file changed, 12 insertions(+), 3 deletions(-)
hw/block/nvme.c +0 -0
index e67f578fbf79..f0989cbb4335 100644
@@ -1348,6 +1348,17 @@ static void nvme_init_state(NvmeCtrl *n)
      n->cq = g_new0(NvmeCQueue *, n->params.max_ioqpairs + 1);

hw/block/nvme.c static void nvme_init_state(NvmeCtrl *n) · line 1358

Quoted 10 lines
hw/block/nvme.c +9 -0
  }
+static int nvme_init_blk(NvmeCtrl *n, Error **errp)
+{
+    blkconf_blocksizes(&n->conf);
+    if (!blkconf_apply_backend_options(&n->conf, blk_is_read_only(n->conf.blk),
+                                       false, errp)) {
+        return -1;
+    }
+
+    return 0;

I'm not sure this is a correct usage of the 'propagating errors' API (see CODING_STYLE.rst and include/qapi/error.h), I'd expect this function to return void, and use a local_error & error_propagate() in nvme_realize().

Quoted 3 lines

However this works, so:

Quoted 5 lines

So, I get that and did use the propagate functionality earlier. But I still used the int return. I'm not sure about the style if returning void - should I check if errp is now non-NULL? Point is that I need to return early since the later calls could fail if previous calls did not complete successfully.

Nevermind, I got it. I've changed it to propagate it correctly.

Reviewed-by on v1 1/16
#2 lore raw

Re: [PATCH 01/16] nvme: fix pci doorbell size calculation

In reply to Klaus Jensen
Quoted 11 lines · Klaus Jensen

From: Klaus Jensen <[email protected]>

The size of the BAR is 0x1000 (main registers) + 8 bytes for each queue. Currently, the size of the BAR is calculated like so:

     n->reg_size = pow2ceil(0x1004 + 2 * (n->params.num_queues + 1) * 4);

Since the 'num_queues' parameter already accounts for the admin queue, this should in any case not need to be incremented by one. Also, the size should be initialized to (0x1000).

Quoted 5 lines
     n->reg_size = pow2ceil(0x1000 + 2 * n->params.num_queues * 4);

This, with the default value of num_queues (64), we will set aside room for 1 admin queue and 63 I/O queues (4 bytes per doorbell, 2 doorbells per queue).

It seems you are right, but I'd feel safer with a Ack-by from Keith.

Do you mind adding definitions such:

#define NVME_IO_SIZE (4 * KiB)
#define DOORBELL_SIZE 4
#define DOORBELL_COUNT 2

Looking at nvme_set_feature() I see better why you introduce max_ioqpairs in patch #7:

    case NVME_NUMBER_OF_QUEUES:
        trace_nvme_setfeat_numq((dw11 & 0xFFFF) + 1,
                                ((dw11 >> 16) & 0xFFFF) + 1,
                                n->num_queues - 1, n->num_queues - 1);
        req->cqe.result =
            cpu_to_le32((n->num_queues - 2) | ((n->num_queues - 2) << 16));
        break;
Quoted 20 lines
---
  hw/block/nvme.c | 2 +-
  1 file changed, 1 insertion(+), 1 deletion(-)
hw/block/nvme.c +1 -1
index d28335cbf377..77f9c151a665 100644
@@ -1345,7 +1345,7 @@ static void nvme_realize(PCIDevice *pci_dev, Error **errp)
      pcie_endpoint_cap_init(pci_dev, 0x80);
 
      n->num_namespaces = 1;
-    n->reg_size = pow2ceil(0x1004 + 2 * (n->num_queues + 1) * 4);
+    n->reg_size = pow2ceil(0x1000 + 2 * n->num_queues * 4);
      n->ns_size = bs_size / (uint64_t)n->num_namespaces;
 
      n->namespaces = g_new0(NvmeNamespace, n->num_namespaces);
#4 lore raw

Re: [PATCH 02/16] nvme: rename trace events to nvme_dev

In reply to Klaus Jensen
Quoted 3 lines · Klaus Jensen

From: Klaus Jensen <[email protected]>

Change the prefix of all nvme device related trace events to 'nvme_dev'

Another option is 'pci_nvme'. None of them make me happy but I can't find a better name.

Quoted 33 lines

to not clash with trace events from the nvme block driver.

---
  hw/block/nvme.c       | 190 +++++++++++++++++++++---------------------
  hw/block/trace-events | 172 +++++++++++++++++++-------------------
  2 files changed, 180 insertions(+), 182 deletions(-)
hw/block/nvme.c +3 -3
index 77f9c151a665..316cfc4d36e0 100644
@@ -112,16 +112,16 @@ static void nvme_irq_assert(NvmeCtrl *n, NvmeCQueue *cq)
  {
      if (cq->irq_enabled) {
          if (msix_enabled(&(n->parent_obj))) {
-            trace_nvme_irq_msix(cq->vector);
+            trace_nvme_dev_irq_msix(cq->vector);
              msix_notify(&(n->parent_obj), cq->vector);
          } else {
-            trace_nvme_irq_pin();
+            trace_nvme_dev_irq_pin();
              assert(cq->cqid < 64);
              n->irq_status |= 1 << cq->cqid;
              nvme_irq_check(n);
          }
      } else {
-        trace_nvme_irq_masked();
+        trace_nvme_dev_irq_masked();
      }
  }

[...]

#32 lore raw
In reply to Klaus Jensen
Patchew URL: https://patchew.org/QEMU/[email protected]/

Patchew URL: https://patchew.org/QEMU/[email protected]/

Hi,

This series seems to have some coding style problems. See output below for more information:

Subject: [PATCH 00/16] nvme: refactoring and cleanups
Message-id: [email protected]
Type: series

=== TEST SCRIPT BEGIN ===
#!/bin/bash
git rev-parse base > /dev/null || exit 0
git config --local diff.renamelimit 0
git config --local diff.renames True
git config --local diff.algorithm histogram
./scripts/checkpatch.pl --mailback base..
=== TEST SCRIPT END ===

Updating 3c8cf5a9c21ff8782164d1def7f44bd888713384
From https://github.com/patchew-project/qemu

   2f7cc1f..73995d1  master     -> master
 - [tag update]      patchew/[email protected] -> patchew/[email protected]
 - [tag update]      patchew/[email protected] -> patchew/[email protected]
 - [tag update]      patchew/[email protected] -> patchew/[email protected]
 * [new tag]         patchew/[email protected] -> patchew/[email protected]

Switched to a new branch 'test'
36a0670 nvme: factor out controller identify setup 0eba9ad nvme: factor out cmb setup
5b5feee nvme: factor out pci setup
577bb77 nvme: factor out namespace setup 9ac7fae nvme: add namespace helpers
ab9bbca nvme: factor out block backend setup ba90026 nvme: factor out device state setup b14d6d1 nvme: factor out property/constraint checks 35fc2dc nvme: remove redundant cmbloc/cmbsz members 802a9ab nvme: add max_ioqpairs device parameter acf5b71 nvme: refactor nvme_addr_read
945aa26 nvme: use constants in identify 06aee41 nvme: move device parameters to separate struct d1f279f nvme: remove superfluous breaks e659f34 nvme: rename trace events to nvme_dev f6d960a nvme: fix pci doorbell size calculation

=== OUTPUT BEGIN ===
1/16 Checking commit f6d960adefde (nvme: fix pci doorbell size calculation) 2/16 Checking commit e659f3474c29 (nvme: rename trace events to nvme_dev) 3/16 Checking commit d1f279f37080 (nvme: remove superfluous breaks) 4/16 Checking commit 06aee411cb67 (nvme: move device parameters to separate struct)
ERROR: Macros with complex values should be enclosed in parenthesis #181: FILE: hw/block/nvme.h:6:
+#define DEFINE_NVME_PROPERTIES(_state, _props) \

+    DEFINE_PROP_STRING("serial", _state, _props.serial), \
+    DEFINE_PROP_UINT32("cmb_size_mb", _state, _props.cmb_size_mb, 0), \
+    DEFINE_PROP_UINT32("num_queues", _state, _props.num_queues, 64)

total: 1 errors, 0 warnings, 181 lines checked

Patch 4/16 has style problems, please review. If any of these errors are false positives report them to the maintainer, see CHECKPATCH in MAINTAINERS.

5/16 Checking commit 945aa26e4b39 (nvme: use constants in identify) 6/16 Checking commit acf5b7156c93 (nvme: refactor nvme_addr_read) 7/16 Checking commit 802a9ab0f8c1 (nvme: add max_ioqpairs device parameter) 8/16 Checking commit 35fc2dcb7465 (nvme: remove redundant cmbloc/cmbsz members) 9/16 Checking commit b14d6d1afb3e (nvme: factor out property/constraint checks) 10/16 Checking commit ba9002645e0c (nvme: factor out device state setup) 11/16 Checking commit ab9bbcaa7af5 (nvme: factor out block backend setup) 12/16 Checking commit 9ac7faec3567 (nvme: add namespace helpers) 13/16 Checking commit 577bb7783e47 (nvme: factor out namespace setup) 14/16 Checking commit 5b5feee08d6d (nvme: factor out pci setup) 15/16 Checking commit 0eba9ade7b81 (nvme: factor out cmb setup) 16/16 Checking commit 36a0670099c1 (nvme: factor out controller identify setup) === OUTPUT END ===

Test command exited with code: 1

The full log is available at
http://patchew.org/logs/[email protected]/testing.checkpatch/?type=message.
---
Email generated automatically by Patchew [https://patchew.org/].
Please send your feedback to [email protected]