* [PATCH v2 01/20] nvme: remove superfluous breaks
2019-10-15 10:38 [PATCH v2 00/20] nvme: support NVMe v1.3d, SGLs and multiple namespaces Klaus Jensen
@ 2019-10-15 10:38 ` Klaus Jensen
2019-10-15 10:38 ` [PATCH v2 02/20] nvme: move device parameters to separate struct Klaus Jensen
` (22 subsequent siblings)
23 siblings, 0 replies; 52+ messages in thread
From: Klaus Jensen @ 2019-10-15 10:38 UTC (permalink / raw)
To: qemu-block
Cc: Kevin Wolf, Fam Zheng, Javier Gonzalez, qemu-devel, Max Reitz,
Keith Busch, Paul Durrant, Stephen Bates
These break statements was left over when commit 3036a626e9ef ("nvme:
add Get/Set Feature Timestamp support") was merged.
Signed-off-by: Klaus Jensen <k.jensen@samsung.com>
---
hw/block/nvme.c | 4 ----
1 file changed, 4 deletions(-)
diff --git a/hw/block/nvme.c b/hw/block/nvme.c
index 12d825425016..c06e3ca31905 100644
--- a/hw/block/nvme.c
+++ b/hw/block/nvme.c
@@ -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_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_err_invalid_setfeat(dw10);
return NVME_INVALID_FIELD | NVME_DNR;
--
2.23.0
^ permalink raw reply related [flat|nested] 52+ messages in thread* [PATCH v2 02/20] nvme: move device parameters to separate struct
2019-10-15 10:38 [PATCH v2 00/20] nvme: support NVMe v1.3d, SGLs and multiple namespaces Klaus Jensen
2019-10-15 10:38 ` [PATCH v2 01/20] nvme: remove superfluous breaks Klaus Jensen
@ 2019-10-15 10:38 ` Klaus Jensen
2019-10-15 10:38 ` [PATCH v2 03/20] nvme: add missing fields in the identify controller data structure Klaus Jensen
` (21 subsequent siblings)
23 siblings, 0 replies; 52+ messages in thread
From: Klaus Jensen @ 2019-10-15 10:38 UTC (permalink / raw)
To: qemu-block
Cc: Kevin Wolf, Fam Zheng, Javier Gonzalez, qemu-devel, Max Reitz,
Keith Busch, Paul Durrant, Stephen Bates
Move device configuration parameters to separate struct to make it
explicit what is configurable and what is set internally.
Signed-off-by: Klaus Jensen <klaus.jensen@cnexlabs.com>
---
hw/block/nvme.c | 44 ++++++++++++++++++++++----------------------
hw/block/nvme.h | 16 +++++++++++++---
2 files changed, 35 insertions(+), 25 deletions(-)
diff --git a/hw/block/nvme.c b/hw/block/nvme.c
index c06e3ca31905..277700fdcc58 100644
--- a/hw/block/nvme.c
+++ b/hw/block/nvme.c
@@ -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_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_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_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_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_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);
}
@@ -1308,7 +1310,7 @@ 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;
}
@@ -1324,7 +1326,7 @@ 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;
}
@@ -1341,25 +1343,25 @@ static void nvme_realize(PCIDevice *pci_dev, Error **errp)
pcie_endpoint_cap_init(pci_dev, 0x80);
n->num_namespaces = 1;
- n->reg_size = pow2ceil(0x1004 + 2 * (n->num_queues + 1) * 4);
+ n->reg_size = pow2ceil(0x1004 + 2 * (n->params.num_queues + 1) * 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;
@@ -1388,7 +1390,7 @@ 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);
@@ -1399,7 +1401,7 @@ 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;
@@ -1438,7 +1440,7 @@ 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);
@@ -1446,9 +1448,7 @@ 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(),
};
diff --git a/hw/block/nvme.h b/hw/block/nvme.h
index 557194ee1954..9957c4a200e2 100644
--- a/hw/block/nvme.h
+++ b/hw/block/nvme.h
@@ -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;
--
2.23.0
^ permalink raw reply related [flat|nested] 52+ messages in thread* [PATCH v2 03/20] nvme: add missing fields in the identify controller data structure
2019-10-15 10:38 [PATCH v2 00/20] nvme: support NVMe v1.3d, SGLs and multiple namespaces Klaus Jensen
2019-10-15 10:38 ` [PATCH v2 01/20] nvme: remove superfluous breaks Klaus Jensen
2019-10-15 10:38 ` [PATCH v2 02/20] nvme: move device parameters to separate struct Klaus Jensen
@ 2019-10-15 10:38 ` Klaus Jensen
2019-10-15 10:38 ` [PATCH v2 04/20] nvme: populate the mandatory subnqn and ver fields Klaus Jensen
` (20 subsequent siblings)
23 siblings, 0 replies; 52+ messages in thread
From: Klaus Jensen @ 2019-10-15 10:38 UTC (permalink / raw)
To: qemu-block
Cc: Kevin Wolf, Fam Zheng, Javier Gonzalez, qemu-devel, Max Reitz,
Keith Busch, Paul Durrant, Stephen Bates
Not used by the device model but added for completeness. See NVM Express
1.2.1, Section 5.11 ("Identify command"), Figure 90.
Signed-off-by: Klaus Jensen <klaus.jensen@cnexlabs.com>
---
include/block/nvme.h | 34 +++++++++++++++++++++++++++++-----
1 file changed, 29 insertions(+), 5 deletions(-)
diff --git a/include/block/nvme.h b/include/block/nvme.h
index 3ec8efcc435e..1b0accd4fe2b 100644
--- a/include/block/nvme.h
+++ b/include/block/nvme.h
@@ -543,7 +543,13 @@ typedef struct NvmeIdCtrl {
uint8_t ieee[3];
uint8_t cmic;
uint8_t mdts;
- uint8_t rsvd255[178];
+ uint16_t cntlid;
+ uint32_t ver;
+ uint16_t rtd3r;
+ uint32_t rtd3e;
+ uint32_t oaes;
+ uint32_t ctratt;
+ uint8_t rsvd255[156];
uint16_t oacs;
uint8_t acl;
uint8_t aerl;
@@ -551,10 +557,22 @@ typedef struct NvmeIdCtrl {
uint8_t lpa;
uint8_t elpe;
uint8_t npss;
- uint8_t rsvd511[248];
+ uint8_t avscc;
+ uint8_t apsta;
+ uint16_t wctemp;
+ uint16_t cctemp;
+ uint16_t mtfa;
+ uint32_t hmpre;
+ uint32_t hmmin;
+ uint8_t tnvmcap[16];
+ uint8_t unvmcap[16];
+ uint32_t rpmbs;
+ uint8_t rsvd319[4];
+ uint16_t kas;
+ uint8_t rsvd511[190];
uint8_t sqes;
uint8_t cqes;
- uint16_t rsvd515;
+ uint16_t maxcmd;
uint32_t nn;
uint16_t oncs;
uint16_t fuses;
@@ -562,8 +580,14 @@ typedef struct NvmeIdCtrl {
uint8_t vwc;
uint16_t awun;
uint16_t awupf;
- uint8_t rsvd703[174];
- uint8_t rsvd2047[1344];
+ uint8_t nvscc;
+ uint8_t rsvd531;
+ uint16_t acwu;
+ uint16_t rsvd535;
+ uint32_t sgls;
+ uint8_t rsvd767[228];
+ uint8_t subnqn[256];
+ uint8_t rsvd2047[1024];
NvmePSD psd[32];
uint8_t vs[1024];
} NvmeIdCtrl;
--
2.23.0
^ permalink raw reply related [flat|nested] 52+ messages in thread* [PATCH v2 04/20] nvme: populate the mandatory subnqn and ver fields
2019-10-15 10:38 [PATCH v2 00/20] nvme: support NVMe v1.3d, SGLs and multiple namespaces Klaus Jensen
` (2 preceding siblings ...)
2019-10-15 10:38 ` [PATCH v2 03/20] nvme: add missing fields in the identify controller data structure Klaus Jensen
@ 2019-10-15 10:38 ` Klaus Jensen
2019-11-12 15:04 ` Beata Michalska
2019-10-15 10:38 ` [PATCH v2 05/20] nvme: allow completion queues in the cmb Klaus Jensen
` (19 subsequent siblings)
23 siblings, 1 reply; 52+ messages in thread
From: Klaus Jensen @ 2019-10-15 10:38 UTC (permalink / raw)
To: qemu-block
Cc: Kevin Wolf, Fam Zheng, Javier Gonzalez, qemu-devel, Max Reitz,
Keith Busch, Paul Durrant, Stephen Bates
Required for compliance with NVMe revision 1.2.1 or later. See NVM
Express 1.2.1, Section 5.11 ("Identify command"), Figure 90 and Section
7.9 ("NVMe Qualified Names").
This also bumps the supported version to 1.2.1.
Signed-off-by: Klaus Jensen <klaus.jensen@cnexlabs.com>
---
hw/block/nvme.c | 11 ++++++++---
1 file changed, 8 insertions(+), 3 deletions(-)
diff --git a/hw/block/nvme.c b/hw/block/nvme.c
index 277700fdcc58..16f0fba10b08 100644
--- a/hw/block/nvme.c
+++ b/hw/block/nvme.c
@@ -9,9 +9,9 @@
*/
/**
- * Reference Specs: http://www.nvmexpress.org, 1.2, 1.1, 1.0e
+ * Reference Specification: NVM Express 1.2.1
*
- * http://www.nvmexpress.org/resources/
+ * https://nvmexpress.org/resources/specifications/
*/
/**
@@ -1366,6 +1366,7 @@ static void nvme_realize(PCIDevice *pci_dev, Error **errp)
id->ieee[0] = 0x00;
id->ieee[1] = 0x02;
id->ieee[2] = 0xb3;
+ id->ver = cpu_to_le32(0x00010201);
id->oacs = cpu_to_le16(0);
id->frmw = 7 << 1;
id->lpa = 1 << 0;
@@ -1373,6 +1374,10 @@ static void nvme_realize(PCIDevice *pci_dev, Error **errp)
id->cqes = (0x4 << 4) | 0x4;
id->nn = cpu_to_le32(n->num_namespaces);
id->oncs = cpu_to_le16(NVME_ONCS_WRITE_ZEROS | NVME_ONCS_TIMESTAMP);
+
+ strcpy((char *) id->subnqn, "nqn.2019-08.org.qemu:");
+ pstrcat((char *) id->subnqn, sizeof(id->subnqn), n->params.serial);
+
id->psd[0].mp = cpu_to_le16(0x9c4);
id->psd[0].enlat = cpu_to_le32(0x10);
id->psd[0].exlat = cpu_to_le32(0x4);
@@ -1387,7 +1392,7 @@ static void nvme_realize(PCIDevice *pci_dev, Error **errp)
NVME_CAP_SET_CSS(n->bar.cap, 1);
NVME_CAP_SET_MPSMAX(n->bar.cap, 4);
- n->bar.vs = 0x00010200;
+ n->bar.vs = 0x00010201;
n->bar.intmc = n->bar.intms = 0;
if (n->params.cmb_size_mb) {
--
2.23.0
^ permalink raw reply related [flat|nested] 52+ messages in thread* Re: [PATCH v2 04/20] nvme: populate the mandatory subnqn and ver fields
2019-10-15 10:38 ` [PATCH v2 04/20] nvme: populate the mandatory subnqn and ver fields Klaus Jensen
@ 2019-11-12 15:04 ` Beata Michalska
2019-11-13 6:16 ` Klaus Birkelund
0 siblings, 1 reply; 52+ messages in thread
From: Beata Michalska @ 2019-11-12 15:04 UTC (permalink / raw)
To: Klaus Jensen
Cc: Kevin Wolf, Fam Zheng, Javier Gonzalez, qemu-block, qemu-devel,
Max Reitz, Keith Busch, Paul Durrant, Stephen Bates
Hi Klaus
On Tue, 15 Oct 2019 at 11:42, Klaus Jensen <its@irrelevant.dk> wrote:
>
> Required for compliance with NVMe revision 1.2.1 or later. See NVM
> Express 1.2.1, Section 5.11 ("Identify command"), Figure 90 and Section
> 7.9 ("NVMe Qualified Names").
>
> This also bumps the supported version to 1.2.1.
>
> Signed-off-by: Klaus Jensen <klaus.jensen@cnexlabs.com>
> ---
> hw/block/nvme.c | 11 ++++++++---
> 1 file changed, 8 insertions(+), 3 deletions(-)
>
> diff --git a/hw/block/nvme.c b/hw/block/nvme.c
> index 277700fdcc58..16f0fba10b08 100644
> --- a/hw/block/nvme.c
> +++ b/hw/block/nvme.c
> @@ -9,9 +9,9 @@
> */
>
> /**
> - * Reference Specs: http://www.nvmexpress.org, 1.2, 1.1, 1.0e
> + * Reference Specification: NVM Express 1.2.1
> *
> - * http://www.nvmexpress.org/resources/
> + * https://nvmexpress.org/resources/specifications/
> */
>
> /**
> @@ -1366,6 +1366,7 @@ static void nvme_realize(PCIDevice *pci_dev, Error **errp)
> id->ieee[0] = 0x00;
> id->ieee[1] = 0x02;
> id->ieee[2] = 0xb3;
> + id->ver = cpu_to_le32(0x00010201);
> id->oacs = cpu_to_le16(0);
> id->frmw = 7 << 1;
> id->lpa = 1 << 0;
> @@ -1373,6 +1374,10 @@ static void nvme_realize(PCIDevice *pci_dev, Error **errp)
> id->cqes = (0x4 << 4) | 0x4;
> id->nn = cpu_to_le32(n->num_namespaces);
> id->oncs = cpu_to_le16(NVME_ONCS_WRITE_ZEROS | NVME_ONCS_TIMESTAMP);
> +
> + strcpy((char *) id->subnqn, "nqn.2019-08.org.qemu:");
> + pstrcat((char *) id->subnqn, sizeof(id->subnqn), n->params.serial);
> +
> id->psd[0].mp = cpu_to_le16(0x9c4);
> id->psd[0].enlat = cpu_to_le32(0x10);
> id->psd[0].exlat = cpu_to_le32(0x4);
> @@ -1387,7 +1392,7 @@ static void nvme_realize(PCIDevice *pci_dev, Error **errp)
> NVME_CAP_SET_CSS(n->bar.cap, 1);
> NVME_CAP_SET_MPSMAX(n->bar.cap, 4);
>
> - n->bar.vs = 0x00010200;
> + n->bar.vs = 0x00010201;
Very minor:
The version number is being set twice in the patch series already.
And it is being set in two places.
It might be worth to make a #define out of it so that only one
needs to be changed.
BR
Beata
> n->bar.intmc = n->bar.intms = 0;
>
> if (n->params.cmb_size_mb) {
> --
> 2.23.0
>
>
^ permalink raw reply [flat|nested] 52+ messages in thread* Re: [PATCH v2 04/20] nvme: populate the mandatory subnqn and ver fields
2019-11-12 15:04 ` Beata Michalska
@ 2019-11-13 6:16 ` Klaus Birkelund
0 siblings, 0 replies; 52+ messages in thread
From: Klaus Birkelund @ 2019-11-13 6:16 UTC (permalink / raw)
To: Beata Michalska
Cc: Kevin Wolf, Fam Zheng, qemu-block, qemu-devel, Max Reitz,
Keith Busch, Paul Durrant
On Tue, Nov 12, 2019 at 03:04:45PM +0000, Beata Michalska wrote:
> Hi Klaus
>
> On Tue, 15 Oct 2019 at 11:42, Klaus Jensen <its@irrelevant.dk> wrote:
> > + n->bar.vs = 0x00010201;
>
> Very minor:
>
> The version number is being set twice in the patch series already.
> And it is being set in two places.
> It might be worth to make a #define out of it so that only one
> needs to be changed.
>
I think you are right. I'll do that.
^ permalink raw reply [flat|nested] 52+ messages in thread
* [PATCH v2 05/20] nvme: allow completion queues in the cmb
2019-10-15 10:38 [PATCH v2 00/20] nvme: support NVMe v1.3d, SGLs and multiple namespaces Klaus Jensen
` (3 preceding siblings ...)
2019-10-15 10:38 ` [PATCH v2 04/20] nvme: populate the mandatory subnqn and ver fields Klaus Jensen
@ 2019-10-15 10:38 ` Klaus Jensen
2019-10-15 10:38 ` [PATCH v2 06/20] nvme: add support for the abort command Klaus Jensen
` (18 subsequent siblings)
23 siblings, 0 replies; 52+ messages in thread
From: Klaus Jensen @ 2019-10-15 10:38 UTC (permalink / raw)
To: qemu-block
Cc: Kevin Wolf, Fam Zheng, Javier Gonzalez, qemu-devel, Max Reitz,
Keith Busch, Paul Durrant, Stephen Bates
Allow completion queues in the controller memory buffer.
This also inlines the nvme_addr_{read,write} functions and adds an
nvme_addr_is_cmb helper.
Signed-off-by: Klaus Jensen <klaus.jensen@cnexlabs.com>
---
hw/block/nvme.c | 38 +++++++++++++++++++++++++++++---------
1 file changed, 29 insertions(+), 9 deletions(-)
diff --git a/hw/block/nvme.c b/hw/block/nvme.c
index 16f0fba10b08..daa2367b0863 100644
--- a/hw/block/nvme.c
+++ b/hw/block/nvme.c
@@ -52,14 +52,34 @@
static void nvme_process_sq(void *opaque);
-static void nvme_addr_read(NvmeCtrl *n, hwaddr addr, void *buf, int size)
+static inline bool nvme_addr_is_cmb(NvmeCtrl *n, hwaddr addr)
{
- if (n->cmbsz && addr >= n->ctrl_mem.addr &&
- addr < (n->ctrl_mem.addr + int128_get64(n->ctrl_mem.size))) {
- memcpy(buf, (void *)&n->cmbuf[addr - n->ctrl_mem.addr], size);
- } else {
- pci_dma_read(&n->parent_obj, addr, buf, size);
+ hwaddr low = n->ctrl_mem.addr;
+ hwaddr hi = n->ctrl_mem.addr + int128_get64(n->ctrl_mem.size);
+
+ return addr >= low && addr < hi;
+}
+
+static inline void nvme_addr_read(NvmeCtrl *n, hwaddr addr, void *buf,
+ int size)
+{
+ if (n->cmbsz && nvme_addr_is_cmb(n, addr)) {
+ memcpy(buf, (void *) &n->cmbuf[addr - n->ctrl_mem.addr], size);
+ return;
}
+
+ pci_dma_read(&n->parent_obj, addr, buf, size);
+}
+
+static inline void nvme_addr_write(NvmeCtrl *n, hwaddr addr, void *buf,
+ int size)
+{
+ if (n->cmbsz && nvme_addr_is_cmb(n, addr)) {
+ memcpy((void *) &n->cmbuf[addr - n->ctrl_mem.addr], buf, size);
+ return;
+ }
+
+ pci_dma_write(&n->parent_obj, addr, buf, size);
}
static int nvme_check_sqid(NvmeCtrl *n, uint16_t sqid)
@@ -281,6 +301,7 @@ static void nvme_post_cqes(void *opaque)
QTAILQ_FOREACH_SAFE(req, &cq->req_list, entry, next) {
NvmeSQueue *sq;
+ NvmeCqe *cqe = &req->cqe;
hwaddr addr;
if (nvme_cq_full(cq)) {
@@ -294,8 +315,7 @@ static void nvme_post_cqes(void *opaque)
req->cqe.sq_head = cpu_to_le16(sq->head);
addr = cq->dma_addr + cq->tail * n->cqe_size;
nvme_inc_cq_tail(cq);
- pci_dma_write(&n->parent_obj, addr, (void *)&req->cqe,
- sizeof(req->cqe));
+ nvme_addr_write(n, addr, (void *) cqe, sizeof(*cqe));
QTAILQ_INSERT_TAIL(&sq->req_list, req, entry);
}
if (cq->tail != cq->head) {
@@ -1401,7 +1421,7 @@ static void nvme_realize(PCIDevice *pci_dev, Error **errp)
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_CQS(n->bar.cmbsz, 1);
NVME_CMBSZ_SET_LISTS(n->bar.cmbsz, 0);
NVME_CMBSZ_SET_RDS(n->bar.cmbsz, 1);
NVME_CMBSZ_SET_WDS(n->bar.cmbsz, 1);
--
2.23.0
^ permalink raw reply related [flat|nested] 52+ messages in thread* [PATCH v2 06/20] nvme: add support for the abort command
2019-10-15 10:38 [PATCH v2 00/20] nvme: support NVMe v1.3d, SGLs and multiple namespaces Klaus Jensen
` (4 preceding siblings ...)
2019-10-15 10:38 ` [PATCH v2 05/20] nvme: allow completion queues in the cmb Klaus Jensen
@ 2019-10-15 10:38 ` Klaus Jensen
2019-11-12 15:04 ` Beata Michalska
2019-10-15 10:38 ` [PATCH v2 07/20] nvme: refactor device realization Klaus Jensen
` (17 subsequent siblings)
23 siblings, 1 reply; 52+ messages in thread
From: Klaus Jensen @ 2019-10-15 10:38 UTC (permalink / raw)
To: qemu-block
Cc: Kevin Wolf, Fam Zheng, Javier Gonzalez, qemu-devel, Max Reitz,
Keith Busch, Paul Durrant, Stephen Bates
Required for compliance with NVMe revision 1.2.1. See NVM Express 1.2.1,
Section 5.1 ("Abort command").
The Abort command is a best effort command; for now, the device always
fails to abort the given command.
Signed-off-by: Klaus Jensen <klaus.jensen@cnexlabs.com>
---
hw/block/nvme.c | 16 ++++++++++++++++
1 file changed, 16 insertions(+)
diff --git a/hw/block/nvme.c b/hw/block/nvme.c
index daa2367b0863..84e4f2ea7a15 100644
--- a/hw/block/nvme.c
+++ b/hw/block/nvme.c
@@ -741,6 +741,18 @@ static uint16_t nvme_identify(NvmeCtrl *n, NvmeCmd *cmd)
}
}
+static uint16_t nvme_abort(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
+{
+ uint16_t sqid = le32_to_cpu(cmd->cdw10) & 0xffff;
+
+ req->cqe.result = 1;
+ if (nvme_check_sqid(n, sqid)) {
+ return NVME_INVALID_FIELD | NVME_DNR;
+ }
+
+ return NVME_SUCCESS;
+}
+
static inline void nvme_set_timestamp(NvmeCtrl *n, uint64_t ts)
{
trace_nvme_setfeat_timestamp(ts);
@@ -859,6 +871,7 @@ static uint16_t nvme_set_feature(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
trace_nvme_err_invalid_setfeat(dw10);
return NVME_INVALID_FIELD | NVME_DNR;
}
+
return NVME_SUCCESS;
}
@@ -875,6 +888,8 @@ static uint16_t nvme_admin_cmd(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
return nvme_create_cq(n, cmd);
case NVME_ADM_CMD_IDENTIFY:
return nvme_identify(n, cmd);
+ case NVME_ADM_CMD_ABORT:
+ return nvme_abort(n, cmd, req);
case NVME_ADM_CMD_SET_FEATURES:
return nvme_set_feature(n, cmd, req);
case NVME_ADM_CMD_GET_FEATURES:
@@ -1388,6 +1403,7 @@ static void nvme_realize(PCIDevice *pci_dev, Error **errp)
id->ieee[2] = 0xb3;
id->ver = cpu_to_le32(0x00010201);
id->oacs = cpu_to_le16(0);
+ id->acl = 3;
id->frmw = 7 << 1;
id->lpa = 1 << 0;
id->sqes = (0x6 << 4) | 0x6;
--
2.23.0
^ permalink raw reply related [flat|nested] 52+ messages in thread* Re: [PATCH v2 06/20] nvme: add support for the abort command
2019-10-15 10:38 ` [PATCH v2 06/20] nvme: add support for the abort command Klaus Jensen
@ 2019-11-12 15:04 ` Beata Michalska
2019-11-13 6:12 ` Klaus Birkelund
0 siblings, 1 reply; 52+ messages in thread
From: Beata Michalska @ 2019-11-12 15:04 UTC (permalink / raw)
To: Klaus Jensen
Cc: Kevin Wolf, Fam Zheng, Javier Gonzalez, qemu-block, qemu-devel,
Max Reitz, Keith Busch, Paul Durrant, Stephen Bates
Hi Klaus
On Tue, 15 Oct 2019 at 11:41, Klaus Jensen <its@irrelevant.dk> wrote:
>
> Required for compliance with NVMe revision 1.2.1. See NVM Express 1.2.1,
> Section 5.1 ("Abort command").
>
> The Abort command is a best effort command; for now, the device always
> fails to abort the given command.
>
> Signed-off-by: Klaus Jensen <klaus.jensen@cnexlabs.com>
> ---
> hw/block/nvme.c | 16 ++++++++++++++++
> 1 file changed, 16 insertions(+)
>
> diff --git a/hw/block/nvme.c b/hw/block/nvme.c
> index daa2367b0863..84e4f2ea7a15 100644
> --- a/hw/block/nvme.c
> +++ b/hw/block/nvme.c
> @@ -741,6 +741,18 @@ static uint16_t nvme_identify(NvmeCtrl *n, NvmeCmd *cmd)
> }
> }
>
> +static uint16_t nvme_abort(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
> +{
> + uint16_t sqid = le32_to_cpu(cmd->cdw10) & 0xffff;
> +
> + req->cqe.result = 1;
> + if (nvme_check_sqid(n, sqid)) {
> + return NVME_INVALID_FIELD | NVME_DNR;
> + }
> +
Shouldn't we validate the CID as well ?
> + return NVME_SUCCESS;
> +}
> +
> static inline void nvme_set_timestamp(NvmeCtrl *n, uint64_t ts)
> {
> trace_nvme_setfeat_timestamp(ts);
> @@ -859,6 +871,7 @@ static uint16_t nvme_set_feature(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
> trace_nvme_err_invalid_setfeat(dw10);
> return NVME_INVALID_FIELD | NVME_DNR;
> }
> +
> return NVME_SUCCESS;
> }
>
> @@ -875,6 +888,8 @@ static uint16_t nvme_admin_cmd(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
> return nvme_create_cq(n, cmd);
> case NVME_ADM_CMD_IDENTIFY:
> return nvme_identify(n, cmd);
> + case NVME_ADM_CMD_ABORT:
> + return nvme_abort(n, cmd, req);
> case NVME_ADM_CMD_SET_FEATURES:
> return nvme_set_feature(n, cmd, req);
> case NVME_ADM_CMD_GET_FEATURES:
> @@ -1388,6 +1403,7 @@ static void nvme_realize(PCIDevice *pci_dev, Error **errp)
> id->ieee[2] = 0xb3;
> id->ver = cpu_to_le32(0x00010201);
> id->oacs = cpu_to_le16(0);
> + id->acl = 3;
So we are setting the max number of concurrent commands
but there is no logic to enforce that and wrap up with the
status suggested by specification.
BR
Beata
> id->frmw = 7 << 1;
> id->lpa = 1 << 0;
> id->sqes = (0x6 << 4) | 0x6;
> --
> 2.23.0
>
>
^ permalink raw reply [flat|nested] 52+ messages in thread* Re: [PATCH v2 06/20] nvme: add support for the abort command
2019-11-12 15:04 ` Beata Michalska
@ 2019-11-13 6:12 ` Klaus Birkelund
2019-11-15 11:56 ` Beata Michalska
0 siblings, 1 reply; 52+ messages in thread
From: Klaus Birkelund @ 2019-11-13 6:12 UTC (permalink / raw)
To: Beata Michalska
Cc: Kevin Wolf, Fam Zheng, Javier Gonzalez, qemu-block, qemu-devel,
Max Reitz, Keith Busch, Paul Durrant, Stephen Bates
On Tue, Nov 12, 2019 at 03:04:38PM +0000, Beata Michalska wrote:
> Hi Klaus
>
Hi Beata,
Thank you very much for your thorough reviews! I'll start going through
them one by one :) You might have seen that I've posted a v3, but I will
make sure to consolidate between v2 and v3!
> On Tue, 15 Oct 2019 at 11:41, Klaus Jensen <its@irrelevant.dk> wrote:
> >
> > Required for compliance with NVMe revision 1.2.1. See NVM Express 1.2.1,
> > Section 5.1 ("Abort command").
> >
> > The Abort command is a best effort command; for now, the device always
> > fails to abort the given command.
> >
> > Signed-off-by: Klaus Jensen <klaus.jensen@cnexlabs.com>
> > ---
> > hw/block/nvme.c | 16 ++++++++++++++++
> > 1 file changed, 16 insertions(+)
> >
> > diff --git a/hw/block/nvme.c b/hw/block/nvme.c
> > index daa2367b0863..84e4f2ea7a15 100644
> > --- a/hw/block/nvme.c
> > +++ b/hw/block/nvme.c
> > @@ -741,6 +741,18 @@ static uint16_t nvme_identify(NvmeCtrl *n, NvmeCmd *cmd)
> > }
> > }
> >
> > +static uint16_t nvme_abort(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
> > +{
> > + uint16_t sqid = le32_to_cpu(cmd->cdw10) & 0xffff;
> > +
> > + req->cqe.result = 1;
> > + if (nvme_check_sqid(n, sqid)) {
> > + return NVME_INVALID_FIELD | NVME_DNR;
> > + }
> > +
> Shouldn't we validate the CID as well ?
>
According to the specification it is "implementation specific if/when a
controller chooses to complete the command when the command to abort is
not found".
I'm interpreting this to mean that, yes, an invalid command identifier
could be given in the command, but this implementation does not care
about that.
I still think the controller should check the validity of the submission
queue identifier though. It is a general invariant that the sqid should
be valid.
> > + return NVME_SUCCESS;
> > +}
> > +
> > static inline void nvme_set_timestamp(NvmeCtrl *n, uint64_t ts)
> > {
> > trace_nvme_setfeat_timestamp(ts);
> > @@ -859,6 +871,7 @@ static uint16_t nvme_set_feature(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
> > trace_nvme_err_invalid_setfeat(dw10);
> > return NVME_INVALID_FIELD | NVME_DNR;
> > }
> > +
> > return NVME_SUCCESS;
> > }
> >
> > @@ -875,6 +888,8 @@ static uint16_t nvme_admin_cmd(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
> > return nvme_create_cq(n, cmd);
> > case NVME_ADM_CMD_IDENTIFY:
> > return nvme_identify(n, cmd);
> > + case NVME_ADM_CMD_ABORT:
> > + return nvme_abort(n, cmd, req);
> > case NVME_ADM_CMD_SET_FEATURES:
> > return nvme_set_feature(n, cmd, req);
> > case NVME_ADM_CMD_GET_FEATURES:
> > @@ -1388,6 +1403,7 @@ static void nvme_realize(PCIDevice *pci_dev, Error **errp)
> > id->ieee[2] = 0xb3;
> > id->ver = cpu_to_le32(0x00010201);
> > id->oacs = cpu_to_le16(0);
> > + id->acl = 3;
> So we are setting the max number of concurrent commands
> but there is no logic to enforce that and wrap up with the
> status suggested by specification.
>
That is true, but because the controller always completes the Abort
command immediately this cannot happen. If the controller did try to
abort executing commands, the Abort command would need to linger in the
controller state until a completion queue entry is posted for the
command to be aborted before the completion queue entry can be posted
for the Abort command. This takes up resources in the controller and is
the reason for the Abort Command Limit.
You could argue that we should set ACL to 0 then, but the specification
recommends a value of 3 and I do not see any harm in conveying a
"reasonable", though inconsequential, value.
^ permalink raw reply [flat|nested] 52+ messages in thread* Re: [PATCH v2 06/20] nvme: add support for the abort command
2019-11-13 6:12 ` Klaus Birkelund
@ 2019-11-15 11:56 ` Beata Michalska
2019-11-18 8:49 ` Klaus Birkelund
0 siblings, 1 reply; 52+ messages in thread
From: Beata Michalska @ 2019-11-15 11:56 UTC (permalink / raw)
To: Klaus Birkelund
Cc: Kevin Wolf, Fam Zheng, Javier Gonzalez, qemu-block, qemu-devel,
Max Reitz, Keith Busch, Paul Durrant, Stephen Bates
Hi Klaus,
On Wed, 13 Nov 2019 at 06:12, Klaus Birkelund <its@irrelevant.dk> wrote:
>
> On Tue, Nov 12, 2019 at 03:04:38PM +0000, Beata Michalska wrote:
> > Hi Klaus
> >
>
> Hi Beata,
>
> Thank you very much for your thorough reviews! I'll start going through
> them one by one :) You might have seen that I've posted a v3, but I will
> make sure to consolidate between v2 and v3!
>
> > On Tue, 15 Oct 2019 at 11:41, Klaus Jensen <its@irrelevant.dk> wrote:
> > >
> > > Required for compliance with NVMe revision 1.2.1. See NVM Express 1.2.1,
> > > Section 5.1 ("Abort command").
> > >
> > > The Abort command is a best effort command; for now, the device always
> > > fails to abort the given command.
> > >
> > > Signed-off-by: Klaus Jensen <klaus.jensen@cnexlabs.com>
> > > ---
> > > hw/block/nvme.c | 16 ++++++++++++++++
> > > 1 file changed, 16 insertions(+)
> > >
> > > diff --git a/hw/block/nvme.c b/hw/block/nvme.c
> > > index daa2367b0863..84e4f2ea7a15 100644
> > > --- a/hw/block/nvme.c
> > > +++ b/hw/block/nvme.c
> > > @@ -741,6 +741,18 @@ static uint16_t nvme_identify(NvmeCtrl *n, NvmeCmd *cmd)
> > > }
> > > }
> > >
> > > +static uint16_t nvme_abort(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
> > > +{
> > > + uint16_t sqid = le32_to_cpu(cmd->cdw10) & 0xffff;
> > > +
> > > + req->cqe.result = 1;
> > > + if (nvme_check_sqid(n, sqid)) {
> > > + return NVME_INVALID_FIELD | NVME_DNR;
> > > + }
> > > +
> > Shouldn't we validate the CID as well ?
> >
>
> According to the specification it is "implementation specific if/when a
> controller chooses to complete the command when the command to abort is
> not found".
>
> I'm interpreting this to mean that, yes, an invalid command identifier
> could be given in the command, but this implementation does not care
> about that.
>
> I still think the controller should check the validity of the submission
> queue identifier though. It is a general invariant that the sqid should
> be valid.
>
> > > + return NVME_SUCCESS;
> > > +}
> > > +
> > > static inline void nvme_set_timestamp(NvmeCtrl *n, uint64_t ts)
> > > {
> > > trace_nvme_setfeat_timestamp(ts);
> > > @@ -859,6 +871,7 @@ static uint16_t nvme_set_feature(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
> > > trace_nvme_err_invalid_setfeat(dw10);
> > > return NVME_INVALID_FIELD | NVME_DNR;
> > > }
> > > +
> > > return NVME_SUCCESS;
> > > }
> > >
> > > @@ -875,6 +888,8 @@ static uint16_t nvme_admin_cmd(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
> > > return nvme_create_cq(n, cmd);
> > > case NVME_ADM_CMD_IDENTIFY:
> > > return nvme_identify(n, cmd);
> > > + case NVME_ADM_CMD_ABORT:
> > > + return nvme_abort(n, cmd, req);
> > > case NVME_ADM_CMD_SET_FEATURES:
> > > return nvme_set_feature(n, cmd, req);
> > > case NVME_ADM_CMD_GET_FEATURES:
> > > @@ -1388,6 +1403,7 @@ static void nvme_realize(PCIDevice *pci_dev, Error **errp)
> > > id->ieee[2] = 0xb3;
> > > id->ver = cpu_to_le32(0x00010201);
> > > id->oacs = cpu_to_le16(0);
> > > + id->acl = 3;
> > So we are setting the max number of concurrent commands
> > but there is no logic to enforce that and wrap up with the
> > status suggested by specification.
> >
>
> That is true, but because the controller always completes the Abort
> command immediately this cannot happen. If the controller did try to
> abort executing commands, the Abort command would need to linger in the
> controller state until a completion queue entry is posted for the
> command to be aborted before the completion queue entry can be posted
> for the Abort command. This takes up resources in the controller and is
> the reason for the Abort Command Limit.
>
> You could argue that we should set ACL to 0 then, but the specification
> recommends a value of 3 and I do not see any harm in conveying a
> "reasonable", though inconsequential, value.
Could we potentially add some comment describing the above ?
BR
Beata
^ permalink raw reply [flat|nested] 52+ messages in thread* Re: [PATCH v2 06/20] nvme: add support for the abort command
2019-11-15 11:56 ` Beata Michalska
@ 2019-11-18 8:49 ` Klaus Birkelund
0 siblings, 0 replies; 52+ messages in thread
From: Klaus Birkelund @ 2019-11-18 8:49 UTC (permalink / raw)
To: Beata Michalska
Cc: Kevin Wolf, Fam Zheng, qemu-block, qemu-devel, Max Reitz,
Keith Busch, Paul Durrant
On Fri, Nov 15, 2019 at 11:56:00AM +0000, Beata Michalska wrote:
> Hi Klaus,
>
> On Wed, 13 Nov 2019 at 06:12, Klaus Birkelund <its@irrelevant.dk> wrote:
> >
> > On Tue, Nov 12, 2019 at 03:04:38PM +0000, Beata Michalska wrote:
> > > Hi Klaus
> > >
> >
> > Hi Beata,
> >
> > Thank you very much for your thorough reviews! I'll start going through
> > them one by one :) You might have seen that I've posted a v3, but I will
> > make sure to consolidate between v2 and v3!
> >
> > > On Tue, 15 Oct 2019 at 11:41, Klaus Jensen <its@irrelevant.dk> wrote:
> > > >
> > > > Required for compliance with NVMe revision 1.2.1. See NVM Express 1.2.1,
> > > > Section 5.1 ("Abort command").
> > > >
> > > > The Abort command is a best effort command; for now, the device always
> > > > fails to abort the given command.
> > > >
> > > > Signed-off-by: Klaus Jensen <klaus.jensen@cnexlabs.com>
> > > > ---
> > > > hw/block/nvme.c | 16 ++++++++++++++++
> > > > 1 file changed, 16 insertions(+)
> > > >
> > > > diff --git a/hw/block/nvme.c b/hw/block/nvme.c
> > > > index daa2367b0863..84e4f2ea7a15 100644
> > > > --- a/hw/block/nvme.c
> > > > +++ b/hw/block/nvme.c
> > > > @@ -741,6 +741,18 @@ static uint16_t nvme_identify(NvmeCtrl *n, NvmeCmd *cmd)
> > > > }
> > > > }
> > > >
> > > > +static uint16_t nvme_abort(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
> > > > +{
> > > > + uint16_t sqid = le32_to_cpu(cmd->cdw10) & 0xffff;
> > > > +
> > > > + req->cqe.result = 1;
> > > > + if (nvme_check_sqid(n, sqid)) {
> > > > + return NVME_INVALID_FIELD | NVME_DNR;
> > > > + }
> > > > +
> > > Shouldn't we validate the CID as well ?
> > >
> >
> > According to the specification it is "implementation specific if/when a
> > controller chooses to complete the command when the command to abort is
> > not found".
> >
> > I'm interpreting this to mean that, yes, an invalid command identifier
> > could be given in the command, but this implementation does not care
> > about that.
> >
> > I still think the controller should check the validity of the submission
> > queue identifier though. It is a general invariant that the sqid should
> > be valid.
> >
> > > > + return NVME_SUCCESS;
> > > > +}
> > > > +
> > > > static inline void nvme_set_timestamp(NvmeCtrl *n, uint64_t ts)
> > > > {
> > > > trace_nvme_setfeat_timestamp(ts);
> > > > @@ -859,6 +871,7 @@ static uint16_t nvme_set_feature(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
> > > > trace_nvme_err_invalid_setfeat(dw10);
> > > > return NVME_INVALID_FIELD | NVME_DNR;
> > > > }
> > > > +
> > > > return NVME_SUCCESS;
> > > > }
> > > >
> > > > @@ -875,6 +888,8 @@ static uint16_t nvme_admin_cmd(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
> > > > return nvme_create_cq(n, cmd);
> > > > case NVME_ADM_CMD_IDENTIFY:
> > > > return nvme_identify(n, cmd);
> > > > + case NVME_ADM_CMD_ABORT:
> > > > + return nvme_abort(n, cmd, req);
> > > > case NVME_ADM_CMD_SET_FEATURES:
> > > > return nvme_set_feature(n, cmd, req);
> > > > case NVME_ADM_CMD_GET_FEATURES:
> > > > @@ -1388,6 +1403,7 @@ static void nvme_realize(PCIDevice *pci_dev, Error **errp)
> > > > id->ieee[2] = 0xb3;
> > > > id->ver = cpu_to_le32(0x00010201);
> > > > id->oacs = cpu_to_le16(0);
> > > > + id->acl = 3;
> > > So we are setting the max number of concurrent commands
> > > but there is no logic to enforce that and wrap up with the
> > > status suggested by specification.
> > >
> >
> > That is true, but because the controller always completes the Abort
> > command immediately this cannot happen. If the controller did try to
> > abort executing commands, the Abort command would need to linger in the
> > controller state until a completion queue entry is posted for the
> > command to be aborted before the completion queue entry can be posted
> > for the Abort command. This takes up resources in the controller and is
> > the reason for the Abort Command Limit.
> >
> > You could argue that we should set ACL to 0 then, but the specification
> > recommends a value of 3 and I do not see any harm in conveying a
> > "reasonable", though inconsequential, value.
>
> Could we potentially add some comment describing the above ?
>
Yes, absolutely! :)
Klaus
^ permalink raw reply [flat|nested] 52+ messages in thread
* [PATCH v2 07/20] nvme: refactor device realization
2019-10-15 10:38 [PATCH v2 00/20] nvme: support NVMe v1.3d, SGLs and multiple namespaces Klaus Jensen
` (5 preceding siblings ...)
2019-10-15 10:38 ` [PATCH v2 06/20] nvme: add support for the abort command Klaus Jensen
@ 2019-10-15 10:38 ` Klaus Jensen
2019-10-15 10:38 ` [PATCH v2 08/20] nvme: add support for the get log page command Klaus Jensen
` (16 subsequent siblings)
23 siblings, 0 replies; 52+ messages in thread
From: Klaus Jensen @ 2019-10-15 10:38 UTC (permalink / raw)
To: qemu-block
Cc: Kevin Wolf, Fam Zheng, Javier Gonzalez, qemu-devel, Max Reitz,
Keith Busch, Paul Durrant, Stephen Bates
This patch splits up nvme_realize into multiple individual functions,
each initializing a different subset of the device.
Signed-off-by: Klaus Jensen <klaus.jensen@cnexlabs.com>
---
hw/block/nvme.c | 176 +++++++++++++++++++++++++++++++-----------------
hw/block/nvme.h | 22 ++++++
2 files changed, 135 insertions(+), 63 deletions(-)
diff --git a/hw/block/nvme.c b/hw/block/nvme.c
index 84e4f2ea7a15..1fdb3b8655ed 100644
--- a/hw/block/nvme.c
+++ b/hw/block/nvme.c
@@ -43,6 +43,8 @@
#include "trace.h"
#include "nvme.h"
+#define NVME_MAX_QS PCI_MSIX_FLAGS_QSIZE
+
#define NVME_GUEST_ERR(trace, fmt, ...) \
do { \
(trace_##trace)(__VA_ARGS__); \
@@ -1336,67 +1338,106 @@ static const MemoryRegionOps nvme_cmb_ops = {
},
};
-static void nvme_realize(PCIDevice *pci_dev, Error **errp)
+static int nvme_check_constraints(NvmeCtrl *n, Error **errp)
{
- NvmeCtrl *n = NVME(pci_dev);
- NvmeIdCtrl *id = &n->id_ctrl;
-
- int i;
- int64_t bs_size;
- uint8_t *pci_conf;
-
- if (!n->params.num_queues) {
- error_setg(errp, "num_queues can't be zero");
- return;
- }
+ NvmeParams *params = &n->params;
if (!n->conf.blk) {
- error_setg(errp, "drive property not set");
- return;
+ error_setg(errp, "nvme: block backend not configured");
+ return 1;
}
- bs_size = blk_getlength(n->conf.blk);
- if (bs_size < 0) {
- error_setg(errp, "could not get backing file size");
- return;
+ if (!params->serial) {
+ error_setg(errp, "nvme: serial not configured");
+ return 1;
}
- if (!n->params.serial) {
- error_setg(errp, "serial property not set");
- return;
+ if ((params->num_queues < 1 || params->num_queues > NVME_MAX_QS)) {
+ error_setg(errp, "nvme: invalid queue configuration");
+ return 1;
}
+
+ return 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;
+ false, errp)) {
+ return 1;
}
- 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);
+ return 0;
+}
+static void nvme_init_state(NvmeCtrl *n)
+{
n->num_namespaces = 1;
n->reg_size = pow2ceil(0x1004 + 2 * (n->params.num_queues + 1) * 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);
+}
+
+static void nvme_init_cmb(NvmeCtrl *n, PCIDevice *pci_dev)
+{
+ 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, 1);
+ 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->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));
+ 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;
- memory_region_init_io(&n->iomem, OBJECT(n), &nvme_mmio_ops, n,
- "nvme", n->reg_size);
+ 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.num_queues, 4, NULL);
+ if (n->params.cmb_size_mb) {
+ nvme_init_cmb(n, pci_dev);
+ }
+}
+
+static void nvme_init_ctrl(NvmeCtrl *n)
+{
+ NvmeIdCtrl *id = &n->id_ctrl;
+ NvmeParams *params = &n->params;
+ uint8_t *pci_conf = n->parent_obj.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", ' ');
strpadcpy((char *)id->fr, sizeof(id->fr), "1.0", ' ');
- strpadcpy((char *)id->sn, sizeof(id->sn), n->params.serial, ' ');
+ strpadcpy((char *)id->sn, sizeof(id->sn), params->serial, ' ');
id->rab = 6;
id->ieee[0] = 0x00;
id->ieee[1] = 0x02;
@@ -1430,46 +1471,55 @@ static void nvme_realize(PCIDevice *pci_dev, Error **errp)
n->bar.vs = 0x00010201;
n->bar.intmc = n->bar.intms = 0;
+}
- if (n->params.cmb_size_mb) {
+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, "blk_getlength");
+ return 1;
+ }
+
+ id_ns->lbaf[0].ds = BDRV_SECTOR_BITS;
+ n->ns_size = bs_size;
+
+ id_ns->ncap = id_ns->nuse = id_ns->nsze =
+ cpu_to_le64(nvme_ns_nlbas(n, ns));
- NVME_CMBLOC_SET_BIR(n->bar.cmbloc, 2);
- NVME_CMBLOC_SET_OFST(n->bar.cmbloc, 0);
+ return 0;
+}
- NVME_CMBSZ_SET_SQS(n->bar.cmbsz, 1);
- NVME_CMBSZ_SET_CQS(n->bar.cmbsz, 1);
- 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);
+static void nvme_realize(PCIDevice *pci_dev, Error **errp)
+{
+ NvmeCtrl *n = NVME(pci_dev);
+ Error *local_err = NULL;
+ int i;
- n->cmbloc = n->bar.cmbloc;
- n->cmbsz = n->bar.cmbsz;
+ if (nvme_check_constraints(n, &local_err)) {
+ error_propagate_prepend(errp, local_err, "nvme_check_constraints: ");
+ return;
+ }
- 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);
+ nvme_init_state(n);
+ if (nvme_init_blk(n, &local_err)) {
+ error_propagate_prepend(errp, local_err, "nvme_init_blk: ");
+ return;
}
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], &local_err)) {
+ error_propagate_prepend(errp, local_err, "nvme_init_namespace: ");
+ return;
+ }
}
+
+ nvme_init_pci(n, pci_dev);
+ nvme_init_ctrl(n);
}
static void nvme_exit(PCIDevice *pci_dev)
diff --git a/hw/block/nvme.h b/hw/block/nvme.h
index 9957c4a200e2..7c3c07bde887 100644
--- a/hw/block/nvme.h
+++ b/hw/block/nvme.h
@@ -101,4 +101,26 @@ typedef struct NvmeCtrl {
NvmeIdCtrl id_ctrl;
} NvmeCtrl;
+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;
+}
+
+static inline size_t nvme_ns_lbads_bytes(NvmeNamespace *ns)
+{
+ return 1 << nvme_ns_lbads(ns);
+}
+
+static inline uint64_t nvme_ns_nlbas(NvmeCtrl *n, NvmeNamespace *ns)
+{
+ return n->ns_size >> nvme_ns_lbads(ns);
+}
+
+
#endif /* HW_NVME_H */
--
2.23.0
^ permalink raw reply related [flat|nested] 52+ messages in thread* [PATCH v2 08/20] nvme: add support for the get log page command
2019-10-15 10:38 [PATCH v2 00/20] nvme: support NVMe v1.3d, SGLs and multiple namespaces Klaus Jensen
` (6 preceding siblings ...)
2019-10-15 10:38 ` [PATCH v2 07/20] nvme: refactor device realization Klaus Jensen
@ 2019-10-15 10:38 ` Klaus Jensen
2019-11-12 15:04 ` Beata Michalska
2019-10-15 10:38 ` [PATCH v2 09/20] nvme: add support for the asynchronous event request command Klaus Jensen
` (15 subsequent siblings)
23 siblings, 1 reply; 52+ messages in thread
From: Klaus Jensen @ 2019-10-15 10:38 UTC (permalink / raw)
To: qemu-block
Cc: Kevin Wolf, Fam Zheng, Javier Gonzalez, qemu-devel, Max Reitz,
Keith Busch, Paul Durrant, Stephen Bates
Add support for the Get Log Page command and basic implementations
of the mandatory Error Information, SMART/Health Information and
Firmware Slot Information log pages.
In violation of the specification, the SMART/Health Information log page
does not persist information over the lifetime of the controller because
the device has no place to store such persistent state.
Required for compliance with NVMe revision 1.2.1. See NVM Express 1.2.1,
Section 5.10 ("Get Log Page command").
Signed-off-by: Klaus Jensen <klaus.jensen@cnexlabs.com>
---
hw/block/nvme.c | 150 +++++++++++++++++++++++++++++++++++++++++-
hw/block/nvme.h | 9 ++-
hw/block/trace-events | 2 +
include/block/nvme.h | 2 +-
4 files changed, 160 insertions(+), 3 deletions(-)
diff --git a/hw/block/nvme.c b/hw/block/nvme.c
index 1fdb3b8655ed..4412a3bea3bc 100644
--- a/hw/block/nvme.c
+++ b/hw/block/nvme.c
@@ -44,6 +44,7 @@
#include "nvme.h"
#define NVME_MAX_QS PCI_MSIX_FLAGS_QSIZE
+#define NVME_TEMPERATURE 0x143
#define NVME_GUEST_ERR(trace, fmt, ...) \
do { \
@@ -577,6 +578,137 @@ static uint16_t nvme_create_sq(NvmeCtrl *n, NvmeCmd *cmd)
return NVME_SUCCESS;
}
+static uint16_t nvme_error_info(NvmeCtrl *n, NvmeCmd *cmd,
+ uint32_t buf_len, uint64_t off, NvmeRequest *req)
+{
+ uint32_t trans_len;
+ uint64_t prp1 = le64_to_cpu(cmd->prp1);
+ uint64_t prp2 = le64_to_cpu(cmd->prp2);
+
+ if (off > sizeof(*n->elpes) * (n->params.elpe + 1)) {
+ return NVME_INVALID_FIELD | NVME_DNR;
+ }
+
+ trans_len = MIN(sizeof(*n->elpes) * (n->params.elpe + 1) - off, buf_len);
+
+ return nvme_dma_read_prp(n, (uint8_t *) n->elpes + off, trans_len, prp1,
+ prp2);
+}
+
+static uint16_t nvme_smart_info(NvmeCtrl *n, NvmeCmd *cmd, uint32_t buf_len,
+ uint64_t off, NvmeRequest *req)
+{
+ uint64_t prp1 = le64_to_cpu(cmd->prp1);
+ uint64_t prp2 = le64_to_cpu(cmd->prp2);
+ uint32_t nsid = le32_to_cpu(cmd->nsid);
+
+ uint32_t trans_len;
+ time_t current_ms;
+ uint64_t units_read = 0, units_written = 0, read_commands = 0,
+ write_commands = 0;
+ NvmeSmartLog smart;
+ BlockAcctStats *s;
+
+ if (!nsid || (nsid != 0xffffffff && nsid > n->num_namespaces)) {
+ trace_nvme_err_invalid_ns(nsid, n->num_namespaces);
+ return NVME_INVALID_NSID | NVME_DNR;
+ }
+
+ s = blk_get_stats(n->conf.blk);
+
+ units_read = s->nr_bytes[BLOCK_ACCT_READ] >> BDRV_SECTOR_BITS;
+ units_written = s->nr_bytes[BLOCK_ACCT_WRITE] >> BDRV_SECTOR_BITS;
+ read_commands = s->nr_ops[BLOCK_ACCT_READ];
+ write_commands = s->nr_ops[BLOCK_ACCT_WRITE];
+
+ if (off > sizeof(smart)) {
+ return NVME_INVALID_FIELD | NVME_DNR;
+ }
+
+ trans_len = MIN(sizeof(smart) - off, buf_len);
+
+ memset(&smart, 0x0, sizeof(smart));
+
+ smart.data_units_read[0] = cpu_to_le64(units_read / 1000);
+ smart.data_units_written[0] = cpu_to_le64(units_written / 1000);
+ smart.host_read_commands[0] = cpu_to_le64(read_commands);
+ smart.host_write_commands[0] = cpu_to_le64(write_commands);
+
+ smart.number_of_error_log_entries[0] = cpu_to_le64(0);
+ smart.temperature[0] = n->temperature & 0xff;
+ smart.temperature[1] = (n->temperature >> 8) & 0xff;
+
+ if (n->features.temp_thresh <= n->temperature) {
+ smart.critical_warning |= NVME_SMART_TEMPERATURE;
+ }
+
+ current_ms = qemu_clock_get_ms(QEMU_CLOCK_VIRTUAL);
+ smart.power_on_hours[0] = cpu_to_le64(
+ (((current_ms - n->starttime_ms) / 1000) / 60) / 60);
+
+ return nvme_dma_read_prp(n, (uint8_t *) &smart + off, trans_len, prp1,
+ prp2);
+}
+
+static uint16_t nvme_fw_log_info(NvmeCtrl *n, NvmeCmd *cmd, uint32_t buf_len,
+ uint64_t off, NvmeRequest *req)
+{
+ uint32_t trans_len;
+ uint64_t prp1 = le64_to_cpu(cmd->prp1);
+ uint64_t prp2 = le64_to_cpu(cmd->prp2);
+ NvmeFwSlotInfoLog fw_log;
+
+ if (off > sizeof(fw_log)) {
+ return NVME_INVALID_FIELD | NVME_DNR;
+ }
+
+ memset(&fw_log, 0, sizeof(NvmeFwSlotInfoLog));
+
+ trans_len = MIN(sizeof(fw_log) - off, buf_len);
+
+ return nvme_dma_read_prp(n, (uint8_t *) &fw_log + off, trans_len, prp1,
+ prp2);
+}
+
+static uint16_t nvme_get_log(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
+{
+ uint32_t dw10 = le32_to_cpu(cmd->cdw10);
+ uint32_t dw11 = le32_to_cpu(cmd->cdw11);
+ uint32_t dw12 = le32_to_cpu(cmd->cdw12);
+ uint32_t dw13 = le32_to_cpu(cmd->cdw13);
+ uint16_t lid = dw10 & 0xff;
+ uint8_t rae = (dw10 >> 15) & 0x1;
+ uint32_t numdl, numdu;
+ uint64_t off, lpol, lpou;
+ size_t len;
+
+ numdl = (dw10 >> 16);
+ numdu = (dw11 & 0xffff);
+ lpol = dw12;
+ lpou = dw13;
+
+ len = (((numdu << 16) | numdl) + 1) << 2;
+ off = (lpou << 32ULL) | lpol;
+
+ if (off & 0x3) {
+ return NVME_INVALID_FIELD | NVME_DNR;
+ }
+
+ trace_nvme_get_log(req->cid, lid, rae, len, off);
+
+ switch (lid) {
+ case NVME_LOG_ERROR_INFO:
+ return nvme_error_info(n, cmd, len, off, req);
+ case NVME_LOG_SMART_INFO:
+ return nvme_smart_info(n, cmd, len, off, req);
+ case NVME_LOG_FW_SLOT_INFO:
+ return nvme_fw_log_info(n, cmd, len, off, req);
+ default:
+ trace_nvme_err_invalid_log_page(req->cid, lid);
+ return NVME_INVALID_LOG_ID | NVME_DNR;
+ }
+}
+
static void nvme_free_cq(NvmeCQueue *cq, NvmeCtrl *n)
{
n->cq[cq->cqid] = NULL;
@@ -812,6 +944,9 @@ static uint16_t nvme_get_feature(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
uint32_t result;
switch (dw10) {
+ case NVME_TEMPERATURE_THRESHOLD:
+ result = cpu_to_le32(n->features.temp_thresh);
+ break;
case NVME_VOLATILE_WRITE_CACHE:
result = blk_enable_write_cache(n->conf.blk);
trace_nvme_getfeat_vwcache(result ? "enabled" : "disabled");
@@ -856,6 +991,10 @@ static uint16_t nvme_set_feature(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
uint32_t dw11 = le32_to_cpu(cmd->cdw11);
switch (dw10) {
+ case NVME_TEMPERATURE_THRESHOLD:
+ n->features.temp_thresh = dw11;
+ break;
+
case NVME_VOLATILE_WRITE_CACHE:
blk_set_enable_write_cache(n->conf.blk, dw11 & 1);
break;
@@ -884,6 +1023,8 @@ static uint16_t nvme_admin_cmd(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
return nvme_del_sq(n, cmd);
case NVME_ADM_CMD_CREATE_SQ:
return nvme_create_sq(n, cmd);
+ case NVME_ADM_CMD_GET_LOG_PAGE:
+ return nvme_get_log(n, cmd, req);
case NVME_ADM_CMD_DELETE_CQ:
return nvme_del_cq(n, cmd);
case NVME_ADM_CMD_CREATE_CQ:
@@ -923,6 +1064,7 @@ static void nvme_process_sq(void *opaque)
QTAILQ_INSERT_TAIL(&sq->out_req_list, req, entry);
memset(&req->cqe, 0, sizeof(req->cqe));
req->cqe.cid = cmd.cid;
+ req->cid = le16_to_cpu(cmd.cid);
status = sq->sqid ? nvme_io_cmd(n, &cmd, req) :
nvme_admin_cmd(n, &cmd, req);
@@ -1378,6 +1520,10 @@ static void nvme_init_state(NvmeCtrl *n)
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->elpes = g_new0(NvmeErrorLog, n->params.elpe + 1);
+ n->starttime_ms = qemu_clock_get_ms(QEMU_CLOCK_VIRTUAL);
+ n->temperature = NVME_TEMPERATURE;
+ n->features.temp_thresh = 0x14d;
}
static void nvme_init_cmb(NvmeCtrl *n, PCIDevice *pci_dev)
@@ -1446,7 +1592,8 @@ static void nvme_init_ctrl(NvmeCtrl *n)
id->oacs = cpu_to_le16(0);
id->acl = 3;
id->frmw = 7 << 1;
- id->lpa = 1 << 0;
+ id->lpa = 1 << 2;
+ id->elpe = n->params.elpe;
id->sqes = (0x6 << 4) | 0x6;
id->cqes = (0x4 << 4) | 0x4;
id->nn = cpu_to_le32(n->num_namespaces);
@@ -1530,6 +1677,7 @@ static void nvme_exit(PCIDevice *pci_dev)
g_free(n->namespaces);
g_free(n->cq);
g_free(n->sq);
+ g_free(n->elpes);
if (n->params.cmb_size_mb) {
g_free(n->cmbuf);
diff --git a/hw/block/nvme.h b/hw/block/nvme.h
index 7c3c07bde887..fcfd504e3f9f 100644
--- a/hw/block/nvme.h
+++ b/hw/block/nvme.h
@@ -6,12 +6,14 @@
#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, 64), \
+ DEFINE_PROP_UINT8("elpe", _state, _props.elpe, 24)
typedef struct NvmeParams {
char *serial;
uint32_t num_queues;
uint32_t cmb_size_mb;
+ uint8_t elpe;
} NvmeParams;
typedef struct NvmeAsyncEvent {
@@ -23,6 +25,7 @@ typedef struct NvmeRequest {
struct NvmeSQueue *sq;
BlockAIOCB *aiocb;
uint16_t status;
+ uint16_t cid;
bool has_sg;
NvmeCqe cqe;
BlockAcctCookie acct;
@@ -92,12 +95,16 @@ typedef struct NvmeCtrl {
uint64_t irq_status;
uint64_t host_timestamp; /* Timestamp sent by the host */
uint64_t timestamp_set_qemu_clock_ms; /* QEMU clock time */
+ uint64_t starttime_ms;
+ uint16_t temperature;
NvmeNamespace *namespaces;
NvmeSQueue **sq;
NvmeCQueue **cq;
NvmeSQueue admin_sq;
NvmeCQueue admin_cq;
+ NvmeFeatureVal features;
+ NvmeErrorLog *elpes;
NvmeIdCtrl id_ctrl;
} NvmeCtrl;
diff --git a/hw/block/trace-events b/hw/block/trace-events
index 13d1b21dd4e4..a2c7919c861e 100644
--- a/hw/block/trace-events
+++ b/hw/block/trace-events
@@ -46,6 +46,7 @@ nvme_getfeat_numq(int result) "get feature number of queues, result=%d"
nvme_setfeat_numq(int reqcq, int reqsq, int gotcq, int gotsq) "requested cq_count=%d sq_count=%d, responding with cq_count=%d sq_count=%d"
nvme_setfeat_timestamp(uint64_t ts) "set feature timestamp = 0x%"PRIx64""
nvme_getfeat_timestamp(uint64_t ts) "get feature timestamp = 0x%"PRIx64""
+nvme_get_log(uint16_t cid, uint16_t lid, uint8_t rae, uint32_t len, uint64_t off) "cid %"PRIu16" lid 0x%"PRIx16" rae 0x%"PRIx8" len %"PRIu32" off %"PRIu64""
nvme_mmio_intm_set(uint64_t data, uint64_t new_mask) "wrote MMIO, interrupt mask set, data=0x%"PRIx64", new_mask=0x%"PRIx64""
nvme_mmio_intm_clr(uint64_t data, uint64_t new_mask) "wrote MMIO, interrupt mask clr, data=0x%"PRIx64", new_mask=0x%"PRIx64""
nvme_mmio_cfg(uint64_t data) "wrote MMIO, config controller config=0x%"PRIx64""
@@ -85,6 +86,7 @@ nvme_err_invalid_create_cq_qflags(uint16_t qflags) "failed creating completion q
nvme_err_invalid_identify_cns(uint16_t cns) "identify, invalid cns=0x%"PRIx16""
nvme_err_invalid_getfeat(int dw10) "invalid get features, dw10=0x%"PRIx32""
nvme_err_invalid_setfeat(uint32_t dw10) "invalid set features, dw10=0x%"PRIx32""
+nvme_err_invalid_log_page(uint16_t cid, uint16_t lid) "cid %"PRIu16" lid 0x%"PRIx16""
nvme_err_startfail_cq(void) "nvme_start_ctrl failed because there are non-admin completion queues"
nvme_err_startfail_sq(void) "nvme_start_ctrl failed because there are non-admin submission queues"
nvme_err_startfail_nbarasq(void) "nvme_start_ctrl failed because the admin submission queue address is null"
diff --git a/include/block/nvme.h b/include/block/nvme.h
index 1b0accd4fe2b..a088ec7d4e38 100644
--- a/include/block/nvme.h
+++ b/include/block/nvme.h
@@ -515,7 +515,7 @@ enum NvmeSmartWarn {
NVME_SMART_FAILED_VOLATILE_MEDIA = 1 << 4,
};
-enum LogIdentifier {
+enum NvmeLogIdentifier {
NVME_LOG_ERROR_INFO = 0x01,
NVME_LOG_SMART_INFO = 0x02,
NVME_LOG_FW_SLOT_INFO = 0x03,
--
2.23.0
^ permalink raw reply related [flat|nested] 52+ messages in thread* Re: [PATCH v2 08/20] nvme: add support for the get log page command
2019-10-15 10:38 ` [PATCH v2 08/20] nvme: add support for the get log page command Klaus Jensen
@ 2019-11-12 15:04 ` Beata Michalska
2019-11-19 20:01 ` Klaus Birkelund
0 siblings, 1 reply; 52+ messages in thread
From: Beata Michalska @ 2019-11-12 15:04 UTC (permalink / raw)
To: Klaus Jensen
Cc: Kevin Wolf, Fam Zheng, Javier Gonzalez, qemu-block, qemu-devel,
Max Reitz, Keith Busch, Paul Durrant, Stephen Bates
Hi Klaus,
On Tue, 15 Oct 2019 at 11:45, Klaus Jensen <its@irrelevant.dk> wrote:
>
> Add support for the Get Log Page command and basic implementations
> of the mandatory Error Information, SMART/Health Information and
> Firmware Slot Information log pages.
>
> In violation of the specification, the SMART/Health Information log page
> does not persist information over the lifetime of the controller because
> the device has no place to store such persistent state.
>
> Required for compliance with NVMe revision 1.2.1. See NVM Express 1.2.1,
> Section 5.10 ("Get Log Page command").
>
> Signed-off-by: Klaus Jensen <klaus.jensen@cnexlabs.com>
> ---
> hw/block/nvme.c | 150 +++++++++++++++++++++++++++++++++++++++++-
> hw/block/nvme.h | 9 ++-
> hw/block/trace-events | 2 +
> include/block/nvme.h | 2 +-
> 4 files changed, 160 insertions(+), 3 deletions(-)
>
> diff --git a/hw/block/nvme.c b/hw/block/nvme.c
> index 1fdb3b8655ed..4412a3bea3bc 100644
> --- a/hw/block/nvme.c
> +++ b/hw/block/nvme.c
> @@ -44,6 +44,7 @@
> #include "nvme.h"
>
> #define NVME_MAX_QS PCI_MSIX_FLAGS_QSIZE
> +#define NVME_TEMPERATURE 0x143
>
> #define NVME_GUEST_ERR(trace, fmt, ...) \
> do { \
> @@ -577,6 +578,137 @@ static uint16_t nvme_create_sq(NvmeCtrl *n, NvmeCmd *cmd)
> return NVME_SUCCESS;
> }
>
> +static uint16_t nvme_error_info(NvmeCtrl *n, NvmeCmd *cmd,
> + uint32_t buf_len, uint64_t off, NvmeRequest *req)
> +{
> + uint32_t trans_len;
> + uint64_t prp1 = le64_to_cpu(cmd->prp1);
> + uint64_t prp2 = le64_to_cpu(cmd->prp2);
> +
> + if (off > sizeof(*n->elpes) * (n->params.elpe + 1)) {
> + return NVME_INVALID_FIELD | NVME_DNR;
> + }
> +
> + trans_len = MIN(sizeof(*n->elpes) * (n->params.elpe + 1) - off, buf_len);
> +
> + return nvme_dma_read_prp(n, (uint8_t *) n->elpes + off, trans_len, prp1,
> + prp2);
> +}
> +
> +static uint16_t nvme_smart_info(NvmeCtrl *n, NvmeCmd *cmd, uint32_t buf_len,
> + uint64_t off, NvmeRequest *req)
> +{
> + uint64_t prp1 = le64_to_cpu(cmd->prp1);
> + uint64_t prp2 = le64_to_cpu(cmd->prp2);
> + uint32_t nsid = le32_to_cpu(cmd->nsid);
> +
> + uint32_t trans_len;
> + time_t current_ms;
> + uint64_t units_read = 0, units_written = 0, read_commands = 0,
> + write_commands = 0;
> + NvmeSmartLog smart;
> + BlockAcctStats *s;
> +
> + if (!nsid || (nsid != 0xffffffff && nsid > n->num_namespaces)) {
> + trace_nvme_err_invalid_ns(nsid, n->num_namespaces);
> + return NVME_INVALID_NSID | NVME_DNR;
> + }
> +
The LAP '0' bit is cleared now - which means there is no support
for per-namespace data. So in theory, if that was the aim, this condition
should check for the values different than 0x0 and 0xFFFFFFFF and either
abort the command or treat that as request for controller specific data.
> + s = blk_get_stats(n->conf.blk);
> +
> + units_read = s->nr_bytes[BLOCK_ACCT_READ] >> BDRV_SECTOR_BITS;
> + units_written = s->nr_bytes[BLOCK_ACCT_WRITE] >> BDRV_SECTOR_BITS;
> + read_commands = s->nr_ops[BLOCK_ACCT_READ];
> + write_commands = s->nr_ops[BLOCK_ACCT_WRITE];
> +
> + if (off > sizeof(smart)) {
> + return NVME_INVALID_FIELD | NVME_DNR;
> + }
> +
> + trans_len = MIN(sizeof(smart) - off, buf_len);
> +
> + memset(&smart, 0x0, sizeof(smart));
> +
> + smart.data_units_read[0] = cpu_to_le64(units_read / 1000);
> + smart.data_units_written[0] = cpu_to_le64(units_written / 1000);
> + smart.host_read_commands[0] = cpu_to_le64(read_commands);
> + smart.host_write_commands[0] = cpu_to_le64(write_commands);
> +
> + smart.number_of_error_log_entries[0] = cpu_to_le64(0);
> + smart.temperature[0] = n->temperature & 0xff;
> + smart.temperature[1] = (n->temperature >> 8) & 0xff;
> +
> + if (n->features.temp_thresh <= n->temperature) {
> + smart.critical_warning |= NVME_SMART_TEMPERATURE;
> + }
> +
> + current_ms = qemu_clock_get_ms(QEMU_CLOCK_VIRTUAL);
> + smart.power_on_hours[0] = cpu_to_le64(
> + (((current_ms - n->starttime_ms) / 1000) / 60) / 60);
> +
> + return nvme_dma_read_prp(n, (uint8_t *) &smart + off, trans_len, prp1,
> + prp2);
> +}
> +
> +static uint16_t nvme_fw_log_info(NvmeCtrl *n, NvmeCmd *cmd, uint32_t buf_len,
> + uint64_t off, NvmeRequest *req)
> +{
> + uint32_t trans_len;
> + uint64_t prp1 = le64_to_cpu(cmd->prp1);
> + uint64_t prp2 = le64_to_cpu(cmd->prp2);
> + NvmeFwSlotInfoLog fw_log;
> +
> + if (off > sizeof(fw_log)) {
> + return NVME_INVALID_FIELD | NVME_DNR;
> + }
> +
> + memset(&fw_log, 0, sizeof(NvmeFwSlotInfoLog));
> +
> + trans_len = MIN(sizeof(fw_log) - off, buf_len);
> +
> + return nvme_dma_read_prp(n, (uint8_t *) &fw_log + off, trans_len, prp1,
> + prp2);
> +}
> +
> +static uint16_t nvme_get_log(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
> +{
> + uint32_t dw10 = le32_to_cpu(cmd->cdw10);
> + uint32_t dw11 = le32_to_cpu(cmd->cdw11);
> + uint32_t dw12 = le32_to_cpu(cmd->cdw12);
> + uint32_t dw13 = le32_to_cpu(cmd->cdw13);
> + uint16_t lid = dw10 & 0xff;
> + uint8_t rae = (dw10 >> 15) & 0x1;
> + uint32_t numdl, numdu;
> + uint64_t off, lpol, lpou;
> + size_t len;
> +
> + numdl = (dw10 >> 16);
> + numdu = (dw11 & 0xffff);
> + lpol = dw12;
> + lpou = dw13;
> +
> + len = (((numdu << 16) | numdl) + 1) << 2;
> + off = (lpou << 32ULL) | lpol;
> +
> + if (off & 0x3) {
> + return NVME_INVALID_FIELD | NVME_DNR;
> + }
> +
> + trace_nvme_get_log(req->cid, lid, rae, len, off);
> +
> + switch (lid) {
> + case NVME_LOG_ERROR_INFO:
> + return nvme_error_info(n, cmd, len, off, req);
> + case NVME_LOG_SMART_INFO:
> + return nvme_smart_info(n, cmd, len, off, req);
> + case NVME_LOG_FW_SLOT_INFO:
> + return nvme_fw_log_info(n, cmd, len, off, req);
> + default:
> + trace_nvme_err_invalid_log_page(req->cid, lid);
> + return NVME_INVALID_LOG_ID | NVME_DNR;
The spec mentions the Invalid Field in Command case processing
command with an unsupported log id.
> + }
> +}
> +
> static void nvme_free_cq(NvmeCQueue *cq, NvmeCtrl *n)
> {
> n->cq[cq->cqid] = NULL;
> @@ -812,6 +944,9 @@ static uint16_t nvme_get_feature(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
> uint32_t result;
>
> switch (dw10) {
> + case NVME_TEMPERATURE_THRESHOLD:
> + result = cpu_to_le32(n->features.temp_thresh);
> + break;
> case NVME_VOLATILE_WRITE_CACHE:
> result = blk_enable_write_cache(n->conf.blk);
> trace_nvme_getfeat_vwcache(result ? "enabled" : "disabled");
> @@ -856,6 +991,10 @@ static uint16_t nvme_set_feature(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
> uint32_t dw11 = le32_to_cpu(cmd->cdw11);
>
> switch (dw10) {
> + case NVME_TEMPERATURE_THRESHOLD:
> + n->features.temp_thresh = dw11;
> + break;
> +
> case NVME_VOLATILE_WRITE_CACHE:
> blk_set_enable_write_cache(n->conf.blk, dw11 & 1);
> break;
> @@ -884,6 +1023,8 @@ static uint16_t nvme_admin_cmd(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
> return nvme_del_sq(n, cmd);
> case NVME_ADM_CMD_CREATE_SQ:
> return nvme_create_sq(n, cmd);
> + case NVME_ADM_CMD_GET_LOG_PAGE:
> + return nvme_get_log(n, cmd, req);
> case NVME_ADM_CMD_DELETE_CQ:
> return nvme_del_cq(n, cmd);
> case NVME_ADM_CMD_CREATE_CQ:
> @@ -923,6 +1064,7 @@ static void nvme_process_sq(void *opaque)
> QTAILQ_INSERT_TAIL(&sq->out_req_list, req, entry);
> memset(&req->cqe, 0, sizeof(req->cqe));
> req->cqe.cid = cmd.cid;
> + req->cid = le16_to_cpu(cmd.cid);
If I haven't missed anything this is being used only in one place
for tracing - is it really worth to duplicate the cid here ?
>
> status = sq->sqid ? nvme_io_cmd(n, &cmd, req) :
> nvme_admin_cmd(n, &cmd, req);
> @@ -1378,6 +1520,10 @@ static void nvme_init_state(NvmeCtrl *n)
> 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->elpes = g_new0(NvmeErrorLog, n->params.elpe + 1);
> + n->starttime_ms = qemu_clock_get_ms(QEMU_CLOCK_VIRTUAL);
> + n->temperature = NVME_TEMPERATURE;
> + n->features.temp_thresh = 0x14d;
> }
>
> static void nvme_init_cmb(NvmeCtrl *n, PCIDevice *pci_dev)
> @@ -1446,7 +1592,8 @@ static void nvme_init_ctrl(NvmeCtrl *n)
> id->oacs = cpu_to_le16(0);
> id->acl = 3;
> id->frmw = 7 << 1;
> - id->lpa = 1 << 0;
> + id->lpa = 1 << 2;
This sets the bit that states support for GLP command but clears the one
that states support for per-namespace SMART/Heatld data - is that expected ?
BR
Beata
> + id->elpe = n->params.elpe;
> id->sqes = (0x6 << 4) | 0x6;
> id->cqes = (0x4 << 4) | 0x4;
> id->nn = cpu_to_le32(n->num_namespaces);
> @@ -1530,6 +1677,7 @@ static void nvme_exit(PCIDevice *pci_dev)
> g_free(n->namespaces);
> g_free(n->cq);
> g_free(n->sq);
> + g_free(n->elpes);
>
> if (n->params.cmb_size_mb) {
> g_free(n->cmbuf);
> diff --git a/hw/block/nvme.h b/hw/block/nvme.h
> index 7c3c07bde887..fcfd504e3f9f 100644
> --- a/hw/block/nvme.h
> +++ b/hw/block/nvme.h
> @@ -6,12 +6,14 @@
> #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, 64), \
> + DEFINE_PROP_UINT8("elpe", _state, _props.elpe, 24)
>
> typedef struct NvmeParams {
> char *serial;
> uint32_t num_queues;
> uint32_t cmb_size_mb;
> + uint8_t elpe;
> } NvmeParams;
>
> typedef struct NvmeAsyncEvent {
> @@ -23,6 +25,7 @@ typedef struct NvmeRequest {
> struct NvmeSQueue *sq;
> BlockAIOCB *aiocb;
> uint16_t status;
> + uint16_t cid;
> bool has_sg;
> NvmeCqe cqe;
> BlockAcctCookie acct;
> @@ -92,12 +95,16 @@ typedef struct NvmeCtrl {
> uint64_t irq_status;
> uint64_t host_timestamp; /* Timestamp sent by the host */
> uint64_t timestamp_set_qemu_clock_ms; /* QEMU clock time */
> + uint64_t starttime_ms;
> + uint16_t temperature;
>
> NvmeNamespace *namespaces;
> NvmeSQueue **sq;
> NvmeCQueue **cq;
> NvmeSQueue admin_sq;
> NvmeCQueue admin_cq;
> + NvmeFeatureVal features;
> + NvmeErrorLog *elpes;
> NvmeIdCtrl id_ctrl;
> } NvmeCtrl;
>
> diff --git a/hw/block/trace-events b/hw/block/trace-events
> index 13d1b21dd4e4..a2c7919c861e 100644
> --- a/hw/block/trace-events
> +++ b/hw/block/trace-events
> @@ -46,6 +46,7 @@ nvme_getfeat_numq(int result) "get feature number of queues, result=%d"
> nvme_setfeat_numq(int reqcq, int reqsq, int gotcq, int gotsq) "requested cq_count=%d sq_count=%d, responding with cq_count=%d sq_count=%d"
> nvme_setfeat_timestamp(uint64_t ts) "set feature timestamp = 0x%"PRIx64""
> nvme_getfeat_timestamp(uint64_t ts) "get feature timestamp = 0x%"PRIx64""
> +nvme_get_log(uint16_t cid, uint16_t lid, uint8_t rae, uint32_t len, uint64_t off) "cid %"PRIu16" lid 0x%"PRIx16" rae 0x%"PRIx8" len %"PRIu32" off %"PRIu64""
> nvme_mmio_intm_set(uint64_t data, uint64_t new_mask) "wrote MMIO, interrupt mask set, data=0x%"PRIx64", new_mask=0x%"PRIx64""
> nvme_mmio_intm_clr(uint64_t data, uint64_t new_mask) "wrote MMIO, interrupt mask clr, data=0x%"PRIx64", new_mask=0x%"PRIx64""
> nvme_mmio_cfg(uint64_t data) "wrote MMIO, config controller config=0x%"PRIx64""
> @@ -85,6 +86,7 @@ nvme_err_invalid_create_cq_qflags(uint16_t qflags) "failed creating completion q
> nvme_err_invalid_identify_cns(uint16_t cns) "identify, invalid cns=0x%"PRIx16""
> nvme_err_invalid_getfeat(int dw10) "invalid get features, dw10=0x%"PRIx32""
> nvme_err_invalid_setfeat(uint32_t dw10) "invalid set features, dw10=0x%"PRIx32""
> +nvme_err_invalid_log_page(uint16_t cid, uint16_t lid) "cid %"PRIu16" lid 0x%"PRIx16""
> nvme_err_startfail_cq(void) "nvme_start_ctrl failed because there are non-admin completion queues"
> nvme_err_startfail_sq(void) "nvme_start_ctrl failed because there are non-admin submission queues"
> nvme_err_startfail_nbarasq(void) "nvme_start_ctrl failed because the admin submission queue address is null"
> diff --git a/include/block/nvme.h b/include/block/nvme.h
> index 1b0accd4fe2b..a088ec7d4e38 100644
> --- a/include/block/nvme.h
> +++ b/include/block/nvme.h
> @@ -515,7 +515,7 @@ enum NvmeSmartWarn {
> NVME_SMART_FAILED_VOLATILE_MEDIA = 1 << 4,
> };
>
> -enum LogIdentifier {
> +enum NvmeLogIdentifier {
> NVME_LOG_ERROR_INFO = 0x01,
> NVME_LOG_SMART_INFO = 0x02,
> NVME_LOG_FW_SLOT_INFO = 0x03,
> --
> 2.23.0
>
>
^ permalink raw reply [flat|nested] 52+ messages in thread* Re: [PATCH v2 08/20] nvme: add support for the get log page command
2019-11-12 15:04 ` Beata Michalska
@ 2019-11-19 20:01 ` Klaus Birkelund
0 siblings, 0 replies; 52+ messages in thread
From: Klaus Birkelund @ 2019-11-19 20:01 UTC (permalink / raw)
To: Beata Michalska
Cc: Kevin Wolf, qemu-block, qemu-devel, Max Reitz, Paul Durrant, Keith Busch
On Tue, Nov 12, 2019 at 03:04:52PM +0000, Beata Michalska wrote:
> Hi Klaus,
>
>
> On Tue, 15 Oct 2019 at 11:45, Klaus Jensen <its@irrelevant.dk> wrote:
> > + if (!nsid || (nsid != 0xffffffff && nsid > n->num_namespaces)) {
> > + trace_nvme_err_invalid_ns(nsid, n->num_namespaces);
> > + return NVME_INVALID_NSID | NVME_DNR;
> > + }
> > +
> The LAP '0' bit is cleared now - which means there is no support
> for per-namespace data. So in theory, if that was the aim, this condition
> should check for the values different than 0x0 and 0xFFFFFFFF and either
> abort the command or treat that as request for controller specific data.
>
This is fixed in v3 (that is, it just checks for values different from
0x0 and 0xffffffff).
> > + switch (lid) {
> > + case NVME_LOG_ERROR_INFO:
> > + return nvme_error_info(n, cmd, len, off, req);
> > + case NVME_LOG_SMART_INFO:
> > + return nvme_smart_info(n, cmd, len, off, req);
> > + case NVME_LOG_FW_SLOT_INFO:
> > + return nvme_fw_log_info(n, cmd, len, off, req);
> > + default:
> > + trace_nvme_err_invalid_log_page(req->cid, lid);
> > + return NVME_INVALID_LOG_ID | NVME_DNR;
>
> The spec mentions the Invalid Field in Command case processing
> command with an unsupported log id.
>
Thanks. Fixed!
> > + }
> > +}
> > +
> > static void nvme_free_cq(NvmeCQueue *cq, NvmeCtrl *n)
> > {
> > n->cq[cq->cqid] = NULL;
> > @@ -812,6 +944,9 @@ static uint16_t nvme_get_feature(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
> > uint32_t result;
> >
> > switch (dw10) {
> > + case NVME_TEMPERATURE_THRESHOLD:
> > + result = cpu_to_le32(n->features.temp_thresh);
> > + break;
> > case NVME_VOLATILE_WRITE_CACHE:
> > result = blk_enable_write_cache(n->conf.blk);
> > trace_nvme_getfeat_vwcache(result ? "enabled" : "disabled");
> > @@ -856,6 +991,10 @@ static uint16_t nvme_set_feature(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
> > uint32_t dw11 = le32_to_cpu(cmd->cdw11);
> >
> > switch (dw10) {
> > + case NVME_TEMPERATURE_THRESHOLD:
> > + n->features.temp_thresh = dw11;
> > + break;
> > +
> > case NVME_VOLATILE_WRITE_CACHE:
> > blk_set_enable_write_cache(n->conf.blk, dw11 & 1);
> > break;
> > @@ -884,6 +1023,8 @@ static uint16_t nvme_admin_cmd(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
> > return nvme_del_sq(n, cmd);
> > case NVME_ADM_CMD_CREATE_SQ:
> > return nvme_create_sq(n, cmd);
> > + case NVME_ADM_CMD_GET_LOG_PAGE:
> > + return nvme_get_log(n, cmd, req);
> > case NVME_ADM_CMD_DELETE_CQ:
> > return nvme_del_cq(n, cmd);
> > case NVME_ADM_CMD_CREATE_CQ:
> > @@ -923,6 +1064,7 @@ static void nvme_process_sq(void *opaque)
> > QTAILQ_INSERT_TAIL(&sq->out_req_list, req, entry);
> > memset(&req->cqe, 0, sizeof(req->cqe));
> > req->cqe.cid = cmd.cid;
> > + req->cid = le16_to_cpu(cmd.cid);
>
> If I haven't missed anything this is being used only in one place
> for tracing - is it really worth to duplicate the cid here ?
>
At this point in the series, yes - it is only used once. But it will be
used extensively for tracing in the later patches.
> > - id->lpa = 1 << 0;
> > + id->lpa = 1 << 2;
>
> This sets the bit that states support for GLP command but clears the one
> that states support for per-namespace SMART/Heatld data - is that expected ?
>
Yes, clearing the bit for per-namespace SMART/Health log page
information is intentional. There is no namespace specific information
defined in the namespace so the global and per-namespace log page
contains the same information.
^ permalink raw reply [flat|nested] 52+ messages in thread
* [PATCH v2 09/20] nvme: add support for the asynchronous event request command
2019-10-15 10:38 [PATCH v2 00/20] nvme: support NVMe v1.3d, SGLs and multiple namespaces Klaus Jensen
` (7 preceding siblings ...)
2019-10-15 10:38 ` [PATCH v2 08/20] nvme: add support for the get log page command Klaus Jensen
@ 2019-10-15 10:38 ` Klaus Jensen
2019-11-12 15:04 ` Beata Michalska
2019-10-15 10:38 ` [PATCH v2 10/20] nvme: add logging to error information log page Klaus Jensen
` (14 subsequent siblings)
23 siblings, 1 reply; 52+ messages in thread
From: Klaus Jensen @ 2019-10-15 10:38 UTC (permalink / raw)
To: qemu-block
Cc: Kevin Wolf, Fam Zheng, Javier Gonzalez, qemu-devel, Max Reitz,
Keith Busch, Paul Durrant, Stephen Bates
Required for compliance with NVMe revision 1.2.1. See NVM Express 1.2.1,
Section 5.2 ("Asynchronous Event Request command").
Mostly imported from Keith's qemu-nvme tree. Modified to not enqueue
events if something of the same type is already queued (but not cleared
by the host).
Signed-off-by: Klaus Jensen <klaus.jensen@cnexlabs.com>
---
hw/block/nvme.c | 180 ++++++++++++++++++++++++++++++++++++++++--
hw/block/nvme.h | 13 ++-
hw/block/trace-events | 8 ++
include/block/nvme.h | 4 +-
4 files changed, 196 insertions(+), 9 deletions(-)
diff --git a/hw/block/nvme.c b/hw/block/nvme.c
index 4412a3bea3bc..5cdee37582f9 100644
--- a/hw/block/nvme.c
+++ b/hw/block/nvme.c
@@ -334,6 +334,46 @@ static void nvme_enqueue_req_completion(NvmeCQueue *cq, NvmeRequest *req)
timer_mod(cq->timer, qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) + 500);
}
+static void nvme_enqueue_event(NvmeCtrl *n, uint8_t event_type,
+ uint8_t event_info, uint8_t log_page)
+{
+ NvmeAsyncEvent *event;
+
+ trace_nvme_enqueue_event(event_type, event_info, log_page);
+
+ /*
+ * Do not enqueue the event if something of this type is already queued.
+ * This bounds the size of the event queue and makes sure it does not grow
+ * indefinitely when events are not processed by the host (i.e. does not
+ * issue any AERs).
+ */
+ if (n->aer_mask_queued & (1 << event_type)) {
+ trace_nvme_enqueue_event_masked(event_type);
+ return;
+ }
+ n->aer_mask_queued |= (1 << event_type);
+
+ event = g_new(NvmeAsyncEvent, 1);
+ event->result = (NvmeAerResult) {
+ .event_type = event_type,
+ .event_info = event_info,
+ .log_page = log_page,
+ };
+
+ QTAILQ_INSERT_TAIL(&n->aer_queue, event, entry);
+
+ timer_mod(n->aer_timer, qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) + 500);
+}
+
+static void nvme_clear_events(NvmeCtrl *n, uint8_t event_type)
+{
+ n->aer_mask &= ~(1 << event_type);
+ if (!QTAILQ_EMPTY(&n->aer_queue)) {
+ timer_mod(n->aer_timer,
+ qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) + 500);
+ }
+}
+
static void nvme_rw_cb(void *opaque, int ret)
{
NvmeRequest *req = opaque;
@@ -578,7 +618,7 @@ static uint16_t nvme_create_sq(NvmeCtrl *n, NvmeCmd *cmd)
return NVME_SUCCESS;
}
-static uint16_t nvme_error_info(NvmeCtrl *n, NvmeCmd *cmd,
+static uint16_t nvme_error_info(NvmeCtrl *n, NvmeCmd *cmd, uint8_t rae,
uint32_t buf_len, uint64_t off, NvmeRequest *req)
{
uint32_t trans_len;
@@ -591,12 +631,16 @@ static uint16_t nvme_error_info(NvmeCtrl *n, NvmeCmd *cmd,
trans_len = MIN(sizeof(*n->elpes) * (n->params.elpe + 1) - off, buf_len);
+ if (!rae) {
+ nvme_clear_events(n, NVME_AER_TYPE_ERROR);
+ }
+
return nvme_dma_read_prp(n, (uint8_t *) n->elpes + off, trans_len, prp1,
prp2);
}
-static uint16_t nvme_smart_info(NvmeCtrl *n, NvmeCmd *cmd, uint32_t buf_len,
- uint64_t off, NvmeRequest *req)
+static uint16_t nvme_smart_info(NvmeCtrl *n, NvmeCmd *cmd, uint8_t rae,
+ uint32_t buf_len, uint64_t off, NvmeRequest *req)
{
uint64_t prp1 = le64_to_cpu(cmd->prp1);
uint64_t prp2 = le64_to_cpu(cmd->prp2);
@@ -646,6 +690,10 @@ static uint16_t nvme_smart_info(NvmeCtrl *n, NvmeCmd *cmd, uint32_t buf_len,
smart.power_on_hours[0] = cpu_to_le64(
(((current_ms - n->starttime_ms) / 1000) / 60) / 60);
+ if (!rae) {
+ nvme_clear_events(n, NVME_AER_TYPE_SMART);
+ }
+
return nvme_dma_read_prp(n, (uint8_t *) &smart + off, trans_len, prp1,
prp2);
}
@@ -698,9 +746,9 @@ static uint16_t nvme_get_log(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
switch (lid) {
case NVME_LOG_ERROR_INFO:
- return nvme_error_info(n, cmd, len, off, req);
+ return nvme_error_info(n, cmd, rae, len, off, req);
case NVME_LOG_SMART_INFO:
- return nvme_smart_info(n, cmd, len, off, req);
+ return nvme_smart_info(n, cmd, rae, len, off, req);
case NVME_LOG_FW_SLOT_INFO:
return nvme_fw_log_info(n, cmd, len, off, req);
default:
@@ -958,6 +1006,9 @@ static uint16_t nvme_get_feature(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
break;
case NVME_TIMESTAMP:
return nvme_get_feature_timestamp(n, cmd);
+ case NVME_ASYNCHRONOUS_EVENT_CONF:
+ result = cpu_to_le32(n->features.async_config);
+ break;
default:
trace_nvme_err_invalid_getfeat(dw10);
return NVME_INVALID_FIELD | NVME_DNR;
@@ -993,6 +1044,12 @@ static uint16_t nvme_set_feature(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
switch (dw10) {
case NVME_TEMPERATURE_THRESHOLD:
n->features.temp_thresh = dw11;
+
+ if (n->features.temp_thresh <= n->temperature) {
+ nvme_enqueue_event(n, NVME_AER_TYPE_SMART,
+ NVME_AER_INFO_SMART_TEMP_THRESH, NVME_LOG_SMART_INFO);
+ }
+
break;
case NVME_VOLATILE_WRITE_CACHE:
@@ -1008,6 +1065,9 @@ static uint16_t nvme_set_feature(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
break;
case NVME_TIMESTAMP:
return nvme_set_feature_timestamp(n, cmd);
+ case NVME_ASYNCHRONOUS_EVENT_CONF:
+ n->features.async_config = dw11;
+ break;
default:
trace_nvme_err_invalid_setfeat(dw10);
return NVME_INVALID_FIELD | NVME_DNR;
@@ -1016,6 +1076,22 @@ static uint16_t nvme_set_feature(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
return NVME_SUCCESS;
}
+static uint16_t nvme_aer(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
+{
+ trace_nvme_aer(req->cid);
+
+ if (n->outstanding_aers > n->params.aerl) {
+ trace_nvme_aer_aerl_exceeded();
+ return NVME_AER_LIMIT_EXCEEDED;
+ }
+
+ n->aer_reqs[n->outstanding_aers] = req;
+ timer_mod(n->aer_timer, qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) + 500);
+ n->outstanding_aers++;
+
+ return NVME_NO_COMPLETE;
+}
+
static uint16_t nvme_admin_cmd(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
{
switch (cmd->opcode) {
@@ -1037,12 +1113,60 @@ static uint16_t nvme_admin_cmd(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
return nvme_set_feature(n, cmd, req);
case NVME_ADM_CMD_GET_FEATURES:
return nvme_get_feature(n, cmd, req);
+ case NVME_ADM_CMD_ASYNC_EV_REQ:
+ return nvme_aer(n, cmd, req);
default:
trace_nvme_err_invalid_admin_opc(cmd->opcode);
return NVME_INVALID_OPCODE | NVME_DNR;
}
}
+static void nvme_process_aers(void *opaque)
+{
+ NvmeCtrl *n = opaque;
+ NvmeAsyncEvent *event, *next;
+
+ trace_nvme_process_aers();
+
+ QTAILQ_FOREACH_SAFE(event, &n->aer_queue, entry, next) {
+ NvmeRequest *req;
+ NvmeAerResult *result;
+
+ /* can't post cqe if there is nothing to complete */
+ if (!n->outstanding_aers) {
+ trace_nvme_no_outstanding_aers();
+ break;
+ }
+
+ /* ignore if masked (cqe posted, but event not cleared) */
+ if (n->aer_mask & (1 << event->result.event_type)) {
+ trace_nvme_aer_masked(event->result.event_type, n->aer_mask);
+ continue;
+ }
+
+ QTAILQ_REMOVE(&n->aer_queue, event, entry);
+
+ n->aer_mask |= 1 << event->result.event_type;
+ n->aer_mask_queued &= ~(1 << event->result.event_type);
+ n->outstanding_aers--;
+
+ req = n->aer_reqs[n->outstanding_aers];
+
+ result = (NvmeAerResult *) &req->cqe.result;
+ result->event_type = event->result.event_type;
+ result->event_info = event->result.event_info;
+ result->log_page = event->result.log_page;
+ g_free(event);
+
+ req->status = NVME_SUCCESS;
+
+ trace_nvme_aer_post_cqe(result->event_type, result->event_info,
+ result->log_page);
+
+ nvme_enqueue_req_completion(&n->admin_cq, req);
+ }
+}
+
static void nvme_process_sq(void *opaque)
{
NvmeSQueue *sq = opaque;
@@ -1092,6 +1216,20 @@ static void nvme_clear_ctrl(NvmeCtrl *n)
}
}
+ if (n->aer_timer) {
+ timer_del(n->aer_timer);
+ timer_free(n->aer_timer);
+ n->aer_timer = NULL;
+ }
+
+ while (!QTAILQ_EMPTY(&n->aer_queue)) {
+ NvmeAsyncEvent *event = QTAILQ_FIRST(&n->aer_queue);
+ QTAILQ_REMOVE(&n->aer_queue, event, entry);
+ g_free(event);
+ }
+
+ n->outstanding_aers = 0;
+
blk_flush(n->conf.blk);
n->bar.cc = 0;
}
@@ -1188,6 +1326,9 @@ static int nvme_start_ctrl(NvmeCtrl *n)
nvme_set_timestamp(n, 0ULL);
+ n->aer_timer = timer_new_ns(QEMU_CLOCK_VIRTUAL, nvme_process_aers, n);
+ QTAILQ_INIT(&n->aer_queue);
+
return 0;
}
@@ -1380,6 +1521,13 @@ static void nvme_process_db(NvmeCtrl *n, hwaddr addr, int val)
"completion queue doorbell write"
" for nonexistent queue,"
" sqid=%"PRIu32", ignoring", qid);
+
+ if (n->outstanding_aers) {
+ nvme_enqueue_event(n, NVME_AER_TYPE_ERROR,
+ NVME_AER_INFO_ERR_INVALID_DB_REGISTER,
+ NVME_LOG_ERROR_INFO);
+ }
+
return;
}
@@ -1390,6 +1538,12 @@ static void nvme_process_db(NvmeCtrl *n, hwaddr addr, int val)
" beyond queue size, sqid=%"PRIu32","
" new_head=%"PRIu16", ignoring",
qid, new_head);
+
+ if (n->outstanding_aers) {
+ nvme_enqueue_event(n, NVME_AER_TYPE_ERROR,
+ NVME_AER_INFO_ERR_INVALID_DB_VALUE, NVME_LOG_ERROR_INFO);
+ }
+
return;
}
@@ -1418,6 +1572,13 @@ static void nvme_process_db(NvmeCtrl *n, hwaddr addr, int val)
"submission queue doorbell write"
" for nonexistent queue,"
" sqid=%"PRIu32", ignoring", qid);
+
+ if (n->outstanding_aers) {
+ nvme_enqueue_event(n, NVME_AER_TYPE_ERROR,
+ NVME_AER_INFO_ERR_INVALID_DB_REGISTER,
+ NVME_LOG_ERROR_INFO);
+ }
+
return;
}
@@ -1428,6 +1589,12 @@ static void nvme_process_db(NvmeCtrl *n, hwaddr addr, int val)
" beyond queue size, sqid=%"PRIu32","
" new_tail=%"PRIu16", ignoring",
qid, new_tail);
+
+ if (n->outstanding_aers) {
+ nvme_enqueue_event(n, NVME_AER_TYPE_ERROR,
+ NVME_AER_INFO_ERR_INVALID_DB_VALUE, NVME_LOG_ERROR_INFO);
+ }
+
return;
}
@@ -1524,6 +1691,7 @@ static void nvme_init_state(NvmeCtrl *n)
n->starttime_ms = qemu_clock_get_ms(QEMU_CLOCK_VIRTUAL);
n->temperature = NVME_TEMPERATURE;
n->features.temp_thresh = 0x14d;
+ n->aer_reqs = g_new0(NvmeRequest *, n->params.aerl + 1);
}
static void nvme_init_cmb(NvmeCtrl *n, PCIDevice *pci_dev)
@@ -1591,6 +1759,7 @@ static void nvme_init_ctrl(NvmeCtrl *n)
id->ver = cpu_to_le32(0x00010201);
id->oacs = cpu_to_le16(0);
id->acl = 3;
+ id->aerl = n->params.aerl;
id->frmw = 7 << 1;
id->lpa = 1 << 2;
id->elpe = n->params.elpe;
@@ -1678,6 +1847,7 @@ static void nvme_exit(PCIDevice *pci_dev)
g_free(n->cq);
g_free(n->sq);
g_free(n->elpes);
+ g_free(n->aer_reqs);
if (n->params.cmb_size_mb) {
g_free(n->cmbuf);
diff --git a/hw/block/nvme.h b/hw/block/nvme.h
index fcfd504e3f9f..3fc36f577b46 100644
--- a/hw/block/nvme.h
+++ b/hw/block/nvme.h
@@ -7,17 +7,19 @@
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_UINT8("elpe", _state, _props.elpe, 24)
+ DEFINE_PROP_UINT8("elpe", _state, _props.elpe, 24), \
+ DEFINE_PROP_UINT8("aerl", _state, _props.aerl, 3)
typedef struct NvmeParams {
char *serial;
uint32_t num_queues;
uint32_t cmb_size_mb;
uint8_t elpe;
+ uint8_t aerl;
} NvmeParams;
typedef struct NvmeAsyncEvent {
- QSIMPLEQ_ENTRY(NvmeAsyncEvent) entry;
+ QTAILQ_ENTRY(NvmeAsyncEvent) entry;
NvmeAerResult result;
} NvmeAsyncEvent;
@@ -89,6 +91,7 @@ typedef struct NvmeCtrl {
uint32_t num_namespaces;
uint32_t max_q_ents;
uint64_t ns_size;
+ uint8_t outstanding_aers;
uint32_t cmbsz;
uint32_t cmbloc;
uint8_t *cmbuf;
@@ -98,6 +101,12 @@ typedef struct NvmeCtrl {
uint64_t starttime_ms;
uint16_t temperature;
+ QEMUTimer *aer_timer;
+ uint8_t aer_mask;
+ uint8_t aer_mask_queued;
+ NvmeRequest **aer_reqs;
+ QTAILQ_HEAD(, NvmeAsyncEvent) aer_queue;
+
NvmeNamespace *namespaces;
NvmeSQueue **sq;
NvmeCQueue **cq;
diff --git a/hw/block/trace-events b/hw/block/trace-events
index a2c7919c861e..6ddb13d34061 100644
--- a/hw/block/trace-events
+++ b/hw/block/trace-events
@@ -47,6 +47,14 @@ nvme_setfeat_numq(int reqcq, int reqsq, int gotcq, int gotsq) "requested cq_coun
nvme_setfeat_timestamp(uint64_t ts) "set feature timestamp = 0x%"PRIx64""
nvme_getfeat_timestamp(uint64_t ts) "get feature timestamp = 0x%"PRIx64""
nvme_get_log(uint16_t cid, uint16_t lid, uint8_t rae, uint32_t len, uint64_t off) "cid %"PRIu16" lid 0x%"PRIx16" rae 0x%"PRIx8" len %"PRIu32" off %"PRIu64""
+nvme_process_aers(void) "processing aers"
+nvme_aer(uint16_t cid) "cid %"PRIu16""
+nvme_aer_aerl_exceeded(void) "aerl exceeded"
+nvme_aer_masked(uint8_t type, uint8_t mask) "type 0x%"PRIx8" mask 0x%"PRIx8""
+nvme_aer_post_cqe(uint8_t typ, uint8_t info, uint8_t log_page) "type 0x%"PRIx8" info 0x%"PRIx8" lid 0x%"PRIx8""
+nvme_enqueue_event(uint8_t typ, uint8_t info, uint8_t log_page) "type 0x%"PRIx8" info 0x%"PRIx8" lid 0x%"PRIx8""
+nvme_enqueue_event_masked(uint8_t typ) "type 0x%"PRIx8""
+nvme_no_outstanding_aers(void) "ignoring event; no outstanding AERs"
nvme_mmio_intm_set(uint64_t data, uint64_t new_mask) "wrote MMIO, interrupt mask set, data=0x%"PRIx64", new_mask=0x%"PRIx64""
nvme_mmio_intm_clr(uint64_t data, uint64_t new_mask) "wrote MMIO, interrupt mask clr, data=0x%"PRIx64", new_mask=0x%"PRIx64""
nvme_mmio_cfg(uint64_t data) "wrote MMIO, config controller config=0x%"PRIx64""
diff --git a/include/block/nvme.h b/include/block/nvme.h
index a088ec7d4e38..7f1832d531f0 100644
--- a/include/block/nvme.h
+++ b/include/block/nvme.h
@@ -386,8 +386,8 @@ enum NvmeAsyncEventRequest {
NVME_AER_TYPE_SMART = 1,
NVME_AER_TYPE_IO_SPECIFIC = 6,
NVME_AER_TYPE_VENDOR_SPECIFIC = 7,
- NVME_AER_INFO_ERR_INVALID_SQ = 0,
- NVME_AER_INFO_ERR_INVALID_DB = 1,
+ NVME_AER_INFO_ERR_INVALID_DB_REGISTER = 0,
+ NVME_AER_INFO_ERR_INVALID_DB_VALUE = 1,
NVME_AER_INFO_ERR_DIAG_FAIL = 2,
NVME_AER_INFO_ERR_PERS_INTERNAL_ERR = 3,
NVME_AER_INFO_ERR_TRANS_INTERNAL_ERR = 4,
--
2.23.0
^ permalink raw reply related [flat|nested] 52+ messages in thread* Re: [PATCH v2 09/20] nvme: add support for the asynchronous event request command
2019-10-15 10:38 ` [PATCH v2 09/20] nvme: add support for the asynchronous event request command Klaus Jensen
@ 2019-11-12 15:04 ` Beata Michalska
2019-11-19 19:51 ` Klaus Birkelund
0 siblings, 1 reply; 52+ messages in thread
From: Beata Michalska @ 2019-11-12 15:04 UTC (permalink / raw)
To: Klaus Jensen
Cc: Kevin Wolf, Fam Zheng, Javier Gonzalez, qemu-block, qemu-devel,
Max Reitz, Keith Busch, Paul Durrant, Stephen Bates
Hi Klaus,
On Tue, 15 Oct 2019 at 11:49, Klaus Jensen <its@irrelevant.dk> wrote:
>
> Required for compliance with NVMe revision 1.2.1. See NVM Express 1.2.1,
> Section 5.2 ("Asynchronous Event Request command").
>
> Mostly imported from Keith's qemu-nvme tree. Modified to not enqueue
> events if something of the same type is already queued (but not cleared
> by the host).
>
> Signed-off-by: Klaus Jensen <klaus.jensen@cnexlabs.com>
> ---
> hw/block/nvme.c | 180 ++++++++++++++++++++++++++++++++++++++++--
> hw/block/nvme.h | 13 ++-
> hw/block/trace-events | 8 ++
> include/block/nvme.h | 4 +-
> 4 files changed, 196 insertions(+), 9 deletions(-)
>
> diff --git a/hw/block/nvme.c b/hw/block/nvme.c
> index 4412a3bea3bc..5cdee37582f9 100644
> --- a/hw/block/nvme.c
> +++ b/hw/block/nvme.c
> @@ -334,6 +334,46 @@ static void nvme_enqueue_req_completion(NvmeCQueue *cq, NvmeRequest *req)
> timer_mod(cq->timer, qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) + 500);
> }
>
> +static void nvme_enqueue_event(NvmeCtrl *n, uint8_t event_type,
> + uint8_t event_info, uint8_t log_page)
> +{
> + NvmeAsyncEvent *event;
> +
> + trace_nvme_enqueue_event(event_type, event_info, log_page);
> +
> + /*
> + * Do not enqueue the event if something of this type is already queued.
> + * This bounds the size of the event queue and makes sure it does not grow
> + * indefinitely when events are not processed by the host (i.e. does not
> + * issue any AERs).
> + */
> + if (n->aer_mask_queued & (1 << event_type)) {
> + trace_nvme_enqueue_event_masked(event_type);
> + return;
> + }
> + n->aer_mask_queued |= (1 << event_type);
> +
> + event = g_new(NvmeAsyncEvent, 1);
> + event->result = (NvmeAerResult) {
> + .event_type = event_type,
> + .event_info = event_info,
> + .log_page = log_page,
> + };
> +
> + QTAILQ_INSERT_TAIL(&n->aer_queue, event, entry);
> +
> + timer_mod(n->aer_timer, qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) + 500);
> +}
> +
> +static void nvme_clear_events(NvmeCtrl *n, uint8_t event_type)
> +{
> + n->aer_mask &= ~(1 << event_type);
> + if (!QTAILQ_EMPTY(&n->aer_queue)) {
> + timer_mod(n->aer_timer,
> + qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) + 500);
> + }
> +}
> +
> static void nvme_rw_cb(void *opaque, int ret)
> {
> NvmeRequest *req = opaque;
> @@ -578,7 +618,7 @@ static uint16_t nvme_create_sq(NvmeCtrl *n, NvmeCmd *cmd)
> return NVME_SUCCESS;
> }
>
> -static uint16_t nvme_error_info(NvmeCtrl *n, NvmeCmd *cmd,
> +static uint16_t nvme_error_info(NvmeCtrl *n, NvmeCmd *cmd, uint8_t rae,
> uint32_t buf_len, uint64_t off, NvmeRequest *req)
> {
> uint32_t trans_len;
> @@ -591,12 +631,16 @@ static uint16_t nvme_error_info(NvmeCtrl *n, NvmeCmd *cmd,
>
> trans_len = MIN(sizeof(*n->elpes) * (n->params.elpe + 1) - off, buf_len);
>
> + if (!rae) {
> + nvme_clear_events(n, NVME_AER_TYPE_ERROR);
> + }
> +
> return nvme_dma_read_prp(n, (uint8_t *) n->elpes + off, trans_len, prp1,
> prp2);
> }
>
> -static uint16_t nvme_smart_info(NvmeCtrl *n, NvmeCmd *cmd, uint32_t buf_len,
> - uint64_t off, NvmeRequest *req)
> +static uint16_t nvme_smart_info(NvmeCtrl *n, NvmeCmd *cmd, uint8_t rae,
> + uint32_t buf_len, uint64_t off, NvmeRequest *req)
> {
> uint64_t prp1 = le64_to_cpu(cmd->prp1);
> uint64_t prp2 = le64_to_cpu(cmd->prp2);
> @@ -646,6 +690,10 @@ static uint16_t nvme_smart_info(NvmeCtrl *n, NvmeCmd *cmd, uint32_t buf_len,
> smart.power_on_hours[0] = cpu_to_le64(
> (((current_ms - n->starttime_ms) / 1000) / 60) / 60);
>
> + if (!rae) {
> + nvme_clear_events(n, NVME_AER_TYPE_SMART);
> + }
> +
> return nvme_dma_read_prp(n, (uint8_t *) &smart + off, trans_len, prp1,
> prp2);
> }
> @@ -698,9 +746,9 @@ static uint16_t nvme_get_log(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
>
> switch (lid) {
> case NVME_LOG_ERROR_INFO:
> - return nvme_error_info(n, cmd, len, off, req);
> + return nvme_error_info(n, cmd, rae, len, off, req);
> case NVME_LOG_SMART_INFO:
> - return nvme_smart_info(n, cmd, len, off, req);
> + return nvme_smart_info(n, cmd, rae, len, off, req);
> case NVME_LOG_FW_SLOT_INFO:
> return nvme_fw_log_info(n, cmd, len, off, req);
> default:
> @@ -958,6 +1006,9 @@ static uint16_t nvme_get_feature(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
> break;
> case NVME_TIMESTAMP:
> return nvme_get_feature_timestamp(n, cmd);
> + case NVME_ASYNCHRONOUS_EVENT_CONF:
> + result = cpu_to_le32(n->features.async_config);
> + break;
> default:
> trace_nvme_err_invalid_getfeat(dw10);
> return NVME_INVALID_FIELD | NVME_DNR;
> @@ -993,6 +1044,12 @@ static uint16_t nvme_set_feature(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
> switch (dw10) {
> case NVME_TEMPERATURE_THRESHOLD:
> n->features.temp_thresh = dw11;
> +
> + if (n->features.temp_thresh <= n->temperature) {
> + nvme_enqueue_event(n, NVME_AER_TYPE_SMART,
> + NVME_AER_INFO_SMART_TEMP_THRESH, NVME_LOG_SMART_INFO);
> + }
> +
> break;
>
> case NVME_VOLATILE_WRITE_CACHE:
> @@ -1008,6 +1065,9 @@ static uint16_t nvme_set_feature(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
> break;
> case NVME_TIMESTAMP:
> return nvme_set_feature_timestamp(n, cmd);
> + case NVME_ASYNCHRONOUS_EVENT_CONF:
> + n->features.async_config = dw11;
> + break;
> default:
> trace_nvme_err_invalid_setfeat(dw10);
> return NVME_INVALID_FIELD | NVME_DNR;
> @@ -1016,6 +1076,22 @@ static uint16_t nvme_set_feature(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
> return NVME_SUCCESS;
> }
>
> +static uint16_t nvme_aer(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
> +{
> + trace_nvme_aer(req->cid);
> +
> + if (n->outstanding_aers > n->params.aerl) {
> + trace_nvme_aer_aerl_exceeded();
> + return NVME_AER_LIMIT_EXCEEDED;
> + }
> +
> + n->aer_reqs[n->outstanding_aers] = req;
> + timer_mod(n->aer_timer, qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) + 500);
> + n->outstanding_aers++;
> +
> + return NVME_NO_COMPLETE;
> +}
> +
> static uint16_t nvme_admin_cmd(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
> {
> switch (cmd->opcode) {
> @@ -1037,12 +1113,60 @@ static uint16_t nvme_admin_cmd(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
> return nvme_set_feature(n, cmd, req);
> case NVME_ADM_CMD_GET_FEATURES:
> return nvme_get_feature(n, cmd, req);
> + case NVME_ADM_CMD_ASYNC_EV_REQ:
> + return nvme_aer(n, cmd, req);
> default:
> trace_nvme_err_invalid_admin_opc(cmd->opcode);
> return NVME_INVALID_OPCODE | NVME_DNR;
> }
> }
>
> +static void nvme_process_aers(void *opaque)
> +{
> + NvmeCtrl *n = opaque;
> + NvmeAsyncEvent *event, *next;
> +
> + trace_nvme_process_aers();
> +
> + QTAILQ_FOREACH_SAFE(event, &n->aer_queue, entry, next) {
> + NvmeRequest *req;
> + NvmeAerResult *result;
> +
> + /* can't post cqe if there is nothing to complete */
> + if (!n->outstanding_aers) {
> + trace_nvme_no_outstanding_aers();
> + break;
> + }
> +
> + /* ignore if masked (cqe posted, but event not cleared) */
> + if (n->aer_mask & (1 << event->result.event_type)) {
> + trace_nvme_aer_masked(event->result.event_type, n->aer_mask);
> + continue;
> + }
> +
> + QTAILQ_REMOVE(&n->aer_queue, event, entry);
> +
> + n->aer_mask |= 1 << event->result.event_type;
> + n->aer_mask_queued &= ~(1 << event->result.event_type);
> + n->outstanding_aers--;
> +
> + req = n->aer_reqs[n->outstanding_aers];
> +
> + result = (NvmeAerResult *) &req->cqe.result;
> + result->event_type = event->result.event_type;
> + result->event_info = event->result.event_info;
> + result->log_page = event->result.log_page;
> + g_free(event);
> +
> + req->status = NVME_SUCCESS;
> +
> + trace_nvme_aer_post_cqe(result->event_type, result->event_info,
> + result->log_page);
> +
> + nvme_enqueue_req_completion(&n->admin_cq, req);
> + }
> +}
> +
> static void nvme_process_sq(void *opaque)
> {
> NvmeSQueue *sq = opaque;
> @@ -1092,6 +1216,20 @@ static void nvme_clear_ctrl(NvmeCtrl *n)
> }
> }
>
> + if (n->aer_timer) {
> + timer_del(n->aer_timer);
> + timer_free(n->aer_timer);
> + n->aer_timer = NULL;
> + }
> +
> + while (!QTAILQ_EMPTY(&n->aer_queue)) {
> + NvmeAsyncEvent *event = QTAILQ_FIRST(&n->aer_queue);
> + QTAILQ_REMOVE(&n->aer_queue, event, entry);
> + g_free(event);
> + }
> +
> + n->outstanding_aers = 0;
> +
> blk_flush(n->conf.blk);
> n->bar.cc = 0;
> }
> @@ -1188,6 +1326,9 @@ static int nvme_start_ctrl(NvmeCtrl *n)
>
> nvme_set_timestamp(n, 0ULL);
>
> + n->aer_timer = timer_new_ns(QEMU_CLOCK_VIRTUAL, nvme_process_aers, n);
> + QTAILQ_INIT(&n->aer_queue);
> +
Is the timer really needed here ? The CEQ can be posted either when requested
by host through AER, if there are any pending events, or once the
event is triggered
and there are active AER's.
> return 0;
> }
>
> @@ -1380,6 +1521,13 @@ static void nvme_process_db(NvmeCtrl *n, hwaddr addr, int val)
> "completion queue doorbell write"
> " for nonexistent queue,"
> " sqid=%"PRIu32", ignoring", qid);
> +
> + if (n->outstanding_aers) {
> + nvme_enqueue_event(n, NVME_AER_TYPE_ERROR,
> + NVME_AER_INFO_ERR_INVALID_DB_REGISTER,
> + NVME_LOG_ERROR_INFO);
> + }
> +
This one (as well as cases below) might not be entirely right
according to the spec. If given event is enabled for asynchronous
reporting the controller should retain that even. In this case, the event
will be ignored as there is no pending request.
> return;
> }
>
> @@ -1390,6 +1538,12 @@ static void nvme_process_db(NvmeCtrl *n, hwaddr addr, int val)
> " beyond queue size, sqid=%"PRIu32","
> " new_head=%"PRIu16", ignoring",
> qid, new_head);
> +
> + if (n->outstanding_aers) {
> + nvme_enqueue_event(n, NVME_AER_TYPE_ERROR,
> + NVME_AER_INFO_ERR_INVALID_DB_VALUE, NVME_LOG_ERROR_INFO);
> + }
> +
> return;
> }
>
> @@ -1418,6 +1572,13 @@ static void nvme_process_db(NvmeCtrl *n, hwaddr addr, int val)
> "submission queue doorbell write"
> " for nonexistent queue,"
> " sqid=%"PRIu32", ignoring", qid);
> +
> + if (n->outstanding_aers) {
> + nvme_enqueue_event(n, NVME_AER_TYPE_ERROR,
> + NVME_AER_INFO_ERR_INVALID_DB_REGISTER,
> + NVME_LOG_ERROR_INFO);
> + }
> +
> return;
> }
>
> @@ -1428,6 +1589,12 @@ static void nvme_process_db(NvmeCtrl *n, hwaddr addr, int val)
> " beyond queue size, sqid=%"PRIu32","
> " new_tail=%"PRIu16", ignoring",
> qid, new_tail);
> +
> + if (n->outstanding_aers) {
> + nvme_enqueue_event(n, NVME_AER_TYPE_ERROR,
> + NVME_AER_INFO_ERR_INVALID_DB_VALUE, NVME_LOG_ERROR_INFO);
> + }
> +
> return;
> }
>
> @@ -1524,6 +1691,7 @@ static void nvme_init_state(NvmeCtrl *n)
> n->starttime_ms = qemu_clock_get_ms(QEMU_CLOCK_VIRTUAL);
> n->temperature = NVME_TEMPERATURE;
> n->features.temp_thresh = 0x14d;
> + n->aer_reqs = g_new0(NvmeRequest *, n->params.aerl + 1);
> }
>
> static void nvme_init_cmb(NvmeCtrl *n, PCIDevice *pci_dev)
> @@ -1591,6 +1759,7 @@ static void nvme_init_ctrl(NvmeCtrl *n)
> id->ver = cpu_to_le32(0x00010201);
> id->oacs = cpu_to_le16(0);
> id->acl = 3;
> + id->aerl = n->params.aerl;
What about the configuration for the asynchronous events ?
BR
Beata
> id->frmw = 7 << 1;
> id->lpa = 1 << 2;
> id->elpe = n->params.elpe;
> @@ -1678,6 +1847,7 @@ static void nvme_exit(PCIDevice *pci_dev)
> g_free(n->cq);
> g_free(n->sq);
> g_free(n->elpes);
> + g_free(n->aer_reqs);
>
> if (n->params.cmb_size_mb) {
> g_free(n->cmbuf);
> diff --git a/hw/block/nvme.h b/hw/block/nvme.h
> index fcfd504e3f9f..3fc36f577b46 100644
> --- a/hw/block/nvme.h
> +++ b/hw/block/nvme.h
> @@ -7,17 +7,19 @@
> 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_UINT8("elpe", _state, _props.elpe, 24)
> + DEFINE_PROP_UINT8("elpe", _state, _props.elpe, 24), \
> + DEFINE_PROP_UINT8("aerl", _state, _props.aerl, 3)
>
> typedef struct NvmeParams {
> char *serial;
> uint32_t num_queues;
> uint32_t cmb_size_mb;
> uint8_t elpe;
> + uint8_t aerl;
> } NvmeParams;
>
> typedef struct NvmeAsyncEvent {
> - QSIMPLEQ_ENTRY(NvmeAsyncEvent) entry;
> + QTAILQ_ENTRY(NvmeAsyncEvent) entry;
> NvmeAerResult result;
> } NvmeAsyncEvent;
>
> @@ -89,6 +91,7 @@ typedef struct NvmeCtrl {
> uint32_t num_namespaces;
> uint32_t max_q_ents;
> uint64_t ns_size;
> + uint8_t outstanding_aers;
> uint32_t cmbsz;
> uint32_t cmbloc;
> uint8_t *cmbuf;
> @@ -98,6 +101,12 @@ typedef struct NvmeCtrl {
> uint64_t starttime_ms;
> uint16_t temperature;
>
> + QEMUTimer *aer_timer;
> + uint8_t aer_mask;
> + uint8_t aer_mask_queued;
> + NvmeRequest **aer_reqs;
> + QTAILQ_HEAD(, NvmeAsyncEvent) aer_queue;
> +
> NvmeNamespace *namespaces;
> NvmeSQueue **sq;
> NvmeCQueue **cq;
> diff --git a/hw/block/trace-events b/hw/block/trace-events
> index a2c7919c861e..6ddb13d34061 100644
> --- a/hw/block/trace-events
> +++ b/hw/block/trace-events
> @@ -47,6 +47,14 @@ nvme_setfeat_numq(int reqcq, int reqsq, int gotcq, int gotsq) "requested cq_coun
> nvme_setfeat_timestamp(uint64_t ts) "set feature timestamp = 0x%"PRIx64""
> nvme_getfeat_timestamp(uint64_t ts) "get feature timestamp = 0x%"PRIx64""
> nvme_get_log(uint16_t cid, uint16_t lid, uint8_t rae, uint32_t len, uint64_t off) "cid %"PRIu16" lid 0x%"PRIx16" rae 0x%"PRIx8" len %"PRIu32" off %"PRIu64""
> +nvme_process_aers(void) "processing aers"
> +nvme_aer(uint16_t cid) "cid %"PRIu16""
> +nvme_aer_aerl_exceeded(void) "aerl exceeded"
> +nvme_aer_masked(uint8_t type, uint8_t mask) "type 0x%"PRIx8" mask 0x%"PRIx8""
> +nvme_aer_post_cqe(uint8_t typ, uint8_t info, uint8_t log_page) "type 0x%"PRIx8" info 0x%"PRIx8" lid 0x%"PRIx8""
> +nvme_enqueue_event(uint8_t typ, uint8_t info, uint8_t log_page) "type 0x%"PRIx8" info 0x%"PRIx8" lid 0x%"PRIx8""
> +nvme_enqueue_event_masked(uint8_t typ) "type 0x%"PRIx8""
> +nvme_no_outstanding_aers(void) "ignoring event; no outstanding AERs"
> nvme_mmio_intm_set(uint64_t data, uint64_t new_mask) "wrote MMIO, interrupt mask set, data=0x%"PRIx64", new_mask=0x%"PRIx64""
> nvme_mmio_intm_clr(uint64_t data, uint64_t new_mask) "wrote MMIO, interrupt mask clr, data=0x%"PRIx64", new_mask=0x%"PRIx64""
> nvme_mmio_cfg(uint64_t data) "wrote MMIO, config controller config=0x%"PRIx64""
> diff --git a/include/block/nvme.h b/include/block/nvme.h
> index a088ec7d4e38..7f1832d531f0 100644
> --- a/include/block/nvme.h
> +++ b/include/block/nvme.h
> @@ -386,8 +386,8 @@ enum NvmeAsyncEventRequest {
> NVME_AER_TYPE_SMART = 1,
> NVME_AER_TYPE_IO_SPECIFIC = 6,
> NVME_AER_TYPE_VENDOR_SPECIFIC = 7,
> - NVME_AER_INFO_ERR_INVALID_SQ = 0,
> - NVME_AER_INFO_ERR_INVALID_DB = 1,
> + NVME_AER_INFO_ERR_INVALID_DB_REGISTER = 0,
> + NVME_AER_INFO_ERR_INVALID_DB_VALUE = 1,
> NVME_AER_INFO_ERR_DIAG_FAIL = 2,
> NVME_AER_INFO_ERR_PERS_INTERNAL_ERR = 3,
> NVME_AER_INFO_ERR_TRANS_INTERNAL_ERR = 4,
> --
> 2.23.0
>
>
^ permalink raw reply [flat|nested] 52+ messages in thread* Re: [PATCH v2 09/20] nvme: add support for the asynchronous event request command
2019-11-12 15:04 ` Beata Michalska
@ 2019-11-19 19:51 ` Klaus Birkelund
2019-11-25 12:44 ` Beata Michalska
0 siblings, 1 reply; 52+ messages in thread
From: Klaus Birkelund @ 2019-11-19 19:51 UTC (permalink / raw)
To: Beata Michalska
Cc: Kevin Wolf, qemu-block, qemu-devel, Max Reitz, Paul Durrant, Keith Busch
On Tue, Nov 12, 2019 at 03:04:59PM +0000, Beata Michalska wrote:
> Hi Klaus,
>
> On Tue, 15 Oct 2019 at 11:49, Klaus Jensen <its@irrelevant.dk> wrote:
> > @@ -1188,6 +1326,9 @@ static int nvme_start_ctrl(NvmeCtrl *n)
> >
> > nvme_set_timestamp(n, 0ULL);
> >
> > + n->aer_timer = timer_new_ns(QEMU_CLOCK_VIRTUAL, nvme_process_aers, n);
> > + QTAILQ_INIT(&n->aer_queue);
> > +
>
> Is the timer really needed here ? The CEQ can be posted either when requested
> by host through AER, if there are any pending events, or once the
> event is triggered
> and there are active AER's.
>
I guess you are right. I mostly cribbed this from Keith's tree, but I
see no reason to keep the timer.
Keith, do you have any comments on this?
> > @@ -1380,6 +1521,13 @@ static void nvme_process_db(NvmeCtrl *n, hwaddr addr, int val)
> > "completion queue doorbell write"
> > " for nonexistent queue,"
> > " sqid=%"PRIu32", ignoring", qid);
> > +
> > + if (n->outstanding_aers) {
> > + nvme_enqueue_event(n, NVME_AER_TYPE_ERROR,
> > + NVME_AER_INFO_ERR_INVALID_DB_REGISTER,
> > + NVME_LOG_ERROR_INFO);
> > + }
> > +
> This one (as well as cases below) might not be entirely right
> according to the spec. If given event is enabled for asynchronous
> reporting the controller should retain that even. In this case, the event
> will be ignored as there is no pending request.
>
I understand these notifications to be special cases (i.e. they cannot
be enabled/disabled through the Asynchronous Event Configuration
feature). See Section 4.1 of NVM Express 1.2.1. The spec specifically
says that "... and an Asynchronous Event Request command is outstanding,
...).
> > @@ -1591,6 +1759,7 @@ static void nvme_init_ctrl(NvmeCtrl *n)
> > id->ver = cpu_to_le32(0x00010201);
> > id->oacs = cpu_to_le16(0);
> > id->acl = 3;
> > + id->aerl = n->params.aerl;
>
> What about the configuration for the asynchronous events ?
>
It will default to an AEC vector of 0 (everything disabled).
K
^ permalink raw reply [flat|nested] 52+ messages in thread* Re: [PATCH v2 09/20] nvme: add support for the asynchronous event request command
2019-11-19 19:51 ` Klaus Birkelund
@ 2019-11-25 12:44 ` Beata Michalska
0 siblings, 0 replies; 52+ messages in thread
From: Beata Michalska @ 2019-11-25 12:44 UTC (permalink / raw)
To: Klaus Birkelund
Cc: Kevin Wolf, qemu-block, qemu-devel, Max Reitz, Paul Durrant, Keith Busch
On Tue, 19 Nov 2019 at 19:51, Klaus Birkelund <its@irrelevant.dk> wrote:
>
> On Tue, Nov 12, 2019 at 03:04:59PM +0000, Beata Michalska wrote:
> > Hi Klaus,
> >
> > On Tue, 15 Oct 2019 at 11:49, Klaus Jensen <its@irrelevant.dk> wrote:
> > > @@ -1188,6 +1326,9 @@ static int nvme_start_ctrl(NvmeCtrl *n)
> > >
> > > nvme_set_timestamp(n, 0ULL);
> > >
> > > + n->aer_timer = timer_new_ns(QEMU_CLOCK_VIRTUAL, nvme_process_aers, n);
> > > + QTAILQ_INIT(&n->aer_queue);
> > > +
> >
> > Is the timer really needed here ? The CEQ can be posted either when requested
> > by host through AER, if there are any pending events, or once the
> > event is triggered
> > and there are active AER's.
> >
>
> I guess you are right. I mostly cribbed this from Keith's tree, but I
> see no reason to keep the timer.
>
> Keith, do you have any comments on this?
>
> > > @@ -1380,6 +1521,13 @@ static void nvme_process_db(NvmeCtrl *n, hwaddr addr, int val)
> > > "completion queue doorbell write"
> > > " for nonexistent queue,"
> > > " sqid=%"PRIu32", ignoring", qid);
> > > +
> > > + if (n->outstanding_aers) {
> > > + nvme_enqueue_event(n, NVME_AER_TYPE_ERROR,
> > > + NVME_AER_INFO_ERR_INVALID_DB_REGISTER,
> > > + NVME_LOG_ERROR_INFO);
> > > + }
> > > +
> > This one (as well as cases below) might not be entirely right
> > according to the spec. If given event is enabled for asynchronous
> > reporting the controller should retain that even. In this case, the event
> > will be ignored as there is no pending request.
> >
>
> I understand these notifications to be special cases (i.e. they cannot
> be enabled/disabled through the Asynchronous Event Configuration
> feature). See Section 4.1 of NVM Express 1.2.1. The spec specifically
> says that "... and an Asynchronous Event Request command is outstanding,
> ...).
>
OK, I have missed that one.
Thanks for the reference.
BR
Beata
> > > @@ -1591,6 +1759,7 @@ static void nvme_init_ctrl(NvmeCtrl *n)
> > > id->ver = cpu_to_le32(0x00010201);
> > > id->oacs = cpu_to_le16(0);
> > > id->acl = 3;
> > > + id->aerl = n->params.aerl;
> >
> > What about the configuration for the asynchronous events ?
> >
>
> It will default to an AEC vector of 0 (everything disabled).
>
>
> K
^ permalink raw reply [flat|nested] 52+ messages in thread
* [PATCH v2 10/20] nvme: add logging to error information log page
2019-10-15 10:38 [PATCH v2 00/20] nvme: support NVMe v1.3d, SGLs and multiple namespaces Klaus Jensen
` (8 preceding siblings ...)
2019-10-15 10:38 ` [PATCH v2 09/20] nvme: add support for the asynchronous event request command Klaus Jensen
@ 2019-10-15 10:38 ` Klaus Jensen
2019-10-15 10:38 ` [PATCH v2 11/20] nvme: add missing mandatory features Klaus Jensen
` (13 subsequent siblings)
23 siblings, 0 replies; 52+ messages in thread
From: Klaus Jensen @ 2019-10-15 10:38 UTC (permalink / raw)
To: qemu-block
Cc: Kevin Wolf, Fam Zheng, Javier Gonzalez, qemu-devel, Max Reitz,
Keith Busch, Paul Durrant, Stephen Bates
This adds the nvme_set_error_page function which allows errors to be
written to the error information log page. The functionality is largely
unused in the device, but with this in place we can at least try to push
new contributions to use it.
NOTE: In violation of the specification the Error Count field is *not*
retained across power off conditions because the device currently has no
place to store this kind of persistent state.
Cribbed from Keith's qemu-nvme tree.
Signed-off-by: Klaus Jensen <k.jensen@samsung.com>
---
hw/block/nvme.c | 22 ++++++++++++++++++++--
hw/block/nvme.h | 2 ++
2 files changed, 22 insertions(+), 2 deletions(-)
diff --git a/hw/block/nvme.c b/hw/block/nvme.c
index 5cdee37582f9..32381d7df655 100644
--- a/hw/block/nvme.c
+++ b/hw/block/nvme.c
@@ -161,6 +161,22 @@ static void nvme_irq_deassert(NvmeCtrl *n, NvmeCQueue *cq)
}
}
+static void nvme_set_error_page(NvmeCtrl *n, uint16_t sqid, uint16_t cid,
+ uint16_t status, uint16_t location, uint64_t lba, uint32_t nsid)
+{
+ NvmeErrorLog *elp;
+
+ elp = &n->elpes[n->elp_index];
+ elp->error_count = n->error_count++;
+ elp->sqid = sqid;
+ elp->cid = cid;
+ elp->status_field = status;
+ elp->param_error_location = location;
+ elp->lba = lba;
+ elp->nsid = nsid;
+ n->elp_index = (n->elp_index + 1) % n->params.elpe;
+}
+
static uint16_t nvme_map_prp(QEMUSGList *qsg, QEMUIOVector *iov, uint64_t prp1,
uint64_t prp2, uint32_t len, NvmeCtrl *n)
{
@@ -386,7 +402,9 @@ static void nvme_rw_cb(void *opaque, int ret)
req->status = NVME_SUCCESS;
} else {
block_acct_failed(blk_get_stats(n->conf.blk), &req->acct);
- req->status = NVME_INTERNAL_DEV_ERROR;
+ nvme_set_error_page(n, sq->sqid, cpu_to_le16(req->cid),
+ NVME_INTERNAL_DEV_ERROR, 0, 0, 1);
+ req->status = NVME_INTERNAL_DEV_ERROR | NVME_MORE;
}
if (req->has_sg) {
qemu_sglist_destroy(&req->qsg);
@@ -678,7 +696,7 @@ static uint16_t nvme_smart_info(NvmeCtrl *n, NvmeCmd *cmd, uint8_t rae,
smart.host_read_commands[0] = cpu_to_le64(read_commands);
smart.host_write_commands[0] = cpu_to_le64(write_commands);
- smart.number_of_error_log_entries[0] = cpu_to_le64(0);
+ smart.number_of_error_log_entries[0] = cpu_to_le64(n->error_count);
smart.temperature[0] = n->temperature & 0xff;
smart.temperature[1] = (n->temperature >> 8) & 0xff;
diff --git a/hw/block/nvme.h b/hw/block/nvme.h
index 3fc36f577b46..d74b0e0f9b2c 100644
--- a/hw/block/nvme.h
+++ b/hw/block/nvme.h
@@ -100,6 +100,8 @@ typedef struct NvmeCtrl {
uint64_t timestamp_set_qemu_clock_ms; /* QEMU clock time */
uint64_t starttime_ms;
uint16_t temperature;
+ uint8_t elp_index;
+ uint64_t error_count;
QEMUTimer *aer_timer;
uint8_t aer_mask;
--
2.23.0
^ permalink raw reply related [flat|nested] 52+ messages in thread* [PATCH v2 11/20] nvme: add missing mandatory features
2019-10-15 10:38 [PATCH v2 00/20] nvme: support NVMe v1.3d, SGLs and multiple namespaces Klaus Jensen
` (9 preceding siblings ...)
2019-10-15 10:38 ` [PATCH v2 10/20] nvme: add logging to error information log page Klaus Jensen
@ 2019-10-15 10:38 ` Klaus Jensen
2019-10-15 10:38 ` [PATCH v2 12/20] nvme: bump supported specification version to 1.3 Klaus Jensen
` (12 subsequent siblings)
23 siblings, 0 replies; 52+ messages in thread
From: Klaus Jensen @ 2019-10-15 10:38 UTC (permalink / raw)
To: qemu-block
Cc: Kevin Wolf, Fam Zheng, Javier Gonzalez, qemu-devel, Max Reitz,
Keith Busch, Paul Durrant, Stephen Bates
Add support for returning a resonable response to Get/Set Features of
mandatory features.
Signed-off-by: Klaus Jensen <klaus.jensen@cnexlabs.com>
---
hw/block/nvme.c | 51 ++++++++++++++++++++++++++++++++++++++++---
hw/block/trace-events | 2 ++
include/block/nvme.h | 3 ++-
3 files changed, 52 insertions(+), 4 deletions(-)
diff --git a/hw/block/nvme.c b/hw/block/nvme.c
index 32381d7df655..e7d46dcc6afe 100644
--- a/hw/block/nvme.c
+++ b/hw/block/nvme.c
@@ -1007,12 +1007,24 @@ static uint16_t nvme_get_feature_timestamp(NvmeCtrl *n, NvmeCmd *cmd)
static uint16_t nvme_get_feature(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
{
uint32_t dw10 = le32_to_cpu(cmd->cdw10);
+ uint32_t dw11 = le32_to_cpu(cmd->cdw11);
uint32_t result;
+ trace_nvme_getfeat(dw10);
+
switch (dw10) {
+ case NVME_ARBITRATION:
+ result = cpu_to_le32(n->features.arbitration);
+ break;
+ case NVME_POWER_MANAGEMENT:
+ result = cpu_to_le32(n->features.power_mgmt);
+ break;
case NVME_TEMPERATURE_THRESHOLD:
result = cpu_to_le32(n->features.temp_thresh);
break;
+ case NVME_ERROR_RECOVERY:
+ result = cpu_to_le32(n->features.err_rec);
+ break;
case NVME_VOLATILE_WRITE_CACHE:
result = blk_enable_write_cache(n->conf.blk);
trace_nvme_getfeat_vwcache(result ? "enabled" : "disabled");
@@ -1024,6 +1036,19 @@ static uint16_t nvme_get_feature(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
break;
case NVME_TIMESTAMP:
return nvme_get_feature_timestamp(n, cmd);
+ case NVME_INTERRUPT_COALESCING:
+ result = cpu_to_le32(n->features.int_coalescing);
+ break;
+ case NVME_INTERRUPT_VECTOR_CONF:
+ if ((dw11 & 0xffff) > n->params.num_queues) {
+ return NVME_INVALID_FIELD | NVME_DNR;
+ }
+
+ result = cpu_to_le32(n->features.int_vector_config[dw11 & 0xffff]);
+ break;
+ case NVME_WRITE_ATOMICITY:
+ result = cpu_to_le32(n->features.write_atomicity);
+ break;
case NVME_ASYNCHRONOUS_EVENT_CONF:
result = cpu_to_le32(n->features.async_config);
break;
@@ -1059,6 +1084,8 @@ static uint16_t nvme_set_feature(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
uint32_t dw10 = le32_to_cpu(cmd->cdw10);
uint32_t dw11 = le32_to_cpu(cmd->cdw11);
+ trace_nvme_setfeat(dw10, dw11);
+
switch (dw10) {
case NVME_TEMPERATURE_THRESHOLD:
n->features.temp_thresh = dw11;
@@ -1086,6 +1113,13 @@ static uint16_t nvme_set_feature(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
case NVME_ASYNCHRONOUS_EVENT_CONF:
n->features.async_config = dw11;
break;
+ case NVME_ARBITRATION:
+ case NVME_POWER_MANAGEMENT:
+ case NVME_ERROR_RECOVERY:
+ case NVME_INTERRUPT_COALESCING:
+ case NVME_INTERRUPT_VECTOR_CONF:
+ case NVME_WRITE_ATOMICITY:
+ return NVME_FEAT_NOT_CHANGABLE | NVME_DNR;
default:
trace_nvme_err_invalid_setfeat(dw10);
return NVME_INVALID_FIELD | NVME_DNR;
@@ -1709,6 +1743,14 @@ static void nvme_init_state(NvmeCtrl *n)
n->starttime_ms = qemu_clock_get_ms(QEMU_CLOCK_VIRTUAL);
n->temperature = NVME_TEMPERATURE;
n->features.temp_thresh = 0x14d;
+ n->features.int_vector_config = g_malloc0_n(n->params.num_queues,
+ sizeof(*n->features.int_vector_config));
+
+ /* disable coalescing (not supported) */
+ for (int i = 0; i < n->params.num_queues; i++) {
+ n->features.int_vector_config[i] = i | (1 << 16);
+ }
+
n->aer_reqs = g_new0(NvmeRequest *, n->params.aerl + 1);
}
@@ -1786,15 +1828,17 @@ static void nvme_init_ctrl(NvmeCtrl *n)
id->nn = cpu_to_le32(n->num_namespaces);
id->oncs = cpu_to_le16(NVME_ONCS_WRITE_ZEROS | NVME_ONCS_TIMESTAMP);
+
+ if (blk_enable_write_cache(n->conf.blk)) {
+ id->vwc = 1;
+ }
+
strcpy((char *) id->subnqn, "nqn.2019-08.org.qemu:");
pstrcat((char *) id->subnqn, sizeof(id->subnqn), n->params.serial);
id->psd[0].mp = cpu_to_le16(0x9c4);
id->psd[0].enlat = cpu_to_le32(0x10);
id->psd[0].exlat = cpu_to_le32(0x4);
- if (blk_enable_write_cache(n->conf.blk)) {
- id->vwc = 1;
- }
n->bar.cap = 0;
NVME_CAP_SET_MQES(n->bar.cap, 0x7ff);
@@ -1866,6 +1910,7 @@ static void nvme_exit(PCIDevice *pci_dev)
g_free(n->sq);
g_free(n->elpes);
g_free(n->aer_reqs);
+ g_free(n->features.int_vector_config);
if (n->params.cmb_size_mb) {
g_free(n->cmbuf);
diff --git a/hw/block/trace-events b/hw/block/trace-events
index 6ddb13d34061..a20a68d85d5a 100644
--- a/hw/block/trace-events
+++ b/hw/block/trace-events
@@ -41,6 +41,8 @@ nvme_del_cq(uint16_t cqid) "deleted completion queue, sqid=%"PRIu16""
nvme_identify_ctrl(void) "identify controller"
nvme_identify_ns(uint16_t ns) "identify namespace, nsid=%"PRIu16""
nvme_identify_nslist(uint16_t ns) "identify namespace list, nsid=%"PRIu16""
+nvme_getfeat(uint32_t fid) "fid 0x%"PRIx32""
+nvme_setfeat(uint32_t fid, uint32_t val) "fid 0x%"PRIx32" val 0x%"PRIx32""
nvme_getfeat_vwcache(const char* result) "get feature volatile write cache, result=%s"
nvme_getfeat_numq(int result) "get feature number of queues, result=%d"
nvme_setfeat_numq(int reqcq, int reqsq, int gotcq, int gotsq) "requested cq_count=%d sq_count=%d, responding with cq_count=%d sq_count=%d"
diff --git a/include/block/nvme.h b/include/block/nvme.h
index 7f1832d531f0..9726839f75bb 100644
--- a/include/block/nvme.h
+++ b/include/block/nvme.h
@@ -445,7 +445,8 @@ enum NvmeStatusCodes {
NVME_FW_REQ_RESET = 0x010b,
NVME_INVALID_QUEUE_DEL = 0x010c,
NVME_FID_NOT_SAVEABLE = 0x010d,
- NVME_FID_NOT_NSID_SPEC = 0x010f,
+ NVME_FEAT_NOT_CHANGABLE = 0x010e,
+ NVME_FEAT_NOT_NSID_SPEC = 0x010f,
NVME_FW_REQ_SUSYSTEM_RESET = 0x0110,
NVME_CONFLICTING_ATTRS = 0x0180,
NVME_INVALID_PROT_INFO = 0x0181,
--
2.23.0
^ permalink raw reply related [flat|nested] 52+ messages in thread* [PATCH v2 12/20] nvme: bump supported specification version to 1.3
2019-10-15 10:38 [PATCH v2 00/20] nvme: support NVMe v1.3d, SGLs and multiple namespaces Klaus Jensen
` (10 preceding siblings ...)
2019-10-15 10:38 ` [PATCH v2 11/20] nvme: add missing mandatory features Klaus Jensen
@ 2019-10-15 10:38 ` Klaus Jensen
2019-11-12 15:05 ` Beata Michalska
2019-10-15 10:38 ` [PATCH v2 13/20] nvme: refactor prp mapping Klaus Jensen
` (11 subsequent siblings)
23 siblings, 1 reply; 52+ messages in thread
From: Klaus Jensen @ 2019-10-15 10:38 UTC (permalink / raw)
To: qemu-block
Cc: Kevin Wolf, Fam Zheng, Javier Gonzalez, qemu-devel, Max Reitz,
Keith Busch, Paul Durrant, Stephen Bates
Add the new Namespace Identification Descriptor List (CNS 03h) and track
creation of queues to enable the controller to return Command Sequence
Error if Set Features is called for Number of Queues after any queues
have been created.
Signed-off-by: Klaus Jensen <klaus.jensen@cnexlabs.com>
---
hw/block/nvme.c | 82 +++++++++++++++++++++++++++++++++++--------
hw/block/nvme.h | 1 +
hw/block/trace-events | 8 +++--
include/block/nvme.h | 30 +++++++++++++---
4 files changed, 100 insertions(+), 21 deletions(-)
diff --git a/hw/block/nvme.c b/hw/block/nvme.c
index e7d46dcc6afe..1e2320b38b14 100644
--- a/hw/block/nvme.c
+++ b/hw/block/nvme.c
@@ -9,20 +9,22 @@
*/
/**
- * Reference Specification: NVM Express 1.2.1
+ * Reference Specification: NVM Express 1.3d
*
* https://nvmexpress.org/resources/specifications/
*/
/**
* Usage: add options:
- * -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]>
+ * -drive file=<file>,if=none,id=<drive_id>
+ * -device nvme,drive=<drive_id>,serial=<serial>,id=<id[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.
+ * Advanced optional options:
+ *
+ * num_queues=<uint32> : Maximum number of IO Queues.
+ * Default: 64
+ * cmb_size_mb=<uint32> : Size of Controller Memory Buffer in MBs.
+ * Default: 0 (disabled)
*/
#include "qemu/osdep.h"
@@ -345,6 +347,8 @@ static void nvme_post_cqes(void *opaque)
static void nvme_enqueue_req_completion(NvmeCQueue *cq, NvmeRequest *req)
{
assert(cq->cqid == req->sq->cqid);
+
+ trace_nvme_enqueue_req_completion(req->cid, cq->cqid, req->status);
QTAILQ_REMOVE(&req->sq->out_req_list, req, entry);
QTAILQ_INSERT_TAIL(&cq->req_list, req, entry);
timer_mod(cq->timer, qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) + 500);
@@ -530,6 +534,7 @@ static void nvme_free_sq(NvmeSQueue *sq, NvmeCtrl *n)
if (sq->sqid) {
g_free(sq);
}
+ n->qs_created--;
}
static uint16_t nvme_del_sq(NvmeCtrl *n, NvmeCmd *cmd)
@@ -596,6 +601,7 @@ static void nvme_init_sq(NvmeSQueue *sq, NvmeCtrl *n, uint64_t dma_addr,
cq = n->cq[cqid];
QTAILQ_INSERT_TAIL(&(cq->sq_list), sq, entry);
n->sq[sqid] = sq;
+ n->qs_created++;
}
static uint16_t nvme_create_sq(NvmeCtrl *n, NvmeCmd *cmd)
@@ -742,7 +748,8 @@ static uint16_t nvme_get_log(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
uint32_t dw11 = le32_to_cpu(cmd->cdw11);
uint32_t dw12 = le32_to_cpu(cmd->cdw12);
uint32_t dw13 = le32_to_cpu(cmd->cdw13);
- uint16_t lid = dw10 & 0xff;
+ uint8_t lid = dw10 & 0xff;
+ uint8_t lsp = (dw10 >> 8) & 0xf;
uint8_t rae = (dw10 >> 15) & 0x1;
uint32_t numdl, numdu;
uint64_t off, lpol, lpou;
@@ -760,7 +767,7 @@ static uint16_t nvme_get_log(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
return NVME_INVALID_FIELD | NVME_DNR;
}
- trace_nvme_get_log(req->cid, lid, rae, len, off);
+ trace_nvme_get_log(req->cid, lid, lsp, rae, len, off);
switch (lid) {
case NVME_LOG_ERROR_INFO:
@@ -784,6 +791,7 @@ static void nvme_free_cq(NvmeCQueue *cq, NvmeCtrl *n)
if (cq->cqid) {
g_free(cq);
}
+ n->qs_created--;
}
static uint16_t nvme_del_cq(NvmeCtrl *n, NvmeCmd *cmd)
@@ -824,6 +832,7 @@ static void nvme_init_cq(NvmeCQueue *cq, NvmeCtrl *n, uint64_t dma_addr,
msix_vector_use(&n->parent_obj, cq->vector);
n->cq[cqid] = cq;
cq->timer = timer_new_ns(QEMU_CLOCK_VIRTUAL, nvme_post_cqes, cq);
+ n->qs_created++;
}
static uint16_t nvme_create_cq(NvmeCtrl *n, NvmeCmd *cmd)
@@ -897,7 +906,7 @@ static uint16_t nvme_identify_ns(NvmeCtrl *n, NvmeIdentify *c)
prp1, prp2);
}
-static uint16_t nvme_identify_nslist(NvmeCtrl *n, NvmeIdentify *c)
+static uint16_t nvme_identify_ns_list(NvmeCtrl *n, NvmeIdentify *c)
{
static const int data_len = 4 * KiB;
uint32_t min_nsid = le32_to_cpu(c->nsid);
@@ -907,7 +916,7 @@ 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_identify_ns_list(min_nsid);
list = g_malloc0(data_len);
for (i = 0; i < n->num_namespaces; i++) {
@@ -924,6 +933,41 @@ static uint16_t nvme_identify_nslist(NvmeCtrl *n, NvmeIdentify *c)
return ret;
}
+static uint16_t nvme_identify_ns_descr_list(NvmeCtrl *n, NvmeCmd *c)
+{
+ static const int len = 4096;
+
+ struct ns_descr {
+ uint8_t nidt;
+ uint8_t nidl;
+ uint8_t rsvd2[2];
+ uint8_t nid[16];
+ };
+
+ uint32_t nsid = le32_to_cpu(c->nsid);
+ uint64_t prp1 = le64_to_cpu(c->prp1);
+ uint64_t prp2 = le64_to_cpu(c->prp2);
+
+ struct ns_descr *list;
+ uint16_t ret;
+
+ trace_nvme_identify_ns_descr_list(nsid);
+
+ if (unlikely(nsid == 0 || nsid > n->num_namespaces)) {
+ trace_nvme_err_invalid_ns(nsid, n->num_namespaces);
+ return NVME_INVALID_NSID | NVME_DNR;
+ }
+
+ list = g_malloc0(len);
+ list->nidt = 0x3;
+ list->nidl = 0x10;
+ *(uint32_t *) &list->nid[12] = cpu_to_be32(nsid);
+
+ ret = nvme_dma_read_prp(n, (uint8_t *) list, len, prp1, prp2);
+ g_free(list);
+ return ret;
+}
+
static uint16_t nvme_identify(NvmeCtrl *n, NvmeCmd *cmd)
{
NvmeIdentify *c = (NvmeIdentify *)cmd;
@@ -934,7 +978,9 @@ static uint16_t nvme_identify(NvmeCtrl *n, NvmeCmd *cmd)
case 0x01:
return nvme_identify_ctrl(n, c);
case 0x02:
- return nvme_identify_nslist(n, c);
+ return nvme_identify_ns_list(n, c);
+ case 0x03:
+ return nvme_identify_ns_descr_list(n, cmd);
default:
trace_nvme_err_invalid_identify_cns(le32_to_cpu(c->cns));
return NVME_INVALID_FIELD | NVME_DNR;
@@ -1101,6 +1147,14 @@ 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:
+ if (n->qs_created > 2) {
+ return NVME_CMD_SEQ_ERROR | NVME_DNR;
+ }
+
+ if ((dw11 & 0xffff) == 0xffff || ((dw11 >> 16) & 0xffff) == 0xffff) {
+ return NVME_INVALID_FIELD | NVME_DNR;
+ }
+
trace_nvme_setfeat_numq((dw11 & 0xFFFF) + 1,
((dw11 >> 16) & 0xFFFF) + 1,
n->params.num_queues - 1,
@@ -1816,7 +1870,7 @@ static void nvme_init_ctrl(NvmeCtrl *n)
id->ieee[0] = 0x00;
id->ieee[1] = 0x02;
id->ieee[2] = 0xb3;
- id->ver = cpu_to_le32(0x00010201);
+ id->ver = cpu_to_le32(0x00010300);
id->oacs = cpu_to_le16(0);
id->acl = 3;
id->aerl = n->params.aerl;
@@ -1847,7 +1901,7 @@ static void nvme_init_ctrl(NvmeCtrl *n)
NVME_CAP_SET_CSS(n->bar.cap, 1);
NVME_CAP_SET_MPSMAX(n->bar.cap, 4);
- n->bar.vs = 0x00010201;
+ n->bar.vs = 0x00010300;
n->bar.intmc = n->bar.intms = 0;
}
diff --git a/hw/block/nvme.h b/hw/block/nvme.h
index d74b0e0f9b2c..3f7bd627e824 100644
--- a/hw/block/nvme.h
+++ b/hw/block/nvme.h
@@ -102,6 +102,7 @@ typedef struct NvmeCtrl {
uint16_t temperature;
uint8_t elp_index;
uint64_t error_count;
+ uint32_t qs_created;
QEMUTimer *aer_timer;
uint8_t aer_mask;
diff --git a/hw/block/trace-events b/hw/block/trace-events
index a20a68d85d5a..f62fa99dc2cd 100644
--- a/hw/block/trace-events
+++ b/hw/block/trace-events
@@ -39,8 +39,9 @@ nvme_create_cq(uint64_t addr, uint16_t cqid, uint16_t vector, uint16_t size, uin
nvme_del_sq(uint16_t qid) "deleting submission queue sqid=%"PRIu16""
nvme_del_cq(uint16_t cqid) "deleted completion queue, sqid=%"PRIu16""
nvme_identify_ctrl(void) "identify controller"
-nvme_identify_ns(uint16_t ns) "identify namespace, nsid=%"PRIu16""
-nvme_identify_nslist(uint16_t ns) "identify namespace list, nsid=%"PRIu16""
+nvme_identify_ns(uint32_t ns) "nsid %"PRIu32""
+nvme_identify_ns_list(uint32_t ns) "nsid %"PRIu32""
+nvme_identify_ns_descr_list(uint32_t ns) "nsid %"PRIu32""
nvme_getfeat(uint32_t fid) "fid 0x%"PRIx32""
nvme_setfeat(uint32_t fid, uint32_t val) "fid 0x%"PRIx32" val 0x%"PRIx32""
nvme_getfeat_vwcache(const char* result) "get feature volatile write cache, result=%s"
@@ -48,12 +49,13 @@ nvme_getfeat_numq(int result) "get feature number of queues, result=%d"
nvme_setfeat_numq(int reqcq, int reqsq, int gotcq, int gotsq) "requested cq_count=%d sq_count=%d, responding with cq_count=%d sq_count=%d"
nvme_setfeat_timestamp(uint64_t ts) "set feature timestamp = 0x%"PRIx64""
nvme_getfeat_timestamp(uint64_t ts) "get feature timestamp = 0x%"PRIx64""
-nvme_get_log(uint16_t cid, uint16_t lid, uint8_t rae, uint32_t len, uint64_t off) "cid %"PRIu16" lid 0x%"PRIx16" rae 0x%"PRIx8" len %"PRIu32" off %"PRIu64""
+nvme_get_log(uint16_t cid, uint16_t lid, uint8_t lsp, uint8_t rae, uint32_t len, uint64_t off) "cid %"PRIu16" lid 0x%"PRIx16" lsp 0x%"PRIx8" rae 0x%"PRIx8" len %"PRIu32" off %"PRIu64""
nvme_process_aers(void) "processing aers"
nvme_aer(uint16_t cid) "cid %"PRIu16""
nvme_aer_aerl_exceeded(void) "aerl exceeded"
nvme_aer_masked(uint8_t type, uint8_t mask) "type 0x%"PRIx8" mask 0x%"PRIx8""
nvme_aer_post_cqe(uint8_t typ, uint8_t info, uint8_t log_page) "type 0x%"PRIx8" info 0x%"PRIx8" lid 0x%"PRIx8""
+nvme_enqueue_req_completion(uint16_t cid, uint16_t cqid, uint16_t status) "cid %"PRIu16" cqid %"PRIu16" status 0x%"PRIx16""
nvme_enqueue_event(uint8_t typ, uint8_t info, uint8_t log_page) "type 0x%"PRIx8" info 0x%"PRIx8" lid 0x%"PRIx8""
nvme_enqueue_event_masked(uint8_t typ) "type 0x%"PRIx8""
nvme_no_outstanding_aers(void) "ignoring event; no outstanding AERs"
diff --git a/include/block/nvme.h b/include/block/nvme.h
index 9726839f75bb..f0f5728b5ec4 100644
--- a/include/block/nvme.h
+++ b/include/block/nvme.h
@@ -550,7 +550,9 @@ typedef struct NvmeIdCtrl {
uint32_t rtd3e;
uint32_t oaes;
uint32_t ctratt;
- uint8_t rsvd255[156];
+ uint8_t rsvd111[12];
+ uint8_t fguid[16];
+ uint8_t rsvd255[128];
uint16_t oacs;
uint8_t acl;
uint8_t aerl;
@@ -568,9 +570,15 @@ typedef struct NvmeIdCtrl {
uint8_t tnvmcap[16];
uint8_t unvmcap[16];
uint32_t rpmbs;
- uint8_t rsvd319[4];
+ uint16_t edstt;
+ uint8_t dsto;
+ uint8_t fwug;
uint16_t kas;
- uint8_t rsvd511[190];
+ uint16_t hctma;
+ uint16_t mntmt;
+ uint16_t mxtmt;
+ uint32_t sanicap;
+ uint8_t rsvd511[180];
uint8_t sqes;
uint8_t cqes;
uint16_t maxcmd;
@@ -678,7 +686,21 @@ typedef struct NvmeIdNs {
uint8_t mc;
uint8_t dpc;
uint8_t dps;
- uint8_t res30[98];
+ uint8_t nmic;
+ uint8_t rescap;
+ uint8_t fpi;
+ uint8_t dlfeat;
+ uint16_t nawun;
+ uint16_t nawupf;
+ uint16_t nacwu;
+ uint16_t nabsn;
+ uint16_t nabo;
+ uint16_t nabspf;
+ uint16_t noiob;
+ uint8_t nvmcap[16];
+ uint8_t resv103[40];
+ uint8_t nguid[16];
+ uint64_t eui64;
NvmeLBAF lbaf[16];
uint8_t res192[192];
uint8_t vs[3712];
--
2.23.0
^ permalink raw reply related [flat|nested] 52+ messages in thread* Re: [PATCH v2 12/20] nvme: bump supported specification version to 1.3
2019-10-15 10:38 ` [PATCH v2 12/20] nvme: bump supported specification version to 1.3 Klaus Jensen
@ 2019-11-12 15:05 ` Beata Michalska
2019-11-18 9:48 ` Klaus Birkelund
0 siblings, 1 reply; 52+ messages in thread
From: Beata Michalska @ 2019-11-12 15:05 UTC (permalink / raw)
To: Klaus Jensen
Cc: Kevin Wolf, Fam Zheng, Javier Gonzalez, qemu-block, qemu-devel,
Max Reitz, Keith Busch, Paul Durrant, Stephen Bates
Hi Klaus,
On Tue, 15 Oct 2019 at 11:52, Klaus Jensen <its@irrelevant.dk> wrote:
>
> Add the new Namespace Identification Descriptor List (CNS 03h) and track
> creation of queues to enable the controller to return Command Sequence
> Error if Set Features is called for Number of Queues after any queues
> have been created.
>
> Signed-off-by: Klaus Jensen <klaus.jensen@cnexlabs.com>
> ---
> hw/block/nvme.c | 82 +++++++++++++++++++++++++++++++++++--------
> hw/block/nvme.h | 1 +
> hw/block/trace-events | 8 +++--
> include/block/nvme.h | 30 +++++++++++++---
> 4 files changed, 100 insertions(+), 21 deletions(-)
>
> diff --git a/hw/block/nvme.c b/hw/block/nvme.c
> index e7d46dcc6afe..1e2320b38b14 100644
> --- a/hw/block/nvme.c
> +++ b/hw/block/nvme.c
> @@ -9,20 +9,22 @@
> */
>
> /**
> - * Reference Specification: NVM Express 1.2.1
> + * Reference Specification: NVM Express 1.3d
> *
> * https://nvmexpress.org/resources/specifications/
> */
>
> /**
> * Usage: add options:
> - * -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]>
> + * -drive file=<file>,if=none,id=<drive_id>
> + * -device nvme,drive=<drive_id>,serial=<serial>,id=<id[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.
> + * Advanced optional options:
> + *
> + * num_queues=<uint32> : Maximum number of IO Queues.
> + * Default: 64
> + * cmb_size_mb=<uint32> : Size of Controller Memory Buffer in MBs.
> + * Default: 0 (disabled)
> */
>
> #include "qemu/osdep.h"
> @@ -345,6 +347,8 @@ static void nvme_post_cqes(void *opaque)
> static void nvme_enqueue_req_completion(NvmeCQueue *cq, NvmeRequest *req)
> {
> assert(cq->cqid == req->sq->cqid);
> +
> + trace_nvme_enqueue_req_completion(req->cid, cq->cqid, req->status);
> QTAILQ_REMOVE(&req->sq->out_req_list, req, entry);
> QTAILQ_INSERT_TAIL(&cq->req_list, req, entry);
> timer_mod(cq->timer, qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) + 500);
> @@ -530,6 +534,7 @@ static void nvme_free_sq(NvmeSQueue *sq, NvmeCtrl *n)
> if (sq->sqid) {
> g_free(sq);
> }
> + n->qs_created--;
> }
>
> static uint16_t nvme_del_sq(NvmeCtrl *n, NvmeCmd *cmd)
> @@ -596,6 +601,7 @@ static void nvme_init_sq(NvmeSQueue *sq, NvmeCtrl *n, uint64_t dma_addr,
> cq = n->cq[cqid];
> QTAILQ_INSERT_TAIL(&(cq->sq_list), sq, entry);
> n->sq[sqid] = sq;
> + n->qs_created++;
> }
>
> static uint16_t nvme_create_sq(NvmeCtrl *n, NvmeCmd *cmd)
> @@ -742,7 +748,8 @@ static uint16_t nvme_get_log(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
> uint32_t dw11 = le32_to_cpu(cmd->cdw11);
> uint32_t dw12 = le32_to_cpu(cmd->cdw12);
> uint32_t dw13 = le32_to_cpu(cmd->cdw13);
> - uint16_t lid = dw10 & 0xff;
> + uint8_t lid = dw10 & 0xff;
> + uint8_t lsp = (dw10 >> 8) & 0xf;
> uint8_t rae = (dw10 >> 15) & 0x1;
> uint32_t numdl, numdu;
> uint64_t off, lpol, lpou;
> @@ -760,7 +767,7 @@ static uint16_t nvme_get_log(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
> return NVME_INVALID_FIELD | NVME_DNR;
> }
>
> - trace_nvme_get_log(req->cid, lid, rae, len, off);
> + trace_nvme_get_log(req->cid, lid, lsp, rae, len, off);
>
> switch (lid) {
> case NVME_LOG_ERROR_INFO:
> @@ -784,6 +791,7 @@ static void nvme_free_cq(NvmeCQueue *cq, NvmeCtrl *n)
> if (cq->cqid) {
> g_free(cq);
> }
> + n->qs_created--;
> }
>
> static uint16_t nvme_del_cq(NvmeCtrl *n, NvmeCmd *cmd)
> @@ -824,6 +832,7 @@ static void nvme_init_cq(NvmeCQueue *cq, NvmeCtrl *n, uint64_t dma_addr,
> msix_vector_use(&n->parent_obj, cq->vector);
> n->cq[cqid] = cq;
> cq->timer = timer_new_ns(QEMU_CLOCK_VIRTUAL, nvme_post_cqes, cq);
> + n->qs_created++;
> }
>
> static uint16_t nvme_create_cq(NvmeCtrl *n, NvmeCmd *cmd)
> @@ -897,7 +906,7 @@ static uint16_t nvme_identify_ns(NvmeCtrl *n, NvmeIdentify *c)
> prp1, prp2);
> }
>
> -static uint16_t nvme_identify_nslist(NvmeCtrl *n, NvmeIdentify *c)
> +static uint16_t nvme_identify_ns_list(NvmeCtrl *n, NvmeIdentify *c)
> {
> static const int data_len = 4 * KiB;
> uint32_t min_nsid = le32_to_cpu(c->nsid);
> @@ -907,7 +916,7 @@ 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_identify_ns_list(min_nsid);
>
> list = g_malloc0(data_len);
> for (i = 0; i < n->num_namespaces; i++) {
> @@ -924,6 +933,41 @@ static uint16_t nvme_identify_nslist(NvmeCtrl *n, NvmeIdentify *c)
> return ret;
> }
>
> +static uint16_t nvme_identify_ns_descr_list(NvmeCtrl *n, NvmeCmd *c)
> +{
> + static const int len = 4096;
> +
> + struct ns_descr {
> + uint8_t nidt;
> + uint8_t nidl;
> + uint8_t rsvd2[2];
> + uint8_t nid[16];
> + };
> +
> + uint32_t nsid = le32_to_cpu(c->nsid);
> + uint64_t prp1 = le64_to_cpu(c->prp1);
> + uint64_t prp2 = le64_to_cpu(c->prp2);
> +
> + struct ns_descr *list;
> + uint16_t ret;
> +
> + trace_nvme_identify_ns_descr_list(nsid);
> +
> + if (unlikely(nsid == 0 || nsid > n->num_namespaces)) {
> + trace_nvme_err_invalid_ns(nsid, n->num_namespaces);
> + return NVME_INVALID_NSID | NVME_DNR;
> + }
> +
In theory this should abort the command for inactive NSIDs as well.
But I guess this will come later on.
> + list = g_malloc0(len);
> + list->nidt = 0x3;
> + list->nidl = 0x10;
> + *(uint32_t *) &list->nid[12] = cpu_to_be32(nsid);
> +
Might be worth to add some comment here -> as per the NGUID/EUI64 format.
Also those are not specified currently in the namespace identity data structure.
> + ret = nvme_dma_read_prp(n, (uint8_t *) list, len, prp1, prp2);
> + g_free(list);
> + return ret;
> +}
> +
> static uint16_t nvme_identify(NvmeCtrl *n, NvmeCmd *cmd)
> {
> NvmeIdentify *c = (NvmeIdentify *)cmd;
> @@ -934,7 +978,9 @@ static uint16_t nvme_identify(NvmeCtrl *n, NvmeCmd *cmd)
> case 0x01:
> return nvme_identify_ctrl(n, c);
> case 0x02:
> - return nvme_identify_nslist(n, c);
> + return nvme_identify_ns_list(n, c);
> + case 0x03:
> + return nvme_identify_ns_descr_list(n, cmd);
> default:
> trace_nvme_err_invalid_identify_cns(le32_to_cpu(c->cns));
> return NVME_INVALID_FIELD | NVME_DNR;
> @@ -1101,6 +1147,14 @@ 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:
> + if (n->qs_created > 2) {
> + return NVME_CMD_SEQ_ERROR | NVME_DNR;
> + }
> +
I am not sure this is entirely correct as the spec says:
"if any I/O Submission and/or Completion Queues (...)"
so it might be enough to have a single queue created
for this command to be valid.
Also I think that the condition here is to make sure that the number
of queues requested is being set once at init phase. Currently this will
allow the setting to happen if there is no active queue -> so at any
point of time (provided the condition mentioned). I might be wrong here
but it seems that what we need is a single status saying any queue
has been created prior to the Set Feature command at all
> + if ((dw11 & 0xffff) == 0xffff || ((dw11 >> 16) & 0xffff) == 0xffff) {
> + return NVME_INVALID_FIELD | NVME_DNR;
> + }
> +
> trace_nvme_setfeat_numq((dw11 & 0xFFFF) + 1,
> ((dw11 >> 16) & 0xFFFF) + 1,
> n->params.num_queues - 1,
> @@ -1816,7 +1870,7 @@ static void nvme_init_ctrl(NvmeCtrl *n)
> id->ieee[0] = 0x00;
> id->ieee[1] = 0x02;
> id->ieee[2] = 0xb3;
> - id->ver = cpu_to_le32(0x00010201);
> + id->ver = cpu_to_le32(0x00010300);
> id->oacs = cpu_to_le16(0);
> id->acl = 3;
> id->aerl = n->params.aerl;
> @@ -1847,7 +1901,7 @@ static void nvme_init_ctrl(NvmeCtrl *n)
> NVME_CAP_SET_CSS(n->bar.cap, 1);
> NVME_CAP_SET_MPSMAX(n->bar.cap, 4);
>
> - n->bar.vs = 0x00010201;
> + n->bar.vs = 0x00010300;
> n->bar.intmc = n->bar.intms = 0;
> }
>
> diff --git a/hw/block/nvme.h b/hw/block/nvme.h
> index d74b0e0f9b2c..3f7bd627e824 100644
> --- a/hw/block/nvme.h
> +++ b/hw/block/nvme.h
> @@ -102,6 +102,7 @@ typedef struct NvmeCtrl {
> uint16_t temperature;
> uint8_t elp_index;
> uint64_t error_count;
> + uint32_t qs_created;
>
> QEMUTimer *aer_timer;
> uint8_t aer_mask;
> diff --git a/hw/block/trace-events b/hw/block/trace-events
> index a20a68d85d5a..f62fa99dc2cd 100644
> --- a/hw/block/trace-events
> +++ b/hw/block/trace-events
> @@ -39,8 +39,9 @@ nvme_create_cq(uint64_t addr, uint16_t cqid, uint16_t vector, uint16_t size, uin
> nvme_del_sq(uint16_t qid) "deleting submission queue sqid=%"PRIu16""
> nvme_del_cq(uint16_t cqid) "deleted completion queue, sqid=%"PRIu16""
> nvme_identify_ctrl(void) "identify controller"
> -nvme_identify_ns(uint16_t ns) "identify namespace, nsid=%"PRIu16""
> -nvme_identify_nslist(uint16_t ns) "identify namespace list, nsid=%"PRIu16""
> +nvme_identify_ns(uint32_t ns) "nsid %"PRIu32""
> +nvme_identify_ns_list(uint32_t ns) "nsid %"PRIu32""
> +nvme_identify_ns_descr_list(uint32_t ns) "nsid %"PRIu32""
> nvme_getfeat(uint32_t fid) "fid 0x%"PRIx32""
> nvme_setfeat(uint32_t fid, uint32_t val) "fid 0x%"PRIx32" val 0x%"PRIx32""
> nvme_getfeat_vwcache(const char* result) "get feature volatile write cache, result=%s"
> @@ -48,12 +49,13 @@ nvme_getfeat_numq(int result) "get feature number of queues, result=%d"
> nvme_setfeat_numq(int reqcq, int reqsq, int gotcq, int gotsq) "requested cq_count=%d sq_count=%d, responding with cq_count=%d sq_count=%d"
> nvme_setfeat_timestamp(uint64_t ts) "set feature timestamp = 0x%"PRIx64""
> nvme_getfeat_timestamp(uint64_t ts) "get feature timestamp = 0x%"PRIx64""
> -nvme_get_log(uint16_t cid, uint16_t lid, uint8_t rae, uint32_t len, uint64_t off) "cid %"PRIu16" lid 0x%"PRIx16" rae 0x%"PRIx8" len %"PRIu32" off %"PRIu64""
> +nvme_get_log(uint16_t cid, uint16_t lid, uint8_t lsp, uint8_t rae, uint32_t len, uint64_t off) "cid %"PRIu16" lid 0x%"PRIx16" lsp 0x%"PRIx8" rae 0x%"PRIx8" len %"PRIu32" off %"PRIu64""
> nvme_process_aers(void) "processing aers"
> nvme_aer(uint16_t cid) "cid %"PRIu16""
> nvme_aer_aerl_exceeded(void) "aerl exceeded"
> nvme_aer_masked(uint8_t type, uint8_t mask) "type 0x%"PRIx8" mask 0x%"PRIx8""
> nvme_aer_post_cqe(uint8_t typ, uint8_t info, uint8_t log_page) "type 0x%"PRIx8" info 0x%"PRIx8" lid 0x%"PRIx8""
> +nvme_enqueue_req_completion(uint16_t cid, uint16_t cqid, uint16_t status) "cid %"PRIu16" cqid %"PRIu16" status 0x%"PRIx16""
> nvme_enqueue_event(uint8_t typ, uint8_t info, uint8_t log_page) "type 0x%"PRIx8" info 0x%"PRIx8" lid 0x%"PRIx8""
> nvme_enqueue_event_masked(uint8_t typ) "type 0x%"PRIx8""
> nvme_no_outstanding_aers(void) "ignoring event; no outstanding AERs"
> diff --git a/include/block/nvme.h b/include/block/nvme.h
> index 9726839f75bb..f0f5728b5ec4 100644
> --- a/include/block/nvme.h
> +++ b/include/block/nvme.h
> @@ -550,7 +550,9 @@ typedef struct NvmeIdCtrl {
> uint32_t rtd3e;
> uint32_t oaes;
> uint32_t ctratt;
> - uint8_t rsvd255[156];
> + uint8_t rsvd111[12];
> + uint8_t fguid[16];
> + uint8_t rsvd255[128];
> uint16_t oacs;
> uint8_t acl;
> uint8_t aerl;
> @@ -568,9 +570,15 @@ typedef struct NvmeIdCtrl {
> uint8_t tnvmcap[16];
> uint8_t unvmcap[16];
> uint32_t rpmbs;
> - uint8_t rsvd319[4];
> + uint16_t edstt;
> + uint8_t dsto;
> + uint8_t fwug;
> uint16_t kas;
> - uint8_t rsvd511[190];
> + uint16_t hctma;
> + uint16_t mntmt;
> + uint16_t mxtmt;
> + uint32_t sanicap;
> + uint8_t rsvd511[180];
> uint8_t sqes;
> uint8_t cqes;
> uint16_t maxcmd;
> @@ -678,7 +686,21 @@ typedef struct NvmeIdNs {
> uint8_t mc;
> uint8_t dpc;
> uint8_t dps;
> - uint8_t res30[98];
> + uint8_t nmic;
> + uint8_t rescap;
> + uint8_t fpi;
> + uint8_t dlfeat;
> + uint16_t nawun;
> + uint16_t nawupf;
> + uint16_t nacwu;
> + uint16_t nabsn;
> + uint16_t nabo;
> + uint16_t nabspf;
> + uint16_t noiob;
> + uint8_t nvmcap[16];
> + uint8_t resv103[40];
> + uint8_t nguid[16];
> + uint64_t eui64;
> NvmeLBAF lbaf[16];
> uint8_t res192[192];
> uint8_t vs[3712];
> --
> 2.23.0
>
>
Small note: this patch seems to be introducing more changes
than specified in the commit message and especially the subject. Might
be worth to extend it a bit.
BR
Beata
^ permalink raw reply [flat|nested] 52+ messages in thread* Re: [PATCH v2 12/20] nvme: bump supported specification version to 1.3
2019-11-12 15:05 ` Beata Michalska
@ 2019-11-18 9:48 ` Klaus Birkelund
2019-11-25 12:13 ` Beata Michalska
0 siblings, 1 reply; 52+ messages in thread
From: Klaus Birkelund @ 2019-11-18 9:48 UTC (permalink / raw)
To: Beata Michalska
Cc: Kevin Wolf, Fam Zheng, qemu-block, qemu-devel, Max Reitz,
Paul Durrant, Keith Busch
On Tue, Nov 12, 2019 at 03:05:06PM +0000, Beata Michalska wrote:
> Hi Klaus,
>
> On Tue, 15 Oct 2019 at 11:52, Klaus Jensen <its@irrelevant.dk> wrote:
> >
> > +static uint16_t nvme_identify_ns_descr_list(NvmeCtrl *n, NvmeCmd *c)
> > +{
> > + static const int len = 4096;
> > +
> > + struct ns_descr {
> > + uint8_t nidt;
> > + uint8_t nidl;
> > + uint8_t rsvd2[2];
> > + uint8_t nid[16];
> > + };
> > +
> > + uint32_t nsid = le32_to_cpu(c->nsid);
> > + uint64_t prp1 = le64_to_cpu(c->prp1);
> > + uint64_t prp2 = le64_to_cpu(c->prp2);
> > +
> > + struct ns_descr *list;
> > + uint16_t ret;
> > +
> > + trace_nvme_identify_ns_descr_list(nsid);
> > +
> > + if (unlikely(nsid == 0 || nsid > n->num_namespaces)) {
> > + trace_nvme_err_invalid_ns(nsid, n->num_namespaces);
> > + return NVME_INVALID_NSID | NVME_DNR;
> > + }
> > +
> In theory this should abort the command for inactive NSIDs as well.
> But I guess this will come later on.
>
At this point in the series, the device does not support multiple
namespaces anyway and num_namespaces is always 1. But this has also been
reported seperately in relation the patch adding multiple namespaces and
is fixed in v3.
> > + list = g_malloc0(len);
> > + list->nidt = 0x3;
> > + list->nidl = 0x10;
> > + *(uint32_t *) &list->nid[12] = cpu_to_be32(nsid);
> > +
> Might be worth to add some comment here -> as per the NGUID/EUI64 format.
> Also those are not specified currently in the namespace identity data structure.
>
I'll add a comment for why the Namespace UUID is set to this value here.
The NGUID/EUI64 fields are not set in the namespace identity data
structure as they are not required. See the descriptions of NGUID and
EUI64. Here for NGUID:
"The controller shall specify a globally unique namespace identifier
in this field, the EUI64 field, or a Namespace UUID in the Namespace
Identification Descriptor..."
Here, I chose to provide it in the Namespace Identification Descriptor
(by setting `list->nidt = 0x3`).
> > + ret = nvme_dma_read_prp(n, (uint8_t *) list, len, prp1, prp2);
> > + g_free(list);
> > + return ret;
> > +}
> > +
> > static uint16_t nvme_identify(NvmeCtrl *n, NvmeCmd *cmd)
> > {
> > NvmeIdentify *c = (NvmeIdentify *)cmd;
> > @@ -934,7 +978,9 @@ static uint16_t nvme_identify(NvmeCtrl *n, NvmeCmd *cmd)
> > case 0x01:
> > return nvme_identify_ctrl(n, c);
> > case 0x02:
> > - return nvme_identify_nslist(n, c);
> > + return nvme_identify_ns_list(n, c);
> > + case 0x03:
> > + return nvme_identify_ns_descr_list(n, cmd);
> > default:
> > trace_nvme_err_invalid_identify_cns(le32_to_cpu(c->cns));
> > return NVME_INVALID_FIELD | NVME_DNR;
> > @@ -1101,6 +1147,14 @@ 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:
> > + if (n->qs_created > 2) {
> > + return NVME_CMD_SEQ_ERROR | NVME_DNR;
> > + }
> > +
> I am not sure this is entirely correct as the spec says:
> "if any I/O Submission and/or Completion Queues (...)"
> so it might be enough to have a single queue created
> for this command to be valid.
> Also I think that the condition here is to make sure that the number
> of queues requested is being set once at init phase. Currently this will
> allow the setting to happen if there is no active queue -> so at any
> point of time (provided the condition mentioned). I might be wrong here
> but it seems that what we need is a single status saying any queue
> has been created prior to the Set Feature command at all
>
Internally, the admin queue pair is counted in qs_created, which is the
reason for checking if is above 2. The admin queues are created when the
controller is enabled (mmio write to the EN register in CC).
I'll add a comment about that - I see why it is unclear.
>
> Small note: this patch seems to be introducing more changes
> than specified in the commit message and especially the subject. Might
> be worth to extend it a bit.
>
You are right. I'll split it up.
^ permalink raw reply [flat|nested] 52+ messages in thread* Re: [PATCH v2 12/20] nvme: bump supported specification version to 1.3
2019-11-18 9:48 ` Klaus Birkelund
@ 2019-11-25 12:13 ` Beata Michalska
2019-11-26 8:40 ` Klaus Birkelund
0 siblings, 1 reply; 52+ messages in thread
From: Beata Michalska @ 2019-11-25 12:13 UTC (permalink / raw)
To: Klaus Birkelund
Cc: Kevin Wolf, Fam Zheng, qemu-block, qemu-devel, Max Reitz,
Paul Durrant, Keith Busch
On Mon, 18 Nov 2019 at 09:48, Klaus Birkelund <its@irrelevant.dk> wrote:
>
> On Tue, Nov 12, 2019 at 03:05:06PM +0000, Beata Michalska wrote:
> > Hi Klaus,
> >
> > On Tue, 15 Oct 2019 at 11:52, Klaus Jensen <its@irrelevant.dk> wrote:
> > >
> > > +static uint16_t nvme_identify_ns_descr_list(NvmeCtrl *n, NvmeCmd *c)
> > > +{
> > > + static const int len = 4096;
> > > +
> > > + struct ns_descr {
> > > + uint8_t nidt;
> > > + uint8_t nidl;
> > > + uint8_t rsvd2[2];
> > > + uint8_t nid[16];
> > > + };
> > > +
> > > + uint32_t nsid = le32_to_cpu(c->nsid);
> > > + uint64_t prp1 = le64_to_cpu(c->prp1);
> > > + uint64_t prp2 = le64_to_cpu(c->prp2);
> > > +
> > > + struct ns_descr *list;
> > > + uint16_t ret;
> > > +
> > > + trace_nvme_identify_ns_descr_list(nsid);
> > > +
> > > + if (unlikely(nsid == 0 || nsid > n->num_namespaces)) {
> > > + trace_nvme_err_invalid_ns(nsid, n->num_namespaces);
> > > + return NVME_INVALID_NSID | NVME_DNR;
> > > + }
> > > +
> > In theory this should abort the command for inactive NSIDs as well.
> > But I guess this will come later on.
> >
>
> At this point in the series, the device does not support multiple
> namespaces anyway and num_namespaces is always 1. But this has also been
> reported seperately in relation the patch adding multiple namespaces and
> is fixed in v3.
>
> > > + list = g_malloc0(len);
> > > + list->nidt = 0x3;
> > > + list->nidl = 0x10;
> > > + *(uint32_t *) &list->nid[12] = cpu_to_be32(nsid);
> > > +
> > Might be worth to add some comment here -> as per the NGUID/EUI64 format.
> > Also those are not specified currently in the namespace identity data structure.
> >
>
> I'll add a comment for why the Namespace UUID is set to this value here.
> The NGUID/EUI64 fields are not set in the namespace identity data
> structure as they are not required. See the descriptions of NGUID and
> EUI64. Here for NGUID:
>
> "The controller shall specify a globally unique namespace identifier
> in this field, the EUI64 field, or a Namespace UUID in the Namespace
> Identification Descriptor..."
>
> Here, I chose to provide it in the Namespace Identification Descriptor
> (by setting `list->nidt = 0x3`).
>
> > > + ret = nvme_dma_read_prp(n, (uint8_t *) list, len, prp1, prp2);
> > > + g_free(list);
> > > + return ret;
> > > +}
> > > +
> > > static uint16_t nvme_identify(NvmeCtrl *n, NvmeCmd *cmd)
> > > {
> > > NvmeIdentify *c = (NvmeIdentify *)cmd;
> > > @@ -934,7 +978,9 @@ static uint16_t nvme_identify(NvmeCtrl *n, NvmeCmd *cmd)
> > > case 0x01:
> > > return nvme_identify_ctrl(n, c);
> > > case 0x02:
> > > - return nvme_identify_nslist(n, c);
> > > + return nvme_identify_ns_list(n, c);
> > > + case 0x03:
> > > + return nvme_identify_ns_descr_list(n, cmd);
> > > default:
> > > trace_nvme_err_invalid_identify_cns(le32_to_cpu(c->cns));
> > > return NVME_INVALID_FIELD | NVME_DNR;
> > > @@ -1101,6 +1147,14 @@ 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:
> > > + if (n->qs_created > 2) {
> > > + return NVME_CMD_SEQ_ERROR | NVME_DNR;
> > > + }
> > > +
> > I am not sure this is entirely correct as the spec says:
> > "if any I/O Submission and/or Completion Queues (...)"
> > so it might be enough to have a single queue created
> > for this command to be valid.
> > Also I think that the condition here is to make sure that the number
> > of queues requested is being set once at init phase. Currently this will
> > allow the setting to happen if there is no active queue -> so at any
> > point of time (provided the condition mentioned). I might be wrong here
> > but it seems that what we need is a single status saying any queue
> > has been created prior to the Set Feature command at all
> >
>
> Internally, the admin queue pair is counted in qs_created, which is the
> reason for checking if is above 2. The admin queues are created when the
> controller is enabled (mmio write to the EN register in CC).
>
> I'll add a comment about that - I see why it is unclear.
>
Ok, so indeed I have missed the fact that the admin queues are being tracked by
'qs_created'. Still, I might be wrong, but, it is enough to create I/O
submission queue and delete it and the code will allow the command to proceed
Whereas the spec says :
"If a Set Features command is issued for this feature after creation of
any I/O Submission and/or I/O Completion Queues, then the Set Features
command shall fail with status code of Command Sequence Error"
I might be misreading it though but it is not entirely clear to me whether
this is : at least one queue create ... or created and in use.
But I guess that is really minor.
BR
Beata
> >
> > Small note: this patch seems to be introducing more changes
> > than specified in the commit message and especially the subject. Might
> > be worth to extend it a bit.
> >
>
> You are right. I'll split it up.
^ permalink raw reply [flat|nested] 52+ messages in thread* Re: [PATCH v2 12/20] nvme: bump supported specification version to 1.3
2019-11-25 12:13 ` Beata Michalska
@ 2019-11-26 8:40 ` Klaus Birkelund
0 siblings, 0 replies; 52+ messages in thread
From: Klaus Birkelund @ 2019-11-26 8:40 UTC (permalink / raw)
To: Beata Michalska
Cc: Kevin Wolf, Keith Busch, qemu-devel, qemu-block, Max Reitz
On Mon, Nov 25, 2019 at 12:13:15PM +0000, Beata Michalska wrote:
> On Mon, 18 Nov 2019 at 09:48, Klaus Birkelund <its@irrelevant.dk> wrote:
> >
> > On Tue, Nov 12, 2019 at 03:05:06PM +0000, Beata Michalska wrote:
> > > Hi Klaus,
> > >
> > > On Tue, 15 Oct 2019 at 11:52, Klaus Jensen <its@irrelevant.dk> wrote:
> > > >
> > > > +static uint16_t nvme_identify_ns_descr_list(NvmeCtrl *n, NvmeCmd *c)
> > > > +{
> > > > + static const int len = 4096;
> > > > +
> > > > + struct ns_descr {
> > > > + uint8_t nidt;
> > > > + uint8_t nidl;
> > > > + uint8_t rsvd2[2];
> > > > + uint8_t nid[16];
> > > > + };
> > > > +
> > > > + uint32_t nsid = le32_to_cpu(c->nsid);
> > > > + uint64_t prp1 = le64_to_cpu(c->prp1);
> > > > + uint64_t prp2 = le64_to_cpu(c->prp2);
> > > > +
> > > > + struct ns_descr *list;
> > > > + uint16_t ret;
> > > > +
> > > > + trace_nvme_identify_ns_descr_list(nsid);
> > > > +
> > > > + if (unlikely(nsid == 0 || nsid > n->num_namespaces)) {
> > > > + trace_nvme_err_invalid_ns(nsid, n->num_namespaces);
> > > > + return NVME_INVALID_NSID | NVME_DNR;
> > > > + }
> > > > +
> > > In theory this should abort the command for inactive NSIDs as well.
> > > But I guess this will come later on.
> > >
> >
> > At this point in the series, the device does not support multiple
> > namespaces anyway and num_namespaces is always 1. But this has also been
> > reported seperately in relation the patch adding multiple namespaces and
> > is fixed in v3.
> >
> > > > + list = g_malloc0(len);
> > > > + list->nidt = 0x3;
> > > > + list->nidl = 0x10;
> > > > + *(uint32_t *) &list->nid[12] = cpu_to_be32(nsid);
> > > > +
> > > Might be worth to add some comment here -> as per the NGUID/EUI64 format.
> > > Also those are not specified currently in the namespace identity data structure.
> > >
> >
> > I'll add a comment for why the Namespace UUID is set to this value here.
> > The NGUID/EUI64 fields are not set in the namespace identity data
> > structure as they are not required. See the descriptions of NGUID and
> > EUI64. Here for NGUID:
> >
> > "The controller shall specify a globally unique namespace identifier
> > in this field, the EUI64 field, or a Namespace UUID in the Namespace
> > Identification Descriptor..."
> >
> > Here, I chose to provide it in the Namespace Identification Descriptor
> > (by setting `list->nidt = 0x3`).
> >
> > > > + ret = nvme_dma_read_prp(n, (uint8_t *) list, len, prp1, prp2);
> > > > + g_free(list);
> > > > + return ret;
> > > > +}
> > > > +
> > > > static uint16_t nvme_identify(NvmeCtrl *n, NvmeCmd *cmd)
> > > > {
> > > > NvmeIdentify *c = (NvmeIdentify *)cmd;
> > > > @@ -934,7 +978,9 @@ static uint16_t nvme_identify(NvmeCtrl *n, NvmeCmd *cmd)
> > > > case 0x01:
> > > > return nvme_identify_ctrl(n, c);
> > > > case 0x02:
> > > > - return nvme_identify_nslist(n, c);
> > > > + return nvme_identify_ns_list(n, c);
> > > > + case 0x03:
> > > > + return nvme_identify_ns_descr_list(n, cmd);
> > > > default:
> > > > trace_nvme_err_invalid_identify_cns(le32_to_cpu(c->cns));
> > > > return NVME_INVALID_FIELD | NVME_DNR;
> > > > @@ -1101,6 +1147,14 @@ 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:
> > > > + if (n->qs_created > 2) {
> > > > + return NVME_CMD_SEQ_ERROR | NVME_DNR;
> > > > + }
> > > > +
> > > I am not sure this is entirely correct as the spec says:
> > > "if any I/O Submission and/or Completion Queues (...)"
> > > so it might be enough to have a single queue created
> > > for this command to be valid.
> > > Also I think that the condition here is to make sure that the number
> > > of queues requested is being set once at init phase. Currently this will
> > > allow the setting to happen if there is no active queue -> so at any
> > > point of time (provided the condition mentioned). I might be wrong here
> > > but it seems that what we need is a single status saying any queue
> > > has been created prior to the Set Feature command at all
> > >
> >
> > Internally, the admin queue pair is counted in qs_created, which is the
> > reason for checking if is above 2. The admin queues are created when the
> > controller is enabled (mmio write to the EN register in CC).
> >
> > I'll add a comment about that - I see why it is unclear.
> >
>
> Ok, so indeed I have missed the fact that the admin queues are being tracked by
> 'qs_created'. Still, I might be wrong, but, it is enough to create I/O
> submission queue and delete it and the code will allow the command to proceed
> Whereas the spec says :
> "If a Set Features command is issued for this feature after creation of
> any I/O Submission and/or I/O Completion Queues, then the Set Features
> command shall fail with status code of Command Sequence Error"
>
> I might be misreading it though but it is not entirely clear to me whether
> this is : at least one queue create ... or created and in use.
>
> But I guess that is really minor.
>
Ohh! I see. Yes you are right. "This feature shall only be issued during
initialization prior to creation of any I/O Submission and/or Completion
Queues.".
To me it looks like the controller shall not allow the Set Feature
command again until after a controller reset. Then we also don't need
the counter, but just a flag to indicate if any I/O queue has been
configured.
I've fixed that up.
^ permalink raw reply [flat|nested] 52+ messages in thread
* [PATCH v2 13/20] nvme: refactor prp mapping
2019-10-15 10:38 [PATCH v2 00/20] nvme: support NVMe v1.3d, SGLs and multiple namespaces Klaus Jensen
` (11 preceding siblings ...)
2019-10-15 10:38 ` [PATCH v2 12/20] nvme: bump supported specification version to 1.3 Klaus Jensen
@ 2019-10-15 10:38 ` Klaus Jensen
2019-11-12 15:23 ` Beata Michalska
2019-10-15 10:38 ` [PATCH v2 14/20] nvme: allow multiple aios per command Klaus Jensen
` (10 subsequent siblings)
23 siblings, 1 reply; 52+ messages in thread
From: Klaus Jensen @ 2019-10-15 10:38 UTC (permalink / raw)
To: qemu-block
Cc: Kevin Wolf, Fam Zheng, Javier Gonzalez, qemu-devel, Max Reitz,
Keith Busch, Paul Durrant, Stephen Bates
Instead of handling both QSGs and IOVs in multiple places, simply use
QSGs everywhere by assuming that the request does not involve the
controller memory buffer (CMB). If the request is found to involve the
CMB, convert the QSG to an IOV and issue the I/O. The QSG is converted
to an IOV by the dma helpers anyway, so the CMB path is not unfairly
affected by this simplifying change.
As a side-effect, this patch also allows PRPs to be located in the CMB.
The logic ensures that if some of the PRP is in the CMB, all of it must
be located there, as per the specification.
Signed-off-by: Klaus Jensen <klaus.jensen@cnexlabs.com>
---
hw/block/nvme.c | 255 ++++++++++++++++++++++++++++--------------
hw/block/nvme.h | 4 +-
hw/block/trace-events | 1 +
include/block/nvme.h | 1 +
4 files changed, 174 insertions(+), 87 deletions(-)
diff --git a/hw/block/nvme.c b/hw/block/nvme.c
index 1e2320b38b14..cbc0b6a660b6 100644
--- a/hw/block/nvme.c
+++ b/hw/block/nvme.c
@@ -179,138 +179,200 @@ static void nvme_set_error_page(NvmeCtrl *n, uint16_t sqid, uint16_t cid,
n->elp_index = (n->elp_index + 1) % n->params.elpe;
}
-static uint16_t nvme_map_prp(QEMUSGList *qsg, QEMUIOVector *iov, uint64_t prp1,
- uint64_t prp2, uint32_t len, NvmeCtrl *n)
+static uint16_t nvme_map_prp(NvmeCtrl *n, QEMUSGList *qsg, uint64_t prp1,
+ uint64_t prp2, uint32_t len, NvmeRequest *req)
{
hwaddr trans_len = n->page_size - (prp1 % n->page_size);
trans_len = MIN(len, trans_len);
int num_prps = (len >> n->page_bits) + 1;
+ uint16_t status = NVME_SUCCESS;
+ bool prp_list_in_cmb = false;
+
+ trace_nvme_map_prp(req->cid, req->cmd.opcode, trans_len, len, prp1, prp2,
+ num_prps);
if (unlikely(!prp1)) {
trace_nvme_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)) {
- qsg->nsg = 0;
- qemu_iovec_init(iov, num_prps);
- qemu_iovec_add(iov, (void *)&n->cmbuf[prp1 - n->ctrl_mem.addr], trans_len);
- } else {
- pci_dma_sglist_init(qsg, &n->parent_obj, num_prps);
- qemu_sglist_add(qsg, prp1, trans_len);
}
+
+ if (nvme_addr_is_cmb(n, prp1)) {
+ req->is_cmb = true;
+ }
+
+ pci_dma_sglist_init(qsg, &n->parent_obj, num_prps);
+ qemu_sglist_add(qsg, prp1, trans_len);
+
len -= trans_len;
if (len) {
if (unlikely(!prp2)) {
trace_nvme_err_invalid_prp2_missing();
+ status = NVME_INVALID_FIELD | NVME_DNR;
goto unmap;
}
+
if (len > n->page_size) {
uint64_t prp_list[n->max_prp_ents];
uint32_t nents, prp_trans;
int i = 0;
+ if (nvme_addr_is_cmb(n, prp2)) {
+ prp_list_in_cmb = true;
+ }
+
nents = (len + n->page_size - 1) >> n->page_bits;
prp_trans = MIN(n->max_prp_ents, nents) * sizeof(uint64_t);
- nvme_addr_read(n, prp2, (void *)prp_list, prp_trans);
+ nvme_addr_read(n, prp2, (void *) prp_list, prp_trans);
while (len != 0) {
+ bool addr_is_cmb;
uint64_t prp_ent = le64_to_cpu(prp_list[i]);
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);
+ status = NVME_INVALID_FIELD | NVME_DNR;
+ goto unmap;
+ }
+
+ addr_is_cmb = nvme_addr_is_cmb(n, prp_ent);
+ if ((prp_list_in_cmb && !addr_is_cmb) ||
+ (!prp_list_in_cmb && addr_is_cmb)) {
+ status = NVME_INVALID_USE_OF_CMB | NVME_DNR;
goto unmap;
}
i = 0;
nents = (len + n->page_size - 1) >> n->page_bits;
prp_trans = MIN(n->max_prp_ents, nents) * sizeof(uint64_t);
- nvme_addr_read(n, prp_ent, (void *)prp_list,
- prp_trans);
+ nvme_addr_read(n, prp_ent, (void *) prp_list, prp_trans);
prp_ent = le64_to_cpu(prp_list[i]);
}
if (unlikely(!prp_ent || prp_ent & (n->page_size - 1))) {
trace_nvme_err_invalid_prplist_ent(prp_ent);
+ status = NVME_INVALID_FIELD | NVME_DNR;
goto unmap;
}
- trans_len = MIN(len, n->page_size);
- if (qsg->nsg){
- qemu_sglist_add(qsg, prp_ent, trans_len);
- } else {
- qemu_iovec_add(iov, (void *)&n->cmbuf[prp_ent - n->ctrl_mem.addr], trans_len);
+ addr_is_cmb = nvme_addr_is_cmb(n, prp_ent);
+ if ((req->is_cmb && !addr_is_cmb) ||
+ (!req->is_cmb && addr_is_cmb)) {
+ status = NVME_INVALID_USE_OF_CMB | NVME_DNR;
+ goto unmap;
}
+
+ trans_len = MIN(len, n->page_size);
+ qemu_sglist_add(qsg, prp_ent, trans_len);
+
len -= trans_len;
i++;
}
} else {
+ bool addr_is_cmb = nvme_addr_is_cmb(n, prp2);
+ if ((req->is_cmb && !addr_is_cmb) ||
+ (!req->is_cmb && addr_is_cmb)) {
+ status = NVME_INVALID_USE_OF_CMB | NVME_DNR;
+ goto unmap;
+ }
+
if (unlikely(prp2 & (n->page_size - 1))) {
trace_nvme_err_invalid_prp2_align(prp2);
+ status = NVME_INVALID_FIELD | NVME_DNR;
goto unmap;
}
- if (qsg->nsg) {
- qemu_sglist_add(qsg, prp2, len);
- } else {
- qemu_iovec_add(iov, (void *)&n->cmbuf[prp2 - n->ctrl_mem.addr], trans_len);
- }
+
+ qemu_sglist_add(qsg, prp2, len);
}
}
+
return NVME_SUCCESS;
- unmap:
+unmap:
qemu_sglist_destroy(qsg);
- return NVME_INVALID_FIELD | NVME_DNR;
+
+ return status;
+}
+
+static void dma_to_cmb(NvmeCtrl *n, QEMUSGList *qsg, QEMUIOVector *iov)
+{
+ for (int i = 0; i < qsg->nsg; i++) {
+ void *addr = &n->cmbuf[qsg->sg[i].base - n->ctrl_mem.addr];
+ qemu_iovec_add(iov, addr, qsg->sg[i].len);
+ }
}
static uint16_t nvme_dma_write_prp(NvmeCtrl *n, uint8_t *ptr, uint32_t len,
- uint64_t prp1, uint64_t prp2)
+ uint64_t prp1, uint64_t prp2, NvmeRequest *req)
{
QEMUSGList qsg;
- QEMUIOVector iov;
uint16_t status = NVME_SUCCESS;
- if (nvme_map_prp(&qsg, &iov, prp1, prp2, len, n)) {
- return NVME_INVALID_FIELD | NVME_DNR;
+ status = nvme_map_prp(n, &qsg, prp1, prp2, len, req);
+ if (status) {
+ return status;
}
- if (qsg.nsg > 0) {
- if (dma_buf_write(ptr, len, &qsg)) {
- status = NVME_INVALID_FIELD | NVME_DNR;
- }
- qemu_sglist_destroy(&qsg);
- } else {
- if (qemu_iovec_to_buf(&iov, 0, ptr, len) != len) {
+
+ if (req->is_cmb) {
+ QEMUIOVector iov;
+
+ qemu_iovec_init(&iov, qsg.nsg);
+ dma_to_cmb(n, &qsg, &iov);
+
+ if (unlikely(qemu_iovec_to_buf(&iov, 0, ptr, len) != len)) {
+ trace_nvme_err_invalid_dma();
status = NVME_INVALID_FIELD | NVME_DNR;
}
+
qemu_iovec_destroy(&iov);
+
+ return status;
+ }
+
+ if (unlikely(dma_buf_write(ptr, len, &qsg))) {
+ trace_nvme_err_invalid_dma();
+ status = NVME_INVALID_FIELD | NVME_DNR;
}
+
+ qemu_sglist_destroy(&qsg);
+
return status;
}
static uint16_t nvme_dma_read_prp(NvmeCtrl *n, uint8_t *ptr, uint32_t len,
- uint64_t prp1, uint64_t prp2)
+ uint64_t prp1, uint64_t prp2, NvmeRequest *req)
{
QEMUSGList qsg;
- QEMUIOVector iov;
uint16_t status = NVME_SUCCESS;
- trace_nvme_dma_read(prp1, prp2);
-
- if (nvme_map_prp(&qsg, &iov, prp1, prp2, len, n)) {
- return NVME_INVALID_FIELD | NVME_DNR;
+ status = nvme_map_prp(n, &qsg, prp1, prp2, len, req);
+ if (status) {
+ return status;
}
- if (qsg.nsg > 0) {
- if (unlikely(dma_buf_read(ptr, len, &qsg))) {
- trace_nvme_err_invalid_dma();
- status = NVME_INVALID_FIELD | NVME_DNR;
- }
- qemu_sglist_destroy(&qsg);
- } else {
+
+ if (req->is_cmb) {
+ QEMUIOVector iov;
+
+ qemu_iovec_init(&iov, qsg.nsg);
+ dma_to_cmb(n, &qsg, &iov);
+
if (unlikely(qemu_iovec_from_buf(&iov, 0, ptr, len) != len)) {
trace_nvme_err_invalid_dma();
status = NVME_INVALID_FIELD | NVME_DNR;
}
+
qemu_iovec_destroy(&iov);
+
+ goto out;
}
+
+ if (unlikely(dma_buf_read(ptr, len, &qsg))) {
+ trace_nvme_err_invalid_dma();
+ status = NVME_INVALID_FIELD | NVME_DNR;
+ }
+
+out:
+ qemu_sglist_destroy(&qsg);
+
return status;
}
@@ -400,6 +462,7 @@ static void nvme_rw_cb(void *opaque, int ret)
NvmeSQueue *sq = req->sq;
NvmeCtrl *n = sq->ctrl;
NvmeCQueue *cq = n->cq[sq->cqid];
+ NvmeRwCmd *rw = (NvmeRwCmd *) &req->cmd;
if (!ret) {
block_acct_done(blk_get_stats(n->conf.blk), &req->acct);
@@ -407,19 +470,23 @@ static void nvme_rw_cb(void *opaque, int ret)
} else {
block_acct_failed(blk_get_stats(n->conf.blk), &req->acct);
nvme_set_error_page(n, sq->sqid, cpu_to_le16(req->cid),
- NVME_INTERNAL_DEV_ERROR, 0, 0, 1);
+ NVME_INTERNAL_DEV_ERROR, offsetof(NvmeRwCmd, slba), rw->slba, 1);
req->status = NVME_INTERNAL_DEV_ERROR | NVME_MORE;
}
- if (req->has_sg) {
+
+ if (req->qsg.nalloc) {
qemu_sglist_destroy(&req->qsg);
}
+ if (req->iov.nalloc) {
+ qemu_iovec_destroy(&req->iov);
+ }
+
nvme_enqueue_req_completion(cq, req);
}
static uint16_t nvme_flush(NvmeCtrl *n, NvmeNamespace *ns, NvmeCmd *cmd,
NvmeRequest *req)
{
- req->has_sg = false;
block_acct_start(blk_get_stats(n->conf.blk), &req->acct, 0,
BLOCK_ACCT_FLUSH);
req->aiocb = blk_aio_flush(n->conf.blk, nvme_rw_cb, req);
@@ -443,7 +510,6 @@ static uint16_t nvme_write_zeros(NvmeCtrl *n, NvmeNamespace *ns, NvmeCmd *cmd,
return NVME_LBA_RANGE | NVME_DNR;
}
- req->has_sg = false;
block_acct_start(blk_get_stats(n->conf.blk), &req->acct, 0,
BLOCK_ACCT_WRITE);
req->aiocb = blk_aio_pwrite_zeroes(n->conf.blk, offset, count,
@@ -475,21 +541,21 @@ static uint16_t nvme_rw(NvmeCtrl *n, NvmeNamespace *ns, NvmeCmd *cmd,
return NVME_LBA_RANGE | NVME_DNR;
}
- if (nvme_map_prp(&req->qsg, &req->iov, prp1, prp2, data_size, n)) {
+ if (nvme_map_prp(n, &req->qsg, prp1, prp2, data_size, req)) {
block_acct_invalid(blk_get_stats(n->conf.blk), acct);
return NVME_INVALID_FIELD | NVME_DNR;
}
dma_acct_start(n->conf.blk, &req->acct, &req->qsg, acct);
- if (req->qsg.nsg > 0) {
- req->has_sg = true;
+ if (!req->is_cmb) {
req->aiocb = is_write ?
dma_blk_write(n->conf.blk, &req->qsg, data_offset, BDRV_SECTOR_SIZE,
nvme_rw_cb, req) :
dma_blk_read(n->conf.blk, &req->qsg, data_offset, BDRV_SECTOR_SIZE,
nvme_rw_cb, req);
} else {
- req->has_sg = false;
+ qemu_iovec_init(&req->iov, req->qsg.nsg);
+ dma_to_cmb(n, &req->qsg, &req->iov);
req->aiocb = is_write ?
blk_aio_pwritev(n->conf.blk, data_offset, &req->iov, 0, nvme_rw_cb,
req) :
@@ -587,7 +653,7 @@ static void nvme_init_sq(NvmeSQueue *sq, NvmeCtrl *n, uint64_t dma_addr,
sq->size = size;
sq->cqid = cqid;
sq->head = sq->tail = 0;
- sq->io_req = g_new(NvmeRequest, sq->size);
+ sq->io_req = g_new0(NvmeRequest, sq->size);
QTAILQ_INIT(&sq->req_list);
QTAILQ_INIT(&sq->out_req_list);
@@ -660,7 +726,7 @@ static uint16_t nvme_error_info(NvmeCtrl *n, NvmeCmd *cmd, uint8_t rae,
}
return nvme_dma_read_prp(n, (uint8_t *) n->elpes + off, trans_len, prp1,
- prp2);
+ prp2, req);
}
static uint16_t nvme_smart_info(NvmeCtrl *n, NvmeCmd *cmd, uint8_t rae,
@@ -719,7 +785,7 @@ static uint16_t nvme_smart_info(NvmeCtrl *n, NvmeCmd *cmd, uint8_t rae,
}
return nvme_dma_read_prp(n, (uint8_t *) &smart + off, trans_len, prp1,
- prp2);
+ prp2, req);
}
static uint16_t nvme_fw_log_info(NvmeCtrl *n, NvmeCmd *cmd, uint32_t buf_len,
@@ -739,7 +805,7 @@ static uint16_t nvme_fw_log_info(NvmeCtrl *n, NvmeCmd *cmd, uint32_t buf_len,
trans_len = MIN(sizeof(fw_log) - off, buf_len);
return nvme_dma_read_prp(n, (uint8_t *) &fw_log + off, trans_len, prp1,
- prp2);
+ prp2, req);
}
static uint16_t nvme_get_log(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
@@ -875,7 +941,8 @@ static uint16_t nvme_create_cq(NvmeCtrl *n, NvmeCmd *cmd)
return NVME_SUCCESS;
}
-static uint16_t nvme_identify_ctrl(NvmeCtrl *n, NvmeIdentify *c)
+static uint16_t nvme_identify_ctrl(NvmeCtrl *n, NvmeIdentify *c,
+ NvmeRequest *req)
{
uint64_t prp1 = le64_to_cpu(c->prp1);
uint64_t prp2 = le64_to_cpu(c->prp2);
@@ -883,10 +950,11 @@ static uint16_t nvme_identify_ctrl(NvmeCtrl *n, NvmeIdentify *c)
trace_nvme_identify_ctrl();
return nvme_dma_read_prp(n, (uint8_t *)&n->id_ctrl, sizeof(n->id_ctrl),
- prp1, prp2);
+ prp1, prp2, req);
}
-static uint16_t nvme_identify_ns(NvmeCtrl *n, NvmeIdentify *c)
+static uint16_t nvme_identify_ns(NvmeCtrl *n, NvmeIdentify *c,
+ NvmeRequest *req)
{
NvmeNamespace *ns;
uint32_t nsid = le32_to_cpu(c->nsid);
@@ -903,10 +971,11 @@ static uint16_t nvme_identify_ns(NvmeCtrl *n, NvmeIdentify *c)
ns = &n->namespaces[nsid - 1];
return nvme_dma_read_prp(n, (uint8_t *)&ns->id_ns, sizeof(ns->id_ns),
- prp1, prp2);
+ prp1, prp2, req);
}
-static uint16_t nvme_identify_ns_list(NvmeCtrl *n, NvmeIdentify *c)
+static uint16_t nvme_identify_ns_list(NvmeCtrl *n, NvmeIdentify *c,
+ NvmeRequest *req)
{
static const int data_len = 4 * KiB;
uint32_t min_nsid = le32_to_cpu(c->nsid);
@@ -928,12 +997,13 @@ static uint16_t nvme_identify_ns_list(NvmeCtrl *n, NvmeIdentify *c)
break;
}
}
- ret = nvme_dma_read_prp(n, (uint8_t *)list, data_len, prp1, prp2);
+ ret = nvme_dma_read_prp(n, (uint8_t *)list, data_len, prp1, prp2, req);
g_free(list);
return ret;
}
-static uint16_t nvme_identify_ns_descr_list(NvmeCtrl *n, NvmeCmd *c)
+static uint16_t nvme_identify_ns_descr_list(NvmeCtrl *n, NvmeIdentify *c,
+ NvmeRequest *req)
{
static const int len = 4096;
@@ -963,24 +1033,24 @@ static uint16_t nvme_identify_ns_descr_list(NvmeCtrl *n, NvmeCmd *c)
list->nidl = 0x10;
*(uint32_t *) &list->nid[12] = cpu_to_be32(nsid);
- ret = nvme_dma_read_prp(n, (uint8_t *) list, len, prp1, prp2);
+ ret = nvme_dma_read_prp(n, (uint8_t *) list, len, prp1, prp2, req);
g_free(list);
return ret;
}
-static uint16_t nvme_identify(NvmeCtrl *n, NvmeCmd *cmd)
+static uint16_t nvme_identify(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
{
NvmeIdentify *c = (NvmeIdentify *)cmd;
switch (le32_to_cpu(c->cns)) {
case 0x00:
- return nvme_identify_ns(n, c);
+ return nvme_identify_ns(n, c, req);
case 0x01:
- return nvme_identify_ctrl(n, c);
+ return nvme_identify_ctrl(n, c, req);
case 0x02:
- return nvme_identify_ns_list(n, c);
+ return nvme_identify_ns_list(n, c, req);
case 0x03:
- return nvme_identify_ns_descr_list(n, cmd);
+ return nvme_identify_ns_descr_list(n, c, req);
default:
trace_nvme_err_invalid_identify_cns(le32_to_cpu(c->cns));
return NVME_INVALID_FIELD | NVME_DNR;
@@ -1039,15 +1109,16 @@ static inline uint64_t nvme_get_timestamp(const NvmeCtrl *n)
return cpu_to_le64(ts.all);
}
-static uint16_t nvme_get_feature_timestamp(NvmeCtrl *n, NvmeCmd *cmd)
+static uint16_t nvme_get_feature_timestamp(NvmeCtrl *n, NvmeCmd *cmd,
+ NvmeRequest *req)
{
uint64_t prp1 = le64_to_cpu(cmd->prp1);
uint64_t prp2 = le64_to_cpu(cmd->prp2);
uint64_t timestamp = nvme_get_timestamp(n);
- return nvme_dma_read_prp(n, (uint8_t *)×tamp,
- sizeof(timestamp), prp1, prp2);
+ return nvme_dma_read_prp(n, (uint8_t *)×tamp, sizeof(timestamp),
+ prp1, prp2, req);
}
static uint16_t nvme_get_feature(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
@@ -1081,7 +1152,7 @@ static uint16_t nvme_get_feature(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
trace_nvme_getfeat_numq(result);
break;
case NVME_TIMESTAMP:
- return nvme_get_feature_timestamp(n, cmd);
+ return nvme_get_feature_timestamp(n, cmd, req);
case NVME_INTERRUPT_COALESCING:
result = cpu_to_le32(n->features.int_coalescing);
break;
@@ -1107,7 +1178,8 @@ static uint16_t nvme_get_feature(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
return NVME_SUCCESS;
}
-static uint16_t nvme_set_feature_timestamp(NvmeCtrl *n, NvmeCmd *cmd)
+static uint16_t nvme_set_feature_timestamp(NvmeCtrl *n, NvmeCmd *cmd,
+ NvmeRequest *req)
{
uint16_t ret;
uint64_t timestamp;
@@ -1115,7 +1187,7 @@ static uint16_t nvme_set_feature_timestamp(NvmeCtrl *n, NvmeCmd *cmd)
uint64_t prp2 = le64_to_cpu(cmd->prp2);
ret = nvme_dma_write_prp(n, (uint8_t *)×tamp,
- sizeof(timestamp), prp1, prp2);
+ sizeof(timestamp), prp1, prp2, req);
if (ret != NVME_SUCCESS) {
return ret;
}
@@ -1163,7 +1235,7 @@ static uint16_t nvme_set_feature(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
((n->params.num_queues - 2) << 16));
break;
case NVME_TIMESTAMP:
- return nvme_set_feature_timestamp(n, cmd);
+ return nvme_set_feature_timestamp(n, cmd, req);
case NVME_ASYNCHRONOUS_EVENT_CONF:
n->features.async_config = dw11;
break;
@@ -1212,7 +1284,7 @@ static uint16_t nvme_admin_cmd(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
case NVME_ADM_CMD_CREATE_CQ:
return nvme_create_cq(n, cmd);
case NVME_ADM_CMD_IDENTIFY:
- return nvme_identify(n, cmd);
+ return nvme_identify(n, cmd, req);
case NVME_ADM_CMD_ABORT:
return nvme_abort(n, cmd, req);
case NVME_ADM_CMD_SET_FEATURES:
@@ -1273,6 +1345,18 @@ static void nvme_process_aers(void *opaque)
}
}
+static void nvme_init_req(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
+{
+ memset(&req->cqe, 0, sizeof(req->cqe));
+ req->cqe.cid = cmd->cid;
+ req->cid = le16_to_cpu(cmd->cid);
+
+ memcpy(&req->cmd, cmd, sizeof(NvmeCmd));
+ req->status = NVME_SUCCESS;
+ req->is_cmb = false;
+ req->is_write = false;
+}
+
static void nvme_process_sq(void *opaque)
{
NvmeSQueue *sq = opaque;
@@ -1292,9 +1376,8 @@ static void nvme_process_sq(void *opaque)
req = QTAILQ_FIRST(&sq->req_list);
QTAILQ_REMOVE(&sq->req_list, req, entry);
QTAILQ_INSERT_TAIL(&sq->out_req_list, req, entry);
- memset(&req->cqe, 0, sizeof(req->cqe));
- req->cqe.cid = cmd.cid;
- req->cid = le16_to_cpu(cmd.cid);
+
+ nvme_init_req(n, &cmd, req);
status = sq->sqid ? nvme_io_cmd(n, &cmd, req) :
nvme_admin_cmd(n, &cmd, req);
@@ -1815,7 +1898,7 @@ static void nvme_init_cmb(NvmeCtrl *n, PCIDevice *pci_dev)
NVME_CMBSZ_SET_SQS(n->bar.cmbsz, 1);
NVME_CMBSZ_SET_CQS(n->bar.cmbsz, 1);
- NVME_CMBSZ_SET_LISTS(n->bar.cmbsz, 0);
+ NVME_CMBSZ_SET_LISTS(n->bar.cmbsz, 1);
NVME_CMBSZ_SET_RDS(n->bar.cmbsz, 1);
NVME_CMBSZ_SET_WDS(n->bar.cmbsz, 1);
NVME_CMBSZ_SET_SZU(n->bar.cmbsz, 2);
diff --git a/hw/block/nvme.h b/hw/block/nvme.h
index 3f7bd627e824..add9ff335aa5 100644
--- a/hw/block/nvme.h
+++ b/hw/block/nvme.h
@@ -28,11 +28,13 @@ typedef struct NvmeRequest {
BlockAIOCB *aiocb;
uint16_t status;
uint16_t cid;
- bool has_sg;
+ bool is_cmb;
+ bool is_write;
NvmeCqe cqe;
BlockAcctCookie acct;
QEMUSGList qsg;
QEMUIOVector iov;
+ NvmeCmd cmd;
QTAILQ_ENTRY(NvmeRequest)entry;
} NvmeRequest;
diff --git a/hw/block/trace-events b/hw/block/trace-events
index f62fa99dc2cd..e81bb3a64ed7 100644
--- a/hw/block/trace-events
+++ b/hw/block/trace-events
@@ -33,6 +33,7 @@ nvme_irq_msix(uint32_t vector) "raising MSI-X IRQ vector %u"
nvme_irq_pin(void) "pulsing IRQ pin"
nvme_irq_masked(void) "IRQ is masked"
nvme_dma_read(uint64_t prp1, uint64_t prp2) "DMA read, prp1=0x%"PRIx64" prp2=0x%"PRIx64""
+nvme_map_prp(uint16_t cid, uint8_t opc, uint64_t trans_len, uint32_t len, uint64_t prp1, uint64_t prp2, int num_prps) "cid %"PRIu16" opc 0x%"PRIx8" trans_len %"PRIu64" len %"PRIu32" prp1 0x%"PRIx64" prp2 0x%"PRIx64" num_prps %d"
nvme_rw(const char *verb, uint32_t blk_count, uint64_t byte_count, uint64_t lba) "%s %"PRIu32" blocks (%"PRIu64" bytes) from LBA %"PRIu64""
nvme_create_sq(uint64_t addr, uint16_t sqid, uint16_t cqid, uint16_t qsize, uint16_t qflags) "create submission queue, addr=0x%"PRIx64", sqid=%"PRIu16", cqid=%"PRIu16", qsize=%"PRIu16", qflags=%"PRIu16""
nvme_create_cq(uint64_t addr, uint16_t cqid, uint16_t vector, uint16_t size, uint16_t qflags, int ien) "create completion queue, addr=0x%"PRIx64", cqid=%"PRIu16", vector=%"PRIu16", qsize=%"PRIu16", qflags=%"PRIu16", ien=%d"
diff --git a/include/block/nvme.h b/include/block/nvme.h
index f0f5728b5ec4..d4990db4fdf8 100644
--- a/include/block/nvme.h
+++ b/include/block/nvme.h
@@ -427,6 +427,7 @@ enum NvmeStatusCodes {
NVME_CMD_ABORT_MISSING_FUSE = 0x000a,
NVME_INVALID_NSID = 0x000b,
NVME_CMD_SEQ_ERROR = 0x000c,
+ NVME_INVALID_USE_OF_CMB = 0x0012,
NVME_LBA_RANGE = 0x0080,
NVME_CAP_EXCEEDED = 0x0081,
NVME_NS_NOT_READY = 0x0082,
--
2.23.0
^ permalink raw reply related [flat|nested] 52+ messages in thread* Re: [PATCH v2 13/20] nvme: refactor prp mapping
2019-10-15 10:38 ` [PATCH v2 13/20] nvme: refactor prp mapping Klaus Jensen
@ 2019-11-12 15:23 ` Beata Michalska
2019-11-20 9:39 ` Klaus Birkelund
0 siblings, 1 reply; 52+ messages in thread
From: Beata Michalska @ 2019-11-12 15:23 UTC (permalink / raw)
To: Klaus Jensen
Cc: Kevin Wolf, Fam Zheng, Javier Gonzalez, qemu-block, qemu-devel,
Max Reitz, Keith Busch, Paul Durrant, Stephen Bates
Hi Klaus,
On Tue, 15 Oct 2019 at 11:57, Klaus Jensen <its@irrelevant.dk> wrote:
>
> Instead of handling both QSGs and IOVs in multiple places, simply use
> QSGs everywhere by assuming that the request does not involve the
> controller memory buffer (CMB). If the request is found to involve the
> CMB, convert the QSG to an IOV and issue the I/O. The QSG is converted
> to an IOV by the dma helpers anyway, so the CMB path is not unfairly
> affected by this simplifying change.
>
Out of curiosity, in how many cases the SG list will have to
be converted to IOV ? Does that justify creating the SG list in vain ?
> As a side-effect, this patch also allows PRPs to be located in the CMB.
> The logic ensures that if some of the PRP is in the CMB, all of it must
> be located there, as per the specification.
>
> Signed-off-by: Klaus Jensen <klaus.jensen@cnexlabs.com>
> ---
> hw/block/nvme.c | 255 ++++++++++++++++++++++++++++--------------
> hw/block/nvme.h | 4 +-
> hw/block/trace-events | 1 +
> include/block/nvme.h | 1 +
> 4 files changed, 174 insertions(+), 87 deletions(-)
>
> diff --git a/hw/block/nvme.c b/hw/block/nvme.c
> index 1e2320b38b14..cbc0b6a660b6 100644
> --- a/hw/block/nvme.c
> +++ b/hw/block/nvme.c
> @@ -179,138 +179,200 @@ static void nvme_set_error_page(NvmeCtrl *n, uint16_t sqid, uint16_t cid,
> n->elp_index = (n->elp_index + 1) % n->params.elpe;
> }
>
> -static uint16_t nvme_map_prp(QEMUSGList *qsg, QEMUIOVector *iov, uint64_t prp1,
> - uint64_t prp2, uint32_t len, NvmeCtrl *n)
> +static uint16_t nvme_map_prp(NvmeCtrl *n, QEMUSGList *qsg, uint64_t prp1,
> + uint64_t prp2, uint32_t len, NvmeRequest *req)
> {
> hwaddr trans_len = n->page_size - (prp1 % n->page_size);
> trans_len = MIN(len, trans_len);
> int num_prps = (len >> n->page_bits) + 1;
> + uint16_t status = NVME_SUCCESS;
> + bool prp_list_in_cmb = false;
> +
> + trace_nvme_map_prp(req->cid, req->cmd.opcode, trans_len, len, prp1, prp2,
> + num_prps);
>
> if (unlikely(!prp1)) {
> trace_nvme_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)) {
> - qsg->nsg = 0;
> - qemu_iovec_init(iov, num_prps);
> - qemu_iovec_add(iov, (void *)&n->cmbuf[prp1 - n->ctrl_mem.addr], trans_len);
> - } else {
> - pci_dma_sglist_init(qsg, &n->parent_obj, num_prps);
> - qemu_sglist_add(qsg, prp1, trans_len);
> }
> +
> + if (nvme_addr_is_cmb(n, prp1)) {
> + req->is_cmb = true;
> + }
> +
This seems to be used here and within read/write functions which are calling
this one. Maybe there is a nicer way to track that instead of passing
the request
from multiple places ?
> + pci_dma_sglist_init(qsg, &n->parent_obj, num_prps);
> + qemu_sglist_add(qsg, prp1, trans_len);
> +
> len -= trans_len;
> if (len) {
> if (unlikely(!prp2)) {
> trace_nvme_err_invalid_prp2_missing();
> + status = NVME_INVALID_FIELD | NVME_DNR;
> goto unmap;
> }
> +
> if (len > n->page_size) {
> uint64_t prp_list[n->max_prp_ents];
> uint32_t nents, prp_trans;
> int i = 0;
>
> + if (nvme_addr_is_cmb(n, prp2)) {
> + prp_list_in_cmb = true;
> + }
> +
> nents = (len + n->page_size - 1) >> n->page_bits;
> prp_trans = MIN(n->max_prp_ents, nents) * sizeof(uint64_t);
> - nvme_addr_read(n, prp2, (void *)prp_list, prp_trans);
> + nvme_addr_read(n, prp2, (void *) prp_list, prp_trans);
> while (len != 0) {
> + bool addr_is_cmb;
> uint64_t prp_ent = le64_to_cpu(prp_list[i]);
>
> 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);
> + status = NVME_INVALID_FIELD | NVME_DNR;
> + goto unmap;
> + }
> +
> + addr_is_cmb = nvme_addr_is_cmb(n, prp_ent);
> + if ((prp_list_in_cmb && !addr_is_cmb) ||
> + (!prp_list_in_cmb && addr_is_cmb)) {
Minor: Same condition (based on different vars) is being used in
multiple places. Might be worth to move it outside and just pass in
the needed values.
> + status = NVME_INVALID_USE_OF_CMB | NVME_DNR;
> goto unmap;
> }
>
> i = 0;
> nents = (len + n->page_size - 1) >> n->page_bits;
> prp_trans = MIN(n->max_prp_ents, nents) * sizeof(uint64_t);
> - nvme_addr_read(n, prp_ent, (void *)prp_list,
> - prp_trans);
> + nvme_addr_read(n, prp_ent, (void *) prp_list, prp_trans);
> prp_ent = le64_to_cpu(prp_list[i]);
> }
>
> if (unlikely(!prp_ent || prp_ent & (n->page_size - 1))) {
> trace_nvme_err_invalid_prplist_ent(prp_ent);
> + status = NVME_INVALID_FIELD | NVME_DNR;
> goto unmap;
> }
>
> - trans_len = MIN(len, n->page_size);
> - if (qsg->nsg){
> - qemu_sglist_add(qsg, prp_ent, trans_len);
> - } else {
> - qemu_iovec_add(iov, (void *)&n->cmbuf[prp_ent - n->ctrl_mem.addr], trans_len);
> + addr_is_cmb = nvme_addr_is_cmb(n, prp_ent);
> + if ((req->is_cmb && !addr_is_cmb) ||
> + (!req->is_cmb && addr_is_cmb)) {
> + status = NVME_INVALID_USE_OF_CMB | NVME_DNR;
> + goto unmap;
> }
> +
> + trans_len = MIN(len, n->page_size);
> + qemu_sglist_add(qsg, prp_ent, trans_len);
> +
> len -= trans_len;
> i++;
> }
> } else {
> + bool addr_is_cmb = nvme_addr_is_cmb(n, prp2);
> + if ((req->is_cmb && !addr_is_cmb) ||
> + (!req->is_cmb && addr_is_cmb)) {
> + status = NVME_INVALID_USE_OF_CMB | NVME_DNR;
> + goto unmap;
> + }
> +
> if (unlikely(prp2 & (n->page_size - 1))) {
> trace_nvme_err_invalid_prp2_align(prp2);
> + status = NVME_INVALID_FIELD | NVME_DNR;
> goto unmap;
> }
> - if (qsg->nsg) {
> - qemu_sglist_add(qsg, prp2, len);
> - } else {
> - qemu_iovec_add(iov, (void *)&n->cmbuf[prp2 - n->ctrl_mem.addr], trans_len);
> - }
> +
> + qemu_sglist_add(qsg, prp2, len);
> }
> }
> +
> return NVME_SUCCESS;
>
> - unmap:
> +unmap:
> qemu_sglist_destroy(qsg);
> - return NVME_INVALID_FIELD | NVME_DNR;
> +
> + return status;
> +}
> +
> +static void dma_to_cmb(NvmeCtrl *n, QEMUSGList *qsg, QEMUIOVector *iov)
> +{
> + for (int i = 0; i < qsg->nsg; i++) {
> + void *addr = &n->cmbuf[qsg->sg[i].base - n->ctrl_mem.addr];
> + qemu_iovec_add(iov, addr, qsg->sg[i].len);
> + }
> }
>
> static uint16_t nvme_dma_write_prp(NvmeCtrl *n, uint8_t *ptr, uint32_t len,
> - uint64_t prp1, uint64_t prp2)
> + uint64_t prp1, uint64_t prp2, NvmeRequest *req)
> {
> QEMUSGList qsg;
> - QEMUIOVector iov;
> uint16_t status = NVME_SUCCESS;
>
> - if (nvme_map_prp(&qsg, &iov, prp1, prp2, len, n)) {
> - return NVME_INVALID_FIELD | NVME_DNR;
> + status = nvme_map_prp(n, &qsg, prp1, prp2, len, req);
> + if (status) {
> + return status;
> }
> - if (qsg.nsg > 0) {
> - if (dma_buf_write(ptr, len, &qsg)) {
> - status = NVME_INVALID_FIELD | NVME_DNR;
> - }
> - qemu_sglist_destroy(&qsg);
> - } else {
> - if (qemu_iovec_to_buf(&iov, 0, ptr, len) != len) {
> +
> + if (req->is_cmb) {
> + QEMUIOVector iov;
> +
> + qemu_iovec_init(&iov, qsg.nsg);
> + dma_to_cmb(n, &qsg, &iov);
> +
> + if (unlikely(qemu_iovec_to_buf(&iov, 0, ptr, len) != len)) {
> + trace_nvme_err_invalid_dma();
> status = NVME_INVALID_FIELD | NVME_DNR;
> }
> +
> qemu_iovec_destroy(&iov);
> +
Aren't we missing the sglist cleanup here ?
(goto as in nvme_dma_read_prp)
> + return status;
> + }
> +
> + if (unlikely(dma_buf_write(ptr, len, &qsg))) {
> + trace_nvme_err_invalid_dma();
> + status = NVME_INVALID_FIELD | NVME_DNR;
> }
> +
> + qemu_sglist_destroy(&qsg);
> +
> return status;
> }
>
> static uint16_t nvme_dma_read_prp(NvmeCtrl *n, uint8_t *ptr, uint32_t len,
> - uint64_t prp1, uint64_t prp2)
> + uint64_t prp1, uint64_t prp2, NvmeRequest *req)
> {
> QEMUSGList qsg;
> - QEMUIOVector iov;
> uint16_t status = NVME_SUCCESS;
>
> - trace_nvme_dma_read(prp1, prp2);
> -
> - if (nvme_map_prp(&qsg, &iov, prp1, prp2, len, n)) {
> - return NVME_INVALID_FIELD | NVME_DNR;
> + status = nvme_map_prp(n, &qsg, prp1, prp2, len, req);
> + if (status) {
> + return status;
> }
> - if (qsg.nsg > 0) {
> - if (unlikely(dma_buf_read(ptr, len, &qsg))) {
> - trace_nvme_err_invalid_dma();
> - status = NVME_INVALID_FIELD | NVME_DNR;
> - }
> - qemu_sglist_destroy(&qsg);
> - } else {
> +
> + if (req->is_cmb) {
> + QEMUIOVector iov;
> +
> + qemu_iovec_init(&iov, qsg.nsg);
> + dma_to_cmb(n, &qsg, &iov);
> +
> if (unlikely(qemu_iovec_from_buf(&iov, 0, ptr, len) != len)) {
> trace_nvme_err_invalid_dma();
> status = NVME_INVALID_FIELD | NVME_DNR;
> }
> +
> qemu_iovec_destroy(&iov);
> +
> + goto out;
> }
> +
> + if (unlikely(dma_buf_read(ptr, len, &qsg))) {
> + trace_nvme_err_invalid_dma();
> + status = NVME_INVALID_FIELD | NVME_DNR;
> + }
> +
> +out:
> + qemu_sglist_destroy(&qsg);
> +
> return status;
> }
>
Aside: both nvme_write_prp and nvme_read_prp seem to differ only
with the final call to either dma or qemu_ioves calls.
Might be worth to unify it and move it to a single function with additional
parameter that will determine the type of the transaction.
> @@ -400,6 +462,7 @@ static void nvme_rw_cb(void *opaque, int ret)
> NvmeSQueue *sq = req->sq;
> NvmeCtrl *n = sq->ctrl;
> NvmeCQueue *cq = n->cq[sq->cqid];
> + NvmeRwCmd *rw = (NvmeRwCmd *) &req->cmd;
>
> if (!ret) {
> block_acct_done(blk_get_stats(n->conf.blk), &req->acct);
> @@ -407,19 +470,23 @@ static void nvme_rw_cb(void *opaque, int ret)
> } else {
> block_acct_failed(blk_get_stats(n->conf.blk), &req->acct);
> nvme_set_error_page(n, sq->sqid, cpu_to_le16(req->cid),
> - NVME_INTERNAL_DEV_ERROR, 0, 0, 1);
> + NVME_INTERNAL_DEV_ERROR, offsetof(NvmeRwCmd, slba), rw->slba, 1);
> req->status = NVME_INTERNAL_DEV_ERROR | NVME_MORE;
> }
> - if (req->has_sg) {
> +
> + if (req->qsg.nalloc) {
> qemu_sglist_destroy(&req->qsg);
> }
> + if (req->iov.nalloc) {
> + qemu_iovec_destroy(&req->iov);
> + }
> +
> nvme_enqueue_req_completion(cq, req);
> }
>
> static uint16_t nvme_flush(NvmeCtrl *n, NvmeNamespace *ns, NvmeCmd *cmd,
> NvmeRequest *req)
> {
> - req->has_sg = false;
> block_acct_start(blk_get_stats(n->conf.blk), &req->acct, 0,
> BLOCK_ACCT_FLUSH);
> req->aiocb = blk_aio_flush(n->conf.blk, nvme_rw_cb, req);
> @@ -443,7 +510,6 @@ static uint16_t nvme_write_zeros(NvmeCtrl *n, NvmeNamespace *ns, NvmeCmd *cmd,
> return NVME_LBA_RANGE | NVME_DNR;
> }
>
> - req->has_sg = false;
> block_acct_start(blk_get_stats(n->conf.blk), &req->acct, 0,
> BLOCK_ACCT_WRITE);
> req->aiocb = blk_aio_pwrite_zeroes(n->conf.blk, offset, count,
> @@ -475,21 +541,21 @@ static uint16_t nvme_rw(NvmeCtrl *n, NvmeNamespace *ns, NvmeCmd *cmd,
> return NVME_LBA_RANGE | NVME_DNR;
> }
>
> - if (nvme_map_prp(&req->qsg, &req->iov, prp1, prp2, data_size, n)) {
> + if (nvme_map_prp(n, &req->qsg, prp1, prp2, data_size, req)) {
> block_acct_invalid(blk_get_stats(n->conf.blk), acct);
> return NVME_INVALID_FIELD | NVME_DNR;
> }
>
> dma_acct_start(n->conf.blk, &req->acct, &req->qsg, acct);
> - if (req->qsg.nsg > 0) {
> - req->has_sg = true;
> + if (!req->is_cmb) {
> req->aiocb = is_write ?
> dma_blk_write(n->conf.blk, &req->qsg, data_offset, BDRV_SECTOR_SIZE,
> nvme_rw_cb, req) :
> dma_blk_read(n->conf.blk, &req->qsg, data_offset, BDRV_SECTOR_SIZE,
> nvme_rw_cb, req);
> } else {
> - req->has_sg = false;
> + qemu_iovec_init(&req->iov, req->qsg.nsg);
> + dma_to_cmb(n, &req->qsg, &req->iov);
> req->aiocb = is_write ?
> blk_aio_pwritev(n->conf.blk, data_offset, &req->iov, 0, nvme_rw_cb,
> req) :
> @@ -587,7 +653,7 @@ static void nvme_init_sq(NvmeSQueue *sq, NvmeCtrl *n, uint64_t dma_addr,
> sq->size = size;
> sq->cqid = cqid;
> sq->head = sq->tail = 0;
> - sq->io_req = g_new(NvmeRequest, sq->size);
> + sq->io_req = g_new0(NvmeRequest, sq->size);
>
> QTAILQ_INIT(&sq->req_list);
> QTAILQ_INIT(&sq->out_req_list);
> @@ -660,7 +726,7 @@ static uint16_t nvme_error_info(NvmeCtrl *n, NvmeCmd *cmd, uint8_t rae,
> }
>
> return nvme_dma_read_prp(n, (uint8_t *) n->elpes + off, trans_len, prp1,
> - prp2);
> + prp2, req);
> }
>
> static uint16_t nvme_smart_info(NvmeCtrl *n, NvmeCmd *cmd, uint8_t rae,
> @@ -719,7 +785,7 @@ static uint16_t nvme_smart_info(NvmeCtrl *n, NvmeCmd *cmd, uint8_t rae,
> }
>
> return nvme_dma_read_prp(n, (uint8_t *) &smart + off, trans_len, prp1,
> - prp2);
> + prp2, req);
> }
>
> static uint16_t nvme_fw_log_info(NvmeCtrl *n, NvmeCmd *cmd, uint32_t buf_len,
> @@ -739,7 +805,7 @@ static uint16_t nvme_fw_log_info(NvmeCtrl *n, NvmeCmd *cmd, uint32_t buf_len,
> trans_len = MIN(sizeof(fw_log) - off, buf_len);
>
> return nvme_dma_read_prp(n, (uint8_t *) &fw_log + off, trans_len, prp1,
> - prp2);
> + prp2, req);
> }
>
> static uint16_t nvme_get_log(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
> @@ -875,7 +941,8 @@ static uint16_t nvme_create_cq(NvmeCtrl *n, NvmeCmd *cmd)
> return NVME_SUCCESS;
> }
>
> -static uint16_t nvme_identify_ctrl(NvmeCtrl *n, NvmeIdentify *c)
> +static uint16_t nvme_identify_ctrl(NvmeCtrl *n, NvmeIdentify *c,
> + NvmeRequest *req)
> {
> uint64_t prp1 = le64_to_cpu(c->prp1);
> uint64_t prp2 = le64_to_cpu(c->prp2);
> @@ -883,10 +950,11 @@ static uint16_t nvme_identify_ctrl(NvmeCtrl *n, NvmeIdentify *c)
> trace_nvme_identify_ctrl();
>
> return nvme_dma_read_prp(n, (uint8_t *)&n->id_ctrl, sizeof(n->id_ctrl),
> - prp1, prp2);
> + prp1, prp2, req);
> }
>
> -static uint16_t nvme_identify_ns(NvmeCtrl *n, NvmeIdentify *c)
> +static uint16_t nvme_identify_ns(NvmeCtrl *n, NvmeIdentify *c,
> + NvmeRequest *req)
> {
> NvmeNamespace *ns;
> uint32_t nsid = le32_to_cpu(c->nsid);
> @@ -903,10 +971,11 @@ static uint16_t nvme_identify_ns(NvmeCtrl *n, NvmeIdentify *c)
> ns = &n->namespaces[nsid - 1];
>
> return nvme_dma_read_prp(n, (uint8_t *)&ns->id_ns, sizeof(ns->id_ns),
> - prp1, prp2);
> + prp1, prp2, req);
> }
>
> -static uint16_t nvme_identify_ns_list(NvmeCtrl *n, NvmeIdentify *c)
> +static uint16_t nvme_identify_ns_list(NvmeCtrl *n, NvmeIdentify *c,
> + NvmeRequest *req)
> {
> static const int data_len = 4 * KiB;
> uint32_t min_nsid = le32_to_cpu(c->nsid);
> @@ -928,12 +997,13 @@ static uint16_t nvme_identify_ns_list(NvmeCtrl *n, NvmeIdentify *c)
> break;
> }
> }
> - ret = nvme_dma_read_prp(n, (uint8_t *)list, data_len, prp1, prp2);
> + ret = nvme_dma_read_prp(n, (uint8_t *)list, data_len, prp1, prp2, req);
> g_free(list);
> return ret;
> }
>
> -static uint16_t nvme_identify_ns_descr_list(NvmeCtrl *n, NvmeCmd *c)
> +static uint16_t nvme_identify_ns_descr_list(NvmeCtrl *n, NvmeIdentify *c,
> + NvmeRequest *req)
> {
> static const int len = 4096;
>
> @@ -963,24 +1033,24 @@ static uint16_t nvme_identify_ns_descr_list(NvmeCtrl *n, NvmeCmd *c)
> list->nidl = 0x10;
> *(uint32_t *) &list->nid[12] = cpu_to_be32(nsid);
>
> - ret = nvme_dma_read_prp(n, (uint8_t *) list, len, prp1, prp2);
> + ret = nvme_dma_read_prp(n, (uint8_t *) list, len, prp1, prp2, req);
> g_free(list);
> return ret;
> }
>
> -static uint16_t nvme_identify(NvmeCtrl *n, NvmeCmd *cmd)
> +static uint16_t nvme_identify(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
> {
> NvmeIdentify *c = (NvmeIdentify *)cmd;
>
> switch (le32_to_cpu(c->cns)) {
> case 0x00:
> - return nvme_identify_ns(n, c);
> + return nvme_identify_ns(n, c, req);
> case 0x01:
> - return nvme_identify_ctrl(n, c);
> + return nvme_identify_ctrl(n, c, req);
> case 0x02:
> - return nvme_identify_ns_list(n, c);
> + return nvme_identify_ns_list(n, c, req);
> case 0x03:
> - return nvme_identify_ns_descr_list(n, cmd);
> + return nvme_identify_ns_descr_list(n, c, req);
> default:
> trace_nvme_err_invalid_identify_cns(le32_to_cpu(c->cns));
> return NVME_INVALID_FIELD | NVME_DNR;
> @@ -1039,15 +1109,16 @@ static inline uint64_t nvme_get_timestamp(const NvmeCtrl *n)
> return cpu_to_le64(ts.all);
> }
>
> -static uint16_t nvme_get_feature_timestamp(NvmeCtrl *n, NvmeCmd *cmd)
> +static uint16_t nvme_get_feature_timestamp(NvmeCtrl *n, NvmeCmd *cmd,
> + NvmeRequest *req)
> {
> uint64_t prp1 = le64_to_cpu(cmd->prp1);
> uint64_t prp2 = le64_to_cpu(cmd->prp2);
>
> uint64_t timestamp = nvme_get_timestamp(n);
>
> - return nvme_dma_read_prp(n, (uint8_t *)×tamp,
> - sizeof(timestamp), prp1, prp2);
> + return nvme_dma_read_prp(n, (uint8_t *)×tamp, sizeof(timestamp),
> + prp1, prp2, req);
> }
>
> static uint16_t nvme_get_feature(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
> @@ -1081,7 +1152,7 @@ static uint16_t nvme_get_feature(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
> trace_nvme_getfeat_numq(result);
> break;
> case NVME_TIMESTAMP:
> - return nvme_get_feature_timestamp(n, cmd);
> + return nvme_get_feature_timestamp(n, cmd, req);
> case NVME_INTERRUPT_COALESCING:
> result = cpu_to_le32(n->features.int_coalescing);
> break;
> @@ -1107,7 +1178,8 @@ static uint16_t nvme_get_feature(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
> return NVME_SUCCESS;
> }
>
> -static uint16_t nvme_set_feature_timestamp(NvmeCtrl *n, NvmeCmd *cmd)
> +static uint16_t nvme_set_feature_timestamp(NvmeCtrl *n, NvmeCmd *cmd,
> + NvmeRequest *req)
> {
> uint16_t ret;
> uint64_t timestamp;
> @@ -1115,7 +1187,7 @@ static uint16_t nvme_set_feature_timestamp(NvmeCtrl *n, NvmeCmd *cmd)
> uint64_t prp2 = le64_to_cpu(cmd->prp2);
>
> ret = nvme_dma_write_prp(n, (uint8_t *)×tamp,
> - sizeof(timestamp), prp1, prp2);
> + sizeof(timestamp), prp1, prp2, req);
> if (ret != NVME_SUCCESS) {
> return ret;
> }
> @@ -1163,7 +1235,7 @@ static uint16_t nvme_set_feature(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
> ((n->params.num_queues - 2) << 16));
> break;
> case NVME_TIMESTAMP:
> - return nvme_set_feature_timestamp(n, cmd);
> + return nvme_set_feature_timestamp(n, cmd, req);
> case NVME_ASYNCHRONOUS_EVENT_CONF:
> n->features.async_config = dw11;
> break;
> @@ -1212,7 +1284,7 @@ static uint16_t nvme_admin_cmd(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
> case NVME_ADM_CMD_CREATE_CQ:
> return nvme_create_cq(n, cmd);
> case NVME_ADM_CMD_IDENTIFY:
> - return nvme_identify(n, cmd);
> + return nvme_identify(n, cmd, req);
> case NVME_ADM_CMD_ABORT:
> return nvme_abort(n, cmd, req);
> case NVME_ADM_CMD_SET_FEATURES:
> @@ -1273,6 +1345,18 @@ static void nvme_process_aers(void *opaque)
> }
> }
>
> +static void nvme_init_req(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
> +{
> + memset(&req->cqe, 0, sizeof(req->cqe));
> + req->cqe.cid = cmd->cid;
> + req->cid = le16_to_cpu(cmd->cid);
> +
> + memcpy(&req->cmd, cmd, sizeof(NvmeCmd));
> + req->status = NVME_SUCCESS;
> + req->is_cmb = false;
> + req->is_write = false;
What is the use case for this one ?
It does not seem to be referenced in this patch.
BR
Beata
> +}
> +
> static void nvme_process_sq(void *opaque)
> {
> NvmeSQueue *sq = opaque;
> @@ -1292,9 +1376,8 @@ static void nvme_process_sq(void *opaque)
> req = QTAILQ_FIRST(&sq->req_list);
> QTAILQ_REMOVE(&sq->req_list, req, entry);
> QTAILQ_INSERT_TAIL(&sq->out_req_list, req, entry);
> - memset(&req->cqe, 0, sizeof(req->cqe));
> - req->cqe.cid = cmd.cid;
> - req->cid = le16_to_cpu(cmd.cid);
> +
> + nvme_init_req(n, &cmd, req);
>
> status = sq->sqid ? nvme_io_cmd(n, &cmd, req) :
> nvme_admin_cmd(n, &cmd, req);
> @@ -1815,7 +1898,7 @@ static void nvme_init_cmb(NvmeCtrl *n, PCIDevice *pci_dev)
>
> NVME_CMBSZ_SET_SQS(n->bar.cmbsz, 1);
> NVME_CMBSZ_SET_CQS(n->bar.cmbsz, 1);
> - NVME_CMBSZ_SET_LISTS(n->bar.cmbsz, 0);
> + NVME_CMBSZ_SET_LISTS(n->bar.cmbsz, 1);
> NVME_CMBSZ_SET_RDS(n->bar.cmbsz, 1);
> NVME_CMBSZ_SET_WDS(n->bar.cmbsz, 1);
> NVME_CMBSZ_SET_SZU(n->bar.cmbsz, 2);
> diff --git a/hw/block/nvme.h b/hw/block/nvme.h
> index 3f7bd627e824..add9ff335aa5 100644
> --- a/hw/block/nvme.h
> +++ b/hw/block/nvme.h
> @@ -28,11 +28,13 @@ typedef struct NvmeRequest {
> BlockAIOCB *aiocb;
> uint16_t status;
> uint16_t cid;
> - bool has_sg;
> + bool is_cmb;
> + bool is_write;
> NvmeCqe cqe;
> BlockAcctCookie acct;
> QEMUSGList qsg;
> QEMUIOVector iov;
> + NvmeCmd cmd;
> QTAILQ_ENTRY(NvmeRequest)entry;
> } NvmeRequest;
>
> diff --git a/hw/block/trace-events b/hw/block/trace-events
> index f62fa99dc2cd..e81bb3a64ed7 100644
> --- a/hw/block/trace-events
> +++ b/hw/block/trace-events
> @@ -33,6 +33,7 @@ nvme_irq_msix(uint32_t vector) "raising MSI-X IRQ vector %u"
> nvme_irq_pin(void) "pulsing IRQ pin"
> nvme_irq_masked(void) "IRQ is masked"
> nvme_dma_read(uint64_t prp1, uint64_t prp2) "DMA read, prp1=0x%"PRIx64" prp2=0x%"PRIx64""
> +nvme_map_prp(uint16_t cid, uint8_t opc, uint64_t trans_len, uint32_t len, uint64_t prp1, uint64_t prp2, int num_prps) "cid %"PRIu16" opc 0x%"PRIx8" trans_len %"PRIu64" len %"PRIu32" prp1 0x%"PRIx64" prp2 0x%"PRIx64" num_prps %d"
> nvme_rw(const char *verb, uint32_t blk_count, uint64_t byte_count, uint64_t lba) "%s %"PRIu32" blocks (%"PRIu64" bytes) from LBA %"PRIu64""
> nvme_create_sq(uint64_t addr, uint16_t sqid, uint16_t cqid, uint16_t qsize, uint16_t qflags) "create submission queue, addr=0x%"PRIx64", sqid=%"PRIu16", cqid=%"PRIu16", qsize=%"PRIu16", qflags=%"PRIu16""
> nvme_create_cq(uint64_t addr, uint16_t cqid, uint16_t vector, uint16_t size, uint16_t qflags, int ien) "create completion queue, addr=0x%"PRIx64", cqid=%"PRIu16", vector=%"PRIu16", qsize=%"PRIu16", qflags=%"PRIu16", ien=%d"
> diff --git a/include/block/nvme.h b/include/block/nvme.h
> index f0f5728b5ec4..d4990db4fdf8 100644
> --- a/include/block/nvme.h
> +++ b/include/block/nvme.h
> @@ -427,6 +427,7 @@ enum NvmeStatusCodes {
> NVME_CMD_ABORT_MISSING_FUSE = 0x000a,
> NVME_INVALID_NSID = 0x000b,
> NVME_CMD_SEQ_ERROR = 0x000c,
> + NVME_INVALID_USE_OF_CMB = 0x0012,
> NVME_LBA_RANGE = 0x0080,
> NVME_CAP_EXCEEDED = 0x0081,
> NVME_NS_NOT_READY = 0x0082,
> --
> 2.23.0
>
>
^ permalink raw reply [flat|nested] 52+ messages in thread* Re: [PATCH v2 13/20] nvme: refactor prp mapping
2019-11-12 15:23 ` Beata Michalska
@ 2019-11-20 9:39 ` Klaus Birkelund
2019-11-25 13:15 ` Beata Michalska
0 siblings, 1 reply; 52+ messages in thread
From: Klaus Birkelund @ 2019-11-20 9:39 UTC (permalink / raw)
To: Beata Michalska
Cc: Kevin Wolf, qemu-block, qemu-devel, Max Reitz, Paul Durrant, Keith Busch
On Tue, Nov 12, 2019 at 03:23:43PM +0000, Beata Michalska wrote:
> Hi Klaus,
>
> On Tue, 15 Oct 2019 at 11:57, Klaus Jensen <its@irrelevant.dk> wrote:
> >
> > Instead of handling both QSGs and IOVs in multiple places, simply use
> > QSGs everywhere by assuming that the request does not involve the
> > controller memory buffer (CMB). If the request is found to involve the
> > CMB, convert the QSG to an IOV and issue the I/O. The QSG is converted
> > to an IOV by the dma helpers anyway, so the CMB path is not unfairly
> > affected by this simplifying change.
> >
>
> Out of curiosity, in how many cases the SG list will have to
> be converted to IOV ? Does that justify creating the SG list in vain ?
>
You got me wondering. Only using QSGs does not really remove much
complexity, so I readded the direct use of IOVs for the CMB path. There
is no harm in that.
> > +static uint16_t nvme_map_prp(NvmeCtrl *n, QEMUSGList *qsg, uint64_t prp1,
> > + uint64_t prp2, uint32_t len, NvmeRequest *req)
> > {
> > hwaddr trans_len = n->page_size - (prp1 % n->page_size);
> > trans_len = MIN(len, trans_len);
> > int num_prps = (len >> n->page_bits) + 1;
> > + uint16_t status = NVME_SUCCESS;
> > + bool prp_list_in_cmb = false;
> > +
> > + trace_nvme_map_prp(req->cid, req->cmd.opcode, trans_len, len, prp1, prp2,
> > + num_prps);
> >
> > if (unlikely(!prp1)) {
> > trace_nvme_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)) {
> > - qsg->nsg = 0;
> > - qemu_iovec_init(iov, num_prps);
> > - qemu_iovec_add(iov, (void *)&n->cmbuf[prp1 - n->ctrl_mem.addr], trans_len);
> > - } else {
> > - pci_dma_sglist_init(qsg, &n->parent_obj, num_prps);
> > - qemu_sglist_add(qsg, prp1, trans_len);
> > }
> > +
> > + if (nvme_addr_is_cmb(n, prp1)) {
> > + req->is_cmb = true;
> > + }
> > +
> This seems to be used here and within read/write functions which are calling
> this one. Maybe there is a nicer way to track that instead of passing
> the request
> from multiple places ?
>
Hmm. Whether or not the command reads/writes from the CMB is really only
something you can determine by looking at the PRPs (which is done in
nvme_map_prp), so I think this is the right way to track it. Or do you
have something else in mind?
> > + pci_dma_sglist_init(qsg, &n->parent_obj, num_prps);
> > + qemu_sglist_add(qsg, prp1, trans_len);
> > +
> > len -= trans_len;
> > if (len) {
> > if (unlikely(!prp2)) {
> > trace_nvme_err_invalid_prp2_missing();
> > + status = NVME_INVALID_FIELD | NVME_DNR;
> > goto unmap;
> > }
> > +
> > if (len > n->page_size) {
> > uint64_t prp_list[n->max_prp_ents];
> > uint32_t nents, prp_trans;
> > int i = 0;
> >
> > + if (nvme_addr_is_cmb(n, prp2)) {
> > + prp_list_in_cmb = true;
> > + }
> > +
> > nents = (len + n->page_size - 1) >> n->page_bits;
> > prp_trans = MIN(n->max_prp_ents, nents) * sizeof(uint64_t);
> > - nvme_addr_read(n, prp2, (void *)prp_list, prp_trans);
> > + nvme_addr_read(n, prp2, (void *) prp_list, prp_trans);
> > while (len != 0) {
> > + bool addr_is_cmb;
> > uint64_t prp_ent = le64_to_cpu(prp_list[i]);
> >
> > 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);
> > + status = NVME_INVALID_FIELD | NVME_DNR;
> > + goto unmap;
> > + }
> > +
> > + addr_is_cmb = nvme_addr_is_cmb(n, prp_ent);
> > + if ((prp_list_in_cmb && !addr_is_cmb) ||
> > + (!prp_list_in_cmb && addr_is_cmb)) {
>
> Minor: Same condition (based on different vars) is being used in
> multiple places. Might be worth to move it outside and just pass in
> the needed values.
>
I'm really not sure what I was smoking when writing those conditions.
It's just `var != nvme_addr_is_cmb(n, prp_ent)`. I fixed that. No need
to pull it out I think.
> > static uint16_t nvme_dma_write_prp(NvmeCtrl *n, uint8_t *ptr, uint32_t len,
> > - uint64_t prp1, uint64_t prp2)
> > + uint64_t prp1, uint64_t prp2, NvmeRequest *req)
> > {
> > QEMUSGList qsg;
> > - QEMUIOVector iov;
> > uint16_t status = NVME_SUCCESS;
> >
> > - if (nvme_map_prp(&qsg, &iov, prp1, prp2, len, n)) {
> > - return NVME_INVALID_FIELD | NVME_DNR;
> > + status = nvme_map_prp(n, &qsg, prp1, prp2, len, req);
> > + if (status) {
> > + return status;
> > }
> > - if (qsg.nsg > 0) {
> > - if (dma_buf_write(ptr, len, &qsg)) {
> > - status = NVME_INVALID_FIELD | NVME_DNR;
> > - }
> > - qemu_sglist_destroy(&qsg);
> > - } else {
> > - if (qemu_iovec_to_buf(&iov, 0, ptr, len) != len) {
> > +
> > + if (req->is_cmb) {
> > + QEMUIOVector iov;
> > +
> > + qemu_iovec_init(&iov, qsg.nsg);
> > + dma_to_cmb(n, &qsg, &iov);
> > +
> > + if (unlikely(qemu_iovec_to_buf(&iov, 0, ptr, len) != len)) {
> > + trace_nvme_err_invalid_dma();
> > status = NVME_INVALID_FIELD | NVME_DNR;
> > }
> > +
> > qemu_iovec_destroy(&iov);
> > +
> Aren't we missing the sglist cleanup here ?
> (goto as in nvme_dma_read_prp)
>
> Aside: both nvme_write_prp and nvme_read_prp seem to differ only
> with the final call to either dma or qemu_ioves calls.
> Might be worth to unify it and move it to a single function with additional
> parameter that will determine the type of the transaction.
>
True. I have combined them into a single nvme_dma_prp function.
> > +static void nvme_init_req(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
> > +{
> > + memset(&req->cqe, 0, sizeof(req->cqe));
> > + req->cqe.cid = cmd->cid;
> > + req->cid = le16_to_cpu(cmd->cid);
> > +
> > + memcpy(&req->cmd, cmd, sizeof(NvmeCmd));
> > + req->status = NVME_SUCCESS;
> > + req->is_cmb = false;
> > + req->is_write = false;
>
> What is the use case for this one ?
> It does not seem to be referenced in this patch.
>
That crept in there by mistake. I have removed it.
^ permalink raw reply [flat|nested] 52+ messages in thread* Re: [PATCH v2 13/20] nvme: refactor prp mapping
2019-11-20 9:39 ` Klaus Birkelund
@ 2019-11-25 13:15 ` Beata Michalska
0 siblings, 0 replies; 52+ messages in thread
From: Beata Michalska @ 2019-11-25 13:15 UTC (permalink / raw)
To: Klaus Birkelund
Cc: Kevin Wolf, qemu-block, qemu-devel, Max Reitz, Paul Durrant, Keith Busch
On Wed, 20 Nov 2019 at 09:39, Klaus Birkelund <its@irrelevant.dk> wrote:
>
> On Tue, Nov 12, 2019 at 03:23:43PM +0000, Beata Michalska wrote:
> > Hi Klaus,
> >
> > On Tue, 15 Oct 2019 at 11:57, Klaus Jensen <its@irrelevant.dk> wrote:
> > >
> > > Instead of handling both QSGs and IOVs in multiple places, simply use
> > > QSGs everywhere by assuming that the request does not involve the
> > > controller memory buffer (CMB). If the request is found to involve the
> > > CMB, convert the QSG to an IOV and issue the I/O. The QSG is converted
> > > to an IOV by the dma helpers anyway, so the CMB path is not unfairly
> > > affected by this simplifying change.
> > >
> >
> > Out of curiosity, in how many cases the SG list will have to
> > be converted to IOV ? Does that justify creating the SG list in vain ?
> >
>
> You got me wondering. Only using QSGs does not really remove much
> complexity, so I readded the direct use of IOVs for the CMB path. There
> is no harm in that.
>
> > > +static uint16_t nvme_map_prp(NvmeCtrl *n, QEMUSGList *qsg, uint64_t prp1,
> > > + uint64_t prp2, uint32_t len, NvmeRequest *req)
> > > {
> > > hwaddr trans_len = n->page_size - (prp1 % n->page_size);
> > > trans_len = MIN(len, trans_len);
> > > int num_prps = (len >> n->page_bits) + 1;
> > > + uint16_t status = NVME_SUCCESS;
> > > + bool prp_list_in_cmb = false;
> > > +
> > > + trace_nvme_map_prp(req->cid, req->cmd.opcode, trans_len, len, prp1, prp2,
> > > + num_prps);
> > >
> > > if (unlikely(!prp1)) {
> > > trace_nvme_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)) {
> > > - qsg->nsg = 0;
> > > - qemu_iovec_init(iov, num_prps);
> > > - qemu_iovec_add(iov, (void *)&n->cmbuf[prp1 - n->ctrl_mem.addr], trans_len);
> > > - } else {
> > > - pci_dma_sglist_init(qsg, &n->parent_obj, num_prps);
> > > - qemu_sglist_add(qsg, prp1, trans_len);
> > > }
> > > +
> > > + if (nvme_addr_is_cmb(n, prp1)) {
> > > + req->is_cmb = true;
> > > + }
> > > +
> > This seems to be used here and within read/write functions which are calling
> > this one. Maybe there is a nicer way to track that instead of passing
> > the request
> > from multiple places ?
> >
>
> Hmm. Whether or not the command reads/writes from the CMB is really only
> something you can determine by looking at the PRPs (which is done in
> nvme_map_prp), so I think this is the right way to track it. Or do you
> have something else in mind?
>
I think what I mean is that is seems that this variable is being used only in
functions that call map_prp directly, but in order to set that variable within
the req structure this needs to be passed along from the top level of command
submission instead of maybe having additional param to map_prpr to set it to be
CMB command or not. If that makes sense.
BR
Beata
> > > + pci_dma_sglist_init(qsg, &n->parent_obj, num_prps);
> > > + qemu_sglist_add(qsg, prp1, trans_len);
> > > +
> > > len -= trans_len;
> > > if (len) {
> > > if (unlikely(!prp2)) {
> > > trace_nvme_err_invalid_prp2_missing();
> > > + status = NVME_INVALID_FIELD | NVME_DNR;
> > > goto unmap;
> > > }
> > > +
> > > if (len > n->page_size) {
> > > uint64_t prp_list[n->max_prp_ents];
> > > uint32_t nents, prp_trans;
> > > int i = 0;
> > >
> > > + if (nvme_addr_is_cmb(n, prp2)) {
> > > + prp_list_in_cmb = true;
> > > + }
> > > +
> > > nents = (len + n->page_size - 1) >> n->page_bits;
> > > prp_trans = MIN(n->max_prp_ents, nents) * sizeof(uint64_t);
> > > - nvme_addr_read(n, prp2, (void *)prp_list, prp_trans);
> > > + nvme_addr_read(n, prp2, (void *) prp_list, prp_trans);
> > > while (len != 0) {
> > > + bool addr_is_cmb;
> > > uint64_t prp_ent = le64_to_cpu(prp_list[i]);
> > >
> > > 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);
> > > + status = NVME_INVALID_FIELD | NVME_DNR;
> > > + goto unmap;
> > > + }
> > > +
> > > + addr_is_cmb = nvme_addr_is_cmb(n, prp_ent);
> > > + if ((prp_list_in_cmb && !addr_is_cmb) ||
> > > + (!prp_list_in_cmb && addr_is_cmb)) {
> >
> > Minor: Same condition (based on different vars) is being used in
> > multiple places. Might be worth to move it outside and just pass in
> > the needed values.
> >
>
> I'm really not sure what I was smoking when writing those conditions.
> It's just `var != nvme_addr_is_cmb(n, prp_ent)`. I fixed that. No need
> to pull it out I think.
>
> > > static uint16_t nvme_dma_write_prp(NvmeCtrl *n, uint8_t *ptr, uint32_t len,
> > > - uint64_t prp1, uint64_t prp2)
> > > + uint64_t prp1, uint64_t prp2, NvmeRequest *req)
> > > {
> > > QEMUSGList qsg;
> > > - QEMUIOVector iov;
> > > uint16_t status = NVME_SUCCESS;
> > >
> > > - if (nvme_map_prp(&qsg, &iov, prp1, prp2, len, n)) {
> > > - return NVME_INVALID_FIELD | NVME_DNR;
> > > + status = nvme_map_prp(n, &qsg, prp1, prp2, len, req);
> > > + if (status) {
> > > + return status;
> > > }
> > > - if (qsg.nsg > 0) {
> > > - if (dma_buf_write(ptr, len, &qsg)) {
> > > - status = NVME_INVALID_FIELD | NVME_DNR;
> > > - }
> > > - qemu_sglist_destroy(&qsg);
> > > - } else {
> > > - if (qemu_iovec_to_buf(&iov, 0, ptr, len) != len) {
> > > +
> > > + if (req->is_cmb) {
> > > + QEMUIOVector iov;
> > > +
> > > + qemu_iovec_init(&iov, qsg.nsg);
> > > + dma_to_cmb(n, &qsg, &iov);
> > > +
> > > + if (unlikely(qemu_iovec_to_buf(&iov, 0, ptr, len) != len)) {
> > > + trace_nvme_err_invalid_dma();
> > > status = NVME_INVALID_FIELD | NVME_DNR;
> > > }
> > > +
> > > qemu_iovec_destroy(&iov);
> > > +
> > Aren't we missing the sglist cleanup here ?
> > (goto as in nvme_dma_read_prp)
> >
> > Aside: both nvme_write_prp and nvme_read_prp seem to differ only
> > with the final call to either dma or qemu_ioves calls.
> > Might be worth to unify it and move it to a single function with additional
> > parameter that will determine the type of the transaction.
> >
>
> True. I have combined them into a single nvme_dma_prp function.
>
> > > +static void nvme_init_req(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
> > > +{
> > > + memset(&req->cqe, 0, sizeof(req->cqe));
> > > + req->cqe.cid = cmd->cid;
> > > + req->cid = le16_to_cpu(cmd->cid);
> > > +
> > > + memcpy(&req->cmd, cmd, sizeof(NvmeCmd));
> > > + req->status = NVME_SUCCESS;
> > > + req->is_cmb = false;
> > > + req->is_write = false;
> >
> > What is the use case for this one ?
> > It does not seem to be referenced in this patch.
> >
>
> That crept in there by mistake. I have removed it.
^ permalink raw reply [flat|nested] 52+ messages in thread
* [PATCH v2 14/20] nvme: allow multiple aios per command
2019-10-15 10:38 [PATCH v2 00/20] nvme: support NVMe v1.3d, SGLs and multiple namespaces Klaus Jensen
` (12 preceding siblings ...)
2019-10-15 10:38 ` [PATCH v2 13/20] nvme: refactor prp mapping Klaus Jensen
@ 2019-10-15 10:38 ` Klaus Jensen
2019-11-12 15:25 ` Beata Michalska
2019-10-15 10:38 ` [PATCH v2 15/20] nvme: add support for scatter gather lists Klaus Jensen
` (9 subsequent siblings)
23 siblings, 1 reply; 52+ messages in thread
From: Klaus Jensen @ 2019-10-15 10:38 UTC (permalink / raw)
To: qemu-block
Cc: Kevin Wolf, Fam Zheng, Javier Gonzalez, qemu-devel, Max Reitz,
Keith Busch, Paul Durrant, Stephen Bates
This refactors how the device issues asynchronous block backend
requests. The NvmeRequest now holds a queue of NvmeAIOs that are
associated with the command. This allows multiple aios to be issued for
a command. Only when all requests have been completed will the device
post a completion queue entry.
Because the device is currently guaranteed to only issue a single aio
request per command, the benefit is not immediately obvious. But this
functionality is required to support metadata.
Signed-off-by: Klaus Jensen <klaus.jensen@cnexlabs.com>
Signed-off-by: Klaus Jensen <k.jensen@samsung.com>
---
hw/block/nvme.c | 455 +++++++++++++++++++++++++++++++++---------
hw/block/nvme.h | 165 ++++++++++++---
hw/block/trace-events | 8 +
3 files changed, 511 insertions(+), 117 deletions(-)
diff --git a/hw/block/nvme.c b/hw/block/nvme.c
index cbc0b6a660b6..f4b9bd36a04e 100644
--- a/hw/block/nvme.c
+++ b/hw/block/nvme.c
@@ -25,6 +25,8 @@
* Default: 64
* cmb_size_mb=<uint32> : Size of Controller Memory Buffer in MBs.
* Default: 0 (disabled)
+ * mdts=<uint8> : Maximum Data Transfer Size (power of two)
+ * Default: 7
*/
#include "qemu/osdep.h"
@@ -56,6 +58,7 @@
} while (0)
static void nvme_process_sq(void *opaque);
+static void nvme_aio_cb(void *opaque, int ret);
static inline bool nvme_addr_is_cmb(NvmeCtrl *n, hwaddr addr)
{
@@ -197,7 +200,7 @@ static uint16_t nvme_map_prp(NvmeCtrl *n, QEMUSGList *qsg, uint64_t prp1,
}
if (nvme_addr_is_cmb(n, prp1)) {
- req->is_cmb = true;
+ nvme_req_set_cmb(req);
}
pci_dma_sglist_init(qsg, &n->parent_obj, num_prps);
@@ -255,8 +258,8 @@ static uint16_t nvme_map_prp(NvmeCtrl *n, QEMUSGList *qsg, uint64_t prp1,
}
addr_is_cmb = nvme_addr_is_cmb(n, prp_ent);
- if ((req->is_cmb && !addr_is_cmb) ||
- (!req->is_cmb && addr_is_cmb)) {
+ if ((nvme_req_is_cmb(req) && !addr_is_cmb) ||
+ (!nvme_req_is_cmb(req) && addr_is_cmb)) {
status = NVME_INVALID_USE_OF_CMB | NVME_DNR;
goto unmap;
}
@@ -269,8 +272,8 @@ static uint16_t nvme_map_prp(NvmeCtrl *n, QEMUSGList *qsg, uint64_t prp1,
}
} else {
bool addr_is_cmb = nvme_addr_is_cmb(n, prp2);
- if ((req->is_cmb && !addr_is_cmb) ||
- (!req->is_cmb && addr_is_cmb)) {
+ if ((nvme_req_is_cmb(req) && !addr_is_cmb) ||
+ (!nvme_req_is_cmb(req) && addr_is_cmb)) {
status = NVME_INVALID_USE_OF_CMB | NVME_DNR;
goto unmap;
}
@@ -312,7 +315,7 @@ static uint16_t nvme_dma_write_prp(NvmeCtrl *n, uint8_t *ptr, uint32_t len,
return status;
}
- if (req->is_cmb) {
+ if (nvme_req_is_cmb(req)) {
QEMUIOVector iov;
qemu_iovec_init(&iov, qsg.nsg);
@@ -341,19 +344,18 @@ static uint16_t nvme_dma_write_prp(NvmeCtrl *n, uint8_t *ptr, uint32_t len,
static uint16_t nvme_dma_read_prp(NvmeCtrl *n, uint8_t *ptr, uint32_t len,
uint64_t prp1, uint64_t prp2, NvmeRequest *req)
{
- QEMUSGList qsg;
uint16_t status = NVME_SUCCESS;
- status = nvme_map_prp(n, &qsg, prp1, prp2, len, req);
+ status = nvme_map_prp(n, &req->qsg, prp1, prp2, len, req);
if (status) {
return status;
}
- if (req->is_cmb) {
+ if (nvme_req_is_cmb(req)) {
QEMUIOVector iov;
- qemu_iovec_init(&iov, qsg.nsg);
- dma_to_cmb(n, &qsg, &iov);
+ qemu_iovec_init(&iov, req->qsg.nsg);
+ dma_to_cmb(n, &req->qsg, &iov);
if (unlikely(qemu_iovec_from_buf(&iov, 0, ptr, len) != len)) {
trace_nvme_err_invalid_dma();
@@ -365,17 +367,137 @@ static uint16_t nvme_dma_read_prp(NvmeCtrl *n, uint8_t *ptr, uint32_t len,
goto out;
}
- if (unlikely(dma_buf_read(ptr, len, &qsg))) {
+ if (unlikely(dma_buf_read(ptr, len, &req->qsg))) {
trace_nvme_err_invalid_dma();
status = NVME_INVALID_FIELD | NVME_DNR;
}
out:
- qemu_sglist_destroy(&qsg);
+ qemu_sglist_destroy(&req->qsg);
return status;
}
+static uint16_t nvme_map(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
+{
+ NvmeNamespace *ns = req->ns;
+
+ uint32_t len = req->nlb << nvme_ns_lbads(ns);
+ uint64_t prp1 = le64_to_cpu(cmd->prp1);
+ uint64_t prp2 = le64_to_cpu(cmd->prp2);
+
+ return nvme_map_prp(n, &req->qsg, prp1, prp2, len, req);
+}
+
+static void nvme_aio_destroy(NvmeAIO *aio)
+{
+ if (aio->iov.nalloc) {
+ qemu_iovec_destroy(&aio->iov);
+ }
+
+ g_free(aio);
+}
+
+static NvmeAIO *nvme_aio_new(BlockBackend *blk, int64_t offset,
+ QEMUSGList *qsg, NvmeRequest *req, NvmeAIOCompletionFunc *cb)
+{
+ NvmeAIO *aio = g_malloc0(sizeof(*aio));
+
+ *aio = (NvmeAIO) {
+ .blk = blk,
+ .offset = offset,
+ .req = req,
+ .qsg = qsg,
+ .cb = cb,
+ };
+
+ if (qsg && nvme_req_is_cmb(req)) {
+ NvmeCtrl *n = nvme_ctrl(req);
+
+ qemu_iovec_init(&aio->iov, qsg->nsg);
+ dma_to_cmb(n, qsg, &aio->iov);
+
+ aio->qsg = NULL;
+ }
+
+ return aio;
+}
+
+static inline void nvme_req_register_aio(NvmeRequest *req, NvmeAIO *aio,
+ NvmeAIOOp opc)
+{
+ aio->opc = opc;
+
+ trace_nvme_req_register_aio(nvme_cid(req), aio, blk_name(aio->blk),
+ aio->offset, aio->qsg ? aio->qsg->size : aio->iov.size,
+ nvme_aio_opc_str(aio), req);
+
+ if (req) {
+ QTAILQ_INSERT_TAIL(&req->aio_tailq, aio, tailq_entry);
+ }
+}
+
+static void nvme_aio(NvmeAIO *aio)
+{
+ BlockBackend *blk = aio->blk;
+ BlockAcctCookie *acct = &aio->acct;
+ BlockAcctStats *stats = blk_get_stats(blk);
+
+ bool is_write, dma;
+
+ switch (aio->opc) {
+ case NVME_AIO_OPC_NONE:
+ break;
+
+ case NVME_AIO_OPC_FLUSH:
+ block_acct_start(stats, acct, 0, BLOCK_ACCT_FLUSH);
+ aio->aiocb = blk_aio_flush(blk, nvme_aio_cb, aio);
+ break;
+
+ case NVME_AIO_OPC_WRITE_ZEROES:
+ block_acct_start(stats, acct, aio->iov.size, BLOCK_ACCT_WRITE);
+ aio->aiocb = blk_aio_pwrite_zeroes(aio->blk, aio->offset,
+ aio->iov.size, BDRV_REQ_MAY_UNMAP, nvme_aio_cb, aio);
+ break;
+
+ case NVME_AIO_OPC_READ:
+ case NVME_AIO_OPC_WRITE:
+ dma = aio->qsg != NULL;
+ is_write = (aio->opc == NVME_AIO_OPC_WRITE);
+
+ block_acct_start(stats, acct,
+ dma ? aio->qsg->size : aio->iov.size,
+ is_write ? BLOCK_ACCT_WRITE : BLOCK_ACCT_READ);
+
+ if (dma) {
+ aio->aiocb = is_write ?
+ dma_blk_write(blk, aio->qsg, aio->offset,
+ BDRV_SECTOR_SIZE, nvme_aio_cb, aio) :
+ dma_blk_read(blk, aio->qsg, aio->offset,
+ BDRV_SECTOR_SIZE, nvme_aio_cb, aio);
+
+ return;
+ }
+
+ aio->aiocb = is_write ?
+ blk_aio_pwritev(blk, aio->offset, &aio->iov, 0,
+ nvme_aio_cb, aio) :
+ blk_aio_preadv(blk, aio->offset, &aio->iov, 0,
+ nvme_aio_cb, aio);
+
+ break;
+ }
+}
+
+static void nvme_rw_aio(BlockBackend *blk, uint64_t offset, QEMUSGList *qsg,
+ NvmeRequest *req)
+{
+ NvmeAIO *aio = nvme_aio_new(blk, offset, qsg, req, NULL);
+ nvme_req_register_aio(req, aio, nvme_req_is_write(req) ?
+ NVME_AIO_OPC_WRITE : NVME_AIO_OPC_READ);
+ nvme_aio(aio);
+}
+
static void nvme_post_cqes(void *opaque)
{
NvmeCQueue *cq = opaque;
@@ -411,6 +533,11 @@ static void nvme_enqueue_req_completion(NvmeCQueue *cq, NvmeRequest *req)
assert(cq->cqid == req->sq->cqid);
trace_nvme_enqueue_req_completion(req->cid, cq->cqid, req->status);
+
+ if (req->qsg.nalloc) {
+ qemu_sglist_destroy(&req->qsg);
+ }
+
QTAILQ_REMOVE(&req->sq->out_req_list, req, entry);
QTAILQ_INSERT_TAIL(&cq->req_list, req, entry);
timer_mod(cq->timer, qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) + 500);
@@ -456,135 +583,266 @@ static void nvme_clear_events(NvmeCtrl *n, uint8_t event_type)
}
}
-static void nvme_rw_cb(void *opaque, int ret)
+static void nvme_rw_cb(NvmeRequest *req, void *opaque)
{
- NvmeRequest *req = opaque;
NvmeSQueue *sq = req->sq;
NvmeCtrl *n = sq->ctrl;
NvmeCQueue *cq = n->cq[sq->cqid];
- NvmeRwCmd *rw = (NvmeRwCmd *) &req->cmd;
+
+ trace_nvme_rw_cb(req->cid, req->cmd.nsid);
+
+ nvme_enqueue_req_completion(cq, req);
+}
+
+static void nvme_aio_cb(void *opaque, int ret)
+{
+ NvmeAIO *aio = opaque;
+ NvmeRequest *req = aio->req;
+
+ BlockBackend *blk = aio->blk;
+ BlockAcctCookie *acct = &aio->acct;
+ BlockAcctStats *stats = blk_get_stats(blk);
+
+ Error *local_err = NULL;
+
+ trace_nvme_aio_cb(nvme_cid(req), aio, blk_name(aio->blk), aio->offset,
+ nvme_aio_opc_str(aio), req);
+
+ if (req) {
+ QTAILQ_REMOVE(&req->aio_tailq, aio, tailq_entry);
+ }
if (!ret) {
- block_acct_done(blk_get_stats(n->conf.blk), &req->acct);
- req->status = NVME_SUCCESS;
+ block_acct_done(stats, acct);
+
+ if (aio->cb) {
+ aio->cb(aio, aio->cb_arg);
+ }
} else {
- block_acct_failed(blk_get_stats(n->conf.blk), &req->acct);
- nvme_set_error_page(n, sq->sqid, cpu_to_le16(req->cid),
- NVME_INTERNAL_DEV_ERROR, offsetof(NvmeRwCmd, slba), rw->slba, 1);
- req->status = NVME_INTERNAL_DEV_ERROR | NVME_MORE;
- }
+ block_acct_failed(stats, acct);
+
+ if (req) {
+ NvmeRwCmd *rw = (NvmeRwCmd *) &req->cmd;
+ NvmeSQueue *sq = req->sq;
+ NvmeCtrl *n = sq->ctrl;
+ uint16_t status;
+
+ switch (aio->opc) {
+ case NVME_AIO_OPC_READ:
+ status = NVME_UNRECOVERED_READ;
+ break;
+ case NVME_AIO_OPC_WRITE:
+ case NVME_AIO_OPC_WRITE_ZEROES:
+ status = NVME_WRITE_FAULT;
+ break;
+ default:
+ status = NVME_INTERNAL_DEV_ERROR;
+ break;
+ }
- if (req->qsg.nalloc) {
- qemu_sglist_destroy(&req->qsg);
+ trace_nvme_err_aio(nvme_cid(req), aio, blk_name(aio->blk),
+ aio->offset, nvme_aio_opc_str(aio), req, status);
+
+ nvme_set_error_page(n, sq->sqid, cpu_to_le16(req->cid), status,
+ offsetof(NvmeRwCmd, slba), rw->slba, 1);
+
+ error_setg_errno(&local_err, -ret, "aio failed");
+ error_report_err(local_err);
+
+ /*
+ * An Internal Error trumps all other errors. For other errors,
+ * only set the first error encountered. Any additional errors will
+ * be recorded in the error information log page.
+ */
+ if (!req->status ||
+ nvme_is_error(status, NVME_INTERNAL_DEV_ERROR)) {
+ req->status = status;
+ }
+ }
}
- if (req->iov.nalloc) {
- qemu_iovec_destroy(&req->iov);
+
+ if (req && QTAILQ_EMPTY(&req->aio_tailq)) {
+ if (req->cb) {
+ req->cb(req, req->cb_arg);
+ } else {
+ NvmeSQueue *sq = req->sq;
+ NvmeCtrl *n = sq->ctrl;
+ NvmeCQueue *cq = n->cq[sq->cqid];
+
+ nvme_enqueue_req_completion(cq, req);
+ }
}
- nvme_enqueue_req_completion(cq, req);
+ nvme_aio_destroy(aio);
}
-static uint16_t nvme_flush(NvmeCtrl *n, NvmeNamespace *ns, NvmeCmd *cmd,
+static inline uint16_t nvme_check_mdts(NvmeCtrl *n, size_t len,
NvmeRequest *req)
{
- block_acct_start(blk_get_stats(n->conf.blk), &req->acct, 0,
- BLOCK_ACCT_FLUSH);
- req->aiocb = blk_aio_flush(n->conf.blk, nvme_rw_cb, req);
+ uint8_t mdts = n->params.mdts;
- return NVME_NO_COMPLETE;
+ if (mdts && len > n->page_size << mdts) {
+ trace_nvme_err_mdts(nvme_cid(req), n->page_size << mdts, len);
+ return NVME_INVALID_FIELD | NVME_DNR;
+ }
+
+ return NVME_SUCCESS;
}
-static uint16_t nvme_write_zeros(NvmeCtrl *n, NvmeNamespace *ns, NvmeCmd *cmd,
- NvmeRequest *req)
+static inline uint16_t nvme_check_prinfo(NvmeCtrl *n, NvmeRequest *req)
{
- NvmeRwCmd *rw = (NvmeRwCmd *)cmd;
- const uint8_t lba_index = NVME_ID_NS_FLBAS_INDEX(ns->id_ns.flbas);
- const uint8_t data_shift = ns->id_ns.lbaf[lba_index].ds;
- uint64_t slba = le64_to_cpu(rw->slba);
- uint32_t nlb = le16_to_cpu(rw->nlb) + 1;
- uint64_t offset = slba << data_shift;
- uint32_t count = nlb << data_shift;
+ NvmeRwCmd *rw = (NvmeRwCmd *) &req->cmd;
+ NvmeNamespace *ns = req->ns;
+
+ uint16_t ctrl = le16_to_cpu(rw->control);
+
+ if ((ctrl & NVME_RW_PRINFO_PRACT) && !(ns->id_ns.dps & DPS_TYPE_MASK)) {
+ trace_nvme_err_prinfo(nvme_cid(req), ctrl);
+ return NVME_INVALID_FIELD | NVME_DNR;
+ }
+
+ return NVME_SUCCESS;
+}
- if (unlikely(slba + nlb > ns->id_ns.nsze)) {
- trace_nvme_err_invalid_lba_range(slba, nlb, ns->id_ns.nsze);
+static inline uint16_t nvme_check_bounds(NvmeCtrl *n, NvmeRequest *req)
+{
+ NvmeNamespace *ns = req->ns;
+ uint64_t nsze = le64_to_cpu(ns->id_ns.nsze);
+
+ if (unlikely((req->slba + req->nlb) > nsze)) {
+ block_acct_invalid(blk_get_stats(n->conf.blk),
+ nvme_req_is_write(req) ? BLOCK_ACCT_WRITE : BLOCK_ACCT_READ);
+ trace_nvme_err_invalid_lba_range(req->slba, req->nlb, nsze);
return NVME_LBA_RANGE | NVME_DNR;
}
- block_acct_start(blk_get_stats(n->conf.blk), &req->acct, 0,
- BLOCK_ACCT_WRITE);
- req->aiocb = blk_aio_pwrite_zeroes(n->conf.blk, offset, count,
- BDRV_REQ_MAY_UNMAP, nvme_rw_cb, req);
+ return NVME_SUCCESS;
+}
+
+static uint16_t nvme_check_rw(NvmeCtrl *n, NvmeRequest *req)
+{
+ NvmeNamespace *ns = req->ns;
+ size_t len = req->nlb << nvme_ns_lbads(ns);
+ uint16_t status;
+
+ status = nvme_check_mdts(n, len, req);
+ if (status) {
+ return status;
+ }
+
+ status = nvme_check_prinfo(n, req);
+ if (status) {
+ return status;
+ }
+
+ status = nvme_check_bounds(n, req);
+ if (status) {
+ return status;
+ }
+
+ return NVME_SUCCESS;
+}
+
+static uint16_t nvme_flush(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
+{
+ NvmeAIO *aio = nvme_aio_new(n->conf.blk, 0x0, NULL, req, NULL);
+
+ nvme_req_register_aio(req, aio, NVME_AIO_OPC_FLUSH);
+ nvme_aio(aio);
+
return NVME_NO_COMPLETE;
}
-static uint16_t nvme_rw(NvmeCtrl *n, NvmeNamespace *ns, NvmeCmd *cmd,
- NvmeRequest *req)
+static uint16_t nvme_write_zeros(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
{
- NvmeRwCmd *rw = (NvmeRwCmd *)cmd;
- uint32_t nlb = le32_to_cpu(rw->nlb) + 1;
- uint64_t slba = le64_to_cpu(rw->slba);
- uint64_t prp1 = le64_to_cpu(rw->prp1);
- uint64_t prp2 = le64_to_cpu(rw->prp2);
+ NvmeAIO *aio;
- uint8_t lba_index = NVME_ID_NS_FLBAS_INDEX(ns->id_ns.flbas);
- uint8_t data_shift = ns->id_ns.lbaf[lba_index].ds;
- uint64_t data_size = (uint64_t)nlb << data_shift;
- uint64_t data_offset = slba << data_shift;
- int is_write = rw->opcode == NVME_CMD_WRITE ? 1 : 0;
- enum BlockAcctType acct = is_write ? BLOCK_ACCT_WRITE : BLOCK_ACCT_READ;
+ NvmeNamespace *ns = req->ns;
+ NvmeRwCmd *rw = (NvmeRwCmd *) cmd;
- trace_nvme_rw(is_write ? "write" : "read", nlb, data_size, slba);
+ int64_t offset;
+ size_t count;
+ uint16_t status;
- 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);
- return NVME_LBA_RANGE | NVME_DNR;
+ req->slba = le64_to_cpu(rw->slba);
+ req->nlb = le16_to_cpu(rw->nlb) + 1;
+
+ trace_nvme_write_zeros(req->cid, le32_to_cpu(cmd->nsid), req->slba,
+ req->nlb);
+
+ status = nvme_check_bounds(n, req);
+ if (unlikely(status)) {
+ block_acct_invalid(blk_get_stats(n->conf.blk), BLOCK_ACCT_WRITE);
+ return status;
}
- if (nvme_map_prp(n, &req->qsg, prp1, prp2, data_size, req)) {
+ offset = req->slba << nvme_ns_lbads(ns);
+ count = req->nlb << nvme_ns_lbads(ns);
+
+ aio = nvme_aio_new(n->conf.blk, offset, NULL, req, NULL);
+
+ aio->iov.size = count;
+
+ nvme_req_register_aio(req, aio, NVME_AIO_OPC_WRITE_ZEROES);
+ nvme_aio(aio);
+
+ return NVME_NO_COMPLETE;
+}
+
+static uint16_t nvme_rw(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
+{
+ NvmeRwCmd *rw = (NvmeRwCmd *) cmd;
+ NvmeNamespace *ns = req->ns;
+ int status;
+
+ enum BlockAcctType acct =
+ nvme_req_is_write(req) ? BLOCK_ACCT_WRITE : BLOCK_ACCT_READ;
+
+ req->nlb = le16_to_cpu(rw->nlb) + 1;
+ req->slba = le64_to_cpu(rw->slba);
+
+ trace_nvme_rw(nvme_req_is_write(req) ? "write" : "read", req->nlb,
+ req->nlb << nvme_ns_lbads(req->ns), req->slba);
+
+ status = nvme_check_rw(n, req);
+ if (status) {
block_acct_invalid(blk_get_stats(n->conf.blk), acct);
- return NVME_INVALID_FIELD | NVME_DNR;
+ return status;
}
- dma_acct_start(n->conf.blk, &req->acct, &req->qsg, acct);
- if (!req->is_cmb) {
- req->aiocb = is_write ?
- dma_blk_write(n->conf.blk, &req->qsg, data_offset, BDRV_SECTOR_SIZE,
- nvme_rw_cb, req) :
- dma_blk_read(n->conf.blk, &req->qsg, data_offset, BDRV_SECTOR_SIZE,
- nvme_rw_cb, req);
- } else {
- qemu_iovec_init(&req->iov, req->qsg.nsg);
- dma_to_cmb(n, &req->qsg, &req->iov);
- req->aiocb = is_write ?
- blk_aio_pwritev(n->conf.blk, data_offset, &req->iov, 0, nvme_rw_cb,
- req) :
- blk_aio_preadv(n->conf.blk, data_offset, &req->iov, 0, nvme_rw_cb,
- req);
+ status = nvme_map(n, cmd, req);
+ if (status) {
+ block_acct_invalid(blk_get_stats(n->conf.blk), acct);
+ return status;
}
+ nvme_rw_aio(n->conf.blk, req->slba << nvme_ns_lbads(ns), &req->qsg, req);
+ nvme_req_set_cb(req, nvme_rw_cb, NULL);
+
return NVME_NO_COMPLETE;
}
static uint16_t nvme_io_cmd(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
{
- NvmeNamespace *ns;
uint32_t nsid = le32_to_cpu(cmd->nsid);
+ trace_nvme_io_cmd(req->cid, nsid, le16_to_cpu(req->sq->sqid), cmd->opcode);
+
if (unlikely(nsid == 0 || nsid > n->num_namespaces)) {
trace_nvme_err_invalid_ns(nsid, n->num_namespaces);
return NVME_INVALID_NSID | NVME_DNR;
}
- ns = &n->namespaces[nsid - 1];
+ req->ns = &n->namespaces[nsid - 1];
+
switch (cmd->opcode) {
case NVME_CMD_FLUSH:
- return nvme_flush(n, ns, cmd, req);
+ return nvme_flush(n, cmd, req);
case NVME_CMD_WRITE_ZEROS:
- return nvme_write_zeros(n, ns, cmd, req);
+ return nvme_write_zeros(n, cmd, req);
case NVME_CMD_WRITE:
case NVME_CMD_READ:
- return nvme_rw(n, ns, cmd, req);
+ return nvme_rw(n, cmd, req);
default:
trace_nvme_err_invalid_opc(cmd->opcode);
return NVME_INVALID_OPCODE | NVME_DNR;
@@ -609,6 +867,7 @@ static uint16_t nvme_del_sq(NvmeCtrl *n, NvmeCmd *cmd)
NvmeRequest *req, *next;
NvmeSQueue *sq;
NvmeCQueue *cq;
+ NvmeAIO *aio;
uint16_t qid = le16_to_cpu(c->qid);
if (unlikely(!qid || nvme_check_sqid(n, qid))) {
@@ -621,8 +880,11 @@ static uint16_t nvme_del_sq(NvmeCtrl *n, NvmeCmd *cmd)
sq = n->sq[qid];
while (!QTAILQ_EMPTY(&sq->out_req_list)) {
req = QTAILQ_FIRST(&sq->out_req_list);
- assert(req->aiocb);
- blk_aio_cancel(req->aiocb);
+ while (!QTAILQ_EMPTY(&req->aio_tailq)) {
+ aio = QTAILQ_FIRST(&req->aio_tailq);
+ assert(aio->aiocb);
+ blk_aio_cancel(aio->aiocb);
+ }
}
if (!nvme_check_cqid(n, sq->cqid)) {
cq = n->cq[sq->cqid];
@@ -659,6 +921,7 @@ static void nvme_init_sq(NvmeSQueue *sq, NvmeCtrl *n, uint64_t dma_addr,
QTAILQ_INIT(&sq->out_req_list);
for (i = 0; i < sq->size; i++) {
sq->io_req[i].sq = sq;
+ QTAILQ_INIT(&(sq->io_req[i].aio_tailq));
QTAILQ_INSERT_TAIL(&(sq->req_list), &sq->io_req[i], entry);
}
sq->timer = timer_new_ns(QEMU_CLOCK_VIRTUAL, nvme_process_sq, sq);
@@ -820,6 +1083,7 @@ static uint16_t nvme_get_log(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
uint32_t numdl, numdu;
uint64_t off, lpol, lpou;
size_t len;
+ uint16_t status;
numdl = (dw10 >> 16);
numdu = (dw11 & 0xffff);
@@ -835,6 +1099,11 @@ static uint16_t nvme_get_log(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
trace_nvme_get_log(req->cid, lid, lsp, rae, len, off);
+ status = nvme_check_mdts(n, len, req);
+ if (status) {
+ return status;
+ }
+
switch (lid) {
case NVME_LOG_ERROR_INFO:
return nvme_error_info(n, cmd, rae, len, off, req);
@@ -1353,8 +1622,9 @@ static void nvme_init_req(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
memcpy(&req->cmd, cmd, sizeof(NvmeCmd));
req->status = NVME_SUCCESS;
- req->is_cmb = false;
- req->is_write = false;
+ req->flags = 0x0;
+ req->cb = NULL;
+ req->cb_arg = NULL;
}
static void nvme_process_sq(void *opaque)
@@ -1953,6 +2223,7 @@ static void nvme_init_ctrl(NvmeCtrl *n)
id->ieee[0] = 0x00;
id->ieee[1] = 0x02;
id->ieee[2] = 0xb3;
+ id->mdts = params->mdts;
id->ver = cpu_to_le32(0x00010300);
id->oacs = cpu_to_le16(0);
id->acl = 3;
diff --git a/hw/block/nvme.h b/hw/block/nvme.h
index add9ff335aa5..2f6706899de1 100644
--- a/hw/block/nvme.h
+++ b/hw/block/nvme.h
@@ -8,7 +8,8 @@
DEFINE_PROP_UINT32("cmb_size_mb", _state, _props.cmb_size_mb, 0), \
DEFINE_PROP_UINT32("num_queues", _state, _props.num_queues, 64), \
DEFINE_PROP_UINT8("elpe", _state, _props.elpe, 24), \
- DEFINE_PROP_UINT8("aerl", _state, _props.aerl, 3)
+ DEFINE_PROP_UINT8("aerl", _state, _props.aerl, 3), \
+ DEFINE_PROP_UINT8("mdts", _state, _props.mdts, 7)
typedef struct NvmeParams {
char *serial;
@@ -16,6 +17,7 @@ typedef struct NvmeParams {
uint32_t cmb_size_mb;
uint8_t elpe;
uint8_t aerl;
+ uint8_t mdts;
} NvmeParams;
typedef struct NvmeAsyncEvent {
@@ -23,23 +25,124 @@ typedef struct NvmeAsyncEvent {
NvmeAerResult result;
} NvmeAsyncEvent;
-typedef struct NvmeRequest {
- struct NvmeSQueue *sq;
- BlockAIOCB *aiocb;
- uint16_t status;
- uint16_t cid;
- bool is_cmb;
- bool is_write;
- NvmeCqe cqe;
- BlockAcctCookie acct;
- QEMUSGList qsg;
- QEMUIOVector iov;
- NvmeCmd cmd;
- QTAILQ_ENTRY(NvmeRequest)entry;
-} NvmeRequest;
-
-typedef struct NvmeSQueue {
- struct NvmeCtrl *ctrl;
+typedef enum NvmeAIOOp {
+ NVME_AIO_OPC_NONE = 0x0,
+ NVME_AIO_OPC_FLUSH = 0x1,
+ NVME_AIO_OPC_READ = 0x2,
+ NVME_AIO_OPC_WRITE = 0x3,
+ NVME_AIO_OPC_WRITE_ZEROES = 0x4,
+} NvmeAIOOp;
+
+typedef struct NvmeRequest NvmeRequest;
+typedef struct NvmeAIO NvmeAIO;
+typedef void NvmeAIOCompletionFunc(NvmeAIO *aio, void *opaque);
+
+struct NvmeAIO {
+ NvmeRequest *req;
+
+ NvmeAIOOp opc;
+ int64_t offset;
+ BlockBackend *blk;
+ BlockAIOCB *aiocb;
+ BlockAcctCookie acct;
+
+ NvmeAIOCompletionFunc *cb;
+ void *cb_arg;
+
+ QEMUSGList *qsg;
+ QEMUIOVector iov;
+
+ QTAILQ_ENTRY(NvmeAIO) tailq_entry;
+};
+
+static inline const char *nvme_aio_opc_str(NvmeAIO *aio)
+{
+ switch (aio->opc) {
+ case NVME_AIO_OPC_NONE: return "NVME_AIO_OP_NONE";
+ case NVME_AIO_OPC_FLUSH: return "NVME_AIO_OP_FLUSH";
+ case NVME_AIO_OPC_READ: return "NVME_AIO_OP_READ";
+ case NVME_AIO_OPC_WRITE: return "NVME_AIO_OP_WRITE";
+ case NVME_AIO_OPC_WRITE_ZEROES: return "NVME_AIO_OP_WRITE_ZEROES";
+ default: return "NVME_AIO_OP_UNKNOWN";
+ }
+}
+
+#define NVME_REQ_TRANSFER_DMA 0x1
+#define NVME_REQ_TRANSFER_CMB 0x2
+#define NVME_REQ_TRANSFER_MASK 0x3
+
+typedef struct NvmeSQueue NvmeSQueue;
+typedef struct NvmeNamespace NvmeNamespace;
+typedef void NvmeRequestCompletionFunc(NvmeRequest *req, void *opaque);
+
+struct NvmeRequest {
+ NvmeSQueue *sq;
+ NvmeNamespace *ns;
+ NvmeCqe cqe;
+ NvmeCmd cmd;
+
+ uint64_t slba;
+ uint32_t nlb;
+ uint16_t status;
+ uint16_t cid;
+ int flags;
+
+ NvmeRequestCompletionFunc *cb;
+ void *cb_arg;
+
+ QEMUSGList qsg;
+
+ QTAILQ_HEAD(, NvmeAIO) aio_tailq;
+ QTAILQ_ENTRY(NvmeRequest) entry;
+};
+
+static inline void nvme_req_set_cb(NvmeRequest *req,
+ NvmeRequestCompletionFunc *cb, void *cb_arg)
+{
+ req->cb = cb;
+ req->cb_arg = cb_arg;
+}
+
+static inline void nvme_req_clear_cb(NvmeRequest *req)
+{
+ req->cb = req->cb_arg = NULL;
+}
+
+static inline uint16_t nvme_cid(NvmeRequest *req)
+{
+ if (req) {
+ return req->cid;
+ }
+
+ return 0xffff;
+}
+
+static inline bool nvme_req_is_cmb(NvmeRequest *req)
+{
+ return (req->flags & NVME_REQ_TRANSFER_MASK) == NVME_REQ_TRANSFER_CMB;
+}
+
+static void nvme_req_set_cmb(NvmeRequest *req)
+{
+ req->flags = NVME_REQ_TRANSFER_CMB;
+}
+
+static inline bool nvme_req_is_write(NvmeRequest *req)
+{
+ switch (req->cmd.opcode) {
+ case NVME_CMD_WRITE:
+ case NVME_CMD_WRITE_UNCOR:
+ case NVME_CMD_WRITE_ZEROS:
+ return true;
+ default:
+ return false;
+ }
+}
+
+typedef struct NvmeCtrl NvmeCtrl;
+
+struct NvmeSQueue {
+ NvmeCtrl *ctrl;
uint16_t sqid;
uint16_t cqid;
uint32_t head;
@@ -51,10 +154,12 @@ typedef struct NvmeSQueue {
QTAILQ_HEAD(, NvmeRequest) req_list;
QTAILQ_HEAD(, NvmeRequest) out_req_list;
QTAILQ_ENTRY(NvmeSQueue) entry;
-} NvmeSQueue;
+};
-typedef struct NvmeCQueue {
- struct NvmeCtrl *ctrl;
+typedef struct NvmeCQueue NvmeCQueue;
+
+struct NvmeCQueue {
+ NvmeCtrl *ctrl;
uint8_t phase;
uint16_t cqid;
uint16_t irq_enabled;
@@ -66,11 +171,11 @@ typedef struct NvmeCQueue {
QEMUTimer *timer;
QTAILQ_HEAD(, NvmeSQueue) sq_list;
QTAILQ_HEAD(, NvmeRequest) req_list;
-} NvmeCQueue;
+};
-typedef struct NvmeNamespace {
+struct NvmeNamespace {
NvmeIdNs id_ns;
-} NvmeNamespace;
+};
#define TYPE_NVME "nvme"
#define NVME(obj) \
@@ -122,6 +227,17 @@ typedef struct NvmeCtrl {
NvmeIdCtrl id_ctrl;
} NvmeCtrl;
+static inline NvmeCtrl *nvme_ctrl(NvmeRequest *req)
+{
+ return req->sq->ctrl;
+}
+
+static inline bool nvme_is_error(uint16_t status, uint16_t err)
+{
+ /* strip DNR and MORE */
+ return (status & 0xfff) == err;
+}
+
static inline NvmeLBAF nvme_ns_lbaf(NvmeNamespace *ns)
{
NvmeIdNs *id_ns = &ns->id_ns;
@@ -143,5 +259,4 @@ static inline uint64_t nvme_ns_nlbas(NvmeCtrl *n, NvmeNamespace *ns)
return n->ns_size >> nvme_ns_lbads(ns);
}
-
#endif /* HW_NVME_H */
diff --git a/hw/block/trace-events b/hw/block/trace-events
index e81bb3a64ed7..c7e0a1849043 100644
--- a/hw/block/trace-events
+++ b/hw/block/trace-events
@@ -34,7 +34,12 @@ nvme_irq_pin(void) "pulsing IRQ pin"
nvme_irq_masked(void) "IRQ is masked"
nvme_dma_read(uint64_t prp1, uint64_t prp2) "DMA read, prp1=0x%"PRIx64" prp2=0x%"PRIx64""
nvme_map_prp(uint16_t cid, uint8_t opc, uint64_t trans_len, uint32_t len, uint64_t prp1, uint64_t prp2, int num_prps) "cid %"PRIu16" opc 0x%"PRIx8" trans_len %"PRIu64" len %"PRIu32" prp1 0x%"PRIx64" prp2 0x%"PRIx64" num_prps %d"
+nvme_req_register_aio(uint16_t cid, void *aio, const char *blkname, uint64_t offset, uint64_t count, const char *opc, void *req) "cid %"PRIu16" aio %p blk \"%s\" offset %"PRIu64" count %"PRIu64" opc \"%s\" req %p"
+nvme_aio_cb(uint16_t cid, void *aio, const char *blkname, uint64_t offset, const char *opc, void *req) "cid %"PRIu16" aio %p blk \"%s\" offset %"PRIu64" opc \"%s\" req %p"
+nvme_io_cmd(uint16_t cid, uint32_t nsid, uint16_t sqid, uint8_t opcode) "cid %"PRIu16" nsid %"PRIu32" sqid %"PRIu16" opc 0x%"PRIx8""
nvme_rw(const char *verb, uint32_t blk_count, uint64_t byte_count, uint64_t lba) "%s %"PRIu32" blocks (%"PRIu64" bytes) from LBA %"PRIu64""
+nvme_rw_cb(uint16_t cid, uint32_t nsid) "cid %"PRIu16" nsid %"PRIu32""
+nvme_write_zeros(uint16_t cid, uint32_t nsid, uint64_t slba, uint32_t nlb) "cid %"PRIu16" nsid %"PRIu32" slba %"PRIu64" nlb %"PRIu32""
nvme_create_sq(uint64_t addr, uint16_t sqid, uint16_t cqid, uint16_t qsize, uint16_t qflags) "create submission queue, addr=0x%"PRIx64", sqid=%"PRIu16", cqid=%"PRIu16", qsize=%"PRIu16", qflags=%"PRIu16""
nvme_create_cq(uint64_t addr, uint16_t cqid, uint16_t vector, uint16_t size, uint16_t qflags, int ien) "create completion queue, addr=0x%"PRIx64", cqid=%"PRIu16", vector=%"PRIu16", qsize=%"PRIu16", qflags=%"PRIu16", ien=%d"
nvme_del_sq(uint16_t qid) "deleting submission queue sqid=%"PRIu16""
@@ -74,6 +79,9 @@ nvme_mmio_shutdown_set(void) "shutdown bit set"
nvme_mmio_shutdown_cleared(void) "shutdown bit cleared"
# nvme traces for error conditions
+nvme_err_mdts(uint16_t cid, size_t mdts, size_t len) "cid %"PRIu16" mdts %"PRIu64" len %"PRIu64""
+nvme_err_prinfo(uint16_t cid, uint16_t ctrl) "cid %"PRIu16" ctrl %"PRIu16""
+nvme_err_aio(uint16_t cid, void *aio, const char *blkname, uint64_t offset, const char *opc, void *req, uint16_t status) "cid %"PRIu16" aio %p blk \"%s\" offset %"PRIu64" opc \"%s\" req %p status 0x%"PRIx16""
nvme_err_invalid_dma(void) "PRP/SGL is too small for transfer size"
nvme_err_invalid_prplist_ent(uint64_t prplist) "PRP list entry is null or not page aligned: 0x%"PRIx64""
nvme_err_invalid_prp2_align(uint64_t prp2) "PRP2 is not page aligned: 0x%"PRIx64""
--
2.23.0
^ permalink raw reply related [flat|nested] 52+ messages in thread* Re: [PATCH v2 14/20] nvme: allow multiple aios per command
2019-10-15 10:38 ` [PATCH v2 14/20] nvme: allow multiple aios per command Klaus Jensen
@ 2019-11-12 15:25 ` Beata Michalska
2019-11-21 11:57 ` Klaus Birkelund
0 siblings, 1 reply; 52+ messages in thread
From: Beata Michalska @ 2019-11-12 15:25 UTC (permalink / raw)
To: Klaus Jensen
Cc: Kevin Wolf, Fam Zheng, Javier Gonzalez, qemu-block, qemu-devel,
Max Reitz, Keith Busch, Paul Durrant, Stephen Bates
Hi Klaus,
On Tue, 15 Oct 2019 at 11:55, Klaus Jensen <its@irrelevant.dk> wrote:
>
> This refactors how the device issues asynchronous block backend
> requests. The NvmeRequest now holds a queue of NvmeAIOs that are
> associated with the command. This allows multiple aios to be issued for
> a command. Only when all requests have been completed will the device
> post a completion queue entry.
>
> Because the device is currently guaranteed to only issue a single aio
> request per command, the benefit is not immediately obvious. But this
> functionality is required to support metadata.
>
> Signed-off-by: Klaus Jensen <klaus.jensen@cnexlabs.com>
> Signed-off-by: Klaus Jensen <k.jensen@samsung.com>
> ---
> hw/block/nvme.c | 455 +++++++++++++++++++++++++++++++++---------
> hw/block/nvme.h | 165 ++++++++++++---
> hw/block/trace-events | 8 +
> 3 files changed, 511 insertions(+), 117 deletions(-)
>
> diff --git a/hw/block/nvme.c b/hw/block/nvme.c
> index cbc0b6a660b6..f4b9bd36a04e 100644
> --- a/hw/block/nvme.c
> +++ b/hw/block/nvme.c
> @@ -25,6 +25,8 @@
> * Default: 64
> * cmb_size_mb=<uint32> : Size of Controller Memory Buffer in MBs.
> * Default: 0 (disabled)
> + * mdts=<uint8> : Maximum Data Transfer Size (power of two)
> + * Default: 7
> */
>
> #include "qemu/osdep.h"
> @@ -56,6 +58,7 @@
> } while (0)
>
> static void nvme_process_sq(void *opaque);
> +static void nvme_aio_cb(void *opaque, int ret);
>
> static inline bool nvme_addr_is_cmb(NvmeCtrl *n, hwaddr addr)
> {
> @@ -197,7 +200,7 @@ static uint16_t nvme_map_prp(NvmeCtrl *n, QEMUSGList *qsg, uint64_t prp1,
> }
>
> if (nvme_addr_is_cmb(n, prp1)) {
> - req->is_cmb = true;
> + nvme_req_set_cmb(req);
> }
>
> pci_dma_sglist_init(qsg, &n->parent_obj, num_prps);
> @@ -255,8 +258,8 @@ static uint16_t nvme_map_prp(NvmeCtrl *n, QEMUSGList *qsg, uint64_t prp1,
> }
>
> addr_is_cmb = nvme_addr_is_cmb(n, prp_ent);
> - if ((req->is_cmb && !addr_is_cmb) ||
> - (!req->is_cmb && addr_is_cmb)) {
> + if ((nvme_req_is_cmb(req) && !addr_is_cmb) ||
> + (!nvme_req_is_cmb(req) && addr_is_cmb)) {
> status = NVME_INVALID_USE_OF_CMB | NVME_DNR;
> goto unmap;
> }
> @@ -269,8 +272,8 @@ static uint16_t nvme_map_prp(NvmeCtrl *n, QEMUSGList *qsg, uint64_t prp1,
> }
> } else {
> bool addr_is_cmb = nvme_addr_is_cmb(n, prp2);
> - if ((req->is_cmb && !addr_is_cmb) ||
> - (!req->is_cmb && addr_is_cmb)) {
> + if ((nvme_req_is_cmb(req) && !addr_is_cmb) ||
> + (!nvme_req_is_cmb(req) && addr_is_cmb)) {
> status = NVME_INVALID_USE_OF_CMB | NVME_DNR;
> goto unmap;
> }
> @@ -312,7 +315,7 @@ static uint16_t nvme_dma_write_prp(NvmeCtrl *n, uint8_t *ptr, uint32_t len,
> return status;
> }
>
> - if (req->is_cmb) {
> + if (nvme_req_is_cmb(req)) {
> QEMUIOVector iov;
>
> qemu_iovec_init(&iov, qsg.nsg);
> @@ -341,19 +344,18 @@ static uint16_t nvme_dma_write_prp(NvmeCtrl *n, uint8_t *ptr, uint32_t len,
Any reason why the nvme_dma_write_prp is missing the changes applied
to nvme_dma_read_prp ?
> static uint16_t nvme_dma_read_prp(NvmeCtrl *n, uint8_t *ptr, uint32_t len,
> uint64_t prp1, uint64_t prp2, NvmeRequest *req)
> {
> - QEMUSGList qsg;
> uint16_t status = NVME_SUCCESS;
>
> - status = nvme_map_prp(n, &qsg, prp1, prp2, len, req);
> + status = nvme_map_prp(n, &req->qsg, prp1, prp2, len, req);
> if (status) {
> return status;
> }
>
> - if (req->is_cmb) {
> + if (nvme_req_is_cmb(req)) {
> QEMUIOVector iov;
>
> - qemu_iovec_init(&iov, qsg.nsg);
> - dma_to_cmb(n, &qsg, &iov);
> + qemu_iovec_init(&iov, req->qsg.nsg);
> + dma_to_cmb(n, &req->qsg, &iov);
>
> if (unlikely(qemu_iovec_from_buf(&iov, 0, ptr, len) != len)) {
> trace_nvme_err_invalid_dma();
> @@ -365,17 +367,137 @@ static uint16_t nvme_dma_read_prp(NvmeCtrl *n, uint8_t *ptr, uint32_t len,
> goto out;
> }
>
> - if (unlikely(dma_buf_read(ptr, len, &qsg))) {
> + if (unlikely(dma_buf_read(ptr, len, &req->qsg))) {
> trace_nvme_err_invalid_dma();
> status = NVME_INVALID_FIELD | NVME_DNR;
> }
>
> out:
> - qemu_sglist_destroy(&qsg);
> + qemu_sglist_destroy(&req->qsg);
>
> return status;
> }
>
> +static uint16_t nvme_map(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
> +{
> + NvmeNamespace *ns = req->ns;
> +
> + uint32_t len = req->nlb << nvme_ns_lbads(ns);
> + uint64_t prp1 = le64_to_cpu(cmd->prp1);
> + uint64_t prp2 = le64_to_cpu(cmd->prp2);
> +
> + return nvme_map_prp(n, &req->qsg, prp1, prp2, len, req);
> +}
> +
> +static void nvme_aio_destroy(NvmeAIO *aio)
> +{
> + if (aio->iov.nalloc) {
> + qemu_iovec_destroy(&aio->iov);
> + }
> +
> + g_free(aio);
> +}
> +
> +static NvmeAIO *nvme_aio_new(BlockBackend *blk, int64_t offset,
> + QEMUSGList *qsg, NvmeRequest *req, NvmeAIOCompletionFunc *cb)
> +{
> + NvmeAIO *aio = g_malloc0(sizeof(*aio));
> +
> + *aio = (NvmeAIO) {
> + .blk = blk,
> + .offset = offset,
> + .req = req,
> + .qsg = qsg,
> + .cb = cb,
> + };
> +
> + if (qsg && nvme_req_is_cmb(req)) {
> + NvmeCtrl *n = nvme_ctrl(req);
> +
> + qemu_iovec_init(&aio->iov, qsg->nsg);
> + dma_to_cmb(n, qsg, &aio->iov);
> +
> + aio->qsg = NULL;
> + }
> +
> + return aio;
> +}
> +
> +static inline void nvme_req_register_aio(NvmeRequest *req, NvmeAIO *aio,
> + NvmeAIOOp opc)
> +{
> + aio->opc = opc;
> +
> + trace_nvme_req_register_aio(nvme_cid(req), aio, blk_name(aio->blk),
> + aio->offset, aio->qsg ? aio->qsg->size : aio->iov.size,
> + nvme_aio_opc_str(aio), req);
> +
> + if (req) {
> + QTAILQ_INSERT_TAIL(&req->aio_tailq, aio, tailq_entry);
> + }
> +}
> +
> +static void nvme_aio(NvmeAIO *aio)
> +{
> + BlockBackend *blk = aio->blk;
> + BlockAcctCookie *acct = &aio->acct;
> + BlockAcctStats *stats = blk_get_stats(blk);
> +
> + bool is_write, dma;
> +
> + switch (aio->opc) {
> + case NVME_AIO_OPC_NONE:
> + break;
> +
> + case NVME_AIO_OPC_FLUSH:
> + block_acct_start(stats, acct, 0, BLOCK_ACCT_FLUSH);
> + aio->aiocb = blk_aio_flush(blk, nvme_aio_cb, aio);
> + break;
> +
> + case NVME_AIO_OPC_WRITE_ZEROES:
> + block_acct_start(stats, acct, aio->iov.size, BLOCK_ACCT_WRITE);
> + aio->aiocb = blk_aio_pwrite_zeroes(aio->blk, aio->offset,
> + aio->iov.size, BDRV_REQ_MAY_UNMAP, nvme_aio_cb, aio);
Minor: aio->blk => blk
> + break;
> +
> + case NVME_AIO_OPC_READ:
> + case NVME_AIO_OPC_WRITE:
> + dma = aio->qsg != NULL;
> + is_write = (aio->opc == NVME_AIO_OPC_WRITE);
> +
> + block_acct_start(stats, acct,
> + dma ? aio->qsg->size : aio->iov.size,
> + is_write ? BLOCK_ACCT_WRITE : BLOCK_ACCT_READ);
> +
> + if (dma) {
> + aio->aiocb = is_write ?
> + dma_blk_write(blk, aio->qsg, aio->offset,
> + BDRV_SECTOR_SIZE, nvme_aio_cb, aio) :
> + dma_blk_read(blk, aio->qsg, aio->offset,
> + BDRV_SECTOR_SIZE, nvme_aio_cb, aio);
> +
> + return;
> + }
> +
> + aio->aiocb = is_write ?
> + blk_aio_pwritev(blk, aio->offset, &aio->iov, 0,
> + nvme_aio_cb, aio) :
> + blk_aio_preadv(blk, aio->offset, &aio->iov, 0,
> + nvme_aio_cb, aio);
> +
> + break;
> + }
> +}
> +
> +static void nvme_rw_aio(BlockBackend *blk, uint64_t offset, QEMUSGList *qsg,
> + NvmeRequest *req)
> +{
> + NvmeAIO *aio = nvme_aio_new(blk, offset, qsg, req, NULL);
> + nvme_req_register_aio(req, aio, nvme_req_is_write(req) ?
> + NVME_AIO_OPC_WRITE : NVME_AIO_OPC_READ);
> + nvme_aio(aio);
> +}
> +
> static void nvme_post_cqes(void *opaque)
> {
> NvmeCQueue *cq = opaque;
> @@ -411,6 +533,11 @@ static void nvme_enqueue_req_completion(NvmeCQueue *cq, NvmeRequest *req)
> assert(cq->cqid == req->sq->cqid);
>
> trace_nvme_enqueue_req_completion(req->cid, cq->cqid, req->status);
> +
> + if (req->qsg.nalloc) {
> + qemu_sglist_destroy(&req->qsg);
> + }
> +
> QTAILQ_REMOVE(&req->sq->out_req_list, req, entry);
> QTAILQ_INSERT_TAIL(&cq->req_list, req, entry);
> timer_mod(cq->timer, qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) + 500);
> @@ -456,135 +583,266 @@ static void nvme_clear_events(NvmeCtrl *n, uint8_t event_type)
> }
> }
>
> -static void nvme_rw_cb(void *opaque, int ret)
> +static void nvme_rw_cb(NvmeRequest *req, void *opaque)
> {
> - NvmeRequest *req = opaque;
> NvmeSQueue *sq = req->sq;
> NvmeCtrl *n = sq->ctrl;
> NvmeCQueue *cq = n->cq[sq->cqid];
> - NvmeRwCmd *rw = (NvmeRwCmd *) &req->cmd;
> +
> + trace_nvme_rw_cb(req->cid, req->cmd.nsid);
> +
> + nvme_enqueue_req_completion(cq, req);
> +}
> +
> +static void nvme_aio_cb(void *opaque, int ret)
> +{
> + NvmeAIO *aio = opaque;
> + NvmeRequest *req = aio->req;
> +
> + BlockBackend *blk = aio->blk;
> + BlockAcctCookie *acct = &aio->acct;
> + BlockAcctStats *stats = blk_get_stats(blk);
> +
> + Error *local_err = NULL;
> +
> + trace_nvme_aio_cb(nvme_cid(req), aio, blk_name(aio->blk), aio->offset,
> + nvme_aio_opc_str(aio), req);
> +
> + if (req) {
> + QTAILQ_REMOVE(&req->aio_tailq, aio, tailq_entry);
> + }
>
> if (!ret) {
> - block_acct_done(blk_get_stats(n->conf.blk), &req->acct);
> - req->status = NVME_SUCCESS;
> + block_acct_done(stats, acct);
> +
> + if (aio->cb) {
> + aio->cb(aio, aio->cb_arg);
> + }
> } else {
> - block_acct_failed(blk_get_stats(n->conf.blk), &req->acct);
> - nvme_set_error_page(n, sq->sqid, cpu_to_le16(req->cid),
> - NVME_INTERNAL_DEV_ERROR, offsetof(NvmeRwCmd, slba), rw->slba, 1);
> - req->status = NVME_INTERNAL_DEV_ERROR | NVME_MORE;
> - }
> + block_acct_failed(stats, acct);
> +
> + if (req) {
> + NvmeRwCmd *rw = (NvmeRwCmd *) &req->cmd;
> + NvmeSQueue *sq = req->sq;
> + NvmeCtrl *n = sq->ctrl;
> + uint16_t status;
> +
> + switch (aio->opc) {
> + case NVME_AIO_OPC_READ:
> + status = NVME_UNRECOVERED_READ;
> + break;
> + case NVME_AIO_OPC_WRITE:
> + case NVME_AIO_OPC_WRITE_ZEROES:
> + status = NVME_WRITE_FAULT;
> + break;
> + default:
> + status = NVME_INTERNAL_DEV_ERROR;
> + break;
> + }
>
> - if (req->qsg.nalloc) {
> - qemu_sglist_destroy(&req->qsg);
> + trace_nvme_err_aio(nvme_cid(req), aio, blk_name(aio->blk),
> + aio->offset, nvme_aio_opc_str(aio), req, status);
> +
> + nvme_set_error_page(n, sq->sqid, cpu_to_le16(req->cid), status,
> + offsetof(NvmeRwCmd, slba), rw->slba, 1);
> +
> + error_setg_errno(&local_err, -ret, "aio failed");
> + error_report_err(local_err);
> +
> + /*
> + * An Internal Error trumps all other errors. For other errors,
> + * only set the first error encountered. Any additional errors will
> + * be recorded in the error information log page.
> + */
> + if (!req->status ||
> + nvme_is_error(status, NVME_INTERNAL_DEV_ERROR)) {
> + req->status = status;
> + }
> + }
> }
> - if (req->iov.nalloc) {
> - qemu_iovec_destroy(&req->iov);
> +
> + if (req && QTAILQ_EMPTY(&req->aio_tailq)) {
> + if (req->cb) {
> + req->cb(req, req->cb_arg);
> + } else {
> + NvmeSQueue *sq = req->sq;
> + NvmeCtrl *n = sq->ctrl;
> + NvmeCQueue *cq = n->cq[sq->cqid];
> +
> + nvme_enqueue_req_completion(cq, req);
> + }
> }
>
> - nvme_enqueue_req_completion(cq, req);
> + nvme_aio_destroy(aio);
> }
>
> -static uint16_t nvme_flush(NvmeCtrl *n, NvmeNamespace *ns, NvmeCmd *cmd,
> +static inline uint16_t nvme_check_mdts(NvmeCtrl *n, size_t len,
> NvmeRequest *req)
> {
> - block_acct_start(blk_get_stats(n->conf.blk), &req->acct, 0,
> - BLOCK_ACCT_FLUSH);
> - req->aiocb = blk_aio_flush(n->conf.blk, nvme_rw_cb, req);
> + uint8_t mdts = n->params.mdts;
>
> - return NVME_NO_COMPLETE;
> + if (mdts && len > n->page_size << mdts) {
> + trace_nvme_err_mdts(nvme_cid(req), n->page_size << mdts, len);
> + return NVME_INVALID_FIELD | NVME_DNR;
> + }
> +
> + return NVME_SUCCESS;
> }
>
> -static uint16_t nvme_write_zeros(NvmeCtrl *n, NvmeNamespace *ns, NvmeCmd *cmd,
> - NvmeRequest *req)
> +static inline uint16_t nvme_check_prinfo(NvmeCtrl *n, NvmeRequest *req)
> {
> - NvmeRwCmd *rw = (NvmeRwCmd *)cmd;
> - const uint8_t lba_index = NVME_ID_NS_FLBAS_INDEX(ns->id_ns.flbas);
> - const uint8_t data_shift = ns->id_ns.lbaf[lba_index].ds;
> - uint64_t slba = le64_to_cpu(rw->slba);
> - uint32_t nlb = le16_to_cpu(rw->nlb) + 1;
> - uint64_t offset = slba << data_shift;
> - uint32_t count = nlb << data_shift;
> + NvmeRwCmd *rw = (NvmeRwCmd *) &req->cmd;
> + NvmeNamespace *ns = req->ns;
> +
> + uint16_t ctrl = le16_to_cpu(rw->control);
> +
> + if ((ctrl & NVME_RW_PRINFO_PRACT) && !(ns->id_ns.dps & DPS_TYPE_MASK)) {
> + trace_nvme_err_prinfo(nvme_cid(req), ctrl);
> + return NVME_INVALID_FIELD | NVME_DNR;
> + }
> +
> + return NVME_SUCCESS;
> +}
>
> - if (unlikely(slba + nlb > ns->id_ns.nsze)) {
> - trace_nvme_err_invalid_lba_range(slba, nlb, ns->id_ns.nsze);
> +static inline uint16_t nvme_check_bounds(NvmeCtrl *n, NvmeRequest *req)
> +{
> + NvmeNamespace *ns = req->ns;
> + uint64_t nsze = le64_to_cpu(ns->id_ns.nsze);
> +
> + if (unlikely((req->slba + req->nlb) > nsze)) {
> + block_acct_invalid(blk_get_stats(n->conf.blk),
> + nvme_req_is_write(req) ? BLOCK_ACCT_WRITE : BLOCK_ACCT_READ);
> + trace_nvme_err_invalid_lba_range(req->slba, req->nlb, nsze);
> return NVME_LBA_RANGE | NVME_DNR;
> }
>
> - block_acct_start(blk_get_stats(n->conf.blk), &req->acct, 0,
> - BLOCK_ACCT_WRITE);
> - req->aiocb = blk_aio_pwrite_zeroes(n->conf.blk, offset, count,
> - BDRV_REQ_MAY_UNMAP, nvme_rw_cb, req);
> + return NVME_SUCCESS;
> +}
> +
> +static uint16_t nvme_check_rw(NvmeCtrl *n, NvmeRequest *req)
> +{
> + NvmeNamespace *ns = req->ns;
> + size_t len = req->nlb << nvme_ns_lbads(ns);
> + uint16_t status;
> +
> + status = nvme_check_mdts(n, len, req);
> + if (status) {
> + return status;
> + }
> +
> + status = nvme_check_prinfo(n, req);
> + if (status) {
> + return status;
> + }
> +
> + status = nvme_check_bounds(n, req);
> + if (status) {
> + return status;
> + }
> +
> + return NVME_SUCCESS;
> +}
> +
> +static uint16_t nvme_flush(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
> +{
> + NvmeAIO *aio = nvme_aio_new(n->conf.blk, 0x0, NULL, req, NULL);
> +
> + nvme_req_register_aio(req, aio, NVME_AIO_OPC_FLUSH);
> + nvme_aio(aio);
> +
> return NVME_NO_COMPLETE;
> }
>
> -static uint16_t nvme_rw(NvmeCtrl *n, NvmeNamespace *ns, NvmeCmd *cmd,
> - NvmeRequest *req)
> +static uint16_t nvme_write_zeros(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
> {
> - NvmeRwCmd *rw = (NvmeRwCmd *)cmd;
> - uint32_t nlb = le32_to_cpu(rw->nlb) + 1;
> - uint64_t slba = le64_to_cpu(rw->slba);
> - uint64_t prp1 = le64_to_cpu(rw->prp1);
> - uint64_t prp2 = le64_to_cpu(rw->prp2);
> + NvmeAIO *aio;
>
> - uint8_t lba_index = NVME_ID_NS_FLBAS_INDEX(ns->id_ns.flbas);
> - uint8_t data_shift = ns->id_ns.lbaf[lba_index].ds;
> - uint64_t data_size = (uint64_t)nlb << data_shift;
> - uint64_t data_offset = slba << data_shift;
> - int is_write = rw->opcode == NVME_CMD_WRITE ? 1 : 0;
> - enum BlockAcctType acct = is_write ? BLOCK_ACCT_WRITE : BLOCK_ACCT_READ;
> + NvmeNamespace *ns = req->ns;
> + NvmeRwCmd *rw = (NvmeRwCmd *) cmd;
>
> - trace_nvme_rw(is_write ? "write" : "read", nlb, data_size, slba);
> + int64_t offset;
> + size_t count;
> + uint16_t status;
>
> - 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);
> - return NVME_LBA_RANGE | NVME_DNR;
> + req->slba = le64_to_cpu(rw->slba);
> + req->nlb = le16_to_cpu(rw->nlb) + 1;
> +
> + trace_nvme_write_zeros(req->cid, le32_to_cpu(cmd->nsid), req->slba,
> + req->nlb);
> +
> + status = nvme_check_bounds(n, req);
> + if (unlikely(status)) {
> + block_acct_invalid(blk_get_stats(n->conf.blk), BLOCK_ACCT_WRITE);
> + return status;
> }
>
> - if (nvme_map_prp(n, &req->qsg, prp1, prp2, data_size, req)) {
> + offset = req->slba << nvme_ns_lbads(ns);
> + count = req->nlb << nvme_ns_lbads(ns);
> +
> + aio = nvme_aio_new(n->conf.blk, offset, NULL, req, NULL);
> +
> + aio->iov.size = count;
> +
> + nvme_req_register_aio(req, aio, NVME_AIO_OPC_WRITE_ZEROES);
> + nvme_aio(aio);
> +
> + return NVME_NO_COMPLETE;
> +}
> +
> +static uint16_t nvme_rw(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
> +{
> + NvmeRwCmd *rw = (NvmeRwCmd *) cmd;
> + NvmeNamespace *ns = req->ns;
> + int status;
> +
> + enum BlockAcctType acct =
> + nvme_req_is_write(req) ? BLOCK_ACCT_WRITE : BLOCK_ACCT_READ;
> +
> + req->nlb = le16_to_cpu(rw->nlb) + 1;
> + req->slba = le64_to_cpu(rw->slba);
> +
> + trace_nvme_rw(nvme_req_is_write(req) ? "write" : "read", req->nlb,
> + req->nlb << nvme_ns_lbads(req->ns), req->slba);
> +
> + status = nvme_check_rw(n, req);
> + if (status) {
> block_acct_invalid(blk_get_stats(n->conf.blk), acct);
> - return NVME_INVALID_FIELD | NVME_DNR;
> + return status;
> }
>
> - dma_acct_start(n->conf.blk, &req->acct, &req->qsg, acct);
> - if (!req->is_cmb) {
> - req->aiocb = is_write ?
> - dma_blk_write(n->conf.blk, &req->qsg, data_offset, BDRV_SECTOR_SIZE,
> - nvme_rw_cb, req) :
> - dma_blk_read(n->conf.blk, &req->qsg, data_offset, BDRV_SECTOR_SIZE,
> - nvme_rw_cb, req);
> - } else {
> - qemu_iovec_init(&req->iov, req->qsg.nsg);
> - dma_to_cmb(n, &req->qsg, &req->iov);
> - req->aiocb = is_write ?
> - blk_aio_pwritev(n->conf.blk, data_offset, &req->iov, 0, nvme_rw_cb,
> - req) :
> - blk_aio_preadv(n->conf.blk, data_offset, &req->iov, 0, nvme_rw_cb,
> - req);
> + status = nvme_map(n, cmd, req);
> + if (status) {
> + block_acct_invalid(blk_get_stats(n->conf.blk), acct);
> + return status;
> }
>
> + nvme_rw_aio(n->conf.blk, req->slba << nvme_ns_lbads(ns), &req->qsg, req);
> + nvme_req_set_cb(req, nvme_rw_cb, NULL);
> +
> return NVME_NO_COMPLETE;
> }
>
> static uint16_t nvme_io_cmd(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
> {
> - NvmeNamespace *ns;
> uint32_t nsid = le32_to_cpu(cmd->nsid);
>
> + trace_nvme_io_cmd(req->cid, nsid, le16_to_cpu(req->sq->sqid), cmd->opcode);
> +
> if (unlikely(nsid == 0 || nsid > n->num_namespaces)) {
> trace_nvme_err_invalid_ns(nsid, n->num_namespaces);
> return NVME_INVALID_NSID | NVME_DNR;
> }
>
> - ns = &n->namespaces[nsid - 1];
> + req->ns = &n->namespaces[nsid - 1];
> +
> switch (cmd->opcode) {
> case NVME_CMD_FLUSH:
> - return nvme_flush(n, ns, cmd, req);
> + return nvme_flush(n, cmd, req);
> case NVME_CMD_WRITE_ZEROS:
> - return nvme_write_zeros(n, ns, cmd, req);
> + return nvme_write_zeros(n, cmd, req);
> case NVME_CMD_WRITE:
> case NVME_CMD_READ:
> - return nvme_rw(n, ns, cmd, req);
> + return nvme_rw(n, cmd, req);
> default:
> trace_nvme_err_invalid_opc(cmd->opcode);
> return NVME_INVALID_OPCODE | NVME_DNR;
> @@ -609,6 +867,7 @@ static uint16_t nvme_del_sq(NvmeCtrl *n, NvmeCmd *cmd)
> NvmeRequest *req, *next;
> NvmeSQueue *sq;
> NvmeCQueue *cq;
> + NvmeAIO *aio;
> uint16_t qid = le16_to_cpu(c->qid);
>
> if (unlikely(!qid || nvme_check_sqid(n, qid))) {
> @@ -621,8 +880,11 @@ static uint16_t nvme_del_sq(NvmeCtrl *n, NvmeCmd *cmd)
> sq = n->sq[qid];
> while (!QTAILQ_EMPTY(&sq->out_req_list)) {
> req = QTAILQ_FIRST(&sq->out_req_list);
> - assert(req->aiocb);
> - blk_aio_cancel(req->aiocb);
> + while (!QTAILQ_EMPTY(&req->aio_tailq)) {
> + aio = QTAILQ_FIRST(&req->aio_tailq);
> + assert(aio->aiocb);
> + blk_aio_cancel(aio->aiocb);
What about releasing memory associated with given aio ?
> + }
> }
> if (!nvme_check_cqid(n, sq->cqid)) {
> cq = n->cq[sq->cqid];
> @@ -659,6 +921,7 @@ static void nvme_init_sq(NvmeSQueue *sq, NvmeCtrl *n, uint64_t dma_addr,
> QTAILQ_INIT(&sq->out_req_list);
> for (i = 0; i < sq->size; i++) {
> sq->io_req[i].sq = sq;
> + QTAILQ_INIT(&(sq->io_req[i].aio_tailq));
> QTAILQ_INSERT_TAIL(&(sq->req_list), &sq->io_req[i], entry);
> }
> sq->timer = timer_new_ns(QEMU_CLOCK_VIRTUAL, nvme_process_sq, sq);
> @@ -820,6 +1083,7 @@ static uint16_t nvme_get_log(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
> uint32_t numdl, numdu;
> uint64_t off, lpol, lpou;
> size_t len;
> + uint16_t status;
>
> numdl = (dw10 >> 16);
> numdu = (dw11 & 0xffff);
> @@ -835,6 +1099,11 @@ static uint16_t nvme_get_log(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
>
> trace_nvme_get_log(req->cid, lid, lsp, rae, len, off);
>
> + status = nvme_check_mdts(n, len, req);
> + if (status) {
> + return status;
> + }
> +
> switch (lid) {
> case NVME_LOG_ERROR_INFO:
> return nvme_error_info(n, cmd, rae, len, off, req);
> @@ -1353,8 +1622,9 @@ static void nvme_init_req(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
>
> memcpy(&req->cmd, cmd, sizeof(NvmeCmd));
> req->status = NVME_SUCCESS;
> - req->is_cmb = false;
> - req->is_write = false;
> + req->flags = 0x0;
> + req->cb = NULL;
> + req->cb_arg = NULL;
> }
>
> static void nvme_process_sq(void *opaque)
> @@ -1953,6 +2223,7 @@ static void nvme_init_ctrl(NvmeCtrl *n)
> id->ieee[0] = 0x00;
> id->ieee[1] = 0x02;
> id->ieee[2] = 0xb3;
> + id->mdts = params->mdts;
> id->ver = cpu_to_le32(0x00010300);
> id->oacs = cpu_to_le16(0);
> id->acl = 3;
> diff --git a/hw/block/nvme.h b/hw/block/nvme.h
> index add9ff335aa5..2f6706899de1 100644
> --- a/hw/block/nvme.h
> +++ b/hw/block/nvme.h
> @@ -8,7 +8,8 @@
> DEFINE_PROP_UINT32("cmb_size_mb", _state, _props.cmb_size_mb, 0), \
> DEFINE_PROP_UINT32("num_queues", _state, _props.num_queues, 64), \
> DEFINE_PROP_UINT8("elpe", _state, _props.elpe, 24), \
> - DEFINE_PROP_UINT8("aerl", _state, _props.aerl, 3)
> + DEFINE_PROP_UINT8("aerl", _state, _props.aerl, 3), \
> + DEFINE_PROP_UINT8("mdts", _state, _props.mdts, 7)
>
> typedef struct NvmeParams {
> char *serial;
> @@ -16,6 +17,7 @@ typedef struct NvmeParams {
> uint32_t cmb_size_mb;
> uint8_t elpe;
> uint8_t aerl;
> + uint8_t mdts;
> } NvmeParams;
>
> typedef struct NvmeAsyncEvent {
> @@ -23,23 +25,124 @@ typedef struct NvmeAsyncEvent {
> NvmeAerResult result;
> } NvmeAsyncEvent;
>
> -typedef struct NvmeRequest {
> - struct NvmeSQueue *sq;
> - BlockAIOCB *aiocb;
> - uint16_t status;
> - uint16_t cid;
> - bool is_cmb;
> - bool is_write;
> - NvmeCqe cqe;
> - BlockAcctCookie acct;
> - QEMUSGList qsg;
> - QEMUIOVector iov;
> - NvmeCmd cmd;
> - QTAILQ_ENTRY(NvmeRequest)entry;
> -} NvmeRequest;
> -
> -typedef struct NvmeSQueue {
> - struct NvmeCtrl *ctrl;
> +typedef enum NvmeAIOOp {
> + NVME_AIO_OPC_NONE = 0x0,
> + NVME_AIO_OPC_FLUSH = 0x1,
> + NVME_AIO_OPC_READ = 0x2,
> + NVME_AIO_OPC_WRITE = 0x3,
> + NVME_AIO_OPC_WRITE_ZEROES = 0x4,
> +} NvmeAIOOp;
> +
> +typedef struct NvmeRequest NvmeRequest;
> +typedef struct NvmeAIO NvmeAIO;
> +typedef void NvmeAIOCompletionFunc(NvmeAIO *aio, void *opaque);
> +
> +struct NvmeAIO {
> + NvmeRequest *req;
> +
> + NvmeAIOOp opc;
> + int64_t offset;
> + BlockBackend *blk;
> + BlockAIOCB *aiocb;
> + BlockAcctCookie acct;
> +
> + NvmeAIOCompletionFunc *cb;
> + void *cb_arg;
> +
> + QEMUSGList *qsg;
> + QEMUIOVector iov;
There is a bit of inconsistency on the ownership of IOVs and SGLs.
SGLs now seem to be owned by request whereas IOVs by the aio.
WOuld be good to have that unified or documented at least.
> +
> + QTAILQ_ENTRY(NvmeAIO) tailq_entry;
> +};
> +
> +static inline const char *nvme_aio_opc_str(NvmeAIO *aio)
> +{
> + switch (aio->opc) {
> + case NVME_AIO_OPC_NONE: return "NVME_AIO_OP_NONE";
> + case NVME_AIO_OPC_FLUSH: return "NVME_AIO_OP_FLUSH";
> + case NVME_AIO_OPC_READ: return "NVME_AIO_OP_READ";
> + case NVME_AIO_OPC_WRITE: return "NVME_AIO_OP_WRITE";
> + case NVME_AIO_OPC_WRITE_ZEROES: return "NVME_AIO_OP_WRITE_ZEROES";
> + default: return "NVME_AIO_OP_UNKNOWN";
> + }
> +}
> +
> +#define NVME_REQ_TRANSFER_DMA 0x1
This one does not seem to be used ....
BR
Beata
> +#define NVME_REQ_TRANSFER_CMB 0x2
> +#define NVME_REQ_TRANSFER_MASK 0x3
> +
> +typedef struct NvmeSQueue NvmeSQueue;
> +typedef struct NvmeNamespace NvmeNamespace;
> +typedef void NvmeRequestCompletionFunc(NvmeRequest *req, void *opaque);
> +
> +struct NvmeRequest {
> + NvmeSQueue *sq;
> + NvmeNamespace *ns;
> + NvmeCqe cqe;
> + NvmeCmd cmd;
> +
> + uint64_t slba;
> + uint32_t nlb;
> + uint16_t status;
> + uint16_t cid;
> + int flags;
> +
> + NvmeRequestCompletionFunc *cb;
> + void *cb_arg;
> +
> + QEMUSGList qsg;
> +
> + QTAILQ_HEAD(, NvmeAIO) aio_tailq;
> + QTAILQ_ENTRY(NvmeRequest) entry;
> +};
> +
> +static inline void nvme_req_set_cb(NvmeRequest *req,
> + NvmeRequestCompletionFunc *cb, void *cb_arg)
> +{
> + req->cb = cb;
> + req->cb_arg = cb_arg;
> +}
> +
> +static inline void nvme_req_clear_cb(NvmeRequest *req)
> +{
> + req->cb = req->cb_arg = NULL;
> +}
> +
> +static inline uint16_t nvme_cid(NvmeRequest *req)
> +{
> + if (req) {
> + return req->cid;
> + }
> +
> + return 0xffff;
> +}
> +
> +static inline bool nvme_req_is_cmb(NvmeRequest *req)
> +{
> + return (req->flags & NVME_REQ_TRANSFER_MASK) == NVME_REQ_TRANSFER_CMB;
> +}
> +
> +static void nvme_req_set_cmb(NvmeRequest *req)
> +{
> + req->flags = NVME_REQ_TRANSFER_CMB;
> +}
> +
> +static inline bool nvme_req_is_write(NvmeRequest *req)
> +{
> + switch (req->cmd.opcode) {
> + case NVME_CMD_WRITE:
> + case NVME_CMD_WRITE_UNCOR:
> + case NVME_CMD_WRITE_ZEROS:
> + return true;
> + default:
> + return false;
> + }
> +}
> +
> +typedef struct NvmeCtrl NvmeCtrl;
> +
> +struct NvmeSQueue {
> + NvmeCtrl *ctrl;
> uint16_t sqid;
> uint16_t cqid;
> uint32_t head;
> @@ -51,10 +154,12 @@ typedef struct NvmeSQueue {
> QTAILQ_HEAD(, NvmeRequest) req_list;
> QTAILQ_HEAD(, NvmeRequest) out_req_list;
> QTAILQ_ENTRY(NvmeSQueue) entry;
> -} NvmeSQueue;
> +};
>
> -typedef struct NvmeCQueue {
> - struct NvmeCtrl *ctrl;
> +typedef struct NvmeCQueue NvmeCQueue;
> +
> +struct NvmeCQueue {
> + NvmeCtrl *ctrl;
> uint8_t phase;
> uint16_t cqid;
> uint16_t irq_enabled;
> @@ -66,11 +171,11 @@ typedef struct NvmeCQueue {
> QEMUTimer *timer;
> QTAILQ_HEAD(, NvmeSQueue) sq_list;
> QTAILQ_HEAD(, NvmeRequest) req_list;
> -} NvmeCQueue;
> +};
>
> -typedef struct NvmeNamespace {
> +struct NvmeNamespace {
> NvmeIdNs id_ns;
> -} NvmeNamespace;
> +};
>
> #define TYPE_NVME "nvme"
> #define NVME(obj) \
> @@ -122,6 +227,17 @@ typedef struct NvmeCtrl {
> NvmeIdCtrl id_ctrl;
> } NvmeCtrl;
>
> +static inline NvmeCtrl *nvme_ctrl(NvmeRequest *req)
> +{
> + return req->sq->ctrl;
> +}
> +
> +static inline bool nvme_is_error(uint16_t status, uint16_t err)
> +{
> + /* strip DNR and MORE */
> + return (status & 0xfff) == err;
> +}
> +
> static inline NvmeLBAF nvme_ns_lbaf(NvmeNamespace *ns)
> {
> NvmeIdNs *id_ns = &ns->id_ns;
> @@ -143,5 +259,4 @@ static inline uint64_t nvme_ns_nlbas(NvmeCtrl *n, NvmeNamespace *ns)
> return n->ns_size >> nvme_ns_lbads(ns);
> }
>
> -
> #endif /* HW_NVME_H */
> diff --git a/hw/block/trace-events b/hw/block/trace-events
> index e81bb3a64ed7..c7e0a1849043 100644
> --- a/hw/block/trace-events
> +++ b/hw/block/trace-events
> @@ -34,7 +34,12 @@ nvme_irq_pin(void) "pulsing IRQ pin"
> nvme_irq_masked(void) "IRQ is masked"
> nvme_dma_read(uint64_t prp1, uint64_t prp2) "DMA read, prp1=0x%"PRIx64" prp2=0x%"PRIx64""
> nvme_map_prp(uint16_t cid, uint8_t opc, uint64_t trans_len, uint32_t len, uint64_t prp1, uint64_t prp2, int num_prps) "cid %"PRIu16" opc 0x%"PRIx8" trans_len %"PRIu64" len %"PRIu32" prp1 0x%"PRIx64" prp2 0x%"PRIx64" num_prps %d"
> +nvme_req_register_aio(uint16_t cid, void *aio, const char *blkname, uint64_t offset, uint64_t count, const char *opc, void *req) "cid %"PRIu16" aio %p blk \"%s\" offset %"PRIu64" count %"PRIu64" opc \"%s\" req %p"
> +nvme_aio_cb(uint16_t cid, void *aio, const char *blkname, uint64_t offset, const char *opc, void *req) "cid %"PRIu16" aio %p blk \"%s\" offset %"PRIu64" opc \"%s\" req %p"
> +nvme_io_cmd(uint16_t cid, uint32_t nsid, uint16_t sqid, uint8_t opcode) "cid %"PRIu16" nsid %"PRIu32" sqid %"PRIu16" opc 0x%"PRIx8""
> nvme_rw(const char *verb, uint32_t blk_count, uint64_t byte_count, uint64_t lba) "%s %"PRIu32" blocks (%"PRIu64" bytes) from LBA %"PRIu64""
> +nvme_rw_cb(uint16_t cid, uint32_t nsid) "cid %"PRIu16" nsid %"PRIu32""
> +nvme_write_zeros(uint16_t cid, uint32_t nsid, uint64_t slba, uint32_t nlb) "cid %"PRIu16" nsid %"PRIu32" slba %"PRIu64" nlb %"PRIu32""
> nvme_create_sq(uint64_t addr, uint16_t sqid, uint16_t cqid, uint16_t qsize, uint16_t qflags) "create submission queue, addr=0x%"PRIx64", sqid=%"PRIu16", cqid=%"PRIu16", qsize=%"PRIu16", qflags=%"PRIu16""
> nvme_create_cq(uint64_t addr, uint16_t cqid, uint16_t vector, uint16_t size, uint16_t qflags, int ien) "create completion queue, addr=0x%"PRIx64", cqid=%"PRIu16", vector=%"PRIu16", qsize=%"PRIu16", qflags=%"PRIu16", ien=%d"
> nvme_del_sq(uint16_t qid) "deleting submission queue sqid=%"PRIu16""
> @@ -74,6 +79,9 @@ nvme_mmio_shutdown_set(void) "shutdown bit set"
> nvme_mmio_shutdown_cleared(void) "shutdown bit cleared"
>
> # nvme traces for error conditions
> +nvme_err_mdts(uint16_t cid, size_t mdts, size_t len) "cid %"PRIu16" mdts %"PRIu64" len %"PRIu64""
> +nvme_err_prinfo(uint16_t cid, uint16_t ctrl) "cid %"PRIu16" ctrl %"PRIu16""
> +nvme_err_aio(uint16_t cid, void *aio, const char *blkname, uint64_t offset, const char *opc, void *req, uint16_t status) "cid %"PRIu16" aio %p blk \"%s\" offset %"PRIu64" opc \"%s\" req %p status 0x%"PRIx16""
> nvme_err_invalid_dma(void) "PRP/SGL is too small for transfer size"
> nvme_err_invalid_prplist_ent(uint64_t prplist) "PRP list entry is null or not page aligned: 0x%"PRIx64""
> nvme_err_invalid_prp2_align(uint64_t prp2) "PRP2 is not page aligned: 0x%"PRIx64""
> --
> 2.23.0
>
>
^ permalink raw reply [flat|nested] 52+ messages in thread* Re: [PATCH v2 14/20] nvme: allow multiple aios per command
2019-11-12 15:25 ` Beata Michalska
@ 2019-11-21 11:57 ` Klaus Birkelund
2019-11-25 13:59 ` Beata Michalska
0 siblings, 1 reply; 52+ messages in thread
From: Klaus Birkelund @ 2019-11-21 11:57 UTC (permalink / raw)
To: Beata Michalska
Cc: Kevin Wolf, qemu-block, qemu-devel, Max Reitz, Paul Durrant, Keith Busch
On Tue, Nov 12, 2019 at 03:25:06PM +0000, Beata Michalska wrote:
> Hi Klaus,
>
> On Tue, 15 Oct 2019 at 11:55, Klaus Jensen <its@irrelevant.dk> wrote:
> > @@ -341,19 +344,18 @@ static uint16_t nvme_dma_write_prp(NvmeCtrl *n, uint8_t *ptr, uint32_t len,
> Any reason why the nvme_dma_write_prp is missing the changes applied
> to nvme_dma_read_prp ?
>
This was adressed by proxy through changes to the previous patch
(by combining the read/write functions).
> > + case NVME_AIO_OPC_WRITE_ZEROES:
> > + block_acct_start(stats, acct, aio->iov.size, BLOCK_ACCT_WRITE);
> > + aio->aiocb = blk_aio_pwrite_zeroes(aio->blk, aio->offset,
> > + aio->iov.size, BDRV_REQ_MAY_UNMAP, nvme_aio_cb, aio);
> Minor: aio->blk => blk
>
Thanks. Fixed this in a couple of other places as well.
> > @@ -621,8 +880,11 @@ static uint16_t nvme_del_sq(NvmeCtrl *n, NvmeCmd *cmd)
> > sq = n->sq[qid];
> > while (!QTAILQ_EMPTY(&sq->out_req_list)) {
> > req = QTAILQ_FIRST(&sq->out_req_list);
> > - assert(req->aiocb);
> > - blk_aio_cancel(req->aiocb);
> > + while (!QTAILQ_EMPTY(&req->aio_tailq)) {
> > + aio = QTAILQ_FIRST(&req->aio_tailq);
> > + assert(aio->aiocb);
> > + blk_aio_cancel(aio->aiocb);
> What about releasing memory associated with given aio ?
I believe the callback is still called when cancelled? That should take
care of it. Or have I misunderstood that? At least for the DMAAIOCBs it
is.
> > +struct NvmeAIO {
> > + NvmeRequest *req;
> > +
> > + NvmeAIOOp opc;
> > + int64_t offset;
> > + BlockBackend *blk;
> > + BlockAIOCB *aiocb;
> > + BlockAcctCookie acct;
> > +
> > + NvmeAIOCompletionFunc *cb;
> > + void *cb_arg;
> > +
> > + QEMUSGList *qsg;
> > + QEMUIOVector iov;
>
> There is a bit of inconsistency on the ownership of IOVs and SGLs.
> SGLs now seem to be owned by request whereas IOVs by the aio.
> WOuld be good to have that unified or documented at least.
>
Fixed this. The NvmeAIO only holds pointers now.
> > +#define NVME_REQ_TRANSFER_DMA 0x1
> This one does not seem to be used ....
>
I have dropped the flags and reverted to a simple req->is_cmb as that is
all that is really needed.
^ permalink raw reply [flat|nested] 52+ messages in thread* Re: [PATCH v2 14/20] nvme: allow multiple aios per command
2019-11-21 11:57 ` Klaus Birkelund
@ 2019-11-25 13:59 ` Beata Michalska
0 siblings, 0 replies; 52+ messages in thread
From: Beata Michalska @ 2019-11-25 13:59 UTC (permalink / raw)
To: Klaus Birkelund
Cc: Kevin Wolf, qemu-block, qemu-devel, Max Reitz, Paul Durrant, Keith Busch
On Thu, 21 Nov 2019 at 11:57, Klaus Birkelund <its@irrelevant.dk> wrote:
>
> On Tue, Nov 12, 2019 at 03:25:06PM +0000, Beata Michalska wrote:
> > Hi Klaus,
> >
> > On Tue, 15 Oct 2019 at 11:55, Klaus Jensen <its@irrelevant.dk> wrote:
> > > @@ -341,19 +344,18 @@ static uint16_t nvme_dma_write_prp(NvmeCtrl *n, uint8_t *ptr, uint32_t len,
> > Any reason why the nvme_dma_write_prp is missing the changes applied
> > to nvme_dma_read_prp ?
> >
>
> This was adressed by proxy through changes to the previous patch
> (by combining the read/write functions).
>
> > > + case NVME_AIO_OPC_WRITE_ZEROES:
> > > + block_acct_start(stats, acct, aio->iov.size, BLOCK_ACCT_WRITE);
> > > + aio->aiocb = blk_aio_pwrite_zeroes(aio->blk, aio->offset,
> > > + aio->iov.size, BDRV_REQ_MAY_UNMAP, nvme_aio_cb, aio);
> > Minor: aio->blk => blk
> >
>
> Thanks. Fixed this in a couple of other places as well.
>
> > > @@ -621,8 +880,11 @@ static uint16_t nvme_del_sq(NvmeCtrl *n, NvmeCmd *cmd)
> > > sq = n->sq[qid];
> > > while (!QTAILQ_EMPTY(&sq->out_req_list)) {
> > > req = QTAILQ_FIRST(&sq->out_req_list);
> > > - assert(req->aiocb);
> > > - blk_aio_cancel(req->aiocb);
> > > + while (!QTAILQ_EMPTY(&req->aio_tailq)) {
> > > + aio = QTAILQ_FIRST(&req->aio_tailq);
> > > + assert(aio->aiocb);
> > > + blk_aio_cancel(aio->aiocb);
> > What about releasing memory associated with given aio ?
>
> I believe the callback is still called when cancelled? That should take
> care of it. Or have I misunderstood that? At least for the DMAAIOCBs it
> is.
>
It seems that the completion callback is supposed to be called.
My bad.
BR
Beata
> > > +struct NvmeAIO {
> > > + NvmeRequest *req;
> > > +
> > > + NvmeAIOOp opc;
> > > + int64_t offset;
> > > + BlockBackend *blk;
> > > + BlockAIOCB *aiocb;
> > > + BlockAcctCookie acct;
> > > +
> > > + NvmeAIOCompletionFunc *cb;
> > > + void *cb_arg;
> > > +
> > > + QEMUSGList *qsg;
> > > + QEMUIOVector iov;
> >
> > There is a bit of inconsistency on the ownership of IOVs and SGLs.
> > SGLs now seem to be owned by request whereas IOVs by the aio.
> > WOuld be good to have that unified or documented at least.
> >
>
> Fixed this. The NvmeAIO only holds pointers now.
>
> > > +#define NVME_REQ_TRANSFER_DMA 0x1
> > This one does not seem to be used ....
> >
>
> I have dropped the flags and reverted to a simple req->is_cmb as that is
> all that is really needed.
>
^ permalink raw reply [flat|nested] 52+ messages in thread
* [PATCH v2 15/20] nvme: add support for scatter gather lists
2019-10-15 10:38 [PATCH v2 00/20] nvme: support NVMe v1.3d, SGLs and multiple namespaces Klaus Jensen
` (13 preceding siblings ...)
2019-10-15 10:38 ` [PATCH v2 14/20] nvme: allow multiple aios per command Klaus Jensen
@ 2019-10-15 10:38 ` Klaus Jensen
2019-11-12 15:25 ` Beata Michalska
2019-10-15 10:38 ` [PATCH v2 16/20] nvme: support multiple namespaces Klaus Jensen
` (8 subsequent siblings)
23 siblings, 1 reply; 52+ messages in thread
From: Klaus Jensen @ 2019-10-15 10:38 UTC (permalink / raw)
To: qemu-block
Cc: Kevin Wolf, Fam Zheng, Javier Gonzalez, qemu-devel, Max Reitz,
Keith Busch, Paul Durrant, Stephen Bates
For now, support the Data Block, Segment and Last Segment descriptor
types.
See NVM Express 1.3d, Section 4.4 ("Scatter Gather List (SGL)").
Signed-off-by: Klaus Jensen <klaus.jensen@cnexlabs.com>
---
block/nvme.c | 18 +-
hw/block/nvme.c | 380 ++++++++++++++++++++++++++++++++++++------
hw/block/trace-events | 3 +
include/block/nvme.h | 62 ++++++-
4 files changed, 398 insertions(+), 65 deletions(-)
diff --git a/block/nvme.c b/block/nvme.c
index 5be3a39b632e..8825c19c72c2 100644
--- a/block/nvme.c
+++ b/block/nvme.c
@@ -440,7 +440,7 @@ static void nvme_identify(BlockDriverState *bs, int namespace, Error **errp)
error_setg(errp, "Cannot map buffer for DMA");
goto out;
}
- cmd.prp1 = cpu_to_le64(iova);
+ cmd.dptr.prp.prp1 = cpu_to_le64(iova);
if (nvme_cmd_sync(bs, s->queues[0], &cmd)) {
error_setg(errp, "Failed to identify controller");
@@ -529,7 +529,7 @@ static bool nvme_add_io_queue(BlockDriverState *bs, Error **errp)
}
cmd = (NvmeCmd) {
.opcode = NVME_ADM_CMD_CREATE_CQ,
- .prp1 = cpu_to_le64(q->cq.iova),
+ .dptr.prp.prp1 = cpu_to_le64(q->cq.iova),
.cdw10 = cpu_to_le32(((queue_size - 1) << 16) | (n & 0xFFFF)),
.cdw11 = cpu_to_le32(0x3),
};
@@ -540,7 +540,7 @@ static bool nvme_add_io_queue(BlockDriverState *bs, Error **errp)
}
cmd = (NvmeCmd) {
.opcode = NVME_ADM_CMD_CREATE_SQ,
- .prp1 = cpu_to_le64(q->sq.iova),
+ .dptr.prp.prp1 = cpu_to_le64(q->sq.iova),
.cdw10 = cpu_to_le32(((queue_size - 1) << 16) | (n & 0xFFFF)),
.cdw11 = cpu_to_le32(0x1 | (n << 16)),
};
@@ -889,16 +889,16 @@ try_map:
case 0:
abort();
case 1:
- cmd->prp1 = pagelist[0];
- cmd->prp2 = 0;
+ cmd->dptr.prp.prp1 = pagelist[0];
+ cmd->dptr.prp.prp2 = 0;
break;
case 2:
- cmd->prp1 = pagelist[0];
- cmd->prp2 = pagelist[1];
+ cmd->dptr.prp.prp1 = pagelist[0];
+ cmd->dptr.prp.prp2 = pagelist[1];
break;
default:
- cmd->prp1 = pagelist[0];
- cmd->prp2 = cpu_to_le64(req->prp_list_iova + sizeof(uint64_t));
+ cmd->dptr.prp.prp1 = pagelist[0];
+ cmd->dptr.prp.prp2 = cpu_to_le64(req->prp_list_iova + sizeof(uint64_t));
break;
}
trace_nvme_cmd_map_qiov(s, cmd, req, qiov, entries);
diff --git a/hw/block/nvme.c b/hw/block/nvme.c
index f4b9bd36a04e..0a5cd079df9a 100644
--- a/hw/block/nvme.c
+++ b/hw/block/nvme.c
@@ -296,6 +296,198 @@ unmap:
return status;
}
+static uint16_t nvme_map_sgl_data(NvmeCtrl *n, QEMUSGList *qsg,
+ NvmeSglDescriptor *segment, uint64_t nsgld, uint32_t *len,
+ NvmeRequest *req)
+{
+ dma_addr_t addr, trans_len;
+
+ for (int i = 0; i < nsgld; i++) {
+ if (NVME_SGL_TYPE(segment[i].type) != SGL_DESCR_TYPE_DATA_BLOCK) {
+ trace_nvme_err_invalid_sgl_descriptor(req->cid,
+ NVME_SGL_TYPE(segment[i].type));
+ return NVME_SGL_DESCRIPTOR_TYPE_INVALID | NVME_DNR;
+ }
+
+ if (*len == 0) {
+ if (!NVME_CTRL_SGLS_EXCESS_LENGTH(n->id_ctrl.sgls)) {
+ trace_nvme_err_invalid_sgl_excess_length(req->cid);
+ return NVME_DATA_SGL_LENGTH_INVALID | NVME_DNR;
+ }
+
+ break;
+ }
+
+ addr = le64_to_cpu(segment[i].addr);
+ trans_len = MIN(*len, le64_to_cpu(segment[i].len));
+
+ if (nvme_addr_is_cmb(n, addr)) {
+ /*
+ * All data and metadata, if any, associated with a particular
+ * command shall be located in either the CMB or host memory. Thus,
+ * if an address if found to be in the CMB and we have already
+ * mapped data that is in host memory, the use is invalid.
+ */
+ if (!nvme_req_is_cmb(req) && qsg->size) {
+ return NVME_INVALID_USE_OF_CMB | NVME_DNR;
+ }
+
+ nvme_req_set_cmb(req);
+ } else {
+ /*
+ * Similarly, if the address does not reference the CMB, but we
+ * have already established that the request has data or metadata
+ * in the CMB, the use is invalid.
+ */
+ if (nvme_req_is_cmb(req)) {
+ return NVME_INVALID_USE_OF_CMB | NVME_DNR;
+ }
+ }
+
+ qemu_sglist_add(qsg, addr, trans_len);
+
+ *len -= trans_len;
+ }
+
+ return NVME_SUCCESS;
+}
+
+static uint16_t nvme_map_sgl(NvmeCtrl *n, QEMUSGList *qsg,
+ NvmeSglDescriptor sgl, uint32_t len, NvmeRequest *req)
+{
+ const int MAX_NSGLD = 256;
+
+ NvmeSglDescriptor segment[MAX_NSGLD];
+ uint64_t nsgld;
+ uint16_t status;
+ bool sgl_in_cmb = false;
+ hwaddr addr = le64_to_cpu(sgl.addr);
+
+ trace_nvme_map_sgl(req->cid, NVME_SGL_TYPE(sgl.type), req->nlb, len);
+
+ pci_dma_sglist_init(qsg, &n->parent_obj, 1);
+
+ /*
+ * If the entire transfer can be described with a single data block it can
+ * be mapped directly.
+ */
+ if (NVME_SGL_TYPE(sgl.type) == SGL_DESCR_TYPE_DATA_BLOCK) {
+ status = nvme_map_sgl_data(n, qsg, &sgl, 1, &len, req);
+ if (status) {
+ goto unmap;
+ }
+
+ goto out;
+ }
+
+ /*
+ * If the segment is located in the CMB, the submission queue of the
+ * request must also reside there.
+ */
+ if (nvme_addr_is_cmb(n, addr)) {
+ if (!nvme_addr_is_cmb(n, req->sq->dma_addr)) {
+ return NVME_INVALID_USE_OF_CMB | NVME_DNR;
+ }
+
+ sgl_in_cmb = true;
+ }
+
+ while (NVME_SGL_TYPE(sgl.type) == SGL_DESCR_TYPE_SEGMENT) {
+ bool addr_is_cmb;
+
+ nsgld = le64_to_cpu(sgl.len) / sizeof(NvmeSglDescriptor);
+
+ /* read the segment in chunks of 256 descriptors (4k) */
+ while (nsgld > MAX_NSGLD) {
+ nvme_addr_read(n, addr, segment, sizeof(segment));
+
+ status = nvme_map_sgl_data(n, qsg, segment, MAX_NSGLD, &len, req);
+ if (status) {
+ goto unmap;
+ }
+
+ nsgld -= MAX_NSGLD;
+ addr += MAX_NSGLD * sizeof(NvmeSglDescriptor);
+ }
+
+ nvme_addr_read(n, addr, segment, nsgld * sizeof(NvmeSglDescriptor));
+
+ sgl = segment[nsgld - 1];
+ addr = le64_to_cpu(sgl.addr);
+
+ /* an SGL is allowed to end with a Data Block in a regular Segment */
+ if (NVME_SGL_TYPE(sgl.type) == SGL_DESCR_TYPE_DATA_BLOCK) {
+ status = nvme_map_sgl_data(n, qsg, segment, nsgld, &len, req);
+ if (status) {
+ goto unmap;
+ }
+
+ goto out;
+ }
+
+ /* do not map last descriptor */
+ status = nvme_map_sgl_data(n, qsg, segment, nsgld - 1, &len, req);
+ if (status) {
+ goto unmap;
+ }
+
+ /*
+ * If the next segment is in the CMB, make sure that the sgl was
+ * already located there.
+ */
+ addr_is_cmb = nvme_addr_is_cmb(n, addr);
+ if ((sgl_in_cmb && !addr_is_cmb) || (!sgl_in_cmb && addr_is_cmb)) {
+ status = NVME_INVALID_USE_OF_CMB | NVME_DNR;
+ goto unmap;
+ }
+ }
+
+ /*
+ * If the segment did not end with a Data Block or a Segment descriptor, it
+ * must be a Last Segment descriptor.
+ */
+ if (NVME_SGL_TYPE(sgl.type) != SGL_DESCR_TYPE_LAST_SEGMENT) {
+ trace_nvme_err_invalid_sgl_descriptor(req->cid,
+ NVME_SGL_TYPE(sgl.type));
+ return NVME_SGL_DESCRIPTOR_TYPE_INVALID | NVME_DNR;
+ }
+
+ nsgld = le64_to_cpu(sgl.len) / sizeof(NvmeSglDescriptor);
+
+ while (nsgld > MAX_NSGLD) {
+ nvme_addr_read(n, addr, segment, sizeof(segment));
+
+ status = nvme_map_sgl_data(n, qsg, segment, MAX_NSGLD, &len, req);
+ if (status) {
+ goto unmap;
+ }
+
+ nsgld -= MAX_NSGLD;
+ addr += MAX_NSGLD * sizeof(NvmeSglDescriptor);
+ }
+
+ nvme_addr_read(n, addr, segment, nsgld * sizeof(NvmeSglDescriptor));
+
+ status = nvme_map_sgl_data(n, qsg, segment, nsgld, &len, req);
+ if (status) {
+ goto unmap;
+ }
+
+out:
+ /* if there is any residual left in len, the SGL was too short */
+ if (len) {
+ status = NVME_DATA_SGL_LENGTH_INVALID | NVME_DNR;
+ goto unmap;
+ }
+
+ return NVME_SUCCESS;
+
+unmap:
+ qemu_sglist_destroy(qsg);
+
+ return status;
+}
+
static void dma_to_cmb(NvmeCtrl *n, QEMUSGList *qsg, QEMUIOVector *iov)
{
for (int i = 0; i < qsg->nsg; i++) {
@@ -341,6 +533,56 @@ static uint16_t nvme_dma_write_prp(NvmeCtrl *n, uint8_t *ptr, uint32_t len,
return status;
}
+static uint16_t nvme_dma_write_sgl(NvmeCtrl *n, uint8_t *ptr, uint32_t len,
+ NvmeSglDescriptor sgl, NvmeRequest *req)
+{
+ QEMUSGList qsg;
+ uint16_t err = NVME_SUCCESS;
+
+ err = nvme_map_sgl(n, &qsg, sgl, len, req);
+ if (err) {
+ return err;
+ }
+
+ if (nvme_req_is_cmb(req)) {
+ QEMUIOVector iov;
+
+ qemu_iovec_init(&iov, qsg.nsg);
+ dma_to_cmb(n, &qsg, &iov);
+
+ if (unlikely(qemu_iovec_to_buf(&iov, 0, ptr, len) != len)) {
+ trace_nvme_err_invalid_dma();
+ err = NVME_INVALID_FIELD | NVME_DNR;
+ }
+
+ qemu_iovec_destroy(&iov);
+
+ return err;
+ }
+
+ if (unlikely(dma_buf_write(ptr, len, &qsg))) {
+ trace_nvme_err_invalid_dma();
+ err = NVME_INVALID_FIELD | NVME_DNR;
+ }
+
+ qemu_sglist_destroy(&qsg);
+
+ return err;
+}
+
+static uint16_t nvme_dma_write(NvmeCtrl *n, uint8_t *ptr, uint32_t len,
+ NvmeCmd *cmd, NvmeRequest *req)
+{
+ if (NVME_CMD_FLAGS_PSDT(cmd->flags)) {
+ return nvme_dma_write_sgl(n, ptr, len, cmd->dptr.sgl, req);
+ }
+
+ uint64_t prp1 = le64_to_cpu(cmd->dptr.prp.prp1);
+ uint64_t prp2 = le64_to_cpu(cmd->dptr.prp.prp2);
+
+ return nvme_dma_write_prp(n, ptr, len, prp1, prp2, req);
+}
+
static uint16_t nvme_dma_read_prp(NvmeCtrl *n, uint8_t *ptr, uint32_t len,
uint64_t prp1, uint64_t prp2, NvmeRequest *req)
{
@@ -378,13 +620,68 @@ out:
return status;
}
+static uint16_t nvme_dma_read_sgl(NvmeCtrl *n, uint8_t *ptr, uint32_t len,
+ NvmeSglDescriptor sgl, NvmeCmd *cmd, NvmeRequest *req)
+{
+ QEMUSGList qsg;
+ uint16_t err = NVME_SUCCESS;
+
+ err = nvme_map_sgl(n, &qsg, sgl, len, req);
+ if (err) {
+ return err;
+ }
+
+ if (nvme_req_is_cmb(req)) {
+ QEMUIOVector iov;
+
+ qemu_iovec_init(&iov, qsg.nsg);
+ dma_to_cmb(n, &qsg, &iov);
+
+ if (unlikely(qemu_iovec_from_buf(&iov, 0, ptr, len) != len)) {
+ trace_nvme_err_invalid_dma();
+ err = NVME_INVALID_FIELD | NVME_DNR;
+ }
+
+ qemu_iovec_destroy(&iov);
+
+ goto out;
+ }
+
+ if (unlikely(dma_buf_read(ptr, len, &qsg))) {
+ trace_nvme_err_invalid_dma();
+ err = NVME_INVALID_FIELD | NVME_DNR;
+ }
+
+out:
+ qemu_sglist_destroy(&qsg);
+
+ return err;
+}
+
+static uint16_t nvme_dma_read(NvmeCtrl *n, uint8_t *ptr, uint32_t len,
+ NvmeCmd *cmd, NvmeRequest *req)
+{
+ if (NVME_CMD_FLAGS_PSDT(cmd->flags)) {
+ return nvme_dma_read_sgl(n, ptr, len, cmd->dptr.sgl, cmd, req);
+ }
+
+ uint64_t prp1 = le64_to_cpu(cmd->dptr.prp.prp1);
+ uint64_t prp2 = le64_to_cpu(cmd->dptr.prp.prp2);
+
+ return nvme_dma_read_prp(n, ptr, len, prp1, prp2, req);
+}
+
static uint16_t nvme_map(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
{
- NvmeNamespace *ns = req->ns;
+ uint32_t len = req->nlb << nvme_ns_lbads(req->ns);
+ uint64_t prp1, prp2;
+
+ if (NVME_CMD_FLAGS_PSDT(cmd->flags)) {
+ return nvme_map_sgl(n, &req->qsg, cmd->dptr.sgl, len, req);
+ }
- uint32_t len = req->nlb << nvme_ns_lbads(ns);
- uint64_t prp1 = le64_to_cpu(cmd->prp1);
- uint64_t prp2 = le64_to_cpu(cmd->prp2);
+ prp1 = le64_to_cpu(cmd->dptr.prp.prp1);
+ prp2 = le64_to_cpu(cmd->dptr.prp.prp2);
return nvme_map_prp(n, &req->qsg, prp1, prp2, len, req);
}
@@ -975,8 +1272,6 @@ static uint16_t nvme_error_info(NvmeCtrl *n, NvmeCmd *cmd, uint8_t rae,
uint32_t buf_len, uint64_t off, NvmeRequest *req)
{
uint32_t trans_len;
- uint64_t prp1 = le64_to_cpu(cmd->prp1);
- uint64_t prp2 = le64_to_cpu(cmd->prp2);
if (off > sizeof(*n->elpes) * (n->params.elpe + 1)) {
return NVME_INVALID_FIELD | NVME_DNR;
@@ -988,15 +1283,12 @@ static uint16_t nvme_error_info(NvmeCtrl *n, NvmeCmd *cmd, uint8_t rae,
nvme_clear_events(n, NVME_AER_TYPE_ERROR);
}
- return nvme_dma_read_prp(n, (uint8_t *) n->elpes + off, trans_len, prp1,
- prp2, req);
+ return nvme_dma_read(n, (uint8_t *) n->elpes + off, trans_len, cmd, req);
}
static uint16_t nvme_smart_info(NvmeCtrl *n, NvmeCmd *cmd, uint8_t rae,
uint32_t buf_len, uint64_t off, NvmeRequest *req)
{
- uint64_t prp1 = le64_to_cpu(cmd->prp1);
- uint64_t prp2 = le64_to_cpu(cmd->prp2);
uint32_t nsid = le32_to_cpu(cmd->nsid);
uint32_t trans_len;
@@ -1047,16 +1339,13 @@ static uint16_t nvme_smart_info(NvmeCtrl *n, NvmeCmd *cmd, uint8_t rae,
nvme_clear_events(n, NVME_AER_TYPE_SMART);
}
- return nvme_dma_read_prp(n, (uint8_t *) &smart + off, trans_len, prp1,
- prp2, req);
+ return nvme_dma_read(n, (uint8_t *) &smart + off, trans_len, cmd, req);
}
static uint16_t nvme_fw_log_info(NvmeCtrl *n, NvmeCmd *cmd, uint32_t buf_len,
uint64_t off, NvmeRequest *req)
{
uint32_t trans_len;
- uint64_t prp1 = le64_to_cpu(cmd->prp1);
- uint64_t prp2 = le64_to_cpu(cmd->prp2);
NvmeFwSlotInfoLog fw_log;
if (off > sizeof(fw_log)) {
@@ -1067,8 +1356,7 @@ static uint16_t nvme_fw_log_info(NvmeCtrl *n, NvmeCmd *cmd, uint32_t buf_len,
trans_len = MIN(sizeof(fw_log) - off, buf_len);
- return nvme_dma_read_prp(n, (uint8_t *) &fw_log + off, trans_len, prp1,
- prp2, req);
+ return nvme_dma_read(n, (uint8_t *) &fw_log + off, trans_len, cmd, req);
}
static uint16_t nvme_get_log(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
@@ -1210,25 +1498,18 @@ static uint16_t nvme_create_cq(NvmeCtrl *n, NvmeCmd *cmd)
return NVME_SUCCESS;
}
-static uint16_t nvme_identify_ctrl(NvmeCtrl *n, NvmeIdentify *c,
- NvmeRequest *req)
+static uint16_t nvme_identify_ctrl(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
{
- uint64_t prp1 = le64_to_cpu(c->prp1);
- uint64_t prp2 = le64_to_cpu(c->prp2);
-
trace_nvme_identify_ctrl();
- return nvme_dma_read_prp(n, (uint8_t *)&n->id_ctrl, sizeof(n->id_ctrl),
- prp1, prp2, req);
+ return nvme_dma_read(n, (uint8_t *) &n->id_ctrl, sizeof(n->id_ctrl), cmd,
+ req);
}
-static uint16_t nvme_identify_ns(NvmeCtrl *n, NvmeIdentify *c,
- NvmeRequest *req)
+static uint16_t nvme_identify_ns(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
{
NvmeNamespace *ns;
- uint32_t nsid = le32_to_cpu(c->nsid);
- uint64_t prp1 = le64_to_cpu(c->prp1);
- uint64_t prp2 = le64_to_cpu(c->prp2);
+ uint32_t nsid = le32_to_cpu(cmd->nsid);
trace_nvme_identify_ns(nsid);
@@ -1239,17 +1520,15 @@ static uint16_t nvme_identify_ns(NvmeCtrl *n, NvmeIdentify *c,
ns = &n->namespaces[nsid - 1];
- return nvme_dma_read_prp(n, (uint8_t *)&ns->id_ns, sizeof(ns->id_ns),
- prp1, prp2, req);
+ return nvme_dma_read(n, (uint8_t *) &ns->id_ns, sizeof(ns->id_ns), cmd,
+ req);
}
-static uint16_t nvme_identify_ns_list(NvmeCtrl *n, NvmeIdentify *c,
+static uint16_t nvme_identify_ns_list(NvmeCtrl *n, NvmeCmd *cmd,
NvmeRequest *req)
{
static const int data_len = 4 * KiB;
- 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);
+ uint32_t min_nsid = le32_to_cpu(cmd->nsid);
uint32_t *list;
uint16_t ret;
int i, j = 0;
@@ -1266,12 +1545,12 @@ static uint16_t nvme_identify_ns_list(NvmeCtrl *n, NvmeIdentify *c,
break;
}
}
- ret = nvme_dma_read_prp(n, (uint8_t *)list, data_len, prp1, prp2, req);
+ ret = nvme_dma_read(n, (uint8_t *) list, data_len, cmd, req);
g_free(list);
return ret;
}
-static uint16_t nvme_identify_ns_descr_list(NvmeCtrl *n, NvmeIdentify *c,
+static uint16_t nvme_identify_ns_descr_list(NvmeCtrl *n, NvmeCmd *cmd,
NvmeRequest *req)
{
static const int len = 4096;
@@ -1283,9 +1562,7 @@ static uint16_t nvme_identify_ns_descr_list(NvmeCtrl *n, NvmeIdentify *c,
uint8_t nid[16];
};
- uint32_t nsid = le32_to_cpu(c->nsid);
- uint64_t prp1 = le64_to_cpu(c->prp1);
- uint64_t prp2 = le64_to_cpu(c->prp2);
+ uint32_t nsid = le32_to_cpu(cmd->nsid);
struct ns_descr *list;
uint16_t ret;
@@ -1302,7 +1579,7 @@ static uint16_t nvme_identify_ns_descr_list(NvmeCtrl *n, NvmeIdentify *c,
list->nidl = 0x10;
*(uint32_t *) &list->nid[12] = cpu_to_be32(nsid);
- ret = nvme_dma_read_prp(n, (uint8_t *) list, len, prp1, prp2, req);
+ ret = nvme_dma_read(n, (uint8_t *) list, len, cmd, req);
g_free(list);
return ret;
}
@@ -1313,13 +1590,13 @@ static uint16_t nvme_identify(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
switch (le32_to_cpu(c->cns)) {
case 0x00:
- return nvme_identify_ns(n, c, req);
+ return nvme_identify_ns(n, cmd, req);
case 0x01:
- return nvme_identify_ctrl(n, c, req);
+ return nvme_identify_ctrl(n, cmd, req);
case 0x02:
- return nvme_identify_ns_list(n, c, req);
+ return nvme_identify_ns_list(n, cmd, req);
case 0x03:
- return nvme_identify_ns_descr_list(n, c, req);
+ return nvme_identify_ns_descr_list(n, cmd, req);
default:
trace_nvme_err_invalid_identify_cns(le32_to_cpu(c->cns));
return NVME_INVALID_FIELD | NVME_DNR;
@@ -1381,13 +1658,10 @@ static inline uint64_t nvme_get_timestamp(const NvmeCtrl *n)
static uint16_t nvme_get_feature_timestamp(NvmeCtrl *n, NvmeCmd *cmd,
NvmeRequest *req)
{
- uint64_t prp1 = le64_to_cpu(cmd->prp1);
- uint64_t prp2 = le64_to_cpu(cmd->prp2);
-
uint64_t timestamp = nvme_get_timestamp(n);
- return nvme_dma_read_prp(n, (uint8_t *)×tamp, sizeof(timestamp),
- prp1, prp2, req);
+ return nvme_dma_read(n, (uint8_t *)×tamp, sizeof(timestamp), cmd,
+ req);
}
static uint16_t nvme_get_feature(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
@@ -1452,11 +1726,9 @@ static uint16_t nvme_set_feature_timestamp(NvmeCtrl *n, NvmeCmd *cmd,
{
uint16_t ret;
uint64_t timestamp;
- uint64_t prp1 = le64_to_cpu(cmd->prp1);
- uint64_t prp2 = le64_to_cpu(cmd->prp2);
- ret = nvme_dma_write_prp(n, (uint8_t *)×tamp,
- sizeof(timestamp), prp1, prp2, req);
+ ret = nvme_dma_write(n, (uint8_t *)×tamp, sizeof(timestamp), cmd,
+ req);
if (ret != NVME_SUCCESS) {
return ret;
}
@@ -2241,6 +2513,8 @@ static void nvme_init_ctrl(NvmeCtrl *n)
id->vwc = 1;
}
+ id->sgls = cpu_to_le32(0x1);
+
strcpy((char *) id->subnqn, "nqn.2019-08.org.qemu:");
pstrcat((char *) id->subnqn, sizeof(id->subnqn), n->params.serial);
diff --git a/hw/block/trace-events b/hw/block/trace-events
index c7e0a1849043..59d42a3b8c39 100644
--- a/hw/block/trace-events
+++ b/hw/block/trace-events
@@ -34,6 +34,7 @@ nvme_irq_pin(void) "pulsing IRQ pin"
nvme_irq_masked(void) "IRQ is masked"
nvme_dma_read(uint64_t prp1, uint64_t prp2) "DMA read, prp1=0x%"PRIx64" prp2=0x%"PRIx64""
nvme_map_prp(uint16_t cid, uint8_t opc, uint64_t trans_len, uint32_t len, uint64_t prp1, uint64_t prp2, int num_prps) "cid %"PRIu16" opc 0x%"PRIx8" trans_len %"PRIu64" len %"PRIu32" prp1 0x%"PRIx64" prp2 0x%"PRIx64" num_prps %d"
+nvme_map_sgl(uint16_t cid, uint8_t typ, uint32_t nlb, uint64_t len) "cid %"PRIu16" type 0x%"PRIx8" nlb %"PRIu32" len %"PRIu64""
nvme_req_register_aio(uint16_t cid, void *aio, const char *blkname, uint64_t offset, uint64_t count, const char *opc, void *req) "cid %"PRIu16" aio %p blk \"%s\" offset %"PRIu64" count %"PRIu64" opc \"%s\" req %p"
nvme_aio_cb(uint16_t cid, void *aio, const char *blkname, uint64_t offset, const char *opc, void *req) "cid %"PRIu16" aio %p blk \"%s\" offset %"PRIu64" opc \"%s\" req %p"
nvme_io_cmd(uint16_t cid, uint32_t nsid, uint16_t sqid, uint8_t opcode) "cid %"PRIu16" nsid %"PRIu32" sqid %"PRIu16" opc 0x%"PRIx8""
@@ -82,6 +83,8 @@ nvme_mmio_shutdown_cleared(void) "shutdown bit cleared"
nvme_err_mdts(uint16_t cid, size_t mdts, size_t len) "cid %"PRIu16" mdts %"PRIu64" len %"PRIu64""
nvme_err_prinfo(uint16_t cid, uint16_t ctrl) "cid %"PRIu16" ctrl %"PRIu16""
nvme_err_aio(uint16_t cid, void *aio, const char *blkname, uint64_t offset, const char *opc, void *req, uint16_t status) "cid %"PRIu16" aio %p blk \"%s\" offset %"PRIu64" opc \"%s\" req %p status 0x%"PRIx16""
+nvme_err_invalid_sgl_descriptor(uint16_t cid, uint8_t typ) "cid %"PRIu16" type 0x%"PRIx8""
+nvme_err_invalid_sgl_excess_length(uint16_t cid) "cid %"PRIu16""
nvme_err_invalid_dma(void) "PRP/SGL is too small for transfer size"
nvme_err_invalid_prplist_ent(uint64_t prplist) "PRP list entry is null or not page aligned: 0x%"PRIx64""
nvme_err_invalid_prp2_align(uint64_t prp2) "PRP2 is not page aligned: 0x%"PRIx64""
diff --git a/include/block/nvme.h b/include/block/nvme.h
index d4990db4fdf8..ba0a9d4e328f 100644
--- a/include/block/nvme.h
+++ b/include/block/nvme.h
@@ -205,15 +205,53 @@ enum NvmeCmbszMask {
#define NVME_CMBSZ_GETSIZE(cmbsz) \
(NVME_CMBSZ_SZ(cmbsz) * (1 << (12 + 4 * NVME_CMBSZ_SZU(cmbsz))))
+enum NvmeSglDescriptorType {
+ SGL_DESCR_TYPE_DATA_BLOCK = 0x0,
+ SGL_DESCR_TYPE_BIT_BUCKET = 0x1,
+ SGL_DESCR_TYPE_SEGMENT = 0x2,
+ SGL_DESCR_TYPE_LAST_SEGMENT = 0x3,
+ SGL_DESCR_TYPE_KEYED_DATA_BLOCK = 0x4,
+
+ SGL_DESCR_TYPE_VENDOR_SPECIFIC = 0xf,
+};
+
+enum NvmeSglDescriptorSubtype {
+ SGL_DESCR_SUBTYPE_ADDRESS = 0x0,
+ SGL_DESCR_SUBTYPE_OFFSET = 0x1,
+};
+
+typedef struct NvmeSglDescriptor {
+ uint64_t addr;
+ uint32_t len;
+ uint8_t rsvd[3];
+ uint8_t type;
+} NvmeSglDescriptor;
+
+#define NVME_SGL_TYPE(type) (type >> 4)
+
+typedef union NvmeCmdDptr {
+ struct {
+ uint64_t prp1;
+ uint64_t prp2;
+ } prp;
+
+ NvmeSglDescriptor sgl;
+} NvmeCmdDptr;
+
+enum NvmePsdt {
+ PSDT_PRP = 0x0,
+ PSDT_SGL_MPTR_CONTIGUOUS = 0x1,
+ PSDT_SGL_MPTR_SGL = 0x2,
+};
+
typedef struct NvmeCmd {
uint8_t opcode;
- uint8_t fuse;
+ uint8_t flags;
uint16_t cid;
uint32_t nsid;
uint64_t res1;
uint64_t mptr;
- uint64_t prp1;
- uint64_t prp2;
+ NvmeCmdDptr dptr;
uint32_t cdw10;
uint32_t cdw11;
uint32_t cdw12;
@@ -222,6 +260,9 @@ typedef struct NvmeCmd {
uint32_t cdw15;
} NvmeCmd;
+#define NVME_CMD_FLAGS_FUSE(flags) (flags & 0x3)
+#define NVME_CMD_FLAGS_PSDT(flags) ((flags >> 6) & 0x3)
+
enum NvmeAdminCommands {
NVME_ADM_CMD_DELETE_SQ = 0x00,
NVME_ADM_CMD_CREATE_SQ = 0x01,
@@ -427,6 +468,11 @@ enum NvmeStatusCodes {
NVME_CMD_ABORT_MISSING_FUSE = 0x000a,
NVME_INVALID_NSID = 0x000b,
NVME_CMD_SEQ_ERROR = 0x000c,
+ NVME_INVALID_SGL_SEG_DESCRIPTOR = 0x000d,
+ NVME_INVALID_NUM_SGL_DESCRIPTORS = 0x000e,
+ NVME_DATA_SGL_LENGTH_INVALID = 0x000f,
+ NVME_METADATA_SGL_LENGTH_INVALID = 0x0010,
+ NVME_SGL_DESCRIPTOR_TYPE_INVALID = 0x0011,
NVME_INVALID_USE_OF_CMB = 0x0012,
NVME_LBA_RANGE = 0x0080,
NVME_CAP_EXCEEDED = 0x0081,
@@ -623,6 +669,16 @@ enum NvmeIdCtrlOncs {
#define NVME_CTRL_CQES_MIN(cqes) ((cqes) & 0xf)
#define NVME_CTRL_CQES_MAX(cqes) (((cqes) >> 4) & 0xf)
+#define NVME_CTRL_SGLS_SUPPORTED(sgls) ((sgls) & 0x3)
+#define NVME_CTRL_SGLS_SUPPORTED_NO_ALIGNMENT(sgls) ((sgls) & (0x1 << 0))
+#define NVME_CTRL_SGLS_SUPPORTED_DWORD_ALIGNMENT(sgls) ((sgls) & (0x1 << 1))
+#define NVME_CTRL_SGLS_KEYED(sgls) ((sgls) & (0x1 << 2))
+#define NVME_CTRL_SGLS_BITBUCKET(sgls) ((sgls) & (0x1 << 16))
+#define NVME_CTRL_SGLS_MPTR_CONTIGUOUS(sgls) ((sgls) & (0x1 << 17))
+#define NVME_CTRL_SGLS_EXCESS_LENGTH(sgls) ((sgls) & (0x1 << 18))
+#define NVME_CTRL_SGLS_MPTR_SGL(sgls) ((sgls) & (0x1 << 19))
+#define NVME_CTRL_SGLS_ADDR_OFFSET(sgls) ((sgls) & (0x1 << 20))
+
typedef struct NvmeFeatureVal {
uint32_t arbitration;
uint32_t power_mgmt;
--
2.23.0
^ permalink raw reply related [flat|nested] 52+ messages in thread* Re: [PATCH v2 15/20] nvme: add support for scatter gather lists
2019-10-15 10:38 ` [PATCH v2 15/20] nvme: add support for scatter gather lists Klaus Jensen
@ 2019-11-12 15:25 ` Beata Michalska
2019-11-25 6:21 ` Klaus Birkelund
0 siblings, 1 reply; 52+ messages in thread
From: Beata Michalska @ 2019-11-12 15:25 UTC (permalink / raw)
To: Klaus Jensen
Cc: Kevin Wolf, Fam Zheng, Javier Gonzalez, qemu-block, qemu-devel,
Max Reitz, Keith Busch, Paul Durrant, Stephen Bates
Hi Klaus,
On Tue, 15 Oct 2019 at 11:57, Klaus Jensen <its@irrelevant.dk> wrote:
>
> For now, support the Data Block, Segment and Last Segment descriptor
> types.
>
> See NVM Express 1.3d, Section 4.4 ("Scatter Gather List (SGL)").
>
> Signed-off-by: Klaus Jensen <klaus.jensen@cnexlabs.com>
> ---
> block/nvme.c | 18 +-
> hw/block/nvme.c | 380 ++++++++++++++++++++++++++++++++++++------
> hw/block/trace-events | 3 +
> include/block/nvme.h | 62 ++++++-
> 4 files changed, 398 insertions(+), 65 deletions(-)
>
> diff --git a/block/nvme.c b/block/nvme.c
> index 5be3a39b632e..8825c19c72c2 100644
> --- a/block/nvme.c
> +++ b/block/nvme.c
> @@ -440,7 +440,7 @@ static void nvme_identify(BlockDriverState *bs, int namespace, Error **errp)
> error_setg(errp, "Cannot map buffer for DMA");
> goto out;
> }
> - cmd.prp1 = cpu_to_le64(iova);
> + cmd.dptr.prp.prp1 = cpu_to_le64(iova);
>
> if (nvme_cmd_sync(bs, s->queues[0], &cmd)) {
> error_setg(errp, "Failed to identify controller");
> @@ -529,7 +529,7 @@ static bool nvme_add_io_queue(BlockDriverState *bs, Error **errp)
> }
> cmd = (NvmeCmd) {
> .opcode = NVME_ADM_CMD_CREATE_CQ,
> - .prp1 = cpu_to_le64(q->cq.iova),
> + .dptr.prp.prp1 = cpu_to_le64(q->cq.iova),
> .cdw10 = cpu_to_le32(((queue_size - 1) << 16) | (n & 0xFFFF)),
> .cdw11 = cpu_to_le32(0x3),
> };
> @@ -540,7 +540,7 @@ static bool nvme_add_io_queue(BlockDriverState *bs, Error **errp)
> }
> cmd = (NvmeCmd) {
> .opcode = NVME_ADM_CMD_CREATE_SQ,
> - .prp1 = cpu_to_le64(q->sq.iova),
> + .dptr.prp.prp1 = cpu_to_le64(q->sq.iova),
> .cdw10 = cpu_to_le32(((queue_size - 1) << 16) | (n & 0xFFFF)),
> .cdw11 = cpu_to_le32(0x1 | (n << 16)),
> };
> @@ -889,16 +889,16 @@ try_map:
> case 0:
> abort();
> case 1:
> - cmd->prp1 = pagelist[0];
> - cmd->prp2 = 0;
> + cmd->dptr.prp.prp1 = pagelist[0];
> + cmd->dptr.prp.prp2 = 0;
> break;
> case 2:
> - cmd->prp1 = pagelist[0];
> - cmd->prp2 = pagelist[1];
> + cmd->dptr.prp.prp1 = pagelist[0];
> + cmd->dptr.prp.prp2 = pagelist[1];
> break;
> default:
> - cmd->prp1 = pagelist[0];
> - cmd->prp2 = cpu_to_le64(req->prp_list_iova + sizeof(uint64_t));
> + cmd->dptr.prp.prp1 = pagelist[0];
> + cmd->dptr.prp.prp2 = cpu_to_le64(req->prp_list_iova + sizeof(uint64_t));
> break;
> }
> trace_nvme_cmd_map_qiov(s, cmd, req, qiov, entries);
> diff --git a/hw/block/nvme.c b/hw/block/nvme.c
> index f4b9bd36a04e..0a5cd079df9a 100644
> --- a/hw/block/nvme.c
> +++ b/hw/block/nvme.c
> @@ -296,6 +296,198 @@ unmap:
> return status;
> }
>
> +static uint16_t nvme_map_sgl_data(NvmeCtrl *n, QEMUSGList *qsg,
> + NvmeSglDescriptor *segment, uint64_t nsgld, uint32_t *len,
> + NvmeRequest *req)
> +{
> + dma_addr_t addr, trans_len;
> +
> + for (int i = 0; i < nsgld; i++) {
> + if (NVME_SGL_TYPE(segment[i].type) != SGL_DESCR_TYPE_DATA_BLOCK) {
> + trace_nvme_err_invalid_sgl_descriptor(req->cid,
> + NVME_SGL_TYPE(segment[i].type));
> + return NVME_SGL_DESCRIPTOR_TYPE_INVALID | NVME_DNR;
> + }
> +
> + if (*len == 0) {
> + if (!NVME_CTRL_SGLS_EXCESS_LENGTH(n->id_ctrl.sgls)) {
> + trace_nvme_err_invalid_sgl_excess_length(req->cid);
> + return NVME_DATA_SGL_LENGTH_INVALID | NVME_DNR;
> + }
> +
> + break;
> + }
> +
> + addr = le64_to_cpu(segment[i].addr);
> + trans_len = MIN(*len, le64_to_cpu(segment[i].len));
> +
> + if (nvme_addr_is_cmb(n, addr)) {
> + /*
> + * All data and metadata, if any, associated with a particular
> + * command shall be located in either the CMB or host memory. Thus,
> + * if an address if found to be in the CMB and we have already
> + * mapped data that is in host memory, the use is invalid.
> + */
> + if (!nvme_req_is_cmb(req) && qsg->size) {
> + return NVME_INVALID_USE_OF_CMB | NVME_DNR;
> + }
> +
> + nvme_req_set_cmb(req);
> + } else {
> + /*
> + * Similarly, if the address does not reference the CMB, but we
> + * have already established that the request has data or metadata
> + * in the CMB, the use is invalid.
> + */
> + if (nvme_req_is_cmb(req)) {
> + return NVME_INVALID_USE_OF_CMB | NVME_DNR;
> + }
> + }
> +
> + qemu_sglist_add(qsg, addr, trans_len);
> +
> + *len -= trans_len;
> + }
> +
> + return NVME_SUCCESS;
> +}
> +
> +static uint16_t nvme_map_sgl(NvmeCtrl *n, QEMUSGList *qsg,
> + NvmeSglDescriptor sgl, uint32_t len, NvmeRequest *req)
> +{
> + const int MAX_NSGLD = 256;
> +
> + NvmeSglDescriptor segment[MAX_NSGLD];
> + uint64_t nsgld;
> + uint16_t status;
> + bool sgl_in_cmb = false;
> + hwaddr addr = le64_to_cpu(sgl.addr);
> +
> + trace_nvme_map_sgl(req->cid, NVME_SGL_TYPE(sgl.type), req->nlb, len);
> +
> + pci_dma_sglist_init(qsg, &n->parent_obj, 1);
> +
> + /*
> + * If the entire transfer can be described with a single data block it can
> + * be mapped directly.
> + */
> + if (NVME_SGL_TYPE(sgl.type) == SGL_DESCR_TYPE_DATA_BLOCK) {
> + status = nvme_map_sgl_data(n, qsg, &sgl, 1, &len, req);
> + if (status) {
> + goto unmap;
> + }
> +
> + goto out;
> + }
> +
> + /*
> + * If the segment is located in the CMB, the submission queue of the
> + * request must also reside there.
> + */
> + if (nvme_addr_is_cmb(n, addr)) {
> + if (!nvme_addr_is_cmb(n, req->sq->dma_addr)) {
> + return NVME_INVALID_USE_OF_CMB | NVME_DNR;
> + }
> +
> + sgl_in_cmb = true;
> + }
> +
> + while (NVME_SGL_TYPE(sgl.type) == SGL_DESCR_TYPE_SEGMENT) {
> + bool addr_is_cmb;
> +
> + nsgld = le64_to_cpu(sgl.len) / sizeof(NvmeSglDescriptor);
> +
> + /* read the segment in chunks of 256 descriptors (4k) */
> + while (nsgld > MAX_NSGLD) {
> + nvme_addr_read(n, addr, segment, sizeof(segment));
Is there any chance this will go outside the CMB?
> +
> + status = nvme_map_sgl_data(n, qsg, segment, MAX_NSGLD, &len, req);
> + if (status) {
> + goto unmap;
> + }
> +
> + nsgld -= MAX_NSGLD;
> + addr += MAX_NSGLD * sizeof(NvmeSglDescriptor);
> + }
> +
> + nvme_addr_read(n, addr, segment, nsgld * sizeof(NvmeSglDescriptor));
> +
> + sgl = segment[nsgld - 1];
> + addr = le64_to_cpu(sgl.addr);
> +
> + /* an SGL is allowed to end with a Data Block in a regular Segment */
> + if (NVME_SGL_TYPE(sgl.type) == SGL_DESCR_TYPE_DATA_BLOCK) {
> + status = nvme_map_sgl_data(n, qsg, segment, nsgld, &len, req);
> + if (status) {
> + goto unmap;
> + }
> +
> + goto out;
> + }
> +
> + /* do not map last descriptor */
> + status = nvme_map_sgl_data(n, qsg, segment, nsgld - 1, &len, req);
> + if (status) {
> + goto unmap;
> + }
> +
> + /*
> + * If the next segment is in the CMB, make sure that the sgl was
> + * already located there.
> + */
> + addr_is_cmb = nvme_addr_is_cmb(n, addr);
> + if ((sgl_in_cmb && !addr_is_cmb) || (!sgl_in_cmb && addr_is_cmb)) {
> + status = NVME_INVALID_USE_OF_CMB | NVME_DNR;
> + goto unmap;
> + }
> + }
> +
> + /*
> + * If the segment did not end with a Data Block or a Segment descriptor, it
> + * must be a Last Segment descriptor.
> + */
> + if (NVME_SGL_TYPE(sgl.type) != SGL_DESCR_TYPE_LAST_SEGMENT) {
> + trace_nvme_err_invalid_sgl_descriptor(req->cid,
> + NVME_SGL_TYPE(sgl.type));
> + return NVME_SGL_DESCRIPTOR_TYPE_INVALID | NVME_DNR;
Shouldn't we handle a case here that requires calling unmap ?
> + }
> +
> + nsgld = le64_to_cpu(sgl.len) / sizeof(NvmeSglDescriptor);
> +
> + while (nsgld > MAX_NSGLD) {
> + nvme_addr_read(n, addr, segment, sizeof(segment));
> +
> + status = nvme_map_sgl_data(n, qsg, segment, MAX_NSGLD, &len, req);
> + if (status) {
> + goto unmap;
> + }
> +
> + nsgld -= MAX_NSGLD;
> + addr += MAX_NSGLD * sizeof(NvmeSglDescriptor);
> + }
> +
> + nvme_addr_read(n, addr, segment, nsgld * sizeof(NvmeSglDescriptor));
> +
> + status = nvme_map_sgl_data(n, qsg, segment, nsgld, &len, req);
> + if (status) {
> + goto unmap;
> + }
> +
> +out:
> + /* if there is any residual left in len, the SGL was too short */
> + if (len) {
> + status = NVME_DATA_SGL_LENGTH_INVALID | NVME_DNR;
> + goto unmap;
> + }
> +
> + return NVME_SUCCESS;
> +
> +unmap:
> + qemu_sglist_destroy(qsg);
> +
> + return status;
> +}
> +
> static void dma_to_cmb(NvmeCtrl *n, QEMUSGList *qsg, QEMUIOVector *iov)
> {
> for (int i = 0; i < qsg->nsg; i++) {
> @@ -341,6 +533,56 @@ static uint16_t nvme_dma_write_prp(NvmeCtrl *n, uint8_t *ptr, uint32_t len,
> return status;
> }
>
> +static uint16_t nvme_dma_write_sgl(NvmeCtrl *n, uint8_t *ptr, uint32_t len,
> + NvmeSglDescriptor sgl, NvmeRequest *req)
> +{
> + QEMUSGList qsg;
> + uint16_t err = NVME_SUCCESS;
> +
> + err = nvme_map_sgl(n, &qsg, sgl, len, req);
> + if (err) {
> + return err;
> + }
> +
> + if (nvme_req_is_cmb(req)) {
> + QEMUIOVector iov;
> +
> + qemu_iovec_init(&iov, qsg.nsg);
> + dma_to_cmb(n, &qsg, &iov);
> +
> + if (unlikely(qemu_iovec_to_buf(&iov, 0, ptr, len) != len)) {
> + trace_nvme_err_invalid_dma();
> + err = NVME_INVALID_FIELD | NVME_DNR;
> + }
> +
> + qemu_iovec_destroy(&iov);
> +
> + return err;
> + }
> +
> + if (unlikely(dma_buf_write(ptr, len, &qsg))) {
> + trace_nvme_err_invalid_dma();
> + err = NVME_INVALID_FIELD | NVME_DNR;
> + }
> +
> + qemu_sglist_destroy(&qsg);
> +
> + return err;
> +}
> +
> +static uint16_t nvme_dma_write(NvmeCtrl *n, uint8_t *ptr, uint32_t len,
> + NvmeCmd *cmd, NvmeRequest *req)
> +{
> + if (NVME_CMD_FLAGS_PSDT(cmd->flags)) {
> + return nvme_dma_write_sgl(n, ptr, len, cmd->dptr.sgl, req);
> + }
> +
> + uint64_t prp1 = le64_to_cpu(cmd->dptr.prp.prp1);
> + uint64_t prp2 = le64_to_cpu(cmd->dptr.prp.prp2);
> +
> + return nvme_dma_write_prp(n, ptr, len, prp1, prp2, req);
> +}
> +
> static uint16_t nvme_dma_read_prp(NvmeCtrl *n, uint8_t *ptr, uint32_t len,
> uint64_t prp1, uint64_t prp2, NvmeRequest *req)
> {
> @@ -378,13 +620,68 @@ out:
> return status;
> }
>
> +static uint16_t nvme_dma_read_sgl(NvmeCtrl *n, uint8_t *ptr, uint32_t len,
> + NvmeSglDescriptor sgl, NvmeCmd *cmd, NvmeRequest *req)
> +{
> + QEMUSGList qsg;
> + uint16_t err = NVME_SUCCESS;
> +
Very minor: Mixing convention: status vs error
> + err = nvme_map_sgl(n, &qsg, sgl, len, req);
> + if (err) {
> + return err;
> + }
> +
> + if (nvme_req_is_cmb(req)) {
> + QEMUIOVector iov;
> +
> + qemu_iovec_init(&iov, qsg.nsg);
> + dma_to_cmb(n, &qsg, &iov);
> +
> + if (unlikely(qemu_iovec_from_buf(&iov, 0, ptr, len) != len)) {
> + trace_nvme_err_invalid_dma();
> + err = NVME_INVALID_FIELD | NVME_DNR;
> + }
> +
> + qemu_iovec_destroy(&iov);
> +
> + goto out;
> + }
> +
> + if (unlikely(dma_buf_read(ptr, len, &qsg))) {
> + trace_nvme_err_invalid_dma();
> + err = NVME_INVALID_FIELD | NVME_DNR;
> + }
> +
> +out:
> + qemu_sglist_destroy(&qsg);
> +
> + return err;
> +}
> +
> +static uint16_t nvme_dma_read(NvmeCtrl *n, uint8_t *ptr, uint32_t len,
> + NvmeCmd *cmd, NvmeRequest *req)
> +{
> + if (NVME_CMD_FLAGS_PSDT(cmd->flags)) {
> + return nvme_dma_read_sgl(n, ptr, len, cmd->dptr.sgl, cmd, req);
> + }
> +
> + uint64_t prp1 = le64_to_cpu(cmd->dptr.prp.prp1);
> + uint64_t prp2 = le64_to_cpu(cmd->dptr.prp.prp2);
> +
> + return nvme_dma_read_prp(n, ptr, len, prp1, prp2, req);
> +}
> +
> static uint16_t nvme_map(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
> {
> - NvmeNamespace *ns = req->ns;
> + uint32_t len = req->nlb << nvme_ns_lbads(req->ns);
> + uint64_t prp1, prp2;
> +
> + if (NVME_CMD_FLAGS_PSDT(cmd->flags)) {
> + return nvme_map_sgl(n, &req->qsg, cmd->dptr.sgl, len, req);
> + }
>
> - uint32_t len = req->nlb << nvme_ns_lbads(ns);
> - uint64_t prp1 = le64_to_cpu(cmd->prp1);
> - uint64_t prp2 = le64_to_cpu(cmd->prp2);
> + prp1 = le64_to_cpu(cmd->dptr.prp.prp1);
> + prp2 = le64_to_cpu(cmd->dptr.prp.prp2);
>
> return nvme_map_prp(n, &req->qsg, prp1, prp2, len, req);
> }
> @@ -975,8 +1272,6 @@ static uint16_t nvme_error_info(NvmeCtrl *n, NvmeCmd *cmd, uint8_t rae,
> uint32_t buf_len, uint64_t off, NvmeRequest *req)
> {
> uint32_t trans_len;
> - uint64_t prp1 = le64_to_cpu(cmd->prp1);
> - uint64_t prp2 = le64_to_cpu(cmd->prp2);
>
> if (off > sizeof(*n->elpes) * (n->params.elpe + 1)) {
> return NVME_INVALID_FIELD | NVME_DNR;
> @@ -988,15 +1283,12 @@ static uint16_t nvme_error_info(NvmeCtrl *n, NvmeCmd *cmd, uint8_t rae,
> nvme_clear_events(n, NVME_AER_TYPE_ERROR);
> }
>
> - return nvme_dma_read_prp(n, (uint8_t *) n->elpes + off, trans_len, prp1,
> - prp2, req);
> + return nvme_dma_read(n, (uint8_t *) n->elpes + off, trans_len, cmd, req);
> }
>
> static uint16_t nvme_smart_info(NvmeCtrl *n, NvmeCmd *cmd, uint8_t rae,
> uint32_t buf_len, uint64_t off, NvmeRequest *req)
> {
> - uint64_t prp1 = le64_to_cpu(cmd->prp1);
> - uint64_t prp2 = le64_to_cpu(cmd->prp2);
> uint32_t nsid = le32_to_cpu(cmd->nsid);
>
> uint32_t trans_len;
> @@ -1047,16 +1339,13 @@ static uint16_t nvme_smart_info(NvmeCtrl *n, NvmeCmd *cmd, uint8_t rae,
> nvme_clear_events(n, NVME_AER_TYPE_SMART);
> }
>
> - return nvme_dma_read_prp(n, (uint8_t *) &smart + off, trans_len, prp1,
> - prp2, req);
> + return nvme_dma_read(n, (uint8_t *) &smart + off, trans_len, cmd, req);
> }
>
> static uint16_t nvme_fw_log_info(NvmeCtrl *n, NvmeCmd *cmd, uint32_t buf_len,
> uint64_t off, NvmeRequest *req)
> {
> uint32_t trans_len;
> - uint64_t prp1 = le64_to_cpu(cmd->prp1);
> - uint64_t prp2 = le64_to_cpu(cmd->prp2);
> NvmeFwSlotInfoLog fw_log;
>
> if (off > sizeof(fw_log)) {
> @@ -1067,8 +1356,7 @@ static uint16_t nvme_fw_log_info(NvmeCtrl *n, NvmeCmd *cmd, uint32_t buf_len,
>
> trans_len = MIN(sizeof(fw_log) - off, buf_len);
>
> - return nvme_dma_read_prp(n, (uint8_t *) &fw_log + off, trans_len, prp1,
> - prp2, req);
> + return nvme_dma_read(n, (uint8_t *) &fw_log + off, trans_len, cmd, req);
> }
>
> static uint16_t nvme_get_log(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
> @@ -1210,25 +1498,18 @@ static uint16_t nvme_create_cq(NvmeCtrl *n, NvmeCmd *cmd)
> return NVME_SUCCESS;
> }
>
> -static uint16_t nvme_identify_ctrl(NvmeCtrl *n, NvmeIdentify *c,
> - NvmeRequest *req)
> +static uint16_t nvme_identify_ctrl(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
> {
> - uint64_t prp1 = le64_to_cpu(c->prp1);
> - uint64_t prp2 = le64_to_cpu(c->prp2);
> -
> trace_nvme_identify_ctrl();
>
> - return nvme_dma_read_prp(n, (uint8_t *)&n->id_ctrl, sizeof(n->id_ctrl),
> - prp1, prp2, req);
> + return nvme_dma_read(n, (uint8_t *) &n->id_ctrl, sizeof(n->id_ctrl), cmd,
> + req);
> }
>
> -static uint16_t nvme_identify_ns(NvmeCtrl *n, NvmeIdentify *c,
> - NvmeRequest *req)
> +static uint16_t nvme_identify_ns(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
> {
> NvmeNamespace *ns;
> - uint32_t nsid = le32_to_cpu(c->nsid);
> - uint64_t prp1 = le64_to_cpu(c->prp1);
> - uint64_t prp2 = le64_to_cpu(c->prp2);
> + uint32_t nsid = le32_to_cpu(cmd->nsid);
>
> trace_nvme_identify_ns(nsid);
>
> @@ -1239,17 +1520,15 @@ static uint16_t nvme_identify_ns(NvmeCtrl *n, NvmeIdentify *c,
>
> ns = &n->namespaces[nsid - 1];
>
> - return nvme_dma_read_prp(n, (uint8_t *)&ns->id_ns, sizeof(ns->id_ns),
> - prp1, prp2, req);
> + return nvme_dma_read(n, (uint8_t *) &ns->id_ns, sizeof(ns->id_ns), cmd,
> + req);
> }
>
> -static uint16_t nvme_identify_ns_list(NvmeCtrl *n, NvmeIdentify *c,
> +static uint16_t nvme_identify_ns_list(NvmeCtrl *n, NvmeCmd *cmd,
> NvmeRequest *req)
> {
> static const int data_len = 4 * KiB;
> - 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);
> + uint32_t min_nsid = le32_to_cpu(cmd->nsid);
> uint32_t *list;
> uint16_t ret;
> int i, j = 0;
> @@ -1266,12 +1545,12 @@ static uint16_t nvme_identify_ns_list(NvmeCtrl *n, NvmeIdentify *c,
> break;
> }
> }
> - ret = nvme_dma_read_prp(n, (uint8_t *)list, data_len, prp1, prp2, req);
> + ret = nvme_dma_read(n, (uint8_t *) list, data_len, cmd, req);
> g_free(list);
> return ret;
> }
>
> -static uint16_t nvme_identify_ns_descr_list(NvmeCtrl *n, NvmeIdentify *c,
> +static uint16_t nvme_identify_ns_descr_list(NvmeCtrl *n, NvmeCmd *cmd,
> NvmeRequest *req)
> {
> static const int len = 4096;
> @@ -1283,9 +1562,7 @@ static uint16_t nvme_identify_ns_descr_list(NvmeCtrl *n, NvmeIdentify *c,
> uint8_t nid[16];
> };
>
> - uint32_t nsid = le32_to_cpu(c->nsid);
> - uint64_t prp1 = le64_to_cpu(c->prp1);
> - uint64_t prp2 = le64_to_cpu(c->prp2);
> + uint32_t nsid = le32_to_cpu(cmd->nsid);
>
> struct ns_descr *list;
> uint16_t ret;
> @@ -1302,7 +1579,7 @@ static uint16_t nvme_identify_ns_descr_list(NvmeCtrl *n, NvmeIdentify *c,
> list->nidl = 0x10;
> *(uint32_t *) &list->nid[12] = cpu_to_be32(nsid);
>
> - ret = nvme_dma_read_prp(n, (uint8_t *) list, len, prp1, prp2, req);
> + ret = nvme_dma_read(n, (uint8_t *) list, len, cmd, req);
> g_free(list);
> return ret;
> }
> @@ -1313,13 +1590,13 @@ static uint16_t nvme_identify(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
>
> switch (le32_to_cpu(c->cns)) {
> case 0x00:
> - return nvme_identify_ns(n, c, req);
> + return nvme_identify_ns(n, cmd, req);
> case 0x01:
> - return nvme_identify_ctrl(n, c, req);
> + return nvme_identify_ctrl(n, cmd, req);
> case 0x02:
> - return nvme_identify_ns_list(n, c, req);
> + return nvme_identify_ns_list(n, cmd, req);
> case 0x03:
> - return nvme_identify_ns_descr_list(n, c, req);
> + return nvme_identify_ns_descr_list(n, cmd, req);
> default:
> trace_nvme_err_invalid_identify_cns(le32_to_cpu(c->cns));
> return NVME_INVALID_FIELD | NVME_DNR;
> @@ -1381,13 +1658,10 @@ static inline uint64_t nvme_get_timestamp(const NvmeCtrl *n)
> static uint16_t nvme_get_feature_timestamp(NvmeCtrl *n, NvmeCmd *cmd,
> NvmeRequest *req)
> {
> - uint64_t prp1 = le64_to_cpu(cmd->prp1);
> - uint64_t prp2 = le64_to_cpu(cmd->prp2);
> -
> uint64_t timestamp = nvme_get_timestamp(n);
>
> - return nvme_dma_read_prp(n, (uint8_t *)×tamp, sizeof(timestamp),
> - prp1, prp2, req);
> + return nvme_dma_read(n, (uint8_t *)×tamp, sizeof(timestamp), cmd,
> + req);
> }
>
> static uint16_t nvme_get_feature(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
> @@ -1452,11 +1726,9 @@ static uint16_t nvme_set_feature_timestamp(NvmeCtrl *n, NvmeCmd *cmd,
> {
> uint16_t ret;
> uint64_t timestamp;
> - uint64_t prp1 = le64_to_cpu(cmd->prp1);
> - uint64_t prp2 = le64_to_cpu(cmd->prp2);
>
> - ret = nvme_dma_write_prp(n, (uint8_t *)×tamp,
> - sizeof(timestamp), prp1, prp2, req);
> + ret = nvme_dma_write(n, (uint8_t *)×tamp, sizeof(timestamp), cmd,
> + req);
> if (ret != NVME_SUCCESS) {
> return ret;
> }
> @@ -2241,6 +2513,8 @@ static void nvme_init_ctrl(NvmeCtrl *n)
> id->vwc = 1;
> }
>
> + id->sgls = cpu_to_le32(0x1);
> +
> strcpy((char *) id->subnqn, "nqn.2019-08.org.qemu:");
> pstrcat((char *) id->subnqn, sizeof(id->subnqn), n->params.serial);
>
> diff --git a/hw/block/trace-events b/hw/block/trace-events
> index c7e0a1849043..59d42a3b8c39 100644
> --- a/hw/block/trace-events
> +++ b/hw/block/trace-events
> @@ -34,6 +34,7 @@ nvme_irq_pin(void) "pulsing IRQ pin"
> nvme_irq_masked(void) "IRQ is masked"
> nvme_dma_read(uint64_t prp1, uint64_t prp2) "DMA read, prp1=0x%"PRIx64" prp2=0x%"PRIx64""
> nvme_map_prp(uint16_t cid, uint8_t opc, uint64_t trans_len, uint32_t len, uint64_t prp1, uint64_t prp2, int num_prps) "cid %"PRIu16" opc 0x%"PRIx8" trans_len %"PRIu64" len %"PRIu32" prp1 0x%"PRIx64" prp2 0x%"PRIx64" num_prps %d"
> +nvme_map_sgl(uint16_t cid, uint8_t typ, uint32_t nlb, uint64_t len) "cid %"PRIu16" type 0x%"PRIx8" nlb %"PRIu32" len %"PRIu64""
> nvme_req_register_aio(uint16_t cid, void *aio, const char *blkname, uint64_t offset, uint64_t count, const char *opc, void *req) "cid %"PRIu16" aio %p blk \"%s\" offset %"PRIu64" count %"PRIu64" opc \"%s\" req %p"
> nvme_aio_cb(uint16_t cid, void *aio, const char *blkname, uint64_t offset, const char *opc, void *req) "cid %"PRIu16" aio %p blk \"%s\" offset %"PRIu64" opc \"%s\" req %p"
> nvme_io_cmd(uint16_t cid, uint32_t nsid, uint16_t sqid, uint8_t opcode) "cid %"PRIu16" nsid %"PRIu32" sqid %"PRIu16" opc 0x%"PRIx8""
> @@ -82,6 +83,8 @@ nvme_mmio_shutdown_cleared(void) "shutdown bit cleared"
> nvme_err_mdts(uint16_t cid, size_t mdts, size_t len) "cid %"PRIu16" mdts %"PRIu64" len %"PRIu64""
> nvme_err_prinfo(uint16_t cid, uint16_t ctrl) "cid %"PRIu16" ctrl %"PRIu16""
> nvme_err_aio(uint16_t cid, void *aio, const char *blkname, uint64_t offset, const char *opc, void *req, uint16_t status) "cid %"PRIu16" aio %p blk \"%s\" offset %"PRIu64" opc \"%s\" req %p status 0x%"PRIx16""
> +nvme_err_invalid_sgl_descriptor(uint16_t cid, uint8_t typ) "cid %"PRIu16" type 0x%"PRIx8""
> +nvme_err_invalid_sgl_excess_length(uint16_t cid) "cid %"PRIu16""
> nvme_err_invalid_dma(void) "PRP/SGL is too small for transfer size"
> nvme_err_invalid_prplist_ent(uint64_t prplist) "PRP list entry is null or not page aligned: 0x%"PRIx64""
> nvme_err_invalid_prp2_align(uint64_t prp2) "PRP2 is not page aligned: 0x%"PRIx64""
> diff --git a/include/block/nvme.h b/include/block/nvme.h
> index d4990db4fdf8..ba0a9d4e328f 100644
> --- a/include/block/nvme.h
> +++ b/include/block/nvme.h
> @@ -205,15 +205,53 @@ enum NvmeCmbszMask {
> #define NVME_CMBSZ_GETSIZE(cmbsz) \
> (NVME_CMBSZ_SZ(cmbsz) * (1 << (12 + 4 * NVME_CMBSZ_SZU(cmbsz))))
>
> +enum NvmeSglDescriptorType {
> + SGL_DESCR_TYPE_DATA_BLOCK = 0x0,
> + SGL_DESCR_TYPE_BIT_BUCKET = 0x1,
> + SGL_DESCR_TYPE_SEGMENT = 0x2,
> + SGL_DESCR_TYPE_LAST_SEGMENT = 0x3,
> + SGL_DESCR_TYPE_KEYED_DATA_BLOCK = 0x4,
> +
> + SGL_DESCR_TYPE_VENDOR_SPECIFIC = 0xf,
> +};
> +
> +enum NvmeSglDescriptorSubtype {
> + SGL_DESCR_SUBTYPE_ADDRESS = 0x0,
> + SGL_DESCR_SUBTYPE_OFFSET = 0x1,
> +};
> +
> +typedef struct NvmeSglDescriptor {
> + uint64_t addr;
> + uint32_t len;
> + uint8_t rsvd[3];
> + uint8_t type;
> +} NvmeSglDescriptor;
> +
> +#define NVME_SGL_TYPE(type) (type >> 4)
> +
> +typedef union NvmeCmdDptr {
> + struct {
> + uint64_t prp1;
> + uint64_t prp2;
> + } prp;
> +
> + NvmeSglDescriptor sgl;
> +} NvmeCmdDptr;
> +
> +enum NvmePsdt {
> + PSDT_PRP = 0x0,
> + PSDT_SGL_MPTR_CONTIGUOUS = 0x1,
> + PSDT_SGL_MPTR_SGL = 0x2,
> +};
> +
> typedef struct NvmeCmd {
> uint8_t opcode;
> - uint8_t fuse;
> + uint8_t flags;
> uint16_t cid;
> uint32_t nsid;
> uint64_t res1;
> uint64_t mptr;
> - uint64_t prp1;
> - uint64_t prp2;
> + NvmeCmdDptr dptr;
> uint32_t cdw10;
> uint32_t cdw11;
> uint32_t cdw12;
> @@ -222,6 +260,9 @@ typedef struct NvmeCmd {
> uint32_t cdw15;
> } NvmeCmd;
>
> +#define NVME_CMD_FLAGS_FUSE(flags) (flags & 0x3)
> +#define NVME_CMD_FLAGS_PSDT(flags) ((flags >> 6) & 0x3)
Minor: This one is slightly misleading - as per the naming and it's usage:
the PSDT is a field name and as such does not imply using SGLs
and it is being used to verify if given command is actually using
SGLs.
BR
Beata
> +
> enum NvmeAdminCommands {
> NVME_ADM_CMD_DELETE_SQ = 0x00,
> NVME_ADM_CMD_CREATE_SQ = 0x01,
> @@ -427,6 +468,11 @@ enum NvmeStatusCodes {
> NVME_CMD_ABORT_MISSING_FUSE = 0x000a,
> NVME_INVALID_NSID = 0x000b,
> NVME_CMD_SEQ_ERROR = 0x000c,
> + NVME_INVALID_SGL_SEG_DESCRIPTOR = 0x000d,
> + NVME_INVALID_NUM_SGL_DESCRIPTORS = 0x000e,
> + NVME_DATA_SGL_LENGTH_INVALID = 0x000f,
> + NVME_METADATA_SGL_LENGTH_INVALID = 0x0010,
> + NVME_SGL_DESCRIPTOR_TYPE_INVALID = 0x0011,
> NVME_INVALID_USE_OF_CMB = 0x0012,
> NVME_LBA_RANGE = 0x0080,
> NVME_CAP_EXCEEDED = 0x0081,
> @@ -623,6 +669,16 @@ enum NvmeIdCtrlOncs {
> #define NVME_CTRL_CQES_MIN(cqes) ((cqes) & 0xf)
> #define NVME_CTRL_CQES_MAX(cqes) (((cqes) >> 4) & 0xf)
>
> +#define NVME_CTRL_SGLS_SUPPORTED(sgls) ((sgls) & 0x3)
> +#define NVME_CTRL_SGLS_SUPPORTED_NO_ALIGNMENT(sgls) ((sgls) & (0x1 << 0))
> +#define NVME_CTRL_SGLS_SUPPORTED_DWORD_ALIGNMENT(sgls) ((sgls) & (0x1 << 1))
> +#define NVME_CTRL_SGLS_KEYED(sgls) ((sgls) & (0x1 << 2))
> +#define NVME_CTRL_SGLS_BITBUCKET(sgls) ((sgls) & (0x1 << 16))
> +#define NVME_CTRL_SGLS_MPTR_CONTIGUOUS(sgls) ((sgls) & (0x1 << 17))
> +#define NVME_CTRL_SGLS_EXCESS_LENGTH(sgls) ((sgls) & (0x1 << 18))
> +#define NVME_CTRL_SGLS_MPTR_SGL(sgls) ((sgls) & (0x1 << 19))
> +#define NVME_CTRL_SGLS_ADDR_OFFSET(sgls) ((sgls) & (0x1 << 20))
> +
> typedef struct NvmeFeatureVal {
> uint32_t arbitration;
> uint32_t power_mgmt;
> --
> 2.23.0
>
>
^ permalink raw reply [flat|nested] 52+ messages in thread* Re: [PATCH v2 15/20] nvme: add support for scatter gather lists
2019-11-12 15:25 ` Beata Michalska
@ 2019-11-25 6:21 ` Klaus Birkelund
2019-11-25 14:10 ` Beata Michalska
0 siblings, 1 reply; 52+ messages in thread
From: Klaus Birkelund @ 2019-11-25 6:21 UTC (permalink / raw)
To: Beata Michalska
Cc: Kevin Wolf, qemu-block, qemu-devel, Max Reitz, Paul Durrant, Keith Busch
On Tue, Nov 12, 2019 at 03:25:18PM +0000, Beata Michalska wrote:
> Hi Klaus,
>
> On Tue, 15 Oct 2019 at 11:57, Klaus Jensen <its@irrelevant.dk> wrote:
> > +static uint16_t nvme_map_sgl(NvmeCtrl *n, QEMUSGList *qsg,
> > + NvmeSglDescriptor sgl, uint32_t len, NvmeRequest *req)
> > +{
> > + const int MAX_NSGLD = 256;
> > +
> > + NvmeSglDescriptor segment[MAX_NSGLD];
> > + uint64_t nsgld;
> > + uint16_t status;
> > + bool sgl_in_cmb = false;
> > + hwaddr addr = le64_to_cpu(sgl.addr);
> > +
> > + trace_nvme_map_sgl(req->cid, NVME_SGL_TYPE(sgl.type), req->nlb, len);
> > +
> > + pci_dma_sglist_init(qsg, &n->parent_obj, 1);
> > +
> > + /*
> > + * If the entire transfer can be described with a single data block it can
> > + * be mapped directly.
> > + */
> > + if (NVME_SGL_TYPE(sgl.type) == SGL_DESCR_TYPE_DATA_BLOCK) {
> > + status = nvme_map_sgl_data(n, qsg, &sgl, 1, &len, req);
> > + if (status) {
> > + goto unmap;
> > + }
> > +
> > + goto out;
> > + }
> > +
> > + /*
> > + * If the segment is located in the CMB, the submission queue of the
> > + * request must also reside there.
> > + */
> > + if (nvme_addr_is_cmb(n, addr)) {
> > + if (!nvme_addr_is_cmb(n, req->sq->dma_addr)) {
> > + return NVME_INVALID_USE_OF_CMB | NVME_DNR;
> > + }
> > +
> > + sgl_in_cmb = true;
> > + }
> > +
> > + while (NVME_SGL_TYPE(sgl.type) == SGL_DESCR_TYPE_SEGMENT) {
> > + bool addr_is_cmb;
> > +
> > + nsgld = le64_to_cpu(sgl.len) / sizeof(NvmeSglDescriptor);
> > +
> > + /* read the segment in chunks of 256 descriptors (4k) */
> > + while (nsgld > MAX_NSGLD) {
> > + nvme_addr_read(n, addr, segment, sizeof(segment));
> Is there any chance this will go outside the CMB?
>
Yes, there certainly was a chance of that. This has been fixed in a
general way for both nvme_map_sgl and nvme_map_sgl_data.
> > +
> > + status = nvme_map_sgl_data(n, qsg, segment, MAX_NSGLD, &len, req);
> > + if (status) {
> > + goto unmap;
> > + }
> > +
> > + nsgld -= MAX_NSGLD;
> > + addr += MAX_NSGLD * sizeof(NvmeSglDescriptor);
> > + }
> > +
> > + nvme_addr_read(n, addr, segment, nsgld * sizeof(NvmeSglDescriptor));
> > +
> > + sgl = segment[nsgld - 1];
> > + addr = le64_to_cpu(sgl.addr);
> > +
> > + /* an SGL is allowed to end with a Data Block in a regular Segment */
> > + if (NVME_SGL_TYPE(sgl.type) == SGL_DESCR_TYPE_DATA_BLOCK) {
> > + status = nvme_map_sgl_data(n, qsg, segment, nsgld, &len, req);
> > + if (status) {
> > + goto unmap;
> > + }
> > +
> > + goto out;
> > + }
> > +
> > + /* do not map last descriptor */
> > + status = nvme_map_sgl_data(n, qsg, segment, nsgld - 1, &len, req);
> > + if (status) {
> > + goto unmap;
> > + }
> > +
> > + /*
> > + * If the next segment is in the CMB, make sure that the sgl was
> > + * already located there.
> > + */
> > + addr_is_cmb = nvme_addr_is_cmb(n, addr);
> > + if ((sgl_in_cmb && !addr_is_cmb) || (!sgl_in_cmb && addr_is_cmb)) {
> > + status = NVME_INVALID_USE_OF_CMB | NVME_DNR;
> > + goto unmap;
> > + }
> > + }
> > +
> > + /*
> > + * If the segment did not end with a Data Block or a Segment descriptor, it
> > + * must be a Last Segment descriptor.
> > + */
> > + if (NVME_SGL_TYPE(sgl.type) != SGL_DESCR_TYPE_LAST_SEGMENT) {
> > + trace_nvme_err_invalid_sgl_descriptor(req->cid,
> > + NVME_SGL_TYPE(sgl.type));
> > + return NVME_SGL_DESCRIPTOR_TYPE_INVALID | NVME_DNR;
> Shouldn't we handle a case here that requires calling unmap ?
Woops. Fixed.
> > +static uint16_t nvme_dma_read_sgl(NvmeCtrl *n, uint8_t *ptr, uint32_t len,
> > + NvmeSglDescriptor sgl, NvmeCmd *cmd, NvmeRequest *req)
> > +{
> > + QEMUSGList qsg;
> > + uint16_t err = NVME_SUCCESS;
> > +
> Very minor: Mixing convention: status vs error
>
Fixed by proxy in another refactor.
> >
> > +#define NVME_CMD_FLAGS_FUSE(flags) (flags & 0x3)
> > +#define NVME_CMD_FLAGS_PSDT(flags) ((flags >> 6) & 0x3)
> Minor: This one is slightly misleading - as per the naming and it's usage:
> the PSDT is a field name and as such does not imply using SGLs
> and it is being used to verify if given command is actually using
> SGLs.
>
Ah, is this because I do
if (NVME_CMD_FLAGS_PSDT(cmd->flags)) {
in the code? That is, just checks for it not being zero? The value of
the PRP or SGL for Data Transfer (PSDT) field *does* specify if the
command uses SGLs or not. 0x0: PRPs, 0x1 SGL for data, 0x10: SGLs for
both data and metadata. Would you prefer the condition was more
explicit?
Thanks!
Klaus
^ permalink raw reply [flat|nested] 52+ messages in thread* Re: [PATCH v2 15/20] nvme: add support for scatter gather lists
2019-11-25 6:21 ` Klaus Birkelund
@ 2019-11-25 14:10 ` Beata Michalska
2019-11-26 8:34 ` Klaus Birkelund
0 siblings, 1 reply; 52+ messages in thread
From: Beata Michalska @ 2019-11-25 14:10 UTC (permalink / raw)
To: Klaus Birkelund
Cc: Kevin Wolf, qemu-block, qemu-devel, Max Reitz, Paul Durrant, Keith Busch
On Mon, 25 Nov 2019 at 06:21, Klaus Birkelund <its@irrelevant.dk> wrote:
>
> On Tue, Nov 12, 2019 at 03:25:18PM +0000, Beata Michalska wrote:
> > Hi Klaus,
> >
> > On Tue, 15 Oct 2019 at 11:57, Klaus Jensen <its@irrelevant.dk> wrote:
> > > +static uint16_t nvme_map_sgl(NvmeCtrl *n, QEMUSGList *qsg,
> > > + NvmeSglDescriptor sgl, uint32_t len, NvmeRequest *req)
> > > +{
> > > + const int MAX_NSGLD = 256;
> > > +
> > > + NvmeSglDescriptor segment[MAX_NSGLD];
> > > + uint64_t nsgld;
> > > + uint16_t status;
> > > + bool sgl_in_cmb = false;
> > > + hwaddr addr = le64_to_cpu(sgl.addr);
> > > +
> > > + trace_nvme_map_sgl(req->cid, NVME_SGL_TYPE(sgl.type), req->nlb, len);
> > > +
> > > + pci_dma_sglist_init(qsg, &n->parent_obj, 1);
> > > +
> > > + /*
> > > + * If the entire transfer can be described with a single data block it can
> > > + * be mapped directly.
> > > + */
> > > + if (NVME_SGL_TYPE(sgl.type) == SGL_DESCR_TYPE_DATA_BLOCK) {
> > > + status = nvme_map_sgl_data(n, qsg, &sgl, 1, &len, req);
> > > + if (status) {
> > > + goto unmap;
> > > + }
> > > +
> > > + goto out;
> > > + }
> > > +
> > > + /*
> > > + * If the segment is located in the CMB, the submission queue of the
> > > + * request must also reside there.
> > > + */
> > > + if (nvme_addr_is_cmb(n, addr)) {
> > > + if (!nvme_addr_is_cmb(n, req->sq->dma_addr)) {
> > > + return NVME_INVALID_USE_OF_CMB | NVME_DNR;
> > > + }
> > > +
> > > + sgl_in_cmb = true;
> > > + }
> > > +
> > > + while (NVME_SGL_TYPE(sgl.type) == SGL_DESCR_TYPE_SEGMENT) {
> > > + bool addr_is_cmb;
> > > +
> > > + nsgld = le64_to_cpu(sgl.len) / sizeof(NvmeSglDescriptor);
> > > +
> > > + /* read the segment in chunks of 256 descriptors (4k) */
> > > + while (nsgld > MAX_NSGLD) {
> > > + nvme_addr_read(n, addr, segment, sizeof(segment));
> > Is there any chance this will go outside the CMB?
> >
>
> Yes, there certainly was a chance of that. This has been fixed in a
> general way for both nvme_map_sgl and nvme_map_sgl_data.
>
> > > +
> > > + status = nvme_map_sgl_data(n, qsg, segment, MAX_NSGLD, &len, req);
> > > + if (status) {
> > > + goto unmap;
> > > + }
> > > +
> > > + nsgld -= MAX_NSGLD;
> > > + addr += MAX_NSGLD * sizeof(NvmeSglDescriptor);
> > > + }
> > > +
> > > + nvme_addr_read(n, addr, segment, nsgld * sizeof(NvmeSglDescriptor));
> > > +
> > > + sgl = segment[nsgld - 1];
> > > + addr = le64_to_cpu(sgl.addr);
> > > +
> > > + /* an SGL is allowed to end with a Data Block in a regular Segment */
> > > + if (NVME_SGL_TYPE(sgl.type) == SGL_DESCR_TYPE_DATA_BLOCK) {
> > > + status = nvme_map_sgl_data(n, qsg, segment, nsgld, &len, req);
> > > + if (status) {
> > > + goto unmap;
> > > + }
> > > +
> > > + goto out;
> > > + }
> > > +
> > > + /* do not map last descriptor */
> > > + status = nvme_map_sgl_data(n, qsg, segment, nsgld - 1, &len, req);
> > > + if (status) {
> > > + goto unmap;
> > > + }
> > > +
> > > + /*
> > > + * If the next segment is in the CMB, make sure that the sgl was
> > > + * already located there.
> > > + */
> > > + addr_is_cmb = nvme_addr_is_cmb(n, addr);
> > > + if ((sgl_in_cmb && !addr_is_cmb) || (!sgl_in_cmb && addr_is_cmb)) {
> > > + status = NVME_INVALID_USE_OF_CMB | NVME_DNR;
> > > + goto unmap;
> > > + }
> > > + }
> > > +
> > > + /*
> > > + * If the segment did not end with a Data Block or a Segment descriptor, it
> > > + * must be a Last Segment descriptor.
> > > + */
> > > + if (NVME_SGL_TYPE(sgl.type) != SGL_DESCR_TYPE_LAST_SEGMENT) {
> > > + trace_nvme_err_invalid_sgl_descriptor(req->cid,
> > > + NVME_SGL_TYPE(sgl.type));
> > > + return NVME_SGL_DESCRIPTOR_TYPE_INVALID | NVME_DNR;
> > Shouldn't we handle a case here that requires calling unmap ?
>
> Woops. Fixed.
>
> > > +static uint16_t nvme_dma_read_sgl(NvmeCtrl *n, uint8_t *ptr, uint32_t len,
> > > + NvmeSglDescriptor sgl, NvmeCmd *cmd, NvmeRequest *req)
> > > +{
> > > + QEMUSGList qsg;
> > > + uint16_t err = NVME_SUCCESS;
> > > +
> > Very minor: Mixing convention: status vs error
> >
>
> Fixed by proxy in another refactor.
>
> > >
> > > +#define NVME_CMD_FLAGS_FUSE(flags) (flags & 0x3)
> > > +#define NVME_CMD_FLAGS_PSDT(flags) ((flags >> 6) & 0x3)
> > Minor: This one is slightly misleading - as per the naming and it's usage:
> > the PSDT is a field name and as such does not imply using SGLs
> > and it is being used to verify if given command is actually using
> > SGLs.
> >
>
> Ah, is this because I do
>
> if (NVME_CMD_FLAGS_PSDT(cmd->flags)) {
>
> in the code? That is, just checks for it not being zero? The value of
> the PRP or SGL for Data Transfer (PSDT) field *does* specify if the
> command uses SGLs or not. 0x0: PRPs, 0x1 SGL for data, 0x10: SGLs for
> both data and metadata. Would you prefer the condition was more
> explicit?
>
Yeah, it is just not obvious( at least to me) without referencing the spec
that non-zero value implies SGL usage. Guess a comment would be helpful
but that is not major.
Thanks,
BR
Beata
>
> Thanks!
> Klaus
^ permalink raw reply [flat|nested] 52+ messages in thread* Re: [PATCH v2 15/20] nvme: add support for scatter gather lists
2019-11-25 14:10 ` Beata Michalska
@ 2019-11-26 8:34 ` Klaus Birkelund
0 siblings, 0 replies; 52+ messages in thread
From: Klaus Birkelund @ 2019-11-26 8:34 UTC (permalink / raw)
To: Beata Michalska
Cc: Kevin Wolf, qemu-block, qemu-devel, Max Reitz, Paul Durrant, Keith Busch
On Mon, Nov 25, 2019 at 02:10:37PM +0000, Beata Michalska wrote:
> On Mon, 25 Nov 2019 at 06:21, Klaus Birkelund <its@irrelevant.dk> wrote:
> >
> > On Tue, Nov 12, 2019 at 03:25:18PM +0000, Beata Michalska wrote:
> > > Hi Klaus,
> > >
> > > On Tue, 15 Oct 2019 at 11:57, Klaus Jensen <its@irrelevant.dk> wrote:
> > > >
> > > > +#define NVME_CMD_FLAGS_FUSE(flags) (flags & 0x3)
> > > > +#define NVME_CMD_FLAGS_PSDT(flags) ((flags >> 6) & 0x3)
> > > Minor: This one is slightly misleading - as per the naming and it's usage:
> > > the PSDT is a field name and as such does not imply using SGLs
> > > and it is being used to verify if given command is actually using
> > > SGLs.
> > >
> >
> > Ah, is this because I do
> >
> > if (NVME_CMD_FLAGS_PSDT(cmd->flags)) {
> >
> > in the code? That is, just checks for it not being zero? The value of
> > the PRP or SGL for Data Transfer (PSDT) field *does* specify if the
> > command uses SGLs or not. 0x0: PRPs, 0x1 SGL for data, 0x10: SGLs for
> > both data and metadata. Would you prefer the condition was more
> > explicit?
> >
> Yeah, it is just not obvious( at least to me) without referencing the spec
> that non-zero value implies SGL usage. Guess a comment would be helpful
> but that is not major.
>
Nah. Thats a good point. I have changed it to use a switch on the value.
This technically also fixes a bug because the above would accept 0x3 as
a valid value and interpret it as SGL use.
Klaus
^ permalink raw reply [flat|nested] 52+ messages in thread
* [PATCH v2 16/20] nvme: support multiple namespaces
2019-10-15 10:38 [PATCH v2 00/20] nvme: support NVMe v1.3d, SGLs and multiple namespaces Klaus Jensen
` (14 preceding siblings ...)
2019-10-15 10:38 ` [PATCH v2 15/20] nvme: add support for scatter gather lists Klaus Jensen
@ 2019-10-15 10:38 ` Klaus Jensen
2019-10-15 10:38 ` [PATCH v2 17/20] nvme: bump controller pci device id Klaus Jensen
` (7 subsequent siblings)
23 siblings, 0 replies; 52+ messages in thread
From: Klaus Jensen @ 2019-10-15 10:38 UTC (permalink / raw)
To: qemu-block
Cc: Kevin Wolf, Fam Zheng, Javier Gonzalez, qemu-devel, Max Reitz,
Keith Busch, Paul Durrant, Stephen Bates
This adds support for multiple namespaces by introducing a new 'nvme-ns'
device model. The nvme device creates a bus named from the device name
('id'). The nvme-ns devices then connect to this and registers
themselves with the nvme device.
This changes how an nvme device is created. Example with two namespaces:
-drive file=nvme0n1.img,if=none,id=disk1
-drive file=nvme0n2.img,if=none,id=disk2
-device nvme,serial=deadbeef,id=nvme0
-device nvme-ns,drive=disk1,bus=nvme0,nsid=1
-device nvme-ns,drive=disk2,bus=nvme0,nsid=2
The drive property is kept on the nvme device to keep the change
backward compatible, but the property is now optional. Specifying a
drive for the nvme device will always create the namespace with nsid 1.
Signed-off-by: Klaus Jensen <klaus.jensen@cnexlabs.com>
Signed-off-by: Klaus Jensen <k.jensen@samsung.com>
---
hw/block/Makefile.objs | 2 +-
hw/block/nvme-ns.c | 139 +++++++++++++++++++++++++++
hw/block/nvme-ns.h | 58 +++++++++++
hw/block/nvme.c | 212 +++++++++++++++++++++++++----------------
hw/block/nvme.h | 51 +++++-----
hw/block/trace-events | 5 +-
6 files changed, 352 insertions(+), 115 deletions(-)
create mode 100644 hw/block/nvme-ns.c
create mode 100644 hw/block/nvme-ns.h
diff --git a/hw/block/Makefile.objs b/hw/block/Makefile.objs
index f5f643f0cc06..d44a2f4b780d 100644
--- a/hw/block/Makefile.objs
+++ b/hw/block/Makefile.objs
@@ -7,7 +7,7 @@ common-obj-$(CONFIG_PFLASH_CFI02) += pflash_cfi02.o
common-obj-$(CONFIG_XEN) += xen-block.o
common-obj-$(CONFIG_ECC) += ecc.o
common-obj-$(CONFIG_ONENAND) += onenand.o
-common-obj-$(CONFIG_NVME_PCI) += nvme.o
+common-obj-$(CONFIG_NVME_PCI) += nvme.o nvme-ns.o
obj-$(CONFIG_SH4) += tc58128.o
diff --git a/hw/block/nvme-ns.c b/hw/block/nvme-ns.c
new file mode 100644
index 000000000000..aa76bb63ef45
--- /dev/null
+++ b/hw/block/nvme-ns.c
@@ -0,0 +1,139 @@
+#include "qemu/osdep.h"
+#include "qemu/units.h"
+#include "qemu/cutils.h"
+#include "qemu/log.h"
+#include "hw/block/block.h"
+#include "hw/pci/msix.h"
+#include "sysemu/sysemu.h"
+#include "sysemu/block-backend.h"
+#include "qapi/error.h"
+
+#include "hw/qdev-properties.h"
+#include "hw/qdev-core.h"
+
+#include "nvme.h"
+#include "nvme-ns.h"
+
+static int nvme_ns_init(NvmeNamespace *ns)
+{
+ NvmeIdNs *id_ns = &ns->id_ns;
+
+ id_ns->lbaf[0].ds = BDRV_SECTOR_BITS;
+ id_ns->nuse = id_ns->ncap = id_ns->nsze =
+ cpu_to_le64(nvme_ns_nlbas(ns));
+
+ return 0;
+}
+
+static int nvme_ns_init_blk(NvmeNamespace *ns, NvmeIdCtrl *id, Error **errp)
+{
+ blkconf_blocksizes(&ns->conf);
+
+ if (!blkconf_apply_backend_options(&ns->conf,
+ blk_is_read_only(ns->conf.blk), false, errp)) {
+ return 1;
+ }
+
+ ns->size = blk_getlength(ns->conf.blk);
+ if (ns->size < 0) {
+ error_setg_errno(errp, -ns->size, "blk_getlength");
+ return 1;
+ }
+
+ if (!blk_enable_write_cache(ns->conf.blk)) {
+ id->vwc = 0;
+ }
+
+ return 0;
+}
+
+static int nvme_ns_check_constraints(NvmeNamespace *ns, Error **errp)
+{
+ if (!ns->conf.blk) {
+ error_setg(errp, "block backend not configured");
+ return 1;
+ }
+
+ return 0;
+}
+
+int nvme_ns_setup(NvmeCtrl *n, NvmeNamespace *ns, Error **errp)
+{
+ Error *local_err = NULL;
+
+ if (nvme_ns_check_constraints(ns, &local_err)) {
+ error_propagate_prepend(errp, local_err,
+ "nvme_ns_check_constraints: ");
+ return 1;
+ }
+
+ if (nvme_ns_init_blk(ns, &n->id_ctrl, &local_err)) {
+ error_propagate_prepend(errp, local_err, "nvme_ns_init_blk: ");
+ return 1;
+ }
+
+ nvme_ns_init(ns);
+ if (nvme_register_namespace(n, ns, &local_err)) {
+ error_propagate_prepend(errp, local_err, "nvme_register_namespace: ");
+ return 1;
+ }
+
+ return 0;
+}
+
+static void nvme_ns_realize(DeviceState *dev, Error **errp)
+{
+ NvmeNamespace *ns = NVME_NS(dev);
+ BusState *s = qdev_get_parent_bus(dev);
+ NvmeCtrl *n = NVME(s->parent);
+ Error *local_err = NULL;
+
+ if (nvme_ns_setup(n, ns, &local_err)) {
+ error_propagate_prepend(errp, local_err, "nvme_ns_setup: ");
+ return;
+ }
+}
+
+static Property nvme_ns_props[] = {
+ DEFINE_BLOCK_PROPERTIES(NvmeNamespace, conf),
+ DEFINE_NVME_NS_PROPERTIES(NvmeNamespace, params),
+ DEFINE_PROP_END_OF_LIST(),
+};
+
+static void nvme_ns_class_init(ObjectClass *oc, void *data)
+{
+ DeviceClass *dc = DEVICE_CLASS(oc);
+
+ set_bit(DEVICE_CATEGORY_STORAGE, dc->categories);
+
+ dc->bus_type = TYPE_NVME_BUS;
+ dc->realize = nvme_ns_realize;
+ dc->props = nvme_ns_props;
+ dc->desc = "virtual nvme namespace";
+}
+
+static void nvme_ns_instance_init(Object *obj)
+{
+ NvmeNamespace *ns = NVME_NS(obj);
+ char *bootindex = g_strdup_printf("/namespace@%d,0", ns->params.nsid);
+
+ device_add_bootindex_property(obj, &ns->conf.bootindex, "bootindex",
+ bootindex, DEVICE(obj), &error_abort);
+
+ g_free(bootindex);
+}
+
+static const TypeInfo nvme_ns_info = {
+ .name = TYPE_NVME_NS,
+ .parent = TYPE_DEVICE,
+ .class_init = nvme_ns_class_init,
+ .instance_size = sizeof(NvmeNamespace),
+ .instance_init = nvme_ns_instance_init,
+};
+
+static void nvme_ns_register_types(void)
+{
+ type_register_static(&nvme_ns_info);
+}
+
+type_init(nvme_ns_register_types)
diff --git a/hw/block/nvme-ns.h b/hw/block/nvme-ns.h
new file mode 100644
index 000000000000..64dd054cf6a9
--- /dev/null
+++ b/hw/block/nvme-ns.h
@@ -0,0 +1,58 @@
+#ifndef NVME_NS_H
+#define NVME_NS_H
+
+#define TYPE_NVME_NS "nvme-ns"
+#define NVME_NS(obj) \
+ OBJECT_CHECK(NvmeNamespace, (obj), TYPE_NVME_NS)
+
+#define DEFINE_NVME_NS_PROPERTIES(_state, _props) \
+ DEFINE_PROP_UINT32("nsid", _state, _props.nsid, 0)
+
+typedef struct NvmeNamespaceParams {
+ uint32_t nsid;
+} NvmeNamespaceParams;
+
+typedef struct NvmeNamespace {
+ DeviceState parent_obj;
+ BlockConf conf;
+ int64_t size;
+
+ NvmeIdNs id_ns;
+ NvmeNamespaceParams params;
+} NvmeNamespace;
+
+static inline uint32_t nvme_nsid(NvmeNamespace *ns)
+{
+ if (ns) {
+ return ns->params.nsid;
+ }
+
+ return -1;
+}
+
+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;
+}
+
+static inline size_t nvme_ns_lbads_bytes(NvmeNamespace *ns)
+{
+ return 1 << nvme_ns_lbads(ns);
+}
+
+static inline uint64_t nvme_ns_nlbas(NvmeNamespace *ns)
+{
+ return ns->size >> nvme_ns_lbads(ns);
+}
+
+typedef struct NvmeCtrl NvmeCtrl;
+
+int nvme_ns_setup(NvmeCtrl *n, NvmeNamespace *ns, Error **errp);
+
+#endif /* NVME_NS_H */
diff --git a/hw/block/nvme.c b/hw/block/nvme.c
index 0a5cd079df9a..a23e9bc4e5ef 100644
--- a/hw/block/nvme.c
+++ b/hw/block/nvme.c
@@ -17,7 +17,8 @@
/**
* Usage: add options:
* -drive file=<file>,if=none,id=<drive_id>
- * -device nvme,drive=<drive_id>,serial=<serial>,id=<id[optional]>
+ * -device nvme,serial=<serial>,id=nvme0
+ * -device nvme-ns,drive=<drive_id>,bus=nvme0,nsid=1
*
* Advanced optional options:
*
@@ -31,6 +32,7 @@
#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"
@@ -46,6 +48,7 @@
#include "qemu/cutils.h"
#include "trace.h"
#include "nvme.h"
+#include "nvme-ns.h"
#define NVME_MAX_QS PCI_MSIX_FLAGS_QSIZE
#define NVME_TEMPERATURE 0x143
@@ -882,11 +885,12 @@ static void nvme_clear_events(NvmeCtrl *n, uint8_t event_type)
static void nvme_rw_cb(NvmeRequest *req, void *opaque)
{
+ NvmeNamespace *ns = req->ns;
NvmeSQueue *sq = req->sq;
NvmeCtrl *n = sq->ctrl;
NvmeCQueue *cq = n->cq[sq->cqid];
- trace_nvme_rw_cb(req->cid, req->cmd.nsid);
+ trace_nvme_rw_cb(req->cid, nvme_nsid(ns));
nvme_enqueue_req_completion(cq, req);
}
@@ -919,6 +923,7 @@ static void nvme_aio_cb(void *opaque, int ret)
block_acct_failed(stats, acct);
if (req) {
+ NvmeNamespace *ns = req->ns;
NvmeRwCmd *rw = (NvmeRwCmd *) &req->cmd;
NvmeSQueue *sq = req->sq;
NvmeCtrl *n = sq->ctrl;
@@ -941,7 +946,7 @@ static void nvme_aio_cb(void *opaque, int ret)
aio->offset, nvme_aio_opc_str(aio), req, status);
nvme_set_error_page(n, sq->sqid, cpu_to_le16(req->cid), status,
- offsetof(NvmeRwCmd, slba), rw->slba, 1);
+ offsetof(NvmeRwCmd, slba), rw->slba, nvme_nsid(ns));
error_setg_errno(&local_err, -ret, "aio failed");
error_report_err(local_err);
@@ -1007,7 +1012,7 @@ static inline uint16_t nvme_check_bounds(NvmeCtrl *n, NvmeRequest *req)
uint64_t nsze = le64_to_cpu(ns->id_ns.nsze);
if (unlikely((req->slba + req->nlb) > nsze)) {
- block_acct_invalid(blk_get_stats(n->conf.blk),
+ block_acct_invalid(blk_get_stats(ns->conf.blk),
nvme_req_is_write(req) ? BLOCK_ACCT_WRITE : BLOCK_ACCT_READ);
trace_nvme_err_invalid_lba_range(req->slba, req->nlb, nsze);
return NVME_LBA_RANGE | NVME_DNR;
@@ -1042,7 +1047,9 @@ static uint16_t nvme_check_rw(NvmeCtrl *n, NvmeRequest *req)
static uint16_t nvme_flush(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
{
- NvmeAIO *aio = nvme_aio_new(n->conf.blk, 0x0, NULL, req, NULL);
+ NvmeNamespace *ns = req->ns;
+
+ NvmeAIO *aio = nvme_aio_new(ns->conf.blk, 0x0, NULL, req, NULL);
nvme_req_register_aio(req, aio, NVME_AIO_OPC_FLUSH);
nvme_aio(aio);
@@ -1064,19 +1071,18 @@ static uint16_t nvme_write_zeros(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
req->slba = le64_to_cpu(rw->slba);
req->nlb = le16_to_cpu(rw->nlb) + 1;
- trace_nvme_write_zeros(req->cid, le32_to_cpu(cmd->nsid), req->slba,
- req->nlb);
+ trace_nvme_write_zeros(req->cid, nvme_nsid(ns), req->slba, req->nlb);
status = nvme_check_bounds(n, req);
if (unlikely(status)) {
- block_acct_invalid(blk_get_stats(n->conf.blk), BLOCK_ACCT_WRITE);
+ block_acct_invalid(blk_get_stats(ns->conf.blk), BLOCK_ACCT_WRITE);
return status;
}
offset = req->slba << nvme_ns_lbads(ns);
count = req->nlb << nvme_ns_lbads(ns);
- aio = nvme_aio_new(n->conf.blk, offset, NULL, req, NULL);
+ aio = nvme_aio_new(ns->conf.blk, offset, NULL, req, NULL);
aio->iov.size = count;
@@ -1098,22 +1104,23 @@ static uint16_t nvme_rw(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
req->nlb = le16_to_cpu(rw->nlb) + 1;
req->slba = le64_to_cpu(rw->slba);
- trace_nvme_rw(nvme_req_is_write(req) ? "write" : "read", req->nlb,
- req->nlb << nvme_ns_lbads(req->ns), req->slba);
+ trace_nvme_rw(req->cid, nvme_req_is_write(req) ? "write" : "read",
+ nvme_nsid(ns), req->nlb, req->nlb << nvme_ns_lbads(ns),
+ req->slba);
status = nvme_check_rw(n, req);
if (status) {
- block_acct_invalid(blk_get_stats(n->conf.blk), acct);
+ block_acct_invalid(blk_get_stats(ns->conf.blk), acct);
return status;
}
status = nvme_map(n, cmd, req);
if (status) {
- block_acct_invalid(blk_get_stats(n->conf.blk), acct);
+ block_acct_invalid(blk_get_stats(ns->conf.blk), acct);
return status;
}
- nvme_rw_aio(n->conf.blk, req->slba << nvme_ns_lbads(ns), &req->qsg, req);
+ nvme_rw_aio(ns->conf.blk, req->slba << nvme_ns_lbads(ns), &req->qsg, req);
nvme_req_set_cb(req, nvme_rw_cb, NULL);
return NVME_NO_COMPLETE;
@@ -1125,13 +1132,13 @@ static uint16_t nvme_io_cmd(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
trace_nvme_io_cmd(req->cid, nsid, le16_to_cpu(req->sq->sqid), cmd->opcode);
- if (unlikely(nsid == 0 || nsid > n->num_namespaces)) {
+ req->ns = nvme_ns(n, nsid);
+
+ if (unlikely(!req->ns)) {
trace_nvme_err_invalid_ns(nsid, n->num_namespaces);
return NVME_INVALID_NSID | NVME_DNR;
}
- req->ns = &n->namespaces[nsid - 1];
-
switch (cmd->opcode) {
case NVME_CMD_FLUSH:
return nvme_flush(n, cmd, req);
@@ -1296,19 +1303,25 @@ static uint16_t nvme_smart_info(NvmeCtrl *n, NvmeCmd *cmd, uint8_t rae,
uint64_t units_read = 0, units_written = 0, read_commands = 0,
write_commands = 0;
NvmeSmartLog smart;
- BlockAcctStats *s;
- if (!nsid || (nsid != 0xffffffff && nsid > n->num_namespaces)) {
+ if (!nsid || (nsid != 0xffffffff && !nvme_ns(n, nsid))) {
trace_nvme_err_invalid_ns(nsid, n->num_namespaces);
return NVME_INVALID_NSID | NVME_DNR;
}
- s = blk_get_stats(n->conf.blk);
+ for (int i = 1; i <= n->num_namespaces; i++) {
+ NvmeNamespace *ns = nvme_ns(n, i);
+ if (!ns) {
+ continue;
+ }
- units_read = s->nr_bytes[BLOCK_ACCT_READ] >> BDRV_SECTOR_BITS;
- units_written = s->nr_bytes[BLOCK_ACCT_WRITE] >> BDRV_SECTOR_BITS;
- read_commands = s->nr_ops[BLOCK_ACCT_READ];
- write_commands = s->nr_ops[BLOCK_ACCT_WRITE];
+ BlockAcctStats *s = blk_get_stats(ns->conf.blk);
+
+ units_read += s->nr_bytes[BLOCK_ACCT_READ] >> BDRV_SECTOR_BITS;
+ units_written += s->nr_bytes[BLOCK_ACCT_WRITE] >> BDRV_SECTOR_BITS;
+ read_commands += s->nr_ops[BLOCK_ACCT_READ];
+ write_commands += s->nr_ops[BLOCK_ACCT_WRITE];
+ }
if (off > sizeof(smart)) {
return NVME_INVALID_FIELD | NVME_DNR;
@@ -1508,18 +1521,16 @@ static uint16_t nvme_identify_ctrl(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
static uint16_t nvme_identify_ns(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
{
- NvmeNamespace *ns;
uint32_t nsid = le32_to_cpu(cmd->nsid);
+ NvmeNamespace *ns = nvme_ns(n, nsid);
trace_nvme_identify_ns(nsid);
- if (unlikely(nsid == 0 || nsid > n->num_namespaces)) {
+ if (unlikely(!ns)) {
trace_nvme_err_invalid_ns(nsid, n->num_namespaces);
return NVME_INVALID_NSID | NVME_DNR;
}
- ns = &n->namespaces[nsid - 1];
-
return nvme_dma_read(n, (uint8_t *) &ns->id_ns, sizeof(ns->id_ns), cmd,
req);
}
@@ -1536,11 +1547,11 @@ static uint16_t nvme_identify_ns_list(NvmeCtrl *n, NvmeCmd *cmd,
trace_nvme_identify_ns_list(min_nsid);
list = g_malloc0(data_len);
- for (i = 0; i < n->num_namespaces; i++) {
- if (i < min_nsid) {
+ for (i = 1; i <= n->num_namespaces; i++) {
+ if (i <= min_nsid || !nvme_ns(n, i)) {
continue;
}
- list[j++] = cpu_to_le32(i + 1);
+ list[j++] = cpu_to_le32(i);
if (j == data_len / sizeof(uint32_t)) {
break;
}
@@ -1569,7 +1580,7 @@ static uint16_t nvme_identify_ns_descr_list(NvmeCtrl *n, NvmeCmd *cmd,
trace_nvme_identify_ns_descr_list(nsid);
- if (unlikely(nsid == 0 || nsid > n->num_namespaces)) {
+ if (unlikely(!nvme_ns(n, nsid))) {
trace_nvme_err_invalid_ns(nsid, n->num_namespaces);
return NVME_INVALID_NSID | NVME_DNR;
}
@@ -1666,9 +1677,11 @@ static uint16_t nvme_get_feature_timestamp(NvmeCtrl *n, NvmeCmd *cmd,
static uint16_t nvme_get_feature(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
{
+ NvmeNamespace *ns;
+
uint32_t dw10 = le32_to_cpu(cmd->cdw10);
uint32_t dw11 = le32_to_cpu(cmd->cdw11);
- uint32_t result;
+ uint32_t result, nsid;
trace_nvme_getfeat(dw10);
@@ -1686,7 +1699,15 @@ static uint16_t nvme_get_feature(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
result = cpu_to_le32(n->features.err_rec);
break;
case NVME_VOLATILE_WRITE_CACHE:
- result = blk_enable_write_cache(n->conf.blk);
+ nsid = le32_to_cpu(req->cmd.nsid);
+ ns = nvme_ns(n, nsid);
+
+ if (unlikely(!ns)) {
+ trace_nvme_err_invalid_ns(nsid, n->num_namespaces);
+ return NVME_INVALID_NSID | NVME_DNR;
+ }
+
+ result = blk_enable_write_cache(ns->conf.blk);
trace_nvme_getfeat_vwcache(result ? "enabled" : "disabled");
break;
case NVME_NUMBER_OF_QUEUES:
@@ -1740,8 +1761,11 @@ static uint16_t nvme_set_feature_timestamp(NvmeCtrl *n, NvmeCmd *cmd,
static uint16_t nvme_set_feature(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
{
+ NvmeNamespace *ns;
+
uint32_t dw10 = le32_to_cpu(cmd->cdw10);
uint32_t dw11 = le32_to_cpu(cmd->cdw11);
+ uint32_t nsid;
trace_nvme_setfeat(dw10, dw11);
@@ -1757,7 +1781,15 @@ static uint16_t nvme_set_feature(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
break;
case NVME_VOLATILE_WRITE_CACHE:
- blk_set_enable_write_cache(n->conf.blk, dw11 & 1);
+ nsid = le32_to_cpu(req->cmd.nsid);
+ ns = nvme_ns(n, nsid);
+
+ if (unlikely(!ns)) {
+ trace_nvme_err_invalid_ns(nsid, n->num_namespaces);
+ return NVME_INVALID_NSID | NVME_DNR;
+ }
+
+ blk_set_enable_write_cache(ns->conf.blk, dw11 & 1);
break;
case NVME_NUMBER_OF_QUEUES:
if (n->qs_created > 2) {
@@ -1932,9 +1964,17 @@ static void nvme_process_sq(void *opaque)
static void nvme_clear_ctrl(NvmeCtrl *n)
{
+ NvmeNamespace *ns;
int i;
- blk_drain(n->conf.blk);
+ for (i = 1; i <= n->num_namespaces; i++) {
+ ns = nvme_ns(n, i);
+ if (!ns) {
+ continue;
+ }
+
+ blk_drain(ns->conf.blk);
+ }
for (i = 0; i < n->params.num_queues; i++) {
if (n->sq[i] != NULL) {
@@ -1961,7 +2001,15 @@ static void nvme_clear_ctrl(NvmeCtrl *n)
n->outstanding_aers = 0;
- blk_flush(n->conf.blk);
+ for (i = 1; i <= n->num_namespaces; i++) {
+ ns = nvme_ns(n, i);
+ if (!ns) {
+ continue;
+ }
+
+ blk_flush(ns->conf.blk);
+ }
+
n->bar.cc = 0;
}
@@ -2382,8 +2430,8 @@ static int nvme_check_constraints(NvmeCtrl *n, Error **errp)
{
NvmeParams *params = &n->params;
- if (!n->conf.blk) {
- error_setg(errp, "nvme: block backend not configured");
+ if (!n->namespace.conf.blk && !n->parent_obj.qdev.id) {
+ error_setg(errp, "nvme: invalid 'id' parameter");
return 1;
}
@@ -2400,22 +2448,10 @@ static int nvme_check_constraints(NvmeCtrl *n, Error **errp)
return 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;
-}
-
static void nvme_init_state(NvmeCtrl *n)
{
- n->num_namespaces = 1;
+ n->num_namespaces = 0;
n->reg_size = pow2ceil(0x1004 + 2 * (n->params.num_queues + 1) * 4);
- 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->elpes = g_new0(NvmeErrorLog, n->params.elpe + 1);
@@ -2507,12 +2543,7 @@ static void nvme_init_ctrl(NvmeCtrl *n)
id->cqes = (0x4 << 4) | 0x4;
id->nn = cpu_to_le32(n->num_namespaces);
id->oncs = cpu_to_le16(NVME_ONCS_WRITE_ZEROS | NVME_ONCS_TIMESTAMP);
-
-
- if (blk_enable_write_cache(n->conf.blk)) {
- id->vwc = 1;
- }
-
+ id->vwc = 1;
id->sgls = cpu_to_le32(0x1);
strcpy((char *) id->subnqn, "nqn.2019-08.org.qemu:");
@@ -2533,22 +2564,25 @@ static void nvme_init_ctrl(NvmeCtrl *n)
n->bar.intmc = n->bar.intms = 0;
}
-static int nvme_init_namespace(NvmeCtrl *n, NvmeNamespace *ns, Error **errp)
+int nvme_register_namespace(NvmeCtrl *n, NvmeNamespace *ns, Error **errp)
{
- int64_t bs_size;
- NvmeIdNs *id_ns = &ns->id_ns;
+ uint32_t nsid = nvme_nsid(ns);
+
+ if (nsid == 0 || nsid > NVME_MAX_NAMESPACES) {
+ error_setg(errp, "invalid nsid");
+ return 1;
+ }
- bs_size = blk_getlength(n->conf.blk);
- if (bs_size < 0) {
- error_setg_errno(errp, -bs_size, "blk_getlength");
+ if (n->namespaces[nsid - 1]) {
+ error_setg(errp, "nsid must be unique");
return 1;
}
- id_ns->lbaf[0].ds = BDRV_SECTOR_BITS;
- n->ns_size = bs_size;
+ trace_nvme_register_namespace(nsid);
- id_ns->ncap = id_ns->nuse = id_ns->nsze =
- cpu_to_le64(nvme_ns_nlbas(n, ns));
+ n->namespaces[nsid - 1] = ns;
+ n->num_namespaces = MAX(n->num_namespaces, nsid);
+ n->id_ctrl.nn = cpu_to_le32(n->num_namespaces);
return 0;
}
@@ -2556,30 +2590,31 @@ static int nvme_init_namespace(NvmeCtrl *n, NvmeNamespace *ns, Error **errp)
static void nvme_realize(PCIDevice *pci_dev, Error **errp)
{
NvmeCtrl *n = NVME(pci_dev);
+ NvmeNamespace *ns;
Error *local_err = NULL;
- int i;
if (nvme_check_constraints(n, &local_err)) {
error_propagate_prepend(errp, local_err, "nvme_check_constraints: ");
return;
}
+ qbus_create_inplace(&n->bus, sizeof(NvmeBus), TYPE_NVME_BUS,
+ &pci_dev->qdev, n->parent_obj.qdev.id);
+
nvme_init_state(n);
+ nvme_init_pci(n, pci_dev);
+ nvme_init_ctrl(n);
- if (nvme_init_blk(n, &local_err)) {
- error_propagate_prepend(errp, local_err, "nvme_init_blk: ");
- return;
- }
+ /* setup a namespace if the controller drive property was given */
+ if (n->namespace.conf.blk) {
+ ns = &n->namespace;
+ ns->params.nsid = 1;
- for (i = 0; i < n->num_namespaces; i++) {
- if (nvme_init_namespace(n, &n->namespaces[i], &local_err)) {
- error_propagate_prepend(errp, local_err, "nvme_init_namespace: ");
+ if (nvme_ns_setup(n, ns, &local_err)) {
+ error_propagate_prepend(errp, local_err, "nvme_ns_setup: ");
return;
}
}
-
- nvme_init_pci(n, pci_dev);
- nvme_init_ctrl(n);
}
static void nvme_exit(PCIDevice *pci_dev)
@@ -2601,7 +2636,7 @@ static void nvme_exit(PCIDevice *pci_dev)
}
static Property nvme_props[] = {
- DEFINE_BLOCK_PROPERTIES(NvmeCtrl, conf),
+ DEFINE_BLOCK_PROPERTIES(NvmeCtrl, namespace.conf),
DEFINE_NVME_PROPERTIES(NvmeCtrl, params),
DEFINE_PROP_END_OF_LIST(),
};
@@ -2633,26 +2668,35 @@ static void nvme_instance_init(Object *obj)
{
NvmeCtrl *s = NVME(obj);
- device_add_bootindex_property(obj, &s->conf.bootindex,
- "bootindex", "/namespace@1,0",
- DEVICE(obj), &error_abort);
+ if (s->namespace.conf.blk) {
+ device_add_bootindex_property(obj, &s->namespace.conf.bootindex,
+ "bootindex", "/namespace@1,0",
+ DEVICE(obj), &error_abort);
+ }
}
static const TypeInfo nvme_info = {
.name = TYPE_NVME,
.parent = TYPE_PCI_DEVICE,
.instance_size = sizeof(NvmeCtrl),
- .class_init = nvme_class_init,
.instance_init = nvme_instance_init,
+ .class_init = nvme_class_init,
.interfaces = (InterfaceInfo[]) {
{ INTERFACE_PCIE_DEVICE },
{ }
},
};
+static const TypeInfo nvme_bus_info = {
+ .name = TYPE_NVME_BUS,
+ .parent = TYPE_BUS,
+ .instance_size = sizeof(NvmeBus),
+};
+
static void nvme_register_types(void)
{
type_register_static(&nvme_info);
+ type_register_static(&nvme_bus_info);
}
type_init(nvme_register_types)
diff --git a/hw/block/nvme.h b/hw/block/nvme.h
index 2f6706899de1..c7da74625bc9 100644
--- a/hw/block/nvme.h
+++ b/hw/block/nvme.h
@@ -2,6 +2,9 @@
#define HW_NVME_H
#include "block/nvme.h"
+#include "nvme-ns.h"
+
+#define NVME_MAX_NAMESPACES 256
#define DEFINE_NVME_PROPERTIES(_state, _props) \
DEFINE_PROP_STRING("serial", _state, _props.serial), \
@@ -72,7 +75,6 @@ static inline const char *nvme_aio_opc_str(NvmeAIO *aio)
#define NVME_REQ_TRANSFER_MASK 0x3
typedef struct NvmeSQueue NvmeSQueue;
-typedef struct NvmeNamespace NvmeNamespace;
typedef void NvmeRequestCompletionFunc(NvmeRequest *req, void *opaque);
struct NvmeRequest {
@@ -122,7 +124,7 @@ static inline bool nvme_req_is_cmb(NvmeRequest *req)
return (req->flags & NVME_REQ_TRANSFER_MASK) == NVME_REQ_TRANSFER_CMB;
}
-static void nvme_req_set_cmb(NvmeRequest *req)
+static inline void nvme_req_set_cmb(NvmeRequest *req)
{
req->flags = NVME_REQ_TRANSFER_CMB;
}
@@ -173,9 +175,12 @@ struct NvmeCQueue {
QTAILQ_HEAD(, NvmeRequest) req_list;
};
-struct NvmeNamespace {
- NvmeIdNs id_ns;
-};
+#define TYPE_NVME_BUS "nvme-bus"
+#define NVME_BUS(obj) OBJECT_CHECK(NvmeBus, (obj), TYPE_NVME_BUS)
+
+typedef struct NvmeBus {
+ BusState parent_bus;
+} NvmeBus;
#define TYPE_NVME "nvme"
#define NVME(obj) \
@@ -186,8 +191,8 @@ typedef struct NvmeCtrl {
MemoryRegion iomem;
MemoryRegion ctrl_mem;
NvmeBar bar;
- BlockConf conf;
NvmeParams params;
+ NvmeBus bus;
uint32_t page_size;
uint16_t page_bits;
@@ -197,7 +202,6 @@ typedef struct NvmeCtrl {
uint32_t reg_size;
uint32_t num_namespaces;
uint32_t max_q_ents;
- uint64_t ns_size;
uint8_t outstanding_aers;
uint32_t cmbsz;
uint32_t cmbloc;
@@ -217,7 +221,8 @@ typedef struct NvmeCtrl {
NvmeRequest **aer_reqs;
QTAILQ_HEAD(, NvmeAsyncEvent) aer_queue;
- NvmeNamespace *namespaces;
+ NvmeNamespace namespace;
+ NvmeNamespace *namespaces[NVME_MAX_NAMESPACES];
NvmeSQueue **sq;
NvmeCQueue **cq;
NvmeSQueue admin_sq;
@@ -227,6 +232,15 @@ typedef struct NvmeCtrl {
NvmeIdCtrl id_ctrl;
} NvmeCtrl;
+static inline NvmeNamespace *nvme_ns(NvmeCtrl *n, uint32_t nsid)
+{
+ if (!nsid) {
+ return NULL;
+ }
+
+ return n->namespaces[nsid - 1];
+}
+
static inline NvmeCtrl *nvme_ctrl(NvmeRequest *req)
{
return req->sq->ctrl;
@@ -238,25 +252,6 @@ static inline bool nvme_is_error(uint16_t status, uint16_t err)
return (status & 0xfff) == err;
}
-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;
-}
-
-static inline size_t nvme_ns_lbads_bytes(NvmeNamespace *ns)
-{
- return 1 << nvme_ns_lbads(ns);
-}
-
-static inline uint64_t nvme_ns_nlbas(NvmeCtrl *n, NvmeNamespace *ns)
-{
- return n->ns_size >> nvme_ns_lbads(ns);
-}
+int nvme_register_namespace(NvmeCtrl *n, NvmeNamespace *ns, Error **errp);
#endif /* HW_NVME_H */
diff --git a/hw/block/trace-events b/hw/block/trace-events
index 59d42a3b8c39..95c24f514754 100644
--- a/hw/block/trace-events
+++ b/hw/block/trace-events
@@ -29,6 +29,7 @@ hd_geometry_guess(void *blk, uint32_t cyls, uint32_t heads, uint32_t secs, int t
# nvme.c
# nvme traces for successful events
+nvme_register_namespace(uint32_t nsid) "nsid %"PRIu32""
nvme_irq_msix(uint32_t vector) "raising MSI-X IRQ vector %u"
nvme_irq_pin(void) "pulsing IRQ pin"
nvme_irq_masked(void) "IRQ is masked"
@@ -38,7 +39,7 @@ nvme_map_sgl(uint16_t cid, uint8_t typ, uint32_t nlb, uint64_t len) "cid %"PRIu1
nvme_req_register_aio(uint16_t cid, void *aio, const char *blkname, uint64_t offset, uint64_t count, const char *opc, void *req) "cid %"PRIu16" aio %p blk \"%s\" offset %"PRIu64" count %"PRIu64" opc \"%s\" req %p"
nvme_aio_cb(uint16_t cid, void *aio, const char *blkname, uint64_t offset, const char *opc, void *req) "cid %"PRIu16" aio %p blk \"%s\" offset %"PRIu64" opc \"%s\" req %p"
nvme_io_cmd(uint16_t cid, uint32_t nsid, uint16_t sqid, uint8_t opcode) "cid %"PRIu16" nsid %"PRIu32" sqid %"PRIu16" opc 0x%"PRIx8""
-nvme_rw(const char *verb, uint32_t blk_count, uint64_t byte_count, uint64_t lba) "%s %"PRIu32" blocks (%"PRIu64" bytes) from LBA %"PRIu64""
+nvme_rw(uint16_t cid, const char *verb, uint32_t nsid, uint32_t nlb, uint64_t count, uint64_t lba) "cid %"PRIu16" %s nsid %"PRIu32" nlb %"PRIu32" count %"PRIu64" lba 0x%"PRIx64""
nvme_rw_cb(uint16_t cid, uint32_t nsid) "cid %"PRIu16" nsid %"PRIu32""
nvme_write_zeros(uint16_t cid, uint32_t nsid, uint64_t slba, uint32_t nlb) "cid %"PRIu16" nsid %"PRIu32" slba %"PRIu64" nlb %"PRIu32""
nvme_create_sq(uint64_t addr, uint16_t sqid, uint16_t cqid, uint16_t qsize, uint16_t qflags) "create submission queue, addr=0x%"PRIx64", sqid=%"PRIu16", cqid=%"PRIu16", qsize=%"PRIu16", qflags=%"PRIu16""
@@ -90,7 +91,7 @@ nvme_err_invalid_prplist_ent(uint64_t prplist) "PRP list entry is null or not pa
nvme_err_invalid_prp2_align(uint64_t prp2) "PRP2 is not page aligned: 0x%"PRIx64""
nvme_err_invalid_prp2_missing(void) "PRP2 is null and more data to be transferred"
nvme_err_invalid_prp(void) "invalid PRP"
-nvme_err_invalid_ns(uint32_t ns, uint32_t limit) "invalid namespace %u not within 1-%u"
+nvme_err_invalid_ns(uint32_t nsid, uint32_t nn) "nsid %"PRIu32" nn %"PRIu32""
nvme_err_invalid_opc(uint8_t opc) "invalid opcode 0x%"PRIx8""
nvme_err_invalid_admin_opc(uint8_t opc) "invalid admin opcode 0x%"PRIx8""
nvme_err_invalid_lba_range(uint64_t start, uint64_t len, uint64_t limit) "Invalid LBA start=%"PRIu64" len=%"PRIu64" limit=%"PRIu64""
--
2.23.0
^ permalink raw reply related [flat|nested] 52+ messages in thread* [PATCH v2 17/20] nvme: bump controller pci device id
2019-10-15 10:38 [PATCH v2 00/20] nvme: support NVMe v1.3d, SGLs and multiple namespaces Klaus Jensen
` (15 preceding siblings ...)
2019-10-15 10:38 ` [PATCH v2 16/20] nvme: support multiple namespaces Klaus Jensen
@ 2019-10-15 10:38 ` Klaus Jensen
2019-10-15 10:38 ` [PATCH v2 18/20] nvme: remove redundant NvmeCmd pointer parameter Klaus Jensen
` (6 subsequent siblings)
23 siblings, 0 replies; 52+ messages in thread
From: Klaus Jensen @ 2019-10-15 10:38 UTC (permalink / raw)
To: qemu-block
Cc: Kevin Wolf, Fam Zheng, Javier Gonzalez, qemu-devel, Max Reitz,
Keith Busch, Paul Durrant, Stephen Bates
Since commits 9d6459d21a6e ("nvme: fix write zeroes offset and count")
and c7fe50bcf1f1 ("nvme: support multiple namespaces") the controller
device no longer has the quirks that the Linux kernel think it has.
As the quirks are applied based on pci vendor and device id, bump the
device id to get rid of them.
Signed-off-by: Klaus Jensen <k.jensen@samsung.com>
---
hw/block/nvme.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/hw/block/nvme.c b/hw/block/nvme.c
index a23e9bc4e5ef..bcd801c345b6 100644
--- a/hw/block/nvme.c
+++ b/hw/block/nvme.c
@@ -2500,7 +2500,7 @@ static void nvme_init_pci(NvmeCtrl *n, PCIDevice *pci_dev)
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_device_id(pci_conf, 0x5846);
pci_config_set_class(pci_conf, PCI_CLASS_STORAGE_EXPRESS);
pcie_endpoint_cap_init(pci_dev, 0x80);
@@ -2655,7 +2655,7 @@ static void nvme_class_init(ObjectClass *oc, void *data)
pc->exit = nvme_exit;
pc->class_id = PCI_CLASS_STORAGE_EXPRESS;
pc->vendor_id = PCI_VENDOR_ID_INTEL;
- pc->device_id = 0x5845;
+ pc->device_id = 0x5846;
pc->revision = 2;
set_bit(DEVICE_CATEGORY_STORAGE, dc->categories);
--
2.23.0
^ permalink raw reply related [flat|nested] 52+ messages in thread* [PATCH v2 18/20] nvme: remove redundant NvmeCmd pointer parameter
2019-10-15 10:38 [PATCH v2 00/20] nvme: support NVMe v1.3d, SGLs and multiple namespaces Klaus Jensen
` (16 preceding siblings ...)
2019-10-15 10:38 ` [PATCH v2 17/20] nvme: bump controller pci device id Klaus Jensen
@ 2019-10-15 10:38 ` Klaus Jensen
2019-10-15 10:38 ` [PATCH v2 19/20] nvme: make lba data size configurable Klaus Jensen
` (5 subsequent siblings)
23 siblings, 0 replies; 52+ messages in thread
From: Klaus Jensen @ 2019-10-15 10:38 UTC (permalink / raw)
To: qemu-block
Cc: Kevin Wolf, Fam Zheng, Javier Gonzalez, qemu-devel, Max Reitz,
Keith Busch, Paul Durrant, Stephen Bates
The command struct is available in the NvmeRequest that we generally
pass around anyway.
Signed-off-by: Klaus Jensen <k.jensen@samsung.com>
---
hw/block/nvme.c | 219 +++++++++++++++++++++++-------------------------
1 file changed, 106 insertions(+), 113 deletions(-)
diff --git a/hw/block/nvme.c b/hw/block/nvme.c
index bcd801c345b6..67f92bf5a3ac 100644
--- a/hw/block/nvme.c
+++ b/hw/block/nvme.c
@@ -574,14 +574,14 @@ static uint16_t nvme_dma_write_sgl(NvmeCtrl *n, uint8_t *ptr, uint32_t len,
}
static uint16_t nvme_dma_write(NvmeCtrl *n, uint8_t *ptr, uint32_t len,
- NvmeCmd *cmd, NvmeRequest *req)
+ NvmeRequest *req)
{
- if (NVME_CMD_FLAGS_PSDT(cmd->flags)) {
- return nvme_dma_write_sgl(n, ptr, len, cmd->dptr.sgl, req);
+ if (NVME_CMD_FLAGS_PSDT(req->cmd.flags)) {
+ return nvme_dma_write_sgl(n, ptr, len, req->cmd.dptr.sgl, req);
}
- uint64_t prp1 = le64_to_cpu(cmd->dptr.prp.prp1);
- uint64_t prp2 = le64_to_cpu(cmd->dptr.prp.prp2);
+ uint64_t prp1 = le64_to_cpu(req->cmd.dptr.prp.prp1);
+ uint64_t prp2 = le64_to_cpu(req->cmd.dptr.prp.prp2);
return nvme_dma_write_prp(n, ptr, len, prp1, prp2, req);
}
@@ -624,7 +624,7 @@ out:
}
static uint16_t nvme_dma_read_sgl(NvmeCtrl *n, uint8_t *ptr, uint32_t len,
- NvmeSglDescriptor sgl, NvmeCmd *cmd, NvmeRequest *req)
+ NvmeSglDescriptor sgl, NvmeRequest *req)
{
QEMUSGList qsg;
uint16_t err = NVME_SUCCESS;
@@ -662,29 +662,29 @@ out:
}
static uint16_t nvme_dma_read(NvmeCtrl *n, uint8_t *ptr, uint32_t len,
- NvmeCmd *cmd, NvmeRequest *req)
+ NvmeRequest *req)
{
- if (NVME_CMD_FLAGS_PSDT(cmd->flags)) {
- return nvme_dma_read_sgl(n, ptr, len, cmd->dptr.sgl, cmd, req);
+ if (NVME_CMD_FLAGS_PSDT(req->cmd.flags)) {
+ return nvme_dma_read_sgl(n, ptr, len, req->cmd.dptr.sgl, req);
}
- uint64_t prp1 = le64_to_cpu(cmd->dptr.prp.prp1);
- uint64_t prp2 = le64_to_cpu(cmd->dptr.prp.prp2);
+ uint64_t prp1 = le64_to_cpu(req->cmd.dptr.prp.prp1);
+ uint64_t prp2 = le64_to_cpu(req->cmd.dptr.prp.prp2);
return nvme_dma_read_prp(n, ptr, len, prp1, prp2, req);
}
-static uint16_t nvme_map(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
+static uint16_t nvme_map(NvmeCtrl *n, NvmeRequest *req)
{
uint32_t len = req->nlb << nvme_ns_lbads(req->ns);
uint64_t prp1, prp2;
- if (NVME_CMD_FLAGS_PSDT(cmd->flags)) {
- return nvme_map_sgl(n, &req->qsg, cmd->dptr.sgl, len, req);
+ if (NVME_CMD_FLAGS_PSDT(req->cmd.flags)) {
+ return nvme_map_sgl(n, &req->qsg, req->cmd.dptr.sgl, len, req);
}
- prp1 = le64_to_cpu(cmd->dptr.prp.prp1);
- prp2 = le64_to_cpu(cmd->dptr.prp.prp2);
+ prp1 = le64_to_cpu(req->cmd.dptr.prp.prp1);
+ prp2 = le64_to_cpu(req->cmd.dptr.prp.prp2);
return nvme_map_prp(n, &req->qsg, prp1, prp2, len, req);
}
@@ -1045,7 +1045,7 @@ static uint16_t nvme_check_rw(NvmeCtrl *n, NvmeRequest *req)
return NVME_SUCCESS;
}
-static uint16_t nvme_flush(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
+static uint16_t nvme_flush(NvmeCtrl *n, NvmeRequest *req)
{
NvmeNamespace *ns = req->ns;
@@ -1057,12 +1057,12 @@ static uint16_t nvme_flush(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
return NVME_NO_COMPLETE;
}
-static uint16_t nvme_write_zeros(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
+static uint16_t nvme_write_zeros(NvmeCtrl *n, NvmeRequest *req)
{
NvmeAIO *aio;
NvmeNamespace *ns = req->ns;
- NvmeRwCmd *rw = (NvmeRwCmd *) cmd;
+ NvmeRwCmd *rw = (NvmeRwCmd *) &req->cmd;
int64_t offset;
size_t count;
@@ -1092,9 +1092,9 @@ static uint16_t nvme_write_zeros(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
return NVME_NO_COMPLETE;
}
-static uint16_t nvme_rw(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
+static uint16_t nvme_rw(NvmeCtrl *n, NvmeRequest *req)
{
- NvmeRwCmd *rw = (NvmeRwCmd *) cmd;
+ NvmeRwCmd *rw = (NvmeRwCmd *) &req->cmd;
NvmeNamespace *ns = req->ns;
int status;
@@ -1114,7 +1114,7 @@ static uint16_t nvme_rw(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
return status;
}
- status = nvme_map(n, cmd, req);
+ status = nvme_map(n, req);
if (status) {
block_acct_invalid(blk_get_stats(ns->conf.blk), acct);
return status;
@@ -1126,11 +1126,12 @@ static uint16_t nvme_rw(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
return NVME_NO_COMPLETE;
}
-static uint16_t nvme_io_cmd(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
+static uint16_t nvme_io_cmd(NvmeCtrl *n, NvmeRequest *req)
{
- uint32_t nsid = le32_to_cpu(cmd->nsid);
+ uint32_t nsid = le32_to_cpu(req->cmd.nsid);
- trace_nvme_io_cmd(req->cid, nsid, le16_to_cpu(req->sq->sqid), cmd->opcode);
+ trace_nvme_io_cmd(req->cid, nsid, le16_to_cpu(req->sq->sqid),
+ req->cmd.opcode);
req->ns = nvme_ns(n, nsid);
@@ -1139,16 +1140,16 @@ static uint16_t nvme_io_cmd(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
return NVME_INVALID_NSID | NVME_DNR;
}
- switch (cmd->opcode) {
+ switch (req->cmd.opcode) {
case NVME_CMD_FLUSH:
- return nvme_flush(n, cmd, req);
+ return nvme_flush(n, req);
case NVME_CMD_WRITE_ZEROS:
- return nvme_write_zeros(n, cmd, req);
+ return nvme_write_zeros(n, req);
case NVME_CMD_WRITE:
case NVME_CMD_READ:
- return nvme_rw(n, cmd, req);
+ return nvme_rw(n, req);
default:
- trace_nvme_err_invalid_opc(cmd->opcode);
+ trace_nvme_err_invalid_opc(req->cmd.opcode);
return NVME_INVALID_OPCODE | NVME_DNR;
}
}
@@ -1165,10 +1166,10 @@ static void nvme_free_sq(NvmeSQueue *sq, NvmeCtrl *n)
n->qs_created--;
}
-static uint16_t nvme_del_sq(NvmeCtrl *n, NvmeCmd *cmd)
+static uint16_t nvme_del_sq(NvmeCtrl *n, NvmeRequest *req)
{
- NvmeDeleteQ *c = (NvmeDeleteQ *)cmd;
- NvmeRequest *req, *next;
+ NvmeDeleteQ *c = (NvmeDeleteQ *) &req->cmd;
+ NvmeRequest *next;
NvmeSQueue *sq;
NvmeCQueue *cq;
NvmeAIO *aio;
@@ -1237,10 +1238,10 @@ static void nvme_init_sq(NvmeSQueue *sq, NvmeCtrl *n, uint64_t dma_addr,
n->qs_created++;
}
-static uint16_t nvme_create_sq(NvmeCtrl *n, NvmeCmd *cmd)
+static uint16_t nvme_create_sq(NvmeCtrl *n, NvmeRequest *req)
{
NvmeSQueue *sq;
- NvmeCreateSq *c = (NvmeCreateSq *)cmd;
+ NvmeCreateSq *c = (NvmeCreateSq *) &req->cmd;
uint16_t cqid = le16_to_cpu(c->cqid);
uint16_t sqid = le16_to_cpu(c->sqid);
@@ -1275,8 +1276,8 @@ static uint16_t nvme_create_sq(NvmeCtrl *n, NvmeCmd *cmd)
return NVME_SUCCESS;
}
-static uint16_t nvme_error_info(NvmeCtrl *n, NvmeCmd *cmd, uint8_t rae,
- uint32_t buf_len, uint64_t off, NvmeRequest *req)
+static uint16_t nvme_error_info(NvmeCtrl *n, uint8_t rae, uint32_t buf_len,
+ uint64_t off, NvmeRequest *req)
{
uint32_t trans_len;
@@ -1290,13 +1291,13 @@ static uint16_t nvme_error_info(NvmeCtrl *n, NvmeCmd *cmd, uint8_t rae,
nvme_clear_events(n, NVME_AER_TYPE_ERROR);
}
- return nvme_dma_read(n, (uint8_t *) n->elpes + off, trans_len, cmd, req);
+ return nvme_dma_read(n, (uint8_t *) n->elpes + off, trans_len, req);
}
-static uint16_t nvme_smart_info(NvmeCtrl *n, NvmeCmd *cmd, uint8_t rae,
- uint32_t buf_len, uint64_t off, NvmeRequest *req)
+static uint16_t nvme_smart_info(NvmeCtrl *n, uint8_t rae, uint32_t buf_len,
+ uint64_t off, NvmeRequest *req)
{
- uint32_t nsid = le32_to_cpu(cmd->nsid);
+ uint32_t nsid = le32_to_cpu(req->cmd.nsid);
uint32_t trans_len;
time_t current_ms;
@@ -1352,11 +1353,11 @@ static uint16_t nvme_smart_info(NvmeCtrl *n, NvmeCmd *cmd, uint8_t rae,
nvme_clear_events(n, NVME_AER_TYPE_SMART);
}
- return nvme_dma_read(n, (uint8_t *) &smart + off, trans_len, cmd, req);
+ return nvme_dma_read(n, (uint8_t *) &smart + off, trans_len, req);
}
-static uint16_t nvme_fw_log_info(NvmeCtrl *n, NvmeCmd *cmd, uint32_t buf_len,
- uint64_t off, NvmeRequest *req)
+static uint16_t nvme_fw_log_info(NvmeCtrl *n, uint32_t buf_len, uint64_t off,
+ NvmeRequest *req)
{
uint32_t trans_len;
NvmeFwSlotInfoLog fw_log;
@@ -1369,15 +1370,15 @@ static uint16_t nvme_fw_log_info(NvmeCtrl *n, NvmeCmd *cmd, uint32_t buf_len,
trans_len = MIN(sizeof(fw_log) - off, buf_len);
- return nvme_dma_read(n, (uint8_t *) &fw_log + off, trans_len, cmd, req);
+ return nvme_dma_read(n, (uint8_t *) &fw_log + off, trans_len, req);
}
-static uint16_t nvme_get_log(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
+static uint16_t nvme_get_log(NvmeCtrl *n, NvmeRequest *req)
{
- uint32_t dw10 = le32_to_cpu(cmd->cdw10);
- uint32_t dw11 = le32_to_cpu(cmd->cdw11);
- uint32_t dw12 = le32_to_cpu(cmd->cdw12);
- uint32_t dw13 = le32_to_cpu(cmd->cdw13);
+ uint32_t dw10 = le32_to_cpu(req->cmd.cdw10);
+ uint32_t dw11 = le32_to_cpu(req->cmd.cdw11);
+ uint32_t dw12 = le32_to_cpu(req->cmd.cdw12);
+ uint32_t dw13 = le32_to_cpu(req->cmd.cdw13);
uint8_t lid = dw10 & 0xff;
uint8_t lsp = (dw10 >> 8) & 0xf;
uint8_t rae = (dw10 >> 15) & 0x1;
@@ -1407,11 +1408,11 @@ static uint16_t nvme_get_log(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
switch (lid) {
case NVME_LOG_ERROR_INFO:
- return nvme_error_info(n, cmd, rae, len, off, req);
+ return nvme_error_info(n, rae, len, off, req);
case NVME_LOG_SMART_INFO:
- return nvme_smart_info(n, cmd, rae, len, off, req);
+ return nvme_smart_info(n, rae, len, off, req);
case NVME_LOG_FW_SLOT_INFO:
- return nvme_fw_log_info(n, cmd, len, off, req);
+ return nvme_fw_log_info(n, len, off, req);
default:
trace_nvme_err_invalid_log_page(req->cid, lid);
return NVME_INVALID_LOG_ID | NVME_DNR;
@@ -1430,9 +1431,9 @@ static void nvme_free_cq(NvmeCQueue *cq, NvmeCtrl *n)
n->qs_created--;
}
-static uint16_t nvme_del_cq(NvmeCtrl *n, NvmeCmd *cmd)
+static uint16_t nvme_del_cq(NvmeCtrl *n, NvmeRequest *req)
{
- NvmeDeleteQ *c = (NvmeDeleteQ *)cmd;
+ NvmeDeleteQ *c = (NvmeDeleteQ *) &req->cmd;
NvmeCQueue *cq;
uint16_t qid = le16_to_cpu(c->qid);
@@ -1471,10 +1472,10 @@ static void nvme_init_cq(NvmeCQueue *cq, NvmeCtrl *n, uint64_t dma_addr,
n->qs_created++;
}
-static uint16_t nvme_create_cq(NvmeCtrl *n, NvmeCmd *cmd)
+static uint16_t nvme_create_cq(NvmeCtrl *n, NvmeRequest *req)
{
NvmeCQueue *cq;
- NvmeCreateCq *c = (NvmeCreateCq *)cmd;
+ NvmeCreateCq *c = (NvmeCreateCq *) &req->cmd;
uint16_t cqid = le16_to_cpu(c->cqid);
uint16_t vector = le16_to_cpu(c->irq_vector);
uint16_t qsize = le16_to_cpu(c->qsize);
@@ -1511,17 +1512,16 @@ static uint16_t nvme_create_cq(NvmeCtrl *n, NvmeCmd *cmd)
return NVME_SUCCESS;
}
-static uint16_t nvme_identify_ctrl(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
+static uint16_t nvme_identify_ctrl(NvmeCtrl *n, NvmeRequest *req)
{
trace_nvme_identify_ctrl();
- return nvme_dma_read(n, (uint8_t *) &n->id_ctrl, sizeof(n->id_ctrl), cmd,
- req);
+ return nvme_dma_read(n, (uint8_t *) &n->id_ctrl, sizeof(n->id_ctrl), req);
}
-static uint16_t nvme_identify_ns(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
+static uint16_t nvme_identify_ns(NvmeCtrl *n, NvmeRequest *req)
{
- uint32_t nsid = le32_to_cpu(cmd->nsid);
+ uint32_t nsid = le32_to_cpu(req->cmd.nsid);
NvmeNamespace *ns = nvme_ns(n, nsid);
trace_nvme_identify_ns(nsid);
@@ -1531,15 +1531,13 @@ static uint16_t nvme_identify_ns(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
return NVME_INVALID_NSID | NVME_DNR;
}
- return nvme_dma_read(n, (uint8_t *) &ns->id_ns, sizeof(ns->id_ns), cmd,
- req);
+ return nvme_dma_read(n, (uint8_t *) &ns->id_ns, sizeof(ns->id_ns), req);
}
-static uint16_t nvme_identify_ns_list(NvmeCtrl *n, NvmeCmd *cmd,
- NvmeRequest *req)
+static uint16_t nvme_identify_ns_list(NvmeCtrl *n, NvmeRequest *req)
{
static const int data_len = 4 * KiB;
- uint32_t min_nsid = le32_to_cpu(cmd->nsid);
+ uint32_t min_nsid = le32_to_cpu(req->cmd.nsid);
uint32_t *list;
uint16_t ret;
int i, j = 0;
@@ -1556,13 +1554,12 @@ static uint16_t nvme_identify_ns_list(NvmeCtrl *n, NvmeCmd *cmd,
break;
}
}
- ret = nvme_dma_read(n, (uint8_t *) list, data_len, cmd, req);
+ ret = nvme_dma_read(n, (uint8_t *) list, data_len, req);
g_free(list);
return ret;
}
-static uint16_t nvme_identify_ns_descr_list(NvmeCtrl *n, NvmeCmd *cmd,
- NvmeRequest *req)
+static uint16_t nvme_identify_ns_descr_list(NvmeCtrl *n, NvmeRequest *req)
{
static const int len = 4096;
@@ -1573,7 +1570,7 @@ static uint16_t nvme_identify_ns_descr_list(NvmeCtrl *n, NvmeCmd *cmd,
uint8_t nid[16];
};
- uint32_t nsid = le32_to_cpu(cmd->nsid);
+ uint32_t nsid = le32_to_cpu(req->cmd.nsid);
struct ns_descr *list;
uint16_t ret;
@@ -1590,33 +1587,33 @@ static uint16_t nvme_identify_ns_descr_list(NvmeCtrl *n, NvmeCmd *cmd,
list->nidl = 0x10;
*(uint32_t *) &list->nid[12] = cpu_to_be32(nsid);
- ret = nvme_dma_read(n, (uint8_t *) list, len, cmd, req);
+ ret = nvme_dma_read(n, (uint8_t *) list, len, req);
g_free(list);
return ret;
}
-static uint16_t nvme_identify(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
+static uint16_t nvme_identify(NvmeCtrl *n, NvmeRequest *req)
{
- NvmeIdentify *c = (NvmeIdentify *)cmd;
+ NvmeIdentify *c = (NvmeIdentify *) &req->cmd;
switch (le32_to_cpu(c->cns)) {
case 0x00:
- return nvme_identify_ns(n, cmd, req);
+ return nvme_identify_ns(n, req);
case 0x01:
- return nvme_identify_ctrl(n, cmd, req);
+ return nvme_identify_ctrl(n, req);
case 0x02:
- return nvme_identify_ns_list(n, cmd, req);
+ return nvme_identify_ns_list(n, req);
case 0x03:
- return nvme_identify_ns_descr_list(n, cmd, req);
+ return nvme_identify_ns_descr_list(n, req);
default:
trace_nvme_err_invalid_identify_cns(le32_to_cpu(c->cns));
return NVME_INVALID_FIELD | NVME_DNR;
}
}
-static uint16_t nvme_abort(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
+static uint16_t nvme_abort(NvmeCtrl *n, NvmeRequest *req)
{
- uint16_t sqid = le32_to_cpu(cmd->cdw10) & 0xffff;
+ uint16_t sqid = le32_to_cpu(req->cmd.cdw10) & 0xffff;
req->cqe.result = 1;
if (nvme_check_sqid(n, sqid)) {
@@ -1666,21 +1663,19 @@ static inline uint64_t nvme_get_timestamp(const NvmeCtrl *n)
return cpu_to_le64(ts.all);
}
-static uint16_t nvme_get_feature_timestamp(NvmeCtrl *n, NvmeCmd *cmd,
- NvmeRequest *req)
+static uint16_t nvme_get_feature_timestamp(NvmeCtrl *n, NvmeRequest *req)
{
uint64_t timestamp = nvme_get_timestamp(n);
- return nvme_dma_read(n, (uint8_t *)×tamp, sizeof(timestamp), cmd,
- req);
+ return nvme_dma_read(n, (uint8_t *)×tamp, sizeof(timestamp), req);
}
-static uint16_t nvme_get_feature(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
+static uint16_t nvme_get_feature(NvmeCtrl *n, NvmeRequest *req)
{
NvmeNamespace *ns;
- uint32_t dw10 = le32_to_cpu(cmd->cdw10);
- uint32_t dw11 = le32_to_cpu(cmd->cdw11);
+ uint32_t dw10 = le32_to_cpu(req->cmd.cdw10);
+ uint32_t dw11 = le32_to_cpu(req->cmd.cdw11);
uint32_t result, nsid;
trace_nvme_getfeat(dw10);
@@ -1716,7 +1711,7 @@ static uint16_t nvme_get_feature(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
trace_nvme_getfeat_numq(result);
break;
case NVME_TIMESTAMP:
- return nvme_get_feature_timestamp(n, cmd, req);
+ return nvme_get_feature_timestamp(n, req);
case NVME_INTERRUPT_COALESCING:
result = cpu_to_le32(n->features.int_coalescing);
break;
@@ -1742,14 +1737,12 @@ static uint16_t nvme_get_feature(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
return NVME_SUCCESS;
}
-static uint16_t nvme_set_feature_timestamp(NvmeCtrl *n, NvmeCmd *cmd,
- NvmeRequest *req)
+static uint16_t nvme_set_feature_timestamp(NvmeCtrl *n, NvmeRequest *req)
{
uint16_t ret;
uint64_t timestamp;
- ret = nvme_dma_write(n, (uint8_t *)×tamp, sizeof(timestamp), cmd,
- req);
+ ret = nvme_dma_write(n, (uint8_t *)×tamp, sizeof(timestamp), req);
if (ret != NVME_SUCCESS) {
return ret;
}
@@ -1759,12 +1752,12 @@ static uint16_t nvme_set_feature_timestamp(NvmeCtrl *n, NvmeCmd *cmd,
return NVME_SUCCESS;
}
-static uint16_t nvme_set_feature(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
+static uint16_t nvme_set_feature(NvmeCtrl *n, NvmeRequest *req)
{
NvmeNamespace *ns;
- uint32_t dw10 = le32_to_cpu(cmd->cdw10);
- uint32_t dw11 = le32_to_cpu(cmd->cdw11);
+ uint32_t dw10 = le32_to_cpu(req->cmd.cdw10);
+ uint32_t dw11 = le32_to_cpu(req->cmd.cdw11);
uint32_t nsid;
trace_nvme_setfeat(dw10, dw11);
@@ -1808,7 +1801,7 @@ static uint16_t nvme_set_feature(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
((n->params.num_queues - 2) << 16));
break;
case NVME_TIMESTAMP:
- return nvme_set_feature_timestamp(n, cmd, req);
+ return nvme_set_feature_timestamp(n, req);
case NVME_ASYNCHRONOUS_EVENT_CONF:
n->features.async_config = dw11;
break;
@@ -1827,7 +1820,7 @@ static uint16_t nvme_set_feature(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
return NVME_SUCCESS;
}
-static uint16_t nvme_aer(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
+static uint16_t nvme_aer(NvmeCtrl *n, NvmeRequest *req)
{
trace_nvme_aer(req->cid);
@@ -1843,31 +1836,31 @@ static uint16_t nvme_aer(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
return NVME_NO_COMPLETE;
}
-static uint16_t nvme_admin_cmd(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)
+static uint16_t nvme_admin_cmd(NvmeCtrl *n, NvmeRequest *req)
{
- switch (cmd->opcode) {
+ switch (req->cmd.opcode) {
case NVME_ADM_CMD_DELETE_SQ:
- return nvme_del_sq(n, cmd);
+ return nvme_del_sq(n, req);
case NVME_ADM_CMD_CREATE_SQ:
- return nvme_create_sq(n, cmd);
+ return nvme_create_sq(n, req);
case NVME_ADM_CMD_GET_LOG_PAGE:
- return nvme_get_log(n, cmd, req);
+ return nvme_get_log(n, req);
case NVME_ADM_CMD_DELETE_CQ:
- return nvme_del_cq(n, cmd);
+ return nvme_del_cq(n, req);
case NVME_ADM_CMD_CREATE_CQ:
- return nvme_create_cq(n, cmd);
+ return nvme_create_cq(n, req);
case NVME_ADM_CMD_IDENTIFY:
- return nvme_identify(n, cmd, req);
+ return nvme_identify(n, req);
case NVME_ADM_CMD_ABORT:
- return nvme_abort(n, cmd, req);
+ return nvme_abort(n, req);
case NVME_ADM_CMD_SET_FEATURES:
- return nvme_set_feature(n, cmd, req);
+ return nvme_set_feature(n, req);
case NVME_ADM_CMD_GET_FEATURES:
- return nvme_get_feature(n, cmd, req);
+ return nvme_get_feature(n, req);
case NVME_ADM_CMD_ASYNC_EV_REQ:
- return nvme_aer(n, cmd, req);
+ return nvme_aer(n, req);
default:
- trace_nvme_err_invalid_admin_opc(cmd->opcode);
+ trace_nvme_err_invalid_admin_opc(req->cmd.opcode);
return NVME_INVALID_OPCODE | NVME_DNR;
}
}
@@ -1944,7 +1937,7 @@ static void nvme_process_sq(void *opaque)
while (!(nvme_sq_empty(sq) || QTAILQ_EMPTY(&sq->req_list))) {
addr = sq->dma_addr + sq->head * n->sqe_size;
- nvme_addr_read(n, addr, (void *)&cmd, sizeof(cmd));
+ nvme_addr_read(n, addr, (void *)&cmd, sizeof(NvmeCmd));
nvme_inc_sq_head(sq);
req = QTAILQ_FIRST(&sq->req_list);
@@ -1953,8 +1946,8 @@ static void nvme_process_sq(void *opaque)
nvme_init_req(n, &cmd, req);
- status = sq->sqid ? nvme_io_cmd(n, &cmd, req) :
- nvme_admin_cmd(n, &cmd, req);
+ status = sq->sqid ? nvme_io_cmd(n, req) :
+ nvme_admin_cmd(n, req);
if (status != NVME_NO_COMPLETE) {
req->status = status;
nvme_enqueue_req_completion(cq, req);
--
2.23.0
^ permalink raw reply related [flat|nested] 52+ messages in thread* [PATCH v2 19/20] nvme: make lba data size configurable
2019-10-15 10:38 [PATCH v2 00/20] nvme: support NVMe v1.3d, SGLs and multiple namespaces Klaus Jensen
` (17 preceding siblings ...)
2019-10-15 10:38 ` [PATCH v2 18/20] nvme: remove redundant NvmeCmd pointer parameter Klaus Jensen
@ 2019-10-15 10:38 ` Klaus Jensen
2019-11-12 15:24 ` Beata Michalska
2019-10-15 10:39 ` [PATCH v2 20/20] nvme: handle dma errors Klaus Jensen
` (4 subsequent siblings)
23 siblings, 1 reply; 52+ messages in thread
From: Klaus Jensen @ 2019-10-15 10:38 UTC (permalink / raw)
To: qemu-block
Cc: Kevin Wolf, Fam Zheng, Javier Gonzalez, qemu-devel, Max Reitz,
Keith Busch, Paul Durrant, Stephen Bates
Signed-off-by: Klaus Jensen <k.jensen@samsung.com>
---
hw/block/nvme-ns.c | 2 +-
hw/block/nvme-ns.h | 4 +++-
hw/block/nvme.c | 1 +
3 files changed, 5 insertions(+), 2 deletions(-)
diff --git a/hw/block/nvme-ns.c b/hw/block/nvme-ns.c
index aa76bb63ef45..70ff622a5729 100644
--- a/hw/block/nvme-ns.c
+++ b/hw/block/nvme-ns.c
@@ -18,7 +18,7 @@ static int nvme_ns_init(NvmeNamespace *ns)
{
NvmeIdNs *id_ns = &ns->id_ns;
- id_ns->lbaf[0].ds = BDRV_SECTOR_BITS;
+ id_ns->lbaf[0].ds = ns->params.lbads;
id_ns->nuse = id_ns->ncap = id_ns->nsze =
cpu_to_le64(nvme_ns_nlbas(ns));
diff --git a/hw/block/nvme-ns.h b/hw/block/nvme-ns.h
index 64dd054cf6a9..aa1c81d85cde 100644
--- a/hw/block/nvme-ns.h
+++ b/hw/block/nvme-ns.h
@@ -6,10 +6,12 @@
OBJECT_CHECK(NvmeNamespace, (obj), TYPE_NVME_NS)
#define DEFINE_NVME_NS_PROPERTIES(_state, _props) \
- DEFINE_PROP_UINT32("nsid", _state, _props.nsid, 0)
+ DEFINE_PROP_UINT32("nsid", _state, _props.nsid, 0), \
+ DEFINE_PROP_UINT8("lbads", _state, _props.lbads, 9)
typedef struct NvmeNamespaceParams {
uint32_t nsid;
+ uint8_t lbads;
} NvmeNamespaceParams;
typedef struct NvmeNamespace {
diff --git a/hw/block/nvme.c b/hw/block/nvme.c
index 67f92bf5a3ac..d0103c16cfe9 100644
--- a/hw/block/nvme.c
+++ b/hw/block/nvme.c
@@ -2602,6 +2602,7 @@ static void nvme_realize(PCIDevice *pci_dev, Error **errp)
if (n->namespace.conf.blk) {
ns = &n->namespace;
ns->params.nsid = 1;
+ ns->params.lbads = 9;
if (nvme_ns_setup(n, ns, &local_err)) {
error_propagate_prepend(errp, local_err, "nvme_ns_setup: ");
--
2.23.0
^ permalink raw reply related [flat|nested] 52+ messages in thread* Re: [PATCH v2 19/20] nvme: make lba data size configurable
2019-10-15 10:38 ` [PATCH v2 19/20] nvme: make lba data size configurable Klaus Jensen
@ 2019-11-12 15:24 ` Beata Michalska
2019-11-13 7:13 ` Klaus Birkelund
0 siblings, 1 reply; 52+ messages in thread
From: Beata Michalska @ 2019-11-12 15:24 UTC (permalink / raw)
To: Klaus Jensen
Cc: Kevin Wolf, Fam Zheng, Javier Gonzalez, qemu-block, qemu-devel,
Max Reitz, Keith Busch, Paul Durrant, Stephen Bates
Hi Klaus,
On Tue, 15 Oct 2019 at 11:50, Klaus Jensen <its@irrelevant.dk> wrote:
>
> Signed-off-by: Klaus Jensen <k.jensen@samsung.com>
> ---
> hw/block/nvme-ns.c | 2 +-
> hw/block/nvme-ns.h | 4 +++-
> hw/block/nvme.c | 1 +
> 3 files changed, 5 insertions(+), 2 deletions(-)
>
> diff --git a/hw/block/nvme-ns.c b/hw/block/nvme-ns.c
> index aa76bb63ef45..70ff622a5729 100644
> --- a/hw/block/nvme-ns.c
> +++ b/hw/block/nvme-ns.c
> @@ -18,7 +18,7 @@ static int nvme_ns_init(NvmeNamespace *ns)
> {
> NvmeIdNs *id_ns = &ns->id_ns;
>
> - id_ns->lbaf[0].ds = BDRV_SECTOR_BITS;
> + id_ns->lbaf[0].ds = ns->params.lbads;
> id_ns->nuse = id_ns->ncap = id_ns->nsze =
> cpu_to_le64(nvme_ns_nlbas(ns));
>
> diff --git a/hw/block/nvme-ns.h b/hw/block/nvme-ns.h
> index 64dd054cf6a9..aa1c81d85cde 100644
> --- a/hw/block/nvme-ns.h
> +++ b/hw/block/nvme-ns.h
> @@ -6,10 +6,12 @@
> OBJECT_CHECK(NvmeNamespace, (obj), TYPE_NVME_NS)
>
> #define DEFINE_NVME_NS_PROPERTIES(_state, _props) \
> - DEFINE_PROP_UINT32("nsid", _state, _props.nsid, 0)
> + DEFINE_PROP_UINT32("nsid", _state, _props.nsid, 0), \
> + DEFINE_PROP_UINT8("lbads", _state, _props.lbads, 9)
>
Could we actually use BDRV_SECTOR_BITS instead of magic numbers?
BR
Beata
> typedef struct NvmeNamespaceParams {
> uint32_t nsid;
> + uint8_t lbads;
> } NvmeNamespaceParams;
>
> typedef struct NvmeNamespace {
> diff --git a/hw/block/nvme.c b/hw/block/nvme.c
> index 67f92bf5a3ac..d0103c16cfe9 100644
> --- a/hw/block/nvme.c
> +++ b/hw/block/nvme.c
> @@ -2602,6 +2602,7 @@ static void nvme_realize(PCIDevice *pci_dev, Error **errp)
> if (n->namespace.conf.blk) {
> ns = &n->namespace;
> ns->params.nsid = 1;
> + ns->params.lbads = 9;
>
> if (nvme_ns_setup(n, ns, &local_err)) {
> error_propagate_prepend(errp, local_err, "nvme_ns_setup: ");
> --
> 2.23.0
>
>
^ permalink raw reply [flat|nested] 52+ messages in thread* Re: [PATCH v2 19/20] nvme: make lba data size configurable
2019-11-12 15:24 ` Beata Michalska
@ 2019-11-13 7:13 ` Klaus Birkelund
0 siblings, 0 replies; 52+ messages in thread
From: Klaus Birkelund @ 2019-11-13 7:13 UTC (permalink / raw)
To: Beata Michalska
Cc: Kevin Wolf, Fam Zheng, qemu-block, qemu-devel, Max Reitz,
Keith Busch, Paul Durrant
On Tue, Nov 12, 2019 at 03:24:00PM +0000, Beata Michalska wrote:
> Hi Klaus,
>
> On Tue, 15 Oct 2019 at 11:50, Klaus Jensen <its@irrelevant.dk> wrote:
> > #define DEFINE_NVME_NS_PROPERTIES(_state, _props) \
> > - DEFINE_PROP_UINT32("nsid", _state, _props.nsid, 0)
> > + DEFINE_PROP_UINT32("nsid", _state, _props.nsid, 0), \
> > + DEFINE_PROP_UINT8("lbads", _state, _props.lbads, 9)
> >
> Could we actually use BDRV_SECTOR_BITS instead of magic numbers?
>
Yes, better. Fixed in two places.
^ permalink raw reply [flat|nested] 52+ messages in thread
* [PATCH v2 20/20] nvme: handle dma errors
2019-10-15 10:38 [PATCH v2 00/20] nvme: support NVMe v1.3d, SGLs and multiple namespaces Klaus Jensen
` (18 preceding siblings ...)
2019-10-15 10:38 ` [PATCH v2 19/20] nvme: make lba data size configurable Klaus Jensen
@ 2019-10-15 10:39 ` Klaus Jensen
2019-10-15 17:19 ` [PATCH v2 00/20] nvme: support NVMe v1.3d, SGLs and multiple namespaces no-reply
` (3 subsequent siblings)
23 siblings, 0 replies; 52+ messages in thread
From: Klaus Jensen @ 2019-10-15 10:39 UTC (permalink / raw)
To: qemu-block
Cc: Kevin Wolf, Fam Zheng, Javier Gonzalez, qemu-devel, Max Reitz,
Keith Busch, Paul Durrant, Stephen Bates
Handling DMA errors gracefully is required for the device to pass the
block/011 test ("disable PCI device while doing I/O") in the blktests
suite.
With this patch the device passes the test by retrying "critical"
transfers (posting of completion entries and processing of submission
queue entries).
If DMA errors occur at any other point in the execution of the command
(say, while mapping the PRPs or SGLs), the command is aborted with a
Data Transfer Error status code.
Signed-off-by: Klaus Jensen <k.jensen@samsung.com>
---
hw/block/nvme.c | 63 +++++++++++++++++++++++++++++++++----------
hw/block/trace-events | 2 ++
include/block/nvme.h | 2 +-
3 files changed, 52 insertions(+), 15 deletions(-)
diff --git a/hw/block/nvme.c b/hw/block/nvme.c
index d0103c16cfe9..00c5b843295b 100644
--- a/hw/block/nvme.c
+++ b/hw/block/nvme.c
@@ -71,26 +71,26 @@ static inline bool nvme_addr_is_cmb(NvmeCtrl *n, hwaddr addr)
return addr >= low && addr < hi;
}
-static inline void nvme_addr_read(NvmeCtrl *n, hwaddr addr, void *buf,
+static inline int nvme_addr_read(NvmeCtrl *n, hwaddr addr, void *buf,
int size)
{
if (n->cmbsz && nvme_addr_is_cmb(n, addr)) {
memcpy(buf, (void *) &n->cmbuf[addr - n->ctrl_mem.addr], size);
- return;
+ return 0;
}
- pci_dma_read(&n->parent_obj, addr, buf, size);
+ return pci_dma_read(&n->parent_obj, addr, buf, size);
}
-static inline void nvme_addr_write(NvmeCtrl *n, hwaddr addr, void *buf,
+static inline int nvme_addr_write(NvmeCtrl *n, hwaddr addr, void *buf,
int size)
{
if (n->cmbsz && nvme_addr_is_cmb(n, addr)) {
memcpy((void *) &n->cmbuf[addr - n->ctrl_mem.addr], buf, size);
- return;
+ return 0;
}
- pci_dma_write(&n->parent_obj, addr, buf, size);
+ return pci_dma_write(&n->parent_obj, addr, buf, size);
}
static int nvme_check_sqid(NvmeCtrl *n, uint16_t sqid)
@@ -228,7 +228,11 @@ static uint16_t nvme_map_prp(NvmeCtrl *n, QEMUSGList *qsg, uint64_t prp1,
nents = (len + n->page_size - 1) >> n->page_bits;
prp_trans = MIN(n->max_prp_ents, nents) * sizeof(uint64_t);
- nvme_addr_read(n, prp2, (void *) prp_list, prp_trans);
+ if (nvme_addr_read(n, prp2, (void *) prp_list, prp_trans)) {
+ trace_nvme_err_addr_read((void *) prp2);
+ status = NVME_DATA_TRANSFER_ERROR;
+ goto unmap;
+ }
while (len != 0) {
bool addr_is_cmb;
uint64_t prp_ent = le64_to_cpu(prp_list[i]);
@@ -250,7 +254,11 @@ static uint16_t nvme_map_prp(NvmeCtrl *n, QEMUSGList *qsg, uint64_t prp1,
i = 0;
nents = (len + n->page_size - 1) >> n->page_bits;
prp_trans = MIN(n->max_prp_ents, nents) * sizeof(uint64_t);
- nvme_addr_read(n, prp_ent, (void *) prp_list, prp_trans);
+ if (nvme_addr_read(n, prp_ent, (void *) prp_list, prp_trans)) {
+ trace_nvme_err_addr_read((void *) prp_ent);
+ status = NVME_DATA_TRANSFER_ERROR;
+ goto unmap;
+ }
prp_ent = le64_to_cpu(prp_list[i]);
}
@@ -402,7 +410,11 @@ static uint16_t nvme_map_sgl(NvmeCtrl *n, QEMUSGList *qsg,
/* read the segment in chunks of 256 descriptors (4k) */
while (nsgld > MAX_NSGLD) {
- nvme_addr_read(n, addr, segment, sizeof(segment));
+ if (nvme_addr_read(n, addr, segment, sizeof(segment))) {
+ trace_nvme_err_addr_read((void *) addr);
+ status = NVME_DATA_TRANSFER_ERROR;
+ goto unmap;
+ }
status = nvme_map_sgl_data(n, qsg, segment, MAX_NSGLD, &len, req);
if (status) {
@@ -413,7 +425,11 @@ static uint16_t nvme_map_sgl(NvmeCtrl *n, QEMUSGList *qsg,
addr += MAX_NSGLD * sizeof(NvmeSglDescriptor);
}
- nvme_addr_read(n, addr, segment, nsgld * sizeof(NvmeSglDescriptor));
+ if (nvme_addr_read(n, addr, segment, nsgld * sizeof(NvmeSglDescriptor))) {
+ trace_nvme_err_addr_read((void *) addr);
+ status = NVME_DATA_TRANSFER_ERROR;
+ goto unmap;
+ }
sgl = segment[nsgld - 1];
addr = le64_to_cpu(sgl.addr);
@@ -458,7 +474,11 @@ static uint16_t nvme_map_sgl(NvmeCtrl *n, QEMUSGList *qsg,
nsgld = le64_to_cpu(sgl.len) / sizeof(NvmeSglDescriptor);
while (nsgld > MAX_NSGLD) {
- nvme_addr_read(n, addr, segment, sizeof(segment));
+ if (nvme_addr_read(n, addr, segment, sizeof(segment))) {
+ trace_nvme_err_addr_read((void *) addr);
+ status = NVME_DATA_TRANSFER_ERROR;
+ goto unmap;
+ }
status = nvme_map_sgl_data(n, qsg, segment, MAX_NSGLD, &len, req);
if (status) {
@@ -469,7 +489,11 @@ static uint16_t nvme_map_sgl(NvmeCtrl *n, QEMUSGList *qsg,
addr += MAX_NSGLD * sizeof(NvmeSglDescriptor);
}
- nvme_addr_read(n, addr, segment, nsgld * sizeof(NvmeSglDescriptor));
+ if (nvme_addr_read(n, addr, segment, nsgld * sizeof(NvmeSglDescriptor))) {
+ trace_nvme_err_addr_read((void *) addr);
+ status = NVME_DATA_TRANSFER_ERROR;
+ goto unmap;
+ }
status = nvme_map_sgl_data(n, qsg, segment, nsgld, &len, req);
if (status) {
@@ -819,8 +843,14 @@ static void nvme_post_cqes(void *opaque)
req->cqe.sq_id = cpu_to_le16(sq->sqid);
req->cqe.sq_head = cpu_to_le16(sq->head);
addr = cq->dma_addr + cq->tail * n->cqe_size;
+ if (nvme_addr_write(n, addr, (void *) cqe, sizeof(*cqe))) {
+ trace_nvme_err_addr_write((void *) addr);
+ QTAILQ_INSERT_TAIL(&cq->req_list, req, entry);
+ timer_mod(cq->timer, qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) +
+ 100 * SCALE_MS);
+ break;
+ }
nvme_inc_cq_tail(cq);
- nvme_addr_write(n, addr, (void *) cqe, sizeof(*cqe));
QTAILQ_INSERT_TAIL(&sq->req_list, req, entry);
}
if (cq->tail != cq->head) {
@@ -1937,7 +1967,12 @@ static void nvme_process_sq(void *opaque)
while (!(nvme_sq_empty(sq) || QTAILQ_EMPTY(&sq->req_list))) {
addr = sq->dma_addr + sq->head * n->sqe_size;
- nvme_addr_read(n, addr, (void *)&cmd, sizeof(NvmeCmd));
+ if (nvme_addr_read(n, addr, (void *)&cmd, sizeof(NvmeCmd))) {
+ trace_nvme_err_addr_read((void *) addr);
+ timer_mod(sq->timer, qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) +
+ 100 * SCALE_MS);
+ break;
+ }
nvme_inc_sq_head(sq);
req = QTAILQ_FIRST(&sq->req_list);
diff --git a/hw/block/trace-events b/hw/block/trace-events
index 95c24f514754..54aa001bf52d 100644
--- a/hw/block/trace-events
+++ b/hw/block/trace-events
@@ -84,6 +84,8 @@ nvme_mmio_shutdown_cleared(void) "shutdown bit cleared"
nvme_err_mdts(uint16_t cid, size_t mdts, size_t len) "cid %"PRIu16" mdts %"PRIu64" len %"PRIu64""
nvme_err_prinfo(uint16_t cid, uint16_t ctrl) "cid %"PRIu16" ctrl %"PRIu16""
nvme_err_aio(uint16_t cid, void *aio, const char *blkname, uint64_t offset, const char *opc, void *req, uint16_t status) "cid %"PRIu16" aio %p blk \"%s\" offset %"PRIu64" opc \"%s\" req %p status 0x%"PRIx16""
+nvme_err_addr_read(void *addr) "addr %p"
+nvme_err_addr_write(void *addr) "addr %p"
nvme_err_invalid_sgl_descriptor(uint16_t cid, uint8_t typ) "cid %"PRIu16" type 0x%"PRIx8""
nvme_err_invalid_sgl_excess_length(uint16_t cid) "cid %"PRIu16""
nvme_err_invalid_dma(void) "PRP/SGL is too small for transfer size"
diff --git a/include/block/nvme.h b/include/block/nvme.h
index ba0a9d4e328f..5a2075e739ee 100644
--- a/include/block/nvme.h
+++ b/include/block/nvme.h
@@ -459,7 +459,7 @@ enum NvmeStatusCodes {
NVME_INVALID_OPCODE = 0x0001,
NVME_INVALID_FIELD = 0x0002,
NVME_CID_CONFLICT = 0x0003,
- NVME_DATA_TRAS_ERROR = 0x0004,
+ NVME_DATA_TRANSFER_ERROR = 0x0004,
NVME_POWER_LOSS_ABORT = 0x0005,
NVME_INTERNAL_DEV_ERROR = 0x0006,
NVME_CMD_ABORT_REQ = 0x0007,
--
2.23.0
^ permalink raw reply related [flat|nested] 52+ messages in thread* Re: [PATCH v2 00/20] nvme: support NVMe v1.3d, SGLs and multiple namespaces
2019-10-15 10:38 [PATCH v2 00/20] nvme: support NVMe v1.3d, SGLs and multiple namespaces Klaus Jensen
` (19 preceding siblings ...)
2019-10-15 10:39 ` [PATCH v2 20/20] nvme: handle dma errors Klaus Jensen
@ 2019-10-15 17:19 ` no-reply
2019-10-15 17:26 ` no-reply
` (2 subsequent siblings)
23 siblings, 0 replies; 52+ messages in thread
From: no-reply @ 2019-10-15 17:19 UTC (permalink / raw)
To: its
Cc: kwolf, fam, javier, qemu-block, qemu-devel, mreitz, keith.busch,
Paul.Durrant, sbates
Patchew URL: https://patchew.org/QEMU/20191015103900.313928-1-its@irrelevant.dk/
Hi,
This series failed the docker-mingw@fedora build test. Please find the testing commands and
their output below. If you have Docker installed, you can probably reproduce it
locally.
=== TEST SCRIPT BEGIN ===
#! /bin/bash
export ARCH=x86_64
make docker-image-fedora V=1 NETWORK=1
time make docker-test-mingw@fedora J=14 NETWORK=1
=== TEST SCRIPT END ===
CC hw/misc/imx7_gpr.o
CC hw/misc/mst_fpga.o
/tmp/qemu-test/src/hw/block/nvme.c: In function 'nvme_map_prp':
/tmp/qemu-test/src/hw/block/nvme.c:232:42: error: cast to pointer from integer of different size [-Werror=int-to-pointer-cast]
trace_nvme_err_addr_read((void *) prp2);
^
/tmp/qemu-test/src/hw/block/nvme.c:258:50: error: cast to pointer from integer of different size [-Werror=int-to-pointer-cast]
trace_nvme_err_addr_read((void *) prp_ent);
^
/tmp/qemu-test/src/hw/block/nvme.c: In function 'nvme_map_sgl':
/tmp/qemu-test/src/hw/block/nvme.c:414:42: error: cast to pointer from integer of different size [-Werror=int-to-pointer-cast]
trace_nvme_err_addr_read((void *) addr);
^
/tmp/qemu-test/src/hw/block/nvme.c:429:38: error: cast to pointer from integer of different size [-Werror=int-to-pointer-cast]
trace_nvme_err_addr_read((void *) addr);
^
/tmp/qemu-test/src/hw/block/nvme.c:478:38: error: cast to pointer from integer of different size [-Werror=int-to-pointer-cast]
trace_nvme_err_addr_read((void *) addr);
^
/tmp/qemu-test/src/hw/block/nvme.c:493:34: error: cast to pointer from integer of different size [-Werror=int-to-pointer-cast]
trace_nvme_err_addr_read((void *) addr);
^
/tmp/qemu-test/src/hw/block/nvme.c: In function 'nvme_post_cqes':
/tmp/qemu-test/src/hw/block/nvme.c:847:39: error: cast to pointer from integer of different size [-Werror=int-to-pointer-cast]
trace_nvme_err_addr_write((void *) addr);
^
/tmp/qemu-test/src/hw/block/nvme.c: In function 'nvme_process_sq':
/tmp/qemu-test/src/hw/block/nvme.c:1971:38: error: cast to pointer from integer of different size [-Werror=int-to-pointer-cast]
trace_nvme_err_addr_read((void *) addr);
^
cc1: all warnings being treated as errors
make: *** [/tmp/qemu-test/src/rules.mak:69: hw/block/nvme.o] Error 1
make: *** Waiting for unfinished jobs....
Traceback (most recent call last):
File "./tests/docker/docker.py", line 662, in <module>
---
raise CalledProcessError(retcode, cmd)
subprocess.CalledProcessError: Command '['sudo', '-n', 'docker', 'run', '--label', 'com.qemu.instance.uuid=8aa0a85fff1f457c9dc7c826d7b3189d', '-u', '1001', '--security-opt', 'seccomp=unconfined', '--rm', '-e', 'TARGET_LIST=', '-e', 'EXTRA_CONFIGURE_OPTS=', '-e', 'V=', '-e', 'J=14', '-e', 'DEBUG=', '-e', 'SHOW_ENV=', '-e', 'CCACHE_DIR=/var/tmp/ccache', '-v', '/home/patchew/.cache/qemu-docker-ccache:/var/tmp/ccache:z', '-v', '/var/tmp/patchew-tester-tmp-2g1bl41s/src/docker-src.2019-10-15-13.13.48.993:/var/tmp/qemu:z,ro', 'qemu:fedora', '/var/tmp/qemu/run', 'test-mingw']' returned non-zero exit status 2.
filter=--filter=label=com.qemu.instance.uuid=8aa0a85fff1f457c9dc7c826d7b3189d
make[1]: *** [docker-run] Error 1
make[1]: Leaving directory `/var/tmp/patchew-tester-tmp-2g1bl41s/src'
make: *** [docker-run-test-mingw@fedora] Error 2
real 5m56.522s
user 0m7.913s
The full log is available at
http://patchew.org/logs/20191015103900.313928-1-its@irrelevant.dk/testing.docker-mingw@fedora/?type=message.
---
Email generated automatically by Patchew [https://patchew.org/].
Please send your feedback to patchew-devel@redhat.com
^ permalink raw reply [flat|nested] 52+ messages in thread* Re: [PATCH v2 00/20] nvme: support NVMe v1.3d, SGLs and multiple namespaces
2019-10-15 10:38 [PATCH v2 00/20] nvme: support NVMe v1.3d, SGLs and multiple namespaces Klaus Jensen
` (20 preceding siblings ...)
2019-10-15 17:19 ` [PATCH v2 00/20] nvme: support NVMe v1.3d, SGLs and multiple namespaces no-reply
@ 2019-10-15 17:26 ` no-reply
2019-10-16 6:29 ` Fam Zheng
2019-10-28 6:09 ` Klaus Birkelund
23 siblings, 0 replies; 52+ messages in thread
From: no-reply @ 2019-10-15 17:26 UTC (permalink / raw)
To: its
Cc: kwolf, fam, javier, qemu-block, qemu-devel, mreitz, keith.busch,
Paul.Durrant, sbates
Patchew URL: https://patchew.org/QEMU/20191015103900.313928-1-its@irrelevant.dk/
Hi,
This series seems to have some coding style problems. See output below for
more information:
Subject: [PATCH v2 00/20] nvme: support NVMe v1.3d, SGLs and multiple namespaces
Type: series
Message-id: 20191015103900.313928-1-its@irrelevant.dk
=== 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 ===
Switched to a new branch 'test'
c68f7e0 nvme: handle dma errors
855f2b8 nvme: make lba data size configurable
68fc575 nvme: remove redundant NvmeCmd pointer parameter
eb585d1 nvme: bump controller pci device id
227280c nvme: support multiple namespaces
ccc877b nvme: add support for scatter gather lists
76d6fe6 nvme: allow multiple aios per command
73227cb nvme: refactor prp mapping
df5fd9f nvme: bump supported specification version to 1.3
c85c0ff nvme: add missing mandatory features
1188552 nvme: add logging to error information log page
714808c nvme: add support for the asynchronous event request command
88bdfce nvme: add support for the get log page command
7716649 nvme: refactor device realization
7d2d51e nvme: add support for the abort command
4ec0e81 nvme: allow completion queues in the cmb
68f00db nvme: populate the mandatory subnqn and ver fields
f08d66a nvme: add missing fields in the identify controller data structure
315a6eb nvme: move device parameters to separate struct
b94cf4a nvme: remove superfluous breaks
=== OUTPUT BEGIN ===
1/20 Checking commit b94cf4aea07b (nvme: remove superfluous breaks)
2/20 Checking commit 315a6eb1f09f (nvme: move device parameters to separate struct)
ERROR: Macros with complex values should be enclosed in parenthesis
#177: 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 2/20 has style problems, please review. If any of these errors
are false positives report them to the maintainer, see
CHECKPATCH in MAINTAINERS.
3/20 Checking commit f08d66aa761b (nvme: add missing fields in the identify controller data structure)
4/20 Checking commit 68f00db57e87 (nvme: populate the mandatory subnqn and ver fields)
5/20 Checking commit 4ec0e81a8ca5 (nvme: allow completion queues in the cmb)
6/20 Checking commit 7d2d51e5da89 (nvme: add support for the abort command)
7/20 Checking commit 7716649c3d6d (nvme: refactor device realization)
8/20 Checking commit 88bdfce1a599 (nvme: add support for the get log page command)
9/20 Checking commit 714808cd3ef8 (nvme: add support for the asynchronous event request command)
10/20 Checking commit 11885522fa87 (nvme: add logging to error information log page)
11/20 Checking commit c85c0ff5ea35 (nvme: add missing mandatory features)
12/20 Checking commit df5fd9f283a4 (nvme: bump supported specification version to 1.3)
13/20 Checking commit 73227cb3c83c (nvme: refactor prp mapping)
14/20 Checking commit 76d6fe6ea1cf (nvme: allow multiple aios per command)
15/20 Checking commit ccc877b6f72b (nvme: add support for scatter gather lists)
16/20 Checking commit 227280c8d08c (nvme: support multiple namespaces)
WARNING: added, moved or deleted file(s), does MAINTAINERS need updating?
#42:
new file mode 100644
total: 0 errors, 1 warnings, 801 lines checked
Patch 16/20 has style problems, please review. If any of these errors
are false positives report them to the maintainer, see
CHECKPATCH in MAINTAINERS.
17/20 Checking commit eb585d1231e3 (nvme: bump controller pci device id)
18/20 Checking commit 68fc575b3fc7 (nvme: remove redundant NvmeCmd pointer parameter)
19/20 Checking commit 855f2b86dd6c (nvme: make lba data size configurable)
20/20 Checking commit c68f7e0d0c55 (nvme: handle dma errors)
WARNING: line over 80 characters
#77: FILE: hw/block/nvme.c:257:
+ if (nvme_addr_read(n, prp_ent, (void *) prp_list, prp_trans)) {
WARNING: line over 80 characters
#103: FILE: hw/block/nvme.c:428:
+ if (nvme_addr_read(n, addr, segment, nsgld * sizeof(NvmeSglDescriptor))) {
total: 0 errors, 2 warnings, 148 lines checked
Patch 20/20 has style problems, please review. If any of these errors
are false positives report them to the maintainer, see
CHECKPATCH in MAINTAINERS.
=== OUTPUT END ===
Test command exited with code: 1
The full log is available at
http://patchew.org/logs/20191015103900.313928-1-its@irrelevant.dk/testing.checkpatch/?type=message.
---
Email generated automatically by Patchew [https://patchew.org/].
Please send your feedback to patchew-devel@redhat.com
^ permalink raw reply [flat|nested] 52+ messages in thread* Re: [PATCH v2 00/20] nvme: support NVMe v1.3d, SGLs and multiple namespaces
2019-10-15 10:38 [PATCH v2 00/20] nvme: support NVMe v1.3d, SGLs and multiple namespaces Klaus Jensen
` (21 preceding siblings ...)
2019-10-15 17:26 ` no-reply
@ 2019-10-16 6:29 ` Fam Zheng
2019-10-28 6:09 ` Klaus Birkelund
23 siblings, 0 replies; 52+ messages in thread
From: Fam Zheng @ 2019-10-16 6:29 UTC (permalink / raw)
To: Klaus Jensen
Cc: Kevin Wolf, Javier Gonzalez, qemu-block, qemu-devel, Max Reitz,
Keith Busch, Paul Durrant, Stephen Bates
On Tue, 10/15 12:38, Klaus Jensen wrote:
> Hi,
>
> (Quick note to Fam): most of this series is irrelevant to you as the
> maintainer of the nvme block driver, but patch "nvme: add support for
> scatter gather lists" touches block/nvme.c due to changes in the shared
> NvmeCmd struct.
Yeah, that part looks sane to me. For the block/nvme.c bit:
Acked-by: Fam Zheng <fam@euphon.net>
^ permalink raw reply [flat|nested] 52+ messages in thread* Re: [PATCH v2 00/20] nvme: support NVMe v1.3d, SGLs and multiple namespaces
2019-10-15 10:38 [PATCH v2 00/20] nvme: support NVMe v1.3d, SGLs and multiple namespaces Klaus Jensen
` (22 preceding siblings ...)
2019-10-16 6:29 ` Fam Zheng
@ 2019-10-28 6:09 ` Klaus Birkelund
23 siblings, 0 replies; 52+ messages in thread
From: Klaus Birkelund @ 2019-10-28 6:09 UTC (permalink / raw)
To: qemu-block
Cc: Kevin Wolf, Fam Zheng, Javier Gonzalez, qemu-devel, Max Reitz,
Paul Durrant, Keith Busch, Stephen Bates
On Tue, Oct 15, 2019 at 12:38:40PM +0200, Klaus Jensen wrote:
> Hi,
>
> (Quick note to Fam): most of this series is irrelevant to you as the
> maintainer of the nvme block driver, but patch "nvme: add support for
> scatter gather lists" touches block/nvme.c due to changes in the shared
> NvmeCmd struct.
>
> Anyway, v2 comes with a good bunch of changes. Compared to v1[1], I have
> squashed some commits in the beginning of the series and heavily
> refactored "nvme: support multiple block requests per request" into the
> new commit "nvme: allow multiple aios per command".
>
> I have also removed the original implementation of the Abort command
> (commit "nvme: add support for the abort command") as it is currently
> too tricky to test reliably. It has been replaced by a stub that,
> besides a trivial sanity check, just fails to abort the given command.
> *Some* implementation of the Abort command is mandatory, but given the
> "best effort" nature of the command this is acceptable for now. When the
> device gains support for arbitration it should be less tricky to test.
>
> The support for multiple namespaces is now backwards compatible. The
> nvme device still accepts a 'drive' parameter, but for multiple
> namespaces the use of 'nvme-ns' devices are required. I also integrated
> some feedback from Paul so the device supports non-consecutive namespace
> ids.
>
> I have also added some new commits at the end:
>
> - "nvme: bump controller pci device id" makes sure the Linux kernel
> doesn't apply any quirks to the controller that it no longer has.
> - "nvme: handle dma errors" won't actually do anything before this[2]
> fix to include/hw/pci/pci.h is merged. With these two patches added,
> the device reliably passes some additional nasty tests from blktests
> (block/011 "disable PCI device while doing I/O" and block/019 "break
> PCI link device while doing I/O"). Before this patch, block/011
> would pass from time to time if you were lucky, but would at least
> mess up the controller pretty badly, causing a reset in the best
> case.
>
>
> [1]: https://patchwork.kernel.org/project/qemu-devel/list/?series=142383
> [2]: https://patchwork.kernel.org/patch/11184911/
>
>
> Klaus Jensen (20):
> nvme: remove superfluous breaks
> nvme: move device parameters to separate struct
> nvme: add missing fields in the identify controller data structure
> nvme: populate the mandatory subnqn and ver fields
> nvme: allow completion queues in the cmb
> nvme: add support for the abort command
> nvme: refactor device realization
> nvme: add support for the get log page command
> nvme: add support for the asynchronous event request command
> nvme: add logging to error information log page
> nvme: add missing mandatory features
> nvme: bump supported specification version to 1.3
> nvme: refactor prp mapping
> nvme: allow multiple aios per command
> nvme: add support for scatter gather lists
> nvme: support multiple namespaces
> nvme: bump controller pci device id
> nvme: remove redundant NvmeCmd pointer parameter
> nvme: make lba data size configurable
> nvme: handle dma errors
>
> block/nvme.c | 18 +-
> hw/block/Makefile.objs | 2 +-
> hw/block/nvme-ns.c | 139 +++
> hw/block/nvme-ns.h | 60 ++
> hw/block/nvme.c | 1863 +++++++++++++++++++++++++++++++++-------
> hw/block/nvme.h | 219 ++++-
> hw/block/trace-events | 37 +-
> include/block/nvme.h | 132 ++-
> 8 files changed, 2094 insertions(+), 376 deletions(-)
> create mode 100644 hw/block/nvme-ns.c
> create mode 100644 hw/block/nvme-ns.h
>
> --
> 2.23.0
>
Gentle ping on this.
I'm aware that this is a lot to go through, but I would like to know if
anyone has had a chance to look at it?
https://patchwork.kernel.org/project/qemu-devel/list/?series=187637
^ permalink raw reply [flat|nested] 52+ messages in thread