From: Klaus Jensen <its@irrelevant.dk>
To: qemu-devel@nongnu.org
Cc: Kevin Wolf <kwolf@redhat.com>, Fam Zheng <fam@euphon.net>,
qemu-block@nongnu.org, Niklas Cassel <Niklas.Cassel@wdc.com>,
Dmitry Fomichev <dmitry.fomichev@wdc.com>,
Klaus Jensen <k.jensen@samsung.com>,
Max Reitz <mreitz@redhat.com>, Keith Busch <kbusch@kernel.org>,
Stefan Hajnoczi <stefanha@redhat.com>,
Klaus Jensen <its@irrelevant.dk>
Subject: [PATCH v5 01/12] hw/block/nvme: Separate read and write handlers
Date: Fri, 27 Nov 2020 00:45:50 +0100 [thread overview]
Message-ID: <20201126234601.689714-2-its@irrelevant.dk> (raw)
In-Reply-To: <20201126234601.689714-1-its@irrelevant.dk>
From: Dmitry Fomichev <dmitry.fomichev@wdc.com>
With ZNS support in place, the majority of code in nvme_rw() has
become read- or write-specific. Move these parts to two separate
handlers, nvme_read() and nvme_write() to make the code more
readable and to remove multiple is_write checks that so far existed
in the i/o path.
This is a refactoring patch, no change in functionality.
Signed-off-by: Dmitry Fomichev <dmitry.fomichev@wdc.com>
Reviewed-by: Niklas Cassel <Niklas.Cassel@wdc.com>
[kj: rebased]
Signed-off-by: Klaus Jensen <k.jensen@samsung.com>
---
hw/block/nvme.c | 105 ++++++++++++++++++++++++++++--------------
hw/block/trace-events | 3 +-
2 files changed, 73 insertions(+), 35 deletions(-)
diff --git a/hw/block/nvme.c b/hw/block/nvme.c
index 7ab53cfcf67d..657d0b8b2922 100644
--- a/hw/block/nvme.c
+++ b/hw/block/nvme.c
@@ -1394,6 +1394,61 @@ static uint16_t nvme_flush(NvmeCtrl *n, NvmeRequest *req)
return NVME_NO_COMPLETE;
}
+static uint16_t nvme_read(NvmeCtrl *n, NvmeRequest *req)
+{
+ NvmeRwCmd *rw = (NvmeRwCmd *)&req->cmd;
+ NvmeNamespace *ns = req->ns;
+ uint64_t slba = le64_to_cpu(rw->slba);
+ uint32_t nlb = (uint32_t)le16_to_cpu(rw->nlb) + 1;
+ uint64_t data_size = nvme_l2b(ns, nlb);
+ uint64_t data_offset;
+ BlockBackend *blk = ns->blkconf.blk;
+ uint16_t status;
+
+ trace_pci_nvme_read(nvme_cid(req), nvme_nsid(ns), nlb, data_size, slba);
+
+ status = nvme_check_mdts(n, data_size);
+ if (status) {
+ trace_pci_nvme_err_mdts(nvme_cid(req), data_size);
+ goto invalid;
+ }
+
+ status = nvme_check_bounds(ns, slba, nlb);
+ if (status) {
+ trace_pci_nvme_err_invalid_lba_range(slba, nlb, ns->id_ns.nsze);
+ goto invalid;
+ }
+
+ if (NVME_ERR_REC_DULBE(ns->features.err_rec)) {
+ status = nvme_check_dulbe(ns, slba, nlb);
+ if (status) {
+ goto invalid;
+ }
+ }
+
+ status = nvme_map_dptr(n, data_size, req);
+ if (status) {
+ goto invalid;
+ }
+
+ data_offset = nvme_l2b(ns, slba);
+
+ block_acct_start(blk_get_stats(blk), &req->acct, data_size,
+ BLOCK_ACCT_READ);
+ if (req->qsg.sg) {
+ req->aiocb = dma_blk_read(blk, &req->qsg, data_offset,
+ BDRV_SECTOR_SIZE, nvme_rw_cb, req);
+ } else {
+ req->aiocb = blk_aio_preadv(blk, data_offset, &req->iov, 0,
+ nvme_rw_cb, req);
+ }
+ return NVME_NO_COMPLETE;
+
+invalid:
+ block_acct_invalid(blk_get_stats(blk), BLOCK_ACCT_READ);
+ return status;
+}
+
static uint16_t nvme_write_zeroes(NvmeCtrl *n, NvmeRequest *req)
{
NvmeRwCmd *rw = (NvmeRwCmd *)&req->cmd;
@@ -1419,22 +1474,19 @@ static uint16_t nvme_write_zeroes(NvmeCtrl *n, NvmeRequest *req)
return NVME_NO_COMPLETE;
}
-static uint16_t nvme_rw(NvmeCtrl *n, NvmeRequest *req)
+static uint16_t nvme_write(NvmeCtrl *n, NvmeRequest *req)
{
NvmeRwCmd *rw = (NvmeRwCmd *)&req->cmd;
NvmeNamespace *ns = req->ns;
- uint32_t nlb = (uint32_t)le16_to_cpu(rw->nlb) + 1;
uint64_t slba = le64_to_cpu(rw->slba);
-
+ uint32_t nlb = (uint32_t)le16_to_cpu(rw->nlb) + 1;
uint64_t data_size = nvme_l2b(ns, nlb);
- uint64_t data_offset = nvme_l2b(ns, slba);
- enum BlockAcctType acct = req->cmd.opcode == NVME_CMD_WRITE ?
- BLOCK_ACCT_WRITE : BLOCK_ACCT_READ;
+ uint64_t data_offset;
BlockBackend *blk = ns->blkconf.blk;
uint16_t status;
- trace_pci_nvme_rw(nvme_cid(req), nvme_io_opc_str(rw->opcode),
- nvme_nsid(ns), nlb, data_size, slba);
+ trace_pci_nvme_write(nvme_cid(req), nvme_io_opc_str(rw->opcode),
+ nvme_nsid(ns), nlb, data_size, slba);
status = nvme_check_mdts(n, data_size);
if (status) {
@@ -1448,42 +1500,26 @@ static uint16_t nvme_rw(NvmeCtrl *n, NvmeRequest *req)
goto invalid;
}
- if (acct == BLOCK_ACCT_READ) {
- if (NVME_ERR_REC_DULBE(ns->features.err_rec)) {
- status = nvme_check_dulbe(ns, slba, nlb);
- if (status) {
- goto invalid;
- }
- }
- }
-
status = nvme_map_dptr(n, data_size, req);
if (status) {
goto invalid;
}
- block_acct_start(blk_get_stats(blk), &req->acct, data_size, acct);
+ data_offset = nvme_l2b(ns, slba);
+
+ block_acct_start(blk_get_stats(blk), &req->acct, data_size,
+ BLOCK_ACCT_WRITE);
if (req->qsg.sg) {
- if (acct == BLOCK_ACCT_WRITE) {
- req->aiocb = dma_blk_write(blk, &req->qsg, data_offset,
- BDRV_SECTOR_SIZE, nvme_rw_cb, req);
- } else {
- req->aiocb = dma_blk_read(blk, &req->qsg, data_offset,
- BDRV_SECTOR_SIZE, nvme_rw_cb, req);
- }
+ req->aiocb = dma_blk_write(blk, &req->qsg, data_offset,
+ BDRV_SECTOR_SIZE, nvme_rw_cb, req);
} else {
- if (acct == BLOCK_ACCT_WRITE) {
- req->aiocb = blk_aio_pwritev(blk, data_offset, &req->iov, 0,
- nvme_rw_cb, req);
- } else {
- req->aiocb = blk_aio_preadv(blk, data_offset, &req->iov, 0,
- nvme_rw_cb, req);
- }
+ req->aiocb = blk_aio_pwritev(blk, data_offset, &req->iov, 0,
+ nvme_rw_cb, req);
}
return NVME_NO_COMPLETE;
invalid:
- block_acct_invalid(blk_get_stats(ns->blkconf.blk), acct);
+ block_acct_invalid(blk_get_stats(blk), BLOCK_ACCT_WRITE);
return status;
}
@@ -1513,8 +1549,9 @@ static uint16_t nvme_io_cmd(NvmeCtrl *n, NvmeRequest *req)
case NVME_CMD_WRITE_ZEROES:
return nvme_write_zeroes(n, req);
case NVME_CMD_WRITE:
+ return nvme_write(n, req);
case NVME_CMD_READ:
- return nvme_rw(n, req);
+ return nvme_read(n, req);
case NVME_CMD_COMPARE:
return nvme_compare(n, req);
case NVME_CMD_DSM:
diff --git a/hw/block/trace-events b/hw/block/trace-events
index dd3a0b386ef9..cc269b51a1e0 100644
--- a/hw/block/trace-events
+++ b/hw/block/trace-events
@@ -40,7 +40,8 @@ pci_nvme_map_prp(uint64_t trans_len, uint32_t len, uint64_t prp1, uint64_t prp2,
pci_nvme_map_sgl(uint16_t cid, uint8_t typ, uint64_t len) "cid %"PRIu16" type 0x%"PRIx8" len %"PRIu64""
pci_nvme_io_cmd(uint16_t cid, uint32_t nsid, uint16_t sqid, uint8_t opcode, const char *opname) "cid %"PRIu16" nsid %"PRIu32" sqid %"PRIu16" opc 0x%"PRIx8" opname '%s'"
pci_nvme_admin_cmd(uint16_t cid, uint16_t sqid, uint8_t opcode, const char *opname) "cid %"PRIu16" sqid %"PRIu16" opc 0x%"PRIx8" opname '%s'"
-pci_nvme_rw(uint16_t cid, const char *verb, uint32_t nsid, uint32_t nlb, uint64_t count, uint64_t lba) "cid %"PRIu16" opname '%s' nsid %"PRIu32" nlb %"PRIu32" count %"PRIu64" lba 0x%"PRIx64""
+pci_nvme_read(uint16_t cid, uint32_t nsid, uint32_t nlb, uint64_t count, uint64_t lba) "cid %"PRIu16" nsid %"PRIu32" nlb %"PRIu32" count %"PRIu64" lba 0x%"PRIx64""
+pci_nvme_write(uint16_t cid, const char *verb, uint32_t nsid, uint32_t nlb, uint64_t count, uint64_t lba) "cid %"PRIu16" opname '%s' nsid %"PRIu32" nlb %"PRIu32" count %"PRIu64" lba 0x%"PRIx64""
pci_nvme_rw_cb(uint16_t cid, const char *blkname) "cid %"PRIu16" blk '%s'"
pci_nvme_copy(uint16_t cid, uint32_t nsid, uint16_t nr, uint8_t format) "cid %"PRIu16" nsid %"PRIu32" nr %"PRIu16" format 0x%"PRIx8""
pci_nvme_copy_source_range(uint64_t slba, uint32_t nlb) "slba 0x%"PRIx64" nlb %"PRIu32""
--
2.29.2
next prev parent reply other threads:[~2020-11-26 23:50 UTC|newest]
Thread overview: 17+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-11-26 23:45 [PATCH v5 00/12] hw/block/nvme: zoned namespace command set Klaus Jensen
2020-11-26 23:45 ` Klaus Jensen [this message]
2020-11-26 23:45 ` [PATCH v5 02/12] hw/block/nvme: Merge nvme_write_zeroes() with nvme_write() Klaus Jensen
2020-11-26 23:45 ` [PATCH v5 03/12] hw/block/nvme: add commands supported and effects log page Klaus Jensen
2020-11-26 23:45 ` [PATCH v5 04/12] hw/block/nvme: Generate namespace UUIDs Klaus Jensen
2020-11-26 23:45 ` [PATCH v5 05/12] hw/block/nvme: support namespace types Klaus Jensen
2020-11-26 23:45 ` [PATCH v5 06/12] hw/block/nvme: add basic read/write for zoned namespaces Klaus Jensen
2020-11-26 23:45 ` [PATCH v5 07/12] hw/block/nvme: add the zone management receive command Klaus Jensen
2020-11-26 23:45 ` [PATCH v5 08/12] hw/block/nvme: add the zone management send command Klaus Jensen
2020-11-26 23:45 ` [PATCH v5 09/12] hw/block/nvme: add the zone append command Klaus Jensen
2020-11-26 23:45 ` [PATCH v5 10/12] hw/block/nvme: track and enforce zone resources Klaus Jensen
2020-11-26 23:46 ` [PATCH v5 11/12] hw/block/nvme: allow open to close zone transitions by controller Klaus Jensen
2020-11-26 23:46 ` [PATCH RFC v5 12/12] hw/block/nvme: add persistence for zone info Klaus Jensen
2020-11-30 12:33 ` Stefan Hajnoczi
2020-11-30 12:59 ` Klaus Jensen
2020-11-30 13:18 ` Klaus Jensen
2020-11-30 14:58 ` Stefan Hajnoczi
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20201126234601.689714-2-its@irrelevant.dk \
--to=its@irrelevant.dk \
--cc=Niklas.Cassel@wdc.com \
--cc=dmitry.fomichev@wdc.com \
--cc=fam@euphon.net \
--cc=k.jensen@samsung.com \
--cc=kbusch@kernel.org \
--cc=kwolf@redhat.com \
--cc=mreitz@redhat.com \
--cc=qemu-block@nongnu.org \
--cc=qemu-devel@nongnu.org \
--cc=stefanha@redhat.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.