qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: Dmitry Fomichev <dmitry.fomichev@wdc.com>
To: "Keith Busch" <kbusch@kernel.org>,
	"Klaus Jensen" <k.jensen@samsung.com>,
	"Kevin Wolf" <kwolf@redhat.com>,
	"Philippe Mathieu-Daudé" <philmd@redhat.com>,
	"Maxim Levitsky" <mlevitsk@redhat.com>,
	"Fam Zheng" <fam@euphon.net>
Cc: Niklas Cassel <niklas.cassel@wdc.com>,
	Damien Le Moal <damien.lemoal@wdc.com>,
	qemu-block@nongnu.org, Dmitry Fomichev <dmitry.fomichev@wdc.com>,
	qemu-devel@nongnu.org,
	Alistair Francis <alistair.francis@wdc.com>,
	Matias Bjorling <matias.bjorling@wdc.com>
Subject: [PATCH v7 10/11] hw/block/nvme: Separate read and write handlers
Date: Mon, 19 Oct 2020 11:17:25 +0900	[thread overview]
Message-ID: <20201019021726.12048-11-dmitry.fomichev@wdc.com> (raw)
In-Reply-To: <20201019021726.12048-1-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>
---
 hw/block/nvme.c       | 191 +++++++++++++++++++++++++-----------------
 hw/block/trace-events |   3 +-
 2 files changed, 114 insertions(+), 80 deletions(-)

diff --git a/hw/block/nvme.c b/hw/block/nvme.c
index 3b9ea326d7..5ec4ce5e28 100644
--- a/hw/block/nvme.c
+++ b/hw/block/nvme.c
@@ -1162,10 +1162,10 @@ typedef struct NvmeReadFillCtx {
     uint32_t  post_rd_fill_nlb;
 } NvmeReadFillCtx;
 
-static uint16_t nvme_check_zone_read(NvmeNamespace *ns, NvmeZone *zone,
-                                     uint64_t slba, uint32_t nlb,
-                                     NvmeReadFillCtx *rfc)
+static uint16_t nvme_check_zone_read(NvmeNamespace *ns, uint64_t slba,
+                                     uint32_t nlb, NvmeReadFillCtx *rfc)
 {
+    NvmeZone *zone = nvme_get_zone_by_slba(ns, slba);
     NvmeZone *next_zone;
     uint64_t bndry = nvme_zone_rd_boundary(ns, zone);
     uint64_t end = slba + nlb, wp1, wp2;
@@ -1449,6 +1449,86 @@ 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;
+    uint32_t fill_len;
+    uint64_t data_size = nvme_l2b(ns, nlb);
+    uint64_t data_offset, fill_ofs;
+    NvmeReadFillCtx rfc;
+    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(n, ns, slba, nlb);
+    if (status) {
+        trace_pci_nvme_err_invalid_lba_range(slba, nlb, ns->id_ns.nsze);
+        goto invalid;
+    }
+
+    if (ns->params.zoned) {
+        status = nvme_check_zone_read(ns, slba, nlb, &rfc);
+        if (status != NVME_SUCCESS) {
+            trace_pci_nvme_err_zone_read_not_ok(slba, nlb, status);
+            goto invalid;
+        }
+    }
+
+    status = nvme_map_dptr(n, data_size, req);
+    if (status) {
+        goto invalid;
+    }
+
+    if (ns->params.zoned) {
+        if (rfc.pre_rd_fill_nlb) {
+            fill_ofs = nvme_l2b(ns, rfc.pre_rd_fill_slba - slba);
+            fill_len = nvme_l2b(ns, rfc.pre_rd_fill_nlb);
+            nvme_fill_read_data(req, fill_ofs, fill_len,
+                                n->params.fill_pattern);
+        }
+        if (!rfc.read_nlb) {
+            /* No backend I/O necessary, only needed to fill the buffer */
+            req->status = NVME_SUCCESS;
+            return NVME_SUCCESS;
+        }
+        if (rfc.post_rd_fill_nlb) {
+            req->fill_ofs = nvme_l2b(ns, rfc.post_rd_fill_slba - slba);
+            req->fill_len = nvme_l2b(ns, rfc.post_rd_fill_nlb);
+        } else {
+            req->fill_len = 0;
+        }
+        slba = rfc.read_slba;
+        data_size = nvme_l2b(ns, rfc.read_nlb);
+    }
+
+    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 | NVME_DNR;
+}
+
 static uint16_t nvme_write_zeroes(NvmeCtrl *n, NvmeRequest *req)
 {
     NvmeRwCmd *rw = (NvmeRwCmd *)&req->cmd;
@@ -1495,25 +1575,20 @@ invalid:
     return status | NVME_DNR;
 }
 
-static uint16_t nvme_rw(NvmeCtrl *n, NvmeRequest *req, bool append)
+static uint16_t nvme_write(NvmeCtrl *n, NvmeRequest *req, bool append)
 {
     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, fill_ofs;
-
+    uint64_t data_offset;
     NvmeZone *zone;
-    uint32_t fill_len;
-    NvmeReadFillCtx rfc;
-    bool is_write = rw->opcode == NVME_CMD_WRITE || append;
-    enum BlockAcctType acct = is_write ? BLOCK_ACCT_WRITE : BLOCK_ACCT_READ;
     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) {
@@ -1530,29 +1605,21 @@ static uint16_t nvme_rw(NvmeCtrl *n, NvmeRequest *req, bool append)
     if (ns->params.zoned) {
         zone = nvme_get_zone_by_slba(ns, slba);
 
-        if (is_write) {
-            status = nvme_check_zone_write(n, ns, zone, slba, nlb, append);
-            if (status != NVME_SUCCESS) {
-                goto invalid;
-            }
-
-            if (append) {
-                slba = zone->w_ptr;
-            }
-
-            status = nvme_auto_open_zone(ns, zone);
-            if (status != NVME_SUCCESS) {
-                goto invalid;
-            }
-
-            req->cqe.result64 = nvme_advance_zone_wp(ns, zone, nlb);
-        } else {
-            status = nvme_check_zone_read(ns, zone, slba, nlb, &rfc);
-            if (status != NVME_SUCCESS) {
-                trace_pci_nvme_err_zone_read_not_ok(slba, nlb, status);
-                goto invalid;
-            }
+        status = nvme_check_zone_write(n, ns, zone, slba, nlb, append);
+        if (status != NVME_SUCCESS) {
+            goto invalid;
         }
+
+        status = nvme_auto_open_zone(ns, zone);
+        if (status != NVME_SUCCESS) {
+            goto invalid;
+        }
+
+        if (append) {
+            slba = zone->w_ptr;
+        }
+
+        req->cqe.result64 = nvme_advance_zone_wp(ns, zone, nlb);
     } else if (append) {
         trace_pci_nvme_err_invalid_opc(rw->opcode);
         status = NVME_INVALID_OPCODE;
@@ -1566,56 +1633,21 @@ static uint16_t nvme_rw(NvmeCtrl *n, NvmeRequest *req, bool append)
         goto invalid;
     }
 
-    if (ns->params.zoned) {
-        if (is_write) {
-            req->cqe.result64 = nvme_advance_zone_wp(ns, zone, nlb);
-        } else {
-            if (rfc.pre_rd_fill_nlb) {
-                fill_ofs = nvme_l2b(ns, rfc.pre_rd_fill_slba - slba);
-                fill_len = nvme_l2b(ns, rfc.pre_rd_fill_nlb);
-                nvme_fill_read_data(req, fill_ofs, fill_len,
-                                    n->params.fill_pattern);
-            }
-            if (!rfc.read_nlb) {
-                /* No backend I/O necessary, only needed to fill the buffer */
-                req->status = NVME_SUCCESS;
-                return NVME_SUCCESS;
-            }
-            if (rfc.post_rd_fill_nlb) {
-                req->fill_ofs = nvme_l2b(ns, rfc.post_rd_fill_slba - slba);
-                req->fill_len = nvme_l2b(ns, rfc.post_rd_fill_nlb);
-            } else {
-                req->fill_len = 0;
-            }
-            slba = rfc.read_slba;
-            data_size = nvme_l2b(ns, rfc.read_nlb);
-        }
-    }
-
     data_offset = nvme_l2b(ns, slba);
 
-    block_acct_start(blk_get_stats(blk), &req->acct, data_size, acct);
+    block_acct_start(blk_get_stats(blk), &req->acct, data_size,
+                     BLOCK_ACCT_WRITE);
     if (req->qsg.sg) {
-        if (is_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 (is_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(blk), acct);
+    block_acct_invalid(blk_get_stats(blk), BLOCK_ACCT_WRITE);
     return status | NVME_DNR;
 }
 
@@ -2096,10 +2128,11 @@ static uint16_t nvme_io_cmd(NvmeCtrl *n, NvmeRequest *req)
     case NVME_CMD_WRITE_ZEROES:
         return nvme_write_zeroes(n, req);
     case NVME_CMD_ZONE_APPEND:
-        return nvme_rw(n, req, true);
+        return nvme_write(n, req, true);
     case NVME_CMD_WRITE:
+        return nvme_write(n, req, false);
     case NVME_CMD_READ:
-        return nvme_rw(n, req, false);
+        return nvme_read(n, req);
     case NVME_CMD_ZONE_MGMT_SEND:
         return nvme_zone_mgmt_send(n, req);
     case NVME_CMD_ZONE_MGMT_RECV:
diff --git a/hw/block/trace-events b/hw/block/trace-events
index 962084e40c..7ee90a50c3 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_write_zeroes(uint16_t cid, uint32_t nsid, uint64_t slba, uint32_t nlb) "cid %"PRIu16" nsid %"PRIu32" slba %"PRIu64" nlb %"PRIu32""
 pci_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""
-- 
2.21.0



  parent reply	other threads:[~2020-10-19  2:27 UTC|newest]

Thread overview: 36+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-10-19  2:17 [PATCH v7 00/11] hw/block/nvme: Support Namespace Types and Zoned Namespace Command Set Dmitry Fomichev
2020-10-19  2:17 ` [PATCH v7 01/11] hw/block/nvme: Add Commands Supported and Effects log Dmitry Fomichev
2020-10-19 19:22   ` Keith Busch
2020-10-19 20:16   ` Klaus Jensen
2020-10-20 23:04     ` Dmitry Fomichev
2020-10-19  2:17 ` [PATCH v7 02/11] hw/block/nvme: Generate namespace UUIDs Dmitry Fomichev
2020-10-19 19:24   ` Keith Busch
2020-10-19 19:30   ` Klaus Jensen
2020-10-19  2:17 ` [PATCH v7 03/11] hw/block/nvme: Add support for Namespace Types Dmitry Fomichev
2020-10-19 19:51   ` Keith Busch
2020-10-19 20:53   ` Klaus Jensen
2020-10-21  1:50     ` Dmitry Fomichev
2020-10-19  2:17 ` [PATCH v7 04/11] hw/block/nvme: Support allocated CNS command variants Dmitry Fomichev
2020-10-19 20:07   ` Keith Busch
2020-10-20  8:21   ` Klaus Jensen
2020-10-20 23:09     ` Dmitry Fomichev
2020-10-19  2:17 ` [PATCH v7 05/11] hw/block/nvme: Support Zoned Namespace Command Set Dmitry Fomichev
2020-10-19  9:50   ` Klaus Jensen
2020-10-19 15:55     ` Klaus Jensen
2020-10-19 12:33   ` Klaus Jensen
2020-10-20 11:08   ` Klaus Jensen
2020-10-21 10:26   ` Klaus Jensen
2020-10-21 23:19     ` Dmitry Fomichev
2020-10-19  2:17 ` [PATCH v7 06/11] hw/block/nvme: Introduce max active and open zone limits Dmitry Fomichev
2020-10-19  2:17 ` [PATCH v7 07/11] hw/block/nvme: Support Zone Descriptor Extensions Dmitry Fomichev
2020-10-19  2:17 ` [PATCH v7 08/11] hw/block/nvme: Add injection of Offline/Read-Only zones Dmitry Fomichev
2020-10-19 11:42   ` Klaus Jensen
2020-10-20 23:01     ` Dmitry Fomichev
2020-10-19  2:17 ` [PATCH v7 09/11] hw/block/nvme: Document zoned parameters in usage text Dmitry Fomichev
2020-10-19  2:17 ` Dmitry Fomichev [this message]
2020-10-20  8:28   ` [PATCH v7 10/11] hw/block/nvme: Separate read and write handlers Klaus Jensen
2020-10-20 12:36     ` Keith Busch
2020-10-20 23:05       ` Dmitry Fomichev
2020-10-19  2:17 ` [PATCH v7 11/11] hw/block/nvme: Merge nvme_write_zeroes() with nvme_write() Dmitry Fomichev
2020-10-20  8:29   ` Klaus Jensen
2020-10-19  7:32 ` [PATCH v7 00/11] hw/block/nvme: Support Namespace Types and Zoned Namespace Command Set Niklas Cassel

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=20201019021726.12048-11-dmitry.fomichev@wdc.com \
    --to=dmitry.fomichev@wdc.com \
    --cc=alistair.francis@wdc.com \
    --cc=damien.lemoal@wdc.com \
    --cc=fam@euphon.net \
    --cc=k.jensen@samsung.com \
    --cc=kbusch@kernel.org \
    --cc=kwolf@redhat.com \
    --cc=matias.bjorling@wdc.com \
    --cc=mlevitsk@redhat.com \
    --cc=niklas.cassel@wdc.com \
    --cc=philmd@redhat.com \
    --cc=qemu-block@nongnu.org \
    --cc=qemu-devel@nongnu.org \
    /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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).