From nobody Wed Nov 12 00:30:46 2025 Delivered-To: importer@patchew.org Received-SPF: pass (zoho.com: domain of gnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; envelope-from=qemu-devel-bounces+importer=patchew.org@nongnu.org; helo=lists.gnu.org; Authentication-Results: mx.zohomail.com; spf=pass (zoho.com: domain of gnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org; dmarc=fail(p=none dis=none) header.from=redhat.com ARC-Seal: i=1; a=rsa-sha256; t=1566717510; cv=none; d=zoho.com; s=zohoarc; b=Ob+hs+lw9QWrBbKzlm65Ylg8NCT9PdZpqd+jHSn3f5lsqY0AfI3Gib4jxIngfqJwc1S8nr9lNY2Zsw6qQ4Xt4Gn5sqDrbB2KRzLieJToMr1vGKpoQdmMRkQksKTLZ9m4sxjTAgiKz+VWHzBz2iRIb90cbqDhFBKx81Mk1gTBYDQ= ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=zoho.com; s=zohoarc; t=1566717510; h=Cc:Date:From:In-Reply-To:List-Subscribe:List-Post:List-Id:List-Archive:List-Help:List-Unsubscribe:Message-ID:References:Sender:Subject:To:ARC-Authentication-Results; bh=s8r6Tl4f9knDXKAbuadbDh5smDYn+/qe5DBBE4DvJaE=; b=oIa4s5GqXMIIs5L3msMP6uiXwWgocIrx5raZzHj1OA+6Kk3EvhlKafvlmyKQd4m9WlZJEUWhXCKlJ0Wvxwd4NR4q1P/ko+F8u82J34fE8HFqLWFq1w/pfpS9PlCTHiBjrl7YrObgOQmNNUvdEFnp0mYWlhC2kYT6OY7bPMUm4pI= ARC-Authentication-Results: i=1; mx.zoho.com; spf=pass (zoho.com: domain of gnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org; dmarc=fail header.from= (p=none dis=none) header.from= Return-Path: Received: from lists.gnu.org (lists.gnu.org [209.51.188.17]) by mx.zohomail.com with SMTPS id 1566717510031246.65476301278773; Sun, 25 Aug 2019 00:18:30 -0700 (PDT) Received: from localhost ([::1]:41158 helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1i1mn9-0003Bp-N1 for importer@patchew.org; Sun, 25 Aug 2019 03:18:23 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]:60776) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1i1mkl-0001ei-Ib for qemu-devel@nongnu.org; Sun, 25 Aug 2019 03:15:56 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1i1mkk-0003yR-80 for qemu-devel@nongnu.org; Sun, 25 Aug 2019 03:15:55 -0400 Received: from mx1.redhat.com ([209.132.183.28]:37698) by eggs.gnu.org with esmtps (TLS1.0:DHE_RSA_AES_256_CBC_SHA1:32) (Exim 4.71) (envelope-from ) id 1i1mkh-0003wb-83; Sun, 25 Aug 2019 03:15:51 -0400 Received: from smtp.corp.redhat.com (int-mx08.intmail.prod.int.phx2.redhat.com [10.5.11.23]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by mx1.redhat.com (Postfix) with ESMTPS id 91A033083362; Sun, 25 Aug 2019 07:15:50 +0000 (UTC) Received: from maximlenovopc.usersys.redhat.com (unknown [10.35.206.49]) by smtp.corp.redhat.com (Postfix) with ESMTP id 5BFF119C6A; Sun, 25 Aug 2019 07:15:48 +0000 (UTC) From: Maxim Levitsky To: qemu-devel@nongnu.org Date: Sun, 25 Aug 2019 10:15:40 +0300 Message-Id: <20190825071541.10389-2-mlevitsk@redhat.com> In-Reply-To: <20190825071541.10389-1-mlevitsk@redhat.com> References: <20190825071541.10389-1-mlevitsk@redhat.com> X-Scanned-By: MIMEDefang 2.84 on 10.5.11.23 X-Greylist: Sender IP whitelisted, not delayed by milter-greylist-4.5.16 (mx1.redhat.com [10.5.110.44]); Sun, 25 Aug 2019 07:15:50 +0000 (UTC) X-detected-operating-system: by eggs.gnu.org: GNU/Linux 2.2.x-3.x [generic] X-Received-From: 209.132.183.28 Subject: [Qemu-devel] [PATCH 1/2] block/nvme: add support for write zeros X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.23 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Cc: Fam Zheng , Kevin Wolf , qemu-block@nongnu.org, Max Reitz , Paolo Bonzini , Maxim Levitsky , John Snow Errors-To: qemu-devel-bounces+importer=patchew.org@nongnu.org Sender: "Qemu-devel" Content-Transfer-Encoding: quoted-printable MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Signed-off-by: Maxim Levitsky --- block/nvme.c | 72 +++++++++++++++++++++++++++++++++++++++++++- block/trace-events | 1 + include/block/nvme.h | 19 +++++++++++- 3 files changed, 90 insertions(+), 2 deletions(-) diff --git a/block/nvme.c b/block/nvme.c index 5be3a39b63..f8bd11e19a 100644 --- a/block/nvme.c +++ b/block/nvme.c @@ -111,6 +111,8 @@ typedef struct { uint64_t max_transfer; bool plugged; =20 + bool supports_write_zeros; + CoMutex dma_map_lock; CoQueue dma_flush_queue; =20 @@ -421,6 +423,7 @@ static void nvme_identify(BlockDriverState *bs, int nam= espace, Error **errp) NvmeIdNs *idns; NvmeLBAF *lbaf; uint8_t *resp; + uint16_t oncs; int r; uint64_t iova; NvmeCmd cmd =3D { @@ -458,6 +461,9 @@ static void nvme_identify(BlockDriverState *bs, int nam= espace, Error **errp) s->max_transfer =3D MIN_NON_ZERO(s->max_transfer, s->page_size / sizeof(uint64_t) * s->page_size); =20 + oncs =3D le16_to_cpu(idctrl->oncs); + s->supports_write_zeros =3D (oncs & NVME_ONCS_WRITE_ZEROS) !=3D 0; + memset(resp, 0, 4096); =20 cmd.cdw10 =3D 0; @@ -470,6 +476,12 @@ static void nvme_identify(BlockDriverState *bs, int na= mespace, Error **errp) s->nsze =3D le64_to_cpu(idns->nsze); lbaf =3D &idns->lbaf[NVME_ID_NS_FLBAS_INDEX(idns->flbas)]; =20 + if (NVME_ID_NS_DLFEAT_WRITE_ZEROS(idns->dlfeat) && + NVME_ID_NS_DLFEAT_READ_BEHAVIOR(idns->dlfeat) =3D=3D + NVME_ID_NS_DLFEAT_READ_BEHAVIOR_ZEROS) { + bs->supported_write_flags |=3D BDRV_REQ_MAY_UNMAP; + } + if (lbaf->ms) { error_setg(errp, "Namespaces with metadata are not yet supported"); goto out; @@ -764,6 +776,8 @@ static int nvme_file_open(BlockDriverState *bs, QDict *= options, int flags, int ret; BDRVNVMeState *s =3D bs->opaque; =20 + bs->supported_write_flags =3D BDRV_REQ_FUA; + opts =3D qemu_opts_create(&runtime_opts, NULL, 0, &error_abort); qemu_opts_absorb_qdict(opts, options, &error_abort); device =3D qemu_opt_get(opts, NVME_BLOCK_OPT_DEVICE); @@ -792,7 +806,6 @@ static int nvme_file_open(BlockDriverState *bs, QDict *= options, int flags, goto fail; } } - bs->supported_write_flags =3D BDRV_REQ_FUA; return 0; fail: nvme_close(bs); @@ -1086,6 +1099,60 @@ static coroutine_fn int nvme_co_flush(BlockDriverSta= te *bs) } =20 =20 +static coroutine_fn int nvme_co_pwrite_zeroes(BlockDriverState *bs, + int64_t offset, + int bytes, + BdrvRequestFlags flags) +{ + BDRVNVMeState *s =3D bs->opaque; + NVMeQueuePair *ioq =3D s->queues[1]; + NVMeRequest *req; + + uint32_t cdw12 =3D ((bytes >> s->blkshift) - 1) & 0xFFFF; + + if (!s->supports_write_zeros) { + return -ENOTSUP; + } + + NvmeCmd cmd =3D { + .opcode =3D NVME_CMD_WRITE_ZEROS, + .nsid =3D cpu_to_le32(s->nsid), + .cdw10 =3D cpu_to_le32((offset >> s->blkshift) & 0xFFFFFFFF), + .cdw11 =3D cpu_to_le32(((offset >> s->blkshift) >> 32) & 0xFFFFFFF= F), + }; + + NVMeCoData data =3D { + .ctx =3D bdrv_get_aio_context(bs), + .ret =3D -EINPROGRESS, + }; + + if (flags & BDRV_REQ_MAY_UNMAP) { + cdw12 |=3D (1 << 25); + } + + if (flags & BDRV_REQ_FUA) { + cdw12 |=3D (1 << 30); + } + + cmd.cdw12 =3D cpu_to_le32(cdw12); + + trace_nvme_write_zeros(s, offset, bytes, flags); + assert(s->nr_queues > 1); + req =3D nvme_get_free_req(ioq); + assert(req); + + nvme_submit_command(s, ioq, req, &cmd, nvme_rw_cb, &data); + + data.co =3D qemu_coroutine_self(); + while (data.ret =3D=3D -EINPROGRESS) { + qemu_coroutine_yield(); + } + + trace_nvme_rw_done(s, true, offset, bytes, data.ret); + return data.ret; +} + + static int nvme_reopen_prepare(BDRVReopenState *reopen_state, BlockReopenQueue *queue, Error **errp) { @@ -1190,6 +1257,9 @@ static BlockDriver bdrv_nvme =3D { =20 .bdrv_co_preadv =3D nvme_co_preadv, .bdrv_co_pwritev =3D nvme_co_pwritev, + + .bdrv_co_pwrite_zeroes =3D nvme_co_pwrite_zeroes, + .bdrv_co_flush_to_disk =3D nvme_co_flush, .bdrv_reopen_prepare =3D nvme_reopen_prepare, =20 diff --git a/block/trace-events b/block/trace-events index 04209f058d..8209fbd0c7 100644 --- a/block/trace-events +++ b/block/trace-events @@ -149,6 +149,7 @@ nvme_submit_command_raw(int c0, int c1, int c2, int c3,= int c4, int c5, int c6, nvme_handle_event(void *s) "s %p" nvme_poll_cb(void *s) "s %p" nvme_prw_aligned(void *s, int is_write, uint64_t offset, uint64_t bytes, i= nt flags, int niov) "s %p is_write %d offset %"PRId64" bytes %"PRId64" flag= s %d niov %d" +nvme_write_zeros(void *s, uint64_t offset, uint64_t bytes, int flags) "s %= p offset %"PRId64" bytes %"PRId64" flags %d" nvme_qiov_unaligned(const void *qiov, int n, void *base, size_t size, int = align) "qiov %p n %d base %p size 0x%zx align 0x%x" nvme_prw_buffered(void *s, uint64_t offset, uint64_t bytes, int niov, int = is_write) "s %p offset %"PRId64" bytes %"PRId64" niov %d is_write %d" nvme_rw_done(void *s, int is_write, uint64_t offset, uint64_t bytes, int r= et) "s %p is_write %d offset %"PRId64" bytes %"PRId64" ret %d" diff --git a/include/block/nvme.h b/include/block/nvme.h index 3ec8efcc43..1f5b406344 100644 --- a/include/block/nvme.h +++ b/include/block/nvme.h @@ -653,12 +653,29 @@ 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; + + uint8_t res30[94]; NvmeLBAF lbaf[16]; uint8_t res192[192]; uint8_t vs[3712]; } NvmeIdNs; =20 + +/*Deallocate Logical Block Features*/ +#define NVME_ID_NS_DLFEAT_GUARD_CRC(dlfeat) ((dlfeat) & 0x10) +#define NVME_ID_NS_DLFEAT_WRITE_ZEROS(dlfeat) ((dlfeat) & 0x08) + +#define NVME_ID_NS_DLFEAT_READ_BEHAVIOR(dlfeat) ((dlfeat) & 0x7) +#define NVME_ID_NS_DLFEAT_READ_BEHAVIOR_UNDEFINED 0 +#define NVME_ID_NS_DLFEAT_READ_BEHAVIOR_ZEROS 1 +#define NVME_ID_NS_DLFEAT_READ_BEHAVIOR_ONES 2 + + #define NVME_ID_NS_NSFEAT_THIN(nsfeat) ((nsfeat & 0x1)) #define NVME_ID_NS_FLBAS_EXTENDED(flbas) ((flbas >> 4) & 0x1) #define NVME_ID_NS_FLBAS_INDEX(flbas) ((flbas & 0xf)) --=20 2.17.2