From patchwork Fri Sep 13 13:36:26 2019 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Maxim Levitsky X-Patchwork-Id: 1162083 Return-Path: X-Original-To: incoming@patchwork.ozlabs.org Delivered-To: patchwork-incoming@bilbo.ozlabs.org Authentication-Results: ozlabs.org; spf=pass (mailfrom) smtp.mailfrom=nongnu.org (client-ip=209.51.188.17; helo=lists.gnu.org; envelope-from=qemu-devel-bounces+incoming=patchwork.ozlabs.org@nongnu.org; receiver=) Authentication-Results: ozlabs.org; dmarc=fail (p=none dis=none) header.from=redhat.com Received: from lists.gnu.org (lists.gnu.org [209.51.188.17]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by ozlabs.org (Postfix) with ESMTPS id 46VGwm2qWhz9sPk for ; Fri, 13 Sep 2019 23:40:23 +1000 (AEST) Received: from localhost ([::1]:44164 helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1i8loC-0008HD-R2 for incoming@patchwork.ozlabs.org; Fri, 13 Sep 2019 09:40:20 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]:37997) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1i8lko-0004Qj-1x for qemu-devel@nongnu.org; Fri, 13 Sep 2019 09:36:51 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1i8lkm-0003Qc-Kg for qemu-devel@nongnu.org; Fri, 13 Sep 2019 09:36:49 -0400 Received: from mx1.redhat.com ([209.132.183.28]:34741) by eggs.gnu.org with esmtps (TLS1.0:DHE_RSA_AES_256_CBC_SHA1:32) (Exim 4.71) (envelope-from ) id 1i8lkj-0003Og-NO; Fri, 13 Sep 2019 09:36:45 -0400 Received: from smtp.corp.redhat.com (int-mx05.intmail.prod.int.phx2.redhat.com [10.5.11.15]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by mx1.redhat.com (Postfix) with ESMTPS id 0C7DB9D1D1; Fri, 13 Sep 2019 13:36:45 +0000 (UTC) Received: from maximlenovopc.usersys.redhat.com (unknown [10.35.206.39]) by smtp.corp.redhat.com (Postfix) with ESMTP id 6E9AE5D712; Fri, 13 Sep 2019 13:36:40 +0000 (UTC) From: Maxim Levitsky To: qemu-devel@nongnu.org Date: Fri, 13 Sep 2019 16:36:26 +0300 Message-Id: <20190913133627.28450-2-mlevitsk@redhat.com> In-Reply-To: <20190913133627.28450-1-mlevitsk@redhat.com> References: <20190913133627.28450-1-mlevitsk@redhat.com> X-Scanned-By: MIMEDefang 2.79 on 10.5.11.15 X-Greylist: Sender IP whitelisted, not delayed by milter-greylist-4.5.16 (mx1.redhat.com [10.5.110.28]); Fri, 13 Sep 2019 13:36:45 +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 v2 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 , Keith Busch , Paolo Bonzini , Maxim Levitsky , John Snow Errors-To: qemu-devel-bounces+incoming=patchwork.ozlabs.org@nongnu.org Sender: "Qemu-devel" Signed-off-by: Maxim Levitsky Reviewed-by: John Snow --- 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..d95265fae4 100644 --- a/block/nvme.c +++ b/block/nvme.c @@ -111,6 +111,8 @@ typedef struct { uint64_t max_transfer; bool plugged; + bool supports_write_zeroes; + CoMutex dma_map_lock; CoQueue dma_flush_queue; @@ -421,6 +423,7 @@ static void nvme_identify(BlockDriverState *bs, int namespace, Error **errp) NvmeIdNs *idns; NvmeLBAF *lbaf; uint8_t *resp; + uint16_t oncs; int r; uint64_t iova; NvmeCmd cmd = { @@ -458,6 +461,9 @@ static void nvme_identify(BlockDriverState *bs, int namespace, Error **errp) s->max_transfer = MIN_NON_ZERO(s->max_transfer, s->page_size / sizeof(uint64_t) * s->page_size); + oncs = le16_to_cpu(idctrl->oncs); + s->supports_write_zeroes = !!(oncs & NVME_ONCS_WRITE_ZEROS); + memset(resp, 0, 4096); cmd.cdw10 = 0; @@ -470,6 +476,12 @@ static void nvme_identify(BlockDriverState *bs, int namespace, Error **errp) s->nsze = le64_to_cpu(idns->nsze); lbaf = &idns->lbaf[NVME_ID_NS_FLBAS_INDEX(idns->flbas)]; + if (NVME_ID_NS_DLFEAT_WRITE_ZEROES(idns->dlfeat) && + NVME_ID_NS_DLFEAT_READ_BEHAVIOR(idns->dlfeat) == + NVME_ID_NS_DLFEAT_READ_BEHAVIOR_ZEROES) { + bs->supported_write_flags |= 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 = bs->opaque; + bs->supported_write_flags = BDRV_REQ_FUA; + opts = qemu_opts_create(&runtime_opts, NULL, 0, &error_abort); qemu_opts_absorb_qdict(opts, options, &error_abort); device = 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 = BDRV_REQ_FUA; return 0; fail: nvme_close(bs); @@ -1086,6 +1099,60 @@ static coroutine_fn int nvme_co_flush(BlockDriverState *bs) } +static coroutine_fn int nvme_co_pwrite_zeroes(BlockDriverState *bs, + int64_t offset, + int bytes, + BdrvRequestFlags flags) +{ + BDRVNVMeState *s = bs->opaque; + NVMeQueuePair *ioq = s->queues[1]; + NVMeRequest *req; + + uint32_t cdw12 = ((bytes >> s->blkshift) - 1) & 0xFFFF; + + if (!s->supports_write_zeroes) { + return -ENOTSUP; + } + + NvmeCmd cmd = { + .opcode = NVME_CMD_WRITE_ZEROS, + .nsid = cpu_to_le32(s->nsid), + .cdw10 = cpu_to_le32((offset >> s->blkshift) & 0xFFFFFFFF), + .cdw11 = cpu_to_le32(((offset >> s->blkshift) >> 32) & 0xFFFFFFFF), + }; + + NVMeCoData data = { + .ctx = bdrv_get_aio_context(bs), + .ret = -EINPROGRESS, + }; + + if (flags & BDRV_REQ_MAY_UNMAP) { + cdw12 |= (1 << 25); + } + + if (flags & BDRV_REQ_FUA) { + cdw12 |= (1 << 30); + } + + cmd.cdw12 = cpu_to_le32(cdw12); + + trace_nvme_write_zeroes(s, offset, bytes, flags); + assert(s->nr_queues > 1); + req = nvme_get_free_req(ioq); + assert(req); + + nvme_submit_command(s, ioq, req, &cmd, nvme_rw_cb, &data); + + data.co = qemu_coroutine_self(); + while (data.ret == -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 = { .bdrv_co_preadv = nvme_co_preadv, .bdrv_co_pwritev = nvme_co_pwritev, + + .bdrv_co_pwrite_zeroes = nvme_co_pwrite_zeroes, + .bdrv_co_flush_to_disk = nvme_co_flush, .bdrv_reopen_prepare = nvme_reopen_prepare, diff --git a/block/trace-events b/block/trace-events index 04209f058d..651aa461d5 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, int flags, int niov) "s %p is_write %d offset %"PRId64" bytes %"PRId64" flags %d niov %d" +nvme_write_zeroes(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 ret) "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..33304c5a65 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 res34[94]; NvmeLBAF lbaf[16]; uint8_t res192[192]; uint8_t vs[3712]; } NvmeIdNs; + +/*Deallocate Logical Block Features*/ +#define NVME_ID_NS_DLFEAT_GUARD_CRC(dlfeat) ((dlfeat) & 0x10) +#define NVME_ID_NS_DLFEAT_WRITE_ZEROES(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_ZEROES 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))