* [Qemu-devel] [PATCH v2 0/2] block/nvme: add support for write zeros and discard
@ 2019-09-13 13:36 Maxim Levitsky
2019-09-13 13:36 ` [Qemu-devel] [PATCH v2 1/2] block/nvme: add support for write zeros Maxim Levitsky
` (2 more replies)
0 siblings, 3 replies; 8+ messages in thread
From: Maxim Levitsky @ 2019-09-13 13:36 UTC (permalink / raw)
To: qemu-devel
Cc: Fam Zheng, Kevin Wolf, qemu-block, Max Reitz, Keith Busch,
Paolo Bonzini, Maxim Levitsky, John Snow
This is the second part of the patches I prepared
for this driver back when I worked on mdev-nvme.
V2: addressed review feedback, no major changes
Best regards,
Maxim Levitsky
Maxim Levitsky (2):
block/nvme: add support for write zeros
block/nvme: add support for discard
block/nvme.c | 155 ++++++++++++++++++++++++++++++++++++++++++-
block/trace-events | 3 +
include/block/nvme.h | 19 +++++-
3 files changed, 175 insertions(+), 2 deletions(-)
--
2.17.2
^ permalink raw reply [flat|nested] 8+ messages in thread
* [Qemu-devel] [PATCH v2 1/2] block/nvme: add support for write zeros
2019-09-13 13:36 [Qemu-devel] [PATCH v2 0/2] block/nvme: add support for write zeros and discard Maxim Levitsky
@ 2019-09-13 13:36 ` Maxim Levitsky
2019-09-18 20:22 ` John Snow
2019-09-13 13:36 ` [Qemu-devel] [PATCH v2 2/2] block/nvme: add support for discard Maxim Levitsky
2019-10-28 10:35 ` [PATCH v2 0/2] block/nvme: add support for write zeros and discard Max Reitz
2 siblings, 1 reply; 8+ messages in thread
From: Maxim Levitsky @ 2019-09-13 13:36 UTC (permalink / raw)
To: qemu-devel
Cc: Fam Zheng, Kevin Wolf, qemu-block, Max Reitz, Keith Busch,
Paolo Bonzini, Maxim Levitsky, John Snow
Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>
---
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))
--
2.17.2
^ permalink raw reply related [flat|nested] 8+ messages in thread
* [Qemu-devel] [PATCH v2 2/2] block/nvme: add support for discard
2019-09-13 13:36 [Qemu-devel] [PATCH v2 0/2] block/nvme: add support for write zeros and discard Maxim Levitsky
2019-09-13 13:36 ` [Qemu-devel] [PATCH v2 1/2] block/nvme: add support for write zeros Maxim Levitsky
@ 2019-09-13 13:36 ` Maxim Levitsky
2019-09-18 20:24 ` John Snow
2019-10-28 10:35 ` [PATCH v2 0/2] block/nvme: add support for write zeros and discard Max Reitz
2 siblings, 1 reply; 8+ messages in thread
From: Maxim Levitsky @ 2019-09-13 13:36 UTC (permalink / raw)
To: qemu-devel
Cc: Fam Zheng, Kevin Wolf, qemu-block, Max Reitz, Keith Busch,
Paolo Bonzini, Maxim Levitsky, John Snow
Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>
---
block/nvme.c | 83 ++++++++++++++++++++++++++++++++++++++++++++++
block/trace-events | 2 ++
2 files changed, 85 insertions(+)
diff --git a/block/nvme.c b/block/nvme.c
index d95265fae4..c17edd6aae 100644
--- a/block/nvme.c
+++ b/block/nvme.c
@@ -112,6 +112,7 @@ typedef struct {
bool plugged;
bool supports_write_zeroes;
+ bool supports_discard;
CoMutex dma_map_lock;
CoQueue dma_flush_queue;
@@ -463,6 +464,7 @@ static void nvme_identify(BlockDriverState *bs, int namespace, Error **errp)
oncs = le16_to_cpu(idctrl->oncs);
s->supports_write_zeroes = !!(oncs & NVME_ONCS_WRITE_ZEROS);
+ s->supports_discard = !!(oncs & NVME_ONCS_DSM);
memset(resp, 0, 4096);
@@ -1153,6 +1155,86 @@ static coroutine_fn int nvme_co_pwrite_zeroes(BlockDriverState *bs,
}
+static int coroutine_fn nvme_co_pdiscard(BlockDriverState *bs,
+ int64_t offset,
+ int bytes)
+{
+ BDRVNVMeState *s = bs->opaque;
+ NVMeQueuePair *ioq = s->queues[1];
+ NVMeRequest *req;
+ NvmeDsmRange *buf;
+ QEMUIOVector local_qiov;
+ int ret;
+
+ NvmeCmd cmd = {
+ .opcode = NVME_CMD_DSM,
+ .nsid = cpu_to_le32(s->nsid),
+ .cdw10 = cpu_to_le32(0), /*number of ranges - 0 based*/
+ .cdw11 = cpu_to_le32(1 << 2), /*deallocate bit*/
+ };
+
+ NVMeCoData data = {
+ .ctx = bdrv_get_aio_context(bs),
+ .ret = -EINPROGRESS,
+ };
+
+ if (!s->supports_discard) {
+ return -ENOTSUP;
+ }
+
+ assert(s->nr_queues > 1);
+
+ buf = qemu_try_blockalign0(bs, s->page_size);
+ if (!buf) {
+ return -ENOMEM;
+ }
+
+ buf->nlb = cpu_to_le32(bytes >> s->blkshift);
+ buf->slba = cpu_to_le64(offset >> s->blkshift);
+ buf->cattr = 0;
+
+ qemu_iovec_init(&local_qiov, 1);
+ qemu_iovec_add(&local_qiov, buf, 4096);
+
+ req = nvme_get_free_req(ioq);
+ assert(req);
+
+ qemu_co_mutex_lock(&s->dma_map_lock);
+ ret = nvme_cmd_map_qiov(bs, &cmd, req, &local_qiov);
+ qemu_co_mutex_unlock(&s->dma_map_lock);
+
+ if (ret) {
+ req->busy = false;
+ goto out;
+ }
+
+ trace_nvme_dsm(s, offset, bytes);
+
+ nvme_submit_command(s, ioq, req, &cmd, nvme_rw_cb, &data);
+
+ data.co = qemu_coroutine_self();
+ while (data.ret == -EINPROGRESS) {
+ qemu_coroutine_yield();
+ }
+
+ qemu_co_mutex_lock(&s->dma_map_lock);
+ ret = nvme_cmd_unmap_qiov(bs, &local_qiov);
+ qemu_co_mutex_unlock(&s->dma_map_lock);
+
+ if (ret) {
+ goto out;
+ }
+
+ ret = data.ret;
+ trace_nvme_dsm_done(s, offset, bytes, ret);
+out:
+ qemu_iovec_destroy(&local_qiov);
+ qemu_vfree(buf);
+ return ret;
+
+}
+
+
static int nvme_reopen_prepare(BDRVReopenState *reopen_state,
BlockReopenQueue *queue, Error **errp)
{
@@ -1259,6 +1341,7 @@ static BlockDriver bdrv_nvme = {
.bdrv_co_pwritev = nvme_co_pwritev,
.bdrv_co_pwrite_zeroes = nvme_co_pwrite_zeroes,
+ .bdrv_co_pdiscard = nvme_co_pdiscard,
.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 651aa461d5..c61553b4b8 100644
--- a/block/trace-events
+++ b/block/trace-events
@@ -153,6 +153,8 @@ nvme_write_zeroes(void *s, uint64_t offset, uint64_t bytes, int flags) "s %p off
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"
+nvme_dsm(void *s, uint64_t offset, uint64_t bytes) "s %p offset %"PRId64" bytes %"PRId64""
+nvme_dsm_done(void *s, uint64_t offset, uint64_t bytes, int ret) "s %p offset %"PRId64" bytes %"PRId64" ret %d"
nvme_dma_map_flush(void *s) "s %p"
nvme_free_req_queue_wait(void *q) "q %p"
nvme_cmd_map_qiov(void *s, void *cmd, void *req, void *qiov, int entries) "s %p cmd %p req %p qiov %p entries %d"
--
2.17.2
^ permalink raw reply related [flat|nested] 8+ messages in thread
* Re: [Qemu-devel] [PATCH v2 1/2] block/nvme: add support for write zeros
2019-09-13 13:36 ` [Qemu-devel] [PATCH v2 1/2] block/nvme: add support for write zeros Maxim Levitsky
@ 2019-09-18 20:22 ` John Snow
0 siblings, 0 replies; 8+ messages in thread
From: John Snow @ 2019-09-18 20:22 UTC (permalink / raw)
To: Maxim Levitsky, qemu-devel
Cc: Fam Zheng, Kevin Wolf, qemu-block, Max Reitz, Keith Busch, Paolo Bonzini
On 9/13/19 9:36 AM, Maxim Levitsky wrote:
> Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>
It'd still be nice to have a commit message...
> ---
Or here, what changed from V1.
> 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
ragged, but can be squished in on commit.
> +
> +
> #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))
>
more or less, looks OK as far as I can tell, but there's a bit of
benefit-of-doubt going on for the exact mechanisms of NVME.
I pointed out some sections in the NVME spec that can be used to help
review this patch last time; your commit message should mention some of
these sections ideally so that constants and registers can be more
quickly verified.
Reviewed-by: John Snow <jsnow@redhat.com>
^ permalink raw reply [flat|nested] 8+ messages in thread
* Re: [Qemu-devel] [PATCH v2 2/2] block/nvme: add support for discard
2019-09-13 13:36 ` [Qemu-devel] [PATCH v2 2/2] block/nvme: add support for discard Maxim Levitsky
@ 2019-09-18 20:24 ` John Snow
0 siblings, 0 replies; 8+ messages in thread
From: John Snow @ 2019-09-18 20:24 UTC (permalink / raw)
To: Maxim Levitsky, qemu-devel
Cc: Fam Zheng, Kevin Wolf, qemu-block, Max Reitz, Keith Busch, Paolo Bonzini
On 9/13/19 9:36 AM, Maxim Levitsky wrote:
> Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>
Same comments as 1/2; but not worth holding anything up. We'll find out
from users if there are problems, but I wish we had a nicer way to test it.
Reviewed-by: John Snow <jsnow@redhat.com>
> ---
> block/nvme.c | 83 ++++++++++++++++++++++++++++++++++++++++++++++
> block/trace-events | 2 ++
> 2 files changed, 85 insertions(+)
>
> diff --git a/block/nvme.c b/block/nvme.c
> index d95265fae4..c17edd6aae 100644
> --- a/block/nvme.c
> +++ b/block/nvme.c
> @@ -112,6 +112,7 @@ typedef struct {
> bool plugged;
>
> bool supports_write_zeroes;
> + bool supports_discard;
>
> CoMutex dma_map_lock;
> CoQueue dma_flush_queue;
> @@ -463,6 +464,7 @@ static void nvme_identify(BlockDriverState *bs, int namespace, Error **errp)
>
> oncs = le16_to_cpu(idctrl->oncs);
> s->supports_write_zeroes = !!(oncs & NVME_ONCS_WRITE_ZEROS);
> + s->supports_discard = !!(oncs & NVME_ONCS_DSM);
>
> memset(resp, 0, 4096);
>
> @@ -1153,6 +1155,86 @@ static coroutine_fn int nvme_co_pwrite_zeroes(BlockDriverState *bs,
> }
>
>
> +static int coroutine_fn nvme_co_pdiscard(BlockDriverState *bs,
> + int64_t offset,
> + int bytes)
> +{
> + BDRVNVMeState *s = bs->opaque;
> + NVMeQueuePair *ioq = s->queues[1];
> + NVMeRequest *req;
> + NvmeDsmRange *buf;
> + QEMUIOVector local_qiov;
> + int ret;
> +
> + NvmeCmd cmd = {
> + .opcode = NVME_CMD_DSM,
> + .nsid = cpu_to_le32(s->nsid),
> + .cdw10 = cpu_to_le32(0), /*number of ranges - 0 based*/
> + .cdw11 = cpu_to_le32(1 << 2), /*deallocate bit*/
> + };
> +
> + NVMeCoData data = {
> + .ctx = bdrv_get_aio_context(bs),
> + .ret = -EINPROGRESS,
> + };
> +
> + if (!s->supports_discard) {
> + return -ENOTSUP;
> + }
> +
> + assert(s->nr_queues > 1);
> +
> + buf = qemu_try_blockalign0(bs, s->page_size);
> + if (!buf) {
> + return -ENOMEM;
> + }
> +
> + buf->nlb = cpu_to_le32(bytes >> s->blkshift);
> + buf->slba = cpu_to_le64(offset >> s->blkshift);
> + buf->cattr = 0;
> +
> + qemu_iovec_init(&local_qiov, 1);
> + qemu_iovec_add(&local_qiov, buf, 4096);
> +
> + req = nvme_get_free_req(ioq);
> + assert(req);
> +
> + qemu_co_mutex_lock(&s->dma_map_lock);
> + ret = nvme_cmd_map_qiov(bs, &cmd, req, &local_qiov);
> + qemu_co_mutex_unlock(&s->dma_map_lock);
> +
> + if (ret) {
> + req->busy = false;
> + goto out;
> + }
> +
> + trace_nvme_dsm(s, offset, bytes);
> +
> + nvme_submit_command(s, ioq, req, &cmd, nvme_rw_cb, &data);
> +
> + data.co = qemu_coroutine_self();
> + while (data.ret == -EINPROGRESS) {
> + qemu_coroutine_yield();
> + }
> +
> + qemu_co_mutex_lock(&s->dma_map_lock);
> + ret = nvme_cmd_unmap_qiov(bs, &local_qiov);
> + qemu_co_mutex_unlock(&s->dma_map_lock);
> +
> + if (ret) {
> + goto out;
> + }
> +
> + ret = data.ret;
> + trace_nvme_dsm_done(s, offset, bytes, ret);
> +out:
> + qemu_iovec_destroy(&local_qiov);
> + qemu_vfree(buf);
> + return ret;
> +
> +}
> +
> +
> static int nvme_reopen_prepare(BDRVReopenState *reopen_state,
> BlockReopenQueue *queue, Error **errp)
> {
> @@ -1259,6 +1341,7 @@ static BlockDriver bdrv_nvme = {
> .bdrv_co_pwritev = nvme_co_pwritev,
>
> .bdrv_co_pwrite_zeroes = nvme_co_pwrite_zeroes,
> + .bdrv_co_pdiscard = nvme_co_pdiscard,
>
> .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 651aa461d5..c61553b4b8 100644
> --- a/block/trace-events
> +++ b/block/trace-events
> @@ -153,6 +153,8 @@ nvme_write_zeroes(void *s, uint64_t offset, uint64_t bytes, int flags) "s %p off
> 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"
> +nvme_dsm(void *s, uint64_t offset, uint64_t bytes) "s %p offset %"PRId64" bytes %"PRId64""
> +nvme_dsm_done(void *s, uint64_t offset, uint64_t bytes, int ret) "s %p offset %"PRId64" bytes %"PRId64" ret %d"
> nvme_dma_map_flush(void *s) "s %p"
> nvme_free_req_queue_wait(void *q) "q %p"
> nvme_cmd_map_qiov(void *s, void *cmd, void *req, void *qiov, int entries) "s %p cmd %p req %p qiov %p entries %d"
>
--
—js
^ permalink raw reply [flat|nested] 8+ messages in thread
* Re: [PATCH v2 0/2] block/nvme: add support for write zeros and discard
2019-09-13 13:36 [Qemu-devel] [PATCH v2 0/2] block/nvme: add support for write zeros and discard Maxim Levitsky
2019-09-13 13:36 ` [Qemu-devel] [PATCH v2 1/2] block/nvme: add support for write zeros Maxim Levitsky
2019-09-13 13:36 ` [Qemu-devel] [PATCH v2 2/2] block/nvme: add support for discard Maxim Levitsky
@ 2019-10-28 10:35 ` Max Reitz
2019-10-29 13:33 ` John Snow
2 siblings, 1 reply; 8+ messages in thread
From: Max Reitz @ 2019-10-28 10:35 UTC (permalink / raw)
To: Maxim Levitsky, qemu-devel
Cc: Fam Zheng, Kevin Wolf, qemu-block, Keith Busch, Paolo Bonzini, John Snow
[-- Attachment #1.1: Type: text/plain, Size: 837 bytes --]
On 13.09.19 15:36, Maxim Levitsky wrote:
> This is the second part of the patches I prepared
> for this driver back when I worked on mdev-nvme.
>
> V2: addressed review feedback, no major changes
>
> Best regards,
> Maxim Levitsky
>
> Maxim Levitsky (2):
> block/nvme: add support for write zeros
> block/nvme: add support for discard
>
> block/nvme.c | 155 ++++++++++++++++++++++++++++++++++++++++++-
> block/trace-events | 3 +
> include/block/nvme.h | 19 +++++-
> 3 files changed, 175 insertions(+), 2 deletions(-)
Thanks, fixed the indentation in nvme.h in patch 1, and applied to my
block branch:
https://git.xanclic.moe/XanClic/qemu/commits/branch/block
For the record, I don’t think !!x has benefits over x != 0 and I
personally prefer bool y = x over any of it. O:-)
Max
[-- Attachment #2: OpenPGP digital signature --]
[-- Type: application/pgp-signature, Size: 488 bytes --]
^ permalink raw reply [flat|nested] 8+ messages in thread
* Re: [PATCH v2 0/2] block/nvme: add support for write zeros and discard
2019-10-28 10:35 ` [PATCH v2 0/2] block/nvme: add support for write zeros and discard Max Reitz
@ 2019-10-29 13:33 ` John Snow
2019-11-04 17:54 ` Maxim Levitsky
0 siblings, 1 reply; 8+ messages in thread
From: John Snow @ 2019-10-29 13:33 UTC (permalink / raw)
To: Max Reitz, Maxim Levitsky, qemu-devel
Cc: Fam Zheng, Paolo Bonzini, qemu-block, Keith Busch, Kevin Wolf
On 10/28/19 6:35 AM, Max Reitz wrote:
> On 13.09.19 15:36, Maxim Levitsky wrote:
>> This is the second part of the patches I prepared
>> for this driver back when I worked on mdev-nvme.
>>
>> V2: addressed review feedback, no major changes
>>
>> Best regards,
>> Maxim Levitsky
>>
>> Maxim Levitsky (2):
>> block/nvme: add support for write zeros
>> block/nvme: add support for discard
>>
>> block/nvme.c | 155 ++++++++++++++++++++++++++++++++++++++++++-
>> block/trace-events | 3 +
>> include/block/nvme.h | 19 +++++-
>> 3 files changed, 175 insertions(+), 2 deletions(-)
> Thanks, fixed the indentation in nvme.h in patch 1, and applied to my
> block branch:
>
> https://git.xanclic.moe/XanClic/qemu/commits/branch/block
>
> For the record, I don’t think !!x has benefits over x != 0 and I
> personally prefer bool y = x over any of it. O:-)
>
Well, that's even better :) For me, it's about making booleans obvious
as booleans and that's all.
--js
^ permalink raw reply [flat|nested] 8+ messages in thread
* Re: [PATCH v2 0/2] block/nvme: add support for write zeros and discard
2019-10-29 13:33 ` John Snow
@ 2019-11-04 17:54 ` Maxim Levitsky
0 siblings, 0 replies; 8+ messages in thread
From: Maxim Levitsky @ 2019-11-04 17:54 UTC (permalink / raw)
To: John Snow, Max Reitz, qemu-devel
Cc: Fam Zheng, Paolo Bonzini, qemu-block, Keith Busch, Kevin Wolf
On Tue, 2019-10-29 at 09:33 -0400, John Snow wrote:
>
> On 10/28/19 6:35 AM, Max Reitz wrote:
> > On 13.09.19 15:36, Maxim Levitsky wrote:
> > > This is the second part of the patches I prepared
> > > for this driver back when I worked on mdev-nvme.
> > >
> > > V2: addressed review feedback, no major changes
> > >
> > > Best regards,
> > > Maxim Levitsky
> > >
> > > Maxim Levitsky (2):
> > > block/nvme: add support for write zeros
> > > block/nvme: add support for discard
> > >
> > > block/nvme.c | 155 ++++++++++++++++++++++++++++++++++++++++++-
> > > block/trace-events | 3 +
> > > include/block/nvme.h | 19 +++++-
> > > 3 files changed, 175 insertions(+), 2 deletions(-)
> >
> > Thanks, fixed the indentation in nvme.h in patch 1, and applied to my
> > block branch:
> >
> > https://git.xanclic.moe/XanClic/qemu/commits/branch/block
> >
> > For the record, I don’t think !!x has benefits over x != 0 and I
> > personally prefer bool y = x over any of it. O:-)
> >
>
> Well, that's even better :) For me, it's about making booleans obvious
> as booleans and that's all.
>
> --js
Thanks to all of you!!
Best regards,
Maxim Levitsky
^ permalink raw reply [flat|nested] 8+ messages in thread
end of thread, other threads:[~2019-11-04 17:57 UTC | newest]
Thread overview: 8+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2019-09-13 13:36 [Qemu-devel] [PATCH v2 0/2] block/nvme: add support for write zeros and discard Maxim Levitsky
2019-09-13 13:36 ` [Qemu-devel] [PATCH v2 1/2] block/nvme: add support for write zeros Maxim Levitsky
2019-09-18 20:22 ` John Snow
2019-09-13 13:36 ` [Qemu-devel] [PATCH v2 2/2] block/nvme: add support for discard Maxim Levitsky
2019-09-18 20:24 ` John Snow
2019-10-28 10:35 ` [PATCH v2 0/2] block/nvme: add support for write zeros and discard Max Reitz
2019-10-29 13:33 ` John Snow
2019-11-04 17:54 ` Maxim Levitsky
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).