Re: [PATCH v2 11/18] hw/block/nvme: Introduce max active and open zone limits

2020-06-30 Thread Klaus Jensen 
On Jun 18 06:34, Dmitry Fomichev wrote:
> Added two module properties, "max_active" and "max_open" to control
> the maximum number of zones that can be active or open. Once these
> variables are set to non-default values, the driver checks these
> limits during I/O and returns Too Many Active or Too Many Open
> command status if they are exceeded.
> 
> Signed-off-by: Hans Holmberg 
> Signed-off-by: Dmitry Fomichev 
> ---
>  hw/block/nvme.c | 183 +++-
>  hw/block/nvme.h |   4 ++
>  2 files changed, 185 insertions(+), 2 deletions(-)
> 
> diff --git a/hw/block/nvme.c b/hw/block/nvme.c
> index 2e03b0b6ed..05a7cbcfcc 100644
> --- a/hw/block/nvme.c
> +++ b/hw/block/nvme.c
> @@ -120,6 +120,87 @@ static void nvme_remove_zone(NvmeCtrl *n, NvmeNamespace 
> *ns, NvmeZoneList *zl,
>  zone->prev = zone->next = 0;
>  }
>  
> +/*
> + * Take the first zone out from a list, return NULL if the list is empty.
> + */
> +static NvmeZone *nvme_remove_zone_head(NvmeCtrl *n, NvmeNamespace *ns,
> +NvmeZoneList *zl)
> +{
> +NvmeZone *zone = nvme_peek_zone_head(ns, zl);
> +
> +if (zone) {
> +--zl->size;
> +if (zl->size == 0) {
> +zl->head = NVME_ZONE_LIST_NIL;
> +zl->tail = NVME_ZONE_LIST_NIL;
> +} else {
> +zl->head = zone->next;
> +ns->zone_array[zl->head].prev = NVME_ZONE_LIST_NIL;
> +}
> +zone->prev = zone->next = 0;
> +}
> +
> +return zone;
> +}
> +
> +/*
> + * Check if we can open a zone without exceeding open/active limits.
> + * AOR stands for "Active and Open Resources" (see TP 4053 section 2.5).
> + */
> +static int nvme_aor_check(NvmeCtrl *n, NvmeNamespace *ns,
> + uint32_t act, uint32_t opn)
> +{
> +if (n->params.max_active_zones != 0 &&
> +ns->nr_active_zones + act > n->params.max_active_zones) {
> +trace_pci_nvme_err_insuff_active_res(n->params.max_active_zones);
> +return NVME_ZONE_TOO_MANY_ACTIVE | NVME_DNR;
> +}
> +if (n->params.max_open_zones != 0 &&
> +ns->nr_open_zones + opn > n->params.max_open_zones) {
> +trace_pci_nvme_err_insuff_open_res(n->params.max_open_zones);
> +return NVME_ZONE_TOO_MANY_OPEN | NVME_DNR;
> +}
> +
> +return NVME_SUCCESS;
> +}
> +
> +static inline void nvme_aor_inc_open(NvmeCtrl *n, NvmeNamespace *ns)
> +{
> +assert(ns->nr_open_zones >= 0);
> +if (n->params.max_open_zones) {
> +ns->nr_open_zones++;
> +assert(ns->nr_open_zones <= n->params.max_open_zones);
> +}
> +}
> +
> +static inline void nvme_aor_dec_open(NvmeCtrl *n, NvmeNamespace *ns)
> +{
> +if (n->params.max_open_zones) {
> +assert(ns->nr_open_zones > 0);
> +ns->nr_open_zones--;
> +}
> +assert(ns->nr_open_zones >= 0);
> +}
> +
> +static inline void nvme_aor_inc_active(NvmeCtrl *n, NvmeNamespace *ns)
> +{
> +assert(ns->nr_active_zones >= 0);
> +if (n->params.max_active_zones) {
> +ns->nr_active_zones++;
> +assert(ns->nr_active_zones <= n->params.max_active_zones);
> +}
> +}
> +
> +static inline void nvme_aor_dec_active(NvmeCtrl *n, NvmeNamespace *ns)
> +{
> +if (n->params.max_active_zones) {
> +assert(ns->nr_active_zones > 0);
> +ns->nr_active_zones--;
> +assert(ns->nr_active_zones >= ns->nr_open_zones);
> +}
> +assert(ns->nr_active_zones >= 0);
> +}
> +
>  static void nvme_assign_zone_state(NvmeCtrl *n, NvmeNamespace *ns,
>  NvmeZone *zone, uint8_t state)
>  {
> @@ -454,6 +535,24 @@ static void nvme_enqueue_req_completion(NvmeCQueue *cq, 
> NvmeRequest *req)
>  timer_mod(cq->timer, qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) + 500);
>  }
>  
> +static void nvme_auto_transition_zone(NvmeCtrl *n, NvmeNamespace *ns,
> +bool implicit, bool adding_active)
> +{
> +NvmeZone *zone;
> +
> +if (implicit && n->params.max_open_zones &&
> +ns->nr_open_zones == n->params.max_open_zones) {
> +zone = nvme_remove_zone_head(n, ns, ns->imp_open_zones);
> +if (zone) {
> +/*
> + * Automatically close this implicitly open zone.
> + */
> +nvme_aor_dec_open(n, ns);
> +nvme_assign_zone_state(n, ns, zone, NVME_ZONE_STATE_CLOSED);
> +}
> +}
> +}
> +
>  static uint16_t nvme_check_zone_write(NvmeZone *zone, uint64_t slba,
>  uint32_t nlb)
>  {
> @@ -531,6 +630,23 @@ static uint16_t nvme_check_zone_read(NvmeCtrl *n, 
> NvmeZone *zone, uint64_t slba,
>  return status;
>  }
>  
> +static uint16_t nvme_auto_open_zone(NvmeCtrl *n, NvmeNamespace *ns,
> +NvmeZone *zone)
> +{
> +uint16_t status = NVME_SUCCESS;
> +uint8_t zs = nvme_get_zone_state(zone);
> +
> +if (zs == NVME_ZONE_STATE_EMPTY) {
> +nvme_auto_transition_zone(n, ns, true, true);
> +status = nvme_aor_check(n, ns, 1, 1);
> +} else if (zs == NVME_ZONE_STATE_CLOSED) {
> +nvme_auto_transition_zone(n, ns, true,

Re: [PATCH v2 11/18] hw/block/nvme: Introduce max active and open zone limits

2020-06-30 Thread Alistair Francis 
On Wed, Jun 17, 2020 at 3:07 PM Dmitry Fomichev  wrote:
>
> Added two module properties, "max_active" and "max_open" to control
> the maximum number of zones that can be active or open. Once these
> variables are set to non-default values, the driver checks these
> limits during I/O and returns Too Many Active or Too Many Open
> command status if they are exceeded.
>
> Signed-off-by: Hans Holmberg 
> Signed-off-by: Dmitry Fomichev 
> ---
>  hw/block/nvme.c | 183 +++-
>  hw/block/nvme.h |   4 ++
>  2 files changed, 185 insertions(+), 2 deletions(-)
>
> diff --git a/hw/block/nvme.c b/hw/block/nvme.c
> index 2e03b0b6ed..05a7cbcfcc 100644
> --- a/hw/block/nvme.c
> +++ b/hw/block/nvme.c
> @@ -120,6 +120,87 @@ static void nvme_remove_zone(NvmeCtrl *n, NvmeNamespace 
> *ns, NvmeZoneList *zl,
>  zone->prev = zone->next = 0;
>  }
>
> +/*
> + * Take the first zone out from a list, return NULL if the list is empty.
> + */
> +static NvmeZone *nvme_remove_zone_head(NvmeCtrl *n, NvmeNamespace *ns,
> +NvmeZoneList *zl)
> +{
> +NvmeZone *zone = nvme_peek_zone_head(ns, zl);
> +
> +if (zone) {
> +--zl->size;
> +if (zl->size == 0) {
> +zl->head = NVME_ZONE_LIST_NIL;
> +zl->tail = NVME_ZONE_LIST_NIL;
> +} else {
> +zl->head = zone->next;
> +ns->zone_array[zl->head].prev = NVME_ZONE_LIST_NIL;
> +}
> +zone->prev = zone->next = 0;
> +}
> +
> +return zone;
> +}
> +
> +/*
> + * Check if we can open a zone without exceeding open/active limits.
> + * AOR stands for "Active and Open Resources" (see TP 4053 section 2.5).
> + */
> +static int nvme_aor_check(NvmeCtrl *n, NvmeNamespace *ns,
> + uint32_t act, uint32_t opn)
> +{
> +if (n->params.max_active_zones != 0 &&
> +ns->nr_active_zones + act > n->params.max_active_zones) {
> +trace_pci_nvme_err_insuff_active_res(n->params.max_active_zones);
> +return NVME_ZONE_TOO_MANY_ACTIVE | NVME_DNR;
> +}
> +if (n->params.max_open_zones != 0 &&
> +ns->nr_open_zones + opn > n->params.max_open_zones) {
> +trace_pci_nvme_err_insuff_open_res(n->params.max_open_zones);
> +return NVME_ZONE_TOO_MANY_OPEN | NVME_DNR;
> +}
> +
> +return NVME_SUCCESS;
> +}
> +
> +static inline void nvme_aor_inc_open(NvmeCtrl *n, NvmeNamespace *ns)
> +{
> +assert(ns->nr_open_zones >= 0);
> +if (n->params.max_open_zones) {
> +ns->nr_open_zones++;
> +assert(ns->nr_open_zones <= n->params.max_open_zones);
> +}
> +}
> +
> +static inline void nvme_aor_dec_open(NvmeCtrl *n, NvmeNamespace *ns)
> +{
> +if (n->params.max_open_zones) {
> +assert(ns->nr_open_zones > 0);
> +ns->nr_open_zones--;
> +}
> +assert(ns->nr_open_zones >= 0);
> +}
> +
> +static inline void nvme_aor_inc_active(NvmeCtrl *n, NvmeNamespace *ns)
> +{
> +assert(ns->nr_active_zones >= 0);
> +if (n->params.max_active_zones) {
> +ns->nr_active_zones++;
> +assert(ns->nr_active_zones <= n->params.max_active_zones);
> +}
> +}
> +
> +static inline void nvme_aor_dec_active(NvmeCtrl *n, NvmeNamespace *ns)
> +{
> +if (n->params.max_active_zones) {
> +assert(ns->nr_active_zones > 0);
> +ns->nr_active_zones--;
> +assert(ns->nr_active_zones >= ns->nr_open_zones);
> +}
> +assert(ns->nr_active_zones >= 0);
> +}
> +
>  static void nvme_assign_zone_state(NvmeCtrl *n, NvmeNamespace *ns,
>  NvmeZone *zone, uint8_t state)
>  {
> @@ -454,6 +535,24 @@ static void nvme_enqueue_req_completion(NvmeCQueue *cq, 
> NvmeRequest *req)
>  timer_mod(cq->timer, qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) + 500);
>  }
>
> +static void nvme_auto_transition_zone(NvmeCtrl *n, NvmeNamespace *ns,
> +bool implicit, bool adding_active)
> +{
> +NvmeZone *zone;
> +
> +if (implicit && n->params.max_open_zones &&
> +ns->nr_open_zones == n->params.max_open_zones) {
> +zone = nvme_remove_zone_head(n, ns, ns->imp_open_zones);
> +if (zone) {
> +/*
> + * Automatically close this implicitly open zone.
> + */
> +nvme_aor_dec_open(n, ns);
> +nvme_assign_zone_state(n, ns, zone, NVME_ZONE_STATE_CLOSED);
> +}
> +}
> +}
> +
>  static uint16_t nvme_check_zone_write(NvmeZone *zone, uint64_t slba,
>  uint32_t nlb)
>  {
> @@ -531,6 +630,23 @@ static uint16_t nvme_check_zone_read(NvmeCtrl *n, 
> NvmeZone *zone, uint64_t slba,
>  return status;
>  }
>
> +static uint16_t nvme_auto_open_zone(NvmeCtrl *n, NvmeNamespace *ns,
> +NvmeZone *zone)
> +{
> +uint16_t status = NVME_SUCCESS;
> +uint8_t zs = nvme_get_zone_state(zone);
> +
> +if (zs == NVME_ZONE_STATE_EMPTY) {
> +nvme_auto_transition_zone(n, ns, true, true);
> +status = nvme_aor_check(n, ns, 1, 1);
> +} else if (zs == NVME_ZONE_STATE_CLOSED) {
> +nvme_auto_transition_zone(n,

[PATCH v2 11/18] hw/block/nvme: Introduce max active and open zone limits

2020-06-17 Thread Dmitry Fomichev 
Added two module properties, "max_active" and "max_open" to control
the maximum number of zones that can be active or open. Once these
variables are set to non-default values, the driver checks these
limits during I/O and returns Too Many Active or Too Many Open
command status if they are exceeded.

Signed-off-by: Hans Holmberg 
Signed-off-by: Dmitry Fomichev 
---
 hw/block/nvme.c | 183 +++-
 hw/block/nvme.h |   4 ++
 2 files changed, 185 insertions(+), 2 deletions(-)

diff --git a/hw/block/nvme.c b/hw/block/nvme.c
index 2e03b0b6ed..05a7cbcfcc 100644
--- a/hw/block/nvme.c
+++ b/hw/block/nvme.c
@@ -120,6 +120,87 @@ static void nvme_remove_zone(NvmeCtrl *n, NvmeNamespace 
*ns, NvmeZoneList *zl,
 zone->prev = zone->next = 0;
 }
 
+/*
+ * Take the first zone out from a list, return NULL if the list is empty.
+ */
+static NvmeZone *nvme_remove_zone_head(NvmeCtrl *n, NvmeNamespace *ns,
+NvmeZoneList *zl)
+{
+NvmeZone *zone = nvme_peek_zone_head(ns, zl);
+
+if (zone) {
+--zl->size;
+if (zl->size == 0) {
+zl->head = NVME_ZONE_LIST_NIL;
+zl->tail = NVME_ZONE_LIST_NIL;
+} else {
+zl->head = zone->next;
+ns->zone_array[zl->head].prev = NVME_ZONE_LIST_NIL;
+}
+zone->prev = zone->next = 0;
+}
+
+return zone;
+}
+
+/*
+ * Check if we can open a zone without exceeding open/active limits.
+ * AOR stands for "Active and Open Resources" (see TP 4053 section 2.5).
+ */
+static int nvme_aor_check(NvmeCtrl *n, NvmeNamespace *ns,
+ uint32_t act, uint32_t opn)
+{
+if (n->params.max_active_zones != 0 &&
+ns->nr_active_zones + act > n->params.max_active_zones) {
+trace_pci_nvme_err_insuff_active_res(n->params.max_active_zones);
+return NVME_ZONE_TOO_MANY_ACTIVE | NVME_DNR;
+}
+if (n->params.max_open_zones != 0 &&
+ns->nr_open_zones + opn > n->params.max_open_zones) {
+trace_pci_nvme_err_insuff_open_res(n->params.max_open_zones);
+return NVME_ZONE_TOO_MANY_OPEN | NVME_DNR;
+}
+
+return NVME_SUCCESS;
+}
+
+static inline void nvme_aor_inc_open(NvmeCtrl *n, NvmeNamespace *ns)
+{
+assert(ns->nr_open_zones >= 0);
+if (n->params.max_open_zones) {
+ns->nr_open_zones++;
+assert(ns->nr_open_zones <= n->params.max_open_zones);
+}
+}
+
+static inline void nvme_aor_dec_open(NvmeCtrl *n, NvmeNamespace *ns)
+{
+if (n->params.max_open_zones) {
+assert(ns->nr_open_zones > 0);
+ns->nr_open_zones--;
+}
+assert(ns->nr_open_zones >= 0);
+}
+
+static inline void nvme_aor_inc_active(NvmeCtrl *n, NvmeNamespace *ns)
+{
+assert(ns->nr_active_zones >= 0);
+if (n->params.max_active_zones) {
+ns->nr_active_zones++;
+assert(ns->nr_active_zones <= n->params.max_active_zones);
+}
+}
+
+static inline void nvme_aor_dec_active(NvmeCtrl *n, NvmeNamespace *ns)
+{
+if (n->params.max_active_zones) {
+assert(ns->nr_active_zones > 0);
+ns->nr_active_zones--;
+assert(ns->nr_active_zones >= ns->nr_open_zones);
+}
+assert(ns->nr_active_zones >= 0);
+}
+
 static void nvme_assign_zone_state(NvmeCtrl *n, NvmeNamespace *ns,
 NvmeZone *zone, uint8_t state)
 {
@@ -454,6 +535,24 @@ static void nvme_enqueue_req_completion(NvmeCQueue *cq, 
NvmeRequest *req)
 timer_mod(cq->timer, qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) + 500);
 }
 
+static void nvme_auto_transition_zone(NvmeCtrl *n, NvmeNamespace *ns,
+bool implicit, bool adding_active)
+{
+NvmeZone *zone;
+
+if (implicit && n->params.max_open_zones &&
+ns->nr_open_zones == n->params.max_open_zones) {
+zone = nvme_remove_zone_head(n, ns, ns->imp_open_zones);
+if (zone) {
+/*
+ * Automatically close this implicitly open zone.
+ */
+nvme_aor_dec_open(n, ns);
+nvme_assign_zone_state(n, ns, zone, NVME_ZONE_STATE_CLOSED);
+}
+}
+}
+
 static uint16_t nvme_check_zone_write(NvmeZone *zone, uint64_t slba,
 uint32_t nlb)
 {
@@ -531,6 +630,23 @@ static uint16_t nvme_check_zone_read(NvmeCtrl *n, NvmeZone 
*zone, uint64_t slba,
 return status;
 }
 
+static uint16_t nvme_auto_open_zone(NvmeCtrl *n, NvmeNamespace *ns,
+NvmeZone *zone)
+{
+uint16_t status = NVME_SUCCESS;
+uint8_t zs = nvme_get_zone_state(zone);
+
+if (zs == NVME_ZONE_STATE_EMPTY) {
+nvme_auto_transition_zone(n, ns, true, true);
+status = nvme_aor_check(n, ns, 1, 1);
+} else if (zs == NVME_ZONE_STATE_CLOSED) {
+nvme_auto_transition_zone(n, ns, true, false);
+status = nvme_aor_check(n, ns, 0, 1);
+}
+
+return status;
+}
+
 static uint64_t nvme_finalize_zone_write(NvmeCtrl *n, NvmeNamespace *ns,
 NvmeZone *zone, uint32_t nlb)
 {
@@ -543,7 +659,11 @@ static uint64_t nvme_finalize_zone_write(NvmeCtrl *n, 
NvmeNamespace *ns,
 switch (zs) {
 case NVM