[v2,3/3] event/cnxk: disable timer resolution estimation

  From: Pavan Nikhilesh <pbhagavatula@marvell.com>

Disable timer resolution estimation, read TIM LF clock registers
to get the current running clock counter as estimating causes
time drift.

Signed-off-by: Pavan Nikhilesh <pbhagavatula@marvell.com>
---
 drivers/common/cnxk/hw/tim.h         |   6 ++
 drivers/event/cnxk/cnxk_tim_evdev.c  | 140 +++------------------------
 drivers/event/cnxk/cnxk_tim_evdev.h  |  49 +++++++---
 drivers/event/cnxk/cnxk_tim_worker.c |  18 ----
 drivers/event/cnxk/cnxk_tim_worker.h |   3 +-
 5 files changed, 62 insertions(+), 154 deletions(-)
  

On Wed, Sep 21, 2022 at 11:48 AM <pbhagavatula@marvell.com> wrote:
>
> From: Pavan Nikhilesh <pbhagavatula@marvell.com>
>
> Disable timer resolution estimation, read TIM LF clock registers
> to get the current running clock counter as estimating causes
> time drift.
>
> Signed-off-by: Pavan Nikhilesh <pbhagavatula@marvell.com>


Applied to dpdk-next-net-eventdev/for-main. Thanks


> ---
>  drivers/common/cnxk/hw/tim.h         |   6 ++
>  drivers/event/cnxk/cnxk_tim_evdev.c  | 140 +++------------------------
>  drivers/event/cnxk/cnxk_tim_evdev.h  |  49 +++++++---
>  drivers/event/cnxk/cnxk_tim_worker.c |  18 ----
>  drivers/event/cnxk/cnxk_tim_worker.h |   3 +-
>  5 files changed, 62 insertions(+), 154 deletions(-)
>
> diff --git a/drivers/common/cnxk/hw/tim.h b/drivers/common/cnxk/hw/tim.h
> index a0fe29ddcf..61c38ae175 100644
> --- a/drivers/common/cnxk/hw/tim.h
> +++ b/drivers/common/cnxk/hw/tim.h
> @@ -31,6 +31,12 @@
>  #define TIM_LF_INT_VEC_NRSPERR_INT (0x0ull)
>  #define TIM_LF_INT_VEC_RAS_INT    (0x1ull)
>  #define TIM_LF_RING_AURA          (0x0)
> +#define TIM_LF_FR_RN_GPIOS        (0x020)
> +#define TIM_LF_FR_RN_GTI          (0x030)
> +#define TIM_LF_FR_RN_PTP          (0x040)
> +#define TIM_LF_FR_RN_TENNS        (0x050)
> +#define TIM_LF_FR_RN_SYNCE        (0x060)
> +#define TIM_LF_FR_RN_BTS          (0x070)
>  #define TIM_LF_RING_BASE          (0x130)
>  #define TIM_LF_NRSPERR_INT        (0x200)
>  #define TIM_LF_NRSPERR_INT_W1S    (0x208)
> diff --git a/drivers/event/cnxk/cnxk_tim_evdev.c b/drivers/event/cnxk/cnxk_tim_evdev.c
> index af67235503..f8a536e71a 100644
> --- a/drivers/event/cnxk/cnxk_tim_evdev.c
> +++ b/drivers/event/cnxk/cnxk_tim_evdev.c
> @@ -119,80 +119,6 @@ cnxk_tim_ring_info_get(const struct rte_event_timer_adapter *adptr,
>                    sizeof(struct rte_event_timer_adapter_conf));
>  }
>
> -static inline void
> -sort_multi_array(double ref_arr[], uint64_t arr1[], uint64_t arr2[],
> -                uint64_t arr3[], uint8_t sz)
> -{
> -       int x;
> -
> -       for (x = 0; x < sz - 1; x++) {
> -               if (ref_arr[x] > ref_arr[x + 1]) {
> -                       PLT_SWAP(ref_arr[x], ref_arr[x + 1]);
> -                       PLT_SWAP(arr1[x], arr1[x + 1]);
> -                       PLT_SWAP(arr2[x], arr2[x + 1]);
> -                       PLT_SWAP(arr3[x], arr3[x + 1]);
> -                       x = -1;
> -               }
> -       }
> -}
> -
> -static inline void
> -populate_sample(uint64_t tck[], uint64_t ns[], double diff[], uint64_t dst[],
> -               uint64_t req_tck, uint64_t clk_freq, double tck_ns, uint8_t sz,
> -               bool mov_fwd)
> -{
> -       int i;
> -
> -       for (i = 0; i < sz; i++) {
> -               tck[i] = i ? tck[i - 1] : req_tck;
> -               do {
> -                       mov_fwd ? tck[i]++ : tck[i]--;
> -                       ns[i] = round((double)tck[i] * tck_ns);
> -                       if (round((double)tck[i] * tck_ns) >
> -                           ((double)tck[i] * tck_ns))
> -                               continue;
> -               } while (ns[i] % (uint64_t)cnxk_tim_ns_per_tck(clk_freq));
> -               diff[i] = PLT_MAX((double)ns[i], (double)tck[i] * tck_ns) -
> -                         PLT_MIN((double)ns[i], (double)tck[i] * tck_ns);
> -               dst[i] = mov_fwd ? tck[i] - req_tck : req_tck - tck[i];
> -       }
> -}
> -
> -static void
> -tim_adjust_resolution(uint64_t *req_ns, uint64_t *req_tck, double tck_ns,
> -                     uint64_t clk_freq, uint64_t max_tmo, uint64_t m_tck)
> -{
> -#define MAX_SAMPLES 5
> -       double rmax_diff[MAX_SAMPLES], rmin_diff[MAX_SAMPLES];
> -       uint64_t min_tck[MAX_SAMPLES], max_tck[MAX_SAMPLES];
> -       uint64_t min_dst[MAX_SAMPLES], max_dst[MAX_SAMPLES];
> -       uint64_t min_ns[MAX_SAMPLES], max_ns[MAX_SAMPLES];
> -       int i;
> -
> -       populate_sample(max_tck, max_ns, rmax_diff, max_dst, *req_tck, clk_freq,
> -                       tck_ns, MAX_SAMPLES, true);
> -       sort_multi_array(rmax_diff, max_dst, max_tck, max_ns, MAX_SAMPLES);
> -
> -       populate_sample(min_tck, min_ns, rmin_diff, min_dst, *req_tck, clk_freq,
> -                       tck_ns, MAX_SAMPLES, false);
> -       sort_multi_array(rmin_diff, min_dst, min_tck, min_ns, MAX_SAMPLES);
> -
> -       for (i = 0; i < MAX_SAMPLES; i++) {
> -               if (min_dst[i] < max_dst[i] && min_tck[i] > m_tck &&
> -                   (max_tmo / min_ns[i]) <=
> -                           (TIM_MAX_BUCKET_SIZE - TIM_MIN_BUCKET_SIZE)) {
> -                       *req_tck = min_tck[i];
> -                       *req_ns = min_ns[i];
> -                       break;
> -               } else if ((max_tmo / max_ns[i]) <
> -                          (TIM_MAX_BUCKET_SIZE - TIM_MIN_BUCKET_SIZE)) {
> -                       *req_tck = max_tck[i];
> -                       *req_ns = max_ns[i];
> -                       break;
> -               }
> -       }
> -}
> -
>  static int
>  cnxk_tim_ring_create(struct rte_event_timer_adapter *adptr)
>  {
> @@ -263,27 +189,7 @@ cnxk_tim_ring_create(struct rte_event_timer_adapter *adptr)
>                 goto tim_hw_free;
>         }
>
> -       tim_ring->tck_nsec =
> -               round(RTE_ALIGN_MUL_NEAR((long double)rcfg->timer_tick_ns,
> -                                        cnxk_tim_ns_per_tck(clk_freq)));
> -       if (log10(clk_freq) - floor(log10(clk_freq)) != 0.0) {
> -               uint64_t req_ns, req_tck;
> -               double tck_ns;
> -
> -               req_ns = tim_ring->tck_nsec;
> -               tck_ns = NSECPERSEC / clk_freq;
> -               req_tck = round(rcfg->timer_tick_ns / tck_ns);
> -               tim_adjust_resolution(&req_ns, &req_tck, tck_ns, clk_freq,
> -                                     rcfg->max_tmo_ns, min_intvl_cyc);
> -               if ((tim_ring->tck_nsec != req_ns) &&
> -                   !(rcfg->flags & RTE_EVENT_TIMER_ADAPTER_F_ADJUST_RES)) {
> -                       rc = -ERANGE;
> -                       goto tim_hw_free;
> -               }
> -               tim_ring->tck_nsec = ceil(req_tck * tck_ns);
> -       }
> -
> -       tim_ring->tck_int = round((long double)tim_ring->tck_nsec /
> +       tim_ring->tck_int = round((double)rcfg->timer_tick_ns /
>                                   cnxk_tim_ns_per_tck(clk_freq));
>         tim_ring->tck_nsec =
>                 ceil(tim_ring->tck_int * cnxk_tim_ns_per_tck(clk_freq));
> @@ -296,6 +202,13 @@ cnxk_tim_ring_create(struct rte_event_timer_adapter *adptr)
>         tim_ring->chunk_sz = dev->chunk_sz;
>         tim_ring->disable_npa = dev->disable_npa;
>         tim_ring->enable_stats = dev->enable_stats;
> +       tim_ring->base = roc_tim_lf_base_get(&dev->tim, tim_ring->ring_id);
> +       tim_ring->tbase = cnxk_tim_get_tick_base(clk_src, tim_ring->base);
> +
> +       if (roc_model_is_cn9k() && (tim_ring->clk_src == ROC_TIM_CLK_SRC_GTI))
> +               tim_ring->tick_fn = cnxk_tim_cntvct;
> +       else
> +               tim_ring->tick_fn = cnxk_tim_tick_read;
>
>         for (i = 0; i < dev->ring_ctl_cnt; i++) {
>                 struct cnxk_tim_ctl *ring_ctl = &dev->ring_ctl_data[i];
> @@ -342,7 +255,6 @@ cnxk_tim_ring_create(struct rte_event_timer_adapter *adptr)
>                 goto tim_chnk_free;
>         }
>
> -       tim_ring->base = roc_tim_lf_base_get(&dev->tim, tim_ring->ring_id);
>         plt_write64((uint64_t)tim_ring->bkt, tim_ring->base + TIM_LF_RING_BASE);
>         plt_write64(tim_ring->aura, tim_ring->base + TIM_LF_RING_AURA);
>
> @@ -391,31 +303,6 @@ cnxk_tim_ring_free(struct rte_event_timer_adapter *adptr)
>         return 0;
>  }
>
> -static void
> -cnxk_tim_calibrate_start_tsc(struct cnxk_tim_ring *tim_ring)
> -{
> -#define CNXK_TIM_CALIB_ITER 1E6
> -       uint32_t real_bkt, bucket;
> -       int icount, ecount = 0;
> -       uint64_t bkt_cyc;
> -
> -       for (icount = 0; icount < CNXK_TIM_CALIB_ITER; icount++) {
> -               real_bkt = plt_read64(tim_ring->base + TIM_LF_RING_REL) >> 44;
> -               bkt_cyc = cnxk_tim_cntvct();
> -               bucket = (bkt_cyc - tim_ring->ring_start_cyc) /
> -                        tim_ring->tck_int;
> -               bucket = bucket % (tim_ring->nb_bkts);
> -               tim_ring->ring_start_cyc =
> -                       bkt_cyc - (real_bkt * tim_ring->tck_int);
> -               if (bucket != real_bkt)
> -                       ecount++;
> -       }
> -       tim_ring->last_updt_cyc = bkt_cyc;
> -       plt_tim_dbg("Bucket mispredict %3.2f distance %d\n",
> -                   100 - (((double)(icount - ecount) / (double)icount) * 100),
> -                   bucket - real_bkt);
> -}
> -
>  static int
>  cnxk_tim_ring_start(const struct rte_event_timer_adapter *adptr)
>  {
> @@ -431,12 +318,16 @@ cnxk_tim_ring_start(const struct rte_event_timer_adapter *adptr)
>         if (rc < 0)
>                 return rc;
>
> -       tim_ring->tot_int = tim_ring->tck_int * tim_ring->nb_bkts;
>         tim_ring->fast_div = rte_reciprocal_value_u64(tim_ring->tck_int);
>         tim_ring->fast_bkt = rte_reciprocal_value_u64(tim_ring->nb_bkts);
>
> -       cnxk_tim_calibrate_start_tsc(tim_ring);
> +       if (roc_model_is_cn9k() && (tim_ring->clk_src == ROC_TIM_CLK_SRC_GTI)) {
> +               uint64_t start_diff;
>
> +               start_diff = cnxk_tim_cntvct(tim_ring->tbase) -
> +                            cnxk_tim_tick_read(tim_ring->tbase);
> +               tim_ring->ring_start_cyc += start_diff;
> +       }
>         return rc;
>  }
>
> @@ -462,7 +353,8 @@ cnxk_tim_stats_get(const struct rte_event_timer_adapter *adapter,
>                    struct rte_event_timer_adapter_stats *stats)
>  {
>         struct cnxk_tim_ring *tim_ring = adapter->data->adapter_priv;
> -       uint64_t bkt_cyc = cnxk_tim_cntvct() - tim_ring->ring_start_cyc;
> +       uint64_t bkt_cyc =
> +               tim_ring->tick_fn(tim_ring->tbase) - tim_ring->ring_start_cyc;
>
>         stats->evtim_exp_count =
>                 __atomic_load_n(&tim_ring->arm_cnt, __ATOMIC_RELAXED);
> diff --git a/drivers/event/cnxk/cnxk_tim_evdev.h b/drivers/event/cnxk/cnxk_tim_evdev.h
> index 91a90ee2ce..0fda9f4f13 100644
> --- a/drivers/event/cnxk/cnxk_tim_evdev.h
> +++ b/drivers/event/cnxk/cnxk_tim_evdev.h
> @@ -24,14 +24,14 @@
>
>  #define CNXK_TIM_EVDEV_NAME        cnxk_tim_eventdev
>  #define CNXK_TIM_MAX_BUCKETS       (0xFFFFF)
> -#define CNXK_TIM_RING_DEF_CHUNK_SZ  (4096)
> +#define CNXK_TIM_RING_DEF_CHUNK_SZ  (256)
>  #define CNXK_TIM_CHUNK_ALIGNMENT    (16)
>  #define CNXK_TIM_MAX_BURST         \
>                         (RTE_CACHE_LINE_SIZE / CNXK_TIM_CHUNK_ALIGNMENT)
>  #define CNXK_TIM_NB_CHUNK_SLOTS(sz) (((sz) / CNXK_TIM_CHUNK_ALIGNMENT) - 1)
>  #define CNXK_TIM_MIN_CHUNK_SLOTS    (0x1)
>  #define CNXK_TIM_MAX_CHUNK_SLOTS    (0x1FFE)
> -#define CNXK_TIM_MAX_POOL_CACHE_SZ  (128)
> +#define CNXK_TIM_MAX_POOL_CACHE_SZ  (16)
>
>  #define CN9K_TIM_MIN_TMO_TKS (256)
>
> @@ -119,18 +119,18 @@ struct cnxk_tim_bkt {
>  };
>
>  struct cnxk_tim_ring {
> -       uintptr_t base;
>         uint16_t nb_chunk_slots;
>         uint32_t nb_bkts;
> -       uint64_t last_updt_cyc;
> +       uintptr_t tbase;
> +       uint64_t (*tick_fn)(uint64_t tbase);
>         uint64_t ring_start_cyc;
> -       uint64_t tck_int;
> -       uint64_t tot_int;
>         struct cnxk_tim_bkt *bkt;
>         struct rte_mempool *chunk_pool;
>         struct rte_reciprocal_u64 fast_div;
>         struct rte_reciprocal_u64 fast_bkt;
> +       uint64_t tck_int;
>         uint64_t arm_cnt;
> +       uintptr_t base;
>         uint8_t prod_type_sp;
>         uint8_t enable_stats;
>         uint8_t disable_npa;
> @@ -163,19 +163,19 @@ cnxk_tim_priv_get(void)
>         return mz->addr;
>  }
>
> -static inline long double
> +static inline double
>  cnxk_tim_ns_per_tck(uint64_t freq)
>  {
> -       return (long double)NSECPERSEC / freq;
> +       return (double)NSECPERSEC / freq;
>  }
>
>  #ifdef RTE_ARCH_ARM64
>  static inline uint64_t
> -cnxk_tim_cntvct(void)
> +cnxk_tim_cntvct(uint64_t base __rte_unused)
>  {
>         uint64_t tsc;
>
> -       asm volatile("mrs %0, cntvct_el0" : "=r"(tsc));
> +       asm volatile("mrs %0, CNTVCT_EL0" : "=r"(tsc)::"memory");
>         return tsc;
>  }
>
> @@ -189,7 +189,7 @@ cnxk_tim_cntfrq(void)
>  }
>  #else
>  static inline uint64_t
> -cnxk_tim_cntvct(void)
> +cnxk_tim_cntvct(uint64_t base __rte_unused)
>  {
>         return 0;
>  }
> @@ -201,6 +201,12 @@ cnxk_tim_cntfrq(void)
>  }
>  #endif
>
> +static inline uint64_t
> +cnxk_tim_tick_read(uint64_t tick_base)
> +{
> +       return plt_read64(tick_base);
> +}
> +
>  static inline enum roc_tim_clk_src
>  cnxk_tim_convert_clk_src(enum rte_event_timer_adapter_clk_src clk_src)
>  {
> @@ -221,6 +227,27 @@ cnxk_tim_convert_clk_src(enum rte_event_timer_adapter_clk_src clk_src)
>         }
>  }
>
> +static inline uintptr_t
> +cnxk_tim_get_tick_base(enum roc_tim_clk_src clk_src, uintptr_t base)
> +{
> +       switch (clk_src) {
> +       case ROC_TIM_CLK_SRC_GTI:
> +               return base + TIM_LF_FR_RN_GTI;
> +       case ROC_TIM_CLK_SRC_GPIO:
> +               return base + TIM_LF_FR_RN_GPIOS;
> +       case ROC_TIM_CLK_SRC_10NS:
> +               return base + TIM_LF_FR_RN_TENNS;
> +       case ROC_TIM_CLK_SRC_PTP:
> +               return base + TIM_LF_FR_RN_PTP;
> +       case ROC_TIM_CLK_SRC_SYNCE:
> +               return base + TIM_LF_FR_RN_SYNCE;
> +       case ROC_TIM_CLK_SRC_BTS:
> +               return base + TIM_LF_FR_RN_BTS;
> +       default:
> +               return ROC_TIM_CLK_SRC_INVALID;
> +       }
> +}
> +
>  static inline int
>  cnxk_tim_get_clk_freq(struct cnxk_tim_evdev *dev, enum roc_tim_clk_src clk_src,
>                       uint64_t *freq)
> diff --git a/drivers/event/cnxk/cnxk_tim_worker.c b/drivers/event/cnxk/cnxk_tim_worker.c
> index dfcfbdc797..923a72093b 100644
> --- a/drivers/event/cnxk/cnxk_tim_worker.c
> +++ b/drivers/event/cnxk/cnxk_tim_worker.c
> @@ -39,22 +39,6 @@ cnxk_tim_format_event(const struct rte_event_timer *const tim,
>         entry->wqe = tim->ev.u64;
>  }
>
> -static inline void
> -cnxk_tim_sync_start_cyc(struct cnxk_tim_ring *tim_ring)
> -{
> -       uint64_t cur_cyc = cnxk_tim_cntvct();
> -       uint32_t real_bkt;
> -
> -       if (cur_cyc - tim_ring->last_updt_cyc > tim_ring->tot_int) {
> -               real_bkt = plt_read64(tim_ring->base + TIM_LF_RING_REL) >> 44;
> -               cur_cyc = cnxk_tim_cntvct();
> -
> -               tim_ring->ring_start_cyc =
> -                       cur_cyc - (real_bkt * tim_ring->tck_int);
> -               tim_ring->last_updt_cyc = cur_cyc;
> -       }
> -}
> -
>  static __rte_always_inline uint16_t
>  cnxk_tim_timer_arm_burst(const struct rte_event_timer_adapter *adptr,
>                          struct rte_event_timer **tim, const uint16_t nb_timers,
> @@ -65,7 +49,6 @@ cnxk_tim_timer_arm_burst(const struct rte_event_timer_adapter *adptr,
>         uint16_t index;
>         int ret = 0;
>
> -       cnxk_tim_sync_start_cyc(tim_ring);
>         for (index = 0; index < nb_timers; index++) {
>                 if (cnxk_tim_arm_checks(tim_ring, tim[index]))
>                         break;
> @@ -127,7 +110,6 @@ cnxk_tim_timer_arm_tmo_brst(const struct rte_event_timer_adapter *adptr,
>                 return 0;
>         }
>
> -       cnxk_tim_sync_start_cyc(tim_ring);
>         while (arr_idx < nb_timers) {
>                 for (idx = 0; idx < CNXK_TIM_MAX_BURST && (arr_idx < nb_timers);
>                      idx++, arr_idx++) {
> diff --git a/drivers/event/cnxk/cnxk_tim_worker.h b/drivers/event/cnxk/cnxk_tim_worker.h
> index 0c9f29cfbe..8d8ed1d3a1 100644
> --- a/drivers/event/cnxk/cnxk_tim_worker.h
> +++ b/drivers/event/cnxk/cnxk_tim_worker.h
> @@ -131,7 +131,8 @@ cnxk_tim_get_target_bucket(struct cnxk_tim_ring *const tim_ring,
>                            const uint32_t rel_bkt, struct cnxk_tim_bkt **bkt,
>                            struct cnxk_tim_bkt **mirr_bkt)
>  {
> -       const uint64_t bkt_cyc = cnxk_tim_cntvct() - tim_ring->ring_start_cyc;
> +       const uint64_t bkt_cyc =
> +               tim_ring->tick_fn(tim_ring->tbase) - tim_ring->ring_start_cyc;
>         uint64_t bucket =
>                 rte_reciprocal_divide_u64(bkt_cyc, &tim_ring->fast_div) +
>                 rel_bkt;
> --
> 2.25.1
>