lightnvm: pblk: garbage collect lines with failed writes

Write failures should not happen under normal circumstances,
so in order to bring the chunk back into a known state as soon
as possible, evacuate all the valid data out of the line and let the
fw judge if the block can be written to in the next reset cycle.

Do this by introducing a new gc list for lines with failed writes,
and ensure that the rate limiter allocates a small portion of
the write bandwidth to get the job done.

The lba list is saved in memory for use during gc as we
cannot gurantee that the emeta data is readable if a write
error occurred.

Signed-off-by: Hans Holmberg <hans.holmberg@cnexlabs.com>
Reviewed-by: Javier González <javier@cnexlabs.com>
Signed-off-by: Matias Bjørling <mb@lightnvm.io>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

1 files changed, 25 insertions, 4 deletions

diff --git a/drivers/lightnvm/pblk-rl.c b/drivers/lightnvm/pblk-rl.c
index 883a7113b19d..6a0616a6fcaf 100644
--- a/drivers/lightnvm/pblk-rl.c
+++ b/drivers/lightnvm/pblk-rl.c
@@ -73,6 +73,16 @@ void pblk_rl_user_in(struct pblk_rl *rl, int nr_entries)
         pblk_rl_kick_u_timer(rl);
 }
 
+void pblk_rl_werr_line_in(struct pblk_rl *rl)
+{
+        atomic_inc(&rl->werr_lines);
+}
+
+void pblk_rl_werr_line_out(struct pblk_rl *rl)
+{
+        atomic_dec(&rl->werr_lines);
+}
+
 void pblk_rl_gc_in(struct pblk_rl *rl, int nr_entries)
 {
         atomic_add(nr_entries, &rl->rb_gc_cnt);
@@ -99,11 +109,21 @@ static void __pblk_rl_update_rates(struct pblk_rl *rl,
 {
         struct pblk *pblk = container_of(rl, struct pblk, rl);
         int max = rl->rb_budget;
+        int werr_gc_needed = atomic_read(&rl->werr_lines);
 
         if (free_blocks >= rl->high) {
-                rl->rb_user_max = max;
-                rl->rb_gc_max = 0;
-                rl->rb_state = PBLK_RL_HIGH;
+                if (werr_gc_needed) {
+                        /* Allocate a small budget for recovering
+                         * lines with write errors
+                         */
+                        rl->rb_gc_max = 1 << rl->rb_windows_pw;
+                        rl->rb_user_max = max - rl->rb_gc_max;
+                        rl->rb_state = PBLK_RL_WERR;
+                } else {
+                        rl->rb_user_max = max;
+                        rl->rb_gc_max = 0;
+                        rl->rb_state = PBLK_RL_OFF;
+                }
         } else if (free_blocks < rl->high) {
                 int shift = rl->high_pw - rl->rb_windows_pw;
                 int user_windows = free_blocks >> shift;
@@ -124,7 +144,7 @@ static void __pblk_rl_update_rates(struct pblk_rl *rl,
                 rl->rb_state = PBLK_RL_LOW;
         }
 
-        if (rl->rb_state == (PBLK_RL_MID | PBLK_RL_LOW))
+        if (rl->rb_state != PBLK_RL_OFF)
                 pblk_gc_should_start(pblk);
         else
                 pblk_gc_should_stop(pblk);
@@ -221,6 +241,7 @@ void pblk_rl_init(struct pblk_rl *rl, int budget)
         atomic_set(&rl->rb_user_cnt, 0);
         atomic_set(&rl->rb_gc_cnt, 0);
         atomic_set(&rl->rb_space, -1);
+        atomic_set(&rl->werr_lines, 0);
 
         timer_setup(&rl->u_timer, pblk_rl_u_timer, 0);