lightnvm: dynamic DMA pool entry size

Currently lightnvm and pblk uses single DMA pool, for which the entry
size always is equal to PAGE_SIZE. The contents of each entry allocated
from the DMA pool consists of a PPA list (8bytes * 64), leaving
56bytes * 64 space for metadata. Since the metadata field can be bigger,
such as 128 bytes, the static size does not cover this use-case.

This patch adds support for I/O metadata above 56 bytes by changing DMA
pool size based on device meta size and allows pblk to use OOB metadata
>=16B.

Reviewed-by: Javier González <javier@cnexlabs.com>
Signed-off-by: Igor Konopko <igor.j.konopko@intel.com>
Signed-off-by: Matias Bjørling <mb@lightnvm.io>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

diff --git a/drivers/lightnvm/core.c b/drivers/lightnvm/core.c
index 69b841d..5f82036 100644 (file)
--- a/drivers/lightnvm/core.c
+++ b/drivers/lightnvm/core.c
@@ -1140,7 +1140,7 @@ EXPORT_SYMBOL(nvm_alloc_dev);
 
 int nvm_register(struct nvm_dev *dev)
 {
-       int ret;
+       int ret, exp_pool_size;
 
        if (!dev->q || !dev->ops)
                return -EINVAL;
@@ -1149,7 +1149,12 @@ int nvm_register(struct nvm_dev *dev)
        if (ret)
                return ret;
 
-       dev->dma_pool = dev->ops->create_dma_pool(dev, "ppalist");
+       exp_pool_size = max_t(int, PAGE_SIZE,
+                             (NVM_MAX_VLBA * (sizeof(u64) + dev->geo.sos)));
+       exp_pool_size = round_up(exp_pool_size, PAGE_SIZE);
+
+       dev->dma_pool = dev->ops->create_dma_pool(dev, "ppalist",
+                                                 exp_pool_size);
        if (!dev->dma_pool) {
                pr_err("nvm: could not create dma pool\n");
                nvm_free(dev);

diff --git a/drivers/lightnvm/pblk-core.c b/drivers/lightnvm/pblk-core.c
index e732b2d..7e3397f 100644 (file)
--- a/drivers/lightnvm/pblk-core.c
+++ b/drivers/lightnvm/pblk-core.c
@@ -250,8 +250,8 @@ int pblk_alloc_rqd_meta(struct pblk *pblk, struct nvm_rq *rqd)
        if (rqd->nr_ppas == 1)
                return 0;
 
-       rqd->ppa_list = rqd->meta_list + pblk_dma_meta_size;
-       rqd->dma_ppa_list = rqd->dma_meta_list + pblk_dma_meta_size;
+       rqd->ppa_list = rqd->meta_list + pblk_dma_meta_size(pblk);
+       rqd->dma_ppa_list = rqd->dma_meta_list + pblk_dma_meta_size(pblk);
 
        return 0;
 }
@@ -846,8 +846,8 @@ int pblk_line_emeta_read(struct pblk *pblk, struct pblk_line *line,
        if (!meta_list)
                return -ENOMEM;
 
-       ppa_list = meta_list + pblk_dma_meta_size;
-       dma_ppa_list = dma_meta_list + pblk_dma_meta_size;
+       ppa_list = meta_list + pblk_dma_meta_size(pblk);
+       dma_ppa_list = dma_meta_list + pblk_dma_meta_size(pblk);
 
 next_rq:
        memset(&rqd, 0, sizeof(struct nvm_rq));

diff --git a/drivers/lightnvm/pblk-init.c b/drivers/lightnvm/pblk-init.c
index 33361bf..ff6a6df 100644 (file)
--- a/drivers/lightnvm/pblk-init.c
+++ b/drivers/lightnvm/pblk-init.c
@@ -406,7 +406,7 @@ static int pblk_core_init(struct pblk *pblk)
        pblk_set_sec_per_write(pblk, pblk->min_write_pgs);
 
        pblk->oob_meta_size = geo->sos;
-       if (pblk->oob_meta_size != sizeof(struct pblk_sec_meta)) {
+       if (pblk->oob_meta_size < sizeof(struct pblk_sec_meta)) {
                pblk_err(pblk, "Unsupported metadata size\n");
                return -EINVAL;
        }

diff --git a/drivers/lightnvm/pblk-recovery.c b/drivers/lightnvm/pblk-recovery.c
index e4dd634..3a775d1 100644 (file)
--- a/drivers/lightnvm/pblk-recovery.c
+++ b/drivers/lightnvm/pblk-recovery.c
@@ -481,8 +481,8 @@ static int pblk_recov_l2p_from_oob(struct pblk *pblk, struct pblk_line *line)
        if (!meta_list)
                return -ENOMEM;
 
-       ppa_list = (void *)(meta_list) + pblk_dma_meta_size;
-       dma_ppa_list = dma_meta_list + pblk_dma_meta_size;
+       ppa_list = (void *)(meta_list) + pblk_dma_meta_size(pblk);
+       dma_ppa_list = dma_meta_list + pblk_dma_meta_size(pblk);
 
        data = kcalloc(pblk->max_write_pgs, geo->csecs, GFP_KERNEL);
        if (!data) {

diff --git a/drivers/lightnvm/pblk.h b/drivers/lightnvm/pblk.h
index 80f3566..9087d53 100644 (file)
--- a/drivers/lightnvm/pblk.h
+++ b/drivers/lightnvm/pblk.h
@@ -104,7 +104,6 @@ enum {
        PBLK_RL_LOW = 4
 };
 
-#define pblk_dma_meta_size (sizeof(struct pblk_sec_meta) * NVM_MAX_VLBA)
 #define pblk_dma_ppa_size (sizeof(u64) * NVM_MAX_VLBA)
 
 /* write buffer completion context */
@@ -1388,4 +1387,9 @@ static inline struct pblk_sec_meta *pblk_get_meta(struct pblk *pblk,
 {
        return meta + pblk->oob_meta_size * index;
 }
+
+static inline int pblk_dma_meta_size(struct pblk *pblk)
+{
+       return pblk->oob_meta_size * NVM_MAX_VLBA;
+}
 #endif /* PBLK_H_ */

diff --git a/drivers/nvme/host/lightnvm.c b/drivers/nvme/host/lightnvm.c
index 51d957c..ba268d7 100644 (file)
--- a/drivers/nvme/host/lightnvm.c
+++ b/drivers/nvme/host/lightnvm.c
@@ -732,11 +732,12 @@ static int nvme_nvm_submit_io_sync(struct nvm_dev *dev, struct nvm_rq *rqd)
        return ret;
 }
 
-static void *nvme_nvm_create_dma_pool(struct nvm_dev *nvmdev, char *name)
+static void *nvme_nvm_create_dma_pool(struct nvm_dev *nvmdev, char *name,
+                                       int size)
 {
        struct nvme_ns *ns = nvmdev->q->queuedata;
 
-       return dma_pool_create(name, ns->ctrl->dev, PAGE_SIZE, PAGE_SIZE, 0);
+       return dma_pool_create(name, ns->ctrl->dev, size, PAGE_SIZE, 0);
 }
 
 static void nvme_nvm_destroy_dma_pool(void *pool)

diff --git a/include/linux/lightnvm.h b/include/linux/lightnvm.h
index 2fdeac1..7afedad 100644 (file)
--- a/include/linux/lightnvm.h
+++ b/include/linux/lightnvm.h
@@ -90,7 +90,7 @@ typedef int (nvm_get_chk_meta_fn)(struct nvm_dev *, sector_t, int,
                                                        struct nvm_chk_meta *);
 typedef int (nvm_submit_io_fn)(struct nvm_dev *, struct nvm_rq *);
 typedef int (nvm_submit_io_sync_fn)(struct nvm_dev *, struct nvm_rq *);
-typedef void *(nvm_create_dma_pool_fn)(struct nvm_dev *, char *);
+typedef void *(nvm_create_dma_pool_fn)(struct nvm_dev *, char *, int);
 typedef void (nvm_destroy_dma_pool_fn)(void *);
 typedef void *(nvm_dev_dma_alloc_fn)(struct nvm_dev *, void *, gfp_t,
                                                                dma_addr_t *);