[PATCH v2] mtd: spinand: cache the last read page to avoid redundant SPI operations

[fzz]

From: Zongzhen Feng <1768315307 at qq.com>

When squashfs reads files through mtdblock, the mtdblock layer
splits I/O into 512-byte sectors. For a 4K-page SPI NAND, this
means reading the same page 8 times (4096 / 512), generating 7x
redundant SPI read-from-cache operations. Each such operation
involves a full SPI bus transaction, significantly slowing down
boot time and file access.

Cache the last successfully read page in spinand_device to avoid
these redundant operations. When the same {target, eraseblock,
page} is requested consecutively, the data is served directly
from the bounce buffer (databuf) via memcpy, skipping the SPI
transaction entirely.

The cache is invalidated on write and erase operations. RAW reads,
OOB reads, and continuous reads are excluded from caching to
maintain correctness.

Signed-off-by: Zongzhen Feng <1768315307 at qq.com>
---
v2: fix build error (use req->mode != MTD_OPS_RAW instead of
    req->disable_ecc), fix whitespace noise, use real name
---
 drivers/mtd/nand/spi/core.c | 34 ++++++++++++++++++++++++++++++++++
 include/linux/mtd/spinand.h |  9 +++++++++
 2 files changed, 43 insertions(+)

diff --git a/drivers/mtd/nand/spi/core.c b/drivers/mtd/nand/spi/core.c
index 8bf9301f25e7..21bc29ae62b8 100644
--- a/drivers/mtd/nand/spi/core.c
+++ b/drivers/mtd/nand/spi/core.c
@@ -560,6 +560,13 @@ static int spinand_read_from_cache_op(struct spinand_device *spinand,
 			       req->ooblen);
 	}
 
+	if (req->datalen && !req->continuous && req->mode != MTD_OPS_RAW) {
+		spinand->cur_target_cache = req->pos.target;
+		spinand->cur_block_cache = req->pos.eraseblock;
+		spinand->cur_page_cache = req->pos.page;
+		spinand->cache_valid = true;
+	}
+
 	return 0;
 }
 
@@ -833,6 +840,20 @@ static int spinand_mtd_regular_page_read(struct mtd_info *mtd, loff_t from,
 		if (disable_ecc)
 			iter.req.mode = MTD_OPS_RAW;
 
+		if (spinand->cache_valid && !disable_ecc &&
+		    !iter.req.ooblen &&
+		    iter.req.pos.target == spinand->cur_target_cache &&
+		    iter.req.pos.eraseblock == spinand->cur_block_cache &&
+		    iter.req.pos.page == spinand->cur_page_cache) {
+			if (iter.req.datalen)
+				memcpy(iter.req.databuf.in,
+				       spinand->databuf + iter.req.dataoffs,
+				       iter.req.datalen);
+			ops->retlen += iter.req.datalen;
+			ops->oobretlen += iter.req.ooblen;
+			continue;
+		}
+
 		ret = spinand_select_target(spinand, iter.req.pos.target);
 		if (ret)
 			break;
@@ -1064,6 +1085,12 @@ static int spinand_mtd_write(struct mtd_info *mtd, loff_t to,
 		if (ret)
 			break;
 
+		if (spinand->cache_valid &&
+		    iter.req.pos.target == spinand->cur_target_cache &&
+		    iter.req.pos.eraseblock == spinand->cur_block_cache &&
+		    iter.req.pos.page == spinand->cur_page_cache)
+			spinand->cache_valid = false;
+
 		ret = spinand_write_page(spinand, &iter.req);
 		if (ret)
 			break;
@@ -1188,6 +1215,11 @@ static int spinand_erase(struct nand_device *nand, const struct nand_pos *pos)
 	if (!ret && (status & STATUS_ERASE_FAILED))
 		ret = -EIO;
 
+	if (!ret && spinand->cache_valid &&
+	    spinand->cur_target_cache == pos->target &&
+	    spinand->cur_block_cache == pos->eraseblock)
+		spinand->cache_valid = false;
+
 	return ret;
 }
 
@@ -2025,6 +2057,7 @@ static void spinand_cleanup(struct spinand_device *spinand)
 	nanddev_ecc_engine_cleanup(nand);
 	nanddev_cleanup(nand);
 	spinand_manufacturer_cleanup(spinand);
+	spinand->cache_valid = false;
 	kfree(spinand->databuf);
 	kfree(spinand->scratchbuf);
 }
@@ -2044,6 +2077,7 @@ static int spinand_probe(struct spi_mem *mem)
 	spi_mem_set_drvdata(mem, spinand);
 	spinand_set_of_node(spinand, mem->spi->dev.of_node);
 	mutex_init(&spinand->lock);
+	spinand->cache_valid = false;
 	mtd = spinand_to_mtd(spinand);
 	mtd->dev.parent = &mem->spi->dev;
 
diff --git a/include/linux/mtd/spinand.h b/include/linux/mtd/spinand.h
index 5f4c00ae72a7..887ef6d34a41 100644
--- a/include/linux/mtd/spinand.h
+++ b/include/linux/mtd/spinand.h
@@ -757,6 +757,10 @@ struct spinand_mem_ops {
  *		   a command addressing a page or an eraseblock embedded in
  *		   this die. Only required if your chip exposes several dies
  * @cur_target: currently selected target/die
+ * @cur_target_cache: target of the cached page
+ * @cur_block_cache: eraseblock of the cached page
+ * @cur_page_cache: page number of the cached page
+ * @cache_valid: whether the cached page is valid
  * @eccinfo: on-die ECC information
  * @cfg_cache: config register cache. One entry per die
  * @databuf: bounce buffer for data
@@ -798,6 +802,11 @@ struct spinand_device {
 			     unsigned int target);
 	unsigned int cur_target;
 
+	unsigned int cur_target_cache;
+	unsigned int cur_block_cache;
+	unsigned int cur_page_cache;
+	bool cache_valid;
+
 	struct spinand_ecc_info eccinfo;
 
 	u8 *cfg_cache;
-- 
2.25.1