Hi Boris,
Boris Brezillon boris.brezillon@bootlin.com wrote on Sat, 15 Dec 2018 13:41:37 +0100:
On Tue, 11 Dec 2018 18:38:28 +0100 Miquel Raynal miquel.raynal@bootlin.com wrote:
marvell_nfc_wait_op() waits for completion during 'timeout_ms' milliseconds before throwing an error. While the logic is fine, the value of 'timeout_ms' is given by the core and actually correspond to the maximum time the NAND chip will take to complete the operation. Assuming there is no overhead in the propagation of the interrupt signal to the the NAND controller (through the Ready/Busy line), this delay does not take into account the latency of the operating system. For instance, for a page write, the delay given by the core is rounded up to 1ms. Hence, when the machine is over loaded, there is chances that this timeout will be reached.
There are two ways to solve this issue that are not incompatible: 1/ Enlarge the timeout value (if so, how much?). 2/ Check after the waiting method if we did not miss any interrupt because of the OS latency (an interrupt is still pending). In this case, we assume the operation exited successfully.
We choose the second approach that is a must in all cases, with the possibility to also modify the timeout value to be, e.g. at least 1 second in all cases.
Fixes: 02f26ecf8c77 ("mtd: nand: add reworked Marvell NAND controller driver") Cc: stable@vger.kernel.org Signed-off-by: Miquel Raynal miquel.raynal@bootlin.com
drivers/mtd/nand/raw/marvell_nand.c | 17 ++++++++++++++--- 1 file changed, 14 insertions(+), 3 deletions(-)
diff --git a/drivers/mtd/nand/raw/marvell_nand.c b/drivers/mtd/nand/raw/marvell_nand.c index e6c3739cea73..bc0eef4ade4f 100644 --- a/drivers/mtd/nand/raw/marvell_nand.c +++ b/drivers/mtd/nand/raw/marvell_nand.c @@ -514,9 +514,14 @@ static void marvell_nfc_enable_int(struct marvell_nfc *nfc, u32 int_mask) writel_relaxed(reg & ~int_mask, nfc->regs + NDCR); } -static void marvell_nfc_clear_int(struct marvell_nfc *nfc, u32 int_mask) +static int marvell_nfc_clear_int(struct marvell_nfc *nfc, u32 int_mask)
^ u32 ?With this fixed:
Reviewed-by: Boris Brezillon boris.brezillon@bootlin.com
Applied with your change to nand/next.
Thanks, Miquèl