| Message ID | 20220510122620.150342-1-angelogioacchino.delregno@collabora.com |
|---|---|
| State | New |
| Headers | show |
| Series | Revert "serial: 8250_mtk: Make sure to select the right FEATURE_SEL" | expand |
Il 10/05/22 17:29, AngeloGioacchino Del Regno ha scritto: > Il 10/05/22 14:56, Mark Brown ha scritto: >> On Tue, May 10, 2022 at 02:46:28PM +0200, AngeloGioacchino Del Regno wrote: >> >>> Sorry for missing this tag, and also I'm sorry for the noise. >> >> Hey, if nobody broke anything all this testing stuff wouldn't be worth >> it! > > > Haha! That's true :-) > > Thank you! Hello Mark, Greg I've just noticed that v5.18 was released, but without this revert. Can you schedule this for backport on v5.18? Thanks, Angelo
Il 23/05/22 14:10, Greg KH ha scritto: > On Mon, May 23, 2022 at 12:17:06PM +0200, AngeloGioacchino Del Regno wrote: >> Il 10/05/22 17:29, AngeloGioacchino Del Regno ha scritto: >>> Il 10/05/22 14:56, Mark Brown ha scritto: >>>> On Tue, May 10, 2022 at 02:46:28PM +0200, AngeloGioacchino Del Regno wrote: >>>> >>>>> Sorry for missing this tag, and also I'm sorry for the noise. >>>> >>>> Hey, if nobody broke anything all this testing stuff wouldn't be worth >>>> it! >>> >>> >>> Haha! That's true :-) >>> >>> Thank you! >> >> >> Hello Mark, Greg >> >> I've just noticed that v5.18 was released, but without this revert. > > What is "this revert"? > "this revert" == "this commit", reverting 6f81fdded0d0 ("serial: 8250_mtk: Make sure to select the right FEATURE_SEL") >> Can you schedule this for backport on v5.18? > > I need more context here, sorry. > As stated in the commit description, some MediaTek SoCs are incompatible with this change, hence it's actually breaking late serial for some machines. > greg k-h
diff --git a/drivers/tty/serial/8250/8250_mtk.c b/drivers/tty/serial/8250/8250_mtk.c index 21053db93ff1..54051ec7b499 100644 --- a/drivers/tty/serial/8250/8250_mtk.c +++ b/drivers/tty/serial/8250/8250_mtk.c @@ -54,9 +54,6 @@ #define MTK_UART_TX_TRIGGER 1 #define MTK_UART_RX_TRIGGER MTK_UART_RX_SIZE -#define MTK_UART_FEATURE_SEL 39 /* Feature Selection register */ -#define MTK_UART_FEAT_NEWRMAP BIT(0) /* Use new register map */ - #define MTK_UART_XON1 40 /* I/O: Xon character 1 */ #define MTK_UART_XOFF1 42 /* I/O: Xoff character 1 */ @@ -575,10 +572,6 @@ static int mtk8250_probe(struct platform_device *pdev) uart.dma = data->dma; #endif - /* Set AP UART new register map */ - writel(MTK_UART_FEAT_NEWRMAP, uart.port.membase + - (MTK_UART_FEATURE_SEL << uart.port.regshift)); - /* Disable Rate Fix function */ writel(0x0, uart.port.membase + (MTK_UART_RATE_FIX << uart.port.regshift));
It was found that some MediaTek SoCs are incompatible with this change. Also, this register was mistakenly understood as it was related to the 16550A register layout selection but, at least on some IPs, if not all, it's related to something else unknown. This reverts commit 6f81fdded0d024c7d4084d434764f30bca1cd6b1. Signed-off-by: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com> --- drivers/tty/serial/8250/8250_mtk.c | 7 ------- 1 file changed, 7 deletions(-)