| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <CA+M3ks74eOSOEwadsjjMcQme_6ivzmYGRdc9jvw4RHYa6dxRTA@mail.gmail.com>
Date: Wed, 11 Oct 2017 16:27:51 +0200
From: Benjamin Gaignard <benjamin.gaignard@...aro.org>
To: Arnd Bergmann <arnd@...db.de>
Cc: Vinod Koul <vinod.koul@...el.com>,
Maxime Coquelin <mcoquelin.stm32@...il.com>,
Alexandre Torgue <alexandre.torgue@...com>,
Linux Kernel Mailing List <linux-kernel@...r.kernel.org>,
Pierre-Yves MORDRET <pierre-yves.mordret@...com>,
dmaengine@...r.kernel.org,
"M'boumba Cedric Madianga" <cedric.madianga@...il.com>,
Dan Williams <dan.j.williams@...el.com>,
linux-arm-kernel@...ts.infradead.org
Subject: Re: [PATCH] dmaengine: stm32-mdma: avoid 64-bit division
2017-10-11 16:01 GMT+02:00 Arnd Bergmann <arnd@...db.de>:
> When building with a 64-bit dma_addr_t, we run into a link
> error:
>
> drivers/dma/stm32-mdma.o: In function `stm32_mdma_prep_dma_memcpy':
> stm32-mdma.c:(.text+0x16a3): undefined reference to `__umoddi3'
>
> Using a 64-bit division here is way too expensive, since the
> divisor is a known power-of-two value in reality. This moves
> the modulo operation into stm32_mdma_get_max_width(), where
> the compiler can optimize out that code, and we can use a 32-bit
> division to be on the safe side.
>
> Fixes: a4ffb13c8946 ("dmaengine: Add STM32 MDMA driver")
> Signed-off-by: Arnd Bergmann <arnd@...db.de>
> ---
> drivers/dma/stm32-mdma.c | 27 ++++++++++++---------------
> 1 file changed, 12 insertions(+), 15 deletions(-)
>
> diff --git a/drivers/dma/stm32-mdma.c b/drivers/dma/stm32-mdma.c
> index 0db59a7e80e0..55151c2c9fae 100644
> --- a/drivers/dma/stm32-mdma.c
> +++ b/drivers/dma/stm32-mdma.c
> @@ -387,7 +387,9 @@ static int stm32_mdma_get_width(struct stm32_mdma_chan *chan,
> }
> }
>
> -static enum dma_slave_buswidth stm32_mdma_get_max_width(u32 buf_len, u32 tlen)
> +static enum dma_slave_buswidth stm32_mdma_get_max_width(u32 buf_len,
> + u32 addr,
> + u32 tlen)
> {
> enum dma_slave_buswidth max_width = DMA_SLAVE_BUSWIDTH_8_BYTES;
>
> @@ -398,6 +400,9 @@ static enum dma_slave_buswidth stm32_mdma_get_max_width(u32 buf_len, u32 tlen)
> break;
> }
>
> + if (addr % max_width)
> + max_width = DMA_SLAVE_BUSWIDTH_1_BYTE;
> +
I'm only half-convince by the implicite 32 bits cast done into
function prototype.
If we keep using dma_addr_t and use do_div() instead of %
does compiler can still optimize the code ?
> return max_width;
> }
>
> @@ -567,7 +572,7 @@ static int stm32_mdma_set_xfer_param(struct stm32_mdma_chan *chan,
> ctcr |= STM32_MDMA_CTCR_DBURST((ilog2(dst_best_burst)));
>
> /* Set memory data size */
> - src_addr_width = stm32_mdma_get_max_width(buf_len, tlen);
> + src_addr_width = stm32_mdma_get_max_width(buf_len, 0, tlen);
> chan->mem_width = src_addr_width;
> src_bus_width = stm32_mdma_get_width(chan, src_addr_width);
> if (src_bus_width < 0)
> @@ -611,7 +616,7 @@ static int stm32_mdma_set_xfer_param(struct stm32_mdma_chan *chan,
> ctcr |= STM32_MDMA_CTCR_SBURST((ilog2(src_best_burst)));
>
> /* Set memory data size */
> - dst_addr_width = stm32_mdma_get_max_width(buf_len, tlen);
> + dst_addr_width = stm32_mdma_get_max_width(buf_len, 0, tlen);
> chan->mem_width = dst_addr_width;
> dst_bus_width = stm32_mdma_get_width(chan, dst_addr_width);
> if (dst_bus_width < 0)
> @@ -956,9 +961,7 @@ stm32_mdma_prep_dma_memcpy(struct dma_chan *c, dma_addr_t dest, dma_addr_t src,
> ctcr |= STM32_MDMA_CTCR_TLEN((tlen - 1));
>
> /* Set source best burst size */
> - max_width = stm32_mdma_get_max_width(len, tlen);
> - if (src % max_width)
> - max_width = DMA_SLAVE_BUSWIDTH_1_BYTE;
> + max_width = stm32_mdma_get_max_width(len, src, tlen);
> src_bus_width = stm32_mdma_get_width(chan, max_width);
>
> max_burst = tlen / max_width;
> @@ -971,9 +974,7 @@ stm32_mdma_prep_dma_memcpy(struct dma_chan *c, dma_addr_t dest, dma_addr_t src,
> STM32_MDMA_CTCR_SINCOS(src_bus_width);
>
> /* Set destination best burst size */
> - max_width = stm32_mdma_get_max_width(len, tlen);
> - if (dest % max_width)
> - max_width = DMA_SLAVE_BUSWIDTH_1_BYTE;
> + max_width = stm32_mdma_get_max_width(len, dest, tlen);
> dst_bus_width = stm32_mdma_get_width(chan, max_width);
>
> max_burst = tlen / max_width;
> @@ -1014,9 +1015,7 @@ stm32_mdma_prep_dma_memcpy(struct dma_chan *c, dma_addr_t dest, dma_addr_t src,
> STM32_MDMA_MAX_BLOCK_LEN);
>
> /* Set source best burst size */
> - max_width = stm32_mdma_get_max_width(len, tlen);
> - if (src % max_width)
> - max_width = DMA_SLAVE_BUSWIDTH_1_BYTE;
> + max_width = stm32_mdma_get_max_width(len, src, tlen);
> src_bus_width = stm32_mdma_get_width(chan, max_width);
>
> max_burst = tlen / max_width;
> @@ -1030,9 +1029,7 @@ stm32_mdma_prep_dma_memcpy(struct dma_chan *c, dma_addr_t dest, dma_addr_t src,
> STM32_MDMA_CTCR_SINCOS(src_bus_width);
>
> /* Set destination best burst size */
> - max_width = stm32_mdma_get_max_width(len, tlen);
> - if (dest % max_width)
> - max_width = DMA_SLAVE_BUSWIDTH_1_BYTE;
> + max_width = stm32_mdma_get_max_width(len, dest, tlen);
> dst_bus_width = stm32_mdma_get_width(chan, max_width);
>
> max_burst = tlen / max_width;
> --
> 2.9.0
>
>
> _______________________________________________
> linux-arm-kernel mailing list
> linux-arm-kernel@...ts.infradead.org
> http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
--
Benjamin Gaignard
Graphic Study Group
Linaro.org │ Open source software for ARM SoCs
Follow Linaro: Facebook | Twitter | Blog
Powered by blists - more mailing lists