From: Alexander Kochetkov <al.kochet@gmail.com> To: Dan Williams <dan.j.williams@intel.com>, Vinod Koul <vinod.koul@intel.com>, dmaengine@vger.kernel.org, linux-kernel@vger.kernel.org, linux-rockchip@lists.infradead.org, hhb@rock-chips.com, shawn.lin@rock-chips.com, caesar.wang@rock-chips.com, sugar.zhang@rock-chips.com, ulysses.huang@rock-chips.com Cc: Alexander Kochetkov <al.kochet@gmail.com> Subject: [PATCH 2/2] dmaengine: pl330: don't emit code for one iteration loop Date: Fri, 14 Apr 2017 17:35:30 +0300 [thread overview] Message-ID: <1492180531-1780-3-git-send-email-al.kochet@gmail.com> (raw) In-Reply-To: <1492180531-1780-1-git-send-email-al.kochet@gmail.com> The patch remove one iteration outer loop in the _loop(). Removing loop saves 4 bytes of MicroCode buffer. This savings make sense for free-running cyclic transfer implementation. DMALP_0 0 ... DMALPENDA_0 bjmpto_9 Signed-off-by: Alexander Kochetkov <al.kochet@gmail.com> --- drivers/dma/pl330.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/dma/pl330.c b/drivers/dma/pl330.c index 56a2377..6126dde 100644 --- a/drivers/dma/pl330.c +++ b/drivers/dma/pl330.c @@ -1268,7 +1268,7 @@ static inline int _loop(struct pl330_dmac *pl330, unsigned dry_run, u8 buf[], lpend.bjump = 0; szlpend = _emit_LPEND(1, buf, &lpend); - if (lcnt0) { + if (lcnt0 > 1) { szlp *= 2; szlpend *= 2; } @@ -1284,7 +1284,7 @@ static inline int _loop(struct pl330_dmac *pl330, unsigned dry_run, u8 buf[], off = 0; - if (lcnt0) { + if (lcnt0 > 1) { off += _emit_LP(dry_run, &buf[off], 0, lcnt0); ljmp0 = off; } @@ -1300,7 +1300,7 @@ static inline int _loop(struct pl330_dmac *pl330, unsigned dry_run, u8 buf[], lpend.bjump = off - ljmp1; off += _emit_LPEND(dry_run, &buf[off], &lpend); - if (lcnt0) { + if (lcnt0 > 1) { lpend.cond = ALWAYS; lpend.forever = false; lpend.loop = 0; @@ -1309,7 +1309,7 @@ static inline int _loop(struct pl330_dmac *pl330, unsigned dry_run, u8 buf[], } *bursts = lcnt1 * cyc; - if (lcnt0) + if (lcnt0 > 1) *bursts *= lcnt0; return off; -- 1.7.9.5
WARNING: multiple messages have this Message-ID (diff)
From: Alexander Kochetkov <al.kochet-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org> To: Dan Williams <dan.j.williams-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>, Vinod Koul <vinod.koul-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>, dmaengine-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, linux-rockchip-IAPFreCvJWM7uuMidbF8XUB+6BGkLq7r@public.gmane.org, hhb-TNX95d0MmH7DzftRWevZcw@public.gmane.org, shawn.lin-TNX95d0MmH7DzftRWevZcw@public.gmane.org, caesar.wang-TNX95d0MmH7DzftRWevZcw@public.gmane.org, sugar.zhang-TNX95d0MmH7DzftRWevZcw@public.gmane.org, ulysses.huang-TNX95d0MmH7DzftRWevZcw@public.gmane.org Cc: Alexander Kochetkov <al.kochet-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org> Subject: [PATCH 2/2] dmaengine: pl330: don't emit code for one iteration loop Date: Fri, 14 Apr 2017 17:35:30 +0300 [thread overview] Message-ID: <1492180531-1780-3-git-send-email-al.kochet@gmail.com> (raw) In-Reply-To: <1492180531-1780-1-git-send-email-al.kochet-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org> The patch remove one iteration outer loop in the _loop(). Removing loop saves 4 bytes of MicroCode buffer. This savings make sense for free-running cyclic transfer implementation. DMALP_0 0 ... DMALPENDA_0 bjmpto_9 Signed-off-by: Alexander Kochetkov <al.kochet-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org> --- drivers/dma/pl330.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/dma/pl330.c b/drivers/dma/pl330.c index 56a2377..6126dde 100644 --- a/drivers/dma/pl330.c +++ b/drivers/dma/pl330.c @@ -1268,7 +1268,7 @@ static inline int _loop(struct pl330_dmac *pl330, unsigned dry_run, u8 buf[], lpend.bjump = 0; szlpend = _emit_LPEND(1, buf, &lpend); - if (lcnt0) { + if (lcnt0 > 1) { szlp *= 2; szlpend *= 2; } @@ -1284,7 +1284,7 @@ static inline int _loop(struct pl330_dmac *pl330, unsigned dry_run, u8 buf[], off = 0; - if (lcnt0) { + if (lcnt0 > 1) { off += _emit_LP(dry_run, &buf[off], 0, lcnt0); ljmp0 = off; } @@ -1300,7 +1300,7 @@ static inline int _loop(struct pl330_dmac *pl330, unsigned dry_run, u8 buf[], lpend.bjump = off - ljmp1; off += _emit_LPEND(dry_run, &buf[off], &lpend); - if (lcnt0) { + if (lcnt0 > 1) { lpend.cond = ALWAYS; lpend.forever = false; lpend.loop = 0; @@ -1309,7 +1309,7 @@ static inline int _loop(struct pl330_dmac *pl330, unsigned dry_run, u8 buf[], } *bursts = lcnt1 * cyc; - if (lcnt0) + if (lcnt0 > 1) *bursts *= lcnt0; return off; -- 1.7.9.5
next prev parent reply other threads:[~2017-04-14 14:36 UTC|newest] Thread overview: 9+ messages / expand[flat|nested] mbox.gz Atom feed top 2017-04-14 14:35 [PATCH 0/2] Free running cyclic transfer implementation for pl330 Alexander Kochetkov 2017-04-14 14:35 ` Alexander Kochetkov 2017-04-14 14:35 ` [PATCH 1/2] dmaengine: pl330: make cyclic transfer free runnable Alexander Kochetkov 2017-04-14 14:35 ` Alexander Kochetkov 2017-04-14 18:04 ` Krzysztof Kozlowski 2017-04-14 14:35 ` Alexander Kochetkov [this message] 2017-04-14 14:35 ` [PATCH 2/2] dmaengine: pl330: don't emit code for one iteration loop Alexander Kochetkov 2017-04-18 2:26 ` [PATCH 0/2] Free running cyclic transfer implementation for pl330 sugar 2017-04-26 17:01 ` Alexander Kochetkov
Reply instructions: You may reply publicly to this message via plain-text email using any one of the following methods: * Save the following mbox file, import it into your mail client, and reply-to-all from there: mbox Avoid top-posting and favor interleaved quoting: https://en.wikipedia.org/wiki/Posting_style#Interleaved_style * Reply using the --to, --cc, and --in-reply-to switches of git-send-email(1): git send-email \ --in-reply-to=1492180531-1780-3-git-send-email-al.kochet@gmail.com \ --to=al.kochet@gmail.com \ --cc=caesar.wang@rock-chips.com \ --cc=dan.j.williams@intel.com \ --cc=dmaengine@vger.kernel.org \ --cc=hhb@rock-chips.com \ --cc=linux-kernel@vger.kernel.org \ --cc=linux-rockchip@lists.infradead.org \ --cc=shawn.lin@rock-chips.com \ --cc=sugar.zhang@rock-chips.com \ --cc=ulysses.huang@rock-chips.com \ --cc=vinod.koul@intel.com \ /path/to/YOUR_REPLY https://kernel.org/pub/software/scm/git/docs/git-send-email.html * If your mail client supports setting the In-Reply-To header via mailto: links, try the mailto: linkBe sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes, see mirroring instructions on how to clone and mirror all data and code used by this external index.