qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: frank.chang@sifive.com
To: qemu-devel@nongnu.org, qemu-riscv@nongnu.org
Cc: Frank Chang <frank.chang@sifive.com>,
	Bin Meng <bin.meng@windriver.com>,
	Green Wan <green.wan@sifive.com>, Max Hsu <max.hsu@sifive.com>,
	Alistair Francis <Alistair.Francis@wdc.com>,
	Palmer Dabbelt <palmer@dabbelt.com>,
	Bin Meng <bmeng.cn@gmail.com>
Subject: [PATCH v2 3/4] hw/dma: sifive_pdma: allow non-multiple transaction size transactions
Date: Sun, 12 Sep 2021 20:44:19 +0800	[thread overview]
Message-ID: <20210912124425.166071-4-frank.chang@sifive.com> (raw)
In-Reply-To: <20210912124425.166071-2-frank.chang@sifive.com>

From: Green Wan <green.wan@sifive.com>

Real PDMA is able to deal with non-multiple transaction size transactions.

The following result is PDMA tested in U-Boot on Unmatched board:

=> mw.l 0x3000000 0x0                      <= Disclaim channel 0
=> mw.l 0x3000000 0x1                      <= Claim channel 0
=> mw.l 0x3000004 0x11000000               <= wsize = rsize = 1 (2^1 = 2 bytes)
=> mw.q 0x3000008 0x3                      <= NextBytes = 3
=> mw.q 0x3000010 0x84000000               <= NextDestination = 0x84000000
=> mw.q 0x3000018 0x84001000               <= NextSource = 0x84001000
=> mw.l 0x84000000 0x87654321              <= Fill test data to dst
=> mw.l 0x84001000 0x12345678              <= Fill test data to src
=> md.l 0x84000000 1; md.l 0x84001000 1    <= Dump src/dst memory contents
84000000: 87654321                               !Ce.
84001000: 12345678                               xV4.
=> md.l 0x3000000 8                        <= Dump PDMA status
03000000: 00000001 11000000 00000003 00000000    ................
03000010: 84000000 00000000 84001000 00000000    ................
=> mw.l 0x3000000 0x3                      <= Set channel 0 run and claim bits
=> md.l 0x3000000 8                        <= Dump PDMA status
03000000: 40000001 11000000 00000003 00000000    ...@............
03000010: 84000000 00000000 84001000 00000000    ................
=> md.l 0x84000000 1; md.l 0x84001000 1    <= Dump src/dst memory contents
84000000: 87345678                               xV4.
84001000: 12345678                               xV4.

Signed-off-by: Green Wan <green.wan@sifive.com>
Reviewed-by: Frank Chang <frank.chang@sifive.com>
Tested-by: Max Hsu <max.hsu@sifive.com>
Reviewed-by: Bin Meng <bmeng.cn@gmail.com>
Tested-by: Bin Meng <bmeng.cn@gmail.com>
---
 hw/dma/sifive_pdma.c | 16 ++++++++++------
 1 file changed, 10 insertions(+), 6 deletions(-)

diff --git a/hw/dma/sifive_pdma.c b/hw/dma/sifive_pdma.c
index a8ce3e6699a..d7d2c53e97e 100644
--- a/hw/dma/sifive_pdma.c
+++ b/hw/dma/sifive_pdma.c
@@ -74,7 +74,7 @@ static void sifive_pdma_run(SiFivePDMAState *s, int ch)
     uint64_t dst = s->chan[ch].next_dst;
     uint64_t src = s->chan[ch].next_src;
     uint32_t config = s->chan[ch].next_config;
-    int wsize, rsize, size;
+    int wsize, rsize, size, remainder;
     uint8_t buf[64];
     int n;

@@ -106,11 +106,7 @@ static void sifive_pdma_run(SiFivePDMAState *s, int ch)
         size = 6;
     }
     size = 1 << size;
-
-    /* the bytes to transfer should be multiple of transaction size */
-    if (bytes % size) {
-        goto error;
-    }
+    remainder = bytes % size;

     /* indicate a DMA transfer is started */
     s->chan[ch].state = DMA_CHAN_STATE_STARTED;
@@ -131,6 +127,14 @@ static void sifive_pdma_run(SiFivePDMAState *s, int ch)
         s->chan[ch].exec_bytes -= size;
     }

+    if (remainder) {
+        cpu_physical_memory_read(s->chan[ch].exec_src, buf, remainder);
+        cpu_physical_memory_write(s->chan[ch].exec_dst, buf, remainder);
+        s->chan[ch].exec_src += remainder;
+        s->chan[ch].exec_dst += remainder;
+        s->chan[ch].exec_bytes -= remainder;
+    }
+
     /* indicate a DMA transfer is done */
     s->chan[ch].state = DMA_CHAN_STATE_DONE;
     s->chan[ch].control &= ~CONTROL_RUN;
--
2.25.1



  parent reply	other threads:[~2021-09-12 12:53 UTC|newest]

Thread overview: 4+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-09-12 12:44 [PATCH v2 1/4] hw/dma: sifive_pdma: reset Next* registers when Control.claim is set frank.chang
2021-09-12 12:44 ` [PATCH v2 2/4] hw/dma: sifive_pdma: claim bit must be set before DMA transactions frank.chang
2021-09-12 12:44 ` frank.chang [this message]
2021-09-12 12:44 ` [PATCH v2 4/4] hw/dma: sifive_pdma: don't set Control.error if 0 bytes to transfer frank.chang

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=20210912124425.166071-4-frank.chang@sifive.com \
    --to=frank.chang@sifive.com \
    --cc=Alistair.Francis@wdc.com \
    --cc=bin.meng@windriver.com \
    --cc=bmeng.cn@gmail.com \
    --cc=green.wan@sifive.com \
    --cc=max.hsu@sifive.com \
    --cc=palmer@dabbelt.com \
    --cc=qemu-devel@nongnu.org \
    --cc=qemu-riscv@nongnu.org \
    /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: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).