From dc3f595b6617ebc0307e0ce151e8f2f2b2489b95 Mon Sep 17 00:00:00 2001 From: Codrin Ciubotariu Date: Wed, 23 Jan 2019 16:33:47 +0000 Subject: dmaengine: at_xdmac: Fix wrongfull report of a channel as in use atchan->status variable is used to store two different information: - pass channel interrupts status from interrupt handler to tasklet; - channel information like whether it is cyclic or paused; This causes a bug when device_terminate_all() is called, (AT_XDMAC_CHAN_IS_CYCLIC cleared on atchan->status) and then a late End of Block interrupt arrives (AT_XDMAC_CIS_BIS), which sets bit 0 of atchan->status. Bit 0 is also used for AT_XDMAC_CHAN_IS_CYCLIC, so when a new descriptor for a cyclic transfer is created, the driver reports the channel as in use: if (test_and_set_bit(AT_XDMAC_CHAN_IS_CYCLIC, &atchan->status)) { dev_err(chan2dev(chan), "channel currently used\n"); return NULL; } This patch fixes the bug by adding a different struct member to keep the interrupts status separated from the channel status bits. Fixes: e1f7c9eee707 ("dmaengine: at_xdmac: creation of the atmel eXtended DMA Controller driver") Signed-off-by: Codrin Ciubotariu Acked-by: Ludovic Desroches Signed-off-by: Vinod Koul --- drivers/dma/at_xdmac.c | 19 ++++++++++--------- 1 file changed, 10 insertions(+), 9 deletions(-) diff --git a/drivers/dma/at_xdmac.c b/drivers/dma/at_xdmac.c index 4e557684f792..fe69dccfa0c0 100644 --- a/drivers/dma/at_xdmac.c +++ b/drivers/dma/at_xdmac.c @@ -203,6 +203,7 @@ struct at_xdmac_chan { u32 save_cim; u32 save_cnda; u32 save_cndc; + u32 irq_status; unsigned long status; struct tasklet_struct tasklet; struct dma_slave_config sconfig; @@ -1580,8 +1581,8 @@ static void at_xdmac_tasklet(unsigned long data) struct at_xdmac_desc *desc; u32 error_mask; - dev_dbg(chan2dev(&atchan->chan), "%s: status=0x%08lx\n", - __func__, atchan->status); + dev_dbg(chan2dev(&atchan->chan), "%s: status=0x%08x\n", + __func__, atchan->irq_status); error_mask = AT_XDMAC_CIS_RBEIS | AT_XDMAC_CIS_WBEIS @@ -1589,15 +1590,15 @@ static void at_xdmac_tasklet(unsigned long data) if (at_xdmac_chan_is_cyclic(atchan)) { at_xdmac_handle_cyclic(atchan); - } else if ((atchan->status & AT_XDMAC_CIS_LIS) - || (atchan->status & error_mask)) { + } else if ((atchan->irq_status & AT_XDMAC_CIS_LIS) + || (atchan->irq_status & error_mask)) { struct dma_async_tx_descriptor *txd; - if (atchan->status & AT_XDMAC_CIS_RBEIS) + if (atchan->irq_status & AT_XDMAC_CIS_RBEIS) dev_err(chan2dev(&atchan->chan), "read bus error!!!"); - if (atchan->status & AT_XDMAC_CIS_WBEIS) + if (atchan->irq_status & AT_XDMAC_CIS_WBEIS) dev_err(chan2dev(&atchan->chan), "write bus error!!!"); - if (atchan->status & AT_XDMAC_CIS_ROIS) + if (atchan->irq_status & AT_XDMAC_CIS_ROIS) dev_err(chan2dev(&atchan->chan), "request overflow error!!!"); spin_lock(&atchan->lock); @@ -1652,7 +1653,7 @@ static irqreturn_t at_xdmac_interrupt(int irq, void *dev_id) atchan = &atxdmac->chan[i]; chan_imr = at_xdmac_chan_read(atchan, AT_XDMAC_CIM); chan_status = at_xdmac_chan_read(atchan, AT_XDMAC_CIS); - atchan->status = chan_status & chan_imr; + atchan->irq_status = chan_status & chan_imr; dev_vdbg(atxdmac->dma.dev, "%s: chan%d: imr=0x%x, status=0x%x\n", __func__, i, chan_imr, chan_status); @@ -1666,7 +1667,7 @@ static irqreturn_t at_xdmac_interrupt(int irq, void *dev_id) at_xdmac_chan_read(atchan, AT_XDMAC_CDA), at_xdmac_chan_read(atchan, AT_XDMAC_CUBC)); - if (atchan->status & (AT_XDMAC_CIS_RBEIS | AT_XDMAC_CIS_WBEIS)) + if (atchan->irq_status & (AT_XDMAC_CIS_RBEIS | AT_XDMAC_CIS_WBEIS)) at_xdmac_write(atxdmac, AT_XDMAC_GD, atchan->mask); tasklet_schedule(&atchan->tasklet); -- cgit From 341198eda723c8c1cddbb006a89ad9e362502ea2 Mon Sep 17 00:00:00 2001 From: Leonid Iziumtsev Date: Tue, 15 Jan 2019 17:15:23 +0000 Subject: dmaengine: imx-dma: fix wrong callback invoke Once the "ld_queue" list is not empty, next descriptor will migrate into "ld_active" list. The "desc" variable will be overwritten during that transition. And later the dmaengine_desc_get_callback_invoke() will use it as an argument. As result we invoke wrong callback. That behaviour was in place since: commit fcaaba6c7136 ("dmaengine: imx-dma: fix callback path in tasklet"). But after commit 4cd13c21b207 ("softirq: Let ksoftirqd do its job") things got worse, since possible delay between tasklet_schedule() from DMA irq handler and actual tasklet function execution got bigger. And that gave more time for new DMA request to be submitted and to be put into "ld_queue" list. It has been noticed that DMA issue is causing problems for "mxc-mmc" driver. While stressing the system with heavy network traffic and writing/reading to/from sd card simultaneously the timeout may happen: 10013000.sdhci: mxcmci_watchdog: read time out (status = 0x30004900) That often lead to file system corruption. Signed-off-by: Leonid Iziumtsev Signed-off-by: Vinod Koul Cc: stable@vger.kernel.org --- drivers/dma/imx-dma.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/dma/imx-dma.c b/drivers/dma/imx-dma.c index c2fff3f6c9ca..4a09af3cd546 100644 --- a/drivers/dma/imx-dma.c +++ b/drivers/dma/imx-dma.c @@ -618,7 +618,7 @@ static void imxdma_tasklet(unsigned long data) { struct imxdma_channel *imxdmac = (void *)data; struct imxdma_engine *imxdma = imxdmac->imxdma; - struct imxdma_desc *desc; + struct imxdma_desc *desc, *next_desc; unsigned long flags; spin_lock_irqsave(&imxdma->lock, flags); @@ -648,10 +648,10 @@ static void imxdma_tasklet(unsigned long data) list_move_tail(imxdmac->ld_active.next, &imxdmac->ld_free); if (!list_empty(&imxdmac->ld_queue)) { - desc = list_first_entry(&imxdmac->ld_queue, struct imxdma_desc, - node); + next_desc = list_first_entry(&imxdmac->ld_queue, + struct imxdma_desc, node); list_move_tail(imxdmac->ld_queue.next, &imxdmac->ld_active); - if (imxdma_xfer_desc(desc) < 0) + if (imxdma_xfer_desc(next_desc) < 0) dev_warn(imxdma->dev, "%s: channel: %d couldn't xfer desc\n", __func__, imxdmac->channel); } -- cgit From f7da7782aba92593f7b82f03d2409a1c5f4db91b Mon Sep 17 00:00:00 2001 From: Lukas Wunner Date: Wed, 23 Jan 2019 09:26:00 +0100 Subject: dmaengine: bcm2835: Fix interrupt race on RT If IRQ handlers are threaded (either because CONFIG_PREEMPT_RT_BASE is enabled or "threadirqs" was passed on the command line) and if system load is sufficiently high that wakeup latency of IRQ threads degrades, SPI DMA transactions on the BCM2835 occasionally break like this: ks8851 spi0.0: SPI transfer timed out bcm2835-dma 3f007000.dma: DMA transfer could not be terminated ks8851 spi0.0 eth2: ks8851_rdfifo: spi_sync() failed The root cause is an assumption made by the DMA driver which is documented in a code comment in bcm2835_dma_terminate_all(): /* * Stop DMA activity: we assume the callback will not be called * after bcm_dma_abort() returns (even if it does, it will see * c->desc is NULL and exit.) */ That assumption falls apart if the IRQ handler bcm2835_dma_callback() is threaded: A client may terminate a descriptor and issue a new one before the IRQ handler had a chance to run. In fact the IRQ handler may miss an *arbitrary* number of descriptors. The result is the following race condition: 1. A descriptor finishes, its interrupt is deferred to the IRQ thread. 2. A client calls dma_terminate_async() which sets channel->desc = NULL. 3. The client issues a new descriptor. Because channel->desc is NULL, bcm2835_dma_issue_pending() immediately starts the descriptor. 4. Finally the IRQ thread runs and writes BCM2835_DMA_INT to the CS register to acknowledge the interrupt. This clears the ACTIVE flag, so the newly issued descriptor is paused in the middle of the transaction. Because channel->desc is not NULL, the IRQ thread finalizes the descriptor and tries to start the next one. I see two possible solutions: The first is to call synchronize_irq() in bcm2835_dma_issue_pending() to wait until the IRQ thread has finished before issuing a new descriptor. The downside of this approach is unnecessary latency if clients desire rapidly terminating and re-issuing descriptors and don't have any use for an IRQ callback. (The SPI TX DMA channel is a case in point.) A better alternative is to make the IRQ thread recognize that it has missed descriptors and avoid finalizing the newly issued descriptor. So first of all, set the ACTIVE flag when acknowledging the interrupt. This keeps a newly issued descriptor running. If the descriptor was finished, the channel remains idle despite the ACTIVE flag being set. However the ACTIVE flag can then no longer be used to check whether the channel is idle, so instead check whether the register containing the current control block address is zero and finalize the current descriptor only if so. That way, there is no impact on latency and throughput if the client doesn't care for the interrupt: Only minimal additional overhead is introduced for non-cyclic descriptors as one further MMIO read is necessary per interrupt to check for idleness of the channel. Cyclic descriptors are sped up slightly by removing one MMIO write per interrupt. Fixes: 96286b576690 ("dmaengine: Add support for BCM2835") Signed-off-by: Lukas Wunner Cc: stable@vger.kernel.org # v3.14+ Cc: Frank Pavlic Cc: Martin Sperl Cc: Florian Meier Cc: Clive Messer Cc: Matthias Reichl Tested-by: Stefan Wahren Acked-by: Florian Kauer Signed-off-by: Vinod Koul --- drivers/dma/bcm2835-dma.c | 33 ++++++++++++++++++--------------- 1 file changed, 18 insertions(+), 15 deletions(-) diff --git a/drivers/dma/bcm2835-dma.c b/drivers/dma/bcm2835-dma.c index 1a44c8086d77..0c3f5c71bb48 100644 --- a/drivers/dma/bcm2835-dma.c +++ b/drivers/dma/bcm2835-dma.c @@ -412,7 +412,12 @@ static int bcm2835_dma_abort(void __iomem *chan_base) long int timeout = 10000; cs = readl(chan_base + BCM2835_DMA_CS); - if (!(cs & BCM2835_DMA_ACTIVE)) + + /* + * A zero control block address means the channel is idle. + * (The ACTIVE flag in the CS register is not a reliable indicator.) + */ + if (!readl(chan_base + BCM2835_DMA_ADDR)) return 0; /* Write 0 to the active bit - Pause the DMA */ @@ -476,8 +481,15 @@ static irqreturn_t bcm2835_dma_callback(int irq, void *data) spin_lock_irqsave(&c->vc.lock, flags); - /* Acknowledge interrupt */ - writel(BCM2835_DMA_INT, c->chan_base + BCM2835_DMA_CS); + /* + * Clear the INT flag to receive further interrupts. Keep the channel + * active in case the descriptor is cyclic or in case the client has + * already terminated the descriptor and issued a new one. (May happen + * if this IRQ handler is threaded.) If the channel is finished, it + * will remain idle despite the ACTIVE flag being set. + */ + writel(BCM2835_DMA_INT | BCM2835_DMA_ACTIVE, + c->chan_base + BCM2835_DMA_CS); d = c->desc; @@ -485,11 +497,7 @@ static irqreturn_t bcm2835_dma_callback(int irq, void *data) if (d->cyclic) { /* call the cyclic callback */ vchan_cyclic_callback(&d->vd); - - /* Keep the DMA engine running */ - writel(BCM2835_DMA_ACTIVE, - c->chan_base + BCM2835_DMA_CS); - } else { + } else if (!readl(c->chan_base + BCM2835_DMA_ADDR)) { vchan_cookie_complete(&c->desc->vd); bcm2835_dma_start_desc(c); } @@ -789,11 +797,7 @@ static int bcm2835_dma_terminate_all(struct dma_chan *chan) list_del_init(&c->node); spin_unlock(&d->lock); - /* - * Stop DMA activity: we assume the callback will not be called - * after bcm_dma_abort() returns (even if it does, it will see - * c->desc is NULL and exit.) - */ + /* stop DMA activity */ if (c->desc) { vchan_terminate_vdesc(&c->desc->vd); c->desc = NULL; @@ -801,8 +805,7 @@ static int bcm2835_dma_terminate_all(struct dma_chan *chan) /* Wait for stopping */ while (--timeout) { - if (!(readl(c->chan_base + BCM2835_DMA_CS) & - BCM2835_DMA_ACTIVE)) + if (!readl(c->chan_base + BCM2835_DMA_ADDR)) break; cpu_relax(); -- cgit From 9e528c799d17a4ac37d788c81440b50377dd592d Mon Sep 17 00:00:00 2001 From: Lukas Wunner Date: Wed, 23 Jan 2019 09:26:00 +0100 Subject: dmaengine: bcm2835: Fix abort of transactions There are multiple issues with bcm2835_dma_abort() (which is called on termination of a transaction): * The algorithm to abort the transaction first pauses the channel by clearing the ACTIVE flag in the CS register, then waits for the PAUSED flag to clear. Page 49 of the spec documents the latter as follows: "Indicates if the DMA is currently paused and not transferring data. This will occur if the active bit has been cleared [...]" https://www.raspberrypi.org/app/uploads/2012/02/BCM2835-ARM-Peripherals.pdf So the function is entering an infinite loop because it is waiting for PAUSED to clear which is always set due to the function having cleared the ACTIVE flag. The only thing that's saving it from itself is the upper bound of 10000 loop iterations. The code comment says that the intention is to "wait for any current AXI transfer to complete", so the author probably wanted to check the WAITING_FOR_OUTSTANDING_WRITES flag instead. Amend the function accordingly. * The CS register is only read at the beginning of the function. It needs to be read again after pausing the channel and before checking for outstanding writes, otherwise writes which were issued between the register read at the beginning of the function and pausing the channel may not be waited for. * The function seeks to abort the transfer by writing 0 to the NEXTCONBK register and setting the ABORT and ACTIVE flags. Thereby, the 0 in NEXTCONBK is sought to be loaded into the CONBLK_AD register. However experimentation has shown this approach to not work: The CONBLK_AD register remains the same as before and the CS register contains 0x00000030 (PAUSED | DREQ_STOPS_DMA). In other words, the control block is not aborted but merely paused and it will be resumed once the next DMA transaction is started. That is absolutely not the desired behavior. A simpler approach is to set the channel's RESET flag instead. This reliably zeroes the NEXTCONBK as well as the CS register. It requires less code and only a single MMIO write. This is also what popular user space DMA drivers do, e.g.: https://github.com/metachris/RPIO/blob/master/source/c_pwm/pwm.c Note that the spec is contradictory whether the NEXTCONBK register is writeable at all. On the one hand, page 41 claims: "The value loaded into the NEXTCONBK register can be overwritten so that the linked list of Control Block data structures can be dynamically altered. However it is only safe to do this when the DMA is paused." On the other hand, page 40 specifies: "Only three registers in each channel's register set are directly writeable (CS, CONBLK_AD and DEBUG). The other registers (TI, SOURCE_AD, DEST_AD, TXFR_LEN, STRIDE & NEXTCONBK), are automatically loaded from a Control Block data structure held in external memory." Fixes: 96286b576690 ("dmaengine: Add support for BCM2835") Signed-off-by: Lukas Wunner Cc: stable@vger.kernel.org # v3.14+ Cc: Frank Pavlic Cc: Martin Sperl Cc: Florian Meier Cc: Clive Messer Cc: Matthias Reichl Tested-by: Stefan Wahren Acked-by: Florian Kauer Signed-off-by: Vinod Koul --- drivers/dma/bcm2835-dma.c | 41 +++++++++-------------------------------- 1 file changed, 9 insertions(+), 32 deletions(-) diff --git a/drivers/dma/bcm2835-dma.c b/drivers/dma/bcm2835-dma.c index 0c3f5c71bb48..ae10f5614f95 100644 --- a/drivers/dma/bcm2835-dma.c +++ b/drivers/dma/bcm2835-dma.c @@ -406,13 +406,11 @@ static void bcm2835_dma_fill_cb_chain_with_sg( } } -static int bcm2835_dma_abort(void __iomem *chan_base) +static int bcm2835_dma_abort(struct bcm2835_chan *c) { - unsigned long cs; + void __iomem *chan_base = c->chan_base; long int timeout = 10000; - cs = readl(chan_base + BCM2835_DMA_CS); - /* * A zero control block address means the channel is idle. * (The ACTIVE flag in the CS register is not a reliable indicator.) @@ -424,25 +422,16 @@ static int bcm2835_dma_abort(void __iomem *chan_base) writel(0, chan_base + BCM2835_DMA_CS); /* Wait for any current AXI transfer to complete */ - while ((cs & BCM2835_DMA_ISPAUSED) && --timeout) { + while ((readl(chan_base + BCM2835_DMA_CS) & + BCM2835_DMA_WAITING_FOR_WRITES) && --timeout) cpu_relax(); - cs = readl(chan_base + BCM2835_DMA_CS); - } - /* We'll un-pause when we set of our next DMA */ + /* Peripheral might be stuck and fail to signal AXI write responses */ if (!timeout) - return -ETIMEDOUT; - - if (!(cs & BCM2835_DMA_ACTIVE)) - return 0; - - /* Terminate the control block chain */ - writel(0, chan_base + BCM2835_DMA_NEXTCB); - - /* Abort the whole DMA */ - writel(BCM2835_DMA_ABORT | BCM2835_DMA_ACTIVE, - chan_base + BCM2835_DMA_CS); + dev_err(c->vc.chan.device->dev, + "failed to complete outstanding writes\n"); + writel(BCM2835_DMA_RESET, chan_base + BCM2835_DMA_CS); return 0; } @@ -787,7 +776,6 @@ static int bcm2835_dma_terminate_all(struct dma_chan *chan) struct bcm2835_chan *c = to_bcm2835_dma_chan(chan); struct bcm2835_dmadev *d = to_bcm2835_dma_dev(c->vc.chan.device); unsigned long flags; - int timeout = 10000; LIST_HEAD(head); spin_lock_irqsave(&c->vc.lock, flags); @@ -801,18 +789,7 @@ static int bcm2835_dma_terminate_all(struct dma_chan *chan) if (c->desc) { vchan_terminate_vdesc(&c->desc->vd); c->desc = NULL; - bcm2835_dma_abort(c->chan_base); - - /* Wait for stopping */ - while (--timeout) { - if (!readl(c->chan_base + BCM2835_DMA_ADDR)) - break; - - cpu_relax(); - } - - if (!timeout) - dev_err(d->ddev.dev, "DMA transfer could not be terminated\n"); + bcm2835_dma_abort(c); } vchan_get_all_descriptors(&c->vc, &head); -- cgit From 6454368a804c4955ccd116236037536f81e5b1f1 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Wed, 30 Jan 2019 21:48:44 +0200 Subject: dmaengine: dmatest: Abort test in case of mapping error In case of mapping error the DMA addresses are invalid and continuing will screw system memory or potentially something else. [ 222.480310] dmatest: dma0chan7-copy0: summary 1 tests, 3 failures 6 iops 349 KB/s (0) ... [ 240.912725] check: Corrupted low memory at 00000000c7c75ac9 (2940 phys) = 5656000000000000 [ 240.921998] check: Corrupted low memory at 000000005715a1cd (2948 phys) = 279f2aca5595ab2b [ 240.931280] check: Corrupted low memory at 000000002f4024c0 (2950 phys) = 5e5624f349e793cf ... Abort any test if mapping failed. Fixes: 4076e755dbec ("dmatest: convert to dmaengine_unmap_data") Cc: Dan Williams Signed-off-by: Andy Shevchenko Signed-off-by: Vinod Koul --- drivers/dma/dmatest.c | 32 ++++++++++++++------------------ 1 file changed, 14 insertions(+), 18 deletions(-) diff --git a/drivers/dma/dmatest.c b/drivers/dma/dmatest.c index 2eea4ef72915..6511928b4cdf 100644 --- a/drivers/dma/dmatest.c +++ b/drivers/dma/dmatest.c @@ -711,11 +711,9 @@ static int dmatest_func(void *data) srcs[i] = um->addr[i] + src_off; ret = dma_mapping_error(dev->dev, um->addr[i]); if (ret) { - dmaengine_unmap_put(um); result("src mapping error", total_tests, src_off, dst_off, len, ret); - failed_tests++; - continue; + goto error_unmap_continue; } um->to_cnt++; } @@ -730,11 +728,9 @@ static int dmatest_func(void *data) DMA_BIDIRECTIONAL); ret = dma_mapping_error(dev->dev, dsts[i]); if (ret) { - dmaengine_unmap_put(um); result("dst mapping error", total_tests, src_off, dst_off, len, ret); - failed_tests++; - continue; + goto error_unmap_continue; } um->bidi_cnt++; } @@ -762,12 +758,10 @@ static int dmatest_func(void *data) } if (!tx) { - dmaengine_unmap_put(um); result("prep error", total_tests, src_off, dst_off, len, ret); msleep(100); - failed_tests++; - continue; + goto error_unmap_continue; } done->done = false; @@ -776,12 +770,10 @@ static int dmatest_func(void *data) cookie = tx->tx_submit(tx); if (dma_submit_error(cookie)) { - dmaengine_unmap_put(um); result("submit error", total_tests, src_off, dst_off, len, ret); msleep(100); - failed_tests++; - continue; + goto error_unmap_continue; } dma_async_issue_pending(chan); @@ -790,22 +782,20 @@ static int dmatest_func(void *data) status = dma_async_is_tx_complete(chan, cookie, NULL, NULL); - dmaengine_unmap_put(um); - if (!done->done) { result("test timed out", total_tests, src_off, dst_off, len, 0); - failed_tests++; - continue; + goto error_unmap_continue; } else if (status != DMA_COMPLETE) { result(status == DMA_ERROR ? "completion error status" : "completion busy status", total_tests, src_off, dst_off, len, ret); - failed_tests++; - continue; + goto error_unmap_continue; } + dmaengine_unmap_put(um); + if (params->noverify) { verbose_result("test passed", total_tests, src_off, dst_off, len, 0); @@ -846,6 +836,12 @@ static int dmatest_func(void *data) verbose_result("test passed", total_tests, src_off, dst_off, len, 0); } + + continue; + +error_unmap_continue: + dmaengine_unmap_put(um); + failed_tests++; } ktime = ktime_sub(ktime_get(), ktime); ktime = ktime_sub(ktime, comparetime); -- cgit