Linaro-mm-sig

linaro-mm-sig@lists.linaro.org

21 participants
3582 discussions

[PATCH V5] i2c: qcom-geni: Add dynamic transfer timeout based on transfer length and frequency

by Aniket Randive

The driver uses a static XFER_TIMEOUT of HZ (1 second) for all transfers regardless of message length or bus frequency, causing unnecessary delays on error paths. Compute the timeout dynamically from message length and bus frequency with a 10x safety margin over the theoretical wire time. Add a 300 ms floor to account for I2C clock stretching and other situations where a slave may keep SCL asserted for an extended period, including faulty devices holding the bus. This replaces the fixed 1-second timeout with a transfer-specific timeout while preserving sufficient margin for software overheads and bus-level delays. For GPI multi-descriptor transfers, use the maximum message length across all queued messages as the per-completion timeout. Signed-off-by: Aniket Randive <aniket.randive(a)oss.qualcomm.com> --- Changes in V5: - Updated the commit message as per the review comments. Changes in V4: - As per konrad suggestion used mult_frac() for bit_usec to avoid intermediate overflow on 32-bit targets. - Updated the commit message and added a driver comment explaining the rationale for the 0.3-second minimum timeout floor value. drivers/i2c/busses/i2c-qcom-geni.c | 47 +++++++++++++++++++++++------- 1 file changed, 37 insertions(+), 10 deletions(-) diff --git a/drivers/i2c/busses/i2c-qcom-geni.c b/drivers/i2c/busses/i2c-qcom-geni.c index 96dbf04138be..f011d2564cd2 100644 --- a/drivers/i2c/busses/i2c-qcom-geni.c +++ b/drivers/i2c/busses/i2c-qcom-geni.c @@ -74,9 +74,14 @@ enum geni_i2c_err_code { #define PACKING_BYTES_PW 4 #define ABORT_TIMEOUT HZ -#define XFER_TIMEOUT HZ #define RST_TIMEOUT HZ +/* 9 bits per byte (8 data + 1 ACK), 10x safety margin */ +#define I2C_TIMEOUT_SAFETY_COEFFICIENT 10 + +/* 300ms floor: budget for clock stretching; slave may hold SCL low indefinitely */ +#define I2C_TIMEOUT_MIN_USEC 300000 + struct geni_i2c_desc { bool no_dma_support; unsigned int tx_fifo_depth; @@ -204,6 +209,16 @@ static int geni_i2c_clk_map_idx(struct geni_i2c_dev *gi2c) return -EINVAL; } +static unsigned long geni_i2c_xfer_timeout(struct geni_i2c_dev *gi2c, size_t len) +{ + size_t bit_cnt = len * 9; + size_t bit_usec = mult_frac(bit_cnt, USEC_PER_SEC, gi2c->clk_freq_out); + size_t xfer_max_usec = (bit_usec * I2C_TIMEOUT_SAFETY_COEFFICIENT) + + I2C_TIMEOUT_MIN_USEC; + + return usecs_to_jiffies(xfer_max_usec); +} + static int qcom_geni_i2c_conf(struct geni_se *se, unsigned long freq) { struct geni_i2c_dev *gi2c = dev_get_drvdata(se->dev); @@ -445,7 +460,7 @@ static int geni_i2c_rx_one_msg(struct geni_i2c_dev *gi2c, struct i2c_msg *msg, u32 m_param) { dma_addr_t rx_dma = 0; - unsigned long time_left; + unsigned long time_left, timeout; void *dma_buf; struct geni_se *se = &gi2c->se; size_t len = msg->len; @@ -470,8 +485,9 @@ static int geni_i2c_rx_one_msg(struct geni_i2c_dev *gi2c, struct i2c_msg *msg, gi2c->dma_buf = dma_buf; } + timeout = geni_i2c_xfer_timeout(gi2c, len); cur = gi2c->cur; - time_left = wait_for_completion_timeout(&gi2c->done, XFER_TIMEOUT); + time_left = wait_for_completion_timeout(&gi2c->done, timeout); if (!time_left) geni_i2c_abort_xfer(gi2c); @@ -484,7 +500,7 @@ static int geni_i2c_tx_one_msg(struct geni_i2c_dev *gi2c, struct i2c_msg *msg, u32 m_param) { dma_addr_t tx_dma = 0; - unsigned long time_left; + unsigned long time_left, timeout; void *dma_buf; struct geni_se *se = &gi2c->se; size_t len = msg->len; @@ -512,8 +528,9 @@ static int geni_i2c_tx_one_msg(struct geni_i2c_dev *gi2c, struct i2c_msg *msg, if (!dma_buf) /* Get FIFO IRQ */ writel_relaxed(1, se->base + SE_GENI_TX_WATERMARK_REG); + timeout = geni_i2c_xfer_timeout(gi2c, len); cur = gi2c->cur; - time_left = wait_for_completion_timeout(&gi2c->done, XFER_TIMEOUT); + time_left = wait_for_completion_timeout(&gi2c->done, timeout); if (!time_left) geni_i2c_abort_xfer(gi2c); @@ -591,7 +608,7 @@ static void geni_i2c_gpi_multi_desc_unmap(struct geni_i2c_dev *gi2c, struct i2c_ * geni_i2c_gpi_multi_xfer_timeout_handler() - Handles multi message transfer timeout * @dev: Pointer to the corresponding dev node * @multi_xfer: Pointer to the geni_i2c_gpi_multi_desc_xfer - * @transfer_timeout_msecs: Timeout value in milliseconds + * @transfer_timeout_msecs: Per-message completion timeout in jiffies * @transfer_comp: Completion object of the transfer * * This function waits for the completion of each processed transfer messages @@ -601,7 +618,7 @@ static void geni_i2c_gpi_multi_desc_unmap(struct geni_i2c_dev *gi2c, struct i2c_ */ static int geni_i2c_gpi_multi_xfer_timeout_handler(struct device *dev, struct geni_i2c_gpi_multi_desc_xfer *multi_xfer, - u32 transfer_timeout_msecs, + unsigned long timeout_jiffies, struct completion *transfer_comp) { int i; @@ -612,7 +629,7 @@ static int geni_i2c_gpi_multi_xfer_timeout_handler(struct device *dev, if (multi_xfer->msg_idx_cnt != multi_xfer->irq_cnt) { time_left = wait_for_completion_timeout(transfer_comp, - transfer_timeout_msecs); + timeout_jiffies); if (!time_left) { dev_err(dev, "%s: Transfer timeout\n", __func__); return -ETIMEDOUT; @@ -736,8 +753,16 @@ static int geni_i2c_gpi(struct geni_i2c_dev *gi2c, struct i2c_msg msgs[], dma_async_issue_pending(gi2c->tx_c); if ((msg_idx == (gi2c->num_msgs - 1)) || flags & DMA_PREP_INTERRUPT) { + unsigned long timeout; + size_t max_len = 0; + int j; + + for (j = 0; j < gi2c->num_msgs; j++) + max_len = max_t(size_t, max_len, msgs[j].len); + + timeout = geni_i2c_xfer_timeout(gi2c, max_len); ret = geni_i2c_gpi_multi_xfer_timeout_handler(gi2c->se.dev, gi2c_gpi_xfer, - XFER_TIMEOUT, &gi2c->done); + timeout, &gi2c->done); if (ret) { dev_err(gi2c->se.dev, "I2C multi write msg transfer timeout: %d\n", @@ -851,8 +876,10 @@ static int geni_i2c_gpi_xfer(struct geni_i2c_dev *gi2c, struct i2c_msg msgs[], i } if (!gi2c->is_tx_multi_desc_xfer) { + unsigned long timeout = geni_i2c_xfer_timeout(gi2c, msgs[i].len); + dma_async_issue_pending(gi2c->tx_c); - time_left = wait_for_completion_timeout(&gi2c->done, XFER_TIMEOUT); + time_left = wait_for_completion_timeout(&gi2c->done, timeout); if (!time_left) { dev_err(gi2c->se.dev, "%s:I2C timeout\n", __func__); gi2c->err = -ETIMEDOUT; -- 2.34.1

1 month, 2 weeks

Re: [PATCH net-next v6 3/3] selftests/net: devmem.py: add check_rx_large_niov

by Jakub Kicinski

On Fri, 31 Jul 2026 15:01:01 -0700 Bobby Eshleman wrote: > Meanwhile, do we want drivers/net/hw/config to workaround by carrying > something like SYNC_FILE or DMABUF_HEAPS, or wait and see about the > udmabuf kconfig change? Let's enable SYNC_FILE for now and pursue the UDMABUF change in parallel. It will land in another tree if at all, so we'll have to wait a while before it propagates to us.

1 month, 3 weeks

Re: [PATCH v5 3/4] drm/prime: use dma_buf_fd_install() to preserve export tracing

by T.J. Mercier

On Wed, Jul 29, 2026 at 11:27 PM Baineng Shou <shoubaineng(a)gmail.com> wrote: > > drm_gem_prime_handle_to_fd() open-codes fd reservation and install > using get_unused_fd_flags() + fd_install() directly. This bypasses > the DMA_BUF_TRACE() call that dma_buf_fd() emits, so observability > tools relying on the trace_dma_buf_fd tracepoint silently miss all > DRM PRIME exports. > > Replace the bare fd_install() with dma_buf_fd_install(), which wraps > fd_install() together with DMA_BUF_TRACE(), restoring full tracepoint > coverage. No functional change; the fd lifecycle (get_unused_fd_flags > → work → install) is already correct. > > Note: this patch depends on dma_buf_fd_install() introduced in > "dma-buf: dma-heap: don't publish fd before copy_to_user() succeeds" > [1]. > > [1] https://lore.kernel.org/dri-devel/20260714114654.3885457-2-shoubaineng@gmai… > > Suggested-by: Christian König <christian.koenig(a)amd.com> > Signed-off-by: Baineng Shou <shoubaineng(a)gmail.com> Reviewed-by: T.J. Mercier <tjmercier(a)google.com> > --- > drivers/gpu/drm/drm_prime.c | 2 +- > 1 file changed, 1 insertion(+), 1 deletion(-) > > diff --git a/drivers/gpu/drm/drm_prime.c b/drivers/gpu/drm/drm_prime.c > index 9b44c78cd77f..fe3436d1235d 100644 > --- a/drivers/gpu/drm/drm_prime.c > +++ b/drivers/gpu/drm/drm_prime.c > @@ -524,7 +524,7 @@ int drm_gem_prime_handle_to_fd(struct drm_device *dev, > return PTR_ERR(dmabuf); > } > > - fd_install(fd, dmabuf->file); > + dma_buf_fd_install(dmabuf, fd); > *prime_fd = fd; > return 0; > } > -- > 2.34.1 >

1 month, 3 weeks

Re: [PATCH v5 4/4] selftests: dmabuf-heaps: add fd-leak-on-EFAULT regression test

by T.J. Mercier

On Wed, Jul 29, 2026 at 11:27 PM Baineng Shou <shoubaineng(a)gmail.com> wrote: > > Add a test case that verifies no file descriptor is leaked when > DMA_HEAP_IOCTL_ALLOC succeeds internally but copy_to_user() fails > to deliver the fd number back to userspace. > > The failure is triggered by placing the ioctl argument in a private > anonymous page and flipping it to PROT_READ (via mprotect) between > the kernel's copy_from_user() and copy_to_user() calls. With the > buggy kernel the ioctl returns -EFAULT but leaves an extra open fd > in the process's fd table; with the fixed kernel the fd count is > unchanged. > > This serves as a regression test for: > "dma-buf: dma-heap: don't publish fd before copy_to_user() succeeds" > > Suggested-by: Sumit Semwal <sumit.semwal(a)linaro.org> > Signed-off-by: Baineng Shou <shoubaineng(a)gmail.com> > --- > .../selftests/dmabuf-heaps/dmabuf-heap.c | 115 +++++++++++++++++- > 1 file changed, 114 insertions(+), 1 deletion(-) > > diff --git a/tools/testing/selftests/dmabuf-heaps/dmabuf-heap.c b/tools/testing/selftests/dmabuf-heaps/dmabuf-heap.c > index fc9694fc4e89..bd58e5b06c8b 100644 > --- a/tools/testing/selftests/dmabuf-heaps/dmabuf-heap.c > +++ b/tools/testing/selftests/dmabuf-heaps/dmabuf-heap.c > @@ -390,6 +390,118 @@ static void test_alloc_errors(char *heap_name) > close(heap_fd); > } > > +/* > + * test_alloc_no_fd_leak_on_efault - verify no fd is leaked when > + * copy_to_user() fails during DMA_HEAP_IOCTL_ALLOC. > + * > + * The bug: dma_buf_fd() called fd_install() before copy_to_user(). > + * If copy_to_user() then failed (e.g. via mprotect), the fd was > + * silently installed in the fd table but never returned to userspace. > + * > + * The fix: reserve the fd with get_unused_fd_flags() first, attempt > + * copy_to_user(), and only call fd_install() on success. > + * > + * We trigger the failure by placing the ioctl argument in a page, > + * flipping it to PROT_READ between copy_from_user and copy_to_user, > + * and counting open file descriptors before and after. > + */ > +static void test_alloc_no_fd_leak_on_efault(char *heap_name) > +{ > + int heap_fd = -1; > + int fd_before, fd_after; > + int ret; > + long page_size; > + struct dma_heap_allocation_data *req; > + > + ksft_print_msg("Testing no fd leak when copy_to_user() fails:\n"); > + > + heap_fd = dmabuf_heap_open(heap_name); > + > + page_size = sysconf(_SC_PAGESIZE); > + > + /* > + * Place the ioctl argument in its own private anonymous page so > + * we can flip its protection independently. > + */ > + req = mmap(NULL, page_size, PROT_READ | PROT_WRITE, > + MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); > + if (req == MAP_FAILED) { > + ksft_test_result_fail("mmap failed: %s\n", strerror(errno)); > + goto out; > + } > + > + memset(req, 0, sizeof(*req)); > + req->len = page_size; > + req->fd_flags = O_RDWR | O_CLOEXEC; > + > + /* Count open fds before the ioctl */ > + fd_before = 0; > + { > + DIR *d = opendir("/proc/self/fd"); > + struct dirent *de; > + > + if (!d) { > + ksft_test_result_fail("opendir /proc/self/fd: %s\n", > + strerror(errno)); > + munmap(req, page_size); > + goto out; > + } > + while ((de = readdir(d))) > + if (de->d_name[0] != '.') > + fd_before++; > + closedir(d); > + /* subtract the fd opened by opendir itself */ But no actual subtraction? > + } > + > + /* > + * Make the page read-only: copy_from_user() in the kernel will > + * still succeed (it already ran), Huh? copy_from_user hasn't run yet. That happens inside the ioctl(). > but copy_to_user() that writes > + * the fd number back will fault. > + */ > + mprotect(req, page_size, PROT_READ); > + > + ret = ioctl(heap_fd, DMA_HEAP_IOCTL_ALLOC, req); > + > + /* Re-allow writes so munmap can clean up */ > + mprotect(req, page_size, PROT_READ | PROT_WRITE); > + munmap(req, page_size); > + > + if (ret != -1 || errno != EFAULT) { This looks like you meant &&, but I think we should just fail if ret != -1. Either the mprotect is broken, or dma-heap didn't actually try to copy_to_user. > + /* > + * If the ioctl didn't fail with EFAULT, either the kernel > + * handled it differently or mprotect raced. mprotect is synchronous, how could it race with anything here? > Skip rather > + * than giving a false pass/fail. > + */ > + ksft_test_result_skip( > + "ioctl did not return EFAULT (ret=%d errno=%d), skipping\n", > + ret, errno); > + goto out; > + } > + > + /* Count open fds after the failed ioctl */ > + fd_after = 0; > + { > + DIR *d = opendir("/proc/self/fd"); > + struct dirent *de; > + > + if (!d) { > + ksft_test_result_fail("opendir /proc/self/fd: %s\n", > + strerror(errno)); > + goto out; > + } > + while ((de = readdir(d))) > + if (de->d_name[0] != '.') > + fd_after++; > + closedir(d); > + } > + > + ksft_test_result(fd_before == fd_after, > + "no fd leak on EFAULT: before=%d after=%d\n", This is for the failure case, so I don't think the "no" should be in the string. > + fd_before, fd_after); > +out: > + close(heap_fd); > +} > + > static int numer_of_heaps(void) > { > DIR *d = opendir(DEVPATH); > @@ -420,7 +532,7 @@ int main(void) > return KSFT_SKIP; > } > > - ksft_set_plan(11 * numer_of_heaps()); > + ksft_set_plan(12 * numer_of_heaps()); > > while ((dir = readdir(d))) { > if (!strncmp(dir->d_name, ".", 2)) > @@ -435,6 +547,7 @@ int main(void) > test_alloc_zeroed(dir->d_name, ONE_MEG); > test_alloc_compat(dir->d_name); > test_alloc_errors(dir->d_name); > + test_alloc_no_fd_leak_on_efault(dir->d_name); > } > closedir(d); > > -- > 2.34.1 >

1 month, 3 weeks

Re: [PATCH net-next v6 3/3] selftests/net: devmem.py: add check_rx_large_niov

by Jakub Kicinski

On Thu, 30 Jul 2026 14:39:37 -0700 Bobby Eshleman wrote: > Poking around, it looks like 231.1.167.0 and above should support > everything, so fw should be okay AFAICT. > > Looks like the config is missing CONFIG_NET_DEVMEM and CONFIG_UDMABUF? Ah, damn, you're right. I grepped for DEVMEM and didn't look closely on a hit. Turns out there's a non-NET DEVMEM, too. Could you send a patch to add the missing config options to tools/testing/selftests/drivers/net/hw/config ? Can be separate or part of this series, doesn't matter. > Sorry, took me a while... was certain it was a bug in my code. > > Not the failure here, but wondering if this was on ARM led to seeing > that 16K hardcoded rx_page_size in run_rx_large_niov() may fail on ARM > with 64K pages because it will fail the IS_ALIGN(16K, 64K) check... Ah, good thought. We've been meaning to get an ARM64 server for NIPA (our current server supplier is out). If it's not too hard could be nice to guard against that. But also not a huge deal for HW tests if they fail instead of skipping.

1 month, 3 weeks

Re: [PATCH net-next v6 3/3] selftests/net: devmem.py: add check_rx_large_niov

by Jakub Kicinski

On Fri, 24 Jul 2026 14:21:17 -0700 Bobby Eshleman wrote: > From: Bobby Eshleman <bobbyeshleman(a)meta.com> > > Add a new devmem test case for binding the dmabuf with rx-page-size=16K. > The test sweeps RX payload sizes straddling the niov boundary to cover > the sub-niov, exact-niov, and multi-niov RX paths. > > Silence pylint invalid-name (`with open() as f`) and too-many-arguments > (ncdevmem_rx grew to 6 args) at file scope. > > Signed-off-by: Bobby Eshleman <bobbyeshleman(a)meta.com> > Acked-by: Stanislav Fomichev <sdf(a)fomichev.me> Hm, odd. In NIPA we're getting: TAP version 13 1..1 # timeout set to 0 # selftests: drivers/net/hw: devmem.py # TAP version 13 # 1..5 # ok 1 devmem.check_rx # SKIP marked as disruptive # ok 2 devmem.check_tx # SKIP marked as disruptive # ok 3 devmem.check_tx_chunks # SKIP marked as disruptive # ok 4 devmem.check_rx_hds # SKIP Test requires devmem support # ok 5 devmem.check_rx_large_niov # SKIP Test requires devmem support # # Totals: pass:0 fail:0 xfail:0 xpass:0 skip:5 error:0 ok 1 selftests: drivers/net/hw: devmem.py # Totals: pass:1 fail:0 xfail:0 xpass:0 skip:0 error:0 https://netdev.bots.linux.dev/logs/hwksft/BCM57508/results/755681/config driver: bnxt fw: 237.1.148.0 Any idea?

1 month, 3 weeks

Re: [PATCH net-next v6 1/3] net: devmem: allow rx-page-size > PAGE_SIZE per dmabuf binding

by Jakub Kicinski

On Fri, 24 Jul 2026 14:21:15 -0700 Bobby Eshleman wrote: > + value: 0 # dummy: codegen needs a number, real value is the PAGE_SIZE macro (header) yamllint says: 12:81 error line too long (89 > 80 characters) (line-length)

1 month, 3 weeks

Re: [PATCH v7 3/5] rust: sync: Add abstraction for rcu_barrier()

by Gary Guo

On Wed Jul 29, 2026 at 6:18 PM BST, Paul E. McKenney wrote: > On Wed, Jul 29, 2026 at 11:45:40AM +0200, Philipp Stanner wrote: >> rcu_barrier() is a frequently used C function which is always safe to be >> called. > > Just checking... Here "always safe" means only from task level, with BH, > preemption, and interrupts all enabled, correct? > > In contrast, if you do this: > > preempt_disable(); > rcu_barrier(); > preempt_enable(); > > the results won't be safe. This is same for all sleepable functions. In order to avoid having to mark all sleeping function unsafe, we've decided that sleeping from non-preemptable context is "safe", but is a bug regardless. Best, Gary

1 month, 3 weeks

Re: [PATCH v4 09/14] nvme-pci: add SGL support for the dmabuf path

by Christoph Hellwig

On Wed, Jul 29, 2026 at 12:45:47PM +0100, Pavel Begunkov wrote: > It was exposed in early version as I was passing a [{dma,len}, ...] > array, but we moved from that. Maybe I should put the minimum > segment size in the map structure, and (possibly over) split using > that for now? Keith had this chunk in his patches: > > + int offset = offset_in_page(bio->bi_iter.bi_bvec_done); > + > + nsegs = ALIGN(bio->bi_iter.bi_size + offset, PAGE_SIZE) >> > + PAGE_SHIFT; > + if (bio->bi_iter.bi_size > max_bytes) { > + bytes = max_bytes; > + nsegs = (bytes + offset) >> PAGE_SHIFT; > + } else if (nsegs > lim->max_segments) { > + nsegs = lim->max_segments; > + bytes = PAGE_SIZE * nsegs - offset; > + } else { > + *segs = nsegs; > + return NULL; > + } This seems very pessimistic, especially for the case of the registration only having a single segment, which I'd expect to be fairly common due to P2P bar mappings, huge pages or IOMMU coalescing. So at very least we'd want to special case that, but in an idea world the caller would be required to provide a useful nr_segments for the I/O.

1 month, 3 weeks

Re: [PATCH v4 09/14] nvme-pci: add SGL support for the dmabuf path

by Christoph Hellwig

On Wed, Jul 29, 2026 at 03:47:23PM +0530, Anuj Gupta/Anuj Gupta wrote: > > But I also don't understand what the use case for this function > > is to start with. struct sg_table tells us how many segments > > exist on the DMA side in the nents member, which should be just > > fine for the SGL threshold calculation. > > sg_table->nents covers the entire exported buffer (<=1GiB), while a > request only covers a subrange[bi_offset, bi_offset+payload). Using > nents would overcount the request's segments. Urgg, yes. > >> + if (!entries) > >> + return BLK_STS_IOERR; > >> + if (entries > NVME_MAX_SEGS) > >> + return BLK_STS_AGAIN; > > > > Given that the block layer enforced data in rw/command and the > > max_segments limit, why do we need the extra check here? > > A dmabuf bio reports nsegs=1 (bio_split_io_at) to the block layer, so > max_segments isn't enforced against the SG entries actually spanned by > the request. Hence the explicit check. We'll need to expose the actual nsegs to the block layer and split based on that. Otherwise I/O might work or fail based on the device capabilities.

1 month, 3 weeks

Jump to page:

2026

2025

2024

2023

2022

2021

2020

2019

2018

2017

2016

2015

2014

2013

2012

2011

Linaro-mm-sig