Linaro-mm-sig

linaro-mm-sig@lists.linaro.org

6 participants
7434 discussions

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

3 days, 11 hours

PO-INV Document

by Sales Team – Pipex Inc

3 days, 15 hours

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.

3 days, 18 hours

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.

3 days, 18 hours

Re: [PATCH v4 01/14] dma-buf: introduce initial file I/O infrastructure

by Christoph Hellwig

On Wed, Jul 29, 2026 at 11:37:19AM +0100, Pavel Begunkov wrote: > On 7/29/26 07:59, Christoph Hellwig wrote: >> The method name feels a bit convoluted, but given all the >> previous discussions I don't care too strongly. I'll leave >> the dma-buf side review to those who understand it. > > I assume you mean this: Yes. > > + int (*init_dma_buf_io_ctx)(struct file *, struct dma_buf_io_ctx *); > > I agree, and all dma_buf_io_[ctx,map] look clunky, but I don't > see what I can drop out of the name. Suggestions? Maybe I at least > should make the fs op sth like "register_dma_buf". I just remember scares from the last discussion :) register_dma_buf sounds fine to be, but unless I misremember there were objections to that before. > > -- > Pavel Begunkov ---end quoted text---

3 days, 18 hours

A Handy Collection of Browser Games for Quick Breaks

by tinoukomori-8558＠yopmail.com

Hello everyone, I wanted to share a website that I've been using recently whenever I have a few minutes to spare: Free Top Games. Web site: https://freetopgames.io/ What I like most is that everything runs directly in the browser, so there's nothing to install or update. The site includes a good mix of game genres such as puzzle, racing, shooting, sports, adventure, and casual games, making it easy to find something that fits your mood. A few things I appreciate: Fast loading games with no downloads required. Works on desktop, tablet, and mobile browsers. A wide variety of free titles that are updated regularly. Great for short gaming sessions during breaks. I'm always interested in discovering browser-based gaming sites with clean interfaces and interesting game collections. If anyone here has other recommendations for free web game platforms, I'd love to hear them. Thanks for reading!

3 days, 21 hours

How to Play and Enjoy Level Devil

by relative.rooster.miqd＠hidingmail.com

Some games are enjoyable because they are relaxing, while others are memorable because they constantly surprise you. Level Devil belongs to the second category. It is a compact platform game built around traps, unexpected changes, and trial-and-error learning. Each stage may look simple at first, but the level itself can shift in ways that challenge your expectations. The fun comes from discovering what each room is hiding and gradually improving through observation and practice. https://leveldevilfull.com Gameplay The main goal is straightforward: guide your character through the stage and reach the exit. You usually move left and right, jump over obstacles, and avoid hazards such as spikes, pits, or moving platforms. However, the game’s real challenge is that familiar rules may suddenly change. A platform might disappear, the screen could shift, or an apparently safe path may reveal a trap. These surprises are designed to make players react quickly, but rushing often leads to mistakes. Instead, each failed attempt provides useful information about the level. The controls are generally easy to understand, which makes the game accessible to beginners. The difficulty comes from timing, patience, and learning how the stage behaves. This makes every successful jump feel satisfying, especially after several attempts. Tips for Playing First, take your time when entering a new area. Look for unusual gaps, suspicious platforms, and objects that seem deliberately placed. The level may be testing whether you notice a visual clue. Second, treat failure as part of the experience. Losing does not necessarily mean you played badly; it often reveals something important about the stage. Remember what happened and adjust your next attempt. It also helps to use short, controlled movements. Holding a direction for too long can send your character into a hazard, while careful taps give you more control. When jumping, focus on both the takeoff and the landing. Some platforms require you to prepare for the next move immediately. Finally, avoid becoming frustrated. Take a short break if a section feels repetitive, then return with a fresh mind. Many difficult moments become easier once you stop trying to force them. Conclusion Level Devil is a good example of how simple controls can support creative and challenging gameplay. Its surprises, quick restarts, and unusual level design make it enjoyable for players who like experimentation. Whether you play for a few minutes or try to complete every stage, the best approach is to stay curious, observe carefully, and learn from each attempt.

3 days, 22 hours

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

by Christoph Hellwig

On Tue, Jul 28, 2026 at 10:29:21PM +0100, Pavel Begunkov wrote: > From: Anuj Gupta <anuj20.g(a)samsung.com> > > Add SGL support in addition to PRP for dmabuf-backed requests, > coalescing the mapping's sg_table into NVMe SGL data descriptors. > > Signed-off-by: Anuj Gupta <anuj20.g(a)samsung.com> > [pavel: rebased] > Signed-off-by: Pavel Begunkov <asml.silence(a)gmail.com> > --- > drivers/nvme/host/pci.c | 191 +++++++++++++++++++++++++++++++++++++++- > 1 file changed, 187 insertions(+), 4 deletions(-) > > diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c > index f1b67c191892..cbb321fb7c50 100644 > --- a/drivers/nvme/host/pci.c > +++ b/drivers/nvme/host/pci.c > @@ -1287,12 +1287,18 @@ static blk_status_t nvme_pci_setup_data_prp(struct request *req, > return BLK_STS_IOERR; > } > > +static void nvme_pci_sgl_set_data_addr(struct nvme_sgl_desc *sge, > + dma_addr_t addr, u32 len) > +{ > + sge->addr = cpu_to_le64(addr); > + sge->length = cpu_to_le32(len); > + sge->type = NVME_SGL_FMT_DATA_DESC << 4; > +} > + > static void nvme_pci_sgl_set_data(struct nvme_sgl_desc *sge, > struct blk_dma_iter *iter) > { > - sge->addr = cpu_to_le64(iter->addr); > - sge->length = cpu_to_le32(iter->len); > - sge->type = NVME_SGL_FMT_DATA_DESC << 4; > + nvme_pci_sgl_set_data_addr(sge, iter->addr, iter->len); > } The naming is a bit confusing (and me passing the iter to nvme_pci_sgl_set_data is probably at faul for that). So maybe spin out a prep patch to rename the old nvme_pci_sgl_set_data to nvme_pci_dma_iter_set_sgl or so, and then add the new one as nvme_pci_sgl_set_data (as before the dma_iter conversion). > > +static unsigned int nvme_pci_dmabuf_sgl_nents(struct request *req, > + dma_addr_t *first_dma, > + u32 *first_len) This is a really good example why the aligning to the opening braces produces totally unreadble code.. 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. > +{ > + struct nvme_iod *iod = blk_mq_rq_to_pdu(req); > + struct bio *bio = req->bio; > + struct nvme_dmabuf_map *map = to_nvme_dmabuf_map(bio->bi_dmabuf_map); > + size_t length = blk_rq_payload_bytes(req); > + struct nvme_sgl_desc *sg_list = NULL; > + dma_addr_t sgl_dma = 0, last_end = 0; > + unsigned int mapped = 0; > + unsigned long tmp; > + struct scatterlist *sg; > + size_t offset, remaining; > + bool have = false; > + > + 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? > + continue; > + } > + > + addr += offset; > + sg_len -= offset; > + offset = 0; > + > + while (sg_len && remaining) { These can't be false on the first iteration, so maybe turn this into a do {} while loop? > + u32 chunk = min_t(size_t, remaining, sg_len); > + > + if (have && last_end == addr) { > + u32 old = le32_to_cpu(sg_list[mapped - 1].length); > + > + sg_list[mapped - 1].length = cpu_to_le32(old + chunk); Overly long line. > + } else { > + if (WARN_ON_ONCE(mapped == entries)) > + goto err_free; > + nvme_pci_sgl_set_data_addr(&sg_list[mapped++], > + addr, chunk); > + } Why do we need this merging? dma_map_sg should have already done any interesting merging, or am I missing something? > + if (use_sgl != SGL_UNSUPPORTED) { > + dma_addr_t first_dma; > + u32 first_len; > + unsigned int entries; > + > + entries = nvme_pci_dmabuf_sgl_nents(req, &first_dma, > + &first_len); > + > + if (use_sgl == SGL_FORCED) { > + ret = nvme_rq_setup_dmabuf_sgl(req, nvmeq, > + entries, first_dma, first_len); > + return ret == BLK_STS_AGAIN ? BLK_STS_IOERR : ret; > + } > + > + if (sgl_threshold && entries && > + DIV_ROUND_UP(blk_rq_payload_bytes(req), entries) >= > + sgl_threshold) { > + ret = nvme_rq_setup_dmabuf_sgl(req, nvmeq, > + entries, first_dma, first_len); > + if (ret != BLK_STS_AGAIN) > + return ret; > + } > + } Various overly long lines. Please factor out a helper for the decisions to use sgl vs not instead of open coding it here.

3 days, 22 hours

Basketball Stars: Rule the Court and Become the MVP

by joeytribuani0＠gmail.com

Basketball Stars is the perfect game for anyone who loves fast-paced street basketball action! From smooth dribble moves and ankle-breaking crossovers to clutch shots and powerful dunks, every match feels intense and competitive. The game’s easy controls make it simple to start playing, but mastering the timing, defense, and shooting mechanics takes real skill. Whether you’re playing quick one-on-one matches or climbing the ranked leaderboard, Basketball Stars keeps every game exciting. One of the best parts is the character customization. You can unlock new outfits, courts, basketballs, and upgrades to create your own unique style on the court. Playing against real opponents online also adds a fun challenge because every player has a different strategy. If you enjoy basketball games with arcade-style gameplay and nonstop action, Basketball Stars is definitely worth checking out. Step onto the court and show everyone who the real MVP is! WEB: https://basketballstars2026.io

3 days, 22 hours

Re: [PATCH v4 08/14] nvme-pci: implement dma_token backed requests

by Christoph Hellwig

> +static int nvme_init_dma_buf_io_ctx(struct block_device *bdev, > + struct dma_buf_io_ctx *ctx) Please stick to two-tab indents for function declaration continuation for the nvme code to keep the code easy to maintain. > +#if defined(CONFIG_DMA_SHARED_BUFFER) This should be good old #ifdef. Same in a few other places over the series. Modulo these minor nits the patch looks good.

3 days, 22 hours

Jump to page:

2026

2025

2024

2023

2022

2021

2020

2019

2018

2017

2016

2015

2014

2013

2012

2011

Linaro-mm-sig