Linaro-mm-sig

linaro-mm-sig@lists.linaro.org

104 participants
7059 discussions

HIRE A LEGIT CRYPT0 REC0VERY EXPERT-T0 RECLIAM ST0LEN CRYPT0: HIRE RAPID DIGITAL REC0VERY

by realross038＠gmail.com

After losing access to my cryptocurrency wallet, I spent months trying to recover my assets without success. I then contacted RAPID DIGITAL RECOVERY for guidance. Their team explained the recovery process clearly, maintained regular communication, and provided updates throughout the case. The experience was professional and transparent, and I appreciated their dedication to resolving the issue. Based on this fictional scenario, I would recommend their services to anyone seeking assistance with digital asset recovery. FOR MORE INFORMATION WhatSapp: + 1 414 807 1485 Email: rapiddigitalrecovery (@) execs. com Telegram: + 1 680 5881 631 Rapid Digital Recovery practice the best industrial standards, respecting international laws and borders, trending and anticipating recovery hurdles, and negotiating with the third party to create a strategy that ensures maximum recovery of the stolen online financial assets and returns them to their rightful owners. Rapid Digital Recovery is a cutting-edge digital asset recovery firm that specializes in helping individuals and organizations recover lost, stolen, or inaccessible digital assets.

2 hours, 3 minutes

Re: [PATCH v2] dma-buf: Split sgl into page-aligned 2G chunks

by Pranjal Shrivastava

On Tue, Jun 23, 2026 at 09:44:46AM +0100, David Laight wrote: Hi David, > On Tue, 23 Jun 2026 01:54:59 +0000 > David Hu <xuehaohu(a)google.com> wrote: > > > Currently, `fill_sg_entry()` splits the scatterlist using `UINT_MAX`. > > This creates a non-page-aligned DMA length (`0xFFFFFFFF`) for the > > first entry, resulting in non-page-aligned DMA addresses for all > > subsequent entries. > > There is a separate issue of whether this code is even needed at all. > Where can transfers over 2G (never mind 4G) actually come from. > > The read, write and similar system calls limit transfers to INT_MAX > (even on 64bit) and a lot of driver code will need fixing it longer > lengths are allowed though. > io_uring better enforce the same limits. > So the transfers can come directly from userspace. > > Not only that but you also need a single physically contiguous buffer. > Good luck allocating that! > > Now maybe there are some peer-to-peer places where the large buffer > is device memory, but they will be unusual and probably need > special treatment anyway. > I agree that traditional VFS read/write face the MAX_RW_COUNT limit (~2GB), and io_uring has its limits, but I'm a little confused by the push to enforce these limits here in the SGL code? File I/O seems to be only one side of the picture. In my view, this fix is necessary and certainly has a use-case: For example, the RDMA subsystem has the capability to import dmabufs [1], which gives rise to use cases for dmabuf beyond standard file ops (via VFS/io_uring). In these scenarios, GPU HBM can be exported as dmabufs. With recent GPUs, HBM capacity can be in the order of hundreds of GBs [2]. RDMA can employ infrastructure like the vfio-dmabuf-exporter [3] or similar dmabuf exporters to frequently move huge blocks of data via P2PDMA. If we restrict incoming dmabuf transfers to fit within VFS-centric limits (2GB), we impose unnecessary overhead on the RDMA stack, forcing it to manage a significantly higher number of memory registrations. By cleanly splitting these massive contiguous device buffers into page-aligned SGL entries, we directly improve the efficiency of P2P transfers and memory registration. Since this change doesn't seem to have a negative impact on standard file I/O or break existing VFS constraints, I'm curious why we shouldn't support splitting these >4GB P2P transfers? Am I missing something? Thanks, Praan [1] https://elixir.bootlin.com/linux/v7.1.1/source/drivers/infiniband/core/umem… [2] https://nvdam.widen.net/s/fdvdqvfvj2/hopper-h200-nvl-product-brief (Table 2-2) [3] https://elixir.bootlin.com/linux/v7.1.1/source/drivers/vfio/pci/vfio_pci_dm…

6 hours, 54 minutes

Re: [PATCH v3 1/9] PCI/P2PDMA: Add CONFIG_PCI_P2PDMA_CORE

by Robin Murphy

On 12/06/2026 3:31 pm, Matt Evans wrote: > Hi Kevin, Pranjal, (+Robin, hi!) Oh hey there! :) > On 12/06/2026 04:39, Tian, Kevin wrote: >>> From: Pranjal Shrivastava <praan(a)google.com> >>> Sent: Friday, June 12, 2026 2:38 AM >>> >>> On Wed, Jun 10, 2026 at 04:43:15PM +0100, Matt Evans wrote: >>>> --- a/drivers/pci/Kconfig >>>> +++ b/drivers/pci/Kconfig >>>> @@ -206,11 +206,7 @@ config PCIE_TPH >>>> config PCI_P2PDMA >>>> bool "PCI peer-to-peer transfer support" >>>> depends on ZONE_DEVICE >>>> - # >>>> - # The need for the scatterlist DMA bus address flag means PCI >>> P2PDMA >>>> - # requires 64bit >>>> - # >>>> - depends on 64BIT >>>> + select PCI_P2PDMA_CORE >>>> select GENERIC_ALLOCATOR >>>> select NEED_SG_DMA_FLAGS >>>> help >>> >>> Nit: Did we drop depends on 64BIT intentionally here? I guess the full >>> PCI_P2PDMA stack still selects NEED_SG_DMA_FLAGS? IIRC, >>> NEED_SG_DMA_FLAGS doesn't select 64BIT? >> >> seems that comment is stale. According to the commit msg: >> >> " it would make vfio-pci only available if CONFIG_ZONE_DEVICE is >> present (e.g. 64-bit systems), " >> >> so it sounds a redundant dependency hence is removed. > > This was intentional. In practice there is still a dependency on 64BIT > for PCI_P2PDMA, but it is because of ZONE_DEVICE (and mem hotplug). The > key need is PCI_P2PDMA_CORE is available on !64BIT for VFIO, but I > didn't see a requirement from PCI_P2PDMA itself (as opposed to its > dependencies). If I've missed one, I can put it back... > > But NEED_SG_DMA_FLAGS doesn't smell quite right; I see from comments in > > af2880ec44021 ("scatterlist: add dedicated config for DMA flags") > > that it assumes 64BIT, but it seems to be missing a "depends on 64BIT". > > Robin -- should that depend on 64BIT? Indeed, looking at the history it seems like that was overlooked, but it worked out at the time since the only selector of NEED_SG_DMA_FLAGS was PCI_P2PDMA as you say. If we're now generalising then moving the explicit 64BIT dependency to NEED_SG_DMA_FLAGS itself sounds like the right thing to do. Cheers, Robin.

10 hours, 2 minutes

[PATCH] dma-buf/dma-fence: Set better string for dma_fence_driver_name()

by Philipp Stanner

dma_fence_driver_name() reports that a driver whose fence is already signaled is a "detached-driver". This is incorrect, the driver might still be loaded and running. Rename that string to something more descriptive. Signed-off-by: Philipp Stanner <phasta(a)kernel.org> --- Just compile-tested. --- drivers/dma-buf/dma-fence.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/dma-buf/dma-fence.c b/drivers/dma-buf/dma-fence.c index c7ea1e75d38a..9c3dfa7b0066 100644 --- a/drivers/dma-buf/dma-fence.c +++ b/drivers/dma-buf/dma-fence.c @@ -1173,7 +1173,7 @@ const char __rcu *dma_fence_driver_name(struct dma_fence *fence) if (!dma_fence_test_signaled_flag(fence)) return (const char __rcu *)ops->get_driver_name(fence); else - return (const char __rcu *)"detached-driver"; + return (const char __rcu *)"driver-whose-fence-is-signaled"; } EXPORT_SYMBOL(dma_fence_driver_name); -- 2.54.0

14 hours, 15 minutes

Re: [PATCH v3 6/9] vfio/pci: Clean up BAR zap and revocation

by Pranjal Shrivastava

On Thu, Jun 18, 2026 at 05:06:27PM +0100, Matt Evans wrote: > Hi Praan, > > On 12/06/2026 20:39, Pranjal Shrivastava wrote: > >> [...] > >> diff --git a/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c b/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c > >> index 86362ec424a5..51990f6d66d5 100644 > >> --- a/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c > >> +++ b/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c > >> @@ -1692,6 +1692,14 @@ static int hisi_acc_vfio_pci_probe(struct pci_dev *pdev, const struct pci_device > >> if (ret) > >> goto out_put_vdev; > >> > >> + /* > >> + * hisi_acc_vfio_pci_mmap() calls down to > >> + * vfio_pci_core_mmap(), so BAR mappings are still > >> + * DMABUF-backed. They don't require a zap on revoke, so opt > >> + * out: > >> + */ > >> + hisi_acc_vdev->core_device.zap_bars_on_revoke = false; > >> + > > > > This seems to be happening after we vfio_pci_core_register_device, which > > could be slightly problematic if another device in the same group races > > to trigger a hot reset before we can set this to false. Could we > > initialize this flag before registration instead? > > Remember it is a safe default, so in the event of a driver not managing > to opt-out before it's required then all that happens is a redundant > unmap_mapping_range(). The default-safe was a nice suggestion from Alex > on v2. > Ack. I see. That makes sense. Thanks, Praan

15 hours, 11 minutes

Re: [PATCH v3 6/9] vfio/pci: Clean up BAR zap and revocation

by Jason Gunthorpe

On Thu, Jun 18, 2026 at 05:02:58PM +0100, Matt Evans wrote: > My understanding is that the sequences above wake a device that happens > to have previously been put into D3, and AFAICT it could only have got > there because of a previous vfio_pci_set_power_state(). Seems its only > caller is from the emulation of PCI_PM_CTRL using > vfio_lock_and_set_power_state(), and this zaps/revokes BAR access before > a transition to D3. Similarly, an attempt to access a BAR via an > ioctl/through vfio_pci_core_do_io_rw() fails the D3 check in > __vfio_pci_memory_enabled(), and besides will try to take the memory_lock. I thought the general design was the bars were made inaccessible before going to a low power state, and remain inaccessible while it is in low power? So the order of D0 doesn't matter. If it is not in D0 then there is no mappings and zap/revoke is a NOP. If is it in D0 then it doesn't matter because D0 is a nop. Jason

15 hours, 14 minutes

Re: [PATCH] drm/drm_crtc: fix race with dma_fence_signal() in ::get_driver_name()

by Philipp Stanner

On Tue, 2026-06-23 at 12:37 +0100, André Draszik wrote: > Hi, > > On Thu, 2026-06-18 at 17:56 +0200, Philipp Stanner wrote: > > +Cc Danilo > > > > On Thu, 2026-06-18 at 15:03 +0100, André Draszik wrote: > > > Since commit 541c8f2468b9 ("dma-buf: detach fence ops on signal v3"), > > > I'm seeing the BUG_ON() triggering in drm_crtc's fence_to_crtc() via > > > drm_crtc_fence_get_driver_name() regularly: > > > > > > Call trace: > > > panic+0x58/0x5c > > > die+0x160/0x178 > > > bug_brk_handler+0x70/0xa4 > > > call_el1_break_hook+0x3c/0x1a0 > > > do_el1_brk64+0x24/0x74 > > > el1_brk64+0x34/0x54 > > > el1h_64_sync_handler+0x80/0xfc > > > el1h_64_sync+0x84/0x88 > > > drm_crtc_fence_get_driver_name+0x60/0x68 (P) > > > sync_file_get_name+0x184/0x45c > > > sync_file_ioctl+0x404/0xf70 > > > __arm64_sys_ioctl+0x124/0x1dc > > > > > > This looks to be caused by a code flow similar to the following: > > > > > > +++ snip +++ > > > thread A thread B > > > > > > ioctl(SYNC_IOC_FILE_INFO) > > > sync_file_ioctl() > > > sync_file_get_name() > > > dma_fence_signal_timestamp_locked() dma_fence_driver_name() > > > ops = rcu_dereference(fence->ops) > > > if (!dma_fence_test_signaled_flag()) > > > ops->get_driver_name(fence) i.e. > > > drm_crtc_fence_get_driver_name() > > > test_and_set_bit(SIGNALED) > > > RCU_INIT_POINTER(fence->ops, NULL) > > > drm_crtc_fence_get_driver_name() > > > BUG_ON(rcu_access_pointer(fence->ops) > > > != &drm_crtc_fence_ops) > > > > Now this looks like a very similar problem that I have recently been > > concerned with: > > > > https://lore.kernel.org/dri-devel/20260612104251.2264707-2-phasta@kernel.or… > > > > https://lore.kernel.org/dri-devel/fa0dc9757bf8343516c4b156a2b70ec91b64ef8f.… > > > > > > I continue to believe because of bugs like this and the ones I have > > quoted in the threads above the robustness of the kernel could be > > greatly improved if we could get dma_fence fully synchronized with its > > lock. > > On top of that, sashiko highlighted (via my other patch) that the existing > code is missing some memory barriers: > > https://sashiko.dev/#/patchset/20260618-linux-drm_crtc_fix-v1-1-801f29c9853… > > I believe Lock synchronization would resolve that (as would adding explicit > memory barriers). That is being discussed in the thread I linked, where Gary lists which barriers you would need for (presumably correct) lockless magic. However, if my issue were to be solved with barriers, the test_and_set_bit() in dma_fence_signal_timestamp_locked() would have to be replaced with the more weakly ordered test_bit() and set_bit(), maybe creating other pitfalls. The ordering issue in the get_*_name() functions plays into that. Setting the bit would then be done after setting the ops-pointer to NULL. So one would have to try to move the NULL set, too. Long story short, this is painful and subtle. But I think what we are realizing over and over again is that dma_fence has many subtleties to its API contract, and the implementation's sparring use of spinlocks leads to workarounds where people take locks manually or have to do an RCU dance. Note that Christian is strongly opposed to guarding everything with locks, in part for supposedly occuring deadlocks in the fence callbacks when the driver needs to take its own locks. The community discussion regarding that problem is currently in some sort of dead end, where none of us seems to know what the correct path forward is. drm_sched users (and future users in Rust) use intermediate fences which decouple e.g. userspace from the actual hardware fences. So one path forward might be to question the callbacks in general and think about some sort of replacement for them. > > [...] > > > > > > Does the CRTC or DRM device need to be kept alive for the RCU grace period, > > or should the fence hold a proper reference to prevent the use-after-free > > when get_driver_name() and get_timeline_name() access the freed CRTC > > structure? > > Do you guys have any preference on that? It appears the use-after-free > should be resolved before merging the removal of the BUG_ON(), and I'd like > to progress on this. My understanding of the current situation is that as an issuer of dma_fence's you, in general, should wait for a grace period until you perform operations like driver unload, or, more generally, have fence- related resources and such being accessed through callbacks go away. Danilo has recently mentioned some life-time inconsistencies between wider kernel device model and DRM device model that might be related to that discussion, and which made him object against some RCU requirements. Maybe he's got the time to share some details with you that are relevant to your work. P. > > Cheers, > Andre'

15 hours, 51 minutes

Unlocking the Daily Puzzle: A Guide to the Connections Game

by graceful.earthworm.hsos＠hidingmail.com

In the ever-expanding world of daily word puzzles, one game has carved out a delightful niche for itself with its unique blend of logic and linguistic intuition: the Connections Game. If you're looking for a fresh, engaging challenge that's more about thoughtful categorization than rapid word association, then Connections is a fantastic game to dive into. It’s the kind of puzzle that rewards careful consideration and the ability to spot subtle patterns, making it a perfect brain-teaser for your morning coffee or an evening wind-down. https://connectionsgamefree.com How to Play: The Art of Grouping The premise of Connections is elegantly simple, yet surprisingly deep. You're presented with 16 words, and your goal is to sort them into four groups of four. Each group shares a common thread or category. The catch? You don’t know what those categories are, and some words might seem to fit into multiple groups at first glance, leading to delightful red herrings. When you start a new game, you'll see the 16 words laid out in a grid. To play, you simply select four words that you believe belong together. Once you’ve made your selection, you submit your guess. If you’re correct, the group will collapse, and its category will be revealed. If you're incorrect, you'll lose one of your precious four mistakes. The game ends when you've successfully grouped all four sets of words, or when you run out of mistakes. The difficulty of the categories varies – some are straightforward, while others require a more lateral way of thinking, making each day's puzzle a fresh adventure. Tips for Becoming a Connections Master To truly enjoy and excel at the Connections Game, here are a few friendly tips that have helped many players, including myself: Don't Rush: Unlike some timed word games, Connections encourages contemplation. Take your time to read all 16 words several times. Don’t jump to conclusions with the first obvious connection you see. Look for the Obvious First (Sometimes): While red herrings are common, sometimes there's a truly obvious group staring you in the face. These "easy" groups can help you clear some clutter and focus on the trickier words. Consider Word Forms: Pay attention to whether words are nouns, verbs, adjectives, or even proper nouns. This can be a huge clue. For example, a group might consist of "verbs related to speaking" or "types of cheeses." Think Broadly and Narrowly: Some categories are very specific (e.g., "Things you find in a toolbox"), while others are more abstract (e.g., "Words that precede 'Light'"). Try to think about both the common dictionary definition and potential idiomatic uses. The "One Away" Clue: If you make an incorrect guess and get the "One Away!" notification, it means three of your chosen words belong to a group, and one does not. This is a powerful clue! Identify the outlier and try swapping it for another word. Look for Synonyms or Antonyms: Sometimes the connection is simply a set of synonyms, or perhaps a group of words that are all antonyms of a particular concept. Conclusion: A Rewarding Daily Ritual Connections is more than just a puzzle; it's a daily exercise in linguistic deduction and pattern recognition. It’s a game that challenges your vocabulary and your ability to think critically about the relationships between words. Whether you’re a seasoned word-game enthusiast or just looking for a delightful new brain-teaser, Connections offers a satisfying and rewarding experience. So, gather your wits, embrace the challenge, and enjoy the delightful "aha!" moments that come with solving each day's unique puzzle.

23 hours, 11 minutes

Drop, Combine, Explode: The Oddly Satisfying World of Watermelon Puzzles

by quarrelsome.quail.btqn＠hidingmail.net

https://suikagame.lol/ There's something uniquely appealing about watching fruits merge together in slow motion. If you've scrolled through gaming communities lately, you've probably noticed more people talking about watermelon puzzle games, and for good reason. These games tap into something genuinely fun—the simple pleasure of combining things and watching them transform. Suika Game has become the poster child of this genre, and it's worth understanding why so many people find themselves absorbed in dropping cherry tomatoes and strawberries into a physics-based box. What's Actually Happening Here? At its heart, a watermelon puzzle is about merging identical fruits to create bigger ones. You start with small items—grapes or cherries—and your job is to drop them into a container and pair them together. When two matching fruits touch, they combine into the next size up. Two grapes become strawberries, two strawberries become oranges, and the chain continues until you're (hopefully) stacking massive watermelons. The catch? Your container has limited space. It's like a vertical Tetris with physics and gravity. Fruits don't stack neatly in rows—they tumble around realistically, bounce off walls, and settle where they land. This means you need to think strategically about where each piece lands. Drop a fruit carelessly, and it might block the path for future combinations or create an awkward pile that leaves no room for your next move. Each game typically continues until you can't fit any more pieces into the box. Some versions include special mechanics—occasional bombs or special items that clear out sections of fruit. But the core loop remains the same: drop, combine, survive as long as possible. Getting Into the Flow

1 day, 1 hour

Why should you buy a dachshund puppy?

by Chong Criston

1 day, 3 hours

Jump to page:

2026

2025

2024

2023

2022

2021

2020

2019

2018

2017

2016

2015

2014

2013

2012

2011

Linaro-mm-sig