April 2024 - Linux-stable-mirror

[PATCH net v2] udp: don't be set unconnected if only UDP cmsg

by Yick Xie

If "udp_cmsg_send()" returned 0 (i.e. only UDP cmsg), "connected" should not be set to 0. Otherwise it stops the connected socket from using the cached route. Fixes: 2e8de8576343 ("udp: add gso segment cmsg") Signed-off-by: Yick Xie <yick.xie(a)gmail.com> Cc: stable(a)vger.kernel.org --- v2: Add Fixes tag v1: https://lore.kernel.org/netdev/20240414195213.106209-1-yick.xie@gmail.com/ --- net/ipv4/udp.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index c02bf011d4a6..420905be5f30 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1123,16 +1123,17 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) if (msg->msg_controllen) { err = udp_cmsg_send(sk, msg, &ipc.gso_size); - if (err > 0) + if (err > 0) { err = ip_cmsg_send(sk, msg, &ipc, sk->sk_family == AF_INET6); + connected = 0; + } if (unlikely(err < 0)) { kfree(ipc.opt); return err; } if (ipc.opt) free = 1; - connected = 0; } if (!ipc.opt) { struct ip_options_rcu *inet_opt; -- 2.34.1

8 months, 3 weeks

4
6
0 0

+ mm-hugetlb-fix-debug_locks_warn_on1-when-dissolve_free_hugetlb_folio.patch added to mm-hotfixes-unstable branch

by Andrew Morton

The patch titled Subject: mm/hugetlb: fix DEBUG_LOCKS_WARN_ON(1) when dissolve_free_hugetlb_folio() has been added to the -mm mm-hotfixes-unstable branch. Its filename is mm-hugetlb-fix-debug_locks_warn_on1-when-dissolve_free_hugetlb_folio.patch This patch will shortly appear at https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patche… This patch will later appear in the mm-hotfixes-unstable branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm Before you just go and hit "reply", please: a) Consider who else should be cc'ed b) Prefer to cc a suitable mailing list as well c) Ideally: find the original patch on the mailing list and do a reply-to-all to that, adding suitable additional cc's *** Remember to use Documentation/process/submit-checklist.rst when testing your code *** The -mm tree is included into linux-next via the mm-everything branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm and is updated there every 2-3 working days ------------------------------------------------------ From: Miaohe Lin <linmiaohe(a)huawei.com> Subject: mm/hugetlb: fix DEBUG_LOCKS_WARN_ON(1) when dissolve_free_hugetlb_folio() Date: Fri, 19 Apr 2024 16:58:19 +0800 When I did memory failure tests recently, below warning occurs: DEBUG_LOCKS_WARN_ON(1) WARNING: CPU: 8 PID: 1011 at kernel/locking/lockdep.c:232 __lock_acquire+0xccb/0x1ca0 Modules linked in: mce_inject hwpoison_inject CPU: 8 PID: 1011 Comm: bash Kdump: loaded Not tainted 6.9.0-rc3-next-20240410-00012-gdb69f219f4be #3 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.14.0-0-g155821a1990b-prebuilt.qemu.org 04/01/2014 RIP: 0010:__lock_acquire+0xccb/0x1ca0 RSP: 0018:ffffa7a1c7fe3bd0 EFLAGS: 00000082 RAX: 0000000000000000 RBX: eb851eb853975fcf RCX: ffffa1ce5fc1c9c8 RDX: 00000000ffffffd8 RSI: 0000000000000027 RDI: ffffa1ce5fc1c9c0 RBP: ffffa1c6865d3280 R08: ffffffffb0f570a8 R09: 0000000000009ffb R10: 0000000000000286 R11: ffffffffb0f2ad50 R12: ffffa1c6865d3d10 R13: ffffa1c6865d3c70 R14: 0000000000000000 R15: 0000000000000004 FS: 00007ff9f32aa740(0000) GS:ffffa1ce5fc00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007ff9f3134ba0 CR3: 00000008484e4000 CR4: 00000000000006f0 Call Trace: <TASK> lock_acquire+0xbe/0x2d0 _raw_spin_lock_irqsave+0x3a/0x60 hugepage_subpool_put_pages.part.0+0xe/0xc0 free_huge_folio+0x253/0x3f0 dissolve_free_huge_page+0x147/0x210 __page_handle_poison+0x9/0x70 memory_failure+0x4e6/0x8c0 hard_offline_page_store+0x55/0xa0 kernfs_fop_write_iter+0x12c/0x1d0 vfs_write+0x380/0x540 ksys_write+0x64/0xe0 do_syscall_64+0xbc/0x1d0 entry_SYSCALL_64_after_hwframe+0x77/0x7f RIP: 0033:0x7ff9f3114887 RSP: 002b:00007ffecbacb458 EFLAGS: 00000246 ORIG_RAX: 0000000000000001 RAX: ffffffffffffffda RBX: 000000000000000c RCX: 00007ff9f3114887 RDX: 000000000000000c RSI: 0000564494164e10 RDI: 0000000000000001 RBP: 0000564494164e10 R08: 00007ff9f31d1460 R09: 000000007fffffff R10: 0000000000000000 R11: 0000000000000246 R12: 000000000000000c R13: 00007ff9f321b780 R14: 00007ff9f3217600 R15: 00007ff9f3216a00 </TASK> Kernel panic - not syncing: kernel: panic_on_warn set ... CPU: 8 PID: 1011 Comm: bash Kdump: loaded Not tainted 6.9.0-rc3-next-20240410-00012-gdb69f219f4be #3 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.14.0-0-g155821a1990b-prebuilt.qemu.org 04/01/2014 Call Trace: <TASK> panic+0x326/0x350 check_panic_on_warn+0x4f/0x50 __warn+0x98/0x190 report_bug+0x18e/0x1a0 handle_bug+0x3d/0x70 exc_invalid_op+0x18/0x70 asm_exc_invalid_op+0x1a/0x20 RIP: 0010:__lock_acquire+0xccb/0x1ca0 RSP: 0018:ffffa7a1c7fe3bd0 EFLAGS: 00000082 RAX: 0000000000000000 RBX: eb851eb853975fcf RCX: ffffa1ce5fc1c9c8 RDX: 00000000ffffffd8 RSI: 0000000000000027 RDI: ffffa1ce5fc1c9c0 RBP: ffffa1c6865d3280 R08: ffffffffb0f570a8 R09: 0000000000009ffb R10: 0000000000000286 R11: ffffffffb0f2ad50 R12: ffffa1c6865d3d10 R13: ffffa1c6865d3c70 R14: 0000000000000000 R15: 0000000000000004 lock_acquire+0xbe/0x2d0 _raw_spin_lock_irqsave+0x3a/0x60 hugepage_subpool_put_pages.part.0+0xe/0xc0 free_huge_folio+0x253/0x3f0 dissolve_free_huge_page+0x147/0x210 __page_handle_poison+0x9/0x70 memory_failure+0x4e6/0x8c0 hard_offline_page_store+0x55/0xa0 kernfs_fop_write_iter+0x12c/0x1d0 vfs_write+0x380/0x540 ksys_write+0x64/0xe0 do_syscall_64+0xbc/0x1d0 entry_SYSCALL_64_after_hwframe+0x77/0x7f RIP: 0033:0x7ff9f3114887 RSP: 002b:00007ffecbacb458 EFLAGS: 00000246 ORIG_RAX: 0000000000000001 RAX: ffffffffffffffda RBX: 000000000000000c RCX: 00007ff9f3114887 RDX: 000000000000000c RSI: 0000564494164e10 RDI: 0000000000000001 RBP: 0000564494164e10 R08: 00007ff9f31d1460 R09: 000000007fffffff R10: 0000000000000000 R11: 0000000000000246 R12: 000000000000000c R13: 00007ff9f321b780 R14: 00007ff9f3217600 R15: 00007ff9f3216a00 </TASK> After git bisecting and digging into the code, I believe the root cause is that _deferred_list field of folio is unioned with _hugetlb_subpool field. In __update_and_free_hugetlb_folio(), folio->_deferred_list is initialized leading to corrupted folio->_hugetlb_subpool when folio is hugetlb. Later free_huge_folio() will use _hugetlb_subpool and above warning happens. But it is assumed hugetlb flag must have been cleared when calling folio_put() in update_and_free_hugetlb_folio(). This assumption is broken due to below race: CPU1 CPU2 dissolve_free_huge_page update_and_free_pages_bulk update_and_free_hugetlb_folio hugetlb_vmemmap_restore_folios folio_clear_hugetlb_vmemmap_optimized clear_flag = folio_test_hugetlb_vmemmap_optimized if (clear_flag) <-- False, it's already cleared. __folio_clear_hugetlb(folio) <-- Hugetlb is not cleared. folio_put free_huge_folio <-- free_the_page is expected. list_for_each_entry() __folio_clear_hugetlb <-- Too late. Fix this issue by checking whether folio is hugetlb directly instead of checking clear_flag to close the race window. Link: https://lkml.kernel.org/r/20240419085819.1901645-1-linmiaohe@huawei.com Fixes: 32c877191e02 ("hugetlb: do not clear hugetlb dtor until allocating vmemmap") Signed-off-by: Miaohe Lin <linmiaohe(a)huawei.com> Cc: Oscar Salvador <osalvador(a)suse.de> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- mm/hugetlb.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) --- a/mm/hugetlb.c~mm-hugetlb-fix-debug_locks_warn_on1-when-dissolve_free_hugetlb_folio +++ a/mm/hugetlb.c @@ -1781,7 +1781,7 @@ static void __update_and_free_hugetlb_fo * If vmemmap pages were allocated above, then we need to clear the * hugetlb destructor under the hugetlb lock. */ - if (clear_dtor) { + if (folio_test_hugetlb(folio)) { spin_lock_irq(&hugetlb_lock); __clear_hugetlb_destructor(h, folio); spin_unlock_irq(&hugetlb_lock); _ Patches currently in -mm which might be from linmiaohe(a)huawei.com are mm-hugetlb-fix-debug_locks_warn_on1-when-dissolve_free_hugetlb_folio.patch

8 months, 3 weeks

1
0
0 0

[PATCH net v2] net: b44: set pause params only when interface is up

by Peter Münster

Hi, This patch fixes a kernel panic when using netifd. Could you please apply it also to linux-5.15.y at least? TIA and kind regards, -- Peter

8 months, 3 weeks

2
1
0 0

[PATCH] mm/writeback: fix possible divide-by-zero in wb_dirty_limits(), again

by Zach O'Keefe

(struct dirty_throttle_control *)->thresh is an unsigned long, but is passed as the u32 divisor argument to div_u64(). On architectures where unsigned long is 64 bytes, the argument will be implicitly truncated. Use div64_u64() instead of div_u64() so that the value used in the "is this a safe division" check is the same as the divisor. Also, remove redundant cast of the numerator to u64, as that should happen implicitly. This would be difficult to exploit in memcg domain, given the ratio-based arithmetic domain_drity_limits() uses, but is much easier in global writeback domain with a BDI_CAP_STRICTLIMIT-backing device, using e.g. vm.dirty_bytes=(1<<32)*PAGE_SIZE so that dtc->thresh == (1<<32) Fixes: f6789593d5ce ("mm/page-writeback.c: fix divide by zero in bdi_dirty_limits()") Cc: Maxim Patlasov <MPatlasov(a)parallels.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Zach O'Keefe <zokeefe(a)google.com> --- mm/page-writeback.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/page-writeback.c b/mm/page-writeback.c index cd4e4ae77c40a..02147b61712bc 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -1638,7 +1638,7 @@ static inline void wb_dirty_limits(struct dirty_throttle_control *dtc) */ dtc->wb_thresh = __wb_calc_thresh(dtc); dtc->wb_bg_thresh = dtc->thresh ? - div_u64((u64)dtc->wb_thresh * dtc->bg_thresh, dtc->thresh) : 0; + div64_u64(dtc->wb_thresh * dtc->bg_thresh, dtc->thresh) : 0; /* * In order to avoid the stacked BDI deadlock we need -- 2.43.0.429.g432eaa2c6b-goog

8 months, 3 weeks

2
4
0 0

Re: [bug-report] task info hung problem in fb_deferred_io_work()

by Harshit Mogalapalli

Hi Nam, +CC stable( heads up as this is a regression affecting 5.15.y and probably others, Greg: this was reproducible upstream so reported everything w.r.t upstream code but initially found on 5.15.y) On 19/04/24 20:29, Nam Cao wrote: > On 2024-04-18 Harshit Mogalapalli wrote: >> While fuzzing 5.15.y kernel with Syzkaller, we noticed a INFO: task hung >> bug in fb_deferred_io_work() > > I think the problem is because of improper offset address calculation. > The kernel calculate address offset with: > offset = vmf->address - vmf->vma->vm_start > > Now the problem is that your C program mmap the framebuffer at 2 > different offsets: > mmap(ptr, 4096, PROT_WRITE, MAP_FIXED | MAP_SHARED, fd, 0xff000); > mmap(ptr, 4096, PROT_WRITE, MAP_FIXED | MAP_SHARED, fd, 0); > > but the kernel doesn't take these different offsets into account. > So, 2 different pages are mistakenly recognized as the same page. > > Can you try the following patch? This patch works well against the reproducer, this simplified repro and the longer repro which syzkaller generated couldn't trigger any hang with the below patch applied. Thanks, Harshit > > Best regards, > Nam > > diff --git a/drivers/video/fbdev/core/fb_defio.c b/drivers/video/fbdev/core/fb_defio.c > index dae96c9f61cf..d5d6cd9e8b29 100644 > --- a/drivers/video/fbdev/core/fb_defio.c > +++ b/drivers/video/fbdev/core/fb_defio.c > @@ -196,7 +196,8 @@ static vm_fault_t fb_deferred_io_track_page(struct fb_info *info, unsigned long > */ > static vm_fault_t fb_deferred_io_page_mkwrite(struct fb_info *info, struct vm_fault *vmf) > { > - unsigned long offset = vmf->address - vmf->vma->vm_start; > + unsigned long offset = vmf->address - vmf->vma->vm_start > + + (vmf->vma->vm_pgoff << PAGE_SHIFT); > struct page *page = vmf->page; > > file_update_time(vmf->vma->vm_file); > >

8 months, 3 weeks

2
2
0 0

[PATCH stable 6.8.y] Revert "vmgenid: emit uevent when VMGENID updates"

by Jason A. Donenfeld

commit 3aadf100f93d80815685493d60cd8cab206403df upstream. This reverts commit ad6bcdad2b6724e113f191a12f859a9e8456b26d. I had nak'd it, and Greg said on the thread that it links that he wasn't going to take it either, especially since it's not his code or his tree, but then, seemingly accidentally, it got pushed up some months later, in what looks like a mistake, with no further discussion in the linked thread. So revert it, since it's clearly not intended. Fixes: ad6bcdad2b67 ("vmgenid: emit uevent when VMGENID updates") Cc: stable(a)vger.kernel.org Acked-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Link: https://lore.kernel.org/r/20230531095119.11202-2-bchalios@amazon.es Signed-off-by: Jason A. Donenfeld <Jason(a)zx2c4.com> --- drivers/virt/vmgenid.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/virt/vmgenid.c b/drivers/virt/vmgenid.c index b67a28da4702..a1c467a0e9f7 100644 --- a/drivers/virt/vmgenid.c +++ b/drivers/virt/vmgenid.c @@ -68,7 +68,6 @@ static int vmgenid_add(struct acpi_device *device) static void vmgenid_notify(struct acpi_device *device, u32 event) { struct vmgenid_state *state = acpi_driver_data(device); - char *envp[] = { "NEW_VMGENID=1", NULL }; u8 old_id[VMGENID_SIZE]; memcpy(old_id, state->this_id, sizeof(old_id)); @@ -76,7 +75,6 @@ static void vmgenid_notify(struct acpi_device *device, u32 event) if (!memcmp(old_id, state->this_id, sizeof(old_id))) return; add_vmfork_randomness(state->this_id, sizeof(state->this_id)); - kobject_uevent_env(&device->dev.kobj, KOBJ_CHANGE, envp); } static const struct acpi_device_id vmgenid_ids[] = { -- 2.44.0

8 months, 3 weeks

1
0
0 0

FAILED: patch "[PATCH] random: handle creditable entropy from atomic process context" failed to apply to 5.15-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.15-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.15.y git checkout FETCH_HEAD git cherry-pick -x e871abcda3b67d0820b4182ebe93435624e9c6a4 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024041901-roundish-flint-1143@gregkh' --subject-prefix 'PATCH 5.15.y' HEAD^.. Possible dependencies: e871abcda3b6 ("random: handle creditable entropy from atomic process context") bbc7e1bed1f5 ("random: add back async readiness notifier") 9148de3196ed ("random: reseed in delayed work rather than on-demand") f62384995e4c ("random: split initialization into early step and later step") 745558f95885 ("random: use hwgenerator randomness more frequently at early boot") 228dfe98a313 ("Merge tag 'char-misc-6.0-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/char-misc") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From e871abcda3b67d0820b4182ebe93435624e9c6a4 Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" <Jason(a)zx2c4.com> Date: Wed, 17 Apr 2024 13:38:29 +0200 Subject: [PATCH] random: handle creditable entropy from atomic process context The entropy accounting changes a static key when the RNG has initialized, since it only ever initializes once. Static key changes, however, cannot be made from atomic context, so depending on where the last creditable entropy comes from, the static key change might need to be deferred to a worker. Previously the code used the execute_in_process_context() helper function, which accounts for whether or not the caller is in_interrupt(). However, that doesn't account for the case where the caller is actually in process context but is holding a spinlock. This turned out to be the case with input_handle_event() in drivers/input/input.c contributing entropy: [<ffffffd613025ba0>] die+0xa8/0x2fc [<ffffffd613027428>] bug_handler+0x44/0xec [<ffffffd613016964>] brk_handler+0x90/0x144 [<ffffffd613041e58>] do_debug_exception+0xa0/0x148 [<ffffffd61400c208>] el1_dbg+0x60/0x7c [<ffffffd61400c000>] el1h_64_sync_handler+0x38/0x90 [<ffffffd613011294>] el1h_64_sync+0x64/0x6c [<ffffffd613102d88>] __might_resched+0x1fc/0x2e8 [<ffffffd613102b54>] __might_sleep+0x44/0x7c [<ffffffd6130b6eac>] cpus_read_lock+0x1c/0xec [<ffffffd6132c2820>] static_key_enable+0x14/0x38 [<ffffffd61400ac08>] crng_set_ready+0x14/0x28 [<ffffffd6130df4dc>] execute_in_process_context+0xb8/0xf8 [<ffffffd61400ab30>] _credit_init_bits+0x118/0x1dc [<ffffffd6138580c8>] add_timer_randomness+0x264/0x270 [<ffffffd613857e54>] add_input_randomness+0x38/0x48 [<ffffffd613a80f94>] input_handle_event+0x2b8/0x490 [<ffffffd613a81310>] input_event+0x6c/0x98 According to Guoyong, it's not really possible to refactor the various drivers to never hold a spinlock there. And in_atomic() isn't reliable. So, rather than trying to be too fancy, just punt the change in the static key to a workqueue always. There's basically no drawback of doing this, as the code already needed to account for the static key not changing immediately, and given that it's just an optimization, there's not exactly a hurry to change the static key right away, so deferal is fine. Reported-by: Guoyong Wang <guoyong.wang(a)mediatek.com> Cc: stable(a)vger.kernel.org Fixes: f5bda35fba61 ("random: use static branch for crng_ready()") Signed-off-by: Jason A. Donenfeld <Jason(a)zx2c4.com> diff --git a/drivers/char/random.c b/drivers/char/random.c index 456be28ba67c..2597cb43f438 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -702,7 +702,7 @@ static void extract_entropy(void *buf, size_t len) static void __cold _credit_init_bits(size_t bits) { - static struct execute_work set_ready; + static DECLARE_WORK(set_ready, crng_set_ready); unsigned int new, orig, add; unsigned long flags; @@ -718,8 +718,8 @@ static void __cold _credit_init_bits(size_t bits) if (orig < POOL_READY_BITS && new >= POOL_READY_BITS) { crng_reseed(NULL); /* Sets crng_init to CRNG_READY under base_crng.lock. */ - if (static_key_initialized) - execute_in_process_context(crng_set_ready, &set_ready); + if (static_key_initialized && system_unbound_wq) + queue_work(system_unbound_wq, &set_ready); atomic_notifier_call_chain(&random_ready_notifier, 0, NULL); wake_up_interruptible(&crng_init_wait); kill_fasync(&fasync, SIGIO, POLL_IN); @@ -890,8 +890,8 @@ void __init random_init(void) /* * If we were initialized by the cpu or bootloader before jump labels - * are initialized, then we should enable the static branch here, where - * it's guaranteed that jump labels have been initialized. + * or workqueues are initialized, then we should enable the static + * branch here, where it's guaranteed that these have been initialized. */ if (!static_branch_likely(&crng_is_ready) && crng_init >= CRNG_READY) crng_set_ready(NULL);

8 months, 3 weeks

2
1
0 0

FAILED: patch "[PATCH] random: handle creditable entropy from atomic process context" failed to apply to 5.10-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.10-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.10.y git checkout FETCH_HEAD git cherry-pick -x e871abcda3b67d0820b4182ebe93435624e9c6a4 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024041903-pentagon-deceiver-fe1d@gregkh' --subject-prefix 'PATCH 5.10.y' HEAD^.. Possible dependencies: e871abcda3b6 ("random: handle creditable entropy from atomic process context") bbc7e1bed1f5 ("random: add back async readiness notifier") 9148de3196ed ("random: reseed in delayed work rather than on-demand") f62384995e4c ("random: split initialization into early step and later step") 745558f95885 ("random: use hwgenerator randomness more frequently at early boot") 228dfe98a313 ("Merge tag 'char-misc-6.0-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/char-misc") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From e871abcda3b67d0820b4182ebe93435624e9c6a4 Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" <Jason(a)zx2c4.com> Date: Wed, 17 Apr 2024 13:38:29 +0200 Subject: [PATCH] random: handle creditable entropy from atomic process context The entropy accounting changes a static key when the RNG has initialized, since it only ever initializes once. Static key changes, however, cannot be made from atomic context, so depending on where the last creditable entropy comes from, the static key change might need to be deferred to a worker. Previously the code used the execute_in_process_context() helper function, which accounts for whether or not the caller is in_interrupt(). However, that doesn't account for the case where the caller is actually in process context but is holding a spinlock. This turned out to be the case with input_handle_event() in drivers/input/input.c contributing entropy: [<ffffffd613025ba0>] die+0xa8/0x2fc [<ffffffd613027428>] bug_handler+0x44/0xec [<ffffffd613016964>] brk_handler+0x90/0x144 [<ffffffd613041e58>] do_debug_exception+0xa0/0x148 [<ffffffd61400c208>] el1_dbg+0x60/0x7c [<ffffffd61400c000>] el1h_64_sync_handler+0x38/0x90 [<ffffffd613011294>] el1h_64_sync+0x64/0x6c [<ffffffd613102d88>] __might_resched+0x1fc/0x2e8 [<ffffffd613102b54>] __might_sleep+0x44/0x7c [<ffffffd6130b6eac>] cpus_read_lock+0x1c/0xec [<ffffffd6132c2820>] static_key_enable+0x14/0x38 [<ffffffd61400ac08>] crng_set_ready+0x14/0x28 [<ffffffd6130df4dc>] execute_in_process_context+0xb8/0xf8 [<ffffffd61400ab30>] _credit_init_bits+0x118/0x1dc [<ffffffd6138580c8>] add_timer_randomness+0x264/0x270 [<ffffffd613857e54>] add_input_randomness+0x38/0x48 [<ffffffd613a80f94>] input_handle_event+0x2b8/0x490 [<ffffffd613a81310>] input_event+0x6c/0x98 According to Guoyong, it's not really possible to refactor the various drivers to never hold a spinlock there. And in_atomic() isn't reliable. So, rather than trying to be too fancy, just punt the change in the static key to a workqueue always. There's basically no drawback of doing this, as the code already needed to account for the static key not changing immediately, and given that it's just an optimization, there's not exactly a hurry to change the static key right away, so deferal is fine. Reported-by: Guoyong Wang <guoyong.wang(a)mediatek.com> Cc: stable(a)vger.kernel.org Fixes: f5bda35fba61 ("random: use static branch for crng_ready()") Signed-off-by: Jason A. Donenfeld <Jason(a)zx2c4.com> diff --git a/drivers/char/random.c b/drivers/char/random.c index 456be28ba67c..2597cb43f438 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -702,7 +702,7 @@ static void extract_entropy(void *buf, size_t len) static void __cold _credit_init_bits(size_t bits) { - static struct execute_work set_ready; + static DECLARE_WORK(set_ready, crng_set_ready); unsigned int new, orig, add; unsigned long flags; @@ -718,8 +718,8 @@ static void __cold _credit_init_bits(size_t bits) if (orig < POOL_READY_BITS && new >= POOL_READY_BITS) { crng_reseed(NULL); /* Sets crng_init to CRNG_READY under base_crng.lock. */ - if (static_key_initialized) - execute_in_process_context(crng_set_ready, &set_ready); + if (static_key_initialized && system_unbound_wq) + queue_work(system_unbound_wq, &set_ready); atomic_notifier_call_chain(&random_ready_notifier, 0, NULL); wake_up_interruptible(&crng_init_wait); kill_fasync(&fasync, SIGIO, POLL_IN); @@ -890,8 +890,8 @@ void __init random_init(void) /* * If we were initialized by the cpu or bootloader before jump labels - * are initialized, then we should enable the static branch here, where - * it's guaranteed that jump labels have been initialized. + * or workqueues are initialized, then we should enable the static + * branch here, where it's guaranteed that these have been initialized. */ if (!static_branch_likely(&crng_is_ready) && crng_init >= CRNG_READY) crng_set_ready(NULL);

8 months, 3 weeks

2
1
0 0

FAILED: patch "[PATCH] random: handle creditable entropy from atomic process context" failed to apply to 5.4-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.4-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.4.y git checkout FETCH_HEAD git cherry-pick -x e871abcda3b67d0820b4182ebe93435624e9c6a4 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024041905-obvious-blush-10d8@gregkh' --subject-prefix 'PATCH 5.4.y' HEAD^.. Possible dependencies: e871abcda3b6 ("random: handle creditable entropy from atomic process context") bbc7e1bed1f5 ("random: add back async readiness notifier") 9148de3196ed ("random: reseed in delayed work rather than on-demand") f62384995e4c ("random: split initialization into early step and later step") 745558f95885 ("random: use hwgenerator randomness more frequently at early boot") 228dfe98a313 ("Merge tag 'char-misc-6.0-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/char-misc") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From e871abcda3b67d0820b4182ebe93435624e9c6a4 Mon Sep 17 00:00:00 2001 From: "Jason A. Donenfeld" <Jason(a)zx2c4.com> Date: Wed, 17 Apr 2024 13:38:29 +0200 Subject: [PATCH] random: handle creditable entropy from atomic process context The entropy accounting changes a static key when the RNG has initialized, since it only ever initializes once. Static key changes, however, cannot be made from atomic context, so depending on where the last creditable entropy comes from, the static key change might need to be deferred to a worker. Previously the code used the execute_in_process_context() helper function, which accounts for whether or not the caller is in_interrupt(). However, that doesn't account for the case where the caller is actually in process context but is holding a spinlock. This turned out to be the case with input_handle_event() in drivers/input/input.c contributing entropy: [<ffffffd613025ba0>] die+0xa8/0x2fc [<ffffffd613027428>] bug_handler+0x44/0xec [<ffffffd613016964>] brk_handler+0x90/0x144 [<ffffffd613041e58>] do_debug_exception+0xa0/0x148 [<ffffffd61400c208>] el1_dbg+0x60/0x7c [<ffffffd61400c000>] el1h_64_sync_handler+0x38/0x90 [<ffffffd613011294>] el1h_64_sync+0x64/0x6c [<ffffffd613102d88>] __might_resched+0x1fc/0x2e8 [<ffffffd613102b54>] __might_sleep+0x44/0x7c [<ffffffd6130b6eac>] cpus_read_lock+0x1c/0xec [<ffffffd6132c2820>] static_key_enable+0x14/0x38 [<ffffffd61400ac08>] crng_set_ready+0x14/0x28 [<ffffffd6130df4dc>] execute_in_process_context+0xb8/0xf8 [<ffffffd61400ab30>] _credit_init_bits+0x118/0x1dc [<ffffffd6138580c8>] add_timer_randomness+0x264/0x270 [<ffffffd613857e54>] add_input_randomness+0x38/0x48 [<ffffffd613a80f94>] input_handle_event+0x2b8/0x490 [<ffffffd613a81310>] input_event+0x6c/0x98 According to Guoyong, it's not really possible to refactor the various drivers to never hold a spinlock there. And in_atomic() isn't reliable. So, rather than trying to be too fancy, just punt the change in the static key to a workqueue always. There's basically no drawback of doing this, as the code already needed to account for the static key not changing immediately, and given that it's just an optimization, there's not exactly a hurry to change the static key right away, so deferal is fine. Reported-by: Guoyong Wang <guoyong.wang(a)mediatek.com> Cc: stable(a)vger.kernel.org Fixes: f5bda35fba61 ("random: use static branch for crng_ready()") Signed-off-by: Jason A. Donenfeld <Jason(a)zx2c4.com> diff --git a/drivers/char/random.c b/drivers/char/random.c index 456be28ba67c..2597cb43f438 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -702,7 +702,7 @@ static void extract_entropy(void *buf, size_t len) static void __cold _credit_init_bits(size_t bits) { - static struct execute_work set_ready; + static DECLARE_WORK(set_ready, crng_set_ready); unsigned int new, orig, add; unsigned long flags; @@ -718,8 +718,8 @@ static void __cold _credit_init_bits(size_t bits) if (orig < POOL_READY_BITS && new >= POOL_READY_BITS) { crng_reseed(NULL); /* Sets crng_init to CRNG_READY under base_crng.lock. */ - if (static_key_initialized) - execute_in_process_context(crng_set_ready, &set_ready); + if (static_key_initialized && system_unbound_wq) + queue_work(system_unbound_wq, &set_ready); atomic_notifier_call_chain(&random_ready_notifier, 0, NULL); wake_up_interruptible(&crng_init_wait); kill_fasync(&fasync, SIGIO, POLL_IN); @@ -890,8 +890,8 @@ void __init random_init(void) /* * If we were initialized by the cpu or bootloader before jump labels - * are initialized, then we should enable the static branch here, where - * it's guaranteed that jump labels have been initialized. + * or workqueues are initialized, then we should enable the static + * branch here, where it's guaranteed that these have been initialized. */ if (!static_branch_likely(&crng_is_ready) && crng_init >= CRNG_READY) crng_set_ready(NULL);

8 months, 3 weeks

2
1
0 0

[PATCH 4.19.y v6 2/2] tracing: Use var_refs[] for hist trigger reference checking

by George Guo

From: Tom Zanussi <tzanussi(a)gmail.com> commit e4f6d245031e04bdd12db390298acec0474a1a46 upstream. Since all the variable reference hist_fields are collected into hist_data->var_refs[] array, there's no need to go through all the fields looking for them, or in separate arrays like synth_var_refs[], which will be going away soon anyway. This also allows us to get rid of some unnecessary code and functions currently used for the same purpose. Link: http://lkml.kernel.org/r/1545246556.4239.7.camel@gmail.com Acked-by: Namhyung Kim <namhyung(a)kernel.org> Reviewed-by: Masami Hiramatsu <mhiramat(a)kernel.org> Signed-off-by: Tom Zanussi <tom.zanussi(a)linux.intel.com> Signed-off-by: Steven Rostedt (VMware) <rostedt(a)goodmis.org> Signed-off-by: George Guo <guodongtai(a)kylinos.cn> --- kernel/trace/trace_events_hist.c | 68 ++++++-------------------------- 1 file changed, 11 insertions(+), 57 deletions(-) diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index e4f5b6894cf2..ede370225245 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -1289,49 +1289,13 @@ check_field_for_var_ref(struct hist_field *hist_field, struct hist_trigger_data *var_data, unsigned int var_idx) { - struct hist_field *found = NULL; - - if (hist_field && hist_field->flags & HIST_FIELD_FL_VAR_REF) { - if (hist_field->var.idx == var_idx && - hist_field->var.hist_data == var_data) { - found = hist_field; - } - } - - return found; -} - -static struct hist_field * -check_field_for_var_refs(struct hist_trigger_data *hist_data, - struct hist_field *hist_field, - struct hist_trigger_data *var_data, - unsigned int var_idx, - unsigned int level) -{ - struct hist_field *found = NULL; - unsigned int i; - - if (level > 3) - return found; - - if (!hist_field) - return found; - - found = check_field_for_var_ref(hist_field, var_data, var_idx); - if (found) - return found; - - for (i = 0; i < HIST_FIELD_OPERANDS_MAX; i++) { - struct hist_field *operand; + WARN_ON(!(hist_field && hist_field->flags & HIST_FIELD_FL_VAR_REF)); - operand = hist_field->operands[i]; - found = check_field_for_var_refs(hist_data, operand, var_data, - var_idx, level + 1); - if (found) - return found; - } + if (hist_field && hist_field->var.idx == var_idx && + hist_field->var.hist_data == var_data) + return hist_field; - return found; + return NULL; } /** @@ -1350,26 +1314,16 @@ static struct hist_field *find_var_ref(struct hist_trigger_data *hist_data, struct hist_trigger_data *var_data, unsigned int var_idx) { - struct hist_field *hist_field, *found = NULL; + struct hist_field *hist_field; unsigned int i; - for_each_hist_field(i, hist_data) { - hist_field = hist_data->fields[i]; - found = check_field_for_var_refs(hist_data, hist_field, - var_data, var_idx, 0); - if (found) - return found; - } - - for (i = 0; i < hist_data->n_synth_var_refs; i++) { - hist_field = hist_data->synth_var_refs[i]; - found = check_field_for_var_refs(hist_data, hist_field, - var_data, var_idx, 0); - if (found) - return found; + for (i = 0; i < hist_data->n_var_refs; i++) { + hist_field = hist_data->var_refs[i]; + if (check_field_for_var_ref(hist_field, var_data, var_idx)) + return hist_field; } - return found; + return NULL; } /** -- 2.34.1

8 months, 3 weeks

1
0
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror April 2024