6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Timur Kristóf timur.kristof@gmail.com

[ Upstream commit 5c05bcf6ae7732da1bd4dc1958d527b5f07f216a ]

On various SI GPUs, a flickering can be observed near the bottom edge of the screen when using a single 4K 60Hz monitor over DP. Disabling MCLK switching works around this problem.

Reviewed-by: Alex Deucher alexander.deucher@amd.com Signed-off-by: Timur Kristóf timur.kristof@gmail.com Signed-off-by: Alex Deucher alexander.deucher@amd.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c | 5 +++++ 1 file changed, 5 insertions(+)

diff --git a/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c b/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c index 70efa4dce3848..a2b411a93b0fe 100644 --- a/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c +++ b/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c @@ -3500,6 +3500,11 @@ static void si_apply_state_adjust_rules(struct amdgpu_device *adev, * for these GPUs to calculate bandwidth requirements. */ if (high_pixelclock_count) { + /* Work around flickering lines at the bottom edge + * of the screen when using a single 4K 60Hz monitor. + */ + disable_mclk_switching = true; + /* On Oland, we observe some flickering when two 4K 60Hz * displays are connected, possibly because voltage is too low. * Raise the voltage by requiring a higher SCLK.

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Pauli Virtanen pav@iki.fi

[ Upstream commit 3b78f50918276ab28fb22eac9aa49401ac436a3b ]

Bluetooth 6lowpan.c netdev has header_ops, so it must set link-local header for RX skb, otherwise things crash, eg. with AF_PACKET SOCK_RAW

Add missing skb_reset_mac_header() for uncompressed ipv6 RX path.

For the compressed one, it is done in lowpan_header_decompress().

Log: (BlueZ 6lowpan-tester Client Recv Raw - Success) ------ kernel BUG at net/core/skbuff.c:212! Call Trace: <IRQ> ... packet_rcv (net/packet/af_packet.c:2152) ... <TASK> __local_bh_enable_ip (kernel/softirq.c:407) netif_rx (net/core/dev.c:5648) chan_recv_cb (net/bluetooth/6lowpan.c:294 net/bluetooth/6lowpan.c:359) ------

Fixes: 18722c247023 ("Bluetooth: Enable 6LoWPAN support for BT LE devices") Reviewed-by: Paul Menzel pmenzel@molgen.mpg.de Signed-off-by: Pauli Virtanen pav@iki.fi Signed-off-by: Luiz Augusto von Dentz luiz.von.dentz@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- net/bluetooth/6lowpan.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/net/bluetooth/6lowpan.c b/net/bluetooth/6lowpan.c index f0c862091bff2..f1d29fa4b4119 100644 --- a/net/bluetooth/6lowpan.c +++ b/net/bluetooth/6lowpan.c @@ -289,6 +289,7 @@ static int recv_pkt(struct sk_buff *skb, struct net_device *dev, local_skb->pkt_type = PACKET_HOST; local_skb->dev = dev;

+ skb_reset_mac_header(local_skb); skb_set_transport_header(local_skb, sizeof(struct ipv6hdr));

if (give_skb_to_upper(local_skb, dev) != NET_RX_SUCCESS) {

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Janusz Krzysztofik janusz.krzysztofik@linux.intel.com

[ Upstream commit 84bbe327a5cbb060f3321c9d9d4d53936fc1ef9b ]

On completion of i915_vma_pin_ww(), a synchronous variant of dma_fence_work_commit() is called. When pinning a VMA to GGTT address space on a Cherry View family processor, or on a Broxton generation SoC with VTD enabled, i.e., when stop_machine() is then called from intel_ggtt_bind_vma(), that can potentially lead to lock inversion among reservation_ww and cpu_hotplug locks.

[86.861179] ====================================================== [86.861193] WARNING: possible circular locking dependency detected [86.861209] 6.15.0-rc5-CI_DRM_16515-gca0305cadc2d+ #1 Tainted: G U [86.861226] ------------------------------------------------------ [86.861238] i915_module_loa/1432 is trying to acquire lock: [86.861252] ffffffff83489090 (cpu_hotplug_lock){++++}-{0:0}, at: stop_machine+0x1c/0x50 [86.861290] but task is already holding lock: [86.861303] ffffc90002e0b4c8 (reservation_ww_class_mutex){+.+.}-{3:3}, at: i915_vma_pin.constprop.0+0x39/0x1d0 [i915] [86.862233] which lock already depends on the new lock. [86.862251] the existing dependency chain (in reverse order) is: [86.862265] -> #5 (reservation_ww_class_mutex){+.+.}-{3:3}: [86.862292] dma_resv_lockdep+0x19a/0x390 [86.862315] do_one_initcall+0x60/0x3f0 [86.862334] kernel_init_freeable+0x3cd/0x680 [86.862353] kernel_init+0x1b/0x200 [86.862369] ret_from_fork+0x47/0x70 [86.862383] ret_from_fork_asm+0x1a/0x30 [86.862399] -> #4 (reservation_ww_class_acquire){+.+.}-{0:0}: [86.862425] dma_resv_lockdep+0x178/0x390 [86.862440] do_one_initcall+0x60/0x3f0 [86.862454] kernel_init_freeable+0x3cd/0x680 [86.862470] kernel_init+0x1b/0x200 [86.862482] ret_from_fork+0x47/0x70 [86.862495] ret_from_fork_asm+0x1a/0x30 [86.862509] -> #3 (&mm->mmap_lock){++++}-{3:3}: [86.862531] down_read_killable+0x46/0x1e0 [86.862546] lock_mm_and_find_vma+0xa2/0x280 [86.862561] do_user_addr_fault+0x266/0x8e0 [86.862578] exc_page_fault+0x8a/0x2f0 [86.862593] asm_exc_page_fault+0x27/0x30 [86.862607] filldir64+0xeb/0x180 [86.862620] kernfs_fop_readdir+0x118/0x480 [86.862635] iterate_dir+0xcf/0x2b0 [86.862648] __x64_sys_getdents64+0x84/0x140 [86.862661] x64_sys_call+0x1058/0x2660 [86.862675] do_syscall_64+0x91/0xe90 [86.862689] entry_SYSCALL_64_after_hwframe+0x76/0x7e [86.862703] -> #2 (&root->kernfs_rwsem){++++}-{3:3}: [86.862725] down_write+0x3e/0xf0 [86.862738] kernfs_add_one+0x30/0x3c0 [86.862751] kernfs_create_dir_ns+0x53/0xb0 [86.862765] internal_create_group+0x134/0x4c0 [86.862779] sysfs_create_group+0x13/0x20 [86.862792] topology_add_dev+0x1d/0x30 [86.862806] cpuhp_invoke_callback+0x4b5/0x850 [86.862822] cpuhp_issue_call+0xbf/0x1f0 [86.862836] __cpuhp_setup_state_cpuslocked+0x111/0x320 [86.862852] __cpuhp_setup_state+0xb0/0x220 [86.862866] topology_sysfs_init+0x30/0x50 [86.862879] do_one_initcall+0x60/0x3f0 [86.862893] kernel_init_freeable+0x3cd/0x680 [86.862908] kernel_init+0x1b/0x200 [86.862921] ret_from_fork+0x47/0x70 [86.862934] ret_from_fork_asm+0x1a/0x30 [86.862947] -> #1 (cpuhp_state_mutex){+.+.}-{3:3}: [86.862969] __mutex_lock+0xaa/0xed0 [86.862982] mutex_lock_nested+0x1b/0x30 [86.862995] __cpuhp_setup_state_cpuslocked+0x67/0x320 [86.863012] __cpuhp_setup_state+0xb0/0x220 [86.863026] page_alloc_init_cpuhp+0x2d/0x60 [86.863041] mm_core_init+0x22/0x2d0 [86.863054] start_kernel+0x576/0xbd0 [86.863068] x86_64_start_reservations+0x18/0x30 [86.863084] x86_64_start_kernel+0xbf/0x110 [86.863098] common_startup_64+0x13e/0x141 [86.863114] -> #0 (cpu_hotplug_lock){++++}-{0:0}: [86.863135] __lock_acquire+0x1635/0x2810 [86.863152] lock_acquire+0xc4/0x2f0 [86.863166] cpus_read_lock+0x41/0x100 [86.863180] stop_machine+0x1c/0x50 [86.863194] bxt_vtd_ggtt_insert_entries__BKL+0x3b/0x60 [i915] [86.863987] intel_ggtt_bind_vma+0x43/0x70 [i915] [86.864735] __vma_bind+0x55/0x70 [i915] [86.865510] fence_work+0x26/0xa0 [i915] [86.866248] fence_notify+0xa1/0x140 [i915] [86.866983] __i915_sw_fence_complete+0x8f/0x270 [i915] [86.867719] i915_sw_fence_commit+0x39/0x60 [i915] [86.868453] i915_vma_pin_ww+0x462/0x1360 [i915] [86.869228] i915_vma_pin.constprop.0+0x133/0x1d0 [i915] [86.870001] initial_plane_vma+0x307/0x840 [i915] [86.870774] intel_initial_plane_config+0x33f/0x670 [i915] [86.871546] intel_display_driver_probe_nogem+0x1c6/0x260 [i915] [86.872330] i915_driver_probe+0x7fa/0xe80 [i915] [86.873057] i915_pci_probe+0xe6/0x220 [i915] [86.873782] local_pci_probe+0x47/0xb0 [86.873802] pci_device_probe+0xf3/0x260 [86.873817] really_probe+0xf1/0x3c0 [86.873833] __driver_probe_device+0x8c/0x180 [86.873848] driver_probe_device+0x24/0xd0 [86.873862] __driver_attach+0x10f/0x220 [86.873876] bus_for_each_dev+0x7f/0xe0 [86.873892] driver_attach+0x1e/0x30 [86.873904] bus_add_driver+0x151/0x290 [86.873917] driver_register+0x5e/0x130 [86.873931] __pci_register_driver+0x7d/0x90 [86.873945] i915_pci_register_driver+0x23/0x30 [i915] [86.874678] i915_init+0x37/0x120 [i915] [86.875347] do_one_initcall+0x60/0x3f0 [86.875369] do_init_module+0x97/0x2a0 [86.875385] load_module+0x2c54/0x2d80 [86.875398] init_module_from_file+0x96/0xe0 [86.875413] idempotent_init_module+0x117/0x330 [86.875426] __x64_sys_finit_module+0x77/0x100 [86.875440] x64_sys_call+0x24de/0x2660 [86.875454] do_syscall_64+0x91/0xe90 [86.875470] entry_SYSCALL_64_after_hwframe+0x76/0x7e [86.875486] other info that might help us debug this: [86.875502] Chain exists of: cpu_hotplug_lock --> reservation_ww_class_acquire --> reservation_ww_class_mutex [86.875539] Possible unsafe locking scenario: [86.875552] CPU0 CPU1 [86.875563] ---- ---- [86.875573] lock(reservation_ww_class_mutex); [86.875588] lock(reservation_ww_class_acquire); [86.875606] lock(reservation_ww_class_mutex); [86.875624] rlock(cpu_hotplug_lock); [86.875637] *** DEADLOCK *** [86.875650] 3 locks held by i915_module_loa/1432: [86.875663] #0: ffff888101f5c1b0 (&dev->mutex){....}-{3:3}, at: __driver_attach+0x104/0x220 [86.875699] #1: ffffc90002e0b4a0 (reservation_ww_class_acquire){+.+.}-{0:0}, at: i915_vma_pin.constprop.0+0x39/0x1d0 [i915] [86.876512] #2: ffffc90002e0b4c8 (reservation_ww_class_mutex){+.+.}-{3:3}, at: i915_vma_pin.constprop.0+0x39/0x1d0 [i915] [86.877305] stack backtrace: [86.877326] CPU: 0 UID: 0 PID: 1432 Comm: i915_module_loa Tainted: G U 6.15.0-rc5-CI_DRM_16515-gca0305cadc2d+ #1 PREEMPT(voluntary) [86.877334] Tainted: [U]=USER [86.877336] Hardware name: /NUC5CPYB, BIOS PYBSWCEL.86A.0079.2020.0420.1316 04/20/2020 [86.877339] Call Trace: [86.877344] <TASK> [86.877353] dump_stack_lvl+0x91/0xf0 [86.877364] dump_stack+0x10/0x20 [86.877369] print_circular_bug+0x285/0x360 [86.877379] check_noncircular+0x135/0x150 [86.877390] __lock_acquire+0x1635/0x2810 [86.877403] lock_acquire+0xc4/0x2f0 [86.877408] ? stop_machine+0x1c/0x50 [86.877422] ? __pfx_bxt_vtd_ggtt_insert_entries__cb+0x10/0x10 [i915] [86.878173] cpus_read_lock+0x41/0x100 [86.878182] ? stop_machine+0x1c/0x50 [86.878191] ? __pfx_bxt_vtd_ggtt_insert_entries__cb+0x10/0x10 [i915] [86.878916] stop_machine+0x1c/0x50 [86.878927] bxt_vtd_ggtt_insert_entries__BKL+0x3b/0x60 [i915] [86.879652] intel_ggtt_bind_vma+0x43/0x70 [i915] [86.880375] __vma_bind+0x55/0x70 [i915] [86.881133] fence_work+0x26/0xa0 [i915] [86.881851] fence_notify+0xa1/0x140 [i915] [86.882566] __i915_sw_fence_complete+0x8f/0x270 [i915] [86.883286] i915_sw_fence_commit+0x39/0x60 [i915] [86.884003] i915_vma_pin_ww+0x462/0x1360 [i915] [86.884756] ? i915_vma_pin.constprop.0+0x6c/0x1d0 [i915] [86.885513] i915_vma_pin.constprop.0+0x133/0x1d0 [i915] [86.886281] initial_plane_vma+0x307/0x840 [i915] [86.887049] intel_initial_plane_config+0x33f/0x670 [i915] [86.887819] intel_display_driver_probe_nogem+0x1c6/0x260 [i915] [86.888587] i915_driver_probe+0x7fa/0xe80 [i915] [86.889293] ? mutex_unlock+0x12/0x20 [86.889301] ? drm_privacy_screen_get+0x171/0x190 [86.889308] ? acpi_dev_found+0x66/0x80 [86.889321] i915_pci_probe+0xe6/0x220 [i915] [86.890038] local_pci_probe+0x47/0xb0 [86.890049] pci_device_probe+0xf3/0x260 [86.890058] really_probe+0xf1/0x3c0 [86.890067] __driver_probe_device+0x8c/0x180 [86.890072] driver_probe_device+0x24/0xd0 [86.890078] __driver_attach+0x10f/0x220 [86.890083] ? __pfx___driver_attach+0x10/0x10 [86.890088] bus_for_each_dev+0x7f/0xe0 [86.890097] driver_attach+0x1e/0x30 [86.890101] bus_add_driver+0x151/0x290 [86.890107] driver_register+0x5e/0x130 [86.890113] __pci_register_driver+0x7d/0x90 [86.890119] i915_pci_register_driver+0x23/0x30 [i915] [86.890833] i915_init+0x37/0x120 [i915] [86.891482] ? __pfx_i915_init+0x10/0x10 [i915] [86.892135] do_one_initcall+0x60/0x3f0 [86.892145] ? __kmalloc_cache_noprof+0x33f/0x470 [86.892157] do_init_module+0x97/0x2a0 [86.892164] load_module+0x2c54/0x2d80 [86.892168] ? __kernel_read+0x15c/0x300 [86.892185] ? kernel_read_file+0x2b1/0x320 [86.892195] init_module_from_file+0x96/0xe0 [86.892199] ? init_module_from_file+0x96/0xe0 [86.892211] idempotent_init_module+0x117/0x330 [86.892224] __x64_sys_finit_module+0x77/0x100 [86.892230] x64_sys_call+0x24de/0x2660 [86.892236] do_syscall_64+0x91/0xe90 [86.892243] ? irqentry_exit+0x77/0xb0 [86.892249] ? sysvec_apic_timer_interrupt+0x57/0xc0 [86.892256] entry_SYSCALL_64_after_hwframe+0x76/0x7e [86.892261] RIP: 0033:0x7303e1b2725d [86.892271] Code: ff c3 66 2e 0f 1f 84 00 00 00 00 00 90 f3 0f 1e fa 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d 8b bb 0d 00 f7 d8 64 89 01 48 [86.892276] RSP: 002b:00007ffddd1fdb38 EFLAGS: 00000246 ORIG_RAX: 0000000000000139 [86.892281] RAX: ffffffffffffffda RBX: 00005d771d88fd90 RCX: 00007303e1b2725d [86.892285] RDX: 0000000000000000 RSI: 00005d771d893aa0 RDI: 000000000000000c [86.892287] RBP: 00007ffddd1fdbf0 R08: 0000000000000040 R09: 00007ffddd1fdb80 [86.892289] R10: 00007303e1c03b20 R11: 0000000000000246 R12: 00005d771d893aa0 [86.892292] R13: 0000000000000000 R14: 00005d771d88f0d0 R15: 00005d771d895710 [86.892304] </TASK>

Call asynchronous variant of dma_fence_work_commit() in that case.

v3: Provide more verbose in-line comment (Andi), - mention target environments in commit message.

Fixes: 7d1c2618eac59 ("drm/i915: Take reservation lock around i915_vma_pin.") Closes: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/14985 Cc: Andi Shyti andi.shyti@kernel.org Signed-off-by: Janusz Krzysztofik janusz.krzysztofik@linux.intel.com Reviewed-by: Sebastian Brzezinka sebastian.brzezinka@intel.com Reviewed-by: Krzysztof Karas krzysztof.karas@intel.com Acked-by: Andi Shyti andi.shyti@linux.intel.com Signed-off-by: Andi Shyti andi.shyti@linux.intel.com Link: https://lore.kernel.org/r/20251023082925.351307-6-janusz.krzysztofik@linux.i... (cherry picked from commit 648ef1324add1c2e2b6041cdf0b28d31fbca5f13) Signed-off-by: Rodrigo Vivi rodrigo.vivi@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpu/drm/i915/i915_vma.c | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c index 25e97031d76e4..30d5889fc809d 100644 --- a/drivers/gpu/drm/i915/i915_vma.c +++ b/drivers/gpu/drm/i915/i915_vma.c @@ -1595,8 +1595,20 @@ int i915_vma_pin_ww(struct i915_vma *vma, struct i915_gem_ww_ctx *ww, err_vma_res: i915_vma_resource_free(vma_res); err_fence: - if (work) - dma_fence_work_commit_imm(&work->base); + if (work) { + /* + * When pinning VMA to GGTT on CHV or BXT with VTD enabled, + * commit VMA binding asynchronously to avoid risk of lock + * inversion among reservation_ww locks held here and + * cpu_hotplug_lock acquired from stop_machine(), which we + * wrap around GGTT updates when running in those environments. + */ + if (i915_vma_is_ggtt(vma) && + intel_vm_no_concurrent_access_wa(vma->vm->i915)) + dma_fence_work_commit(&work->base); + else + dma_fence_work_commit_imm(&work->base); + } err_rpm: intel_runtime_pm_put(&vma->vm->i915->runtime_pm, wakeref);

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Luiz Augusto von Dentz luiz.von.dentz@intel.com

[ Upstream commit 41bf23338a501e745c398e0faee948dd05d0be98 ]

Contrary to what was stated on d36349ea73d8 ("Bluetooth: hci_conn: Fix running bis_cleanup for hci_conn->type PA_LINK") the PA_LINK does in fact needs to run bis_cleanup in order to terminate the PA Sync, since that is bond to the listening socket which is the entity that controls the lifetime of PA Sync, so if it is closed/released the PA Sync shall be terminated, terminating the PA Sync shall not result in the BIG Sync being terminated since once the later is established it doesn't depend on the former anymore.

If the use user wants to reconnect/rebind a number of BIS(s) it shall keep the socket open until it no longer needs the PA Sync, which means it retains full control of the lifetime of both PA and BIG Syncs.

Fixes: d36349ea73d8 ("Bluetooth: hci_conn: Fix running bis_cleanup for hci_conn->type PA_LINK") Fixes: a7bcffc673de ("Bluetooth: Add PA_LINK to distinguish BIG sync and PA sync connections") Signed-off-by: Luiz Augusto von Dentz luiz.von.dentz@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- net/bluetooth/hci_conn.c | 33 +++++++++++++++++++-------------- net/bluetooth/hci_event.c | 7 +------ net/bluetooth/hci_sync.c | 2 +- 3 files changed, 21 insertions(+), 21 deletions(-)

diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index c021c6cb3d9a5..5846b4bae77a3 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -769,21 +769,23 @@ static void find_bis(struct hci_conn *conn, void *data) d->count++; }

-static int hci_le_big_terminate(struct hci_dev *hdev, u8 big, struct hci_conn *conn) +static int hci_le_big_terminate(struct hci_dev *hdev, struct hci_conn *conn) { struct iso_list_data *d; int ret;

- bt_dev_dbg(hdev, "big 0x%2.2x sync_handle 0x%4.4x", big, conn->sync_handle); + bt_dev_dbg(hdev, "hcon %p big 0x%2.2x sync_handle 0x%4.4x", conn, + conn->iso_qos.bcast.big, conn->sync_handle);

d = kzalloc(sizeof(*d), GFP_KERNEL); if (!d) return -ENOMEM;

- d->big = big; + d->big = conn->iso_qos.bcast.big; d->sync_handle = conn->sync_handle;

- if (test_and_clear_bit(HCI_CONN_PA_SYNC, &conn->flags)) { + if (conn->type == PA_LINK && + test_and_clear_bit(HCI_CONN_PA_SYNC, &conn->flags)) { hci_conn_hash_list_flag(hdev, find_bis, PA_LINK, HCI_CONN_PA_SYNC, d);

@@ -801,6 +803,9 @@ static int hci_le_big_terminate(struct hci_dev *hdev, u8 big, struct hci_conn *c d->big_sync_term = true; }

+ if (!d->pa_sync_term && !d->big_sync_term) + return 0; + ret = hci_cmd_sync_queue(hdev, big_terminate_sync, d, terminate_big_destroy); if (ret) @@ -852,8 +857,7 @@ static void bis_cleanup(struct hci_conn *conn)

hci_le_terminate_big(hdev, conn); } else { - hci_le_big_terminate(hdev, conn->iso_qos.bcast.big, - conn); + hci_le_big_terminate(hdev, conn); } }

@@ -995,19 +999,20 @@ static struct hci_conn *__hci_conn_add(struct hci_dev *hdev, int type, bdaddr_t conn->mtu = hdev->le_mtu ? hdev->le_mtu : hdev->acl_mtu; break; case CIS_LINK: - case BIS_LINK: - case PA_LINK: /* conn->src should reflect the local identity address */ hci_copy_identity_address(hdev, &conn->src, &conn->src_type);

- /* set proper cleanup function */ - if (!bacmp(dst, BDADDR_ANY)) - conn->cleanup = bis_cleanup; - else if (conn->role == HCI_ROLE_MASTER) + if (conn->role == HCI_ROLE_MASTER) conn->cleanup = cis_cleanup;

- conn->mtu = hdev->iso_mtu ? hdev->iso_mtu : - hdev->le_mtu ? hdev->le_mtu : hdev->acl_mtu; + conn->mtu = hdev->iso_mtu; + break; + case PA_LINK: + case BIS_LINK: + /* conn->src should reflect the local identity address */ + hci_copy_identity_address(hdev, &conn->src, &conn->src_type); + conn->cleanup = bis_cleanup; + conn->mtu = hdev->iso_mtu; break; case SCO_LINK: if (lmp_esco_capable(hdev)) diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 7ee8bc7ac5a2a..0380d2f596c97 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -7011,14 +7011,9 @@ static void hci_le_big_sync_established_evt(struct hci_dev *hdev, void *data, continue; }

- if (ev->status != 0x42) { + if (ev->status != 0x42) /* Mark PA sync as established */ set_bit(HCI_CONN_PA_SYNC, &bis->flags); - /* Reset cleanup callback of PA Sync so it doesn't - * terminate the sync when deleting the connection. - */ - conn->cleanup = NULL; - }

bis->sync_handle = conn->sync_handle; bis->iso_qos.bcast.big = ev->handle; diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c index 73fc41b68b687..6e76798ec786b 100644 --- a/net/bluetooth/hci_sync.c +++ b/net/bluetooth/hci_sync.c @@ -6999,7 +6999,7 @@ static void create_pa_complete(struct hci_dev *hdev, void *data, int err)

hci_dev_lock(hdev);

- if (!hci_conn_valid(hdev, conn)) + if (hci_conn_valid(hdev, conn)) clear_bit(HCI_CONN_CREATE_PA_SYNC, &conn->flags);

if (!err)

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jonathan Kim jonathan.kim@amd.com

[ Upstream commit 079ae5118e1f0dcf5b1ab68ffdb5760b06ed79a2 ]

Suspend/resume all gangs should be done with the device lock is held.

Signed-off-by: Jonathan Kim jonathan.kim@amd.com Acked-by: Alex Deucher alexander.deucher@amd.com Reviewed-by: Harish Kasiviswanathan harish.kasiviswanathan@amd.com Signed-off-by: Alex Deucher alexander.deucher@amd.com Signed-off-by: Sasha Levin sashal@kernel.org --- .../drm/amd/amdkfd/kfd_device_queue_manager.c | 73 ++++++------------- 1 file changed, 21 insertions(+), 52 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c index 6c5c7c1bf5eda..6e7bc983fc0b6 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c @@ -1209,6 +1209,15 @@ static int evict_process_queues_cpsch(struct device_queue_manager *dqm, pr_debug_ratelimited("Evicting process pid %d queues\n", pdd->process->lead_thread->pid);

+ if (dqm->dev->kfd->shared_resources.enable_mes) { + pdd->last_evict_timestamp = get_jiffies_64(); + retval = suspend_all_queues_mes(dqm); + if (retval) { + dev_err(dev, "Suspending all queues failed"); + goto out; + } + } + /* Mark all queues as evicted. Deactivate all active queues on * the qpd. */ @@ -1221,23 +1230,27 @@ static int evict_process_queues_cpsch(struct device_queue_manager *dqm, decrement_queue_count(dqm, qpd, q);

if (dqm->dev->kfd->shared_resources.enable_mes) { - int err; - - err = remove_queue_mes(dqm, q, qpd); - if (err) { + retval = remove_queue_mes(dqm, q, qpd); + if (retval) { dev_err(dev, "Failed to evict queue %d\n", q->properties.queue_id); - retval = err; + goto out; } } } - pdd->last_evict_timestamp = get_jiffies_64(); - if (!dqm->dev->kfd->shared_resources.enable_mes) + + if (!dqm->dev->kfd->shared_resources.enable_mes) { + pdd->last_evict_timestamp = get_jiffies_64(); retval = execute_queues_cpsch(dqm, qpd->is_debug ? KFD_UNMAP_QUEUES_FILTER_ALL_QUEUES : KFD_UNMAP_QUEUES_FILTER_DYNAMIC_QUEUES, 0, USE_DEFAULT_GRACE_PERIOD); + } else { + retval = resume_all_queues_mes(dqm); + if (retval) + dev_err(dev, "Resuming all queues failed"); + }

out: dqm_unlock(dqm); @@ -3098,61 +3111,17 @@ int kfd_dqm_suspend_bad_queue_mes(struct kfd_node *knode, u32 pasid, u32 doorbel return ret; }

-static int kfd_dqm_evict_pasid_mes(struct device_queue_manager *dqm, - struct qcm_process_device *qpd) -{ - struct device *dev = dqm->dev->adev->dev; - int ret = 0; - - /* Check if process is already evicted */ - dqm_lock(dqm); - if (qpd->evicted) { - /* Increment the evicted count to make sure the - * process stays evicted before its terminated. - */ - qpd->evicted++; - dqm_unlock(dqm); - goto out; - } - dqm_unlock(dqm); - - ret = suspend_all_queues_mes(dqm); - if (ret) { - dev_err(dev, "Suspending all queues failed"); - goto out; - } - - ret = dqm->ops.evict_process_queues(dqm, qpd); - if (ret) { - dev_err(dev, "Evicting process queues failed"); - goto out; - } - - ret = resume_all_queues_mes(dqm); - if (ret) - dev_err(dev, "Resuming all queues failed"); - -out: - return ret; -} - int kfd_evict_process_device(struct kfd_process_device *pdd) { struct device_queue_manager *dqm; struct kfd_process *p; - int ret = 0;

p = pdd->process; dqm = pdd->dev->dqm;

WARN(debug_evictions, "Evicting pid %d", p->lead_thread->pid);

- if (dqm->dev->kfd->shared_resources.enable_mes) - ret = kfd_dqm_evict_pasid_mes(dqm, &pdd->qpd); - else - ret = dqm->ops.evict_process_queues(dqm, &pdd->qpd); - - return ret; + return dqm->ops.evict_process_queues(dqm, &pdd->qpd); }

int reserve_debug_trap_vmid(struct device_queue_manager *dqm,

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jesse.Zhang Jesse.Zhang@amd.com

[ Upstream commit 883f309add55060233bf11c1ea6947140372920f ]

Previously, APU platforms (and other scenarios with uninitialized VRAM managers) triggered a NULL pointer dereference in `ttm_resource_manager_usage()`. The root cause is not that the `struct ttm_resource_manager *man` pointer itself is NULL, but that `man->bdev` (the backing device pointer within the manager) remains uninitialized (NULL) on APUs—since APUs lack dedicated VRAM and do not fully set up VRAM manager structures. When `ttm_resource_manager_usage()` attempts to acquire `man->bdev->lru_lock`, it dereferences the NULL `man->bdev`, leading to a kernel OOPS.

1. **amdgpu_cs.c**: Extend the existing bandwidth control check in `amdgpu_cs_get_threshold_for_moves()` to include a check for `ttm_resource_manager_used()`. If the manager is not used (uninitialized `bdev`), return 0 for migration thresholds immediately—skipping VRAM-specific logic that would trigger the NULL dereference.

2. **amdgpu_kms.c**: Update the `AMDGPU_INFO_VRAM_USAGE` ioctl and memory info reporting to use a conditional: if the manager is used, return the real VRAM usage; otherwise, return 0. This avoids accessing `man->bdev` when it is NULL.

3. **amdgpu_virt.c**: Modify the vf2pf (virtual function to physical function) data write path. Use `ttm_resource_manager_used()` to check validity: if the manager is usable, calculate `fb_usage` from VRAM usage; otherwise, set `fb_usage` to 0 (APUs have no discrete framebuffer to report).

This approach is more robust than APU-specific checks because it: - Works for all scenarios where the VRAM manager is uninitialized (not just APUs), - Aligns with TTM's design by using its native helper function, - Preserves correct behavior for discrete GPUs (which have fully initialized `man->bdev` and pass the `ttm_resource_manager_used()` check).

v4: use ttm_resource_manager_used(&adev->mman.vram_mgr.manager) instead of checking the adev->gmc.is_app_apu flag (Christian)

Reviewed-by: Christian König christian.koenig@amd.com Suggested-by: Lijo Lazar lijo.lazar@amd.com Signed-off-by: Jesse Zhang Jesse.Zhang@amd.com Signed-off-by: Alex Deucher alexander.deucher@amd.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c | 2 +- drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c | 7 ++++--- drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c | 4 ++-- 3 files changed, 7 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c index 1ce1fd0c87a57..338fe62e864e9 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c @@ -714,7 +714,7 @@ static void amdgpu_cs_get_threshold_for_moves(struct amdgpu_device *adev, */ const s64 us_upper_bound = 200000;

- if (!adev->mm_stats.log2_max_MBps) { + if ((!adev->mm_stats.log2_max_MBps) || !ttm_resource_manager_used(&adev->mman.vram_mgr.manager)) { *max_bytes = 0; *max_vis_bytes = 0; return; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c index 8a76960803c65..8162f7f625a86 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c @@ -758,7 +758,8 @@ int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) ui64 = atomic64_read(&adev->num_vram_cpu_page_faults); return copy_to_user(out, &ui64, min(size, 8u)) ? -EFAULT : 0; case AMDGPU_INFO_VRAM_USAGE: - ui64 = ttm_resource_manager_usage(&adev->mman.vram_mgr.manager); + ui64 = ttm_resource_manager_used(&adev->mman.vram_mgr.manager) ? + ttm_resource_manager_usage(&adev->mman.vram_mgr.manager) : 0; return copy_to_user(out, &ui64, min(size, 8u)) ? -EFAULT : 0; case AMDGPU_INFO_VIS_VRAM_USAGE: ui64 = amdgpu_vram_mgr_vis_usage(&adev->mman.vram_mgr); @@ -804,8 +805,8 @@ int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) mem.vram.usable_heap_size = adev->gmc.real_vram_size - atomic64_read(&adev->vram_pin_size) - AMDGPU_VM_RESERVED_VRAM; - mem.vram.heap_usage = - ttm_resource_manager_usage(vram_man); + mem.vram.heap_usage = ttm_resource_manager_used(&adev->mman.vram_mgr.manager) ? + ttm_resource_manager_usage(vram_man) : 0; mem.vram.max_allocation = mem.vram.usable_heap_size * 3 / 4;

mem.cpu_accessible_vram.total_heap_size = diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c index 13f0cdeb59c46..e13bf2345ef5c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c @@ -598,8 +598,8 @@ static int amdgpu_virt_write_vf2pf_data(struct amdgpu_device *adev) vf2pf_info->driver_cert = 0; vf2pf_info->os_info.all = 0;

- vf2pf_info->fb_usage = - ttm_resource_manager_usage(&adev->mman.vram_mgr.manager) >> 20; + vf2pf_info->fb_usage = ttm_resource_manager_used(&adev->mman.vram_mgr.manager) ? + ttm_resource_manager_usage(&adev->mman.vram_mgr.manager) >> 20 : 0; vf2pf_info->fb_vis_usage = amdgpu_vram_mgr_vis_usage(&adev->mman.vram_mgr) >> 20; vf2pf_info->fb_size = adev->gmc.real_vram_size >> 20;

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Cristian Ciocaltea cristian.ciocaltea@collabora.com

[ Upstream commit ee70bacef1c6050e4836409927294d744dbcfa72 ]

The interrupt handler offloads the microphone detection logic to nau8821_jdet_work(), which implies a sleep operation. However, before being able to process any subsequent hotplug event, the interrupt handler needs to wait for any prior scheduled work to complete.

Move the sleep out of jdet_work by converting it to a delayed work. This eliminates the undesired blocking in the interrupt handler when attempting to cancel a recently scheduled work item and should help reducing transient input reports that might confuse user-space.

Signed-off-by: Cristian Ciocaltea cristian.ciocaltea@collabora.com Link: https://patch.msgid.link/20251003-nau8821-jdet-fixes-v1-5-f7b0e2543f09@colla... Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- sound/soc/codecs/nau8821.c | 22 ++++++++++++---------- sound/soc/codecs/nau8821.h | 2 +- 2 files changed, 13 insertions(+), 11 deletions(-)

diff --git a/sound/soc/codecs/nau8821.c b/sound/soc/codecs/nau8821.c index a8ff2ce70be9a..4fa9a785513e5 100644 --- a/sound/soc/codecs/nau8821.c +++ b/sound/soc/codecs/nau8821.c @@ -1104,16 +1104,12 @@ static void nau8821_eject_jack(struct nau8821 *nau8821) static void nau8821_jdet_work(struct work_struct *work) { struct nau8821 *nau8821 = - container_of(work, struct nau8821, jdet_work); + container_of(work, struct nau8821, jdet_work.work); struct snd_soc_dapm_context *dapm = nau8821->dapm; struct snd_soc_component *component = snd_soc_dapm_to_component(dapm); struct regmap *regmap = nau8821->regmap; int jack_status_reg, mic_detected, event = 0, event_mask = 0;

- snd_soc_component_force_enable_pin(component, "MICBIAS"); - snd_soc_dapm_sync(dapm); - msleep(20); - regmap_read(regmap, NAU8821_R58_I2C_DEVICE_ID, &jack_status_reg); mic_detected = !(jack_status_reg & NAU8821_KEYDET); if (mic_detected) { @@ -1146,6 +1142,7 @@ static void nau8821_jdet_work(struct work_struct *work) snd_soc_component_disable_pin(component, "MICBIAS"); snd_soc_dapm_sync(dapm); } + event_mask |= SND_JACK_HEADSET; snd_soc_jack_report(nau8821->jack, event, event_mask); } @@ -1194,6 +1191,7 @@ static irqreturn_t nau8821_interrupt(int irq, void *data) { struct nau8821 *nau8821 = (struct nau8821 *)data; struct regmap *regmap = nau8821->regmap; + struct snd_soc_component *component; int active_irq, event = 0, event_mask = 0;

if (regmap_read(regmap, NAU8821_R10_IRQ_STATUS, &active_irq)) { @@ -1205,7 +1203,7 @@ static irqreturn_t nau8821_interrupt(int irq, void *data)

if ((active_irq & NAU8821_JACK_EJECT_IRQ_MASK) == NAU8821_JACK_EJECT_DETECTED) { - cancel_work_sync(&nau8821->jdet_work); + cancel_delayed_work_sync(&nau8821->jdet_work); regmap_update_bits(regmap, NAU8821_R71_ANALOG_ADC_1, NAU8821_MICDET_MASK, NAU8821_MICDET_DIS); nau8821_eject_jack(nau8821); @@ -1219,12 +1217,15 @@ static irqreturn_t nau8821_interrupt(int irq, void *data) nau8821_irq_status_clear(regmap, NAU8821_KEY_RELEASE_IRQ); } else if ((active_irq & NAU8821_JACK_INSERT_IRQ_MASK) == NAU8821_JACK_INSERT_DETECTED) { - cancel_work_sync(&nau8821->jdet_work); + cancel_delayed_work_sync(&nau8821->jdet_work); regmap_update_bits(regmap, NAU8821_R71_ANALOG_ADC_1, NAU8821_MICDET_MASK, NAU8821_MICDET_EN); if (nau8821_is_jack_inserted(regmap)) { - /* detect microphone and jack type */ - schedule_work(&nau8821->jdet_work); + /* Detect microphone and jack type */ + component = snd_soc_dapm_to_component(nau8821->dapm); + snd_soc_component_force_enable_pin(component, "MICBIAS"); + snd_soc_dapm_sync(nau8821->dapm); + schedule_delayed_work(&nau8821->jdet_work, msecs_to_jiffies(20)); /* Turn off insertion interruption at manual mode */ nau8821_setup_inserted_irq(nau8821); } else { @@ -1661,7 +1662,8 @@ int nau8821_enable_jack_detect(struct snd_soc_component *component,

nau8821->jack = jack; /* Initiate jack detection work queue */ - INIT_WORK(&nau8821->jdet_work, nau8821_jdet_work); + INIT_DELAYED_WORK(&nau8821->jdet_work, nau8821_jdet_work); + ret = devm_request_threaded_irq(nau8821->dev, nau8821->irq, NULL, nau8821_interrupt, IRQF_TRIGGER_LOW | IRQF_ONESHOT, "nau8821", nau8821); diff --git a/sound/soc/codecs/nau8821.h b/sound/soc/codecs/nau8821.h index f0935ffafcbec..88602923780d8 100644 --- a/sound/soc/codecs/nau8821.h +++ b/sound/soc/codecs/nau8821.h @@ -561,7 +561,7 @@ struct nau8821 { struct regmap *regmap; struct snd_soc_dapm_context *dapm; struct snd_soc_jack *jack; - struct work_struct jdet_work; + struct delayed_work jdet_work; int irq; int clk_id; int micbias_voltage;

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Tristan Lobb tristan.lobb@it-lobb.de

[ Upstream commit 0be4253bf878d9aaa2b96031ac8683fceeb81480 ]

The Cooler Master Mice Dongle includes a vendor defined HID interface alongside its mouse interface. Not polling it will cause the mouse to stop responding to polls on any interface once woken up again after going into power saving mode.

Add the HID_QUIRK_ALWAYS_POLL quirk alongside the Cooler Master VID and the Dongle's PID.

Signed-off-by: Tristan Lobb tristan.lobb@it-lobb.de Signed-off-by: Jiri Kosina jkosina@suse.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/hid/hid-ids.h | 3 +++ drivers/hid/hid-quirks.c | 1 + 2 files changed, 4 insertions(+)

diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index 5721b8414bbdf..d05a62bbafffb 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -342,6 +342,9 @@ #define USB_DEVICE_ID_CODEMERCS_IOW_FIRST 0x1500 #define USB_DEVICE_ID_CODEMERCS_IOW_LAST 0x15ff

+#define USB_VENDOR_ID_COOLER_MASTER 0x2516 +#define USB_DEVICE_ID_COOLER_MASTER_MICE_DONGLE 0x01b7 + #define USB_VENDOR_ID_CORSAIR 0x1b1c #define USB_DEVICE_ID_CORSAIR_K90 0x1b02 #define USB_DEVICE_ID_CORSAIR_K70R 0x1b09 diff --git a/drivers/hid/hid-quirks.c b/drivers/hid/hid-quirks.c index ffd034566e2e1..d7105a8395982 100644 --- a/drivers/hid/hid-quirks.c +++ b/drivers/hid/hid-quirks.c @@ -57,6 +57,7 @@ static const struct hid_device_id hid_quirks[] = { { HID_USB_DEVICE(USB_VENDOR_ID_CH, USB_DEVICE_ID_CH_FLIGHT_SIM_YOKE), HID_QUIRK_NOGET }, { HID_USB_DEVICE(USB_VENDOR_ID_CH, USB_DEVICE_ID_CH_PRO_PEDALS), HID_QUIRK_NOGET }, { HID_USB_DEVICE(USB_VENDOR_ID_CH, USB_DEVICE_ID_CH_PRO_THROTTLE), HID_QUIRK_NOGET }, + { HID_USB_DEVICE(USB_VENDOR_ID_COOLER_MASTER, USB_DEVICE_ID_COOLER_MASTER_MICE_DONGLE), HID_QUIRK_ALWAYS_POLL }, { HID_USB_DEVICE(USB_VENDOR_ID_CORSAIR, USB_DEVICE_ID_CORSAIR_K65RGB), HID_QUIRK_NO_INIT_REPORTS }, { HID_USB_DEVICE(USB_VENDOR_ID_CORSAIR, USB_DEVICE_ID_CORSAIR_K65RGB_RAPIDFIRE), HID_QUIRK_NO_INIT_REPORTS | HID_QUIRK_ALWAYS_POLL }, { HID_USB_DEVICE(USB_VENDOR_ID_CORSAIR, USB_DEVICE_ID_CORSAIR_K70RGB), HID_QUIRK_NO_INIT_REPORTS },

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ranganath V N vnranganath.20@gmail.com

[ Upstream commit 62b656e43eaeae445a39cd8021a4f47065af4389 ]

In tcf_connmark_dump(), the variable 'opt' was partially initialized using a designatied initializer. While the padding bytes are reamined uninitialized. nla_put() copies the entire structure into a netlink message, these uninitialized bytes leaked to userspace.

Initialize the structure with memset before assigning its fields to ensure all members and padding are cleared prior to beign copied.

Reported-by: syzbot+0c85cae3350b7d486aee@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=0c85cae3350b7d486aee Tested-by: syzbot+0c85cae3350b7d486aee@syzkaller.appspotmail.com Fixes: 22a5dc0e5e3e ("net: sched: Introduce connmark action") Signed-off-by: Ranganath V N vnranganath.20@gmail.com Reviewed-by: Eric Dumazet edumazet@google.com Link: https://patch.msgid.link/20251109091336.9277-2-vnranganath.20@gmail.com Acked-by: Cong Wang xiyou.wangcong@gmail.com Signed-off-by: Paolo Abeni pabeni@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- net/sched/act_connmark.c | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c index 3e89927d71164..26ba8c2d20abf 100644 --- a/net/sched/act_connmark.c +++ b/net/sched/act_connmark.c @@ -195,13 +195,15 @@ static inline int tcf_connmark_dump(struct sk_buff *skb, struct tc_action *a, const struct tcf_connmark_info *ci = to_connmark(a); unsigned char *b = skb_tail_pointer(skb); const struct tcf_connmark_parms *parms; - struct tc_connmark opt = { - .index = ci->tcf_index, - .refcnt = refcount_read(&ci->tcf_refcnt) - ref, - .bindcnt = atomic_read(&ci->tcf_bindcnt) - bind, - }; + struct tc_connmark opt; struct tcf_t t;

+ memset(&opt, 0, sizeof(opt)); + + opt.index = ci->tcf_index; + opt.refcnt = refcount_read(&ci->tcf_refcnt) - ref; + opt.bindcnt = atomic_read(&ci->tcf_bindcnt) - bind; + rcu_read_lock(); parms = rcu_dereference(ci->parms);

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Joshua Watt jpewhacker@gmail.com

[ Upstream commit 9bb3baa9d1604cd20f49ae7dac9306b4037a0e7a ]

Since the last renewal time was initialized to 0 and jiffies start counting at -5 minutes, any clients connected in the first 5 minutes after a reboot would have their renewal timer set to a very long interval. If the connection was idle, this would result in the client state timing out on the server and the next call to the server would return NFS4ERR_BADSESSION.

Fix this by initializing the last renewal time to the current jiffies instead of 0.

Signed-off-by: Joshua Watt jpewhacker@gmail.com Signed-off-by: Anna Schumaker anna.schumaker@oracle.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/nfs/nfs4client.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c index 6fddf43d729c8..5998d6bd8a4f4 100644 --- a/fs/nfs/nfs4client.c +++ b/fs/nfs/nfs4client.c @@ -222,6 +222,7 @@ struct nfs_client *nfs4_alloc_client(const struct nfs_client_initdata *cl_init) clp->cl_state = 1 << NFS4CLNT_LEASE_EXPIRED; clp->cl_mvops = nfs_v4_minor_ops[cl_init->minorversion]; clp->cl_mig_gen = 1; + clp->cl_last_renewal = jiffies; #if IS_ENABLED(CONFIG_NFS_V4_1) init_waitqueue_head(&clp->cl_lock_waitq); #endif

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jedrzej Jagielski jedrzej.jagielski@intel.com

[ Upstream commit f7f97cbc03a470ce405d48dedb7f135713caa0fa ]

Update supported API version and provide handler for IXGBE_VF_GET_PF_LINK_STATE cmd. Simply put stored values of link speed and link_up from adapter context.

Reviewed-by: Przemek Kitszel przemyslaw.kitszel@intel.com Reviewed-by: Aleksandr Loktionov aleksandr.loktionov@intel.com Signed-off-by: Jedrzej Jagielski jedrzej.jagielski@intel.com Link: https://lore.kernel.org/stable/20250828095227.1857066-3-jedrzej.jagielski%40... Tested-by: Rafal Romanowski rafal.romanowski@intel.com Signed-off-by: Jacob Keller jacob.e.keller@intel.com Link: https://patch.msgid.link/20251009-jk-iwl-net-2025-10-01-v3-3-ef32a425b92a@in... Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.h | 5 +++ .../net/ethernet/intel/ixgbe/ixgbe_sriov.c | 42 +++++++++++++++++++ 2 files changed, 47 insertions(+)

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.h index 4af149b63a39f..f7256a339c99b 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.h @@ -50,6 +50,8 @@ enum ixgbe_pfvf_api_rev { ixgbe_mbox_api_12, /* API version 1.2, linux/freebsd VF driver */ ixgbe_mbox_api_13, /* API version 1.3, linux/freebsd VF driver */ ixgbe_mbox_api_14, /* API version 1.4, linux/freebsd VF driver */ + ixgbe_mbox_api_15, /* API version 1.5, linux/freebsd VF driver */ + ixgbe_mbox_api_16, /* API version 1.6, linux/freebsd VF driver */ /* This value should always be last */ ixgbe_mbox_api_unknown, /* indicates that API version is not known */ }; @@ -86,6 +88,9 @@ enum ixgbe_pfvf_api_rev {

#define IXGBE_VF_GET_LINK_STATE 0x10 /* get vf link state */

+/* mailbox API, version 1.6 VF requests */ +#define IXGBE_VF_GET_PF_LINK_STATE 0x11 /* request PF to send link info */ + /* length of permanent address message returned from PF */ #define IXGBE_VF_PERMADDR_MSG_LEN 4 /* word in permanent address message with the current multicast type */ diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c index 32ac1e020d915..b09271d61a4ef 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c @@ -510,6 +510,7 @@ static int ixgbe_set_vf_lpe(struct ixgbe_adapter *adapter, u32 max_frame, u32 vf case ixgbe_mbox_api_12: case ixgbe_mbox_api_13: case ixgbe_mbox_api_14: + case ixgbe_mbox_api_16: /* Version 1.1 supports jumbo frames on VFs if PF has * jumbo frames enabled which means legacy VFs are * disabled @@ -1046,6 +1047,7 @@ static int ixgbe_negotiate_vf_api(struct ixgbe_adapter *adapter, case ixgbe_mbox_api_12: case ixgbe_mbox_api_13: case ixgbe_mbox_api_14: + case ixgbe_mbox_api_16: adapter->vfinfo[vf].vf_api = api; return 0; default: @@ -1072,6 +1074,7 @@ static int ixgbe_get_vf_queues(struct ixgbe_adapter *adapter, case ixgbe_mbox_api_12: case ixgbe_mbox_api_13: case ixgbe_mbox_api_14: + case ixgbe_mbox_api_16: break; default: return -1; @@ -1112,6 +1115,7 @@ static int ixgbe_get_vf_reta(struct ixgbe_adapter *adapter, u32 *msgbuf, u32 vf)

/* verify the PF is supporting the correct API */ switch (adapter->vfinfo[vf].vf_api) { + case ixgbe_mbox_api_16: case ixgbe_mbox_api_14: case ixgbe_mbox_api_13: case ixgbe_mbox_api_12: @@ -1145,6 +1149,7 @@ static int ixgbe_get_vf_rss_key(struct ixgbe_adapter *adapter,

/* verify the PF is supporting the correct API */ switch (adapter->vfinfo[vf].vf_api) { + case ixgbe_mbox_api_16: case ixgbe_mbox_api_14: case ixgbe_mbox_api_13: case ixgbe_mbox_api_12: @@ -1174,6 +1179,7 @@ static int ixgbe_update_vf_xcast_mode(struct ixgbe_adapter *adapter, fallthrough; case ixgbe_mbox_api_13: case ixgbe_mbox_api_14: + case ixgbe_mbox_api_16: break; default: return -EOPNOTSUPP; @@ -1244,6 +1250,7 @@ static int ixgbe_get_vf_link_state(struct ixgbe_adapter *adapter, case ixgbe_mbox_api_12: case ixgbe_mbox_api_13: case ixgbe_mbox_api_14: + case ixgbe_mbox_api_16: break; default: return -EOPNOTSUPP; @@ -1254,6 +1261,38 @@ static int ixgbe_get_vf_link_state(struct ixgbe_adapter *adapter, return 0; }

+/** + * ixgbe_send_vf_link_status - send link status data to VF + * @adapter: pointer to adapter struct + * @msgbuf: pointer to message buffers + * @vf: VF identifier + * + * Reply for IXGBE_VF_GET_PF_LINK_STATE mbox command sending link status data. + * + * Return: 0 on success or -EOPNOTSUPP when operation is not supported. + */ +static int ixgbe_send_vf_link_status(struct ixgbe_adapter *adapter, + u32 *msgbuf, u32 vf) +{ + struct ixgbe_hw *hw = &adapter->hw; + + switch (adapter->vfinfo[vf].vf_api) { + case ixgbe_mbox_api_16: + if (hw->mac.type != ixgbe_mac_e610) + return -EOPNOTSUPP; + break; + default: + return -EOPNOTSUPP; + } + /* Simply provide stored values as watchdog & link status events take + * care of its freshness. + */ + msgbuf[1] = adapter->link_speed; + msgbuf[2] = adapter->link_up; + + return 0; +} + static int ixgbe_rcv_msg_from_vf(struct ixgbe_adapter *adapter, u32 vf) { u32 mbx_size = IXGBE_VFMAILBOX_SIZE; @@ -1328,6 +1367,9 @@ static int ixgbe_rcv_msg_from_vf(struct ixgbe_adapter *adapter, u32 vf) case IXGBE_VF_IPSEC_DEL: retval = ixgbe_ipsec_vf_del_sa(adapter, msgbuf, vf); break; + case IXGBE_VF_GET_PF_LINK_STATE: + retval = ixgbe_send_vf_link_status(adapter, msgbuf, vf); + break; default: e_err(drv, "Unhandled Msg %8.8x\n", msgbuf[0]); retval = -EIO;

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Cosmin Ratiu cratiu@nvidia.com

[ Upstream commit 917449e7c3cdc7a0dfe429de997e39098d9cdd20 ]

Also convert it to a simple define.

Signed-off-by: Cosmin Ratiu cratiu@nvidia.com Reviewed-by: Dragos Tatulea dtatulea@nvidia.com Signed-off-by: Tariq Toukan tariqt@nvidia.com Reviewed-by: Simon Horman horms@kernel.org Signed-off-by: Jakub Kicinski kuba@kernel.org Stable-dep-of: e5eba42f0134 ("mlx5: Fix default values in create CQ") Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/mellanox/mlx5/core/eq.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c index 1ab77159409d6..f3c714ebd9cb4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c @@ -32,9 +32,7 @@ enum { MLX5_EQ_STATE_ALWAYS_ARMED = 0xb, };

-enum { - MLX5_EQ_DOORBEL_OFFSET = 0x40, -}; +#define MLX5_EQ_DOORBELL_OFFSET 0x40

/* budget must be smaller than MLX5_NUM_SPARE_EQE to guarantee that we update * the ci before we polled all the entries in the EQ. MLX5_NUM_SPARE_EQE is @@ -322,7 +320,7 @@ create_map_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq, eq->eqn = MLX5_GET(create_eq_out, out, eq_number); eq->irqn = pci_irq_vector(dev->pdev, vecidx); eq->dev = dev; - eq->doorbell = priv->uar->map + MLX5_EQ_DOORBEL_OFFSET; + eq->doorbell = priv->uar->map + MLX5_EQ_DOORBELL_OFFSET;

err = mlx5_debug_eq_add(dev, eq); if (err)

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jaehun Gou p22gone@gmail.com

[ Upstream commit 82ebecdc74ff555daf70b811d854b1f32a296bea ]

We found an infinite loop bug in the exFAT file system that can lead to a Denial-of-Service (DoS) condition. When a dentry in an exFAT filesystem is malformed, the following system calls — SYS_openat, SYS_ftruncate, and SYS_pwrite64 — can cause the kernel to hang.

Root cause analysis shows that the size validation code in exfat_find() does not check whether dentry.stream.valid_size is negative. As a result, the system calls mentioned above can succeed and eventually trigger the DoS issue.

This patch adds a check for negative dentry.stream.valid_size to prevent this vulnerability.

Co-developed-by: Seunghun Han kkamagui@gmail.com Signed-off-by: Seunghun Han kkamagui@gmail.com Co-developed-by: Jihoon Kwon jimmyxyz010315@gmail.com Signed-off-by: Jihoon Kwon jimmyxyz010315@gmail.com Signed-off-by: Jaehun Gou p22gone@gmail.com Signed-off-by: Namjae Jeon linkinjeon@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- fs/exfat/namei.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/fs/exfat/namei.c b/fs/exfat/namei.c index f5f1c4e8a29fd..d8964d7368142 100644 --- a/fs/exfat/namei.c +++ b/fs/exfat/namei.c @@ -642,10 +642,14 @@ static int exfat_find(struct inode *dir, struct qstr *qname,

info->type = exfat_get_entry_type(ep); info->attr = le16_to_cpu(ep->dentry.file.attr); - info->size = le64_to_cpu(ep2->dentry.stream.valid_size); info->valid_size = le64_to_cpu(ep2->dentry.stream.valid_size); info->size = le64_to_cpu(ep2->dentry.stream.size);

+ if (info->valid_size < 0) { + exfat_fs_error(sb, "data valid size is invalid(%lld)", info->valid_size); + return -EIO; + } + if (unlikely(EXFAT_B_TO_CLU_ROUND_UP(info->size, sbi) > sbi->used_clusters)) { exfat_fs_error(sb, "data size is invalid(%lld)", info->size); return -EIO;

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Pavel Begunkov asml.silence@gmail.com

[ Upstream commit 437c23357d897f5b5b7d297c477da44b56654d46 ]

There might be many reasons why a user is resizing a ring, e.g. moving to huge pages or for some memory compaction using IORING_SETUP_NO_MMAP. Don't bypass resizing, the user will definitely be surprised seeing 0 while the rings weren't actually moved to a new place.

Signed-off-by: Pavel Begunkov asml.silence@gmail.com Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Sasha Levin sashal@kernel.org --- io_uring/register.c | 7 ------- 1 file changed, 7 deletions(-)

diff --git a/io_uring/register.c b/io_uring/register.c index b1772a470bf6e..dacbe8596b5c2 100644 --- a/io_uring/register.c +++ b/io_uring/register.c @@ -426,13 +426,6 @@ static int io_register_resize_rings(struct io_ring_ctx *ctx, void __user *arg) if (unlikely(ret)) return ret;

- /* nothing to do, but copy params back */ - if (p.sq_entries == ctx->sq_entries && p.cq_entries == ctx->cq_entries) { - if (copy_to_user(arg, &p, sizeof(p))) - return -EFAULT; - return 0; - } - size = rings_size(p.flags, p.sq_entries, p.cq_entries, &sq_array_offset); if (size == SIZE_MAX)

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Balasubramani Vivekanandan balasubramani.vivekanandan@intel.com

[ Upstream commit 95af8f4fdce8349a5fe75264007f1af2aa1082ea ]

Cancel and wait for any Dead CT worker to complete before continuing with device unbinding. Else the worker will end up using resources freed by the undind operation.

Cc: Zhanjun Dong zhanjun.dong@intel.com Fixes: d2c5a5a926f4 ("drm/xe/guc: Dead CT helper") Signed-off-by: Balasubramani Vivekanandan balasubramani.vivekanandan@intel.com Reviewed-by: Stuart Summers stuart.summers@intel.com Link: https://patch.msgid.link/20251103123144.3231829-6-balasubramani.vivekanandan... Signed-off-by: Lucas De Marchi lucas.demarchi@intel.com (cherry picked from commit 492671339114e376aaa38626d637a2751cdef263) Signed-off-by: Lucas De Marchi lucas.demarchi@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpu/drm/xe/xe_guc_ct.c | 3 +++ 1 file changed, 3 insertions(+)

diff --git a/drivers/gpu/drm/xe/xe_guc_ct.c b/drivers/gpu/drm/xe/xe_guc_ct.c index 22eff8476ad48..75ac0c424476e 100644 --- a/drivers/gpu/drm/xe/xe_guc_ct.c +++ b/drivers/gpu/drm/xe/xe_guc_ct.c @@ -200,6 +200,9 @@ static void guc_ct_fini(struct drm_device *drm, void *arg) { struct xe_guc_ct *ct = arg;

+#if IS_ENABLED(CONFIG_DRM_XE_DEBUG) + cancel_work_sync(&ct->dead.worker); +#endif ct_exit_safe_mode(ct); destroy_workqueue(ct->g2h_wq); xa_destroy(&ct->fence_lookup);

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Andrii Melnychenko a.melnychenko@vyos.io

[ Upstream commit 90918e3b6404c2a37837b8f11692471b4c512de2 ]

Sequence adjustment may be required for FTP traffic with PASV/EPSV modes. due to need to re-write packet payload (IP, port) on the ftp control connection. This can require changes to the TCP length and expected seq / ack_seq.

The easiest way to reproduce this issue is with PASV mode. Example ruleset: table inet ftp_nat { ct helper ftp_helper { type "ftp" protocol tcp l3proto inet }

chain prerouting { type filter hook prerouting priority 0; policy accept; tcp dport 21 ct state new ct helper set "ftp_helper" } } table ip nat { chain prerouting { type nat hook prerouting priority -100; policy accept; tcp dport 21 dnat ip prefix to ip daddr map { 192.168.100.1 : 192.168.13.2/32 } }

chain postrouting { type nat hook postrouting priority 100 ; policy accept; tcp sport 21 snat ip prefix to ip saddr map { 192.168.13.2 : 192.168.100.1/32 } } }

Note that the ftp helper gets assigned *after* the dnat setup.

The inverse (nat after helper assign) is handled by an existing check in nf_nat_setup_info() and will not show the problem.

Topoloy:

+-------------------+ +----------------------------------+ | FTP: 192.168.13.2 | <-> | NAT: 192.168.13.3, 192.168.100.1 | +-------------------+ +----------------------------------+ | +-----------------------+ | Client: 192.168.100.2 | +-----------------------+

ftp nat changes do not work as expected in this case: Connected to 192.168.100.1. [..] ftp> epsv EPSV/EPRT on IPv4 off. ftp> ls 227 Entering passive mode (192,168,100,1,209,129). 421 Service not available, remote server has closed connection.

Kernel logs: Missing nfct_seqadj_ext_add() setup call WARNING: CPU: 1 PID: 0 at net/netfilter/nf_conntrack_seqadj.c:41 [..] __nf_nat_mangle_tcp_packet+0x100/0x160 [nf_nat] nf_nat_ftp+0x142/0x280 [nf_nat_ftp] help+0x4d1/0x880 [nf_conntrack_ftp] nf_confirm+0x122/0x2e0 [nf_conntrack] nf_hook_slow+0x3c/0xb0 ..

Fix this by adding the required extension when a conntrack helper is assigned to a connection that has a nat binding.

Fixes: 1a64edf54f55 ("netfilter: nft_ct: add helper set support") Signed-off-by: Andrii Melnychenko a.melnychenko@vyos.io Signed-off-by: Florian Westphal fw@strlen.de Signed-off-by: Sasha Levin sashal@kernel.org --- net/netfilter/nft_ct.c | 5 +++++ 1 file changed, 5 insertions(+)

diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c index d526e69a2a2b8..f358cdc5e6926 100644 --- a/net/netfilter/nft_ct.c +++ b/net/netfilter/nft_ct.c @@ -22,6 +22,7 @@ #include <net/netfilter/nf_conntrack_timeout.h> #include <net/netfilter/nf_conntrack_l4proto.h> #include <net/netfilter/nf_conntrack_expect.h> +#include <net/netfilter/nf_conntrack_seqadj.h>

struct nft_ct_helper_obj { struct nf_conntrack_helper *helper4; @@ -1173,6 +1174,10 @@ static void nft_ct_helper_obj_eval(struct nft_object *obj, if (help) { rcu_assign_pointer(help->helper, to_assign); set_bit(IPS_HELPER_BIT, &ct->status); + + if ((ct->status & IPS_NAT_MASK) && !nfct_seqadj(ct)) + if (!nfct_seqadj_ext_add(ct)) + regs->verdict.code = NF_DROP; } }

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Caleb Sander Mateos csander@purestorage.com

[ Upstream commit 2d0e88f3fd1dcb37072d499c36162baf5b009d41 ]

io_buffer_register_bvec() currently uses blk_rq_nr_phys_segments() as the number of bvecs in the request. However, bvecs may be split into multiple segments depending on the queue limits. Thus, the number of segments may overestimate the number of bvecs. For ublk devices, the only current users of io_buffer_register_bvec(), virt_boundary_mask, seg_boundary_mask, max_segments, and max_segment_size can all be set arbitrarily by the ublk server process. Set imu->nr_bvecs based on the number of bvecs the rq_for_each_bvec() loop actually yields. However, continue using blk_rq_nr_phys_segments() as an upper bound on the number of bvecs when allocating imu to avoid needing to iterate the bvecs a second time.

Link: https://lore.kernel.org/io-uring/20251111191530.1268875-1-csander@purestorag... Signed-off-by: Caleb Sander Mateos csander@purestorage.com Fixes: 27cb27b6d5ea ("io_uring: add support for kernel registered bvecs") Reviewed-by: Ming Lei ming.lei@redhat.com Reviewed-by: Chaitanya Kulkarni kch@nvidia.com Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Sasha Levin sashal@kernel.org --- io_uring/rsrc.c | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-)

diff --git a/io_uring/rsrc.c b/io_uring/rsrc.c index 5961f21dd65d1..b0852674730c5 100644 --- a/io_uring/rsrc.c +++ b/io_uring/rsrc.c @@ -942,8 +942,8 @@ int io_buffer_register_bvec(struct io_uring_cmd *cmd, struct request *rq, struct req_iterator rq_iter; struct io_mapped_ubuf *imu; struct io_rsrc_node *node; - struct bio_vec bv, *bvec; - u16 nr_bvecs; + struct bio_vec bv; + unsigned int nr_bvecs = 0; int ret = 0;

io_ring_submit_lock(ctx, issue_flags); @@ -964,8 +964,11 @@ int io_buffer_register_bvec(struct io_uring_cmd *cmd, struct request *rq, goto unlock; }

- nr_bvecs = blk_rq_nr_phys_segments(rq); - imu = io_alloc_imu(ctx, nr_bvecs); + /* + * blk_rq_nr_phys_segments() may overestimate the number of bvecs + * but avoids needing to iterate over the bvecs + */ + imu = io_alloc_imu(ctx, blk_rq_nr_phys_segments(rq)); if (!imu) { kfree(node); ret = -ENOMEM; @@ -976,16 +979,15 @@ int io_buffer_register_bvec(struct io_uring_cmd *cmd, struct request *rq, imu->len = blk_rq_bytes(rq); imu->acct_pages = 0; imu->folio_shift = PAGE_SHIFT; - imu->nr_bvecs = nr_bvecs; refcount_set(&imu->refs, 1); imu->release = release; imu->priv = rq; imu->is_kbuf = true; imu->dir = 1 << rq_data_dir(rq);

- bvec = imu->bvec; rq_for_each_bvec(bv, rq, rq_iter) - *bvec++ = bv; + imu->bvec[nr_bvecs++] = bv; + imu->nr_bvecs = nr_bvecs;

node->buf = imu; data->nodes[index] = node;

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Tejas Upadhyay tejas.upadhyay@intel.com

[ Upstream commit 9cd27eec872f0b95dcdd811edc39d2d32e4158c8 ]

The xe_device_shutdown() function was needing a few declarations that were only required under a specific condition. This change moves those declarations to be within that conditional branch to avoid unnecessary declarations.

Reviewed-by: Nitin Gote nitin.r.gote@intel.com Link: https://patchwork.freedesktop.org/patch/msgid/20251007100208.1407021-1-tejas... Signed-off-by: Tejas Upadhyay tejas.upadhyay@intel.com (cherry picked from commit 15b3036045188f4da4ca62b2ed01b0f160252e9b) Signed-off-by: Lucas De Marchi lucas.demarchi@intel.com Stable-dep-of: b11a020d914c ("drm/xe: Do clean shutdown also when using flr") Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpu/drm/xe/xe_device.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c index d399c2628fa33..528e818edbd7f 100644 --- a/drivers/gpu/drm/xe/xe_device.c +++ b/drivers/gpu/drm/xe/xe_device.c @@ -962,12 +962,12 @@ void xe_device_remove(struct xe_device *xe)

void xe_device_shutdown(struct xe_device *xe) { - struct xe_gt *gt; - u8 id; - drm_dbg(&xe->drm, "Shutting down device\n");

if (xe_driver_flr_disabled(xe)) { + struct xe_gt *gt; + u8 id; + xe_display_pm_shutdown(xe);

xe_irq_suspend(xe);

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jouni Högander jouni.hogander@intel.com

[ Upstream commit b11a020d914c3b7628f56a9ea476a5b03679489b ]

Currently Xe driver is triggering flr without any clean-up on shutdown. This is causing random warnings from pending related works as the underlying hardware is reset in the middle of their execution.

Fix this by performing clean shutdown also when using flr.

Fixes: 501d799a47e2 ("drm/xe: Wire up device shutdown handler") Cc: Maarten Lankhorst maarten.lankhorst@linux.intel.com Signed-off-by: Jouni Högander jouni.hogander@intel.com Reviewed-by: Maarten Lankhorst dev@lankhorst.se Link: https://patch.msgid.link/20251031122312.1836534-1-jouni.hogander@intel.com Signed-off-by: Maarten Lankhorst dev@lankhorst.se (cherry picked from commit a4ff26b7c8ef38e4dd34f77cbcd73576fdde6dd4) Signed-off-by: Lucas De Marchi lucas.demarchi@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpu/drm/xe/xe_device.c | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c index 528e818edbd7f..107c1f48e87fc 100644 --- a/drivers/gpu/drm/xe/xe_device.c +++ b/drivers/gpu/drm/xe/xe_device.c @@ -962,21 +962,21 @@ void xe_device_remove(struct xe_device *xe)

void xe_device_shutdown(struct xe_device *xe) { + struct xe_gt *gt; + u8 id; + drm_dbg(&xe->drm, "Shutting down device\n");

- if (xe_driver_flr_disabled(xe)) { - struct xe_gt *gt; - u8 id; + xe_display_pm_shutdown(xe);

- xe_display_pm_shutdown(xe); + xe_irq_suspend(xe);

- xe_irq_suspend(xe); + for_each_gt(gt, xe, id) + xe_gt_shutdown(gt);

- for_each_gt(gt, xe, id) - xe_gt_shutdown(gt); + xe_display_pm_shutdown_late(xe);

- xe_display_pm_shutdown_late(xe); - } else { + if (!xe_driver_flr_disabled(xe)) { /* BOOM! */ __xe_driver_flr(xe); }

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Trond Myklebust trond.myklebust@hammerspace.com

[ Upstream commit 8ab523ce78d4ca13add6b4ecbacff0f84c274603 ]

The default setting for the transport security policy must be RPC_XPRTSEC_NONE, when using a TCP or RDMA connection without TLS. Conversely, when using TLS, the security policy needs to be set.

Fixes: 6c0a8c5fcf71 ("NFS: Have struct nfs_client carry a TLS policy field") Signed-off-by: Trond Myklebust trond.myklebust@hammerspace.com Reviewed-by: Chuck Lever chuck.lever@oracle.com Signed-off-by: Anna Schumaker anna.schumaker@oracle.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/nfs/nfs3client.c | 14 ++++++++++++-- fs/nfs/nfs4client.c | 14 ++++++++++++-- 2 files changed, 24 insertions(+), 4 deletions(-)

diff --git a/fs/nfs/nfs3client.c b/fs/nfs/nfs3client.c index 0d7310c1ee0c0..5d97c1d38bb62 100644 --- a/fs/nfs/nfs3client.c +++ b/fs/nfs/nfs3client.c @@ -2,6 +2,7 @@ #include <linux/nfs_fs.h> #include <linux/nfs_mount.h> #include <linux/sunrpc/addr.h> +#include <net/handshake.h> #include "internal.h" #include "nfs3_fs.h" #include "netns.h" @@ -98,7 +99,11 @@ struct nfs_client *nfs3_set_ds_client(struct nfs_server *mds_srv, .net = mds_clp->cl_net, .timeparms = &ds_timeout, .cred = mds_srv->cred, - .xprtsec = mds_clp->cl_xprtsec, + .xprtsec = { + .policy = RPC_XPRTSEC_NONE, + .cert_serial = TLS_NO_CERT, + .privkey_serial = TLS_NO_PRIVKEY, + }, .connect_timeout = connect_timeout, .reconnect_timeout = connect_timeout, }; @@ -111,9 +116,14 @@ struct nfs_client *nfs3_set_ds_client(struct nfs_server *mds_srv, cl_init.hostname = buf;

switch (ds_proto) { + case XPRT_TRANSPORT_TCP_TLS: + if (mds_clp->cl_xprtsec.policy != RPC_XPRTSEC_NONE) + cl_init.xprtsec = mds_clp->cl_xprtsec; + else + ds_proto = XPRT_TRANSPORT_TCP; + fallthrough; case XPRT_TRANSPORT_RDMA: case XPRT_TRANSPORT_TCP: - case XPRT_TRANSPORT_TCP_TLS: if (mds_clp->cl_nconnect > 1) cl_init.nconnect = mds_clp->cl_nconnect; } diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c index 5998d6bd8a4f4..3a4baed993c96 100644 --- a/fs/nfs/nfs4client.c +++ b/fs/nfs/nfs4client.c @@ -11,6 +11,7 @@ #include <linux/sunrpc/xprt.h> #include <linux/sunrpc/bc_xprt.h> #include <linux/sunrpc/rpc_pipe_fs.h> +#include <net/handshake.h> #include "internal.h" #include "callback.h" #include "delegation.h" @@ -983,7 +984,11 @@ struct nfs_client *nfs4_set_ds_client(struct nfs_server *mds_srv, .net = mds_clp->cl_net, .timeparms = &ds_timeout, .cred = mds_srv->cred, - .xprtsec = mds_srv->nfs_client->cl_xprtsec, + .xprtsec = { + .policy = RPC_XPRTSEC_NONE, + .cert_serial = TLS_NO_CERT, + .privkey_serial = TLS_NO_PRIVKEY, + }, }; char buf[INET6_ADDRSTRLEN + 1];

@@ -992,9 +997,14 @@ struct nfs_client *nfs4_set_ds_client(struct nfs_server *mds_srv, cl_init.hostname = buf;

switch (ds_proto) { + case XPRT_TRANSPORT_TCP_TLS: + if (mds_srv->nfs_client->cl_xprtsec.policy != RPC_XPRTSEC_NONE) + cl_init.xprtsec = mds_srv->nfs_client->cl_xprtsec; + else + ds_proto = XPRT_TRANSPORT_TCP; + fallthrough; case XPRT_TRANSPORT_RDMA: case XPRT_TRANSPORT_TCP: - case XPRT_TRANSPORT_TCP_TLS: if (mds_clp->cl_nconnect > 1) { cl_init.nconnect = mds_clp->cl_nconnect; cl_init.max_connect = NFS_MAX_TRANSPORTS;

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Dave Jiang dave.jiang@intel.com

[ Upstream commit 214291cbaaceeb28debd773336642b1fca393ae0 ]

The following lockdep splat was observed while kernel auto-online a CXL memory region:

====================================================== WARNING: possible circular locking dependency detected 6.17.0djtest+ #53 Tainted: G W ------------------------------------------------------ systemd-udevd/3334 is trying to acquire lock: ffffffff90346188 (hmem_resource_lock){+.+.}-{4:4}, at: hmem_register_resource+0x31/0x50

but task is already holding lock: ffffffff90338890 ((node_chain).rwsem){++++}-{4:4}, at: blocking_notifier_call_chain+0x2e/0x70

which lock already depends on the new lock. [..] Chain exists of: hmem_resource_lock --> mem_hotplug_lock --> (node_chain).rwsem

Possible unsafe locking scenario:

CPU0 CPU1 ---- ---- rlock((node_chain).rwsem); lock(mem_hotplug_lock); lock((node_chain).rwsem); lock(hmem_resource_lock);

The lock ordering can cause potential deadlock. There are instances where hmem_resource_lock is taken after (node_chain).rwsem, and vice versa.

Split out the target update section of hmat_register_target() so that hmat_callback() only envokes that section instead of attempt to register hmem devices that it does not need to.

[ dj: Fix up comment to be closer to 80cols. (Jonathan) ]

Fixes: cf8741ac57ed ("ACPI: NUMA: HMAT: Register "soft reserved" memory as an "hmem" device") Reviewed-by: Jonathan Cameron jonathan.cameron@huawei.com Tested-by: Smita Koralahalli Smita.KoralahalliChannabasappa@amd.com Reviewed-by: Smita Koralahalli Smita.KoralahalliChannabasappa@amd.com Reviewed-by: Dan Williams dan.j.williams@intel.com Link: https://patch.msgid.link/20251105235115.85062-3-dave.jiang@intel.com Signed-off-by: Dave Jiang dave.jiang@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/acpi/numa/hmat.c | 46 ++++++++++++++++++++++------------------ 1 file changed, 25 insertions(+), 21 deletions(-)

diff --git a/drivers/acpi/numa/hmat.c b/drivers/acpi/numa/hmat.c index 4958301f54179..9085375830605 100644 --- a/drivers/acpi/numa/hmat.c +++ b/drivers/acpi/numa/hmat.c @@ -908,10 +908,32 @@ static void hmat_register_target_devices(struct memory_target *target) } }

-static void hmat_register_target(struct memory_target *target) +static void hmat_hotplug_target(struct memory_target *target) { int nid = pxm_to_node(target->memory_pxm);

+ /* + * Skip offline nodes. This can happen when memory marked EFI_MEMORY_SP, + * "specific purpose", is applied to all the memory in a proximity + * domain leading to * the node being marked offline / unplugged, or if + * memory-only "hotplug" node is offline. + */ + if (nid == NUMA_NO_NODE || !node_online(nid)) + return; + + guard(mutex)(&target_lock); + if (target->registered) + return; + + hmat_register_target_initiators(target); + hmat_register_target_cache(target); + hmat_register_target_perf(target, ACCESS_COORDINATE_LOCAL); + hmat_register_target_perf(target, ACCESS_COORDINATE_CPU); + target->registered = true; +} + +static void hmat_register_target(struct memory_target *target) +{ /* * Devices may belong to either an offline or online * node, so unconditionally add them. @@ -929,25 +951,7 @@ static void hmat_register_target(struct memory_target *target) } mutex_unlock(&target_lock);

- /* - * Skip offline nodes. This can happen when memory - * marked EFI_MEMORY_SP, "specific purpose", is applied - * to all the memory in a proximity domain leading to - * the node being marked offline / unplugged, or if - * memory-only "hotplug" node is offline. - */ - if (nid == NUMA_NO_NODE || !node_online(nid)) - return; - - mutex_lock(&target_lock); - if (!target->registered) { - hmat_register_target_initiators(target); - hmat_register_target_cache(target); - hmat_register_target_perf(target, ACCESS_COORDINATE_LOCAL); - hmat_register_target_perf(target, ACCESS_COORDINATE_CPU); - target->registered = true; - } - mutex_unlock(&target_lock); + hmat_hotplug_target(target); }

static void hmat_register_targets(void) @@ -973,7 +977,7 @@ static int hmat_callback(struct notifier_block *self, if (!target) return NOTIFY_OK;

- hmat_register_target(target); + hmat_hotplug_target(target); return NOTIFY_OK; }

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Timur Kristóf timur.kristof@gmail.com

[ Upstream commit b515dcb0dc4e85d8254f5459cfb32fce88dacbfb ]

This commit adds the pixel_clock field to the display config struct so that power management (DPM) can use it.

We currently don't have a proper bandwidth calculation on old GPUs with DCE 6-10 because dce_calcs only supports DCE 11+. So the power management (DPM) on these GPUs may need to make ad-hoc decisions for display based on the pixel clock.

Also rename sym_clock to pixel_clock in dm_pp_single_disp_config to avoid confusion with other code where the sym_clock refers to the DisplayPort symbol clock.

Signed-off-by: Timur Kristóf timur.kristof@gmail.com Signed-off-by: Alex Deucher alexander.deucher@amd.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c | 1 + drivers/gpu/drm/amd/display/dc/clk_mgr/dce110/dce110_clk_mgr.c | 2 +- drivers/gpu/drm/amd/display/dc/dm_services_types.h | 2 +- drivers/gpu/drm/amd/include/dm_pp_interface.h | 1 + 4 files changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c index 848c5b4bb301a..016230896d0e1 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c @@ -97,6 +97,7 @@ bool dm_pp_apply_display_requirements( const struct dm_pp_single_disp_config *dc_cfg = &pp_display_cfg->disp_configs[i]; adev->pm.pm_display_cfg.displays[i].controller_id = dc_cfg->pipe_idx + 1; + adev->pm.pm_display_cfg.displays[i].pixel_clock = dc_cfg->pixel_clock; }

amdgpu_dpm_display_configuration_change(adev, &adev->pm.pm_display_cfg); diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dce110/dce110_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dce110/dce110_clk_mgr.c index 13cf415e38e50..d50b9440210e4 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dce110/dce110_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dce110/dce110_clk_mgr.c @@ -164,7 +164,7 @@ void dce110_fill_display_configs( stream->link->cur_link_settings.link_rate; cfg->link_settings.link_spread = stream->link->cur_link_settings.link_spread; - cfg->sym_clock = stream->phy_pix_clk; + cfg->pixel_clock = stream->phy_pix_clk; /* Round v_refresh*/ cfg->v_refresh = stream->timing.pix_clk_100hz * 100; cfg->v_refresh /= stream->timing.h_total; diff --git a/drivers/gpu/drm/amd/display/dc/dm_services_types.h b/drivers/gpu/drm/amd/display/dc/dm_services_types.h index bf63da266a18c..3b093b8699abd 100644 --- a/drivers/gpu/drm/amd/display/dc/dm_services_types.h +++ b/drivers/gpu/drm/amd/display/dc/dm_services_types.h @@ -127,7 +127,7 @@ struct dm_pp_single_disp_config { uint32_t src_height; uint32_t src_width; uint32_t v_refresh; - uint32_t sym_clock; /* HDMI only */ + uint32_t pixel_clock; /* Pixel clock in KHz (for HDMI only: normalized) */ struct dc_link_settings link_settings; /* DP only */ };

diff --git a/drivers/gpu/drm/amd/include/dm_pp_interface.h b/drivers/gpu/drm/amd/include/dm_pp_interface.h index acd1cef61b7c5..349544504c93c 100644 --- a/drivers/gpu/drm/amd/include/dm_pp_interface.h +++ b/drivers/gpu/drm/amd/include/dm_pp_interface.h @@ -65,6 +65,7 @@ struct single_display_configuration { uint32_t view_resolution_cy; enum amd_pp_display_config_type displayconfigtype; uint32_t vertical_refresh; /* for active display */ + uint32_t pixel_clock; /* Pixel clock in KHz (for HDMI only: normalized) */ };

#define MAX_NUM_DISPLAY 32

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Timur Kristóf timur.kristof@gmail.com

[ Upstream commit 7495962cbceb967e095233a5673ea71f3bcdee7e ]

It already didn't work on DCE 8, so there is no reason to assume it would on DCE 6.

Signed-off-by: Timur Kristóf timur.kristof@gmail.com Reviewed-by: Rodrigo Siqueira siqueira@igalia.com Reviewed-by: Alex Deucher alexander.deucher@amd.com Reviewed-by: Alex Hung alex.hung@amd.com Signed-off-by: Alex Deucher alexander.deucher@amd.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c index 32fd6bdc18d73..537f538114607 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c @@ -1923,10 +1923,8 @@ void dce110_enable_accelerated_mode(struct dc *dc, struct dc_state *context)

get_edp_streams(context, edp_streams, &edp_stream_num);

- // Check fastboot support, disable on DCE8 because of blank screens - if (edp_num && edp_stream_num && dc->ctx->dce_version != DCE_VERSION_8_0 && - dc->ctx->dce_version != DCE_VERSION_8_1 && - dc->ctx->dce_version != DCE_VERSION_8_3) { + /* Check fastboot support, disable on DCE 6-8 because of blank screens */ + if (edp_num && edp_stream_num && dc->ctx->dce_version < DCE_VERSION_10_0) { for (i = 0; i < edp_num; i++) { edp_link = edp_links[i]; if (edp_link != edp_streams[0]->link)

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Arnaldo Carvalho de Melo acme@kernel.org

[ Upstream commit a09e5967ad6819379fd31894634d7aed29c18409 ]

This is one more remnant of the BUILD_NONDISTRO series to make building with binutils-devel opt-in due to license incompatibility.

In this case just the references at link time were still in place, which make building the test-all.bin file fail, which wasn't detected before probably because the last test was done with binutils-devel available, doh.

Now:

$ rpm -q binutils-devel package binutils-devel is not installed $ file /tmp/build/perf-tools/feature/test-all.bin /tmp/build/perf-tools/feature/test-all.bin: ELF 64-bit LSB executable, x86-64, version 1 (SYSV), dynamically linked, interpreter /lib64/ld-linux-x86-64.so.2, BuildID[sha1]=4b5388a346b51f1b993f0b0dbd49f4570769b03c, for GNU/Linux 3.2.0, not stripped $

Fixes: 970ae86307718c34 ("perf build: The bfd features are opt-in, stop testing for them by default") Reviewed-by: Ian Rogers irogers@google.com Cc: Adrian Hunter adrian.hunter@intel.com Cc: James Clark james.clark@linaro.org Cc: Jiri Olsa jolsa@kernel.org Cc: Namhyung Kim namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo acme@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- tools/build/feature/Makefile | 4 ++-- tools/perf/Makefile.config | 5 ++--- 2 files changed, 4 insertions(+), 5 deletions(-)

diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile index bd615a708a0aa..049d5d2b36468 100644 --- a/tools/build/feature/Makefile +++ b/tools/build/feature/Makefile @@ -110,7 +110,7 @@ all: $(FILES) __BUILD = $(CC) $(CFLAGS) -MD -Wall -Werror -o $@ $(patsubst %.bin,%.c,$(@F)) $(LDFLAGS) BUILD = $(__BUILD) > $(@:.bin=.make.output) 2>&1 BUILD_BFD = $(BUILD) -DPACKAGE='"perf"' -lbfd -ldl - BUILD_ALL = $(BUILD) -fstack-protector-all -O2 -D_FORTIFY_SOURCE=2 -ldw -lelf -lnuma -lelf -lslang $(FLAGS_PERL_EMBED) $(FLAGS_PYTHON_EMBED) -DPACKAGE='"perf"' -lbfd -ldl -lz -llzma -lzstd + BUILD_ALL = $(BUILD) -fstack-protector-all -O2 -D_FORTIFY_SOURCE=2 -ldw -lelf -lnuma -lelf -lslang $(FLAGS_PERL_EMBED) $(FLAGS_PYTHON_EMBED) -ldl -lz -llzma -lzstd

__BUILDXX = $(CXX) $(CXXFLAGS) -MD -Wall -Werror -o $@ $(patsubst %.bin,%.cpp,$(@F)) $(LDFLAGS) BUILDXX = $(__BUILDXX) > $(@:.bin=.make.output) 2>&1 @@ -118,7 +118,7 @@ __BUILDXX = $(CXX) $(CXXFLAGS) -MD -Wall -Werror -o $@ $(patsubst %.bin,%.cpp,$( ###############################

$(OUTPUT)test-all.bin: - $(BUILD_ALL) || $(BUILD_ALL) -lopcodes -liberty + $(BUILD_ALL)

$(OUTPUT)test-hello.bin: $(BUILD) diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index 5a5832ee7b53c..5a3026bba31c6 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -323,9 +323,6 @@ FEATURE_CHECK_LDFLAGS-libpython := $(PYTHON_EMBED_LDOPTS)

FEATURE_CHECK_LDFLAGS-libaio = -lrt

-FEATURE_CHECK_LDFLAGS-disassembler-four-args = -lbfd -lopcodes -ldl -FEATURE_CHECK_LDFLAGS-disassembler-init-styled = -lbfd -lopcodes -ldl - CORE_CFLAGS += -fno-omit-frame-pointer CORE_CFLAGS += -Wall CORE_CFLAGS += -Wextra @@ -921,6 +918,8 @@ ifdef BUILD_NONDISTRO

ifeq ($(feature-libbfd), 1) EXTLIBS += -lbfd -lopcodes + FEATURE_CHECK_LDFLAGS-disassembler-four-args = -lbfd -lopcodes -ldl + FEATURE_CHECK_LDFLAGS-disassembler-init-styled = -lbfd -lopcodes -ldl else # we are on a system that requires -liberty and (maybe) -lz # to link against -lbfd; test each case individually here

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jedrzej Jagielski jedrzej.jagielski@intel.com

[ Upstream commit 823be089f9c8ab136ba382b516aedd3f7ac854bd ]

Send to VF information about features supported by the PF driver.

Increase API version to 1.7.

Reviewed-by: Przemek Kitszel przemyslaw.kitszel@intel.com Reviewed-by: Aleksandr Loktionov aleksandr.loktionov@intel.com Signed-off-by: Jedrzej Jagielski jedrzej.jagielski@intel.com Tested-by: Rafal Romanowski rafal.romanowski@intel.com Signed-off-by: Jacob Keller jacob.e.keller@intel.com Link: https://patch.msgid.link/20251009-jk-iwl-net-2025-10-01-v3-5-ef32a425b92a@in... Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.h | 10 +++++ .../net/ethernet/intel/ixgbe/ixgbe_sriov.c | 37 +++++++++++++++++++ 2 files changed, 47 insertions(+)

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.h index f7256a339c99b..0334ed4b8fa39 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.h @@ -52,6 +52,7 @@ enum ixgbe_pfvf_api_rev { ixgbe_mbox_api_14, /* API version 1.4, linux/freebsd VF driver */ ixgbe_mbox_api_15, /* API version 1.5, linux/freebsd VF driver */ ixgbe_mbox_api_16, /* API version 1.6, linux/freebsd VF driver */ + ixgbe_mbox_api_17, /* API version 1.7, linux/freebsd VF driver */ /* This value should always be last */ ixgbe_mbox_api_unknown, /* indicates that API version is not known */ }; @@ -91,6 +92,9 @@ enum ixgbe_pfvf_api_rev { /* mailbox API, version 1.6 VF requests */ #define IXGBE_VF_GET_PF_LINK_STATE 0x11 /* request PF to send link info */

+/* mailbox API, version 1.7 VF requests */ +#define IXGBE_VF_FEATURES_NEGOTIATE 0x12 /* get features supported by PF */ + /* length of permanent address message returned from PF */ #define IXGBE_VF_PERMADDR_MSG_LEN 4 /* word in permanent address message with the current multicast type */ @@ -101,6 +105,12 @@ enum ixgbe_pfvf_api_rev { #define IXGBE_VF_MBX_INIT_TIMEOUT 2000 /* number of retries on mailbox */ #define IXGBE_VF_MBX_INIT_DELAY 500 /* microseconds between retries */

+/* features negotiated between PF/VF */ +#define IXGBEVF_PF_SUP_IPSEC BIT(0) +#define IXGBEVF_PF_SUP_ESX_MBX BIT(1) + +#define IXGBE_SUPPORTED_FEATURES IXGBEVF_PF_SUP_IPSEC + struct ixgbe_hw;

int ixgbe_read_mbx(struct ixgbe_hw *, u32 *, u16, u16); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c index b09271d61a4ef..ee133d6749b37 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c @@ -511,6 +511,7 @@ static int ixgbe_set_vf_lpe(struct ixgbe_adapter *adapter, u32 max_frame, u32 vf case ixgbe_mbox_api_13: case ixgbe_mbox_api_14: case ixgbe_mbox_api_16: + case ixgbe_mbox_api_17: /* Version 1.1 supports jumbo frames on VFs if PF has * jumbo frames enabled which means legacy VFs are * disabled @@ -1048,6 +1049,7 @@ static int ixgbe_negotiate_vf_api(struct ixgbe_adapter *adapter, case ixgbe_mbox_api_13: case ixgbe_mbox_api_14: case ixgbe_mbox_api_16: + case ixgbe_mbox_api_17: adapter->vfinfo[vf].vf_api = api; return 0; default: @@ -1075,6 +1077,7 @@ static int ixgbe_get_vf_queues(struct ixgbe_adapter *adapter, case ixgbe_mbox_api_13: case ixgbe_mbox_api_14: case ixgbe_mbox_api_16: + case ixgbe_mbox_api_17: break; default: return -1; @@ -1115,6 +1118,7 @@ static int ixgbe_get_vf_reta(struct ixgbe_adapter *adapter, u32 *msgbuf, u32 vf)

/* verify the PF is supporting the correct API */ switch (adapter->vfinfo[vf].vf_api) { + case ixgbe_mbox_api_17: case ixgbe_mbox_api_16: case ixgbe_mbox_api_14: case ixgbe_mbox_api_13: @@ -1149,6 +1153,7 @@ static int ixgbe_get_vf_rss_key(struct ixgbe_adapter *adapter,

/* verify the PF is supporting the correct API */ switch (adapter->vfinfo[vf].vf_api) { + case ixgbe_mbox_api_17: case ixgbe_mbox_api_16: case ixgbe_mbox_api_14: case ixgbe_mbox_api_13: @@ -1180,6 +1185,7 @@ static int ixgbe_update_vf_xcast_mode(struct ixgbe_adapter *adapter, case ixgbe_mbox_api_13: case ixgbe_mbox_api_14: case ixgbe_mbox_api_16: + case ixgbe_mbox_api_17: break; default: return -EOPNOTSUPP; @@ -1251,6 +1257,7 @@ static int ixgbe_get_vf_link_state(struct ixgbe_adapter *adapter, case ixgbe_mbox_api_13: case ixgbe_mbox_api_14: case ixgbe_mbox_api_16: + case ixgbe_mbox_api_17: break; default: return -EOPNOTSUPP; @@ -1278,6 +1285,7 @@ static int ixgbe_send_vf_link_status(struct ixgbe_adapter *adapter,

switch (adapter->vfinfo[vf].vf_api) { case ixgbe_mbox_api_16: + case ixgbe_mbox_api_17: if (hw->mac.type != ixgbe_mac_e610) return -EOPNOTSUPP; break; @@ -1293,6 +1301,32 @@ static int ixgbe_send_vf_link_status(struct ixgbe_adapter *adapter, return 0; }

+/** + * ixgbe_negotiate_vf_features - negotiate supported features with VF driver + * @adapter: pointer to adapter struct + * @msgbuf: pointer to message buffers + * @vf: VF identifier + * + * Return: 0 on success or -EOPNOTSUPP when operation is not supported. + */ +static int ixgbe_negotiate_vf_features(struct ixgbe_adapter *adapter, + u32 *msgbuf, u32 vf) +{ + u32 features = msgbuf[1]; + + switch (adapter->vfinfo[vf].vf_api) { + case ixgbe_mbox_api_17: + break; + default: + return -EOPNOTSUPP; + } + + features &= IXGBE_SUPPORTED_FEATURES; + msgbuf[1] = features; + + return 0; +} + static int ixgbe_rcv_msg_from_vf(struct ixgbe_adapter *adapter, u32 vf) { u32 mbx_size = IXGBE_VFMAILBOX_SIZE; @@ -1370,6 +1404,9 @@ static int ixgbe_rcv_msg_from_vf(struct ixgbe_adapter *adapter, u32 vf) case IXGBE_VF_GET_PF_LINK_STATE: retval = ixgbe_send_vf_link_status(adapter, msgbuf, vf); break; + case IXGBE_VF_FEATURES_NEGOTIATE: + retval = ixgbe_negotiate_vf_features(adapter, msgbuf, vf); + break; default: e_err(drv, "Unhandled Msg %8.8x\n", msgbuf[0]); retval = -EIO;

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Nicolas Escande nico.escande@gmail.com

[ Upstream commit 9065b968752334f972e0d48e50c4463a172fc2a7 ]

When reporting tx completion using ieee80211_tx_status_xxx() family of functions, the status part of the struct ieee80211_tx_info nested in the skb is used to report things like transmit rates & retry count to mac80211

On the TX data path, this is correctly memset to 0 before calling ieee80211_tx_status_ext(), but on the tx mgmt path this was not done.

This leads to mac80211 treating garbage values as valid transmit counters (like tx retries for example) and accounting them as real statistics that makes their way to userland via station dump.

The same issue was resolved in ath12k by commit 9903c0986f78 ("wifi: ath12k: Add memset and update default rate value in wmi tx completion")

Tested-on: QCN9074 PCI WLAN.HK.2.9.0.1-01977-QCAHKSWPL_SILICONZ-1

Fixes: d5c65159f289 ("ath11k: driver for Qualcomm IEEE 802.11ax devices") Signed-off-by: Nicolas Escande nico.escande@gmail.com Reviewed-by: Vasanthakumar Thiagarajan vasanthakumar.thiagarajan@oss.qualcomm.com Reviewed-by: Baochen Qiang baochen.qiang@oss.qualcomm.com Link: https://patch.msgid.link/20251104083957.717825-1-nico.escande@gmail.com Signed-off-by: Jeff Johnson jeff.johnson@oss.qualcomm.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/wireless/ath/ath11k/wmi.c | 3 +++ 1 file changed, 3 insertions(+)

diff --git a/drivers/net/wireless/ath/ath11k/wmi.c b/drivers/net/wireless/ath/ath11k/wmi.c index 0491e3fd6b5e1..e3b444333deed 100644 --- a/drivers/net/wireless/ath/ath11k/wmi.c +++ b/drivers/net/wireless/ath/ath11k/wmi.c @@ -5961,6 +5961,9 @@ static int wmi_process_mgmt_tx_comp(struct ath11k *ar, dma_unmap_single(ar->ab->dev, skb_cb->paddr, msdu->len, DMA_TO_DEVICE);

info = IEEE80211_SKB_CB(msdu); + memset(&info->status, 0, sizeof(info->status)); + info->status.rates[0].idx = -1; + if ((!(info->flags & IEEE80211_TX_CTL_NO_ACK)) && !tx_compl_param->status) { info->flags |= IEEE80211_TX_STAT_ACK;

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Benjamin Berg benjamin.berg@intel.com

[ Upstream commit 7fe0d21f5633af8c3fab9f0ef0706c6156623484 ]

If for example the sniffer did not follow any AIDs in an MU frame, then some of the information may not be filled in or is even expected to be invalid. As an example, in that case it is expected that Nss is zero.

Fixes: 2ff5e52e7836 ("radiotap: add 0-length PSDU "not captured" type") Signed-off-by: Benjamin Berg benjamin.berg@intel.com Signed-off-by: Miri Korenblit miriam.rachel.korenblit@intel.com Link: https://patch.msgid.link/20251110142554.83a2858ee15b.I9f78ce7984872f474722f9... Signed-off-by: Johannes Berg johannes.berg@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- net/mac80211/rx.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 59baca24aa6b9..dcf4b24cc39cf 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -5352,10 +5352,14 @@ void ieee80211_rx_list(struct ieee80211_hw *hw, struct ieee80211_sta *pubsta, if (WARN_ON(!local->started)) goto drop;

- if (likely(!(status->flag & RX_FLAG_FAILED_PLCP_CRC))) { + if (likely(!(status->flag & RX_FLAG_FAILED_PLCP_CRC) && + !(status->flag & RX_FLAG_NO_PSDU && + status->zero_length_psdu_type == + IEEE80211_RADIOTAP_ZERO_LEN_PSDU_NOT_CAPTURED))) { /* - * Validate the rate, unless a PLCP error means that - * we probably can't have a valid rate here anyway. + * Validate the rate, unless there was a PLCP error which may + * have an invalid rate or the PSDU was not capture and may be + * missing rate information. */

switch (status->encoding) {

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Pauli Virtanen pav@iki.fi

[ Upstream commit b454505bf57a2e4f5d49951d4deb03730a9348d9 ]

Bluetooth 6lowpan.c confuses BDADDR_LE and ADDR_LE_DEV address types, e.g. debugfs "connect" command takes the former, and "disconnect" and "connect" to already connected device take the latter. This is due to using same value both for l2cap_chan_connect and hci_conn_hash_lookup_le which take different dst_type values.

Fix address type passed to hci_conn_hash_lookup_le().

Retain the debugfs API difference between "connect" and "disconnect" commands since it's been like this since 2015 and nobody apparently complained.

Fixes: f5ad4ffceba0 ("Bluetooth: 6lowpan: Use hci_conn_hash_lookup_le() when possible") Reviewed-by: Paul Menzel pmenzel@molgen.mpg.de Signed-off-by: Pauli Virtanen pav@iki.fi Signed-off-by: Luiz Augusto von Dentz luiz.von.dentz@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- net/bluetooth/6lowpan.c | 28 ++++++++++++++++++++++++---- 1 file changed, 24 insertions(+), 4 deletions(-)

diff --git a/net/bluetooth/6lowpan.c b/net/bluetooth/6lowpan.c index f1d29fa4b4119..0d8c2e2e9a6cf 100644 --- a/net/bluetooth/6lowpan.c +++ b/net/bluetooth/6lowpan.c @@ -957,10 +957,11 @@ static struct l2cap_chan *bt_6lowpan_listen(void) }

static int get_l2cap_conn(char *buf, bdaddr_t *addr, u8 *addr_type, - struct l2cap_conn **conn) + struct l2cap_conn **conn, bool disconnect) { struct hci_conn *hcon; struct hci_dev *hdev; + int le_addr_type; int n;

n = sscanf(buf, "%hhx:%hhx:%hhx:%hhx:%hhx:%hhx %hhu", @@ -971,13 +972,32 @@ static int get_l2cap_conn(char *buf, bdaddr_t *addr, u8 *addr_type, if (n < 7) return -EINVAL;

+ if (disconnect) { + /* The "disconnect" debugfs command has used different address + * type constants than "connect" since 2015. Let's retain that + * for now even though it's obviously buggy... + */ + *addr_type += 1; + } + + switch (*addr_type) { + case BDADDR_LE_PUBLIC: + le_addr_type = ADDR_LE_DEV_PUBLIC; + break; + case BDADDR_LE_RANDOM: + le_addr_type = ADDR_LE_DEV_RANDOM; + break; + default: + return -EINVAL; + } + /* The LE_PUBLIC address type is ignored because of BDADDR_ANY */ hdev = hci_get_route(addr, BDADDR_ANY, BDADDR_LE_PUBLIC); if (!hdev) return -ENOENT;

hci_dev_lock(hdev); - hcon = hci_conn_hash_lookup_le(hdev, addr, *addr_type); + hcon = hci_conn_hash_lookup_le(hdev, addr, le_addr_type); hci_dev_unlock(hdev); hci_dev_put(hdev);

@@ -1104,7 +1124,7 @@ static ssize_t lowpan_control_write(struct file *fp, buf[buf_size] = '\0';

if (memcmp(buf, "connect ", 8) == 0) { - ret = get_l2cap_conn(&buf[8], &addr, &addr_type, &conn); + ret = get_l2cap_conn(&buf[8], &addr, &addr_type, &conn, false); if (ret == -EINVAL) return ret;

@@ -1141,7 +1161,7 @@ static ssize_t lowpan_control_write(struct file *fp, }

if (memcmp(buf, "disconnect ", 11) == 0) { - ret = get_l2cap_conn(&buf[11], &addr, &addr_type, &conn); + ret = get_l2cap_conn(&buf[11], &addr, &addr_type, &conn, true); if (ret < 0) return ret;

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Zilin Guan zilin@seu.edu.cn

[ Upstream commit 3072f00bba764082fa41b3c3a2a7b013335353d2 ]

In tls_handshake_accept(), a netlink message is allocated using genlmsg_new(). In the error handling path, genlmsg_cancel() is called to cancel the message construction, but the message itself is not freed. This leads to a memory leak.

Fix this by calling nlmsg_free() in the error path after genlmsg_cancel() to release the allocated memory.

Fixes: 2fd5532044a89 ("net/handshake: Add a kernel API for requesting a TLSv1.3 handshake") Signed-off-by: Zilin Guan zilin@seu.edu.cn Reviewed-by: Chuck Lever chuck.lever@oracle.com Link: https://patch.msgid.link/20251106144511.3859535-1-zilin@seu.edu.cn Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- net/handshake/tlshd.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/net/handshake/tlshd.c b/net/handshake/tlshd.c index 081093dfd5533..8f9532a15f43f 100644 --- a/net/handshake/tlshd.c +++ b/net/handshake/tlshd.c @@ -259,6 +259,7 @@ static int tls_handshake_accept(struct handshake_req *req,

out_cancel: genlmsg_cancel(msg, hdr); + nlmsg_free(msg); out: return ret; }

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Abdun Nihaal nihaal@cse.iitm.ac.in

[ Upstream commit 8513c154f8ad7097653dd9bf43d6155e5aad4ab3 ]

The memory allocated for buf is not freed in the error paths when ps_get_report() fails. Free buf before jumping to transfer_failed label

Fixes: 947992c7fa9e ("HID: playstation: DS4: Fix calibration workaround for clone devices") Signed-off-by: Abdun Nihaal nihaal@cse.iitm.ac.in Reviewed-by: Silvan Jegen s.jegen@gmail.com Signed-off-by: Jiri Kosina jkosina@suse.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/hid/hid-playstation.c | 2 ++ 1 file changed, 2 insertions(+)

diff --git a/drivers/hid/hid-playstation.c b/drivers/hid/hid-playstation.c index 1468fb11e39df..657e9ae1be1ee 100644 --- a/drivers/hid/hid-playstation.c +++ b/drivers/hid/hid-playstation.c @@ -1807,6 +1807,7 @@ static int dualshock4_get_calibration_data(struct dualshock4 *ds4)

hid_warn(hdev, "Failed to retrieve DualShock4 calibration info: %d\n", ret); ret = -EILSEQ; + kfree(buf); goto transfer_failed; } else { break; @@ -1824,6 +1825,7 @@ static int dualshock4_get_calibration_data(struct dualshock4 *ds4)

if (ret) { hid_warn(hdev, "Failed to retrieve DualShock4 calibration info: %d\n", ret); + kfree(buf); goto transfer_failed; } }

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Bibo Mao maobibo@loongson.cn

commit 5001bcf86edf2de02f025a0f789bcac37fa040e6 upstream.

On LoongArch system, guest PMU hardware is shared by guest and host but PMU interrupt is separated. PMU is pass-through to VM, and there is PMU context switch when exit to host and return to guest.

There is optimiation to check whether PMU is enabled by guest. If not, it is not necessary to return to guest. However, if it is enabled, PMU context for guest need switch on. Now KVM_REQ_PMU notification is set on vCPU context switch, but it is missing if there is no vCPU context switch while PMU is used by guest VM, so fix it.

Cc: stable@vger.kernel.org Fixes: f4e40ea9f78f ("LoongArch: KVM: Add PMU support for guest") Signed-off-by: Bibo Mao maobibo@loongson.cn Signed-off-by: Huacai Chen chenhuacai@loongson.cn Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/loongarch/kvm/vcpu.c | 5 +++++ 1 file changed, 5 insertions(+)

--- a/arch/loongarch/kvm/vcpu.c +++ b/arch/loongarch/kvm/vcpu.c @@ -133,6 +133,9 @@ static void kvm_lose_pmu(struct kvm_vcpu * Clear KVM_LARCH_PMU if the guest is not using PMU CSRs when * exiting the guest, so that the next time trap into the guest. * We don't need to deal with PMU CSRs contexts. + * + * Otherwise set the request bit KVM_REQ_PMU to restore guest PMU + * before entering guest VM */ val = kvm_read_sw_gcsr(csr, LOONGARCH_CSR_PERFCTRL0); val |= kvm_read_sw_gcsr(csr, LOONGARCH_CSR_PERFCTRL1); @@ -140,6 +143,8 @@ static void kvm_lose_pmu(struct kvm_vcpu val |= kvm_read_sw_gcsr(csr, LOONGARCH_CSR_PERFCTRL3); if (!(val & KVM_PMU_EVENT_ENABLED)) vcpu->arch.aux_inuse &= ~KVM_LARCH_PMU; + else + kvm_make_request(KVM_REQ_PMU, vcpu);

kvm_restore_host_pmu(vcpu); }

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Eslam Khafagy eslam.medhat1993@gmail.com

[ Upstream commit e0fd4d42e27f761e9cc82801b3f183e658dc749d ]

When posix timer creation is set to allocate a given timer ID and the access to the user space value faults, the function terminates without freeing the already allocated posix timer structure.

Move the allocation after the user space access to cure that.

[ tglx: Massaged change log ]

Fixes: ec2d0c04624b3 ("posix-timers: Provide a mechanism to allocate a given timer ID") Reported-by: syzbot+9c47ad18f978d4394986@syzkaller.appspotmail.com Suggested-by: Cyrill Gorcunov gorcunov@gmail.com Signed-off-by: Eslam Khafagy eslam.medhat1993@gmail.com Signed-off-by: Thomas Gleixner tglx@linutronix.de Reviewed-by: Frederic Weisbecker frederic@kernel.org Link: https://patch.msgid.link/20251114122739.994326-1-eslam.medhat1993@gmail.com Closes: https://lore.kernel.org/all/69155df4.a70a0220.3124cb.0017.GAE@google.com/T/ Signed-off-by: Sasha Levin sashal@kernel.org --- kernel/time/posix-timers.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c index 8b582174b1f94..42db8396f1999 100644 --- a/kernel/time/posix-timers.c +++ b/kernel/time/posix-timers.c @@ -476,12 +476,6 @@ static int do_timer_create(clockid_t which_clock, struct sigevent *event, if (!kc->timer_create) return -EOPNOTSUPP;

- new_timer = alloc_posix_timer(); - if (unlikely(!new_timer)) - return -EAGAIN; - - spin_lock_init(&new_timer->it_lock); - /* Special case for CRIU to restore timers with a given timer ID. */ if (unlikely(current->signal->timer_create_restore_ids)) { if (copy_from_user(&req_id, created_timer_id, sizeof(req_id))) @@ -491,6 +485,12 @@ static int do_timer_create(clockid_t which_clock, struct sigevent *event, return -EINVAL; }

+ new_timer = alloc_posix_timer(); + if (unlikely(!new_timer)) + return -EAGAIN; + + spin_lock_init(&new_timer->it_lock); + /* * Add the timer to the hash table. The timer is not yet valid * after insertion, but has a unique ID allocated.

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: David Howells dhowells@redhat.com

[ Upstream commit 330e2c514823008b22e6afd2055715bc46dd8d55 ]

When a process tries to access an entry in /afs, normally what happens is that an automount dentry is created by ->lookup() and then triggered, which jumps through the ->d_automount() op. Currently, afs_dynroot_lookup() does not do cell DNS lookup, leaving that to afs_d_automount() to perform - however, it is possible to use access() or stat() on the automount point, which will always return successfully, have briefly created an afs_cell record if one did not already exist.

This means that something like:

test -d "/afs/.west" && echo Directory exists

will print "Directory exists" even though no such cell is configured. This breaks the "west" python module available on PIP as it expects this access to fail.

Now, it could be possible to make afs_dynroot_lookup() perform the DNS[*] lookup, but that would make "ls --color /afs" do this for each cell in /afs that is listed but not yet probed. kafs-client, probably wrongly, preloads the entire cell database and all the known cells are then listed in /afs - and doing ls /afs would be very, very slow, especially if any cell supplied addresses but was wholly inaccessible.

[*] When I say "DNS", actually read getaddrinfo(), which could use any one of a host of mechanisms. Could also use static configuration.

To fix this, make the following changes:

(1) Create an enum to specify the origination point of a call to afs_lookup_cell() and pass this value into that function in place of the "excl" parameter (which can be derived from it). There are six points of origination:

- Cell preload through /proc/net/afs/cells - Root cell config through /proc/net/afs/rootcell - Lookup in dynamic root - Automount trigger - Direct mount with mount() syscall - Alias check where YFS tells us the cell name is different

(2) Add an extra state into the afs_cell state machine to indicate a cell that's been initialised, but not yet looked up. This is separate from one that can be considered active and has been looked up at least once.

(3) Make afs_lookup_cell() vary its behaviour more, depending on where it was called from:

If called from preload or root cell config, DNS lookup will not happen until we definitely want to use the cell (dynroot mount, automount, direct mount or alias check). The cell will appear in /afs but stat() won't trigger DNS lookup.

If the cell already exists, dynroot will not wait for the DNS lookup to complete. If the cell did not already exist, dynroot will wait.

If called from automount, direct mount or alias check, it will wait for the DNS lookup to complete.

(4) Make afs_lookup_cell() return an error if lookup failed in one way or another. We try to return -ENOENT if the DNS says the cell does not exist and -EDESTADDRREQ if we couldn't access the DNS.

Reported-by: Markus Suvanto markus.suvanto@gmail.com Closes: https://bugzilla.kernel.org/show_bug.cgi?id=220685 Signed-off-by: David Howells dhowells@redhat.com Link: https://patch.msgid.link/1784747.1761158912@warthog.procyon.org.uk Fixes: 1d0b929fc070 ("afs: Change dynroot to create contents on demand") Tested-by: Markus Suvanto markus.suvanto@gmail.com cc: Marc Dionne marc.dionne@auristor.com cc: linux-afs@lists.infradead.org Signed-off-by: Christian Brauner brauner@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- fs/afs/cell.c | 78 +++++++++++++++++++++++++++++++++++++++-------- fs/afs/dynroot.c | 3 +- fs/afs/internal.h | 12 +++++++- fs/afs/mntpt.c | 3 +- fs/afs/proc.c | 3 +- fs/afs/super.c | 2 +- fs/afs/vl_alias.c | 3 +- 7 files changed, 86 insertions(+), 18 deletions(-)

diff --git a/fs/afs/cell.c b/fs/afs/cell.c index f31359922e98d..d9b6fa1088b7b 100644 --- a/fs/afs/cell.c +++ b/fs/afs/cell.c @@ -229,7 +229,7 @@ static struct afs_cell *afs_alloc_cell(struct afs_net *net, * @name: The name of the cell. * @namesz: The strlen of the cell name. * @vllist: A colon/comma separated list of numeric IP addresses or NULL. - * @excl: T if an error should be given if the cell name already exists. + * @reason: The reason we're doing the lookup * @trace: The reason to be logged if the lookup is successful. * * Look up a cell record by name and query the DNS for VL server addresses if @@ -239,7 +239,8 @@ static struct afs_cell *afs_alloc_cell(struct afs_net *net, */ struct afs_cell *afs_lookup_cell(struct afs_net *net, const char *name, unsigned int namesz, - const char *vllist, bool excl, + const char *vllist, + enum afs_lookup_cell_for reason, enum afs_cell_trace trace) { struct afs_cell *cell, *candidate, *cursor; @@ -247,12 +248,18 @@ struct afs_cell *afs_lookup_cell(struct afs_net *net, enum afs_cell_state state; int ret, n;

- _enter("%s,%s", name, vllist); + _enter("%s,%s,%u", name, vllist, reason);

- if (!excl) { + if (reason != AFS_LOOKUP_CELL_PRELOAD) { cell = afs_find_cell(net, name, namesz, trace); - if (!IS_ERR(cell)) + if (!IS_ERR(cell)) { + if (reason == AFS_LOOKUP_CELL_DYNROOT) + goto no_wait; + if (cell->state == AFS_CELL_SETTING_UP || + cell->state == AFS_CELL_UNLOOKED) + goto lookup_cell; goto wait_for_cell; + } }

/* Assume we're probably going to create a cell and preallocate and @@ -298,26 +305,69 @@ struct afs_cell *afs_lookup_cell(struct afs_net *net, rb_insert_color(&cell->net_node, &net->cells); up_write(&net->cells_lock);

- afs_queue_cell(cell, afs_cell_trace_queue_new); +lookup_cell: + if (reason != AFS_LOOKUP_CELL_PRELOAD && + reason != AFS_LOOKUP_CELL_ROOTCELL) { + set_bit(AFS_CELL_FL_DO_LOOKUP, &cell->flags); + afs_queue_cell(cell, afs_cell_trace_queue_new); + }

wait_for_cell: - _debug("wait_for_cell"); state = smp_load_acquire(&cell->state); /* vs error */ - if (state != AFS_CELL_ACTIVE && - state != AFS_CELL_DEAD) { + switch (state) { + case AFS_CELL_ACTIVE: + case AFS_CELL_DEAD: + break; + case AFS_CELL_UNLOOKED: + default: + if (reason == AFS_LOOKUP_CELL_PRELOAD || + reason == AFS_LOOKUP_CELL_ROOTCELL) + break; + _debug("wait_for_cell"); afs_see_cell(cell, afs_cell_trace_wait); wait_var_event(&cell->state, ({ state = smp_load_acquire(&cell->state); /* vs error */ state == AFS_CELL_ACTIVE || state == AFS_CELL_DEAD; })); + _debug("waited_for_cell %d %d", cell->state, cell->error); }

+no_wait: /* Check the state obtained from the wait check. */ + state = smp_load_acquire(&cell->state); /* vs error */ if (state == AFS_CELL_DEAD) { ret = cell->error; goto error; } + if (state == AFS_CELL_ACTIVE) { + switch (cell->dns_status) { + case DNS_LOOKUP_NOT_DONE: + if (cell->dns_source == DNS_RECORD_FROM_CONFIG) { + ret = 0; + break; + } + fallthrough; + default: + ret = -EIO; + goto error; + case DNS_LOOKUP_GOOD: + case DNS_LOOKUP_GOOD_WITH_BAD: + ret = 0; + break; + case DNS_LOOKUP_GOT_NOT_FOUND: + ret = -ENOENT; + goto error; + case DNS_LOOKUP_BAD: + ret = -EREMOTEIO; + goto error; + case DNS_LOOKUP_GOT_LOCAL_FAILURE: + case DNS_LOOKUP_GOT_TEMP_FAILURE: + case DNS_LOOKUP_GOT_NS_FAILURE: + ret = -EDESTADDRREQ; + goto error; + } + }

_leave(" = %p [cell]", cell); return cell; @@ -325,7 +375,7 @@ struct afs_cell *afs_lookup_cell(struct afs_net *net, cell_already_exists: _debug("cell exists"); cell = cursor; - if (excl) { + if (reason == AFS_LOOKUP_CELL_PRELOAD) { ret = -EEXIST; } else { afs_use_cell(cursor, trace); @@ -384,7 +434,8 @@ int afs_cell_init(struct afs_net *net, const char *rootcell) return -EINVAL;

/* allocate a cell record for the root/workstation cell */ - new_root = afs_lookup_cell(net, rootcell, len, vllist, false, + new_root = afs_lookup_cell(net, rootcell, len, vllist, + AFS_LOOKUP_CELL_ROOTCELL, afs_cell_trace_use_lookup_ws); if (IS_ERR(new_root)) { _leave(" = %ld", PTR_ERR(new_root)); @@ -777,6 +828,7 @@ static bool afs_manage_cell(struct afs_cell *cell) switch (cell->state) { case AFS_CELL_SETTING_UP: goto set_up_cell; + case AFS_CELL_UNLOOKED: case AFS_CELL_ACTIVE: goto cell_is_active; case AFS_CELL_REMOVING: @@ -797,7 +849,7 @@ static bool afs_manage_cell(struct afs_cell *cell) goto remove_cell; }

- afs_set_cell_state(cell, AFS_CELL_ACTIVE); + afs_set_cell_state(cell, AFS_CELL_UNLOOKED);

cell_is_active: if (afs_has_cell_expired(cell, &next_manage)) @@ -807,6 +859,8 @@ static bool afs_manage_cell(struct afs_cell *cell) ret = afs_update_cell(cell); if (ret < 0) cell->error = ret; + if (cell->state == AFS_CELL_UNLOOKED) + afs_set_cell_state(cell, AFS_CELL_ACTIVE); }

if (next_manage < TIME64_MAX && cell->net->live) { diff --git a/fs/afs/dynroot.c b/fs/afs/dynroot.c index 8c6130789fde3..dc9d29e3739e7 100644 --- a/fs/afs/dynroot.c +++ b/fs/afs/dynroot.c @@ -108,7 +108,8 @@ static struct dentry *afs_dynroot_lookup_cell(struct inode *dir, struct dentry * dotted = true; }

- cell = afs_lookup_cell(net, name, len, NULL, false, + cell = afs_lookup_cell(net, name, len, NULL, + AFS_LOOKUP_CELL_DYNROOT, afs_cell_trace_use_lookup_dynroot); if (IS_ERR(cell)) { ret = PTR_ERR(cell); diff --git a/fs/afs/internal.h b/fs/afs/internal.h index 1124ea4000cb1..87828d685293f 100644 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@ -343,6 +343,7 @@ extern const char afs_init_sysname[];

enum afs_cell_state { AFS_CELL_SETTING_UP, + AFS_CELL_UNLOOKED, AFS_CELL_ACTIVE, AFS_CELL_REMOVING, AFS_CELL_DEAD, @@ -1047,9 +1048,18 @@ static inline bool afs_cb_is_broken(unsigned int cb_break, extern int afs_cell_init(struct afs_net *, const char *); extern struct afs_cell *afs_find_cell(struct afs_net *, const char *, unsigned, enum afs_cell_trace); +enum afs_lookup_cell_for { + AFS_LOOKUP_CELL_DYNROOT, + AFS_LOOKUP_CELL_MOUNTPOINT, + AFS_LOOKUP_CELL_DIRECT_MOUNT, + AFS_LOOKUP_CELL_PRELOAD, + AFS_LOOKUP_CELL_ROOTCELL, + AFS_LOOKUP_CELL_ALIAS_CHECK, +}; struct afs_cell *afs_lookup_cell(struct afs_net *net, const char *name, unsigned int namesz, - const char *vllist, bool excl, + const char *vllist, + enum afs_lookup_cell_for reason, enum afs_cell_trace trace); extern struct afs_cell *afs_use_cell(struct afs_cell *, enum afs_cell_trace); void afs_unuse_cell(struct afs_cell *cell, enum afs_cell_trace reason); diff --git a/fs/afs/mntpt.c b/fs/afs/mntpt.c index 9434a5399f2b0..828347fa26450 100644 --- a/fs/afs/mntpt.c +++ b/fs/afs/mntpt.c @@ -107,7 +107,8 @@ static int afs_mntpt_set_params(struct fs_context *fc, struct dentry *mntpt) if (size > AFS_MAXCELLNAME) return -ENAMETOOLONG;

- cell = afs_lookup_cell(ctx->net, p, size, NULL, false, + cell = afs_lookup_cell(ctx->net, p, size, NULL, + AFS_LOOKUP_CELL_MOUNTPOINT, afs_cell_trace_use_lookup_mntpt); if (IS_ERR(cell)) { pr_err("kAFS: unable to lookup cell '%pd'\n", mntpt); diff --git a/fs/afs/proc.c b/fs/afs/proc.c index 40e879c8ca773..44520549b509a 100644 --- a/fs/afs/proc.c +++ b/fs/afs/proc.c @@ -122,7 +122,8 @@ static int afs_proc_cells_write(struct file *file, char *buf, size_t size) if (strcmp(buf, "add") == 0) { struct afs_cell *cell;

- cell = afs_lookup_cell(net, name, strlen(name), args, true, + cell = afs_lookup_cell(net, name, strlen(name), args, + AFS_LOOKUP_CELL_PRELOAD, afs_cell_trace_use_lookup_add); if (IS_ERR(cell)) { ret = PTR_ERR(cell); diff --git a/fs/afs/super.c b/fs/afs/super.c index da407f2d6f0d1..d672b7ab57ae2 100644 --- a/fs/afs/super.c +++ b/fs/afs/super.c @@ -290,7 +290,7 @@ static int afs_parse_source(struct fs_context *fc, struct fs_parameter *param) /* lookup the cell record */ if (cellname) { cell = afs_lookup_cell(ctx->net, cellname, cellnamesz, - NULL, false, + NULL, AFS_LOOKUP_CELL_DIRECT_MOUNT, afs_cell_trace_use_lookup_mount); if (IS_ERR(cell)) { pr_err("kAFS: unable to lookup cell '%*.*s'\n", diff --git a/fs/afs/vl_alias.c b/fs/afs/vl_alias.c index 709b4cdb723ee..fc9676abd2527 100644 --- a/fs/afs/vl_alias.c +++ b/fs/afs/vl_alias.c @@ -269,7 +269,8 @@ static int yfs_check_canonical_cell_name(struct afs_cell *cell, struct key *key) if (!name_len || name_len > AFS_MAXCELLNAME) master = ERR_PTR(-EOPNOTSUPP); else - master = afs_lookup_cell(cell->net, cell_name, name_len, NULL, false, + master = afs_lookup_cell(cell->net, cell_name, name_len, NULL, + AFS_LOOKUP_CELL_ALIAS_CHECK, afs_cell_trace_use_lookup_canonical); kfree(cell_name); if (IS_ERR(master))

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Gal Pressman gal@nvidia.com

[ Upstream commit 9fcc2b6c10523f7e75db6387946c86fcf19dc97e ]

Change the debug message to print the correct units instead of always assuming Gbps, as the value can be in either 100 Mbps or 1 Gbps units.

Fixes: 5da8bc3effb6 ("net/mlx5e: DCBNL, Add debug messages log") Signed-off-by: Gal Pressman gal@nvidia.com Reviewed-by: Nimrod Oren noren@nvidia.com Signed-off-by: Tariq Toukan tariqt@nvidia.com Link: https://patch.msgid.link/1762681073-1084058-6-git-send-email-tariqt@nvidia.c... Signed-off-by: Paolo Abeni pabeni@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- .../net/ethernet/mellanox/mlx5/core/en_dcbnl.c | 18 ++++++++++++++++-- 1 file changed, 16 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c index d88a48210fdcb..9b93da4d52f64 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c @@ -598,6 +598,19 @@ static int mlx5e_dcbnl_ieee_setmaxrate(struct net_device *netdev, __u64 upper_limit_mbps; __u64 upper_limit_gbps; int i; + struct { + int scale; + const char *units_str; + } units[] = { + [MLX5_100_MBPS_UNIT] = { + .scale = 100, + .units_str = "Mbps", + }, + [MLX5_GBPS_UNIT] = { + .scale = 1, + .units_str = "Gbps", + }, + };

memset(max_bw_value, 0, sizeof(max_bw_value)); memset(max_bw_unit, 0, sizeof(max_bw_unit)); @@ -628,8 +641,9 @@ static int mlx5e_dcbnl_ieee_setmaxrate(struct net_device *netdev, }

for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) { - netdev_dbg(netdev, "%s: tc_%d <=> max_bw %d Gbps\n", - __func__, i, max_bw_value[i]); + netdev_dbg(netdev, "%s: tc_%d <=> max_bw %u %s\n", __func__, i, + max_bw_value[i] * units[max_bw_unit[i]].scale, + units[max_bw_unit[i]].units_str); }

return mlx5_modify_port_ets_rate_limit(mdev, max_bw_value, max_bw_unit);

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Horatiu Vultur horatiu.vultur@microchip.com

[ Upstream commit d471793a9b67bbe3d7198ff695004190fd7b6bc7 ]

The functions lan_*_page_reg gets as a second parameter the page where the register is. In all the functions the page was hardcoded. Replace the hardcoded values with defines to make it more clear what are those parameters.

Reviewed-by: Russell King (Oracle) rmk+kernel@armlinux.org.uk Signed-off-by: Horatiu Vultur horatiu.vultur@microchip.com Link: https://patch.msgid.link/20250818075121.1298170-4-horatiu.vultur@microchip.c... Signed-off-by: Paolo Abeni pabeni@redhat.com Stable-dep-of: 96a9178a29a6 ("net: phy: micrel: lan8814 fix reset of the QSGMII interface") Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/phy/micrel.c | 342 ++++++++++++++++++++++++++------------- 1 file changed, 233 insertions(+), 109 deletions(-)

diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c index 0efc5adbf789d..107e5c4c7da3b 100644 --- a/drivers/net/phy/micrel.c +++ b/drivers/net/phy/micrel.c @@ -2790,6 +2790,52 @@ static int ksz886x_cable_test_get_status(struct phy_device *phydev, return ret; }

+/** + * LAN8814_PAGE_AFE_PMA - Selects Extended Page 1. + * + * This page appears to control the Analog Front-End (AFE) and Physical + * Medium Attachment (PMA) layers. It is used to access registers like + * LAN8814_PD_CONTROLS and LAN8814_LINK_QUALITY. + */ +#define LAN8814_PAGE_AFE_PMA 1 + +/** + * LAN8814_PAGE_PCS_DIGITAL - Selects Extended Page 2. + * + * This page seems dedicated to the Physical Coding Sublayer (PCS) and other + * digital logic. It is used for MDI-X alignment (LAN8814_ALIGN_SWAP) and EEE + * state (LAN8814_EEE_STATE) in the LAN8814, and is repurposed for statistics + * and self-test counters in the LAN8842. + */ +#define LAN8814_PAGE_PCS_DIGITAL 2 + +/** + * LAN8814_PAGE_COMMON_REGS - Selects Extended Page 4. + * + * This page contains device-common registers that affect the entire chip. + * It includes controls for chip-level resets, strap status, GPIO, + * QSGMII, the shared 1588 PTP block, and the PVT monitor. + */ +#define LAN8814_PAGE_COMMON_REGS 4 + +/** + * LAN8814_PAGE_PORT_REGS - Selects Extended Page 5. + * + * This page contains port-specific registers that must be accessed + * on a per-port basis. It includes controls for port LEDs, QSGMII PCS, + * rate adaptation FIFOs, and the per-port 1588 TSU block. + */ +#define LAN8814_PAGE_PORT_REGS 5 + +/** + * LAN8814_PAGE_SYSTEM_CTRL - Selects Extended Page 31. + * + * This page appears to hold fundamental system or global controls. In the + * driver, it is used by the related LAN8804 to access the + * LAN8814_CLOCK_MANAGEMENT register. + */ +#define LAN8814_PAGE_SYSTEM_CTRL 31 + #define LAN_EXT_PAGE_ACCESS_CONTROL 0x16 #define LAN_EXT_PAGE_ACCESS_ADDRESS_DATA 0x17 #define LAN_EXT_PAGE_ACCESS_CTRL_EP_FUNC 0x4000 @@ -2871,35 +2917,46 @@ static int lan8814_config_ts_intr(struct phy_device *phydev, bool enable) PTP_TSU_INT_EN_PTP_RX_TS_EN_ | PTP_TSU_INT_EN_PTP_RX_TS_OVRFL_EN_;

- return lanphy_write_page_reg(phydev, 5, PTP_TSU_INT_EN, val); + return lanphy_write_page_reg(phydev, LAN8814_PAGE_PORT_REGS, + PTP_TSU_INT_EN, val); }

static void lan8814_ptp_rx_ts_get(struct phy_device *phydev, u32 *seconds, u32 *nano_seconds, u16 *seq_id) { - *seconds = lanphy_read_page_reg(phydev, 5, PTP_RX_INGRESS_SEC_HI); + *seconds = lanphy_read_page_reg(phydev, LAN8814_PAGE_PORT_REGS, + PTP_RX_INGRESS_SEC_HI); *seconds = (*seconds << 16) | - lanphy_read_page_reg(phydev, 5, PTP_RX_INGRESS_SEC_LO); + lanphy_read_page_reg(phydev, LAN8814_PAGE_PORT_REGS, + PTP_RX_INGRESS_SEC_LO);

- *nano_seconds = lanphy_read_page_reg(phydev, 5, PTP_RX_INGRESS_NS_HI); + *nano_seconds = lanphy_read_page_reg(phydev, LAN8814_PAGE_PORT_REGS, + PTP_RX_INGRESS_NS_HI); *nano_seconds = ((*nano_seconds & 0x3fff) << 16) | - lanphy_read_page_reg(phydev, 5, PTP_RX_INGRESS_NS_LO); + lanphy_read_page_reg(phydev, LAN8814_PAGE_PORT_REGS, + PTP_RX_INGRESS_NS_LO);

- *seq_id = lanphy_read_page_reg(phydev, 5, PTP_RX_MSG_HEADER2); + *seq_id = lanphy_read_page_reg(phydev, LAN8814_PAGE_PORT_REGS, + PTP_RX_MSG_HEADER2); }

static void lan8814_ptp_tx_ts_get(struct phy_device *phydev, u32 *seconds, u32 *nano_seconds, u16 *seq_id) { - *seconds = lanphy_read_page_reg(phydev, 5, PTP_TX_EGRESS_SEC_HI); + *seconds = lanphy_read_page_reg(phydev, LAN8814_PAGE_PORT_REGS, + PTP_TX_EGRESS_SEC_HI); *seconds = *seconds << 16 | - lanphy_read_page_reg(phydev, 5, PTP_TX_EGRESS_SEC_LO); + lanphy_read_page_reg(phydev, LAN8814_PAGE_PORT_REGS, + PTP_TX_EGRESS_SEC_LO);

- *nano_seconds = lanphy_read_page_reg(phydev, 5, PTP_TX_EGRESS_NS_HI); + *nano_seconds = lanphy_read_page_reg(phydev, LAN8814_PAGE_PORT_REGS, + PTP_TX_EGRESS_NS_HI); *nano_seconds = ((*nano_seconds & 0x3fff) << 16) | - lanphy_read_page_reg(phydev, 5, PTP_TX_EGRESS_NS_LO); + lanphy_read_page_reg(phydev, LAN8814_PAGE_PORT_REGS, + PTP_TX_EGRESS_NS_LO);

- *seq_id = lanphy_read_page_reg(phydev, 5, PTP_TX_MSG_HEADER2); + *seq_id = lanphy_read_page_reg(phydev, LAN8814_PAGE_PORT_REGS, + PTP_TX_MSG_HEADER2); }

static int lan8814_ts_info(struct mii_timestamper *mii_ts, struct kernel_ethtool_ts_info *info) @@ -2933,11 +2990,11 @@ static void lan8814_flush_fifo(struct phy_device *phydev, bool egress) int i;

for (i = 0; i < FIFO_SIZE; ++i) - lanphy_read_page_reg(phydev, 5, + lanphy_read_page_reg(phydev, LAN8814_PAGE_PORT_REGS, egress ? PTP_TX_MSG_HEADER2 : PTP_RX_MSG_HEADER2);

/* Read to clear overflow status bit */ - lanphy_read_page_reg(phydev, 5, PTP_TSU_INT_STS); + lanphy_read_page_reg(phydev, LAN8814_PAGE_PORT_REGS, PTP_TSU_INT_STS); }

static int lan8814_hwtstamp(struct mii_timestamper *mii_ts, @@ -2987,20 +3044,26 @@ static int lan8814_hwtstamp(struct mii_timestamper *mii_ts, rxcfg |= PTP_RX_PARSE_CONFIG_IPV4_EN_ | PTP_RX_PARSE_CONFIG_IPV6_EN_; txcfg |= PTP_TX_PARSE_CONFIG_IPV4_EN_ | PTP_TX_PARSE_CONFIG_IPV6_EN_; } - lanphy_write_page_reg(ptp_priv->phydev, 5, PTP_RX_PARSE_CONFIG, rxcfg); - lanphy_write_page_reg(ptp_priv->phydev, 5, PTP_TX_PARSE_CONFIG, txcfg); + lanphy_write_page_reg(ptp_priv->phydev, LAN8814_PAGE_PORT_REGS, + PTP_RX_PARSE_CONFIG, rxcfg); + lanphy_write_page_reg(ptp_priv->phydev, LAN8814_PAGE_PORT_REGS, + PTP_TX_PARSE_CONFIG, txcfg);

pkt_ts_enable = PTP_TIMESTAMP_EN_SYNC_ | PTP_TIMESTAMP_EN_DREQ_ | PTP_TIMESTAMP_EN_PDREQ_ | PTP_TIMESTAMP_EN_PDRES_; - lanphy_write_page_reg(ptp_priv->phydev, 5, PTP_RX_TIMESTAMP_EN, pkt_ts_enable); - lanphy_write_page_reg(ptp_priv->phydev, 5, PTP_TX_TIMESTAMP_EN, pkt_ts_enable); + lanphy_write_page_reg(ptp_priv->phydev, LAN8814_PAGE_PORT_REGS, + PTP_RX_TIMESTAMP_EN, pkt_ts_enable); + lanphy_write_page_reg(ptp_priv->phydev, LAN8814_PAGE_PORT_REGS, + PTP_TX_TIMESTAMP_EN, pkt_ts_enable);

if (ptp_priv->hwts_tx_type == HWTSTAMP_TX_ONESTEP_SYNC) { - lanphy_modify_page_reg(ptp_priv->phydev, 5, PTP_TX_MOD, + lanphy_modify_page_reg(ptp_priv->phydev, LAN8814_PAGE_PORT_REGS, + PTP_TX_MOD, PTP_TX_MOD_TX_PTP_SYNC_TS_INSERT_, PTP_TX_MOD_TX_PTP_SYNC_TS_INSERT_); } else if (ptp_priv->hwts_tx_type == HWTSTAMP_TX_ON) { - lanphy_modify_page_reg(ptp_priv->phydev, 5, PTP_TX_MOD, + lanphy_modify_page_reg(ptp_priv->phydev, LAN8814_PAGE_PORT_REGS, + PTP_TX_MOD, PTP_TX_MOD_TX_PTP_SYNC_TS_INSERT_, 0); } @@ -3124,29 +3187,41 @@ static bool lan8814_rxtstamp(struct mii_timestamper *mii_ts, struct sk_buff *skb static void lan8814_ptp_clock_set(struct phy_device *phydev, time64_t sec, u32 nsec) { - lanphy_write_page_reg(phydev, 4, PTP_CLOCK_SET_SEC_LO, lower_16_bits(sec)); - lanphy_write_page_reg(phydev, 4, PTP_CLOCK_SET_SEC_MID, upper_16_bits(sec)); - lanphy_write_page_reg(phydev, 4, PTP_CLOCK_SET_SEC_HI, upper_32_bits(sec)); - lanphy_write_page_reg(phydev, 4, PTP_CLOCK_SET_NS_LO, lower_16_bits(nsec)); - lanphy_write_page_reg(phydev, 4, PTP_CLOCK_SET_NS_HI, upper_16_bits(nsec)); + lanphy_write_page_reg(phydev, LAN8814_PAGE_COMMON_REGS, + PTP_CLOCK_SET_SEC_LO, lower_16_bits(sec)); + lanphy_write_page_reg(phydev, LAN8814_PAGE_COMMON_REGS, + PTP_CLOCK_SET_SEC_MID, upper_16_bits(sec)); + lanphy_write_page_reg(phydev, LAN8814_PAGE_COMMON_REGS, + PTP_CLOCK_SET_SEC_HI, upper_32_bits(sec)); + lanphy_write_page_reg(phydev, LAN8814_PAGE_COMMON_REGS, + PTP_CLOCK_SET_NS_LO, lower_16_bits(nsec)); + lanphy_write_page_reg(phydev, LAN8814_PAGE_COMMON_REGS, + PTP_CLOCK_SET_NS_HI, upper_16_bits(nsec));

- lanphy_write_page_reg(phydev, 4, PTP_CMD_CTL, PTP_CMD_CTL_PTP_CLOCK_LOAD_); + lanphy_write_page_reg(phydev, LAN8814_PAGE_COMMON_REGS, PTP_CMD_CTL, + PTP_CMD_CTL_PTP_CLOCK_LOAD_); }

static void lan8814_ptp_clock_get(struct phy_device *phydev, time64_t *sec, u32 *nsec) { - lanphy_write_page_reg(phydev, 4, PTP_CMD_CTL, PTP_CMD_CTL_PTP_CLOCK_READ_); + lanphy_write_page_reg(phydev, LAN8814_PAGE_COMMON_REGS, PTP_CMD_CTL, + PTP_CMD_CTL_PTP_CLOCK_READ_);

- *sec = lanphy_read_page_reg(phydev, 4, PTP_CLOCK_READ_SEC_HI); + *sec = lanphy_read_page_reg(phydev, LAN8814_PAGE_COMMON_REGS, + PTP_CLOCK_READ_SEC_HI); *sec <<= 16; - *sec |= lanphy_read_page_reg(phydev, 4, PTP_CLOCK_READ_SEC_MID); + *sec |= lanphy_read_page_reg(phydev, LAN8814_PAGE_COMMON_REGS, + PTP_CLOCK_READ_SEC_MID); *sec <<= 16; - *sec |= lanphy_read_page_reg(phydev, 4, PTP_CLOCK_READ_SEC_LO); + *sec |= lanphy_read_page_reg(phydev, LAN8814_PAGE_COMMON_REGS, + PTP_CLOCK_READ_SEC_LO);

- *nsec = lanphy_read_page_reg(phydev, 4, PTP_CLOCK_READ_NS_HI); + *nsec = lanphy_read_page_reg(phydev, LAN8814_PAGE_COMMON_REGS, + PTP_CLOCK_READ_NS_HI); *nsec <<= 16; - *nsec |= lanphy_read_page_reg(phydev, 4, PTP_CLOCK_READ_NS_LO); + *nsec |= lanphy_read_page_reg(phydev, LAN8814_PAGE_COMMON_REGS, + PTP_CLOCK_READ_NS_LO); }

static int lan8814_ptpci_gettime64(struct ptp_clock_info *ptpci, @@ -3185,14 +3260,18 @@ static void lan8814_ptp_set_target(struct phy_device *phydev, int event, s64 start_sec, u32 start_nsec) { /* Set the start time */ - lanphy_write_page_reg(phydev, 4, LAN8814_PTP_CLOCK_TARGET_SEC_LO(event), + lanphy_write_page_reg(phydev, LAN8814_PAGE_COMMON_REGS, + LAN8814_PTP_CLOCK_TARGET_SEC_LO(event), lower_16_bits(start_sec)); - lanphy_write_page_reg(phydev, 4, LAN8814_PTP_CLOCK_TARGET_SEC_HI(event), + lanphy_write_page_reg(phydev, LAN8814_PAGE_COMMON_REGS, + LAN8814_PTP_CLOCK_TARGET_SEC_HI(event), upper_16_bits(start_sec));

- lanphy_write_page_reg(phydev, 4, LAN8814_PTP_CLOCK_TARGET_NS_LO(event), + lanphy_write_page_reg(phydev, LAN8814_PAGE_COMMON_REGS, + LAN8814_PTP_CLOCK_TARGET_NS_LO(event), lower_16_bits(start_nsec)); - lanphy_write_page_reg(phydev, 4, LAN8814_PTP_CLOCK_TARGET_NS_HI(event), + lanphy_write_page_reg(phydev, LAN8814_PAGE_COMMON_REGS, + LAN8814_PTP_CLOCK_TARGET_NS_HI(event), upper_16_bits(start_nsec) & 0x3fff); }

@@ -3290,9 +3369,11 @@ static void lan8814_ptp_clock_step(struct phy_device *phydev, adjustment_value_lo = adjustment_value & 0xffff; adjustment_value_hi = (adjustment_value >> 16) & 0x3fff;

- lanphy_write_page_reg(phydev, 4, PTP_LTC_STEP_ADJ_LO, + lanphy_write_page_reg(phydev, LAN8814_PAGE_COMMON_REGS, + PTP_LTC_STEP_ADJ_LO, adjustment_value_lo); - lanphy_write_page_reg(phydev, 4, PTP_LTC_STEP_ADJ_HI, + lanphy_write_page_reg(phydev, LAN8814_PAGE_COMMON_REGS, + PTP_LTC_STEP_ADJ_HI, PTP_LTC_STEP_ADJ_DIR_ | adjustment_value_hi); seconds -= ((s32)adjustment_value); @@ -3310,9 +3391,11 @@ static void lan8814_ptp_clock_step(struct phy_device *phydev, adjustment_value_lo = adjustment_value & 0xffff; adjustment_value_hi = (adjustment_value >> 16) & 0x3fff;

- lanphy_write_page_reg(phydev, 4, PTP_LTC_STEP_ADJ_LO, + lanphy_write_page_reg(phydev, LAN8814_PAGE_COMMON_REGS, + PTP_LTC_STEP_ADJ_LO, adjustment_value_lo); - lanphy_write_page_reg(phydev, 4, PTP_LTC_STEP_ADJ_HI, + lanphy_write_page_reg(phydev, LAN8814_PAGE_COMMON_REGS, + PTP_LTC_STEP_ADJ_HI, adjustment_value_hi); seconds += ((s32)adjustment_value);

@@ -3320,8 +3403,8 @@ static void lan8814_ptp_clock_step(struct phy_device *phydev, set_seconds += adjustment_value; lan8814_ptp_update_target(phydev, set_seconds); } - lanphy_write_page_reg(phydev, 4, PTP_CMD_CTL, - PTP_CMD_CTL_PTP_LTC_STEP_SEC_); + lanphy_write_page_reg(phydev, LAN8814_PAGE_COMMON_REGS, + PTP_CMD_CTL, PTP_CMD_CTL_PTP_LTC_STEP_SEC_); } if (nano_seconds) { u16 nano_seconds_lo; @@ -3330,12 +3413,14 @@ static void lan8814_ptp_clock_step(struct phy_device *phydev, nano_seconds_lo = nano_seconds & 0xffff; nano_seconds_hi = (nano_seconds >> 16) & 0x3fff;

- lanphy_write_page_reg(phydev, 4, PTP_LTC_STEP_ADJ_LO, + lanphy_write_page_reg(phydev, LAN8814_PAGE_COMMON_REGS, + PTP_LTC_STEP_ADJ_LO, nano_seconds_lo); - lanphy_write_page_reg(phydev, 4, PTP_LTC_STEP_ADJ_HI, + lanphy_write_page_reg(phydev, LAN8814_PAGE_COMMON_REGS, + PTP_LTC_STEP_ADJ_HI, PTP_LTC_STEP_ADJ_DIR_ | nano_seconds_hi); - lanphy_write_page_reg(phydev, 4, PTP_CMD_CTL, + lanphy_write_page_reg(phydev, LAN8814_PAGE_COMMON_REGS, PTP_CMD_CTL, PTP_CMD_CTL_PTP_LTC_STEP_NSEC_); } } @@ -3377,8 +3462,10 @@ static int lan8814_ptpci_adjfine(struct ptp_clock_info *ptpci, long scaled_ppm) kszphy_rate_adj_hi |= PTP_CLOCK_RATE_ADJ_DIR_;

mutex_lock(&shared->shared_lock); - lanphy_write_page_reg(phydev, 4, PTP_CLOCK_RATE_ADJ_HI, kszphy_rate_adj_hi); - lanphy_write_page_reg(phydev, 4, PTP_CLOCK_RATE_ADJ_LO, kszphy_rate_adj_lo); + lanphy_write_page_reg(phydev, LAN8814_PAGE_COMMON_REGS, PTP_CLOCK_RATE_ADJ_HI, + kszphy_rate_adj_hi); + lanphy_write_page_reg(phydev, LAN8814_PAGE_COMMON_REGS, PTP_CLOCK_RATE_ADJ_LO, + kszphy_rate_adj_lo); mutex_unlock(&shared->shared_lock);

return 0; @@ -3387,17 +3474,17 @@ static int lan8814_ptpci_adjfine(struct ptp_clock_info *ptpci, long scaled_ppm) static void lan8814_ptp_set_reload(struct phy_device *phydev, int event, s64 period_sec, u32 period_nsec) { - lanphy_write_page_reg(phydev, 4, + lanphy_write_page_reg(phydev, LAN8814_PAGE_COMMON_REGS, LAN8814_PTP_CLOCK_TARGET_RELOAD_SEC_LO(event), lower_16_bits(period_sec)); - lanphy_write_page_reg(phydev, 4, + lanphy_write_page_reg(phydev, LAN8814_PAGE_COMMON_REGS, LAN8814_PTP_CLOCK_TARGET_RELOAD_SEC_HI(event), upper_16_bits(period_sec));

- lanphy_write_page_reg(phydev, 4, + lanphy_write_page_reg(phydev, LAN8814_PAGE_COMMON_REGS, LAN8814_PTP_CLOCK_TARGET_RELOAD_NS_LO(event), lower_16_bits(period_nsec)); - lanphy_write_page_reg(phydev, 4, + lanphy_write_page_reg(phydev, LAN8814_PAGE_COMMON_REGS, LAN8814_PTP_CLOCK_TARGET_RELOAD_NS_HI(event), upper_16_bits(period_nsec) & 0x3fff); } @@ -3410,7 +3497,7 @@ static void lan8814_ptp_enable_event(struct phy_device *phydev, int event, * local time reaches or pass it * Set the polarity high */ - lanphy_modify_page_reg(phydev, 4, LAN8814_PTP_GENERAL_CONFIG, + lanphy_modify_page_reg(phydev, LAN8814_PAGE_COMMON_REGS, LAN8814_PTP_GENERAL_CONFIG, LAN8814_PTP_GENERAL_CONFIG_LTC_EVENT_MASK(event) | LAN8814_PTP_GENERAL_CONFIG_LTC_EVENT_SET(event, pulse_width) | LAN8814_PTP_GENERAL_CONFIG_RELOAD_ADD_X(event) | @@ -3425,7 +3512,7 @@ static void lan8814_ptp_disable_event(struct phy_device *phydev, int event) lan8814_ptp_set_target(phydev, event, 0xFFFFFFFF, 0);

/* And then reload once it recheas the target */ - lanphy_modify_page_reg(phydev, 4, LAN8814_PTP_GENERAL_CONFIG, + lanphy_modify_page_reg(phydev, LAN8814_PAGE_COMMON_REGS, LAN8814_PTP_GENERAL_CONFIG, LAN8814_PTP_GENERAL_CONFIG_RELOAD_ADD_X(event), LAN8814_PTP_GENERAL_CONFIG_RELOAD_ADD_X(event)); } @@ -3436,15 +3523,18 @@ static void lan8814_ptp_perout_off(struct phy_device *phydev, int pin) * 1: select as gpio, * 0: select alt func */ - lanphy_modify_page_reg(phydev, 4, LAN8814_GPIO_EN_ADDR(pin), + lanphy_modify_page_reg(phydev, LAN8814_PAGE_COMMON_REGS, + LAN8814_GPIO_EN_ADDR(pin), LAN8814_GPIO_EN_BIT(pin), LAN8814_GPIO_EN_BIT(pin));

- lanphy_modify_page_reg(phydev, 4, LAN8814_GPIO_DIR_ADDR(pin), + lanphy_modify_page_reg(phydev, LAN8814_PAGE_COMMON_REGS, + LAN8814_GPIO_DIR_ADDR(pin), LAN8814_GPIO_DIR_BIT(pin), 0);

- lanphy_modify_page_reg(phydev, 4, LAN8814_GPIO_BUF_ADDR(pin), + lanphy_modify_page_reg(phydev, LAN8814_PAGE_COMMON_REGS, + LAN8814_GPIO_BUF_ADDR(pin), LAN8814_GPIO_BUF_BIT(pin), 0); } @@ -3452,17 +3542,20 @@ static void lan8814_ptp_perout_off(struct phy_device *phydev, int pin) static void lan8814_ptp_perout_on(struct phy_device *phydev, int pin) { /* Set as gpio output */ - lanphy_modify_page_reg(phydev, 4, LAN8814_GPIO_DIR_ADDR(pin), + lanphy_modify_page_reg(phydev, LAN8814_PAGE_COMMON_REGS, + LAN8814_GPIO_DIR_ADDR(pin), LAN8814_GPIO_DIR_BIT(pin), LAN8814_GPIO_DIR_BIT(pin));

/* Enable gpio 0:for alternate function, 1:gpio */ - lanphy_modify_page_reg(phydev, 4, LAN8814_GPIO_EN_ADDR(pin), + lanphy_modify_page_reg(phydev, LAN8814_PAGE_COMMON_REGS, + LAN8814_GPIO_EN_ADDR(pin), LAN8814_GPIO_EN_BIT(pin), 0);

/* Set buffer type to push pull */ - lanphy_modify_page_reg(phydev, 4, LAN8814_GPIO_BUF_ADDR(pin), + lanphy_modify_page_reg(phydev, LAN8814_PAGE_COMMON_REGS, + LAN8814_GPIO_BUF_ADDR(pin), LAN8814_GPIO_BUF_BIT(pin), LAN8814_GPIO_BUF_BIT(pin)); } @@ -3580,27 +3673,29 @@ static int lan8814_ptp_perout(struct ptp_clock_info *ptpci, static void lan8814_ptp_extts_on(struct phy_device *phydev, int pin, u32 flags) { /* Set as gpio input */ - lanphy_modify_page_reg(phydev, 4, LAN8814_GPIO_DIR_ADDR(pin), + lanphy_modify_page_reg(phydev, LAN8814_PAGE_COMMON_REGS, + LAN8814_GPIO_DIR_ADDR(pin), LAN8814_GPIO_DIR_BIT(pin), 0);

/* Map the pin to ltc pin 0 of the capture map registers */ - lanphy_modify_page_reg(phydev, 4, PTP_GPIO_CAP_MAP_LO, - pin, - pin); + lanphy_modify_page_reg(phydev, LAN8814_PAGE_COMMON_REGS, + PTP_GPIO_CAP_MAP_LO, pin, pin);

/* Enable capture on the edges of the ltc pin */ if (flags & PTP_RISING_EDGE) - lanphy_modify_page_reg(phydev, 4, PTP_GPIO_CAP_EN, + lanphy_modify_page_reg(phydev, LAN8814_PAGE_COMMON_REGS, + PTP_GPIO_CAP_EN, PTP_GPIO_CAP_EN_GPIO_RE_CAPTURE_ENABLE(0), PTP_GPIO_CAP_EN_GPIO_RE_CAPTURE_ENABLE(0)); if (flags & PTP_FALLING_EDGE) - lanphy_modify_page_reg(phydev, 4, PTP_GPIO_CAP_EN, + lanphy_modify_page_reg(phydev, LAN8814_PAGE_COMMON_REGS, + PTP_GPIO_CAP_EN, PTP_GPIO_CAP_EN_GPIO_FE_CAPTURE_ENABLE(0), PTP_GPIO_CAP_EN_GPIO_FE_CAPTURE_ENABLE(0));

/* Enable interrupt top interrupt */ - lanphy_modify_page_reg(phydev, 4, PTP_COMMON_INT_ENA, + lanphy_modify_page_reg(phydev, LAN8814_PAGE_COMMON_REGS, PTP_COMMON_INT_ENA, PTP_COMMON_INT_ENA_GPIO_CAP_EN, PTP_COMMON_INT_ENA_GPIO_CAP_EN); } @@ -3608,28 +3703,31 @@ static void lan8814_ptp_extts_on(struct phy_device *phydev, int pin, u32 flags) static void lan8814_ptp_extts_off(struct phy_device *phydev, int pin) { /* Set as gpio out */ - lanphy_modify_page_reg(phydev, 4, LAN8814_GPIO_DIR_ADDR(pin), + lanphy_modify_page_reg(phydev, LAN8814_PAGE_COMMON_REGS, + LAN8814_GPIO_DIR_ADDR(pin), LAN8814_GPIO_DIR_BIT(pin), LAN8814_GPIO_DIR_BIT(pin));

/* Enable alternate, 0:for alternate function, 1:gpio */ - lanphy_modify_page_reg(phydev, 4, LAN8814_GPIO_EN_ADDR(pin), + lanphy_modify_page_reg(phydev, LAN8814_PAGE_COMMON_REGS, + LAN8814_GPIO_EN_ADDR(pin), LAN8814_GPIO_EN_BIT(pin), 0);

/* Clear the mapping of pin to registers 0 of the capture registers */ - lanphy_modify_page_reg(phydev, 4, PTP_GPIO_CAP_MAP_LO, + lanphy_modify_page_reg(phydev, LAN8814_PAGE_COMMON_REGS, + PTP_GPIO_CAP_MAP_LO, GENMASK(3, 0), 0);

/* Disable capture on both of the edges */ - lanphy_modify_page_reg(phydev, 4, PTP_GPIO_CAP_EN, + lanphy_modify_page_reg(phydev, LAN8814_PAGE_COMMON_REGS, PTP_GPIO_CAP_EN, PTP_GPIO_CAP_EN_GPIO_RE_CAPTURE_ENABLE(pin) | PTP_GPIO_CAP_EN_GPIO_FE_CAPTURE_ENABLE(pin), 0);

/* Disable interrupt top interrupt */ - lanphy_modify_page_reg(phydev, 4, PTP_COMMON_INT_ENA, + lanphy_modify_page_reg(phydev, LAN8814_PAGE_COMMON_REGS, PTP_COMMON_INT_ENA, PTP_COMMON_INT_ENA_GPIO_CAP_EN, 0); } @@ -3761,7 +3859,8 @@ static void lan8814_get_tx_ts(struct kszphy_ptp_priv *ptp_priv) /* If other timestamps are available in the FIFO, * process them. */ - reg = lanphy_read_page_reg(phydev, 5, PTP_CAP_INFO); + reg = lanphy_read_page_reg(phydev, LAN8814_PAGE_PORT_REGS, + PTP_CAP_INFO); } while (PTP_CAP_INFO_TX_TS_CNT_GET_(reg) > 0); }

@@ -3834,7 +3933,8 @@ static void lan8814_get_rx_ts(struct kszphy_ptp_priv *ptp_priv) /* If other timestamps are available in the FIFO, * process them. */ - reg = lanphy_read_page_reg(phydev, 5, PTP_CAP_INFO); + reg = lanphy_read_page_reg(phydev, LAN8814_PAGE_PORT_REGS, + PTP_CAP_INFO); } while (PTP_CAP_INFO_RX_TS_CNT_GET_(reg) > 0); }

@@ -3871,31 +3971,40 @@ static int lan8814_gpio_process_cap(struct lan8814_shared_priv *shared) /* This is 0 because whatever was the input pin it was mapped it to * ltc gpio pin 0 */ - lanphy_modify_page_reg(phydev, 4, PTP_GPIO_SEL, + lanphy_modify_page_reg(phydev, LAN8814_PAGE_COMMON_REGS, PTP_GPIO_SEL, PTP_GPIO_SEL_GPIO_SEL(0), PTP_GPIO_SEL_GPIO_SEL(0));

- tmp = lanphy_read_page_reg(phydev, 4, PTP_GPIO_CAP_STS); + tmp = lanphy_read_page_reg(phydev, LAN8814_PAGE_COMMON_REGS, + PTP_GPIO_CAP_STS); if (!(tmp & PTP_GPIO_CAP_STS_PTP_GPIO_RE_STS(0)) && !(tmp & PTP_GPIO_CAP_STS_PTP_GPIO_FE_STS(0))) return -1;

if (tmp & BIT(0)) { - sec = lanphy_read_page_reg(phydev, 4, PTP_GPIO_RE_LTC_SEC_HI_CAP); + sec = lanphy_read_page_reg(phydev, LAN8814_PAGE_COMMON_REGS, + PTP_GPIO_RE_LTC_SEC_HI_CAP); sec <<= 16; - sec |= lanphy_read_page_reg(phydev, 4, PTP_GPIO_RE_LTC_SEC_LO_CAP); + sec |= lanphy_read_page_reg(phydev, LAN8814_PAGE_COMMON_REGS, + PTP_GPIO_RE_LTC_SEC_LO_CAP);

- nsec = lanphy_read_page_reg(phydev, 4, PTP_GPIO_RE_LTC_NS_HI_CAP) & 0x3fff; + nsec = lanphy_read_page_reg(phydev, LAN8814_PAGE_COMMON_REGS, + PTP_GPIO_RE_LTC_NS_HI_CAP) & 0x3fff; nsec <<= 16; - nsec |= lanphy_read_page_reg(phydev, 4, PTP_GPIO_RE_LTC_NS_LO_CAP); + nsec |= lanphy_read_page_reg(phydev, LAN8814_PAGE_COMMON_REGS, + PTP_GPIO_RE_LTC_NS_LO_CAP); } else { - sec = lanphy_read_page_reg(phydev, 4, PTP_GPIO_FE_LTC_SEC_HI_CAP); + sec = lanphy_read_page_reg(phydev, LAN8814_PAGE_COMMON_REGS, + PTP_GPIO_FE_LTC_SEC_HI_CAP); sec <<= 16; - sec |= lanphy_read_page_reg(phydev, 4, PTP_GPIO_FE_LTC_SEC_LO_CAP); + sec |= lanphy_read_page_reg(phydev, LAN8814_PAGE_COMMON_REGS, + PTP_GPIO_FE_LTC_SEC_LO_CAP);

- nsec = lanphy_read_page_reg(phydev, 4, PTP_GPIO_FE_LTC_NS_HI_CAP) & 0x3fff; + nsec = lanphy_read_page_reg(phydev, LAN8814_PAGE_COMMON_REGS, + PTP_GPIO_FE_LTC_NS_HI_CAP) & 0x3fff; nsec <<= 16; - nsec |= lanphy_read_page_reg(phydev, 4, PTP_GPIO_RE_LTC_NS_LO_CAP); + nsec |= lanphy_read_page_reg(phydev, LAN8814_PAGE_COMMON_REGS, + PTP_GPIO_RE_LTC_NS_LO_CAP); }

ptp_event.index = 0; @@ -3921,15 +4030,16 @@ static int lan8814_handle_gpio_interrupt(struct phy_device *phydev, u16 status) static int lan8804_config_init(struct phy_device *phydev) { /* MDI-X setting for swap A,B transmit */ - lanphy_modify_page_reg(phydev, 2, LAN8804_ALIGN_SWAP, + lanphy_modify_page_reg(phydev, LAN8814_PAGE_PCS_DIGITAL, LAN8804_ALIGN_SWAP, LAN8804_ALIGN_TX_A_B_SWAP_MASK, LAN8804_ALIGN_TX_A_B_SWAP);

/* Make sure that the PHY will not stop generating the clock when the * link partner goes down */ - lanphy_write_page_reg(phydev, 31, LAN8814_CLOCK_MANAGEMENT, 0x27e); - lanphy_read_page_reg(phydev, 1, LAN8814_LINK_QUALITY); + lanphy_write_page_reg(phydev, LAN8814_PAGE_SYSTEM_CTRL, + LAN8814_CLOCK_MANAGEMENT, 0x27e); + lanphy_read_page_reg(phydev, LAN8814_PAGE_AFE_PMA, LAN8814_LINK_QUALITY);

return 0; } @@ -4011,7 +4121,8 @@ static irqreturn_t lan8814_handle_interrupt(struct phy_device *phydev) }

while (true) { - irq_status = lanphy_read_page_reg(phydev, 5, PTP_TSU_INT_STS); + irq_status = lanphy_read_page_reg(phydev, LAN8814_PAGE_PORT_REGS, + PTP_TSU_INT_STS); if (!irq_status) break;

@@ -4039,7 +4150,7 @@ static int lan8814_config_intr(struct phy_device *phydev) { int err;

- lanphy_write_page_reg(phydev, 4, LAN8814_INTR_CTRL_REG, + lanphy_write_page_reg(phydev, LAN8814_PAGE_COMMON_REGS, LAN8814_INTR_CTRL_REG, LAN8814_INTR_CTRL_REG_POLARITY | LAN8814_INTR_CTRL_REG_INTR_ENABLE);

@@ -4070,29 +4181,36 @@ static void lan8814_ptp_init(struct phy_device *phydev) !IS_ENABLED(CONFIG_NETWORK_PHY_TIMESTAMPING)) return;

- lanphy_write_page_reg(phydev, 5, TSU_HARD_RESET, TSU_HARD_RESET_); + lanphy_write_page_reg(phydev, LAN8814_PAGE_PORT_REGS, + TSU_HARD_RESET, TSU_HARD_RESET_);

- lanphy_modify_page_reg(phydev, 5, PTP_TX_MOD, + lanphy_modify_page_reg(phydev, LAN8814_PAGE_PORT_REGS, PTP_TX_MOD, PTP_TX_MOD_BAD_UDPV4_CHKSUM_FORCE_FCS_DIS_, PTP_TX_MOD_BAD_UDPV4_CHKSUM_FORCE_FCS_DIS_);

- lanphy_modify_page_reg(phydev, 5, PTP_RX_MOD, + lanphy_modify_page_reg(phydev, LAN8814_PAGE_PORT_REGS, PTP_RX_MOD, PTP_RX_MOD_BAD_UDPV4_CHKSUM_FORCE_FCS_DIS_, PTP_RX_MOD_BAD_UDPV4_CHKSUM_FORCE_FCS_DIS_);

- lanphy_write_page_reg(phydev, 5, PTP_RX_PARSE_CONFIG, 0); - lanphy_write_page_reg(phydev, 5, PTP_TX_PARSE_CONFIG, 0); + lanphy_write_page_reg(phydev, LAN8814_PAGE_PORT_REGS, + PTP_RX_PARSE_CONFIG, 0); + lanphy_write_page_reg(phydev, LAN8814_PAGE_PORT_REGS, + PTP_TX_PARSE_CONFIG, 0);

/* Removing default registers configs related to L2 and IP */ - lanphy_write_page_reg(phydev, 5, PTP_TX_PARSE_L2_ADDR_EN, 0); - lanphy_write_page_reg(phydev, 5, PTP_RX_PARSE_L2_ADDR_EN, 0); - lanphy_write_page_reg(phydev, 5, PTP_TX_PARSE_IP_ADDR_EN, 0); - lanphy_write_page_reg(phydev, 5, PTP_RX_PARSE_IP_ADDR_EN, 0); + lanphy_write_page_reg(phydev, LAN8814_PAGE_PORT_REGS, + PTP_TX_PARSE_L2_ADDR_EN, 0); + lanphy_write_page_reg(phydev, LAN8814_PAGE_PORT_REGS, + PTP_RX_PARSE_L2_ADDR_EN, 0); + lanphy_write_page_reg(phydev, LAN8814_PAGE_PORT_REGS, + PTP_TX_PARSE_IP_ADDR_EN, 0); + lanphy_write_page_reg(phydev, LAN8814_PAGE_PORT_REGS, + PTP_RX_PARSE_IP_ADDR_EN, 0);

/* Disable checking for minorVersionPTP field */ - lanphy_write_page_reg(phydev, 5, PTP_RX_VERSION, + lanphy_write_page_reg(phydev, LAN8814_PAGE_PORT_REGS, PTP_RX_VERSION, PTP_MAX_VERSION(0xff) | PTP_MIN_VERSION(0x0)); - lanphy_write_page_reg(phydev, 5, PTP_TX_VERSION, + lanphy_write_page_reg(phydev, LAN8814_PAGE_PORT_REGS, PTP_TX_VERSION, PTP_MAX_VERSION(0xff) | PTP_MIN_VERSION(0x0));

skb_queue_head_init(&ptp_priv->tx_queue); @@ -4177,12 +4295,14 @@ static int lan8814_ptp_probe_once(struct phy_device *phydev) /* The EP.4 is shared between all the PHYs in the package and also it * can be accessed by any of the PHYs */ - lanphy_write_page_reg(phydev, 4, LTC_HARD_RESET, LTC_HARD_RESET_); - lanphy_write_page_reg(phydev, 4, PTP_OPERATING_MODE, + lanphy_write_page_reg(phydev, LAN8814_PAGE_COMMON_REGS, + LTC_HARD_RESET, LTC_HARD_RESET_); + lanphy_write_page_reg(phydev, LAN8814_PAGE_COMMON_REGS, PTP_OPERATING_MODE, PTP_OPERATING_MODE_STANDALONE_);

/* Enable ptp to run LTC clock for ptp and gpio 1PPS operation */ - lanphy_write_page_reg(phydev, 4, PTP_CMD_CTL, PTP_CMD_CTL_PTP_ENABLE_); + lanphy_write_page_reg(phydev, LAN8814_PAGE_COMMON_REGS, PTP_CMD_CTL, + PTP_CMD_CTL_PTP_ENABLE_);

return 0; } @@ -4191,14 +4311,16 @@ static void lan8814_setup_led(struct phy_device *phydev, int val) { int temp;

- temp = lanphy_read_page_reg(phydev, 5, LAN8814_LED_CTRL_1); + temp = lanphy_read_page_reg(phydev, LAN8814_PAGE_PORT_REGS, + LAN8814_LED_CTRL_1);

if (val) temp |= LAN8814_LED_CTRL_1_KSZ9031_LED_MODE_; else temp &= ~LAN8814_LED_CTRL_1_KSZ9031_LED_MODE_;

- lanphy_write_page_reg(phydev, 5, LAN8814_LED_CTRL_1, temp); + lanphy_write_page_reg(phydev, LAN8814_PAGE_PORT_REGS, + LAN8814_LED_CTRL_1, temp); }

static int lan8814_config_init(struct phy_device *phydev) @@ -4206,17 +4328,19 @@ static int lan8814_config_init(struct phy_device *phydev) struct kszphy_priv *lan8814 = phydev->priv;

/* Reset the PHY */ - lanphy_modify_page_reg(phydev, 4, LAN8814_QSGMII_SOFT_RESET, + lanphy_modify_page_reg(phydev, LAN8814_PAGE_COMMON_REGS, + LAN8814_QSGMII_SOFT_RESET, LAN8814_QSGMII_SOFT_RESET_BIT, LAN8814_QSGMII_SOFT_RESET_BIT);

/* Disable ANEG with QSGMII PCS Host side */ - lanphy_modify_page_reg(phydev, 4, LAN8814_QSGMII_PCS1G_ANEG_CONFIG, + lanphy_modify_page_reg(phydev, LAN8814_PAGE_COMMON_REGS, + LAN8814_QSGMII_PCS1G_ANEG_CONFIG, LAN8814_QSGMII_PCS1G_ANEG_CONFIG_ANEG_ENA, 0);

/* MDI-X setting for swap A,B transmit */ - lanphy_modify_page_reg(phydev, 2, LAN8814_ALIGN_SWAP, + lanphy_modify_page_reg(phydev, LAN8814_PAGE_PCS_DIGITAL, LAN8814_ALIGN_SWAP, LAN8814_ALIGN_TX_A_B_SWAP_MASK, LAN8814_ALIGN_TX_A_B_SWAP);

@@ -4253,7 +4377,7 @@ static void lan8814_clear_2psp_bit(struct phy_device *phydev) * cable is removed then the LED was still one even though there is no * link */ - lanphy_modify_page_reg(phydev, 2, LAN8814_EEE_STATE, + lanphy_modify_page_reg(phydev, LAN8814_PAGE_PCS_DIGITAL, LAN8814_EEE_STATE, LAN8814_EEE_STATE_MASK2P5P, 0); } @@ -4264,7 +4388,7 @@ static void lan8814_update_meas_time(struct phy_device *phydev) * longer than 100m to be used. This configuration can be used * regardless of the mode of operation of the PHY */ - lanphy_modify_page_reg(phydev, 1, LAN8814_PD_CONTROLS, + lanphy_modify_page_reg(phydev, LAN8814_PAGE_AFE_PMA, LAN8814_PD_CONTROLS, LAN8814_PD_CONTROLS_PD_MEAS_TIME_MASK, LAN8814_PD_CONTROLS_PD_MEAS_TIME_VAL); } @@ -4289,7 +4413,7 @@ static int lan8814_probe(struct phy_device *phydev) /* Strap-in value for PHY address, below register read gives starting * phy address value */ - addr = lanphy_read_page_reg(phydev, 4, 0) & 0x1F; + addr = lanphy_read_page_reg(phydev, LAN8814_PAGE_COMMON_REGS, 0) & 0x1F; devm_phy_package_join(&phydev->mdio.dev, phydev, addr, sizeof(struct lan8814_shared_priv));

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Pasha Tatashin pasha.tatashin@soleen.com

commit e38f65d317df1fd2dcafe614d9c537475ecf9992 upstream.

Patch series "KHO: kfence + KHO memory corruption fix", v3.

This series fixes a memory corruption bug in KHO that occurs when KFENCE is enabled.

The root cause is that KHO metadata, allocated via kzalloc(), can be randomly serviced by kfence_alloc(). When a kernel boots via KHO, the early memblock allocator is restricted to a "scratch area". This forces the KFENCE pool to be allocated within this scratch area, creating a conflict. If KHO metadata is subsequently placed in this pool, it gets corrupted during the next kexec operation.

Google is using KHO and have had obscure crashes due to this memory corruption, with stacks all over the place. I would prefer this fix to be properly backported to stable so we can also automatically consume it once we switch to the upstream KHO.

Patch 1/3 introduces a debug-only feature (CONFIG_KEXEC_HANDOVER_DEBUG) that adds checks to detect and fail any operation that attempts to place KHO metadata or preserved memory within the scratch area. This serves as a validation and diagnostic tool to confirm the problem without affecting production builds.

Patch 2/3 Increases bitmap to PAGE_SIZE, so buddy allocator can be used.

Patch 3/3 Provides the fix by modifying KHO to allocate its metadata directly from the buddy allocator instead of slab. This bypasses the KFENCE interception entirely.

This patch (of 3):

It is invalid for KHO metadata or preserved memory regions to be located within the KHO scratch area, as this area is overwritten when the next kernel is loaded, and used early in boot by the next kernel. This can lead to memory corruption.

Add checks to kho_preserve_* and KHO's internal metadata allocators (xa_load_or_alloc, new_chunk) to verify that the physical address of the memory does not overlap with any defined scratch region. If an overlap is detected, the operation will fail and a WARN_ON is triggered. To avoid performance overhead in production kernels, these checks are enabled only when CONFIG_KEXEC_HANDOVER_DEBUG is selected.

[rppt@kernel.org: fix KEXEC_HANDOVER_DEBUG Kconfig dependency] Link: https://lkml.kernel.org/r/aQHUyyFtiNZhx8jo@kernel.org [pasha.tatashin@soleen.com: build fix] Link: https://lkml.kernel.org/r/CA+CK2bBnorfsTymKtv4rKvqGBHs=y=MjEMMRg_tE-RME6n-zU... Link: https://lkml.kernel.org/r/20251021000852.2924827-1-pasha.tatashin@soleen.com Link: https://lkml.kernel.org/r/20251021000852.2924827-2-pasha.tatashin@soleen.com Fixes: fc33e4b44b27 ("kexec: enable KHO support for memory preservation") Signed-off-by: Pasha Tatashin pasha.tatashin@soleen.com Signed-off-by: Mike Rapoport rppt@kernel.org Reviewed-by: Mike Rapoport (Microsoft) rppt@kernel.org Reviewed-by: Pratyush Yadav pratyush@kernel.org Cc: Alexander Graf graf@amazon.com Cc: Christian Brauner brauner@kernel.org Cc: David Matlack dmatlack@google.com Cc: Jason Gunthorpe jgg@ziepe.ca Cc: Jonathan Corbet corbet@lwn.net Cc: Masahiro Yamada masahiroy@kernel.org Cc: Miguel Ojeda ojeda@kernel.org Cc: Randy Dunlap rdunlap@infradead.org Cc: Samiullah Khawaja skhawaja@google.com Cc: Tejun Heo tj@kernel.org Cc: stable@vger.kernel.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- kernel/Kconfig.kexec | 9 ++++++ kernel/Makefile | 1 kernel/kexec_handover.c | 57 ++++++++++++++++++++++++++------------- kernel/kexec_handover_debug.c | 25 +++++++++++++++++ kernel/kexec_handover_internal.h | 20 +++++++++++++ 5 files changed, 93 insertions(+), 19 deletions(-) create mode 100644 kernel/kexec_handover_debug.c create mode 100644 kernel/kexec_handover_internal.h

--- a/kernel/Kconfig.kexec +++ b/kernel/Kconfig.kexec @@ -109,6 +109,15 @@ config KEXEC_HANDOVER to keep data or state alive across the kexec. For this to work, both source and target kernels need to have this option enabled.

+config KEXEC_HANDOVER_DEBUG + bool "Enable Kexec Handover debug checks" + depends on KEXEC_HANDOVER + help + This option enables extra sanity checks for the Kexec Handover + subsystem. Since, KHO performance is crucial in live update + scenarios and the extra code might be adding overhead it is + only optionally enabled. + config CRASH_DUMP bool "kernel crash dumps" default ARCH_DEFAULT_CRASH_DUMP --- a/kernel/Makefile +++ b/kernel/Makefile @@ -82,6 +82,7 @@ obj-$(CONFIG_KEXEC) += kexec.o obj-$(CONFIG_KEXEC_FILE) += kexec_file.o obj-$(CONFIG_KEXEC_ELF) += kexec_elf.o obj-$(CONFIG_KEXEC_HANDOVER) += kexec_handover.o +obj-$(CONFIG_KEXEC_HANDOVER_DEBUG) += kexec_handover_debug.o obj-$(CONFIG_BACKTRACE_SELF_TEST) += backtracetest.o obj-$(CONFIG_COMPAT) += compat.o obj-$(CONFIG_CGROUPS) += cgroup/ --- a/kernel/kexec_handover.c +++ b/kernel/kexec_handover.c @@ -8,6 +8,7 @@

#define pr_fmt(fmt) "KHO: " fmt

+#include <linux/cleanup.h> #include <linux/cma.h> #include <linux/count_zeros.h> #include <linux/debugfs.h> @@ -21,6 +22,7 @@

#include <asm/early_ioremap.h>

+#include "kexec_handover_internal.h" /* * KHO is tightly coupled with mm init and needs access to some of mm * internal APIs. @@ -93,26 +95,26 @@ struct kho_serialization {

static void *xa_load_or_alloc(struct xarray *xa, unsigned long index, size_t sz) { - void *elm, *res; + void *res = xa_load(xa, index);

- elm = xa_load(xa, index); - if (elm) - return elm; + if (res) + return res; + + void *elm __free(kfree) = kzalloc(sz, GFP_KERNEL);

- elm = kzalloc(sz, GFP_KERNEL); if (!elm) return ERR_PTR(-ENOMEM);

+ if (WARN_ON(kho_scratch_overlap(virt_to_phys(elm), sz))) + return ERR_PTR(-EINVAL); + res = xa_cmpxchg(xa, index, NULL, elm, GFP_KERNEL); if (xa_is_err(res)) - res = ERR_PTR(xa_err(res)); - - if (res) { - kfree(elm); + return ERR_PTR(xa_err(res)); + else if (res) return res; - }

- return elm; + return no_free_ptr(elm); }

static void __kho_unpreserve(struct kho_mem_track *track, unsigned long pfn, @@ -263,15 +265,19 @@ static_assert(sizeof(struct khoser_mem_c static struct khoser_mem_chunk *new_chunk(struct khoser_mem_chunk *cur_chunk, unsigned long order) { - struct khoser_mem_chunk *chunk; + struct khoser_mem_chunk *chunk __free(kfree) = NULL;

chunk = kzalloc(PAGE_SIZE, GFP_KERNEL); if (!chunk) - return NULL; + return ERR_PTR(-ENOMEM); + + if (WARN_ON(kho_scratch_overlap(virt_to_phys(chunk), PAGE_SIZE))) + return ERR_PTR(-EINVAL); + chunk->hdr.order = order; if (cur_chunk) KHOSER_STORE_PTR(cur_chunk->hdr.next, chunk); - return chunk; + return no_free_ptr(chunk); }

static void kho_mem_ser_free(struct khoser_mem_chunk *first_chunk) @@ -292,14 +298,17 @@ static int kho_mem_serialize(struct kho_ struct khoser_mem_chunk *chunk = NULL; struct kho_mem_phys *physxa; unsigned long order; + int err = -ENOMEM;

xa_for_each(&ser->track.orders, order, physxa) { struct kho_mem_phys_bits *bits; unsigned long phys;

chunk = new_chunk(chunk, order); - if (!chunk) + if (IS_ERR(chunk)) { + err = PTR_ERR(chunk); goto err_free; + }

if (!first_chunk) first_chunk = chunk; @@ -309,8 +318,10 @@ static int kho_mem_serialize(struct kho_

if (chunk->hdr.num_elms == ARRAY_SIZE(chunk->bitmaps)) { chunk = new_chunk(chunk, order); - if (!chunk) + if (IS_ERR(chunk)) { + err = PTR_ERR(chunk); goto err_free; + } }

elm = &chunk->bitmaps[chunk->hdr.num_elms]; @@ -327,7 +338,7 @@ static int kho_mem_serialize(struct kho_

err_free: kho_mem_ser_free(first_chunk); - return -ENOMEM; + return err; }

static void __init deserialize_bitmap(unsigned int order, @@ -380,8 +391,8 @@ static void __init kho_mem_deserialize(c * area for early allocations that happen before page allocator is * initialized. */ -static struct kho_scratch *kho_scratch; -static unsigned int kho_scratch_cnt; +struct kho_scratch *kho_scratch; +unsigned int kho_scratch_cnt;

/* * The scratch areas are scaled by default as percent of memory allocated from @@ -684,6 +695,9 @@ int kho_preserve_folio(struct folio *fol if (kho_out.finalized) return -EBUSY;

+ if (WARN_ON(kho_scratch_overlap(pfn << PAGE_SHIFT, PAGE_SIZE << order))) + return -EINVAL; + return __kho_preserve_order(track, pfn, order); } EXPORT_SYMBOL_GPL(kho_preserve_folio); @@ -713,6 +727,11 @@ int kho_preserve_phys(phys_addr_t phys, if (!PAGE_ALIGNED(phys) || !PAGE_ALIGNED(size)) return -EINVAL;

+ if (WARN_ON(kho_scratch_overlap(start_pfn << PAGE_SHIFT, + nr_pages << PAGE_SHIFT))) { + return -EINVAL; + } + while (pfn < end_pfn) { const unsigned int order = min(count_trailing_zeros(pfn), ilog2(end_pfn - pfn)); --- /dev/null +++ b/kernel/kexec_handover_debug.c @@ -0,0 +1,25 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * kexec_handover_debug.c - kexec handover optional debug functionality + * Copyright (C) 2025 Google LLC, Pasha Tatashin pasha.tatashin@soleen.com + */ + +#define pr_fmt(fmt) "KHO: " fmt + +#include "kexec_handover_internal.h" + +bool kho_scratch_overlap(phys_addr_t phys, size_t size) +{ + phys_addr_t scratch_start, scratch_end; + unsigned int i; + + for (i = 0; i < kho_scratch_cnt; i++) { + scratch_start = kho_scratch[i].addr; + scratch_end = kho_scratch[i].addr + kho_scratch[i].size; + + if (phys < scratch_end && (phys + size) > scratch_start) + return true; + } + + return false; +} --- /dev/null +++ b/kernel/kexec_handover_internal.h @@ -0,0 +1,20 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef LINUX_KEXEC_HANDOVER_INTERNAL_H +#define LINUX_KEXEC_HANDOVER_INTERNAL_H + +#include <linux/kexec_handover.h> +#include <linux/types.h> + +extern struct kho_scratch *kho_scratch; +extern unsigned int kho_scratch_cnt; + +#ifdef CONFIG_KEXEC_HANDOVER_DEBUG +bool kho_scratch_overlap(phys_addr_t phys, size_t size); +#else +static inline bool kho_scratch_overlap(phys_addr_t phys, size_t size) +{ + return false; +} +#endif /* CONFIG_KEXEC_HANDOVER_DEBUG */ + +#endif /* LINUX_KEXEC_HANDOVER_INTERNAL_H */

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Gao Xiang hsiangkao@linux.alibaba.com

[ Upstream commit f2a12cc3b97f062186568a7b94ddb7aa2ef68140 ]

Currently, the decompression logic incorrectly spins if compressed data is truncated in crafted (deliberately corrupted) images.

Fixes: 7c35de4df105 ("erofs: Zstandard compression support") Reported-by: Robert Morris rtm@csail.mit.edu Closes: https://lore.kernel.org/r/50958.1761605413@localhost Signed-off-by: Gao Xiang hsiangkao@linux.alibaba.com Reviewed-by: Chunhai Guo guochunhai@vivo.com Reviewed-by: Chao Yu chao@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- fs/erofs/decompressor_zstd.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/fs/erofs/decompressor_zstd.c b/fs/erofs/decompressor_zstd.c index b4bfe14229f9f..e38d93bb21048 100644 --- a/fs/erofs/decompressor_zstd.c +++ b/fs/erofs/decompressor_zstd.c @@ -172,7 +172,6 @@ static int z_erofs_zstd_decompress(struct z_erofs_decompress_req *rq, dctx.bounce = strm->bounce;

do { - dctx.avail_out = out_buf.size - out_buf.pos; dctx.inbuf_sz = in_buf.size; dctx.inbuf_pos = in_buf.pos; err = z_erofs_stream_switch_bufs(&dctx, &out_buf.dst, @@ -188,14 +187,18 @@ static int z_erofs_zstd_decompress(struct z_erofs_decompress_req *rq, in_buf.pos = dctx.inbuf_pos;

zerr = zstd_decompress_stream(stream, &out_buf, &in_buf); - if (zstd_is_error(zerr) || (!zerr && rq->outputsize)) { + dctx.avail_out = out_buf.size - out_buf.pos; + if (zstd_is_error(zerr) || + ((rq->outputsize + dctx.avail_out) && (!zerr || (zerr > 0 && + !(rq->inputsize + in_buf.size - in_buf.pos))))) { erofs_err(sb, "failed to decompress in[%u] out[%u]: %s", rq->inputsize, rq->outputsize, - zerr ? zstd_get_error_name(zerr) : "unexpected end of stream"); + zstd_is_error(zerr) ? zstd_get_error_name(zerr) : + "unexpected end of stream"); err = -EFSCORRUPTED; break; } - } while (rq->outputsize || out_buf.pos < out_buf.size); + } while (rq->outputsize + dctx.avail_out);

if (dctx.kout) kunmap_local(dctx.kout);

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Pasha Tatashin pasha.tatashin@soleen.com

commit a2fff99f92dae9c0eaf0d75de3def70ec68dad92 upstream.

KHO memory preservation metadata is preserved in 512 byte chunks which requires their allocation from slab allocator. Slabs are not safe to be used with KHO because of kfence, and because partial slabs may lead leaks to the next kernel. Change the size to be PAGE_SIZE.

The kfence specifically may cause memory corruption, where it randomly provides slab objects that can be within the scratch area. The reason for that is that kfence allocates its objects prior to KHO scratch is marked as CMA region.

While this change could potentially increase metadata overhead on systems with sparsely preserved memory, this is being mitigated by ongoing work to reduce sparseness during preservation via 1G guest pages. Furthermore, this change aligns with future work on a stateless KHO, which will also use page-sized bitmaps for its radix tree metadata.

Link: https://lkml.kernel.org/r/20251021000852.2924827-3-pasha.tatashin@soleen.com Fixes: fc33e4b44b27 ("kexec: enable KHO support for memory preservation") Signed-off-by: Pasha Tatashin pasha.tatashin@soleen.com Reviewed-by: Mike Rapoport (Microsoft) rppt@kernel.org Reviewed-by: Pratyush Yadav pratyush@kernel.org Cc: Alexander Graf graf@amazon.com Cc: Christian Brauner brauner@kernel.org Cc: David Matlack dmatlack@google.com Cc: Jason Gunthorpe jgg@ziepe.ca Cc: Jonathan Corbet corbet@lwn.net Cc: Masahiro Yamada masahiroy@kernel.org Cc: Miguel Ojeda ojeda@kernel.org Cc: Randy Dunlap rdunlap@infradead.org Cc: Samiullah Khawaja skhawaja@google.com Cc: Tejun Heo tj@kernel.org Cc: stable@vger.kernel.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- kernel/kexec_handover.c | 21 +++++++++++---------- 1 file changed, 11 insertions(+), 10 deletions(-)

--- a/kernel/kexec_handover.c +++ b/kernel/kexec_handover.c @@ -52,10 +52,10 @@ early_param("kho", kho_parse_enable); * Keep track of memory that is to be preserved across KHO. * * The serializing side uses two levels of xarrays to manage chunks of per-order - * 512 byte bitmaps. For instance if PAGE_SIZE = 4096, the entire 1G order of a - * 1TB system would fit inside a single 512 byte bitmap. For order 0 allocations - * each bitmap will cover 16M of address space. Thus, for 16G of memory at most - * 512K of bitmap memory will be needed for order 0. + * PAGE_SIZE byte bitmaps. For instance if PAGE_SIZE = 4096, the entire 1G order + * of a 8TB system would fit inside a single 4096 byte bitmap. For order 0 + * allocations each bitmap will cover 128M of address space. Thus, for 16G of + * memory at most 512K of bitmap memory will be needed for order 0. * * This approach is fully incremental, as the serialization progresses folios * can continue be aggregated to the tracker. The final step, immediately prior @@ -63,12 +63,14 @@ early_param("kho", kho_parse_enable); * successor kernel to parse. */

-#define PRESERVE_BITS (512 * 8) +#define PRESERVE_BITS (PAGE_SIZE * 8)

struct kho_mem_phys_bits { DECLARE_BITMAP(preserve, PRESERVE_BITS); };

+static_assert(sizeof(struct kho_mem_phys_bits) == PAGE_SIZE); + struct kho_mem_phys { /* * Points to kho_mem_phys_bits, a sparse bitmap array. Each bit is sized @@ -93,19 +95,19 @@ struct kho_serialization { struct khoser_mem_chunk *preserved_mem_map; };

-static void *xa_load_or_alloc(struct xarray *xa, unsigned long index, size_t sz) +static void *xa_load_or_alloc(struct xarray *xa, unsigned long index) { void *res = xa_load(xa, index);

if (res) return res;

- void *elm __free(kfree) = kzalloc(sz, GFP_KERNEL); + void *elm __free(kfree) = kzalloc(PAGE_SIZE, GFP_KERNEL);

if (!elm) return ERR_PTR(-ENOMEM);

- if (WARN_ON(kho_scratch_overlap(virt_to_phys(elm), sz))) + if (WARN_ON(kho_scratch_overlap(virt_to_phys(elm), PAGE_SIZE))) return ERR_PTR(-EINVAL);

res = xa_cmpxchg(xa, index, NULL, elm, GFP_KERNEL); @@ -175,8 +177,7 @@ static int __kho_preserve_order(struct k } }

- bits = xa_load_or_alloc(&physxa->phys_bits, pfn_high / PRESERVE_BITS, - sizeof(*bits)); + bits = xa_load_or_alloc(&physxa->phys_bits, pfn_high / PRESERVE_BITS); if (IS_ERR(bits)) return PTR_ERR(bits);

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Carolina Jubran cjubran@nvidia.com

[ Upstream commit 0bcd5b3b50cc1fcbf775479322cc37c15d35a489 ]

Assign the return value of mlx5_eswitch_block_mode() to 'err' before checking it to avoid returning an uninitialized error code.

Fixes: 22239eb258bc ("net/mlx5e: Prevent tunnel reformat when tunnel mode not allowed") Reported-by: kernel test robot lkp@intel.com Reported-by: Dan Carpenter dan.carpenter@linaro.org Closes: https://lore.kernel.org/r/202510271649.uwsIxD6O-lkp@intel.com/ Closes: http://lore.kernel.org/linux-rdma/aPIEK4rLB586FdDt@stanley.mountain/ Signed-off-by: Carolina Jubran cjubran@nvidia.com Reviewed-by: Jianbo Liu jianbol@nvidia.com Signed-off-by: Tariq Toukan tariqt@nvidia.com Link: https://patch.msgid.link/1762681073-1084058-2-git-send-email-tariqt@nvidia.c... Signed-off-by: Paolo Abeni pabeni@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c index 0a4fb8c922684..35d9530037a65 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c @@ -804,7 +804,8 @@ static int mlx5e_xfrm_add_state(struct net_device *dev, goto err_xfrm; }

- if (mlx5_eswitch_block_mode(priv->mdev)) + err = mlx5_eswitch_block_mode(priv->mdev); + if (err) goto unblock_ipsec;

if (x->props.mode == XFRM_MODE_TUNNEL &&

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Gal Pressman gal@nvidia.com

[ Upstream commit a7bf4d5063c7837096aab2853224eb23628514d9 ]

The previous calculation used roundup() which caused an overflow for rates between 25.5Gbps and 26Gbps. For example, a rate of 25.6Gbps would result in using 100Mbps units with value of 256, which would overflow the 8 bits field.

Simplify the upper_limit_mbps calculation by removing the unnecessary roundup, and adjust the comparison to use <= to correctly handle the boundary condition.

Fixes: d8880795dabf ("net/mlx5e: Implement DCBNL IEEE max rate") Signed-off-by: Gal Pressman gal@nvidia.com Reviewed-by: Nimrod Oren noren@nvidia.com Signed-off-by: Tariq Toukan tariqt@nvidia.com Link: https://patch.msgid.link/1762681073-1084058-4-git-send-email-tariqt@nvidia.c... Signed-off-by: Paolo Abeni pabeni@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c index d166c0d5189e1..3456144710528 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c @@ -595,18 +595,19 @@ static int mlx5e_dcbnl_ieee_setmaxrate(struct net_device *netdev, struct mlx5_core_dev *mdev = priv->mdev; u8 max_bw_value[IEEE_8021QAZ_MAX_TCS]; u8 max_bw_unit[IEEE_8021QAZ_MAX_TCS]; - __u64 upper_limit_mbps = roundup(255 * MLX5E_100MB, MLX5E_1GB); + __u64 upper_limit_mbps; int i;

memset(max_bw_value, 0, sizeof(max_bw_value)); memset(max_bw_unit, 0, sizeof(max_bw_unit)); + upper_limit_mbps = 255 * MLX5E_100MB;

for (i = 0; i <= mlx5_max_tc(mdev); i++) { if (!maxrate->tc_maxrate[i]) { max_bw_unit[i] = MLX5_BW_NO_LIMIT; continue; } - if (maxrate->tc_maxrate[i] < upper_limit_mbps) { + if (maxrate->tc_maxrate[i] <= upper_limit_mbps) { max_bw_value[i] = div_u64(maxrate->tc_maxrate[i], MLX5E_100MB); max_bw_value[i] = max_bw_value[i] ? max_bw_value[i] : 1;

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Joshua Rogers linux@joshua.hu

commit 98a5fd31cbf72d46bf18e50b3ab0ce86d5f319a9 upstream.

When the per-IP connection limit is exceeded in ksmbd_kthread_fn(), the code sets ret = -EAGAIN and continues the accept loop without closing the just-accepted socket. That leaks one socket per rejected attempt from a single IP and enables a trivial remote DoS.

Release client_sk before continuing.

This bug was found with ZeroPath.

Cc: stable@vger.kernel.org Signed-off-by: Joshua Rogers linux@joshua.hu Acked-by: Namjae Jeon linkinjeon@kernel.org Signed-off-by: Steve French stfrench@microsoft.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/smb/server/transport_tcp.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-)

--- a/fs/smb/server/transport_tcp.c +++ b/fs/smb/server/transport_tcp.c @@ -284,8 +284,11 @@ static int ksmbd_kthread_fn(void *p) } } up_read(&conn_list_lock); - if (ret == -EAGAIN) + if (ret == -EAGAIN) { + /* Per-IP limit hit: release the just-accepted socket. */ + sock_release(client_sk); continue; + }

skip_max_ip_conns_limit: if (server_conf.max_connections &&

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Xi Ruoyao xry111@xry111.site

[ Upstream commit fe4b3a34e9a9654d98d274218dac0270779db0ae ]

It's used to work around an objtool issue since commit abb2a5572264 ("LoongArch: Add cflag -fno-isolate-erroneous-paths-dereference"), but it's then passed to bindgen and cause an error because Clang does not have this option.

Fixes: abb2a5572264 ("LoongArch: Add cflag -fno-isolate-erroneous-paths-dereference") Acked-by: Miguel Ojeda ojeda@kernel.org Tested-by: Mingcong Bai jeffbai@aosc.io Signed-off-by: Xi Ruoyao xry111@xry111.site Signed-off-by: Huacai Chen chenhuacai@loongson.cn Signed-off-by: Sasha Levin sashal@kernel.org --- rust/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/rust/Makefile b/rust/Makefile index 9ec1119c02d39..403ce8518381d 100644 --- a/rust/Makefile +++ b/rust/Makefile @@ -299,7 +299,7 @@ bindgen_skip_c_flags := -mno-fp-ret-in-387 -mpreferred-stack-boundary=% \ -fno-inline-functions-called-once -fsanitize=bounds-strict \ -fstrict-flex-arrays=% -fmin-function-alignment=% \ -fzero-init-padding-bits=% -mno-fdpic \ - --param=% --param asan-% + --param=% --param asan-% -fno-isolate-erroneous-paths-dereference

# Derived from `scripts/Makefile.clang`. BINDGEN_TARGET_x86 := x86_64-linux-gnu

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Gal Pressman gal@nvidia.com

[ Upstream commit 43b27d1bd88a4bce34ec2437d103acfae9655f9e ]

Add validation to reject rates exceeding 255 Gbps that would overflow the 8 bits max bandwidth field.

Fixes: d8880795dabf ("net/mlx5e: Implement DCBNL IEEE max rate") Signed-off-by: Gal Pressman gal@nvidia.com Reviewed-by: Nimrod Oren noren@nvidia.com Signed-off-by: Tariq Toukan tariqt@nvidia.com Link: https://patch.msgid.link/1762681073-1084058-5-git-send-email-tariqt@nvidia.c... Signed-off-by: Paolo Abeni pabeni@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c index 3456144710528..d88a48210fdcb 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c @@ -596,11 +596,13 @@ static int mlx5e_dcbnl_ieee_setmaxrate(struct net_device *netdev, u8 max_bw_value[IEEE_8021QAZ_MAX_TCS]; u8 max_bw_unit[IEEE_8021QAZ_MAX_TCS]; __u64 upper_limit_mbps; + __u64 upper_limit_gbps; int i;

memset(max_bw_value, 0, sizeof(max_bw_value)); memset(max_bw_unit, 0, sizeof(max_bw_unit)); upper_limit_mbps = 255 * MLX5E_100MB; + upper_limit_gbps = 255 * MLX5E_1GB;

for (i = 0; i <= mlx5_max_tc(mdev); i++) { if (!maxrate->tc_maxrate[i]) { @@ -612,10 +614,16 @@ static int mlx5e_dcbnl_ieee_setmaxrate(struct net_device *netdev, MLX5E_100MB); max_bw_value[i] = max_bw_value[i] ? max_bw_value[i] : 1; max_bw_unit[i] = MLX5_100_MBPS_UNIT; - } else { + } else if (max_bw_value[i] <= upper_limit_gbps) { max_bw_value[i] = div_u64(maxrate->tc_maxrate[i], MLX5E_1GB); max_bw_unit[i] = MLX5_GBPS_UNIT; + } else { + netdev_err(netdev, + "tc_%d maxrate %llu Kbps exceeds limit %llu\n", + i, maxrate->tc_maxrate[i], + upper_limit_gbps); + return -EINVAL; } }

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Gautham R. Shenoy gautham.shenoy@amd.com

[ Upstream commit 6dd3b8a709a130a4d55c866af9804c81b8486d28 ]

per_cpu(cpc_desc_ptr, cpu) object is initialized for only the online CPUs via acpi_soft_cpu_online() --> __acpi_processor_start() --> acpi_cppc_processor_probe().

However the function acpi_cpc_valid() checks for the validity of the _CPC object for all the present CPUs. This breaks when the kernel is booted with "nosmt=force".

Hence check the validity of the _CPC objects of only the online CPUs.

Fixes: 2aeca6bd0277 ("ACPI: CPPC: Check present CPUs for determining _CPC is valid") Reported-by: Christopher Harris chris.harris79@gmail.com Closes: https://lore.kernel.org/lkml/CAM+eXpdDT7KjLV0AxEwOLkSJ2QtrsvGvjA2cCHvt1d0k2_... Suggested-by: Mario Limonciello mario.limonciello@amd.com Reviewed-by: "Mario Limonciello (AMD) (kernel.org)" superm1@kernel.org Tested-by: Chrisopher Harris chris.harris79@gmail.com Signed-off-by: Gautham R. Shenoy gautham.shenoy@amd.com Link: https://patch.msgid.link/20251107074145.2340-3-gautham.shenoy@amd.com Signed-off-by: Rafael J. Wysocki rafael.j.wysocki@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/acpi/cppc_acpi.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/acpi/cppc_acpi.c b/drivers/acpi/cppc_acpi.c index 6b649031808f8..6694412a1e139 100644 --- a/drivers/acpi/cppc_acpi.c +++ b/drivers/acpi/cppc_acpi.c @@ -460,7 +460,7 @@ bool acpi_cpc_valid(void) if (acpi_disabled) return false;

- for_each_present_cpu(cpu) { + for_each_online_cpu(cpu) { cpc_ptr = per_cpu(cpc_desc_ptr, cpu); if (!cpc_ptr) return false;

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Quanmin Yan yanquanmin1@huawei.com

commit 2f6ce7e714ef842e43120ecd6a7ed287b502026d upstream.

Patch series "mm/damon: fixes for the jiffies-related issues", v2.

On 32-bit systems, the kernel initializes jiffies to "-5 minutes" to make jiffies wrap bugs appear earlier. However, this may cause the time_before() series of functions to return unexpected values, resulting in DAMON not functioning as intended. Meanwhile, similar issues exist in some specific user operation scenarios.

This patchset addresses these issues. The first patch is about the DAMON_STAT module, and the second patch is about the core layer's sysfs.

This patch (of 2):

In DAMON_STAT's damon_stat_damon_call_fn(), time_before_eq() is used to avoid unnecessarily frequent stat update.

On 32-bit systems, the kernel initializes jiffies to "-5 minutes" to make jiffies wrap bugs appear earlier. However, this causes time_before_eq() in DAMON_STAT to unexpectedly return true during the first 5 minutes after boot on 32-bit systems (see [1] for more explanation, which fixes another jiffies-related issue before). As a result, DAMON_STAT does not update any monitoring results during that period, which becomes more confusing when DAMON_STAT_ENABLED_DEFAULT is enabled.

There is also an issue unrelated to the system's word size[2]: if the user stops DAMON_STAT just after last_refresh_jiffies is updated and restarts it after 5 seconds or a longer delay, last_refresh_jiffies will retain an older value, causing time_before_eq() to return false and the update to happen earlier than expected.

Fix these issues by making last_refresh_jiffies a global variable and initializing it each time DAMON_STAT is started.

Link: https://lkml.kernel.org/r/20251030020746.967174-2-yanquanmin1@huawei.com Link: https://lkml.kernel.org/r/20250822025057.1740854-1-ekffu200098@gmail.com [1] Link: https://lore.kernel.org/all/20251028143250.50144-1-sj@kernel.org/ [2] Fixes: fabdd1e911da ("mm/damon/stat: calculate and expose estimated memory bandwidth") Signed-off-by: Quanmin Yan yanquanmin1@huawei.com Suggested-by: SeongJae Park sj@kernel.org Reviewed-by: SeongJae Park sj@kernel.org Cc: Kefeng Wang wangkefeng.wang@huawei.com Cc: ze zuo zuoze1@huawei.com Cc: stable@vger.kernel.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- mm/damon/stat.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-)

--- a/mm/damon/stat.c +++ b/mm/damon/stat.c @@ -41,6 +41,8 @@ MODULE_PARM_DESC(memory_idle_ms_percenti

static struct damon_ctx *damon_stat_context;

+static unsigned long damon_stat_last_refresh_jiffies; + static void damon_stat_set_estimated_memory_bandwidth(struct damon_ctx *c) { struct damon_target *t; @@ -125,13 +127,12 @@ static void damon_stat_set_idletime_perc static int damon_stat_damon_call_fn(void *data) { struct damon_ctx *c = data; - static unsigned long last_refresh_jiffies;

/* avoid unnecessarily frequent stat update */ - if (time_before_eq(jiffies, last_refresh_jiffies + + if (time_before_eq(jiffies, damon_stat_last_refresh_jiffies + msecs_to_jiffies(5 * MSEC_PER_SEC))) return 0; - last_refresh_jiffies = jiffies; + damon_stat_last_refresh_jiffies = jiffies;

damon_stat_set_estimated_memory_bandwidth(c); damon_stat_set_idletime_percentiles(c); @@ -204,6 +205,8 @@ static int damon_stat_start(void) err = damon_start(&damon_stat_context, 1, true); if (err) return err; + + damon_stat_last_refresh_jiffies = jiffies; call_control.data = damon_stat_context; return damon_call(damon_stat_context, &call_control); }

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Cosmin Ratiu cratiu@nvidia.com

[ Upstream commit a315b723e87ba4e4573e1e5c759d512f38bdc0b3 ]

Completion queues (CQs) in mlx5 use the same global doorbell, which may become contended when accessed concurrently from many cores.

This patch prepares the CQ management code for supporting different doorbells per CQ. This will be used in downstream patches to allow separate doorbells to be used by channels CQs.

The main change is moving the 'uar' pointer from struct mlx5_core_cq to struct mlx5e_cq, as the uar page to be used is better off stored directly there. Other users of mlx5_core_cq also store the UAR to be used separately and therefore the pointer being removed is dead weight for them. As evidence, in this patch there are two users which set the mcq.uar pointer but didn't use it, Software Steering and old Innova CQ creation code. Instead, they rang the doorbell directly from another pointer.

The 'uar' pointer added to struct mlx5e_cq remains in a hot cacheline (as before), because it may get accessed for each packet.

Signed-off-by: Cosmin Ratiu cratiu@nvidia.com Reviewed-by: Dragos Tatulea dtatulea@nvidia.com Signed-off-by: Tariq Toukan tariqt@nvidia.com Reviewed-by: Simon Horman horms@kernel.org Signed-off-by: Jakub Kicinski kuba@kernel.org Stable-dep-of: e5eba42f0134 ("mlx5: Fix default values in create CQ") Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/mellanox/mlx5/core/cq.c | 1 - drivers/net/ethernet/mellanox/mlx5/core/en.h | 1 + drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h | 5 +---- drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 10 +++++++--- drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c | 1 - .../ethernet/mellanox/mlx5/core/steering/sws/dr_send.c | 1 - include/linux/mlx5/cq.h | 1 - 7 files changed, 9 insertions(+), 11 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cq.c b/drivers/net/ethernet/mellanox/mlx5/core/cq.c index 35039a95dcfd4..e9f319a9bdd6b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cq.c @@ -145,7 +145,6 @@ int mlx5_create_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq, mlx5_core_dbg(dev, "failed adding CP 0x%x to debug file system\n", cq->cqn);

- cq->uar = dev->priv.bfreg.up; cq->irqn = eq->core.irqn;

return 0; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index ff4a68648e604..4fc102d18354f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -344,6 +344,7 @@ struct mlx5e_cq { /* data path - accessed per napi poll */ u16 event_ctr; struct napi_struct *napi; + struct mlx5_uars_page *uar; struct mlx5_core_cq mcq; struct mlx5e_ch_stats *ch_stats;

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h index 5dc04bbfc71bb..6760bb0336df9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h @@ -309,10 +309,7 @@ mlx5e_notify_hw(struct mlx5_wq_cyc *wq, u16 pc, void __iomem *uar_map,

static inline void mlx5e_cq_arm(struct mlx5e_cq *cq) { - struct mlx5_core_cq *mcq; - - mcq = &cq->mcq; - mlx5_cq_arm(mcq, MLX5_CQ_DB_REQ_NOT, mcq->uar->map, cq->wq.cc); + mlx5_cq_arm(&cq->mcq, MLX5_CQ_DB_REQ_NOT, cq->uar->map, cq->wq.cc); }

static inline struct mlx5e_sq_dma * diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 1a90fd1d44edb..110d654796de9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -2201,6 +2201,7 @@ static void mlx5e_close_xdpredirect_sq(struct mlx5e_xdpsq *xdpsq) static int mlx5e_alloc_cq_common(struct mlx5_core_dev *mdev, struct net_device *netdev, struct workqueue_struct *workqueue, + struct mlx5_uars_page *uar, struct mlx5e_cq_param *param, struct mlx5e_cq *cq) { @@ -2232,6 +2233,7 @@ static int mlx5e_alloc_cq_common(struct mlx5_core_dev *mdev, cq->mdev = mdev; cq->netdev = netdev; cq->workqueue = workqueue; + cq->uar = uar;

return 0; } @@ -2247,7 +2249,8 @@ static int mlx5e_alloc_cq(struct mlx5_core_dev *mdev, param->wq.db_numa_node = ccp->node; param->eq_ix = ccp->ix;

- err = mlx5e_alloc_cq_common(mdev, ccp->netdev, ccp->wq, param, cq); + err = mlx5e_alloc_cq_common(mdev, ccp->netdev, ccp->wq, + mdev->priv.bfreg.up, param, cq);

cq->napi = ccp->napi; cq->ch_stats = ccp->ch_stats; @@ -2292,7 +2295,7 @@ static int mlx5e_create_cq(struct mlx5e_cq *cq, struct mlx5e_cq_param *param) MLX5_SET(cqc, cqc, cq_period_mode, mlx5e_cq_period_mode(param->cq_period_mode));

MLX5_SET(cqc, cqc, c_eqn_or_apu_element, eqn); - MLX5_SET(cqc, cqc, uar_page, mdev->priv.bfreg.up->index); + MLX5_SET(cqc, cqc, uar_page, cq->uar->index); MLX5_SET(cqc, cqc, log_page_size, cq->wq_ctrl.buf.page_shift - MLX5_ADAPTER_PAGE_SHIFT); MLX5_SET64(cqc, cqc, dbr_addr, cq->wq_ctrl.db.dma); @@ -3584,7 +3587,8 @@ static int mlx5e_alloc_drop_cq(struct mlx5e_priv *priv, param->wq.buf_numa_node = dev_to_node(mlx5_core_dma_dev(mdev)); param->wq.db_numa_node = dev_to_node(mlx5_core_dma_dev(mdev));

- return mlx5e_alloc_cq_common(priv->mdev, priv->netdev, priv->wq, param, cq); + return mlx5e_alloc_cq_common(priv->mdev, priv->netdev, priv->wq, + mdev->priv.bfreg.up, param, cq); }

int mlx5e_open_drop_rq(struct mlx5e_priv *priv, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c index c4de6bf8d1b65..cb1319974f83f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c @@ -475,7 +475,6 @@ static int mlx5_fpga_conn_create_cq(struct mlx5_fpga_conn *conn, int cq_size) *conn->cq.mcq.arm_db = 0; conn->cq.mcq.vector = 0; conn->cq.mcq.comp = mlx5_fpga_conn_cq_complete; - conn->cq.mcq.uar = fdev->conn_res.uar; tasklet_setup(&conn->cq.tasklet, mlx5_fpga_conn_cq_tasklet);

mlx5_fpga_dbg(fdev, "Created CQ #0x%x\n", conn->cq.mcq.cqn); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_send.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_send.c index 4fd4e8483382c..077a77fde670e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_send.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_send.c @@ -1131,7 +1131,6 @@ static struct mlx5dr_cq *dr_create_cq(struct mlx5_core_dev *mdev, *cq->mcq.arm_db = cpu_to_be32(2 << 28);

cq->mcq.vector = 0; - cq->mcq.uar = uar; cq->mdev = mdev;

return cq; diff --git a/include/linux/mlx5/cq.h b/include/linux/mlx5/cq.h index 991526039ccbd..7ef2c7c7d803d 100644 --- a/include/linux/mlx5/cq.h +++ b/include/linux/mlx5/cq.h @@ -41,7 +41,6 @@ struct mlx5_core_cq { int cqe_sz; __be32 *set_ci_db; __be32 *arm_db; - struct mlx5_uars_page *uar; refcount_t refcount; struct completion free; unsigned vector;

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Gautham R. Shenoy gautham.shenoy@amd.com

[ Upstream commit 0fce75870666b46b700cfbd3216380b422f975da ]

per_cpu(cpc_desc_ptr, cpu) object is initialized for only the online CPU via acpi_soft_cpu_online() --> __acpi_processor_start() --> acpi_cppc_processor_probe().

However the function cppc_perf_ctrs_in_pcc() checks if the CPPC perf-ctrs are in a PCC region for all the present CPUs, which breaks when the kernel is booted with "nosmt=force".

Hence, limit the check only to the online CPUs.

Fixes: ae2df912d1a5 ("ACPI: CPPC: Disable FIE if registers in PCC regions") Reviewed-by: "Mario Limonciello (AMD) (kernel.org)" superm1@kernel.org Signed-off-by: Gautham R. Shenoy gautham.shenoy@amd.com Link: https://patch.msgid.link/20251107074145.2340-5-gautham.shenoy@amd.com Signed-off-by: Rafael J. Wysocki rafael.j.wysocki@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/acpi/cppc_acpi.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/acpi/cppc_acpi.c b/drivers/acpi/cppc_acpi.c index 51e925f289bf3..002c3dde283ff 100644 --- a/drivers/acpi/cppc_acpi.c +++ b/drivers/acpi/cppc_acpi.c @@ -1435,7 +1435,7 @@ bool cppc_perf_ctrs_in_pcc(void) { int cpu;

- for_each_present_cpu(cpu) { + for_each_online_cpu(cpu) { struct cpc_register_resource *ref_perf_reg; struct cpc_desc *cpc_desc;

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Pauli Virtanen pav@iki.fi

[ Upstream commit e060088db0bdf7932e0e3c2d24b7371c4c5b867c ]

l2cap_chan_put() is exported, so export also l2cap_chan_hold() for modules.

l2cap_chan_hold() has use case in net/bluetooth/6lowpan.c

Signed-off-by: Pauli Virtanen pav@iki.fi Reviewed-by: Paul Menzel pmenzel@molgen.mpg.de Signed-off-by: Luiz Augusto von Dentz luiz.von.dentz@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- net/bluetooth/l2cap_core.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index d08320380ad67..35c57657bcf4e 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -497,6 +497,7 @@ void l2cap_chan_hold(struct l2cap_chan *c)

kref_get(&c->kref); } +EXPORT_SYMBOL_GPL(l2cap_chan_hold);

struct l2cap_chan *l2cap_chan_hold_unless_zero(struct l2cap_chan *c) {

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Wei Yang albinwyang@tencent.com

commit 895b4c0c79b092d732544011c3cecaf7322c36a1 upstream.

Pde is erased from subdir rbtree through rb_erase(), but not set the node to EMPTY, which may result in uaf access. We should use RB_CLEAR_NODE() set the erased node to EMPTY, then pde_subdir_next() will return NULL to avoid uaf access.

We found an uaf issue while using stress-ng testing, need to run testcase getdent and tun in the same time. The steps of the issue is as follows:

1) use getdent to traverse dir /proc/pid/net/dev_snmp6/, and current pde is tun3;

2) in the [time windows] unregister netdevice tun3 and tun2, and erase them from rbtree. erase tun3 first, and then erase tun2. the pde(tun2) will be released to slab;

3) continue to getdent process, then pde_subdir_next() will return pde(tun2) which is released, it will case uaf access.

CPU 0 | CPU 1 ------------------------------------------------------------------------- traverse dir /proc/pid/net/dev_snmp6/ | unregister_netdevice(tun->dev) //tun3 tun2 sys_getdents64() | iterate_dir() | proc_readdir() | proc_readdir_de() | snmp6_unregister_dev() pde_get(de); | proc_remove() read_unlock(&proc_subdir_lock); | remove_proc_subtree() | write_lock(&proc_subdir_lock); [time window] | rb_erase(&root->subdir_node, &parent->subdir); | write_unlock(&proc_subdir_lock); read_lock(&proc_subdir_lock); | next = pde_subdir_next(de); | pde_put(de); | de = next; //UAF |

rbtree of dev_snmp6 | pde(tun3) / \ NULL pde(tun2)

Link: https://lkml.kernel.org/r/20251025024233.158363-1-albin_yang@163.com Signed-off-by: Wei Yang albinwyang@tencent.com Cc: Al Viro viro@zeniv.linux.org.uk Cc: Christian Brauner brauner@kernel.org Cc: wangzijie wangzijie1@honor.com Cc: Alexey Dobriyan adobriyan@gmail.com Cc: stable@vger.kernel.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/proc/generic.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-)

--- a/fs/proc/generic.c +++ b/fs/proc/generic.c @@ -698,6 +698,12 @@ void pde_put(struct proc_dir_entry *pde) } }

+static void pde_erase(struct proc_dir_entry *pde, struct proc_dir_entry *parent) +{ + rb_erase(&pde->subdir_node, &parent->subdir); + RB_CLEAR_NODE(&pde->subdir_node); +} + /* * Remove a /proc entry and free it if it's not currently in use. */ @@ -720,7 +726,7 @@ void remove_proc_entry(const char *name, WARN(1, "removing permanent /proc entry '%s'", de->name); de = NULL; } else { - rb_erase(&de->subdir_node, &parent->subdir); + pde_erase(de, parent); if (S_ISDIR(de->mode)) parent->nlink--; } @@ -764,7 +770,7 @@ int remove_proc_subtree(const char *name root->parent->name, root->name); return -EINVAL; } - rb_erase(&root->subdir_node, &parent->subdir); + pde_erase(root, parent);

de = root; while (1) { @@ -776,7 +782,7 @@ int remove_proc_subtree(const char *name next->parent->name, next->name); return -EINVAL; } - rb_erase(&next->subdir_node, &de->subdir); + pde_erase(next, de); de = next; continue; }

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Steven Rostedt rostedt@goodmis.org

commit dd4adb986a86727ed8f56c48b6d0695f1e211e65 upstream.

The tracing selftest "event-filter-function.tc" was failing because it first runs the "sample_events" function that triggers the kmem_cache_free event and it looks at what function was used during a call to "ls".

But the first time it calls this, it could trigger events that are used to pull pages into the page cache.

The rest of the test uses the function it finds during that call to see if it will be called in subsequent "sample_events" calls. But if there's no need to pull pages into the page cache, it will not trigger that function and the test will fail.

Call the "sample_events" twice to trigger all the page cache work before it calls it to find a function to use in subsequent checks.

Cc: stable@vger.kernel.org Fixes: eb50d0f250e96 ("selftests/ftrace: Choose target function for filter test from samples") Signed-off-by: Steven Rostedt (Google) rostedt@goodmis.org Acked-by: Masami Hiramatsu (Google) mhiramat@kernel.org Signed-off-by: Shuah Khan skhan@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- tools/testing/selftests/ftrace/test.d/filter/event-filter-function.tc | 4 ++++ 1 file changed, 4 insertions(+)

--- a/tools/testing/selftests/ftrace/test.d/filter/event-filter-function.tc +++ b/tools/testing/selftests/ftrace/test.d/filter/event-filter-function.tc @@ -20,6 +20,10 @@ sample_events() { echo 0 > tracing_on echo 0 > events/enable

+# Clear functions caused by page cache; run sample_events twice +sample_events +sample_events + echo "Get the most frequently calling function" echo > trace sample_events

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Haotian Zhang vulab@iscas.ac.cn

[ Upstream commit 6b6eddc63ce871897d3a5bc4f8f593e698aef104 ]

The probe function enables regulators at the beginning but fails to disable them in its error handling path. If any operation after enabling the regulators fails, the probe will exit with an error, leaving the regulators permanently enabled, which could lead to a resource leak.

Add a proper error handling path to call regulator_bulk_disable() before returning an error.

Fixes: 9a397f473657 ("ASoC: cs4271: add regulator consumer support") Signed-off-by: Haotian Zhang vulab@iscas.ac.cn Reviewed-by: Charles Keepax ckeepax@opensource.cirrus.com Link: https://patch.msgid.link/20251105062246.1955-1-vulab@iscas.ac.cn Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- sound/soc/codecs/cs4271.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/sound/soc/codecs/cs4271.c b/sound/soc/codecs/cs4271.c index 6a3cca3d26c7e..ead447a5da7f8 100644 --- a/sound/soc/codecs/cs4271.c +++ b/sound/soc/codecs/cs4271.c @@ -581,17 +581,17 @@ static int cs4271_component_probe(struct snd_soc_component *component)

ret = regcache_sync(cs4271->regmap); if (ret < 0) - return ret; + goto err_disable_regulator;

ret = regmap_update_bits(cs4271->regmap, CS4271_MODE2, CS4271_MODE2_PDN | CS4271_MODE2_CPEN, CS4271_MODE2_PDN | CS4271_MODE2_CPEN); if (ret < 0) - return ret; + goto err_disable_regulator; ret = regmap_update_bits(cs4271->regmap, CS4271_MODE2, CS4271_MODE2_PDN, 0); if (ret < 0) - return ret; + goto err_disable_regulator; /* Power-up sequence requires 85 uS */ udelay(85);

@@ -601,6 +601,10 @@ static int cs4271_component_probe(struct snd_soc_component *component) CS4271_MODE2_MUTECAEQUB);

return 0; + +err_disable_regulator: + regulator_bulk_disable(ARRAY_SIZE(cs4271->supplies), cs4271->supplies); + return ret; }

static void cs4271_component_remove(struct snd_soc_component *component)

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Shuai Xue xueshuai@linux.alibaba.com

[ Upstream commit 7c3643f204edf1c5edb12b36b34838683ee5f8dc ]

The Generic Initiator Affinity Structure in SRAT table uses device handle type field to indicate the device type. According to ACPI specification, the device handle type value of 1 represents PCI device, not 0.

Fixes: 894c26a1c274 ("ACPI: Support Generic Initiator only domains") Reported-by: Wu Zongyong wuzongyong@linux.alibaba.com Signed-off-by: Shuai Xue xueshuai@linux.alibaba.com Reviewed-by: Jonathan Cameron jonathan.cameron@huawei.com Link: https://patch.msgid.link/20250913023224.39281-1-xueshuai@linux.alibaba.com Signed-off-by: Dave Jiang dave.jiang@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/acpi/numa/srat.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/acpi/numa/srat.c b/drivers/acpi/numa/srat.c index 53816dfab6452..aa87ee1583a4e 100644 --- a/drivers/acpi/numa/srat.c +++ b/drivers/acpi/numa/srat.c @@ -237,7 +237,7 @@ acpi_table_print_srat_entry(struct acpi_subtable_header *header) struct acpi_srat_generic_affinity *p = (struct acpi_srat_generic_affinity *)header;

- if (p->device_handle_type == 0) { + if (p->device_handle_type == 1) { /* * For pci devices this may be the only place they * are assigned a proximity domain

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ian Forbes ian.forbes@broadcom.com

[ Upstream commit 32b415a9dc2c212e809b7ebc2b14bc3fbda2b9af ]

This data originates from userspace and is used in buffer offset calculations which could potentially overflow causing an out-of-bounds access.

Fixes: 8ce75f8ab904 ("drm/vmwgfx: Update device includes for DX device functionality") Reported-by: Rohit Keshri rkeshri@redhat.com Signed-off-by: Ian Forbes ian.forbes@broadcom.com Reviewed-by: Maaz Mombasawala maaz.mombasawala@broadcom.com Signed-off-by: Zack Rusin zack.rusin@broadcom.com Link: https://patch.msgid.link/20251021190128.13014-1-ian.forbes@broadcom.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c | 5 +++++ 1 file changed, 5 insertions(+)

diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c index d539f25b5fbe0..3057f8baa7d25 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c @@ -3668,6 +3668,11 @@ static int vmw_cmd_check(struct vmw_private *dev_priv,

cmd_id = header->id; + if (header->size > SVGA_CMD_MAX_DATASIZE) { + VMW_DEBUG_USER("SVGA3D command: %d is too big.\n", + cmd_id + SVGA_3D_CMD_BASE); + return -E2BIG; + } *size = header->size + sizeof(SVGA3dCmdHeader);

cmd_id -= SVGA_3D_CMD_BASE;

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Johannes Berg johannes.berg@intel.com

commit a9da90e618cd0669a22bcc06a96209db5dd96e9b upstream.

While connecting, the MAC address can already no longer be changed. The change is already rejected if netif_carrier_ok(), but of course that's not true yet while connecting. Check for auth_data or assoc_data, so the MAC address cannot be changed.

Also more comprehensively check that there are no stations on the interface being changed - if any peer station is added it will know about our address already, so we cannot change it.

Cc: stable@vger.kernel.org Fixes: 3c06e91b40db ("wifi: mac80211: Support POWERED_ADDR_CHANGE feature") Link: https://patch.msgid.link/20251105154119.f9f6c1df81bb.I9bb3760ede650fb96588be... Signed-off-by: Johannes Berg johannes.berg@intel.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/mac80211/iface.c | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-)

--- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -223,6 +223,10 @@ static int ieee80211_can_powered_addr_ch if (netif_carrier_ok(sdata->dev)) return -EBUSY;

+ /* if any stations are set known (so they know this vif too), reject */ + if (sta_info_get_by_idx(sdata, 0)) + return -EBUSY; + /* First check no ROC work is happening on this iface */ list_for_each_entry(roc, &local->roc_list, list) { if (roc->sdata != sdata) @@ -242,12 +246,16 @@ static int ieee80211_can_powered_addr_ch ret = -EBUSY; }

+ /* + * More interface types could be added here but changing the + * address while powered makes the most sense in client modes. + */ switch (sdata->vif.type) { case NL80211_IFTYPE_STATION: case NL80211_IFTYPE_P2P_CLIENT: - /* More interface types could be added here but changing the - * address while powered makes the most sense in client modes. - */ + /* refuse while connecting */ + if (sdata->u.mgd.auth_data || sdata->u.mgd.assoc_data) + return -EBUSY; break; default: ret = -EOPNOTSUPP;

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Sourabh Jain sourabhjain@linux.ibm.com

commit 00fbff75c5acb4755f06f08bd1071879c63940c5 upstream.

When crashkernel is configured with a high reservation, shrinking its value below the low crashkernel reservation causes two issues:

1. Invalid crashkernel resource objects 2. Kernel crash if crashkernel shrinking is done twice

For example, with crashkernel=200M,high, the kernel reserves 200MB of high memory and some default low memory (say 256MB). The reservation appears as:

cat /proc/iomem | grep -i crash af000000-beffffff : Crash kernel 433000000-43f7fffff : Crash kernel

If crashkernel is then shrunk to 50MB (echo 52428800 > /sys/kernel/kexec_crash_size), /proc/iomem still shows 256MB reserved: af000000-beffffff : Crash kernel

Instead, it should show 50MB: af000000-b21fffff : Crash kernel

Further shrinking crashkernel to 40MB causes a kernel crash with the following trace (x86):

BUG: kernel NULL pointer dereference, address: 0000000000000038 PGD 0 P4D 0 Oops: 0000 [#1] PREEMPT SMP NOPTI <snip...> Call Trace: <TASK> ? __die_body.cold+0x19/0x27 ? page_fault_oops+0x15a/0x2f0 ? search_module_extables+0x19/0x60 ? search_bpf_extables+0x5f/0x80 ? exc_page_fault+0x7e/0x180 ? asm_exc_page_fault+0x26/0x30 ? __release_resource+0xd/0xb0 release_resource+0x26/0x40 __crash_shrink_memory+0xe5/0x110 crash_shrink_memory+0x12a/0x190 kexec_crash_size_store+0x41/0x80 kernfs_fop_write_iter+0x141/0x1f0 vfs_write+0x294/0x460 ksys_write+0x6d/0xf0 <snip...>

This happens because __crash_shrink_memory()/kernel/crash_core.c incorrectly updates the crashk_res resource object even when crashk_low_res should be updated.

Fix this by ensuring the correct crashkernel resource object is updated when shrinking crashkernel memory.

Link: https://lkml.kernel.org/r/20251101193741.289252-1-sourabhjain@linux.ibm.com Fixes: 16c6006af4d4 ("kexec: enable kexec_crash_size to support two crash kernel regions") Signed-off-by: Sourabh Jain sourabhjain@linux.ibm.com Acked-by: Baoquan He bhe@redhat.com Cc: Zhen Lei thunder.leizhen@huawei.com Cc: stable@vger.kernel.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- kernel/crash_core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/kernel/crash_core.c +++ b/kernel/crash_core.c @@ -367,7 +367,7 @@ static int __crash_shrink_memory(struct old_res->start = 0; old_res->end = 0; } else { - crashk_res.end = ram_res->start - 1; + old_res->end = ram_res->start - 1; }

crash_free_reserved_phys_range(ram_res->start, ram_res->end);

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Dai Ngo dai.ngo@oracle.com

[ Upstream commit b623390045a81fc559decb9bfeb79319721d3dfb ]

The utimes01 and utime06 tests fail when delegated timestamps are enabled, specifically in subtests that modify the atime and mtime fields using the 'nobody' user ID.

The problem can be reproduced as follow:

# echo "/media *(rw,no_root_squash,sync)" >> /etc/exports # export -ra # mount -o rw,nfsvers=4.2 127.0.0.1:/media /tmpdir # cd /opt/ltp # ./runltp -d /tmpdir -s utimes01 # ./runltp -d /tmpdir -s utime06

This issue occurs because nfs_setattr does not verify the inode's UID against the caller's fsuid when delegated timestamps are permitted for the inode.

This patch adds the UID check and if it does not match then the request is sent to the server for permission checking.

Fixes: e12912d94137 ("NFSv4: Add support for delegated atime and mtime attributes") Signed-off-by: Dai Ngo dai.ngo@oracle.com Signed-off-by: Anna Schumaker anna.schumaker@oracle.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/nfs/inode.c | 18 ++++++++++++------ 1 file changed, 12 insertions(+), 6 deletions(-)

diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 49df9debb1a69..35bdb49236bac 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -718,6 +718,8 @@ nfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct nfs_fattr *fattr; loff_t oldsize = i_size_read(inode); int error = 0; + kuid_t task_uid = current_fsuid(); + kuid_t owner_uid = inode->i_uid;

nfs_inc_stats(inode, NFSIOS_VFSSETATTR);

@@ -739,9 +741,11 @@ nfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, if (nfs_have_delegated_mtime(inode) && attr->ia_valid & ATTR_MTIME) { spin_lock(&inode->i_lock); if (attr->ia_valid & ATTR_MTIME_SET) { - nfs_set_timestamps_to_ts(inode, attr); - attr->ia_valid &= ~(ATTR_MTIME|ATTR_MTIME_SET| + if (uid_eq(task_uid, owner_uid)) { + nfs_set_timestamps_to_ts(inode, attr); + attr->ia_valid &= ~(ATTR_MTIME|ATTR_MTIME_SET| ATTR_ATIME|ATTR_ATIME_SET); + } } else { nfs_update_timestamps(inode, attr->ia_valid); attr->ia_valid &= ~(ATTR_MTIME|ATTR_ATIME); @@ -751,10 +755,12 @@ nfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, attr->ia_valid & ATTR_ATIME && !(attr->ia_valid & ATTR_MTIME)) { if (attr->ia_valid & ATTR_ATIME_SET) { - spin_lock(&inode->i_lock); - nfs_set_timestamps_to_ts(inode, attr); - spin_unlock(&inode->i_lock); - attr->ia_valid &= ~(ATTR_ATIME|ATTR_ATIME_SET); + if (uid_eq(task_uid, owner_uid)) { + spin_lock(&inode->i_lock); + nfs_set_timestamps_to_ts(inode, attr); + spin_unlock(&inode->i_lock); + attr->ia_valid &= ~(ATTR_ATIME|ATTR_ATIME_SET); + } } else { nfs_update_delegated_atime(inode); attr->ia_valid &= ~ATTR_ATIME;

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Johannes Berg johannes.berg@intel.com

[ Upstream commit 3592c0083fb29cca13cd9978b8844d58b4eff548 ]

During the development of the rate changes, I evidently made some changes that shouldn't have been there; beacon templates with rate_n_flags are only in old versions, so no changes to them should have been necessary, and evidently broke on some devices. This also would have broken fixed (injection) rates, it would seem. Restore the old handling of this.

Fixes: dabc88cb3b78 ("wifi: iwlwifi: handle v3 rates") Closes: https://bugzilla.kernel.org/show_bug.cgi?id=220558 Reviewed-by: Benjamin Berg benjamin.berg@intel.com Signed-off-by: Johannes Berg johannes.berg@intel.com Link: https://patch.msgid.link/20251008112044.3bb8ea849d8d.I90f4d2b2c1f62eaedaf304... Signed-off-by: Miri Korenblit miriam.rachel.korenblit@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c | 13 +++---------- drivers/net/wireless/intel/iwlwifi/mvm/utils.c | 12 +++++++++--- 2 files changed, 12 insertions(+), 13 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c index 8805ab344895a..0065c2ead56b1 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c @@ -938,19 +938,12 @@ u8 iwl_mvm_mac_ctxt_get_lowest_rate(struct iwl_mvm *mvm,

u16 iwl_mvm_mac_ctxt_get_beacon_flags(const struct iwl_fw *fw, u8 rate_idx) { + u16 flags = iwl_mvm_mac80211_idx_to_hwrate(fw, rate_idx); bool is_new_rate = iwl_fw_lookup_cmd_ver(fw, BEACON_TEMPLATE_CMD, 0) > 10; - u16 flags, cck_flag; - - if (is_new_rate) { - flags = iwl_mvm_mac80211_idx_to_hwrate(fw, rate_idx); - cck_flag = IWL_MAC_BEACON_CCK; - } else { - cck_flag = IWL_MAC_BEACON_CCK_V1; - flags = iwl_fw_rate_idx_to_plcp(rate_idx); - }

if (rate_idx <= IWL_LAST_CCK_RATE) - flags |= cck_flag; + flags |= is_new_rate ? IWL_MAC_BEACON_CCK + : IWL_MAC_BEACON_CCK_V1;

return flags; } diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/utils.c b/drivers/net/wireless/intel/iwlwifi/mvm/utils.c index 62da0132f3838..a62f5288dfd06 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/utils.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/utils.c @@ -169,9 +169,15 @@ int iwl_mvm_legacy_rate_to_mac80211_idx(u32 rate_n_flags,

u8 iwl_mvm_mac80211_idx_to_hwrate(const struct iwl_fw *fw, int rate_idx) { - return (rate_idx >= IWL_FIRST_OFDM_RATE ? - rate_idx - IWL_FIRST_OFDM_RATE : - rate_idx); + if (iwl_fw_lookup_cmd_ver(fw, TX_CMD, 0) > 8) + /* In the new rate legacy rates are indexed: + * 0 - 3 for CCK and 0 - 7 for OFDM. + */ + return (rate_idx >= IWL_FIRST_OFDM_RATE ? + rate_idx - IWL_FIRST_OFDM_RATE : + rate_idx); + + return iwl_fw_rate_idx_to_plcp(rate_idx); }

u8 iwl_mvm_mac80211_ac_to_ucode_ac(enum ieee80211_ac_numbers ac)

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Andrei Vagin avagin@google.com

[ Upstream commit 78f0e33cd6c939a555aa80dbed2fec6b333a7660 ]

grab_requested_mnt_ns was changed to return error codes on failure, but its callers were not updated to check for error pointers, still checking only for a NULL return value.

This commit updates the callers to use IS_ERR() or IS_ERR_OR_NULL() and PTR_ERR() to correctly check for and propagate errors.

This also makes sure that the logic actually works and mount namespace file descriptors can be used to refere to mounts.

Christian Brauner brauner@kernel.org says:

Rework the patch to be more ergonomic and in line with our overall error handling patterns.

Fixes: 7b9d14af8777 ("fs: allow mount namespace fd") Cc: Christian Brauner brauner@kernel.org Signed-off-by: Andrei Vagin avagin@google.com Link: https://patch.msgid.link/20251111062815.2546189-1-avagin@google.com Reviewed-by: Jan Kara jack@suse.cz Signed-off-by: Christian Brauner brauner@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- fs/namespace.c | 32 ++++++++++++++++---------------- include/uapi/linux/mount.h | 2 +- 2 files changed, 17 insertions(+), 17 deletions(-)

diff --git a/fs/namespace.c b/fs/namespace.c index fa7c034ac4a69..0026a6e7730e9 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -186,7 +186,8 @@ static void mnt_ns_release(struct mnt_namespace *ns) kfree(ns); } } -DEFINE_FREE(mnt_ns_release, struct mnt_namespace *, if (_T) mnt_ns_release(_T)) +DEFINE_FREE(mnt_ns_release, struct mnt_namespace *, + if (!IS_ERR(_T)) mnt_ns_release(_T))

static void mnt_ns_release_rcu(struct rcu_head *rcu) { @@ -5881,7 +5882,7 @@ static int copy_mnt_id_req(const struct mnt_id_req __user *req, ret = copy_struct_from_user(kreq, sizeof(*kreq), req, usize); if (ret) return ret; - if (kreq->spare != 0) + if (kreq->mnt_ns_fd != 0 && kreq->mnt_ns_id) return -EINVAL; /* The first valid unique mount id is MNT_UNIQUE_ID_OFFSET + 1. */ if (kreq->mnt_id <= MNT_UNIQUE_ID_OFFSET) @@ -5898,16 +5899,12 @@ static struct mnt_namespace *grab_requested_mnt_ns(const struct mnt_id_req *kreq { struct mnt_namespace *mnt_ns;

- if (kreq->mnt_ns_id && kreq->spare) - return ERR_PTR(-EINVAL); - - if (kreq->mnt_ns_id) - return lookup_mnt_ns(kreq->mnt_ns_id); - - if (kreq->spare) { + if (kreq->mnt_ns_id) { + mnt_ns = lookup_mnt_ns(kreq->mnt_ns_id); + } else if (kreq->mnt_ns_fd) { struct ns_common *ns;

- CLASS(fd, f)(kreq->spare); + CLASS(fd, f)(kreq->mnt_ns_fd); if (fd_empty(f)) return ERR_PTR(-EBADF);

@@ -5922,6 +5919,8 @@ static struct mnt_namespace *grab_requested_mnt_ns(const struct mnt_id_req *kreq } else { mnt_ns = current->nsproxy->mnt_ns; } + if (!mnt_ns) + return ERR_PTR(-ENOENT);

refcount_inc(&mnt_ns->passive); return mnt_ns; @@ -5946,8 +5945,8 @@ SYSCALL_DEFINE4(statmount, const struct mnt_id_req __user *, req, return ret;

ns = grab_requested_mnt_ns(&kreq); - if (!ns) - return -ENOENT; + if (IS_ERR(ns)) + return PTR_ERR(ns);

if (kreq.mnt_ns_id && (ns != current->nsproxy->mnt_ns) && !ns_capable_noaudit(ns->user_ns, CAP_SYS_ADMIN)) @@ -6056,8 +6055,8 @@ static void __free_klistmount_free(const struct klistmount *kls) static inline int prepare_klistmount(struct klistmount *kls, struct mnt_id_req *kreq, size_t nr_mnt_ids) { - u64 last_mnt_id = kreq->param; + struct mnt_namespace *ns;

/* The first valid unique mount id is MNT_UNIQUE_ID_OFFSET + 1. */ if (last_mnt_id != 0 && last_mnt_id <= MNT_UNIQUE_ID_OFFSET) @@ -6071,9 +6070,10 @@ static inline int prepare_klistmount(struct klistmount *kls, struct mnt_id_req * if (!kls->kmnt_ids) return -ENOMEM;

- kls->ns = grab_requested_mnt_ns(kreq); - if (!kls->ns) - return -ENOENT; + ns = grab_requested_mnt_ns(kreq); + if (IS_ERR(ns)) + return PTR_ERR(ns); + kls->ns = ns;

kls->mnt_parent_id = kreq->mnt_id; return 0; diff --git a/include/uapi/linux/mount.h b/include/uapi/linux/mount.h index 7fa67c2031a5d..5d3f8c9e3a625 100644 --- a/include/uapi/linux/mount.h +++ b/include/uapi/linux/mount.h @@ -197,7 +197,7 @@ struct statmount { */ struct mnt_id_req { __u32 size; - __u32 spare; + __u32 mnt_ns_fd; __u64 mnt_id; __u64 param; __u64 mnt_ns_id;

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Thomas Falcon thomas.falcon@intel.com

[ Upstream commit 85c894a80ac46aa177df04e0a33bcad409b7d64f ]

With commit f0d0f978f3f5830a ("perf header: Don't write empty BPF/BTF info"), the write_bpf_( prog_info() | btf() ) functions exit without writing anything if env->bpf_prog.(infos| btfs)_cnt is zero.

process_bpf_( prog_info() | btf() ), however, still expect a "count" value to exist in the data file. If btf information is empty, for example, process_bpf_btf will read garbage or some other data as the number of btf nodes in the data file. As a result, the data file will not be processed correctly.

Instead, write the count to the data file and exit if it is zero.

Fixes: f0d0f978f3f5830a ("perf header: Don't write empty BPF/BTF info") Reviewed-by: Ian Rogers irogers@google.com Signed-off-by: Thomas Falcon thomas.falcon@intel.com Acked-by: Namhyung Kim namhyung@kernel.org Cc: Adrian Hunter adrian.hunter@intel.com Cc: Alexander Shishkin alexander.shishkin@linux.intel.com Cc: Ingo Molnar mingo@redhat.com Cc: Jiri Olsa jolsa@kernel.org Cc: Mark Rutland mark.rutland@arm.com Cc: Peter Zijlstra peterz@infradead.org Signed-off-by: Arnaldo Carvalho de Melo acme@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- tools/perf/util/header.c | 10 ++-------- 1 file changed, 2 insertions(+), 8 deletions(-)

diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index 4f2a6e10ed5cc..4e12be579140a 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -1022,12 +1022,9 @@ static int write_bpf_prog_info(struct feat_fd *ff,

down_read(&env->bpf_progs.lock);

- if (env->bpf_progs.infos_cnt == 0) - goto out; - ret = do_write(ff, &env->bpf_progs.infos_cnt, sizeof(env->bpf_progs.infos_cnt)); - if (ret < 0) + if (ret < 0 || env->bpf_progs.infos_cnt == 0) goto out;

root = &env->bpf_progs.infos; @@ -1067,13 +1064,10 @@ static int write_bpf_btf(struct feat_fd *ff,

down_read(&env->bpf_progs.lock);

- if (env->bpf_progs.btfs_cnt == 0) - goto out; - ret = do_write(ff, &env->bpf_progs.btfs_cnt, sizeof(env->bpf_progs.btfs_cnt));

- if (ret < 0) + if (ret < 0 || env->bpf_progs.btfs_cnt == 0) goto out;

root = &env->bpf_progs.btfs;

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Niravkumar L Rabara niravkumarlaxmidas.rabara@altera.com

commit fd3ecda38fe0cb713d167b5477d25f6b350f0514 upstream.

The OCRAM ECC is always enabled either by the BootROM or by the Secure Device Manager (SDM) during a power-on reset on SoCFPGA.

However, during a warm reset, the OCRAM content is retained to preserve data, while the control and status registers are reset to their default values. As a result, ECC must be explicitly re-enabled after a warm reset.

Fixes: 17e47dc6db4f ("EDAC/altera: Add Stratix10 OCRAM ECC support") Signed-off-by: Niravkumar L Rabara niravkumarlaxmidas.rabara@altera.com Signed-off-by: Borislav Petkov (AMD) bp@alien8.de Acked-by: Dinh Nguyen dinguyen@kernel.org Cc: stable@vger.kernel.org Link: https://patch.msgid.link/20251111080801.1279401-1-niravkumarlaxmidas.rabara@... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/edac/altera_edac.c | 18 +++++++++++++++--- 1 file changed, 15 insertions(+), 3 deletions(-)

--- a/drivers/edac/altera_edac.c +++ b/drivers/edac/altera_edac.c @@ -1184,10 +1184,22 @@ altr_check_ocram_deps_init(struct altr_e if (ret) return ret;

- /* Verify OCRAM has been initialized */ + /* + * Verify that OCRAM has been initialized. + * During a warm reset, OCRAM contents are retained, but the control + * and status registers are reset to their default values. Therefore, + * ECC must be explicitly re-enabled in the control register. + * Error condition: if INITCOMPLETEA is clear and ECC_EN is already set. + */ if (!ecc_test_bits(ALTR_A10_ECC_INITCOMPLETEA, - (base + ALTR_A10_ECC_INITSTAT_OFST))) - return -ENODEV; + (base + ALTR_A10_ECC_INITSTAT_OFST))) { + if (!ecc_test_bits(ALTR_A10_ECC_EN, + (base + ALTR_A10_ECC_CTRL_OFST))) + ecc_set_bits(ALTR_A10_ECC_EN, + (base + ALTR_A10_ECC_CTRL_OFST)); + else + return -ENODEV; + }

/* Enable IRQ on Single Bit Error */ writel(ALTR_A10_ECC_SERRINTEN, (base + ALTR_A10_ECC_ERRINTENS_OFST));

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Trond Myklebust trond.myklebust@hammerspace.com

[ Upstream commit 7aca00d950e782e66c34fbd045c9605eca343a36 ]

Don't try to add an RDMA transport to a client that is already marked as being a TCP/TLS transport.

Fixes: 04a15263662a ("pnfs/flexfiles: connect to NFSv3 DS using TLS if MDS connection uses TLS") Signed-off-by: Trond Myklebust trond.myklebust@hammerspace.com Signed-off-by: Anna Schumaker anna.schumaker@oracle.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/nfs/pnfs_nfs.c | 32 ++++++++++++++++++-------------- 1 file changed, 18 insertions(+), 14 deletions(-)

diff --git a/fs/nfs/pnfs_nfs.c b/fs/nfs/pnfs_nfs.c index 7b32afb297827..ff48056bf750e 100644 --- a/fs/nfs/pnfs_nfs.c +++ b/fs/nfs/pnfs_nfs.c @@ -809,8 +809,11 @@ static int _nfs4_pnfs_v3_ds_connect(struct nfs_server *mds_srv, unsigned int retrans) { struct nfs_client *clp = ERR_PTR(-EIO); + struct nfs_client *mds_clp = mds_srv->nfs_client; + enum xprtsec_policies xprtsec_policy = mds_clp->cl_xprtsec.policy; struct nfs4_pnfs_ds_addr *da; unsigned long connect_timeout = timeo * (retrans + 1) * HZ / 10; + int ds_proto; int status = 0;

dprintk("--> %s DS %s\n", __func__, ds->ds_remotestr); @@ -834,27 +837,28 @@ static int _nfs4_pnfs_v3_ds_connect(struct nfs_server *mds_srv, .xprtsec = clp->cl_xprtsec, };

- if (da->da_transport != clp->cl_proto && - clp->cl_proto != XPRT_TRANSPORT_TCP_TLS) - continue; - if (da->da_transport == XPRT_TRANSPORT_TCP && - mds_srv->nfs_client->cl_proto == XPRT_TRANSPORT_TCP_TLS) + if (xprt_args.ident == XPRT_TRANSPORT_TCP && + clp->cl_proto == XPRT_TRANSPORT_TCP_TLS) xprt_args.ident = XPRT_TRANSPORT_TCP_TLS;

- if (da->da_addr.ss_family != clp->cl_addr.ss_family) + if (xprt_args.ident != clp->cl_proto) + continue; + if (xprt_args.dstaddr->sa_family != + clp->cl_addr.ss_family) continue; /* Add this address as an alias */ rpc_clnt_add_xprt(clp->cl_rpcclient, &xprt_args, - rpc_clnt_test_and_add_xprt, NULL); + rpc_clnt_test_and_add_xprt, NULL); continue; } - if (da->da_transport == XPRT_TRANSPORT_TCP && - mds_srv->nfs_client->cl_proto == XPRT_TRANSPORT_TCP_TLS) - da->da_transport = XPRT_TRANSPORT_TCP_TLS; - clp = get_v3_ds_connect(mds_srv, - &da->da_addr, - da->da_addrlen, da->da_transport, - timeo, retrans); + + ds_proto = da->da_transport; + if (ds_proto == XPRT_TRANSPORT_TCP && + xprtsec_policy != RPC_XPRTSEC_NONE) + ds_proto = XPRT_TRANSPORT_TCP_TLS; + + clp = get_v3_ds_connect(mds_srv, &da->da_addr, da->da_addrlen, + ds_proto, timeo, retrans); if (IS_ERR(clp)) continue; clp->cl_rpcclient->cl_softerr = 0;

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Zqiang qiang.zhang@linux.dev

[ Upstream commit 5f02151c411dda46efcc5dc57b0845efcdcfc26d ]

For built with CONFIG_PREEMPT_RT=y kernels, the dump_lock will be converted sleepable spinlock and not disable-irq, so the following scenarios occur:

inconsistent {IN-HARDIRQ-W} -> {HARDIRQ-ON-W} usage. irq_work/0/27 [HC0[0]:SC0[0]:HE1:SE1] takes: (&rq->__lock){?...}-{2:2}, at: raw_spin_rq_lock_nested+0x2b/0x40 {IN-HARDIRQ-W} state was registered at: lock_acquire+0x1e1/0x510 _raw_spin_lock_nested+0x42/0x80 raw_spin_rq_lock_nested+0x2b/0x40 sched_tick+0xae/0x7b0 update_process_times+0x14c/0x1b0 tick_periodic+0x62/0x1f0 tick_handle_periodic+0x48/0xf0 timer_interrupt+0x55/0x80 __handle_irq_event_percpu+0x20a/0x5c0 handle_irq_event_percpu+0x18/0xc0 handle_irq_event+0xb5/0x150 handle_level_irq+0x220/0x460 __common_interrupt+0xa2/0x1e0 common_interrupt+0xb0/0xd0 asm_common_interrupt+0x2b/0x40 _raw_spin_unlock_irqrestore+0x45/0x80 __setup_irq+0xc34/0x1a30 request_threaded_irq+0x214/0x2f0 hpet_time_init+0x3e/0x60 x86_late_time_init+0x5b/0xb0 start_kernel+0x308/0x410 x86_64_start_reservations+0x1c/0x30 x86_64_start_kernel+0x96/0xa0 common_startup_64+0x13e/0x148

other info that might help us debug this: Possible unsafe locking scenario:

CPU0 ---- lock(&rq->__lock); <Interrupt> lock(&rq->__lock);

*** DEADLOCK ***

stack backtrace: CPU: 0 UID: 0 PID: 27 Comm: irq_work/0 Call Trace: <TASK> dump_stack_lvl+0x8c/0xd0 dump_stack+0x14/0x20 print_usage_bug+0x42e/0x690 mark_lock.part.44+0x867/0xa70 ? __pfx_mark_lock.part.44+0x10/0x10 ? string_nocheck+0x19c/0x310 ? number+0x739/0x9f0 ? __pfx_string_nocheck+0x10/0x10 ? __pfx_check_pointer+0x10/0x10 ? kvm_sched_clock_read+0x15/0x30 ? sched_clock_noinstr+0xd/0x20 ? local_clock_noinstr+0x1c/0xe0 __lock_acquire+0xc4b/0x62b0 ? __pfx_format_decode+0x10/0x10 ? __pfx_string+0x10/0x10 ? __pfx___lock_acquire+0x10/0x10 ? __pfx_vsnprintf+0x10/0x10 lock_acquire+0x1e1/0x510 ? raw_spin_rq_lock_nested+0x2b/0x40 ? __pfx_lock_acquire+0x10/0x10 ? dump_line+0x12e/0x270 ? raw_spin_rq_lock_nested+0x20/0x40 _raw_spin_lock_nested+0x42/0x80 ? raw_spin_rq_lock_nested+0x2b/0x40 raw_spin_rq_lock_nested+0x2b/0x40 scx_dump_state+0x3b3/0x1270 ? finish_task_switch+0x27e/0x840 scx_ops_error_irq_workfn+0x67/0x80 irq_work_single+0x113/0x260 irq_work_run_list.part.3+0x44/0x70 run_irq_workd+0x6b/0x90 ? __pfx_run_irq_workd+0x10/0x10 smpboot_thread_fn+0x529/0x870 ? __pfx_smpboot_thread_fn+0x10/0x10 kthread+0x305/0x3f0 ? __pfx_kthread+0x10/0x10 ret_from_fork+0x40/0x70 ? __pfx_kthread+0x10/0x10 ret_from_fork_asm+0x1a/0x30 </TASK>

This commit therefore use rq_lock_irqsave/irqrestore() to replace rq_lock/unlock() in the scx_dump_state().

Fixes: 07814a9439a3 ("sched_ext: Print debug dump after an error exit") Signed-off-by: Zqiang qiang.zhang@linux.dev Signed-off-by: Tejun Heo tj@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- kernel/sched/ext.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index e1b502ef1243c..313206067ea3d 100644 --- a/kernel/sched/ext.c +++ b/kernel/sched/ext.c @@ -4270,7 +4270,7 @@ static void scx_dump_state(struct scx_exit_info *ei, size_t dump_len) size_t avail, used; bool idle;

- rq_lock(rq, &rf); + rq_lock_irqsave(rq, &rf);

idle = list_empty(&rq->scx.runnable_list) && rq->curr->sched_class == &idle_sched_class; @@ -4339,7 +4339,7 @@ static void scx_dump_state(struct scx_exit_info *ei, size_t dump_len) list_for_each_entry(p, &rq->scx.runnable_list, scx.runnable_node) scx_dump_task(&s, &dctx, p, ' '); next: - rq_unlock(rq, &rf); + rq_unlock_irqrestore(rq, &rf); }

dump_newline(&s);

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ian Rogers irogers@google.com

[ Upstream commit 8b93f8933d37591d17c59fd71b18fc61966d9515 ]

In test_record_concurrent, as stderr is sent to /dev/null, error messages are hidden. Change this to gather the error messages and dump them on failure.

Some minor sh->bash changes to add some more diagnostics in trap_cleanup.

Reviewed-by: James Clark james.clark@linaro.org Signed-off-by: Ian Rogers irogers@google.com Acked-by: Namhyung Kim namhyung@kernel.org Cc: Adrian Hunter adrian.hunter@intel.com Cc: Alexander Shishkin alexander.shishkin@linux.intel.com Cc: Athira Rajeev atrajeev@linux.ibm.com Cc: Blake Jones blakejones@google.com Cc: Chun-Tse Shao ctshao@google.com Cc: Collin Funk collin.funk1@gmail.com Cc: Howard Chu howardchu95@gmail.com Cc: Ingo Molnar mingo@redhat.com Cc: Jan Polensky japo@linux.ibm.com Cc: Jiri Olsa jolsa@kernel.org Cc: Kan Liang kan.liang@linux.intel.com Cc: Li Huafei lihuafei1@huawei.com Cc: Mark Rutland mark.rutland@arm.com Cc: Nam Cao namcao@linutronix.de Cc: Peter Zijlstra peterz@infradead.org Cc: Steinar H. Gunderson sesse@google.com Cc: Thomas Gleixner tglx@linutronix.de Link: https://lore.kernel.org/r/20250821163820.1132977-5-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo acme@redhat.com Stable-dep-of: 3c723f449723 ("perf test: Fix lock contention test") Signed-off-by: Sasha Levin sashal@kernel.org --- tools/perf/tests/shell/lock_contention.sh | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/tools/perf/tests/shell/lock_contention.sh b/tools/perf/tests/shell/lock_contention.sh index d33d9e4392b06..7248a74ca2a32 100755 --- a/tools/perf/tests/shell/lock_contention.sh +++ b/tools/perf/tests/shell/lock_contention.sh @@ -7,14 +7,17 @@ set -e err=0 perfdata=$(mktemp /tmp/__perf_test.perf.data.XXXXX) result=$(mktemp /tmp/__perf_test.result.XXXXX) +errout=$(mktemp /tmp/__perf_test.errout.XXXXX)

cleanup() { rm -f ${perfdata} rm -f ${result} + rm -f ${errout} trap - EXIT TERM INT }

trap_cleanup() { + echo "Unexpected signal in ${FUNCNAME[1]}" cleanup exit ${err} } @@ -75,10 +78,12 @@ test_bpf() test_record_concurrent() { echo "Testing perf lock record and perf lock contention at the same time" - perf lock record -o- -- perf bench sched messaging -p 2> /dev/null | \ + perf lock record -o- -- perf bench sched messaging -p 2> ${errout} | \ perf lock contention -i- -E 1 -q 2> ${result} if [ "$(cat "${result}" | wc -l)" != "1" ]; then echo "[Fail] Recorded result count is not 1:" "$(cat "${result}" | wc -l)" + cat ${errout} + cat ${result} err=1 exit fi

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Trond Myklebust trond.myklebust@hammerspace.com

[ Upstream commit 28e19737e1570c7c71890547c2e43c3e0da79df9 ]

Don't try to add an RDMA transport to a client that is already marked as being a TCP/TLS transport.

Fixes: a35518cae4b3 ("NFSv4.1/pnfs: fix NFS with TLS in pnfs") Signed-off-by: Trond Myklebust trond.myklebust@hammerspace.com Signed-off-by: Anna Schumaker anna.schumaker@oracle.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/nfs/pnfs_nfs.c | 34 +++++++++++++++++----------------- 1 file changed, 17 insertions(+), 17 deletions(-)

diff --git a/fs/nfs/pnfs_nfs.c b/fs/nfs/pnfs_nfs.c index ff48056bf750e..9976cc16b6890 100644 --- a/fs/nfs/pnfs_nfs.c +++ b/fs/nfs/pnfs_nfs.c @@ -884,7 +884,10 @@ static int _nfs4_pnfs_v4_ds_connect(struct nfs_server *mds_srv, u32 minor_version) { struct nfs_client *clp = ERR_PTR(-EIO); + struct nfs_client *mds_clp = mds_srv->nfs_client; + enum xprtsec_policies xprtsec_policy = mds_clp->cl_xprtsec.policy; struct nfs4_pnfs_ds_addr *da; + int ds_proto; int status = 0;

dprintk("--> %s DS %s\n", __func__, ds->ds_remotestr); @@ -912,12 +915,8 @@ static int _nfs4_pnfs_v4_ds_connect(struct nfs_server *mds_srv, .data = &xprtdata, };

- if (da->da_transport != clp->cl_proto && - clp->cl_proto != XPRT_TRANSPORT_TCP_TLS) - continue; - if (da->da_transport == XPRT_TRANSPORT_TCP && - mds_srv->nfs_client->cl_proto == - XPRT_TRANSPORT_TCP_TLS) { + if (xprt_args.ident == XPRT_TRANSPORT_TCP && + clp->cl_proto == XPRT_TRANSPORT_TCP_TLS) { struct sockaddr *addr = (struct sockaddr *)&da->da_addr; struct sockaddr_in *sin = @@ -948,7 +947,10 @@ static int _nfs4_pnfs_v4_ds_connect(struct nfs_server *mds_srv, xprt_args.ident = XPRT_TRANSPORT_TCP_TLS; xprt_args.servername = servername; } - if (da->da_addr.ss_family != clp->cl_addr.ss_family) + if (xprt_args.ident != clp->cl_proto) + continue; + if (xprt_args.dstaddr->sa_family != + clp->cl_addr.ss_family) continue;

/** @@ -962,15 +964,14 @@ static int _nfs4_pnfs_v4_ds_connect(struct nfs_server *mds_srv, if (xprtdata.cred) put_cred(xprtdata.cred); } else { - if (da->da_transport == XPRT_TRANSPORT_TCP && - mds_srv->nfs_client->cl_proto == - XPRT_TRANSPORT_TCP_TLS) - da->da_transport = XPRT_TRANSPORT_TCP_TLS; - clp = nfs4_set_ds_client(mds_srv, - &da->da_addr, - da->da_addrlen, - da->da_transport, timeo, - retrans, minor_version); + ds_proto = da->da_transport; + if (ds_proto == XPRT_TRANSPORT_TCP && + xprtsec_policy != RPC_XPRTSEC_NONE) + ds_proto = XPRT_TRANSPORT_TCP_TLS; + + clp = nfs4_set_ds_client(mds_srv, &da->da_addr, + da->da_addrlen, ds_proto, + timeo, retrans, minor_version); if (IS_ERR(clp)) continue;

@@ -981,7 +982,6 @@ static int _nfs4_pnfs_v4_ds_connect(struct nfs_server *mds_srv, clp = ERR_PTR(-EIO); continue; } - } }

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Trond Myklebust trond.myklebust@hammerspace.com

[ Upstream commit fb2cba0854a7f315c8100a807a6959b99d72479e ]

If the TLS security policy is of type RPC_XPRTSEC_TLS_X509, then the cert_serial and privkey_serial fields need to match as well since they define the client's identity, as presented to the server.

Fixes: 90c9550a8d65 ("NFS: support the kernel keyring for TLS") Signed-off-by: Trond Myklebust trond.myklebust@hammerspace.com Signed-off-by: Anna Schumaker anna.schumaker@oracle.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/nfs/client.c | 8 ++++++++ 1 file changed, 8 insertions(+)

diff --git a/fs/nfs/client.c b/fs/nfs/client.c index 4e3dcc157a83c..54699299d5b16 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -338,6 +338,14 @@ static struct nfs_client *nfs_match_client(const struct nfs_client_initdata *dat /* Match the xprt security policy */ if (clp->cl_xprtsec.policy != data->xprtsec.policy) continue; + if (clp->cl_xprtsec.policy == RPC_XPRTSEC_TLS_X509) { + if (clp->cl_xprtsec.cert_serial != + data->xprtsec.cert_serial) + continue; + if (clp->cl_xprtsec.privkey_serial != + data->xprtsec.privkey_serial) + continue; + }

refcount_inc(&clp->cl_count); return clp;

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Eric Dumazet edumazet@google.com

[ Upstream commit 0345552a653ce5542affeb69ac5aa52177a5199b ]

After commit 100dfa74cad9 ("inet: dev_queue_xmit() llist adoption") I started seeing many qdisc requeues on IDPF under high TX workload.

$ tc -s qd sh dev eth1 handle 1: ; sleep 1; tc -s qd sh dev eth1 handle 1: qdisc mq 1: root Sent 43534617319319 bytes 268186451819 pkt (dropped 0, overlimits 0 requeues 3532840114) backlog 1056Kb 6675p requeues 3532840114 qdisc mq 1: root Sent 43554665866695 bytes 268309964788 pkt (dropped 0, overlimits 0 requeues 3537737653) backlog 781164b 4822p requeues 3537737653

This is caused by try_bulk_dequeue_skb() being only limited by BQL budget.

perf record -C120-239 -e qdisc:qdisc_dequeue sleep 1 ; perf script ... netperf 75332 [146] 2711.138269: qdisc:qdisc_dequeue: dequeue ifindex=5 qdisc handle=0x80150000 parent=0x10013 txq_state=0x0 packets=1292 skbaddr=0xff378005a1e9f200 netperf 75332 [146] 2711.138953: qdisc:qdisc_dequeue: dequeue ifindex=5 qdisc handle=0x80150000 parent=0x10013 txq_state=0x0 packets=1213 skbaddr=0xff378004d607a500 netperf 75330 [144] 2711.139631: qdisc:qdisc_dequeue: dequeue ifindex=5 qdisc handle=0x80150000 parent=0x10013 txq_state=0x0 packets=1233 skbaddr=0xff3780046be20100 netperf 75333 [147] 2711.140356: qdisc:qdisc_dequeue: dequeue ifindex=5 qdisc handle=0x80150000 parent=0x10013 txq_state=0x0 packets=1093 skbaddr=0xff37800514845b00 netperf 75337 [151] 2711.141037: qdisc:qdisc_dequeue: dequeue ifindex=5 qdisc handle=0x80150000 parent=0x10013 txq_state=0x0 packets=1353 skbaddr=0xff37800460753300 netperf 75337 [151] 2711.141877: qdisc:qdisc_dequeue: dequeue ifindex=5 qdisc handle=0x80150000 parent=0x10013 txq_state=0x0 packets=1367 skbaddr=0xff378004e72c7b00 netperf 75330 [144] 2711.142643: qdisc:qdisc_dequeue: dequeue ifindex=5 qdisc handle=0x80150000 parent=0x10013 txq_state=0x0 packets=1202 skbaddr=0xff3780045bd60000 ...

This is bad because :

1) Large batches hold one victim cpu for a very long time.

2) Driver often hit their own TX ring limit (all slots are used).

3) We call dev_requeue_skb()

4) Requeues are using a FIFO (q->gso_skb), breaking qdisc ability to implement FQ or priority scheduling.

5) dequeue_skb() gets packets from q->gso_skb one skb at a time with no xmit_more support. This is causing many spinlock games between the qdisc and the device driver.

Requeues were supposed to be very rare, lets keep them this way.

Limit batch sizes to /proc/sys/net/core/dev_weight (default 64) as __qdisc_run() was designed to use.

Fixes: 5772e9a3463b ("qdisc: bulk dequeue support for qdiscs with TCQ_F_ONETXQUEUE") Signed-off-by: Eric Dumazet edumazet@google.com Reviewed-by: Toke Høiland-Jørgensen toke@redhat.com Acked-by: Jesper Dangaard Brouer hawk@kernel.org Link: https://patch.msgid.link/20251109161215.2574081-1-edumazet@google.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- net/sched/sch_generic.c | 17 ++++++++++------- 1 file changed, 10 insertions(+), 7 deletions(-)

diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 1e008a228ebdf..7dee9748a56be 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -180,9 +180,10 @@ static inline void dev_requeue_skb(struct sk_buff *skb, struct Qdisc *q) static void try_bulk_dequeue_skb(struct Qdisc *q, struct sk_buff *skb, const struct netdev_queue *txq, - int *packets) + int *packets, int budget) { int bytelimit = qdisc_avail_bulklimit(txq) - skb->len; + int cnt = 0;

while (bytelimit > 0) { struct sk_buff *nskb = q->dequeue(q); @@ -193,8 +194,10 @@ static void try_bulk_dequeue_skb(struct Qdisc *q, bytelimit -= nskb->len; /* covers GSO len */ skb->next = nskb; skb = nskb; - (*packets)++; /* GSO counts as one pkt */ + if (++cnt >= budget) + break; } + (*packets) += cnt; skb_mark_not_on_list(skb); }

@@ -228,7 +231,7 @@ static void try_bulk_dequeue_skb_slow(struct Qdisc *q, * A requeued skb (via q->gso_skb) can also be a SKB list. */ static struct sk_buff *dequeue_skb(struct Qdisc *q, bool *validate, - int *packets) + int *packets, int budget) { const struct netdev_queue *txq = q->dev_queue; struct sk_buff *skb = NULL; @@ -295,7 +298,7 @@ static struct sk_buff *dequeue_skb(struct Qdisc *q, bool *validate, if (skb) { bulk: if (qdisc_may_bulk(q)) - try_bulk_dequeue_skb(q, skb, txq, packets); + try_bulk_dequeue_skb(q, skb, txq, packets, budget); else try_bulk_dequeue_skb_slow(q, skb, packets); } @@ -387,7 +390,7 @@ bool sch_direct_xmit(struct sk_buff *skb, struct Qdisc *q, * >0 - queue is not empty. * */ -static inline bool qdisc_restart(struct Qdisc *q, int *packets) +static inline bool qdisc_restart(struct Qdisc *q, int *packets, int budget) { spinlock_t *root_lock = NULL; struct netdev_queue *txq; @@ -396,7 +399,7 @@ static inline bool qdisc_restart(struct Qdisc *q, int *packets) bool validate;

/* Dequeue packet */ - skb = dequeue_skb(q, &validate, packets); + skb = dequeue_skb(q, &validate, packets, budget); if (unlikely(!skb)) return false;

@@ -414,7 +417,7 @@ void __qdisc_run(struct Qdisc *q) int quota = READ_ONCE(net_hotdata.dev_tx_weight); int packets;

- while (qdisc_restart(q, &packets)) { + while (qdisc_restart(q, &packets, quota)) { quota -= packets; if (quota <= 0) { if (q->flags & TCQ_F_NOLOCK)

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Kairui Song kasong@tencent.com

commit 1c2a936edd71e133f2806e68324ec81a4eb07588 upstream.

Since commit 78524b05f1a3 ("mm, swap: avoid redundant swap device pinning"), the common helper for allocating and preparing a folio in the swap cache layer no longer tries to get a swap device reference internally, because all callers of __read_swap_cache_async are already holding a swap entry reference. The repeated swap device pinning isn't needed on the same swap device.

Caller of VMA readahead is also holding a reference to the target entry's swap device, but VMA readahead walks the page table, so it might encounter swap entries from other devices, and call __read_swap_cache_async on another device without holding a reference to it.

So it is possible to cause a UAF when swapoff of device A raced with swapin on device B, and VMA readahead tries to read swap entries from device A. It's not easy to trigger, but in theory, it could cause real issues.

Make VMA readahead try to get the device reference first if the swap device is a different one from the target entry.

Link: https://lkml.kernel.org/r/20251111-swap-fix-vma-uaf-v1-1-41c660e58562@tencen... Fixes: 78524b05f1a3 ("mm, swap: avoid redundant swap device pinning") Suggested-by: Huang Ying ying.huang@linux.alibaba.com Signed-off-by: Kairui Song kasong@tencent.com Acked-by: Chris Li chrisl@kernel.org Cc: Baoquan He bhe@redhat.com Cc: Barry Song baohua@kernel.org Cc: Kemeng Shi shikemeng@huaweicloud.com Cc: Nhat Pham nphamcs@gmail.com Cc: stable@vger.kernel.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- mm/swap_state.c | 13 +++++++++++++ 1 file changed, 13 insertions(+)

--- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -746,6 +746,8 @@ static struct folio *swap_vma_readahead(

blk_start_plug(&plug); for (addr = start; addr < end; ilx++, addr += PAGE_SIZE) { + struct swap_info_struct *si = NULL; + if (!pte++) { pte = pte_offset_map(vmf->pmd, addr); if (!pte) @@ -759,8 +761,19 @@ static struct folio *swap_vma_readahead( continue; pte_unmap(pte); pte = NULL; + /* + * Readahead entry may come from a device that we are not + * holding a reference to, try to grab a reference, or skip. + */ + if (swp_type(entry) != swp_type(targ_entry)) { + si = get_swap_device(entry); + if (!si) + continue; + } folio = __read_swap_cache_async(entry, gfp_mask, mpol, ilx, &page_allocated, false); + if (si) + put_swap_device(si); if (!folio) continue; if (page_allocated) {

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Al Viro viro@zeniv.linux.org.uk

[ Upstream commit aae9db5739164353fa1894db000fabad940a835b ]

1) finish_no_open() takes ERR_PTR() as dentry now. 2) caller of ->atomic_open() will call d_lookup_done() itself, no need to do it here.

Reviewed-by: NeilBrown neil@brown.name Signed-off-by: Al Viro viro@zeniv.linux.org.uk Stable-dep-of: 85d2c2392ac6 ("NFSv2/v3: Fix error handling in nfs_atomic_open_v23()") Signed-off-by: Sasha Levin sashal@kernel.org --- fs/nfs/dir.c | 16 +++++----------- 1 file changed, 5 insertions(+), 11 deletions(-)

diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index d812179239362..c8dd1d0b8d850 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -2260,7 +2260,7 @@ int nfs_atomic_open_v23(struct inode *dir, struct dentry *dentry, struct file *file, unsigned int open_flags, umode_t mode) { - + struct dentry *res = NULL; /* Same as look+open from lookup_open(), but with different O_TRUNC * handling. */ @@ -2275,21 +2275,15 @@ int nfs_atomic_open_v23(struct inode *dir, struct dentry *dentry, if (error) return error; return finish_open(file, dentry, NULL); - } else if (d_in_lookup(dentry)) { + } + if (d_in_lookup(dentry)) { /* The only flags nfs_lookup considers are * LOOKUP_EXCL and LOOKUP_RENAME_TARGET, and * we want those to be zero so the lookup isn't skipped. */ - struct dentry *res = nfs_lookup(dir, dentry, 0); - - d_lookup_done(dentry); - if (unlikely(res)) { - if (IS_ERR(res)) - return PTR_ERR(res); - return finish_no_open(file, res); - } + res = nfs_lookup(dir, dentry, 0); } - return finish_no_open(file, NULL); + return finish_no_open(file, res);

} EXPORT_SYMBOL_GPL(nfs_atomic_open_v23);

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Zilin Guan zilin@seu.edu.cn

commit c367af440e03eba7beb0c9f3fe540f9bcb69134a upstream.

data_reloc_print_warning_inode() calls btrfs_get_fs_root() to obtain local_root, but fails to release its reference when paths_from_inode() returns an error. This causes a potential memory leak.

Add a missing btrfs_put_root() call in the error path to properly decrease the reference count of local_root.

Fixes: b9a9a85059cde ("btrfs: output affected files when relocation fails") CC: stable@vger.kernel.org # 6.6+ Reviewed-by: Qu Wenruo wqu@suse.com Signed-off-by: Zilin Guan zilin@seu.edu.cn Reviewed-by: David Sterba dsterba@suse.com Signed-off-by: David Sterba dsterba@suse.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/btrfs/inode.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

--- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -174,8 +174,10 @@ static int data_reloc_print_warning_inod return ret; } ret = paths_from_inode(inum, ipath); - if (ret < 0) + if (ret < 0) { + btrfs_put_root(local_root); goto err; + }

/* * We deliberately ignore the bit ipath might have been too small to

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Sean Christopherson seanjc@google.com

commit ae431059e75d36170a5ae6b44cc4d06d43613215 upstream.

When unbinding a memslot from a guest_memfd instance, remove the bindings even if the guest_memfd file is dying, i.e. even if its file refcount has gone to zero. If the memslot is freed before the file is fully released, nullifying the memslot side of the binding in kvm_gmem_release() will write to freed memory, as detected by syzbot+KASAN:

================================================================== BUG: KASAN: slab-use-after-free in kvm_gmem_release+0x176/0x440 virt/kvm/guest_memfd.c:353 Write of size 8 at addr ffff88807befa508 by task syz.0.17/6022

CPU: 0 UID: 0 PID: 6022 Comm: syz.0.17 Not tainted syzkaller #0 PREEMPT(full) Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 10/02/2025 Call Trace: <TASK> dump_stack_lvl+0x189/0x250 lib/dump_stack.c:120 print_address_description mm/kasan/report.c:378 [inline] print_report+0xca/0x240 mm/kasan/report.c:482 kasan_report+0x118/0x150 mm/kasan/report.c:595 kvm_gmem_release+0x176/0x440 virt/kvm/guest_memfd.c:353 __fput+0x44c/0xa70 fs/file_table.c:468 task_work_run+0x1d4/0x260 kernel/task_work.c:227 resume_user_mode_work include/linux/resume_user_mode.h:50 [inline] exit_to_user_mode_loop+0xe9/0x130 kernel/entry/common.c:43 exit_to_user_mode_prepare include/linux/irq-entry-common.h:225 [inline] syscall_exit_to_user_mode_work include/linux/entry-common.h:175 [inline] syscall_exit_to_user_mode include/linux/entry-common.h:210 [inline] do_syscall_64+0x2bd/0xfa0 arch/x86/entry/syscall_64.c:100 entry_SYSCALL_64_after_hwframe+0x77/0x7f RIP: 0033:0x7fbeeff8efc9 </TASK>

Allocated by task 6023: kasan_save_stack mm/kasan/common.c:56 [inline] kasan_save_track+0x3e/0x80 mm/kasan/common.c:77 poison_kmalloc_redzone mm/kasan/common.c:397 [inline] __kasan_kmalloc+0x93/0xb0 mm/kasan/common.c:414 kasan_kmalloc include/linux/kasan.h:262 [inline] __kmalloc_cache_noprof+0x3e2/0x700 mm/slub.c:5758 kmalloc_noprof include/linux/slab.h:957 [inline] kzalloc_noprof include/linux/slab.h:1094 [inline] kvm_set_memory_region+0x747/0xb90 virt/kvm/kvm_main.c:2104 kvm_vm_ioctl_set_memory_region+0x6f/0xd0 virt/kvm/kvm_main.c:2154 kvm_vm_ioctl+0x957/0xc60 virt/kvm/kvm_main.c:5201 vfs_ioctl fs/ioctl.c:51 [inline] __do_sys_ioctl fs/ioctl.c:597 [inline] __se_sys_ioctl+0xfc/0x170 fs/ioctl.c:583 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline] do_syscall_64+0xfa/0xfa0 arch/x86/entry/syscall_64.c:94 entry_SYSCALL_64_after_hwframe+0x77/0x7f

Freed by task 6023: kasan_save_stack mm/kasan/common.c:56 [inline] kasan_save_track+0x3e/0x80 mm/kasan/common.c:77 kasan_save_free_info+0x46/0x50 mm/kasan/generic.c:584 poison_slab_object mm/kasan/common.c:252 [inline] __kasan_slab_free+0x5c/0x80 mm/kasan/common.c:284 kasan_slab_free include/linux/kasan.h:234 [inline] slab_free_hook mm/slub.c:2533 [inline] slab_free mm/slub.c:6622 [inline] kfree+0x19a/0x6d0 mm/slub.c:6829 kvm_set_memory_region+0x9c4/0xb90 virt/kvm/kvm_main.c:2130 kvm_vm_ioctl_set_memory_region+0x6f/0xd0 virt/kvm/kvm_main.c:2154 kvm_vm_ioctl+0x957/0xc60 virt/kvm/kvm_main.c:5201 vfs_ioctl fs/ioctl.c:51 [inline] __do_sys_ioctl fs/ioctl.c:597 [inline] __se_sys_ioctl+0xfc/0x170 fs/ioctl.c:583 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline] do_syscall_64+0xfa/0xfa0 arch/x86/entry/syscall_64.c:94 entry_SYSCALL_64_after_hwframe+0x77/0x7f

Deliberately don't acquire filemap invalid lock when the file is dying as the lifecycle of f_mapping is outside the purview of KVM. Dereferencing the mapping is *probably* fine, but there's no need to invalidate anything as memslot deletion is responsible for zapping SPTEs, and the only code that can access the dying file is kvm_gmem_release(), whose core code is mutually exclusive with unbinding.

Note, the mutual exclusivity is also what makes it safe to access the bindings on a dying gmem instance. Unbinding either runs with slots_lock held, or after the last reference to the owning "struct kvm" is put, and kvm_gmem_release() nullifies the slot pointer under slots_lock, and puts its reference to the VM after that is done.

Reported-by: syzbot+2479e53d0db9b32ae2aa@syzkaller.appspotmail.com Closes: https://lore.kernel.org/all/68fa7a22.a70a0220.3bf6c6.008b.GAE@google.com Tested-by: syzbot+2479e53d0db9b32ae2aa@syzkaller.appspotmail.com Fixes: a7800aa80ea4 ("KVM: Add KVM_CREATE_GUEST_MEMFD ioctl() for guest-specific backing memory") Cc: stable@vger.kernel.org Cc: Hillf Danton hdanton@sina.com Reviewed-By: Vishal Annapurve vannapurve@google.com Link: https://patch.msgid.link/20251104011205.3853541-1-seanjc@google.com Signed-off-by: Sean Christopherson seanjc@google.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- virt/kvm/guest_memfd.c | 45 ++++++++++++++++++++++++++++++++------------- 1 file changed, 32 insertions(+), 13 deletions(-)

--- a/virt/kvm/guest_memfd.c +++ b/virt/kvm/guest_memfd.c @@ -523,31 +523,50 @@ err: return r; }

-void kvm_gmem_unbind(struct kvm_memory_slot *slot) +static void __kvm_gmem_unbind(struct kvm_memory_slot *slot, struct kvm_gmem *gmem) { unsigned long start = slot->gmem.pgoff; unsigned long end = start + slot->npages; - struct kvm_gmem *gmem; + + xa_store_range(&gmem->bindings, start, end - 1, NULL, GFP_KERNEL); + + /* + * synchronize_srcu(&kvm->srcu) ensured that kvm_gmem_get_pfn() + * cannot see this memslot. + */ + WRITE_ONCE(slot->gmem.file, NULL); +} + +void kvm_gmem_unbind(struct kvm_memory_slot *slot) +{ struct file *file;

/* - * Nothing to do if the underlying file was already closed (or is being - * closed right now), kvm_gmem_release() invalidates all bindings. + * Nothing to do if the underlying file was _already_ closed, as + * kvm_gmem_release() invalidates and nullifies all bindings. */ - file = kvm_gmem_get_file(slot); - if (!file) + if (!slot->gmem.file) return;

- gmem = file->private_data; - - filemap_invalidate_lock(file->f_mapping); - xa_store_range(&gmem->bindings, start, end - 1, NULL, GFP_KERNEL); + file = kvm_gmem_get_file(slot);

/* - * synchronize_srcu(&kvm->srcu) ensured that kvm_gmem_get_pfn() - * cannot see this memslot. + * However, if the file is _being_ closed, then the bindings need to be + * removed as kvm_gmem_release() might not run until after the memslot + * is freed. Note, modifying the bindings is safe even though the file + * is dying as kvm_gmem_release() nullifies slot->gmem.file under + * slots_lock, and only puts its reference to KVM after destroying all + * bindings. I.e. reaching this point means kvm_gmem_release() hasn't + * yet destroyed the bindings or freed the gmem_file, and can't do so + * until the caller drops slots_lock. */ - WRITE_ONCE(slot->gmem.file, NULL); + if (!file) { + __kvm_gmem_unbind(slot, slot->gmem.file->private_data); + return; + } + + filemap_invalidate_lock(file->f_mapping); + __kvm_gmem_unbind(slot, file->private_data); filemap_invalidate_unlock(file->f_mapping);

fput(file);

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Eduard Zingerman eddyz87@gmail.com

[ Upstream commit b0c8e6d3d866b6a7f73877f71968dbffd27b7785 ]

The usage pattern for widen_imprecise_scalars() looks as follows:

prev_st = find_prev_entry(env, ...); queued_st = push_stack(...); widen_imprecise_scalars(env, prev_st, queued_st);

Where prev_st is an ancestor of the queued_st in the explored states tree. This ancestor is not guaranteed to have same allocated stack depth as queued_st. E.g. in the following case:

def main(): for i in 1..2: foo(i) // same callsite, differnt param

def foo(i): if i == 1: use 128 bytes of stack iterator based loop

Here, for a second 'foo' call prev_st->allocated_stack is 128, while queued_st->allocated_stack is much smaller. widen_imprecise_scalars() needs to take this into account and avoid accessing bpf_verifier_state->frame[*]->stack out of bounds.

Fixes: 2793a8b015f7 ("bpf: exact states comparison for iterator convergence checks") Reported-by: Emil Tsalapatis emil@etsalapatis.com Signed-off-by: Eduard Zingerman eddyz87@gmail.com Link: https://lore.kernel.org/r/20251114025730.772723-1-eddyz87@gmail.com Signed-off-by: Alexei Starovoitov ast@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- kernel/bpf/verifier.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 2844adf4da61a..c3cdf2bf09aa4 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -8917,7 +8917,7 @@ static int widen_imprecise_scalars(struct bpf_verifier_env *env, struct bpf_verifier_state *cur) { struct bpf_func_state *fold, *fcur; - int i, fr; + int i, fr, num_slots;

reset_idmap_scratch(env); for (fr = old->curframe; fr >= 0; fr--) { @@ -8930,7 +8930,9 @@ static int widen_imprecise_scalars(struct bpf_verifier_env *env, &fcur->regs[i], &env->idmap_scratch);

- for (i = 0; i < fold->allocated_stack / BPF_REG_SIZE; i++) { + num_slots = min(fold->allocated_stack / BPF_REG_SIZE, + fcur->allocated_stack / BPF_REG_SIZE); + for (i = 0; i < num_slots; i++) { if (!is_spilled_reg(&fold->stack[i]) || !is_spilled_reg(&fcur->stack[i])) continue;

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Cosmin Ratiu cratiu@nvidia.com

[ Upstream commit aa4595d0ada65d5d44fa924a42a87c175d9d88e3 ]

The global doorbell is used for more than just Ethernet resources, so move it out of mlx5e_hw_objs into a common place (mlx5_priv), to avoid non-Ethernet modules (e.g. HWS, ASO) depending on Ethernet structs.

Use this opportunity to consolidate it with the 'uar' pointer already there, which was used as an RX doorbell. Underneath the 'uar' pointer is identical to 'bfreg->up', so store a single resource and use that instead.

For CQ doorbells, care is taken to always use bfreg->up->index instead of bfreg->index, which may refer to a subsequent UAR page from the same ALLOC_UAR batch on some NICs.

This paves the way for cleanly supporting multiple doorbells in the Ethernet driver.

Signed-off-by: Cosmin Ratiu cratiu@nvidia.com Reviewed-by: Dragos Tatulea dtatulea@nvidia.com Signed-off-by: Tariq Toukan tariqt@nvidia.com Reviewed-by: Simon Horman horms@kernel.org Signed-off-by: Jakub Kicinski kuba@kernel.org Stable-dep-of: e5eba42f0134 ("mlx5: Fix default values in create CQ") Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/infiniband/hw/mlx5/cq.c | 4 ++-- drivers/net/ethernet/mellanox/mlx5/core/cq.c | 2 +- drivers/net/ethernet/mellanox/mlx5/core/en/params.c | 2 +- drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c | 2 +- drivers/net/ethernet/mellanox/mlx5/core/en_common.c | 11 +---------- drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 10 +++++----- drivers/net/ethernet/mellanox/mlx5/core/eq.c | 4 ++-- drivers/net/ethernet/mellanox/mlx5/core/lib/aso.c | 8 ++++---- drivers/net/ethernet/mellanox/mlx5/core/main.c | 11 +++++------ .../ethernet/mellanox/mlx5/core/steering/hws/send.c | 8 ++++---- drivers/net/ethernet/mellanox/mlx5/core/wc.c | 4 ++-- include/linux/mlx5/driver.h | 3 +-- 12 files changed, 29 insertions(+), 40 deletions(-)

diff --git a/drivers/infiniband/hw/mlx5/cq.c b/drivers/infiniband/hw/mlx5/cq.c index 9c8003a783343..a23b364e24ffe 100644 --- a/drivers/infiniband/hw/mlx5/cq.c +++ b/drivers/infiniband/hw/mlx5/cq.c @@ -648,7 +648,7 @@ int mlx5_ib_arm_cq(struct ib_cq *ibcq, enum ib_cq_notify_flags flags) { struct mlx5_core_dev *mdev = to_mdev(ibcq->device)->mdev; struct mlx5_ib_cq *cq = to_mcq(ibcq); - void __iomem *uar_page = mdev->priv.uar->map; + void __iomem *uar_page = mdev->priv.bfreg.up->map; unsigned long irq_flags; int ret = 0;

@@ -923,7 +923,7 @@ static int create_cq_kernel(struct mlx5_ib_dev *dev, struct mlx5_ib_cq *cq, cq->buf.frag_buf.page_shift - MLX5_ADAPTER_PAGE_SHIFT);

- *index = dev->mdev->priv.uar->index; + *index = dev->mdev->priv.bfreg.up->index;

return 0;

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cq.c b/drivers/net/ethernet/mellanox/mlx5/core/cq.c index 1fd403713bafc..35039a95dcfd4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cq.c @@ -145,7 +145,7 @@ int mlx5_create_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq, mlx5_core_dbg(dev, "failed adding CP 0x%x to debug file system\n", cq->cqn);

- cq->uar = dev->priv.uar; + cq->uar = dev->priv.bfreg.up; cq->irqn = eq->core.irqn;

return 0; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c index 06e1a04e693f3..c24cb2ab91cb1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c @@ -810,7 +810,7 @@ static void mlx5e_build_common_cq_param(struct mlx5_core_dev *mdev, { void *cqc = param->cqc;

- MLX5_SET(cqc, cqc, uar_page, mdev->priv.uar->index); + MLX5_SET(cqc, cqc, uar_page, mdev->priv.bfreg.up->index); if (MLX5_CAP_GEN(mdev, cqe_128_always) && cache_line_size() >= 128) MLX5_SET(cqc, cqc, cqe_sz, CQE_STRIDE_128_PAD); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c index 391b4e9c9dc49..7c1d9a9ea4645 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c @@ -334,7 +334,7 @@ static int mlx5e_ptp_alloc_txqsq(struct mlx5e_ptp *c, int txq_ix, sq->mdev = mdev; sq->ch_ix = MLX5E_PTP_CHANNEL_IX; sq->txq_ix = txq_ix; - sq->uar_map = mdev->mlx5e_res.hw_objs.bfreg.map; + sq->uar_map = mdev->priv.bfreg.map; sq->min_inline_mode = params->tx_min_inline_mode; sq->hw_mtu = MLX5E_SW2HW_MTU(params, params->sw_mtu); sq->stats = &c->priv->ptp_stats.sq[tc]; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c index 6ed3a32b7e226..e9e36358c39d1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c @@ -163,17 +163,11 @@ int mlx5e_create_mdev_resources(struct mlx5_core_dev *mdev, bool create_tises) goto err_dealloc_transport_domain; }

- err = mlx5_alloc_bfreg(mdev, &res->bfreg, false, false); - if (err) { - mlx5_core_err(mdev, "alloc bfreg failed, %d\n", err); - goto err_destroy_mkey; - } - if (create_tises) { err = mlx5e_create_tises(mdev, res->tisn); if (err) { mlx5_core_err(mdev, "alloc tises failed, %d\n", err); - goto err_destroy_bfreg; + goto err_destroy_mkey; } res->tisn_valid = true; } @@ -190,8 +184,6 @@ int mlx5e_create_mdev_resources(struct mlx5_core_dev *mdev, bool create_tises)

return 0;

-err_destroy_bfreg: - mlx5_free_bfreg(mdev, &res->bfreg); err_destroy_mkey: mlx5_core_destroy_mkey(mdev, res->mkey); err_dealloc_transport_domain: @@ -209,7 +201,6 @@ void mlx5e_destroy_mdev_resources(struct mlx5_core_dev *mdev) mdev->mlx5e_res.dek_priv = NULL; if (res->tisn_valid) mlx5e_destroy_tises(mdev, res->tisn); - mlx5_free_bfreg(mdev, &res->bfreg); mlx5_core_destroy_mkey(mdev, res->mkey); mlx5_core_dealloc_transport_domain(mdev, res->td.tdn); mlx5_core_dealloc_pd(mdev, res->pdn); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 2c82c5100af3c..1a90fd1d44edb 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -1551,7 +1551,7 @@ static int mlx5e_alloc_xdpsq(struct mlx5e_channel *c, sq->pdev = c->pdev; sq->mkey_be = c->mkey_be; sq->channel = c; - sq->uar_map = mdev->mlx5e_res.hw_objs.bfreg.map; + sq->uar_map = mdev->priv.bfreg.map; sq->min_inline_mode = params->tx_min_inline_mode; sq->hw_mtu = MLX5E_SW2HW_MTU(params, params->sw_mtu) - ETH_FCS_LEN; sq->xsk_pool = xsk_pool; @@ -1636,7 +1636,7 @@ static int mlx5e_alloc_icosq(struct mlx5e_channel *c, int err;

sq->channel = c; - sq->uar_map = mdev->mlx5e_res.hw_objs.bfreg.map; + sq->uar_map = mdev->priv.bfreg.map; sq->reserved_room = param->stop_room;

param->wq.db_numa_node = cpu_to_node(c->cpu); @@ -1721,7 +1721,7 @@ static int mlx5e_alloc_txqsq(struct mlx5e_channel *c, sq->priv = c->priv; sq->ch_ix = c->ix; sq->txq_ix = txq_ix; - sq->uar_map = mdev->mlx5e_res.hw_objs.bfreg.map; + sq->uar_map = mdev->priv.bfreg.map; sq->min_inline_mode = params->tx_min_inline_mode; sq->hw_mtu = MLX5E_SW2HW_MTU(params, params->sw_mtu); sq->max_sq_mpw_wqebbs = mlx5e_get_max_sq_aligned_wqebbs(mdev); @@ -1797,7 +1797,7 @@ static int mlx5e_create_sq(struct mlx5_core_dev *mdev, MLX5_SET(sqc, sqc, flush_in_error_en, 1);

MLX5_SET(wq, wq, wq_type, MLX5_WQ_TYPE_CYCLIC); - MLX5_SET(wq, wq, uar_page, mdev->mlx5e_res.hw_objs.bfreg.index); + MLX5_SET(wq, wq, uar_page, mdev->priv.bfreg.index); MLX5_SET(wq, wq, log_wq_pg_sz, csp->wq_ctrl->buf.page_shift - MLX5_ADAPTER_PAGE_SHIFT); MLX5_SET64(wq, wq, dbr_addr, csp->wq_ctrl->db.dma); @@ -2292,7 +2292,7 @@ static int mlx5e_create_cq(struct mlx5e_cq *cq, struct mlx5e_cq_param *param) MLX5_SET(cqc, cqc, cq_period_mode, mlx5e_cq_period_mode(param->cq_period_mode));

MLX5_SET(cqc, cqc, c_eqn_or_apu_element, eqn); - MLX5_SET(cqc, cqc, uar_page, mdev->priv.uar->index); + MLX5_SET(cqc, cqc, uar_page, mdev->priv.bfreg.up->index); MLX5_SET(cqc, cqc, log_page_size, cq->wq_ctrl.buf.page_shift - MLX5_ADAPTER_PAGE_SHIFT); MLX5_SET64(cqc, cqc, dbr_addr, cq->wq_ctrl.db.dma); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c index f3c714ebd9cb4..25499da177bc4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c @@ -307,7 +307,7 @@ create_map_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq,

eqc = MLX5_ADDR_OF(create_eq_in, in, eq_context_entry); MLX5_SET(eqc, eqc, log_eq_size, eq->fbc.log_sz); - MLX5_SET(eqc, eqc, uar_page, priv->uar->index); + MLX5_SET(eqc, eqc, uar_page, priv->bfreg.up->index); MLX5_SET(eqc, eqc, intr, vecidx); MLX5_SET(eqc, eqc, log_page_size, eq->frag_buf.page_shift - MLX5_ADAPTER_PAGE_SHIFT); @@ -320,7 +320,7 @@ create_map_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq, eq->eqn = MLX5_GET(create_eq_out, out, eq_number); eq->irqn = pci_irq_vector(dev->pdev, vecidx); eq->dev = dev; - eq->doorbell = priv->uar->map + MLX5_EQ_DOORBELL_OFFSET; + eq->doorbell = priv->bfreg.up->map + MLX5_EQ_DOORBELL_OFFSET;

err = mlx5_debug_eq_add(dev, eq); if (err) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/aso.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/aso.c index 58bd749b5e4de..129725159a935 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/aso.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/aso.c @@ -100,7 +100,7 @@ static int create_aso_cq(struct mlx5_aso_cq *cq, void *cqc_data)

MLX5_SET(cqc, cqc, cq_period_mode, MLX5_CQ_PERIOD_MODE_START_FROM_EQE); MLX5_SET(cqc, cqc, c_eqn_or_apu_element, eqn); - MLX5_SET(cqc, cqc, uar_page, mdev->priv.uar->index); + MLX5_SET(cqc, cqc, uar_page, mdev->priv.bfreg.up->index); MLX5_SET(cqc, cqc, log_page_size, cq->wq_ctrl.buf.page_shift - MLX5_ADAPTER_PAGE_SHIFT); MLX5_SET64(cqc, cqc, dbr_addr, cq->wq_ctrl.db.dma); @@ -129,7 +129,7 @@ static int mlx5_aso_create_cq(struct mlx5_core_dev *mdev, int numa_node, return -ENOMEM;

MLX5_SET(cqc, cqc_data, log_cq_size, 1); - MLX5_SET(cqc, cqc_data, uar_page, mdev->priv.uar->index); + MLX5_SET(cqc, cqc_data, uar_page, mdev->priv.bfreg.up->index); if (MLX5_CAP_GEN(mdev, cqe_128_always) && cache_line_size() >= 128) MLX5_SET(cqc, cqc_data, cqe_sz, CQE_STRIDE_128_PAD);

@@ -163,7 +163,7 @@ static int mlx5_aso_alloc_sq(struct mlx5_core_dev *mdev, int numa_node, struct mlx5_wq_param param; int err;

- sq->uar_map = mdev->mlx5e_res.hw_objs.bfreg.map; + sq->uar_map = mdev->priv.bfreg.map;

param.db_numa_node = numa_node; param.buf_numa_node = numa_node; @@ -203,7 +203,7 @@ static int create_aso_sq(struct mlx5_core_dev *mdev, int pdn, MLX5_SET(sqc, sqc, ts_format, ts_format);

MLX5_SET(wq, wq, wq_type, MLX5_WQ_TYPE_CYCLIC); - MLX5_SET(wq, wq, uar_page, mdev->mlx5e_res.hw_objs.bfreg.index); + MLX5_SET(wq, wq, uar_page, mdev->priv.bfreg.index); MLX5_SET(wq, wq, log_wq_pg_sz, sq->wq_ctrl.buf.page_shift - MLX5_ADAPTER_PAGE_SHIFT); MLX5_SET64(wq, wq, dbr_addr, sq->wq_ctrl.db.dma); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 8517d4e5d5efc..3df7401f2256c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -1340,10 +1340,9 @@ static int mlx5_load(struct mlx5_core_dev *dev) { int err;

- dev->priv.uar = mlx5_get_uars_page(dev); - if (IS_ERR(dev->priv.uar)) { - mlx5_core_err(dev, "Failed allocating uar, aborting\n"); - err = PTR_ERR(dev->priv.uar); + err = mlx5_alloc_bfreg(dev, &dev->priv.bfreg, false, false); + if (err) { + mlx5_core_err(dev, "Failed allocating bfreg, %d\n", err); return err; }

@@ -1454,7 +1453,7 @@ static int mlx5_load(struct mlx5_core_dev *dev) err_irq_table: mlx5_pagealloc_stop(dev); mlx5_events_stop(dev); - mlx5_put_uars_page(dev, dev->priv.uar); + mlx5_free_bfreg(dev, &dev->priv.bfreg); return err; }

@@ -1479,7 +1478,7 @@ static void mlx5_unload(struct mlx5_core_dev *dev) mlx5_irq_table_destroy(dev); mlx5_pagealloc_stop(dev); mlx5_events_stop(dev); - mlx5_put_uars_page(dev, dev->priv.uar); + mlx5_free_bfreg(dev, &dev->priv.bfreg); }

int mlx5_init_one_devl_locked(struct mlx5_core_dev *dev) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/send.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/send.c index b0595c9b09e42..24ef7d66fa8aa 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/send.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/send.c @@ -690,7 +690,7 @@ static int hws_send_ring_alloc_sq(struct mlx5_core_dev *mdev, size_t buf_sz; int err;

- sq->uar_map = mdev->mlx5e_res.hw_objs.bfreg.map; + sq->uar_map = mdev->priv.bfreg.map; sq->mdev = mdev;

param.db_numa_node = numa_node; @@ -764,7 +764,7 @@ static int hws_send_ring_create_sq(struct mlx5_core_dev *mdev, u32 pdn, MLX5_SET(sqc, sqc, ts_format, ts_format);

MLX5_SET(wq, wq, wq_type, MLX5_WQ_TYPE_CYCLIC); - MLX5_SET(wq, wq, uar_page, mdev->mlx5e_res.hw_objs.bfreg.index); + MLX5_SET(wq, wq, uar_page, mdev->priv.bfreg.index); MLX5_SET(wq, wq, log_wq_pg_sz, sq->wq_ctrl.buf.page_shift - MLX5_ADAPTER_PAGE_SHIFT); MLX5_SET64(wq, wq, dbr_addr, sq->wq_ctrl.db.dma);

@@ -940,7 +940,7 @@ static int hws_send_ring_create_cq(struct mlx5_core_dev *mdev, (__be64 *)MLX5_ADDR_OF(create_cq_in, in, pas));

MLX5_SET(cqc, cqc, c_eqn_or_apu_element, eqn); - MLX5_SET(cqc, cqc, uar_page, mdev->priv.uar->index); + MLX5_SET(cqc, cqc, uar_page, mdev->priv.bfreg.up->index); MLX5_SET(cqc, cqc, log_page_size, cq->wq_ctrl.buf.page_shift - MLX5_ADAPTER_PAGE_SHIFT); MLX5_SET64(cqc, cqc, dbr_addr, cq->wq_ctrl.db.dma);

@@ -963,7 +963,7 @@ static int hws_send_ring_open_cq(struct mlx5_core_dev *mdev, if (!cqc_data) return -ENOMEM;

- MLX5_SET(cqc, cqc_data, uar_page, mdev->priv.uar->index); + MLX5_SET(cqc, cqc_data, uar_page, mdev->priv.bfreg.up->index); MLX5_SET(cqc, cqc_data, log_cq_size, ilog2(queue->num_entries));

err = hws_send_ring_alloc_cq(mdev, numa_node, queue, cqc_data, cq); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/wc.c b/drivers/net/ethernet/mellanox/mlx5/core/wc.c index 2f0316616fa40..0d3591ff22733 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/wc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/wc.c @@ -94,7 +94,7 @@ static int create_wc_cq(struct mlx5_wc_cq *cq, void *cqc_data)

MLX5_SET(cqc, cqc, cq_period_mode, MLX5_CQ_PERIOD_MODE_START_FROM_EQE); MLX5_SET(cqc, cqc, c_eqn_or_apu_element, eqn); - MLX5_SET(cqc, cqc, uar_page, mdev->priv.uar->index); + MLX5_SET(cqc, cqc, uar_page, mdev->priv.bfreg.up->index); MLX5_SET(cqc, cqc, log_page_size, cq->wq_ctrl.buf.page_shift - MLX5_ADAPTER_PAGE_SHIFT); MLX5_SET64(cqc, cqc, dbr_addr, cq->wq_ctrl.db.dma); @@ -116,7 +116,7 @@ static int mlx5_wc_create_cq(struct mlx5_core_dev *mdev, struct mlx5_wc_cq *cq) return -ENOMEM;

MLX5_SET(cqc, cqc, log_cq_size, TEST_WC_LOG_CQ_SZ); - MLX5_SET(cqc, cqc, uar_page, mdev->priv.uar->index); + MLX5_SET(cqc, cqc, uar_page, mdev->priv.bfreg.up->index); if (MLX5_CAP_GEN(mdev, cqe_128_always) && cache_line_size() >= 128) MLX5_SET(cqc, cqc, cqe_sz, CQE_STRIDE_128_PAD);

diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 10fe492e1fedc..c185f082748ae 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -611,7 +611,7 @@ struct mlx5_priv { struct mlx5_ft_pool *ft_pool;

struct mlx5_bfreg_data bfregs; - struct mlx5_uars_page *uar; + struct mlx5_sq_bfreg bfreg; #ifdef CONFIG_MLX5_SF struct mlx5_vhca_state_notifier *vhca_state_notifier; struct mlx5_sf_dev_table *sf_dev_table; @@ -657,7 +657,6 @@ struct mlx5e_resources { u32 pdn; struct mlx5_td td; u32 mkey; - struct mlx5_sq_bfreg bfreg; #define MLX5_MAX_NUM_TC 8 u32 tisn[MLX5_MAX_PORTS][MLX5_MAX_NUM_TC]; bool tisn_valid;

6.17-stable review patch. If anyone has any objections, please let me know.

------------------

From: Xuan Zhuo xuanzhuo@linux.alibaba.com

[ Upstream commit 0eff2eaa5322b5b141ff5d5ded26fac4a52b5f7b ]

The purpose of commit 703eec1b2422 ("virtio_net: fixing XDP for fully checksummed packets handling") is to record the flags in advance, as their value may be overwritten in the XDP case. However, the flags recorded under big mode are incorrect, because in big mode, the passed buf does not point to the rx buffer, but rather to the page of the submitted buffer. This commit fixes this issue.

For the small mode, the commit c11a49d58ad2 ("virtio_net: Fix mismatched buf address when unmapping for small packets") fixed it.

Tested-by: Alyssa Ross hi@alyssa.is Fixes: 703eec1b2422 ("virtio_net: fixing XDP for fully checksummed packets handling") Signed-off-by: Xuan Zhuo xuanzhuo@linux.alibaba.com Acked-by: Jason Wang jasowang@redhat.com Acked-by: Michael S. Tsirkin mst@redhat.com Link: https://patch.msgid.link/20251111090828.23186-1-xuanzhuo@linux.alibaba.com Signed-off-by: Paolo Abeni pabeni@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/virtio_net.c | 16 +++++++++++----- 1 file changed, 11 insertions(+), 5 deletions(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 35bdbf1f45ee6..36b1bc0d56846 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -2632,22 +2632,28 @@ static void receive_buf(struct virtnet_info *vi, struct receive_queue *rq, return; }

- /* 1. Save the flags early, as the XDP program might overwrite them. + /* About the flags below: + * 1. Save the flags early, as the XDP program might overwrite them. * These flags ensure packets marked as VIRTIO_NET_HDR_F_DATA_VALID * stay valid after XDP processing. * 2. XDP doesn't work with partially checksummed packets (refer to * virtnet_xdp_set()), so packets marked as * VIRTIO_NET_HDR_F_NEEDS_CSUM get dropped during XDP processing. */ - flags = ((struct virtio_net_common_hdr *)buf)->hdr.flags;

- if (vi->mergeable_rx_bufs) + if (vi->mergeable_rx_bufs) { + flags = ((struct virtio_net_common_hdr *)buf)->hdr.flags; skb = receive_mergeable(dev, vi, rq, buf, ctx, len, xdp_xmit, stats); - else if (vi->big_packets) + } else if (vi->big_packets) { + void *p = page_address((struct page *)buf); + + flags = ((struct virtio_net_common_hdr *)p)->hdr.flags; skb = receive_big(dev, vi, rq, buf, len, stats); - else + } else { + flags = ((struct virtio_net_common_hdr *)buf)->hdr.flags; skb = receive_small(dev, vi, rq, buf, ctx, len, xdp_xmit, stats); + }

if (unlikely(!skb)) return;