6.18.40-rc1 review
Subsystems (13)
Greg Kroah-Hartman
maintainerPATCH 799/1611 perf bpf: Validate array presence before casting BPF prog info pointers
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Arnaldo Carvalho de Melo <[email protected]>
[ Upstream commit 5ebf4137d23a4fd6c0cc6a6fb766ee60d2b09193 ]
Several functions cast bpf_prog_info fields (jited_ksyms, jited_func_lens, jited_prog_insns) from u64 to pointers and dereference them. These fields are only valid pointers if bpil_offs_to_addr() converted their file offsets to addresses, which only happens when the corresponding PERF_BPIL_* bits are set in info_linear->arrays.
A crafted perf.data can leave these bits unset while setting non-zero counts and offset values, causing the functions to dereference raw file offsets as pointers.
Add array bitmask validation to all perf.data processing paths:
- __bpf_event__print_bpf_prog_info(): check JITED_KSYMS and JITED_FUNC_LENS (changed to take struct perf_bpil *)
- machine__process_bpf_event_load(): check JITED_KSYMS
- bpf_read(): check JITED_INSNS before memcpy from jited_prog_insns
- dso__disassemble_filename(): check JITED_INSNS before returning jited_prog_insns pointer
--- tools/perf/util/bpf-event.c | 20 +++++++++++++++++--- tools/perf/util/bpf-event.h | 4 ++-- tools/perf/util/dso.c | 10 ++++++++++ tools/perf/util/header.c | 3 +-- 4 files changed, 30 insertions(+), 7 deletions(-)
tools/perf/util/bpf-event.c +17 -3
@@ -59,6 +59,10 @@ static int machine__process_bpf_event_load(struct machine *machine,return 0 ; info_linear = info_node->info_linear; +/* jited_ksyms is only valid if bpil_offs_to_addr() converted it */ +if (!(info_linear->arrays & (1UL <<PERF_BPIL_JITED_KSYMS ))) +return 0 ; +for (i =0 ; i < info_linear->info.nr_jited_ksyms; i++) {u64 *addrs = (u64 *)(uintptr_t )(info_linear->info.jited_ksyms);u64 addr = addrs[i];
@@ -961,12 +965,15 @@ int evlist__add_bpf_sb_event(struct evlist *evlist, struct perf_env *env)return evlist__add_sb_event (evlist, &attr, bpf_event__sb_cb, env); } -void __bpf_event__print_bpf_prog_info (struct bpf_prog_info *info, +void __bpf_event__print_bpf_prog_info (struct perf_bpil *info_linear,struct perf_env *env,FILE *fp) { -__u32 *prog_lens = (__u32 *)(uintptr_t )(info->jited_func_lens); -__u64 *prog_addrs = (__u64 *)(uintptr_t )(info->jited_ksyms); +struct bpf_prog_info *info = &info_linear->info; +__u64 required_arrays = (1UL <<PERF_BPIL_JITED_KSYMS ) | + (1UL <<PERF_BPIL_JITED_FUNC_LENS ); +__u32 *prog_lens; +__u64 *prog_addrs;char name[KSYM_NAME_LEN ];struct btf *btf =NULL ;u32 sub_prog_cnt, i;
@@ -976,6 +983,13 @@ void __bpf_event__print_bpf_prog_info(struct bpf_prog_info *info, sub_prog_cnt != info->nr_jited_func_lens)return ; +/* Ensure the arrays were present and converted by bpil_offs_to_addr() */ +if ((info_linear->arrays & required_arrays) != required_arrays) +return ; + + prog_lens = (__u32 *)(uintptr_t )(info->jited_func_lens); + prog_addrs = (__u64 *)(uintptr_t )(info->jited_ksyms); +if (info->btf_id) {struct btf_node *node;
tools/perf/util/bpf-event.h +2 -2
@@ -40,7 +40,7 @@ struct btf_node {int machine__process_bpf (struct machine *machine,union perf_event *event,struct perf_sample *sample);int evlist__add_bpf_sb_event (struct evlist *evlist,struct perf_env *env); -void __bpf_event__print_bpf_prog_info (struct bpf_prog_info *info, +void __bpf_event__print_bpf_prog_info (struct perf_bpil *info_linear,struct perf_env *env,FILE *fp);void bpf_metadata_free (struct bpf_metadata *metadata);
@@ -58,7 +58,7 @@ static inline int evlist__add_bpf_sb_event(struct evlist *evlist __maybe_unused,return 0 ; } -static inline void __bpf_event__print_bpf_prog_info (struct bpf_prog_info *info__maybe_unused , +static inline void __bpf_event__print_bpf_prog_info (struct perf_bpil *info_linear__maybe_unused ,struct perf_env *env__maybe_unused ,FILE *fp__maybe_unused ) {
tools/perf/util/dso.c +10 -0
@@ -882,6 +882,12 @@ static ssize_t bpf_read(struct dso *dso, u64 offset, char *data)return -1 ; } +/* jited_prog_insns is only valid if bpil_offs_to_addr() converted it */ +if (!(node->info_linear->arrays & (1UL <<PERF_BPIL_JITED_INSNS ))) { +dso__data (dso)->status =DSO_DATA_STATUS_ERROR ; +return -1 ; + } + len = node->info_linear->info.jited_prog_len; buf = (u8 *)(uintptr_t )node->info_linear->info.jited_prog_insns;
@@ -1927,6 +1933,10 @@ const u8 *dso__read_symbol(struct dso *dso, const char *symfs_filename,return NULL ; } info_linear = info_node->info_linear; +if (!(info_linear->arrays & (1UL <<PERF_BPIL_JITED_INSNS ))) { + errno =SYMBOL_ANNOTATE_ERRNO__BPF_MISSING_BTF ; +return NULL ; + }assert (len <= info_linear->info.jited_prog_len); *out_buf_len = len;return (const u8 *)(uintptr_t )(info_linear->info.jited_prog_insns);
tools/perf/util/header.c +1 -2
@@ -1825,8 +1825,7 @@ static void print_bpf_prog_info(struct feat_fd *ff, FILE *fp) node = rb_entry(next, struct bpf_prog_info_node, rb_node); next =rb_next (&node->rb_node); -__bpf_event__print_bpf_prog_info (&node->info_linear->info, - env, fp); +__bpf_event__print_bpf_prog_info (node->info_linear, env, fp); }up_read (&env->bpf_progs.lock);
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 800/1611 perf dso: Set standard errno on decompression failure
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Arnaldo Carvalho de Melo <[email protected]>
[ Upstream commit 1a5f9334a45a6b0c1cd7341cc72a3b87adad1d27 ]
dso__get_filename() sets errno to a negative custom DSO_LOAD_ERRNO value when kernel module decompression fails:
errno = *dso__load_errno(dso); /* e.g. -9996 */
The caller __open_dso() then computes fd = -errno, producing a large positive value (9996) that looks like a valid file descriptor. This can cause close_data_fd() to close an unrelated fd used by another subsystem.
Set errno to EIO instead. The detailed error code is already stored in dso__load_errno(dso) for diagnostic messages.
--- tools/perf/util/dso.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-)
tools/perf/util/dso.c +7 -1
@@ -602,7 +602,13 @@ static char *dso__get_filename(struct dso *dso, const char *root_dir,size_t len =sizeof (newpath);if (dso__decompress_kmodule_path (dso, name, newpath, len) <0 ) { - errno = *dso__load_errno (dso); +/* +* Use a standard errno value, not the negative custom +* DSO_LOAD_ERRNO stored in dso__load_errno(dso): +* __open_dso() computes fd = -errno, so a negative +* errno produces a positive fd that looks valid. +*/ + errno =EIO ; goto out; }
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 801/1611 ASoC: tlv320aic3x: restrict CLKDIV bypass Q values in dual-rate mode
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Sen Wang <[email protected]>
[ Upstream commit fdf043f5f3bae150b678feae3d7bb1beed87ec14 ]
The datasheet documents that when the PLL is disabled and dual-rate mode is enabled, only Q values {4, 8, 9, 12, 16} are valid for the CLKDIV bypass path; all other Q values produce invalid bitclock output.
The existing loop iterates Q from 2 to 17 without this restriction, causing silent audio failure when an out-of-spec Q is picked.
Restrict the Q search to the allowed set in dual-rate mode.
--- sound/soc/codecs/tlv320aic3x.c | 25 +++++++++++++++++++------ 1 file changed, 19 insertions(+), 6 deletions(-)
sound/soc/codecs/tlv320aic3x.c +19 -6
@@ -1049,11 +1049,13 @@ static int aic3x_hw_params(struct snd_pcm_substream *substream,struct snd_pcm_hw_params *params, struct snd_soc_dai *dai) { + static const u8 dual_rate_q[] = {4, 8, 9, 12, 16};struct snd_soc_component *component = dai->component;struct aic3x_priv *aic3x =snd_soc_component_get_drvdata (component);int codec_clk =0 , bypass_pll =0 , fsref, last_clk =0 ;u8 data, j, r, p, pll_q, pll_p =1 , pll_r =1 , pll_j =1 ;u16 d, pll_d =1 ; +bool dual_rate;int clk;int width = aic3x->slot_width;
@@ -1079,14 +1081,25 @@ static int aic3x_hw_params(struct snd_pcm_substream *substream,/* Fsref can be 44100 or 48000 */ fsref = (params_rate (params) %11025 ==0 ) ?44100 :48000 ; + dual_rate =params_rate (params) >=64000 ;/* Try to find a value for Q which allows us to bypass the PLL and * generate CODEC_CLK directly. */ -for (pll_q =2 ; pll_q <18 ; pll_q++) -if (aic3x->sysclk / (128 * pll_q) == fsref) { - bypass_pll =1 ; -break ; +if (dual_rate) { +for (int i =0 ; i <ARRAY_SIZE (dual_rate_q); i++) { + pll_q = dual_rate_q[i]; +if (aic3x->sysclk / (128 * pll_q) == fsref) { + bypass_pll =1 ; +break ; + } } + }else { +for (pll_q =2 ; pll_q <18 ; pll_q++) +if (aic3x->sysclk / (128 * pll_q) == fsref) { + bypass_pll =1 ; +break ; + } + }if (bypass_pll) { pll_q &=0xf ;
@@ -1106,13 +1119,13 @@ static int aic3x_hw_params(struct snd_pcm_substream *substream,* right DAC to right channel input */ data = (LDAC2LCH |RDAC2RCH ); data |= (fsref ==44100 ) ?FSREF_44100 :FSREF_48000 ; -if (params_rate (params) >=64000 ) +if (dual_rate) data |=DUAL_RATE_MODE ;snd_soc_component_write (component,AIC3X_CODEC_DATAPATH_REG , data);/* codec sample rate select */ data = (fsref *20 ) /params_rate (params); -if (params_rate (params) <64000 ) +if (!dual_rate) data /=2 ; data /=5 ; data -=2 ;
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 802/1611 drm/amdkfd: Avoid double-unpin of DOORBELL/MMIO BOs on free
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Yunxiang Li <[email protected]>
[ Upstream commit 3f0cc1735273a57c5116710cf0202e12152f59cc ]
amdgpu_amdkfd_gpuvm_free_memory_of_gpu() unpinned DOORBELL and MMIO remap BOs (which are pinned at allocation time) before checking whether the BO is still mapped to the GPU. When the BO is still mapped, the function returns -EBUSY and leaves the BO alive, but it has already been unpinned. The BO is then unpinned again when it is finally freed during process teardown, triggering a ttm_bo_unpin() underflow warning:
WARNING: CPU: 18 PID: 15066 at ttm/ttm_bo.c:650 amdttm_bo_unpin+0x6d/0x80 [amdttm] Workqueue: kfd_process_wq kfd_process_wq_release [amdgpu] RIP: 0010:amdttm_bo_unpin+0x6d/0x80 [amdttm] Call Trace: amdgpu_bo_unpin+0x1a/0x90 [amdgpu] amdgpu_amdkfd_gpuvm_unpin_bo+0x31/0xb0 [amdgpu] amdgpu_amdkfd_gpuvm_free_memory_of_gpu+0x3bf/0x460 [amdgpu] kfd_process_free_outstanding_kfd_bos+0xd4/0x170 [amdgpu] kfd_process_wq_release+0x109/0x1b0 [amdgpu] process_one_work+0x1e2/0x3b0 worker_thread+0x50/0x3a0 kthread+0xdd/0x100 ret_from_fork+0x29/0x50
Move the unpin after the mapped_to_gpu_memory check so it only happens once we are committed to freeing the BO.
--- drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-)
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c +9 -7
@@ -1896,13 +1896,6 @@ int amdgpu_amdkfd_gpuvm_free_memory_of_gpu(mutex_lock (&mem->lock); -/* Unpin MMIO/DOORBELL BO's that were pinned during allocation */ -if (mem->alloc_flags & - (KFD_IOC_ALLOC_MEM_FLAGS_DOORBELL | -KFD_IOC_ALLOC_MEM_FLAGS_MMIO_REMAP )) { -amdgpu_amdkfd_gpuvm_unpin_bo (mem->bo); - } - mapped_to_gpu_memory = mem->mapped_to_gpu_memory; is_imported = mem->is_imported;mutex_unlock (&mem->lock);
@@ -1916,6 +1909,15 @@ int amdgpu_amdkfd_gpuvm_free_memory_of_gpu(return -EBUSY ; } +/* At this point the BO is guaranteed to be freed, so unpin the +* MMIO/DOORBELL BOs that were pinned during allocation. +*/ +if (mem->alloc_flags & + (KFD_IOC_ALLOC_MEM_FLAGS_DOORBELL | +KFD_IOC_ALLOC_MEM_FLAGS_MMIO_REMAP )) { +amdgpu_amdkfd_gpuvm_unpin_bo (mem->bo); + } +/* Make sure restore workers don't access the BO any more */ mutex_lock (&process_info->lock);list_del (&mem->validate_list);
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 803/1611 drm/amd/display: Fix mem_type change detection for async flips
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Matthew Schwartz <[email protected]>
[ Upstream commit 8e792f018e10e68f488f279fbd4f38009a2e066d ]
[Why]amdgpu_dm_crtc_mem_type_changed() fetches the "old" and "new" plane state with two drm_atomic_get_plane_state() calls, which both return the new state. It compares a state against itself, so it never detects a mem_type change and never rejects the async flip.
On DCN 3.0.1, this shows up as intermittent corruption when a single DCC plane is scanned out with immediate flips under gamescope and its buffer moves between the VRAM carveout and GTT.
[How]
Use drm_atomic_get_old_plane_state() and drm_atomic_get_new_plane_state() to compare the actual old and new states. These return NULL rather than an error pointer for a plane that is not part of the commit, so the IS_ERR() check becomes a NULL check that skips those planes, such as an unmodified cursor still in the CRTC's plane_mask.
--- drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-)
drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +4 -6
@@ -12177,13 +12177,11 @@ static bool amdgpu_dm_crtc_mem_type_changed(struct drm_device *dev,struct drm_plane_state *new_plane_state, *old_plane_state;drm_for_each_plane_mask (plane, dev, crtc_state->plane_mask) { - new_plane_state =drm_atomic_get_plane_state (state, plane); - old_plane_state =drm_atomic_get_plane_state (state, plane); + new_plane_state =drm_atomic_get_new_plane_state (state, plane); + old_plane_state =drm_atomic_get_old_plane_state (state, plane); -if (IS_ERR (new_plane_state) ||IS_ERR (old_plane_state)) { -drm_err (dev,"Failed to get plane state for plane %s\n" , plane->name); -return false; - } +if (!old_plane_state || !new_plane_state) +continue ;if (old_plane_state->fb && new_plane_state->fb &&get_mem_type (old_plane_state->fb) !=get_mem_type (new_plane_state->fb))
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 804/1611 drm/amdkfd: fix list_del corruption in kfd_criu_resume_svm
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Mario Limonciello <[email protected]>
[ Upstream commit 8fa5655da368d0306c03e9dc9cda8ae2a7840926 ]
The cleanup tail of kfd_criu_resume_svm() walks svms->criu_svm_metadata_list and kfree()s each struct criu_svm_metadata without removing it from the list. The list head is left pointing at freed kmalloc-96 objects.
A second AMDKFD_IOC_CRIU_OP from the same process re-enters: list_empty() reads the dangling ->next (use-after-free), the loop walks freed entries, and each is kfree()'d again (double-free). This is reachable by an unprivileged render-group user via /dev/kfd with no capabilities required.
Add list_del() before the kfree() so the list is properly emptied. The list_for_each_entry_safe() iterator already caches the next pointer, so unlinking during the walk is safe.
--- drivers/gpu/drm/amd/amdkfd/kfd_svm.c | 1 + 1 file changed, 1 insertion(+)
drivers/gpu/drm/amd/amdkfd/kfd_svm.c +1 -0
@@ -4063,6 +4063,7 @@ int kfd_criu_resume_svm(struct kfd_process *p)list_for_each_entry_safe (criu_svm_md, next, &svms->criu_svm_metadata_list, list) {pr_debug ("freeing criu_svm_md[]\n\tstart: 0x%llx\n" , criu_svm_md->data.start_addr); +list_del (&criu_svm_md->list);kfree (criu_svm_md); }
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 805/1611 drm/amdgpu: initialize irq.lock spinlock earlier
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Thadeu Lima de Souza Cascardo <[email protected]>
[ Upstream commit a2b270c0ecf6d95bcd14ef4c20d0301a88143ff5 ]
If there is an early failure during amdgpu probe, like missing firmware, it will end up calling amdgpu_irq_disable_all, which takes irq.lock spinlock without it being initialized.
Initializing irq.lock earlier at amdgpu_device_init fixes the issue.
[ 79.334079] INFO: trying to register non-static key. [ 79.334081] The code is fine but needs lockdep annotation, or maybe [ 79.334083] you didn't initialize this object before use? [ 79.334084] turning off the locking correctness validator. [ 79.334088] CPU: 2 UID: 0 PID: 1819 Comm: bash Not tainted 7.1.0-rc5-gfd06300b2348 #96 PREEMPT 8e8f461221633dae3c832d6689eaf0546c0ed4cd [ 79.334092] Hardware name: Valve Jupiter/Jupiter, BIOS F7A0133 08/05/2024 [ 79.334094] Call Trace: [ 79.334095] <TASK> [ 79.334097] dump_stack_lvl+0x5d/0x80 [ 79.334103] register_lock_class+0x7af/0x7c0 [ 79.334109] __lock_acquire+0x416/0x2610 [ 79.334114] lock_acquire+0xcf/0x310 [ 79.334117] ? amdgpu_irq_disable_all+0x3b/0xf0 [amdgpu c88bab43d391d519ad0d5c8e5a099b4aceefa180] [ 79.334503] ? _raw_spin_lock_irqsave+0x53/0x60 [ 79.334508] _raw_spin_lock_irqsave+0x3f/0x60 [ 79.334510] ? amdgpu_irq_disable_all+0x3b/0xf0 [amdgpu c88bab43d391d519ad0d5c8e5a099b4aceefa180] [ 79.334881] amdgpu_irq_disable_all+0x3b/0xf0 [amdgpu c88bab43d391d519ad0d5c8e5a099b4aceefa180] [ 79.335240] amdgpu_device_fini_hw+0x90/0x32c [amdgpu c88bab43d391d519ad0d5c8e5a099b4aceefa180] [ 79.335704] amdgpu_driver_load_kms.cold+0x22/0x44 [amdgpu c88bab43d391d519ad0d5c8e5a099b4aceefa180] [ 79.336159] amdgpu_pci_probe+0x204/0x440 [amdgpu c88bab43d391d519ad0d5c8e5a099b4aceefa180] [ 79.336494] local_pci_probe+0x3c/0x80 [ 79.336500] pci_call_probe+0x55/0x2e0 [ 79.336505] ? _raw_spin_unlock+0x2d/0x50 [ 79.336508] ? pci_match_device+0x157/0x180 [ 79.336512] pci_device_probe+0x9b/0x170 [ 79.336516] really_probe+0xd5/0x370 [ 79.336521] __driver_probe_device+0x84/0x150 [ 79.336525] device_driver_attach+0x47/0xb0 [ 79.336528] bind_store+0x73/0xc0 [ 79.336531] kernfs_fop_write_iter+0x176/0x250 [ 79.336536] vfs_write+0x24d/0x560 [ 79.336542] ksys_write+0x71/0xe0 [ 79.336546] do_syscall_64+0x122/0x710 [ 79.336550] ? do_syscall_64+0xd1/0x710 [ 79.336553] entry_SYSCALL_64_after_hwframe+0x4b/0x53 [ 79.336557] RIP: 0033:0x7f92fd675006 [ 79.336561] Code: 5d e8 41 8b 93 08 03 00 00 59 5e 48 83 f8 fc 75 19 83 e2 39 83 fa 08 75 11 e8 26 ff ff ff 66 0f 1f 44 00 00 48 8b 45 10 0f 05 <48> 8b 5d f8 c9 c3 0f 1f 40 00 f3 0f 1e fa 55 48 89 e5 48 83 ec 08 [ 79.336562] RSP: 002b:00007ffe4fa867a0 EFLAGS: 00000202 ORIG_RAX: 0000000000000001 [ 79.336565] RAX: ffffffffffffffda RBX: 000000000000000d RCX: 00007f92fd675006 [ 79.336567] RDX: 000000000000000d RSI: 000055b2dfce59b0 RDI: 0000000000000001 [ 79.336568] RBP: 00007ffe4fa867c0 R08: 0000000000000000 R09: 0000000000000000 [ 79.336569] R10: 0000000000000000 R11: 0000000000000202 R12: 000000000000000d [ 79.336570] R13: 000055b2dfce59b0 R14: 00007f92fd7ca5c0 R15: 000055b2dfdbaf70 [ 79.336574] </TASK>
--- drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 2 ++ drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c | 2 -- 2 files changed, 2 insertions(+), 2 deletions(-)
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +2 -0
@@ -4504,6 +4504,8 @@ int amdgpu_device_init(struct amdgpu_device *adev,mutex_init (&adev->vcn.workload_profile_mutex);mutex_init (&adev->userq_mutex); +spin_lock_init (&adev->irq.lock); +amdgpu_device_init_apu_flags (adev); r =amdgpu_device_check_arguments (adev);
drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c +0 -2
@@ -274,8 +274,6 @@ int amdgpu_irq_init(struct amdgpu_device *adev)unsigned int irq, flags;int r; -spin_lock_init (&adev->irq.lock); -/* Enable MSI if not disabled by module parameter */ adev->irq.msi_enabled = false;
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 806/1611 octeontx2-pf: Fix leak of SQ timestamp buffer on teardown
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Ratheesh Kannoth <[email protected]>
[ Upstream commit a056db30de92945ff8ee6033096678bfbae878e3 ]
The send-queue timestamp ring is allocated with qmem_alloc() when timestamping is used, but otx2_free_sq_res() never freed sq->timestamps, leaking that memory across ifdown and device removal. Add the missing qmem_free() alongside the other SQ companion buffers.
--- drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c | 1 + 1 file changed, 1 insertion(+)
drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c +1 -0
@@ -1578,6 +1578,7 @@ static void otx2_free_sq_res(struct otx2_nic *pf)qmem_free (pf->dev, sq->sqe_ring);qmem_free (pf->dev, sq->cpt_resp);qmem_free (pf->dev, sq->tso_hdrs); +qmem_free (pf->dev, sq->timestamps);kfree (sq->sg);kfree (sq->sqb_ptrs); }
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 807/1611 net: psample: fix info leak in PSAMPLE_ATTR_DATA
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Jakub Kicinski <[email protected]>
[ Upstream commit aedd02af1f8b0bceb7f42f5a21c41634ca9ed390 ]
psample open codes nla_put() presumably to avoid wiping the data with 0s just to override it with packet data. This open coding is missing clearing the pad, however, each netlink attr is padded to 4B and data_len may not be divisible by 4B.
--- net/psample/psample.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-)
net/psample/psample.c +4 -2
@@ -476,15 +476,17 @@ void psample_sample_packet(struct psample_group *group, goto error;if (data_len) { -int nla_len =nla_total_size (data_len); +int nla_len =nla_attr_size (data_len);struct nlattr *nla; nla =skb_put (nl_skb, nla_len); nla->nla_type =PSAMPLE_ATTR_DATA ; - nla->nla_len =nla_attr_size (data_len); + nla->nla_len = nla_len;if (skb_copy_bits (skb,0 ,nla_data (nla), data_len)) goto error; + +skb_put_zero (nl_skb,nla_padlen (data_len)); }#ifdef CONFIG_INET
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 808/1611 sctp: hold socket lock when dumping endpoints in sctp_diag
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Xin Long <[email protected]>
[ Upstream commit 7d8297e26b4e20b5d1c3c3fe51fe81a1c7fbc823 ]
SCTP_DIAG endpoint dumping was traversing endpoint address lists without holding lock_sock(), while those lists could change concurrently via socket operations (e.g., bindx changes). This creates a race where nla_reserve() counts addresses under RCU protection, but the subsequent copy may see fewer entries, potentially leaking uninitialized memory to userspace.
Fix this by:
- Taking a reference on each endpoint during hash traversal
- Moving socket operations (lock_sock()) outside read_lock_bh()
- Serializing address list access during dump
- Reworking sctp_for_each_endpoint() to support restart-based traversal with (net, pos) tracking
Also:
- Add WARN_ON_ONCE() for inconsistent address counts
- Fix idiag_states filtering for LISTEN vs association cases
- Skip dumping endpoints being freed (ep->base.dead)
- Move dump position tracking into iterator, removing cb->args[4] and its comment for sctp_ep_dump().,
- Update the comment for cb->args[4] and remove the comment for unused cb->args[5] for sctp_sock_dump().
Note: traversal is restart-based and may re-scan buckets multiple times, but this is acceptable due to small bucket sizes and required to support sleeping-safe callbacks.
This issue was reported by Nico Yip (@_cyeaa_) working with TrendAI Zero Day Initiative.
--- include/net/sctp/sctp.h | 3 +- net/sctp/diag.c | 67 ++++++++++++++++++++--------------------- net/sctp/socket.c | 29 +++++++++++++----- 3 files changed, 56 insertions(+), 43 deletions(-)
include/net/sctp/sctp.h +2 -1
@@ -112,7 +112,8 @@ int sctp_transport_lookup_process(sctp_callback_t cb, struct net *net, const union sctp_addr *paddr, void *p, int dif);int sctp_transport_traverse_process (sctp_callback_t cb,sctp_callback_t cb_done,struct net *net,int *pos,void *p); -int sctp_for_each_endpoint (int (*cb)(struct sctp_endpoint *,void *),void *p); +int sctp_for_each_endpoint (int (*cb)(struct sctp_endpoint *,void *), +struct net *net,int *pos,void *p);int sctp_get_sctp_info (struct sock *sk,struct sctp_association *asoc,struct sctp_info *info);
net/sctp/diag.c +32 -35
121 lines not on this page · raw message
net/sctp/socket.c +22 -7
@@ -5310,24 +5310,39 @@ struct sctp_transport *sctp_transport_get_idx(struct net *net, }int sctp_for_each_endpoint (int (*cb)(struct sctp_endpoint *,void *), -void *p) { -int err =0 ; -int hash =0 ; -struct sctp_endpoint *ep; +struct net *net,int *pos,void *p) { +int err, hash =0 , idx =0 , start;struct sctp_hashbucket *head; +struct sctp_endpoint *ep;for (head = sctp_ep_hashtable; hash < sctp_ep_hashsize; hash++, head++) { + start = idx; +again:read_lock_bh (&head->lock);sctp_for_each_hentry (ep, &head->chain) { - err =cb (ep, p); -if (err) +if (sock_net (ep->base.sk) != net) +continue ; +if (idx++ >= *pos) { +sctp_endpoint_hold (ep);break ; + } }read_unlock_bh (&head->lock); + +if (ep) { + err =cb (ep, p); +sctp_endpoint_put (ep); +if (err) +return err; + (*pos)++; + + idx = start; + goto again; + } } -return err; +return 0 ; }EXPORT_SYMBOL_GPL (sctp_for_each_endpoint);
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 809/1611 ALSA: usb-audio: qcom: reject stream disable with no active interface
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Michael Bommarito <[email protected]>
[ Upstream commit bdb640be82e645e2828731648f485224d0c2587b ]
handle_uaudio_stream_req() resolves an interface index with info_idx_from_ifnum(), which returns -EINVAL when no interface matches. The enable branch and the response: cleanup label both guard against a negative index, but the disable branch does not: it forms info = &uadev[pcm_card_num].info[info_idx] and dereferences it.
uadev[].info is a pointer allocated only when a stream is first enabled, so a negative info_idx on the disable path is unsafe in two ways:
- If the card was never enabled, .info is NULL and &info[-EINVAL] is a wild pointer; reading info->data_ep_pipe faults (kernel oops).
- If the card was enabled at least once (.info allocated) and the disable names an interface that does not match, &info[-EINVAL] points before the allocation; info->data_ep_pipe / info->sync_ep_pipe are an out-of-bounds slab read and, when non-zero, an out-of-bounds 4-byte write (both pipe fields are cleared to 0). That is memory corruption, not just a NULL dereference.
The request is reachable from unprivileged local userspace over AF_QIPCRTR. Reject a disable request with no resolved interface, matching the guard the enable path already has.
--- sound/usb/qcom/qc_audio_offload.c | 5 +++++ 1 file changed, 5 insertions(+)
sound/usb/qcom/qc_audio_offload.c +5 -0
@@ -1648,6 +1648,11 @@ static void handle_uaudio_stream_req(struct qmi_handle *handle, subs->opened =0 ; } }else { +if (info_idx <0 ) { + ret = -EINVAL ; + goto response; + } + info = &uadev[pcm_card_num].info[info_idx];if (info->data_ep_pipe) { ep = usb_pipe_endpoint(uadev[pcm_card_num].udev,
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 810/1611 ALSA: usb-audio: qcom: clear opened when stream enable fails
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Michael Bommarito <[email protected]>
[ Upstream commit 3c7af07943b2718087ae791cad450af5cf646d90 ]
On enable, subs->opened is set before the service_interval is validated; an invalid interval jumps to the response label without clearing it, so the substream is wedged at -EBUSY until a disable or disconnect.
Clear subs->opened on the enable error path.
--- sound/usb/qcom/qc_audio_offload.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-)
sound/usb/qcom/qc_audio_offload.c +6 -1
@@ -1626,8 +1626,13 @@ static void handle_uaudio_stream_req(struct qmi_handle *handle,if (req_msg->service_interval_valid) { ret =get_data_interval_from_si (subs, req_msg->service_interval); -if (ret == -EINVAL ) +if (ret == -EINVAL ) { +if (req_msg->enable) { +guard (mutex)(&chip->mutex); + subs->opened =0 ; + } goto response; + } datainterval = ret; }
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 811/1611 PCI: iproc: Restore .map_irq() for the platform bus driver
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Mark Tomlinson <[email protected]>
[ Upstream commit 3c2e6cc6affa8acdb99a580be1f8f297edf54204 ]
Commit b64aa11eb2dd ("PCI: Set bridge map_irq and swizzle_irq to default functions") moved the assignment of default .map_irq() callback to devm_of_pci_bridge_init() and removed the initialization of 'iproc_pcie::map_irq' in platform bus driver. This led to the callback getting assigned the NULL pointer for platform bus driver, thereby breaking the INTx functionality, since 'iproc_pcie::map_irq' overrides the 'pci_host_bridge::map_irq' callback in iproc_pcie_setup().
This issue only affected the iproc platform bus driver as this driver relies on the default callback for non-PAXC controllers. iproc-brcm driver was already providing the custom mapping function, so it was unaffected.
Restore the original (and intended) behaviour to use the default map_irq function by removing the local 'iproc_pcie::map_irq' pointer and directly assigning the 'pci_host_bridge::map_irq' callback in iproc-bcma driver. This ensures that the default 'map_irq' callback is used for platform bus driver and only iproc-brcm driver overrides it with a custom one.
--- drivers/pci/controller/pcie-iproc-bcma.c | 2 +- drivers/pci/controller/pcie-iproc-platform.c | 2 +- drivers/pci/controller/pcie-iproc.c | 1 - drivers/pci/controller/pcie-iproc.h | 2 -- 4 files changed, 2 insertions(+), 5 deletions(-)
drivers/pci/controller/pcie-iproc-bcma.c +1 -1
@@ -64,7 +64,7 @@ static int iproc_bcma_pcie_probe(struct bcma_device *bdev)if (ret)return ret; - pcie->map_irq = iproc_bcma_pcie_map_irq; + bridge->map_irq = iproc_bcma_pcie_map_irq;bcma_set_drvdata (bdev, pcie);
drivers/pci/controller/pcie-iproc-platform.c +1 -1
@@ -98,7 +98,7 @@ static int iproc_pltfm_pcie_probe(struct platform_device *pdev)switch (pcie->type) {case IPROC_PCIE_PAXC :case IPROC_PCIE_PAXC_V2 : - pcie->map_irq =NULL ; + bridge->map_irq =NULL ;break ;default :break ;
drivers/pci/controller/pcie-iproc.c +0 -1
@@ -1514,7 +1514,6 @@ int iproc_pcie_setup(struct iproc_pcie *pcie, struct list_head *res) host->ops = &iproc_pcie_ops; host->sysdata = pcie; - host->map_irq = pcie->map_irq; ret =pci_host_probe (host);if (ret <0 ) {
drivers/pci/controller/pcie-iproc.h +0 -2
@@ -61,7 +61,6 @@ struct iproc_msi;* @base_addr: PCIe host controller register base physical address * @mem: host bridge memory window resource * @phy: optional PHY device that controls the Serdes -* @map_irq: function callback to map interrupts * @ep_is_internal: indicates an internal emulated endpoint device is connected * @iproc_cfg_read: indicates the iProc config read function should be used * @rej_unconfig_pf: indicates the root complex needs to detect and reject
@@ -91,7 +90,6 @@ struct iproc_pcie {phys_addr_t base_addr;struct resource mem;struct phy *phy; -int (*map_irq)(const struct pci_dev *,u8 ,u8 );bool ep_is_internal;bool iproc_cfg_read;bool rej_unconfig_pf;
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 812/1611 spi: rpc-if: Use correct device for hardware reinitialization on resume
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Quang Nguyen <[email protected]>
[ Upstream commit 7b25dbafa2fce50b1a48c1d057adb35da3563f9b ]
rpcif_spi_resume() currently passes the SPI controller device to rpcif_hw_init(), but the function should be called with the RPC interface device.
Retrieve the rpcif private data from the SPI controller and pass rpc->dev instead. Also propagate the return value of rpcif_hw_init() so that a failure during resume is properly reported rather than silently ignored.
--- drivers/spi/spi-rpc-if.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-)
drivers/spi/spi-rpc-if.c +5 -1
@@ -206,8 +206,12 @@ static int rpcif_spi_suspend(struct device *dev)static int rpcif_spi_resume (struct device *dev) {struct spi_controller *ctlr =dev_get_drvdata (dev); +struct rpcif *rpc =spi_controller_get_devdata (ctlr); +int ret; -rpcif_hw_init (dev, false); + ret =rpcif_hw_init (rpc->dev, false); +if (ret) +return ret;return spi_controller_resume (ctlr); }
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 813/1611 virtio-net: fix len check in receive_big()
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Xiang Mei <[email protected]>
[ Upstream commit 9e5ad06ea826322ce8c58b4a68442a96f600c3c4 ]
receive_big() bounds the device-announced length by (big_packets_num_skbfrags + 1) * PAGE_SIZE. That is still too loose:add_recvbuf_big() sets sg[1] to start at offset sizeof(struct padded_vnet_hdr) into the first page, so the chain actually carries hdr_len + (PAGE_SIZE - sizeof(padded_vnet_hdr)) + big_packets_num_skbfrags * PAGE_SIZE bytes -- 20 bytes less than the check allows for the common hdr_len == 12 case.
A malicious virtio backend can announce a len in that gap. page_to_skb() then walks one frag past the page chain, storing a NULL page->private into skb_shinfo()->frags[MAX_SKB_FRAGS], which is both an out-of-bounds write past the static frag array and a NULL frag handed up the rx path.
Bound len by the size add_recvbuf_big() actually advertised.
--- drivers/net/virtio_net.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-)
drivers/net/virtio_net.c +6 -3
@@ -2105,15 +2105,18 @@ static struct sk_buff *receive_big(struct net_device *dev, struct virtnet_rq_stats *stats) {struct page *page = buf; +unsigned long max_len;struct sk_buff *skb; + max_len = (vi->big_packets_num_skbfrags +1 ) *PAGE_SIZE - +sizeof (struct padded_vnet_hdr ) + vi->hdr_len; +/* Make sure that len does not exceed the size allocated in * add_recvbuf_big. */ -if (unlikely (len > (vi->big_packets_num_skbfrags +1 ) *PAGE_SIZE )) { +if (unlikely (len > max_len)) {pr_debug ("%s: rx error: len %u exceeds allocated size %lu\n" , - dev->name, len, - (vi->big_packets_num_skbfrags +1 ) *PAGE_SIZE ); + dev->name, len, max_len); goto err; }
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 814/1611 dpaa2-switch: fix VLAN upper check not rejecting bridge join
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Ioana Ciornei <[email protected]>
[ Upstream commit ed2294f94e34e97342850c40b320833d881c3819 ]
The blamed commit refactored the prechangeupper event handling but failed to actually return an error in case dpaa2_switch_prevent_bridging_with_8021q_upper() detected a 802.1q upper on a port which tries to join a bridge. Fix this by returning err instead of 0.
--- drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c +1 -1
@@ -2177,7 +2177,7 @@ dpaa2_switch_prechangeupper_sanity_checks(struct net_device *netdev,if (err) {NL_SET_ERR_MSG_MOD (extack,"Cannot join a bridge while VLAN uppers are present" ); -return 0 ; +return err; }netdev_for_each_lower_dev (upper_dev, other_dev, iter) {
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 815/1611 devlink: Fix parent ref leak in devl_rate_node_create()
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Cosmin Ratiu <[email protected]>
[ Upstream commit ba45106342bbdd905651cb9fcefb8c11871d4c25 ]
In the original commit the function bails out on kstrdup failure, forgetting to decrement the refcnt of the parent.
Fix that by moving the parent refcnt setting after kstrdup.
--- net/devlink/rate.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-)
net/devlink/rate.c +5 -5
@@ -724,11 +724,6 @@ devl_rate_node_create(struct devlink *devlink, void *priv, char *node_name,if (!rate_node)return ERR_PTR (-ENOMEM ); -if (parent) { - rate_node->parent = parent; -refcount_inc (&rate_node->parent->refcnt); - } - rate_node->type =DEVLINK_RATE_TYPE_NODE ; rate_node->devlink = devlink; rate_node->priv = priv;
@@ -739,6 +734,11 @@ devl_rate_node_create(struct devlink *devlink, void *priv, char *node_name,return ERR_PTR (-ENOMEM ); } +if (parent) { + rate_node->parent = parent; +refcount_inc (&rate_node->parent->refcnt); + } +refcount_set (&rate_node->refcnt,1 );list_add (&rate_node->list, &devlink->rate_list);devlink_rate_notify (rate_node,DEVLINK_CMD_RATE_NEW );
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 816/1611 devlink: Fix parent ref leak on tc-bw failure
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Cosmin Ratiu <[email protected]>
[ Upstream commit ba81a8b80f042038b9f73a4e5bb135de890b59bb ]
When a node is created via rate-new with tc-bw and a parent node, devlink_nl_rate_set() executes the sequence of ops. It bails out on the first failure and doesn't rollback anything. For most things that is fine (setting some numbers), but the parent set can leak if there's another failure after that.
That is precisely what happens when parent setting isn't the last block in the function. After the referenced "Fixes" commit, when tc-bw fails to be set the function bails out after having set the parent and incremented its refcount.
There are two callers:
- devlink_nl_rate_set_doit() is fine, it just reports the error.
- but devlink_nl_rate_new_doit() frees the newly created node and leaks the parent refcnt.
Fix that by reordering the blocks so parent setting is last and adding a comment explaining this so future modification preserve the ordering (hopefully).
--- net/devlink/rate.c | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-)
net/devlink/rate.c +9 -6
@@ -487,16 +487,19 @@ static int devlink_nl_rate_set(struct devlink_rate *devlink_rate, devlink_rate->tx_weight = weight; } - nla_parent = attrs[DEVLINK_ATTR_RATE_PARENT_NODE_NAME ]; -if (nla_parent) { - err =devlink_nl_rate_parent_node_set (devlink_rate, info, - nla_parent); +if (attrs[DEVLINK_ATTR_RATE_TC_BWS ]) { + err =devlink_nl_rate_tc_bw_set (devlink_rate, info);if (err)return err; } -if (attrs[DEVLINK_ATTR_RATE_TC_BWS ]) { - err =devlink_nl_rate_tc_bw_set (devlink_rate, info); +/* Keep parent setting last because it takes a reference. This function +* has no rollback, so failing after taking the ref would leak it. +*/ + nla_parent = attrs[DEVLINK_ATTR_RATE_PARENT_NODE_NAME ]; +if (nla_parent) { + err =devlink_nl_rate_parent_node_set (devlink_rate, info, + nla_parent);if (err)return err; }
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 817/1611 net: airoha: fix foe_check_time allocation size
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Wayen Yan <[email protected]>
[ Upstream commit 5c121ee635680c93d7074becf14cfbaac140f80d ]
foe_check_time is declared as u16 pointer but was allocated with only ppe_num_entries bytes instead of ppe_num_entries * sizeof(u16).
When airoha_ppe_foe_verify_entry() is called with hash >= ppe_num_entries/2, it writes beyond the allocated buffer, causing heap buffer overflow and potential kernel crash.
--- drivers/net/ethernet/airoha/airoha_ppe.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)
drivers/net/ethernet/airoha/airoha_ppe.c +2 -1
@@ -1538,7 +1538,8 @@ int airoha_ppe_init(struct airoha_eth *eth)return -ENOMEM ; } - ppe->foe_check_time =devm_kzalloc (eth->dev, ppe_num_entries, + ppe->foe_check_time =devm_kzalloc (eth->dev, + ppe_num_entries *sizeof (*ppe->foe_check_time),GFP_KERNEL );if (!ppe->foe_check_time)return -ENOMEM ;
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 818/1611 net: macb: add TX stall timeout callback to recover from lost TSTART write
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Lukasz Raczylo <[email protected]>
[ Upstream commit e438ec3e9e95cd3f49a8120e5f63ae3f9606e6fa ]
The MACB found in the Raspberry Pi RP1 suffers from sporadic stalls on the TX queue.
While the exact root cause is not yet fully understood, it is likely related to a hardware issue where a TSTART write to the NCR register is missed, preventing the transmission from being kicked off.
Implement a timeout callback to handle TX queue stalls, triggering the existing restart mechanism to recover.
--- drivers/net/ethernet/cadence/macb_main.c | 8 ++++++++ 1 file changed, 8 insertions(+)
drivers/net/ethernet/cadence/macb_main.c +8 -0
@@ -4416,6 +4416,13 @@ static int macb_setup_tc(struct net_device *dev, enum tc_setup_type type, } } +static void macb_tx_timeout (struct net_device *dev,unsigned int q) +{ +struct macb *bp =netdev_priv (dev); + +macb_tx_restart (&bp->queues[q]); +} +static const struct net_device_ops macb_netdev_ops = { .ndo_open = macb_open, .ndo_stop = macb_close,
@@ -4434,6 +4441,7 @@ static const struct net_device_ops macb_netdev_ops = { .ndo_hwtstamp_set = macb_hwtstamp_set, .ndo_hwtstamp_get = macb_hwtstamp_get, .ndo_setup_tc = macb_setup_tc, + .ndo_tx_timeout = macb_tx_timeout, };/* Configure peripheral capabilities according to device tree
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 819/1611 flow_dissector: check device type before reading ETH_ADDRS
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Yun Zhou <[email protected]>
[ Upstream commit bf6e8af2c8be77489bedeae9f8a9654cb710e500 ]
__skb_flow_dissect() unconditionally reads 12 bytes from eth_hdr(skb) when FLOW_DISSECTOR_KEY_ETH_ADDRS is requested. This assumes the skb has a valid Ethernet header at mac_header, which is not always the case.
The problem can be triggered by:
1. Creating a TUN device in L3 mode (IFF_TUN, hard_header_len=0)
2. Attaching a multiq qdisc with a flower filter matching on eth_src
3. Sending a packet through AF_PACKET
Since TUN in L3 mode has no link-layer header, mac_header points to the L3 data area. The flow dissector reads 12 bytes of uninitialized skb memory, which then propagates through fl_set_masked_key() and is used as a rhashtable lookup key in __fl_lookup(), as reported by KMSAN.
Rejecting the filter in the control path (at tc filter add time) is not feasible because TC filter blocks can be shared between arbitrary devices -- a filter installed on an Ethernet device may later classify packets on a headerless device through a shared block. The device association is not fixed at filter creation time.
Fix this by gating the memcpy on dev->type == ARPHRD_ETHER, which ensures only true Ethernet-framed packets have their addresses read. This is more precise than the previous hard_header_len >= 12 check, which would incorrectly pass for non-Ethernet link types like IPoIB (ARPHRD_INFINIBAND, hard_header_len=24) and FDDI (hard_header_len=21) whose L2 headers are not in Ethernet format. Additionally check skb_mac_header_was_set() to guard against the pathological case where mac_header is the unset sentinel (~0U), which would cause eth_hdr() to return a wild pointer.
For the act_mirred redirect case (Ethernet packet redirected to a non-Ethernet device sharing a TC block), zeroing the key is the correct
behavior: the packet is now being classified on the target device, where Ethernet address matching is not semantically meaningful.
Note: on non-Ethernet devices, the zeroed key will match a filter configured with all-zero MAC addresses. This is an improvement over the previous behavior where uninitialized memory could randomly match any filter.
--- net/core/flow_dissector.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-)
net/core/flow_dissector.c +10 -2
@@ -1173,13 +1173,21 @@ bool __skb_flow_dissect(const struct net *net,if (dissector_uses_key (flow_dissector,FLOW_DISSECTOR_KEY_ETH_ADDRS )) { -struct ethhdr *eth =eth_hdr (skb);struct flow_dissector_key_eth_addrs *key_eth_addrs; key_eth_addrs =skb_flow_dissector_target (flow_dissector,FLOW_DISSECTOR_KEY_ETH_ADDRS , target_container); -memcpy (key_eth_addrs, eth,sizeof (*key_eth_addrs)); +/* TC filter blocks can be shared across devices with +* different link types, so we cannot validate this +* when the filter is installed -- check at dissect time. +*/ +if (skb && skb->dev && + skb->dev->type ==ARPHRD_ETHER && +skb_mac_header_was_set (skb)) +memcpy (key_eth_addrs,eth_hdr (skb),sizeof (*key_eth_addrs)); +else +memset (key_eth_addrs,0 ,sizeof (*key_eth_addrs)); } if (dissector_uses_key(flow_dissector,
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 820/1611 selftests: vlan_bridge_binding: Fix flaky operational state check
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Ido Schimmel <[email protected]>
[ Upstream commit 4045f1c3d68ef4b589ae2587e6ff66ce8017daf2 ]
check_operstate() busy waits for up to one second for the operational state to change to the expected state. This is not enough since carrier loss events can be delayed by the kernel for up to one second (see __linkwatch_run_queue()), leading to sporadic failures.
Fix by increasing the busy wait period to two seconds.
--- tools/testing/selftests/net/vlan_bridge_binding.sh | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
tools/testing/selftests/net/vlan_bridge_binding.sh +1 -1
@@ -64,7 +64,7 @@ check_operstate() local expect=$1; shift local operstate - operstate=$(busywait 1000 \ + operstate=$(busywait 2000 \ operstate_is "$dev" "$expect") check_err $? "Got operstate of $operstate, expected $expect" }
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 821/1611 ALSA: usb-audio: Kill MIDI 2.0 URBs before freeing endpoints
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Cen Zhang <[email protected]>
[ Upstream commit f199c8a8bdd54296d3458777e70fe82a78bd9817 ]
MIDI 2.0 input URBs are started during snd_usb_midi_v2_create(). A later setup failure can still jump to snd_usb_midi_v2_free(), which currently frees each endpoint and its coherent URB buffers without first stopping the submitted URBs. A completion can then dereference the embedded URB context and endpoint state after they have been freed, or try to resubmit from the stale endpoint.
This was observed as a KASAN slab-use-after-free in input_urb_complete().
The buggy scenario involves two paths, with each column showing the order within that path:
probe error path: USB completion path:
1. start_input_streams() submits 1. The HCD still owns a
input URBs. submitted input URB.
2. A later setup helper returns 2. input_urb_complete() runs
an error. with urb->context in ep.
3. snd_usb_midi_v2_free() frees 3. The completion reads ep
endpoint storage and URB buffers. state and can requeue URBs.
Make the endpoint destructor follow the same teardown ordering used for disconnect when the endpoint has not already been disconnected: publish ep->disconnected, kill the URBs synchronously, and drain the endpoint before freeing URB buffers and endpoint storage. The guard avoids repeating the stop sequence after the normal snd_usb_midi_v2_disconnect_all() path, while still synchronizing the direct MIDI 2.0 create-error free path.
Validation reproduced this kernel report:
BUG: KASAN: slab-use-after-free in input_urb_complete+0x37/0x1b0 Workqueue: usb_hub_wq hub_event RIP: 0010:_raw_spin_unlock_irq+0x2e/0x50 Read of size 8 Call trace: dump_stack_lvl+0x77/0xb0 print_report+0xce/0x5f0 input_urb_complete+0x37/0x1b0 (sound/usb/midi2.c:186) srso_alias_return_thunk+0x5/0xfbef5 __virt_addr_valid+0x19f/0x330 kasan_report+0xe0/0x110 __usb_hcd_giveback_urb+0x112/0x1d0 dummy_timer+0xaaa/0x19a0 lock_is_held_type+0x9a/0x110 __lock_acquire+0x467/0x28b0 mark_held_locks+0x40/0x70 _raw_spin_unlock_irqrestore+0x44/0x60 lockdep_hardirqs_on_prepare+0xbb/0x1a0 __hrtimer_run_queues+0x101/0x520 hrtimer_run_softirq+0xd0/0x130 handle_softirqs+0x15b/0x670 __irq_exit_rcu+0xd0/0x170 irq_exit_rcu+0xe/0x20 sysvec_apic_timer_interrupt+0x6c/0x80 asm_sysvec_apic_timer_interrupt+0x1a/0x20
--- sound/usb/midi2.c | 5 +++++ 1 file changed, 5 insertions(+)
sound/usb/midi2.c +5 -0
@@ -470,6 +470,11 @@ static int create_midi2_endpoint(struct snd_usb_midi2_interface *umidi,static void free_midi2_endpoint (struct snd_usb_midi2_endpoint *ep) {list_del (&ep->list); +if (!ep->disconnected) { + ep->disconnected =1 ; +kill_midi_urbs (ep, false); +drain_urb_queue (ep); + }free_midi_urbs (ep);kfree (ep); }
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 822/1611 arm64/hw_breakpoint: reject unaligned watchpoints that would truncate BAS
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Breno Leitao <[email protected]>
[ Upstream commit 4cc70f75853bebac022334b6a86b953348072f74 ]
hw_breakpoint_arch_parse() positions the BAS bit pattern in hw->ctrl.len with
offset = hw->address & alignment_mask; /* 0..7 */ hw->ctrl.len <<= offset;
ctrl.len is an 8-bit bitfield (struct arch_hw_breakpoint_ctrl::len is u32 :8), so the shift silently drops any bits past bit 7. For non-compat AArch64 watchpoints the offset is unbounded relative to ctrl.len: a perf_event_open(PERF_TYPE_BREAKPOINT) caller asking for HW_BREAKPOINT_W with bp_addr=page+1 and bp_len=HW_BREAKPOINT_LEN_8 ends up with 0xff << 1 = 0x1fe, stored as 0xfe. The kernel programs WCR.BAS=0xfe and the hardware watches bytes [1..7] instead of the requested [1..8] -- the eighth byte is silently dropped. The syscall still returns success, leaving userspace to discover the gap by empirical probing.
The same class affects HW_BREAKPOINT_LEN_{2,4} when offset pushes the high BAS bit past bit 7 (e.g. LEN_4 with offset=5 yields 0xe0 instead of 0x1e0). No memory-safety impact -- the value is masked into 8 bits before encoding -- but debuggers and perf users observe missed events on bytes they thought they were watching.
The AArch32 branch immediately above already rejects unrepresentable (offset, len) combinations via an explicit switch. Mirror that for the non-compat branch by checking that the shifted pattern fits in the BAS field, returning -EINVAL when it does not.
GDB and similar debuggers are unaffected by the stricter check. aarch64_linux_set_debug_regs() already treats EINVAL on NT_ARM_HW_WATCH as a downgrade signal: it clears kernel_supports_any_contiguous_range, calls aarch64_downgrade_regs() to round the BAS up to a legacy 0x01/03/0f/ff mask with an aligned base, and retries -- the same fallback path that PR-20207 introduced. The new -EINVAL is therefore reachable only from a raw perf_event_open() that pairs an unaligned base with an oversized bp_len, which is precisely the bug.
Reproducer:
struct perf_event_attr a = {
.type = PERF_TYPE_BREAKPOINT, .size = sizeof(a),
.bp_type = HW_BREAKPOINT_W,
.bp_addr = (uintptr_t)(buf + 1),
.bp_len = HW_BREAKPOINT_LEN_8,
.exclude_kernel = 1, .exclude_hv = 1, };
int fd = perf_event_open(&a, 0, -1, -1, 0);
/* before this fix: succeeds, watches 7 bytes (buf+1..buf+7) */
/* after this fix: fails with EINVAL */
--- arch/arm64/kernel/hw_breakpoint.c | 9 +++++++++ 1 file changed, 9 insertions(+)
arch/arm64/kernel/hw_breakpoint.c +9 -0
@@ -559,6 +559,15 @@ int hw_breakpoint_arch_parse(struct perf_event *bp,else alignment_mask =0x7 ; offset = hw->address & alignment_mask; + +/* +* BAS is an 8-bit field in WCR/BCR; the shift below would +* silently drop the high bits of ctrl.len when offset + len +* exceeds 8, programming hardware to watch fewer bytes than +* the user requested. +*/ +if (((u32 )hw->ctrl.len << offset) >ARM_BREAKPOINT_LEN_8 ) +return -EINVAL ; } hw->address &= ~alignment_mask;
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 823/1611 thermal: intel: Fix dangling resources on thermal_throttle_online() failure
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Ricardo Neri <[email protected]>
[ Upstream commit b91d287fa7a1ba0727eed5823c6ee4924ee5fa31 ]
The function thermal_throttle_add_dev() may fail and abort a CPU hotplug online operation. Since the failure occurs within the online callback, thermal_throttle_online(), the CPU hotplug framework does not invoke the corresponding offline callback. As a result, the hardware and software resources set up during the failed operation are not torn down.
Since only thermal_throttle_add_dev() can fail, call it before setting up the rest of the resources.
--- drivers/thermal/intel/therm_throt.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-)
drivers/thermal/intel/therm_throt.c +6 -1
@@ -528,8 +528,13 @@ static int thermal_throttle_online(unsigned int cpu) {struct thermal_state *state = &per_cpu (thermal_state, cpu);struct device *dev =get_cpu_device (cpu); +int err;u32 l; + err =thermal_throttle_add_dev (dev, cpu); +if (err) +return err; + state->package_throttle.level =PACKAGE_LEVEL ; state->core_throttle.level =CORE_LEVEL ;
@@ -547,7 +552,7 @@ static int thermal_throttle_online(unsigned int cpu) l =apic_read (APIC_LVTTHMR );apic_write (APIC_LVTTHMR , l & ~APIC_LVT_MASKED ); -return thermal_throttle_add_dev (dev, cpu); +return err; }static int thermal_throttle_offline (unsigned int cpu)
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 824/1611 ACPI: resource: Amend kernel-doc style
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Andy Shevchenko <[email protected]>
[ Upstream commit 78ad5c7722b7bed9d35ffc5b45eb0f12e2c22fee ]
The functions are referred as func() in the kernel-doc. The % (percent) character makes the rendering for constants as described in the respective documentation. Amend all these.
--- drivers/acpi/resource.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)
drivers/acpi/resource.c +3 -3
@@ -871,7 +871,7 @@ bool acpi_dev_resource_interrupt(struct acpi_resource *ares, int index,EXPORT_SYMBOL_GPL (acpi_dev_resource_interrupt);/** -* acpi_dev_free_resource_list - Free resource from %acpi_dev_get_resources(). +* acpi_dev_free_resource_list - Free resource from acpi_dev_get_resources(). * @list: The head of the resource list to free. */ void acpi_dev_free_resource_list (struct list_head *list)
@@ -991,7 +991,7 @@ static int __acpi_dev_get_resources(struct acpi_device *adev,* * The resultant struct resource objects are put on the list pointed to by * @list, that must be empty initially, as members of struct resource_entry -* objects. Callers of this routine should use %acpi_dev_free_resource_list() to +* objects. Callers of this routine should use acpi_dev_free_resource_list() to * free that list. * * The number of resources in the output list is returned on success, an error
@@ -1032,7 +1032,7 @@ static int is_memory(struct acpi_resource *ares, void *not_used)* The resultant struct resource objects are put on the list pointed to * by @list, that must be empty initially, as members of struct * resource_entry objects. Callers of this routine should use -* %acpi_dev_free_resource_list() to free that list. +* acpi_dev_free_resource_list() to free that list. * * The number of resources in the output list is returned on success, * an error code reflecting the error condition is returned otherwise.
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 825/1611 ACPI: IPMI: Fix inverted interface check in ipmi_bmc_gone()
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Xu Rao <[email protected]>
[ Upstream commit 71b57aca295d61276a60e131d8f62b0cc7cf1a35 ]
Before commit a1a69b297e47 ("ACPI / IPMI: Fix race caused by the unprotected ACPI IPMI user"), ipmi_bmc_gone() skipped entries whose interface number did not match the SMI being removed, then killed the matching entry:
if (ipmi_device->ipmi_ifnum != iface) continue; __ipmi_dev_kill(ipmi_device);
That commit folded the removal block into the existing non-match test while converting the object lifetime handling, but left the comparison unchanged. The old != meant "continue past this entry"; after the refactor it meant "kill this entry".
As a result, a single ACPI IPMI interface is never removed when its SMI disappears. If multiple interfaces are tracked, the first interface whose number differs from iface is removed instead, while the interface that actually disappeared remains on driver_data.ipmi_devices. The stale entry is not marked dead and can continue to be selected for ACPI IPMI transactions. It can also prevent the same ACPI handle from being registered again.
Change the comparison to == so ipmi_bmc_gone() removes exactly the interface reported as gone by the SMI watcher. This restores the pre-a1a69b297e47 behavior and is the correct interface matching logic.
--- drivers/acpi/acpi_ipmi.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/acpi/acpi_ipmi.c +1 -1
@@ -490,7 +490,7 @@ static void ipmi_bmc_gone(int iface)mutex_lock (&driver_data.ipmi_lock);list_for_each_entry_safe (iter, temp, &driver_data.ipmi_devices, head) { -if (iter->ipmi_ifnum != iface) { +if (iter->ipmi_ifnum == iface) { ipmi_device = iter;__ipmi_dev_kill (iter);break ;
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 826/1611 ieee802154: Restore initial state on failed device_rename() in cfg802154_switch_netns()
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Ivan Abramov <[email protected]>
[ Upstream commit a2e06b4bef20b59446d5088e938c2be53cc4e6c6 ]
Currently, the return value of device_rename() is not acted upon.
To avoid an inconsistent state in case of failure, roll back the changes made before the device_rename() call.
Found by Linux Verification Center (linuxtesting.org) with Syzkaller.
--- net/ieee802154/core.c | 45 ++++++++++++++++++++++++------------------- 1 file changed, 25 insertions(+), 20 deletions(-)
net/ieee802154/core.c +25 -20
@@ -233,31 +233,36 @@ int cfg802154_switch_netns(struct cfg802154_registered_device *rdev, wpan_dev->netdev->netns_immutable = true; } -if (err) { -/* failed -- clean up to old netns */ - net =wpan_phy_net (&rdev->wpan_phy); - -list_for_each_entry_continue_reverse (wpan_dev, - &rdev->wpan_dev_list, - list) { -if (!wpan_dev->netdev) -continue ; - wpan_dev->netdev->netns_immutable = false; - err =dev_change_net_namespace (wpan_dev->netdev, net, -"wpan%d" ); -WARN_ON (err); - wpan_dev->netdev->netns_immutable = true; - } - -return err; - } - -wpan_phy_net_set (&rdev->wpan_phy, net); +if (err) + goto errout; err =device_rename (&rdev->wpan_phy.dev,dev_name (&rdev->wpan_phy.dev));WARN_ON (err); +if (err) + goto errout; + +wpan_phy_net_set (&rdev->wpan_phy, net); +return 0 ; + +errout: +/* failed -- clean up to old netns */ + net =wpan_phy_net (&rdev->wpan_phy); + +list_for_each_entry_continue_reverse (wpan_dev, + &rdev->wpan_dev_list, + list) { +if (!wpan_dev->netdev) +continue ; + wpan_dev->netdev->netns_immutable = false; + err =dev_change_net_namespace (wpan_dev->netdev, net, +"wpan%d" ); +WARN_ON (err); + wpan_dev->netdev->netns_immutable = true; + } + +return err; }void cfg802154_dev_free (struct cfg802154_registered_device *rdev)
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 827/1611 ieee802154: Avoid calling WARN_ON() on -ENOMEM in cfg802154_switch_netns()
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Ivan Abramov <[email protected]>
[ Upstream commit 0569f67ed6a7af838e2141da93c68e6b6013f483 ]
It's pointless to call WARN_ON() in case of an allocation failure in dev_change_net_namespace() and device_rename(), since it only leads to useless splats caused by deliberate fault injections, so avoid it.
Found by Linux Verification Center (linuxtesting.org) with Syzkaller.
--- net/ieee802154/core.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-)
net/ieee802154/core.c +5 -3
@@ -228,8 +228,10 @@ int cfg802154_switch_netns(struct cfg802154_registered_device *rdev,continue ; wpan_dev->netdev->netns_immutable = false; err =dev_change_net_namespace (wpan_dev->netdev, net,"wpan%d" ); -if (err) +if (err) { +WARN_ON (err && err != -ENOMEM );break ; + } wpan_dev->netdev->netns_immutable = true; }
@@ -237,7 +239,7 @@ int cfg802154_switch_netns(struct cfg802154_registered_device *rdev, goto errout; err =device_rename (&rdev->wpan_phy.dev,dev_name (&rdev->wpan_phy.dev)); -WARN_ON (err); +WARN_ON (err && err != -ENOMEM );if (err) goto errout;
@@ -258,7 +260,7 @@ int cfg802154_switch_netns(struct cfg802154_registered_device *rdev, wpan_dev->netdev->netns_immutable = false; err =dev_change_net_namespace (wpan_dev->netdev, net,"wpan%d" ); -WARN_ON (err); +WARN_ON (err && err != -ENOMEM ); wpan_dev->netdev->netns_immutable = true; }
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 828/1611 ieee802154: Remove WARN_ON() in cfg802154_pernet_exit()
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Ivan Abramov <[email protected]>
[ Upstream commit e69ed6fc9fb3b386b5fcdb9f51623f122cee2ebd ]
There's no need to call WARN_ON() in cfg802154_pernet_exit(), since every point of failure in cfg802154_switch_netns() is covered with WARN_ON(), so remove it.
Found by Linux Verification Center (linuxtesting.org) with Syzkaller.
--- net/ieee802154/core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
net/ieee802154/core.c +1 -1
@@ -358,7 +358,7 @@ static void __net_exit cfg802154_pernet_exit(struct net *net)rtnl_lock ();list_for_each_entry (rdev, &cfg802154_rdev_list, list) {if (net_eq (wpan_phy_net (&rdev->wpan_phy), net)) -WARN_ON (cfg802154_switch_netns (rdev, &init_net)); +cfg802154_switch_netns (rdev, &init_net); }rtnl_unlock (); }
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 829/1611 ieee802154: fix kernel-infoleak in dgram_recvmsg()
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Aleksandr Nogikh <[email protected]>
[ Upstream commit 4db86f8ab11b5a41bfc36680be837e6ac1375ec6 ]
KMSAN reported a kernel-infoleak in move_addr_to_user():
BUG: KMSAN: kernel-infoleak in instrument_copy_to_user include/linux/instrumented.h:131 [inline] BUG: KMSAN: kernel-infoleak in _inline_copy_to_user include/linux/uaccess.h:205 [inline] BUG: KMSAN: kernel-infoleak in _copy_to_user+0xcc/0x120 lib/usercopy.c:26 instrument_copy_to_user include/linux/instrumented.h:131 [inline] _inline_copy_to_user include/linux/uaccess.h:205 [inline] _copy_to_user+0xcc/0x120 lib/usercopy.c:26 copy_to_user include/linux/uaccess.h:236 [inline] move_addr_to_user+0x2e7/0x440 net/socket.c:302 ____sys_recvmsg+0x232/0x610 net/socket.c:2925 ... Uninit was stored to memory at: ieee802154_addr_to_sa include/net/ieee802154_netdev.h:369 [inline] dgram_recvmsg+0xa09/0xbe0 net/ieee802154/socket.c:739
The issue occurs because the pan_id field of struct ieee802154_addr is left uninitialized when the address mode is IEEE802154_ADDR_NONE. The execution flow is as follows:
1. __ieee802154_rx_handle_packet() declares a local struct ieee802154_hdr hdr on the stack.
2. ieee802154_hdr_pull() calls ieee802154_hdr_get_addr() to parse the source and destination addresses into this structure.
3. If the address mode is IEEE802154_ADDR_NONE, ieee802154_hdr_get_addr() previously only set the mode field, leaving the pan_id field containing uninitialized stack memory.
4. This uninitialized pan_id is later copied into a struct sockaddr_ieee802154 in dgram_recvmsg() via ieee802154_addr_to_sa().
5. Finally, move_addr_to_user() copies the socket address structure to user space, leaking the uninitialized bytes.
Fix this by using memset to zero out the address structure in ieee802154_hdr_get_addr() when the mode is IEEE802154_ADDR_NONE.
--- net/ieee802154/header_ops.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-)
net/ieee802154/header_ops.c +6 -3
@@ -173,10 +173,13 @@ ieee802154_hdr_get_addr(const u8 *buf, int mode, bool omit_pan, {int pos =0 ; - addr->mode = mode; - -if (mode ==IEEE802154_ADDR_NONE ) +if (mode ==IEEE802154_ADDR_NONE ) { +memset (addr,0 ,sizeof (*addr)); + addr->mode =IEEE802154_ADDR_NONE ;return 0 ; + } + + addr->mode = mode;if (!omit_pan) {memcpy (&addr->pan_id, buf + pos,2 );
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 830/1611 mac802154: Prevent overwrite return code in mac802154_perform_association()
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Robertus Diawan Chris <[email protected]>
[ Upstream commit 649147cb3f8b3c0c9aeba5d89d69a6ef221c12c2 ]
When assoc_status not equal to IEEE802154_ASSOCIATION_SUCCESSFUL, the return value assigned to either "-ERANGE" or "-EPERM" but this return value will be overwritten to 0 after exiting the conditional scope. So, jump to clear_assoc label to preserve the return value when assoc_status not equal to IEEE802154_ASSOCIATION_SUCCESSFUL.
This is reported by Coverity Scan as "Unused value".
--- net/mac802154/scan.c | 1 + 1 file changed, 1 insertion(+)
net/mac802154/scan.c +1 -0
@@ -594,6 +594,7 @@ int mac802154_perform_association(struct ieee802154_sub_if_data *sdata,"Negative ASSOC RESP received from %8phC: %s\n" , &ceaddr, local->assoc_status ==IEEE802154_PAN_AT_CAPACITY ? "PAN at capacity" : "access denied"); + goto clear_assoc; } ret =0 ;
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 831/1611 md: merge mddev has_superblock into mddev_flags
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Yu Kuai <[email protected]>
[ Upstream commit fba4a980403d2f489bc680dbff7d7d2514e669f9 ]
There is not need to use a separate field in struct mddev, there are no functional changes.
Stable-dep-of: a286cb88ddb2 ("md/raid1: honor REQ_NOWAIT when waiting for behind writes")
--- drivers/md/md.c | 6 +++--- drivers/md/md.h | 3 ++- 2 files changed, 5 insertions(+), 4 deletions(-)
drivers/md/md.c +3 -3
@@ -6537,7 +6537,7 @@ int md_run(struct mddev *mddev)* the only valid external interface is through the md * device. */ - mddev->has_superblocks = false; +clear_bit (MD_HAS_SUPERBLOCK , &mddev->flags);rdev_for_each (rdev, mddev) {if (test_bit (Faulty, &rdev->flags))continue ;
@@ -6550,7 +6550,7 @@ int md_run(struct mddev *mddev) }if (rdev->sb_page) - mddev->has_superblocks = true; +set_bit (MD_HAS_SUPERBLOCK , &mddev->flags);/* perform some consistency tests on the device. * We don't want the data to overlap the metadata,
@@ -9173,7 +9173,7 @@ void md_write_start(struct mddev *mddev, struct bio *bi)rcu_read_unlock ();if (did_change)sysfs_notify_dirent_safe (mddev->sysfs_state); -if (!mddev->has_superblocks) +if (!test_bit (MD_HAS_SUPERBLOCK , &mddev->flags))return ;wait_event (mddev->sb_wait, !test_bit (MD_SB_CHANGE_PENDING , &mddev->sb_flags));
drivers/md/md.h +2 -1
@@ -340,6 +340,7 @@ struct md_cluster_operations;* array is ready yet. * @MD_BROKEN: This is used to stop writes and mark array as failed. * @MD_DELETED: This device is being deleted +* @MD_HAS_SUPERBLOCK: There is persistence sb in member disks. * * change UNSUPPORTED_MDDEV_FLAGS for each array type if new flag is added */
@@ -356,6 +357,7 @@ enum mddev_flags {MD_BROKEN ,MD_DO_DELETE ,MD_DELETED , + MD_HAS_SUPERBLOCK, }; enum mddev_sb_flags {
@@ -622,7 +624,6 @@ struct mddev {/* The sequence number for sync thread */ atomic_t sync_seq; - bool has_superblocks:1; bool fail_last_dev:1; bool serialize_policy:1; };
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 832/1611 md: merge mddev faillast_dev into mddev_flags
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Yu Kuai <[email protected]>
[ Upstream commit 4f6d2e648cbe963b328cb8815290676da3866434 ]
There is not need to use a separate field in struct mddev, there are no functional changes.
Stable-dep-of: a286cb88ddb2 ("md/raid1: honor REQ_NOWAIT when waiting for behind writes")
--- drivers/md/md.c | 10 ++++++---- drivers/md/md.h | 3 ++- drivers/md/raid0.c | 3 ++- drivers/md/raid1.c | 4 ++-- drivers/md/raid10.c | 4 ++-- drivers/md/raid5.c | 5 ++++- 6 files changed, 18 insertions(+), 11 deletions(-)
drivers/md/md.c +6 -4
@@ -5868,11 +5868,11 @@ __ATTR(consistency_policy, S_IRUGO | S_IWUSR, consistency_policy_show,static ssize_t fail_last_dev_show (struct mddev *mddev,char *page) { -return sprintf (page,"%d\n" , mddev->fail_last_dev); +return sprintf (page,"%d\n" ,test_bit (MD_FAILLAST_DEV , &mddev->flags)); }/* -* Setting fail_last_dev to true to allow last device to be forcibly removed +* Setting MD_FAILLAST_DEV to allow last device to be forcibly removed * from RAID1/RAID10. */ static ssize_t
@@ -5885,8 +5885,10 @@ fail_last_dev_store(struct mddev *mddev, const char *buf, size_t len)if (ret)return ret; -if (value != mddev->fail_last_dev) - mddev->fail_last_dev = value; +if (value) +set_bit (MD_FAILLAST_DEV , &mddev->flags); +else +clear_bit (MD_FAILLAST_DEV , &mddev->flags);return len; }
drivers/md/md.h +2 -1
@@ -341,6 +341,7 @@ struct md_cluster_operations;* @MD_BROKEN: This is used to stop writes and mark array as failed. * @MD_DELETED: This device is being deleted * @MD_HAS_SUPERBLOCK: There is persistence sb in member disks. +* @MD_FAILLAST_DEV: Allow last rdev to be removed. * * change UNSUPPORTED_MDDEV_FLAGS for each array type if new flag is added */
@@ -358,6 +359,7 @@ enum mddev_flags {MD_DO_DELETE ,MD_DELETED ,MD_HAS_SUPERBLOCK , + MD_FAILLAST_DEV, }; enum mddev_sb_flags {
@@ -624,7 +626,6 @@ struct mddev {/* The sequence number for sync thread */ atomic_t sync_seq; - bool fail_last_dev:1; bool serialize_policy:1; };
drivers/md/raid0.c +2 -1
@@ -27,7 +27,8 @@ module_param(default_layout, int, 0644); (1L <<MD_JOURNAL_CLEAN ) | \ (1L <<MD_FAILFAST_SUPPORTED ) |\ (1L <<MD_HAS_PPL ) | \ - (1L << MD_HAS_MULTIPLE_PPLS)) + (1L <<MD_HAS_MULTIPLE_PPLS ) | \ + (1L << MD_FAILLAST_DEV))/* * inform the user of the raid configuration
drivers/md/raid1.c +2 -2
@@ -1748,7 +1748,7 @@ static void raid1_status(struct seq_file *seq, struct mddev *mddev)* - &mddev->degraded is bumped. * * @rdev is marked as &Faulty excluding case when array is failed and -* &mddev->fail_last_dev is off. +* MD_FAILLAST_DEV is not set. */ static void raid1_error (struct mddev *mddev,struct md_rdev *rdev) {
@@ -1761,7 +1761,7 @@ static void raid1_error(struct mddev *mddev, struct md_rdev *rdev) (conf->raid_disks - mddev->degraded) == 1) {set_bit (MD_BROKEN , &mddev->flags); -if (!mddev->fail_last_dev) { +if (!test_bit (MD_FAILLAST_DEV , &mddev->flags)) { conf->recovery_disabled = mddev->recovery_disabled;spin_unlock_irqrestore (&conf->device_lock, flags);return ;
drivers/md/raid10.c +2 -2
@@ -1991,7 +1991,7 @@ static int enough(struct r10conf *conf, int ignore)* - &mddev->degraded is bumped. * * @rdev is marked as &Faulty excluding case when array is failed and -* &mddev->fail_last_dev is off. +* MD_FAILLAST_DEV is not set. */ static void raid10_error (struct mddev *mddev,struct md_rdev *rdev) {
@@ -2003,7 +2003,7 @@ static void raid10_error(struct mddev *mddev, struct md_rdev *rdev)if (test_bit (In_sync, &rdev->flags) && !enough (conf, rdev->raid_disk)) {set_bit (MD_BROKEN , &mddev->flags); -if (!mddev->fail_last_dev) { +if (!test_bit (MD_FAILLAST_DEV , &mddev->flags)) {spin_unlock_irqrestore (&conf->device_lock, flags);return ; }
drivers/md/raid5.c +4 -1
@@ -56,7 +56,10 @@#include "md-bitmap.h" #include "raid5-log.h" -#define UNSUPPORTED_MDDEV_FLAGS (1L << MD_FAILFAST_SUPPORTED) +#define UNSUPPORTED_MDDEV_FLAGS \ + ((1L << MD_FAILFAST_SUPPORTED) | \ + (1L << MD_FAILLAST_DEV)) +#define cpu_to_group (cpu) cpu_to_node(cpu)#define ANY_GROUP NUMA_NO_NODE
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 833/1611 md: merge mddev serialize_policy into mddev_flags
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Yu Kuai <[email protected]>
[ Upstream commit 10787568cc1f3f80afc510b2728751989dfa0ae6 ]
There is not need to use a separate field in struct mddev, there are no functional changes.
Stable-dep-of: a286cb88ddb2 ("md/raid1: honor REQ_NOWAIT when waiting for behind writes")
--- drivers/md/md-bitmap.c | 4 ++-- drivers/md/md.c | 20 ++++++++++++-------- drivers/md/md.h | 4 ++-- drivers/md/raid0.c | 3 ++- drivers/md/raid1.c | 4 ++-- drivers/md/raid5.c | 3 ++- 6 files changed, 22 insertions(+), 16 deletions(-)
drivers/md/md-bitmap.c +2 -2
@@ -2086,7 +2086,7 @@ static void bitmap_destroy(struct mddev *mddev)return ;bitmap_wait_behind_writes (mddev); -if (!mddev->serialize_policy) +if (!test_bit (MD_SERIALIZE_POLICY , &mddev->flags))mddev_destroy_serial_pool (mddev,NULL );mutex_lock (&mddev->bitmap_info.mutex);
@@ -2864,7 +2864,7 @@ backlog_store(struct mddev *mddev, const char *buf, size_t len) mddev->bitmap_info.max_write_behind = backlog;if (!backlog && mddev->serial_info_pool) {/* serial_info_pool is not needed if backlog is zero */ -if (!mddev->serialize_policy) +if (!test_bit (MD_SERIALIZE_POLICY , &mddev->flags))mddev_destroy_serial_pool (mddev,NULL ); }else if (backlog && !mddev->serial_info_pool) {/* serial_info_pool is needed since backlog is not zero */
drivers/md/md.c +12 -8
@@ -278,7 +278,8 @@ void mddev_destroy_serial_pool(struct mddev *mddev, struct md_rdev *rdev)rdev_for_each (temp, mddev) {if (!rdev) { -if (!mddev->serialize_policy || +if (!test_bit (MD_SERIALIZE_POLICY , + &mddev->flags) || !rdev_need_serial (temp))rdev_uninit_serial (temp);else
@@ -5901,11 +5902,12 @@ static ssize_t serialize_policy_show(struct mddev *mddev, char *page)if (mddev->pers ==NULL || (mddev->pers->head.id !=ID_RAID1 ))return sprintf (page,"n/a\n" );else -return sprintf (page,"%d\n" , mddev->serialize_policy); +return sprintf (page,"%d\n" , +test_bit (MD_SERIALIZE_POLICY , &mddev->flags)); }/* -* Setting serialize_policy to true to enforce write IO is not reordered +* Setting MD_SERIALIZE_POLICY enforce write IO is not reordered * for raid1. */ static ssize_t
@@ -5918,7 +5920,7 @@ serialize_policy_store(struct mddev *mddev, const char *buf, size_t len)if (err)return err; -if (value == mddev->serialize_policy) +if (value ==test_bit (MD_SERIALIZE_POLICY , &mddev->flags))return len; err =mddev_suspend_and_lock (mddev);
@@ -5930,11 +5932,13 @@ serialize_policy_store(struct mddev *mddev, const char *buf, size_t len) goto unlock; } -if (value) +if (value) {mddev_create_serial_pool (mddev,NULL ); -else +set_bit (MD_SERIALIZE_POLICY , &mddev->flags); + }else {mddev_destroy_serial_pool (mddev,NULL ); - mddev->serialize_policy = value; +clear_bit (MD_SERIALIZE_POLICY , &mddev->flags); + } unlock:mddev_unlock_and_resume (mddev);return err ?: len;
@@ -6907,7 +6911,7 @@ static void __md_stop_writes(struct mddev *mddev)md_update_sb (mddev,1 ); }/* disable policy to guarantee rdevs free resources for serialization */ - mddev->serialize_policy =0 ; +clear_bit (MD_SERIALIZE_POLICY , &mddev->flags);mddev_destroy_serial_pool (mddev,NULL ); }
drivers/md/md.h +2 -2
@@ -342,6 +342,7 @@ struct md_cluster_operations;* @MD_DELETED: This device is being deleted * @MD_HAS_SUPERBLOCK: There is persistence sb in member disks. * @MD_FAILLAST_DEV: Allow last rdev to be removed. +* @MD_SERIALIZE_POLICY: Enforce write IO is not reordered, just used by raid1. * * change UNSUPPORTED_MDDEV_FLAGS for each array type if new flag is added */
@@ -360,6 +361,7 @@ enum mddev_flags {MD_DELETED ,MD_HAS_SUPERBLOCK ,MD_FAILLAST_DEV , + MD_SERIALIZE_POLICY, }; enum mddev_sb_flags {
@@ -625,8 +627,6 @@ struct mddev {/* The sequence number for sync thread */ atomic_t sync_seq; - - bool serialize_policy:1; };enum recovery_flags {
drivers/md/raid0.c +2 -1
@@ -28,7 +28,8 @@ module_param(default_layout, int, 0644); (1L <<MD_FAILFAST_SUPPORTED ) |\ (1L <<MD_HAS_PPL ) | \ (1L <<MD_HAS_MULTIPLE_PPLS ) | \ - (1L << MD_FAILLAST_DEV)) + (1L <<MD_FAILLAST_DEV ) | \ + (1L << MD_SERIALIZE_POLICY))/* * inform the user of the raid configuration
drivers/md/raid1.c +2 -2
@@ -542,7 +542,7 @@ static void raid1_end_write_request(struct bio *bio)call_bio_endio (r1_bio); } } - }else if (rdev->mddev->serialize_policy) + }else if (test_bit (MD_SERIALIZE_POLICY , &rdev->mddev->flags))remove_serial (rdev, lo, hi);if (r1_bio->bios[mirror] ==NULL )rdev_dec_pending (rdev, conf->mddev);
@@ -1646,7 +1646,7 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio, mbio =bio_alloc_clone (rdev->bdev, bio,GFP_NOIO , &mddev->bio_set); -if (mddev->serialize_policy) +if (test_bit (MD_SERIALIZE_POLICY , &mddev->flags))wait_for_serialization (rdev, r1_bio); }
drivers/md/raid5.c +2 -1
@@ -58,7 +58,8 @@#define UNSUPPORTED_MDDEV_FLAGS \ ((1L << MD_FAILFAST_SUPPORTED) | \ - (1L << MD_FAILLAST_DEV)) + (1L << MD_FAILLAST_DEV) | \ + (1L << MD_SERIALIZE_POLICY))#define cpu_to_group (cpu) cpu_to_node(cpu)
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 834/1611 md/raid1: honor REQ_NOWAIT when waiting for behind writes
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Abd-Alrhman Masalkhi <[email protected]>
[ Upstream commit a286cb88ddb26c5f4377859d8e77233d9181eb82 ]
raid1 supports REQ_NOWAIT reads by avoiding waits in the barrier path through wait_read_barrier(). However, a read can still block on a WriteMostly device when the array uses a bitmap and there are outstanding behind writes.
In that case raid1 unconditionally calls wait_behind_writes(), which may sleep until all behind writes complete. As a result, a REQ_NOWAIT read can block despite the caller explicitly requesting non-blocking behavior.
This ensures that raid1 consistently honors REQ_NOWAIT reads across all paths that may otherwise wait for behind writes.
--- drivers/md/md-bitmap.c | 9 +++++++-- drivers/md/md-bitmap.h | 2 +- drivers/md/md-llbitmap.c | 13 ++++++++----- drivers/md/md.c | 2 +- drivers/md/raid1.c | 10 +++++++--- 5 files changed, 24 insertions(+), 12 deletions(-)
drivers/md/md-bitmap.c +7 -2
@@ -2064,18 +2064,23 @@ static void bitmap_end_behind_write(struct mddev *mddev) bitmap->mddev->bitmap_info.max_write_behind); } -static void bitmap_wait_behind_writes (struct mddev *mddev) +static bool bitmap_wait_behind_writes (struct mddev *mddev,bool nowait) {struct bitmap *bitmap = mddev->bitmap;/* wait for behind writes to complete */ if (bitmap &&atomic_read (&bitmap->behind_writes) >0 ) { +if (nowait) +return false; +pr_debug ("md:%s: behind writes in progress - waiting to stop.\n" ,mdname (mddev));/* need to kick something here to make sure I/O goes? */ wait_event (bitmap->behind_wait,atomic_read (&bitmap->behind_writes) ==0 ); } + +return true; }static void bitmap_destroy (struct mddev *mddev)
@@ -2085,7 +2090,7 @@ static void bitmap_destroy(struct mddev *mddev)if (!bitmap)/* there was no bitmap */ return ; -bitmap_wait_behind_writes (mddev); +bitmap_wait_behind_writes (mddev, false);if (!test_bit (MD_SERIALIZE_POLICY , &mddev->flags))mddev_destroy_serial_pool (mddev,NULL );
drivers/md/md-bitmap.h +1 -1
@@ -98,7 +98,7 @@ struct bitmap_operations {void (*start_behind_write)(struct mddev *mddev);void (*end_behind_write)(struct mddev *mddev); -void (*wait_behind_writes)(struct mddev *mddev); +bool (*wait_behind_writes)(struct mddev *mddev,bool nowait);md_bitmap_fn *start_write;md_bitmap_fn *end_write;
drivers/md/md-llbitmap.c +8 -5
@@ -1432,16 +1432,19 @@ static void llbitmap_end_behind_write(struct mddev *mddev)wake_up (&llbitmap->behind_wait); } -static void llbitmap_wait_behind_writes (struct mddev *mddev) +static bool llbitmap_wait_behind_writes (struct mddev *mddev,bool nowait) {struct llbitmap *llbitmap = mddev->bitmap; -if (!llbitmap) -return ; +if (llbitmap &&atomic_read (&llbitmap->behind_writes) >0 ) { +if (nowait) +return false; -wait_event (llbitmap->behind_wait, -atomic_read (&llbitmap->behind_writes) ==0 ); +wait_event (llbitmap->behind_wait, +atomic_read (&llbitmap->behind_writes) ==0 ); + } +return true; }static ssize_t bits_show (struct mddev *mddev,char *page)
drivers/md/md.c +1 -1
@@ -6928,7 +6928,7 @@ EXPORT_SYMBOL_GPL(md_stop_writes);static void mddev_detach (struct mddev *mddev) {if (md_bitmap_enabled (mddev, false)) - mddev->bitmap_ops->wait_behind_writes (mddev); + mddev->bitmap_ops->wait_behind_writes (mddev, false);if (mddev->pers && mddev->pers->quiesce && !is_md_suspended (mddev)) { mddev->pers->quiesce (mddev,1 ); mddev->pers->quiesce (mddev,0 );
drivers/md/raid1.c +7 -3
@@ -1319,6 +1319,7 @@ static void raid1_read_request(struct mddev *mddev, struct bio *bio,int max_sectors;int rdisk;bool r1bio_existed = !!r1_bio; +bool nowait = bio->bi_opf &REQ_NOWAIT ;/* * If r1_bio is set, we are blocking the raid1d thread
@@ -1331,8 +1332,7 @@ static void raid1_read_request(struct mddev *mddev, struct bio *bio,* Still need barrier for READ in case that whole * array is frozen. */ -if (!wait_read_barrier (conf, bio->bi_iter.bi_sector, - bio->bi_opf &REQ_NOWAIT )) { +if (!wait_read_barrier (conf, bio->bi_iter.bi_sector, nowait)) {bio_wouldblock_error (bio);return ; }
@@ -1373,7 +1373,11 @@ static void raid1_read_request(struct mddev *mddev, struct bio *bio,* over-take any writes that are 'behind' */ mddev_add_trace_msg (mddev,"raid1 wait behind writes" ); - mddev->bitmap_ops->wait_behind_writes (mddev); +if (!mddev->bitmap_ops->wait_behind_writes (mddev, nowait)) { +bio_wouldblock_error (bio); +set_bit (R1BIO_Returned, &r1_bio->state); + goto err_handle; + } }if (max_sectors <bio_sectors (bio)) {
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 835/1611 md/raid1: free r1_bio when REQ_NOWAIT is set and read would block on retry
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Abd-Alrhman Masalkhi <[email protected]>
[ Upstream commit 69ad6ce47f9bf2b9fe0ed69b042db993d33bbf12 ]
When a read is retried, raid1_read_request() may be called with a pre-allocated r1_bio. If wait_read_barrier() fails for a REQ_NOWAIT read, the bio is completed and the function returns immediately. In this case the existing r1_bio is leaked.
This fixes a leak of pre-allocated r1_bio structures for retried reads.
--- drivers/md/raid1.c | 6 ++++++ 1 file changed, 6 insertions(+)
drivers/md/raid1.c +6 -0
@@ -1334,6 +1334,12 @@ static void raid1_read_request(struct mddev *mddev, struct bio *bio,*/ if (!wait_read_barrier (conf, bio->bi_iter.bi_sector, nowait)) {bio_wouldblock_error (bio); + +if (r1bio_existed) { +set_bit (R1BIO_Returned, &r1_bio->state); +raid_end_bio_io (r1_bio); + } +return ; }
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 836/1611 netfilter: ipset: Fix data race between add and dump in all hash types
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Jozsef Kadlecsik <[email protected]>
[ Upstream commit 2358f7427ccd6ec8867a48205d8fcec973683a3f ]
When adding a new entry to the next position in the existing hash bucket, the position index was incremented too early and parallel dump could read it before the entry was populated with the value. Move the setting of the position index after populating the entry.
v2: Position counting fixed, noticed by Florian Westphal.
Stable-dep-of: e4b4984e28c1 ("netfilter: ipset: Don't use test_bit() in lockless RCU readers in hash types")
--- net/netfilter/ipset/ip_set_hash_gen.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-)
net/netfilter/ipset/ip_set_hash_gen.h +5 -2
@@ -844,7 +844,7 @@ mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext,const struct mtype_elem *d = value;struct mtype_elem *data;struct hbucket *n, *old =ERR_PTR (-ENOENT ); -int i, j =-1 , ret; +int i, j =-1 , npos =0 , ret;bool flag_exist = flags &IPSET_FLAG_EXIST ;bool deleted = false, forceadd = false, reuse = false;u32 r, key, multi =0 , elements, maxelem;
@@ -889,6 +889,7 @@ mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext,ext_size (AHASH_INIT_SIZE , set->dsize); goto copy_elem; } + npos = n->pos;for (i =0 ; i < n->pos; i++) {if (!test_bit (i, n->used)) {/* Reuse first deleted entry */
@@ -962,7 +963,8 @@ mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext, } copy_elem: - j = n->pos++; + j = npos; + npos = n->pos +1 ; data =ahash_data (n, j, set->dsize); copy_data: t->hregion[r].elements++;
@@ -985,6 +987,7 @@ mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext,if (SET_WITH_TIMEOUT (set))ip_set_timeout_set (ext_timeout (data, set), ext->timeout);smp_mb__before_atomic (); + n->pos = npos;set_bit (j, n->used);if (old !=ERR_PTR (-ENOENT )) {rcu_assign_pointer (hbucket (t, key), n);
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 837/1611 netfilter: ipset: annotate "pos" for concurrent readers/writers
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Jozsef Kadlecsik <[email protected]>
[ Upstream commit 7f7445840b7771338618930e45ee641104b38ed8 ]
The "pos" structure member of struct hbucket stores the first free slot in the hash bucket of a hash type of set and there are concurrent readers/writers. Annotate accesses properly.
Stable-dep-of: e4b4984e28c1 ("netfilter: ipset: Don't use test_bit() in lockless RCU readers in hash types")
--- net/netfilter/ipset/ip_set_hash_gen.h | 62 ++++++++++++++++----------- 1 file changed, 38 insertions(+), 24 deletions(-)
net/netfilter/ipset/ip_set_hash_gen.h +38 -24
@@ -386,8 +386,9 @@ static void mtype_ext_cleanup(struct ip_set *set, struct hbucket *n) { int i; +u8 pos =smp_load_acquire (&n->pos); -for (i =0 ; i < n->pos; i++) +for (i =0 ; i < pos; i++)if (test_bit (i, n->used))ip_set_ext_destroy (set,ahash_data (n, i, set->dsize)); }
@@ -490,7 +491,7 @@ mtype_gc_do(struct ip_set *set, struct htype *h, struct htable *t, u32 r)#ifdef IP_SET_HASH_WITH_NETS u8 k;#endif -u8 htable_bits = t->htable_bits; +u8 pos, htable_bits = t->htable_bits;spin_lock_bh (&t->hregion[r].lock); for (i = ahash_bucket_start(r, htable_bits);
@@ -498,7 +499,8 @@ mtype_gc_do(struct ip_set *set, struct htype *h, struct htable *t, u32 r) n =__ipset_dereference (hbucket (t, i));if (!n)continue ; -for (j =0 , d =0 ; j < n->pos; j++) { + pos =smp_load_acquire (&n->pos); +for (j =0 , d =0 ; j < pos; j++) {if (!test_bit (j, n->used)) { d++;continue ;
@@ -534,7 +536,7 @@ mtype_gc_do(struct ip_set *set, struct htype *h, struct htable *t, u32 r)/* Still try to delete expired elements. */ continue ; tmp->size = n->size -AHASH_INIT_SIZE ; -for (j =0 , d =0 ; j < n->pos; j++) { +for (j =0 , d =0 ; j < pos; j++) {if (!test_bit (j, n->used))continue ; data =ahash_data (n, j, dsize);
@@ -623,7 +625,7 @@ mtype_resize(struct ip_set *set, bool retried) {struct htype *h = set->data;struct htable *t, *orig; -u8 htable_bits; +u8 pos, htable_bits;size_t hsize, dsize = set->dsize;#ifdef IP_SET_HASH_WITH_NETS u8 flags;
@@ -685,7 +687,8 @@ mtype_resize(struct ip_set *set, bool retried) n =__ipset_dereference (hbucket (orig, i));if (!n)continue ; -for (j =0 ; j < n->pos; j++) { + pos =smp_load_acquire (&n->pos); +for (j =0 ; j < pos; j++) {if (!test_bit (j, n->used))continue ; data =ahash_data (n, j, dsize);
@@ -809,9 +812,10 @@ mtype_ext_size(struct ip_set *set, u32 *elements, size_t *ext_size) {struct htype *h = set->data;const struct htable *t; -u32 i, j, r;struct hbucket *n;struct mtype_elem *data; +u32 i, j, r; +u8 pos; t =rcu_dereference_bh (h->table);for (r =0 ; r <ahash_numof_locks (t->htable_bits); r++) {
@@ -820,7 +824,8 @@ mtype_ext_size(struct ip_set *set, u32 *elements, size_t *ext_size) n =rcu_dereference_bh (hbucket (t, i));if (!n)continue ; -for (j =0 ; j < n->pos; j++) { + pos =smp_load_acquire (&n->pos); +for (j =0 ; j < pos; j++) {if (!test_bit (j, n->used))continue ; data =ahash_data (n, j, set->dsize);
@@ -844,10 +849,11 @@ mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext,const struct mtype_elem *d = value;struct mtype_elem *data;struct hbucket *n, *old =ERR_PTR (-ENOENT ); -int i, j =-1 , npos =0 , ret; +int i, j =-1 , ret;bool flag_exist = flags &IPSET_FLAG_EXIST ;bool deleted = false, forceadd = false, reuse = false;u32 r, key, multi =0 , elements, maxelem; +u8 npos =0 ;rcu_read_lock_bh (); t =rcu_dereference_bh (h->table);
@@ -889,8 +895,8 @@ mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext,ext_size (AHASH_INIT_SIZE , set->dsize); goto copy_elem; } - npos = n->pos; -for (i =0 ; i < n->pos; i++) { + npos =smp_load_acquire (&n->pos); +for (i =0 ; i < npos; i++) {if (!test_bit (i, n->used)) {/* Reuse first deleted entry */ if (j ==-1 ) {
@@ -934,7 +940,7 @@ mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext,if (elements >= maxelem) goto set_full;/* Create a new slot */ -if (n->pos >= n->size) { +if (npos >= n->size) {#ifdef IP_SET_HASH_WITH_MULTI if (h->bucketsize >=AHASH_MAX_TUNED ) goto set_full;
@@ -963,8 +969,7 @@ mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext, } copy_elem: - j = npos; - npos = n->pos +1 ; + j = npos++; data =ahash_data (n, j, set->dsize); copy_data: t->hregion[r].elements++;
@@ -987,7 +992,8 @@ mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext,if (SET_WITH_TIMEOUT (set))ip_set_timeout_set (ext_timeout (data, set), ext->timeout);smp_mb__before_atomic (); - n->pos = npos; +/* Ensure all data writes are visible before updating position */ +smp_store_release (&n->pos, npos);set_bit (j, n->used);if (old !=ERR_PTR (-ENOENT )) {rcu_assign_pointer (hbucket (t, key), n);
@@ -1046,6 +1052,7 @@ mtype_del(struct ip_set *set, void *value, const struct ip_set_ext *ext,int i, j, k, r, ret = -IPSET_ERR_EXIST ;u32 key, multi =0 ;size_t dsize = set->dsize; +u8 pos;/* Userspace add and resize is excluded by the mutex. * Kernespace add does not trigger resize.
@@ -1061,7 +1068,8 @@ mtype_del(struct ip_set *set, void *value, const struct ip_set_ext *ext, n =rcu_dereference_bh (hbucket (t, key));if (!n) goto out; -for (i =0 , k =0 ; i < n->pos; i++) { + pos =smp_load_acquire (&n->pos); +for (i =0 , k =0 ; i < pos; i++) {if (!test_bit (i, n->used)) { k++;continue ;
@@ -1075,8 +1083,8 @@ mtype_del(struct ip_set *set, void *value, const struct ip_set_ext *ext, ret =0 ;clear_bit (i, n->used);smp_mb__after_atomic (); -if (i +1 == n->pos) - n->pos--; +if (i +1 == pos) +smp_store_release (&n->pos, --pos); t->hregion[r].elements--;#ifdef IP_SET_HASH_WITH_NETS for (j =0 ; j <IPSET_NET_COUNT ; j++)
@@ -1098,11 +1106,11 @@ mtype_del(struct ip_set *set, void *value, const struct ip_set_ext *ext, x->flags = flags; } } -for (; i < n->pos; i++) { +for (; i < pos; i++) {if (!test_bit (i, n->used)) k++; } -if (k == n->pos) { +if (k == pos) { t->hregion[r].ext_size -=ext_size (n->size, dsize);rcu_assign_pointer (hbucket (t, key),NULL );kfree_rcu (n, rcu);
@@ -1113,7 +1121,7 @@ mtype_del(struct ip_set *set, void *value, const struct ip_set_ext *ext,if (!tmp) goto out; tmp->size = n->size -AHASH_INIT_SIZE ; -for (j =0 , k =0 ; j < n->pos; j++) { +for (j =0 , k =0 ; j < pos; j++) {if (!test_bit (j, n->used))continue ; data =ahash_data (n, j, dsize);
@@ -1174,6 +1182,7 @@ mtype_test_cidrs(struct ip_set *set, struct mtype_elem *d,int ret, i, j =0 ;#endif u32 key, multi =0 ; +u8 pos;pr_debug ("test by nets\n" );for (; j <NLEN && h->nets[j].cidr[0 ] && !multi; j++) {
@@ -1191,7 +1200,8 @@ mtype_test_cidrs(struct ip_set *set, struct mtype_elem *d, n =rcu_dereference_bh (hbucket (t, key));if (!n)continue ; -for (i =0 ; i < n->pos; i++) { + pos =smp_load_acquire (&n->pos); +for (i =0 ; i < pos; i++) {if (!test_bit (i, n->used))continue ; data =ahash_data (n, i, set->dsize);
@@ -1225,6 +1235,7 @@ mtype_test(struct ip_set *set, void *value, const struct ip_set_ext *ext,struct mtype_elem *data;int i, ret =0 ;u32 key, multi =0 ; +u8 pos;rcu_read_lock_bh (); t =rcu_dereference_bh (h->table);
@@ -1247,7 +1258,8 @@ mtype_test(struct ip_set *set, void *value, const struct ip_set_ext *ext, ret =0 ; goto out; } -for (i =0 ; i < n->pos; i++) { + pos =smp_load_acquire (&n->pos); +for (i =0 ; i < pos; i++) {if (!test_bit (i, n->used))continue ; data =ahash_data (n, i, set->dsize);
@@ -1364,6 +1376,7 @@ mtype_list(const struct ip_set *set,/* We assume that one hash bucket fills into one page */ void *incomplete;int i, ret =0 ; +u8 pos; atd =nla_nest_start (skb,IPSET_ATTR_ADT );if (!atd)
@@ -1382,7 +1395,8 @@ mtype_list(const struct ip_set *set, cb->args[IPSET_CB_ARG0], t, n);if (!n)continue ; -for (i =0 ; i < n->pos; i++) { + pos =smp_load_acquire (&n->pos); +for (i =0 ; i < pos; i++) {if (!test_bit (i, n->used))continue ; e =ahash_data (n, i, set->dsize);
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 838/1611 netfilter: ipset: Dont use test_bit() in lockless RCU readers in hash types
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Jozsef Kadlecsik <[email protected]>
[ Upstream commit e4b4984e28c16406ecb318444dea4a8bf47def3e ]
Sashiko pointed out that there are a few lockless RCU readers using test_bit() which is a relaxed atomic operation and provides no memory barrier guarantees. Use test_bit_acquire() instead where the operation may run parallel with add/del/gc, i.e. is not one from the next cases
- protected by region lock
- in a set destroy phase
- in a new/temporary set creation phase
--- net/netfilter/ipset/ip_set_hash_gen.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-)
net/netfilter/ipset/ip_set_hash_gen.h +5 -5
@@ -689,7 +689,7 @@ mtype_resize(struct ip_set *set, bool retried)continue ; pos =smp_load_acquire (&n->pos);for (j =0 ; j < pos; j++) { -if (!test_bit (j, n->used)) +if (!test_bit_acquire (j, n->used))continue ; data =ahash_data (n, j, dsize);if (SET_ELEM_EXPIRED (set, data))
@@ -826,7 +826,7 @@ mtype_ext_size(struct ip_set *set, u32 *elements, size_t *ext_size)continue ; pos =smp_load_acquire (&n->pos);for (j =0 ; j < pos; j++) { -if (!test_bit (j, n->used)) +if (!test_bit_acquire (j, n->used))continue ; data =ahash_data (n, j, set->dsize);if (!SET_ELEM_EXPIRED (set, data))
@@ -1202,7 +1202,7 @@ mtype_test_cidrs(struct ip_set *set, struct mtype_elem *d,continue ; pos =smp_load_acquire (&n->pos);for (i =0 ; i < pos; i++) { -if (!test_bit (i, n->used)) +if (!test_bit_acquire (i, n->used))continue ; data =ahash_data (n, i, set->dsize);if (!mtype_data_equal (data, d, &multi))
@@ -1260,7 +1260,7 @@ mtype_test(struct ip_set *set, void *value, const struct ip_set_ext *ext, } pos =smp_load_acquire (&n->pos);for (i =0 ; i < pos; i++) { -if (!test_bit (i, n->used)) +if (!test_bit_acquire (i, n->used))continue ; data =ahash_data (n, i, set->dsize);if (!mtype_data_equal (data, d, &multi))
@@ -1397,7 +1397,7 @@ mtype_list(const struct ip_set *set,continue ; pos =smp_load_acquire (&n->pos);for (i =0 ; i < pos; i++) { -if (!test_bit (i, n->used)) +if (!test_bit_acquire (i, n->used))continue ; e =ahash_data (n, i, set->dsize);if (SET_ELEM_EXPIRED (set, e))
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 839/1611 netfilter: ipset: fix order of kfree_rcu() and rcu_assign_pointer()
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Jozsef Kadlecsik <[email protected]>
[ Upstream commit 3ca9982a8882470aa0ac4e8bb9a552b181d1efcd ]
Sashiko pointed out that kfree_rcu() was called before rcu_assign_pointer() in handling the comment extension. Fix the order so that rcu_assign_pointer() called first.
--- net/netfilter/ipset/ip_set_core.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
net/netfilter/ipset/ip_set_core.c +2 -2
@@ -351,8 +351,8 @@ ip_set_init_comment(struct ip_set *set, struct ip_set_comment *comment,if (unlikely (c)) { set->ext_size -=sizeof (*c) +strlen (c->str) +1 ; -kfree_rcu (c, rcu);rcu_assign_pointer (comment->c,NULL ); +kfree_rcu (c, rcu); }if (!len)return ;
@@ -393,8 +393,8 @@ ip_set_comment_free(struct ip_set *set, void *ptr)if (unlikely (!c))return ; set->ext_size -=sizeof (*c) +strlen (c->str) +1 ; -kfree_rcu (c, rcu);rcu_assign_pointer (comment->c,NULL ); +kfree_rcu (c, rcu); }typedef void (*destroyer )(struct ip_set *,void *);
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 840/1611 netfilter: ipset: make sure gc is properly stopped
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Jozsef Kadlecsik <[email protected]>
[ Upstream commit 4a597a87e2e2f608edb6be2c510dc826b4fdfb53 ]
Sashiko noticed that when destroying a set,cancel_delayed_work_sync() was called while gc
calls queue_delayed_work() unconditionally which
can lead not to properly shutting down the gc.
--- net/netfilter/ipset/ip_set_hash_gen.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
net/netfilter/ipset/ip_set_hash_gen.h +1 -1
@@ -606,7 +606,7 @@ mtype_cancel_gc(struct ip_set *set)struct htype *h = set->data;if (SET_WITH_TIMEOUT (set)) -cancel_delayed_work_sync (&h->gc.dwork); +disable_delayed_work_sync (&h->gc.dwork); } static int
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 841/1611 netfilter: nft_payload: reject offsets exceeding 65535 bytes
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Florian Westphal <[email protected]>
[ Upstream commit 213be32f46a29ca15a314df06c3424ecffd6c90a ]
Large offsets were rejected based on netlink policy, but blamed commit removed the policy without updating nft_payload_inner_init() to use the truncation-check helper.
Silent truncation is not a problem, but not wanted either, so add a check.
--- net/netfilter/nft_payload.c | 16 +++++++++++++--- 1 file changed, 13 insertions(+), 3 deletions(-)
net/netfilter/nft_payload.c +13 -3
@@ -224,11 +224,17 @@ static int nft_payload_init(const struct nft_ctx *ctx, const struct nlattr * const tb[]) {struct nft_payload *priv =nft_expr_priv (expr); +u32 offset; +int err; priv->base =ntohl (nla_get_be32 (tb[NFTA_PAYLOAD_BASE ])); - priv->offset =ntohl (nla_get_be32 (tb[NFTA_PAYLOAD_OFFSET ])); priv->len =ntohl (nla_get_be32 (tb[NFTA_PAYLOAD_LEN ])); + err =nft_parse_u32_check (tb[NFTA_PAYLOAD_OFFSET ],U16_MAX , &offset); +if (err <0 ) +return err; + priv->offset = offset; +return nft_parse_register_store (ctx, tb[NFTA_PAYLOAD_DREG ], &priv->dreg,NULL ,NFT_DATA_VALUE , priv->len);
@@ -648,7 +654,8 @@ static int nft_payload_inner_init(const struct nft_ctx *ctx, const struct nlattr * const tb[]) {struct nft_payload *priv =nft_expr_priv (expr); -u32 base; +u32 base, offset; +int err;if (!tb[NFTA_PAYLOAD_BASE ] || !tb[NFTA_PAYLOAD_OFFSET ] || !tb[NFTA_PAYLOAD_LEN ] || !tb[NFTA_PAYLOAD_DREG ])
@@ -666,8 +673,11 @@ static int nft_payload_inner_init(const struct nft_ctx *ctx, } priv->base = base; - priv->offset =ntohl (nla_get_be32 (tb[NFTA_PAYLOAD_OFFSET ])); priv->len =ntohl (nla_get_be32 (tb[NFTA_PAYLOAD_LEN ])); + err =nft_parse_u32_check (tb[NFTA_PAYLOAD_OFFSET ],U16_MAX , &offset); +if (err <0 ) +return err; + priv->offset = offset; return nft_parse_register_store(ctx, tb[NFTA_PAYLOAD_DREG], &priv->dreg, NULL, NFT_DATA_VALUE,
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 842/1611 netfilter: nft_meta_bridge: add validate callback for get operations
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Florian Westphal <[email protected]>
[ Upstream commit bff1c8b49a9cb5c04af20f4e7d43bf4af5863bc6 ]
Blamed commit added NFT_META_BRI_IIFHWADDR to the set validate callback, yet this is a get operation.
Add a get validate callback and move the NFT_META_BRI_IIFHWADDR key there.
AFAICS this is harmless, NFT_META_BRI_IIFHWADDR can deal with a NULL input device and the set handler ignores a NFT_META_BRI_IIFHWADDR operation, but it allows to read 4 bytes off bridge skb->cb[].
--- include/net/netfilter/nft_meta.h | 2 ++ net/bridge/netfilter/nft_meta_bridge.c | 19 ++++++++++++++++++- net/netfilter/nft_meta.c | 5 +++-- 3 files changed, 23 insertions(+), 3 deletions(-)
include/net/netfilter/nft_meta.h +2 -0
@@ -40,6 +40,8 @@ void nft_meta_set_eval(const struct nft_expr *expr,void nft_meta_set_destroy (const struct nft_ctx *ctx,const struct nft_expr *expr); +int nft_meta_get_validate (const struct nft_ctx *ctx, +const struct nft_expr *expr);int nft_meta_set_validate (const struct nft_ctx *ctx,const struct nft_expr *expr);
net/bridge/netfilter/nft_meta_bridge.c +18 -1
@@ -107,12 +107,30 @@ static int nft_meta_bridge_get_init(const struct nft_ctx *ctx, NULL, NFT_DATA_VALUE, len); } +static int nft_meta_bridge_get_validate (const struct nft_ctx *ctx, +const struct nft_expr *expr) +{ +struct nft_meta *priv =nft_expr_priv (expr); +unsigned int hooks; + +switch (priv->key) { +case NFT_META_BRI_IIFHWADDR : + hooks =1 <<NF_BR_PRE_ROUTING ; +break ; +default : +return nft_meta_get_validate (ctx, expr); + } + +return nft_chain_validate_hooks (ctx->chain, hooks); +} +static struct nft_expr_type nft_meta_bridge_type;static const struct nft_expr_ops nft_meta_bridge_get_ops = { .type = &nft_meta_bridge_type, .size =NFT_EXPR_SIZE (sizeof (struct nft_meta )), .eval = nft_meta_bridge_get_eval, .init = nft_meta_bridge_get_init, + .validate = nft_meta_bridge_get_validate, .dump = nft_meta_get_dump, .reduce = nft_meta_get_reduce, };
@@ -187,7 +205,6 @@ static int nft_meta_bridge_set_validate(const struct nft_ctx *ctx,switch (priv->key) {case NFT_META_BRI_BROUTE : -case NFT_META_BRI_IIFHWADDR : hooks =1 <<NF_BR_PRE_ROUTING ;break ;default :
net/netfilter/nft_meta.c +3 -2
@@ -580,8 +580,8 @@ static int nft_meta_get_validate_xfrm(const struct nft_ctx *ctx)#endif } -static int nft_meta_get_validate (const struct nft_ctx *ctx, -const struct nft_expr *expr) +int nft_meta_get_validate (const struct nft_ctx *ctx, +const struct nft_expr *expr) {const struct nft_meta *priv =nft_expr_priv (expr);
@@ -597,6 +597,7 @@ static int nft_meta_get_validate(const struct nft_ctx *ctx,return 0 ; } +EXPORT_SYMBOL_GPL (nft_meta_get_validate);int nft_meta_set_validate (const struct nft_ctx *ctx,const struct nft_expr *expr)
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 843/1611 netfilter: flowtable: move path discovery infrastructure to its own file
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Pablo Neira Ayuso <[email protected]>
[ Upstream commit 93d7a7ed07342f5e3da2d250cfd67f899d0b5318 ]
This file contains the path discovery that is run from the forward chain for the packet offloading the flow into the flowtable. This consists of a series of calls to dev_fill_forward_path() for each device stack.
More topologies may be supported in the future, so move this code to its own file to separate it from the nftables flow_offload expression.
Stable-dep-of: e409c23c2d06 ("netfilter: nft_flow_offload: zero device address for non-ether case")
--- include/net/netfilter/nf_flow_table.h | 6 + net/netfilter/Makefile | 1 + net/netfilter/nf_flow_table_path.c | 274 ++++++++++++++++++++++++++ net/netfilter/nft_flow_offload.c | 259 ------------------------ 4 files changed, 281 insertions(+), 259 deletions(-) create mode 100644 net/netfilter/nf_flow_table_path.c
include/net/netfilter/nf_flow_table.h +6 -0
@@ -222,6 +222,12 @@ struct nf_flow_route {struct flow_offload *flow_offload_alloc (struct nf_conn *ct);void flow_offload_free (struct flow_offload *flow); +struct nft_flowtable ; +struct nft_pktinfo ; +int nft_flow_route (const struct nft_pktinfo *pkt,const struct nf_conn *ct, +struct nf_flow_route *route,enum ip_conntrack_dir dir, +struct nft_flowtable *ft); +static inline int nf_flow_table_offload_add_cb (struct nf_flowtable *flow_table,flow_setup_cb_t *cb,void *cb_priv)
net/netfilter/Makefile +1 -0
@@ -141,6 +141,7 @@ obj-$(CONFIG_NFT_FWD_NETDEV) += nft_fwd_netdev.o # flow table infrastructure obj-$(CONFIG_NF_FLOW_TABLE) += nf_flow_table.o nf_flow_table-objs := nf_flow_table_core.o nf_flow_table_ip.o \ + nf_flow_table_path.o \ nf_flow_table_offload.o nf_flow_table_xdp.o nf_flow_table-$(CONFIG_NF_FLOW_TABLE_PROCFS) += nf_flow_table_procfs.o ifeq ($(CONFIG_NF_FLOW_TABLE),m)
net/netfilter/nf_flow_table_path.c new file +274 -0
274 lines not on this page · raw message
net/netfilter/nft_flow_offload.c +0 -259
265 lines not on this page · raw message
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 844/1611 netfilter: nft_flow_offload: zero device address for non-ether case
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Florian Westphal <[email protected]>
[ Upstream commit e409c23c2d0630f3b95efd12428b2e58800b7645 ]
LLM points out that the skip causes unitialised stack array to propagate down into dev_fill_forward_path(). Its not clear to me that there is a guarantee that a later ctx.dev->netdev_ops->ndo_fill_forward_path() would always fix this up.
--- net/netfilter/nf_flow_table_path.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)
net/netfilter/nf_flow_table_path.c +3 -1
@@ -52,8 +52,10 @@ static int nft_dev_fill_forward_path(const struct nf_flow_route *route,struct neighbour *n;u8 nud_state; -if (!nft_is_valid_ether_device (dev)) +if (!nft_is_valid_ether_device (dev)) { +eth_zero_addr (ha); goto out; + } n =dst_neigh_lookup (dst_cache, daddr);if (!n)
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 845/1611 netfilter: nf_reject: skip iphdr options when looking for icmp header
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Florian Westphal <[email protected]>
[ Upstream commit af8d6ae09c0a5f8b8a0d5680203c74b3c1daa85b ]
Not a big deal but this hould have used the real ip header length and not the base header size. As-is, if there are options then nf_skb_is_icmp_unreach() result will be random.
--- net/ipv4/netfilter/nf_reject_ipv4.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
net/ipv4/netfilter/nf_reject_ipv4.c +1 -1
@@ -89,7 +89,7 @@ static bool nf_skb_is_icmp_unreach(const struct sk_buff *skb)if (iph->protocol !=IPPROTO_ICMP )return false; - thoff =skb_network_offset (skb) +sizeof (*iph); + thoff =skb_network_offset (skb) +ip_hdrlen (skb); tp = skb_header_pointer(skb, thoff + offsetof(struct icmphdr, type),
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 846/1611 netfilter: nft_meta_bridge: fix NFT_META_BRI_IIFPVID stack leak
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Florian Westphal <[email protected]>
[ Upstream commit 27dd2997746d54ebc079bb13161cc1bdd401d4a6 ]
This needs to test for nonzero retval.
--- net/bridge/netfilter/nft_meta_bridge.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)
net/bridge/netfilter/nft_meta_bridge.c +3 -1
@@ -44,7 +44,9 @@ static void nft_meta_bridge_get_eval(const struct nft_expr *expr,if (!br_dev || !br_vlan_enabled (br_dev)) goto err; -br_vlan_get_pvid_rcu (in, &p_pvid); +if (br_vlan_get_pvid_rcu (in, &p_pvid)) + goto err; +nft_reg_store16 (dest, p_pvid);return ; }
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 847/1611 mailbox: imx: Forward the timeout/ error in imx_mu_generic_tx()
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Sebastian Andrzej Siewior <[email protected]>
[ Upstream commit 82ef9a635d7130ca27ec9dd88c16afc39c83a4e8 ]
imx_mu_generic_tx() for the IMX_MU_TYPE_TXDB_V2 type polls on a register which may timeout and is recognized as an error. This error is siltently dropped and not dropped to the caller.
Forward the error to the caller.
--- drivers/mailbox/imx-mailbox.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)
drivers/mailbox/imx-mailbox.c +2 -1
@@ -229,6 +229,7 @@ static int imx_mu_generic_tx(struct imx_mu_priv *priv,u32 val;int ret, count; + ret =0 ;switch (cp->type) {case IMX_MU_TYPE_TX :imx_mu_write (priv, *arg, priv->dcfg->xTR + cp->idx *4 );
@@ -261,7 +262,7 @@ static int imx_mu_generic_tx(struct imx_mu_priv *priv,return -EINVAL ; } -return 0 ; +return ret; } static int imx_mu_generic_rx(struct imx_mu_priv *priv,
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 848/1611 irqchip/crossbar: Fix parent domain resource leak
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Bhargav Joshi <[email protected]>
[ Upstream commit a1074dd62faa6572921d387e8a21589ccea00efc ]
irq_domain_alloc_irqs_parent() is called in allocate_gic_irq() but irq_domain_free_irqs_parent() is never called which causes a resource leak.
Fix this by calling irq_domain_free_irqs_parent() in crossbar_domain_free().
--- drivers/irqchip/irq-crossbar.c | 1 + 1 file changed, 1 insertion(+)
drivers/irqchip/irq-crossbar.c +1 -0
@@ -163,6 +163,7 @@ static void crossbar_domain_free(struct irq_domain *domain, unsigned int virq, cb->write (d->hwirq, cb->safe_map); }raw_spin_unlock (&cb->lock); +irq_domain_free_irqs_parent (domain, virq, nr_irqs); } static int crossbar_domain_translate(struct irq_domain *d,
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 849/1611 alloc_tag: fix use-after-free in /proc/allocinfo after module unload
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Hao Ge <[email protected]>
[ Upstream commit 2956268efc457cb05d29c1bf94de1e8e684d7bbc ]
allocinfo_start() only reinitializes the codetag iterator at position 0. For subsequent reads (position > 0), it reuses cached iterator state from the previous batch. allocinfo_stop() drops mod_lock between read batches, which allows module unload to complete and free the module memory that the cached iterator still references:
CPU0 (read) CPU1 (rmmod)
---- ----
allocinfo_start(pos=0)
down_read(mod_lock)
allocinfo_show()
...
allocinfo_stop()
up_read(mod_lock)
codetag_unload_module()
kfree(cmod)
release_module_tags()
...
free_mod_mem()
allocinfo_start(pos=N)
down_read(mod_lock)
// reuses cached iter, skips re-init
allocinfo_show()
ct->filename <-- UAFAfter free_mod_mem() frees the module's .rodata, allocinfo_show() dereferences ct->filename, ct->function which point there.
Save the iterator state in allocinfo_next() and resume from it in allocinfo_start() with codetag_next_ct(), which detects module removal via idr_find() returning NULL and skips to the next module.
--- lib/alloc_tag.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-)
lib/alloc_tag.c +7 -2
@@ -45,6 +45,7 @@ int alloc_tag_ref_offs;struct allocinfo_private {struct codetag_iterator iter; +struct codetag_iterator reported_iter;bool print_header; };
@@ -58,16 +59,20 @@ static void *allocinfo_start(struct seq_file *m, loff_t *pos)if (node ==0 ) { priv->print_header = true; priv->iter =codetag_get_ct_iter (alloc_tag_cttype); -codetag_next_ct (&priv->iter); + }else { + priv->iter = priv->reported_iter; } +codetag_next_ct (&priv->iter);return priv->iter.ct ? priv :NULL ; }static void *allocinfo_next (struct seq_file *m,void *arg,loff_t *pos) {struct allocinfo_private *priv = (struct allocinfo_private *)arg; -struct codetag *ct =codetag_next_ct (&priv->iter); +struct codetag *ct; + priv->reported_iter = priv->iter; + ct =codetag_next_ct (&priv->iter); (*pos)++;if (!ct)return NULL ;
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 850/1611 selftests/mm: restore default nr_hugepages value via exit trap in charge_reserved_hugetlb.sh
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Sayali Patil <[email protected]>
[ Upstream commit a3f66e9b6e4dad38444656ffc28c28c33a4d4e1f ]
Patch series "selftests/mm: fix failures and robustness improvements", v7.
Powerpc systems with a 64K base page size exposed several issues while running mm selftests. Some tests assume specific hugetlb configurations, use incorrect interfaces, or fail instead of skipping when the required kernel features are not available.
This series fixes these issues and improves test robustness.
This patch (of 13):
cleanup() resets nr_hugepages to 0 on every invocation, while the test reconfigures it again in the next iteration. This leads to repeated allocation and freeing of large numbers of hugepages, especially when the original value is high.
Additionally, with set -e, failures in earlier cleanup steps (e.g., rmdir or umount returning EBUSY while background activity is still ongoing) can cause the script to exit before restoring the original value, leaving the system in a modified state.
Introduce a trap on EXIT, INT, and TERM to restore the original nr_hugepages value once at script termination. This avoids unnecessary allocation churn and ensures the original value is reliably restored on all exit paths.
--- tools/testing/selftests/mm/charge_reserved_hugetlb.sh | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-)
tools/testing/selftests/mm/charge_reserved_hugetlb.sh +1 -2
@@ -12,6 +12,7 @@ if [[ $(id -u) -ne 0 ]]; then fi nr_hugepgs=$(cat /proc/sys/vm/nr_hugepages) +trap 'echo "$nr_hugepgs" > /proc/sys/vm/nr_hugepages' EXIT INT TERM fault_limit_file=limit_in_bytes reservation_limit_file=rsvd.limit_in_bytes
@@ -65,7 +66,6 @@ function cleanup() { if [[ -e $cgroup_path/hugetlb_cgroup_test2 ]]; then rmdir $cgroup_path/hugetlb_cgroup_test2 fi - echo 0 >/proc/sys/vm/nr_hugepages echo CLEANUP DONE }
@@ -585,4 +585,3 @@ if [[ $do_umount ]]; then rmdir $cgroup_path fi -echo "$nr_hugepgs" > /proc/sys/vm/nr_hugepages
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 851/1611 selftests/mm: restore default nr_hugepages value via exit trap in hugetlb_reparenting_test.sh
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Sayali Patil <[email protected]>
[ Upstream commit 7f9c0920ff3debae3cb4d60260e3daf56ab68395 ]
The test modifies nr_hugepages during execution and restores it from cleanup() and again reconfigure it setup, which is invoked multiple times across test flow. This can lead to repeated allocation/freeing of hugepages.
With set -e, failures in cleanup (e.g., rmdir/umount) can also cause early exit before restoring the original value at the end.
Move restoration of the original nr_hugepages value to a trap handler registered for EXIT, INT, and TERM signals so it is always restored on all exit paths. This also avoids unnecessary allocation churn across repeated cleanup/setup cycles.
--- tools/testing/selftests/mm/hugetlb_reparenting_test.sh | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
tools/testing/selftests/mm/hugetlb_reparenting_test.sh +2 -2
@@ -12,6 +12,8 @@ if [[ $(id -u) -ne 0 ]]; then fi nr_hugepgs=$(cat /proc/sys/vm/nr_hugepages) +trap 'echo "$nr_hugepgs" > /proc/sys/vm/nr_hugepages' EXIT INT TERM + usage_file=usage_in_bytes if [[ "$1" == "-cgroup-v2" ]]; then
@@ -56,7 +58,6 @@ function cleanup() { rmdir "$CGROUP_ROOT"/a/b 2>/dev/null rmdir "$CGROUP_ROOT"/a 2>/dev/null rmdir "$CGROUP_ROOT"/test1 2>/dev/null - echo $nr_hugepgs >/proc/sys/vm/nr_hugepages set -e }
@@ -240,4 +241,3 @@ if [[ $do_umount ]]; then rm -rf $CGROUP_ROOT fi -echo "$nr_hugepgs" > /proc/sys/vm/nr_hugepages
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 852/1611 selftests/mm: fix hugetlb pathname construction in hugetlb_reparenting_test.sh
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Sayali Patil <[email protected]>
[ Upstream commit 76f9a212a0a93572a28b58d9869e9187c4022342 ]
The hugetlb_reparenting_test.sh script constructs hugetlb cgroup memory interface file names based on the configured huge page size. The script formats the size only in MB units, which causes mismatches on systems using larger huge pages where the kernel exposes normalized units (e.g. "1GB" instead of "1024MB").
As a result, the test fails to locate the corresponding cgroup files when 1GB huge pages are configured.
Update the script to detect the huge page size and select the appropriate unit (MB or GB) so that the constructed paths match the kernel's hugetlb controller naming.
Also print an explicit "Fail" message when a test failure occurs to improve result visibility.
--- .../selftests/mm/hugetlb_reparenting_test.sh | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-)
tools/testing/selftests/mm/hugetlb_reparenting_test.sh +12 -2
@@ -48,6 +48,13 @@ function get_machine_hugepage_size() { } MB=$(get_machine_hugepage_size) +if (( MB >= 1024 )); then + UNIT="GB" + MB_DISPLAY=$((MB / 1024)) +else + UNIT="MB" + MB_DISPLAY=$MB +fi function cleanup() { echo cleanup
@@ -88,6 +95,7 @@ function assert_with_retry() { if [[ $elapsed -ge $timeout ]]; then echo "actual = $((${actual%% *} / 1024 / 1024)) MB" echo "expected = $((${expected%% *} / 1024 / 1024)) MB" + echo FAIL cleanup exit 1 fi
@@ -108,11 +116,13 @@ function assert_state() { fi assert_with_retry "$CGROUP_ROOT/a/memory.$usage_file" "$expected_a" - assert_with_retry "$CGROUP_ROOT/a/hugetlb.${MB}MB.$usage_file" "$expected_a_hugetlb" + assert_with_retry \ + "$CGROUP_ROOT/a/hugetlb.${MB_DISPLAY}${UNIT}.$usage_file" "$expected_a_hugetlb" if [[ -n "$expected_b" && -n "$expected_b_hugetlb" ]]; then assert_with_retry "$CGROUP_ROOT/a/b/memory.$usage_file" "$expected_b" - assert_with_retry "$CGROUP_ROOT/a/b/hugetlb.${MB}MB.$usage_file" "$expected_b_hugetlb" + assert_with_retry \ + "$CGROUP_ROOT/a/b/hugetlb.${MB_DISPLAY}${UNIT}.$usage_file" "$expected_b_hugetlb" fi }
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 853/1611 selftests/mm: fix cgroup task placement and drop memory.current checks in hugetlb_reparenting_test.sh
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Sayali Patil <[email protected]>
[ Upstream commit 7bbdc459527075c4d0b96133de25a53822397af0 ]
The test currently moves the calling shell ($$) into the target cgroup before executing write_to_hugetlbfs. This results in the shell and any intermediate allocations being charged to the cgroup, introducing noise and nondeterminism in accounting. It also requires moving the shell back to the root cgroup after execution.
Spawn a helper process that joins the target cgroup and exec()'s write_to_hugetlbfs. This ensures that only the workload is accounted to the cgroup and avoids unintended charging from the shell.
The test currently validates both hugetlb usage and memory.current. However, memory.current includes internal memcg allocations and per-CPU batched accounting (MEMCG_CHARGE_BATCH), which are not synchronized and can vary across systems, leading to non-deterministic results.
Since hugetlb memory is accounted via hugetlb.<size>.current, memory.current is not a reliable indicator here. Drop memory.current checks and rely only on hugetlb controller statistics for stable and accurate validation.
--- .../selftests/mm/hugetlb_reparenting_test.sh | 42 ++++++++----------- 1 file changed, 18 insertions(+), 24 deletions(-)
tools/testing/selftests/mm/hugetlb_reparenting_test.sh +18 -24
@@ -105,22 +105,17 @@ function assert_with_retry() { } function assert_state() { - local expected_a="$1" - local expected_a_hugetlb="$2" - local expected_b="" + local expected_a_hugetlb="$1" local expected_b_hugetlb="" - if [ ! -z ${3:-} ] && [ ! -z ${4:-} ]; then - expected_b="$3" - expected_b_hugetlb="$4" + if [ ! -z ${2:-} ]; then + expected_b_hugetlb="$2" fi - assert_with_retry "$CGROUP_ROOT/a/memory.$usage_file" "$expected_a" assert_with_retry \ "$CGROUP_ROOT/a/hugetlb.${MB_DISPLAY}${UNIT}.$usage_file" "$expected_a_hugetlb" - if [[ -n "$expected_b" && -n "$expected_b_hugetlb" ]]; then - assert_with_retry "$CGROUP_ROOT/a/b/memory.$usage_file" "$expected_b" + if [[ -n "$expected_b_hugetlb" ]]; then assert_with_retry \ "$CGROUP_ROOT/a/b/hugetlb.${MB_DISPLAY}${UNIT}.$usage_file" "$expected_b_hugetlb" fi
@@ -154,18 +149,17 @@ write_hugetlbfs() { local size="$3" if [[ $cgroup2 ]]; then - echo $$ >$CGROUP_ROOT/$cgroup/cgroup.procs + cg_file="$CGROUP_ROOT/$cgroup/cgroup.procs" else echo 0 >$CGROUP_ROOT/$cgroup/cpuset.mems echo 0 >$CGROUP_ROOT/$cgroup/cpuset.cpus - echo $$ >"$CGROUP_ROOT/$cgroup/tasks" - fi - ./write_to_hugetlbfs -p "$path" -s "$size" -m 0 -o - if [[ $cgroup2 ]]; then - echo $$ >$CGROUP_ROOT/cgroup.procs - else - echo $$ >"$CGROUP_ROOT/tasks" + cg_file="$CGROUP_ROOT/$cgroup/tasks" fi + + # Spawn helper to join cgroup before exec to ensure correct cgroup accounting + bash -c 'echo $$ > "$1"; exec ./write_to_hugetlbfs -p "$2" -s "$3" -m 0 -o' _ \ + "$cg_file" "$path" "$size" & pid=$! + wait "$pid" echo }
@@ -203,21 +197,21 @@ if [[ ! $cgroup2 ]]; then write_hugetlbfs a "$MNT"/test $size echo Assert memory charged correctly for parent use. - assert_state 0 $size 0 0 + assert_state $size 0 write_hugetlbfs a/b "$MNT"/test2 $size echo Assert memory charged correctly for child use. - assert_state 0 $(($size * 2)) 0 $size + assert_state $(($size * 2)) $size rmdir "$CGROUP_ROOT"/a/b echo Assert memory reparent correctly. - assert_state 0 $(($size * 2)) + assert_state $(($size * 2)) rm -rf "$MNT"/* umount "$MNT" echo Assert memory uncharged correctly. - assert_state 0 0 + assert_state 0 cleanup fi
@@ -231,16 +225,16 @@ echo write write_hugetlbfs a/b "$MNT"/test2 $size echo Assert memory charged correctly for child only use. -assert_state 0 $(($size)) 0 $size +assert_state $(($size)) $size rmdir "$CGROUP_ROOT"/a/b echo Assert memory reparent correctly. -assert_state 0 $size +assert_state $size rm -rf "$MNT"/* umount "$MNT" echo Assert memory uncharged correctly. -assert_state 0 0 +assert_state 0 cleanup
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 854/1611 selftests/mm: size tmpfs according to PMD page size in split_huge_page_test
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Sayali Patil <[email protected]>
[ Upstream commit a2dde8a065d5c8d63b53b1c8f035017e4aeac0c2 ]
The split_file_backed_thp() test mounts a tmpfs with a fixed size of "4m". This works on systems with smaller PMD page sizes, but fails on configurations where the PMD huge page size is larger (e.g. 16MB).
On such systems, the fixed 4MB tmpfs is insufficient to allocate even a single PMD-sized THP, causing the test to fail.
Fix this by sizing the tmpfs dynamically based on the runtime pmd_pagesize, allocating space for two PMD-sized pages.
Before patch:
running ./split_huge_page_test /tmp/xfs_dir_YTrI5E
--------------------------------------------------
TAP version 13
1..55
ok 1 Split zero filled huge pages successful
ok 2 Split huge pages to order 0 successful
ok 3 Split huge pages to order 2 successful
ok 4 Split huge pages to order 3 successful
ok 5 Split huge pages to order 4 successful
ok 6 Split huge pages to order 5 successful
ok 7 Split huge pages to order 6 successful
ok 8 Split huge pages to order 7 successful
ok 9 Split PTE-mapped huge pages successful
Please enable pr_debug in split_huge_pages_in_file() for more info. Failed to write data to testing file: Success (0)
Bail out! Error occurred
Planned tests != run tests (55 != 9)
Totals: pass:9 fail:0 xfail:0 xpass:0 skip:0 error:0
[FAIL]
After patch:
running ./split_huge_page_test /tmp/xfs_dir_bMvj6o
--------------------------------------------------
TAP version 13
1..55
ok 1 Split zero filled huge pages successful
ok 2 Split huge pages to order 0 successful
ok 3 Split huge pages to order 2 successful
ok 4 Split huge pages to order 3 successful
ok 5 Split huge pages to order 4 successful
ok 6 Split huge pages to order 5 successful
ok 7 Split huge pages to order 6 successful
ok 8 Split huge pages to order 7 successful
ok 9 Split PTE-mapped huge pages successful
Please enable pr_debug in split_huge_pages_in_file() for more info. Please check dmesg for more information
ok 10 File-backed THP split to order 0 test done
Please enable pr_debug in split_huge_pages_in_file() for more info. Please check dmesg for more information
ok 11 File-backed THP split to order 1 test done
Please enable pr_debug in split_huge_pages_in_file() for more info. Please check dmesg for more information
ok 12 File-backed THP split to order 2 test done
...
ok 55 Split PMD-mapped pagecache folio to order 7 at
in-folio offset 128 passed
Totals: pass:55 fail:0 xfail:0 xpass:0 skip:0 error:0 [PASS]
ok 1 split_huge_page_test /tmp/xfs_dir_bMvj6o
--- tools/testing/selftests/mm/split_huge_page_test.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-)
tools/testing/selftests/mm/split_huge_page_test.c +4 -1
@@ -484,6 +484,8 @@ static void split_file_backed_thp(int order)char tmpfs_template[] ="/tmp/thp_split_XXXXXX" ;const char *tmpfs_loc =mkdtemp (tmpfs_template);char testfile[INPUT_MAX ]; +unsigned long size =2 * pmd_pagesize; +char opts[64 ];ssize_t num_written, num_read;char *file_buf1, *file_buf2;uint64_t pgoff_start =0 , pgoff_end =1024 ;
@@ -503,7 +505,8 @@ static void split_file_backed_thp(int order) file_buf1[i] = (char )i;memset (file_buf2,0 , pmd_pagesize); - status =mount ("tmpfs" , tmpfs_loc,"tmpfs" ,0 ,"huge=always,size=4m" ); +snprintf (opts,sizeof (opts),"huge=always,size=%lu" , size); + status =mount ("tmpfs" , tmpfs_loc,"tmpfs" ,0 , opts);if (status)ksft_exit_fail_msg ("Unable to create a tmpfs for testing\n" );
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 855/1611 selftests/mm: free dynamically allocated PMD-sized buffers in split_huge_page_test
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Sayali Patil <[email protected]>
[ Upstream commit e5d3e1422e92d54e28e81fad8bfc7c1ecb41a353 ]
Dynamically allocated buffers of PMD size for file-backed THP operations (file_buf1 and file_buf2) were not freed on the success path and some failure paths. Since the function is called repeatedly in a loop for each split order, this can cause significant memory leaks.
On architectures with large PMD sizes, repeated leaks could exhaust system memory and trigger the OOM killer during test execution.
Ensure all allocated buffers are freed to maintain stable repeated test runs.
--- .../selftests/mm/split_huge_page_test.c | 22 ++++++++++++++----- 1 file changed, 16 insertions(+), 6 deletions(-)
tools/testing/selftests/mm/split_huge_page_test.c +16 -6
@@ -487,12 +487,15 @@ static void split_file_backed_thp(int order)unsigned long size =2 * pmd_pagesize;char opts[64 ];ssize_t num_written, num_read; -char *file_buf1, *file_buf2; +char *file_buf1 =NULL , *file_buf2 =NULL ;uint64_t pgoff_start =0 , pgoff_end =1024 ;int i;ksft_print_msg ("Please enable pr_debug in split_huge_pages_in_file() for more info.\n" ); +if (!tmpfs_loc) +ksft_exit_fail_msg ("mkdtemp failed\n" ); + file_buf1 = (char *)malloc (pmd_pagesize); file_buf2 = (char *)malloc (pmd_pagesize);
@@ -508,8 +511,10 @@ static void split_file_backed_thp(int order)snprintf (opts,sizeof (opts),"huge=always,size=%lu" , size); status =mount ("tmpfs" , tmpfs_loc,"tmpfs" ,0 , opts); -if (status) -ksft_exit_fail_msg ("Unable to create a tmpfs for testing\n" ); +if (status) { +ksft_print_msg ("Unable to create a tmpfs for testing\n" ); + goto out; + } status =snprintf (testfile,INPUT_MAX ,"%s/thp_file" , tmpfs_loc);if (status >=INPUT_MAX ) {
@@ -561,10 +566,13 @@ static void split_file_backed_thp(int order) status =umount (tmpfs_loc);if (status) { -rmdir (tmpfs_loc); -ksft_exit_fail_msg ("Unable to umount %s\n" , tmpfs_loc); +ksft_print_msg ("Unable to umount %s\n" , tmpfs_loc); + goto out; } +free (file_buf1); +free (file_buf2); + status =rmdir (tmpfs_loc);if (status)ksft_exit_fail_msg ("cannot remove tmp dir: %s\n" ,strerror (errno));
@@ -577,8 +585,10 @@ static void split_file_backed_thp(int order)close (fd); cleanup:umount (tmpfs_loc); -rmdir (tmpfs_loc); out: +free (file_buf1); +free (file_buf2); +rmdir (tmpfs_loc);ksft_exit_fail_msg ("Error occurred\n" ); }
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 856/1611 selftest/mm: register existing mapping with userfaultfd in hugetlb-mremap
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Sayali Patil <[email protected]>
[ Upstream commit 1df31d5ef58dc6bdf0f2a8b809152d835c60b28e ]
Previously, register_region_with_uffd() created a new anonymous mapping and overwrote the address supplied by the caller before registering the range with userfaultfd.
As a result, userfaultfd was applied to an unrelated anonymous mapping instead of the hugetlb region used by the test.
Remove the extra mmap() and register the caller-provided address range directly using UFFDIO_REGISTER_MODE_MISSING, so that faults are generated for the hugetlb mapping used by the test.
This ensures userfaultfd operates on the actual hugetlb test region and validates the expected fault handling.
Before patch:
running ./hugetlb-mremap
-------------------------
TAP version 13
1..1
Map haddr: Returned address is 0x7eaa40000000 Map daddr: Returned address is 0x7daa40000000 Map vaddr: Returned address is 0x7faa40000000 Address returned by mmap() = 0x7fff9d000000
Mremap: Returned address is 0x7faa40000000 First hex is 0
First hex is 3020100
ok 1 Read same data
Totals: pass:1 fail:0 xfail:0 xpass:0 skip:0 error:0 [PASS]
ok 1 hugetlb-mremap
After patch:
running ./hugetb-mremap
-------------------------
TAP version 13
1..1
Map haddr: Returned address is 0x7eaa40000000
Map daddr: Returned address is 0x7daa40000000
Map vaddr: Returned address is 0x7faa40000000 Registered memory at address 0x7eaa40000000 with userfaultfd
Mremap: Returned address is 0x7faa40000000
First hex is 0
First hex is 3020100
ok 1 Read same data
Totals: pass:1 fail:0 xfail:0 xpass:0 skip:0 error:0 [PASS]
ok 1 hugetlb-mremap
--- tools/testing/selftests/mm/hugepage-mremap.c | 21 +++++--------------- 1 file changed, 5 insertions(+), 16 deletions(-)
tools/testing/selftests/mm/hugepage-mremap.c +5 -16
@@ -85,25 +85,14 @@ static void register_region_with_uffd(char *addr, size_t len)if (ioctl (uffd,UFFDIO_API , &uffdio_api) ==-1 )ksft_exit_fail_msg ("ioctl-UFFDIO_API: %s\n" ,strerror (errno)); -/* Create a private anonymous mapping. The memory will be -* demand-zero paged--that is, not yet allocated. When we -* actually touch the memory, it will be allocated via -* the userfaultfd. -*/ - - addr =mmap (NULL , len,PROT_READ |PROT_WRITE , -MAP_PRIVATE |MAP_ANONYMOUS ,-1 ,0 ); -if (addr ==MAP_FAILED ) -ksft_exit_fail_msg ("mmap: %s\n" ,strerror (errno)); - -ksft_print_msg ("Address returned by mmap() = %p\n" , addr); - -/* Register the memory range of the mapping we just created for -* handling by the userfaultfd object. In mode, we request to track -* missing pages (i.e., pages that have not yet been faulted in). +/* Register the passed memory range for handling by the userfaultfd object. +* In mode, we request to track missing pages +* (i.e., pages that have not yet been faulted in). */ if (uffd_register (uffd, addr, len, true, false, false))ksft_exit_fail_msg ("ioctl-UFFDIO_REGISTER: %s\n" ,strerror (errno)); + +ksft_print_msg ("Registered memory at address %p with userfaultfd\n" , addr); }int main (int argc,char *argv[])
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 857/1611 selftests/mm: ensure destination is hugetlb-backed in hugetlb-mremap
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Sayali Patil <[email protected]>
[ Upstream commit f20ca8972e83f111c4300c60d74314568c8964bc ]
The hugetlb-mremap selftest reserves the destination address using a anonymous base-page mapping before calling mremap() with MREMAP_FIXED, while the source region is hugetlb-backed.
When remapping a hugetlb mapping into a base-page VMA may fail with:
mremap: Device or resource busy
This is observed on powerpc hash MMU systems where slice constraints and page size incompatibilities prevent the remap.
Ensure the destination region is created using MAP_HUGETLB so that both source and destination VMAs are hugetlb-backed and compatible.
Update the FLAGS macro to include MAP_HUGETLB | MAP_SHARED so that both mappings are hugetlb-backed and compatible. Also use the macro for the mmap() calls to avoid repeating the flag combination.
This ensures the test reliably exercises hugetlb mremap instead of failing due to VMA type mismatch.
--- tools/testing/selftests/mm/hugepage-mremap.c | 11 ++++------- 1 file changed, 4 insertions(+), 7 deletions(-)
tools/testing/selftests/mm/hugepage-mremap.c +4 -7
@@ -31,7 +31,7 @@#define MB_TO_BYTES (x) (x * 1024 * 1024)#define PROTECTION (PROT_READ | PROT_WRITE | PROT_EXEC) -#define FLAGS (MAP_SHARED | MAP_ANONYMOUS) +#define FLAGS (MAP_HUGETLB | MAP_SHARED)static void check_bytes (char *addr) {
@@ -121,23 +121,20 @@ int main(int argc, char *argv[])/* mmap to a PUD aligned address to hopefully trigger pmd sharing. */ unsigned long suggested_addr =0x7eaa40000000 ; -void *haddr =mmap ((void *)suggested_addr, length,PROTECTION , -MAP_HUGETLB |MAP_SHARED |MAP_POPULATE , fd,0 ); +void *haddr =mmap ((void *)suggested_addr, length,PROTECTION ,FLAGS , fd,0 );ksft_print_msg ("Map haddr: Returned address is %p\n" , haddr);if (haddr ==MAP_FAILED )ksft_exit_fail_msg ("mmap1: %s\n" ,strerror (errno));/* mmap again to a dummy address to hopefully trigger pmd sharing. */ suggested_addr =0x7daa40000000 ; -void *daddr =mmap ((void *)suggested_addr, length,PROTECTION , -MAP_HUGETLB |MAP_SHARED |MAP_POPULATE , fd,0 ); +void *daddr =mmap ((void *)suggested_addr, length,PROTECTION ,FLAGS , fd,0 );ksft_print_msg ("Map daddr: Returned address is %p\n" , daddr);if (daddr ==MAP_FAILED )ksft_exit_fail_msg ("mmap3: %s\n" ,strerror (errno)); suggested_addr =0x7faa40000000 ; -void *vaddr = -mmap ((void *)suggested_addr, length,PROTECTION ,FLAGS ,-1 ,0 ); +void *vaddr =mmap ((void *)suggested_addr, length,PROTECTION ,FLAGS , fd,0 );ksft_print_msg ("Map vaddr: Returned address is %p\n" , vaddr);if (vaddr ==MAP_FAILED )ksft_exit_fail_msg ("mmap2: %s\n" ,strerror (errno));
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 858/1611 selftests/mm: skip uffd-stress test when nr_pages_per_cpu is zero
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Sayali Patil <[email protected]>
[ Upstream commit f3bd00507f226a419125df6064632bcbd47d8e70 ]
uffd-stress currently fails when the computed nr_pages_per_cpu evaluates to zero:
nr_pages_per_cpu = bytes / page_size / nr_parallel
This can occur on systems with large hugepage sizes (e.g. 1GB) and a high number of CPUs, where the total allocated memory is sufficient overall but not enough to provide at least one page per cpu.
In such cases, the failure is due to insufficient test resources rather than incorrect kernel behaviour. Update the test to treat this condition as a test skip instead of reporting an error.
--- tools/testing/selftests/mm/uffd-stress.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-)
tools/testing/selftests/mm/uffd-stress.c +2 -3
@@ -491,9 +491,8 @@ int main(int argc, char **argv) gopts->nr_pages_per_cpu = bytes / gopts->page_size / gopts->nr_parallel;if (!gopts->nr_pages_per_cpu) { -_err ("pages_per_cpu = 0, cannot test (%lu / %lu / %lu)" , - bytes, gopts->page_size, gopts->nr_parallel); -usage (); +ksft_exit_skip ("pages_per_cpu = 0, cannot test (%zu / %lu / %lu)\n" , + bytes, gopts->page_size, gopts->nr_parallel); } bounces =atoi (argv[3 ]);
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 859/1611 selftests/mm: clarify alternate unmapping in compaction_test
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Sayali Patil <[email protected]>
[ Upstream commit 69ba1d76d93ab818245333cf400928477ba72053 ]
Add a comment explaining that every other entry in the list is unmapped to intentionally create fragmentation with locked pages before invoking check_compaction().
--- tools/testing/selftests/mm/compaction_test.c | 3 +++ 1 file changed, 3 insertions(+)
tools/testing/selftests/mm/compaction_test.c +3 -0
@@ -261,6 +261,9 @@ int main(int argc, char **argv) mem_fragmentable_MB -=MAP_SIZE_MB ; } +/* Unmap every other entry in the list to create fragmentation with +* locked pages before invoking check_compaction(). +*/ for (entry = list; entry !=NULL ; entry = entry->next) {munmap (entry->map,MAP_SIZE );if (!entry->next)
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 860/1611 selftests/mm: allow PUD-level entries in compound testcase of hmm tests
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Sayali Patil <[email protected]>
[ Upstream commit 224ed0e019b122d08580362abe57574a78f2b5fa ]
Patch series "selftests/mm: assorted fixes for hmm-tests", v3.
This series fixes a few issues in hmm-tests that show up when page-size and huge-page configuration differ from the hardcoded assumptions the tests were written for (PMD/THP sizing, default hugepage size, and related cases).
It also includes a fix to exclusive_cow: the test ignored the return value of fork(), so both parent and child ran the same teardown path.
This patch (of 3):
The HMM compound testcase currently assumes only PMD-level mappings and fails on systems where default_hugepagesz=1G is set, because the region is then reported by the device at PUD level.
Determine the mapping level (PMD or PUD) the device reports for the first page of the range and require every page to match that level exactly via ASSERT_EQ(). This accepts PUD-level mappings while preserving the expected/observed protection values printed on failure, and rejects a fragmented mapping that mixes PMD- and PUD-level entries within the same range (which a per-page OR check would have let pass).
--- tools/testing/selftests/mm/hmm-tests.c | 32 +++++++++++++++++++------- 1 file changed, 24 insertions(+), 8 deletions(-)
tools/testing/selftests/mm/hmm-tests.c +24 -8
@@ -1612,8 +1612,8 @@ TEST_F(hmm2, snapshot) }/* -* Test the hmm_range_fault() HMM_PFN_PMD flag for large pages that -* should be mapped by a large page table entry. +* Test the hmm_range_fault() handling of large pages (PMD or PUD) +* that should be mapped by a large page table entry. */ TEST_F(hmm, compound) {
@@ -1623,6 +1623,7 @@ TEST_F(hmm, compound)unsigned long default_hsize;int *ptr;unsigned char *m; +unsigned char prot;int ret;unsigned long i;
@@ -1661,11 +1662,20 @@ TEST_F(hmm, compound)ASSERT_EQ (ret,0 );ASSERT_EQ (buffer->cpages, npages); -/* Check what the device saw. */ +/* +* Check what the device saw. The region is backed by a single huge +* page that the device reports either at PMD or at PUD level depending +* on the configured default hugepage size. Determine that level from +* the first page and require every page in the range to match it +* exactly, so that a fragmented mapping mixing levels (or a missing +* large-page bit) is still caught and reported with its actual value. +*/ m = buffer->mirror; + prot =HMM_DMIRROR_PROT_WRITE | + ((m[0 ] &HMM_DMIRROR_PROT_PUD ) ?HMM_DMIRROR_PROT_PUD : +HMM_DMIRROR_PROT_PMD );for (i =0 ; i < npages; ++i) -ASSERT_EQ (m[i],HMM_DMIRROR_PROT_WRITE | -HMM_DMIRROR_PROT_PMD ); +ASSERT_EQ (m[i], prot);/* Make the region read-only. */ ret =mprotect (buffer->ptr, size,PROT_READ );
@@ -1676,11 +1686,17 @@ TEST_F(hmm, compound)ASSERT_EQ (ret,0 );ASSERT_EQ (buffer->cpages, npages); -/* Check what the device saw. */ +/* +* Check what the device saw after mprotect(PROT_READ). Same +* approach as above: determine the mapping level from the first +* page and require every page to match it exactly. +*/ m = buffer->mirror; + prot =HMM_DMIRROR_PROT_READ | + ((m[0 ] &HMM_DMIRROR_PROT_PUD ) ?HMM_DMIRROR_PROT_PUD : +HMM_DMIRROR_PROT_PMD );for (i =0 ; i < npages; ++i) -ASSERT_EQ (m[i],HMM_DMIRROR_PROT_READ | -HMM_DMIRROR_PROT_PMD ); +ASSERT_EQ (m[i], prot);munmap (buffer->ptr, buffer->size); buffer->ptr =NULL ;
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 861/1611 selftests/mm: fix exclusive_cow test fork() handling
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Aboorva Devarajan <[email protected]>
[ Upstream commit cea5702144615878600d3a39b5d8b3cc34719012 ]
The test ignores the return value of fork(), so both the parent and the (newly created) child run the COW verification loops and then call hmm_buffer_free() before returning into the kselftest harness, which _exit()s each side. This duplicated teardown sequence has been observed to manifest as a SIGSEGV in the test child, e.g.:
hmm-tests[360141]: segfault (11) at 0 nip 10006964 lr 1000ac3c code 1 in hmm-tests[6964,10000000+30000]
Fix this by adopting the same fork()-then-wait pattern already used by the nearby anon_write_child / anon_write_child_shared tests in this file: the child performs the COW verification and then _exit(0)s so it does not run the test teardown, while the parent independently verifies COW, waits for the child, and only then frees the buffer.
--- tools/testing/selftests/mm/hmm-tests.c | 31 +++++++++++++++++++++++--- 1 file changed, 28 insertions(+), 3 deletions(-)
tools/testing/selftests/mm/hmm-tests.c +28 -3
@@ -1896,6 +1896,8 @@ TEST_F(hmm, exclusive_cow)unsigned long i;int *ptr;int ret; +pid_t pid; +int status; npages =ALIGN (HMM_BUFFER_SIZE , self->page_size) >> self->page_shift;ASSERT_NE (npages,0 );
@@ -1924,14 +1926,37 @@ TEST_F(hmm, exclusive_cow)ASSERT_EQ (ret,0 );ASSERT_EQ (buffer->cpages, npages); -fork (); + pid =fork (); +if (pid ==-1 ) +ASSERT_EQ (pid,0 ); -/* Fault pages back to system memory and check them. */ +if (pid ==0 ) { +/* +* Child verifies COW independently, then _exit(0)s so it does +* not run the test teardown. A failed ASSERT_* here makes the +* harness abort() the child, so the parent sees +* !WIFEXITED(status) below and fails in turn. +*/ +for (i =0 , ptr = buffer->ptr; i < size /sizeof (*ptr); ++i) +ASSERT_EQ (ptr[i]++, i); + +for (i =0 , ptr = buffer->ptr; i < size /sizeof (*ptr); ++i) +ASSERT_EQ (ptr[i], i +1 ); + +_exit (0 ); + } + +/* Parent: also increment to verify COW works for both processes. */ for (i =0 , ptr = buffer->ptr; i < size /sizeof (*ptr); ++i)ASSERT_EQ (ptr[i]++, i);for (i =0 , ptr = buffer->ptr; i < size /sizeof (*ptr); ++i) -ASSERT_EQ (ptr[i], i+1 ); +ASSERT_EQ (ptr[i], i +1 ); + +/* Parent: wait for child and then free the buffer. */ +ASSERT_EQ (waitpid (pid, &status,0 ), pid); +ASSERT_TRUE (WIFEXITED (status)); +ASSERT_EQ (WEXITSTATUS (status),0 );hmm_buffer_free (buffer); }
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 862/1611 net: marvell: prestera: initialize err in prestera_port_sfp_bind
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Ruoyu Wang <[email protected]>
[ Upstream commit 62b01f72d93c7bc8fde3b2e5b5f783eca5f53324 ]
prestera_port_sfp_bind() returns err after walking the ports node. If no child node matches the port's front-panel id, err is never assigned.
Initialize err to 0 because absence of a matching optional port device tree node is not an error. In that case no phylink is created and port creation should continue with port->phy_link left NULL. Errors from malformed matched nodes and phylink_create() still propagate.
--- drivers/net/ethernet/marvell/prestera/prestera_main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/net/ethernet/marvell/prestera/prestera_main.c +1 -1
@@ -373,7 +373,7 @@ static int prestera_port_sfp_bind(struct prestera_port *port)struct device_node *ports, *node;struct fwnode_handle *fwnode;struct phylink *phy_link; -int err; +int err =0 ;if (!sw->np)return 0 ;
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 863/1611 tipc: fix use-after-free of the discoverer in tipc_disc_rcv()
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Weiming Shi <[email protected]>
[ Upstream commit 1579342d71133da7f00daa02c75cebec7372097b ]
bearer_disable() frees b->disc with tipc_disc_delete()'s plain kfree(), but tipc_disc_rcv() still dereferences b->disc in RX softirq under rcu_read_lock() (tipc_udp_recv -> tipc_rcv -> tipc_disc_rcv).
L2 bearers are safe thanks to the synchronize_net() in tipc_disable_l2_media(), but the UDP bearer defers that call to the cleanup_bearer() workqueue, so the discoverer is freed with no grace period:
BUG: KASAN: slab-use-after-free in tipc_disc_rcv (net/tipc/discover.c:149) Read of size 8 at addr ffff88802348b728 by task poc_tipc/184 <IRQ> tipc_disc_rcv (net/tipc/discover.c:149) tipc_rcv (net/tipc/node.c:2126) tipc_udp_recv (net/tipc/udp_media.c:391) udp_rcv (net/ipv4/udp.c:2643) ip_local_deliver_finish (net/ipv4/ip_input.c:241) </IRQ> Freed by task 181: kfree (mm/slub.c:6565) bearer_disable (net/tipc/bearer.c:418) tipc_nl_bearer_disable (net/tipc/bearer.c:1001)
The bearer is freed with kfree_rcu(); free the discoverer the same way. Add an rcu_head to struct tipc_discoverer and free it and its skb from an RCU callback.
Because the RCU callback (tipc_disc_free_rcu) lives in module text, a call_rcu() that is still pending when the tipc module is unloaded would invoke a freed function. Add an rcu_barrier() to tipc_exit() after the bearer subsystem has been torn down, so all pending discoverer callbacks have run before the module text goes away.
Reachable from an unprivileged user namespace: the TIPCv2 genl family is netnsok and its bearer commands have no GENL_ADMIN_PERM. Needs CONFIG_TIPC and CONFIG_TIPC_MEDIA_UDP.
--- net/tipc/core.c | 5 +++++ net/tipc/discover.c | 14 ++++++++++++-- 2 files changed, 17 insertions(+), 2 deletions(-)
net/tipc/core.c +5 -0
@@ -218,6 +218,11 @@ static void __exit tipc_exit(void)unregister_pernet_device (&tipc_net_ops);tipc_unregister_sysctl (); +/* TODO: Wait for all timers that called call_rcu() to finish before +* calling rcu_barrier(). +*/ +rcu_barrier (); +pr_info ("Deactivated\n" ); }
net/tipc/discover.c +12 -2
@@ -58,6 +58,7 @@* @skb: request message to be (repeatedly) sent * @timer: timer governing period between requests * @timer_intv: current interval between requests (in ms) +* @rcu: RCU head for deferred freeing */ struct tipc_discoverer {u32 bearer_id;
@@ -69,6 +70,7 @@ struct tipc_discoverer {struct sk_buff *skb;struct timer_list timer;unsigned long timer_intv; +struct rcu_head rcu; };/**
@@ -382,6 +384,15 @@ int tipc_disc_create(struct net *net, struct tipc_bearer *b,return 0 ; } +static void tipc_disc_free_rcu (struct rcu_head *rp) +{ + struct tipc_discoverer *d = container_of(rp, struct tipc_discoverer, + rcu); + +kfree_skb (d->skb); +kfree (d); +} +/** * tipc_disc_delete - destroy object sending periodic link setup requests * @d: ptr to link dest structure
@@ -389,8 +400,7 @@ int tipc_disc_create(struct net *net, struct tipc_bearer *b,void tipc_disc_delete (struct tipc_discoverer *d) {timer_shutdown_sync (&d->timer); -kfree_skb (d->skb); -kfree (d); +call_rcu (&d->rcu, tipc_disc_free_rcu); }/**
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 864/1611 net: ethernet: mtk_ppe: Fix rhashtable leak in mtk_ppe_init error paths
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Wayen Yan <[email protected]>
[ Upstream commit 41782770be567abc6509169d0ffdada31c783a66 ]
In mtk_ppe_init(), when accounting is enabled, the error paths for dmam_alloc_coherent(mib) and devm_kzalloc(acct) failures return NULL directly, bypassing the err_free_l2_flows label that destroys the rhashtable initialized earlier.
While this leak only occurs during probe (not runtime) and the leaked memory is minimal (an empty rhash table), fixing it ensures proper error path cleanup consistency.
Fix by changing the two return NULL statements to goto err_free_l2_flows.
--- drivers/net/ethernet/mediatek/mtk_ppe.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
drivers/net/ethernet/mediatek/mtk_ppe.c +2 -2
@@ -918,7 +918,7 @@ struct mtk_ppe *mtk_ppe_init(struct mtk_eth *eth, void __iomem *base, int index) mib =dmam_alloc_coherent (ppe->dev,MTK_PPE_ENTRIES *sizeof (*mib), &ppe->mib_phys,GFP_KERNEL );if (!mib) -return NULL ; + goto err_free_l2_flows; ppe->mib_table = mib;
@@ -926,7 +926,7 @@ struct mtk_ppe *mtk_ppe_init(struct mtk_eth *eth, void __iomem *base, int index) GFP_KERNEL);if (!acct) -return NULL ; + goto err_free_l2_flows; ppe->acct_table = acct; }
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 865/1611 octeontx2-af: mcs: Fix unsupported secy stats read
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Geetha sowjanya <[email protected]>
[ Upstream commit d4b7440f7316e76f013f57d8b6da069a1b9c34e7 ]
Secy control stats counter doesn't exist for CNF10KB platform. Skip reading this respective register for CNF10KB silicon while fetching secy stats.
--- drivers/net/ethernet/marvell/octeontx2/af/mcs.c | 6 +++--- drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c | 3 ++- 2 files changed, 5 insertions(+), 4 deletions(-)
drivers/net/ethernet/marvell/octeontx2/af/mcs.c +3 -3
@@ -120,13 +120,13 @@ void mcs_get_rx_secy_stats(struct mcs *mcs, struct mcs_secy_stats *stats, int id reg =MCSX_CSE_RX_MEM_SLAVE_INPKTSSECYUNTAGGEDX (id); stats->pkt_untaged_cnt =mcs_reg_read (mcs, reg); - reg =MCSX_CSE_RX_MEM_SLAVE_INPKTSSECYCTLX (id); - stats->pkt_ctl_cnt =mcs_reg_read (mcs, reg); -if (mcs->hw->mcs_blks >1 ) { reg =MCSX_CSE_RX_MEM_SLAVE_INPKTSSECYNOTAGX (id); stats->pkt_notag_cnt =mcs_reg_read (mcs, reg); +return ; } + reg =MCSX_CSE_RX_MEM_SLAVE_INPKTSSECYCTLX (id); + stats->pkt_ctl_cnt =mcs_reg_read (mcs, reg); } void mcs_get_flowid_stats(struct mcs *mcs, struct mcs_flowid_stats *stats,
drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c +2 -1
@@ -478,10 +478,11 @@ static int rvu_dbg_mcs_rx_secy_stats_display(struct seq_file *filp, void *unusedseq_printf (filp,"secy%d: Tagged ctrl pkts: %lld\n" , secy_id, stats.pkt_tagged_ctl_cnt);seq_printf (filp,"secy%d: Untaged pkts: %lld\n" , secy_id, stats.pkt_untaged_cnt); -seq_printf (filp,"secy%d: Ctrl pkts: %lld\n" , secy_id, stats.pkt_ctl_cnt);if (mcs->hw->mcs_blks >1 )seq_printf (filp,"secy%d: pkts notag: %lld\n" , secy_id, stats.pkt_notag_cnt); +else +seq_printf (filp,"secy%d: Ctrl pkts: %lld\n" , secy_id, stats.pkt_ctl_cnt); }mutex_unlock (&mcs->stats_lock);return 0 ;
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 866/1611 octeontx2-pf: Clear stats of all resources when freeing resources
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Subbaraya Sundeep <[email protected]>
[ Upstream commit fd4460721fb4062ef470ecdfdaedadfe7e415c09 ]
When all MCS resources mapped to a PF are being freed then clear stats of all those resources too.
--- drivers/net/ethernet/marvell/octeontx2/nic/cn10k_macsec.c | 1 + 1 file changed, 1 insertion(+)
drivers/net/ethernet/marvell/octeontx2/nic/cn10k_macsec.c +1 -0
@@ -211,6 +211,7 @@ static void cn10k_mcs_free_rsrc(struct otx2_nic *pfvf, enum mcs_direction dir, clear_req->id = hw_rsrc_id; clear_req->type = type; clear_req->dir = dir; + clear_req->all = all; req =otx2_mbox_alloc_msg_mcs_free_resources (mbox);if (!req)
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 867/1611 octeontx2-pf: mcs: Fix mcs resources free on PF shutdown
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Geetha sowjanya <[email protected]>
[ Upstream commit 450d0e90b10393bd9f50c127875a9fdd4cc81c30 ]
On PF shutdown, the current driver free mcs hardware resources though mcs resources are not allocated to it. This patch checks the mcs resources status and if resources are allocated then only sends mailbox message to free them.
--- .../net/ethernet/marvell/octeontx2/nic/cn10k_macsec.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-)
drivers/net/ethernet/marvell/octeontx2/nic/cn10k_macsec.c +7 -2
@@ -1806,11 +1806,16 @@ int cn10k_mcs_init(struct otx2_nic *pfvf)void cn10k_mcs_free (struct otx2_nic *pfvf) { +struct cn10k_mcs_cfg *cfg = pfvf->macsec_cfg; +if (!test_bit (CN10K_HW_MACSEC , &pfvf->hw.cap_flag))return ; -cn10k_mcs_free_rsrc (pfvf,MCS_TX ,MCS_RSRC_TYPE_SECY ,0 , true); -cn10k_mcs_free_rsrc (pfvf,MCS_RX ,MCS_RSRC_TYPE_SECY ,0 , true); +if (!list_empty (&cfg->txsc_list)) { +cn10k_mcs_free_rsrc (pfvf,MCS_TX ,MCS_RSRC_TYPE_SECY ,0 , true); +cn10k_mcs_free_rsrc (pfvf,MCS_RX ,MCS_RSRC_TYPE_SECY ,0 , true); + } +kfree (pfvf->macsec_cfg); pfvf->macsec_cfg =NULL ; }
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 868/1611 net: emac: Fix NULL pointer dereference in emac_probe
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Rosen Penev <[email protected]>
[ Upstream commit f623d38fe6c4e8c40b23f42cc6fe6963fa49997b ]
Move devm_request_irq() after devm_platform_ioremap_resource() so that dev->emacp is mapped before the interrupt handler can fire. An early interrupt hitting emac_irq() would dereference the NULL dev->emacp and crash.
Also remove redundant error message. devm_platform_ioremap_resource() already returns an error message with dev_err_probe().
--- drivers/net/ethernet/ibm/emac/core.c | 13 ++++++------- 1 file changed, 6 insertions(+), 7 deletions(-)
drivers/net/ethernet/ibm/emac/core.c +6 -7
@@ -3035,6 +3035,12 @@ static int emac_probe(struct platform_device *ofdev)if (err) goto err_gone; + dev->emacp =devm_platform_ioremap_resource (ofdev,0 ); +if (IS_ERR (dev->emacp)) { + err =PTR_ERR (dev->emacp); + goto err_gone; + } +/* Setup error IRQ handler */ dev->emac_irq =platform_get_irq (ofdev,0 ); err = devm_request_irq(&ofdev->dev, dev->emac_irq, emac_irq, 0, "EMAC",
@@ -3047,13 +3053,6 @@ static int emac_probe(struct platform_device *ofdev) ndev->irq = dev->emac_irq; - dev->emacp =devm_platform_ioremap_resource (ofdev,0 ); -if (IS_ERR (dev->emacp)) { -dev_err (&ofdev->dev,"can't map device registers" ); - err =PTR_ERR (dev->emacp); - goto err_gone; - } -/* Wait for dependent devices */ err =emac_wait_deps (dev);if (err)
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 869/1611 net/sched: act_ct: fix nf_connlabels leak on two error paths
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Michael Bommarito <[email protected]>
[ Upstream commit 16e088016f38cf728a0de709c3335cc5a3850476 ]
tcf_ct_fill_params() calls nf_connlabels_get() (setting put_labels) when TCA_CT_LABELS is present, but two later error sites use a bare return instead of "goto err", skipping the err: nf_connlabels_put() cleanup. They also precede the "p->put_labels = put_labels" assignment, so the tcf_ct_params_free() fallback does not release the count either. Each failed RTM_NEWACTION on these paths leaks one nf_connlabels reference:net->ct.labels_used is incremented and never released. The action is reachable with CAP_NET_ADMIN over the netns, i.e. from an unprivileged user namespace on default-userns kernels.
Impact: an unprivileged user with CAP_NET_ADMIN over a network namespace (e.g. via user namespaces) leaks one nf_connlabels reference per failed RTM_NEWACTION on the two error paths; net->ct.labels_used is never released.
The err: label is safe to reach from both sites: p->tmpl is still NULL there (kzalloc'd, not yet assigned) and nf_ct_put(NULL) is a no-op, so no inline release is needed.
--- net/sched/act_ct.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-)
net/sched/act_ct.c +4 -2
@@ -1293,7 +1293,8 @@ static int tcf_ct_fill_params(struct net *net,if (tb[TCA_CT_ZONE ]) {if (!IS_ENABLED (CONFIG_NF_CONNTRACK_ZONES )) {NL_SET_ERR_MSG_MOD (extack,"Conntrack zones isn't enabled." ); -return -EOPNOTSUPP ; + err = -EOPNOTSUPP ; + goto err; } tcf_ct_set_key_val(tb,
@@ -1306,7 +1307,8 @@ static int tcf_ct_fill_params(struct net *net, tmpl =nf_ct_tmpl_alloc (net, &zone,GFP_KERNEL );if (!tmpl) {NL_SET_ERR_MSG_MOD (extack,"Failed to allocate conntrack template" ); -return -ENOMEM ; + err = -ENOMEM ; + goto err; } p->tmpl = tmpl;if (tb[TCA_CT_HELPER_NAME ]) {
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 870/1611 net: airoha: Fix skb->priority underflow in airoha_dev_select_queue()
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Wayen Yan <[email protected]>
[ Upstream commit 86e51aa24686cc95bb35613059e8b94b9b81e3f0 ]
In airoha_dev_select_queue(), the expression:
queue = (skb->priority - 1) % AIROHA_NUM_QOS_QUEUES;
implicitly converts to unsigned arithmetic: when skb->priority is 0 (the default for unclassified traffic), (0u - 1u) wraps to UINT_MAX, and UINT_MAX % 8 = 7, routing default best-effort packets to the highest-priority QoS queue. This causes QoS inversion where the majority of traffic on a PON gateway starves actual high-priority flows (VoIP, gaming, etc.).
The "- 1" offset was a leftover from the ETS offload implementation that has since been removed. The correct mapping is a direct modulo:
queue = skb->priority % AIROHA_NUM_QOS_QUEUES;
This maps priority 0 → queue 0 (lowest), priority 7 → queue 7 (highest), with higher priorities wrapping around. This is the standard Linux sk_prio → HW queue mapping used by other drivers.
--- drivers/net/ethernet/airoha/airoha_eth.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/net/ethernet/airoha/airoha_eth.c +1 -1
@@ -1937,7 +1937,7 @@ static u16 airoha_dev_select_queue(struct net_device *dev, struct sk_buff *skb,*/ channel =netdev_uses_dsa (dev) ?skb_get_queue_mapping (skb) : port->id; channel = channel %AIROHA_NUM_QOS_CHANNELS ; - queue = (skb->priority -1 ) %AIROHA_NUM_QOS_QUEUES ;/* QoS queue */ + queue = skb->priority %AIROHA_NUM_QOS_QUEUES ; queue = channel *AIROHA_NUM_QOS_QUEUES + queue;return queue < dev->num_tx_queues ? queue :0 ;
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 871/1611 ipv6: ndisc: fix NULL deref in accept_untracked_na()
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Weiming Shi <[email protected]>
[ Upstream commit d186e942365acece7c56d39da05dd63bf95b280a ]
accept_untracked_na() re-fetches the inet6_dev with __in6_dev_get(dev) and dereferences idev->cnf.accept_untracked_na without a NULL check, even though its only caller ndisc_recv_na() already fetched and NULL-checked idev for the same device.
Both reads of dev->ip6_ptr run in the same RCU read-side critical section, but a concurrent addrconf_ifdown() can clear dev->ip6_ptr between them: lowering the MTU below IPV6_MIN_MTU calls addrconf_ifdown() without the synchronize_net() that orders the unregister path, so the re-fetch returns NULL and oopses:
BUG: KASAN: null-ptr-deref in ndisc_recv_na (net/ipv6/ndisc.c:974) Read of size 4 at addr 0000000000000364 Call Trace: <IRQ> ndisc_recv_na (net/ipv6/ndisc.c:974) icmpv6_rcv (net/ipv6/icmp.c:1193) ip6_protocol_deliver_rcu (net/ipv6/ip6_input.c:479) ip6_input_finish (net/ipv6/ip6_input.c:534) ip6_input (net/ipv6/ip6_input.c:545) ip6_mc_input (net/ipv6/ip6_input.c:635) ipv6_rcv (net/ipv6/ip6_input.c:351) </IRQ>
It is reachable by an unprivileged user via a network namespace.
Pass the caller's already validated idev instead of re-fetching it; the idev stays alive for the whole RCU critical section, so it is safe even after dev->ip6_ptr has been cleared.
--- net/ipv6/ndisc.c | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-)
net/ipv6/ndisc.c +3 -5
@@ -966,10 +966,8 @@ static enum skb_drop_reason ndisc_recv_ns(struct sk_buff *skb)return reason; } -static int accept_untracked_na (struct net_device *dev,struct in6_addr *saddr) +static int accept_untracked_na (struct inet6_dev *idev,struct in6_addr *saddr) { -struct inet6_dev *idev =__in6_dev_get (dev); -switch (READ_ONCE (idev->cnf.accept_untracked_na)) {case 0 :/* Don't accept untracked na (absent in neighbor cache) */ return 0 ;
@@ -979,7 +977,7 @@ static int accept_untracked_na(struct net_device *dev, struct in6_addr *saddr)* same subnet as an address configured on the interface that * received the na */ -return !!ipv6_chk_prefix (saddr, dev); +return !!ipv6_chk_prefix (saddr, idev->dev);default :return 0 ; }
@@ -1077,7 +1075,7 @@ static enum skb_drop_reason ndisc_recv_na(struct sk_buff *skb)*/ new_state = msg->icmph.icmp6_solicited ?NUD_REACHABLE :NUD_STALE ;if (!neigh && lladdr && idev &&READ_ONCE (idev->cnf.forwarding)) { -if (accept_untracked_na (dev, saddr)) { +if (accept_untracked_na (idev, saddr)) { neigh =neigh_create (&nd_tbl, &msg->target, dev); new_state =NUD_STALE ; }
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 872/1611 ipv6: ioam: fix type confusion of dst_entry
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Jiayuan Chen <[email protected]>
[ Upstream commit 9ed19e11d2146076d117d51a940643990118449b ]
IOAM uses a dummy dst_entry(null_dst) to mark that the destination should not be changed after the transformation. This dst is stored in the IOAM lwt state and may be passed to dst_cache_set_ip6().
However, the IPv6 dst cache path eventually calls rt6_get_cookie(), which treats the dst_entry as part of a struct rt6_info. Since the null_dst was embedded directly as a struct dst_entry in struct ioam6_lwt, this resulted in an invalid cast and rt6_get_cookie() reading fields from the wrong object.
In practice, the wrong cookie is not used while dst->obsolete is zero, but rt6_get_cookie() may also access per-cpu value when rt->sernum is zero. In this case, rt->sernum aliases ioam6_lwt::cache::reset_ts, which can become zero, making this a potential invalid pointer access.
Fix this by embedding a full struct rt6_info for the dummy IPv6 route and passing its dst member to the dst APIs.
--- net/ipv6/ioam6_iptunnel.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-)
net/ipv6/ioam6_iptunnel.c +4 -4
@@ -35,7 +35,7 @@ struct ioam6_lwt_freq { };struct ioam6_lwt { -struct dst_entry null_dst; +struct rt6_info null_rt;struct dst_cache cache;struct ioam6_lwt_freq freq;atomic_t pkt_cnt;
@@ -176,7 +176,7 @@ static int ioam6_build_state(struct net *net, struct nlattr *nla,* it is stored in the cache. Then, +1/-1 each time we read the cache * and release it. Long story short, we're fine. */ -dst_init (&ilwt->null_dst,NULL ,NULL ,DST_OBSOLETE_NONE ,DST_NOCOUNT ); +dst_init (&ilwt->null_rt.dst,NULL ,NULL ,DST_OBSOLETE_NONE ,DST_NOCOUNT );atomic_set (&ilwt->pkt_cnt,0 ); ilwt->freq.k = freq_k;
@@ -360,7 +360,7 @@ static int ioam6_output(struct net *net, struct sock *sk, struct sk_buff *skb)/* This is how we notify that the destination does not change after * transformation and that we need to use orig_dst instead of the cache */ -if (dst == &ilwt->null_dst) { +if (dst == &ilwt->null_rt.dst) {dst_release (dst); dst = orig_dst;
@@ -429,7 +429,7 @@ static int ioam6_output(struct net *net, struct sock *sk, struct sk_buff *skb)local_bh_disable ();if (orig_dst->lwtstate == dst->lwtstate)dst_cache_set_ip6 (&ilwt->cache, - &ilwt->null_dst, &fl6.saddr); + &ilwt->null_rt.dst, &fl6.saddr);else dst_cache_set_ip6 (&ilwt->cache, dst, &fl6.saddr);local_bh_enable ();
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 873/1611 dpaa2-switch: do not accept VLAN uppers while bridged
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Ioana Ciornei <[email protected]>
[ Upstream commit d07d80b6a129a44538cda1549b7acf95154fb197 ]
The dpaa2-switch driver does not support VLAN uppers while its ports are bridged. This scenario tried to be prevented by rejecting a bridge join while VLAN uppers exist but the reverse order was still possible.
This patches adds a check so that the dpaa2-switch also does not accept VLAN uppers while bridged.
--- drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c | 8 ++++++++ 1 file changed, 8 insertions(+)
drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c +8 -0
@@ -2198,6 +2198,7 @@ dpaa2_switch_prechangeupper_sanity_checks(struct net_device *netdev,static int dpaa2_switch_port_prechangeupper (struct net_device *netdev,struct netdev_notifier_changeupper_info *info) { +struct ethsw_port_priv *port_priv;struct netlink_ext_ack *extack;struct net_device *upper_dev;int err;
@@ -2216,6 +2217,13 @@ static int dpaa2_switch_port_prechangeupper(struct net_device *netdev,if (!info->linking)dpaa2_switch_port_pre_bridge_leave (netdev); + }else if (is_vlan_dev (upper_dev)) { + port_priv =netdev_priv (netdev); +if (port_priv->fdb->bridge_dev) { +NL_SET_ERR_MSG_MOD (extack, +"Cannot accept VLAN uppers while bridged" ); +return -EOPNOTSUPP ; + } }return 0 ;
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 874/1611 rtc: abx80x: fix the RTC_VL_CLR clearing all status flags
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Antoni Pokusinski <[email protected]>
[ Upstream commit 419719c514252a2dbb2e2976f564c83417dd6d0a ]
The RTC_VL_CLR ioctl intends to clear only the battery low flag (BLF), however the current implementation writes 0 to the status register, clearing all status bits.
Fix this by writing back the masked status value so that only BLF is cleared, preserving other status flags.
--- drivers/rtc/rtc-abx80x.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)
drivers/rtc/rtc-abx80x.c +2 -1
@@ -545,7 +545,8 @@ static int abx80x_ioctl(struct device *dev, unsigned int cmd, unsigned long arg) status &= ~ABX8XX_STATUS_BLF ; - tmp =i2c_smbus_write_byte_data (client,ABX8XX_REG_STATUS ,0 ); + tmp =i2c_smbus_write_byte_data (client,ABX8XX_REG_STATUS , + status);if (tmp <0 )return tmp;
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 875/1611 rtc: ds1307: handle oscillator stop flag for ds1337/ds1339/ds3231
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Ronan Dalton <[email protected]>
[ Upstream commit a091e1ba3b68cabc9caedafc6f81d9fe9b3b2200 ]
Prior to commit 48458654659c ("rtc: ds1307: remove clear of oscillator stop flag (OSF) in probe"), the oscillator stop flag (OSF) bit was checked during device probe for the ds1337, ds1339, ds1341, and ds3231 chips; if it was set, it would be cleared and a warning would be logged saying "SET TIME!". Since that commit, the OSF bit is no longer cleared, but the warning is still printed.
Directly following that commit, there was no way to get rid of this warning because nothing cleared the OSF bit on these chips.
The commit associated with the previous commit, 523923cfd5d6 ("rtc:
ds1307: handle oscillator stop flag (OSF) for ds1341"), made proper use of the OSF when getting and setting the time in the RTC. However, the other RTC variants ds1337, ds1339 and ds3231 didn't have a corresponding change made.
Given that the OSF bit is no longer cleared at probe time when it is set, the remaining three chips should have the same handling as the ds1341 chip has for the OSF bit.
Fix the issue on the ds1337, ds1339 and ds3231 chips by applying the same logic as the ds1341 has to these chips.
Note that any devices brought up between the first referenced commit and this one may begin mistrusting the time reported by the RTC until it is set again, if the bit was never explicitly cleared.
Note that only the ds1339 was tested with this change, but the datasheets for the other chips contain essentially identical descriptions of the OSF bit so the same change should work.
--- drivers/rtc/rtc-ds1307.c | 28 +++++++++++++++++----------- 1 file changed, 17 insertions(+), 11 deletions(-)
drivers/rtc/rtc-ds1307.c +17 -11
@@ -269,6 +269,16 @@ static int ds1307_get_time(struct device *dev, struct rtc_time *t)if (tmp &DS1338_BIT_OSF )return -EINVAL ;break ; +case ds_1337: +case ds_1339: +case ds_1341: +case ds_3231: + ret =regmap_read (ds1307->regmap,DS1337_REG_STATUS , &tmp); +if (ret) +return ret; +if (tmp &DS1337_BIT_OSF ) +return -EINVAL ; +break ;case ds_1340:if (tmp & DS1340_BIT_nEOSC)return -EINVAL ;
@@ -279,13 +289,6 @@ static int ds1307_get_time(struct device *dev, struct rtc_time *t)if (tmp &DS1340_BIT_OSF )return -EINVAL ;break ; -case ds_1341: - ret =regmap_read (ds1307->regmap,DS1337_REG_STATUS , &tmp); -if (ret) -return ret; -if (tmp &DS1337_BIT_OSF ) -return -EINVAL ; -break ;case ds_1388: ret =regmap_read (ds1307->regmap,DS1388_REG_FLAG , &tmp);if (ret)
@@ -380,14 +383,17 @@ static int ds1307_set_time(struct device *dev, struct rtc_time *t)regmap_update_bits (ds1307->regmap,DS1307_REG_CONTROL ,DS1338_BIT_OSF ,0 );break ; -case ds_1340: -regmap_update_bits (ds1307->regmap,DS1340_REG_FLAG , -DS1340_BIT_OSF ,0 ); -break ; +case ds_1337: +case ds_1339:case ds_1341: +case ds_3231:regmap_update_bits (ds1307->regmap,DS1337_REG_STATUS ,DS1337_BIT_OSF ,0 );break ; +case ds_1340: +regmap_update_bits (ds1307->regmap,DS1340_REG_FLAG , +DS1340_BIT_OSF ,0 ); +break ;case ds_1388:regmap_update_bits (ds1307->regmap,DS1388_REG_FLAG ,DS1388_BIT_OSF ,0 );
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 876/1611 bpf: Fix stack slot index in nospec checks
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Nuoqi Gui <[email protected]>
[ Upstream commit d1d53aa30ab3b5ae89161c9cc840b3f7489ad386 ]
check_stack_write_fixed_off() computes the byte slot for a fixed-offset stack write as -off - 1, and records each written byte in slot_type[] with (slot - i) % BPF_REG_SIZE.
The Spectre v4 sanitization pre-check uses slot_type[i] instead. For a 4-byte write at fp-8 after the lower half of fp-8 has been zeroed, the pre-check scans bytes 0..3 and sees STACK_ZERO while the actual write updates bytes 7..4. That can leave the second half-slot write without nospec_result even though the bytes being overwritten still require sanitization.
Use the same slot index in the sanitization pre-check that the write path uses when updating slot_type[].
--- kernel/bpf/verifier.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)
kernel/bpf/verifier.c +2 -1
@@ -5143,7 +5143,8 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env,bool sanitize = reg &&is_spillable_regtype (reg->type);for (i =0 ; i < size; i++) { -u8 type = state->stack[spi].slot_type[i]; +u8 type = state->stack[spi].slot_type[(slot - i) % +BPF_REG_SIZE ];if (type !=STACK_MISC && type !=STACK_ZERO ) { sanitize = true;
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 877/1611 bpftool: Fix vmlinux BTF leak in cgroup commands
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Yichong Chen <[email protected]>
[ Upstream commit bda6a7308ef8e79cfbb7d09e48e1c7ffaa522269 ]
bpftool cgroup show and tree call libbpf_find_kernel_btf() to resolve attach_btf names, but never release the returned BTF object.
For cgroup tree, do_show_tree_fn() is called once for each cgroup visited by nftw(). When more than one cgroup has attached programs, each callback overwrites btf_vmlinux with a new object and loses the previous allocation.
Load vmlinux BTF only once during a tree walk and release it when cgroup show or tree completes. Reset btf_vmlinux_id at the same time so batch mode starts with clean state.
--- tools/bpf/bpftool/cgroup.c | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-)
tools/bpf/bpftool/cgroup.c +13 -1
@@ -78,6 +78,13 @@ static unsigned int query_flags;static struct btf *btf_vmlinux;static __u32 btf_vmlinux_id; +static void free_btf_vmlinux (void ) +{ +btf__free (btf_vmlinux); + btf_vmlinux =NULL ; + btf_vmlinux_id =0 ; +} +static enum bpf_attach_type parse_attach_type (const char *str) {const char *attach_type_str;
@@ -388,6 +395,8 @@ static int do_show(int argc, char **argv)if (json_output)jsonw_end_array (json_wtr); +free_btf_vmlinux (); + exit_cgroup:close (cgroup_fd); exit:
@@ -437,7 +446,9 @@ static int do_show_tree_fn(const char *fpath, const struct stat *sb,printf ("%s\n" , fpath); } - btf_vmlinux =libbpf_find_kernel_btf (); +if (!btf_vmlinux) + btf_vmlinux =libbpf_find_kernel_btf (); +for (i =0 ; i <ARRAY_SIZE (cgroup_attach_types); i++)show_bpf_progs (cgroup_fd, cgroup_attach_types[i], ftw->level);
@@ -540,6 +551,7 @@ static int do_show_tree(int argc, char **argv)if (json_output)jsonw_end_array (json_wtr); +free_btf_vmlinux ();free (cgroup_alloced);return ret;
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 878/1611 bpf: zero-initialize the fib lookup flow struct
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Avinash Duduskar <[email protected]>
[ Upstream commit 0dfcb68a6a5ac517b22dff6a1f01cb4f126dfc57 ]
bpf_ipv4_fib_lookup() and bpf_ipv6_fib_lookup() build the flow key on the stack with a bare "struct flowi4 fl4;" / "struct flowi6 fl6;" and fill it field by field, but never set flowi4_l3mdev / flowi6_l3mdev.
On the non-DIRECT path the lookup goes through the fib rules whenever the netns has custom rules, which a VRF installs:
bpf_ipv4_fib_lookup() -> fib_lookup() -> __fib_lookup() -> l3mdev_update_flow() reads !fl->flowi_l3mdev -> fib_rules_lookup() -> fib_rule_match() -> l3mdev_fib_rule_match() uses fl->flowi_l3mdev
l3mdev_update_flow() resolves the l3mdev master from the ingress device only while the field is still zero. Left at a nonzero stack value the resolution is skipped, and l3mdev_fib_rule_match() then tests that value as an ifindex, so the VRF master is not resolved and the rule fails to
match: an ingress enslaved to a VRF can fail to select its table. FIB rules matching on an L3 master device (l3mdev_fib_rule_iif_match()/ _oif_match()) read the same value, so an "ip rule iif/oif <vrf>" mismatches the same way.
Zero-initialize the whole flow struct rather than adding one more field assignment, so any flowi field added later is covered too. ip_route_input_slow() likewise zeroes the field before its input lookup.
CONFIG_INIT_STACK_ALL_ZERO masks this by default, but it depends on compiler support (CC_HAS_AUTO_VAR_INIT_ZERO), so INIT_STACK_NONE builds, including older toolchains that fall back to it, are exposed. Built with INIT_STACK_ALL_PATTERN, a plain bpf_fib_lookup (no VLAN, no DIRECT) over a VRF slave whose destination is routed only in the VRF table returns BPF_FIB_LKUP_RET_NOT_FWDED, and resolves with this patch. On the default config the lookup succeeds either way, so ordinary testing does not catch the bug.
--- net/core/filter.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
net/core/filter.c +2 -2
@@ -6076,7 +6076,7 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params,struct neighbour *neigh;struct net_device *dev;struct fib_result res; -struct flowi4 fl4; +struct flowi4 fl4 = {};u32 mtu =0 ;int err;
@@ -6216,7 +6216,7 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params,struct neighbour *neigh;struct net_device *dev;struct inet6_dev *idev; -struct flowi6 fl6; +struct flowi6 fl6 = {};int strict =0 ;int oif, err;u32 mtu =0 ;
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 879/1611 bpf: Fix effective prog array index with BPF_F_PREORDER
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Amery Hung <[email protected]>
[ Upstream commit f08aaee3152d0dfc578b3f2586932d82062701dd ]
replace_effective_prog() and purge_effective_progs() located the slot in the effective array by walking the program hlist and counting entries linearly. That count does not match the array layout: compute_effective_ progs() places BPF_F_PREORDER programs at the front (ancestor cgroup first, attach order within a cgroup) and the rest after them (descendant cgroup first). So when a preorder program is present, the linear hlist position no longer equals the program's index in the effective array.
For replace_effective_prog() (bpf_link_update()) this overwrote the wrong slot, corrupting the effective order. For purge_effective_progs(), it could dummy out a slot belonging to a different program and leave the detached program in the array while bpf_prog_put() drops its reference, i.e. a use-after-free.
Fix both by replaying compute_effective_progs()'s placement (including the per-cgroup preorder reversal) in a shared effective_prog_pos() helper. Identify the entry by its struct bpf_prog_list pointer rather than by (prog, link) value, so the lookup resolves to exactly the attachment the syscall selected even when the same bpf_prog is attached to several cgroups in the hierarchy.
--- kernel/bpf/cgroup.c | 108 +++++++++++++++++++++++++------------------- 1 file changed, 62 insertions(+), 46 deletions(-)
kernel/bpf/cgroup.c +62 -46
@@ -939,19 +939,65 @@ static int cgroup_bpf_attach(struct cgroup *cgrp,return ret; } +static int effective_prog_pos (struct cgroup *cgrp, +enum cgroup_bpf_attach_type atype, +struct bpf_prog_list *target_pl) +{ +int cnt =0 , preorder_cnt =0 , fstart, bstart, init_bstart, pos =-1 ; +struct bpf_prog_list *pl; +struct cgroup *p = cgrp; + +/* count effective programs to find where the preorder region ends */ +do { +if (cnt ==0 || (p->bpf.flags[atype] &BPF_F_ALLOW_MULTI )) + cnt +=prog_list_length (&p->bpf.progs[atype], &preorder_cnt); + p =cgroup_parent (p); + }while (p); + +/* replay compute_effective_progs() placement and record target's slot */ + cnt =0 ; + p = cgrp; + fstart = preorder_cnt; + bstart = preorder_cnt -1 ; +do { +if (cnt >0 && !(p->bpf.flags[atype] &BPF_F_ALLOW_MULTI )) +continue ; + + init_bstart = bstart; +hlist_for_each_entry (pl, &p->bpf.progs[atype], node) { +if (!prog_list_prog (pl)) +continue ; + +if (pl->flags &BPF_F_PREORDER ) { +if (pl == target_pl) + pos = bstart; + bstart--; + }else { +if (pl == target_pl) + pos = fstart; + fstart++; + } + cnt++; + } + +/* reverse pre-ordering progs at this cgroup level */ +if (pos >= bstart +1 && pos <= init_bstart) + pos = bstart +1 + init_bstart - pos; + }while ((p =cgroup_parent (p))); + +return pos; +} +/* Swap updated BPF program for given link in effective program arrays across * all descendant cgroups. This function is guaranteed to succeed. */ static void replace_effective_prog (struct cgroup *cgrp,enum cgroup_bpf_attach_type atype, -struct bpf_cgroup_link *link) +struct bpf_prog_list *pl) {struct bpf_prog_array_item *item;struct cgroup_subsys_state *css;struct bpf_prog_array *progs; -struct bpf_prog_list *pl; -struct hlist_head *head; -struct cgroup *cg;int pos;css_for_each_descendant_pre (css, &cgrp->self) {
@@ -960,27 +1006,15 @@ static void replace_effective_prog(struct cgroup *cgrp,if (percpu_ref_is_zero (&desc->bpf.refcnt))continue ; -/* find position of link in effective progs array */ -for (pos =0 , cg = desc; cg; cg =cgroup_parent (cg)) { -if (pos && !(cg->bpf.flags[atype] &BPF_F_ALLOW_MULTI )) -continue ; + pos =effective_prog_pos (desc, atype, pl); +if (WARN_ON_ONCE (pos <0 )) +continue ; - head = &cg->bpf.progs[atype]; -hlist_for_each_entry (pl, head, node) { -if (!prog_list_prog (pl)) -continue ; -if (pl->link == link) - goto found; - pos++; - } - } -found: -BUG_ON (!cg); progs =rcu_dereference_protected ( desc->bpf.effective[atype],lockdep_is_held (&cgroup_mutex)); item = &progs->items[pos]; -WRITE_ONCE (item->prog, link->link.prog); +WRITE_ONCE (item->prog, pl->link->link.prog); } }
@@ -1024,7 +1058,7 @@ static int __cgroup_bpf_replace(struct cgroup *cgrp, cgrp->bpf.revisions[atype] +=1 ; old_prog =xchg (&link->link.prog, new_prog); -replace_effective_prog (cgrp, atype, link); +replace_effective_prog (cgrp, atype, pl);bpf_prog_put (old_prog);return 0 ; }
@@ -1091,19 +1125,14 @@ static struct bpf_prog_list *find_detach_entry(struct hlist_head *progs,* recomputing the array in place. * * @cgrp: The cgroup which descendants to travers -* @prog: A program to detach or NULL -* @link: A link to detach or NULL +* @pl: The prog_list entry being detached * @atype: Type of detach operation */ -static void purge_effective_progs (struct cgroup *cgrp,struct bpf_prog *prog, -struct bpf_cgroup_link *link, +static void purge_effective_progs (struct cgroup *cgrp,struct bpf_prog_list *pl,enum cgroup_bpf_attach_type atype) {struct cgroup_subsys_state *css;struct bpf_prog_array *progs; -struct bpf_prog_list *pl; -struct hlist_head *head; -struct cgroup *cg;int pos;/* recompute effective prog array in place */
@@ -1113,24 +1142,11 @@ static void purge_effective_progs(struct cgroup *cgrp, struct bpf_prog *prog,if (percpu_ref_is_zero (&desc->bpf.refcnt))continue ; -/* find position of link or prog in effective progs array */ -for (pos =0 , cg = desc; cg; cg =cgroup_parent (cg)) { -if (pos && !(cg->bpf.flags[atype] &BPF_F_ALLOW_MULTI )) -continue ; - - head = &cg->bpf.progs[atype]; -hlist_for_each_entry (pl, head, node) { -if (!prog_list_prog (pl)) -continue ; -if (pl->prog == prog && pl->link == link) - goto found; - pos++; - } - } - + pos =effective_prog_pos (desc, atype, pl);/* no link or prog match, skip the cgroup of this layer */ -continue ; -found: +if (pos <0 ) +continue ; + progs =rcu_dereference_protected ( desc->bpf.effective[atype],lockdep_is_held (&cgroup_mutex));
@@ -1196,7 +1212,7 @@ static int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog,/* if update effective array failed replace the prog with a dummy prog*/ pl->prog = old_prog; pl->link = link; -purge_effective_progs (cgrp, old_prog, link, atype); +purge_effective_progs (cgrp, pl, atype); }/* now can actually delete it from this cgroup list */
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 880/1611 power: sequencing: fix ABBA deadlock in pwrseq_device_unregister()
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Bartosz Golaszewski <[email protected]>
[ Upstream commit 2d5a7d406ecece5837af1e278ffbbf6c0315560a ]
The pwrseq core takes three locks in consistent order everywhere:
pwrseq_sem -> pwrseq->rw_lock -> pwrseq->state_lock
pwrseq_get() -> pwrseq_match_device() takes pwrseq_sem for reading, then rw_lock for reading. pwrseq_power_on()/pwrseq_power_off() take rw_lock for reading and then state_lock.
pwrseq_device_unregister() is the only exception, it takes: state_lock, then rw_lock for writing and finally pwrseq_sem for writing. This created two potential ABBA deadlock situations that sashiko pointed out.
- pwrseq_power_on/off() take rw_lock for reading then state_lock, while pwrseq_unregister() takes state_lock then rw_lock for writing
- pwrseq_get() takes pwrseq_sem for reading then rw_lock for reading, while pwrseq_unregister() takes rw_lock for writing then pwrseq_sem for writing
Reorder the unregister path to taking pwrseq_sem for writing -> rw_lock for writing and drop the state_lock entirely. This is safe as enable_count is only ever written under rw_lock held for read (via pwrseq_unit_enable()/disable(), reached only from pwrseq_power_on/off()), so holding rw_lock for writing already excludes every other writer and reader and the active-users WARN() stays race-free without state_lock.
--- drivers/power/sequencing/core.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-)
drivers/power/sequencing/core.c +6 -3
@@ -543,15 +543,18 @@ void pwrseq_device_unregister(struct pwrseq_device *pwrseq)struct device *dev = &pwrseq->dev;struct pwrseq_target *target; - scoped_guard(mutex, &pwrseq->state_lock) { + scoped_guard(rwsem_write, &pwrseq_sem) {guard (rwsem_write)(&pwrseq->rw_lock); +/* +* Holding rw_lock for write excludes all power on/off callers +* (they hold it for read), so it's safe to read enable_count +* here without taking the state_lock. +*/ list_for_each_entry (target, &pwrseq->targets, list)WARN (target->unit->enable_count,"REMOVING POWER SEQUENCER WITH ACTIVE USERS\n" ); -guard (rwsem_write)(&pwrseq_sem); -device_del (dev); }
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 881/1611 gpiolib: initialize return value in gpiochip_set_multiple()
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Ruoyu Wang <[email protected]>
[ Upstream commit 99dfa46baba29513d1094c8f30bc86c6ef88543a ]
gpiochip_set_multiple() falls back to setting lines one by one when the chip does not provide set_multiple(). If the fallback path receives an empty mask, the loop is skipped and ret is returned without being initialized.
Initialize ret to 0 so an empty mask is treated as a successful no-op.
--- drivers/gpio/gpiolib.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/gpio/gpiolib.c +1 -1
@@ -3657,7 +3657,7 @@ static int gpiochip_set_multiple(struct gpio_chip *gc, unsigned long *mask, unsigned long *bits) { unsigned int i; -int ret; +int ret =0 ;lockdep_assert_held (&gc->gpiodev->srcu);
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 882/1611 drm/edid: fix OOB read in drm_parse_tiled_block()
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Xiang Mei <[email protected]>
[ Upstream commit faaa1e1155833e7d4ce7e3cfaf64c0d636b190db ]
drm_parse_tiled_block() casts the DisplayID block to a struct displayid_tiled_block and reads the full fixed layout up to tile->topology_id[7] without checking block->num_bytes. The DisplayID iterator only validates the declared payload length, so a crafted EDID can advertise a tiled-display block (tag DATA_BLOCK_TILED_DISPLAY, or DATA_BLOCK_2_TILED_DISPLAY_TOPOLOGY for v2.0) with a small num_bytes at the end of a DisplayID extension. The read then runs past the end of the exact-sized kmemdup()'d EDID allocation, a heap out-of-bounds read.
Reject blocks shorter than the spec's 22-byte tiled payload before reading the fixed struct, as drm_parse_vesa_mso_data() already does.
BUG: KASAN: slab-out-of-bounds in drm_edid_connector_update Read of size 2 at addr ffff888010077700 by task exploit/147 dump_stack_lvl (lib/dump_stack.c:94 ...) print_report (mm/kasan/report.c:378 ...) kasan_report (mm/kasan/report.c:595) drm_edid_connector_update (drivers/gpu/drm/drm_edid.c:7581) bochs_connector_helper_get_modes (drivers/gpu/drm/tiny/bochs.c:574) drm_helper_probe_single_connector_modes (drivers/gpu/drm/drm_probe_helper.c:426) status_store (drivers/gpu/drm/drm_sysfs.c:219) ... vfs_write (fs/read_write.c:595 fs/read_write.c:688) ksys_write (fs/read_write.c:740)
--- drivers/gpu/drm/drm_edid.c | 8 ++++++++ 1 file changed, 8 insertions(+)
drivers/gpu/drm/drm_edid.c +8 -0
@@ -7500,6 +7500,14 @@ static void drm_parse_tiled_block(struct drm_connector *connector,u8 num_v_tile, num_h_tile;struct drm_tile_group *tg; +/* tiled block payload per spec: cap 1 + topo 3 + size 4 + bezel 5 + id 9 = 22 */ +if (block->num_bytes <22 ) { +drm_dbg_kms (connector->dev, +"[CONNECTOR:%d:%s] Unexpected tiled block size %u\n" , + connector->base.id, connector->name, block->num_bytes); +return ; + } + w = tile->tile_size[0 ] | tile->tile_size[1 ] <<8 ; h = tile->tile_size[2 ] | tile->tile_size[3 ] <<8 ;
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 883/1611 PCI: endpoint: pci-epf-vntb: Add check to detect db_count value of 0
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Manivannan Sadhasivam <[email protected]>
[ Upstream commit 33bd1ea748bc897c4d13437284e08c658e8d1340 ]
epf_ntb->db_count value should be within 1 to MAX_DB_COUNT. Current code only checks for the upper bound, while the lower bound is unchecked. This can cause a lot of issues in the driver if the user passes 'db_count' as 0.
Add a check for 0 also. While at it, remove the redundant 'db_count' assignment.
--- drivers/pci/endpoint/functions/pci-epf-vntb.c | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-)
drivers/pci/endpoint/functions/pci-epf-vntb.c +3 -6
@@ -466,7 +466,6 @@ static int epf_ntb_configure_interrupt(struct epf_ntb *ntb) {const struct pci_epc_features *epc_features;struct device *dev; -u32 db_count;int ret; dev = &ntb->epf->dev;
@@ -478,14 +477,12 @@ static int epf_ntb_configure_interrupt(struct epf_ntb *ntb)return -EINVAL ; } - db_count = ntb->db_count; -if (db_count >MAX_DB_COUNT ) { -dev_err (dev,"DB count cannot be more than %d\n" ,MAX_DB_COUNT ); +if (!ntb->db_count || ntb->db_count >MAX_DB_COUNT ) { +dev_err (dev,"DB count %d out of range (1 - %d)\n" , + ntb->db_count,MAX_DB_COUNT );return -EINVAL ; } - ntb->db_count = db_count; -if (epc_features->msi_capable) { ret = pci_epc_set_msi(ntb->epf->epc, ntb->epf->func_no,
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 884/1611 PCI: endpoint: pci-epf-ntb: Add check to detect db_count value of 0
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Manivannan Sadhasivam <[email protected]>
[ Upstream commit d1db6d7c2485ee475a04d8354fbb5b26ea10d978 ]
epf_ntb->db_count value should be within 1 to MAX_DB_COUNT. Current code only checks for the upper bound, while the lower bound is unchecked. This can cause a lot of issues in the driver if the user passes 'db_count' as 0.
Add a check for 0 also. While at it, remove the redundant 'db_count' variable from epf_ntb_configure_interrupt().
--- drivers/pci/endpoint/functions/pci-epf-ntb.c | 21 ++++++++++---------- 1 file changed, 11 insertions(+), 10 deletions(-)
drivers/pci/endpoint/functions/pci-epf-ntb.c +11 -10
@@ -559,12 +559,15 @@ static int epf_ntb_configure_db(struct epf_ntb *ntb,struct pci_epc *epc;int ret; -if (db_count >MAX_DB_COUNT ) -return -EINVAL ; - ntb_epc = ntb->epc[type]; epc = ntb_epc->epc; +if (!db_count || db_count >MAX_DB_COUNT ) { +dev_err (&epc->dev,"DB count %d out of range (1 - %d)\n" , + db_count,MAX_DB_COUNT ); +return -EINVAL ; + } +if (msix) ret =epf_ntb_configure_msix (ntb, type, db_count);else
@@ -1278,7 +1281,6 @@ static int epf_ntb_configure_interrupt(struct epf_ntb *ntb,u8 func_no, vfunc_no;struct pci_epc *epc;struct device *dev; -u32 db_count;int ret; ntb_epc = ntb->epc[type];
@@ -1296,17 +1298,16 @@ static int epf_ntb_configure_interrupt(struct epf_ntb *ntb, func_no = ntb_epc->func_no; vfunc_no = ntb_epc->vfunc_no; - db_count = ntb->db_count; -if (db_count >MAX_DB_COUNT ) { -dev_err (dev,"DB count cannot be more than %d\n" ,MAX_DB_COUNT ); +if (!ntb->db_count || ntb->db_count >MAX_DB_COUNT ) { +dev_err (dev,"DB count %d out of range (1 - %d)\n" , + ntb->db_count,MAX_DB_COUNT );return -EINVAL ; } - ntb->db_count = db_count; epc = ntb_epc->epc;if (msi_capable) { - ret =pci_epc_set_msi (epc, func_no, vfunc_no, db_count); + ret =pci_epc_set_msi (epc, func_no, vfunc_no, ntb->db_count);if (ret) {dev_err (dev,"%s intf: MSI configuration failed\n" ,pci_epc_interface_string (type));
@@ -1315,7 +1316,7 @@ static int epf_ntb_configure_interrupt(struct epf_ntb *ntb, }if (msix_capable) { - ret =pci_epc_set_msix (epc, func_no, vfunc_no, db_count, + ret =pci_epc_set_msix (epc, func_no, vfunc_no, ntb->db_count, ntb_epc->msix_bar, ntb_epc->msix_table_offset);if (ret) {
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 885/1611 ice: fix FDIR CTRL VSI resource leak in ice_reset_all_vfs()
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Dawid Osuchowski <[email protected]>
[ Upstream commit ebbe8868cf473f698e0fbaf436d2618b2bcda806 ]
Resetting all VFs causes resource leak on VFs with FDIR filters enabled as CTRL VSIs are only invalidated and not freed. Fix by using ice_vf_ctrl_vsi_release() instead of ice_vf_ctrl_invalidate_vsi() which aligns behavior with the ice_reset_vf() function.
Reproduction:
echo 1 > /sys/class/net/$pf/device/sriov_numvfs ethtool -N $vf flow-type ether proto 0x9000 action 0 echo 1 > /sys/class/net/$pf/device/reset
--- drivers/net/ethernet/intel/ice/ice_vf_lib.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/net/ethernet/intel/ice/ice_vf_lib.c +1 -1
@@ -801,7 +801,7 @@ void ice_reset_all_vfs(struct ice_pf *pf)* setup only when VF creates its first FDIR rule. */ if (vf->ctrl_vsi_idx !=ICE_NO_VSI ) -ice_vf_ctrl_invalidate_vsi (vf); +ice_vf_ctrl_vsi_release (vf);ice_vf_pre_vsi_rebuild (vf);if (ice_vf_rebuild_vsi (vf)) {
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 886/1611 ice: fix AQ error code comparison in ice_set_pauseparam()
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Lukasz Czapnik <[email protected]>
[ Upstream commit 2bf7744bc3221a63b95c76c94eab1dad832fa401 ]
Fix unreachable code: the conditionals in ice_set_pauseparam() used the bitwise-AND operator suggesting aq_failures is a bitmap, but it is actually an enum, making the third condition logically unreachable.
Replace the if-else ladder with a switch statement. Also move the aq_failures initialization to the variable declaration and remove the redundant zeroing from ice_set_fc().
--- drivers/net/ethernet/intel/ice/ice_common.c | 1 - drivers/net/ethernet/intel/ice/ice_ethtool.c | 12 ++++++++---- 2 files changed, 8 insertions(+), 5 deletions(-)
drivers/net/ethernet/intel/ice/ice_common.c +0 -1
@@ -3919,7 +3919,6 @@ ice_set_fc(struct ice_port_info *pi, u8 *aq_failures, bool ena_auto_link_update)if (!pi || !aq_failures)return -EINVAL ; - *aq_failures =0 ; hw = pi->hw; pcaps =kzalloc (sizeof (*pcaps),GFP_KERNEL );
drivers/net/ethernet/intel/ice/ice_ethtool.c +8 -4
@@ -3488,7 +3488,7 @@ ice_set_pauseparam(struct net_device *netdev, struct ethtool_pauseparam *pause)struct ice_vsi *vsi = np->vsi;struct ice_hw *hw = &pf->hw;struct ice_port_info *pi; -u8 aq_failures; +u8 aq_failures =0 ;bool link_up;u32 is_an;int err;
@@ -3559,18 +3559,22 @@ ice_set_pauseparam(struct net_device *netdev, struct ethtool_pauseparam *pause)/* Set the FC mode and only restart AN if link is up */ err =ice_set_fc (pi, &aq_failures, link_up); -if (aq_failures &ICE_SET_FC_AQ_FAIL_GET ) { +switch (aq_failures) { +case ICE_SET_FC_AQ_FAIL_GET :netdev_info (netdev,"Set fc failed on the get_phy_capabilities call with err %d aq_err %s\n" , err,libie_aq_str (hw->adminq.sq_last_status)); err = -EAGAIN ; - }else if (aq_failures &ICE_SET_FC_AQ_FAIL_SET ) { +break ; +case ICE_SET_FC_AQ_FAIL_SET :netdev_info (netdev,"Set fc failed on the set_phy_config call with err %d aq_err %s\n" , err,libie_aq_str (hw->adminq.sq_last_status)); err = -EAGAIN ; - }else if (aq_failures &ICE_SET_FC_AQ_FAIL_UPDATE ) { +break ; +case ICE_SET_FC_AQ_FAIL_UPDATE :netdev_info (netdev,"Set fc failed on the get_link_info call with err %d aq_err %s\n" , err,libie_aq_str (hw->adminq.sq_last_status)); err = -EAGAIN ; +break ; }return err;
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 887/1611 ice: call netif_keep_dst() once when entering switchdev mode
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Marcin Szycik <[email protected]>
[ Upstream commit c0d00c882bc432990d57052a659f9a8bd1f60687 ]
netif_keep_dst() only needs to be called once for the uplink VSI, not once for each port representor. Move it from ice_eswitch_setup_repr() to ice_eswitch_enable_switchdev().
--- drivers/net/ethernet/intel/ice/ice_eswitch.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
drivers/net/ethernet/intel/ice/ice_eswitch.c +2 -2
@@ -117,8 +117,6 @@ static int ice_eswitch_setup_repr(struct ice_pf *pf, struct ice_repr *repr)if (!repr->dst)return -ENOMEM ; -netif_keep_dst (uplink_vsi->netdev); - dst = repr->dst; dst->u.port_info.port_id = vsi->vsi_num; dst->u.port_info.lower_dev = uplink_vsi->netdev;
@@ -312,6 +310,8 @@ static int ice_eswitch_enable_switchdev(struct ice_pf *pf)if (ice_eswitch_br_offloads_init (pf)) goto err_br_offloads; +netif_keep_dst (uplink_vsi->netdev); + pf->eswitch.is_running = true;return 0 ;
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 888/1611 rtc: isl1208: Balance enable_irq_wake() with disable_irq_wake() on cleanup
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: John Madieu <[email protected]>
[ Upstream commit 1afe4f19d6ad404621150f0e91feeccf12fb1037 ]
isl1208_setup_irq() calls enable_irq_wake() after a successful IRQ request, but the driver has no remove path that balances it. The driver is devm-only, so on unbind devm releases the IRQ - but enable_irq_wake() is not undone by IRQ release, so the wake count for that IRQ stays incremented.
Each rebind therefore leaks one wake reference; the leak doubles for the chip variant that has a separate evdet IRQ, since isl1208_setup_irq() is then called twice during probe.
Register a devm action that calls disable_irq_wake() per IRQ. While at it, check enable_irq_wake()'s return value:
on failure, propagate the error rather than silently registering a disable action for an IRQ whose wake state was never enabled.
--- drivers/rtc/rtc-isl1208.c | 15 ++++++++++++++- 1 file changed, 14 insertions(+), 1 deletion(-)
drivers/rtc/rtc-isl1208.c +14 -1
@@ -822,6 +822,11 @@ static const struct nvmem_config isl1208_nvmem_config = { .reg_write = isl1208_nvmem_write, }; +static void isl1208_disable_irq_wake_action (void *data) +{ +disable_irq_wake ((unsigned long )data); +} +static int isl1208_setup_irq (struct i2c_client *client,int irq) { int rc = devm_request_threaded_irq(&client->dev, irq, NULL,
@@ -831,7 +836,15 @@ static int isl1208_setup_irq(struct i2c_client *client, int irq) client);if (!rc) {device_init_wakeup (&client->dev, true); -enable_irq_wake (irq); + rc =enable_irq_wake (irq); +if (rc) +return rc; + + rc =devm_add_action_or_reset (&client->dev, + isl1208_disable_irq_wake_action, + (void *)(unsigned long )irq); +if (rc) +return rc; }else { dev_err(&client->dev, "Unable to request irq %d, no alarm support\n",
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 889/1611 ice: dpll: set pointers to NULL after kfree in ice_dpll_deinit_info
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: ZhaoJinming <[email protected]>
[ Upstream commit a903afff66d7379c6ece42bd18b2a17f4c79d1a9 ]
ice_dpll_deinit_info() calls kfree() on several pf->dplls fields (inputs, outputs, eec.input_prio, pps.input_prio) but does not set the pointers to NULL afterward. This leaves dangling pointers in the pf->dplls structure.
While not currently exploitable through existing code paths, this is unsafe because:
1. If ice_dpll_init_info() is called again after a deinit (e.g. during driver recovery), and a subsequent allocation within init fails, the error path will jump to deinit_info and call ice_dpll_deinit_info() again. Since some pointers still hold the old freed addresses, this would result in a double-free.
2. Any future code that checks these pointers before use or after free would be unprotected against use-after-free.
Follow the common kernel convention of setting pointers to NULL after kfree() so that:
- kfree(NULL) is a safe no-op, preventing double-free
- NULL checks on these pointers become meaningful
This is a preparatory fix for a subsequent patch that routes additional error paths in ice_dpll_init_info() to the deinit_info label.
--- drivers/net/ethernet/intel/ice/ice_dpll.c | 4 ++++ 1 file changed, 4 insertions(+)
drivers/net/ethernet/intel/ice/ice_dpll.c +4 -0
@@ -3772,9 +3772,13 @@ ice_dpll_init_pins_info(struct ice_pf *pf, enum ice_dpll_pin_type pin_type)static void ice_dpll_deinit_info (struct ice_pf *pf) {kfree (pf->dplls.inputs); + pf->dplls.inputs =NULL ;kfree (pf->dplls.outputs); + pf->dplls.outputs =NULL ;kfree (pf->dplls.eec.input_prio); + pf->dplls.eec.input_prio =NULL ;kfree (pf->dplls.pps.input_prio); + pf->dplls.pps.input_prio =NULL ; }/**
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 890/1611 ice: dpll: fix memory leak in ice_dpll_init_info error paths
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: ZhaoJinming <[email protected]>
[ Upstream commit 20da495f2df0fd4adc435d3d621366e8c807539c ]
Several error return paths in ice_dpll_init_info() directly return without freeing previously allocated resources, causing memory leaks:
- When de->input_prio allocation fails, d->inputs is leaked
- When dp->input_prio allocation fails, d->inputs and de->input_prio are leaked
- When ice_get_cgu_rclk_pin_info() fails, all previously allocated inputs/outputs/input_prio are leaked
- When ice_dpll_init_pins_info(RCLK_INPUT) fails, same resources are leaked
Fix this by jumping to the deinit_info label which properly calls ice_dpll_deinit_info() to free all allocated resources.
--- drivers/net/ethernet/intel/ice/ice_dpll.c | 16 ++++++++++------ 1 file changed, 10 insertions(+), 6 deletions(-)
drivers/net/ethernet/intel/ice/ice_dpll.c +10 -6
@@ -3826,12 +3826,16 @@ static int ice_dpll_init_info(struct ice_pf *pf, bool cgu) alloc_size =sizeof (*de->input_prio) * d->num_inputs; de->input_prio =kzalloc (alloc_size,GFP_KERNEL ); -if (!de->input_prio) -return -ENOMEM ; +if (!de->input_prio) { + ret = -ENOMEM ; + goto deinit_info; + } dp->input_prio =kzalloc (alloc_size,GFP_KERNEL ); -if (!dp->input_prio) -return -ENOMEM ; +if (!dp->input_prio) { + ret = -ENOMEM ; + goto deinit_info; + } ret =ice_dpll_init_pins_info (pf,ICE_DPLL_PIN_TYPE_INPUT );if (ret)
@@ -3856,12 +3860,12 @@ static int ice_dpll_init_info(struct ice_pf *pf, bool cgu) ret =ice_get_cgu_rclk_pin_info (&pf->hw, &d->base_rclk_idx, &pf->dplls.rclk.num_parents);if (ret) -return ret; + goto deinit_info;for (i =0 ; i < pf->dplls.rclk.num_parents; i++) pf->dplls.rclk.parent_idx[i] = d->base_rclk_idx + i; ret =ice_dpll_init_pins_info (pf,ICE_DPLL_PIN_TYPE_RCLK_INPUT );if (ret) -return ret; + goto deinit_info; de->mode =DPLL_MODE_AUTOMATIC ; dp->mode =DPLL_MODE_AUTOMATIC ;
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 891/1611 i40e: Fix i40e_debug() to use struct i40e_hw argument
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Mohamed Khalfella <[email protected]>
[ Upstream commit 798f94603eb0737033861efd320a9159f382a7c5 ]
i40e_debug() macro takes struct i40e_hw *h as first argument. But the macro body uses hw instead of h. This has been working so far because hw happens to be the name of the variable in the context where the macro is expanded. Fix the macro to use the passed argument.
--- drivers/net/ethernet/intel/i40e/i40e_debug.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/net/ethernet/intel/i40e/i40e_debug.h +1 -1
@@ -42,7 +42,7 @@ struct device *i40e_hw_to_dev(struct i40e_hw *hw);#define i40e_debug (h, m, s, ...) \ do { \ if (((m) & (h)->debug_mask)) \ - dev_info(i40e_hw_to_dev(hw), s, ##__VA_ARGS__); \ + dev_info(i40e_hw_to_dev(h), s, ##__VA_ARGS__); \ } while (0)#endif /* _I40E_DEBUG_H_ */
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 892/1611 rtc: msc313: fix NULL deref in shared IRQ handler at probe
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Stepan Ionichev <[email protected]>
[ Upstream commit a369f48be8de426a7d2bca18dbd46c2ad1138803 ]
msc313_rtc_probe() calls devm_request_irq() with IRQF_SHARED and &pdev->dev as the cookie, but platform_set_drvdata() is only called later after the clock setup. With a shared IRQ line, another device on the same line can trigger the handler in that window. The handler does dev_get_drvdata() on the cookie, gets NULL, and dereferences priv->rtc_base in interrupt context.
Pass priv as the cookie directly so the handler reads it from dev_id without the lookup, removing the dependency on probe order.
--- drivers/rtc/rtc-msc313.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
drivers/rtc/rtc-msc313.c +2 -2
@@ -160,7 +160,7 @@ static const struct rtc_class_ops msc313_rtc_ops = {static irqreturn_t msc313_rtc_interrupt (s32 irq,void *dev_id) { -struct msc313_rtc *priv =dev_get_drvdata (dev_id); +struct msc313_rtc *priv = dev_id;u16 reg; reg =readw (priv->rtc_base +REG_RTC_STATUS_INT );
@@ -206,7 +206,7 @@ static int msc313_rtc_probe(struct platform_device *pdev) priv->rtc_dev->range_max =U32_MAX ; ret =devm_request_irq (dev, irq, msc313_rtc_interrupt,IRQF_SHARED , -dev_name (&pdev->dev), &pdev->dev); +dev_name (&pdev->dev), priv);if (ret) {dev_err (dev,"Could not request IRQ\n" );return ret;
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 893/1611 ksmbd: fix use-after-free of conn->preauth_info in concurrent SMB2 NEGOTIATE
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Gil Portnoy <[email protected]>
[ Upstream commit 0c054227479ed7e36ebccb3a558bc0ef698264f6 ]
conn->preauth_info is shared connection state (struct preauth_integrity_info, kmalloc-96) that is allocated and freed by the SMB2 NEGOTIATE handler and read by the response send path.
smb2_handle_negotiate() allocates conn->preauth_info, and on a deassemble_neg_contexts() failure kfrees it and sets it to NULL. Both the allocation and the free/NULL happen under ksmbd_conn_lock(conn) (the connection srv_mutex), which is held across the whole handler body.
The response send path smb3_preauth_hash_rsp(), called from the send:
block of __handle_ksmbd_work(), reads conn->preauth_info and dereferences conn->preauth_info->Preauth_HashValue (via ksmbd_gen_preauth_integrity_hash()) without taking conn_lock. When a client drives two SMB2 NEGOTIATE requests on the same connection, one worker can free conn->preauth_info on the failing-negotiate path while a concurrent send-path worker is reading it, producing a slab use-after-free read (KASAN-confirmed).
The send-path read tested conn->preauth_info for NULL but raced with the free that occurs between the NULL check and the dereference, so the NULL guard alone does not close the window.
Serialize the NEGOTIATE-branch read in smb3_preauth_hash_rsp() under ksmbd_conn_lock(conn) and re-check conn->preauth_info inside the lock. Because the negotiate handler holds conn_lock across its kfree + NULL assignment, a reader that also takes conn_lock either runs fully before the allocation or fully after the NULL store, and can never observe the freed-but-not-yet-NULLed pointer. ksmbd_gen_preauth_integrity_hash() takes no locks itself (it only computes a SHA-512 over the buffer), so no lock-ordering inversion is introduced, and conn_lock is a sleepable mutex which is safe on this send path (it already performs network I/O).
--- fs/smb/server/smb2pdu.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-)
fs/smb/server/smb2pdu.c +7 -4
@@ -9217,10 +9217,13 @@ void smb3_preauth_hash_rsp(struct ksmbd_work *work)WORK_BUFFERS (work, req, rsp); -if (le16_to_cpu (req->Command) ==SMB2_NEGOTIATE_HE && - conn->preauth_info) -ksmbd_gen_preauth_integrity_hash (conn, work->response_buf, - conn->preauth_info->Preauth_HashValue); +if (le16_to_cpu (req->Command) ==SMB2_NEGOTIATE_HE ) { +ksmbd_conn_lock (conn); +if (conn->preauth_info) +ksmbd_gen_preauth_integrity_hash (conn, work->response_buf, + conn->preauth_info->Preauth_HashValue); +ksmbd_conn_unlock (conn); + }if (le16_to_cpu (rsp->Command) ==SMB2_SESSION_SETUP_HE && sess) {__u8 *hash_value;
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 894/1611 ipv6: Fix null-ptr-deref in fib6_nh_mtu_change().
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Xiang Mei <[email protected]>
[ Upstream commit 46c3b8191aad3d032776bf3bebf03efdf5f4b905 ]
fib6_nh_mtu_change() re-fetches idev via __in6_dev_get(arg->dev) and dereferences idev->cnf.mtu6 without a NULL check. addrconf_ifdown() clears dev->ip6_ptr with RCU_INIT_POINTER() after rt6_disable_ip() has released tb6_lock, so the RA-driven MTU walk can observe a NULL idev and oops. The caller rt6_mtu_change_route() guards its own __in6_dev_get(), but this re-fetch is unguarded; nexthop-backed routes survive addrconf_ifdown()'s flush, so the walk still reaches it after ip6_ptr is nulled.
Return 0 when idev is NULL, matching rt6_mtu_change_route() and the fib6_mtu() fix in commit 5ad509c1fdad ("ipv6: Fix null-ptr-deref in fib6_mtu().").
Oops: general protection fault, ... KASAN: null-ptr-deref in range
[0x00000000000002a8-0x00000000000002af]
RIP: 0010:fib6_nh_mtu_change+0x203/0x990
rt6_mtu_change_route+0x141/0x1d0
__fib6_clean_all+0xd0/0x160
rt6_mtu_change+0xb4/0x100
ndisc_router_discovery+0x24b5/0x2cb0
icmpv6_rcv+0x12e9/0x1710
ipv6_rcv+0x39b/0x410--- net/ipv6/route.c | 3 +++ 1 file changed, 3 insertions(+)
net/ipv6/route.c +3 -0
@@ -5043,6 +5043,9 @@ static int fib6_nh_mtu_change(struct fib6_nh *nh, void *_arg)struct inet6_dev *idev =__in6_dev_get (arg->dev);u32 mtu = f6i->fib6_pmtu; +if (!idev) +return 0 ; +if (mtu >= arg->mtu || (mtu < arg->mtu && mtu == idev->cnf.mtu6))fib6_metric_set (f6i,RTAX_MTU , arg->mtu);
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 895/1611 eth: bnxt: gather and report HW-GRO stats
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Jakub Kicinski <[email protected]>
[ Upstream commit a7fc1a488f09f0fbf727fe3ca5b017e7657f152d ]
Count and report HW-GRO stats as seen by the kernel. The device stats for GRO seem to not reflect the reality, perhaps they count sessions which did not actually result in any aggregation. Also they count wire packets, so we have to count super-frames, anyway.
Stable-dep-of: 40529e58629b ("eth: bnxt: improve the timing of stats")
--- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 15 +++++++++++++-- drivers/net/ethernet/broadcom/bnxt/bnxt.h | 6 ++++++ 2 files changed, 19 insertions(+), 2 deletions(-)
drivers/net/ethernet/broadcom/bnxt/bnxt.c +13 -2
@@ -1803,7 +1803,8 @@ static inline struct sk_buff *bnxt_gro_skb(struct bnxt *bp,struct bnxt_tpa_info *tpa_info, struct rx_tpa_end_cmp *tpa_end, struct rx_tpa_end_cmp_ext *tpa_end1, - struct sk_buff *skb) + struct sk_buff *skb, + struct bnxt_rx_sw_stats *rx_stats) { #ifdef CONFIG_INET int payload_off;
@@ -1813,6 +1814,9 @@ static inline struct sk_buff *bnxt_gro_skb(struct bnxt *bp,if (segs ==1 )return skb; + rx_stats->rx_hw_gro_packets++; + rx_stats->rx_hw_gro_wire_packets += segs; +NAPI_GRO_CB (skb)->count = segs;skb_shinfo (skb)->gso_size =le32_to_cpu (tpa_end1->rx_tpa_end_cmp_seg_len);
@@ -1986,7 +1990,8 @@ static inline struct sk_buff *bnxt_tpa_end(struct bnxt *bp, }if (gro) - skb =bnxt_gro_skb (bp, tpa_info, tpa_end, tpa_end1, skb); + skb =bnxt_gro_skb (bp, tpa_info, tpa_end, tpa_end1, skb, + &cpr->sw_stats->rx);return skb; }
@@ -13413,6 +13418,8 @@ static void bnxt_get_one_ring_err_stats(struct bnxt *bp, stats->rx_total_netpoll_discards += sw_stats->rx.rx_netpoll_discards; stats->rx_total_ring_discards +=BNXT_GET_RING_STATS64 (hw_stats, rx_discard_pkts); + stats->rx_total_hw_gro_packets += sw_stats->rx.rx_hw_gro_packets; + stats->rx_total_hw_gro_wire_packets += sw_stats->rx.rx_hw_gro_wire_packets; stats->tx_total_resets += sw_stats->tx.tx_resets; stats->tx_total_ring_discards +=BNXT_GET_RING_STATS64 (hw_stats, tx_discard_pkts);
@@ -15844,6 +15851,8 @@ static void bnxt_get_queue_stats_rx(struct net_device *dev, int i, stats->bytes +=BNXT_GET_RING_STATS64 (sw, rx_bcast_bytes); stats->alloc_fail = cpr->sw_stats->rx.rx_oom_discards; + stats->hw_gro_packets = cpr->sw_stats->rx.rx_hw_gro_packets; + stats->hw_gro_wire_packets = cpr->sw_stats->rx.rx_hw_gro_wire_packets; } static void bnxt_get_queue_stats_tx(struct net_device *dev, int i,
@@ -15879,6 +15888,8 @@ static void bnxt_get_base_stats(struct net_device *dev, rx->packets = bp->net_stats_prev.rx_packets; rx->bytes = bp->net_stats_prev.rx_bytes; rx->alloc_fail = bp->ring_err_stats_prev.rx_total_oom_discards; + rx->hw_gro_packets = bp->ring_err_stats_prev.rx_total_hw_gro_packets; + rx->hw_gro_wire_packets = bp->ring_err_stats_prev.rx_total_hw_gro_wire_packets; tx->packets = bp->net_stats_prev.tx_packets; tx->bytes = bp->net_stats_prev.tx_bytes;
drivers/net/ethernet/broadcom/bnxt/bnxt.h +6 -0
@@ -1123,8 +1123,11 @@ struct bnxt_rx_sw_stats {u64 rx_l4_csum_errors;u64 rx_resets;u64 rx_buf_errors; +/* end of ethtool -S stats */ u64 rx_oom_discards;u64 rx_netpoll_discards; +u64 rx_hw_gro_packets; +u64 rx_hw_gro_wire_packets; };struct bnxt_tx_sw_stats {
@@ -1151,6 +1154,9 @@ struct bnxt_total_ring_err_stats {u64 tx_total_resets;u64 tx_total_ring_discards;u64 total_missed_irqs; +/* end of ethtool -S stats */ +u64 rx_total_hw_gro_packets; +u64 rx_total_hw_gro_wire_packets; };struct bnxt_stats_mem {
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 896/1611 eth: bnxt: rename ring_err_stats -> ring_drv_stats
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Jakub Kicinski <[email protected]>
[ Upstream commit 6c32b07650676ab4c112ff8e9d345b6770ae2be5 ]
We recently added GRO stats to bnxt, which are maintained by the driver. Having "err" in the name of the struct for ring stats no longer makes sense (as pointed out by Michael, see Link).
Rename them to "drv" stats, as these are all maintained by the driver (even if partially based on info from descriptors). Michael suggested calling these misc, happy to go back to that. IMHO "drv" is a bit more meaningful that "misc".
Pure rename using sed, no functional changes.
Stable-dep-of: 40529e58629b ("eth: bnxt: improve the timing of stats")
--- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 18 ++++++++--------- drivers/net/ethernet/broadcom/bnxt/bnxt.h | 8 ++++---- .../net/ethernet/broadcom/bnxt/bnxt_ethtool.c | 20 +++++++++---------- 3 files changed, 23 insertions(+), 23 deletions(-)
drivers/net/ethernet/broadcom/bnxt/bnxt.c +9 -9
@@ -13159,7 +13159,7 @@ static void __bnxt_close_nic(struct bnxt *bp, bool irq_re_init,/* Save ring stats before shutdown */ if (bp->bnapi && irq_re_init) {bnxt_get_ring_stats (bp, &bp->net_stats_prev); -bnxt_get_ring_err_stats (bp, &bp->ring_err_stats_prev); +bnxt_get_ring_drv_stats (bp, &bp->ring_drv_stats_prev); }if (irq_re_init) {bnxt_free_irq (bp);
@@ -13404,8 +13404,8 @@ bnxt_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats)clear_bit (BNXT_STATE_READ_STATS , &bp->state); } -static void bnxt_get_one_ring_err_stats (struct bnxt *bp, -struct bnxt_total_ring_err_stats *stats, +static void bnxt_get_one_ring_drv_stats (struct bnxt *bp, +struct bnxt_total_ring_drv_stats *stats,struct bnxt_cp_ring_info *cpr) {struct bnxt_sw_stats *sw_stats = cpr->sw_stats;
@@ -13426,13 +13426,13 @@ static void bnxt_get_one_ring_err_stats(struct bnxt *bp, stats->total_missed_irqs += sw_stats->cmn.missed_irqs; } -void bnxt_get_ring_err_stats (struct bnxt *bp, -struct bnxt_total_ring_err_stats *stats) +void bnxt_get_ring_drv_stats (struct bnxt *bp, +struct bnxt_total_ring_drv_stats *stats) {int i;for (i =0 ; i < bp->cp_nr_rings; i++) -bnxt_get_one_ring_err_stats (bp, stats, &bp->bnapi[i]->cp_ring); +bnxt_get_one_ring_drv_stats (bp, stats, &bp->bnapi[i]->cp_ring); }static bool bnxt_mc_list_updated (struct bnxt *bp,u32 *rx_mask)
@@ -15887,9 +15887,9 @@ static void bnxt_get_base_stats(struct net_device *dev, rx->packets = bp->net_stats_prev.rx_packets; rx->bytes = bp->net_stats_prev.rx_bytes; - rx->alloc_fail = bp->ring_err_stats_prev.rx_total_oom_discards; - rx->hw_gro_packets = bp->ring_err_stats_prev.rx_total_hw_gro_packets; - rx->hw_gro_wire_packets = bp->ring_err_stats_prev.rx_total_hw_gro_wire_packets; + rx->alloc_fail = bp->ring_drv_stats_prev.rx_total_oom_discards; + rx->hw_gro_packets = bp->ring_drv_stats_prev.rx_total_hw_gro_packets; + rx->hw_gro_wire_packets = bp->ring_drv_stats_prev.rx_total_hw_gro_wire_packets; tx->packets = bp->net_stats_prev.tx_packets; tx->bytes = bp->net_stats_prev.tx_bytes;
drivers/net/ethernet/broadcom/bnxt/bnxt.h +4 -4
@@ -1144,7 +1144,7 @@ struct bnxt_sw_stats {struct bnxt_cmn_sw_stats cmn; }; -struct bnxt_total_ring_err_stats { +struct bnxt_total_ring_drv_stats {u64 rx_total_l4_csum_errors;u64 rx_total_resets;u64 rx_total_buf_errors;
@@ -2562,7 +2562,7 @@ struct bnxt {u8 pri2cos_idx[8 ];u8 pri2cos_valid; -struct bnxt_total_ring_err_stats ring_err_stats_prev; +struct bnxt_total_ring_drv_stats ring_drv_stats_prev;u16 hwrm_max_req_len;u16 hwrm_max_ext_req_len;
@@ -2963,8 +2963,8 @@ int bnxt_half_open_nic(struct bnxt *bp);void bnxt_half_close_nic (struct bnxt *bp);void bnxt_reenable_sriov (struct bnxt *bp);void bnxt_close_nic (struct bnxt *,bool ,bool ); -void bnxt_get_ring_err_stats (struct bnxt *bp, -struct bnxt_total_ring_err_stats *stats); +void bnxt_get_ring_drv_stats (struct bnxt *bp, +struct bnxt_total_ring_drv_stats *stats);bool bnxt_rfs_capable (struct bnxt *bp,bool new_rss_ctx);int bnxt_dbg_hwrm_rd_reg (struct bnxt *bp,u32 reg_off,u16 num_words,u32 *reg_buf);
drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c +10 -10
@@ -340,7 +340,7 @@ enum { RX_NETPOLL_DISCARDS, }; -static const char *const bnxt_ring_err_stats_arr[] = { +static const char *const bnxt_ring_drv_stats_arr[] = {"rx_total_l4_csum_errors" ,"rx_total_resets" ,"rx_total_buf_errors" ,
@@ -500,7 +500,7 @@ static const struct { BNXT_TX_STATS_PRI_ENTRIES(tx_packets), }; -#define BNXT_NUM_RING_ERR_STATS ARRAY_SIZE(bnxt_ring_err_stats_arr) +#define BNXT_NUM_RING_DRV_STATS ARRAY_SIZE(bnxt_ring_drv_stats_arr)#define BNXT_NUM_PORT_STATS ARRAY_SIZE(bnxt_port_stats_arr)#define BNXT_NUM_STATS_PRI \ (ARRAY_SIZE(bnxt_rx_bytes_pri_arr) + \
@@ -539,7 +539,7 @@ static int bnxt_get_num_stats(struct bnxt *bp)int num_stats =bnxt_get_num_ring_stats (bp);int len; - num_stats +=BNXT_NUM_RING_ERR_STATS ; + num_stats +=BNXT_NUM_RING_DRV_STATS ;if (bp->flags &BNXT_FLAG_PORT_STATS ) num_stats +=BNXT_NUM_PORT_STATS ;
@@ -594,7 +594,7 @@ static bool is_tx_ring(struct bnxt *bp, int ring_num)static void bnxt_get_ethtool_stats (struct net_device *dev,struct ethtool_stats *stats,u64 *buf) { -struct bnxt_total_ring_err_stats ring_err_stats = {0 }; +struct bnxt_total_ring_drv_stats ring_drv_stats = {0 };struct bnxt *bp =netdev_priv (dev);u64 *curr, *prev;u32 tpa_stats;
@@ -643,12 +643,12 @@ static void bnxt_get_ethtool_stats(struct net_device *dev, buf[j] = sw[k]; } -bnxt_get_ring_err_stats (bp, &ring_err_stats); +bnxt_get_ring_drv_stats (bp, &ring_drv_stats); skip_ring_stats: - curr = &ring_err_stats.rx_total_l4_csum_errors; - prev = &bp->ring_err_stats_prev.rx_total_l4_csum_errors; -for (i =0 ; i <BNXT_NUM_RING_ERR_STATS ; i++, j++, curr++, prev++) + curr = &ring_drv_stats.rx_total_l4_csum_errors; + prev = &bp->ring_drv_stats_prev.rx_total_l4_csum_errors; +for (i =0 ; i <BNXT_NUM_RING_DRV_STATS ; i++, j++, curr++, prev++) buf[j] = *curr + *prev;if (bp->flags &BNXT_FLAG_PORT_STATS ) {
@@ -752,8 +752,8 @@ static void bnxt_get_strings(struct net_device *dev, u32 stringset, u8 *buf)ethtool_sprintf (&buf,"[%d]: %s" , i, str); } } -for (i =0 ; i <BNXT_NUM_RING_ERR_STATS ; i++) -ethtool_puts (&buf, bnxt_ring_err_stats_arr[i]); +for (i =0 ; i <BNXT_NUM_RING_DRV_STATS ; i++) +ethtool_puts (&buf, bnxt_ring_drv_stats_arr[i]);if (bp->flags &BNXT_FLAG_PORT_STATS )for (i =0 ; i <BNXT_NUM_PORT_STATS ; i++) {
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 897/1611 eth: bnxt: improve the timing of stats
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Jakub Kicinski <[email protected]>
[ Upstream commit 40529e58629baa9ce72143cb46cf1b3d2ca0d465 ]
Kernel selftests wait 1.25x of the promised stats refresh time (as read from ethtool -c). bnxt reports 1sec by default, but the stats update process has two steps. First device DMAs the new values, then the service task performs update in full-width SW counters. So the worst case delay is actually 2x.
Note that the behavior is different for ring stats and port stats. Port stats are fetched synchronously by the service worker, so there's no risk of doubling up the delay there.
The problem of stale stats impacts not only tests but real workloads which monitor egress bandwidth of a NIC. The inaccuracy causes double counting in the next cycle and spurious overload alarms.
Try to read from the DMA buffer more aggressively, to mitigate timing issues between DMA and service task. The SW update should be cheap.
--- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 48 ++++++++++++++++++- drivers/net/ethernet/broadcom/bnxt/bnxt.h | 5 ++ .../net/ethernet/broadcom/bnxt/bnxt_ethtool.c | 1 + 3 files changed, 53 insertions(+), 1 deletion(-)
drivers/net/ethernet/broadcom/bnxt/bnxt.c +47 -1
@@ -10367,7 +10367,7 @@ static void bnxt_accumulate_stats(struct bnxt_stats_mem *stats) stats->hw_masks, stats->len / 8, false); } -static void bnxt_accumulate_all_stats (struct bnxt *bp) +static void bnxt_accumulate_ring_stats (struct bnxt *bp) {struct bnxt_stats_mem *ring0_stats;bool ignore_zero = false;
@@ -10390,6 +10390,10 @@ static void bnxt_accumulate_all_stats(struct bnxt *bp) ring0_stats->hw_masks, ring0_stats->len / 8, ignore_zero); } +} + +static void bnxt_accumulate_port_stats (struct bnxt *bp) +{if (bp->flags &BNXT_FLAG_PORT_STATS ) {struct bnxt_stats_mem *stats = &bp->port_stats;__le64 *hw_stats = stats->hw_stats;
@@ -10412,6 +10416,41 @@ static void bnxt_accumulate_all_stats(struct bnxt *bp) } } +static void bnxt_accumulate_all_stats (struct bnxt *bp) +{ +bnxt_accumulate_ring_stats (bp); +bnxt_accumulate_port_stats (bp); +} + +/* Re-accumulate ring stats from DMA buffers if stale. +* uAPIs for reading sw_stats should call this first. +* +* We promise user space update frequency of bp->stats_coal_ticks but +* the update is a two step process - first device updates the DMA buffer, +* then we have to update from that buffer to driver stats in the service work. +* Worst case we would be 2x off from the desired frequency. +* Sync the stats sooner, if stale. The 20% threshold was chosen arbitrarily. +* +* Ideally we would split the user-configured time into two portions, +* i.e. also lower the DMA period by the 20%. But the DMA timer seems to have +* too coarse granularity to play such tricks. +*/ +void bnxt_sync_ring_stats (struct bnxt *bp) +{ +unsigned long stale; + +if (!netif_running (bp->dev) || !bp->stats_coal_ticks) +return ; + +spin_lock (&bp->stats_lock); + stale =usecs_to_jiffies (bp->stats_coal_ticks /5 ); +if (time_after_eq (jiffies, bp->stats_updated_jiffies + stale)) { +bnxt_accumulate_ring_stats (bp); + bp->stats_updated_jiffies = jiffies; + } +spin_unlock (&bp->stats_lock); +} +static int bnxt_hwrm_port_qstats (struct bnxt *bp,u8 flags) {struct hwrm_port_qstats_input *req;
@@ -13376,6 +13415,7 @@ bnxt_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats)return ; } +bnxt_sync_ring_stats (bp);bnxt_get_ring_stats (bp, stats);bnxt_add_prev_stats (bp, stats);
@@ -14548,7 +14588,10 @@ static void bnxt_sp_task(struct work_struct *work)if (test_and_clear_bit (BNXT_PERIODIC_STATS_SP_EVENT , &bp->sp_event)) {bnxt_hwrm_port_qstats (bp,0 );bnxt_hwrm_port_qstats_ext (bp,0 ); +spin_lock (&bp->stats_lock);bnxt_accumulate_all_stats (bp); + bp->stats_updated_jiffies = jiffies; +spin_unlock (&bp->stats_lock); }if (test_and_clear_bit (BNXT_LINK_CHNG_SP_EVENT , &bp->sp_event)) {
@@ -15279,6 +15322,7 @@ static int bnxt_init_board(struct pci_dev *pdev, struct net_device *dev)INIT_DELAYED_WORK (&bp->fw_reset_task, bnxt_fw_reset_task);spin_lock_init (&bp->ntp_fltr_lock); +spin_lock_init (&bp->stats_lock);#if BITS_PER_LONG ==32 spin_lock_init (&bp->db_lock);#endif
@@ -15837,6 +15881,7 @@ static void bnxt_get_queue_stats_rx(struct net_device *dev, int i,if (!bp->bnapi)return ; +bnxt_sync_ring_stats (bp); cpr = &bp->bnapi[i]->cp_ring; sw = cpr->stats.sw_stats;
@@ -15865,6 +15910,7 @@ static void bnxt_get_queue_stats_tx(struct net_device *dev, int i,if (!bp->tx_ring)return ; +bnxt_sync_ring_stats (bp); bnapi = bp->tx_ring[bp->tx_ring_map[i]].bnapi; sw = bnapi->cp_ring.stats.sw_stats;
drivers/net/ethernet/broadcom/bnxt/bnxt.h +5 -0
@@ -2601,6 +2601,10 @@ struct bnxt {#define BNXT_MIN_STATS_COAL_TICKS 250000#define BNXT_MAX_STATS_COAL_TICKS 1000000 +/* Protects stats_updated_jiffies and writes to sw_stats */ +spinlock_t stats_lock; +unsigned long stats_updated_jiffies; +struct work_struct sp_task;unsigned long sp_event;#define BNXT_RX_MASK_SP_EVENT 0
@@ -2965,6 +2969,7 @@ void bnxt_reenable_sriov(struct bnxt *bp);void bnxt_close_nic (struct bnxt *,bool ,bool );void bnxt_get_ring_drv_stats (struct bnxt *bp,struct bnxt_total_ring_drv_stats *stats); +void bnxt_sync_ring_stats (struct bnxt *bp);bool bnxt_rfs_capable (struct bnxt *bp,bool new_rss_ctx);int bnxt_dbg_hwrm_rd_reg (struct bnxt *bp,u32 reg_off,u16 num_words,u32 *reg_buf);
drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c +1 -0
@@ -605,6 +605,7 @@ static void bnxt_get_ethtool_stats(struct net_device *dev, goto skip_ring_stats; } +bnxt_sync_ring_stats (bp); tpa_stats =bnxt_get_num_tpa_ring_stats (bp);for (i =0 ; i < bp->cp_nr_rings; i++) {struct bnxt_napi *bnapi = bp->bnapi[i];
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 898/1611 ipv4: fib: Dont ignore error route in local/main tables.
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Kuniyuki Iwashima <[email protected]>
[ Upstream commit b72f0db64205d9ce462038ba995d5d31eff32dc1 ]
When CONFIG_IP_MULTIPLE_TABLES is enabled but no rule is added, fib_lookup() performs route lookup directly on two tables.
Since the first lookup does not properly bail out, the result of an error route in the merged local/main table could be overwritten by another route in the default table:
# unshare -n
# ip link set lo up
# ip route add 192.168.0.0/24 dev lo table 253
# ip route add unreachable 192.168.0.0/24
# ip route get 192.168.0.1
192.168.0.1 dev lo table default uid 0
cache <local>Once a random rule is added, the error route is respected:
# ip rule add table 0 # ip rule del table 0 # ip route get 192.168.0.1 RTNETLINK answers: No route to host
Let's fix the inconsistent behaviour.
--- include/net/ip_fib.h | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-)
include/net/ip_fib.h +3 -4
@@ -375,7 +375,7 @@ static inline int fib_lookup(struct net *net, struct flowi4 *flp, struct fib_result *res, unsigned int flags) {struct fib_table *tb; -int err = -ENETUNREACH ; +int err = -EAGAIN ; flags |=FIB_LOOKUP_NOREF ;if (net->ipv4.fib_has_custom_rules)
@@ -389,17 +389,16 @@ static inline int fib_lookup(struct net *net, struct flowi4 *flp,if (tb) err =fib_table_lookup (tb, flp, res, flags); -if (!err) +if (err != -EAGAIN ) goto out; tb =rcu_dereference_rtnl (net->ipv4.fib_default);if (tb) err =fib_table_lookup (tb, flp, res, flags); -out:if (err == -EAGAIN ) err = -ENETUNREACH ; - +out:rcu_read_unlock ();return err;
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 899/1611 md/raid5: use stripe state snapshot in break_stripe_batch_list()
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Chen Cheng <[email protected]>
[ Upstream commit 9b249f5ffbeda24c57e6c56ed896c5ca4fc70549 ]
The patch just suppress KCSAN noise. No functional change.
RAID-5 can group multi full-stripe-write aka stripe_head into a batch aka batch_list, with one head_sh leading them. Call break_stripe_batch_list() when the batch is finished, or, a stripe has to be dropped out of the batch.
break_stripe_batch_list() reads stripe state several times while request paths can update thost state words concurrently with lockless bitops, which reported by KCSAN.
Use a snapshot to guarantees that the value used for warning, copying, and handle checks is internally consistent at current read moment.
KCSAN report:
==============================================
BUG: KCSAN: data-race in __add_stripe_bio / break_stripe_batch_list
write (marked) to 0xffff8e89d4f0b988 of 8 bytes by task 4323 on cpu 3:
__add_stripe_bio+0x35e/0x400 raid5_make_request+0x6ac/0x2930 md_handle_request+0x4a2/0xa40 md_submit_bio+0x109/0x1a0 __submit_bio+0x2ec/0x390 submit_bio_noacct_nocheck+0x457/0x710 submit_bio_noacct+0x2a7/0xc20 submit_bio+0x56/0x250 blkdev_direct_IO+0x54c/0xda0 blkdev_write_iter+0x38f/0x570 aio_write+0x22b/0x490 io_submit_one+0xa51/0xf70
read to 0xffff8e89d4f0b988 of 8 bytes by task 4290 on cpu 4:
break_stripe_batch_list+0x3ce/0x480 handle_stripe_clean_event+0x720/0x9b0 handle_stripe+0x32fb/0x4500 handle_active_stripes.isra.0+0x6e0/0xa50 raid5d+0x7e0/0xba0
Stable-dep-of: 55b77337bdd0 ("md/raid5: avoid R5_Overlap races while breaking stripe batches")
--- drivers/md/raid5.c | 45 ++++++++++++++++++++++++++------------------- 1 file changed, 26 insertions(+), 19 deletions(-)
drivers/md/raid5.c +26 -19
@@ -4853,31 +4853,35 @@ static void break_stripe_batch_list(struct stripe_head *head_sh, {struct stripe_head *sh, *next;int i; +unsigned long state;list_for_each_entry_safe (sh, next, &head_sh->batch_list, batch_list) {list_del_init (&sh->batch_list); -WARN_ONCE (sh->state & ((1 <<STRIPE_ACTIVE ) | - (1 <<STRIPE_SYNCING ) | - (1 <<STRIPE_REPLACED ) | - (1 <<STRIPE_DELAYED ) | - (1 <<STRIPE_BIT_DELAY ) | - (1 <<STRIPE_FULL_WRITE ) | - (1 <<STRIPE_BIOFILL_RUN ) | - (1 <<STRIPE_COMPUTE_RUN ) | - (1 <<STRIPE_DISCARD ) | - (1 <<STRIPE_BATCH_READY ) | - (1 <<STRIPE_BATCH_ERR )), -"stripe state: %lx\n" , sh->state); -WARN_ONCE (head_sh->state & ((1 <<STRIPE_DISCARD ) | - (1 <<STRIPE_REPLACED )), -"head stripe state: %lx\n" , head_sh->state); + state =READ_ONCE (sh->state); +WARN_ONCE (state & ((1 <<STRIPE_ACTIVE ) | + (1 <<STRIPE_SYNCING ) | + (1 <<STRIPE_REPLACED ) | + (1 <<STRIPE_DELAYED ) | + (1 <<STRIPE_BIT_DELAY ) | + (1 <<STRIPE_FULL_WRITE ) | + (1 <<STRIPE_BIOFILL_RUN ) | + (1 <<STRIPE_COMPUTE_RUN ) | + (1 <<STRIPE_DISCARD ) | + (1 <<STRIPE_BATCH_READY ) | + (1 <<STRIPE_BATCH_ERR )), +"stripe state: %lx\n" , state); + + state =READ_ONCE (head_sh->state); +WARN_ONCE (state & ((1 <<STRIPE_DISCARD ) | + (1 <<STRIPE_REPLACED )), +"head stripe state: %lx\n" , state);set_mask_bits (&sh->state, ~(STRIPE_EXPAND_SYNC_FLAGS | (1 <<STRIPE_PREREAD_ACTIVE ) | (1 <<STRIPE_ON_UNPLUG_LIST )), - head_sh->state & (1 <<STRIPE_INSYNC )); + state & (1 <<STRIPE_INSYNC )); sh->check_state = head_sh->check_state; sh->reconstruct_state = head_sh->reconstruct_state;
@@ -4890,8 +4894,9 @@ static void break_stripe_batch_list(struct stripe_head *head_sh, sh->dev[i].flags = head_sh->dev[i].flags & (~((1 << R5_WriteError) | (1 << R5_Overlap))); } -if (handle_flags ==0 || - sh->state & handle_flags) + + state =READ_ONCE (sh->state); +if (handle_flags ==0 || (state & handle_flags))set_bit (STRIPE_HANDLE , &sh->state);raid5_release_stripe (sh); }
@@ -4901,7 +4906,9 @@ static void break_stripe_batch_list(struct stripe_head *head_sh,for (i =0 ; i < head_sh->disks; i++)if (test_and_clear_bit (R5_Overlap, &head_sh->dev[i].flags))wake_up_bit (&head_sh->dev[i].flags, R5_Overlap); -if (head_sh->state & handle_flags) + + state =READ_ONCE (head_sh->state); +if (state & handle_flags)set_bit (STRIPE_HANDLE , &head_sh->state); }
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 900/1611 md/raid5: avoid R5_Overlap races while breaking stripe batches
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Chen Cheng <[email protected]>
[ Upstream commit 55b77337bdd088c77461588e5ec094421b89911b ]
KCSAN report a race in break_stripe_batch_list() vs. raid5_make_request() on sh->dev[i].flags (plain word write vs. atomic bit op)..
and .. one possible scenario is:
CPU1 CPU2break_stripe_batch_list(sh1)
-> handle sh2
-> lock(sh2)
-> sh2->batch_head = NULL
-> unlock(sh2)
-> test_and_clear_bit(R5_Overlap, sh2->dev[i].flags) -> wake_up_bit(sh2->dev[i].flags)
raid5_make_request()
-> add_all_stripe_bios(sh2)
-> lock(sh2)
-> stripe_bio_overlaps(sh2) returns true
batch_head is NULL, so new bio overlap
exist bio on sh2 -> true
-> set_bit(R5_Overlap, sh2->dev[i].flags)
-> unlock(sh2)
-> wait_on_bit(sh2->dev[i].flags)-> sh2->dev[i].flags = sh1->dev[i].flags & ~R5_Overlap
No wait_up_bit(), CPU2 could be wait_on_bit() forever...
Fix by :
- Expand the protect zone.
- Use batch_head's device flag's snaphot when no held head_sh->stripe_lock.
- Move sh/head_sh->batch_head = NULL to the end of protected zone , and , any concurrent add_all_stripe_bios() grabs sh->stripe_lock now either:
- see batch_head != null, and , is rejected by stripe_bio_overlaps() under the lock (no R5_Overlap wait ) , or ,
- sees batch_head == NULL, only after dev[i].flags has already been set and the prior R5_Overlap waiters worken.
KCSAN report:
================================================
BUG: KCSAN: data-race in break_stripe_batch_list / raid5_make_request
write (marked) to 0xffff8e89c8117548 of 8 bytes by task 4042 on cpu 0:
raid5_make_request+0xea0/0x2930
md_handle_request+0x4a2/0xa40
md_submit_bio+0x109/0x1a0
__submit_bio+0x2ec/0x390
submit_bio_noacct_nocheck+0x457/0x710
submit_bio_noacct+0x2a7/0xc20
submit_bio+0x56/0x250
blkdev_direct_IO+0x54c/0xda0
blkdev_write_iter+0x38f/0x570
aio_write+0x22b/0x490
io_submit_one+0xa51/0xf70
__x64_sys_io_submit+0xf7/0x220
x64_sys_call+0x1907/0x1c60
do_syscall_64+0x130/0x570
entry_SYSCALL_64_after_hwframe+0x76/0x7e read to 0xffff8e89c8117548 of 8 bytes by task 4010 on cpu 5:
break_stripe_batch_list+0x249/0x480
handle_stripe_clean_event+0x720/0x9b0
handle_stripe+0x32fb/0x4500
handle_active_stripes.isra.0+0x6e0/0xa50
raid5d+0x7e0/0xba0
md_thread+0x15a/0x2d0
kthread+0x1e3/0x220
ret_from_fork+0x37a/0x410
ret_from_fork_asm+0x1a/0x30 value changed: 0x0000000000000019 -> 0x0000000000000099 --> R5_Overlap
--- drivers/md/raid5.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-)
drivers/md/raid5.c +5 -5
@@ -4886,14 +4886,14 @@ static void break_stripe_batch_list(struct stripe_head *head_sh, sh->check_state = head_sh->check_state; sh->reconstruct_state = head_sh->reconstruct_state;spin_lock_irq (&sh->stripe_lock); - sh->batch_head =NULL ; -spin_unlock_irq (&sh->stripe_lock);for (i =0 ; i < sh->disks; i++) {if (test_and_clear_bit (R5_Overlap, &sh->dev[i].flags))wake_up_bit (&sh->dev[i].flags, R5_Overlap); - sh->dev[i].flags = head_sh->dev[i].flags & + sh->dev[i].flags =READ_ONCE (head_sh->dev[i].flags) & (~((1 << R5_WriteError) | (1 << R5_Overlap))); } + sh->batch_head =NULL ; +spin_unlock_irq (&sh->stripe_lock); state =READ_ONCE (sh->state);if (handle_flags ==0 || (state & handle_flags))
@@ -4901,11 +4901,11 @@ static void break_stripe_batch_list(struct stripe_head *head_sh,raid5_release_stripe (sh); }spin_lock_irq (&head_sh->stripe_lock); - head_sh->batch_head =NULL ; -spin_unlock_irq (&head_sh->stripe_lock);for (i =0 ; i < head_sh->disks; i++)if (test_and_clear_bit (R5_Overlap, &head_sh->dev[i].flags))wake_up_bit (&head_sh->dev[i].flags, R5_Overlap); + head_sh->batch_head =NULL ; +spin_unlock_irq (&head_sh->stripe_lock); state =READ_ONCE (head_sh->state);if (state & handle_flags)
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 901/1611 bpf: Disable xfrm_decode_session hook attachment
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Bradley Morgan <[email protected]>
[ Upstream commit 12091470c6b4c1c14b2de12dcbae2ada6cb6d20b ]
BPF LSM programs can currently attach to xfrm_decode_session(). That hook may return an error, but security_skb_classify_flow() calls it from a void path and triggers BUG_ON() if an error is returned.
Disable BPF attachment to the hook to prevent a BPF LSM program from turning packet classification into a full panic.
--- kernel/bpf/bpf_lsm.c | 3 +++ 1 file changed, 3 insertions(+)
kernel/bpf/bpf_lsm.c +3 -0
@@ -50,6 +50,9 @@ BTF_ID(func, bpf_lsm_key_getsecurity)#ifdef CONFIG_AUDIT BTF_ID(func, bpf_lsm_audit_rule_match)#endif +#ifdef CONFIG_SECURITY_NETWORK_XFRM +BTF_ID(func, bpf_lsm_xfrm_decode_session) +#endif BTF_ID(func, bpf_lsm_ismaclabel)BTF_SET_END (bpf_lsm_disabled_hooks)
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 902/1611 netfilter: nf_nat: avoid invalid nat_net pointer use on failed nf_nat_init()
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Mathias Krause <[email protected]>
[ Upstream commit 069cfe3de2a5e16069485893cd04665ab769c1d8 ]
We ran into below KASAN splat, which is mostly uninteresting, beside for having nf_nat_register_fn() in the call chain as a cause for the offending access:
==================================================================
BUG: KASAN: slab-out-of-bounds in nf_nat_register_fn+0x5f9/0x640 Read of size 8 at addr ffff890031e54c20 by task iptables/9510 CPU: 0 UID: 0 PID: 9510 Comm: iptables Not tainted 6.18.18-grsec-full-20260320181326 #1 PREEMPT(voluntary) Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.16.3-debian-1.16.3-2 04/01/2014 Call Trace: <TASK> […] dump_stack_lvl+0xee/0x160 ffff88004117eeb8 […] print_report+0x6e/0x640 ffff88004117eee0 […] ? __phys_addr+0x8e/0x140 ffff88004117eef0 […] ? kasan_addr_to_slab+0x51/0xe0 ffff88004117ef08 […] ? complete_report_info+0xec/0x1c0 ffff88004117ef20 […] ? nf_nat_register_fn+0x5f9/0x640 ffff88004117ef48 […] kasan_report+0xbc/0x140 ffff88004117ef50 […] ? nf_nat_register_fn+0x5f9/0x640 ffff88004117ef90 […] nf_nat_register_fn+0x5f9/0x640 ffff88004117eff8 […] ? nf_nat_icmp_reply_translation+0x6e0/0x6e0 ffff88004117f070 […] nf_tables_register_hook.part.0+0xa0/0x220 ffff88004117f080 […] nf_tables_addchain.constprop.0+0x1054/0x1fc0 ffff88004117f0b8 […] ? nft_chain_lookup.part.0+0x4ce/0xac0 ffff88004117f130 […] ? nf_tables_abort+0x3d80/0x3d80 ffff88004117f190 […] ? nf_tables_dumpreset_obj+0x100/0x100 ffff88004117f1c8 […] ? nft_table_lookup.part.0+0x255/0x300 ffff88004117f310 […] ? nf_tables_newchain+0x21a4/0x2fa0 ffff88004117f358 […] nf_tables_newchain+0x21a4/0x2fa0 ffff88004117f360 […] ? nf_tables_addchain.constprop.0+0x1fc0/0x1fc0 ffff88004117f458 […] ? nla_get_range_signed+0x4a0/0x4a0 ffff88004117f488 […] ? lock_acquire+0x16f/0x320 ffff88004117f490 […] ? find_held_lock+0x3b/0xe0 ffff88004117f4b0 […] ? __nla_parse+0x45/0x80 ffff88004117f500 […] nfnetlink_rcv_batch+0xbca/0x19a0 ffff88004117f550 […] ? nfnetlink_net_exit_batch+0x120/0x120 ffff88004117f618 […] ? __sanitizer_cov_trace_switch+0x63/0xe0 ffff88004117f720 […] ? gr_acl_handle_mmap+0x1c4/0x320 ffff88004117f7c0 […] ? nla_get_range_signed+0x4a0/0x4a0 ffff88004117f7e8 […] ? gr_is_capable+0x6f/0xe0 ffff88004117f830 […] ? __nla_parse+0x45/0x80 ffff88004117f860 […] ? skb_pull+0x103/0x1a0 ffff88004117f880 […] nfnetlink_rcv+0x3db/0x4a0 ffff88004117f8b0 […] ? nfnetlink_rcv_batch+0x19a0/0x19a0 ffff88004117f8d8 […] ? netlink_lookup+0xe2/0x240 ffff88004117f900 […] netlink_unicast+0x74b/0xb00 ffff88004117f930 […] ? netlink_attachskb+0xb20/0xb20 ffff88004117f980 […] ? __check_object_size+0x3e/0xaa0 ffff88004117f998 […] ? security_netlink_send+0x51/0x160 ffff88004117f9c8 […] netlink_sendmsg+0xa03/0x1200 ffff88004117f9f8 […] ? netlink_unicast+0xb00/0xb00 ffff88004117fa70 […] ? netlink_unicast+0xb00/0xb00 ffff88004117fac8 […] ? ____sys_sendmsg+0xe2a/0x1040 ffff88004117faf8 […] ____sys_sendmsg+0xe2a/0x1040 ffff88004117fb00 […] ? kernel_recvmsg+0x300/0x300 ffff88004117fb60 […] ? reacquire_held_locks+0xe9/0x260 ffff88004117fbc8 […] ___sys_sendmsg+0x138/0x200 ffff88004117fbf8 […] ? do_recvmmsg+0x7e0/0x7e0 ffff88004117fc30 […] ? lockdep_hardirqs_on_prepare+0x101/0x1e0 ffff88004117fc50 […] ? lock_acquire+0x16f/0x320 ffff88004117fd20 […] ? lock_acquire+0x16f/0x320 ffff88004117fd58 […] ? find_held_lock+0x3b/0xe0 ffff88004117fd70 […] __sys_sendmsg+0x17a/0x260 ffff88004117fdc8 […] ? __sys_sendmsg_sock+0x80/0x80 ffff88004117fdf0 […] ? syscall_trace_enter+0x15e/0x2c0 ffff88004117fe98 […] do_syscall_64+0x7d/0x400 ffff88004117fec8 […] entry_SYSCALL_64_safe_stack+0x4a/0x60 ffff88004117fef8 </TASK> ==================================================================
The out-of-bounds report, though, is a red herring as it is for an access that shouldn't have happened in the first place.
When nf_nat_init() fails to register its BPF kfuncs, it'll unwind and, among others, call unregister_pernet_subsys() to deregister its per-net ops. This makes the previously allocated net id available for reuse by the next caller of register_pernet_subsys(), in our case, synproxy. However, 'nat_net_id' will still hold the previously allocated value.
If nf_nat.o gets build as a module, all this doesn't matter. A failed initialization routine makes the module fail to load and any dependent module won't be able to load either. However, if nf_nat.o is built-in, a failing init won't /completely/ make its functionality unavailable to dependent modules, namely the code and static data is still there, free to be called by modules like nft_chain_nat.ko.
Case in point, nft_chain_nat registers hooks that'll call into nf_nat which, in our case, failed to initialize and therefore won't have a valid net id nor related net_nat object any more.
Code in nf_nat, namely nf_nat_register_fn() and nf_nat_unregister_fn(), still making use of the reallocated net id, lead to a type confusion as the call to net_generic() will no longer return memory belonging to an object suited to fit 'struct nat_net' but 'struct synproxy_net' instead. The latter is only 24 bytes on 64-bit systems, much smaller than struct nat_net which is 176 bytes, perfectly explaining the OOB KASAN report.
Detect and handle a failed nf_nat_init() by testing the 'nf_nat_hook' pointer which will be reset to NULL on initialization errors to prevent the usage of an invalid nat_net pointer.
As this check is only needed when nf_nat.o is built-in, guard it by '#ifndef MODULE...'.
--- net/netfilter/nf_nat_core.c | 10 ++++++++++ 1 file changed, 10 insertions(+)
net/netfilter/nf_nat_core.c +10 -0
@@ -1187,6 +1187,16 @@ int nf_nat_register_fn(struct net *net, u8 pf, const struct nf_hook_ops *ops,struct nf_hook_ops *nat_ops;int i, ret; +#ifndef MODULE +/* If nf_nat_core is built-in and nf_nat_init() fails, dependent +* modules like nft_chain_nat.ko may still call this function. +* However, nat_net would be invalid, likely pointing to some other +* per-net structure. +*/ +if (WARN_ON_ONCE (!nf_nat_hook)) +return -EOPNOTSUPP ; +#endif +if (WARN_ON_ONCE (pf >=ARRAY_SIZE (nat_net->nat_proto_net)))return -EINVAL ;
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 903/1611 netfilter: nf_conncount: prevent connlimit drops for early confirmed ct
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Fernando Fernandez Mancera <[email protected]>
[ Upstream commit c8b6f36f766991e3ebebec6596daee4b04dcbc49 ]
Commit 69894e5b4c5e ("netfilter: nft_connlimit: update the count if add was skipped") introduced a regression where packets for valid connections are dropped when using connlimit for soft-limiting scenarios.
The issue occurs when a new connection reuses a socket currently in the TIME_WAIT state. In this scenario, the connection tracking entry is evaluated as already confirmed. Previously, __nf_conncount_add() assumed that if a connection was confirmed and did not originate from the loopback interface, it should skip the addition and return -EEXIST.
Skipping the addition triggers a garbage collection run that cleans up the TIME_WAIT connection. Consequently, the active connection count drops to 0, which xt_connlimit mishandles, leading to the false rejection of the perfectly valid new connection.
Fix this by replacing the interface check with protocol-agnostic state checks. We now skip the tree insertion and preserve the lockless garbage collection optimization only if the connection is IPS_ASSURED. This allows early-confirmed setup packets (such as reused TIME_WAIT sockets or locally generated SYN-ACKs) to be properly evaluated and counted without falsely dropping. The goto check_connections path is maintained to ensure these setup packets are deduplicated correctly.
This has been tested with slowhttptest and HTTP server configured locally to ensure we are not breaking soft-limiting scenarios for local or external connections. In addition, it was tested with a OVS zone limit too.
--- net/netfilter/nf_conncount.c | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-)
net/netfilter/nf_conncount.c +5 -6
@@ -179,17 +179,16 @@ static int __nf_conncount_add(struct net *net,return -ENOENT ;if (ct &&nf_ct_is_confirmed (ct)) { -/* local connections are confirmed in postrouting so confirmation -* might have happened before hitting connlimit +/* Connection is confirmed but might still be in the setup phase. +* Only skip the tracking if it is fully assured. This guarantees +* that setup packets or retransmissions are properly counted and +* deduplicated. */ -if (skb->skb_iif !=LOOPBACK_IFINDEX ) { +if (test_bit (IPS_ASSURED_BIT , &ct->status)) { err = -EEXIST ; goto out_put; } -/* this is likely a local connection, skip optimization to avoid -* adding duplicates from a 'packet train' -*/ goto check_connections; }
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 904/1611 netfilter: nft_synproxy: stop bypassing the priv->info snapshot
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Runyu Xiao <[email protected]>
[ Upstream commit 11d4bc4e26fb66040a5b5d95e9abf37deac2b1fc ]
nft_synproxy_eval_v4() and nft_synproxy_eval_v6() already take a whole-object READ_ONCE() snapshot of the shared priv->info state before building the SYNACK reply, but nft_synproxy_tcp_options() still masks opts->options with priv->info.options from the live shared object.
When a named synproxy object is updated concurrently with SYN traffic, the eval path can then mix mss and timestamp handling from the local snapshot with an options mask taken from a newer configuration, so one SYNACK no longer reflects a coherent synproxy configuration.
Use info->options so nft_synproxy_tcp_options() stays on the same local snapshot that the eval path already copied from priv->info.
--- net/netfilter/nft_synproxy.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-)
net/netfilter/nft_synproxy.c +4 -5
@@ -23,14 +23,13 @@ static const struct nla_policy nft_synproxy_policy[NFTA_SYNPROXY_MAX + 1] = {static void nft_synproxy_tcp_options (struct synproxy_options *opts,const struct tcphdr *tcp,struct synproxy_net *snet, -struct nf_synproxy_info *info, -const struct nft_synproxy *priv) +struct nf_synproxy_info *info) {this_cpu_inc (snet->stats->syn_received);if (tcp->ece && tcp->cwr) opts->options |=NF_SYNPROXY_OPT_ECN ; - opts->options &= priv->info.options; + opts->options &= info->options; opts->mss_encode = opts->mss_option; opts->mss_option = info->mss;if (opts->options &NF_SYNPROXY_OPT_TIMESTAMP )
@@ -55,7 +54,7 @@ static void nft_synproxy_eval_v4(const struct nft_synproxy *priv,if (tcp->syn) {/* Initial SYN from client */ -nft_synproxy_tcp_options (opts, tcp, snet, &info, priv); +nft_synproxy_tcp_options (opts, tcp, snet, &info);synproxy_send_client_synack (net, skb, tcp, opts);consume_skb (skb); regs->verdict.code =NF_STOLEN ;
@@ -86,7 +85,7 @@ static void nft_synproxy_eval_v6(const struct nft_synproxy *priv,if (tcp->syn) {/* Initial SYN from client */ -nft_synproxy_tcp_options (opts, tcp, snet, &info, priv); +nft_synproxy_tcp_options (opts, tcp, snet, &info);synproxy_send_client_synack_ipv6 (net, skb, tcp, opts);consume_skb (skb); regs->verdict.code =NF_STOLEN ;
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 905/1611 netfilter: nft_compat: ebtables emulation must reject non-bridge targets
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Florian Westphal <[email protected]>
[ Upstream commit 9dbba7e694ec045f21ede2f892fb42b81b4e1692 ]
xtables targets return netfilter verdicts: NF_ACCEPT, NF_DROP, and so on. ebtables targets return incompatible verdicts: EBT_ACCEPT,EBT_DROP, ... We cannot allow fallback to NFPROTO_UNSPEC.
ebtables doesn't permit this since11ff7288beb2 ("netfilter: ebtables: reject non-bridge targets") but that commit missed the nft_compat layer.
--- net/netfilter/nft_compat.c | 24 +++++++++++++++++++++--- 1 file changed, 21 insertions(+), 3 deletions(-)
net/netfilter/nft_compat.c +21 -3
@@ -389,6 +389,22 @@ static int nft_target_validate(const struct nft_ctx *ctx,return 0 ; } +static int nft_target_bridge_validate (const struct nft_ctx *ctx, +const struct nft_expr *expr) +{ +struct xt_target *target = expr->ops->data; + +/* Do not allow UNSPEC to stand-in for NFPROTO_BRIDGE +* targets: they are incompatible. ebtables targets return +* EBT_ACCEPT, DROP and so on which are not compatible with +* NF_ACCEPT, NF_DROP and so on. +*/ +if (target->family !=NFPROTO_BRIDGE ) +return -ENOENT ; + +return nft_target_validate (ctx, expr); +} + static void __nft_match_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt,
@@ -916,14 +932,16 @@ nft_target_select_ops(const struct nft_ctx *ctx, ops->init = nft_target_init; ops->destroy = nft_target_destroy; ops->dump = nft_target_dump; - ops->validate = nft_target_validate; ops->data = target; ops->reduce =NFT_REDUCE_READONLY ; -if (family ==NFPROTO_BRIDGE ) +if (family ==NFPROTO_BRIDGE ) { ops->eval = nft_target_eval_bridge; -else + ops->validate = nft_target_bridge_validate; + }else { ops->eval = nft_target_eval_xt; + ops->validate = nft_target_validate; + }return ops; err:
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 906/1611 gpio: davinci: fix IRQ domain leak on devm_kzalloc failure
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Qingshuang Fu <[email protected]>
[ Upstream commit 4e8eb6952aa6749726c6c3763ae0032a6332c24f ]
In davinci_gpio_irq_setup(), after successfully creating an IRQ domain with irq_domain_create_legacy(), a subsequent devm_kzalloc() failure in the bank loop causes the function to return -ENOMEM without removing the IRQ domain.
Unlike devm-managed resources, irq_domain_create_legacy() does not auto-clean up on probe failure, so the domain is leaked.
Fix by calling irq_domain_remove() before returning on allocation failure.
--- drivers/gpio/gpio-davinci.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)
drivers/gpio/gpio-davinci.c +3 -1
@@ -550,8 +550,10 @@ static int davinci_gpio_irq_setup(struct platform_device *pdev)sizeof (struct davinci_gpio_irq_data ), GFP_KERNEL); -if (!irqdata) +if (!irqdata) { +irq_domain_remove (chips->irq_domain);return -ENOMEM ; + } irqdata->regs = g; irqdata->bank_num = bank;
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 907/1611 NTB: epf: Make db_valid_mask cover only real doorbell bits
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Koichiro Den <[email protected]>
[ Upstream commit 6eb7e28f1f24a28234add38755687a7ed8bc2654 ]
ndev->db_count includes an unused doorbell slot due to the legacy extra offset in the peer doorbell path. db_valid_mask must cover only the real doorbell bits and exclude the unused slot.
Set db_valid_mask to BIT_ULL(db_count - 1) - 1.
--- drivers/ntb/hw/epf/ntb_hw_epf.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-)
drivers/ntb/hw/epf/ntb_hw_epf.c +5 -1
@@ -560,7 +560,11 @@ static int ntb_epf_init_dev(struct ntb_epf_dev *ndev)return ret; } - ndev->db_valid_mask =BIT_ULL (ndev->db_count) -1 ; +/* +* ndev->db_count includes an extra skipped slot due to the legacy +* doorbell layout, hence -1. +*/ + ndev->db_valid_mask =BIT_ULL (ndev->db_count -1 ) -1 ; ndev->mw_count =readl (ndev->ctrl_reg +NTB_EPF_MW_COUNT ); ndev->spad_count =readl (ndev->ctrl_reg +NTB_EPF_SPAD_COUNT );
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 908/1611 NTB: epf: Report 0-based doorbell vector via ntb_db_event()
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Koichiro Den <[email protected]>
[ Upstream commit 3147f0964cecca15e349cbfbdd6a28eb6d50379d ]
ntb_db_event() expects the vector number to be relative to the first doorbell vector starting at 0.
Vector 0 is reserved for link events in the EPF driver, so doorbells start at vector 1. However, both supported peers (ntb_hw_epf with pci-epf-ntb, and pci-epf-vntb) have historically skipped vector 1 and started doorbells at vector 2.
Pass (irq_no - 2) to ntb_db_event() so doorbells are reported as 0..N-1. If irq_no == 1 is ever observed, warn and ignore it, since the slot is reserved in the legacy layout and reporting it as DB#0 would collide with the real DB#0 slot.
--- drivers/ntb/hw/epf/ntb_hw_epf.c | 16 +++++++++++++--- 1 file changed, 13 insertions(+), 3 deletions(-)
drivers/ntb/hw/epf/ntb_hw_epf.c +13 -3
@@ -69,6 +69,12 @@ enum epf_ntb_bar { NTB_BAR_NUM, }; +enum epf_irq_slot { +EPF_IRQ_LINK =0 , +EPF_IRQ_RESERVED_DB ,/* Historically skipped slot */ +EPF_IRQ_DB_START , +}; +#define NTB_EPF_MAX_MW_COUNT (NTB_BAR_NUM - BAR_MW1)struct ntb_epf_dev {
@@ -322,10 +328,14 @@ static irqreturn_t ntb_epf_vec_isr(int irq, void *dev) irq_no = irq - ndev->irq_base; ndev->db_val = irq_no +1 ; -if (irq_no ==0 ) +if (irq_no ==EPF_IRQ_LINK ) {ntb_link_event (&ndev->ntb); -else -ntb_db_event (&ndev->ntb, irq_no); + }else if (irq_no ==EPF_IRQ_RESERVED_DB ) { +dev_warn_ratelimited (ndev->dev, +"Unexpected reserved doorbell slot IRQ received\n" ); + }else { +ntb_db_event (&ndev->ntb, irq_no -EPF_IRQ_DB_START ); + }return IRQ_HANDLED ; }
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 909/1611 NTB: epf: Fix doorbell bitmask and IRQ vector handling
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Koichiro Den <[email protected]>
[ Upstream commit 4fdea8dbb62d746429498e07385a3ba0b0f6d1ab ]
The EPF driver currently stores the incoming doorbell as a vector number (irq_no + 1) in db_val and db_clear() clears all bits unconditionally. This breaks db_read()/db_clear() semantics when multiple doorbells are used.
Store doorbells as a bitmask (BIT_ULL(vector)) and make db_clear(db_bits) clear only the specified bits. Use atomic64 operations as db_val is updated from interrupt context.
Once db_val is stored as a bitmask, the ISR's doorbell vector is used not only for ntb_db_event(), but also as the bit index for BIT_ULL(). The existing ISR derives that vector by subtracting pci_irq_vector(pdev,
0) from the Linux IRQ number passed to the handler, but Linux IRQ numbers are not guaranteed to be contiguous.
Pass per-vector context as request_irq() dev_id instead, so the ISR gets the device vector directly.
Validate the doorbell vector before updating db_val or calling ntb_db_event(), so an unexpected vector cannot create an invalid shift or be reported to NTB clients.
While at it, read and validate mw_count before requesting interrupt vectors. An unsupported memory-window count does not need IRQs, and failing before ntb_epf_init_isr() keeps the probe error path simple.
--- drivers/ntb/hw/epf/ntb_hw_epf.c | 61 +++++++++++++++++++++------------ 1 file changed, 39 insertions(+), 22 deletions(-)
drivers/ntb/hw/epf/ntb_hw_epf.c +39 -22
@@ -6,6 +6,7 @@* Author: Kishon Vijay Abraham I <[email protected]> */ +#include <linux/atomic.h> #include <linux/delay.h> #include <linux/module.h> #include <linux/pci.h>
@@ -77,6 +78,13 @@ enum epf_irq_slot {#define NTB_EPF_MAX_MW_COUNT (NTB_BAR_NUM - BAR_MW1) +struct ntb_epf_dev ; + +struct ntb_epf_irq_ctx { +struct ntb_epf_dev *ndev; +unsigned int irq_no; +}; +struct ntb_epf_dev {struct ntb_dev ntb;struct device *dev;
@@ -96,9 +104,9 @@ struct ntb_epf_dev {unsigned int self_spad;unsigned int peer_spad; -int db_val; +atomic64_t db_val;u64 db_valid_mask; -int irq_base; +struct ntb_epf_irq_ctx irq_ctx[NTB_EPF_MAX_DB_COUNT +1 ]; };#define ntb_ndev (__ntb) container_of(__ntb, struct ntb_epf_dev, ntb)
@@ -322,11 +330,10 @@ static int ntb_epf_link_disable(struct ntb_dev *ntb)static irqreturn_t ntb_epf_vec_isr (int irq,void *dev) { -struct ntb_epf_dev *ndev = dev; -int irq_no; - - irq_no = irq - ndev->irq_base; - ndev->db_val = irq_no +1 ; +struct ntb_epf_irq_ctx *ctx = dev; +struct ntb_epf_dev *ndev = ctx->ndev; +unsigned int db_vector; +unsigned int irq_no = ctx->irq_no;if (irq_no ==EPF_IRQ_LINK ) {ntb_link_event (&ndev->ntb);
@@ -334,7 +341,17 @@ static irqreturn_t ntb_epf_vec_isr(int irq, void *dev)dev_warn_ratelimited (ndev->dev,"Unexpected reserved doorbell slot IRQ received\n" ); }else { -ntb_db_event (&ndev->ntb, irq_no -EPF_IRQ_DB_START ); + db_vector = irq_no -EPF_IRQ_DB_START ; +if (ndev->db_count <NTB_EPF_MIN_DB_COUNT || + db_vector >= ndev->db_count -1 ) { +dev_warn_ratelimited (ndev->dev, +"Unexpected doorbell vector %u (db_count %u)\n" , + db_vector, ndev->db_count); +return IRQ_HANDLED ; + } + +atomic64_or (BIT_ULL (db_vector), &ndev->db_val); +ntb_db_event (&ndev->ntb, db_vector); }return IRQ_HANDLED ;
@@ -361,18 +378,18 @@ static int ntb_epf_init_isr(struct ntb_epf_dev *ndev, int msi_min, int msi_max) argument &= ~MSIX_ENABLE ; } - ndev->irq_base =pci_irq_vector (pdev,0 ); + ndev->db_count = irq -1 ;for (i =0 ; i < irq; i++) { + ndev->irq_ctx[i].ndev = ndev; + ndev->irq_ctx[i].irq_no = i; ret =request_irq (pci_irq_vector (pdev, i), ntb_epf_vec_isr, -0 ,"ntb_epf" , ndev); +0 ,"ntb_epf" , &ndev->irq_ctx[i]);if (ret) {dev_err (dev,"Failed to request irq\n" ); goto err_free_irq; } } - ndev->db_count = irq -1 ; - ret =ntb_epf_send_command (ndev,CMD_CONFIGURE_DOORBELL , argument | irq);if (ret) {
@@ -384,7 +401,7 @@ static int ntb_epf_init_isr(struct ntb_epf_dev *ndev, int msi_min, int msi_max) err_free_irq:while (i--) -free_irq (pci_irq_vector (pdev, i), ndev); +free_irq (pci_irq_vector (pdev, i), &ndev->irq_ctx[i]);pci_free_irq_vectors (pdev);return ret;
@@ -509,7 +526,7 @@ static u64 ntb_epf_db_read(struct ntb_dev *ntb) {struct ntb_epf_dev *ndev =ntb_ndev (ntb); -return ndev->db_val; +return atomic64_read (&ndev->db_val); }static int ntb_epf_db_clear_mask (struct ntb_dev *ntb,u64 db_bits)
@@ -521,7 +538,7 @@ static int ntb_epf_db_clear(struct ntb_dev *ntb, u64 db_bits) {struct ntb_epf_dev *ndev =ntb_ndev (ntb); - ndev->db_val =0 ; +atomic64_and (~db_bits, &ndev->db_val);return 0 ; }
@@ -562,6 +579,12 @@ static int ntb_epf_init_dev(struct ntb_epf_dev *ndev)struct device *dev = ndev->dev;int ret; + ndev->mw_count =readl (ndev->ctrl_reg +NTB_EPF_MW_COUNT ); +if (ndev->mw_count >NTB_EPF_MAX_MW_COUNT ) { +dev_err (dev,"Unsupported MW count: %u\n" , ndev->mw_count); +return -EINVAL ; + } +/* One Link interrupt and rest doorbell interrupt */ ret =ntb_epf_init_isr (ndev,NTB_EPF_MIN_DB_COUNT +1 ,NTB_EPF_MAX_DB_COUNT +1 );
@@ -575,14 +598,8 @@ static int ntb_epf_init_dev(struct ntb_epf_dev *ndev)* doorbell layout, hence -1. */ ndev->db_valid_mask =BIT_ULL (ndev->db_count -1 ) -1 ; - ndev->mw_count =readl (ndev->ctrl_reg +NTB_EPF_MW_COUNT ); ndev->spad_count =readl (ndev->ctrl_reg +NTB_EPF_SPAD_COUNT ); -if (ndev->mw_count >NTB_EPF_MAX_MW_COUNT ) { -dev_err (dev,"Unsupported MW count: %u\n" , ndev->mw_count); -return -EINVAL ; - } -return 0 ; }
@@ -677,7 +694,7 @@ static void ntb_epf_cleanup_isr(struct ntb_epf_dev *ndev)ntb_epf_send_command (ndev,CMD_TEARDOWN_DOORBELL , ndev->db_count +1 );for (i =0 ; i < ndev->db_count +1 ; i++) -free_irq (pci_irq_vector (pdev, i), ndev); +free_irq (pci_irq_vector (pdev, i), &ndev->irq_ctx[i]);pci_free_irq_vectors (pdev); }
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 910/1611 alpha/PCI: Add security_locked_down() check to pci_mmap_resource()
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Krzysztof Wilczyński <[email protected]>
[ Upstream commit 78a228f0aa0e9eba31955950c8a40a9945e2c8bb ]
Currently, Alpha's pci_mmap_resource() does not check security_locked_down(LOCKDOWN_PCI_ACCESS) before allowing userspace to mmap PCI BARs.
The generic version has had this check since commit eb627e17727e ("PCI:
Lock down BAR access when the kernel is locked down") to prevent DMA attacks when the kernel is locked down.
Add the same check to Alpha's pci_mmap_resource().
--- arch/alpha/kernel/pci-sysfs.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-)
arch/alpha/kernel/pci-sysfs.c +6 -1
@@ -11,6 +11,7 @@*/ #include <linux/sched.h> +#include <linux/security.h> #include <linux/stat.h> #include <linux/slab.h> #include <linux/pci.h>
@@ -71,7 +72,11 @@ static int pci_mmap_resource(struct kobject *kobj,struct resource *res = attr->private;enum pci_mmap_state mmap_type;struct pci_bus_region bar; -int i; +int i, ret; + + ret =security_locked_down (LOCKDOWN_PCI_ACCESS ); +if (ret) +return ret;for (i =0 ; i <PCI_STD_NUM_BARS ; i++)if (res == &pdev->resource[i])
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 911/1611 alpha/PCI: Fix __pci_mmap_fits() overflow for zero-length BARs
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Krzysztof Wilczyński <[email protected]>
[ Upstream commit 802a3b3f470b9bc1148f26e01fc9cbfeb4dfcb57 ]
Currently, __pci_mmap_fits() computes the BAR size using "pci_resource_len() - 1", which wraps to a large value when the BAR length is zero, causing the bounds check to incorrectly succeed.
Add an early return for empty resources.
--- arch/alpha/kernel/pci-sysfs.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-)
arch/alpha/kernel/pci-sysfs.c +5 -1
@@ -37,12 +37,16 @@ static int hose_mmap_page_range(struct pci_controller *hose,static int __pci_mmap_fits (struct pci_dev *pdev,int num,struct vm_area_struct *vma,int sparse) { +resource_size_t len =pci_resource_len (pdev, num);unsigned long nr, start, size;int shift = sparse ?5 :0 ; +if (!len) +return 0 ; + nr =vma_pages (vma); start = vma->vm_pgoff; - size = ((pci_resource_len (pdev, num) -1 ) >> (PAGE_SHIFT - shift)) +1 ; + size = ((len -1 ) >> (PAGE_SHIFT - shift)) +1 ;if (start < size && size - start >= nr)return 1 ;
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 912/1611 net, bpf: check master for NULL in xdp_master_redirect()
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Xiang Mei <[email protected]>
[ Upstream commit e82d8cc4321c373dc46e741cd2dfdaa7921fddb7 ]
xdp_master_redirect() dereferences the result of netdev_master_upper_dev_get_rcu() without a NULL check, but that helper returns NULL when the receiving device has no upper-master adjacency.
The reach guard only checks netif_is_bond_slave(). On bond slave release bond_upper_dev_unlink() drops the upper-master adjacency before clearing IFF_SLAVE, so an XDP_TX reaching xdp_master_redirect() in that window still passes netif_is_bond_slave() while master is already NULL, and faults on master->flags at offset 0xb0:
BUG: kernel NULL pointer dereference, address: 00000000000000b0 RIP: 0010:xdp_master_redirect (net/core/filter.c:4432) Call Trace: xdp_master_redirect (net/core/filter.c:4432) bpf_prog_run_generic_xdp (include/net/xdp.h:700) do_xdp_generic (net/core/dev.c:5608) __netif_receive_skb_one_core (net/core/dev.c:6204) process_backlog (net/core/dev.c:6319) __napi_poll (net/core/dev.c:7729) net_rx_action (net/core/dev.c:7792) handle_softirqs (kernel/softirq.c:622) __dev_queue_xmit (include/linux/bottom_half.h:33) packet_sendmsg (net/packet/af_packet.c:3082) __sys_sendto (net/socket.c:2252) Kernel panic - not syncing: Fatal exception in interrupt
The missing check dates back to the original code; commit 1921f91298d1 ("net, bpf: fix null-ptr-deref in xdp_master_redirect() for down master") later added the master->flags read where the fault now lands but kept the unconditional deref. Check master for NULL before use; a NULL master is treated the same as one that is not up.
--- net/core/filter.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
net/core/filter.c +1 -1
@@ -4424,7 +4424,7 @@ u32 xdp_master_redirect(struct xdp_buff *xdp)struct net_device *master, *slave; master =netdev_master_upper_dev_get_rcu (xdp->rxq->dev); -if (unlikely (!(master->flags &IFF_UP ))) +if (unlikely (!master || !(master->flags &IFF_UP )))return XDP_ABORTED ; slave = master->netdev_ops->ndo_xdp_get_xmit_slave (master, xdp);if (slave && slave != xdp->rxq->dev) {
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 913/1611 net: do not acquire dev->tx_global_lock in netdev_watchdog_up()
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Eric Dumazet <[email protected]>
[ Upstream commit d09a78a2a469e4fab75108325efb813c49520809 ]
Marek Szyprowski reported a deadlock during system resume when virtio_net driver is used.
The deadlock occurs because netif_device_attach() is called while holding dev->tx_global_lock (via netif_tx_lock_bh() in virtnet_restore_up()). netif_device_attach() calls __netdev_watchdog_up(), which now also tries to acquire dev->tx_global_lock to synchronize with dev_watchdog().
This recursive lock acquisition results in a deadlock.
Fix this by removing the tx_global_lock acquisition from netdev_watchdog_up().
The critical state (watchdog_timer and watchdog_ref_held) is already protected by dev->watchdog_lock, which was introduced in the blamed commit.
--- net/sched/sch_generic.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-)
net/sched/sch_generic.c +2 -5
@@ -569,9 +569,8 @@ void netdev_watchdog_up(struct net_device *dev)return ;if (dev->watchdog_timeo <=0 ) dev->watchdog_timeo =5 *HZ ; -spin_lock_bh (&dev->tx_global_lock); -spin_lock (&dev->watchdog_lock); +spin_lock_bh (&dev->watchdog_lock);if (!mod_timer (&dev->watchdog_timer,round_jiffies (jiffies + dev->watchdog_timeo))) {if (!dev->watchdog_ref_held) {
@@ -580,9 +579,7 @@ void netdev_watchdog_up(struct net_device *dev) dev->watchdog_ref_held = true; } } -spin_unlock (&dev->watchdog_lock); - -spin_unlock_bh (&dev->tx_global_lock); +spin_unlock_bh (&dev->watchdog_lock); }EXPORT_SYMBOL_GPL (netdev_watchdog_up);
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 914/1611 net: dsa: sja1105: round up PTP perout pin duration
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Aleksandrova Alyona <[email protected]>
[ Upstream commit aee5836273b07b439fb245fb43930664d8b78518 ]
pin_duration is converted from the user-provided period to SJA1105 clock ticks and is later passed as the cycle_time argument to future_base_time().
Very small period values may become zero after the conversion, which can lead to a division by zero in future_base_time().
Round zero pin_duration up to 1 tick so that the smallest unsupported periods use the minimum non-zero hardware duration instead of passing zero to future_base_time().
--- drivers/net/dsa/sja1105/sja1105_ptp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/net/dsa/sja1105/sja1105_ptp.c +1 -1
@@ -755,7 +755,7 @@ static int sja1105_per_out_enable(struct sja1105_private *priv,* 2 edges on PTP_CLK. So check for truncation which happens * at periods larger than around 68.7 seconds. */ - pin_duration =ns_to_sja1105_ticks (pin_duration /2 ); + pin_duration =max_t (u64,ns_to_sja1105_ticks (pin_duration /2 ),1 );if (pin_duration >U32_MAX ) { rc = -ERANGE ; goto out;
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 915/1611 veth: fix NAPI leak in XDP enable error path
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Eric Dumazet <[email protected]>
[ Upstream commit 6739027cb72da26890edd424c77080d187b2a92e ]
During XDP enablement in veth, if xdp_rxq_info_reg() or xdp_rxq_info_reg_mem_model() fails, the driver rolls back the changes.
However, the rollback loop:
for (i--; i >= start; i--) {decrements the loop index 'i' before the first iteration. This correctly skips unregistering the rxq for the failed index 'i' (as registration failed or was already cleaned up), but it also erroneously skips calling netif_napi_deli() for rq[i].xdp_napi.
Since netif_napi_add() was already called for index 'i', this leaves a dangling napi_struct in the device's napi_list. When the veth device is later destroyed, the freed queue memory (which contains the leaked NAPI structure) can be reused.
The subsequent device teardown iterates the NAPI list and corrupts the reallocated memory, leading to UAF.
Fix this by explicitly deleting the NAPI association for the failed index 'i' before rolling back the successfully configured queues.
--- drivers/net/veth.c | 2 ++ 1 file changed, 2 insertions(+)
drivers/net/veth.c +2 -0
@@ -1136,6 +1136,8 @@ static int veth_enable_xdp_range(struct net_device *dev, int start, int end, err_reg_mem:xdp_rxq_info_unreg (&priv->rq[i].xdp_rxq); err_rxq_reg: +if (!napi_already_on) +netif_napi_del (&priv->rq[i].xdp_napi);for (i--; i >= start; i--) {struct veth_rq *rq = &priv->rq[i];
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 916/1611 net: usb: lan78xx: restore VLAN and hash filters after link up
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Nicolai Buchwitz <[email protected]>
[ Upstream commit 5c12248673c76f10ab900f70724c5da288c7efa5 ]
Configured VLANs intermittently stop receiving traffic after a link down/up cycle, e.g. when the network cable is unplugged and plugged back in. VLAN filtering stays enabled but all VLAN-tagged frames are dropped until a VLAN is added or removed again.
The LAN7801 datasheet (DS00002123E) states:
"A portion of the MAC operates on clocks generated by the Ethernet
PHY. During a PHY reset event, this portion of the MAC is designed to not be taken out of reset until the PHY clocks are operational"
(section 8.10, MAC Reset Watchdog Timer)
"After a reset event, the RFE will automatically initialize the
contents of the VHF to 0h."
(section 7.1.4, VHF Organization)
Thus a link down/up cycle stops and restarts the PHY clock, resets the PHY-clocked portion of the MAC, and the RFE clears its VLAN/DA hash filter (VHF) memory. The VHF holds both the VLAN filter table and the multicast hash table, but the driver never reprograms either from its shadow copy once the link is back, so both stay empty.
Reprogram the VLAN filter and multicast hash tables on link up.
--- drivers/net/usb/lan78xx.c | 37 +++++++++++++++++++++++++++++++------ 1 file changed, 31 insertions(+), 6 deletions(-)
drivers/net/usb/lan78xx.c +31 -6
@@ -1452,6 +1452,15 @@ static inline u32 lan78xx_hash(char addr[ETH_ALEN])return (ether_crc (ETH_ALEN , addr) >>23 ) &0x1ff ; } +static int lan78xx_write_mchash_table (struct lan78xx_net *dev) +{ +struct lan78xx_priv *pdata = (struct lan78xx_priv *)(dev->data[0 ]); + +return lan78xx_dataport_write (dev,DP_SEL_RSEL_VLAN_DA_ , +DP_SEL_VHF_VLAN_LEN , +DP_SEL_VHF_HASH_LEN , pdata->mchash_table); +} +static void lan78xx_deferred_multicast_write (struct work_struct *param) { struct lan78xx_priv *pdata =
@@ -1462,9 +1471,7 @@ static void lan78xx_deferred_multicast_write(struct work_struct *param)netif_dbg (dev, drv, dev->net,"deferred multicast write 0x%08x\n" , pdata->rfe_ctl); - ret =lan78xx_dataport_write (dev,DP_SEL_RSEL_VLAN_DA_ , -DP_SEL_VHF_VLAN_LEN , -DP_SEL_VHF_HASH_LEN , pdata->mchash_table); + ret =lan78xx_write_mchash_table (dev);if (ret <0 ) goto multicast_write_done;
@@ -1557,6 +1564,7 @@ static void lan78xx_set_multicast(struct net_device *netdev) }static void lan78xx_rx_urb_submit_all (struct lan78xx_net *dev); +static int lan78xx_write_vlan_table (struct lan78xx_net *dev);static int lan78xx_mac_reset (struct lan78xx_net *dev) {
@@ -2514,6 +2522,17 @@ static void lan78xx_mac_link_up(struct phylink_config *config,if (ret <0 ) goto link_up_fail; +/* The RFE clears the VLAN/DA hash filter (VHF) on a link down/up +* cycle, so reprogram both tables from their shadow copies. +*/ + ret =lan78xx_write_vlan_table (dev); +if (ret <0 ) + goto link_up_fail; + + ret =lan78xx_write_mchash_table (dev); +if (ret <0 ) + goto link_up_fail; +netif_start_queue (net);return ;
@@ -3065,14 +3084,20 @@ static int lan78xx_set_features(struct net_device *netdev,return lan78xx_write_reg (dev,RFE_CTL , pdata->rfe_ctl); } +static int lan78xx_write_vlan_table (struct lan78xx_net *dev) +{ +struct lan78xx_priv *pdata = (struct lan78xx_priv *)(dev->data[0 ]); + +return lan78xx_dataport_write (dev,DP_SEL_RSEL_VLAN_DA_ ,0 , +DP_SEL_VHF_VLAN_LEN , pdata->vlan_table); +} +static void lan78xx_deferred_vlan_write (struct work_struct *param) {struct lan78xx_priv *pdata = container_of(param, struct lan78xx_priv, set_vlan); -struct lan78xx_net *dev = pdata->dev; -lan78xx_dataport_write (dev,DP_SEL_RSEL_VLAN_DA_ ,0 , -DP_SEL_VHF_VLAN_LEN , pdata->vlan_table); +lan78xx_write_vlan_table (pdata->dev); } static int lan78xx_vlan_rx_add_vid(struct net_device *netdev,
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 917/1611 net/sched: cls_api: Handle TC_ACT_CONSUMED in tcf_qevent_handle
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Jamal Hadi Salim <[email protected]>
[ Upstream commit a8a02897f2b479127db261de05cbf0c28b98d159 ]
tcf_classify() can return TC_ACT_CONSUMED while the skb is held by the defragmentation engine (e.g. act_ct on out-of-order fragments). When that happens the skb is no longer owned by the caller and must not be touched again.
tcf_qevent_handle() did not handle TC_ACT_CONSUMED: it fell through the switch and returned the skb to the caller as if classification had passed. The only qdisc that wires up qevents today is RED, via three call sites (qe_mark on RED_PROB_MARK/HARD_MARK, qe_early_drop on congestion_drop) red_enqueue() was continuing to operate on an skb it no longer owns in this case -- enqueueing it, dropping it, or updating statistics. Resulting in a UAF.
tc qdisc add dev eth0 root handle 1: red ... qevent early_drop block 10 tc filter add block 10 ... action ct
(with ct defrag enabled and traffic that produces out-of-order fragments, e.g. a fragmented UDP stream)
Handle TC_ACT_CONSUMED in tcf_qevent_handle() the same way the ingress and egress fast paths do: treat it as stolen and return NULL without touching the skb. Unlike the TC_ACT_STOLEN case, the skb must not be dropped/freed here, as it is no longer owned by us.
--- net/sched/cls_api.c | 3 +++ 1 file changed, 3 insertions(+)
net/sched/cls_api.c +3 -0
@@ -4050,6 +4050,9 @@ struct sk_buff *tcf_qevent_handle(struct tcf_qevent *qe, struct Qdisc *sch, struskb_do_redirect (skb); *ret = __NET_XMIT_STOLEN;return NULL ; +case TC_ACT_CONSUMED : + *ret = __NET_XMIT_STOLEN; +return NULL ; }return skb;
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 918/1611 ipv6: fix error handling in disable_ipv6 sysctl
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Fernando Fernandez Mancera <[email protected]>
[ Upstream commit c779441e5070e2268bdfe77f6e2e0de926c431e3 ]
When writing to the disable_ipv6 sysctl, if proc_dointvec() fails to parse the input, it returns a negative error code. The current implementation is overwriting that error for write operations.
This results in a silent failure, it returns a successful write although the configuration was not modified at all. When modifying the "all" variant it can also modify the configuration of existing interfaces to the wrong value.
Fix this by checking the return value of proc_dointvec() and returning early on failure.
--- net/ipv6/addrconf.c | 2 ++ 1 file changed, 2 insertions(+)
net/ipv6/addrconf.c +2 -0
@@ -6447,6 +6447,8 @@ static int addrconf_sysctl_disable(const struct ctl_table *ctl, int write, lctl.data = &val; ret =proc_dointvec (&lctl, write, buffer, lenp, ppos); +if (ret) +return ret;if (write) ret =addrconf_disable_ipv6 (ctl, valp, val);
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 919/1611 ipv6: fix error handling in ignore_routes_with_linkdown sysctl
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Fernando Fernandez Mancera <[email protected]>
[ Upstream commit cf4f2b14401f29ccac56393ca9e4b42a2505f540 ]
When writing to the ignore_routes_with_linkdown sysctl, if proc_dointvec() fails to parse the input, it returns a negative error code. The current implementation is overwriting that error for write operations.
This results in a silent failure, it returns a successful write although the configuration was not modified at all. When modifying the "all" variant it can also modify the configuration of existing interfaces to the wrong value.
Fix this by checking the return value of proc_dointvec() and returning early on failure.
--- net/ipv6/addrconf.c | 2 ++ 1 file changed, 2 insertions(+)
net/ipv6/addrconf.c +2 -0
@@ -6651,6 +6651,8 @@ int addrconf_sysctl_ignore_routes_with_linkdown(const struct ctl_table *ctl, lctl.data = &val; ret =proc_dointvec (&lctl, write, buffer, lenp, ppos); +if (ret) +return ret;if (write) ret =addrconf_fixup_linkdown (ctl, valp, val);
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 920/1611 ipv6: fix error handling in forwarding sysctl
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Fernando Fernandez Mancera <[email protected]>
[ Upstream commit 058b9b19f9639fe1e1225a17c540f61b65bee6ad ]
When writing to the forwarding sysctl, if proc_dointvec() fails to parse the input, it returns a negative error code. The current implementation is overwriting that error for write operations.
This results in a silent failure, it returns a successful write although the configuration was not modified at all. When modifying the "all" variant it can also modify the configuration of existing interfaces to the wrong value.
Fix this by checking the return value of proc_dointvec() and returning early on failure. In addition, adjust return code of addrconf_fixup_forwarding() for successful operation.
--- net/ipv6/addrconf.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)
net/ipv6/addrconf.c +3 -1
@@ -913,7 +913,7 @@ static int addrconf_fixup_forwarding(const struct ctl_table *table, int *p, intif (newf)rt6_purge_dflt_routers (net); -return 1 ; +return 0 ; }static void addrconf_linkdown_change (struct net *net,__s32 newf)
@@ -6350,6 +6350,8 @@ static int addrconf_sysctl_forward(const struct ctl_table *ctl, int write, lctl.data = &val; ret =proc_dointvec (&lctl, write, buffer, lenp, ppos); +if (ret) +return ret;if (write) ret =addrconf_fixup_forwarding (ctl, valp, val);
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 921/1611 ipv6: fix error handling in disable_policy sysctl
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Fernando Fernandez Mancera <[email protected]>
[ Upstream commit 3e0e51c0ee1d08cc9d48dc17f3248d5b31cf8066 ]
When writing to the disable_policy sysctl, if proc_dointvec() fails to parse the input, it returns a negative error code. The current implementation is resetting the position argument even if an error occurred during proc_dointvec() and not only during sysctl restart.
Fix this by checking the return value of proc_dointvec() and returning early on failure.
--- net/ipv6/addrconf.c | 2 ++ 1 file changed, 2 insertions(+)
net/ipv6/addrconf.c +2 -0
@@ -6749,6 +6749,8 @@ static int addrconf_sysctl_disable_policy(const struct ctl_table *ctl, int write lctl = *ctl; lctl.data = &val; ret =proc_dointvec (&lctl, write, buffer, lenp, ppos); +if (ret) +return ret;if (write && (*valp != val)) ret =addrconf_disable_policy (ctl, valp, val);
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 922/1611 ipv6: fix state corruption during proxy_ndp sysctl restart
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Fernando Fernandez Mancera <[email protected]>
[ Upstream commit 6a1b50e585f033f3e201f42a18b37f070095fb80 ]
When handling proxy_ndp, if rtnl_net_trylock() fails, the operation is retried but as the value was already modified by the initial proc_dointvec() call, the restarted syscall will read the newly modified value as the 'old' state.
Fix this by taking the RTNL lock before parsing the input value if the operation is a write.
--- net/ipv6/addrconf.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-)
net/ipv6/addrconf.c +7 -7
@@ -6462,20 +6462,19 @@ static int addrconf_sysctl_disable(const struct ctl_table *ctl, int write,static int addrconf_sysctl_proxy_ndp (const struct ctl_table *ctl,int write,void *buffer,size_t *lenp,loff_t *ppos) { +struct net *net = ctl->extra2;int *valp = ctl->data; -int ret;int old, new; +int ret; + +if (write && !rtnl_net_trylock (net)) +return restart_syscall (); old = *valp; ret =proc_dointvec (ctl, write, buffer, lenp, ppos); new = *valp;if (write && old != new) { -struct net *net = ctl->extra2; - -if (!rtnl_net_trylock (net)) -return restart_syscall (); -if (valp == &net->ipv6.devconf_dflt->proxy_ndp) { inet6_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_PROXY_NEIGH,
@@ -6494,8 +6493,9 @@ static int addrconf_sysctl_proxy_ndp(const struct ctl_table *ctl, int write, idev->dev->ifindex, &idev->cnf); } -rtnl_net_unlock (net); } +if (write) +rtnl_net_unlock (net);return ret; }
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 923/1611 ipv6: fix missing notification for ignore_routes_with_linkdown
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Fernando Fernandez Mancera <[email protected]>
[ Upstream commit 17dc3b245de45b1f2012e3a48ec51889f544e67b ]
When changing the ignore_routes_with_linkdown sysctl for a specific interface, the RTM_NEWNETCONF netlink notification was not being emitted to userspace. Fix this by emitting the notification when needed.
In addition, fix bogus return value for successful "all" and specific interface write operation leading to a wrong reset of the position pointer.
--- net/ipv6/addrconf.c | 18 ++++++++++++------ 1 file changed, 12 insertions(+), 6 deletions(-)
net/ipv6/addrconf.c +12 -6
@@ -955,11 +955,7 @@ static int addrconf_fixup_linkdown(const struct ctl_table *table, int *p, int neNETCONFA_IGNORE_ROUTES_WITH_LINKDOWN ,NETCONFA_IFINDEX_DEFAULT , net->ipv6.devconf_dflt); -rtnl_net_unlock (net); -return 0 ; - } - -if (p == &net->ipv6.devconf_all->ignore_routes_with_linkdown) { + }else if (p == &net->ipv6.devconf_all->ignore_routes_with_linkdown) {WRITE_ONCE (net->ipv6.devconf_dflt->ignore_routes_with_linkdown, newf);addrconf_linkdown_change (net, newf);if ((!newf) ^ (!old))
@@ -968,11 +964,21 @@ static int addrconf_fixup_linkdown(const struct ctl_table *table, int *p, int neNETCONFA_IGNORE_ROUTES_WITH_LINKDOWN ,NETCONFA_IFINDEX_ALL , net->ipv6.devconf_all); + }else { +if (!newf ^ !old) { +struct inet6_dev *idev = table->extra1; + +inet6_netconf_notify_devconf (net, +RTM_NEWNETCONF , +NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN , + idev->dev->ifindex, + &idev->cnf); + } }rtnl_net_unlock (net); -return 1 ; +return 0 ; }#endif
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 924/1611 eth: fbnic: fix ordering of heartbeat vs ownership
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Jakub Kicinski <[email protected]>
[ Upstream commit d87363b0edfc7504ff2b144fe4cdd8154f90f42e ]
When requesting ownership of the NIC (MAC/PHY control), we set up the heartbeat to look stale:
/* Initialize heartbeat, set last response to 1 second in the past
* so that we will trigger a timeout if the firmware doesn't respond */
fbd->last_heartbeat_response = req_time - HZ; fbd->last_heartbeat_request = req_time;
The response handler then sets:
fbd->last_heartbeat_response = jiffies;
for which we wait via:
fbnic_fw_init_heartbeat() -> fbnic_fw_heartbeat_current()
The scheme is a bit odd, but it should work in principle.
Fix the ordering of operations. We have to set up the stale heartbeat before we send the message. Otherwise if the response is very fast we will override it. This triggers on QEMU if we run on the core that handles the IRQ, and results in ndo_open failing with ETIMEDOUT.
The change in ordering doesn't impact releasing the ownership. Both ndo_stop and heartbeat check are under rtnl_lock.
--- drivers/net/ethernet/meta/fbnic/fbnic_fw.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-)
drivers/net/ethernet/meta/fbnic/fbnic_fw.c +4 -5
@@ -484,15 +484,10 @@ int fbnic_fw_xmit_ownership_msg(struct fbnic_dev *fbd, bool take_ownership) goto free_message; } - err =fbnic_mbx_map_tlv_msg (fbd, msg); -if (err) - goto free_message; -/* Initialize heartbeat, set last response to 1 second in the past * so that we will trigger a timeout if the firmware doesn't respond */ fbd->last_heartbeat_response = req_time -HZ ; - fbd->last_heartbeat_request = req_time;/* Set prev_firmware_time to 0 to avoid triggering firmware crash
@@ -500,6 +495,10 @@ int fbnic_fw_xmit_ownership_msg(struct fbnic_dev *fbd, bool take_ownership)*/ fbd->prev_firmware_time =0 ; + err =fbnic_mbx_map_tlv_msg (fbd, msg); +if (err) + goto free_message; +/* Set heartbeat detection based on if we are taking ownership */ fbd->fw_heartbeat_enabled = take_ownership;
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 925/1611 thermal: testing: zone: Flush work items during cleanup
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Rafael J. Wysocki <[email protected]>
[ Upstream commit fb1a5dfe86d3af1e1c3ce168cf0d8d43897e0f77 ]
To prevent freed module code from being executed during the thermal testing module unload, make it add a dedicated workqueue for thermal testing work items and flush it in thermal_testing_exit().
--- drivers/thermal/testing/command.c | 36 ++++++++++++++++++++--- drivers/thermal/testing/thermal_testing.h | 8 +++++ drivers/thermal/testing/zone.c | 7 ++--- 3 files changed, 43 insertions(+), 8 deletions(-)
drivers/thermal/testing/command.c +32 -4
@@ -86,7 +86,10 @@#include "thermal_testing.h" -struct dentry *d_testing; +struct workqueue_struct *tt_wq__ro_after_init ; + +struct dentry *d_testing__ro_after_init ; +static struct dentry *d_command__ro_after_init ;#define TT_COMMAND_SIZE 16
@@ -203,17 +206,42 @@ static const struct file_operations tt_command_fops = {static int __init thermal_testing_init (void ) { +int error; + + tt_wq =alloc_workqueue ("thermal_testing" ,WQ_UNBOUND ,0 ); +if (!tt_wq) +return -ENOMEM ; + d_testing =debugfs_create_dir ("thermal-testing" ,NULL ); -if (!IS_ERR (d_testing)) -debugfs_create_file ("command" ,0200 , d_testing,NULL , - &tt_command_fops); +if (IS_ERR (d_testing)) { + error =PTR_ERR (d_testing); + goto destroy_wq; + } + + d_command =debugfs_create_file ("command" ,0200 , d_testing,NULL , &tt_command_fops); +if (IS_ERR (d_command)) { + error =PTR_ERR (d_command); + goto remove_d_testing; + }return 0 ; + +remove_d_testing: +debugfs_remove (d_testing); +destroy_wq: +destroy_workqueue (tt_wq); +return error; }module_init (thermal_testing_init); static void __exit thermal_testing_exit(void) { +/* First, prevent new commands from being entered. */ +debugfs_remove (d_command); +/* Flush commands in progress (if any). */ +flush_workqueue (tt_wq); +destroy_workqueue (tt_wq); +/* Remove the directory structure and clean up. */ debugfs_remove (d_testing);tt_zone_cleanup (); }
drivers/thermal/testing/thermal_testing.h +8 -0
@@ -1,4 +1,12 @@/* SPDX-License-Identifier: GPL-2.0 */ +#include <linux/workqueue.h> + +extern struct workqueue_struct *tt_wq; + +static inline void tt_queue_work (struct work_struct *work) +{ +queue_work (tt_wq, work); +}extern struct dentry *d_testing;
drivers/thermal/testing/zone.c +3 -4
@@ -13,7 +13,6 @@#include <linux/idr.h> #include <linux/list.h> #include <linux/thermal.h> -#include <linux/workqueue.h> #include "thermal_testing.h"
@@ -208,7 +207,7 @@ int tt_add_tz(void)INIT_WORK (&tt_work->work, tt_add_tz_work_fn); tt_work->tt_zone =no_free_ptr (tt_zone); -schedule_work (&(no_free_ptr (tt_work)->work)); +tt_queue_work (&(no_free_ptr (tt_work)->work));return 0 ; }
@@ -270,7 +269,7 @@ int tt_del_tz(const char *arg)INIT_WORK (&tt_work->work, tt_del_tz_work_fn); tt_work->tt_zone = tt_zone; -schedule_work (&(no_free_ptr (tt_work)->work)); +tt_queue_work (&(no_free_ptr (tt_work)->work));return 0 ; }
@@ -359,7 +358,7 @@ int tt_zone_add_trip(const char *arg)INIT_WORK (&tt_work->work, tt_zone_add_trip_work_fn); tt_work->tt_zone =no_free_ptr (tt_zone); tt_work->tt_trip =no_free_ptr (tt_trip); -schedule_work (&(no_free_ptr (tt_work)->work)); +tt_queue_work (&(no_free_ptr (tt_work)->work));return 0 ; }
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 926/1611 ACPI: processor_idle: Mark LPI enter functions as __cpuidle
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Li RongQing <[email protected]>
[ Upstream commit 956ca5d72c76504824c8eb601879da9476973e15 ]
When function tracing or Kprobes is enabled, entering an ACPI Low Power Idle (LPI) state triggers the following RCU splat:
RCU not on for: acpi_idle_lpi_enter+0x4/0xd8
WARNING: CPU: 8 PID: 0 at include/linux/trace_recursion.h:162 function_trace_call+0x1e8/0x228
The acpi_idle_lpi_enter() function is invoked within the cpuidle path after RCU has already been disabled for the current local CPU. Consequently, ftrace's function_trace_call() expects RCU to be actively watching before recording trace data, emitting a warning if it is not.
Fix this by annotating acpi_idle_lpi_enter(), the generic __weak stub, and the RISC-V implementation of acpi_processor_ffh_lpi_enter() with __cpuidle. This moves these functions into the '.cpuidle.text' section, implicitly disabling ftrace instrumentation (notrace) along this sensitive path and preventing trace-induced RCU warnings during idle entry.
--- drivers/acpi/processor_idle.c | 4 ++-- drivers/acpi/riscv/cpuidle.c | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-)
drivers/acpi/processor_idle.c +2 -2
@@ -1159,7 +1159,7 @@ static int acpi_processor_get_lpi_info(struct acpi_processor *pr)return 0 ; } -int __weak acpi_processor_ffh_lpi_enter (struct acpi_lpi_state *lpi) +int __weak __cpuidle acpi_processor_ffh_lpi_enter(struct acpi_lpi_state *lpi) {return -ENODEV ; }
@@ -1172,7 +1172,7 @@ int __weak acpi_processor_ffh_lpi_enter(struct acpi_lpi_state *lpi)* * Return: 0 for success or negative value for error */ -static int acpi_idle_lpi_enter (struct cpuidle_device *dev, +static int __cpuidle acpi_idle_lpi_enter(struct cpuidle_device *dev,struct cpuidle_driver *drv,int index) {struct acpi_processor *pr;
drivers/acpi/riscv/cpuidle.c +1 -1
@@ -66,7 +66,7 @@ int acpi_processor_ffh_lpi_probe(unsigned int cpu)return acpi_cpu_init_idle (cpu); } -int acpi_processor_ffh_lpi_enter (struct acpi_lpi_state *lpi) +int __cpuidle acpi_processor_ffh_lpi_enter(struct acpi_lpi_state *lpi) {u32 state = lpi->address;
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 927/1611 smb/client: preserve errors from smb2_set_sparse()
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Huiwen He <[email protected]>
[ Upstream commit 2a4b3d2db5c6fcdba889baf7b2ae5661b0beac89 ]
smb2_set_sparse() converts every FSCTL_SET_SPARSE failure to false and marks sparse support as broken for the share. Callers therefore report EOPNOTSUPP even for errors such as ENOSPC or EACCES, and later sparse operations remain disabled until the share is unmounted.
Return the SMB2 ioctl error directly. Set broken_sparse_sup only for EOPNOTSUPP, which indicates that the server does not support the request.
Update smb3_punch_hole() to propagate the error returned by smb2_set_sparse().
--- fs/smb/client/smb2ops.c | 30 +++++++++++++++--------------- 1 file changed, 15 insertions(+), 15 deletions(-)
fs/smb/client/smb2ops.c +15 -15
@@ -2096,8 +2096,9 @@ smb2_sync_write(const unsigned int xid, struct cifs_fid *pfid, }/* Set or clear the SPARSE_FILE attribute based on value passed in setsparse */ -static bool smb2_set_sparse (const unsigned int xid,struct cifs_tcon *tcon, -struct cifsFileInfo *cfile,struct inode *inode,__u8 setsparse) +static int smb2_set_sparse (const unsigned int xid,struct cifs_tcon *tcon, +struct cifsFileInfo *cfile,struct inode *inode, +__u8 setsparse) {struct cifsInodeInfo *cifsi;int rc;
@@ -2106,31 +2107,31 @@ static bool smb2_set_sparse(const unsigned int xid, struct cifs_tcon *tcon,/* if file already sparse don't bother setting sparse again */ if ((cifsi->cifsAttrs &FILE_ATTRIBUTE_SPARSE_FILE ) && setsparse) -return true;/* already sparse */ +return 0 ;/* already sparse */ if (!(cifsi->cifsAttrs &FILE_ATTRIBUTE_SPARSE_FILE ) && !setsparse) -return true;/* already not sparse */ +return 0 ;/* already not sparse */ /* * Can't check for sparse support on share the usual way via the * FS attribute info (FILE_SUPPORTS_SPARSE_FILES) on the share * since Samba server doesn't set the flag on the share, yet * supports the set sparse FSCTL and returns sparse correctly -* in the file attributes. If we fail setting sparse though we -* mark that server does not support sparse files for this share -* to avoid repeatedly sending the unsupported fsctl to server -* if the file is repeatedly extended. +* in the file attributes. If the server returns EOPNOTSUPP, mark +* that sparse files are not supported on this share to avoid +* repeatedly sending the unsupported FSCTL. */ if (tcon->broken_sparse_sup) -return false; +return -EOPNOTSUPP ; rc =SMB2_ioctl (xid, tcon, cfile->fid.persistent_fid, cfile->fid.volatile_fid,FSCTL_SET_SPARSE , &setsparse,1 , CIFSMaxBufSize,NULL ,NULL );if (rc) { - tcon->broken_sparse_sup = true; +if (rc == -EOPNOTSUPP ) + tcon->broken_sparse_sup = true;cifs_dbg (FYI ,"set sparse rc = %d\n" , rc); -return false; +return rc; }if (setsparse)
@@ -2138,7 +2139,7 @@ static bool smb2_set_sparse(const unsigned int xid, struct cifs_tcon *tcon,else cifsi->cifsAttrs &= (~FILE_ATTRIBUTE_SPARSE_FILE ); -return true; +return 0 ; } static int
@@ -3451,10 +3452,9 @@ static long smb3_punch_hole(struct file *file, struct cifs_tcon *tcon,/* Need to make file sparse, if not already, before freeing range. */ /* Consider adding equivalent for compressed since it could also work */ -if (!smb2_set_sparse (xid, tcon, cfile, inode, set_sparse)) { - rc = -EOPNOTSUPP ; + rc =smb2_set_sparse (xid, tcon, cfile, inode, set_sparse); +if (rc) goto out; - }filemap_invalidate_lock (inode->i_mapping);/*
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 928/1611 rtc: ds1307: Fix off-by-one issue with wday for rx8130
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Fredrik M Olsson <[email protected]>
[ Upstream commit 6882aab3c66112b33b251be95c09c8ead3e8d580 ]
The RTC represent each weekday with a individual bit set in the WDAY register, where the 0th bit represent the first day of the week and the 6th bit represents the last day of the week. For each passed day the chip performs a rotary-left-shift by one to advance the weekday by one.
The tm_wday field represent weekdays by a value in the range of 0-6.
The fls() function return the bit index of the last bit set. To handle when there are no bits set it will return 0, and if the 0th bit is set it will return 1, and if the 1st bit is set it will return 2, and so on.
In order to make the result of the fls() function fall into the expected range of 0-6 (instead of 1-7) this patch subtracts one from the result (which matches how the value is written in ds1307_set_time()).
--- drivers/rtc/rtc-ds1307.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/rtc/rtc-ds1307.c +1 -1
@@ -311,7 +311,7 @@ static int ds1307_get_time(struct device *dev, struct rtc_time *t) t->tm_hour =bcd2bin (tmp);/* rx8130 is bit position, not BCD */ if (ds1307->type == rx_8130) - t->tm_wday =fls (regs[DS1307_REG_WDAY ] &0x7f ); + t->tm_wday =fls (regs[DS1307_REG_WDAY ] &0x7f ) -1 ;else t->tm_wday =bcd2bin (regs[DS1307_REG_WDAY ] &0x07 ) -1 ; t->tm_mday =bcd2bin (regs[DS1307_REG_MDAY ] &0x3f );
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 929/1611 rtc: cmos: unregister HPET IRQ handler on probe failure
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Haoxiang Li <[email protected]>
[ Upstream commit a5bb580df018b5d1c5668f05f7979044fb19e23a ]
cmos_do_probe() registers cmos_interrupt() as the HPET RTC IRQ handler before requesting the RTC IRQ and registering the RTC device. If either request_irq() or devm_rtc_register_device() fails afterwards, the error path leaves the HPET RTC IRQ handler installed. This leaves a stale handler behind and make a later hpet_register_irq_handler() fail with -EBUSY.
Track whether the HPET handler was registered successfully and undo the registration on the probe error path. Also mask the HPET RTC IRQ bits to match the normal shutdown cleanup.
--- drivers/rtc/rtc-cmos.c | 6 ++++++ 1 file changed, 6 insertions(+)
drivers/rtc/rtc-cmos.c +6 -0
@@ -927,6 +927,7 @@ cmos_do_probe(struct device *dev, struct resource *ports, int rtc_irq)unsigned char rtc_control;unsigned address_space;u32 flags =0 ; +bool hpet_registered = false;struct nvmem_config nvmem_cfg = { .name ="cmos_nvram" , .word_size =1 ,
@@ -1084,6 +1085,7 @@ cmos_do_probe(struct device *dev, struct resource *ports, int rtc_irq) " failed in rtc_init()."); goto cleanup1; } + hpet_registered = true; }else rtc_cmos_int_handler = cmos_interrupt;
@@ -1133,6 +1135,10 @@ cmos_do_probe(struct device *dev, struct resource *ports, int rtc_irq)if (is_valid_irq (rtc_irq))free_irq (rtc_irq, cmos_rtc.rtc); cleanup1: +if (hpet_registered) { +hpet_mask_rtc_irq_bit (RTC_IRQMASK ); +hpet_unregister_irq_handler (cmos_interrupt); + } cmos_rtc.dev =NULL ; cleanup0:if (RTC_IOMAPPED )
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 930/1611 net: dsa: realtek: fix memory leak in rtl8366rb_setup_led()
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: David Yang <[email protected]>
[ Upstream commit 056a5087d87ead77dedbe9cf5bde53b7cd4b4651 ]
led_classdev_register_ext() only reads init_data.devicename - it never stores the pointer. However, the caller allocated devicename with kasprintf() but never freed it, leaking the string memory.
Fix it with a stack buffer to avoid dynamic buffers completely.
--- drivers/net/dsa/realtek/rtl8366rb-leds.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-)
drivers/net/dsa/realtek/rtl8366rb-leds.c +4 -4
@@ -89,6 +89,7 @@ static int rtl8366rb_setup_led(struct realtek_priv *priv, struct dsa_port *dp,struct led_init_data init_data = { };enum led_default_state state;struct rtl8366rb_led *led; +char name[64 ];u32 led_group;int ret;
@@ -129,10 +130,9 @@ static int rtl8366rb_setup_led(struct realtek_priv *priv, struct dsa_port *dp, init_data.fwnode = led_fwnode; init_data.devname_mandatory = true; - init_data.devicename =kasprintf (GFP_KERNEL ,"Realtek-%d:0%d:%d" , - dp->ds->index, dp->index, led_group); -if (!init_data.devicename) -return -ENOMEM ; +snprintf (name,sizeof (name),"Realtek-%d:0%d:%d" , + dp->ds->index, dp->index, led_group); + init_data.devicename = name; ret =devm_led_classdev_register_ext (priv->dev, &led->cdev, &init_data);if (ret) {
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 931/1611 net: phy: realtek: Clear MDIO_AN_10GBT_CTRL_ADV10G bit
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Jan Klos <[email protected]>
[ Upstream commit 510a283f4d12367a3f811f382a2c89202954bbd1 ]
On RTL8127A connected to a link partner that advertises 10000baseT speed cannot be changed to anything other than 10000baseT as 10GbE is always advertised regardless of any setting. Fix this by clearing MDIO_AN_10GBT_CTRL_ADV10G bit in rtl822x_config_aneg()'s call to phy_modify_mmd_changed().
--- drivers/net/phy/realtek/realtek_main.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)
drivers/net/phy/realtek/realtek_main.c +2 -1
@@ -1330,7 +1330,8 @@ static int rtl822x_config_aneg(struct phy_device *phydev) ret =phy_modify_mmd_changed (phydev,MDIO_MMD_VEND2 ,RTL_MDIO_AN_10GBT_CTRL ,MDIO_AN_10GBT_CTRL_ADV2_5G | -MDIO_AN_10GBT_CTRL_ADV5G , adv); +MDIO_AN_10GBT_CTRL_ADV5G | +MDIO_AN_10GBT_CTRL_ADV10G , adv);if (ret <0 )return ret; }
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 932/1611 octeontx2-af: Validate NIX maximum LFs correctly
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Subbaraya Sundeep <[email protected]>
[ Upstream commit 1576d12a39860418d6a68b402fda71a48f04a57c ]
NIX maximum number of LFs can be set via devlink command but that can be done before assigning any LFs to a PF/VF. The condition used to check whether any LFs are assigned is incorrect. This patch fixes that condition.
--- .../marvell/octeontx2/af/rvu_devlink.c | 27 +++++++++++++------ 1 file changed, 19 insertions(+), 8 deletions(-)
drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c +19 -8
@@ -1442,7 +1442,9 @@ static int rvu_af_dl_nix_maxlf_validate(struct devlink *devlink, u32 id,struct rvu_devlink *rvu_dl =devlink_priv (devlink);struct rvu *rvu = rvu_dl->rvu;u16 max_nix0_lf, max_nix1_lf; -struct npc_mcam *mcam; +struct rvu_block *block; +int blkaddr =0 ; +int free_lfs;u64 cfg; cfg =rvu_read64 (rvu,BLKADDR_NIX0 ,NIX_AF_CONST2 );
@@ -1450,14 +1452,23 @@ static int rvu_af_dl_nix_maxlf_validate(struct devlink *devlink, u32 id, cfg =rvu_read64 (rvu,BLKADDR_NIX1 ,NIX_AF_CONST2 ); max_nix1_lf = cfg &0xFFF ; -/* Do not allow user to modify maximum NIX LFs while mcam entries -* have already been assigned. +/* Do not allow user to modify maximum NIX LFs while NIX LFs +* have already been assigned. Note that modifying NIX LFs count +* can be done only before any LF attach requests from PFs and VFs +* and not later or concurrently. */ - mcam = &rvu->hw->mcam; -if (mcam->bmap_fcnt < mcam->bmap_entries) { -NL_SET_ERR_MSG_MOD (extack, -"mcam entries have already been assigned, can't resize" ); -return -EPERM ; + blkaddr =rvu_get_next_nix_blkaddr (rvu, blkaddr); +while (blkaddr) { + block = &rvu->hw->block[blkaddr]; + + free_lfs =rvu_rsrc_free_count (&block->lf); +if (free_lfs != block->lf.max) { +NL_SET_ERR_MSG_MOD (extack, +"NIX LFs already assigned, can't resize" ); +return -EPERM ; + } + + blkaddr =rvu_get_next_nix_blkaddr (rvu, blkaddr); }if (max_nix0_lf && val.vu16 > max_nix0_lf) {
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 933/1611 net: mvneta: re-enable percpu interrupt on resume
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Yun Zhou <[email protected]>
[ Upstream commit fd398d6480987e4c84fff0aaab6b9d6642a93343 ]
On Marvell MPIC platforms (Armada 370/XP/38x), mvneta uses a percpu IRQ disable/enable scheme for NAPI: the ISR (mvneta_percpu_isr) calls disable_percpu_irq() to mask the MPIC per-CPU interrupt and schedules NAPI poll, which calls enable_percpu_irq() on completion to unmask.
If suspend occurs while NAPI poll is pending (between disable_percpu_irq in the ISR and enable_percpu_irq in poll completion), the interrupt is never re-enabled:
1. mvneta_percpu_isr: disable_percpu_irq() + napi_schedule() => MPIC masked, percpu_enabled cpumask bit cleared
2. NAPI poll does not complete before suspend proceeds (on PREEMPT_RT this is highly likely since softirqs run in ksoftirqd which gets frozen; on non-RT it can happen when softirq processing is deferred to ksoftirqd)
3. mvneta_stop_dev => napi_disable(): cancels the pending poll without executing the completion path
4. suspend_device_irqs => IRQCHIP_MASK_ON_SUSPEND: masks MPIC (already masked, but records IRQS_SUSPENDED)
5. Resume: mpic_resume checks irq_percpu_is_enabled() => false (bit was cleared in step 1) => skips unmask
6. mvneta_start_dev only restores device-level INTR_NEW_MASK, does not touch the MPIC per-CPU mask
Result: MPIC per-CPU interrupt stays masked permanently. The NIC generates interrupts (INTR_NEW_CAUSE != 0) but the CPU never receives them, causing complete loss of network connectivity.
Fix by calling on_each_cpu(mvneta_percpu_enable) in the resume path to unconditionally unmask the MPIC per-CPU interrupt regardless of pre-suspend state.
--- drivers/net/ethernet/marvell/mvneta.c | 3 +++ 1 file changed, 3 insertions(+)
drivers/net/ethernet/marvell/mvneta.c +3 -0
@@ -5905,6 +5905,9 @@ static int mvneta_resume(struct device *device)rtnl_unlock ();mvneta_set_rx_mode (dev); +if (!pp->neta_armada3700) +on_each_cpu (mvneta_percpu_enable, pp, true); + return 0; }#endif
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 934/1611 net: sungem: fix probe error cleanup
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Ruoyu Wang <[email protected]>
[ Upstream commit 36dea2f639249460d13f6ca66b2a9064187cd34d ]
gem_init_one() calls gem_remove_one() when register_netdev() fails. gem_remove_one() unregisters and frees resources owned by the net_device, including the DMA block, MMIO mapping, PCI regions, and the net_device itself. gem_init_one() then falls through to its own cleanup labels and frees the same resources again.
Keep the register_netdev() error path in gem_init_one(): clear drvdata so PM/remove paths do not see a half-registered device, remove the NAPI instance added during probe, and let the existing cleanup labels release the resources once.
The issue was found by a local static-analysis checker for probe error paths. The reported path was manually inspected before sending this fix.
Compile-tested with CONFIG_SUNGEM=y. Runtime testing was not performed because no sungem hardware is available.
--- drivers/net/ethernet/sun/sungem.c | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-)
drivers/net/ethernet/sun/sungem.c +9 -4
@@ -2986,10 +2986,10 @@ static int gem_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) dev->max_mtu =GEM_MAX_MTU ;/* Register with kernel */ -if (register_netdev (dev)) { + err =register_netdev (dev); +if (err) {pr_err ("Cannot register net device, aborting\n" ); - err = -ENOMEM ; - goto err_out_free_consistent; + goto err_out_clear_drvdata; }/* Undo the get_cell with appropriate locking (we could use
@@ -3003,8 +3003,13 @@ static int gem_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) dev->dev_addr);return 0 ; +err_out_clear_drvdata: +pci_set_drvdata (pdev,NULL ); +netif_napi_del (&gp->napi); + err_out_free_consistent: -gem_remove_one (pdev); +dma_free_coherent (&pdev->dev,sizeof (struct gem_init_block ), + gp->init_block, gp->gblock_dvma); err_out_iounmap:gem_put_cell (gp);iounmap (gp->regs);
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 935/1611 net: ethernet: sunplus: spl2sw: fix phy_node refcount leak in remove
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Shitalkumar Gandhi <[email protected]>
[ Upstream commit a9e29dcd8a84081177f693439d663ca9e216c9fa ]
mac->phy_node is acquired via of_parse_phandle() in spl2sw_probe() and stored in the mac private data, transferring ownership of the device_node reference to mac. On driver removal, spl2sw_phy_remove() disconnects the PHY but never drops that reference, so each probe-then-remove cycle leaks one of_node refcount per port permanently.
Drop the reference after phy_disconnect(). While at it, remove the redundant inner "if (ndev)" check; comm->ndev[i] was just verified non-NULL on the line above.
Compile-tested only; no SP7021 hardware available.
--- drivers/net/ethernet/sunplus/spl2sw_phy.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-)
drivers/net/ethernet/sunplus/spl2sw_phy.c +4 -2
@@ -79,12 +79,14 @@ int spl2sw_phy_connect(struct spl2sw_common *comm)void spl2sw_phy_remove (struct spl2sw_common *comm) {struct net_device *ndev; +struct spl2sw_mac *mac;int i;for (i =0 ; i <MAX_NETDEV_NUM ; i++)if (comm->ndev[i]) { ndev = comm->ndev[i]; -if (ndev) -phy_disconnect (ndev->phydev); + mac =netdev_priv (ndev); +phy_disconnect (ndev->phydev); +of_node_put (mac->phy_node); } }
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 936/1611 LoongArch: Move struct kimage forward declaration before use
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: 谢致邦 (XIE Zhibang) <[email protected]>
[ Upstream commit d4e58d2c21d94282d512979dfa7e045c5034b0be ]
arch_kimage_file_post_load_cleanup() and load_other_segments(), both inside the CONFIG_KEXEC_FILE block, take a struct kimage pointer before the forward declaration appears. Move the forward declaration above so it precedes its first use instead of relying on a transitive include.
--- arch/loongarch/include/asm/kexec.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)
arch/loongarch/include/asm/kexec.h +2 -1
@@ -41,6 +41,8 @@ struct kimage_arch {unsigned long systable_ptr; }; +struct kimage ; +#ifdef CONFIG_KEXEC_FILE extern const struct kexec_file_ops kexec_efi_ops;extern const struct kexec_file_ops kexec_elf_ops;
@@ -59,7 +61,6 @@ typedef void (*do_kexec_t)(unsigned long efi_boot,unsigned long start_addr, unsigned long first_ind_entry); -struct kimage ;extern const unsigned char relocate_new_kernel[];extern const size_t relocate_new_kernel_size;extern void kexec_reboot (void );
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 937/1611 LoongArch: BPF: Fix outdated tail call comments
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Tiezhu Yang <[email protected]>
[ Upstream commit 25d9127bb0e27275d55a5b3d0fd30b04bafffd5a ]
The current LoongArch BPF JIT implementation hardcodes the number of prologue instructions skipped during a tail call as a magic number '7' in the jirl instruction. However, the accompanying comment explaining this offset is completely outdated. It inaccurately states that only a single TCC initialization instruction is bypassed, but in reality, multiple setup slots are skipped, so fix these outdated comments in __build_epilogue().
While at it, refine the comments in build_prologue() to describe the skipped setup slots (RA saving, fentry nops, and the TCC register slot) using proper dynamic tracing context. Also, remove the magic number '7' by introducing descriptive macros to formally define the prologue layout and make the tail call jump offset self-documenting.
--- arch/loongarch/net/bpf_jit.c | 20 ++++++++++++++++---- 1 file changed, 16 insertions(+), 4 deletions(-)
arch/loongarch/net/bpf_jit.c +16 -4
@@ -9,7 +9,13 @@#define LOONGARCH_MAX_REG_ARGS 8 +#define LOONGARCH_SAVE_RA_NINSNS 1#define LOONGARCH_LONG_JUMP_NINSNS 5 +#define LOONGARCH_TCC_SLOT_NINSNS 1 + +#define LOONGARCH_PROLOGUE_SKIP_INSNS \ + (LOONGARCH_SAVE_RA_NINSNS + LOONGARCH_LONG_JUMP_NINSNS + LOONGARCH_TCC_SLOT_NINSNS) +#define LOONGARCH_LONG_JUMP_NBYTES (LOONGARCH_LONG_JUMP_NINSNS * 4)#define LOONGARCH_FENTRY_NINSNS 2
@@ -139,8 +145,13 @@ static void build_prologue(struct jit_ctx *ctx) stack_adjust =round_up (stack_adjust,16 ); stack_adjust += bpf_stack_adjust; +/* +* Save the original return address to a temporary register to prevent +* it from being overwritten, then reserve space for the long jump and +* fentry trampoline slot for dynamically patching by ftrace at runtime. +* These instructions are bypassed during a tail call invocation. +*/ move_reg (ctx,LOONGARCH_GPR_T0 ,LOONGARCH_GPR_RA ); -/* Reserve space for the move_imm + jirl instruction */ for (i =0 ; i <LOONGARCH_LONG_JUMP_NINSNS ; i++)emit_insn (ctx, nop);
@@ -236,10 +247,11 @@ static void __build_epilogue(struct jit_ctx *ctx, bool is_tail_call)emit_insn (ctx, jirl,LOONGARCH_GPR_ZERO ,LOONGARCH_GPR_RA ,0 ); }else {/* -* Call the next bpf prog and skip the first instruction -* of TCC initialization. +* Tail call to the next BPF program, passing offset in number +* of instructions to jirl to bypass the initial setup slots. */ -emit_insn (ctx, jirl,LOONGARCH_GPR_ZERO ,LOONGARCH_GPR_T3 ,7 ); +emit_insn (ctx, jirl,LOONGARCH_GPR_ZERO , +LOONGARCH_GPR_T3 ,LOONGARCH_PROLOGUE_SKIP_INSNS ); } }
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 938/1611 LoongArch: BPF: Fix off-by-one error in tail call
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Tiezhu Yang <[email protected]>
[ Upstream commit 0379d10f09bc21ba739636796669dfb4936172a3 ]
The current code updates the tail call counter (TCC) using a pre-increment approach, it stores the incremented value back to memory before performing any boundary or target validation checks.
This causes two major issues:
1. When a tail call fails because the target program is NULL, the TCC is incorrectly incremented and saved in memory anyway.
2. This dummy increment implicitly consumes one slot of the allowed tail call budget. As a result, the subsequent loop reaches the maximum limit prematurely, leading to a test failure where the actual loop count is 32 instead of the expected 33.
Fix this by deferring the counter update. Change the branch condition to BPF_JSGE (greater or equal) so that we check the boundary first. The TCC is only incremented and stored back to memory after the boundary check and the NULL-target check both pass.
Before:
$ sudo ./test_progs -t tailcalls/tailcall_3 ... test_tailcall_count:FAIL:tailcall count unexpected tailcall count: actual 32 != expected 33 ... #465/3 tailcalls/tailcall_3:FAIL #465 tailcalls:FAIL
After:
$ sudo ./test_progs -t tailcalls/tailcall_3 #465/3 tailcalls/tailcall_3:OK #465 tailcalls:OK Summary: 1/1 PASSED, 0 SKIPPED, 0 FAILED
--- arch/loongarch/net/bpf_jit.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-)
arch/loongarch/net/bpf_jit.c +5 -3
@@ -307,12 +307,12 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx, int insn)*/ emit_insn (ctx, ldd,REG_TCC ,LOONGARCH_GPR_SP , tcc_ptr_off);emit_insn (ctx, ldd, t3,REG_TCC ,0 ); -emit_insn (ctx, addid, t3, t3,1 ); -emit_insn (ctx, std, t3,REG_TCC ,0 );emit_insn (ctx, addid, t2,LOONGARCH_GPR_ZERO ,MAX_TAIL_CALL_CNT ); -if (emit_tailcall_jmp (ctx,BPF_JSGT , t3, t2, jmp_offset) <0 ) +if (emit_tailcall_jmp (ctx,BPF_JSGE , t3, t2, jmp_offset) <0 ) goto toofar; +emit_insn (ctx, addid, t3, t3,1 ); +/* * prog = array->ptrs[index]; * if (!prog)
@@ -325,6 +325,8 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx, int insn)if (emit_tailcall_jmp (ctx,BPF_JEQ , t2,LOONGARCH_GPR_ZERO , jmp_offset) <0 ) goto toofar; +emit_insn (ctx, std, t3,REG_TCC ,0 ); +/* goto *(prog->bpf_func + 4); */ off = offsetof(struct bpf_prog , bpf_func);emit_insn (ctx, ldd, t3, t2, off);
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 939/1611 ASoC: fsl_asrc_dma: fix eDMA maxburst misalignment with channel count
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Shengjiu Wang <[email protected]>
[ Upstream commit cf6f56990ea21172e085f0588e5bbf2089ce8f58 ]
The back-end consumes data in units of the number of channels. When the maxburst value is not evenly divisible by the channel count, the DMA transfer length does not align with the FIFO frame boundary, causing wrong data to be copied and audible noise at the end of the stream.
This is specific to eDMA: eDMA only responds to DMA requests from the back-end, whereas SDMA handles requests from both the front-end and the back-end and is not affected.
For eDMA, when the back-end maxburst is not evenly divisible by the channel count, align it to the nearest valid boundary:
- If maxburst >= channel count, override to the channel count so each transfer corresponds to exactly one audio frame.
- If maxburst < channel count, override to 1 to avoid partial-frame transfers.
Retain the original maxburst for SDMA or when it already aligns with the channel count.
--- sound/soc/fsl/fsl_asrc_dma.c | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+)
sound/soc/fsl/fsl_asrc_dma.c +20 -0
@@ -288,6 +288,26 @@ static int fsl_asrc_dma_hw_params(struct snd_soc_component *component, config_be.dst_addr_width = buswidth; config_be.dst_maxburst = dma_params_be->maxburst; +/* +* For eDMA, the back-end may report a maxburst size that is not evenly +* divisible by the channel count. This causes the DMA transfer length +* to misalign with the FIFO boundary, resulting in wrong data and +* audible noise. Align maxburst to the nearest valid boundary: +* - If maxburst >= channel count, override to the channel count so +* each transfer equals exactly one audio frame. +* - If maxburst < channel count, override to 1 to avoid partial-frame +* transfers. +*/ +if (asrc->use_edma && (dma_params_be->maxburst %params_channels (params))) { +if (dma_params_be->maxburst >=params_channels (params)) { + config_be.src_maxburst =params_channels (params); + config_be.dst_maxburst =params_channels (params); + }else { + config_be.src_maxburst =1 ; + config_be.dst_maxburst =1 ; + } + } +memset (&audio_config,0 ,sizeof (audio_config)); config_be.peripheral_config = &audio_config; config_be.peripheral_size =sizeof (audio_config);
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 940/1611 net: udp_tunnel: prevent double queueing in udp_tunnel_nic_device_sync
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Eric Dumazet <[email protected]>
[ Upstream commit ecf69d4b43370c587e48d4d70289dbdb7e039d4d ]
Yue Sun reported a use-after-free and debugobjects warning in udp_tunnel_nic_device_sync_work() during concurrent device operations.
The workqueue core clears the internal pending bit before invoking the worker. At that point, a concurrent thread can queue the work again. When the already running worker eventually clears the work_pending flag to 0, it mistakenly clears the flag for the newly queued instance. udp_tunnel_nic_unregister() then observes work_pending as 0 and frees the structure while the second work item is still active in the queue, leading to UAF.
Fix this by returning early in udp_tunnel_nic_device_sync() if work_pending is already set, preventing redundant work queueing.
--- net/ipv4/udp_tunnel_nic.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
net/ipv4/udp_tunnel_nic.c +1 -1
@@ -301,7 +301,7 @@ __udp_tunnel_nic_device_sync(struct net_device *dev, struct udp_tunnel_nic *utn)static void udp_tunnel_nic_device_sync (struct net_device *dev,struct udp_tunnel_nic *utn) { -if (!utn->need_sync) +if (!utn->need_sync || utn->work_pending)return ;queue_work (udp_tunnel_nic_workqueue, &utn->work);
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 941/1611 dt-bindings: net: renesas,ether: Drop example "ethernet-phy-ieee802.3-c22" fallback
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Rob Herring (Arm) <[email protected]>
[ Upstream commit 14eb1d2c03b38ce3427f299967f7a4d97ebff4c2 ]
Fix the Micrel PHY in the example which shouldn't have the fallback "ethernet-phy-ieee802.3-c22" compatible:
Documentation/devicetree/bindings/net/renesas,ether.example.dtb: ethernet-phy@1 \
(ethernet-phy-id0022.1537): compatible: ['ethernet-phy-id0022.1537', 'ethernet-phy-ieee802.3-c22'] is too long
from schema $id: http://devicetree.org/schemas/net/micrel.yaml
--- Documentation/devicetree/bindings/net/renesas,ether.yaml | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-)
Documentation/devicetree/bindings/net/renesas,ether.yaml +1 -2
@@ -121,8 +121,7 @@ examples: #size-cells = <0>; phy1: ethernet-phy@1 { - compatible = "ethernet-phy-id0022.1537", - "ethernet-phy-ieee802.3-c22"; + compatible = "ethernet-phy-id0022.1537"; reg = <1>; interrupt-parent = <&irqc0>; interrupts = <0 IRQ_TYPE_LEVEL_LOW>;
Signature · 1 line
2.53.0
Greg Kroah-Hartman
maintainerPATCH 942/1611 selftests: tls: size splice_short pipe by page size
In reply to Greg Kroah-Hartman6.18-stable review patch. If anyone has any objections, please let me know.
------------------
From: Nirmoy Das <[email protected]>
[ Upstream commit 3e52f56875c6fafee619b5c2b4ded25f2efbd2ec ]
splice_short grows its pipe with (MAX_FRAGS + 1) * 0x1000 so it can queue one short vmsplice() buffer for each fragment before draining the pipe. That assumes 4K pipe buffers.
On 64K-page kernels the request is rounded to 262144 bytes, which provides only four pipe buffers. The fifth one-byte vmsplice() blocks in pipe_wait_writable and the test times out before it reaches the TLS path.
Request enough bytes for the same number of pipe buffers using the runtime page size, and assert that the kernel granted at least that much. If an unprivileged run cannot raise the pipe above the system pipe-max-size limit, skip the test because it cannot exercise the intended path.
--- tools/testing/selftests/net/tls.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-)
tools/testing/selftests/net/tls.c +7 -1
@@ -954,6 +954,8 @@ TEST_F(tls, splice_short)char sendbuf[0x100 ];char sendchar ='S' ;int pipefds[2 ]; +int pipe_sz; +int ret;int i; sendchar_iov.iov_base = &sendchar;
@@ -962,7 +964,11 @@ TEST_F(tls, splice_short)memset (sendbuf,'s' ,sizeof (sendbuf));ASSERT_GE (pipe2 (pipefds,O_NONBLOCK ),0 ); -ASSERT_GE (fcntl (pipefds[0 ],F_SETPIPE_SZ , (MAX_FRAGS +1 ) *0x1000 ),0 ); + pipe_sz = (MAX_FRAGS +1 ) *getpagesize (); + ret =fcntl (pipefds[0 ],F_SETPIPE_SZ , pipe_sz); +if (ret <0 && errno ==EPERM ) +SKIP (return,"insufficient pipe capacity" ); +ASSERT_GE (ret, pipe_sz);for (i =0 ; i <MAX_FRAGS ; i++)ASSERT_GE (vmsplice (pipefds[1 ], &sendchar_iov,1 ,0 ),0 );
Signature · 1 line
2.53.0