Skip to contentSkip to conversation

6.18.17-rc1 review

PATCH In review Sasha Levin 16 participants 334 messages Mar 10 – Mar 17 Page 2 of 3

Subsystems (11)
lore
Share & tools
lore
author maintainer
#124 lore raw

PATCH 118/314 btrfs: zoned: fixup last alloc pointer after extent removal for RAID0/10

In reply to Sasha Levin

From: Naohiro Aota <[email protected]>

[ Upstream commit 52ee9965d09b2c56a027613db30d1fb20d623861 ]

When a block group is composed of a sequential write zone and a conventional zone, we recover the (pseudo) write pointer of the conventional zone using the end of the last allocated position.

However, if the last extent in a block group is removed, the last extent position will be smaller than the other real write pointer position. Then, that will cause an error due to mismatch of the write pointers.

We can fixup this case by moving the alloc_offset to the corresponding write pointer position.

Fixes 568220fa9657 ("btrfs: zoned: support RAID0/1/10 on top of raid stripe tree")
---
 fs/btrfs/zoned.c | 194 +++++++++++++++++++++++++++++++++++++++++++----
 1 file changed, 179 insertions(+), 15 deletions(-)
fs/btrfs/zoned.c +179 -15
index 4cbe1ba7af66d..e14a4234954ba 100644
@@ -1553,7 +1553,9 @@ static int btrfs_load_block_group_raid0(struct btrfs_block_group *bg,
 {
 	struct btrfs_fs_info *fs_info = bg->fs_info;
 	u64 stripe_nr = 0, stripe_offset = 0;
+	u64 prev_offset = 0;
 	u32 stripe_index = 0;
+	bool has_partial = false, has_conventional = false;
 
 	if ((map->type & BTRFS_BLOCK_GROUP_DATA) && !fs_info->stripe_root) {
 		btrfs_err(fs_info, "zoned: data %s needs raid-stripe-tree",
@@ -1561,6 +1563,35 @@ static int btrfs_load_block_group_raid0(struct btrfs_block_group *bg,
 		return -EINVAL;
 	}
 
+	/*
+	 * When the last extent is removed, last_alloc can be smaller than the other write
+	 * pointer. In that case, last_alloc should be moved to the corresponding write
+	 * pointer position.
+	 */
+	for (int i = 0; i < map->num_stripes; i++) {
+		u64 alloc;
+
+		if (zone_info[i].alloc_offset == WP_MISSING_DEV ||
+		    zone_info[i].alloc_offset == WP_CONVENTIONAL)
+			continue;
+
+		stripe_nr = zone_info[i].alloc_offset >> BTRFS_STRIPE_LEN_SHIFT;
+		stripe_offset = zone_info[i].alloc_offset & BTRFS_STRIPE_LEN_MASK;
+		if (stripe_offset == 0 && stripe_nr > 0) {
+			stripe_nr--;
+			stripe_offset = BTRFS_STRIPE_LEN;
+		}
+		alloc = ((stripe_nr * map->num_stripes + i) << BTRFS_STRIPE_LEN_SHIFT) +
+			stripe_offset;
+		last_alloc = max(last_alloc, alloc);
+
+		/* Partially written stripe found. It should be last. */
+		if (zone_info[i].alloc_offset & BTRFS_STRIPE_LEN_MASK)
+			break;
+	}
+	stripe_nr = 0;
+	stripe_offset = 0;
+
 	if (last_alloc) {
 		u32 factor = map->num_stripes;
 
@@ -1574,7 +1605,7 @@ static int btrfs_load_block_group_raid0(struct btrfs_block_group *bg,
 			continue;
 
 		if (zone_info[i].alloc_offset == WP_CONVENTIONAL) {
-
+			has_conventional = true;
 			zone_info[i].alloc_offset = btrfs_stripe_nr_to_offset(stripe_nr);
 
 			if (stripe_index > i)
@@ -1583,6 +1614,28 @@ static int btrfs_load_block_group_raid0(struct btrfs_block_group *bg,
 				zone_info[i].alloc_offset += stripe_offset;
 		}
 
+		/* Verification */
+		if (i != 0) {
+			if (unlikely(prev_offset < zone_info[i].alloc_offset)) {
+				btrfs_err(fs_info,
+				"zoned: stripe position disorder found in block group %llu",
+					  bg->start);
+				return -EIO;
+			}
+
+			if (unlikely(has_partial &&
+				     (zone_info[i].alloc_offset & BTRFS_STRIPE_LEN_MASK))) {
+				btrfs_err(fs_info,
+				"zoned: multiple partial written stripe found in block group %llu",
+					  bg->start);
+				return -EIO;
+			}
+		}
+		prev_offset = zone_info[i].alloc_offset;
+
+		if ((zone_info[i].alloc_offset & BTRFS_STRIPE_LEN_MASK) != 0)
+			has_partial = true;
+
 		if (test_bit(0, active) != test_bit(i, active)) {
 			if (unlikely(!btrfs_zone_activate(bg)))
 				return -EIO;
@@ -1594,6 +1647,19 @@ static int btrfs_load_block_group_raid0(struct btrfs_block_group *bg,
 		bg->alloc_offset += zone_info[i].alloc_offset;
 	}
 
+	/* Check if all devices stay in the same stripe row. */
+	if (unlikely(zone_info[0].alloc_offset -
+		     zone_info[map->num_stripes - 1].alloc_offset > BTRFS_STRIPE_LEN)) {
+		btrfs_err(fs_info, "zoned: stripe gap too large in block group %llu", bg->start);
+		return -EIO;
+	}
+
+	if (unlikely(has_conventional && bg->alloc_offset < last_alloc)) {
+		btrfs_err(fs_info, "zoned: allocated extent stays beyond write pointers %llu %llu",
+			  bg->alloc_offset, last_alloc);
+		return -EIO;
+	}
+
 	return 0;
 }
 
@@ -1604,8 +1670,11 @@ static int btrfs_load_block_group_raid10(struct btrfs_block_group *bg,
 					 u64 last_alloc)
 {
 	struct btrfs_fs_info *fs_info = bg->fs_info;
+	u64 AUTO_KFREE(raid0_allocs);
 	u64 stripe_nr = 0, stripe_offset = 0;
 	u32 stripe_index = 0;
+	bool has_partial = false, has_conventional = false;
+	u64 prev_offset = 0;
 
 	if ((map->type & BTRFS_BLOCK_GROUP_DATA) && !fs_info->stripe_root) {
 		btrfs_err(fs_info, "zoned: data %s needs raid-stripe-tree",
@@ -1613,6 +1682,60 @@ static int btrfs_load_block_group_raid10(struct btrfs_block_group *bg,
 		return -EINVAL;
 	}
 
+	raid0_allocs = kcalloc(map->num_stripes / map->sub_stripes, sizeof(*raid0_allocs),
+			       GFP_NOFS);
+	if (!raid0_allocs)
+		return -ENOMEM;
+
+	/*
+	 * When the last extent is removed, last_alloc can be smaller than the other write
+	 * pointer. In that case, last_alloc should be moved to the corresponding write
+	 * pointer position.
+	 */
+	for (int i = 0; i < map->num_stripes; i += map->sub_stripes) {
+		u64 alloc = zone_info[i].alloc_offset;
+
+		for (int j = 1; j < map->sub_stripes; j++) {
+			int idx = i + j;
+
+			if (zone_info[idx].alloc_offset == WP_MISSING_DEV ||
+			    zone_info[idx].alloc_offset == WP_CONVENTIONAL)
+				continue;
+			if (alloc == WP_MISSING_DEV || alloc == WP_CONVENTIONAL) {
+				alloc = zone_info[idx].alloc_offset;
+			} else if (unlikely(zone_info[idx].alloc_offset != alloc)) {
+				btrfs_err(fs_info,
+				"zoned: write pointer mismatch found in block group %llu",
+					  bg->start);
+				return -EIO;
+			}
+		}
+
+		raid0_allocs[i / map->sub_stripes] = alloc;
+		if (alloc == WP_CONVENTIONAL)
+			continue;
+		if (unlikely(alloc == WP_MISSING_DEV)) {
+			btrfs_err(fs_info,
+			"zoned: cannot recover write pointer of block group %llu due to missing device",
+				  bg->start);
+			return -EIO;
+		}
+
+		stripe_nr = alloc >> BTRFS_STRIPE_LEN_SHIFT;
+		stripe_offset = alloc & BTRFS_STRIPE_LEN_MASK;
+		if (stripe_offset == 0 && stripe_nr > 0) {
+			stripe_nr--;
+			stripe_offset = BTRFS_STRIPE_LEN;
+		}
+
+		alloc = ((stripe_nr * (map->num_stripes / map->sub_stripes) +
+			  (i / map->sub_stripes)) <<
+			 BTRFS_STRIPE_LEN_SHIFT) + stripe_offset;
+		last_alloc = max(last_alloc, alloc);
+	}
+	stripe_nr = 0;
+	stripe_offset = 0;
+
 	if (last_alloc) {
 		u32 factor = map->num_stripes / map->sub_stripes;
 
@@ -1622,24 +1745,51 @@ static int btrfs_load_block_group_raid10(struct btrfs_block_group *bg,
 	}
 
 	for (int i = 0; i < map->num_stripes; i++) {
-		if (zone_info[i].alloc_offset == WP_MISSING_DEV)
-			continue;
+		int idx = i / map->sub_stripes;
 
-		if (test_bit(0, active) != test_bit(i, active)) {
-			if (unlikely(!btrfs_zone_activate(bg)))
-				return -EIO;
-		} else {
-			if (test_bit(0, active))
-				set_bit(BLOCK_GROUP_FLAG_ZONE_IS_ACTIVE, &bg->runtime_flags);
+		if (raid0_allocs[idx] == WP_CONVENTIONAL) {
+			has_conventional = true;
+			raid0_allocs[idx] = btrfs_stripe_nr_to_offset(stripe_nr);
+
+			if (stripe_index > idx)
+				raid0_allocs[idx] += BTRFS_STRIPE_LEN;
+			else if (stripe_index == idx)
+				raid0_allocs[idx] += stripe_offset;
 		}
 
-		if (zone_info[i].alloc_offset == WP_CONVENTIONAL) {
-			zone_info[i].alloc_offset = btrfs_stripe_nr_to_offset(stripe_nr);
+		if ((i % map->sub_stripes) == 0) {
+			/* Verification */
+			if (i != 0) {
+				if (unlikely(prev_offset < raid0_allocs[idx])) {
+					btrfs_err(fs_info,
+					"zoned: stripe position disorder found in block group %llu",
+						  bg->start);
+					return -EIO;
+				}
 
-			if (stripe_index > (i / map->sub_stripes))
-				zone_info[i].alloc_offset += BTRFS_STRIPE_LEN;
-			else if (stripe_index == (i / map->sub_stripes))
-				zone_info[i].alloc_offset += stripe_offset;
+				if (unlikely(has_partial &&
+					     (raid0_allocs[idx] & BTRFS_STRIPE_LEN_MASK))) {
+					btrfs_err(fs_info,
+					"zoned: multiple partial written stripe found in block group %llu",
+						  bg->start);
+					return -EIO;
+				}
+			}
+			prev_offset = raid0_allocs[idx];
+
+			if ((raid0_allocs[idx] & BTRFS_STRIPE_LEN_MASK) != 0)
+				has_partial = true;
+		}
+
+		if (zone_info[i].alloc_offset == WP_MISSING_DEV ||
+		    zone_info[i].alloc_offset == WP_CONVENTIONAL)
+			zone_info[i].alloc_offset = raid0_allocs[idx];
+
+		if (test_bit(0, active) != test_bit(i, active)) {
+			if (unlikely(!btrfs_zone_activate(bg)))
+				return -EIO;
+		} else if (test_bit(0, active)) {
+			set_bit(BLOCK_GROUP_FLAG_ZONE_IS_ACTIVE, &bg->runtime_flags);
 		}
 
 		if ((i % map->sub_stripes) == 0) {
@@ -1648,6 +1798,20 @@ static int btrfs_load_block_group_raid10(struct btrfs_block_group *bg,
 		}
 	}
 
+	/* Check if all devices stay in the same stripe row. */
+	if (unlikely(zone_info[0].alloc_offset -
+		     zone_info[map->num_stripes - 1].alloc_offset > BTRFS_STRIPE_LEN)) {
+		btrfs_err(fs_info, "zoned: stripe gap too large in block group %llu",
+			  bg->start);
+		return -EIO;
+	}
+
+	if (unlikely(has_conventional && bg->alloc_offset < last_alloc)) {
+		btrfs_err(fs_info, "zoned: allocated extent stays beyond write pointers %llu %llu",
+			  bg->alloc_offset, last_alloc);
+		return -EIO;
+	}
+
 	return 0;
 }
 
Signature · 1 line
2.51.0
author maintainer
#125 lore raw

PATCH 119/314 PM: sleep: core: Avoid bit field races related to work_in_progress

In reply to Sasha Levin

From: Xuewen Yan <[email protected]>

[ Upstream commit 0491f3f9f664e7e0131eb4d2a8b19c49562e5c64 ]

In all of the system suspend transition phases, the async processing of a device may be carried out in parallel with power.work_in_progress updates for the device's parent or suppliers and if it touches bit fields from the same group (for example, power.must_resume or power.wakeup_path), bit field corruption is possible.

To avoid that, turn work_in_progress in struct dev_pm_info into a proper bool field and relocate it to save space.

Fixes aa7a9275ab81 ("PM: sleep: Suspend async parents after suspending children")
Fixes 443046d1ad66 ("PM: sleep: Make suspend of devices more asynchronous")
Cc All applicable <[email protected]>
[ rjw: Added subject and changelog ]
---
 include/linux/pm.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
include/linux/pm.h +1 -1
index cc7b2dc28574c..12782f775a17e 100644
@@ -677,10 +677,10 @@ struct dev_pm_info {
 	struct list_head	entry;
 	struct completion	completion;
 	struct wakeup_source	*wakeup;
+	bool			work_in_progress;	/* Owned by the PM core */
 	bool			wakeup_path:1;
 	bool			syscore:1;
 	bool			no_pm_callbacks:1;	/* Owned by the PM core */
-	bool			work_in_progress:1;	/* Owned by the PM core */
 	bool			smart_suspend:1;	/* Owned by the PM core */
 	bool			must_resume:1;		/* Owned by the PM core */
 	bool			may_skip_resume:1;	/* Set by subsystems */
Signature · 1 line
2.51.0
author maintainer
#126 lore raw

PATCH 120/314 drm/amd: Fix hang on amdgpu unload by using pci_dev_is_disconnected()

In reply to Sasha Levin

From: Mario Limonciello <[email protected]>

[ Upstream commit f7afda7fcd169a9168695247d07ad94cf7b9798f ]

The commit 6a23e7b4332c ("drm/amd: Clean up kfd node on surprise disconnect") introduced early KFD cleanup when drm_dev_is_unplugged() returns true. However, this causes hangs during normal module unload (rmmod amdgpu).

The issue occurs because drm_dev_unplug() is called in amdgpu_pci_remove() for all removal scenarios, not just surprise disconnects. This was done intentionally in commit 39934d3ed572 ("Revert "drm/amdgpu: TA unload messages are not actually sent to psp when amdgpu is uninstalled"") to fix IGT PCI software unplug test failures. As a result, drm_dev_is_unplugged() returns true even during normal module unload, triggering the early KFD cleanup inappropriately.

The correct check should distinguish between:
- Actual surprise disconnect (eGPU unplugged): pci_dev_is_disconnected() returns true
- Normal module unload (rmmod): pci_dev_is_disconnected() returns false

Replace drm_dev_is_unplugged() with pci_dev_is_disconnected() to ensure the early cleanup only happens during true hardware disconnect events.

---
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +2 -2
index fb096bf551ef2..dbcd55611a37d 100644
@@ -4991,7 +4991,7 @@ void amdgpu_device_fini_hw(struct amdgpu_device *adev)
 	 * before ip_fini_early to prevent kfd locking refcount issues by calling
 	 * amdgpu_amdkfd_suspend()
 	 */
-	if (drm_dev_is_unplugged(adev_to_drm(adev)))
+	if (pci_dev_is_disconnected(adev->pdev))
 		amdgpu_amdkfd_device_fini_sw(adev);
 
 	amdgpu_device_ip_fini_early(adev);
@@ -5003,7 +5003,7 @@ void amdgpu_device_fini_hw(struct amdgpu_device *adev)
 
 	amdgpu_gart_dummy_page_fini(adev);
 
-	if (drm_dev_is_unplugged(adev_to_drm(adev)))
+	if (pci_dev_is_disconnected(adev->pdev))
 		amdgpu_device_unmap_mmio(adev);
 
 }
Signature · 1 line
2.51.0
author maintainer
#127 lore raw

PATCH 121/314 hwmon: (max16065) Use READ/WRITE_ONCE to avoid compiler optimization induced race

In reply to Sasha Levin

From: Gui-Dong Han <[email protected]>

[ Upstream commit 007be4327e443d79c9dd9e56dc16c36f6395d208 ]

Simply copying shared data to a local variable cannot prevent data races. The compiler is allowed to optimize away the local copy and re-read the shared memory, causing a Time-of-Check Time-of-Use (TOCTOU) issue if the data changes between the check and the usage.

To enforce the use of the local variable, use READ_ONCE() when reading the shared data and WRITE_ONCE() when updating it. Apply these macros to the three identified locations (curr_sense, adc, and fault) where local variables are used for error validation, ensuring the value remains consistent.

Fixes f5bae2642e3d ("hwmon: Driver for MAX16065 System Manager and compatibles")
Fixes b8d5acdcf525 ("hwmon: (max16065) Use local variable to avoid TOCTOU")
---
 drivers/hwmon/max16065.c | 26 +++++++++++++-------------
 1 file changed, 13 insertions(+), 13 deletions(-)
drivers/hwmon/max16065.c +13 -13
index 4c9e7892a73c1..43fbb9b26b102 100644
@@ -151,27 +151,27 @@ static struct max16065_data *max16065_update_device(struct device *dev)
 		int i;
 
 		for (i = 0; i < data->num_adc; i++)
-			data->adc[i]
-			  = max16065_read_adc(client, MAX16065_ADC(i));
+			WRITE_ONCE(data->adc[i],
+				   max16065_read_adc(client, MAX16065_ADC(i)));
 
 		if (data->have_current) {
-			data->adc[MAX16065_NUM_ADC]
-			  = max16065_read_adc(client, MAX16065_CSP_ADC);
-			data->curr_sense
-			  = i2c_smbus_read_byte_data(client,
-						     MAX16065_CURR_SENSE);
+			WRITE_ONCE(data->adc[MAX16065_NUM_ADC],
+				   max16065_read_adc(client, MAX16065_CSP_ADC));
+			WRITE_ONCE(data->curr_sense,
+				   i2c_smbus_read_byte_data(client, MAX16065_CURR_SENSE));
 		}
 
 		for (i = 0; i < 2; i++)
-			data->fault[i]
-			  = i2c_smbus_read_byte_data(client, MAX16065_FAULT(i));
+			WRITE_ONCE(data->fault[i],
+				   i2c_smbus_read_byte_data(client, MAX16065_FAULT(i)));
 
 		/*
 		 * MAX16067 and MAX16068 have separate undervoltage and
 		 * overvoltage alarm bits. Squash them together.
 		 */
 		if (data->chip == max16067 || data->chip == max16068)
-			data->fault[0] |= data->fault[1];
+			WRITE_ONCE(data->fault[0],
+				   data->fault[0] | data->fault[1]);
 
 		data->last_updated = jiffies;
 		data->valid = true;
@@ -185,7 +185,7 @@ static ssize_t max16065_alarm_show(struct device *dev,
 {
 	struct sensor_device_attribute_2 *attr2 = to_sensor_dev_attr_2(da);
 	struct max16065_data *data = max16065_update_device(dev);
-	int val = data->fault[attr2->nr];
+	int val = READ_ONCE(data->fault[attr2->nr]);
 
 	if (val < 0)
 		return val;
@@ -203,7 +203,7 @@ static ssize_t max16065_input_show(struct device *dev,
 {
 	struct sensor_device_attribute *attr = to_sensor_dev_attr(da);
 	struct max16065_data *data = max16065_update_device(dev);
-	int adc = data->adc[attr->index];
+	int adc = READ_ONCE(data->adc[attr->index]);
 
 	if (unlikely(adc < 0))
 		return adc;
@@ -216,7 +216,7 @@ static ssize_t max16065_current_show(struct device *dev,
 				     struct device_attribute *da, char *buf)
 {
 	struct max16065_data *data = max16065_update_device(dev);
-	int curr_sense = data->curr_sense;
+	int curr_sense = READ_ONCE(data->curr_sense);
 
 	if (unlikely(curr_sense < 0))
 		return curr_sense;
Signature · 1 line
2.51.0
author maintainer
#128 lore raw

PATCH 122/314 slub: remove CONFIG_SLUB_TINY specific code paths

In reply to Sasha Levin

From: Vlastimil Babka <[email protected]>

[ Upstream commit 31e0886fd57d426d18a239dd55e176032c9c1cb0 ]

CONFIG_SLUB_TINY minimizes the SLUB's memory overhead in multiple ways, mainly by avoiding percpu caching of slabs and objects. It also reduces code size by replacing some code paths with simplified ones through ifdefs, but the benefits of that are smaller and would complicate the upcoming changes.

Thus remove these code paths and associated ifdefs and simplify the code base.

Stable-dep-of: a1e244a9f177 ("mm/slab: use prandom if !allow_spin")

---
 mm/slab.h |   2 -
 mm/slub.c | 107 ++----------------------------------------------------
 2 files changed, 4 insertions(+), 105 deletions(-)
mm/slab.h +0 -2
index bf9d8940b8f21..36893299fa67c 100644
@@ -236,10 +236,8 @@ struct kmem_cache_order_objects {
  * Slab cache management.
  */
 struct kmem_cache {
-#ifndef CONFIG_SLUB_TINY
 	struct kmem_cache_cpu __percpu *cpu_slab;
 	struct lock_class_key lock_key;
-#endif
 	struct slub_percpu_sheaves __percpu *cpu_sheaves;
 	/* Used for retrieving partial slabs, etc. */
 	slab_flags_t flags;
mm/slub.c +4 -103

265 lines not on this page · raw message

Signature · 1 line
2.51.0
author maintainer
#129 lore raw

PATCH 123/314 mm/slab: use prandom if !allow_spin

In reply to Sasha Levin

From: Harry Yoo <[email protected]>

[ Upstream commit a1e244a9f177894969c6cd5ebbc6d72c19fc4a7a ]

When CONFIG_SLAB_FREELIST_RANDOM is enabled and get_random_u32() is called in an NMI context, lockdep complains because it acquires a local_lock:

================================
WARNING: inconsistent lock state
6.19.0-rc5-slab-for-next+ #325 Tainted: G N
--------------------------------
inconsistent {INITIAL USE} -> {IN-NMI} usage.
kunit_try_catch/8312 [HC2[2]:SC0[0]:HE0:SE1] takes:
ffff88a02ec49cc0 (batched_entropy_u32.lock){-.-.}-{3:3}, at: get_random_u32+0x7f/0x2e0 {INITIAL USE} state was registered at:

    lock_acquire+0xd9/0x2f0
    get_random_u32+0x93/0x2e0
    __get_random_u32_below+0x17/0x70
    cache_random_seq_create+0x121/0x1c0
    init_cache_random_seq+0x5d/0x110
    do_kmem_cache_create+0x1e0/0xa30
    __kmem_cache_create_args+0x4ec/0x830
    create_kmalloc_caches+0xe6/0x130
    kmem_cache_init+0x1b1/0x660
    mm_core_init+0x1d8/0x4b0
    start_kernel+0x620/0xcd0
    x86_64_start_reservations+0x18/0x30
    x86_64_start_kernel+0xf3/0x140
    common_startup_64+0x13e/0x148
  irq event stamp: 76
  hardirqs last  enabled at (75): [<ffffffff8298b77a>] exc_nmi+0x11a/0x240
  hardirqs last disabled at (76): [<ffffffff8298b991>] sysvec_irq_work+0x11/0x110
  softirqs last  enabled at (0): [<ffffffff813b2dda>] copy_process+0xc7a/0x2350
  softirqs last disabled at (0): [<0000000000000000>] 0x0

other info that might help us debug this:

   Possible unsafe locking scenario:
         CPU0
         ----
    lock(batched_entropy_u32.lock);
    <Interrupt>
      lock(batched_entropy_u32.lock);

*** DEADLOCK ***

Fix this by using pseudo-random number generator if !allow_spin. This means kmalloc_nolock() users won't get truly random numbers, but there is not much we can do about it.

Note that an NMI handler might interrupt prandom_u32_state() and change the random state, but that's safe.

---
 mm/slub.c | 28 ++++++++++++++++++++++++----
 1 file changed, 24 insertions(+), 4 deletions(-)
mm/slub.c +24 -4
index 4db84fbc71bab..870b8e00a938b 100644
@@ -41,6 +41,7 @@
 #include <linux/prefetch.h>
 #include <linux/memcontrol.h>
 #include <linux/random.h>
+#include <linux/prandom.h>
 #include <kunit/test.h>
 #include <kunit/test-bug.h>
 #include <linux/sort.h>
@@ -3176,8 +3177,11 @@ static void *next_freelist_entry(struct kmem_cache *s,
 	return (char *)start + idx;
 }
 
+static DEFINE_PER_CPU(struct rnd_state, slab_rnd_state);
+
 /* Shuffle the single linked freelist based on a random pre-computed sequence */
-static bool shuffle_freelist(struct kmem_cache *s, struct slab *slab)
+static bool shuffle_freelist(struct kmem_cache *s, struct slab *slab,
+			     bool allow_spin)
 {
 	void *start;
 	void *cur;
@@ -3188,7 +3192,19 @@ static bool shuffle_freelist(struct kmem_cache *s, struct slab *slab)
 		return false;
 
 	freelist_count = oo_objects(s->oo);
-	pos = get_random_u32_below(freelist_count);
+	if (allow_spin) {
+		pos = get_random_u32_below(freelist_count);
+	} else {
+		struct rnd_state *state;
+
+		/*
+		 * An interrupt or NMI handler might interrupt and change
+		 * the state in the middle, but that's safe.
+		 */
+		state = &get_cpu_var(slab_rnd_state);
+		pos = prandom_u32_state(state) % freelist_count;
+		put_cpu_var(slab_rnd_state);
+	}
 
 	page_limit = slab->objects * s->size;
 	start = fixup_red_left(s, slab_address(slab));
@@ -3215,7 +3231,8 @@ static inline int init_cache_random_seq(struct kmem_cache *s)
 	return 0;
 }
 static inline void init_freelist_randomization(void) { }
-static inline bool shuffle_freelist(struct kmem_cache *s, struct slab *slab)
+static inline bool shuffle_freelist(struct kmem_cache *s, struct slab *slab,
+				    bool allow_spin)
 {
 	return false;
 }
@@ -3300,7 +3317,7 @@ static struct slab *allocate_slab(struct kmem_cache *s, gfp_t flags, int node)
 
 	setup_slab_debug(s, slab, start);
 
-	shuffle = shuffle_freelist(s, slab);
+	shuffle = shuffle_freelist(s, slab, allow_spin);
 
 	if (!shuffle) {
 		start = fixup_red_left(s, start);
@@ -8511,6 +8528,9 @@ void __init kmem_cache_init_late(void)
 {
 	flushwq = alloc_workqueue("slub_flushwq", WQ_MEM_RECLAIM, 0);
 	WARN_ON(!flushwq);
+#ifdef CONFIG_SLAB_FREELIST_RANDOM
+	prandom_init_once(&slab_rnd_state);
+#endif
 }
 
 struct kmem_cache *
Signature · 1 line
2.51.0
author maintainer
#130 lore raw

PATCH 124/314 LoongArch: Remove unnecessary checks for ORC unwinder

In reply to Sasha Levin

From: Tiezhu Yang <[email protected]>

[ Upstream commit 4cd641a79e69270a062777f64a0dd330abb9044a ]

According to the following function definitions, __kernel_text_address() already checks __module_text_address(), so it should remove the check of __module_text_address() in bt_address() at least.

int __kernel_text_address(unsigned long addr)

{
	if (kernel_text_address(addr))
		return 1;
	...
	return 0;
}

int kernel_text_address(unsigned long addr)

{
	bool no_rcu;
	int ret = 1;
	...
	if (is_module_text_address(addr))
		goto out;
	...
	return ret;
}

bool is_module_text_address(unsigned long addr)

{
	guard(rcu)();
	return __module_text_address(addr) != NULL;
}

Furthermore, there are two checks of __kernel_text_address(), one is in bt_address() and the other is after calling bt_address(), it looks like redundant.

Handle the exception address first and then use __kernel_text_address() to validate the calculated address for exception or the normal address in bt_address(), then it can remove the check of __kernel_text_address() after calling bt_address().

Just remove unnecessary checks, no functional changes intended.

Stable-dep-of: 055c7e75190e ("LoongArch: Handle percpu handler address for ORC unwinder")

---
 arch/loongarch/kernel/unwind_orc.c | 16 +++++-----------
 1 file changed, 5 insertions(+), 11 deletions(-)
arch/loongarch/kernel/unwind_orc.c +5 -11
index e410048489c66..b67f065905256 100644
@@ -360,12 +360,6 @@ static inline unsigned long bt_address(unsigned long ra)
 {
 	extern unsigned long eentry;
 
-	if (__kernel_text_address(ra))
-		return ra;
-
-	if (__module_text_address(ra))
-		return ra;
-
 	if (ra >= eentry && ra < eentry +  EXCCODE_INT_END * VECSIZE) {
 		unsigned long func;
 		unsigned long type = (ra - eentry) / VECSIZE;
@@ -383,10 +377,13 @@ static inline unsigned long bt_address(unsigned long ra)
 			break;
 		}
 
-		return func + offset;
+		ra = func + offset;
 	}
 
-	return ra;
+	if (__kernel_text_address(ra))
+		return ra;
+
+	return 0;
 }
 
 bool unwind_next_frame(struct unwind_state *state)
@@ -512,9 +509,6 @@ bool unwind_next_frame(struct unwind_state *state)
 		goto err;
 	}
 
-	if (!__kernel_text_address(state->pc))
-		goto err;
-
 	return true;
 
 err:
Signature · 1 line
2.51.0
author maintainer
#131 lore raw

PATCH 125/314 LoongArch: Handle percpu handler address for ORC unwinder

In reply to Sasha Levin

From: Tiezhu Yang <[email protected]>

[ Upstream commit 055c7e75190e0be43037bd663a3f6aced194416e ]

After commit 4cd641a79e69 ("LoongArch: Remove unnecessary checks for ORC unwinder"), the system can not boot normally under some configs (such as enable KASAN), there are many error messages "cannot find unwind pc".

The kernel boots normally with the defconfig, so no problem found out at the first time. Here is one way to reproduce:

  cd linux
  make mrproper defconfig -j"$(nproc)"
  scripts/config -e KASAN
  make olddefconfig all -j"$(nproc)"
  sudo make modules_install
  sudo make install
  sudo reboot

The address that can not unwind is not a valid kernel address which is between "pcpu_handlers[cpu]" and "pcpu_handlers[cpu] + vec_sz" due to the code of eentry was copied to the new area of pcpu_handlers[cpu] in setup_tlb_handler(), handle this special case to get the valid address to unwind normally.

---
 arch/loongarch/include/asm/setup.h |  3 +++
 arch/loongarch/kernel/unwind_orc.c | 16 ++++++++++++++++
 2 files changed, 19 insertions(+)
arch/loongarch/include/asm/setup.h +3 -0
index 3c2fb16b11b64..f81375e5e89c0 100644
@@ -7,6 +7,7 @@
 #define _LOONGARCH_SETUP_H
 
 #include <linux/types.h>
+#include <linux/threads.h>
 #include <asm/sections.h>
 #include <uapi/asm/setup.h>
 
@@ -14,6 +15,8 @@
 
 extern unsigned long eentry;
 extern unsigned long tlbrentry;
+extern unsigned long pcpu_handlers[NR_CPUS];
+extern long exception_handlers[VECSIZE * 128 / sizeof(long)];
 extern char init_command_line[COMMAND_LINE_SIZE];
 extern void tlb_init(int cpu);
 extern void cpu_cache_init(void);
arch/loongarch/kernel/unwind_orc.c +16 -0
index b67f065905256..ad7e63f495045 100644
@@ -360,6 +360,22 @@ static inline unsigned long bt_address(unsigned long ra)
 {
 	extern unsigned long eentry;
 
+#if defined(CONFIG_NUMA) && !defined(CONFIG_PREEMPT_RT)
+	int cpu;
+	int vec_sz = sizeof(exception_handlers);
+
+	for_each_possible_cpu(cpu) {
+		if (!pcpu_handlers[cpu])
+			continue;
+
+		if (ra >= pcpu_handlers[cpu] &&
+		    ra < pcpu_handlers[cpu] + vec_sz) {
+			ra = ra + eentry - pcpu_handlers[cpu];
+			break;
+		}
+	}
+#endif
+
 	if (ra >= eentry && ra < eentry +  EXCCODE_INT_END * VECSIZE) {
 		unsigned long func;
 		unsigned long type = (ra - eentry) / VECSIZE;
Signature · 1 line
2.51.0
author maintainer
#132 lore raw

PATCH 126/314 LoongArch: Remove some extern variables in source files

In reply to Sasha Levin

From: Tiezhu Yang <[email protected]>

[ Upstream commit 0e6f596d6ac635e80bb265d587b2287ef8fa1cd6 ]

There are declarations of the variable "eentry", "pcpu_handlers[]" and "exception_handlers[]" in asm/setup.h, the source files already include this header file directly or indirectly, so no need to declare them in the source files, just remove the code.

---
 arch/loongarch/kernel/unwind_orc.c      | 2 --
 arch/loongarch/kernel/unwind_prologue.c | 4 ----
 arch/loongarch/mm/tlb.c                 | 1 -
 3 files changed, 7 deletions(-)
arch/loongarch/kernel/unwind_orc.c +0 -2
index ad7e63f495045..85c2fcb76930c 100644
@@ -358,8 +358,6 @@ static bool is_entry_func(unsigned long addr)
 
 static inline unsigned long bt_address(unsigned long ra)
 {
-	extern unsigned long eentry;
-
 #if defined(CONFIG_NUMA) && !defined(CONFIG_PREEMPT_RT)
 	int cpu;
 	int vec_sz = sizeof(exception_handlers);
arch/loongarch/kernel/unwind_prologue.c +0 -4
index ee1c29686ab05..da07acad7973a 100644
@@ -23,10 +23,6 @@ extern const int unwind_hint_lasx;
 extern const int unwind_hint_lbt;
 extern const int unwind_hint_ri;
 extern const int unwind_hint_watch;
-extern unsigned long eentry;
-#ifdef CONFIG_NUMA
-extern unsigned long pcpu_handlers[NR_CPUS];
-#endif
 
 static inline bool scan_handlers(unsigned long entry_offset)
 {
arch/loongarch/mm/tlb.c +0 -1
index f46c15d6e7eae..24add95ecb65e 100644
@@ -260,7 +260,6 @@ static void output_pgtable_bits_defines(void)
 #ifdef CONFIG_NUMA
 unsigned long pcpu_handlers[NR_CPUS];
 #endif
-extern long exception_handlers[VECSIZE * 128 / sizeof(long)];
 
 static void setup_tlb_handler(int cpu)
 {
Signature · 1 line
2.51.0
author maintainer
#133 lore raw

PATCH 127/314 drm/i915/dp: Fail state computation for invalid DSC source input BPP values

In reply to Sasha Levin

From: Imre Deak <[email protected]>

[ Upstream commit 338465490cf7bd4a700ecd33e4855fee4622fa5f ]

There is no reason to accept an invalid minimum/maximum DSC source input BPP value (i.e a minimum DSC input BPP value above the maximum pipe BPP or a maximum DSC input BPP value below the minimum pipe BPP value), fail the state computation in these cases.

Stable-dep-of: fe26ae6ac8b8 ("drm/i915/dp: Fix pipe BPP clamping due to HDR")

---
 drivers/gpu/drm/i915/display/intel_dp.c | 28 ++++++++++++++++++-------
 1 file changed, 21 insertions(+), 7 deletions(-)
drivers/gpu/drm/i915/display/intel_dp.c +21 -7
index 2eab591a8ef56..057b366c5ae29 100644
@@ -2523,16 +2523,30 @@ intel_dp_compute_config_link_bpp_limits(struct intel_dp *intel_dp,
 	return true;
 }
 
-static void
-intel_dp_dsc_compute_pipe_bpp_limits(struct intel_dp *intel_dp,
+static bool
+intel_dp_dsc_compute_pipe_bpp_limits(struct intel_connector *connector,
 				     struct link_config_limits *limits)
 {
-	struct intel_display *display = to_intel_display(intel_dp);
+	struct intel_display *display = to_intel_display(connector);
+	const struct link_config_limits orig_limits = *limits;
 	int dsc_min_bpc = intel_dp_dsc_min_src_input_bpc();
 	int dsc_max_bpc = intel_dp_dsc_max_src_input_bpc(display);
 
-	limits->pipe.max_bpp = clamp(limits->pipe.max_bpp, dsc_min_bpc * 3, dsc_max_bpc * 3);
-	limits->pipe.min_bpp = clamp(limits->pipe.min_bpp, dsc_min_bpc * 3, dsc_max_bpc * 3);
+	limits->pipe.min_bpp = max(limits->pipe.min_bpp, dsc_min_bpc * 3);
+	limits->pipe.max_bpp = min(limits->pipe.max_bpp, dsc_max_bpc * 3);
+
+	if (limits->pipe.min_bpp <= 0 ||
+	    limits->pipe.min_bpp > limits->pipe.max_bpp) {
+		drm_dbg_kms(display->drm,
+			    "[CONNECTOR:%d:%s] Invalid DSC src/sink input BPP (src:%d-%d pipe:%d-%d)\n",
+			    connector->base.base.id, connector->base.name,
+			    dsc_min_bpc * 3, dsc_max_bpc * 3,
+			    orig_limits.pipe.min_bpp, orig_limits.pipe.max_bpp);
+
+		return false;
+	}
+
+	return true;
 }
 
 bool
@@ -2572,8 +2586,8 @@ intel_dp_compute_config_limits(struct intel_dp *intel_dp,
 							respect_downstream_limits);
 	}
 
-	if (dsc)
-		intel_dp_dsc_compute_pipe_bpp_limits(intel_dp, limits);
+	if (dsc && !intel_dp_dsc_compute_pipe_bpp_limits(connector, limits))
+		return false;
 
 	if (is_mst || intel_dp->use_max_params) {
 		/*
Signature · 1 line
2.51.0
author maintainer
#134 lore raw

PATCH 128/314 drm/i915/dp: Fix pipe BPP clamping due to HDR

In reply to Sasha Levin

From: Imre Deak <[email protected]>

[ Upstream commit fe26ae6ac8b88fcdac5036b557c129a17fe520d2 ]

The pipe BPP value shouldn't be set outside of the source's / sink's valid pipe BPP range, ensure this when increasing the minimum pipe BPP value to 30 due to HDR.

While at it debug print if the HDR mode was requested for a connector by setting the corresponding HDR connector property. This indicates if the requested HDR mode could not be enabled, since the selected pipe BPP is below 30, due to a sink capability or link BW limit.

v2:
- Also handle the case where the sink could support the target 30 BPP only in DSC mode due to a BW limit, but the sink doesn't support DSC or 30 BPP as a DSC input BPP. (Chaitanya)
- Debug print the connector's HDR mode in the link config dump, to indicate if a BPP >= 30 required by HDR couldn't be reached. (Ankit)
- Add Closes: trailer. (Ankit)
- Don't print the 30 BPP-outside of valid BPP range debug message if the min BPP is already > 30 (and so a target BPP >= 30 required for HDR is ensured).

Fixes ba49a4643cf53 ("drm/i915/dp: Set min_bpp limit to 30 in HDR mode")
Cc Chaitanya Kumar Borah <[email protected]>
Cc <[email protected]> # v6.18+
(cherry picked from commit 08b7ef16b6a03e8c966e286ee1ac608a6ffb3d4a)
---
 drivers/gpu/drm/i915/display/intel_dp.c | 20 +++++++++++++++++---
 1 file changed, 17 insertions(+), 3 deletions(-)
drivers/gpu/drm/i915/display/intel_dp.c +17 -3
index 057b366c5ae29..be3d54729a440 100644
@@ -2557,6 +2557,7 @@ intel_dp_compute_config_limits(struct intel_dp *intel_dp,
 			       bool dsc,
 			       struct link_config_limits *limits)
 {
+	struct intel_display *display = to_intel_display(intel_dp);
 	bool is_mst = intel_crtc_has_type(crtc_state, INTEL_OUTPUT_DP_MST);
 	struct intel_connector *connector =
 		to_intel_connector(conn_state->connector);
@@ -2569,8 +2570,7 @@ intel_dp_compute_config_limits(struct intel_dp *intel_dp,
 	limits->min_lane_count = intel_dp_min_lane_count(intel_dp);
 	limits->max_lane_count = intel_dp_max_lane_count(intel_dp);
 
-	limits->pipe.min_bpp = intel_dp_in_hdr_mode(conn_state) ? 30 :
-				intel_dp_min_bpp(crtc_state->output_format);
+	limits->pipe.min_bpp = intel_dp_min_bpp(crtc_state->output_format);
 	if (is_mst) {
 		/*
 		 * FIXME: If all the streams can't fit into the link with their
@@ -2586,6 +2586,19 @@ intel_dp_compute_config_limits(struct intel_dp *intel_dp,
 							respect_downstream_limits);
 	}
 
+	if (!dsc && intel_dp_in_hdr_mode(conn_state)) {
+		if (intel_dp_supports_dsc(intel_dp, connector, crtc_state) &&
+		    limits->pipe.max_bpp >= 30)
+			limits->pipe.min_bpp = max(limits->pipe.min_bpp, 30);
+		else
+			drm_dbg_kms(display->drm,
+				    "[CONNECTOR:%d:%s] Can't force 30 bpp for HDR (pipe bpp: %d-%d DSC-support: %s)\n",
+				    connector->base.base.id, connector->base.name,
+				    limits->pipe.min_bpp, limits->pipe.max_bpp,
+				    str_yes_no(intel_dp_supports_dsc(intel_dp, connector,
+								     crtc_state)));
+	}
+
 	if (dsc && !intel_dp_dsc_compute_pipe_bpp_limits(connector, limits))
 		return false;
 
@@ -2716,10 +2729,11 @@ intel_dp_compute_link_config(struct intel_encoder *encoder,
 	}
 
 	drm_dbg_kms(display->drm,
-		    "DP lane count %d clock %d bpp input %d compressed " FXP_Q4_FMT " link rate required %d available %d\n",
+		    "DP lane count %d clock %d bpp input %d compressed " FXP_Q4_FMT " HDR %s link rate required %d available %d\n",
 		    pipe_config->lane_count, pipe_config->port_clock,
 		    pipe_config->pipe_bpp,
 		    FXP_Q4_ARGS(pipe_config->dsc.compressed_bpp_x16),
+		    str_yes_no(intel_dp_in_hdr_mode(conn_state)),
 		    intel_dp_config_required_rate(pipe_config),
 		    intel_dp_max_link_data_rate(intel_dp,
 						pipe_config->port_clock,
Signature · 1 line
2.51.0
author maintainer
#135 lore raw

PATCH 129/314 net: arcnet: com20020-pci: fix support for 2.5Mbit cards

In reply to Sasha Levin

From: Ethan Nelson-Moore <[email protected]>

[ Upstream commit c7d9be66b71af490446127c6ffcb66d6bb71b8b9 ]

Commit 8c14f9c70327 ("ARCNET: add com20020 PCI IDs with metadata") converted the com20020-pci driver to use a card info structure instead of a single flag mask in driver_data. However, it failed to take into account that in the original code, driver_data of 0 indicates a card with no special flags, not a card that should not have any card info structure. This introduced a null pointer dereference when cards with no flags were probed.

Commit bd6f1fd5d33d ("net: arcnet: com20020: Fix null-ptr-deref in com20020pci_probe()") then papered over this issue by rejecting cards with no driver_data instead of resolving the problem at its source.

Fix the original issue by introducing a new card info structure for 2.5Mbit cards that does not set any flags and using it if no driver_data is present.

Fixes 8c14f9c70327 ("ARCNET: add com20020 PCI IDs with metadata")
Fixes bd6f1fd5d33d ("net: arcnet: com20020: Fix null-ptr-deref in com20020pci_probe()")
---
 drivers/net/arcnet/com20020-pci.c | 16 +++++++++++++++-
 1 file changed, 15 insertions(+), 1 deletion(-)
drivers/net/arcnet/com20020-pci.c +15 -1
index 0472bcdff1307..b5729d6c0b47c 100644
@@ -115,6 +115,8 @@ static const struct attribute_group com20020_state_group = {
 	.attrs = com20020_state_attrs,
 };
 
+static struct com20020_pci_card_info card_info_2p5mbit;
+
 static void com20020pci_remove(struct pci_dev *pdev);
 
 static int com20020pci_probe(struct pci_dev *pdev,
@@ -140,7 +142,7 @@ static int com20020pci_probe(struct pci_dev *pdev,
 
 	ci = (struct com20020_pci_card_info *)id->driver_data;
 	if (!ci)
-		return -EINVAL;
+		ci = &card_info_2p5mbit;
 
 	priv->ci = ci;
 	mm = &ci->misc_map;
@@ -347,6 +349,18 @@ static struct com20020_pci_card_info card_info_5mbit = {
 	.flags = ARC_IS_5MBIT,
 };
 
+static struct com20020_pci_card_info card_info_2p5mbit = {
+	.name = "ARC-PCI",
+	.devcount = 1,
+	.chan_map_tbl = {
+		{
+			.bar = 2,
+			.offset = 0x00,
+			.size = 0x08,
+		},
+	},
+};
+
 static struct com20020_pci_card_info card_info_sohard = {
 	.name = "SOHARD SH ARC-PCI",
 	.devcount = 1,
Signature · 1 line
2.51.0
author maintainer
#136 lore raw

PATCH 130/314 eventpoll: Fix integer overflow in ep_loop_check_proc()

In reply to Sasha Levin

From: Jann Horn <[email protected]>

commit fdcfce93073d990ed4b71752e31ad1c1d6e9d58b upstream.

If a recursive call to ep_loop_check_proc() hits the result = INT_MAX, an integer overflow will occur in the calling ep_loop_check_proc() at result = max(result, ep_loop_check_proc(ep_tovisit, depth + 1) + 1), breaking the recursion depth check.

Fix it by using a different placeholder value that can't lead to an overflow.

---
 fs/eventpoll.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)
fs/eventpoll.c +3 -2
index ee7c4b683ec3d..bcc7dcbefc419 100644
@@ -2061,7 +2061,8 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events,
  * @ep: the &struct eventpoll to be currently checked.
  * @depth: Current depth of the path being checked.
  *
- * Return: depth of the subtree, or INT_MAX if we found a loop or went too deep.
+ * Return: depth of the subtree, or a value bigger than EP_MAX_NESTS if we found
+ * a loop or went too deep.
  */
 static int ep_loop_check_proc(struct eventpoll *ep, int depth)
 {
@@ -2080,7 +2081,7 @@ static int ep_loop_check_proc(struct eventpoll *ep, int depth)
 			struct eventpoll *ep_tovisit;
 			ep_tovisit = epi->ffd.file->private_data;
 			if (ep_tovisit == inserting_into || depth > EP_MAX_NESTS)
-				result = INT_MAX;
+				result = EP_MAX_NESTS+1;
 			else
 				result = max(result, ep_loop_check_proc(ep_tovisit, depth + 1) + 1);
 			if (result > EP_MAX_NESTS)
Signature · 1 line
2.51.0
author maintainer
#137 lore raw

PATCH 131/314 namespace: fix proc mount iteration

In reply to Sasha Levin

From: Christian Brauner <[email protected]>

commit 4a403d7aa9074f527f064ef0806aaab38d14b07c upstream.

The m->index isn't updated when m->show() overflows and retains its value before the current mount causing a restart to start at the same value. If that happens in short order to due a quickly expanding mount table this would cause the same mount to be shown again and again.

Ensure that *pos always equals the mount id of the mount that was returned by start/next. On restart after overflow mnt_find_id_at(*pos) finds the exact mount. This should avoid duplicates, avoid skips and should handle concurrent modification just fine.

Cc: <[email protected]>
Fixed: 2eea9ce4310d8 ("mounts: keep list of mounts in an rbtree")

---
 fs/namespace.c | 20 +++++++++++++++-----
 1 file changed, 15 insertions(+), 5 deletions(-)
fs/namespace.c +15 -5
index b312905c2be5b..8531b8deee416 100644
@@ -1531,23 +1531,33 @@ static struct mount *mnt_find_id_at_reverse(struct mnt_namespace *ns, u64 mnt_id
 static void *m_start(struct seq_file *m, loff_t *pos)
 {
 	struct proc_mounts *p = m->private;
+	struct mount *mnt;
 
 	down_read(&namespace_sem);
 
-	return mnt_find_id_at(p->ns, *pos);
+	mnt = mnt_find_id_at(p->ns, *pos);
+	if (mnt)
+		*pos = mnt->mnt_id_unique;
+	return mnt;
 }
 
 static void *m_next(struct seq_file *m, void *v, loff_t *pos)
 {
-	struct mount *next = NULL, *mnt = v;
+	struct mount *mnt = v;
 	struct rb_node *node = rb_next(&mnt->mnt_node);
 
-	++*pos;
 	if (node) {
-		next = node_to_mount(node);
+		struct mount *next = node_to_mount(node);
 		*pos = next->mnt_id_unique;
+		return next;
 	}
-	return next;
+
+	/*
+	 * No more mounts. Set pos past current mount's ID so that if
+	 * iteration restarts, mnt_find_id_at() returns NULL.
+	 */
+	*pos = mnt->mnt_id_unique + 1;
+	return NULL;
 }
 
 static void m_stop(struct seq_file *m, void *v)
Signature · 1 line
2.51.0
author maintainer
#138 lore raw

PATCH 132/314 media: dvb-core: fix wrong reinitialization of ringbuffer on reopen

In reply to Sasha Levin

From: Jens Axboe <[email protected]>

commit bfbc0b5b32a8f28ce284add619bf226716a59bc0 upstream.

dvb_dvr_open() calls dvb_ringbuffer_init() when a new reader opens the DVR device. dvb_ringbuffer_init() calls init_waitqueue_head(), which reinitializes the waitqueue list head to empty.

Since dmxdev->dvr_buffer.queue is a shared waitqueue (all opens of the same DVR device share it), this orphans any existing waitqueue entries from io_uring poll or epoll, leaving them with stale prev/next pointers while the list head is reset to {self, self}.

The waitqueue and spinlock in dvr_buffer are already properly initialized once in dvb_dmxdev_init(). The open path only needs to reset the buffer data pointer, size, and read/write positions.

Replace the dvb_ringbuffer_init() call in dvb_dvr_open() with direct assignment of data/size and a call to dvb_ringbuffer_reset(), which properly resets pread, pwrite, and error with correct memory ordering without touching the waitqueue or spinlock.

---
 drivers/media/dvb-core/dmxdev.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)
drivers/media/dvb-core/dmxdev.c +3 -1
index 8a9cca6da3e0e..ab34be22cd1aa 100644
@@ -168,7 +168,9 @@ static int dvb_dvr_open(struct inode *inode, struct file *file)
 			mutex_unlock(&dmxdev->mutex);
 			return -ENOMEM;
 		}
-		dvb_ringbuffer_init(&dmxdev->dvr_buffer, mem, DVR_BUFFER_SIZE);
+		dmxdev->dvr_buffer.data = mem;
+		dmxdev->dvr_buffer.size = DVR_BUFFER_SIZE;
+		dvb_ringbuffer_reset(&dmxdev->dvr_buffer);
 		if (dmxdev->may_do_mmap)
 			dvb_vb2_init(&dmxdev->dvr_vb2_ctx, "dvr",
 				     file->f_flags & O_NONBLOCK);
Signature · 1 line
2.51.0
author maintainer
#139 lore raw

PATCH 133/314 nfc: pn533: properly drop the usb interface reference on disconnect

In reply to Sasha Levin

From: Greg Kroah-Hartman <[email protected]>

commit 12133a483dfa832241fbbf09321109a0ea8a520e upstream.

When the device is disconnected from the driver, there is a "dangling" reference count on the usb interface that was grabbed in the probe callback. Fix this up by properly dropping the reference after we are done with it.

---
 drivers/nfc/pn533/usb.c | 1 +
 1 file changed, 1 insertion(+)
drivers/nfc/pn533/usb.c +1 -0
index 018a80674f06e..0f12f86ebb023 100644
@@ -628,6 +628,7 @@ static void pn533_usb_disconnect(struct usb_interface *interface)
 	usb_free_urb(phy->out_urb);
 	usb_free_urb(phy->ack_urb);
 	kfree(phy->ack_buffer);
+	usb_put_dev(phy->udev);
 
 	nfc_info(&interface->dev, "NXP PN533 NFC device disconnected\n");
 }
Signature · 1 line
2.51.0
author maintainer
#140 lore raw

PATCH 134/314 net: usb: kaweth: validate USB endpoints

In reply to Sasha Levin

From: Greg Kroah-Hartman <[email protected]>

commit 4b063c002ca759d1b299988ee23f564c9609c875 upstream.

The kaweth driver should validate that the device it is probing has the proper number and types of USB endpoints it is expecting before it binds to it. If a malicious device were to not have the same urbs the driver will crash later on when it blindly accesses these endpoints.

---
 drivers/net/usb/kaweth.c | 13 +++++++++++++
 1 file changed, 13 insertions(+)
drivers/net/usb/kaweth.c +13 -0
index e01d14f6c3667..cb2472b59e104 100644
@@ -883,6 +883,13 @@ static int kaweth_probe(
 	const eth_addr_t bcast_addr = { 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF };
 	int result = 0;
 	int rv = -EIO;
+	static const u8 bulk_ep_addr[] = {
+		1 | USB_DIR_IN,
+		2 | USB_DIR_OUT,
+		0};
+	static const u8 int_ep_addr[] = {
+		3 | USB_DIR_IN,
+		0};
 
 	dev_dbg(dev,
 		"Kawasaki Device Probe (Device number:%d): 0x%4.4x:0x%4.4x:0x%4.4x\n",
@@ -896,6 +903,12 @@ static int kaweth_probe(
 		(int)udev->descriptor.bLength,
 		(int)udev->descriptor.bDescriptorType);
 
+	if (!usb_check_bulk_endpoints(intf, bulk_ep_addr) ||
+	    !usb_check_int_endpoints(intf, int_ep_addr)) {
+		dev_err(dev, "couldn't find required endpoints\n");
+		return -ENODEV;
+	}
+
 	netdev = alloc_etherdev(sizeof(*kaweth));
 	if (!netdev)
 		return -ENOMEM;
Signature · 1 line
2.51.0
author maintainer
#141 lore raw

PATCH 135/314 net: usb: kalmia: validate USB endpoints

In reply to Sasha Levin

From: Greg Kroah-Hartman <[email protected]>

commit c58b6c29a4c9b8125e8ad3bca0637e00b71e2693 upstream.

The kalmia driver should validate that the device it is probing has the proper number and types of USB endpoints it is expecting before it binds to it. If a malicious device were to not have the same urbs the driver will crash later on when it blindly accesses these endpoints.

---
 drivers/net/usb/kalmia.c | 7 +++++++
 1 file changed, 7 insertions(+)
drivers/net/usb/kalmia.c +7 -0
index 613fc6910f148..ee9c48f7f68f9 100644
@@ -132,11 +132,18 @@ kalmia_bind(struct usbnet *dev, struct usb_interface *intf)
 {
 	int status;
 	u8 ethernet_addr[ETH_ALEN];
+	static const u8 ep_addr[] = {
+		1 | USB_DIR_IN,
+		2 | USB_DIR_OUT,
+		0};
 
 	/* Don't bind to AT command interface */
 	if (intf->cur_altsetting->desc.bInterfaceClass != USB_CLASS_VENDOR_SPEC)
 		return -EINVAL;
 
+	if (!usb_check_bulk_endpoints(intf, ep_addr))
+		return -ENODEV;
+
 	dev->in = usb_rcvbulkpipe(dev->udev, 0x81 & USB_ENDPOINT_NUMBER_MASK);
 	dev->out = usb_sndbulkpipe(dev->udev, 0x02 & USB_ENDPOINT_NUMBER_MASK);
 	dev->status = NULL;
Signature · 1 line
2.51.0
author maintainer
#142 lore raw

PATCH 136/314 net: usb: pegasus: validate USB endpoints

In reply to Sasha Levin

From: Greg Kroah-Hartman <[email protected]>

commit 11de1d3ae5565ed22ef1f89d73d8f2d00322c699 upstream.

The pegasus driver should validate that the device it is probing has the proper number and types of USB endpoints it is expecting before it binds to it. If a malicious device were to not have the same urbs the driver will crash later on when it blindly accesses these endpoints.

---
 drivers/net/usb/pegasus.c | 13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)
drivers/net/usb/pegasus.c +12 -1
index 0f16a133c75d1..475b066081c7f 100644
@@ -815,8 +815,19 @@ static void unlink_all_urbs(pegasus_t *pegasus)
 
 static int alloc_urbs(pegasus_t *pegasus)
 {
+	static const u8 bulk_ep_addr[] = {
+		1 | USB_DIR_IN,
+		2 | USB_DIR_OUT,
+		0};
+	static const u8 int_ep_addr[] = {
+		3 | USB_DIR_IN,
+		0};
 	int res = -ENOMEM;
 
+	if (!usb_check_bulk_endpoints(pegasus->intf, bulk_ep_addr) ||
+	    !usb_check_int_endpoints(pegasus->intf, int_ep_addr))
+		return -ENODEV;
+
 	pegasus->rx_urb = usb_alloc_urb(0, GFP_KERNEL);
 	if (!pegasus->rx_urb) {
 		return res;
@@ -1171,6 +1182,7 @@ static int pegasus_probe(struct usb_interface *intf,
 
 	pegasus = netdev_priv(net);
 	pegasus->dev_index = dev_index;
+	pegasus->intf = intf;
 
 	res = alloc_urbs(pegasus);
 	if (res < 0) {
@@ -1182,7 +1194,6 @@ static int pegasus_probe(struct usb_interface *intf,
 
 	INIT_DELAYED_WORK(&pegasus->carrier_check, check_carrier);
 
-	pegasus->intf = intf;
 	pegasus->usb = dev;
 	pegasus->net = net;
 
Signature · 1 line
2.51.0
author maintainer
#143 lore raw

PATCH 137/314 can: ems_usb: ems_usb_read_bulk_callback(): check the proper length of a message

In reply to Sasha Levin

From: Greg Kroah-Hartman <[email protected]>

commit 38a01c9700b0dcafe97dfa9dc7531bf4a245deff upstream.

When looking at the data in a USB urb, the actual_length is the size of the buffer passed to the driver, not the transfer_buffer_length which is set by the driver as the max size of the buffer.

When parsing the messages in ems_usb_read_bulk_callback() properly check the size both at the beginning of parsing the message to make sure it is big enough for the expected structure, and at the end of the message to make sure we don't overflow past the end of the buffer for the next message.

Cc Vincent Mailhol <[email protected]>
Cc Marc Kleine-Budde <[email protected]>
Assisted-by gkh_clanker_2000
Fixes 702171adeed3 ("ems_usb: Added support for EMS CPC-USB/ARM7 CAN/USB interface")
---
 drivers/net/can/usb/ems_usb.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)
drivers/net/can/usb/ems_usb.c +6 -1
index fac8ac79df59f..d8c881130e900 100644
@@ -445,6 +445,11 @@ static void ems_usb_read_bulk_callback(struct urb *urb)
 		start = CPC_HEADER_SIZE;
 
 		while (msg_count) {
+			if (start + CPC_MSG_HEADER_LEN > urb->actual_length) {
+				netdev_err(netdev, "format error\n");
+				break;
+			}
+
 			msg = (struct ems_cpc_msg *)&ibuf[start];
 
 			switch (msg->type) {
@@ -474,7 +479,7 @@ static void ems_usb_read_bulk_callback(struct urb *urb)
 			start += CPC_MSG_HEADER_LEN + msg->length;
 			msg_count--;
 
-			if (start > urb->transfer_buffer_length) {
+			if (start > urb->actual_length) {
 				netdev_err(netdev, "format error\n");
 				break;
 			}
Signature · 1 line
2.51.0
author maintainer
#144 lore raw

PATCH 138/314 can: usb: f81604: correctly anchor the urb in the read bulk callback

In reply to Sasha Levin

From: Greg Kroah-Hartman <[email protected]>

commit 952caa5da10bed22be09612433964f6877ba0dde upstream.

When submitting an urb, that is using the anchor pattern, it needs to be anchored before submitting it otherwise it could be leaked if usb_kill_anchored_urbs() is called. This logic is correctly done elsewhere in the driver, except in the read bulk callback so do that here also.

Cc Ji-Ze Hong (Peter Hong) <[email protected]>
Cc Marc Kleine-Budde <[email protected]>
Cc Vincent Mailhol <[email protected]>
Assisted-by gkh_clanker_2000
Fixes 88da17436973 ("can: usb: f81604: add Fintek F81604 support")
---
 drivers/net/can/usb/f81604.c | 15 +++++++++++++--
 1 file changed, 13 insertions(+), 2 deletions(-)
drivers/net/can/usb/f81604.c +13 -2
index e0cfa1460b0b8..9e416cb642dcf 100644
@@ -413,6 +413,7 @@ static void f81604_read_bulk_callback(struct urb *urb)
 {
 	struct f81604_can_frame *frame = urb->transfer_buffer;
 	struct net_device *netdev = urb->context;
+	struct f81604_port_priv *priv = netdev_priv(netdev);
 	int ret;
 
 	if (!netif_device_present(netdev))
@@ -445,10 +446,15 @@ static void f81604_read_bulk_callback(struct urb *urb)
 	f81604_process_rx_packet(netdev, frame);
 
 resubmit_urb:
+	usb_anchor_urb(urb, &priv->urbs_anchor);
 	ret = usb_submit_urb(urb, GFP_ATOMIC);
+	if (!ret)
+		return;
+	usb_unanchor_urb(urb);
+
 	if (ret == -ENODEV)
 		netif_device_detach(netdev);
-	else if (ret)
+	else
 		netdev_err(netdev,
 			   "%s: failed to resubmit read bulk urb: %pe\n",
 			   __func__, ERR_PTR(ret));
@@ -646,10 +652,15 @@ static void f81604_read_int_callback(struct urb *urb)
 		f81604_handle_tx(priv, data);
 
 resubmit_urb:
+	usb_anchor_urb(urb, &priv->urbs_anchor);
 	ret = usb_submit_urb(urb, GFP_ATOMIC);
+	if (!ret)
+		return;
+	usb_unanchor_urb(urb);
+
 	if (ret == -ENODEV)
 		netif_device_detach(netdev);
-	else if (ret)
+	else
 		netdev_err(netdev, "%s: failed to resubmit int urb: %pe\n",
 			   __func__, ERR_PTR(ret));
 }
Signature · 1 line
2.51.0
author maintainer
#145 lore raw

PATCH 139/314 can: ucan: Fix infinite loop from zero-length messages

In reply to Sasha Levin

From: Greg Kroah-Hartman <[email protected]>

commit 1e446fd0582ad8be9f6dafb115fc2e7245f9bea7 upstream.

If a broken ucan device gets a message with the message length field set to 0, then the driver will loop for forever in ucan_read_bulk_callback(), hanging the system. If the length is 0, just skip the message and go on to the next one.

This has been fixed in the kvaser_usb driver in the past in commit 0c73772cd2b8 ("can: kvaser_usb: leaf: Fix potential infinite loop in command parsers"), so there must be some broken devices out there like this somewhere.

Cc Marc Kleine-Budde <[email protected]>
Cc Vincent Mailhol <[email protected]>
Assisted-by gkh_clanker_2000
Fixes 9f2d3eae88d2 ("can: ucan: add driver for Theobroma Systems UCAN devices")
---
 drivers/net/can/usb/ucan.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/net/can/usb/ucan.c +1 -1
index 07406daf7c88e..6c90b4a7d955a 100644
@@ -749,7 +749,7 @@ static void ucan_read_bulk_callback(struct urb *urb)
 		len = le16_to_cpu(m->len);
 
 		/* check sanity (length of content) */
-		if (urb->actual_length - pos < len) {
+		if ((len == 0) || (urb->actual_length - pos < len)) {
 			netdev_warn(up->netdev,
 				    "invalid message (short; no data; l:%d)\n",
 				    urb->actual_length);
Signature · 1 line
2.51.0
author maintainer
#146 lore raw

PATCH 140/314 can: usb: etas_es58x: correctly anchor the urb in the read bulk callback

In reply to Sasha Levin

From: Greg Kroah-Hartman <[email protected]>

commit 5eaad4f768266f1f17e01232ffe2ef009f8129b7 upstream.

When submitting an urb, that is using the anchor pattern, it needs to be anchored before submitting it otherwise it could be leaked if usb_kill_anchored_urbs() is called. This logic is correctly done elsewhere in the driver, except in the read bulk callback so do that here also.

Cc Vincent Mailhol <[email protected]>
Cc Marc Kleine-Budde <[email protected]>
Assisted-by gkh_clanker_2000
Fixes 8537257874e9 ("can: etas_es58x: add core support for ETAS ES58X CAN USB interfaces")
---
 drivers/net/can/usb/etas_es58x/es58x_core.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)
drivers/net/can/usb/etas_es58x/es58x_core.c +7 -1
index 6eeba9baa1317..1e44bd1dfee9b 100644
@@ -1461,12 +1461,18 @@ static void es58x_read_bulk_callback(struct urb *urb)
 	}
 
  resubmit_urb:
+	usb_anchor_urb(urb, &es58x_dev->rx_urbs);
 	ret = usb_submit_urb(urb, GFP_ATOMIC);
+	if (!ret)
+		return;
+
+	usb_unanchor_urb(urb);
+
 	if (ret == -ENODEV) {
 		for (i = 0; i < es58x_dev->num_can_ch; i++)
 			if (es58x_dev->netdev[i])
 				netif_device_detach(es58x_dev->netdev[i]);
-	} else if (ret)
+	} else
 		dev_err_ratelimited(dev,
 				    "Failed resubmitting read bulk urb: %pe\n",
 				    ERR_PTR(ret));
Signature · 1 line
2.51.0
author maintainer
#147 lore raw

PATCH 141/314 can: usb: f81604: handle short interrupt urb messages properly

In reply to Sasha Levin

From: Greg Kroah-Hartman <[email protected]>

commit 7299b1b39a255f6092ce4ec0b65f66e9d6a357af upstream.

If an interrupt urb is received that is not the correct length, properly detect it and don't attempt to treat the data as valid.

Cc Ji-Ze Hong (Peter Hong) <[email protected]>
Cc Marc Kleine-Budde <[email protected]>
Cc Vincent Mailhol <[email protected]>
Assisted-by gkh_clanker_2000
Fixes 88da17436973 ("can: usb: f81604: add Fintek F81604 support")
---
 drivers/net/can/usb/f81604.c | 6 ++++++
 1 file changed, 6 insertions(+)
drivers/net/can/usb/f81604.c +6 -0
index 9e416cb642dcf..e87e2674ac585 100644
@@ -626,6 +626,12 @@ static void f81604_read_int_callback(struct urb *urb)
 		netdev_info(netdev, "%s: Int URB aborted: %pe\n", __func__,
 			    ERR_PTR(urb->status));
 
+	if (urb->actual_length < sizeof(*data)) {
+		netdev_warn(netdev, "%s: short int URB: %u < %zu\n",
+			    __func__, urb->actual_length, sizeof(*data));
+		goto resubmit_urb;
+	}
+
 	switch (urb->status) {
 	case 0: /* success */
 		break;
Signature · 1 line
2.51.0
author maintainer
#148 lore raw

PATCH 142/314 can: usb: f81604: handle bulk write errors properly

In reply to Sasha Levin

From: Greg Kroah-Hartman <[email protected]>

commit 51f94780720fa90c424f67e3e9784cb8ef8190e5 upstream.

If a write urb fails then more needs to be done other than just logging the message, otherwise the transmission could be stalled. Properly increment the error counters and wake up the queues so that data will continue to flow.

Cc Ji-Ze Hong (Peter Hong) <[email protected]>
Cc Marc Kleine-Budde <[email protected]>
Cc Vincent Mailhol <[email protected]>
Assisted-by gkh_clanker_2000
Fixes 88da17436973 ("can: usb: f81604: add Fintek F81604 support")
---
 drivers/net/can/usb/f81604.c | 24 +++++++++++++++++++++---
 1 file changed, 21 insertions(+), 3 deletions(-)
drivers/net/can/usb/f81604.c +21 -3
index e87e2674ac585..6b8b2795c0188 100644
@@ -891,9 +891,27 @@ static void f81604_write_bulk_callback(struct urb *urb)
 	if (!netif_device_present(netdev))
 		return;
 
-	if (urb->status)
-		netdev_info(netdev, "%s: Tx URB error: %pe\n", __func__,
-			    ERR_PTR(urb->status));
+	if (!urb->status)
+		return;
+
+	switch (urb->status) {
+	case -ENOENT:
+	case -ECONNRESET:
+	case -ESHUTDOWN:
+		return;
+	default:
+		break;
+	}
+
+	if (net_ratelimit())
+		netdev_err(netdev, "%s: Tx URB error: %pe\n", __func__,
+			   ERR_PTR(urb->status));
+
+	can_free_echo_skb(netdev, 0, NULL);
+	netdev->stats.tx_dropped++;
+	netdev->stats.tx_errors++;
+
+	netif_wake_queue(netdev);
 }
 
 static void f81604_clear_reg_work(struct work_struct *work)
Signature · 1 line
2.51.0
author maintainer
#149 lore raw

PATCH 143/314 HID: Add HID_CLAIMED_INPUT guards in raw_event callbacks missing them

In reply to Sasha Levin

From: Greg Kroah-Hartman <[email protected]>

commit ecfa6f34492c493a9a1dc2900f3edeb01c79946b upstream.

In commit 2ff5baa9b527 ("HID: appleir: Fix potential NULL dereference at raw event handle"), we handle the fact that raw event callbacks can happen even for a HID device that has not been "claimed" causing a crash if a broken device were attempted to be connected to the system.

Fix up the remaining in-tree HID drivers that forgot to add this same check to resolve the same issue.

Cc Jiri Kosina <[email protected]>
Cc Benjamin Tissoires <[email protected]>
Cc Bastien Nocera <[email protected]>
Cc stable <[email protected]>
Assisted-by gkh_clanker_2000
---
 drivers/hid/hid-cmedia.c          | 2 +-
 drivers/hid/hid-creative-sb0540.c | 2 +-
 drivers/hid/hid-zydacron.c        | 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)
drivers/hid/hid-cmedia.c +1 -1
index 528d7f3612157..8bf5649b0c793 100644
@@ -99,7 +99,7 @@ static int cmhid_raw_event(struct hid_device *hid, struct hid_report *report,
 {
 	struct cmhid *cm = hid_get_drvdata(hid);
 
-	if (len != CM6533_JD_RAWEV_LEN)
+	if (len != CM6533_JD_RAWEV_LEN || !(hid->claimed & HID_CLAIMED_INPUT))
 		goto out;
 	if (memcmp(data+CM6533_JD_SFX_OFFSET, ji_sfx, sizeof(ji_sfx)))
 		goto out;
drivers/hid/hid-creative-sb0540.c +1 -1
index b4c8e7a5d3e02..dfd6add353d19 100644
@@ -153,7 +153,7 @@ static int creative_sb0540_raw_event(struct hid_device *hid,
 	u64 code, main_code;
 	int key;
 
-	if (len != 6)
+	if (len != 6 || !(hid->claimed & HID_CLAIMED_INPUT))
 		return 0;
 
 	/* From daemons/hw_hiddev.c sb0540_rec() in lirc */
drivers/hid/hid-zydacron.c +1 -1
index 3bdb26f455925..1aae80f848f50 100644
@@ -114,7 +114,7 @@ static int zc_raw_event(struct hid_device *hdev, struct hid_report *report,
 	unsigned key;
 	unsigned short index;
 
-	if (report->id == data[0]) {
+	if (report->id == data[0] && (hdev->claimed & HID_CLAIMED_INPUT)) {
 
 		/* break keys */
 		for (index = 0; index < 4; index++) {
Signature · 1 line
2.51.0
author maintainer
#150 lore raw

PATCH 144/314 HID: pidff: Fix condition effect bit clearing

In reply to Sasha Levin

From: Tomasz Pakuła <[email protected]>

commit 97d5c8f5c09a604c4873c8348f58de3cea69a7df upstream.

As reported by MPDarkGuy on discord, NULL pointer dereferences were happening because not all the conditional effects bits were cleared.

Properly clear all conditional effect bits from ffbit

Fixes 7f3d7bc0df4b ("HID: pidff: Better quirk assigment when searching for fields")
Cc [email protected] # 6.18.x
---
 drivers/hid/usbhid/hid-pidff.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)
drivers/hid/usbhid/hid-pidff.c +7 -4
index a4e700b40ba9b..56d6af39ba81e 100644
@@ -1452,10 +1452,13 @@ static int pidff_init_fields(struct pidff_device *pidff, struct input_dev *dev)
 		hid_warn(pidff->hid, "unknown ramp effect layout\n");
 
 	if (PIDFF_FIND_FIELDS(set_condition, PID_SET_CONDITION, 1)) {
-		if (test_and_clear_bit(FF_SPRING, dev->ffbit)   ||
-		    test_and_clear_bit(FF_DAMPER, dev->ffbit)   ||
-		    test_and_clear_bit(FF_FRICTION, dev->ffbit) ||
-		    test_and_clear_bit(FF_INERTIA, dev->ffbit))
+		bool test = false;
+
+		test |= test_and_clear_bit(FF_SPRING, dev->ffbit);
+		test |= test_and_clear_bit(FF_DAMPER, dev->ffbit);
+		test |= test_and_clear_bit(FF_FRICTION, dev->ffbit);
+		test |= test_and_clear_bit(FF_INERTIA, dev->ffbit);
+		if (test)
 			hid_warn(pidff->hid, "unknown condition effect layout\n");
 	}
 
Signature · 1 line
2.51.0
author maintainer
#151 lore raw

PATCH 145/314 HID: multitouch: Keep latency normal on deactivate for reactivation gesture

In reply to Sasha Levin

From: Werner Sembach <[email protected]>

commit ec3070f01fa30f2c5547d645dbb76174304bf0e4 upstream.

Uniwill devices have a built in gesture in the touchpad to de- and reactivate it by double taping the upper left corner. This gesture stops working when latency is set to high, so this patch keeps the latency on normal.

---
 drivers/hid/hid-multitouch.c | 32 +++++++++++++++++++++++++++++---
 1 file changed, 29 insertions(+), 3 deletions(-)
drivers/hid/hid-multitouch.c +29 -3
index 4dcb1d43df27a..1f8accb7ff435 100644
@@ -77,6 +77,7 @@ MODULE_LICENSE("GPL");
 #define MT_QUIRK_ORIENTATION_INVERT	BIT(22)
 #define MT_QUIRK_APPLE_TOUCHBAR		BIT(23)
 #define MT_QUIRK_YOGABOOK9I		BIT(24)
+#define MT_QUIRK_KEEP_LATENCY_ON_CLOSE	BIT(25)
 
 #define MT_INPUTMODE_TOUCHSCREEN	0x02
 #define MT_INPUTMODE_TOUCHPAD		0x03
@@ -212,6 +213,7 @@ static void mt_post_parse(struct mt_device *td, struct mt_application *app);
 #define MT_CLS_WIN_8_DISABLE_WAKEUP		0x0016
 #define MT_CLS_WIN_8_NO_STICKY_FINGERS		0x0017
 #define MT_CLS_WIN_8_FORCE_MULTI_INPUT_NSMU	0x0018
+#define MT_CLS_WIN_8_KEEP_LATENCY_ON_CLOSE	0x0019
 
 /* vendor specific classes */
 #define MT_CLS_3M				0x0101
@@ -332,6 +334,15 @@ static const struct mt_class mt_classes[] = {
 			MT_QUIRK_CONTACT_CNT_ACCURATE |
 			MT_QUIRK_WIN8_PTP_BUTTONS,
 		.export_all_inputs = true },
+	{ .name = MT_CLS_WIN_8_KEEP_LATENCY_ON_CLOSE,
+		.quirks = MT_QUIRK_ALWAYS_VALID |
+			MT_QUIRK_IGNORE_DUPLICATES |
+			MT_QUIRK_HOVERING |
+			MT_QUIRK_CONTACT_CNT_ACCURATE |
+			MT_QUIRK_STICKY_FINGERS |
+			MT_QUIRK_WIN8_PTP_BUTTONS |
+			MT_QUIRK_KEEP_LATENCY_ON_CLOSE,
+		.export_all_inputs = true },
 
 	/*
 	 * vendor specific classes
@@ -841,7 +852,8 @@ static int mt_touch_input_mapping(struct hid_device *hdev, struct hid_input *hi,
 			if ((cls->name == MT_CLS_WIN_8 ||
 			     cls->name == MT_CLS_WIN_8_FORCE_MULTI_INPUT ||
 			     cls->name == MT_CLS_WIN_8_FORCE_MULTI_INPUT_NSMU ||
-			     cls->name == MT_CLS_WIN_8_DISABLE_WAKEUP) &&
+			     cls->name == MT_CLS_WIN_8_DISABLE_WAKEUP ||
+			     cls->name == MT_CLS_WIN_8_KEEP_LATENCY_ON_CLOSE) &&
 				(field->application == HID_DG_TOUCHPAD ||
 				 field->application == HID_DG_TOUCHSCREEN))
 				app->quirks |= MT_QUIRK_CONFIDENCE;
@@ -1752,7 +1764,8 @@ static int mt_input_configured(struct hid_device *hdev, struct hid_input *hi)
 	int ret;
 
 	if (td->is_haptic_touchpad && (td->mtclass.name == MT_CLS_WIN_8 ||
-	    td->mtclass.name == MT_CLS_WIN_8_FORCE_MULTI_INPUT)) {
+	    td->mtclass.name == MT_CLS_WIN_8_FORCE_MULTI_INPUT ||
+	    td->mtclass.name == MT_CLS_WIN_8_KEEP_LATENCY_ON_CLOSE)) {
 		if (hid_haptic_input_configured(hdev, td->haptic, hi) == 0)
 			td->is_haptic_touchpad = false;
 	} else {
@@ -2065,7 +2078,12 @@ static void mt_on_hid_hw_open(struct hid_device *hdev)
 
 static void mt_on_hid_hw_close(struct hid_device *hdev)
 {
-	mt_set_modes(hdev, HID_LATENCY_HIGH, TOUCHPAD_REPORT_NONE);
+	struct mt_device *td = hid_get_drvdata(hdev);
+
+	if (td->mtclass.quirks & MT_QUIRK_KEEP_LATENCY_ON_CLOSE)
+		mt_set_modes(hdev, HID_LATENCY_NORMAL, TOUCHPAD_REPORT_NONE);
+	else
+		mt_set_modes(hdev, HID_LATENCY_HIGH, TOUCHPAD_REPORT_NONE);
 }
 
 /*
@@ -2451,6 +2469,14 @@ static const struct hid_device_id mt_devices[] = {
 		MT_USB_DEVICE(USB_VENDOR_ID_UNITEC,
 			USB_DEVICE_ID_UNITEC_USB_TOUCH_0A19) },
 
+	/* Uniwill touchpads */
+	{ .driver_data = MT_CLS_WIN_8_KEEP_LATENCY_ON_CLOSE,
+		HID_DEVICE(BUS_I2C, HID_GROUP_MULTITOUCH_WIN_8,
+			USB_VENDOR_ID_PIXART, 0x0255) },
+	{ .driver_data = MT_CLS_WIN_8_KEEP_LATENCY_ON_CLOSE,
+		HID_DEVICE(BUS_I2C, HID_GROUP_MULTITOUCH_WIN_8,
+			USB_VENDOR_ID_PIXART, 0x0274) },
+
 	/* VTL panels */
 	{ .driver_data = MT_CLS_VTL,
 		MT_USB_DEVICE(USB_VENDOR_ID_VTL,
Signature · 1 line
2.51.0
author maintainer
#152 lore raw

PATCH 146/314 x86/efi: defer freeing of boot services memory

In reply to Sasha Levin

From: "Mike Rapoport (Microsoft)" <[email protected]>

commit a4b0bf6a40f3c107c67a24fbc614510ef5719980 upstream.

efi_free_boot_services() frees memory occupied by EFI_BOOT_SERVICES_CODE and EFI_BOOT_SERVICES_DATA using memblock_free_late().

There are two issue with that: memblock_free_late() should be used for memory allocated with memblock_alloc() while the memory reserved with memblock_reserve() should be freed with free_reserved_area().

More acutely, with CONFIG_DEFERRED_STRUCT_PAGE_INIT=y efi_free_boot_services() is called before deferred initialization of the memory map is complete.

Benjamin Herrenschmidt reports that this causes a leak of ~140MB of RAM on EC2 t3a.nano instances which only have 512MB or RAM.

If the freed memory resides in the areas that memory map for them is still uninitialized, they won't be actually freed because memblock_free_late() calls memblock_free_pages() and the latter skips uninitialized pages.

Using free_reserved_area() at this point is also problematic because __free_page() accesses the buddy of the freed page and that again might end up in uninitialized part of the memory map.

Delaying the entire efi_free_boot_services() could be problematic because in addition to freeing boot services memory it updates efi.memmap without any synchronization and that's undesirable late in boot when there is concurrency.

More robust approach is to only defer freeing of the EFI boot services memory.

Split efi_free_boot_services() in two. First efi_unmap_boot_services() collects ranges that should be freed into an array then efi_free_boot_services() later frees them after deferred init is complete.

---
 arch/x86/include/asm/efi.h          |  2 +-
 arch/x86/platform/efi/efi.c         |  2 +-
 arch/x86/platform/efi/quirks.c      | 55 +++++++++++++++++++++++++++--
 drivers/firmware/efi/mokvar-table.c |  2 +-
 4 files changed, 55 insertions(+), 6 deletions(-)
arch/x86/include/asm/efi.h +1 -1
index f227a70ac91f0..51b4cdbea061a 100644
@@ -138,7 +138,7 @@ extern void __init efi_apply_memmap_quirks(void);
 extern int __init efi_reuse_config(u64 tables, int nr_tables);
 extern void efi_delete_dummy_variable(void);
 extern void efi_crash_gracefully_on_page_fault(unsigned long phys_addr);
-extern void efi_free_boot_services(void);
+extern void efi_unmap_boot_services(void);
 
 void arch_efi_call_virt_setup(void);
 void arch_efi_call_virt_teardown(void);
arch/x86/platform/efi/efi.c +1 -1
index 463b784499a8f..791c52c8393f4 100644
@@ -837,7 +837,7 @@ static void __init __efi_enter_virtual_mode(void)
 	}
 
 	efi_check_for_embedded_firmwares();
-	efi_free_boot_services();
+	efi_unmap_boot_services();
 
 	if (!efi_is_mixed())
 		efi_native_runtime_setup();
arch/x86/platform/efi/quirks.c +52 -3

89 lines not on this page · raw message

drivers/firmware/efi/mokvar-table.c +1 -1
index aedbbd627706a..741674a0a70c5 100644
@@ -85,7 +85,7 @@ static struct kobject *mokvar_kobj;
  * as an alternative to ordinary EFI variables, due to platform-dependent
  * limitations. The memory occupied by this table is marked as reserved.
  *
- * This routine must be called before efi_free_boot_services() in order
+ * This routine must be called before efi_unmap_boot_services() in order
  * to guarantee that it can mark the table as reserved.
  *
  * Implicit inputs:
Signature · 1 line
2.51.0
author maintainer
#153 lore raw

PATCH 147/314 perf/x86/intel/uncore: Add per-scheduler IMC CAS count events

In reply to Sasha Levin

From: Zide Chen <[email protected]>

commit 6a8a48644c4b804123e59dbfc5d6cd29a0194046 upstream.

IMC on SPR and EMR does not support sub-channels. In contrast, CPUs that use gnr_uncores[] (e.g. Granite Rapids and Sierra Forest) implement two command schedulers (SCH0/SCH1) per memory channel, providing logically independent command and data paths.

Do not reuse the spr_uncore_imc[] configuration for these CPUs. Instead, introduce a dedicated gnr_uncore_imc[] with per-scheduler events, so userspace can monitor SCH0 and SCH1 independently.

On these CPUs, replace cas_count_{read,write} with cas_count_{read,write}_sch{0,1}. This may break existing userspace that relies on cas_count_{read,write}, prompting it to switch to the per-scheduler events, as the legacy event reports only partial traffic (SCH0).

Fixes 632c4bf6d007 ("perf/x86/intel/uncore: Support Granite Rapids")
Fixes cb4a6ccf3583 ("perf/x86/intel/uncore: Support Sierra Forest and Grand Ridge")
---
 arch/x86/events/intel/uncore_snbep.c | 28 +++++++++++++++++++++++++++-
 1 file changed, 27 insertions(+), 1 deletion(-)
arch/x86/events/intel/uncore_snbep.c +27 -1
index e1f370b8d065f..a338ee01bb242 100644
@@ -6610,6 +6610,32 @@ static struct intel_uncore_type gnr_uncore_ubox = {
 	.attr_update		= uncore_alias_groups,
 };
 
+static struct uncore_event_desc gnr_uncore_imc_events[] = {
+	INTEL_UNCORE_EVENT_DESC(clockticks,      "event=0x01,umask=0x00"),
+	INTEL_UNCORE_EVENT_DESC(cas_count_read_sch0,  "event=0x05,umask=0xcf"),
+	INTEL_UNCORE_EVENT_DESC(cas_count_read_sch0.scale, "6.103515625e-5"),
+	INTEL_UNCORE_EVENT_DESC(cas_count_read_sch0.unit, "MiB"),
+	INTEL_UNCORE_EVENT_DESC(cas_count_read_sch1,  "event=0x06,umask=0xcf"),
+	INTEL_UNCORE_EVENT_DESC(cas_count_read_sch1.scale, "6.103515625e-5"),
+	INTEL_UNCORE_EVENT_DESC(cas_count_read_sch1.unit, "MiB"),
+	INTEL_UNCORE_EVENT_DESC(cas_count_write_sch0, "event=0x05,umask=0xf0"),
+	INTEL_UNCORE_EVENT_DESC(cas_count_write_sch0.scale, "6.103515625e-5"),
+	INTEL_UNCORE_EVENT_DESC(cas_count_write_sch0.unit, "MiB"),
+	INTEL_UNCORE_EVENT_DESC(cas_count_write_sch1, "event=0x06,umask=0xf0"),
+	INTEL_UNCORE_EVENT_DESC(cas_count_write_sch1.scale, "6.103515625e-5"),
+	INTEL_UNCORE_EVENT_DESC(cas_count_write_sch1.unit, "MiB"),
+	{ /* end: all zeroes */ },
+};
+
+static struct intel_uncore_type gnr_uncore_imc = {
+	SPR_UNCORE_MMIO_COMMON_FORMAT(),
+	.name			= "imc",
+	.fixed_ctr_bits		= 48,
+	.fixed_ctr		= SNR_IMC_MMIO_PMON_FIXED_CTR,
+	.fixed_ctl		= SNR_IMC_MMIO_PMON_FIXED_CTL,
+	.event_descs		= gnr_uncore_imc_events,
+};
+
 static struct intel_uncore_type gnr_uncore_pciex8 = {
 	SPR_UNCORE_PCI_COMMON_FORMAT(),
 	.name			= "pciex8",
@@ -6657,7 +6683,7 @@ static struct intel_uncore_type *gnr_uncores[UNCORE_GNR_NUM_UNCORE_TYPES] = {
 	NULL,
 	&spr_uncore_pcu,
 	&gnr_uncore_ubox,
-	&spr_uncore_imc,
+	&gnr_uncore_imc,
 	NULL,
 	&gnr_uncore_upi,
 	NULL,
Signature · 1 line
2.51.0
author maintainer
#154 lore raw

PATCH 148/314 x86/boot: Handle relative CONFIG_EFI_SBAT_FILE file paths

In reply to Sasha Levin

From: Jan Stancek <[email protected]>

commit 3d1973a0c76a78a4728cff13648a188ed486cf44 upstream.

CONFIG_EFI_SBAT_FILE can be a relative path. When compiling using a different output directory (O=) the build currently fails because it can't find the filename set in CONFIG_EFI_SBAT_FILE:

arch/x86/boot/compressed/sbat.S: Assembler messages:
arch/x86/boot/compressed/sbat.S:6: Error: file not found: kernel.sbat

Add $(srctree) as include dir for sbat.o.

[ bp: Massage commit message. ]

---
 arch/x86/boot/compressed/Makefile | 1 +
 1 file changed, 1 insertion(+)
arch/x86/boot/compressed/Makefile +1 -0
index 74657589264df..2013840d6318f 100644
@@ -110,6 +110,7 @@ vmlinux-objs-$(CONFIG_EFI_SBAT) += $(obj)/sbat.o
 
 ifdef CONFIG_EFI_SBAT
 $(obj)/sbat.o: $(CONFIG_EFI_SBAT_FILE)
+AFLAGS_sbat.o += -I $(srctree)
 endif
 
 $(obj)/vmlinux: $(vmlinux-objs-y) $(vmlinux-libs-y) FORCE
Signature · 1 line
2.51.0
author maintainer
#155 lore raw

PATCH 149/314 x86/sev: Allow IBPB-on-Entry feature for SNP guests

In reply to Sasha Levin

From: Kim Phillips <[email protected]>

commit 9073428bb204d921ae15326bb7d4558d9d269aab upstream.

The SEV-SNP IBPB-on-Entry feature does not require a guest-side implementation. It was added in Zen5 h/w, after the first SNP Zen implementation, and thus was not accounted for when the initial set of SNP features were added to the kernel.

In its abundant precaution, commit

8c29f0165405 ("x86/sev: Add SEV-SNP guest feature negotiation support")

included SEV_STATUS' IBPB-on-Entry bit as a reserved bit, thereby masking guests from using the feature.

Allow guests to make use of IBPB-on-Entry when supported by the hypervisor, as the bit is now architecturally defined and safe to expose.

---
 arch/x86/boot/compressed/sev.c   | 1 +
 arch/x86/coco/sev/core.c         | 1 +
 arch/x86/include/asm/msr-index.h | 5 ++++-
 3 files changed, 6 insertions(+), 1 deletion(-)
arch/x86/boot/compressed/sev.c +1 -0
index 6e5c32a53d034..0d20bc178629e 100644
@@ -187,6 +187,7 @@ bool sev_es_check_ghcb_fault(unsigned long address)
 				 MSR_AMD64_SNP_RESERVED_BIT13 |		\
 				 MSR_AMD64_SNP_RESERVED_BIT15 |		\
 				 MSR_AMD64_SNP_SECURE_AVIC |		\
+				 MSR_AMD64_SNP_RESERVED_BITS19_22 |	\
 				 MSR_AMD64_SNP_RESERVED_MASK)
 
 #ifdef CONFIG_AMD_SECURE_AVIC
arch/x86/coco/sev/core.c +1 -0
index c8ddb9febe3d9..d20e9cc065a87 100644
@@ -122,6 +122,7 @@ static const char * const sev_status_feat_names[] = {
 	[MSR_AMD64_SNP_VMSA_REG_PROT_BIT]	= "VMSARegProt",
 	[MSR_AMD64_SNP_SMT_PROT_BIT]		= "SMTProt",
 	[MSR_AMD64_SNP_SECURE_AVIC_BIT]		= "SecureAVIC",
+	[MSR_AMD64_SNP_IBPB_ON_ENTRY_BIT]	= "IBPBOnEntry",
 };
 
 /*
arch/x86/include/asm/msr-index.h +4 -1
index 9e1720d73244f..d9e03c6d1d5c1 100644
@@ -711,7 +711,10 @@
 #define MSR_AMD64_SNP_SMT_PROT		BIT_ULL(MSR_AMD64_SNP_SMT_PROT_BIT)
 #define MSR_AMD64_SNP_SECURE_AVIC_BIT	18
 #define MSR_AMD64_SNP_SECURE_AVIC	BIT_ULL(MSR_AMD64_SNP_SECURE_AVIC_BIT)
-#define MSR_AMD64_SNP_RESV_BIT		19
+#define MSR_AMD64_SNP_RESERVED_BITS19_22 GENMASK_ULL(22, 19)
+#define MSR_AMD64_SNP_IBPB_ON_ENTRY_BIT	23
+#define MSR_AMD64_SNP_IBPB_ON_ENTRY	BIT_ULL(MSR_AMD64_SNP_IBPB_ON_ENTRY_BIT)
+#define MSR_AMD64_SNP_RESV_BIT		24
 #define MSR_AMD64_SNP_RESERVED_MASK	GENMASK_ULL(63, MSR_AMD64_SNP_RESV_BIT)
 #define MSR_AMD64_SAVIC_CONTROL		0xc0010138
 #define MSR_AMD64_SAVIC_EN_BIT		0
Signature · 1 line
2.51.0
author maintainer
#156 lore raw

PATCH 150/314 x86/boot/sev: Move SEV decompressor variables into the .data section

In reply to Sasha Levin

From: Tom Lendacky <[email protected]>

commit 4ca191cec17a997d0e3b2cd312f3a884288acc27 upstream.

As part of the work to remove the dependency on calling into the decompressor code (startup_64()) for a UEFI boot, a call to rmpadjust() was removed from sev_enable() in favor of checking the value of the snp_vmpl variable.

When booting through a non-UEFI path and calling startup_64(), the call to sev_enable() is performed before the BSS section is zeroed. With the removal of the rmpadjust() call and the corresponding check of the return code, the snp_vmpl variable is checked.

Since the kernel is running at VMPL0, the snp_vmpl variable will not have been set and should be the default value of 0. However, since the call occurs before the BSS is zeroed, the snp_vmpl variable may not actually be zero, which will cause the guest boot to fail.

Since the decompressor relocates itself, the BSS would need to be cleared both before and after the relocation, but this would, in effect, cause all of the changes to BSS variables before relocation to be lost after relocation.

Instead, move the snp_vmpl variable into the .data section so that it is initialized and the value made safe during relocation. As a pre-caution against future changes, move other SEV-related decompressor variables into the .data section, too.

---
 arch/x86/boot/compressed/sev.c     | 8 ++++----
 arch/x86/boot/startup/sev-shared.c | 2 +-
 2 files changed, 5 insertions(+), 5 deletions(-)
arch/x86/boot/compressed/sev.c +4 -4
index 0d20bc178629e..b688303666052 100644
@@ -27,17 +27,17 @@
 #include "sev.h"
 
 static struct ghcb boot_ghcb_page __aligned(PAGE_SIZE);
-struct ghcb *boot_ghcb;
+struct ghcb *boot_ghcb __section(".data");
 
 #undef __init
 #define __init
 
 #define __BOOT_COMPRESSED
 
-u8 snp_vmpl;
-u16 ghcb_version;
+u8 snp_vmpl __section(".data");
+u16 ghcb_version __section(".data");
 
-u64 boot_svsm_caa_pa;
+u64 boot_svsm_caa_pa __section(".data");
 
 /* Include code for early handlers */
 #include "../../boot/startup/sev-shared.c"
arch/x86/boot/startup/sev-shared.c +1 -1
index 4e22ffd735168..e52e886ad313d 100644
@@ -31,7 +31,7 @@ static u32 cpuid_std_range_max __ro_after_init;
 static u32 cpuid_hyp_range_max __ro_after_init;
 static u32 cpuid_ext_range_max __ro_after_init;
 
-bool sev_snp_needs_sfw;
+bool sev_snp_needs_sfw __section(".data");
 
 void __noreturn
 sev_es_terminate(unsigned int set, unsigned int reason)
Signature · 1 line
2.51.0
author maintainer
#157 lore raw

PATCH 151/314 platform/x86: dell-wmi-sysman: Don't hex dump plaintext password data

In reply to Sasha Levin

From: Thorsten Blum <[email protected]>

commit d1a196e0a6dcddd03748468a0e9e3100790fc85c upstream.

set_new_password() hex dumps the entire buffer, which contains plaintext password data, including current and new passwords. Remove the hex dump to avoid leaking credentials.

Fixes e8a60aa7404b ("platform/x86: Introduce support for Systems Management Driver over WMI for Dell Systems")
---
 .../platform/x86/dell/dell-wmi-sysman/passwordattr-interface.c   | 1 -
 1 file changed, 1 deletion(-)
drivers/platform/x86/dell/dell-wmi-sysman/passwordattr-interface.c +0 -1
index 86ec962aace9b..e586f7957946b 100644
@@ -93,7 +93,6 @@ int set_new_password(const char *password_type, const char *new)
 	if (ret < 0)
 		goto out;
 
-	print_hex_dump_bytes("set new password data: ", DUMP_PREFIX_NONE, buffer, buffer_size);
 	ret = call_password_interface(wmi_priv.password_attr_wdev, buffer, buffer_size);
 	/* on success copy the new password to current password */
 	if (!ret)
Signature · 1 line
2.51.0
author maintainer
#158 lore raw

PATCH 152/314 platform/x86: alienware-wmi-wmax: Add G-Mode support to m18 laptops

In reply to Sasha Levin

From: Kurt Borja <[email protected]>

commit bd5914caeb4b2de233992c31babccda88041b035 upstream.

Alienware m18 laptops support G-Mode. Therefore, match them with G-Series quirks.

---
 drivers/platform/x86/dell/alienware-wmi-wmax.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/platform/x86/dell/alienware-wmi-wmax.c +1 -1
index 01af6dde9057f..fdae40689f178 100644
@@ -175,7 +175,7 @@ static const struct dmi_system_id awcc_dmi_table[] __initconst = {
 			DMI_MATCH(DMI_SYS_VENDOR, "Alienware"),
 			DMI_MATCH(DMI_PRODUCT_NAME, "Alienware m18"),
 		},
-		.driver_data = &generic_quirks,
+		.driver_data = &g_series_quirks,
 	},
 	{
 		.ident = "Alienware x15",
Signature · 1 line
2.51.0
author maintainer
#159 lore raw

PATCH 153/314 platform/x86: dell-wmi: Add audio/mic mute key codes

In reply to Sasha Levin

From: Kurt Borja <[email protected]>

commit 26a7601471f62b95d56a81c3a8ccb551b5a6630f upstream.

Add audio/mic mute key codes found in Alienware m18 r1 AMD.

---
 drivers/platform/x86/dell/dell-wmi-base.c | 6 ++++++
 1 file changed, 6 insertions(+)
drivers/platform/x86/dell/dell-wmi-base.c +6 -0
index 28076929d6af5..907f1da01c8db 100644
@@ -80,6 +80,12 @@ static const struct dmi_system_id dell_wmi_smbios_list[] __initconst = {
 static const struct key_entry dell_wmi_keymap_type_0000[] = {
 	{ KE_IGNORE, 0x003a, { KEY_CAPSLOCK } },
 
+	/* Audio mute toggle */
+	{ KE_KEY,    0x0109, { KEY_MUTE } },
+
+	/* Mic mute toggle */
+	{ KE_KEY,    0x0150, { KEY_MICMUTE } },
+
 	/* Meta key lock */
 	{ KE_IGNORE, 0xe000, { KEY_RIGHTMETA } },
 
Signature · 1 line
2.51.0
author maintainer
#160 lore raw

PATCH 154/314 ALSA: hda/realtek: Add quirk for HP Pavilion 15-eh1xxx to enable mute LED

In reply to Sasha Levin

From: Zhang Heng <[email protected]>

commit 068641bc9dc3d680d1ec4f6ee9199d4812041dff upstream.

The HP Pavilion 15-eh1xxx series uses the HP mainboard 88D1 with ALC245 and needs the ALC245_FIXUP_HP_MUTE_LED_V1_COEFBIT quirk to make the mute led working.

---
 sound/hda/codecs/realtek/alc269.c | 1 +
 1 file changed, 1 insertion(+)
sound/hda/codecs/realtek/alc269.c +1 -0
index 6d3d464f1f6c6..e1e0b4de4a69f 100644
@@ -6732,6 +6732,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x103c, 0x8898, "HP EliteBook 845 G8 Notebook PC", ALC285_FIXUP_HP_LIMIT_INT_MIC_BOOST),
 	SND_PCI_QUIRK(0x103c, 0x88b3, "HP ENVY x360 Convertible 15-es0xxx", ALC245_FIXUP_HP_ENVY_X360_MUTE_LED),
 	SND_PCI_QUIRK(0x103c, 0x88d0, "HP Pavilion 15-eh1xxx (mainboard 88D0)", ALC287_FIXUP_HP_GPIO_LED),
+	SND_PCI_QUIRK(0x103c, 0x88d1, "HP Pavilion 15-eh1xxx (mainboard 88D1)", ALC245_FIXUP_HP_MUTE_LED_V1_COEFBIT),
 	SND_PCI_QUIRK(0x103c, 0x88dd, "HP Pavilion 15z-ec200", ALC285_FIXUP_HP_MUTE_LED),
 	SND_PCI_QUIRK(0x103c, 0x88eb, "HP Victus 16-e0xxx", ALC245_FIXUP_HP_MUTE_LED_V2_COEFBIT),
 	SND_PCI_QUIRK(0x103c, 0x8902, "HP OMEN 16", ALC285_FIXUP_HP_MUTE_LED),
Signature · 1 line
2.51.0
author maintainer
#161 lore raw

PATCH 155/314 ALSA: doc: usb-audio: Add doc for QUIRK_FLAG_SKIP_IFACE_SETUP

In reply to Sasha Levin

From: Rong Zhang <[email protected]>

commit 93992667d0ab695ac30ceec91a516fd4bf725d75 upstream.

QUIRK_FLAG_SKIP_IFACE_SETUP was introduced into usb-audio before without appropriate documentation, so add it.

Fixes 38c322068a26 ("ALSA: usb-audio: Add QUIRK_FLAG_SKIP_IFACE_SETUP")
---
 Documentation/sound/alsa-configuration.rst | 4 ++++
 1 file changed, 4 insertions(+)
Documentation/sound/alsa-configuration.rst +4 -0
index 0a4eaa7d66ddd..55b845d382368 100644
@@ -2372,6 +2372,10 @@ quirk_flags
           audible volume
         * bit 25: ``mixer_capture_min_mute``
           Similar to bit 24 but for capture streams
+        * bit 26: ``skip_iface_setup``
+          Skip the probe-time interface setup (usb_set_interface,
+          init_pitch, init_sample_rate); redundant with
+          snd_usb_endpoint_prepare() at stream-open time
 
 This module supports multiple devices, autoprobe and hotplugging.
 
Signature · 1 line
2.51.0
author maintainer
#162 lore raw

PATCH 156/314 ALSA: usb-audio: Use correct version for UAC3 header validation

In reply to Sasha Levin

From: Jun Seo <[email protected]>

commit 54f9d645a5453d0bfece0c465d34aaf072ea99fa upstream.

The entry of the validators table for UAC3 AC header descriptor is defined with the wrong protocol version UAC_VERSION_2, while it should have been UAC_VERSION_3. This results in the validator never matching for actual UAC3 devices (protocol == UAC_VERSION_3), causing their header descriptors to bypass validation entirely. A malicious USB device presenting a truncated UAC3 header could exploit this to cause out-of-bounds reads when the driver later accesses unvalidated descriptor fields.

The bug was introduced in the same commit as the recently fixed UAC3 feature unit sub-type typo, and appears to be from the same copy-paste error when the UAC3 section was created from the UAC2 section.

Fixes 57f8770620e9 ("ALSA: usb-audio: More validations of descriptor units")
---
 sound/usb/validate.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
sound/usb/validate.c +1 -1
index 4bb4893f6e74f..f62b7cc041dc9 100644
@@ -281,7 +281,7 @@ static const struct usb_desc_validator audio_validators[] = {
 	/* UAC_VERSION_2, UAC2_SAMPLE_RATE_CONVERTER: not implemented yet */
 
 	/* UAC3 */
-	FIXED(UAC_VERSION_2, UAC_HEADER, struct uac3_ac_header_descriptor),
+	FIXED(UAC_VERSION_3, UAC_HEADER, struct uac3_ac_header_descriptor),
 	FIXED(UAC_VERSION_3, UAC_INPUT_TERMINAL,
 	      struct uac3_input_terminal_descriptor),
 	FIXED(UAC_VERSION_3, UAC_OUTPUT_TERMINAL,
Signature · 1 line
2.51.0
author maintainer
#163 lore raw

PATCH 157/314 ALSA: hda/intel: increase default bdl_pos_adj for Nvidia controllers

In reply to Sasha Levin

From: Panagiotis Foliadis <[email protected]>

commit e9fb2028f1eb563e653cff3b0d1c87c5e0203d45 upstream.

The default bdl_pos_adj of 32 for Nvidia HDA controllers is insufficient on GA102 (and likely other recent Nvidia GPUs) after S3 suspend/resume. The controller's DMA timing degrades after resume, causing premature IRQ detection in azx_position_ok() which results in silent HDMI/DP audio output despite userspace reporting a valid playback state and correct ELD data.

Increase bdl_pos_adj to 64 for AZX_DRIVER_NVIDIA, matching the value already used by Intel Apollo Lake for the same class of timing issue.

---
 sound/hda/controllers/intel.c | 2 ++
 1 file changed, 2 insertions(+)
sound/hda/controllers/intel.c +2 -0
index a19258c95886c..9306e7a31f02b 100644
@@ -1751,6 +1751,8 @@ static int default_bdl_pos_adj(struct azx *chip)
 		return 1;
 	case AZX_DRIVER_ZHAOXINHDMI:
 		return 128;
+	case AZX_DRIVER_NVIDIA:
+		return 64;
 	default:
 		return 32;
 	}
Signature · 1 line
2.51.0
author maintainer
#164 lore raw

PATCH 158/314 ALSA: hda/realtek: fix model name typo for Samsung Galaxy Book Flex (NT950QCG-X716)

In reply to Sasha Levin

From: Juhyung Park <[email protected]>

commit 43a44fb7f2fa163926b23149805e989ba2395db1 upstream.

There's no product named "Samsung Galaxy Flex Book". Use the correct "Samsung Galaxy Book Flex" name.

---
 sound/hda/codecs/realtek/alc269.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
sound/hda/codecs/realtek/alc269.c +1 -1
index e1e0b4de4a69f..11c526d94858d 100644
@@ -7149,7 +7149,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x144d, 0xc109, "Samsung Ativ book 9 (NP900X3G)", ALC269_FIXUP_INV_DMIC),
 	SND_PCI_QUIRK(0x144d, 0xc169, "Samsung Notebook 9 Pen (NP930SBE-K01US)", ALC298_FIXUP_SAMSUNG_AMP),
 	SND_PCI_QUIRK(0x144d, 0xc176, "Samsung Notebook 9 Pro (NP930MBE-K04US)", ALC298_FIXUP_SAMSUNG_AMP),
-	SND_PCI_QUIRK(0x144d, 0xc189, "Samsung Galaxy Flex Book (NT950QCG-X716)", ALC298_FIXUP_SAMSUNG_AMP),
+	SND_PCI_QUIRK(0x144d, 0xc189, "Samsung Galaxy Book Flex (NT950QCG-X716)", ALC298_FIXUP_SAMSUNG_AMP),
 	SND_PCI_QUIRK(0x144d, 0xc18a, "Samsung Galaxy Book Ion (NP930XCJ-K01US)", ALC298_FIXUP_SAMSUNG_AMP),
 	SND_PCI_QUIRK(0x144d, 0xc1a3, "Samsung Galaxy Book Pro (NP935XDB-KC1SE)", ALC298_FIXUP_SAMSUNG_AMP),
 	SND_PCI_QUIRK(0x144d, 0xc1a4, "Samsung Galaxy Book Pro 360 (NT935QBD)", ALC298_FIXUP_SAMSUNG_AMP),
Signature · 1 line
2.51.0
author maintainer
#165 lore raw

PATCH 159/314 ALSA: hda/realtek: Add quirk for Acer Aspire V3-572G

In reply to Sasha Levin

From: Panagiotis Foliadis <[email protected]>

commit cbddd303416456db5ceeedaf9e262096f079e861 upstream.

The Acer Aspire V3-572G has a combo jack (ALC283) but the BIOS sets pin 0x19 to 0x411111f0 (not connected), so the headset mic is not detected.

Add a quirk to override pin 0x19 as a headset mic and enable headset mode.

---
 sound/hda/codecs/realtek/alc269.c | 1 +
 1 file changed, 1 insertion(+)
sound/hda/codecs/realtek/alc269.c +1 -0
index 11c526d94858d..a094d60194b53 100644
@@ -6451,6 +6451,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1025, 0x079b, "Acer Aspire V5-573G", ALC282_FIXUP_ASPIRE_V5_PINS),
 	SND_PCI_QUIRK(0x1025, 0x080d, "Acer Aspire V5-122P", ALC269_FIXUP_ASPIRE_HEADSET_MIC),
 	SND_PCI_QUIRK(0x1025, 0x0840, "Acer Aspire E1", ALC269VB_FIXUP_ASPIRE_E1_COEF),
+	SND_PCI_QUIRK(0x1025, 0x0943, "Acer Aspire V3-572G", ALC269_FIXUP_ASPIRE_HEADSET_MIC),
 	SND_PCI_QUIRK(0x1025, 0x100c, "Acer Aspire E5-574G", ALC255_FIXUP_ACER_LIMIT_INT_MIC_BOOST),
 	SND_PCI_QUIRK(0x1025, 0x101c, "Acer Veriton N2510G", ALC269_FIXUP_LIFEBOOK),
 	SND_PCI_QUIRK(0x1025, 0x102b, "Acer Aspire C24-860", ALC286_FIXUP_ACER_AIO_MIC_NO_PRESENCE),
Signature · 1 line
2.51.0
author maintainer
#166 lore raw

PATCH 160/314 ALSA: hda/realtek: add quirk for Samsung Galaxy Book Flex (NT950QCT-A38A)

In reply to Sasha Levin

From: Juhyung Park <[email protected]>

commit 9fb16a5c5ff93058851099a2b80a899b0c53fe3f upstream.

Similar to other Samsung laptops, NT950QCT also requires the ALC298_FIXUP_SAMSUNG_AMP quirk applied.

---
 sound/hda/codecs/realtek/alc269.c | 1 +
 1 file changed, 1 insertion(+)
sound/hda/codecs/realtek/alc269.c +1 -0
index a094d60194b53..f40e00a578d99 100644
@@ -7150,6 +7150,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x144d, 0xc109, "Samsung Ativ book 9 (NP900X3G)", ALC269_FIXUP_INV_DMIC),
 	SND_PCI_QUIRK(0x144d, 0xc169, "Samsung Notebook 9 Pen (NP930SBE-K01US)", ALC298_FIXUP_SAMSUNG_AMP),
 	SND_PCI_QUIRK(0x144d, 0xc176, "Samsung Notebook 9 Pro (NP930MBE-K04US)", ALC298_FIXUP_SAMSUNG_AMP),
+	SND_PCI_QUIRK(0x144d, 0xc188, "Samsung Galaxy Book Flex (NT950QCT-A38A)", ALC298_FIXUP_SAMSUNG_AMP),
 	SND_PCI_QUIRK(0x144d, 0xc189, "Samsung Galaxy Book Flex (NT950QCG-X716)", ALC298_FIXUP_SAMSUNG_AMP),
 	SND_PCI_QUIRK(0x144d, 0xc18a, "Samsung Galaxy Book Ion (NP930XCJ-K01US)", ALC298_FIXUP_SAMSUNG_AMP),
 	SND_PCI_QUIRK(0x144d, 0xc1a3, "Samsung Galaxy Book Pro (NP935XDB-KC1SE)", ALC298_FIXUP_SAMSUNG_AMP),
Signature · 1 line
2.51.0
author maintainer
#167 lore raw

PATCH 161/314 wifi: radiotap: reject radiotap with unknown bits

In reply to Sasha Levin

From: Johannes Berg <[email protected]>

commit c854758abe0b8d86f9c43dc060ff56a0ee5b31e0 upstream.

The radiotap parser is currently only used with the radiotap namespace (not with vendor namespaces), but if the undefined field 18 is used, the alignment/size is unknown as well. In this case, iterator->_next_ns_data isn't initialized (it's only set for skipping vendor namespaces), and syzbot points out that we later compare against this uninitialized value.

Fix this by moving the rejection of unknown radiotap fields down to after the in-namespace lookup, so it will really use iterator->_next_ns_data only for vendor namespaces, even in case undefined fields are present.

---
 net/wireless/radiotap.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)
net/wireless/radiotap.c +2 -2
index 326faea38ca38..c85eaa583a466 100644
@@ -239,14 +239,14 @@ int ieee80211_radiotap_iterator_next(
 		default:
 			if (!iterator->current_namespace ||
 			    iterator->_arg_index >= iterator->current_namespace->n_bits) {
-				if (iterator->current_namespace == &radiotap_ns)
-					return -ENOENT;
 				align = 0;
 			} else {
 				align = iterator->current_namespace->align_size[iterator->_arg_index].align;
 				size = iterator->current_namespace->align_size[iterator->_arg_index].size;
 			}
 			if (!align) {
+				if (iterator->current_namespace == &radiotap_ns)
+					return -ENOENT;
 				/* skip all subsequent data */
 				iterator->_arg = iterator->_next_ns_data;
 				/* give up on this namespace */
Signature · 1 line
2.51.0
author maintainer
#168 lore raw

PATCH 162/314 wifi: libertas: fix use-after-free in lbs_free_adapter()

In reply to Sasha Levin

From: Daniel Hodges <[email protected]>

commit 03cc8f90d0537fcd4985c3319b4fafbf2e3fb1f0 upstream.

The lbs_free_adapter() function uses timer_delete() (non-synchronous) for both command_timer and tx_lockup_timer before the structure is freed. This is incorrect because timer_delete() does not wait for any running timer callback to complete.

If a timer callback is executing when lbs_free_adapter() is called, the callback will access freed memory since lbs_cfg_free() frees the containing structure immediately after lbs_free_adapter() returns.

Both timer callbacks (lbs_cmd_timeout_handler and lbs_tx_lockup_handler) access priv->driver_lock, priv->cur_cmd, priv->dev, and other fields, which would all be use-after-free violations.

Use timer_delete_sync() instead to ensure any running timer callback has completed before returning.

This bug was introduced in commit 8f641d93c38a ("libertas: detect TX lockups and reset hardware") where del_timer() was used instead of del_timer_sync() in the cleanup path. The command_timer has had the same issue since the driver was first written.

Fixes 8f641d93c38a ("libertas: detect TX lockups and reset hardware")
Fixes 954ee164f4f4 ("[PATCH] libertas: reorganize and simplify init sequence")
---
 drivers/net/wireless/marvell/libertas/main.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)
drivers/net/wireless/marvell/libertas/main.c +2 -2
index d44e02c6fe385..dd97f1b61f4d1 100644
@@ -799,8 +799,8 @@ static void lbs_free_adapter(struct lbs_private *priv)
 {
 	lbs_free_cmd_buffer(priv);
 	kfifo_free(&priv->event_fifo);
-	timer_delete(&priv->command_timer);
-	timer_delete(&priv->tx_lockup_timer);
+	timer_delete_sync(&priv->command_timer);
+	timer_delete_sync(&priv->tx_lockup_timer);
 }
 
 static const struct net_device_ops lbs_netdev_ops = {
Signature · 1 line
2.51.0
author maintainer
#169 lore raw

PATCH 163/314 wifi: cfg80211: cancel rfkill_block work in wiphy_unregister()

In reply to Sasha Levin

From: Daniil Dulov <[email protected]>

commit 767d23ade706d5fa51c36168e92a9c5533c351a1 upstream.

There is a use-after-free error in cfg80211_shutdown_all_interfaces found by syzkaller:

BUG: KASAN: use-after-free in cfg80211_shutdown_all_interfaces+0x213/0x220
Read of size 8 at addr ffff888112a78d98 by task kworker/0:5/5326
CPU: 0 UID: 0 PID: 5326 Comm: kworker/0:5 Not tainted 6.19.0-rc2 #2 PREEMPT(voluntary)
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.15.0-1 04/01/2014
Workqueue: events cfg80211_rfkill_block_work
Call Trace:
 <TASK>
 dump_stack_lvl+0x116/0x1f0
 print_report+0xcd/0x630
 kasan_report+0xe0/0x110
 cfg80211_shutdown_all_interfaces+0x213/0x220
 cfg80211_rfkill_block_work+0x1e/0x30
 process_one_work+0x9cf/0x1b70
 worker_thread+0x6c8/0xf10
 kthread+0x3c5/0x780
 ret_from_fork+0x56d/0x700
 ret_from_fork_asm+0x1a/0x30
 </TASK>

The problem arises due to the rfkill_block work is not cancelled when wiphy is being unregistered. In order to fix the issue cancel the corresponding work in wiphy_unregister().

Found by Linux Verification Center (linuxtesting.org) with Syzkaller.

---
 net/wireless/core.c | 1 +
 1 file changed, 1 insertion(+)
net/wireless/core.c +1 -0
index 2ce6e39926d05..6b204ca91a140 100644
@@ -1195,6 +1195,7 @@ void wiphy_unregister(struct wiphy *wiphy)
 	/* this has nothing to do now but make sure it's gone */
 	cancel_work_sync(&rdev->wiphy_work);
 
+	cancel_work_sync(&rdev->rfkill_block);
 	cancel_work_sync(&rdev->conn_work);
 	flush_work(&rdev->event_work);
 	cancel_delayed_work_sync(&rdev->dfs_update_channels_wk);
Signature · 1 line
2.51.0
author maintainer
#170 lore raw

PATCH 164/314 wifi: mac80211: bounds-check link_id in ieee80211_ml_reconfiguration

In reply to Sasha Levin

From: Ariel Silver <[email protected]>

commit 162d331d833dc73a3e905a24c44dd33732af1fc5 upstream.

link_id is taken from the ML Reconfiguration element (control & 0x000f), so it can be 0..15. link_removal_timeout[] has IEEE80211_MLD_MAX_NUM_LINKS
(15) elements, so index 15 is out-of-bounds. Skip subelements with link_id >= IEEE80211_MLD_MAX_NUM_LINKS to avoid a stack out-of-bounds write.

Fixes 8eb8dd2ffbbb ("wifi: mac80211: Support link removal using Reconfiguration ML element")
---
 net/mac80211/mlme.c | 3 +++
 1 file changed, 3 insertions(+)
net/mac80211/mlme.c +3 -0
index 8ba199cd38c0f..f119149bcc1c1 100644
@@ -6977,6 +6977,9 @@ static void ieee80211_ml_reconfiguration(struct ieee80211_sub_if_data *sdata,
 		control = le16_to_cpu(prof->control);
 		link_id = control & IEEE80211_MLE_STA_RECONF_CONTROL_LINK_ID;
 
+		if (link_id >= IEEE80211_MLD_MAX_NUM_LINKS)
+			continue;
+
 		removed_links |= BIT(link_id);
 
 		/* the MAC address should not be included, but handle it */
Signature · 1 line
2.51.0
author maintainer
#171 lore raw

PATCH 165/314 wifi: mac80211: fix NULL pointer dereference in mesh_rx_csa_frame()

In reply to Sasha Levin

From: Vahagn Vardanian <[email protected]>

commit 017c1792525064a723971f0216e6ef86a8c7af11 upstream.

In mesh_rx_csa_frame(), elems->mesh_chansw_params_ie is dereferenced at lines 1638 and 1642 without a prior NULL check:

    ifmsh->chsw_ttl = elems->mesh_chansw_params_ie->mesh_ttl;
    ...
    pre_value = le16_to_cpu(elems->mesh_chansw_params_ie->mesh_pre_value);

The mesh_matches_local() check above only validates the Mesh ID, Mesh Configuration, and Supported Rates IEs. It does not verify the presence of the Mesh Channel Switch Parameters IE (element ID 118). When a received CSA action frame omits that IE, ieee802_11_parse_elems() leaves elems->mesh_chansw_params_ie as NULL, and the unconditional dereference causes a kernel NULL pointer dereference.

A remote mesh peer with an established peer link (PLINK_ESTAB) can trigger this by sending a crafted SPECTRUM_MGMT/CHL_SWITCH action frame that includes a matching Mesh ID and Mesh Configuration IE but omits the Mesh Channel Switch Parameters IE. No authentication beyond the default open mesh peering is required.

Crash confirmed on kernel 6.17.0-5-generic via mac80211_hwsim:

  BUG: kernel NULL pointer dereference, address: 0000000000000000
  Oops: Oops: 0000 [#1] SMP NOPTI
  RIP: 0010:ieee80211_mesh_rx_queued_mgmt+0x143/0x2a0 [mac80211]
  CR2: 0000000000000000

Fix by adding a NULL check for mesh_chansw_params_ie after mesh_matches_local() returns, consistent with how other optional IEs are guarded throughout the mesh code.

The bug has been present since v3.13 (released 2014-01-19).

Fixes 8f2535b92d68 ("mac80211: process the CSA frame for mesh accordingly")
---
 net/mac80211/mesh.c | 3 +++
 1 file changed, 3 insertions(+)
net/mac80211/mesh.c +3 -0
index f37068a533f4e..e235ab7a5651c 100644
@@ -1629,6 +1629,9 @@ static void mesh_rx_csa_frame(struct ieee80211_sub_if_data *sdata,
 	if (!mesh_matches_local(sdata, elems))
 		goto free;
 
+	if (!elems->mesh_chansw_params_ie)
+		goto free;
+
 	ifmsh->chsw_ttl = elems->mesh_chansw_params_ie->mesh_ttl;
 	if (!--ifmsh->chsw_ttl)
 		fwd_csa = false;
Signature · 1 line
2.51.0
author maintainer
#172 lore raw

PATCH 166/314 Bluetooth: purge error queues in socket destructors

In reply to Sasha Levin

From: Heitor Alves de Siqueira <[email protected]>

commit 21e4271e65094172aadd5beb8caea95dd0fbf6d7 upstream.

When TX timestamping is enabled via SO_TIMESTAMPING, SKBs may be queued into sk_error_queue and will stay there until consumed. If userspace never gets to read the timestamps, or if the controller is removed unexpectedly, these SKBs will leak.

Fix by adding skb_queue_purge() calls for sk_error_queue in affected bluetooth destructors. RFCOMM does not currently use sk_error_queue.

Fixes 134f4b39df7b ("Bluetooth: add support for skb TX SND/COMPLETION timestamping")
Reported-by [email protected]
---
 net/bluetooth/hci_sock.c   | 1 +
 net/bluetooth/iso.c        | 1 +
 net/bluetooth/l2cap_sock.c | 1 +
 net/bluetooth/sco.c        | 1 +
 4 files changed, 4 insertions(+)
net/bluetooth/hci_sock.c +1 -0
index ad19022ae127a..5295ff001e38c 100644
@@ -2166,6 +2166,7 @@ static void hci_sock_destruct(struct sock *sk)
 	mgmt_cleanup(sk);
 	skb_queue_purge(&sk->sk_receive_queue);
 	skb_queue_purge(&sk->sk_write_queue);
+	skb_queue_purge(&sk->sk_error_queue);
 }
 
 static const struct proto_ops hci_sock_ops = {
net/bluetooth/iso.c +1 -0
index 616c2fef91d24..46ebd69026fe2 100644
@@ -728,6 +728,7 @@ static void iso_sock_destruct(struct sock *sk)
 
 	skb_queue_purge(&sk->sk_receive_queue);
 	skb_queue_purge(&sk->sk_write_queue);
+	skb_queue_purge(&sk->sk_error_queue);
 }
 
 static void iso_sock_cleanup_listen(struct sock *parent)
net/bluetooth/l2cap_sock.c +1 -0
index c877fe5aed07d..ab86aeef98d18 100644
@@ -1806,6 +1806,7 @@ static void l2cap_sock_destruct(struct sock *sk)
 
 	skb_queue_purge(&sk->sk_receive_queue);
 	skb_queue_purge(&sk->sk_write_queue);
+	skb_queue_purge(&sk->sk_error_queue);
 }
 
 static void l2cap_skb_msg_name(struct sk_buff *skb, void *msg_name,
net/bluetooth/sco.c +1 -0
index 298c2a9ab4df8..49a47eaa674da 100644
@@ -470,6 +470,7 @@ static void sco_sock_destruct(struct sock *sk)
 
 	skb_queue_purge(&sk->sk_receive_queue);
 	skb_queue_purge(&sk->sk_write_queue);
+	skb_queue_purge(&sk->sk_error_queue);
 }
 
 static void sco_sock_cleanup_listen(struct sock *parent)
Signature · 1 line
2.51.0
author maintainer
#173 lore raw

PATCH 167/314 gve: fix incorrect buffer cleanup in gve_tx_clean_pending_packets for QPL

In reply to Sasha Levin

From: Ankit Garg <[email protected]>

commit fb868db5f4bccd7a78219313ab2917429f715cea upstream.

In DQ-QPL mode, gve_tx_clean_pending_packets() incorrectly uses the RDA buffer cleanup path. It iterates num_bufs times and attempts to unmap entries in the dma array.

This leads to two issues:
1. The dma array shares storage with tx_qpl_buf_ids (union). Interpreting buffer IDs as DMA addresses results in attempting to unmap incorrect memory locations.
2. num_bufs in QPL mode (counting 2K chunks) can significantly exceed the size of the dma array, causing out-of-bounds access warnings
(trace below is how we noticed this issue).

UBSAN: array-index-out-of-bounds in
drivers/net/ethernet/drivers/net/ethernet/google/gve/gve_tx_dqo.c:178:5 index 18 is out of
range for type 'dma_addr_t[18]' (aka 'unsigned long long[18]')
Workqueue: gve gve_service_task [gve]
Call Trace:
<TASK>
dump_stack_lvl+0x33/0xa0
__ubsan_handle_out_of_bounds+0xdc/0x110
gve_tx_stop_ring_dqo+0x182/0x200 [gve]
gve_close+0x1be/0x450 [gve]
gve_reset+0x99/0x120 [gve]
gve_service_task+0x61/0x100 [gve]
process_scheduled_works+0x1e9/0x380

Fix this by properly checking for QPL mode and delegating to gve_free_tx_qpl_bufs() to reclaim the buffers.

---
 drivers/net/ethernet/google/gve/gve_tx_dqo.c | 56 +++++++++-----------
 1 file changed, 25 insertions(+), 31 deletions(-)
drivers/net/ethernet/google/gve/gve_tx_dqo.c +25 -31
index 6f1d515673d25..5fbee184f0e7a 100644
@@ -167,6 +167,25 @@ gve_free_pending_packet(struct gve_tx_ring *tx,
 	}
 }
 
+static void gve_unmap_packet(struct device *dev,
+			     struct gve_tx_pending_packet_dqo *pkt)
+{
+	int i;
+
+	if (!pkt->num_bufs)
+		return;
+
+	/* SKB linear portion is guaranteed to be mapped */
+	dma_unmap_single(dev, dma_unmap_addr(pkt, dma[0]),
+			 dma_unmap_len(pkt, len[0]), DMA_TO_DEVICE);
+	for (i = 1; i < pkt->num_bufs; i++) {
+		netmem_dma_unmap_page_attrs(dev, dma_unmap_addr(pkt, dma[i]),
+					    dma_unmap_len(pkt, len[i]),
+					    DMA_TO_DEVICE, 0);
+	}
+	pkt->num_bufs = 0;
+}
+
 /* gve_tx_free_desc - Cleans up all pending tx requests and buffers.
  */
 static void gve_tx_clean_pending_packets(struct gve_tx_ring *tx)
@@ -176,21 +195,12 @@ static void gve_tx_clean_pending_packets(struct gve_tx_ring *tx)
 	for (i = 0; i < tx->dqo.num_pending_packets; i++) {
 		struct gve_tx_pending_packet_dqo *cur_state =
 			&tx->dqo.pending_packets[i];
-		int j;
-
-		for (j = 0; j < cur_state->num_bufs; j++) {
-			if (j == 0) {
-				dma_unmap_single(tx->dev,
-					dma_unmap_addr(cur_state, dma[j]),
-					dma_unmap_len(cur_state, len[j]),
-					DMA_TO_DEVICE);
-			} else {
-				dma_unmap_page(tx->dev,
-					dma_unmap_addr(cur_state, dma[j]),
-					dma_unmap_len(cur_state, len[j]),
-					DMA_TO_DEVICE);
-			}
-		}
+
+		if (tx->dqo.qpl)
+			gve_free_tx_qpl_bufs(tx, cur_state);
+		else
+			gve_unmap_packet(tx->dev, cur_state);
+
 		if (cur_state->skb) {
 			dev_consume_skb_any(cur_state->skb);
 			cur_state->skb = NULL;
@@ -1158,22 +1168,6 @@ static void remove_from_list(struct gve_tx_ring *tx,
 	}
 }
 
-static void gve_unmap_packet(struct device *dev,
-			     struct gve_tx_pending_packet_dqo *pkt)
-{
-	int i;
-
-	/* SKB linear portion is guaranteed to be mapped */
-	dma_unmap_single(dev, dma_unmap_addr(pkt, dma[0]),
-			 dma_unmap_len(pkt, len[0]), DMA_TO_DEVICE);
-	for (i = 1; i < pkt->num_bufs; i++) {
-		netmem_dma_unmap_page_attrs(dev, dma_unmap_addr(pkt, dma[i]),
-					    dma_unmap_len(pkt, len[i]),
-					    DMA_TO_DEVICE, 0);
-	}
-	pkt->num_bufs = 0;
-}
-
 /* Completion types and expected behavior:
  * No Miss compl + Packet compl = Packet completed normally.
  * Miss compl + Re-inject compl = Packet completed normally.
Signature · 1 line
2.51.0
author maintainer
#174 lore raw

PATCH 168/314 net: phy: register phy led_triggers during probe to avoid AB-BA deadlock

In reply to Sasha Levin

From: Andrew Lunn <[email protected]>

commit c8dbdc6e380e7e96a51706db3e4b7870d8a9402d upstream.

There is an AB-BA deadlock when both LEDS_TRIGGER_NETDEV and LED_TRIGGER_PHY are enabled:

[ 1362.049207] [<8054e4b8>] led_trigger_register+0x5c/0x1fc             <-- Trying to get lock "triggers_list_lock" via down_write(&triggers_list_lock);
[ 1362.054536] [<80662830>] phy_led_triggers_register+0xd0/0x234
[ 1362.060329] [<8065e200>] phy_attach_direct+0x33c/0x40c
[ 1362.065489] [<80651fc4>] phylink_fwnode_phy_connect+0x15c/0x23c
[ 1362.071480] [<8066ee18>] mtk_open+0x7c/0xba0
[ 1362.075849] [<806d714c>] __dev_open+0x280/0x2b0
[ 1362.080384] [<806d7668>] __dev_change_flags+0x244/0x24c
[ 1362.085598] [<806d7698>] dev_change_flags+0x28/0x78
[ 1362.090528] [<807150e4>] dev_ioctl+0x4c0/0x654                       <-- Hold lock "rtnl_mutex" by calling rtnl_lock();
[ 1362.094985] [<80694360>] sock_ioctl+0x2f4/0x4e0
[ 1362.099567] [<802e9c4c>] sys_ioctl+0x32c/0xd8c
[ 1362.104022] [<80014504>] syscall_common+0x34/0x58

Here LED_TRIGGER_PHY is registering LED triggers during phy_attach while holding RTNL and then taking triggers_list_lock.

[ 1362.191101] [<806c2640>] register_netdevice_notifier+0x60/0x168      <-- Trying to get lock "rtnl_mutex" via rtnl_lock();
[ 1362.197073] [<805504ac>] netdev_trig_activate+0x194/0x1e4
[ 1362.202490] [<8054e28c>] led_trigger_set+0x1d4/0x360                 <-- Hold lock "triggers_list_lock" by down_read(&triggers_list_lock);
[ 1362.207511] [<8054eb38>] led_trigger_write+0xd8/0x14c
[ 1362.212566] [<80381d98>] sysfs_kf_bin_write+0x80/0xbc
[ 1362.217688] [<8037fcd8>] kernfs_fop_write_iter+0x17c/0x28c
[ 1362.223174] [<802cbd70>] vfs_write+0x21c/0x3c4
[ 1362.227712] [<802cc0c4>] ksys_write+0x78/0x12c
[ 1362.232164] [<80014504>] syscall_common+0x34/0x58

Here LEDS_TRIGGER_NETDEV is being enabled on an LED. It first takes triggers_list_lock and then RTNL. A classical AB-BA deadlock.

phy_led_triggers_registers() does not require the RTNL, it does not make any calls into the network stack which require protection. There is also no requirement the PHY has been attached to a MAC, the triggers only make use of phydev state. This allows the call to phy_led_triggers_registers() to be placed elsewhere. PHY probe() and release() don't hold RTNL, so solving the AB-BA deadlock.

---
 drivers/net/phy/phy_device.c | 25 +++++++++++++++++--------
 1 file changed, 17 insertions(+), 8 deletions(-)
drivers/net/phy/phy_device.c +17 -8
index 7a67c900e79a5..2353d6eced68d 100644
@@ -1751,8 +1751,6 @@ int phy_attach_direct(struct net_device *dev, struct phy_device *phydev,
 		goto error;
 
 	phy_resume(phydev);
-	if (!phydev->is_on_sfp_module)
-		phy_led_triggers_register(phydev);
 
 	/**
 	 * If the external phy used by current mac interface is managed by
@@ -1867,9 +1865,6 @@ void phy_detach(struct phy_device *phydev)
 	phydev->phy_link_change = NULL;
 	phydev->phylink = NULL;
 
-	if (!phydev->is_on_sfp_module)
-		phy_led_triggers_unregister(phydev);
-
 	if (phydev->mdio.dev.driver)
 		module_put(phydev->mdio.dev.driver->owner);
 
@@ -3500,16 +3495,27 @@ static int phy_probe(struct device *dev)
 	/* Set the state to READY by default */
 	phydev->state = PHY_READY;
 
+	/* Register the PHY LED triggers */
+	if (!phydev->is_on_sfp_module)
+		phy_led_triggers_register(phydev);
+
 	/* Get the LEDs from the device tree, and instantiate standard
 	 * LEDs for them.
 	 */
-	if (IS_ENABLED(CONFIG_PHYLIB_LEDS) && !phy_driver_is_genphy(phydev))
+	if (IS_ENABLED(CONFIG_PHYLIB_LEDS) && !phy_driver_is_genphy(phydev)) {
 		err = of_phy_leds(phydev);
+		if (err)
+			goto out;
+	}
+
+	return 0;
 
 out:
+	if (!phydev->is_on_sfp_module)
+		phy_led_triggers_unregister(phydev);
+
 	/* Re-assert the reset signal on error */
-	if (err)
-		phy_device_reset(phydev, 1);
+	phy_device_reset(phydev, 1);
 
 	return err;
 }
@@ -3523,6 +3529,9 @@ static int phy_remove(struct device *dev)
 	if (IS_ENABLED(CONFIG_PHYLIB_LEDS) && !phy_driver_is_genphy(phydev))
 		phy_leds_unregister(phydev);
 
+	if (!phydev->is_on_sfp_module)
+		phy_led_triggers_unregister(phydev);
+
 	phydev->state = PHY_DOWN;
 
 	sfp_bus_del_upstream(phydev->sfp_bus);
Signature · 1 line
2.51.0
author maintainer
#175 lore raw

PATCH 169/314 IB/mthca: Add missed mthca_unmap_user_db() for mthca_create_srq()

In reply to Sasha Levin

From: Jason Gunthorpe <[email protected]>

commit 117942ca43e2e3c3d121faae530989931b7f67e1 upstream.

Fix a user triggerable leak on the system call failure path.

---
 drivers/infiniband/hw/mthca/mthca_provider.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)
drivers/infiniband/hw/mthca/mthca_provider.c +3 -2
index dd572d76866c2..e095873b381b6 100644
@@ -428,6 +428,8 @@ static int mthca_create_srq(struct ib_srq *ibsrq,
 
 	if (context && ib_copy_to_udata(udata, &srq->srqn, sizeof(__u32))) {
 		mthca_free_srq(to_mdev(ibsrq->device), srq);
+		mthca_unmap_user_db(to_mdev(ibsrq->device), &context->uar,
+				    context->db_tab, ucmd.db_index);
 		return -EFAULT;
 	}
 
@@ -436,6 +438,7 @@ static int mthca_create_srq(struct ib_srq *ibsrq,
 
 static int mthca_destroy_srq(struct ib_srq *srq, struct ib_udata *udata)
 {
+	mthca_free_srq(to_mdev(srq->device), to_msrq(srq));
 	if (udata) {
 		struct mthca_ucontext *context =
 			rdma_udata_to_drv_context(
@@ -446,8 +449,6 @@ static int mthca_destroy_srq(struct ib_srq *srq, struct ib_udata *udata)
 		mthca_unmap_user_db(to_mdev(srq->device), &context->uar,
 				    context->db_tab, to_msrq(srq)->db_index);
 	}
-
-	mthca_free_srq(to_mdev(srq->device), to_msrq(srq));
 	return 0;
 }
 
Signature · 1 line
2.51.0
author maintainer
#176 lore raw

PATCH 170/314 RDMA/irdma: Fix kernel stack leak in irdma_create_user_ah()

In reply to Sasha Levin

From: Jason Gunthorpe <[email protected]>

commit 74586c6da9ea222a61c98394f2fc0a604748438c upstream.

struct irdma_create_ah_resp {  // 8 bytes, no padding
    __u32 ah_id;               // offset 0 - SET (uresp.ah_id = ah->sc_ah.ah_info.ah_idx)
    __u8  rsvd[4];             // offset 4 - NEVER SET <- LEAK

};

rsvd[4]: 4 bytes of stack memory leaked unconditionally. Only ah_id is assigned before ib_respond_udata().

The reserved members of the structure were not zeroed.

Fixes b48c24c2d710 ("RDMA/irdma: Implement device supported verb APIs")
---
 drivers/infiniband/hw/irdma/verbs.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/infiniband/hw/irdma/verbs.c +1 -1
index b8655504da290..5d027c04dba6f 100644
@@ -5202,7 +5202,7 @@ static int irdma_create_user_ah(struct ib_ah *ibah,
 #define IRDMA_CREATE_AH_MIN_RESP_LEN offsetofend(struct irdma_create_ah_resp, rsvd)
 	struct irdma_ah *ah = container_of(ibah, struct irdma_ah, ibah);
 	struct irdma_device *iwdev = to_iwdev(ibah->pd->device);
-	struct irdma_create_ah_resp uresp;
+	struct irdma_create_ah_resp uresp = {};
 	struct irdma_ah *parent_ah;
 	int err;
 
Signature · 1 line
2.51.0
author maintainer
#177 lore raw

PATCH 171/314 RDMA/ionic: Fix kernel stack leak in ionic_create_cq()

In reply to Sasha Levin

From: Jason Gunthorpe <[email protected]>

commit faa72102b178c7ae6c6afea23879e7c84fc59b4e upstream.

struct ionic_cq_resp resp {

    __u32 cqid[2];         // offset 0 - PARTIALLY SET (see below)
    __u8  udma_mask;       // offset 8 - SET (resp.udma_mask = vcq->udma_mask)
    __u8  rsvd[7];         // offset 9 - NEVER SET <- LEAK

};

rsvd[7]: 7 bytes of stack memory leaked unconditionally.

cqid[2]: The loop at line 1256 iterates over udma_idx but skips indices where !(vcq->udma_mask & BIT(udma_idx)). The array has 2 entries but udma_count could be 1, meaning cqid[1] might never be written via ionic_create_cq_common(). If udma_mask only has bit 0 set, cqid[1] (4 bytes) is also leaked. So potentially 11 bytes leaked.

---
 drivers/infiniband/hw/ionic/ionic_controlpath.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/infiniband/hw/ionic/ionic_controlpath.c +1 -1
index ea12d9b8e125f..83573721af2c0 100644
@@ -1218,7 +1218,7 @@ int ionic_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
 		rdma_udata_to_drv_context(udata, struct ionic_ctx, ibctx);
 	struct ionic_vcq *vcq = to_ionic_vcq(ibcq);
 	struct ionic_tbl_buf buf = {};
-	struct ionic_cq_resp resp;
+	struct ionic_cq_resp resp = {};
 	struct ionic_cq_req req;
 	int udma_idx = 0, rc;
 
Signature · 1 line
2.51.0
author maintainer
#178 lore raw

PATCH 172/314 cpufreq: intel_pstate: Fix crash during turbo disable

In reply to Sasha Levin

From: Srinivas Pandruvada <[email protected]>

commit 6b050482ec40569429d963ac52afa878691b04c9 upstream.

When the system is booted with kernel command line argument "nosmt" or "maxcpus" to limit the number of CPUs, disabling turbo via:

echo 1 > /sys/devices/system/cpu/intel_pstate/no_turbo

results in a crash:

PF: supervisor read access in kernel mode
PF: error_code(0x0000) - not-present page
PGD 0 P4D 0

 Oops: Oops: 0000 [#1] SMP PTI
 ...
 RIP: 0010:store_no_turbo+0x100/0x1f0
 ...

This occurs because for_each_possible_cpu() returns CPUs even if they are not online. For those CPUs, all_cpu_data[] will be NULL. Since commit 973207ae3d7c ("cpufreq: intel_pstate: Rearrange max frequency updates handling code"), all_cpu_data[] is dereferenced even for CPUs which are not online, causing the NULL pointer dereference.

To fix that, pass CPU number to intel_pstate_update_max_freq() and use all_cpu_data[] for those CPUs for which there is a valid cpufreq policy.

Fixes 973207ae3d7c ("cpufreq: intel_pstate: Rearrange max frequency updates handling code")
Cc 6.16+ <[email protected]> # 6.16+
---
 drivers/cpufreq/intel_pstate.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)
drivers/cpufreq/intel_pstate.c +5 -5
index 38333f7da40db..00b87f8ee70bc 100644
@@ -1467,13 +1467,13 @@ static void __intel_pstate_update_max_freq(struct cpufreq_policy *policy,
 	refresh_frequency_limits(policy);
 }
 
-static bool intel_pstate_update_max_freq(struct cpudata *cpudata)
+static bool intel_pstate_update_max_freq(int cpu)
 {
-	struct cpufreq_policy *policy __free(put_cpufreq_policy) = cpufreq_cpu_get(cpudata->cpu);
+	struct cpufreq_policy *policy __free(put_cpufreq_policy) = cpufreq_cpu_get(cpu);
 	if (!policy)
 		return false;
 
-	__intel_pstate_update_max_freq(policy, cpudata);
+	__intel_pstate_update_max_freq(policy, all_cpu_data[cpu]);
 
 	return true;
 }
@@ -1492,7 +1492,7 @@ static void intel_pstate_update_limits_for_all(void)
 	int cpu;
 
 	for_each_possible_cpu(cpu)
-		intel_pstate_update_max_freq(all_cpu_data[cpu]);
+		intel_pstate_update_max_freq(cpu);
 
 	mutex_lock(&hybrid_capacity_lock);
 
@@ -1932,7 +1932,7 @@ static void intel_pstate_notify_work(struct work_struct *work)
 	struct cpudata *cpudata =
 		container_of(to_delayed_work(work), struct cpudata, hwp_notify_work);
 
-	if (intel_pstate_update_max_freq(cpudata)) {
+	if (intel_pstate_update_max_freq(cpudata->cpu)) {
 		/*
 		 * The driver will not be unregistered while this function is
 		 * running, so update the capacity without acquiring the driver
Signature · 1 line
2.51.0
author maintainer
#179 lore raw

PATCH 173/314 arm64: gcs: Do not set PTE_SHARED on GCS mappings if FEAT_LPA2 is enabled

In reply to Sasha Levin

From: Catalin Marinas <[email protected]>

commit 8a85b3131225a8c8143ba2ae29c0eef8c1f9117f upstream.

When FEAT_LPA2 is enabled, bits 8-9 of the PTE replace the shareability attribute with bits 50-51 of the output address. The _PAGE_GCS{,_RO} definitions include the PTE_SHARED bits as 0b11 (this matches the other _PAGE_* definitions) but using this macro directly leads to the following panic when enabling GCS on a system/model with LPA2:

  Unable to handle kernel paging request at virtual address fffff1ffc32d8008
  Mem abort info:
    ESR = 0x0000000096000004
    EC = 0x25: DABT (current EL), IL = 32 bits
    SET = 0, FnV = 0
    EA = 0, S1PTW = 0
    FSC = 0x04: level 0 translation fault
  Data abort info:
    ISV = 0, ISS = 0x00000004, ISS2 = 0x00000000
    CM = 0, WnR = 0, TnD = 0, TagAccess = 0
    GCS = 0, Overlay = 0, DirtyBit = 0, Xs = 0
  swapper pgtable: 4k pages, 52-bit VAs, pgdp=0000000060f4d000
  [fffff1ffc32d8008] pgd=100000006184b003, p4d=0000000000000000
  Internal error: Oops: 0000000096000004 [#1]  SMP
  CPU: 0 UID: 0 PID: 513 Comm: gcs_write_fault Tainted: G   M                7.0.0-rc1 #1 PREEMPT
  Tainted: [M]=MACHINE_CHECK
  Hardware name: QEMU QEMU Virtual Machine, BIOS 2025.02-8+deb13u1 11/08/2025
  pstate: 03402005 (nzcv daif +PAN -UAO +TCO +DIT -SSBS BTYPE=--)
  pc : zap_huge_pmd+0x168/0x468
  lr : zap_huge_pmd+0x2c/0x468
  sp : ffff800080beb660
  x29: ffff800080beb660 x28: fff00000c2058180 x27: ffff800080beb898
  x26: fff00000c2058180 x25: ffff800080beb820 x24: 00c800010b600f41
  x23: ffffc1ffc30af1a8 x22: fff00000c2058180 x21: 0000ffff8dc00000
  x20: fff00000c2bc6370 x19: ffff800080beb898 x18: ffff800080bebb60
  x17: 0000000000000000 x16: 0000000000000000 x15: 0000000000000007
  x14: 000000000000000a x13: 0000aaaacbbbffff x12: 0000000000000000
  x11: 0000ffff8ddfffff x10: 00000000000001fe x9 : 0000ffff8ddfffff
  x8 : 0000ffff8de00000 x7 : 0000ffff8da00000 x6 : fff00000c2bc6370
  x5 : 0000ffff8da00000 x4 : 000000010b600000 x3 : ffffc1ffc0000000
  x2 : fff00000c2058180 x1 : fffff1ffc32d8000 x0 : 000000c00010b600
  Call trace:
   zap_huge_pmd+0x168/0x468 (P)
   unmap_page_range+0xd70/0x1560
   unmap_single_vma+0x48/0x80
   unmap_vmas+0x90/0x180
   unmap_region+0x88/0xe4
   vms_complete_munmap_vmas+0xf8/0x1e0
   do_vmi_align_munmap+0x158/0x180
   do_vmi_munmap+0xac/0x160
   __vm_munmap+0xb0/0x138
   vm_munmap+0x14/0x20
   gcs_free+0x70/0x80
   mm_release+0x1c/0xc8
   exit_mm_release+0x28/0x38
   do_exit+0x190/0x8ec
   do_group_exit+0x34/0x90
   get_signal+0x794/0x858
   arch_do_signal_or_restart+0x11c/0x3e0
   exit_to_user_mode_loop+0x10c/0x17c
   el0_da+0x8c/0x9c
   el0t_64_sync_handler+0xd0/0xf0
   el0t_64_sync+0x198/0x19c
  Code: aa1603e2 d34cfc00 cb813001 8b011861 (f9400420)

Similarly to how the kernel handles protection_map[], use a gcs_page_prot variable to store the protection bits and clear PTE_SHARED if LPA2 is enabled.

Also remove the unused PAGE_GCS{,_RO} macros.

Fixes 6497b66ba694 ("arm64/mm: Map pages for guarded control stack")
Cc Mark Brown <[email protected]>
Cc Will Deacon <[email protected]>
---
 arch/arm64/include/asm/pgtable-prot.h | 3 ---
 arch/arm64/mm/mmap.c                  | 8 ++++++--
 2 files changed, 6 insertions(+), 5 deletions(-)
arch/arm64/include/asm/pgtable-prot.h +0 -3
index 85dceb1c66f45..a64a26aaceba4 100644
@@ -164,9 +164,6 @@ static inline bool __pure lpa2_is_enabled(void)
 #define _PAGE_GCS	(_PAGE_DEFAULT | PTE_NG | PTE_UXN | PTE_WRITE | PTE_USER)
 #define _PAGE_GCS_RO	(_PAGE_DEFAULT | PTE_NG | PTE_UXN | PTE_USER)
 
-#define PAGE_GCS	__pgprot(_PAGE_GCS)
-#define PAGE_GCS_RO	__pgprot(_PAGE_GCS_RO)
-
 #define PIE_E0	( \
 	PIRx_ELx_PERM_PREP(pte_pi_index(_PAGE_GCS),           PIE_GCS)  | \
 	PIRx_ELx_PERM_PREP(pte_pi_index(_PAGE_GCS_RO),        PIE_R)   | \
arch/arm64/mm/mmap.c +6 -2
index 08ee177432c2f..75f343009b4b1 100644
@@ -34,6 +34,8 @@ static pgprot_t protection_map[16] __ro_after_init = {
 	[VM_SHARED | VM_EXEC | VM_WRITE | VM_READ]	= PAGE_SHARED_EXEC
 };
 
+static ptdesc_t gcs_page_prot __ro_after_init = _PAGE_GCS_RO;
+
 /*
  * You really shouldn't be using read() or write() on /dev/mem.  This might go
  * away in the future.
@@ -73,9 +75,11 @@ static int __init adjust_protection_map(void)
 		protection_map[VM_EXEC | VM_SHARED] = PAGE_EXECONLY;
 	}
 
-	if (lpa2_is_enabled())
+	if (lpa2_is_enabled()) {
 		for (int i = 0; i < ARRAY_SIZE(protection_map); i++)
 			pgprot_val(protection_map[i]) &= ~PTE_SHARED;
+		gcs_page_prot &= ~PTE_SHARED;
+	}
 
 	return 0;
 }
@@ -87,7 +91,7 @@ pgprot_t vm_get_page_prot(vm_flags_t vm_flags)
 
 	/* Short circuit GCS to avoid bloating the table. */
 	if (system_supports_gcs() && (vm_flags & VM_SHADOW_STACK)) {
-		prot = _PAGE_GCS_RO;
+		prot = gcs_page_prot;
 	} else {
 		prot = pgprot_val(protection_map[vm_flags &
 				   (VM_READ|VM_WRITE|VM_EXEC|VM_SHARED)]);
Signature · 1 line
2.51.0
author maintainer
#180 lore raw

PATCH 174/314 net/sched: ets: fix divide by zero in the offload path

In reply to Sasha Levin

From: Davide Caratti <[email protected]>

commit e35626f610f3d2b7953ccddf6a77453da22b3a9e upstream.

Offloading ETS requires computing each class' WRR weight: this is done by averaging over the sums of quanta as 'q_sum' and 'q_psum'. Using unsigned int, the same integer size as the individual DRR quanta, can overflow and even cause division by zero, like it happened in the following splat:

 Oops: divide error: 0000 [#1] SMP PTI
 CPU: 13 UID: 0 PID: 487 Comm: tc Tainted: G            E       6.19.0-virtme #45 PREEMPT(full)
 Tainted: [E]=UNSIGNED_MODULE
 Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011
 RIP: 0010:ets_offload_change+0x11f/0x290 [sch_ets]
 Code: e4 45 31 ff eb 03 41 89 c7 41 89 cb 89 ce 83 f9 0f 0f 87 b7 00 00 00 45 8b 08 31 c0 45 01 cc 45 85 c9 74 09 41 6b c4 64 31 d2 <41> f7 f2 89 c2 44 29 fa 45 89 df 41 83 fb 0f 0f 87 c7 00 00 00 44
 RSP: 0018:ffffd0a180d77588 EFLAGS: 00010246
 RAX: 00000000ffffff38 RBX: ffff8d3d482ca000 RCX: 0000000000000000
 RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffffd0a180d77660
 RBP: ffffd0a180d77690 R08: ffff8d3d482ca2d8 R09: 00000000fffffffe
 R10: 0000000000000000 R11: 0000000000000000 R12: 00000000fffffffe
 R13: ffff8d3d472f2000 R14: 0000000000000003 R15: 0000000000000000
 FS:  00007f440b6c2740(0000) GS:ffff8d3dc9803000(0000) knlGS:0000000000000000
 CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
 CR2: 000000003cdd2000 CR3: 0000000007b58002 CR4: 0000000000172ef0
 Call Trace:
  <TASK>
  ets_qdisc_change+0x870/0xf40 [sch_ets]
  qdisc_create+0x12b/0x540
  tc_modify_qdisc+0x6d7/0xbd0
  rtnetlink_rcv_msg+0x168/0x6b0
  netlink_rcv_skb+0x5c/0x110
  netlink_unicast+0x1d6/0x2b0
  netlink_sendmsg+0x22e/0x470
  ____sys_sendmsg+0x38a/0x3c0
  ___sys_sendmsg+0x99/0xe0
  __sys_sendmsg+0x8a/0xf0
  do_syscall_64+0x111/0xf80
  entry_SYSCALL_64_after_hwframe+0x77/0x7f
 RIP: 0033:0x7f440b81c77e
 Code: 4d 89 d8 e8 d4 bc 00 00 4c 8b 5d f8 41 8b 93 08 03 00 00 59 5e 48 83 f8 fc 74 11 c9 c3 0f 1f 80 00 00 00 00 48 8b 45 10 0f 05 <c9> c3 83 e2 39 83 fa 08 75 e7 e8 13 ff ff ff 0f 1f 00 f3 0f 1e fa
 RSP: 002b:00007fff951e4c10 EFLAGS: 00000202 ORIG_RAX: 000000000000002e
 RAX: ffffffffffffffda RBX: 0000000000481820 RCX: 00007f440b81c77e
 RDX: 0000000000000000 RSI: 00007fff951e4cd0 RDI: 0000000000000003
 RBP: 00007fff951e4c20 R08: 0000000000000000 R09: 0000000000000000
 R10: 0000000000000000 R11: 0000000000000202 R12: 00007fff951f4fa8
 R13: 00000000699ddede R14: 00007f440bb01000 R15: 0000000000486980
  </TASK>
 Modules linked in: sch_ets(E) netdevsim(E)
 ---[ end trace 0000000000000000 ]---
 RIP: 0010:ets_offload_change+0x11f/0x290 [sch_ets]
 Code: e4 45 31 ff eb 03 41 89 c7 41 89 cb 89 ce 83 f9 0f 0f 87 b7 00 00 00 45 8b 08 31 c0 45 01 cc 45 85 c9 74 09 41 6b c4 64 31 d2 <41> f7 f2 89 c2 44 29 fa 45 89 df 41 83 fb 0f 0f 87 c7 00 00 00 44
 RSP: 0018:ffffd0a180d77588 EFLAGS: 00010246
 RAX: 00000000ffffff38 RBX: ffff8d3d482ca000 RCX: 0000000000000000
 RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffffd0a180d77660
 RBP: ffffd0a180d77690 R08: ffff8d3d482ca2d8 R09: 00000000fffffffe
 R10: 0000000000000000 R11: 0000000000000000 R12: 00000000fffffffe
 R13: ffff8d3d472f2000 R14: 0000000000000003 R15: 0000000000000000
 FS:  00007f440b6c2740(0000) GS:ffff8d3dc9803000(0000) knlGS:0000000000000000
 CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
 CR2: 000000003cdd2000 CR3: 0000000007b58002 CR4: 0000000000172ef0
 Kernel panic - not syncing: Fatal exception
 Kernel Offset: 0x30000000 from 0xffffffff81000000 (relocation range: 0xffffffff80000000-0xffffffffbfffffff)
 ---[ end Kernel panic - not syncing: Fatal exception ]---

Fix this using 64-bit integers for 'q_sum' and 'q_psum'.

---
 net/sched/sch_ets.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)
net/sched/sch_ets.c +8 -4
index 306e046276d46..a4b07b661b775 100644
@@ -115,12 +115,12 @@ static void ets_offload_change(struct Qdisc *sch)
 	struct ets_sched *q = qdisc_priv(sch);
 	struct tc_ets_qopt_offload qopt;
 	unsigned int w_psum_prev = 0;
-	unsigned int q_psum = 0;
-	unsigned int q_sum = 0;
 	unsigned int quantum;
 	unsigned int w_psum;
 	unsigned int weight;
 	unsigned int i;
+	u64 q_psum = 0;
+	u64 q_sum = 0;
 
 	if (!tc_can_offload(dev) || !dev->netdev_ops->ndo_setup_tc)
 		return;
@@ -138,8 +138,12 @@ static void ets_offload_change(struct Qdisc *sch)
 
 	for (i = 0; i < q->nbands; i++) {
 		quantum = q->classes[i].quantum;
-		q_psum += quantum;
-		w_psum = quantum ? q_psum * 100 / q_sum : 0;
+		if (quantum) {
+			q_psum += quantum;
+			w_psum = div64_u64(q_psum * 100, q_sum);
+		} else {
+			w_psum = 0;
+		}
 		weight = w_psum - w_psum_prev;
 		w_psum_prev = w_psum;
 
Signature · 1 line
2.51.0
author maintainer
#181 lore raw

PATCH 175/314 nfsd: Fix cred ref leak in nfsd_nl_threads_set_doit().

In reply to Sasha Levin

From: Kuniyuki Iwashima <[email protected]>

commit 1cb968a2013ffa8112d52ebe605009ea1c6a582c upstream.

syzbot reported memory leak of struct cred. [0]

nfsd_nl_threads_set_doit() passes get_current_cred() to nfsd_svc(), but put_cred() is not called after that.

The cred is finally passed down to _svc_xprt_create(), which calls get_cred() with the cred for struct svc_xprt.

The ownership of the refcount by get_current_cred() is not transferred to anywhere and is just leaked.

nfsd_svc() is also called from write_threads(), but it does not bump file->f_cred there.

nfsd_nl_threads_set_doit() is called from sendmsg() and current->cred does not go away.

Let's use current_cred() in nfsd_nl_threads_set_doit().

[0]:

BUG: memory leak
unreferenced object 0xffff888108b89480 (size 184):
  comm "syz-executor", pid 5994, jiffies 4294943386
  hex dump (first 32 bytes):
    01 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
    00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
  backtrace (crc 369454a7):
    kmemleak_alloc_recursive include/linux/kmemleak.h:44 [inline]
    slab_post_alloc_hook mm/slub.c:4958 [inline]
    slab_alloc_node mm/slub.c:5263 [inline]
    kmem_cache_alloc_noprof+0x412/0x580 mm/slub.c:5270
    prepare_creds+0x22/0x600 kernel/cred.c:185
    copy_creds+0x44/0x290 kernel/cred.c:286
    copy_process+0x7a7/0x2870 kernel/fork.c:2086
    kernel_clone+0xac/0x6e0 kernel/fork.c:2651
    __do_sys_clone+0x7f/0xb0 kernel/fork.c:2792
    do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline]
    do_syscall_64+0xa4/0xf80 arch/x86/entry/syscall_64.c:94
    entry_SYSCALL_64_after_hwframe+0x77/0x7f
---
 fs/nfsd/nfsctl.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
fs/nfsd/nfsctl.c +1 -1
index 8cbfb9dc3abb7..5b00b7a863b94 100644
@@ -1642,7 +1642,7 @@ int nfsd_nl_threads_set_doit(struct sk_buff *skb, struct genl_info *info)
 			scope = nla_data(attr);
 	}
 
-	ret = nfsd_svc(nrpools, nthreads, net, get_current_cred(), scope);
+	ret = nfsd_svc(nrpools, nthreads, net, current_cred(), scope);
 	if (ret > 0)
 		ret = 0;
 out_unlock:
Signature · 1 line
2.51.0
author maintainer
#182 lore raw

PATCH 176/314 tracing: Fix WARN_ON in tracing_buffers_mmap_close

In reply to Sasha Levin

From: Qing Wang <[email protected]>

commit e39bb9e02b68942f8e9359d2a3efe7d37ae6be0e upstream.

When a process forks, the child process copies the parent's VMAs but the user_mapped reference count is not incremented. As a result, when both the parent and child processes exit, tracing_buffers_mmap_close() is called twice. On the second call, user_mapped is already 0, causing the function to return -ENODEV and triggering a WARN_ON.

Normally, this isn't an issue as the memory is mapped with VM_DONTCOPY set. But this is only a hint, and the application can call madvise(MADVISE_DOFORK) which resets the VM_DONTCOPY flag. When the application does that, it can trigger this issue on fork.

Fix it by incrementing the user_mapped reference count without re-mapping the pages in the VMA's open callback.

Cc Masami Hiramatsu <[email protected]>
Cc Mathieu Desnoyers <[email protected]>
Cc Vincent Donnefort <[email protected]>
Cc Lorenzo Stoakes <[email protected]>
Fixes cf9f0f7c4c5bb ("tracing: Allow user-space mapping of the ring-buffer")
Reported-by [email protected]
---
 include/linux/ring_buffer.h |  1 +
 kernel/trace/ring_buffer.c  | 21 +++++++++++++++++++++
 kernel/trace/trace.c        | 13 +++++++++++++
 3 files changed, 35 insertions(+)
include/linux/ring_buffer.h +1 -0
index 876358cfe1b12..d862fa610270b 100644
@@ -248,6 +248,7 @@ int trace_rb_cpu_prepare(unsigned int cpu, struct hlist_node *node);
 
 int ring_buffer_map(struct trace_buffer *buffer, int cpu,
 		    struct vm_area_struct *vma);
+void ring_buffer_map_dup(struct trace_buffer *buffer, int cpu);
 int ring_buffer_unmap(struct trace_buffer *buffer, int cpu);
 int ring_buffer_map_get_reader(struct trace_buffer *buffer, int cpu);
 #endif /* _LINUX_RING_BUFFER_H */
kernel/trace/ring_buffer.c +21 -0
index 54d70bd0a3cb9..98ca4beabf023 100644
@@ -7283,6 +7283,27 @@ int ring_buffer_map(struct trace_buffer *buffer, int cpu,
 	return err;
 }
 
+/*
+ * This is called when a VMA is duplicated (e.g., on fork()) to increment
+ * the user_mapped counter without remapping pages.
+ */
+void ring_buffer_map_dup(struct trace_buffer *buffer, int cpu)
+{
+	struct ring_buffer_per_cpu *cpu_buffer;
+
+	if (WARN_ON(!cpumask_test_cpu(cpu, buffer->cpumask)))
+		return;
+
+	cpu_buffer = buffer->buffers[cpu];
+
+	guard(mutex)(&cpu_buffer->mapping_lock);
+
+	if (cpu_buffer->user_mapped)
+		__rb_inc_dec_mapped(cpu_buffer, true);
+	else
+		WARN(1, "Unexpected buffer stat, it should be mapped");
+}
+
 int ring_buffer_unmap(struct trace_buffer *buffer, int cpu)
 {
 	struct ring_buffer_per_cpu *cpu_buffer;
kernel/trace/trace.c +13 -0
index d2eabc162205c..38fab063c3687 100644
@@ -8784,6 +8784,18 @@ static inline int get_snapshot_map(struct trace_array *tr) { return 0; }
 static inline void put_snapshot_map(struct trace_array *tr) { }
 #endif
 
+/*
+ * This is called when a VMA is duplicated (e.g., on fork()) to increment
+ * the user_mapped counter without remapping pages.
+ */
+static void tracing_buffers_mmap_open(struct vm_area_struct *vma)
+{
+	struct ftrace_buffer_info *info = vma->vm_file->private_data;
+	struct trace_iterator *iter = &info->iter;
+
+	ring_buffer_map_dup(iter->array_buffer->buffer, iter->cpu_file);
+}
+
 static void tracing_buffers_mmap_close(struct vm_area_struct *vma)
 {
 	struct ftrace_buffer_info *info = vma->vm_file->private_data;
@@ -8803,6 +8815,7 @@ static int tracing_buffers_may_split(struct vm_area_struct *vma, unsigned long a
 }
 
 static const struct vm_operations_struct tracing_buffers_vmops = {
+	.open		= tracing_buffers_mmap_open,
 	.close		= tracing_buffers_mmap_close,
 	.may_split      = tracing_buffers_may_split,
 };
Signature · 1 line
2.51.0
author maintainer
#183 lore raw

PATCH 177/314 scsi: target: Fix recursive locking in __configfs_open_file()

In reply to Sasha Levin

From: Prithvi Tambewagh <[email protected]>

commit 14d4ac19d1895397532eec407433c5d74d9da53b upstream.

In flush_write_buffer, &p->frag_sem is acquired and then the loaded store function is called, which, here, is target_core_item_dbroot_store(). This function called filp_open(), following which these functions were called (in reverse order), according to the call trace:

down_read
__configfs_open_file
do_dentry_open
vfs_open
do_open
path_openat
do_filp_open
file_open_name
filp_open
target_core_item_dbroot_store
flush_write_buffer
configfs_write_iter

target_core_item_dbroot_store() tries to validate the new file path by trying to open the file path provided to it; however, in this case, the bug report shows:

db_root: not a directory: /sys/kernel/config/target/dbroot

indicating that the same configfs file was tried to be opened, on which it is currently working on. Thus, it is trying to acquire frag_sem semaphore of the same file of which it already holds the semaphore obtained in flush_write_buffer(), leading to acquiring the semaphore in a nested manner and a possibility of recursive locking.

Fix this by modifying target_core_item_dbroot_store() to use kern_path() instead of filp_open() to avoid opening the file using filesystem-specific function __configfs_open_file(), and further modifying it to make this fix compatible.

---
 drivers/target/target_core_configfs.c | 15 ++++++---------
 1 file changed, 6 insertions(+), 9 deletions(-)
drivers/target/target_core_configfs.c +6 -9
index 1bd28482e7cb3..a2bd2e81d2c68 100644
@@ -108,8 +108,8 @@ static ssize_t target_core_item_dbroot_store(struct config_item *item,
 					const char *page, size_t count)
 {
 	ssize_t read_bytes;
-	struct file *fp;
 	ssize_t r = -EINVAL;
+	struct path path = {};
 
 	mutex_lock(&target_devices_lock);
 	if (target_devices) {
@@ -131,17 +131,14 @@ static ssize_t target_core_item_dbroot_store(struct config_item *item,
 		db_root_stage[read_bytes - 1] = '\0';
 
 	/* validate new db root before accepting it */
-	fp = filp_open(db_root_stage, O_RDONLY, 0);
-	if (IS_ERR(fp)) {
+	r = kern_path(db_root_stage, LOOKUP_FOLLOW | LOOKUP_DIRECTORY, &path);
+	if (r) {
 		pr_err("db_root: cannot open: %s\n", db_root_stage);
+		if (r == -ENOTDIR)
+			pr_err("db_root: not a directory: %s\n", db_root_stage);
 		goto unlock;
 	}
-	if (!S_ISDIR(file_inode(fp)->i_mode)) {
-		filp_close(fp, NULL);
-		pr_err("db_root: not a directory: %s\n", db_root_stage);
-		goto unlock;
-	}
-	filp_close(fp, NULL);
+	path_put(&path);
 
 	strscpy(db_root, db_root_stage);
 	pr_debug("Target_Core_ConfigFS: db_root set to %s\n", db_root);
Signature · 1 line
2.51.0
author maintainer
#184 lore raw

PATCH 178/314 mm: thp: deny THP for files on anonymous inodes

In reply to Sasha Levin

From: Deepanshu Kartikey <[email protected]>

commit dd085fe9a8ebfc5d10314c60452db38d2b75e609 upstream.

file_thp_enabled() incorrectly allows THP for files on anonymous inodes (e.g. guest_memfd and secretmem). These files are created via alloc_file_pseudo(), which does not call get_write_access() and leaves inode->i_writecount at 0. Combined with S_ISREG(inode->i_mode) being true, they appear as read-only regular files when CONFIG_READ_ONLY_THP_FOR_FS is enabled, making them eligible for THP collapse.

Anonymous inodes can never pass the inode_is_open_for_write() check since their i_writecount is never incremented through the normal VFS open path. The right thing to do is to exclude them from THP eligibility altogether, since CONFIG_READ_ONLY_THP_FOR_FS was designed for real filesystem files (e.g. shared libraries), not for pseudo-filesystem inodes.

For guest_memfd, this allows khugepaged and MADV_COLLAPSE to create large folios in the page cache via the collapse path, but the guest_memfd fault handler does not support large folios. This triggers WARN_ON_ONCE(folio_test_large(folio)) in kvm_gmem_fault_user_mapping().

For secretmem, collapse_file() tries to copy page contents through the direct map, but secretmem pages are removed from the direct map. This can result in a kernel crash:

    BUG: unable to handle page fault for address: ffff88810284d000
    RIP: 0010:memcpy_orig+0x16/0x130
    Call Trace:
     collapse_file
     hpage_collapse_scan_file
     madvise_collapse

Secretmem is not affected by the crash on upstream as the memory failure recovery handles the failed copy gracefully, but it still triggers confusing false memory failure reports:

Memory failure: 0x106d96f: recovery action for clean unevictable LRU page: Recovered

Check IS_ANON_FILE(inode) in file_thp_enabled() to deny THP for all anonymous inode files.

---
 mm/huge_memory.c | 3 +++
 1 file changed, 3 insertions(+)
mm/huge_memory.c +3 -0
index 8ad170b9855a5..35ec12c4d7766 100644
@@ -94,6 +94,9 @@ static inline bool file_thp_enabled(struct vm_area_struct *vma)
 
 	inode = file_inode(vma->vm_file);
 
+	if (IS_ANON_FILE(inode))
+		return false;
+
 	return !inode_is_open_for_write(inode) && S_ISREG(inode->i_mode);
 }
 
Signature · 1 line
2.51.0
author maintainer
#185 lore raw

PATCH 179/314 Squashfs: check metadata block offset is within range

In reply to Sasha Levin

From: Phillip Lougher <[email protected]>

commit fdb24a820a5832ec4532273282cbd4f22c291a0d upstream.

Syzkaller reports a "general protection fault in squashfs_copy_data"

This is ultimately caused by a corrupted index look-up table, which produces a negative metadata block offset.

This is subsequently passed to squashfs_copy_data (via squashfs_read_metadata) where the negative offset causes an out of bounds access.

The fix is to check that the offset is within range in squashfs_read_metadata. This will trap this and other cases.

---
 fs/squashfs/cache.c | 3 +++
 1 file changed, 3 insertions(+)
fs/squashfs/cache.c +3 -0
index 181260e72680c..92fb857d2c761 100644
@@ -344,6 +344,9 @@ int squashfs_read_metadata(struct super_block *sb, void *buffer,
 	if (unlikely(length < 0))
 		return -EIO;
 
+	if (unlikely(*offset < 0 || *offset >= SQUASHFS_METADATA_SIZE))
+		return -EIO;
+
 	while (length) {
 		entry = squashfs_cache_get(sb, msblk->block_cache, *block, 0);
 		if (entry->error) {
Signature · 1 line
2.51.0
author maintainer
#186 lore raw

PATCH 180/314 drbd: fix "LOGIC BUG" in drbd_al_begin_io_nonblock()

In reply to Sasha Levin

From: Lars Ellenberg <[email protected]>

commit ab140365fb62c0bdab22b2f516aff563b2559e3b upstream.

Even though we check that we "should" be able to do lc_get_cumulative() while holding the device->al_lock spinlock, it may still fail, if some other code path decided to do lc_try_lock() with bad timing.

If that happened, we logged "LOGIC BUG for enr=...", but still did not return an error.

The rest of the code now assumed that this request has references for the relevant activity log extents.

The implcations are that during an active resync, mutual exclusivity of resync versus application IO is not guaranteed. And a potential crash at this point may not realizs that these extents could have been target of in-flight IO and would need to be resynced just in case.

Also, once the request completes, it will give up activity log references it does not even hold, which will trigger a BUG_ON(refcnt == 0) in lc_put().

Fix:

Do not crash the kernel for a condition that is harmless during normal
operation: also catch "e->refcnt == 0", not only "e == NULL" when being noisy about "al_complete_io() called on inactive extent %u\n".

And do not try to be smart and "guess" whether something will work, then be surprised when it does not.
Deal with the fact that it may or may not work. If it does not, remember a possible "partially in activity log" state (only possible for requests that cross extent boundaries), and return an error code from drbd_al_begin_io_nonblock().

A latter call for the same request will then resume from where we left off.

---
 drivers/block/drbd/drbd_actlog.c   | 53 +++++++++++++-----------------
 drivers/block/drbd/drbd_interval.h |  5 ++-
 2 files changed, 27 insertions(+), 31 deletions(-)
drivers/block/drbd/drbd_actlog.c +23 -30
index 742b2908ff686..b3dbf6c76e98f 100644
@@ -483,38 +483,20 @@ void drbd_al_begin_io(struct drbd_device *device, struct drbd_interval *i)
 
 int drbd_al_begin_io_nonblock(struct drbd_device *device, struct drbd_interval *i)
 {
-	struct lru_cache *al = device->act_log;
 	/* for bios crossing activity log extent boundaries,
 	 * we may need to activate two extents in one go */
 	unsigned first = i->sector >> (AL_EXTENT_SHIFT-9);
 	unsigned last = i->size == 0 ? first : (i->sector + (i->size >> 9) - 1) >> (AL_EXTENT_SHIFT-9);
-	unsigned nr_al_extents;
-	unsigned available_update_slots;
 	unsigned enr;
 
-	D_ASSERT(device, first <= last);
-
-	nr_al_extents = 1 + last - first; /* worst case: all touched extends are cold. */
-	available_update_slots = min(al->nr_elements - al->used,
-				al->max_pending_changes - al->pending_changes);
-
-	/* We want all necessary updates for a given request within the same transaction
-	 * We could first check how many updates are *actually* needed,
-	 * and use that instead of the worst-case nr_al_extents */
-	if (available_update_slots < nr_al_extents) {
-		/* Too many activity log extents are currently "hot".
-		 *
-		 * If we have accumulated pending changes already,
-		 * we made progress.
-		 *
-		 * If we cannot get even a single pending change through,
-		 * stop the fast path until we made some progress,
-		 * or requests to "cold" extents could be starved. */
-		if (!al->pending_changes)
-			__set_bit(__LC_STARVING, &device->act_log->flags);
-		return -ENOBUFS;
+	if (i->partially_in_al_next_enr) {
+		D_ASSERT(device, first < i->partially_in_al_next_enr);
+		D_ASSERT(device, last >= i->partially_in_al_next_enr);
+		first = i->partially_in_al_next_enr;
 	}
 
+	D_ASSERT(device, first <= last);
+
 	/* Is resync active in this area? */
 	for (enr = first; enr <= last; enr++) {
 		struct lc_element *tmp;
@@ -529,14 +511,21 @@ int drbd_al_begin_io_nonblock(struct drbd_device *device, struct drbd_interval *
 		}
 	}
 
-	/* Checkout the refcounts.
-	 * Given that we checked for available elements and update slots above,
-	 * this has to be successful. */
+	/* Try to checkout the refcounts. */
 	for (enr = first; enr <= last; enr++) {
 		struct lc_element *al_ext;
 		al_ext = lc_get_cumulative(device->act_log, enr);
-		if (!al_ext)
-			drbd_info(device, "LOGIC BUG for enr=%u\n", enr);
+
+		if (!al_ext) {
+			/* Did not work. We may have exhausted the possible
+			 * changes per transaction. Or raced with someone
+			 * "locking" it against changes.
+			 * Remember where to continue from.
+			 */
+			if (enr > first)
+				i->partially_in_al_next_enr = enr;
+			return -ENOBUFS;
+		}
 	}
 	return 0;
 }
@@ -556,7 +545,11 @@ void drbd_al_complete_io(struct drbd_device *device, struct drbd_interval *i)
 
 	for (enr = first; enr <= last; enr++) {
 		extent = lc_find(device->act_log, enr);
-		if (!extent) {
+		/* Yes, this masks a bug elsewhere.  However, during normal
+		 * operation this is harmless, so no need to crash the kernel
+		 * by the BUG_ON(refcount == 0) in lc_put().
+		 */
+		if (!extent || extent->refcnt == 0) {
 			drbd_err(device, "al_complete_io() called on inactive extent %u\n", enr);
 			continue;
 		}
drivers/block/drbd/drbd_interval.h +4 -1
index 366489b72fe97..5d3213b81eede 100644
@@ -8,12 +8,15 @@
 struct drbd_interval {
 	struct rb_node rb;
 	sector_t sector;		/* start sector of the interval */
-	unsigned int size;		/* size in bytes */
 	sector_t end;			/* highest interval end in subtree */
+	unsigned int size;		/* size in bytes */
 	unsigned int local:1		/* local or remote request? */;
 	unsigned int waiting:1;		/* someone is waiting for completion */
 	unsigned int completed:1;	/* this has been completed already;
 					 * ignore for conflict detection */
+
+	/* to resume a partially successful drbd_al_begin_io_nonblock(); */
+	unsigned int partially_in_al_next_enr;
 };
 
 static inline void drbd_clear_interval(struct drbd_interval *i)
Signature · 1 line
2.51.0
author maintainer
#187 lore raw

PATCH 181/314 drbd: fix null-pointer dereference on local read error

In reply to Sasha Levin

From: Christoph Böhmwalder <[email protected]>

commit 0d195d3b205ca90db30d70d09d7bb6909aac178f upstream.

In drbd_request_endio(), READ_COMPLETED_WITH_ERROR is passed to __req_mod() with a NULL peer_device:

  __req_mod(req, what, NULL, &m);

The READ_COMPLETED_WITH_ERROR handler then unconditionally passes this NULL peer_device to drbd_set_out_of_sync(), which dereferences it, causing a null-pointer dereference.

Fix this by obtaining the peer_device via first_peer_device(device), matching how drbd_req_destroy() handles the same situation.

---
 drivers/block/drbd/drbd_req.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)
drivers/block/drbd/drbd_req.c +2 -1
index d15826f6ee81d..70f75ef079457 100644
@@ -621,7 +621,8 @@ int __req_mod(struct drbd_request *req, enum drbd_req_event what,
 		break;
 
 	case READ_COMPLETED_WITH_ERROR:
-		drbd_set_out_of_sync(peer_device, req->i.sector, req->i.size);
+		drbd_set_out_of_sync(first_peer_device(device),
+				req->i.sector, req->i.size);
 		drbd_report_io_error(device, req);
 		__drbd_chk_io_error(device, DRBD_READ_ERROR);
 		fallthrough;
Signature · 1 line
2.51.0
author maintainer
#188 lore raw

PATCH 182/314 xfs: fix xfs_group release bug in xfs_dax_notify_dev_failure

In reply to Sasha Levin

From: "Darrick J. Wong" <[email protected]>

commit eb8550fb75a875657dc29e3925a40244ec6b6bd6 upstream.

Chris Mason reports that his AI tools noticed that we were using xfs_perag_put and xfs_group_put to release the group reference returned by xfs_group_next_range. However, the iterator function returns an object with an active refcount, which means that we must use the correct function to release the active refcount, which is _rele.

Cc <[email protected]> # v6.0
Fixes 6f643c57d57c56 ("xfs: implement ->notify_failure() for XFS")
---
 fs/xfs/xfs_notify_failure.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)
fs/xfs/xfs_notify_failure.c +2 -2
index b176728899420..0700a723f38e7 100644
@@ -293,7 +293,7 @@ xfs_dax_notify_dev_failure(
 
 			error = xfs_alloc_read_agf(pag, tp, 0, &agf_bp);
 			if (error) {
-				xfs_perag_put(pag);
+				xfs_perag_rele(pag);
 				break;
 			}
 
@@ -329,7 +329,7 @@ xfs_dax_notify_dev_failure(
 		if (rtg)
 			xfs_rtgroup_unlock(rtg, XFS_RTGLOCK_RMAP);
 		if (error) {
-			xfs_group_put(xg);
+			xfs_group_rele(xg);
 			break;
 		}
 	}
Signature · 1 line
2.51.0
author maintainer
#189 lore raw

PATCH 183/314 xfs: Fix error pointer dereference

In reply to Sasha Levin

From: Ethan Tidmore <[email protected]>

commit cddfa648f1ab99e30e91455be19cd5ade26338c2 upstream.

The function try_lookup_noperm() can return an error pointer and is not checked for one.

Add checks for error pointer in xrep_adoption_check_dcache() and xrep_adoption_zap_dcache().

Detected by Smatch:
fs/xfs/scrub/orphanage.c:449 xrep_adoption_check_dcache() error:
'd_child' dereferencing possible ERR_PTR()

fs/xfs/scrub/orphanage.c:485 xrep_adoption_zap_dcache() error:
'd_child' dereferencing possible ERR_PTR()

Fixes 73597e3e42b4 ("xfs: ensure dentry consistency when the orphanage adopts a file")
---
 fs/xfs/scrub/orphanage.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)
fs/xfs/scrub/orphanage.c +6 -1
index 9c12cb8442311..3c4f3b542c20f 100644
@@ -445,6 +445,11 @@ xrep_adoption_check_dcache(
 		return 0;
 
 	d_child = try_lookup_noperm(&qname, d_orphanage);
+	if (IS_ERR(d_child)) {
+		dput(d_orphanage);
+		return PTR_ERR(d_child);
+	}
+
 	if (d_child) {
 		trace_xrep_adoption_check_child(sc->mp, d_child);
 
@@ -482,7 +487,7 @@ xrep_adoption_zap_dcache(
 		return;
 
 	d_child = try_lookup_noperm(&qname, d_orphanage);
-	while (d_child != NULL) {
+	while (!IS_ERR_OR_NULL(d_child)) {
 		trace_xrep_adoption_invalidate_child(sc->mp, d_child);
 
 		ASSERT(d_is_negative(d_child));
Signature · 1 line
2.51.0
author maintainer
#190 lore raw

PATCH 184/314 smb: client: fix cifs_pick_channel when channels are equally loaded

In reply to Sasha Levin

From: Henrique Carvalho <[email protected]>

commit 663c28469d3274d6456f206a6671c91493d85ff1 upstream.

cifs_pick_channel uses (start % chan_count) when channels are equally loaded, but that can return a channel that failed the eligibility checks.

Drop the fallback and return the scan-selected channel instead. If none is eligible, keep the existing behavior of using the primary channel.

---
 fs/smb/client/transport.c | 21 ++++++++++-----------
 1 file changed, 10 insertions(+), 11 deletions(-)
fs/smb/client/transport.c +10 -11
index 915cedde5d664..2d7140767dc43 100644
@@ -806,16 +806,21 @@ cifs_cancelled_callback(struct mid_q_entry *mid)
 }
 
 /*
- * Return a channel (master if none) of @ses that can be used to send
- * regular requests.
+ * cifs_pick_channel - pick an eligible channel for network operations
  *
- * If we are currently binding a new channel (negprot/sess.setup),
- * return the new incomplete channel.
+ * @ses: session reference
+ *
+ * Select an eligible channel (not terminating and not marked as needing
+ * reconnect), preferring the least loaded one. If no eligible channel is
+ * found, fall back to the primary channel (index 0).
+ *
+ * Return: TCP_Server_Info pointer for the chosen channel, or NULL if @ses is
+ * NULL.
  */
 struct TCP_Server_Info *cifs_pick_channel(struct cifs_ses *ses)
 {
 	uint index = 0;
-	unsigned int min_in_flight = UINT_MAX, max_in_flight = 0;
+	unsigned int min_in_flight = UINT_MAX;
 	struct TCP_Server_Info *server = NULL;
 	int i, start, cur;
 
@@ -845,14 +850,8 @@ struct TCP_Server_Info *cifs_pick_channel(struct cifs_ses *ses)
 			min_in_flight = server->in_flight;
 			index = cur;
 		}
-		if (server->in_flight > max_in_flight)
-			max_in_flight = server->in_flight;
 	}
 
-	/* if all channels are equally loaded, fall back to round-robin */
-	if (min_in_flight == max_in_flight)
-		index = (uint)start % ses->chan_count;
-
 	server = ses->chans[index].server;
 	spin_unlock(&ses->chan_lock);
 
Signature · 1 line
2.51.0
author maintainer
#191 lore raw

PATCH 185/314 smb: client: fix broken multichannel with krb5+signing

In reply to Sasha Levin

From: Paulo Alcantara <[email protected]>

commit d9d1e319b39ea685ede59319002d567c159d23c3 upstream.

When mounting a share with 'multichannel,max_channels=n,sec=krb5i', the client was duplicating signing key for all secondary channels, thus making the server fail all commands sent from secondary channels due to bad signatures.

Every channel has its own signing key, so when establishing a new channel with krb5 auth, make sure to use the new session key as the derived key to generate channel's signing key in SMB2_auth_kerberos().

Repro:

$ mount.cifs //srv/share /mnt -o multichannel,max_channels=4,sec=krb5i
$ sleep 5
$ umount /mnt
$ dmesg
  ...
  CIFS: VFS: sign fail cmd 0x5 message id 0x2
  CIFS: VFS: \\srv SMB signature verification returned error = -13
  CIFS: VFS: sign fail cmd 0x5 message id 0x2
  CIFS: VFS: \\srv SMB signature verification returned error = -13
  CIFS: VFS: sign fail cmd 0x4 message id 0x2
  CIFS: VFS: \\srv SMB signature verification returned error = -13
---
 fs/smb/client/smb2pdu.c | 22 ++++++++++------------
 1 file changed, 10 insertions(+), 12 deletions(-)
fs/smb/client/smb2pdu.c +10 -12
index 1ef82408ecad6..58238e65c7edf 100644
@@ -1650,19 +1650,17 @@ SMB2_auth_kerberos(struct SMB2_sess_data *sess_data)
 	is_binding = (ses->ses_status == SES_GOOD);
 	spin_unlock(&ses->ses_lock);
 
-	/* keep session key if binding */
-	if (!is_binding) {
-		kfree_sensitive(ses->auth_key.response);
-		ses->auth_key.response = kmemdup(msg->data, msg->sesskey_len,
-						 GFP_KERNEL);
-		if (!ses->auth_key.response) {
-			cifs_dbg(VFS, "Kerberos can't allocate (%u bytes) memory\n",
-				 msg->sesskey_len);
-			rc = -ENOMEM;
-			goto out_put_spnego_key;
-		}
-		ses->auth_key.len = msg->sesskey_len;
+	kfree_sensitive(ses->auth_key.response);
+	ses->auth_key.response = kmemdup(msg->data,
+					 msg->sesskey_len,
+					 GFP_KERNEL);
+	if (!ses->auth_key.response) {
+		cifs_dbg(VFS, "%s: can't allocate (%u bytes) memory\n",
+			 __func__, msg->sesskey_len);
+		rc = -ENOMEM;
+		goto out_put_spnego_key;
 	}
+	ses->auth_key.len = msg->sesskey_len;
 
 	sess_data->iov[1].iov_base = msg->data + msg->sesskey_len;
 	sess_data->iov[1].iov_len = msg->secblob_len;
Signature · 1 line
2.51.0
author maintainer
#192 lore raw

PATCH 186/314 smb: client: Don't log plaintext credentials in cifs_set_cifscreds

In reply to Sasha Levin

From: Thorsten Blum <[email protected]>

commit 2f37dc436d4e61ff7ae0b0353cf91b8c10396e4d upstream.

When debug logging is enabled, cifs_set_cifscreds() logs the key payload and exposes the plaintext username and password. Remove the debug log to avoid exposing credentials.

Fixes 8a8798a5ff90 ("cifs: fetch credentials out of keyring for non-krb5 auth multiuser mounts")
---
 fs/smb/client/connect.c | 1 -
 1 file changed, 1 deletion(-)
fs/smb/client/connect.c +0 -1
index d96d23a8f4903..dd7f48f530979 100644
@@ -2235,7 +2235,6 @@ cifs_set_cifscreds(struct smb3_fs_context *ctx, struct cifs_ses *ses)
 	/* find first : in payload */
 	payload = upayload->data;
 	delim = strnchr(payload, upayload->datalen, ':');
-	cifs_dbg(FYI, "payload=%s\n", payload);
 	if (!delim) {
 		cifs_dbg(FYI, "Unable to find ':' in payload (datalen=%d)\n",
 			 upayload->datalen);
Signature · 1 line
2.51.0
author maintainer
#193 lore raw

PATCH 187/314 smb: client: fix oops due to uninitialised var in smb2_unlink()

In reply to Sasha Levin

From: Paulo Alcantara <[email protected]>

commit 048efe129a297256d3c2088cf8d79515ff5ec864 upstream.

If SMB2_open_init() or SMB2_close_init() fails (e.g. reconnect), the iovs set @rqst will be left uninitialised, hence calling SMB2_open_free(), SMB2_close_free() or smb2_set_related() on them will oops.

Fix this by initialising @close_iov and @open_iov before setting them in @rqst.

Fixes 1cf9f2a6a544 ("smb: client: handle unlink(2) of files open by different clients")
Cc David Howells <[email protected]>
---
 fs/smb/client/smb2inode.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)
fs/smb/client/smb2inode.c +3 -1
index 69cb81fa0d3ab..5c25f25aa2efb 100644
@@ -1205,6 +1205,7 @@ smb2_unlink(const unsigned int xid, struct cifs_tcon *tcon, const char *name,
 	memset(resp_buftype, 0, sizeof(resp_buftype));
 	memset(rsp_iov, 0, sizeof(rsp_iov));
 
+	memset(open_iov, 0, sizeof(open_iov));
 	rqst[0].rq_iov = open_iov;
 	rqst[0].rq_nvec = ARRAY_SIZE(open_iov);
 
@@ -1229,14 +1230,15 @@ smb2_unlink(const unsigned int xid, struct cifs_tcon *tcon, const char *name,
 	creq = rqst[0].rq_iov[0].iov_base;
 	creq->ShareAccess = FILE_SHARE_DELETE_LE;
 
+	memset(&close_iov, 0, sizeof(close_iov));
 	rqst[1].rq_iov = &close_iov;
 	rqst[1].rq_nvec = 1;
 
 	rc = SMB2_close_init(tcon, server, &rqst[1],
 			     COMPOUND_FID, COMPOUND_FID, false);
-	smb2_set_related(&rqst[1]);
 	if (rc)
 		goto err_free;
+	smb2_set_related(&rqst[1]);
 
 	if (retries) {
 		for (int i = 0; i < ARRAY_SIZE(rqst);  i++)
Signature · 1 line
2.51.0
author maintainer
#194 lore raw

PATCH 188/314 scsi: core: Fix refcount leak for tagset_refcnt

In reply to Sasha Levin

From: Junxiao Bi <[email protected]>

commit 1ac22c8eae81366101597d48360718dff9b9d980 upstream.

This leak will cause a hang when tearing down the SCSI host. For example, iscsid hangs with the following call trace:

[130120.652718] scsi_alloc_sdev: Allocation failure during SCSI scanning, some SCSI devices might not be configured

PID: 2528 TASK: ffff9d0408974e00 CPU: 3 COMMAND: "iscsid"
#0 [ffffb5b9c134b9e0] __schedule at ffffffff860657d4
#1 [ffffb5b9c134ba28] schedule at ffffffff86065c6f
#2 [ffffb5b9c134ba40] schedule_timeout at ffffffff86069fb0
#3 [ffffb5b9c134bab0] __wait_for_common at ffffffff8606674f
#4 [ffffb5b9c134bb10] scsi_remove_host at ffffffff85bfe84b
#5 [ffffb5b9c134bb30] iscsi_sw_tcp_session_destroy at ffffffffc03031c4 [iscsi_tcp] #6 [ffffb5b9c134bb48] iscsi_if_recv_msg at ffffffffc0292692 [scsi_transport_iscsi] #7 [ffffb5b9c134bb98] iscsi_if_rx at ffffffffc02929c2 [scsi_transport_iscsi] #8 [ffffb5b9c134bbf0] netlink_unicast at ffffffff85e551d6
#9 [ffffb5b9c134bc38] netlink_sendmsg at ffffffff85e554ef

---
 drivers/scsi/scsi_scan.c | 1 +
 1 file changed, 1 insertion(+)
drivers/scsi/scsi_scan.c +1 -0
index 3c6e089e80c38..f405ef9c0e1e8 100644
@@ -356,6 +356,7 @@ static struct scsi_device *scsi_alloc_sdev(struct scsi_target *starget,
 	 * since we use this queue depth most of times.
 	 */
 	if (scsi_realloc_sdev_budget_map(sdev, depth)) {
+		kref_put(&sdev->host->tagset_refcnt, scsi_mq_free_tags);
 		put_device(&starget->dev);
 		kfree(sdev);
 		goto out;
Signature · 1 line
2.51.0
author maintainer
#195 lore raw

PATCH 189/314 mptcp: pm: avoid sending RM_ADDR over same subflow

In reply to Sasha Levin

From: "Matthieu Baerts (NGI0)" <[email protected]>

commit fb8d0bccb221080630efcd9660c9f9349e53cc9e upstream.

RM_ADDR are sent over an active subflow, the first one in the subflows list. There is then a high chance the initial subflow is picked. With the in-kernel PM, when an endpoint is removed, a RM_ADDR is sent, then linked subflows are closed. This is done for each active MPTCP connection.

MPTCP endpoints are likely removed because the attached network is no longer available or usable. In this case, it is better to avoid sending this RM_ADDR over the subflow that is going to be removed, but prefer sending it over another active and non stale subflow, if any.

This modification avoids situations where the other end is not notified when a subflow is no longer usable: typically when the endpoint linked to the initial subflow is removed, especially on the server side.

---
 net/mptcp/pm.c | 55 +++++++++++++++++++++++++++++++++++++++-----------
 1 file changed, 43 insertions(+), 12 deletions(-)
net/mptcp/pm.c +43 -12
index 9604b91902b8b..e22d53af0ffa0 100644
@@ -212,9 +212,24 @@ void mptcp_pm_send_ack(struct mptcp_sock *msk,
 	spin_lock_bh(&msk->pm.lock);
 }
 
-void mptcp_pm_addr_send_ack(struct mptcp_sock *msk)
+static bool subflow_in_rm_list(const struct mptcp_subflow_context *subflow,
+			       const struct mptcp_rm_list *rm_list)
+{
+	u8 i, id = subflow_get_local_id(subflow);
+
+	for (i = 0; i < rm_list->nr; i++) {
+		if (rm_list->ids[i] == id)
+			return true;
+	}
+
+	return false;
+}
+
+static void
+mptcp_pm_addr_send_ack_avoid_list(struct mptcp_sock *msk,
+				  const struct mptcp_rm_list *rm_list)
 {
-	struct mptcp_subflow_context *subflow, *alt = NULL;
+	struct mptcp_subflow_context *subflow, *stale = NULL, *same_id = NULL;
 
 	msk_owned_by_me(msk);
 	lockdep_assert_held(&msk->pm.lock);
@@ -224,19 +239,35 @@ void mptcp_pm_addr_send_ack(struct mptcp_sock *msk)
 		return;
 
 	mptcp_for_each_subflow(msk, subflow) {
-		if (__mptcp_subflow_active(subflow)) {
-			if (!subflow->stale) {
-				mptcp_pm_send_ack(msk, subflow, false, false);
-				return;
-			}
+		if (!__mptcp_subflow_active(subflow))
+			continue;
 
-			if (!alt)
-				alt = subflow;
+		if (unlikely(subflow->stale)) {
+			if (!stale)
+				stale = subflow;
+		} else if (unlikely(rm_list &&
+				    subflow_in_rm_list(subflow, rm_list))) {
+			if (!same_id)
+				same_id = subflow;
+		} else {
+			goto send_ack;
 		}
 	}
 
-	if (alt)
-		mptcp_pm_send_ack(msk, alt, false, false);
+	if (same_id)
+		subflow = same_id;
+	else if (stale)
+		subflow = stale;
+	else
+		return;
+
+send_ack:
+	mptcp_pm_send_ack(msk, subflow, false, false);
+}
+
+void mptcp_pm_addr_send_ack(struct mptcp_sock *msk)
+{
+	mptcp_pm_addr_send_ack_avoid_list(msk, NULL);
 }
 
 int mptcp_pm_mp_prio_send_ack(struct mptcp_sock *msk,
@@ -470,7 +501,7 @@ int mptcp_pm_remove_addr(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_
 	msk->pm.rm_list_tx = *rm_list;
 	rm_addr |= BIT(MPTCP_RM_ADDR_SIGNAL);
 	WRITE_ONCE(msk->pm.addr_signal, rm_addr);
-	mptcp_pm_addr_send_ack(msk);
+	mptcp_pm_addr_send_ack_avoid_list(msk, rm_list);
 	return 0;
 }
 
Signature · 1 line
2.51.0
author maintainer
#196 lore raw

PATCH 190/314 mptcp: pm: in-kernel: always mark signal+subflow endp as used

In reply to Sasha Levin

From: "Matthieu Baerts (NGI0)" <[email protected]>

commit 579a752464a64cb5f9139102f0e6b90a1f595ceb upstream.

Syzkaller managed to find a combination of actions that was generating this warning:

msk->pm.local_addr_used == 0

  WARNING: net/mptcp/pm_kernel.c:1071 at __mark_subflow_endp_available net/mptcp/pm_kernel.c:1071 [inline], CPU#1: syz.2.17/961
  WARNING: net/mptcp/pm_kernel.c:1071 at mptcp_nl_remove_subflow_and_signal_addr net/mptcp/pm_kernel.c:1103 [inline], CPU#1: syz.2.17/961
  WARNING: net/mptcp/pm_kernel.c:1071 at mptcp_pm_nl_del_addr_doit+0x81d/0x8f0 net/mptcp/pm_kernel.c:1210, CPU#1: syz.2.17/961
  Modules linked in:
  CPU: 1 UID: 0 PID: 961 Comm: syz.2.17 Not tainted 6.19.0-08368-gfafda3b4b06b #22 PREEMPT(full)
  Hardware name: QEMU Ubuntu 25.10 PC v2 (i440FX + PIIX, + 10.1 machine, 1996), BIOS 1.17.0-debian-1.17.0-1build1 04/01/2014
  RIP: 0010:__mark_subflow_endp_available net/mptcp/pm_kernel.c:1071 [inline]
  RIP: 0010:mptcp_nl_remove_subflow_and_signal_addr net/mptcp/pm_kernel.c:1103 [inline]
  RIP: 0010:mptcp_pm_nl_del_addr_doit+0x81d/0x8f0 net/mptcp/pm_kernel.c:1210
  Code: 89 c5 e8 46 30 6f fe e9 21 fd ff ff 49 83 ed 80 e8 38 30 6f fe 4c 89 ef be 03 00 00 00 e8 db 49 df fe eb ac e8 24 30 6f fe 90 <0f> 0b 90 e9 1d ff ff ff e8 16 30 6f fe eb 05 e8 0f 30 6f fe e8 9a
  RSP: 0018:ffffc90001663880 EFLAGS: 00010293
  RAX: ffffffff82de1a6c RBX: 0000000000000000 RCX: ffff88800722b500
  RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000000
  RBP: ffff8880158b22d0 R08: 0000000000010425 R09: ffffffffffffffff
  R10: ffffffff82de18ba R11: 0000000000000000 R12: ffff88800641a640
  R13: ffff8880158b1880 R14: ffff88801ec3c900 R15: ffff88800641a650
  FS:  00005555722c3500(0000) GS:ffff8880f909d000(0000) knlGS:0000000000000000
  CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
  CR2: 00007f66346e0f60 CR3: 000000001607c000 CR4: 0000000000350ef0
  Call Trace:
   <TASK>
   genl_family_rcv_msg_doit+0x117/0x180 net/netlink/genetlink.c:1115
   genl_family_rcv_msg net/netlink/genetlink.c:1195 [inline]
   genl_rcv_msg+0x3a8/0x3f0 net/netlink/genetlink.c:1210
   netlink_rcv_skb+0x16d/0x240 net/netlink/af_netlink.c:2550
   genl_rcv+0x28/0x40 net/netlink/genetlink.c:1219
   netlink_unicast_kernel net/netlink/af_netlink.c:1318 [inline]
   netlink_unicast+0x3e9/0x4c0 net/netlink/af_netlink.c:1344
   netlink_sendmsg+0x4aa/0x5b0 net/netlink/af_netlink.c:1894
   sock_sendmsg_nosec net/socket.c:727 [inline]
   __sock_sendmsg+0xc9/0xf0 net/socket.c:742
   ____sys_sendmsg+0x272/0x3b0 net/socket.c:2592
   ___sys_sendmsg+0x2de/0x320 net/socket.c:2646
   __sys_sendmsg net/socket.c:2678 [inline]
   __do_sys_sendmsg net/socket.c:2683 [inline]
   __se_sys_sendmsg net/socket.c:2681 [inline]
   __x64_sys_sendmsg+0x110/0x1a0 net/socket.c:2681
   do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline]
   do_syscall_64+0x143/0x440 arch/x86/entry/syscall_64.c:94
   entry_SYSCALL_64_after_hwframe+0x77/0x7f
  RIP: 0033:0x7f66346f826d
  Code: ff c3 66 2e 0f 1f 84 00 00 00 00 00 90 f3 0f 1e fa 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 e8 ff ff ff f7 d8 64 89 01 48
  RSP: 002b:00007ffc83d8bdc8 EFLAGS: 00000246 ORIG_RAX: 000000000000002e
  RAX: ffffffffffffffda RBX: 00007f6634985fa0 RCX: 00007f66346f826d
  RDX: 00000000040000b0 RSI: 0000200000000740 RDI: 0000000000000007
  RBP: 0000000000000000 R08: 0000000000000000 R09: 0000000000000000
  R10: 0000000000000000 R11: 0000000000000246 R12: 00007f6634985fa8
  R13: 00007f6634985fac R14: 0000000000000000 R15: 0000000000001770
   </TASK>

The actions that caused that seem to be:

- Set the MPTCP subflows limit to 0
- Create an MPTCP endpoint with both the 'signal' and 'subflow' flags
- Create a new MPTCP connection from a different address: an ADD_ADDR linked to the MPTCP endpoint will be sent ('signal' flag), but no subflows is initiated ('subflow' flag)
- Remove the MPTCP endpoint

In this case, msk->pm.local_addr_used has been kept to 0 -- because no subflows have been created -- but the corresponding bit in msk->pm.id_avail_bitmap has been cleared when the ADD_ADDR has been sent. This later causes a splat when removing the MPTCP endpoint because msk->pm.local_addr_used has been kept to 0.

Now, if an endpoint has both the signal and subflow flags, but it is not possible to create subflows because of the limits or the c-flag case, then the local endpoint counter is still incremented: the endpoint is used at the end. This avoids issues later when removing the endpoint and calling __mark_subflow_endp_available(), which expects msk->pm.local_addr_used to have been previously incremented if the endpoint was marked as used according to msk->pm.id_avail_bitmap.

Note that signal_and_subflow variable is reset to false when the limits and the c-flag case allows subflows creation. Also, local_addr_used is only incremented for non ID0 subflows.

---
 net/mptcp/pm_kernel.c | 9 +++++++++
 1 file changed, 9 insertions(+)
net/mptcp/pm_kernel.c +9 -0
index f47c91141631f..6fd393f451bf4 100644
@@ -407,6 +407,15 @@ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk)
 	}
 
 exit:
+	/* If an endpoint has both the signal and subflow flags, but it is not
+	 * possible to create subflows -- the 'while' loop body above never
+	 * executed --  then still mark the endp as used, which is somehow the
+	 * case. This avoids issues later when removing the endpoint and calling
+	 * __mark_subflow_endp_available(), which expects the increment here.
+	 */
+	if (signal_and_subflow && local.addr.id != msk->mpc_endpoint_id)
+		msk->pm.local_addr_used++;
+
 	mptcp_pm_nl_check_work_pending(msk);
 }
 
Signature · 1 line
2.51.0
author maintainer
#197 lore raw

PATCH 191/314 selftests: mptcp: more stable simult_flows tests

In reply to Sasha Levin

From: Paolo Abeni <[email protected]>

commit 8c09412e584d9bcc0e71d758ec1008d1c8d1a326 upstream.

By default, the netem qdisc can keep up to 1000 packets under its belly to deal with the configured rate and delay. The simult flows test-case simulates very low speed links, to avoid problems due to slow CPUs and the TCP stack tend to transmit at a slightly higher rate than the (virtual) link constraints.

All the above causes a relatively large amount of packets being enqueued in the netem qdiscs - the longer the transfer, the longer the queue - producing increasingly high TCP RTT samples and consequently increasingly larger receive buffer size due to DRS.

When the receive buffer size becomes considerably larger than the needed size, the tests results can flake, i.e. because minimal inaccuracy in the pacing rate can lead to a single subflow usage towards the end of the connection for a considerable amount of data.

Address the issue explicitly setting netem limits suitable for the configured link speeds and unflake all the affected tests.

---
 tools/testing/selftests/net/mptcp/simult_flows.sh | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)
tools/testing/selftests/net/mptcp/simult_flows.sh +7 -4
index 1903e8e84a315..76730e511f92e 100755
@@ -233,10 +233,13 @@ run_test()
 	for dev in ns2eth1 ns2eth2; do
 		tc -n $ns2 qdisc del dev $dev root >/dev/null 2>&1
 	done
-	tc -n $ns1 qdisc add dev ns1eth1 root netem rate ${rate1}mbit $delay1
-	tc -n $ns1 qdisc add dev ns1eth2 root netem rate ${rate2}mbit $delay2
-	tc -n $ns2 qdisc add dev ns2eth1 root netem rate ${rate1}mbit $delay1
-	tc -n $ns2 qdisc add dev ns2eth2 root netem rate ${rate2}mbit $delay2
+
+	# keep the queued pkts number low, or the RTT estimator will see
+	# increasing latency over time.
+	tc -n $ns1 qdisc add dev ns1eth1 root netem rate ${rate1}mbit $delay1 limit 50
+	tc -n $ns1 qdisc add dev ns1eth2 root netem rate ${rate2}mbit $delay2 limit 50
+	tc -n $ns2 qdisc add dev ns2eth1 root netem rate ${rate1}mbit $delay1 limit 50
+	tc -n $ns2 qdisc add dev ns2eth2 root netem rate ${rate2}mbit $delay2 limit 50
 
 	# time is measured in ms, account for transfer size, aggregated link speed
 	# and header overhead (10%)
Signature · 1 line
2.51.0
author maintainer
#198 lore raw

PATCH 192/314 selftests: mptcp: join: check RM_ADDR not sent over same subflow

In reply to Sasha Levin

From: "Matthieu Baerts (NGI0)" <[email protected]>

commit 560edd99b5f58b2d4bbe3c8e51e1eed68d887b0e upstream.

This validates the previous commit: RM_ADDR were sent over the first found active subflow which could be the same as the one being removed. It is more likely to loose this notification.

For this check, RM_ADDR are explicitly dropped when trying to send them over the initial subflow, when removing the endpoint attached to it. If it is dropped, the test will complain because some RM_ADDR have not been received.

Note that only the RM_ADDR are dropped, to allow the linked subflow to be quickly and cleanly closed. To only drop those RM_ADDR, a cBPF byte code is used. If the IPTables commands fail, that's OK, the tests will continue to pass, but not validate this part. This can be ignored:
another subtest fully depends on such command, and will be marked as skipped.

The 'Fixes' tag here below is the same as the one from the previous
commit: this patch here is not fixing anything wrong in the selftests, but it validates the previous fix for an issue introduced by this commit ID.

---
 .../testing/selftests/net/mptcp/mptcp_join.sh | 36 +++++++++++++++++++
 1 file changed, 36 insertions(+)
tools/testing/selftests/net/mptcp/mptcp_join.sh +36 -0
index 9a95830005061..f29a10f2b31b2 100755
@@ -103,6 +103,24 @@ CBPF_MPTCP_SUBOPTION_ADD_ADDR="14,
 			       6 0 0 65535,
 			       6 0 0 0"
 
+# IPv4: TCP hdr of 48B, a first suboption of 12B (DACK8), the RM_ADDR suboption
+# generated using "nfbpf_compile '(ip[32] & 0xf0) == 0xc0 && ip[53] == 0x0c &&
+#				  (ip[66] & 0xf0) == 0x40'"
+CBPF_MPTCP_SUBOPTION_RM_ADDR="13,
+			      48 0 0 0,
+			      84 0 0 240,
+			      21 0 9 64,
+			      48 0 0 32,
+			      84 0 0 240,
+			      21 0 6 192,
+			      48 0 0 53,
+			      21 0 4 12,
+			      48 0 0 66,
+			      84 0 0 240,
+			      21 0 1 64,
+			      6 0 0 65535,
+			      6 0 0 0"
+
 init_partial()
 {
 	capout=$(mktemp)
@@ -4067,6 +4085,14 @@ endpoint_tests()
 		chk_subflow_nr "after no reject" 3
 		chk_mptcp_info subflows 2 subflows 2
 
+		# To make sure RM_ADDR are sent over a different subflow, but
+		# allow the rest to quickly and cleanly close the subflow
+		local ipt=1
+		ip netns exec "${ns2}" ${iptables} -I OUTPUT -s "10.0.1.2" \
+			-p tcp -m tcp --tcp-option 30 \
+			-m bpf --bytecode \
+			"$CBPF_MPTCP_SUBOPTION_RM_ADDR" \
+			-j DROP || ipt=0
 		local i
 		for i in $(seq 3); do
 			pm_nl_del_endpoint $ns2 1 10.0.1.2
@@ -4079,6 +4105,7 @@ endpoint_tests()
 			chk_subflow_nr "after re-add id 0 ($i)" 3
 			chk_mptcp_info subflows 3 subflows 3
 		done
+		[ ${ipt} = 1 ] && ip netns exec "${ns2}" ${iptables} -D OUTPUT 1
 
 		mptcp_lib_kill_group_wait $tests_pid
 
@@ -4138,11 +4165,20 @@ endpoint_tests()
 		chk_mptcp_info subflows 2 subflows 2
 		chk_mptcp_info add_addr_signal 2 add_addr_accepted 2
 
+		# To make sure RM_ADDR are sent over a different subflow, but
+		# allow the rest to quickly and cleanly close the subflow
+		local ipt=1
+		ip netns exec "${ns1}" ${iptables} -I OUTPUT -s "10.0.1.1" \
+			-p tcp -m tcp --tcp-option 30 \
+			-m bpf --bytecode \
+			"$CBPF_MPTCP_SUBOPTION_RM_ADDR" \
+			-j DROP || ipt=0
 		pm_nl_del_endpoint $ns1 42 10.0.1.1
 		sleep 0.5
 		chk_subflow_nr "after delete ID 0" 2
 		chk_mptcp_info subflows 2 subflows 2
 		chk_mptcp_info add_addr_signal 2 add_addr_accepted 2
+		[ ${ipt} = 1 ] && ip netns exec "${ns1}" ${iptables} -D OUTPUT 1
 
 		pm_nl_add_endpoint $ns1 10.0.1.1 id 99 flags signal
 		wait_mpj $ns2
Signature · 1 line
2.51.0
author maintainer
#199 lore raw

PATCH 193/314 selftests: mptcp: join: check removing signal+subflow endp

In reply to Sasha Levin

From: "Matthieu Baerts (NGI0)" <[email protected]>

commit 1777f349ff41b62dfe27454b69c27b0bc99ffca5 upstream.

This validates the previous commit: endpoints with both the signal and subflow flags should always be marked as used even if it was not possible to create new subflows due to the MPTCP PM limits.

For this test, an extra endpoint is created with both the signal and the subflow flags, and limits are set not to create extra subflows. In this case, an ADD_ADDR is sent, but no subflows are created. Still, the local endpoint is marked as used, and no warning is fired when removing the endpoint, after having sent a RM_ADDR.

The 'Fixes' tag here below is the same as the one from the previous
commit: this patch here is not fixing anything wrong in the selftests, but it validates the previous fix for an issue introduced by this commit ID.

---
 tools/testing/selftests/net/mptcp/mptcp_join.sh | 13 +++++++++++++
 1 file changed, 13 insertions(+)
tools/testing/selftests/net/mptcp/mptcp_join.sh +13 -0
index f29a10f2b31b2..8990cd99f4e32 100755
@@ -2613,6 +2613,19 @@ remove_tests()
 		chk_rst_nr 0 0
 	fi
 
+	# signal+subflow with limits, remove
+	if reset "remove signal+subflow with limits"; then
+		pm_nl_set_limits $ns1 0 0
+		pm_nl_add_endpoint $ns1 10.0.2.1 flags signal,subflow
+		pm_nl_set_limits $ns2 0 0
+		addr_nr_ns1=-1 speed=slow \
+			run_tests $ns1 $ns2 10.0.1.1
+		chk_join_nr 0 0 0
+		chk_add_nr 1 1
+		chk_rm_nr 1 0 invert
+		chk_rst_nr 0 0
+	fi
+
 	# addresses remove
 	if reset "remove addresses"; then
 		pm_nl_set_limits $ns1 3 3
Signature · 1 line
2.51.0
author maintainer
#200 lore raw

PATCH 194/314 kbuild: Split .modinfo out from ELF_DETAILS

In reply to Sasha Levin

From: Nathan Chancellor <[email protected]>

commit 8678591b47469fe16357234efef9b260317b8be4 upstream.

Commit 3e86e4d74c04 ("kbuild: keep .modinfo section in vmlinux.unstripped") added .modinfo to ELF_DETAILS while removing it from COMMON_DISCARDS, as it was needed in vmlinux.unstripped and ELF_DETAILS was present in all architecture specific vmlinux linker scripts. While this shuffle is fine for vmlinux, ELF_DETAILS and COMMON_DISCARDS may be used by other linker scripts, such as the s390 and x86 compressed boot images, which may not expect to have a .modinfo section. In certain circumstances, this could result in a bootloader failing to load the compressed kernel [1].

Commit ddc6cbef3ef1 ("s390/boot/vmlinux.lds.S: Ensure bzImage ends with SecureBoot trailer") recently addressed this for the s390 bzImage but the same bug remains for arm, parisc, and x86. The presence of .modinfo in the x86 bzImage was the root cause of the issue worked around with commit d50f21091358 ("kbuild: align modinfo section for Secureboot Authenticode EDK2 compat"). misc.c in arch/x86/boot/compressed includes lib/decompress_unzstd.c, which in turn includes lib/xxhash.c and its MODULE_LICENSE / MODULE_DESCRIPTION macros due to the STATIC definition.

Split .modinfo out from ELF_DETAILS into its own macro and handle it in all vmlinux linker scripts. Discard .modinfo in the places where it was previously being discarded from being in COMMON_DISCARDS, as it has never been necessary in those uses.

---
 arch/alpha/kernel/vmlinux.lds.S           | 1 +
 arch/arc/kernel/vmlinux.lds.S             | 1 +
 arch/arm/boot/compressed/vmlinux.lds.S    | 1 +
 arch/arm/kernel/vmlinux-xip.lds.S         | 1 +
 arch/arm/kernel/vmlinux.lds.S             | 1 +
 arch/arm64/kernel/vmlinux.lds.S           | 1 +
 arch/csky/kernel/vmlinux.lds.S            | 1 +
 arch/hexagon/kernel/vmlinux.lds.S         | 1 +
 arch/loongarch/kernel/vmlinux.lds.S       | 1 +
 arch/m68k/kernel/vmlinux-nommu.lds        | 1 +
 arch/m68k/kernel/vmlinux-std.lds          | 1 +
 arch/m68k/kernel/vmlinux-sun3.lds         | 1 +
 arch/mips/kernel/vmlinux.lds.S            | 1 +
 arch/nios2/kernel/vmlinux.lds.S           | 1 +
 arch/openrisc/kernel/vmlinux.lds.S        | 1 +
 arch/parisc/boot/compressed/vmlinux.lds.S | 1 +
 arch/parisc/kernel/vmlinux.lds.S          | 1 +
 arch/powerpc/kernel/vmlinux.lds.S         | 1 +
 arch/riscv/kernel/vmlinux.lds.S           | 1 +
 arch/s390/kernel/vmlinux.lds.S            | 1 +
 arch/sh/kernel/vmlinux.lds.S              | 1 +
 arch/sparc/kernel/vmlinux.lds.S           | 1 +
 arch/um/kernel/dyn.lds.S                  | 1 +
 arch/um/kernel/uml.lds.S                  | 1 +
 arch/x86/boot/compressed/vmlinux.lds.S    | 2 +-
 arch/x86/kernel/vmlinux.lds.S             | 1 +
 include/asm-generic/vmlinux.lds.h         | 4 +++-
 27 files changed, 29 insertions(+), 2 deletions(-)
arch/alpha/kernel/vmlinux.lds.S +1 -0
index 2efa7dfc798a9..2d136c63db161 100644
@@ -71,6 +71,7 @@ SECTIONS
 
 	STABS_DEBUG
 	DWARF_DEBUG
+	MODINFO
 	ELF_DETAILS
 
 	DISCARDS
arch/arc/kernel/vmlinux.lds.S +1 -0
index 61a1b2b96e1d8..6af63084ff285 100644
@@ -123,6 +123,7 @@ SECTIONS
 	_end = . ;
 
 	STABS_DEBUG
+	MODINFO
 	ELF_DETAILS
 	DISCARDS
 
arch/arm/boot/compressed/vmlinux.lds.S +1 -0
index d411abd4310ea..2d916647df03c 100644
@@ -21,6 +21,7 @@ SECTIONS
     COMMON_DISCARDS
     *(.ARM.exidx*)
     *(.ARM.extab*)
+    *(.modinfo)
     *(.note.*)
     *(.rel.*)
     *(.printk_index)
arch/arm/kernel/vmlinux-xip.lds.S +1 -0
index f2e8d4fac0687..5afb725998ec0 100644
@@ -154,6 +154,7 @@ SECTIONS
 
 	STABS_DEBUG
 	DWARF_DEBUG
+	MODINFO
 	ARM_DETAILS
 
 	ARM_ASSERTS
arch/arm/kernel/vmlinux.lds.S +1 -0
index d592a203f9c6b..c07843c3c53d3 100644
@@ -153,6 +153,7 @@ SECTIONS
 
 	STABS_DEBUG
 	DWARF_DEBUG
+	MODINFO
 	ARM_DETAILS
 
 	ARM_ASSERTS
arch/arm64/kernel/vmlinux.lds.S +1 -0
index ad6133b89e7a4..2964aad0362e4 100644
@@ -349,6 +349,7 @@ SECTIONS
 
 	STABS_DEBUG
 	DWARF_DEBUG
+	MODINFO
 	ELF_DETAILS
 
 	HEAD_SYMBOLS
arch/csky/kernel/vmlinux.lds.S +1 -0
index d718961786d24..81943981b3af4 100644
@@ -109,6 +109,7 @@ SECTIONS
 
 	STABS_DEBUG
 	DWARF_DEBUG
+	MODINFO
 	ELF_DETAILS
 
 	DISCARDS
arch/hexagon/kernel/vmlinux.lds.S +1 -0
index 1150b77fa281c..aae22283b5e00 100644
@@ -62,6 +62,7 @@ SECTIONS
 
 	STABS_DEBUG
 	DWARF_DEBUG
+	MODINFO
 	ELF_DETAILS
 	.hexagon.attributes 0 : { *(.hexagon.attributes) }
 
arch/loongarch/kernel/vmlinux.lds.S +1 -0
index 08ea921cdec16..d0e1377a041d6 100644
@@ -147,6 +147,7 @@ SECTIONS
 
 	STABS_DEBUG
 	DWARF_DEBUG
+	MODINFO
 	ELF_DETAILS
 
 #ifdef CONFIG_EFI_STUB
arch/m68k/kernel/vmlinux-nommu.lds +1 -0
index 2624fc18c131f..45d7f4b0177b4 100644
@@ -85,6 +85,7 @@ SECTIONS {
 	_end = .;
 
 	STABS_DEBUG
+	MODINFO
 	ELF_DETAILS
 
 	/* Sections to be discarded */
arch/m68k/kernel/vmlinux-std.lds +1 -0
index 1ccdd04ae4624..7326586afe15f 100644
@@ -58,6 +58,7 @@ SECTIONS
   _end = . ;
 
   STABS_DEBUG
+  MODINFO
   ELF_DETAILS
 
   /* Sections to be discarded */
arch/m68k/kernel/vmlinux-sun3.lds +1 -0
index f13ddcc2af5c2..1b19fef201fba 100644
@@ -51,6 +51,7 @@ __init_begin = .;
   _end = . ;
 
   STABS_DEBUG
+  MODINFO
   ELF_DETAILS
 
   /* Sections to be discarded */
arch/mips/kernel/vmlinux.lds.S +1 -0
index 2b708fac8d2c1..579b2cc1995ae 100644
@@ -217,6 +217,7 @@ SECTIONS
 
 	STABS_DEBUG
 	DWARF_DEBUG
+	MODINFO
 	ELF_DETAILS
 
 	/* These must appear regardless of  .  */
arch/nios2/kernel/vmlinux.lds.S +1 -0
index 37b9580550646..206f92445bfad 100644
@@ -57,6 +57,7 @@ SECTIONS
 
 	STABS_DEBUG
 	DWARF_DEBUG
+	MODINFO
 	ELF_DETAILS
 
 	DISCARDS
arch/openrisc/kernel/vmlinux.lds.S +1 -0
index 049bff45f6126..9b29c3211774c 100644
@@ -101,6 +101,7 @@ SECTIONS
 	/* Throw in the debugging sections */
 	STABS_DEBUG
 	DWARF_DEBUG
+	MODINFO
 	ELF_DETAILS
 
         /* Sections to be discarded -- must be last */
arch/parisc/boot/compressed/vmlinux.lds.S +1 -0
index ab7b439908578..87d24cc824b66 100644
@@ -90,6 +90,7 @@ SECTIONS
 	/* Sections to be discarded */
 	DISCARDS
 	/DISCARD/ : {
+		*(.modinfo)
 #ifdef CONFIG_64BIT
 		/* temporary hack until binutils is fixed to not emit these
 		 * for static binaries
arch/parisc/kernel/vmlinux.lds.S +1 -0
index b445e47903cfd..0ca93d6d72354 100644
@@ -165,6 +165,7 @@ SECTIONS
 	_end = . ;
 
 	STABS_DEBUG
+	MODINFO
 	ELF_DETAILS
 	.note 0 : { *(.note) }
 
arch/powerpc/kernel/vmlinux.lds.S +1 -0
index de6ee7d35cff0..5589af3e40844 100644
@@ -398,6 +398,7 @@ SECTIONS
 	_end = . ;
 
 	DWARF_DEBUG
+	MODINFO
 	ELF_DETAILS
 
 	DISCARDS
arch/riscv/kernel/vmlinux.lds.S +1 -0
index 61bd5ba6680a7..997f9eb3b22b1 100644
@@ -170,6 +170,7 @@ SECTIONS
 
 	STABS_DEBUG
 	DWARF_DEBUG
+	MODINFO
 	ELF_DETAILS
 	.riscv.attributes 0 : { *(.riscv.attributes) }
 
arch/s390/kernel/vmlinux.lds.S +1 -0
index d74d4c52ccd05..9289e9e535c70 100644
@@ -212,6 +212,7 @@ SECTIONS
 	/* Debugging sections.	*/
 	STABS_DEBUG
 	DWARF_DEBUG
+	MODINFO
 	ELF_DETAILS
 
 	/*
arch/sh/kernel/vmlinux.lds.S +1 -0
index 008c30289eaa6..169c63fb3c1dc 100644
@@ -89,6 +89,7 @@ SECTIONS
 
 	STABS_DEBUG
 	DWARF_DEBUG
+	MODINFO
 	ELF_DETAILS
 
 	DISCARDS
arch/sparc/kernel/vmlinux.lds.S +1 -0
index f1b86eb303404..7ea510d9b42f2 100644
@@ -191,6 +191,7 @@ SECTIONS
 
 	STABS_DEBUG
 	DWARF_DEBUG
+	MODINFO
 	ELF_DETAILS
 
 	DISCARDS
arch/um/kernel/dyn.lds.S +1 -0
index a36b7918a011a..ad3cefeff2acb 100644
@@ -172,6 +172,7 @@ SECTIONS
 
   STABS_DEBUG
   DWARF_DEBUG
+  MODINFO
   ELF_DETAILS
 
   DISCARDS
arch/um/kernel/uml.lds.S +1 -0
index a409d4b66114f..30aa24348d60c 100644
@@ -113,6 +113,7 @@ SECTIONS
 
   STABS_DEBUG
   DWARF_DEBUG
+  MODINFO
   ELF_DETAILS
 
   DISCARDS
arch/x86/boot/compressed/vmlinux.lds.S +1 -1
index 587ce3e7c5048..e0b152715d9c6 100644
@@ -88,7 +88,7 @@ SECTIONS
 	/DISCARD/ : {
 		*(.dynamic) *(.dynsym) *(.dynstr) *(.dynbss)
 		*(.hash) *(.gnu.hash)
-		*(.note.*)
+		*(.note.*) *(.modinfo)
 	}
 
 	.got.plt (INFO) : {
arch/x86/kernel/vmlinux.lds.S +1 -0
index d7af4a64c211b..4ed82b1fe173b 100644
@@ -424,6 +424,7 @@ SECTIONS
 	.llvm_bb_addr_map : { *(.llvm_bb_addr_map) }
 #endif
 
+	MODINFO
 	ELF_DETAILS
 
 	DISCARDS
include/asm-generic/vmlinux.lds.h +3 -1
index e04d56a5332e6..6640e06ef2f13 100644
@@ -832,12 +832,14 @@ defined(CONFIG_AUTOFDO_CLANG) || defined(CONFIG_PROPELLER_CLANG)
 
 /* Required sections not related to debugging. */
 #define ELF_DETAILS							\
-		.modinfo : { *(.modinfo) . = ALIGN(8); }		\
 		.comment 0 : { *(.comment) }				\
 		.symtab 0 : { *(.symtab) }				\
 		.strtab 0 : { *(.strtab) }				\
 		.shstrtab 0 : { *(.shstrtab) }
 
+#define MODINFO								\
+		.modinfo : { *(.modinfo) . = ALIGN(8); }
+
 #ifdef CONFIG_GENERIC_BUG
 #define BUG_TABLE							\
 	. = ALIGN(8);							\
Signature · 1 line
2.51.0
author maintainer
#201 lore raw

PATCH 195/314 Revert "netfilter: nft_set_rbtree: validate open interval overlap"

In reply to Sasha Levin

From: Greg Kroah-Hartman <[email protected]>

This reverts commit 12b1681793e9b7552495290785a3570c539f409d which is commit 648946966a08e4cb1a71619e3d1b12bd7642de7b upstream.

It is causing netfilter issues, so revert it for now.

---
 include/net/netfilter/nf_tables.h |  4 --
 net/netfilter/nf_tables_api.c     | 21 ++-------
 net/netfilter/nft_set_rbtree.c    | 71 +++++--------------------------
 3 files changed, 14 insertions(+), 82 deletions(-)
include/net/netfilter/nf_tables.h +0 -4
index 05f57ba622447..f1b67b40dd4de 100644
@@ -278,8 +278,6 @@ struct nft_userdata {
 	unsigned char		data[];
 };
 
-#define NFT_SET_ELEM_INTERNAL_LAST	0x1
-
 /* placeholder structure for opaque set element backend representation. */
 struct nft_elem_priv { };
 
@@ -289,7 +287,6 @@ struct nft_elem_priv { };
  *	@key: element key
  *	@key_end: closing element key
  *	@data: element data
- * 	@flags: flags
  *	@priv: element private data and extensions
  */
 struct nft_set_elem {
@@ -305,7 +302,6 @@ struct nft_set_elem {
 		u32		buf[NFT_DATA_VALUE_MAXLEN / sizeof(u32)];
 		struct nft_data val;
 	} data;
-	u32			flags;
 	struct nft_elem_priv	*priv;
 };
 
net/netfilter/nf_tables_api.c +4 -17
index d4babc4d3bff3..89039bbf7d638 100644
@@ -7272,8 +7272,7 @@ static u32 nft_set_maxsize(const struct nft_set *set)
 }
 
 static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
-			    const struct nlattr *attr, u32 nlmsg_flags,
-			    bool last)
+			    const struct nlattr *attr, u32 nlmsg_flags)
 {
 	struct nft_expr *expr_array[NFT_SET_EXPR_MAX] = {};
 	struct nlattr *nla[NFTA_SET_ELEM_MAX + 1];
@@ -7559,11 +7558,6 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
 	if (flags)
 		*nft_set_ext_flags(ext) = flags;
 
-	if (last)
-		elem.flags = NFT_SET_ELEM_INTERNAL_LAST;
-	else
-		elem.flags = 0;
-
 	if (obj)
 		*nft_set_ext_obj(ext) = obj;
 
@@ -7727,8 +7721,7 @@ static int nf_tables_newsetelem(struct sk_buff *skb,
 	nft_ctx_init(&ctx, net, skb, info->nlh, family, table, NULL, nla);
 
 	nla_for_each_nested(attr, nla[NFTA_SET_ELEM_LIST_ELEMENTS], rem) {
-		err = nft_add_set_elem(&ctx, set, attr, info->nlh->nlmsg_flags,
-				       nla_is_last(attr, rem));
+		err = nft_add_set_elem(&ctx, set, attr, info->nlh->nlmsg_flags);
 		if (err < 0) {
 			NL_SET_BAD_ATTR(extack, attr);
 			return err;
@@ -7852,7 +7845,7 @@ static void nft_trans_elems_destroy_abort(const struct nft_ctx *ctx,
 }
 
 static int nft_del_setelem(struct nft_ctx *ctx, struct nft_set *set,
-			   const struct nlattr *attr, bool last)
+			   const struct nlattr *attr)
 {
 	struct nlattr *nla[NFTA_SET_ELEM_MAX + 1];
 	struct nft_set_ext_tmpl tmpl;
@@ -7920,11 +7913,6 @@ static int nft_del_setelem(struct nft_ctx *ctx, struct nft_set *set,
 	if (flags)
 		*nft_set_ext_flags(ext) = flags;
 
-	if (last)
-		elem.flags = NFT_SET_ELEM_INTERNAL_LAST;
-	else
-		elem.flags = 0;
-
 	trans = nft_trans_elem_alloc(ctx, NFT_MSG_DELSETELEM, set);
 	if (trans == NULL)
 		goto fail_trans;
@@ -8072,8 +8060,7 @@ static int nf_tables_delsetelem(struct sk_buff *skb,
 		return nft_set_flush(&ctx, set, genmask);
 
 	nla_for_each_nested(attr, nla[NFTA_SET_ELEM_LIST_ELEMENTS], rem) {
-		err = nft_del_setelem(&ctx, set, attr,
-				      nla_is_last(attr, rem));
+		err = nft_del_setelem(&ctx, set, attr);
 		if (err == -ENOENT &&
 		    NFNL_MSG_TYPE(info->nlh->nlmsg_type) == NFT_MSG_DESTROYSETELEM)
 			continue;
net/netfilter/nft_set_rbtree.c +10 -61

136 lines not on this page · raw message

Signature · 1 line
2.51.0
author maintainer
#202 lore raw

PATCH 196/314 ARM: clean up the memset64() C wrapper

In reply to Sasha Levin

From: Thomas Weißschuh <[email protected]>

commit b52343d1cb47bb27ca32a3f4952cc2fd3cd165bf upstream.

The current logic to split the 64-bit argument into its 32-bit halves is byte-order specific and a bit clunky. Use a union instead which is easier to read and works in all cases.

GCC still generates the same machine code.

While at it, rename the arguments of the __memset64() prototype to actually reflect their semantics.

---
 arch/arm/include/asm/string.h | 14 +++++++++-----
 1 file changed, 9 insertions(+), 5 deletions(-)
arch/arm/include/asm/string.h +9 -5
index c35250c4991bc..96fc6cf460ecb 100644
@@ -39,13 +39,17 @@ static inline void *memset32(uint32_t *p, uint32_t v, __kernel_size_t n)
 }
 
 #define __HAVE_ARCH_MEMSET64
-extern void *__memset64(uint64_t *, uint32_t low, __kernel_size_t, uint32_t hi);
+extern void *__memset64(uint64_t *, uint32_t first, __kernel_size_t, uint32_t second);
 static inline void *memset64(uint64_t *p, uint64_t v, __kernel_size_t n)
 {
-	if (IS_ENABLED(CONFIG_CPU_LITTLE_ENDIAN))
-		return __memset64(p, v, n * 8, v >> 32);
-	else
-		return __memset64(p, v >> 32, n * 8, v);
+	union {
+		uint64_t val;
+		struct {
+			uint32_t first, second;
+		};
+	} word = { .val = v };
+
+	return __memset64(p, word.first, n * 8, word.second);
 }
 
 /*
Signature · 1 line
2.51.0
author maintainer
#203 lore raw

PATCH 197/314 ASoC: fsl_xcvr: use dev_err_probe() replacing dev_err() + return

In reply to Sasha Levin

From: Alexander Stein <[email protected]>

commit 8ae28d04593a5fdddb16d3edcdabb8d1e4330d0b upstream.

Use dev_err_probe() to simplify the code. This also silences -517 errors.

---
 sound/soc/fsl/fsl_xcvr.c | 86 ++++++++++++++++------------------------
 1 file changed, 34 insertions(+), 52 deletions(-)
sound/soc/fsl/fsl_xcvr.c +34 -52
index 58db4906a01d5..06434b2c9a0fb 100644
@@ -1548,28 +1548,24 @@ static int fsl_xcvr_probe(struct platform_device *pdev)
 	xcvr->soc_data = of_device_get_match_data(&pdev->dev);
 
 	xcvr->ipg_clk = devm_clk_get(dev, "ipg");
-	if (IS_ERR(xcvr->ipg_clk)) {
-		dev_err(dev, "failed to get ipg clock\n");
-		return PTR_ERR(xcvr->ipg_clk);
-	}
+	if (IS_ERR(xcvr->ipg_clk))
+		return dev_err_probe(dev, PTR_ERR(xcvr->ipg_clk),
+				     "failed to get ipg clock\n");
 
 	xcvr->phy_clk = devm_clk_get(dev, "phy");
-	if (IS_ERR(xcvr->phy_clk)) {
-		dev_err(dev, "failed to get phy clock\n");
-		return PTR_ERR(xcvr->phy_clk);
-	}
+	if (IS_ERR(xcvr->phy_clk))
+		return dev_err_probe(dev, PTR_ERR(xcvr->phy_clk),
+				     "failed to get phy clock\n");
 
 	xcvr->spba_clk = devm_clk_get(dev, "spba");
-	if (IS_ERR(xcvr->spba_clk)) {
-		dev_err(dev, "failed to get spba clock\n");
-		return PTR_ERR(xcvr->spba_clk);
-	}
+	if (IS_ERR(xcvr->spba_clk))
+		return dev_err_probe(dev, PTR_ERR(xcvr->spba_clk),
+				     "failed to get spba clock\n");
 
 	xcvr->pll_ipg_clk = devm_clk_get(dev, "pll_ipg");
-	if (IS_ERR(xcvr->pll_ipg_clk)) {
-		dev_err(dev, "failed to get pll_ipg clock\n");
-		return PTR_ERR(xcvr->pll_ipg_clk);
-	}
+	if (IS_ERR(xcvr->pll_ipg_clk))
+		return dev_err_probe(dev, PTR_ERR(xcvr->pll_ipg_clk),
+				     "failed to get pll_ipg clock\n");
 
 	fsl_asoc_get_pll_clocks(dev, &xcvr->pll8k_clk,
 				&xcvr->pll11k_clk);
@@ -1593,51 +1589,42 @@ static int fsl_xcvr_probe(struct platform_device *pdev)
 
 	xcvr->regmap = devm_regmap_init_mmio_clk(dev, NULL, regs,
 						 &fsl_xcvr_regmap_cfg);
-	if (IS_ERR(xcvr->regmap)) {
-		dev_err(dev, "failed to init XCVR regmap: %ld\n",
-			PTR_ERR(xcvr->regmap));
-		return PTR_ERR(xcvr->regmap);
-	}
+	if (IS_ERR(xcvr->regmap))
+		return dev_err_probe(dev, PTR_ERR(xcvr->regmap), "failed to init XCVR regmap\n");
 
 	if (xcvr->soc_data->use_phy) {
 		xcvr->regmap_phy = devm_regmap_init(dev, NULL, xcvr,
 						    &fsl_xcvr_regmap_phy_cfg);
-		if (IS_ERR(xcvr->regmap_phy)) {
-			dev_err(dev, "failed to init XCVR PHY regmap: %ld\n",
-				PTR_ERR(xcvr->regmap_phy));
-			return PTR_ERR(xcvr->regmap_phy);
-		}
+		if (IS_ERR(xcvr->regmap_phy))
+			return dev_err_probe(dev, PTR_ERR(xcvr->regmap_phy),
+					     "failed to init XCVR PHY regmap\n");
 
 		switch (xcvr->soc_data->pll_ver) {
 		case PLL_MX8MP:
 			xcvr->regmap_pll = devm_regmap_init(dev, NULL, xcvr,
 							    &fsl_xcvr_regmap_pllv0_cfg);
-			if (IS_ERR(xcvr->regmap_pll)) {
-				dev_err(dev, "failed to init XCVR PLL regmap: %ld\n",
-					PTR_ERR(xcvr->regmap_pll));
-				return PTR_ERR(xcvr->regmap_pll);
-			}
+			if (IS_ERR(xcvr->regmap_pll))
+				return dev_err_probe(dev, PTR_ERR(xcvr->regmap_pll),
+						     "failed to init XCVR PLL regmap\n");
 			break;
 		case PLL_MX95:
 			xcvr->regmap_pll = devm_regmap_init(dev, NULL, xcvr,
 							    &fsl_xcvr_regmap_pllv1_cfg);
-			if (IS_ERR(xcvr->regmap_pll)) {
-				dev_err(dev, "failed to init XCVR PLL regmap: %ld\n",
-					PTR_ERR(xcvr->regmap_pll));
-				return PTR_ERR(xcvr->regmap_pll);
-			}
+			if (IS_ERR(xcvr->regmap_pll))
+				return dev_err_probe(dev, PTR_ERR(xcvr->regmap_pll),
+						     "failed to init XCVR PLL regmap\n");
 			break;
 		default:
-			dev_err(dev, "Error for PLL version %d\n", xcvr->soc_data->pll_ver);
-			return -EINVAL;
+			return dev_err_probe(dev, -EINVAL,
+					     "Error for PLL version %d\n",
+					     xcvr->soc_data->pll_ver);
 		}
 	}
 
 	xcvr->reset = devm_reset_control_get_optional_exclusive(dev, NULL);
-	if (IS_ERR(xcvr->reset)) {
-		dev_err(dev, "failed to get XCVR reset control\n");
-		return PTR_ERR(xcvr->reset);
-	}
+	if (IS_ERR(xcvr->reset))
+		return dev_err_probe(dev, PTR_ERR(xcvr->reset),
+				     "failed to get XCVR reset control\n");
 
 	/* get IRQs */
 	irq = platform_get_irq(pdev, 0);
@@ -1645,17 +1632,13 @@ static int fsl_xcvr_probe(struct platform_device *pdev)
 		return irq;
 
 	ret = devm_request_irq(dev, irq, irq0_isr, 0, pdev->name, xcvr);
-	if (ret) {
-		dev_err(dev, "failed to claim IRQ0: %i\n", ret);
-		return ret;
-	}
+	if (ret)
+		return dev_err_probe(dev, ret, "failed to claim IRQ0\n");
 
 	rx_res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "rxfifo");
 	tx_res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "txfifo");
-	if (!rx_res || !tx_res) {
-		dev_err(dev, "could not find rxfifo or txfifo resource\n");
-		return -EINVAL;
-	}
+	if (!rx_res || !tx_res)
+		return dev_err_probe(dev, -EINVAL, "could not find rxfifo or txfifo resource\n");
 	xcvr->dma_prms_rx.chan_name = "rx";
 	xcvr->dma_prms_tx.chan_name = "tx";
 	xcvr->dma_prms_rx.addr = rx_res->start;
@@ -1678,8 +1661,7 @@ static int fsl_xcvr_probe(struct platform_device *pdev)
 	ret = devm_snd_dmaengine_pcm_register(dev, NULL, 0);
 	if (ret) {
 		pm_runtime_disable(dev);
-		dev_err(dev, "failed to pcm register\n");
-		return ret;
+		return dev_err_probe(dev, ret, "failed to pcm register\n");
 	}
 
 	ret = devm_snd_soc_register_component(dev, &fsl_xcvr_comp,
Signature · 1 line
2.51.0
author maintainer
#204 lore raw

PATCH 198/314 ASoC: fsl_xcvr: provide regmap names

In reply to Sasha Levin

From: Alexander Stein <[email protected]>

commit 08fd332eeb88515af4f1892d91f6ef4ea7558b71 upstream.

This driver uses multiple regmaps, which will causes name conflicts in debugfs like:
debugfs: '30cc0000.xcvr' already exists in 'regmap'
Fix this by adding a name for the non-core regmap configurations.

---
 sound/soc/fsl/fsl_xcvr.c | 3 +++
 1 file changed, 3 insertions(+)
sound/soc/fsl/fsl_xcvr.c +3 -0
index 06434b2c9a0fb..a268fb81a2f86 100644
@@ -1323,6 +1323,7 @@ static const struct reg_default fsl_xcvr_phy_reg_defaults[] = {
 };
 
 static const struct regmap_config fsl_xcvr_regmap_phy_cfg = {
+	.name = "phy",
 	.reg_bits = 8,
 	.reg_stride = 4,
 	.val_bits = 32,
@@ -1335,6 +1336,7 @@ static const struct regmap_config fsl_xcvr_regmap_phy_cfg = {
 };
 
 static const struct regmap_config fsl_xcvr_regmap_pllv0_cfg = {
+	.name = "pllv0",
 	.reg_bits = 8,
 	.reg_stride = 4,
 	.val_bits = 32,
@@ -1345,6 +1347,7 @@ static const struct regmap_config fsl_xcvr_regmap_pllv0_cfg = {
 };
 
 static const struct regmap_config fsl_xcvr_regmap_pllv1_cfg = {
+	.name = "pllv1",
 	.reg_bits = 8,
 	.reg_stride = 4,
 	.val_bits = 32,
Signature · 1 line
2.51.0
author maintainer
#205 lore raw

PATCH 199/314 ipmi: Fix use-after-free and list corruption on sender error

In reply to Sasha Levin

From: Corey Minyard <[email protected]>

commit 594c11d0e1d445f580898a2b8c850f2e3f099368 upstream.

The analysis from Breno:

When the SMI sender returns an error, smi_work() delivers an error response but then jumps back to restart without cleaning up properly:

1. intf->curr_msg is not cleared, so no new message is pulled
2. newmsg still points to the message, causing sender() to be called again with the same message
3. If sender() fails again, deliver_err_response() is called with the same recv_msg that was already queued for delivery

This causes list_add corruption ("list_add double add") because the recv_msg is added to the user_msgs list twice. Subsequently, the corrupted list leads to use-after-free when the memory is freed and reused, and eventually a NULL pointer dereference when accessing recv_msg->done.

The buggy sequence:

sender() fails

    -> deliver_err_response(recv_msg)  // recv_msg queued for delivery
    -> goto restart                    // curr_msg not cleared!
  sender() fails again (same message!)
    -> deliver_err_response(recv_msg)  // tries to queue same recv_msg
    -> LIST CORRUPTION

Fix this by freeing the message and setting it to NULL on a send error. Also, always free the newmsg on a send error, otherwise it will leak.

---
 drivers/char/ipmi/ipmi_msghandler.c | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)
drivers/char/ipmi/ipmi_msghandler.c +9 -2
index 0a886399f9daf..5ed8e95589fb7 100644
@@ -4848,8 +4848,15 @@ static void smi_work(struct work_struct *t)
 			if (newmsg->recv_msg)
 				deliver_err_response(intf,
 						     newmsg->recv_msg, cc);
-			else
-				ipmi_free_smi_msg(newmsg);
+			if (!run_to_completion)
+				spin_lock_irqsave(&intf->xmit_msgs_lock,
+						  flags);
+			intf->curr_msg = NULL;
+			if (!run_to_completion)
+				spin_unlock_irqrestore(&intf->xmit_msgs_lock,
+						       flags);
+			ipmi_free_smi_msg(newmsg);
+			newmsg = NULL;
 			goto restart;
 		}
 	}
Signature · 1 line
2.51.0
author maintainer
#206 lore raw

PATCH 200/314 ksmbd: call ksmbd_vfs_kern_path_end_removing() on some error paths

In reply to Sasha Levin

From: Fedor Pchelkin <[email protected]>

[ Upstream commit a09dc10d1353f0e92c21eae2a79af1c2b1ddcde8 ]

There are two places where ksmbd_vfs_kern_path_end_removing() needs to be called in order to balance what the corresponding successful call to ksmbd_vfs_kern_path_start_removing() has done, i.e. drop inode locks and put the taken references. Otherwise there might be potential deadlocks and unbalanced locks which are caught like:

BUG: workqueue leaked lock or atomic: kworker/5:21/0x00000000/7596
     last function: handle_ksmbd_work
2 locks held by kworker/5:21/7596:
 #0: ffff8881051ae448 (sb_writers#3){.+.+}-{0:0}, at: ksmbd_vfs_kern_path_locked+0x142/0x660
 #1: ffff888130e966c0 (&type->i_mutex_dir_key#3/1){+.+.}-{4:4}, at: ksmbd_vfs_kern_path_locked+0x17d/0x660
CPU: 5 PID: 7596 Comm: kworker/5:21 Not tainted 6.1.162-00456-gc29b353f383b #138
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.17.0-debian-1.17.0-1 04/01/2014
Workqueue: ksmbd-io handle_ksmbd_work
Call Trace:
 <TASK>
 dump_stack_lvl+0x44/0x5b
 process_one_work.cold+0x57/0x5c
 worker_thread+0x82/0x600
 kthread+0x153/0x190
 ret_from_fork+0x22/0x30
 </TASK>

Found by Linux Verification Center (linuxtesting.org).

Fixes d5fc1400a34b ("smb/server: avoid deadlock when linking with ReplaceIfExists")
[ ksmbd_vfs_kern_path_end_removing() -> ksmbd_vfs_kern_path_unlock() ]
---
 fs/smb/server/smb2pdu.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)
fs/smb/server/smb2pdu.c +2 -2
index bf8c480594367..e52b9136abbff 100644
@@ -6117,14 +6117,14 @@ static int smb2_create_link(struct ksmbd_work *work,
 				rc = -EINVAL;
 				ksmbd_debug(SMB, "cannot delete %s\n",
 					    link_name);
-				goto out;
 			}
 		} else {
 			rc = -EEXIST;
 			ksmbd_debug(SMB, "link already exists\n");
-			goto out;
 		}
 		ksmbd_vfs_kern_path_unlock(&path);
+		if (rc)
+			goto out;
 	}
 	rc = ksmbd_vfs_link(work, target_name, link_name);
 	if (rc)
Signature · 1 line
2.51.0
author maintainer
#207 lore raw

PATCH 201/314 platform/x86: hp-bioscfg: Support allocations of larger data

In reply to Sasha Levin

From: Mario Limonciello <[email protected]>

[ Upstream commit 916727cfdb72cd01fef3fa6746e648f8cb70e713 ]

Some systems have much larger amounts of enumeration attributes than have been previously encountered. This can lead to page allocation failures when using kcalloc(). Switch over to using kvcalloc() to allow larger allocations.

---
 drivers/platform/x86/hp/hp-bioscfg/enum-attributes.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)
drivers/platform/x86/hp/hp-bioscfg/enum-attributes.c +6 -3
index f346aad8e9d89..af4d1920d4880 100644
@@ -94,8 +94,11 @@ int hp_alloc_enumeration_data(void)
 	bioscfg_drv.enumeration_instances_count =
 		hp_get_instance_count(HP_WMI_BIOS_ENUMERATION_GUID);
 
-	bioscfg_drv.enumeration_data = kcalloc(bioscfg_drv.enumeration_instances_count,
-					       sizeof(*bioscfg_drv.enumeration_data), GFP_KERNEL);
+	if (!bioscfg_drv.enumeration_instances_count)
+		return -EINVAL;
+	bioscfg_drv.enumeration_data = kvcalloc(bioscfg_drv.enumeration_instances_count,
+						sizeof(*bioscfg_drv.enumeration_data), GFP_KERNEL);
+
 	if (!bioscfg_drv.enumeration_data) {
 		bioscfg_drv.enumeration_instances_count = 0;
 		return -ENOMEM;
@@ -444,6 +447,6 @@ void hp_exit_enumeration_attributes(void)
 	}
 	bioscfg_drv.enumeration_instances_count = 0;
 
-	kfree(bioscfg_drv.enumeration_data);
+	kvfree(bioscfg_drv.enumeration_data);
 	bioscfg_drv.enumeration_data = NULL;
 }
Signature · 1 line
2.51.0
author maintainer
#208 lore raw

PATCH 202/314 net: stmmac: remove support for lpi_intr_o

In reply to Sasha Levin

From: "Russell King (Oracle)" <[email protected]>

commit 14eb64db8ff07b58a35b98375f446d9e20765674 upstream.

The dwmac databook for v3.74a states that lpi_intr_o is a sideband signal which should be used to ungate the application clock, and this signal is synchronous to the receive clock. The receive clock can run at 2.5, 25 or 125MHz depending on the media speed, and can stop under the control of the link partner. This means that the time it takes to clear is dependent on the negotiated media speed, and thus can be 8, 40, or 400ns after reading the LPI control and status register.

It has been observed with some aggressive link partners, this clock can stop while lpi_intr_o is still asserted, meaning that the signal remains asserted for an indefinite period that the local system has no direct control over.

The LPI interrupts will still be signalled through the main interrupt path in any case, and this path is not dependent on the receive clock.

This, since we do not gate the application clock, and the chances of adding clock gating in the future are slim due to the clocks being ill-defined, lpi_intr_o serves no useful purpose. Remove the code which requests the interrupt, and all associated code.

---
 drivers/net/ethernet/stmicro/stmmac/common.h  |  1 -
 .../net/ethernet/stmicro/stmmac/dwmac-intel.c |  4 ---
 .../ethernet/stmicro/stmmac/dwmac-loongson.c  |  7 ----
 drivers/net/ethernet/stmicro/stmmac/stmmac.h  |  2 --
 .../net/ethernet/stmicro/stmmac/stmmac_main.c | 36 -------------------
 .../ethernet/stmicro/stmmac/stmmac_platform.c |  8 -----
 include/linux/stmmac.h                        |  1 -
 7 files changed, 59 deletions(-)
drivers/net/ethernet/stmicro/stmmac/common.h +0 -1
index 23ec3a59ca8f1..9e012720a69fa 100644
@@ -381,7 +381,6 @@ enum request_irq_err {
 	REQ_IRQ_ERR_SFTY,
 	REQ_IRQ_ERR_SFTY_UE,
 	REQ_IRQ_ERR_SFTY_CE,
-	REQ_IRQ_ERR_LPI,
 	REQ_IRQ_ERR_WOL,
 	REQ_IRQ_ERR_MAC,
 	REQ_IRQ_ERR_NO,
drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c +0 -4
index b2194e414ec1f..47fda982d6b15 100644
@@ -759,7 +759,6 @@ static int intel_mgbe_common_data(struct pci_dev *pdev,
 
 	/* Setup MSI vector offset specific to Intel mGbE controller */
 	plat->msi_mac_vec = 29;
-	plat->msi_lpi_vec = 28;
 	plat->msi_sfty_ce_vec = 27;
 	plat->msi_sfty_ue_vec = 26;
 	plat->msi_rx_base_vec = 0;
@@ -1217,8 +1216,6 @@ static int stmmac_config_multi_msi(struct pci_dev *pdev,
 		res->irq = pci_irq_vector(pdev, plat->msi_mac_vec);
 	if (plat->msi_wol_vec < STMMAC_MSI_VEC_MAX)
 		res->wol_irq = pci_irq_vector(pdev, plat->msi_wol_vec);
-	if (plat->msi_lpi_vec < STMMAC_MSI_VEC_MAX)
-		res->lpi_irq = pci_irq_vector(pdev, plat->msi_lpi_vec);
 	if (plat->msi_sfty_ce_vec < STMMAC_MSI_VEC_MAX)
 		res->sfty_ce_irq = pci_irq_vector(pdev, plat->msi_sfty_ce_vec);
 	if (plat->msi_sfty_ue_vec < STMMAC_MSI_VEC_MAX)
@@ -1334,7 +1331,6 @@ static int intel_eth_pci_probe(struct pci_dev *pdev,
 	 */
 	plat->msi_mac_vec = STMMAC_MSI_VEC_MAX;
 	plat->msi_wol_vec = STMMAC_MSI_VEC_MAX;
-	plat->msi_lpi_vec = STMMAC_MSI_VEC_MAX;
 	plat->msi_sfty_ce_vec = STMMAC_MSI_VEC_MAX;
 	plat->msi_sfty_ue_vec = STMMAC_MSI_VEC_MAX;
 	plat->msi_rx_base_vec = STMMAC_MSI_VEC_MAX;
drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c +0 -7
index 47bc3aeee857d..ab431bf9b25f2 100644
@@ -465,13 +465,6 @@ static int loongson_dwmac_dt_config(struct pci_dev *pdev,
 		res->wol_irq = res->irq;
 	}
 
-	res->lpi_irq = of_irq_get_byname(np, "eth_lpi");
-	if (res->lpi_irq < 0) {
-		dev_err(&pdev->dev, "IRQ eth_lpi not found\n");
-		ret = -ENODEV;
-		goto err_put_node;
-	}
-
 	ret = device_get_phy_mode(&pdev->dev);
 	if (ret < 0) {
 		dev_err(&pdev->dev, "phy_mode not found\n");
drivers/net/ethernet/stmicro/stmmac/stmmac.h +0 -2
index 7ca5477be390b..c42cead28de98 100644
@@ -29,7 +29,6 @@ struct stmmac_resources {
 	void __iomem *addr;
 	u8 mac[ETH_ALEN];
 	int wol_irq;
-	int lpi_irq;
 	int irq;
 	int sfty_irq;
 	int sfty_ce_irq;
@@ -291,7 +290,6 @@ struct stmmac_priv {
 	int wol_irq;
 	u32 gmii_address_bus_config;
 	struct timer_list eee_ctrl_timer;
-	int lpi_irq;
 	u32 tx_lpi_timer;
 	bool tx_lpi_clk_stop;
 	bool eee_enabled;
drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +0 -36
index 46299b7925b44..754b36e733eb5 100644
@@ -3579,10 +3579,6 @@ static void stmmac_free_irq(struct net_device *dev,
 			free_irq(priv->sfty_ce_irq, dev);
 		fallthrough;
 	case REQ_IRQ_ERR_SFTY_CE:
-		if (priv->lpi_irq > 0 && priv->lpi_irq != dev->irq)
-			free_irq(priv->lpi_irq, dev);
-		fallthrough;
-	case REQ_IRQ_ERR_LPI:
 		if (priv->wol_irq > 0 && priv->wol_irq != dev->irq)
 			free_irq(priv->wol_irq, dev);
 		fallthrough;
@@ -3640,24 +3636,6 @@ static int stmmac_request_irq_multi_msi(struct net_device *dev)
 		}
 	}
 
-	/* Request the LPI IRQ in case of another line
-	 * is used for LPI
-	 */
-	if (priv->lpi_irq > 0 && priv->lpi_irq != dev->irq) {
-		int_name = priv->int_name_lpi;
-		sprintf(int_name, "%s:%s", dev->name, "lpi");
-		ret = request_irq(priv->lpi_irq,
-				  stmmac_mac_interrupt,
-				  0, int_name, dev);
-		if (unlikely(ret < 0)) {
-			netdev_err(priv->dev,
-				   "%s: alloc lpi MSI %d (error: %d)\n",
-				   __func__, priv->lpi_irq, ret);
-			irq_err = REQ_IRQ_ERR_LPI;
-			goto irq_error;
-		}
-	}
-
 	/* Request the common Safety Feature Correctible/Uncorrectible
 	 * Error line in case of another line is used
 	 */
@@ -3797,19 +3775,6 @@ static int stmmac_request_irq_single(struct net_device *dev)
 		}
 	}
 
-	/* Request the IRQ lines */
-	if (priv->lpi_irq > 0 && priv->lpi_irq != dev->irq) {
-		ret = request_irq(priv->lpi_irq, stmmac_interrupt,
-				  IRQF_SHARED, dev->name, dev);
-		if (unlikely(ret < 0)) {
-			netdev_err(priv->dev,
-				   "%s: ERROR: allocating the LPI IRQ %d (%d)\n",
-				   __func__, priv->lpi_irq, ret);
-			irq_err = REQ_IRQ_ERR_LPI;
-			goto irq_error;
-		}
-	}
-
 	/* Request the common Safety Feature Correctible/Uncorrectible
 	 * Error line in case of another line is used
 	 */
@@ -7445,7 +7410,6 @@ int stmmac_dvr_probe(struct device *device,
 
 	priv->dev->irq = res->irq;
 	priv->wol_irq = res->wol_irq;
-	priv->lpi_irq = res->lpi_irq;
 	priv->sfty_irq = res->sfty_irq;
 	priv->sfty_ce_irq = res->sfty_ce_irq;
 	priv->sfty_ue_irq = res->sfty_ue_irq;
drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +0 -8
index fbb92cc6ab598..0cb51935c4056 100644
@@ -761,14 +761,6 @@ int stmmac_get_platform_resources(struct platform_device *pdev,
 		stmmac_res->wol_irq = stmmac_res->irq;
 	}
 
-	stmmac_res->lpi_irq =
-		platform_get_irq_byname_optional(pdev, "eth_lpi");
-	if (stmmac_res->lpi_irq < 0) {
-		if (stmmac_res->lpi_irq == -EPROBE_DEFER)
-			return -EPROBE_DEFER;
-		dev_info(&pdev->dev, "IRQ eth_lpi not found\n");
-	}
-
 	stmmac_res->sfty_irq =
 		platform_get_irq_byname_optional(pdev, "sfty");
 	if (stmmac_res->sfty_irq < 0) {
include/linux/stmmac.h +0 -1
index 151c81c560c8c..7e989d0edead2 100644
@@ -296,7 +296,6 @@ struct plat_stmmacenet_data {
 	int int_snapshot_num;
 	int msi_mac_vec;
 	int msi_wol_vec;
-	int msi_lpi_vec;
 	int msi_sfty_ce_vec;
 	int msi_sfty_ue_vec;
 	int msi_rx_base_vec;
Signature · 1 line
2.51.0
author maintainer
#209 lore raw

PATCH 203/314 Bluetooth: Fix CIS host feature condition

In reply to Sasha Levin

From: Mariusz Skamra <[email protected]>

commit 7cff9a40c6b0f72ccefdaf0ffe03cfac30348f51 upstream.

This fixes the condition for sending the LE Set Host Feature command. The command is sent to indicate host support for Connected Isochronous Streams in this case. It has been observed that the system could not initialize BIS-only capable controllers because the controllers do not support the command.

As per Core v6.2 | Vol 4, Part E, Table 3.1 the command shall be supported if CIS Central or CIS Peripheral is supported; otherwise, the command is optional.

Fixes 709788b154ca ("Bluetooth: hci_core: Fix using {cis,bis}_capable for current settings")
[ iso_capable() => cis_capable() ]
---
 net/bluetooth/hci_sync.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
net/bluetooth/hci_sync.c +1 -1
index cc1d340a32c62..9f01837250a5e 100644
@@ -4546,7 +4546,7 @@ static int hci_le_set_host_feature_sync(struct hci_dev *hdev)
 {
 	struct hci_cp_le_set_host_feature cp;
 
-	if (!iso_capable(hdev))
+	if (!cis_capable(hdev))
 		return 0;
 
 	memset(&cp, 0, sizeof(cp));
Signature · 1 line
2.51.0
author maintainer
#210 lore raw

PATCH 204/314 drm/amd/display: Use GFP_ATOMIC in dc_create_stream_for_sink

In reply to Sasha Levin

From: Natalie Vock <[email protected]>

commit 28dfe4317541e57fe52f9a290394cd29c348228b upstream.

This can be called while preemption is disabled, for example by dcn32_internal_validate_bw which is called with the FPU active.

Fixes "BUG: scheduling while atomic" messages I encounter on my Navi31 machine.

(cherry picked from commit b42dae2ebc5c84a68de63ec4ffdfec49362d53f1)
[ Context ]
---
 drivers/gpu/drm/amd/display/dc/core/dc_stream.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/gpu/drm/amd/display/dc/core/dc_stream.c +1 -1
index 0a46e834357a1..0886bef32a5de 100644
@@ -169,7 +169,7 @@ struct dc_stream_state *dc_create_stream_for_sink(
 	if (sink == NULL)
 		return NULL;
 
-	stream = kzalloc(sizeof(struct dc_stream_state), GFP_KERNEL);
+	stream = kzalloc(sizeof(struct dc_stream_state), GFP_ATOMIC);
 	if (stream == NULL)
 		goto alloc_fail;
 
Signature · 1 line
2.51.0
author maintainer
#211 lore raw

PATCH 205/314 nvme: fix admin queue leak on controller reset

In reply to Sasha Levin

From: Ming Lei <[email protected]>

[ Upstream commit b84bb7bd913d8ca2f976ee6faf4a174f91c02b8d ]

When nvme_alloc_admin_tag_set() is called during a controller reset, a previous admin queue may still exist. Release it properly before allocating a new one to avoid orphaning the old queue.

This fixes a regression introduced by commit 03b3bcd319b3 ("nvme: fix admin request_queue lifetime").

---
 drivers/nvme/host/core.c | 7 +++++++
 1 file changed, 7 insertions(+)
drivers/nvme/host/core.c +7 -0
index f1f719351f3f2..2ba7244fdaf1c 100644
@@ -4865,6 +4865,13 @@ int nvme_alloc_admin_tag_set(struct nvme_ctrl *ctrl, struct blk_mq_tag_set *set,
 	if (ret)
 		return ret;
 
+	/*
+	 * If a previous admin queue exists (e.g., from before a reset),
+	 * put it now before allocating a new one to avoid orphaning it.
+	 */
+	if (ctrl->admin_q)
+		blk_put_queue(ctrl->admin_q);
+
 	ctrl->admin_q = blk_mq_alloc_queue(set, &lim, NULL);
 	if (IS_ERR(ctrl->admin_q)) {
 		ret = PTR_ERR(ctrl->admin_q);
Signature · 1 line
2.51.0
author maintainer
#212 lore raw

PATCH 206/314 hwmon: (aht10) Add support for dht20

In reply to Sasha Levin

From: Akhilesh Patil <[email protected]>

[ Upstream commit 3eaf1b631506e8de2cb37c278d5bc042521e82c1 ]

Add support for dht20 temperature and humidity sensor from Aosong. Modify aht10 driver to handle different init command for dht20 sensor by adding init_cmd entry in the driver data. dht20 sensor is compatible with aht10 hwmon driver with this change.

Tested on TI am62x SK board with dht20 sensor connected at i2c-2 port.

Stable-dep-of: b7497b5a99f5 ("hwmon: (aht10) Fix initialization commands for AHT20")

---
 Documentation/hwmon/aht10.rst | 10 +++++++++-
 drivers/hwmon/Kconfig         |  6 +++---
 drivers/hwmon/aht10.c         | 19 ++++++++++++++++---
 3 files changed, 28 insertions(+), 7 deletions(-)
Documentation/hwmon/aht10.rst +9 -1
index 213644b4ecba6..7903b6434326d 100644
@@ -20,6 +20,14 @@ Supported chips:
 
       English: http://www.aosong.com/userfiles/files/media/Data%20Sheet%20AHT20.pdf
 
+  * Aosong DHT20
+
+    Prefix: 'dht20'
+
+    Addresses scanned: None
+
+    Datasheet: https://www.digikey.co.nz/en/htmldatasheets/production/9184855/0/0/1/101020932
+
 Author: Johannes Cornelis Draaijer <[email protected]>
 
 
@@ -33,7 +41,7 @@ The address of this i2c device may only be 0x38
 Special Features
 ----------------
 
-AHT20 has additional CRC8 support which is sent as the last byte of the sensor
+AHT20, DHT20 has additional CRC8 support which is sent as the last byte of the sensor
 values.
 
 Usage Notes
drivers/hwmon/Kconfig +3 -3
index 2760feb9f83b5..2a71b6e834b08 100644
@@ -245,12 +245,12 @@ config SENSORS_ADT7475
 	  will be called adt7475.
 
 config SENSORS_AHT10
-	tristate "Aosong AHT10, AHT20"
+	tristate "Aosong AHT10, AHT20, DHT20"
 	depends on I2C
 	select CRC8
 	help
-	  If you say yes here, you get support for the Aosong AHT10 and AHT20
-	  temperature and humidity sensors
+	  If you say yes here, you get support for the Aosong AHT10, AHT20 and
+	  DHT20 temperature and humidity sensors
 
 	  This driver can also be built as a module. If so, the module
 	  will be called aht10.
drivers/hwmon/aht10.c +16 -3
index d1c55e2eb4799..a153282eef6a2 100644
@@ -37,6 +37,8 @@
 #define AHT10_CMD_MEAS	0b10101100
 #define AHT10_CMD_RST	0b10111010
 
+#define DHT20_CMD_INIT	0x71
+
 /*
  * Flags in the answer byte/command
  */
@@ -48,11 +50,12 @@
 
 #define AHT10_MAX_POLL_INTERVAL_LEN	30
 
-enum aht10_variant { aht10, aht20 };
+enum aht10_variant { aht10, aht20, dht20};
 
 static const struct i2c_device_id aht10_id[] = {
 	{ "aht10", aht10 },
 	{ "aht20", aht20 },
+	{ "dht20", dht20 },
 	{ },
 };
 MODULE_DEVICE_TABLE(i2c, aht10_id);
@@ -77,6 +80,7 @@ MODULE_DEVICE_TABLE(i2c, aht10_id);
  *              AHT10/AHT20
  *   @crc8: crc8 support flag
  *   @meas_size: measurements data size
+ *   @init_cmd: Initialization command
  */
 
 struct aht10_data {
@@ -92,6 +96,7 @@ struct aht10_data {
 	int humidity;
 	bool crc8;
 	unsigned int meas_size;
+	u8 init_cmd;
 };
 
 /*
@@ -101,13 +106,13 @@ struct aht10_data {
  */
 static int aht10_init(struct aht10_data *data)
 {
-	const u8 cmd_init[] = {AHT10_CMD_INIT, AHT10_CAL_ENABLED | AHT10_MODE_CYC,
+	const u8 cmd_init[] = {data->init_cmd, AHT10_CAL_ENABLED | AHT10_MODE_CYC,
 			       0x00};
 	int res;
 	u8 status;
 	struct i2c_client *client = data->client;
 
-	res = i2c_master_send(client, cmd_init, 3);
+	res = i2c_master_send(client, cmd_init, sizeof(cmd_init));
 	if (res < 0)
 		return res;
 
@@ -352,9 +357,17 @@ static int aht10_probe(struct i2c_client *client)
 		data->meas_size = AHT20_MEAS_SIZE;
 		data->crc8 = true;
 		crc8_populate_msb(crc8_table, AHT20_CRC8_POLY);
+		data->init_cmd = AHT10_CMD_INIT;
+		break;
+	case dht20:
+		data->meas_size = AHT20_MEAS_SIZE;
+		data->crc8 = true;
+		crc8_populate_msb(crc8_table, AHT20_CRC8_POLY);
+		data->init_cmd = DHT20_CMD_INIT;
 		break;
 	default:
 		data->meas_size = AHT10_MEAS_SIZE;
+		data->init_cmd = AHT10_CMD_INIT;
 		break;
 	}
 
Signature · 1 line
2.51.0
author maintainer
#213 lore raw

PATCH 207/314 hwmon: (aht10) Fix initialization commands for AHT20

In reply to Sasha Levin

From: Hao Yu <[email protected]>

[ Upstream commit b7497b5a99f54ab8dcda5b14a308385b2fb03d8d ]

According to the AHT20 datasheet (updated to V1.0 after the 2023.09 version), the initialization command for AHT20 is 0b10111110 (0xBE). The previous sequence (0xE1) used in earlier versions is no longer compatible with newer AHT20 sensors. Update the initialization command to ensure the sensor is properly initialized.

While at it, use binary notation for DHT20_CMD_INIT to match the notation used in the datasheet.

Fixes d2abcb5cc885 ("hwmon: (aht10) Add support for compatible aht20")
---
 drivers/hwmon/aht10.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)
drivers/hwmon/aht10.c +4 -2
index a153282eef6a2..7ba00bafb57d6 100644
@@ -37,7 +37,9 @@
 #define AHT10_CMD_MEAS	0b10101100
 #define AHT10_CMD_RST	0b10111010
 
-#define DHT20_CMD_INIT	0x71
+#define AHT20_CMD_INIT	0b10111110
+
+#define DHT20_CMD_INIT	0b01110001
 
 /*
  * Flags in the answer byte/command
@@ -357,7 +359,7 @@ static int aht10_probe(struct i2c_client *client)
 		data->meas_size = AHT20_MEAS_SIZE;
 		data->crc8 = true;
 		crc8_populate_msb(crc8_table, AHT20_CRC8_POLY);
-		data->init_cmd = AHT10_CMD_INIT;
+		data->init_cmd = AHT20_CMD_INIT;
 		break;
 	case dht20:
 		data->meas_size = AHT20_MEAS_SIZE;
Signature · 1 line
2.51.0
author maintainer
#214 lore raw

PATCH 208/314 pinctrl: equilibrium: rename irq_chip function callbacks

In reply to Sasha Levin

From: Florian Eckert <[email protected]>

[ Upstream commit 1f96b84835eafb3e6f366dc3a66c0e69504cec9d ]

Renaming of the irq_chip callback functions to improve clarity.

Stable-dep-of: 3e00b1b332e5 ("pinctrl: equilibrium: fix warning trace on load")

---
 drivers/pinctrl/pinctrl-equilibrium.c | 24 ++++++++++++------------
 1 file changed, 12 insertions(+), 12 deletions(-)
drivers/pinctrl/pinctrl-equilibrium.c +12 -12
index 48b55c5bf8d4f..49c8232b525a9 100644
@@ -23,7 +23,7 @@
 #define PIN_NAME_LEN	10
 #define PAD_REG_OFF	0x100
 
-static void eqbr_gpio_disable_irq(struct irq_data *d)
+static void eqbr_irq_mask(struct irq_data *d)
 {
 	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
 	struct eqbr_gpio_ctrl *gctrl = gpiochip_get_data(gc);
@@ -36,7 +36,7 @@ static void eqbr_gpio_disable_irq(struct irq_data *d)
 	gpiochip_disable_irq(gc, offset);
 }
 
-static void eqbr_gpio_enable_irq(struct irq_data *d)
+static void eqbr_irq_unmask(struct irq_data *d)
 {
 	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
 	struct eqbr_gpio_ctrl *gctrl = gpiochip_get_data(gc);
@@ -50,7 +50,7 @@ static void eqbr_gpio_enable_irq(struct irq_data *d)
 	raw_spin_unlock_irqrestore(&gctrl->lock, flags);
 }
 
-static void eqbr_gpio_ack_irq(struct irq_data *d)
+static void eqbr_irq_ack(struct irq_data *d)
 {
 	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
 	struct eqbr_gpio_ctrl *gctrl = gpiochip_get_data(gc);
@@ -62,10 +62,10 @@ static void eqbr_gpio_ack_irq(struct irq_data *d)
 	raw_spin_unlock_irqrestore(&gctrl->lock, flags);
 }
 
-static void eqbr_gpio_mask_ack_irq(struct irq_data *d)
+static void eqbr_irq_mask_ack(struct irq_data *d)
 {
-	eqbr_gpio_disable_irq(d);
-	eqbr_gpio_ack_irq(d);
+	eqbr_irq_mask(d);
+	eqbr_irq_ack(d);
 }
 
 static inline void eqbr_cfg_bit(void __iomem *addr,
@@ -92,7 +92,7 @@ static int eqbr_irq_type_cfg(struct gpio_irq_type *type,
 	return 0;
 }
 
-static int eqbr_gpio_set_irq_type(struct irq_data *d, unsigned int type)
+static int eqbr_irq_set_type(struct irq_data *d, unsigned int type)
 {
 	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
 	struct eqbr_gpio_ctrl *gctrl = gpiochip_get_data(gc);
@@ -166,11 +166,11 @@ static void eqbr_irq_handler(struct irq_desc *desc)
 
 static const struct irq_chip eqbr_irq_chip = {
 	.name = "gpio_irq",
-	.irq_mask = eqbr_gpio_disable_irq,
-	.irq_unmask = eqbr_gpio_enable_irq,
-	.irq_ack = eqbr_gpio_ack_irq,
-	.irq_mask_ack = eqbr_gpio_mask_ack_irq,
-	.irq_set_type = eqbr_gpio_set_irq_type,
+	.irq_ack = eqbr_irq_ack,
+	.irq_mask = eqbr_irq_mask,
+	.irq_mask_ack = eqbr_irq_mask_ack,
+	.irq_unmask = eqbr_irq_unmask,
+	.irq_set_type = eqbr_irq_set_type,
 	.flags = IRQCHIP_IMMUTABLE,
 	GPIOCHIP_IRQ_RESOURCE_HELPERS,
 };
Signature · 1 line
2.51.0
author maintainer
#215 lore raw

PATCH 209/314 pinctrl: equilibrium: fix warning trace on load

In reply to Sasha Levin

From: Florian Eckert <[email protected]>

[ Upstream commit 3e00b1b332e54ba50cca6691f628b9c06574024f ]

The callback functions 'eqbr_irq_mask()' and 'eqbr_irq_ack()' are also called in the callback function 'eqbr_irq_mask_ack()'. This is done to avoid source code duplication. The problem, is that in the function 'eqbr_irq_mask()' also calles the gpiolib function 'gpiochip_disable_irq()'

This generates the following warning trace in the log for every gpio on load.

[    6.088111] ------------[ cut here ]------------
[    6.092440] WARNING: CPU: 3 PID: 1 at drivers/gpio/gpiolib.c:3810 gpiochip_disable_irq+0x39/0x50
[    6.097847] Modules linked in:
[    6.097847] CPU: 3 UID: 0 PID: 1 Comm: swapper/0 Tainted: G        W          6.12.59+ #0
[    6.097847] Tainted: [W]=WARN
[    6.097847] RIP: 0010:gpiochip_disable_irq+0x39/0x50
[    6.097847] Code: 39 c6 48 19 c0 21 c6 48 c1 e6 05 48 03 b2 38 03 00 00 48 81 fe 00 f0 ff ff 77 11 48 8b 46 08 f6 c4 02 74 06 f0 80 66 09 fb c3 <0f> 0b 90 0f 1f 40 00 c3 66 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 40
[    6.097847] RSP: 0000:ffffc9000000b830 EFLAGS: 00010046
[    6.097847] RAX: 0000000000000045 RBX: ffff888001be02a0 RCX: 0000000000000008
[    6.097847] RDX: ffff888001be9000 RSI: ffff888001b2dd00 RDI: ffff888001be02a0
[    6.097847] RBP: ffffc9000000b860 R08: 0000000000000000 R09: 0000000000000000
[    6.097847] R10: 0000000000000001 R11: ffff888001b2a154 R12: ffff888001be0514
[    6.097847] R13: ffff888001be02a0 R14: 0000000000000008 R15: 0000000000000000
[    6.097847] FS:  0000000000000000(0000) GS:ffff888041d80000(0000) knlGS:0000000000000000
[    6.097847] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[    6.097847] CR2: 0000000000000000 CR3: 0000000003030000 CR4: 00000000001026b0
[    6.097847] Call Trace:
[    6.097847]  <TASK>
[    6.097847]  ? eqbr_irq_mask+0x63/0x70
[    6.097847]  ? no_action+0x10/0x10
[    6.097847]  eqbr_irq_mask_ack+0x11/0x60

In an other driver (drivers/pinctrl/starfive/pinctrl-starfive-jh7100.c) the interrupt is not disabled here.

To fix this, do not call the 'eqbr_irq_mask()' and 'eqbr_irq_ack()' function. Implement instead this directly without disabling the interrupts.

Fixes 52066a53bd11 ("pinctrl: equilibrium: Convert to immutable irq_chip")
---
 drivers/pinctrl/pinctrl-equilibrium.c | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)
drivers/pinctrl/pinctrl-equilibrium.c +9 -2
index 49c8232b525a9..ba1c867b7b891 100644
@@ -64,8 +64,15 @@ static void eqbr_irq_ack(struct irq_data *d)
 
 static void eqbr_irq_mask_ack(struct irq_data *d)
 {
-	eqbr_irq_mask(d);
-	eqbr_irq_ack(d);
+	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
+	struct eqbr_gpio_ctrl *gctrl = gpiochip_get_data(gc);
+	unsigned int offset = irqd_to_hwirq(d);
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&gctrl->lock, flags);
+	writel(BIT(offset), gctrl->membase + GPIO_IRNENCLR);
+	writel(BIT(offset), gctrl->membase + GPIO_IRNCR);
+	raw_spin_unlock_irqrestore(&gctrl->lock, flags);
 }
 
 static inline void eqbr_cfg_bit(void __iomem *addr,
Signature · 1 line
2.51.0
author maintainer
#216 lore raw

PATCH 210/314 pinctrl: qcom: qcs615: Add missing dual edge GPIO IRQ errata flag

In reply to Sasha Levin

From: Maulik Shah <[email protected]>

[ Upstream commit 09a30b7a035f9f4ac918c8a9af89d70e43462152 ]

Wakeup capable GPIOs uses PDC as parent IRQ chip and PDC on qcs615 do not support dual edge IRQs. Add missing wakeirq_dual_edge_errata configuration to enable workaround for dual edge GPIO IRQs.

Fixes b698f36a9d40 ("pinctrl: qcom: add the tlmm driver for QCS615 platform")
---
 drivers/pinctrl/qcom/pinctrl-qcs615.c | 1 +
 1 file changed, 1 insertion(+)
drivers/pinctrl/qcom/pinctrl-qcs615.c +1 -0
index 4dfa820d4e77c..f1c827ddbfbfa 100644
@@ -1067,6 +1067,7 @@ static const struct msm_pinctrl_soc_data qcs615_tlmm = {
 	.ntiles = ARRAY_SIZE(qcs615_tiles),
 	.wakeirq_map = qcs615_pdc_map,
 	.nwakeirq_map = ARRAY_SIZE(qcs615_pdc_map),
+	.wakeirq_dual_edge_errata = true,
 };
 
 static const struct of_device_id qcs615_tlmm_of_match[] = {
Signature · 1 line
2.51.0
author maintainer
#217 lore raw

PATCH 211/314 platform/x86: thinkpad_acpi: Fix errors reading battery thresholds

In reply to Sasha Levin

From: Jonathan Teh <[email protected]>

[ Upstream commit 53e977b1d50c46f2c4ec3865cd13a822f58ad3cd ]

Check whether the battery supports the relevant charge threshold before reading the value to silence these errors:

thinkpad_acpi: acpi_evalf(BCTG, dd, ...) failed: AE_NOT_FOUND
ACPI: \_SB_.PCI0.LPC_.EC__.HKEY: BCTG: evaluate failed
thinkpad_acpi: acpi_evalf(BCSG, dd, ...) failed: AE_NOT_FOUND
ACPI: \_SB_.PCI0.LPC_.EC__.HKEY: BCSG: evaluate failed

when reading the charge thresholds via sysfs on platforms that do not support them such as the ThinkPad T400.

---
 drivers/platform/x86/lenovo/thinkpad_acpi.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)
drivers/platform/x86/lenovo/thinkpad_acpi.c +4 -2
index cc19fe520ea96..075543cd0e77e 100644
@@ -9525,14 +9525,16 @@ static int tpacpi_battery_get(int what, int battery, int *ret)
 {
 	switch (what) {
 	case THRESHOLD_START:
-		if ACPI_FAILURE(tpacpi_battery_acpi_eval(GET_START, ret, battery))
+		if (!battery_info.batteries[battery].start_support ||
+		    ACPI_FAILURE(tpacpi_battery_acpi_eval(GET_START, ret, battery)))
 			return -ENODEV;
 
 		/* The value is in the low 8 bits of the response */
 		*ret = *ret & 0xFF;
 		return 0;
 	case THRESHOLD_STOP:
-		if ACPI_FAILURE(tpacpi_battery_acpi_eval(GET_STOP, ret, battery))
+		if (!battery_info.batteries[battery].stop_support ||
+		    ACPI_FAILURE(tpacpi_battery_acpi_eval(GET_STOP, ret, battery)))
 			return -ENODEV;
 		/* Value is in lower 8 bits */
 		*ret = *ret & 0xFF;
Signature · 1 line
2.51.0
author maintainer
#218 lore raw

PATCH 212/314 module: Remove duplicate freeing of lockdep classes

In reply to Sasha Levin

From: Petr Pavlu <[email protected]>

[ Upstream commit a7b4bc094fbaa7dc7b7b91ae33549bbd7eefaac1 ]

In the error path of load_module(), under the free_module label, the code calls lockdep_free_key_range() to release lock classes associated with the MOD_DATA, MOD_RODATA and MOD_RO_AFTER_INIT module regions, and subsequently invokes module_deallocate().

Since commit ac3b43283923 ("module: replace module_layout with module_memory"), the module_deallocate() function calls free_mod_mem(), which releases the lock classes as well and considers all module regions.

Attempting to free these classes twice is unnecessary. Remove the redundant code in load_module().

---
 kernel/module/main.c | 6 ------
 1 file changed, 6 deletions(-)
kernel/module/main.c +0 -6
index c66b261849362..a2c798d06e3f5 100644
@@ -3544,12 +3544,6 @@ static int load_module(struct load_info *info, const char __user *uargs,
 	mutex_unlock(&module_mutex);
  free_module:
 	mod_stat_bump_invalid(info, flags);
-	/* Free lock-classes; relies on the preceding sync_rcu() */
-	for_class_mod_mem_type(type, core_data) {
-		lockdep_free_key_range(mod->mem[type].base,
-				       mod->mem[type].size);
-	}
-
 	module_memory_restore_rox(mod);
 	module_deallocate(mod, info);
  free_copy:
Signature · 1 line
2.51.0
author maintainer
#219 lore raw

PATCH 213/314 HID: multitouch: new class MT_CLS_EGALAX_P80H84

In reply to Sasha Levin

From: Ian Ray <[email protected]>

[ Upstream commit a2e70a89fa58133521b2deae4427d35776bda935 ]

Fixes f9e82295eec1 ("HID: multitouch: add eGalaxTouch P80H84 support")
---
 drivers/hid/hid-multitouch.c | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)
drivers/hid/hid-multitouch.c +9 -2
index 1f8accb7ff435..af19e089b0122 100644
@@ -233,6 +233,7 @@ static void mt_post_parse(struct mt_device *td, struct mt_application *app);
 #define MT_CLS_SMART_TECH			0x0113
 #define MT_CLS_APPLE_TOUCHBAR			0x0114
 #define MT_CLS_YOGABOOK9I			0x0115
+#define MT_CLS_EGALAX_P80H84			0x0116
 #define MT_CLS_SIS				0x0457
 
 #define MT_DEFAULT_MAXCONTACT	10
@@ -447,6 +448,11 @@ static const struct mt_class mt_classes[] = {
 			MT_QUIRK_YOGABOOK9I,
 		.export_all_inputs = true
 	},
+	{ .name = MT_CLS_EGALAX_P80H84,
+		.quirks = MT_QUIRK_ALWAYS_VALID |
+			MT_QUIRK_IGNORE_DUPLICATES |
+			MT_QUIRK_CONTACT_CNT_ACCURATE,
+	},
 	{ }
 };
 
@@ -2223,8 +2229,9 @@ static const struct hid_device_id mt_devices[] = {
 	{ .driver_data = MT_CLS_EGALAX_SERIAL,
 		MT_USB_DEVICE(USB_VENDOR_ID_DWAV,
 			USB_DEVICE_ID_DWAV_EGALAX_MULTITOUCH_C000) },
-	{ .driver_data = MT_CLS_EGALAX,
-		MT_USB_DEVICE(USB_VENDOR_ID_DWAV,
+	{ .driver_data = MT_CLS_EGALAX_P80H84,
+		HID_DEVICE(HID_BUS_ANY, HID_GROUP_MULTITOUCH_WIN_8,
+			USB_VENDOR_ID_DWAV,
 			USB_DEVICE_ID_DWAV_EGALAX_MULTITOUCH_C002) },
 
 	/* Elan devices */
Signature · 1 line
2.51.0
author maintainer
#220 lore raw

PATCH 214/314 pinctrl: generic: move function to amlogic-am4 driver

In reply to Sasha Levin

From: Conor Dooley <[email protected]>

[ Upstream commit 9c5a40f2922a5a6d6b42e7b3d4c8e253918c07a1 ]

pinconf_generic_dt_node_to_map_pinmux() is not actually a generic function, and really belongs in the amlogic-am4 driver. There are three reasons why.

First, and least, of the reasons is that this function behaves differently to the other dt_node_to_map functions in a way that is not obvious from a first glance. This difference stems for the devicetree properties that the function is intended for use with, and how they are typically used. The other generic dt_node_to_map functions support platforms where the pins, groups and functions are described statically in the driver and require a function that will produce a mapping from dt nodes to these pre-established descriptions. No other code in the driver is require to be executed at runtime. pinconf_generic_dt_node_to_map_pinmux() on the other hand is intended for use with the pinmux property, where groups and functions are determined entirely from the devicetree. As a result, there are no statically defined groups and functions in the driver for this function to perform a mapping to. Other drivers that use the pinmux property (e.g. the k1) their dt_node_to_map function creates the groups and functions as the devicetree is parsed. Instead of that, pinconf_generic_dt_node_to_map_pinmux() requires that the devicetree is parsed twice, once by it and once at probe, so that the driver dynamically creates the groups and functions before the dt_node_to_map callback is executed. I don't believe this double parsing requirement is how developers would expect this to work and is not necessary given there are drivers that do not have this behaviour.

Secondly and thirdly, the function bakes in some assumptions that only really match the amlogic platform about how the devicetree is constructed. These, to me, are problematic for something that claims to be generic.

The other dt_node_to_map implementations accept a being called for either a node containing pin configuration properties or a node containing child nodes that each contain the configuration properties. IOW, they support the following two devicetree configurations:

| cfg {
| 	label: group {
| 		pinmux = <asjhdasjhlajskd>;
| 		config-item1;
| 	};
| };
| label: cfg {
| 	group1 {
| 		pinmux = <dsjhlfka>;
| 		config-item2;
| 	};
| 	group2 {
| 		pinmux = <lsdjhaf>;
| 		config-item1;
| 	};
| };

pinconf_generic_dt_node_to_map_pinmux() only supports the latter.

The other assumption about devicetree configuration that the function makes is that the labeled node's parent is a "function node". The amlogic driver uses these "function nodes" to create the functions at probe time, and pinconf_generic_dt_node_to_map_pinmux() finds the parent of the node it is operating on's name as part of the mapping. IOW, it requires that the devicetree look like:

| pinctrl@bla {
|
| 	func-foo {
| 		label: group-default {
| 			pinmuxes = <lskdf>;
| 		};
| 	};
| };

and couldn't be used if the nodes containing the pinmux and configuration properties are children of the pinctrl node itself:

| pinctrl@bla {
|
| 	label: group-default {
| 		pinmuxes = <lskdf>;
| 	};
| };

These final two reasons are mainly why I believe this is not suitable as a generic function, and should be moved into the driver that is the sole user and originator of the "generic" function.

Stable-dep-of: a2539b92e4b7 ("pinctrl: meson: amlogic-a4: Fix device node reference leak in aml_dt_node_to_map_pinmux()")

---
 drivers/pinctrl/meson/pinctrl-amlogic-a4.c | 71 +++++++++++++++++++++-
 drivers/pinctrl/pinconf-generic.c          | 69 ---------------------
 include/linux/pinctrl/pinconf-generic.h    |  5 --
 3 files changed, 70 insertions(+), 75 deletions(-)
drivers/pinctrl/meson/pinctrl-amlogic-a4.c +70 -1
index 40542edd557e0..dfa32b11555cd 100644
@@ -24,6 +24,7 @@
 #include <dt-bindings/pinctrl/amlogic,pinctrl.h>
 
 #include "../core.h"
+#include "../pinctrl-utils.h"
 #include "../pinconf.h"
 
 #define gpio_chip_to_bank(chip) \
@@ -672,11 +673,79 @@ static void aml_pin_dbg_show(struct pinctrl_dev *pcdev, struct seq_file *s,
 	seq_printf(s, " %s", dev_name(pcdev->dev));
 }
 
+static int aml_dt_node_to_map_pinmux(struct pinctrl_dev *pctldev,
+				     struct device_node *np,
+				     struct pinctrl_map **map,
+				     unsigned int *num_maps)
+{
+	struct device *dev = pctldev->dev;
+	struct device_node *pnode;
+	unsigned long *configs = NULL;
+	unsigned int num_configs = 0;
+	struct property *prop;
+	unsigned int reserved_maps;
+	int reserve;
+	int ret;
+
+	prop = of_find_property(np, "pinmux", NULL);
+	if (!prop) {
+		dev_info(dev, "Missing pinmux property\n");
+		return -ENOENT;
+	}
+
+	pnode = of_get_parent(np);
+	if (!pnode) {
+		dev_info(dev, "Missing function node\n");
+		return -EINVAL;
+	}
+
+	reserved_maps = 0;
+	*map = NULL;
+	*num_maps = 0;
+
+	ret = pinconf_generic_parse_dt_config(np, pctldev, &configs,
+					      &num_configs);
+	if (ret < 0) {
+		dev_err(dev, "%pOF: could not parse node property\n", np);
+		return ret;
+	}
+
+	reserve = 1;
+	if (num_configs)
+		reserve++;
+
+	ret = pinctrl_utils_reserve_map(pctldev, map, &reserved_maps,
+					num_maps, reserve);
+	if (ret < 0)
+		goto exit;
+
+	ret = pinctrl_utils_add_map_mux(pctldev, map,
+					&reserved_maps, num_maps, np->name,
+					pnode->name);
+	if (ret < 0)
+		goto exit;
+
+	if (num_configs) {
+		ret = pinctrl_utils_add_map_configs(pctldev, map, &reserved_maps,
+						    num_maps, np->name, configs,
+						    num_configs, PIN_MAP_TYPE_CONFIGS_GROUP);
+		if (ret < 0)
+			goto exit;
+	}
+
+exit:
+	kfree(configs);
+	if (ret)
+		pinctrl_utils_free_map(pctldev, *map, *num_maps);
+
+	return ret;
+}
+
 static const struct pinctrl_ops aml_pctrl_ops = {
 	.get_groups_count	= aml_get_groups_count,
 	.get_group_name		= aml_get_group_name,
 	.get_group_pins		= aml_get_group_pins,
-	.dt_node_to_map		= pinconf_generic_dt_node_to_map_pinmux,
+	.dt_node_to_map		= aml_dt_node_to_map_pinmux,
 	.dt_free_map		= pinconf_generic_dt_free_map,
 	.pin_dbg_show		= aml_pin_dbg_show,
 };
drivers/pinctrl/pinconf-generic.c +0 -69

75 lines not on this page · raw message

include/linux/pinctrl/pinconf-generic.h +0 -5
index d9245ecec71dc..4e22aa44bcd4c 100644
@@ -235,9 +235,4 @@ static inline int pinconf_generic_dt_node_to_map_all(struct pinctrl_dev *pctldev
 	return pinconf_generic_dt_node_to_map(pctldev, np_config, map, num_maps,
 			PIN_MAP_TYPE_INVALID);
 }
-
-int pinconf_generic_dt_node_to_map_pinmux(struct pinctrl_dev *pctldev,
-					  struct device_node *np,
-					  struct pinctrl_map **map,
-					  unsigned int *num_maps);
 #endif /* __LINUX_PINCTRL_PINCONF_GENERIC_H */
Signature · 1 line
2.51.0
author maintainer
#221 lore raw

PATCH 215/314 pinctrl: meson: amlogic-a4: Fix device node reference leak in aml_dt_node_to_map_pinmux()

In reply to Sasha Levin

From: Felix Gu <[email protected]>

[ Upstream commit a2539b92e4b791c1ba482930b5e51b1591975461 ]

The of_get_parent() function returns a device_node with an incremented reference count.

Use the __free(device_node) cleanup attribute to ensure of_node_put() is automatically called when pnode goes out of scope, fixing a reference leak.

Fixes 6e9be3abb78c ("pinctrl: Add driver support for Amlogic SoCs")
---
 drivers/pinctrl/meson/pinctrl-amlogic-a4.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)
drivers/pinctrl/meson/pinctrl-amlogic-a4.c +1 -2
index dfa32b11555cd..e2293a872dcb7 100644
@@ -679,7 +679,6 @@ static int aml_dt_node_to_map_pinmux(struct pinctrl_dev *pctldev,
 				     unsigned int *num_maps)
 {
 	struct device *dev = pctldev->dev;
-	struct device_node *pnode;
 	unsigned long *configs = NULL;
 	unsigned int num_configs = 0;
 	struct property *prop;
@@ -693,7 +692,7 @@ static int aml_dt_node_to_map_pinmux(struct pinctrl_dev *pctldev,
 		return -ENOENT;
 	}
 
-	pnode = of_get_parent(np);
+	struct device_node *pnode __free(device_node) = of_get_parent(np);
 	if (!pnode) {
 		dev_info(dev, "Missing function node\n");
 		return -EINVAL;
Signature · 1 line
2.51.0
author maintainer
#222 lore raw

PATCH 216/314 pinctrl: cirrus: cs42l43: Fix double-put in cs42l43_pin_probe()

In reply to Sasha Levin

From: Felix Gu <[email protected]>

[ Upstream commit fd5bed798f45eb3a178ad527b43ab92705faaf8a ]

devm_add_action_or_reset() already invokes the action on failure, so the explicit put causes a double-put.

Fixes 9b07cdf86a0b ("pinctrl: cirrus: Fix fwnode leak in cs42l43_pin_probe()")
---
 drivers/pinctrl/cirrus/pinctrl-cs42l43.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)
drivers/pinctrl/cirrus/pinctrl-cs42l43.c +2 -3
index a8f82104a3842..227c37c360e19 100644
@@ -574,10 +574,9 @@ static int cs42l43_pin_probe(struct platform_device *pdev)
 		if (child) {
 			ret = devm_add_action_or_reset(&pdev->dev,
 				cs42l43_fwnode_put, child);
-			if (ret) {
-				fwnode_handle_put(child);
+			if (ret)
 				return ret;
-			}
+
 			if (!child->dev)
 				child->dev = priv->dev;
 			fwnode = child;
Signature · 1 line
2.51.0
author maintainer
#223 lore raw

PATCH 217/314 hwmon: (it87) Check the it87_lock() return value

In reply to Sasha Levin

From: Bart Van Assche <[email protected]>

[ Upstream commit 07ed4f05bbfd2bc014974dcc4297fd3aa1cb88c0 ]

Return early in it87_resume() if it87_lock() fails instead of ignoring the return value of that function. This patch suppresses a Clang thread-safety warning.

Cc Frank Crawford <[email protected]>
Cc Guenter Roeck <[email protected]>
Cc Jean Delvare <[email protected]>
Fixes 376e1a937b30 ("hwmon: (it87) Add calls to smbus_enable/smbus_disable as required")
[groeck: Declare 'ret' at the beginning of it87_resume()]
---
 drivers/hwmon/it87.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)
drivers/hwmon/it87.c +4 -1
index e233aafa8856c..5cfb98a0512f0 100644
@@ -3590,10 +3590,13 @@ static int it87_resume(struct device *dev)
 {
 	struct platform_device *pdev = to_platform_device(dev);
 	struct it87_data *data = dev_get_drvdata(dev);
+	int err;
 
 	it87_resume_sio(pdev);
 
-	it87_lock(data);
+	err = it87_lock(data);
+	if (err)
+		return err;
 
 	it87_check_pwm(dev);
 	it87_check_limit_regs(data);
Signature · 1 line
2.51.0
author maintainer
#224 lore raw

PATCH 218/314 idpf: increment completion queue next_to_clean in sw marker wait routine

In reply to Sasha Levin

From: Li Li <[email protected]>

[ Upstream commit 712896ac4bce38a965a1c175f6e7804ed0381334 ]

Currently, in idpf_wait_for_sw_marker_completion(), when an IDPF_TXD_COMPLT_SW_MARKER packet is found, the routine breaks out of the for loop and does not increment the next_to_clean counter. This causes the subsequent NAPI polls to run into the same IDPF_TXD_COMPLT_SW_MARKER packet again and print out the following:

    [   23.261341] idpf 0000:05:00.0 eth1: Unknown TX completion type: 5

Instead, we should increment next_to_clean regardless when an IDPF_TXD_COMPLT_SW_MARKER packet is found.

Tested: with the patch applied, we do not see the errors above from NAPI polls anymore.

Fixes 9d39447051a0 ("idpf: remove SW marker handling from NAPI")
---
 drivers/net/ethernet/intel/idpf/idpf_txrx.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)
drivers/net/ethernet/intel/idpf/idpf_txrx.c +3 -3
index a48088eb9b822..83cc9504e7e1a 100644
@@ -2326,7 +2326,7 @@ void idpf_wait_for_sw_marker_completion(const struct idpf_tx_queue *txq)
 
 	do {
 		struct idpf_splitq_4b_tx_compl_desc *tx_desc;
-		struct idpf_tx_queue *target;
+		struct idpf_tx_queue *target = NULL;
 		u32 ctype_gen, id;
 
 		tx_desc = flow ? &complq->comp[ntc].common :
@@ -2346,14 +2346,14 @@ void idpf_wait_for_sw_marker_completion(const struct idpf_tx_queue *txq)
 		target = complq->txq_grp->txqs[id];
 
 		idpf_queue_clear(SW_MARKER, target);
-		if (target == txq)
-			break;
 
 next:
 		if (unlikely(++ntc == complq->desc_count)) {
 			ntc = 0;
 			gen_flag = !gen_flag;
 		}
+		if (target == txq)
+			break;
 	} while (time_before(jiffies, timeout));
 
 	idpf_queue_assign(GEN_CHK, complq, gen_flag);
Signature · 1 line
2.51.0
author maintainer
#225 lore raw

PATCH 219/314 idpf: change IRQ naming to match netdev and ethtool queue numbering

In reply to Sasha Levin

From: Brian Vazquez <[email protected]>

[ Upstream commit 1500a8662d2d41d6bb03e034de45ddfe6d7d362d ]

The code uses the vidx for the IRQ name but that doesn't match ethtool reporting nor netdev naming, this makes it hard to tune the device and associate queues with IRQs. Sequentially requesting irqs starting from '0' makes the output consistent.

This commit changes the interrupt numbering but preserves the name format, maintaining ABI compatibility. Existing tools relying on the old numbering are already non-functional, as they lack a useful correlation to the interrupts.

Before:

ethtool -L eth1 tx 1 combined 3

grep . /proc/irq/*/*idpf*/../smp_affinity_list /proc/irq/67/idpf-Mailbox-0/../smp_affinity_list:0-55,112-167 /proc/irq/68/idpf-eth1-TxRx-1/../smp_affinity_list:0 /proc/irq/70/idpf-eth1-TxRx-3/../smp_affinity_list:1 /proc/irq/71/idpf-eth1-TxRx-4/../smp_affinity_list:2 /proc/irq/72/idpf-eth1-Tx-5/../smp_affinity_list:3

ethtool -S eth1 | grep -v ': 0'
NIC statistics:

     tx_q-0_pkts: 1002
     tx_q-1_pkts: 2679
     tx_q-2_pkts: 1113
     tx_q-3_pkts: 1192 <----- tx_q-3 vs idpf-eth1-Tx-5
     rx_q-0_pkts: 1143
     rx_q-1_pkts: 3172
     rx_q-2_pkts: 1074

After:

ethtool -L eth1 tx 1 combined 3

grep . /proc/irq/*/*idpf*/../smp_affinity_list

/proc/irq/67/idpf-Mailbox-0/../smp_affinity_list:0-55,112-167 /proc/irq/68/idpf-eth1-TxRx-0/../smp_affinity_list:0 /proc/irq/70/idpf-eth1-TxRx-1/../smp_affinity_list:1 /proc/irq/71/idpf-eth1-TxRx-2/../smp_affinity_list:2 /proc/irq/72/idpf-eth1-Tx-3/../smp_affinity_list:3

ethtool -S eth1 | grep -v ': 0'
NIC statistics:

     tx_q-0_pkts: 118
     tx_q-1_pkts: 134
     tx_q-2_pkts: 228
     tx_q-3_pkts: 138 <--- tx_q-3 matches idpf-eth1-Tx-3
     rx_q-0_pkts: 111
     rx_q-1_pkts: 366
     rx_q-2_pkts: 120
---
 drivers/net/ethernet/intel/idpf/idpf_txrx.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/net/ethernet/intel/idpf/idpf_txrx.c +1 -1
index 83cc9504e7e1a..c859665b2dc89 100644
@@ -4038,7 +4038,7 @@ static int idpf_vport_intr_req_irq(struct idpf_vport *vport)
 			continue;
 
 		name = kasprintf(GFP_KERNEL, "%s-%s-%s-%d", drv_name, if_name,
-				 vec_name, vidx);
+				 vec_name, vector);
 
 		err = request_irq(irq_num, idpf_vport_intr_clean_queues, 0,
 				  name, q_vector);
Signature · 1 line
2.51.0
author maintainer
#226 lore raw

PATCH 220/314 idpf: Fix flow rule delete failure due to invalid validation

In reply to Sasha Levin

From: Sreedevi Joshi <[email protected]>

[ Upstream commit 2c31557336a8e4d209ed8d4513cef2c0f15e7ef4 ]

When deleting a flow rule using "ethtool -N <dev> delete <location>", idpf_sideband_action_ena() incorrectly validates fsp->ring_cookie even though ethtool doesn't populate this field for delete operations. The uninitialized ring_cookie may randomly match RX_CLS_FLOW_DISC or RX_CLS_FLOW_WAKE, causing validation to fail and preventing legitimate rule deletions. Remove the unnecessary sideband action enable check and ring_cookie validation during delete operations since action validation is not required when removing existing rules.

---
 drivers/net/ethernet/intel/idpf/idpf_ethtool.c | 3 ---
 1 file changed, 3 deletions(-)
drivers/net/ethernet/intel/idpf/idpf_ethtool.c +0 -3
index 3e191cf528b69..6c0a9296eccc8 100644
@@ -291,9 +291,6 @@ static int idpf_del_flow_steer(struct net_device *netdev,
 	vport_config = vport->adapter->vport_config[np->vport_idx];
 	user_config = &vport_config->user_config;
 
-	if (!idpf_sideband_action_ena(vport, fsp))
-		return -EOPNOTSUPP;
-
 	rule = kzalloc(struct_size(rule, rule_info, 1), GFP_KERNEL);
 	if (!rule)
 		return -ENOMEM;
Signature · 1 line
2.51.0
author maintainer
#227 lore raw

PATCH 221/314 ice: recap the VSI and QoS info after rebuild

In reply to Sasha Levin

From: Aaron Ma <[email protected]>

[ Upstream commit 6aa07e23dd3ccd35a0100c06fcb6b6c3b01e7965 ]

Fix IRDMA hardware initialization timeout (-110) after resume by separating VSI-dependent configuration from RDMA resource allocation, ensuring VSI is rebuilt before IRDMA accesses it.

After resume from suspend, IRDMA hardware initialization fails:
ice: IRDMA hardware initialization FAILED init_state=4 status=-110

Separate RDMA initialization into two phases:
1. ice_init_rdma() - Allocate resources only (no VSI/QoS access, no plug)
2. ice_rdma_finalize_setup() - Assign VSI/QoS info and plug device

This allows:
- ice_init_rdma() to stay in ice_resume() (mirrors ice_deinit_rdma() in ice_suspend())
- VSI assignment deferred until after ice_vsi_rebuild() completes
- QoS info updated after ice_dcb_rebuild() completes
- Device plugged only when control queues, VSI, and DCB are all ready

Fixes bc69ad74867db ("ice: avoid IRQ collision to fix init failure on ACPI S3 resume")
---
 drivers/net/ethernet/intel/ice/ice.h      |  1 +
 drivers/net/ethernet/intel/ice/ice_idc.c  | 44 +++++++++++++++++------
 drivers/net/ethernet/intel/ice/ice_main.c |  7 +++-
 3 files changed, 41 insertions(+), 11 deletions(-)
drivers/net/ethernet/intel/ice/ice.h +1 -0
index a23ccd4ba08d2..6886188043764 100644
@@ -988,6 +988,7 @@ int ice_schedule_reset(struct ice_pf *pf, enum ice_reset_req reset);
 void ice_print_link_msg(struct ice_vsi *vsi, bool isup);
 int ice_plug_aux_dev(struct ice_pf *pf);
 void ice_unplug_aux_dev(struct ice_pf *pf);
+void ice_rdma_finalize_setup(struct ice_pf *pf);
 int ice_init_rdma(struct ice_pf *pf);
 void ice_deinit_rdma(struct ice_pf *pf);
 bool ice_is_wol_supported(struct ice_hw *hw);
drivers/net/ethernet/intel/ice/ice_idc.c +34 -10

69 lines not on this page · raw message

drivers/net/ethernet/intel/ice/ice_main.c +6 -1
index f2b91f7f87861..a4ae032f2161b 100644
@@ -5147,6 +5147,9 @@ int ice_load(struct ice_pf *pf)
 	if (err)
 		goto err_init_rdma;
 
+	/* Finalize RDMA: VSI already created, assign info and plug device */
+	ice_rdma_finalize_setup(pf);
+
 	ice_service_task_restart(pf);
 
 	clear_bit(ICE_DOWN, pf->state);
@@ -5178,6 +5181,7 @@ void ice_unload(struct ice_pf *pf)
 
 	devl_assert_locked(priv_to_devlink(pf));
 
+	ice_unplug_aux_dev(pf);
 	ice_deinit_rdma(pf);
 	ice_deinit_features(pf);
 	ice_tc_indir_block_unregister(vsi);
@@ -5604,6 +5608,7 @@ static int ice_suspend(struct device *dev)
 	 */
 	disabled = ice_service_task_stop(pf);
 
+	ice_unplug_aux_dev(pf);
 	ice_deinit_rdma(pf);
 
 	/* Already suspended?, then there is nothing to do */
@@ -7809,7 +7814,7 @@ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type)
 
 	ice_health_clear(pf);
 
-	ice_plug_aux_dev(pf);
+	ice_rdma_finalize_setup(pf);
 	if (ice_is_feature_supported(pf, ICE_F_SRIOV_LAG))
 		ice_lag_rebuild(pf);
 
Signature · 1 line
2.51.0
author maintainer
#228 lore raw

PATCH 222/314 i40e: Fix preempt count leak in napi poll tracepoint

In reply to Sasha Levin

From: Thomas Gleixner <[email protected]>

[ Upstream commit 4b3d54a85bd37ebf2d9836f0d0de775c0ff21af9 ]

Using get_cpu() in the tracepoint assignment causes an obvious preempt count leak because nothing invokes put_cpu() to undo it:

softirq: huh, entered softirq 3 NET_RX with preempt_count 00000100, exited with 00000101?

This clearly has seen a lot of testing in the last 3+ years...

Use smp_processor_id() instead.

Fixes 6d4d584a7ea8 ("i40e: Add i40e_napi_poll tracepoint")
Cc Tony Nguyen <[email protected]>
Cc Przemek Kitszel <[email protected]>
---
 drivers/net/ethernet/intel/i40e/i40e_trace.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/net/ethernet/intel/i40e/i40e_trace.h +1 -1
index 759f3d1c4c8f0..dde0ccd789ed1 100644
@@ -88,7 +88,7 @@ TRACE_EVENT(i40e_napi_poll,
 		__entry->rx_clean_complete = rx_clean_complete;
 		__entry->tx_clean_complete = tx_clean_complete;
 		__entry->irq_num = q->irq_num;
-		__entry->curr_cpu = get_cpu();
+		__entry->curr_cpu = smp_processor_id();
 		__assign_str(qname);
 		__assign_str(dev_name);
 		__assign_bitmask(irq_affinity, cpumask_bits(&q->affinity_mask),
Signature · 1 line
2.51.0
author maintainer
#229 lore raw

PATCH 223/314 e1000e: clear DPG_EN after reset to avoid autonomous power-gating

In reply to Sasha Levin

From: Vitaly Lifshits <[email protected]>

[ Upstream commit 0942fc6d324eb9c6b16187b2aa994c0823557f06 ]

Panther Lake systems introduced an autonomous power gating feature for the integrated Gigabit Ethernet in shutdown state (S5) state. As part of it, the reset value of DPG_EN bit was changed to 1. Clear this bit after performing hardware reset to avoid errors such as Tx/Rx hangs, or packet loss/corruption.

Fixes 0c9183ce61bc ("e1000e: Add support for the next LOM generation")
---
 drivers/net/ethernet/intel/e1000e/defines.h | 1 +
 drivers/net/ethernet/intel/e1000e/ich8lan.c | 9 +++++++++
 2 files changed, 10 insertions(+)
drivers/net/ethernet/intel/e1000e/defines.h +1 -0
index ba331899d1861..d4a1041e456dc 100644
@@ -33,6 +33,7 @@
 
 /* Extended Device Control */
 #define E1000_CTRL_EXT_LPCD  0x00000004     /* LCD Power Cycle Done */
+#define E1000_CTRL_EXT_DPG_EN	0x00000008 /* Dynamic Power Gating Enable */
 #define E1000_CTRL_EXT_SDP3_DATA 0x00000080 /* Value of SW Definable Pin 3 */
 #define E1000_CTRL_EXT_FORCE_SMBUS 0x00000800 /* Force SMBus mode */
 #define E1000_CTRL_EXT_EE_RST    0x00002000 /* Reinitialize from EEPROM */
drivers/net/ethernet/intel/e1000e/ich8lan.c +9 -0
index df4e7d781cb1c..f9328caefe44b 100644
@@ -4925,6 +4925,15 @@ static s32 e1000_reset_hw_ich8lan(struct e1000_hw *hw)
 	reg |= E1000_KABGTXD_BGSQLBIAS;
 	ew32(KABGTXD, reg);
 
+	/* The hardware reset value of the DPG_EN bit is 1.
+	 * Clear DPG_EN to prevent unexpected autonomous power gating.
+	 */
+	if (hw->mac.type >= e1000_pch_ptp) {
+		reg = er32(CTRL_EXT);
+		reg &= ~E1000_CTRL_EXT_DPG_EN;
+		ew32(CTRL_EXT, reg);
+	}
+
 	return 0;
 }
 
Signature · 1 line
2.51.0
author maintainer
#230 lore raw

PATCH 224/314 drm/solomon: Fix page start when updating rectangle in page addressing mode

In reply to Sasha Levin

From: Francesco Lavra <[email protected]>

[ Upstream commit 36d9579fed6c9429aa172f77bd28c58696ce8e2b ]

In page addressing mode, the pixel values of a dirty rectangle must be sent to the display controller one page at a time. The range of pages corresponding to a given rectangle is being incorrectly calculated as if the Y value of the top left coordinate of the rectangle was 0. This can result in rectangle updates being displayed on wrong parts of the screen.

Fix the above issue by consolidating the start page calculation in a single place at the beginning of the update_rect function, and using the calculated value for all addressing modes.

---
 drivers/gpu/drm/solomon/ssd130x.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)
drivers/gpu/drm/solomon/ssd130x.c +2 -4
index eec43d1a55951..18d2294c526de 100644
@@ -736,6 +736,7 @@ static int ssd130x_update_rect(struct ssd130x_device *ssd130x,
 	unsigned int height = drm_rect_height(rect);
 	unsigned int line_length = DIV_ROUND_UP(width, 8);
 	unsigned int page_height = SSD130X_PAGE_HEIGHT;
+	u8 page_start = ssd130x->page_offset + y / page_height;
 	unsigned int pages = DIV_ROUND_UP(height, page_height);
 	struct drm_device *drm = &ssd130x->drm;
 	u32 array_idx = 0;
@@ -773,14 +774,11 @@ static int ssd130x_update_rect(struct ssd130x_device *ssd130x,
 	 */
 
 	if (!ssd130x->page_address_mode) {
-		u8 page_start;
-
 		/* Set address range for horizontal addressing mode */
 		ret = ssd130x_set_col_range(ssd130x, ssd130x->col_offset + x, width);
 		if (ret < 0)
 			return ret;
 
-		page_start = ssd130x->page_offset + y / page_height;
 		ret = ssd130x_set_page_range(ssd130x, page_start, pages);
 		if (ret < 0)
 			return ret;
@@ -812,7 +810,7 @@ static int ssd130x_update_rect(struct ssd130x_device *ssd130x,
 		 */
 		if (ssd130x->page_address_mode) {
 			ret = ssd130x_set_page_pos(ssd130x,
-						   ssd130x->page_offset + i,
+						   page_start + i,
 						   ssd130x->col_offset + x);
 			if (ret < 0)
 				return ret;
Signature · 1 line
2.51.0
author maintainer
#231 lore raw

PATCH 225/314 netfs: Fix unbuffered/DIO writes to dispatch subrequests in strict sequence

In reply to Sasha Levin

From: David Howells <[email protected]>

[ Upstream commit a0b4c7a49137ed21279f354eb59f49ddae8dffc2 ]

Fix netfslib such that when it's making an unbuffered or DIO write, to make sure that it sends each subrequest strictly sequentially, waiting till the previous one is 'committed' before sending the next so that we don't have pieces landing out of order and potentially leaving a hole if an error occurs (ENOSPC for example).

This is done by copying in just those bits of issuing, collecting and retrying subrequests that are necessary to do one subrequest at a time. Retrying, in particular, is simpler because if the current subrequest needs retrying, the source iterator can just be copied again and the subrequest prepped and issued again without needing to be concerned about whether it needs merging with the previous or next in the sequence.

Note that the issuing loop waits for a subrequest to complete right after issuing it, but this wait could be moved elsewhere allowing preparatory steps to be performed whilst the subrequest is in progress. In particular, once content encryption is available in netfslib, that could be done whilst waiting, as could cleanup of buffers that have been completed.

---
 fs/netfs/direct_write.c      | 228 ++++++++++++++++++++++++++++++++---
 fs/netfs/internal.h          |   4 +-
 fs/netfs/write_collect.c     |  21 ----
 fs/netfs/write_issue.c       |  41 +------
 include/trace/events/netfs.h |   4 +-
 5 files changed, 221 insertions(+), 77 deletions(-)
fs/netfs/direct_write.c +212 -16
index a9d1c3b2c0842..dd1451bf7543d 100644
@@ -9,6 +9,202 @@
 #include <linux/uio.h>
 #include "internal.h"
 
+/*
+ * Perform the cleanup rituals after an unbuffered write is complete.
+ */
+static void netfs_unbuffered_write_done(struct netfs_io_request *wreq)
+{
+	struct netfs_inode *ictx = netfs_inode(wreq->inode);
+
+	_enter("R=%x", wreq->debug_id);
+
+	/* Okay, declare that all I/O is complete. */
+	trace_netfs_rreq(wreq, netfs_rreq_trace_write_done);
+
+	if (!wreq->error)
+		netfs_update_i_size(ictx, &ictx->inode, wreq->start, wreq->transferred);
+
+	if (wreq->origin == NETFS_DIO_WRITE &&
+	    wreq->mapping->nrpages) {
+		/* mmap may have got underfoot and we may now have folios
+		 * locally covering the region we just wrote.  Attempt to
+		 * discard the folios, but leave in place any modified locally.
+		 * ->write_iter() is prevented from interfering by the DIO
+		 * counter.
+		 */
+		pgoff_t first = wreq->start >> PAGE_SHIFT;
+		pgoff_t last = (wreq->start + wreq->transferred - 1) >> PAGE_SHIFT;
+
+		invalidate_inode_pages2_range(wreq->mapping, first, last);
+	}
+
+	if (wreq->origin == NETFS_DIO_WRITE)
+		inode_dio_end(wreq->inode);
+
+	_debug("finished");
+	netfs_wake_rreq_flag(wreq, NETFS_RREQ_IN_PROGRESS, netfs_rreq_trace_wake_ip);
+	/* As we cleared NETFS_RREQ_IN_PROGRESS, we acquired its ref. */
+
+	if (wreq->iocb) {
+		size_t written = umin(wreq->transferred, wreq->len);
+
+		wreq->iocb->ki_pos += written;
+		if (wreq->iocb->ki_complete) {
+			trace_netfs_rreq(wreq, netfs_rreq_trace_ki_complete);
+			wreq->iocb->ki_complete(wreq->iocb, wreq->error ?: written);
+		}
+		wreq->iocb = VFS_PTR_POISON;
+	}
+
+	netfs_clear_subrequests(wreq);
+}
+
+/*
+ * Collect the subrequest results of unbuffered write subrequests.
+ */
+static void netfs_unbuffered_write_collect(struct netfs_io_request *wreq,
+					   struct netfs_io_stream *stream,
+					   struct netfs_io_subrequest *subreq)
+{
+	trace_netfs_collect_sreq(wreq, subreq);
+
+	spin_lock(&wreq->lock);
+	list_del_init(&subreq->rreq_link);
+	spin_unlock(&wreq->lock);
+
+	wreq->transferred += subreq->transferred;
+	iov_iter_advance(&wreq->buffer.iter, subreq->transferred);
+
+	stream->collected_to = subreq->start + subreq->transferred;
+	wreq->collected_to = stream->collected_to;
+	netfs_put_subrequest(subreq, netfs_sreq_trace_put_done);
+
+	trace_netfs_collect_stream(wreq, stream);
+	trace_netfs_collect_state(wreq, wreq->collected_to, 0);
+}
+
+/*
+ * Write data to the server without going through the pagecache and without
+ * writing it to the local cache.  We dispatch the subrequests serially and
+ * wait for each to complete before dispatching the next, lest we leave a gap
+ * in the data written due to a failure such as ENOSPC.  We could, however
+ * attempt to do preparation such as content encryption for the next subreq
+ * whilst the current is in progress.
+ */
+static int netfs_unbuffered_write(struct netfs_io_request *wreq)
+{
+	struct netfs_io_subrequest *subreq = NULL;
+	struct netfs_io_stream *stream = &wreq->io_streams[0];
+	int ret;
+
+	_enter("%llx", wreq->len);
+
+	if (wreq->origin == NETFS_DIO_WRITE)
+		inode_dio_begin(wreq->inode);
+
+	stream->collected_to = wreq->start;
+
+	for (;;) {
+		bool retry = false;
+
+		if (!subreq) {
+			netfs_prepare_write(wreq, stream, wreq->start + wreq->transferred);
+			subreq = stream->construct;
+			stream->construct = NULL;
+			stream->front = NULL;
+		}
+
+		/* Check if (re-)preparation failed. */
+		if (unlikely(test_bit(NETFS_SREQ_FAILED, &subreq->flags))) {
+			netfs_write_subrequest_terminated(subreq, subreq->error);
+			wreq->error = subreq->error;
+			break;
+		}
+
+		iov_iter_truncate(&subreq->io_iter, wreq->len - wreq->transferred);
+		if (!iov_iter_count(&subreq->io_iter))
+			break;
+
+		subreq->len = netfs_limit_iter(&subreq->io_iter, 0,
+					       stream->sreq_max_len,
+					       stream->sreq_max_segs);
+		iov_iter_truncate(&subreq->io_iter, subreq->len);
+		stream->submit_extendable_to = subreq->len;
+
+		trace_netfs_sreq(subreq, netfs_sreq_trace_submit);
+		stream->issue_write(subreq);
+
+		/* Async, need to wait. */
+		netfs_wait_for_in_progress_stream(wreq, stream);
+
+		if (test_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags)) {
+			retry = true;
+		} else if (test_bit(NETFS_SREQ_FAILED, &subreq->flags)) {
+			ret = subreq->error;
+			wreq->error = ret;
+			netfs_see_subrequest(subreq, netfs_sreq_trace_see_failed);
+			subreq = NULL;
+			break;
+		}
+		ret = 0;
+
+		if (!retry) {
+			netfs_unbuffered_write_collect(wreq, stream, subreq);
+			subreq = NULL;
+			if (wreq->transferred >= wreq->len)
+				break;
+			if (!wreq->iocb && signal_pending(current)) {
+				ret = wreq->transferred ? -EINTR : -ERESTARTSYS;
+				trace_netfs_rreq(wreq, netfs_rreq_trace_intr);
+				break;
+			}
+			continue;
+		}
+
+		/* We need to retry the last subrequest, so first reset the
+		 * iterator, taking into account what, if anything, we managed
+		 * to transfer.
+		 */
+		subreq->error = -EAGAIN;
+		trace_netfs_sreq(subreq, netfs_sreq_trace_retry);
+		if (subreq->transferred > 0)
+			iov_iter_advance(&wreq->buffer.iter, subreq->transferred);
+
+		if (stream->source == NETFS_UPLOAD_TO_SERVER &&
+		    wreq->netfs_ops->retry_request)
+			wreq->netfs_ops->retry_request(wreq, stream);
+
+		__clear_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags);
+		__clear_bit(NETFS_SREQ_BOUNDARY, &subreq->flags);
+		__clear_bit(NETFS_SREQ_FAILED, &subreq->flags);
+		subreq->io_iter		= wreq->buffer.iter;
+		subreq->start		= wreq->start + wreq->transferred;
+		subreq->len		= wreq->len   - wreq->transferred;
+		subreq->transferred	= 0;
+		subreq->retry_count	+= 1;
+		stream->sreq_max_len	= UINT_MAX;
+		stream->sreq_max_segs	= INT_MAX;
+
+		netfs_get_subrequest(subreq, netfs_sreq_trace_get_resubmit);
+		stream->prepare_write(subreq);
+
+		__set_bit(NETFS_SREQ_IN_PROGRESS, &subreq->flags);
+		netfs_stat(&netfs_n_wh_retry_write_subreq);
+	}
+
+	netfs_unbuffered_write_done(wreq);
+	_leave(" = %d", ret);
+	return ret;
+}
+
+static void netfs_unbuffered_write_async(struct work_struct *work)
+{
+	struct netfs_io_request *wreq = container_of(work, struct netfs_io_request, work);
+
+	netfs_unbuffered_write(wreq);
+	netfs_put_request(wreq, netfs_rreq_trace_put_complete);
+}
+
 /*
  * Perform an unbuffered write where we may have to do an RMW operation on an
  * encrypted file.  This can also be used for direct I/O writes.
@@ -70,35 +266,35 @@ ssize_t netfs_unbuffered_write_iter_locked(struct kiocb *iocb, struct iov_iter *
 			 */
 			wreq->buffer.iter = *iter;
 		}
+
+		wreq->len = iov_iter_count(&wreq->buffer.iter);
 	}
 
 	__set_bit(NETFS_RREQ_USE_IO_ITER, &wreq->flags);
-	if (async)
-		__set_bit(NETFS_RREQ_OFFLOAD_COLLECTION, &wreq->flags);
 
 	/* Copy the data into the bounce buffer and encrypt it. */
 	// TODO
 
 	/* Dispatch the write. */
 	__set_bit(NETFS_RREQ_UPLOAD_TO_SERVER, &wreq->flags);
-	if (async)
-		wreq->iocb = iocb;
-	wreq->len = iov_iter_count(&wreq->buffer.iter);
-	ret = netfs_unbuffered_write(wreq, is_sync_kiocb(iocb), wreq->len);
-	if (ret < 0) {
-		_debug("begin = %zd", ret);
-		goto out;
-	}
 
-	if (!async) {
-		ret = netfs_wait_for_write(wreq);
-		if (ret > 0)
-			iocb->ki_pos += ret;
-	} else {
+	if (async) {
+		INIT_WORK(&wreq->work, netfs_unbuffered_write_async);
+		wreq->iocb = iocb;
+		queue_work(system_dfl_wq, &wreq->work);
 		ret = -EIOCBQUEUED;
+	} else {
+		ret = netfs_unbuffered_write(wreq);
+		if (ret < 0) {
+			_debug("begin = %zd", ret);
+		} else {
+			iocb->ki_pos += wreq->transferred;
+			ret = wreq->transferred ?: wreq->error;
+		}
+
+		netfs_put_request(wreq, netfs_rreq_trace_put_complete);
 	}
 
-out:
 	netfs_put_request(wreq, netfs_rreq_trace_put_return);
 	return ret;
 
fs/netfs/internal.h +3 -1
index 4319611f53544..d436e20d34185 100644
@@ -198,6 +198,9 @@ struct netfs_io_request *netfs_create_write_req(struct address_space *mapping,
 						struct file *file,
 						loff_t start,
 						enum netfs_io_origin origin);
+void netfs_prepare_write(struct netfs_io_request *wreq,
+			 struct netfs_io_stream *stream,
+			 loff_t start);
 void netfs_reissue_write(struct netfs_io_stream *stream,
 			 struct netfs_io_subrequest *subreq,
 			 struct iov_iter *source);
@@ -212,7 +215,6 @@ int netfs_advance_writethrough(struct netfs_io_request *wreq, struct writeback_c
 			       struct folio **writethrough_cache);
 ssize_t netfs_end_writethrough(struct netfs_io_request *wreq, struct writeback_control *wbc,
 			       struct folio *writethrough_cache);
-int netfs_unbuffered_write(struct netfs_io_request *wreq, bool may_wait, size_t len);
 
 /*
  * write_retry.c
fs/netfs/write_collect.c +0 -21
index 61eab34ea67ef..83eb3dc1adf8a 100644
@@ -399,27 +399,6 @@ bool netfs_write_collection(struct netfs_io_request *wreq)
 		ictx->ops->invalidate_cache(wreq);
 	}
 
-	if ((wreq->origin == NETFS_UNBUFFERED_WRITE ||
-	     wreq->origin == NETFS_DIO_WRITE) &&
-	    !wreq->error)
-		netfs_update_i_size(ictx, &ictx->inode, wreq->start, wreq->transferred);
-
-	if (wreq->origin == NETFS_DIO_WRITE &&
-	    wreq->mapping->nrpages) {
-		/* mmap may have got underfoot and we may now have folios
-		 * locally covering the region we just wrote.  Attempt to
-		 * discard the folios, but leave in place any modified locally.
-		 * ->write_iter() is prevented from interfering by the DIO
-		 * counter.
-		 */
-		pgoff_t first = wreq->start >> PAGE_SHIFT;
-		pgoff_t last = (wreq->start + wreq->transferred - 1) >> PAGE_SHIFT;
-		invalidate_inode_pages2_range(wreq->mapping, first, last);
-	}
-
-	if (wreq->origin == NETFS_DIO_WRITE)
-		inode_dio_end(wreq->inode);
-
 	_debug("finished");
 	netfs_wake_rreq_flag(wreq, NETFS_RREQ_IN_PROGRESS, netfs_rreq_trace_wake_ip);
 	/* As we cleared NETFS_RREQ_IN_PROGRESS, we acquired its ref. */
fs/netfs/write_issue.c +3 -38

53 lines not on this page · raw message

include/trace/events/netfs.h +3 -1
index 64a382fbc31a8..2d366be46a1c3 100644
@@ -57,6 +57,7 @@
 	EM(netfs_rreq_trace_done,		"DONE   ")	\
 	EM(netfs_rreq_trace_end_copy_to_cache,	"END-C2C")	\
 	EM(netfs_rreq_trace_free,		"FREE   ")	\
+	EM(netfs_rreq_trace_intr,		"INTR   ")	\
 	EM(netfs_rreq_trace_ki_complete,	"KI-CMPL")	\
 	EM(netfs_rreq_trace_recollect,		"RECLLCT")	\
 	EM(netfs_rreq_trace_redirty,		"REDIRTY")	\
@@ -169,7 +170,8 @@
 	EM(netfs_sreq_trace_put_oom,		"PUT OOM    ")	\
 	EM(netfs_sreq_trace_put_wip,		"PUT WIP    ")	\
 	EM(netfs_sreq_trace_put_work,		"PUT WORK   ")	\
-	E_(netfs_sreq_trace_put_terminated,	"PUT TERM   ")
+	EM(netfs_sreq_trace_put_terminated,	"PUT TERM   ")	\
+	E_(netfs_sreq_trace_see_failed,		"SEE FAILED ")
 
 #define netfs_folio_traces					\
 	EM(netfs_folio_is_uptodate,		"mod-uptodate")	\
Signature · 1 line
2.51.0
author maintainer
#232 lore raw

PATCH 226/314 nvmet-fcloop: Check remoteport port_state before calling done callback

In reply to Sasha Levin

From: Justin Tee <[email protected]>

[ Upstream commit dd677d0598387ea623820ab2bd0e029c377445a3 ]

In nvme_fc_handle_ls_rqst_work, the lsrsp->done callback is only set when remoteport->port_state is FC_OBJSTATE_ONLINE. Otherwise, the nvme_fc_xmt_ls_rsp's LLDD call to lport->ops->xmt_ls_rsp is expected to fail and the nvme-fc transport layer itself will directly call nvme_fc_xmt_ls_rsp_free instead of relying on LLDD's done callback to free the lsrsp resources.

Update the fcloop_t2h_xmt_ls_rsp routine to check remoteport->port_state. If online, then lsrsp->done callback will free the lsrsp. Else, return -ENODEV to signal the nvme-fc transport to handle freeing lsrsp.

---
 drivers/nvme/target/fcloop.c | 15 +++++++++++----
 1 file changed, 11 insertions(+), 4 deletions(-)
drivers/nvme/target/fcloop.c +11 -4
index 5dffcc5becae8..305ab7ee6e760 100644
@@ -492,6 +492,7 @@ fcloop_t2h_xmt_ls_rsp(struct nvme_fc_local_port *localport,
 	struct fcloop_rport *rport = remoteport->private;
 	struct nvmet_fc_target_port *targetport = rport->targetport;
 	struct fcloop_tport *tport;
+	int ret = 0;
 
 	if (!targetport) {
 		/*
@@ -501,12 +502,18 @@ fcloop_t2h_xmt_ls_rsp(struct nvme_fc_local_port *localport,
 		 * We end up here from delete association exchange:
 		 * nvmet_fc_xmt_disconnect_assoc sends an async request.
 		 *
-		 * Return success because this is what LLDDs do; silently
-		 * drop the response.
+		 * Return success when remoteport is still online because this
+		 * is what LLDDs do and silently drop the response.  Otherwise,
+		 * return with error to signal upper layer to perform the lsrsp
+		 * resource cleanup.
 		 */
-		lsrsp->done(lsrsp);
+		if (remoteport->port_state == FC_OBJSTATE_ONLINE)
+			lsrsp->done(lsrsp);
+		else
+			ret = -ENODEV;
+
 		kmem_cache_free(lsreq_cache, tls_req);
-		return 0;
+		return ret;
 	}
 
 	memcpy(lsreq->rspaddr, lsrsp->rspbuf,
Signature · 1 line
2.51.0
author maintainer
#233 lore raw

PATCH 227/314 net: annotate data-races around sk->sk_{data_ready,write_space}

In reply to Sasha Levin

From: Eric Dumazet <[email protected]>

[ Upstream commit 2ef2b20cf4e04ac8a6ba68493f8780776ff84300 ]

skmsg (and probably other layers) are changing these pointers while other cpus might read them concurrently.

Add corresponding READ_ONCE()/WRITE_ONCE() annotations for UDP, TCP and AF_UNIX.

Fixes 604326b41a6f ("bpf, sockmap: convert to generic sk_msg interface")
Reported-by [email protected]
Cc Daniel Borkmann <[email protected]>
Cc John Fastabend <[email protected]>
Cc Jakub Sitnicki <[email protected]>
Cc Willem de Bruijn <[email protected]>
---
 net/core/skmsg.c         | 14 +++++++-------
 net/ipv4/tcp.c           |  4 ++--
 net/ipv4/tcp_bpf.c       |  2 +-
 net/ipv4/tcp_input.c     | 14 ++++++++------
 net/ipv4/tcp_minisocks.c |  2 +-
 net/ipv4/udp.c           |  2 +-
 net/ipv4/udp_bpf.c       |  2 +-
 net/unix/af_unix.c       |  8 ++++----
 8 files changed, 25 insertions(+), 23 deletions(-)
net/core/skmsg.c +7 -7
index ddde93dd8bc6d..12fbb0545c712 100644
@@ -1205,8 +1205,8 @@ void sk_psock_start_strp(struct sock *sk, struct sk_psock *psock)
 		return;
 
 	psock->saved_data_ready = sk->sk_data_ready;
-	sk->sk_data_ready = sk_psock_strp_data_ready;
-	sk->sk_write_space = sk_psock_write_space;
+	WRITE_ONCE(sk->sk_data_ready, sk_psock_strp_data_ready);
+	WRITE_ONCE(sk->sk_write_space, sk_psock_write_space);
 }
 
 void sk_psock_stop_strp(struct sock *sk, struct sk_psock *psock)
@@ -1216,8 +1216,8 @@ void sk_psock_stop_strp(struct sock *sk, struct sk_psock *psock)
 	if (!psock->saved_data_ready)
 		return;
 
-	sk->sk_data_ready = psock->saved_data_ready;
-	psock->saved_data_ready = NULL;
+	WRITE_ONCE(sk->sk_data_ready, psock->saved_data_ready);
+	WRITE_ONCE(psock->saved_data_ready, NULL);
 	strp_stop(&psock->strp);
 }
 
@@ -1296,8 +1296,8 @@ void sk_psock_start_verdict(struct sock *sk, struct sk_psock *psock)
 		return;
 
 	psock->saved_data_ready = sk->sk_data_ready;
-	sk->sk_data_ready = sk_psock_verdict_data_ready;
-	sk->sk_write_space = sk_psock_write_space;
+	WRITE_ONCE(sk->sk_data_ready, sk_psock_verdict_data_ready);
+	WRITE_ONCE(sk->sk_write_space, sk_psock_write_space);
 }
 
 void sk_psock_stop_verdict(struct sock *sk, struct sk_psock *psock)
@@ -1308,6 +1308,6 @@ void sk_psock_stop_verdict(struct sock *sk, struct sk_psock *psock)
 	if (!psock->saved_data_ready)
 		return;
 
-	sk->sk_data_ready = psock->saved_data_ready;
+	WRITE_ONCE(sk->sk_data_ready, psock->saved_data_ready);
 	psock->saved_data_ready = NULL;
 }
net/ipv4/tcp.c +2 -2
index e35825656e6ea..f665c87edc0f7 100644
@@ -1398,7 +1398,7 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size)
 	err = sk_stream_error(sk, flags, err);
 	/* make sure we wake any epoll edge trigger waiter */
 	if (unlikely(tcp_rtx_and_write_queues_empty(sk) && err == -EAGAIN)) {
-		sk->sk_write_space(sk);
+		READ_ONCE(sk->sk_write_space)(sk);
 		tcp_chrono_stop(sk, TCP_CHRONO_SNDBUF_LIMITED);
 	}
 	if (binding)
@@ -4111,7 +4111,7 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname,
 		break;
 	case TCP_NOTSENT_LOWAT:
 		WRITE_ONCE(tp->notsent_lowat, val);
-		sk->sk_write_space(sk);
+		READ_ONCE(sk->sk_write_space)(sk);
 		break;
 	case TCP_INQ:
 		if (val > 1 || val < 0)
net/ipv4/tcp_bpf.c +1 -1
index ca8a5cb8e569d..d3d6a47af5270 100644
@@ -725,7 +725,7 @@ int tcp_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore)
 			WRITE_ONCE(sk->sk_prot->unhash, psock->saved_unhash);
 			tcp_update_ulp(sk, psock->sk_proto, psock->saved_write_space);
 		} else {
-			sk->sk_write_space = psock->saved_write_space;
+			WRITE_ONCE(sk->sk_write_space, psock->saved_write_space);
 			/* Pairs with lockless read in sk_clone_lock() */
 			sock_replace_proto(sk, psock->sk_proto);
 		}
net/ipv4/tcp_input.c +8 -6
index abd0d5c5a5e3f..834cd37276d59 100644
@@ -5151,7 +5151,7 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb)
 
 	if (unlikely(tcp_try_rmem_schedule(sk, skb, skb->truesize))) {
 		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPOFODROP);
-		sk->sk_data_ready(sk);
+		READ_ONCE(sk->sk_data_ready)(sk);
 		tcp_drop_reason(sk, skb, SKB_DROP_REASON_PROTO_MEM);
 		return;
 	}
@@ -5361,7 +5361,7 @@ int tcp_send_rcvq(struct sock *sk, struct msghdr *msg, size_t size)
 void tcp_data_ready(struct sock *sk)
 {
 	if (tcp_epollin_ready(sk, sk->sk_rcvlowat) || sock_flag(sk, SOCK_DONE))
-		sk->sk_data_ready(sk);
+		READ_ONCE(sk->sk_data_ready)(sk);
 }
 
 static void tcp_data_queue(struct sock *sk, struct sk_buff *skb)
@@ -5417,7 +5417,7 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb)
 			inet_csk(sk)->icsk_ack.pending |=
 					(ICSK_ACK_NOMEM | ICSK_ACK_NOW);
 			inet_csk_schedule_ack(sk);
-			sk->sk_data_ready(sk);
+			READ_ONCE(sk->sk_data_ready)(sk);
 
 			if (skb_queue_len(&sk->sk_receive_queue) && skb->len) {
 				reason = SKB_DROP_REASON_PROTO_MEM;
@@ -5859,7 +5859,9 @@ static void tcp_new_space(struct sock *sk)
 		tp->snd_cwnd_stamp = tcp_jiffies32;
 	}
 
-	INDIRECT_CALL_1(sk->sk_write_space, sk_stream_write_space, sk);
+	INDIRECT_CALL_1(READ_ONCE(sk->sk_write_space),
+			sk_stream_write_space,
+			sk);
 }
 
 /* Caller made space either from:
@@ -6065,7 +6067,7 @@ static void tcp_urg(struct sock *sk, struct sk_buff *skb, const struct tcphdr *t
 				BUG();
 			WRITE_ONCE(tp->urg_data, TCP_URG_VALID | tmp);
 			if (!sock_flag(sk, SOCK_DEAD))
-				sk->sk_data_ready(sk);
+				READ_ONCE(sk->sk_data_ready)(sk);
 		}
 	}
 }
@@ -7531,7 +7533,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
 			sock_put(fastopen_sk);
 			goto drop_and_free;
 		}
-		sk->sk_data_ready(sk);
+		READ_ONCE(sk->sk_data_ready)(sk);
 		bh_unlock_sock(fastopen_sk);
 		sock_put(fastopen_sk);
 	} else {
net/ipv4/tcp_minisocks.c +1 -1
index 95c30b6ec44cd..c70c29a3a0905 100644
@@ -990,7 +990,7 @@ enum skb_drop_reason tcp_child_process(struct sock *parent, struct sock *child,
 		reason = tcp_rcv_state_process(child, skb);
 		/* Wakeup parent, send SIGIO */
 		if (state == TCP_SYN_RECV && child->sk_state != state)
-			parent->sk_data_ready(parent);
+			READ_ONCE(parent->sk_data_ready)(parent);
 	} else {
 		/* Alas, it is possible again, because we do lookup
 		 * in main socket hash table and lock on listening
net/ipv4/udp.c +1 -1
index 860bd61ff047f..777199fa9502f 100644
@@ -1786,7 +1786,7 @@ int __udp_enqueue_schedule_skb(struct sock *sk, struct sk_buff *skb)
 		 * using prepare_to_wait_exclusive().
 		 */
 		while (nb) {
-			INDIRECT_CALL_1(sk->sk_data_ready,
+			INDIRECT_CALL_1(READ_ONCE(sk->sk_data_ready),
 					sock_def_readable, sk);
 			nb--;
 		}
net/ipv4/udp_bpf.c +1 -1
index 91233e37cd97a..779a3a03762f1 100644
@@ -158,7 +158,7 @@ int udp_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore)
 	int family = sk->sk_family == AF_INET ? UDP_BPF_IPV4 : UDP_BPF_IPV6;
 
 	if (restore) {
-		sk->sk_write_space = psock->saved_write_space;
+		WRITE_ONCE(sk->sk_write_space, psock->saved_write_space);
 		sock_replace_proto(sk, psock->sk_proto);
 		return 0;
 	}
net/unix/af_unix.c +4 -4
index 9dad3af700af3..79943fb348064 100644
@@ -1806,7 +1806,7 @@ static int unix_stream_connect(struct socket *sock, struct sockaddr *uaddr,
 	__skb_queue_tail(&other->sk_receive_queue, skb);
 	spin_unlock(&other->sk_receive_queue.lock);
 	unix_state_unlock(other);
-	other->sk_data_ready(other);
+	READ_ONCE(other->sk_data_ready)(other);
 	sock_put(other);
 	return 0;
 
@@ -2301,7 +2301,7 @@ static int unix_dgram_sendmsg(struct socket *sock, struct msghdr *msg,
 	scm_stat_add(other, skb);
 	skb_queue_tail(&other->sk_receive_queue, skb);
 	unix_state_unlock(other);
-	other->sk_data_ready(other);
+	READ_ONCE(other->sk_data_ready)(other);
 	sock_put(other);
 	scm_destroy(&scm);
 	return len;
@@ -2374,7 +2374,7 @@ static int queue_oob(struct sock *sk, struct msghdr *msg, struct sock *other,
 
 	sk_send_sigurg(other);
 	unix_state_unlock(other);
-	other->sk_data_ready(other);
+	READ_ONCE(other->sk_data_ready)(other);
 
 	return 0;
 out_unlock:
@@ -2502,7 +2502,7 @@ static int unix_stream_sendmsg(struct socket *sock, struct msghdr *msg,
 		spin_unlock(&other->sk_receive_queue.lock);
 
 		unix_state_unlock(other);
-		other->sk_data_ready(other);
+		READ_ONCE(other->sk_data_ready)(other);
 		sent += size;
 	}
 
Signature · 1 line
2.51.0
author maintainer
#234 lore raw

PATCH 228/314 net: ethernet: ti: am65-cpsw-nuss/cpsw-ale: Fix multicast entry handling in ALE table

In reply to Sasha Levin

From: Chintan Vankar <[email protected]>

[ Upstream commit be11a537224d72b906db6b98510619770298c8a4 ]

In the current implementation, flushing multicast entries in MAC mode incorrectly deletes entries for all ports instead of only the target port, disrupting multicast traffic on other ports. The cause is adding multicast entries by setting only host port bit, and not setting the MAC port bits.

Fix this by setting the MAC port's bit in the port mask while adding the multicast entry. Also fix the flush logic to preserve the host port bit during removal of MAC port and free ALE entries when mask contains only host port.

Fixes 5c50a856d550 ("drivers: net: ethernet: cpsw: add multicast address to ALE table")
---
 drivers/net/ethernet/ti/am65-cpsw-nuss.c | 2 +-
 drivers/net/ethernet/ti/cpsw_ale.c       | 9 ++++-----
 2 files changed, 5 insertions(+), 6 deletions(-)
drivers/net/ethernet/ti/am65-cpsw-nuss.c +1 -1
index 110eb2da8dbc1..77c2cf61c1fb4 100644
@@ -391,7 +391,7 @@ static void am65_cpsw_nuss_ndo_slave_set_rx_mode(struct net_device *ndev)
 	cpsw_ale_set_allmulti(common->ale,
 			      ndev->flags & IFF_ALLMULTI, port->port_id);
 
-	port_mask = ALE_PORT_HOST;
+	port_mask = BIT(port->port_id) | ALE_PORT_HOST;
 	/* Clear all mcast from ALE */
 	cpsw_ale_flush_multicast(common->ale, port_mask, -1);
 
drivers/net/ethernet/ti/cpsw_ale.c +4 -5
index fbe35af615a6f..9632ad3741de1 100644
@@ -455,14 +455,13 @@ static void cpsw_ale_flush_mcast(struct cpsw_ale *ale, u32 *ale_entry,
 				      ale->port_mask_bits);
 	if ((mask & port_mask) == 0)
 		return; /* ports dont intersect, not interested */
-	mask &= ~port_mask;
+	mask &= (~port_mask | ALE_PORT_HOST);
 
-	/* free if only remaining port is host port */
-	if (mask)
+	if (mask == 0x0 || mask == ALE_PORT_HOST)
+		cpsw_ale_set_entry_type(ale_entry, ALE_TYPE_FREE);
+	else
 		cpsw_ale_set_port_mask(ale_entry, mask,
 				       ale->port_mask_bits);
-	else
-		cpsw_ale_set_entry_type(ale_entry, ALE_TYPE_FREE);
 }
 
 int cpsw_ale_flush_multicast(struct cpsw_ale *ale, int port_mask, int vid)
Signature · 1 line
2.51.0
author maintainer
#235 lore raw

PATCH 229/314 nvme-multipath: fix leak on try_module_get failure

In reply to Sasha Levin

From: Keith Busch <[email protected]>

[ Upstream commit 0f5197ea9a73a4c406c75e6d8af3a13f7f96ae89 ]

We need to fall back to the synchronous removal if we can't get a reference on the module needed for the deferred removal.

Fixes 62188639ec16 ("nvme-multipath: introduce delayed removal of the multipath head node")
---
 drivers/nvme/host/multipath.c | 12 +++++-------
 1 file changed, 5 insertions(+), 7 deletions(-)
drivers/nvme/host/multipath.c +5 -7
index e35eccacee8c8..81ccdd91f7790 100644
@@ -1310,13 +1310,11 @@ void nvme_mpath_remove_disk(struct nvme_ns_head *head)
 	if (!list_empty(&head->list))
 		goto out;
 
-	if (head->delayed_removal_secs) {
-		/*
-		 * Ensure that no one could remove this module while the head
-		 * remove work is pending.
-		 */
-		if (!try_module_get(THIS_MODULE))
-			goto out;
+	/*
+	 * Ensure that no one could remove this module while the head
+	 * remove work is pending.
+	 */
+	if (head->delayed_removal_secs && try_module_get(THIS_MODULE)) {
 		mod_delayed_work(nvme_wq, &head->remove_work,
 				head->delayed_removal_secs * HZ);
 	} else {
Signature · 1 line
2.51.0
author maintainer
#236 lore raw

PATCH 230/314 inet: annotate data-races around isk->inet_num

In reply to Sasha Levin

From: Eric Dumazet <[email protected]>

[ Upstream commit 29252397bcc1e0a1f85e5c3bee59c325f5c26341 ]

UDP/TCP lookups are using RCU, thus isk->inet_num accesses should use READ_ONCE() and WRITE_ONCE() where needed.

Fixes 3ab5aee7fe84 ("net: Convert TCP & DCCP hash tables to use RCU / hlist_nulls")
---
 include/net/inet6_hashtables.h | 2 +-
 include/net/inet_hashtables.h  | 2 +-
 include/net/ip.h               | 2 +-
 net/ipv4/inet_hashtables.c     | 8 ++++----
 net/ipv4/tcp_diag.c            | 2 +-
 net/ipv6/inet6_hashtables.c    | 3 ++-
 6 files changed, 10 insertions(+), 9 deletions(-)
include/net/inet6_hashtables.h +1 -1
index 282e29237d936..c16de5b7963fd 100644
@@ -175,7 +175,7 @@ static inline bool inet6_match(const struct net *net, const struct sock *sk,
 {
 	if (!net_eq(sock_net(sk), net) ||
 	    sk->sk_family != AF_INET6 ||
-	    sk->sk_portpair != ports ||
+	    READ_ONCE(sk->sk_portpair) != ports ||
 	    !ipv6_addr_equal(&sk->sk_v6_daddr, saddr) ||
 	    !ipv6_addr_equal(&sk->sk_v6_rcv_saddr, daddr))
 		return false;
include/net/inet_hashtables.h +1 -1
index ac05a52d9e138..5a979dcab5383 100644
@@ -345,7 +345,7 @@ static inline bool inet_match(const struct net *net, const struct sock *sk,
 			      int dif, int sdif)
 {
 	if (!net_eq(sock_net(sk), net) ||
-	    sk->sk_portpair != ports ||
+	    READ_ONCE(sk->sk_portpair) != ports ||
 	    sk->sk_addrpair != cookie)
 	        return false;
 
include/net/ip.h +1 -1
index 380afb691c419..1ce79e62a76fb 100644
@@ -101,7 +101,7 @@ static inline void ipcm_init_sk(struct ipcm_cookie *ipcm,
 
 	ipcm->oif = READ_ONCE(inet->sk.sk_bound_dev_if);
 	ipcm->addr = inet->inet_saddr;
-	ipcm->protocol = inet->inet_num;
+	ipcm->protocol = READ_ONCE(inet->inet_num);
 }
 
 #define IPCB(skb) ((struct inet_skb_parm*)((skb)->cb))
net/ipv4/inet_hashtables.c +4 -4
index b7024e3d9ac3d..a57e33ff92d77 100644
@@ -200,7 +200,7 @@ static bool inet_bind2_bucket_addr_match(const struct inet_bind2_bucket *tb2,
 void inet_bind_hash(struct sock *sk, struct inet_bind_bucket *tb,
 		    struct inet_bind2_bucket *tb2, unsigned short port)
 {
-	inet_sk(sk)->inet_num = port;
+	WRITE_ONCE(inet_sk(sk)->inet_num, port);
 	inet_csk(sk)->icsk_bind_hash = tb;
 	inet_csk(sk)->icsk_bind2_hash = tb2;
 	sk_add_bind_node(sk, &tb2->owners);
@@ -224,7 +224,7 @@ static void __inet_put_port(struct sock *sk)
 	spin_lock(&head->lock);
 	tb = inet_csk(sk)->icsk_bind_hash;
 	inet_csk(sk)->icsk_bind_hash = NULL;
-	inet_sk(sk)->inet_num = 0;
+	WRITE_ONCE(inet_sk(sk)->inet_num, 0);
 	sk->sk_userlocks &= ~SOCK_CONNECT_BIND;
 
 	spin_lock(&head2->lock);
@@ -352,7 +352,7 @@ static inline int compute_score(struct sock *sk, const struct net *net,
 {
 	int score = -1;
 
-	if (net_eq(sock_net(sk), net) && sk->sk_num == hnum &&
+	if (net_eq(sock_net(sk), net) && READ_ONCE(sk->sk_num) == hnum &&
 			!ipv6_only_sock(sk)) {
 		if (sk->sk_rcv_saddr != daddr)
 			return -1;
@@ -1202,7 +1202,7 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row,
 
 		sk->sk_hash = 0;
 		inet_sk(sk)->inet_sport = 0;
-		inet_sk(sk)->inet_num = 0;
+		WRITE_ONCE(inet_sk(sk)->inet_num, 0);
 
 		if (tw)
 			inet_twsk_bind_unhash(tw, hinfo);
net/ipv4/tcp_diag.c +1 -1
index d83efd91f461c..7935702e394b2 100644
@@ -509,7 +509,7 @@ static void tcp_diag_dump(struct sk_buff *skb, struct netlink_callback *cb,
 			if (r->sdiag_family != AF_UNSPEC &&
 			    sk->sk_family != r->sdiag_family)
 				goto next_normal;
-			if (r->id.idiag_sport != htons(sk->sk_num) &&
+			if (r->id.idiag_sport != htons(READ_ONCE(sk->sk_num)) &&
 			    r->id.idiag_sport)
 				goto next_normal;
 			if (r->id.idiag_dport != sk->sk_dport &&
net/ipv6/inet6_hashtables.c +2 -1
index 5e1da088d8e11..182d38e6d6d8d 100644
@@ -95,7 +95,8 @@ static inline int compute_score(struct sock *sk, const struct net *net,
 {
 	int score = -1;
 
-	if (net_eq(sock_net(sk), net) && inet_sk(sk)->inet_num == hnum &&
+	if (net_eq(sock_net(sk), net) &&
+	    READ_ONCE(inet_sk(sk)->inet_num) == hnum &&
 	    sk->sk_family == PF_INET6) {
 		if (!ipv6_addr_equal(&sk->sk_v6_rcv_saddr, daddr))
 			return -1;
Signature · 1 line
2.51.0
author maintainer
#237 lore raw

PATCH 231/314 udp: Unhash auto-bound connected sk from 4-tuple hash table when disconnected.

In reply to Sasha Levin

From: Kuniyuki Iwashima <[email protected]>

[ Upstream commit 6996a2d2d0a64808c19c98002aeb5d9d1b2df6a4 ]

Let's say we bind() an UDP socket to the wildcard address with a non-zero port, connect() it to an address, and disconnect it from the address.

bind() sets SOCK_BINDPORT_LOCK on sk->sk_userlocks (but not SOCK_BINDADDR_LOCK), and connect() calls udp_lib_hash4() to put the socket into the 4-tuple hash table.

Then, __udp_disconnect() calls sk->sk_prot->rehash(sk).

It computes a new hash based on the wildcard address and moves the socket to a new slot in the 4-tuple hash table, leaving a garbage in the chain that no packet hits.

Let's remove such a socket from 4-tuple hash table when disconnected.

Note that udp_sk(sk)->udp_portaddr_hash needs to be udpated after udp_hash4_dec(hslot2) in udp_unhash4().

Fixes 78c91ae2c6de ("ipv4/udp: Add 4-tuple hash for connected socket")
---
 net/ipv4/udp.c | 25 +++++++++++++++----------
 1 file changed, 15 insertions(+), 10 deletions(-)
net/ipv4/udp.c +15 -10
index 777199fa9502f..024cb4f5978c1 100644
@@ -2266,7 +2266,6 @@ void udp_lib_rehash(struct sock *sk, u16 newhash, u16 newhash4)
 				     udp_sk(sk)->udp_port_hash);
 		hslot2 = udp_hashslot2(udptable, udp_sk(sk)->udp_portaddr_hash);
 		nhslot2 = udp_hashslot2(udptable, newhash);
-		udp_sk(sk)->udp_portaddr_hash = newhash;
 
 		if (hslot2 != nhslot2 ||
 		    rcu_access_pointer(sk->sk_reuseport_cb)) {
@@ -2300,19 +2299,25 @@ void udp_lib_rehash(struct sock *sk, u16 newhash, u16 newhash4)
 		if (udp_hashed4(sk)) {
 			spin_lock_bh(&hslot->lock);
 
-			udp_rehash4(udptable, sk, newhash4);
-			if (hslot2 != nhslot2) {
-				spin_lock(&hslot2->lock);
-				udp_hash4_dec(hslot2);
-				spin_unlock(&hslot2->lock);
-
-				spin_lock(&nhslot2->lock);
-				udp_hash4_inc(nhslot2);
-				spin_unlock(&nhslot2->lock);
+			if (inet_rcv_saddr_any(sk)) {
+				udp_unhash4(udptable, sk);
+			} else {
+				udp_rehash4(udptable, sk, newhash4);
+				if (hslot2 != nhslot2) {
+					spin_lock(&hslot2->lock);
+					udp_hash4_dec(hslot2);
+					spin_unlock(&hslot2->lock);
+
+					spin_lock(&nhslot2->lock);
+					udp_hash4_inc(nhslot2);
+					spin_unlock(&nhslot2->lock);
+				}
 			}
 
 			spin_unlock_bh(&hslot->lock);
 		}
+
+		udp_sk(sk)->udp_portaddr_hash = newhash;
 	}
 }
 EXPORT_IPV6_MOD(udp_lib_rehash);
Signature · 1 line
2.51.0
author maintainer
#238 lore raw

PATCH 232/314 tcp: give up on stronger sk_rcvbuf checks (for now)

In reply to Sasha Levin

From: Jakub Kicinski <[email protected]>

[ Upstream commit 026dfef287c07f37d4d4eef7a0b5a4bfdb29b32d ]

We hit another corner case which leads to TcpExtTCPRcvQDrop

Connections which send RPCs in the 20-80kB range over loopback experience spurious drops. The exact conditions for most of the drops I investigated are that:
- socket exchanged >1MB of data so its not completely fresh
- rcvbuf is around 128kB (default, hasn't grown)
- there is ~60kB of data in rcvq
- skb > 64kB arrives

The sum of skb->len (!) of both of the skbs (the one already in rcvq and the arriving one) is larger than rwnd.
My suspicion is that this happens because __tcp_select_window() rounds the rwnd up to (1 << wscale) if less than half of the rwnd has been consumed.

Eric suggests that given the number of Fixes we already have pointing to 1d2fbaad7cd8 it's probably time to give up on it, until a bigger revamp of rmem management.

Also while we could risk tweaking the rwnd math, there are other drops on workloads I investigated, after the commit in question, not explained by this phenomenon.

---
 net/ipv4/tcp_input.c | 16 +---------------
 1 file changed, 1 insertion(+), 15 deletions(-)
net/ipv4/tcp_input.c +1 -15
index 834cd37276d59..87e678903b977 100644
@@ -5100,25 +5100,11 @@ static void tcp_ofo_queue(struct sock *sk)
 static bool tcp_prune_ofo_queue(struct sock *sk, const struct sk_buff *in_skb);
 static int tcp_prune_queue(struct sock *sk, const struct sk_buff *in_skb);
 
-/* Check if this incoming skb can be added to socket receive queues
- * while satisfying sk->sk_rcvbuf limit.
- *
- * In theory we should use skb->truesize, but this can cause problems
- * when applications use too small SO_RCVBUF values.
- * When LRO / hw gro is used, the socket might have a high tp->scaling_ratio,
- * allowing RWIN to be close to available space.
- * Whenever the receive queue gets full, we can receive a small packet
- * filling RWIN, but with a high skb->truesize, because most NIC use 4K page
- * plus sk_buff metadata even when receiving less than 1500 bytes of payload.
- *
- * Note that we use skb->len to decide to accept or drop this packet,
- * but sk->sk_rmem_alloc is the sum of all skb->truesize.
- */
 static bool tcp_can_ingest(const struct sock *sk, const struct sk_buff *skb)
 {
 	unsigned int rmem = atomic_read(&sk->sk_rmem_alloc);
 
-	return rmem + skb->len <= sk->sk_rcvbuf;
+	return rmem <= sk->sk_rcvbuf;
 }
 
 static int tcp_try_rmem_schedule(struct sock *sk, const struct sk_buff *skb,
Signature · 1 line
2.51.0
author maintainer
#239 lore raw

PATCH 233/314 xsk: Fix fragment node deletion to prevent buffer leak

In reply to Sasha Levin

From: "Nikhil P. Rao" <[email protected]>

[ Upstream commit 60abb0ac11dccd6b98fd9182bc5f85b621688861 ]

After commit b692bf9a7543 ("xsk: Get rid of xdp_buff_xsk::xskb_list_node"), the list_node field is reused for both the xskb pool list and the buffer free list, this causes a buffer leak as described below.

xp_free() checks if a buffer is already on the free list using list_empty(&xskb->list_node). When list_del() is used to remove a node from the xskb pool list, it doesn't reinitialize the node pointers. This means list_empty() will return false even after the node has been removed, causing xp_free() to incorrectly skip adding the buffer to the free list.

Fix this by using list_del_init() instead of list_del() in all fragment handling paths, this ensures the list node is reinitialized after removal, allowing the list_empty() to work correctly.

---
 include/net/xdp_sock_drv.h | 6 +++---
 net/xdp/xsk.c              | 2 +-
 2 files changed, 4 insertions(+), 4 deletions(-)
include/net/xdp_sock_drv.h +3 -3
index 4f2d3268a6769..99b6c3358e363 100644
@@ -118,7 +118,7 @@ static inline void xsk_buff_free(struct xdp_buff *xdp)
 		goto out;
 
 	list_for_each_entry_safe(pos, tmp, xskb_list, list_node) {
-		list_del(&pos->list_node);
+		list_del_init(&pos->list_node);
 		xp_free(pos);
 	}
 
@@ -153,7 +153,7 @@ static inline struct xdp_buff *xsk_buff_get_frag(const struct xdp_buff *first)
 	frag = list_first_entry_or_null(&xskb->pool->xskb_list,
 					struct xdp_buff_xsk, list_node);
 	if (frag) {
-		list_del(&frag->list_node);
+		list_del_init(&frag->list_node);
 		ret = &frag->xdp;
 	}
 
@@ -164,7 +164,7 @@ static inline void xsk_buff_del_frag(struct xdp_buff *xdp)
 {
 	struct xdp_buff_xsk *xskb = container_of(xdp, struct xdp_buff_xsk, xdp);
 
-	list_del(&xskb->list_node);
+	list_del_init(&xskb->list_node);
 }
 
 static inline struct xdp_buff *xsk_buff_get_head(struct xdp_buff *first)
net/xdp/xsk.c +1 -1
index 69bbcca8ac753..0d3fc72147f84 100644
@@ -186,7 +186,7 @@ static int xsk_rcv_zc(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len)
 		err = __xsk_rcv_zc(xs, pos, len, contd);
 		if (err)
 			goto err;
-		list_del(&pos->list_node);
+		list_del_init(&pos->list_node);
 	}
 
 	return 0;
Signature · 1 line
2.51.0
author maintainer
#240 lore raw

PATCH 234/314 xsk: Fix zero-copy AF_XDP fragment drop

In reply to Sasha Levin

From: "Nikhil P. Rao" <[email protected]>

[ Upstream commit f7387d6579d65efd490a864254101cb665f2e7a7 ]

AF_XDP should ensure that only a complete packet is sent to application. In the zero-copy case, if the Rx queue gets full as fragments are being enqueued, the remaining fragments are dropped.

For the multi-buffer case, add a check to ensure that the Rx queue has enough space for all fragments of a packet before starting to enqueue them.

---
 net/xdp/xsk.c | 24 +++++++++++++++---------
 1 file changed, 15 insertions(+), 9 deletions(-)
net/xdp/xsk.c +15 -9
index 0d3fc72147f84..a78cdc3356937 100644
@@ -167,25 +167,31 @@ static int xsk_rcv_zc(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len)
 	struct xdp_buff_xsk *pos, *tmp;
 	struct list_head *xskb_list;
 	u32 contd = 0;
+	u32 num_desc;
 	int err;
 
-	if (frags)
-		contd = XDP_PKT_CONTD;
+	if (likely(!frags)) {
+		err = __xsk_rcv_zc(xs, xskb, len, contd);
+		if (err)
+			goto err;
+		return 0;
+	}
 
-	err = __xsk_rcv_zc(xs, xskb, len, contd);
-	if (err)
+	contd = XDP_PKT_CONTD;
+	num_desc = xdp_get_shared_info_from_buff(xdp)->nr_frags + 1;
+	if (xskq_prod_nb_free(xs->rx, num_desc) < num_desc) {
+		xs->rx_queue_full++;
+		err = -ENOBUFS;
 		goto err;
-	if (likely(!frags))
-		return 0;
+	}
 
+	__xsk_rcv_zc(xs, xskb, len, contd);
 	xskb_list = &xskb->pool->xskb_list;
 	list_for_each_entry_safe(pos, tmp, xskb_list, list_node) {
 		if (list_is_singular(xskb_list))
 			contd = 0;
 		len = pos->xdp.data_end - pos->xdp.data;
-		err = __xsk_rcv_zc(xs, pos, len, contd);
-		if (err)
-			goto err;
+		__xsk_rcv_zc(xs, pos, len, contd);
 		list_del_init(&pos->list_node);
 	}
 
Signature · 1 line
2.51.0
author maintainer
#241 lore raw

PATCH 235/314 dpaa2-switch: Fix interrupt storm after receiving bad if_id in IRQ handler

In reply to Sasha Levin

From: Guenter Roeck <[email protected]>

[ Upstream commit 74badb9c20b1a9c02a95c735c6d3cd6121679c93 ]

Commit 31a7a0bbeb00 ("dpaa2-switch: add bounds check for if_id in IRQ handler") introduces a range check for if_id to avoid an out-of-bounds access. If an out-of-bounds if_id is detected, the interrupt status is not cleared. This may result in an interrupt storm.

Clear the interrupt status after detecting an out-of-bounds if_id to avoid the problem.

Found by an experimental AI code review agent at Google.

Fixes 31a7a0bbeb00 ("dpaa2-switch: add bounds check for if_id in IRQ handler")
Cc Junrui Luo <[email protected]>
---
 drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)
drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c +2 -1
index 78e21b46a5ba8..e212a014c8d41 100644
@@ -1533,7 +1533,7 @@ static irqreturn_t dpaa2_switch_irq0_handler_thread(int irq_num, void *arg)
 	if_id = (status & 0xFFFF0000) >> 16;
 	if (if_id >= ethsw->sw_attr.num_ifs) {
 		dev_err(dev, "Invalid if_id %d in IRQ status\n", if_id);
-		goto out;
+		goto out_clear;
 	}
 	port_priv = ethsw->ports[if_id];
 
@@ -1553,6 +1553,7 @@ static irqreturn_t dpaa2_switch_irq0_handler_thread(int irq_num, void *arg)
 			dpaa2_switch_port_connect_mac(port_priv);
 	}
 
+out_clear:
 	err = dpsw_clear_irq_status(ethsw->mc_io, 0, ethsw->dpsw_handle,
 				    DPSW_IRQ_INDEX_IF, status);
 	if (err)
Signature · 1 line
2.51.0
author maintainer
#242 lore raw

PATCH 236/314 atm: lec: fix null-ptr-deref in lec_arp_clear_vccs

In reply to Sasha Levin

From: Jiayuan Chen <[email protected]>

[ Upstream commit 101bacb303e89dc2e0640ae6a5e0fb97c4eb45bb ]

syzkaller reported a null-ptr-deref in lec_arp_clear_vccs(). This issue can be easily reproduced using the syzkaller reproducer.

In the ATM LANE (LAN Emulation) module, the same atm_vcc can be shared by multiple lec_arp_table entries (e.g., via entry->vcc or entry->recv_vcc). When the underlying VCC is closed, lec_vcc_close() iterates over all ARP entries and calls lec_arp_clear_vccs() for each matched entry.

For example, when lec_vcc_close() iterates through the hlists in priv->lec_arp_empty_ones or other ARP tables:

1. In the first iteration, for the first matched ARP entry sharing the VCC, lec_arp_clear_vccs() frees the associated vpriv (which is vcc->user_back) and sets vcc->user_back to NULL.
2. In the second iteration, for the next matched ARP entry sharing the same VCC, lec_arp_clear_vccs() is called again. It obtains a NULL vpriv from vcc->user_back (via LEC_VCC_PRIV(vcc)) and then attempts to dereference it via vcc->pop = vpriv->old_pop, leading to a null-ptr-deref crash.

Fix this by adding a null check for vpriv before dereferencing it. If vpriv is already NULL, it means the VCC has been cleared by a previous call, so we can safely skip the cleanup and just clear the entry's vcc/recv_vcc pointers.

The entire cleanup block (including vcc_release_async()) is placed inside the vpriv guard because a NULL vpriv indicates the VCC has already been fully released by a prior iteration — repeating the teardown would redundantly set flags and trigger callbacks on an already-closing socket.

The Fixes tag points to the initial commit because the entry->vcc path has been vulnerable since the original code. The entry->recv_vcc path was later added by commit 8d9f73c0ad2f ("atm: fix a memory leak of vcc->user_back") with the same pattern, and both paths are fixed here.

---
 net/atm/lec.c | 26 +++++++++++++++-----------
 1 file changed, 15 insertions(+), 11 deletions(-)
net/atm/lec.c +15 -11
index afb8d3eb21850..c39dc5d367979 100644
@@ -1260,24 +1260,28 @@ static void lec_arp_clear_vccs(struct lec_arp_table *entry)
 		struct lec_vcc_priv *vpriv = LEC_VCC_PRIV(vcc);
 		struct net_device *dev = (struct net_device *)vcc->proto_data;
 
-		vcc->pop = vpriv->old_pop;
-		if (vpriv->xoff)
-			netif_wake_queue(dev);
-		kfree(vpriv);
-		vcc->user_back = NULL;
-		vcc->push = entry->old_push;
-		vcc_release_async(vcc, -EPIPE);
+		if (vpriv) {
+			vcc->pop = vpriv->old_pop;
+			if (vpriv->xoff)
+				netif_wake_queue(dev);
+			kfree(vpriv);
+			vcc->user_back = NULL;
+			vcc->push = entry->old_push;
+			vcc_release_async(vcc, -EPIPE);
+		}
 		entry->vcc = NULL;
 	}
 	if (entry->recv_vcc) {
 		struct atm_vcc *vcc = entry->recv_vcc;
 		struct lec_vcc_priv *vpriv = LEC_VCC_PRIV(vcc);
 
-		kfree(vpriv);
-		vcc->user_back = NULL;
+		if (vpriv) {
+			kfree(vpriv);
+			vcc->user_back = NULL;
 
-		entry->recv_vcc->push = entry->old_recv_push;
-		vcc_release_async(entry->recv_vcc, -EPIPE);
+			entry->recv_vcc->push = entry->old_recv_push;
+			vcc_release_async(entry->recv_vcc, -EPIPE);
+		}
 		entry->recv_vcc = NULL;
 	}
 }
Signature · 1 line
2.51.0
author maintainer
#243 lore raw

PATCH 237/314 net: ti: icssg-prueth: Fix ping failure after offload mode setup when link speed is not 1G

In reply to Sasha Levin

From: MD Danish Anwar <[email protected]>

[ Upstream commit 147792c395db870756a0dc87ce656c75ae7ab7e8 ]

When both eth interfaces with links up are added to a bridge or hsr interface, ping fails if the link speed is not 1Gbps (e.g., 100Mbps).

The issue is seen because when switching to offload (bridge/hsr) mode, prueth_emac_restart() restarts the firmware and clears DRAM with memset_io(), setting all memory to 0. This includes PORT_LINK_SPEED_OFFSET which firmware reads for link speed. The value 0 corresponds to FW_LINK_SPEED_1G (0x00), so for 1Gbps links the default value is correct and ping works. For 100Mbps links, the firmware needs FW_LINK_SPEED_100M (0x01) but gets 0 instead, causing ping to fail. The function emac_adjust_link() is called to reconfigure, but it detects no state change (emac->link is still 1, speed/duplex match PHY) so new_state remains false and icssg_config_set_speed() is never called to correct the firmware speed value.

The fix resets emac->link to 0 before calling emac_adjust_link() in prueth_emac_common_start(). This forces new_state=true, ensuring icssg_config_set_speed() is called to write the correct speed value to firmware memory.

Fixes 06feac15406f ("net: ti: icssg-prueth: Fix emac link speed handling")
---
 drivers/net/ethernet/ti/icssg/icssg_prueth.c | 8 ++++++++
 1 file changed, 8 insertions(+)
drivers/net/ethernet/ti/icssg/icssg_prueth.c +8 -0
index e42d0fdefee12..07489564270b2 100644
@@ -270,6 +270,14 @@ static int prueth_emac_common_start(struct prueth *prueth)
 		if (ret)
 			goto disable_class;
 
+		/* Reset link state to force reconfiguration in
+		 * emac_adjust_link(). Without this, if the link was already up
+		 * before restart, emac_adjust_link() won't detect any state
+		 * change and will skip critical configuration like writing
+		 * speed to firmware.
+		 */
+		emac->link = 0;
+
 		mutex_lock(&emac->ndev->phydev->lock);
 		emac_adjust_link(emac->ndev);
 		mutex_unlock(&emac->ndev->phydev->lock);
Signature · 1 line
2.51.0
author maintainer
#244 lore raw

PATCH 238/314 amd-xgbe: fix MAC_TCR_SS register width for 2.5G and 10M speeds

In reply to Sasha Levin

From: Raju Rangoju <[email protected]>

[ Upstream commit 9439a661c2e80485406ce2c90b107ca17858382d ]

Extend the MAC_TCR_SS (Speed Select) register field width from 2 bits to 3 bits to properly support all speed settings.

The MAC_TCR register's SS field encoding requires 3 bits to represent all supported speeds:
- 0x00: 10Gbps (XGMII)
- 0x02: 2.5Gbps (GMII) / 100Mbps
- 0x03: 1Gbps / 10Mbps
- 0x06: 2.5Gbps (XGMII) - P100a only

With only 2 bits, values 0x04-0x07 cannot be represented, which breaks 2.5G XGMII mode on newer platforms and causes incorrect speed select values to be programmed.

---
 drivers/net/ethernet/amd/xgbe/xgbe-common.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/net/ethernet/amd/xgbe/xgbe-common.h +1 -1
index 62b01de93db49..826c5caa70d71 100644
@@ -431,7 +431,7 @@
 #define MAC_SSIR_SSINC_INDEX		16
 #define MAC_SSIR_SSINC_WIDTH		8
 #define MAC_TCR_SS_INDEX		29
-#define MAC_TCR_SS_WIDTH		2
+#define MAC_TCR_SS_WIDTH		3
 #define MAC_TCR_TE_INDEX		0
 #define MAC_TCR_TE_WIDTH		1
 #define MAC_TCR_VNE_INDEX		24
Signature · 1 line
2.51.0
author maintainer
#245 lore raw

PATCH 239/314 can: bcm: fix locking for bcm_op runtime updates

In reply to Sasha Levin

From: Oliver Hartkopp <[email protected]>

[ Upstream commit c35636e91e392e1540949bbc67932167cb48bc3a ]

Commit c2aba69d0c36 ("can: bcm: add locking for bcm_op runtime updates") added a locking for some variables that can be modified at runtime when updating the sending bcm_op with a new TX_SETUP command in bcm_tx_setup().

Usually the RX_SETUP only handles and filters incoming traffic with one
exception: When the RX_RTR_FRAME flag is set a predefined CAN frame is sent when a specific RTR frame is received. Therefore the rx bcm_op uses bcm_can_tx() which uses the bcm_tx_lock that was only initialized in bcm_tx_setup(). Add the missing spin_lock_init() when allocating the bcm_op in bcm_rx_setup() to handle the RTR case properly.

---
 net/can/bcm.c | 1 +
 1 file changed, 1 insertion(+)
net/can/bcm.c +1 -0
index 5e690a2377e48..756acfd20c6c2 100644
@@ -1170,6 +1170,7 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 		if (!op)
 			return -ENOMEM;
 
+		spin_lock_init(&op->bcm_tx_lock);
 		op->can_id = msg_head->can_id;
 		op->nframes = msg_head->nframes;
 		op->cfsiz = CFSIZ(msg_head->flags);
Signature · 1 line
2.51.0
author maintainer
#246 lore raw

PATCH 240/314 can: mcp251x: fix deadlock in error path of mcp251x_open

In reply to Sasha Levin

From: Alban Bedel <[email protected]>

[ Upstream commit ab3f894de216f4a62adc3b57e9191888cbf26885 ]

The mcp251x_open() function call free_irq() in its error path with the mpc_lock mutex held. But if an interrupt already occurred the interrupt handler will be waiting for the mpc_lock and free_irq() will deadlock waiting for the handler to finish.

This issue is similar to the one fixed in commit 7dd9c26bd6cf ("can:
mcp251x: fix deadlock if an interrupt occurs during mcp251x_open") but for the error path.

To solve this issue move the call to free_irq() after the lock is released. Setting priv->force_quit = 1 beforehand ensure that the IRQ handler will exit right away once it acquired the lock.

Fixes bf66f3736a94 ("can: mcp251x: Move to threaded interrupts instead of workqueues.")
---
 drivers/net/can/spi/mcp251x.c | 15 ++++++++++++++-
 1 file changed, 14 insertions(+), 1 deletion(-)
drivers/net/can/spi/mcp251x.c +14 -1
index b797e08499d70..b46262e791301 100644
@@ -1214,6 +1214,7 @@ static int mcp251x_open(struct net_device *net)
 {
 	struct mcp251x_priv *priv = netdev_priv(net);
 	struct spi_device *spi = priv->spi;
+	bool release_irq = false;
 	unsigned long flags = 0;
 	int ret;
 
@@ -1257,12 +1258,24 @@ static int mcp251x_open(struct net_device *net)
 	return 0;
 
 out_free_irq:
-	free_irq(spi->irq, priv);
+	/* The IRQ handler might be running, and if so it will be waiting
+	 * for the lock. But free_irq() must wait for the handler to finish
+	 * so calling it here would deadlock.
+	 *
+	 * Setting priv->force_quit will let the handler exit right away
+	 * without any access to the hardware. This make it safe to call
+	 * free_irq() after the lock is released.
+	 */
+	priv->force_quit = 1;
+	release_irq = true;
+
 	mcp251x_hw_sleep(spi);
 out_close:
 	mcp251x_power_enable(priv->transceiver, 0);
 	close_candev(net);
 	mutex_unlock(&priv->mcp_lock);
+	if (release_irq)
+		free_irq(spi->irq, priv);
 	return ret;
 }
 
Signature · 1 line
2.51.0
author maintainer
#247 lore raw

PATCH 241/314 wifi: rsi: Don't default to -EOPNOTSUPP in rsi_mac80211_config

In reply to Sasha Levin

From: Sebastian Krzyszkowiak <[email protected]>

[ Upstream commit d973b1039ccde6b241b438d53297edce4de45b5c ]

This triggers a WARN_ON in ieee80211_hw_conf_init and isn't the expected behavior from the driver - other drivers default to 0 too.

Fixes 0a44dfc07074 ("wifi: mac80211: simplify non-chanctx drivers")
---
 drivers/net/wireless/rsi/rsi_91x_mac80211.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/net/wireless/rsi/rsi_91x_mac80211.c +1 -1
index 8c8e074a3a705..c7ae8031436ae 100644
@@ -668,7 +668,7 @@ static int rsi_mac80211_config(struct ieee80211_hw *hw,
 	struct rsi_hw *adapter = hw->priv;
 	struct rsi_common *common = adapter->priv;
 	struct ieee80211_conf *conf = &hw->conf;
-	int status = -EOPNOTSUPP;
+	int status = 0;
 
 	mutex_lock(&common->mutex);
 
Signature · 1 line
2.51.0
author maintainer
#248 lore raw

PATCH 242/314 drm/syncobj: Fix handle <-> fd ioctls with dirty stack

In reply to Sasha Levin

From: Julian Orth <[email protected]>

[ Upstream commit 2e3649e237237258a08d75afef96648dd2b379f7 ]

Consider the following application:

    #include <fcntl.h>
    #include <string.h>
    #include <drm/drm.h>
    #include <sys/ioctl.h>

    int main(void) {
        int fd = open("/dev/dri/renderD128", O_RDWR);
        struct drm_syncobj_create arg1;
        ioctl(fd, DRM_IOCTL_SYNCOBJ_CREATE, &arg1);
        struct drm_syncobj_handle arg2;
        memset(&arg2, 1, sizeof(arg2)); // simulate dirty stack
        arg2.handle = arg1.handle;
        arg2.flags = 0;
        arg2.fd = 0;
        arg2.pad = 0;
        // arg2.point = 0; // userspace is required to set point to 0
        ioctl(fd, DRM_IOCTL_SYNCOBJ_HANDLE_TO_FD, &arg2);
    }

The last ioctl returns EINVAL because args->point is not 0. However, userspace developed against older kernel versions is not aware of the new point field and might therefore not initialize it.

The correct check would be

    if (args->flags & DRM_SYNCOBJ_FD_TO_HANDLE_FLAGS_TIMELINE)
        return -EINVAL;

However, there might already be userspace that relies on this not returning an error as long as point == 0. Therefore use the more lenient check.

Fixes c2d3a7300695 ("drm/syncobj: Extend EXPORT_SYNC_FILE for timeline syncobjs")
---
 drivers/gpu/drm/drm_syncobj.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)
drivers/gpu/drm/drm_syncobj.c +2 -2
index e1b0fa4000cdd..7eb2cdbc574a0 100644
@@ -900,7 +900,7 @@ drm_syncobj_handle_to_fd_ioctl(struct drm_device *dev, void *data,
 		return drm_syncobj_export_sync_file(file_private, args->handle,
 						    point, &args->fd);
 
-	if (args->point)
+	if (point)
 		return -EINVAL;
 
 	return drm_syncobj_handle_to_fd(file_private, args->handle,
@@ -934,7 +934,7 @@ drm_syncobj_fd_to_handle_ioctl(struct drm_device *dev, void *data,
 							  args->handle,
 							  point);
 
-	if (args->point)
+	if (point)
 		return -EINVAL;
 
 	return drm_syncobj_fd_to_handle(file_private, args->fd,
Signature · 1 line
2.51.0
author maintainer
#249 lore raw

PATCH 243/314 drm/xe: Do not preempt fence signaling CS instructions

In reply to Sasha Levin

From: Matthew Brost <[email protected]>

[ Upstream commit cdc8a1e11f4d5b480ec750e28010c357185b95a6 ]

If a batch buffer is complete, it makes little sense to preempt the fence signaling instructions in the ring, as the largest portion of the work (the batch buffer) is already done and fence signaling consists of only a few instructions. If these instructions are preempted, the GuC would need to perform a context switch just to signal the fence, which is costly and delays fence signaling. Avoid this scenario by disabling preemption immediately after the BB start instruction and re-enabling it after executing the fence signaling instructions.

Fixes dd08ebf6c352 ("drm/xe: Introduce a new DRM driver for Intel GPUs")
Cc Daniele Ceraolo Spurio <[email protected]>
Cc Carlos Santa <[email protected]>
(cherry picked from commit 2bcbf2dcde0c839a73af664a3c77d4e77d58a3eb)
---
 drivers/gpu/drm/xe/xe_ring_ops.c | 9 +++++++++
 1 file changed, 9 insertions(+)
drivers/gpu/drm/xe/xe_ring_ops.c +9 -0
index d71837773d6c6..e0082b55e2162 100644
@@ -265,6 +265,9 @@ static void __emit_job_gen12_simple(struct xe_sched_job *job, struct xe_lrc *lrc
 
 	i = emit_bb_start(batch_addr, ppgtt_flag, dw, i);
 
+	/* Don't preempt fence signaling */
+	dw[i++] = MI_ARB_ON_OFF | MI_ARB_DISABLE;
+
 	if (job->user_fence.used) {
 		i = emit_flush_dw(dw, i);
 		i = emit_store_imm_ppgtt_posted(job->user_fence.addr,
@@ -328,6 +331,9 @@ static void __emit_job_gen12_video(struct xe_sched_job *job, struct xe_lrc *lrc,
 
 	i = emit_bb_start(batch_addr, ppgtt_flag, dw, i);
 
+	/* Don't preempt fence signaling */
+	dw[i++] = MI_ARB_ON_OFF | MI_ARB_DISABLE;
+
 	if (job->user_fence.used) {
 		i = emit_flush_dw(dw, i);
 		i = emit_store_imm_ppgtt_posted(job->user_fence.addr,
@@ -377,6 +383,9 @@ static void __emit_job_gen12_render_compute(struct xe_sched_job *job,
 
 	i = emit_bb_start(batch_addr, ppgtt_flag, dw, i);
 
+	/* Don't preempt fence signaling */
+	dw[i++] = MI_ARB_ON_OFF | MI_ARB_DISABLE;
+
 	i = emit_render_cache_flush(job, dw, i);
 
 	if (job->user_fence.used)
Signature · 1 line
2.51.0
author maintainer
#250 lore raw

PATCH 244/314 drm/xe/configfs: Free ctx_restore_mid_bb in release

In reply to Sasha Levin

From: Shuicheng Lin <[email protected]>

[ Upstream commit e377182f0266f46f02d01838e6bde67b9dac0d66 ]

ctx_restore_mid_bb memory is allocated in wa_bb_store(), but xe_config_device_release() only frees ctx_restore_post_bb.

Free ctx_restore_mid_bb[0].cs as well to avoid leaking the allocation when the configfs device is removed.

Fixes b30d5de3d40c ("drm/xe/configfs: Add mid context restore bb")
(cherry picked from commit a235e7d0098337c3f2d1e8f3610c719a589e115f)
---
 drivers/gpu/drm/xe/xe_configfs.c | 1 +
 1 file changed, 1 insertion(+)
drivers/gpu/drm/xe/xe_configfs.c +1 -0
index 6688b2954d20b..08f379cb5321f 100644
@@ -688,6 +688,7 @@ static void xe_config_device_release(struct config_item *item)
 
 	mutex_destroy(&dev->lock);
 
+	kfree(dev->config.ctx_restore_mid_bb[0].cs);
 	kfree(dev->config.ctx_restore_post_bb[0].cs);
 	kfree(dev);
 }
Signature · 1 line
2.51.0
author maintainer
#251 lore raw

PATCH 245/314 rust: kunit: fix warning when !CONFIG_PRINTK

In reply to Sasha Levin

From: Alexandre Courbot <[email protected]>

[ Upstream commit 7dd34dfc8dfa92a7244242098110388367996ac3 ]

If CONFIG_PRINTK is not set, then the following warnings are issued during build:

warning: unused variable: args

    --> ../rust/kernel/kunit.rs:16:12
    |

16 | pub fn err(args: fmt::Arguments<'_>) {
| ^^^^ help: if this is intentional, prefix it with an underscore: _args
|
= note: #[warn(unused_variables)] (part of #[warn(unused)]) on by default

warning: unused variable: args

    --> ../rust/kernel/kunit.rs:32:13
    |

32 | pub fn info(args: fmt::Arguments<'_>) {
| ^^^^ help: if this is intentional, prefix it with an underscore: _args

Fix this by adding a no-op assignment using args when CONFIG_PRINTK is not set.

Fixes a66d733da801 ("rust: support running Rust documentation tests as KUnit ones")
---
 rust/kernel/kunit.rs | 8 ++++++++
 1 file changed, 8 insertions(+)
rust/kernel/kunit.rs +8 -0
index 79436509dd73d..8907b6f89ece5 100644
@@ -17,6 +17,10 @@
 /// Public but hidden since it should only be used from KUnit generated code.
 #[doc(hidden)]
 pub fn err(args: fmt::Arguments<'_>) {
+    // `args` is unused if `CONFIG_PRINTK` is not set - this avoids a build-time warning.
+    #[cfg(not(CONFIG_PRINTK))]
+    let _ = args;
+
     // SAFETY: The format string is null-terminated and the `%pA` specifier matches the argument we
     // are passing.
     #[cfg(CONFIG_PRINTK)]
@@ -33,6 +37,10 @@ pub fn err(args: fmt::Arguments<'_>) {
 /// Public but hidden since it should only be used from KUnit generated code.
 #[doc(hidden)]
 pub fn info(args: fmt::Arguments<'_>) {
+    // `args` is unused if `CONFIG_PRINTK` is not set - this avoids a build-time warning.
+    #[cfg(not(CONFIG_PRINTK))]
+    let _ = args;
+
     // SAFETY: The format string is null-terminated and the `%pA` specifier matches the argument we
     // are passing.
     #[cfg(CONFIG_PRINTK)]
Signature · 1 line
2.51.0
author maintainer
#252 lore raw

PATCH 246/314 kunit: tool: copy caller args in run_kernel to prevent mutation

In reply to Sasha Levin

From: Shuvam Pandey <[email protected]>

[ Upstream commit 40804c4974b8df2adab72f6475d343eaff72b7f6 ]

run_kernel() appended KUnit flags directly to the caller-provided args list. When exec_tests() calls run_kernel() repeatedly (e.g. with --run_isolated), each call mutated the same list, causing later runs to inherit stale filter_glob values and duplicate kunit.enable flags.

Fix this by copying args at the start of run_kernel(). Add a regression test that calls run_kernel() twice with the same list and verifies the original remains unchanged.

Fixes ff9e09a3762f ("kunit: tool: support running each suite/test separately")
---
 tools/testing/kunit/kunit_kernel.py    |  6 ++++--
 tools/testing/kunit/kunit_tool_test.py | 26 ++++++++++++++++++++++++++
 2 files changed, 30 insertions(+), 2 deletions(-)
tools/testing/kunit/kunit_kernel.py +4 -2
index 260d8d9aa1db4..2998e1bc088b2 100644
@@ -346,8 +346,10 @@ class LinuxSourceTree:
 		return self.validate_config(build_dir)
 
 	def run_kernel(self, args: Optional[List[str]]=None, build_dir: str='', filter_glob: str='', filter: str='', filter_action: Optional[str]=None, timeout: Optional[int]=None) -> Iterator[str]:
-		if not args:
-			args = []
+		# Copy to avoid mutating the caller-supplied list. exec_tests() reuses
+		# the same args across repeated run_kernel() calls (e.g. --run_isolated),
+		# so appending to the original would accumulate stale flags on each call.
+		args = list(args) if args else []
 		if filter_glob:
 			args.append('kunit.filter_glob=' + filter_glob)
 		if filter:
tools/testing/kunit/kunit_tool_test.py +26 -0
index bbba921e0eacb..ed45bac1548d9 100755
@@ -489,6 +489,32 @@ class LinuxSourceTreeTest(unittest.TestCase):
 			with open(kunit_kernel.get_outfile_path(build_dir), 'rt') as outfile:
 				self.assertEqual(outfile.read(), 'hi\nbye\n', msg='Missing some output')
 
+	def test_run_kernel_args_not_mutated(self):
+		"""Verify run_kernel() copies args so callers can reuse them."""
+		start_calls = []
+
+		def fake_start(start_args, unused_build_dir):
+			start_calls.append(list(start_args))
+			return subprocess.Popen(['printf', 'KTAP version 1\n'],
+						text=True, stdout=subprocess.PIPE)
+
+		with tempfile.TemporaryDirectory('') as build_dir:
+			tree = kunit_kernel.LinuxSourceTree(build_dir,
+					kunitconfig_paths=[os.devnull])
+			with mock.patch.object(tree._ops, 'start', side_effect=fake_start), \
+			     mock.patch.object(kunit_kernel.subprocess, 'call'):
+				kernel_args = ['mem=1G']
+				for _ in tree.run_kernel(args=kernel_args, build_dir=build_dir,
+							 filter_glob='suite.test1'):
+					pass
+				for _ in tree.run_kernel(args=kernel_args, build_dir=build_dir,
+							 filter_glob='suite.test2'):
+					pass
+				self.assertEqual(kernel_args, ['mem=1G'],
+					'run_kernel() should not modify caller args')
+				self.assertIn('kunit.filter_glob=suite.test1', start_calls[0])
+				self.assertIn('kunit.filter_glob=suite.test2', start_calls[1])
+
 	def test_build_reconfig_no_config(self):
 		with tempfile.TemporaryDirectory('') as build_dir:
 			with open(kunit_kernel.get_kunitconfig_path(build_dir), 'w') as f:
Signature · 1 line
2.51.0
author maintainer
#253 lore raw

PATCH 247/314 net: dsa: realtek: rtl8365mb: fix rtl8365mb_phy_ocp_write return value

In reply to Sasha Levin

From: Mieczyslaw Nalewaj <[email protected]>

[ Upstream commit 7cbe98f7bef965241a5908d50d557008cf998aee ]

Function rtl8365mb_phy_ocp_write() always returns 0, even when an error occurs during register access. This patch fixes the return value to propagate the actual error code from regmap operations.

---
 drivers/net/dsa/realtek/rtl8365mb.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/net/dsa/realtek/rtl8365mb.c +1 -1
index 964a56ee16cc9..d06b384d47643 100644
@@ -769,7 +769,7 @@ static int rtl8365mb_phy_ocp_write(struct realtek_priv *priv, int phy,
 out:
 	rtl83xx_unlock(priv);
 
-	return 0;
+	return ret;
 }
 
 static int rtl8365mb_phy_read(struct realtek_priv *priv, int phy, int regnum)
Signature · 1 line
2.51.0
author maintainer
#254 lore raw

PATCH 248/314 bpf/bonding: reject vlan+srcmac xmit_hash_policy change when XDP is loaded

In reply to Sasha Levin

From: Jiayuan Chen <[email protected]>

[ Upstream commit 479d589b40b836442bbdadc3fdb37f001bb67f26 ]

bond_option_mode_set() already rejects mode changes that would make a loaded XDP program incompatible via bond_xdp_check(). However, bond_option_xmit_hash_policy_set() has no such guard.

For 802.3ad and balance-xor modes, bond_xdp_check() returns false when xmit_hash_policy is vlan+srcmac, because the 802.1q payload is usually absent due to hardware offload. This means a user can:

1. Attach a native XDP program to a bond in 802.3ad/balance-xor mode with a compatible xmit_hash_policy (e.g. layer2+3).
2. Change xmit_hash_policy to vlan+srcmac while XDP remains loaded.

This leaves bond->xdp_prog set but bond_xdp_check() now returning false for the same device. When the bond is later destroyed, dev_xdp_uninstall() calls bond_xdp_set(dev, NULL, NULL) to remove the program, which hits the bond_xdp_check() guard and returns -EOPNOTSUPP, triggering:

WARN_ON(dev_xdp_install(dev, mode, bpf_op, NULL, 0, NULL))

Fix this by rejecting xmit_hash_policy changes to vlan+srcmac when an XDP program is loaded on a bond in 802.3ad or balance-xor mode.

commit 39a0876d595b ("net, bonding: Disallow vlan+srcmac with XDP") introduced bond_xdp_check() which returns false for 802.3ad/balance-xor modes when xmit_hash_policy is vlan+srcmac. The check was wired into bond_xdp_set() to reject XDP attachment with an incompatible policy, but the symmetric path -- preventing xmit_hash_policy from being changed to an incompatible value after XDP is already loaded -- was left unguarded in bond_option_xmit_hash_policy_set().

Note:
commit 094ee6017ea0 ("bonding: check xdp prog when set bond mode") later added a similar guard to bond_option_mode_set(), but bond_option_xmit_hash_policy_set() remained unprotected.

---
 drivers/net/bonding/bond_main.c    | 9 +++++++--
 drivers/net/bonding/bond_options.c | 2 ++
 include/net/bonding.h              | 1 +
 3 files changed, 10 insertions(+), 2 deletions(-)
drivers/net/bonding/bond_main.c +7 -2
index dba8f68690947..55f98d6254af8 100644
@@ -324,7 +324,7 @@ static bool bond_sk_check(struct bonding *bond)
 	}
 }
 
-bool bond_xdp_check(struct bonding *bond, int mode)
+bool __bond_xdp_check(int mode, int xmit_policy)
 {
 	switch (mode) {
 	case BOND_MODE_ROUNDROBIN:
@@ -335,7 +335,7 @@ bool bond_xdp_check(struct bonding *bond, int mode)
 		/* vlan+srcmac is not supported with XDP as in most cases the 802.1q
 		 * payload is not in the packet due to hardware offload.
 		 */
-		if (bond->params.xmit_policy != BOND_XMIT_POLICY_VLAN_SRCMAC)
+		if (xmit_policy != BOND_XMIT_POLICY_VLAN_SRCMAC)
 			return true;
 		fallthrough;
 	default:
@@ -343,6 +343,11 @@ bool bond_xdp_check(struct bonding *bond, int mode)
 	}
 }
 
+bool bond_xdp_check(struct bonding *bond, int mode)
+{
+	return __bond_xdp_check(mode, bond->params.xmit_policy);
+}
+
 /*---------------------------------- VLAN -----------------------------------*/
 
 /* In the following 2 functions, bond_vlan_rx_add_vid and bond_vlan_rx_kill_vid,
drivers/net/bonding/bond_options.c +2 -0
index f1c6e9d8f6167..adc216df43459 100644
@@ -1574,6 +1574,8 @@ static int bond_option_fail_over_mac_set(struct bonding *bond,
 static int bond_option_xmit_hash_policy_set(struct bonding *bond,
 					    const struct bond_opt_value *newval)
 {
+	if (bond->xdp_prog && !__bond_xdp_check(BOND_MODE(bond), newval->value))
+		return -EOPNOTSUPP;
 	netdev_dbg(bond->dev, "Setting xmit hash policy to %s (%llu)\n",
 		   newval->string, newval->value);
 	bond->params.xmit_policy = newval->value;
include/net/bonding.h +1 -0
index 4620784035570..99c1bdadcd11a 100644
@@ -698,6 +698,7 @@ void bond_debug_register(struct bonding *bond);
 void bond_debug_unregister(struct bonding *bond);
 void bond_debug_reregister(struct bonding *bond);
 const char *bond_mode_name(int mode);
+bool __bond_xdp_check(int mode, int xmit_policy);
 bool bond_xdp_check(struct bonding *bond, int mode);
 void bond_setup(struct net_device *bond_dev);
 unsigned int bond_get_num_tx_queues(void);
Signature · 1 line
2.51.0
author maintainer
#255 lore raw

PATCH 249/314 octeon_ep: Relocate counter updates before NAPI

In reply to Sasha Levin

From: Vimlesh Kumar <[email protected]>

[ Upstream commit 18c04a808c436d629d5812ce883e3822a5f5a47f ]

Relocate IQ/OQ IN/OUT_CNTS updates to occur before NAPI completion, and replace napi_complete with napi_complete_done.

Moving the IQ/OQ counter updates before napi_complete_done ensures
1. Counter registers are updated before re-enabling interrupts.
2. Prevents a race where new packets arrive but counters aren't properly synchronized.
napi_complete_done (vs napi_complete) allows for better interrupt coalescing.

Fixes 37d79d0596062 ("octeon_ep: add Tx/Rx processing and interrupt support")
---
 .../ethernet/marvell/octeon_ep/octep_main.c   | 19 +++++++++++++++----
 1 file changed, 15 insertions(+), 4 deletions(-)
drivers/net/ethernet/marvell/octeon_ep/octep_main.c +15 -4
index 57db7ea2f5be9..7f8ed8f0ade49 100644
@@ -555,12 +555,12 @@ static void octep_clean_irqs(struct octep_device *oct)
 }
 
 /**
- * octep_enable_ioq_irq() - Enable MSI-x interrupt of a Tx/Rx queue.
+ * octep_update_pkt() - Update IQ/OQ IN/OUT_CNT registers.
  *
  * @iq: Octeon Tx queue data structure.
  * @oq: Octeon Rx queue data structure.
  */
-static void octep_enable_ioq_irq(struct octep_iq *iq, struct octep_oq *oq)
+static void octep_update_pkt(struct octep_iq *iq, struct octep_oq *oq)
 {
 	u32 pkts_pend = oq->pkts_pending;
 
@@ -576,7 +576,17 @@ static void octep_enable_ioq_irq(struct octep_iq *iq, struct octep_oq *oq)
 	}
 
 	/* Flush the previous wrties before writing to RESEND bit */
-	wmb();
+	smp_wmb();
+}
+
+/**
+ * octep_enable_ioq_irq() - Enable MSI-x interrupt of a Tx/Rx queue.
+ *
+ * @iq: Octeon Tx queue data structure.
+ * @oq: Octeon Rx queue data structure.
+ */
+static void octep_enable_ioq_irq(struct octep_iq *iq, struct octep_oq *oq)
+{
 	writeq(1UL << OCTEP_OQ_INTR_RESEND_BIT, oq->pkts_sent_reg);
 	writeq(1UL << OCTEP_IQ_INTR_RESEND_BIT, iq->inst_cnt_reg);
 }
@@ -602,7 +612,8 @@ static int octep_napi_poll(struct napi_struct *napi, int budget)
 	if (tx_pending || rx_done >= budget)
 		return budget;
 
-	napi_complete(napi);
+	octep_update_pkt(ioq_vector->iq, ioq_vector->oq);
+	napi_complete_done(napi, rx_done);
 	octep_enable_ioq_irq(ioq_vector->iq, ioq_vector->oq);
 	return rx_done;
 }
Signature · 1 line
2.51.0
author maintainer
#256 lore raw

PATCH 250/314 octeon_ep: avoid compiler and IQ/OQ reordering

In reply to Sasha Levin

From: Vimlesh Kumar <[email protected]>

[ Upstream commit 43b3160cb639079a15daeb5f080120afbfbfc918 ]

Utilize READ_ONCE and WRITE_ONCE APIs for IO queue Tx/Rx variable access to prevent compiler optimization and reordering. Additionally, ensure IO queue OUT/IN_CNT registers are flushed by performing a read-back after writing.

The compiler could reorder reads/writes to pkts_pending, last_pkt_count, etc., causing stale values to be used when calculating packets to process or register updates to send to hardware. The Octeon hardware requires a read-back after writing to OUT_CNT/IN_CNT registers to ensure the write has been flushed through any posted write buffers before the interrupt resend bit is set. Without this, we have observed cases where the hardware didn't properly update its internal state.

wmb/rmb only provides ordering guarantees but doesn't prevent the compiler from performing optimizations like caching in registers, load tearing etc.

Fixes 37d79d0596062 ("octeon_ep: add Tx/Rx processing and interrupt support")
---
 .../ethernet/marvell/octeon_ep/octep_main.c   | 21 +++++++++------
 .../net/ethernet/marvell/octeon_ep/octep_rx.c | 27 +++++++++++++------
 2 files changed, 32 insertions(+), 16 deletions(-)
drivers/net/ethernet/marvell/octeon_ep/octep_main.c +13 -8
index 7f8ed8f0ade49..16f52d4b11e91 100644
@@ -562,17 +562,22 @@ static void octep_clean_irqs(struct octep_device *oct)
  */
 static void octep_update_pkt(struct octep_iq *iq, struct octep_oq *oq)
 {
-	u32 pkts_pend = oq->pkts_pending;
+	u32 pkts_pend = READ_ONCE(oq->pkts_pending);
+	u32 last_pkt_count = READ_ONCE(oq->last_pkt_count);
+	u32 pkts_processed = READ_ONCE(iq->pkts_processed);
+	u32 pkt_in_done = READ_ONCE(iq->pkt_in_done);
 
 	netdev_dbg(iq->netdev, "enabling intr for Q-%u\n", iq->q_no);
-	if (iq->pkts_processed) {
-		writel(iq->pkts_processed, iq->inst_cnt_reg);
-		iq->pkt_in_done -= iq->pkts_processed;
-		iq->pkts_processed = 0;
+	if (pkts_processed) {
+		writel(pkts_processed, iq->inst_cnt_reg);
+		readl(iq->inst_cnt_reg);
+		WRITE_ONCE(iq->pkt_in_done, (pkt_in_done - pkts_processed));
+		WRITE_ONCE(iq->pkts_processed, 0);
 	}
-	if (oq->last_pkt_count - pkts_pend) {
-		writel(oq->last_pkt_count - pkts_pend, oq->pkts_sent_reg);
-		oq->last_pkt_count = pkts_pend;
+	if (last_pkt_count - pkts_pend) {
+		writel(last_pkt_count - pkts_pend, oq->pkts_sent_reg);
+		readl(oq->pkts_sent_reg);
+		WRITE_ONCE(oq->last_pkt_count, pkts_pend);
 	}
 
 	/* Flush the previous wrties before writing to RESEND bit */
drivers/net/ethernet/marvell/octeon_ep/octep_rx.c +19 -8
index f2a7c6a76c742..74de19166488f 100644
@@ -324,10 +324,16 @@ static int octep_oq_check_hw_for_pkts(struct octep_device *oct,
 				      struct octep_oq *oq)
 {
 	u32 pkt_count, new_pkts;
+	u32 last_pkt_count, pkts_pending;
 
 	pkt_count = readl(oq->pkts_sent_reg);
-	new_pkts = pkt_count - oq->last_pkt_count;
+	last_pkt_count = READ_ONCE(oq->last_pkt_count);
+	new_pkts = pkt_count - last_pkt_count;
 
+	if (pkt_count < last_pkt_count) {
+		dev_err(oq->dev, "OQ-%u pkt_count(%u) < oq->last_pkt_count(%u)\n",
+			oq->q_no, pkt_count, last_pkt_count);
+	}
 	/* Clear the hardware packets counter register if the rx queue is
 	 * being processed continuously with-in a single interrupt and
 	 * reached half its max value.
@@ -338,8 +344,9 @@ static int octep_oq_check_hw_for_pkts(struct octep_device *oct,
 		pkt_count = readl(oq->pkts_sent_reg);
 		new_pkts += pkt_count;
 	}
-	oq->last_pkt_count = pkt_count;
-	oq->pkts_pending += new_pkts;
+	WRITE_ONCE(oq->last_pkt_count, pkt_count);
+	pkts_pending = READ_ONCE(oq->pkts_pending);
+	WRITE_ONCE(oq->pkts_pending, (pkts_pending + new_pkts));
 	return new_pkts;
 }
 
@@ -414,7 +421,7 @@ static int __octep_oq_process_rx(struct octep_device *oct,
 	u16 rx_ol_flags;
 	u32 read_idx;
 
-	read_idx = oq->host_read_idx;
+	read_idx = READ_ONCE(oq->host_read_idx);
 	rx_bytes = 0;
 	desc_used = 0;
 	for (pkt = 0; pkt < pkts_to_process; pkt++) {
@@ -499,7 +506,7 @@ static int __octep_oq_process_rx(struct octep_device *oct,
 		napi_gro_receive(oq->napi, skb);
 	}
 
-	oq->host_read_idx = read_idx;
+	WRITE_ONCE(oq->host_read_idx, read_idx);
 	oq->refill_count += desc_used;
 	oq->stats->packets += pkt;
 	oq->stats->bytes += rx_bytes;
@@ -522,22 +529,26 @@ int octep_oq_process_rx(struct octep_oq *oq, int budget)
 {
 	u32 pkts_available, pkts_processed, total_pkts_processed;
 	struct octep_device *oct = oq->octep_dev;
+	u32 pkts_pending;
 
 	pkts_available = 0;
 	pkts_processed = 0;
 	total_pkts_processed = 0;
 	while (total_pkts_processed < budget) {
 		 /* update pending count only when current one exhausted */
-		if (oq->pkts_pending == 0)
+		pkts_pending = READ_ONCE(oq->pkts_pending);
+		if (pkts_pending == 0)
 			octep_oq_check_hw_for_pkts(oct, oq);
+		pkts_pending = READ_ONCE(oq->pkts_pending);
 		pkts_available = min(budget - total_pkts_processed,
-				     oq->pkts_pending);
+				     pkts_pending);
 		if (!pkts_available)
 			break;
 
 		pkts_processed = __octep_oq_process_rx(oct, oq,
 						       pkts_available);
-		oq->pkts_pending -= pkts_processed;
+		pkts_pending = READ_ONCE(oq->pkts_pending);
+		WRITE_ONCE(oq->pkts_pending, (pkts_pending - pkts_processed));
 		total_pkts_processed += pkts_processed;
 	}
 
Signature · 1 line
2.51.0
author maintainer
#257 lore raw

PATCH 251/314 octeon_ep_vf: Relocate counter updates before NAPI

In reply to Sasha Levin

From: Vimlesh Kumar <[email protected]>

[ Upstream commit 2ae7d20fb24f598f60faa8f6ecc856dac782261a ]

Relocate IQ/OQ IN/OUT_CNTS updates to occur before NAPI completion. Moving the IQ/OQ counter updates before napi_complete_done ensures
1. Counter registers are updated before re-enabling interrupts.
2. Prevents a race where new packets arrive but counters aren't properly synchronized.

Fixes 1cd3b407977c3 ("octeon_ep_vf: add Tx/Rx processing and interrupt support")
---
 .../marvell/octeon_ep_vf/octep_vf_main.c        | 17 +++++++++++++++--
 1 file changed, 15 insertions(+), 2 deletions(-)
drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_main.c +15 -2
index 1d9760b4b8f47..17efc8eab4cfb 100644
@@ -286,12 +286,13 @@ static void octep_vf_clean_irqs(struct octep_vf_device *oct)
 }
 
 /**
- * octep_vf_enable_ioq_irq() - Enable MSI-x interrupt of a Tx/Rx queue.
+ * octep_vf_update_pkt() - Update IQ/OQ IN/OUT_CNT registers.
  *
  * @iq: Octeon Tx queue data structure.
  * @oq: Octeon Rx queue data structure.
  */
-static void octep_vf_enable_ioq_irq(struct octep_vf_iq *iq, struct octep_vf_oq *oq)
+
+static void octep_vf_update_pkt(struct octep_vf_iq *iq, struct octep_vf_oq *oq)
 {
 	u32 pkts_pend = oq->pkts_pending;
 
@@ -308,6 +309,17 @@ static void octep_vf_enable_ioq_irq(struct octep_vf_iq *iq, struct octep_vf_oq *
 
 	/* Flush the previous wrties before writing to RESEND bit */
 	smp_wmb();
+}
+
+/**
+ * octep_vf_enable_ioq_irq() - Enable MSI-x interrupt of a Tx/Rx queue.
+ *
+ * @iq: Octeon Tx queue data structure.
+ * @oq: Octeon Rx queue data structure.
+ */
+static void octep_vf_enable_ioq_irq(struct octep_vf_iq *iq,
+				    struct octep_vf_oq *oq)
+{
 	writeq(1UL << OCTEP_VF_OQ_INTR_RESEND_BIT, oq->pkts_sent_reg);
 	writeq(1UL << OCTEP_VF_IQ_INTR_RESEND_BIT, iq->inst_cnt_reg);
 }
@@ -333,6 +345,7 @@ static int octep_vf_napi_poll(struct napi_struct *napi, int budget)
 	if (tx_pending || rx_done >= budget)
 		return budget;
 
+	octep_vf_update_pkt(ioq_vector->iq, ioq_vector->oq);
 	if (likely(napi_complete_done(napi, rx_done)))
 		octep_vf_enable_ioq_irq(ioq_vector->iq, ioq_vector->oq);
 
Signature · 1 line
2.51.0
author maintainer
#258 lore raw

PATCH 252/314 octeon_ep_vf: avoid compiler and IQ/OQ reordering

In reply to Sasha Levin

From: Vimlesh Kumar <[email protected]>

[ Upstream commit 6c73126ecd1080351b468fe43353b2f705487f44 ]

Utilize READ_ONCE and WRITE_ONCE APIs for IO queue Tx/Rx variable access to prevent compiler optimization and reordering. Additionally, ensure IO queue OUT/IN_CNT registers are flushed by performing a read-back after writing.

The compiler could reorder reads/writes to pkts_pending, last_pkt_count, etc., causing stale values to be used when calculating packets to process or register updates to send to hardware. The Octeon hardware requires a read-back after writing to OUT_CNT/IN_CNT registers to ensure the write has been flushed through any posted write buffers before the interrupt resend bit is set. Without this, we have observed cases where the hardware didn't properly update its internal state.

wmb/rmb only provides ordering guarantees but doesn't prevent the compiler from performing optimizations like caching in registers, load tearing etc.

Fixes 1cd3b407977c3 ("octeon_ep_vf: add Tx/Rx processing and interrupt support")
---
 .../marvell/octeon_ep_vf/octep_vf_main.c      | 21 ++++++++------
 .../marvell/octeon_ep_vf/octep_vf_rx.c        | 28 +++++++++++++------
 2 files changed, 33 insertions(+), 16 deletions(-)
drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_main.c +13 -8
index 17efc8eab4cfb..a3c359124887e 100644
@@ -294,17 +294,22 @@ static void octep_vf_clean_irqs(struct octep_vf_device *oct)
 
 static void octep_vf_update_pkt(struct octep_vf_iq *iq, struct octep_vf_oq *oq)
 {
-	u32 pkts_pend = oq->pkts_pending;
+	u32 pkts_pend = READ_ONCE(oq->pkts_pending);
+	u32 last_pkt_count = READ_ONCE(oq->last_pkt_count);
+	u32 pkts_processed = READ_ONCE(iq->pkts_processed);
+	u32 pkt_in_done = READ_ONCE(iq->pkt_in_done);
 
 	netdev_dbg(iq->netdev, "enabling intr for Q-%u\n", iq->q_no);
-	if (iq->pkts_processed) {
-		writel(iq->pkts_processed, iq->inst_cnt_reg);
-		iq->pkt_in_done -= iq->pkts_processed;
-		iq->pkts_processed = 0;
+	if (pkts_processed) {
+		writel(pkts_processed, iq->inst_cnt_reg);
+		readl(iq->inst_cnt_reg);
+		WRITE_ONCE(iq->pkt_in_done, (pkt_in_done - pkts_processed));
+		WRITE_ONCE(iq->pkts_processed, 0);
 	}
-	if (oq->last_pkt_count - pkts_pend) {
-		writel(oq->last_pkt_count - pkts_pend, oq->pkts_sent_reg);
-		oq->last_pkt_count = pkts_pend;
+	if (last_pkt_count - pkts_pend) {
+		writel(last_pkt_count - pkts_pend, oq->pkts_sent_reg);
+		readl(oq->pkts_sent_reg);
+		WRITE_ONCE(oq->last_pkt_count, pkts_pend);
 	}
 
 	/* Flush the previous wrties before writing to RESEND bit */
drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_rx.c +20 -8
index 6f865dbbba6c6..b579d5b545c46 100644
@@ -325,9 +325,16 @@ static int octep_vf_oq_check_hw_for_pkts(struct octep_vf_device *oct,
 					 struct octep_vf_oq *oq)
 {
 	u32 pkt_count, new_pkts;
+	u32 last_pkt_count, pkts_pending;
 
 	pkt_count = readl(oq->pkts_sent_reg);
-	new_pkts = pkt_count - oq->last_pkt_count;
+	last_pkt_count = READ_ONCE(oq->last_pkt_count);
+	new_pkts = pkt_count - last_pkt_count;
+
+	if (pkt_count < last_pkt_count) {
+		dev_err(oq->dev, "OQ-%u pkt_count(%u) < oq->last_pkt_count(%u)\n",
+			oq->q_no, pkt_count, last_pkt_count);
+	}
 
 	/* Clear the hardware packets counter register if the rx queue is
 	 * being processed continuously with-in a single interrupt and
@@ -339,8 +346,9 @@ static int octep_vf_oq_check_hw_for_pkts(struct octep_vf_device *oct,
 		pkt_count = readl(oq->pkts_sent_reg);
 		new_pkts += pkt_count;
 	}
-	oq->last_pkt_count = pkt_count;
-	oq->pkts_pending += new_pkts;
+	WRITE_ONCE(oq->last_pkt_count, pkt_count);
+	pkts_pending = READ_ONCE(oq->pkts_pending);
+	WRITE_ONCE(oq->pkts_pending, (pkts_pending + new_pkts));
 	return new_pkts;
 }
 
@@ -369,7 +377,7 @@ static int __octep_vf_oq_process_rx(struct octep_vf_device *oct,
 	struct sk_buff *skb;
 	u32 read_idx;
 
-	read_idx = oq->host_read_idx;
+	read_idx = READ_ONCE(oq->host_read_idx);
 	rx_bytes = 0;
 	desc_used = 0;
 	for (pkt = 0; pkt < pkts_to_process; pkt++) {
@@ -463,7 +471,7 @@ static int __octep_vf_oq_process_rx(struct octep_vf_device *oct,
 		napi_gro_receive(oq->napi, skb);
 	}
 
-	oq->host_read_idx = read_idx;
+	WRITE_ONCE(oq->host_read_idx, read_idx);
 	oq->refill_count += desc_used;
 	oq->stats->packets += pkt;
 	oq->stats->bytes += rx_bytes;
@@ -486,22 +494,26 @@ int octep_vf_oq_process_rx(struct octep_vf_oq *oq, int budget)
 {
 	u32 pkts_available, pkts_processed, total_pkts_processed;
 	struct octep_vf_device *oct = oq->octep_vf_dev;
+	u32 pkts_pending;
 
 	pkts_available = 0;
 	pkts_processed = 0;
 	total_pkts_processed = 0;
 	while (total_pkts_processed < budget) {
 		 /* update pending count only when current one exhausted */
-		if (oq->pkts_pending == 0)
+		pkts_pending = READ_ONCE(oq->pkts_pending);
+		if (pkts_pending == 0)
 			octep_vf_oq_check_hw_for_pkts(oct, oq);
+		pkts_pending = READ_ONCE(oq->pkts_pending);
 		pkts_available = min(budget - total_pkts_processed,
-				     oq->pkts_pending);
+				     pkts_pending);
 		if (!pkts_available)
 			break;
 
 		pkts_processed = __octep_vf_oq_process_rx(oct, oq,
 							  pkts_available);
-		oq->pkts_pending -= pkts_processed;
+		pkts_pending = READ_ONCE(oq->pkts_pending);
+		WRITE_ONCE(oq->pkts_pending, (pkts_pending - pkts_processed));
 		total_pkts_processed += pkts_processed;
 	}
 
Signature · 1 line
2.51.0
author maintainer
#259 lore raw

PATCH 253/314 wifi: cw1200: Fix locking in error paths

In reply to Sasha Levin

From: Bart Van Assche <[email protected]>

[ Upstream commit d98c24617a831e92e7224a07dcaed2dd0b02af96 ]

cw1200_wow_suspend() must only return with priv->conf_mutex locked if it returns zero. This mutex must be unlocked if an error is returned. Add mutex_unlock() calls to the error paths from which that call is missing. This has been detected by the Clang thread-safety analyzer.

Fixes a910e4a94f69 ("cw1200: add driver for the ST-E CW1100 & CW1200 WLAN chipsets")
---
 drivers/net/wireless/st/cw1200/pm.c | 2 ++
 1 file changed, 2 insertions(+)
drivers/net/wireless/st/cw1200/pm.c +2 -0
index 2002e3f9fe45b..b656afe65db07 100644
@@ -264,12 +264,14 @@ int cw1200_wow_suspend(struct ieee80211_hw *hw, struct cfg80211_wowlan *wowlan)
 		wiphy_err(priv->hw->wiphy,
 			  "PM request failed: %d. WoW is disabled.\n", ret);
 		cw1200_wow_resume(hw);
+		mutex_unlock(&priv->conf_mutex);
 		return -EBUSY;
 	}
 
 	/* Force resume if event is coming from the device. */
 	if (atomic_read(&priv->bh_rx)) {
 		cw1200_wow_resume(hw);
+		mutex_unlock(&priv->conf_mutex);
 		return -EAGAIN;
 	}
 
Signature · 1 line
2.51.0
author maintainer
#260 lore raw

PATCH 254/314 wifi: wlcore: Fix a locking bug

In reply to Sasha Levin

From: Bart Van Assche <[email protected]>

[ Upstream commit 72c6df8f284b3a49812ce2ac136727ace70acc7c ]

Make sure that wl->mutex is locked before it is unlocked. This has been detected by the Clang thread-safety analyzer.

Fixes 45aa7f071b06 ("wlcore: Use generic runtime pm calls for wowlan elp configuration")
---
 drivers/net/wireless/ti/wlcore/main.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)
drivers/net/wireless/ti/wlcore/main.c +2 -2
index 6116a8522d960..bdb06584d7e45 100644
@@ -1880,6 +1880,8 @@ static int __maybe_unused wl1271_op_resume(struct ieee80211_hw *hw)
 		     wl->wow_enabled);
 	WARN_ON(!wl->wow_enabled);
 
+	mutex_lock(&wl->mutex);
+
 	ret = pm_runtime_force_resume(wl->dev);
 	if (ret < 0) {
 		wl1271_error("ELP wakeup failure!");
@@ -1896,8 +1898,6 @@ static int __maybe_unused wl1271_op_resume(struct ieee80211_hw *hw)
 		run_irq_work = true;
 	spin_unlock_irqrestore(&wl->wl_lock, flags);
 
-	mutex_lock(&wl->mutex);
-
 	/* test the recovery flag before calling any SDIO functions */
 	pending_recovery = test_bit(WL1271_FLAG_RECOVERY_IN_PROGRESS,
 				    &wl->flags);
Signature · 1 line
2.51.0
author maintainer
#261 lore raw

PATCH 255/314 wifi: mt76: mt7996: Fix possible oob access in mt7996_mac_write_txwi_80211()

In reply to Sasha Levin

From: Lorenzo Bianconi <[email protected]>

[ Upstream commit 60862846308627e9e15546bb647a00de44deb27b ]

Check frame length before accessing the mgmt fields in mt7996_mac_write_txwi_80211 in order to avoid a possible oob access.

Fixes 98686cd21624c ("wifi: mt76: mt7996: add driver for MediaTek Wi-Fi 7 (802.11be) devices")
---
 drivers/net/wireless/mediatek/mt76/mt7996/mac.c | 1 +
 1 file changed, 1 insertion(+)
drivers/net/wireless/mediatek/mt76/mt7996/mac.c +1 -0
index 502136691a69e..0958961d2758e 100644
@@ -799,6 +799,7 @@ mt7996_mac_write_txwi_80211(struct mt7996_dev *dev, __le32 *txwi,
 	u32 val;
 
 	if (ieee80211_is_action(fc) &&
+	    skb->len >= IEEE80211_MIN_ACTION_SIZE + 1 &&
 	    mgmt->u.action.category == WLAN_CATEGORY_BACK &&
 	    mgmt->u.action.u.addba_req.action_code == WLAN_ACTION_ADDBA_REQ) {
 		if (is_mt7990(&dev->mt76))
Signature · 1 line
2.51.0
author maintainer
#262 lore raw

PATCH 256/314 wifi: mt76: mt7925: Fix possible oob access in mt7925_mac_write_txwi_80211()

In reply to Sasha Levin

From: Lorenzo Bianconi <[email protected]>

[ Upstream commit c41a9abd6ae31d130e8f332e7c8800c4c866234b ]

Check frame length before accessing the mgmt fields in mt7925_mac_write_txwi_80211 in order to avoid a possible oob access.

Fixes c948b5da6bbec ("wifi: mt76: mt7925: add Mediatek Wi-Fi7 driver for mt7925 chips")
---
 drivers/net/wireless/mediatek/mt76/mt7925/mac.c | 1 +
 1 file changed, 1 insertion(+)
drivers/net/wireless/mediatek/mt76/mt7925/mac.c +1 -0
index 1e44e96f034e9..e880f3820a1ad 100644
@@ -667,6 +667,7 @@ mt7925_mac_write_txwi_80211(struct mt76_dev *dev, __le32 *txwi,
 	u32 val;
 
 	if (ieee80211_is_action(fc) &&
+	    skb->len >= IEEE80211_MIN_ACTION_SIZE + 1 &&
 	    mgmt->u.action.category == WLAN_CATEGORY_BACK &&
 	    mgmt->u.action.u.addba_req.action_code == WLAN_ACTION_ADDBA_REQ)
 		tid = MT_TX_ADDBA;
Signature · 1 line
2.51.0