6.6.51-rc1 review

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

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

From: Guenter Roeck <[email protected]>

[ Upstream commit 5c1de37969b7bc0abcb20b86e91e70caebbd4f89 ]

DIV_ROUND_CLOSEST() after kstrtol() results in an underflow if a large negative number such as -9223372036854775808 is provided by the user. Fix it by reordering clamp_val() and DIV_ROUND_CLOSEST() operations.

---
 drivers/hwmon/w83627ehf.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

index fe960c0a624f..7d7d70afde65 100644
@@ -895,7 +895,7 @@ store_target_temp(struct device *dev, struct device_attribute *attr,
 	if (err < 0)
 		return err;
 
-	val = clamp_val(DIV_ROUND_CLOSEST(val, 1000), 0, 127);
+	val = DIV_ROUND_CLOSEST(clamp_val(val, 0, 127000), 1000);
 
 	mutex_lock(&data->update_lock);
 	data->target_temp[nr] = val;

@@ -920,7 +920,7 @@ store_tolerance(struct device *dev, struct device_attribute *attr,
 		return err;
 
 	/* Limit the temp to 0C - 15C */
-	val = clamp_val(DIV_ROUND_CLOSEST(val, 1000), 0, 15);
+	val = DIV_ROUND_CLOSEST(clamp_val(val, 0, 15000), 1000);
 
 	mutex_lock(&data->update_lock);
 	reg = w83627ehf_read_value(data, W83627EHF_REG_TOLERANCE[nr]);

2.43.0

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

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

From: Shenghao Ding <[email protected]>

[ Upstream commit 1cc509edbe23b61e8c245611bd15d88edb635a38 ]

Use get_unaligned_be16 instead of be16_to_cpup and get_unaligned_be32 instead of be32_to_cpup for potentially broken alignment.

---
 sound/soc/codecs/tas2781-fmwlib.c | 71 +++++++++++++++----------------
 1 file changed, 35 insertions(+), 36 deletions(-)

index 41ad82a42916..3639dcd0bbb2 100644
@@ -21,7 +21,7 @@
 #include <sound/soc.h>
 #include <sound/tlv.h>
 #include <sound/tas2781.h>
-
+#include <asm/unaligned.h>
 
 #define ERROR_PRAM_CRCCHK			0x0000000
 #define ERROR_YRAM_CRCCHK			0x0000001

@@ -125,8 +125,7 @@ static struct tasdevice_config_info *tasdevice_add_config(
 	/* convert data[offset], data[offset + 1], data[offset + 2] and
 	 * data[offset + 3] into host
 	 */
-	cfg_info->nblocks =
-		be32_to_cpup((__be32 *)&config_data[config_offset]);
+	cfg_info->nblocks = get_unaligned_be32(&config_data[config_offset]);
 	config_offset += 4;
 
 	/* Several kinds of dsp/algorithm firmwares can run on tas2781,

@@ -170,14 +169,14 @@ static struct tasdevice_config_info *tasdevice_add_config(
 
 		}
 		bk_da[i]->yram_checksum =
-			be16_to_cpup((__be16 *)&config_data[config_offset]);
+			get_unaligned_be16(&config_data[config_offset]);
 		config_offset += 2;
 		bk_da[i]->block_size =
-			be32_to_cpup((__be32 *)&config_data[config_offset]);
+			get_unaligned_be32(&config_data[config_offset]);
 		config_offset += 4;
 
 		bk_da[i]->n_subblks =
-			be32_to_cpup((__be32 *)&config_data[config_offset]);
+			get_unaligned_be32(&config_data[config_offset]);
 
 		config_offset += 4;
 

@@ -227,7 +226,7 @@ int tasdevice_rca_parser(void *context, const struct firmware *fmw)
 	}
 	buf = (unsigned char *)fmw->data;
 
-	fw_hdr->img_sz = be32_to_cpup((__be32 *)&buf[offset]);
+	fw_hdr->img_sz = get_unaligned_be32(&buf[offset]);
 	offset += 4;
 	if (fw_hdr->img_sz != fmw->size) {
 		dev_err(tas_priv->dev,

@@ -238,9 +237,9 @@ int tasdevice_rca_parser(void *context, const struct firmware *fmw)
 		goto out;
 	}
 
-	fw_hdr->checksum = be32_to_cpup((__be32 *)&buf[offset]);
+	fw_hdr->checksum = get_unaligned_be32(&buf[offset]);
 	offset += 4;
-	fw_hdr->binary_version_num = be32_to_cpup((__be32 *)&buf[offset]);
+	fw_hdr->binary_version_num = get_unaligned_be32(&buf[offset]);
 	if (fw_hdr->binary_version_num < 0x103) {
 		dev_err(tas_priv->dev, "File version 0x%04x is too low",
 			fw_hdr->binary_version_num);

@@ -249,7 +248,7 @@ int tasdevice_rca_parser(void *context, const struct firmware *fmw)
 		goto out;
 	}
 	offset += 4;
-	fw_hdr->drv_fw_version = be32_to_cpup((__be32 *)&buf[offset]);
+	fw_hdr->drv_fw_version = get_unaligned_be32(&buf[offset]);
 	offset += 8;
 	fw_hdr->plat_type = buf[offset];
 	offset += 1;

@@ -277,11 +276,11 @@ int tasdevice_rca_parser(void *context, const struct firmware *fmw)
 	for (i = 0; i < TASDEVICE_DEVICE_SUM; i++, offset++)
 		fw_hdr->devs[i] = buf[offset];
 
-	fw_hdr->nconfig = be32_to_cpup((__be32 *)&buf[offset]);
+	fw_hdr->nconfig = get_unaligned_be32(&buf[offset]);
 	offset += 4;
 
 	for (i = 0; i < TASDEVICE_CONFIG_SUM; i++) {
-		fw_hdr->config_size[i] = be32_to_cpup((__be32 *)&buf[offset]);
+		fw_hdr->config_size[i] = get_unaligned_be32(&buf[offset]);
 		offset += 4;
 		total_config_sz += fw_hdr->config_size[i];
 	}

@@ -330,7 +329,7 @@ static int fw_parse_block_data_kernel(struct tasdevice_fw *tas_fmw,
 	/* convert data[offset], data[offset + 1], data[offset + 2] and
 	 * data[offset + 3] into host
 	 */
-	block->type = be32_to_cpup((__be32 *)&data[offset]);
+	block->type = get_unaligned_be32(&data[offset]);
 	offset += 4;
 
 	block->is_pchksum_present = data[offset];

@@ -345,10 +344,10 @@ static int fw_parse_block_data_kernel(struct tasdevice_fw *tas_fmw,
 	block->ychksum = data[offset];
 	offset++;
 
-	block->blk_size = be32_to_cpup((__be32 *)&data[offset]);
+	block->blk_size = get_unaligned_be32(&data[offset]);
 	offset += 4;
 
-	block->nr_subblocks = be32_to_cpup((__be32 *)&data[offset]);
+	block->nr_subblocks = get_unaligned_be32(&data[offset]);
 	offset += 4;
 
 	if (offset + block->blk_size > fmw->size) {

@@ -381,7 +380,7 @@ static int fw_parse_data_kernel(struct tasdevice_fw *tas_fmw,
 		offset = -EINVAL;
 		goto out;
 	}
-	img_data->nr_blk = be32_to_cpup((__be32 *)&data[offset]);
+	img_data->nr_blk = get_unaligned_be32(&data[offset]);
 	offset += 4;
 
 	img_data->dev_blks = kcalloc(img_data->nr_blk,

@@ -477,14 +476,14 @@ static int fw_parse_variable_header_kernel(
 		offset = -EINVAL;
 		goto out;
 	}
-	fw_hdr->device_family = be16_to_cpup((__be16 *)&buf[offset]);
+	fw_hdr->device_family = get_unaligned_be16(&buf[offset]);
 	if (fw_hdr->device_family != 0) {
 		dev_err(tas_priv->dev, "%s:not TAS device\n", __func__);
 		offset = -EINVAL;
 		goto out;
 	}
 	offset += 2;
-	fw_hdr->device = be16_to_cpup((__be16 *)&buf[offset]);
+	fw_hdr->device = get_unaligned_be16(&buf[offset]);
 	if (fw_hdr->device >= TASDEVICE_DSP_TAS_MAX_DEVICE ||
 		fw_hdr->device == 6) {
 		dev_err(tas_priv->dev, "Unsupported dev %d\n", fw_hdr->device);

@@ -502,7 +501,7 @@ static int fw_parse_variable_header_kernel(
 		goto out;
 	}
 
-	tas_fmw->nr_programs = be32_to_cpup((__be32 *)&buf[offset]);
+	tas_fmw->nr_programs = get_unaligned_be32(&buf[offset]);
 	offset += 4;
 
 	if (tas_fmw->nr_programs == 0 || tas_fmw->nr_programs >

@@ -521,14 +520,14 @@ static int fw_parse_variable_header_kernel(
 
 	for (i = 0; i < tas_fmw->nr_programs; i++) {
 		program = &(tas_fmw->programs[i]);
-		program->prog_size = be32_to_cpup((__be32 *)&buf[offset]);
+		program->prog_size = get_unaligned_be32(&buf[offset]);
 		offset += 4;
 	}
 
 	/* Skip the unused prog_size */
 	offset += 4 * (TASDEVICE_MAXPROGRAM_NUM_KERNEL - tas_fmw->nr_programs);
 
-	tas_fmw->nr_configurations = be32_to_cpup((__be32 *)&buf[offset]);
+	tas_fmw->nr_configurations = get_unaligned_be32(&buf[offset]);
 	offset += 4;
 
 	/* The max number of config in firmware greater than 4 pieces of

@@ -560,7 +559,7 @@ static int fw_parse_variable_header_kernel(
 
 	for (i = 0; i < tas_fmw->nr_programs; i++) {
 		config = &(tas_fmw->configs[i]);
-		config->cfg_size = be32_to_cpup((__be32 *)&buf[offset]);
+		config->cfg_size = get_unaligned_be32(&buf[offset]);
 		offset += 4;
 	}
 

@@ -598,7 +597,7 @@ static int tasdevice_process_block(void *context, unsigned char *data,
 		switch (subblk_typ) {
 		case TASDEVICE_CMD_SING_W: {
 			int i;
-			unsigned short len = be16_to_cpup((__be16 *)&data[2]);
+			unsigned short len = get_unaligned_be16(&data[2]);
 
 			subblk_offset += 2;
 			if (subblk_offset + 4 * len > sublocksize) {

@@ -624,7 +623,7 @@ static int tasdevice_process_block(void *context, unsigned char *data,
 		}
 			break;
 		case TASDEVICE_CMD_BURST: {
-			unsigned short len = be16_to_cpup((__be16 *)&data[2]);
+			unsigned short len = get_unaligned_be16(&data[2]);
 
 			subblk_offset += 2;
 			if (subblk_offset + 4 + len > sublocksize) {

@@ -665,7 +664,7 @@ static int tasdevice_process_block(void *context, unsigned char *data,
 				is_err = true;
 				break;
 			}
-			sleep_time = be16_to_cpup((__be16 *)&data[2]) * 1000;
+			sleep_time = get_unaligned_be16(&data[2]) * 1000;
 			usleep_range(sleep_time, sleep_time + 50);
 			subblk_offset += 2;
 		}

@@ -940,7 +939,7 @@ static int fw_parse_variable_hdr(struct tasdevice_priv
 
 	offset += len;
 
-	fw_hdr->device_family = be32_to_cpup((__be32 *)&buf[offset]);
+	fw_hdr->device_family = get_unaligned_be32(&buf[offset]);
 	if (fw_hdr->device_family != 0) {
 		dev_err(tas_priv->dev, "%s: not TAS device\n", __func__);
 		offset = -EINVAL;

@@ -948,7 +947,7 @@ static int fw_parse_variable_hdr(struct tasdevice_priv
 	}
 	offset += 4;
 
-	fw_hdr->device = be32_to_cpup((__be32 *)&buf[offset]);
+	fw_hdr->device = get_unaligned_be32(&buf[offset]);
 	if (fw_hdr->device >= TASDEVICE_DSP_TAS_MAX_DEVICE ||
 		fw_hdr->device == 6) {
 		dev_err(tas_priv->dev, "Unsupported dev %d\n", fw_hdr->device);

@@ -993,7 +992,7 @@ static int fw_parse_block_data(struct tasdevice_fw *tas_fmw,
 		offset = -EINVAL;
 		goto out;
 	}
-	block->type = be32_to_cpup((__be32 *)&data[offset]);
+	block->type = get_unaligned_be32(&data[offset]);
 	offset += 4;
 
 	if (tas_fmw->fw_hdr.fixed_hdr.drv_ver >= PPC_DRIVER_CRCCHK) {

@@ -1018,7 +1017,7 @@ static int fw_parse_block_data(struct tasdevice_fw *tas_fmw,
 		block->is_ychksum_present = 0;
 	}
 
-	block->nr_cmds = be32_to_cpup((__be32 *)&data[offset]);
+	block->nr_cmds = get_unaligned_be32(&data[offset]);
 	offset += 4;
 
 	n = block->nr_cmds * 4;

@@ -1069,7 +1068,7 @@ static int fw_parse_data(struct tasdevice_fw *tas_fmw,
 		goto out;
 	}
 	offset += n;
-	img_data->nr_blk = be16_to_cpup((__be16 *)&data[offset]);
+	img_data->nr_blk = get_unaligned_be16(&data[offset]);
 	offset += 2;
 
 	img_data->dev_blks = kcalloc(img_data->nr_blk,

@@ -1106,7 +1105,7 @@ static int fw_parse_program_data(struct tasdevice_priv *tas_priv,
 		offset = -EINVAL;
 		goto out;
 	}
-	tas_fmw->nr_programs = be16_to_cpup((__be16 *)&buf[offset]);
+	tas_fmw->nr_programs = get_unaligned_be16(&buf[offset]);
 	offset += 2;
 
 	if (tas_fmw->nr_programs == 0) {

@@ -1173,7 +1172,7 @@ static int fw_parse_configuration_data(
 		offset = -EINVAL;
 		goto out;
 	}
-	tas_fmw->nr_configurations = be16_to_cpup((__be16 *)&data[offset]);
+	tas_fmw->nr_configurations = get_unaligned_be16(&data[offset]);
 	offset += 2;
 
 	if (tas_fmw->nr_configurations == 0) {

@@ -1805,7 +1804,7 @@ static int fw_parse_header(struct tasdevice_priv *tas_priv,
 	/* Convert data[offset], data[offset + 1], data[offset + 2] and
 	 * data[offset + 3] into host
 	 */
-	fw_fixed_hdr->fwsize = be32_to_cpup((__be32 *)&buf[offset]);
+	fw_fixed_hdr->fwsize = get_unaligned_be32(&buf[offset]);
 	offset += 4;
 	if (fw_fixed_hdr->fwsize != fmw->size) {
 		dev_err(tas_priv->dev, "File size not match, %lu %u",

@@ -1814,9 +1813,9 @@ static int fw_parse_header(struct tasdevice_priv *tas_priv,
 		goto out;
 	}
 	offset += 4;
-	fw_fixed_hdr->ppcver = be32_to_cpup((__be32 *)&buf[offset]);
+	fw_fixed_hdr->ppcver = get_unaligned_be32(&buf[offset]);
 	offset += 8;
-	fw_fixed_hdr->drv_ver = be32_to_cpup((__be32 *)&buf[offset]);
+	fw_fixed_hdr->drv_ver = get_unaligned_be32(&buf[offset]);
 	offset += 72;
 
  out:

@@ -1858,7 +1857,7 @@ static int fw_parse_calibration_data(struct tasdevice_priv *tas_priv,
 		offset = -EINVAL;
 		goto out;
 	}
-	tas_fmw->nr_calibrations = be16_to_cpup((__be16 *)&data[offset]);
+	tas_fmw->nr_calibrations = get_unaligned_be16(&data[offset]);
 	offset += 2;
 
 	if (tas_fmw->nr_calibrations != 1) {

2.43.0

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

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

From: Andreas Ziegler <[email protected]>

[ Upstream commit cedc12c5b57f7efa6dbebfb2b140e8675f5a2616 ]

In the current state, an erroneous call to bpf_object__find_map_by_name(NULL, ...) leads to a segmentation fault through the following call chain:

bpf_object__find_map_by_name(obj = NULL, ...)
-> bpf_object__for_each_map(pos, obj = NULL)
-> bpf_object__next_map((obj = NULL), NULL)
-> return (obj = NULL)->maps

While calling bpf_object__find_map_by_name with obj = NULL is obviously incorrect, this should not lead to a segmentation fault but rather be handled gracefully.

As __bpf_map__iter already handles this situation correctly, we can delegate the check for the regular case there and only add a check in case the prev or next parameter is NULL.

---
 tools/lib/bpf/libbpf.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

index de35b9a21dad..ceed16a10285 100644
@@ -9753,7 +9753,7 @@ __bpf_map__iter(const struct bpf_map *m, const struct bpf_object *obj, int i)
 struct bpf_map *
 bpf_object__next_map(const struct bpf_object *obj, const struct bpf_map *prev)
 {
-	if (prev == NULL)
+	if (prev == NULL && obj != NULL)
 		return obj->maps;
 
 	return __bpf_map__iter(prev, obj, 1);

@@ -9762,7 +9762,7 @@ bpf_object__next_map(const struct bpf_object *obj, const struct bpf_map *prev)
 struct bpf_map *
 bpf_object__prev_map(const struct bpf_object *obj, const struct bpf_map *next)
 {
-	if (next == NULL) {
+	if (next == NULL && obj != NULL) {
 		if (!obj->nr_maps)
 			return NULL;
 		return obj->maps + obj->nr_maps - 1;

2.43.0

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

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

From: Yifan Zha <[email protected]>

[ Upstream commit 33f23fc3155b13c4a96d94a0a22dc26db767440b ]

[Why]
If VF request full GPU access and the request failed,
the VF driver can get stuck accessing registers for an extended period during the unload of KMS.

[How]
Set no_hw_access flag when VF request for full GPU access fails This prevents further hardware access attempts, avoiding the prolonged stuck state.

---
 drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

index d9dc675b46ae..22575422ca7e 100644
@@ -137,8 +137,10 @@ int amdgpu_virt_request_full_gpu(struct amdgpu_device *adev, bool init)
 
 	if (virt->ops && virt->ops->req_full_gpu) {
 		r = virt->ops->req_full_gpu(adev, init);
-		if (r)
+		if (r) {
+			adev->no_hw_access = true;
 			return r;
+		}
 
 		adev->virt.caps &= ~AMDGPU_SRIOV_CAPS_RUNTIME;
 	}

2.43.0

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

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

From: Luis Henriques (SUSE) <[email protected]>

[ Upstream commit 63469662cc45d41705f14b4648481d5d29cf5999 ]

In the fast commit code there are a few places where tid_t variables are being compared without taking into account the fact that these sequence numbers may wrap. Fix this issue by using the helper functions tid_gt() and tid_geq().

---
 fs/ext4/fast_commit.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

index 5d473e50598f..f32a91d7c05d 100644
@@ -353,7 +353,7 @@ void ext4_fc_mark_ineligible(struct super_block *sb, int reason, handle_t *handl
 		read_unlock(&sbi->s_journal->j_state_lock);
 	}
 	spin_lock(&sbi->s_fc_lock);
-	if (sbi->s_fc_ineligible_tid < tid)
+	if (tid_gt(tid, sbi->s_fc_ineligible_tid))
 		sbi->s_fc_ineligible_tid = tid;
 	spin_unlock(&sbi->s_fc_lock);
 	WARN_ON(reason >= EXT4_FC_REASON_MAX);

@@ -1213,7 +1213,7 @@ int ext4_fc_commit(journal_t *journal, tid_t commit_tid)
 	if (ret == -EALREADY) {
 		/* There was an ongoing commit, check if we need to restart */
 		if (atomic_read(&sbi->s_fc_subtid) <= subtid &&
-			commit_tid > journal->j_commit_sequence)
+		    tid_gt(commit_tid, journal->j_commit_sequence))
 			goto restart_fc;
 		ext4_fc_update_stats(sb, EXT4_FC_STATUS_SKIPPED, 0, 0,
 				commit_tid);

@@ -1288,7 +1288,7 @@ static void ext4_fc_cleanup(journal_t *journal, int full, tid_t tid)
 		list_del_init(&iter->i_fc_list);
 		ext4_clear_inode_state(&iter->vfs_inode,
 				       EXT4_STATE_FC_COMMITTING);
-		if (iter->i_sync_tid <= tid)
+		if (tid_geq(tid, iter->i_sync_tid))
 			ext4_fc_reset_inode(&iter->vfs_inode);
 		/* Make sure EXT4_STATE_FC_COMMITTING bit is clear */
 		smp_mb();

@@ -1319,7 +1319,7 @@ static void ext4_fc_cleanup(journal_t *journal, int full, tid_t tid)
 	list_splice_init(&sbi->s_fc_q[FC_Q_STAGING],
 				&sbi->s_fc_q[FC_Q_MAIN]);
 
-	if (tid >= sbi->s_fc_ineligible_tid) {
+	if (tid_geq(tid, sbi->s_fc_ineligible_tid)) {
 		sbi->s_fc_ineligible_tid = 0;
 		ext4_clear_mount_flag(sb, EXT4_MF_FC_INELIGIBLE);
 	}

2.43.0

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

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

From: Ye Bin <[email protected]>

[ Upstream commit 0bab8db4152c4a2185a1367db09cc402bdc62d5e ]

We encountered a problem that the file system could not be mounted in the power-off scenario. The analysis of the file system mirror shows that only part of the data is written to the last commit block.
The valid data of the commit block is concentrated in the first sector. However, the data of the entire block is involved in the checksum calculation. For different hardware, the minimum atomic unit may be different. If the checksum of a committed block is incorrect, clear the data except the 'commit_header' and then calculate the checksum. If the checkusm is correct, it is considered that the block is partially committed, Then continue to replay journal.

---
 fs/jbd2/recovery.c | 30 ++++++++++++++++++++++++++++++
 1 file changed, 30 insertions(+)

index 5b771a3d8d9a..421c0d360836 100644
@@ -448,6 +448,27 @@ static int jbd2_commit_block_csum_verify(journal_t *j, void *buf)
 	return provided == cpu_to_be32(calculated);
 }
 
+static bool jbd2_commit_block_csum_verify_partial(journal_t *j, void *buf)
+{
+	struct commit_header *h;
+	__be32 provided;
+	__u32 calculated;
+	void *tmpbuf;
+
+	tmpbuf = kzalloc(j->j_blocksize, GFP_KERNEL);
+	if (!tmpbuf)
+		return false;
+
+	memcpy(tmpbuf, buf, sizeof(struct commit_header));
+	h = tmpbuf;
+	provided = h->h_chksum[0];
+	h->h_chksum[0] = 0;
+	calculated = jbd2_chksum(j, j->j_csum_seed, tmpbuf, j->j_blocksize);
+	kfree(tmpbuf);
+
+	return provided == cpu_to_be32(calculated);
+}
+
 static int jbd2_block_tag_csum_verify(journal_t *j, journal_block_tag_t *tag,
 				      journal_block_tag3_t *tag3,
 				      void *buf, __u32 sequence)

@@ -814,6 +835,13 @@ static int do_one_pass(journal_t *journal,
 			if (pass == PASS_SCAN &&
 			    !jbd2_commit_block_csum_verify(journal,
 							   bh->b_data)) {
+				if (jbd2_commit_block_csum_verify_partial(
+								  journal,
+								  bh->b_data)) {
+					pr_notice("JBD2: Find incomplete commit block in transaction %u block %lu\n",
+						  next_commit_ID, next_log_block);
+					goto chksum_ok;
+				}
 			chksum_error:
 				if (commit_time < last_trans_commit_time)
 					goto ignore_crc_mismatch;

@@ -828,6 +856,7 @@ static int do_one_pass(journal_t *journal,
 				}
 			}
 			if (pass == PASS_SCAN) {
+			chksum_ok:
 				last_trans_commit_time = commit_time;
 				head_block = next_log_block;
 			}

@@ -847,6 +876,7 @@ static int do_one_pass(journal_t *journal,
 					  next_log_block);
 				need_check_commit_time = true;
 			}
+
 			/* If we aren't in the REVOKE pass, then we can
 			 * just skip over this block. */
 			if (pass != PASS_REVOKE) {

2.43.0

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

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

From: Yicong Yang <[email protected]>

[ Upstream commit 54624acf8843375a6de3717ac18df3b5104c39c5 ]

The test thread will start N benchmark kthreads and then schedule out until the test time finished and notify the benchmark kthreads to stop. The benchmark kthreads will keep running until notified to stop. There's a problem with current implementation when the benchmark kthreads number is equal to the CPUs on a non-preemptible kernel:
since the scheduler will balance the kthreads across the CPUs and when the test time's out the test thread won't get a chance to be scheduled on any CPU then cannot notify the benchmark kthreads to stop.

This can be easily reproduced on a VM (simulated with 16 CPUs) with PREEMPT_VOLUNTARY:

estuary:/mnt$ ./dma_map_benchmark -t 16 -s 1
 rcu: INFO: rcu_sched self-detected stall on CPU
 rcu:     10-...!: (5221 ticks this GP) idle=ed24/1/0x4000000000000000 softirq=142/142 fqs=0
 rcu:     (t=5254 jiffies g=-559 q=45 ncpus=16)
 rcu: rcu_sched kthread starved for 5255 jiffies! g-559 f0x0 RCU_GP_WAIT_FQS(5) ->state=0x0 ->cpu=12
 rcu:     Unless rcu_sched kthread gets sufficient CPU time, OOM is now expected behavior.
 rcu: RCU grace-period kthread stack dump:
 task:rcu_sched       state:R  running task     stack:0     pid:16    tgid:16    ppid:2      flags:0x00000008
 Call trace
  __switch_to+0xec/0x138
  __schedule+0x2f8/0x1080
  schedule+0x30/0x130
  schedule_timeout+0xa0/0x188
  rcu_gp_fqs_loop+0x128/0x528
  rcu_gp_kthread+0x1c8/0x208
  kthread+0xec/0xf8
  ret_from_fork+0x10/0x20
 Sending NMI from CPU 10 to CPUs 0:
 NMI backtrace for cpu 0
 CPU: 0 PID: 332 Comm: dma-map-benchma Not tainted 6.10.0-rc1-vanilla-LSE #8
 Hardware name: QEMU KVM Virtual Machine, BIOS 0.0.0 02/06/2015
 pstate: 20400005 (nzCv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--)
 pc : arm_smmu_cmdq_issue_cmdlist+0x218/0x730
 lr : arm_smmu_cmdq_issue_cmdlist+0x488/0x730
 sp : ffff80008748b630
 x29: ffff80008748b630 x28: 0000000000000000 x27: ffff80008748b780
 x26: 0000000000000000 x25: 000000000000bc70 x24: 000000000001bc70
 x23: ffff0000c12af080 x22: 0000000000010000 x21: 000000000000ffff
 x20: ffff80008748b700 x19: ffff0000c12af0c0 x18: 0000000000010000
 x17: 0000000000000001 x16: 0000000000000040 x15: ffffffffffffffff
 x14: 0001ffffffffffff x13: 000000000000ffff x12: 00000000000002f1
 x11: 000000000001ffff x10: 0000000000000031 x9 : ffff800080b6b0b8
 x8 : ffff0000c2a48000 x7 : 000000000001bc71 x6 : 0001800000000000
 x5 : 00000000000002f1 x4 : 01ffffffffffffff x3 : 000000000009aaf1
 x2 : 0000000000000018 x1 : 000000000000000f x0 : ffff0000c12af18c
 Call trace:
  arm_smmu_cmdq_issue_cmdlist+0x218/0x730
  __arm_smmu_tlb_inv_range+0xe0/0x1a8
  arm_smmu_iotlb_sync+0xc0/0x128
  __iommu_dma_unmap+0x248/0x320
  iommu_dma_unmap_page+0x5c/0xe8
  dma_unmap_page_attrs+0x38/0x1d0
  map_benchmark_thread+0x118/0x2c0
  kthread+0xec/0xf8
  ret_from_fork+0x10/0x20

Solve this by adding scheduling point in the kthread loop, so if there're other threads in the system they may have a chance to run, especially the thread to notify the test end. However this may degrade the test concurrency so it's recommended to run this on an idle system.

---
 kernel/dma/map_benchmark.c | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

index 4950e0b622b1..cc19a3efea89 100644
@@ -89,6 +89,22 @@ static int map_benchmark_thread(void *data)
 		atomic64_add(map_sq, &map->sum_sq_map);
 		atomic64_add(unmap_sq, &map->sum_sq_unmap);
 		atomic64_inc(&map->loops);
+
+		/*
+		 * We may test for a long time so periodically check whether
+		 * we need to schedule to avoid starving the others. Otherwise
+		 * we may hangup the kernel in a non-preemptible kernel when
+		 * the test kthreads number >= CPU number, the test kthreads
+		 * will run endless on every CPU since the thread resposible
+		 * for notifying the kthread stop (in do_map_benchmark())
+		 * could not be scheduled.
+		 *
+		 * Note this may degrade the test concurrency since the test
+		 * threads may need to share the CPU time with other load
+		 * in the system. So it's recommended to run this benchmark
+		 * on an idle system.
+		 */
+		cond_resched();
 	}
 
 out:

2.43.0

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

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

From: Sascha Hauer <[email protected]>

[ Upstream commit c145eea2f75ff7949392aebecf7ef0a81c1f6c14 ]

mwifiex_get_priv_by_id() returns the priv pointer corresponding to the bss_num and bss_type, but without checking if the priv is actually currently in use.
Unused priv pointers do not have a wiphy attached to them which can lead to NULL pointer dereferences further down the callstack. Fix this by returning only used priv pointers which have priv->bss_mode set to something else than NL80211_IFTYPE_UNSPECIFIED.

Said NULL pointer dereference happened when an Accesspoint was started with wpa_supplicant -i mlan0 with this config:

network={
        ssid="somessid"
        mode=2
        frequency=2412
        key_mgmt=WPA-PSK WPA-PSK-SHA256
        proto=RSN
        group=CCMP
        pairwise=CCMP
        psk="12345678"
}

When waiting for the AP to be established, interrupting wpa_supplicant with <ctrl-c> and starting it again this happens:

| Unable to handle kernel NULL pointer dereference at virtual address 0000000000000140
| 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
| user pgtable: 4k pages, 48-bit VAs, pgdp=0000000046d96000
| [0000000000000140] pgd=0000000000000000, p4d=0000000000000000
| Internal error: Oops: 0000000096000004 [#1] PREEMPT SMP
| Modules linked in: caam_jr caamhash_desc spidev caamalg_desc crypto_engine authenc libdes mwifiex_sdio
+mwifiex crct10dif_ce cdc_acm onboard_usb_hub fsl_imx8_ddr_perf imx8m_ddrc rtc_ds1307 lm75 rtc_snvs
+imx_sdma caam imx8mm_thermal spi_imx error imx_cpufreq_dt fuse ip_tables x_tables ipv6
| CPU: 0 PID: 8 Comm: kworker/0:1 Not tainted 6.9.0-00007-g937242013fce-dirty #18
| Hardware name: somemachine (DT)
| Workqueue: events sdio_irq_work
| pstate: 00000005 (nzcv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--)
| pc : mwifiex_get_cfp+0xd8/0x15c [mwifiex]
| lr : mwifiex_get_cfp+0x34/0x15c [mwifiex]
| sp : ffff8000818b3a70
| x29: ffff8000818b3a70 x28: ffff000006bfd8a5 x27: 0000000000000004
| x26: 000000000000002c x25: 0000000000001511 x24: 0000000002e86bc9
| x23: ffff000006bfd996 x22: 0000000000000004 x21: ffff000007bec000
| x20: 000000000000002c x19: 0000000000000000 x18: 0000000000000000
| x17: 000000040044ffff x16: 00500072b5503510 x15: ccc283740681e517
| x14: 0201000101006d15 x13: 0000000002e8ff43 x12: 002c01000000ffb1
| x11: 0100000000000000 x10: 02e8ff43002c0100 x9 : 0000ffb100100157
| x8 : ffff000003d20000 x7 : 00000000000002f1 x6 : 00000000ffffe124
| x5 : 0000000000000001 x4 : 0000000000000003 x3 : 0000000000000000
| x2 : 0000000000000000 x1 : 0001000000011001 x0 : 0000000000000000
| Call trace:
|  mwifiex_get_cfp+0xd8/0x15c [mwifiex]
|  mwifiex_parse_single_response_buf+0x1d0/0x504 [mwifiex]
|  mwifiex_handle_event_ext_scan_report+0x19c/0x2f8 [mwifiex]
|  mwifiex_process_sta_event+0x298/0xf0c [mwifiex]
|  mwifiex_process_event+0x110/0x238 [mwifiex]
|  mwifiex_main_process+0x428/0xa44 [mwifiex]
|  mwifiex_sdio_interrupt+0x64/0x12c [mwifiex_sdio]
|  process_sdio_pending_irqs+0x64/0x1b8
|  sdio_irq_work+0x4c/0x7c
|  process_one_work+0x148/0x2a0
|  worker_thread+0x2fc/0x40c
|  kthread+0x110/0x114
|  ret_from_fork+0x10/0x20
| Code: a94153f3 a8c37bfd d50323bf d65f03c0 (f940a000)
| ---[ end trace 0000000000000000 ]---

---
 drivers/net/wireless/marvell/mwifiex/main.h | 3 +++
 1 file changed, 3 insertions(+)

index 7bdec6c62248..dc6b4cf616be 100644
@@ -1290,6 +1290,9 @@ mwifiex_get_priv_by_id(struct mwifiex_adapter *adapter,
 
 	for (i = 0; i < adapter->priv_num; i++) {
 		if (adapter->priv[i]) {
+			if (adapter->priv[i]->bss_mode == NL80211_IFTYPE_UNSPECIFIED)
+				continue;
+
 			if ((adapter->priv[i]->bss_num == bss_num) &&
 			    (adapter->priv[i]->bss_type == bss_type))
 				break;

2.43.0

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

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

From: Christian König <[email protected]>

[ Upstream commit 320debca1ba3a81c87247eac84eff976ead09ee0 ]

A gang submit won't work if the VMID is reserved and we can't flush out VM changes from multiple engines at the same time.

---
 drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c  | 15 +++++++++++++++
 drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c | 15 ++++++++++++++-
 drivers/gpu/drm/amd/amdgpu/amdgpu_ids.h |  1 +
 3 files changed, 30 insertions(+), 1 deletion(-)

index 61668a784315..e361dc37a089 100644
@@ -1096,6 +1096,21 @@ static int amdgpu_cs_vm_handling(struct amdgpu_cs_parser *p)
 	unsigned int i;
 	int r;
 
+	/*
+	 * We can't use gang submit on with reserved VMIDs when the VM changes
+	 * can't be invalidated by more than one engine at the same time.
+	 */
+	if (p->gang_size > 1 && !p->adev->vm_manager.concurrent_flush) {
+		for (i = 0; i < p->gang_size; ++i) {
+			struct drm_sched_entity *entity = p->entities[i];
+			struct drm_gpu_scheduler *sched = entity->rq->sched;
+			struct amdgpu_ring *ring = to_amdgpu_ring(sched);
+
+			if (amdgpu_vmid_uses_reserved(vm, ring->vm_hub))
+				return -EINVAL;
+		}
+	}
+
 	r = amdgpu_vm_clear_freed(adev, vm, NULL);
 	if (r)
 		return r;

index ff1ea99292fb..69dfc699d78b 100644
@@ -409,7 +409,7 @@ int amdgpu_vmid_grab(struct amdgpu_vm *vm, struct amdgpu_ring *ring,
 	if (r || !idle)
 		goto error;
 
-	if (vm->reserved_vmid[vmhub] || (enforce_isolation && (vmhub == AMDGPU_GFXHUB(0)))) {
+	if (amdgpu_vmid_uses_reserved(vm, vmhub)) {
 		r = amdgpu_vmid_grab_reserved(vm, ring, job, &id, fence);
 		if (r || !id)
 			goto error;

@@ -459,6 +459,19 @@ int amdgpu_vmid_grab(struct amdgpu_vm *vm, struct amdgpu_ring *ring,
 	return r;
 }
 
+/*
+ * amdgpu_vmid_uses_reserved - check if a VM will use a reserved VMID
+ * @vm: the VM to check
+ * @vmhub: the VMHUB which will be used
+ *
+ * Returns: True if the VM will use a reserved VMID.
+ */
+bool amdgpu_vmid_uses_reserved(struct amdgpu_vm *vm, unsigned int vmhub)
+{
+	return vm->reserved_vmid[vmhub] ||
+		(enforce_isolation && (vmhub == AMDGPU_GFXHUB(0)));
+}
+
 int amdgpu_vmid_alloc_reserved(struct amdgpu_device *adev,
 			       unsigned vmhub)
 {

index fa8c42c83d5d..240fa6751260 100644
@@ -78,6 +78,7 @@ void amdgpu_pasid_free_delayed(struct dma_resv *resv,
 
 bool amdgpu_vmid_had_gpu_reset(struct amdgpu_device *adev,
 			       struct amdgpu_vmid *id);
+bool amdgpu_vmid_uses_reserved(struct amdgpu_vm *vm, unsigned int vmhub);
 int amdgpu_vmid_alloc_reserved(struct amdgpu_device *adev,
 				unsigned vmhub);
 void amdgpu_vmid_free_reserved(struct amdgpu_device *adev,

2.43.0

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

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

From: Zqiang <[email protected]>

[ Upstream commit 77aeb1b685f9db73d276bad4bb30d48505a6fd23 ]

For CONFIG_DEBUG_OBJECTS_WORK=y kernels sscs.work defined by INIT_WORK_ONSTACK() is initialized by debug_object_init_on_stack() for the debug check in __init_work() to work correctly.

But this lacks the counterpart to remove the tracked object from debug objects again, which will cause a debug object warning once the stack is freed.

Add the missing destroy_work_on_stack() invocation to cure that.

[ tglx: Massaged changelog ]

---
 kernel/smp.c | 1 +
 1 file changed, 1 insertion(+)

index 695eb13a276d..3eeffeaf5450 100644
@@ -1119,6 +1119,7 @@ int smp_call_on_cpu(unsigned int cpu, int (*func)(void *), void *par, bool phys)
 
 	queue_work_on(cpu, system_wq, &sscs.work);
 	wait_for_completion(&sscs.done);
+	destroy_work_on_stack(&sscs.work);
 
 	return sscs.ret;
 }

2.43.0

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

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

From: Konstantin Komarov <[email protected]>

[ Upstream commit 744375343662058cbfda96d871786e5a5cbe1947 ]

Mark ntfs dirty in this case.
Rename ntfs_filldir to ntfs_dir_emit.

---
 fs/ntfs3/dir.c | 52 +++++++++++++++++++++++++++++++-------------------
 1 file changed, 32 insertions(+), 20 deletions(-)

index 9d0a09f00b38..e1b856ecce61 100644
@@ -272,9 +272,12 @@ struct inode *dir_search_u(struct inode *dir, const struct cpu_str *uni,
 	return err == -ENOENT ? NULL : err ? ERR_PTR(err) : inode;
 }
 
-static inline int ntfs_filldir(struct ntfs_sb_info *sbi, struct ntfs_inode *ni,
-			       const struct NTFS_DE *e, u8 *name,
-			       struct dir_context *ctx)
+/*
+ * returns false if 'ctx' if full
+ */
+static inline bool ntfs_dir_emit(struct ntfs_sb_info *sbi,
+				 struct ntfs_inode *ni, const struct NTFS_DE *e,
+				 u8 *name, struct dir_context *ctx)
 {
 	const struct ATTR_FILE_NAME *fname;
 	unsigned long ino;

@@ -284,29 +287,29 @@ static inline int ntfs_filldir(struct ntfs_sb_info *sbi, struct ntfs_inode *ni,
 	fname = Add2Ptr(e, sizeof(struct NTFS_DE));
 
 	if (fname->type == FILE_NAME_DOS)
-		return 0;
+		return true;
 
 	if (!mi_is_ref(&ni->mi, &fname->home))
-		return 0;
+		return true;
 
 	ino = ino_get(&e->ref);
 
 	if (ino == MFT_REC_ROOT)
-		return 0;
+		return true;
 
 	/* Skip meta files. Unless option to show metafiles is set. */
 	if (!sbi->options->showmeta && ntfs_is_meta_file(sbi, ino))
-		return 0;
+		return true;
 
 	if (sbi->options->nohidden && (fname->dup.fa & FILE_ATTRIBUTE_HIDDEN))
-		return 0;
+		return true;
 
 	name_len = ntfs_utf16_to_nls(sbi, fname->name, fname->name_len, name,
 				     PATH_MAX);
 	if (name_len <= 0) {
 		ntfs_warn(sbi->sb, "failed to convert name for inode %lx.",
 			  ino);
-		return 0;
+		return true;
 	}
 
 	/*

@@ -336,17 +339,20 @@ static inline int ntfs_filldir(struct ntfs_sb_info *sbi, struct ntfs_inode *ni,
 		}
 	}
 
-	return !dir_emit(ctx, (s8 *)name, name_len, ino, dt_type);
+	return dir_emit(ctx, (s8 *)name, name_len, ino, dt_type);
 }
 
 /*
  * ntfs_read_hdr - Helper function for ntfs_readdir().
+ *
+ * returns 0 if ok.
+ * returns -EINVAL if directory is corrupted.
+ * returns +1 if 'ctx' is full.
  */
 static int ntfs_read_hdr(struct ntfs_sb_info *sbi, struct ntfs_inode *ni,
 			 const struct INDEX_HDR *hdr, u64 vbo, u64 pos,
 			 u8 *name, struct dir_context *ctx)
 {
-	int err;
 	const struct NTFS_DE *e;
 	u32 e_size;
 	u32 end = le32_to_cpu(hdr->used);

@@ -354,12 +360,12 @@ static int ntfs_read_hdr(struct ntfs_sb_info *sbi, struct ntfs_inode *ni,
 
 	for (;; off += e_size) {
 		if (off + sizeof(struct NTFS_DE) > end)
-			return -1;
+			return -EINVAL;
 
 		e = Add2Ptr(hdr, off);
 		e_size = le16_to_cpu(e->size);
 		if (e_size < sizeof(struct NTFS_DE) || off + e_size > end)
-			return -1;
+			return -EINVAL;
 
 		if (de_is_last(e))
 			return 0;

@@ -369,14 +375,15 @@ static int ntfs_read_hdr(struct ntfs_sb_info *sbi, struct ntfs_inode *ni,
 			continue;
 
 		if (le16_to_cpu(e->key_size) < SIZEOF_ATTRIBUTE_FILENAME)
-			return -1;
+			return -EINVAL;
 
 		ctx->pos = vbo + off;
 
 		/* Submit the name to the filldir callback. */
-		err = ntfs_filldir(sbi, ni, e, name, ctx);
-		if (err)
-			return err;
+		if (!ntfs_dir_emit(sbi, ni, e, name, ctx)) {
+			/* ctx is full. */
+			return +1;
+		}
 	}
 }
 

@@ -475,8 +482,6 @@ static int ntfs_readdir(struct file *file, struct dir_context *ctx)
 
 		vbo = (u64)bit << index_bits;
 		if (vbo >= i_size) {
-			ntfs_inode_err(dir, "Looks like your dir is corrupt");
-			ctx->pos = eod;
 			err = -EINVAL;
 			goto out;
 		}

@@ -499,9 +504,16 @@ static int ntfs_readdir(struct file *file, struct dir_context *ctx)
 	__putname(name);
 	put_indx_node(node);
 
-	if (err == -ENOENT) {
+	if (err == 1) {
+		/* 'ctx' is full. */
+		err = 0;
+	} else if (err == -ENOENT) {
 		err = 0;
 		ctx->pos = pos;
+	} else if (err < 0) {
+		if (err == -EINVAL)
+			ntfs_inode_err(dir, "directory corrupted");
+		ctx->pos = eod;
 	}
 
 	return err;

2.43.0

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

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

From: Josef Bacik <[email protected]>

[ Upstream commit 1f9d44c0a12730a24f8bb75c5e1102207413cc9b ]

We have a couple of areas where we check to make sure the tree block is locked before looking up or messing with references. This is old code so it has this as BUG_ON(). Convert this to ASSERT() for developers.

---
 fs/btrfs/extent-tree.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

index c6ecfd05e1db..2d39481fb3ce 100644
@@ -5144,7 +5144,7 @@ static noinline int walk_down_proc(struct btrfs_trans_handle *trans,
 	if (lookup_info &&
 	    ((wc->stage == DROP_REFERENCE && wc->refs[level] != 1) ||
 	     (wc->stage == UPDATE_BACKREF && !(wc->flags[level] & flag)))) {
-		BUG_ON(!path->locks[level]);
+		ASSERT(path->locks[level]);
 		ret = btrfs_lookup_extent_info(trans, fs_info,
 					       eb->start, level, 1,
 					       &wc->refs[level],

@@ -5168,7 +5168,7 @@ static noinline int walk_down_proc(struct btrfs_trans_handle *trans,
 
 	/* wc->stage == UPDATE_BACKREF */
 	if (!(wc->flags[level] & flag)) {
-		BUG_ON(!path->locks[level]);
+		ASSERT(path->locks[level]);
 		ret = btrfs_inc_ref(trans, root, eb, 1);
 		BUG_ON(ret); /* -ENOMEM */
 		ret = btrfs_dec_ref(trans, root, eb, 0);

2.43.0

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

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

From: Josef Bacik <[email protected]>

[ Upstream commit b8ccef048354074a548f108e51d0557d6adfd3a3 ]

In reada we BUG_ON(refs == 0), which could be unkind since we aren't holding a lock on the extent leaf and thus could get a transient incorrect answer. In walk_down_proc we also BUG_ON(refs == 0), which could happen if we have extent tree corruption. Change that to return -EUCLEAN. In do_walk_down() we catch this case and handle it correctly, however we return -EIO, which -EUCLEAN is a more appropriate error code. Finally in walk_up_proc we have the same BUG_ON(refs == 0), so convert that to proper error handling. Also adjust the error message so we can actually do something with the information.

---
 fs/btrfs/extent-tree.c | 28 +++++++++++++++++++++++-----
 1 file changed, 23 insertions(+), 5 deletions(-)

index 2d39481fb3ce..72851adc1fee 100644
@@ -5085,7 +5085,15 @@ static noinline void reada_walk_down(struct btrfs_trans_handle *trans,
 		/* We don't care about errors in readahead. */
 		if (ret < 0)
 			continue;
-		BUG_ON(refs == 0);
+
+		/*
+		 * This could be racey, it's conceivable that we raced and end
+		 * up with a bogus refs count, if that's the case just skip, if
+		 * we are actually corrupt we will notice when we look up
+		 * everything again with our locks.
+		 */
+		if (refs == 0)
+			continue;
 
 		if (wc->stage == DROP_REFERENCE) {
 			if (refs == 1)

@@ -5152,7 +5160,11 @@ static noinline int walk_down_proc(struct btrfs_trans_handle *trans,
 		BUG_ON(ret == -ENOMEM);
 		if (ret)
 			return ret;
-		BUG_ON(wc->refs[level] == 0);
+		if (unlikely(wc->refs[level] == 0)) {
+			btrfs_err(fs_info, "bytenr %llu has 0 references, expect > 0",
+				  eb->start);
+			return -EUCLEAN;
+		}
 	}
 
 	if (wc->stage == DROP_REFERENCE) {

@@ -5286,8 +5298,9 @@ static noinline int do_walk_down(struct btrfs_trans_handle *trans,
 		goto out_unlock;
 
 	if (unlikely(wc->refs[level - 1] == 0)) {
-		btrfs_err(fs_info, "Missing references.");
-		ret = -EIO;
+		btrfs_err(fs_info, "bytenr %llu has 0 references, expect > 0",
+			  bytenr);
+		ret = -EUCLEAN;
 		goto out_unlock;
 	}
 	*lookup_info = 0;

@@ -5487,7 +5500,12 @@ static noinline int walk_up_proc(struct btrfs_trans_handle *trans,
 				path->locks[level] = 0;
 				return ret;
 			}
-			BUG_ON(wc->refs[level] == 0);
+			if (unlikely(wc->refs[level] == 0)) {
+				btrfs_tree_unlock_rw(eb, path->locks[level]);
+				btrfs_err(fs_info, "bytenr %llu has 0 references, expect > 0",
+					  eb->start);
+				return -EUCLEAN;
+			}
 			if (wc->refs[level] == 1) {
 				btrfs_tree_unlock_rw(eb, path->locks[level]);
 				path->locks[level] = 0;

2.43.0

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

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

From: Filipe Manana <[email protected]>

[ Upstream commit b56329a782314fde5b61058e2a25097af7ccb675 ]

Instead of a BUG_ON() just return an error, log an error message and abort the transaction in case we find an extent buffer belonging to the relocation tree that doesn't have the full backref flag set. This is unexpected and should never happen (save for bugs or a potential bad memory).

---
 fs/btrfs/ctree.c | 12 ++++++++++--
 1 file changed, 10 insertions(+), 2 deletions(-)

index 118ad4d2cbbe..2eb4e03080ac 100644
@@ -451,8 +451,16 @@ static noinline int update_ref_for_cow(struct btrfs_trans_handle *trans,
 	}
 
 	owner = btrfs_header_owner(buf);
-	BUG_ON(owner == BTRFS_TREE_RELOC_OBJECTID &&
-	       !(flags & BTRFS_BLOCK_FLAG_FULL_BACKREF));
+	if (unlikely(owner == BTRFS_TREE_RELOC_OBJECTID &&
+		     !(flags & BTRFS_BLOCK_FLAG_FULL_BACKREF))) {
+		btrfs_crit(fs_info,
+"found tree block at bytenr %llu level %d root %llu refs %llu flags %llx without full backref flag set",
+			   buf->start, btrfs_header_level(buf),
+			   btrfs_root_id(root), refs, flags);
+		ret = -EUCLEAN;
+		btrfs_abort_transaction(trans, ret);
+		return ret;
+	}
 
 	if (refs > 1) {
 		if ((owner == root->root_key.objectid ||

2.43.0

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

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

From: Alison Schofield <[email protected]>

[ Upstream commit 82a3e3a235633aa0575fac9507d648dd80f3437f ]

When a root decoder is configured the interleave target list is read from the BIOS populated CFMWS structure. Per the CXL spec 3.1 Table 9-22 the target list is in interleave order. The CXL driver populates its decoder target list in the same order and stores it in 'struct cxl_switch_decoder' field "@target: active ordered target list in current decoder configuration"

Given the promise of an ordered list, the driver can stop duplicating the work of BIOS and simply check target positions against the ordered list during region configuration.

The simplified check against the ordered list is presented here. A follow-on patch will remove the unused code.

For Modulo arithmetic this is not a fix, only a simplification. For XOR arithmetic this is a fix for HB IW of 3,6,12.

---
 drivers/cxl/core/region.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

index bc5a43897d57..5060d9802795 100644
@@ -1528,10 +1528,13 @@ static int cxl_region_attach_position(struct cxl_region *cxlr,
 				      const struct cxl_dport *dport, int pos)
 {
 	struct cxl_memdev *cxlmd = cxled_to_memdev(cxled);
+	struct cxl_switch_decoder *cxlsd = &cxlrd->cxlsd;
+	struct cxl_decoder *cxld = &cxlsd->cxld;
+	int iw = cxld->interleave_ways;
 	struct cxl_port *iter;
 	int rc;
 
-	if (cxlrd->calc_hb(cxlrd, pos) != dport) {
+	if (dport != cxlrd->cxlsd.target[pos % iw]) {
 		dev_dbg(&cxlr->dev, "%s:%s invalid target position for %s\n",
 			dev_name(&cxlmd->dev), dev_name(&cxled->cxld.dev),
 			dev_name(&cxlrd->cxlsd.cxld.dev));

2.43.0

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

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

From: yang.zhang <[email protected]>

[ Upstream commit 6ad8735994b854b23c824dd6b1dd2126e893a3b4 ]

The exception vector of the booting hart is not set before enabling the mmu and then still points to the value of the previous firmware, typically _start. That makes it hard to debug setup_vm() when bad things happen. So fix that by setting the exception vector earlier.

---
 arch/riscv/kernel/head.S | 3 +++
 1 file changed, 3 insertions(+)

index 0097c145385f..9691fa8f2faa 100644
@@ -305,6 +305,9 @@ clear_bss_done:
 #else
 	mv a0, a1
 #endif /* CONFIG_BUILTIN_DTB */
+	/* Set trap vector to spin forever to help debug */
+	la a3, .Lsecondary_park
+	csrw CSR_TVEC, a3
 	call setup_vm
 #ifdef CONFIG_MMU
 	la a0, early_pg_dir

2.43.0

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

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

From: Dan Williams <[email protected]>

[ Upstream commit a4e772898f8bf2e7e1cf661a12c60a5612c4afab ]

One of the true positives that the cfg_access_lock lockdep effort identified is this sequence:

  WARNING: CPU: 14 PID: 1 at drivers/pci/pci.c:4886 pci_bridge_secondary_bus_reset+0x5d/0x70
  RIP: 0010:pci_bridge_secondary_bus_reset+0x5d/0x70
  Call Trace:
   <TASK>
   ? __warn+0x8c/0x190
   ? pci_bridge_secondary_bus_reset+0x5d/0x70
   ? report_bug+0x1f8/0x200
   ? handle_bug+0x3c/0x70
   ? exc_invalid_op+0x18/0x70
   ? asm_exc_invalid_op+0x1a/0x20
   ? pci_bridge_secondary_bus_reset+0x5d/0x70
   pci_reset_bus+0x1d8/0x270
   vmd_probe+0x778/0xa10
   pci_device_probe+0x95/0x120

Where pci_reset_bus() users are triggering unlocked secondary bus resets. Ironically pci_bus_reset(), several calls down from pci_reset_bus(), uses pci_bus_lock() before issuing the reset which locks everything *but* the bridge itself.

For the same motivation as adding:

  bridge = pci_upstream_bridge(dev);
  if (bridge)
    pci_dev_lock(bridge);

to pci_reset_function() for the "bus" and "cxl_bus" reset cases, add pci_dev_lock() for @bus->self to pci_bus_lock().

[bhelgaas: squash in recursive locking deadlock fix from Keith Busch:
https://lore.kernel.org/r/[email protected]]

---
 drivers/pci/pci.c | 35 +++++++++++++++++++++--------------
 1 file changed, 21 insertions(+), 14 deletions(-)

index a0f961a380fa..53e9e9788bd5 100644
@@ -5718,10 +5718,12 @@ static void pci_bus_lock(struct pci_bus *bus)
 {
 	struct pci_dev *dev;
 
+	pci_dev_lock(bus->self);
 	list_for_each_entry(dev, &bus->devices, bus_list) {
-		pci_dev_lock(dev);
 		if (dev->subordinate)
 			pci_bus_lock(dev->subordinate);
+		else
+			pci_dev_lock(dev);
 	}
 }
 

@@ -5733,8 +5735,10 @@ static void pci_bus_unlock(struct pci_bus *bus)
 	list_for_each_entry(dev, &bus->devices, bus_list) {
 		if (dev->subordinate)
 			pci_bus_unlock(dev->subordinate);
-		pci_dev_unlock(dev);
+		else
+			pci_dev_unlock(dev);
 	}
+	pci_dev_unlock(bus->self);
 }
 
 /* Return 1 on successful lock, 0 on contention */

@@ -5742,15 +5746,15 @@ static int pci_bus_trylock(struct pci_bus *bus)
 {
 	struct pci_dev *dev;
 
+	if (!pci_dev_trylock(bus->self))
+		return 0;
+
 	list_for_each_entry(dev, &bus->devices, bus_list) {
-		if (!pci_dev_trylock(dev))
-			goto unlock;
 		if (dev->subordinate) {
-			if (!pci_bus_trylock(dev->subordinate)) {
-				pci_dev_unlock(dev);
+			if (!pci_bus_trylock(dev->subordinate))
 				goto unlock;
-			}
-		}
+		} else if (!pci_dev_trylock(dev))
+			goto unlock;
 	}
 	return 1;
 

@@ -5758,8 +5762,10 @@ static int pci_bus_trylock(struct pci_bus *bus)
 	list_for_each_entry_continue_reverse(dev, &bus->devices, bus_list) {
 		if (dev->subordinate)
 			pci_bus_unlock(dev->subordinate);
-		pci_dev_unlock(dev);
+		else
+			pci_dev_unlock(dev);
 	}
+	pci_dev_unlock(bus->self);
 	return 0;
 }
 

@@ -5791,9 +5797,10 @@ static void pci_slot_lock(struct pci_slot *slot)
 	list_for_each_entry(dev, &slot->bus->devices, bus_list) {
 		if (!dev->slot || dev->slot != slot)
 			continue;
-		pci_dev_lock(dev);
 		if (dev->subordinate)
 			pci_bus_lock(dev->subordinate);
+		else
+			pci_dev_lock(dev);
 	}
 }
 

@@ -5819,14 +5826,13 @@ static int pci_slot_trylock(struct pci_slot *slot)
 	list_for_each_entry(dev, &slot->bus->devices, bus_list) {
 		if (!dev->slot || dev->slot != slot)
 			continue;
-		if (!pci_dev_trylock(dev))
-			goto unlock;
 		if (dev->subordinate) {
 			if (!pci_bus_trylock(dev->subordinate)) {
 				pci_dev_unlock(dev);
 				goto unlock;
 			}
-		}
+		} else if (!pci_dev_trylock(dev))
+			goto unlock;
 	}
 	return 1;
 

@@ -5837,7 +5843,8 @@ static int pci_slot_trylock(struct pci_slot *slot)
 			continue;
 		if (dev->subordinate)
 			pci_bus_unlock(dev->subordinate);
-		pci_dev_unlock(dev);
+		else
+			pci_dev_unlock(dev);
 	}
 	return 0;
 }

2.43.0

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

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

From: Kuniyuki Iwashima <[email protected]>

[ Upstream commit 23e89e8ee7be73e21200947885a6d3a109a2c58d ]

RFC 9293 states that in the case of simultaneous connect(), the connection gets established when SYN+ACK is received. [0]

TCP Peer A TCP Peer B

  1.  CLOSED                                           CLOSED
  2.  SYN-SENT     --> <SEQ=100><CTL=SYN>              ...
  3.  SYN-RECEIVED <-- <SEQ=300><CTL=SYN>              <-- SYN-SENT
  4.               ... <SEQ=100><CTL=SYN>              --> SYN-RECEIVED

5. SYN-RECEIVED --> <SEQ=100><ACK=301><CTL=SYN,ACK> ...
6. ESTABLISHED <-- <SEQ=300><ACK=101><CTL=SYN,ACK> <-- SYN-RECEIVED
7. ... <SEQ=100><ACK=301><CTL=SYN,ACK> --> ESTABLISHED

However, since commit 0c24604b68fc ("tcp: implement RFC 5961 4.2"), such a SYN+ACK is dropped in tcp_validate_incoming() and responded with Challenge ACK.

For example, the write() syscall in the following packetdrill script fails with -EAGAIN, and wrong SNMP stats get incremented.

0 socket(..., SOCK_STREAM|SOCK_NONBLOCK, IPPROTO_TCP) = 3
+0 connect(3, ..., ...) = -1 EINPROGRESS (Operation now in progress)

+0 > S 0:0(0) <mss 1460,sackOK,TS val 1000 ecr 0,nop,wscale 8> +0 < S 0:0(0) win 1000 <mss 1000>
+0 > S. 0:0(0) ack 1 <mss 1460,sackOK,TS val 3308134035 ecr 0,nop,wscale 8> +0 < S. 0:0(0) ack 1 win 1000

+0 write(3, ..., 100) = 100
+0 > P. 1:101(100) ack 1

--

  # packetdrill cross-synack.pkt
  cross-synack.pkt:13: runtime error in write call: Expected result 100 but got -1 with errno 11 (Resource temporarily unavailable)
  # nstat
  ...
  TcpExtTCPChallengeACK           1                  0.0
  TcpExtTCPSYNChallenge           1                  0.0

The problem is that bpf_skops_established() is triggered by the Challenge ACK instead of SYN+ACK. This causes the bpf prog to miss the chance to check if the peer supports a TCP option that is expected to be exchanged in SYN and SYN+ACK.

Let's accept a bare SYN+ACK for active-open TCP_SYN_RECV sockets to avoid such a situation.

Note that tcp_ack_snd_check() in tcp_rcv_state_process() is skipped not to send an unnecessary ACK, but this could be a bit risky for net.git, so this targets for net-next.

---
 net/ipv4/tcp_input.c | 9 +++++++++
 1 file changed, 9 insertions(+)

index 24c7c955dc95..336bc97e86d5 100644
@@ -5880,6 +5880,11 @@ static bool tcp_validate_incoming(struct sock *sk, struct sk_buff *skb,
 	 * RFC 5961 4.2 : Send a challenge ack
 	 */
 	if (th->syn) {
+		if (sk->sk_state == TCP_SYN_RECV && sk->sk_socket && th->ack &&
+		    TCP_SKB_CB(skb)->seq + 1 == TCP_SKB_CB(skb)->end_seq &&
+		    TCP_SKB_CB(skb)->seq + 1 == tp->rcv_nxt &&
+		    TCP_SKB_CB(skb)->ack_seq == tp->snd_nxt)
+			goto pass;
 syn_challenge:
 		if (syn_inerr)
 			TCP_INC_STATS(sock_net(sk), TCP_MIB_INERRS);

@@ -5889,6 +5894,7 @@ static bool tcp_validate_incoming(struct sock *sk, struct sk_buff *skb,
 		goto discard;
 	}
 
+pass:
 	bpf_skops_parse_hdr(sk, skb);
 
 	return true;

@@ -6673,6 +6679,9 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
 		tcp_fast_path_on(tp);
 		if (sk->sk_shutdown & SEND_SHUTDOWN)
 			tcp_shutdown(sk, SEND_SHUTDOWN);
+
+		if (sk->sk_socket)
+			goto consume;
 		break;
 
 	case TCP_FIN_WAIT1: {

2.43.0

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

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

From: Neeraj Sanjay Kale <[email protected]>

[ Upstream commit c68bbf5e334b35b36ac5b9f0419f1f93f796bad1 ]

This adds a check before freeing the rx->skb in flush and close functions to handle the kernel crash seen while removing driver after FW download fails or before FW download completes.

dmesg log:

[   54.634586] Unable to handle kernel NULL pointer dereference at virtual address 0000000000000080
[   54.643398] Mem abort info:
[   54.646204]   ESR = 0x0000000096000004
[   54.649964]   EC = 0x25: DABT (current EL), IL = 32 bits
[   54.655286]   SET = 0, FnV = 0
[   54.658348]   EA = 0, S1PTW = 0
[   54.661498]   FSC = 0x04: level 0 translation fault
[   54.666391] Data abort info:
[   54.669273]   ISV = 0, ISS = 0x00000004, ISS2 = 0x00000000
[   54.674768]   CM = 0, WnR = 0, TnD = 0, TagAccess = 0
[   54.674771]   GCS = 0, Overlay = 0, DirtyBit = 0, Xs = 0
[   54.674775] user pgtable: 4k pages, 48-bit VAs, pgdp=0000000048860000
[   54.674780] [0000000000000080] pgd=0000000000000000, p4d=0000000000000000
[   54.703880] Internal error: Oops: 0000000096000004 [#1] PREEMPT SMP
[   54.710152] Modules linked in: btnxpuart(-) overlay fsl_jr_uio caam_jr caamkeyblob_desc caamhash_desc caamalg_desc crypto_engine authenc libdes crct10dif_ce polyval_ce polyval_generic snd_soc_imx_spdif snd_soc_imx_card snd_soc_ak5558 snd_soc_ak4458 caam secvio error snd_soc_fsl_micfil snd_soc_fsl_spdif snd_soc_fsl_sai snd_soc_fsl_utils imx_pcm_dma gpio_ir_recv rc_core sch_fq_codel fuse
[   54.744357] CPU: 3 PID: 72 Comm: kworker/u9:0 Not tainted 6.6.3-otbr-g128004619037 #2
[   54.744364] Hardware name: FSL i.MX8MM EVK board (DT)
[   54.744368] Workqueue: hci0 hci_power_on
[   54.757244] pstate: 60000005 (nZCv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--)
[   54.757249] pc : kfree_skb_reason+0x18/0xb0
[   54.772299] lr : btnxpuart_flush+0x40/0x58 [btnxpuart]
[   54.782921] sp : ffff8000805ebca0
[   54.782923] x29: ffff8000805ebca0 x28: ffffa5c6cf1869c0 x27: ffffa5c6cf186000
[   54.782931] x26: ffff377b84852400 x25: ffff377b848523c0 x24: ffff377b845e7230
[   54.782938] x23: ffffa5c6ce8dbe08 x22: ffffa5c6ceb65410 x21: 00000000ffffff92
[   54.782945] x20: ffffa5c6ce8dbe98 x19: ffffffffffffffac x18: ffffffffffffffff
[   54.807651] x17: 0000000000000000 x16: ffffa5c6ce2824ec x15: ffff8001005eb857
[   54.821917] x14: 0000000000000000 x13: ffffa5c6cf1a02e0 x12: 0000000000000642
[   54.821924] x11: 0000000000000040 x10: ffffa5c6cf19d690 x9 : ffffa5c6cf19d688
[   54.821931] x8 : ffff377b86000028 x7 : 0000000000000000 x6 : 0000000000000000
[   54.821938] x5 : ffff377b86000000 x4 : 0000000000000000 x3 : 0000000000000000
[   54.843331] x2 : 0000000000000000 x1 : 0000000000000002 x0 : ffffffffffffffac
[   54.857599] Call trace:
[   54.857601]  kfree_skb_reason+0x18/0xb0
[   54.863878]  btnxpuart_flush+0x40/0x58 [btnxpuart]
[   54.863888]  hci_dev_open_sync+0x3a8/0xa04
[   54.872773]  hci_power_on+0x54/0x2e4
[   54.881832]  process_one_work+0x138/0x260
[   54.881842]  worker_thread+0x32c/0x438
[   54.881847]  kthread+0x118/0x11c
[   54.881853]  ret_from_fork+0x10/0x20
[   54.896406] Code: a9be7bfd 910003fd f9000bf3 aa0003f3 (b940d400)
[   54.896410] ---[ end trace 0000000000000000 ]---

---
 drivers/bluetooth/btnxpuart.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

index 814dd966b1a4..5ee9a8b8dcfd 100644
@@ -1326,8 +1326,10 @@ static int btnxpuart_close(struct hci_dev *hdev)
 
 	serdev_device_close(nxpdev->serdev);
 	skb_queue_purge(&nxpdev->txq);
-	kfree_skb(nxpdev->rx_skb);
-	nxpdev->rx_skb = NULL;
+	if (!IS_ERR_OR_NULL(nxpdev->rx_skb)) {
+		kfree_skb(nxpdev->rx_skb);
+		nxpdev->rx_skb = NULL;
+	}
 	clear_bit(BTNXPUART_SERDEV_OPEN, &nxpdev->tx_state);
 	return 0;
 }

@@ -1342,8 +1344,10 @@ static int btnxpuart_flush(struct hci_dev *hdev)
 
 	cancel_work_sync(&nxpdev->tx_work);
 
-	kfree_skb(nxpdev->rx_skb);
-	nxpdev->rx_skb = NULL;
+	if (!IS_ERR_OR_NULL(nxpdev->rx_skb)) {
+		kfree_skb(nxpdev->rx_skb);
+		nxpdev->rx_skb = NULL;
+	}
 
 	return 0;
 }

2.43.0

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

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

From: Vladimir Oltean <[email protected]>

[ Upstream commit 555a05d84ca2c587e2d4777006e2c2fb3dfbd91d ]

The dpaa-eth driver is written for PowerPC and Arm SoCs which have 1-24 CPUs. It depends on CONFIG_NR_CPUS having a reasonably small value in Kconfig. Otherwise, there are 2 functions which allocate on-stack arrays of NR_CPUS elements, and these can quickly explode in size, leading to warnings such as:

drivers/net/ethernet/freescale/dpaa/dpaa_eth.c:3280:12: warning:
stack frame size (16664) exceeds limit (2048) in 'dpaa_eth_probe' [-Wframe-larger-than]

The problem is twofold:
- Reducing the array size to the boot-time num_possible_cpus() (rather than the compile-time NR_CPUS) creates a variable-length array, which should be avoided in the Linux kernel.
- Using NR_CPUS as an array size makes the driver blow up in stack consumption with generic, as opposed to hand-crafted, .config files.

A simple solution is to use dynamic allocation for num_possible_cpus() elements (aka a small number determined at runtime).

---
 .../net/ethernet/freescale/dpaa/dpaa_eth.c    | 20 ++++++++++++++-----
 .../ethernet/freescale/dpaa/dpaa_ethtool.c    | 10 +++++++++-
 2 files changed, 24 insertions(+), 6 deletions(-)

index dcbc598b11c6..c6a3eefd83bf 100644
@@ -931,14 +931,18 @@ static inline void dpaa_setup_egress(const struct dpaa_priv *priv,
 	}
 }
 
-static void dpaa_fq_setup(struct dpaa_priv *priv,
-			  const struct dpaa_fq_cbs *fq_cbs,
-			  struct fman_port *tx_port)
+static int dpaa_fq_setup(struct dpaa_priv *priv,
+			 const struct dpaa_fq_cbs *fq_cbs,
+			 struct fman_port *tx_port)
 {
 	int egress_cnt = 0, conf_cnt = 0, num_portals = 0, portal_cnt = 0, cpu;
 	const cpumask_t *affine_cpus = qman_affine_cpus();
-	u16 channels[NR_CPUS];
 	struct dpaa_fq *fq;
+	u16 *channels;
+
+	channels = kcalloc(num_possible_cpus(), sizeof(u16), GFP_KERNEL);
+	if (!channels)
+		return -ENOMEM;
 
 	for_each_cpu_and(cpu, affine_cpus, cpu_online_mask)
 		channels[num_portals++] = qman_affine_channel(cpu);

@@ -997,6 +1001,10 @@ static void dpaa_fq_setup(struct dpaa_priv *priv,
 				break;
 		}
 	}
+
+	kfree(channels);
+
+	return 0;
 }
 
 static inline int dpaa_tx_fq_to_id(const struct dpaa_priv *priv,

@@ -3416,7 +3424,9 @@ static int dpaa_eth_probe(struct platform_device *pdev)
 	 */
 	dpaa_eth_add_channel(priv->channel, &pdev->dev);
 
-	dpaa_fq_setup(priv, &dpaa_fq_cbs, priv->mac_dev->port[TX]);
+	err = dpaa_fq_setup(priv, &dpaa_fq_cbs, priv->mac_dev->port[TX]);
+	if (err)
+		goto free_dpaa_bps;
 
 	/* Create a congestion group for this netdev, with
 	 * dynamically-allocated CGR ID.

index 5bd0b36d1feb..3f8cd4a7d845 100644
@@ -457,12 +457,16 @@ static int dpaa_set_coalesce(struct net_device *dev,
 			     struct netlink_ext_ack *extack)
 {
 	const cpumask_t *cpus = qman_affine_cpus();
-	bool needs_revert[NR_CPUS] = {false};
 	struct qman_portal *portal;
 	u32 period, prev_period;
 	u8 thresh, prev_thresh;
+	bool *needs_revert;
 	int cpu, res;
 
+	needs_revert = kcalloc(num_possible_cpus(), sizeof(bool), GFP_KERNEL);
+	if (!needs_revert)
+		return -ENOMEM;
+
 	period = c->rx_coalesce_usecs;
 	thresh = c->rx_max_coalesced_frames;
 

@@ -485,6 +489,8 @@ static int dpaa_set_coalesce(struct net_device *dev,
 		needs_revert[cpu] = true;
 	}
 
+	kfree(needs_revert);
+
 	return 0;
 
 revert_values:

@@ -498,6 +504,8 @@ static int dpaa_set_coalesce(struct net_device *dev,
 		qman_dqrr_set_ithresh(portal, prev_thresh);
 	}
 
+	kfree(needs_revert);
+
 	return res;
 }
 

2.43.0

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

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

From: Huacai Chen <[email protected]>

[ Upstream commit 0124fbb4c6dba23dbdf80c829be68adbccde2722 ]

fw_arg1 is in memory space rather than I/O space, so we should use early_memremap_ro() instead of early_ioremap() to map the cmdline. Moreover, we should unmap it after using.

---
 arch/loongarch/kernel/relocate.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

index 1acfa704c8d0..0eddd4a66b87 100644
@@ -13,6 +13,7 @@
 #include <asm/bootinfo.h>
 #include <asm/early_ioremap.h>
 #include <asm/inst.h>
+#include <asm/io.h>
 #include <asm/sections.h>
 #include <asm/setup.h>
 

@@ -170,7 +171,7 @@ unsigned long __init relocate_kernel(void)
 	unsigned long kernel_length;
 	unsigned long random_offset = 0;
 	void *location_new = _text; /* Default to original kernel start */
-	char *cmdline = early_ioremap(fw_arg1, COMMAND_LINE_SIZE); /* Boot command line is passed in fw_arg1 */
+	char *cmdline = early_memremap_ro(fw_arg1, COMMAND_LINE_SIZE); /* Boot command line is passed in fw_arg1 */
 
 	strscpy(boot_command_line, cmdline, COMMAND_LINE_SIZE);
 

@@ -182,6 +183,7 @@ unsigned long __init relocate_kernel(void)
 		random_offset = (unsigned long)location_new - (unsigned long)(_text);
 #endif
 	reloc_offset = (unsigned long)_text - VMLINUX_LOAD_ADDRESS;
+	early_memunmap(cmdline, COMMAND_LINE_SIZE);
 
 	if (random_offset) {
 		kernel_length = (long)(_end) - (long)(_text);

2.43.0

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

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

From: Arnd Bergmann <[email protected]>

[ Upstream commit 542440fd7b30983cae23e32bd22f69a076ec7ef4 ]

With gcc-14.1, there is a false-postive -Wuninitialized warning in regcache_maple_drop:

drivers/base/regmap/regcache-maple.c: In function 'regcache_maple_drop':
drivers/base/regmap/regcache-maple.c:113:23: error: 'lower_index' is used uninitialized [-Werror=uninitialized]

  113 |         unsigned long lower_index, lower_last;
      |                       ^~~~~~~~~~~

drivers/base/regmap/regcache-maple.c:113:36: error: 'lower_last' is used uninitialized [-Werror=uninitialized]
113 | unsigned long lower_index, lower_last;
| ^~~~~~~~~~

I've created a reduced test case to see if this needs to be reported as a gcc, but it appears that the gcc-14.x branch already has a change that turns this into a more sensible -Wmaybe-uninitialized warning, so I ended up not reporting it so far.

The reduced test case also produces a warning for gcc-13 and gcc-12 but I don't see that with the version in the kernel.

---
 drivers/base/regmap/regcache-maple.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

index 55999a50ccc0..0b6c2277128b 100644
@@ -110,7 +110,8 @@ static int regcache_maple_drop(struct regmap *map, unsigned int min,
 	struct maple_tree *mt = map->cache;
 	MA_STATE(mas, mt, min, max);
 	unsigned long *entry, *lower, *upper;
-	unsigned long lower_index, lower_last;
+	/* initialized to work around false-positive -Wuninitialized warning */
+	unsigned long lower_index = 0, lower_last = 0;
 	unsigned long upper_index, upper_last;
 	int ret = 0;
 

2.43.0

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

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

From: David Howells <[email protected]>

[ Upstream commit c3a5e3e872f3688ae0dc57bb78ca633921d96a91 ]

When using cachefiles, lockdep may emit something similar to the circular locking dependency notice below. The problem appears to stem from the following:

(1) Cachefiles manipulates xattrs on the files in its cache when called

     from ->writepages().

(2) The setxattr() and removexattr() system call handlers get the name (and value) from userspace after taking the sb_writers lock, putting accesses of the vma->vm_lock and mm->mmap_lock inside of that.

(3) The afs filesystem uses a per-inode lock to prevent multiple revalidation RPCs and in writeback vs truncate to prevent parallel operations from deadlocking against the server on one side and local page locks on the other.

Fix this by moving the getting of the name and value in {get,remove}xattr() outside of the sb_writers lock. This also has the minor benefits that we don't need to reget these in the event of a retry and we never try to take the sb_writers lock in the event we can't pull the name and value into the kernel.

Alternative approaches that might fix this include moving the dispatch of a write to the cache off to a workqueue or trying to do without the validation lock in afs. Note that this might also affect other filesystems that use netfslib and/or cachefiles.

======================================================
WARNING: possible circular locking dependency detected
6.10.0-build2+ #956 Not tainted
------------------------------------------------------
fsstress/6050 is trying to acquire lock:
ffff888138fd82f0 (mapping.invalidate_lock#3){++++}-{3:3}, at: filemap_fault+0x26e/0x8b0

but task is already holding lock:
ffff888113f26d18 (&vma->vm_lock->lock){++++}-{3:3}, at: lock_vma_under_rcu+0x165/0x250

which lock already depends on the new lock.

the existing dependency chain (in reverse order) is:

-> #4 (&vma->vm_lock->lock){++++}-{3:3}:

        __lock_acquire+0xaf0/0xd80
        lock_acquire.part.0+0x103/0x280
        down_write+0x3b/0x50
        vma_start_write+0x6b/0xa0
        vma_link+0xcc/0x140
        insert_vm_struct+0xb7/0xf0
        alloc_bprm+0x2c1/0x390
        kernel_execve+0x65/0x1a0
        call_usermodehelper_exec_async+0x14d/0x190
        ret_from_fork+0x24/0x40
        ret_from_fork_asm+0x1a/0x30

-> #3 (&mm->mmap_lock){++++}-{3:3}:

        __lock_acquire+0xaf0/0xd80
        lock_acquire.part.0+0x103/0x280
        __might_fault+0x7c/0xb0
        strncpy_from_user+0x25/0x160
        removexattr+0x7f/0x100
        __do_sys_fremovexattr+0x7e/0xb0
        do_syscall_64+0x9f/0x100
        entry_SYSCALL_64_after_hwframe+0x76/0x7e

-> #2 (sb_writers#14){.+.+}-{0:0}:

        __lock_acquire+0xaf0/0xd80
        lock_acquire.part.0+0x103/0x280
        percpu_down_read+0x3c/0x90
        vfs_iocb_iter_write+0xe9/0x1d0
        __cachefiles_write+0x367/0x430
        cachefiles_issue_write+0x299/0x2f0
        netfs_advance_write+0x117/0x140
        netfs_write_folio.isra.0+0x5ca/0x6e0
        netfs_writepages+0x230/0x2f0
        afs_writepages+0x4d/0x70
        do_writepages+0x1e8/0x3e0
        filemap_fdatawrite_wbc+0x84/0xa0
        __filemap_fdatawrite_range+0xa8/0xf0
        file_write_and_wait_range+0x59/0x90
        afs_release+0x10f/0x270
        __fput+0x25f/0x3d0
        __do_sys_close+0x43/0x70
        do_syscall_64+0x9f/0x100
        entry_SYSCALL_64_after_hwframe+0x76/0x7e

-> #1 (&vnode->validate_lock){++++}-{3:3}:

        __lock_acquire+0xaf0/0xd80
        lock_acquire.part.0+0x103/0x280
        down_read+0x95/0x200
        afs_writepages+0x37/0x70
        do_writepages+0x1e8/0x3e0
        filemap_fdatawrite_wbc+0x84/0xa0
        filemap_invalidate_inode+0x167/0x1e0
        netfs_unbuffered_write_iter+0x1bd/0x2d0
        vfs_write+0x22e/0x320
        ksys_write+0xbc/0x130
        do_syscall_64+0x9f/0x100
        entry_SYSCALL_64_after_hwframe+0x76/0x7e

-> #0 (mapping.invalidate_lock#3){++++}-{3:3}:

        check_noncircular+0x119/0x160
        check_prev_add+0x195/0x430
        __lock_acquire+0xaf0/0xd80
        lock_acquire.part.0+0x103/0x280
        down_read+0x95/0x200
        filemap_fault+0x26e/0x8b0
        __do_fault+0x57/0xd0
        do_pte_missing+0x23b/0x320
        __handle_mm_fault+0x2d4/0x320
        handle_mm_fault+0x14f/0x260
        do_user_addr_fault+0x2a2/0x500
        exc_page_fault+0x71/0x90
        asm_exc_page_fault+0x22/0x30

other info that might help us debug this:

 Chain exists of:
   mapping.invalidate_lock#3 --> &mm->mmap_lock --> &vma->vm_lock->lock

  Possible unsafe locking scenario:

        CPU0                    CPU1
        ----                    ----
   rlock(&vma->vm_lock->lock);
                                lock(&mm->mmap_lock);
                                lock(&vma->vm_lock->lock);

rlock(mapping.invalidate_lock#3);

*** DEADLOCK ***

1 lock held by fsstress/6050:
#0: ffff888113f26d18 (&vma->vm_lock->lock){++++}-{3:3}, at: lock_vma_under_rcu+0x165/0x250

 stack backtrace:
 CPU: 0 PID: 6050 Comm: fsstress Not tainted 6.10.0-build2+ #956
 Hardware name: ASUS All Series/H97-PLUS, BIOS 2306 10/09/2014
 Call Trace:
  <TASK>
  dump_stack_lvl+0x57/0x80
  check_noncircular+0x119/0x160
  ? queued_spin_lock_slowpath+0x4be/0x510
  ? __pfx_check_noncircular+0x10/0x10
  ? __pfx_queued_spin_lock_slowpath+0x10/0x10
  ? mark_lock+0x47/0x160
  ? init_chain_block+0x9c/0xc0
  ? add_chain_block+0x84/0xf0
  check_prev_add+0x195/0x430
  __lock_acquire+0xaf0/0xd80
  ? __pfx___lock_acquire+0x10/0x10
  ? __lock_release.isra.0+0x13b/0x230
  lock_acquire.part.0+0x103/0x280
  ? filemap_fault+0x26e/0x8b0
  ? __pfx_lock_acquire.part.0+0x10/0x10
  ? rcu_is_watching+0x34/0x60
  ? lock_acquire+0xd7/0x120
  down_read+0x95/0x200
  ? filemap_fault+0x26e/0x8b0
  ? __pfx_down_read+0x10/0x10
  ? __filemap_get_folio+0x25/0x1a0
  filemap_fault+0x26e/0x8b0
  ? __pfx_filemap_fault+0x10/0x10
  ? find_held_lock+0x7c/0x90
  ? __pfx___lock_release.isra.0+0x10/0x10
  ? __pte_offset_map+0x99/0x110
  __do_fault+0x57/0xd0
  do_pte_missing+0x23b/0x320
  __handle_mm_fault+0x2d4/0x320
  ? __pfx___handle_mm_fault+0x10/0x10
  handle_mm_fault+0x14f/0x260
  do_user_addr_fault+0x2a2/0x500
  exc_page_fault+0x71/0x90
  asm_exc_page_fault+0x22/0x30

---
 fs/xattr.c | 91 ++++++++++++++++++++++++++++--------------------------
 1 file changed, 48 insertions(+), 43 deletions(-)

index efd4736bc94b..c20046548f21 100644
@@ -631,10 +631,9 @@ int do_setxattr(struct mnt_idmap *idmap, struct dentry *dentry,
 			ctx->kvalue, ctx->size, ctx->flags);
 }
 
-static long
-setxattr(struct mnt_idmap *idmap, struct dentry *d,
-	const char __user *name, const void __user *value, size_t size,
-	int flags)
+static int path_setxattr(const char __user *pathname,
+			 const char __user *name, const void __user *value,
+			 size_t size, int flags, unsigned int lookup_flags)
 {
 	struct xattr_name kname;
 	struct xattr_ctx ctx = {

@@ -644,33 +643,20 @@ setxattr(struct mnt_idmap *idmap, struct dentry *d,
 		.kname    = &kname,
 		.flags    = flags,
 	};
+	struct path path;
 	int error;
 
 	error = setxattr_copy(name, &ctx);
 	if (error)
 		return error;
 
-	error = do_setxattr(idmap, d, &ctx);
-
-	kvfree(ctx.kvalue);
-	return error;
-}
-
-static int path_setxattr(const char __user *pathname,
-			 const char __user *name, const void __user *value,
-			 size_t size, int flags, unsigned int lookup_flags)
-{
-	struct path path;
-	int error;
-
 retry:
 	error = user_path_at(AT_FDCWD, pathname, lookup_flags, &path);
 	if (error)
-		return error;
+		goto out;
 	error = mnt_want_write(path.mnt);
 	if (!error) {
-		error = setxattr(mnt_idmap(path.mnt), path.dentry, name,
-				 value, size, flags);
+		error = do_setxattr(mnt_idmap(path.mnt), path.dentry, &ctx);
 		mnt_drop_write(path.mnt);
 	}
 	path_put(&path);

@@ -678,6 +664,9 @@ static int path_setxattr(const char __user *pathname,
 		lookup_flags |= LOOKUP_REVAL;
 		goto retry;
 	}
+
+out:
+	kvfree(ctx.kvalue);
 	return error;
 }
 

@@ -698,20 +687,32 @@ SYSCALL_DEFINE5(lsetxattr, const char __user *, pathname,
 SYSCALL_DEFINE5(fsetxattr, int, fd, const char __user *, name,
 		const void __user *,value, size_t, size, int, flags)
 {
-	struct fd f = fdget(fd);
-	int error = -EBADF;
+	struct xattr_name kname;
+	struct xattr_ctx ctx = {
+		.cvalue   = value,
+		.kvalue   = NULL,
+		.size     = size,
+		.kname    = &kname,
+		.flags    = flags,
+	};
+	int error;
 
+	CLASS(fd, f)(fd);
 	if (!f.file)
-		return error;
+		return -EBADF;
+
 	audit_file(f.file);
+	error = setxattr_copy(name, &ctx);
+	if (error)
+		return error;
+
 	error = mnt_want_write_file(f.file);
 	if (!error) {
-		error = setxattr(file_mnt_idmap(f.file),
-				 f.file->f_path.dentry, name,
-				 value, size, flags);
+		error = do_setxattr(file_mnt_idmap(f.file),
+				    f.file->f_path.dentry, &ctx);
 		mnt_drop_write_file(f.file);
 	}
-	fdput(f);
+	kvfree(ctx.kvalue);
 	return error;
 }
 

@@ -900,9 +901,17 @@ SYSCALL_DEFINE3(flistxattr, int, fd, char __user *, list, size_t, size)
  * Extended attribute REMOVE operations
  */
 static long
-removexattr(struct mnt_idmap *idmap, struct dentry *d,
-	    const char __user *name)
+removexattr(struct mnt_idmap *idmap, struct dentry *d, const char *name)
 {
+	if (is_posix_acl_xattr(name))
+		return vfs_remove_acl(idmap, d, name);
+	return vfs_removexattr(idmap, d, name);
+}
+
+static int path_removexattr(const char __user *pathname,
+			    const char __user *name, unsigned int lookup_flags)
+{
+	struct path path;
 	int error;
 	char kname[XATTR_NAME_MAX + 1];
 

@@ -911,25 +920,13 @@ removexattr(struct mnt_idmap *idmap, struct dentry *d,
 		error = -ERANGE;
 	if (error < 0)
 		return error;
-
-	if (is_posix_acl_xattr(kname))
-		return vfs_remove_acl(idmap, d, kname);
-
-	return vfs_removexattr(idmap, d, kname);
-}
-
-static int path_removexattr(const char __user *pathname,
-			    const char __user *name, unsigned int lookup_flags)
-{
-	struct path path;
-	int error;
 retry:
 	error = user_path_at(AT_FDCWD, pathname, lookup_flags, &path);
 	if (error)
 		return error;
 	error = mnt_want_write(path.mnt);
 	if (!error) {
-		error = removexattr(mnt_idmap(path.mnt), path.dentry, name);
+		error = removexattr(mnt_idmap(path.mnt), path.dentry, kname);
 		mnt_drop_write(path.mnt);
 	}
 	path_put(&path);

@@ -955,15 +952,23 @@ SYSCALL_DEFINE2(lremovexattr, const char __user *, pathname,
 SYSCALL_DEFINE2(fremovexattr, int, fd, const char __user *, name)
 {
 	struct fd f = fdget(fd);
+	char kname[XATTR_NAME_MAX + 1];
 	int error = -EBADF;
 
 	if (!f.file)
 		return error;
 	audit_file(f.file);
+
+	error = strncpy_from_user(kname, name, sizeof(kname));
+	if (error == 0 || error == sizeof(kname))
+		error = -ERANGE;
+	if (error < 0)
+		return error;
+
 	error = mnt_want_write_file(f.file);
 	if (!error) {
 		error = removexattr(file_mnt_idmap(f.file),
-				    f.file->f_path.dentry, name);
+				    f.file->f_path.dentry, kname);
 		mnt_drop_write_file(f.file);
 	}
 	fdput(f);

2.43.0

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

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

From: Frank Li <[email protected]>

[ Upstream commit 9bc7501b0b90f4d0c34b97c14ff1f708ce7ad8f3 ]

According to I3C Spec 1.1.1, 11-Jun-2021, section: 5.1.2.2.3:

If the Controller chooses to start an I3C Message with an I3C Dynamic Address, then special provisions shall be made because that same I3C Target may be initiating an IBI or a Controller Role Request. So, one of three things may happen: (skip 1, 2)

3. The Addresses match and the RnW bits also match, and so neither Controller nor Target will ACK since both are expecting the other side to provide ACK. As a result, each side might think it had "won" arbitration, but neither side would continue, as each would subsequently see that the other did not provide ACK.
...
For either value of RnW: Due to the NACK, the Controller shall defer the Private Write or Private Read, and should typically transmit the Target

						    ^^^^^^^^^^^^^^^^^^^

Address again after a Repeated START (i.e., the next one or any one prior ^^^^^^^^^^^^^
to a STOP in the Frame). Since the Address Header following a Repeated START is not arbitrated, the Controller will always win (see Section 5.1.2.2.4).

Resend target address again if address is not 7E and controller get NACK.

---
 drivers/i3c/master/svc-i3c-master.c | 58 ++++++++++++++++++++++-------
 1 file changed, 44 insertions(+), 14 deletions(-)

index ccd0c4680be2..acc937275c18 100644
@@ -1037,29 +1037,59 @@ static int svc_i3c_master_xfer(struct svc_i3c_master *master,
 			       u8 *in, const u8 *out, unsigned int xfer_len,
 			       unsigned int *actual_len, bool continued)
 {
+	int retry = 2;
 	u32 reg;
 	int ret;
 
 	/* clean SVC_I3C_MINT_IBIWON w1c bits */
 	writel(SVC_I3C_MINT_IBIWON, master->regs + SVC_I3C_MSTATUS);
 
-	writel(SVC_I3C_MCTRL_REQUEST_START_ADDR |
-	       xfer_type |
-	       SVC_I3C_MCTRL_IBIRESP_NACK |
-	       SVC_I3C_MCTRL_DIR(rnw) |
-	       SVC_I3C_MCTRL_ADDR(addr) |
-	       SVC_I3C_MCTRL_RDTERM(*actual_len),
-	       master->regs + SVC_I3C_MCTRL);
 
-	ret = readl_poll_timeout(master->regs + SVC_I3C_MSTATUS, reg,
+	while (retry--) {
+		writel(SVC_I3C_MCTRL_REQUEST_START_ADDR |
+		       xfer_type |
+		       SVC_I3C_MCTRL_IBIRESP_NACK |
+		       SVC_I3C_MCTRL_DIR(rnw) |
+		       SVC_I3C_MCTRL_ADDR(addr) |
+		       SVC_I3C_MCTRL_RDTERM(*actual_len),
+		       master->regs + SVC_I3C_MCTRL);
+
+		ret = readl_poll_timeout(master->regs + SVC_I3C_MSTATUS, reg,
 				 SVC_I3C_MSTATUS_MCTRLDONE(reg), 0, 1000);
-	if (ret)
-		goto emit_stop;
+		if (ret)
+			goto emit_stop;
 
-	if (readl(master->regs + SVC_I3C_MERRWARN) & SVC_I3C_MERRWARN_NACK) {
-		ret = -ENXIO;
-		*actual_len = 0;
-		goto emit_stop;
+		if (readl(master->regs + SVC_I3C_MERRWARN) & SVC_I3C_MERRWARN_NACK) {
+			/*
+			 * According to I3C Spec 1.1.1, 11-Jun-2021, section: 5.1.2.2.3.
+			 * If the Controller chooses to start an I3C Message with an I3C Dynamic
+			 * Address, then special provisions shall be made because that same I3C
+			 * Target may be initiating an IBI or a Controller Role Request. So, one of
+			 * three things may happen: (skip 1, 2)
+			 *
+			 * 3. The Addresses match and the RnW bits also match, and so neither
+			 * Controller nor Target will ACK since both are expecting the other side to
+			 * provide ACK. As a result, each side might think it had "won" arbitration,
+			 * but neither side would continue, as each would subsequently see that the
+			 * other did not provide ACK.
+			 * ...
+			 * For either value of RnW: Due to the NACK, the Controller shall defer the
+			 * Private Write or Private Read, and should typically transmit the Target
+			 * Address again after a Repeated START (i.e., the next one or any one prior
+			 * to a STOP in the Frame). Since the Address Header following a Repeated
+			 * START is not arbitrated, the Controller will always win (see Section
+			 * 5.1.2.2.4).
+			 */
+			if (retry && addr != 0x7e) {
+				writel(SVC_I3C_MERRWARN_NACK, master->regs + SVC_I3C_MERRWARN);
+			} else {
+				ret = -ENXIO;
+				*actual_len = 0;
+				goto emit_stop;
+			}
+		} else {
+			break;
+		}
 	}
 
 	/*

2.43.0

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

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

From: Jarkko Nikula <[email protected]>

[ Upstream commit 8a2be2f1db268ec735419e53ef04ca039fc027dc ]

Definitely condition dma_get_cache_alignment * defined value > 256 during driver initialization is not reason to BUG_ON(). Turn that to graceful error out with -EINVAL.

---
 drivers/i3c/master/mipi-i3c-hci/dma.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

index 337c95d43f3f..edc3a69bfe31 100644
@@ -291,7 +291,10 @@ static int hci_dma_init(struct i3c_hci *hci)
 
 		rh->ibi_chunk_sz = dma_get_cache_alignment();
 		rh->ibi_chunk_sz *= IBI_CHUNK_CACHELINES;
-		BUG_ON(rh->ibi_chunk_sz > 256);
+		if (rh->ibi_chunk_sz > 256) {
+			ret = -EINVAL;
+			goto err_out;
+		}
 
 		ibi_status_ring_sz = rh->ibi_status_sz * rh->ibi_status_entries;
 		ibi_data_ring_sz = rh->ibi_chunk_sz * rh->ibi_chunks_total;

2.43.0

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

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

From: Zenghui Yu <[email protected]>

[ Upstream commit 291e4baf70019f17a81b7b47aeb186b27d222159 ]

Even if a vgem device is configured in, we will skip the import_vgem_fd() test almost every time.

TAP version 13
1..11
# Testing heap: system
# =======================================
# Testing allocation and importing:
ok 1 # SKIP Could not open vgem -1

The problem is that we use the DRM_IOCTL_VERSION ioctl to query the driver version information but leave the name field a non-null-terminated string. Terminate it properly to actually test against the vgem device.

While at it, let's check the length of the driver name is exactly 4 bytes and return early otherwise (in case there is a name like "vgemfoo" that gets converted to "vgem\0" unexpectedly).

---
 tools/testing/selftests/dmabuf-heaps/dmabuf-heap.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

index 890a8236a8ba..2809f9a25c43 100644
@@ -28,9 +28,11 @@ static int check_vgem(int fd)
 	version.name = name;
 
 	ret = ioctl(fd, DRM_IOCTL_VERSION, &version);
-	if (ret)
+	if (ret || version.name_len != 4)
 		return 0;
 
+	name[4] = '\0';
+
 	return !strcmp(name, "vgem");
 }
 

2.43.0

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

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

From: Devyn Liu <[email protected]>

[ Upstream commit 5127c42c77de18651aa9e8e0a3ced190103b449c ]

If the value of max_speed_hz is 0, it may cause a division by zero error in hisi_calc_effective_speed().
The value of max_speed_hz is provided by firmware.
Firmware is generally considered as a trusted domain. However, as division by zero errors can cause system failure, for defense measure, the value of max_speed is validated here. So 0 is regarded as invalid and an error code is returned.

---
 drivers/spi/spi-hisi-kunpeng.c | 3 +++
 1 file changed, 3 insertions(+)

index 6910b4d4c427..16054695bdb0 100644
@@ -481,6 +481,9 @@ static int hisi_spi_probe(struct platform_device *pdev)
 		return -EINVAL;
 	}
 
+	if (host->max_speed_hz == 0)
+		return dev_err_probe(dev, -EINVAL, "spi-max-frequency can't be 0\n");
+
 	ret = device_property_read_u16(dev, "num-cs",
 					&host->num_chipselect);
 	if (ret)

2.43.0

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

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

From: David Sterba <[email protected]>

[ Upstream commit b8e947e9f64cac9df85a07672b658df5b2bcff07 ]

Some arch + compiler combinations report a potentially unused variable location in btrfs_lookup_dentry(). This is a false alert as the variable is passed by value and always valid or there's an error. The compilers cannot probably reason about that although btrfs_inode_by_name() is in the same file.

+uninitialized in this function [-Werror=maybe-uninitialized]: => 5603:9

+uninitialized in this function [-Werror=maybe-uninitialized]: => 5674:5

m68k-gcc8/m68k-allmodconfig
mips-gcc8/mips-allmodconfig
powerpc-gcc5/powerpc-all{mod,yes}config
powerpc-gcc5/ppc64_defconfig

Initialize it to zero, this should fix the warnings and won't change the behaviour as btrfs_inode_by_name() accepts only a root or inode item types, otherwise returns an error.

---
 fs/btrfs/inode.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index 18ce5353092d..a42238211887 100644
@@ -5668,7 +5668,7 @@ struct inode *btrfs_lookup_dentry(struct inode *dir, struct dentry *dentry)
 	struct inode *inode;
 	struct btrfs_root *root = BTRFS_I(dir)->root;
 	struct btrfs_root *sub_root = root;
-	struct btrfs_key location;
+	struct btrfs_key location = { 0 };
 	u8 di_type = 0;
 	int ret = 0;
 

2.43.0

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

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

From: Heiko Carstens <[email protected]>

[ Upstream commit 75c10d5377d8821efafed32e4d72068d9c1f8ec0 ]

The .data.rel.ro and .got section were added between the rodata and ro_after_init data section, which adds an RW mapping in between all RO mapping of the kernel image:

---[ Kernel Image Start ]---
0x000003ffe0000000-0x000003ffe0e00000 14M PMD RO X
0x000003ffe0e00000-0x000003ffe0ec7000 796K PTE RO X
0x000003ffe0ec7000-0x000003ffe0f00000 228K PTE RO NX
0x000003ffe0f00000-0x000003ffe1300000 4M PMD RO NX

0x000003ffe1300000-0x000003ffe1331000       196K PTE RO NX
0x000003ffe1331000-0x000003ffe13b3000       520K PTE RW NX <---
0x000003ffe13b3000-0x000003ffe13d5000       136K PTE RO NX
0x000003ffe13d5000-0x000003ffe1400000       172K PTE RW NX
0x000003ffe1400000-0x000003ffe1500000         1M PMD RW NX
0x000003ffe1500000-0x000003ffe1700000         2M PTE RW NX
0x000003ffe1700000-0x000003ffe1800000         1M PMD RW NX

0x000003ffe1800000-0x000003ffe187e000 504K PTE RW NX
---[ Kernel Image End ]---

Move the ro_after_init data section again right behind the rodata section to prevent interleaving RO and RW mappings:

---[ Kernel Image Start ]---
0x000003ffe0000000-0x000003ffe0e00000 14M PMD RO X
0x000003ffe0e00000-0x000003ffe0ec7000 796K PTE RO X
0x000003ffe0ec7000-0x000003ffe0f00000 228K PTE RO NX
0x000003ffe0f00000-0x000003ffe1300000 4M PMD RO NX
0x000003ffe1300000-0x000003ffe1353000 332K PTE RO NX
0x000003ffe1353000-0x000003ffe1400000 692K PTE RW NX

0x000003ffe1400000-0x000003ffe1500000         1M PMD RW NX
0x000003ffe1500000-0x000003ffe1700000         2M PTE RW NX
0x000003ffe1700000-0x000003ffe1800000         1M PMD RW NX

0x000003ffe1800000-0x000003ffe187e000 504K PTE RW NX
---[ Kernel Image End ]---

---
 arch/s390/kernel/vmlinux.lds.S | 9 +++++++++
 1 file changed, 9 insertions(+)

index 2ae201ebf90b..de5f9f623f5b 100644
@@ -71,6 +71,15 @@ SECTIONS
 	. = ALIGN(PAGE_SIZE);
 	__end_ro_after_init = .;
 
+	.data.rel.ro : {
+		*(.data.rel.ro .data.rel.ro.*)
+	}
+	.got : {
+		__got_start = .;
+		*(.got)
+		__got_end = .;
+	}
+
 	RW_DATA(0x100, PAGE_SIZE, THREAD_SIZE)
 	BOOT_DATA_PRESERVED
 

2.43.0

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

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

From: Camila Alvarez <[email protected]>

[ Upstream commit a6e9c391d45b5865b61e569146304cff72821a5d ]

report_fixup for the Cougar 500k Gaming Keyboard was not verifying that the report descriptor size was correct before accessing it

---
 drivers/hid/hid-cougar.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index cb8bd8aae15b..0fa785f52707 100644
@@ -106,7 +106,7 @@ static void cougar_fix_g6_mapping(void)
 static __u8 *cougar_report_fixup(struct hid_device *hdev, __u8 *rdesc,
 				 unsigned int *rsize)
 {
-	if (rdesc[2] == 0x09 && rdesc[3] == 0x02 &&
+	if (*rsize >= 117 && rdesc[2] == 0x09 && rdesc[3] == 0x02 &&
 	    (rdesc[115] | rdesc[116] << 8) >= HID_MAX_USAGES) {
 		hid_info(hdev,
 			"usage count exceeds max: fixing up report descriptor\n");

2.43.0

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

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

From: Olivier Sobrie <[email protected]>

[ Upstream commit 97155021ae17b86985121b33cf8098bcde00d497 ]

HID driver callbacks aren't called anymore once hid_destroy_device() has been called. Hence, hid driver_data should be freed only after the hid_destroy_device() function returned as driver_data is used in several callbacks.

I observed a crash with kernel 6.10.0 on my T14s Gen 3, after enabling KASAN to debug memory allocation, I got this output:

  [   13.050438] ==================================================================
  [   13.054060] BUG: KASAN: slab-use-after-free in amd_sfh_get_report+0x3ec/0x530 [amd_sfh]
  [   13.054809] psmouse serio1: trackpoint: Synaptics TrackPoint firmware: 0x02, buttons: 3/3
  [   13.056432] Read of size 8 at addr ffff88813152f408 by task (udev-worker)/479

  [   13.060970] CPU: 5 PID: 479 Comm: (udev-worker) Not tainted 6.10.0-arch1-2 #1 893bb55d7f0073f25c46adbb49eb3785fefd74b0
  [   13.063978] Hardware name: LENOVO 21CQCTO1WW/21CQCTO1WW, BIOS R22ET70W (1.40 ) 03/21/2024
  [   13.067860] Call Trace:
  [   13.069383] input: TPPS/2 Synaptics TrackPoint as /devices/platform/i8042/serio1/input/input8
  [   13.071486]  <TASK>
  [   13.071492]  dump_stack_lvl+0x5d/0x80
  [   13.074870] snd_hda_intel 0000:33:00.6: enabling device (0000 -> 0002)
  [   13.078296]  ? amd_sfh_get_report+0x3ec/0x530 [amd_sfh 05f43221435b5205f734cd9da29399130f398a38]
  [   13.082199]  print_report+0x174/0x505
  [   13.085776]  ? __pfx__raw_spin_lock_irqsave+0x10/0x10
  [   13.089367]  ? srso_alias_return_thunk+0x5/0xfbef5
  [   13.093255]  ? amd_sfh_get_report+0x3ec/0x530 [amd_sfh 05f43221435b5205f734cd9da29399130f398a38]
  [   13.097464]  kasan_report+0xc8/0x150
  [   13.101461]  ? amd_sfh_get_report+0x3ec/0x530 [amd_sfh 05f43221435b5205f734cd9da29399130f398a38]
  [   13.105802]  amd_sfh_get_report+0x3ec/0x530 [amd_sfh 05f43221435b5205f734cd9da29399130f398a38]
  [   13.110303]  amdtp_hid_request+0xb8/0x110 [amd_sfh 05f43221435b5205f734cd9da29399130f398a38]
  [   13.114879]  ? srso_alias_return_thunk+0x5/0xfbef5
  [   13.119450]  sensor_hub_get_feature+0x1d3/0x540 [hid_sensor_hub 3f13be3016ff415bea03008d45d99da837ee3082]
  [   13.124097]  hid_sensor_parse_common_attributes+0x4d0/0xad0 [hid_sensor_iio_common c3a5cbe93969c28b122609768bbe23efe52eb8f5]
  [   13.127404]  ? srso_alias_return_thunk+0x5/0xfbef5
  [   13.131925]  ? __pfx_hid_sensor_parse_common_attributes+0x10/0x10 [hid_sensor_iio_common c3a5cbe93969c28b122609768bbe23efe52eb8f5]
  [   13.136455]  ? _raw_spin_lock_irqsave+0x96/0xf0
  [   13.140197]  ? __pfx__raw_spin_lock_irqsave+0x10/0x10
  [   13.143602]  ? devm_iio_device_alloc+0x34/0x50 [industrialio 3d261d5e5765625d2b052be40e526d62b1d2123b]
  [   13.147234]  ? srso_alias_return_thunk+0x5/0xfbef5
  [   13.150446]  ? __devm_add_action+0x167/0x1d0
  [   13.155061]  hid_gyro_3d_probe+0x120/0x7f0 [hid_sensor_gyro_3d 63da36a143b775846ab2dbb86c343b401b5e3172]
  [   13.158581]  ? srso_alias_return_thunk+0x5/0xfbef5
  [   13.161814]  platform_probe+0xa2/0x150
  [   13.165029]  really_probe+0x1e3/0x8a0
  [   13.168243]  __driver_probe_device+0x18c/0x370
  [   13.171500]  driver_probe_device+0x4a/0x120
  [   13.175000]  __driver_attach+0x190/0x4a0
  [   13.178521]  ? __pfx___driver_attach+0x10/0x10
  [   13.181771]  bus_for_each_dev+0x106/0x180
  [   13.185033]  ? __pfx__raw_spin_lock+0x10/0x10
  [   13.188229]  ? __pfx_bus_for_each_dev+0x10/0x10
  [   13.191446]  ? srso_alias_return_thunk+0x5/0xfbef5
  [   13.194382]  bus_add_driver+0x29e/0x4d0
  [   13.197328]  driver_register+0x1a5/0x360
  [   13.200283]  ? __pfx_hid_gyro_3d_platform_driver_init+0x10/0x10 [hid_sensor_gyro_3d 63da36a143b775846ab2dbb86c343b401b5e3172]
  [   13.203362]  do_one_initcall+0xa7/0x380
  [   13.206432]  ? __pfx_do_one_initcall+0x10/0x10
  [   13.210175]  ? srso_alias_return_thunk+0x5/0xfbef5
  [   13.213211]  ? kasan_unpoison+0x44/0x70
  [   13.216688]  do_init_module+0x238/0x750
  [   13.219696]  load_module+0x5011/0x6af0
  [   13.223096]  ? kasan_save_stack+0x30/0x50
  [   13.226743]  ? kasan_save_track+0x14/0x30
  [   13.230080]  ? kasan_save_free_info+0x3b/0x60
  [   13.233323]  ? poison_slab_object+0x109/0x180
  [   13.236778]  ? __pfx_load_module+0x10/0x10
  [   13.239703]  ? poison_slab_object+0x109/0x180
  [   13.243070]  ? srso_alias_return_thunk+0x5/0xfbef5
  [   13.245924]  ? init_module_from_file+0x13d/0x150
  [   13.248745]  ? srso_alias_return_thunk+0x5/0xfbef5
  [   13.251503]  ? init_module_from_file+0xdf/0x150
  [   13.254198]  init_module_from_file+0xdf/0x150
  [   13.256826]  ? __pfx_init_module_from_file+0x10/0x10
  [   13.259428]  ? kasan_save_track+0x14/0x30
  [   13.261959]  ? srso_alias_return_thunk+0x5/0xfbef5
  [   13.264471]  ? kasan_save_free_info+0x3b/0x60
  [   13.267026]  ? poison_slab_object+0x109/0x180
  [   13.269494]  ? srso_alias_return_thunk+0x5/0xfbef5
  [   13.271949]  ? srso_alias_return_thunk+0x5/0xfbef5
  [   13.274324]  ? _raw_spin_lock+0x85/0xe0
  [   13.276671]  ? __pfx__raw_spin_lock+0x10/0x10
  [   13.278963]  ? __rseq_handle_notify_resume+0x1a6/0xad0
  [   13.281193]  idempotent_init_module+0x23b/0x650
  [   13.283420]  ? __pfx_idempotent_init_module+0x10/0x10
  [   13.285619]  ? __pfx___seccomp_filter+0x10/0x10
  [   13.287714]  ? srso_alias_return_thunk+0x5/0xfbef5
  [   13.289828]  ? __fget_light+0x57/0x420
  [   13.291870]  ? srso_alias_return_thunk+0x5/0xfbef5
  [   13.293880]  ? security_capable+0x74/0xb0
  [   13.295820]  __x64_sys_finit_module+0xbe/0x130
  [   13.297874]  do_syscall_64+0x82/0x190
  [   13.299898]  ? srso_alias_return_thunk+0x5/0xfbef5
  [   13.301905]  ? irqtime_account_irq+0x3d/0x1f0
  [   13.303877]  ? srso_alias_return_thunk+0x5/0xfbef5
  [   13.305753]  ? __irq_exit_rcu+0x4e/0x130
  [   13.307577]  ? srso_alias_return_thunk+0x5/0xfbef5
  [   13.309489]  entry_SYSCALL_64_after_hwframe+0x76/0x7e
  [   13.311371] RIP: 0033:0x7a21f96ade9d
  [   13.313234] Code: ff c3 66 2e 0f 1f 84 00 00 00 00 00 90 f3 0f 1e fa 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d 63 de 0c 00 f7 d8 64 89 01 48
  [   13.317051] RSP: 002b:00007ffeae934e78 EFLAGS: 00000246 ORIG_RAX: 0000000000000139
  [   13.319024] RAX: ffffffffffffffda RBX: 00005987276bfcf0 RCX: 00007a21f96ade9d
  [   13.321100] RDX: 0000000000000004 RSI: 00007a21f8eda376 RDI: 000000000000001c
  [   13.323314] RBP: 00007a21f8eda376 R08: 0000000000000001 R09: 00007ffeae934ec0
  [   13.325505] R10: 0000000000000050 R11: 0000000000000246 R12: 0000000000020000
  [   13.327637] R13: 00005987276c1250 R14: 0000000000000000 R15: 00005987276c4530
  [   13.329737]  </TASK>

  [   13.333945] Allocated by task 139:
  [   13.336111]  kasan_save_stack+0x30/0x50
  [   13.336121]  kasan_save_track+0x14/0x30
  [   13.336125]  __kasan_kmalloc+0xaa/0xb0
  [   13.336129]  amdtp_hid_probe+0xb1/0x440 [amd_sfh]
  [   13.336138]  amd_sfh_hid_client_init+0xb8a/0x10f0 [amd_sfh]
  [   13.336144]  sfh_init_work+0x47/0x120 [amd_sfh]
  [   13.336150]  process_one_work+0x673/0xeb0
  [   13.336155]  worker_thread+0x795/0x1250
  [   13.336160]  kthread+0x290/0x350
  [   13.336164]  ret_from_fork+0x34/0x70
  [   13.336169]  ret_from_fork_asm+0x1a/0x30

  [   13.338175] Freed by task 139:
  [   13.340064]  kasan_save_stack+0x30/0x50
  [   13.340072]  kasan_save_track+0x14/0x30
  [   13.340076]  kasan_save_free_info+0x3b/0x60
  [   13.340081]  poison_slab_object+0x109/0x180
  [   13.340085]  __kasan_slab_free+0x32/0x50
  [   13.340089]  kfree+0xe5/0x310
  [   13.340094]  amdtp_hid_remove+0xb2/0x160 [amd_sfh]
  [   13.340102]  amd_sfh_hid_client_deinit+0x324/0x640 [amd_sfh]
  [   13.340107]  amd_sfh_hid_client_init+0x94a/0x10f0 [amd_sfh]
  [   13.340113]  sfh_init_work+0x47/0x120 [amd_sfh]
  [   13.340118]  process_one_work+0x673/0xeb0
  [   13.340123]  worker_thread+0x795/0x1250
  [   13.340127]  kthread+0x290/0x350
  [   13.340132]  ret_from_fork+0x34/0x70
  [   13.340136]  ret_from_fork_asm+0x1a/0x30

  [   13.342482] The buggy address belongs to the object at ffff88813152f400
                  which belongs to the cache kmalloc-64 of size 64
  [   13.347357] The buggy address is located 8 bytes inside of
                  freed 64-byte region [ffff88813152f400, ffff88813152f440)

  [   13.347367] The buggy address belongs to the physical page:
  [   13.355409] page: refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x13152f
  [   13.355416] anon flags: 0x2ffff8000000000(node=0|zone=2|lastcpupid=0x1ffff)
  [   13.355423] page_type: 0xffffefff(slab)
  [   13.355429] raw: 02ffff8000000000 ffff8881000428c0 ffffea0004c43a00 0000000000000005
  [   13.355435] raw: 0000000000000000 0000000000200020 00000001ffffefff 0000000000000000
  [   13.355439] page dumped because: kasan: bad access detected

  [   13.357295] Memory state around the buggy address:
  [   13.357299]  ffff88813152f300: fa fb fb fb fb fb fb fb fc fc fc fc fc fc fc fc
  [   13.357303]  ffff88813152f380: fa fb fb fb fb fb fb fb fc fc fc fc fc fc fc fc
  [   13.357306] >ffff88813152f400: fa fb fb fb fb fb fb fb fc fc fc fc fc fc fc fc
  [   13.357309]                       ^
  [   13.357311]  ffff88813152f480: 00 00 00 00 00 fc fc fc fc fc fc fc fc fc fc fc
  [   13.357315]  ffff88813152f500: 00 00 00 00 00 00 00 06 fc fc fc fc fc fc fc fc
  [   13.357318] ==================================================================
  [   13.357405] Disabling lock debugging due to kernel taint
  [   13.383534] Oops: general protection fault, probably for non-canonical address 0xe0a1bc4140000013: 0000 [#1] PREEMPT SMP KASAN NOPTI
  [   13.383544] KASAN: maybe wild-memory-access in range [0x050e020a00000098-0x050e020a0000009f]
  [   13.383551] CPU: 3 PID: 479 Comm: (udev-worker) Tainted: G    B              6.10.0-arch1-2 #1 893bb55d7f0073f25c46adbb49eb3785fefd74b0
  [   13.383561] Hardware name: LENOVO 21CQCTO1WW/21CQCTO1WW, BIOS R22ET70W (1.40 ) 03/21/2024
  [   13.383565] RIP: 0010:amd_sfh_get_report+0x81/0x530 [amd_sfh]
  [   13.383580] Code: 89 fa 48 c1 ea 03 80 3c 02 00 0f 85 78 03 00 00 48 b8 00 00 00 00 00 fc ff df 4c 8b 63 08 49 8d 7c 24 10 48 89 fa 48 c1 ea 03 <0f> b6 04 02 84 c0 74 08 3c 03 0f 8e 1a 03 00 00 45 8b 74 24 10 45
  [   13.383585] RSP: 0018:ffff8881261f7388 EFLAGS: 00010212
  [   13.383592] RAX: dffffc0000000000 RBX: ffff88813152f400 RCX: 0000000000000002
  [   13.383597] RDX: 00a1c04140000013 RSI: 0000000000000008 RDI: 050e020a0000009b
  [   13.383600] RBP: ffff88814d010000 R08: 0000000000000002 R09: fffffbfff3ddb8c0
  [   13.383604] R10: ffffffff9eedc607 R11: ffff88810ce98000 R12: 050e020a0000008b
  [   13.383607] R13: ffff88814d010000 R14: dffffc0000000000 R15: 0000000000000004
  [   13.383611] FS:  00007a21f94d0880(0000) GS:ffff8887e7d80000(0000) knlGS:0000000000000000
  [   13.383615] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
  [   13.383618] CR2: 00007e0014c438f0 CR3: 000000012614c000 CR4: 0000000000f50ef0
  [   13.383622] PKRU: 55555554
  [   13.383625] Call Trace:
  [   13.383629]  <TASK>
  [   13.383632]  ? __die_body.cold+0x19/0x27
  [   13.383644]  ? die_addr+0x46/0x70
  [   13.383652]  ? exc_general_protection+0x150/0x240
  [   13.383664]  ? asm_exc_general_protection+0x26/0x30
  [   13.383674]  ? amd_sfh_get_report+0x81/0x530 [amd_sfh 05f43221435b5205f734cd9da29399130f398a38]
  [   13.383686]  ? amd_sfh_get_report+0x3ec/0x530 [amd_sfh 05f43221435b5205f734cd9da29399130f398a38]
  [   13.383697]  amdtp_hid_request+0xb8/0x110 [amd_sfh 05f43221435b5205f734cd9da29399130f398a38]
  [   13.383706]  ? srso_alias_return_thunk+0x5/0xfbef5
  [   13.383713]  sensor_hub_get_feature+0x1d3/0x540 [hid_sensor_hub 3f13be3016ff415bea03008d45d99da837ee3082]
  [   13.383727]  hid_sensor_parse_common_attributes+0x4d0/0xad0 [hid_sensor_iio_common c3a5cbe93969c28b122609768bbe23efe52eb8f5]
  [   13.383739]  ? srso_alias_return_thunk+0x5/0xfbef5
  [   13.383745]  ? __pfx_hid_sensor_parse_common_attributes+0x10/0x10 [hid_sensor_iio_common c3a5cbe93969c28b122609768bbe23efe52eb8f5]
  [   13.383753]  ? _raw_spin_lock_irqsave+0x96/0xf0
  [   13.383762]  ? __pfx__raw_spin_lock_irqsave+0x10/0x10
  [   13.383768]  ? devm_iio_device_alloc+0x34/0x50 [industrialio 3d261d5e5765625d2b052be40e526d62b1d2123b]
  [   13.383790]  ? srso_alias_return_thunk+0x5/0xfbef5
  [   13.383795]  ? __devm_add_action+0x167/0x1d0
  [   13.383806]  hid_gyro_3d_probe+0x120/0x7f0 [hid_sensor_gyro_3d 63da36a143b775846ab2dbb86c343b401b5e3172]
  [   13.383818]  ? srso_alias_return_thunk+0x5/0xfbef5
  [   13.383826]  platform_probe+0xa2/0x150
  [   13.383832]  really_probe+0x1e3/0x8a0
  [   13.383838]  __driver_probe_device+0x18c/0x370
  [   13.383844]  driver_probe_device+0x4a/0x120
  [   13.383851]  __driver_attach+0x190/0x4a0
  [   13.383857]  ? __pfx___driver_attach+0x10/0x10
  [   13.383863]  bus_for_each_dev+0x106/0x180
  [   13.383868]  ? __pfx__raw_spin_lock+0x10/0x10
  [   13.383874]  ? __pfx_bus_for_each_dev+0x10/0x10
  [   13.383880]  ? srso_alias_return_thunk+0x5/0xfbef5
  [   13.383887]  bus_add_driver+0x29e/0x4d0
  [   13.383895]  driver_register+0x1a5/0x360
  [   13.383902]  ? __pfx_hid_gyro_3d_platform_driver_init+0x10/0x10 [hid_sensor_gyro_3d 63da36a143b775846ab2dbb86c343b401b5e3172]
  [   13.383910]  do_one_initcall+0xa7/0x380
  [   13.383919]  ? __pfx_do_one_initcall+0x10/0x10
  [   13.383927]  ? srso_alias_return_thunk+0x5/0xfbef5
  [   13.383933]  ? kasan_unpoison+0x44/0x70
  [   13.383943]  do_init_module+0x238/0x750
  [   13.383955]  load_module+0x5011/0x6af0
  [   13.383962]  ? kasan_save_stack+0x30/0x50
  [   13.383968]  ? kasan_save_track+0x14/0x30
  [   13.383973]  ? kasan_save_free_info+0x3b/0x60
  [   13.383980]  ? poison_slab_object+0x109/0x180
  [   13.383993]  ? __pfx_load_module+0x10/0x10
  [   13.384007]  ? poison_slab_object+0x109/0x180
  [   13.384012]  ? srso_alias_return_thunk+0x5/0xfbef5
  [   13.384018]  ? init_module_from_file+0x13d/0x150
  [   13.384025]  ? srso_alias_return_thunk+0x5/0xfbef5
  [   13.384032]  ? init_module_from_file+0xdf/0x150
  [   13.384037]  init_module_from_file+0xdf/0x150
  [   13.384044]  ? __pfx_init_module_from_file+0x10/0x10
  [   13.384050]  ? kasan_save_track+0x14/0x30
  [   13.384055]  ? srso_alias_return_thunk+0x5/0xfbef5
  [   13.384060]  ? kasan_save_free_info+0x3b/0x60
  [   13.384066]  ? poison_slab_object+0x109/0x180
  [   13.384071]  ? srso_alias_return_thunk+0x5/0xfbef5
  [   13.384080]  ? srso_alias_return_thunk+0x5/0xfbef5
  [   13.384085]  ? _raw_spin_lock+0x85/0xe0
  [   13.384091]  ? __pfx__raw_spin_lock+0x10/0x10
  [   13.384096]  ? __rseq_handle_notify_resume+0x1a6/0xad0
  [   13.384106]  idempotent_init_module+0x23b/0x650
  [   13.384114]  ? __pfx_idempotent_init_module+0x10/0x10
  [   13.384120]  ? __pfx___seccomp_filter+0x10/0x10
  [   13.384129]  ? srso_alias_return_thunk+0x5/0xfbef5
  [   13.384135]  ? __fget_light+0x57/0x420
  [   13.384142]  ? srso_alias_return_thunk+0x5/0xfbef5
  [   13.384147]  ? security_capable+0x74/0xb0
  [   13.384157]  __x64_sys_finit_module+0xbe/0x130
  [   13.384164]  do_syscall_64+0x82/0x190
  [   13.384174]  ? srso_alias_return_thunk+0x5/0xfbef5
  [   13.384179]  ? irqtime_account_irq+0x3d/0x1f0
  [   13.384188]  ? srso_alias_return_thunk+0x5/0xfbef5
  [   13.384193]  ? __irq_exit_rcu+0x4e/0x130
  [   13.384201]  ? srso_alias_return_thunk+0x5/0xfbef5
  [   13.384206]  entry_SYSCALL_64_after_hwframe+0x76/0x7e
  [   13.384212] RIP: 0033:0x7a21f96ade9d
  [   13.384263] Code: ff c3 66 2e 0f 1f 84 00 00 00 00 00 90 f3 0f 1e fa 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d 63 de 0c 00 f7 d8 64 89 01 48
  [   13.384267] RSP: 002b:00007ffeae934e78 EFLAGS: 00000246 ORIG_RAX: 0000000000000139
  [   13.384273] RAX: ffffffffffffffda RBX: 00005987276bfcf0 RCX: 00007a21f96ade9d
  [   13.384277] RDX: 0000000000000004 RSI: 00007a21f8eda376 RDI: 000000000000001c
  [   13.384280] RBP: 00007a21f8eda376 R08: 0000000000000001 R09: 00007ffeae934ec0
  [   13.384284] R10: 0000000000000050 R11: 0000000000000246 R12: 0000000000020000
  [   13.384288] R13: 00005987276c1250 R14: 0000000000000000 R15: 00005987276c4530
  [   13.384297]  </TASK>
  [   13.384299] Modules linked in: soundwire_amd(+) hid_sensor_gyro_3d(+) hid_sensor_magn_3d hid_sensor_accel_3d soundwire_generic_allocation amdxcp hid_sensor_trigger drm_exec industrialio_triggered_buffer soundwire_bus gpu_sched kvm_amd kfifo_buf qmi_helpers joydev drm_buddy hid_sensor_iio_common mousedev snd_soc_core industrialio i2c_algo_bit mac80211 snd_compress drm_suballoc_helper kvm snd_hda_intel drm_ttm_helper ac97_bus snd_pcm_dmaengine snd_intel_dspcfg ttm thinkpad_acpi(+) snd_intel_sdw_acpi hid_sensor_hub snd_rpl_pci_acp6x drm_display_helper snd_hda_codec hid_multitouch libarc4 snd_acp_pci platform_profile think_lmi(+) hid_generic firmware_attributes_class wmi_bmof cec snd_acp_legacy_common sparse_keymap rapl snd_hda_core psmouse cfg80211 pcspkr snd_pci_acp6x snd_hwdep video snd_pcm snd_pci_acp5x snd_timer snd_rn_pci_acp3x ucsi_acpi snd_acp_config snd sp5100_tco rfkill snd_soc_acpi typec_ucsi thunderbolt amd_sfh k10temp mhi soundcore i2c_piix4 snd_pci_acp3x typec i2c_hid_acpi roles i2c_hid wmi acpi_tad amd_pmc
  [   13.384454]  mac_hid i2c_dev crypto_user loop nfnetlink zram ip_tables x_tables dm_crypt cbc encrypted_keys trusted asn1_encoder tee dm_mod crct10dif_pclmul crc32_pclmul polyval_clmulni polyval_generic gf128mul ghash_clmulni_intel serio_raw sha512_ssse3 atkbd sha256_ssse3 libps2 sha1_ssse3 vivaldi_fmap nvme aesni_intel crypto_simd nvme_core cryptd ccp xhci_pci i8042 nvme_auth xhci_pci_renesas serio vfat fat btrfs blake2b_generic libcrc32c crc32c_generic crc32c_intel xor raid6_pq
  [   13.384552] ---[ end trace 0000000000000000 ]---

KASAN reports a use-after-free of hid->driver_data in function amd_sfh_get_report(). The backtrace indicates that the function is called by amdtp_hid_request() which is one of the callbacks of hid device. The current make sure that driver_data is freed only once hid_destroy_device() returned.

Note that I observed the crash both on v6.9.9 and v6.10.0. The code seems to be as it was from the early days of the driver.

---
 drivers/hid/amd-sfh-hid/amd_sfh_hid.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

index 705b52337068..81f3024b7b1b 100644
@@ -171,11 +171,13 @@ int amdtp_hid_probe(u32 cur_hid_dev, struct amdtp_cl_data *cli_data)
 void amdtp_hid_remove(struct amdtp_cl_data *cli_data)
 {
 	int i;
+	struct amdtp_hid_data *hid_data;
 
 	for (i = 0; i < cli_data->num_hid_devices; ++i) {
 		if (cli_data->hid_sensor_hubs[i]) {
-			kfree(cli_data->hid_sensor_hubs[i]->driver_data);
+			hid_data = cli_data->hid_sensor_hubs[i]->driver_data;
 			hid_destroy_device(cli_data->hid_sensor_hubs[i]);
+			kfree(hid_data);
 			cli_data->hid_sensor_hubs[i] = NULL;
 		}
 	}

2.43.0

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

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

From: Dmitry Torokhov <[email protected]>

[ Upstream commit 206f533a0a7c683982af473079c4111f4a0f9f5e ]

From: Dmitry Torokhov <[email protected]>

When exercising uinput interface syzkaller may try setting up device with a really large number of slots, which causes memory allocation failure in input_mt_init_slots(). While this allocation failure is handled properly and request is rejected, it results in syzkaller reports. Additionally, such request may put undue burden on the system which will try to free a lot of memory for a bogus request.

Fix it by limiting allowed number of slots to 100. This can easily be extended if we see devices that can track more than 100 contacts.

---
 drivers/input/misc/uinput.c | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

index d98212d55108..2c973f15cab7 100644
@@ -417,6 +417,20 @@ static int uinput_validate_absinfo(struct input_dev *dev, unsigned int code,
 		return -EINVAL;
 	}
 
+	/*
+	 * Limit number of contacts to a reasonable value (100). This
+	 * ensures that we need less than 2 pages for struct input_mt
+	 * (we are not using in-kernel slot assignment so not going to
+	 * allocate memory for the "red" table), and we should have no
+	 * trouble getting this much memory.
+	 */
+	if (code == ABS_MT_SLOT && max > 99) {
+		printk(KERN_DEBUG
+		       "%s: unreasonably large number of slots requested: %d\n",
+		       UINPUT_NAME, max);
+		return -EINVAL;
+	}
+
 	return 0;
 }
 

2.43.0

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

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

From: Oliver Neukum <[email protected]>

[ Upstream commit e5876b088ba03a62124266fa20d00e65533c7269 ]

ipheth_sndbulk_callback() can submit carrier_work as a part of its error handling. That means that the driver must make sure that the work is cancelled after it has made sure that no more URB can terminate with an error condition.

Hence the order of actions in ipheth_close() needs to be inverted.

---
 drivers/net/usb/ipheth.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index 687d70cfc556..6eeef10edada 100644
@@ -475,8 +475,8 @@ static int ipheth_close(struct net_device *net)
 {
 	struct ipheth_device *dev = netdev_priv(net);
 
-	cancel_delayed_work_sync(&dev->carrier_work);
 	netif_stop_queue(net);
+	cancel_delayed_work_sync(&dev->carrier_work);
 	return 0;
 }
 

2.43.0

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

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

From: Phillip Lougher <[email protected]>

[ Upstream commit 810ee43d9cd245d138a2733d87a24858a23f577d ]

Syzkiller reports a "KMSAN: uninit-value in pick_link" bug.

This is caused by an uninitialised page, which is ultimately caused by a corrupted symbolic link size read from disk.

The reason why the corrupted symlink size causes an uninitialised page is due to the following sequence of events:

1. squashfs_read_inode() is called to read the symbolic link from disk. This assigns the corrupted value 3875536935 to inode->i_size.

2. Later squashfs_symlink_read_folio() is called, which assigns this corrupted value to the length variable, which being a signed int, overflows producing a negative number.

3. The following loop that fills in the page contents checks that the copied bytes is less than length, which being negative means the loop is skipped, producing an uninitialised page.

This patch adds a sanity check which checks that the symbolic link size is not larger than expected.

--

V2: fix spelling mistake.

---
 fs/squashfs/inode.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

index 16bd693d0b3a..d5918eba27e3 100644
@@ -279,8 +279,13 @@ int squashfs_read_inode(struct inode *inode, long long ino)
 		if (err < 0)
 			goto failed_read;
 
-		set_nlink(inode, le32_to_cpu(sqsh_ino->nlink));
 		inode->i_size = le32_to_cpu(sqsh_ino->symlink_size);
+		if (inode->i_size > PAGE_SIZE) {
+			ERROR("Corrupted symlink\n");
+			return -EINVAL;
+		}
+
+		set_nlink(inode, le32_to_cpu(sqsh_ino->nlink));
 		inode->i_op = &squashfs_symlink_inode_ops;
 		inode_nohighmem(inode);
 		inode->i_data.a_ops = &squashfs_symlink_aops;

2.43.0

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

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

From: Stefan Wiehler <[email protected]>

[ Upstream commit b739dffa5d570b411d4bdf4bb9b8dfd6b7d72305 ]

When of_irq_parse_raw() is invoked with a device address smaller than the interrupt parent node (from #address-cells property), KASAN detects the following out-of-bounds read when populating the initial match table (dyndbg="func of_irq_parse_* +p"):

OF: of_irq_parse_one: dev=/soc@0/picasso/watchdog, index=0
OF: parent=/soc@0/pci@878000000000/gpio0@17,0, intsize=2
OF: intspec=4
OF: of_irq_parse_raw: ipar=/soc@0/pci@878000000000/gpio0@17,0, size=2
OF: -> addrsize=3
==================================================================

  BUG: KASAN: slab-out-of-bounds in of_irq_parse_raw+0x2b8/0x8d0
  Read of size 4 at addr ffffff81beca5608 by task bash/764

  CPU: 1 PID: 764 Comm: bash Tainted: G           O       6.1.67-484c613561-nokia_sm_arm64 #1
  Hardware name: Unknown Unknown Product/Unknown Product, BIOS 2023.01-12.24.03-dirty 01/01/2023
  Call trace:
   dump_backtrace+0xdc/0x130
   show_stack+0x1c/0x30
   dump_stack_lvl+0x6c/0x84
   print_report+0x150/0x448
   kasan_report+0x98/0x140
   __asan_load4+0x78/0xa0
   of_irq_parse_raw+0x2b8/0x8d0
   of_irq_parse_one+0x24c/0x270
   parse_interrupts+0xc0/0x120
   of_fwnode_add_links+0x100/0x2d0
   fw_devlink_parse_fwtree+0x64/0xc0
   device_add+0xb38/0xc30
   of_device_add+0x64/0x90
   of_platform_device_create_pdata+0xd0/0x170
   of_platform_bus_create+0x244/0x600
   of_platform_notify+0x1b0/0x254
   blocking_notifier_call_chain+0x9c/0xd0
   __of_changeset_entry_notify+0x1b8/0x230
   __of_changeset_apply_notify+0x54/0xe4
   of_overlay_fdt_apply+0xc04/0xd94
   ...

  The buggy address belongs to the object at ffffff81beca5600
   which belongs to the cache kmalloc-128 of size 128
  The buggy address is located 8 bytes inside of
   128-byte region [ffffff81beca5600, ffffff81beca5680)

  The buggy address belongs to the physical page:
  page:00000000230d3d03 refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x1beca4
  head:00000000230d3d03 order:1 compound_mapcount:0 compound_pincount:0
  flags: 0x8000000000010200(slab|head|zone=2)
  raw: 8000000000010200 0000000000000000 dead000000000122 ffffff810000c300
  raw: 0000000000000000 0000000000200020 00000001ffffffff 0000000000000000
  page dumped because: kasan: bad access detected

  Memory state around the buggy address:
   ffffff81beca5500: 04 fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
   ffffff81beca5580: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
  >ffffff81beca5600: 00 fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
                        ^
   ffffff81beca5680: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
   ffffff81beca5700: 00 00 00 00 00 00 fc fc fc fc fc fc fc fc fc fc
  ==================================================================
  OF:  -> got it !

Prevent the out-of-bounds read by copying the device address into a buffer of sufficient size.

---
 drivers/of/irq.c | 15 +++++++++++----
 1 file changed, 11 insertions(+), 4 deletions(-)

index c94203ce65bb..8fd63100ba8f 100644
@@ -344,7 +344,8 @@ int of_irq_parse_one(struct device_node *device, int index, struct of_phandle_ar
 	struct device_node *p;
 	const __be32 *addr;
 	u32 intsize;
-	int i, res;
+	int i, res, addr_len;
+	__be32 addr_buf[3] = { 0 };
 
 	pr_debug("of_irq_parse_one: dev=%pOF, index=%d\n", device, index);
 

@@ -353,13 +354,19 @@ int of_irq_parse_one(struct device_node *device, int index, struct of_phandle_ar
 		return of_irq_parse_oldworld(device, index, out_irq);
 
 	/* Get the reg property (if any) */
-	addr = of_get_property(device, "reg", NULL);
+	addr = of_get_property(device, "reg", &addr_len);
+
+	/* Prevent out-of-bounds read in case of longer interrupt parent address size */
+	if (addr_len > (3 * sizeof(__be32)))
+		addr_len = 3 * sizeof(__be32);
+	if (addr)
+		memcpy(addr_buf, addr, addr_len);
 
 	/* Try the new-style interrupts-extended first */
 	res = of_parse_phandle_with_args(device, "interrupts-extended",
 					"#interrupt-cells", index, out_irq);
 	if (!res)
-		return of_irq_parse_raw(addr, out_irq);
+		return of_irq_parse_raw(addr_buf, out_irq);
 
 	/* Look for the interrupt parent. */
 	p = of_irq_find_parent(device);

@@ -389,7 +396,7 @@ int of_irq_parse_one(struct device_node *device, int index, struct of_phandle_ar
 
 
 	/* Check if there are any interrupt-map translations to process */
-	res = of_irq_parse_raw(addr, out_irq);
+	res = of_irq_parse_raw(addr_buf, out_irq);
  out:
 	of_node_put(p);
 	return res;

2.43.0

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

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

From: Kent Overstreet <[email protected]>

[ Upstream commit b2f11c6f3e1fc60742673b8675c95b78447f3dae ]

If we need to increase the tree depth, allocate a new node, and then race with another thread that increased the tree depth before us, we'll still have a preallocated node that might be used later.

If we then use that node for a new non-root node, it'll still have a pointer to the old root instead of being zeroed - fix this by zeroing it in the cmpxchg failure path.

---
 lib/generic-radix-tree.c | 2 ++
 1 file changed, 2 insertions(+)

index 7dfa88282b00..78f081d695d0 100644
@@ -131,6 +131,8 @@ void *__genradix_ptr_alloc(struct __genradix *radix, size_t offset,
 		if ((v = cmpxchg_release(&radix->root, r, new_root)) == r) {
 			v = new_root;
 			new_node = NULL;
+		} else {
+			new_node->children[0] = NULL;
 		}
 	}
 

2.43.0

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

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

From: Jiaxun Yang <[email protected]>

[ Upstream commit 50f2b98dc83de7809a5c5bf0ccf9af2e75c37c13 ]

This avoids warning:

[    0.118053] BUG: sleeping function called from invalid context at kernel/locking/mutex.c:283

Caused by get_c0_compare_int on secondary CPU.

We also skipped saving IRQ number to struct clock_event_device *cd as it's never used by clockevent core, as per comments it's only meant for "non CPU local devices".

---
 arch/mips/kernel/cevt-r4k.c | 15 +++++++--------
 1 file changed, 7 insertions(+), 8 deletions(-)

index 368e8475870f..5f6e9e2ebbdb 100644
@@ -303,13 +303,6 @@ int r4k_clockevent_init(void)
 	if (!c0_compare_int_usable())
 		return -ENXIO;
 
-	/*
-	 * With vectored interrupts things are getting platform specific.
-	 * get_c0_compare_int is a hook to allow a platform to return the
-	 * interrupt number of its liking.
-	 */
-	irq = get_c0_compare_int();
-
 	cd = &per_cpu(mips_clockevent_device, cpu);
 
 	cd->name		= "MIPS";

@@ -320,7 +313,6 @@ int r4k_clockevent_init(void)
 	min_delta		= calculate_min_delta();
 
 	cd->rating		= 300;
-	cd->irq			= irq;
 	cd->cpumask		= cpumask_of(cpu);
 	cd->set_next_event	= mips_next_event;
 	cd->event_handler	= mips_event_handler;

@@ -332,6 +324,13 @@ int r4k_clockevent_init(void)
 
 	cp0_timer_irq_installed = 1;
 
+	/*
+	 * With vectored interrupts things are getting platform specific.
+	 * get_c0_compare_int is a hook to allow a platform to return the
+	 * interrupt number of its liking.
+	 */
+	irq = get_c0_compare_int();
+
 	if (request_irq(irq, c0_compare_interrupt, flags, "timer",
 			c0_compare_interrupt))
 		pr_err("Failed to request irq %d (timer)\n", irq);

2.43.0

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

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

From: Carlos Song <[email protected]>

[ Upstream commit 783bf5d09f86b9736605f3e01a3472e55ef98ff8 ]

Referring to the errata ERR051608 of I.MX93, LPSPI TCR[PRESCALE] can only be configured to be 0 or 1, other values are not valid and will cause LPSPI to not work.

Add the prescale limitation for LPSPI in I.MX93. Other platforms are not affected.

---
 drivers/spi/spi-fsl-lpspi.c | 31 +++++++++++++++++++++++++++++--
 1 file changed, 29 insertions(+), 2 deletions(-)

index 3c0f7dc9614d..f02b2f741681 100644
@@ -82,6 +82,10 @@
 #define TCR_RXMSK	BIT(19)
 #define TCR_TXMSK	BIT(18)
 
+struct fsl_lpspi_devtype_data {
+	u8 prescale_max;
+};
+
 struct lpspi_config {
 	u8 bpw;
 	u8 chip_select;

@@ -119,10 +123,25 @@ struct fsl_lpspi_data {
 	bool usedma;
 	struct completion dma_rx_completion;
 	struct completion dma_tx_completion;
+
+	const struct fsl_lpspi_devtype_data *devtype_data;
+};
+
+/*
+ * ERR051608 fixed or not:
+ * https://www.nxp.com/docs/en/errata/i.MX93_1P87f.pdf
+ */
+static struct fsl_lpspi_devtype_data imx93_lpspi_devtype_data = {
+	.prescale_max = 1,
+};
+
+static struct fsl_lpspi_devtype_data imx7ulp_lpspi_devtype_data = {
+	.prescale_max = 8,
 };
 
 static const struct of_device_id fsl_lpspi_dt_ids[] = {
-	{ .compatible = "fsl,imx7ulp-spi", },
+	{ .compatible = "fsl,imx7ulp-spi", .data = &imx7ulp_lpspi_devtype_data,},
+	{ .compatible = "fsl,imx93-spi", .data = &imx93_lpspi_devtype_data,},
 	{ /* sentinel */ }
 };
 MODULE_DEVICE_TABLE(of, fsl_lpspi_dt_ids);

@@ -297,9 +316,11 @@ static int fsl_lpspi_set_bitrate(struct fsl_lpspi_data *fsl_lpspi)
 {
 	struct lpspi_config config = fsl_lpspi->config;
 	unsigned int perclk_rate, scldiv, div;
+	u8 prescale_max;
 	u8 prescale;
 
 	perclk_rate = clk_get_rate(fsl_lpspi->clk_per);
+	prescale_max = fsl_lpspi->devtype_data->prescale_max;
 
 	if (!config.speed_hz) {
 		dev_err(fsl_lpspi->dev,

@@ -315,7 +336,7 @@ static int fsl_lpspi_set_bitrate(struct fsl_lpspi_data *fsl_lpspi)
 
 	div = DIV_ROUND_UP(perclk_rate, config.speed_hz);
 
-	for (prescale = 0; prescale < 8; prescale++) {
+	for (prescale = 0; prescale < prescale_max; prescale++) {
 		scldiv = div / (1 << prescale) - 2;
 		if (scldiv < 256) {
 			fsl_lpspi->config.prescale = prescale;

@@ -822,6 +843,7 @@ static int fsl_lpspi_init_rpm(struct fsl_lpspi_data *fsl_lpspi)
 
 static int fsl_lpspi_probe(struct platform_device *pdev)
 {
+	const struct fsl_lpspi_devtype_data *devtype_data;
 	struct fsl_lpspi_data *fsl_lpspi;
 	struct spi_controller *controller;
 	struct resource *res;

@@ -830,6 +852,10 @@ static int fsl_lpspi_probe(struct platform_device *pdev)
 	u32 temp;
 	bool is_target;
 
+	devtype_data = of_device_get_match_data(&pdev->dev);
+	if (!devtype_data)
+		return -ENODEV;
+
 	is_target = of_property_read_bool((&pdev->dev)->of_node, "spi-slave");
 	if (is_target)
 		controller = devm_spi_alloc_target(&pdev->dev,

@@ -848,6 +874,7 @@ static int fsl_lpspi_probe(struct platform_device *pdev)
 	fsl_lpspi->is_target = is_target;
 	fsl_lpspi->is_only_cs1 = of_property_read_bool((&pdev->dev)->of_node,
 						"fsl,spi-only-use-cs1-sel");
+	fsl_lpspi->devtype_data = devtype_data;
 
 	init_completion(&fsl_lpspi->xfer_done);
 

2.43.0

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

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

From: Michael Ellerman <[email protected]>

[ Upstream commit d4bc0a264fb482b019c84fbc7202dd3cab059087 ]

The overflow/underflow conditions in pata_macio_qc_prep() should never happen. But if they do there's no need to kill the system entirely, a WARN and failing the IO request should be sufficient and might allow the system to keep running.

---
 drivers/ata/pata_macio.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

index 17f6ccee53c7..ffbb2e8591ce 100644
@@ -541,7 +541,8 @@ static enum ata_completion_errors pata_macio_qc_prep(struct ata_queued_cmd *qc)
 
 		while (sg_len) {
 			/* table overflow should never happen */
-			BUG_ON (pi++ >= MAX_DCMDS);
+			if (WARN_ON_ONCE(pi >= MAX_DCMDS))
+				return AC_ERR_SYSTEM;
 
 			len = (sg_len < MAX_DBDMA_SEG) ? sg_len : MAX_DBDMA_SEG;
 			table->command = cpu_to_le16(write ? OUTPUT_MORE: INPUT_MORE);

@@ -553,11 +554,13 @@ static enum ata_completion_errors pata_macio_qc_prep(struct ata_queued_cmd *qc)
 			addr += len;
 			sg_len -= len;
 			++table;
+			++pi;
 		}
 	}
 
 	/* Should never happen according to Tejun */
-	BUG_ON(!pi);
+	if (WARN_ON_ONCE(!pi))
+		return AC_ERR_SYSTEM;
 
 	/* Convert the last command to an input/output */
 	table--;

2.43.0

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

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

From: ChenXiaoSong <[email protected]>

[ Upstream commit 4e8771a3666c8f216eefd6bd2fd50121c6c437db ]

null-ptr-deref will occur when (req_op_level == SMB2_OPLOCK_LEVEL_LEASE) and parse_lease_state() return NULL.

Fix this by check if 'lease_ctx_info' is NULL.

Additionally, remove the redundant parentheses in
parse_durable_handle_context().

---
 fs/smb/server/oplock.c  |  2 +-
 fs/smb/server/smb2pdu.c | 10 +++++-----
 2 files changed, 6 insertions(+), 6 deletions(-)

index a8f52c4ebbda..e546ffa57b55 100644
@@ -1510,7 +1510,7 @@ void create_lease_buf(u8 *rbuf, struct lease *lease)
  * parse_lease_state() - parse lease context containted in file open request
  * @open_req:	buffer containing smb2 file open(create) request
  *
- * Return:  oplock state, -ENOENT if create lease context not found
+ * Return: allocated lease context object on success, otherwise NULL
  */
 struct lease_ctx_info *parse_lease_state(void *open_req)
 {

index c55924f5164e..458cc736286a 100644
@@ -2771,8 +2771,8 @@ static int parse_durable_handle_context(struct ksmbd_work *work,
 				}
 			}
 
-			if (((lc && (lc->req_state & SMB2_LEASE_HANDLE_CACHING_LE)) ||
-			     req_op_level == SMB2_OPLOCK_LEVEL_BATCH)) {
+			if ((lc && (lc->req_state & SMB2_LEASE_HANDLE_CACHING_LE)) ||
+			    req_op_level == SMB2_OPLOCK_LEVEL_BATCH) {
 				dh_info->CreateGuid =
 					durable_v2_blob->CreateGuid;
 				dh_info->persistent =

@@ -2792,8 +2792,8 @@ static int parse_durable_handle_context(struct ksmbd_work *work,
 				goto out;
 			}
 
-			if (((lc && (lc->req_state & SMB2_LEASE_HANDLE_CACHING_LE)) ||
-			     req_op_level == SMB2_OPLOCK_LEVEL_BATCH)) {
+			if ((lc && (lc->req_state & SMB2_LEASE_HANDLE_CACHING_LE)) ||
+			    req_op_level == SMB2_OPLOCK_LEVEL_BATCH) {
 				ksmbd_debug(SMB, "Request for durable open\n");
 				dh_info->type = dh_idx;
 			}

@@ -3415,7 +3415,7 @@ int smb2_open(struct ksmbd_work *work)
 			goto err_out1;
 		}
 	} else {
-		if (req_op_level == SMB2_OPLOCK_LEVEL_LEASE) {
+		if (req_op_level == SMB2_OPLOCK_LEVEL_LEASE && lc) {
 			if (S_ISDIR(file_inode(filp)->i_mode)) {
 				lc->req_state &= ~SMB2_LEASE_WRITE_CACHING_LE;
 				lc->is_dir = true;

2.43.0

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

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

From: Trond Myklebust <[email protected]>

[ Upstream commit a017ad1313fc91bdf235097fd0a02f673fc7bb11 ]

We're seeing reports of soft lockups when iterating through the loops, so let's add rescheduling points.

---
 fs/nfs/super.c | 2 ++
 1 file changed, 2 insertions(+)

index 0d6473cb00cb..f63513e477c5 100644
@@ -47,6 +47,7 @@
 #include <linux/vfs.h>
 #include <linux/inet.h>
 #include <linux/in6.h>
+#include <linux/sched.h>
 #include <linux/slab.h>
 #include <net/ipv6.h>
 #include <linux/netdevice.h>

@@ -223,6 +224,7 @@ static int __nfs_list_for_each_server(struct list_head *head,
 		ret = fn(server, data);
 		if (ret)
 			goto out;
+		cond_resched();
 		rcu_read_lock();
 	}
 	rcu_read_unlock();

2.43.0

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

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

From: Alexandre Ghiti <[email protected]>

commit c30fa83b49897e708a52e122dd10616a52a4c82b upstream.

To avoid any compiler "weirdness" when accessing page table entries which are concurrently modified by the HW, let's use WRITE_ONCE() macro (commit 20a004e7b017 ("arm64: mm: Use READ_ONCE/WRITE_ONCE when accessing page tables") gives a great explanation with more details).

---
 arch/riscv/include/asm/pgtable-64.h |    6 +++---
 arch/riscv/include/asm/pgtable.h    |    4 ++--
 2 files changed, 5 insertions(+), 5 deletions(-)

@@ -198,7 +198,7 @@ static inline int pud_user(pud_t pud)
 
 static inline void set_pud(pud_t *pudp, pud_t pud)
 {
-	*pudp = pud;
+	WRITE_ONCE(*pudp, pud);
 }
 
 static inline void pud_clear(pud_t *pudp)

@@ -274,7 +274,7 @@ static inline unsigned long _pmd_pfn(pmd
 static inline void set_p4d(p4d_t *p4dp, p4d_t p4d)
 {
 	if (pgtable_l4_enabled)
-		*p4dp = p4d;
+		WRITE_ONCE(*p4dp, p4d);
 	else
 		set_pud((pud_t *)p4dp, (pud_t){ p4d_val(p4d) });
 }

@@ -347,7 +347,7 @@ static inline pud_t *pud_offset(p4d_t *p
 static inline void set_pgd(pgd_t *pgdp, pgd_t pgd)
 {
 	if (pgtable_l5_enabled)
-		*pgdp = pgd;
+		WRITE_ONCE(*pgdp, pgd);
 	else
 		set_p4d((p4d_t *)pgdp, (p4d_t){ pgd_val(pgd) });
 }

@@ -248,7 +248,7 @@ static inline int pmd_leaf(pmd_t pmd)
 
 static inline void set_pmd(pmd_t *pmdp, pmd_t pmd)
 {
-	*pmdp = pmd;
+	WRITE_ONCE(*pmdp, pmd);
 }
 
 static inline void pmd_clear(pmd_t *pmdp)

@@ -515,7 +515,7 @@ static inline int pte_same(pte_t pte_a,
  */
 static inline void set_pte(pte_t *ptep, pte_t pteval)
 {
-	*ptep = pteval;
+	WRITE_ONCE(*ptep, pteval);
 }
 
 void flush_icache_pte(pte_t pte);

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

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

From: Alexandre Ghiti <[email protected]>

commit eba2591d99d1f14a04c8a8a845ab0795b93f5646 upstream.

Instead of directly dereferencing page tables entries, which can cause issues (see commit 20a004e7b017 ("arm64: mm: Use READ_ONCE/WRITE_ONCE when accessing page tables"), let's introduce new functions to get the pud/p4d/pgd entries (the pte and pmd versions already exist).

Note that arm pgd_t is actually an array so pgdp_get() is defined as a macro to avoid a build error.

Those new functions will be used in subsequent commits by the riscv architecture.

---
 arch/arm/include/asm/pgtable.h |    2 ++
 include/linux/pgtable.h        |   21 +++++++++++++++++++++
 2 files changed, 23 insertions(+)

@@ -151,6 +151,8 @@ extern pgprot_t phys_mem_access_prot(str
 
 extern pgd_t swapper_pg_dir[PTRS_PER_PGD];
 
+#define pgdp_get(pgpd)		READ_ONCE(*pgdp)
+
 #define pud_page(pud)		pmd_page(__pmd(pud_val(pud)))
 #define pud_write(pud)		pmd_write(__pmd(pud_val(pud)))
 

@@ -292,6 +292,27 @@ static inline pmd_t pmdp_get(pmd_t *pmdp
 }
 #endif
 
+#ifndef pudp_get
+static inline pud_t pudp_get(pud_t *pudp)
+{
+	return READ_ONCE(*pudp);
+}
+#endif
+
+#ifndef p4dp_get
+static inline p4d_t p4dp_get(p4d_t *p4dp)
+{
+	return READ_ONCE(*p4dp);
+}
+#endif
+
+#ifndef pgdp_get
+static inline pgd_t pgdp_get(pgd_t *pgdp)
+{
+	return READ_ONCE(*pgdp);
+}
+#endif
+
 #ifndef __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
 static inline int ptep_test_and_clear_young(struct vm_area_struct *vma,
 					    unsigned long address,

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

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

From: Alexandre Ghiti <[email protected]>

commit d6508999d1882ddd0db8b3b4bd7967d83e9909fa upstream.

All functions defined in there depend on MMU, so no need to compile it for !MMU configs.

---
 arch/riscv/mm/Makefile |    3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

@@ -13,10 +13,9 @@ endif
 KCOV_INSTRUMENT_init.o := n
 
 obj-y += init.o
-obj-$(CONFIG_MMU) += extable.o fault.o pageattr.o
+obj-$(CONFIG_MMU) += extable.o fault.o pageattr.o pgtable.o
 obj-y += cacheflush.o
 obj-y += context.o
-obj-y += pgtable.o
 obj-y += pmem.o
 
 ifeq ($(CONFIG_MMU),y)

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

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

From: Alexandre Ghiti <[email protected]>

commit edf955647269422e387732870d04fc15933a25ea upstream.

As very well explained in commit 20a004e7b017 ("arm64: mm: Use READ_ONCE/WRITE_ONCE when accessing page tables"), an architecture whose page table walker can modify the PTE in parallel must use READ_ONCE()/WRITE_ONCE() macro to avoid any compiler transformation.

So apply that to riscv which is such architecture.

---
 arch/riscv/include/asm/kfence.h     |    4 +-
 arch/riscv/include/asm/pgtable-64.h |   16 +----------
 arch/riscv/include/asm/pgtable.h    |   29 ++++----------------
 arch/riscv/kernel/efi.c             |    2 -
 arch/riscv/kvm/mmu.c                |   22 +++++++--------
 arch/riscv/mm/fault.c               |   16 +++++------
 arch/riscv/mm/hugetlbpage.c         |   12 ++++----
 arch/riscv/mm/kasan_init.c          |   45 ++++++++++++++++---------------
 arch/riscv/mm/pageattr.c            |   44 +++++++++++++++----------------
 arch/riscv/mm/pgtable.c             |   51 ++++++++++++++++++++++++++++++++----
 10 files changed, 128 insertions(+), 113 deletions(-)

@@ -18,9 +18,9 @@ static inline bool kfence_protect_page(u
 	pte_t *pte = virt_to_kpte(addr);
 
 	if (protect)
-		set_pte(pte, __pte(pte_val(*pte) & ~_PAGE_PRESENT));
+		set_pte(pte, __pte(pte_val(ptep_get(pte)) & ~_PAGE_PRESENT));
 	else
-		set_pte(pte, __pte(pte_val(*pte) | _PAGE_PRESENT));
+		set_pte(pte, __pte(pte_val(ptep_get(pte)) | _PAGE_PRESENT));
 
 	flush_tlb_kernel_range(addr, addr + PAGE_SIZE);
 

@@ -336,13 +336,7 @@ static inline struct page *p4d_page(p4d_
 #define pud_index(addr) (((addr) >> PUD_SHIFT) & (PTRS_PER_PUD - 1))
 
 #define pud_offset pud_offset
-static inline pud_t *pud_offset(p4d_t *p4d, unsigned long address)
-{
-	if (pgtable_l4_enabled)
-		return p4d_pgtable(*p4d) + pud_index(address);
-
-	return (pud_t *)p4d;
-}
+pud_t *pud_offset(p4d_t *p4d, unsigned long address);
 
 static inline void set_pgd(pgd_t *pgdp, pgd_t pgd)
 {

@@ -400,12 +394,6 @@ static inline struct page *pgd_page(pgd_
 #define p4d_index(addr) (((addr) >> P4D_SHIFT) & (PTRS_PER_P4D - 1))
 
 #define p4d_offset p4d_offset
-static inline p4d_t *p4d_offset(pgd_t *pgd, unsigned long address)
-{
-	if (pgtable_l5_enabled)
-		return pgd_pgtable(*pgd) + p4d_index(address);
-
-	return (p4d_t *)pgd;
-}
+p4d_t *p4d_offset(pgd_t *pgd, unsigned long address);
 
 #endif /* _ASM_RISCV_PGTABLE_64_H */

@@ -549,19 +549,12 @@ static inline void pte_clear(struct mm_s
 	__set_pte_at(ptep, __pte(0));
 }
 
-#define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
-static inline int ptep_set_access_flags(struct vm_area_struct *vma,
-					unsigned long address, pte_t *ptep,
-					pte_t entry, int dirty)
-{
-	if (!pte_same(*ptep, entry))
-		__set_pte_at(ptep, entry);
-	/*
-	 * update_mmu_cache will unconditionally execute, handling both
-	 * the case that the PTE changed and the spurious fault case.
-	 */
-	return true;
-}
+#define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS	/* defined in mm/pgtable.c */
+extern int ptep_set_access_flags(struct vm_area_struct *vma, unsigned long address,
+				 pte_t *ptep, pte_t entry, int dirty);
+#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG	/* defined in mm/pgtable.c */
+extern int ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned long address,
+				     pte_t *ptep);
 
 #define __HAVE_ARCH_PTEP_GET_AND_CLEAR
 static inline pte_t ptep_get_and_clear(struct mm_struct *mm,

@@ -574,16 +567,6 @@ static inline pte_t ptep_get_and_clear(s
 	return pte;
 }
 
-#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
-static inline int ptep_test_and_clear_young(struct vm_area_struct *vma,
-					    unsigned long address,
-					    pte_t *ptep)
-{
-	if (!pte_young(*ptep))
-		return 0;
-	return test_and_clear_bit(_PAGE_ACCESSED_OFFSET, &pte_val(*ptep));
-}
-
 #define __HAVE_ARCH_PTEP_SET_WRPROTECT
 static inline void ptep_set_wrprotect(struct mm_struct *mm,
 				      unsigned long address, pte_t *ptep)

@@ -60,7 +60,7 @@ int __init efi_create_mapping(struct mm_
 static int __init set_permissions(pte_t *ptep, unsigned long addr, void *data)
 {
 	efi_memory_desc_t *md = data;
-	pte_t pte = READ_ONCE(*ptep);
+	pte_t pte = ptep_get(ptep);
 	unsigned long val;
 
 	if (md->attribute & EFI_MEMORY_RO) {

@@ -103,7 +103,7 @@ static bool gstage_get_leaf_entry(struct
 	*ptep_level = current_level;
 	ptep = (pte_t *)kvm->arch.pgd;
 	ptep = &ptep[gstage_pte_index(addr, current_level)];
-	while (ptep && pte_val(*ptep)) {
+	while (ptep && pte_val(ptep_get(ptep))) {
 		if (gstage_pte_leaf(ptep)) {
 			*ptep_level = current_level;
 			*ptepp = ptep;

@@ -113,7 +113,7 @@ static bool gstage_get_leaf_entry(struct
 		if (current_level) {
 			current_level--;
 			*ptep_level = current_level;
-			ptep = (pte_t *)gstage_pte_page_vaddr(*ptep);
+			ptep = (pte_t *)gstage_pte_page_vaddr(ptep_get(ptep));
 			ptep = &ptep[gstage_pte_index(addr, current_level)];
 		} else {
 			ptep = NULL;

@@ -149,25 +149,25 @@ static int gstage_set_pte(struct kvm *kv
 		if (gstage_pte_leaf(ptep))
 			return -EEXIST;
 
-		if (!pte_val(*ptep)) {
+		if (!pte_val(ptep_get(ptep))) {
 			if (!pcache)
 				return -ENOMEM;
 			next_ptep = kvm_mmu_memory_cache_alloc(pcache);
 			if (!next_ptep)
 				return -ENOMEM;
-			*ptep = pfn_pte(PFN_DOWN(__pa(next_ptep)),
-					__pgprot(_PAGE_TABLE));
+			set_pte(ptep, pfn_pte(PFN_DOWN(__pa(next_ptep)),
+					      __pgprot(_PAGE_TABLE)));
 		} else {
 			if (gstage_pte_leaf(ptep))
 				return -EEXIST;
-			next_ptep = (pte_t *)gstage_pte_page_vaddr(*ptep);
+			next_ptep = (pte_t *)gstage_pte_page_vaddr(ptep_get(ptep));
 		}
 
 		current_level--;
 		ptep = &next_ptep[gstage_pte_index(addr, current_level)];
 	}
 
-	*ptep = *new_pte;
+	set_pte(ptep, *new_pte);
 	if (gstage_pte_leaf(ptep))
 		gstage_remote_tlb_flush(kvm, current_level, addr);
 

@@ -239,11 +239,11 @@ static void gstage_op_pte(struct kvm *kv
 
 	BUG_ON(addr & (page_size - 1));
 
-	if (!pte_val(*ptep))
+	if (!pte_val(ptep_get(ptep)))
 		return;
 
 	if (ptep_level && !gstage_pte_leaf(ptep)) {
-		next_ptep = (pte_t *)gstage_pte_page_vaddr(*ptep);
+		next_ptep = (pte_t *)gstage_pte_page_vaddr(ptep_get(ptep));
 		next_ptep_level = ptep_level - 1;
 		ret = gstage_level_to_page_size(next_ptep_level,
 						&next_page_size);

@@ -261,7 +261,7 @@ static void gstage_op_pte(struct kvm *kv
 		if (op == GSTAGE_OP_CLEAR)
 			set_pte(ptep, __pte(0));
 		else if (op == GSTAGE_OP_WP)
-			set_pte(ptep, __pte(pte_val(*ptep) & ~_PAGE_WRITE));
+			set_pte(ptep, __pte(pte_val(ptep_get(ptep)) & ~_PAGE_WRITE));
 		gstage_remote_tlb_flush(kvm, ptep_level, addr);
 	}
 }

@@ -603,7 +603,7 @@ bool kvm_test_age_gfn(struct kvm *kvm, s
 				   &ptep, &ptep_level))
 		return false;
 
-	return pte_young(*ptep);
+	return pte_young(ptep_get(ptep));
 }
 
 int kvm_riscv_gstage_map(struct kvm_vcpu *vcpu,

@@ -137,24 +137,24 @@ static inline void vmalloc_fault(struct
 	pgd = (pgd_t *)pfn_to_virt(pfn) + index;
 	pgd_k = init_mm.pgd + index;
 
-	if (!pgd_present(*pgd_k)) {
+	if (!pgd_present(pgdp_get(pgd_k))) {
 		no_context(regs, addr);
 		return;
 	}
-	set_pgd(pgd, *pgd_k);
+	set_pgd(pgd, pgdp_get(pgd_k));
 
 	p4d_k = p4d_offset(pgd_k, addr);
-	if (!p4d_present(*p4d_k)) {
+	if (!p4d_present(p4dp_get(p4d_k))) {
 		no_context(regs, addr);
 		return;
 	}
 
 	pud_k = pud_offset(p4d_k, addr);
-	if (!pud_present(*pud_k)) {
+	if (!pud_present(pudp_get(pud_k))) {
 		no_context(regs, addr);
 		return;
 	}
-	if (pud_leaf(*pud_k))
+	if (pud_leaf(pudp_get(pud_k)))
 		goto flush_tlb;
 
 	/*

@@ -162,11 +162,11 @@ static inline void vmalloc_fault(struct
 	 * to copy individual PTEs
 	 */
 	pmd_k = pmd_offset(pud_k, addr);
-	if (!pmd_present(*pmd_k)) {
+	if (!pmd_present(pmdp_get(pmd_k))) {
 		no_context(regs, addr);
 		return;
 	}
-	if (pmd_leaf(*pmd_k))
+	if (pmd_leaf(pmdp_get(pmd_k)))
 		goto flush_tlb;
 
 	/*

@@ -176,7 +176,7 @@ static inline void vmalloc_fault(struct
 	 * silently loop forever.
 	 */
 	pte_k = pte_offset_kernel(pmd_k, addr);
-	if (!pte_present(*pte_k)) {
+	if (!pte_present(ptep_get(pte_k))) {
 		no_context(regs, addr);
 		return;
 	}

@@ -54,7 +54,7 @@ pte_t *huge_pte_alloc(struct mm_struct *
 	}
 
 	if (sz == PMD_SIZE) {
-		if (want_pmd_share(vma, addr) && pud_none(*pud))
+		if (want_pmd_share(vma, addr) && pud_none(pudp_get(pud)))
 			pte = huge_pmd_share(mm, vma, addr, pud);
 		else
 			pte = (pte_t *)pmd_alloc(mm, pud, addr);

@@ -93,11 +93,11 @@ pte_t *huge_pte_offset(struct mm_struct
 	pmd_t *pmd;
 
 	pgd = pgd_offset(mm, addr);
-	if (!pgd_present(*pgd))
+	if (!pgd_present(pgdp_get(pgd)))
 		return NULL;
 
 	p4d = p4d_offset(pgd, addr);
-	if (!p4d_present(*p4d))
+	if (!p4d_present(p4dp_get(p4d)))
 		return NULL;
 
 	pud = pud_offset(p4d, addr);

@@ -105,7 +105,7 @@ pte_t *huge_pte_offset(struct mm_struct
 		/* must be pud huge, non-present or none */
 		return (pte_t *)pud;
 
-	if (!pud_present(*pud))
+	if (!pud_present(pudp_get(pud)))
 		return NULL;
 
 	pmd = pmd_offset(pud, addr);

@@ -113,7 +113,7 @@ pte_t *huge_pte_offset(struct mm_struct
 		/* must be pmd huge, non-present or none */
 		return (pte_t *)pmd;
 
-	if (!pmd_present(*pmd))
+	if (!pmd_present(pmdp_get(pmd)))
 		return NULL;
 
 	for_each_napot_order(order) {

@@ -351,7 +351,7 @@ void huge_pte_clear(struct mm_struct *mm
 		    pte_t *ptep,
 		    unsigned long sz)
 {
-	pte_t pte = READ_ONCE(*ptep);
+	pte_t pte = ptep_get(ptep);
 	int i, pte_num;
 
 	if (!pte_napot(pte)) {

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

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

From: Meng Li <[email protected]>

commit 12753d71e8c5c3e716cedba23ddeed508da0bdc4 upstream.

Add support for getting the highest performance to the generic CPPC driver. This enables downstream drivers such as amd-pstate to discover and use these values.

Refer to Chapter 8.4.6.1.1.1. Highest Performance of ACPI Specification 6.5 for details on continuous performance control of CPPC (linked below).

---
 drivers/acpi/cppc_acpi.c |   13 +++++++++++++
 include/acpi/cppc_acpi.h |    5 +++++
 2 files changed, 18 insertions(+)

@@ -1197,6 +1197,19 @@ int cppc_get_nominal_perf(int cpunum, u6
 }
 
 /**
+ * cppc_get_highest_perf - Get the highest performance register value.
+ * @cpunum: CPU from which to get highest performance.
+ * @highest_perf: Return address.
+ *
+ * Return: 0 for success, -EIO otherwise.
+ */
+int cppc_get_highest_perf(int cpunum, u64 *highest_perf)
+{
+	return cppc_get_perf(cpunum, HIGHEST_PERF, highest_perf);
+}
+EXPORT_SYMBOL_GPL(cppc_get_highest_perf);
+
+/**
  * cppc_get_epp_perf - Get the epp register value.
  * @cpunum: CPU from which to get epp preference value.
  * @epp_perf: Return address.

@@ -139,6 +139,7 @@ struct cppc_cpudata {
 #ifdef CONFIG_ACPI_CPPC_LIB
 extern int cppc_get_desired_perf(int cpunum, u64 *desired_perf);
 extern int cppc_get_nominal_perf(int cpunum, u64 *nominal_perf);
+extern int cppc_get_highest_perf(int cpunum, u64 *highest_perf);
 extern int cppc_get_perf_ctrs(int cpu, struct cppc_perf_fb_ctrs *perf_fb_ctrs);
 extern int cppc_set_perf(int cpu, struct cppc_perf_ctrls *perf_ctrls);
 extern int cppc_set_enable(int cpu, bool enable);

@@ -165,6 +166,10 @@ static inline int cppc_get_nominal_perf(
 {
 	return -ENOTSUPP;
 }
+static inline int cppc_get_highest_perf(int cpunum, u64 *highest_perf)
+{
+	return -ENOTSUPP;
+}
 static inline int cppc_get_perf_ctrs(int cpu, struct cppc_perf_fb_ctrs *perf_fb_ctrs)
 {
 	return -ENOTSUPP;

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

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

From: Meng Li <[email protected]>

commit f3a052391822b772b4e27f2594526cf1eb103cab upstream.

amd-pstate driver utilizes the functions and data structures provided by the ITMT architecture to enable the scheduler to favor scheduling on cores which can be get a higher frequency with lower voltage. We call it amd-pstate preferrred core.

Here sched_set_itmt_core_prio() is called to set priorities and sched_set_itmt_support() is called to enable ITMT feature. amd-pstate driver uses the highest performance value to indicate the priority of CPU. The higher value has a higher priority.

The initial core rankings are set up by amd-pstate when the system boots.

Add a variable hw_prefcore in cpudata structure. It will check if the processor and power firmware support preferred core feature.

Add one new early parameter disable to allow user to disable the preferred core.

Only when hardware supports preferred core and user set enabled in early parameter, amd pstate driver supports preferred core featue.