From b99a1f0f18ee50445907f55069e88bcfd8947383 Mon Sep 17 00:00:00 2001 From: Jie Wang Date: Thu, 23 Apr 2026 13:39:34 +0000 Subject: [PATCH 001/297] gfs2: fix quota init duplicate scan gfs2_quota_init() checks for duplicate quota_change IDs while holding qd_lock and the quota hash bucket bitlock. That path used gfs2_qd_search_bucket(), which takes a lockref reference via lockref_get_not_dead(). On PREEMPT_RT this may sleep, which is not allowed under the bucket bitlock, triggering "sleeping function called from invalid context". Use a no-ref bucket lookup in this path, then continue duplicate handling without taking a lockref there. Refactor gfs2_qd_search_bucket() to build on top of the no-ref helper so lookup traversal stays in one place. This patch fixes a bug reported by syzbot. Reported-by: syzbot+642d0561f78362d67d3f@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=642d0561f78362d67d3f Tested-by: syzbot+642d0561f78362d67d3f@syzkaller.appspotmail.com Signed-off-by: Jie Wang Signed-off-by: Andreas Gruenbacher --- fs/gfs2/quota.c | 33 +++++++++++++++++++++++---------- 1 file changed, 23 insertions(+), 10 deletions(-) diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c index 5290865f27f1..934397248fe7 100644 --- a/fs/gfs2/quota.c +++ b/fs/gfs2/quota.c @@ -254,9 +254,13 @@ fail: return NULL; } -static struct gfs2_quota_data *gfs2_qd_search_bucket(unsigned int hash, - const struct gfs2_sbd *sdp, - struct kqid qid) +/* + * Lookup variant for callers which already hold qd_lock + bucket lock. + */ +static struct gfs2_quota_data * +gfs2_qd_search_bucket_noref(unsigned int hash, + const struct gfs2_sbd *sdp, + struct kqid qid) { struct gfs2_quota_data *qd; struct hlist_bl_node *h; @@ -264,12 +268,22 @@ static struct gfs2_quota_data *gfs2_qd_search_bucket(unsigned int hash, hlist_bl_for_each_entry_rcu(qd, h, &qd_hash_table[hash], qd_hlist) { if (!qid_eq(qd->qd_id, qid)) continue; - if (qd->qd_sbd != sdp) - continue; - if (lockref_get_not_dead(&qd->qd_lockref)) { - list_lru_del_obj(&gfs2_qd_lru, &qd->qd_lru); + if (qd->qd_sbd == sdp) return qd; - } + } + + return NULL; +} + +static struct gfs2_quota_data * +gfs2_qd_search_bucket(unsigned int hash, const struct gfs2_sbd *sdp, struct kqid qid) +{ + struct gfs2_quota_data *qd; + + qd = gfs2_qd_search_bucket_noref(hash, sdp, qid); + if (qd && lockref_get_not_dead(&qd->qd_lockref)) { + list_lru_del_obj(&gfs2_qd_lru, &qd->qd_lru); + return qd; } return NULL; @@ -1458,7 +1472,7 @@ int gfs2_quota_init(struct gfs2_sbd *sdp) spin_lock(&qd_lock); spin_lock_bucket(hash); - old_qd = gfs2_qd_search_bucket(hash, sdp, qc_id); + old_qd = gfs2_qd_search_bucket_noref(hash, sdp, qc_id); if (old_qd) { fs_err(sdp, "Corruption found in quota_change%u" "file: duplicate identifier in " @@ -1467,7 +1481,6 @@ int gfs2_quota_init(struct gfs2_sbd *sdp) spin_unlock_bucket(hash); spin_unlock(&qd_lock); - qd_put(old_qd); gfs2_glock_put(qd->qd_gl); kmem_cache_free(gfs2_quotad_cachep, qd); From 942202677f8f2ee448a6a2feb06aeeaf520342e3 Mon Sep 17 00:00:00 2001 From: Jie Wang Date: Tue, 21 Apr 2026 16:32:07 +0000 Subject: [PATCH 002/297] gfs2: move quota_init qc iterator increment Move qc++ from the loop body into the for-loop increment expression in gfs2_quota_init(). This keeps iterator progression explicit and avoids mixing pointer advance with duplicate-slot handling in the loop body. Signed-off-by: Jie Wang Signed-off-by: Andreas Gruenbacher --- fs/gfs2/quota.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c index 934397248fe7..91e9975d25e8 100644 --- a/fs/gfs2/quota.c +++ b/fs/gfs2/quota.c @@ -1447,7 +1447,7 @@ int gfs2_quota_init(struct gfs2_sbd *sdp) qc = (struct gfs2_quota_change *)(bh->b_data + sizeof(struct gfs2_meta_header)); for (y = 0; y < sdp->sd_qc_per_block && slot < sdp->sd_quota_slots; - y++, slot++) { + y++, slot++, qc++) { struct gfs2_quota_data *old_qd, *qd; s64 qc_change = be64_to_cpu(qc->qc_change); u32 qc_flags = be32_to_cpu(qc->qc_flags); @@ -1455,7 +1455,6 @@ int gfs2_quota_init(struct gfs2_sbd *sdp) USRQUOTA : GRPQUOTA; struct kqid qc_id = make_kqid(&init_user_ns, qtype, be32_to_cpu(qc->qc_id)); - qc++; if (!qc_change) continue; From f9c9ec2c319f843b70ecdf939d48b52d189bc081 Mon Sep 17 00:00:00 2001 From: Tristan Madani Date: Fri, 1 May 2026 11:02:03 +0000 Subject: [PATCH 003/297] gfs2: fix use-after-free in gfs2_qd_dealloc gfs2_qd_dealloc(), called as an RCU callback from gfs2_qd_dispose(), accesses the superblock object sdp through qd->qd_sbd after freeing qd. It does so to decrement sd_quota_count and wake up sd_kill_wait. However, by the time the RCU callback runs, gfs2_put_super() may have already freed sdp via free_sbd(). This can happen when gfs2_quota_cleanup() is called during unmount: it disposes of quota objects via call_rcu() and then waits on sd_kill_wait with a 60-second timeout. If the timeout expires, or if gfs2_gl_hash_clear() triggers additional qd_put() calls that schedule more RCU callbacks after the wait completes, gfs2_put_super() will proceed to free the superblock while RCU callbacks referencing it are still pending. Add an rcu_barrier() before free_sbd() in gfs2_put_super() to ensure all pending RCU callbacks (including gfs2_qd_dealloc) have completed before the superblock is freed. Fixes: a475c5dd16e5 ("gfs2: Free quota data objects synchronously") Reported-by: syzbot+42a37bf8045847d8f9d2@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=42a37bf8045847d8f9d2 Tested-by: syzbot+42a37bf8045847d8f9d2@syzkaller.appspotmail.com Cc: stable@vger.kernel.org Signed-off-by: Tristan Madani Signed-off-by: Andreas Gruenbacher --- fs/gfs2/super.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c index a2ea121331f1..4d854556b529 100644 --- a/fs/gfs2/super.c +++ b/fs/gfs2/super.c @@ -643,6 +643,7 @@ restart: gfs2_delete_debugfs_file(sdp); gfs2_sys_fs_del(sdp); + rcu_barrier(); free_sbd(sdp); } From b72386864481cf7fb6153842d22561ac3032302f Mon Sep 17 00:00:00 2001 From: Maxwell Doose Date: Sun, 3 May 2026 15:12:36 -0500 Subject: [PATCH 004/297] rtc: ab8500: replace sprintf() with sysfs_emit() This patch replaces sprintf() with sysfs_emit() to ensure proper bounds checking. It also simplifies the return logic by directly returning the error after logging, instead of logging, calling sprintf(), then returning. Reviewed-by: Linus Walleij Signed-off-by: Maxwell Doose Link: https://patch.msgid.link/20260503201236.29685-1-m32285159@gmail.com Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-ab8500.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/rtc/rtc-ab8500.c b/drivers/rtc/rtc-ab8500.c index ed2b6b8bb3bf..c6147837f957 100644 --- a/drivers/rtc/rtc-ab8500.c +++ b/drivers/rtc/rtc-ab8500.c @@ -284,11 +284,10 @@ static ssize_t ab8500_sysfs_show_rtc_calibration(struct device *dev, retval = ab8500_rtc_get_calibration(dev, &calibration); if (retval < 0) { dev_err(dev, "Failed to read RTC calibration attribute\n"); - sprintf(buf, "0\n"); return retval; } - return sprintf(buf, "%d\n", calibration); + return sysfs_emit(buf, "%d\n", calibration); } static DEVICE_ATTR(rtc_calibration, S_IRUGO | S_IWUSR, From 4d97a37e2cedb008eb39354b2a4e2af9ae8bdbe7 Mon Sep 17 00:00:00 2001 From: Alexey Velichayshiy Date: Sun, 12 Apr 2026 16:50:08 +0300 Subject: [PATCH 005/297] ecryptfs: remove redundant variable found_auth_tok The found_auth_tok variable is no longer needed, as the fact of finding a token is determined directly by jumping to the found_matching_auth_tok label inside the loop. Remove found_auth_tok, simplifying the function logic. Found by Linux Verification Center (linuxtesting.org) with SVACE. Signed-off-by: Alexey Velichayshiy [tyhicks: Unsplit log message string] Signed-off-by: Tyler Hicks --- fs/ecryptfs/keystore.c | 16 +++++----------- 1 file changed, 5 insertions(+), 11 deletions(-) diff --git a/fs/ecryptfs/keystore.c b/fs/ecryptfs/keystore.c index 0be746493e56..ebebc9551f1f 100644 --- a/fs/ecryptfs/keystore.c +++ b/fs/ecryptfs/keystore.c @@ -1718,7 +1718,6 @@ int ecryptfs_parse_packet_set(struct ecryptfs_crypt_stat *crypt_stat, struct dentry *ecryptfs_dentry) { size_t i = 0; - size_t found_auth_tok; size_t next_packet_is_auth_tok_packet; LIST_HEAD(auth_tok_list); struct ecryptfs_auth_tok *matching_auth_tok; @@ -1822,7 +1821,6 @@ int ecryptfs_parse_packet_set(struct ecryptfs_crypt_stat *crypt_stat, * the metadata. There may be several potential matches, but * just one will be sufficient to decrypt to get the FEK. */ find_next_matching_auth_tok: - found_auth_tok = 0; list_for_each_entry(auth_tok_list_item, &auth_tok_list, list) { candidate_auth_tok = &auth_tok_list_item->auth_tok; if (unlikely(ecryptfs_verbosity > 0)) { @@ -1843,17 +1841,13 @@ find_next_matching_auth_tok: &matching_auth_tok, crypt_stat->mount_crypt_stat, candidate_auth_tok_sig); - if (!rc) { - found_auth_tok = 1; + if (!rc) goto found_matching_auth_tok; - } - } - if (!found_auth_tok) { - ecryptfs_printk(KERN_ERR, "Could not find a usable " - "authentication token\n"); - rc = -EIO; - goto out_wipe_list; } + ecryptfs_printk(KERN_ERR, + "Could not find a usable authentication token\n"); + rc = -EIO; + goto out_wipe_list; found_matching_auth_tok: if (candidate_auth_tok->token_type == ECRYPTFS_PRIVATE_KEY) { memcpy(&(candidate_auth_tok->token.private_key), From 70008e22ab3fd619fb2a50dcfa80b9dfa26c5d8a Mon Sep 17 00:00:00 2001 From: Andreas Gruenbacher Date: Sat, 23 May 2026 12:12:37 +0200 Subject: [PATCH 006/297] gfs2: Remove unused fallocate_chunk argument The mode argument of fallocate_chunk() became unused in commit 1885867b84d5 ("GFS2: Update i_size properly on fallocate"), so remove it. Signed-off-by: Andreas Gruenbacher --- fs/gfs2/file.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c index 9704f1ef6ad1..48ebda5ba808 100644 --- a/fs/gfs2/file.c +++ b/fs/gfs2/file.c @@ -1173,8 +1173,7 @@ out_unlock: return ret; } -static int fallocate_chunk(struct inode *inode, loff_t offset, loff_t len, - int mode) +static int fallocate_chunk(struct inode *inode, loff_t offset, loff_t len) { struct super_block *sb = inode->i_sb; struct gfs2_inode *ip = GFS2_I(inode); @@ -1336,7 +1335,7 @@ static long __gfs2_fallocate(struct file *file, int mode, loff_t offset, loff_t if (error) goto out_trans_fail; - error = fallocate_chunk(inode, offset, max_bytes, mode); + error = fallocate_chunk(inode, offset, max_bytes); gfs2_trans_end(sdp); if (error) From 4982e58669b11c43644efb5fb7435975848b716e Mon Sep 17 00:00:00 2001 From: Andreas Gruenbacher Date: Wed, 27 May 2026 21:15:04 +0200 Subject: [PATCH 007/297] gfs2: page poisoning fix Processes can write to the last page of a file using mmap, and when the file size is not a multiple of the page size, this can be used to write beyond the end of the file. This is sometimes referred to as page poisoning, and it is not a problem in itself because the data beyond eof will be ignored. However, we currently fail to clear out any space beyond the end of the file that we skip over when the file size is increased, so that "poison" can end up getting exposed. Fix that. Fixes xfstest generic/363. Signed-off-by: Andreas Gruenbacher --- fs/gfs2/bmap.c | 19 +++++++++++++++++++ fs/gfs2/bmap.h | 1 + fs/gfs2/file.c | 10 ++++++++++ 3 files changed, 30 insertions(+) diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c index b3d7fcd95f03..95a64819fe2c 100644 --- a/fs/gfs2/bmap.c +++ b/fs/gfs2/bmap.c @@ -1321,6 +1321,19 @@ static int gfs2_block_zero_range(struct inode *inode, loff_t from, loff_t length &gfs2_iomap_write_ops, NULL); } +int gfs2_clear_beyond_eof(struct inode *inode, loff_t end) +{ + loff_t isize = i_size_read(inode); + unsigned int len = isize & ~PAGE_MASK; + + if (!len || isize >= end) + return 0; + len = PAGE_SIZE - len; + if (end - isize < len) + len = end - isize; + return gfs2_block_zero_range(inode, isize, len); +} + #define GFS2_JTRUNC_REVOKES 8192 /** @@ -2096,6 +2109,12 @@ static int do_grow(struct inode *inode, u64 size) unstuff = 1; } + if (!unstuff) { + error = gfs2_clear_beyond_eof(inode, size); + if (error) + goto do_grow_qunlock; + } + error = gfs2_trans_begin(sdp, RES_DINODE + RES_STATFS + RES_RG_BIT + (unstuff && gfs2_is_jdata(ip) ? RES_JDATA : 0) + diff --git a/fs/gfs2/bmap.h b/fs/gfs2/bmap.h index 6cdc72dd55a3..e3d6efdfd890 100644 --- a/fs/gfs2/bmap.h +++ b/fs/gfs2/bmap.h @@ -58,6 +58,7 @@ int gfs2_get_extent(struct inode *inode, u64 lblock, u64 *dblock, unsigned int *extlen); int gfs2_alloc_extent(struct inode *inode, u64 lblock, u64 *dblock, unsigned *extlen, bool *new); +int gfs2_clear_beyond_eof(struct inode *inode, loff_t end); int gfs2_setattr_size(struct inode *inode, u64 size); int gfs2_truncatei_resume(struct gfs2_inode *ip); int gfs2_file_dealloc(struct gfs2_inode *ip); diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c index 48ebda5ba808..b8c10de113ba 100644 --- a/fs/gfs2/file.c +++ b/fs/gfs2/file.c @@ -1057,6 +1057,10 @@ retry: goto out_unlock; } + ret = gfs2_clear_beyond_eof(inode, iocb->ki_pos); + if (ret) + goto out_unlock; + pagefault_disable(); ret = iomap_file_buffered_write(iocb, from, &gfs2_iomap_ops, &gfs2_iomap_write_ops, NULL); @@ -1265,6 +1269,12 @@ static long __gfs2_fallocate(struct file *file, int mode, loff_t offset, loff_t next = (next + 1) << sdp->sd_sb.sb_bsize_shift; + if (!(mode & FALLOC_FL_KEEP_SIZE)) { + error = gfs2_clear_beyond_eof(inode, offset + len); + if (error) + return error; + } + offset &= bsize_mask; len = next - offset; From 95ce5ffd54cf66098f91892f98606c3bd33846fe Mon Sep 17 00:00:00 2001 From: Thorsten Blum Date: Mon, 18 May 2026 09:38:45 +0200 Subject: [PATCH 008/297] ecryptfs: use kasprintf in ecryptfs_crypto_api_algify_cipher_name Use kasprintf() to simplify ecryptfs_crypto_api_algify_cipher_name(). Use const char * for the read-only cipher name and chaining modifier while at it. Signed-off-by: Thorsten Blum Signed-off-by: Tyler Hicks --- fs/ecryptfs/crypto.c | 24 +++++++----------------- 1 file changed, 7 insertions(+), 17 deletions(-) diff --git a/fs/ecryptfs/crypto.c b/fs/ecryptfs/crypto.c index 5ef67b2674ee..74b02b55e3f6 100644 --- a/fs/ecryptfs/crypto.c +++ b/fs/ecryptfs/crypto.c @@ -49,25 +49,15 @@ void ecryptfs_from_hex(char *dst, char *src, int dst_size) } static int ecryptfs_crypto_api_algify_cipher_name(char **algified_name, - char *cipher_name, - char *chaining_modifier) + const char *cipher_name, + const char *chaining_modifier) { - int cipher_name_len = strlen(cipher_name); - int chaining_modifier_len = strlen(chaining_modifier); - int algified_name_len; - int rc; + (*algified_name) = kasprintf(GFP_KERNEL, "%s(%s)", chaining_modifier, + cipher_name); + if (!(*algified_name)) + return -ENOMEM; - algified_name_len = (chaining_modifier_len + cipher_name_len + 3); - (*algified_name) = kmalloc(algified_name_len, GFP_KERNEL); - if (!(*algified_name)) { - rc = -ENOMEM; - goto out; - } - snprintf((*algified_name), algified_name_len, "%s(%s)", - chaining_modifier, cipher_name); - rc = 0; -out: - return rc; + return 0; } /** From 2b40d72de9354a76f5e3bb71230a4210eaa92849 Mon Sep 17 00:00:00 2001 From: Biju Das Date: Thu, 4 Jun 2026 10:56:31 +0100 Subject: [PATCH 009/297] pwm: rzg2l-gpt: Fix period_ticks type from u32 to u64 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit period_ticks is used to store PWM period values that can exceed the 32-bit range, so change its type from u32 to u64 to prevent overflow. Cc: stable@kernel.org Fixes: 061f087f5d0b ("pwm: Add support for RZ/G2L GPT") Signed-off-by: Biju Das Link: https://patch.msgid.link/20260604095647.108654-2-biju.das.jz@bp.renesas.com Signed-off-by: Uwe Kleine-König --- drivers/pwm/pwm-rzg2l-gpt.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/pwm/pwm-rzg2l-gpt.c b/drivers/pwm/pwm-rzg2l-gpt.c index 4856af080e8e..c9dfa59bc1ea 100644 --- a/drivers/pwm/pwm-rzg2l-gpt.c +++ b/drivers/pwm/pwm-rzg2l-gpt.c @@ -81,7 +81,7 @@ struct rzg2l_gpt_chip { void __iomem *mmio; struct mutex lock; /* lock to protect shared channel resources */ unsigned long rate_khz; - u32 period_ticks[RZG2L_MAX_HW_CHANNELS]; + u64 period_ticks[RZG2L_MAX_HW_CHANNELS]; u32 channel_request_count[RZG2L_MAX_HW_CHANNELS]; u32 channel_enable_count[RZG2L_MAX_HW_CHANNELS]; }; From 898ab0f30e008e411ce93ddf81c4099abd9d4e46 Mon Sep 17 00:00:00 2001 From: Biju Das Date: Thu, 4 Jun 2026 10:56:34 +0100 Subject: [PATCH 010/297] pwm: rzg2l-gpt: Add missing newlines to dev_err_probe() messages MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit dev_err_probe() internally calls dev_err() which uses pr_fmt() and printk(). Kernel log messages should end with a newline character to ensure proper log formatting. Add missing '\n' at the end of the error strings in rzg2l_gpt_probe(). Signed-off-by: Biju Das Link: https://patch.msgid.link/20260604095647.108654-5-biju.das.jz@bp.renesas.com Fixes: 061f087f5d0b ("pwm: Add support for RZ/G2L GPT") Signed-off-by: Uwe Kleine-König --- drivers/pwm/pwm-rzg2l-gpt.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/pwm/pwm-rzg2l-gpt.c b/drivers/pwm/pwm-rzg2l-gpt.c index c9dfa59bc1ea..dfa1d11a48a8 100644 --- a/drivers/pwm/pwm-rzg2l-gpt.c +++ b/drivers/pwm/pwm-rzg2l-gpt.c @@ -408,14 +408,14 @@ static int rzg2l_gpt_probe(struct platform_device *pdev) rate = clk_get_rate(clk); if (!rate) - return dev_err_probe(dev, -EINVAL, "The gpt clk rate is 0"); + return dev_err_probe(dev, -EINVAL, "The gpt clk rate is 0\n"); /* * Refuse clk rates > 1 GHz to prevent overflow later for computing * period and duty cycle. */ if (rate > NSEC_PER_SEC) - return dev_err_probe(dev, -EINVAL, "The gpt clk rate is > 1GHz"); + return dev_err_probe(dev, -EINVAL, "The gpt clk rate is > 1GHz\n"); /* * Rate is in MHz and is always integer for peripheral clk @@ -424,7 +424,7 @@ static int rzg2l_gpt_probe(struct platform_device *pdev) */ rzg2l_gpt->rate_khz = rate / KILO; if (rzg2l_gpt->rate_khz * KILO != rate) - return dev_err_probe(dev, -EINVAL, "Rate is not multiple of 1000"); + return dev_err_probe(dev, -EINVAL, "Rate is not multiple of 1000\n"); mutex_init(&rzg2l_gpt->lock); From e7ab91e2bf01b024691d6ce488546533943e7a6b Mon Sep 17 00:00:00 2001 From: Karol Wachowski Date: Thu, 11 Jun 2026 07:51:40 +0200 Subject: [PATCH 011/297] accel/ivpu: fix HWS command queue leak on registration failure A command queue is considered valid and usable by the driver only when it has a doorbell ID assigned (db_id != 0), meaning both the FW cmdq creation and doorbell registration completed successfully. However, when either ivpu_register_db() or set_context_sched_properties() fails after ivpu_hws_cmdq_init() has already created the cmdq in FW, the command queue is left registered in FW while the driver treats it as uninitialized (db_id remains 0). On the next submission attempt the driver tries to register the same cmdq again, which fails because FW already has an entry for it. Fix by calling ivpu_jsm_hws_destroy_cmdq() on error paths to properly unwind FW state and allow subsequent registration attempts to succeed. Fixes: 465a3914b254 ("accel/ivpu: Add API for command queue create/destroy/submit") Reviewed-by: Andrzej Kacprowski Signed-off-by: Karol Wachowski Link: https://patch.msgid.link/20260611055140.948684-1-karol.wachowski@linux.intel.com --- drivers/accel/ivpu/ivpu_job.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/drivers/accel/ivpu/ivpu_job.c b/drivers/accel/ivpu/ivpu_job.c index 521931d1f7fc..b24f31a8b567 100644 --- a/drivers/accel/ivpu/ivpu_job.c +++ b/drivers/accel/ivpu/ivpu_job.c @@ -208,9 +208,9 @@ static int ivpu_hws_cmdq_init(struct ivpu_file_priv *file_priv, struct ivpu_cmdq ret = ivpu_jsm_hws_set_context_sched_properties(vdev, file_priv->ctx.id, cmdq->id, priority); if (ret) - return ret; + ivpu_jsm_hws_destroy_cmdq(vdev, file_priv->ctx.id, cmdq->id); - return 0; + return ret; } static int ivpu_register_db(struct ivpu_file_priv *file_priv, struct ivpu_cmdq *cmdq) @@ -281,10 +281,10 @@ static int ivpu_cmdq_register(struct ivpu_file_priv *file_priv, struct ivpu_cmdq } ret = ivpu_register_db(file_priv, cmdq); - if (ret) - return ret; + if (ret && vdev->fw->sched_mode == VPU_SCHEDULING_MODE_HW) + ivpu_jsm_hws_destroy_cmdq(vdev, file_priv->ctx.id, cmdq->id); - return 0; + return ret; } static int ivpu_cmdq_unregister(struct ivpu_file_priv *file_priv, struct ivpu_cmdq *cmdq) From 90c0486a82e27393f9eaf3bb350f51a0bd38cb6b Mon Sep 17 00:00:00 2001 From: Jani Nikula Date: Wed, 10 Jun 2026 17:15:49 +0300 Subject: [PATCH 012/297] drm/displayid: fix Tiled Display Topology ID size The Tiled Display Topology ID of a DisplayID Tiled Display Topology Data Block consists of three fields: - Tiled Display Manufacturer/Vendor ID Field (3 bytes) - Tiled Display Product ID Code Field (2 bytes) - Tiled Display Serial Number Field (4 bytes) i.e. a total of 9 bytes, not 8. The DisplayID Tiled Display Topology ID is used as the tile group identifier. Update both struct displayid_tiled_block topology_id member and struct drm_tile_group group_data member to full 9 bytes. The group data was missing the last byte of the serial number. I don't know whether there are known bug reports that might be linked to this, but it's plausible the last byte could be the differentiating part for the tile groups, and fewer tile groups might have been created than intended. Fixes: b49b55bd4fba ("drm/displayid: add displayid defines and edid extension (v2)") Fixes: 138f9ebb9755 ("drm: add tile_group support. (v3)") Cc: Dave Airlie Cc: stable@vger.kernel.org # v3.19+ Reviewed-by: Dave Airlie Link: https://patch.msgid.link/20260610141549.555605-1-jani.nikula@intel.com Signed-off-by: Jani Nikula --- drivers/gpu/drm/drm_connector.c | 12 ++++++------ drivers/gpu/drm/drm_displayid_internal.h | 2 +- include/drm/drm_connector.h | 6 +++--- 3 files changed, 10 insertions(+), 10 deletions(-) diff --git a/drivers/gpu/drm/drm_connector.c b/drivers/gpu/drm/drm_connector.c index 47dc53c4a738..29634757c06d 100644 --- a/drivers/gpu/drm/drm_connector.c +++ b/drivers/gpu/drm/drm_connector.c @@ -3576,7 +3576,7 @@ EXPORT_SYMBOL(drm_mode_put_tile_group); /** * drm_mode_get_tile_group - get a reference to an existing tile group * @dev: DRM device - * @topology: 8-bytes unique per monitor. + * @topology_id: 9-byte unique ID per monitor. * * Use the unique bytes to get a reference to an existing tile group. * @@ -3584,14 +3584,14 @@ EXPORT_SYMBOL(drm_mode_put_tile_group); * tile group or NULL if not found. */ struct drm_tile_group *drm_mode_get_tile_group(struct drm_device *dev, - const char topology[8]) + const char topology_id[9]) { struct drm_tile_group *tg; int id; mutex_lock(&dev->mode_config.idr_mutex); idr_for_each_entry(&dev->mode_config.tile_idr, tg, id) { - if (!memcmp(tg->group_data, topology, 8)) { + if (!memcmp(tg->group_data, topology_id, sizeof(tg->group_data))) { if (!kref_get_unless_zero(&tg->refcount)) tg = NULL; mutex_unlock(&dev->mode_config.idr_mutex); @@ -3606,7 +3606,7 @@ EXPORT_SYMBOL(drm_mode_get_tile_group); /** * drm_mode_create_tile_group - create a tile group from a displayid description * @dev: DRM device - * @topology: 8-bytes unique per monitor. + * @topology_id: 9-byte unique ID per monitor. * * Create a tile group for the unique monitor, and get a unique * identifier for the tile group. @@ -3615,7 +3615,7 @@ EXPORT_SYMBOL(drm_mode_get_tile_group); * new tile group or NULL. */ struct drm_tile_group *drm_mode_create_tile_group(struct drm_device *dev, - const char topology[8]) + const char topology_id[9]) { struct drm_tile_group *tg; int ret; @@ -3625,7 +3625,7 @@ struct drm_tile_group *drm_mode_create_tile_group(struct drm_device *dev, return NULL; kref_init(&tg->refcount); - memcpy(tg->group_data, topology, 8); + memcpy(tg->group_data, topology_id, sizeof(tg->group_data)); tg->dev = dev; mutex_lock(&dev->mode_config.idr_mutex); diff --git a/drivers/gpu/drm/drm_displayid_internal.h b/drivers/gpu/drm/drm_displayid_internal.h index 5b1b32f73516..4590d6a3d821 100644 --- a/drivers/gpu/drm/drm_displayid_internal.h +++ b/drivers/gpu/drm/drm_displayid_internal.h @@ -109,7 +109,7 @@ struct displayid_tiled_block { u8 topo[3]; u8 tile_size[4]; u8 tile_pixel_bezel[5]; - u8 topology_id[8]; + u8 topology_id[9]; } __packed; struct displayid_detailed_timings_1 { diff --git a/include/drm/drm_connector.h b/include/drm/drm_connector.h index f83f28cae207..877b5ca87e95 100644 --- a/include/drm/drm_connector.h +++ b/include/drm/drm_connector.h @@ -2608,13 +2608,13 @@ struct drm_tile_group { struct kref refcount; struct drm_device *dev; int id; - u8 group_data[8]; + u8 group_data[9]; }; struct drm_tile_group *drm_mode_create_tile_group(struct drm_device *dev, - const char topology[8]); + const char topology_id[9]); struct drm_tile_group *drm_mode_get_tile_group(struct drm_device *dev, - const char topology[8]); + const char topology_id[9]); void drm_mode_put_tile_group(struct drm_device *dev, struct drm_tile_group *tg); From 9108f7fa493b4c88cbc09503e0c164244456bad5 Mon Sep 17 00:00:00 2001 From: Francesco Lavra Date: Tue, 16 Jun 2026 13:44:29 +0200 Subject: [PATCH 013/297] regcache: Do not overwrite error code when finalizing cache after error During regcache initialization, if an error occurs in the cache_ops->populate callback, and if cache operations include an exit callback, the error code from populate() is overwritten with the return value from exit(). This hides the error condition from the caller of regcache_init(), and can cause NULL pointer dereferences when the regcache is later accessed. Fixes: 94a3a95f0315 ("regcache: Add ->populate() callback to separate from ->init()") Signed-off-by: Francesco Lavra Link: https://patch.msgid.link/20260616114429.1852456-1-flavra@baylibre.com Signed-off-by: Mark Brown --- drivers/base/regmap/regcache.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/base/regmap/regcache.c b/drivers/base/regmap/regcache.c index 27616b05111c..aa8f2efed779 100644 --- a/drivers/base/regmap/regcache.c +++ b/drivers/base/regmap/regcache.c @@ -245,7 +245,7 @@ err_exit: if (map->cache_ops->exit) { dev_dbg(map->dev, "Destroying %s cache\n", map->cache_ops->name); map->lock(map->lock_arg); - ret = map->cache_ops->exit(map); + map->cache_ops->exit(map); map->unlock(map->lock_arg); } err_free_reg_defaults: From 5ce9ac1531b8e27e754a7d17fa07fa9da0d4a6b3 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= Date: Thu, 9 Apr 2026 13:08:40 +0300 Subject: [PATCH 014/297] drm/i915/mst: Call intel_pfit_compute_config() for sharpness filter MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The sharpness filter property is on the CRTC (as opposed to the connector) so the expectation is that it's usable on all output types. Since the sharpness filter is now fully integrateds into the normal pfit code intel_pfit_compute_config() must be called from the encoder .compute_config() on all relevant output types. Sharpness filter is supported on LNL+ so only HDMI and DP SST/MST outputs are actually relevant. I already took care of HDMI and DP SST, but (as usual) forgot about DP MST. Add the missing intel_pfit_compute_config() call to make the sharpness filter operational on DP MST as well. Cc: Nemesa Garg Fixes: d4686f34bbeb ("drm/i915/pfit: Call intel_pfit_compute_config() unconditionally on (e)DP/HDMI") Signed-off-by: Ville Syrjälä Link: https://patch.msgid.link/20260409100841.1907-1-ville.syrjala@linux.intel.com Reviewed-by: Nemesa Garg (cherry picked from commit ca97f5546f191bf460b3f4b59ade3ea5e7378796) Signed-off-by: Rodrigo Vivi --- drivers/gpu/drm/i915/display/intel_dp_mst.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/gpu/drm/i915/display/intel_dp_mst.c b/drivers/gpu/drm/i915/display/intel_dp_mst.c index bcdc50491347..0aa3e6b4c781 100644 --- a/drivers/gpu/drm/i915/display/intel_dp_mst.c +++ b/drivers/gpu/drm/i915/display/intel_dp_mst.c @@ -722,6 +722,10 @@ static int mst_stream_compute_config(struct intel_encoder *encoder, pipe_config->sink_format = INTEL_OUTPUT_FORMAT_RGB; pipe_config->output_format = INTEL_OUTPUT_FORMAT_RGB; + ret = intel_pfit_compute_config(pipe_config, conn_state); + if (ret) + return ret; + ret = intel_pfit_compute_config(pipe_config, conn_state); if (ret) return ret; From 31f077088e0faae6be8377741f356dea1b94ba46 Mon Sep 17 00:00:00 2001 From: Guangshuo Li Date: Fri, 12 Jun 2026 11:53:10 +0800 Subject: [PATCH 015/297] drm/i915: clear CRTC color blob pointers after dropping refs intel_crtc_put_color_blobs() drops the CRTC color blob references, but leaves the corresponding pointers unchanged. This can matter in intel_crtc_prepare_cleared_state(), which frees the old CRTC hw state before calling intel_dp_tunnel_atomic_clear_stream_bw(). The latter can fail while looking up the DP tunnel group state, for example with -EDEADLK. If that happens, the function returns without completing the cleared state preparation. The failed atomic state will then be cleared by the atomic core and intel_crtc_free_hw_state() can be called again for the same state, dropping the same blob references again. Clear the blob pointers after dropping the references so repeated cleanup of the same CRTC hw state is safe. Fixes: 77fcf58df15e ("drm/i915/dp_tunnel: Fix error handling when clearing stream BW in atomic state") Suggested-by: Imre Deak Signed-off-by: Guangshuo Li Reviewed-by: Imre Deak Signed-off-by: Imre Deak Link: https://patch.msgid.link/20260612035310.3013066-1-lgs201920130244@gmail.com (cherry picked from commit d5005addb5f68e8a0edce249506757bdc9e3d8c8) Signed-off-by: Rodrigo Vivi --- drivers/gpu/drm/i915/display/intel_atomic.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/gpu/drm/i915/display/intel_atomic.c b/drivers/gpu/drm/i915/display/intel_atomic.c index 0e4f0678c53c..9d0d47c79dd1 100644 --- a/drivers/gpu/drm/i915/display/intel_atomic.c +++ b/drivers/gpu/drm/i915/display/intel_atomic.c @@ -288,6 +288,12 @@ static void intel_crtc_put_color_blobs(struct intel_crtc_state *crtc_state) drm_property_blob_put(crtc_state->pre_csc_lut); drm_property_blob_put(crtc_state->post_csc_lut); + + crtc_state->hw.degamma_lut = NULL; + crtc_state->hw.gamma_lut = NULL; + crtc_state->hw.ctm = NULL; + crtc_state->pre_csc_lut = NULL; + crtc_state->post_csc_lut = NULL; } void intel_crtc_free_hw_state(struct intel_crtc_state *crtc_state) From 062499cc4813b5a3cbed5dd4fbe0177265858450 Mon Sep 17 00:00:00 2001 From: Imre Deak Date: Fri, 12 Jun 2026 20:26:17 +0300 Subject: [PATCH 016/297] drm/i915/mtl+: Enable PPS before PLL MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Enabling PPS after a display port's PLL is enabled leads to PLL / DDI BUF timeouts during system resuming after a long (> 45 mins) suspended state, at least on some ARL and MTL laptops, either all or some of them also containing an Nvidia GPU. Enabling PPS first and then the PLL fixes the problem for all the reporters. A similar issue is seen when enabling an external DP output on PHY B (vs. PHY A in the above eDP cases), where this change will not have any effect (since no PPS is used in that case). There isn't any direct connection between PPS and PLL, so the fix for eDP works by some side-effect only. However Bspec does seem to require enabling PPS first, so let's do that. Further investigation continues on the actual root cause and a cure for external panels. Fixes: 1a7fad2aea74 ("drm/i915/cx0: Enable dpll framework for MTL+") Closes: https://gitlab.freedesktop.org/drm/i915/kernel/-/work_items/16098 Closes: https://gitlab.freedesktop.org/drm/i915/kernel/-/work_items/16064 Closes: https://gitlab.freedesktop.org/drm/i915/kernel/-/work_items/16042 Cc: Mika Kahola Cc: stable@vger.kernel.org # v7.0+ Tested-by: Jouni Högander Tested-by: Marco Nenciarini Reviewed-by: Suraj Kandpal Signed-off-by: Imre Deak Link: https://patch.msgid.link/20260612172617.3427027-1-imre.deak@intel.com (cherry picked from commit 28783a274e886dd6da61419be6020bd9d0384e9f) Signed-off-by: Rodrigo Vivi --- drivers/gpu/drm/i915/display/intel_ddi.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/i915/display/intel_ddi.c b/drivers/gpu/drm/i915/display/intel_ddi.c index 205978c9feb6..6296635c4e79 100644 --- a/drivers/gpu/drm/i915/display/intel_ddi.c +++ b/drivers/gpu/drm/i915/display/intel_ddi.c @@ -2652,9 +2652,6 @@ static void mtl_ddi_pre_enable_dp(struct intel_atomic_state *state, /* 3. Select Thunderbolt */ mtl_port_buf_ctl_io_selection(encoder); - /* 4. Enable Panel Power if PPS is required */ - intel_pps_on(intel_dp); - /* 5. Enable the port PLL */ intel_ddi_enable_clock(encoder, crtc_state); @@ -3708,6 +3705,14 @@ intel_ddi_pre_pll_enable(struct intel_atomic_state *state, else if (display->platform.geminilake || display->platform.broxton) bxt_dpio_phy_set_lane_optim_mask(encoder, crtc_state->lane_lat_optim_mask); + + /* + * There is no direct connection between the PLL and PPS, however + * enabling PPS before PLL is required to avoid PLL/DDI BUF timeouts + * during system resume. Do that matching the Bspec order as well. + */ + if (DISPLAY_VER(display) >= 14) + intel_pps_on(&dig_port->dp); } static void adlp_tbt_to_dp_alt_switch_wa(struct intel_encoder *encoder) From b4b15e4f12ad1dd83b69d453ef826553917eb8cb Mon Sep 17 00:00:00 2001 From: Daniele Ceraolo Spurio Date: Fri, 29 May 2026 12:36:02 -0700 Subject: [PATCH 017/297] Revert "drm/xe/nvls: Define GuC firmware for NVL-S" This reverts commit 4e88de313ff4d1c67b644b1f39f9fb4089711b71. The early GuC FW definition meant for our CI branch was accidentally merged to the drm-xe-next branch instead. This GuC FW will never be released to linux-firmware, so we do not want the definition to be available in the mainline Linux codebase. Fixes: 4e88de313ff4 ("drm/xe/nvls: Define GuC firmware for NVL-S") Signed-off-by: Daniele Ceraolo Spurio Cc: Julia Filipchuk Cc: Rodrigo Vivi Cc: Matt Roper Cc: stable@vger.kernel.org # v7.0+ Reviewed-by: Rodrigo Vivi Link: https://patch.msgid.link/20260529193558.185436-11-daniele.ceraolospurio@intel.com Signed-off-by: Rodrigo Vivi (cherry picked from commit 65b8e0ac86e48cfc9128c04dfc53ea3395d030dd) Signed-off-by: Matthew Brost --- drivers/gpu/drm/xe/xe_uc_fw.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/gpu/drm/xe/xe_uc_fw.c b/drivers/gpu/drm/xe/xe_uc_fw.c index df2aa196f6f9..3f08a3b54062 100644 --- a/drivers/gpu/drm/xe/xe_uc_fw.c +++ b/drivers/gpu/drm/xe/xe_uc_fw.c @@ -115,7 +115,6 @@ struct fw_blobs_by_type { #define XE_GT_TYPE_ANY XE_GT_TYPE_UNINITIALIZED #define XE_GUC_FIRMWARE_DEFS(fw_def, mmp_ver, major_ver) \ - fw_def(NOVALAKE_S, GT_TYPE_ANY, mmp_ver(xe, guc, nvl, 70, 55, 4)) \ fw_def(PANTHERLAKE, GT_TYPE_ANY, major_ver(xe, guc, ptl, 70, 54, 0)) \ fw_def(BATTLEMAGE, GT_TYPE_ANY, major_ver(xe, guc, bmg, 70, 54, 0)) \ fw_def(LUNARLAKE, GT_TYPE_ANY, major_ver(xe, guc, lnl, 70, 53, 0)) \ From 65b1f95802f90fea0283f226317dc02dba494c81 Mon Sep 17 00:00:00 2001 From: Tangudu Tilak Tirumalesh Date: Wed, 3 Jun 2026 12:22:15 +0530 Subject: [PATCH 018/297] Revert "drm/xe: Skip exec queue schedule toggle if queue is idle during suspend" This reverts commit 8533051ce92015e9cc6f75e0d52119b9d91610b6. The idle-skip optimization bypasses GuC suspend, so the GPU may not perform the context switch that flushes TLB entries for invalidated userptr VMAs. In LR/preempt-fence VM mode, this can lead to missed TLB invalidation and page faults during userptr invalidation tests. Restore unconditional schedule toggling on suspend so the context-switch TLB flush is always performed. This optimization will be reintroduced with a fix that does not skip suspend in LR/preempt-fence VM mode. Fixes: 8533051ce920 ("drm/xe: Skip exec queue schedule toggle if queue is idle during suspend") Cc: stable@vger.kernel.org # v7.0+ Suggested-by: Thomas Hellstrom Signed-off-by: Tangudu Tilak Tirumalesh Reviewed-by: Thomas Hellstrom Signed-off-by: Daniele Ceraolo Spurio Link: https://patch.msgid.link/20260603065217.3131066-2-tilak.tirumalesh.tangudu@intel.com (cherry picked from commit 6a1e7934d9a6cf46aecae00a99c2603d1295e170) Signed-off-by: Matthew Brost --- drivers/gpu/drm/xe/xe_exec_queue.h | 17 -------- drivers/gpu/drm/xe/xe_guc_submit.c | 55 ++----------------------- drivers/gpu/drm/xe/xe_hw_engine_group.c | 10 +---- 3 files changed, 5 insertions(+), 77 deletions(-) diff --git a/drivers/gpu/drm/xe/xe_exec_queue.h b/drivers/gpu/drm/xe/xe_exec_queue.h index a82d99bd77bc..0225426c57b0 100644 --- a/drivers/gpu/drm/xe/xe_exec_queue.h +++ b/drivers/gpu/drm/xe/xe_exec_queue.h @@ -162,21 +162,4 @@ int xe_exec_queue_contexts_hwsp_rebase(struct xe_exec_queue *q, void *scratch); struct xe_lrc *xe_exec_queue_lrc(struct xe_exec_queue *q); struct xe_lrc *xe_exec_queue_get_lrc(struct xe_exec_queue *q, u16 idx); -/** - * xe_exec_queue_idle_skip_suspend() - Can exec queue skip suspend - * @q: The exec_queue - * - * If an exec queue is not parallel and is idle, the suspend steps can be - * skipped in the submission backend immediatley signaling the suspend fence. - * Parallel queues cannot skip this step due to limitations in the submission - * backend. - * - * Return: True if exec queue is idle and can skip suspend steps, False - * otherwise - */ -static inline bool xe_exec_queue_idle_skip_suspend(struct xe_exec_queue *q) -{ - return !xe_exec_queue_is_parallel(q) && xe_exec_queue_is_idle(q); -} - #endif diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c index ab501513d806..d1ab66ca1856 100644 --- a/drivers/gpu/drm/xe/xe_guc_submit.c +++ b/drivers/gpu/drm/xe/xe_guc_submit.c @@ -71,7 +71,6 @@ exec_queue_to_guc(struct xe_exec_queue *q) #define EXEC_QUEUE_STATE_WEDGED (1 << 8) #define EXEC_QUEUE_STATE_BANNED (1 << 9) #define EXEC_QUEUE_STATE_PENDING_RESUME (1 << 10) -#define EXEC_QUEUE_STATE_IDLE_SKIP_SUSPEND (1 << 11) static bool exec_queue_registered(struct xe_exec_queue *q) { @@ -218,21 +217,6 @@ static void clear_exec_queue_pending_resume(struct xe_exec_queue *q) atomic_and(~EXEC_QUEUE_STATE_PENDING_RESUME, &q->guc->state); } -static bool exec_queue_idle_skip_suspend(struct xe_exec_queue *q) -{ - return atomic_read(&q->guc->state) & EXEC_QUEUE_STATE_IDLE_SKIP_SUSPEND; -} - -static void set_exec_queue_idle_skip_suspend(struct xe_exec_queue *q) -{ - atomic_or(EXEC_QUEUE_STATE_IDLE_SKIP_SUSPEND, &q->guc->state); -} - -static void clear_exec_queue_idle_skip_suspend(struct xe_exec_queue *q) -{ - atomic_and(~EXEC_QUEUE_STATE_IDLE_SKIP_SUSPEND, &q->guc->state); -} - static bool exec_queue_killed_or_banned_or_wedged(struct xe_exec_queue *q) { return (atomic_read(&q->guc->state) & @@ -1157,7 +1141,7 @@ static void submit_exec_queue(struct xe_exec_queue *q, struct xe_sched_job *job) if (!job->restore_replay || job->last_replay) { if (xe_exec_queue_is_parallel(q)) wq_item_append(q); - else if (!exec_queue_idle_skip_suspend(q)) + else xe_lrc_set_ring_tail(lrc, lrc->ring.tail); job->last_replay = false; } @@ -1812,10 +1796,9 @@ static void __guc_exec_queue_process_msg_suspend(struct xe_sched_msg *msg) { struct xe_exec_queue *q = msg->private_data; struct xe_guc *guc = exec_queue_to_guc(q); - bool idle_skip_suspend = xe_exec_queue_idle_skip_suspend(q); - if (!idle_skip_suspend && guc_exec_queue_allowed_to_change_state(q) && - !exec_queue_suspended(q) && exec_queue_enabled(q)) { + if (guc_exec_queue_allowed_to_change_state(q) && !exec_queue_suspended(q) && + exec_queue_enabled(q)) { wait_event(guc->ct.wq, vf_recovery(guc) || ((q->guc->resume_time != RESUME_PENDING || xe_guc_read_stopped(guc)) && !exec_queue_pending_disable(q))); @@ -1834,33 +1817,11 @@ static void __guc_exec_queue_process_msg_suspend(struct xe_sched_msg *msg) disable_scheduling(q, false); } } else if (q->guc->suspend_pending) { - if (idle_skip_suspend) - set_exec_queue_idle_skip_suspend(q); set_exec_queue_suspended(q); suspend_fence_signal(q); } } -static void sched_context(struct xe_exec_queue *q) -{ - struct xe_guc *guc = exec_queue_to_guc(q); - struct xe_lrc *lrc = q->lrc[0]; - u32 action[] = { - XE_GUC_ACTION_SCHED_CONTEXT, - q->guc->id, - }; - - xe_gt_assert(guc_to_gt(guc), !xe_exec_queue_is_parallel(q)); - xe_gt_assert(guc_to_gt(guc), !exec_queue_destroyed(q)); - xe_gt_assert(guc_to_gt(guc), exec_queue_registered(q)); - xe_gt_assert(guc_to_gt(guc), !exec_queue_pending_disable(q)); - - trace_xe_exec_queue_submit(q); - - xe_lrc_set_ring_tail(lrc, lrc->ring.tail); - xe_guc_ct_send(&guc->ct, action, ARRAY_SIZE(action), 0, 0); -} - static void __guc_exec_queue_process_msg_resume(struct xe_sched_msg *msg) { struct xe_exec_queue *q = msg->private_data; @@ -1868,22 +1829,12 @@ static void __guc_exec_queue_process_msg_resume(struct xe_sched_msg *msg) if (guc_exec_queue_allowed_to_change_state(q)) { clear_exec_queue_suspended(q); if (!exec_queue_enabled(q)) { - if (exec_queue_idle_skip_suspend(q)) { - struct xe_lrc *lrc = q->lrc[0]; - - clear_exec_queue_idle_skip_suspend(q); - xe_lrc_set_ring_tail(lrc, lrc->ring.tail); - } q->guc->resume_time = RESUME_PENDING; set_exec_queue_pending_resume(q); enable_scheduling(q); - } else if (exec_queue_idle_skip_suspend(q)) { - clear_exec_queue_idle_skip_suspend(q); - sched_context(q); } } else { clear_exec_queue_suspended(q); - clear_exec_queue_idle_skip_suspend(q); } } diff --git a/drivers/gpu/drm/xe/xe_hw_engine_group.c b/drivers/gpu/drm/xe/xe_hw_engine_group.c index 4c2b113364d3..02cf32ae5aa9 100644 --- a/drivers/gpu/drm/xe/xe_hw_engine_group.c +++ b/drivers/gpu/drm/xe/xe_hw_engine_group.c @@ -208,21 +208,15 @@ static int xe_hw_engine_group_suspend_faulting_lr_jobs(struct xe_hw_engine_group lockdep_assert_held_write(&group->mode_sem); list_for_each_entry(q, &group->exec_queue_list, hw_engine_group_link) { - bool idle_skip_suspend; if (!xe_vm_in_fault_mode(q->vm)) continue; - idle_skip_suspend = xe_exec_queue_idle_skip_suspend(q); - if (!idle_skip_suspend && has_deps) + if (has_deps) return -EAGAIN; xe_gt_stats_incr(q->gt, XE_GT_STATS_ID_HW_ENGINE_GROUP_SUSPEND_LR_QUEUE_COUNT, 1); - if (idle_skip_suspend) - xe_gt_stats_incr(q->gt, - XE_GT_STATS_ID_HW_ENGINE_GROUP_SKIP_LR_QUEUE_COUNT, 1); - - need_resume |= !idle_skip_suspend; + need_resume = true; q->ops->suspend(q); gt = q->gt; } From 1141574cb85db5226042b3d903157f95bfc631b1 Mon Sep 17 00:00:00 2001 From: Tangudu Tilak Tirumalesh Date: Wed, 3 Jun 2026 12:22:16 +0530 Subject: [PATCH 019/297] drm/xe: Clear pending_disable before signaling suspend fence In the schedule-disable done path for suspend, we signal the suspend fence before clearing pending_disable. That wakeup can let suspend_wait complete and resume be queued immediately. The resume path may then reach enable_scheduling() while pending_disable is still set and hit the !exec_queue_pending_disable(q) assertion. Fix this by clearing pending_disable before signaling the suspend fence, so any resumed transition observes a consistent state. Fixes: 87651f31ae4e ("drm/xe/guc_submit: fix race around suspend_pending") Cc: stable@vger.kernel.org # v7.0+ Signed-off-by: Tangudu Tilak Tirumalesh Reviewed-by: Thomas Hellstrom Signed-off-by: Daniele Ceraolo Spurio Link: https://patch.msgid.link/20260603065217.3131066-3-tilak.tirumalesh.tangudu@intel.com (cherry picked from commit 4b1ae138b0e103d753773956a84eebc2edbf62c4) Signed-off-by: Matthew Brost --- drivers/gpu/drm/xe/xe_guc_submit.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c index d1ab66ca1856..122a0983df18 100644 --- a/drivers/gpu/drm/xe/xe_guc_submit.c +++ b/drivers/gpu/drm/xe/xe_guc_submit.c @@ -2791,8 +2791,8 @@ static void handle_sched_done(struct xe_guc *guc, struct xe_exec_queue *q, xe_gt_assert(guc_to_gt(guc), exec_queue_pending_disable(q)); if (q->guc->suspend_pending) { - suspend_fence_signal(q); clear_exec_queue_pending_disable(q); + suspend_fence_signal(q); } else { if (exec_queue_banned(q)) { smp_wmb(); From 65280af331aa15eab7012bd7f07823be13754ba2 Mon Sep 17 00:00:00 2001 From: Niranjana Vishwanathapura Date: Wed, 3 Jun 2026 16:39:47 -0700 Subject: [PATCH 020/297] drm/xe/multi_queue: skip submit when primary queue is suspended Return early in submit path when the multi-queue primary exec queue is suspended to avoid submitting while suspended. v2: Remove idle_skip_suspend fix as that feature is being reverted here https://patchwork.freedesktop.org/series/167262/ Fixes: bc5775c59258 ("drm/xe/multi_queue: Add GuC interface for multi queue support") Cc: stable@vger.kernel.org # v7.0+ Assisted-by: GitHub-Copilot:claude-sonnet-4.6 Reviewed-by: Daniele Ceraolo Spurio Signed-off-by: Niranjana Vishwanathapura Link: https://patch.msgid.link/20260603233946.863663-2-niranjana.vishwanathapura@intel.com (cherry picked from commit b7fb55cc3364ca128cfff9d50649ffd4327cd01e) Signed-off-by: Matthew Brost --- drivers/gpu/drm/xe/xe_guc_submit.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c index 122a0983df18..4b247a3019d2 100644 --- a/drivers/gpu/drm/xe/xe_guc_submit.c +++ b/drivers/gpu/drm/xe/xe_guc_submit.c @@ -1151,9 +1151,12 @@ static void submit_exec_queue(struct xe_exec_queue *q, struct xe_sched_job *job) /* * All queues in a multi-queue group will use the primary queue - * of the group to interface with GuC. + * of the group to interface with GuC. If primay is suspended, + * just return. Jobs will get scheduled once primary is resumed. */ q = xe_exec_queue_multi_queue_primary(q); + if (exec_queue_suspended(q)) + return; if (!exec_queue_enabled(q) && !exec_queue_suspended(q)) { action[len++] = XE_GUC_ACTION_SCHED_CONTEXT_MODE_SET; From 45fa032b68570a9ccd80328a857ac5872217be92 Mon Sep 17 00:00:00 2001 From: Raag Jadav Date: Tue, 2 Jun 2026 10:18:42 +0530 Subject: [PATCH 021/297] drm/xe/drm_ras: Make counter allocation drm managed cleanup_node_param() is not registered for previous node in case of counter allocation failure, which results in stale memory of previous node that isn't cleaned up on unwind. Fix this using drm managed allocation, which is guaranteed to be cleaned up on unwind. Fixes: b40db12b542f ("drm/xe/xe_drm_ras: Add support for XE DRM RAS") Signed-off-by: Raag Jadav Reviewed-by: Riana Tauro Link: https://patch.msgid.link/20260602044919.702209-3-raag.jadav@intel.com Signed-off-by: Matt Roper (cherry picked from commit 58d77c77ea0c5cb2b755ebe23e973c8272acd896) Signed-off-by: Matthew Brost --- drivers/gpu/drm/xe/xe_drm_ras.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/gpu/drm/xe/xe_drm_ras.c b/drivers/gpu/drm/xe/xe_drm_ras.c index c21c8b428de6..c1d5ac198a7c 100644 --- a/drivers/gpu/drm/xe/xe_drm_ras.c +++ b/drivers/gpu/drm/xe/xe_drm_ras.c @@ -80,7 +80,7 @@ static struct xe_drm_ras_counter *allocate_and_copy_counters(struct xe_device *x struct xe_drm_ras_counter *counter; int i; - counter = kcalloc(DRM_XE_RAS_ERR_COMP_MAX, sizeof(*counter), GFP_KERNEL); + counter = drmm_kcalloc(&xe->drm, DRM_XE_RAS_ERR_COMP_MAX, sizeof(*counter), GFP_KERNEL); if (!counter) return ERR_PTR(-ENOMEM); @@ -135,7 +135,6 @@ static void cleanup_node_param(struct xe_drm_ras *ras, const enum drm_xe_ras_err { struct drm_ras_node *node = &ras->node[severity]; - kfree(ras->info[severity]); ras->info[severity] = NULL; kfree(node->device_name); From 042f1d5f20d63fb9b0e2fbba97648d16fe1a845d Mon Sep 17 00:00:00 2001 From: Raag Jadav Date: Tue, 2 Jun 2026 10:18:43 +0530 Subject: [PATCH 022/297] drm/xe/drm_ras: Add per node cleanup action cleanup_node_param() is not registered for previous node in case of counter allocation failure, which results in stale memory of previous node that isn't cleaned up on unwind. Add per node cleanup action which guarantees cleanup on unwind and also simplifies the cleanup logic. Fixes: b40db12b542f ("drm/xe/xe_drm_ras: Add support for XE DRM RAS") Signed-off-by: Raag Jadav Reviewed-by: Riana Tauro Link: https://patch.msgid.link/20260602044919.702209-4-raag.jadav@intel.com Signed-off-by: Matt Roper (cherry picked from commit 67fc5543d8274b2fcbef87734fad0469358f4478) Signed-off-by: Matthew Brost --- drivers/gpu/drm/xe/xe_drm_ras.c | 58 +++++++++++++-------------------- 1 file changed, 23 insertions(+), 35 deletions(-) diff --git a/drivers/gpu/drm/xe/xe_drm_ras.c b/drivers/gpu/drm/xe/xe_drm_ras.c index c1d5ac198a7c..cd236f53699e 100644 --- a/drivers/gpu/drm/xe/xe_drm_ras.c +++ b/drivers/gpu/drm/xe/xe_drm_ras.c @@ -131,53 +131,47 @@ static int assign_node_params(struct xe_device *xe, struct drm_ras_node *node, return 0; } -static void cleanup_node_param(struct xe_drm_ras *ras, const enum drm_xe_ras_error_severity severity) +static void cleanup_node_param(struct drm_ras_node *node) { - struct drm_ras_node *node = &ras->node[severity]; - - ras->info[severity] = NULL; - kfree(node->device_name); node->device_name = NULL; } +static void cleanup_node(struct drm_device *drm, void *node) +{ + drm_ras_node_unregister(node); + cleanup_node_param(node); +} + static int register_nodes(struct xe_device *xe) { struct xe_drm_ras *ras = &xe->ras; - int i; + struct drm_ras_node *node; + int i, ret; for_each_error_severity(i) { - struct drm_ras_node *node = &ras->node[i]; - int ret; + node = &ras->node[i]; ret = assign_node_params(xe, node, i); - if (ret) { - cleanup_node_param(ras, i); - return ret; - } + if (ret) + goto free_param; ret = drm_ras_node_register(node); - if (ret) { - cleanup_node_param(ras, i); - return ret; - } + if (ret) + goto free_param; + + ret = drmm_add_action_or_reset(&xe->drm, cleanup_node, node); + if (ret) + goto null_info; } return 0; -} -static void xe_drm_ras_unregister_nodes(struct drm_device *device, void *arg) -{ - struct xe_device *xe = arg; - struct xe_drm_ras *ras = &xe->ras; - int i; - - for_each_error_severity(i) { - struct drm_ras_node *node = &ras->node[i]; - - drm_ras_node_unregister(node); - cleanup_node_param(ras, i); - } +free_param: + cleanup_node_param(node); +null_info: + ras->info[i] = NULL; + return ret; } /** @@ -206,11 +200,5 @@ int xe_drm_ras_init(struct xe_device *xe) return err; } - err = drmm_add_action_or_reset(&xe->drm, xe_drm_ras_unregister_nodes, xe); - if (err) { - drm_err(&xe->drm, "Failed to add action for Xe DRM RAS (%pe)\n", ERR_PTR(err)); - return err; - } - return 0; } From d46319bc8273c1018fa532a383eb515ee1b1de4b Mon Sep 17 00:00:00 2001 From: Raag Jadav Date: Tue, 2 Jun 2026 10:18:44 +0530 Subject: [PATCH 023/297] drm/xe/hw_error: Use HW_ERR prefix in log Hardware errors should be logged with HW_ERR prefix. Make them consistent with existing logs. Fixes: 01aab7e1c9d4 ("drm/xe/xe_hw_error: Add support for PVC SoC errors") Signed-off-by: Raag Jadav Reviewed-by: Riana Tauro Link: https://patch.msgid.link/20260602044919.702209-5-raag.jadav@intel.com Signed-off-by: Matt Roper (cherry picked from commit ad60a618c49fef07d1860bfb1091140d29f5eddb) Signed-off-by: Matthew Brost --- drivers/gpu/drm/xe/xe_hw_error.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/drivers/gpu/drm/xe/xe_hw_error.c b/drivers/gpu/drm/xe/xe_hw_error.c index 5135e8e4093f..4b72959b2276 100644 --- a/drivers/gpu/drm/xe/xe_hw_error.c +++ b/drivers/gpu/drm/xe/xe_hw_error.c @@ -223,9 +223,9 @@ static void log_hw_error(struct xe_tile *tile, const char *name, struct xe_device *xe = tile_to_xe(tile); if (severity == DRM_XE_RAS_ERR_SEV_CORRECTABLE) - drm_warn(&xe->drm, "%s %s detected\n", name, severity_str); + drm_warn(&xe->drm, HW_ERR "%s %s detected\n", name, severity_str); else - drm_err_ratelimited(&xe->drm, "%s %s detected\n", name, severity_str); + drm_err_ratelimited(&xe->drm, HW_ERR "%s %s detected\n", name, severity_str); } static void log_gt_err(struct xe_tile *tile, const char *name, int i, u32 err, @@ -235,10 +235,10 @@ static void log_gt_err(struct xe_tile *tile, const char *name, int i, u32 err, struct xe_device *xe = tile_to_xe(tile); if (severity == DRM_XE_RAS_ERR_SEV_CORRECTABLE) - drm_warn(&xe->drm, "%s %s detected, ERROR_STAT_GT_VECTOR%d:0x%08x\n", + drm_warn(&xe->drm, HW_ERR "%s %s detected, ERROR_STAT_GT_VECTOR%d:0x%08x\n", name, severity_str, i, err); else - drm_err_ratelimited(&xe->drm, "%s %s detected, ERROR_STAT_GT_VECTOR%d:0x%08x\n", + drm_err_ratelimited(&xe->drm, HW_ERR "%s %s detected, ERROR_STAT_GT_VECTOR%d:0x%08x\n", name, severity_str, i, err); } @@ -255,9 +255,9 @@ static void log_soc_error(struct xe_tile *tile, const char * const *reg_info, if (strcmp(name, "Undefined")) { if (severity == DRM_XE_RAS_ERR_SEV_CORRECTABLE) - drm_warn(&xe->drm, "%s SOC %s detected", name, severity_str); + drm_warn(&xe->drm, HW_ERR "%s SOC %s detected", name, severity_str); else - drm_err_ratelimited(&xe->drm, "%s SOC %s detected", name, severity_str); + drm_err_ratelimited(&xe->drm, HW_ERR "%s SOC %s detected", name, severity_str); atomic_inc(&info[index].counter); } } From f2d238408db2b963951f0f2ae70ff7f9e337b540 Mon Sep 17 00:00:00 2001 From: Tangudu Tilak Tirumalesh Date: Mon, 8 Jun 2026 21:57:44 +0530 Subject: [PATCH 024/297] drm/xe: include all registered queues in TLB invalidation MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Context-based TLB invalidation currently selects only scheduling-active exec queues via q->ops->active(). During rebind flows, queues may be suspended (or transitioning through resume) while still owning valid translations, causing them to be skipped from invalidation and leading to missed TLB invalidations on LR rebinds. The underlying issue is a TOCTOU: q->guc->state bits are flipped lock-free from enable_scheduling(), disable_scheduling{,_deregister}(), the suspend/resume sched-msg handlers, handle_sched_done(), and guc_exec_queue_stop(); nothing in send_tlb_inval_ctx_ppgtt() serializes against them, so any state-based predicate can race. Include all the registered queues so that TLB invalidations are not missed. This is race-free because list membership on vm->exec_queues.list is stable under vm->exec_queues.lock held by the caller. The performance impact is expected to be minimal and harmless. If it does turn out to be a concern, we can come back with a race-safe solution to ignore certain queues. Fixes: 6cdaa5346d6f ("drm/xe: Add context-based invalidation to GuC TLB invalidation backend") Assisted-by: Claude:claude-opus-4.6 Suggested-by: Thomas Hellstrom Signed-off-by: Tangudu Tilak Tirumalesh Reviewed-by: Thomas Hellström Reviewed-by: Matthew Brost Link: https://patch.msgid.link/20260608162745.338725-2-tilak.tirumalesh.tangudu@intel.com Signed-off-by: Shuicheng Lin (cherry picked from commit aa625e1e9f0710e424fe4f0e3f032807df81b5b0) Signed-off-by: Matthew Brost --- drivers/gpu/drm/xe/xe_guc_tlb_inval.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/xe/xe_guc_tlb_inval.c b/drivers/gpu/drm/xe/xe_guc_tlb_inval.c index ced58f46f846..cf6d106e6036 100644 --- a/drivers/gpu/drm/xe/xe_guc_tlb_inval.c +++ b/drivers/gpu/drm/xe/xe_guc_tlb_inval.c @@ -255,9 +255,8 @@ static int send_tlb_inval_ctx_ppgtt(struct xe_tlb_inval *tlb_inval, u32 seqno, #undef EXEC_QUEUE_COUNT_FULL_THRESHOLD /* - * Move exec queues to a temporary list to issue invalidations. The exec - * queue must active and a reference must be taken to prevent concurrent - * deregistrations. + * Move exec queues to a temporary list to issue invalidations. A + * reference must be taken to prevent concurrent deregistrations. * * List modification is safe because we hold 'vm->exec_queues.lock' for * reading, which prevents external modifications. Using a per-GT list @@ -266,7 +265,7 @@ static int send_tlb_inval_ctx_ppgtt(struct xe_tlb_inval *tlb_inval, u32 seqno, */ list_for_each_entry_safe(q, next, &vm->exec_queues.list[id], vm_exec_queue_link) { - if (q->ops->active(q) && xe_exec_queue_get_unless_zero(q)) { + if (xe_exec_queue_get_unless_zero(q)) { last_q = q; list_move_tail(&q->vm_exec_queue_link, &tlb_inval_list); } From 0b837315ca0adc317e5c8a9c7e484a0e29199b9b Mon Sep 17 00:00:00 2001 From: Wentao Liang Date: Wed, 10 Jun 2026 10:27:05 -0700 Subject: [PATCH 025/297] drm/xe: fix refcount leak in xe_range_fence_insert() xe_range_fence_insert() acquires a reference on fence via dma_fence_get() and stores it in rfence->fence. It then calls dma_fence_add_callback() and handles two cases: when the callback is successfully registered (err == 0) the fence is transferred to the tree for later cleanup; when the fence is already signaled (err == -ENOENT) it manually drops the extra reference with dma_fence_put(fence). However, dma_fence_add_callback() can fail with other errors (e.g. -EINVAL) and in that case the code falls through to the free: label without releasing the acquired reference, leaking it. Fix the leak by adding an else branch that calls dma_fence_put() before jumping to free: for any error other than -ENOENT. Fixes: 845f64bdbfc9 ("drm/xe: Introduce a range-fence utility") Signed-off-by: Wentao Liang Reviewed-by: Matthew Brost Signed-off-by: Matthew Brost Link: https://patch.msgid.link/20260610172705.3450560-1-matthew.brost@intel.com (cherry picked from commit 98c4a4201290823c2c5c7ba21692bd9a64b61021) Signed-off-by: Matthew Brost --- drivers/gpu/drm/xe/xe_range_fence.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/gpu/drm/xe/xe_range_fence.c b/drivers/gpu/drm/xe/xe_range_fence.c index 372378e89e98..3d8fa194a7b0 100644 --- a/drivers/gpu/drm/xe/xe_range_fence.c +++ b/drivers/gpu/drm/xe/xe_range_fence.c @@ -77,6 +77,8 @@ int xe_range_fence_insert(struct xe_range_fence_tree *tree, } else if (err == 0) { xe_range_fence_tree_insert(rfence, &tree->root); return 0; + } else { + dma_fence_put(fence); } free: From 770031ec2312bfab307d05db5469f24fd297e758 Mon Sep 17 00:00:00 2001 From: Rodrigo Vivi Date: Wed, 10 Jun 2026 11:25:49 -0400 Subject: [PATCH 026/297] drm/xe: fix job timeout recovery for unstarted jobs and kernel queues A job that GuC never scheduled (never started) indicates a GuC scheduling failure; previously such jobs were silently errored out instead of triggering a GT reset to recover. Trigger a GT reset and resubmit them, but only when the queue was not already killed or banned: an unstarted job on an already banned queue is the ban working as intended and must neither clear the ban nor kick off a reset, otherwise a banned userspace queue could be resurrected and spam GT resets. Kernel queues are always recovered this way and wedge the device once recovery attempts are exhausted, since kernel work must not silently fail. A started job that times out on a userspace VM bind queue stays banned rather than being reset and retried. The queue is banned early in the timeout handler to signal the G2H scheduling-done handler so it wakes the disable-scheduling waiter; without it the waiter sleeps the full 5s timeout. When a reset is warranted the ban is cleared before rearming so that guc_exec_queue_start() can resubmit jobs after the GT reset - a still-banned queue would block resubmission and cause an infinite TDR loop. The already-banned case is gated out before this point via skip_timeout_check, so it is unaffected. v2: (Himal) Do it for any queue type, not just kernel/migration v3: - (Sashiko and Sanjay): don't clear the ban / GT reset for already killed/banned queues on unstarted-job timeout - Update commit message - (Matt) Add Fixes tag Fixes: fe05cee4d953 ("drm/xe: Don't short circuit TDR on jobs not started") Cc: Matthew Auld Cc: Matthew Brost Cc: Sanjay Yadav Cc: Himal Prasad Ghimiray Assisted-by: GitHub-Copilot:claude-sonnet-4.6 Assisted-by: GitHub-Copilot:claude-opus-4.8 Tested-by: Sanjay Yadav Reviewed-by: Sanjay Yadav Reviewed-by: Matthew Brost Reviewed-by: Himal Prasad Ghimiray Link: https://patch.msgid.link/20260610152548.404575-3-rodrigo.vivi@intel.com Signed-off-by: Rodrigo Vivi (cherry picked from commit b1107d085e7e8ed15ba6f80c102528a9c8a6cb0e) Signed-off-by: Matthew Brost --- drivers/gpu/drm/xe/xe_guc_submit.c | 49 +++++++++++++++++++++--------- 1 file changed, 35 insertions(+), 14 deletions(-) diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c index 4b247a3019d2..12a410458df6 100644 --- a/drivers/gpu/drm/xe/xe_guc_submit.c +++ b/drivers/gpu/drm/xe/xe_guc_submit.c @@ -157,6 +157,11 @@ static void set_exec_queue_banned(struct xe_exec_queue *q) atomic_or(EXEC_QUEUE_STATE_BANNED, &q->guc->state); } +static void clear_exec_queue_banned(struct xe_exec_queue *q) +{ + atomic_andnot(EXEC_QUEUE_STATE_BANNED, &q->guc->state); +} + static bool exec_queue_suspended(struct xe_exec_queue *q) { return atomic_read(&q->guc->state) & EXEC_QUEUE_STATE_SUSPENDED; @@ -1363,7 +1368,8 @@ static bool check_timeout(struct xe_exec_queue *q, struct xe_sched_job *job) xe_sched_job_seqno(job), xe_sched_job_lrc_seqno(job), q->guc->id); - return xe_sched_invalidate_job(job, 2); + /* GuC never scheduled this job - let the caller trigger a GT reset. */ + return true; } ctx_timestamp = lower_32_bits(xe_lrc_timestamp(q->lrc[0])); @@ -1460,6 +1466,21 @@ static void disable_scheduling(struct xe_exec_queue *q, bool immediate) G2H_LEN_DW_SCHED_CONTEXT_MODE_SET, 1); } +/* + * Recover via GT reset for a kernel queue, or for a GuC scheduling failure (job + * never started) on a queue that was not already killed or banned. An already + * banned queue must stay banned, so its unstarted jobs do not clear the ban or + * trigger a reset. + */ +static bool timeout_needs_gt_reset(struct xe_exec_queue *q, struct xe_sched_job *job, + bool skip_timeout_check) +{ + if (q->flags & EXEC_QUEUE_FLAG_KERNEL) + return true; + + return !skip_timeout_check && !xe_sched_job_started(job); +} + static enum drm_gpu_sched_stat guc_exec_queue_timedout_job(struct drm_sched_job *drm_job) { @@ -1608,19 +1629,19 @@ trigger_reset: xe_sched_job_seqno(job), xe_sched_job_lrc_seqno(job), q->guc->id, q->flags); - /* - * Kernel jobs should never fail, nor should VM jobs if they do - * somethings has gone wrong and the GT needs a reset - */ - xe_gt_WARN(q->gt, q->flags & EXEC_QUEUE_FLAG_KERNEL, - "Kernel-submitted job timed out\n"); - xe_gt_WARN(q->gt, q->flags & EXEC_QUEUE_FLAG_VM && !exec_queue_killed(q), - "VM job timed out on non-killed execqueue\n"); - if (!wedged && (q->flags & EXEC_QUEUE_FLAG_KERNEL || - (q->flags & EXEC_QUEUE_FLAG_VM && !exec_queue_killed(q)))) { - if (!xe_sched_invalidate_job(job, 2)) { - xe_gt_reset_async(q->gt); - goto rearm; + if (!wedged) { + if (timeout_needs_gt_reset(q, job, skip_timeout_check)) { + if (!xe_sched_invalidate_job(job, 2)) { + clear_exec_queue_banned(q); + xe_gt_reset_async(q->gt); + goto rearm; + } + if (q->flags & EXEC_QUEUE_FLAG_KERNEL) { + xe_gt_WARN(q->gt, true, "Kernel-submitted job timed out\n"); + xe_device_declare_wedged(gt_to_xe(q->gt)); + } + } else if (q->flags & EXEC_QUEUE_FLAG_VM && !exec_queue_killed(q)) { + xe_gt_WARN(q->gt, true, "VM job timed out on non-killed execqueue\n"); } } From 92dc59ab2a09097cdf249e0288ff9b69261761c6 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Thomas=20Hellstr=C3=B6m?= Date: Thu, 4 Jun 2026 09:45:00 +0200 Subject: [PATCH 027/297] drm/xe: Fix wa_oob codegen recipe for external module builds MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When building with 'make M=drivers/gpu/drm/xe modules', kbuild invokes scripts/Makefile.build with obj=., causing $(obj) to expand to '.'. Make normalizes './xe_gen_wa_oob' to 'xe_gen_wa_oob' when constructing the $^ automatic variable (target name normalization), so the recipe command becomes just 'xe_gen_wa_oob ...' without any path prefix, and the shell cannot find the tool. Fix by replacing $^ with explicit $(obj)/xe_gen_wa_oob and $(src)/ references in both wa_oob recipe commands. In recipe strings, make does not apply target name normalization, so $(obj)/xe_gen_wa_oob correctly expands to './xe_gen_wa_oob' and the shell can execute it. This matches the pattern already used by other DRM drivers (e.g. radeon's mkregtable). Fixes: f037e0b78e6d ("drm/xe: add xe_device_wa infrastructure") Cc: Matt Atwood Cc: Matthew Brost Cc: Rodrigo Vivi Cc: intel-xe@lists.freedesktop.org Assisted-by: GitHub_Copilot:claude-sonnet-4.6 Signed-off-by: Thomas Hellström Reviewed-by: Rodrigo Vivi Link: https://patch.msgid.link/20260604074501.172129-1-thomas.hellstrom@linux.intel.com (cherry picked from commit 3a11a63cc16660d514ff584e7551589655337e87) Signed-off-by: Matthew Brost --- drivers/gpu/drm/xe/Makefile | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/xe/Makefile b/drivers/gpu/drm/xe/Makefile index 09661f079d03..8e7b146880f4 100644 --- a/drivers/gpu/drm/xe/Makefile +++ b/drivers/gpu/drm/xe/Makefile @@ -16,14 +16,14 @@ subdir-ccflags-y += -I$(obj) -I$(src) hostprogs := xe_gen_wa_oob generated_oob := $(obj)/generated/xe_wa_oob.c $(obj)/generated/xe_wa_oob.h quiet_cmd_wa_oob = GEN $(notdir $(generated_oob)) - cmd_wa_oob = mkdir -p $(@D); $^ $(generated_oob) + cmd_wa_oob = mkdir -p $(@D); $(obj)/xe_gen_wa_oob $(src)/xe_wa_oob.rules $(generated_oob) $(obj)/generated/%_wa_oob.c $(obj)/generated/%_wa_oob.h: $(obj)/xe_gen_wa_oob \ $(src)/xe_wa_oob.rules $(call cmd,wa_oob) generated_device_oob := $(obj)/generated/xe_device_wa_oob.c $(obj)/generated/xe_device_wa_oob.h quiet_cmd_device_wa_oob = GEN $(notdir $(generated_device_oob)) - cmd_device_wa_oob = mkdir -p $(@D); $^ $(generated_device_oob) + cmd_device_wa_oob = mkdir -p $(@D); $(obj)/xe_gen_wa_oob $(src)/xe_device_wa_oob.rules $(generated_device_oob) $(obj)/generated/%_device_wa_oob.c $(obj)/generated/%_device_wa_oob.h: $(obj)/xe_gen_wa_oob \ $(src)/xe_device_wa_oob.rules $(call cmd,device_wa_oob) From ba7fd163422877ad5a5cf31306a38c07d3932b0c Mon Sep 17 00:00:00 2001 From: Matthew Brost Date: Thu, 11 Jun 2026 16:58:44 -0700 Subject: [PATCH 028/297] drm/xe: Set TTM device beneficial_order to 9 (2M) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Set the TTM device beneficial_order to 9 (2M), which is the sweet spot for Xe when attempting reclaim on system memory BOs, as it matches the large GPU page size. This ensures reclaim is attempted at the most effective order for the driver. This fixes an issue where an order-10 (4M) allocation cannot be found despite an abundance of memory. The 4M allocation triggers reclaim, unnecessarily evicting the working set and hurting performance. Since the TTM infrastructure was introduced recently, we are tagging the TTM patch as the Fixes target, even though this resolves an Xe-side problem. Fixes: 7e9c548d3709 ("drm/ttm: Allow drivers to specify maximum beneficial TTM pool size") Cc: stable@vger.kernel.org Signed-off-by: Matthew Brost Reviewed-by: Andi Shyti Reviewed-by: Thomas Hellström Link: https://patch.msgid.link/20260611235844.3725147-1-matthew.brost@intel.com (cherry picked from commit 0d81db90d364cb3d733410829118759f28957c5a) Signed-off-by: Matthew Brost --- drivers/gpu/drm/xe/xe_device.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c index d224861b6f6f..abe25aedeead 100644 --- a/drivers/gpu/drm/xe/xe_device.c +++ b/drivers/gpu/drm/xe/xe_device.c @@ -526,7 +526,8 @@ int xe_device_init_early(struct xe_device *xe) err = ttm_device_init(&xe->ttm, &xe_ttm_funcs, xe->drm.dev, xe->drm.anon_inode->i_mapping, - xe->drm.vma_offset_manager, 0); + xe->drm.vma_offset_manager, + TTM_ALLOCATION_POOL_BENEFICIAL_ORDER(get_order(SZ_2M))); if (err) return err; From 632ecc90e1ca5d3b6822bb4d08f84a175b6c42c0 Mon Sep 17 00:00:00 2001 From: Tejas Upadhyay Date: Fri, 12 Jun 2026 12:34:02 +0530 Subject: [PATCH 029/297] drm/xe/guc: Fix buffer overflow in steered register list allocation The size calculation for the steered register extarray uses only the geometry DSS mask (g_dss_mask) to determine the number of entries to allocate: total = bitmap_weight(gt->fuse_topo.g_dss_mask, ...) * steer_reg_num; However, the filling loop uses for_each_dss_steering(), which iterates over for_each_dss(), defined as the union of g_dss_mask and c_dss_mask (geometry + compute DSS). On platforms with compute-only DSS bits, the loop writes past the allocated buffer, corrupting adjacent slab objects. This manifests as list_del corruption and SLUB redzone overwrites during drm_managed_release on device unbind, since the overflow corrupts the drmres list_head of neighboring allocations. Fix by computing the allocation size using the union of both DSS masks, matching the iteration pattern of for_each_dss_steering(). -- v2: - use bitmap_weighted_or() (Zhanjun) Fixes: b170d696c1e2 ("drm/xe/guc: Add XE_LP steered register lists") Closes: https://gitlab.freedesktop.org/drm/xe/kernel/-/issues/8049 Cc: Zhanjun Dong Cc: stable@vger.kernel.org Assisted-by: GitHub-Copilot:claude-opus-4.6 Reviewed-by: Zhanjun Dong Link: https://patch.msgid.link/20260612070401.543305-2-tejas.upadhyay@intel.com Signed-off-by: Tejas Upadhyay (cherry picked from commit 0a78a44f4901aa6c9263e66be7fce02282f1109f) Signed-off-by: Matthew Brost --- drivers/gpu/drm/xe/xe_guc_capture.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/xe/xe_guc_capture.c b/drivers/gpu/drm/xe/xe_guc_capture.c index 21f7caf9ea08..1a019137ddf4 100644 --- a/drivers/gpu/drm/xe/xe_guc_capture.c +++ b/drivers/gpu/drm/xe/xe_guc_capture.c @@ -461,8 +461,14 @@ static void guc_capture_alloc_steered_lists(struct xe_guc *guc) if (!list || guc->capture->extlists) return; - total = bitmap_weight(gt->fuse_topo.g_dss_mask, sizeof(gt->fuse_topo.g_dss_mask) * 8) * - guc_capture_get_steer_reg_num(guc_to_xe(guc)); + { + xe_dss_mask_t all_dss; + + total = bitmap_weighted_or(all_dss, gt->fuse_topo.g_dss_mask, + gt->fuse_topo.c_dss_mask, + XE_MAX_DSS_FUSE_BITS) * + guc_capture_get_steer_reg_num(guc_to_xe(guc)); + } if (!total) return; From 0b5ed2756d45b04669502a1f13b1657ec7664571 Mon Sep 17 00:00:00 2001 From: Brian Nguyen Date: Fri, 5 Jun 2026 22:42:58 +0000 Subject: [PATCH 030/297] drm/xe: Add compact-PT and addr mask handling for page reclaim Current implementation of generate_reclaim_entry() overlooks some differences between the different page implementations: address masking and compact 64K page handling. Address masking of each leaf varies depending on the leaf entry size. generate_reclaim_entry() is using XE_PTE_ADDR_MASK [51:12] for all leaf entries. For 2MB PTEs, bit 12 (PAT) is part of the flags so the old mask corrupts the physical address extraction. 64K pages can be represented as PS64 and a compact PT, which the latter was not handled. Compact pages aren't walked by the unbind walker, so we separately walk through the compact PT to ensure none of the leaf 64K PTEs are dropped. Previously, compact PT were causing an abort since it was considered covered and not descended into. v2: - Update 64K entry/unbind walker for 64K compact PT handling. (Matthew) - Rework calculations of reclamation and address mask size. - Add new func abstracting the error handling before generating the reclaim entry. v3: - Report finer addr granularity in abort debug print for compact. (Zongyao) - Add comments for ADDR_MASK usage. (Zongyao) - Drop existing phys_addr asserts, the new XE_PAGE_ADDR_MASK clears bits checked, so redundant asserts. (Sashiko) - WARN_ON to verify compact pt and edge pt won't be possible. Fixes: b912138df299 ("drm/xe: Create page reclaim list on unbind") Assisted-by: Sashiko-Review:gemini-3.1-pro-preview Cc: stable@vger.kernel.org Cc: Matthew Auld Suggested-by: Zongyao Bai Signed-off-by: Brian Nguyen Reviewed-by: Matthew Auld Reviewed-by: Zongyao Bai Link: https://patch.msgid.link/20260605224257.2194194-2-brian3.nguyen@intel.com Signed-off-by: Matt Roper (cherry picked from commit 669252801a4aa4098fbc5dd9dd0bd93f0625abd7) Signed-off-by: Matthew Brost --- drivers/gpu/drm/xe/regs/xe_gtt_defs.h | 6 +- drivers/gpu/drm/xe/xe_pt.c | 131 +++++++++++++++----------- 2 files changed, 82 insertions(+), 55 deletions(-) diff --git a/drivers/gpu/drm/xe/regs/xe_gtt_defs.h b/drivers/gpu/drm/xe/regs/xe_gtt_defs.h index 4d83461e538b..d6bc19ef277b 100644 --- a/drivers/gpu/drm/xe/regs/xe_gtt_defs.h +++ b/drivers/gpu/drm/xe/regs/xe_gtt_defs.h @@ -9,7 +9,11 @@ #define XELPG_GGTT_PTE_PAT0 BIT_ULL(52) #define XELPG_GGTT_PTE_PAT1 BIT_ULL(53) -#define XE_PTE_ADDR_MASK GENMASK_ULL(51, 12) +/* + * Mask for PTE address bits [51:shift]. + * shift is the lower address boundary of page. + */ +#define XE_PAGE_ADDR_MASK(shift) GENMASK_ULL(51, (shift)) #define GGTT_PTE_VFID GENMASK_ULL(11, 2) #define GUC_GGTT_TOP 0xFEE00000 diff --git a/drivers/gpu/drm/xe/xe_pt.c b/drivers/gpu/drm/xe/xe_pt.c index 2669ff5ee747..18a98667c0e6 100644 --- a/drivers/gpu/drm/xe/xe_pt.c +++ b/drivers/gpu/drm/xe/xe_pt.c @@ -1602,23 +1602,21 @@ static bool xe_pt_check_kill(u64 addr, u64 next, unsigned int level, return false; } -/* page_size = 2^(reclamation_size + XE_PTE_SHIFT) */ -#define COMPUTE_RECLAIM_ADDRESS_MASK(page_size) \ -({ \ - BUILD_BUG_ON(!__builtin_constant_p(page_size)); \ - ilog2(page_size) - XE_PTE_SHIFT; \ -}) - static int generate_reclaim_entry(struct xe_tile *tile, struct xe_page_reclaim_list *prl, u64 pte, struct xe_pt *xe_child) { struct xe_gt *gt = tile->primary_gt; struct xe_guc_page_reclaim_entry *reclaim_entries = prl->entries; - u64 phys_addr = pte & XE_PTE_ADDR_MASK; + bool is_2m = xe_child->level == 1 && (pte & XE_PDE_PS_2M); + bool is_64k = xe_child->level == 0 && ((pte & XE_PTE_PS64) || xe_child->is_compact); + u32 page_shift = is_2m ? ilog2(SZ_2M) : is_64k ? ilog2(SZ_64K) : ilog2(SZ_4K); + /* Physical address bits start at page shift: 2M->[51:21], 64K->[51:16], 4K->[51:12] */ + u64 phys_addr = pte & XE_PAGE_ADDR_MASK(page_shift); + /* Page address is relative to 4K page regardless of entry level */ u64 phys_page = phys_addr >> XE_PTE_SHIFT; int num_entries = prl->num_entries; - u32 reclamation_size; + u32 reclamation_size = page_shift - XE_PTE_SHIFT; xe_tile_assert(tile, xe_child->level <= MAX_HUGEPTE_LEVEL); xe_tile_assert(tile, reclaim_entries); @@ -1633,18 +1631,12 @@ static int generate_reclaim_entry(struct xe_tile *tile, * Page size is computed as 2^(reclamation_size + XE_PTE_SHIFT) bytes. * Only 4K, 64K (level 0), and 2M pages are supported by hardware for page reclaim */ - if (xe_child->level == 0 && !(pte & XE_PTE_PS64)) { - xe_gt_stats_incr(gt, XE_GT_STATS_ID_PRL_4K_ENTRY_COUNT, 1); - reclamation_size = COMPUTE_RECLAIM_ADDRESS_MASK(SZ_4K); /* reclamation_size = 0 */ - xe_tile_assert(tile, phys_addr % SZ_4K == 0); - } else if (xe_child->level == 0) { - xe_gt_stats_incr(gt, XE_GT_STATS_ID_PRL_64K_ENTRY_COUNT, 1); - reclamation_size = COMPUTE_RECLAIM_ADDRESS_MASK(SZ_64K); /* reclamation_size = 4 */ - xe_tile_assert(tile, phys_addr % SZ_64K == 0); - } else if (xe_child->level == 1 && pte & XE_PDE_PS_2M) { + if (is_2m) { xe_gt_stats_incr(gt, XE_GT_STATS_ID_PRL_2M_ENTRY_COUNT, 1); - reclamation_size = COMPUTE_RECLAIM_ADDRESS_MASK(SZ_2M); /* reclamation_size = 9 */ - xe_tile_assert(tile, phys_addr % SZ_2M == 0); + } else if (is_64k) { + xe_gt_stats_incr(gt, XE_GT_STATS_ID_PRL_64K_ENTRY_COUNT, 1); + } else if (xe_child->level == 0) { + xe_gt_stats_incr(gt, XE_GT_STATS_ID_PRL_4K_ENTRY_COUNT, 1); } else { xe_page_reclaim_list_abort(tile->primary_gt, prl, "unsupported PTE level=%u pte=%#llx", @@ -1665,6 +1657,48 @@ static int generate_reclaim_entry(struct xe_tile *tile, return 0; } +static int add_pte_to_prl(struct xe_tile *tile, struct xe_page_reclaim_list *prl, + struct xe_pt *xe_child, u64 pte, u64 addr) +{ + /* + * In rare scenarios, pte may not be written yet due to racy conditions. + * In such cases, invalidate the PRL and fallback to full PPC invalidation. + */ + if (!pte) { + xe_page_reclaim_list_abort(tile->primary_gt, prl, + "found zero pte at addr=%#llx", addr); + return -EINVAL; + } + + /* Ensure it is a defined page */ + xe_tile_assert(tile, xe_child->level == 0 || + (pte & (XE_PDE_PS_2M | XE_PDPE_PS_1G))); + + /* Account for NULL terminated entry on end (-1) */ + if (prl->num_entries >= XE_PAGE_RECLAIM_MAX_ENTRIES - 1) { + xe_page_reclaim_list_abort(tile->primary_gt, prl, + "overflow while adding pte=%#llx", pte); + return -ENOSPC; + } + + return generate_reclaim_entry(tile, prl, pte, xe_child); +} + +static bool add_compact_pt_prl(struct xe_tile *tile, struct xe_page_reclaim_list *prl, + struct xe_device *xe, struct xe_pt *compact_pt, u64 addr) +{ + struct iosys_map *map = &compact_pt->bo->vmap; + + for (pgoff_t i = 0; i < SZ_2M / SZ_64K && xe_page_reclaim_list_valid(prl); i++) { + u64 pte = xe_map_rd(xe, map, i * sizeof(u64), u64); + + if (add_pte_to_prl(tile, prl, compact_pt, pte, addr + i * SZ_64K)) + break; + } + + return xe_page_reclaim_list_valid(prl); +} + static int xe_pt_stage_unbind_entry(struct xe_ptw *parent, pgoff_t offset, unsigned int level, u64 addr, u64 next, struct xe_ptw **child, @@ -1674,21 +1708,22 @@ static int xe_pt_stage_unbind_entry(struct xe_ptw *parent, pgoff_t offset, struct xe_pt *xe_child = container_of(*child, typeof(*xe_child), base); struct xe_pt_stage_unbind_walk *xe_walk = container_of(walk, typeof(*xe_walk), base); - struct xe_device *xe = tile_to_xe(xe_walk->tile); + struct xe_page_reclaim_list *prl = xe_walk->prl; + struct xe_tile *tile = xe_walk->tile; + struct xe_device *xe = tile_to_xe(tile); pgoff_t first = xe_pt_offset(addr, xe_child->level, walk); bool killed; XE_WARN_ON(!*child); XE_WARN_ON(!level); /* Check for leaf node */ - if (xe_walk->prl && xe_page_reclaim_list_valid(xe_walk->prl) && + if (prl && xe_page_reclaim_list_valid(prl) && xe_child->level <= MAX_HUGEPTE_LEVEL) { struct iosys_map *leaf_map = &xe_child->bo->vmap; pgoff_t count = xe_pt_num_entries(addr, next, xe_child->level, walk); for (pgoff_t i = 0; i < count; i++) { u64 pte; - int ret; /* * If not a leaf pt, skip unless non-leaf pt is interleaved between @@ -1698,10 +1733,23 @@ static int xe_pt_stage_unbind_entry(struct xe_ptw *parent, pgoff_t offset, u64 pt_size = 1ULL << walk->shifts[xe_child->level]; bool edge_pt = (i == 0 && !IS_ALIGNED(addr, pt_size)) || (i == count - 1 && !IS_ALIGNED(next, pt_size)); + struct xe_pt *child_pt = + container_of(xe_child->base.children[first + i], + struct xe_pt, base); - if (!edge_pt) { - xe_page_reclaim_list_abort(xe_walk->tile->primary_gt, - xe_walk->prl, + /* Compact PTs always fill a full 2M-aligned slot, never an edge. */ + XE_WARN_ON(child_pt->is_compact && edge_pt); + if (edge_pt) + continue; + + /* Walker never descends into compact PTs, descend now */ + if (child_pt->is_compact) { + if (!add_compact_pt_prl(tile, prl, xe, child_pt, + addr + (u64)i * pt_size)) + break; + } else { + xe_page_reclaim_list_abort(tile->primary_gt, + prl, "PT is skipped by walk at level=%u offset=%lu", xe_child->level, first + i); break; @@ -1711,37 +1759,12 @@ static int xe_pt_stage_unbind_entry(struct xe_ptw *parent, pgoff_t offset, pte = xe_map_rd(xe, leaf_map, (first + i) * sizeof(u64), u64); - /* - * In rare scenarios, pte may not be written yet due to racy conditions. - * In such cases, invalidate the PRL and fallback to full PPC invalidation. - */ - if (!pte) { - xe_page_reclaim_list_abort(xe_walk->tile->primary_gt, xe_walk->prl, - "found zero pte at addr=%#llx", addr); + if (add_pte_to_prl(tile, prl, xe_child, pte, addr)) break; - } - - /* Ensure it is a defined page */ - xe_tile_assert(xe_walk->tile, xe_child->level == 0 || - (pte & (XE_PDE_PS_2M | XE_PDPE_PS_1G))); /* An entry should be added for 64KB but contigious 4K have XE_PTE_PS64 */ if (pte & XE_PTE_PS64) i += 15; /* Skip other 15 consecutive 4K pages in the 64K page */ - - /* Account for NULL terminated entry on end (-1) */ - if (xe_walk->prl->num_entries < XE_PAGE_RECLAIM_MAX_ENTRIES - 1) { - ret = generate_reclaim_entry(xe_walk->tile, xe_walk->prl, - pte, xe_child); - if (ret) - break; - } else { - /* overflow, mark as invalid */ - xe_page_reclaim_list_abort(xe_walk->tile->primary_gt, xe_walk->prl, - "overflow while adding pte=%#llx", - pte); - break; - } } } @@ -1751,7 +1774,7 @@ static int xe_pt_stage_unbind_entry(struct xe_ptw *parent, pgoff_t offset, * Verify if any PTE are potentially dropped at non-leaf levels, either from being * killed or the page walk covers the region. */ - if (xe_walk->prl && xe_page_reclaim_list_valid(xe_walk->prl) && + if (prl && xe_page_reclaim_list_valid(prl) && xe_child->level > MAX_HUGEPTE_LEVEL && xe_child->num_live) { bool covered = xe_pt_covers(addr, next, xe_child->level, &xe_walk->base); @@ -1760,7 +1783,7 @@ static int xe_pt_stage_unbind_entry(struct xe_ptw *parent, pgoff_t offset, * we need to invalidate the PRL. */ if (killed || covered) - xe_page_reclaim_list_abort(xe_walk->tile->primary_gt, xe_walk->prl, + xe_page_reclaim_list_abort(tile->primary_gt, prl, "kill at level=%u addr=%#llx next=%#llx num_live=%u", level, addr, next, xe_child->num_live); } From 7caf2a2351d4053075670ff3e26a6815da0a9e1e Mon Sep 17 00:00:00 2001 From: Shuvam Pandey Date: Tue, 16 Jun 2026 02:03:00 +0545 Subject: [PATCH 031/297] accel/amdxdna: Use caller client for debug BO sync amdxdna_drm_sync_bo_ioctl() looks up args->handle in the ioctl caller's drm_file. For SYNC_DIRECT_FROM_DEVICE, it then calls amdxdna_hwctx_sync_debug_bo(), but passes abo->client. amdxdna_hwctx_sync_debug_bo() uses the passed client both as the handle namespace for debug_bo_hdl and as the owner of the hardware context xarray. Those must match the file that supplied args->handle. The BO's stored client pointer is object state, not the ioctl context. Pass filp->driver_priv instead, matching the original handle lookup. Fixes: 7ea046838021 ("accel/amdxdna: Support firmware debug buffer") Cc: stable@vger.kernel.org # v6.19+ Signed-off-by: Shuvam Pandey Reviewed-by: Lizhi Hou Signed-off-by: Lizhi Hou Link: https://patch.msgid.link/178155468039.81818.12173237984867749651@gmail.com --- drivers/accel/amdxdna/amdxdna_gem.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/accel/amdxdna/amdxdna_gem.c b/drivers/accel/amdxdna/amdxdna_gem.c index 6e367ddb9e1b..6c16b21994ab 100644 --- a/drivers/accel/amdxdna/amdxdna_gem.c +++ b/drivers/accel/amdxdna/amdxdna_gem.c @@ -1027,6 +1027,7 @@ int amdxdna_drm_get_bo_info_ioctl(struct drm_device *dev, void *data, struct drm int amdxdna_drm_sync_bo_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) { + struct amdxdna_client *client = filp->driver_priv; struct amdxdna_dev *xdna = to_xdna_dev(dev); struct amdxdna_drm_sync_bo *args = data; struct amdxdna_gem_obj *abo; @@ -1061,7 +1062,7 @@ int amdxdna_drm_sync_bo_ioctl(struct drm_device *dev, args->handle, args->offset, args->size); if (args->direction == SYNC_DIRECT_FROM_DEVICE) - ret = amdxdna_hwctx_sync_debug_bo(abo->client, args->handle); + ret = amdxdna_hwctx_sync_debug_bo(client, args->handle); put_obj: drm_gem_object_put(gobj); From f1b061b4d4c6cbf861319ba954caa80145cf018f Mon Sep 17 00:00:00 2001 From: guoqi0226 Date: Tue, 16 Jun 2026 18:30:18 +0800 Subject: [PATCH 032/297] spi: Add NULL check for spi_get_device_id() in spi_get_device_match_data() Prevent NULL pointer dereference when spi_get_device_id() returns NULL, which can happen when using driver_override without matching SPI ID entry. Signed-off-by: guoqi0226 Link: https://patch.msgid.link/20260616103018.105612-3-guoqi0226@163.com Signed-off-by: Mark Brown --- drivers/spi/spi.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c index fe7e3b3b98fc..ab37b50bbf79 100644 --- a/drivers/spi/spi.c +++ b/drivers/spi/spi.c @@ -355,12 +355,16 @@ EXPORT_SYMBOL_GPL(spi_get_device_id); const void *spi_get_device_match_data(const struct spi_device *sdev) { const void *match; + const struct spi_device_id *id; match = device_get_match_data(&sdev->dev); if (match) return match; - return (const void *)spi_get_device_id(sdev)->driver_data; + id = spi_get_device_id(sdev); + if (!id) + return NULL; + return (const void *)id->driver_data; } EXPORT_SYMBOL_GPL(spi_get_device_match_data); From f3ad1c87d8201e54b66bd6072442f0b5d5a308ee Mon Sep 17 00:00:00 2001 From: Kunihiko Hayashi Date: Tue, 16 Jun 2026 10:12:23 +0900 Subject: [PATCH 033/297] spi: uniphier: Fix completion initialization order before devm_request_irq() The driver calls devm_request_irq() before initializing the completion used by the interrupt handler. Because the interrupt may occur immediately after devm_request_irq(), the handler may execute before init_completion(). This may result in calling complete() on an uninitialized completion, causing undefined behavior. This has been observed with KASAN. Fix this by initializing the completion before registering the IRQ. Reported-by: Sangyun Kim Reported-by: Kyungwook Boo Fixes: 5ba155a4d4cc ("spi: add SPI controller driver for UniPhier SoC") Cc: stable@vger.kernel.org Cc: Masami Hiramatsu Signed-off-by: Kunihiko Hayashi Reviewed-by: Masami Hiramatsu (Google) Link: https://patch.msgid.link/20260616011223.201357-1-hayashi.kunihiko@socionext.com Signed-off-by: Mark Brown --- drivers/spi/spi-uniphier.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/spi/spi-uniphier.c b/drivers/spi/spi-uniphier.c index cc20fd11f03f..86fce9a571da 100644 --- a/drivers/spi/spi-uniphier.c +++ b/drivers/spi/spi-uniphier.c @@ -656,6 +656,8 @@ static int uniphier_spi_probe(struct platform_device *pdev) priv->host = host; priv->is_save_param = false; + init_completion(&priv->xfer_done); + priv->base = devm_platform_get_and_ioremap_resource(pdev, 0, &res); if (IS_ERR(priv->base)) return PTR_ERR(priv->base); @@ -679,8 +681,6 @@ static int uniphier_spi_probe(struct platform_device *pdev) return ret; } - init_completion(&priv->xfer_done); - clk_rate = clk_get_rate(priv->clk); host->max_speed_hz = DIV_ROUND_UP(clk_rate, SSI_MIN_CLK_DIVIDER); From 66b6605bcea7af7aca3d1d858b9c5f14903f9f9a Mon Sep 17 00:00:00 2001 From: Jisheng Zhang Date: Fri, 12 Jun 2026 08:28:35 +0800 Subject: [PATCH 034/297] spi: dw: fix wrong BAUDR setting after resume After resuming from suspend to ram, spi transfer stops working. Further debugging shows that the BAUDR register isn't correctly set, this is due to dws->current_freq doesn't match the HW BAUDR setting, specifically, the dws->current_freq equals to speed_hz, but BAUDR is 0. so the dw_spi_set_clk() in below code won't be called: if (dws->current_freq != speed_hz) { dw_spi_set_clk(dws, clk_div); dws->current_freq = speed_hz; } The mismatch comes from dw_spi_shutdown_chip() when suspending. Fix this mismatch by setting dws->current_freq to 0 as well when clearing BAUDR reg in dw_spi_shutdown_chip(). Fixes: e24c74527207 ("spi: controller driver for Designware SPI core") Signed-off-by: Jisheng Zhang Link: https://patch.msgid.link/20260612002835.5240-1-jszhang@kernel.org Signed-off-by: Mark Brown --- drivers/spi/spi-dw.h | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/spi/spi-dw.h b/drivers/spi/spi-dw.h index 9cc79c566a70..2f2debc64e73 100644 --- a/drivers/spi/spi-dw.h +++ b/drivers/spi/spi-dw.h @@ -282,6 +282,7 @@ static inline void dw_spi_shutdown_chip(struct dw_spi *dws) { dw_spi_enable_chip(dws, 0); dw_spi_set_clk(dws, 0); + dws->current_freq = 0; } extern void dw_spi_set_cs(struct spi_device *spi, bool enable); From 4a60127debb9e370d6c0e22a307326b624a141f3 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?C=C3=A1ssio=20Gabriel?= Date: Mon, 15 Jun 2026 10:37:26 -0300 Subject: [PATCH 035/297] ALSA: compress: Fix task creation error unwind MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit snd_compr_task_new() allocates the driver task before validating the returned DMA buffers and reserving file descriptors. When either of those later steps fails, the core frees its task wrapper and DMA-buffer references without calling the driver's task_free() callback. Any driver resources allocated by task_create() are therefore leaked. The dual-fd allocation path also jumps to cleanup without storing the negative get_unused_fd_flags() result in retval. Since retval still contains the successful task_create() return value, TASK_CREATE can incorrectly report success although the task was discarded. Preserve the fd allocation errors and call task_free() when failure occurs after a successful task_create() callback. Fixes: 04177158cf98 ("ALSA: compress_offload: introduce accel operation mode") Fixes: 3d3f43fab4cf ("ALSA: compress_offload: improve file descriptors installation for dma-buf") Cc: stable@vger.kernel.org Signed-off-by: Cássio Gabriel Link: https://patch.msgid.link/20260615-alsa-compress-task-unwind-v1-1-39e8ad3ddb27@gmail.com Signed-off-by: Takashi Iwai --- sound/core/compress_offload.c | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) diff --git a/sound/core/compress_offload.c b/sound/core/compress_offload.c index fd63d219bf86..ea699491f0c3 100644 --- a/sound/core/compress_offload.c +++ b/sound/core/compress_offload.c @@ -1083,15 +1083,18 @@ static int snd_compr_task_new(struct snd_compr_stream *stream, struct snd_compr_ file descriptors are allocated before fd_install() */ if (!task->input || !task->input->file || !task->output || !task->output->file) { retval = -EINVAL; - goto cleanup; + goto free_driver_task; } fd_i = get_unused_fd_flags(O_WRONLY|O_CLOEXEC); - if (fd_i < 0) - goto cleanup; + if (fd_i < 0) { + retval = fd_i; + goto free_driver_task; + } fd_o = get_unused_fd_flags(O_RDONLY|O_CLOEXEC); if (fd_o < 0) { + retval = fd_o; put_unused_fd(fd_i); - goto cleanup; + goto free_driver_task; } /* keep dmabuf reference until freed with task free ioctl */ get_dma_buf(task->input); @@ -1103,6 +1106,8 @@ static int snd_compr_task_new(struct snd_compr_stream *stream, struct snd_compr_ list_add_tail(&task->list, &stream->runtime->tasks); stream->runtime->total_tasks++; return 0; +free_driver_task: + stream->ops->task_free(stream, task); cleanup: snd_compr_task_free(task); return retval; From f7c4968ae3af3e819428da5416c2dfd361473f5c Mon Sep 17 00:00:00 2001 From: Galen Hassen Date: Tue, 16 Jun 2026 10:32:57 -0700 Subject: [PATCH 036/297] ALSA: hda/conexant: Add pin config quirk for Lenovo IdeaPad Slim 5 16AKP10 The Lenovo IdeaPad Slim 5 16AKP10 (PCI SSID 17aa:38b6) uses the Conexant SN6140 codec. The internal microphone is on pin 0x1a but the BIOS configures it with pin default 0x95a60120, which includes a jack detection bit that causes the kernel to treat it as an unplugged external mic rather than a fixed internal mic. Add a pin config quirk that overrides pin 0x1a to 0x95a60130, setting the connectivity bits to indicate a fixed/always-connected device. This allows the internal microphone to be correctly identified and used. Signed-off-by: Galen Hassen Link: https://patch.msgid.link/20260616173257.37373-1-rwekyes@gmail.com Signed-off-by: Takashi Iwai --- sound/hda/codecs/conexant.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/sound/hda/codecs/conexant.c b/sound/hda/codecs/conexant.c index e3b6aaabe3a9..3d92262763f6 100644 --- a/sound/hda/codecs/conexant.c +++ b/sound/hda/codecs/conexant.c @@ -291,6 +291,7 @@ enum { CXT_FIXUP_HEADSET_MIC, CXT_FIXUP_HP_MIC_NO_PRESENCE, CXT_PINCFG_SWS_JS201D, + CXT_PINCFG_LENOVO_IDEAPAD_SLIM5_16AKP10, CXT_PINCFG_TOP_SPEAKER, CXT_FIXUP_HP_A_U, CXT_FIXUP_ACER_SWIFT_HP, @@ -826,6 +827,12 @@ static const struct hda_pintbl cxt_pincfg_lemote[] = { {} }; +/* Lenovo IdeaPad Slim 5 16AKP10 with SN6140 */ +static const struct hda_pintbl cxt_pincfg_lenovo_ideapad_slim5_16akp10[] = { + { 0x1a, 0x95a60130 }, /* Internal mic, fixed/always-connected */ + {} +}; + /* SuoWoSi/South-holding JS201D with sn6140 */ static const struct hda_pintbl cxt_pincfg_sws_js201d[] = { { 0x16, 0x03211040 }, /* hp out */ @@ -1006,6 +1013,10 @@ static const struct hda_fixup cxt_fixups[] = { .type = HDA_FIXUP_PINS, .v.pins = cxt_pincfg_sws_js201d, }, + [CXT_PINCFG_LENOVO_IDEAPAD_SLIM5_16AKP10] = { + .type = HDA_FIXUP_PINS, + .v.pins = cxt_pincfg_lenovo_ideapad_slim5_16akp10, + }, [CXT_PINCFG_TOP_SPEAKER] = { .type = HDA_FIXUP_PINS, .v.pins = (const struct hda_pintbl[]) { @@ -1114,6 +1125,7 @@ static const struct hda_quirk cxt5066_fixups[] = { SND_PCI_QUIRK(0x17aa, 0x21da, "Lenovo X220", CXT_PINCFG_LENOVO_TP410), SND_PCI_QUIRK(0x17aa, 0x21db, "Lenovo X220-tablet", CXT_PINCFG_LENOVO_TP410), SND_PCI_QUIRK(0x17aa, 0x38af, "Lenovo IdeaPad Z560", CXT_FIXUP_MUTE_LED_EAPD), + SND_PCI_QUIRK(0x17aa, 0x38b6, "Lenovo IdeaPad Slim 5 16AKP10", CXT_PINCFG_LENOVO_IDEAPAD_SLIM5_16AKP10), SND_PCI_QUIRK(0x17aa, 0x3905, "Lenovo G50-30", CXT_FIXUP_STEREO_DMIC), SND_PCI_QUIRK(0x17aa, 0x390b, "Lenovo G50-80", CXT_FIXUP_STEREO_DMIC), SND_PCI_QUIRK(0x17aa, 0x3975, "Lenovo U300s", CXT_FIXUP_STEREO_DMIC), From 7d69804a35103a50852eae41bfe6a2e0061c68fd Mon Sep 17 00:00:00 2001 From: Xu Rao Date: Tue, 16 Jun 2026 19:59:16 +0800 Subject: [PATCH 037/297] ALSA: usb-audio: qcom: Free sideband sg_table objects The Qualcomm USB audio offload driver obtains an endpoint transfer-ring table by calling xhci_sideband_get_endpoint_buffer(). This getter passes the endpoint ring to xhci_ring_to_sgtable(), which allocates the outer struct sg_table with kzalloc_obj(*sgt). The event-ring path is equivalent: xhci_sideband_get_event_buffer() also returns the result of xhci_ring_to_sgtable(). Inside xhci_ring_to_sgtable(), sg_alloc_table_from_pages() separately allocates the scatterlist storage referenced by sgt->sgl. The returned object therefore has two allocation layers: the outer struct sg_table and its internal scatterlist storage. The Qualcomm caller only invokes sg_free_table(sgt). sg_free_table() releases the scatterlist storage owned by the table, but it does not free the separately allocated outer struct sg_table. The local sgt pointer is then discarded, so every successful endpoint or event-ring query leaks the outer object. Call kfree(sgt) after sg_free_table(sgt) in both setup paths, after the required page and DMA addresses have been copied out. Fixes: 326bbc348298 ("ALSA: usb-audio: qcom: Introduce QC USB SND offloading support") Signed-off-by: Xu Rao Link: https://patch.msgid.link/90B353283AA150C4+20260616115916.1222915-1-raoxu@uniontech.com Signed-off-by: Takashi Iwai --- sound/usb/qcom/qc_audio_offload.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/sound/usb/qcom/qc_audio_offload.c b/sound/usb/qcom/qc_audio_offload.c index a3f90cc7c6ca..436d6821c5c9 100644 --- a/sound/usb/qcom/qc_audio_offload.c +++ b/sound/usb/qcom/qc_audio_offload.c @@ -1160,6 +1160,7 @@ uaudio_endpoint_setup(struct snd_usb_substream *subs, tr_pa = page_to_phys(pg); mem_info->dma = sg_dma_address(sgt->sgl); sg_free_table(sgt); + kfree(sgt); /* data transfer ring */ iova = uaudio_iommu_map_pa(MEM_XFER_RING, dma_coherent, tr_pa, @@ -1229,6 +1230,7 @@ static int uaudio_event_ring_setup(struct snd_usb_substream *subs, er_pa = page_to_phys(pg); mem_info->dma = sg_dma_address(sgt->sgl); sg_free_table(sgt); + kfree(sgt); iova = uaudio_iommu_map_pa(MEM_EVENT_RING, dma_coherent, er_pa, PAGE_SIZE); From 8956950dab22fbaefe92ca1980728165c5da793d Mon Sep 17 00:00:00 2001 From: Ai Chao Date: Wed, 17 Jun 2026 10:52:34 +0800 Subject: [PATCH 038/297] ALSA: usb-audio: Add quirk flags for SC13A The SC13A ( VID 0x1ff7, PID 0x0f81) not support reading the current sample rate and results in an error message printed to kmsg. Set QUIRK_FLAG_GET_SAMPLE_RATE to skip the sample rate check. Quirky device sample: usb 3-5.2.4.1: new high-speed USB device number 11 using xhci_hcd usb 3-5.2.4.1: New USB device found, idVendor=1ff7, idProduct=0f81 usb 3-5.2.4.1: New USB device strings: Mfr=1, Product=2, SerialNumber=3 usb 3-5.2.4.1: Product: SC13A usb 3-5.2.4.1: Manufacturer: Linux Foundation usb 3-5.2.4.1: SerialNumber: 000002 usb 3-5.2.4.1: Found UVC 1.50 device SC13A (1ff7:0f81) usb 3-5.2.4.1: 3:1: cannot get freq at ep 0x86 usb 3-5.2.4.1: Warning! Unlikely big volume range (=4096), cval->res is probably wrong. usb 3-5.2.4.1: [5] FU [Mic Capture Volume] ch = 1, val = 0/4096/1 usbcore: registered new interface driver snd-usb-audio usb 3-5.2.4.1: 3:1: cannot get freq at ep 0x86 usb 3-5.2.4.1: 3:1: cannot get freq at ep 0x86 Signed-off-by: Ai Chao Link: https://patch.msgid.link/20260617025234.3344935-1-aichao@kylinos.cn Signed-off-by: Takashi Iwai --- sound/usb/quirks.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index 30f6d572e4d1..1cb588691e16 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -2413,6 +2413,8 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = { QUIRK_FLAG_GET_SAMPLE_RATE | QUIRK_FLAG_MIC_RES_16), DEVICE_FLG(0x1bcf, 0x2283, /* NexiGo N930AF FHD Webcam */ QUIRK_FLAG_GET_SAMPLE_RATE | QUIRK_FLAG_MIC_RES_16), + DEVICE_FLG(0x1ff7, 0x0f81, /* SC13A Webcam */ + QUIRK_FLAG_GET_SAMPLE_RATE), DEVICE_FLG(0x2040, 0x7200, /* Hauppauge HVR-950Q */ QUIRK_FLAG_SHARE_MEDIA_DEVICE | QUIRK_FLAG_ALIGN_TRANSFER), DEVICE_FLG(0x2040, 0x7201, /* Hauppauge HVR-950Q-MXL */ From 9e6febe7891316182bcd80cb46b745a08ad0cacf Mon Sep 17 00:00:00 2001 From: Markus Elfring Date: Wed, 17 Jun 2026 08:42:18 +0200 Subject: [PATCH 039/297] ALSA: sh: Use more common error handling code in snd_aica_probe() Use an additional label so that a bit of exception handling can be better reused at the end of this function implementation. This issue was detected by using the Coccinelle software. Signed-off-by: Markus Elfring Link: https://patch.msgid.link/47413de1-015b-4543-8e8c-25e41dfa9e39@web.de Signed-off-by: Takashi Iwai --- sound/sh/aica.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/sound/sh/aica.c b/sound/sh/aica.c index 9438c3a68ee9..8196e1bf0416 100644 --- a/sound/sh/aica.c +++ b/sound/sh/aica.c @@ -564,10 +564,9 @@ static int snd_aica_probe(struct platform_device *devptr) return -ENOMEM; err = snd_card_new(&devptr->dev, index, SND_AICA_DRIVER, THIS_MODULE, 0, &dreamcastcard->card); - if (unlikely(err < 0)) { - kfree(dreamcastcard); - return err; - } + if (unlikely(err < 0)) + goto free_card; + strscpy(dreamcastcard->card->driver, "snd_aica"); strscpy(dreamcastcard->card->shortname, SND_AICA_DRIVER); strscpy(dreamcastcard->card->longname, @@ -593,6 +592,7 @@ static int snd_aica_probe(struct platform_device *devptr) return 0; freedreamcast: snd_card_free(dreamcastcard->card); +free_card: kfree(dreamcastcard); return err; } From 2e9261761b35f0b67b7487688cd1365f535be0b3 Mon Sep 17 00:00:00 2001 From: Srinivas Kandagatla Date: Tue, 16 Jun 2026 18:02:57 +0100 Subject: [PATCH 040/297] ASoC: qcom: q6apm: fix NULL pointer dereference in graph_callback When q6apm_free_fragments() is called it frees rx_data.buf/tx_data.buf and sets them to NULL under graph->lock. A late DSP buffer-done response can race with this: graph_callback() passes the !graph->ar_graph guard (not yet NULL), acquires the lock, but then dereferences a now-NULL buf pointer to read buf[token].phys, crashing at virtual address 0x10. Add a NULL check for buf inside the mutex-protected section in both the write-done (DATA_CMD_RSP_WR_SH_MEM_EP_DATA_BUFFER_DONE_V2) and read-done (DATA_CMD_RSP_RD_SH_MEM_EP_DATA_BUFFER_V2) handlers and bail out cleanly if buffers have already been freed. This problem is only shown up recently while apr bus was updated to process the commands per service rather from single global queue. Fixes: 5477518b8a0e ("ASoC: qdsp6: audioreach: add q6apm support") Cc: Stable@vger.kernel.org Assisted-by: Claude:claude-4-6-sonnet Reported-by: Val Packett Closes: https://lore.kernel.org/all/133ced18-1aa9-475d-80d8-6120678bdde4@packett.cool/ Signed-off-by: Srinivas Kandagatla Link: https://patch.msgid.link/20260616170257.9381-1-srinivas.kandagatla@oss.qualcomm.com Signed-off-by: Mark Brown --- sound/soc/qcom/qdsp6/q6apm.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/sound/soc/qcom/qdsp6/q6apm.c b/sound/soc/qcom/qdsp6/q6apm.c index 2e5b25b8d00f..641d6d243229 100644 --- a/sound/soc/qcom/qdsp6/q6apm.c +++ b/sound/soc/qcom/qdsp6/q6apm.c @@ -587,6 +587,10 @@ static int graph_callback(const struct gpr_resp_pkt *data, void *priv, int op) token = hdr->token & APM_WRITE_TOKEN_MASK; done = data->payload; + if (!graph->rx_data.buf) { + mutex_unlock(&graph->lock); + break; + } phys = graph->rx_data.buf[token].phys; mutex_unlock(&graph->lock); /* token numbering starts at 0 */ @@ -609,6 +613,10 @@ static int graph_callback(const struct gpr_resp_pkt *data, void *priv, int op) client_event = APM_CLIENT_EVENT_DATA_READ_DONE; mutex_lock(&graph->lock); rd_done = data->payload; + if (!graph->tx_data.buf) { + mutex_unlock(&graph->lock); + break; + } phys = graph->tx_data.buf[hdr->token].phys; mutex_unlock(&graph->lock); /* token numbering starts at 0 */ From 1a3c8e28959790ae3e06029681418278b7821a3c Mon Sep 17 00:00:00 2001 From: Nicolas Frattaroli Date: Wed, 17 Jun 2026 13:46:04 +0200 Subject: [PATCH 041/297] ASoC: rockchip: Drop problematic guard() changes This reverts commit f7fe9f707360 ("ASoC: rockchip: rockchip_sai: Use guard() for spin locks"). This is very noisy pointless churn that was not tested by the submitter, nor was it addressed to the driver's maintainer. It mixes unrelated whitespace changes (eliminating the blank line between the includes - why?) with hard to review diffs that add a whole indentation level to the function for no benefit, while also not following kernel code style by doing stuff like "ret == 0". The driver is better off without these changes, and they're not worth the time to validate whether they really do make no functional changes. Signed-off-by: Nicolas Frattaroli Link: https://patch.msgid.link/20260617-sai-revert-v1-1-e46adda2213b@collabora.com Signed-off-by: Mark Brown --- sound/soc/rockchip/rockchip_sai.c | 274 +++++++++++++++--------------- 1 file changed, 139 insertions(+), 135 deletions(-) diff --git a/sound/soc/rockchip/rockchip_sai.c b/sound/soc/rockchip/rockchip_sai.c index a195e96fed0a..ed393e5034a4 100644 --- a/sound/soc/rockchip/rockchip_sai.c +++ b/sound/soc/rockchip/rockchip_sai.c @@ -18,6 +18,7 @@ #include #include #include + #include "rockchip_sai.h" #define DRV_NAME "rockchip-sai" @@ -215,12 +216,14 @@ wait_for_idle: static int rockchip_sai_runtime_suspend(struct device *dev) { struct rk_sai_dev *sai = dev_get_drvdata(dev); + unsigned long flags; rockchip_sai_fsync_lost_detect(sai, 0); rockchip_sai_fsync_err_detect(sai, 0); - scoped_guard(spinlock_irqsave, &sai->xfer_lock) - rockchip_sai_xfer_clk_stop_and_wait(sai, NULL); + spin_lock_irqsave(&sai->xfer_lock, flags); + rockchip_sai_xfer_clk_stop_and_wait(sai, NULL); + spin_unlock_irqrestore(&sai->xfer_lock, flags); regcache_cache_only(sai->regmap, true); /* @@ -480,6 +483,7 @@ static int rockchip_sai_set_fmt(struct snd_soc_dai *dai, unsigned int fmt) struct rk_sai_dev *sai = snd_soc_dai_get_drvdata(dai); unsigned int mask = 0, val = 0; unsigned int clk_gates; + unsigned long flags; int ret = 0; pm_runtime_get_sync(dai->dev); @@ -495,56 +499,56 @@ static int rockchip_sai_set_fmt(struct snd_soc_dai *dai, unsigned int fmt) sai->is_master_mode = false; break; default: - pm_runtime_put(dai->dev); - return -EINVAL; + ret = -EINVAL; + goto err_pm_put; } - scoped_guard(spinlock_irqsave, &sai->xfer_lock) { - rockchip_sai_xfer_clk_stop_and_wait(sai, &clk_gates); - if (sai->initialized) { - if (sai->has_capture && sai->has_playback) - rockchip_sai_xfer_stop(sai, -1); - else if (sai->has_capture) - rockchip_sai_xfer_stop(sai, SNDRV_PCM_STREAM_CAPTURE); - else - rockchip_sai_xfer_stop(sai, SNDRV_PCM_STREAM_PLAYBACK); - } else { - rockchip_sai_clear(sai, 0); - sai->initialized = true; - } - - regmap_update_bits(sai->regmap, SAI_CKR, mask, val); - - mask = SAI_CKR_CKP_MASK | SAI_CKR_FSP_MASK; - switch (fmt & SND_SOC_DAIFMT_INV_MASK) { - case SND_SOC_DAIFMT_NB_NF: - val = SAI_CKR_CKP_NORMAL | SAI_CKR_FSP_NORMAL; - break; - case SND_SOC_DAIFMT_NB_IF: - val = SAI_CKR_CKP_NORMAL | SAI_CKR_FSP_INVERTED; - break; - case SND_SOC_DAIFMT_IB_NF: - val = SAI_CKR_CKP_INVERTED | SAI_CKR_FSP_NORMAL; - break; - case SND_SOC_DAIFMT_IB_IF: - val = SAI_CKR_CKP_INVERTED | SAI_CKR_FSP_INVERTED; - break; - default: - ret = -EINVAL; - break; - } - - if (ret == 0) { - regmap_update_bits(sai->regmap, SAI_CKR, mask, val); - rockchip_sai_fmt_create(sai, fmt); - } - - if (clk_gates) - regmap_update_bits(sai->regmap, SAI_XFER, - SAI_XFER_CLK_MASK | SAI_XFER_FSS_MASK, - clk_gates); + spin_lock_irqsave(&sai->xfer_lock, flags); + rockchip_sai_xfer_clk_stop_and_wait(sai, &clk_gates); + if (sai->initialized) { + if (sai->has_capture && sai->has_playback) + rockchip_sai_xfer_stop(sai, -1); + else if (sai->has_capture) + rockchip_sai_xfer_stop(sai, SNDRV_PCM_STREAM_CAPTURE); + else + rockchip_sai_xfer_stop(sai, SNDRV_PCM_STREAM_PLAYBACK); + } else { + rockchip_sai_clear(sai, 0); + sai->initialized = true; } + regmap_update_bits(sai->regmap, SAI_CKR, mask, val); + + mask = SAI_CKR_CKP_MASK | SAI_CKR_FSP_MASK; + switch (fmt & SND_SOC_DAIFMT_INV_MASK) { + case SND_SOC_DAIFMT_NB_NF: + val = SAI_CKR_CKP_NORMAL | SAI_CKR_FSP_NORMAL; + break; + case SND_SOC_DAIFMT_NB_IF: + val = SAI_CKR_CKP_NORMAL | SAI_CKR_FSP_INVERTED; + break; + case SND_SOC_DAIFMT_IB_NF: + val = SAI_CKR_CKP_INVERTED | SAI_CKR_FSP_NORMAL; + break; + case SND_SOC_DAIFMT_IB_IF: + val = SAI_CKR_CKP_INVERTED | SAI_CKR_FSP_INVERTED; + break; + default: + ret = -EINVAL; + goto err_xfer_unlock; + } + + regmap_update_bits(sai->regmap, SAI_CKR, mask, val); + + rockchip_sai_fmt_create(sai, fmt); + +err_xfer_unlock: + if (clk_gates) + regmap_update_bits(sai->regmap, SAI_XFER, + SAI_XFER_CLK_MASK | SAI_XFER_FSS_MASK, + clk_gates); + spin_unlock_irqrestore(&sai->xfer_lock, flags); +err_pm_put: pm_runtime_put(dai->dev); return ret; @@ -560,6 +564,7 @@ static int rockchip_sai_hw_params(struct snd_pcm_substream *substream, unsigned int ch_per_lane, slot_width; unsigned int val, fscr, reg; unsigned int lanes, req_lanes; + unsigned long flags; int ret = 0; if (!rockchip_sai_stream_valid(substream, dai)) @@ -586,8 +591,8 @@ static int rockchip_sai_hw_params(struct snd_pcm_substream *substream, dev_err(sai->dev, "not enough lanes (%d) for requested number of %s channels (%d)\n", lanes, reg == SAI_TXCR ? "playback" : "capture", params_channels(params)); - pm_runtime_put(sai->dev); - return -EINVAL; + ret = -EINVAL; + goto err_pm_put; } else { lanes = req_lanes; } @@ -613,88 +618,84 @@ static int rockchip_sai_hw_params(struct snd_pcm_substream *substream, val = SAI_XCR_VDW(32); break; default: - pm_runtime_put(sai->dev); - return -EINVAL; + ret = -EINVAL; + goto err_pm_put; } val |= SAI_XCR_CSR(lanes); - scoped_guard(spinlock_irqsave, &sai->xfer_lock) { + spin_lock_irqsave(&sai->xfer_lock, flags); - regmap_update_bits(sai->regmap, reg, SAI_XCR_VDW_MASK | SAI_XCR_CSR_MASK, val); + regmap_update_bits(sai->regmap, reg, SAI_XCR_VDW_MASK | SAI_XCR_CSR_MASK, val); - if (!sai->is_tdm) - regmap_update_bits(sai->regmap, reg, SAI_XCR_SBW_MASK, - SAI_XCR_SBW(params_physical_width(params))); + if (!sai->is_tdm) + regmap_update_bits(sai->regmap, reg, SAI_XCR_SBW_MASK, + SAI_XCR_SBW(params_physical_width(params))); - regmap_read(sai->regmap, reg, &val); + regmap_read(sai->regmap, reg, &val); - slot_width = SAI_XCR_SBW_V(val); - ch_per_lane = params_channels(params) / lanes; + slot_width = SAI_XCR_SBW_V(val); + ch_per_lane = params_channels(params) / lanes; - regmap_update_bits(sai->regmap, reg, SAI_XCR_SNB_MASK, - SAI_XCR_SNB(ch_per_lane)); + regmap_update_bits(sai->regmap, reg, SAI_XCR_SNB_MASK, + SAI_XCR_SNB(ch_per_lane)); - fscr = SAI_FSCR_FW(sai->fw_ratio * slot_width * ch_per_lane); + fscr = SAI_FSCR_FW(sai->fw_ratio * slot_width * ch_per_lane); - switch (sai->fpw) { - case FPW_ONE_BCLK_WIDTH: - fscr |= SAI_FSCR_FPW(1); - break; - case FPW_ONE_SLOT_WIDTH: - fscr |= SAI_FSCR_FPW(slot_width); - break; - case FPW_HALF_FRAME_WIDTH: - fscr |= SAI_FSCR_FPW(sai->fw_ratio * slot_width * ch_per_lane / 2); - break; - default: - dev_err(sai->dev, "Invalid Frame Pulse Width %d\n", sai->fpw); - ret = -EINVAL; - break; - } - - if (ret == 0) { - regmap_update_bits(sai->regmap, SAI_FSCR, - SAI_FSCR_FW_MASK | SAI_FSCR_FPW_MASK, fscr); - - if (sai->is_master_mode) { - bclk_rate = sai->fw_ratio * slot_width * - ch_per_lane * params_rate(params); - ret = clk_set_rate(sai->mclk, sai->mclk_rate); - if (ret) - dev_err(sai->dev, "Failed to set mclk to %u: %pe\n", - sai->mclk_rate, ERR_PTR(ret)); - else { - mclk_rate = clk_get_rate(sai->mclk); - if (mclk_rate < bclk_rate) { - dev_err(sai->dev, "Mismatch mclk: %u, at least %u\n", - mclk_rate, bclk_rate); - ret = -EINVAL; - } else { - - div_bclk = DIV_ROUND_CLOSEST(mclk_rate, bclk_rate); - mclk_req_rate = bclk_rate * div_bclk; - - if (mclk_rate < - mclk_req_rate - CLK_SHIFT_RATE_HZ_MAX || - mclk_rate > - mclk_req_rate + CLK_SHIFT_RATE_HZ_MAX) { - dev_err(sai->dev, - "Mismatch mclk: %u, expected %u (+/- %dHz)\n", - mclk_rate, mclk_req_rate, - CLK_SHIFT_RATE_HZ_MAX); - ret = -EINVAL; - } else - regmap_update_bits(sai->regmap, - SAI_CKR, - SAI_CKR_MDIV_MASK, - SAI_CKR_MDIV(div_bclk)); - } - } - } - } + switch (sai->fpw) { + case FPW_ONE_BCLK_WIDTH: + fscr |= SAI_FSCR_FPW(1); + break; + case FPW_ONE_SLOT_WIDTH: + fscr |= SAI_FSCR_FPW(slot_width); + break; + case FPW_HALF_FRAME_WIDTH: + fscr |= SAI_FSCR_FPW(sai->fw_ratio * slot_width * ch_per_lane / 2); + break; + default: + dev_err(sai->dev, "Invalid Frame Pulse Width %d\n", sai->fpw); + ret = -EINVAL; + goto err_xfer_unlock; } + regmap_update_bits(sai->regmap, SAI_FSCR, + SAI_FSCR_FW_MASK | SAI_FSCR_FPW_MASK, fscr); + + if (sai->is_master_mode) { + bclk_rate = sai->fw_ratio * slot_width * ch_per_lane * params_rate(params); + ret = clk_set_rate(sai->mclk, sai->mclk_rate); + if (ret) { + dev_err(sai->dev, "Failed to set mclk to %u: %pe\n", + sai->mclk_rate, ERR_PTR(ret)); + goto err_xfer_unlock; + } + + mclk_rate = clk_get_rate(sai->mclk); + if (mclk_rate < bclk_rate) { + dev_err(sai->dev, "Mismatch mclk: %u, at least %u\n", + mclk_rate, bclk_rate); + ret = -EINVAL; + goto err_xfer_unlock; + } + + div_bclk = DIV_ROUND_CLOSEST(mclk_rate, bclk_rate); + mclk_req_rate = bclk_rate * div_bclk; + + if (mclk_rate < mclk_req_rate - CLK_SHIFT_RATE_HZ_MAX || + mclk_rate > mclk_req_rate + CLK_SHIFT_RATE_HZ_MAX) { + dev_err(sai->dev, "Mismatch mclk: %u, expected %u (+/- %dHz)\n", + mclk_rate, mclk_req_rate, CLK_SHIFT_RATE_HZ_MAX); + ret = -EINVAL; + goto err_xfer_unlock; + } + + regmap_update_bits(sai->regmap, SAI_CKR, SAI_CKR_MDIV_MASK, + SAI_CKR_MDIV(div_bclk)); + } + +err_xfer_unlock: + spin_unlock_irqrestore(&sai->xfer_lock, flags); +err_pm_put: pm_runtime_put(sai->dev); return ret; @@ -704,6 +705,7 @@ static int rockchip_sai_prepare(struct snd_pcm_substream *substream, struct snd_soc_dai *dai) { struct rk_sai_dev *sai = snd_soc_dai_get_drvdata(dai); + unsigned long flags; if (!rockchip_sai_stream_valid(substream, dai)) return 0; @@ -724,12 +726,13 @@ static int rockchip_sai_prepare(struct snd_pcm_substream *substream, * udelay falls short. */ udelay(20); - scoped_guard(spinlock_irqsave, &sai->xfer_lock) - regmap_update_bits(sai->regmap, SAI_XFER, - SAI_XFER_CLK_MASK | - SAI_XFER_FSS_MASK, - SAI_XFER_CLK_EN | - SAI_XFER_FSS_EN); + spin_lock_irqsave(&sai->xfer_lock, flags); + regmap_update_bits(sai->regmap, SAI_XFER, + SAI_XFER_CLK_MASK | + SAI_XFER_FSS_MASK, + SAI_XFER_CLK_EN | + SAI_XFER_FSS_EN); + spin_unlock_irqrestore(&sai->xfer_lock, flags); } rockchip_sai_fsync_lost_detect(sai, 1); @@ -912,6 +915,7 @@ static int rockchip_sai_set_tdm_slot(struct snd_soc_dai *dai, int slots, int slot_width) { struct rk_sai_dev *sai = snd_soc_dai_get_drvdata(dai); + unsigned long flags; unsigned int clk_gates; int sw = slot_width; @@ -927,16 +931,16 @@ static int rockchip_sai_set_tdm_slot(struct snd_soc_dai *dai, return -EINVAL; pm_runtime_get_sync(dai->dev); - scoped_guard(spinlock_irqsave, &sai->xfer_lock) { - rockchip_sai_xfer_clk_stop_and_wait(sai, &clk_gates); - regmap_update_bits(sai->regmap, SAI_TXCR, SAI_XCR_SBW_MASK, - SAI_XCR_SBW(sw)); - regmap_update_bits(sai->regmap, SAI_RXCR, SAI_XCR_SBW_MASK, - SAI_XCR_SBW(sw)); - regmap_update_bits(sai->regmap, SAI_XFER, - SAI_XFER_CLK_MASK | SAI_XFER_FSS_MASK, - clk_gates); - } + spin_lock_irqsave(&sai->xfer_lock, flags); + rockchip_sai_xfer_clk_stop_and_wait(sai, &clk_gates); + regmap_update_bits(sai->regmap, SAI_TXCR, SAI_XCR_SBW_MASK, + SAI_XCR_SBW(sw)); + regmap_update_bits(sai->regmap, SAI_RXCR, SAI_XCR_SBW_MASK, + SAI_XCR_SBW(sw)); + regmap_update_bits(sai->regmap, SAI_XFER, + SAI_XFER_CLK_MASK | SAI_XFER_FSS_MASK, + clk_gates); + spin_unlock_irqrestore(&sai->xfer_lock, flags); pm_runtime_put(dai->dev); return 0; From fdf043f5f3bae150b678feae3d7bb1beed87ec14 Mon Sep 17 00:00:00 2001 From: Sen Wang Date: Tue, 16 Jun 2026 18:33:22 -0500 Subject: [PATCH 042/297] ASoC: tlv320aic3x: restrict CLKDIV bypass Q values in dual-rate mode The datasheet documents that when the PLL is disabled and dual-rate mode is enabled, only Q values {4, 8, 9, 12, 16} are valid for the CLKDIV bypass path; all other Q values produce invalid bitclock output. The existing loop iterates Q from 2 to 17 without this restriction, causing silent audio failure when an out-of-spec Q is picked. Restrict the Q search to the allowed set in dual-rate mode. Fixes: 4f9c16ccfa26 ("[ALSA] soc - tlv320aic3x - revisit clock setup") Suggested-by: Mir Jeffres Signed-off-by: Sen Wang Link: https://patch.msgid.link/20260616233322.873081-1-sen@ti.com Signed-off-by: Mark Brown --- sound/soc/codecs/tlv320aic3x.c | 25 +++++++++++++++++++------ 1 file changed, 19 insertions(+), 6 deletions(-) diff --git a/sound/soc/codecs/tlv320aic3x.c b/sound/soc/codecs/tlv320aic3x.c index b12c1952823b..b38393a8130f 100644 --- a/sound/soc/codecs/tlv320aic3x.c +++ b/sound/soc/codecs/tlv320aic3x.c @@ -1049,11 +1049,13 @@ static int aic3x_hw_params(struct snd_pcm_substream *substream, struct snd_pcm_hw_params *params, struct snd_soc_dai *dai) { + static const u8 dual_rate_q[] = {4, 8, 9, 12, 16}; struct snd_soc_component *component = dai->component; struct aic3x_priv *aic3x = snd_soc_component_get_drvdata(component); int codec_clk = 0, bypass_pll = 0, fsref, last_clk = 0; u8 data, j, r, p, pll_q, pll_p = 1, pll_r = 1, pll_j = 1; u16 d, pll_d = 1; + bool dual_rate; int clk; int width = aic3x->slot_width; @@ -1079,14 +1081,25 @@ static int aic3x_hw_params(struct snd_pcm_substream *substream, /* Fsref can be 44100 or 48000 */ fsref = (params_rate(params) % 11025 == 0) ? 44100 : 48000; + dual_rate = params_rate(params) >= 64000; /* Try to find a value for Q which allows us to bypass the PLL and * generate CODEC_CLK directly. */ - for (pll_q = 2; pll_q < 18; pll_q++) - if (aic3x->sysclk / (128 * pll_q) == fsref) { - bypass_pll = 1; - break; + if (dual_rate) { + for (int i = 0; i < ARRAY_SIZE(dual_rate_q); i++) { + pll_q = dual_rate_q[i]; + if (aic3x->sysclk / (128 * pll_q) == fsref) { + bypass_pll = 1; + break; + } } + } else { + for (pll_q = 2; pll_q < 18; pll_q++) + if (aic3x->sysclk / (128 * pll_q) == fsref) { + bypass_pll = 1; + break; + } + } if (bypass_pll) { pll_q &= 0xf; @@ -1106,13 +1119,13 @@ static int aic3x_hw_params(struct snd_pcm_substream *substream, * right DAC to right channel input */ data = (LDAC2LCH | RDAC2RCH); data |= (fsref == 44100) ? FSREF_44100 : FSREF_48000; - if (params_rate(params) >= 64000) + if (dual_rate) data |= DUAL_RATE_MODE; snd_soc_component_write(component, AIC3X_CODEC_DATAPATH_REG, data); /* codec sample rate select */ data = (fsref * 20) / params_rate(params); - if (params_rate(params) < 64000) + if (!dual_rate) data /= 2; data /= 5; data -= 2; From 5096a1634def431cd7f89e2b0af4456de91dd26d Mon Sep 17 00:00:00 2001 From: Shuming Fan Date: Mon, 15 Jun 2026 17:10:12 +0800 Subject: [PATCH 043/297] ASoC: rt5650: enhance spk protection function This patch adjusts several default settings to ensure the speaker protection function can be enabled safely. Signed-off-by: Shuming Fan Link: https://patch.msgid.link/20260615091012.718168-1-shumingf@realtek.com Signed-off-by: Mark Brown --- sound/soc/codecs/rt5645.c | 6 ++---- sound/soc/codecs/rt5645.h | 1 + 2 files changed, 3 insertions(+), 4 deletions(-) diff --git a/sound/soc/codecs/rt5645.c b/sound/soc/codecs/rt5645.c index 8a9af260e5f7..e9819653b30d 100644 --- a/sound/soc/codecs/rt5645.c +++ b/sound/soc/codecs/rt5645.c @@ -83,6 +83,8 @@ static const struct reg_sequence rt5650_init_list[] = { {RT5645_PWR_ANLG1, 0x02}, {RT5645_IL_CMD3, 0x6728}, {RT5645_PR_BASE + 0x3a, 0x0000}, + {RT5645_CLSD_OUT_CTRL1, 0x4059}, + {RT5645_GEN_CTRL3, 0x0200}, }; static const struct reg_default rt5645_reg[] = { @@ -1855,13 +1857,9 @@ static int rt5645_spk_event(struct snd_soc_dapm_widget *w, RT5645_PWR_CLS_D_L, RT5645_PWR_CLS_D | RT5645_PWR_CLS_D_R | RT5645_PWR_CLS_D_L); - snd_soc_component_update_bits(component, RT5645_GEN_CTRL3, - RT5645_DET_CLK_MASK, RT5645_DET_CLK_MODE1); break; case SND_SOC_DAPM_PRE_PMD: - snd_soc_component_update_bits(component, RT5645_GEN_CTRL3, - RT5645_DET_CLK_MASK, RT5645_DET_CLK_DIS); snd_soc_component_write(component, RT5645_EQ_CTRL2, 0); snd_soc_component_update_bits(component, RT5645_PWR_DIG1, RT5645_PWR_CLS_D | RT5645_PWR_CLS_D_R | diff --git a/sound/soc/codecs/rt5645.h b/sound/soc/codecs/rt5645.h index bef74b29fd54..a5bfe9861b8b 100644 --- a/sound/soc/codecs/rt5645.h +++ b/sound/soc/codecs/rt5645.h @@ -118,6 +118,7 @@ #define RT5645_A_JD_CTRL1 0x94 #define RT5645_VAD_CTRL4 0x9d #define RT5645_CLSD_OUT_CTRL 0xa0 +#define RT5645_CLSD_OUT_CTRL1 0xa1 /* Function - Digital */ #define RT5645_ADC_EQ_CTRL1 0xae #define RT5645_ADC_EQ_CTRL2 0xaf From 12aad822fb9a761f3a9d278083a5bdcb1524e5ec Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Wed, 17 Jun 2026 11:24:06 +0200 Subject: [PATCH 044/297] spi: acpi: Free resource list at appropriate time We do unneeded "double free" (emptying an empty list) in one case. This is not a critical issue at all, the fix just makes code robust against any possible future changes in the flow. Signed-off-by: Andy Shevchenko Link: https://patch.msgid.link/20260617092406.2649384-1-andriy.shevchenko@linux.intel.com Signed-off-by: Mark Brown --- drivers/spi/spi.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c index ab37b50bbf79..d7e584afa301 100644 --- a/drivers/spi/spi.c +++ b/drivers/spi/spi.c @@ -2979,12 +2979,12 @@ struct spi_device *acpi_spi_device_alloc(struct spi_controller *ctlr, INIT_LIST_HEAD(&resource_list); ret = acpi_dev_get_resources(adev, &resource_list, acpi_spi_add_resource, &lookup); - acpi_dev_free_resource_list(&resource_list); - if (ret < 0) /* Found SPI in _CRS but it points to another controller */ return ERR_PTR(ret); + acpi_dev_free_resource_list(&resource_list); + if (!lookup.max_speed_hz && ACPI_SUCCESS(acpi_get_parent(adev->handle, &parent_handle)) && device_match_acpi_handle(lookup.ctlr->dev.parent, parent_handle)) { From 9ef450ca74e43dacf9a2a15db7a851052c78dcf0 Mon Sep 17 00:00:00 2001 From: Zhongqiu Han Date: Tue, 16 Jun 2026 23:47:33 +0800 Subject: [PATCH 045/297] cpufreq: schedutil: Fix uncleared need_freq_update on the .adjust_perf() path The need_freq_update flag makes sugov_should_update_freq() return true regardless of the rate_limit_us throttling, and is cleared in sugov_update_next_freq(). sugov_update_single_freq() and sugov_update_shared() go through that helper, so the flag does not persist there. However, sugov_update_single_perf(), used by drivers implementing the .adjust_perf() callback (e.g. intel_pstate or amd-pstate in passive mode) calls cpufreq_driver_adjust_perf() directly and never goes through sugov_update_next_freq(), so the need_freq_update flag is not cleared in that path. Before commit 75da043d8f88 ("cpufreq/sched: Set need_freq_update in ignore_dl_rate_limit()"), this was effectively harmless because sugov_should_update_freq() still honored the rate limit even when need_freq_update was set. After that change, the flag forces sugov_should_update_freq() to always return true, so once set, it stays effective indefinitely on the .adjust_perf() path. As a result, cpufreq_driver_adjust_perf() gets called on every scheduler utilization update (with the runqueue lock held) rather than being throttled by rate_limit_us, even if the driver itself may skip redundant hardware updates. Clear need_freq_update at the end of the adjust_perf path as well. Fixes: 75da043d8f88 ("cpufreq/sched: Set need_freq_update in ignore_dl_rate_limit()") Signed-off-by: Zhongqiu Han Reviewed-by: Hongyan Xia Reviewed-by: Christian Loehle Cc: All applicable [ rjw: Subject and changelog edits ] Link: https://patch.msgid.link/20260616154733.2405236-1-zhongqiu.han@oss.qualcomm.com Signed-off-by: Rafael J. Wysocki --- kernel/sched/cpufreq_schedutil.c | 1 + 1 file changed, 1 insertion(+) diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c index ae9fd211cec1..a4e689eefdfb 100644 --- a/kernel/sched/cpufreq_schedutil.c +++ b/kernel/sched/cpufreq_schedutil.c @@ -486,6 +486,7 @@ static void sugov_update_single_perf(struct update_util_data *hook, u64 time, cpufreq_driver_adjust_perf(sg_policy->policy, sg_cpu->bw_min, sg_cpu->util, max_cap); + sg_policy->need_freq_update = false; sg_policy->last_freq_update_time = time; } From 3f0cc1735273a57c5116710cf0202e12152f59cc Mon Sep 17 00:00:00 2001 From: Yunxiang Li Date: Thu, 4 Jun 2026 12:59:11 -0400 Subject: [PATCH 046/297] drm/amdkfd: Avoid double-unpin of DOORBELL/MMIO BOs on free amdgpu_amdkfd_gpuvm_free_memory_of_gpu() unpinned DOORBELL and MMIO remap BOs (which are pinned at allocation time) before checking whether the BO is still mapped to the GPU. When the BO is still mapped, the function returns -EBUSY and leaves the BO alive, but it has already been unpinned. The BO is then unpinned again when it is finally freed during process teardown, triggering a ttm_bo_unpin() underflow warning: WARNING: CPU: 18 PID: 15066 at ttm/ttm_bo.c:650 amdttm_bo_unpin+0x6d/0x80 [amdttm] Workqueue: kfd_process_wq kfd_process_wq_release [amdgpu] RIP: 0010:amdttm_bo_unpin+0x6d/0x80 [amdttm] Call Trace: amdgpu_bo_unpin+0x1a/0x90 [amdgpu] amdgpu_amdkfd_gpuvm_unpin_bo+0x31/0xb0 [amdgpu] amdgpu_amdkfd_gpuvm_free_memory_of_gpu+0x3bf/0x460 [amdgpu] kfd_process_free_outstanding_kfd_bos+0xd4/0x170 [amdgpu] kfd_process_wq_release+0x109/0x1b0 [amdgpu] process_one_work+0x1e2/0x3b0 worker_thread+0x50/0x3a0 kthread+0xdd/0x100 ret_from_fork+0x29/0x50 Move the unpin after the mapped_to_gpu_memory check so it only happens once we are committed to freeing the BO. Fixes: d25e35bc26c3 ("drm/amdgpu: Pin MMIO/DOORBELL BO's in GTT domain") Signed-off-by: Yunxiang Li Reviewed-by: Felix Kuehling Signed-off-by: Alex Deucher (cherry picked from commit 927c5b2defb9b09856444d94bebfd056a002bd75) --- drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c index d54794e5b18b..35fe2c974699 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c @@ -1914,13 +1914,6 @@ int amdgpu_amdkfd_gpuvm_free_memory_of_gpu( mutex_lock(&mem->lock); - /* Unpin MMIO/DOORBELL BO's that were pinned during allocation */ - if (mem->alloc_flags & - (KFD_IOC_ALLOC_MEM_FLAGS_DOORBELL | - KFD_IOC_ALLOC_MEM_FLAGS_MMIO_REMAP)) { - amdgpu_amdkfd_gpuvm_unpin_bo(mem->bo); - } - mapped_to_gpu_memory = mem->mapped_to_gpu_memory; is_imported = mem->is_imported; mutex_unlock(&mem->lock); @@ -1934,6 +1927,15 @@ int amdgpu_amdkfd_gpuvm_free_memory_of_gpu( return -EBUSY; } + /* At this point the BO is guaranteed to be freed, so unpin the + * MMIO/DOORBELL BOs that were pinned during allocation. + */ + if (mem->alloc_flags & + (KFD_IOC_ALLOC_MEM_FLAGS_DOORBELL | + KFD_IOC_ALLOC_MEM_FLAGS_MMIO_REMAP)) { + amdgpu_amdkfd_gpuvm_unpin_bo(mem->bo); + } + /* Make sure restore workers don't access the BO any more */ mutex_lock(&process_info->lock); if (!list_empty(&mem->validate_list)) From 1c2d7a656655a50bd1b7227fb26d173959a1955d Mon Sep 17 00:00:00 2001 From: Qiang Yu Date: Tue, 26 May 2026 14:45:48 +0800 Subject: [PATCH 047/297] drm/amdgpu: initialize iter.start in amdgpu_devcoredump_format This fixes read /sys/class/drm/cardN/device/devcoredump/data return empty content sometimes. amdgpu_devcoredump_format() leaves struct drm_print_iterator's .start field uninitialized on the stack before passing it to drm_coredump_printer(). __drm_puts_coredump() compares the running .offset against .start to decide whether to skip or copy each chunk: if (iterator->offset < iterator->start) { if (iterator->offset + len <= iterator->start) { iterator->offset += len; return; } ... } Fixes: 4bbba79a7f1d ("drm/amdgpu: move devcoredump generation to a worker") Acked-by: Alex Deucher Signed-off-by: Qiang Yu Signed-off-by: Alex Deucher (cherry picked from commit cd6397b7af8262a380e188dc32e9de11ff897ed2) --- drivers/gpu/drm/amd/amdgpu/amdgpu_dev_coredump.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dev_coredump.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dev_coredump.c index 27830518a230..bed68f0c3080 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dev_coredump.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dev_coredump.c @@ -229,6 +229,7 @@ amdgpu_devcoredump_format(char *buffer, size_t count, struct amdgpu_coredump_inf sizing_pass = buffer == NULL; iter.data = buffer; + iter.start = 0; iter.offset = 0; iter.remain = count; From 76589bcc73f477ef2b3b90e4fae6a7a4dfd925af Mon Sep 17 00:00:00 2001 From: Shubhankar Milind Sardeshpande Date: Thu, 21 May 2026 10:55:18 +0530 Subject: [PATCH 048/297] drm/amd/pm: re-enable MC access after PrepareMp1ForUnload on SMU V15 APUs During smu_v15_0_0_system_features_control(), the driver sends a PrepareMp1ForUnload message to PMFW. PMFW then performs nBIF and SYSHUB function-level resets (FLR), disabling PCIe CFG space reset, which clears the framebuffer enable bit to zero and disables MC (memory controller) access from the host. Re-enable MC access via the nbio mc_access_enable callback right after PrepareMp1ForUnload completes in smu_v15_0_0_system_features_control(). Signed-off-by: Shubhankar Milind Sardeshpande Signed-off-by: Suresh Guttula Signed-off-by: Alex Deucher (cherry picked from commit 840a3c5aeae779a3bc75d7f747c3ed18b1af6507) Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/pm/swsmu/smu15/smu_v15_0_0_ppt.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu15/smu_v15_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu15/smu_v15_0_0_ppt.c index fb1145691410..a214ddbd4c86 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu15/smu_v15_0_0_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu15/smu_v15_0_0_ppt.c @@ -227,9 +227,14 @@ static int smu_v15_0_0_system_features_control(struct smu_context *smu, bool en) struct amdgpu_device *adev = smu->adev; int ret = 0; - if (!en && !adev->in_s0ix) + if (!en && !adev->in_s0ix) { ret = smu_cmn_send_smc_msg(smu, SMU_MSG_PrepareMp1ForUnload, NULL); + /* SMU resets BIF_FB_EN to zero, re-enable MC access on APUs with SMU V15 */ + if (!ret && adev->nbio.funcs && adev->nbio.funcs->mc_access_enable) + adev->nbio.funcs->mc_access_enable(adev, true); + } + return ret; } From 20a5e7ffdfecddc34c60a6b4483f42acf3d8731d Mon Sep 17 00:00:00 2001 From: David Francis Date: Thu, 4 Jun 2026 15:04:03 -0400 Subject: [PATCH 049/297] drm/amdkfd: Properly acquire queue buffers in CRIU restore When kfd_queue_acquire_buffers() was split off from set_queue_properties_from_user(), set_queue_properties_from_criu() was missed. Thus, set_queue_properties_from_criu() is not filling out the buffer fields of queue_properties, which can come up when subsequent code expects them to be non-null. Add the proper call to kfd_queue_acquire_buffers(), and also use the right cast types in set_queue_properties_from_criu() (which were missed at the same time) Signed-off-by: David Francis Reviewed-by: Kent Russell Signed-off-by: Alex Deucher (cherry picked from commit 88ed96abbbe27b70193544fbc1ee06448c274714) --- .../gpu/drm/amd/amdkfd/kfd_process_queue_manager.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c index 44e39ce222b7..0ac35789b239 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c @@ -962,8 +962,8 @@ static void set_queue_properties_from_criu(struct queue_properties *qp, qp->priority = q_data->priority; qp->queue_address = q_data->q_address; qp->queue_size = q_data->q_size; - qp->read_ptr = (uint32_t *) q_data->read_ptr_addr; - qp->write_ptr = (uint32_t *) q_data->write_ptr_addr; + qp->read_ptr = (void __user *)q_data->read_ptr_addr; + qp->write_ptr = (void __user *)q_data->write_ptr_addr; qp->eop_ring_buffer_address = q_data->eop_ring_buffer_address; qp->eop_ring_buffer_size = q_data->eop_ring_buffer_size; qp->ctx_save_restore_area_address = q_data->ctx_save_restore_area_address; @@ -1042,10 +1042,18 @@ int kfd_criu_restore_queue(struct kfd_process *p, memset(&qp, 0, sizeof(qp)); set_queue_properties_from_criu(&qp, q_data, NUM_XCC(pdd->dev->adev->gfx.xcc_mask)); + ret = kfd_queue_acquire_buffers(pdd, &qp); + if (ret) { + pr_debug("failed to acquire user queue buffers for CRIU\n"); + goto exit; + } + print_queue_properties(&qp); ret = pqm_create_queue(&p->pqm, pdd->dev, &qp, &queue_id, q_data, mqd, ctl_stack, NULL); if (ret) { + kfd_queue_unref_bo_vas(pdd, &qp); + kfd_queue_release_buffers(pdd, &qp); pr_err("Failed to create new queue err:%d\n", ret); goto exit; } From b29aaf0a72222bfafe4d73899dadb0486b5bcb09 Mon Sep 17 00:00:00 2001 From: Yunxiang Li Date: Fri, 5 Jun 2026 08:59:34 -0400 Subject: [PATCH 050/297] drm/amdgpu: skip already suspended IP blocks in ip_suspend_phase2 The GPU reload test (S3 / mode1 reset / module reload) triggers a WARN_ON in amdgpu_irq_put() on gfx10 when unloading amdgpu: WARNING: CPU: 0 PID: 2314 at amd/amdgpu/amdgpu_irq.c:676 amdgpu_irq_put+0xc3/0xe0 [amdgpu] Call Trace: gfx_v10_0_hw_fini+0x41/0x150 [amdgpu] amdgpu_ip_block_hw_fini+0x29/0xc0 [amdgpu] amdgpu_device_fini_hw+0x315/0x610 [amdgpu] amdgpu_driver_unload_kms+0x7c/0x90 [amdgpu] amdgpu_pci_remove+0x51/0x90 [amdgpu] amdgpu_device_ip_resume_phase2() skips IP blocks whose status.hw is already set, but amdgpu_device_ip_suspend_phase2() never had the matching guard, so a block can be suspended twice (e.g. a reset or recovery issued while the device is already suspended). The second suspend runs hw_fini again, which now releases the gfx fault IRQs unconditionally, dropping a refcount that is already zero and tripping the WARN_ON in amdgpu_irq_put(). The fault/EOP IRQ get/put were balanced through late_init/hw_fini before, which masked the double-suspend; moving the get into hw_init made the suspend/resume asymmetry visible as an IRQ refcount underflow. Honor status.hw in ip_suspend_phase2() so suspend mirrors resume and a block is only torn down once. Fixes: 9117d8be850b ("drm/amdgpu/gfx: move fault and EOP IRQ get/put to hw_init/hw_fini") Fixes: 482f0e538580 ("drm/amdgpu: fix double ucode load by PSP(v3)") Signed-off-by: Yunxiang Li Reviewed-by: Alex Deucher Signed-off-by: Alex Deucher (cherry picked from commit f44f2af13c418969be358b15743f939d705de998) --- drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 942f0251c748..0fa2ce36c2ea 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -3043,7 +3043,7 @@ static int amdgpu_device_ip_suspend_phase2(struct amdgpu_device *adev) amdgpu_dpm_gfx_state_change(adev, sGpuChangeState_D3Entry); for (i = adev->num_ip_blocks - 1; i >= 0; i--) { - if (!adev->ip_blocks[i].status.valid) + if (!adev->ip_blocks[i].status.valid || !adev->ip_blocks[i].status.hw) continue; /* displays are handled in phase1 */ if (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_DCE) From fe7945d092a1d3c340febc2ab176cee50d0f6c80 Mon Sep 17 00:00:00 2001 From: Roman Li Date: Wed, 20 May 2026 16:50:34 -0400 Subject: [PATCH 051/297] drm/amd/display: Skip PHY SSC reduction on some 8K panels [Why] Some 8K displays cannot tolerate the reduced phy ssc value at high link utilization and show corruption or black screen. [How] Add an EDID panel-id quirk to utilize existing skip_phy_ssc_reduction flag. To pass the link into the quirk handler, change the signature of apply_edid_quirks() to take link as an argument. The dev local in dm_helpers_parse_edid_caps() becomes unused and is removed. Fixes: 5fa62c87cffd ("drm/amd/display: Add option to disable PHY SSC reduction on transmitter enable") Reviewed-by: Alex Hung Signed-off-by: Roman Li Signed-off-by: Aurabindo Pillai Tested-by: Dan Wheeler Signed-off-by: Alex Deucher (cherry picked from commit 144169e7be0831e09958a906d08d1856751aa6c6) --- .../drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c index f257ea91a34d..c6f94eb71ffa 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c @@ -95,8 +95,11 @@ static u32 edid_extract_panel_id(struct edid *edid) (u32)EDID_PRODUCT_ID(edid); } -static void apply_edid_quirks(struct drm_device *dev, struct edid *edid, struct dc_edid_caps *edid_caps) +static void apply_edid_quirks(struct dc_link *link, struct edid *edid, + struct dc_edid_caps *edid_caps) { + struct amdgpu_dm_connector *aconnector = link->priv; + struct drm_device *dev = aconnector->base.dev; uint32_t panel_id = edid_extract_panel_id(edid); switch (panel_id) { @@ -126,6 +129,11 @@ static void apply_edid_quirks(struct drm_device *dev, struct edid *edid, struct drm_dbg_driver(dev, "Disabling VSC on monitor with panel id %X\n", panel_id); edid_caps->panel_patch.disable_colorimetry = true; break; + /* Workaround for monitors that get corrupted by the PHY SSC reduction */ + case drm_edid_encode_panel_id('D', 'E', 'L', 0x4147): + drm_dbg_driver(dev, "Skip PHY SSC reduction on panel id %X\n", panel_id); + link->wa_flags.skip_phy_ssc_reduction = true; + break; default: return; } @@ -147,7 +155,6 @@ enum dc_edid_status dm_helpers_parse_edid_caps( { struct amdgpu_dm_connector *aconnector = link->priv; struct drm_connector *connector = &aconnector->base; - struct drm_device *dev = connector->dev; struct edid *edid_buf = edid ? (struct edid *) edid->raw_edid : NULL; struct cea_sad *sads; int sad_count = -1; @@ -188,7 +195,7 @@ enum dc_edid_status dm_helpers_parse_edid_caps( edid_caps->frl_dsc_max_frl_rate, edid_caps->frl_dsc_total_chunk_kbytes); } - apply_edid_quirks(dev, edid_buf, edid_caps); + apply_edid_quirks(link, edid_buf, edid_caps); sad_count = drm_edid_to_sad((struct edid *) edid->raw_edid, &sads); if (sad_count <= 0) From 5cc0f35d83e2c72f70edaf7478db350af3082a17 Mon Sep 17 00:00:00 2001 From: Ivan Lipski Date: Thu, 28 May 2026 12:28:51 -0400 Subject: [PATCH 052/297] drm/amd/display: Restore periodic detection for DCN35 [Why&How] Periodic detection callbacks from DCN35 was removed for higher IPS residency causing some displays to fail to recover after DPMS sleep. The monitors bounces HPD ~1.2s after link training, and without periodic detection the system enters IPS with no mechanism to wake and rediscover the display. Restore the periodic detection calls in dcn35_clk_mgr for now. It should be replaced with a proper IPS-aware solution long term using DMUB. Also remove it from dcn31 and dcn314_clk_mgr.c since they do not have IPS, thus should not affect them. Fixes: 3f6c060846be ("drm/amd/display: Remove periodic detection callbacks from dcn35+") Closes: https://gitlab.freedesktop.org/drm/amd/-/work_items/5318 Reviewed-by: Nicholas Kazlauskas Signed-off-by: Ivan Lipski Signed-off-by: Aurabindo Pillai Tested-by: Dan Wheeler Signed-off-by: Alex Deucher (cherry picked from commit 0c300e6a76916e944b6b18a64c73f7895a0fee87) Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_clk_mgr.c | 2 -- drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.c | 2 -- drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c | 2 ++ 3 files changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_clk_mgr.c index 00c4be7c3aa4..ff47af3854b6 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_clk_mgr.c @@ -158,7 +158,6 @@ void dcn31_update_clocks(struct clk_mgr *clk_mgr_base, if (new_clocks->zstate_support != DCN_ZSTATE_SUPPORT_DISALLOW && new_clocks->zstate_support != clk_mgr_base->clks.zstate_support) { dcn31_smu_set_zstate_support(clk_mgr, new_clocks->zstate_support); - dm_helpers_enable_periodic_detection(clk_mgr_base->ctx, true); clk_mgr_base->clks.zstate_support = new_clocks->zstate_support; } @@ -184,7 +183,6 @@ void dcn31_update_clocks(struct clk_mgr *clk_mgr_base, if (new_clocks->zstate_support == DCN_ZSTATE_SUPPORT_DISALLOW && new_clocks->zstate_support != clk_mgr_base->clks.zstate_support) { dcn31_smu_set_zstate_support(clk_mgr, DCN_ZSTATE_SUPPORT_DISALLOW); - dm_helpers_enable_periodic_detection(clk_mgr_base->ctx, false); clk_mgr_base->clks.zstate_support = new_clocks->zstate_support; } diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.c index dd6f11ecb9c9..24f6304011ae 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.c @@ -230,7 +230,6 @@ void dcn314_update_clocks(struct clk_mgr *clk_mgr_base, if (new_clocks->zstate_support != DCN_ZSTATE_SUPPORT_DISALLOW && new_clocks->zstate_support != clk_mgr_base->clks.zstate_support) { dcn314_smu_set_zstate_support(clk_mgr, new_clocks->zstate_support); - dm_helpers_enable_periodic_detection(clk_mgr_base->ctx, true); clk_mgr_base->clks.zstate_support = new_clocks->zstate_support; } @@ -255,7 +254,6 @@ void dcn314_update_clocks(struct clk_mgr *clk_mgr_base, if (new_clocks->zstate_support == DCN_ZSTATE_SUPPORT_DISALLOW && new_clocks->zstate_support != clk_mgr_base->clks.zstate_support) { dcn314_smu_set_zstate_support(clk_mgr, DCN_ZSTATE_SUPPORT_DISALLOW); - dm_helpers_enable_periodic_detection(clk_mgr_base->ctx, false); clk_mgr_base->clks.zstate_support = new_clocks->zstate_support; } diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c index 103013e2a0de..a69824e1eb26 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c @@ -419,6 +419,7 @@ void dcn35_update_clocks(struct clk_mgr *clk_mgr_base, if (new_clocks->zstate_support != DCN_ZSTATE_SUPPORT_DISALLOW && new_clocks->zstate_support != clk_mgr_base->clks.zstate_support) { dcn35_smu_set_zstate_support(clk_mgr, new_clocks->zstate_support); + dm_helpers_enable_periodic_detection(clk_mgr_base->ctx, true); clk_mgr_base->clks.zstate_support = new_clocks->zstate_support; } @@ -438,6 +439,7 @@ void dcn35_update_clocks(struct clk_mgr *clk_mgr_base, if (new_clocks->zstate_support == DCN_ZSTATE_SUPPORT_DISALLOW && new_clocks->zstate_support != clk_mgr_base->clks.zstate_support) { dcn35_smu_set_zstate_support(clk_mgr, DCN_ZSTATE_SUPPORT_DISALLOW); + dm_helpers_enable_periodic_detection(clk_mgr_base->ctx, false); clk_mgr_base->clks.zstate_support = new_clocks->zstate_support; } From 1142738572ef3fcf8b169f1c48d94b4a71cc2d97 Mon Sep 17 00:00:00 2001 From: Andrew Martin Date: Thu, 28 May 2026 10:32:52 -0400 Subject: [PATCH 053/297] drm/amdkfd: Fix SMI event PID reporting for containers SMI events were reporting incorrect PIDs in containerized environments, causing test failures where container processes expected to see their namespace-local PIDs but instead received global host PIDs. The issue had two root causes: 1. Event functions were called from kernel context (page fault handlers, migration workers) where 'current' refers to the kernel worker thread, not the userspace GPU process that triggered the event. 2. PID conversion used task_tgid_vnr() which returns the PID in the caller's namespace (init namespace for kernel threads), not the task's own namespace. This patch updates the SMI event interface: - Change 8 event function signatures to accept task_struct pointer instead of pid_t, allowing proper namespace-aware PID conversion - Convert PIDs using task_tgid_nr_ns(task, task_active_pid_ns(task)) which returns the PID as the process sees it via getpid() - Update 10 call sites to pass p->lead_thread (the GPU process) instead of p->lead_thread->pid or current (kernel worker) This ensures SMI events report container-local PIDs, which is critical for containerized GPU workloads to correctly correlate events with their processes. Tested-by: Andrew Martin Assisted-by: Claude:Sonnet 4-5 Signed-off-by: Andrew Martin Reviewed-by: Harish Kasiviswanathan Signed-off-by: Alex Deucher (cherry picked from commit 60271ec06e04ba5d69d68714f3abdf637d86c257) --- drivers/gpu/drm/amd/amdkfd/kfd_migrate.c | 8 +- drivers/gpu/drm/amd/amdkfd/kfd_process.c | 6 +- drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c | 99 +++++++++++++-------- drivers/gpu/drm/amd/amdkfd/kfd_smi_events.h | 14 +-- drivers/gpu/drm/amd/amdkfd/kfd_svm.c | 6 +- 5 files changed, 77 insertions(+), 56 deletions(-) diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c index 28dc6886c1ff..226e76ae0be7 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c @@ -424,7 +424,7 @@ svm_migrate_vma_to_vram(struct kfd_node *node, struct svm_range *prange, migrate.dst = migrate.src + npages; scratch = (dma_addr_t *)(migrate.dst + npages); - kfd_smi_event_migration_start(node, p->lead_thread->pid, + kfd_smi_event_migration_start(node, p->lead_thread, start >> PAGE_SHIFT, end >> PAGE_SHIFT, 0, node->id, prange->prefetch_loc, prange->preferred_loc, trigger); @@ -462,7 +462,7 @@ svm_migrate_vma_to_vram(struct kfd_node *node, struct svm_range *prange, out_free: kvfree(buf); - kfd_smi_event_migration_end(node, p->lead_thread->pid, + kfd_smi_event_migration_end(node, p->lead_thread, start >> PAGE_SHIFT, end >> PAGE_SHIFT, 0, node->id, trigger, r); out: @@ -727,7 +727,7 @@ svm_migrate_vma_to_ram(struct kfd_node *node, struct svm_range *prange, migrate.fault_page = fault_page; scratch = (dma_addr_t *)(migrate.dst + npages); - kfd_smi_event_migration_start(node, p->lead_thread->pid, + kfd_smi_event_migration_start(node, p->lead_thread, start >> PAGE_SHIFT, end >> PAGE_SHIFT, node->id, 0, prange->prefetch_loc, prange->preferred_loc, trigger); @@ -766,7 +766,7 @@ svm_migrate_vma_to_ram(struct kfd_node *node, struct svm_range *prange, out_free: kvfree(buf); - kfd_smi_event_migration_end(node, p->lead_thread->pid, + kfd_smi_event_migration_end(node, p->lead_thread, start >> PAGE_SHIFT, end >> PAGE_SHIFT, node->id, 0, trigger, r); out: diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c index 368283d53077..63815be995fc 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c @@ -1969,7 +1969,7 @@ int kfd_process_evict_queues(struct kfd_process *p, uint32_t trigger) struct kfd_process_device *pdd = p->pdds[i]; struct device *dev = pdd->dev->adev->dev; - kfd_smi_event_queue_eviction(pdd->dev, p->lead_thread->pid, + kfd_smi_event_queue_eviction(pdd->dev, p->lead_thread, trigger); r = pdd->dev->dqm->ops.evict_process_queues(pdd->dev->dqm, @@ -1999,7 +1999,7 @@ fail: if (n_evicted == 0) break; - kfd_smi_event_queue_restore(pdd->dev, p->lead_thread->pid); + kfd_smi_event_queue_restore(pdd->dev, p->lead_thread); if (pdd->dev->dqm->ops.restore_process_queues(pdd->dev->dqm, &pdd->qpd)) @@ -2022,7 +2022,7 @@ int kfd_process_restore_queues(struct kfd_process *p) struct kfd_process_device *pdd = p->pdds[i]; struct device *dev = pdd->dev->adev->dev; - kfd_smi_event_queue_restore(pdd->dev, p->lead_thread->pid); + kfd_smi_event_queue_restore(pdd->dev, p->lead_thread); r = pdd->dev->dqm->ops.restore_process_queues(pdd->dev->dqm, &pdd->qpd); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c b/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c index dfbde5a571f6..e659cd50eb0b 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c @@ -195,17 +195,35 @@ static void add_event_to_kfifo(pid_t pid, struct kfd_node *dev, rcu_read_unlock(); } +/** + * kfd_smi_task_to_pid - Convert task to namespace-aware PID + * @task: task_struct pointer (typically p->lead_thread) + * + * Returns the PID as it appears in the task's own PID namespace. + * For containerized processes, this returns the container-local PID + * (what getpid() returns), not the global host PID. + * + * Returns 0 if task is NULL. + */ +static inline pid_t kfd_smi_task_to_pid(struct task_struct *task) +{ + return task ? task_tgid_nr_ns(task, task_active_pid_ns(task)) : 0; +} + __printf(4, 5) -static void kfd_smi_event_add(pid_t pid, struct kfd_node *dev, +static void kfd_smi_event_add(struct task_struct *task, struct kfd_node *dev, unsigned int event, char *fmt, ...) { char fifo_in[KFD_SMI_EVENT_MSG_SIZE]; int len; va_list args; + pid_t pid; if (list_empty(&dev->smi_clients)) return; + pid = kfd_smi_task_to_pid(task); + len = snprintf(fifo_in, sizeof(fifo_in), "%x ", event); va_start(args, fmt); @@ -234,14 +252,15 @@ void kfd_smi_event_update_gpu_reset(struct kfd_node *dev, bool post_reset, amdgpu_reset_get_desc(reset_context, reset_cause, sizeof(reset_cause)); - kfd_smi_event_add(0, dev, event, KFD_EVENT_FMT_UPDATE_GPU_RESET( + kfd_smi_event_add(NULL, dev, event, KFD_EVENT_FMT_UPDATE_GPU_RESET( dev->reset_seq_num, reset_cause)); } void kfd_smi_event_update_thermal_throttling(struct kfd_node *dev, uint64_t throttle_bitmask) { - kfd_smi_event_add(0, dev, KFD_SMI_EVENT_THERMAL_THROTTLE, KFD_EVENT_FMT_THERMAL_THROTTLING( + kfd_smi_event_add(NULL, dev, KFD_SMI_EVENT_THERMAL_THROTTLE, + KFD_EVENT_FMT_THERMAL_THROTTLING( throttle_bitmask, amdgpu_dpm_get_thermal_throttling_counter(dev->adev))); } @@ -254,67 +273,67 @@ void kfd_smi_event_update_vmfault(struct kfd_node *dev, uint16_t pasid) if (task_info) { /* Report VM faults from user applications, not retry from kernel */ if (task_info->task.pid) - kfd_smi_event_add(task_info->tgid, dev, - KFD_SMI_EVENT_VMFAULT, - KFD_EVENT_FMT_VMFAULT(task_info->task.pid, - task_info->task.comm)); + kfd_smi_event_add(NULL, dev, KFD_SMI_EVENT_VMFAULT, KFD_EVENT_FMT_VMFAULT( + task_info->task.pid, task_info->task.comm)); amdgpu_vm_put_task_info(task_info); } } -void kfd_smi_event_page_fault_start(struct kfd_node *node, pid_t pid, +void kfd_smi_event_page_fault_start(struct kfd_node *node, struct task_struct *task, unsigned long address, bool write_fault, ktime_t ts) { - kfd_smi_event_add(pid, node, KFD_SMI_EVENT_PAGE_FAULT_START, - KFD_EVENT_FMT_PAGEFAULT_START(ktime_to_ns(ts), pid, - address, node->id, write_fault ? 'W' : 'R')); + kfd_smi_event_add(task, node, KFD_SMI_EVENT_PAGE_FAULT_START, + KFD_EVENT_FMT_PAGEFAULT_START(ktime_to_ns(ts), + kfd_smi_task_to_pid(task), address, node->id, + write_fault ? 'W' : 'R')); } -void kfd_smi_event_page_fault_end(struct kfd_node *node, pid_t pid, +void kfd_smi_event_page_fault_end(struct kfd_node *node, struct task_struct *task, unsigned long address, bool migration) { - kfd_smi_event_add(pid, node, KFD_SMI_EVENT_PAGE_FAULT_END, + kfd_smi_event_add(task, node, KFD_SMI_EVENT_PAGE_FAULT_END, KFD_EVENT_FMT_PAGEFAULT_END(ktime_get_boottime_ns(), - pid, address, node->id, migration ? 'M' : 'U')); + kfd_smi_task_to_pid(task), address, node->id, + migration ? 'M' : 'U')); } -void kfd_smi_event_migration_start(struct kfd_node *node, pid_t pid, +void kfd_smi_event_migration_start(struct kfd_node *node, struct task_struct *task, unsigned long start, unsigned long end, uint32_t from, uint32_t to, uint32_t prefetch_loc, uint32_t preferred_loc, uint32_t trigger) { - kfd_smi_event_add(pid, node, KFD_SMI_EVENT_MIGRATE_START, - KFD_EVENT_FMT_MIGRATE_START( - ktime_get_boottime_ns(), pid, start, end - start, - from, to, prefetch_loc, preferred_loc, trigger)); + kfd_smi_event_add(task, node, KFD_SMI_EVENT_MIGRATE_START, + KFD_EVENT_FMT_MIGRATE_START(ktime_get_boottime_ns(), + kfd_smi_task_to_pid(task), start, end - start, from, + to, prefetch_loc, preferred_loc, trigger)); } -void kfd_smi_event_migration_end(struct kfd_node *node, pid_t pid, +void kfd_smi_event_migration_end(struct kfd_node *node, struct task_struct *task, unsigned long start, unsigned long end, uint32_t from, uint32_t to, uint32_t trigger, int error_code) { - kfd_smi_event_add(pid, node, KFD_SMI_EVENT_MIGRATE_END, - KFD_EVENT_FMT_MIGRATE_END( - ktime_get_boottime_ns(), pid, start, end - start, - from, to, trigger, error_code)); + kfd_smi_event_add(task, node, KFD_SMI_EVENT_MIGRATE_END, + KFD_EVENT_FMT_MIGRATE_END(ktime_get_boottime_ns(), + kfd_smi_task_to_pid(task), start, end - start, from, + to, trigger, error_code)); } -void kfd_smi_event_queue_eviction(struct kfd_node *node, pid_t pid, +void kfd_smi_event_queue_eviction(struct kfd_node *node, struct task_struct *task, uint32_t trigger) { - kfd_smi_event_add(pid, node, KFD_SMI_EVENT_QUEUE_EVICTION, - KFD_EVENT_FMT_QUEUE_EVICTION(ktime_get_boottime_ns(), pid, - node->id, trigger)); + kfd_smi_event_add(task, node, KFD_SMI_EVENT_QUEUE_EVICTION, + KFD_EVENT_FMT_QUEUE_EVICTION(ktime_get_boottime_ns(), + kfd_smi_task_to_pid(task), node->id, trigger)); } -void kfd_smi_event_queue_restore(struct kfd_node *node, pid_t pid) +void kfd_smi_event_queue_restore(struct kfd_node *node, struct task_struct *task) { - kfd_smi_event_add(pid, node, KFD_SMI_EVENT_QUEUE_RESTORE, - KFD_EVENT_FMT_QUEUE_RESTORE(ktime_get_boottime_ns(), pid, - node->id, '0')); + kfd_smi_event_add(task, node, KFD_SMI_EVENT_QUEUE_RESTORE, + KFD_EVENT_FMT_QUEUE_RESTORE(ktime_get_boottime_ns(), + kfd_smi_task_to_pid(task), node->id, '0')); } void kfd_smi_event_queue_restore_rescheduled(struct mm_struct *mm) @@ -329,21 +348,23 @@ void kfd_smi_event_queue_restore_rescheduled(struct mm_struct *mm) for (i = 0; i < p->n_pdds; i++) { struct kfd_process_device *pdd = p->pdds[i]; - kfd_smi_event_add(p->lead_thread->pid, pdd->dev, + kfd_smi_event_add(p->lead_thread, pdd->dev, KFD_SMI_EVENT_QUEUE_RESTORE, KFD_EVENT_FMT_QUEUE_RESTORE(ktime_get_boottime_ns(), - p->lead_thread->pid, pdd->dev->id, 'R')); + kfd_smi_task_to_pid(p->lead_thread), + pdd->dev->id, 'R')); } kfd_unref_process(p); } -void kfd_smi_event_unmap_from_gpu(struct kfd_node *node, pid_t pid, +void kfd_smi_event_unmap_from_gpu(struct kfd_node *node, struct task_struct *task, unsigned long address, unsigned long last, uint32_t trigger) { - kfd_smi_event_add(pid, node, KFD_SMI_EVENT_UNMAP_FROM_GPU, + kfd_smi_event_add(task, node, KFD_SMI_EVENT_UNMAP_FROM_GPU, KFD_EVENT_FMT_UNMAP_FROM_GPU(ktime_get_boottime_ns(), - pid, address, last - address + 1, node->id, trigger)); + kfd_smi_task_to_pid(task), address, + last - address + 1, node->id, trigger)); } void kfd_smi_event_process(struct kfd_process_device *pdd, bool start) @@ -358,7 +379,7 @@ void kfd_smi_event_process(struct kfd_process_device *pdd, bool start) task_info = amdgpu_vm_get_task_info_vm(avm); if (task_info) { - kfd_smi_event_add(task_info->tgid, pdd->dev, + kfd_smi_event_add(NULL, pdd->dev, start ? KFD_SMI_EVENT_PROCESS_START : KFD_SMI_EVENT_PROCESS_END, KFD_EVENT_FMT_PROCESS(task_info->task.pid, @@ -387,7 +408,7 @@ int kfd_smi_event_open(struct kfd_node *dev, uint32_t *fd) spin_lock_init(&client->lock); client->events = 0; client->dev = dev; - client->pid = current->tgid; + client->pid = kfd_smi_task_to_pid(current); client->suser = capable(CAP_SYS_ADMIN); spin_lock(&dev->smi_lock); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.h b/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.h index bb4d72b57387..afa93d7cfa7f 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.h @@ -32,25 +32,25 @@ void kfd_smi_event_update_thermal_throttling(struct kfd_node *dev, uint64_t throttle_bitmask); void kfd_smi_event_update_gpu_reset(struct kfd_node *dev, bool post_reset, struct amdgpu_reset_context *reset_context); -void kfd_smi_event_page_fault_start(struct kfd_node *node, pid_t pid, +void kfd_smi_event_page_fault_start(struct kfd_node *node, struct task_struct *task, unsigned long address, bool write_fault, ktime_t ts); -void kfd_smi_event_page_fault_end(struct kfd_node *node, pid_t pid, +void kfd_smi_event_page_fault_end(struct kfd_node *node, struct task_struct *task, unsigned long address, bool migration); -void kfd_smi_event_migration_start(struct kfd_node *node, pid_t pid, +void kfd_smi_event_migration_start(struct kfd_node *node, struct task_struct *task, unsigned long start, unsigned long end, uint32_t from, uint32_t to, uint32_t prefetch_loc, uint32_t preferred_loc, uint32_t trigger); -void kfd_smi_event_migration_end(struct kfd_node *node, pid_t pid, +void kfd_smi_event_migration_end(struct kfd_node *node, struct task_struct *task, unsigned long start, unsigned long end, uint32_t from, uint32_t to, uint32_t trigger, int error_code); -void kfd_smi_event_queue_eviction(struct kfd_node *node, pid_t pid, +void kfd_smi_event_queue_eviction(struct kfd_node *node, struct task_struct *task, uint32_t trigger); -void kfd_smi_event_queue_restore(struct kfd_node *node, pid_t pid); +void kfd_smi_event_queue_restore(struct kfd_node *node, struct task_struct *task); void kfd_smi_event_queue_restore_rescheduled(struct mm_struct *mm); -void kfd_smi_event_unmap_from_gpu(struct kfd_node *node, pid_t pid, +void kfd_smi_event_unmap_from_gpu(struct kfd_node *node, struct task_struct *task, unsigned long address, unsigned long last, uint32_t trigger); void kfd_smi_event_process(struct kfd_process_device *pdd, bool start); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c index 3841943da5ec..d64d104783d4 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c @@ -1408,7 +1408,7 @@ svm_range_unmap_from_gpus(struct svm_range *prange, unsigned long start, return -EINVAL; } - kfd_smi_event_unmap_from_gpu(pdd->dev, p->lead_thread->pid, + kfd_smi_event_unmap_from_gpu(pdd->dev, p->lead_thread, start, last, trigger); r = svm_range_unmap_from_gpu(pdd->dev->adev, @@ -3205,7 +3205,7 @@ retry_write_locked: svms, prange->start, prange->last, best_loc, prange->actual_loc); - kfd_smi_event_page_fault_start(node, p->lead_thread->pid, addr, + kfd_smi_event_page_fault_start(node, p->lead_thread, addr, write_fault, timestamp); /* Align migration range start and size to granularity size */ @@ -3248,7 +3248,7 @@ retry_write_locked: r, svms, start, last); out_migrate_fail: - kfd_smi_event_page_fault_end(node, p->lead_thread->pid, addr, + kfd_smi_event_page_fault_end(node, p->lead_thread, addr, migration); out_unlock_range: From 3d3372add033528ca90d1949abb52142504f5d23 Mon Sep 17 00:00:00 2001 From: Prike Liang Date: Fri, 5 Jun 2026 15:28:40 +0800 Subject: [PATCH 054/297] drm/amdgpu: allocate lockdep mutex on the heap to fix stack overflow Replace the stack-allocated amdgpu_lockdep mutex with a heap allocation via kmalloc to fix a stack overflow caused by the large struct size. Signed-off-by: Prike Liang Reviewed-by: Vitaly Prosyak Signed-off-by: Alex Deucher (cherry picked from commit dbae980eefb2f46f31cee12f1f8540d0d79f61ae) --- drivers/gpu/drm/amd/amdgpu/amdgpu_lockdep.c | 103 ++++++++++---------- 1 file changed, 53 insertions(+), 50 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_lockdep.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_lockdep.c index d5d71fd7c70d..61450af539a6 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_lockdep.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_lockdep.c @@ -16,6 +16,17 @@ #ifdef CONFIG_LOCKDEP +struct amdgpu_lockdep_dummy_locks { + struct mutex reset_lock; + struct mutex userq_sch_mutex; + struct mutex userq_mutex; + struct mutex notifier_lock; + struct mutex vram_lock; + struct mutex srbm_mutex; + struct mutex grbm_idx_mutex; + spinlock_t mmio_idx_lock; +}; + /* Lock class keys for associating with real driver locks */ static struct lock_class_key amdgpu_userq_sch_mutex_key; static struct lock_class_key amdgpu_userq_mutex_key; @@ -84,72 +95,65 @@ void amdgpu_lockdep_set_class(struct amdgpu_device *adev) int amdgpu_lockdep_init(void) { struct amdgpu_reset_domain *reset_domain = NULL; - struct amdgpu_reset_control reset_ctl; - struct mutex userq_sch_mutex; - struct mutex userq_mutex; - struct mutex notifier_lock; - struct mutex vram_lock; - struct mutex srbm_mutex; - struct mutex grbm_idx_mutex; - spinlock_t mmio_idx_lock; + struct amdgpu_lockdep_dummy_locks *locks; unsigned long flags; + locks = kzalloc(sizeof(*locks), GFP_KERNEL); + if (!locks) + return -ENOMEM; + /* * Initialize dummy reset domain */ reset_domain = amdgpu_reset_create_reset_domain(SINGLE_DEVICE, "lockdep_test"); - if (!reset_domain) + if (!reset_domain) { + kfree(locks); return -ENOMEM; - + } /* Initialize dummy locks */ - mutex_init(&userq_sch_mutex); - mutex_init(&userq_mutex); - mutex_init(¬ifier_lock); - mutex_init(&vram_lock); - mutex_init(&reset_ctl.reset_lock); - mutex_init(&srbm_mutex); - mutex_init(&grbm_idx_mutex); - spin_lock_init(&mmio_idx_lock); + mutex_init(&locks->userq_sch_mutex); + mutex_init(&locks->userq_mutex); + mutex_init(&locks->notifier_lock); + mutex_init(&locks->vram_lock); + mutex_init(&locks->reset_lock); + mutex_init(&locks->srbm_mutex); + mutex_init(&locks->grbm_idx_mutex); + spin_lock_init(&locks->mmio_idx_lock); /* * Associate dummy locks with the same class keys used for real * driver locks. This ensures lockdep connects the ordering learned * here with the actual locks used at runtime. */ - lockdep_set_class(&userq_sch_mutex, &amdgpu_userq_sch_mutex_key); - lockdep_set_class(&userq_mutex, &amdgpu_userq_mutex_key); - lockdep_set_class(¬ifier_lock, &amdgpu_notifier_lock_key); - lockdep_set_class(&vram_lock, &amdgpu_vram_lock_key); + lockdep_set_class(&locks->userq_sch_mutex, &amdgpu_userq_sch_mutex_key); + lockdep_set_class(&locks->userq_mutex, &amdgpu_userq_mutex_key); + lockdep_set_class(&locks->notifier_lock, &amdgpu_notifier_lock_key); + lockdep_set_class(&locks->vram_lock, &amdgpu_vram_lock_key); lockdep_set_class(&reset_domain->sem, &amdgpu_reset_sem_key); - lockdep_set_class(&reset_ctl.reset_lock, &amdgpu_reset_lock_key); - lockdep_set_class(&srbm_mutex, &amdgpu_srbm_lock_key); - lockdep_set_class(&grbm_idx_mutex, &amdgpu_grbm_lock_key); - lockdep_set_class(&mmio_idx_lock, &amdgpu_mmio_lock_key); - + lockdep_set_class(&locks->reset_lock, &amdgpu_reset_lock_key); + lockdep_set_class(&locks->srbm_mutex, &amdgpu_srbm_lock_key); + lockdep_set_class(&locks->grbm_idx_mutex, &amdgpu_grbm_lock_key); + lockdep_set_class(&locks->mmio_idx_lock, &amdgpu_mmio_lock_key); /* * Take locks in the correct order to train lockdep. * This establishes the dependency chain. */ /* Level 1: Global userq scheduler mutex (outermost) */ - mutex_lock(&userq_sch_mutex); + mutex_lock(&locks->userq_sch_mutex); /* Level 2: Per-context userq mutex */ - mutex_lock(&userq_mutex); - + mutex_lock(&locks->userq_mutex); /* Level 3: MMU notifier lock */ - mutex_lock(¬ifier_lock); - + mutex_lock(&locks->notifier_lock); /* Level 4: VRAM allocator lock */ - mutex_lock(&vram_lock); - + mutex_lock(&locks->vram_lock); /* Level 5: Reset domain semaphore */ down_read(&reset_domain->sem); /* Level 6: Reset control lock */ - mutex_lock(&reset_ctl.reset_lock); - + mutex_lock(&locks->reset_lock); /* * Mark potential memory reclaim boundary. * GPU operations might trigger memory allocation/reclaim. @@ -157,36 +161,35 @@ int amdgpu_lockdep_init(void) fs_reclaim_acquire(GFP_KERNEL); /* Level 7: SRBM register access */ - mutex_lock(&srbm_mutex); - + mutex_lock(&locks->srbm_mutex); /* Level 8: GRBM index access */ - mutex_lock(&grbm_idx_mutex); + mutex_lock(&locks->grbm_idx_mutex); /* Level 9: MMIO index access (innermost lock, spinlock) */ - spin_lock_irqsave(&mmio_idx_lock, flags); - + spin_lock_irqsave(&locks->mmio_idx_lock, flags); /* * All locks acquired in order. * Lockdep has now learned the valid dependency chain. */ /* Release in reverse order */ - spin_unlock_irqrestore(&mmio_idx_lock, flags); - mutex_unlock(&grbm_idx_mutex); - mutex_unlock(&srbm_mutex); - + spin_unlock_irqrestore(&locks->mmio_idx_lock, flags); + mutex_unlock(&locks->grbm_idx_mutex); + mutex_unlock(&locks->srbm_mutex); fs_reclaim_release(GFP_KERNEL); - mutex_unlock(&reset_ctl.reset_lock); + mutex_unlock(&locks->reset_lock); up_read(&reset_domain->sem); - mutex_unlock(&vram_lock); - mutex_unlock(¬ifier_lock); - mutex_unlock(&userq_mutex); - mutex_unlock(&userq_sch_mutex); + + mutex_unlock(&locks->vram_lock); + mutex_unlock(&locks->notifier_lock); + mutex_unlock(&locks->userq_mutex); + mutex_unlock(&locks->userq_sch_mutex); /* Cleanup */ amdgpu_reset_put_reset_domain(reset_domain); + kfree(locks); pr_info("AMDGPU: Lockdep annotations initialized (9 lock levels)\n"); return 0; From 3e864bf2a32a1cbdf1e0f9c5a5a4176e8575f4a3 Mon Sep 17 00:00:00 2001 From: Asad Kamal Date: Fri, 5 Jun 2026 23:44:08 +0800 Subject: [PATCH 055/297] drm/amdgpu/gfx: fix cleaner shader IB buffer overflow The cleaner shader sysfs path allocates a 16-dword (64 byte) IB but incorrectly fills (align_mask + 1) dwords. On GFX rings align_mask is 0xff, so the loop wrote 256 dwords into a 64-byte buffer, causing a kernel page fault. The IB only needs to be a minimal NOP shell to schedule the job; the cleaner shader itself is emitted on the ring via emit_cleaner_shader(). Fill 16 dwords to match the allocation. v2: Use ib_size_dw variable (Lijo) Fixes: d361ad5d2fc0 ("drm/amdgpu: Add sysfs interface for running cleaner shader") Suggested-by: Lijo Lazar Signed-off-by: Asad Kamal Reviewed-by: Lijo Lazar Signed-off-by: Alex Deucher (cherry picked from commit bf21af331ebf72d0935fd70c73192414a422c03a) CC: stable@vger.kernel.org --- drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c index 1e190fb54a97..85372af1216d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c @@ -1664,12 +1664,13 @@ static int amdgpu_gfx_run_cleaner_shader_job(struct amdgpu_ring *ring) struct amdgpu_device *adev = ring->adev; struct drm_gpu_scheduler *sched = &ring->sched; struct drm_sched_entity entity; + unsigned int ib_size_dw = 16; static atomic_t counter; struct dma_fence *f; struct amdgpu_job *job; struct amdgpu_ib *ib; void *owner; - int i, r; + int r; /* Initialize the scheduler entity */ r = drm_sched_entity_init(&entity, DRM_SCHED_PRIORITY_NORMAL, @@ -1687,7 +1688,7 @@ static int amdgpu_gfx_run_cleaner_shader_job(struct amdgpu_ring *ring) owner = (void *)(unsigned long)atomic_inc_return(&counter); r = amdgpu_job_alloc_with_ib(ring->adev, &entity, owner, - 64, 0, &job, + ib_size_dw * sizeof(uint32_t), 0, &job, AMDGPU_KERNEL_JOB_ID_CLEANER_SHADER); if (r) goto err; @@ -1697,9 +1698,8 @@ static int amdgpu_gfx_run_cleaner_shader_job(struct amdgpu_ring *ring) job->run_cleaner_shader = true; ib = &job->ibs[0]; - for (i = 0; i <= ring->funcs->align_mask; ++i) - ib->ptr[i] = ring->funcs->nop; - ib->length_dw = ring->funcs->align_mask + 1; + memset32(ib->ptr, ring->funcs->nop, ib_size_dw); + ib->length_dw = ib_size_dw; f = amdgpu_job_submit(job); From 40f9e2f514924312ea737c1c16ba945a5a7e374d Mon Sep 17 00:00:00 2001 From: James Lin Date: Fri, 12 Jun 2026 10:05:29 -0400 Subject: [PATCH 056/297] drm/amd/display: Add IN_FORMATS_ASYNC support for planes [Why] The DRM core exposes an IN_FORMATS_ASYNC plane property describing the set of format/modifier pairs that are valid for asynchronous (immediate) page flips. amdgpu already advertises async page flip support via mode_config.async_page_flip = true, but never implemented the .format_mod_supported_async plane callback, so the IN_FORMATS_ASYNC property was not created. This inconsistency (advertising async flips while exposing IN_FORMATS but no IN_FORMATS_ASYNC) causes userspace, such as igt-gpu-tools, to emit a repeated warning during plane initialization, which in turn demotes many otherwise passing KMS subtests to a WARN result. [How] Wire up .format_mod_supported_async to the existing amdgpu_dm_plane_format_mod_supported callback so the async format list is populated. amdgpu does not restrict async flips at the format/modifier level: the async flip constraints are enforced at atomic check and commit time and only require a fast update (no change to FB pitch, DCC state, rotation or memory type) between the old and new buffers. Therefore the set of formats/modifiers valid for async flips is identical to the regular IN_FORMATS set, and the same callback can be reused. Reviewed-by: Aurabindo Pillai Signed-off-by: James Lin Signed-off-by: Ivan Lipski Signed-off-by: Alex Deucher (cherry picked from commit 8e2d7bbd6b184c0c1b0fe7cb404c9b5214d89931) --- drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c index e957657b06c7..c7f8e08feaf4 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c @@ -1859,6 +1859,7 @@ static const struct drm_plane_funcs dm_plane_funcs = { .atomic_duplicate_state = amdgpu_dm_plane_drm_plane_duplicate_state, .atomic_destroy_state = amdgpu_dm_plane_drm_plane_destroy_state, .format_mod_supported = amdgpu_dm_plane_format_mod_supported, + .format_mod_supported_async = amdgpu_dm_plane_format_mod_supported, #ifdef AMD_PRIVATE_COLOR .atomic_set_property = dm_atomic_plane_set_property, .atomic_get_property = dm_atomic_plane_get_property, From 8e792f018e10e68f488f279fbd4f38009a2e066d Mon Sep 17 00:00:00 2001 From: Matthew Schwartz Date: Thu, 11 Jun 2026 08:44:38 -0700 Subject: [PATCH 057/297] drm/amd/display: Fix mem_type change detection for async flips [Why] amdgpu_dm_crtc_mem_type_changed() fetches the "old" and "new" plane state with two drm_atomic_get_plane_state() calls, which both return the new state. It compares a state against itself, so it never detects a mem_type change and never rejects the async flip. On DCN 3.0.1, this shows up as intermittent corruption when a single DCC plane is scanned out with immediate flips under gamescope and its buffer moves between the VRAM carveout and GTT. [How] Use drm_atomic_get_old_plane_state() and drm_atomic_get_new_plane_state() to compare the actual old and new states. These return NULL rather than an error pointer for a plane that is not part of the commit, so the IS_ERR() check becomes a NULL check that skips those planes, such as an unmodified cursor still in the CRTC's plane_mask. Fixes: 4caacd1671b7 ("drm/amd/display: Do not elevate mem_type change to full update") Reviewed-by: Harry Wentland Reviewed-by: Melissa Wen Signed-off-by: Matthew Schwartz Signed-off-by: Alex Deucher (cherry picked from commit 13158e5dbd896281f3e9982b5437cffa5fd621b2) --- drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index 1ed697a3a453..eb5696b5daeb 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -12938,13 +12938,11 @@ static bool amdgpu_dm_crtc_mem_type_changed(struct drm_device *dev, struct drm_plane_state *new_plane_state, *old_plane_state; drm_for_each_plane_mask(plane, dev, crtc_state->plane_mask) { - new_plane_state = drm_atomic_get_plane_state(state, plane); - old_plane_state = drm_atomic_get_plane_state(state, plane); + new_plane_state = drm_atomic_get_new_plane_state(state, plane); + old_plane_state = drm_atomic_get_old_plane_state(state, plane); - if (IS_ERR(new_plane_state) || IS_ERR(old_plane_state)) { - drm_err(dev, "Failed to get plane state for plane %s\n", plane->name); - return false; - } + if (!old_plane_state || !new_plane_state) + continue; if (old_plane_state->fb && new_plane_state->fb && get_mem_type(old_plane_state->fb) != get_mem_type(new_plane_state->fb)) From f896e86273dbbebb5eac966b4a201b5c62a02e9a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Pavel=20Ondra=C4=8Dka?= Date: Wed, 10 Jun 2026 10:32:45 +0200 Subject: [PATCH 058/297] drm/radeon: fix r100_copy_blit for large BOs MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit r100_copy_blit() copies BOs as 1024-pixel-wide ARGB8888 blits, so one GPU page becomes one blit row. Large copies are split into chunks of at most 8191 rows. The kernel register header names the packet coordinate dwords SRC_Y_X and DST_Y_X. In the BITBLT_MULTI description in R5xx_Acceleration_v1.5.pdf docs, these correspond to [SRC_X1 | SRC_Y1] and [DST_X1 | DST_Y1], which are signed 13-bit coordinates in the -8192..8191 range. The old code kept SRC/DST_PITCH_OFFSET at the BO base and used SRC_Y_X/DST_Y_X as the chunk address, so large BO moves could exceed that coordinate range. Compute per-chunk SRC/DST_PITCH_OFFSET bases and emit zero source and destination coordinates. r100_copy_blit() already packs SRC/DST_PITCH_OFFSET as pitch plus base offset, so large chunk addresses belong there rather than in the coordinate fields. This fixes Prison Architect corruption with 4096x4096 mipped textures after they are evicted to GTT under memory pressure on RV530. Closes: https://gitlab.freedesktop.org/mesa/mesa/-/work_items/6716 Acked-by: Christian König Signed-off-by: Pavel Ondračka Signed-off-by: Alex Deucher (cherry picked from commit 87be26aee76239c6da03e599f238a426897f78ad) Cc: stable@vger.kernel.org --- drivers/gpu/drm/radeon/r100.c | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/radeon/r100.c b/drivers/gpu/drm/radeon/r100.c index 3ac1a79b6f13..533215d6e9cb 100644 --- a/drivers/gpu/drm/radeon/r100.c +++ b/drivers/gpu/drm/radeon/r100.c @@ -906,6 +906,7 @@ struct radeon_fence *r100_copy_blit(struct radeon_device *rdev, { struct radeon_ring *ring = &rdev->ring[RADEON_RING_TYPE_GFX_INDEX]; struct radeon_fence *fence; + uint64_t cur_src_offset, cur_dst_offset; uint32_t cur_pages; uint32_t stride_bytes = RADEON_GPU_PAGE_SIZE; uint32_t pitch; @@ -934,6 +935,10 @@ struct radeon_fence *r100_copy_blit(struct radeon_device *rdev, cur_pages = 8191; } num_gpu_pages -= cur_pages; + cur_src_offset = src_offset + + (uint64_t)num_gpu_pages * RADEON_GPU_PAGE_SIZE; + cur_dst_offset = dst_offset + + (uint64_t)num_gpu_pages * RADEON_GPU_PAGE_SIZE; /* pages are in Y direction - height page width in X direction - width */ @@ -950,13 +955,13 @@ struct radeon_fence *r100_copy_blit(struct radeon_device *rdev, RADEON_DP_SRC_SOURCE_MEMORY | RADEON_GMC_CLR_CMP_CNTL_DIS | RADEON_GMC_WR_MSK_DIS); - radeon_ring_write(ring, (pitch << 22) | (src_offset >> 10)); - radeon_ring_write(ring, (pitch << 22) | (dst_offset >> 10)); + radeon_ring_write(ring, (pitch << 22) | (cur_src_offset >> 10)); + radeon_ring_write(ring, (pitch << 22) | (cur_dst_offset >> 10)); radeon_ring_write(ring, (0x1fff) | (0x1fff << 16)); radeon_ring_write(ring, 0); radeon_ring_write(ring, (0x1fff) | (0x1fff << 16)); - radeon_ring_write(ring, num_gpu_pages); - radeon_ring_write(ring, num_gpu_pages); + radeon_ring_write(ring, 0); + radeon_ring_write(ring, 0); radeon_ring_write(ring, cur_pages | (stride_pixels << 16)); } radeon_ring_write(ring, PACKET0(RADEON_DSTCACHE_CTLSTAT, 0)); From 8fa5655da368d0306c03e9dc9cda8ae2a7840926 Mon Sep 17 00:00:00 2001 From: Mario Limonciello Date: Fri, 12 Jun 2026 21:22:04 -0500 Subject: [PATCH 059/297] drm/amdkfd: fix list_del corruption in kfd_criu_resume_svm The cleanup tail of kfd_criu_resume_svm() walks svms->criu_svm_metadata_list and kfree()s each struct criu_svm_metadata without removing it from the list. The list head is left pointing at freed kmalloc-96 objects. A second AMDKFD_IOC_CRIU_OP from the same process re-enters: list_empty() reads the dangling ->next (use-after-free), the loop walks freed entries, and each is kfree()'d again (double-free). This is reachable by an unprivileged render-group user via /dev/kfd with no capabilities required. Add list_del() before the kfree() so the list is properly emptied. The list_for_each_entry_safe() iterator already caches the next pointer, so unlinking during the walk is safe. Fixes: 2a909ae71871 ("drm/amdkfd: CRIU resume shared virtual memory ranges") Reviewed-by: Alex Deucher Signed-off-by: Mario Limonciello Signed-off-by: Alex Deucher (cherry picked from commit 6322d278a298e2c1430b9d2697743d3a04b788b1) --- drivers/gpu/drm/amd/amdkfd/kfd_svm.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c index d64d104783d4..5a56d86b3ecf 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c @@ -4115,6 +4115,7 @@ exit: list_for_each_entry_safe(criu_svm_md, next, &svms->criu_svm_metadata_list, list) { pr_debug("freeing criu_svm_md[]\n\tstart: 0x%llx\n", criu_svm_md->data.start_addr); + list_del(&criu_svm_md->list); kfree(criu_svm_md); } From a2b270c0ecf6d95bcd14ef4c20d0301a88143ff5 Mon Sep 17 00:00:00 2001 From: Thadeu Lima de Souza Cascardo Date: Mon, 8 Jun 2026 16:22:35 -0300 Subject: [PATCH 060/297] drm/amdgpu: initialize irq.lock spinlock earlier If there is an early failure during amdgpu probe, like missing firmware, it will end up calling amdgpu_irq_disable_all, which takes irq.lock spinlock without it being initialized. Initializing irq.lock earlier at amdgpu_device_init fixes the issue. [ 79.334079] INFO: trying to register non-static key. [ 79.334081] The code is fine but needs lockdep annotation, or maybe [ 79.334083] you didn't initialize this object before use? [ 79.334084] turning off the locking correctness validator. [ 79.334088] CPU: 2 UID: 0 PID: 1819 Comm: bash Not tainted 7.1.0-rc5-gfd06300b2348 #96 PREEMPT 8e8f461221633dae3c832d6689eaf0546c0ed4cd [ 79.334092] Hardware name: Valve Jupiter/Jupiter, BIOS F7A0133 08/05/2024 [ 79.334094] Call Trace: [ 79.334095] [ 79.334097] dump_stack_lvl+0x5d/0x80 [ 79.334103] register_lock_class+0x7af/0x7c0 [ 79.334109] __lock_acquire+0x416/0x2610 [ 79.334114] lock_acquire+0xcf/0x310 [ 79.334117] ? amdgpu_irq_disable_all+0x3b/0xf0 [amdgpu c88bab43d391d519ad0d5c8e5a099b4aceefa180] [ 79.334503] ? _raw_spin_lock_irqsave+0x53/0x60 [ 79.334508] _raw_spin_lock_irqsave+0x3f/0x60 [ 79.334510] ? amdgpu_irq_disable_all+0x3b/0xf0 [amdgpu c88bab43d391d519ad0d5c8e5a099b4aceefa180] [ 79.334881] amdgpu_irq_disable_all+0x3b/0xf0 [amdgpu c88bab43d391d519ad0d5c8e5a099b4aceefa180] [ 79.335240] amdgpu_device_fini_hw+0x90/0x32c [amdgpu c88bab43d391d519ad0d5c8e5a099b4aceefa180] [ 79.335704] amdgpu_driver_load_kms.cold+0x22/0x44 [amdgpu c88bab43d391d519ad0d5c8e5a099b4aceefa180] [ 79.336159] amdgpu_pci_probe+0x204/0x440 [amdgpu c88bab43d391d519ad0d5c8e5a099b4aceefa180] [ 79.336494] local_pci_probe+0x3c/0x80 [ 79.336500] pci_call_probe+0x55/0x2e0 [ 79.336505] ? _raw_spin_unlock+0x2d/0x50 [ 79.336508] ? pci_match_device+0x157/0x180 [ 79.336512] pci_device_probe+0x9b/0x170 [ 79.336516] really_probe+0xd5/0x370 [ 79.336521] __driver_probe_device+0x84/0x150 [ 79.336525] device_driver_attach+0x47/0xb0 [ 79.336528] bind_store+0x73/0xc0 [ 79.336531] kernfs_fop_write_iter+0x176/0x250 [ 79.336536] vfs_write+0x24d/0x560 [ 79.336542] ksys_write+0x71/0xe0 [ 79.336546] do_syscall_64+0x122/0x710 [ 79.336550] ? do_syscall_64+0xd1/0x710 [ 79.336553] entry_SYSCALL_64_after_hwframe+0x4b/0x53 [ 79.336557] RIP: 0033:0x7f92fd675006 [ 79.336561] Code: 5d e8 41 8b 93 08 03 00 00 59 5e 48 83 f8 fc 75 19 83 e2 39 83 fa 08 75 11 e8 26 ff ff ff 66 0f 1f 44 00 00 48 8b 45 10 0f 05 <48> 8b 5d f8 c9 c3 0f 1f 40 00 f3 0f 1e fa 55 48 89 e5 48 83 ec 08 [ 79.336562] RSP: 002b:00007ffe4fa867a0 EFLAGS: 00000202 ORIG_RAX: 0000000000000001 [ 79.336565] RAX: ffffffffffffffda RBX: 000000000000000d RCX: 00007f92fd675006 [ 79.336567] RDX: 000000000000000d RSI: 000055b2dfce59b0 RDI: 0000000000000001 [ 79.336568] RBP: 00007ffe4fa867c0 R08: 0000000000000000 R09: 0000000000000000 [ 79.336569] R10: 0000000000000000 R11: 0000000000000202 R12: 000000000000000d [ 79.336570] R13: 000055b2dfce59b0 R14: 00007f92fd7ca5c0 R15: 000055b2dfdbaf70 [ 79.336574] Fixes: 9950cda2a018 ("drm/amdgpu: drop the drm irq pre/post/un install callbacks") Reviewed-by: Tvrtko Ursulin Signed-off-by: Thadeu Lima de Souza Cascardo Signed-off-by: Alex Deucher (cherry picked from commit 7dba3e10ecdeec85208e255853fcd3890880b10e) --- drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 2 ++ drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c | 2 -- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 0fa2ce36c2ea..211d30f03d25 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -3771,6 +3771,8 @@ int amdgpu_device_init(struct amdgpu_device *adev, mutex_init(&adev->gfx.workload_profile_mutex); mutex_init(&adev->vcn.workload_profile_mutex); + spin_lock_init(&adev->irq.lock); + amdgpu_device_init_apu_flags(adev); r = amdgpu_device_check_arguments(adev); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c index 254a4e983f40..40b8506ac66f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c @@ -309,8 +309,6 @@ int amdgpu_irq_init(struct amdgpu_device *adev) unsigned int irq, flags; int r; - spin_lock_init(&adev->irq.lock); - /* Enable MSI if not disabled by module parameter */ adev->irq.msi_enabled = false; From 93475c34111916df71c63e510fc52db01351f809 Mon Sep 17 00:00:00 2001 From: Mario Limonciello Date: Fri, 12 Jun 2026 21:11:53 -0500 Subject: [PATCH 061/297] drm/amdgpu: check amdgpu_vm_bo_find() result in GET_MAPPING_INFO The AMDGPU_GEM_OP_GET_MAPPING_INFO path of amdgpu_gem_op_ioctl() looks up the bo_va for the buffer object in the caller's VM via amdgpu_vm_bo_find(), but uses the returned pointer without checking it. amdgpu_vm_bo_find() returns NULL when the BO has no bo_va in that VM, which is the normal case for a BO that has never been mapped. The result is fed straight into amdgpu_vm_bo_va_for_each_valid_mapping(), which expands to list_for_each_entry(mapping, &(bo_va)->valids, list) and dereferences bo_va, causing a NULL pointer dereference. This is reachable by any process able to issue the ioctl (render group) simply by requesting mapping info for an unmapped BO. Return -ENOENT when no bo_va is found, jumping to out_exec so the drm_exec context and GEM object reference are released. Fixes: 4d82724f7f2b ("drm/amdgpu: Add mapping info option for GEM_OP ioctl") Reviewed-by: Alex Deucher Signed-off-by: Mario Limonciello Signed-off-by: Alex Deucher (cherry picked from commit 528b19377affc1cc7362a70a254c1dda793595f9) Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c index 212c14d99f6b..76da3f932f24 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c @@ -1094,6 +1094,11 @@ int amdgpu_gem_op_ioctl(struct drm_device *dev, void *data, * If that number is larger than the size of the array, the ioctl must * be retried. */ + if (!bo_va) { + r = -ENOENT; + goto out_exec; + } + if (args->num_entries > INT_MAX / sizeof(*vm_entries)) { r = -EINVAL; goto out_exec; From 84c4c36acd5c4b2558b5069f869a165b2c655c84 Mon Sep 17 00:00:00 2001 From: Mario Limonciello Date: Fri, 12 Jun 2026 21:07:24 -0500 Subject: [PATCH 062/297] drm/amdgpu: validate CP_GFX_SHADOW chunk size in CS pass1 Add a minimum-length check for the AMDGPU_CHUNK_ID_CP_GFX_SHADOW chunk in amdgpu_cs_pass1(), matching the gate already present for the IB, FENCE and BO_HANDLES chunk types. The CP_GFX_SHADOW case previously shared a bare break with the dependency and syncobj chunk types, which do not dereference a fixed-size struct. When userspace submits this chunk with length_dw == 0, vmemdup_array_user() is called with size 0 and returns ZERO_SIZE_PTR, which passes the IS_ERR() check. amdgpu_cs_p2_shadow() then dereferences chunk->kdata as a struct drm_amdgpu_cs_chunk_cp_gfx_shadow (reading shadow->flags), faulting on the ZERO_SIZE_PTR and causing a NULL-pointer dereference. This is reachable by an unprivileged process in the render group. Reject undersized chunks with -EINVAL during pass1 so the bad submission is rejected before pass2 ever dereferences the data. Fixes: ac9287055ff1 ("drm/amdgpu: add gfx shadow CS IOCTL support") Reviewed-by: Alex Deucher Signed-off-by: Mario Limonciello Signed-off-by: Alex Deucher (cherry picked from commit 7f61b2eef7415eccdb40850aca0de94211948657) Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c index 115b134b4cd1..c2e6495a28bc 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c @@ -247,13 +247,17 @@ static int amdgpu_cs_pass1(struct amdgpu_cs_parser *p, goto free_partial_kdata; break; + case AMDGPU_CHUNK_ID_CP_GFX_SHADOW: + if (size < sizeof(struct drm_amdgpu_cs_chunk_cp_gfx_shadow)) + goto free_partial_kdata; + break; + case AMDGPU_CHUNK_ID_DEPENDENCIES: case AMDGPU_CHUNK_ID_SYNCOBJ_IN: case AMDGPU_CHUNK_ID_SYNCOBJ_OUT: case AMDGPU_CHUNK_ID_SCHEDULED_DEPENDENCIES: case AMDGPU_CHUNK_ID_SYNCOBJ_TIMELINE_WAIT: case AMDGPU_CHUNK_ID_SYNCOBJ_TIMELINE_SIGNAL: - case AMDGPU_CHUNK_ID_CP_GFX_SHADOW: break; default: From d072a3f603c639ee12a05126aa0bab0ff1732323 Mon Sep 17 00:00:00 2001 From: Geoffrey McRae Date: Mon, 1 Jun 2026 23:55:53 +1000 Subject: [PATCH 063/297] drm/amdkfd: Fix NULL deref during sysfs teardown Move kfd_process_remove_sysfs() earlier in kfd_process_wq_release() so that all sysfs/procfs entries are removed before tearing down PDDs and dropping lead_thread. The per-process sysfs attributes are backed by struct kfd_process_device, and their show/store callbacks dereference PDD fields. Since sysfs removal waits for active callbacks to complete, removing these entries first closes a race where userspace reads sdma_* and stats_* files after PDD teardown. Previously this cleanup ran after kfd_process_destroy_pdds(), which resets p->n_pdds to 0. This meant kfd_process_remove_sysfs() could no longer walk the PDD array, so the per-PDD sysfs cleanup did not run as intended. This race caused NULL pointer dereferences observed in kfd_sdma_activity_worker and kfd_procfs_stats_show. Also harden kfd_process_remove_sysfs() against partially initialized or already-freed objects: - Check kobj_queues before removing PASID and deleting it - Guard kobj_stats and kobj_counters before use These checks prevent invalid dereferences during cleanup. Cc: Felix Kuehling Cc: Alex Deucher Signed-off-by: Geoffrey McRae Reviewed-by: Felix Kuehling Signed-off-by: Alex Deucher (cherry picked from commit 674c692702341fed321720b4b92036c5934fb485) --- drivers/gpu/drm/amd/amdkfd/kfd_process.c | 40 ++++++++++++++---------- 1 file changed, 24 insertions(+), 16 deletions(-) diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c index 63815be995fc..ca71fa726e32 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c @@ -1175,10 +1175,12 @@ static void kfd_process_remove_sysfs(struct kfd_process *p) if (!p->kobj) return; - sysfs_remove_file(p->kobj, &p->attr_pasid); - kobject_del(p->kobj_queues); - kobject_put(p->kobj_queues); - p->kobj_queues = NULL; + if (p->kobj_queues) { + sysfs_remove_file(p->kobj, &p->attr_pasid); + kobject_del(p->kobj_queues); + kobject_put(p->kobj_queues); + p->kobj_queues = NULL; + } for (i = 0; i < p->n_pdds; i++) { pdd = p->pdds[i]; @@ -1186,17 +1188,21 @@ static void kfd_process_remove_sysfs(struct kfd_process *p) sysfs_remove_file(p->kobj, &pdd->attr_vram); sysfs_remove_file(p->kobj, &pdd->attr_sdma); - sysfs_remove_file(pdd->kobj_stats, &pdd->attr_evict); - if (pdd->dev->kfd2kgd->get_cu_occupancy) - sysfs_remove_file(pdd->kobj_stats, - &pdd->attr_cu_occupancy); - kobject_del(pdd->kobj_stats); - kobject_put(pdd->kobj_stats); - pdd->kobj_stats = NULL; + if (pdd->kobj_stats) { + sysfs_remove_file(pdd->kobj_stats, &pdd->attr_evict); + if (pdd->dev->kfd2kgd->get_cu_occupancy) + sysfs_remove_file(pdd->kobj_stats, + &pdd->attr_cu_occupancy); + kobject_del(pdd->kobj_stats); + kobject_put(pdd->kobj_stats); + pdd->kobj_stats = NULL; + } } for_each_set_bit(i, p->svms.bitmap_supported, p->n_pdds) { pdd = p->pdds[i]; + if (!pdd->kobj_counters) + continue; sysfs_remove_file(pdd->kobj_counters, &pdd->attr_faults); sysfs_remove_file(pdd->kobj_counters, &pdd->attr_page_in); @@ -1254,6 +1260,13 @@ static void kfd_process_wq_release(struct work_struct *work) kfd_debugfs_remove_process(p); + /* + * Remove the proc/sysfs entries before destroying PDDs. The removal path + * walks the PDD array and sysfs callbacks dereference PDD fields, so the + * backing data must remain valid until sysfs removal has completed. + */ + kfd_process_remove_sysfs(p); + kfd_process_kunmap_signal_bo(p); kfd_process_free_outstanding_kfd_bos(p); svm_range_list_fini(p); @@ -1267,11 +1280,6 @@ static void kfd_process_wq_release(struct work_struct *work) put_task_struct(p->lead_thread); - /* the last step is removing process entries under /sys - * to indicate the process has been terminated. - */ - kfd_process_remove_sysfs(p); - kfree(p); } From 75b3e4d0494f5f831939bec835deceebff0bded7 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig=20=28The=20Capable=20Hub=29?= Date: Tue, 28 Apr 2026 16:47:03 +0200 Subject: [PATCH 064/297] drm/amdgpu: Don't use UTS_RELEASE directly MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit UTS_RELEASE evaluates to a static string and changes quite easily (e.g. uncommitted changes in the source tree or new commits). So when checking if a patch introduces changes to the resulting binary each usage of UTS_RELEASE is source of annoyance. Instead of using UTS_RELEASE directly use init_utsname()->release which evaluates to the same string but with that a change of UTS_RELEASE doesn't affect amdgpu_dev_coredump.o. Reviewed-by: Mario Limonciello (AMD) Signed-off-by: Uwe Kleine-König (The Capable Hub) Link: https://patch.msgid.link/20260428144704.1114562-2-u.kleine-koenig@baylibre.com Signed-off-by: Mario Limonciello Signed-off-by: Alex Deucher (cherry picked from commit d785df5598fd1d1cc2f2f45c05448271b6d490b7) --- drivers/gpu/drm/amd/amdgpu/amdgpu_dev_coredump.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dev_coredump.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dev_coredump.c index bed68f0c3080..322c55aaf15f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dev_coredump.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dev_coredump.c @@ -22,8 +22,8 @@ * */ -#include #include +#include #include "amdgpu_dev_coredump.h" #include "atom.h" @@ -237,7 +237,7 @@ amdgpu_devcoredump_format(char *buffer, size_t count, struct amdgpu_coredump_inf drm_printf(&p, "**** AMDGPU Device Coredump ****\n"); drm_printf(&p, "version: " AMDGPU_COREDUMP_VERSION "\n"); - drm_printf(&p, "kernel: " UTS_RELEASE "\n"); + drm_printf(&p, "kernel: %s\n", init_utsname()->release); drm_printf(&p, "module: " KBUILD_MODNAME "\n"); drm_printf(&p, "time: %ptSp\n", &coredump->reset_time); From 9920249a5288e7cbec222cd52996bbd9aac7ec9e Mon Sep 17 00:00:00 2001 From: Mikhail Gavrilov Date: Fri, 29 May 2026 11:47:38 +0500 Subject: [PATCH 065/297] drm/amdgpu: convert amdgpu_vm_lock_by_pasid() to drm_exec MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit amdgpu_vm_lock_by_pasid() looks up a VM by PASID and reserves its root PD with a bare amdgpu_bo_reserve(), returning the still-reserved root to the caller. A caller that then needs to reserve further BOs (for example the devcoredump IB dump) ends up nesting reservation_ww_class_mutex acquires without a ww_acquire_ctx, which lockdep flags as recursive locking. Convert the helper to take a drm_exec context and lock the root PD with drm_exec_lock_obj(). Callers now run it inside a drm_exec_until_all_locked() loop and can lock additional BOs in the same ww ticket, so there is no nested ww_mutex acquire. The drm_exec context holds its own reference on the locked root BO, so the helper no longer hands a root reference back to the caller: the root output parameter is dropped, and the transient reference taken across the PASID lookup is released before returning. The only existing caller, amdgpu_vm_handle_fault(), is updated accordingly. Its is_compute_context path, which previously dropped the root reservation around svm_range_restore_pages() and re-took it, now finalises the drm_exec context and re-initialises a fresh one; behaviour is otherwise unchanged. No functional change intended for the page-fault path. Reviewed-by: Christian König Signed-off-by: Mikhail Gavrilov Signed-off-by: Alex Deucher (cherry picked from commit 14682de8ad377bf13ea66e47c26dcfea0b19a21d) --- drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 91 ++++++++++++++++---------- drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h | 2 +- 2 files changed, 58 insertions(+), 35 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index 7d51880b4860..fee4c94c2585 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -2920,47 +2920,56 @@ int amdgpu_vm_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) } /** - * amdgpu_vm_lock_by_pasid - return an amdgpu_vm and its root bo from a pasid, if possible. + * amdgpu_vm_lock_by_pasid - look up a VM by PASID and lock its root PD * @adev: amdgpu device pointer - * @root: root BO of the VM * @pasid: PASID of the VM - * The caller needs to unreserve and unref the root bo on success. + * @exec: drm_exec context to lock the root PD in + * + * Must be called from within a drm_exec_until_all_locked() loop; the caller + * runs drm_exec_retry_on_contention() afterwards. The drm_exec context holds + * a reference on the root BO until it is finalised. + * + * Return: the VM on success, or NULL if the PASID has no VM, the VM is being + * torn down, or locking the root PD failed. */ struct amdgpu_vm *amdgpu_vm_lock_by_pasid(struct amdgpu_device *adev, - struct amdgpu_bo **root, u32 pasid) + u32 pasid, struct drm_exec *exec) { unsigned long irqflags; + struct amdgpu_bo *root; struct amdgpu_vm *vm; int r; xa_lock_irqsave(&adev->vm_manager.pasids, irqflags); vm = xa_load(&adev->vm_manager.pasids, pasid); - *root = vm ? amdgpu_bo_ref(vm->root.bo) : NULL; + root = vm ? amdgpu_bo_ref(vm->root.bo) : NULL; xa_unlock_irqrestore(&adev->vm_manager.pasids, irqflags); - if (!*root) + if (!root) return NULL; - r = amdgpu_bo_reserve(*root, true); - if (r) - goto error_unref; + r = drm_exec_lock_obj(exec, &root->tbo.base); + if (r) { + amdgpu_bo_unref(&root); + return NULL; + } /* Double check that the VM still exists */ xa_lock_irqsave(&adev->vm_manager.pasids, irqflags); vm = xa_load(&adev->vm_manager.pasids, pasid); - if (vm && vm->root.bo != *root) + if (vm && vm->root.bo != root) vm = NULL; xa_unlock_irqrestore(&adev->vm_manager.pasids, irqflags); - if (!vm) - goto error_unlock; + if (!vm) { + drm_exec_unlock_obj(exec, &root->tbo.base); + amdgpu_bo_unref(&root); + return NULL; + } + + /* The drm_exec context holds its own reference on the root BO. */ + amdgpu_bo_unref(&root); return vm; -error_unlock: - amdgpu_bo_unreserve(*root); - -error_unref: - amdgpu_bo_unref(root); - return NULL; } /** @@ -2982,33 +2991,49 @@ bool amdgpu_vm_handle_fault(struct amdgpu_device *adev, u32 pasid, uint64_t ts, bool write_fault) { bool is_compute_context = false; - struct amdgpu_bo *root; + struct drm_exec exec; uint64_t value, flags; struct amdgpu_vm *vm; int r; - vm = amdgpu_vm_lock_by_pasid(adev, &root, pasid); - if (!vm) + drm_exec_init(&exec, 0, 1); + drm_exec_until_all_locked(&exec) { + vm = amdgpu_vm_lock_by_pasid(adev, pasid, &exec); + drm_exec_retry_on_contention(&exec); + if (!vm) + break; + } + if (!vm) { + drm_exec_fini(&exec); return false; + } is_compute_context = vm->is_compute_context; if (is_compute_context) { - /* Unreserve root since svm_range_restore_pages might try to reserve it. */ - /* TODO: rework svm_range_restore_pages so that this isn't necessary. */ - amdgpu_bo_unreserve(root); + /* Release the root PD lock since svm_range_restore_pages + * might try to take it. + * TODO: rework svm_range_restore_pages so that this isn't + * necessary. + */ + drm_exec_fini(&exec); if (!svm_range_restore_pages(adev, pasid, vmid, - node_id, addr >> PAGE_SHIFT, ts, write_fault)) { - amdgpu_bo_unref(&root); + node_id, addr >> PAGE_SHIFT, ts, write_fault)) return true; - } - amdgpu_bo_unref(&root); /* Re-acquire the VM lock, could be that the VM was freed in between. */ - vm = amdgpu_vm_lock_by_pasid(adev, &root, pasid); - if (!vm) + drm_exec_init(&exec, 0, 1); + drm_exec_until_all_locked(&exec) { + vm = amdgpu_vm_lock_by_pasid(adev, pasid, &exec); + drm_exec_retry_on_contention(&exec); + if (!vm) + break; + } + if (!vm) { + drm_exec_fini(&exec); return false; + } } addr /= AMDGPU_GPU_PAGE_SIZE; @@ -3032,7 +3057,7 @@ bool amdgpu_vm_handle_fault(struct amdgpu_device *adev, u32 pasid, value = 0; } - r = dma_resv_reserve_fences(root->tbo.base.resv, 1); + r = dma_resv_reserve_fences(vm->root.bo->tbo.base.resv, 1); if (r) { pr_debug("failed %d to reserve fence slot\n", r); goto error_unlock; @@ -3046,12 +3071,10 @@ bool amdgpu_vm_handle_fault(struct amdgpu_device *adev, u32 pasid, r = amdgpu_vm_update_pdes(adev, vm, true); error_unlock: - amdgpu_bo_unreserve(root); + drm_exec_fini(&exec); if (r < 0) dev_err(adev->dev, "Can't handle page fault (%d)\n", r); - amdgpu_bo_unref(&root); - return false; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h index 3695299f1a03..b32f51a78cd8 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h @@ -592,7 +592,7 @@ bool amdgpu_vm_handle_fault(struct amdgpu_device *adev, u32 pasid, bool write_fault); struct amdgpu_vm *amdgpu_vm_lock_by_pasid(struct amdgpu_device *adev, - struct amdgpu_bo **root, u32 pasid); + u32 pasid, struct drm_exec *exec); void amdgpu_vm_set_task_info(struct amdgpu_vm *vm); From 7152b248dc3c8d5fa8629e99ed5655dd41b51562 Mon Sep 17 00:00:00 2001 From: Mikhail Gavrilov Date: Fri, 29 May 2026 11:47:39 +0500 Subject: [PATCH 066/297] drm/amdgpu: fix recursive ww_mutex acquire in amdgpu_devcoredump_format MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When dumping IB contents from a hung job, amdgpu_devcoredump_format() acquired the VM root PD's reservation via amdgpu_vm_lock_by_pasid() and then, for each IB, called amdgpu_bo_reserve() on the BO backing the IB. Both reservations are reservation_ww_class_mutex objects and neither used a ww_acquire_ctx, which trips lockdep: WARNING: possible recursive locking detected -------------------------------------------- kworker/u128:0 is trying to acquire lock: ffff88838b16e1f0 (reservation_ww_class_mutex){+.+.}-{4:4}, at: amdgpu_devcoredump_format+0x1594/0x23f0 [amdgpu] but task is already holding lock: ffff8882f82681f0 (reservation_ww_class_mutex){+.+.}-{4:4}, at: amdgpu_devcoredump_format+0x1594/0x23f0 [amdgpu] Possible unsafe locking scenario: CPU0 ---- lock(reservation_ww_class_mutex); lock(reservation_ww_class_mutex); *** DEADLOCK *** May be due to missing lock nesting notation Workqueue: events_unbound amdgpu_devcoredump_deferred_work [amdgpu] Call Trace: __ww_mutex_lock.constprop.0 ww_mutex_lock amdgpu_bo_reserve amdgpu_devcoredump_format+0x1594 [amdgpu] amdgpu_devcoredump_deferred_work+0xea [amdgpu] The two reservations are on different BOs in the captured trace, so the splat is a lockdep-correctness warning, not an observed deadlock. It becomes a real self-deadlock whenever the IB BO shares its dma_resv with the root PD (the always-valid case, see amdgpu_vm_is_bo_always_valid()): amdgpu_bo_reserve(abo) re-acquires the same ww_mutex without a ticket and blocks forever. With amdgpu.gpu_recovery=0 the timeout handler refires every ~2 s and each invocation produces this splat, drowning the kernel ring buffer. Now that amdgpu_vm_lock_by_pasid() takes a drm_exec context, move the IB dumping into a separate helper that locks the root PD and every IB BO together in a single drm_exec ticket. DRM_EXEC_IGNORE_DUPLICATES handles IB BOs that share a dma_resv (e.g. always-valid BOs, or two IBs backed by the same BO). Every lock is now a top-level acquire under one ww_acquire_ctx, so the recursive ww_mutex condition is gone, and the per-IB amdgpu_bo_reserve()/amdgpu_bo_unref() dance -- including a BO refcount leak on the amdgpu_bo_reserve() failure path -- is removed. Fixes: 7b15fc2d1f1a ("drm/amdgpu: dump job ibs in the devcoredump") Suggested-by: Christian König Signed-off-by: Mikhail Gavrilov Reviewed-by: Christian König Signed-off-by: Alex Deucher (cherry picked from commit d6bf4242731219ee08ce54c365631e395486651e) --- .../gpu/drm/amd/amdgpu/amdgpu_dev_coredump.c | 215 ++++++++++-------- 1 file changed, 126 insertions(+), 89 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dev_coredump.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dev_coredump.c index 322c55aaf15f..e77db76b48b8 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dev_coredump.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dev_coredump.c @@ -24,6 +24,7 @@ #include #include +#include #include "amdgpu_dev_coredump.h" #include "atom.h" @@ -207,23 +208,137 @@ static void amdgpu_devcoredump_fw_info(struct amdgpu_device *adev, } } +static void +amdgpu_devcoredump_print_ibs(struct drm_printer *p, + struct amdgpu_coredump_info *coredump, + bool sizing_pass) +{ + struct amdgpu_device *adev = coredump->adev; + struct amdgpu_bo_va_mapping *mapping; + struct amdgpu_bo *abo; + struct drm_exec exec; + struct amdgpu_vm *vm; + u32 *ib_content; + u64 va_start, offset; + u8 *kptr; + u32 off; + int r; + + /* + * On the sizing pass there is no VM to look up and no BO to lock; the + * size estimate doesn't depend on whether the IB BOs are reachable. + * Just emit the per-IB headers (the content is not written anywhere). + */ + if (sizing_pass) { + for (int i = 0; i < coredump->num_ibs; i++) { + drm_printf(p, "\nIB #%d 0x%llx %d dw\n", i, + coredump->ibs[i].gpu_addr, + coredump->ibs[i].ib_size_dw); + } + return; + } + + /* + * Lock the VM root PD and every IB BO together in a single drm_exec + * ticket. Reserving the IB BOs one by one while the root PD is held + * would be a recursive reservation_ww_class_mutex acquire without a + * ww_acquire_ctx, which trips lockdep and self-deadlocks for IB BOs + * that share their dma_resv with the root PD (always-valid BOs). + */ + drm_exec_init(&exec, DRM_EXEC_IGNORE_DUPLICATES, 1 + coredump->num_ibs); + drm_exec_until_all_locked(&exec) { + vm = amdgpu_vm_lock_by_pasid(adev, coredump->pasid, &exec); + if (!vm) + goto unlock; + + for (int i = 0; i < coredump->num_ibs; i++) { + u64 pfn = (coredump->ibs[i].gpu_addr & + AMDGPU_GMC_HOLE_MASK) / AMDGPU_GPU_PAGE_SIZE; + + mapping = amdgpu_vm_bo_lookup_mapping(vm, pfn); + if (!mapping) + continue; + + abo = mapping->bo_va->base.bo; + r = drm_exec_lock_obj(&exec, &abo->tbo.base); + drm_exec_retry_on_contention(&exec); + if (r) + goto unlock; + } + } + + for (int i = 0; i < coredump->num_ibs; i++) { + bool emit_content = false; + + ib_content = kvmalloc_array(coredump->ibs[i].ib_size_dw, 4, + GFP_KERNEL); + if (!ib_content) + continue; + + va_start = coredump->ibs[i].gpu_addr & AMDGPU_GMC_HOLE_MASK; + mapping = amdgpu_vm_bo_lookup_mapping(vm, + va_start / AMDGPU_GPU_PAGE_SIZE); + if (!mapping) + goto output_ib_content; + + abo = mapping->bo_va->base.bo; + offset = va_start - mapping->start * AMDGPU_GPU_PAGE_SIZE; + + if (abo->flags & AMDGPU_GEM_CREATE_NO_CPU_ACCESS) { + struct amdgpu_res_cursor cursor; + + off = 0; + + if (abo->tbo.resource->mem_type != TTM_PL_VRAM) + goto output_ib_content; + + amdgpu_res_first(abo->tbo.resource, offset, + coredump->ibs[i].ib_size_dw * 4, &cursor); + while (cursor.remaining) { + amdgpu_device_mm_access(adev, cursor.start / 4, + &ib_content[off], cursor.size / 4, + false); + off += cursor.size; + amdgpu_res_next(&cursor, cursor.size); + } + emit_content = true; + } else { + r = ttm_bo_kmap(&abo->tbo, 0, PFN_UP(abo->tbo.base.size), + &abo->kmap); + if (r) + goto output_ib_content; + + kptr = amdgpu_bo_kptr(abo); + kptr += offset; + memcpy(ib_content, kptr, coredump->ibs[i].ib_size_dw * 4); + + amdgpu_bo_kunmap(abo); + emit_content = true; + } + +output_ib_content: + drm_printf(p, "\nIB #%d 0x%llx %d dw\n", i, + coredump->ibs[i].gpu_addr, coredump->ibs[i].ib_size_dw); + if (emit_content) { + for (int j = 0; j < coredump->ibs[i].ib_size_dw; j++) + drm_printf(p, "0x%08x\n", ib_content[j]); + } + kvfree(ib_content); + } + +unlock: + drm_exec_fini(&exec); +} + static ssize_t amdgpu_devcoredump_format(char *buffer, size_t count, struct amdgpu_coredump_info *coredump) { - struct amdgpu_device *adev = coredump->adev; struct drm_printer p; struct drm_print_iterator iter; struct amdgpu_vm_fault_info *fault_info; - struct amdgpu_bo_va_mapping *mapping; struct amdgpu_ip_block *ip_block; - struct amdgpu_res_cursor cursor; - struct amdgpu_bo *abo, *root; - uint64_t va_start, offset; struct amdgpu_ring *ring; - struct amdgpu_vm *vm; - u32 *ib_content; - uint8_t *kptr; - int ver, i, j, r; + int ver, i, j; u32 ring_idx, off; bool sizing_pass; @@ -343,86 +458,8 @@ amdgpu_devcoredump_format(char *buffer, size_t count, struct amdgpu_coredump_inf else if (coredump->reset_vram_lost) drm_printf(&p, "VRAM is lost due to GPU reset!\n"); - if (coredump->num_ibs) { - /* Don't try to lookup the VM or map the BOs when calculating the - * size required to store the devcoredump. - */ - if (sizing_pass) - vm = NULL; - else - vm = amdgpu_vm_lock_by_pasid(adev, &root, coredump->pasid); - - for (int i = 0; i < coredump->num_ibs && (sizing_pass || vm); i++) { - ib_content = kvmalloc_array(coredump->ibs[i].ib_size_dw, 4, - GFP_KERNEL); - if (!ib_content) - continue; - - /* vm=NULL can only happen when 'sizing_pass' is true. Skip to the - * drm_printf() calls (ib_content doesn't need to be initialized - * as its content won't be written anywhere). - */ - if (!vm) - goto output_ib_content; - - va_start = coredump->ibs[i].gpu_addr & AMDGPU_GMC_HOLE_MASK; - mapping = amdgpu_vm_bo_lookup_mapping(vm, va_start / AMDGPU_GPU_PAGE_SIZE); - if (!mapping) - goto free_ib_content; - - offset = va_start - (mapping->start * AMDGPU_GPU_PAGE_SIZE); - abo = amdgpu_bo_ref(mapping->bo_va->base.bo); - r = amdgpu_bo_reserve(abo, false); - if (r) - goto free_ib_content; - - if (abo->flags & AMDGPU_GEM_CREATE_NO_CPU_ACCESS) { - off = 0; - - if (abo->tbo.resource->mem_type != TTM_PL_VRAM) - goto unreserve_abo; - - amdgpu_res_first(abo->tbo.resource, offset, - coredump->ibs[i].ib_size_dw * 4, - &cursor); - while (cursor.remaining) { - amdgpu_device_mm_access(adev, cursor.start / 4, - &ib_content[off], cursor.size / 4, - false); - off += cursor.size; - amdgpu_res_next(&cursor, cursor.size); - } - } else { - r = ttm_bo_kmap(&abo->tbo, 0, - PFN_UP(abo->tbo.base.size), - &abo->kmap); - if (r) - goto unreserve_abo; - - kptr = amdgpu_bo_kptr(abo); - kptr += offset; - memcpy(ib_content, kptr, - coredump->ibs[i].ib_size_dw * 4); - - amdgpu_bo_kunmap(abo); - } - -output_ib_content: - drm_printf(&p, "\nIB #%d 0x%llx %d dw\n", - i, coredump->ibs[i].gpu_addr, coredump->ibs[i].ib_size_dw); - for (int j = 0; j < coredump->ibs[i].ib_size_dw; j++) - drm_printf(&p, "0x%08x\n", ib_content[j]); -unreserve_abo: - if (vm) - amdgpu_bo_unreserve(abo); -free_ib_content: - kvfree(ib_content); - } - if (vm) { - amdgpu_bo_unreserve(root); - amdgpu_bo_unref(&root); - } - } + if (coredump->num_ibs) + amdgpu_devcoredump_print_ibs(&p, coredump, sizing_pass); return count - iter.remain; } From 8242a8d9d7194d5ef8a8b38a5621ca0966a3ec15 Mon Sep 17 00:00:00 2001 From: Xiaogang Chen Date: Tue, 26 May 2026 22:50:02 -0500 Subject: [PATCH 067/297] drm/amdkfd: Let driver decide buffer size at AMDKFD_IOC_GET_DMABUF_INFO ioctl amdkfd driver needs allocate buffer to return bo metadata to user space. The buffer size is controlled by user currently. It is a potential security issue that hostile value (e.g. 2 GiB) lets any render-group user trigger order-MAX allocation/OOM in kernel context. This patch first finds bo metadata size. If the size is smaller than user provided value drive can safely allocate buffer in kernel space and copy to user space buffer. If not, driver will let user know, not allocate and copy. User will redo with new buffer in user space. This patch lets driver decide buffer allocation size to avoid potential hostile size from user space. Signed-off-by: Xiaogang Chen Reviewed-by: Alex Deucher Signed-off-by: Alex Deucher (cherry picked from commit f54ce9e8cbd3abe0eda3a285f54dc4f572fe589a) --- drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c | 23 ++++++++++++++++++---- drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h | 2 +- drivers/gpu/drm/amd/amdkfd/kfd_chardev.c | 10 ++-------- 3 files changed, 22 insertions(+), 13 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c index 9783a3cefb04..da325863ad76 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c @@ -558,7 +558,7 @@ uint32_t amdgpu_amdkfd_get_max_engine_clock_in_mhz(struct amdgpu_device *adev) int amdgpu_amdkfd_get_dmabuf_info(struct amdgpu_device *adev, int dma_buf_fd, struct amdgpu_device **dmabuf_adev, - uint64_t *bo_size, void *metadata_buffer, + uint64_t *bo_size, void **metadata_buffer, size_t buffer_size, uint32_t *metadata_size, uint32_t *flags, int8_t *xcp_id) { @@ -593,9 +593,24 @@ int amdgpu_amdkfd_get_dmabuf_info(struct amdgpu_device *adev, int dma_buf_fd, *dmabuf_adev = adev; if (bo_size) *bo_size = amdgpu_bo_size(bo); - if (metadata_buffer) - r = amdgpu_bo_get_metadata(bo, metadata_buffer, buffer_size, - metadata_size, &metadata_flags); + if (metadata_buffer) { + /* first get metadata_size by buffer = NULL */ + r = amdgpu_bo_get_metadata(bo, NULL, 0, + metadata_size, NULL); + + /* user buf_size is bigger than bo metadata_size + * allocate a buf at kernel space and copy */ + if (*metadata_size <= buffer_size) { + *metadata_buffer = kzalloc(*metadata_size, GFP_KERNEL); + + if (!*metadata_buffer) + return -ENOMEM; + + r = amdgpu_bo_get_metadata(bo, *metadata_buffer, *metadata_size, + NULL, &metadata_flags); + } else + r = -EINVAL; + } if (flags) { *flags = (bo->preferred_domains & AMDGPU_GEM_DOMAIN_VRAM) ? KFD_IOC_ALLOC_MEM_FLAGS_VRAM diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h index 5333e052d56d..e443a7277299 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h @@ -262,7 +262,7 @@ uint64_t amdgpu_amdkfd_get_gpu_clock_counter(struct amdgpu_device *adev); uint32_t amdgpu_amdkfd_get_max_engine_clock_in_mhz(struct amdgpu_device *adev); int amdgpu_amdkfd_get_dmabuf_info(struct amdgpu_device *adev, int dma_buf_fd, struct amdgpu_device **dmabuf_adev, - uint64_t *bo_size, void *metadata_buffer, + uint64_t *bo_size, void **metadata_buffer, size_t buffer_size, uint32_t *metadata_size, uint32_t *flags, int8_t *xcp_id); int amdgpu_amdkfd_get_pcie_bandwidth_mbytes(struct amdgpu_device *adev, bool is_min); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c index a2b100d14425..6a991ffa53fc 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c @@ -1562,16 +1562,10 @@ static int kfd_ioctl_get_dmabuf_info(struct file *filep, if (!dev) return -EINVAL; - if (args->metadata_ptr) { - metadata_buffer = kzalloc(args->metadata_size, GFP_KERNEL); - if (!metadata_buffer) - return -ENOMEM; - } - /* Get dmabuf info from KGD */ r = amdgpu_amdkfd_get_dmabuf_info(dev->adev, args->dmabuf_fd, &dmabuf_adev, &args->size, - metadata_buffer, args->metadata_size, + &metadata_buffer, args->metadata_size, &args->metadata_size, &flags, &xcp_id); if (r) goto exit; @@ -1583,7 +1577,7 @@ static int kfd_ioctl_get_dmabuf_info(struct file *filep, args->flags = flags; /* Copy metadata buffer to user mode */ - if (metadata_buffer) { + if (metadata_buffer && args->metadata_ptr) { r = copy_to_user((void __user *)args->metadata_ptr, metadata_buffer, args->metadata_size); if (r != 0) From 516bf737a5602875f6c28d1028967837c8edf2c0 Mon Sep 17 00:00:00 2001 From: Xiaogang Chen Date: Tue, 16 Jun 2026 12:54:49 -0500 Subject: [PATCH 068/297] drm/amdkfd: check find_first_zero_bit before __set_bit on kfd->doorbell_bitmap If inx from find_first_zero_bit is beyond range not need set doorbell_bitmap. Signed-off-by: Xiaogang Chen Reviewed-by: Alex Deucher Signed-off-by: Alex Deucher (cherry picked from commit 2664ce9143d174651a793d96a6a2326050c4f45a) --- drivers/gpu/drm/amd/amdkfd/kfd_doorbell.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_doorbell.c b/drivers/gpu/drm/amd/amdkfd/kfd_doorbell.c index 05c74887fd6f..fdcf7f2d1b5b 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_doorbell.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_doorbell.c @@ -153,14 +153,16 @@ void __iomem *kfd_get_kernel_doorbell(struct kfd_dev *kfd, u32 inx; mutex_lock(&kfd->doorbell_mutex); + inx = find_first_zero_bit(kfd->doorbell_bitmap, PAGE_SIZE / sizeof(u32)); + if (inx >= KFD_MAX_NUM_OF_QUEUES_PER_PROCESS) { + mutex_unlock(&kfd->doorbell_mutex); + return NULL; + } __set_bit(inx, kfd->doorbell_bitmap); mutex_unlock(&kfd->doorbell_mutex); - if (inx >= KFD_MAX_NUM_OF_QUEUES_PER_PROCESS) - return NULL; - *doorbell_off = amdgpu_doorbell_index_on_bar(kfd->adev, kfd->doorbells, inx, From 2321831d7e95d4e1abaff3ffd682be9dd45db62e Mon Sep 17 00:00:00 2001 From: Xiaogang Chen Date: Tue, 16 Jun 2026 13:25:56 -0500 Subject: [PATCH 069/297] drm/amdkfd: Use memdup_array_user to copy data from/to user space at kfd ioctls Several kfd ioctls need transfer array data from/to user space. Kfd driver uses kmalloc_array with user provided size. That can oversize alloc or 32-bit wrap with hostile value. Replace it by memdup_array_user that does overflow checking and allocates through dedicated slab caches, also physical continuous as kmalloc. Signed-off-by: Xiaogang Chen Reviewed-by: Alex Deucher Signed-off-by: Alex Deucher (cherry picked from commit 4eca4742eb215951f9739ffe0122d179d545a7a4) --- drivers/gpu/drm/amd/amdkfd/kfd_chardev.c | 46 +++++++----------------- 1 file changed, 12 insertions(+), 34 deletions(-) diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c index 6a991ffa53fc..531e20748198 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c @@ -1299,18 +1299,11 @@ static int kfd_ioctl_map_memory_to_gpu(struct file *filep, return -EINVAL; } - devices_arr = kmalloc_array(args->n_devices, sizeof(*devices_arr), - GFP_KERNEL); - if (!devices_arr) - return -ENOMEM; + devices_arr = memdup_array_user((void *)args->device_ids_array_ptr, + args->n_devices, sizeof(*devices_arr)); - err = copy_from_user(devices_arr, - (void __user *)args->device_ids_array_ptr, - args->n_devices * sizeof(*devices_arr)); - if (err != 0) { - err = -EFAULT; - goto copy_from_user_failed; - } + if (IS_ERR(devices_arr)) + return PTR_ERR(devices_arr); mutex_lock(&p->mutex); pdd = kfd_process_device_data_by_id(p, GET_GPU_ID(args->handle)); @@ -1391,7 +1384,6 @@ get_mem_obj_from_handle_failed: map_memory_to_gpu_failed: sync_memory_failed: mutex_unlock(&p->mutex); -copy_from_user_failed: kfree(devices_arr); return err; @@ -1416,18 +1408,11 @@ static int kfd_ioctl_unmap_memory_from_gpu(struct file *filep, return -EINVAL; } - devices_arr = kmalloc_array(args->n_devices, sizeof(*devices_arr), - GFP_KERNEL); - if (!devices_arr) - return -ENOMEM; + devices_arr = memdup_array_user((void *)args->device_ids_array_ptr, + args->n_devices, sizeof(*devices_arr)); - err = copy_from_user(devices_arr, - (void __user *)args->device_ids_array_ptr, - args->n_devices * sizeof(*devices_arr)); - if (err != 0) { - err = -EFAULT; - goto copy_from_user_failed; - } + if (IS_ERR(devices_arr)) + return PTR_ERR(devices_arr); mutex_lock(&p->mutex); pdd = kfd_process_device_data_by_id(p, GET_GPU_ID(args->handle)); @@ -1493,7 +1478,6 @@ get_mem_obj_from_handle_failed: unmap_memory_from_gpu_failed: sync_memory_failed: mutex_unlock(&p->mutex); -copy_from_user_failed: kfree(devices_arr); return err; } @@ -2353,17 +2337,11 @@ static int criu_restore_devices(struct kfd_process *p, if (*priv_offset + (args->num_devices * sizeof(*device_privs)) > max_priv_data_size) return -EINVAL; - device_buckets = kmalloc_objs(*device_buckets, args->num_devices); - if (!device_buckets) - return -ENOMEM; + device_buckets = memdup_array_user((void *)args->devices, + args->num_devices, sizeof(*device_buckets)); - ret = copy_from_user(device_buckets, (void __user *)args->devices, - args->num_devices * sizeof(*device_buckets)); - if (ret) { - pr_err("Failed to copy devices buckets from user\n"); - ret = -EFAULT; - goto exit; - } + if (IS_ERR(device_buckets)) + return PTR_ERR(device_buckets); for (i = 0; i < args->num_devices; i++) { struct kfd_node *dev; From c1dc4ccb82c9e56325d8e7514ca4c90bd1efb351 Mon Sep 17 00:00:00 2001 From: Tvrtko Ursulin Date: Mon, 1 Jun 2026 15:08:22 +0100 Subject: [PATCH 070/297] drm/amdgpu: Fix context pstate override handling MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit There are several problems in the context pstate handling code. The most serious ones are potential use-after-free and NULL pointer dereferences at context initialization time. Both are due amdgpu_ctx_init() not holding the adev->pm.stable_pstate_ctx_lock, which is otherwise used from both sysfs and the context code itself for modifying and clearing the stored context pointer. Second issue is that context fini can trample over the pstate configuration set via sysfs. This is due the restore state (ctx->stable_pstate) being saved at context init time, and not if, or when the context actually changes the pstate. As the context exits it will therefore incorrectly restore to what was set before the sysfs override was requested. The simplest fix is to drastically simplify how the state is tracked, by clearly defining the points at which pstate ownership is taken and released, and to handle all transitions under the correct lock. Instead of at context init time, the previous state is saved only at the point the context overrides the current state, and is restored on context exit only if the context is still the owner of the current override state. Signed-off-by: Tvrtko Ursulin Fixes: 79610d304133 ("drm/amdgpu: fix pstate setting issue") Cc: Chengming Gui Cc: Alex Deucher Cc: "Christian König" Signed-off-by: Alex Deucher (cherry picked from commit 1b5e413713c0a93bc1818394d0ce49aaad21bd27) Cc: # v6.1+ --- drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c | 73 +++++++++++++++---------- 1 file changed, 43 insertions(+), 30 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c index 0d7f6cd74f79..ce35b415093d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c @@ -326,7 +326,6 @@ static int amdgpu_ctx_init(struct amdgpu_ctx_mgr *mgr, int32_t priority, struct drm_file *filp, struct amdgpu_ctx *ctx) { struct amdgpu_fpriv *fpriv = filp->driver_priv; - u32 current_stable_pstate; int r; r = amdgpu_ctx_priority_permit(filp, priority); @@ -344,36 +343,21 @@ static int amdgpu_ctx_init(struct amdgpu_ctx_mgr *mgr, int32_t priority, ctx->generation = amdgpu_vm_generation(mgr->adev, &fpriv->vm); ctx->init_priority = priority; ctx->override_priority = AMDGPU_CTX_PRIORITY_UNSET; - - r = amdgpu_ctx_get_stable_pstate(ctx, ¤t_stable_pstate); - if (r) - return r; - - if (mgr->adev->pm.stable_pstate_ctx) - ctx->stable_pstate = mgr->adev->pm.stable_pstate_ctx->stable_pstate; - else - ctx->stable_pstate = current_stable_pstate; + ctx->stable_pstate = AMDGPU_CTX_STABLE_PSTATE_NONE; return 0; } -static int amdgpu_ctx_set_stable_pstate(struct amdgpu_ctx *ctx, - u32 stable_pstate) +static int __amdgpu_ctx_set_stable_pstate(struct amdgpu_ctx *ctx, + u32 stable_pstate) { struct amdgpu_device *adev = ctx->mgr->adev; enum amd_dpm_forced_level level; + struct amdgpu_ctx *current_ctx; u32 current_stable_pstate; - int r; + int r = 0; - mutex_lock(&adev->pm.stable_pstate_ctx_lock); - if (adev->pm.stable_pstate_ctx && adev->pm.stable_pstate_ctx != ctx) { - r = -EBUSY; - goto done; - } - - r = amdgpu_ctx_get_stable_pstate(ctx, ¤t_stable_pstate); - if (r || (stable_pstate == current_stable_pstate)) - goto done; + lockdep_assert_held(&adev->pm.stable_pstate_ctx_lock); switch (stable_pstate) { case AMDGPU_CTX_STABLE_PSTATE_NONE: @@ -392,17 +376,41 @@ static int amdgpu_ctx_set_stable_pstate(struct amdgpu_ctx *ctx, level = AMD_DPM_FORCED_LEVEL_PROFILE_PEAK; break; default: - r = -EINVAL; - goto done; + return -EINVAL; } - r = amdgpu_dpm_force_performance_level(adev, level); + current_ctx = adev->pm.stable_pstate_ctx; + if (current_ctx && current_ctx != ctx) + return -EBUSY; - if (level == AMD_DPM_FORCED_LEVEL_AUTO) - adev->pm.stable_pstate_ctx = NULL; - else + r = amdgpu_ctx_get_stable_pstate(ctx, ¤t_stable_pstate); + if (r || current_stable_pstate == stable_pstate) + return r; + + r = amdgpu_dpm_force_performance_level(adev, level); + if (r) + return r; + + if (!current_ctx) { adev->pm.stable_pstate_ctx = ctx; -done: + /* + * Serialized by context taking ownership for the first time + * while holding adev->pm.stable_pstate_ctx_lock). + */ + WRITE_ONCE(ctx->stable_pstate, current_stable_pstate); + } + + return 0; +} + +static int amdgpu_ctx_set_stable_pstate(struct amdgpu_ctx *ctx, + u32 stable_pstate) +{ + struct amdgpu_device *adev = ctx->mgr->adev; + int r; + + mutex_lock(&adev->pm.stable_pstate_ctx_lock); + r = __amdgpu_ctx_set_stable_pstate(ctx, stable_pstate); mutex_unlock(&adev->pm.stable_pstate_ctx_lock); return r; @@ -428,7 +436,12 @@ static void amdgpu_ctx_fini(struct kref *ref) } if (drm_dev_enter(adev_to_drm(adev), &idx)) { - amdgpu_ctx_set_stable_pstate(ctx, ctx->stable_pstate); + mutex_lock(&adev->pm.stable_pstate_ctx_lock); + if (adev->pm.stable_pstate_ctx == ctx) { + __amdgpu_ctx_set_stable_pstate(ctx, ctx->stable_pstate); + adev->pm.stable_pstate_ctx = NULL; + } + mutex_unlock(&adev->pm.stable_pstate_ctx_lock); drm_dev_exit(idx); } From 8882f8897e554053af9e72f4c2da8b1e2cce56c7 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Timur=20Krist=C3=B3f?= Date: Mon, 25 May 2026 13:33:17 +0200 Subject: [PATCH 071/297] drm/amdgpu: Respect placement requirements in amdgpu_gtt_mgr functions MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When testing intersection and compatibility, respect the actual placement requirements. This is a pre-requisite for ensuring that UVD CS BOs do not cross 256M segments. Fixes: ded910f368a5 ("drm/amdgpu: Implement intersect/compatible functions") Suggested-by: Christian König Signed-off-by: Timur Kristóf Reviewed-by: Christian König Signed-off-by: Alex Deucher (cherry picked from commit bc06579ca29dee9c245a41b12e39c7bb6938af5d) Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c | 30 +++++++++++++++++++-- 1 file changed, 28 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c index d23a91d029aa..0ea32561c4bc 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c @@ -272,7 +272,20 @@ static bool amdgpu_gtt_mgr_intersects(struct ttm_resource_manager *man, const struct ttm_place *place, size_t size) { - return !place->lpfn || amdgpu_gtt_mgr_has_gart_addr(res); + const struct drm_mm_node *const node = &to_ttm_range_mgr_node(res)->mm_nodes[0]; + const u32 num_pages = PFN_UP(size); + + if (!place->lpfn) + return true; + + if (!amdgpu_gtt_mgr_has_gart_addr(res)) + return false; + + if (place->fpfn >= (node->start + num_pages) || + (place->lpfn && place->lpfn <= node->start)) + return false; + + return true; } /** @@ -290,7 +303,20 @@ static bool amdgpu_gtt_mgr_compatible(struct ttm_resource_manager *man, const struct ttm_place *place, size_t size) { - return !place->lpfn || amdgpu_gtt_mgr_has_gart_addr(res); + const struct drm_mm_node *const node = &to_ttm_range_mgr_node(res)->mm_nodes[0]; + const u32 num_pages = PFN_UP(size); + + if (!place->lpfn) + return true; + + if (!amdgpu_gtt_mgr_has_gart_addr(res)) + return false; + + if (node->start < place->fpfn || + (place->lpfn && (node->start + num_pages) > place->lpfn)) + return false; + + return true; } /** From ee94a65f192c05c543b4d3ad7137cd696b5c18fc Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Timur=20Krist=C3=B3f?= Date: Mon, 25 May 2026 13:33:18 +0200 Subject: [PATCH 072/297] drm/amdgpu: Fix amdgpu_bo_move() when old_mem and new_mem are both GTT MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The UVD code relies on GTT to GTT moves in order to ensure that its BOs don't cross 256M segments. Fixes: bfe5e585b44f ("drm/ttm: move last binding into the drivers.") Signed-off-by: Timur Kristóf Reviewed-by: Christian König Signed-off-by: Alex Deucher (cherry picked from commit 21fd45e5e2628d00b478590bcc3d14d3de5d45b6) Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index 2740de94e93c..16c060badaee 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -515,6 +515,15 @@ static int amdgpu_bo_move(struct ttm_buffer_object *bo, bool evict, if (new_mem->mem_type == TTM_PL_TT || new_mem->mem_type == AMDGPU_PL_PREEMPT) { + if (old_mem && (old_mem->mem_type == TTM_PL_TT || + old_mem->mem_type == AMDGPU_PL_PREEMPT)) { + r = ttm_bo_wait_ctx(bo, ctx); + if (r) + return r; + + amdgpu_ttm_backend_unbind(bo->bdev, bo->ttm); + } + r = amdgpu_ttm_backend_bind(bo->bdev, bo->ttm, new_mem); if (r) return r; @@ -549,6 +558,15 @@ static int amdgpu_bo_move(struct ttm_buffer_object *bo, bool evict, ttm_bo_assign_mem(bo, new_mem); return 0; } + if ((old_mem->mem_type == TTM_PL_TT || + old_mem->mem_type == AMDGPU_PL_PREEMPT) && + (new_mem->mem_type == TTM_PL_TT || + new_mem->mem_type == AMDGPU_PL_PREEMPT)) { + amdgpu_bo_move_notify(bo, evict, new_mem); + ttm_resource_free(bo, &bo->resource); + ttm_bo_assign_mem(bo, new_mem); + return 0; + } if (old_mem->mem_type == AMDGPU_PL_GDS || old_mem->mem_type == AMDGPU_PL_GWS || From 8002b744ad70055ef11ff7d0a7d685bfe8ffe6e4 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Timur=20Krist=C3=B3f?= Date: Mon, 25 May 2026 13:33:19 +0200 Subject: [PATCH 073/297] drm/amdgpu/uvd: Place VCPU BO only in VRAM for UVD 4.x and older MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit These UVD versions don't fully support GPUVM and are only validated to work when their VCPU BO is placed in VRAM. Signed-off-by: Timur Kristóf Reviewed-by: Christian König Signed-off-by: Alex Deucher (cherry picked from commit 01b8dfc0660db5d6cdd62c22dc20f774a26ce853) Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c | 17 +++++++++++------ 1 file changed, 11 insertions(+), 6 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c index 3a3bc0d370fa..1e59ca924abe 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c @@ -188,6 +188,7 @@ int amdgpu_uvd_sw_init(struct amdgpu_device *adev) const struct common_firmware_header *hdr; unsigned int family_id; int i, j, r; + u32 vcpu_bo_domain; INIT_DELAYED_WORK(&adev->uvd.idle_work, amdgpu_uvd_idle_work_handler); @@ -319,12 +320,20 @@ int amdgpu_uvd_sw_init(struct amdgpu_device *adev) if (adev->firmware.load_type != AMDGPU_FW_LOAD_PSP) bo_size += AMDGPU_GPU_PAGE_ALIGN(le32_to_cpu(hdr->ucode_size_bytes) + 8); + /* UVD 5.0 and newer HW can use 64 bit addressing. */ + adev->uvd.address_64_bit = + !amdgpu_device_ip_block_version_cmp(adev, AMD_IP_BLOCK_TYPE_UVD, 5, 0); + + vcpu_bo_domain = AMDGPU_GEM_DOMAIN_VRAM; + if (adev->uvd.address_64_bit) + vcpu_bo_domain |= AMDGPU_GEM_DOMAIN_GTT; + for (j = 0; j < adev->uvd.num_uvd_inst; j++) { if (adev->uvd.harvest_config & (1 << j)) continue; + r = amdgpu_bo_create_kernel(adev, bo_size, PAGE_SIZE, - AMDGPU_GEM_DOMAIN_VRAM | - AMDGPU_GEM_DOMAIN_GTT, + vcpu_bo_domain, &adev->uvd.inst[j].vcpu_bo, &adev->uvd.inst[j].gpu_addr, &adev->uvd.inst[j].cpu_addr); @@ -339,10 +348,6 @@ int amdgpu_uvd_sw_init(struct amdgpu_device *adev) adev->uvd.filp[i] = NULL; } - /* from uvd v5.0 HW addressing capacity increased to 64 bits */ - if (!amdgpu_device_ip_block_version_cmp(adev, AMD_IP_BLOCK_TYPE_UVD, 5, 0)) - adev->uvd.address_64_bit = true; - r = amdgpu_uvd_create_msg_bo_helper(adev, 128 << 10, &adev->uvd.ib_bo); if (r) return r; From 32bd35f068a3507a1b3922cd12ea2985fc58c85b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Timur=20Krist=C3=B3f?= Date: Mon, 25 May 2026 13:33:20 +0200 Subject: [PATCH 074/297] drm/amdgpu/uvd: Fix forcing MSG, FB BOs into VCPU segment when it isn't at 0 (v2) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit UVD 4.x and older can only access MSG, FEEDBACK buffers from a specific 256M VRAM segment that the VCPU BO is also located in. We already modify all placements of the given BO to ensure the BO is placed within this segment. Previously, it always assumed that the VCPU segment is the first 256M of VRAM, even though under some conditions the VCPU BO could be allocated outside this segment, which made UVD non-functional as the BOs were not inside the same segment as the UVD VCPU BO. Solve that by using the segment where the VCPU BO actually is. This fixes an issue with UVD failing to initialize on SI/CIK when resizable BAR is enabled and the VCPU BO is allocated in a different segment. v2: - For other BOs, keep using the same UVD segment as before. Closes: https://gitlab.freedesktop.org/drm/amd/-/work_items/3851 Reviewed-by: Christian König Signed-off-by: Timur Kristóf Signed-off-by: Alex Deucher (cherry picked from commit cbfd4d3fc2061a1ec8e9d36e65973ac3e813358a) Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c | 33 ++++++++++++++++++------- 1 file changed, 24 insertions(+), 9 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c index 1e59ca924abe..480bf88def46 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c @@ -135,7 +135,7 @@ MODULE_FIRMWARE(FIRMWARE_VEGA12); MODULE_FIRMWARE(FIRMWARE_VEGA20); static void amdgpu_uvd_idle_work_handler(struct work_struct *work); -static void amdgpu_uvd_force_into_uvd_segment(struct amdgpu_bo *abo); +static void amdgpu_uvd_force_into_vcpu_segment(struct amdgpu_bo *abo); static int amdgpu_uvd_create_msg_bo_helper(struct amdgpu_device *adev, uint32_t size, @@ -158,7 +158,7 @@ static int amdgpu_uvd_create_msg_bo_helper(struct amdgpu_device *adev, amdgpu_bo_kunmap(bo); amdgpu_bo_unpin(bo); amdgpu_bo_placement_from_domain(bo, AMDGPU_GEM_DOMAIN_VRAM); - amdgpu_uvd_force_into_uvd_segment(bo); + amdgpu_uvd_force_into_vcpu_segment(bo); r = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx); if (r) goto err; @@ -550,6 +550,24 @@ void amdgpu_uvd_free_handles(struct amdgpu_device *adev, struct drm_file *filp) } } +static void amdgpu_uvd_force_into_vcpu_segment(struct amdgpu_bo *bo) +{ + struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev); + struct amdgpu_bo *vcpu_bo = adev->uvd.inst[0].vcpu_bo; + struct amdgpu_res_cursor vcpu_cur; + + amdgpu_res_first(vcpu_bo->tbo.resource, 0, + amdgpu_bo_size(vcpu_bo), &vcpu_cur); + + bo->placement.num_placement = 1; + bo->placement.placement = &bo->placements[0]; + bo->placements[0].fpfn = ALIGN_DOWN(vcpu_cur.start, SZ_256M) >> PAGE_SHIFT; + bo->placements[0].lpfn = bo->placements[0].fpfn + (SZ_256M >> PAGE_SHIFT); + bo->placements[0].mem_type = vcpu_bo->tbo.resource->mem_type; + if (bo->placements[0].mem_type == TTM_PL_VRAM) + bo->placements[0].flags |= TTM_PL_FLAG_CONTIGUOUS; +} + static void amdgpu_uvd_force_into_uvd_segment(struct amdgpu_bo *abo) { int i; @@ -600,13 +618,10 @@ static int amdgpu_uvd_cs_pass1(struct amdgpu_uvd_cs_ctx *ctx) if (!ctx->parser->adev->uvd.address_64_bit) { /* check if it's a message or feedback command */ cmd = amdgpu_ib_get_value(ctx->ib, ctx->idx) >> 1; - if (cmd == 0x0 || cmd == 0x3) { - /* yes, force it into VRAM */ - uint32_t domain = AMDGPU_GEM_DOMAIN_VRAM; - - amdgpu_bo_placement_from_domain(bo, domain); - } - amdgpu_uvd_force_into_uvd_segment(bo); + if (cmd == 0x0 || cmd == 0x3) + amdgpu_uvd_force_into_vcpu_segment(bo); + else + amdgpu_uvd_force_into_uvd_segment(bo); r = ttm_bo_validate(&bo->tbo, &bo->placement, &tctx); } From 85ed06d990ff73212b5a91a406671cabd962e521 Mon Sep 17 00:00:00 2001 From: Jiqian Chen Date: Thu, 4 Jun 2026 18:30:23 +0800 Subject: [PATCH 075/297] drm/amdgpu/gfx9: Fix Ring and IB test fail after mode2 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit For Renior APU with gfx9, in some test scenarios with disabling ring_reset, like accessing an unmapped invalid address, it can trigger a gpu job timeout event, then driver uses Mode2 reset to reset GPU, but after Mode2 compute Ring test and IB test fail randomly. It because the HQDs of MECs are always active before or after Mode2, that causes MECs use stale HQDs when MECs are unhalted before driver restore MQDs, and causes CPC and CPF are still stuck after Mode2, then causes compute Ring and IB tests fail. So, add sequences to deactivate HQDs of MECs in suspend IP function of the resetting process. v2: Move all sequences into a new function gfx_v9_0_cp_mode2_clear_state (Ray Huang) To check reset Mode2 method in the if condition (Ray Huang) v3: Move all sequences before Mode2 instead of after Mode2 (Timur Kristóf) v4: Call amdgpu_gfx_rlc_enter/exit_safe_mode int the begin and end of gfx_v9_0_deactivate_kcq_hqd (Alex Deucher) Signed-off-by: Jiqian Chen Reviewed-by: Huang Rui Reviewed-by: Timur Kristóf Reviewed-by: Alex Deucher Signed-off-by: Alex Deucher (cherry picked from commit c3988a7ad4799514447294f04f063b422e0551df) Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c | 39 +++++++++++++++++++++++++++ 1 file changed, 39 insertions(+) diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c index 47721d0c3781..81a759a98725 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c @@ -4071,6 +4071,41 @@ err_priv_inst: return r; } +static void gfx_v9_0_deactivate_kcq_hqd(struct amdgpu_device *adev) +{ + amdgpu_gfx_rlc_enter_safe_mode(adev, 0); + for (int i = 0; i < adev->gfx.num_compute_rings; i++) { + u32 tmp; + struct amdgpu_ring *ring = &adev->gfx.compute_ring[i]; + + mutex_lock(&adev->srbm_mutex); + soc15_grbm_select(adev, ring->me, ring->pipe, ring->queue, 0, 0); + tmp = RREG32_SOC15(GC, 0, mmCP_HQD_ACTIVE); + /* disable the queue if it's active */ + if (tmp & CP_HQD_ACTIVE__ACTIVE_MASK) { + int j; + + WREG32_SOC15(GC, 0, mmCP_HQD_DEQUEUE_REQUEST, 1); + for (j = 0; j < adev->usec_timeout; j++) { + tmp = RREG32_SOC15(GC, 0, mmCP_HQD_ACTIVE); + if (!(tmp & CP_HQD_ACTIVE__ACTIVE_MASK)) + break; + udelay(1); + } + if (j == AMDGPU_MAX_USEC_TIMEOUT) { + DRM_DEBUG("comp_%u_%u_%u dequeue request failed.\n", + ring->me, ring->pipe, ring->queue); + /* Manual disable if dequeue request times out */ + WREG32_SOC15(GC, 0, mmCP_HQD_ACTIVE, 0); + } + WREG32_SOC15(GC, 0, mmCP_HQD_DEQUEUE_REQUEST, 0); + } + soc15_grbm_select(adev, 0, 0, 0, 0, 0); + mutex_unlock(&adev->srbm_mutex); + } + amdgpu_gfx_rlc_exit_safe_mode(adev, 0); +} + static int gfx_v9_0_hw_fini(struct amdgpu_ip_block *ip_block) { struct amdgpu_device *adev = ip_block->adev; @@ -4095,6 +4130,10 @@ static int gfx_v9_0_hw_fini(struct amdgpu_ip_block *ip_block) return 0; } + if ((adev->flags & AMD_IS_APU) && amdgpu_in_reset(adev) && + amdgpu_asic_reset_method(adev) == AMD_RESET_METHOD_MODE2) + gfx_v9_0_deactivate_kcq_hqd(adev); + /* Use deinitialize sequence from CAIL when unbinding device from driver, * otherwise KIQ is hanging when binding back */ From b89d58b6595d79dc3fe75e213e1f4c5efd0251d4 Mon Sep 17 00:00:00 2001 From: Gerhard Schwanzer Date: Tue, 16 Jun 2026 10:56:06 +0000 Subject: [PATCH 076/297] drm/amdkfd: Use exclusive bounds for SVM split alignment checks SVM ranges use inclusive page indices: prange->last is the last page in the range. The split-remap logic introduced by commit 448ee45353ef ("drm/amdkfd: Use huge page size to check split svm range alignment") uses ALIGN_DOWN(prange->last, 512) to determine whether the original range can contain a 2MB huge-page mapping. That aligns the last page itself down. Thus a range ending one page before the next 2MB boundary is classified as if the final 2MB block did not exist. When such a range is split inside that final block, the split head or tail can be left off the remap list even though it was derived from an original range that may have PMD mappings. Use prange->last + 1 as the exclusive upper bound when computing the original range's last 2MB-aligned boundary. Then use the actual split boundary for the head and tail alignment checks: tail->start for a tail split, and new_start for a head split. new_start is equivalent to head->last + 1 and directly names the exclusive end of the split head. Using head->last for the head-side check can both remap a head that ends exactly one page before a 2MB boundary and miss a head whose split boundary is one page after such a boundary. Philip Yang pointed out in the review of the original change that this condition should use head->last + 1 or new_start. Xiaogang Chen identified the inclusive-last cause and posted the candidate fix in the regression thread. With the culprit change active and the local revert not applied, the unchanged C/HSA reproducer completes 10/10 runs with this change on an RX 7600 XT. Fixes: 448ee45353ef ("drm/amdkfd: Use huge page size to check split svm range alignment") Closes: https://gitlab.freedesktop.org/drm/amd/-/work_items/4914 Link: https://lore.kernel.org/stable/IA1PR12MB85172F7FE9157C092EDA46A0E3112@IA1PR12MB8517.namprd12.prod.outlook.com/ Link: https://lore.kernel.org/all/32ce2b72-aa16-4202-9f99-92e3cd4408bc@amd.com/ Suggested-by: Xiaogang Chen Acked-by: Alex Deucher Signed-off-by: Gerhard Schwanzer Signed-off-by: Alex Deucher (cherry picked from commit a60ea15807126b148a328051636977a33ad0e9bb) Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/amdkfd/kfd_svm.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c index 5a56d86b3ecf..0900bb23349e 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c @@ -1144,7 +1144,7 @@ static int svm_range_split_tail(struct svm_range *prange, uint64_t new_last, struct list_head *insert_list, struct list_head *remap_list) { - unsigned long last_align_down = ALIGN_DOWN(prange->last, 512); + unsigned long last_align_down = ALIGN_DOWN(prange->last + 1, 512); unsigned long start_align = ALIGN(prange->start, 512); bool huge_page_mapping = last_align_down > start_align; struct svm_range *tail = NULL; @@ -1168,7 +1168,7 @@ static int svm_range_split_head(struct svm_range *prange, uint64_t new_start, struct list_head *insert_list, struct list_head *remap_list) { - unsigned long last_align_down = ALIGN_DOWN(prange->last, 512); + unsigned long last_align_down = ALIGN_DOWN(prange->last + 1, 512); unsigned long start_align = ALIGN(prange->start, 512); bool huge_page_mapping = last_align_down > start_align; struct svm_range *head = NULL; @@ -1181,8 +1181,8 @@ svm_range_split_head(struct svm_range *prange, uint64_t new_start, list_add(&head->list, insert_list); - if (huge_page_mapping && head->last + 1 > start_align && - head->last + 1 < last_align_down && (!IS_ALIGNED(head->last, 512))) + if (huge_page_mapping && new_start > start_align && + new_start < last_align_down && !IS_ALIGNED(new_start, 512)) list_add(&head->update_list, remap_list); return 0; From 29b5def20a2cc3d7df375bf3803980c86f7b10ee Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Timur=20Krist=C3=B3f?= Date: Wed, 13 May 2026 19:08:47 +0200 Subject: [PATCH 077/297] amdgpu/ih6.1: Fix minor version MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Report the correct version of IH v6.1 (previously it showed v6.0). Reviewed-by: Tvrtko Ursulin Signed-off-by: Timur Kristóf Signed-off-by: Alex Deucher (cherry picked from commit 940d33ebbcdebaf095fade86e9c981ad8789aee2) --- drivers/gpu/drm/amd/amdgpu/ih_v6_1.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/ih_v6_1.c b/drivers/gpu/drm/amd/amdgpu/ih_v6_1.c index 95b3f4e55ec3..699c274d357e 100644 --- a/drivers/gpu/drm/amd/amdgpu/ih_v6_1.c +++ b/drivers/gpu/drm/amd/amdgpu/ih_v6_1.c @@ -790,7 +790,7 @@ static void ih_v6_1_set_interrupt_funcs(struct amdgpu_device *adev) const struct amdgpu_ip_block_version ih_v6_1_ip_block = { .type = AMD_IP_BLOCK_TYPE_IH, .major = 6, - .minor = 0, + .minor = 1, .rev = 0, .funcs = &ih_v6_1_ip_funcs, }; From ba2977dcce72127986fbad76c4c67f134e2f69ae Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Timur=20Krist=C3=B3f?= Date: Wed, 13 May 2026 19:08:49 +0200 Subject: [PATCH 078/297] drm/amdgpu: Use system unbound workqueue for soft IH ring MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Allow the kernel to dispatch the soft IH work on other CPUs. Otherwise it can happen that the soft IH ring fills up before it actually starts processing anything, which can easily happen with retry page faults, in which case the CP repeatedly spams the CPU with a lot of interrupts. This significantly improves retry page fault handling on GPUs that don't have the filter CAM and must rely on software based filtering. Reviewed-by: Tvrtko Ursulin Signed-off-by: Timur Kristóf Signed-off-by: Alex Deucher (cherry picked from commit 3cdff3c8b93c2834977224d9c2b201fc334dd184) --- drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c index 40b8506ac66f..53be764968e4 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c @@ -545,7 +545,7 @@ void amdgpu_irq_delegate(struct amdgpu_device *adev, unsigned int num_dw) { amdgpu_ih_ring_write(adev, &adev->irq.ih_soft, entry->iv_entry, num_dw); - schedule_work(&adev->irq.ih_soft_work); + queue_work(system_unbound_wq, &adev->irq.ih_soft_work); } /** From 53d1ae7c20d97b08741d667ba54bb09d330eba3b Mon Sep 17 00:00:00 2001 From: Ben Dooks Date: Wed, 17 Jun 2026 11:29:43 +0100 Subject: [PATCH 079/297] ALSA: pcm: fix __le32 cast warning in snd_pcm_set_sync_per_card In snd_pcm_set_sync_per_card() the le32 value is written to an u32 instead of an __le32 pointer. Fix the following warning by fixing the type: sound/soc/soc-pcm.c:2166:9: warning: incorrect type in argument 7 (different base types) sound/soc/soc-pcm.c:2166:9: expected int sound/soc/soc-pcm.c:2166:9: got restricted snd_pcm_format_t Signed-off-by: Ben Dooks Link: https://patch.msgid.link/20260617102943.893950-1-ben.dooks@codethink.co.uk Signed-off-by: Takashi Iwai --- sound/core/pcm_lib.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/core/pcm_lib.c b/sound/core/pcm_lib.c index fe597f7d522d..4d665b4148d7 100644 --- a/sound/core/pcm_lib.c +++ b/sound/core/pcm_lib.c @@ -545,7 +545,7 @@ void snd_pcm_set_sync_per_card(struct snd_pcm_substream *substream, struct snd_pcm_hw_params *params, const unsigned char *id, unsigned int len) { - *(__u32 *)params->sync = cpu_to_le32(substream->pcm->card->number); + *(__le32 *)params->sync = cpu_to_le32(substream->pcm->card->number); len = min(12, len); memcpy(params->sync + 4, id, len); memset(params->sync + 4 + len, 0, 12 - len); From f7f3f9fd81e7adbaa12c2e62ee07f0e094a543fd Mon Sep 17 00:00:00 2001 From: Maoyi Xie Date: Thu, 18 Jun 2026 14:03:15 +0800 Subject: [PATCH 080/297] ALSA: caiaq: fix out-of-bounds read in the Traktor Kontrol S4 input parser snd_usb_caiaq_tks4_dispatch() decodes the Traktor Kontrol S4 input stream in fixed 16-byte (TKS4_MSGBLOCK_SIZE) message blocks. On every iteration it advances buf and subtracts the block size while looping on "while (len)". len is urb->actual_length. That value is supplied by the device and is not guaranteed to be a multiple of 16. When a final short block leaves len between 1 and 15, the loop runs once more, reads up to buf[15], and then does "len -= TKS4_MSGBLOCK_SIZE". As len is unsigned this underflows to a huge value. The loop then keeps iterating and walking buf far past the end of the 512-byte ep4_in_buf, reading out of bounds until a bogus block id happens to be hit. Iterate only while a full message block is available. This stops the unsigned underflow and silently drops any trailing partial block, which carries no complete control value anyway. The sibling endpoint-4 parsers are not affected. The Traktor Kontrol X1 and Maschine arms in snd_usb_caiaq_ep4_reply_dispatch() floor urb->actual_length before dispatching. Fixes: 15c5ab607045 ("ALSA: snd-usb-caiaq: Add support for Traktor Kontrol S4") Cc: stable@vger.kernel.org Signed-off-by: Maoyi Xie Link: https://patch.msgid.link/178176259547.3343534.2724779296835237429@maoyixie.com Signed-off-by: Takashi Iwai --- sound/usb/caiaq/input.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/usb/caiaq/input.c b/sound/usb/caiaq/input.c index 5c70fdf61cc1..2db4d1332df1 100644 --- a/sound/usb/caiaq/input.c +++ b/sound/usb/caiaq/input.c @@ -330,7 +330,7 @@ static void snd_usb_caiaq_tks4_dispatch(struct snd_usb_caiaqdev *cdev, { struct device *dev = caiaqdev_to_dev(cdev); - while (len) { + while (len >= TKS4_MSGBLOCK_SIZE) { unsigned int i, block_id = (buf[0] << 8) | buf[1]; switch (block_id) { From 58fc1275b3f288500ee79a02dbe89ed4197fdc3e Mon Sep 17 00:00:00 2001 From: Maoyi Xie Date: Thu, 18 Jun 2026 14:03:15 +0800 Subject: [PATCH 081/297] ALSA: caiaq: bound the length in the EP1 input parsers snd_caiaq_input_read_erp() and snd_caiaq_input_read_io() can be reached from snd_usb_caiaq_input_dispatch(). They read fixed byte offsets from the reply buffer without checking the reported length. On a short reply they decode stale bytes left from a previous, longer report and feed them to the input layer. This is not an out-of-bounds access. Every offset is a compile-time driver constant. The largest is buf[21] in the Maschine ERP case. The EP1 transfer buffer ep1_in_buf is EP1_BUFSIZE (64) bytes, and the USB core caps actual_length at 64, so a short reply only reads in-bounds stale data. Acting on data the device did not send is still wrong, so bail out per usb_id case when the reply is shorter than the bytes that case consumes. read_erp: AK1 needs 2 bytes, Kore needs 16, Maschine needs 22. read_io: the Kore case needs 5 bytes (buf[4]) and the Traktor Kontrol X1 case needs 7 (buf[5]/buf[6]). The preceding key bit loop is already bounded by "i < len * 8" and is left untouched. snd_caiaq_input_read_analog() and snd_usb_caiaq_maschine_dispatch() are not changed. Their callers already floor the reply length. Suggested-by: Takashi Iwai Signed-off-by: Maoyi Xie Link: https://patch.msgid.link/178176259547.3343534.6659489917322808916@maoyixie.com Signed-off-by: Takashi Iwai --- sound/usb/caiaq/input.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/sound/usb/caiaq/input.c b/sound/usb/caiaq/input.c index 2db4d1332df1..eabbf41fdfb2 100644 --- a/sound/usb/caiaq/input.c +++ b/sound/usb/caiaq/input.c @@ -237,12 +237,16 @@ static void snd_caiaq_input_read_erp(struct snd_usb_caiaqdev *cdev, switch (cdev->chip.usb_id) { case USB_ID(USB_VID_NATIVEINSTRUMENTS, USB_PID_AK1): + if (len < 2) + return; i = decode_erp(buf[0], buf[1]); input_report_abs(input_dev, ABS_X, i); input_sync(input_dev); break; case USB_ID(USB_VID_NATIVEINSTRUMENTS, USB_PID_KORECONTROLLER): case USB_ID(USB_VID_NATIVEINSTRUMENTS, USB_PID_KORECONTROLLER2): + if (len < 16) + return; i = decode_erp(buf[7], buf[5]); input_report_abs(input_dev, ABS_HAT0X, i); i = decode_erp(buf[12], buf[14]); @@ -263,6 +267,8 @@ static void snd_caiaq_input_read_erp(struct snd_usb_caiaqdev *cdev, break; case USB_ID(USB_VID_NATIVEINSTRUMENTS, USB_PID_MASCHINECONTROLLER): + if (len < 22) + return; /* 4 under the left screen */ input_report_abs(input_dev, ABS_HAT0X, decode_erp(buf[21], buf[20])); input_report_abs(input_dev, ABS_HAT0Y, decode_erp(buf[15], buf[14])); @@ -308,9 +314,13 @@ static void snd_caiaq_input_read_io(struct snd_usb_caiaqdev *cdev, switch (cdev->chip.usb_id) { case USB_ID(USB_VID_NATIVEINSTRUMENTS, USB_PID_KORECONTROLLER): case USB_ID(USB_VID_NATIVEINSTRUMENTS, USB_PID_KORECONTROLLER2): + if (len < 5) + return; input_report_abs(cdev->input_dev, ABS_MISC, 255 - buf[4]); break; case USB_ID(USB_VID_NATIVEINSTRUMENTS, USB_PID_TRAKTORKONTROLX1): + if (len < 7) + return; /* rotary encoders */ input_report_abs(cdev->input_dev, ABS_X, buf[5] & 0xf); input_report_abs(cdev->input_dev, ABS_Y, buf[5] >> 4); From 4520fbbaedbeda8861f0f0bfbe50b3bca4deae08 Mon Sep 17 00:00:00 2001 From: Haowen Tu Date: Thu, 18 Jun 2026 15:54:31 +0800 Subject: [PATCH 082/297] ALSA: hda/realtek: Add headset mic quirk for Acer S40-54 Acer S40-54 with ALC256 does not restore headset mic detection properly after S4 resume. After resume, headset plug events may no longer update the headset mic state, leaving the headset microphone unavailable. The system uses subsystem ID 1025:161f. Applying the existing ALC256_FIXUP_ACER_MIC_NO_PRESENCE fixup restores headset mic detection on this machine. Add a machine-specific quirk for this system. Signed-off-by: Haowen Tu Link: https://patch.msgid.link/20260618075431.1116988-1-tuhaowen@uniontech.com Signed-off-by: Takashi Iwai --- sound/hda/codecs/realtek/alc269.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/hda/codecs/realtek/alc269.c b/sound/hda/codecs/realtek/alc269.c index 5d09baa6d32e..d209efdb8272 100644 --- a/sound/hda/codecs/realtek/alc269.c +++ b/sound/hda/codecs/realtek/alc269.c @@ -6807,6 +6807,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1025, 0x159c, "Acer Nitro 5 AN515-58", ALC287_FIXUP_ACER_MICMUTE_LED), SND_PCI_QUIRK(0x1025, 0x1597, "Acer Nitro 5 AN517-55", ALC2XX_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x1025, 0x160e, "Acer PT316-51S", ALC2XX_FIXUP_HEADSET_MIC), + SND_PCI_QUIRK(0x1025, 0x161f, "Acer S40-54", ALC256_FIXUP_ACER_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1025, 0x1640, "Acer Aspire A315-44P", ALC256_FIXUP_ACER_SFG16_MICMUTE_LED), SND_PCI_QUIRK(0x1025, 0x1679, "Acer Nitro 16 AN16-41", ALC2XX_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x1025, 0x169a, "Acer Swift SFG16", ALC256_FIXUP_ACER_SFG16_MICMUTE_LED), From bdb640be82e645e2828731648f485224d0c2587b Mon Sep 17 00:00:00 2001 From: Michael Bommarito Date: Wed, 17 Jun 2026 22:51:25 -0400 Subject: [PATCH 083/297] ALSA: usb-audio: qcom: reject stream disable with no active interface handle_uaudio_stream_req() resolves an interface index with info_idx_from_ifnum(), which returns -EINVAL when no interface matches. The enable branch and the response: cleanup label both guard against a negative index, but the disable branch does not: it forms info = &uadev[pcm_card_num].info[info_idx] and dereferences it. uadev[].info is a pointer allocated only when a stream is first enabled, so a negative info_idx on the disable path is unsafe in two ways: - If the card was never enabled, .info is NULL and &info[-EINVAL] is a wild pointer; reading info->data_ep_pipe faults (kernel oops). - If the card was enabled at least once (.info allocated) and the disable names an interface that does not match, &info[-EINVAL] points before the allocation; info->data_ep_pipe / info->sync_ep_pipe are an out-of-bounds slab read and, when non-zero, an out-of-bounds 4-byte write (both pipe fields are cleared to 0). That is memory corruption, not just a NULL dereference. The request is reachable from unprivileged local userspace over AF_QIPCRTR. Reject a disable request with no resolved interface, matching the guard the enable path already has. Fixes: 326bbc348298a ("ALSA: usb-audio: qcom: Introduce QC USB SND offloading support") Assisted-by: Claude:claude-opus-4-8 Signed-off-by: Michael Bommarito Link: https://patch.msgid.link/20260618025126.1862954-2-michael.bommarito@gmail.com Signed-off-by: Takashi Iwai --- sound/usb/qcom/qc_audio_offload.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/sound/usb/qcom/qc_audio_offload.c b/sound/usb/qcom/qc_audio_offload.c index 436d6821c5c9..3b05dadbbeae 100644 --- a/sound/usb/qcom/qc_audio_offload.c +++ b/sound/usb/qcom/qc_audio_offload.c @@ -1642,6 +1642,11 @@ static void handle_uaudio_stream_req(struct qmi_handle *handle, subs->opened = 0; } } else { + if (info_idx < 0) { + ret = -EINVAL; + goto response; + } + info = &uadev[pcm_card_num].info[info_idx]; if (info->data_ep_pipe) { ep = usb_pipe_endpoint(uadev[pcm_card_num].udev, From 3c7af07943b2718087ae791cad450af5cf646d90 Mon Sep 17 00:00:00 2001 From: Michael Bommarito Date: Wed, 17 Jun 2026 22:51:26 -0400 Subject: [PATCH 084/297] ALSA: usb-audio: qcom: clear opened when stream enable fails On enable, subs->opened is set before the service_interval is validated; an invalid interval jumps to the response label without clearing it, so the substream is wedged at -EBUSY until a disable or disconnect. Clear subs->opened on the enable error path. Fixes: 326bbc348298a ("ALSA: usb-audio: qcom: Introduce QC USB SND offloading support") Assisted-by: Claude:claude-opus-4-8 Signed-off-by: Michael Bommarito Link: https://patch.msgid.link/20260618025126.1862954-3-michael.bommarito@gmail.com Signed-off-by: Takashi Iwai --- sound/usb/qcom/qc_audio_offload.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/sound/usb/qcom/qc_audio_offload.c b/sound/usb/qcom/qc_audio_offload.c index 3b05dadbbeae..3a586fd16e72 100644 --- a/sound/usb/qcom/qc_audio_offload.c +++ b/sound/usb/qcom/qc_audio_offload.c @@ -1620,8 +1620,13 @@ static void handle_uaudio_stream_req(struct qmi_handle *handle, if (req_msg->service_interval_valid) { ret = get_data_interval_from_si(subs, req_msg->service_interval); - if (ret == -EINVAL) + if (ret == -EINVAL) { + if (req_msg->enable) { + guard(mutex)(&chip->mutex); + subs->opened = 0; + } goto response; + } datainterval = ret; } From e6fa716c9d7248e03cb93f566874bd5709901bcf Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Alvin=20=C5=A0ipraga?= Date: Wed, 17 Jun 2026 16:55:08 +0200 Subject: [PATCH 085/297] ASoC: audio-graph-card2: Drop warning for manually selected DAI formats MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Sometimes the DAI format must be specified in the audio-graph-card2 device tree, so emitting a warning can be misleading. Revert back to emitting no warning. A few examples where automatic format selection might not be applicable: - For DPCM, where the other side of the DAI link is not apparent, no proper selection can actually be made. This can lead to disagreeing formats. - Due to hardware peculiarities, some ostensibly supported formats might not work in practice. In either case, the only correct solution is for the sound card to set the format Link: https://lore.kernel.org/all/87ik7s36k2.wl-kuninori.morimoto.gx@renesas.com/ Signed-off-by: Alvin Šipraga Acked-by: Kuninori Morimoto Link: https://patch.msgid.link/20260617145508.327213-1-alvin@pqrs.dk Signed-off-by: Mark Brown --- sound/soc/generic/audio-graph-card2.c | 12 ------------ 1 file changed, 12 deletions(-) diff --git a/sound/soc/generic/audio-graph-card2.c b/sound/soc/generic/audio-graph-card2.c index 6894bb936cfd..0202ed0ee78e 100644 --- a/sound/soc/generic/audio-graph-card2.c +++ b/sound/soc/generic/audio-graph-card2.c @@ -778,18 +778,6 @@ static void graph_link_init(struct simple_util_priv *priv, graph_parse_daifmt(ports_cpu, &daifmt); graph_parse_daifmt(ports_codec, &daifmt); graph_parse_daifmt(lnk, &daifmt); - if (daifmt) { - struct device *dev = simple_priv_to_dev(priv); - - /* - * Recommend to use Auto Select by using .auto_selectable_formats. - * linux/sound/soc/renesas/rcar/core.c can be good sample for it. - * - * One note is that Audio Graph Card2 still keeps compatible to set - * DAI format via DT. - */ - dev_warn_once(dev, "use .auto_selectable_formats on each corresponding CPU/Codec driver"); - } graph_util_parse_link_direction(lnk, &playback_only, &capture_only); graph_util_parse_link_direction(ports_cpu, &playback_only, &capture_only); From 348f69320e4db6ebec6940c81154bec4b9eb275a Mon Sep 17 00:00:00 2001 From: Jean-Louis Colaco Date: Thu, 18 Jun 2026 13:32:02 +0200 Subject: [PATCH 086/297] ALSA: usb-audio: Add quirk for YAMAHA CDS3000 This quirk is identical to the one for the Yamaha Steinberg UR22, here applied to a CD player that also uses the Steinberg USB interface. This quirk is necessary to avoid sporadic "clic" noise when using the DAC of the player. Signed-off-by: Jean-Louis Colaco Link: https://patch.msgid.link/20260618113202.8363-1-jean-louis.colaco@orange.fr Signed-off-by: Takashi Iwai --- sound/usb/quirks-table.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) diff --git a/sound/usb/quirks-table.h b/sound/usb/quirks-table.h index 97f28c53d201..71444c2898b4 100644 --- a/sound/usb/quirks-table.h +++ b/sound/usb/quirks-table.h @@ -390,6 +390,20 @@ YAMAHA_DEVICE(0x105d, NULL), } } }, +{ + USB_DEVICE(0x0499, 0x150d), + QUIRK_DRIVER_INFO { + /* .vendor_name = "Yamaha", */ + /* .product_name = "CDS3000", */ + QUIRK_DATA_COMPOSITE { + { QUIRK_DATA_STANDARD_AUDIO(1) }, + { QUIRK_DATA_STANDARD_AUDIO(2) }, + { QUIRK_DATA_MIDI_YAMAHA(3) }, + { QUIRK_DATA_IGNORE(4) }, + QUIRK_COMPOSITE_END + } + } +}, { USB_DEVICE(0x0499, 0x1718), QUIRK_DRIVER_INFO { From b59aff62767bf59ca0c787015c0ddc14f60ab10d Mon Sep 17 00:00:00 2001 From: Markus Elfring Date: Thu, 18 Jun 2026 12:24:36 +0200 Subject: [PATCH 087/297] ALSA: emu10k1: Use common error handling code in snd_emu10k1_playback_open() Use an additional label so that a bit of exception handling can be better reused at the end of this function implementation. This issue was detected by using the Coccinelle software. Signed-off-by: Markus Elfring Link: https://patch.msgid.link/d709474d-62b0-4f7e-9011-a0f716b35383@web.de Signed-off-by: Takashi Iwai --- sound/pci/emu10k1/emupcm.c | 18 ++++++++++-------- 1 file changed, 10 insertions(+), 8 deletions(-) diff --git a/sound/pci/emu10k1/emupcm.c b/sound/pci/emu10k1/emupcm.c index 9023f3444d20..b8749e0131ad 100644 --- a/sound/pci/emu10k1/emupcm.c +++ b/sound/pci/emu10k1/emupcm.c @@ -1181,19 +1181,17 @@ static int snd_emu10k1_playback_open(struct snd_pcm_substream *substream) runtime->private_free = snd_emu10k1_pcm_free_substream; runtime->hw = snd_emu10k1_playback; err = snd_emu10k1_playback_set_constraints(runtime); - if (err < 0) { - kfree(epcm); - return err; - } + if (err < 0) + goto free_epcm; + if (emu->card_capabilities->emu_model) sample_rate = emu->emu1010.word_clock; else sample_rate = 48000; err = snd_pcm_hw_rule_noresample(runtime, sample_rate); - if (err < 0) { - kfree(epcm); - return err; - } + if (err < 0) + goto free_epcm; + mix = &emu->pcm_mixer[substream->number]; for (i = 0; i < 8; i++) mix->send_routing[0][i] = mix->send_routing[1][i] = mix->send_routing[2][i] = i; @@ -1204,6 +1202,10 @@ static int snd_emu10k1_playback_open(struct snd_pcm_substream *substream) mix->epcm = epcm; snd_emu10k1_pcm_mixer_notify(emu, substream->number, 1); return 0; + +free_epcm: + kfree(epcm); + return err; } static int snd_emu10k1_playback_close(struct snd_pcm_substream *substream) From 7b25dbafa2fce50b1a48c1d057adb35da3563f9b Mon Sep 17 00:00:00 2001 From: Quang Nguyen Date: Thu, 18 Jun 2026 09:19:30 +0100 Subject: [PATCH 088/297] spi: rpc-if: Use correct device for hardware reinitialization on resume rpcif_spi_resume() currently passes the SPI controller device to rpcif_hw_init(), but the function should be called with the RPC interface device. Retrieve the rpcif private data from the SPI controller and pass rpc->dev instead. Also propagate the return value of rpcif_hw_init() so that a failure during resume is properly reported rather than silently ignored. Fixes: ad4728740bd6 ("spi: rpc-if: Add resume support for RZ/G3E") Signed-off-by: Quang Nguyen Signed-off-by: Biju Das Reviewed-by: Geert Uytterhoeven Link: https://patch.msgid.link/20260618081932.172168-1-biju.das.jz@bp.renesas.com Signed-off-by: Mark Brown --- drivers/spi/spi-rpc-if.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/spi/spi-rpc-if.c b/drivers/spi/spi-rpc-if.c index 1ef7bd91b3b3..b63c7856e758 100644 --- a/drivers/spi/spi-rpc-if.c +++ b/drivers/spi/spi-rpc-if.c @@ -206,8 +206,12 @@ static int rpcif_spi_suspend(struct device *dev) static int rpcif_spi_resume(struct device *dev) { struct spi_controller *ctlr = dev_get_drvdata(dev); + struct rpcif *rpc = spi_controller_get_devdata(ctlr); + int ret; - rpcif_hw_init(dev, false); + ret = rpcif_hw_init(rpc->dev, false); + if (ret) + return ret; return spi_controller_resume(ctlr); } From 4be31c943a3a27a5a0251dbb8f5cb89059ec3d5a Mon Sep 17 00:00:00 2001 From: Zhao Zhang Date: Thu, 18 Jun 2026 23:28:05 +0800 Subject: [PATCH 089/297] smb: client: fix double-free in SMB2_flush() replay SMB2_flush() keeps its response buffer bookkeeping across replay attempts. If a replayable flush response is received and the retry then fails before cifs_send_recv() stores a replacement response, flush_exit will free the stale response pointer a second time. Reinitialize resp_buftype and rsp_iov at the top of the replay loop so cleanup only acts on response state produced by the current attempt. This fixes a double-free without changing replay handling for successful requests. Fixes: 4f1fffa23769 ("cifs: commands that are retried should have replay flag set") Cc: stable@vger.kernel.org Reported-by: Yuan Tan Reported-by: Zhengchuan Liang Reported-by: Xin Liu Assisted-by: Codex:GPT-5.4 Acked-by: Henrique Carvalho Signed-off-by: Zhao Zhang Signed-off-by: Ren Wei Signed-off-by: Steve French --- fs/smb/client/smb2pdu.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c index 3c7691b39377..318559cd00db 100644 --- a/fs/smb/client/smb2pdu.c +++ b/fs/smb/client/smb2pdu.c @@ -4450,6 +4450,8 @@ SMB2_flush(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid, replay_again: /* reinitialize for possible replay */ + resp_buftype = CIFS_NO_BUFFER; + memset(&rsp_iov, 0, sizeof(rsp_iov)); flags = 0; server = cifs_pick_channel(ses); From b55e182f2324bc6a604c21a47aa6c448f719a532 Mon Sep 17 00:00:00 2001 From: Henrique Carvalho Date: Thu, 18 Jun 2026 17:34:33 -0300 Subject: [PATCH 090/297] smb: client: fix double-free in SMB2_open() replay A response-bearing attempt can return a replayable error and free its response buffer. If SMB2_open_init() fails before the next send, cleanup retains the previous buffer type and frees that response again. Reset response bookkeeping before each attempt to prevent the stale free. Fixes: 4f1fffa23769 ("cifs: commands that are retried should have replay flag set") Cc: stable@vger.kernel.org Signed-off-by: Henrique Carvalho Signed-off-by: Steve French --- fs/smb/client/smb2pdu.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c index 318559cd00db..4d6a989748f9 100644 --- a/fs/smb/client/smb2pdu.c +++ b/fs/smb/client/smb2pdu.c @@ -3305,6 +3305,8 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path, replay_again: /* reinitialize for possible replay */ + resp_buftype = CIFS_NO_BUFFER; + memset(&rsp_iov, 0, sizeof(rsp_iov)); flags = 0; server = cifs_pick_channel(ses); oparms->replay = !!(retries); From f9bbadb6c94583e3b4af1afc449bfceb1d1ddec9 Mon Sep 17 00:00:00 2001 From: Henrique Carvalho Date: Thu, 18 Jun 2026 17:34:34 -0300 Subject: [PATCH 091/297] smb: client: fix double-free in SMB2_ioctl() replay A response-bearing attempt can return a replayable error and free its response buffer. If SMB2_ioctl_init() fails before the next send, cleanup retains the previous buffer type and frees that response again. Reset response bookkeeping before each attempt to prevent the stale free. Fixes: 4f1fffa23769 ("cifs: commands that are retried should have replay flag set") Cc: stable@vger.kernel.org Signed-off-by: Henrique Carvalho Signed-off-by: Steve French --- fs/smb/client/smb2pdu.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c index 4d6a989748f9..121ae914c3cf 100644 --- a/fs/smb/client/smb2pdu.c +++ b/fs/smb/client/smb2pdu.c @@ -3532,6 +3532,8 @@ SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid, replay_again: /* reinitialize for possible replay */ + resp_buftype = CIFS_NO_BUFFER; + memset(&rsp_iov, 0, sizeof(rsp_iov)); flags = 0; server = cifs_pick_channel(ses); From f96e1cdcb63ed3321142ff2fcdf784e32cda8fee Mon Sep 17 00:00:00 2001 From: Henrique Carvalho Date: Thu, 18 Jun 2026 17:34:35 -0300 Subject: [PATCH 092/297] smb: client: fix double-free in SMB2_close() replay A response-bearing attempt can return a replayable error and free its response buffer. If SMB2_close_init() fails before the next send, cleanup retains the previous buffer type and frees that response again. Reset response bookkeeping before each attempt to prevent the stale free. Fixes: 4f1fffa23769 ("cifs: commands that are retried should have replay flag set") Cc: stable@vger.kernel.org Signed-off-by: Henrique Carvalho Signed-off-by: Steve French --- fs/smb/client/smb2pdu.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c index 121ae914c3cf..a7b1fbe28a2d 100644 --- a/fs/smb/client/smb2pdu.c +++ b/fs/smb/client/smb2pdu.c @@ -3728,6 +3728,8 @@ __SMB2_close(const unsigned int xid, struct cifs_tcon *tcon, replay_again: /* reinitialize for possible replay */ + resp_buftype = CIFS_NO_BUFFER; + memset(&rsp_iov, 0, sizeof(rsp_iov)); flags = 0; query_attrs = false; server = cifs_pick_channel(ses); From 2a88561d66eb855813cf004a0abe648bbb17de5e Mon Sep 17 00:00:00 2001 From: Henrique Carvalho Date: Thu, 18 Jun 2026 17:34:36 -0300 Subject: [PATCH 093/297] smb: client: fix query_info() replay double-free A response-bearing attempt can return a replayable error and free its response buffer. If SMB2_query_info_init() fails before the next send, cleanup retains the previous buffer type and frees that response again. Reset response bookkeeping before each attempt to prevent the stale free. Fixes: 4f1fffa23769 ("cifs: commands that are retried should have replay flag set") Cc: stable@vger.kernel.org Signed-off-by: Henrique Carvalho Signed-off-by: Steve French --- fs/smb/client/smb2pdu.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c index a7b1fbe28a2d..6e6aed87ab0a 100644 --- a/fs/smb/client/smb2pdu.c +++ b/fs/smb/client/smb2pdu.c @@ -3942,6 +3942,8 @@ query_info(const unsigned int xid, struct cifs_tcon *tcon, replay_again: /* reinitialize for possible replay */ + resp_buftype = CIFS_NO_BUFFER; + memset(&rsp_iov, 0, sizeof(rsp_iov)); flags = 0; allocated = false; server = cifs_pick_channel(ses); From 145f820dcbb2cced374f2532f8a61a44dce4a615 Mon Sep 17 00:00:00 2001 From: Henrique Carvalho Date: Thu, 18 Jun 2026 17:34:37 -0300 Subject: [PATCH 094/297] smb: client: fix change notify replay double-free A response-bearing attempt can return a replayable error and free its response buffer. If SMB2_notify_init() fails before the next send, cleanup retains the previous buffer type and frees that response again. Reset response bookkeeping before each attempt to prevent the stale free. Fixes: 4f1fffa23769 ("cifs: commands that are retried should have replay flag set") Cc: stable@vger.kernel.org Signed-off-by: Henrique Carvalho Signed-off-by: Steve French --- fs/smb/client/smb2pdu.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c index 6e6aed87ab0a..7d4b37b776c5 100644 --- a/fs/smb/client/smb2pdu.c +++ b/fs/smb/client/smb2pdu.c @@ -4116,6 +4116,8 @@ SMB2_change_notify(const unsigned int xid, struct cifs_tcon *tcon, replay_again: /* reinitialize for possible replay */ + resp_buftype = CIFS_NO_BUFFER; + memset(&rsp_iov, 0, sizeof(rsp_iov)); flags = 0; server = cifs_pick_channel(ses); From 9647492b5e41954be59d5157eddbcd4cdc1656f7 Mon Sep 17 00:00:00 2001 From: Henrique Carvalho Date: Thu, 18 Jun 2026 17:34:38 -0300 Subject: [PATCH 095/297] smb: client: fix query directory replay double-free A response-bearing attempt can return a replayable error and free its response buffer. If SMB2_query_directory_init() fails before the next send, cleanup retains the previous buffer type and frees that response again. Reset response bookkeeping before each attempt to prevent the stale free. Fixes: 4f1fffa23769 ("cifs: commands that are retried should have replay flag set") Cc: stable@vger.kernel.org Signed-off-by: Henrique Carvalho Signed-off-by: Steve French --- fs/smb/client/smb2pdu.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c index 7d4b37b776c5..85642ea992d5 100644 --- a/fs/smb/client/smb2pdu.c +++ b/fs/smb/client/smb2pdu.c @@ -5720,6 +5720,8 @@ SMB2_query_directory(const unsigned int xid, struct cifs_tcon *tcon, replay_again: /* reinitialize for possible replay */ + resp_buftype = CIFS_NO_BUFFER; + memset(&rsp_iov, 0, sizeof(rsp_iov)); flags = 0; server = cifs_pick_channel(ses); From f199c8a8bdd54296d3458777e70fe82a78bd9817 Mon Sep 17 00:00:00 2001 From: Cen Zhang Date: Fri, 19 Jun 2026 01:00:10 +0800 Subject: [PATCH 096/297] ALSA: usb-audio: Kill MIDI 2.0 URBs before freeing endpoints MIDI 2.0 input URBs are started during snd_usb_midi_v2_create(). A later setup failure can still jump to snd_usb_midi_v2_free(), which currently frees each endpoint and its coherent URB buffers without first stopping the submitted URBs. A completion can then dereference the embedded URB context and endpoint state after they have been freed, or try to resubmit from the stale endpoint. This was observed as a KASAN slab-use-after-free in input_urb_complete(). The buggy scenario involves two paths, with each column showing the order within that path: probe error path: USB completion path: 1. start_input_streams() submits 1. The HCD still owns a input URBs. submitted input URB. 2. A later setup helper returns 2. input_urb_complete() runs an error. with urb->context in ep. 3. snd_usb_midi_v2_free() frees 3. The completion reads ep endpoint storage and URB buffers. state and can requeue URBs. Make the endpoint destructor follow the same teardown ordering used for disconnect when the endpoint has not already been disconnected: publish ep->disconnected, kill the URBs synchronously, and drain the endpoint before freeing URB buffers and endpoint storage. The guard avoids repeating the stop sequence after the normal snd_usb_midi_v2_disconnect_all() path, while still synchronizing the direct MIDI 2.0 create-error free path. Validation reproduced this kernel report: BUG: KASAN: slab-use-after-free in input_urb_complete+0x37/0x1b0 Workqueue: usb_hub_wq hub_event RIP: 0010:_raw_spin_unlock_irq+0x2e/0x50 Read of size 8 Call trace: dump_stack_lvl+0x77/0xb0 print_report+0xce/0x5f0 input_urb_complete+0x37/0x1b0 (sound/usb/midi2.c:186) srso_alias_return_thunk+0x5/0xfbef5 __virt_addr_valid+0x19f/0x330 kasan_report+0xe0/0x110 __usb_hcd_giveback_urb+0x112/0x1d0 dummy_timer+0xaaa/0x19a0 lock_is_held_type+0x9a/0x110 __lock_acquire+0x467/0x28b0 mark_held_locks+0x40/0x70 _raw_spin_unlock_irqrestore+0x44/0x60 lockdep_hardirqs_on_prepare+0xbb/0x1a0 __hrtimer_run_queues+0x101/0x520 hrtimer_run_softirq+0xd0/0x130 handle_softirqs+0x15b/0x670 __irq_exit_rcu+0xd0/0x170 irq_exit_rcu+0xe/0x20 sysvec_apic_timer_interrupt+0x6c/0x80 asm_sysvec_apic_timer_interrupt+0x1a/0x20 Fixes: d9c99876868c ("ALSA: usb-audio: Create UMP blocks from USB MIDI GTBs") Assisted-by: Codex:gpt-5.5 Signed-off-by: Cen Zhang Link: https://patch.msgid.link/20260618170010.191433-1-zzzccc427@gmail.com Signed-off-by: Takashi Iwai --- sound/usb/midi2.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/sound/usb/midi2.c b/sound/usb/midi2.c index 04aeb9052f13..3ec633291772 100644 --- a/sound/usb/midi2.c +++ b/sound/usb/midi2.c @@ -470,6 +470,11 @@ static int create_midi2_endpoint(struct snd_usb_midi2_interface *umidi, static void free_midi2_endpoint(struct snd_usb_midi2_endpoint *ep) { list_del(&ep->list); + if (!ep->disconnected) { + ep->disconnected = 1; + kill_midi_urbs(ep, false); + drain_urb_queue(ep); + } free_midi_urbs(ep); kfree(ep); } From f56521ab6f76faeaa5a524320898835454e3bc31 Mon Sep 17 00:00:00 2001 From: Ramcharan Rajpurohit Date: Fri, 19 Jun 2026 11:54:35 +0530 Subject: [PATCH 097/297] ALSA: hda/realtek: Enable mute LED on HP EliteBook 840 G6 The HP EliteBook 840 G6 (PCI SSID 103c:854d) has an ALC215 codec whose mic-mute and audio-mute LEDs are wired to the same GPIOs as the already supported EliteBook 830 G6 and 840 G7. Without a matching quirk the LEDs are never registered, so the front-panel mic-mute LED stays permanently lit and does not track the mute state. Apply ALC285_FIXUP_HP_GPIO_LED, mirroring the sibling EliteBook entries. With this fixup the codec registers an "hda::micmute" LED class device and the LED correctly follows the capture-mute state. This was verified on the affected machine by forcing the same fixup at runtime via snd_sof_intel_hda_generic.hda_model=103c:8548, which made the LED work as expected. Signed-off-by: Ramcharan Rajpurohit Link: https://patch.msgid.link/20260619062435.26256-1-b23ci1032@iitj.ac.in Signed-off-by: Takashi Iwai --- sound/hda/codecs/realtek/alc269.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/hda/codecs/realtek/alc269.c b/sound/hda/codecs/realtek/alc269.c index d209efdb8272..2df491335a76 100644 --- a/sound/hda/codecs/realtek/alc269.c +++ b/sound/hda/codecs/realtek/alc269.c @@ -6987,6 +6987,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8537, "HP ProBook 440 G6", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), SND_PCI_QUIRK(0x103c, 0x8548, "HP EliteBook x360 830 G6", ALC285_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x854a, "HP EliteBook 830 G6", ALC285_FIXUP_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x854d, "HP EliteBook 840 G6", ALC285_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x856a, "HP Pavilion 15-cs1xxx", ALC295_FIXUP_HP_PAVILION_MUTE_LED_1B), SND_PCI_QUIRK(0x103c, 0x85c6, "HP Pavilion x360 Convertible 14-dy1xxx", ALC295_FIXUP_HP_MUTE_LED_COEFBIT11), SND_PCI_QUIRK(0x103c, 0x85de, "HP Envy x360 13-ar0xxx", ALC285_FIXUP_HP_ENVY_X360), From 998d4d789d2d625e1d8c77c1b6c3951e30e81bb0 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 11 Jun 2026 15:21:44 +0200 Subject: [PATCH 098/297] arm64: static_call: include asm/insns.h I came a cross a missing declaration in a randconfig build: arch/arm64/kernel/static_call.c:16:5: error: call to undeclared function 'aarch64_insn_adrp_get_offset'; ISO C99 and later do not support implicit function declarations [-Wimplicit-function-declaration] 16 | aarch64_insn_adrp_get_offset(le32_to_cpup(tramp + 4)) + | ^ Include the header that contains this definition explicitly, rather than relying on it to come indirectly through another header. Fixes: 54ac9ff8f119 ("arm64: Use static call trampolines when kCFI is enabled") Signed-off-by: Arnd Bergmann Signed-off-by: Will Deacon --- arch/arm64/kernel/static_call.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/arm64/kernel/static_call.c b/arch/arm64/kernel/static_call.c index 8b3a19e10871..c126edced022 100644 --- a/arch/arm64/kernel/static_call.c +++ b/arch/arm64/kernel/static_call.c @@ -2,6 +2,7 @@ #include #include #include +#include void arch_static_call_transform(void *site, void *tramp, void *func, bool tail) { From 4cc70f75853bebac022334b6a86b953348072f74 Mon Sep 17 00:00:00 2001 From: Breno Leitao Date: Tue, 9 Jun 2026 06:15:53 -0700 Subject: [PATCH 099/297] arm64/hw_breakpoint: reject unaligned watchpoints that would truncate BAS hw_breakpoint_arch_parse() positions the BAS bit pattern in hw->ctrl.len with offset = hw->address & alignment_mask; /* 0..7 */ hw->ctrl.len <<= offset; ctrl.len is an 8-bit bitfield (struct arch_hw_breakpoint_ctrl::len is u32 :8), so the shift silently drops any bits past bit 7. For non-compat AArch64 watchpoints the offset is unbounded relative to ctrl.len: a perf_event_open(PERF_TYPE_BREAKPOINT) caller asking for HW_BREAKPOINT_W with bp_addr=page+1 and bp_len=HW_BREAKPOINT_LEN_8 ends up with 0xff << 1 = 0x1fe, stored as 0xfe. The kernel programs WCR.BAS=0xfe and the hardware watches bytes [1..7] instead of the requested [1..8] -- the eighth byte is silently dropped. The syscall still returns success, leaving userspace to discover the gap by empirical probing. The same class affects HW_BREAKPOINT_LEN_{2,4} when offset pushes the high BAS bit past bit 7 (e.g. LEN_4 with offset=5 yields 0xe0 instead of 0x1e0). No memory-safety impact -- the value is masked into 8 bits before encoding -- but debuggers and perf users observe missed events on bytes they thought they were watching. The AArch32 branch immediately above already rejects unrepresentable (offset, len) combinations via an explicit switch. Mirror that for the non-compat branch by checking that the shifted pattern fits in the BAS field, returning -EINVAL when it does not. GDB and similar debuggers are unaffected by the stricter check. aarch64_linux_set_debug_regs() already treats EINVAL on NT_ARM_HW_WATCH as a downgrade signal: it clears kernel_supports_any_contiguous_range, calls aarch64_downgrade_regs() to round the BAS up to a legacy 0x01/03/0f/ff mask with an aligned base, and retries -- the same fallback path that PR-20207 introduced. The new -EINVAL is therefore reachable only from a raw perf_event_open() that pairs an unaligned base with an oversized bp_len, which is precisely the bug. Reproducer: struct perf_event_attr a = { .type = PERF_TYPE_BREAKPOINT, .size = sizeof(a), .bp_type = HW_BREAKPOINT_W, .bp_addr = (uintptr_t)(buf + 1), .bp_len = HW_BREAKPOINT_LEN_8, .exclude_kernel = 1, .exclude_hv = 1, }; int fd = perf_event_open(&a, 0, -1, -1, 0); /* before this fix: succeeds, watches 7 bytes (buf+1..buf+7) */ /* after this fix: fails with EINVAL */ Fixes: b08fb180bb88 ("arm64: Allow hw watchpoint at varied offset from base address") Signed-off-by: Breno Leitao Signed-off-by: Will Deacon --- arch/arm64/kernel/hw_breakpoint.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c index ab76b36dce82..73cce8ac8368 100644 --- a/arch/arm64/kernel/hw_breakpoint.c +++ b/arch/arm64/kernel/hw_breakpoint.c @@ -559,6 +559,15 @@ int hw_breakpoint_arch_parse(struct perf_event *bp, else alignment_mask = 0x7; offset = hw->address & alignment_mask; + + /* + * BAS is an 8-bit field in WCR/BCR; the shift below would + * silently drop the high bits of ctrl.len when offset + len + * exceeds 8, programming hardware to watch fewer bytes than + * the user requested. + */ + if (((u32)hw->ctrl.len << offset) > ARM_BREAKPOINT_LEN_8) + return -EINVAL; } hw->address &= ~alignment_mask; From 07f251e0ed0b78591114101b3ce16db2e1365171 Mon Sep 17 00:00:00 2001 From: Changhuang Liang Date: Fri, 19 Jun 2026 07:34:42 -0700 Subject: [PATCH 100/297] spi: dt-bindings: snps,dw-apb-ssi: Add starfive,jhb100-spi Add a new compatible string "starfive,jhb100-spi" for the StarFive JHB100 SPI, it based on the Synopsys DesignWare SSI version 2.00a, uses snps,dwc-ssi-2.00a as the primary fallback and snps,dwc-ssi-1.01a as the secondary fallback. Signed-off-by: Changhuang Liang Acked-by: Conor Dooley Link: https://patch.msgid.link/20260619143443.22267-2-changhuang.liang@starfivetech.com Signed-off-by: Mark Brown --- Documentation/devicetree/bindings/spi/snps,dw-apb-ssi.yaml | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/Documentation/devicetree/bindings/spi/snps,dw-apb-ssi.yaml b/Documentation/devicetree/bindings/spi/snps,dw-apb-ssi.yaml index 8ebebcebca16..4458316326fc 100644 --- a/Documentation/devicetree/bindings/spi/snps,dw-apb-ssi.yaml +++ b/Documentation/devicetree/bindings/spi/snps,dw-apb-ssi.yaml @@ -54,6 +54,12 @@ properties: - sophgo,sg2042-spi - thead,th1520-spi - const: snps,dw-apb-ssi + - description: Vendor controllers which use snps,dwc-ssi-2.00a as fallback + items: + - enum: + - starfive,jhb100-spi + - const: snps,dwc-ssi-2.00a + - const: snps,dwc-ssi-1.01a - description: Intel Keem Bay SPI Controller const: intel,keembay-ssi - description: Intel Mount Evans Integrated Management Complex SPI Controller From 914e708e3049c9e0be46533406abd832a46c6e8d Mon Sep 17 00:00:00 2001 From: Changhuang Liang Date: Fri, 19 Jun 2026 07:34:43 -0700 Subject: [PATCH 101/297] spi: dw: Add support for snps,dwc-ssi-2.00a Add a new compatible entry "snps,dwc-ssi-2.00a" for the Synopsys DesignWare SSI controller version 2.00a. This variant uses the same initialization routine as snps,dwc-ssi-1.01a (dw_spi_hssi_init). Signed-off-by: Changhuang Liang Link: https://patch.msgid.link/20260619143443.22267-3-changhuang.liang@starfivetech.com Signed-off-by: Mark Brown --- drivers/spi/spi-dw-mmio.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/spi/spi-dw-mmio.c b/drivers/spi/spi-dw-mmio.c index 4fc864d38cff..603e81a92c57 100644 --- a/drivers/spi/spi-dw-mmio.c +++ b/drivers/spi/spi-dw-mmio.c @@ -438,6 +438,7 @@ static const struct of_device_id dw_spi_mmio_of_match[] = { { .compatible = "amazon,alpine-dw-apb-ssi", .data = dw_spi_alpine_init}, { .compatible = "renesas,rzn1-spi", .data = dw_spi_pssi_init}, { .compatible = "snps,dwc-ssi-1.01a", .data = dw_spi_hssi_init}, + { .compatible = "snps,dwc-ssi-2.00a", .data = dw_spi_hssi_init}, { .compatible = "intel,keembay-ssi", .data = dw_spi_hssi_no_dma_init}, { .compatible = "intel,mountevans-imc-ssi", From fbef4191b4961c125585c715407e693f7d0024a9 Mon Sep 17 00:00:00 2001 From: Joy Zou Date: Thu, 18 Jun 2026 10:03:05 +0800 Subject: [PATCH 102/297] regulator: pca9450: Correct default t_off_deb for PCA9451A/PCA9452 The PMIC PCA9451A and PCA9452 have a default power-off debounce time of 2ms according to their datasheet, while PCA9450A and PCA9450BC use 120us. Add default_t_off_deb field to struct pca9450 to support per-variant default configuration when the device tree property is not specified. Datasheet reference links: - PCA9451A Rev.2.1: https://www.nxp.com/docs/en/data-sheet/PCA9451A.pdf - PCA9452 Rev.1.0: https://www.nxp.com/docs/en/data-sheet/PCA9452.pdf Signed-off-by: Joy Zou Reviewed-by: Frank Li Link: https://patch.msgid.link/20260618-b4-regulator-opt-v1-1-c43b1f62aaf6@oss.nxp.com Signed-off-by: Mark Brown --- drivers/regulator/pca9450-regulator.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/regulator/pca9450-regulator.c b/drivers/regulator/pca9450-regulator.c index 45d7dc44c2cd..c41db70fa052 100644 --- a/drivers/regulator/pca9450-regulator.c +++ b/drivers/regulator/pca9450-regulator.c @@ -44,6 +44,7 @@ struct pca9450 { unsigned int rcnt; int irq; bool sd_vsel_fixed_low; + int default_t_off_deb; }; static const struct regmap_range pca9450_status_range = { @@ -1209,7 +1210,7 @@ static int pca9450_of_init(struct pca9450 *pca9450) ret = of_property_read_u32(i2c->dev.of_node, "nxp,pmic-on-req-off-debounce-us", &val); if (ret == -EINVAL) - t_off_deb = T_OFF_DEB_120US; + t_off_deb = pca9450->default_t_off_deb; else if (ret) return ret; else { @@ -1304,21 +1305,25 @@ static int pca9450_i2c_probe(struct i2c_client *i2c) case PCA9450_TYPE_PCA9450A: regulator_desc = pca9450a_regulators; pca9450->rcnt = ARRAY_SIZE(pca9450a_regulators); + pca9450->default_t_off_deb = T_OFF_DEB_120US; type_name = "pca9450a"; break; case PCA9450_TYPE_PCA9450BC: regulator_desc = pca9450bc_regulators; pca9450->rcnt = ARRAY_SIZE(pca9450bc_regulators); + pca9450->default_t_off_deb = T_OFF_DEB_120US; type_name = "pca9450bc"; break; case PCA9450_TYPE_PCA9451A: regulator_desc = pca9451a_regulators; pca9450->rcnt = ARRAY_SIZE(pca9451a_regulators); + pca9450->default_t_off_deb = T_OFF_DEB_2MS; type_name = "pca9451a"; break; case PCA9450_TYPE_PCA9452: regulator_desc = pca9451a_regulators; pca9450->rcnt = ARRAY_SIZE(pca9451a_regulators); + pca9450->default_t_off_deb = T_OFF_DEB_2MS; type_name = "pca9452"; break; default: From b91d287fa7a1ba0727eed5823c6ee4924ee5fa31 Mon Sep 17 00:00:00 2001 From: Ricardo Neri Date: Sat, 13 Jun 2026 15:17:47 -0700 Subject: [PATCH 103/297] thermal: intel: Fix dangling resources on thermal_throttle_online() failure The function thermal_throttle_add_dev() may fail and abort a CPU hotplug online operation. Since the failure occurs within the online callback, thermal_throttle_online(), the CPU hotplug framework does not invoke the corresponding offline callback. As a result, the hardware and software resources set up during the failed operation are not torn down. Since only thermal_throttle_add_dev() can fail, call it before setting up the rest of the resources. Fixes: f6656208f04e ("x86/mce/therm_throt: Optimize notifications of thermal throttle") Signed-off-by: Ricardo Neri Link: https://patch.msgid.link/20260613-rneri-directed-therm-intr-v3-1-3a26d1e47fc8@linux.intel.com Signed-off-by: Rafael J. Wysocki --- drivers/thermal/intel/therm_throt.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/thermal/intel/therm_throt.c b/drivers/thermal/intel/therm_throt.c index 44fa4dd15dd1..45a8ef4a608b 100644 --- a/drivers/thermal/intel/therm_throt.c +++ b/drivers/thermal/intel/therm_throt.c @@ -529,8 +529,13 @@ static int thermal_throttle_online(unsigned int cpu) { struct thermal_state *state = &per_cpu(thermal_state, cpu); struct device *dev = get_cpu_device(cpu); + int err; u32 l; + err = thermal_throttle_add_dev(dev, cpu); + if (err) + return err; + state->package_throttle.level = PACKAGE_LEVEL; state->core_throttle.level = CORE_LEVEL; @@ -548,7 +553,7 @@ static int thermal_throttle_online(unsigned int cpu) l = apic_read(APIC_LVTTHMR); apic_write(APIC_LVTTHMR, l & ~APIC_LVT_MASKED); - return thermal_throttle_add_dev(dev, cpu); + return err; } static int thermal_throttle_offline(unsigned int cpu) From b2b42ad22828da9cdb876eedb8914134e0759355 Mon Sep 17 00:00:00 2001 From: Zenghui Yu Date: Thu, 11 Jun 2026 22:25:18 +0800 Subject: [PATCH 104/297] ACPI: sysfs: Fix path of module parameters in comments The correct path of module parameters should be /sys/module/acpi/parameters/xxx. Fix them. Signed-off-by: Zenghui Yu Link: https://patch.msgid.link/20260611142518.77343-1-zenghui.yu@linux.dev Signed-off-by: Rafael J. Wysocki --- drivers/acpi/sysfs.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/drivers/acpi/sysfs.c b/drivers/acpi/sysfs.c index a625de3c3c8b..908cc5c7e643 100644 --- a/drivers/acpi/sysfs.c +++ b/drivers/acpi/sysfs.c @@ -17,12 +17,12 @@ #ifdef CONFIG_ACPI_DEBUG /* * ACPI debug sysfs I/F, including: - * /sys/modules/acpi/parameters/debug_layer - * /sys/modules/acpi/parameters/debug_level - * /sys/modules/acpi/parameters/trace_method_name - * /sys/modules/acpi/parameters/trace_state - * /sys/modules/acpi/parameters/trace_debug_layer - * /sys/modules/acpi/parameters/trace_debug_level + * /sys/module/acpi/parameters/debug_layer + * /sys/module/acpi/parameters/debug_level + * /sys/module/acpi/parameters/trace_method_name + * /sys/module/acpi/parameters/trace_state + * /sys/module/acpi/parameters/trace_debug_layer + * /sys/module/acpi/parameters/trace_debug_level */ struct acpi_dlayer { @@ -269,7 +269,7 @@ module_param_call(trace_state, param_set_trace_state, param_get_trace_state, #endif /* CONFIG_ACPI_DEBUG */ -/* /sys/modules/acpi/parameters/aml_debug_output */ +/* /sys/module/acpi/parameters/aml_debug_output */ module_param_named(aml_debug_output, acpi_gbl_enable_aml_debug_object, byte, 0644); From 78ad5c7722b7bed9d35ffc5b45eb0f12e2c22fee Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Wed, 17 Jun 2026 11:05:55 +0200 Subject: [PATCH 105/297] ACPI: resource: Amend kernel-doc style The functions are referred as func() in the kernel-doc. The % (percent) character makes the rendering for constants as described in the respective documentation. Amend all these. Fixes: 8e345c991c8c ("ACPI: Centralized processing of ACPI device resources") Signed-off-by: Andy Shevchenko Link: https://patch.msgid.link/20260617090555.2648709-1-andriy.shevchenko@linux.intel.com Signed-off-by: Rafael J. Wysocki --- drivers/acpi/resource.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/acpi/resource.c b/drivers/acpi/resource.c index bc8050d8a6f5..56df4599d360 100644 --- a/drivers/acpi/resource.c +++ b/drivers/acpi/resource.c @@ -871,7 +871,7 @@ bool acpi_dev_resource_interrupt(struct acpi_resource *ares, int index, EXPORT_SYMBOL_GPL(acpi_dev_resource_interrupt); /** - * acpi_dev_free_resource_list - Free resource from %acpi_dev_get_resources(). + * acpi_dev_free_resource_list - Free resource from acpi_dev_get_resources(). * @list: The head of the resource list to free. */ void acpi_dev_free_resource_list(struct list_head *list) @@ -991,7 +991,7 @@ static int __acpi_dev_get_resources(struct acpi_device *adev, * * The resultant struct resource objects are put on the list pointed to by * @list, that must be empty initially, as members of struct resource_entry - * objects. Callers of this routine should use %acpi_dev_free_resource_list() to + * objects. Callers of this routine should use acpi_dev_free_resource_list() to * free that list. * * The number of resources in the output list is returned on success, an error @@ -1032,7 +1032,7 @@ static int is_memory(struct acpi_resource *ares, void *not_used) * The resultant struct resource objects are put on the list pointed to * by @list, that must be empty initially, as members of struct * resource_entry objects. Callers of this routine should use - * %acpi_dev_free_resource_list() to free that list. + * acpi_dev_free_resource_list() to free that list. * * The number of resources in the output list is returned on success, * an error code reflecting the error condition is returned otherwise. From 71b57aca295d61276a60e131d8f62b0cc7cf1a35 Mon Sep 17 00:00:00 2001 From: Xu Rao Date: Tue, 16 Jun 2026 17:36:21 +0800 Subject: [PATCH 106/297] ACPI: IPMI: Fix inverted interface check in ipmi_bmc_gone() Before commit a1a69b297e47 ("ACPI / IPMI: Fix race caused by the unprotected ACPI IPMI user"), ipmi_bmc_gone() skipped entries whose interface number did not match the SMI being removed, then killed the matching entry: if (ipmi_device->ipmi_ifnum != iface) continue; __ipmi_dev_kill(ipmi_device); That commit folded the removal block into the existing non-match test while converting the object lifetime handling, but left the comparison unchanged. The old != meant "continue past this entry"; after the refactor it meant "kill this entry". As a result, a single ACPI IPMI interface is never removed when its SMI disappears. If multiple interfaces are tracked, the first interface whose number differs from iface is removed instead, while the interface that actually disappeared remains on driver_data.ipmi_devices. The stale entry is not marked dead and can continue to be selected for ACPI IPMI transactions. It can also prevent the same ACPI handle from being registered again. Change the comparison to == so ipmi_bmc_gone() removes exactly the interface reported as gone by the SMI watcher. This restores the pre-a1a69b297e47 behavior and is the correct interface matching logic. Fixes: a1a69b297e47 ("ACPI / IPMI: Fix race caused by the unprotected ACPI IPMI user") Signed-off-by: Xu Rao Link: https://patch.msgid.link/B486593E06E6F6E0+20260616093621.1039943-1-raoxu@uniontech.com Signed-off-by: Rafael J. Wysocki --- drivers/acpi/acpi_ipmi.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/acpi/acpi_ipmi.c b/drivers/acpi/acpi_ipmi.c index 79ce6e72bf29..2dbed92d54b3 100644 --- a/drivers/acpi/acpi_ipmi.c +++ b/drivers/acpi/acpi_ipmi.c @@ -490,7 +490,7 @@ static void ipmi_bmc_gone(int iface) mutex_lock(&driver_data.ipmi_lock); list_for_each_entry_safe(iter, temp, &driver_data.ipmi_devices, head) { - if (iter->ipmi_ifnum != iface) { + if (iter->ipmi_ifnum == iface) { ipmi_device = iter; __ipmi_dev_kill(iter); break; From a540a64c4801fe02e452ee37e961018106418260 Mon Sep 17 00:00:00 2001 From: Ralph Boehme Date: Sat, 20 Jun 2026 09:06:58 +0200 Subject: [PATCH 107/297] smb: client: refactor ACL setting control flow in id_mode_to_cifs_acl() Refactor the control flow in id_mode_to_cifs_acl() to reduce nesting and prevent error code overwriting. Instead of wrapping the call to ops->set_acl() in a conditional block, introduce early exits (goto id_mode_to_cifs_acl_exit) when build_sec_desc() fails or ops->set_acl is NULL. This ensures that any actual error returned by build_sec_desc() is not overwritten with -EOPNOTSUPP. Signed-off-by: Ralph Boehme Signed-off-by: Steve French --- fs/smb/client/cifsacl.c | 16 ++++++++++------ 1 file changed, 10 insertions(+), 6 deletions(-) diff --git a/fs/smb/client/cifsacl.c b/fs/smb/client/cifsacl.c index 42a3115359da..5bbf73736358 100644 --- a/fs/smb/client/cifsacl.c +++ b/fs/smb/client/cifsacl.c @@ -1834,14 +1834,18 @@ id_mode_to_cifs_acl(struct inode *inode, const char *path, __u64 *pnmode, cifs_dbg(NOISY, "build_sec_desc rc: %d\n", rc); - if (ops->set_acl == NULL) - rc = -EOPNOTSUPP; + if (rc != 0) + goto id_mode_to_cifs_acl_exit; - if (!rc) { - /* Set the security descriptor */ - rc = ops->set_acl(pnntsd, nsecdesclen, inode, path, aclflag); - cifs_dbg(NOISY, "set_cifs_acl rc: %d\n", rc); + if (ops->set_acl == NULL) { + rc = -EOPNOTSUPP; + goto id_mode_to_cifs_acl_exit; } + + /* Set the security descriptor */ + rc = ops->set_acl(pnntsd, nsecdesclen, inode, path, aclflag); + cifs_dbg(NOISY, "set_cifs_acl rc: %d\n", rc); + id_mode_to_cifs_acl_exit: cifs_put_tlink(tlink); From c3027973f692077a1b66a9fb26d6a7c46c0dc72c Mon Sep 17 00:00:00 2001 From: Wentao Liang Date: Sat, 6 Jun 2026 15:56:06 +0000 Subject: [PATCH 108/297] drm/nouveau/acr: fix missing nvkm_done() in error path of nvkm_acr_oneinit() In nvkm_acr_oneinit(), nvkm_kmap(acr->wpr) is invoked unconditionally at line 309 to obtain a mapping reference. Additionally, when both acr->wpr_fw and acr->wpr_comp are present, a second nvkm_kmap() is called inside the conditional block. Both mappings are expected to be released by nvkm_done(acr->wpr) at line 320 before the function returns successfully. However, when a mismatch is detected during the loop within the conditional block, the function returns -EINVAL at line 318 without calling nvkm_done(). This results in a leak of the kmap reference(s) acquired earlier. Fix the issue by invoking nvkm_done(acr->wpr) prior to the early return to ensure proper release of the mapping references. Fixes: 22dcda45a3d1 ("drm/nouveau/acr: implement new subdev to replace "secure boot"") Cc: stable@vger.kernel.org Signed-off-by: Wentao Liang Link: https://patch.msgid.link/20260606155606.77593-1-vulab@iscas.ac.cn Signed-off-by: Danilo Krummrich --- drivers/gpu/drm/nouveau/nvkm/subdev/acr/base.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/acr/base.c b/drivers/gpu/drm/nouveau/nvkm/subdev/acr/base.c index 4c7745cd6ae5..7fd967a2554f 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/acr/base.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/acr/base.c @@ -315,6 +315,7 @@ nvkm_acr_oneinit(struct nvkm_subdev *subdev) i, us, fw); } } + nvkm_done(acr->wpr); return -EINVAL; } nvkm_done(acr->wpr); From ab99ead646b1b833ecd57fe577a2816f2e848167 Mon Sep 17 00:00:00 2001 From: Junrui Luo Date: Wed, 10 Jun 2026 18:01:28 +0800 Subject: [PATCH 109/297] drm/nouveau: fix reversed error cleanup order in ucopy functions nouveau_uvmm_vm_bind_ucopy() and nouveau_exec_ucopy() place their error cleanup labels in allocation order rather than reverse allocation order. On a u_memcpya() failure for in_sync.s, the goto to err_free_ops (or err_free_pushs) frees the first allocation and then falls through to err_free_ins, which calls u_free() on args->in_sync.s. Since args->in_sync.s still holds the ERR_PTR returned by the failed u_memcpya(), and ERR_PTR values are not caught by ZERO_OR_NULL_PTR(), kvfree() proceeds to dereference it, which can result in a kernel oops. A failure for out_sync.s instead jumps to err_free_ins and skips freeing the first allocation, leading to a memory leak. Fix by swapping the cleanup label order so resources are freed in the correct reverse allocation sequence. Fixes: b88baab82871 ("drm/nouveau: implement new VM_BIND uAPI") Reported-by: Yuhao Jiang Cc: stable@vger.kernel.org Signed-off-by: Junrui Luo Link: https://patch.msgid.link/SYBPR01MB7881484D91A6F80271415F71AF1A2@SYBPR01MB7881.ausprd01.prod.outlook.com Signed-off-by: Danilo Krummrich --- drivers/gpu/drm/nouveau/nouveau_exec.c | 4 ++-- drivers/gpu/drm/nouveau/nouveau_uvmm.c | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/nouveau/nouveau_exec.c b/drivers/gpu/drm/nouveau/nouveau_exec.c index c01a01aee32b..a08ab1cfea9b 100644 --- a/drivers/gpu/drm/nouveau/nouveau_exec.c +++ b/drivers/gpu/drm/nouveau/nouveau_exec.c @@ -331,10 +331,10 @@ nouveau_exec_ucopy(struct nouveau_exec_job_args *args, return 0; -err_free_pushs: - u_free(args->push.s); err_free_ins: u_free(args->in_sync.s); +err_free_pushs: + u_free(args->push.s); return ret; } diff --git a/drivers/gpu/drm/nouveau/nouveau_uvmm.c b/drivers/gpu/drm/nouveau/nouveau_uvmm.c index 36445915aa58..f5e4756b4de4 100644 --- a/drivers/gpu/drm/nouveau/nouveau_uvmm.c +++ b/drivers/gpu/drm/nouveau/nouveau_uvmm.c @@ -1779,10 +1779,10 @@ nouveau_uvmm_vm_bind_ucopy(struct nouveau_uvmm_bind_job_args *args, return 0; -err_free_ops: - u_free(args->op.s); err_free_ins: u_free(args->in_sync.s); +err_free_ops: + u_free(args->op.s); return ret; } From c7ab7504631d8d9aecee3d1509cc779eb4778844 Mon Sep 17 00:00:00 2001 From: Udaya Kiran Challa Date: Thu, 14 May 2026 23:03:32 +0530 Subject: [PATCH 110/297] dt-bindings: rtc: epson,rx6110: Convert to DT Schema Convert the Epson RX6110 Real Time Clock devicetree binding from the legacy text format to DT schema. Signed-off-by: Udaya Kiran Challa Reviewed-by: Krzysztof Kozlowski Link: https://patch.msgid.link/20260514173851.25088-1-challauday369@gmail.com Signed-off-by: Alexandre Belloni --- .../devicetree/bindings/rtc/epson,rx6110.txt | 39 ----------- .../devicetree/bindings/rtc/epson,rx6110.yaml | 68 +++++++++++++++++++ 2 files changed, 68 insertions(+), 39 deletions(-) delete mode 100644 Documentation/devicetree/bindings/rtc/epson,rx6110.txt create mode 100644 Documentation/devicetree/bindings/rtc/epson,rx6110.yaml diff --git a/Documentation/devicetree/bindings/rtc/epson,rx6110.txt b/Documentation/devicetree/bindings/rtc/epson,rx6110.txt deleted file mode 100644 index 3dc313e01f77..000000000000 --- a/Documentation/devicetree/bindings/rtc/epson,rx6110.txt +++ /dev/null @@ -1,39 +0,0 @@ -Epson RX6110 Real Time Clock -============================ - -The Epson RX6110 can be used with SPI or I2C busses. The kind of -bus depends on the SPISEL pin and can not be configured via software. - -I2C mode --------- - -Required properties: - - compatible: should be: "epson,rx6110" - - reg : the I2C address of the device for I2C - -Example: - - rtc: rtc@32 { - compatible = "epson,rx6110" - reg = <0x32>; - }; - -SPI mode --------- - -Required properties: - - compatible: should be: "epson,rx6110" - - reg: chip select number - - spi-cs-high: RX6110 needs chipselect high - - spi-cpha: RX6110 works with SPI shifted clock phase - - spi-cpol: RX6110 works with SPI inverse clock polarity - -Example: - - rtc: rtc@3 { - compatible = "epson,rx6110" - reg = <3> - spi-cs-high; - spi-cpha; - spi-cpol; - }; diff --git a/Documentation/devicetree/bindings/rtc/epson,rx6110.yaml b/Documentation/devicetree/bindings/rtc/epson,rx6110.yaml new file mode 100644 index 000000000000..55086ac7d1e2 --- /dev/null +++ b/Documentation/devicetree/bindings/rtc/epson,rx6110.yaml @@ -0,0 +1,68 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/rtc/epson,rx6110.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Epson RX6110 Real Time Clock + +description: + The Epson RX6110 can be used with SPI or I2C busses. The kind of bus depends + on the SPISEL pin and cannot be configured via software. + +maintainers: + - Alexandre Belloni + +allOf: + - $ref: rtc.yaml# + - $ref: /schemas/spi/spi-peripheral-props.yaml# + +properties: + compatible: + const: epson,rx6110 + + reg: + maxItems: 1 + + spi-cs-high: true + spi-cpha: true + spi-cpol: true + +required: + - compatible + - reg + +dependencies: + spi-cs-high: [ spi-cpha, spi-cpol ] + spi-cpha: [ spi-cs-high, spi-cpol ] + spi-cpol: [ spi-cs-high, spi-cpha ] + +unevaluatedProperties: false + +examples: + # I2C mode + - | + i2c { + #address-cells = <1>; + #size-cells = <0>; + + rtc@32 { + compatible = "epson,rx6110"; + reg = <0x32>; + }; + }; + + # SPI mode + - | + spi { + #address-cells = <1>; + #size-cells = <0>; + + rtc@3 { + compatible = "epson,rx6110"; + reg = <3>; + spi-cs-high; + spi-cpha; + spi-cpol; + }; + }; From 7e342d87aa8e6b831cf6d21ca41b1f7e032d0fcf Mon Sep 17 00:00:00 2001 From: Lad Prabhakar Date: Tue, 2 Jun 2026 20:25:55 +0100 Subject: [PATCH 111/297] rtc: renesas-rtca3: Fix PIE clear polling condition in alarm setup error path In rtca3_set_alarm(), the setup_failed path attempts to disable the Periodic Interrupt Enable (PIE) bit and wait until it is cleared. However, the polling condition passed to readb_poll_timeout_atomic() uses an incorrect expression: !(tmp & ~RTCA3_RCR1_PIE) As ~RTCA3_RCR1_PIE evaluates to a mask of all bits except PIE, the condition effectively waits for all non-PIE bits to become zero, which is unrelated to the intended operation and is unlikely to ever be true. This causes the poll to time out unnecessarily. Fix the condition to check for the PIE bit itself being cleared: !(tmp & RTCA3_RCR1_PIE) This correctly waits until PIE is deasserted after being cleared. Fixes: d4488377609e3 ("rtc: renesas-rtca3: Add driver for RTCA-3 available on Renesas RZ/G3S SoC") Cc: stable@vger.kernel.org Signed-off-by: Lad Prabhakar Reviewed-by: Claudiu Beznea Tested-by: Claudiu Beznea # on RZ/G3S Link: https://patch.msgid.link/20260602192559.1791344-2-prabhakar.mahadev-lad.rj@bp.renesas.com Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-renesas-rtca3.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/rtc/rtc-renesas-rtca3.c b/drivers/rtc/rtc-renesas-rtca3.c index cbabaa4dc96a..2dc080d0eb6c 100644 --- a/drivers/rtc/rtc-renesas-rtca3.c +++ b/drivers/rtc/rtc-renesas-rtca3.c @@ -455,7 +455,7 @@ setup_failed: * specified timeout for setup. */ writeb(rcr1 & ~RTCA3_RCR1_PIE, priv->base + RTCA3_RCR1); - readb_poll_timeout_atomic(priv->base + RTCA3_RCR1, tmp, !(tmp & ~RTCA3_RCR1_PIE), + readb_poll_timeout_atomic(priv->base + RTCA3_RCR1, tmp, !(tmp & RTCA3_RCR1_PIE), 10, RTCA3_DEFAULT_TIMEOUT_US); atomic_set(&priv->alrm_sstep, RTCA3_ALRM_SSTEP_DONE); } From fafb016d081200c7652e84202f8ba5951e659a53 Mon Sep 17 00:00:00 2001 From: Lad Prabhakar Date: Tue, 2 Jun 2026 20:25:56 +0100 Subject: [PATCH 112/297] rtc: renesas-rtca3: Check RADJ poll result during initial setup In rtca3_initial_setup(), the driver clears the RTCA3_RADJ register and waits for it to reach zero using readb_poll_timeout(). Check the return value of readb_poll_timeout() and propagate the error if the poll fails. Signed-off-by: Lad Prabhakar Reviewed-by: Claudiu Beznea Tested-by: Claudiu Beznea # on RZ/G3S Link: https://patch.msgid.link/20260602192559.1791344-3-prabhakar.mahadev-lad.rj@bp.renesas.com Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-renesas-rtca3.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/rtc/rtc-renesas-rtca3.c b/drivers/rtc/rtc-renesas-rtca3.c index 2dc080d0eb6c..af2a3878289e 100644 --- a/drivers/rtc/rtc-renesas-rtca3.c +++ b/drivers/rtc/rtc-renesas-rtca3.c @@ -634,6 +634,8 @@ static int rtca3_initial_setup(struct clk *clk, struct rtca3_priv *priv) writeb(0, priv->base + RTCA3_RADJ); ret = readb_poll_timeout(priv->base + RTCA3_RADJ, tmp, !tmp, 10, RTCA3_DEFAULT_TIMEOUT_US); + if (ret) + return ret; /* Start the RTC and enable automatic time error adjustment. */ mask = RTCA3_RCR2_START | RTCA3_RCR2_AADJE; From 09939630aad95fc3dc4cc2d94a5a96d7c4d6642f Mon Sep 17 00:00:00 2001 From: Lad Prabhakar Date: Tue, 2 Jun 2026 20:25:57 +0100 Subject: [PATCH 113/297] rtc: renesas-rtca3: Fix incorrect error message for reset assert Update the message to "assert reset" to accurately reflect the operation being performed. Signed-off-by: Lad Prabhakar Reviewed-by: Claudiu Beznea Tested-by: Claudiu Beznea # on RZ/G3S Link: https://patch.msgid.link/20260602192559.1791344-4-prabhakar.mahadev-lad.rj@bp.renesas.com Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-renesas-rtca3.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/rtc/rtc-renesas-rtca3.c b/drivers/rtc/rtc-renesas-rtca3.c index af2a3878289e..8763745b9172 100644 --- a/drivers/rtc/rtc-renesas-rtca3.c +++ b/drivers/rtc/rtc-renesas-rtca3.c @@ -702,7 +702,7 @@ static void rtca3_action(void *data) ret = reset_control_assert(priv->rstc); if (ret) - dev_err(dev, "Failed to de-assert reset!"); + dev_err(dev, "Failed to assert reset!"); ret = pm_runtime_put_sync(dev); if (ret < 0) From 9fb12656a7a5473b1ce46e27f78e92e5e8df7c58 Mon Sep 17 00:00:00 2001 From: Lad Prabhakar Date: Tue, 2 Jun 2026 20:25:58 +0100 Subject: [PATCH 114/297] rtc: renesas-rtca3: Fix typo in rtca3_ppb_per_cycle documentation Correct a typo in the kernel-doc comment for struct rtca3_ppb_per_cycle by fixing "adjutment" to "adjustment". Signed-off-by: Lad Prabhakar Reviewed-by: Claudiu Beznea Tested-by: Claudiu Beznea # on RZ/G3S Link: https://patch.msgid.link/20260602192559.1791344-5-prabhakar.mahadev-lad.rj@bp.renesas.com Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-renesas-rtca3.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/rtc/rtc-renesas-rtca3.c b/drivers/rtc/rtc-renesas-rtca3.c index 8763745b9172..97e7e65f59a5 100644 --- a/drivers/rtc/rtc-renesas-rtca3.c +++ b/drivers/rtc/rtc-renesas-rtca3.c @@ -103,7 +103,7 @@ enum rtca3_alrm_set_step { /** * struct rtca3_ppb_per_cycle - PPB per cycle - * @ten_sec: PPB per cycle in 10 seconds adjutment mode + * @ten_sec: PPB per cycle in 10 seconds adjustment mode * @sixty_sec: PPB per cycle in 60 seconds adjustment mode */ struct rtca3_ppb_per_cycle { From 2098bb8ac5f5a66b1a0e02512ae11b6208936c92 Mon Sep 17 00:00:00 2001 From: Lad Prabhakar Date: Tue, 2 Jun 2026 20:25:59 +0100 Subject: [PATCH 115/297] rtc: renesas-rtca3: Factor out year decoding helper The logic to decode the year value from the hardware registers is duplicated in both rtca3_read_time() and rtca3_read_alarm(). Introduce a helper rtca3_decode_year() to centralize this conversion. Signed-off-by: Lad Prabhakar Reviewed-by: Claudiu Beznea Tested-by: Claudiu Beznea # on RZ/G3S Link: https://patch.msgid.link/20260602192559.1791344-6-prabhakar.mahadev-lad.rj@bp.renesas.com Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-renesas-rtca3.c | 18 ++++++++++-------- 1 file changed, 10 insertions(+), 8 deletions(-) diff --git a/drivers/rtc/rtc-renesas-rtca3.c b/drivers/rtc/rtc-renesas-rtca3.c index 97e7e65f59a5..b3875d041de5 100644 --- a/drivers/rtc/rtc-renesas-rtca3.c +++ b/drivers/rtc/rtc-renesas-rtca3.c @@ -228,12 +228,19 @@ static void rtca3_prepare_cntalrm_regs_for_read(struct rtca3_priv *priv, bool cn } } +static u32 rtca3_decode_year(u8 mask, u16 year) +{ + u8 y = FIELD_GET(mask, year); + u32 century = bcd2bin((y == 0x99) ? 0x19 : 0x20); + + return (century * 100 + bcd2bin(y)) - 1900; +} + static int rtca3_read_time(struct device *dev, struct rtc_time *tm) { struct rtca3_priv *priv = dev_get_drvdata(dev); u8 sec, min, hour, wday, mday, month, tmp; u8 trials = 0; - u32 year100; u16 year; guard(spinlock_irqsave)(&priv->lock); @@ -274,9 +281,7 @@ static int rtca3_read_time(struct device *dev, struct rtc_time *tm) tm->tm_wday = bcd2bin(FIELD_GET(RTCA3_RWKCNT_WK, wday)); tm->tm_mday = bcd2bin(FIELD_GET(RTCA3_RDAYCNT_DAY, mday)); tm->tm_mon = bcd2bin(FIELD_GET(RTCA3_RMONCNT_MONTH, month)) - 1; - year = FIELD_GET(RTCA3_RYRCNT_YEAR, year); - year100 = bcd2bin((year == 0x99) ? 0x19 : 0x20); - tm->tm_year = (year100 * 100 + bcd2bin(year)) - 1900; + tm->tm_year = rtca3_decode_year(RTCA3_RYRCNT_YEAR, year); return 0; } @@ -354,7 +359,6 @@ static int rtca3_read_alarm(struct device *dev, struct rtc_wkalrm *wkalrm) struct rtca3_priv *priv = dev_get_drvdata(dev); u8 sec, min, hour, wday, mday, month; struct rtc_time *tm = &wkalrm->time; - u32 year100; u16 year; guard(spinlock_irqsave)(&priv->lock); @@ -373,9 +377,7 @@ static int rtca3_read_alarm(struct device *dev, struct rtc_wkalrm *wkalrm) tm->tm_wday = bcd2bin(FIELD_GET(RTCA3_RWKAR_DAYW, wday)); tm->tm_mday = bcd2bin(FIELD_GET(RTCA3_RDAYAR_DATE, mday)); tm->tm_mon = bcd2bin(FIELD_GET(RTCA3_RMONAR_MON, month)) - 1; - year = FIELD_GET(RTCA3_RYRAR_YR, year); - year100 = bcd2bin((year == 0x99) ? 0x19 : 0x20); - tm->tm_year = (year100 * 100 + bcd2bin(year)) - 1900; + tm->tm_year = rtca3_decode_year(RTCA3_RYRAR_YR, year); wkalrm->enabled = !!(readb(priv->base + RTCA3_RCR1) & RTCA3_RCR1_AIE); From 419719c514252a2dbb2e2976f564c83417dd6d0a Mon Sep 17 00:00:00 2001 From: Antoni Pokusinski Date: Wed, 15 Apr 2026 18:06:11 +0200 Subject: [PATCH 116/297] rtc: abx80x: fix the RTC_VL_CLR clearing all status flags The RTC_VL_CLR ioctl intends to clear only the battery low flag (BLF), however the current implementation writes 0 to the status register, clearing all status bits. Fix this by writing back the masked status value so that only BLF is cleared, preserving other status flags. Fixes: ffe1c5a2d427 ("rtc: abx80x: Implement RTC_VL_READ,CLR ioctls") Signed-off-by: Antoni Pokusinski Link: https://patch.msgid.link/20260415160610.127155-2-apokusinski01@gmail.com Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-abx80x.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/rtc/rtc-abx80x.c b/drivers/rtc/rtc-abx80x.c index 00d7de64ed3e..008a70baa69f 100644 --- a/drivers/rtc/rtc-abx80x.c +++ b/drivers/rtc/rtc-abx80x.c @@ -545,7 +545,8 @@ static int abx80x_ioctl(struct device *dev, unsigned int cmd, unsigned long arg) status &= ~ABX8XX_STATUS_BLF; - tmp = i2c_smbus_write_byte_data(client, ABX8XX_REG_STATUS, 0); + tmp = i2c_smbus_write_byte_data(client, ABX8XX_REG_STATUS, + status); if (tmp < 0) return tmp; From 9792ff8afa9017fe14f436f3ef3cd75f41f9f145 Mon Sep 17 00:00:00 2001 From: Conor Dooley Date: Wed, 13 May 2026 18:55:55 +0100 Subject: [PATCH 117/297] rtc: mpfs: fix counter upload completion condition The condition that needs to be checked for upload completion is the UPLOAD bit in the completion register going low. The original iterations of this driver used a do-while and this was converted to a read_poll_timeout() during upstreaming without the condition being inverted as it should have been. I suspect that this went unnoticed until now because a) the first read was done when the bit was still set, immediately completing the read_poll_timeout() and b) because the RTC doesn't hold time when power is removed from the SoC reducing its utility (I for one keep it disabled). If my first suspicion was true when the driver was upstreamed, it's not true any longer though, hence the detection of the problem. Fixes: 0b31d703598dc ("rtc: Add driver for Microchip PolarFire SoC") CC: stable@vger.kernel.org Signed-off-by: Conor Dooley Tested-by: Valentina Fernandez Link: https://patch.msgid.link/20260513-panhandle-ashy-70c6abf84d59@spud Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-mpfs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/rtc/rtc-mpfs.c b/drivers/rtc/rtc-mpfs.c index 6aa3eae575d2..ece6de4a6adb 100644 --- a/drivers/rtc/rtc-mpfs.c +++ b/drivers/rtc/rtc-mpfs.c @@ -112,7 +112,7 @@ static int mpfs_rtc_settime(struct device *dev, struct rtc_time *tm) ctrl |= CONTROL_UPLOAD_BIT; writel(ctrl, rtcdev->base + CONTROL_REG); - ret = read_poll_timeout(readl, prog, prog & CONTROL_UPLOAD_BIT, 0, UPLOAD_TIMEOUT_US, + ret = read_poll_timeout(readl, prog, !(prog & CONTROL_UPLOAD_BIT), 0, UPLOAD_TIMEOUT_US, false, rtcdev->base + CONTROL_REG); if (ret) { dev_err(dev, "timed out uploading time to rtc"); From a091e1ba3b68cabc9caedafc6f81d9fe9b3b2200 Mon Sep 17 00:00:00 2001 From: Ronan Dalton Date: Fri, 8 May 2026 15:24:49 +1200 Subject: [PATCH 118/297] rtc: ds1307: handle oscillator stop flag for ds1337/ds1339/ds3231 Prior to commit 48458654659c ("rtc: ds1307: remove clear of oscillator stop flag (OSF) in probe"), the oscillator stop flag (OSF) bit was checked during device probe for the ds1337, ds1339, ds1341, and ds3231 chips; if it was set, it would be cleared and a warning would be logged saying "SET TIME!". Since that commit, the OSF bit is no longer cleared, but the warning is still printed. Directly following that commit, there was no way to get rid of this warning because nothing cleared the OSF bit on these chips. The commit associated with the previous commit, 523923cfd5d6 ("rtc: ds1307: handle oscillator stop flag (OSF) for ds1341"), made proper use of the OSF when getting and setting the time in the RTC. However, the other RTC variants ds1337, ds1339 and ds3231 didn't have a corresponding change made. Given that the OSF bit is no longer cleared at probe time when it is set, the remaining three chips should have the same handling as the ds1341 chip has for the OSF bit. Fix the issue on the ds1337, ds1339 and ds3231 chips by applying the same logic as the ds1341 has to these chips. Note that any devices brought up between the first referenced commit and this one may begin mistrusting the time reported by the RTC until it is set again, if the bit was never explicitly cleared. Note that only the ds1339 was tested with this change, but the datasheets for the other chips contain essentially identical descriptions of the OSF bit so the same change should work. Signed-off-by: Ronan Dalton Cc: linux-rtc@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: Alexandre Belloni Cc: Tyler Hicks Cc: Sasha Levin Cc: Meagan Lloyd Cc: Rodolfo Giometti Cc: Chris Packham Fixes: 48458654659c ("rtc: ds1307: remove clear of oscillator stop flag (OSF) in probe") Reviewed-by: Meagan Lloyd Reviewed-by: Tyler Hicks Link: https://patch.msgid.link/20260508032518.3696705-2-ronan.dalton@alliedtelesis.co.nz Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-ds1307.c | 28 +++++++++++++++++----------- 1 file changed, 17 insertions(+), 11 deletions(-) diff --git a/drivers/rtc/rtc-ds1307.c b/drivers/rtc/rtc-ds1307.c index 7205c59ff729..edf81b975dec 100644 --- a/drivers/rtc/rtc-ds1307.c +++ b/drivers/rtc/rtc-ds1307.c @@ -269,6 +269,16 @@ static int ds1307_get_time(struct device *dev, struct rtc_time *t) if (tmp & DS1338_BIT_OSF) return -EINVAL; break; + case ds_1337: + case ds_1339: + case ds_1341: + case ds_3231: + ret = regmap_read(ds1307->regmap, DS1337_REG_STATUS, &tmp); + if (ret) + return ret; + if (tmp & DS1337_BIT_OSF) + return -EINVAL; + break; case ds_1340: if (tmp & DS1340_BIT_nEOSC) return -EINVAL; @@ -279,13 +289,6 @@ static int ds1307_get_time(struct device *dev, struct rtc_time *t) if (tmp & DS1340_BIT_OSF) return -EINVAL; break; - case ds_1341: - ret = regmap_read(ds1307->regmap, DS1337_REG_STATUS, &tmp); - if (ret) - return ret; - if (tmp & DS1337_BIT_OSF) - return -EINVAL; - break; case ds_1388: ret = regmap_read(ds1307->regmap, DS1388_REG_FLAG, &tmp); if (ret) @@ -380,14 +383,17 @@ static int ds1307_set_time(struct device *dev, struct rtc_time *t) regmap_update_bits(ds1307->regmap, DS1307_REG_CONTROL, DS1338_BIT_OSF, 0); break; + case ds_1337: + case ds_1339: + case ds_1341: + case ds_3231: + regmap_update_bits(ds1307->regmap, DS1337_REG_STATUS, + DS1337_BIT_OSF, 0); + break; case ds_1340: regmap_update_bits(ds1307->regmap, DS1340_REG_FLAG, DS1340_BIT_OSF, 0); break; - case ds_1341: - regmap_update_bits(ds1307->regmap, DS1337_REG_STATUS, - DS1337_BIT_OSF, 0); - break; case ds_1388: regmap_update_bits(ds1307->regmap, DS1388_REG_FLAG, DS1388_BIT_OSF, 0); From 3eebec1cb5dc1abd9d0b6a97a752800bf1a4e035 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig=20=28The=20Capable=20Hub=29?= Date: Fri, 15 May 2026 17:47:20 +0200 Subject: [PATCH 119/297] rtc: Use named initializers for arrays of i2c_device_data MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit While being less compact, using named initializers allows to more easily see which members of the structs are assigned which value without having to lookup the declaration of the struct. And it's also more robust against changes to the struct definition. The mentioned robustness is relevant for a planned change to struct i2c_device_id that replaces .driver_data by an anonymous union. While touching all these arrays, unify usage of whitespace and commas. This patch doesn't modify the compiled arrays, only their representation in source form benefits. The former was confirmed with x86 and arm64 builds. Signed-off-by: Uwe Kleine-König (The Capable Hub) Reviewed-by: Tóth János Link: https://patch.msgid.link/20260515154720.406128-2-u.kleine-koenig@baylibre.com Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-ab-b5ze-s3.c | 2 +- drivers/rtc/rtc-ab-eoz9.c | 2 +- drivers/rtc/rtc-abx80x.c | 20 ++++++++++---------- drivers/rtc/rtc-bq32k.c | 2 +- drivers/rtc/rtc-ds1307.c | 36 ++++++++++++++++++------------------ drivers/rtc/rtc-ds1374.c | 2 +- drivers/rtc/rtc-ds1672.c | 2 +- drivers/rtc/rtc-ds3232.c | 2 +- drivers/rtc/rtc-em3027.c | 2 +- drivers/rtc/rtc-fm3130.c | 2 +- drivers/rtc/rtc-hym8563.c | 4 ++-- drivers/rtc/rtc-isl12022.c | 2 +- drivers/rtc/rtc-isl12026.c | 4 ++-- drivers/rtc/rtc-isl1208.c | 10 +++++----- drivers/rtc/rtc-m41t80.c | 22 +++++++++++----------- drivers/rtc/rtc-max31335.c | 4 ++-- drivers/rtc/rtc-max6900.c | 2 +- drivers/rtc/rtc-nct3018y.c | 2 +- drivers/rtc/rtc-pcf2127.c | 8 ++++---- drivers/rtc/rtc-pcf85063.c | 12 ++++++------ drivers/rtc/rtc-pcf8523.c | 2 +- drivers/rtc/rtc-pcf8563.c | 6 +++--- drivers/rtc/rtc-pcf8583.c | 2 +- drivers/rtc/rtc-rs5c372.c | 12 ++++++------ drivers/rtc/rtc-rv3029c2.c | 4 ++-- drivers/rtc/rtc-rv8803.c | 8 ++++---- drivers/rtc/rtc-rx6110.c | 2 +- drivers/rtc/rtc-rx8010.c | 2 +- drivers/rtc/rtc-rx8025.c | 4 ++-- drivers/rtc/rtc-rx8581.c | 2 +- drivers/rtc/rtc-s35390a.c | 2 +- drivers/rtc/rtc-sd2405al.c | 2 +- drivers/rtc/rtc-sd3078.c | 2 +- drivers/rtc/rtc-x1205.c | 2 +- 34 files changed, 97 insertions(+), 97 deletions(-) diff --git a/drivers/rtc/rtc-ab-b5ze-s3.c b/drivers/rtc/rtc-ab-b5ze-s3.c index 684f9898d768..6439ca427c32 100644 --- a/drivers/rtc/rtc-ab-b5ze-s3.c +++ b/drivers/rtc/rtc-ab-b5ze-s3.c @@ -933,7 +933,7 @@ MODULE_DEVICE_TABLE(of, abb5zes3_dt_match); #endif static const struct i2c_device_id abb5zes3_id[] = { - { "abb5zes3" }, + { .name = "abb5zes3" }, { } }; MODULE_DEVICE_TABLE(i2c, abb5zes3_id); diff --git a/drivers/rtc/rtc-ab-eoz9.c b/drivers/rtc/rtc-ab-eoz9.c index de002f7a39bf..b75f4f665076 100644 --- a/drivers/rtc/rtc-ab-eoz9.c +++ b/drivers/rtc/rtc-ab-eoz9.c @@ -546,7 +546,7 @@ MODULE_DEVICE_TABLE(of, abeoz9_dt_match); #endif static const struct i2c_device_id abeoz9_id[] = { - { "abeoz9" }, + { .name = "abeoz9" }, { } }; diff --git a/drivers/rtc/rtc-abx80x.c b/drivers/rtc/rtc-abx80x.c index 008a70baa69f..5486d9d0b1e5 100644 --- a/drivers/rtc/rtc-abx80x.c +++ b/drivers/rtc/rtc-abx80x.c @@ -753,16 +753,16 @@ static int abx80x_setup_nvmem(struct abx80x_priv *priv) } static const struct i2c_device_id abx80x_id[] = { - { "abx80x", ABX80X }, - { "ab0801", AB0801 }, - { "ab0803", AB0803 }, - { "ab0804", AB0804 }, - { "ab0805", AB0805 }, - { "ab1801", AB1801 }, - { "ab1803", AB1803 }, - { "ab1804", AB1804 }, - { "ab1805", AB1805 }, - { "rv1805", RV1805 }, + { .name = "abx80x", .driver_data = ABX80X }, + { .name = "ab0801", .driver_data = AB0801 }, + { .name = "ab0803", .driver_data = AB0803 }, + { .name = "ab0804", .driver_data = AB0804 }, + { .name = "ab0805", .driver_data = AB0805 }, + { .name = "ab1801", .driver_data = AB1801 }, + { .name = "ab1803", .driver_data = AB1803 }, + { .name = "ab1804", .driver_data = AB1804 }, + { .name = "ab1805", .driver_data = AB1805 }, + { .name = "rv1805", .driver_data = RV1805 }, { } }; MODULE_DEVICE_TABLE(i2c, abx80x_id); diff --git a/drivers/rtc/rtc-bq32k.c b/drivers/rtc/rtc-bq32k.c index 7ad34539be4d..20cd92d00fa1 100644 --- a/drivers/rtc/rtc-bq32k.c +++ b/drivers/rtc/rtc-bq32k.c @@ -304,7 +304,7 @@ static void bq32k_remove(struct i2c_client *client) } static const struct i2c_device_id bq32k_id[] = { - { "bq32000" }, + { .name = "bq32000" }, { } }; MODULE_DEVICE_TABLE(i2c, bq32k_id); diff --git a/drivers/rtc/rtc-ds1307.c b/drivers/rtc/rtc-ds1307.c index edf81b975dec..ee6e75a5efc5 100644 --- a/drivers/rtc/rtc-ds1307.c +++ b/drivers/rtc/rtc-ds1307.c @@ -1069,24 +1069,24 @@ static const struct chip_desc chips[last_ds_type] = { }; static const struct i2c_device_id ds1307_id[] = { - { "ds1307", ds_1307 }, - { "ds1308", ds_1308 }, - { "ds1337", ds_1337 }, - { "ds1338", ds_1338 }, - { "ds1339", ds_1339 }, - { "ds1388", ds_1388 }, - { "ds1340", ds_1340 }, - { "ds1341", ds_1341 }, - { "ds3231", ds_3231 }, - { "m41t0", m41t0 }, - { "m41t00", m41t00 }, - { "m41t11", m41t11 }, - { "mcp7940x", mcp794xx }, - { "mcp7941x", mcp794xx }, - { "pt7c4338", ds_1307 }, - { "rx8025", rx_8025 }, - { "isl12057", ds_1337 }, - { "rx8130", rx_8130 }, + { .name = "ds1307", .driver_data = ds_1307 }, + { .name = "ds1308", .driver_data = ds_1308 }, + { .name = "ds1337", .driver_data = ds_1337 }, + { .name = "ds1338", .driver_data = ds_1338 }, + { .name = "ds1339", .driver_data = ds_1339 }, + { .name = "ds1388", .driver_data = ds_1388 }, + { .name = "ds1340", .driver_data = ds_1340 }, + { .name = "ds1341", .driver_data = ds_1341 }, + { .name = "ds3231", .driver_data = ds_3231 }, + { .name = "m41t0", .driver_data = m41t0 }, + { .name = "m41t00", .driver_data = m41t00 }, + { .name = "m41t11", .driver_data = m41t11 }, + { .name = "mcp7940x", .driver_data = mcp794xx }, + { .name = "mcp7941x", .driver_data = mcp794xx }, + { .name = "pt7c4338", .driver_data = ds_1307 }, + { .name = "rx8025", .driver_data = rx_8025 }, + { .name = "isl12057", .driver_data = ds_1337 }, + { .name = "rx8130", .driver_data = rx_8130 }, { } }; MODULE_DEVICE_TABLE(i2c, ds1307_id); diff --git a/drivers/rtc/rtc-ds1374.c b/drivers/rtc/rtc-ds1374.c index c2359eb86bc9..8c247215d611 100644 --- a/drivers/rtc/rtc-ds1374.c +++ b/drivers/rtc/rtc-ds1374.c @@ -52,7 +52,7 @@ #define DS1374_REG_TCR 0x09 /* Trickle Charge */ static const struct i2c_device_id ds1374_id[] = { - { "ds1374" }, + { .name = "ds1374" }, { } }; MODULE_DEVICE_TABLE(i2c, ds1374_id); diff --git a/drivers/rtc/rtc-ds1672.c b/drivers/rtc/rtc-ds1672.c index 6e5314215d00..c610beb55bb5 100644 --- a/drivers/rtc/rtc-ds1672.c +++ b/drivers/rtc/rtc-ds1672.c @@ -133,7 +133,7 @@ static int ds1672_probe(struct i2c_client *client) } static const struct i2c_device_id ds1672_id[] = { - { "ds1672" }, + { .name = "ds1672" }, { } }; MODULE_DEVICE_TABLE(i2c, ds1672_id); diff --git a/drivers/rtc/rtc-ds3232.c b/drivers/rtc/rtc-ds3232.c index 18f35823b4b5..d1ef9e0dad34 100644 --- a/drivers/rtc/rtc-ds3232.c +++ b/drivers/rtc/rtc-ds3232.c @@ -566,7 +566,7 @@ static int ds3232_i2c_probe(struct i2c_client *client) } static const struct i2c_device_id ds3232_id[] = { - { "ds3232" }, + { .name = "ds3232" }, { } }; MODULE_DEVICE_TABLE(i2c, ds3232_id); diff --git a/drivers/rtc/rtc-em3027.c b/drivers/rtc/rtc-em3027.c index dc1ccbc65dcb..d555e5d59881 100644 --- a/drivers/rtc/rtc-em3027.c +++ b/drivers/rtc/rtc-em3027.c @@ -129,7 +129,7 @@ static int em3027_probe(struct i2c_client *client) } static const struct i2c_device_id em3027_id[] = { - { "em3027" }, + { .name = "em3027" }, { } }; MODULE_DEVICE_TABLE(i2c, em3027_id); diff --git a/drivers/rtc/rtc-fm3130.c b/drivers/rtc/rtc-fm3130.c index f82728ebac0c..28bb6d3f644e 100644 --- a/drivers/rtc/rtc-fm3130.c +++ b/drivers/rtc/rtc-fm3130.c @@ -53,7 +53,7 @@ struct fm3130 { int data_valid; }; static const struct i2c_device_id fm3130_id[] = { - { "fm3130" }, + { .name = "fm3130" }, { } }; MODULE_DEVICE_TABLE(i2c, fm3130_id); diff --git a/drivers/rtc/rtc-hym8563.c b/drivers/rtc/rtc-hym8563.c index 7a170c0f9710..3156aa5f2d9f 100644 --- a/drivers/rtc/rtc-hym8563.c +++ b/drivers/rtc/rtc-hym8563.c @@ -564,8 +564,8 @@ static int hym8563_probe(struct i2c_client *client) } static const struct i2c_device_id hym8563_id[] = { - { "hym8563" }, - {} + { .name = "hym8563" }, + { } }; MODULE_DEVICE_TABLE(i2c, hym8563_id); diff --git a/drivers/rtc/rtc-isl12022.c b/drivers/rtc/rtc-isl12022.c index 5fc52dc64213..bc36288854ee 100644 --- a/drivers/rtc/rtc-isl12022.c +++ b/drivers/rtc/rtc-isl12022.c @@ -604,7 +604,7 @@ static const struct of_device_id isl12022_dt_match[] = { MODULE_DEVICE_TABLE(of, isl12022_dt_match); static const struct i2c_device_id isl12022_id[] = { - { "isl12022" }, + { .name = "isl12022" }, { } }; MODULE_DEVICE_TABLE(i2c, isl12022_id); diff --git a/drivers/rtc/rtc-isl12026.c b/drivers/rtc/rtc-isl12026.c index 45a2c9f676c5..b86a325d8a23 100644 --- a/drivers/rtc/rtc-isl12026.c +++ b/drivers/rtc/rtc-isl12026.c @@ -485,8 +485,8 @@ static const struct of_device_id isl12026_dt_match[] = { MODULE_DEVICE_TABLE(of, isl12026_dt_match); static const struct i2c_device_id isl12026_id[] = { - { "isl12026" }, - { }, + { .name = "isl12026" }, + { } }; MODULE_DEVICE_TABLE(i2c, isl12026_id); diff --git a/drivers/rtc/rtc-isl1208.c b/drivers/rtc/rtc-isl1208.c index f71a6bb77b2a..bcaa766a5068 100644 --- a/drivers/rtc/rtc-isl1208.c +++ b/drivers/rtc/rtc-isl1208.c @@ -110,11 +110,11 @@ static const struct isl1208_config config_raa215300_a0 = { }; static const struct i2c_device_id isl1208_id[] = { - { "isl1208", .driver_data = (kernel_ulong_t)&config_isl1208 }, - { "isl1209", .driver_data = (kernel_ulong_t)&config_isl1209 }, - { "isl1218", .driver_data = (kernel_ulong_t)&config_isl1218 }, - { "isl1219", .driver_data = (kernel_ulong_t)&config_isl1219 }, - { "raa215300_a0", .driver_data = (kernel_ulong_t)&config_raa215300_a0 }, + { .name = "isl1208", .driver_data = (kernel_ulong_t)&config_isl1208 }, + { .name = "isl1209", .driver_data = (kernel_ulong_t)&config_isl1209 }, + { .name = "isl1218", .driver_data = (kernel_ulong_t)&config_isl1218 }, + { .name = "isl1219", .driver_data = (kernel_ulong_t)&config_isl1219 }, + { .name = "raa215300_a0", .driver_data = (kernel_ulong_t)&config_raa215300_a0 }, { } }; MODULE_DEVICE_TABLE(i2c, isl1208_id); diff --git a/drivers/rtc/rtc-m41t80.c b/drivers/rtc/rtc-m41t80.c index b26afef37d9c..3c8c379392c1 100644 --- a/drivers/rtc/rtc-m41t80.c +++ b/drivers/rtc/rtc-m41t80.c @@ -71,17 +71,17 @@ #define M41T80_FEATURE_SQ_ALT BIT(4) /* RSx bits are in reg 4 */ static const struct i2c_device_id m41t80_id[] = { - { "m41t62", M41T80_FEATURE_SQ | M41T80_FEATURE_SQ_ALT }, - { "m41t65", M41T80_FEATURE_WD }, - { "m41t80", M41T80_FEATURE_SQ }, - { "m41t81", M41T80_FEATURE_HT | M41T80_FEATURE_SQ}, - { "m41t81s", M41T80_FEATURE_HT | M41T80_FEATURE_BL | M41T80_FEATURE_SQ }, - { "m41t82", M41T80_FEATURE_HT | M41T80_FEATURE_BL | M41T80_FEATURE_SQ }, - { "m41t83", M41T80_FEATURE_HT | M41T80_FEATURE_BL | M41T80_FEATURE_SQ }, - { "m41st84", M41T80_FEATURE_HT | M41T80_FEATURE_BL | M41T80_FEATURE_SQ }, - { "m41st85", M41T80_FEATURE_HT | M41T80_FEATURE_BL | M41T80_FEATURE_SQ }, - { "m41st87", M41T80_FEATURE_HT | M41T80_FEATURE_BL | M41T80_FEATURE_SQ }, - { "rv4162", M41T80_FEATURE_SQ | M41T80_FEATURE_WD | M41T80_FEATURE_SQ_ALT }, + { .name = "m41t62", .driver_data = M41T80_FEATURE_SQ | M41T80_FEATURE_SQ_ALT }, + { .name = "m41t65", .driver_data = M41T80_FEATURE_WD }, + { .name = "m41t80", .driver_data = M41T80_FEATURE_SQ }, + { .name = "m41t81", .driver_data = M41T80_FEATURE_HT | M41T80_FEATURE_SQ}, + { .name = "m41t81s", .driver_data = M41T80_FEATURE_HT | M41T80_FEATURE_BL | M41T80_FEATURE_SQ }, + { .name = "m41t82", .driver_data = M41T80_FEATURE_HT | M41T80_FEATURE_BL | M41T80_FEATURE_SQ }, + { .name = "m41t83", .driver_data = M41T80_FEATURE_HT | M41T80_FEATURE_BL | M41T80_FEATURE_SQ }, + { .name = "m41st84", .driver_data = M41T80_FEATURE_HT | M41T80_FEATURE_BL | M41T80_FEATURE_SQ }, + { .name = "m41st85", .driver_data = M41T80_FEATURE_HT | M41T80_FEATURE_BL | M41T80_FEATURE_SQ }, + { .name = "m41st87", .driver_data = M41T80_FEATURE_HT | M41T80_FEATURE_BL | M41T80_FEATURE_SQ }, + { .name = "rv4162", .driver_data = M41T80_FEATURE_SQ | M41T80_FEATURE_WD | M41T80_FEATURE_SQ_ALT }, { } }; MODULE_DEVICE_TABLE(i2c, m41t80_id); diff --git a/drivers/rtc/rtc-max31335.c b/drivers/rtc/rtc-max31335.c index 952b455071d6..595816973851 100644 --- a/drivers/rtc/rtc-max31335.c +++ b/drivers/rtc/rtc-max31335.c @@ -745,8 +745,8 @@ static int max31335_probe(struct i2c_client *client) } static const struct i2c_device_id max31335_id[] = { - { "max31331", (kernel_ulong_t)&chip[ID_MAX31331] }, - { "max31335", (kernel_ulong_t)&chip[ID_MAX31335] }, + { .name = "max31331", .driver_data = (kernel_ulong_t)&chip[ID_MAX31331] }, + { .name = "max31335", .driver_data = (kernel_ulong_t)&chip[ID_MAX31335] }, { } }; diff --git a/drivers/rtc/rtc-max6900.c b/drivers/rtc/rtc-max6900.c index 7be31fce5bc7..8ef6d0fcd032 100644 --- a/drivers/rtc/rtc-max6900.c +++ b/drivers/rtc/rtc-max6900.c @@ -215,7 +215,7 @@ static int max6900_probe(struct i2c_client *client) } static const struct i2c_device_id max6900_id[] = { - { "max6900" }, + { .name = "max6900" }, { } }; MODULE_DEVICE_TABLE(i2c, max6900_id); diff --git a/drivers/rtc/rtc-nct3018y.c b/drivers/rtc/rtc-nct3018y.c index cd4b1db902e9..700a395fad3a 100644 --- a/drivers/rtc/rtc-nct3018y.c +++ b/drivers/rtc/rtc-nct3018y.c @@ -572,7 +572,7 @@ static int nct3018y_probe(struct i2c_client *client) } static const struct i2c_device_id nct3018y_id[] = { - { "nct3018y" }, + { .name = "nct3018y" }, { } }; MODULE_DEVICE_TABLE(i2c, nct3018y_id); diff --git a/drivers/rtc/rtc-pcf2127.c b/drivers/rtc/rtc-pcf2127.c index e4785c5a55d0..1995e9f2756d 100644 --- a/drivers/rtc/rtc-pcf2127.c +++ b/drivers/rtc/rtc-pcf2127.c @@ -1449,10 +1449,10 @@ static const struct regmap_bus pcf2127_i2c_regmap = { static struct i2c_driver pcf2127_i2c_driver; static const struct i2c_device_id pcf2127_i2c_id[] = { - { "pcf2127", (kernel_ulong_t)&pcf21xx_cfg[PCF2127] }, - { "pcf2129", (kernel_ulong_t)&pcf21xx_cfg[PCF2129] }, - { "pca2129", (kernel_ulong_t)&pcf21xx_cfg[PCF2129] }, - { "pcf2131", (kernel_ulong_t)&pcf21xx_cfg[PCF2131] }, + { .name = "pcf2127", .driver_data = (kernel_ulong_t)&pcf21xx_cfg[PCF2127] }, + { .name = "pcf2129", .driver_data = (kernel_ulong_t)&pcf21xx_cfg[PCF2129] }, + { .name = "pca2129", .driver_data = (kernel_ulong_t)&pcf21xx_cfg[PCF2129] }, + { .name = "pcf2131", .driver_data = (kernel_ulong_t)&pcf21xx_cfg[PCF2131] }, { } }; MODULE_DEVICE_TABLE(i2c, pcf2127_i2c_id); diff --git a/drivers/rtc/rtc-pcf85063.c b/drivers/rtc/rtc-pcf85063.c index f643e0bd7351..01e209d88f5f 100644 --- a/drivers/rtc/rtc-pcf85063.c +++ b/drivers/rtc/rtc-pcf85063.c @@ -665,12 +665,12 @@ static const struct pcf85063_config config_rv8263 = { }; static const struct i2c_device_id pcf85063_ids[] = { - { "pca85073a", .driver_data = (kernel_ulong_t)&config_pcf85063a }, - { "pcf85063", .driver_data = (kernel_ulong_t)&config_pcf85063 }, - { "pcf85063tp", .driver_data = (kernel_ulong_t)&config_pcf85063tp }, - { "pcf85063a", .driver_data = (kernel_ulong_t)&config_pcf85063a }, - { "rv8263", .driver_data = (kernel_ulong_t)&config_rv8263 }, - {} + { .name = "pca85073a", .driver_data = (kernel_ulong_t)&config_pcf85063a }, + { .name = "pcf85063", .driver_data = (kernel_ulong_t)&config_pcf85063 }, + { .name = "pcf85063tp", .driver_data = (kernel_ulong_t)&config_pcf85063tp }, + { .name = "pcf85063a", .driver_data = (kernel_ulong_t)&config_pcf85063a }, + { .name = "rv8263", .driver_data = (kernel_ulong_t)&config_rv8263 }, + { } }; MODULE_DEVICE_TABLE(i2c, pcf85063_ids); diff --git a/drivers/rtc/rtc-pcf8523.c b/drivers/rtc/rtc-pcf8523.c index 2c63c0ffd05a..e8354953836c 100644 --- a/drivers/rtc/rtc-pcf8523.c +++ b/drivers/rtc/rtc-pcf8523.c @@ -495,7 +495,7 @@ static int pcf8523_probe(struct i2c_client *client) } static const struct i2c_device_id pcf8523_id[] = { - { "pcf8523" }, + { .name = "pcf8523" }, { } }; MODULE_DEVICE_TABLE(i2c, pcf8523_id); diff --git a/drivers/rtc/rtc-pcf8563.c b/drivers/rtc/rtc-pcf8563.c index b281e9489df1..81d13733b1e9 100644 --- a/drivers/rtc/rtc-pcf8563.c +++ b/drivers/rtc/rtc-pcf8563.c @@ -557,9 +557,9 @@ static int pcf8563_probe(struct i2c_client *client) } static const struct i2c_device_id pcf8563_id[] = { - { "pcf8563" }, - { "rtc8564" }, - { "pca8565" }, + { .name = "pcf8563" }, + { .name = "rtc8564" }, + { .name = "pca8565" }, { } }; MODULE_DEVICE_TABLE(i2c, pcf8563_id); diff --git a/drivers/rtc/rtc-pcf8583.c b/drivers/rtc/rtc-pcf8583.c index 652b9dfa7566..df5e20cbc26c 100644 --- a/drivers/rtc/rtc-pcf8583.c +++ b/drivers/rtc/rtc-pcf8583.c @@ -297,7 +297,7 @@ static int pcf8583_probe(struct i2c_client *client) } static const struct i2c_device_id pcf8583_id[] = { - { "pcf8583" }, + { .name = "pcf8583" }, { } }; MODULE_DEVICE_TABLE(i2c, pcf8583_id); diff --git a/drivers/rtc/rtc-rs5c372.c b/drivers/rtc/rtc-rs5c372.c index 936f4f05c8c7..24bd795d9d95 100644 --- a/drivers/rtc/rtc-rs5c372.c +++ b/drivers/rtc/rtc-rs5c372.c @@ -75,12 +75,12 @@ enum rtc_type { }; static const struct i2c_device_id rs5c372_id[] = { - { "r2025sd", rtc_r2025sd }, - { "r2221tl", rtc_r2221tl }, - { "rs5c372a", rtc_rs5c372a }, - { "rs5c372b", rtc_rs5c372b }, - { "rv5c386", rtc_rv5c386 }, - { "rv5c387a", rtc_rv5c387a }, + { .name = "r2025sd", .driver_data = rtc_r2025sd }, + { .name = "r2221tl", .driver_data = rtc_r2221tl }, + { .name = "rs5c372a", .driver_data = rtc_rs5c372a }, + { .name = "rs5c372b", .driver_data = rtc_rs5c372b }, + { .name = "rv5c386", .driver_data = rtc_rv5c386 }, + { .name = "rv5c387a", .driver_data = rtc_rv5c387a }, { } }; MODULE_DEVICE_TABLE(i2c, rs5c372_id); diff --git a/drivers/rtc/rtc-rv3029c2.c b/drivers/rtc/rtc-rv3029c2.c index 83331d1fcab0..98953af2a24a 100644 --- a/drivers/rtc/rtc-rv3029c2.c +++ b/drivers/rtc/rtc-rv3029c2.c @@ -807,8 +807,8 @@ static int rv3029_i2c_probe(struct i2c_client *client) } static const struct i2c_device_id rv3029_id[] = { - { "rv3029" }, - { "rv3029c2" }, + { .name = "rv3029" }, + { .name = "rv3029c2" }, { } }; MODULE_DEVICE_TABLE(i2c, rv3029_id); diff --git a/drivers/rtc/rtc-rv8803.c b/drivers/rtc/rtc-rv8803.c index 2bf988a89fd7..b9b5fee16ee4 100644 --- a/drivers/rtc/rtc-rv8803.c +++ b/drivers/rtc/rtc-rv8803.c @@ -631,10 +631,10 @@ static int rv8803_suspend(struct device *dev) static DEFINE_SIMPLE_DEV_PM_OPS(rv8803_pm_ops, rv8803_suspend, rv8803_resume); static const struct i2c_device_id rv8803_id[] = { - { "rv8803", rv_8803 }, - { "rv8804", rx_8804 }, - { "rx8803", rx_8803 }, - { "rx8900", rx_8900 }, + { .name = "rv8803", .driver_data = rv_8803 }, + { .name = "rv8804", .driver_data = rx_8804 }, + { .name = "rx8803", .driver_data = rx_8803 }, + { .name = "rx8900", .driver_data = rx_8900 }, { } }; MODULE_DEVICE_TABLE(i2c, rv8803_id); diff --git a/drivers/rtc/rtc-rx6110.c b/drivers/rtc/rtc-rx6110.c index 07bf35ac8d79..1eacd470a27c 100644 --- a/drivers/rtc/rtc-rx6110.c +++ b/drivers/rtc/rtc-rx6110.c @@ -449,7 +449,7 @@ static const struct acpi_device_id rx6110_i2c_acpi_match[] = { MODULE_DEVICE_TABLE(acpi, rx6110_i2c_acpi_match); static const struct i2c_device_id rx6110_i2c_id[] = { - { "rx6110" }, + { .name = "rx6110" }, { } }; MODULE_DEVICE_TABLE(i2c, rx6110_i2c_id); diff --git a/drivers/rtc/rtc-rx8010.c b/drivers/rtc/rtc-rx8010.c index 171240e50f48..ce3954132336 100644 --- a/drivers/rtc/rtc-rx8010.c +++ b/drivers/rtc/rtc-rx8010.c @@ -50,7 +50,7 @@ #define RX8010_ALARM_AE BIT(7) static const struct i2c_device_id rx8010_id[] = { - { "rx8010" }, + { .name = "rx8010" }, { } }; MODULE_DEVICE_TABLE(i2c, rx8010_id); diff --git a/drivers/rtc/rtc-rx8025.c b/drivers/rtc/rtc-rx8025.c index c57081f9e02b..5eeaa929f3ef 100644 --- a/drivers/rtc/rtc-rx8025.c +++ b/drivers/rtc/rtc-rx8025.c @@ -71,8 +71,8 @@ enum rx_model { }; static const struct i2c_device_id rx8025_id[] = { - { "rx8025", model_rx_8025 }, - { "rx8035", model_rx_8035 }, + { .name = "rx8025", .driver_data = model_rx_8025 }, + { .name = "rx8035", .driver_data = model_rx_8035 }, { } }; MODULE_DEVICE_TABLE(i2c, rx8025_id); diff --git a/drivers/rtc/rtc-rx8581.c b/drivers/rtc/rtc-rx8581.c index 20c2dff01bae..cf4dab94c337 100644 --- a/drivers/rtc/rtc-rx8581.c +++ b/drivers/rtc/rtc-rx8581.c @@ -294,7 +294,7 @@ static int rx8581_probe(struct i2c_client *client) } static const struct i2c_device_id rx8581_id[] = { - { "rx8581" }, + { .name = "rx8581" }, { } }; MODULE_DEVICE_TABLE(i2c, rx8581_id); diff --git a/drivers/rtc/rtc-s35390a.c b/drivers/rtc/rtc-s35390a.c index a4678d7c6cf6..31394f34fb70 100644 --- a/drivers/rtc/rtc-s35390a.c +++ b/drivers/rtc/rtc-s35390a.c @@ -51,7 +51,7 @@ #define S35390A_INT2_MODE_PMIN (BIT(3) | BIT(2)) /* INT2FE | INT2ME */ static const struct i2c_device_id s35390a_id[] = { - { "s35390a" }, + { .name = "s35390a" }, { } }; MODULE_DEVICE_TABLE(i2c, s35390a_id); diff --git a/drivers/rtc/rtc-sd2405al.c b/drivers/rtc/rtc-sd2405al.c index 708ea5d964de..7982a910a537 100644 --- a/drivers/rtc/rtc-sd2405al.c +++ b/drivers/rtc/rtc-sd2405al.c @@ -202,7 +202,7 @@ static int sd2405al_probe(struct i2c_client *client) } static const struct i2c_device_id sd2405al_id[] = { - { "sd2405al" }, + { .name = "sd2405al" }, { /* sentinel */ } }; MODULE_DEVICE_TABLE(i2c, sd2405al_id); diff --git a/drivers/rtc/rtc-sd3078.c b/drivers/rtc/rtc-sd3078.c index 10cc1dcfc774..2c61f0e204a4 100644 --- a/drivers/rtc/rtc-sd3078.c +++ b/drivers/rtc/rtc-sd3078.c @@ -186,7 +186,7 @@ static int sd3078_probe(struct i2c_client *client) } static const struct i2c_device_id sd3078_id[] = { - { "sd3078" }, + { .name = "sd3078" }, { } }; MODULE_DEVICE_TABLE(i2c, sd3078_id); diff --git a/drivers/rtc/rtc-x1205.c b/drivers/rtc/rtc-x1205.c index b8a0fccef14e..bb1a5c86f621 100644 --- a/drivers/rtc/rtc-x1205.c +++ b/drivers/rtc/rtc-x1205.c @@ -663,7 +663,7 @@ static void x1205_remove(struct i2c_client *client) } static const struct i2c_device_id x1205_id[] = { - { "x1205" }, + { .name = "x1205" }, { } }; MODULE_DEVICE_TABLE(i2c, x1205_id); From ba5dca876b54c848fe4ba6526454a6eed7856f57 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig=20=28The=20Capable=20Hub=29?= Date: Thu, 28 May 2026 08:48:10 +0200 Subject: [PATCH 120/297] rtc: Drop unused assignment of platform_device_id driver data MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The two drivers explicitly set the .driver_data member of struct platform_device_id to zero without relying on that value. Drop this unused assignments. While touching these array unify spacing, usage of commas and use named initializers for .name. Signed-off-by: Uwe Kleine-König (The Capable Hub) Reviewed-by: Tzung-Bi Shih Link: https://patch.msgid.link/9ec7a174605a17dd19c011ee2253de28d09b02bd.1779950275.git.u.kleine-koenig@baylibre.com Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-cros-ec.c | 4 ++-- drivers/rtc/rtc-max8997.c | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/rtc/rtc-cros-ec.c b/drivers/rtc/rtc-cros-ec.c index e956505a06fb..f3ecd017e2f7 100644 --- a/drivers/rtc/rtc-cros-ec.c +++ b/drivers/rtc/rtc-cros-ec.c @@ -388,8 +388,8 @@ static void cros_ec_rtc_remove(struct platform_device *pdev) } static const struct platform_device_id cros_ec_rtc_id[] = { - { DRV_NAME, 0 }, - {} + { .name = DRV_NAME }, + { } }; MODULE_DEVICE_TABLE(platform, cros_ec_rtc_id); diff --git a/drivers/rtc/rtc-max8997.c b/drivers/rtc/rtc-max8997.c index e7618d715bd8..89203c92e2cd 100644 --- a/drivers/rtc/rtc-max8997.c +++ b/drivers/rtc/rtc-max8997.c @@ -512,8 +512,8 @@ static void max8997_rtc_shutdown(struct platform_device *pdev) } static const struct platform_device_id rtc_id[] = { - { "max8997-rtc", 0 }, - {}, + { .name = "max8997-rtc" }, + { } }; MODULE_DEVICE_TABLE(platform, rtc_id); From 6e2f1f0184dad775c95c09e5374234d3df39de65 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig=20=28The=20Capable=20Hub=29?= Date: Thu, 28 May 2026 08:48:11 +0200 Subject: [PATCH 121/297] rtc: ab8500: Simplify driver_data handling MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Instead of hiding the rtc ops for the only supported device behind an abstraction for multi-device support, hardcode the used ops which gets rid of the need to call platform_get_device_id and two casts. Signed-off-by: Uwe Kleine-König (The Capable Hub) Reviewed-by: Linus Walleij Link: https://patch.msgid.link/a909d3c59d00756130ac16051ceedbec0ce9cec7.1779950275.git.u.kleine-koenig@baylibre.com Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-ab8500.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/rtc/rtc-ab8500.c b/drivers/rtc/rtc-ab8500.c index c6147837f957..0978bd0a3393 100644 --- a/drivers/rtc/rtc-ab8500.c +++ b/drivers/rtc/rtc-ab8500.c @@ -323,14 +323,13 @@ static const struct rtc_class_ops ab8500_rtc_ops = { }; static const struct platform_device_id ab85xx_rtc_ids[] = { - { "ab8500-rtc", (kernel_ulong_t)&ab8500_rtc_ops, }, + { .name = "ab8500-rtc" }, { /* sentinel */ } }; MODULE_DEVICE_TABLE(platform, ab85xx_rtc_ids); static int ab8500_rtc_probe(struct platform_device *pdev) { - const struct platform_device_id *platid = platform_get_device_id(pdev); int err; struct rtc_device *rtc; u8 rtc_ctrl; @@ -366,7 +365,7 @@ static int ab8500_rtc_probe(struct platform_device *pdev) if (IS_ERR(rtc)) return PTR_ERR(rtc); - rtc->ops = (struct rtc_class_ops *)platid->driver_data; + rtc->ops = &ab8500_rtc_ops; err = devm_request_threaded_irq(&pdev->dev, irq, NULL, rtc_alarm_handler, IRQF_ONESHOT, From 041ca8884410a4f70b40521f34258c7b773ea5c2 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig=20=28The=20Capable=20Hub=29?= Date: Thu, 28 May 2026 08:48:12 +0200 Subject: [PATCH 122/297] rtc: Use named initializers for platform_device_id arrays MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Named initializers are better readable and more robust to changes of the struct definition. This robustness is relevant for a planned change to struct platform_device_id replacing .driver_data by an anonymous union. While touching these arrays unify spacing and usage of commas. Signed-off-by: Uwe Kleine-König (The Capable Hub) Reviewed-by: Matti Vaittinen Reviewed-by: Linus Walleij Acked-by: Karel Balej # for Marvell 88PM886 Link: https://patch.msgid.link/d14b9076b2c7703708bcc5cc35f339cd97fc10cd.1779950275.git.u.kleine-koenig@baylibre.com Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-88pm886.c | 2 +- drivers/rtc/rtc-bd70528.c | 8 ++++---- drivers/rtc/rtc-max77686.c | 10 +++++----- drivers/rtc/rtc-max8998.c | 4 ++-- drivers/rtc/rtc-s5m.c | 12 ++++++------ drivers/rtc/rtc-tps6594.c | 4 ++-- 6 files changed, 20 insertions(+), 20 deletions(-) diff --git a/drivers/rtc/rtc-88pm886.c b/drivers/rtc/rtc-88pm886.c index 57e9b0a66eed..13aa3ae82239 100644 --- a/drivers/rtc/rtc-88pm886.c +++ b/drivers/rtc/rtc-88pm886.c @@ -78,7 +78,7 @@ static int pm886_rtc_probe(struct platform_device *pdev) } static const struct platform_device_id pm886_rtc_id_table[] = { - { "88pm886-rtc", }, + { .name = "88pm886-rtc" }, { } }; MODULE_DEVICE_TABLE(platform, pm886_rtc_id_table); diff --git a/drivers/rtc/rtc-bd70528.c b/drivers/rtc/rtc-bd70528.c index 4c8599761b2e..482810b61495 100644 --- a/drivers/rtc/rtc-bd70528.c +++ b/drivers/rtc/rtc-bd70528.c @@ -341,10 +341,10 @@ static int bd70528_probe(struct platform_device *pdev) } static const struct platform_device_id bd718x7_rtc_id[] = { - { "bd71828-rtc", ROHM_CHIP_TYPE_BD71828 }, - { "bd71815-rtc", ROHM_CHIP_TYPE_BD71815 }, - { "bd72720-rtc", ROHM_CHIP_TYPE_BD72720 }, - { }, + { .name = "bd71828-rtc", .driver_data = ROHM_CHIP_TYPE_BD71828 }, + { .name = "bd71815-rtc", .driver_data = ROHM_CHIP_TYPE_BD71815 }, + { .name = "bd72720-rtc", .driver_data = ROHM_CHIP_TYPE_BD72720 }, + { } }; MODULE_DEVICE_TABLE(platform, bd718x7_rtc_id); diff --git a/drivers/rtc/rtc-max77686.c b/drivers/rtc/rtc-max77686.c index 3cdfd78a07cc..375565a3bddf 100644 --- a/drivers/rtc/rtc-max77686.c +++ b/drivers/rtc/rtc-max77686.c @@ -866,11 +866,11 @@ static SIMPLE_DEV_PM_OPS(max77686_rtc_pm_ops, max77686_rtc_suspend, max77686_rtc_resume); static const struct platform_device_id rtc_id[] = { - { "max77686-rtc", .driver_data = (kernel_ulong_t)&max77686_drv_data, }, - { "max77802-rtc", .driver_data = (kernel_ulong_t)&max77802_drv_data, }, - { "max77620-rtc", .driver_data = (kernel_ulong_t)&max77620_drv_data, }, - { "max77714-rtc", .driver_data = (kernel_ulong_t)&max77714_drv_data, }, - {}, + { .name = "max77686-rtc", .driver_data = (kernel_ulong_t)&max77686_drv_data }, + { .name = "max77802-rtc", .driver_data = (kernel_ulong_t)&max77802_drv_data }, + { .name = "max77620-rtc", .driver_data = (kernel_ulong_t)&max77620_drv_data }, + { .name = "max77714-rtc", .driver_data = (kernel_ulong_t)&max77714_drv_data }, + { } }; MODULE_DEVICE_TABLE(platform, rtc_id); diff --git a/drivers/rtc/rtc-max8998.c b/drivers/rtc/rtc-max8998.c index c873b4509b3c..a2c946edcd1a 100644 --- a/drivers/rtc/rtc-max8998.c +++ b/drivers/rtc/rtc-max8998.c @@ -299,8 +299,8 @@ no_irq: } static const struct platform_device_id max8998_rtc_id[] = { - { "max8998-rtc", TYPE_MAX8998 }, - { "lp3974-rtc", TYPE_LP3974 }, + { .name = "max8998-rtc", .driver_data = TYPE_MAX8998 }, + { .name = "lp3974-rtc", .driver_data = TYPE_LP3974 }, { } }; MODULE_DEVICE_TABLE(platform, max8998_rtc_id); diff --git a/drivers/rtc/rtc-s5m.c b/drivers/rtc/rtc-s5m.c index c6ed5a4ca8a0..aa706074ec3e 100644 --- a/drivers/rtc/rtc-s5m.c +++ b/drivers/rtc/rtc-s5m.c @@ -807,12 +807,12 @@ static int s5m_rtc_suspend(struct device *dev) static SIMPLE_DEV_PM_OPS(s5m_rtc_pm_ops, s5m_rtc_suspend, s5m_rtc_resume); static const struct platform_device_id s5m_rtc_id[] = { - { "s5m-rtc", S5M8767X }, - { "s2mpg10-rtc", S2MPG10 }, - { "s2mps13-rtc", S2MPS13X }, - { "s2mps14-rtc", S2MPS14X }, - { "s2mps15-rtc", S2MPS15X }, - { }, + { .name = "s5m-rtc", .driver_data = S5M8767X }, + { .name = "s2mpg10-rtc", .driver_data = S2MPG10 }, + { .name = "s2mps13-rtc", .driver_data = S2MPS13X }, + { .name = "s2mps14-rtc", .driver_data = S2MPS14X }, + { .name = "s2mps15-rtc", .driver_data = S2MPS15X }, + { } }; MODULE_DEVICE_TABLE(platform, s5m_rtc_id); diff --git a/drivers/rtc/rtc-tps6594.c b/drivers/rtc/rtc-tps6594.c index 7c6246e3f029..2cebd54c2dbf 100644 --- a/drivers/rtc/rtc-tps6594.c +++ b/drivers/rtc/rtc-tps6594.c @@ -485,8 +485,8 @@ static int tps6594_rtc_suspend(struct device *dev) static DEFINE_SIMPLE_DEV_PM_OPS(tps6594_rtc_pm_ops, tps6594_rtc_suspend, tps6594_rtc_resume); static const struct platform_device_id tps6594_rtc_id_table[] = { - { "tps6594-rtc", }, - {} + { .name = "tps6594-rtc" }, + { } }; MODULE_DEVICE_TABLE(platform, tps6594_rtc_id_table); From faaa1e1155833e7d4ce7e3cfaf64c0d636b190db Mon Sep 17 00:00:00 2001 From: Xiang Mei Date: Mon, 15 Jun 2026 11:47:37 -0700 Subject: [PATCH 123/297] drm/edid: fix OOB read in drm_parse_tiled_block() drm_parse_tiled_block() casts the DisplayID block to a struct displayid_tiled_block and reads the full fixed layout up to tile->topology_id[7] without checking block->num_bytes. The DisplayID iterator only validates the declared payload length, so a crafted EDID can advertise a tiled-display block (tag DATA_BLOCK_TILED_DISPLAY, or DATA_BLOCK_2_TILED_DISPLAY_TOPOLOGY for v2.0) with a small num_bytes at the end of a DisplayID extension. The read then runs past the end of the exact-sized kmemdup()'d EDID allocation, a heap out-of-bounds read. Reject blocks shorter than the spec's 22-byte tiled payload before reading the fixed struct, as drm_parse_vesa_mso_data() already does. BUG: KASAN: slab-out-of-bounds in drm_edid_connector_update Read of size 2 at addr ffff888010077700 by task exploit/147 dump_stack_lvl (lib/dump_stack.c:94 ...) print_report (mm/kasan/report.c:378 ...) kasan_report (mm/kasan/report.c:595) drm_edid_connector_update (drivers/gpu/drm/drm_edid.c:7581) bochs_connector_helper_get_modes (drivers/gpu/drm/tiny/bochs.c:574) drm_helper_probe_single_connector_modes (drivers/gpu/drm/drm_probe_helper.c:426) status_store (drivers/gpu/drm/drm_sysfs.c:219) ... vfs_write (fs/read_write.c:595 fs/read_write.c:688) ksys_write (fs/read_write.c:740) Fixes: 40d9b043a89e ("drm/connector: store tile information from displayid (v3)") Reported-by: Weiming Shi Assisted-by: Claude:claude-opus-4-8 Signed-off-by: Xiang Mei Reviewed-by: Jani Nikula Link: https://patch.msgid.link/20260615184737.899892-1-xmei5@asu.edu Signed-off-by: Jani Nikula --- drivers/gpu/drm/drm_edid.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c index 404208bf23a6..df3c25bac761 100644 --- a/drivers/gpu/drm/drm_edid.c +++ b/drivers/gpu/drm/drm_edid.c @@ -7575,6 +7575,14 @@ static void drm_parse_tiled_block(struct drm_connector *connector, u8 num_v_tile, num_h_tile; struct drm_tile_group *tg; + /* tiled block payload per spec: cap 1 + topo 3 + size 4 + bezel 5 + id 9 = 22 */ + if (block->num_bytes < 22) { + drm_dbg_kms(connector->dev, + "[CONNECTOR:%d:%s] Unexpected tiled block size %u\n", + connector->base.id, connector->name, block->num_bytes); + return; + } + w = tile->tile_size[0] | tile->tile_size[1] << 8; h = tile->tile_size[2] | tile->tile_size[3] << 8; From b70f007a9fc665ee988683fd5085ab34e2c10ad3 Mon Sep 17 00:00:00 2001 From: Chris Aherin Date: Sun, 21 Jun 2026 19:12:10 -0500 Subject: [PATCH 124/297] ALSA: hda/realtek: Add quirk for Lenovo Yoga 7 16IAP7 The Yoga 7 16IAP7 (board LNVNB161216, codec SSID 17aa:386a) has pin complex 0x17 (bass speakers) wrongly reported as unconnected, causing only one of four speaker pins (0x14) to be configured and resulting in mono/tinny audio. SOF corrupts the PCI subsystem ID to 17aa:0000, preventing SND_PCI_QUIRK from matching. HDA_CODEC_QUIRK is used instead, which matches against codec->core.subsystem_id read directly from the HDA codec register and unaffected by the SOF bug. Applies ALC287_FIXUP_YOGA9_14IAP7_BASS_SPK_PIN, the same fixup used for the Yoga 7 14IAL7, which corrects pin 0x17's default configuration and enables both speaker pairs. Signed-off-by: Chris Aherin Link: https://patch.msgid.link/20260622001210.20553-1-chrisaherin@gmail.com Signed-off-by: Takashi Iwai --- sound/hda/codecs/realtek/alc269.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/hda/codecs/realtek/alc269.c b/sound/hda/codecs/realtek/alc269.c index 2df491335a76..c83c1654ed45 100644 --- a/sound/hda/codecs/realtek/alc269.c +++ b/sound/hda/codecs/realtek/alc269.c @@ -7755,6 +7755,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x3865, "Lenovo 13X", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x17aa, 0x3866, "Lenovo 13X", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x17aa, 0x3869, "Lenovo Yoga7 14IAL7", ALC287_FIXUP_YOGA9_14IAP7_BASS_SPK_PIN), + HDA_CODEC_QUIRK(0x17aa, 0x386a, "Lenovo Yoga 7 16IAP7", ALC287_FIXUP_YOGA9_14IAP7_BASS_SPK_PIN), HDA_CODEC_QUIRK(0x17aa, 0x386e, "Legion Y9000X 2022 IAH7", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x17aa, 0x386e, "Yoga Pro 7 14ARP8", ALC285_FIXUP_SPEAKER2_TO_DAC1), HDA_CODEC_QUIRK(0x17aa, 0x38a8, "Legion Pro 7 16ARX8H", ALC287_FIXUP_TAS2781_I2C), /* this must match before PCI SSID 17aa:386f below */ From 6efb1897209ab50940c58384d15a68fd4212821c Mon Sep 17 00:00:00 2001 From: Dirk Su Date: Mon, 22 Jun 2026 15:20:04 +0800 Subject: [PATCH 125/297] ALSA: hda/realtek: Add LED fixup for HP EliteBook 6 G2i Laptops The HP EliteBook 6 G2i laptops requires specific LED control method ALC236_FIXUP_HP_GPIO_LED to work Signed-off-by: Dirk Su Link: https://patch.msgid.link/20260622072019.56351-1-dirk.su@canonical.com Signed-off-by: Takashi Iwai --- sound/hda/codecs/realtek/alc269.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/sound/hda/codecs/realtek/alc269.c b/sound/hda/codecs/realtek/alc269.c index c83c1654ed45..e88ca720f4e5 100644 --- a/sound/hda/codecs/realtek/alc269.c +++ b/sound/hda/codecs/realtek/alc269.c @@ -7328,6 +7328,10 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8f0e, "HP ZBook X G2i 16W", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8f2d, "HP Auster 14", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x103c, 0x8f2e, "HP Auster 14", ALC287_FIXUP_CS35L41_I2C_2), + SND_PCI_QUIRK(0x103c, 0x8f37, "HP EliteBook 6 G2i", ALC236_FIXUP_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8f38, "HP EliteBook 6 G2i", ALC236_FIXUP_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8f39, "HP EliteBook 6 G2i", ALC236_FIXUP_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8f3a, "HP EliteBook 6 G2i", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8f3c, "HP EliteBook 6 G2a", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), SND_PCI_QUIRK(0x103c, 0x8f3d, "HP EliteBook 6 G2a", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), SND_PCI_QUIRK(0x103c, 0x8f40, "HP ZBook 8 G2a 14", ALC245_FIXUP_HP_TAS2781_I2C_MUTE_LED), From 134844856c399bfa9462a159dcf860bfdb748055 Mon Sep 17 00:00:00 2001 From: Thomas Zimmermann Date: Thu, 18 Jun 2026 10:41:57 +0200 Subject: [PATCH 126/297] drm/sysfb: Do not page-align visible size of the framebuffer Only return the actually visible size of the system framebuffer in drm_sysfb_get_visible_size_si(). Drivers use this size value for reserving access to framebuffer memory. Increasing the value can make later attempts to do so fail. Signed-off-by: Thomas Zimmermann Fixes: 32ae90c66fb6 ("drm/sysfb: Add efidrm for EFI displays") Fixes: a84eb6abe2b6 ("drm/sysfb: Add vesadrm for VESA displays") Reviewed-by: Javier Martinez Canillas Cc: Thomas Zimmermann Cc: Javier Martinez Canillas Cc: dri-devel@lists.freedesktop.org Cc: # v6.16+ Link: https://patch.msgid.link/20260618084327.46567-2-tzimmermann@suse.de --- drivers/gpu/drm/sysfb/drm_sysfb_screen_info.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/sysfb/drm_sysfb_screen_info.c b/drivers/gpu/drm/sysfb/drm_sysfb_screen_info.c index 749290196c6a..361b7233600c 100644 --- a/drivers/gpu/drm/sysfb/drm_sysfb_screen_info.c +++ b/drivers/gpu/drm/sysfb/drm_sysfb_screen_info.c @@ -67,7 +67,7 @@ EXPORT_SYMBOL(drm_sysfb_get_stride_si); u64 drm_sysfb_get_visible_size_si(struct drm_device *dev, const struct screen_info *si, unsigned int height, unsigned int stride, u64 size) { - u64 vsize = PAGE_ALIGN(height * stride); + u64 vsize = height * stride; return drm_sysfb_get_validated_size0(dev, "visible size", vsize, size); } From b771974988ec7ce077a7246fa0fa588c246fe581 Mon Sep 17 00:00:00 2001 From: Thomas Zimmermann Date: Thu, 18 Jun 2026 10:41:58 +0200 Subject: [PATCH 127/297] drm/sysfb: Avoid possible truncation with calculating visible size Calculating the visible size of the system framebuffer can result in truncation of the result. The calculation uses 32-bit arithmetics, which can overflow if the values for height and stride are large. Fix the issue by multiplying with mul_u32_u32(). Signed-off-by: Thomas Zimmermann Fixes: 32ae90c66fb6 ("drm/sysfb: Add efidrm for EFI displays") Fixes: a84eb6abe2b6 ("drm/sysfb: Add vesadrm for VESA displays") Reported-by: Sashiko Closes: https://lore.kernel.org/dri-devel/20260617114027.1F2A71F000E9@smtp.kernel.org/ Cc: Thomas Zimmermann Cc: Javier Martinez Canillas Cc: dri-devel@lists.freedesktop.org Cc: # v6.16+ Reviewed-by: Javier Martinez Canillas Link: https://patch.msgid.link/20260618084327.46567-3-tzimmermann@suse.de --- drivers/gpu/drm/sysfb/drm_sysfb_screen_info.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/sysfb/drm_sysfb_screen_info.c b/drivers/gpu/drm/sysfb/drm_sysfb_screen_info.c index 361b7233600c..8b14eaa304c0 100644 --- a/drivers/gpu/drm/sysfb/drm_sysfb_screen_info.c +++ b/drivers/gpu/drm/sysfb/drm_sysfb_screen_info.c @@ -2,6 +2,7 @@ #include #include +#include #include #include @@ -67,7 +68,7 @@ EXPORT_SYMBOL(drm_sysfb_get_stride_si); u64 drm_sysfb_get_visible_size_si(struct drm_device *dev, const struct screen_info *si, unsigned int height, unsigned int stride, u64 size) { - u64 vsize = height * stride; + u64 vsize = mul_u32_u32(height, stride); return drm_sysfb_get_validated_size0(dev, "visible size", vsize, size); } From 7bab0f09d753f098977bbba3955d694c2e2c25da Mon Sep 17 00:00:00 2001 From: Thomas Zimmermann Date: Thu, 18 Jun 2026 10:41:59 +0200 Subject: [PATCH 128/297] drm/sysfb: Return errno code from drm_sysfb_get_visible_size() Change the return type of drm_sysfb_get_visible_size() to s64 so that it returns a possible errno code from _get_validated_size0(). Fix callers to handle the errno code. The currently returned unsigned type converts an errno code to a very large size value, which drivers interpret as visible size of the system framebuffer. Later efforts to reserve the framebuffer resource fail. The bug has been present since efidrm and vesadrm got merged. It was then part of each driver. Signed-off-by: Thomas Zimmermann Fixes: 32ae90c66fb6 ("drm/sysfb: Add efidrm for EFI displays") Fixes: a84eb6abe2b6 ("drm/sysfb: Add vesadrm for VESA displays") Reviewed-by: Javier Martinez Canillas Cc: Thomas Zimmermann Cc: Javier Martinez Canillas Cc: dri-devel@lists.freedesktop.org Cc: # v6.16+ Link: https://patch.msgid.link/20260618084327.46567-4-tzimmermann@suse.de --- drivers/gpu/drm/sysfb/drm_sysfb_helper.h | 2 +- drivers/gpu/drm/sysfb/drm_sysfb_screen_info.c | 2 +- drivers/gpu/drm/sysfb/efidrm.c | 7 ++++--- drivers/gpu/drm/sysfb/vesadrm.c | 6 +++--- 4 files changed, 9 insertions(+), 8 deletions(-) diff --git a/drivers/gpu/drm/sysfb/drm_sysfb_helper.h b/drivers/gpu/drm/sysfb/drm_sysfb_helper.h index b14df5b54bc9..d48b92a903f7 100644 --- a/drivers/gpu/drm/sysfb/drm_sysfb_helper.h +++ b/drivers/gpu/drm/sysfb/drm_sysfb_helper.h @@ -50,7 +50,7 @@ struct resource *drm_sysfb_get_memory_si(struct drm_device *dev, int drm_sysfb_get_stride_si(struct drm_device *dev, const struct screen_info *si, const struct drm_format_info *format, unsigned int width, unsigned int height, u64 size); -u64 drm_sysfb_get_visible_size_si(struct drm_device *dev, const struct screen_info *si, +s64 drm_sysfb_get_visible_size_si(struct drm_device *dev, const struct screen_info *si, unsigned int height, unsigned int stride, u64 size); #endif diff --git a/drivers/gpu/drm/sysfb/drm_sysfb_screen_info.c b/drivers/gpu/drm/sysfb/drm_sysfb_screen_info.c index 8b14eaa304c0..042d1b796696 100644 --- a/drivers/gpu/drm/sysfb/drm_sysfb_screen_info.c +++ b/drivers/gpu/drm/sysfb/drm_sysfb_screen_info.c @@ -65,7 +65,7 @@ int drm_sysfb_get_stride_si(struct drm_device *dev, const struct screen_info *si } EXPORT_SYMBOL(drm_sysfb_get_stride_si); -u64 drm_sysfb_get_visible_size_si(struct drm_device *dev, const struct screen_info *si, +s64 drm_sysfb_get_visible_size_si(struct drm_device *dev, const struct screen_info *si, unsigned int height, unsigned int stride, u64 size) { u64 vsize = mul_u32_u32(height, stride); diff --git a/drivers/gpu/drm/sysfb/efidrm.c b/drivers/gpu/drm/sysfb/efidrm.c index a335c94a7bd7..d5adef5deb63 100644 --- a/drivers/gpu/drm/sysfb/efidrm.c +++ b/drivers/gpu/drm/sysfb/efidrm.c @@ -150,7 +150,8 @@ static struct efidrm_device *efidrm_device_create(struct drm_driver *drv, const struct screen_info *si; const struct drm_format_info *format; int width, height, stride; - u64 vsize, mem_flags; + s64 vsize; + u64 mem_flags; struct resource resbuf; struct resource *res; struct efidrm_device *efi; @@ -204,8 +205,8 @@ static struct efidrm_device *efidrm_device_create(struct drm_driver *drv, if (stride < 0) return ERR_PTR(stride); vsize = drm_sysfb_get_visible_size_si(dev, si, height, stride, resource_size(res)); - if (!vsize) - return ERR_PTR(-EINVAL); + if (vsize < 0) + return ERR_PTR(vsize); drm_dbg(dev, "framebuffer format=%p4cc, size=%dx%d, stride=%d bytes\n", &format->format, width, height, stride); diff --git a/drivers/gpu/drm/sysfb/vesadrm.c b/drivers/gpu/drm/sysfb/vesadrm.c index 4e00113e5c77..d60a67fc1d5b 100644 --- a/drivers/gpu/drm/sysfb/vesadrm.c +++ b/drivers/gpu/drm/sysfb/vesadrm.c @@ -400,7 +400,7 @@ static struct vesadrm_device *vesadrm_device_create(struct drm_driver *drv, const struct screen_info *si; const struct drm_format_info *format; int width, height, stride; - u64 vsize; + s64 vsize; struct resource resbuf; struct resource *res; struct vesadrm_device *vesa; @@ -455,8 +455,8 @@ static struct vesadrm_device *vesadrm_device_create(struct drm_driver *drv, if (stride < 0) return ERR_PTR(stride); vsize = drm_sysfb_get_visible_size_si(dev, si, height, stride, resource_size(res)); - if (!vsize) - return ERR_PTR(-EINVAL); + if (vsize < 0) + return ERR_PTR(vsize); drm_dbg(dev, "framebuffer format=%p4cc, size=%dx%d, stride=%d bytes\n", &format->format, width, height, stride); From 9206b22fb959f4a9cf1921f34aed0df1dcb1ab04 Mon Sep 17 00:00:00 2001 From: Thomas Zimmermann Date: Thu, 18 Jun 2026 10:42:00 +0200 Subject: [PATCH 129/297] drm/sysfb: Avoid truncating maximum stride Passing a maximum as 64-bit type to drm_sysfb_get_validated_int0() can truncate the value to 32 bits. Use drm_sysfb_get_validated_size0(), which uses 64-bit arithmetics. Then test the returned stride against the limits of int to avoid truncations in the returned value. A valid stride is in the range of [1, INT_MAX] inclusive. Signed-off-by: Thomas Zimmermann Reported-by: Sashiko Closes: https://lore.kernel.org/dri-devel/20260617114016.5A5991F000E9@smtp.kernel.org/ Fixes: 32ae90c66fb6 ("drm/sysfb: Add efidrm for EFI displays") Fixes: a84eb6abe2b6 ("drm/sysfb: Add vesadrm for VESA displays") Cc: Thomas Zimmermann Cc: Javier Martinez Canillas Cc: dri-devel@lists.freedesktop.org Cc: # v6.16+ Reviewed-by: Javier Martinez Canillas Link: https://patch.msgid.link/20260618084327.46567-5-tzimmermann@suse.de --- drivers/gpu/drm/sysfb/drm_sysfb_screen_info.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/sysfb/drm_sysfb_screen_info.c b/drivers/gpu/drm/sysfb/drm_sysfb_screen_info.c index 042d1b796696..1c479ce0e503 100644 --- a/drivers/gpu/drm/sysfb/drm_sysfb_screen_info.c +++ b/drivers/gpu/drm/sysfb/drm_sysfb_screen_info.c @@ -57,11 +57,17 @@ int drm_sysfb_get_stride_si(struct drm_device *dev, const struct screen_info *si unsigned int width, unsigned int height, u64 size) { u64 lfb_linelength = si->lfb_linelength; + s64 stride; if (!lfb_linelength) lfb_linelength = drm_format_info_min_pitch(format, 0, width); - return drm_sysfb_get_validated_int0(dev, "stride", lfb_linelength, div64_u64(size, height)); + stride = drm_sysfb_get_validated_size0(dev, "stride", lfb_linelength, + div64_u64(size, height)); + if (stride < INT_MIN || stride > INT_MAX) + return -EINVAL; + + return (int)stride; /* stride or negative errno code */ } EXPORT_SYMBOL(drm_sysfb_get_stride_si); From 493765b8e922a506e09e22e80b6cc9ff05e8295b Mon Sep 17 00:00:00 2001 From: Aaron Erhardt Date: Tue, 19 May 2026 17:49:48 +0200 Subject: [PATCH 130/297] ALSA: hda/realtek: Fix noisy mic for Clevo V6xxAW Add a PCI quirk to reduce the volume of the internal microphone to prevent extremely noisy signal. Signed-off-by: Aaron Erhardt Signed-off-by: Werner Sembach Cc: stable@vger.kernel.org Link: https://patch.msgid.link/20260519155047.106096-1-wse@tuxedocomputers.com Signed-off-by: Takashi Iwai --- sound/hda/codecs/realtek/alc269.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/hda/codecs/realtek/alc269.c b/sound/hda/codecs/realtek/alc269.c index e88ca720f4e5..0d932f6ae3e8 100644 --- a/sound/hda/codecs/realtek/alc269.c +++ b/sound/hda/codecs/realtek/alc269.c @@ -7603,6 +7603,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1558, 0x51b3, "Clevo NS70AU", ALC256_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x5630, "Clevo NP50RNJS", ALC256_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x5700, "Clevo X560WN[RST]", ALC256_FIXUP_SYSTEM76_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1558, 0x6480, "Clevo V6xxAW", ALC245_FIXUP_CLEVO_NOISY_MIC), SND_PCI_QUIRK(0x1558, 0x70a1, "Clevo NB70T[HJK]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x70b3, "Clevo NK70SB", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1558, 0x70f2, "Clevo NH79EPY", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), From cf81b260916c92cf610c907d41627a175e86e37d Mon Sep 17 00:00:00 2001 From: Ahmad Fatoum Date: Wed, 17 Jun 2026 16:47:53 +0200 Subject: [PATCH 131/297] ASoC: cs530x: Fix expected MCLK rates for CS5302/4/8 When this driver was first added, it accepted rates of 24.56 MHz and 22.572 MHz for the MCLK when PLL bypass is enabled. These rates seem to have no basis in the datasheets and were thus replaced with 45.1584 MHz and 49.152 MHz, respectively, in commit e7ab858390f2 ("ASoC: cs530x: Correct MCLK reference frequency values"). While the new rates are indeed correct for the CS4xxx ICs[0][1][2][3], they are incorrect for the CS530x ICs the driver was originally written to support as the MCLK frequencies are halved there[4][5][6]. Fix this by checking against the correct type-appropriate rates. While at it, drop the CS530X_SYSCLK_REF_* macros. They arguably confuse more than they help, especially as they are not applicable to the cs5302/4/8. [0]: https://statics.cirrus.com/pubs/proDatasheet/CS4282P_DS1318F1.pdf [1]: https://statics.cirrus.com/pubs/proDatasheet/CS4302P_DS1315F1.pdf [2]: https://statics.cirrus.com/pubs/proDatasheet/CS4304P_DS1316F1.pdf [3]: https://statics.cirrus.com/pubs/proDatasheet/CS4308P_DS1317F1.pdf [4]: https://statics.cirrus.com/pubs/proDatasheet/CS5302P_DS1312F1.pdf [5]: https://statics.cirrus.com/pubs/proDatasheet/CS5304P_DS1313F1.pdf [6]: https://statics.cirrus.com/pubs/proDatasheet/CS5308P_DS1314F1.pdf Fixes: 2884c29152c0 ("ASoC: cs530x: Support for cs530x ADCs") Signed-off-by: Ahmad Fatoum Reviewed-by: Charles Keepax Link: https://patch.msgid.link/20260617-cs530x-mclk-v1-1-0215b5f1a0a4@pengutronix.de Signed-off-by: Mark Brown --- sound/soc/codecs/cs530x.c | 29 ++++++++++++++++++++++++----- sound/soc/codecs/cs530x.h | 6 ------ 2 files changed, 24 insertions(+), 11 deletions(-) diff --git a/sound/soc/codecs/cs530x.c b/sound/soc/codecs/cs530x.c index 18b5ff75feec..2c7e33135911 100644 --- a/sound/soc/codecs/cs530x.c +++ b/sound/soc/codecs/cs530x.c @@ -1093,6 +1093,29 @@ static int cs530x_component_probe(struct snd_soc_component *component) return 0; } +static bool cs530x_mclk_freq_is_valid(struct cs530x_priv *cs530x, + unsigned int freq) +{ + /* + * All these chips support 48 kHz- and 44.1 kHz-related sample rates, + * but they differ in what MCLK frequency is required for achieving + * the sample rate. + */ + switch (cs530x->devtype) { + case CS4282: + case CS4302: + case CS4304: + case CS4308: + return freq == 49152000 || freq == 45158400; + case CS5302: + case CS5304: + case CS5308: + return freq == 24576000 || freq == 22579200; + } + + return false; +} + static int cs530x_set_sysclk(struct snd_soc_component *component, int clk_id, int source, unsigned int freq, int dir) { @@ -1101,11 +1124,7 @@ static int cs530x_set_sysclk(struct snd_soc_component *component, int clk_id, switch (source) { case CS530X_SYSCLK_SRC_MCLK: - switch (freq) { - case CS530X_SYSCLK_REF_45_1MHZ: - case CS530X_SYSCLK_REF_49_1MHZ: - break; - default: + if (!cs530x_mclk_freq_is_valid(cs530x, freq)) { dev_err(component->dev, "Invalid MCLK source rate %d\n", freq); return -EINVAL; } diff --git a/sound/soc/codecs/cs530x.h b/sound/soc/codecs/cs530x.h index 1e2f6a7a589c..18aa4dfd0c86 100644 --- a/sound/soc/codecs/cs530x.h +++ b/sound/soc/codecs/cs530x.h @@ -200,12 +200,6 @@ /* IN_VOL_CTL5 and OUT_VOL_CTL5 */ #define CS530X_INOUT_VU BIT(0) -/* MCLK Reference Source Frequency */ -/* 41KHz related */ -#define CS530X_SYSCLK_REF_45_1MHZ 45158400 -/* 48KHz related */ -#define CS530X_SYSCLK_REF_49_1MHZ 49152000 - /* System Clock Source */ #define CS530X_SYSCLK_SRC_MCLK 0 #define CS530X_SYSCLK_SRC_PLL 1 From dd015b566d505d698386103e9c80b739c7336eb8 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Thu, 18 Jun 2026 11:06:51 -0700 Subject: [PATCH 132/297] fscrypt: Fix key setup in edge case with multiple data unit sizes The addition of support for customizable data unit sizes introduced an edge case where a file's contents can be en/decrypted with the wrong data unit size. It occurs when there are multiple v2 policies that: - Have *different* data unit sizes, via the log2_data_unit_size field - Share the same master_key_identifier, contents_encryption_mode, and either FSCRYPT_POLICY_FLAG_DIRECT_KEY, FSCRYPT_POLICY_FLAG_IV_INO_LBLK_32, or FSCRYPT_POLICY_FLAG_IV_INO_LBLK_64 - Are being used on the same filesystem, which also must be mounted with the "inlinecrypt" mount option. Fortunately this edge case doesn't actually occur in practice. I just found it via code review. But it needs to be fixed regardless. The bug is caused by the data unit size not being fully considered when blk_crypto_keys are cached in mk_direct_keys, mk_iv_ino_lblk_32_keys, and mk_iv_ino_lblk_64_keys. They're differentiated only by master key, encryption mode, and flag. However, each one actually has a data unit size too. Only the first data unit size that is cached is used. To fix this, start using the data unit size to differentiate the cached keys. For several reasons, including avoiding increasing the size of struct fscrypt_master_key, just replace all three arrays with a single linked list instead of changing them into two-dimensional arrays. This works well when considering that in practice at most 2 entries are used across all three arrays, so it was already mostly wasted space. For simplicity, make the list also take over the publish/subscribe of the prepared key itself. That is, create separate list nodes for blk_crypto_keys vs crypto_skciphers, and add nodes to the list only when their key is actually prepared. (Note that the legacy fscrypt_direct_keys table in fs/crypto/keysetup_v1.c already works this way.) This eliminates the need for the additional memory barriers when reading and writing the fields of struct fscrypt_prepared_key. Note that I technically should have included the data unit size in the HKDF info string as well. But it's too late to change that. Fixes: 5b1188847180 ("fscrypt: support crypto data unit size less than filesystem block size") Cc: stable@vger.kernel.org Link: https://patch.msgid.link/20260618180652.52742-1-ebiggers@kernel.org Signed-off-by: Eric Biggers --- fs/crypto/fscrypt_private.h | 52 +++++++++------- fs/crypto/inline_crypt.c | 8 +-- fs/crypto/keyring.c | 23 ++++--- fs/crypto/keysetup.c | 118 ++++++++++++++++++++++-------------- 4 files changed, 120 insertions(+), 81 deletions(-) diff --git a/fs/crypto/fscrypt_private.h b/fs/crypto/fscrypt_private.h index 8d3c278a7591..4263cac24b32 100644 --- a/fs/crypto/fscrypt_private.h +++ b/fs/crypto/fscrypt_private.h @@ -236,7 +236,7 @@ struct fscrypt_symlink_data { * @tfm: crypto API transform object * @blk_key: key for blk-crypto * - * Normally only one of the fields will be non-NULL. + * Only one of the fields is non-NULL. */ struct fscrypt_prepared_key { struct crypto_sync_skcipher *tfm; @@ -245,6 +245,15 @@ struct fscrypt_prepared_key { #endif }; +/* An entry in the linked list ->mk_mode_keys */ +struct fscrypt_mode_key { + struct fscrypt_prepared_key key; + struct list_head link; + u8 hkdf_context; + u8 mode_num; + u8 data_unit_bits; +}; + /* * fscrypt_inode_info - the "encryption key" for an inode * @@ -430,20 +439,12 @@ int fscrypt_derive_sw_secret(struct super_block *sb, * @prep_key, depending on which encryption implementation the file will use. */ static inline bool -fscrypt_is_key_prepared(struct fscrypt_prepared_key *prep_key, +fscrypt_is_key_prepared(const struct fscrypt_prepared_key *prep_key, const struct fscrypt_inode_info *ci) { - /* - * The two smp_load_acquire()'s here pair with the smp_store_release()'s - * in fscrypt_prepare_inline_crypt_key() and fscrypt_prepare_key(). - * I.e., in some cases (namely, if this prep_key is a per-mode - * encryption key) another task can publish blk_key or tfm concurrently, - * executing a RELEASE barrier. We need to use smp_load_acquire() here - * to safely ACQUIRE the memory the other task published. - */ if (fscrypt_using_inline_encryption(ci)) - return smp_load_acquire(&prep_key->blk_key) != NULL; - return smp_load_acquire(&prep_key->tfm) != NULL; + return prep_key->blk_key != NULL; + return prep_key->tfm != NULL; } #else /* CONFIG_FS_ENCRYPTION_INLINE_CRYPT */ @@ -486,10 +487,10 @@ fscrypt_derive_sw_secret(struct super_block *sb, } static inline bool -fscrypt_is_key_prepared(struct fscrypt_prepared_key *prep_key, +fscrypt_is_key_prepared(const struct fscrypt_prepared_key *prep_key, const struct fscrypt_inode_info *ci) { - return smp_load_acquire(&prep_key->tfm) != NULL; + return prep_key->tfm != NULL; } #endif /* !CONFIG_FS_ENCRYPTION_INLINE_CRYPT */ @@ -577,8 +578,8 @@ struct fscrypt_master_key { /* * Active and structural reference counts. An active ref guarantees * that the struct continues to exist, continues to be in the keyring - * ->s_master_keys, and that any embedded subkeys (e.g. - * ->mk_direct_keys) that have been prepared continue to exist. + * ->s_master_keys, and that any non-file-scoped subkeys (e.g. + * ->mk_mode_keys) that have been prepared continue to exist. * A structural ref only guarantees that the struct continues to exist. * * There is one active ref associated with ->mk_present being true, and @@ -632,12 +633,21 @@ struct fscrypt_master_key { spinlock_t mk_decrypted_inodes_lock; /* - * Per-mode encryption keys for the various types of encryption policies - * that use them. Allocated and derived on-demand. + * A list of 'struct fscrypt_mode_key' for the (hkdf_context, mode_num, + * data_unit_bits, inlinecrypt) combinations that are in use for this + * master key, for hkdf_context in [HKDF_CONTEXT_DIRECT_KEY, + * HKDF_CONTEXT_IV_INO_LBLK_32_KEY, HKDF_CONTEXT_IV_INO_LBLK_64_KEY]. + * + * This is a linked list and not a hash table because in practice + * there's just a single encryption policy per master key, using + * _at most_ 2 nodes in this list. Per-file keys don't use this at all. + * + * This list is append-only until the master key is fully removed, at + * which time the list is cleared. Before then, + * fscrypt_mode_key_setup_mutex synchronizes appends, and searches use + * the RCU read lock together with ->mk_sem held for read. */ - struct fscrypt_prepared_key mk_direct_keys[FSCRYPT_MODE_MAX + 1]; - struct fscrypt_prepared_key mk_iv_ino_lblk_64_keys[FSCRYPT_MODE_MAX + 1]; - struct fscrypt_prepared_key mk_iv_ino_lblk_32_keys[FSCRYPT_MODE_MAX + 1]; + struct list_head mk_mode_keys; /* Hash key for inode numbers. Initialized only when needed. */ siphash_key_t mk_ino_hash_key; diff --git a/fs/crypto/inline_crypt.c b/fs/crypto/inline_crypt.c index 37d42d357925..47324062fee5 100644 --- a/fs/crypto/inline_crypt.c +++ b/fs/crypto/inline_crypt.c @@ -198,13 +198,7 @@ int fscrypt_prepare_inline_crypt_key(struct fscrypt_prepared_key *prep_key, goto fail; } - /* - * Pairs with the smp_load_acquire() in fscrypt_is_key_prepared(). - * I.e., here we publish ->blk_key with a RELEASE barrier so that - * concurrent tasks can ACQUIRE it. Note that this concurrency is only - * possible for per-mode keys, not for per-file keys. - */ - smp_store_release(&prep_key->blk_key, blk_key); + prep_key->blk_key = blk_key; return 0; fail: diff --git a/fs/crypto/keyring.c b/fs/crypto/keyring.c index be8e6e8011f2..5fe0d985a58d 100644 --- a/fs/crypto/keyring.c +++ b/fs/crypto/keyring.c @@ -87,14 +87,14 @@ void fscrypt_put_master_key(struct fscrypt_master_key *mk) void fscrypt_put_master_key_activeref(struct super_block *sb, struct fscrypt_master_key *mk) { - size_t i; + struct fscrypt_mode_key *node, *tmp; if (!refcount_dec_and_test(&mk->mk_active_refs)) return; /* * No active references left, so complete the full removal of this * fscrypt_master_key struct by removing it from the keyring and - * destroying any subkeys embedded in it. + * destroying any non-file-scoped subkeys. */ if (WARN_ON_ONCE(!sb->s_master_keys)) @@ -110,13 +110,16 @@ void fscrypt_put_master_key_activeref(struct super_block *sb, WARN_ON_ONCE(mk->mk_present); WARN_ON_ONCE(!list_empty(&mk->mk_decrypted_inodes)); - for (i = 0; i <= FSCRYPT_MODE_MAX; i++) { - fscrypt_destroy_prepared_key( - sb, &mk->mk_direct_keys[i]); - fscrypt_destroy_prepared_key( - sb, &mk->mk_iv_ino_lblk_64_keys[i]); - fscrypt_destroy_prepared_key( - sb, &mk->mk_iv_ino_lblk_32_keys[i]); + /* + * Destroy any non-file-scoped subkeys. Since ->mk_active_refs == 0, + * they're no longer referenced by any inodes. Nor can key setup run + * and use them again. So they're no longer needed. (This implies no + * concurrent readers, so we don't need list_del_rcu() for example.) + */ + list_for_each_entry_safe(node, tmp, &mk->mk_mode_keys, link) { + fscrypt_destroy_prepared_key(sb, &node->key); + list_del(&node->link); + kfree(node); } memzero_explicit(&mk->mk_ino_hash_key, sizeof(mk->mk_ino_hash_key)); @@ -445,6 +448,8 @@ static int add_new_master_key(struct super_block *sb, INIT_LIST_HEAD(&mk->mk_decrypted_inodes); spin_lock_init(&mk->mk_decrypted_inodes_lock); + INIT_LIST_HEAD(&mk->mk_mode_keys); + if (mk_spec->type == FSCRYPT_KEY_SPEC_TYPE_IDENTIFIER) { err = allocate_master_key_users_keyring(mk); if (err) diff --git a/fs/crypto/keysetup.c b/fs/crypto/keysetup.c index ce327bfdada4..f905f9f94bdd 100644 --- a/fs/crypto/keysetup.c +++ b/fs/crypto/keysetup.c @@ -163,13 +163,7 @@ int fscrypt_prepare_key(struct fscrypt_prepared_key *prep_key, tfm = fscrypt_allocate_skcipher(ci->ci_mode, raw_key, ci->ci_inode); if (IS_ERR(tfm)) return PTR_ERR(tfm); - /* - * Pairs with the smp_load_acquire() in fscrypt_is_key_prepared(). - * I.e., here we publish ->tfm with a RELEASE barrier so that - * concurrent tasks can ACQUIRE it. Note that this concurrency is only - * possible for per-mode keys, not for per-file keys. - */ - smp_store_release(&prep_key->tfm, tfm); + prep_key->tfm = tfm; return 0; } @@ -190,9 +184,37 @@ int fscrypt_set_per_file_enc_key(struct fscrypt_inode_info *ci, return fscrypt_prepare_key(&ci->ci_enc_key, raw_key, ci); } +/* + * Find the fscrypt_prepared_key (if any) for a particular (mk, hkdf_context, + * mode_num, data_unit_bits, inlinecrypt) combination. + * + * The caller must hold ->mk_sem for reading and ->mk_present must be true, + * ensuring that ->mk_mode_keys is still append-only. + */ +static struct fscrypt_prepared_key * +fscrypt_find_mode_key(struct fscrypt_master_key *mk, u8 hkdf_context, + u8 mode_num, const struct fscrypt_inode_info *ci) +{ + struct fscrypt_mode_key *node; + + /* + * The RCU read lock here is used only to synchronize with concurrent + * list_add_tail_rcu(). Concurrent deletions are impossible here, so + * returning a pointer to a node without taking any refcount is safe. + */ + guard(rcu)(); + list_for_each_entry_rcu(node, &mk->mk_mode_keys, link) { + if (node->hkdf_context == hkdf_context && + node->mode_num == mode_num && + node->data_unit_bits == ci->ci_data_unit_bits && + fscrypt_is_key_prepared(&node->key, ci)) + return &node->key; + } + return NULL; +} + static int setup_per_mode_enc_key(struct fscrypt_inode_info *ci, struct fscrypt_master_key *mk, - struct fscrypt_prepared_key *keys, u8 hkdf_context, bool include_fs_uuid) { const struct inode *inode = ci->ci_inode; @@ -200,7 +222,8 @@ static int setup_per_mode_enc_key(struct fscrypt_inode_info *ci, struct fscrypt_mode *mode = ci->ci_mode; const u8 mode_num = mode - fscrypt_modes; struct fscrypt_prepared_key *prep_key; - u8 mode_key[FSCRYPT_MAX_RAW_KEY_SIZE]; + struct fscrypt_mode_key *new_node; + u8 raw_mode_key[FSCRYPT_MAX_RAW_KEY_SIZE]; u8 hkdf_info[sizeof(mode_num) + sizeof(sb->s_uuid)]; unsigned int hkdf_infolen = 0; bool use_hw_wrapped_key = false; @@ -223,48 +246,56 @@ static int setup_per_mode_enc_key(struct fscrypt_inode_info *ci, use_hw_wrapped_key = true; } - prep_key = &keys[mode_num]; - if (fscrypt_is_key_prepared(prep_key, ci)) { + prep_key = fscrypt_find_mode_key(mk, hkdf_context, mode_num, ci); + if (prep_key) { ci->ci_enc_key = *prep_key; return 0; } - mutex_lock(&fscrypt_mode_key_setup_mutex); + guard(mutex)(&fscrypt_mode_key_setup_mutex); - if (fscrypt_is_key_prepared(prep_key, ci)) - goto done_unlock; + prep_key = fscrypt_find_mode_key(mk, hkdf_context, mode_num, ci); + if (prep_key) { + ci->ci_enc_key = *prep_key; + return 0; + } + + new_node = kzalloc_obj(*new_node); + if (!new_node) + return -ENOMEM; + new_node->hkdf_context = hkdf_context; + new_node->mode_num = mode_num; + new_node->data_unit_bits = ci->ci_data_unit_bits; + prep_key = &new_node->key; if (use_hw_wrapped_key) { err = fscrypt_prepare_inline_crypt_key(prep_key, mk->mk_secret.bytes, mk->mk_secret.size, true, ci); - if (err) - goto out_unlock; - goto done_unlock; + } else { + static_assert(sizeof(mode_num) == 1); + static_assert(sizeof(sb->s_uuid) == 16); + static_assert(sizeof(hkdf_info) == 17); + hkdf_info[hkdf_infolen++] = mode_num; + if (include_fs_uuid) { + memcpy(&hkdf_info[hkdf_infolen], &sb->s_uuid, + sizeof(sb->s_uuid)); + hkdf_infolen += sizeof(sb->s_uuid); + } + fscrypt_hkdf_expand(&mk->mk_secret.hkdf, hkdf_context, + hkdf_info, hkdf_infolen, raw_mode_key, + mode->keysize); + err = fscrypt_prepare_key(prep_key, raw_mode_key, ci); + memzero_explicit(raw_mode_key, mode->keysize); } - - BUILD_BUG_ON(sizeof(mode_num) != 1); - BUILD_BUG_ON(sizeof(sb->s_uuid) != 16); - BUILD_BUG_ON(sizeof(hkdf_info) != 17); - hkdf_info[hkdf_infolen++] = mode_num; - if (include_fs_uuid) { - memcpy(&hkdf_info[hkdf_infolen], &sb->s_uuid, - sizeof(sb->s_uuid)); - hkdf_infolen += sizeof(sb->s_uuid); + if (err) { + kfree(new_node); + return err; } - fscrypt_hkdf_expand(&mk->mk_secret.hkdf, hkdf_context, hkdf_info, - hkdf_infolen, mode_key, mode->keysize); - err = fscrypt_prepare_key(prep_key, mode_key, ci); - memzero_explicit(mode_key, mode->keysize); - if (err) - goto out_unlock; -done_unlock: + list_add_tail_rcu(&new_node->link, &mk->mk_mode_keys); ci->ci_enc_key = *prep_key; - err = 0; -out_unlock: - mutex_unlock(&fscrypt_mode_key_setup_mutex); - return err; + return 0; } /* @@ -311,8 +342,8 @@ static int fscrypt_setup_iv_ino_lblk_32_key(struct fscrypt_inode_info *ci, { int err; - err = setup_per_mode_enc_key(ci, mk, mk->mk_iv_ino_lblk_32_keys, - HKDF_CONTEXT_IV_INO_LBLK_32_KEY, true); + err = setup_per_mode_enc_key(ci, mk, HKDF_CONTEXT_IV_INO_LBLK_32_KEY, + true); if (err) return err; @@ -364,8 +395,8 @@ static int fscrypt_setup_v2_file_key(struct fscrypt_inode_info *ci, * encryption key. This ensures that the master key is * consistently used only for HKDF, avoiding key reuse issues. */ - err = setup_per_mode_enc_key(ci, mk, mk->mk_direct_keys, - HKDF_CONTEXT_DIRECT_KEY, false); + err = setup_per_mode_enc_key(ci, mk, HKDF_CONTEXT_DIRECT_KEY, + false); } else if (ci->ci_policy.v2.flags & FSCRYPT_POLICY_FLAG_IV_INO_LBLK_64) { /* @@ -374,9 +405,8 @@ static int fscrypt_setup_v2_file_key(struct fscrypt_inode_info *ci, * the IVs. This format is optimized for use with inline * encryption hardware compliant with the UFS standard. */ - err = setup_per_mode_enc_key(ci, mk, mk->mk_iv_ino_lblk_64_keys, - HKDF_CONTEXT_IV_INO_LBLK_64_KEY, - true); + err = setup_per_mode_enc_key( + ci, mk, HKDF_CONTEXT_IV_INO_LBLK_64_KEY, true); } else if (ci->ci_policy.v2.flags & FSCRYPT_POLICY_FLAG_IV_INO_LBLK_32) { err = fscrypt_setup_iv_ino_lblk_32_key(ci, mk); From 696c030e1e3438955aba443b308ee8b6faa3983e Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Thu, 18 Jun 2026 15:19:21 -0700 Subject: [PATCH 133/297] fscrypt: Replace mk_users keyring with simple list Change mk_users (the set of user claims to an fscrypt master key) from a 'struct key' keyring to a simple linked list. It's still a collection of 'struct key' for quota tracking. It was originally thought to be natural that a collection of 'struct key' should be held in a 'struct key' keyring. In reality, it's just been causing problems, similar to how using 'struct key' for the filesystem keyring caused problems and was removed in commit d7e7b9af104c ("fscrypt: stop using keyrings subsystem for fscrypt_master_key"). Commit d3a7bd420076 ("fscrypt: clear keyring before calling key_put()") fixed mk_users cleanup to be synchronous. But that apparently wasn't enough: the keyring subsystem's redundant locking is still generating lockdep false positives due to the interaction with filesystem reclaim. With the simple list, the redundant locking and lockdep issue goes away. Of course, searching a linked list is linear-time whereas the 'struct key' keyring used a fancy constant-time associative array. But that's fine here, since in practice there's just one entry in the list. In fact the new code is much faster in practice, since it's much smaller and doesn't have to convert the kuid_t into a string to search for it. Reported-by: syzbot+f55b043dacf43776b50c@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=f55b043dacf43776b50c Reported-by: Mohammed EL Kadiri Closes: https://lore.kernel.org/keyrings/20260614150041.21172-1-med08elkadiri@gmail.com/ Fixes: 23c688b54016 ("fscrypt: allow unprivileged users to add/remove keys for v2 policies") Cc: stable@vger.kernel.org Link: https://patch.msgid.link/20260618221921.87896-1-ebiggers@kernel.org Signed-off-by: Eric Biggers --- fs/crypto/fscrypt_private.h | 32 ++++-- fs/crypto/keyring.c | 216 +++++++++++++++--------------------- 2 files changed, 113 insertions(+), 135 deletions(-) diff --git a/fs/crypto/fscrypt_private.h b/fs/crypto/fscrypt_private.h index 4263cac24b32..0053b5c45412 100644 --- a/fs/crypto/fscrypt_private.h +++ b/fs/crypto/fscrypt_private.h @@ -496,6 +496,19 @@ fscrypt_is_key_prepared(const struct fscrypt_prepared_key *prep_key, /* keyring.c */ +/* + * fscrypt_master_key_user - a user's claim to a master key + */ +struct fscrypt_master_key_user { + struct list_head link; + kuid_t uid; + /* + * This 'struct key' contains no secret. It exists solely to charge the + * appropriate user's key quota. + */ + struct key *quota_key; +}; + /* * fscrypt_master_key_secret - secret key material of an in-use master key */ @@ -611,19 +624,18 @@ struct fscrypt_master_key { struct fscrypt_key_specifier mk_spec; /* - * Keyring which contains a key of type 'key_type_fscrypt_user' for each - * user who has added this key. Normally each key will be added by just - * one user, but it's possible that multiple users share a key, and in - * that case we need to keep track of those users so that one user can't - * remove the key before the others want it removed too. + * List of user claims to this key (struct fscrypt_master_key_user). + * Normally each key will be added by just one user, but it's possible + * that multiple users share a key, and in that case we need to keep + * track of those users so that one user can't remove the key before the + * others want it removed too. * - * This is NULL for v1 policy keys; those can only be added by root. + * Used only for v2 policy keys. v1 policy keys can be added only by + * root, so user tracking doesn't apply to them. * - * Locking: protected by ->mk_sem. (We don't just rely on the keyrings - * subsystem semaphore ->mk_users->sem, as we need support for atomic - * search+insert along with proper synchronization with other fields.) + * Locking: protected by ->mk_sem. */ - struct key *mk_users; + struct list_head mk_users; /* * List of inodes that were unlocked using this key. This allows the diff --git a/fs/crypto/keyring.c b/fs/crypto/keyring.c index 5fe0d985a58d..38b73e703073 100644 --- a/fs/crypto/keyring.c +++ b/fs/crypto/keyring.c @@ -65,22 +65,19 @@ static void fscrypt_free_master_key(struct rcu_head *head) kfree_sensitive(mk); } +static void clear_mk_users(struct fscrypt_master_key *mk); + void fscrypt_put_master_key(struct fscrypt_master_key *mk) { if (!refcount_dec_and_test(&mk->mk_struct_refs)) return; /* - * No structural references left, so free ->mk_users, and also free the + * No structural references left, so clear ->mk_users, and also free the * fscrypt_master_key struct itself after an RCU grace period ensures * that concurrent keyring lookups can no longer find it. */ WARN_ON_ONCE(refcount_read(&mk->mk_active_refs) != 0); - if (mk->mk_users) { - /* Clear the keyring so the quota gets released right away. */ - keyring_clear(mk->mk_users); - key_put(mk->mk_users); - mk->mk_users = NULL; - } + clear_mk_users(mk); call_rcu(&mk->mk_rcu_head, fscrypt_free_master_key); } @@ -165,8 +162,8 @@ static void fscrypt_user_key_describe(const struct key *key, struct seq_file *m) } /* - * Type of key in ->mk_users. Each key of this type represents a particular - * user who has added a particular master key. + * Type of fscrypt_master_key_user::quota_key. This contains no secret; it + * exists solely to charge a user's key quota. * * Note that the name of this key type really should be something like * ".fscrypt-user" instead of simply ".fscrypt". But the shorter name is chosen @@ -180,30 +177,9 @@ static struct key_type key_type_fscrypt_user = { .describe = fscrypt_user_key_describe, }; -#define FSCRYPT_MK_USERS_DESCRIPTION_SIZE \ - (CONST_STRLEN("fscrypt-") + 2 * FSCRYPT_KEY_IDENTIFIER_SIZE + \ - CONST_STRLEN("-users") + 1) - #define FSCRYPT_MK_USER_DESCRIPTION_SIZE \ (2 * FSCRYPT_KEY_IDENTIFIER_SIZE + CONST_STRLEN(".uid.") + 10 + 1) -static void format_mk_users_keyring_description( - char description[FSCRYPT_MK_USERS_DESCRIPTION_SIZE], - const u8 mk_identifier[FSCRYPT_KEY_IDENTIFIER_SIZE]) -{ - sprintf(description, "fscrypt-%*phN-users", - FSCRYPT_KEY_IDENTIFIER_SIZE, mk_identifier); -} - -static void format_mk_user_description( - char description[FSCRYPT_MK_USER_DESCRIPTION_SIZE], - const u8 mk_identifier[FSCRYPT_KEY_IDENTIFIER_SIZE]) -{ - - sprintf(description, "%*phN.uid.%u", FSCRYPT_KEY_IDENTIFIER_SIZE, - mk_identifier, __kuid_val(current_fsuid())); -} - /* Create ->s_master_keys if needed. Synchronized by fscrypt_add_key_mutex. */ static int allocate_filesystem_keyring(struct super_block *sb) { @@ -338,91 +314,94 @@ out: return mk; } -static int allocate_master_key_users_keyring(struct fscrypt_master_key *mk) +/* Find the current user's claim in ->mk_users. ->mk_sem must be held. */ +static struct fscrypt_master_key_user * +find_master_key_user(struct fscrypt_master_key *mk) { - char description[FSCRYPT_MK_USERS_DESCRIPTION_SIZE]; - struct key *keyring; + struct fscrypt_master_key_user *mk_user; + kuid_t uid = current_fsuid(); - format_mk_users_keyring_description(description, - mk->mk_spec.u.identifier); - keyring = keyring_alloc(description, GLOBAL_ROOT_UID, GLOBAL_ROOT_GID, - current_cred(), KEY_POS_SEARCH | - KEY_USR_SEARCH | KEY_USR_READ | KEY_USR_VIEW, - KEY_ALLOC_NOT_IN_QUOTA, NULL, NULL); - if (IS_ERR(keyring)) - return PTR_ERR(keyring); - - mk->mk_users = keyring; - return 0; -} - -/* - * Find the current user's "key" in the master key's ->mk_users. - * Returns ERR_PTR(-ENOKEY) if not found. - */ -static struct key *find_master_key_user(struct fscrypt_master_key *mk) -{ - char description[FSCRYPT_MK_USER_DESCRIPTION_SIZE]; - key_ref_t keyref; - - format_mk_user_description(description, mk->mk_spec.u.identifier); - - /* - * We need to mark the keyring reference as "possessed" so that we - * acquire permission to search it, via the KEY_POS_SEARCH permission. - */ - keyref = keyring_search(make_key_ref(mk->mk_users, true /*possessed*/), - &key_type_fscrypt_user, description, false); - if (IS_ERR(keyref)) { - if (PTR_ERR(keyref) == -EAGAIN || /* not found */ - PTR_ERR(keyref) == -EKEYREVOKED) /* recently invalidated */ - keyref = ERR_PTR(-ENOKEY); - return ERR_CAST(keyref); + list_for_each_entry(mk_user, &mk->mk_users, link) { + if (uid_eq(mk_user->uid, uid)) + return mk_user; } - return key_ref_to_ptr(keyref); + return NULL; } /* - * Give the current user a "key" in ->mk_users. This charges the user's quota + * Give the current user a claim in ->mk_users. This charges the user's quota * and marks the master key as added by the current user, so that it cannot be * removed by another user with the key. Either ->mk_sem must be held for * write, or the master key must be still undergoing initialization. */ static int add_master_key_user(struct fscrypt_master_key *mk) { + kuid_t uid = current_fsuid(); char description[FSCRYPT_MK_USER_DESCRIPTION_SIZE]; - struct key *mk_user; + struct key *quota_key; + struct fscrypt_master_key_user *mk_user; int err; - format_mk_user_description(description, mk->mk_spec.u.identifier); - mk_user = key_alloc(&key_type_fscrypt_user, description, - current_fsuid(), current_gid(), current_cred(), - KEY_POS_SEARCH | KEY_USR_VIEW, 0, NULL); - if (IS_ERR(mk_user)) - return PTR_ERR(mk_user); + snprintf(description, sizeof(description), "%*phN.uid.%u", + FSCRYPT_KEY_IDENTIFIER_SIZE, mk->mk_spec.u.identifier, + __kuid_val(uid)); + quota_key = key_alloc(&key_type_fscrypt_user, description, uid, + current_gid(), current_cred(), + KEY_POS_SEARCH | KEY_USR_VIEW, 0, NULL); + if (IS_ERR(quota_key)) + return PTR_ERR(quota_key); - err = key_instantiate_and_link(mk_user, NULL, 0, mk->mk_users, NULL); - key_put(mk_user); - return err; + err = key_instantiate_and_link(quota_key, NULL, 0, NULL, NULL); + if (err) { + key_put(quota_key); + return err; + } + + mk_user = kzalloc_obj(*mk_user); + if (!mk_user) { + key_put(quota_key); + return -ENOMEM; + } + mk_user->uid = uid; + mk_user->quota_key = quota_key; + list_add(&mk_user->link, &mk->mk_users); + return 0; +} + +static void unlink_and_free_mk_user(struct fscrypt_master_key_user *mk_user) +{ + list_del(&mk_user->link); + key_put(mk_user->quota_key); + kfree(mk_user); } /* - * Remove the current user's "key" from ->mk_users. + * Remove the current user's claim from ->mk_users. * ->mk_sem must be held for write. * - * Returns 0 if removed, -ENOKEY if not found, or another -errno code. + * Returns 0 if removed or -ENOKEY if not found. */ static int remove_master_key_user(struct fscrypt_master_key *mk) { - struct key *mk_user; - int err; + struct fscrypt_master_key_user *mk_user; mk_user = find_master_key_user(mk); - if (IS_ERR(mk_user)) - return PTR_ERR(mk_user); - err = key_unlink(mk->mk_users, mk_user); - key_put(mk_user); - return err; + if (!mk_user) + return -ENOKEY; + unlink_and_free_mk_user(mk_user); + return 0; +} + +/* + * Clear ->mk_users. Either ->mk_sem must be held for write, or 'mk' must have + * no structural references left. + */ +static void clear_mk_users(struct fscrypt_master_key *mk) +{ + struct fscrypt_master_key_user *mk_user, *tmp; + + list_for_each_entry_safe(mk_user, tmp, &mk->mk_users, link) + unlink_and_free_mk_user(mk_user); } /* @@ -445,15 +424,14 @@ static int add_new_master_key(struct super_block *sb, refcount_set(&mk->mk_struct_refs, 1); mk->mk_spec = *mk_spec; + INIT_LIST_HEAD(&mk->mk_users); + INIT_LIST_HEAD(&mk->mk_decrypted_inodes); spin_lock_init(&mk->mk_decrypted_inodes_lock); INIT_LIST_HEAD(&mk->mk_mode_keys); if (mk_spec->type == FSCRYPT_KEY_SPEC_TYPE_IDENTIFIER) { - err = allocate_master_key_users_keyring(mk); - if (err) - goto out_put; err = add_master_key_user(mk); if (err) goto out_put; @@ -482,19 +460,13 @@ static int add_existing_master_key(struct fscrypt_master_key *mk, int err; /* - * If the current user is already in ->mk_users, then there's nothing to - * do. Otherwise, we need to add the user to ->mk_users. (Neither is - * applicable for v1 policy keys, which have NULL ->mk_users.) + * For v2 policy keys (FSCRYPT_KEY_SPEC_TYPE_IDENTIFIER): If the current + * user is already in ->mk_users, then there's nothing to do. + * Otherwise, add the user to ->mk_users. */ - if (mk->mk_users) { - struct key *mk_user = find_master_key_user(mk); - - if (mk_user != ERR_PTR(-ENOKEY)) { - if (IS_ERR(mk_user)) - return PTR_ERR(mk_user); - key_put(mk_user); + if (mk->mk_spec.type == FSCRYPT_KEY_SPEC_TYPE_IDENTIFIER) { + if (find_master_key_user(mk) != NULL) return 0; - } err = add_master_key_user(mk); if (err) return err; @@ -893,7 +865,6 @@ int fscrypt_verify_key_added(struct super_block *sb, { struct fscrypt_key_specifier mk_spec; struct fscrypt_master_key *mk; - struct key *mk_user; int err; mk_spec.type = FSCRYPT_KEY_SPEC_TYPE_IDENTIFIER; @@ -905,13 +876,10 @@ int fscrypt_verify_key_added(struct super_block *sb, goto out; } down_read(&mk->mk_sem); - mk_user = find_master_key_user(mk); - if (IS_ERR(mk_user)) { - err = PTR_ERR(mk_user); - } else { - key_put(mk_user); + if (find_master_key_user(mk) != NULL) err = 0; - } + else + err = -ENOKEY; up_read(&mk->mk_sem); fscrypt_put_master_key(mk); out: @@ -1103,16 +1071,18 @@ static int do_remove_key(struct file *filp, void __user *_uarg, bool all_users) down_write(&mk->mk_sem); /* If relevant, remove current user's (or all users) claim to the key */ - if (mk->mk_users && mk->mk_users->keys.nr_leaves_on_tree != 0) { - if (all_users) - err = keyring_clear(mk->mk_users); - else + if (!list_empty(&mk->mk_users)) { + if (all_users) { + clear_mk_users(mk); + err = 0; + } else { err = remove_master_key_user(mk); + } if (err) { up_write(&mk->mk_sem); goto out_put_key; } - if (mk->mk_users->keys.nr_leaves_on_tree != 0) { + if (!list_empty(&mk->mk_users)) { /* * Other users have still added the key too. We removed * the current user's claim to the key, but we still @@ -1198,6 +1168,8 @@ int fscrypt_ioctl_get_key_status(struct file *filp, void __user *uarg) struct super_block *sb = file_inode(filp)->i_sb; struct fscrypt_get_key_status_arg arg; struct fscrypt_master_key *mk; + kuid_t uid; + const struct fscrypt_master_key_user *mk_user; int err; if (copy_from_user(&arg, uarg, sizeof(arg))) @@ -1230,19 +1202,13 @@ int fscrypt_ioctl_get_key_status(struct file *filp, void __user *uarg) } arg.status = FSCRYPT_KEY_STATUS_PRESENT; - if (mk->mk_users) { - struct key *mk_user; - arg.user_count = mk->mk_users->keys.nr_leaves_on_tree; - mk_user = find_master_key_user(mk); - if (!IS_ERR(mk_user)) { + uid = current_fsuid(); + list_for_each_entry(mk_user, &mk->mk_users, link) { + arg.user_count++; + if (uid_eq(mk_user->uid, uid)) arg.status_flags |= FSCRYPT_KEY_STATUS_FLAG_ADDED_BY_SELF; - key_put(mk_user); - } else if (mk_user != ERR_PTR(-ENOKEY)) { - err = PTR_ERR(mk_user); - goto out_release_key; - } } err = 0; out_release_key: From e5c6b06a97c88227da49874d805393f960b661c6 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Fri, 24 Apr 2026 12:39:31 +0200 Subject: [PATCH 134/297] rbd: switch to dynamic root device Driver core expects devices to be dynamically allocated and will, for example, complain loudly when no release function has been provided. Use root_device_register() to allocate and register the root device instead of open coding using a static device. Signed-off-by: Johan Hovold Reviewed-by: Ilya Dryomov Signed-off-by: Ilya Dryomov --- drivers/block/rbd.c | 23 +++++++---------------- 1 file changed, 7 insertions(+), 16 deletions(-) diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index 6c1e7347e6a7..94709466ad19 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -580,14 +580,7 @@ static const struct bus_type rbd_bus_type = { .bus_groups = rbd_bus_groups, }; -static void rbd_root_dev_release(struct device *dev) -{ -} - -static struct device rbd_root_dev = { - .init_name = "rbd", - .release = rbd_root_dev_release, -}; +static struct device *rbd_root_dev; static __printf(2, 3) void rbd_warn(struct rbd_device *rbd_dev, const char *fmt, ...) @@ -5378,7 +5371,7 @@ static struct rbd_device *__rbd_dev_create(struct rbd_spec *spec) rbd_dev->dev.bus = &rbd_bus_type; rbd_dev->dev.type = &rbd_device_type; - rbd_dev->dev.parent = &rbd_root_dev; + rbd_dev->dev.parent = rbd_root_dev; device_initialize(&rbd_dev->dev); return rbd_dev; @@ -7327,15 +7320,13 @@ static int __init rbd_sysfs_init(void) { int ret; - ret = device_register(&rbd_root_dev); - if (ret < 0) { - put_device(&rbd_root_dev); - return ret; - } + rbd_root_dev = root_device_register("rbd"); + if (IS_ERR(rbd_root_dev)) + return PTR_ERR(rbd_root_dev); ret = bus_register(&rbd_bus_type); if (ret < 0) - device_unregister(&rbd_root_dev); + root_device_unregister(rbd_root_dev); return ret; } @@ -7343,7 +7334,7 @@ static int __init rbd_sysfs_init(void) static void __exit rbd_sysfs_cleanup(void) { bus_unregister(&rbd_bus_type); - device_unregister(&rbd_root_dev); + root_device_unregister(rbd_root_dev); } static int __init rbd_slab_init(void) From e120e2b666851c4c0c7bffd315ff69a09f9fe4ac Mon Sep 17 00:00:00 2001 From: Alex Markuze Date: Thu, 7 May 2026 08:05:30 +0000 Subject: [PATCH 135/297] ceph: convert inode flags to named bit positions and atomic bitops Define named bit-position constants for all CEPH_I_* inode flags and derive the bitmask values from them. This gives every flag a named _BIT constant usable with the test_bit/set_bit/clear_bit family. The intentionally unused bit position 1 is documented inline. Convert all flag modifications to use atomic bitops (set_bit, clear_bit, test_and_clear_bit). The previous code mixed lockless atomic ops on some flags (ERROR_WRITE, ODIRECT) with non-atomic read-modify-write (|= / &= ~) on other flags sharing the same unsigned long. A concurrent non-atomic RMW can clobber an adjacent lockless atomic update -- for example, a lockless clear_bit(ERROR_WRITE) could be silently resurrected by a concurrent ci->i_ceph_flags |= CEPH_I_FLUSH under the spinlock. Using atomic bitops for all modifications eliminates this class of race entirely. Flags whose only users are now the _BIT form (ERROR_WRITE, ASYNC_CHECK_CAPS) have their old mask defines removed to document that callers must use the _BIT constant with the set_bit/test_bit family. ERROR_FILELOCK and SHUTDOWN retain their mask defines because they are still used via bitmask tests in lockless readers (ceph_inode_is_shutdown, reconnect_caps_cb). The direct assignment in ceph_finish_async_create() is converted from i_ceph_flags = CEPH_I_ASYNC_CREATE to set_bit(). This inode is I_NEW at this point -- still invisible to other threads and guaranteed to have zero flags from alloc_inode -- so either form is safe, but set_bit() keeps the conversion uniform. Signed-off-by: Alex Markuze Reviewed-by: Viacheslav Dubeyko Signed-off-by: Viacheslav Dubeyko Signed-off-by: Ilya Dryomov --- fs/ceph/addr.c | 20 +++++++------- fs/ceph/caps.c | 24 ++++++++--------- fs/ceph/file.c | 13 ++++----- fs/ceph/inode.c | 4 +-- fs/ceph/locks.c | 22 ++++----------- fs/ceph/mds_client.c | 3 ++- fs/ceph/mds_client.h | 2 +- fs/ceph/snap.c | 2 +- fs/ceph/super.h | 64 +++++++++++++++++++++++--------------------- fs/ceph/xattr.c | 2 +- 10 files changed, 74 insertions(+), 82 deletions(-) diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index 0a86f672cc09..61bd6d92ff25 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -2561,7 +2561,8 @@ int ceph_pool_perm_check(struct inode *inode, int need) struct ceph_inode_info *ci = ceph_inode(inode); struct ceph_string *pool_ns; s64 pool; - int ret, flags; + int ret; + unsigned long flags; /* Only need to do this for regular files */ if (!S_ISREG(inode->i_mode)) @@ -2603,20 +2604,19 @@ check: if (ret < 0) return ret; - flags = CEPH_I_POOL_PERM; - if (ret & POOL_READ) - flags |= CEPH_I_POOL_RD; - if (ret & POOL_WRITE) - flags |= CEPH_I_POOL_WR; - spin_lock(&ci->i_ceph_lock); if (pool == ci->i_layout.pool_id && pool_ns == rcu_dereference_raw(ci->i_layout.pool_ns)) { - ci->i_ceph_flags |= flags; - } else { + set_bit(CEPH_I_POOL_PERM_BIT, &ci->i_ceph_flags); + if (ret & POOL_READ) + set_bit(CEPH_I_POOL_RD_BIT, &ci->i_ceph_flags); + if (ret & POOL_WRITE) + set_bit(CEPH_I_POOL_WR_BIT, &ci->i_ceph_flags); + } else { pool = ci->i_layout.pool_id; - flags = ci->i_ceph_flags; } + /* Re-read flags under the lock so check: sees the updated bits. */ + flags = ci->i_ceph_flags; spin_unlock(&ci->i_ceph_lock); goto check; } diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index d51454e995a8..cb9e78b713d9 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -549,7 +549,7 @@ static void __cap_delay_requeue_front(struct ceph_mds_client *mdsc, doutc(mdsc->fsc->client, "%p %llx.%llx\n", inode, ceph_vinop(inode)); spin_lock(&mdsc->cap_delay_lock); - ci->i_ceph_flags |= CEPH_I_FLUSH; + set_bit(CEPH_I_FLUSH_BIT, &ci->i_ceph_flags); if (!list_empty(&ci->i_cap_delay_list)) list_del_init(&ci->i_cap_delay_list); list_add(&ci->i_cap_delay_list, &mdsc->cap_delay_list); @@ -1409,7 +1409,7 @@ static void __prep_cap(struct cap_msg_args *arg, struct ceph_cap *cap, ceph_cap_string(revoking)); BUG_ON((retain & CEPH_CAP_PIN) == 0); - ci->i_ceph_flags &= ~CEPH_I_FLUSH; + clear_bit(CEPH_I_FLUSH_BIT, &ci->i_ceph_flags); cap->issued &= retain; /* drop bits we don't want */ /* @@ -1666,7 +1666,7 @@ static void __ceph_flush_snaps(struct ceph_inode_info *ci, last_tid = capsnap->cap_flush.tid; } - ci->i_ceph_flags &= ~CEPH_I_FLUSH_SNAPS; + clear_bit(CEPH_I_FLUSH_SNAPS_BIT, &ci->i_ceph_flags); while (first_tid <= last_tid) { struct ceph_cap *cap = ci->i_auth_cap; @@ -2026,7 +2026,7 @@ void ceph_check_caps(struct ceph_inode_info *ci, int flags) spin_lock(&ci->i_ceph_lock); if (ci->i_ceph_flags & CEPH_I_ASYNC_CREATE) { - ci->i_ceph_flags |= CEPH_I_ASYNC_CHECK_CAPS; + set_bit(CEPH_I_ASYNC_CHECK_CAPS_BIT, &ci->i_ceph_flags); /* Don't send messages until we get async create reply */ spin_unlock(&ci->i_ceph_lock); @@ -2577,7 +2577,7 @@ static void __kick_flushing_caps(struct ceph_mds_client *mdsc, if (ci->i_ceph_flags & CEPH_I_ASYNC_CREATE) return; - ci->i_ceph_flags &= ~CEPH_I_KICK_FLUSH; + clear_bit(CEPH_I_KICK_FLUSH_BIT, &ci->i_ceph_flags); list_for_each_entry_reverse(cf, &ci->i_cap_flush_list, i_list) { if (cf->is_capsnap) { @@ -2686,7 +2686,7 @@ void ceph_early_kick_flushing_caps(struct ceph_mds_client *mdsc, __kick_flushing_caps(mdsc, session, ci, oldest_flush_tid); } else { - ci->i_ceph_flags |= CEPH_I_KICK_FLUSH; + set_bit(CEPH_I_KICK_FLUSH_BIT, &ci->i_ceph_flags); } spin_unlock(&ci->i_ceph_lock); @@ -2829,7 +2829,7 @@ again: spin_lock(&ci->i_ceph_lock); if ((flags & CHECK_FILELOCK) && - (ci->i_ceph_flags & CEPH_I_ERROR_FILELOCK)) { + test_bit(CEPH_I_ERROR_FILELOCK_BIT, &ci->i_ceph_flags)) { doutc(cl, "%p %llx.%llx error filelock\n", inode, ceph_vinop(inode)); ret = -EIO; @@ -3207,7 +3207,7 @@ static int ceph_try_drop_cap_snap(struct ceph_inode_info *ci, BUG_ON(capsnap->cap_flush.tid > 0); ceph_put_snap_context(capsnap->context); if (!list_is_last(&capsnap->ci_item, &ci->i_cap_snaps)) - ci->i_ceph_flags |= CEPH_I_FLUSH_SNAPS; + set_bit(CEPH_I_FLUSH_SNAPS_BIT, &ci->i_ceph_flags); list_del(&capsnap->ci_item); ceph_put_cap_snap(capsnap); @@ -3396,7 +3396,7 @@ void ceph_put_wrbuffer_cap_refs(struct ceph_inode_info *ci, int nr, if (ceph_try_drop_cap_snap(ci, capsnap)) { put++; } else { - ci->i_ceph_flags |= CEPH_I_FLUSH_SNAPS; + set_bit(CEPH_I_FLUSH_SNAPS_BIT, &ci->i_ceph_flags); flush_snaps = true; } } @@ -3648,7 +3648,7 @@ static void handle_cap_grant(struct inode *inode, if (ci->i_layout.pool_id != old_pool || extra_info->pool_ns != old_ns) - ci->i_ceph_flags &= ~CEPH_I_POOL_PERM; + clear_bit(CEPH_I_POOL_PERM_BIT, &ci->i_ceph_flags); extra_info->pool_ns = old_ns; @@ -4815,7 +4815,7 @@ int ceph_drop_caps_for_unlink(struct inode *inode) doutc(mdsc->fsc->client, "%p %llx.%llx\n", inode, ceph_vinop(inode)); spin_lock(&mdsc->cap_delay_lock); - ci->i_ceph_flags |= CEPH_I_FLUSH; + set_bit(CEPH_I_FLUSH_BIT, &ci->i_ceph_flags); if (!list_empty(&ci->i_cap_delay_list)) list_del_init(&ci->i_cap_delay_list); list_add_tail(&ci->i_cap_delay_list, @@ -5080,7 +5080,7 @@ int ceph_purge_inode_cap(struct inode *inode, struct ceph_cap *cap, bool *invali if (atomic_read(&ci->i_filelock_ref) > 0) { /* make further file lock syscall return -EIO */ - ci->i_ceph_flags |= CEPH_I_ERROR_FILELOCK; + set_bit(CEPH_I_ERROR_FILELOCK_BIT, &ci->i_ceph_flags); pr_warn_ratelimited_client(cl, " dropping file locks for %p %llx.%llx\n", inode, ceph_vinop(inode)); diff --git a/fs/ceph/file.c b/fs/ceph/file.c index d54d71669176..7ca9f60fb0e5 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -598,12 +598,12 @@ static void wake_async_create_waiters(struct inode *inode, spin_lock(&ci->i_ceph_lock); if (ci->i_ceph_flags & CEPH_I_ASYNC_CREATE) { - clear_and_wake_up_bit(CEPH_ASYNC_CREATE_BIT, &ci->i_ceph_flags); + /* Serialized by i_ceph_lock; the two ops touch different bits. */ + clear_and_wake_up_bit(CEPH_I_ASYNC_CREATE_BIT, &ci->i_ceph_flags); - if (ci->i_ceph_flags & CEPH_I_ASYNC_CHECK_CAPS) { - ci->i_ceph_flags &= ~CEPH_I_ASYNC_CHECK_CAPS; + if (test_and_clear_bit(CEPH_I_ASYNC_CHECK_CAPS_BIT, + &ci->i_ceph_flags)) check_cap = true; - } } ceph_kick_flushing_inode_caps(session, ci); spin_unlock(&ci->i_ceph_lock); @@ -766,7 +766,8 @@ static int ceph_finish_async_create(struct inode *dir, struct inode *inode, * that point and don't worry about setting * CEPH_I_ASYNC_CREATE. */ - ceph_inode(inode)->i_ceph_flags = CEPH_I_ASYNC_CREATE; + set_bit(CEPH_I_ASYNC_CREATE_BIT, + &ceph_inode(inode)->i_ceph_flags); unlock_new_inode(inode); } if (d_in_lookup(dentry) || d_really_is_negative(dentry)) { @@ -2482,7 +2483,7 @@ retry_snap: if ((got & (CEPH_CAP_FILE_BUFFER|CEPH_CAP_FILE_LAZYIO)) == 0 || (iocb->ki_flags & IOCB_DIRECT) || (fi->flags & CEPH_F_SYNC) || - (ci->i_ceph_flags & CEPH_I_ERROR_WRITE)) { + test_bit(CEPH_I_ERROR_WRITE_BIT, &ci->i_ceph_flags)) { struct ceph_snap_context *snapc; struct iov_iter data; diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index 22c7da1ea61c..4871d7ab2730 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -1180,7 +1180,7 @@ int ceph_fill_inode(struct inode *inode, struct page *locked_page, rcu_assign_pointer(ci->i_layout.pool_ns, pool_ns); if (ci->i_layout.pool_id != old_pool || pool_ns != old_ns) - ci->i_ceph_flags &= ~CEPH_I_POOL_PERM; + clear_bit(CEPH_I_POOL_PERM_BIT, &ci->i_ceph_flags); pool_ns = old_ns; @@ -3240,7 +3240,7 @@ void ceph_inode_shutdown(struct inode *inode) bool invalidate = false; spin_lock(&ci->i_ceph_lock); - ci->i_ceph_flags |= CEPH_I_SHUTDOWN; + set_bit(CEPH_I_SHUTDOWN_BIT, &ci->i_ceph_flags); p = rb_first(&ci->i_caps); while (p) { struct ceph_cap *cap = rb_entry(p, struct ceph_cap, ci_node); diff --git a/fs/ceph/locks.c b/fs/ceph/locks.c index dd764f9c64b9..c4ff2266bb94 100644 --- a/fs/ceph/locks.c +++ b/fs/ceph/locks.c @@ -57,9 +57,7 @@ static void ceph_fl_release_lock(struct file_lock *fl) ci = ceph_inode(inode); if (atomic_dec_and_test(&ci->i_filelock_ref)) { /* clear error when all locks are released */ - spin_lock(&ci->i_ceph_lock); - ci->i_ceph_flags &= ~CEPH_I_ERROR_FILELOCK; - spin_unlock(&ci->i_ceph_lock); + clear_bit(CEPH_I_ERROR_FILELOCK_BIT, &ci->i_ceph_flags); } fl->fl_u.ceph.inode = NULL; iput(inode); @@ -271,15 +269,10 @@ int ceph_lock(struct file *file, int cmd, struct file_lock *fl) else if (IS_SETLKW(cmd)) wait = 1; - spin_lock(&ci->i_ceph_lock); - if (ci->i_ceph_flags & CEPH_I_ERROR_FILELOCK) { - err = -EIO; - } - spin_unlock(&ci->i_ceph_lock); - if (err < 0) { + if (test_bit(CEPH_I_ERROR_FILELOCK_BIT, &ci->i_ceph_flags)) { if (op == CEPH_MDS_OP_SETFILELOCK && lock_is_unlock(fl)) posix_lock_file(file, fl, NULL); - return err; + return -EIO; } if (lock_is_read(fl)) @@ -331,15 +324,10 @@ int ceph_flock(struct file *file, int cmd, struct file_lock *fl) doutc(cl, "fl_file: %p\n", fl->c.flc_file); - spin_lock(&ci->i_ceph_lock); - if (ci->i_ceph_flags & CEPH_I_ERROR_FILELOCK) { - err = -EIO; - } - spin_unlock(&ci->i_ceph_lock); - if (err < 0) { + if (test_bit(CEPH_I_ERROR_FILELOCK_BIT, &ci->i_ceph_flags)) { if (lock_is_unlock(fl)) locks_lock_file_wait(file, fl); - return err; + return -EIO; } if (IS_SETLKW(cmd)) diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index ed17e0023705..53f1012a9e7d 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -3657,7 +3657,8 @@ static void __do_request(struct ceph_mds_client *mdsc, spin_lock(&ci->i_ceph_lock); cap = ci->i_auth_cap; - if (ci->i_ceph_flags & CEPH_I_ASYNC_CREATE && mds != cap->mds) { + if (test_bit(CEPH_I_ASYNC_CREATE_BIT, &ci->i_ceph_flags) && + mds != cap->mds) { doutc(cl, "session changed for auth cap %d -> %d\n", cap->session->s_mds, session->s_mds); diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h index 4e6c87f8414c..d873e784b025 100644 --- a/fs/ceph/mds_client.h +++ b/fs/ceph/mds_client.h @@ -670,7 +670,7 @@ static inline int ceph_wait_on_async_create(struct inode *inode) { struct ceph_inode_info *ci = ceph_inode(inode); - return wait_on_bit(&ci->i_ceph_flags, CEPH_ASYNC_CREATE_BIT, + return wait_on_bit(&ci->i_ceph_flags, CEPH_I_ASYNC_CREATE_BIT, TASK_KILLABLE); } diff --git a/fs/ceph/snap.c b/fs/ceph/snap.c index 52b4c2684f92..9b79a5eaca93 100644 --- a/fs/ceph/snap.c +++ b/fs/ceph/snap.c @@ -700,7 +700,7 @@ int __ceph_finish_cap_snap(struct ceph_inode_info *ci, return 0; } - ci->i_ceph_flags |= CEPH_I_FLUSH_SNAPS; + set_bit(CEPH_I_FLUSH_SNAPS_BIT, &ci->i_ceph_flags); doutc(cl, "%p %llx.%llx cap_snap %p snapc %p %llu %s s=%llu\n", inode, ceph_vinop(inode), capsnap, capsnap->context, capsnap->context->seq, ceph_cap_string(capsnap->dirty), diff --git a/fs/ceph/super.h b/fs/ceph/super.h index afc89ce91804..cb45a59dbb19 100644 --- a/fs/ceph/super.h +++ b/fs/ceph/super.h @@ -665,23 +665,34 @@ static inline struct inode *ceph_find_inode(struct super_block *sb, /* * Ceph inode. */ -#define CEPH_I_DIR_ORDERED (1 << 0) /* dentries in dir are ordered */ -#define CEPH_I_FLUSH (1 << 2) /* do not delay flush of dirty metadata */ -#define CEPH_I_POOL_PERM (1 << 3) /* pool rd/wr bits are valid */ -#define CEPH_I_POOL_RD (1 << 4) /* can read from pool */ -#define CEPH_I_POOL_WR (1 << 5) /* can write to pool */ -#define CEPH_I_SEC_INITED (1 << 6) /* security initialized */ -#define CEPH_I_KICK_FLUSH (1 << 7) /* kick flushing caps */ -#define CEPH_I_FLUSH_SNAPS (1 << 8) /* need flush snapss */ -#define CEPH_I_ERROR_WRITE (1 << 9) /* have seen write errors */ -#define CEPH_I_ERROR_FILELOCK (1 << 10) /* have seen file lock errors */ -#define CEPH_I_ODIRECT_BIT (11) /* inode in direct I/O mode */ -#define CEPH_I_ODIRECT (1 << CEPH_I_ODIRECT_BIT) -#define CEPH_ASYNC_CREATE_BIT (12) /* async create in flight for this */ -#define CEPH_I_ASYNC_CREATE (1 << CEPH_ASYNC_CREATE_BIT) -#define CEPH_I_SHUTDOWN (1 << 13) /* inode is no longer usable */ -#define CEPH_I_ASYNC_CHECK_CAPS (1 << 14) /* check caps immediately after async - creating finishes */ +#define CEPH_I_DIR_ORDERED_BIT (0) /* dentries in dir are ordered */ + /* bit 1 historically unused */ +#define CEPH_I_FLUSH_BIT (2) /* do not delay flush of dirty metadata */ +#define CEPH_I_POOL_PERM_BIT (3) /* pool rd/wr bits are valid */ +#define CEPH_I_POOL_RD_BIT (4) /* can read from pool */ +#define CEPH_I_POOL_WR_BIT (5) /* can write to pool */ +#define CEPH_I_SEC_INITED_BIT (6) /* security initialized */ +#define CEPH_I_KICK_FLUSH_BIT (7) /* kick flushing caps */ +#define CEPH_I_FLUSH_SNAPS_BIT (8) /* need flush snaps */ +#define CEPH_I_ERROR_WRITE_BIT (9) /* have seen write errors */ +#define CEPH_I_ERROR_FILELOCK_BIT (10) /* have seen file lock errors */ +#define CEPH_I_ODIRECT_BIT (11) /* inode in direct I/O mode */ +#define CEPH_I_ASYNC_CREATE_BIT (12) /* async create in flight for this */ +#define CEPH_I_SHUTDOWN_BIT (13) /* inode is no longer usable */ +#define CEPH_I_ASYNC_CHECK_CAPS_BIT (14) /* check caps after async creating finishes */ + +#define CEPH_I_DIR_ORDERED (1 << CEPH_I_DIR_ORDERED_BIT) +#define CEPH_I_FLUSH (1 << CEPH_I_FLUSH_BIT) +#define CEPH_I_POOL_PERM (1 << CEPH_I_POOL_PERM_BIT) +#define CEPH_I_POOL_RD (1 << CEPH_I_POOL_RD_BIT) +#define CEPH_I_POOL_WR (1 << CEPH_I_POOL_WR_BIT) +#define CEPH_I_SEC_INITED (1 << CEPH_I_SEC_INITED_BIT) +#define CEPH_I_KICK_FLUSH (1 << CEPH_I_KICK_FLUSH_BIT) +#define CEPH_I_FLUSH_SNAPS (1 << CEPH_I_FLUSH_SNAPS_BIT) +#define CEPH_I_ERROR_FILELOCK (1 << CEPH_I_ERROR_FILELOCK_BIT) +#define CEPH_I_ODIRECT (1 << CEPH_I_ODIRECT_BIT) +#define CEPH_I_ASYNC_CREATE (1 << CEPH_I_ASYNC_CREATE_BIT) +#define CEPH_I_SHUTDOWN (1 << CEPH_I_SHUTDOWN_BIT) /* * Masks of ceph inode work. @@ -694,27 +705,18 @@ static inline struct inode *ceph_find_inode(struct super_block *sb, /* * We set the ERROR_WRITE bit when we start seeing write errors on an inode - * and then clear it when they start succeeding. Note that we do a lockless - * check first, and only take the lock if it looks like it needs to be changed. - * The write submission code just takes this as a hint, so we're not too - * worried if a few slip through in either direction. + * and then clear it when they start succeeding. The write submission code + * just takes this as a hint, so we're not too worried if a few slip through + * in either direction. */ static inline void ceph_set_error_write(struct ceph_inode_info *ci) { - if (!(READ_ONCE(ci->i_ceph_flags) & CEPH_I_ERROR_WRITE)) { - spin_lock(&ci->i_ceph_lock); - ci->i_ceph_flags |= CEPH_I_ERROR_WRITE; - spin_unlock(&ci->i_ceph_lock); - } + set_bit(CEPH_I_ERROR_WRITE_BIT, &ci->i_ceph_flags); } static inline void ceph_clear_error_write(struct ceph_inode_info *ci) { - if (READ_ONCE(ci->i_ceph_flags) & CEPH_I_ERROR_WRITE) { - spin_lock(&ci->i_ceph_lock); - ci->i_ceph_flags &= ~CEPH_I_ERROR_WRITE; - spin_unlock(&ci->i_ceph_lock); - } + clear_bit(CEPH_I_ERROR_WRITE_BIT, &ci->i_ceph_flags); } static inline void __ceph_dir_set_complete(struct ceph_inode_info *ci, diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c index e773be07f767..860fc8e1867d 100644 --- a/fs/ceph/xattr.c +++ b/fs/ceph/xattr.c @@ -1054,7 +1054,7 @@ handle_non_vxattrs: if (current->journal_info && !strncmp(name, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN) && security_ismaclabel(name + XATTR_SECURITY_PREFIX_LEN)) - ci->i_ceph_flags |= CEPH_I_SEC_INITED; + set_bit(CEPH_I_SEC_INITED_BIT, &ci->i_ceph_flags); out: spin_unlock(&ci->i_ceph_lock); return err; From 248e514000d552095025de0473165becfe8e810d Mon Sep 17 00:00:00 2001 From: Alex Markuze Date: Tue, 28 Apr 2026 07:41:33 +0000 Subject: [PATCH 136/297] ceph: use proper endian conversion for flock_len in reconnect Replace the __force __le32 cast with cpu_to_le32() for the flock_len field in reconnect_caps_cb(). The old code used a type-system bypass to silence sparse; the new form uses the proper endian conversion macro. Also switch from a raw bitmask test against i_ceph_flags to test_bit() on the named CEPH_I_ERROR_FILELOCK_BIT, which is the correct accessor for the unsigned long flags field after the bit-position conversion. Remove the now-unused CEPH_I_ERROR_FILELOCK mask define since all callers use the _BIT form with test_bit/set_bit/clear_bit. Signed-off-by: Alex Markuze Reviewed-by: Viacheslav Dubeyko Signed-off-by: Viacheslav Dubeyko Signed-off-by: Ilya Dryomov --- fs/ceph/mds_client.c | 5 +++-- fs/ceph/super.h | 1 - 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 53f1012a9e7d..d9543399b129 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -4747,8 +4747,9 @@ static int reconnect_caps_cb(struct inode *inode, int mds, void *arg) rec.v2.issued = cpu_to_le32(cap->issued); rec.v2.snaprealm = cpu_to_le64(ci->i_snap_realm->ino); rec.v2.pathbase = cpu_to_le64(path_info.vino.ino); - rec.v2.flock_len = (__force __le32) - ((ci->i_ceph_flags & CEPH_I_ERROR_FILELOCK) ? 0 : 1); + rec.v2.flock_len = cpu_to_le32( + test_bit(CEPH_I_ERROR_FILELOCK_BIT, + &ci->i_ceph_flags) ? 0 : 1); } else { struct timespec64 ts; diff --git a/fs/ceph/super.h b/fs/ceph/super.h index cb45a59dbb19..8afc6f3a10da 100644 --- a/fs/ceph/super.h +++ b/fs/ceph/super.h @@ -689,7 +689,6 @@ static inline struct inode *ceph_find_inode(struct super_block *sb, #define CEPH_I_SEC_INITED (1 << CEPH_I_SEC_INITED_BIT) #define CEPH_I_KICK_FLUSH (1 << CEPH_I_KICK_FLUSH_BIT) #define CEPH_I_FLUSH_SNAPS (1 << CEPH_I_FLUSH_SNAPS_BIT) -#define CEPH_I_ERROR_FILELOCK (1 << CEPH_I_ERROR_FILELOCK_BIT) #define CEPH_I_ODIRECT (1 << CEPH_I_ODIRECT_BIT) #define CEPH_I_ASYNC_CREATE (1 << CEPH_I_ASYNC_CREATE_BIT) #define CEPH_I_SHUTDOWN (1 << CEPH_I_SHUTDOWN_BIT) From 39fe3031589386ae7ce3fd7132beb6bb229e22ce Mon Sep 17 00:00:00 2001 From: Alex Markuze Date: Tue, 28 Apr 2026 07:43:03 +0000 Subject: [PATCH 137/297] ceph: harden send_mds_reconnect and handle active-MDS peer reset Change send_mds_reconnect() to return an error code so callers can detect and report reconnect failures instead of silently ignoring them. Add early bailout checks for sessions that are already closed, rejected, or unregistered, which avoids sending reconnect messages for sessions that can no longer be recovered. The early -ESTALE and -ENOENT bailouts use a separate fail_return label that skips the pr_err_client diagnostic, since these codes indicate expected concurrent-teardown races rather than genuine reconnect build failures. Move the "reconnect start" log after the early-bailout checks so it only appears for sessions that actually proceed with reconnect. Save the prior session state before transitioning to RECONNECTING, and restore it in the failure path. Without this, a transient build or encoding failure (-ENOMEM, -ENOSPC) strands the session in RECONNECTING indefinitely because check_new_map() only retries sessions in RESTARTING state. Rewrite mds_peer_reset() to handle the case where the MDS is past its RECONNECT phase (i.e. active). An active MDS rejects CLIENT_RECONNECT messages because it only accepts them during its own RECONNECT window after restart. Previously, the client would send a doomed reconnect that the MDS would reject or ignore. Now, the client tears the session down locally and lets new requests re-open a fresh session, which is the correct recovery for this scenario. The RECONNECTING state is handled on the same teardown path, since the MDS will reject reconnect attempts from an active client regardless of the session's local state. Add explicit cases for CLOSED and REJECTED session states in mds_peer_reset() since these are terminal states where a connection drop is expected behavior. The session teardown path in mds_peer_reset() follows the established drop-and-reacquire locking pattern from check_new_map(): take mdsc->mutex for session unregistration, release it, then take s->s_mutex separately for cleanup. This avoids introducing a new simultaneous lock nesting pattern. Log reconnect failures from check_new_map() and mds_peer_reset() at pr_warn level rather than pr_err, since return codes like -ESTALE (closed/rejected session) and -ENOENT (unregistered session) are expected during concurrent teardown. Log dropped messages for unregistered sessions via doutc() (dynamic debug) rather than pr_info, as post-reset message arrival is routine and does not warrant unconditional logging. Signed-off-by: Alex Markuze Reviewed-by: Viacheslav Dubeyko Signed-off-by: Viacheslav Dubeyko Signed-off-by: Ilya Dryomov --- fs/ceph/mds_client.c | 180 +++++++++++++++++++++++++++++++++++++++---- 1 file changed, 164 insertions(+), 16 deletions(-) diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index d9543399b129..249419c17d3c 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -4470,9 +4470,14 @@ skip_cap_auths: break; case CEPH_SESSION_REJECT: - WARN_ON(session->s_state != CEPH_MDS_SESSION_OPENING); - pr_info_client(cl, "mds%d rejected session\n", - session->s_mds); + WARN_ON(session->s_state != CEPH_MDS_SESSION_OPENING && + session->s_state != CEPH_MDS_SESSION_RECONNECTING); + if (session->s_state == CEPH_MDS_SESSION_RECONNECTING) + pr_info_client(cl, "mds%d reconnect rejected\n", + session->s_mds); + else + pr_info_client(cl, "mds%d rejected session\n", + session->s_mds); session->s_state = CEPH_MDS_SESSION_REJECTED; cleanup_session_requests(mdsc, session); remove_session_caps(session); @@ -4732,6 +4737,14 @@ static int reconnect_caps_cb(struct inode *inode, int mds, void *arg) cap->mseq = 0; /* and migrate_seq */ cap->cap_gen = atomic_read(&cap->session->s_cap_gen); + /* + * Note: CEPH_I_ERROR_FILELOCK is not set during reconnect. + * Instead, locks are submitted for best-effort MDS reclaim + * via the flock_len field below. If reclaim fails (e.g., + * another client grabbed a conflicting lock), future lock + * operations will fail and set the error flag at that point. + */ + /* These are lost when the session goes away */ if (S_ISDIR(inode->i_mode)) { if (cap->issued & CEPH_CAP_DIR_CREATE) { @@ -4946,20 +4959,19 @@ fail: * * This is a relatively heavyweight operation, but it's rare. */ -static void send_mds_reconnect(struct ceph_mds_client *mdsc, - struct ceph_mds_session *session) +static int send_mds_reconnect(struct ceph_mds_client *mdsc, + struct ceph_mds_session *session) { struct ceph_client *cl = mdsc->fsc->client; struct ceph_msg *reply; int mds = session->s_mds; int err = -ENOMEM; + int old_state; struct ceph_reconnect_state recon_state = { .session = session, }; LIST_HEAD(dispose); - pr_info_client(cl, "mds%d reconnect start\n", mds); - recon_state.pagelist = ceph_pagelist_alloc(GFP_NOFS); if (!recon_state.pagelist) goto fail_nopagelist; @@ -4968,9 +4980,37 @@ static void send_mds_reconnect(struct ceph_mds_client *mdsc, if (!reply) goto fail_nomsg; - xa_destroy(&session->s_delegated_inos); - mutex_lock(&session->s_mutex); + + /* Serialized by s_mutex against concurrent ceph_get_deleg_ino(). */ + xa_destroy(&session->s_delegated_inos); + if (session->s_state == CEPH_MDS_SESSION_CLOSED || + session->s_state == CEPH_MDS_SESSION_REJECTED) { + pr_info_client(cl, "mds%d skipping reconnect, session %s\n", + mds, + ceph_session_state_name(session->s_state)); + mutex_unlock(&session->s_mutex); + ceph_msg_put(reply); + err = -ESTALE; + goto fail_return; + } + + /* s_mutex -> mdsc->mutex matches cleanup_session_requests() order. */ + mutex_lock(&mdsc->mutex); + if (mds >= mdsc->max_sessions || mdsc->sessions[mds] != session) { + mutex_unlock(&mdsc->mutex); + pr_info_client(cl, + "mds%d skipping reconnect, session unregistered\n", + mds); + mutex_unlock(&session->s_mutex); + ceph_msg_put(reply); + err = -ENOENT; + goto fail_return; + } + mutex_unlock(&mdsc->mutex); + + pr_info_client(cl, "mds%d reconnect start\n", mds); + old_state = session->s_state; session->s_state = CEPH_MDS_SESSION_RECONNECTING; session->s_seq = 0; @@ -5100,7 +5140,7 @@ static void send_mds_reconnect(struct ceph_mds_client *mdsc, up_read(&mdsc->snap_rwsem); ceph_pagelist_release(recon_state.pagelist); - return; + return 0; fail_clear_cap_reconnect: spin_lock(&session->s_cap_lock); @@ -5109,13 +5149,29 @@ fail_clear_cap_reconnect: fail: ceph_msg_put(reply); up_read(&mdsc->snap_rwsem); + /* + * Restore prior session state so map-driven reconnect logic + * (check_new_map) can retry. Without this, a transient build + * failure strands the session in RECONNECTING indefinitely. + */ + session->s_state = old_state; mutex_unlock(&session->s_mutex); fail_nomsg: ceph_pagelist_release(recon_state.pagelist); fail_nopagelist: pr_err_client(cl, "error %d preparing reconnect for mds%d\n", err, mds); - return; + return err; + +fail_return: + /* + * Early-exit path for expected concurrent-teardown races + * (-ESTALE for closed/rejected sessions, -ENOENT for + * unregistered sessions). Skip the pr_err_client diagnostic + * since these are not genuine reconnect build failures. + */ + ceph_pagelist_release(recon_state.pagelist); + return err; } @@ -5196,9 +5252,15 @@ static void check_new_map(struct ceph_mds_client *mdsc, */ if (s->s_state == CEPH_MDS_SESSION_RESTARTING && newstate >= CEPH_MDS_STATE_RECONNECT) { + int rc; + mutex_unlock(&mdsc->mutex); clear_bit(i, targets); - send_mds_reconnect(mdsc, s); + rc = send_mds_reconnect(mdsc, s); + if (rc) + pr_warn_client(cl, + "mds%d reconnect failed: %d\n", + i, rc); mutex_lock(&mdsc->mutex); } @@ -5262,7 +5324,11 @@ static void check_new_map(struct ceph_mds_client *mdsc, } doutc(cl, "send reconnect to export target mds.%d\n", i); mutex_unlock(&mdsc->mutex); - send_mds_reconnect(mdsc, s); + err = send_mds_reconnect(mdsc, s); + if (err) + pr_warn_client(cl, + "mds%d export target reconnect failed: %d\n", + i, err); ceph_put_mds_session(s); mutex_lock(&mdsc->mutex); } @@ -6350,12 +6416,92 @@ static void mds_peer_reset(struct ceph_connection *con) { struct ceph_mds_session *s = con->private; struct ceph_mds_client *mdsc = s->s_mdsc; + int session_state; pr_warn_client(mdsc->fsc->client, "mds%d closed our session\n", s->s_mds); - if (READ_ONCE(mdsc->fsc->mount_state) != CEPH_MOUNT_FENCE_IO && - ceph_mdsmap_get_state(mdsc->mdsmap, s->s_mds) >= CEPH_MDS_STATE_RECONNECT) - send_mds_reconnect(mdsc, s); + + if (READ_ONCE(mdsc->fsc->mount_state) == CEPH_MOUNT_FENCE_IO || + ceph_mdsmap_get_state(mdsc->mdsmap, s->s_mds) < CEPH_MDS_STATE_RECONNECT) + return; + + /* + * Only reconnect if MDS is in its RECONNECT phase. An MDS past + * RECONNECT (REJOIN, CLIENTREPLAY, ACTIVE) will reject reconnect + * attempts, so those states fall through to session teardown below. + */ + if (ceph_mdsmap_get_state(mdsc->mdsmap, s->s_mds) == CEPH_MDS_STATE_RECONNECT) { + int rc = send_mds_reconnect(mdsc, s); + + if (rc) + pr_warn_client(mdsc->fsc->client, + "mds%d reconnect failed: %d\n", + s->s_mds, rc); + return; + } + + /* + * MDS is active (past RECONNECT). It will not accept a + * CLIENT_RECONNECT from us, so tear the session down locally + * and let new requests re-open a fresh session. + * + * Snapshot session state with READ_ONCE, then revalidate under + * mdsc->mutex before acting. The subsequent mdsc->mutex + * section rechecks s_state to catch concurrent transitions, so + * the lockless snapshot here is safe. s->s_mutex is taken + * separately for cleanup after unregistration, which avoids + * introducing a new s->s_mutex + mdsc->mutex nesting. + */ + session_state = READ_ONCE(s->s_state); + + switch (session_state) { + case CEPH_MDS_SESSION_RESTARTING: + case CEPH_MDS_SESSION_RECONNECTING: + case CEPH_MDS_SESSION_CLOSING: + case CEPH_MDS_SESSION_OPEN: + case CEPH_MDS_SESSION_HUNG: + case CEPH_MDS_SESSION_OPENING: + mutex_lock(&mdsc->mutex); + if (s->s_mds >= mdsc->max_sessions || + mdsc->sessions[s->s_mds] != s || + s->s_state != session_state) { + pr_info_client(mdsc->fsc->client, + "mds%d state changed to %s during peer reset\n", + s->s_mds, + ceph_session_state_name(s->s_state)); + mutex_unlock(&mdsc->mutex); + return; + } + + ceph_get_mds_session(s); + s->s_state = CEPH_MDS_SESSION_CLOSED; + __unregister_session(mdsc, s); + __wake_requests(mdsc, &s->s_waiting); + mutex_unlock(&mdsc->mutex); + + mutex_lock(&s->s_mutex); + cleanup_session_requests(mdsc, s); + remove_session_caps(s); + mutex_unlock(&s->s_mutex); + + wake_up_all(&mdsc->session_close_wq); + + mutex_lock(&mdsc->mutex); + kick_requests(mdsc, s->s_mds); + mutex_unlock(&mdsc->mutex); + + ceph_put_mds_session(s); + break; + case CEPH_MDS_SESSION_CLOSED: + case CEPH_MDS_SESSION_REJECTED: + break; + default: + pr_warn_client(mdsc->fsc->client, + "mds%d peer reset in unexpected state %s\n", + s->s_mds, + ceph_session_state_name(session_state)); + break; + } } static void mds_dispatch(struct ceph_connection *con, struct ceph_msg *msg) @@ -6367,6 +6513,8 @@ static void mds_dispatch(struct ceph_connection *con, struct ceph_msg *msg) mutex_lock(&mdsc->mutex); if (__verify_registered_session(mdsc, s) < 0) { + doutc(cl, "dropping tid %llu from unregistered session %d\n", + le64_to_cpu(msg->hdr.tid), s->s_mds); mutex_unlock(&mdsc->mutex); goto out; } From ebbbab66bd74dbd213d51afc3b029dc8b109ee47 Mon Sep 17 00:00:00 2001 From: Alex Markuze Date: Thu, 7 May 2026 08:45:27 +0000 Subject: [PATCH 138/297] ceph: add diagnostic timeout loop to wait_caps_flush() Convert wait_caps_flush() from a silent indefinite wait into a diagnostic wait loop that periodically dumps pending cap flush state. The underlying wait semantics remain intact: callers still wait until the requested cap flushes complete. The difference is that long stalls now produce actionable diagnostics instead of looking like a silent hang. CEPH_CAP_FLUSH_MAX_DUMP_ENTRIES limits the number of entries emitted per diagnostic dump, and CEPH_CAP_FLUSH_MAX_DUMP_ITERS limits the number of timed diagnostic dumps before the wait continues silently. When more entries exist than the per-dump limit, a truncation count is reported. When the dump iteration limit is reached, a final suppression message is emitted so the transition to silence is explicit. The diagnostic dump collects flush entry data under cap_dirty_lock into a bounded on-stack array, then prints after releasing the lock. This avoids holding the spinlock across printk calls. A null cf->ci on the global flush list indicates a bug since all cap_flush entries are initialized with a valid ci before being added. Signal this with WARN_ON_ONCE while still printing enough context for debugging. READ_ONCE is used for the i_last_cap_flush_ack field, which is read outside the inode lock domain. Flush tids are monotonically increasing and acks are processed in order under i_ceph_lock, so the latest ack tid is always the most recently written value. Add a ci pointer to struct ceph_cap_flush so that the diagnostic dump can identify which inode each pending flush belongs to. The new i_last_cap_flush_ack field tracks the latest acknowledged flush tid per inode for diagnostic correlation. This improves reset-drain observability and is also useful for existing sync and writeback troubleshooting paths. Signed-off-by: Alex Markuze Reviewed-by: Viacheslav Dubeyko Signed-off-by: Viacheslav Dubeyko Signed-off-by: Ilya Dryomov --- fs/ceph/caps.c | 10 +++++ fs/ceph/inode.c | 1 + fs/ceph/mds_client.c | 101 +++++++++++++++++++++++++++++++++++++++++-- fs/ceph/mds_client.h | 3 ++ fs/ceph/super.h | 6 +++ 5 files changed, 117 insertions(+), 4 deletions(-) diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index cb9e78b713d9..4b37d9ffdf7f 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -1648,6 +1648,7 @@ static void __ceph_flush_snaps(struct ceph_inode_info *ci, spin_lock(&mdsc->cap_dirty_lock); capsnap->cap_flush.tid = ++mdsc->last_cap_flush_tid; + capsnap->cap_flush.ci = ci; list_add_tail(&capsnap->cap_flush.g_list, &mdsc->cap_flush_list); if (oldest_flush_tid == 0) @@ -1846,6 +1847,7 @@ struct ceph_cap_flush *ceph_alloc_cap_flush(void) return NULL; cf->is_capsnap = false; + cf->ci = NULL; return cf; } @@ -1931,6 +1933,7 @@ static u64 __mark_caps_flushing(struct inode *inode, doutc(cl, "%p %llx.%llx now !dirty\n", inode, ceph_vinop(inode)); swap(cf, ci->i_prealloc_cap_flush); + cf->ci = ci; cf->caps = flushing; cf->wake = wake; @@ -3826,6 +3829,13 @@ static void handle_cap_flush_ack(struct inode *inode, u64 flush_tid, bool wake_ci = false; bool wake_mdsc = false; + /* + * Flush tids are monotonically increasing and acks arrive in + * order under i_ceph_lock, so this is always the latest tid. + * Diagnostic readers use READ_ONCE() without holding the lock. + */ + WRITE_ONCE(ci->i_last_cap_flush_ack, flush_tid); + list_for_each_entry_safe(cf, tmp_cf, &ci->i_cap_flush_list, i_list) { /* Is this the one that was flushed? */ if (cf->tid == flush_tid) diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index 4871d7ab2730..61d7c0b8161f 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -671,6 +671,7 @@ struct inode *ceph_alloc_inode(struct super_block *sb) INIT_LIST_HEAD(&ci->i_cap_snaps); ci->i_head_snapc = NULL; ci->i_snap_caps = 0; + ci->i_last_cap_flush_ack = 0; ci->i_last_rd = ci->i_last_wr = jiffies - 3600 * HZ; for (i = 0; i < CEPH_FILE_MODE_BITS; i++) diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 249419c17d3c..eddd3ccf5bba 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -2330,19 +2330,112 @@ static int check_caps_flush(struct ceph_mds_client *mdsc, } /* - * flush all dirty inode data to disk. + * Snapshot of a single cap_flush entry for diagnostic dump. + * Collected under cap_dirty_lock, printed after releasing it. + */ +struct flush_dump_entry { + u64 ino; /* inode number */ + u64 snap; /* snap id */ + int caps; /* dirty cap bits */ + u64 tid; /* flush transaction id */ + u64 last_ack; /* most recent ack tid for this inode */ + bool wake; /* whether completion was requested */ + bool is_capsnap; /* true if this is a cap snap flush */ + bool ci_null; /* true if cf->ci was unexpectedly NULL */ +}; + +/* + * Dump pending cap flushes for diagnostic purposes. * - * returns true if we've flushed through want_flush_tid + * cf->ci is safe to dereference here: cap_flush entries hold a + * reference on the inode (via the cap), and entries are removed from + * cap_flush_list under cap_dirty_lock before the cap (and thus the + * inode reference) is released. Holding cap_dirty_lock therefore + * guarantees the inode remains valid for the lifetime of the scan. + */ + +static void dump_cap_flushes(struct ceph_mds_client *mdsc, u64 want_tid) +{ + struct ceph_client *cl = mdsc->fsc->client; + struct flush_dump_entry entries[CEPH_CAP_FLUSH_MAX_DUMP_ENTRIES]; + struct ceph_cap_flush *cf; + int n = 0, remaining = 0; + int i; + + spin_lock(&mdsc->cap_dirty_lock); + list_for_each_entry(cf, &mdsc->cap_flush_list, g_list) { + if (cf->tid > want_tid) + break; + if (n < CEPH_CAP_FLUSH_MAX_DUMP_ENTRIES) { + struct flush_dump_entry *e = &entries[n++]; + + e->ci_null = WARN_ON_ONCE(!cf->ci); + if (!e->ci_null) { + e->ino = ceph_ino(&cf->ci->netfs.inode); + e->snap = ceph_snap(&cf->ci->netfs.inode); + e->last_ack = READ_ONCE(cf->ci->i_last_cap_flush_ack); + } + e->caps = cf->caps; + e->tid = cf->tid; + e->wake = cf->wake; + e->is_capsnap = cf->is_capsnap; + } else { + remaining++; + } + } + spin_unlock(&mdsc->cap_dirty_lock); + + pr_info_client(cl, "still waiting for cap flushes through %llu:\n", + want_tid); + for (i = 0; i < n; i++) { + struct flush_dump_entry *e = &entries[i]; + + if (e->ci_null) + pr_info_client(cl, + " (null ci) %s tid=%llu wake=%d%s\n", + ceph_cap_string(e->caps), e->tid, + e->wake, + e->is_capsnap ? " is_capsnap" : ""); + else + pr_info_client(cl, + " %llx.%llx %s tid=%llu last_ack=%llu wake=%d%s\n", + e->ino, e->snap, + ceph_cap_string(e->caps), e->tid, + e->last_ack, e->wake, + e->is_capsnap ? " is_capsnap" : ""); + } + if (remaining) + pr_info_client(cl, " ... and %d more pending flushes\n", + remaining); +} + +/* + * Wait for all cap flushes through @want_flush_tid to complete. + * Periodically dumps pending cap flush state for diagnostics. */ static void wait_caps_flush(struct ceph_mds_client *mdsc, u64 want_flush_tid) { struct ceph_client *cl = mdsc->fsc->client; + int i = 0; + long ret; doutc(cl, "want %llu\n", want_flush_tid); - wait_event(mdsc->cap_flushing_wq, - check_caps_flush(mdsc, want_flush_tid)); + do { + /* 60 * HZ fits in a long on all supported architectures. */ + ret = wait_event_timeout(mdsc->cap_flushing_wq, + check_caps_flush(mdsc, want_flush_tid), + CEPH_CAP_FLUSH_WAIT_TIMEOUT_SEC * HZ); + if (ret == 0) { + if (i < CEPH_CAP_FLUSH_MAX_DUMP_ITERS) + dump_cap_flushes(mdsc, want_flush_tid); + else if (i == CEPH_CAP_FLUSH_MAX_DUMP_ITERS) + pr_info_client(cl, + "still waiting for cap flushes; suppressing further dumps\n"); + i++; + } + } while (ret == 0); doutc(cl, "ok, flushed thru %llu\n", want_flush_tid); } diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h index d873e784b025..8208fdf02efe 100644 --- a/fs/ceph/mds_client.h +++ b/fs/ceph/mds_client.h @@ -77,6 +77,9 @@ struct ceph_fs_client; struct ceph_cap; #define MDS_AUTH_UID_ANY -1 +#define CEPH_CAP_FLUSH_WAIT_TIMEOUT_SEC 60 +#define CEPH_CAP_FLUSH_MAX_DUMP_ENTRIES 5 +#define CEPH_CAP_FLUSH_MAX_DUMP_ITERS 5 struct ceph_mds_cap_match { s64 uid; /* default to MDS_AUTH_UID_ANY */ diff --git a/fs/ceph/super.h b/fs/ceph/super.h index 8afc6f3a10da..a4993644d543 100644 --- a/fs/ceph/super.h +++ b/fs/ceph/super.h @@ -239,6 +239,7 @@ struct ceph_cap_flush { bool is_capsnap; /* true means capsnap */ struct list_head g_list; // global struct list_head i_list; // per inode + struct ceph_inode_info *ci; }; /* @@ -453,6 +454,11 @@ struct ceph_inode_info { struct ceph_snap_context *i_head_snapc; /* set if wr_buffer_head > 0 or dirty|flushing caps */ unsigned i_snap_caps; /* cap bits for snapped files */ + /* + * Written under i_ceph_lock, read via READ_ONCE() + * from diagnostic paths. + */ + u64 i_last_cap_flush_ack; unsigned long i_last_rd; unsigned long i_last_wr; From b52861897be8a7ba563077ae62cd48158d16a5d9 Mon Sep 17 00:00:00 2001 From: Alex Markuze Date: Thu, 7 May 2026 09:11:59 +0000 Subject: [PATCH 139/297] ceph: add client reset state machine and session teardown Add the client-side reset state machine, request gating, and manual session teardown implementation. Manual reset is an operator-triggered escape hatch for client/MDS stalemates in which caps, locks, or unsafe metadata state stop making forward progress. The reset blocks new metadata work, attempts a bounded best-effort drain of dirty client state while sessions are still alive, and finally asks the MDS to close sessions before tearing local session state down directly. The reset state machine tracks four phases: IDLE -> QUIESCING -> DRAINING -> TEARDOWN -> IDLE. QUIESCING is set synchronously by schedule_reset() before the workqueue item is dispatched, so that new metadata requests and file-lock acquisitions are gated immediately -- even before the work function begins running. All non-IDLE phases block callers on blocked_wq, preventing races with session teardown. The drain phase flushes mdlog state, dirty caps, and pending cap releases for a bounded interval. State that still cannot make progress within that interval is discarded during teardown, which is the point of the reset: break the stalemate and allow fresh sessions to rebuild clean state. The session teardown follows the established check_new_map() forced-close pattern: unregister sessions under mdsc->mutex, then clean up caps and requests under s->s_mutex. Reconnect is not attempted because the MDS only accepts reconnects during its own RECONNECT phase after restart, not from an active client. Blocked callers are released when reset completes and observe the final result via -EAGAIN (reset failed) or 0 (success). Internal work-function errors such as -ENOMEM are not propagated to unrelated callers like open() or flock(); the detailed error remains in debugfs and tracepoints. The work function checks st->shutdown before each phase transition (DRAINING, TEARDOWN) so that a concurrent ceph_mdsc_destroy() is not overwritten. If destroy already took ownership, the work function releases session references and returns without touching the state. The timeout calculation for blocked-request waiters uses max_t() to prevent jiffies underflow when the deadline has already passed. The close-grace sleep before teardown is a best-effort nudge to let queued REQUEST_CLOSE messages egress; it is not a correctness requirement since the MDS still has session_autoclose as a fallback. The destroy path marks reset as failed and wakes blocked waiters before cancel_work_sync() so unmount does not stall. Signed-off-by: Alex Markuze Reviewed-by: Viacheslav Dubeyko Signed-off-by: Viacheslav Dubeyko Signed-off-by: Ilya Dryomov --- fs/ceph/locks.c | 16 ++ fs/ceph/mds_client.c | 508 +++++++++++++++++++++++++++++++++++++++++++ fs/ceph/mds_client.h | 47 ++++ 3 files changed, 571 insertions(+) diff --git a/fs/ceph/locks.c b/fs/ceph/locks.c index c4ff2266bb94..677221bd64e0 100644 --- a/fs/ceph/locks.c +++ b/fs/ceph/locks.c @@ -249,6 +249,7 @@ int ceph_lock(struct file *file, int cmd, struct file_lock *fl) { struct inode *inode = file_inode(file); struct ceph_inode_info *ci = ceph_inode(inode); + struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(inode->i_sb); struct ceph_client *cl = ceph_inode_to_client(inode); int err = 0; u16 op = CEPH_MDS_OP_SETFILELOCK; @@ -275,6 +276,13 @@ int ceph_lock(struct file *file, int cmd, struct file_lock *fl) return -EIO; } + /* Wait for reset to complete before acquiring new locks */ + if (op == CEPH_MDS_OP_SETFILELOCK && !lock_is_unlock(fl)) { + err = ceph_mdsc_wait_for_reset(mdsc); + if (err) + return err; + } + if (lock_is_read(fl)) lock_cmd = CEPH_LOCK_SHARED; else if (lock_is_write(fl)) @@ -311,6 +319,7 @@ int ceph_flock(struct file *file, int cmd, struct file_lock *fl) { struct inode *inode = file_inode(file); struct ceph_inode_info *ci = ceph_inode(inode); + struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(inode->i_sb); struct ceph_client *cl = ceph_inode_to_client(inode); int err = 0; u8 wait = 0; @@ -330,6 +339,13 @@ int ceph_flock(struct file *file, int cmd, struct file_lock *fl) return -EIO; } + /* Wait for reset to complete before acquiring new locks */ + if (!lock_is_unlock(fl)) { + err = ceph_mdsc_wait_for_reset(mdsc); + if (err) + return err; + } + if (IS_SETLKW(cmd)) wait = 1; diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index eddd3ccf5bba..ddafbd6917b0 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -6,6 +6,7 @@ #include #include #include +#include #include #include #include @@ -65,6 +66,7 @@ static void __wake_requests(struct ceph_mds_client *mdsc, struct list_head *head); static void ceph_cap_release_work(struct work_struct *work); static void ceph_cap_reclaim_work(struct work_struct *work); +static void ceph_mdsc_reset_workfn(struct work_struct *work); static const struct ceph_connection_operations mds_con_ops; @@ -3845,6 +3847,22 @@ int ceph_mdsc_submit_request(struct ceph_mds_client *mdsc, struct inode *dir, struct ceph_client *cl = mdsc->fsc->client; int err = 0; + /* + * If a reset is in progress, wait for it to complete. + * + * This is best-effort: a request can pass this check just + * before the phase leaves IDLE and proceed concurrently with + * reset. That is acceptable because (a) such requests will + * either complete normally or fail and be retried by the + * caller, and (b) adding lock serialization here would + * penalize every request for a rare manual operation. + */ + err = ceph_mdsc_wait_for_reset(mdsc); + if (err) { + doutc(cl, "wait_for_reset failed: %d\n", err); + return err; + } + /* take CAP_PIN refs for r_inode, r_parent, r_old_dentry */ if (req->r_inode) ceph_get_cap_refs(ceph_inode(req->r_inode), CEPH_CAP_PIN); @@ -5267,6 +5285,474 @@ fail_return: return err; } +const char *ceph_reset_phase_name(enum ceph_client_reset_phase phase) +{ + switch (phase) { + case CEPH_CLIENT_RESET_IDLE: return "idle"; + case CEPH_CLIENT_RESET_QUIESCING: return "quiescing"; + case CEPH_CLIENT_RESET_DRAINING: return "draining"; + case CEPH_CLIENT_RESET_TEARDOWN: return "teardown"; + default: return "unknown"; + } +} + +/** + * ceph_mdsc_wait_for_reset - wait for an active reset to complete + * @mdsc: MDS client + * + * Returns 0 if reset completed successfully or no reset was active. + * Returns -EAGAIN if reset completed with an error, signalling the + * caller to retry. The internal error (e.g. -ENOMEM) is not propagated + * because callers like open() or flock() have no way to act on + * work-function internals. The detailed error is available via debugfs + * reset/status and tracepoints. + * Returns -ETIMEDOUT if we timed out waiting. + * Returns -ERESTARTSYS if interrupted by signal. + */ +int ceph_mdsc_wait_for_reset(struct ceph_mds_client *mdsc) +{ + struct ceph_client_reset_state *st = &mdsc->reset_state; + struct ceph_client *cl = mdsc->fsc->client; + unsigned long deadline = jiffies + CEPH_CLIENT_RESET_WAIT_TIMEOUT_SEC * HZ; + int blocked_count; + long remaining; + long wait_ret; + int ret; + + if (ceph_reset_is_idle(st)) + return 0; + + blocked_count = atomic_inc_return(&st->blocked_requests); + doutc(cl, "request blocked during reset, %d total blocked\n", + blocked_count); + +retry: + remaining = max_t(long, deadline - jiffies, 1); + wait_ret = wait_event_interruptible_timeout(st->blocked_wq, + ceph_reset_is_idle(st), + remaining); + + if (wait_ret == 0) { + atomic_dec(&st->blocked_requests); + pr_warn_client(cl, "timed out waiting for reset to complete\n"); + return -ETIMEDOUT; + } + if (wait_ret < 0) { + atomic_dec(&st->blocked_requests); + return (int)wait_ret; /* -ERESTARTSYS */ + } + + /* + * Verify phase is still IDLE under the lock. If another reset + * was scheduled between the wake-up and this check, loop back + * and wait for it to finish rather than returning a stale result. + */ + spin_lock(&st->lock); + if (st->phase != CEPH_CLIENT_RESET_IDLE) { + spin_unlock(&st->lock); + if (time_before(jiffies, deadline)) + goto retry; + atomic_dec(&st->blocked_requests); + return -ETIMEDOUT; + } + ret = st->last_errno; + spin_unlock(&st->lock); + + atomic_dec(&st->blocked_requests); + return ret ? -EAGAIN : 0; +} + +static void ceph_mdsc_reset_complete(struct ceph_mds_client *mdsc, int ret) +{ + struct ceph_client_reset_state *st = &mdsc->reset_state; + + spin_lock(&st->lock); + /* + * If destroy already marked us as shut down, it owns the + * final bookkeeping and waiter wakeup. Just bail so we + * don't overwrite its state. + */ + if (st->shutdown) { + spin_unlock(&st->lock); + return; + } + st->last_finish = jiffies; + st->last_errno = ret; + st->phase = CEPH_CLIENT_RESET_IDLE; + if (ret) + st->failure_count++; + else + st->success_count++; + spin_unlock(&st->lock); + + /* Wake up all requests that were blocked waiting for reset */ + wake_up_all(&st->blocked_wq); + +} + +static void ceph_mdsc_reset_workfn(struct work_struct *work) +{ + struct ceph_mds_client *mdsc = + container_of(work, struct ceph_mds_client, reset_work); + struct ceph_client_reset_state *st = &mdsc->reset_state; + struct ceph_client *cl = mdsc->fsc->client; + struct ceph_mds_session **sessions = NULL; + char reason[CEPH_CLIENT_RESET_REASON_LEN]; + unsigned long drain_deadline; + int max_sessions, i, n = 0, torn_down = 0; + int ret = 0; + + spin_lock(&st->lock); + strscpy(reason, st->last_reason, sizeof(reason)); + spin_unlock(&st->lock); + + mutex_lock(&mdsc->mutex); + max_sessions = mdsc->max_sessions; + if (max_sessions <= 0) { + mutex_unlock(&mdsc->mutex); + goto out_complete; + } + + sessions = kcalloc(max_sessions, sizeof(*sessions), GFP_KERNEL); + if (!sessions) { + mutex_unlock(&mdsc->mutex); + ret = -ENOMEM; + pr_err_client(cl, + "manual session reset failed to allocate session array\n"); + ceph_mdsc_reset_complete(mdsc, ret); + return; + } + + for (i = 0; i < max_sessions; i++) { + struct ceph_mds_session *session = mdsc->sessions[i]; + + if (!session) + continue; + + /* + * Read session state without s_mutex to avoid nesting + * mdsc->mutex -> s_mutex, which would invert the + * s_mutex -> mdsc->mutex order used by + * cleanup_session_requests(). s_state is an int + * so loads are atomic; the teardown loop below + * handles races with concurrent state transitions. + */ + switch (READ_ONCE(session->s_state)) { + case CEPH_MDS_SESSION_OPEN: + case CEPH_MDS_SESSION_HUNG: + case CEPH_MDS_SESSION_OPENING: + case CEPH_MDS_SESSION_RESTARTING: + case CEPH_MDS_SESSION_RECONNECTING: + case CEPH_MDS_SESSION_CLOSING: + sessions[n++] = ceph_get_mds_session(session); + break; + default: + pr_info_client(cl, + "mds%d in state %s, skipping reset\n", + session->s_mds, + ceph_session_state_name(session->s_state)); + break; + } + } + mutex_unlock(&mdsc->mutex); + + pr_info_client(cl, + "manual session reset executing (sessions=%d, reason=\"%s\")\n", + n, reason); + + if (n == 0) { + kfree(sessions); + goto out_complete; + } + + spin_lock(&st->lock); + if (st->shutdown) { + spin_unlock(&st->lock); + goto out_sessions; + } + st->phase = CEPH_CLIENT_RESET_DRAINING; + spin_unlock(&st->lock); + + /* + * Best-effort drain: flush dirty state while sessions are still + * alive. New requests are blocked while phase != IDLE. + * The sessions are functional, so non-stuck state drains normally. + * Stuck state (the cause of the stalemate the operator is trying + * to break) will not drain -- that is expected, and we proceed to + * forced teardown after the timeout. + * + * Four things are drained: + * 1. MDS journal -- send_flush_mdlog asks each MDS to journal + * pending unsafe operations (creates, renames, setattrs). + * 2. Unsafe requests -- bounded wait for each unsafe write + * request to reach safe status via r_safe_completion. + * 3. Dirty caps -- ceph_flush_dirty_caps triggers cap flush on + * all sessions. Non-stuck caps flush in milliseconds. + * 4. Cap releases -- push pending cap release messages. + * + * The unsafe-request wait and cap-flush wait below provide + * the bounded drain window during which all categories can + * make progress. + */ + for (i = 0; i < n; i++) + send_flush_mdlog(sessions[i]); + + /* + * Both drain legs (unsafe requests and cap flushes) share a + * single deadline so the total drain time is bounded at + * CEPH_CLIENT_RESET_DRAIN_SEC. + */ + drain_deadline = jiffies + CEPH_CLIENT_RESET_DRAIN_SEC * HZ; + + /* + * Wait for unsafe write requests (creates, renames, setattrs) + * to reach safe status. Uses the same pattern as + * flush_mdlog_and_wait_mdsc_unsafe_requests() but bounded by + * the shared drain deadline. Requests that do not complete within + * the window are force-dropped during teardown. + */ + { + struct ceph_mds_request *req; + struct rb_node *rn; + u64 last_tid; + + mutex_lock(&mdsc->mutex); + last_tid = mdsc->last_tid; + mutex_unlock(&mdsc->mutex); + + mutex_lock(&mdsc->mutex); + rn = rb_first(&mdsc->request_tree); + while (rn) { + req = rb_entry(rn, struct ceph_mds_request, r_node); + if (req->r_tid > last_tid) + break; + if (req->r_op == CEPH_MDS_OP_SETFILELOCK || + !(req->r_op & CEPH_MDS_OP_WRITE)) { + rn = rb_next(rn); + continue; + } + ceph_mdsc_get_request(req); + mutex_unlock(&mdsc->mutex); + + wait_for_completion_timeout(&req->r_safe_completion, + max_t(long, drain_deadline - jiffies, 1)); + + mutex_lock(&mdsc->mutex); + ceph_mdsc_put_request(req); + if (time_after(jiffies, drain_deadline)) + break; + rn = rb_first(&mdsc->request_tree); + } + mutex_unlock(&mdsc->mutex); + + if (time_after_eq(jiffies, drain_deadline)) + WRITE_ONCE(st->drain_timed_out, true); + } + + ceph_flush_dirty_caps(mdsc); + ceph_flush_cap_releases(mdsc); + + spin_lock(&mdsc->cap_dirty_lock); + if (!list_empty(&mdsc->cap_flush_list)) { + struct ceph_cap_flush *cf = + list_last_entry(&mdsc->cap_flush_list, + struct ceph_cap_flush, g_list); + u64 want_flush = mdsc->last_cap_flush_tid; + long drain_ret; + + /* + * Setting wake on the last entry is sufficient: flush + * entries complete in order, so when this entry finishes + * all earlier ones are already done. + */ + cf->wake = true; + spin_unlock(&mdsc->cap_dirty_lock); + pr_info_client(cl, + "draining (want_flush=%llu, %d sessions)\n", + want_flush, n); + drain_ret = wait_event_timeout(mdsc->cap_flushing_wq, + check_caps_flush(mdsc, + want_flush), + max_t(long, + drain_deadline - jiffies, + 1)); + if (drain_ret == 0) { + pr_info_client(cl, + "drain timed out, proceeding with forced teardown\n"); + WRITE_ONCE(st->drain_timed_out, true); + } else { + pr_info_client(cl, "drain completed successfully\n"); + } + } else { + spin_unlock(&mdsc->cap_dirty_lock); + } + + spin_lock(&st->lock); + if (st->shutdown) { + spin_unlock(&st->lock); + goto out_sessions; + } + st->phase = CEPH_CLIENT_RESET_TEARDOWN; + spin_unlock(&st->lock); + + /* + * Ask each MDS to close the session before we tear it down + * locally. Without this the MDS sees only a connection drop and + * waits for the client to reconnect (up to session_autoclose + * seconds) before evicting the session and releasing locks. + * + * Reuse the normal close machinery so the session state/sequence + * snapshot is serialized under s_mutex and a racing s_seq bump + * retransmits REQUEST_CLOSE while the session remains CLOSING. + * We send all close requests first, then yield briefly to let the + * network stack transmit them before __unregister_session() + * closes the connections. + */ + for (i = 0; i < n; i++) { + int err; + + mutex_lock(&sessions[i]->s_mutex); + err = __close_session(mdsc, sessions[i]); + mutex_unlock(&sessions[i]->s_mutex); + if (err < 0) + pr_warn_client(cl, + "mds%d failed to queue close request before reset: %d\n", + sessions[i]->s_mds, err); + } + /* + * Best-effort grace period: yield briefly so the network stack + * can transmit the queued REQUEST_CLOSE messages before we tear + * down connections. Not a correctness requirement -- the MDS + * will still evict via session_autoclose if it never receives + * the close request. + * + * Event-based waiting is not viable here: there is no completion + * event for "message left the NIC," and waiting for the MDS + * SESSION_CLOSE response would re-create the stalemate that the + * reset is meant to break. + */ + if (n > 0) + msleep(CEPH_CLIENT_RESET_CLOSE_GRACE_MS); + + /* + * Tear down each session: close the connection, remove all + * caps, clean up requests, then kick pending requests so they + * re-open a fresh session on the next attempt. + * + * This is modeled on the check_new_map() forced-close path + * for stopped MDS ranks - a proven pattern for hard session + * teardown. We do NOT attempt send_mds_reconnect() because + * the MDS only accepts reconnects during its own RECONNECT + * phase (after MDS restart), not from an active client. + * + * Any state that did not drain (caps that didn't flush, unsafe + * requests that the MDS didn't journal) is force-dropped here. + * This is intentional: that state is stuck and is the reason + * the operator triggered the reset. + */ + for (i = 0; i < n; i++) { + int mds = sessions[i]->s_mds; + + pr_info_client(cl, "mds%d resetting session\n", mds); + + mutex_lock(&mdsc->mutex); + if (mds >= mdsc->max_sessions || + mdsc->sessions[mds] != sessions[i]) { + pr_info_client(cl, + "mds%d session already torn down, skipping\n", + mds); + mutex_unlock(&mdsc->mutex); + ceph_put_mds_session(sessions[i]); + sessions[i] = NULL; + continue; + } + sessions[i]->s_state = CEPH_MDS_SESSION_CLOSED; + __unregister_session(mdsc, sessions[i]); + __wake_requests(mdsc, &sessions[i]->s_waiting); + mutex_unlock(&mdsc->mutex); + + mutex_lock(&sessions[i]->s_mutex); + cleanup_session_requests(mdsc, sessions[i]); + remove_session_caps(sessions[i]); + mutex_unlock(&sessions[i]->s_mutex); + + wake_up_all(&mdsc->session_close_wq); + + ceph_put_mds_session(sessions[i]); + + mutex_lock(&mdsc->mutex); + kick_requests(mdsc, mds); + mutex_unlock(&mdsc->mutex); + + torn_down++; + pr_info_client(cl, "mds%d session reset complete\n", mds); + } + + kfree(sessions); + + spin_lock(&st->lock); + st->sessions_reset = torn_down; + spin_unlock(&st->lock); + +out_complete: + ceph_mdsc_reset_complete(mdsc, ret); + return; + +out_sessions: + /* shutdown == true: ceph_mdsc_destroy() owns the final transition. */ + for (i = 0; i < n; i++) + ceph_put_mds_session(sessions[i]); + kfree(sessions); +} + +int ceph_mdsc_schedule_reset(struct ceph_mds_client *mdsc, + const char *reason) +{ + struct ceph_client_reset_state *st = &mdsc->reset_state; + struct ceph_fs_client *fsc = mdsc->fsc; + const char *msg = (reason && reason[0]) ? reason : "manual"; + int mount_state; + + mount_state = READ_ONCE(fsc->mount_state); + if (mount_state != CEPH_MOUNT_MOUNTED) { + pr_warn_client(fsc->client, + "reset rejected: mount_state=%d (not mounted)\n", + mount_state); + return -EINVAL; + } + + spin_lock(&st->lock); + if (st->phase != CEPH_CLIENT_RESET_IDLE) { + spin_unlock(&st->lock); + return -EBUSY; + } + + st->phase = CEPH_CLIENT_RESET_QUIESCING; + st->last_start = jiffies; + st->last_errno = 0; + st->drain_timed_out = false; + st->sessions_reset = 0; + st->trigger_count++; + strscpy(st->last_reason, msg, sizeof(st->last_reason)); + spin_unlock(&st->lock); + + if (WARN_ON_ONCE(!queue_work(system_unbound_wq, &mdsc->reset_work))) { + spin_lock(&st->lock); + st->phase = CEPH_CLIENT_RESET_IDLE; + st->last_errno = -EALREADY; + st->last_finish = jiffies; + st->failure_count++; + spin_unlock(&st->lock); + wake_up_all(&st->blocked_wq); + return -EALREADY; + } + + pr_info_client(mdsc->fsc->client, + "manual session reset scheduled (reason=\"%s\")\n", + msg); + return 0; +} + /* * compare old and new mdsmaps, kicking requests @@ -5812,6 +6298,11 @@ int ceph_mdsc_init(struct ceph_fs_client *fsc) INIT_LIST_HEAD(&mdsc->dentry_leases); INIT_LIST_HEAD(&mdsc->dentry_dir_leases); + spin_lock_init(&mdsc->reset_state.lock); + init_waitqueue_head(&mdsc->reset_state.blocked_wq); + atomic_set(&mdsc->reset_state.blocked_requests, 0); + INIT_WORK(&mdsc->reset_work, ceph_mdsc_reset_workfn); + ceph_caps_init(mdsc); ceph_adjust_caps_max_min(mdsc, fsc->mount_options); @@ -6337,6 +6828,23 @@ void ceph_mdsc_destroy(struct ceph_fs_client *fsc) /* flush out any connection work with references to us */ ceph_msgr_flush(); + /* + * Mark reset as failed and wake any blocked waiters before + * cancelling, so unmount doesn't stall on blocked_wq timeout + * if cancel_work_sync() prevents the work from running. + */ + spin_lock(&mdsc->reset_state.lock); + mdsc->reset_state.shutdown = true; + if (mdsc->reset_state.phase != CEPH_CLIENT_RESET_IDLE) { + mdsc->reset_state.phase = CEPH_CLIENT_RESET_IDLE; + mdsc->reset_state.last_errno = -ESHUTDOWN; + mdsc->reset_state.last_finish = jiffies; + mdsc->reset_state.failure_count++; + } + spin_unlock(&mdsc->reset_state.lock); + wake_up_all(&mdsc->reset_state.blocked_wq); + + cancel_work_sync(&mdsc->reset_work); ceph_mdsc_stop(mdsc); ceph_metric_destroy(&mdsc->metric); diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h index 8208fdf02efe..731d6ad04956 100644 --- a/fs/ceph/mds_client.h +++ b/fs/ceph/mds_client.h @@ -80,6 +80,47 @@ struct ceph_cap; #define CEPH_CAP_FLUSH_WAIT_TIMEOUT_SEC 60 #define CEPH_CAP_FLUSH_MAX_DUMP_ENTRIES 5 #define CEPH_CAP_FLUSH_MAX_DUMP_ITERS 5 +#define CEPH_CLIENT_RESET_REASON_LEN 64 +#define CEPH_CLIENT_RESET_DRAIN_SEC 30 +#define CEPH_CLIENT_RESET_CLOSE_GRACE_MS 100 +#define CEPH_CLIENT_RESET_WAIT_TIMEOUT_SEC 120 + +enum ceph_client_reset_phase { + CEPH_CLIENT_RESET_IDLE = 0, + /* + * QUIESCING is set synchronously by schedule_reset() before the + * workqueue item is dispatched. It gates new requests (any + * phase != IDLE blocks callers) during the window between + * scheduling and the work function's transition to DRAINING. + */ + CEPH_CLIENT_RESET_QUIESCING, + CEPH_CLIENT_RESET_DRAINING, + CEPH_CLIENT_RESET_TEARDOWN, +}; + +struct ceph_client_reset_state { + spinlock_t lock; /* protects all fields below */ + u64 trigger_count; /* number of resets triggered */ + u64 success_count; /* number of successful resets */ + u64 failure_count; /* number of failed resets */ + unsigned long last_start; /* jiffies when last reset started */ + unsigned long last_finish; /* jiffies when last reset finished */ + int last_errno; /* result of most recent reset */ + enum ceph_client_reset_phase phase; /* current reset phase */ + bool drain_timed_out; /* drain exceeded timeout */ + bool shutdown; /* destroy in progress */ + int sessions_reset; /* sessions torn down in last reset */ + char last_reason[CEPH_CLIENT_RESET_REASON_LEN]; /* operator-supplied reason */ + + /* Request blocking during reset */ + wait_queue_head_t blocked_wq; /* waitqueue for blocked callers */ + atomic_t blocked_requests; /* count of blocked callers */ +}; + +static inline bool ceph_reset_is_idle(struct ceph_client_reset_state *st) +{ + return READ_ONCE(st->phase) == CEPH_CLIENT_RESET_IDLE; +} struct ceph_mds_cap_match { s64 uid; /* default to MDS_AUTH_UID_ANY */ @@ -543,6 +584,8 @@ struct ceph_mds_client { struct list_head dentry_dir_leases; /* lru list */ struct ceph_client_metric metric; + struct work_struct reset_work; + struct ceph_client_reset_state reset_state; struct ceph_subvolume_metrics_tracker subvol_metrics; /* Subvolume metrics send tracking */ @@ -574,10 +617,14 @@ extern struct ceph_mds_session * __ceph_lookup_mds_session(struct ceph_mds_client *, int mds); extern const char *ceph_session_state_name(int s); +extern const char *ceph_reset_phase_name(enum ceph_client_reset_phase phase); extern struct ceph_mds_session * ceph_get_mds_session(struct ceph_mds_session *s); extern void ceph_put_mds_session(struct ceph_mds_session *s); +int ceph_mdsc_schedule_reset(struct ceph_mds_client *mdsc, + const char *reason); +int ceph_mdsc_wait_for_reset(struct ceph_mds_client *mdsc); extern int ceph_mdsc_init(struct ceph_fs_client *fsc); extern void ceph_mdsc_close_sessions(struct ceph_mds_client *mdsc); From 7e1f9e2cd2d0e780c394a4402c40e125109fec72 Mon Sep 17 00:00:00 2001 From: Alex Markuze Date: Thu, 7 May 2026 08:54:07 +0000 Subject: [PATCH 140/297] ceph: add manual reset debugfs control and tracepoints Add the debugfs and trace plumbing used to trigger and observe manual client reset. The reset interface exposes a trigger file for operator-initiated reset and a status file for tracking the most recent run. The tracepoints record scheduling, completion, and blocked caller behavior so reset progress can be diagnosed from the client side. debugfs layout under /sys/kernel/debug/ceph//reset/: trigger - write to initiate a manual reset status - read to see the most recent reset result The reset directory is cleaned up via debugfs_remove_recursive() on the parent, so individual file dentries are not stored. Tracepoints: ceph_client_reset_schedule - reset queued ceph_client_reset_complete - reset finished (success or failure) ceph_client_reset_blocked - caller blocked waiting for reset ceph_client_reset_unblocked - caller unblocked after reset All tracepoints use a null-safe access for monc.auth->global_id to guard against early-init or late-teardown edge cases. Signed-off-by: Alex Markuze Reviewed-by: Viacheslav Dubeyko Signed-off-by: Viacheslav Dubeyko Signed-off-by: Ilya Dryomov --- fs/ceph/debugfs.c | 103 ++++++++++++++++++++++++++++++++++++ fs/ceph/mds_client.c | 7 +++ fs/ceph/super.h | 1 + include/trace/events/ceph.h | 67 +++++++++++++++++++++++ 4 files changed, 178 insertions(+) diff --git a/fs/ceph/debugfs.c b/fs/ceph/debugfs.c index e2463f93cf6b..18eb5da03411 100644 --- a/fs/ceph/debugfs.c +++ b/fs/ceph/debugfs.c @@ -9,6 +9,7 @@ #include #include #include +#include #include #include @@ -392,6 +393,90 @@ static int status_show(struct seq_file *s, void *p) return 0; } +static int reset_status_show(struct seq_file *s, void *p) +{ + struct ceph_fs_client *fsc = s->private; + struct ceph_mds_client *mdsc = fsc->mdsc; + struct ceph_client_reset_state *st; + u64 trigger = 0, success = 0, failure = 0; + unsigned long last_start = 0, last_finish = 0; + int last_errno = 0; + enum ceph_client_reset_phase phase = CEPH_CLIENT_RESET_IDLE; + bool drain_timed_out = false; + int sessions_reset = 0; + int blocked_requests = 0; + char reason[CEPH_CLIENT_RESET_REASON_LEN]; + + if (!mdsc) + return 0; + + st = &mdsc->reset_state; + + spin_lock(&st->lock); + trigger = st->trigger_count; + success = st->success_count; + failure = st->failure_count; + last_start = st->last_start; + last_finish = st->last_finish; + last_errno = st->last_errno; + phase = st->phase; + drain_timed_out = st->drain_timed_out; + sessions_reset = st->sessions_reset; + strscpy(reason, st->last_reason, sizeof(reason)); + spin_unlock(&st->lock); + + blocked_requests = atomic_read(&st->blocked_requests); + + seq_printf(s, "phase: %s\n", ceph_reset_phase_name(phase)); + seq_printf(s, "trigger_count: %llu\n", trigger); + seq_printf(s, "success_count: %llu\n", success); + seq_printf(s, "failure_count: %llu\n", failure); + if (last_start) + seq_printf(s, "last_start_ms_ago: %u\n", + jiffies_to_msecs(jiffies - last_start)); + else + seq_puts(s, "last_start_ms_ago: (never)\n"); + if (last_finish) + seq_printf(s, "last_finish_ms_ago: %u\n", + jiffies_to_msecs(jiffies - last_finish)); + else + seq_puts(s, "last_finish_ms_ago: (never)\n"); + seq_printf(s, "last_errno: %d\n", last_errno); + seq_printf(s, "last_reason: %s\n", + reason[0] ? reason : "(none)"); + seq_printf(s, "drain_timed_out: %s\n", + drain_timed_out ? "yes" : "no"); + seq_printf(s, "sessions_reset: %d\n", sessions_reset); + seq_printf(s, "blocked_requests: %d\n", blocked_requests); + + return 0; +} + +static ssize_t reset_trigger_write(struct file *file, const char __user *buf, + size_t len, loff_t *ppos) +{ + struct ceph_fs_client *fsc = file->private_data; + struct ceph_mds_client *mdsc = fsc->mdsc; + char reason[CEPH_CLIENT_RESET_REASON_LEN]; + size_t copy; + int ret; + + if (!mdsc) + return -ENODEV; + + copy = min_t(size_t, len, sizeof(reason) - 1); + if (copy && copy_from_user(reason, buf, copy)) + return -EFAULT; + reason[copy] = '\0'; + strim(reason); + + ret = ceph_mdsc_schedule_reset(mdsc, reason); + if (ret) + return ret; + + return len; +} + static int subvolume_metrics_show(struct seq_file *s, void *p) { struct ceph_fs_client *fsc = s->private; @@ -450,6 +535,7 @@ DEFINE_SHOW_ATTRIBUTE(mdsc); DEFINE_SHOW_ATTRIBUTE(caps); DEFINE_SHOW_ATTRIBUTE(mds_sessions); DEFINE_SHOW_ATTRIBUTE(status); +DEFINE_SHOW_ATTRIBUTE(reset_status); DEFINE_SHOW_ATTRIBUTE(metrics_file); DEFINE_SHOW_ATTRIBUTE(metrics_latency); DEFINE_SHOW_ATTRIBUTE(metrics_size); @@ -521,6 +607,13 @@ static int metric_features_show(struct seq_file *s, void *p) DEFINE_SHOW_ATTRIBUTE(metric_features); +static const struct file_operations ceph_reset_trigger_fops = { + .owner = THIS_MODULE, + .open = simple_open, + .write = reset_trigger_write, + .llseek = noop_llseek, +}; + /* * debugfs */ @@ -554,6 +647,7 @@ void ceph_fs_debugfs_cleanup(struct ceph_fs_client *fsc) debugfs_remove(fsc->debugfs_caps); debugfs_remove(fsc->debugfs_status); debugfs_remove(fsc->debugfs_mdsc); + debugfs_remove_recursive(fsc->debugfs_reset_dir); debugfs_remove(fsc->debugfs_subvolume_metrics); debugfs_remove_recursive(fsc->debugfs_metrics_dir); doutc(fsc->client, "done\n"); @@ -602,6 +696,15 @@ void ceph_fs_debugfs_init(struct ceph_fs_client *fsc) fsc, &caps_fops); + fsc->debugfs_reset_dir = debugfs_create_dir("reset", + fsc->client->debugfs_dir); + debugfs_create_file("trigger", 0200, + fsc->debugfs_reset_dir, fsc, + &ceph_reset_trigger_fops); + debugfs_create_file("status", 0400, + fsc->debugfs_reset_dir, fsc, + &reset_status_fops); + fsc->debugfs_status = debugfs_create_file("status", 0400, fsc->client->debugfs_dir, diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index ddafbd6917b0..9f84ef2ac6e4 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -5325,6 +5325,7 @@ int ceph_mdsc_wait_for_reset(struct ceph_mds_client *mdsc) blocked_count = atomic_inc_return(&st->blocked_requests); doutc(cl, "request blocked during reset, %d total blocked\n", blocked_count); + trace_ceph_client_reset_blocked(mdsc, blocked_count); retry: remaining = max_t(long, deadline - jiffies, 1); @@ -5335,10 +5336,12 @@ retry: if (wait_ret == 0) { atomic_dec(&st->blocked_requests); pr_warn_client(cl, "timed out waiting for reset to complete\n"); + trace_ceph_client_reset_unblocked(mdsc, -ETIMEDOUT); return -ETIMEDOUT; } if (wait_ret < 0) { atomic_dec(&st->blocked_requests); + trace_ceph_client_reset_unblocked(mdsc, (int)wait_ret); return (int)wait_ret; /* -ERESTARTSYS */ } @@ -5353,12 +5356,14 @@ retry: if (time_before(jiffies, deadline)) goto retry; atomic_dec(&st->blocked_requests); + trace_ceph_client_reset_unblocked(mdsc, -ETIMEDOUT); return -ETIMEDOUT; } ret = st->last_errno; spin_unlock(&st->lock); atomic_dec(&st->blocked_requests); + trace_ceph_client_reset_unblocked(mdsc, ret); return ret ? -EAGAIN : 0; } @@ -5388,6 +5393,7 @@ static void ceph_mdsc_reset_complete(struct ceph_mds_client *mdsc, int ret) /* Wake up all requests that were blocked waiting for reset */ wake_up_all(&st->blocked_wq); + trace_ceph_client_reset_complete(mdsc, ret); } static void ceph_mdsc_reset_workfn(struct work_struct *work) @@ -5750,6 +5756,7 @@ int ceph_mdsc_schedule_reset(struct ceph_mds_client *mdsc, pr_info_client(mdsc->fsc->client, "manual session reset scheduled (reason=\"%s\")\n", msg); + trace_ceph_client_reset_schedule(mdsc, msg); return 0; } diff --git a/fs/ceph/super.h b/fs/ceph/super.h index a4993644d543..1d6aab060780 100644 --- a/fs/ceph/super.h +++ b/fs/ceph/super.h @@ -179,6 +179,7 @@ struct ceph_fs_client { struct dentry *debugfs_status; struct dentry *debugfs_mds_sessions; struct dentry *debugfs_metrics_dir; + struct dentry *debugfs_reset_dir; struct dentry *debugfs_subvolume_metrics; #endif diff --git a/include/trace/events/ceph.h b/include/trace/events/ceph.h index 08cb0659fbfc..1b990632f62b 100644 --- a/include/trace/events/ceph.h +++ b/include/trace/events/ceph.h @@ -226,6 +226,73 @@ TRACE_EVENT(ceph_handle_caps, __entry->mseq) ); +/* + * Client reset tracepoints - identify the client by its monitor- + * assigned global_id so traces remain meaningful when kernel pointer + * hashing is enabled. + */ +TRACE_EVENT(ceph_client_reset_schedule, + TP_PROTO(const struct ceph_mds_client *mdsc, const char *reason), + TP_ARGS(mdsc, reason), + TP_STRUCT__entry( + __field(u64, client_id) + __string(reason, reason ? reason : "") + ), + TP_fast_assign( + __entry->client_id = mdsc->fsc->client->monc.auth ? + mdsc->fsc->client->monc.auth->global_id : 0; + __assign_str(reason); + ), + TP_printk("client_id=%llu reason=%s", + __entry->client_id, __get_str(reason)) +); + +TRACE_EVENT(ceph_client_reset_complete, + TP_PROTO(const struct ceph_mds_client *mdsc, int ret), + TP_ARGS(mdsc, ret), + TP_STRUCT__entry( + __field(u64, client_id) + __field(int, ret) + ), + TP_fast_assign( + __entry->client_id = mdsc->fsc->client->monc.auth ? + mdsc->fsc->client->monc.auth->global_id : 0; + __entry->ret = ret; + ), + TP_printk("client_id=%llu ret=%d", __entry->client_id, __entry->ret) +); + +TRACE_EVENT(ceph_client_reset_blocked, + TP_PROTO(const struct ceph_mds_client *mdsc, int blocked_count), + TP_ARGS(mdsc, blocked_count), + TP_STRUCT__entry( + __field(u64, client_id) + __field(int, blocked_count) + ), + TP_fast_assign( + __entry->client_id = mdsc->fsc->client->monc.auth ? + mdsc->fsc->client->monc.auth->global_id : 0; + __entry->blocked_count = blocked_count; + ), + TP_printk("client_id=%llu blocked_count=%d", __entry->client_id, + __entry->blocked_count) +); + +TRACE_EVENT(ceph_client_reset_unblocked, + TP_PROTO(const struct ceph_mds_client *mdsc, int ret), + TP_ARGS(mdsc, ret), + TP_STRUCT__entry( + __field(u64, client_id) + __field(int, ret) + ), + TP_fast_assign( + __entry->client_id = mdsc->fsc->client->monc.auth ? + mdsc->fsc->client->monc.auth->global_id : 0; + __entry->ret = ret; + ), + TP_printk("client_id=%llu ret=%d", __entry->client_id, __entry->ret) +); + #undef EM #undef E_ #endif /* _TRACE_CEPH_H */ From 1afe4f19d6ad404621150f0e91feeccf12fb1037 Mon Sep 17 00:00:00 2001 From: John Madieu Date: Sat, 25 Apr 2026 15:49:59 +0000 Subject: [PATCH 141/297] rtc: isl1208: Balance enable_irq_wake() with disable_irq_wake() on cleanup isl1208_setup_irq() calls enable_irq_wake() after a successful IRQ request, but the driver has no remove path that balances it. The driver is devm-only, so on unbind devm releases the IRQ - but enable_irq_wake() is not undone by IRQ release, so the wake count for that IRQ stays incremented. Each rebind therefore leaks one wake reference; the leak doubles for the chip variant that has a separate evdet IRQ, since isl1208_setup_irq() is then called twice during probe. Register a devm action that calls disable_irq_wake() per IRQ. While at it, check enable_irq_wake()'s return value: on failure, propagate the error rather than silently registering a disable action for an IRQ whose wake state was never enabled. Fixes: 9ece7cd833a3 ("rtc: isl1208: Add "evdet" interrupt source for isl1219") Signed-off-by: John Madieu Link: https://patch.msgid.link/20260425154959.2796261-3-john.madieu.xa@bp.renesas.com Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-isl1208.c | 15 ++++++++++++++- 1 file changed, 14 insertions(+), 1 deletion(-) diff --git a/drivers/rtc/rtc-isl1208.c b/drivers/rtc/rtc-isl1208.c index bcaa766a5068..9bdd5d121571 100644 --- a/drivers/rtc/rtc-isl1208.c +++ b/drivers/rtc/rtc-isl1208.c @@ -822,6 +822,11 @@ static const struct nvmem_config isl1208_nvmem_config = { .reg_write = isl1208_nvmem_write, }; +static void isl1208_disable_irq_wake_action(void *data) +{ + disable_irq_wake((unsigned long)data); +} + static int isl1208_setup_irq(struct i2c_client *client, int irq) { int rc = devm_request_threaded_irq(&client->dev, irq, NULL, @@ -831,7 +836,15 @@ static int isl1208_setup_irq(struct i2c_client *client, int irq) client); if (!rc) { device_init_wakeup(&client->dev, true); - enable_irq_wake(irq); + rc = enable_irq_wake(irq); + if (rc) + return rc; + + rc = devm_add_action_or_reset(&client->dev, + isl1208_disable_irq_wake_action, + (void *)(unsigned long)irq); + if (rc) + return rc; } else { dev_err(&client->dev, "Unable to request irq %d, no alarm support\n", From 947d7ea6f60b5fe24d8f8b69e55e0d6e1e8855e7 Mon Sep 17 00:00:00 2001 From: Mario Limonciello Date: Wed, 20 May 2026 23:37:13 -0500 Subject: [PATCH 142/297] rtc: interface: Add rtc_read_next_alarm() to read next expiring timer Add a new function rtc_read_next_alarm() that reads the next expiring alarm from the RTC timerqueue. This is different from rtc_read_alarm(), which only reads the aie_timer. The wakealarm sysfs file programs the rtc->aie_timer, whereas the alarmtimer suspend routine programs its own timer into the RTC timerqueue. Both timers end up in the RTC's timerqueue, and the first expiring timer is what gets armed in the hardware. This new function allows code to query which alarm will actually fire next, regardless of which subsystem programmed it. This is needed by platform code that needs to program secondary timers based on the actual next wakeup time. Link: https://lore.kernel.org/all/87ed50z0le.ffs@tglx Suggested-by: Thomas Gleixner Assisted-by: Claude:claude-opus-4-6 Signed-off-by: Mario Limonciello Link: https://patch.msgid.link/20260521043714.1022930-2-mario.limonciello@amd.com Signed-off-by: Alexandre Belloni --- drivers/rtc/interface.c | 40 ++++++++++++++++++++++++++++++++++++++++ include/linux/rtc.h | 2 ++ 2 files changed, 42 insertions(+) diff --git a/drivers/rtc/interface.c b/drivers/rtc/interface.c index 1906f4884a83..7859be8f2a92 100644 --- a/drivers/rtc/interface.c +++ b/drivers/rtc/interface.c @@ -384,6 +384,46 @@ done: return err; } +/** + * rtc_read_next_alarm - read the next expiring alarm + * @rtc: RTC device + * @alarm: storage for the alarm information + * + * Read the next expiring alarm from the RTC timerqueue. This returns + * the alarm that will actually fire next, which may be different from + * rtc_read_alarm() if multiple timers are queued (e.g., alarmtimer + * and wakealarm sysfs both active). + * + * Returns: 0 on success, -ENOENT if no alarm is pending, or other error. + */ +int rtc_read_next_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alarm) +{ + struct timerqueue_node *next; + int err; + + if (!rtc || !alarm) + return -EINVAL; + + err = mutex_lock_interruptible(&rtc->ops_lock); + if (err) + return err; + + next = timerqueue_getnext(&rtc->timerqueue); + if (!next) { + err = -ENOENT; + goto unlock; + } + + memset(alarm, 0, sizeof(struct rtc_wkalrm)); + alarm->time = rtc_ktime_to_tm(next->expires); + alarm->enabled = 1; + +unlock: + mutex_unlock(&rtc->ops_lock); + return err; +} +EXPORT_SYMBOL_GPL(rtc_read_next_alarm); + int rtc_read_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alarm) { int err; diff --git a/include/linux/rtc.h b/include/linux/rtc.h index 95da051fb155..c09fc22819d0 100644 --- a/include/linux/rtc.h +++ b/include/linux/rtc.h @@ -190,6 +190,8 @@ extern int rtc_set_time(struct rtc_device *rtc, struct rtc_time *tm); int __rtc_read_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alarm); extern int rtc_read_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alrm); +extern int rtc_read_next_alarm(struct rtc_device *rtc, + struct rtc_wkalrm *alrm); extern int rtc_set_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alrm); extern int rtc_initialize_alarm(struct rtc_device *rtc, From a50b23a57fce4157156014bc00b0cf9f4ab1a69f Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 27 May 2026 21:39:03 +0200 Subject: [PATCH 143/297] rtc: remove unused pcap driver The platform was removed a few years ago, and the mfd driver is also gone now, so it is impossible to build or use it. Signed-off-by: Arnd Bergmann Link: https://patch.msgid.link/20260527193927.3523952-1-arnd@kernel.org Signed-off-by: Alexandre Belloni --- drivers/rtc/Kconfig | 7 -- drivers/rtc/Makefile | 1 - drivers/rtc/rtc-pcap.c | 179 ----------------------------------------- 3 files changed, 187 deletions(-) delete mode 100644 drivers/rtc/rtc-pcap.c diff --git a/drivers/rtc/Kconfig b/drivers/rtc/Kconfig index 364afc73f8ab..01def8231873 100644 --- a/drivers/rtc/Kconfig +++ b/drivers/rtc/Kconfig @@ -1763,13 +1763,6 @@ config RTC_DRV_STMP This driver can also be built as a module. If so, the module will be called rtc-stmp3xxx. -config RTC_DRV_PCAP - tristate "PCAP RTC" - depends on EZX_PCAP - help - If you say Y here you will get support for the RTC found on - the PCAP2 ASIC used on some Motorola phones. - config RTC_DRV_MC13XXX depends on MFD_MC13XXX tristate "Freescale MC13xxx RTC" diff --git a/drivers/rtc/Makefile b/drivers/rtc/Makefile index 6cf7e066314e..0347645b021f 100644 --- a/drivers/rtc/Makefile +++ b/drivers/rtc/Makefile @@ -128,7 +128,6 @@ obj-$(CONFIG_RTC_DRV_OMAP) += rtc-omap.o obj-$(CONFIG_RTC_DRV_OPAL) += rtc-opal.o obj-$(CONFIG_RTC_DRV_OPTEE) += rtc-optee.o obj-$(CONFIG_RTC_DRV_PALMAS) += rtc-palmas.o -obj-$(CONFIG_RTC_DRV_PCAP) += rtc-pcap.o obj-$(CONFIG_RTC_DRV_PCF2123) += rtc-pcf2123.o obj-$(CONFIG_RTC_DRV_PCF2127) += rtc-pcf2127.o obj-$(CONFIG_RTC_DRV_PCF85063) += rtc-pcf85063.o diff --git a/drivers/rtc/rtc-pcap.c b/drivers/rtc/rtc-pcap.c deleted file mode 100644 index d6651611a0c6..000000000000 --- a/drivers/rtc/rtc-pcap.c +++ /dev/null @@ -1,179 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * pcap rtc code for Motorola EZX phones - * - * Copyright (c) 2008 guiming zhuo - * Copyright (c) 2009 Daniel Ribeiro - * - * Based on Motorola's rtc.c Copyright (c) 2003-2005 Motorola - */ - -#include -#include -#include -#include -#include -#include -#include - -struct pcap_rtc { - struct pcap_chip *pcap; - struct rtc_device *rtc; -}; - -static irqreturn_t pcap_rtc_irq(int irq, void *_pcap_rtc) -{ - struct pcap_rtc *pcap_rtc = _pcap_rtc; - unsigned long rtc_events; - - if (irq == pcap_to_irq(pcap_rtc->pcap, PCAP_IRQ_1HZ)) - rtc_events = RTC_IRQF | RTC_UF; - else if (irq == pcap_to_irq(pcap_rtc->pcap, PCAP_IRQ_TODA)) - rtc_events = RTC_IRQF | RTC_AF; - else - rtc_events = 0; - - rtc_update_irq(pcap_rtc->rtc, 1, rtc_events); - return IRQ_HANDLED; -} - -static int pcap_rtc_read_alarm(struct device *dev, struct rtc_wkalrm *alrm) -{ - struct pcap_rtc *pcap_rtc = dev_get_drvdata(dev); - struct rtc_time *tm = &alrm->time; - unsigned long secs; - u32 tod; /* time of day, seconds since midnight */ - u32 days; /* days since 1/1/1970 */ - - ezx_pcap_read(pcap_rtc->pcap, PCAP_REG_RTC_TODA, &tod); - secs = tod & PCAP_RTC_TOD_MASK; - - ezx_pcap_read(pcap_rtc->pcap, PCAP_REG_RTC_DAYA, &days); - secs += (days & PCAP_RTC_DAY_MASK) * SEC_PER_DAY; - - rtc_time64_to_tm(secs, tm); - - return 0; -} - -static int pcap_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alrm) -{ - struct pcap_rtc *pcap_rtc = dev_get_drvdata(dev); - unsigned long secs = rtc_tm_to_time64(&alrm->time); - u32 tod, days; - - tod = secs % SEC_PER_DAY; - ezx_pcap_write(pcap_rtc->pcap, PCAP_REG_RTC_TODA, tod); - - days = secs / SEC_PER_DAY; - ezx_pcap_write(pcap_rtc->pcap, PCAP_REG_RTC_DAYA, days); - - return 0; -} - -static int pcap_rtc_read_time(struct device *dev, struct rtc_time *tm) -{ - struct pcap_rtc *pcap_rtc = dev_get_drvdata(dev); - unsigned long secs; - u32 tod, days; - - ezx_pcap_read(pcap_rtc->pcap, PCAP_REG_RTC_TOD, &tod); - secs = tod & PCAP_RTC_TOD_MASK; - - ezx_pcap_read(pcap_rtc->pcap, PCAP_REG_RTC_DAY, &days); - secs += (days & PCAP_RTC_DAY_MASK) * SEC_PER_DAY; - - rtc_time64_to_tm(secs, tm); - - return 0; -} - -static int pcap_rtc_set_time(struct device *dev, struct rtc_time *tm) -{ - struct pcap_rtc *pcap_rtc = dev_get_drvdata(dev); - unsigned long secs = rtc_tm_to_time64(tm); - u32 tod, days; - - tod = secs % SEC_PER_DAY; - ezx_pcap_write(pcap_rtc->pcap, PCAP_REG_RTC_TOD, tod); - - days = secs / SEC_PER_DAY; - ezx_pcap_write(pcap_rtc->pcap, PCAP_REG_RTC_DAY, days); - - return 0; -} - -static int pcap_rtc_irq_enable(struct device *dev, int pirq, unsigned int en) -{ - struct pcap_rtc *pcap_rtc = dev_get_drvdata(dev); - - if (en) - enable_irq(pcap_to_irq(pcap_rtc->pcap, pirq)); - else - disable_irq(pcap_to_irq(pcap_rtc->pcap, pirq)); - - return 0; -} - -static int pcap_rtc_alarm_irq_enable(struct device *dev, unsigned int en) -{ - return pcap_rtc_irq_enable(dev, PCAP_IRQ_TODA, en); -} - -static const struct rtc_class_ops pcap_rtc_ops = { - .read_time = pcap_rtc_read_time, - .set_time = pcap_rtc_set_time, - .read_alarm = pcap_rtc_read_alarm, - .set_alarm = pcap_rtc_set_alarm, - .alarm_irq_enable = pcap_rtc_alarm_irq_enable, -}; - -static int __init pcap_rtc_probe(struct platform_device *pdev) -{ - struct pcap_rtc *pcap_rtc; - int timer_irq, alarm_irq; - int err = -ENOMEM; - - pcap_rtc = devm_kzalloc(&pdev->dev, sizeof(struct pcap_rtc), - GFP_KERNEL); - if (!pcap_rtc) - return err; - - pcap_rtc->pcap = dev_get_drvdata(pdev->dev.parent); - - platform_set_drvdata(pdev, pcap_rtc); - - pcap_rtc->rtc = devm_rtc_allocate_device(&pdev->dev); - if (IS_ERR(pcap_rtc->rtc)) - return PTR_ERR(pcap_rtc->rtc); - - pcap_rtc->rtc->ops = &pcap_rtc_ops; - pcap_rtc->rtc->range_max = (1 << 14) * 86400ULL - 1; - - timer_irq = pcap_to_irq(pcap_rtc->pcap, PCAP_IRQ_1HZ); - alarm_irq = pcap_to_irq(pcap_rtc->pcap, PCAP_IRQ_TODA); - - err = devm_request_irq(&pdev->dev, timer_irq, pcap_rtc_irq, 0, - "RTC Timer", pcap_rtc); - if (err) - return err; - - err = devm_request_irq(&pdev->dev, alarm_irq, pcap_rtc_irq, 0, - "RTC Alarm", pcap_rtc); - if (err) - return err; - - return devm_rtc_register_device(pcap_rtc->rtc); -} - -static struct platform_driver pcap_rtc_driver = { - .driver = { - .name = "pcap-rtc", - }, -}; - -module_platform_driver_probe(pcap_rtc_driver, pcap_rtc_probe); - -MODULE_DESCRIPTION("Motorola pcap rtc driver"); -MODULE_AUTHOR("guiming zhuo "); -MODULE_LICENSE("GPL"); From a369f48be8de426a7d2bca18dbd46c2ad1138803 Mon Sep 17 00:00:00 2001 From: Stepan Ionichev Date: Mon, 11 May 2026 08:27:03 +0500 Subject: [PATCH 144/297] rtc: msc313: fix NULL deref in shared IRQ handler at probe msc313_rtc_probe() calls devm_request_irq() with IRQF_SHARED and &pdev->dev as the cookie, but platform_set_drvdata() is only called later after the clock setup. With a shared IRQ line, another device on the same line can trigger the handler in that window. The handler does dev_get_drvdata() on the cookie, gets NULL, and dereferences priv->rtc_base in interrupt context. Pass priv as the cookie directly so the handler reads it from dev_id without the lookup, removing the dependency on probe order. Fixes: be7d9c9161b9 ("rtc: Add support for the MSTAR MSC313 RTC") Signed-off-by: Stepan Ionichev Link: https://patch.msgid.link/20260511032703.48262-1-sozdayvek@gmail.com Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-msc313.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/rtc/rtc-msc313.c b/drivers/rtc/rtc-msc313.c index 8d7737e0e2e0..6ef9c4efd7c9 100644 --- a/drivers/rtc/rtc-msc313.c +++ b/drivers/rtc/rtc-msc313.c @@ -160,7 +160,7 @@ static const struct rtc_class_ops msc313_rtc_ops = { static irqreturn_t msc313_rtc_interrupt(s32 irq, void *dev_id) { - struct msc313_rtc *priv = dev_get_drvdata(dev_id); + struct msc313_rtc *priv = dev_id; u16 reg; reg = readw(priv->rtc_base + REG_RTC_STATUS_INT); @@ -206,7 +206,7 @@ static int msc313_rtc_probe(struct platform_device *pdev) priv->rtc_dev->range_max = U32_MAX; ret = devm_request_irq(dev, irq, msc313_rtc_interrupt, IRQF_SHARED, - dev_name(&pdev->dev), &pdev->dev); + dev_name(&pdev->dev), priv); if (ret) { dev_err(dev, "Could not request IRQ\n"); return ret; From 4202e4254403156a00711990ec99982f43bd99f5 Mon Sep 17 00:00:00 2001 From: Yahya Saqban Date: Wed, 13 May 2026 00:02:35 +0300 Subject: [PATCH 145/297] rtc: interface: fix typos in rtc_handle_legacy_irq() documentation Fix spelling of 'occurence' to 'occurrence' and 'of' to 'or' in the kernel-doc comment for rtc_handle_legacy_irq(). Signed-off-by: Yahya Saqban Link: https://patch.msgid.link/20260512210235.343070-1-yahyasaqban@gmail.com Signed-off-by: Alexandre Belloni --- drivers/rtc/interface.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/rtc/interface.c b/drivers/rtc/interface.c index 7859be8f2a92..96626f8068f9 100644 --- a/drivers/rtc/interface.c +++ b/drivers/rtc/interface.c @@ -675,8 +675,8 @@ EXPORT_SYMBOL_GPL(rtc_update_irq_enable); /** * rtc_handle_legacy_irq - AIE, UIE and PIE event hook * @rtc: pointer to the rtc device - * @num: number of occurence of the event - * @mode: type of the event, RTC_AF, RTC_UF of RTC_PF + * @num: number of occurrence of the event + * @mode: type of the event, RTC_AF, RTC_UF or RTC_PF * * This function is called when an AIE, UIE or PIE mode interrupt * has occurred (or been emulated). From 5e7f746bc106ad9cd300e161bff42f62a8bf1e6b Mon Sep 17 00:00:00 2001 From: Tommy Huang Date: Mon, 1 Jun 2026 17:14:06 +0800 Subject: [PATCH 146/297] dt-bindings: rtc: add ASPEED AST2700 compatible Document the compatible string for the RTC controller found on ASPEED AST2700 SoCs. Signed-off-by: Tommy Huang Acked-by: Conor Dooley Link: https://patch.msgid.link/20260601-ast2700-rtc-v1-1-15d4ca46500a@aspeedtech.com Signed-off-by: Alexandre Belloni --- Documentation/devicetree/bindings/rtc/trivial-rtc.yaml | 2 ++ 1 file changed, 2 insertions(+) diff --git a/Documentation/devicetree/bindings/rtc/trivial-rtc.yaml b/Documentation/devicetree/bindings/rtc/trivial-rtc.yaml index 722176c831aa..f4d0eed98a08 100644 --- a/Documentation/devicetree/bindings/rtc/trivial-rtc.yaml +++ b/Documentation/devicetree/bindings/rtc/trivial-rtc.yaml @@ -30,6 +30,8 @@ properties: - aspeed,ast2500-rtc # ASPEED BMC ast2600 Real-time Clock - aspeed,ast2600-rtc + # ASPEED BMC ast2700 Real-time Clock + - aspeed,ast2700-rtc # Conexant Digicolor Real Time Clock Controller - cnxt,cx92755-rtc # I2C, 32-Bit Binary Counter Watchdog RTC with Trickle Charger and Reset Input/Output From 3319cfeeb8c4047026f84df045c438f7bbd338a6 Mon Sep 17 00:00:00 2001 From: Tommy Huang Date: Mon, 1 Jun 2026 17:14:07 +0800 Subject: [PATCH 147/297] rtc: aspeed: add AST2700 compatible Add support for matching the RTC controller on ASPEED AST2700 SoCs. The AST2700 RTC controller is compatible with the existing ASPEED RTC driver implementation. Signed-off-by: Tommy Huang Link: https://patch.msgid.link/20260601-ast2700-rtc-v1-2-15d4ca46500a@aspeedtech.com Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-aspeed.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/rtc/rtc-aspeed.c b/drivers/rtc/rtc-aspeed.c index 0d0053b52f9b..8f5b440f8c0a 100644 --- a/drivers/rtc/rtc-aspeed.c +++ b/drivers/rtc/rtc-aspeed.c @@ -111,6 +111,7 @@ static const struct of_device_id aspeed_rtc_match[] = { { .compatible = "aspeed,ast2400-rtc", }, { .compatible = "aspeed,ast2500-rtc", }, { .compatible = "aspeed,ast2600-rtc", }, + { .compatible = "aspeed,ast2700-rtc", }, {} }; MODULE_DEVICE_TABLE(of, aspeed_rtc_match); From 851d961ff248218f681c53cf0f7f08cf8201a117 Mon Sep 17 00:00:00 2001 From: Xue Lei Date: Thu, 11 Jun 2026 10:33:50 +0800 Subject: [PATCH 148/297] rtc: mv: add suspend/resume support for wakeup Add PM suspend/resume callbacks to enable/disable IRQ wake for the RTC alarm interrupt. This allows the RTC alarm to wake the system from STR (e.g. via rtcwake -m mem -s N). Without this, the RTC IRQ is masked during suspend by the MPIC's IRQCHIP_MASK_ON_SUSPEND behavior, preventing alarm-based wakeup. Signed-off-by: Xue Lei Link: https://patch.msgid.link/20260611023350.1370881-1-Xue.Lei@windriver.com Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-mv.c | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) diff --git a/drivers/rtc/rtc-mv.c b/drivers/rtc/rtc-mv.c index c27ad626d09f..f88976fd6d5d 100644 --- a/drivers/rtc/rtc-mv.c +++ b/drivers/rtc/rtc-mv.c @@ -301,6 +301,28 @@ static const struct of_device_id rtc_mv_of_match_table[] = { MODULE_DEVICE_TABLE(of, rtc_mv_of_match_table); #endif +#ifdef CONFIG_PM_SLEEP +static int mv_rtc_suspend(struct device *dev) +{ + struct rtc_plat_data *pdata = dev_get_drvdata(dev); + + if (device_may_wakeup(dev) && pdata->irq >= 0) + enable_irq_wake(pdata->irq); + return 0; +} + +static int mv_rtc_resume(struct device *dev) +{ + struct rtc_plat_data *pdata = dev_get_drvdata(dev); + + if (device_may_wakeup(dev) && pdata->irq >= 0) + disable_irq_wake(pdata->irq); + return 0; +} +#endif + +static SIMPLE_DEV_PM_OPS(mv_rtc_pm_ops, mv_rtc_suspend, mv_rtc_resume); + /* * mv_rtc_remove() lives in .exit.text. For drivers registered via * module_platform_driver_probe() this is ok because they cannot get unbound at @@ -312,6 +334,7 @@ static struct platform_driver mv_rtc_driver __refdata = { .driver = { .name = "rtc-mv", .of_match_table = of_match_ptr(rtc_mv_of_match_table), + .pm = &mv_rtc_pm_ops, }, }; From c1016dd1d8b2bcd1158bbaabe94a31bb7e7431fb Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Mon, 15 Jun 2026 10:00:00 +0900 Subject: [PATCH 149/297] ksmbd: track the connection owning a byte-range lock SMB2_LOCK adds each granted byte-range lock to both the file lock list and the lock list of the connection which handled the request. The final close and durable handle paths, however, remove the connection list entry while holding fp->conn->llist_lock. With SMB3 multichannel, the connection handling the LOCK request can be different from the connection which opened the file. The entry can therefore be removed under a different spinlock from the one protecting the list it belongs to. A concurrent traversal can then access freed struct ksmbd_lock and struct file_lock objects. Record the connection owning each lock's clist entry and hold a reference to it while the entry is linked. Use that connection and its llist_lock for unlock, rollback, close, and durable preserve. Durable reconnect assigns the new connection as the owner when publishing the locks again. Fixes: f5a544e3bab7 ("ksmbd: add support for SMB3 multichannel") Cc: stable@vger.kernel.org Reported-by: Musaab Khan Signed-off-by: Namjae Jeon Signed-off-by: Steve French --- fs/smb/server/smb2pdu.c | 10 ++++++++-- fs/smb/server/vfs_cache.c | 23 +++++++++++++++++------ fs/smb/server/vfs_cache.h | 1 + 3 files changed, 26 insertions(+), 8 deletions(-) diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index c1c6c1a64f60..ba24040d05eb 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -7774,9 +7774,11 @@ int smb2_lock(struct ksmbd_work *work) nolock = 0; list_del(&cmp_lock->flist); list_del(&cmp_lock->clist); + cmp_lock->conn = NULL; spin_unlock(&conn->llist_lock); up_read(&conn_list_lock); + ksmbd_conn_put(conn); locks_free_lock(cmp_lock->fl); kfree(cmp_lock); goto out_check_cl; @@ -7911,6 +7913,7 @@ skip: goto out2; } else if (!rc) { list_add(&smb_lock->llist, &rollback_list); + smb_lock->conn = ksmbd_conn_get(work->conn); spin_lock(&work->conn->llist_lock); list_add_tail(&smb_lock->clist, &work->conn->lock_list); @@ -7965,11 +7968,14 @@ out: } list_del(&smb_lock->llist); - spin_lock(&work->conn->llist_lock); + conn = smb_lock->conn; + spin_lock(&conn->llist_lock); if (!list_empty(&smb_lock->flist)) list_del(&smb_lock->flist); list_del(&smb_lock->clist); - spin_unlock(&work->conn->llist_lock); + smb_lock->conn = NULL; + spin_unlock(&conn->llist_lock); + ksmbd_conn_put(conn); locks_free_lock(smb_lock->fl); if (rlock) diff --git a/fs/smb/server/vfs_cache.c b/fs/smb/server/vfs_cache.c index 8c556e46cc10..39c56942ae44 100644 --- a/fs/smb/server/vfs_cache.c +++ b/fs/smb/server/vfs_cache.c @@ -484,10 +484,14 @@ static void __ksmbd_close_fd(struct ksmbd_file_table *ft, struct ksmbd_file *fp) * there are not accesses to fp->lock_list. */ list_for_each_entry_safe(smb_lock, tmp_lock, &fp->lock_list, flist) { - if (!list_empty(&smb_lock->clist) && fp->conn) { - spin_lock(&fp->conn->llist_lock); - list_del(&smb_lock->clist); - spin_unlock(&fp->conn->llist_lock); + struct ksmbd_conn *conn = smb_lock->conn; + + if (conn) { + spin_lock(&conn->llist_lock); + list_del_init(&smb_lock->clist); + smb_lock->conn = NULL; + spin_unlock(&conn->llist_lock); + ksmbd_conn_put(conn); } list_del(&smb_lock->flist); @@ -1303,9 +1307,15 @@ static bool session_fd_check(struct ksmbd_tree_connect *tcon, up_write(&ci->m_lock); list_for_each_entry_safe(smb_lock, tmp_lock, &fp->lock_list, flist) { - spin_lock(&conn->llist_lock); + struct ksmbd_conn *lock_conn = smb_lock->conn; + + if (!lock_conn) + continue; + spin_lock(&lock_conn->llist_lock); list_del_init(&smb_lock->clist); - spin_unlock(&conn->llist_lock); + smb_lock->conn = NULL; + spin_unlock(&lock_conn->llist_lock); + ksmbd_conn_put(lock_conn); } fp->conn = NULL; @@ -1435,6 +1445,7 @@ int ksmbd_reopen_durable_fd(struct ksmbd_work *work, struct ksmbd_file *fp) } list_for_each_entry(smb_lock, &fp->lock_list, flist) { + smb_lock->conn = ksmbd_conn_get(conn); spin_lock(&conn->llist_lock); list_add_tail(&smb_lock->clist, &conn->lock_list); spin_unlock(&conn->llist_lock); diff --git a/fs/smb/server/vfs_cache.h b/fs/smb/server/vfs_cache.h index 7d547e1a74f7..a3a9fda6de91 100644 --- a/fs/smb/server/vfs_cache.h +++ b/fs/smb/server/vfs_cache.h @@ -32,6 +32,7 @@ struct ksmbd_session; struct ksmbd_lock { struct file_lock *fl; + struct ksmbd_conn *conn; struct list_head clist; struct list_head flist; struct list_head llist; From 37ee476071bcbf4fa97a5a7b208b3a51073b4fcc Mon Sep 17 00:00:00 2001 From: ChenXiaoSong Date: Wed, 17 Jun 2026 02:36:32 +0000 Subject: [PATCH 150/297] smb/server: fix debug log endianness in smb2_cancel() Convert to CPU byte order to avoid incorrect debug log on big-endian architectures. Signed-off-by: ChenXiaoSong Acked-by: Namjae Jeon Signed-off-by: Steve French --- fs/smb/server/smb2pdu.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index ba24040d05eb..95c7b09c6743 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -7459,7 +7459,8 @@ int smb2_cancel(struct ksmbd_work *work) hdr = ksmbd_resp_buf_next(work); ksmbd_debug(SMB, "smb2 cancel called on mid %llu, async flags 0x%x\n", - hdr->MessageId, hdr->Flags); + le64_to_cpu(hdr->MessageId), + le32_to_cpu(hdr->Flags)); if (hdr->Flags & SMB2_FLAGS_ASYNC_COMMAND) { command_list = &conn->async_requests; From b69be2c58615950ee7353b61a21acdf8508c0cbb Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Thu, 18 Jun 2026 10:32:44 +0900 Subject: [PATCH 151/297] ksmbd: validate SMB2 lease create contexts Validate SMB2 lease context lengths, requested lease state bits, and v2 flags before using the context. Return errors via ERR_PTR so CREATE can distinguish a missing lease context from a malformed one. Also ignore lease v2 contexts for SMB 2.1, where they are not valid. Signed-off-by: Namjae Jeon Signed-off-by: Steve French --- fs/smb/server/oplock.c | 33 ++++++++++++++++++++++++++++----- fs/smb/server/smb2pdu.c | 24 +++++++++++++++++++++++- 2 files changed, 51 insertions(+), 6 deletions(-) diff --git a/fs/smb/server/oplock.c b/fs/smb/server/oplock.c index 60e7e821c245..5c6c0550a477 100644 --- a/fs/smb/server/oplock.c +++ b/fs/smb/server/oplock.c @@ -5,6 +5,7 @@ */ #include +#include #include "glob.h" #include "oplock.h" @@ -19,6 +20,20 @@ static LIST_HEAD(lease_table_list); static DEFINE_RWLOCK(lease_list_lock); +#define SMB2_LEASE_STATE_MASK_LE (SMB2_LEASE_READ_CACHING_LE | \ + SMB2_LEASE_HANDLE_CACHING_LE | \ + SMB2_LEASE_WRITE_CACHING_LE) + +static bool lease_state_valid(__le32 state) +{ + return !(state & ~SMB2_LEASE_STATE_MASK_LE); +} + +static bool lease_v2_flags_valid(__le32 flags) +{ + return !(flags & ~SMB2_LEASE_FLAG_PARENT_LEASE_KEY_SET_LE); +} + /** * alloc_opinfo() - allocate a new opinfo object for oplock info * @work: smb work @@ -1537,12 +1552,14 @@ struct lease_ctx_info *parse_lease_state(void *open_req) struct lease_ctx_info *lreq; cc = smb2_find_context_vals(req, SMB2_CREATE_REQUEST_LEASE, 4); - if (IS_ERR_OR_NULL(cc)) + if (IS_ERR(cc)) + return ERR_CAST(cc); + if (!cc) return NULL; lreq = kzalloc_obj(struct lease_ctx_info, KSMBD_DEFAULT_GFP); if (!lreq) - return NULL; + return ERR_PTR(-ENOMEM); if (sizeof(struct lease_context_v2) == le32_to_cpu(cc->DataLength)) { struct create_lease_v2 *lc = (struct create_lease_v2 *)cc; @@ -1556,11 +1573,14 @@ struct lease_ctx_info *parse_lease_state(void *open_req) lreq->flags = lc->lcontext.LeaseFlags; lreq->epoch = lc->lcontext.Epoch; lreq->duration = lc->lcontext.LeaseDuration; + if (!lease_state_valid(lreq->req_state) || + !lease_v2_flags_valid(lreq->flags)) + goto err_out; if (lreq->flags == SMB2_LEASE_FLAG_PARENT_LEASE_KEY_SET_LE) memcpy(lreq->parent_lease_key, lc->lcontext.ParentLeaseKey, SMB2_LEASE_KEY_SIZE); lreq->version = 2; - } else { + } else if (sizeof(struct lease_context) == le32_to_cpu(cc->DataLength)) { struct create_lease *lc = (struct create_lease *)cc; if (le16_to_cpu(cc->DataOffset) + le32_to_cpu(cc->DataLength) < @@ -1571,12 +1591,15 @@ struct lease_ctx_info *parse_lease_state(void *open_req) lreq->req_state = lc->lcontext.LeaseState; lreq->flags = lc->lcontext.LeaseFlags; lreq->duration = lc->lcontext.LeaseDuration; + if (!lease_state_valid(lreq->req_state)) + goto err_out; lreq->version = 1; - } + } else + goto err_out; return lreq; err_out: kfree(lreq); - return NULL; + return ERR_PTR(-EINVAL); } /** diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index 95c7b09c6743..19e819898fd0 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -3108,6 +3108,17 @@ int smb2_open(struct ksmbd_work *work) if (server_conf.flags & KSMBD_GLOBAL_FLAG_DURABLE_HANDLE && req->CreateContextsOffset) { lc = parse_lease_state(req); + if (IS_ERR(lc)) { + rc = PTR_ERR(lc); + lc = NULL; + goto err_out2; + } + if (lc && lc->version == 2 && conn->dialect < SMB30_PROT_ID) { + kfree(lc); + lc = NULL; + if (req_op_level == SMB2_OPLOCK_LEVEL_LEASE) + req_op_level = SMB2_OPLOCK_LEVEL_NONE; + } rc = parse_durable_handle_context(work, req, lc, &dh_info); if (rc) { ksmbd_debug(SMB, "error parsing durable handle context\n"); @@ -3139,8 +3150,19 @@ int smb2_open(struct ksmbd_work *work) goto reconnected_fp; } - } else if (req_op_level == SMB2_OPLOCK_LEVEL_LEASE) + } else if (req_op_level == SMB2_OPLOCK_LEVEL_LEASE) { lc = parse_lease_state(req); + if (IS_ERR(lc)) { + rc = PTR_ERR(lc); + lc = NULL; + goto err_out2; + } + if (lc && lc->version == 2 && conn->dialect < SMB30_PROT_ID) { + kfree(lc); + lc = NULL; + req_op_level = SMB2_OPLOCK_LEVEL_NONE; + } + } if (le32_to_cpu(req->ImpersonationLevel) > le32_to_cpu(IL_DELEGATE)) { pr_err("Invalid impersonationlevel : 0x%x\n", From fa111daae1a02dbff5693dfc12f368bccd9eb5f4 Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Thu, 18 Jun 2026 10:33:20 +0900 Subject: [PATCH 152/297] ksmbd: use connection ClientGUID for lease lookup MS-SMB2 defines the lease table lookup key as Connection.ClientGuid. Use the connection ClientGUID consistently when checking for same-client leases and duplicate lease keys. Also preserve directory and parent lease metadata when copying an existing lease state to a new open. Signed-off-by: Namjae Jeon Signed-off-by: Steve French --- fs/smb/server/oplock.c | 16 +++++++++------- fs/smb/server/oplock.h | 2 +- fs/smb/server/smb2pdu.c | 2 +- 3 files changed, 11 insertions(+), 9 deletions(-) diff --git a/fs/smb/server/oplock.c b/fs/smb/server/oplock.c index 5c6c0550a477..627cea7fd7ea 100644 --- a/fs/smb/server/oplock.c +++ b/fs/smb/server/oplock.c @@ -520,7 +520,7 @@ static inline int compare_guid_key(struct oplock_info *opinfo, * Return: oplock(lease) object on success, otherwise NULL */ static struct oplock_info *same_client_has_lease(struct ksmbd_inode *ci, - char *client_guid, + const char *client_guid, struct lease_ctx_info *lctx) { int ret; @@ -1012,7 +1012,7 @@ again: write_unlock(&lease_list_lock); } -int find_same_lease_key(struct ksmbd_session *sess, struct ksmbd_inode *ci, +int find_same_lease_key(struct ksmbd_conn *conn, struct ksmbd_inode *ci, struct lease_ctx_info *lctx) { struct oplock_info *opinfo; @@ -1029,7 +1029,7 @@ int find_same_lease_key(struct ksmbd_session *sess, struct ksmbd_inode *ci, } list_for_each_entry(lb, &lease_table_list, l_entry) { - if (!memcmp(lb->client_guid, sess->ClientGUID, + if (!memcmp(lb->client_guid, conn->ClientGUID, SMB2_CLIENT_GUID_SIZE)) goto found; } @@ -1045,7 +1045,7 @@ found: rcu_read_unlock(); if (opinfo->o_fp->f_ci == ci) goto op_next; - err = compare_guid_key(opinfo, sess->ClientGUID, + err = compare_guid_key(opinfo, conn->ClientGUID, lctx->lease_key); if (err) { err = -EINVAL; @@ -1078,6 +1078,9 @@ static void copy_lease(struct oplock_info *op1, struct oplock_info *op2) lease2->flags = lease1->flags; lease2->epoch = lease1->epoch; lease2->version = lease1->version; + lease2->is_dir = lease1->is_dir; + memcpy(lease2->parent_lease_key, lease1->parent_lease_key, + SMB2_LEASE_KEY_SIZE); } static void add_lease_global_list(struct oplock_info *opinfo, @@ -1216,7 +1219,6 @@ int smb_grant_oplock(struct ksmbd_work *work, int req_op_level, u64 pid, struct ksmbd_file *fp, __u16 tid, struct lease_ctx_info *lctx, int share_ret) { - struct ksmbd_session *sess = work->sess; int err = 0; struct oplock_info *opinfo = NULL, *prev_opinfo = NULL; struct ksmbd_inode *ci = fp->f_ci; @@ -1259,12 +1261,12 @@ int smb_grant_oplock(struct ksmbd_work *work, int req_op_level, u64 pid, struct oplock_info *m_opinfo; /* is lease already granted ? */ - m_opinfo = same_client_has_lease(ci, sess->ClientGUID, + m_opinfo = same_client_has_lease(ci, work->conn->ClientGUID, lctx); if (m_opinfo) { copy_lease(m_opinfo, opinfo); if (atomic_read(&m_opinfo->breaking_cnt)) - opinfo->o_lease->flags = + opinfo->o_lease->flags |= SMB2_LEASE_FLAG_BREAK_IN_PROGRESS_LE; opinfo_put(m_opinfo); goto out; diff --git a/fs/smb/server/oplock.h b/fs/smb/server/oplock.h index d91a8266e065..795a9119dad9 100644 --- a/fs/smb/server/oplock.h +++ b/fs/smb/server/oplock.h @@ -116,7 +116,7 @@ void create_posix_rsp_buf(char *cc, struct ksmbd_file *fp); struct create_context *smb2_find_context_vals(void *open_req, const char *tag, int tag_len); struct oplock_info *lookup_lease_in_table(struct ksmbd_conn *conn, char *lease_key); -int find_same_lease_key(struct ksmbd_session *sess, struct ksmbd_inode *ci, +int find_same_lease_key(struct ksmbd_conn *conn, struct ksmbd_inode *ci, struct lease_ctx_info *lctx); void destroy_lease_table(struct ksmbd_conn *conn); void smb_send_parent_lease_break_noti(struct ksmbd_file *fp, diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index 19e819898fd0..0766f0d662be 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -3637,7 +3637,7 @@ int smb2_open(struct ksmbd_work *work) ksmbd_debug(SMB, "lease req for(%s) req oplock state 0x%x, lease state 0x%x\n", name, req_op_level, lc->req_state); - rc = find_same_lease_key(sess, fp->f_ci, lc); + rc = find_same_lease_key(conn, fp->f_ci, lc); if (rc) goto err_out1; } else if (open_flags == O_RDONLY && From 5015191096db311759fef98769270336cd8b1324 Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Thu, 18 Jun 2026 10:33:53 +0900 Subject: [PATCH 153/297] ksmbd: fix lease break and ack state handling Do not skip valid lease states containing WRITE_CACHING when breaking level-II/read leases for writes and truncates. Handle lease break acknowledgments according to the SMB2 rule that the acknowledged state must be a subset of the server's break target. Apply the acknowledged state directly and keep the break pending on failed ACKs. Signed-off-by: Namjae Jeon Signed-off-by: Steve French --- fs/smb/server/oplock.c | 24 +++------ fs/smb/server/smb2pdu.c | 106 ++++++++++------------------------------ 2 files changed, 34 insertions(+), 96 deletions(-) diff --git a/fs/smb/server/oplock.c b/fs/smb/server/oplock.c index 627cea7fd7ea..cc5eb95ab3f2 100644 --- a/fs/smb/server/oplock.c +++ b/fs/smb/server/oplock.c @@ -1419,14 +1419,8 @@ void smb_break_all_levII_oplock(struct ksmbd_work *work, struct ksmbd_file *fp, continue; } - if (brk_op->is_lease && (brk_op->o_lease->state & - (~(SMB2_LEASE_READ_CACHING_LE | - SMB2_LEASE_HANDLE_CACHING_LE)))) { - ksmbd_debug(OPLOCK, "unexpected lease state(0x%x)\n", - brk_op->o_lease->state); - goto next; - } else if (brk_op->level != - SMB2_OPLOCK_LEVEL_II) { + if (!brk_op->is_lease && + brk_op->level != SMB2_OPLOCK_LEVEL_II) { ksmbd_debug(OPLOCK, "unexpected oplock(0x%x)\n", brk_op->level); goto next; @@ -1478,15 +1472,13 @@ void smb_break_all_oplock(struct ksmbd_work *work, struct ksmbd_file *fp) */ __u8 smb2_map_lease_to_oplock(__le32 lease_state) { - if (lease_state == (SMB2_LEASE_HANDLE_CACHING_LE | - SMB2_LEASE_READ_CACHING_LE | - SMB2_LEASE_WRITE_CACHING_LE)) { + if ((lease_state & SMB2_LEASE_WRITE_CACHING_LE) && + (lease_state & SMB2_LEASE_HANDLE_CACHING_LE)) { return SMB2_OPLOCK_LEVEL_BATCH; - } else if (lease_state != SMB2_LEASE_WRITE_CACHING_LE && - lease_state & SMB2_LEASE_WRITE_CACHING_LE) { - if (!(lease_state & SMB2_LEASE_HANDLE_CACHING_LE)) - return SMB2_OPLOCK_LEVEL_EXCLUSIVE; - } else if (lease_state & SMB2_LEASE_READ_CACHING_LE) { + } else if (lease_state & SMB2_LEASE_WRITE_CACHING_LE) { + return SMB2_OPLOCK_LEVEL_EXCLUSIVE; + } else if (lease_state & (SMB2_LEASE_READ_CACHING_LE | + SMB2_LEASE_HANDLE_CACHING_LE)) { return SMB2_OPLOCK_LEVEL_II; } return 0; diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index 0766f0d662be..75ee9184e553 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -9013,16 +9013,17 @@ err_out: ksmbd_fd_put(work, fp); } +static bool smb2_lease_state_valid(__le32 state) +{ + return !(state & ~(SMB2_LEASE_READ_CACHING_LE | + SMB2_LEASE_HANDLE_CACHING_LE | + SMB2_LEASE_WRITE_CACHING_LE)); +} + static int check_lease_state(struct lease *lease, __le32 req_state) { - if ((lease->new_state == - (SMB2_LEASE_READ_CACHING_LE | SMB2_LEASE_HANDLE_CACHING_LE)) && - !(req_state & SMB2_LEASE_WRITE_CACHING_LE)) { - lease->new_state = req_state; - return 0; - } - - if (lease->new_state == req_state) + if (smb2_lease_state_valid(req_state) && + !(req_state & ~lease->new_state)) return 0; return 1; @@ -9040,9 +9041,7 @@ static void smb21_lease_break_ack(struct ksmbd_work *work) struct smb2_lease_ack *req; struct smb2_lease_ack *rsp; struct oplock_info *opinfo; - __le32 err = 0; int ret = 0; - unsigned int lease_change_type; __le32 lease_state; struct lease *lease; @@ -9066,6 +9065,11 @@ static void smb21_lease_break_ack(struct ksmbd_work *work) goto err_out; } + if (!atomic_read(&opinfo->breaking_cnt)) { + rsp->hdr.Status = STATUS_UNSUCCESSFUL; + goto err_out; + } + if (check_lease_state(lease, req->LeaseState)) { rsp->hdr.Status = STATUS_REQUEST_NOT_ACCEPTED; ksmbd_debug(OPLOCK, @@ -9074,72 +9078,10 @@ static void smb21_lease_break_ack(struct ksmbd_work *work) goto err_out; } - if (!atomic_read(&opinfo->breaking_cnt)) { - rsp->hdr.Status = STATUS_UNSUCCESSFUL; - goto err_out; - } - - /* check for bad lease state */ - if (req->LeaseState & - (~(SMB2_LEASE_READ_CACHING_LE | SMB2_LEASE_HANDLE_CACHING_LE))) { - err = STATUS_INVALID_OPLOCK_PROTOCOL; - if (lease->state & SMB2_LEASE_WRITE_CACHING_LE) - lease_change_type = OPLOCK_WRITE_TO_NONE; - else - lease_change_type = OPLOCK_READ_TO_NONE; - ksmbd_debug(OPLOCK, "handle bad lease state 0x%x -> 0x%x\n", - le32_to_cpu(lease->state), - le32_to_cpu(req->LeaseState)); - } else if (lease->state == SMB2_LEASE_READ_CACHING_LE && - req->LeaseState != SMB2_LEASE_NONE_LE) { - err = STATUS_INVALID_OPLOCK_PROTOCOL; - lease_change_type = OPLOCK_READ_TO_NONE; - ksmbd_debug(OPLOCK, "handle bad lease state 0x%x -> 0x%x\n", - le32_to_cpu(lease->state), - le32_to_cpu(req->LeaseState)); - } else { - /* valid lease state changes */ - err = STATUS_INVALID_DEVICE_STATE; - if (req->LeaseState == SMB2_LEASE_NONE_LE) { - if (lease->state & SMB2_LEASE_WRITE_CACHING_LE) - lease_change_type = OPLOCK_WRITE_TO_NONE; - else - lease_change_type = OPLOCK_READ_TO_NONE; - } else if (req->LeaseState & SMB2_LEASE_READ_CACHING_LE) { - if (lease->state & SMB2_LEASE_WRITE_CACHING_LE) - lease_change_type = OPLOCK_WRITE_TO_READ; - else - lease_change_type = OPLOCK_READ_HANDLE_TO_READ; - } else { - lease_change_type = 0; - } - } - - switch (lease_change_type) { - case OPLOCK_WRITE_TO_READ: - ret = opinfo_write_to_read(opinfo); - break; - case OPLOCK_READ_HANDLE_TO_READ: - ret = opinfo_read_handle_to_read(opinfo); - break; - case OPLOCK_WRITE_TO_NONE: - ret = opinfo_write_to_none(opinfo); - break; - case OPLOCK_READ_TO_NONE: - ret = opinfo_read_to_none(opinfo); - break; - default: - ksmbd_debug(OPLOCK, "unknown lease change 0x%x -> 0x%x\n", - le32_to_cpu(lease->state), - le32_to_cpu(req->LeaseState)); - } - - if (ret < 0) { - rsp->hdr.Status = err; - goto err_out; - } - - lease_state = lease->state; + lease_state = req->LeaseState; + lease->state = lease_state; + lease->new_state = SMB2_LEASE_NONE_LE; + opinfo->level = smb2_map_lease_to_oplock(lease_state); rsp->StructureSize = cpu_to_le16(36); rsp->Reserved = 0; @@ -9148,16 +9090,20 @@ static void smb21_lease_break_ack(struct ksmbd_work *work) rsp->LeaseState = lease_state; rsp->LeaseDuration = 0; ret = ksmbd_iov_pin_rsp(work, rsp, sizeof(struct smb2_lease_ack)); - if (ret) { -err_out: - smb2_set_err_rsp(work); - } + if (ret) + goto err_out; opinfo->op_state = OPLOCK_STATE_NONE; wake_up_interruptible_all(&opinfo->oplock_q); atomic_dec(&opinfo->breaking_cnt); wake_up_interruptible_all(&opinfo->oplock_brk); opinfo_put(opinfo); + return; + +err_out: + smb2_set_err_rsp(work); + opinfo_put(opinfo); + return; } /** From 0fa8abc6ab6dcc571f76c1e05ad3582540fb56d5 Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Thu, 18 Jun 2026 10:34:24 +0900 Subject: [PATCH 154/297] ksmbd: clean up lease response flags and directory leases Do not echo reserved v1 lease flags back to clients. For lease v2 responses, only return BREAK_IN_PROGRESS and PARENT_LEASE_KEY_SET when they are meaningful, and preserve the parent lease key in the response. Allow directory leases whenever the request is a valid lease v2 request, and initialize v2 lease epochs from the first server-granted state change. Signed-off-by: Namjae Jeon Signed-off-by: Steve French --- fs/smb/server/oplock.c | 23 +++++++++++++++-------- 1 file changed, 15 insertions(+), 8 deletions(-) diff --git a/fs/smb/server/oplock.c b/fs/smb/server/oplock.c index cc5eb95ab3f2..8ae6a6afbe04 100644 --- a/fs/smb/server/oplock.c +++ b/fs/smb/server/oplock.c @@ -34,6 +34,11 @@ static bool lease_v2_flags_valid(__le32 flags) return !(flags & ~SMB2_LEASE_FLAG_PARENT_LEASE_KEY_SET_LE); } +static bool lease_has_parent_key(struct lease *lease) +{ + return lease->flags & SMB2_LEASE_FLAG_PARENT_LEASE_KEY_SET_LE; +} + /** * alloc_opinfo() - allocate a new opinfo object for oplock info * @work: smb work @@ -126,7 +131,7 @@ static int alloc_lease(struct oplock_info *opinfo, struct lease_ctx_info *lctx) lease->is_dir = lctx->is_dir; memcpy(lease->parent_lease_key, lctx->parent_lease_key, SMB2_LEASE_KEY_SIZE); lease->version = lctx->version; - lease->epoch = le16_to_cpu(lctx->epoch) + 1; + lease->epoch = lctx->version == 2 ? 1 : 0; INIT_LIST_HEAD(&opinfo->lease_entry); opinfo->o_lease = lease; @@ -1228,9 +1233,7 @@ int smb_grant_oplock(struct ksmbd_work *work, int req_op_level, u64 pid, /* Only v2 leases handle the directory */ if (S_ISDIR(file_inode(fp->filp)->i_mode)) { - if (!lctx || lctx->version != 2 || - (lctx->flags != SMB2_LEASE_FLAG_PARENT_LEASE_KEY_SET_LE && - !lctx->epoch)) + if (!lctx || lctx->version != 2) return 0; } @@ -1493,14 +1496,17 @@ void create_lease_buf(u8 *rbuf, struct lease *lease) { if (lease->version == 2) { struct create_lease_v2 *buf = (struct create_lease_v2 *)rbuf; + __le32 flags = lease->flags & SMB2_LEASE_FLAG_BREAK_IN_PROGRESS_LE; memset(buf, 0, sizeof(struct create_lease_v2)); memcpy(buf->lcontext.LeaseKey, lease->lease_key, SMB2_LEASE_KEY_SIZE); - buf->lcontext.LeaseFlags = lease->flags; + if (lease_has_parent_key(lease)) + flags |= SMB2_LEASE_FLAG_PARENT_LEASE_KEY_SET_LE; + buf->lcontext.LeaseFlags = flags; buf->lcontext.Epoch = cpu_to_le16(lease->epoch); buf->lcontext.LeaseState = lease->state; - if (lease->flags == SMB2_LEASE_FLAG_PARENT_LEASE_KEY_SET_LE) + if (lease_has_parent_key(lease)) memcpy(buf->lcontext.ParentLeaseKey, lease->parent_lease_key, SMB2_LEASE_KEY_SIZE); buf->ccontext.DataOffset = cpu_to_le16(offsetof @@ -1518,7 +1524,8 @@ void create_lease_buf(u8 *rbuf, struct lease *lease) memset(buf, 0, sizeof(struct create_lease)); memcpy(buf->lcontext.LeaseKey, lease->lease_key, SMB2_LEASE_KEY_SIZE); - buf->lcontext.LeaseFlags = lease->flags; + buf->lcontext.LeaseFlags = + lease->flags & SMB2_LEASE_FLAG_BREAK_IN_PROGRESS_LE; buf->lcontext.LeaseState = lease->state; buf->ccontext.DataOffset = cpu_to_le16(offsetof (struct create_lease, lcontext)); @@ -1583,7 +1590,7 @@ struct lease_ctx_info *parse_lease_state(void *open_req) memcpy(lreq->lease_key, lc->lcontext.LeaseKey, SMB2_LEASE_KEY_SIZE); lreq->req_state = lc->lcontext.LeaseState; - lreq->flags = lc->lcontext.LeaseFlags; + lreq->flags = 0; lreq->duration = lc->lcontext.LeaseDuration; if (!lease_state_valid(lreq->req_state)) goto err_out; From 079927f5fda5a05355a620d794e2f4b9eb1f70fd Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Thu, 18 Jun 2026 10:35:06 +0900 Subject: [PATCH 155/297] ksmbd: share SMB2 lease state across opens Model SMB2 leases as per-client/per-key objects instead of keeping a separate lease copy in every oplock_info. The lease table now stores lease objects and each lease tracks the opens that reference it. This makes same ClientGuid/LeaseKey opens observe a single lease state, so lease upgrades, breaks, ACKs, and close teardown do not diverge across per-open copies. Keep one reference for the lease table entry and one reference for each open, and remove the table entry when the last open is detached. Update lease break ACK handling to refresh all open oplock levels from the shared lease state. Signed-off-by: Namjae Jeon Signed-off-by: Steve French --- fs/smb/server/oplock.c | 262 ++++++++++++++++++++++------------------ fs/smb/server/oplock.h | 6 + fs/smb/server/smb2pdu.c | 2 +- 3 files changed, 151 insertions(+), 119 deletions(-) diff --git a/fs/smb/server/oplock.c b/fs/smb/server/oplock.c index 8ae6a6afbe04..81716317bb61 100644 --- a/fs/smb/server/oplock.c +++ b/fs/smb/server/oplock.c @@ -65,6 +65,7 @@ static struct oplock_info *alloc_opinfo(struct ksmbd_work *work, opinfo->fid = id; opinfo->Tid = Tid; INIT_LIST_HEAD(&opinfo->op_entry); + INIT_LIST_HEAD(&opinfo->lease_entry); init_waitqueue_head(&opinfo->oplock_q); init_waitqueue_head(&opinfo->oplock_brk); atomic_set(&opinfo->refcount, 1); @@ -73,31 +74,44 @@ static struct oplock_info *alloc_opinfo(struct ksmbd_work *work, return opinfo; } -static void lease_add_list(struct oplock_info *opinfo) +static void lease_get(struct lease *lease) { - struct lease_table *lb = opinfo->o_lease->l_lb; + atomic_inc(&lease->refcount); +} +static void lease_put(struct lease *lease) +{ + if (lease && atomic_dec_and_test(&lease->refcount)) + kfree(lease); +} + +static void lease_add_table(struct lease *lease, struct lease_table *lb) +{ + lease_get(lease); + lease->l_lb = lb; spin_lock(&lb->lb_lock); - list_add_rcu(&opinfo->lease_entry, &lb->lease_list); + list_add_rcu(&lease->l_entry, &lb->lease_list); spin_unlock(&lb->lb_lock); } -static void lease_del_list(struct oplock_info *opinfo) +static void lease_del_table(struct lease *lease) { - struct lease_table *lb = opinfo->o_lease->l_lb; + struct lease_table *lb = lease->l_lb; if (!lb) return; spin_lock(&lb->lb_lock); - if (list_empty(&opinfo->lease_entry)) { + if (list_empty(&lease->l_entry)) { spin_unlock(&lb->lb_lock); return; } - list_del_init(&opinfo->lease_entry); - opinfo->o_lease->l_lb = NULL; + list_del_init(&lease->l_entry); + lease->l_lb = NULL; spin_unlock(&lb->lb_lock); + + lease_put(lease); } static struct lease_table *alloc_lease_table(struct oplock_info *opinfo) @@ -115,13 +129,14 @@ static struct lease_table *alloc_lease_table(struct oplock_info *opinfo) return lb; } -static int alloc_lease(struct oplock_info *opinfo, struct lease_ctx_info *lctx) +static struct lease *alloc_lease(struct lease_ctx_info *lctx, + struct ksmbd_inode *ci) { struct lease *lease; lease = kmalloc_obj(struct lease, KSMBD_DEFAULT_GFP); if (!lease) - return -ENOMEM; + return NULL; memcpy(lease->lease_key, lctx->lease_key, SMB2_LEASE_KEY_SIZE); lease->state = lctx->req_state; @@ -132,18 +147,48 @@ static int alloc_lease(struct oplock_info *opinfo, struct lease_ctx_info *lctx) memcpy(lease->parent_lease_key, lctx->parent_lease_key, SMB2_LEASE_KEY_SIZE); lease->version = lctx->version; lease->epoch = lctx->version == 2 ? 1 : 0; - INIT_LIST_HEAD(&opinfo->lease_entry); - opinfo->o_lease = lease; + lease->ci = ci; + lease->l_lb = NULL; + INIT_LIST_HEAD(&lease->l_entry); + INIT_LIST_HEAD(&lease->open_list); + spin_lock_init(&lease->lock); + atomic_set(&lease->refcount, 1); - return 0; + return lease; +} + +static void lease_add_open(struct lease *lease, struct oplock_info *opinfo) +{ + spin_lock(&lease->lock); + list_add(&opinfo->lease_entry, &lease->open_list); + spin_unlock(&lease->lock); +} + +static void lease_del_open(struct oplock_info *opinfo) +{ + struct lease *lease = opinfo->o_lease; + bool remove_table = false; + + if (!lease) + return; + + spin_lock(&lease->lock); + if (!list_empty(&opinfo->lease_entry)) { + list_del_init(&opinfo->lease_entry); + remove_table = list_empty(&lease->open_list); + } + spin_unlock(&lease->lock); + + if (remove_table) { + write_lock(&lease_list_lock); + lease_del_table(lease); + write_unlock(&lease_list_lock); + } } static void free_lease(struct oplock_info *opinfo) { - struct lease *lease; - - lease = opinfo->o_lease; - kfree(lease); + lease_put(opinfo->o_lease); } static void __free_opinfo(struct oplock_info *opinfo) @@ -166,6 +211,21 @@ static void free_opinfo(struct oplock_info *opinfo) call_rcu(&opinfo->rcu, free_opinfo_rcu); } +void lease_update_oplock_levels(struct lease *lease) +{ + struct oplock_info *opinfo; + __u8 level; + + if (!lease) + return; + + level = smb2_map_lease_to_oplock(lease->state); + spin_lock(&lease->lock); + list_for_each_entry(opinfo, &lease->open_list, lease_entry) + opinfo->level = level; + spin_unlock(&lease->lock); +} + struct oplock_info *opinfo_get(struct ksmbd_file *fp) { struct oplock_info *opinfo; @@ -226,11 +286,9 @@ static void opinfo_del(struct oplock_info *opinfo) { struct ksmbd_inode *ci = opinfo->o_fp->f_ci; - if (opinfo->is_lease) { - write_lock(&lease_list_lock); - lease_del_list(opinfo); - write_unlock(&lease_list_lock); - } + if (opinfo->is_lease) + lease_del_open(opinfo); + down_write(&ci->m_lock); list_del(&opinfo->op_entry); up_write(&ci->m_lock); @@ -279,8 +337,10 @@ int opinfo_write_to_read(struct oplock_info *opinfo) } opinfo->level = SMB2_OPLOCK_LEVEL_II; - if (opinfo->is_lease) + if (opinfo->is_lease) { lease->state = lease->new_state; + lease_update_oplock_levels(lease); + } return 0; } @@ -295,7 +355,7 @@ int opinfo_read_handle_to_read(struct oplock_info *opinfo) struct lease *lease = opinfo->o_lease; lease->state = lease->new_state; - opinfo->level = SMB2_OPLOCK_LEVEL_II; + lease_update_oplock_levels(lease); return 0; } @@ -317,8 +377,10 @@ int opinfo_write_to_none(struct oplock_info *opinfo) return -EINVAL; } opinfo->level = SMB2_OPLOCK_LEVEL_NONE; - if (opinfo->is_lease) + if (opinfo->is_lease) { lease->state = lease->new_state; + lease_update_oplock_levels(lease); + } return 0; } @@ -339,8 +401,10 @@ int opinfo_read_to_none(struct oplock_info *opinfo) return -EINVAL; } opinfo->level = SMB2_OPLOCK_LEVEL_NONE; - if (opinfo->is_lease) + if (opinfo->is_lease) { lease->state = lease->new_state; + lease_update_oplock_levels(lease); + } return 0; } @@ -361,10 +425,7 @@ int lease_read_to_write(struct oplock_info *opinfo) lease->new_state = SMB2_LEASE_NONE_LE; lease->state |= SMB2_LEASE_WRITE_CACHING_LE; - if (lease->state & SMB2_LEASE_HANDLE_CACHING_LE) - opinfo->level = SMB2_OPLOCK_LEVEL_BATCH; - else - opinfo->level = SMB2_OPLOCK_LEVEL_EXCLUSIVE; + lease_update_oplock_levels(lease); return 0; } @@ -386,15 +447,7 @@ static int lease_none_upgrade(struct oplock_info *opinfo, __le32 new_state) lease->new_state = SMB2_LEASE_NONE_LE; lease->state = new_state; - if (lease->state & SMB2_LEASE_HANDLE_CACHING_LE) - if (lease->state & SMB2_LEASE_WRITE_CACHING_LE) - opinfo->level = SMB2_OPLOCK_LEVEL_BATCH; - else - opinfo->level = SMB2_OPLOCK_LEVEL_II; - else if (lease->state & SMB2_LEASE_WRITE_CACHING_LE) - opinfo->level = SMB2_OPLOCK_LEVEL_EXCLUSIVE; - else if (lease->state & SMB2_LEASE_READ_CACHING_LE) - opinfo->level = SMB2_OPLOCK_LEVEL_II; + lease_update_oplock_levels(lease); return 0; } @@ -577,6 +630,7 @@ static struct oplock_info *same_client_has_lease(struct ksmbd_inode *ci, SMB2_LEASE_HANDLE_CACHING_LE)) { lease->epoch++; lease->state = lctx->req_state; + lease_update_oplock_levels(lease); } } @@ -603,8 +657,10 @@ static void wait_for_break_ack(struct oplock_info *opinfo) /* is this a timeout ? */ if (!rc) { - if (opinfo->is_lease) + if (opinfo->is_lease) { opinfo->o_lease->state = SMB2_LEASE_NONE_LE; + lease_update_oplock_levels(opinfo->o_lease); + } opinfo->level = SMB2_OPLOCK_LEVEL_NONE; opinfo->op_state = OPLOCK_STATE_NONE; } @@ -884,8 +940,8 @@ static int smb2_lease_break_noti(struct oplock_info *opinfo) } else { __smb2_lease_break_noti(&work->work); if (opinfo->o_lease->new_state == SMB2_LEASE_NONE_LE) { - opinfo->level = SMB2_OPLOCK_LEVEL_NONE; opinfo->o_lease->state = SMB2_LEASE_NONE_LE; + lease_update_oplock_levels(opinfo->o_lease); } } return 0; @@ -990,7 +1046,7 @@ static int oplock_break(struct oplock_info *brk_opinfo, int req_op_level, void destroy_lease_table(struct ksmbd_conn *conn) { struct lease_table *lb, *lbtmp; - struct oplock_info *opinfo; + struct lease *lease, *ltmp; write_lock(&lease_list_lock); if (list_empty(&lease_table_list)) { @@ -1002,15 +1058,8 @@ void destroy_lease_table(struct ksmbd_conn *conn) if (conn && memcmp(lb->client_guid, conn->ClientGUID, SMB2_CLIENT_GUID_SIZE)) continue; -again: - rcu_read_lock(); - list_for_each_entry_rcu(opinfo, &lb->lease_list, - lease_entry) { - rcu_read_unlock(); - lease_del_list(opinfo); - goto again; - } - rcu_read_unlock(); + list_for_each_entry_safe(lease, ltmp, &lb->lease_list, l_entry) + lease_del_table(lease); list_del(&lb->l_entry); kfree(lb); } @@ -1020,7 +1069,7 @@ again: int find_same_lease_key(struct ksmbd_conn *conn, struct ksmbd_inode *ci, struct lease_ctx_info *lctx) { - struct oplock_info *opinfo; + struct lease *lease; int err = 0; struct lease_table *lb; @@ -1043,70 +1092,40 @@ int find_same_lease_key(struct ksmbd_conn *conn, struct ksmbd_inode *ci, return 0; found: - rcu_read_lock(); - list_for_each_entry_rcu(opinfo, &lb->lease_list, lease_entry) { - if (!atomic_inc_not_zero(&opinfo->refcount)) + list_for_each_entry(lease, &lb->lease_list, l_entry) { + if (lease->ci == ci) continue; - rcu_read_unlock(); - if (opinfo->o_fp->f_ci == ci) - goto op_next; - err = compare_guid_key(opinfo, conn->ClientGUID, - lctx->lease_key); - if (err) { + if (!memcmp(lease->lease_key, lctx->lease_key, + SMB2_LEASE_KEY_SIZE)) { err = -EINVAL; ksmbd_debug(OPLOCK, "found same lease key is already used in other files\n"); - opinfo_put(opinfo); goto out; } -op_next: - opinfo_put(opinfo); - rcu_read_lock(); } - rcu_read_unlock(); out: read_unlock(&lease_list_lock); return err; } -static void copy_lease(struct oplock_info *op1, struct oplock_info *op2) -{ - struct lease *lease1 = op1->o_lease; - struct lease *lease2 = op2->o_lease; - - op2->level = op1->level; - lease2->state = lease1->state; - memcpy(lease2->lease_key, lease1->lease_key, - SMB2_LEASE_KEY_SIZE); - lease2->duration = lease1->duration; - lease2->flags = lease1->flags; - lease2->epoch = lease1->epoch; - lease2->version = lease1->version; - lease2->is_dir = lease1->is_dir; - memcpy(lease2->parent_lease_key, lease1->parent_lease_key, - SMB2_LEASE_KEY_SIZE); -} - -static void add_lease_global_list(struct oplock_info *opinfo, +static void add_lease_global_list(struct lease *lease, struct ksmbd_conn *conn, struct lease_table *new_lb) { struct lease_table *lb; write_lock(&lease_list_lock); list_for_each_entry(lb, &lease_table_list, l_entry) { - if (!memcmp(lb->client_guid, opinfo->conn->ClientGUID, + if (!memcmp(lb->client_guid, conn->ClientGUID, SMB2_CLIENT_GUID_SIZE)) { - opinfo->o_lease->l_lb = lb; - lease_add_list(opinfo); + lease_add_table(lease, lb); write_unlock(&lease_list_lock); kfree(new_lb); return; } } - opinfo->o_lease->l_lb = new_lb; - lease_add_list(opinfo); + lease_add_table(lease, new_lb); list_add(&new_lb->l_entry, &lease_table_list); write_unlock(&lease_list_lock); } @@ -1229,6 +1248,7 @@ int smb_grant_oplock(struct ksmbd_work *work, int req_op_level, u64 pid, struct ksmbd_inode *ci = fp->f_ci; struct lease_table *new_lb = NULL; bool prev_op_has_lease; + bool new_lease = false; __le32 prev_op_state = 0; /* Only v2 leases handle the directory */ @@ -1242,10 +1262,13 @@ int smb_grant_oplock(struct ksmbd_work *work, int req_op_level, u64 pid, return -ENOMEM; if (lctx) { - err = alloc_lease(opinfo, lctx); - if (err) + opinfo->o_lease = alloc_lease(lctx, ci); + if (!opinfo->o_lease) { + err = -ENOMEM; goto err_out; + } opinfo->is_lease = 1; + new_lease = true; } /* ci does not have any oplock */ @@ -1267,7 +1290,11 @@ int smb_grant_oplock(struct ksmbd_work *work, int req_op_level, u64 pid, m_opinfo = same_client_has_lease(ci, work->conn->ClientGUID, lctx); if (m_opinfo) { - copy_lease(m_opinfo, opinfo); + lease_put(opinfo->o_lease); + lease_get(m_opinfo->o_lease); + opinfo->o_lease = m_opinfo->o_lease; + opinfo->level = m_opinfo->level; + new_lease = false; if (atomic_read(&m_opinfo->breaking_cnt)) opinfo->o_lease->flags |= SMB2_LEASE_FLAG_BREAK_IN_PROGRESS_LE; @@ -1330,17 +1357,13 @@ set_lev: out: /* - * Set o_fp before any publication so that concurrent readers - * (e.g. find_same_lease_key() on the lease list) that - * dereference opinfo->o_fp don't hit a NULL pointer. - * * Keep the original publication order so concurrent opens can * still observe the in-flight grant via ci->m_op_list, but make * everything after opinfo_add() no-fail by preallocating any new * lease_table first. */ opinfo->o_fp = fp; - if (opinfo->is_lease) { + if (new_lease) { new_lb = alloc_lease_table(opinfo); if (!new_lb) { err = -ENOMEM; @@ -1351,8 +1374,10 @@ out: opinfo_count_inc(fp); opinfo_add(opinfo, fp); + if (new_lease) + add_lease_global_list(opinfo->o_lease, opinfo->conn, new_lb); if (opinfo->is_lease) - add_lease_global_list(opinfo, new_lb); + lease_add_open(opinfo->o_lease, opinfo); rcu_assign_pointer(fp->f_opinfo, opinfo); @@ -1834,8 +1859,8 @@ struct oplock_info *lookup_lease_in_table(struct ksmbd_conn *conn, char *lease_key) { struct oplock_info *opinfo = NULL, *ret_op = NULL; + struct lease *lease; struct lease_table *lt; - int ret; read_lock(&lease_list_lock); list_for_each_entry(lt, &lease_table_list, l_entry) { @@ -1848,29 +1873,30 @@ struct oplock_info *lookup_lease_in_table(struct ksmbd_conn *conn, return NULL; found: - rcu_read_lock(); - list_for_each_entry_rcu(opinfo, <->lease_list, lease_entry) { - if (!atomic_inc_not_zero(&opinfo->refcount)) + list_for_each_entry(lease, <->lease_list, l_entry) { + if (memcmp(lease->lease_key, lease_key, SMB2_LEASE_KEY_SIZE)) continue; - rcu_read_unlock(); - if (!opinfo->op_state || opinfo->op_state == OPLOCK_CLOSING) - goto op_next; - if (!(opinfo->o_lease->state & - (SMB2_LEASE_HANDLE_CACHING_LE | - SMB2_LEASE_WRITE_CACHING_LE))) - goto op_next; - ret = compare_guid_key(opinfo, conn->ClientGUID, - lease_key); - if (ret) { - ksmbd_debug(OPLOCK, "found opinfo\n"); + if (!(lease->state & (SMB2_LEASE_HANDLE_CACHING_LE | + SMB2_LEASE_WRITE_CACHING_LE))) + break; + + spin_lock(&lease->lock); + list_for_each_entry(opinfo, &lease->open_list, lease_entry) { + if (!opinfo->op_state || + opinfo->op_state == OPLOCK_CLOSING) + continue; + if (!atomic_inc_not_zero(&opinfo->refcount)) + continue; ret_op = opinfo; + break; + } + spin_unlock(&lease->lock); + if (ret_op) { + ksmbd_debug(OPLOCK, "found opinfo\n"); goto out; } -op_next: - opinfo_put(opinfo); - rcu_read_lock(); + break; } - rcu_read_unlock(); out: read_unlock(&lease_list_lock); diff --git a/fs/smb/server/oplock.h b/fs/smb/server/oplock.h index 795a9119dad9..30bad6d65048 100644 --- a/fs/smb/server/oplock.h +++ b/fs/smb/server/oplock.h @@ -49,7 +49,12 @@ struct lease { int version; unsigned short epoch; bool is_dir; + struct ksmbd_inode *ci; struct lease_table *l_lb; + struct list_head l_entry; + struct list_head open_list; + spinlock_t lock; + atomic_t refcount; }; struct oplock_info { @@ -105,6 +110,7 @@ void opinfo_put(struct oplock_info *opinfo); void create_lease_buf(u8 *rbuf, struct lease *lease); struct lease_ctx_info *parse_lease_state(void *open_req); __u8 smb2_map_lease_to_oplock(__le32 lease_state); +void lease_update_oplock_levels(struct lease *lease); int lease_read_to_write(struct oplock_info *opinfo); /* Durable related functions */ diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index 75ee9184e553..f3a57a32c4a8 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -9081,7 +9081,7 @@ static void smb21_lease_break_ack(struct ksmbd_work *work) lease_state = req->LeaseState; lease->state = lease_state; lease->new_state = SMB2_LEASE_NONE_LE; - opinfo->level = smb2_map_lease_to_oplock(lease_state); + lease_update_oplock_levels(lease); rsp->StructureSize = cpu_to_le16(36); rsp->Reserved = 0; From 80a56d4a826c6c84430286fcf7d8655f7c5b0868 Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Thu, 18 Jun 2026 10:35:42 +0900 Subject: [PATCH 156/297] ksmbd: align SMB2 oplock break ack handling Handle SMB2 oplock break acknowledgments according to the server-side validation rules in MS-SMB2. Return STATUS_INVALID_DEVICE_STATE when an ACK arrives while the open is not breaking, reject SMB2_OPLOCK_LEVEL_LEASE with STATUS_INVALID_PARAMETER, allow BATCH acknowledgments to EXCLUSIVE, and make invalid ACK levels fail with STATUS_INVALID_OPLOCK_PROTOCOL after lowering the oplock to NONE. Update the successful response from the final granted oplock level instead of relying on the oplock transition helpers, which could turn invalid ACKs into successful responses. Signed-off-by: Namjae Jeon Signed-off-by: Steve French --- fs/smb/server/smb2pdu.c | 108 ++++++++++++++++++---------------------- 1 file changed, 48 insertions(+), 60 deletions(-) diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index f3a57a32c4a8..b84062b16a75 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -8900,11 +8900,10 @@ static void smb20_oplock_break_ack(struct ksmbd_work *work) struct smb2_oplock_break *rsp; struct ksmbd_file *fp; struct oplock_info *opinfo = NULL; - __le32 err = 0; - int ret = 0; + __le32 status = STATUS_SUCCESS; + int ret; u64 volatile_id, persistent_id; char req_oplevel = 0, rsp_oplevel = 0; - unsigned int oplock_change_type; WORK_BUFFERS(work, req, rsp); @@ -8930,70 +8929,54 @@ static void smb20_oplock_break_ack(struct ksmbd_work *work) return; } + if (opinfo->op_state != OPLOCK_ACK_WAIT) { + ksmbd_debug(SMB, "unexpected oplock state 0x%x\n", + opinfo->op_state); + status = STATUS_INVALID_DEVICE_STATE; + goto err_out; + } + + if (req_oplevel == SMB2_OPLOCK_LEVEL_LEASE) { + opinfo->level = SMB2_OPLOCK_LEVEL_NONE; + status = STATUS_INVALID_PARAMETER; + goto err_out; + } + if (opinfo->level == SMB2_OPLOCK_LEVEL_NONE) { - rsp->hdr.Status = STATUS_INVALID_OPLOCK_PROTOCOL; + status = STATUS_INVALID_OPLOCK_PROTOCOL; goto err_out; } - if (opinfo->op_state == OPLOCK_STATE_NONE) { - ksmbd_debug(SMB, "unexpected oplock state 0x%x\n", opinfo->op_state); - rsp->hdr.Status = STATUS_UNSUCCESSFUL; + if (opinfo->level == SMB2_OPLOCK_LEVEL_EXCLUSIVE && + req_oplevel != SMB2_OPLOCK_LEVEL_II && + req_oplevel != SMB2_OPLOCK_LEVEL_NONE) { + opinfo->level = SMB2_OPLOCK_LEVEL_NONE; + status = STATUS_INVALID_OPLOCK_PROTOCOL; goto err_out; } - if ((opinfo->level == SMB2_OPLOCK_LEVEL_EXCLUSIVE || - opinfo->level == SMB2_OPLOCK_LEVEL_BATCH) && - (req_oplevel != SMB2_OPLOCK_LEVEL_II && - req_oplevel != SMB2_OPLOCK_LEVEL_NONE)) { - err = STATUS_INVALID_OPLOCK_PROTOCOL; - oplock_change_type = OPLOCK_WRITE_TO_NONE; - } else if (opinfo->level == SMB2_OPLOCK_LEVEL_II && - req_oplevel != SMB2_OPLOCK_LEVEL_NONE) { - err = STATUS_INVALID_OPLOCK_PROTOCOL; - oplock_change_type = OPLOCK_READ_TO_NONE; - } else if (req_oplevel == SMB2_OPLOCK_LEVEL_II || - req_oplevel == SMB2_OPLOCK_LEVEL_NONE) { - err = STATUS_INVALID_DEVICE_STATE; - if ((opinfo->level == SMB2_OPLOCK_LEVEL_EXCLUSIVE || - opinfo->level == SMB2_OPLOCK_LEVEL_BATCH) && - req_oplevel == SMB2_OPLOCK_LEVEL_II) { - oplock_change_type = OPLOCK_WRITE_TO_READ; - } else if ((opinfo->level == SMB2_OPLOCK_LEVEL_EXCLUSIVE || - opinfo->level == SMB2_OPLOCK_LEVEL_BATCH) && - req_oplevel == SMB2_OPLOCK_LEVEL_NONE) { - oplock_change_type = OPLOCK_WRITE_TO_NONE; - } else if (opinfo->level == SMB2_OPLOCK_LEVEL_II && - req_oplevel == SMB2_OPLOCK_LEVEL_NONE) { - oplock_change_type = OPLOCK_READ_TO_NONE; - } else { - oplock_change_type = 0; - } - } else { - oplock_change_type = 0; + if (opinfo->level == SMB2_OPLOCK_LEVEL_BATCH && + req_oplevel != SMB2_OPLOCK_LEVEL_II && + req_oplevel != SMB2_OPLOCK_LEVEL_NONE && + req_oplevel != SMB2_OPLOCK_LEVEL_EXCLUSIVE) { + opinfo->level = SMB2_OPLOCK_LEVEL_NONE; + status = STATUS_INVALID_OPLOCK_PROTOCOL; + goto err_out; } - switch (oplock_change_type) { - case OPLOCK_WRITE_TO_READ: - ret = opinfo_write_to_read(opinfo); - rsp_oplevel = SMB2_OPLOCK_LEVEL_II; - break; - case OPLOCK_WRITE_TO_NONE: - ret = opinfo_write_to_none(opinfo); + if (opinfo->level == SMB2_OPLOCK_LEVEL_II && + req_oplevel != SMB2_OPLOCK_LEVEL_NONE) { + opinfo->level = SMB2_OPLOCK_LEVEL_NONE; + status = STATUS_INVALID_OPLOCK_PROTOCOL; + goto err_out; + } + + if (req_oplevel == SMB2_OPLOCK_LEVEL_EXCLUSIVE) rsp_oplevel = SMB2_OPLOCK_LEVEL_NONE; - break; - case OPLOCK_READ_TO_NONE: - ret = opinfo_read_to_none(opinfo); - rsp_oplevel = SMB2_OPLOCK_LEVEL_NONE; - break; - default: - pr_err("unknown oplock change 0x%x -> 0x%x\n", - opinfo->level, rsp_oplevel); - } + else + rsp_oplevel = req_oplevel; - if (ret < 0) { - rsp->hdr.Status = err; - goto err_out; - } + opinfo->level = rsp_oplevel; rsp->StructureSize = cpu_to_le16(24); rsp->OplockLevel = rsp_oplevel; @@ -9002,11 +8985,16 @@ static void smb20_oplock_break_ack(struct ksmbd_work *work) rsp->VolatileFid = volatile_id; rsp->PersistentFid = persistent_id; ret = ksmbd_iov_pin_rsp(work, rsp, sizeof(struct smb2_oplock_break)); - if (ret) { -err_out: - smb2_set_err_rsp(work); - } + if (ret) + ksmbd_debug(SMB, "failed to pin oplock break response: %d\n", + ret); + goto out; +err_out: + rsp->hdr.Status = status; + smb2_set_err_rsp(work); + +out: opinfo->op_state = OPLOCK_STATE_NONE; wake_up_interruptible_all(&opinfo->oplock_q); opinfo_put(opinfo); From 171b5d72dd80f99271c073c6e38d5263687c3b6d Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Thu, 18 Jun 2026 10:36:17 +0900 Subject: [PATCH 157/297] ksmbd: treat unnamed DATA stream as base file The SMB path suffix :: names the unnamed data stream of the base file, not an alternate data stream backed by a DosStream xattr. Canonicalize an empty stream name with an explicit type to a NULL stream name after parsing. This keeps the base filename produced by strsep() and lets open continue through the normal base-file path instead of looking for a non-existent empty stream xattr. Signed-off-by: Namjae Jeon Signed-off-by: Steve French --- fs/smb/server/misc.c | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) diff --git a/fs/smb/server/misc.c b/fs/smb/server/misc.c index 966004c414a8..2dd91c9e956a 100644 --- a/fs/smb/server/misc.c +++ b/fs/smb/server/misc.c @@ -121,7 +121,9 @@ int parse_stream_name(char *filename, char **stream_name, int *s_type) char *stream_type; char *s_name; int rc = 0; + bool has_stream_type = false; + *stream_name = NULL; s_name = filename; filename = strsep(&s_name, ":"); ksmbd_debug(SMB, "filename : %s, streams : %s\n", filename, s_name); @@ -137,14 +139,20 @@ int parse_stream_name(char *filename, char **stream_name, int *s_type) ksmbd_debug(SMB, "stream name : %s, stream type : %s\n", s_name, stream_type); - if (!strncasecmp("$data", stream_type, 5)) + if (!strncasecmp("$data", stream_type, 5)) { *s_type = DATA_STREAM; - else if (!strncasecmp("$index_allocation", stream_type, 17)) + has_stream_type = true; + } else if (!strncasecmp("$index_allocation", stream_type, 17)) { *s_type = DIR_STREAM; - else + has_stream_type = true; + } else { rc = -ENOENT; + } } + if (has_stream_type && !s_name[0] && *s_type == DATA_STREAM) + goto out; + *stream_name = s_name; out: return rc; From 890825ed5c427fcb542ae1a0fd7495e551dcacaf Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Thu, 18 Jun 2026 10:36:59 +0900 Subject: [PATCH 158/297] ksmbd: compute lease break-in-progress flag on response SMB2_LEASE_FLAG_BREAK_IN_PROGRESS is a transient create response flag, not persistent lease state. Do not store the flag in lease->flags when a same-key open is granted during a pending break. Instead, derive it from lease opens that are still waiting for a break ACK while building the lease create response, and keep lease->flags for persistent lease flags such as the parent lease key. This clears the flag naturally after the break ACK completes and fixes reopen responses that report BREAK_IN_PROGRESS after the lease is no longer breaking. Signed-off-by: Namjae Jeon Signed-off-by: Steve French --- fs/smb/server/oplock.c | 41 +++++++++++++++++++++++++++++------------ 1 file changed, 29 insertions(+), 12 deletions(-) diff --git a/fs/smb/server/oplock.c b/fs/smb/server/oplock.c index 81716317bb61..b1740fe988e6 100644 --- a/fs/smb/server/oplock.c +++ b/fs/smb/server/oplock.c @@ -39,6 +39,23 @@ static bool lease_has_parent_key(struct lease *lease) return lease->flags & SMB2_LEASE_FLAG_PARENT_LEASE_KEY_SET_LE; } +static bool lease_break_in_progress(struct lease *lease) +{ + struct oplock_info *opinfo; + bool ret = false; + + spin_lock(&lease->lock); + list_for_each_entry(opinfo, &lease->open_list, lease_entry) { + if (opinfo->op_state == OPLOCK_ACK_WAIT) { + ret = true; + break; + } + } + spin_unlock(&lease->lock); + + return ret; +} + /** * alloc_opinfo() - allocate a new opinfo object for oplock info * @work: smb work @@ -1292,15 +1309,12 @@ int smb_grant_oplock(struct ksmbd_work *work, int req_op_level, u64 pid, if (m_opinfo) { lease_put(opinfo->o_lease); lease_get(m_opinfo->o_lease); - opinfo->o_lease = m_opinfo->o_lease; - opinfo->level = m_opinfo->level; - new_lease = false; - if (atomic_read(&m_opinfo->breaking_cnt)) - opinfo->o_lease->flags |= - SMB2_LEASE_FLAG_BREAK_IN_PROGRESS_LE; - opinfo_put(m_opinfo); - goto out; - } + opinfo->o_lease = m_opinfo->o_lease; + opinfo->level = m_opinfo->level; + new_lease = false; + opinfo_put(m_opinfo); + goto out; + } } prev_opinfo = opinfo_get_list(ci); if (!prev_opinfo || @@ -1521,13 +1535,15 @@ void create_lease_buf(u8 *rbuf, struct lease *lease) { if (lease->version == 2) { struct create_lease_v2 *buf = (struct create_lease_v2 *)rbuf; - __le32 flags = lease->flags & SMB2_LEASE_FLAG_BREAK_IN_PROGRESS_LE; + __le32 flags = 0; memset(buf, 0, sizeof(struct create_lease_v2)); memcpy(buf->lcontext.LeaseKey, lease->lease_key, SMB2_LEASE_KEY_SIZE); if (lease_has_parent_key(lease)) flags |= SMB2_LEASE_FLAG_PARENT_LEASE_KEY_SET_LE; + if (lease_break_in_progress(lease)) + flags |= SMB2_LEASE_FLAG_BREAK_IN_PROGRESS_LE; buf->lcontext.LeaseFlags = flags; buf->lcontext.Epoch = cpu_to_le16(lease->epoch); buf->lcontext.LeaseState = lease->state; @@ -1549,8 +1565,9 @@ void create_lease_buf(u8 *rbuf, struct lease *lease) memset(buf, 0, sizeof(struct create_lease)); memcpy(buf->lcontext.LeaseKey, lease->lease_key, SMB2_LEASE_KEY_SIZE); - buf->lcontext.LeaseFlags = - lease->flags & SMB2_LEASE_FLAG_BREAK_IN_PROGRESS_LE; + if (lease_break_in_progress(lease)) + buf->lcontext.LeaseFlags = + SMB2_LEASE_FLAG_BREAK_IN_PROGRESS_LE; buf->lcontext.LeaseState = lease->state; buf->ccontext.DataOffset = cpu_to_le16(offsetof (struct create_lease, lcontext)); From 7efb3f2458a8d260ce6ab37807f4b2a926483f76 Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Tue, 23 Jun 2026 08:28:55 +0900 Subject: [PATCH 159/297] ksmbd: chain pending lease breaks before waking waiters A pending open can require more than one lease break before the existing lease becomes compatible with the operation that triggered the break. smb2.lease.breaking3 expects the server to hold the pending normal open through RWH->RH and RH->R, while a later overwrite waiter must not collapse that second break directly to RH->NONE. Keep pending_break held for lease breaks until the current triggering operation is compatible with the lease state. Snapshot the truncate request per oplock_break() call so another waiter cannot overwrite the state of the active break. Use the requested oplock level when deciding whether to chain another break. A second lease open only needs RWH->RH, while a normal none-oplock open can continue down to R and then NONE. For non-truncating metadata operations, break leases only down to read caching. Operations such as delete-on-close need to drop handle caching, but should not send a second R->NONE break after the client acknowledges RH->R. Also send STATUS_PENDING for levelII/read-lease break waiters. An async SMB2 create becomes cancelable only after the server sends an NT_STATUS_PENDING interim response. A waiter that blocks behind an already active lease break must receive the interim response before sleeping on pending_break, otherwise the client can process a later lease break while the create request is still not marked pending. Avoid duplicate interim responses when an overwrite first breaks a write oplock and then scans levelII/read leases. Signed-off-by: Namjae Jeon Signed-off-by: Steve French --- fs/smb/server/oplock.c | 108 ++++++++++++++++++++++++++++++----------- 1 file changed, 81 insertions(+), 27 deletions(-) diff --git a/fs/smb/server/oplock.c b/fs/smb/server/oplock.c index b1740fe988e6..608961c838c9 100644 --- a/fs/smb/server/oplock.c +++ b/fs/smb/server/oplock.c @@ -727,6 +727,17 @@ static int oplock_break_pending(struct oplock_info *opinfo, int req_op_level) return 0; } +static bool lease_break_needed(struct oplock_info *opinfo, int req_op_level, + bool open_trunc) +{ + struct lease *lease = opinfo->o_lease; + + if (open_trunc) + return lease->state != SMB2_LEASE_NONE_LE; + + return opinfo->level > req_op_level; +} + /** * __smb2_oplock_break_noti() - send smb2 oplock break cmd from conn * to client @@ -985,6 +996,7 @@ static int oplock_break(struct oplock_info *brk_opinfo, int req_op_level, struct ksmbd_work *in_work) { int err = 0; + bool sent_interim = false; /* Need to break exclusive/batch oplock, write lease or overwrite_if */ ksmbd_debug(OPLOCK, @@ -993,13 +1005,22 @@ static int oplock_break(struct oplock_info *brk_opinfo, int req_op_level, if (brk_opinfo->is_lease) { struct lease *lease = brk_opinfo->o_lease; + bool open_trunc = brk_opinfo->open_trunc; + + if (in_work && test_bit(0, &brk_opinfo->pending_break)) { + setup_async_work(in_work, NULL, NULL); + smb2_send_interim_resp(in_work, STATUS_PENDING); + release_async_work(in_work); + sent_interim = true; + } - atomic_inc(&brk_opinfo->breaking_cnt); err = oplock_break_pending(brk_opinfo, req_op_level); if (err) return err < 0 ? err : 0; - if (brk_opinfo->open_trunc) { +again: + atomic_inc(&brk_opinfo->breaking_cnt); + if (open_trunc) { /* * Create overwrite break trigger the lease break to * none. @@ -1024,17 +1045,31 @@ static int oplock_break(struct oplock_info *brk_opinfo, int req_op_level, } } + if (in_work && !sent_interim) { + setup_async_work(in_work, NULL, NULL); + smb2_send_interim_resp(in_work, STATUS_PENDING); + release_async_work(in_work); + sent_interim = true; + } + if (lease->state & (SMB2_LEASE_WRITE_CACHING_LE | SMB2_LEASE_HANDLE_CACHING_LE)) { - if (in_work) { - setup_async_work(in_work, NULL, NULL); - smb2_send_interim_resp(in_work, STATUS_PENDING); - release_async_work(in_work); - } - brk_opinfo->op_state = OPLOCK_ACK_WAIT; } else atomic_dec(&brk_opinfo->breaking_cnt); + + err = smb2_lease_break_noti(brk_opinfo); + + ksmbd_debug(OPLOCK, "oplock granted = %d\n", brk_opinfo->level); + if (brk_opinfo->op_state == OPLOCK_CLOSING) + err = -ENOENT; + + wait_lease_breaking(brk_opinfo); + if (!err && lease_break_needed(brk_opinfo, req_op_level, open_trunc)) + goto again; + + wake_up_oplock_break(brk_opinfo); + return err; } else { err = oplock_break_pending(brk_opinfo, req_op_level); if (err) @@ -1045,18 +1080,13 @@ static int oplock_break(struct oplock_info *brk_opinfo, int req_op_level, brk_opinfo->op_state = OPLOCK_ACK_WAIT; } - if (brk_opinfo->is_lease) - err = smb2_lease_break_noti(brk_opinfo); - else - err = smb2_oplock_break_noti(brk_opinfo); + err = smb2_oplock_break_noti(brk_opinfo); ksmbd_debug(OPLOCK, "oplock granted = %d\n", brk_opinfo->level); if (brk_opinfo->op_state == OPLOCK_CLOSING) err = -ENOENT; wake_up_oplock_break(brk_opinfo); - wait_lease_breaking(brk_opinfo); - return err; } @@ -1261,6 +1291,7 @@ int smb_grant_oplock(struct ksmbd_work *work, int req_op_level, u64 pid, struct lease_ctx_info *lctx, int share_ret) { int err = 0; + int break_level = SMB2_OPLOCK_LEVEL_II; struct oplock_info *opinfo = NULL, *prev_opinfo = NULL; struct ksmbd_inode *ci = fp->f_ci; struct lease_table *new_lb = NULL; @@ -1325,6 +1356,9 @@ int smb_grant_oplock(struct ksmbd_work *work, int req_op_level, u64 pid, prev_op_has_lease = prev_opinfo->is_lease; if (prev_op_has_lease) prev_op_state = prev_opinfo->o_lease->state; + if (prev_op_has_lease && !lctx && + prev_op_state & SMB2_LEASE_HANDLE_CACHING_LE) + break_level = SMB2_OPLOCK_LEVEL_NONE; if (share_ret < 0 && prev_opinfo->level == SMB2_OPLOCK_LEVEL_EXCLUSIVE) { @@ -1339,7 +1373,7 @@ int smb_grant_oplock(struct ksmbd_work *work, int req_op_level, u64 pid, goto op_break_not_needed; } - err = oplock_break(prev_opinfo, SMB2_OPLOCK_LEVEL_II, work); + err = oplock_break(prev_opinfo, break_level, work); opinfo_put(prev_opinfo); if (err == -ENOENT) goto set_lev; @@ -1408,38 +1442,46 @@ err_out: * @fp: ksmbd file pointer * @is_trunc: truncate on open */ -static void smb_break_all_write_oplock(struct ksmbd_work *work, +static bool smb_break_all_write_oplock(struct ksmbd_work *work, struct ksmbd_file *fp, int is_trunc) { struct oplock_info *brk_opinfo; + bool sent_break = false; brk_opinfo = opinfo_get_list(fp->f_ci); if (!brk_opinfo) - return; + return false; if (brk_opinfo->level != SMB2_OPLOCK_LEVEL_BATCH && brk_opinfo->level != SMB2_OPLOCK_LEVEL_EXCLUSIVE) { opinfo_put(brk_opinfo); - return; + return false; } brk_opinfo->open_trunc = is_trunc; oplock_break(brk_opinfo, SMB2_OPLOCK_LEVEL_II, work); + sent_break = true; opinfo_put(brk_opinfo); + + return sent_break; } /** - * smb_break_all_levII_oplock() - send level2 oplock or read lease break command + * __smb_break_all_levII_oplock() - send level2 oplock or read lease break command * from server to client - * @work: smb work - * @fp: ksmbd file pointer - * @is_trunc: truncate on open + * @work: smb work + * @fp: ksmbd file pointer + * @is_trunc: truncate on open + * @send_interim: send interim response to the client + * @send_oplock_break: send oplock break notification to the client */ -void smb_break_all_levII_oplock(struct ksmbd_work *work, struct ksmbd_file *fp, - int is_trunc) +static void __smb_break_all_levII_oplock(struct ksmbd_work *work, + struct ksmbd_file *fp, int is_trunc, + bool send_interim) { struct oplock_info *op, *brk_op; struct ksmbd_inode *ci; struct ksmbd_conn *conn = work->conn; + bool sent_interim = false; if (!test_share_config_flag(work->tcon->share_conf, KSMBD_SHARE_FLAG_OPLOCKS)) @@ -1481,7 +1523,11 @@ void smb_break_all_levII_oplock(struct ksmbd_work *work, struct ksmbd_file *fp, SMB2_LEASE_KEY_SIZE)) goto next; brk_op->open_trunc = is_trunc; - oplock_break(brk_op, SMB2_OPLOCK_LEVEL_NONE, NULL); + oplock_break(brk_op, + brk_op->is_lease && !is_trunc ? + SMB2_OPLOCK_LEVEL_II : SMB2_OPLOCK_LEVEL_NONE, + send_interim && !sent_interim ? work : NULL); + sent_interim = true; next: opinfo_put(brk_op); } @@ -1491,6 +1537,12 @@ next: opinfo_put(op); } +void smb_break_all_levII_oplock(struct ksmbd_work *work, struct ksmbd_file *fp, + int is_trunc) +{ + __smb_break_all_levII_oplock(work, fp, is_trunc, true); +} + /** * smb_break_all_oplock() - break both batch/exclusive and level2 oplock * @work: smb work @@ -1498,12 +1550,14 @@ next: */ void smb_break_all_oplock(struct ksmbd_work *work, struct ksmbd_file *fp) { + bool sent_break; + if (!test_share_config_flag(work->tcon->share_conf, KSMBD_SHARE_FLAG_OPLOCKS)) return; - smb_break_all_write_oplock(work, fp, 1); - smb_break_all_levII_oplock(work, fp, 1); + sent_break = smb_break_all_write_oplock(work, fp, 1); + __smb_break_all_levII_oplock(work, fp, 1, !sent_break); } /** From 752bbd323e779691998920035b6e9417d5a6a78c Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Thu, 18 Jun 2026 21:31:53 +0900 Subject: [PATCH 160/297] ksmbd: do not wait for RH lease break ack on overwrite smb2.lease.breaking4 expects an overwrite against an RH lease to send RH->NONE lease break notification but complete the triggering create without waiting for the break ack. Keep the lease in break-in-progress state until the client eventually acknowledges the downgrade, but do not hold the overwrite request behind that ack. Signed-off-by: Namjae Jeon Signed-off-by: Steve French --- fs/smb/server/oplock.c | 17 ++++++++++++----- 1 file changed, 12 insertions(+), 5 deletions(-) diff --git a/fs/smb/server/oplock.c b/fs/smb/server/oplock.c index 608961c838c9..4d89fbb6c9c5 100644 --- a/fs/smb/server/oplock.c +++ b/fs/smb/server/oplock.c @@ -927,7 +927,7 @@ out: * * Return: 0 on success, otherwise error */ -static int smb2_lease_break_noti(struct oplock_info *opinfo) +static int smb2_lease_break_noti(struct oplock_info *opinfo, bool wait_ack) { struct ksmbd_conn *conn; struct ksmbd_work *work; @@ -964,7 +964,8 @@ static int smb2_lease_break_noti(struct oplock_info *opinfo) if (opinfo->op_state == OPLOCK_ACK_WAIT) { INIT_WORK(&work->work, __smb2_lease_break_noti); ksmbd_queue_work(work); - wait_for_break_ack(opinfo); + if (wait_ack) + wait_for_break_ack(opinfo); } else { __smb2_lease_break_noti(&work->work); if (opinfo->o_lease->new_state == SMB2_LEASE_NONE_LE) { @@ -1006,6 +1007,7 @@ static int oplock_break(struct oplock_info *brk_opinfo, int req_op_level, if (brk_opinfo->is_lease) { struct lease *lease = brk_opinfo->o_lease; bool open_trunc = brk_opinfo->open_trunc; + bool wait_ack; if (in_work && test_bit(0, &brk_opinfo->pending_break)) { setup_async_work(in_work, NULL, NULL); @@ -1058,14 +1060,19 @@ again: } else atomic_dec(&brk_opinfo->breaking_cnt); - err = smb2_lease_break_noti(brk_opinfo); + wait_ack = !(open_trunc && + lease->state == (SMB2_LEASE_READ_CACHING_LE | + SMB2_LEASE_HANDLE_CACHING_LE)); + err = smb2_lease_break_noti(brk_opinfo, wait_ack); ksmbd_debug(OPLOCK, "oplock granted = %d\n", brk_opinfo->level); if (brk_opinfo->op_state == OPLOCK_CLOSING) err = -ENOENT; - wait_lease_breaking(brk_opinfo); - if (!err && lease_break_needed(brk_opinfo, req_op_level, open_trunc)) + if (wait_ack) + wait_lease_breaking(brk_opinfo); + if (wait_ack && !err && + lease_break_needed(brk_opinfo, req_op_level, open_trunc)) goto again; wake_up_oplock_break(brk_opinfo); From dc2264a9efe7b56040b018024d1dfe0b3839d5ae Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Thu, 18 Jun 2026 21:32:29 +0900 Subject: [PATCH 161/297] ksmbd: honor SMB2 v2 lease epochs v2 lease responses should continue from the client supplied epoch. Initialize a new v2 lease from the requested epoch plus one so create responses match the epoch returned by Windows and expected by smbtorture. For a single chained break sequence, increment the epoch only for the first break notification. Follow-up breaks such as RH->R and R->NONE in smb2.lease.v2_breaking3 reuse the same epoch. Record when a waiter slept behind pending_break and let the later truncate/open overwrite break consume that marker to reuse the current epoch instead of assigning a new one. Do not increment the epoch when a same-client, same-key create asks for the already granted RH state. The epoch changes only when the granted lease state changes. Signed-off-by: Namjae Jeon Signed-off-by: Steve French --- fs/smb/server/oplock.c | 39 +++++++++++++++++++++++++++++---------- fs/smb/server/oplock.h | 1 + 2 files changed, 30 insertions(+), 10 deletions(-) diff --git a/fs/smb/server/oplock.c b/fs/smb/server/oplock.c index 4d89fbb6c9c5..fe0bbb0e1c89 100644 --- a/fs/smb/server/oplock.c +++ b/fs/smb/server/oplock.c @@ -163,8 +163,9 @@ static struct lease *alloc_lease(struct lease_ctx_info *lctx, lease->is_dir = lctx->is_dir; memcpy(lease->parent_lease_key, lctx->parent_lease_key, SMB2_LEASE_KEY_SIZE); lease->version = lctx->version; - lease->epoch = lctx->version == 2 ? 1 : 0; + lease->epoch = lctx->version == 2 ? le16_to_cpu(lctx->epoch) + 1 : 0; lease->ci = ci; + lease->reuse_epoch = false; lease->l_lb = NULL; INIT_LIST_HEAD(&lease->l_entry); INIT_LIST_HEAD(&lease->open_list); @@ -645,9 +646,11 @@ static struct oplock_info *same_client_has_lease(struct ksmbd_inode *ci, if (lctx->req_state == (SMB2_LEASE_READ_CACHING_LE | SMB2_LEASE_HANDLE_CACHING_LE)) { - lease->epoch++; - lease->state = lctx->req_state; - lease_update_oplock_levels(lease); + if (lease->state != lctx->req_state) { + lease->epoch++; + lease->state = lctx->req_state; + lease_update_oplock_levels(lease); + } } } @@ -694,6 +697,9 @@ static void wake_up_oplock_break(struct oplock_info *opinfo) static int oplock_break_pending(struct oplock_info *opinfo, int req_op_level) { while (test_and_set_bit(0, &opinfo->pending_break)) { + if (opinfo->is_lease) + opinfo->o_lease->reuse_epoch = true; + wait_on_bit(&opinfo->pending_break, 0, TASK_UNINTERRUPTIBLE); /* Not immediately break to none. */ @@ -927,7 +933,8 @@ out: * * Return: 0 on success, otherwise error */ -static int smb2_lease_break_noti(struct oplock_info *opinfo, bool wait_ack) +static int smb2_lease_break_noti(struct oplock_info *opinfo, bool wait_ack, + bool inc_epoch) { struct ksmbd_conn *conn; struct ksmbd_work *work; @@ -950,10 +957,13 @@ static int smb2_lease_break_noti(struct oplock_info *opinfo, bool wait_ack) br_info->curr_state = lease->state; br_info->new_state = lease->new_state; - if (lease->version == 2) - br_info->epoch = cpu_to_le16(++lease->epoch); - else + if (lease->version == 2) { + if (inc_epoch) + lease->epoch++; + br_info->epoch = cpu_to_le16(lease->epoch); + } else { br_info->epoch = 0; + } memcpy(br_info->lease_key, lease->lease_key, SMB2_LEASE_KEY_SIZE); work->request_buf = (char *)br_info; @@ -1007,9 +1017,11 @@ static int oplock_break(struct oplock_info *brk_opinfo, int req_op_level, if (brk_opinfo->is_lease) { struct lease *lease = brk_opinfo->o_lease; bool open_trunc = brk_opinfo->open_trunc; + bool was_pending = test_bit(0, &brk_opinfo->pending_break); bool wait_ack; + bool inc_epoch = true; - if (in_work && test_bit(0, &brk_opinfo->pending_break)) { + if (in_work && was_pending) { setup_async_work(in_work, NULL, NULL); smb2_send_interim_resp(in_work, STATUS_PENDING); release_async_work(in_work); @@ -1019,6 +1031,8 @@ static int oplock_break(struct oplock_info *brk_opinfo, int req_op_level, err = oplock_break_pending(brk_opinfo, req_op_level); if (err) return err < 0 ? err : 0; + if (was_pending) + open_trunc = brk_opinfo->open_trunc; again: atomic_inc(&brk_opinfo->breaking_cnt); @@ -1063,7 +1077,12 @@ again: wait_ack = !(open_trunc && lease->state == (SMB2_LEASE_READ_CACHING_LE | SMB2_LEASE_HANDLE_CACHING_LE)); - err = smb2_lease_break_noti(brk_opinfo, wait_ack); + if (lease->reuse_epoch) { + inc_epoch = false; + lease->reuse_epoch = false; + } + err = smb2_lease_break_noti(brk_opinfo, wait_ack, inc_epoch); + inc_epoch = false; ksmbd_debug(OPLOCK, "oplock granted = %d\n", brk_opinfo->level); if (brk_opinfo->op_state == OPLOCK_CLOSING) diff --git a/fs/smb/server/oplock.h b/fs/smb/server/oplock.h index 30bad6d65048..1dd52b44557f 100644 --- a/fs/smb/server/oplock.h +++ b/fs/smb/server/oplock.h @@ -49,6 +49,7 @@ struct lease { int version; unsigned short epoch; bool is_dir; + bool reuse_epoch; struct ksmbd_inode *ci; struct lease_table *l_lb; struct list_head l_entry; From 1f1083c36fa11c5d9011451c7b9ab380545c72ea Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Thu, 18 Jun 2026 21:33:07 +0900 Subject: [PATCH 162/297] ksmbd: break RH leases before delete-on-close The delete paths only marked the opened file delete pending or delete-on-close. When another client still held a read/handle lease, no lease break was sent before the delete state changed. smb2.lease.unlink uses a create request with FILE_DELETE_ON_CLOSE and expects the second client's unlink to break the first client's RH lease to R with ACK_REQUIRED set. SetInfo(FileDispositionInformation) has the same lease-breaking requirement. Break level-II/read-handle leases before setting delete pending or delete-on-close so clients are notified before the file is removed. Signed-off-by: Namjae Jeon Signed-off-by: Steve French --- fs/smb/server/smb2pdu.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index b84062b16a75..f1a0bce0c1f7 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -3653,8 +3653,10 @@ int smb2_open(struct ksmbd_work *work) goto err_out1; } - if (req->CreateOptions & FILE_DELETE_ON_CLOSE_LE) + if (req->CreateOptions & FILE_DELETE_ON_CLOSE_LE) { + smb_break_all_levII_oplock(work, fp, 0); ksmbd_fd_set_delete_on_close(fp, file_info); + } if (need_truncate) { rc = smb2_create_truncate(&fp->filp->f_path); @@ -6584,7 +6586,8 @@ static int set_rename_info(struct ksmbd_work *work, struct ksmbd_file *fp, return smb2_rename(work, fp, rename_info, work->conn->local_nls); } -static int set_file_disposition_info(struct ksmbd_file *fp, +static int set_file_disposition_info(struct ksmbd_work *work, + struct ksmbd_file *fp, struct smb2_file_disposition_info *file_info) { struct inode *inode; @@ -6599,6 +6602,7 @@ static int set_file_disposition_info(struct ksmbd_file *fp, if (S_ISDIR(inode->i_mode) && ksmbd_vfs_empty_dir(fp) == -ENOTEMPTY) return -EBUSY; + smb_break_all_levII_oplock(work, fp, 0); ksmbd_set_inode_pending_delete(fp); } else { ksmbd_clear_inode_pending_delete(fp); @@ -6725,7 +6729,7 @@ static int smb2_set_info_file(struct ksmbd_work *work, struct ksmbd_file *fp, if (buf_len < sizeof(struct smb2_file_disposition_info)) return -EMSGSIZE; - return set_file_disposition_info(fp, + return set_file_disposition_info(work, fp, (struct smb2_file_disposition_info *)buffer); } case FILE_FULL_EA_INFORMATION: From 2145945feb2c27d8e20f113ef81dc373631c4f05 Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Thu, 18 Jun 2026 21:33:40 +0900 Subject: [PATCH 163/297] ksmbd: route v2 lease breaks on the client lease channel v2 leases are scoped by ClientGuid. When the same client uses multiple connections, smbtorture expects lease break notifications to be sent on the connection associated with the client lease table, not necessarily on the connection that owns the individual open being broken. Keep a referenced connection in the lease table and use it for v2 lease break notifications while it is still active. Fall back to the open's connection if the table connection is being released. Signed-off-by: Namjae Jeon Signed-off-by: Steve French --- fs/smb/server/oplock.c | 17 +++++++++++++++-- fs/smb/server/oplock.h | 1 + 2 files changed, 16 insertions(+), 2 deletions(-) diff --git a/fs/smb/server/oplock.c b/fs/smb/server/oplock.c index fe0bbb0e1c89..d936c338f7c7 100644 --- a/fs/smb/server/oplock.c +++ b/fs/smb/server/oplock.c @@ -141,11 +141,21 @@ static struct lease_table *alloc_lease_table(struct oplock_info *opinfo) memcpy(lb->client_guid, opinfo->conn->ClientGUID, SMB2_CLIENT_GUID_SIZE); + lb->conn = ksmbd_conn_get(opinfo->conn); INIT_LIST_HEAD(&lb->lease_list); spin_lock_init(&lb->lb_lock); return lb; } +static void free_lease_table(struct lease_table *lb) +{ + if (!lb) + return; + + ksmbd_conn_put(lb->conn); + kfree(lb); +} + static struct lease *alloc_lease(struct lease_ctx_info *lctx, struct ksmbd_inode *ci) { @@ -942,6 +952,9 @@ static int smb2_lease_break_noti(struct oplock_info *opinfo, bool wait_ack, struct lease *lease = opinfo->o_lease; conn = READ_ONCE(opinfo->conn); + if (lease->version == 2 && lease->l_lb && lease->l_lb->conn && + !ksmbd_conn_releasing(lease->l_lb->conn)) + conn = lease->l_lb->conn; if (!conn) return 0; @@ -1134,7 +1147,7 @@ void destroy_lease_table(struct ksmbd_conn *conn) list_for_each_entry_safe(lease, ltmp, &lb->lease_list, l_entry) lease_del_table(lease); list_del(&lb->l_entry); - kfree(lb); + free_lease_table(lb); } write_unlock(&lease_list_lock); } @@ -1193,7 +1206,7 @@ static void add_lease_global_list(struct lease *lease, struct ksmbd_conn *conn, SMB2_CLIENT_GUID_SIZE)) { lease_add_table(lease, lb); write_unlock(&lease_list_lock); - kfree(new_lb); + free_lease_table(new_lb); return; } } diff --git a/fs/smb/server/oplock.h b/fs/smb/server/oplock.h index 1dd52b44557f..8d1943586246 100644 --- a/fs/smb/server/oplock.h +++ b/fs/smb/server/oplock.h @@ -34,6 +34,7 @@ struct lease_ctx_info { struct lease_table { char client_guid[SMB2_CLIENT_GUID_SIZE]; + struct ksmbd_conn *conn; struct list_head lease_list; struct list_head l_entry; spinlock_t lb_lock; From 411398c9a1414094f4e52c8893ef55ae3c61bf2a Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Thu, 18 Jun 2026 21:54:43 +0900 Subject: [PATCH 164/297] ksmbd: keep common response iovecs in the work item Most SMB responses need no more than four kvec entries, but every work item currently allocates a separate four-entry array and frees it after the response is sent. Embed the common array in struct ksmbd_work and allocate a larger array only when a response exceeds the inline capacity. This removes one allocation and one free from the common request path while preserving support for larger compound and read responses. Signed-off-by: Namjae Jeon Signed-off-by: Steve French --- fs/smb/server/ksmbd_work.c | 58 ++++++++++++++++++++++++-------------- fs/smb/server/ksmbd_work.h | 3 ++ 2 files changed, 40 insertions(+), 21 deletions(-) diff --git a/fs/smb/server/ksmbd_work.c b/fs/smb/server/ksmbd_work.c index a5ab6799a65c..e2c2f45264be 100644 --- a/fs/smb/server/ksmbd_work.c +++ b/fs/smb/server/ksmbd_work.c @@ -16,6 +16,36 @@ static struct kmem_cache *work_cache; static struct workqueue_struct *ksmbd_wq; +static int ksmbd_reserve_iov(struct ksmbd_work *work, int need_iov_cnt) +{ + struct kvec *new; + int new_alloc_cnt = work->iov_alloc_cnt; + + if (work->iov_alloc_cnt >= work->iov_cnt + need_iov_cnt) + return 0; + + do { + new_alloc_cnt += KSMBD_WORK_INLINE_IOVS; + } while (new_alloc_cnt < work->iov_cnt + need_iov_cnt); + + if (work->iov == work->iov_inline) { + new = kcalloc(new_alloc_cnt, sizeof(*new), KSMBD_DEFAULT_GFP); + if (!new) + return -ENOMEM; + + memcpy(new, work->iov_inline, sizeof(work->iov_inline)); + } else { + new = krealloc(work->iov, sizeof(*new) * new_alloc_cnt, + KSMBD_DEFAULT_GFP | __GFP_ZERO); + if (!new) + return -ENOMEM; + } + + work->iov = new; + work->iov_alloc_cnt = new_alloc_cnt; + return 0; +} + struct ksmbd_work *ksmbd_alloc_work_struct(void) { struct ksmbd_work *work = kmem_cache_zalloc(work_cache, KSMBD_DEFAULT_GFP); @@ -27,13 +57,8 @@ struct ksmbd_work *ksmbd_alloc_work_struct(void) INIT_LIST_HEAD(&work->async_request_entry); INIT_LIST_HEAD(&work->fp_entry); INIT_LIST_HEAD(&work->aux_read_list); - work->iov_alloc_cnt = 4; - work->iov = kzalloc_objs(struct kvec, work->iov_alloc_cnt, - KSMBD_DEFAULT_GFP); - if (!work->iov) { - kmem_cache_free(work_cache, work); - work = NULL; - } + work->iov_alloc_cnt = ARRAY_SIZE(work->iov_inline); + work->iov = work->iov_inline; } return work; } @@ -55,7 +80,8 @@ void ksmbd_free_work_struct(struct ksmbd_work *work) kfree(work->tr_buf); kvfree(work->compress_buf); kvfree(work->request_buf); - kfree(work->iov); + if (work->iov != work->iov_inline) + kfree(work->iov); if (work->async_id) ksmbd_release_id(&work->conn->async_ida, work->async_id); @@ -117,19 +143,9 @@ static int __ksmbd_iov_pin_rsp(struct ksmbd_work *work, void *ib, int len, return -ENOMEM; } - if (work->iov_alloc_cnt < work->iov_cnt + need_iov_cnt) { - struct kvec *new; - - work->iov_alloc_cnt += 4; - new = krealloc(work->iov, - sizeof(struct kvec) * work->iov_alloc_cnt, - KSMBD_DEFAULT_GFP | __GFP_ZERO); - if (!new) { - kfree(ar); - work->iov_alloc_cnt -= 4; - return -ENOMEM; - } - work->iov = new; + if (ksmbd_reserve_iov(work, need_iov_cnt)) { + kfree(ar); + return -ENOMEM; } /* Plus rfc_length size on first iov */ diff --git a/fs/smb/server/ksmbd_work.h b/fs/smb/server/ksmbd_work.h index 0da8cc0972d6..5368430561fb 100644 --- a/fs/smb/server/ksmbd_work.h +++ b/fs/smb/server/ksmbd_work.h @@ -13,6 +13,8 @@ struct ksmbd_conn; struct ksmbd_session; struct ksmbd_tree_connect; +#define KSMBD_WORK_INLINE_IOVS 4 + enum { KSMBD_WORK_ACTIVE = 0, KSMBD_WORK_CANCELLED, @@ -42,6 +44,7 @@ struct ksmbd_work { int iov_alloc_cnt; int iov_cnt; int iov_idx; + struct kvec iov_inline[KSMBD_WORK_INLINE_IOVS]; /* Next cmd hdr in compound req buf*/ int next_smb2_rcv_hdr_off; From 0c054227479ed7e36ebccb3a558bc0ef698264f6 Mon Sep 17 00:00:00 2001 From: Gil Portnoy Date: Fri, 19 Jun 2026 08:25:46 +0900 Subject: [PATCH 165/297] ksmbd: fix use-after-free of conn->preauth_info in concurrent SMB2 NEGOTIATE conn->preauth_info is shared connection state (struct preauth_integrity_info, kmalloc-96) that is allocated and freed by the SMB2 NEGOTIATE handler and read by the response send path. smb2_handle_negotiate() allocates conn->preauth_info, and on a deassemble_neg_contexts() failure kfrees it and sets it to NULL. Both the allocation and the free/NULL happen under ksmbd_conn_lock(conn) (the connection srv_mutex), which is held across the whole handler body. The response send path smb3_preauth_hash_rsp(), called from the send: block of __handle_ksmbd_work(), reads conn->preauth_info and dereferences conn->preauth_info->Preauth_HashValue (via ksmbd_gen_preauth_integrity_hash()) without taking conn_lock. When a client drives two SMB2 NEGOTIATE requests on the same connection, one worker can free conn->preauth_info on the failing-negotiate path while a concurrent send-path worker is reading it, producing a slab use-after-free read (KASAN-confirmed). The send-path read tested conn->preauth_info for NULL but raced with the free that occurs between the NULL check and the dereference, so the NULL guard alone does not close the window. Serialize the NEGOTIATE-branch read in smb3_preauth_hash_rsp() under ksmbd_conn_lock(conn) and re-check conn->preauth_info inside the lock. Because the negotiate handler holds conn_lock across its kfree + NULL assignment, a reader that also takes conn_lock either runs fully before the allocation or fully after the NULL store, and can never observe the freed-but-not-yet-NULLed pointer. ksmbd_gen_preauth_integrity_hash() takes no locks itself (it only computes a SHA-512 over the buffer), so no lock-ordering inversion is introduced, and conn_lock is a sleepable mutex which is safe on this send path (it already performs network I/O). Fixes: aa7253c2393f ("ksmbd: fix memory leak in smb2_handle_negotiate") Signed-off-by: Gil Portnoy Acked-by: Namjae Jeon Signed-off-by: Steve French --- fs/smb/server/smb2pdu.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index f1a0bce0c1f7..2bc275ed450a 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -9368,10 +9368,13 @@ void smb3_preauth_hash_rsp(struct ksmbd_work *work) WORK_BUFFERS(work, req, rsp); - if (le16_to_cpu(req->Command) == SMB2_NEGOTIATE_HE && - conn->preauth_info) - ksmbd_gen_preauth_integrity_hash(conn, work->response_buf, - conn->preauth_info->Preauth_HashValue); + if (le16_to_cpu(req->Command) == SMB2_NEGOTIATE_HE) { + ksmbd_conn_lock(conn); + if (conn->preauth_info) + ksmbd_gen_preauth_integrity_hash(conn, work->response_buf, + conn->preauth_info->Preauth_HashValue); + ksmbd_conn_unlock(conn); + } if (le16_to_cpu(rsp->Command) == SMB2_SESSION_SETUP_HE && sess) { __u8 *hash_value; From a04159d96c27fd4836538ea6e8ff653b65242eac Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Sun, 21 Jun 2026 19:32:18 +0900 Subject: [PATCH 166/297] ksmbd: handle missing create contexts for lease opens smb2_find_context_vals() assumes that callers only search create contexts when the SMB2 CREATE request contains a non-empty create context area. That is not always true. a client can send RequestedOplockLevel set to SMB2_OPLOCK_LEVEL_LEASE without a lease create context. In that case parse_lease_state() searches for a lease context and smb2_find_context_vals() starts parsing from offset 0 with length 0, returning -EINVAL. This makes the open fail with STATUS_INVALID_PARAMETER. The smbtorture smb2.lease.duplicate_open test hits this while creating a second file without a lease request. Return NULL when the request has no create context area so the missing context is treated the same as any other absent create context. The open then continues without granting a lease. Signed-off-by: Namjae Jeon Signed-off-by: Steve French --- fs/smb/server/oplock.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/fs/smb/server/oplock.c b/fs/smb/server/oplock.c index d936c338f7c7..5424f2a5cf3d 100644 --- a/fs/smb/server/oplock.c +++ b/fs/smb/server/oplock.c @@ -1760,6 +1760,9 @@ struct create_context *smb2_find_context_vals(void *open_req, const char *tag, i * CreateContextsOffset and CreateContextsLength are guaranteed to * be valid because of ksmbd_smb2_check_message(). */ + if (!req->CreateContextsOffset || !req->CreateContextsLength) + return NULL; + cc = (struct create_context *)((char *)req + le32_to_cpu(req->CreateContextsOffset)); remain_len = le32_to_cpu(req->CreateContextsLength); From 166e4c07023b9c5d076f69e63164b6e1d52709c9 Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Sun, 21 Jun 2026 19:33:03 +0900 Subject: [PATCH 167/297] ksmbd: supersede disconnected delete-on-close durable handle A durable handle opened with FILE_DELETE_ON_CLOSE is preserved across a disconnect so it can be reclaimed by a durable reconnect. smb2.durable-open.delete_on_close2 disconnects such a handle and then reconnects it, expecting the reconnect to succeed. When the client does not reconnect but instead opens the same name with a new delete-on-close create, the preserved handle keeps the file present with delete-on-close set. ksmbd then rejects the new open with STATUS_ACCESS_DENIED on the file_present + FILE_DELETE_ON_CLOSE + OPEN_IF/OVERWRITE_IF path. smb2.durable-open.delete_on_close1 expects this open to create a fresh, empty file instead, i.e. the disconnected handle's delete-on-close must take effect first. Add ksmbd_close_disconnected_durable_delete_on_close(), which closes disconnected (conn == NULL) durable handles that keep a delete-on-close file present. The final close promotes S_DEL_ON_CLS to S_DEL_PENDING and unlinks the file, so a re-resolved path is absent and the new open creates it fresh. Call it from smb2_open() before the delete-on-close conflict check, only for the conflicting open shapes. A live (connected) handle still keeps the file and blocks the open as before. Signed-off-by: Namjae Jeon Signed-off-by: Steve French --- fs/smb/server/smb2pdu.c | 17 ++++++++++++ fs/smb/server/vfs_cache.c | 57 +++++++++++++++++++++++++++++++++++++++ fs/smb/server/vfs_cache.h | 1 + 3 files changed, 75 insertions(+) diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index 2bc275ed450a..37a20c5740cd 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -3272,6 +3272,23 @@ int smb2_open(struct ksmbd_work *work) rc = ksmbd_vfs_kern_path(work, name, LOOKUP_NO_SYMLINKS, &path, 1); + + /* + * A durable handle opened with delete-on-close is preserved across a + * disconnect so it can be reclaimed by a durable reconnect. When a new + * delete-on-close open for the same name arrives instead, the + * disconnected handle must give way: close it so its delete-on-close + * removes the file, then re-resolve so this open can create a fresh one. + */ + if (!rc && (req->CreateOptions & FILE_DELETE_ON_CLOSE_LE) && + (req->CreateDisposition == FILE_OVERWRITE_IF_LE || + req->CreateDisposition == FILE_OPEN_IF_LE) && + ksmbd_close_disconnected_durable_delete_on_close(path.dentry)) { + path_put(&path); + rc = ksmbd_vfs_kern_path(work, name, LOOKUP_NO_SYMLINKS, + &path, 1); + } + if (!rc) { file_present = true; diff --git a/fs/smb/server/vfs_cache.c b/fs/smb/server/vfs_cache.c index 39c56942ae44..96fa3f160d5b 100644 --- a/fs/smb/server/vfs_cache.c +++ b/fs/smb/server/vfs_cache.c @@ -517,6 +517,63 @@ static void __ksmbd_close_fd(struct ksmbd_file_table *ft, struct ksmbd_file *fp) kmem_cache_free(filp_cache, fp); } +/** + * ksmbd_close_disconnected_durable_delete_on_close() - drop a delete-on-close + * file kept present only by disconnected durable handles + * @dentry: dentry of the file being opened + * + * A durable handle opened with delete-on-close is preserved across a + * disconnect so it can be reclaimed by a durable reconnect. When a new + * (non-reconnect) open arrives for the same name instead, the disconnected + * handle has to give way. Close such handles so their delete-on-close is + * applied and the file is removed once the last handle is gone, letting the + * new open create a fresh file. + * + * The caller's inode reference is dropped before closing so that the final + * close can promote S_DEL_ON_CLS to S_DEL_PENDING and unlink the file. + * + * Return: true if a disconnected durable handle was closed. + */ +bool ksmbd_close_disconnected_durable_delete_on_close(struct dentry *dentry) +{ + struct ksmbd_inode *ci; + struct ksmbd_file *fp, *tmp; + LIST_HEAD(dispose); + bool closed = false; + + ci = ksmbd_inode_lookup_lock(dentry); + if (!ci) + return false; + + down_write(&ci->m_lock); + if (ci->m_flags & (S_DEL_ON_CLS | S_DEL_ON_CLS_STREAM | S_DEL_PENDING)) { + list_for_each_entry_safe(fp, tmp, &ci->m_fp_list, node) { + if (fp->conn || !fp->is_durable || + fp->f_state != FP_INITED) + continue; + list_move_tail(&fp->node, &dispose); + } + } + up_write(&ci->m_lock); + + /* + * Drop our lookup reference before closing so the last __ksmbd_close_fd() + * can drop m_count to zero and unlink the delete-on-close file. The + * collected handles still hold references, so ci stays valid until they + * are closed below. + */ + ksmbd_inode_put(ci); + + while (!list_empty(&dispose)) { + fp = list_first_entry(&dispose, struct ksmbd_file, node); + list_del_init(&fp->node); + __ksmbd_close_fd(NULL, fp); + closed = true; + } + + return closed; +} + static struct ksmbd_file *ksmbd_fp_get(struct ksmbd_file *fp) { if (fp->f_state != FP_INITED) diff --git a/fs/smb/server/vfs_cache.h b/fs/smb/server/vfs_cache.h index a3a9fda6de91..21c24956c7c2 100644 --- a/fs/smb/server/vfs_cache.h +++ b/fs/smb/server/vfs_cache.h @@ -160,6 +160,7 @@ struct ksmbd_file *ksmbd_lookup_fd_slow(struct ksmbd_work *work, u64 id, void ksmbd_fd_put(struct ksmbd_work *work, struct ksmbd_file *fp); struct ksmbd_inode *ksmbd_inode_lookup_lock(struct dentry *d); void ksmbd_inode_put(struct ksmbd_inode *ci); +bool ksmbd_close_disconnected_durable_delete_on_close(struct dentry *dentry); struct ksmbd_file *ksmbd_lookup_global_fd(unsigned long long id); struct ksmbd_file *ksmbd_lookup_durable_fd(unsigned long long id); void ksmbd_put_durable_fd(struct ksmbd_file *fp); From 26fa88dc877ccd2736e9125d37c22e058a4c7b86 Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Sun, 21 Jun 2026 19:33:54 +0900 Subject: [PATCH 168/297] ksmbd: invalidate durable handles on oplock break When a durable handle is preserved after a disconnect, its oplock state can still block later opens. If another client opens the same file and the preserved oplock or lease has to be broken, the old durable handle must no longer be reconnectable after the break cannot be acknowledged. ksmbd was treating a missing connection, or an oplock break timeout, as a successful break only by downgrading the oplock state. The old durable handle remained reconnectable, so a later durable reconnect for that stale handle could succeed. The open path can also see a detached durable handle before the break notification helpers fully dispose of it. Invalidate such a preserved durable handle directly when a competing open has to break its batch or exclusive oplock, while leaving ordinary durable reconnects without a competing open untouched. If the old handle still reaches the reconnect path, reject it when the same inode already has another active open. This matches the smb2.durable-open.open2-lease/open2-oplock sequence where a later open replaces the disconnected durable owner and the stale first handle must not be reclaimed. Also, reconnect lookup used only the persistent id. A new durable open can get a persistent id that matches the stale reconnect request after the old durable state is invalidated. Preserve the disconnected handle's old volatile id and require durable reconnect contexts to match it, so a stale reconnect cannot attach to a different durable open. Windows allows the later open to proceed and rejects the old reconnect with STATUS_OBJECT_NAME_NOT_FOUND. The smbtorture smb2.durable-open.oplock test covers this case. Signed-off-by: Namjae Jeon Signed-off-by: Steve French --- fs/smb/server/oplock.c | 40 +++++++++++++++++++++++++------ fs/smb/server/smb2pdu.c | 14 +++++++++++ fs/smb/server/vfs_cache.c | 50 ++++++++++++++++++++++++++++++++++++++- fs/smb/server/vfs_cache.h | 4 ++++ 4 files changed, 100 insertions(+), 8 deletions(-) diff --git a/fs/smb/server/oplock.c b/fs/smb/server/oplock.c index 5424f2a5cf3d..0fddbaa5ba63 100644 --- a/fs/smb/server/oplock.c +++ b/fs/smb/server/oplock.c @@ -676,7 +676,7 @@ static struct oplock_info *same_client_has_lease(struct ksmbd_inode *ci, return m_opinfo; } -static void wait_for_break_ack(struct oplock_info *opinfo) +static bool wait_for_break_ack(struct oplock_info *opinfo) { int rc = 0; @@ -693,7 +693,10 @@ static void wait_for_break_ack(struct oplock_info *opinfo) } opinfo->level = SMB2_OPLOCK_LEVEL_NONE; opinfo->op_state = OPLOCK_STATE_NONE; + return true; } + + return false; } static void wake_up_oplock_break(struct oplock_info *opinfo) @@ -843,7 +846,7 @@ static int smb2_oplock_break_noti(struct oplock_info *opinfo) conn = READ_ONCE(opinfo->conn); if (!conn) - return 0; + return ksmbd_invalidate_durable_fd(opinfo->fid); work = ksmbd_alloc_work_struct(); if (!work) @@ -868,7 +871,8 @@ static int smb2_oplock_break_noti(struct oplock_info *opinfo) INIT_WORK(&work->work, __smb2_oplock_break_noti); ksmbd_queue_work(work); - wait_for_break_ack(opinfo); + if (wait_for_break_ack(opinfo)) + ret = ksmbd_invalidate_durable_fd(opinfo->fid); } else { __smb2_oplock_break_noti(&work->work); if (opinfo->level == SMB2_OPLOCK_LEVEL_II) @@ -950,13 +954,14 @@ static int smb2_lease_break_noti(struct oplock_info *opinfo, bool wait_ack, struct ksmbd_work *work; struct lease_break_info *br_info; struct lease *lease = opinfo->o_lease; + int ret = 0; conn = READ_ONCE(opinfo->conn); if (lease->version == 2 && lease->l_lb && lease->l_lb->conn && !ksmbd_conn_releasing(lease->l_lb->conn)) conn = lease->l_lb->conn; if (!conn) - return 0; + return ksmbd_invalidate_durable_fd(opinfo->fid); work = ksmbd_alloc_work_struct(); if (!work) @@ -987,8 +992,10 @@ static int smb2_lease_break_noti(struct oplock_info *opinfo, bool wait_ack, if (opinfo->op_state == OPLOCK_ACK_WAIT) { INIT_WORK(&work->work, __smb2_lease_break_noti); ksmbd_queue_work(work); - if (wait_ack) - wait_for_break_ack(opinfo); + if (wait_ack) { + if (wait_for_break_ack(opinfo)) + ret = ksmbd_invalidate_durable_fd(opinfo->fid); + } } else { __smb2_lease_break_noti(&work->work); if (opinfo->o_lease->new_state == SMB2_LEASE_NONE_LE) { @@ -996,7 +1003,7 @@ static int smb2_lease_break_noti(struct oplock_info *opinfo, bool wait_ack, lease_update_oplock_levels(opinfo->o_lease); } } - return 0; + return ret; } static void wait_lease_breaking(struct oplock_info *opinfo) @@ -1335,6 +1342,9 @@ int smb_grant_oplock(struct ksmbd_work *work, int req_op_level, u64 pid, struct ksmbd_inode *ci = fp->f_ci; struct lease_table *new_lb = NULL; bool prev_op_has_lease; + bool prev_durable_open = false; + bool prev_durable_detached = false; + unsigned long long prev_fid = KSMBD_NO_FID; bool new_lease = false; __le32 prev_op_state = 0; @@ -1412,7 +1422,17 @@ int smb_grant_oplock(struct ksmbd_work *work, int req_op_level, u64 pid, goto op_break_not_needed; } + if (prev_opinfo->o_fp && prev_opinfo->o_fp != fp && + prev_opinfo->o_fp->is_durable) { + prev_durable_open = true; + prev_durable_detached = !prev_opinfo->o_fp->conn || + !prev_opinfo->o_fp->tcon; + prev_fid = prev_opinfo->fid; + } + err = oplock_break(prev_opinfo, break_level, work); + if (prev_durable_detached || (prev_durable_open && err == -ENOENT)) + ksmbd_invalidate_durable_fd(prev_fid); opinfo_put(prev_opinfo); if (err == -ENOENT) goto set_lev; @@ -2029,6 +2049,12 @@ int smb2_check_durable_oplock(struct ksmbd_conn *conn, if (!opinfo) return 0; + if (ksmbd_has_other_active_fd(fp)) { + ksmbd_debug(SMB, "Durable handle reconnect failed: competing open\n"); + ret = -EBADF; + goto out; + } + if (ksmbd_vfs_compare_durable_owner(fp, user) == false) { ksmbd_debug(SMB, "Durable handle reconnect failed: owner mismatch\n"); ret = -EBADF; diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index 37a20c5740cd..f700f2f94ff2 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -2861,6 +2861,13 @@ static int parse_durable_handle_context(struct ksmbd_work *work, goto out; } + if (dh_info->fp->durable_volatile_id != + recon_v2->dcontext.Fid.VolatileFileId) { + err = -EBADF; + ksmbd_put_durable_fd(dh_info->fp); + goto out; + } + if (memcmp(dh_info->fp->create_guid, recon_v2->dcontext.CreateGuid, SMB2_CREATE_GUID_SIZE)) { err = -EBADF; @@ -2901,6 +2908,13 @@ static int parse_durable_handle_context(struct ksmbd_work *work, goto out; } + if (dh_info->fp->durable_volatile_id != + recon->Data.Fid.VolatileFileId) { + err = -EBADF; + ksmbd_put_durable_fd(dh_info->fp); + goto out; + } + dh_info->type = dh_idx; dh_info->reconnected = true; ksmbd_debug(SMB, "reconnect Persistent-id from reconnect = %llu\n", diff --git a/fs/smb/server/vfs_cache.c b/fs/smb/server/vfs_cache.c index 96fa3f160d5b..3546d95df76f 100644 --- a/fs/smb/server/vfs_cache.c +++ b/fs/smb/server/vfs_cache.c @@ -731,7 +731,8 @@ struct ksmbd_file *ksmbd_lookup_durable_fd(unsigned long long id) struct ksmbd_file *fp; fp = __ksmbd_lookup_fd(&global_ft, id); - if (fp && (fp->conn || + if (fp && (fp->durable_reconnect_disabled || + fp->conn || (fp->durable_scavenger_timeout && (fp->durable_scavenger_timeout < jiffies_to_msecs(jiffies))))) { @@ -750,6 +751,52 @@ void ksmbd_put_durable_fd(struct ksmbd_file *fp) __ksmbd_close_fd(NULL, fp); } +bool ksmbd_has_other_active_fd(struct ksmbd_file *fp) +{ + struct ksmbd_file *lfp; + struct ksmbd_inode *ci = fp->f_ci; + bool ret = false; + + down_read(&ci->m_lock); + list_for_each_entry(lfp, &ci->m_fp_list, node) { + if (lfp == fp) + continue; + + if (lfp->f_state == FP_INITED && + (READ_ONCE(lfp->conn) || READ_ONCE(lfp->tcon))) { + ret = true; + break; + } + } + up_read(&ci->m_lock); + + return ret; +} + +int ksmbd_invalidate_durable_fd(unsigned long long id) +{ + struct ksmbd_file *fp; + + fp = ksmbd_lookup_global_fd(id); + if (!fp) + return -ENOENT; + + fp->durable_reconnect_disabled = true; + + if (fp->conn) { + ksmbd_put_durable_fd(fp); + return -ENOENT; + } + + fp->durable_timeout = 1; + fp->durable_scavenger_timeout = jiffies_to_msecs(jiffies); + ksmbd_put_durable_fd(fp); + if (waitqueue_active(&dh_wq)) + wake_up(&dh_wq); + + return -ENOENT; +} + struct ksmbd_file *ksmbd_lookup_fd_cguid(char *cguid) { struct ksmbd_file *fp = NULL; @@ -990,6 +1037,7 @@ __close_file_table_ids(struct ksmbd_session *sess, * global_ft. */ idr_remove(ft->idr, id); + fp->durable_volatile_id = fp->volatile_id; fp->volatile_id = KSMBD_NO_FID; write_unlock(&ft->lock); diff --git a/fs/smb/server/vfs_cache.h b/fs/smb/server/vfs_cache.h index 21c24956c7c2..4803f41a91ef 100644 --- a/fs/smb/server/vfs_cache.h +++ b/fs/smb/server/vfs_cache.h @@ -81,6 +81,7 @@ struct ksmbd_file { struct file *filp; u64 persistent_id; u64 volatile_id; + u64 durable_volatile_id; spinlock_t f_lock; @@ -122,6 +123,7 @@ struct ksmbd_file { bool is_durable; bool is_persistent; bool is_resilient; + bool durable_reconnect_disabled; bool is_posix_ctxt; struct durable_owner owner; @@ -164,6 +166,8 @@ bool ksmbd_close_disconnected_durable_delete_on_close(struct dentry *dentry); struct ksmbd_file *ksmbd_lookup_global_fd(unsigned long long id); struct ksmbd_file *ksmbd_lookup_durable_fd(unsigned long long id); void ksmbd_put_durable_fd(struct ksmbd_file *fp); +int ksmbd_invalidate_durable_fd(unsigned long long id); +bool ksmbd_has_other_active_fd(struct ksmbd_file *fp); struct ksmbd_file *ksmbd_lookup_fd_cguid(char *cguid); struct ksmbd_file *ksmbd_lookup_fd_inode(struct dentry *dentry); unsigned int ksmbd_open_durable_fd(struct ksmbd_file *fp); From 73cd6295d01d8d49abaa03472878ef133e43d26a Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Sun, 21 Jun 2026 19:34:37 +0900 Subject: [PATCH 169/297] ksmbd: fix durable reconnect context parsing SMB2 create context DataLength describes only the create context data payload. It does not include the create context header, name field, or any local padding that exists in ksmbd's helper structures. ksmbd validated durable reconnect contexts by comparing DataOffset + DataLength against sizeof the whole helper structure. This rejects a valid durable v2 reconnect context because the wire DH2C data is 36 bytes while struct create_durable_handle_reconnect_v2 contains an extra four byte pad. Validate the durable context payload length against the corresponding payload member instead. Also keep the reconnect context authoritative when a later durable request context is present, matching the existing durable v1 reconnect behavior. This fixes smbtorture smb2.durable-v2-open.durable-v2-setinfo, where the durable v2 reconnect after SET_INFO was rejected with STATUS_INVALID_PARAMETER. Signed-off-by: Namjae Jeon Signed-off-by: Steve French --- fs/smb/server/smb2pdu.c | 15 ++++++--------- 1 file changed, 6 insertions(+), 9 deletions(-) diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index f700f2f94ff2..35db86da79d3 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -2845,9 +2845,8 @@ static int parse_durable_handle_context(struct ksmbd_work *work, goto out; } - if (le16_to_cpu(context->DataOffset) + - le32_to_cpu(context->DataLength) < - sizeof(struct create_durable_handle_reconnect_v2)) { + if (le32_to_cpu(context->DataLength) < + sizeof(recon_v2->dcontext)) { err = -EINVAL; goto out; } @@ -2892,9 +2891,8 @@ static int parse_durable_handle_context(struct ksmbd_work *work, goto out; } - if (le16_to_cpu(context->DataOffset) + - le32_to_cpu(context->DataLength) < - sizeof(create_durable_reconn_t)) { + if (le32_to_cpu(context->DataLength) < + sizeof(recon->Data)) { err = -EINVAL; goto out; } @@ -2931,9 +2929,8 @@ static int parse_durable_handle_context(struct ksmbd_work *work, goto out; } - if (le16_to_cpu(context->DataOffset) + - le32_to_cpu(context->DataLength) < - sizeof(struct create_durable_req_v2)) { + if (le32_to_cpu(context->DataLength) < + sizeof(durable_v2_blob->dcontext)) { err = -EINVAL; goto out; } From 16c30649709d949b439273e61769028b1e706327 Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Sun, 21 Jun 2026 19:35:12 +0900 Subject: [PATCH 170/297] ksmbd: handle durable v2 app instance id The SMB2_CREATE_APP_INSTANCE_ID create context is used with durable v2 opens to identify another open from the same application instance. When a new durable v2 open arrives with the same AppInstanceId as an existing open, the server should close the previous open without sending an oplock break notification. ksmbd ignored this create context. A second durable v2 batch oplock open with the same AppInstanceId therefore went through the normal competing open path and sent an oplock break to the first opener. smbtorture smb2.durable-v2-open.app-instance expects no oplock break and then expects the old handle to be closed. Parse and store AppInstanceId for durable v2 opens. Before creating the new open, find an existing file with the same AppInstanceId and close it through the normal close teardown path without issuing an oplock break. Signed-off-by: Namjae Jeon Signed-off-by: Steve French --- fs/smb/server/smb2pdu.c | 37 ++++++++++++++++++++ fs/smb/server/vfs_cache.c | 72 +++++++++++++++++++++++++++++++++++++++ fs/smb/server/vfs_cache.h | 1 + 3 files changed, 110 insertions(+) diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index 35db86da79d3..a21760394637 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -2807,8 +2807,10 @@ struct durable_info { unsigned short int type; bool persistent; bool reconnected; + bool app_instance_id; unsigned int timeout; char *CreateGuid; + char AppInstanceId[SMB2_CREATE_GUID_SIZE]; }; static int parse_durable_handle_context(struct ksmbd_work *work, @@ -2993,6 +2995,31 @@ out: return err; } +static int parse_app_instance_id(struct smb2_create_req *req, + struct durable_info *dh_info) +{ + struct create_context *context; + char *data; + + context = smb2_find_context_vals(req, SMB2_CREATE_APP_INSTANCE_ID, + SMB2_CREATE_GUID_SIZE); + if (IS_ERR(context)) + return PTR_ERR(context); + if (!context) + return 0; + + if (le32_to_cpu(context->DataLength) < 20) + return -EINVAL; + + data = (char *)context + le16_to_cpu(context->DataOffset); + if (data[0] != 20 || data[1]) + return -EINVAL; + + memcpy(dh_info->AppInstanceId, data + 4, SMB2_CREATE_GUID_SIZE); + dh_info->app_instance_id = true; + return 0; +} + /** * smb2_open() - handler for smb file open request * @work: smb work containing request buffer @@ -3135,6 +3162,9 @@ int smb2_open(struct ksmbd_work *work) ksmbd_debug(SMB, "error parsing durable handle context\n"); goto err_out2; } + rc = parse_app_instance_id(req, &dh_info); + if (rc) + goto err_out2; if (dh_info.reconnected == true) { rc = smb2_check_durable_oplock(conn, share, dh_info.fp, @@ -3161,6 +3191,9 @@ int smb2_open(struct ksmbd_work *work) goto reconnected_fp; } + + if (dh_info.type == DURABLE_REQ_V2 && dh_info.app_instance_id) + ksmbd_close_fd_app_instance_id(dh_info.AppInstanceId); } else if (req_op_level == SMB2_OPLOCK_LEVEL_LEASE) { lc = parse_lease_state(req); if (IS_ERR(lc)) { @@ -3775,6 +3808,10 @@ int smb2_open(struct ksmbd_work *work) if (dh_info.type == DURABLE_REQ_V2) { memcpy(fp->create_guid, dh_info.CreateGuid, SMB2_CREATE_GUID_SIZE); + if (dh_info.app_instance_id) + memcpy(fp->app_instance_id, + dh_info.AppInstanceId, + SMB2_CREATE_GUID_SIZE); if (dh_info.timeout) fp->durable_timeout = min_t(unsigned int, dh_info.timeout, diff --git a/fs/smb/server/vfs_cache.c b/fs/smb/server/vfs_cache.c index 3546d95df76f..5a2fddadcddf 100644 --- a/fs/smb/server/vfs_cache.c +++ b/fs/smb/server/vfs_cache.c @@ -37,6 +37,8 @@ static struct ksmbd_file_table global_ft; static atomic_long_t fd_limit; static struct kmem_cache *filp_cache; +static int ksmbd_mark_fp_closed(struct ksmbd_file *fp); + #define OPLOCK_NONE 0 #define OPLOCK_EXCLUSIVE 1 #define OPLOCK_BATCH 2 @@ -773,6 +775,76 @@ bool ksmbd_has_other_active_fd(struct ksmbd_file *fp) return ret; } +static struct ksmbd_file *ksmbd_lookup_fd_app_instance_id(char *app_instance_id) +{ + struct ksmbd_file *fp = NULL; + unsigned int id; + + if (!memchr_inv(app_instance_id, 0, SMB2_CREATE_GUID_SIZE)) + return NULL; + + read_lock(&global_ft.lock); + idr_for_each_entry(global_ft.idr, fp, id) { + if (!memcmp(fp->app_instance_id, app_instance_id, + SMB2_CREATE_GUID_SIZE)) { + fp = ksmbd_fp_get(fp); + break; + } + } + read_unlock(&global_ft.lock); + + return fp; +} + +int ksmbd_close_fd_app_instance_id(char *app_instance_id) +{ + struct ksmbd_file_table *ft; + struct ksmbd_file *fp; + struct oplock_info *opinfo; + int n_to_drop = 0; + + fp = ksmbd_lookup_fd_app_instance_id(app_instance_id); + if (!fp) + return 0; + + opinfo = opinfo_get(fp); + if (!opinfo || !opinfo->sess) + goto out; + + ft = &opinfo->sess->file_table; + write_lock(&ft->lock); + if (fp->f_state == FP_INITED) { + if (has_file_id(fp->volatile_id)) { + idr_remove(ft->idr, fp->volatile_id); + fp->volatile_id = KSMBD_NO_FID; + } + n_to_drop = ksmbd_mark_fp_closed(fp); + } + write_unlock(&ft->lock); + opinfo_put(opinfo); + opinfo = NULL; + + if (!n_to_drop) + goto out; + + down_write(&fp->f_ci->m_lock); + list_del_init(&fp->node); + up_write(&fp->f_ci->m_lock); + + if (atomic_sub_and_test(n_to_drop, &fp->refcount)) { + if (fp->conn) + atomic_dec(&fp->conn->stats.open_files_count); + __ksmbd_close_fd(NULL, fp); + } + return 0; + +out: + if (opinfo) + opinfo_put(opinfo); + ksmbd_put_durable_fd(fp); + return 0; +} + int ksmbd_invalidate_durable_fd(unsigned long long id) { struct ksmbd_file *fp; diff --git a/fs/smb/server/vfs_cache.h b/fs/smb/server/vfs_cache.h index 4803f41a91ef..ca391d597e2e 100644 --- a/fs/smb/server/vfs_cache.h +++ b/fs/smb/server/vfs_cache.h @@ -168,6 +168,7 @@ struct ksmbd_file *ksmbd_lookup_durable_fd(unsigned long long id); void ksmbd_put_durable_fd(struct ksmbd_file *fp); int ksmbd_invalidate_durable_fd(unsigned long long id); bool ksmbd_has_other_active_fd(struct ksmbd_file *fp); +int ksmbd_close_fd_app_instance_id(char *app_instance_id); struct ksmbd_file *ksmbd_lookup_fd_cguid(char *cguid); struct ksmbd_file *ksmbd_lookup_fd_inode(struct dentry *dentry); unsigned int ksmbd_open_durable_fd(struct ksmbd_file *fp); From 24dcee8305d6ba18c69594ca6fb42eaa32f8e63e Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Sun, 21 Jun 2026 19:36:40 +0900 Subject: [PATCH 171/297] ksmbd: preserve open change time across rename inode ctime is updated when a file is renamed. ksmbd returned that ctime directly as SMB2 ChangeTime for handle-based query information. This makes ChangeTime change after a rename through an already-open handle, while Windows keeps the handle's ChangeTime stable for this case. Store the SMB ChangeTime in struct ksmbd_file when the handle is opened and use that value for create, close, and handle-based query information responses. If a client explicitly sets FILE_BASIC_INFORMATION ChangeTime, update the stored value as well. This fixes smbtorture smb2.rename.simple_modtime, which expects ChangeTime and LastWriteTime to remain unchanged after renaming an already-open file. Signed-off-by: Namjae Jeon Signed-off-by: Steve French --- fs/smb/server/smb2pdu.c | 23 ++++++++++------------- fs/smb/server/vfs_cache.h | 1 + 2 files changed, 11 insertions(+), 13 deletions(-) diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index a21760394637..f2ba52c7e325 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -3783,6 +3783,7 @@ int smb2_open(struct ksmbd_work *work) fp->create_time = ksmbd_UnixTimeToNT(stat.btime); else fp->create_time = ksmbd_UnixTimeToNT(stat.ctime); + fp->change_time = ksmbd_UnixTimeToNT(stat.ctime); if (req->FileAttributes || fp->f_ci->m_fattr == 0) fp->f_ci->m_fattr = cpu_to_le32(smb2_get_dos_mode(&stat, le32_to_cpu(req->FileAttributes))); @@ -3832,8 +3833,7 @@ reconnected_fp: rsp->LastAccessTime = cpu_to_le64(time); time = ksmbd_UnixTimeToNT(stat.mtime); rsp->LastWriteTime = cpu_to_le64(time); - time = ksmbd_UnixTimeToNT(stat.ctime); - rsp->ChangeTime = cpu_to_le64(time); + rsp->ChangeTime = cpu_to_le64(fp->change_time); rsp->AllocationSize = S_ISDIR(stat.mode) ? 0 : cpu_to_le64(stat.blocks << 9); rsp->EndofFile = S_ISDIR(stat.mode) ? 0 : cpu_to_le64(stat.size); @@ -5102,8 +5102,7 @@ static int get_file_basic_info(struct smb2_query_info_rsp *rsp, basic_info->LastAccessTime = cpu_to_le64(time); time = ksmbd_UnixTimeToNT(stat.mtime); basic_info->LastWriteTime = cpu_to_le64(time); - time = ksmbd_UnixTimeToNT(stat.ctime); - basic_info->ChangeTime = cpu_to_le64(time); + basic_info->ChangeTime = cpu_to_le64(fp->change_time); basic_info->Attributes = fp->f_ci->m_fattr; basic_info->Pad = 0; rsp->OutputBufferLength = @@ -5205,8 +5204,7 @@ static int get_file_all_info(struct ksmbd_work *work, file_info->LastAccessTime = cpu_to_le64(time); time = ksmbd_UnixTimeToNT(stat.mtime); file_info->LastWriteTime = cpu_to_le64(time); - time = ksmbd_UnixTimeToNT(stat.ctime); - file_info->ChangeTime = cpu_to_le64(time); + file_info->ChangeTime = cpu_to_le64(fp->change_time); file_info->Attributes = fp->f_ci->m_fattr; file_info->Pad1 = 0; if (ksmbd_stream_fd(fp) == false) { @@ -5415,8 +5413,7 @@ static int get_file_network_open_info(struct smb2_query_info_rsp *rsp, file_info->LastAccessTime = cpu_to_le64(time); time = ksmbd_UnixTimeToNT(stat.mtime); file_info->LastWriteTime = cpu_to_le64(time); - time = ksmbd_UnixTimeToNT(stat.ctime); - file_info->ChangeTime = cpu_to_le64(time); + file_info->ChangeTime = cpu_to_le64(fp->change_time); file_info->Attributes = fp->f_ci->m_fattr; if (ksmbd_stream_fd(fp) == false) { file_info->AllocationSize = cpu_to_le64(stat.blocks << 9); @@ -5547,8 +5544,7 @@ static int find_file_posix_info(struct smb2_query_info_rsp *rsp, file_info->LastAccessTime = cpu_to_le64(time); time = ksmbd_UnixTimeToNT(stat.mtime); file_info->LastWriteTime = cpu_to_le64(time); - time = ksmbd_UnixTimeToNT(stat.ctime); - file_info->ChangeTime = cpu_to_le64(time); + file_info->ChangeTime = cpu_to_le64(fp->change_time); file_info->DosAttributes = fp->f_ci->m_fattr; file_info->Inode = cpu_to_le64(stat.ino); if (ksmbd_stream_fd(fp) == false) { @@ -6271,8 +6267,7 @@ int smb2_close(struct ksmbd_work *work) rsp->LastAccessTime = cpu_to_le64(time); time = ksmbd_UnixTimeToNT(stat.mtime); rsp->LastWriteTime = cpu_to_le64(time); - time = ksmbd_UnixTimeToNT(stat.ctime); - rsp->ChangeTime = cpu_to_le64(time); + rsp->ChangeTime = cpu_to_le64(fp->change_time); ksmbd_fd_put(work, fp); } else { rsp->Flags = 0; @@ -6485,9 +6480,11 @@ static int set_file_basic_info(struct ksmbd_file *fp, attrs.ia_valid |= (ATTR_ATIME | ATTR_ATIME_SET); } - if (file_info->ChangeTime) + if (file_info->ChangeTime) { + fp->change_time = le64_to_cpu(file_info->ChangeTime); inode_set_ctime_to_ts(inode, ksmbd_NTtimeToUnix(file_info->ChangeTime)); + } if (file_info->LastWriteTime) { attrs.ia_mtime = ksmbd_NTtimeToUnix(file_info->LastWriteTime); diff --git a/fs/smb/server/vfs_cache.h b/fs/smb/server/vfs_cache.h index ca391d597e2e..8c456484cab2 100644 --- a/fs/smb/server/vfs_cache.h +++ b/fs/smb/server/vfs_cache.h @@ -97,6 +97,7 @@ struct ksmbd_file { __le32 coption; __le32 cdoption; __u64 create_time; + __u64 change_time; __u64 itime; bool is_nt_open; From 9a5784f4d58b0ad772998329f0309f39b3bc1a09 Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Sun, 21 Jun 2026 19:37:22 +0900 Subject: [PATCH 172/297] ksmbd: check parent directory sharing conflicts on rename When renaming a file, some existing opens on the parent directory must block the rename with STATUS_SHARING_VIOLATION. This includes parent directory handles opened with DELETE access and handles opened without FILE_SHARE_DELETE. ksmbd checked only the parent's desired access for FILE_DELETE. That handled smb2.rename.share_delete_and_delete_access, but missed the case where the parent directory was opened without delete access and without delete sharing, so smb2.rename.no_share_delete_no_delete_access incorrectly succeeded. Attribute-only parent opens, however, must not block the rename. smb2.rename.msword opens the parent directory with only SYNCHRONIZE and FILE_READ_ATTRIBUTES, no share access, and then renames an already-open child file. Windows allows this pattern. Reject parent directory handles that request DELETE access, and reject non-attribute-only parent opens that deny FILE_SHARE_DELETE, while allowing attribute-only parent opens to coexist with child rename. Signed-off-by: Namjae Jeon Signed-off-by: Steve French --- fs/smb/server/vfs.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/fs/smb/server/vfs.c b/fs/smb/server/vfs.c index 74b0307cb100..80fd27752b2c 100644 --- a/fs/smb/server/vfs.c +++ b/fs/smb/server/vfs.c @@ -702,8 +702,10 @@ retry: parent_fp = ksmbd_lookup_fd_inode(old_child->d_parent); if (parent_fp) { - if (parent_fp->daccess & FILE_DELETE_LE) { - pr_err("parent dir is opened with delete access\n"); + if ((parent_fp->daccess & FILE_DELETE_LE) || + (!parent_fp->attrib_only && + !(parent_fp->saccess & FILE_SHARE_DELETE_LE))) { + pr_err("parent dir blocks delete sharing\n"); err = -ESHARE; ksmbd_fd_put(work, parent_fp); goto out3; From c841bd3d8dec33a000d6e31b7e7fafb22c39e4e9 Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Sun, 21 Jun 2026 19:37:56 +0900 Subject: [PATCH 173/297] ksmbd: deny renaming directory with open children Windows denies renaming a directory while a file below that directory is still open. smb2.rename.rename_dir_openfile checks this by keeping a file handle open under the directory and then attempting to rename the directory handle. ksmbd did not check open children before calling vfs_rename(), so the rename incorrectly succeeded. For non-POSIX clients, scan the global open file table for active handles whose dentries are below the directory being renamed. If any child is open, fail the rename with -EACCES so the client receives STATUS_ACCESS_DENIED. Signed-off-by: Namjae Jeon Signed-off-by: Steve French --- fs/smb/server/vfs.c | 6 ++++++ fs/smb/server/vfs_cache.c | 25 +++++++++++++++++++++++++ fs/smb/server/vfs_cache.h | 1 + 3 files changed, 32 insertions(+) diff --git a/fs/smb/server/vfs.c b/fs/smb/server/vfs.c index 80fd27752b2c..f5fa22d87603 100644 --- a/fs/smb/server/vfs.c +++ b/fs/smb/server/vfs.c @@ -700,6 +700,12 @@ retry: if (err) goto out_drop_write; + if (!work->tcon->posix_extensions && d_is_dir(old_child) && + ksmbd_has_open_files(old_child)) { + err = -EACCES; + goto out3; + } + parent_fp = ksmbd_lookup_fd_inode(old_child->d_parent); if (parent_fp) { if ((parent_fp->daccess & FILE_DELETE_LE) || diff --git a/fs/smb/server/vfs_cache.c b/fs/smb/server/vfs_cache.c index 5a2fddadcddf..98c5bac93d63 100644 --- a/fs/smb/server/vfs_cache.c +++ b/fs/smb/server/vfs_cache.c @@ -10,6 +10,7 @@ #include #include #include +#include #include "glob.h" #include "vfs_cache.h" @@ -914,6 +915,30 @@ struct ksmbd_file *ksmbd_lookup_fd_inode(struct dentry *dentry) return NULL; } +bool ksmbd_has_open_files(struct dentry *dentry) +{ + struct ksmbd_file *fp; + unsigned int id; + bool ret = false; + + read_lock(&global_ft.lock); + idr_for_each_entry(global_ft.idr, fp, id) { + struct dentry *fp_dentry = fp->filp->f_path.dentry; + + if (fp->f_state != FP_INITED) + continue; + if (fp_dentry == dentry) + continue; + if (is_subdir(fp_dentry, dentry)) { + ret = true; + break; + } + } + read_unlock(&global_ft.lock); + + return ret; +} + #define OPEN_ID_TYPE_VOLATILE_ID (0) #define OPEN_ID_TYPE_PERSISTENT_ID (1) diff --git a/fs/smb/server/vfs_cache.h b/fs/smb/server/vfs_cache.h index 8c456484cab2..52a0e8b1f79f 100644 --- a/fs/smb/server/vfs_cache.h +++ b/fs/smb/server/vfs_cache.h @@ -172,6 +172,7 @@ bool ksmbd_has_other_active_fd(struct ksmbd_file *fp); int ksmbd_close_fd_app_instance_id(char *app_instance_id); struct ksmbd_file *ksmbd_lookup_fd_cguid(char *cguid); struct ksmbd_file *ksmbd_lookup_fd_inode(struct dentry *dentry); +bool ksmbd_has_open_files(struct dentry *dentry); unsigned int ksmbd_open_durable_fd(struct ksmbd_file *fp); struct ksmbd_file *ksmbd_open_fd(struct ksmbd_work *work, struct file *filp); void ksmbd_launch_ksmbd_durable_scavenger(void); From 3f67e624e591747c2b2c9c607a76d79f7ffdcabc Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Sun, 21 Jun 2026 19:39:28 +0900 Subject: [PATCH 174/297] ksmbd: propagate failed command status in related compounds In a related compound request, later commands can refer to the file handle from an earlier command using the related FID value. If the earlier command fails without producing a valid compound FID, the later related commands must fail with the same status instead of operating on an invalid or stale handle. smb2.compound.related4 sends CREATE followed by IOCTL, CLOSE and SET_INFO. The CREATE is expected to fail with STATUS_ACCESS_DENIED, and the remaining related commands are expected to return STATUS_ACCESS_DENIED as well. ksmbd only stored the compound FID on successful CREATE and did not remember failed compound statuses. Store the failed status in the work item and make related handle-based requests fail immediately with that status only when the compound FID is invalid. Also preserve and consume the related FID across successful FLUSH, READ and WRITE requests whose responses do not carry a file id. Keep a valid compound FID across non-close failures so later related commands can continue to use the handle. When extracting the FID from a successful READ, WRITE or FLUSH request, use the request structure matching the SMB2 command: READ and WRITE place PersistentFileId and VolatileFileId at a different offset than FLUSH, so a single smb2_flush_req cast can save the wrong value as compound_fid and make the following related request fail with STATUS_FILE_CLOSED (smb2.compound_async.write_write after smb2.compound_async.flush_flush). Only update the saved compound FID when the request carries a valid volatile FID. otherwise an all-ones related FID would overwrite the CREATE FID and break smb2.compound.related6. Signed-off-by: Namjae Jeon Signed-off-by: Steve French --- fs/smb/server/ksmbd_work.h | 1 + fs/smb/server/smb2pdu.c | 159 ++++++++++++++++++++++++++++++++++++- 2 files changed, 156 insertions(+), 4 deletions(-) diff --git a/fs/smb/server/ksmbd_work.h b/fs/smb/server/ksmbd_work.h index 5368430561fb..df0554a2c50d 100644 --- a/fs/smb/server/ksmbd_work.h +++ b/fs/smb/server/ksmbd_work.h @@ -60,6 +60,7 @@ struct ksmbd_work { u64 compound_fid; u64 compound_pfid; u64 compound_sid; + __le32 compound_status; const struct cred *saved_cred; diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index f2ba52c7e325..df79533dc0a2 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -405,6 +405,59 @@ static void init_chained_smb2_rsp(struct ksmbd_work *work) work->compound_fid = ((struct smb2_create_rsp *)rsp)->VolatileFileId; work->compound_pfid = ((struct smb2_create_rsp *)rsp)->PersistentFileId; work->compound_sid = le64_to_cpu(rsp->SessionId); + work->compound_status = STATUS_SUCCESS; + } else if ((req->Command == SMB2_FLUSH || + req->Command == SMB2_READ || + req->Command == SMB2_WRITE) && + rsp->Status == STATUS_SUCCESS) { + u64 volatile_id = KSMBD_NO_FID; + u64 persistent_id = KSMBD_NO_FID; + + if (req->Command == SMB2_FLUSH) { + struct smb2_flush_req *flush_req = + (struct smb2_flush_req *)req; + + volatile_id = flush_req->VolatileFileId; + persistent_id = flush_req->PersistentFileId; + } else if (req->Command == SMB2_READ) { + struct smb2_read_req *read_req = + (struct smb2_read_req *)req; + + volatile_id = read_req->VolatileFileId; + persistent_id = read_req->PersistentFileId; + } else { + struct smb2_write_req *write_req = + (struct smb2_write_req *)req; + + volatile_id = write_req->VolatileFileId; + persistent_id = write_req->PersistentFileId; + } + + if (has_file_id(volatile_id)) { + work->compound_fid = volatile_id; + work->compound_pfid = persistent_id; + work->compound_sid = le64_to_cpu(rsp->SessionId); + work->compound_status = STATUS_SUCCESS; + } + } else if (req->Command == SMB2_CREATE) { + work->compound_fid = KSMBD_NO_FID; + work->compound_pfid = KSMBD_NO_FID; + work->compound_sid = le64_to_cpu(rsp->SessionId); + work->compound_status = rsp->Status; + } else if (rsp->Status != STATUS_SUCCESS) { + work->compound_sid = le64_to_cpu(rsp->SessionId); + /* + * Only carry the failed status forward when the failing command + * was itself part of the related chain. An unrelated command + * that fails (e.g. a standalone request with a bad session id) + * must not seed the status for a following related command, + * which has to be evaluated on its own (and may legitimately + * fail with a different status such as INVALID_PARAMETER). The + * compound session id is still tracked so a following related + * command can validate it. + */ + if (req->Flags & SMB2_FLAGS_RELATED_OPERATIONS) + work->compound_status = rsp->Status; } len = get_rfc1002_len(work->response_buf) - work->next_smb2_rsp_hdr_off; @@ -430,6 +483,7 @@ static void init_chained_smb2_rsp(struct ksmbd_work *work) ksmbd_debug(SMB, "related flag should be set\n"); work->compound_fid = KSMBD_NO_FID; work->compound_pfid = KSMBD_NO_FID; + work->compound_status = STATUS_SUCCESS; } memset((char *)rsp_hdr, 0, sizeof(struct smb2_hdr) + 2); rsp_hdr->ProtocolId = SMB2_PROTO_NUMBER; @@ -449,6 +503,19 @@ static void init_chained_smb2_rsp(struct ksmbd_work *work) memcpy(rsp_hdr->Signature, rcv_hdr->Signature, 16); } +static bool smb2_compound_has_failed(struct ksmbd_work *work, + struct smb2_hdr *rsp) +{ + if (!work->next_smb2_rcv_hdr_off || + has_file_id(work->compound_fid) || + work->compound_status == STATUS_SUCCESS) + return false; + + rsp->Status = work->compound_status; + smb2_set_err_rsp(work); + return true; +} + /** * is_chained_smb2_message() - check for chained command * @work: smb work containing smb request buffer @@ -4608,11 +4675,28 @@ int smb2_query_dir(struct ksmbd_work *work) unsigned char srch_flag; int buffer_sz; struct smb2_query_dir_private query_dir_private = {NULL, }; + unsigned int id = KSMBD_NO_FID, pid = KSMBD_NO_FID; ksmbd_debug(SMB, "Received smb2 query directory request\n"); WORK_BUFFERS(work, req, rsp); + if (smb2_compound_has_failed(work, &rsp->hdr)) + return -EACCES; + + if (work->next_smb2_rcv_hdr_off && + !has_file_id(req->VolatileFileId)) { + ksmbd_debug(SMB, "Compound request set FID = %llu\n", + work->compound_fid); + id = work->compound_fid; + pid = work->compound_pfid; + } + + if (!has_file_id(id)) { + id = req->VolatileFileId; + pid = req->PersistentFileId; + } + if (ksmbd_override_fsids(work)) { rsp->hdr.Status = STATUS_NO_MEMORY; smb2_set_err_rsp(work); @@ -4625,7 +4709,7 @@ int smb2_query_dir(struct ksmbd_work *work) goto err_out2; } - dir_fp = ksmbd_lookup_fd_slow(work, req->VolatileFileId, req->PersistentFileId); + dir_fp = ksmbd_lookup_fd_slow(work, id, pid); if (!dir_fp) { rc = -EBADF; goto err_out2; @@ -6088,6 +6172,9 @@ int smb2_query_info(struct ksmbd_work *work) WORK_BUFFERS(work, req, rsp); + if (smb2_compound_has_failed(work, &rsp->hdr)) + return -EACCES; + if (ksmbd_override_fsids(work)) { rc = -ENOMEM; goto err_out; @@ -6192,6 +6279,9 @@ int smb2_close(struct ksmbd_work *work) WORK_BUFFERS(work, req, rsp); + if (smb2_compound_has_failed(work, &rsp->hdr)) + return -EACCES; + if (test_share_config_flag(work->tcon->share_conf, KSMBD_SHARE_FLAG_PIPE)) { ksmbd_debug(SMB, "IPC pipe close request\n"); @@ -6862,6 +6952,8 @@ int smb2_set_info(struct ksmbd_work *work) if (work->next_smb2_rcv_hdr_off) { req = ksmbd_req_buf_next(work); rsp = ksmbd_resp_buf_next(work); + if (smb2_compound_has_failed(work, &rsp->hdr)) + return -EACCES; if (!has_file_id(req->VolatileFileId)) { ksmbd_debug(SMB, "Compound request set FID = %llu\n", work->compound_fid); @@ -7093,6 +7185,8 @@ int smb2_read(struct ksmbd_work *work) if (work->next_smb2_rcv_hdr_off) { req = ksmbd_req_buf_next(work); rsp = ksmbd_resp_buf_next(work); + if (smb2_compound_has_failed(work, &rsp->hdr)) + return -EACCES; if (!has_file_id(req->VolatileFileId)) { ksmbd_debug(SMB, "Compound request set FID = %llu\n", work->compound_fid); @@ -7366,11 +7460,28 @@ int smb2_write(struct ksmbd_work *work) bool writethrough = false, is_rdma_channel = false; int err = 0; unsigned int max_write_size = work->conn->vals->max_write_size; + unsigned int id = KSMBD_NO_FID, pid = KSMBD_NO_FID; ksmbd_debug(SMB, "Received smb2 write request\n"); WORK_BUFFERS(work, req, rsp); + if (smb2_compound_has_failed(work, &rsp->hdr)) + return -EACCES; + + if (work->next_smb2_rcv_hdr_off && + !has_file_id(req->VolatileFileId)) { + ksmbd_debug(SMB, "Compound request set FID = %llu\n", + work->compound_fid); + id = work->compound_fid; + pid = work->compound_pfid; + } + + if (!has_file_id(id)) { + id = req->VolatileFileId; + pid = req->PersistentFileId; + } + if (test_share_config_flag(work->tcon->share_conf, KSMBD_SHARE_FLAG_PIPE)) { ksmbd_debug(SMB, "IPC pipe write request\n"); return smb2_write_pipe(work); @@ -7415,7 +7526,7 @@ int smb2_write(struct ksmbd_work *work) goto out; } - fp = ksmbd_lookup_fd_slow(work, req->VolatileFileId, req->PersistentFileId); + fp = ksmbd_lookup_fd_slow(work, id, pid); if (!fp) { err = -ENOENT; goto out; @@ -7509,13 +7620,30 @@ int smb2_flush(struct ksmbd_work *work) { struct smb2_flush_req *req; struct smb2_flush_rsp *rsp; + u64 id = KSMBD_NO_FID, pid = KSMBD_NO_FID; int err; WORK_BUFFERS(work, req, rsp); ksmbd_debug(SMB, "Received smb2 flush request(fid : %llu)\n", req->VolatileFileId); - err = ksmbd_vfs_fsync(work, req->VolatileFileId, req->PersistentFileId); + if (smb2_compound_has_failed(work, &rsp->hdr)) + return -EACCES; + + if (work->next_smb2_rcv_hdr_off && + !has_file_id(req->VolatileFileId)) { + ksmbd_debug(SMB, "Compound request set FID = %llu\n", + work->compound_fid); + id = work->compound_fid; + pid = work->compound_pfid; + } + + if (!has_file_id(id)) { + id = req->VolatileFileId; + pid = req->PersistentFileId; + } + + err = ksmbd_vfs_fsync(work, id, pid); if (err) goto out; @@ -7734,11 +7862,29 @@ int smb2_lock(struct ksmbd_work *work) LIST_HEAD(lock_list); LIST_HEAD(rollback_list); int prior_lock = 0, bkt; + unsigned int id = KSMBD_NO_FID, pid = KSMBD_NO_FID; WORK_BUFFERS(work, req, rsp); ksmbd_debug(SMB, "Received smb2 lock request\n"); - fp = ksmbd_lookup_fd_slow(work, req->VolatileFileId, req->PersistentFileId); + + if (smb2_compound_has_failed(work, &rsp->hdr)) + return -EACCES; + + if (work->next_smb2_rcv_hdr_off && + !has_file_id(req->VolatileFileId)) { + ksmbd_debug(SMB, "Compound request set FID = %llu\n", + work->compound_fid); + id = work->compound_fid; + pid = work->compound_pfid; + } + + if (!has_file_id(id)) { + id = req->VolatileFileId; + pid = req->PersistentFileId; + } + + fp = ksmbd_lookup_fd_slow(work, id, pid); if (!fp) { ksmbd_debug(SMB, "Invalid file id for lock : %llu\n", req->VolatileFileId); err = -ENOENT; @@ -8544,6 +8690,8 @@ int smb2_ioctl(struct ksmbd_work *work) if (work->next_smb2_rcv_hdr_off) { req = ksmbd_req_buf_next(work); rsp = ksmbd_resp_buf_next(work); + if (smb2_compound_has_failed(work, &rsp->hdr)) + return -EACCES; if (!has_file_id(req->VolatileFileId)) { ksmbd_debug(SMB, "Compound request set FID = %llu\n", work->compound_fid); @@ -9208,6 +9356,9 @@ int smb2_notify(struct ksmbd_work *work) WORK_BUFFERS(work, req, rsp); + if (smb2_compound_has_failed(work, &rsp->hdr)) + return -EACCES; + if (work->next_smb2_rcv_hdr_off && req->hdr.NextCommand) { rsp->hdr.Status = STATUS_INTERNAL_ERROR; smb2_set_err_rsp(work); From 7d258465ea49d82668f52de96f3f0c84727003e4 Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Sun, 21 Jun 2026 19:39:59 +0900 Subject: [PATCH 175/297] ksmbd: validate handle for create or get object id FSCTL_CREATE_OR_GET_OBJECT_ID returned a dummy successful response without checking whether the request handle was valid. That let an invalid related compound handle succeed in smb2.compound.related5, although the client expected STATUS_FILE_CLOSED. Look up the file handle before building the object id response and fail with STATUS_FILE_CLOSED when the handle is invalid or already closed. Signed-off-by: Namjae Jeon Signed-off-by: Steve French --- fs/smb/server/smb2pdu.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index df79533dc0a2..d3bd198ec938 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -8789,6 +8789,15 @@ int smb2_ioctl(struct ksmbd_work *work) case FSCTL_CREATE_OR_GET_OBJECT_ID: { struct file_object_buf_type1_ioctl_rsp *obj_buf; + struct ksmbd_file *fp; + + fp = ksmbd_lookup_fd_fast(work, id); + if (!fp) { + ret = -EBADF; + rsp->hdr.Status = STATUS_FILE_CLOSED; + goto out2; + } + ksmbd_fd_put(work, fp); nbytes = sizeof(struct file_object_buf_type1_ioctl_rsp); obj_buf = (struct file_object_buf_type1_ioctl_rsp *) From e50a07437a9ef5a3b2efe414643e2cdcb6b2e644 Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Sun, 21 Jun 2026 19:40:37 +0900 Subject: [PATCH 176/297] ksmbd: preserve compound responses for chained errors set_smb2_rsp_status() resets the response iov and compound offsets before building an error response. That is fine for a single request, but it corrupts a compound response when an error is detected after an earlier compound element has already been completed. smb2.compound.invalid4 sends a READ as the first compound element and a bogus command as the second one. The READ response must remain in the compound response with STATUS_END_OF_FILE, followed by the bogus command response with STATUS_INVALID_PARAMETER. Resetting the response state for the second command breaks the compound framing and the client reports NT_STATUS_INVALID_NETWORK_RESPONSE. When setting an error for a chained command, update and pin only the current compound response slot instead of resetting the whole response. Signed-off-by: Namjae Jeon Signed-off-by: Steve French --- fs/smb/server/smb2pdu.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index d3bd198ec938..35f23b427bd1 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -246,6 +246,13 @@ void set_smb2_rsp_status(struct ksmbd_work *work, __le32 err) { struct smb2_hdr *rsp_hdr; + if (work->next_smb2_rcv_hdr_off) { + rsp_hdr = ksmbd_resp_buf_next(work); + rsp_hdr->Status = err; + smb2_set_err_rsp(work); + return; + } + rsp_hdr = smb_get_msg(work->response_buf); rsp_hdr->Status = err; From c5db4de8988f1a621556ca5c4537f77b766ca07d Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Sun, 21 Jun 2026 19:41:08 +0900 Subject: [PATCH 177/297] ksmbd: return success for deferred final close ksmbd_close_fd() marks an open file as FP_CLOSED and drops the file table reference. If another in-flight request still holds a reference, the final close is deferred until that request drops its reference. The function currently returns -EINVAL in that deferred-final-close case because fp is cleared when the reference count does not reach zero. That turns a valid close into STATUS_FILE_CLOSED. smb2.compound_find.compound_find_close sends QUERY_DIRECTORY and then closes the same directory handle before receiving the find response. The query holds a reference while it builds the response, so close must mark the handle closed and return success even though final teardown is delayed. Track whether the handle was successfully transitioned to FP_CLOSED and return success when only the final close is deferred. Signed-off-by: Namjae Jeon Signed-off-by: Steve French --- fs/smb/server/vfs_cache.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/fs/smb/server/vfs_cache.c b/fs/smb/server/vfs_cache.c index 98c5bac93d63..b617edef950a 100644 --- a/fs/smb/server/vfs_cache.c +++ b/fs/smb/server/vfs_cache.c @@ -640,6 +640,7 @@ int ksmbd_close_fd(struct ksmbd_work *work, u64 id) { struct ksmbd_file *fp; struct ksmbd_file_table *ft; + bool closed = false; if (!has_file_id(id)) return 0; @@ -654,6 +655,7 @@ int ksmbd_close_fd(struct ksmbd_work *work, u64 id) fp = NULL; else { fp->f_state = FP_CLOSED; + closed = true; if (!atomic_dec_and_test(&fp->refcount)) fp = NULL; } @@ -661,7 +663,7 @@ int ksmbd_close_fd(struct ksmbd_work *work, u64 id) write_unlock(&ft->lock); if (!fp) - return -EINVAL; + return closed ? 0 : -EINVAL; __put_fd_final(work, fp); return 0; From affcd98fddc57d81648d8ede8546d31e4a3f8450 Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Sun, 21 Jun 2026 19:43:35 +0900 Subject: [PATCH 178/297] ksmbd: send pending interim for last compound I/O smb2.compound_async.write_write and smb2.compound_async.read_read expect the last I/O request in a compound request to become cancellable before its final response is received. smb clients mark a request cancellable after receiving an interim STATUS_PENDING response. ksmbd handled the last READ/WRITE synchronously and returned the final response directly, so the client never observed STATUS_PENDING and req->cancel.can_cancel remained false. For the last READ or WRITE in a compound request, register the work briefly as async and send a STATUS_PENDING interim response before continuing with the normal synchronous completion. The final READ/WRITE response remains unchanged. Signed-off-by: Namjae Jeon Signed-off-by: Steve French --- fs/smb/server/smb2pdu.c | 30 +++++++++++++++++++++++++++++- 1 file changed, 29 insertions(+), 1 deletion(-) diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index 35f23b427bd1..cc9cd9297557 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -7176,7 +7176,7 @@ int smb2_read(struct ksmbd_work *work) size_t length, mincount; ssize_t nbytes = 0, remain_bytes = 0; int err = 0; - bool is_rdma_channel = false; + bool is_rdma_channel = false, async_interim = false; unsigned int max_read_size = conn->vals->max_read_size; unsigned int id = KSMBD_NO_FID, pid = KSMBD_NO_FID; void *aux_payload_buf; @@ -7248,6 +7248,14 @@ int smb2_read(struct ksmbd_work *work) goto out; } + if (work->next_smb2_rcv_hdr_off && !req->hdr.NextCommand) { + err = setup_async_work(work, NULL, NULL); + if (err) + goto out; + smb2_send_interim_resp(work, STATUS_PENDING); + async_interim = true; + } + offset = le64_to_cpu(req->Offset); if (offset < 0) { err = -EINVAL; @@ -7283,6 +7291,8 @@ int smb2_read(struct ksmbd_work *work) kvfree(aux_payload_buf); rsp->hdr.Status = STATUS_END_OF_FILE; smb2_set_err_rsp(work); + if (async_interim) + release_async_work(work); ksmbd_fd_put(work, fp); return -ENODATA; } @@ -7317,6 +7327,8 @@ int smb2_read(struct ksmbd_work *work) kvfree(aux_payload_buf); goto out; } + if (async_interim) + release_async_work(work); /* * RDMA responses are transferred through channel buffers and encrypted * responses use the encryption transform, so only normal SMB transport @@ -7330,6 +7342,8 @@ int smb2_read(struct ksmbd_work *work) return 0; out: + if (async_interim) + release_async_work(work); if (err) { if (err == -EISDIR) rsp->hdr.Status = STATUS_INVALID_DEVICE_REQUEST; @@ -7465,6 +7479,7 @@ int smb2_write(struct ksmbd_work *work) ssize_t nbytes; char *data_buf; bool writethrough = false, is_rdma_channel = false; + bool async_interim = false; int err = 0; unsigned int max_write_size = work->conn->vals->max_write_size; unsigned int id = KSMBD_NO_FID, pid = KSMBD_NO_FID; @@ -7545,6 +7560,14 @@ int smb2_write(struct ksmbd_work *work) goto out; } + if (work->next_smb2_rcv_hdr_off && !req->hdr.NextCommand) { + err = setup_async_work(work, NULL, NULL); + if (err) + goto out; + smb2_send_interim_resp(work, STATUS_PENDING); + async_interim = true; + } + if (length > max_write_size) { ksmbd_debug(SMB, "limiting write size to max size(%u)\n", max_write_size); @@ -7593,10 +7616,15 @@ int smb2_write(struct ksmbd_work *work) err = ksmbd_iov_pin_rsp(work, rsp, offsetof(struct smb2_write_rsp, Buffer)); if (err) goto out; + if (async_interim) + release_async_work(work); ksmbd_fd_put(work, fp); return 0; out: + if (async_interim) + release_async_work(work); + if (err == -EAGAIN) rsp->hdr.Status = STATUS_FILE_LOCK_CONFLICT; else if (err == -ENOSPC || err == -EFBIG) From 19043971c947d307c9fc76e8b5e750ce7140b486 Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Sun, 21 Jun 2026 19:44:09 +0900 Subject: [PATCH 179/297] ksmbd: honor stream delete sharing for base file smb2.streams.delete opens an alternate data stream without FILE_SHARE_DELETE and then tries to delete the base file. Windows rejects the base-file delete with STATUS_SHARING_VIOLATION while the stream handle is open. ksmbd tracks stream opens on the same ksmbd_inode as the base file, but the delete-on-close path only checked delete access on the base handle before marking the inode delete-pending. As a result, deleting the base file succeeded even though an open stream handle denied delete sharing. Add a helper to detect open stream handles on the same inode that do not allow FILE_SHARE_DELETE, and reject base-file delete pending and DELETE opens with a sharing violation in that case. Signed-off-by: Namjae Jeon Signed-off-by: Steve French --- fs/smb/server/smb2pdu.c | 9 +++++++++ fs/smb/server/vfs_cache.c | 27 +++++++++++++++++++++++++++ fs/smb/server/vfs_cache.h | 1 + 3 files changed, 37 insertions(+) diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index cc9cd9297557..a3ae37e8b24d 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -3737,6 +3737,12 @@ int smb2_open(struct ksmbd_work *work) goto err_out; } + if (!stream_name && daccess & FILE_DELETE_LE && + ksmbd_has_stream_without_delete_share(fp)) { + rc = -EPERM; + goto err_out; + } + if (file_present || created) path_put(&path); @@ -6758,6 +6764,9 @@ static int set_file_disposition_info(struct ksmbd_work *work, inode = file_inode(fp->filp); if (file_info->DeletePending) { + if (ksmbd_has_stream_without_delete_share(fp)) + return -ESHARE; + if (S_ISDIR(inode->i_mode) && ksmbd_vfs_empty_dir(fp) == -ENOTEMPTY) return -EBUSY; diff --git a/fs/smb/server/vfs_cache.c b/fs/smb/server/vfs_cache.c index b617edef950a..11b51320b96e 100644 --- a/fs/smb/server/vfs_cache.c +++ b/fs/smb/server/vfs_cache.c @@ -254,6 +254,33 @@ void ksmbd_clear_inode_pending_delete(struct ksmbd_file *fp) up_write(&ci->m_lock); } +bool ksmbd_has_stream_without_delete_share(struct ksmbd_file *fp) +{ + struct ksmbd_file *prev_fp; + struct ksmbd_inode *ci = fp->f_ci; + bool ret = false; + + if (ksmbd_stream_fd(fp)) + return false; + + down_read(&ci->m_lock); + list_for_each_entry(prev_fp, &ci->m_fp_list, node) { + if (prev_fp == fp || !ksmbd_stream_fd(prev_fp)) + continue; + + if (file_inode(fp->filp) != file_inode(prev_fp->filp)) + continue; + + if (!(prev_fp->saccess & FILE_SHARE_DELETE_LE)) { + ret = true; + break; + } + } + up_read(&ci->m_lock); + + return ret; +} + void ksmbd_fd_set_delete_on_close(struct ksmbd_file *fp, int file_info) { diff --git a/fs/smb/server/vfs_cache.h b/fs/smb/server/vfs_cache.h index 52a0e8b1f79f..8aa87843025f 100644 --- a/fs/smb/server/vfs_cache.h +++ b/fs/smb/server/vfs_cache.h @@ -169,6 +169,7 @@ struct ksmbd_file *ksmbd_lookup_durable_fd(unsigned long long id); void ksmbd_put_durable_fd(struct ksmbd_file *fp); int ksmbd_invalidate_durable_fd(unsigned long long id); bool ksmbd_has_other_active_fd(struct ksmbd_file *fp); +bool ksmbd_has_stream_without_delete_share(struct ksmbd_file *fp); int ksmbd_close_fd_app_instance_id(char *app_instance_id); struct ksmbd_file *ksmbd_lookup_fd_cguid(char *cguid); struct ksmbd_file *ksmbd_lookup_fd_inode(struct dentry *dentry); From 4687da7b28cff019a61d802afac44e2bf92edb98 Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Sun, 21 Jun 2026 19:44:40 +0900 Subject: [PATCH 180/297] ksmbd: reject empty-attribute synchronize-only create smb2.create.gentest checks each desired access bit independently and expects an open that requests only SYNCHRONIZE with CreateDisposition OPEN_IF and FileAttributes 0 to fail with STATUS_ACCESS_DENIED. Rejecting all SYNCHRONIZE-only opens is too broad: SYNCHRONIZE does not imply read, write, or delete data access, and smb2.sharemode.sharemode-access expects a SYNCHRONIZE-only open to succeed when it does not conflict with the existing share mode. Limit the rejection to the gentest create shape: SYNCHRONIZE-only access, OPEN_IF disposition, and no file attributes. Other synchronize-only opens are handled by the normal permission and share-mode checks. Signed-off-by: Namjae Jeon Signed-off-by: Steve French --- fs/smb/server/smb2pdu.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index a3ae37e8b24d..9a1308f32f45 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -3332,6 +3332,13 @@ int smb2_open(struct ksmbd_work *work) goto err_out2; } + if (req->DesiredAccess == FILE_SYNCHRONIZE_LE && + req->CreateDisposition == FILE_OPEN_IF_LE && + !req->FileAttributes) { + rc = -EACCES; + goto err_out2; + } + if (req->FileAttributes && !(req->FileAttributes & FILE_ATTRIBUTE_MASK_LE)) { pr_err("Invalid file attribute : 0x%x\n", le32_to_cpu(req->FileAttributes)); From 0984b1f058fe1f501a04dea2c97897735be1d9f4 Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Sun, 21 Jun 2026 19:45:07 +0900 Subject: [PATCH 181/297] ksmbd: tighten create file attribute validation smb2.create.gentest checks each create FileAttributes bit independently and expects FILE_ATTRIBUTE_INTEGRITY_STREAM and FILE_ATTRIBUTE_NO_SCRUB_DATA to be rejected with STATUS_INVALID_PARAMETER. ksmbd validates create FileAttributes against FILE_ATTRIBUTE_MASK, which includes those bits. It also rejects only requests that have no known attribute bit at all, so a request containing both known and unknown bits can pass validation. Use a create-specific attribute mask that excludes INTEGRITY_STREAM and NO_SCRUB_DATA, and reject any bit outside that mask. Signed-off-by: Namjae Jeon Signed-off-by: Steve French --- fs/smb/server/smb2pdu.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index 9a1308f32f45..d6001cdce085 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -57,6 +57,10 @@ static void __wbuf(struct ksmbd_work *work, void **req, void **rsp) #define WORK_BUFFERS(w, rq, rs) __wbuf((w), (void **)&(rq), (void **)&(rs)) +#define SMB2_CREATE_FILE_ATTRIBUTE_MASK \ + (FILE_ATTRIBUTE_MASK & ~(FILE_ATTRIBUTE_INTEGRITY_STREAM | \ + FILE_ATTRIBUTE_NO_SCRUB_DATA)) + /** * check_session_id() - check for valid session id in smb header * @conn: connection instance @@ -3339,7 +3343,8 @@ int smb2_open(struct ksmbd_work *work) goto err_out2; } - if (req->FileAttributes && !(req->FileAttributes & FILE_ATTRIBUTE_MASK_LE)) { + if (req->FileAttributes && + (req->FileAttributes & ~cpu_to_le32(SMB2_CREATE_FILE_ATTRIBUTE_MASK))) { pr_err("Invalid file attribute : 0x%x\n", le32_to_cpu(req->FileAttributes)); rc = -EINVAL; From 3b41d8b05dc89b1f3c53ca7f1a084c7c93712ebf Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Sun, 21 Jun 2026 19:47:02 +0900 Subject: [PATCH 182/297] ksmbd: return requested create allocation size smb2.create.blob sends an SMB2_CREATE_ALLOCATION_SIZE create context with a 1MiB allocation size and expects the create response AllocationSize field to match the requested size. smb2.create.open additionally compares the AllocationSize returned in the CREATE response with the AllocationSize returned by FILE_ALL_INFORMATION on the same handle. ksmbd applies the allocation with fallocate(), but then fills both the create response and handle-based information from stat.blocks << 9. On filesystems such as ext4 this can include filesystem allocation rounding and metadata effects, causing a response larger than the SMB2 allocation size context and a disagreement between the two queries. Remember the requested allocation size while processing the create context, store the reported allocation size in struct ksmbd_file, and use it for both the create response and handle-based allocation size responses. Update the stored value when FILE_ALLOCATION_INFORMATION changes it, and fall back to stat.blocks << 9 when no allocation size context was provided. Signed-off-by: Namjae Jeon Signed-off-by: Steve French --- fs/smb/server/smb2pdu.c | 34 +++++++++++++++++++++++----------- fs/smb/server/vfs_cache.h | 1 + 2 files changed, 24 insertions(+), 11 deletions(-) diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index d6001cdce085..68d761690002 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -3133,7 +3133,7 @@ int smb2_open(struct ksmbd_work *work) char *stream_name = NULL; bool file_present = false, created = false, already_permitted = false; int share_ret, need_truncate = 0; - u64 time; + u64 time, alloc_size = 0; umode_t posix_mode = 0; __le32 daccess, maximal_access = 0; int iov_len = 0; @@ -3826,7 +3826,6 @@ int smb2_open(struct ksmbd_work *work) rc = PTR_ERR(az_req); goto err_out1; } else if (az_req) { - loff_t alloc_size; int err; if (le16_to_cpu(az_req->ccontext.DataOffset) + @@ -3876,6 +3875,8 @@ int smb2_open(struct ksmbd_work *work) else fp->create_time = ksmbd_UnixTimeToNT(stat.ctime); fp->change_time = ksmbd_UnixTimeToNT(stat.ctime); + fp->allocation_size = S_ISDIR(stat.mode) ? 0 : + (alloc_size ?: stat.blocks << 9); if (req->FileAttributes || fp->f_ci->m_fattr == 0) fp->f_ci->m_fattr = cpu_to_le32(smb2_get_dos_mode(&stat, le32_to_cpu(req->FileAttributes))); @@ -3926,8 +3927,19 @@ reconnected_fp: time = ksmbd_UnixTimeToNT(stat.mtime); rsp->LastWriteTime = cpu_to_le64(time); rsp->ChangeTime = cpu_to_le64(fp->change_time); - rsp->AllocationSize = S_ISDIR(stat.mode) ? 0 : - cpu_to_le64(stat.blocks << 9); + /* + * The cached allocation size hides filesystem rounding for the + * requested allocation, but it can go stale when the file grows past + * it via writes (e.g. across a durable reconnect). Refresh it once the + * file exceeds the cached value, rounding the end of file up to the + * volume allocation unit (the filesystem block size, matching the + * SectorsPerAllocationUnit/BytesPerSector ksmbd advertises) rather than + * using the raw on-disk block count, which can include filesystem + * preallocation and metadata rounding. + */ + if (!S_ISDIR(stat.mode) && stat.size > fp->allocation_size) + fp->allocation_size = round_up(stat.size, stat.blksize); + rsp->AllocationSize = cpu_to_le64(fp->allocation_size); rsp->EndofFile = S_ISDIR(stat.mode) ? 0 : cpu_to_le64(stat.size); rsp->FileAttributes = fp->f_ci->m_fattr; @@ -5236,7 +5248,7 @@ static int get_file_standard_info(struct smb2_query_info_rsp *rsp, delete_pending = ksmbd_inode_pending_delete(fp); if (ksmbd_stream_fd(fp) == false) { - sinfo->AllocationSize = cpu_to_le64(stat.blocks << 9); + sinfo->AllocationSize = cpu_to_le64(fp->allocation_size); sinfo->EndOfFile = S_ISDIR(stat.mode) ? 0 : cpu_to_le64(stat.size); } else { sinfo->AllocationSize = cpu_to_le64(fp->stream.size); @@ -5317,8 +5329,7 @@ static int get_file_all_info(struct ksmbd_work *work, file_info->Attributes = fp->f_ci->m_fattr; file_info->Pad1 = 0; if (ksmbd_stream_fd(fp) == false) { - file_info->AllocationSize = - cpu_to_le64(stat.blocks << 9); + file_info->AllocationSize = cpu_to_le64(fp->allocation_size); file_info->EndOfFile = S_ISDIR(stat.mode) ? 0 : cpu_to_le64(stat.size); } else { file_info->AllocationSize = cpu_to_le64(fp->stream.size); @@ -5525,7 +5536,7 @@ static int get_file_network_open_info(struct smb2_query_info_rsp *rsp, file_info->ChangeTime = cpu_to_le64(fp->change_time); file_info->Attributes = fp->f_ci->m_fattr; if (ksmbd_stream_fd(fp) == false) { - file_info->AllocationSize = cpu_to_le64(stat.blocks << 9); + file_info->AllocationSize = cpu_to_le64(fp->allocation_size); file_info->EndOfFile = S_ISDIR(stat.mode) ? 0 : cpu_to_le64(stat.size); } else { file_info->AllocationSize = cpu_to_le64(fp->stream.size); @@ -5658,7 +5669,7 @@ static int find_file_posix_info(struct smb2_query_info_rsp *rsp, file_info->Inode = cpu_to_le64(stat.ino); if (ksmbd_stream_fd(fp) == false) { file_info->EndOfFile = cpu_to_le64(stat.size); - file_info->AllocationSize = cpu_to_le64(stat.blocks << 9); + file_info->AllocationSize = cpu_to_le64(fp->allocation_size); } else { file_info->EndOfFile = cpu_to_le64(fp->stream.size); file_info->AllocationSize = cpu_to_le64(fp->stream.size); @@ -6373,8 +6384,7 @@ int smb2_close(struct ksmbd_work *work) } rsp->Flags = SMB2_CLOSE_FLAG_POSTQUERY_ATTRIB; - rsp->AllocationSize = S_ISDIR(stat.mode) ? 0 : - cpu_to_le64(stat.blocks << 9); + rsp->AllocationSize = cpu_to_le64(fp->allocation_size); rsp->EndOfFile = cpu_to_le64(stat.size); rsp->Attributes = fp->f_ci->m_fattr; rsp->CreationTime = cpu_to_le64(fp->create_time); @@ -6707,6 +6717,8 @@ static int set_file_allocation_info(struct ksmbd_work *work, if (size < alloc_blks * 512) i_size_write(inode, size); } + + fp->allocation_size = le64_to_cpu(file_alloc_info->AllocationSize); return 0; } diff --git a/fs/smb/server/vfs_cache.h b/fs/smb/server/vfs_cache.h index 8aa87843025f..f85021c11d6e 100644 --- a/fs/smb/server/vfs_cache.h +++ b/fs/smb/server/vfs_cache.h @@ -98,6 +98,7 @@ struct ksmbd_file { __le32 cdoption; __u64 create_time; __u64 change_time; + __u64 allocation_size; __u64 itime; bool is_nt_open; From ba3cf6ee4f0eacc1f8c607b80188e3b32ef5e0e3 Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Sun, 21 Jun 2026 19:47:56 +0900 Subject: [PATCH 183/297] ksmbd: apply create security descriptor first smb2.create.aclfile creates files with an SMB2_CREATE_SD_BUFFER create context and expects the resulting security descriptor to match the descriptor supplied by the client. ksmbd currently tries to inherit the parent DACL first and only parses the SMB2_CREATE_SD_BUFFER context when DACL inheritance fails. If inheritance succeeds, the explicit security descriptor supplied on create is ignored. This breaks create requests that include owner/group information in the security descriptor. Apply the create security descriptor first when the context is present. Fall back to the existing inherited/default ACL path only when no create security descriptor was supplied. Signed-off-by: Namjae Jeon Signed-off-by: Steve French --- fs/smb/server/smb2pdu.c | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index 68d761690002..6b84a8ea5b15 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -3651,14 +3651,16 @@ int smb2_open(struct ksmbd_work *work) if (posix_acl_rc) ksmbd_debug(SMB, "inherit posix acl failed : %d\n", posix_acl_rc); - if (test_share_config_flag(work->tcon->share_conf, - KSMBD_SHARE_FLAG_ACL_XATTR)) { - rc = smb_inherit_dacl(conn, &path, sess->user->uid, - sess->user->gid); - } + rc = smb2_create_sd_buffer(work, req, &path); + if (rc && rc != -ENOENT) + goto err_out; - if (rc) { - rc = smb2_create_sd_buffer(work, req, &path); + if (rc == -ENOENT) { + if (test_share_config_flag(work->tcon->share_conf, + KSMBD_SHARE_FLAG_ACL_XATTR)) { + rc = smb_inherit_dacl(conn, &path, sess->user->uid, + sess->user->gid); + } if (rc) { if (posix_acl_rc) ksmbd_vfs_set_init_posix_acl(idmap, From 7db0da9915fdfd40156d01f20faac08f040fcfa3 Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Sun, 21 Jun 2026 19:48:27 +0900 Subject: [PATCH 184/297] ksmbd: downgrade oplock after break timeout smb2.oplock.batch22a opens a file with a batch oplock and then issues a second open that waits for the oplock break timeout. After the timeout the second open should succeed, but the granted oplock level must be level II. When the break times out, oplock_break() returns -ENOENT after invalidating the previous opener. smb_grant_oplock() went straight to set_lev with the original requested oplock level, so the second open could be granted a new batch oplock. Downgrade the requested oplock to level II on the -ENOENT break-timeout path before granting the oplock to the new open. A break that completes because the previous owner closed its handle from the oplock break handler must be distinguished from a real timeout. smb2.oplock.batch7 closes the first handle during the break wait, and the second open is then expected to be granted the originally requested batch oplock. Return -EAGAIN from the non-lease break path when the previous opener closed during the break wait, recheck sharing in smb_grant_oplock(), and grant the requested oplock if the close removed the conflict. Real break timeouts still return -ENOENT and keep the downgrade to level II. Signed-off-by: Namjae Jeon Signed-off-by: Steve French --- fs/smb/server/oplock.c | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-) diff --git a/fs/smb/server/oplock.c b/fs/smb/server/oplock.c index 0fddbaa5ba63..3f35ee7f7d00 100644 --- a/fs/smb/server/oplock.c +++ b/fs/smb/server/oplock.c @@ -1130,7 +1130,7 @@ again: ksmbd_debug(OPLOCK, "oplock granted = %d\n", brk_opinfo->level); if (brk_opinfo->op_state == OPLOCK_CLOSING) - err = -ENOENT; + err = -EAGAIN; wake_up_oplock_break(brk_opinfo); return err; @@ -1434,8 +1434,19 @@ int smb_grant_oplock(struct ksmbd_work *work, int req_op_level, u64 pid, if (prev_durable_detached || (prev_durable_open && err == -ENOENT)) ksmbd_invalidate_durable_fd(prev_fid); opinfo_put(prev_opinfo); - if (err == -ENOENT) + if (err == -EAGAIN) { + share_ret = ksmbd_smb_check_shared_mode(fp->filp, fp); + if (share_ret < 0) { + err = share_ret; + goto err_out; + } goto set_lev; + } + if (err == -ENOENT) { + if (req_op_level != SMB2_OPLOCK_LEVEL_NONE) + req_op_level = SMB2_OPLOCK_LEVEL_II; + goto set_lev; + } /* Check all oplock was freed by close */ else if (err < 0) goto err_out; From ec476c2580050ea050c562eeeb508519fc69ea21 Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Sun, 21 Jun 2026 19:49:05 +0900 Subject: [PATCH 185/297] ksmbd: avoid level II oplock break notification on unlink smb2_util_unlink() opens the target with FILE_DELETE_ON_CLOSE and then closes that handle. Other clients can also mark a file for delete with SMB2 SET_INFO FileDispositionInformation. When these unlink paths break existing SMB2 level II oplocks, ksmbd sends an unsolicited SMB2_OPLOCK_BREAK notification to none. This races with the synchronous CREATE or SET_INFO response expected by the client, and smbtorture reports NT_STATUS_INVALID_NETWORK_RESPONSE while running smb2.oplock.exclusive2. SMB2 level II oplock breaks do not require an acknowledgment in the delete path. Keep lease handling unchanged, but drop plain SMB2 level II oplocks locally for unlink requests without sending a break notification. Normal write/truncate paths still send the level II to none notification, preserving the behavior covered by smb2.oplock.levelII500. Signed-off-by: Namjae Jeon Signed-off-by: Steve French --- fs/smb/server/oplock.c | 31 ++++++++++++++++++++++++------- fs/smb/server/oplock.h | 4 ++++ fs/smb/server/smb2pdu.c | 4 ++-- 3 files changed, 30 insertions(+), 9 deletions(-) diff --git a/fs/smb/server/oplock.c b/fs/smb/server/oplock.c index 3f35ee7f7d00..5abeb90ebebb 100644 --- a/fs/smb/server/oplock.c +++ b/fs/smb/server/oplock.c @@ -1546,7 +1546,7 @@ static bool smb_break_all_write_oplock(struct ksmbd_work *work, */ static void __smb_break_all_levII_oplock(struct ksmbd_work *work, struct ksmbd_file *fp, int is_trunc, - bool send_interim) + bool send_interim, bool send_oplock_break) { struct oplock_info *op, *brk_op; struct ksmbd_inode *ci; @@ -1593,10 +1593,15 @@ static void __smb_break_all_levII_oplock(struct ksmbd_work *work, SMB2_LEASE_KEY_SIZE)) goto next; brk_op->open_trunc = is_trunc; - oplock_break(brk_op, - brk_op->is_lease && !is_trunc ? - SMB2_OPLOCK_LEVEL_II : SMB2_OPLOCK_LEVEL_NONE, - send_interim && !sent_interim ? work : NULL); + if (!brk_op->is_lease && !send_oplock_break) { + brk_op->level = SMB2_OPLOCK_LEVEL_NONE; + brk_op->op_state = OPLOCK_STATE_NONE; + } else { + oplock_break(brk_op, + brk_op->is_lease && !is_trunc ? + SMB2_OPLOCK_LEVEL_II : SMB2_OPLOCK_LEVEL_NONE, + send_interim && !sent_interim ? work : NULL); + } sent_interim = true; next: opinfo_put(brk_op); @@ -1610,7 +1615,19 @@ next: void smb_break_all_levII_oplock(struct ksmbd_work *work, struct ksmbd_file *fp, int is_trunc) { - __smb_break_all_levII_oplock(work, fp, is_trunc, true); + __smb_break_all_levII_oplock(work, fp, is_trunc, true, true); +} + +void smb_break_all_levII_oplock_no_interim(struct ksmbd_work *work, + struct ksmbd_file *fp, int is_trunc) +{ + __smb_break_all_levII_oplock(work, fp, is_trunc, false, true); +} + +void smb_break_all_levII_oplock_for_delete(struct ksmbd_work *work, + struct ksmbd_file *fp) +{ + __smb_break_all_levII_oplock(work, fp, 0, false, false); } /** @@ -1627,7 +1644,7 @@ void smb_break_all_oplock(struct ksmbd_work *work, struct ksmbd_file *fp) return; sent_break = smb_break_all_write_oplock(work, fp, 1); - __smb_break_all_levII_oplock(work, fp, 1, !sent_break); + __smb_break_all_levII_oplock(work, fp, 1, !sent_break, true); } /** diff --git a/fs/smb/server/oplock.h b/fs/smb/server/oplock.h index 8d1943586246..3f581d22bb67 100644 --- a/fs/smb/server/oplock.h +++ b/fs/smb/server/oplock.h @@ -99,6 +99,10 @@ int smb_grant_oplock(struct ksmbd_work *work, int req_op_level, struct lease_ctx_info *lctx, int share_ret); void smb_break_all_levII_oplock(struct ksmbd_work *work, struct ksmbd_file *fp, int is_trunc); +void smb_break_all_levII_oplock_no_interim(struct ksmbd_work *work, + struct ksmbd_file *fp, int is_trunc); +void smb_break_all_levII_oplock_for_delete(struct ksmbd_work *work, + struct ksmbd_file *fp); int opinfo_write_to_read(struct oplock_info *opinfo); int opinfo_read_handle_to_read(struct oplock_info *opinfo); int opinfo_write_to_none(struct oplock_info *opinfo); diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index 6b84a8ea5b15..d4a40cede7bd 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -3809,7 +3809,7 @@ int smb2_open(struct ksmbd_work *work) } if (req->CreateOptions & FILE_DELETE_ON_CLOSE_LE) { - smb_break_all_levII_oplock(work, fp, 0); + smb_break_all_levII_oplock_for_delete(work, fp); ksmbd_fd_set_delete_on_close(fp, file_info); } @@ -6796,7 +6796,7 @@ static int set_file_disposition_info(struct ksmbd_work *work, if (S_ISDIR(inode->i_mode) && ksmbd_vfs_empty_dir(fp) == -ENOTEMPTY) return -EBUSY; - smb_break_all_levII_oplock(work, fp, 0); + smb_break_all_levII_oplock_for_delete(work, fp); ksmbd_set_inode_pending_delete(fp); } else { ksmbd_clear_inode_pending_delete(fp); From 854b4f8f80f879aceead300028faeda8c90b4b91 Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Sun, 21 Jun 2026 19:49:41 +0900 Subject: [PATCH 186/297] ksmbd: return oplock protocol error for level II ack SMB2 level II to none oplock breaks do not require an acknowledgment from the client. smb2.oplock.levelii500 intentionally acknowledges such a break and expects the server to reject it with STATUS_INVALID_OPLOCK_PROTOCOL. ksmbd drops the local level II oplock to none immediately after sending the break notification because it does not wait for an ACK. When the client then sends the invalid ACK, smb20_oplock_break_ack() sees that the oplock is not in OPLOCK_ACK_WAIT state and returns STATUS_INVALID_DEVICE_STATE before checking the current oplock level. If the oplock is already none when an unexpected SMB2 oplock break ACK arrives, report STATUS_INVALID_OPLOCK_PROTOCOL. Keep the existing STATUS_INVALID_DEVICE_STATE response for other unexpected non-wait states. Signed-off-by: Namjae Jeon Signed-off-by: Steve French --- fs/smb/server/smb2pdu.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index d4a40cede7bd..705cef655702 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -9225,7 +9225,10 @@ static void smb20_oplock_break_ack(struct ksmbd_work *work) if (opinfo->op_state != OPLOCK_ACK_WAIT) { ksmbd_debug(SMB, "unexpected oplock state 0x%x\n", opinfo->op_state); - status = STATUS_INVALID_DEVICE_STATE; + if (opinfo->level == SMB2_OPLOCK_LEVEL_NONE) + status = STATUS_INVALID_OPLOCK_PROTOCOL; + else + status = STATUS_INVALID_DEVICE_STATE; goto err_out; } From 43f21349427dc964bfc7aa450e7e560f292698bb Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Sun, 21 Jun 2026 19:50:12 +0900 Subject: [PATCH 187/297] ksmbd: normalize ungrantable lease states smb2.lease.request verifies which SMB2 lease state combinations are granted by the server. Requests for H-only, W-only, and HW leases are valid lease state bitmasks, but they are not grantable combinations and should be returned as lease state none. ksmbd only checked that the requested bits were inside the SMB2 lease state mask. As a result it could grant H-only, W-only, or HW requests and return non-zero lease states where the client expects no lease. Keep the bitmask validation, but normalize ungrantable combinations to zero before allocating or looking up the lease. The grantable combinations remain unchanged: R, RH, RW, and RHW. Signed-off-by: Namjae Jeon Signed-off-by: Steve French --- fs/smb/server/oplock.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/fs/smb/server/oplock.c b/fs/smb/server/oplock.c index 5abeb90ebebb..331ce10dbb66 100644 --- a/fs/smb/server/oplock.c +++ b/fs/smb/server/oplock.c @@ -29,6 +29,17 @@ static bool lease_state_valid(__le32 state) return !(state & ~SMB2_LEASE_STATE_MASK_LE); } +static __le32 lease_state_grantable(__le32 state) +{ + if (state == SMB2_LEASE_READ_CACHING_LE || + state == (SMB2_LEASE_READ_CACHING_LE | SMB2_LEASE_HANDLE_CACHING_LE) || + state == (SMB2_LEASE_READ_CACHING_LE | SMB2_LEASE_WRITE_CACHING_LE) || + state == SMB2_LEASE_STATE_MASK_LE) + return state; + + return 0; +} + static bool lease_v2_flags_valid(__le32 flags) { return !(flags & ~SMB2_LEASE_FLAG_PARENT_LEASE_KEY_SET_LE); @@ -1760,6 +1771,7 @@ struct lease_ctx_info *parse_lease_state(void *open_req) if (!lease_state_valid(lreq->req_state) || !lease_v2_flags_valid(lreq->flags)) goto err_out; + lreq->req_state = lease_state_grantable(lreq->req_state); if (lreq->flags == SMB2_LEASE_FLAG_PARENT_LEASE_KEY_SET_LE) memcpy(lreq->parent_lease_key, lc->lcontext.ParentLeaseKey, SMB2_LEASE_KEY_SIZE); @@ -1777,6 +1789,7 @@ struct lease_ctx_info *parse_lease_state(void *open_req) lreq->duration = lc->lcontext.LeaseDuration; if (!lease_state_valid(lreq->req_state)) goto err_out; + lreq->req_state = lease_state_grantable(lreq->req_state); lreq->version = 1; } else goto err_out; From b35f8f898cd99d61ac9acbdc87ca3955922e956a Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Sun, 21 Jun 2026 19:50:41 +0900 Subject: [PATCH 188/297] ksmbd: break handle caching for share conflicts smb2.lease.break_twice first opens a file with an RHW lease and then tries a second open with restrictive sharing. That open must fail with a sharing violation, but the existing lease should be broken from RHW to RW because only handle caching conflicts with the requested sharing. ksmbd used the normal write-cache break calculation for this path, so RHW was broken to RH. The following successful open then did not generate the expected second break from RW to R. Pass share-conflict context into the lease break helper and, for lease breaks caused by sharing, drop only SMB2_LEASE_HANDLE_CACHING from the current lease state. Other break paths keep the existing write/truncate break behavior. A share-conflict break must also remain a single break. The triggering open fails with a sharing violation and is never granted, so there is no target oplock level to converge on. The lease break retry loop, however, keeps breaking while the lease level is still above req_op_level, which broke RHW all the way down to R in one open (lease_break_info.count became 2 instead of 1). Skip the again loop for share-conflict breaks so the sharing open produces exactly one RHW->RW break and the later successful open produces the separate RW->R break the test expects. Signed-off-by: Namjae Jeon Signed-off-by: Steve French --- fs/smb/server/oplock.c | 26 +++++++++++++++++++------- 1 file changed, 19 insertions(+), 7 deletions(-) diff --git a/fs/smb/server/oplock.c b/fs/smb/server/oplock.c index 331ce10dbb66..33e93084c3b5 100644 --- a/fs/smb/server/oplock.c +++ b/fs/smb/server/oplock.c @@ -1035,7 +1035,7 @@ static void wait_lease_breaking(struct oplock_info *opinfo) } static int oplock_break(struct oplock_info *brk_opinfo, int req_op_level, - struct ksmbd_work *in_work) + struct ksmbd_work *in_work, bool share_break) { int err = 0; bool sent_interim = false; @@ -1073,6 +1073,10 @@ again: * none. */ lease->new_state = SMB2_LEASE_NONE_LE; + } else if (share_break && + lease->state & SMB2_LEASE_HANDLE_CACHING_LE) { + lease->new_state = + lease->state & ~SMB2_LEASE_HANDLE_CACHING_LE; } else { if (lease->state & SMB2_LEASE_WRITE_CACHING_LE) { if (lease->state & SMB2_LEASE_HANDLE_CACHING_LE) @@ -1121,7 +1125,13 @@ again: if (wait_ack) wait_lease_breaking(brk_opinfo); - if (wait_ack && !err && + /* + * A break caused by a share-mode conflict only drops the + * conflicting caching bit and the triggering open still fails + * with a sharing violation, so it must stay a single break. + * Do not cascade down to req_op_level through the again loop. + */ + if (wait_ack && !err && !share_break && lease_break_needed(brk_opinfo, req_op_level, open_trunc)) goto again; @@ -1281,7 +1291,7 @@ void smb_send_parent_lease_break_noti(struct ksmbd_file *fp, continue; } - oplock_break(opinfo, SMB2_OPLOCK_LEVEL_NONE, NULL); + oplock_break(opinfo, SMB2_OPLOCK_LEVEL_NONE, NULL, false); opinfo_put(opinfo); } } @@ -1322,7 +1332,7 @@ void smb_lazy_parent_lease_break_close(struct ksmbd_file *fp) continue; } - oplock_break(opinfo, SMB2_OPLOCK_LEVEL_NONE, NULL); + oplock_break(opinfo, SMB2_OPLOCK_LEVEL_NONE, NULL, false); opinfo_put(opinfo); } } @@ -1441,7 +1451,8 @@ int smb_grant_oplock(struct ksmbd_work *work, int req_op_level, u64 pid, prev_fid = prev_opinfo->fid; } - err = oplock_break(prev_opinfo, break_level, work); + err = oplock_break(prev_opinfo, break_level, work, + share_ret < 0 && prev_opinfo->is_lease); if (prev_durable_detached || (prev_durable_open && err == -ENOENT)) ksmbd_invalidate_durable_fd(prev_fid); opinfo_put(prev_opinfo); @@ -1539,7 +1550,7 @@ static bool smb_break_all_write_oplock(struct ksmbd_work *work, } brk_opinfo->open_trunc = is_trunc; - oplock_break(brk_opinfo, SMB2_OPLOCK_LEVEL_II, work); + oplock_break(brk_opinfo, SMB2_OPLOCK_LEVEL_II, work, false); sent_break = true; opinfo_put(brk_opinfo); @@ -1611,7 +1622,8 @@ static void __smb_break_all_levII_oplock(struct ksmbd_work *work, oplock_break(brk_op, brk_op->is_lease && !is_trunc ? SMB2_OPLOCK_LEVEL_II : SMB2_OPLOCK_LEVEL_NONE, - send_interim && !sent_interim ? work : NULL); + send_interim && !sent_interim ? work : NULL, + false); } sent_interim = true; next: From 889d2e38943ad9ab253dfd7520e6d92867825e7d Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Sun, 21 Jun 2026 19:51:35 +0900 Subject: [PATCH 189/297] ksmbd: break conflicting-open leases only as far as needed smb2.lease.oplock and smb2.lease.breaking1 hold a lease and then issue a single conflicting open on the same file. The held lease must break one step to drop write caching (RWH->RH, RW->R) and then stop, so lease_break_info.count is 1 and the lease keeps its read/handle caching. ksmbd instead cascaded the break all the way down to none (e.g. RWH->RH->R->none), so the break count was 2 or 3 and the reported lease state ended at 0. Commit "chain pending lease breaks before waking waiters" forces break_level to SMB2_OPLOCK_LEVEL_NONE for any non-lease open against a handle-caching lease, which drives oplock_break()'s retry loop down to none even when only one open is contending. Drop that break_level override so a conflicting open breaks a lease only to its own compatible level (level II, i.e. RH/R). A deeper break is still required when a truncating open is also waiting behind the same lease break. smb2.lease.breaking3 keeps a normal open pending through RWH->RH and an overwrite open pending behind it, and expects the lease to continue RH->R->none before either open completes. The overwrite waiter sets open_trunc on the lease while it blocks on the pending break, so extend the retry loop to chain another break while that truncating waiter still needs the lease at none. The per-break open_trunc snapshot stays cleared, so the cascade steps down (RH->R->none) instead of collapsing straight to none, and the normal open stays pending until the lease is fully broken. Signed-off-by: Namjae Jeon Signed-off-by: Steve French --- fs/smb/server/oplock.c | 23 ++++++++++++++--------- 1 file changed, 14 insertions(+), 9 deletions(-) diff --git a/fs/smb/server/oplock.c b/fs/smb/server/oplock.c index 33e93084c3b5..afd492be88fb 100644 --- a/fs/smb/server/oplock.c +++ b/fs/smb/server/oplock.c @@ -1126,13 +1126,22 @@ again: if (wait_ack) wait_lease_breaking(brk_opinfo); /* - * A break caused by a share-mode conflict only drops the - * conflicting caching bit and the triggering open still fails - * with a sharing violation, so it must stay a single break. - * Do not cascade down to req_op_level through the again loop. + * A share-mode conflict break only drops the conflicting + * caching bit; the triggering open fails with a sharing + * violation, so keep it to a single break. + * + * Otherwise chain another break while the lease is still + * incompatible with this open (req_op_level), or while a + * truncating waiter that arrived during the break still needs + * the lease dropped to none. open_trunc snapshotted for this + * break stays cleared, so the next state is computed from the + * lease state and the cascade steps down (e.g. RH->R->none) + * instead of collapsing straight to none. */ if (wait_ack && !err && !share_break && - lease_break_needed(brk_opinfo, req_op_level, open_trunc)) + (lease_break_needed(brk_opinfo, req_op_level, open_trunc) || + (brk_opinfo->open_trunc && + lease->state != SMB2_LEASE_NONE_LE))) goto again; wake_up_oplock_break(brk_opinfo); @@ -1426,10 +1435,6 @@ int smb_grant_oplock(struct ksmbd_work *work, int req_op_level, u64 pid, prev_op_has_lease = prev_opinfo->is_lease; if (prev_op_has_lease) prev_op_state = prev_opinfo->o_lease->state; - if (prev_op_has_lease && !lctx && - prev_op_state & SMB2_LEASE_HANDLE_CACHING_LE) - break_level = SMB2_OPLOCK_LEVEL_NONE; - if (share_ret < 0 && prev_opinfo->level == SMB2_OPLOCK_LEVEL_EXCLUSIVE) { err = share_ret; From 256257279c187386ceb18540a1f8e19252fd01f6 Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Sun, 21 Jun 2026 19:52:55 +0900 Subject: [PATCH 190/297] ksmbd: validate :: stream type against directory create smb2.streams.dir opens ::$DATA with FILE_DIRECTORY_FILE and expects STATUS_NOT_A_DIRECTORY, then opens ::$DATA without it and expects STATUS_FILE_IS_A_DIRECTORY. Commit "treat unnamed DATA stream as base file" canonicalizes the ::$DATA suffix to a NULL stream name so the open continues through the base-file path. That skipped the stream/directory type validation, which was guarded by "if (stream_name)", so opening a directory's ::$DATA stream with FILE_DIRECTORY_FILE incorrectly returned STATUS_OK and a plain open of it no longer reported STATUS_FILE_IS_A_DIRECTORY. parse_stream_name() still records the explicit $DATA type in s_type even when it clears stream_name. Run the data-stream vs directory validation whenever s_type is DATA_STREAM, not only when stream_name is set, so the canonicalized ::$DATA open is rejected with the correct status. Signed-off-by: Namjae Jeon Signed-off-by: Steve French --- fs/smb/server/smb2pdu.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index 705cef655702..c0d3062e4d93 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -3453,7 +3453,14 @@ int smb2_open(struct ksmbd_work *work) rc = 0; } - if (stream_name) { + /* + * An explicit ::$DATA suffix names the unnamed data stream and is + * canonicalized to a NULL stream name (base file), but the request + * still has to be validated against the data-stream type, e.g. opening + * ::$DATA with FILE_DIRECTORY_FILE must fail with + * STATUS_NOT_A_DIRECTORY. + */ + if (stream_name || s_type == DATA_STREAM) { if (req->CreateOptions & FILE_DIRECTORY_FILE_LE) { if (s_type == DATA_STREAM) { rc = -EIO; From be939e11c4724d1de3650e8bafd4c3583d9684b2 Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Sun, 21 Jun 2026 19:57:55 +0900 Subject: [PATCH 191/297] ksmbd: treat read-control opens as stat opens only for leases A second open that requests only metadata-level access must not break the existing caching state. ksmbd already skips the break for such opens via fp->attrib_only (FILE_READ_ATTRIBUTES, FILE_WRITE_ATTRIBUTES and FILE_SYNCHRONIZE). An open requesting only READ_CONTROL (reading the security descriptor) must be treated differently depending on the existing caching state. smbtorture smb2.lease.statopen4 expects a read-control open NOT to break a caching lease, while smb2.oplock.statopen1 expects the same open to break a batch oplock. So READ_CONTROL is a stat open for leases but not for oplocks. Extend the stat-open break-skip in smb_grant_oplock() to also cover a read-control-only open, but only when the existing holder is a lease. The global fp->attrib_only flag (used for share-mode, rename and truncate decisions) is left unchanged so oplock behaviour is preserved. Signed-off-by: Namjae Jeon Signed-off-by: Steve French --- fs/smb/server/oplock.c | 30 +++++++++++++++++++++++++++--- 1 file changed, 27 insertions(+), 3 deletions(-) diff --git a/fs/smb/server/oplock.c b/fs/smb/server/oplock.c index afd492be88fb..99cbd7aa03fc 100644 --- a/fs/smb/server/oplock.c +++ b/fs/smb/server/oplock.c @@ -312,6 +312,18 @@ void opinfo_put(struct oplock_info *opinfo) free_opinfo(opinfo); } +static bool ksmbd_inode_has_lease(struct ksmbd_inode *ci) +{ + struct oplock_info *opinfo = opinfo_get_list(ci); + bool is_lease; + + if (!opinfo) + return false; + is_lease = opinfo->is_lease; + opinfo_put(opinfo); + return is_lease; +} + static void opinfo_add(struct oplock_info *opinfo, struct ksmbd_file *fp) { struct ksmbd_inode *ci = fp->f_ci; @@ -1402,10 +1414,22 @@ int smb_grant_oplock(struct ksmbd_work *work, int req_op_level, u64 pid, if (!opinfo_count(fp)) goto set_lev; - /* grant none-oplock if second open is trunc */ - if (fp->attrib_only && fp->cdoption != FILE_OVERWRITE_IF_LE && + /* + * A stat open that only requests metadata access must not break the + * existing caching state. READ_CONTROL (reading the security + * descriptor) does not conflict with a lease, but it does conflict + * with an oplock, so only treat a read-control-only open as a stat + * open when the existing holder is a lease. + */ + if (fp->cdoption != FILE_OVERWRITE_IF_LE && fp->cdoption != FILE_OVERWRITE_LE && - fp->cdoption != FILE_SUPERSEDE_LE) { + fp->cdoption != FILE_SUPERSEDE_LE && + (fp->attrib_only || + (!(fp->daccess & ~(FILE_READ_ATTRIBUTES_LE | + FILE_WRITE_ATTRIBUTES_LE | + FILE_SYNCHRONIZE_LE | + FILE_READ_CONTROL_LE)) && + ksmbd_inode_has_lease(ci)))) { req_op_level = SMB2_OPLOCK_LEVEL_NONE; goto set_lev; } From 6b375be0b4e1be89e9a817880515311503a19114 Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Sun, 21 Jun 2026 19:59:06 +0900 Subject: [PATCH 192/297] ksmbd: start file id allocation at 1 ksmbd allocates both the volatile id (per-session file table) and the persistent id (global file table) with idr_alloc_cyclic() starting at 0. The first open after the module loads therefore gets volatile id 0 and persistent id 0, and ksmbd returns an SMB2 FileId of {0, 0} in the create response. Clients treat an all-zero FileId as a null handle. smbtorture's smb2_util_handle_empty() considers {0, 0} empty, so tests that guard the close with it (e.g. smb2.oplock.statopen1, smb2.lease.statopen*) never close that first handle. The leaked open keeps the inode's oplock count non-zero, so a later batch oplock request on the same file is downgraded to level II and the test fails. Start the id allocation at 1 (KSMBD_START_FID) so no handle is ever assigned a {0, 0} FileId, matching the behaviour of other SMB servers. Signed-off-by: Namjae Jeon Signed-off-by: Steve French --- fs/smb/server/vfs_cache.c | 3 ++- fs/smb/server/vfs_cache.h | 7 ++++++- 2 files changed, 8 insertions(+), 2 deletions(-) diff --git a/fs/smb/server/vfs_cache.c b/fs/smb/server/vfs_cache.c index 11b51320b96e..7495166b0262 100644 --- a/fs/smb/server/vfs_cache.c +++ b/fs/smb/server/vfs_cache.c @@ -992,7 +992,8 @@ static int __open_id(struct ksmbd_file_table *ft, struct ksmbd_file *fp, idr_preload(KSMBD_DEFAULT_GFP); write_lock(&ft->lock); - ret = idr_alloc_cyclic(ft->idr, fp, 0, INT_MAX - 1, GFP_NOWAIT); + ret = idr_alloc_cyclic(ft->idr, fp, KSMBD_START_FID, INT_MAX - 1, + GFP_NOWAIT); if (ret >= 0) { id = ret; ret = 0; diff --git a/fs/smb/server/vfs_cache.h b/fs/smb/server/vfs_cache.h index f85021c11d6e..287f3e675cd3 100644 --- a/fs/smb/server/vfs_cache.h +++ b/fs/smb/server/vfs_cache.h @@ -23,7 +23,12 @@ #define FILE_GENERIC_WRITE 0x120116 #define FILE_GENERIC_EXECUTE 0X1200a0 -#define KSMBD_START_FID 0 +/* + * Start volatile/persistent file id allocation at 1. A file id of 0 yields an + * SMB2 FileId of {0, 0}, which clients (e.g. Windows, Samba) treat as a null + * handle and never close, leaking the open on the server. + */ +#define KSMBD_START_FID 1 #define KSMBD_NO_FID (INT_MAX) #define SMB2_NO_FID (0xFFFFFFFFFFFFFFFFULL) From 5a7f4d6d8e7fc9c3b67412f1b8e5b56c9aec21af Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Sun, 21 Jun 2026 19:59:56 +0900 Subject: [PATCH 193/297] ksmbd: sleep interruptibly in the durable handle scavenger The durable handle scavenger kthread waits up to DURABLE_HANDLE_MAX_TIMEOUT (300 seconds) between scans using wait_event_timeout(), which sleeps in TASK_UNINTERRUPTIBLE. When there are no durable handles pending expiry the task stays in D state far longer than 120 seconds, so the hung task detector prints a bogus "task ksmbd-durable-s blocked for more than 120 seconds" warning with a backtrace, even though the thread is only idle. Use wait_event_interruptible_timeout() so the thread sleeps in TASK_INTERRUPTIBLE, which the hung task detector ignores. This also suits the already-freezable kthread. Treat a negative return (e.g. -ERESTARTSYS) like a timeout when recomputing the next wake interval. Signed-off-by: Namjae Jeon Signed-off-by: Steve French --- fs/smb/server/vfs_cache.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/smb/server/vfs_cache.c b/fs/smb/server/vfs_cache.c index 7495166b0262..fde22742d193 100644 --- a/fs/smb/server/vfs_cache.c +++ b/fs/smb/server/vfs_cache.c @@ -1344,10 +1344,10 @@ static int ksmbd_durable_scavenger(void *dummy) if (try_to_freeze()) continue; - remaining_jiffies = wait_event_timeout(dh_wq, + remaining_jiffies = wait_event_interruptible_timeout(dh_wq, ksmbd_durable_scavenger_alive() == false, __msecs_to_jiffies(min_timeout)); - if (remaining_jiffies) + if ((long)remaining_jiffies > 0) min_timeout = jiffies_to_msecs(remaining_jiffies); else min_timeout = DURABLE_HANDLE_MAX_TIMEOUT; From 474fd91f3828a89dd7dc0a862f77f14e9f9240ff Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Sun, 21 Jun 2026 21:21:01 +0900 Subject: [PATCH 194/297] ksmbd: fix UBSAN array-index-out-of-bounds in decode_compress_ctxt() decode_compress_ctxt() walks CompressionAlgorithms[] using the client supplied CompressionAlgorithmCount. That field is declared in struct smb2_compression_capabilities_context as a fixed 4-element array, but the number of algorithms is actually variable and clients such as Windows advertise more than four (e.g. LZ77, LZ77+Huffman, LZNT1, Pattern_V1 and LZ4). The on-wire context length is already validated, so the access is within the received buffer, but indexing the statically sized [4] array makes UBSAN report an out-of-bounds access: UBSAN: array-index-out-of-bounds in smb2pdu.c:1122:48 index 4 is out of range for type '__le16 [4]' Call Trace: smb2_handle_negotiate+0xda7/0xde0 [ksmbd] ksmbd_smb_negotiate_common+0x27b/0x3e0 [ksmbd] smb2_negotiate_request+0x14/0x20 [ksmbd] handle_ksmbd_work+0x181/0x500 [ksmbd] Walk the algorithms through a pointer so the fixed-array bounds check is not applied, while keeping the existing length validation that bounds the loop to the data actually received. Signed-off-by: Namjae Jeon Signed-off-by: Steve French --- fs/smb/server/smb2pdu.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index c0d3062e4d93..5859fa68bb84 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -1094,6 +1094,7 @@ static __le32 decode_compress_ctxt(struct ksmbd_conn *conn, int ctxt_len) { int alg_cnt, algs_size, i; + __le16 *algs; if (sizeof(struct smb2_neg_context) + 10 > ctxt_len) { pr_err("Invalid SMB2_COMPRESSION_CAPABILITIES context length\n"); @@ -1118,8 +1119,15 @@ static __le32 decode_compress_ctxt(struct ksmbd_conn *conn, return STATUS_INVALID_PARAMETER; } + /* + * CompressionAlgorithms[] is declared as a fixed 4-element array, but + * the actual element count is variable (clients such as Windows may + * advertise more). The on-wire length was validated above, so walk the + * algorithms through a pointer to avoid a fixed-array bounds check. + */ + algs = pneg_ctxt->CompressionAlgorithms; for (i = 0; i < alg_cnt; i++) { - __le16 alg = pneg_ctxt->CompressionAlgorithms[i]; + __le16 alg = algs[i]; /* * LZ77 is the required general-purpose codec. Pattern_V1 is an From 4429b56506f45891d445f4dc4c8a22b3ec9b12de Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Mon, 22 Jun 2026 10:16:41 +0900 Subject: [PATCH 195/297] ksmbd: increase SMB3_DEFAULT_TRANS_SIZE from 1MB to 4MB This patch raises `SMB3_DEFAULT_TRANS_SIZE` to 4MB to align it with `smb2 max read/write`. This allows better I/O negotiation with modern clients and improves sequential read/write performance on high-speed networks. Signed-off-by: Namjae Jeon Signed-off-by: Steve French --- fs/smb/server/smb2pdu.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/smb/server/smb2pdu.h b/fs/smb/server/smb2pdu.h index 3bed676bb5ad..c2512dbcdec8 100644 --- a/fs/smb/server/smb2pdu.h +++ b/fs/smb/server/smb2pdu.h @@ -23,7 +23,7 @@ #define MAX_SMB2_HDR_SIZE 0x78 /* 4 len + 64 hdr + (2*24 wct) + 2 bct + 2 pad */ #define SMB21_DEFAULT_IOSIZE (1024 * 1024) -#define SMB3_DEFAULT_TRANS_SIZE (1024 * 1024) +#define SMB3_DEFAULT_TRANS_SIZE (4 * 1024 * 1024) #define SMB3_MIN_IOSIZE (64 * 1024) #define SMB3_MAX_IOSIZE (8 * 1024 * 1024) #define SMB3_MAX_MSGSIZE (4 * 4096) From fc36dd30412a3b9df3b408e36e8e2cd24bd9e33c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Wed, 17 Jun 2026 11:44:08 +0200 Subject: [PATCH 196/297] fbdev: vga16fb: Drop unused assignment of platform_device_id driver data MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The driver explicitly sets the .driver_data member of struct platform_device_id to zero without relying on that value. Drop these unused assignments. While touching this array unify spacing and usage of commas and use named initializers for .name. Signed-off-by: Uwe Kleine-König (The Capable Hub) Signed-off-by: Helge Deller --- drivers/video/fbdev/vga16fb.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/video/fbdev/vga16fb.c b/drivers/video/fbdev/vga16fb.c index 22085d3668e8..cdd6b8de0ceb 100644 --- a/drivers/video/fbdev/vga16fb.c +++ b/drivers/video/fbdev/vga16fb.c @@ -1421,8 +1421,8 @@ static void vga16fb_remove(struct platform_device *dev) } static const struct platform_device_id vga16fb_driver_id_table[] = { - {"ega-framebuffer", 0}, - {"vga-framebuffer", 0}, + { .name = "ega-framebuffer" }, + { .name = "vga-framebuffer" }, { } }; MODULE_DEVICE_TABLE(platform, vga16fb_driver_id_table); From 914a76a9f08366434bf595700f62026b7a19a9cc Mon Sep 17 00:00:00 2001 From: Joonas Lahtinen Date: Mon, 22 Jun 2026 16:25:39 +0300 Subject: [PATCH 197/297] drm/i915/gem: Add missing nospec on parallel submit slot Add missing Spectre mitigation for userspace controlled parallel submission slot. Discovered using AI-assisted static analysis confirmed by Intel Product Security. Reported-by: Martin Hodo Fixes: e5e32171a2cf ("drm/i915/guc: Connect UAPI to GuC multi-lrc interface") Cc: Matthew Brost Cc: Tvrtko Ursulin Signed-off-by: Joonas Lahtinen Reviewed-by: Matthew Brost Reviewed-by: Tvrtko Ursulin Cc: # v5.16+ Link: https://patch.msgid.link/20260622132539.165558-1-joonas.lahtinen@linux.intel.com (cherry picked from commit 15b9353deff3cf72331c387780de3cf9c316b643) Signed-off-by: Joonas Lahtinen --- drivers/gpu/drm/i915/gem/i915_gem_context.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c index 6ac0f23570f3..aeafe1742d30 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_context.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c @@ -613,6 +613,7 @@ set_proto_ctx_engines_parallel_submit(struct i915_user_extension __user *base, return -EINVAL; } + slot = array_index_nospec(slot, set->num_engines); if (set->engines[slot].type != I915_GEM_ENGINE_TYPE_INVALID) { drm_dbg(&i915->drm, "Invalid placement[%d], already occupied\n", slot); From e0ecb324246be9cf3a0689346a658e48a38546b2 Mon Sep 17 00:00:00 2001 From: "Geoffrey D. Bennett" Date: Tue, 23 Jun 2026 02:59:04 +0930 Subject: [PATCH 198/297] ALSA: FCP: Add Focusrite ISA C8X support Add USB PID 0x821e to the list of devices handled by the Focusrite Control Protocol (FCP) driver. Cc: stable@vger.kernel.org Signed-off-by: Geoffrey D. Bennett Link: https://patch.msgid.link/ajlw4HK+2RSW3nUl@m.b4.vu Signed-off-by: Takashi Iwai --- sound/usb/mixer_quirks.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/usb/mixer_quirks.c b/sound/usb/mixer_quirks.c index 628f841b04aa..f6f2bc8e97a7 100644 --- a/sound/usb/mixer_quirks.c +++ b/sound/usb/mixer_quirks.c @@ -4526,6 +4526,7 @@ int snd_usb_mixer_apply_create_quirk(struct usb_mixer_interface *mixer) case USB_ID(0x1235, 0x821b): /* Focusrite Scarlett 16i16 4th Gen */ case USB_ID(0x1235, 0x821c): /* Focusrite Scarlett 18i16 4th Gen */ case USB_ID(0x1235, 0x821d): /* Focusrite Scarlett 18i20 4th Gen */ + case USB_ID(0x1235, 0x821e): /* Focusrite ISA C8X */ err = snd_fcp_init(mixer); break; From 5714c8359f4fc171ab8e0bd0dfc4c61fb36e1db6 Mon Sep 17 00:00:00 2001 From: Charles Keepax Date: Tue, 23 Jun 2026 11:18:10 +0100 Subject: [PATCH 199/297] soundwire: Move wait for initialisation helper to header As SoundWire devices tend to enumerate on the bus after probe, drivers frequently need to wait for the device to initialise from common driver code. The common system is to split drivers into a core module and then a module for each communication bus. These two facts tend to cause Kconfig issues, the issue tends to be when SOUNDWIRE=m and DRIVER_I2C=y, this usually selects DRIVER=y. The driver code then wants to call sdw_slave_wait_for_init(), but this results in calling a module function from built in code. A depends on SOUNDWIRE | !SOUNDWIRE could be added to the end driver but this seems slightly off as it adds a lot of counter intuitive depends. A simpler solution is to make sdw_slave_wait_for_init() a static inline function. As part of doing this add a check for the slave device being NULL acknowledging that this is likely called from code that is shared between control buses. It does require dropping the call to sdw_show_ping_status() but this can be added back in end drivers that used it originally. Currently this is causing rand config issues on RT5682 and will soon also cause similar problems on cs42l43. Acked-by: Vinod Koul Acked-by: Arnd Bergmann Signed-off-by: Charles Keepax Link: https://patch.msgid.link/20260623101814.24044-2-ckeepax@opensource.cirrus.com Signed-off-by: Mark Brown --- drivers/soundwire/bus.c | 28 -------------------------- include/linux/soundwire/sdw.h | 38 +++++++++++++++++++++++++++-------- 2 files changed, 30 insertions(+), 36 deletions(-) diff --git a/drivers/soundwire/bus.c b/drivers/soundwire/bus.c index b7bdf19ebb42..fe5316d93fef 100644 --- a/drivers/soundwire/bus.c +++ b/drivers/soundwire/bus.c @@ -1372,34 +1372,6 @@ int sdw_slave_get_current_bank(struct sdw_slave *slave) } EXPORT_SYMBOL_GPL(sdw_slave_get_current_bank); -/** - * sdw_slave_wait_for_init - Wait for device initialisation - * @slave: Pointer to the SoundWire peripheral. - * @timeout_ms: Timeout in milliseconds. - * - * Wait for a peripheral device to enumerate and be initialised by the - * SoundWire core. - * - * Return: Zero on success, and a negative error code on failure. - */ -int sdw_slave_wait_for_init(struct sdw_slave *slave, int timeout_ms) -{ - unsigned long time; - - time = wait_for_completion_timeout(&slave->initialization_complete, - msecs_to_jiffies(timeout_ms)); - if (!time) { - dev_err(&slave->dev, "Initialization not complete\n"); - sdw_show_ping_status(slave->bus, true); - return -ETIMEDOUT; - } - - slave->unattach_request = 0; - - return 0; -} -EXPORT_SYMBOL_GPL(sdw_slave_wait_for_init); - static int sdw_slave_set_frequency(struct sdw_slave *slave) { int scale_index; diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h index a46cbaec5949..b484784e2690 100644 --- a/include/linux/soundwire/sdw.h +++ b/include/linux/soundwire/sdw.h @@ -11,6 +11,7 @@ #include #include #include +#include #include #include #include @@ -1093,8 +1094,6 @@ int sdw_slave_get_current_bank(struct sdw_slave *sdev); int sdw_slave_get_scale_index(struct sdw_slave *slave, u8 *base); -int sdw_slave_wait_for_init(struct sdw_slave *slave, int timeout_ms); - /* messaging and data APIs */ int sdw_read(struct sdw_slave *slave, u32 addr); int sdw_write(struct sdw_slave *slave, u32 addr, u8 value); @@ -1138,12 +1137,6 @@ static inline int sdw_slave_get_current_bank(struct sdw_slave *sdev) return -EINVAL; } -static inline int sdw_slave_wait_for_init(struct sdw_slave *slave, int timeout_ms) -{ - WARN_ONCE(1, "SoundWire API is disabled"); - return -EINVAL; -} - /* messaging and data APIs */ static inline int sdw_read(struct sdw_slave *slave, u32 addr) { @@ -1207,4 +1200,33 @@ static inline int sdw_update_no_pm(struct sdw_slave *slave, u32 addr, u8 mask, u #endif /* CONFIG_SOUNDWIRE */ +/** + * sdw_slave_wait_for_init - Wait for device initialisation + * @slave: Pointer to the SoundWire peripheral. + * @timeout_ms: Timeout in milliseconds. + * + * Wait for a peripheral device to enumerate and be initialised by the + * SoundWire core. + * + * Return: Zero on success, and a negative error code on failure. + */ +static inline int sdw_slave_wait_for_init(struct sdw_slave *slave, int timeout_ms) +{ + unsigned long time; + + if (!slave) + return 0; + + time = wait_for_completion_timeout(&slave->initialization_complete, + msecs_to_jiffies(timeout_ms)); + if (!time) { + dev_err(&slave->dev, "Initialization not complete\n"); + return -ETIMEDOUT; + } + + slave->unattach_request = 0; + + return 0; +} + #endif /* __SOUNDWIRE_H */ From ce52450319fb0ee122e5be5ec8dfb888ee1e0237 Mon Sep 17 00:00:00 2001 From: Charles Keepax Date: Tue, 23 Jun 2026 11:18:11 +0100 Subject: [PATCH 200/297] ASoC: es9356: Add back local call to sdw_show_ping_status() As the core no longer calls this debug helper add it back to the drivers that originally called it. Acked-by: Arnd Bergmann Signed-off-by: Charles Keepax Link: https://patch.msgid.link/20260623101814.24044-3-ckeepax@opensource.cirrus.com Signed-off-by: Mark Brown --- sound/soc/codecs/es9356.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/sound/soc/codecs/es9356.c b/sound/soc/codecs/es9356.c index 670e918b56a4..8db81d574624 100644 --- a/sound/soc/codecs/es9356.c +++ b/sound/soc/codecs/es9356.c @@ -1111,8 +1111,10 @@ static int es9356_sdca_dev_resume(struct device *dev) es9356->disable_irq = false; ret = sdw_slave_wait_for_init(slave, es9356_PROBE_TIMEOUT); - if (ret) + if (ret) { + sdw_show_ping_status(slave->bus, true); return ret; + } regcache_cache_only(es9356->regmap, false); regcache_sync(es9356->regmap); From 1921303a1d2f26ae70446aa18fb218767bddd913 Mon Sep 17 00:00:00 2001 From: Charles Keepax Date: Tue, 23 Jun 2026 11:18:12 +0100 Subject: [PATCH 201/297] ASoC: max98373: Add back local call to sdw_show_ping_status() As the core no longer calls this debug helper add it back to the drivers that originally called it. Acked-by: Arnd Bergmann Signed-off-by: Charles Keepax Link: https://patch.msgid.link/20260623101814.24044-4-ckeepax@opensource.cirrus.com Signed-off-by: Mark Brown --- sound/soc/codecs/max98373-sdw.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/sound/soc/codecs/max98373-sdw.c b/sound/soc/codecs/max98373-sdw.c index 6829fa07c9ec..7a42052dc051 100644 --- a/sound/soc/codecs/max98373-sdw.c +++ b/sound/soc/codecs/max98373-sdw.c @@ -272,8 +272,10 @@ static int max98373_resume(struct device *dev) return 0; ret = sdw_slave_wait_for_init(slave, MAX98373_PROBE_TIMEOUT); - if (ret) + if (ret) { + sdw_show_ping_status(slave->bus, true); return ret; + } regcache_cache_only(max98373->regmap, false); regcache_sync(max98373->regmap); From ea9ff3b7bcfbcd1e61d34590c7c632005ef3d9aa Mon Sep 17 00:00:00 2001 From: Charles Keepax Date: Tue, 23 Jun 2026 11:18:13 +0100 Subject: [PATCH 202/297] ASoC: ti: Add back local call to sdw_show_ping_status() As the core no longer calls this debug helper add it back to the drivers that originally called it. Acked-by: Arnd Bergmann Signed-off-by: Charles Keepax Link: https://patch.msgid.link/20260623101814.24044-5-ckeepax@opensource.cirrus.com Signed-off-by: Mark Brown --- sound/soc/codecs/tac5xx2-sdw.c | 4 +++- sound/soc/codecs/tas2783-sdw.c | 4 +++- 2 files changed, 6 insertions(+), 2 deletions(-) diff --git a/sound/soc/codecs/tac5xx2-sdw.c b/sound/soc/codecs/tac5xx2-sdw.c index bb12cfb6da12..ace06f5ab58c 100644 --- a/sound/soc/codecs/tac5xx2-sdw.c +++ b/sound/soc/codecs/tac5xx2-sdw.c @@ -1445,8 +1445,10 @@ static s32 tac5xx2_sdca_dev_resume(struct device *dev) } ret = sdw_slave_wait_for_init(slave, TAC5XX2_PROBE_TIMEOUT_MS); - if (ret) + if (ret) { + sdw_show_ping_status(slave->bus, true); return ret; + } regcache_cache_only(tac_dev->regmap, false); regcache_mark_dirty(tac_dev->regmap); diff --git a/sound/soc/codecs/tas2783-sdw.c b/sound/soc/codecs/tas2783-sdw.c index 7d70e7e3f24f..1127ea59b5e4 100644 --- a/sound/soc/codecs/tas2783-sdw.c +++ b/sound/soc/codecs/tas2783-sdw.c @@ -1083,8 +1083,10 @@ static s32 tas2783_sdca_dev_resume(struct device *dev) int ret; ret = sdw_slave_wait_for_init(slave, TAS2783_PROBE_TIMEOUT); - if (ret) + if (ret) { + sdw_show_ping_status(slave->bus, true); return ret; + } regcache_cache_only(tas_dev->regmap, false); regcache_sync(tas_dev->regmap); From 6540b9d9ccc32ad1546dcc7b4d4bcbb68c667714 Mon Sep 17 00:00:00 2001 From: Charles Keepax Date: Tue, 23 Jun 2026 11:18:14 +0100 Subject: [PATCH 203/297] ASoC: realtek: Add back local call to sdw_show_ping_status() As the core no longer calls this debug helper add it back to the drivers that originally called it. Acked-by: Arnd Bergmann Signed-off-by: Charles Keepax Link: https://patch.msgid.link/20260623101814.24044-6-ckeepax@opensource.cirrus.com Signed-off-by: Mark Brown --- sound/soc/codecs/rt1017-sdca-sdw.c | 4 +++- sound/soc/codecs/rt1308-sdw.c | 4 +++- sound/soc/codecs/rt1316-sdw.c | 4 +++- sound/soc/codecs/rt5682-sdw.c | 4 +++- sound/soc/codecs/rt700-sdw.c | 4 +++- sound/soc/codecs/rt711-sdca-sdw.c | 4 +++- sound/soc/codecs/rt712-sdca-dmic.c | 4 +++- sound/soc/codecs/rt712-sdca-sdw.c | 4 +++- sound/soc/codecs/rt715-sdca-sdw.c | 4 +++- sound/soc/codecs/rt715-sdw.c | 4 +++- sound/soc/codecs/rt721-sdca-sdw.c | 4 +++- sound/soc/codecs/rt722-sdca-sdw.c | 4 +++- 12 files changed, 36 insertions(+), 12 deletions(-) diff --git a/sound/soc/codecs/rt1017-sdca-sdw.c b/sound/soc/codecs/rt1017-sdca-sdw.c index d62e8a253676..91d3d43cd998 100644 --- a/sound/soc/codecs/rt1017-sdca-sdw.c +++ b/sound/soc/codecs/rt1017-sdca-sdw.c @@ -779,8 +779,10 @@ static int rt1017_sdca_dev_resume(struct device *dev) return 0; ret = sdw_slave_wait_for_init(slave, RT1017_PROBE_TIMEOUT); - if (ret) + if (ret) { + sdw_show_ping_status(slave->bus, true); return ret; + } regcache_cache_only(rt1017->regmap, false); regcache_sync(rt1017->regmap); diff --git a/sound/soc/codecs/rt1308-sdw.c b/sound/soc/codecs/rt1308-sdw.c index 39e06a3a7560..60e5040b6dd9 100644 --- a/sound/soc/codecs/rt1308-sdw.c +++ b/sound/soc/codecs/rt1308-sdw.c @@ -774,8 +774,10 @@ static int rt1308_dev_resume(struct device *dev) return 0; ret = sdw_slave_wait_for_init(slave, RT1308_PROBE_TIMEOUT); - if (ret) + if (ret) { + sdw_show_ping_status(slave->bus, true); return ret; + } regcache_cache_only(rt1308->regmap, false); regcache_sync_region(rt1308->regmap, 0xc000, 0xcfff); diff --git a/sound/soc/codecs/rt1316-sdw.c b/sound/soc/codecs/rt1316-sdw.c index 1828fd9d5af6..5e8eda6a5f7f 100644 --- a/sound/soc/codecs/rt1316-sdw.c +++ b/sound/soc/codecs/rt1316-sdw.c @@ -751,8 +751,10 @@ static int rt1316_dev_resume(struct device *dev) return 0; ret = sdw_slave_wait_for_init(slave, RT1316_PROBE_TIMEOUT); - if (ret) + if (ret) { + sdw_show_ping_status(slave->bus, true); return ret; + } regcache_cache_only(rt1316->regmap, false); regcache_sync(rt1316->regmap); diff --git a/sound/soc/codecs/rt5682-sdw.c b/sound/soc/codecs/rt5682-sdw.c index ec2a35a0cacd..dec8c2147d68 100644 --- a/sound/soc/codecs/rt5682-sdw.c +++ b/sound/soc/codecs/rt5682-sdw.c @@ -769,8 +769,10 @@ static int rt5682_dev_resume(struct device *dev) } ret = sdw_slave_wait_for_init(slave, RT5682_PROBE_TIMEOUT); - if (ret) + if (ret) { + sdw_show_ping_status(slave->bus, true); return ret; + } regcache_cache_only(rt5682->sdw_regmap, false); regcache_cache_only(rt5682->regmap, false); diff --git a/sound/soc/codecs/rt700-sdw.c b/sound/soc/codecs/rt700-sdw.c index 30fcca210f05..6bc636c86f42 100644 --- a/sound/soc/codecs/rt700-sdw.c +++ b/sound/soc/codecs/rt700-sdw.c @@ -528,8 +528,10 @@ static int rt700_dev_resume(struct device *dev) return 0; ret = sdw_slave_wait_for_init(slave, RT700_PROBE_TIMEOUT); - if (ret) + if (ret) { + sdw_show_ping_status(slave->bus, true); return ret; + } regcache_cache_only(rt700->regmap, false); regcache_sync_region(rt700->regmap, 0x3000, 0x8fff); diff --git a/sound/soc/codecs/rt711-sdca-sdw.c b/sound/soc/codecs/rt711-sdca-sdw.c index a8164fc3979a..461315844ba9 100644 --- a/sound/soc/codecs/rt711-sdca-sdw.c +++ b/sound/soc/codecs/rt711-sdca-sdw.c @@ -454,8 +454,10 @@ static int rt711_sdca_dev_resume(struct device *dev) } ret = sdw_slave_wait_for_init(slave, RT711_PROBE_TIMEOUT); - if (ret) + if (ret) { + sdw_show_ping_status(slave->bus, true); return ret; + } regcache_cache_only(rt711->regmap, false); regcache_sync(rt711->regmap); diff --git a/sound/soc/codecs/rt712-sdca-dmic.c b/sound/soc/codecs/rt712-sdca-dmic.c index 4c5c2f5ba5ed..8b7d50a80ff9 100644 --- a/sound/soc/codecs/rt712-sdca-dmic.c +++ b/sound/soc/codecs/rt712-sdca-dmic.c @@ -911,8 +911,10 @@ static int rt712_sdca_dmic_dev_resume(struct device *dev) return 0; ret = sdw_slave_wait_for_init(slave, RT712_PROBE_TIMEOUT); - if (ret) + if (ret) { + sdw_show_ping_status(slave->bus, true); return ret; + } regcache_cache_only(rt712->regmap, false); regcache_sync(rt712->regmap); diff --git a/sound/soc/codecs/rt712-sdca-sdw.c b/sound/soc/codecs/rt712-sdca-sdw.c index 581732180473..2787524c796e 100644 --- a/sound/soc/codecs/rt712-sdca-sdw.c +++ b/sound/soc/codecs/rt712-sdca-sdw.c @@ -467,8 +467,10 @@ static int rt712_sdca_dev_resume(struct device *dev) } ret = sdw_slave_wait_for_init(slave, RT712_PROBE_TIMEOUT); - if (ret) + if (ret) { + sdw_show_ping_status(slave->bus, true); return ret; + } regcache_cache_only(rt712->regmap, false); regcache_sync(rt712->regmap); diff --git a/sound/soc/codecs/rt715-sdca-sdw.c b/sound/soc/codecs/rt715-sdca-sdw.c index 4b9815b5628d..fabd21bbbe5b 100644 --- a/sound/soc/codecs/rt715-sdca-sdw.c +++ b/sound/soc/codecs/rt715-sdca-sdw.c @@ -230,8 +230,10 @@ static int rt715_dev_resume(struct device *dev) return 0; ret = sdw_slave_wait_for_init(slave, RT715_PROBE_TIMEOUT); - if (ret) + if (ret) { + sdw_show_ping_status(slave->bus, true); return ret; + } regcache_cache_only(rt715->regmap, false); regcache_sync_region(rt715->regmap, diff --git a/sound/soc/codecs/rt715-sdw.c b/sound/soc/codecs/rt715-sdw.c index 7f83a8f1a06e..a4a3945522e8 100644 --- a/sound/soc/codecs/rt715-sdw.c +++ b/sound/soc/codecs/rt715-sdw.c @@ -507,8 +507,10 @@ static int rt715_dev_resume(struct device *dev) return 0; ret = sdw_slave_wait_for_init(slave, RT715_PROBE_TIMEOUT); - if (ret) + if (ret) { + sdw_show_ping_status(slave->bus, true); return ret; + } regcache_cache_only(rt715->regmap, false); regcache_sync_region(rt715->regmap, 0x3000, 0x8fff); diff --git a/sound/soc/codecs/rt721-sdca-sdw.c b/sound/soc/codecs/rt721-sdca-sdw.c index 58606209316a..02df04a0ddad 100644 --- a/sound/soc/codecs/rt721-sdca-sdw.c +++ b/sound/soc/codecs/rt721-sdca-sdw.c @@ -505,8 +505,10 @@ static int rt721_sdca_dev_resume(struct device *dev) } ret = sdw_slave_wait_for_init(slave, RT721_PROBE_TIMEOUT); - if (ret) + if (ret) { + sdw_show_ping_status(slave->bus, true); return ret; + } regcache_cache_only(rt721->regmap, false); regcache_sync(rt721->regmap); diff --git a/sound/soc/codecs/rt722-sdca-sdw.c b/sound/soc/codecs/rt722-sdca-sdw.c index 0f76492ff915..284900933ebf 100644 --- a/sound/soc/codecs/rt722-sdca-sdw.c +++ b/sound/soc/codecs/rt722-sdca-sdw.c @@ -552,8 +552,10 @@ static int rt722_sdca_dev_resume(struct device *dev) } ret = sdw_slave_wait_for_init(slave, RT722_PROBE_TIMEOUT); - if (ret) + if (ret) { + sdw_show_ping_status(slave->bus, true); return ret; + } regcache_cache_only(rt722->regmap, false); regcache_sync(rt722->regmap); From 68ff4a3ccda9f98c74f23c70c8c7c581f9eee931 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Wed, 17 Jun 2026 18:16:16 +0200 Subject: [PATCH 204/297] cpuidle: Allow exit latency to exceed target residency Commit 76934e495cdc ("cpuidle: Add sanity check for exit latency and target residency") had added a check to prevent the exit latency of an idle state from exceeding its target residency that later was limited to printing a warning message in that case in commit 4bf944f3fcb6 ("cpuidle: Warn instead of bailing out if target residency check fails"). However, a thorough code inspection with that in mind leads to the conclusion that actually there are no assumptions in cpuidle regarding the relationship between the exit latency and target residency of a given idle state. It is generally assumed that the idle states table provided by a cpuidle driver will be sorted by both the target residency and exit latency in ascending order, but that's a different matter. Accordingly, drop the check in question along with the message printed when it triggers and the inaccurate comment preceding it. Fixes: 4bf944f3fcb6 ("cpuidle: Warn instead of bailing out if target residency check fails") Signed-off-by: Rafael J. Wysocki Reviewed-by: Christian Loehle [ rjw: Subject fixup ] Link: https://patch.msgid.link/3444162.aeNJFYEL58@rafael.j.wysocki Signed-off-by: Rafael J. Wysocki --- drivers/cpuidle/driver.c | 8 -------- 1 file changed, 8 deletions(-) diff --git a/drivers/cpuidle/driver.c b/drivers/cpuidle/driver.c index 370664c47e65..e355b42043cf 100644 --- a/drivers/cpuidle/driver.c +++ b/drivers/cpuidle/driver.c @@ -195,14 +195,6 @@ static void __cpuidle_driver_init(struct cpuidle_driver *drv) s->exit_latency_ns = 0; else s->exit_latency = div_u64(s->exit_latency_ns, NSEC_PER_USEC); - - /* - * Warn if the exit latency of a CPU idle state exceeds its - * target residency which is assumed to never happen in cpuidle - * in multiple places. - */ - if (s->exit_latency_ns > s->target_residency_ns) - pr_warn("Idle state %d target residency too low\n", i); } } From 1ce42a11bed134903e352010a01fa53073a6b395 Mon Sep 17 00:00:00 2001 From: HyeongJun An Date: Tue, 23 Jun 2026 20:05:26 +0900 Subject: [PATCH 205/297] ASoC: SDCA: Validate written enum value in ge_put_enum_double() ge_put_enum_double() passes the user-supplied enumeration index item[0] to snd_soc_enum_item_to_val() without checking it against the number of items in the enum: ret = snd_soc_enum_item_to_val(e, item[0]); snd_soc_enum_item_to_val() indexes the heap-allocated e->values[] array with that index (e->values is set from a devm_kcalloc() of e->items entries), so a control write with an out-of-range item[0] reads past the end of the values buffer. The bounds check in snd_soc_dapm_put_enum_double() only runs afterwards, so it does not prevent the read here. Reject an out-of-range item before using it, matching the other enum put handlers. This issue was pointed out by the Sashiko AI review bot while reviewing a related enum-validation series: https://lore.kernel.org/all/20260609125735.CEB651F00893@smtp.kernel.org/ Fixes: 812ff1baa764 ("ASoC: SDCA: Limit values user can write to Selected Mode") Signed-off-by: HyeongJun An Reviewed-by: Charles Keepax Link: https://patch.msgid.link/20260623110526.813217-1-sammiee5311@gmail.com Signed-off-by: Mark Brown --- sound/soc/sdca/sdca_asoc.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/sound/soc/sdca/sdca_asoc.c b/sound/soc/sdca/sdca_asoc.c index e76afa396b0a..b4dedba719dc 100644 --- a/sound/soc/sdca/sdca_asoc.c +++ b/sound/soc/sdca/sdca_asoc.c @@ -160,6 +160,9 @@ static int ge_put_enum_double(struct snd_kcontrol *kcontrol, unsigned int reg = e->reg; int ret; + if (item[0] >= e->items) + return -EINVAL; + reg &= ~SDW_SDCA_CTL_CSEL(0x3F); reg |= SDW_SDCA_CTL_CSEL(SDCA_CTL_GE_DETECTED_MODE); From e26bb459d0f3dad83c6a31d5e4480e60760c262b Mon Sep 17 00:00:00 2001 From: Bartosz Juraszewski Date: Mon, 22 Jun 2026 20:27:33 +0200 Subject: [PATCH 206/297] ASoC: tas2783: Update loaded firmware names to linux-firmware 20260519 In linux-firmware commit from 2026-05-19 `2f90f4fe5c67f51a8410907a...` `ASoC: tas2783: Add Firmware files for tas2783A projects` by Baojun Xu 138 new firmware files for tas2783 were added, none of which are loaded by the kernel. Kernel expects files to be named with the following convention: "%04X-%1X-%1X.bin". However the added firmware files follow "-0x%1X.bin" naming instead with `0x` hex prefix, which fails to load resulting in following dmesg log: slave-tas2783 sdw:0:1:0102:0000:01:8: Direct firmware load for 1714-1-8.bin failed with error -2 slave-tas2783 sdw:0:1:0102:0000:01:8: Failed to read fw binary 1714-1-8.bin slave-tas2783 sdw:0:1:0102:0000:01:b: Direct firmware load for 1714-1-B.bin failed with error -2 slave-tas2783 sdw:0:1:0102:0000:01:b: Failed to read fw binary 1714-1-B.bin slave-tas2783 sdw:0:1:0102:0000:01:8: error playback without fw download slave-tas2783 sdw:0:1:0102:0000:01:8: ASoC error (-22): at snd_soc_dai_hw_params() on tas2783-codec This same commit removes all 22 symlinks from WHENCE, that used naming without the '0x' prefix to only 6 prevoiusly existing .bin files. This patch adds `0x` prefix explicitly to the generated firmware name allowing file to successfully load. In case prefixed firmware is missing due to out of date linux-firmware, we set the fallback flag and attempt to load firmware again based on the old file names. This prefix change results in functioning firmware loading on ASUS ProArt PX13 HN7306EAC, which uses 1714-1-0x8.bin and 1714-1-0xB.bin firmware files. Tested on top of 7.1 and next-20260619 with SND_SOC_AMD_ACP7X set to no. Signed-off-by: Bartosz Juraszewski Link: https://patch.msgid.link/20260622182733.23947-1-bjuraszewski@gmail.com Signed-off-by: Mark Brown --- sound/soc/codecs/tas2783-sdw.c | 73 +++++++++++++++++++++++----------- 1 file changed, 50 insertions(+), 23 deletions(-) diff --git a/sound/soc/codecs/tas2783-sdw.c b/sound/soc/codecs/tas2783-sdw.c index 1127ea59b5e4..3d0b116544cc 100644 --- a/sound/soc/codecs/tas2783-sdw.c +++ b/sound/soc/codecs/tas2783-sdw.c @@ -100,6 +100,8 @@ struct tas2783_prv { wait_queue_head_t fw_wait; bool fw_dl_task_done; bool fw_dl_success; + /* use fallback fw name */ + bool fw_use_fallback; }; static const struct reg_default tas2783_reg_default[] = { @@ -740,11 +742,19 @@ static void tas2783_fw_ready(const struct firmware *fmw, void *context) goto out; } + /* firmware binary not found*/ if (!fmw || !fmw->data) { - /* firmware binary not found*/ - dev_err(tas_dev->dev, - "Failed to read fw binary %s\n", - tas_dev->rca_binaryname); + if (!tas_dev->fw_use_fallback) { + tas_dev->fw_use_fallback = true; + dev_info(tas_dev->dev, + "Failed to read preferred fw binary: %s, attempting fallback binary load\n", + tas_dev->rca_binaryname); + } else { + dev_err(tas_dev->dev, + "Failed to read fallback fw binary %s\n", + tas_dev->rca_binaryname); + } + ret = -EINVAL; goto out; } @@ -1105,13 +1115,16 @@ static void tas_generate_fw_name(struct sdw_slave *slave, char *name, size_t siz bool pci_found = false; #if IS_ENABLED(CONFIG_PCI) struct device *dev = &slave->dev; + struct tas2783_prv *tas_dev = dev_get_drvdata(&slave->dev); struct pci_dev *pci = NULL; + const char *fw_uid_prefix = tas_dev->fw_use_fallback ? "" : "0x"; for (; dev; dev = dev->parent) { if (dev->bus == &pci_bus_type) { pci = to_pci_dev(dev); - scnprintf(name, size, "%04X-%1X-%1X.bin", - pci->subsystem_device, bus->link_id, unique_id); + scnprintf(name, size, "%04X-%1X-%s%1X.bin", + pci->subsystem_device, bus->link_id, + fw_uid_prefix, unique_id); pci_found = true; break; } @@ -1123,28 +1136,15 @@ static void tas_generate_fw_name(struct sdw_slave *slave, char *name, size_t siz bus->link_id, unique_id); } -static s32 tas_io_init(struct device *dev, struct sdw_slave *slave) +static s32 tas_fw_load(struct tas2783_prv *tas_dev, struct sdw_slave *slave) { - struct tas2783_prv *tas_dev = dev_get_drvdata(dev); s32 ret; u8 unique_id = tas_dev->sdw_peripheral->id.unique_id; - if (tas_dev->hw_init) - return 0; - - tas_dev->fw_dl_task_done = false; - tas_dev->fw_dl_success = false; - - ret = regmap_write(tas_dev->regmap, TAS2783_SW_RESET, 0x1); - if (ret) { - dev_err(dev, "sw reset failed, err=%d", ret); - return ret; - } - usleep_range(2000, 2200); - tas_generate_fw_name(slave, tas_dev->rca_binaryname, sizeof(tas_dev->rca_binaryname)); + tas_dev->fw_dl_task_done = false; ret = request_firmware_nowait(THIS_MODULE, FW_ACTION_UEVENT, tas_dev->rca_binaryname, tas_dev->dev, GFP_KERNEL, tas_dev, tas2783_fw_ready); @@ -1159,8 +1159,35 @@ static s32 tas_io_init(struct device *dev, struct sdw_slave *slave) msecs_to_jiffies(TIMEOUT_FW_DL_MS)); if (!ret) { dev_err(tas_dev->dev, "fw request, wait_event timeout\n"); - ret = -EAGAIN; - } else { + return -EAGAIN; + } + + return 0; +} + +static s32 tas_io_init(struct device *dev, struct sdw_slave *slave) +{ + struct tas2783_prv *tas_dev = dev_get_drvdata(dev); + s32 ret; + + if (tas_dev->hw_init) + return 0; + + tas_dev->fw_dl_success = false; + + ret = regmap_write(tas_dev->regmap, TAS2783_SW_RESET, 0x1); + if (ret) { + dev_err(dev, "sw reset failed, err=%d", ret); + return ret; + } + usleep_range(2000, 2200); + + tas_dev->fw_use_fallback = false; + ret = tas_fw_load(tas_dev, slave); + if (!ret && tas_dev->fw_use_fallback) + ret = tas_fw_load(tas_dev, slave); + + if (!ret) { if (tas_dev->sa_func_data) ret = sdca_regmap_write_init(dev, tas_dev->regmap, tas_dev->sa_func_data); From d0c415f0076b71b956f62ff6f31de885f0fa2489 Mon Sep 17 00:00:00 2001 From: Oder Chiou Date: Tue, 23 Jun 2026 18:25:14 +0800 Subject: [PATCH 207/297] ASoC: rt5575: Use __le32 for SPI burst write address The addr field in the SPI burst write buffer represents on-wire little-endian data. Define it as __le32 so that the assignment of cpu_to_le32() is type correct and avoids sparse endian warnings. Closes: https://lore.kernel.org/oe-kbuild-all/202606230139.rFZUVpCa-lkp@intel.com/ Fixes: 420739112e95 ("ASoC: rt5575: Add the codec driver for the ALC5575") Reported-by: kernel test robot Signed-off-by: Oder Chiou Link: https://patch.msgid.link/20260623102514.2422990-1-oder_chiou@realtek.com Signed-off-by: Mark Brown --- sound/soc/codecs/rt5575-spi.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/soc/codecs/rt5575-spi.c b/sound/soc/codecs/rt5575-spi.c index 9a349965435b..d5b3a57c8866 100644 --- a/sound/soc/codecs/rt5575-spi.c +++ b/sound/soc/codecs/rt5575-spi.c @@ -17,7 +17,7 @@ struct rt5575_spi_burst_write { u8 cmd; - u32 addr; + __le32 addr; u8 data[RT5575_SPI_BUF_LEN]; u8 dummy; } __packed; From 2e9a7f68329be41792c0b123c28e6c53c2fa2249 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Thu, 18 Jun 2026 16:49:34 +0200 Subject: [PATCH 208/297] i2c: mpc: Fix timeout calculations At first glance the harmless cleanup of the driver does nothing bad. However, as the operator precedence list states the '*' (multiplication) and '/' division operators have order 5 with left-to-right associativity the *= has order 17 and associativity right-to-left. It wouldn't be a problem to replace foo = foo * HZ / 1000000; with foo *= HZ / 1000000; if HZ constant is in Hertz. The problem is that in the Linux kernel HZ is defined in jiffy units, which is order of magnitude smaller than a million. That's why operator precedence has a crucial role here. Fix the regression by reverting pre-optimized calculations. Fixes: be40a3ae719f ("i2c: mpc: Use of_property_read_u32 instead of of_get_property") Signed-off-by: Andy Shevchenko Cc: # v6.4+ Reviewed-by: Chris Packham Signed-off-by: Andi Shyti Link: https://lore.kernel.org/r/20260618144934.3249950-1-andriy.shevchenko@linux.intel.com --- drivers/i2c/busses/i2c-mpc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/i2c/busses/i2c-mpc.c b/drivers/i2c/busses/i2c-mpc.c index 28c5c5c1fb7a..a21fa45bd64c 100644 --- a/drivers/i2c/busses/i2c-mpc.c +++ b/drivers/i2c/busses/i2c-mpc.c @@ -844,7 +844,7 @@ static int fsl_i2c_probe(struct platform_device *op) "fsl,timeout", &mpc_ops.timeout); if (!result) { - mpc_ops.timeout *= HZ / 1000000; + mpc_ops.timeout = mpc_ops.timeout * HZ / 1000000; if (mpc_ops.timeout < 5) mpc_ops.timeout = 5; } else { From 10dd1a736d557e310a77117832874729a0175d57 Mon Sep 17 00:00:00 2001 From: Mingyu Wang <25181214217@stu.xidian.edu.cn> Date: Tue, 12 May 2026 17:35:34 +0800 Subject: [PATCH 209/297] i2c: i801: fix hardware state machine corruption in error path A severe livelock and subsequent Hung Task panic were observed in the i2c-i801 driver during concurrent Fuzzing. The crash is caused by an unconditional hardware register cleanup in the error handling path of i801_access(). When i801_check_pre() fails (e.g., returning -EBUSY because the SMBus controller is actively used by BIOS/ACPI), the kernel does not actually acquire the hardware ownership. However, the code jumps to the 'out' label and executes: iowrite8(SMBHSTSTS_INUSE_STS | STATUS_FLAGS, SMBHSTSTS(priv)); This forcefully clears the INUSE_STS lock and resets the hardware status flags without owning the controller. Doing so interrupts ongoing BIOS/ACPI transactions and totally corrupts the SMBus hardware state machine. Consequently, all subsequent i801_access() calls fail at the pre-check stage, triggering an endless stream of "SMBus is busy, can't use it!" error logs. Over a slow serial console, this printk flood monopolizes the CPU (Console Livelock), starving other processes trying to acquire the mmap_lock down_read semaphore, ultimately triggering the hung task watchdog. Fix this by moving the 'out' label below the hardware register cleanup. If i801_check_pre() fails, we safely bypass the iowrite8() and only release the software locks (pm_runtime and mutex), strictly adhering to the rule of not releasing resources that were never acquired. Fixes: 1f760b87e54c ("i2c: i801: Call i801_check_pre() from i801_access()") Signed-off-by: Mingyu Wang <25181214217@stu.xidian.edu.cn> Cc: # v6.3+ Signed-off-by: Andi Shyti Link: https://lore.kernel.org/r/20260512093534.348655-1-w15303746062@163.com --- drivers/i2c/busses/i2c-i801.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/i2c/busses/i2c-i801.c b/drivers/i2c/busses/i2c-i801.c index 32a3cef02c7b..b29c99ed3883 100644 --- a/drivers/i2c/busses/i2c-i801.c +++ b/drivers/i2c/busses/i2c-i801.c @@ -931,13 +931,13 @@ static s32 i801_access(struct i2c_adapter *adap, u16 addr, */ if (hwpec) iowrite8(ioread8(SMBAUXCTL(priv)) & ~SMBAUXCTL_CRC, SMBAUXCTL(priv)); -out: /* * Unlock the SMBus device for use by BIOS/ACPI, * and clear status flags if not done already. */ iowrite8(SMBHSTSTS_INUSE_STS | STATUS_FLAGS, SMBHSTSTS(priv)); +out: pm_runtime_put_autosuspend(&priv->pci_dev->dev); mutex_unlock(&priv->acpi_lock); return ret; From 954d196bebb2b50151cb96454c72dc113b2af1ac Mon Sep 17 00:00:00 2001 From: Haofeng Li Date: Tue, 23 Jun 2026 09:30:26 +0800 Subject: [PATCH 210/297] ksmbd: validate NTLMv2 response before updating session key ksmbd_auth_ntlmv2() derives the NTLMv2 session key into sess->sess_key before it verifies the NTLMv2 response. ksmbd_decode_ntlmssp_auth_blob() then continues into KEY_XCH even when ksmbd_auth_ntlmv2() failed. With SMB3 multichannel binding, the failed authentication operates on an existing session and the session setup error path does not expire binding sessions. A client can send a binding session setup with a bad NT proof and KEY_XCH and still modify sess->sess_key before STATUS_LOGON_FAILURE is returned. Relevant path: smb2_sess_setup() -> conn->binding = true -> ntlm_authenticate() -> session_user() -> ksmbd_decode_ntlmssp_auth_blob() -> ksmbd_auth_ntlmv2() -> calc_ntlmv2_hash() -> hmac_md5_usingrawkey(..., sess->sess_key) -> crypto_memneq() returns mismatch -> KEY_XCH arc4_crypt(..., sess->sess_key, ...) -> out_err without expiring the binding session Derive the base session key into a local buffer and copy it to sess->sess_key only after the proof matches. Return immediately on authentication failure so KEY_XCH is only processed after successful authentication. Fixes: e2f34481b24d ("cifsd: add server-side procedures for SMB3") Fixes: f9929ef6a2a5 ("ksmbd: add support for key exchange") Cc: stable@vger.kernel.org Signed-off-by: Haofeng Li Reviewed-by: ChenXiaoSong Acked-by: Namjae Jeon Signed-off-by: Steve French --- fs/smb/server/auth.c | 20 ++++++++++++++++---- 1 file changed, 16 insertions(+), 4 deletions(-) diff --git a/fs/smb/server/auth.c b/fs/smb/server/auth.c index e99409fa721c..86f521e849d5 100644 --- a/fs/smb/server/auth.c +++ b/fs/smb/server/auth.c @@ -142,6 +142,7 @@ int ksmbd_auth_ntlmv2(struct ksmbd_conn *conn, struct ksmbd_session *sess, { char ntlmv2_hash[CIFS_ENCPWD_SIZE]; char ntlmv2_rsp[CIFS_HMAC_MD5_HASH_SIZE]; + char sess_key[SMB2_NTLMV2_SESSKEY_SIZE]; struct hmac_md5_ctx ctx; int rc; @@ -164,12 +165,21 @@ int ksmbd_auth_ntlmv2(struct ksmbd_conn *conn, struct ksmbd_session *sess, /* Generate the session key */ hmac_md5_usingrawkey(ntlmv2_hash, CIFS_HMAC_MD5_HASH_SIZE, ntlmv2_rsp, CIFS_HMAC_MD5_HASH_SIZE, - sess->sess_key); + sess_key); if (crypto_memneq(ntlmv2->ntlmv2_hash, ntlmv2_rsp, - CIFS_HMAC_MD5_HASH_SIZE)) - return -EINVAL; - return 0; + CIFS_HMAC_MD5_HASH_SIZE)) { + rc = -EINVAL; + goto out; + } + + memcpy(sess->sess_key, sess_key, sizeof(sess_key)); + rc = 0; +out: + memzero_explicit(ntlmv2_hash, sizeof(ntlmv2_hash)); + memzero_explicit(ntlmv2_rsp, sizeof(ntlmv2_rsp)); + memzero_explicit(sess_key, sizeof(sess_key)); + return rc; } /** @@ -226,6 +236,8 @@ int ksmbd_decode_ntlmssp_auth_blob(struct authenticate_message *authblob, nt_len - CIFS_ENCPWD_SIZE, domain_name, conn->ntlmssp.cryptkey); kfree(domain_name); + if (ret) + return ret; /* The recovered secondary session key */ if (conn->ntlmssp.client_flags & NTLMSSP_NEGOTIATE_KEY_XCH) { From f455ea21f23e2a82e4adf00d8ee65c268ad82036 Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Tue, 23 Jun 2026 17:21:29 +0900 Subject: [PATCH 211/297] ksmbd: fix inconsistent indenting warnings Detected by Smatch. fs/smb/server/oplock.c:1446 smb_grant_oplock() warn: inconsistent indenting Reported-by: Dan Carpenter Signed-off-by: Namjae Jeon Signed-off-by: Steve French --- fs/smb/server/oplock.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/fs/smb/server/oplock.c b/fs/smb/server/oplock.c index 99cbd7aa03fc..673182f243d6 100644 --- a/fs/smb/server/oplock.c +++ b/fs/smb/server/oplock.c @@ -1443,12 +1443,12 @@ int smb_grant_oplock(struct ksmbd_work *work, int req_op_level, u64 pid, if (m_opinfo) { lease_put(opinfo->o_lease); lease_get(m_opinfo->o_lease); - opinfo->o_lease = m_opinfo->o_lease; - opinfo->level = m_opinfo->level; - new_lease = false; - opinfo_put(m_opinfo); - goto out; - } + opinfo->o_lease = m_opinfo->o_lease; + opinfo->level = m_opinfo->level; + new_lease = false; + opinfo_put(m_opinfo); + goto out; + } } prev_opinfo = opinfo_get_list(ci); if (!prev_opinfo || From da793cf6d60233f47ea5e7e9e39425d71dfcdb79 Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Wed, 24 Jun 2026 05:59:13 +0900 Subject: [PATCH 212/297] ksmbd: fix kernel-doc warnings in smb2_lease_break_noti() kernel test robot report missing kernel-doc descriptions for the 'wait_ack' and 'inc_epoch' parameters of smb2_lease_break_noti(): Warning: fs/smb/server/oplock.c:937 function parameter 'wait_ack' not described in 'smb2_lease_break_noti' Warning: fs/smb/server/oplock.c:937 function parameter 'inc_epoch' not described in 'smb2_lease_break_noti' Document both parameters to silence the warnings. Reported-by: kernel test robot Signed-off-by: Namjae Jeon Signed-off-by: Steve French --- fs/smb/server/oplock.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/smb/server/oplock.c b/fs/smb/server/oplock.c index 673182f243d6..31dd9f3479b2 100644 --- a/fs/smb/server/oplock.c +++ b/fs/smb/server/oplock.c @@ -967,6 +967,8 @@ out: * smb2_lease_break_noti() - break lease when a new client request * write lease * @opinfo: contains lease state information + * @wait_ack: wait for lease break acknowledgment from the client + * @inc_epoch: increment the lease epoch before sending the break * * Return: 0 on success, otherwise error */ From 435990e25bf1f4af3e6df12a6fbfd1f7ba4a97d4 Mon Sep 17 00:00:00 2001 From: HyeongJun An Date: Wed, 24 Jun 2026 08:38:40 +0900 Subject: [PATCH 213/297] ALSA: seq: Fix uninitialised heap leak in snd_seq_event_dup() snd_seq_event_dup() copies an incoming event into a pool cell and, in the UMP-enabled build, clears the trailing cell->ump.raw.extra word that the memcpy() did not cover. The guard deciding whether to clear it compares the copied size against sizeof(cell->event): memcpy(&cell->ump, event, size); if (size < sizeof(cell->event)) cell->ump.raw.extra = 0; For a legacy (non-UMP) event, size == sizeof(struct snd_seq_event) == sizeof(cell->event), so the condition is false and the extra word keeps stale data. The cell pool is allocated with kvmalloc() (not zeroed) and cells are reused via a free list, so that word holds uninitialised heap or leftover event data. When such a cell is delivered to a UMP client (client->midi_version > 0) that set SNDRV_SEQ_FILTER_NO_CONVERT -- so the legacy event reaches it unconverted -- snd_seq_read() reads it out as the larger struct snd_seq_ump_event and copies the stale word to user space, a 4-byte kernel heap infoleak to an unprivileged /dev/snd/seq client. Compare against sizeof(cell->ump) instead, so the trailing word is zeroed for every event shorter than the UMP cell. Fixes: 46397622a3fa ("ALSA: seq: Add UMP support") Cc: stable@vger.kernel.org Assisted-by: Claude:claude-opus-4-8 Signed-off-by: HyeongJun An Link: https://patch.msgid.link/20260623233841.853326-1-sammiee5311@gmail.com Signed-off-by: Takashi Iwai --- sound/core/seq/seq_memory.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/core/seq/seq_memory.c b/sound/core/seq/seq_memory.c index ca9f6db0022c..209b08c2a940 100644 --- a/sound/core/seq/seq_memory.c +++ b/sound/core/seq/seq_memory.c @@ -364,7 +364,7 @@ int snd_seq_event_dup(struct snd_seq_pool *pool, struct snd_seq_event *event, size = snd_seq_event_packet_size(event); memcpy(&cell->ump, event, size); #if IS_ENABLED(CONFIG_SND_SEQ_UMP) - if (size < sizeof(cell->event)) + if (size < sizeof(cell->ump)) cell->ump.raw.extra = 0; #endif From 2ee8dbd880b14fb0b5115bf2353c7900aa33b95b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= Date: Fri, 12 Jun 2026 20:36:48 +0300 Subject: [PATCH 214/297] drm/i915/cdclk: Fix up CDCLK_FREQ_DECIMAL without a full PLL re-enable MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The GOP (and even Bspec on some platforms) is a bit inconsistent on what the CDCLK_FREQ_DECIMAL divider should be. Currently any mismatch there causes a full CDCLK PLL disable+re-enable, which we really don't want to do if any displays are currently active. Let's instead just reprogram CDCLK_FREQ_DECIMAL when that is the only thing amiss. For any other (more serious) mismatch we still punt to the full PLL reprogramming. We also need to tweak the bxt_cdclk_cd2x_pipe() stuff a bit to consistently select pipe==NONE since we have no idea which pipes are enabled at this point. Since we're not actually changing the CDCLK frequency here we don't need to sync the update to any pipe. Closes: https://gitlab.freedesktop.org/drm/i915/kernel/-/work_items/16209 Signed-off-by: Ville Syrjälä Link: https://patch.msgid.link/20260612173653.7830-2-ville.syrjala@linux.intel.com Reviewed-by: Michał Grzelak (cherry picked from commit 3f9de66f8acbf8ff45a91b4920605ed10c6b7c06) Fixes: ba91b9eecb47 ("drm/i915/cdclk: Decouple cdclk from state->modeset") Fixes: d66a21947e21 ("drm/i915/bxt: Sanitize CDCLK to fix breakage during S4 resume") Fixes: c73666f394fc ("drm/i915/skl: If needed sanitize bios programmed cdclk") Cc: # v4.5+ Signed-off-by: Joonas Lahtinen --- drivers/gpu/drm/i915/display/intel_cdclk.c | 41 ++++++++++++++++++---- 1 file changed, 34 insertions(+), 7 deletions(-) diff --git a/drivers/gpu/drm/i915/display/intel_cdclk.c b/drivers/gpu/drm/i915/display/intel_cdclk.c index 189ae2d3cfc9..7bc9b956554b 100644 --- a/drivers/gpu/drm/i915/display/intel_cdclk.c +++ b/drivers/gpu/drm/i915/display/intel_cdclk.c @@ -1256,9 +1256,22 @@ static void skl_sanitize_cdclk(struct intel_display *display) cdctl = intel_de_read(display, CDCLK_CTL); expected = (cdctl & CDCLK_FREQ_SEL_MASK) | skl_cdclk_decimal(display->cdclk.hw.cdclk); - if (cdctl == expected) - /* All well; nothing to sanitize */ - return; + + if (cdctl != expected) { + cdctl &= ~CDCLK_FREQ_DECIMAL_MASK; + cdctl |= expected & CDCLK_FREQ_DECIMAL_MASK; + + if (cdctl != expected) + goto sanitize; + + drm_dbg_kms(display->drm, "Sanitizing CDCLK decimal divider (CDCLK_CTL 0x%x, expected 0x%x)\n", + intel_de_read(display, CDCLK_CTL), expected); + + intel_de_write(display, CDCLK_CTL, expected); + } + + /* All well; nothing to sanitize */ + return; sanitize: drm_dbg_kms(display->drm, "Sanitizing cdclk programmed by pre-os\n"); @@ -2354,11 +2367,25 @@ static void bxt_sanitize_cdclk(struct intel_display *display) * (PIPE_NONE). */ cdctl &= ~bxt_cdclk_cd2x_pipe(display, INVALID_PIPE); - expected &= ~bxt_cdclk_cd2x_pipe(display, INVALID_PIPE); + cdctl |= bxt_cdclk_cd2x_pipe(display, INVALID_PIPE); - if (cdctl == expected) - /* All well; nothing to sanitize */ - return; + if (cdctl != expected) { + if (DISPLAY_VER(display) < 20) { + cdctl &= ~CDCLK_FREQ_DECIMAL_MASK; + cdctl |= expected & CDCLK_FREQ_DECIMAL_MASK; + } + + if (cdctl != expected) + goto sanitize; + + drm_dbg_kms(display->drm, "Sanitizing CDCLK decimal divider (CDCLK_CTL 0x%x, expected 0x%x)\n", + intel_de_read(display, CDCLK_CTL), expected); + + intel_de_write(display, CDCLK_CTL, expected); + } + + /* All well; nothing to sanitize */ + return; sanitize: drm_dbg_kms(display->drm, "Sanitizing cdclk programmed by pre-os\n"); From 7ddbf1cde4a03e36e17d06fbc711870eb0b256d7 Mon Sep 17 00:00:00 2001 From: Pengpeng Hou Date: Wed, 24 Jun 2026 14:00:24 +0800 Subject: [PATCH 215/297] regulator: da9121: Use subvariant ids in the I2C table da9121_i2c_probe() stores i2c_get_match_data() in chip->subvariant_id and da9121_assign_chip_model() switches on DA9121_SUBTYPE_* values. The OF table provides those subvariant values, but the I2C id table currently provides DA9121_TYPE_* values. Make the I2C id table use the same subvariant namespace as the OF table so non-DT I2C matches feed the expected data type into the model assignment code. Signed-off-by: Pengpeng Hou Link: https://patch.msgid.link/20260624060024.61300-1-pengpeng@iscas.ac.cn Signed-off-by: Mark Brown --- drivers/regulator/da9121-regulator.c | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) diff --git a/drivers/regulator/da9121-regulator.c b/drivers/regulator/da9121-regulator.c index 2b150bb4d471..36a52f707602 100644 --- a/drivers/regulator/da9121-regulator.c +++ b/drivers/regulator/da9121-regulator.c @@ -1195,15 +1195,15 @@ static void da9121_i2c_remove(struct i2c_client *i2c) } static const struct i2c_device_id da9121_i2c_id[] = { - {"da9121", DA9121_TYPE_DA9121_DA9130}, - {"da9130", DA9121_TYPE_DA9121_DA9130}, - {"da9217", DA9121_TYPE_DA9217}, - {"da9122", DA9121_TYPE_DA9122_DA9131}, - {"da9131", DA9121_TYPE_DA9122_DA9131}, - {"da9220", DA9121_TYPE_DA9220_DA9132}, - {"da9132", DA9121_TYPE_DA9220_DA9132}, - {"da9141", DA9121_TYPE_DA9141}, - {"da9142", DA9121_TYPE_DA9142}, + {"da9121", DA9121_SUBTYPE_DA9121}, + {"da9130", DA9121_SUBTYPE_DA9130}, + {"da9217", DA9121_SUBTYPE_DA9217}, + {"da9122", DA9121_SUBTYPE_DA9122}, + {"da9131", DA9121_SUBTYPE_DA9131}, + {"da9220", DA9121_SUBTYPE_DA9220}, + {"da9132", DA9121_SUBTYPE_DA9132}, + {"da9141", DA9121_SUBTYPE_DA9141}, + {"da9142", DA9121_SUBTYPE_DA9142}, {}, }; MODULE_DEVICE_TABLE(i2c, da9121_i2c_id); From 83d53eca7e5512b53ecef6cf67ea8cbfb595516e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig=20=28The=20Capable=20Hub=29?= Date: Wed, 24 Jun 2026 10:37:07 +0200 Subject: [PATCH 216/297] ASoC: rockchip: rockchip_sai: #include explicitly MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Currently that header is only included via: -> -> which doesn't look reliable, still more in the presence of the comment: /* For the current users of sound/soc.h to avoid build issues */ in . Signed-off-by: Uwe Kleine-König (The Capable Hub) Reviewed-by: Nicolas Frattaroli Link: https://patch.msgid.link/20260624083708.254517-2-u.kleine-koenig@baylibre.com Signed-off-by: Mark Brown --- sound/soc/rockchip/rockchip_sai.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/soc/rockchip/rockchip_sai.c b/sound/soc/rockchip/rockchip_sai.c index ed393e5034a4..585e89f61f0d 100644 --- a/sound/soc/rockchip/rockchip_sai.c +++ b/sound/soc/rockchip/rockchip_sai.c @@ -11,6 +11,7 @@ #include #include #include +#include #include #include #include From a7ea04d1ad39d60da397de75b503062ad5fa562b Mon Sep 17 00:00:00 2001 From: Richard Fitzgerald Date: Tue, 23 Jun 2026 14:58:21 +0100 Subject: [PATCH 217/297] ASoC: soc-core: Don't fail if device_link could not be created If device_link_add() fails in snd_soc_bind_card() just skip that driver pair and carry on. This means that ASoC must now keep track of which components it was able to device_link to the card->dev. The new card_device_link member of struct snd_soc_component is non-NULL if a device_link exists. The intent of the device link is to ensure that the machine driver system-suspends before the component drivers, to prevent ASoC suspend attempting to reconfigure a driver that has already suspended. It isn't possible to create this device link if the machine driver is a parent of the component driver or already has a device_link in the opposite direction. In this case skip the link. A warn is placed in kernel log since this might indicate a genuine design problem with those two drivers (this can be downgraded to dbg in future when people are happy that all these special drivers correctly handle their reversed shutdown order). Fixes: 0f54ce994b23 ("ASoC: soc-core: Create device_link to ensure correct suspend order") Reported-by: Marek Szyprowski Closes: https://lore.kernel.org/linux-sound/61bd38e7-5eb9-4448-a93f-afa2ccbd1c9d@opensource.cirrus.com/T/#m496fe5a11b0a3649afd2e85da5e1cea82bb16d8a Tested-by: Marek Szyprowski Signed-off-by: Richard Fitzgerald Link: https://patch.msgid.link/20260623135821.4125543-1-rf@opensource.cirrus.com Signed-off-by: Mark Brown --- include/sound/soc-component.h | 4 ++++ sound/soc/soc-core.c | 35 +++++++++++++++-------------------- 2 files changed, 19 insertions(+), 20 deletions(-) diff --git a/include/sound/soc-component.h b/include/sound/soc-component.h index 11bc9527653f..aa423865dbe7 100644 --- a/include/sound/soc-component.h +++ b/include/sound/soc-component.h @@ -10,6 +10,8 @@ #include +struct device_link; + /* * Component probe and remove ordering levels for components with runtime * dependencies. @@ -216,6 +218,8 @@ struct snd_soc_component { struct list_head card_aux_list; /* for auxiliary bound components */ struct list_head card_list; + struct device_link *card_device_link; + const struct snd_soc_component_driver *driver; struct list_head dai_list; diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c index 86b6c752a56b..7817beea5b3b 100644 --- a/sound/soc/soc-core.c +++ b/sound/soc/soc-core.c @@ -1980,19 +1980,15 @@ static void soc_cleanup_card_resources(struct snd_soc_card *card) } } -static void snd_soc_remove_device_links(struct snd_soc_card *card, - struct snd_soc_component *stop_at) +static void snd_soc_remove_device_links(struct snd_soc_card *card) { struct snd_soc_component *component; for_each_card_components(card, component) { - if (card->dev == component->dev) - continue; - - device_link_remove(card->dev, component->dev); - - if (component == stop_at) - return; + if (component->card_device_link) { + device_link_del(component->card_device_link); + component->card_device_link = NULL; + } } } @@ -2001,7 +1997,7 @@ static void snd_soc_unbind_card(struct snd_soc_card *card) if (snd_soc_card_is_instantiated(card)) { card->instantiated = false; - snd_soc_remove_device_links(card, NULL); + snd_soc_remove_device_links(card); soc_cleanup_card_resources(card); } @@ -2012,7 +2008,6 @@ static int snd_soc_bind_card(struct snd_soc_card *card) struct snd_soc_pcm_runtime *rtd; struct snd_soc_component *component; struct snd_soc_dapm_context *dapm = snd_soc_card_to_dapm(card); - struct snd_soc_component *last_devlinked_component = NULL; int ret; snd_soc_card_mutex_lock_root(card); @@ -2141,19 +2136,21 @@ static int snd_soc_bind_card(struct snd_soc_card *card) * Add device_link from card to component so that system_suspend * will be done in the correct order. The card must suspend first * to stop audio activity before the components suspend. + * + * If a driver pair already have a link in the opposite direction + * they must manage their own suspend order. */ for_each_card_components(card, component) { if (card->dev == component->dev) continue; - if (!device_link_add(card->dev, component->dev, DL_FLAG_STATELESS)) { - dev_warn(card->dev, "Failed to create device link to %s\n", + component->card_device_link = device_link_add(card->dev, + component->dev, + DL_FLAG_STATELESS); + if (!component->card_device_link) { + dev_warn(card->dev, "Could not create device link to %s\n", dev_name(component->dev)); - ret = -EINVAL; - goto probe_end; } - - last_devlinked_component = component; } ret = snd_soc_card_late_probe(card); @@ -2185,9 +2182,7 @@ static int snd_soc_bind_card(struct snd_soc_card *card) probe_end: if (ret < 0) { - if (last_devlinked_component) - snd_soc_remove_device_links(card, last_devlinked_component); - + snd_soc_remove_device_links(card); soc_cleanup_card_resources(card); } From f36cb64bd39deecde690efadf4a5d6f8155fcb93 Mon Sep 17 00:00:00 2001 From: Alban Bedel Date: Thu, 18 Jun 2026 17:20:34 +0200 Subject: [PATCH 218/297] of: property: Fix of_fwnode_get_reference_args() with negative index fwnode_property_get_reference_args() should return -ENOENT when an out of bound index is passed. An issue arised with the OF backend because the OF API use signed indexes while the fwnode API use unsigned ones. When an index value greater the INT_MAX was passed to the OF backend it got casted to a negative value and it returned -EINVAL instead of -ENOENT. This patch add a check to of_fwnode_get_reference_args() to catch negative index before they are passed to the OF API and return -ENOENT right away. This issue appeared when the following pattern was used in the LED subsystem: index = fwnode_property_match_string(fwnode, "led-names", name) led_node = fwnode_find_reference(fwnode, "leds", index); Unlike the same pattern with the OF API, this pattern implicitly cast the signed return value of fwnode_property_match_string() to an unsigned index leading to the above issue with the OF backend. It can be argued that the return value of fwnode_property_match_string() should be checked separately, but I think there is value in supporting such simple and straight to the point patterns. Link: https://lore.kernel.org/linux-leds/aimVRwJPhlGxsIUj@tom-desktop/T/#mc43cbf7e0599991b56dd0d9680714d28d145fbc8 Cc: Tommaso Merciai Reviewed-by: Krzysztof Kozlowski Signed-off-by: Alban Bedel Link: https://patch.msgid.link/20260618152035.1600436-1-alban.bedel@lht.dlh.de Signed-off-by: Rob Herring (Arm) --- drivers/of/property.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/drivers/of/property.c b/drivers/of/property.c index b276d1de3222..72cf12907de0 100644 --- a/drivers/of/property.c +++ b/drivers/of/property.c @@ -1172,6 +1172,14 @@ of_fwnode_get_reference_args(const struct fwnode_handle *fwnode, unsigned int i; int ret; + /* + * This function should return -ENOENT for out of bound indexes, + * but the OF API uses signed indexes and consider negative indexes + * as invalid. Catch them here to correctly implement the fwnode API. + */ + if ((int)index < 0) + return -ENOENT; + if (nargs_prop) ret = of_parse_phandle_with_args(to_of_node(fwnode), prop, nargs_prop, index, &of_args); From a67963e9cbdd1ab44e64af0fefef3027c3fad74e Mon Sep 17 00:00:00 2001 From: Vijayanand Jitta Date: Fri, 19 Jun 2026 11:16:47 +0530 Subject: [PATCH 219/297] of: Fix RST inline emphasis warnings in of_map_id() kernel-doc The @filter_np parameter descriptions in of_map_id() and of_map_msi_id() contained the text '*filter_np' in prose. Docutils interprets a leading '*' as the start of RST emphasis (italic), but finds no closing '*', triggering: Documentation/devicetree/kernel-api:11: ./drivers/of/base.c:2134: WARNING: Inline emphasis start-string without end-string. [docutils] Documentation/devicetree/kernel-api:11: ./drivers/of/base.c:2260: WARNING: Inline emphasis start-string without end-string. [docutils] Fix by wrapping '*filter_np' in double backticks (*filter_np) to render it as an RST inline code literal, which is also the correct kernel-doc convention for pointer expressions. Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-kbuild-all/202606130111.ldC96rqf-lkp@intel.com/ Signed-off-by: Vijayanand Jitta Link: https://patch.msgid.link/20260619-iommu_map_kdoc_fix-v1-1-9573e1cf30b3@oss.qualcomm.com Signed-off-by: Rob Herring (Arm) --- drivers/of/base.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/of/base.c b/drivers/of/base.c index 7cb0d7e88247..6e7a42dedad3 100644 --- a/drivers/of/base.c +++ b/drivers/of/base.c @@ -2160,7 +2160,7 @@ static bool of_check_bad_map(const __be32 *map, int len) * @map_mask_name: optional property name of the mask to use. * @filter_np: pointer to an optional filter node, or NULL to allow bypass. * If non-NULL, the map property must exist (-ENODEV if absent). If - * *filter_np is also non-NULL, only entries targeting that node match. + * ``*filter_np`` is also non-NULL, only entries targeting that node match. * @arg: pointer to a &struct of_phandle_args for the result. On success, * @arg->args_count will be set to the number of output specifier cells * as defined by @cells_name in the target node, and @@ -2350,7 +2350,7 @@ EXPORT_SYMBOL_GPL(of_map_iommu_id); * stream/device ID) used as the lookup key in the msi-map table. * @filter_np: pointer to an optional filter node, or NULL to allow bypass. * If non-NULL, the map property must exist (-ENODEV if absent). If - * *filter_np is also non-NULL, only entries targeting that node match. + * ``*filter_np`` is also non-NULL, only entries targeting that node match. * @arg: pointer to a &struct of_phandle_args for the result. On success, * @arg->args_count will be set to the number of output specifier cells * and @arg->args[0..args_count-1] will contain the translated output From 41f1be36957c29c35a1e0703673cf1ae8f4db195 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Mon, 22 Jun 2026 12:02:32 +0200 Subject: [PATCH 220/297] dt-bindings: thermal: amlogic: Fix missing header in the example Usage of defines from headers requires including relevant header, otherwise dt_binding_check fails: Lexical error: Documentation/devicetree/bindings/thermal/amlogic,thermal.example.dts:59.27-34 Unexpected 'GIC_SPI' Lexical error: Documentation/devicetree/bindings/thermal/amlogic,thermal.example.dts:59.38-57 Unexpected 'IRQ_TYPE_LEVEL_HIGH' Lexical error: Documentation/devicetree/bindings/thermal/amlogic,thermal.example.dts:60.37-45 Unexpected 'CLKID_TS' Fixes: b1c8ccdbd4e9 ("dt-bindings: thermal: amlogic: Add support for T7") Signed-off-by: Krzysztof Kozlowski Acked-by: Conor Dooley Link: https://patch.msgid.link/20260622100231.438435-3-krzysztof.kozlowski@oss.qualcomm.com Signed-off-by: Rob Herring (Arm) --- Documentation/devicetree/bindings/thermal/amlogic,thermal.yaml | 3 +++ 1 file changed, 3 insertions(+) diff --git a/Documentation/devicetree/bindings/thermal/amlogic,thermal.yaml b/Documentation/devicetree/bindings/thermal/amlogic,thermal.yaml index e28612510d67..d8f7f3eb7ae2 100644 --- a/Documentation/devicetree/bindings/thermal/amlogic,thermal.yaml +++ b/Documentation/devicetree/bindings/thermal/amlogic,thermal.yaml @@ -87,6 +87,9 @@ examples: amlogic,ao-secure = <&sec_AO>; }; - | + #include + #include + temperature-sensor@20000 { compatible = "amlogic,t7-thermal"; reg = <0x0 0x20000 0x0 0x50>; From 6d5bb4b54288798d23a8119e4666a1e9dccf3c41 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Mon, 22 Jun 2026 12:02:33 +0200 Subject: [PATCH 221/297] dt-bindings: thermal: amlogic: Correct 'reg' in the example The example DTS is tested in a wrapped node with address/size-cells=1, thus reg had incorrect entry leading to dt_binding_check fails: thermal/amlogic,thermal.example.dtb: temperature-sensor@20000 (amlogic,t7-thermal): reg: [[0, 131072], [0, 80]] is too long Fixes: b1c8ccdbd4e9 ("dt-bindings: thermal: amlogic: Add support for T7") Signed-off-by: Krzysztof Kozlowski Acked-by: Conor Dooley Link: https://patch.msgid.link/20260622100231.438435-4-krzysztof.kozlowski@oss.qualcomm.com Signed-off-by: Rob Herring (Arm) --- Documentation/devicetree/bindings/thermal/amlogic,thermal.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Documentation/devicetree/bindings/thermal/amlogic,thermal.yaml b/Documentation/devicetree/bindings/thermal/amlogic,thermal.yaml index d8f7f3eb7ae2..8cfa44dcda58 100644 --- a/Documentation/devicetree/bindings/thermal/amlogic,thermal.yaml +++ b/Documentation/devicetree/bindings/thermal/amlogic,thermal.yaml @@ -92,7 +92,7 @@ examples: temperature-sensor@20000 { compatible = "amlogic,t7-thermal"; - reg = <0x0 0x20000 0x0 0x50>; + reg = <0x20000 0x50>; interrupts = ; clocks = <&clkc_periphs CLKID_TS>; #thermal-sensor-cells = <0>; From fb1a5dfe86d3af1e1c3ce168cf0d8d43897e0f77 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Fri, 19 Jun 2026 17:01:27 +0200 Subject: [PATCH 222/297] thermal: testing: zone: Flush work items during cleanup To prevent freed module code from being executed during the thermal testing module unload, make it add a dedicated workqueue for thermal testing work items and flush it in thermal_testing_exit(). Fixes: f6a034f2df42 ("thermal: Introduce a debugfs-based testing facility") Link: https://sashiko.dev/#/patchset/20260605185212.2491144-1-sam.moelius%40trailofbits.com Signed-off-by: Rafael J. Wysocki Link: https://patch.msgid.link/1959388.tdWV9SEqCh@rafael.j.wysocki [ rjw: Make variable d_command static ] Signed-off-by: Rafael J. Wysocki --- drivers/thermal/testing/command.c | 36 ++++++++++++++++++++--- drivers/thermal/testing/thermal_testing.h | 8 +++++ drivers/thermal/testing/zone.c | 7 ++--- 3 files changed, 43 insertions(+), 8 deletions(-) diff --git a/drivers/thermal/testing/command.c b/drivers/thermal/testing/command.c index fbf7ab9729b5..90e06c593327 100644 --- a/drivers/thermal/testing/command.c +++ b/drivers/thermal/testing/command.c @@ -86,7 +86,10 @@ #include "thermal_testing.h" -struct dentry *d_testing; +struct workqueue_struct *tt_wq __ro_after_init; + +struct dentry *d_testing __ro_after_init; +static struct dentry *d_command __ro_after_init; #define TT_COMMAND_SIZE 16 @@ -203,17 +206,42 @@ static const struct file_operations tt_command_fops = { static int __init thermal_testing_init(void) { + int error; + + tt_wq = alloc_workqueue("thermal_testing", WQ_UNBOUND, 0); + if (!tt_wq) + return -ENOMEM; + d_testing = debugfs_create_dir("thermal-testing", NULL); - if (!IS_ERR(d_testing)) - debugfs_create_file("command", 0200, d_testing, NULL, - &tt_command_fops); + if (IS_ERR(d_testing)) { + error = PTR_ERR(d_testing); + goto destroy_wq; + } + + d_command = debugfs_create_file("command", 0200, d_testing, NULL, &tt_command_fops); + if (IS_ERR(d_command)) { + error = PTR_ERR(d_command); + goto remove_d_testing; + } return 0; + +remove_d_testing: + debugfs_remove(d_testing); +destroy_wq: + destroy_workqueue(tt_wq); + return error; } module_init(thermal_testing_init); static void __exit thermal_testing_exit(void) { + /* First, prevent new commands from being entered. */ + debugfs_remove(d_command); + /* Flush commands in progress (if any). */ + flush_workqueue(tt_wq); + destroy_workqueue(tt_wq); + /* Remove the directory structure and clean up. */ debugfs_remove(d_testing); tt_zone_cleanup(); } diff --git a/drivers/thermal/testing/thermal_testing.h b/drivers/thermal/testing/thermal_testing.h index c790a32aae4e..5880c9a63dba 100644 --- a/drivers/thermal/testing/thermal_testing.h +++ b/drivers/thermal/testing/thermal_testing.h @@ -1,4 +1,12 @@ /* SPDX-License-Identifier: GPL-2.0 */ +#include + +extern struct workqueue_struct *tt_wq; + +static inline void tt_queue_work(struct work_struct *work) +{ + queue_work(tt_wq, work); +} extern struct dentry *d_testing; diff --git a/drivers/thermal/testing/zone.c b/drivers/thermal/testing/zone.c index f7f9ca2f1f2c..6db26276dd41 100644 --- a/drivers/thermal/testing/zone.c +++ b/drivers/thermal/testing/zone.c @@ -13,7 +13,6 @@ #include #include #include -#include #include "thermal_testing.h" @@ -207,7 +206,7 @@ int tt_add_tz(void) INIT_WORK(&tt_work->work, tt_add_tz_work_fn); tt_work->tt_zone = no_free_ptr(tt_zone); - schedule_work(&(no_free_ptr(tt_work)->work)); + tt_queue_work(&(no_free_ptr(tt_work)->work)); return 0; } @@ -269,7 +268,7 @@ int tt_del_tz(const char *arg) INIT_WORK(&tt_work->work, tt_del_tz_work_fn); tt_work->tt_zone = tt_zone; - schedule_work(&(no_free_ptr(tt_work)->work)); + tt_queue_work(&(no_free_ptr(tt_work)->work)); return 0; } @@ -358,7 +357,7 @@ int tt_zone_add_trip(const char *arg) INIT_WORK(&tt_work->work, tt_zone_add_trip_work_fn); tt_work->tt_zone = no_free_ptr(tt_zone); tt_work->tt_trip = no_free_ptr(tt_trip); - schedule_work(&(no_free_ptr(tt_work)->work)); + tt_queue_work(&(no_free_ptr(tt_work)->work)); return 0; } From 292db66afd20dd0b7a3c9a3dad9b864a64c8bddf Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Mon, 22 Jun 2026 20:23:09 +0200 Subject: [PATCH 223/297] ACPICA: Unbreak tools build after switching over to strscpy_pad() Commit 97f7d3f9c9ac ("ACPICA: Replace strncpy() with strscpy_pad() in acpi_ut_safe_strncpy()") switched over the ACPICA code in the kernel to using strscpy_pad() instead of a combination of strncpy() and manual NUL-termination of the destination string, but it overlooked the fact that tools also use the code in question and strscpy_pad() is not defined in those builds. Address that by using the original ACPICA code in non-kernel builds. Fixes: 97f7d3f9c9ac ("ACPICA: Replace strncpy() with strscpy_pad() in acpi_ut_safe_strncpy()") Reported-by: Jiri Slaby Closes: https://lore.kernel.org/all/79e9e913-0fb1-4110-804b-c3b5d0edafe4@kernel Signed-off-by: Rafael J. Wysocki Reviewed-by: Kees Cook [ rjw: Fixed up the number of added code lines ] Link: https://patch.msgid.link/12923581.O9o76ZdvQC@rafael.j.wysocki Signed-off-by: Rafael J. Wysocki --- drivers/acpi/acpica/utnonansi.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/drivers/acpi/acpica/utnonansi.c b/drivers/acpi/acpica/utnonansi.c index 3a7952be6545..93867ad7f342 100644 --- a/drivers/acpi/acpica/utnonansi.c +++ b/drivers/acpi/acpica/utnonansi.c @@ -168,7 +168,16 @@ void acpi_ut_safe_strncpy(char *dest, char *source, acpi_size dest_size) { /* Always terminate destination string */ +#ifdef __KERNEL__ strscpy_pad(dest, source, dest_size); +#else + /* + * strscpy_pad() is not defined in ACPICA tools builds, so use strncpy() + * and directly NUL-terminate the destination string in that case. + */ + strncpy(dest, source, dest_size); + dest[dest_size - 1] = 0; +#endif } #endif From 527a336c609c6bb5020df46da582c583445bfc56 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Otto=20Pfl=C3=BCger?= Date: Sat, 20 Jun 2026 10:54:00 +0200 Subject: [PATCH 224/297] regulator: dt-bindings: Add Unisoc SC2730 PMIC MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add bindings for the regulators found in the Spreadtrum/Unisoc SC2730 PMIC, used e.g. with the UMS512 and UMS9230 SoCs. Signed-off-by: Otto Pflüger Reviewed-by: Krzysztof Kozlowski Link: https://patch.msgid.link/20260620-sc2730-regulators-v6-1-bbd2db395231@abscue.de Signed-off-by: Rob Herring (Arm) --- .../regulator/sprd,sc2730-regulator.yaml | 44 +++++++++++++++++++ 1 file changed, 44 insertions(+) create mode 100644 Documentation/devicetree/bindings/regulator/sprd,sc2730-regulator.yaml diff --git a/Documentation/devicetree/bindings/regulator/sprd,sc2730-regulator.yaml b/Documentation/devicetree/bindings/regulator/sprd,sc2730-regulator.yaml new file mode 100644 index 000000000000..ab945c46b08e --- /dev/null +++ b/Documentation/devicetree/bindings/regulator/sprd,sc2730-regulator.yaml @@ -0,0 +1,44 @@ +# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/regulator/sprd,sc2730-regulator.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Unisoc SC2730 Power Management IC regulators + +maintainers: + - Otto Pflüger + +patternProperties: + "^dcdc-(core|cpu|gen[0-1]|gpu|mem|memq|modem|sram)$": + type: object + $ref: regulator.yaml# + unevaluatedProperties: false + + "^ldo-avdd(12|18)$": + type: object + $ref: regulator.yaml# + unevaluatedProperties: false + + "^ldo-vdd(18-dcxo|28)$": + type: object + $ref: regulator.yaml# + unevaluatedProperties: false + + "^ldo-vdd(emmccore|kpled|ldo[0-2]|sd(core|io)|sim[0-2]|usb33|wcn|wifipa)$": + type: object + $ref: regulator.yaml# + unevaluatedProperties: false + + "^ldo-vddcam(a0|a1|d0|d1|io|mot)$": + type: object + $ref: regulator.yaml# + unevaluatedProperties: false + + "^ldo-vddrf(1v25|18)$": + type: object + $ref: regulator.yaml# + unevaluatedProperties: false + +additionalProperties: false +... From 38b1d6ed23910a4c7cf7c222d9b3a4fcd282a632 Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Sat, 23 May 2026 21:25:50 +0200 Subject: [PATCH 225/297] dt-bindings: clock: renesas: div6: Use ZT/ZTR trace clock in R-Mobile APE6 example Since commit 2abdc3dcf978 ("dt-bindings: clock: renesas,cpg-clocks: Document ZT/ZTR trace clock on R-Mobile APE6"), the APE6 clock node expects two additional "clock-output-names" entries, "zt" and "ztr". Update the example accordingly. Fixes: 2abdc3dcf978 ("dt-bindings: clock: renesas,cpg-clocks: Document ZT/ZTR trace clock on R-Mobile APE6") Signed-off-by: Marek Vasut Acked-by: Conor Dooley Link: https://patch.msgid.link/20260523192622.56605-1-marek.vasut+renesas@mailbox.org Signed-off-by: Rob Herring (Arm) --- .../devicetree/bindings/clock/renesas,cpg-div6-clock.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Documentation/devicetree/bindings/clock/renesas,cpg-div6-clock.yaml b/Documentation/devicetree/bindings/clock/renesas,cpg-div6-clock.yaml index 2197c952e21d..b6ee8c8efd46 100644 --- a/Documentation/devicetree/bindings/clock/renesas,cpg-div6-clock.yaml +++ b/Documentation/devicetree/bindings/clock/renesas,cpg-div6-clock.yaml @@ -60,7 +60,7 @@ examples: clock-output-names = "main", "pll0", "pll1", "pll2", "pll2s", "pll2h", "z", "z2", "i", "m3", "b", "m1", "m2", - "zx", "zs", "hp"; + "zx", "zs", "hp", "ztr", "zt"; }; sdhi2_clk: sdhi2_clk@e615007c { From 956ca5d72c76504824c8eb601879da9476973e15 Mon Sep 17 00:00:00 2001 From: Li RongQing Date: Tue, 16 Jun 2026 15:26:17 +0800 Subject: [PATCH 226/297] ACPI: processor_idle: Mark LPI enter functions as __cpuidle When function tracing or Kprobes is enabled, entering an ACPI Low Power Idle (LPI) state triggers the following RCU splat: RCU not on for: acpi_idle_lpi_enter+0x4/0xd8 WARNING: CPU: 8 PID: 0 at include/linux/trace_recursion.h:162 function_trace_call+0x1e8/0x228 The acpi_idle_lpi_enter() function is invoked within the cpuidle path after RCU has already been disabled for the current local CPU. Consequently, ftrace's function_trace_call() expects RCU to be actively watching before recording trace data, emitting a warning if it is not. Fix this by annotating acpi_idle_lpi_enter(), the generic __weak stub, and the RISC-V implementation of acpi_processor_ffh_lpi_enter() with __cpuidle. This moves these functions into the '.cpuidle.text' section, implicitly disabling ftrace instrumentation (notrace) along this sensitive path and preventing trace-induced RCU warnings during idle entry. Fixes: a36a7fecfe60 ("ACPI / processor_idle: Add support for Low Power Idle(LPI) states") Signed-off-by: Li RongQing Acked-by: lihuisong@huawei.com Link: https://patch.msgid.link/20260616072617.2272-1-lirongqing@baidu.com Signed-off-by: Rafael J. Wysocki --- drivers/acpi/processor_idle.c | 4 ++-- drivers/acpi/riscv/cpuidle.c | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c index 390ab5f1d313..4482cf28f56a 100644 --- a/drivers/acpi/processor_idle.c +++ b/drivers/acpi/processor_idle.c @@ -1143,7 +1143,7 @@ static int acpi_processor_get_lpi_info(struct acpi_processor *pr) return 0; } -int __weak acpi_processor_ffh_lpi_enter(struct acpi_lpi_state *lpi) +int __weak __cpuidle acpi_processor_ffh_lpi_enter(struct acpi_lpi_state *lpi) { return -ENODEV; } @@ -1156,7 +1156,7 @@ int __weak acpi_processor_ffh_lpi_enter(struct acpi_lpi_state *lpi) * * Return: 0 for success or negative value for error */ -static int acpi_idle_lpi_enter(struct cpuidle_device *dev, +static int __cpuidle acpi_idle_lpi_enter(struct cpuidle_device *dev, struct cpuidle_driver *drv, int index) { struct acpi_processor *pr; diff --git a/drivers/acpi/riscv/cpuidle.c b/drivers/acpi/riscv/cpuidle.c index 624f9bbdb58c..c76dbabff702 100644 --- a/drivers/acpi/riscv/cpuidle.c +++ b/drivers/acpi/riscv/cpuidle.c @@ -66,7 +66,7 @@ int acpi_processor_ffh_lpi_probe(unsigned int cpu) return acpi_cpu_init_idle(cpu); } -int acpi_processor_ffh_lpi_enter(struct acpi_lpi_state *lpi) +int __cpuidle acpi_processor_ffh_lpi_enter(struct acpi_lpi_state *lpi) { u32 state = lpi->address; From b39a6b2e9d5bd6a3153aed4c7440172b8f6a739e Mon Sep 17 00:00:00 2001 From: "Rob Herring (Arm)" Date: Wed, 24 Jun 2026 08:36:42 -0500 Subject: [PATCH 227/297] dt-bindings: mfd: khadas,mcu: Drop type reference from "fan-supply" "fan-supply" already has a type and shouldn't have a type $ref. Drop the $ref to fix the warning. Fixes: 39dd85d9246e ("dt-bindings: mfd: khadas: Add new compatible for Khadas VIM4 MCU") Link: https://patch.msgid.link/20260624133643.4146351-1-robh@kernel.org Signed-off-by: Rob Herring (Arm) --- Documentation/devicetree/bindings/mfd/khadas,mcu.yaml | 1 - 1 file changed, 1 deletion(-) diff --git a/Documentation/devicetree/bindings/mfd/khadas,mcu.yaml b/Documentation/devicetree/bindings/mfd/khadas,mcu.yaml index 1f135618e3b6..c6f91e7bc8aa 100644 --- a/Documentation/devicetree/bindings/mfd/khadas,mcu.yaml +++ b/Documentation/devicetree/bindings/mfd/khadas,mcu.yaml @@ -28,7 +28,6 @@ properties: fan-supply: description: Phandle to the regulator that powers the fan. - $ref: /schemas/types.yaml#/definitions/phandle required: - compatible From 36fa5ffa60344bcc59fb3f50b33af8187e6b8753 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Tue, 23 Jun 2026 22:28:18 +0200 Subject: [PATCH 228/297] arm64: mm: Defer read-only remap of data/bss linear alias Since commit f2ba877402e5 ("arm64: mm: Map the kernel data/bss read-only in the linear map") the linear alias of the .data and .bss regions is remapped read-only early during the boot. (Note that a subsequent patch to unmap this region entirely was reverted just before the v7.2 merge window, and will be brought back in an improved form for the v7.3 cycle) Fuad reports that in some cases, the KVM init code may apply relocations to variables that reside in .data, and does so via the linear map. This means that remapping .data read-only beforehand is a bad idea, and results in an early boot crash. These variables in .data are only present when CONFIG_NVHE_EL2_DEBUG or CONFIG_NVHE_EL2_TRACING are enabled, which is why it was not spotted in testing. So move the remap to mark_rodata_ro(), which is a reasonable place to put this, and ensures that it happens much later during the boot. It also means that rodata=off is now taken into account, and so the linear alias will remain writable in that case. Fixes: f2ba877402e5 ("arm64: mm: Map the kernel data/bss read-only in the linear map") Reviewed-by: Fuad Tabba Tested-by: Fuad Tabba Signed-off-by: Ard Biesheuvel Reviewed-by: Kevin Brodsky Signed-off-by: Will Deacon --- arch/arm64/mm/mmu.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 354bedf0e638..60c2778f413c 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -1198,11 +1198,6 @@ static void __init map_mem(void) __map_memblock(start, end, pgprot_tagged(PAGE_KERNEL), flags); } - - /* Map the kernel data/bss read-only in the linear map */ - __map_memblock(init_end, kernel_end, PAGE_KERNEL_RO, flags); - flush_tlb_kernel_range((unsigned long)lm_alias(__init_end), - (unsigned long)lm_alias(__bss_stop)); } void mark_rodata_ro(void) @@ -1221,6 +1216,12 @@ void mark_rodata_ro(void) update_mapping_prot(__pa_symbol(_text), (unsigned long)_text, (unsigned long)_stext - (unsigned long)_text, PAGE_KERNEL_RO); + + /* Map the kernel data/bss read-only in the linear map */ + update_mapping_prot(__pa_symbol(__init_end), + (unsigned long)lm_alias(__init_end), + (unsigned long)__bss_stop - (unsigned long)__init_end, + PAGE_KERNEL_RO); } static void __init declare_vma(struct vm_struct *vma, From 4939889c985da68936090cc013e58c28b7bff34f Mon Sep 17 00:00:00 2001 From: Ralph Boehme Date: Sat, 20 Jun 2026 09:12:42 +0200 Subject: [PATCH 229/297] smb/client: fix security flag calculation when setting security descriptors In id_mode_to_cifs_acl(), aclflag was initialized to CIFS_ACL_DACL by default. This forced the client to request setting the DACL even when only an ownership (chown) or group (chgrp) change was being performed. Let build_sec_desc() do the proper flag calculation by initializing aclflag to 0. build_sec_desc() sets the appropriate bits (CIFS_ACL_OWNER, CIFS_ACL_GROUP, or CIFS_ACL_DACL) depending on what actually changed. During ownership transfer, CIFS_ACL_DACL is only set if replace_sids_and_copy_aces() actually replaces the SIDs inside any of the DACL's ACEs. If build_sec_desc() results in aclflag being 0 (meaning no changes were mapped), exit early to avoid sending an empty security descriptor update to the server. Signed-off-by: Ralph Boehme Signed-off-by: Steve French --- fs/smb/client/cifsacl.c | 22 ++++++++++++++++------ 1 file changed, 16 insertions(+), 6 deletions(-) diff --git a/fs/smb/client/cifsacl.c b/fs/smb/client/cifsacl.c index 5bbf73736358..07cf0e578233 100644 --- a/fs/smb/client/cifsacl.c +++ b/fs/smb/client/cifsacl.c @@ -1185,7 +1185,8 @@ set_size: static __u16 replace_sids_and_copy_aces(struct smb_acl *pdacl, struct smb_acl *pndacl, struct smb_sid *pownersid, struct smb_sid *pgrpsid, - struct smb_sid *pnownersid, struct smb_sid *pngrpsid) + struct smb_sid *pnownersid, struct smb_sid *pngrpsid, + int *aclflag) { int i; u16 size = 0; @@ -1209,12 +1210,15 @@ static __u16 replace_sids_and_copy_aces(struct smb_acl *pdacl, struct smb_acl *p pntace = (struct smb_ace *) (acl_base + size); pnntace = (struct smb_ace *) (nacl_base + nsize); - if (pnownersid && compare_sids(&pntace->sid, pownersid) == 0) + if (pnownersid && compare_sids(&pntace->sid, pownersid) == 0) { ace_size = cifs_copy_ace(pnntace, pntace, pnownersid); - else if (pngrpsid && compare_sids(&pntace->sid, pgrpsid) == 0) + *aclflag |= CIFS_ACL_DACL; + } else if (pngrpsid && compare_sids(&pntace->sid, pgrpsid) == 0) { ace_size = cifs_copy_ace(pnntace, pntace, pngrpsid); - else + *aclflag |= CIFS_ACL_DACL; + } else { ace_size = cifs_copy_ace(pnntace, pntace, NULL); + } size += le16_to_cpu(pntace->size); nsize += ace_size; @@ -1521,7 +1525,8 @@ static int build_sec_desc(struct smb_ntsd *pntsd, struct smb_ntsd *pnntsd, /* Replace ACEs for old owner with new one */ size = replace_sids_and_copy_aces(dacl_ptr, ndacl_ptr, owner_sid_ptr, group_sid_ptr, - nowner_sid_ptr, ngroup_sid_ptr); + nowner_sid_ptr, ngroup_sid_ptr, + aclflag); ndacl_ptr->size = cpu_to_le16(size); } @@ -1738,7 +1743,7 @@ id_mode_to_cifs_acl(struct inode *inode, const char *path, __u64 *pnmode, kuid_t uid, kgid_t gid) { int rc = 0; - int aclflag = CIFS_ACL_DACL; /* default flag to set */ + int aclflag = 0; __u32 secdesclen = 0; __u32 nsecdesclen = 0; __u32 dacloffset = 0; @@ -1837,6 +1842,11 @@ id_mode_to_cifs_acl(struct inode *inode, const char *path, __u64 *pnmode, if (rc != 0) goto id_mode_to_cifs_acl_exit; + if (aclflag == 0) { + cifs_dbg(FYI, "set_cifs_acl aclflag=0, no change mapped\n"); + goto id_mode_to_cifs_acl_exit; + } + if (ops->set_acl == NULL) { rc = -EOPNOTSUPP; goto id_mode_to_cifs_acl_exit; From 760ef2c579c2609cf17fb1cd5392f64d42d43d33 Mon Sep 17 00:00:00 2001 From: Ralph Boehme Date: Sun, 7 Jun 2026 15:23:18 +0200 Subject: [PATCH 230/297] smb/client: fix chown/chgrp with SMB3 POSIX Extensions Ownership (chown) and group (chgrp) modifications were being ignored when mounting with SMB3 POSIX Extensions unless CIFS_MOUNT_CIFS_ACL or CIFS_MOUNT_MODE_FROM_SID were also explicitly set. Fix this by checking for posix_extensions in cifs_setattr_nounix() when updating UID and GID, ensuring that id_mode_to_cifs_acl() is called to map and set the ownership/group information on the server. Cc: stable@vger.kernel.org Signed-off-by: Ralph Boehme Signed-off-by: Steve French --- fs/smb/client/inode.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/smb/client/inode.c b/fs/smb/client/inode.c index 51fb7c418d52..56b0f109e41b 100644 --- a/fs/smb/client/inode.c +++ b/fs/smb/client/inode.c @@ -3376,7 +3376,8 @@ cifs_setattr_nounix(struct dentry *direntry, struct iattr *attrs) if (attrs->ia_valid & ATTR_GID) gid = attrs->ia_gid; - if (sbflags & (CIFS_MOUNT_CIFS_ACL | CIFS_MOUNT_MODE_FROM_SID)) { + if ((sbflags & (CIFS_MOUNT_CIFS_ACL | CIFS_MOUNT_MODE_FROM_SID)) || + cifs_sb_master_tcon(cifs_sb)->posix_extensions) { if (uid_valid(uid) || gid_valid(gid)) { mode = NO_CHANGE_64; rc = id_mode_to_cifs_acl(inode, full_path, &mode, From d281a757ff1ca230b80b0eae16559f8054927083 Mon Sep 17 00:00:00 2001 From: Steve French Date: Sun, 21 Jun 2026 20:39:59 -0500 Subject: [PATCH 231/297] smb common: add missing AAPL defines Add various defines for AAPL open context, e.g. for queries of server capabilities. Signed-off-by: Steve French --- fs/smb/common/smb2pdu.h | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) diff --git a/fs/smb/common/smb2pdu.h b/fs/smb/common/smb2pdu.h index 325ff83b12fe..e7ff52b8aba5 100644 --- a/fs/smb/common/smb2pdu.h +++ b/fs/smb/common/smb2pdu.h @@ -1243,6 +1243,30 @@ struct create_mxac_req { __le64 Timestamp; } __packed; +/* + * AAPL flags. See Samba libcli/smb/smb2_create_ctx.h + */ + +/* "AAPL" Context Command Codes */ +#define SMB2_CRTCTX_AAPL_SERVER_QUERY 1 +#define SMB2_CRTCTX_AAPL_RESOLVE_ID 2 + +/* "AAPL" Server Query request/response bitmap */ +#define SMB2_CRTCTX_AAPL_SERVER_CAPS 1 +#define SMB2_CRTCTX_AAPL_VOLUME_CAPS 2 +#define SMB2_CRTCTX_AAPL_MODEL_INFO 4 + +/* "AAPL" Client/Server Capabilities bitmap */ +#define SMB2_CRTCTX_AAPL_SUPPORTS_READ_DIR_ATTR 1 +#define SMB2_CRTCTX_AAPL_SUPPORTS_OSX_COPYFILE 2 +#define SMB2_CRTCTX_AAPL_UNIX_BASED 4 +#define SMB2_CRTCTX_AAPL_SUPPORTS_NFS_ACE 8 + +/* "AAPL" Volume Capabilities bitmap */ +#define SMB2_CRTCTX_AAPL_SUPPORT_RESOLVE_ID 1 +#define SMB2_CRTCTX_AAPL_CASE_SENSITIVE 2 +#define SMB2_CRTCTX_AAPL_FULL_SYNC 4 + /* * Flags * See MS-SMB2 2.2.13.2.11 From 898d280f4e4d6da53da8c1f5884a65487ae93603 Mon Sep 17 00:00:00 2001 From: Huiwen He Date: Tue, 23 Jun 2026 10:46:13 +0800 Subject: [PATCH 232/297] smb/client: name the default fallocate mode FALLOC_FL_ALLOCATE_RANGE identifies the default fallocate allocation mode and is defined as zero. Use the symbolic name instead of a literal zero in smb3_fallocate() to make the mode dispatch clearer. This does not change behavior. Signed-off-by: Huiwen He Reviewed-by: ChenXiaoSong Signed-off-by: Steve French --- fs/smb/client/smb2ops.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c index a8f8feeeccb5..2964f461fc84 100644 --- a/fs/smb/client/smb2ops.c +++ b/fs/smb/client/smb2ops.c @@ -4071,7 +4071,7 @@ static long smb3_fallocate(struct file *file, struct cifs_tcon *tcon, int mode, return smb3_collapse_range(file, tcon, off, len); else if (mode == FALLOC_FL_INSERT_RANGE) return smb3_insert_range(file, tcon, off, len); - else if (mode == 0) + else if (mode == FALLOC_FL_ALLOCATE_RANGE) return smb3_simple_falloc(file, tcon, off, len, false); return -EOPNOTSUPP; From 2c253f230a31d4394f6f926a73f5e157ad88d347 Mon Sep 17 00:00:00 2001 From: Fredric Cover Date: Tue, 23 Jun 2026 09:49:15 -0700 Subject: [PATCH 233/297] smb/client: use %pe to print error pointer Currently, __reconnect_target_locked() prints the error pointer 'hostname' using PTR_ERR() and %ld, printing only the error code. Fix this by using by using %pe to print the error symbolic code instead, and remove PTR_ERR(). Signed-off-by: Fredric Cover Signed-off-by: Steve French --- fs/smb/client/connect.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/smb/client/connect.c b/fs/smb/client/connect.c index 74197766471c..85aec302c89e 100644 --- a/fs/smb/client/connect.c +++ b/fs/smb/client/connect.c @@ -457,8 +457,8 @@ static int __reconnect_target_locked(struct TCP_Server_Info *server, server->hostname = hostname; spin_unlock(&server->srv_lock); } else { - cifs_dbg(FYI, "%s: couldn't extract hostname or address from dfs target: %ld\n", - __func__, PTR_ERR(hostname)); + cifs_dbg(FYI, "%s: couldn't extract hostname or address from dfs target: %pe\n", + __func__, hostname); cifs_dbg(FYI, "%s: default to last target server: %s\n", __func__, server->hostname); } From 1c6267a1d5cf4c73b656f8181b310cbbb3e4767b Mon Sep 17 00:00:00 2001 From: Haoxiang Li Date: Tue, 23 Jun 2026 09:45:38 +0800 Subject: [PATCH 234/297] smb: client: Fix next buffer leak in receive_encrypted_standard() receive_encrypted_standard() allocates next_buffer before checking whether the number of compound PDUs already reached MAX_COMPOUND. If the limit check fails, the function returns immediately and the newly allocated next_buffer is not assigned to server->smallbuf/server->bigbuf, making it leaked. Move the MAX_COMPOUND check before allocating next_buffer. Fixes: b24df3e30cbf ("cifs: update receive_encrypted_standard to handle compounded responses") Cc: stable@vger.kernel.org Signed-off-by: Haoxiang Li Signed-off-by: Steve French --- fs/smb/client/smb2ops.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c index 2964f461fc84..c862a98e52df 100644 --- a/fs/smb/client/smb2ops.c +++ b/fs/smb/client/smb2ops.c @@ -5111,6 +5111,12 @@ receive_encrypted_standard(struct TCP_Server_Info *server, one_more: shdr = (struct smb2_hdr *)buf; next_cmd = le32_to_cpu(shdr->NextCommand); + + if (*num_mids >= MAX_COMPOUND) { + cifs_server_dbg(VFS, "too many PDUs in compound\n"); + return -1; + } + if (next_cmd) { if (WARN_ON_ONCE(next_cmd > pdu_length)) return -1; @@ -5134,10 +5140,6 @@ one_more: mid_entry->resp_buf_size = server->pdu_size; } - if (*num_mids >= MAX_COMPOUND) { - cifs_server_dbg(VFS, "too many PDUs in compound\n"); - return -1; - } bufs[*num_mids] = buf; mids[(*num_mids)++] = mid_entry; From 2a4b3d2db5c6fcdba889baf7b2ae5661b0beac89 Mon Sep 17 00:00:00 2001 From: Huiwen He Date: Wed, 24 Jun 2026 10:15:43 +0800 Subject: [PATCH 235/297] smb/client: preserve errors from smb2_set_sparse() smb2_set_sparse() converts every FSCTL_SET_SPARSE failure to false and marks sparse support as broken for the share. Callers therefore report EOPNOTSUPP even for errors such as ENOSPC or EACCES, and later sparse operations remain disabled until the share is unmounted. Return the SMB2 ioctl error directly. Set broken_sparse_sup only for EOPNOTSUPP, which indicates that the server does not support the request. Update smb3_punch_hole() to propagate the error returned by smb2_set_sparse(). Fixes: 3d1a3745d8ca ("Add sparse file support to SMB2/SMB3 mounts") Signed-off-by: Huiwen He Reviewed-by: ChenXiaoSong Signed-off-by: Steve French --- fs/smb/client/smb2ops.c | 30 +++++++++++++++--------------- 1 file changed, 15 insertions(+), 15 deletions(-) diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c index c862a98e52df..06e9322a762a 100644 --- a/fs/smb/client/smb2ops.c +++ b/fs/smb/client/smb2ops.c @@ -2117,8 +2117,9 @@ smb2_sync_write(const unsigned int xid, struct cifs_fid *pfid, } /* Set or clear the SPARSE_FILE attribute based on value passed in setsparse */ -static bool smb2_set_sparse(const unsigned int xid, struct cifs_tcon *tcon, - struct cifsFileInfo *cfile, struct inode *inode, __u8 setsparse) +static int smb2_set_sparse(const unsigned int xid, struct cifs_tcon *tcon, + struct cifsFileInfo *cfile, struct inode *inode, + __u8 setsparse) { struct cifsInodeInfo *cifsi; int rc; @@ -2127,31 +2128,31 @@ static bool smb2_set_sparse(const unsigned int xid, struct cifs_tcon *tcon, /* if file already sparse don't bother setting sparse again */ if ((cifsi->cifsAttrs & FILE_ATTRIBUTE_SPARSE_FILE) && setsparse) - return true; /* already sparse */ + return 0; /* already sparse */ if (!(cifsi->cifsAttrs & FILE_ATTRIBUTE_SPARSE_FILE) && !setsparse) - return true; /* already not sparse */ + return 0; /* already not sparse */ /* * Can't check for sparse support on share the usual way via the * FS attribute info (FILE_SUPPORTS_SPARSE_FILES) on the share * since Samba server doesn't set the flag on the share, yet * supports the set sparse FSCTL and returns sparse correctly - * in the file attributes. If we fail setting sparse though we - * mark that server does not support sparse files for this share - * to avoid repeatedly sending the unsupported fsctl to server - * if the file is repeatedly extended. + * in the file attributes. If the server returns EOPNOTSUPP, mark + * that sparse files are not supported on this share to avoid + * repeatedly sending the unsupported FSCTL. */ if (tcon->broken_sparse_sup) - return false; + return -EOPNOTSUPP; rc = SMB2_ioctl(xid, tcon, cfile->fid.persistent_fid, cfile->fid.volatile_fid, FSCTL_SET_SPARSE, &setsparse, 1, CIFSMaxBufSize, NULL, NULL); if (rc) { - tcon->broken_sparse_sup = true; + if (rc == -EOPNOTSUPP) + tcon->broken_sparse_sup = true; cifs_dbg(FYI, "set sparse rc = %d\n", rc); - return false; + return rc; } if (setsparse) @@ -2159,7 +2160,7 @@ static bool smb2_set_sparse(const unsigned int xid, struct cifs_tcon *tcon, else cifsi->cifsAttrs &= (~FILE_ATTRIBUTE_SPARSE_FILE); - return true; + return 0; } static int @@ -3483,10 +3484,9 @@ static long smb3_punch_hole(struct file *file, struct cifs_tcon *tcon, /* Need to make file sparse, if not already, before freeing range. */ /* Consider adding equivalent for compressed since it could also work */ - if (!smb2_set_sparse(xid, tcon, cfile, inode, set_sparse)) { - rc = -EOPNOTSUPP; + rc = smb2_set_sparse(xid, tcon, cfile, inode, set_sparse); + if (rc) goto out; - } filemap_invalidate_lock(inode->i_mapping); /* From 245404c26563aafb36aafb01298f148db1851be3 Mon Sep 17 00:00:00 2001 From: Javier Fernandez Pastrana Date: Wed, 24 Jun 2026 17:19:58 +0200 Subject: [PATCH 236/297] spi: imx: reconfigure for PIO when DMA cannot be started When spi_imx_can_dma() selects DMA, the ECSPI is configured for DMA: spi_imx_setupxfer() sets CTRL.SMC and clears dynamic_burst, and spi_imx_dma_transfer() programs the dynamic-burst BURST_LENGTH and the SDMA watermarks. If the DMA descriptor cannot be prepared (dmaengine_prep_slave_single() returns NULL), the transfer is failed with SPI_TRANS_FAIL_NO_START and falls back to PIO. The dynamic-burst DMA path uses its own bounce buffers instead of the SPI core's mapping, so xfer->{tx,rx}_sg_mapped are not set and the core's DMA->PIO retry is skipped; the driver falls back to PIO internally. But none of the DMA-mode configuration is undone, so the PIO transfer runs with CTRL.SMC set, the wrong burst length and dynamic_burst cleared, and the transferred data is corrupted. This is easily hit on i.MX8MP boards that describe ECSPI DMA in the device tree but run SDMA on ROM firmware (no external sdma-imx7d.bin): every ECSPI DMA prepare fails. An Infineon SLB9670 TPM on ECSPI1 then returns shifted TPM2_GetCapability data, is flagged "field failure mode", /dev/tpmrm0 is never created. Set controller->fallback before re-running spi_imx_setupxfer() so the ECSPI is reconfigured exactly like a normal PIO transfer. With controller->fallback set, spi_imx_setupxfer() sees spi_imx_can_dma() return false, so it clears spi_imx->usedma and reprograms the controller (clears CTRL.SMC, restores dynamic_burst and the PIO burst length). No explicit spi_imx->usedma = false is needed: setupxfer() already updates it from the can_dma() result. Fixes: faa8e404ad8e ("spi: imx: support dynamic burst length for ECSPI DMA mode") Cc: stable@vger.kernel.org Signed-off-by: Javier Fernandez Pastrana Acked-by: Carlos Song Reviewed-by: Frank Li Link: https://patch.msgid.link/20260624151958.18626-1-javier.pastrana@linutronix.de Signed-off-by: Mark Brown --- drivers/spi/spi-imx.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/spi/spi-imx.c b/drivers/spi/spi-imx.c index ae9912905c67..79a6c1a60b0a 100644 --- a/drivers/spi/spi-imx.c +++ b/drivers/spi/spi-imx.c @@ -2152,7 +2152,8 @@ static int spi_imx_transfer_one(struct spi_controller *controller, if (spi_imx->usedma) { ret = spi_imx_dma_transfer(spi_imx, transfer); if (transfer->error & SPI_TRANS_FAIL_NO_START) { - spi_imx->usedma = false; + controller->fallback = true; + spi_imx_setupxfer(spi, transfer); if (spi_imx->target_mode) return spi_imx_pio_transfer_target(spi, transfer); else From 18d39c71e3171eeb7296cb288bbac48a89a7cf4b Mon Sep 17 00:00:00 2001 From: Akhilesh Patil Date: Tue, 19 Aug 2025 16:17:23 +0530 Subject: [PATCH 237/297] rtc: ds1307: add support for clock provider in ds1307 Add support for square-wave output for ds1307 rtc via common clock framework clock provider. tested on TI am62x SK board using ds1307 RTC hardware module. Signed-off-by: Akhilesh Patil Link: https://patch.msgid.link/6b44b47567e418a7bc3f68b626e287b8106641f3.1755599808.git.akhilesh@ee.iitb.ac.in Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-ds1307.c | 139 ++++++++++++++++++++++++++++++++++++++- 1 file changed, 137 insertions(+), 2 deletions(-) diff --git a/drivers/rtc/rtc-ds1307.c b/drivers/rtc/rtc-ds1307.c index ee6e75a5efc5..8fc258d5a1f4 100644 --- a/drivers/rtc/rtc-ds1307.c +++ b/drivers/rtc/rtc-ds1307.c @@ -1664,18 +1664,153 @@ static int ds3231_clks_register(struct ds1307 *ds1307) return 0; } +/* ds1307 RTC clock output support */ +static unsigned long ds1307_clk_rates[] = { + 1, + 4096, + 8192, + 32768, +}; + +static unsigned long ds1307_clk_sqw_recalc_rate(struct clk_hw *hw, + unsigned long parent_rate) +{ + int ret; + unsigned int rate_id; + struct ds1307 *ds1307 = clk_sqw_to_ds1307(hw); + + ret = regmap_read(ds1307->regmap, DS1307_REG_CONTROL, &rate_id); + if (ret) + return ret; + + rate_id &= (DS1307_BIT_RS1 | DS1307_BIT_RS0); + + return ds1307_clk_rates[rate_id]; +} + +static int ds1307_clk_sqw_determine_rate(struct clk_hw *hw, + struct clk_rate_request *req) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(ds1307_clk_rates); i++) { + if (req->rate <= ds1307_clk_rates[i]) { + req->rate = ds1307_clk_rates[i]; + return 0; + } + } + + /* Default rate 1Hz */ + req->rate = ds1307_clk_rates[0]; + + return 0; +} + +static int ds1307_clk_sqw_set_rate(struct clk_hw *hw, unsigned long rate, + unsigned long parent_rate) +{ + int id, ret; + struct ds1307 *ds1307 = clk_sqw_to_ds1307(hw); + + for (id = 0; id < ARRAY_SIZE(ds1307_clk_rates); id++) { + if (ds1307_clk_rates[id] == rate) + break; + } + + if (id >= ARRAY_SIZE(ds1307_clk_rates)) + return -EINVAL; + + ret = regmap_update_bits(ds1307->regmap, DS1307_REG_CONTROL, + DS1307_BIT_RS0 | DS1307_BIT_RS1, id); + + return ret; +} + +static int ds1307_clk_sqw_prepare(struct clk_hw *hw) +{ + int ret; + struct ds1307 *ds1307 = clk_sqw_to_ds1307(hw); + + ret = regmap_update_bits(ds1307->regmap, DS1307_REG_CONTROL, + DS1307_BIT_SQWE, DS1307_BIT_SQWE); + + return ret; +} + +static void ds1307_clk_sqw_unprepare(struct clk_hw *hw) +{ + struct ds1307 *ds1307 = clk_sqw_to_ds1307(hw); + + regmap_update_bits(ds1307->regmap, DS1307_REG_CONTROL, + DS1307_BIT_SQWE, ~DS1307_BIT_SQWE); +} + +static int ds1307_clk_sqw_is_prepared(struct clk_hw *hw) +{ + int ret; + struct ds1307 *ds1307 = clk_sqw_to_ds1307(hw); + unsigned int status; + + ret = regmap_read(ds1307->regmap, DS1307_REG_CONTROL, &status); + if (ret) + return ret; + + return !!(status & DS1307_BIT_SQWE); +} + +static const struct clk_ops ds1307_clk_sqw_ops = { + .prepare = ds1307_clk_sqw_prepare, + .unprepare = ds1307_clk_sqw_unprepare, + .is_prepared = ds1307_clk_sqw_is_prepared, + .recalc_rate = ds1307_clk_sqw_recalc_rate, + .set_rate = ds1307_clk_sqw_set_rate, + .determine_rate = ds1307_clk_sqw_determine_rate, +}; + +static int rtc_ds1307_clks_register(struct ds1307 *ds1307) +{ + struct device_node *node = ds1307->dev->of_node; + struct clk *clk; + struct clk_init_data init = {0}; + + init.name = "ds1307_clk_sqw"; + init.ops = &ds1307_clk_sqw_ops; + + ds1307->clks[0].init = &init; + + /* Register the clock with CCF */ + clk = devm_clk_register(ds1307->dev, &ds1307->clks[0]); + if (IS_ERR(clk)) + return PTR_ERR(clk); + + if (node) + of_clk_add_provider(node, of_clk_src_simple_get, clk); + + return 0; +} + static void ds1307_clks_register(struct ds1307 *ds1307) { int ret; - if (ds1307->type != ds_3231) + switch (ds1307->type) { + case ds_3231: + ret = ds3231_clks_register(ds1307); + break; + + case ds_1307: + ret = rtc_ds1307_clks_register(ds1307); + break; + + default: return; + } - ret = ds3231_clks_register(ds1307); if (ret) { dev_warn(ds1307->dev, "unable to register clock device %d\n", ret); } + } #else From b70598b3769ea64978e76601d1824a12de556da1 Mon Sep 17 00:00:00 2001 From: Akhilesh Patil Date: Sat, 20 Sep 2025 20:31:24 +0530 Subject: [PATCH 238/297] dt-bindings: rtc: Add ST m41t93 Document DT bindings for m41t93 rtc which supports time, date, alarm, watchdog, square wave clock output provider, user sram and 8 bit timer. Signed-off-by: Akhilesh Patil Reviewed-by: Rob Herring (Arm) Link: https://patch.msgid.link/b1b1f7abde8a4ee8b625361bca32934679bf1e1a.1758379856.git.akhilesh@ee.iitb.ac.in Signed-off-by: Alexandre Belloni --- .../devicetree/bindings/rtc/st,m41t93.yaml | 50 +++++++++++++++++++ 1 file changed, 50 insertions(+) create mode 100644 Documentation/devicetree/bindings/rtc/st,m41t93.yaml diff --git a/Documentation/devicetree/bindings/rtc/st,m41t93.yaml b/Documentation/devicetree/bindings/rtc/st,m41t93.yaml new file mode 100644 index 000000000000..bdd995c5c1f4 --- /dev/null +++ b/Documentation/devicetree/bindings/rtc/st,m41t93.yaml @@ -0,0 +1,50 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/rtc/st,m41t93.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: ST M41T93 RTC and compatible + +maintainers: + - Akhilesh Patil + +description: + ST M41T93 is spi based Real Time Clock (RTC) with time, date, + alarm, watchdog, square wave clock output, 8 bit timer and + 7 bytes of user SRAM. + +properties: + compatible: + enum: + - st,m41t93 + + reg: + maxItems: 1 + + "#clock-cells": + const: 0 + +required: + - compatible + - reg + +allOf: + - $ref: rtc.yaml + - $ref: /schemas/spi/spi-peripheral-props.yaml# + +unevaluatedProperties: false + +examples: + - | + spi { + #address-cells = <1>; + #size-cells = <0>; + rtc@0 { + compatible = "st,m41t93"; + reg = <0>; + #clock-cells = <0>; + spi-max-frequency = <2000000>; + }; + }; + From 081e3de28c7663b0bd33e3eb374fb38a139e8064 Mon Sep 17 00:00:00 2001 From: Akhilesh Patil Date: Sat, 20 Sep 2025 20:31:47 +0530 Subject: [PATCH 239/297] rtc: m41t93: add device tree support Add device tree support for m41t93 rtc by adding of_match_table. Define compatible string - "st,m41t93" which can be used to instantiate this rtc device via DT node. Signed-off-by: Akhilesh Patil Link: https://patch.msgid.link/060ef5c5adaa444d2c623aa8ce4c540fa19d0f95.1758379856.git.akhilesh@ee.iitb.ac.in Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-m41t93.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/rtc/rtc-m41t93.c b/drivers/rtc/rtc-m41t93.c index 9444cb5f5190..4e803ff0ce49 100644 --- a/drivers/rtc/rtc-m41t93.c +++ b/drivers/rtc/rtc-m41t93.c @@ -191,9 +191,16 @@ static int m41t93_probe(struct spi_device *spi) return 0; } +static const struct of_device_id m41t93_dt_match[] = { + { .compatible = "st,m41t93" }, + { } +}; +MODULE_DEVICE_TABLE(of, m41t93_dt_match); + static struct spi_driver m41t93_driver = { .driver = { .name = "rtc-m41t93", + .of_match_table = m41t93_dt_match, }, .probe = m41t93_probe, }; From d86e8682593c79d8599537707f49e201456a76de Mon Sep 17 00:00:00 2001 From: Akhilesh Patil Date: Sat, 20 Sep 2025 20:32:16 +0530 Subject: [PATCH 240/297] rtc: m41t93: migrate to regmap api for register access Adapt driver to use regmap api with spi bus instead of direct spi subsystem calls to access device registers. Simplify and standardize the register interactions using more abstract and bus agnostic regmap api to reduce code duplication and improve maintainability. Define spi regmap config suitable for m41t93 spi bus protocol to achieve same transactions on spi bus. Tested on TI am62x sk board with m41t93 rtc chip connected over spi0. Validated set and get time using hwclock tool and verified spi bus transfers using logic analyzer. Signed-off-by: Akhilesh Patil Link: https://patch.msgid.link/180f9b6c3ee7c490fe3537c2d50a92cec359e4cd.1758379856.git.akhilesh@ee.iitb.ac.in Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-m41t93.c | 121 ++++++++++++++++++++++----------------- 1 file changed, 70 insertions(+), 51 deletions(-) diff --git a/drivers/rtc/rtc-m41t93.c b/drivers/rtc/rtc-m41t93.c index 4e803ff0ce49..61e761af56ad 100644 --- a/drivers/rtc/rtc-m41t93.c +++ b/drivers/rtc/rtc-m41t93.c @@ -12,6 +12,7 @@ #include #include #include +#include #define M41T93_REG_SSEC 0 #define M41T93_REG_ST_SEC 1 @@ -31,23 +32,17 @@ #define M41T93_FLAG_BL (1 << 4) #define M41T93_FLAG_HT (1 << 6) -static inline int m41t93_set_reg(struct spi_device *spi, u8 addr, u8 data) -{ - u8 buf[2]; - - /* MSB must be '1' to write */ - buf[0] = addr | 0x80; - buf[1] = data; - - return spi_write(spi, buf, sizeof(buf)); -} +struct m41t93_data { + struct rtc_device *rtc; + struct regmap *regmap; +}; static int m41t93_set_time(struct device *dev, struct rtc_time *tm) { - struct spi_device *spi = to_spi_device(dev); - int tmp; - u8 buf[9] = {0x80}; /* write cmd + 8 data bytes */ - u8 * const data = &buf[1]; /* ptr to first data byte */ + struct m41t93_data *m41t93 = dev_get_drvdata(dev); + int tmp, ret; + u8 buf[8] = {0}; /* 8 data bytes */ + u8 * const data = &buf[0]; /* ptr to first data byte */ dev_dbg(dev, "%s secs=%d, mins=%d, " "hours=%d, mday=%d, mon=%d, year=%d, wday=%d\n", @@ -56,31 +51,31 @@ static int m41t93_set_time(struct device *dev, struct rtc_time *tm) tm->tm_mon, tm->tm_year, tm->tm_wday); if (tm->tm_year < 100) { - dev_warn(&spi->dev, "unsupported date (before 2000-01-01).\n"); + dev_warn(dev, "unsupported date (before 2000-01-01).\n"); return -EINVAL; } - tmp = spi_w8r8(spi, M41T93_REG_FLAGS); - if (tmp < 0) - return tmp; + ret = regmap_read(m41t93->regmap, M41T93_REG_FLAGS, &tmp); + if (ret < 0) + return ret; if (tmp & M41T93_FLAG_OF) { - dev_warn(&spi->dev, "OF bit is set, resetting.\n"); - m41t93_set_reg(spi, M41T93_REG_FLAGS, tmp & ~M41T93_FLAG_OF); + dev_warn(dev, "OF bit is set, resetting.\n"); + regmap_write(m41t93->regmap, M41T93_REG_FLAGS, tmp & ~M41T93_FLAG_OF); - tmp = spi_w8r8(spi, M41T93_REG_FLAGS); - if (tmp < 0) { - return tmp; + ret = regmap_read(m41t93->regmap, M41T93_REG_FLAGS, &tmp); + if (ret < 0) { + return ret; } else if (tmp & M41T93_FLAG_OF) { /* OF cannot be immediately reset: oscillator has to be * restarted. */ u8 reset_osc = buf[M41T93_REG_ST_SEC] | M41T93_FLAG_ST; - dev_warn(&spi->dev, + dev_warn(dev, "OF bit is still set, kickstarting clock.\n"); - m41t93_set_reg(spi, M41T93_REG_ST_SEC, reset_osc); + regmap_write(m41t93->regmap, M41T93_REG_ST_SEC, reset_osc); reset_osc &= ~M41T93_FLAG_ST; - m41t93_set_reg(spi, M41T93_REG_ST_SEC, reset_osc); + regmap_write(m41t93->regmap, M41T93_REG_ST_SEC, reset_osc); } } @@ -94,14 +89,13 @@ static int m41t93_set_time(struct device *dev, struct rtc_time *tm) data[M41T93_REG_MON] = bin2bcd(tm->tm_mon + 1); data[M41T93_REG_YEAR] = bin2bcd(tm->tm_year % 100); - return spi_write(spi, buf, sizeof(buf)); + return regmap_bulk_write(m41t93->regmap, M41T93_REG_SSEC, buf, sizeof(buf)); } static int m41t93_get_time(struct device *dev, struct rtc_time *tm) { - struct spi_device *spi = to_spi_device(dev); - const u8 start_addr = 0; + struct m41t93_data *m41t93 = dev_get_drvdata(dev); u8 buf[8]; int century_after_1900; int tmp; @@ -113,32 +107,32 @@ static int m41t93_get_time(struct device *dev, struct rtc_time *tm) case after poweron. Time is valid after resetting HT bit. 2. oscillator fail bit (OF) is set: time is invalid. */ - tmp = spi_w8r8(spi, M41T93_REG_ALM_HOUR_HT); - if (tmp < 0) - return tmp; + ret = regmap_read(m41t93->regmap, M41T93_REG_ALM_HOUR_HT, &tmp); + if (ret < 0) + return ret; if (tmp & M41T93_FLAG_HT) { - dev_dbg(&spi->dev, "HT bit is set, reenable clock update.\n"); - m41t93_set_reg(spi, M41T93_REG_ALM_HOUR_HT, - tmp & ~M41T93_FLAG_HT); + dev_dbg(dev, "HT bit is set, reenable clock update.\n"); + regmap_write(m41t93->regmap, M41T93_REG_ALM_HOUR_HT, + tmp & ~M41T93_FLAG_HT); } - tmp = spi_w8r8(spi, M41T93_REG_FLAGS); - if (tmp < 0) - return tmp; + ret = regmap_read(m41t93->regmap, M41T93_REG_FLAGS, &tmp); + if (ret < 0) + return ret; if (tmp & M41T93_FLAG_OF) { ret = -EINVAL; - dev_warn(&spi->dev, "OF bit is set, write time to restart.\n"); + dev_warn(dev, "OF bit is set, write time to restart.\n"); } if (tmp & M41T93_FLAG_BL) - dev_warn(&spi->dev, "BL bit is set, replace battery.\n"); + dev_warn(dev, "BL bit is set, replace battery.\n"); /* read actual time/date */ - tmp = spi_write_then_read(spi, &start_addr, 1, buf, sizeof(buf)); - if (tmp < 0) - return tmp; + ret = regmap_bulk_read(m41t93->regmap, M41T93_REG_SSEC, buf, sizeof(buf)); + if (ret < 0) + return ret; tm->tm_sec = bcd2bin(buf[M41T93_REG_ST_SEC]); tm->tm_min = bcd2bin(buf[M41T93_REG_MIN]); @@ -167,26 +161,51 @@ static const struct rtc_class_ops m41t93_rtc_ops = { static struct spi_driver m41t93_driver; +static const struct regmap_config regmap_config = { + .reg_bits = 8, + .val_bits = 8, + .read_flag_mask = 0x00, + .write_flag_mask = 0x80, + .zero_flag_mask = true, +}; + static int m41t93_probe(struct spi_device *spi) { - struct rtc_device *rtc; - int res; + int res, ret; + struct m41t93_data *m41t93; spi->bits_per_word = 8; spi_setup(spi); - res = spi_w8r8(spi, M41T93_REG_WDAY); + m41t93 = devm_kzalloc(&spi->dev, sizeof(struct m41t93_data), GFP_KERNEL); + + if (!m41t93) + return -ENOMEM; + + /* Set up regmap to access device registers*/ + m41t93->regmap = devm_regmap_init_spi(spi, ®map_config); + if (IS_ERR(m41t93->regmap)) { + dev_err(&spi->dev, "regmap init failure\n"); + return PTR_ERR(m41t93->regmap); + } + + ret = regmap_read(m41t93->regmap, M41T93_REG_WDAY, &res); + if (ret < 0) { + dev_err(&spi->dev, "IO error\n"); + return -EIO; + } + if (res < 0 || (res & 0xf8) != 0) { dev_err(&spi->dev, "not found 0x%x.\n", res); return -ENODEV; } - rtc = devm_rtc_device_register(&spi->dev, m41t93_driver.driver.name, - &m41t93_rtc_ops, THIS_MODULE); - if (IS_ERR(rtc)) - return PTR_ERR(rtc); + spi_set_drvdata(spi, m41t93); - spi_set_drvdata(spi, rtc); + m41t93->rtc = devm_rtc_device_register(&spi->dev, m41t93_driver.driver.name, + &m41t93_rtc_ops, THIS_MODULE); + if (IS_ERR(m41t93->rtc)) + return PTR_ERR(m41t93->rtc); return 0; } From 5b55ff7cace4c176c7ebdf9512e50ac870f17fac Mon Sep 17 00:00:00 2001 From: Akhilesh Patil Date: Sat, 20 Sep 2025 20:32:46 +0530 Subject: [PATCH 241/297] rtc: m41t93: Add alarm support Implement alarm feature for rtc-m41t93 by adding necessary callbacks - set_alarm, read_alarm and alarm_irq_enable. Enable support to configure alarm 1 out of 2 alarms present in this rtc. Support only alarm configuration in this commit. This commit does not implement alarm irq handling. Use selftests/rtc/rtctest for testing. Tested by observing IRQ pin (pin 12 of SOX18 package) on logic analyzer going low after alarm condition is met. Signed-off-by: Akhilesh Patil Link: https://patch.msgid.link/1b272ff1a5392d5eb76e129a4785ac8424763356.1758379856.git.akhilesh@ee.iitb.ac.in Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-m41t93.c | 105 +++++++++++++++++++++++++++++++++++++++ 1 file changed, 105 insertions(+) diff --git a/drivers/rtc/rtc-m41t93.c b/drivers/rtc/rtc-m41t93.c index 61e761af56ad..489bad15695d 100644 --- a/drivers/rtc/rtc-m41t93.c +++ b/drivers/rtc/rtc-m41t93.c @@ -22,6 +22,14 @@ #define M41T93_REG_DAY 5 #define M41T93_REG_MON 6 #define M41T93_REG_YEAR 7 +#define M41T93_REG_AL1_MONTH 0xa +#define M41T93_REG_AL1_DATE 0xb +#define M41T93_REG_AL1_HOUR 0xc +#define M41T93_REG_AL1_MIN 0xd +#define M41T93_REG_AL1_SEC 0xe +#define M41T93_BIT_A1IE BIT(7) +#define M41T93_BIT_ABE BIT(5) +#define M41T93_FLAG_AF1 BIT(6) #define M41T93_REG_ALM_HOUR_HT 0xc @@ -153,10 +161,107 @@ static int m41t93_get_time(struct device *dev, struct rtc_time *tm) return ret; } +static int m41t93_set_alarm(struct device *dev, struct rtc_wkalrm *alrm) +{ + struct m41t93_data *m41t93 = dev_get_drvdata(dev); + int ret; + unsigned int val; + u8 alarm_vals[5] = {0}; + + ret = regmap_bulk_write(m41t93->regmap, M41T93_REG_AL1_DATE, alarm_vals, 4); + if (ret) + return ret; + + /* Set alarm values */ + alarm_vals[0] = bin2bcd(alrm->time.tm_mon + 1) & 0x1f; + alarm_vals[1] = bin2bcd(alrm->time.tm_mday) & 0x3f; + alarm_vals[2] = bin2bcd(alrm->time.tm_hour) & 0x3f; + alarm_vals[3] = bin2bcd(alrm->time.tm_min) & 0x7f; + alarm_vals[4] = bin2bcd(alrm->time.tm_sec) & 0x7f; + + if (alrm->enabled) { + /* Enable alarm IRQ generation */ + alarm_vals[0] |= M41T93_BIT_A1IE | M41T93_BIT_ABE; + } + + /* Preserve SQWE bit */ + ret = regmap_read(m41t93->regmap, M41T93_REG_AL1_MONTH, &val); + if (ret) + return ret; + + alarm_vals[0] |= val & 0x40; + + ret = regmap_bulk_write(m41t93->regmap, M41T93_REG_AL1_MONTH, + alarm_vals, sizeof(alarm_vals)); + if (ret) + return ret; + + /* Device address pointer is now at FLAG register, move it to other location + * to finish setting alarm, as recommended by the datasheet. + * We do read of AL1_MONTH register to achieve this. + */ + ret = regmap_read(m41t93->regmap, M41T93_REG_AL1_MONTH, &val); + if (ret) + return ret; + + if (bcd2bin(val & 0x1f) == (alrm->time.tm_mon & 0x1f)) + dev_notice(dev, "Alarm set successfully\n"); + + return 0; +} + +static int m41t93_get_alarm(struct device *dev, struct rtc_wkalrm *alrm) +{ + struct m41t93_data *m41t93 = dev_get_drvdata(dev); + int ret; + unsigned int val; + u8 alarm_vals[5] = {0}; + + ret = regmap_bulk_read(m41t93->regmap, M41T93_REG_AL1_MONTH, + alarm_vals, sizeof(alarm_vals)); + if (ret) + return ret; + + alrm->time.tm_mon = bcd2bin(alarm_vals[0] & 0x1f) - 1; + alrm->time.tm_mday = bcd2bin(alarm_vals[1] & 0x3f); + alrm->time.tm_hour = bcd2bin(alarm_vals[2] & 0x3f); + alrm->time.tm_min = bcd2bin(alarm_vals[3] & 0x7f); + alrm->time.tm_sec = bcd2bin(alarm_vals[4] & 0x7f); + + alrm->enabled = !!(alarm_vals[0] & M41T93_BIT_A1IE); + + ret = regmap_read(m41t93->regmap, M41T93_REG_FLAGS, &val); + if (ret) + return ret; + + alrm->pending = (val & M41T93_FLAG_AF1) && alrm->enabled; + + return 0; +} + +static int m41t93_alarm_irq_enable(struct device *dev, unsigned int enabled) +{ + struct m41t93_data *m41t93 = dev_get_drvdata(dev); + unsigned int val; + int ret; + + val = enabled ? M41T93_BIT_A1IE | M41T93_BIT_ABE : 0; + + ret = regmap_update_bits(m41t93->regmap, M41T93_REG_AL1_MONTH, + M41T93_BIT_A1IE | M41T93_BIT_ABE, val); + if (ret) + return ret; + + return 0; +} + static const struct rtc_class_ops m41t93_rtc_ops = { .read_time = m41t93_get_time, .set_time = m41t93_set_time, + .set_alarm = m41t93_set_alarm, + .read_alarm = m41t93_get_alarm, + .alarm_irq_enable = m41t93_alarm_irq_enable, }; static struct spi_driver m41t93_driver; From 5cb6816cd81b21246f45fe9803efdc21576574e3 Mon Sep 17 00:00:00 2001 From: Akhilesh Patil Date: Sat, 20 Sep 2025 20:33:08 +0530 Subject: [PATCH 242/297] rtc: m41t93: Add square wave clock provider support Implement support to configure square wave output (SQW) of m41t93 rtc via common clock framework clock provider api. Add clock provider callbacks to control output frequency ranging from 1Hz to 32KHz as supported by this rtc chip. Use clock framework debugfs interface or clock consumer DT node to test. Tested by measuring various frequencies on pull-up connected SWQ(7) pin of m41t93 rtc chip using logic analyzer. Signed-off-by: Akhilesh Patil Link: https://patch.msgid.link/a8c4d3741be4e9dfa52c57cbd653f561ba4ed934.1758379856.git.akhilesh@ee.iitb.ac.in Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-m41t93.c | 156 ++++++++++++++++++++++++++++++++++++++- 1 file changed, 155 insertions(+), 1 deletion(-) diff --git a/drivers/rtc/rtc-m41t93.c b/drivers/rtc/rtc-m41t93.c index 489bad15695d..aaeafe06e8b4 100644 --- a/drivers/rtc/rtc-m41t93.c +++ b/drivers/rtc/rtc-m41t93.c @@ -13,6 +13,7 @@ #include #include #include +#include #define M41T93_REG_SSEC 0 #define M41T93_REG_ST_SEC 1 @@ -30,7 +31,11 @@ #define M41T93_BIT_A1IE BIT(7) #define M41T93_BIT_ABE BIT(5) #define M41T93_FLAG_AF1 BIT(6) - +#define M41T93_SRAM_BASE 0x19 +#define M41T93_REG_SQW 0x13 +#define M41T93_SQW_RS_MASK 0xf0 +#define M41T93_SQW_RS_SHIFT 4 +#define M41T93_BIT_SQWE BIT(6) #define M41T93_REG_ALM_HOUR_HT 0xc #define M41T93_REG_FLAGS 0xf @@ -43,6 +48,9 @@ struct m41t93_data { struct rtc_device *rtc; struct regmap *regmap; +#ifdef CONFIG_COMMON_CLK + struct clk_hw clks; +#endif }; static int m41t93_set_time(struct device *dev, struct rtc_time *tm) @@ -264,6 +272,146 @@ static const struct rtc_class_ops m41t93_rtc_ops = { .alarm_irq_enable = m41t93_alarm_irq_enable, }; +#ifdef CONFIG_COMMON_CLK +#define clk_sqw_to_m41t93_data(clk) \ + container_of(clk, struct m41t93_data, clks) + +/* m41t93 RTC clock output support */ +static unsigned long m41t93_clk_rates[] = { + 0, + 32768, /* RS3:RS0 = 0b0001 */ + 8192, + 4096, + 2048, + 1024, + 512, + 256, + 128, + 64, + 32, + 16, + 8, + 4, + 2, + 1, /* RS3:RS0 = 0b1111 */ +}; + +static unsigned long m41t93_clk_sqw_recalc_rate(struct clk_hw *hw, + unsigned long parent_rate) +{ + int ret; + unsigned int rate_id; + struct m41t93_data *m41t93 = clk_sqw_to_m41t93_data(hw); + + ret = regmap_read(m41t93->regmap, M41T93_REG_SQW, &rate_id); + if (ret) + return ret; + + rate_id &= M41T93_SQW_RS_MASK; + rate_id >>= M41T93_SQW_RS_SHIFT; + + return m41t93_clk_rates[rate_id]; +} + +static int m41t93_clk_sqw_determine_rate(struct clk_hw *hw, + struct clk_rate_request *req) +{ + int i; + + for (i = 1; i < ARRAY_SIZE(m41t93_clk_rates); i++) { + if (req->rate >= m41t93_clk_rates[i]) { + req->rate = m41t93_clk_rates[i]; + return 0; + } + } + + return 0; +} + +static int m41t93_clk_sqw_set_rate(struct clk_hw *hw, unsigned long rate, + unsigned long parent_rate) +{ + int id, ret; + struct m41t93_data *m41t93 = clk_sqw_to_m41t93_data(hw); + + for (id = 0; id < ARRAY_SIZE(m41t93_clk_rates); id++) { + if (m41t93_clk_rates[id] == rate) + break; + } + + if (id >= ARRAY_SIZE(m41t93_clk_rates)) + return -EINVAL; + + ret = regmap_update_bits(m41t93->regmap, M41T93_REG_SQW, + M41T93_SQW_RS_MASK, id << M41T93_SQW_RS_SHIFT); + + return ret; +} + +static int m41t93_clk_sqw_prepare(struct clk_hw *hw) +{ + int ret; + struct m41t93_data *m41t93 = clk_sqw_to_m41t93_data(hw); + + ret = regmap_update_bits(m41t93->regmap, M41T93_REG_AL1_MONTH, + M41T93_BIT_SQWE, M41T93_BIT_SQWE); + + return ret; +} + +static void m41t93_clk_sqw_unprepare(struct clk_hw *hw) +{ + struct m41t93_data *m41t93 = clk_sqw_to_m41t93_data(hw); + + regmap_update_bits(m41t93->regmap, M41T93_REG_AL1_MONTH, + M41T93_BIT_SQWE, 0); +} + +static int m41t93_clk_sqw_is_prepared(struct clk_hw *hw) +{ + int ret; + struct m41t93_data *m41t93 = clk_sqw_to_m41t93_data(hw); + unsigned int status; + + ret = regmap_read(m41t93->regmap, M41T93_REG_AL1_MONTH, &status); + if (ret) + return ret; + + return !!(status & M41T93_BIT_SQWE); +} + +static const struct clk_ops m41t93_clk_sqw_ops = { + .prepare = m41t93_clk_sqw_prepare, + .unprepare = m41t93_clk_sqw_unprepare, + .is_prepared = m41t93_clk_sqw_is_prepared, + .recalc_rate = m41t93_clk_sqw_recalc_rate, + .set_rate = m41t93_clk_sqw_set_rate, + .determine_rate = m41t93_clk_sqw_determine_rate, +}; + +static int rtc_m41t93_clks_register(struct device *dev, struct m41t93_data *m41t93) +{ + struct device_node *node = dev->of_node; + struct clk *clk; + struct clk_init_data init = {0}; + + init.name = "m41t93_clk_sqw"; + init.ops = &m41t93_clk_sqw_ops; + + m41t93->clks.init = &init; + + /* Register the clock with CCF */ + clk = devm_clk_register(dev, &m41t93->clks); + if (IS_ERR(clk)) + return PTR_ERR(clk); + + if (node) + of_clk_add_provider(node, of_clk_src_simple_get, clk); + + return 0; +} +#endif + static struct spi_driver m41t93_driver; static const struct regmap_config regmap_config = { @@ -312,6 +460,12 @@ static int m41t93_probe(struct spi_device *spi) if (IS_ERR(m41t93->rtc)) return PTR_ERR(m41t93->rtc); +#ifdef CONFIG_COMMON_CLK + ret = rtc_m41t93_clks_register(&spi->dev, m41t93); + if (ret) + dev_warn(&spi->dev, "Unable to register clock\n"); +#endif + return 0; } From 15ec2ce19962b61576c8bf25bc129fc61a653c2e Mon Sep 17 00:00:00 2001 From: Akhilesh Patil Date: Sat, 20 Sep 2025 20:33:34 +0530 Subject: [PATCH 243/297] rtc: m41t93: Add watchdog support Implement watchdog feature for m41t93 rtc with 1s resolution. Implement alarm only support (WDIOF_ALARMONLY) in this commit. Define start, stop, ping, and set_timeout callbacks as needed by the watchdog framework. Use selftests/watchdog/watchdog-test kselftest for testing. Observed IRQ pin(12) of rtc chip going low after late pinging the watchdog. Signed-off-by: Akhilesh Patil Link: https://patch.msgid.link/77c2e9f4ab0811a919595d7a5476b00abd1c2803.1758379856.git.akhilesh@ee.iitb.ac.in Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-m41t93.c | 99 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 99 insertions(+) diff --git a/drivers/rtc/rtc-m41t93.c b/drivers/rtc/rtc-m41t93.c index aaeafe06e8b4..fa7a4b5f848d 100644 --- a/drivers/rtc/rtc-m41t93.c +++ b/drivers/rtc/rtc-m41t93.c @@ -14,6 +14,7 @@ #include #include #include +#include #define M41T93_REG_SSEC 0 #define M41T93_REG_ST_SEC 1 @@ -36,6 +37,10 @@ #define M41T93_SQW_RS_MASK 0xf0 #define M41T93_SQW_RS_SHIFT 4 #define M41T93_BIT_SQWE BIT(6) +#define M41T93_REG_WATCHDOG 0x9 +#define M41T93_WDT_RB_MASK 0x3 +#define M41T93_WDT_BMB_MASK 0x7c +#define M41T93_WDT_BMB_SHIFT 2 #define M41T93_REG_ALM_HOUR_HT 0xc #define M41T93_REG_FLAGS 0xf @@ -51,6 +56,9 @@ struct m41t93_data { #ifdef CONFIG_COMMON_CLK struct clk_hw clks; #endif +#ifdef CONFIG_WATCHDOG + struct watchdog_device wdd; +#endif }; static int m41t93_set_time(struct device *dev, struct rtc_time *tm) @@ -412,6 +420,92 @@ static int rtc_m41t93_clks_register(struct device *dev, struct m41t93_data *m41t } #endif +#ifdef CONFIG_WATCHDOG +static int m41t93_wdt_ping(struct watchdog_device *wdd) +{ + u8 resolution, mult; + u8 val = 0; + int ret; + struct m41t93_data *m41t93 = watchdog_get_drvdata(wdd); + + /* Resolution supported by hardware + * 0b00 : 1/16 seconds + * 0b01 : 1/4 second + * 0b10 : 1 second + * 0b11 : 4 seconds + */ + resolution = 0x2; /* hardcode resolution to 1s */ + mult = wdd->timeout; + val = resolution | (mult << M41T93_WDT_BMB_SHIFT & M41T93_WDT_BMB_MASK); + + ret = regmap_write_bits(m41t93->regmap, M41T93_REG_WATCHDOG, + M41T93_WDT_RB_MASK | M41T93_WDT_BMB_MASK, val); + + return ret; +} + +static int m41t93_wdt_start(struct watchdog_device *wdd) +{ + return m41t93_wdt_ping(wdd); +} + +static int m41t93_wdt_stop(struct watchdog_device *wdd) +{ + struct m41t93_data *m41t93 = watchdog_get_drvdata(wdd); + + /* Write 0 to watchdog register */ + return regmap_write_bits(m41t93->regmap, M41T93_REG_WATCHDOG, + M41T93_WDT_RB_MASK | M41T93_WDT_BMB_MASK, 0); +} + +static int m41t93_wdt_set_timeout(struct watchdog_device *wdd, + unsigned int new_timeout) +{ + wdd->timeout = new_timeout; + + return 0; +} + +static const struct watchdog_info m41t93_wdt_info = { + .identity = "m41t93 rtc Watchdog", + .options = WDIOF_ALARMONLY | WDIOF_SETTIMEOUT | WDIOF_KEEPALIVEPING, +}; + +static const struct watchdog_ops m41t93_watchdog_ops = { + .owner = THIS_MODULE, + .start = m41t93_wdt_start, + .stop = m41t93_wdt_stop, + .ping = m41t93_wdt_ping, + .set_timeout = m41t93_wdt_set_timeout, +}; + +static int m41t93_watchdog_register(struct device *dev, struct m41t93_data *m41t93) +{ + int ret; + + m41t93->wdd.parent = dev; + m41t93->wdd.info = &m41t93_wdt_info; + m41t93->wdd.ops = &m41t93_watchdog_ops; + m41t93->wdd.min_timeout = 0; + m41t93->wdd.max_timeout = 10; + m41t93->wdd.timeout = 3; /* Default timeout is 3 sec */ + m41t93->wdd.status = WATCHDOG_NOWAYOUT_INIT_STATUS; + + watchdog_set_drvdata(&m41t93->wdd, m41t93); + + ret = devm_watchdog_register_device(dev, &m41t93->wdd); + if (ret) { + dev_warn(dev, "Failed to register watchdog\n"); + return ret; + } + + /* Disable watchdog at start */ + ret = m41t93_wdt_stop(&m41t93->wdd); + + return ret; +} +#endif + static struct spi_driver m41t93_driver; static const struct regmap_config regmap_config = { @@ -465,6 +559,11 @@ static int m41t93_probe(struct spi_device *spi) if (ret) dev_warn(&spi->dev, "Unable to register clock\n"); #endif +#ifdef CONFIG_WATCHDOG + ret = m41t93_watchdog_register(&spi->dev, m41t93); + if (ret) + dev_warn(&spi->dev, "Unable to register watchdog\n"); +#endif return 0; } From d4992b7050a10079bc760bdc5b8688e05a09dfc2 Mon Sep 17 00:00:00 2001 From: Adriana Stancu Date: Thu, 16 Apr 2026 07:21:51 -0700 Subject: [PATCH 244/297] rtc: bq32000: add delay between RTC reads When the RTC is used on systems without a interrupt line, userspace tools like `hwclock` fall back to a frequent polling loop to synchronize with the edge of the next second. On the BQ32000, this aggressive polling can temporarly lock the register refresh cycle, because the continuous transfers prevent the hardware from updating the buffer. This results in stale data reads or select() timeouts in userspace. This patch introduces a delay before reading the RTC registers in order to provide a sufficient idle time for the hardware to sync with the register buffer. Signed-off-by: Adriana Stancu Link: https://patch.msgid.link/20260416142151.3385827-1-adriana@arista.com Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-bq32k.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/drivers/rtc/rtc-bq32k.c b/drivers/rtc/rtc-bq32k.c index 20cd92d00fa1..573231613e52 100644 --- a/drivers/rtc/rtc-bq32k.c +++ b/drivers/rtc/rtc-bq32k.c @@ -16,6 +16,7 @@ #include #include #include +#include #define BQ32K_SECONDS 0x00 /* Seconds register address */ #define BQ32K_SECONDS_MASK 0x7F /* Mask over seconds value */ @@ -89,9 +90,17 @@ static int bq32k_write(struct device *dev, void *data, uint8_t off, uint8_t len) static int bq32k_rtc_read_time(struct device *dev, struct rtc_time *tm) { + struct i2c_client *client = to_i2c_client(dev); struct bq32k_regs regs; int error; + /* + * When the device doesn't have the interrupt connected, prevent + * userpace from polling the RTC registers too frequently. + */ + if (client->irq <= 0) + usleep_range(2000, 2500); + error = bq32k_read(dev, ®s, 0, sizeof(regs)); if (error) return error; From cc387941c0a125fb6730e7270b4bb91edead5407 Mon Sep 17 00:00:00 2001 From: Fredrik M Olsson Date: Wed, 20 May 2026 16:48:53 +0200 Subject: [PATCH 245/297] dt-bindings: rtc: ds1307: Add epson,rx8901 Add compatible string epson,rx8901 for the Epson RX8901CE RTC. Acked-by: Krzysztof Kozlowski Reviewed-by: Nobuhiro Iwamatsu Signed-off-by: Fredrik M Olsson Link: https://patch.msgid.link/20260520-ds1307-rx8901-add-v2-1-e069ea32e1db@axis.com Signed-off-by: Alexandre Belloni --- Documentation/devicetree/bindings/rtc/rtc-ds1307.yaml | 1 + 1 file changed, 1 insertion(+) diff --git a/Documentation/devicetree/bindings/rtc/rtc-ds1307.yaml b/Documentation/devicetree/bindings/rtc/rtc-ds1307.yaml index 98d10e680144..9b2796804f07 100644 --- a/Documentation/devicetree/bindings/rtc/rtc-ds1307.yaml +++ b/Documentation/devicetree/bindings/rtc/rtc-ds1307.yaml @@ -31,6 +31,7 @@ properties: - epson,rx8025 - isil,isl12057 - epson,rx8130 + - epson,rx8901 - items: - enum: From 6882aab3c66112b33b251be95c09c8ead3e8d580 Mon Sep 17 00:00:00 2001 From: Fredrik M Olsson Date: Wed, 20 May 2026 16:48:54 +0200 Subject: [PATCH 246/297] rtc: ds1307: Fix off-by-one issue with wday for rx8130 The RTC represent each weekday with a individual bit set in the WDAY register, where the 0th bit represent the first day of the week and the 6th bit represents the last day of the week. For each passed day the chip performs a rotary-left-shift by one to advance the weekday by one. The tm_wday field represent weekdays by a value in the range of 0-6. The fls() function return the bit index of the last bit set. To handle when there are no bits set it will return 0, and if the 0th bit is set it will return 1, and if the 1st bit is set it will return 2, and so on. In order to make the result of the fls() function fall into the expected range of 0-6 (instead of 1-7) this patch subtracts one from the result (which matches how the value is written in ds1307_set_time()). Fixes: 204756f016726 ("rtc: ds1307: Fix wday settings for rx8130") Reviewed-by: Nobuhiro Iwamatsu Signed-off-by: Fredrik M Olsson Link: https://patch.msgid.link/20260520-ds1307-rx8901-add-v2-2-e069ea32e1db@axis.com Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-ds1307.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/rtc/rtc-ds1307.c b/drivers/rtc/rtc-ds1307.c index 8fc258d5a1f4..a77580c4eea7 100644 --- a/drivers/rtc/rtc-ds1307.c +++ b/drivers/rtc/rtc-ds1307.c @@ -311,7 +311,7 @@ static int ds1307_get_time(struct device *dev, struct rtc_time *t) t->tm_hour = bcd2bin(tmp); /* rx8130 is bit position, not BCD */ if (ds1307->type == rx_8130) - t->tm_wday = fls(regs[DS1307_REG_WDAY] & 0x7f); + t->tm_wday = fls(regs[DS1307_REG_WDAY] & 0x7f) - 1; else t->tm_wday = bcd2bin(regs[DS1307_REG_WDAY] & 0x07) - 1; t->tm_mday = bcd2bin(regs[DS1307_REG_MDAY] & 0x3f); From 99cd0a6eeb6c20fc6b914e7ce192c6b08e1ef906 Mon Sep 17 00:00:00 2001 From: Huiwen He Date: Wed, 24 Jun 2026 10:15:46 +0800 Subject: [PATCH 247/297] smb/client: do not account EOF extension as allocation cifs_setsize() updates the local inode size after SetEOF succeeds. It also used the new EOF as a local i_blocks estimate, but extending EOF does not prove that the intervening range was allocated. For example, after writing 1 MiB and then extending EOF to 10 MiB, the client can report the file as fully allocated even though the server still reports a much smaller AllocationSize: $ dd if=/dev/zero of=test bs=1M count=1 $ truncate -s 10M test && stat -c 'size=%s blocks=%b' test $ stat --cached=never -c 'size=%s blocks=%b' test client stat: size=10485760 blocks=20480 server stat: size=10485760 blocks=2056 client stat after revalidation: size=10485760 blocks=2056 A later attribute revalidation may correct i_blocks, but callers such as xfstests generic/495 invoke swapon immediately after truncate. The swapfile hole check can therefore observe the inflated local i_blocks value and accept a sparse file. Do not grow i_blocks from cifs_setsize() on EOF extension. Only clamp it on shrink; allocation growth must come from write completion or from server-reported AllocationSize. With this change, EOF extension no longer makes a sparse file appear fully allocated before the next attribute revalidation, and xfstests generic/495 no longer accepts it through the inflated local i_blocks value. Signed-off-by: Huiwen He Reviewed-by: ChenXiaoSong Signed-off-by: Steve French --- fs/smb/client/inode.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) diff --git a/fs/smb/client/inode.c b/fs/smb/client/inode.c index 56b0f109e41b..1dbcfd163ff0 100644 --- a/fs/smb/client/inode.c +++ b/fs/smb/client/inode.c @@ -3038,13 +3038,20 @@ int cifs_fiemap(struct inode *inode, struct fiemap_extent_info *fei, u64 start, void cifs_setsize(struct inode *inode, loff_t offset) { + loff_t old_size; + u64 blocks = CIFS_INO_BLOCKS(offset); + spin_lock(&inode->i_lock); + old_size = i_size_read(inode); i_size_write(inode, offset); + /* - * Until we can query the server for actual allocation size, - * this is best estimate we have for blocks allocated for a file. + * Extending EOF does not allocate the intervening range. Only clamp + * i_blocks on shrink; allocation growth comes from writes or from the + * server-reported AllocationSize. */ - inode->i_blocks = CIFS_INO_BLOCKS(offset); + if (offset < old_size && (u64)inode->i_blocks > blocks) + inode->i_blocks = blocks; spin_unlock(&inode->i_lock); inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); truncate_pagecache(inode, offset); From a5bb580df018b5d1c5668f05f7979044fb19e23a Mon Sep 17 00:00:00 2001 From: Haoxiang Li Date: Tue, 23 Jun 2026 18:08:48 +0800 Subject: [PATCH 248/297] rtc: cmos: unregister HPET IRQ handler on probe failure cmos_do_probe() registers cmos_interrupt() as the HPET RTC IRQ handler before requesting the RTC IRQ and registering the RTC device. If either request_irq() or devm_rtc_register_device() fails afterwards, the error path leaves the HPET RTC IRQ handler installed. This leaves a stale handler behind and make a later hpet_register_irq_handler() fail with -EBUSY. Track whether the HPET handler was registered successfully and undo the registration on the probe error path. Also mask the HPET RTC IRQ bits to match the normal shutdown cleanup. Fixes: 9d8af78b0797 ("rtc: add HPET RTC emulation to RTC_DRV_CMOS") Signed-off-by: Haoxiang Li Link: https://patch.msgid.link/20260623100848.2127281-1-haoxiang_li2024@163.com Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-cmos.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/rtc/rtc-cmos.c b/drivers/rtc/rtc-cmos.c index f89ab58f5048..fa04ece151b8 100644 --- a/drivers/rtc/rtc-cmos.c +++ b/drivers/rtc/rtc-cmos.c @@ -934,6 +934,7 @@ cmos_do_probe(struct device *dev, struct resource *ports, int rtc_irq) unsigned char rtc_control; unsigned address_space; u32 flags = 0; + bool hpet_registered = false; struct nvmem_config nvmem_cfg = { .name = "cmos_nvram", .word_size = 1, @@ -1091,6 +1092,7 @@ cmos_do_probe(struct device *dev, struct resource *ports, int rtc_irq) " failed in rtc_init()."); goto cleanup1; } + hpet_registered = true; } else rtc_cmos_int_handler = cmos_interrupt; @@ -1140,6 +1142,10 @@ cleanup2: if (is_valid_irq(rtc_irq)) free_irq(rtc_irq, cmos_rtc.rtc); cleanup1: + if (hpet_registered) { + hpet_mask_rtc_irq_bit(RTC_IRQMASK); + hpet_unregister_irq_handler(cmos_interrupt); + } cmos_rtc.dev = NULL; cleanup0: if (RTC_IOMAPPED) From f53208233b2acaafe2af99c63c02481b2f5bcb39 Mon Sep 17 00:00:00 2001 From: Shyam Prasad N Date: Tue, 10 Mar 2026 16:00:17 +0530 Subject: [PATCH 249/297] cifs: define variable sized buffer for querydir responses QueryDirectory responses today are stored in one of two fixed sized buffers: smallbuf (448 bytes) or bigbuf (16KB). These are borrowed from server struct and are not sufficient for large-sized query dir operations. With this change we will now define a new buffer type specifically for cifs_search_info to hold variable sized responses. These will be allocated by kmalloc and freed by kfree. Signed-off-by: Shyam Prasad N Signed-off-by: Steve French --- fs/smb/client/cifsglob.h | 2 ++ fs/smb/client/file.c | 2 ++ fs/smb/client/readdir.c | 2 ++ fs/smb/client/smb2pdu.c | 14 +++++++++++--- 4 files changed, 17 insertions(+), 3 deletions(-) diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h index befc5eecb55c..99f9e6dca62b 100644 --- a/fs/smb/client/cifsglob.h +++ b/fs/smb/client/cifsglob.h @@ -1393,6 +1393,7 @@ struct cifs_search_info { bool emptyDir:1; bool unicode:1; bool smallBuf:1; /* so we know which buf_release function to call */ + bool is_dynamic_buf:1; /* dynamically allocated buffer - can be variable size */ }; #define ACL_NO_MODE ((umode_t)(-1)) @@ -1906,6 +1907,7 @@ enum cifs_find_flags { #define CIFS_NO_BUFFER 0 /* Response buffer not returned */ #define CIFS_SMALL_BUFFER 1 #define CIFS_LARGE_BUFFER 2 +#define CIFS_DYNAMIC_BUFFER 3 /* Dynamically allocated buffer */ #define CIFS_IOVEC 4 /* array of response buffers */ /* Type of Request to SendReceive2 */ diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c index 58430ba51b10..8b25d6c9ec5e 100644 --- a/fs/smb/client/file.c +++ b/fs/smb/client/file.c @@ -1563,6 +1563,8 @@ int cifs_closedir(struct inode *inode, struct file *file) cfile->srch_inf.ntwrk_buf_start = NULL; if (cfile->srch_inf.smallBuf) cifs_small_buf_release(buf); + else if (cfile->srch_inf.is_dynamic_buf) + kfree(buf); else cifs_buf_release(buf); } diff --git a/fs/smb/client/readdir.c b/fs/smb/client/readdir.c index 1ff77f3d1de0..a50c86bbe60f 100644 --- a/fs/smb/client/readdir.c +++ b/fs/smb/client/readdir.c @@ -732,6 +732,8 @@ find_cifs_entry(const unsigned int xid, struct cifs_tcon *tcon, loff_t pos, if (cfile->srch_inf.smallBuf) cifs_small_buf_release(cfile->srch_inf. ntwrk_buf_start); + else if (cfile->srch_inf.is_dynamic_buf) + kfree(cfile->srch_inf.ntwrk_buf_start); else cifs_buf_release(cfile->srch_inf. ntwrk_buf_start); diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c index 85642ea992d5..d058584b8f05 100644 --- a/fs/smb/client/smb2pdu.c +++ b/fs/smb/client/smb2pdu.c @@ -5673,6 +5673,8 @@ smb2_parse_query_directory(struct cifs_tcon *tcon, if (srch_inf->ntwrk_buf_start) { if (srch_inf->smallBuf) cifs_small_buf_release(srch_inf->ntwrk_buf_start); + else if (srch_inf->is_dynamic_buf) + kfree(srch_inf->ntwrk_buf_start); else cifs_buf_release(srch_inf->ntwrk_buf_start); } @@ -5692,12 +5694,18 @@ smb2_parse_query_directory(struct cifs_tcon *tcon, cifs_dbg(FYI, "num entries %d last_index %lld srch start %p srch end %p\n", srch_inf->entries_in_buffer, srch_inf->index_of_last_entry, srch_inf->srch_entries_start, srch_inf->last_entry); - if (resp_buftype == CIFS_LARGE_BUFFER) + if (resp_buftype == CIFS_LARGE_BUFFER) { srch_inf->smallBuf = false; - else if (resp_buftype == CIFS_SMALL_BUFFER) + srch_inf->is_dynamic_buf = false; + } else if (resp_buftype == CIFS_SMALL_BUFFER) { srch_inf->smallBuf = true; - else + srch_inf->is_dynamic_buf = false; + } else if (resp_buftype == CIFS_DYNAMIC_BUFFER) { + srch_inf->smallBuf = false; + srch_inf->is_dynamic_buf = true; + } else { cifs_tcon_dbg(VFS, "Invalid search buffer type\n"); + } return 0; } From 7b5944d6ed369e43aeaf37beba9f89f7fb6c633b Mon Sep 17 00:00:00 2001 From: Tiezhu Yang Date: Thu, 25 Jun 2026 13:03:47 +0800 Subject: [PATCH 250/297] LoongArch: Add THREAD_INFO_IN_TASK implementation Like other architectures such as x86, arm64, riscv, powerpc and s390, select THREAD_INFO_IN_TASK for LoongArch to move thread_info off the stack into task_struct. This follows modern kernel standards and also makes the system more secure. With this patch, thread_info is included in task_struct at an offset of 0 instead of being placed at the bottom of the kernel stack. Thus, the $tp register points to both thread_info and task_struct. To support this, introduce a per-CPU variable cpu_tasks to store the pointer to the current task_struct. This decouples the recovery of the $tp register from the stack pointer during exception entry. Then initialize cpu_tasks for the primary and secondary CPUs during arch-specific setup and SMP boot paths. To eliminate the dangerous windows during the early initialization where the cpu_tasks remains uninitialized, set_current() is invoked as early as possible in both setup_arch() and start_secondary(). This ensures the $tp recovery barrier is armed in case any early boot exceptions or kernel panics occur. Modify SAVE_SOME and handle_syscall to restore the $tp register from cpu_tasks, and also use the la_abs absolute addressing for cpu_tasks access in assembly to bypass the relocation limits within exception handling sections. By advancing the preservation of u0 in SAVE_SOME, we reuse the PERCPU_BASE_KS value in u0 for the cpu_tasks calculation, effectively eliminating a duplicate csrrd instruction execution on SMP platforms. Update and to fully support the CONFIG_THREAD_INFO_IN_TASK feature. Remove the obsolete next_ti argument from __switch_to(), which shifts the remaining arguments ahead in the calling convention (sched_ra from a3 to a2, and sched_cfa from a4 to a3). Under the new configuration, __switch_to() now directly derives the thread pointer ($tp) from the next task_struct pointer in a1. To preserve the optimal and clean "move tp, a1" path for 64-bit kernels, the thread pointer ($tp) is assigned directly from a1 in the core path. For 32-bit kernels, where a1 carries a 2000-byte structural pointer bias at entry, an explicit adjustment "PTR_ADDI tp, tp, -TASK_STRUCT_OFFSET" is introduced at the function exit. In the context of __switch_to(), local interrupts are disabled, and the kernel is in a critical switching phase where handling any synchronous exception is practically impossible and prohibited. If any synchronous exception or watchpoint does trigger in this narrow window, it constitutes a fatal double fault and the kernel is expected to die/panic immediately anyway. Therefore, the temporary biased value in $tp is safe and acceptable here. Additionally, evaluate the stack lookup as a single load instruction "LONG_LPTR t0, a1, (TASK_STACK - TASK_STRUCT_OFFSET)", this perfectly satisfies both 32-bit and 64-bit kernels. Using the "next" pointer in a1 as the base register, rather than $tp, effectively unchains the data dependency (RAW hazard) from the preceding move instruction, maximizing the instruction-level parallelism and superscalar execution efficiency while naturally adapting the structural shift. With CONFIG_THREAD_INFO_IN_TASK enabled, the kernel stack life cycle is decoupled from task_struct and can be freed concurrently. Currently, show_stacktrace() reads raw stack data via __get_addr() and subsequently calls show_backtrace() to unwind the frame, without holding any reference to the target task's stack. If show_stacktrace() is called on a concurrently exiting task, it could attempt to read from a freed or reallocated kernel stack. This introduces a severe use-after-free (UAF) read risk or kernel panics. Wrap the entire stack inspection process inside show_stacktrace() with a try_get_task_stack() and put_task_stack() pair. This ensures the task stack remains pinned safely during both the raw stack data dump loop and the subsequent stack unwinding phase. Also, ensure that the task pointer is initialized to "current" early if it is NULL, so that try_get_task_stack() always operates on a valid task reference. Signed-off-by: Tiezhu Yang Signed-off-by: Huacai Chen --- .../core/thread-info-in-task/arch-support.txt | 2 +- arch/loongarch/Kconfig | 1 + arch/loongarch/include/asm/current.h | 31 +++++++++++++++++++ arch/loongarch/include/asm/percpu.h | 1 - arch/loongarch/include/asm/smp.h | 3 +- arch/loongarch/include/asm/stackframe.h | 10 ++++-- arch/loongarch/include/asm/switch_to.h | 7 ++--- arch/loongarch/include/asm/thread_info.h | 10 ------ arch/loongarch/kernel/asm-offsets.c | 6 ++-- arch/loongarch/kernel/entry.S | 7 +++-- arch/loongarch/kernel/head.S | 18 ++++++----- arch/loongarch/kernel/process.c | 2 ++ arch/loongarch/kernel/relocate.c | 2 +- arch/loongarch/kernel/setup.c | 1 + arch/loongarch/kernel/smp.c | 6 ++-- arch/loongarch/kernel/switch.S | 14 +++++---- arch/loongarch/kernel/traps.c | 8 +++++ 17 files changed, 88 insertions(+), 41 deletions(-) create mode 100644 arch/loongarch/include/asm/current.h diff --git a/Documentation/features/core/thread-info-in-task/arch-support.txt b/Documentation/features/core/thread-info-in-task/arch-support.txt index f3d744c76061..e26efdfbb6b4 100644 --- a/Documentation/features/core/thread-info-in-task/arch-support.txt +++ b/Documentation/features/core/thread-info-in-task/arch-support.txt @@ -12,7 +12,7 @@ | arm64: | ok | | csky: | TODO | | hexagon: | TODO | - | loongarch: | TODO | + | loongarch: | ok | | m68k: | TODO | | microblaze: | TODO | | mips: | TODO | diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig index 606597da46b8..cf8d3cf91814 100644 --- a/arch/loongarch/Kconfig +++ b/arch/loongarch/Kconfig @@ -210,6 +210,7 @@ config LOONGARCH select SYSCTL_ARCH_UNALIGN_NO_WARN select SYSCTL_EXCEPTION_TRACE select SWIOTLB if 64BIT + select THREAD_INFO_IN_TASK select TRACE_IRQFLAGS_SUPPORT select USE_PERCPU_NUMA_NODE_ID select USER_STACKTRACE_SUPPORT diff --git a/arch/loongarch/include/asm/current.h b/arch/loongarch/include/asm/current.h new file mode 100644 index 000000000000..fa4fb7987075 --- /dev/null +++ b/arch/loongarch/include/asm/current.h @@ -0,0 +1,31 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __ASM_LOONGARCH_CURRENT_H +#define __ASM_LOONGARCH_CURRENT_H + +#include + +#ifndef __ASSEMBLER__ + +#include + +struct task_struct; + +DECLARE_PER_CPU(struct task_struct *, cpu_tasks); + +register struct task_struct *current_thread_pointer __asm__("$tp"); + +static __always_inline struct task_struct *get_current(void) +{ + return current_thread_pointer; +} + +#define current get_current() + +static __always_inline void set_current(struct task_struct *task) +{ + __this_cpu_write(cpu_tasks, task); +} + +#endif /* __ASSEMBLER__ */ + +#endif /* __ASM_LOONGARCH_CURRENT_H */ diff --git a/arch/loongarch/include/asm/percpu.h b/arch/loongarch/include/asm/percpu.h index 583f2466262f..500c51754ea5 100644 --- a/arch/loongarch/include/asm/percpu.h +++ b/arch/loongarch/include/asm/percpu.h @@ -5,7 +5,6 @@ #ifndef __ASM_PERCPU_H #define __ASM_PERCPU_H -#include #include /* diff --git a/arch/loongarch/include/asm/smp.h b/arch/loongarch/include/asm/smp.h index 3a47f52959a8..dd1457065690 100644 --- a/arch/loongarch/include/asm/smp.h +++ b/arch/loongarch/include/asm/smp.h @@ -81,8 +81,9 @@ extern int __cpu_logical_map[NR_CPUS]; struct seq_file; struct secondary_data { + unsigned long task; unsigned long stack; - unsigned long thread_info; + unsigned long offset; }; extern struct secondary_data cpuboot_data; diff --git a/arch/loongarch/include/asm/stackframe.h b/arch/loongarch/include/asm/stackframe.h index ecc8e50fffa8..79526fa423a7 100644 --- a/arch/loongarch/include/asm/stackframe.h +++ b/arch/loongarch/include/asm/stackframe.h @@ -184,6 +184,7 @@ .cfi_rel_offset ra, PT_ERA .endif cfi_st tp, PT_R2, \docfi + cfi_st u0, PT_R21, \docfi cfi_st fp, PT_R22, \docfi /* Set thread_info if we're coming from user mode */ @@ -191,10 +192,13 @@ andi t0, t0, 0x3 /* extract pplv bit */ beqz t0, 9f - LONG_LI tp, ~_THREAD_MASK - and tp, tp, sp - cfi_st u0, PT_R21, \docfi csrrd u0, PERCPU_BASE_KS + + la_abs t1, cpu_tasks +#ifdef CONFIG_SMP + LONG_ADD t1, t1, u0 +#endif + LONG_L tp, t1, 0 9: #ifdef CONFIG_KGDB li.w t0, CSR_CRMD_WE diff --git a/arch/loongarch/include/asm/switch_to.h b/arch/loongarch/include/asm/switch_to.h index 5b225aff3ba2..27acbf913774 100644 --- a/arch/loongarch/include/asm/switch_to.h +++ b/arch/loongarch/include/asm/switch_to.h @@ -15,7 +15,6 @@ struct task_struct; * __switch_to - switch execution of a task * @prev: The task previously executed. * @next: The task to begin executing. - * @next_ti: task_thread_info(next). * @sched_ra: __schedule return address. * @sched_cfa: __schedule call frame address. * @@ -23,8 +22,7 @@ struct task_struct; * the context of next. Returns prev. */ extern asmlinkage struct task_struct *__switch_to(struct task_struct *prev, - struct task_struct *next, struct thread_info *next_ti, - void *sched_ra, void *sched_cfa); + struct task_struct *next, void *sched_ra, void *sched_cfa); /* * For newly created kernel threads switch_to() will return to @@ -37,7 +35,8 @@ do { \ lose_fpu_inatomic(1, prev); \ lose_lbt_inatomic(1, prev); \ hw_breakpoint_thread_switch(next); \ - (last) = __switch_to(prev, next, task_thread_info(next), \ + set_current(next); \ + (last) = __switch_to(prev, next, \ __builtin_return_address(0), __builtin_frame_address(0)); \ } while (0) diff --git a/arch/loongarch/include/asm/thread_info.h b/arch/loongarch/include/asm/thread_info.h index 4d7117fcdc78..41eabe4fb647 100644 --- a/arch/loongarch/include/asm/thread_info.h +++ b/arch/loongarch/include/asm/thread_info.h @@ -22,7 +22,6 @@ * must also be changed */ struct thread_info { - struct task_struct *task; /* main task structure */ unsigned long flags; /* low level flags */ unsigned long tp_value; /* thread pointer */ __u32 cpu; /* current CPU */ @@ -37,20 +36,11 @@ struct thread_info { */ #define INIT_THREAD_INFO(tsk) \ { \ - .task = &tsk, \ .flags = _TIF_FIXADE, \ .cpu = 0, \ .preempt_count = INIT_PREEMPT_COUNT, \ } -/* How to get the thread information struct from C. */ -register struct thread_info *__current_thread_info __asm__("$tp"); - -static inline struct thread_info *current_thread_info(void) -{ - return __current_thread_info; -} - register unsigned long current_stack_pointer __asm__("$sp"); #endif /* !__ASSEMBLER__ */ diff --git a/arch/loongarch/kernel/asm-offsets.c b/arch/loongarch/kernel/asm-offsets.c index 2cc953f113ac..1b861cbc5e10 100644 --- a/arch/loongarch/kernel/asm-offsets.c +++ b/arch/loongarch/kernel/asm-offsets.c @@ -70,7 +70,7 @@ static void __used output_task_defines(void) { COMMENT("LoongArch task_struct offsets."); OFFSET(TASK_STATE, task_struct, __state); - OFFSET(TASK_THREAD_INFO, task_struct, stack); + OFFSET(TASK_STACK, task_struct, stack); OFFSET(TASK_FLAGS, task_struct, flags); OFFSET(TASK_MM, task_struct, mm); OFFSET(TASK_PID, task_struct, pid); @@ -84,7 +84,6 @@ static void __used output_task_defines(void) static void __used output_thread_info_defines(void) { COMMENT("LoongArch thread_info offsets."); - OFFSET(TI_TASK, thread_info, task); OFFSET(TI_FLAGS, thread_info, flags); OFFSET(TI_TP_VALUE, thread_info, tp_value); OFFSET(TI_CPU, thread_info, cpu); @@ -266,8 +265,9 @@ static void __used output_signal_defines(void) static void __used output_smpboot_defines(void) { COMMENT("Linux smp cpu boot offsets."); + OFFSET(CPU_BOOT_TASK, secondary_data, task); OFFSET(CPU_BOOT_STACK, secondary_data, stack); - OFFSET(CPU_BOOT_TINFO, secondary_data, thread_info); + OFFSET(CPU_BOOT_OFFSET, secondary_data, offset); BLANK(); } #endif diff --git a/arch/loongarch/kernel/entry.S b/arch/loongarch/kernel/entry.S index b53d333a7c42..53bce27f516b 100644 --- a/arch/loongarch/kernel/entry.S +++ b/arch/loongarch/kernel/entry.S @@ -67,8 +67,11 @@ SYM_CODE_START(handle_syscall) #endif move u0, t0 - LONG_LI tp, ~_THREAD_MASK - and tp, tp, sp + la_abs t1, cpu_tasks +#ifdef CONFIG_SMP + LONG_ADD t1, t1, u0 +#endif + LONG_L tp, t1, 0 move a0, sp bl do_syscall diff --git a/arch/loongarch/kernel/head.S b/arch/loongarch/kernel/head.S index 4eed7bc312a8..601ddd78b233 100644 --- a/arch/loongarch/kernel/head.S +++ b/arch/loongarch/kernel/head.S @@ -74,10 +74,11 @@ SYM_CODE_START(kernel_entry) # kernel entry point /* GPR21 used for percpu base (runtime), initialized as 0 */ move u0, zero - la.pcrel tp, init_thread_union - /* Set the SP after an empty pt_regs. */ - PTR_LI sp, (_THREAD_SIZE - PT_SIZE) - PTR_ADD sp, sp, tp + la.pcrel tp, init_task + la.pcrel t0, init_stack + PTR_LI t1, _THREAD_SIZE + PTR_ADD t0, t0, t1 + PTR_ADDI sp, t0, -PT_SIZE set_saved_sp sp, t0, t1 #ifdef CONFIG_RELOCATABLE @@ -86,8 +87,10 @@ SYM_CODE_START(kernel_entry) # kernel entry point #ifdef CONFIG_RANDOMIZE_BASE /* Repoint the sp into the new kernel */ - PTR_LI sp, (_THREAD_SIZE - PT_SIZE) - PTR_ADD sp, sp, tp + LONG_LPTR t0, tp, TASK_STACK + PTR_LI t1, _THREAD_SIZE + PTR_ADD t0, t0, t1 + PTR_ADDI sp, t0, -PT_SIZE set_saved_sp sp, t0, t1 /* Jump to the new kernel: new_pc = current_pc + random_offset */ @@ -127,8 +130,9 @@ SYM_CODE_START(smpboot_entry) csrxchg t0, t1, LOONGARCH_CSR_IMPCTL1 #endif la.pcrel t0, cpuboot_data + ld.d tp, t0, CPU_BOOT_TASK ld.d sp, t0, CPU_BOOT_STACK - ld.d tp, t0, CPU_BOOT_TINFO + ld.d u0, t0, CPU_BOOT_OFFSET bl start_secondary ASM_BUG() diff --git a/arch/loongarch/kernel/process.c b/arch/loongarch/kernel/process.c index 5505fc355e1b..baa683fbfc53 100644 --- a/arch/loongarch/kernel/process.c +++ b/arch/loongarch/kernel/process.c @@ -60,6 +60,8 @@ unsigned long __stack_chk_guard __read_mostly; EXPORT_SYMBOL(__stack_chk_guard); #endif +DEFINE_PER_CPU(struct task_struct *, cpu_tasks); + /* * Idle related variables and functions */ diff --git a/arch/loongarch/kernel/relocate.c b/arch/loongarch/kernel/relocate.c index 4b61a9632a98..2a42874e5eb7 100644 --- a/arch/loongarch/kernel/relocate.c +++ b/arch/loongarch/kernel/relocate.c @@ -313,7 +313,7 @@ unsigned long __init relocate_kernel(void) reloc_offset += random_offset; /* The current thread is now within the relocated kernel */ - __current_thread_info = RELOCATED_KASLR(__current_thread_info); + current_thread_pointer = RELOCATED_KASLR(current_thread_pointer); update_reloc_offset(&reloc_offset, random_offset); } diff --git a/arch/loongarch/kernel/setup.c b/arch/loongarch/kernel/setup.c index 839b23edee87..369262117c63 100644 --- a/arch/loongarch/kernel/setup.c +++ b/arch/loongarch/kernel/setup.c @@ -593,6 +593,7 @@ void __init setup_arch(char **cmdline_p) { cpu_probe(); unwind_init(); + set_current(current); init_environ(); efi_init(); diff --git a/arch/loongarch/kernel/smp.c b/arch/loongarch/kernel/smp.c index 64a048f1b880..b4fb45440d65 100644 --- a/arch/loongarch/kernel/smp.c +++ b/arch/loongarch/kernel/smp.c @@ -400,8 +400,9 @@ void loongson_boot_secondary(int cpu, struct task_struct *idle) pr_info("Booting CPU#%d...\n", cpu); entry = __pa_symbol((unsigned long)&smpboot_entry); - cpuboot_data.stack = (unsigned long)__KSTK_TOS(idle); - cpuboot_data.thread_info = (unsigned long)task_thread_info(idle); + cpuboot_data.task = (unsigned long)idle; + cpuboot_data.stack = (unsigned long)task_pt_regs(idle); + cpuboot_data.offset = per_cpu_offset(cpu); csr_mail_send(entry, cpu_logical_map(cpu), 0); @@ -663,6 +664,7 @@ asmlinkage void start_secondary(void) set_my_cpu_offset(per_cpu_offset(cpu)); cpu_probe(); + set_current(current); constant_clockevent_init(); loongson_init_secondary(); diff --git a/arch/loongarch/kernel/switch.S b/arch/loongarch/kernel/switch.S index f377d8f5c51a..d6e0d05d6fd3 100644 --- a/arch/loongarch/kernel/switch.S +++ b/arch/loongarch/kernel/switch.S @@ -12,7 +12,7 @@ /* * task_struct *__switch_to(task_struct *prev, task_struct *next, - * struct thread_info *next_ti, void *sched_ra, void *sched_cfa) + * void *sched_ra, void *sched_cfa) */ .align 5 SYM_FUNC_START(__switch_to) @@ -24,8 +24,8 @@ SYM_FUNC_START(__switch_to) LONG_SPTR t1, a0, (THREAD_CSRPRMD - TASK_STRUCT_OFFSET) cpu_save_nonscratch a0 - LONG_SPTR a3, a0, (THREAD_SCHED_RA - TASK_STRUCT_OFFSET) - LONG_SPTR a4, a0, (THREAD_SCHED_CFA - TASK_STRUCT_OFFSET) + LONG_SPTR a2, a0, (THREAD_SCHED_RA - TASK_STRUCT_OFFSET) + LONG_SPTR a3, a0, (THREAD_SCHED_CFA - TASK_STRUCT_OFFSET) #if defined(CONFIG_STACKPROTECTOR) && !defined(CONFIG_SMP) la t7, __stack_chk_guard @@ -33,11 +33,12 @@ SYM_FUNC_START(__switch_to) LONG_SPTR t8, t7, 0 #endif - move tp, a2 + move tp, a1 cpu_restore_nonscratch a1 - li.w t0, _THREAD_SIZE - PTR_ADD t0, t0, tp + LONG_LPTR t0, a1, (TASK_STACK - TASK_STRUCT_OFFSET) + PTR_LI t1, _THREAD_SIZE + PTR_ADD t0, t0, t1 set_saved_sp t0, t1, t2 LONG_LPTR t1, a1, (THREAD_CSRPRMD - TASK_STRUCT_OFFSET) @@ -45,6 +46,7 @@ SYM_FUNC_START(__switch_to) #ifdef CONFIG_32BIT PTR_ADDI a0, a0, -TASK_STRUCT_OFFSET + PTR_ADDI tp, tp, -TASK_STRUCT_OFFSET #endif jr ra SYM_FUNC_END(__switch_to) diff --git a/arch/loongarch/kernel/traps.c b/arch/loongarch/kernel/traps.c index 5d49b742e3bf..776523747ea3 100644 --- a/arch/loongarch/kernel/traps.c +++ b/arch/loongarch/kernel/traps.c @@ -107,6 +107,12 @@ static void show_stacktrace(struct task_struct *task, unsigned long stackdata; unsigned long *sp = (unsigned long *)regs->regs[3]; + if (!task) + task = current; + + if (!try_get_task_stack(task)) + return; + printk("%sStack :", loglvl); i = 0; while ((unsigned long) sp & (PAGE_SIZE - 1)) { @@ -129,6 +135,8 @@ static void show_stacktrace(struct task_struct *task, } pr_cont("\n"); show_backtrace(task, regs, loglvl, user); + + put_task_stack(task); } void show_stack(struct task_struct *task, unsigned long *sp, const char *loglvl) From 6061e65f95713b01f4313cda6637dfe3aa5412b4 Mon Sep 17 00:00:00 2001 From: Huacai Chen Date: Thu, 25 Jun 2026 13:03:47 +0800 Subject: [PATCH 251/297] LoongArch: Add PIO for early access before ACPI PCI root register For ACPI system we suppose the ISA/LPC PIO range is registered together with PCI root bridge. But the fact is there may be some early access to the ISA/LPC PIO range before ACPI PCI root register (most of them are due to abnormal BIOS). Unconditionally register the ISA/LPC PIO range usually causes ACPI PCI root register fail because of the address range confliction. So we add a pair of helpers: acpi_add_early_pio() to add PIO for early access, and acpi_remove_early_pio() to remove PIO before PCI root register. Since acpi_remove_early_pio() may be called multiple times, we add an acpi_pio flag to ensure PIO be removed only once. Cc: Tested-by: Yuanzhen Gan Signed-off-by: Huacai Chen --- arch/loongarch/include/asm/acpi.h | 2 ++ arch/loongarch/kernel/acpi.c | 28 ++++++++++++++++++++++++++++ arch/loongarch/kernel/setup.c | 2 ++ arch/loongarch/pci/acpi.c | 2 ++ 4 files changed, 34 insertions(+) diff --git a/arch/loongarch/include/asm/acpi.h b/arch/loongarch/include/asm/acpi.h index eda9d4d0a493..c05168aedcaa 100644 --- a/arch/loongarch/include/asm/acpi.h +++ b/arch/loongarch/include/asm/acpi.h @@ -38,6 +38,8 @@ static inline bool acpi_has_cpu_in_madt(void) extern struct list_head acpi_wakeup_device_list; extern struct acpi_madt_core_pic acpi_core_pic[MAX_CORE_PIC]; +extern void acpi_add_early_pio(void); +extern void acpi_remove_early_pio(void); extern int __init parse_acpi_topology(void); #endif /* !CONFIG_ACPI */ diff --git a/arch/loongarch/kernel/acpi.c b/arch/loongarch/kernel/acpi.c index 058f0dbe8e8f..8f650c9ffecd 100644 --- a/arch/loongarch/kernel/acpi.c +++ b/arch/loongarch/kernel/acpi.c @@ -16,6 +16,7 @@ #include #include #include +#include #include #include #include @@ -59,6 +60,33 @@ void __iomem *acpi_os_ioremap(acpi_physical_address phys, acpi_size size) return ioremap_cache(phys, size); } +#define PIO_BASE (unsigned long)PCI_IOBASE +#define PIO_SIZE ALIGN(ISA_IOSIZE, PAGE_SIZE) + +static bool acpi_pio; + +/* Add PIO for early access */ +void acpi_add_early_pio(void) +{ + if (!acpi_disabled) { + acpi_pio = true; + vmap_page_range(PIO_BASE, PIO_BASE + PIO_SIZE, + LOONGSON_LIO_BASE, pgprot_device(PAGE_KERNEL)); + } +} + +/* Remove PIO for PCI register */ +void acpi_remove_early_pio(void) +{ + if (!acpi_pio) + return; + + if (!acpi_disabled) { + acpi_pio = false; + vunmap_range(PIO_BASE, PIO_BASE + PIO_SIZE); + } +} + #ifdef CONFIG_SMP static int set_processor_mask(u32 id, u32 pass) { diff --git a/arch/loongarch/kernel/setup.c b/arch/loongarch/kernel/setup.c index 369262117c63..eaebb52bd36e 100644 --- a/arch/loongarch/kernel/setup.c +++ b/arch/loongarch/kernel/setup.c @@ -502,6 +502,8 @@ static __init int arch_reserve_pio_range(void) { struct device_node *np; + acpi_add_early_pio(); + for_each_node_by_name(np, "isa") { struct of_range range; struct of_range_parser parser; diff --git a/arch/loongarch/pci/acpi.c b/arch/loongarch/pci/acpi.c index b02698a338ee..ccbcea61fcd9 100644 --- a/arch/loongarch/pci/acpi.c +++ b/arch/loongarch/pci/acpi.c @@ -65,6 +65,8 @@ static int acpi_prepare_root_resources(struct acpi_pci_root_info *ci) struct resource_entry *entry, *tmp; struct acpi_device *device = ci->bridge; + acpi_remove_early_pio(); + status = acpi_pci_probe_root_resources(ci); if (status > 0) { acpi_evaluate_integer(device->handle, "PCIH", NULL, &pci_h); From f2539c56c74691e7a88af6372ba2b48c06ed2fe4 Mon Sep 17 00:00:00 2001 From: Huacai Chen Date: Thu, 25 Jun 2026 13:03:49 +0800 Subject: [PATCH 252/297] LoongArch: Report dying CPU to RCU in stop_this_cpu() This is a port of MIPS commit 9f3f3bdc6d9dac1 ("MIPS: smp: report dying CPU to RCU in stop_this_cpu()"). smp_send_stop() parks all secondary CPUs in stop_this_cpu(). And the function marks the CPU offline for the scheduler via set_cpu_online(false) but never informs RCU, so RCU keeps expecting a quiescent state from CPUs that are now spinning forever with interrupts disabled. As long as nothing waits for an RCU grace period after smp_send_stop() this is harmless, which is why it went unnoticed. However, since commit 91840be8f710370 ("irq_work: Fix use-after-free in irq_work_single() on PREEMPT_RT"), irq_work_sync() calls synchronize_rcu() on architectures without an irq_work self-IPI, i.e. where arch_irq_work_has_interrupt() returns false. Any irq_work_sync() issued in the reboot/shutdown/halt path after smp_send_stop() then blocks on a grace period that can never complete, hanging the reboot: WARNING: CPU: 0 PID: 15 at kernel/irq_work.c:144 irq_work_queue_on ... rcu: INFO: rcu_sched detected stalls on CPUs/tasks: rcu: Offline CPU 1 blocking current GP. rcu: Offline CPU 2 blocking current GP. rcu: Offline CPU 3 blocking current GP. This issue needs some hacks to reproduce, and it was not noticed on LoongArch because arch_irq_work_has_interrupt() usually returns true. Call rcutree_report_cpu_dead() once interrupts are disabled, mirroring the generic CPU-hotplug offline path, so RCU stops waiting on the parked CPUs and grace periods can still complete. LoongArch shuts down all CPUs here without going through the CPU-hotplug mechanism, so this report is not otherwise issued. Cc: Fixes: 91840be8f710 ("irq_work: Fix use-after-free in irq_work_single() on PREEMPT_RT") Reviewed-by: Guo Ren Signed-off-by: Huacai Chen --- arch/loongarch/kernel/smp.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/loongarch/kernel/smp.c b/arch/loongarch/kernel/smp.c index b4fb45440d65..38ae08e613c7 100644 --- a/arch/loongarch/kernel/smp.c +++ b/arch/loongarch/kernel/smp.c @@ -707,6 +707,7 @@ static void stop_this_cpu(void *dummy) set_cpu_online(smp_processor_id(), false); calculate_cpu_foreign_map(); local_irq_disable(); + rcutree_report_cpu_dead(); while (true); } From d4e58d2c21d94282d512979dfa7e045c5034b0be Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E8=B0=A2=E8=87=B4=E9=82=A6=20=28XIE=20Zhibang=29?= Date: Thu, 25 Jun 2026 13:03:49 +0800 Subject: [PATCH 253/297] LoongArch: Move struct kimage forward declaration before use MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit arch_kimage_file_post_load_cleanup() and load_other_segments(), both inside the CONFIG_KEXEC_FILE block, take a struct kimage pointer before the forward declaration appears. Move the forward declaration above so it precedes its first use instead of relying on a transitive include. Fixes: d162feec6b6e ("LoongArch: Add preparatory infrastructure for kexec_file") Signed-off-by: 谢致邦 (XIE Zhibang) Signed-off-by: Huacai Chen --- arch/loongarch/include/asm/kexec.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/loongarch/include/asm/kexec.h b/arch/loongarch/include/asm/kexec.h index 209fa43222e1..6be136e9f0a0 100644 --- a/arch/loongarch/include/asm/kexec.h +++ b/arch/loongarch/include/asm/kexec.h @@ -41,6 +41,8 @@ struct kimage_arch { unsigned long systable_ptr; }; +struct kimage; + #ifdef CONFIG_KEXEC_FILE extern const struct kexec_file_ops kexec_efi_ops; extern const struct kexec_file_ops kexec_elf_ops; @@ -59,7 +61,6 @@ typedef void (*do_kexec_t)(unsigned long efi_boot, unsigned long start_addr, unsigned long first_ind_entry); -struct kimage; extern const unsigned char relocate_new_kernel[]; extern const size_t relocate_new_kernel_size; extern void kexec_reboot(void); From 018e9828eb523c638fa3d9bdf0fd4956b74555b2 Mon Sep 17 00:00:00 2001 From: Hongchen Zhang Date: Thu, 25 Jun 2026 13:03:49 +0800 Subject: [PATCH 254/297] LoongArch: Fix missing dirty page tracking in {pte,pmd}_wrprotect() When hardware page table walker (PTW) is enabled on LoongArch, the CPU may set _PAGE_DIRTY directly in the page table entry during a write TLB miss, without going through the software TLB store handler. The software TLB store handler (tlbex.S:254) sets both _PAGE_DIRTY and_PAGE_MODIFIED together: ori t0, t0, (_PAGE_VALID | _PAGE_DIRTY | _PAGE_MODIFIED) Since hardware PTW only sets _PAGE_DIRTY, the software-only bit, i.e. _PAGE_MODIFIED is left unchanged. This creates a window where a PTE has _PAGE_DIRTY set (hardware knows the page is dirty) but _PAGE_MODIFIED clear (software is unaware). When fork()/clone() triggers copy-on-write, __copy_present_ptes() calls pte_wrprotect(), which unconditionally clears both the _PAGE_WRITE and _PAGE_DIRTY bits: pte_val(pte) &= ~(_PAGE_WRITE | _PAGE_DIRTY); Since _PAGE_MODIFIED was never set, the dirtiness information is lost completely. Subsequently, when memory pressure triggers page reclaim, page_mkclean() / try_to_unmap() sees the page as clean (i.e. pte_dirty() returns false) and the page may be freed without writeback, causing data corruption. Fix this by propagating the _PAGE_DIRTY bit to the _PAGE_MODIFIED bit in both pte_wrprotect() and pmd_wrprotect() before clearing writeable bits: if (pte_val(pte) & _PAGE_DIRTY) pte_val(pte) |= _PAGE_MODIFIED; The pmd_wrprotect() fix handles the CONFIG_TRANSPARENT_HUGEPAGE case, where pmd entries need the same treatment. This ensures the software dirty tracking bit (checked by pte_dirty() and pmd_dirty(), which read both the _PAGE_DIRTY and _PAGE_MODIFIED bits) is preserved across fork COW write-protection. The issue was found by the LTP madvise09 test case, which exercises page reclaim after "madvise(MADV_FREE), write and fork" operation sequence on private anonymous mappings. Cc: stable@vger.kernel.org Fixes: 09cfefb7fa70 ("LoongArch: Add memory management") Co-developed-by: Tianyang Zhang Signed-off-by: Tianyang Zhang Signed-off-by: Hongchen Zhang Signed-off-by: Huacai Chen --- arch/loongarch/include/asm/pgtable.h | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/arch/loongarch/include/asm/pgtable.h b/arch/loongarch/include/asm/pgtable.h index 2a0b63ae421f..223528c04d73 100644 --- a/arch/loongarch/include/asm/pgtable.h +++ b/arch/loongarch/include/asm/pgtable.h @@ -429,6 +429,8 @@ static inline pte_t pte_mkwrite_novma(pte_t pte) static inline pte_t pte_wrprotect(pte_t pte) { + if (pte_val(pte) & _PAGE_DIRTY) + pte_val(pte) |= _PAGE_MODIFIED; pte_val(pte) &= ~(_PAGE_WRITE | _PAGE_DIRTY); return pte; } @@ -535,6 +537,8 @@ static inline pmd_t pmd_mkwrite_novma(pmd_t pmd) static inline pmd_t pmd_wrprotect(pmd_t pmd) { + if (pmd_val(pmd) & _PAGE_DIRTY) + pmd_val(pmd) |= _PAGE_MODIFIED; pmd_val(pmd) &= ~(_PAGE_WRITE | _PAGE_DIRTY); return pmd; } From 70378a710598432f13509bdc16a1c0f06b3ecb53 Mon Sep 17 00:00:00 2001 From: Xuewen Wang Date: Thu, 25 Jun 2026 13:03:49 +0800 Subject: [PATCH 255/297] LoongArch: Fix nr passing in set_direct_map_valid_noflush() set_direct_map_valid_noflush() incorrectly passes 1 to __set_memory() instead of nr. This causes only the first page's attr to be updated when nr > 1. Other architectures all pass nr correctly. Cc: stable@vger.kernel.org Fixes: 0c6378a71574 ("arch: introduce set_direct_map_valid_noflush()") Signed-off-by: Xuewen Wang Signed-off-by: Huacai Chen --- arch/loongarch/mm/pageattr.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/loongarch/mm/pageattr.c b/arch/loongarch/mm/pageattr.c index f5e910b68229..614ccc7afccb 100644 --- a/arch/loongarch/mm/pageattr.c +++ b/arch/loongarch/mm/pageattr.c @@ -234,5 +234,5 @@ int set_direct_map_valid_noflush(struct page *page, unsigned nr, bool valid) clear = __pgprot(_PAGE_PRESENT | _PAGE_VALID); } - return __set_memory(addr, 1, set, clear); + return __set_memory(addr, nr, set, clear); } From c2bd59bf44d6cd1a0bbb23a55e17b24bfb6b3df8 Mon Sep 17 00:00:00 2001 From: Bastian Blank Date: Thu, 25 Jun 2026 13:03:50 +0800 Subject: [PATCH 256/297] LoongArch: Add build salt to the vDSO The vDSO needs to have a unique build id in a similar manner to the kernel and modules. Use the build salt macro. Signed-off-by: Bastian Blank Signed-off-by: Huacai Chen --- arch/loongarch/vdso/elf.S | 3 +++ 1 file changed, 3 insertions(+) diff --git a/arch/loongarch/vdso/elf.S b/arch/loongarch/vdso/elf.S index 9bb21b9f9583..d6e000003b85 100644 --- a/arch/loongarch/vdso/elf.S +++ b/arch/loongarch/vdso/elf.S @@ -7,9 +7,12 @@ #include +#include #include #include ELFNOTE_START(Linux, 0, "a") .long LINUX_VERSION_CODE ELFNOTE_END + +BUILD_SALT From 25d9127bb0e27275d55a5b3d0fd30b04bafffd5a Mon Sep 17 00:00:00 2001 From: Tiezhu Yang Date: Thu, 25 Jun 2026 13:03:53 +0800 Subject: [PATCH 257/297] LoongArch: BPF: Fix outdated tail call comments The current LoongArch BPF JIT implementation hardcodes the number of prologue instructions skipped during a tail call as a magic number '7' in the jirl instruction. However, the accompanying comment explaining this offset is completely outdated. It inaccurately states that only a single TCC initialization instruction is bypassed, but in reality, multiple setup slots are skipped, so fix these outdated comments in __build_epilogue(). While at it, refine the comments in build_prologue() to describe the skipped setup slots (RA saving, fentry nops, and the TCC register slot) using proper dynamic tracing context. Also, remove the magic number '7' by introducing descriptive macros to formally define the prologue layout and make the tail call jump offset self-documenting. Fixes: 61319d15a560 ("LoongArch: BPF: Adjust the jump offset of tail calls") Signed-off-by: Tiezhu Yang Signed-off-by: Huacai Chen --- arch/loongarch/net/bpf_jit.c | 20 ++++++++++++++++---- 1 file changed, 16 insertions(+), 4 deletions(-) diff --git a/arch/loongarch/net/bpf_jit.c b/arch/loongarch/net/bpf_jit.c index 058ffbbaad85..a2a42c0a0f9d 100644 --- a/arch/loongarch/net/bpf_jit.c +++ b/arch/loongarch/net/bpf_jit.c @@ -9,7 +9,13 @@ #define LOONGARCH_MAX_REG_ARGS 8 +#define LOONGARCH_SAVE_RA_NINSNS 1 #define LOONGARCH_LONG_JUMP_NINSNS 5 +#define LOONGARCH_TCC_SLOT_NINSNS 1 + +#define LOONGARCH_PROLOGUE_SKIP_INSNS \ + (LOONGARCH_SAVE_RA_NINSNS + LOONGARCH_LONG_JUMP_NINSNS + LOONGARCH_TCC_SLOT_NINSNS) + #define LOONGARCH_LONG_JUMP_NBYTES (LOONGARCH_LONG_JUMP_NINSNS * 4) #define LOONGARCH_FENTRY_NINSNS 2 @@ -143,8 +149,13 @@ static void build_prologue(struct jit_ctx *ctx) stack_adjust = round_up(stack_adjust, 16); stack_adjust += bpf_stack_adjust; + /* + * Save the original return address to a temporary register to prevent + * it from being overwritten, then reserve space for the long jump and + * fentry trampoline slot for dynamically patching by ftrace at runtime. + * These instructions are bypassed during a tail call invocation. + */ move_reg(ctx, LOONGARCH_GPR_T0, LOONGARCH_GPR_RA); - /* Reserve space for the move_imm + jirl instruction */ for (i = 0; i < LOONGARCH_LONG_JUMP_NINSNS; i++) emit_insn(ctx, nop); @@ -253,10 +264,11 @@ static void __build_epilogue(struct jit_ctx *ctx, bool is_tail_call) emit_insn(ctx, jirl, LOONGARCH_GPR_ZERO, LOONGARCH_GPR_RA, 0); } else { /* - * Call the next bpf prog and skip the first instruction - * of TCC initialization. + * Tail call to the next BPF program, passing offset in number + * of instructions to jirl to bypass the initial setup slots. */ - emit_insn(ctx, jirl, LOONGARCH_GPR_ZERO, LOONGARCH_GPR_T3, 7); + emit_insn(ctx, jirl, LOONGARCH_GPR_ZERO, + LOONGARCH_GPR_T3, LOONGARCH_PROLOGUE_SKIP_INSNS); } } From 0379d10f09bc21ba739636796669dfb4936172a3 Mon Sep 17 00:00:00 2001 From: Tiezhu Yang Date: Thu, 25 Jun 2026 13:03:53 +0800 Subject: [PATCH 258/297] LoongArch: BPF: Fix off-by-one error in tail call The current code updates the tail call counter (TCC) using a pre-increment approach, it stores the incremented value back to memory before performing any boundary or target validation checks. This causes two major issues: 1. When a tail call fails because the target program is NULL, the TCC is incorrectly incremented and saved in memory anyway. 2. This dummy increment implicitly consumes one slot of the allowed tail call budget. As a result, the subsequent loop reaches the maximum limit prematurely, leading to a test failure where the actual loop count is 32 instead of the expected 33. Fix this by deferring the counter update. Change the branch condition to BPF_JSGE (greater or equal) so that we check the boundary first. The TCC is only incremented and stored back to memory after the boundary check and the NULL-target check both pass. Before: $ sudo ./test_progs -t tailcalls/tailcall_3 ... test_tailcall_count:FAIL:tailcall count unexpected tailcall count: actual 32 != expected 33 ... #465/3 tailcalls/tailcall_3:FAIL #465 tailcalls:FAIL After: $ sudo ./test_progs -t tailcalls/tailcall_3 #465/3 tailcalls/tailcall_3:OK #465 tailcalls:OK Summary: 1/1 PASSED, 0 SKIPPED, 0 FAILED Fixes: c0fcc955ff82 ("LoongArch: BPF: Fix the tailcall hierarchy") Signed-off-by: Tiezhu Yang Signed-off-by: Huacai Chen --- arch/loongarch/net/bpf_jit.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/arch/loongarch/net/bpf_jit.c b/arch/loongarch/net/bpf_jit.c index a2a42c0a0f9d..99294f930914 100644 --- a/arch/loongarch/net/bpf_jit.c +++ b/arch/loongarch/net/bpf_jit.c @@ -324,12 +324,12 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx, int insn) */ emit_insn(ctx, ldd, REG_TCC, LOONGARCH_GPR_SP, tcc_ptr_off); emit_insn(ctx, ldd, t3, REG_TCC, 0); - emit_insn(ctx, addid, t3, t3, 1); - emit_insn(ctx, std, t3, REG_TCC, 0); emit_insn(ctx, addid, t2, LOONGARCH_GPR_ZERO, MAX_TAIL_CALL_CNT); - if (emit_tailcall_jmp(ctx, BPF_JSGT, t3, t2, jmp_offset) < 0) + if (emit_tailcall_jmp(ctx, BPF_JSGE, t3, t2, jmp_offset) < 0) goto toofar; + emit_insn(ctx, addid, t3, t3, 1); + /* * prog = array->ptrs[index]; * if (!prog) @@ -342,6 +342,8 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx, int insn) if (emit_tailcall_jmp(ctx, BPF_JEQ, t2, LOONGARCH_GPR_ZERO, jmp_offset) < 0) goto toofar; + emit_insn(ctx, std, t3, REG_TCC, 0); + /* goto *(prog->bpf_func + 4); */ off = offsetof(struct bpf_prog, bpf_func); emit_insn(ctx, ldd, t3, t2, off); From 7f5c21fcd7ab2150d2b6d8ed2597820167ae0744 Mon Sep 17 00:00:00 2001 From: Tiezhu Yang Date: Thu, 25 Jun 2026 13:03:53 +0800 Subject: [PATCH 259/297] LoongArch: BPF: Inline bpf_get_current_task/_btf() helpers The pointer to task_struct is always available in the $tp register, so the calls to bpf_get_current_task() and bpf_get_current_task_btf() can be inlined into a single move instruction. (1) Here is the sample test.c: #include #include SEC("raw_tp/sys_enter") long test_task(void *ctx) { return (long)bpf_get_current_task(); } char _license[] SEC("license") = "GPL"; (2) Here are the test steps: sudo yum install libbpf-devel kernel-devel bpftool clang -target bpf -O2 -c test.c -o test.o sudo sysctl -w net.core.bpf_jit_enable=1 sudo bpftool prog show name test_task sudo rm -f /sys/fs/bpf/test_task sudo bpftool prog load test.o /sys/fs/bpf/test_task ID=$(sudo bpftool prog show pinned /sys/fs/bpf/test_task | grep -oE '^[0-9]+') sudo bpftool prog dump jited id $ID (3) Here are the test results: Before: 6 instructions ... 64: lu12i.w $t1, 1093 68: ori $t1, $t1, 3320 6c: lu32i.d $t1, 0 70: lu52i.d $t1, $t1, -1792 74: jirl $ra, $t1, 0 78: move $a5, $a0 ... After: 1 instruction ... 64: move $a5, $tp ... This is similar with commit 2bb138cb20a6 ("bpf, arm64: Inline bpf_get_current_task/_btf() helpers"). Signed-off-by: Tiezhu Yang Signed-off-by: Huacai Chen --- arch/loongarch/net/bpf_jit.c | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) diff --git a/arch/loongarch/net/bpf_jit.c b/arch/loongarch/net/bpf_jit.c index 99294f930914..66e8c1d2d5cb 100644 --- a/arch/loongarch/net/bpf_jit.c +++ b/arch/loongarch/net/bpf_jit.c @@ -1161,6 +1161,13 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, bool ext /* function call */ case BPF_JMP | BPF_CALL: + /* Implement helper call to bpf_get_current_task/_btf() inline */ + if (insn->src_reg == 0 && (insn->imm == BPF_FUNC_get_current_task || + insn->imm == BPF_FUNC_get_current_task_btf)) { + move_reg(ctx, regmap[BPF_REG_0], LOONGARCH_GPR_TP); + break; + } + ret = bpf_jit_get_func_addr(ctx->prog, insn, extra_pass, &func_addr, &func_addr_fixed); if (ret < 0) @@ -2381,3 +2388,14 @@ bool bpf_jit_supports_subprog_tailcalls(void) { return true; } + +bool bpf_jit_inlines_helper_call(s32 imm) +{ + switch (imm) { + case BPF_FUNC_get_current_task: + case BPF_FUNC_get_current_task_btf: + return true; + default: + return false; + } +} From 68571a63f25e44291af472d079eb4f906dea08e2 Mon Sep 17 00:00:00 2001 From: Tiezhu Yang Date: Thu, 25 Jun 2026 13:03:53 +0800 Subject: [PATCH 260/297] LoongArch: BPF: Inline bpf_get_smp_processor_id() helper The pointer to thread_info is always available in the $tp register, so the call to bpf_get_smp_processor_id() can be inlined into a single load instruction. (1) Here is the sample test.c: #include #include SEC("raw_tp/sys_enter") int test_cpuid(void *ctx) { return bpf_get_smp_processor_id(); } char _license[] SEC("license") = "GPL"; (2) Here are the test steps: sudo yum install libbpf-devel kernel-devel bpftool clang -target bpf -O2 -c test.c -o test.o sudo sysctl -w net.core.bpf_jit_enable=1 sudo bpftool prog show name test_cpuid sudo rm -f /sys/fs/bpf/test_cpuid sudo bpftool prog load test.o /sys/fs/bpf/test_cpuid ID=$(sudo bpftool prog show pinned /sys/fs/bpf/test_cpuid | grep -oE '^[0-9]+') sudo bpftool prog dump jited id $ID (3) Here are the test results: Before: 6 instructions ... 64: lu12i.w $t1, 1213 68: ori $t1, $t1, 1680 6c: lu32i.d $t1, 0 70: lu52i.d $t1, $t1, -1792 74: jirl $ra, $t1, 0 78: move $a5, $a0 ... After: 1 instruction ... 64: ld.wu $a5, $tp, 16 ... This is similar with commit 2ddec2c80b44 ("riscv, bpf: inline bpf_get_smp_processor_id()"). Signed-off-by: Tiezhu Yang Signed-off-by: Huacai Chen --- arch/loongarch/net/bpf_jit.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/arch/loongarch/net/bpf_jit.c b/arch/loongarch/net/bpf_jit.c index 66e8c1d2d5cb..ad7e28375aa9 100644 --- a/arch/loongarch/net/bpf_jit.c +++ b/arch/loongarch/net/bpf_jit.c @@ -5,6 +5,7 @@ * Copyright (C) 2022 Loongson Technology Corporation Limited */ #include +#include #include "bpf_jit.h" #define LOONGARCH_MAX_REG_ARGS 8 @@ -1168,6 +1169,12 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, bool ext break; } + /* Implement helper call to bpf_get_smp_processor_id() inline */ + if (insn->src_reg == 0 && insn->imm == BPF_FUNC_get_smp_processor_id) { + emit_insn(ctx, ldwu, regmap[BPF_REG_0], LOONGARCH_GPR_TP, TI_CPU); + break; + } + ret = bpf_jit_get_func_addr(ctx->prog, insn, extra_pass, &func_addr, &func_addr_fixed); if (ret < 0) @@ -2394,6 +2401,7 @@ bool bpf_jit_inlines_helper_call(s32 imm) switch (imm) { case BPF_FUNC_get_current_task: case BPF_FUNC_get_current_task_btf: + case BPF_FUNC_get_smp_processor_id: return true; default: return false; From bb3c90fe347a5321e7d176ed5b21367aa28be9ee Mon Sep 17 00:00:00 2001 From: Hongliang Wang Date: Thu, 25 Jun 2026 13:03:56 +0800 Subject: [PATCH 261/297] LoongArch: dts: Add i2c clocks and clock-frequency properties to LS2K0500 Add missing clocks and clock-frequency properties to i2c nodes for LS2K0500. Signed-off-by: Hongliang Wang Signed-off-by: Huacai Chen --- arch/loongarch/boot/dts/loongson-2k0500.dtsi | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/arch/loongarch/boot/dts/loongson-2k0500.dtsi b/arch/loongarch/boot/dts/loongson-2k0500.dtsi index 1b502064df11..992b1d0de9ec 100644 --- a/arch/loongarch/boot/dts/loongson-2k0500.dtsi +++ b/arch/loongarch/boot/dts/loongson-2k0500.dtsi @@ -405,6 +405,8 @@ i2c0: i2c@1ff48000 { compatible = "loongson,ls2k-i2c"; reg = <0x0 0x1ff48000 0x0 0x0800>; + clock-frequency = <100000>; + clocks = <&clk LOONGSON2_APB_CLK>; interrupt-parent = <&eiointc>; interrupts = <14>; status = "disabled"; @@ -413,6 +415,8 @@ i2c@1ff48800 { compatible = "loongson,ls2k-i2c"; reg = <0x0 0x1ff48800 0x0 0x0800>; + clock-frequency = <100000>; + clocks = <&clk LOONGSON2_APB_CLK>; interrupt-parent = <&eiointc>; interrupts = <15>; status = "disabled"; @@ -421,6 +425,8 @@ i2c@1ff49000 { compatible = "loongson,ls2k-i2c"; reg = <0x0 0x1ff49000 0x0 0x0800>; + clock-frequency = <100000>; + clocks = <&clk LOONGSON2_APB_CLK>; interrupt-parent = <&eiointc>; interrupts = <16>; status = "disabled"; @@ -429,6 +435,8 @@ i2c@1ff49800 { compatible = "loongson,ls2k-i2c"; reg = <0x0 0x1ff49800 0x0 0x0800>; + clock-frequency = <100000>; + clocks = <&clk LOONGSON2_APB_CLK>; interrupt-parent = <&eiointc>; interrupts = <17>; status = "disabled"; @@ -437,6 +445,8 @@ i2c@1ff4a000 { compatible = "loongson,ls2k-i2c"; reg = <0x0 0x1ff4a000 0x0 0x0800>; + clock-frequency = <100000>; + clocks = <&clk LOONGSON2_APB_CLK>; interrupt-parent = <&eiointc>; interrupts = <18>; status = "disabled"; @@ -445,6 +455,8 @@ i2c@1ff4a800 { compatible = "loongson,ls2k-i2c"; reg = <0x0 0x1ff4a800 0x0 0x0800>; + clock-frequency = <100000>; + clocks = <&clk LOONGSON2_APB_CLK>; interrupt-parent = <&eiointc>; interrupts = <19>; status = "disabled"; From 0526f3ea9f5aeed79caf353679c15280af1539ec Mon Sep 17 00:00:00 2001 From: Hongliang Wang Date: Thu, 25 Jun 2026 13:03:57 +0800 Subject: [PATCH 262/297] LoongArch: dts: Add i2c clocks and clock-frequency properties to LS2K1000 Add missing clocks and clock-frequency properties to i2c nodes for LS2K1000. Signed-off-by: Hongliang Wang Signed-off-by: Huacai Chen --- arch/loongarch/boot/dts/loongson-2k1000.dtsi | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/arch/loongarch/boot/dts/loongson-2k1000.dtsi b/arch/loongarch/boot/dts/loongson-2k1000.dtsi index ab6a55937e9e..e6f0fe093ab3 100644 --- a/arch/loongarch/boot/dts/loongson-2k1000.dtsi +++ b/arch/loongarch/boot/dts/loongson-2k1000.dtsi @@ -311,6 +311,8 @@ i2c2: i2c@1fe21000 { compatible = "loongson,ls2k-i2c"; reg = <0x0 0x1fe21000 0x0 0x8>; + clock-frequency = <100000>; + clocks = <&clk LOONGSON2_APB_CLK>; interrupt-parent = <&liointc0>; interrupts = <22 IRQ_TYPE_LEVEL_HIGH>; status = "disabled"; @@ -319,6 +321,8 @@ i2c3: i2c@1fe21800 { compatible = "loongson,ls2k-i2c"; reg = <0x0 0x1fe21800 0x0 0x8>; + clock-frequency = <100000>; + clocks = <&clk LOONGSON2_APB_CLK>; interrupt-parent = <&liointc0>; interrupts = <23 IRQ_TYPE_LEVEL_HIGH>; status = "disabled"; From eae0693d13da2f95d687c8003a5d4dd8f521670a Mon Sep 17 00:00:00 2001 From: Hongliang Wang Date: Thu, 25 Jun 2026 13:03:57 +0800 Subject: [PATCH 263/297] LoongArch: dts: Add i2c clocks and clock-frequency properties to LS2K2000 Add missing clocks and clock-frequency properties to i2c nodes for LS2K2000. Signed-off-by: Hongliang Wang Signed-off-by: Huacai Chen --- arch/loongarch/boot/dts/loongson-2k2000.dtsi | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/arch/loongarch/boot/dts/loongson-2k2000.dtsi b/arch/loongarch/boot/dts/loongson-2k2000.dtsi index 3678c084adf7..7fdc4192d2f2 100644 --- a/arch/loongarch/boot/dts/loongson-2k2000.dtsi +++ b/arch/loongarch/boot/dts/loongson-2k2000.dtsi @@ -239,6 +239,8 @@ i2c@1fe00120 { compatible = "loongson,ls2k-i2c"; reg = <0x0 0x1fe00120 0x0 0x8>; + clock-frequency = <100000>; + clocks = <&clk LOONGSON2_MISC_CLK>; interrupt-parent = <&liointc>; interrupts = <8 IRQ_TYPE_LEVEL_HIGH>; status = "disabled"; @@ -247,6 +249,8 @@ i2c@1fe00130 { compatible = "loongson,ls2k-i2c"; reg = <0x0 0x1fe00130 0x0 0x8>; + clock-frequency = <100000>; + clocks = <&clk LOONGSON2_MISC_CLK>; interrupt-parent = <&liointc>; interrupts = <9 IRQ_TYPE_LEVEL_HIGH>; status = "disabled"; From edc5cb8b2b617b67c35777e4e7dc3e8e6c275cfd Mon Sep 17 00:00:00 2001 From: Tiezhu Yang Date: Thu, 25 Jun 2026 13:08:57 +0800 Subject: [PATCH 264/297] selftests/bpf: Add get_preempt_count() support for LoongArch There is no LoongArch support for get_preempt_count() currently and its fallback path always returns 0, just add it so that bpf_in_interrupt(), bpf_in_nmi(), bpf_in_hardirq(), bpf_in_serving_softirq(), bpf_in_task() work for LoongArch as well. The latest kernels select CONFIG_THREAD_INFO_IN_TASK, it can just read preempt_count from the thread_info which is embedded within task_struct. With this patch, "./test_progs -t exe_ctx" passes on LoongArch. Signed-off-by: Tiezhu Yang Signed-off-by: Huacai Chen --- tools/testing/selftests/bpf/bpf_experimental.h | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/tools/testing/selftests/bpf/bpf_experimental.h b/tools/testing/selftests/bpf/bpf_experimental.h index d1db355e872b..67ff7882299e 100644 --- a/tools/testing/selftests/bpf/bpf_experimental.h +++ b/tools/testing/selftests/bpf/bpf_experimental.h @@ -423,6 +423,8 @@ static inline int get_preempt_count(void) return bpf_get_current_task_btf()->thread_info.preempt_count; #elif defined(bpf_target_s390) return bpf_get_lowcore()->preempt_count; +#elif defined(bpf_target_loongarch) + return bpf_get_current_task_btf()->thread_info.preempt_count; #endif return 0; } @@ -433,6 +435,7 @@ static inline int get_preempt_count(void) * * arm64 * * powerpc64 * * s390x + * * loongarch */ static inline int bpf_in_interrupt(void) { @@ -454,6 +457,7 @@ static inline int bpf_in_interrupt(void) * * arm64 * * powerpc64 * * s390x + * * loongarch */ static inline int bpf_in_nmi(void) { @@ -466,6 +470,7 @@ static inline int bpf_in_nmi(void) * * arm64 * * powerpc64 * * s390x + * * loongarch */ static inline int bpf_in_hardirq(void) { @@ -478,6 +483,7 @@ static inline int bpf_in_hardirq(void) * * arm64 * * powerpc64 * * s390x + * * loongarch */ static inline int bpf_in_serving_softirq(void) { @@ -498,6 +504,7 @@ static inline int bpf_in_serving_softirq(void) * * arm64 * * powerpc64 * * s390x + * * loongarch */ static inline int bpf_in_task(void) { From d5381d2dd456465a383e36f3e18a26d8ea6f7d2e Mon Sep 17 00:00:00 2001 From: Tiezhu Yang Date: Thu, 25 Jun 2026 13:08:57 +0800 Subject: [PATCH 265/297] selftests/bpf: Add __arch_loongarch to limit test cases for LoongArch Make it possible to limit certain tests to LoongArch, just like it is already done for x86_64, arm64, riscv64, and s390x. This is a follow up patch of: commit ee7fe84468b1 ("selftests/bpf: __arch_* macro to limit test cases to specific archs") commit 1e4e6b9e260d ("selftests/bpf: Add __arch_s390x macro") Signed-off-by: Tiezhu Yang Signed-off-by: Huacai Chen --- tools/testing/selftests/bpf/progs/bpf_misc.h | 1 + tools/testing/selftests/bpf/test_loader.c | 5 +++++ 2 files changed, 6 insertions(+) diff --git a/tools/testing/selftests/bpf/progs/bpf_misc.h b/tools/testing/selftests/bpf/progs/bpf_misc.h index 9eeb5b0b63d6..b0c441384f20 100644 --- a/tools/testing/selftests/bpf/progs/bpf_misc.h +++ b/tools/testing/selftests/bpf/progs/bpf_misc.h @@ -158,6 +158,7 @@ #define __arch_arm64 __arch("ARM64") #define __arch_riscv64 __arch("RISCV64") #define __arch_s390x __arch("s390x") +#define __arch_loongarch __arch("LOONGARCH") #define __caps_unpriv(caps) __test_tag("test_caps_unpriv=" EXPAND_QUOTE(caps)) #define __load_if_JITed() __test_tag("load_mode=jited") #define __load_if_no_JITed() __test_tag("load_mode=no_jited") diff --git a/tools/testing/selftests/bpf/test_loader.c b/tools/testing/selftests/bpf/test_loader.c index abdb9e6e3713..3ce32d134e2c 100644 --- a/tools/testing/selftests/bpf/test_loader.c +++ b/tools/testing/selftests/bpf/test_loader.c @@ -377,6 +377,7 @@ enum arch { ARCH_ARM64 = 0x4, ARCH_RISCV64 = 0x8, ARCH_S390X = 0x10, + ARCH_LOONGARCH = 0x20, }; static int get_current_arch(void) @@ -389,6 +390,8 @@ static int get_current_arch(void) return ARCH_RISCV64; #elif defined(__s390x__) return ARCH_S390X; +#elif defined(__loongarch__) + return ARCH_LOONGARCH; #endif return ARCH_UNKNOWN; } @@ -580,6 +583,8 @@ static int parse_test_spec(struct test_loader *tester, arch = ARCH_RISCV64; } else if (strcmp(val, "s390x") == 0) { arch = ARCH_S390X; + } else if (strcmp(val, "LOONGARCH") == 0) { + arch = ARCH_LOONGARCH; } else { PRINT_FAIL("bad arch spec: '%s'\n", val); err = -EINVAL; From 689c121446f2c8c850dd6206a038f0cf25c807e2 Mon Sep 17 00:00:00 2001 From: Tiezhu Yang Date: Thu, 25 Jun 2026 13:08:58 +0800 Subject: [PATCH 266/297] selftests/bpf: Test jited inline of bpf_get_current_task() for LoongArch Add the jited inline instruction of bpf_get_current_task() for LoongArch to pass the test case. Before: $ sudo ./test_progs -t verifier_jit_inline #604/1 verifier_jit_inline/inline_bpf_get_current_task:SKIP #604 verifier_jit_inline:SKIP Summary: 1/0 PASSED, 1 SKIPPED, 0 FAILED After: $ sudo ./test_progs -t verifier_jit_inline #604/1 verifier_jit_inline/inline_bpf_get_current_task:OK #604 verifier_jit_inline:OK Summary: 1/1 PASSED, 0 SKIPPED, 0 FAILED Signed-off-by: Tiezhu Yang Signed-off-by: Huacai Chen --- tools/testing/selftests/bpf/progs/verifier_jit_inline.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/tools/testing/selftests/bpf/progs/verifier_jit_inline.c b/tools/testing/selftests/bpf/progs/verifier_jit_inline.c index 76d80605ec7f..8560577f2557 100644 --- a/tools/testing/selftests/bpf/progs/verifier_jit_inline.c +++ b/tools/testing/selftests/bpf/progs/verifier_jit_inline.c @@ -12,6 +12,8 @@ __arch_arm64 __jited(" mrs x8, SP_EL0") __arch_riscv64 __jited(" mv a5, tp") +__arch_loongarch +__jited(" move $a5, $tp") int inline_bpf_get_current_task(void) { bpf_get_current_task(); From 262a3b4fa1792d40728c69995924e11cf761f5cf Mon Sep 17 00:00:00 2001 From: Tiezhu Yang Date: Thu, 25 Jun 2026 13:08:58 +0800 Subject: [PATCH 267/297] selftests/bpf: Test jited inline of bpf_get_smp_processor_id() for LoongArch Add the testcase for the jited inline of bpf_get_smp_processor_id(), only for LoongArch currently. Here is the test result on LoongArch: $ sudo ./test_progs -t verifier_jit_inline #604/1 verifier_jit_inline/inline_bpf_get_current_task:OK #604/2 verifier_jit_inline/inline_bpf_get_smp_processor_id:OK #604 verifier_jit_inline:OK Summary: 1/2 PASSED, 0 SKIPPED, 0 FAILED Signed-off-by: Tiezhu Yang Signed-off-by: Huacai Chen --- .../testing/selftests/bpf/progs/verifier_jit_inline.c | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/tools/testing/selftests/bpf/progs/verifier_jit_inline.c b/tools/testing/selftests/bpf/progs/verifier_jit_inline.c index 8560577f2557..02e562f56f9d 100644 --- a/tools/testing/selftests/bpf/progs/verifier_jit_inline.c +++ b/tools/testing/selftests/bpf/progs/verifier_jit_inline.c @@ -21,4 +21,15 @@ int inline_bpf_get_current_task(void) return 0; } +SEC("fentry/bpf_fentry_test2") +__success __retval(0) +__arch_loongarch +__jited(" ld.wu $a5, $tp, 16") +int inline_bpf_get_smp_processor_id(void) +{ + bpf_get_smp_processor_id(); + + return 0; +} + char _license[] SEC("license") = "GPL"; From 50ccdc31010ed623e68e496aebd4b1d3d8430664 Mon Sep 17 00:00:00 2001 From: Alexandre Belloni Date: Wed, 24 Jun 2026 22:42:22 +0200 Subject: [PATCH 268/297] rtc: s35390a: fix typo in comment Fix trivial typo Link: https://patch.msgid.link/20260624204223.1479003-1-alexandre.belloni@bootlin.com Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-s35390a.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/rtc/rtc-s35390a.c b/drivers/rtc/rtc-s35390a.c index 31394f34fb70..b72eef4fb099 100644 --- a/drivers/rtc/rtc-s35390a.c +++ b/drivers/rtc/rtc-s35390a.c @@ -297,7 +297,7 @@ static int s35390a_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alm) else sts = S35390A_INT2_MODE_NOINTR; - /* set interupt mode*/ + /* set interrupt mode*/ err = s35390a_set_reg(s35390a, S35390A_CMD_STATUS2, &sts, sizeof(sts)); if (err < 0) return err; From 00e44a68efef50f65b12854b41f098b4d50f10be Mon Sep 17 00:00:00 2001 From: Oleg Kucheryavenko Date: Wed, 24 Jun 2026 22:13:01 +0300 Subject: [PATCH 269/297] ALSA: hda/realtek: Add quirk for Acer Nitro ANV15-41 The Acer Nitro ANV15-41 laptop with ALC245 codec does not detect the headset microphone in the combo jack by default. Apply the ALC2XX_FIXUP_HEADSET_MIC quirk to fix it. Signed-off-by: Oleg Kucheryavenko Link: https://patch.msgid.link/20260624191301.10162-1-oleg.kucheryavenko2018@gmail.com Signed-off-by: Takashi Iwai --- sound/hda/codecs/realtek/alc269.c | 1 + 1 file changed, 1 insertion(+) diff --git a/sound/hda/codecs/realtek/alc269.c b/sound/hda/codecs/realtek/alc269.c index 0d932f6ae3e8..2a7a693ecedf 100644 --- a/sound/hda/codecs/realtek/alc269.c +++ b/sound/hda/codecs/realtek/alc269.c @@ -6813,6 +6813,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1025, 0x169a, "Acer Swift SFG16", ALC256_FIXUP_ACER_SFG16_MICMUTE_LED), SND_PCI_QUIRK(0x1025, 0x171e, "Acer Nitro ANV15-51", ALC245_FIXUP_ACER_MICMUTE_LED), SND_PCI_QUIRK(0x1025, 0x173a, "Acer Swift SFG14-73", ALC245_FIXUP_ACER_MICMUTE_LED), + SND_PCI_QUIRK(0x1025, 0x1758, "Acer Nitro ANV15-41", ALC2XX_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x1025, 0x1826, "Acer Helios ZPC", ALC287_FIXUP_PREDATOR_SPK_CS35L41_I2C_2), SND_PCI_QUIRK(0x1025, 0x182c, "Acer Helios ZPD", ALC287_FIXUP_PREDATOR_SPK_CS35L41_I2C_2), SND_PCI_QUIRK(0x1025, 0x1844, "Acer Helios ZPS", ALC287_FIXUP_PREDATOR_SPK_CS35L41_I2C_2), From 7693c0cc415f3a16a7a3355f245474a5e661be4e Mon Sep 17 00:00:00 2001 From: Darvell Long Date: Wed, 24 Jun 2026 07:37:23 -0700 Subject: [PATCH 270/297] ALSA: usb-audio: avoid kobject path lookup in DualSense match The DualSense jack-detection input handler verifies that a matching input device belongs to the same physical controller by building kobject path strings for both the input device and the USB audio device, then comparing the path prefix. This was observed when a weak physical connection caused the controller to rapidly disconnect and reconnect. During that repeated hotplug, snd_dualsense_ih_match() can run while the controller's USB device is being disconnected. kobject_get_path() walks ancestor kobjects and dereferences their names; if the USB device kobject name is no longer valid, this can fault in strlen(): RIP: 0010:strlen+0x10/0x30 Call Trace: kobject_get_path+0x34/0x150 snd_dualsense_ih_match+0x49/0xd0 [snd_usb_audio] input_register_device+0x566/0x6a0 ps_probe+0xb89/0x1590 [hid_playstation] The same ownership check can be done without building kobject path strings. The input device is parented below the HID device, USB interface and USB device, so walking the input device parent chain and comparing against the mixer USB device preserves the check without dereferencing kobject names during disconnect. Fixes: 79d561c4ec04 ("ALSA: usb-audio: Add mixer quirk for Sony DualSense PS5") Cc: Assisted-by: Cute:gpt-5.5 Signed-off-by: Darvell Long Link: https://patch.msgid.link/20260624143723.2986353-1-contact@darvell.me Signed-off-by: Takashi Iwai --- sound/usb/mixer_quirks.c | 40 ++++++++++++---------------------------- 1 file changed, 12 insertions(+), 28 deletions(-) diff --git a/sound/usb/mixer_quirks.c b/sound/usb/mixer_quirks.c index f6f2bc8e97a7..10792d26fa94 100644 --- a/sound/usb/mixer_quirks.c +++ b/sound/usb/mixer_quirks.c @@ -577,46 +577,30 @@ static bool snd_dualsense_ih_match(struct input_handler *handler, { struct dualsense_mixer_elem_info *mei; struct usb_device *snd_dev; - char *input_dev_path, *usb_dev_path; - size_t usb_dev_path_len; - bool match = false; + struct device *parent; mei = container_of(handler, struct dualsense_mixer_elem_info, ih); snd_dev = mei->info.head.mixer->chip->dev; - input_dev_path = kobject_get_path(&dev->dev.kobj, GFP_KERNEL); - if (!input_dev_path) { - dev_warn(&snd_dev->dev, "Failed to get input dev path\n"); - return false; - } - - usb_dev_path = kobject_get_path(&snd_dev->dev.kobj, GFP_KERNEL); - if (!usb_dev_path) { - dev_warn(&snd_dev->dev, "Failed to get USB dev path\n"); - goto free_paths; - } - /* * Ensure the VID:PID matched input device supposedly owned by the * hid-playstation driver belongs to the actual hardware handled by - * the current USB audio device, which implies input_dev_path being - * a subpath of usb_dev_path. + * the current USB audio device. * * This verification is necessary when there is more than one identical * controller attached to the host system. + * + * The input device is registered below the HID device, USB interface and + * USB device, so compare the parent chain directly instead of building + * kobject path strings. This avoids dereferencing kobject names while the + * USB device hierarchy is being torn down during disconnect. */ - usb_dev_path_len = strlen(usb_dev_path); - if (usb_dev_path_len >= strlen(input_dev_path)) - goto free_paths; + for (parent = dev->dev.parent; parent; parent = parent->parent) { + if (parent == &snd_dev->dev) + return true; + } - usb_dev_path[usb_dev_path_len] = '/'; - match = !memcmp(input_dev_path, usb_dev_path, usb_dev_path_len + 1); - -free_paths: - kfree(input_dev_path); - kfree(usb_dev_path); - - return match; + return false; } static int snd_dualsense_ih_connect(struct input_handler *handler, From 6485da8579e2b0132630faa1ee2ac72ccaf01501 Mon Sep 17 00:00:00 2001 From: Kamlesh Chhetty Date: Mon, 22 Jun 2026 13:22:47 -0400 Subject: [PATCH 271/297] ALSA: hda: Add Lenovo Legion 7i 16IAX7 17AA3874 quirk Lenovo Legion 7i 16IAX7 systems with Realtek ALC287 codec SSID 17aa:3874 and CSC3551/CS35L41 speaker amps do not provide the required CS35L41 _DSD properties in ACPI. Without a quirk, cs35l41-hda fails probing the amps with missing cirrus,dev-index / Platform not supported errors, leaving the built-in speakers silent. This model is similar to the already-supported 17AA386F Legion 7i 16IAX7 variant. Add the Realtek ALC287 quirk to select ALC287_FIXUP_CS35L41_I2C_2 and add 17AA3874 to the CS35L41 property table using the same two-amp external-boost configuration. Tested on a Lenovo Legion 7 16IAX7 with Ubuntu 7.0.0-22-generic. Both CSC3551 CS35L41 amps probe and bind, firmware loads, calibration applies, built-in speaker playback works, and the cirrus,dev-index failure is gone. Closes: https://bugzilla.kernel.org/show_bug.cgi?id=221663 Link: https://bugs.launchpad.net/ubuntu/+source/linux/+bug/2157060 Signed-off-by: Kamlesh Chhetty Link: https://patch.msgid.link/20260622172247.19301-1-kamleshkc2002@gmail.com Signed-off-by: Takashi Iwai --- sound/hda/codecs/realtek/alc269.c | 1 + sound/hda/codecs/side-codecs/cs35l41_hda_property.c | 2 ++ 2 files changed, 3 insertions(+) diff --git a/sound/hda/codecs/realtek/alc269.c b/sound/hda/codecs/realtek/alc269.c index 2a7a693ecedf..71625394aa99 100644 --- a/sound/hda/codecs/realtek/alc269.c +++ b/sound/hda/codecs/realtek/alc269.c @@ -7767,6 +7767,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { HDA_CODEC_QUIRK(0x17aa, 0x38a8, "Legion Pro 7 16ARX8H", ALC287_FIXUP_TAS2781_I2C), /* this must match before PCI SSID 17aa:386f below */ SND_PCI_QUIRK(0x17aa, 0x386f, "Legion Pro 7i 16IAX7", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x17aa, 0x3870, "Lenovo Yoga 7 14ARB7", ALC287_FIXUP_YOGA7_14ARB7_I2C), + SND_PCI_QUIRK(0x17aa, 0x3874, "Legion 7i 16IAX7", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x17aa, 0x3877, "Lenovo Legion 7 Slim 16ARHA7", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x17aa, 0x3878, "Lenovo Legion 7 Slim 16ARHA7", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x17aa, 0x387d, "Yoga S780-16 pro Quad AAC", ALC287_FIXUP_TAS2781_I2C), diff --git a/sound/hda/codecs/side-codecs/cs35l41_hda_property.c b/sound/hda/codecs/side-codecs/cs35l41_hda_property.c index 732ae534db36..416d7bf3e289 100644 --- a/sound/hda/codecs/side-codecs/cs35l41_hda_property.c +++ b/sound/hda/codecs/side-codecs/cs35l41_hda_property.c @@ -128,6 +128,7 @@ static const struct cs35l41_config cs35l41_config_table[] = { { "17AA3866", 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, -1, -1, 0, 0, 0 }, { "17AA386E", 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, 2, -1, 0, 0, 0 }, { "17AA386F", 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, -1, -1, 0, 0, 0 }, + { "17AA3874", 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, -1, -1, 0, 0, 0 }, { "17AA3877", 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, -1, -1, 0, 0, 0 }, { "17AA3878", 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, -1, -1, 0, 0, 0 }, { "17AA38A9", 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, 2, -1, 0, 0, 0 }, @@ -554,6 +555,7 @@ static const struct cs35l41_prop_model cs35l41_prop_model_table[] = { { "CSC3551", "17AA3866", generic_dsd_config }, { "CSC3551", "17AA386E", generic_dsd_config }, { "CSC3551", "17AA386F", generic_dsd_config }, + { "CSC3551", "17AA3874", generic_dsd_config }, { "CSC3551", "17AA3877", generic_dsd_config }, { "CSC3551", "17AA3878", generic_dsd_config }, { "CSC3551", "17AA38A9", generic_dsd_config }, From b8ff1f3578f83dedf5feb796d97a3f67c1bea58f Mon Sep 17 00:00:00 2001 From: Xu Rao Date: Tue, 23 Jun 2026 15:13:08 +0800 Subject: [PATCH 272/297] ALSA: usb-audio: qcom: Free QMI handle qc_usb_audio_probe() allocates svc->uaudio_svc_hdl separately from the uaudio_qmi_svc object. qmi_handle_release() releases the resources owned by an initialized QMI handle, but does not free the memory containing the struct qmi_handle itself. The probe error path and the remove path currently release the handle and then free svc, losing the last pointer to the separately allocated handle. This leaks one struct qmi_handle on each affected probe unwind and on each successful probe/remove cycle. Free the handle after qmi_handle_release() in both paths. Signed-off-by: Xu Rao Link: https://patch.msgid.link/9108EC860F3F87DF+20260623071308.2549182-1-raoxu@uniontech.com Signed-off-by: Takashi Iwai --- sound/usb/qcom/qc_audio_offload.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/sound/usb/qcom/qc_audio_offload.c b/sound/usb/qcom/qc_audio_offload.c index 3a586fd16e72..e4bfd43a2488 100644 --- a/sound/usb/qcom/qc_audio_offload.c +++ b/sound/usb/qcom/qc_audio_offload.c @@ -1988,6 +1988,7 @@ static int qc_usb_audio_probe(struct auxiliary_device *auxdev, release_qmi: qc_usb_audio_cleanup_qmi_dev(); qmi_handle_release(svc->uaudio_svc_hdl); + kfree(svc->uaudio_svc_hdl); free_svc: kfree(svc); @@ -2012,6 +2013,7 @@ static void qc_usb_audio_remove(struct auxiliary_device *auxdev) qc_usb_audio_cleanup_qmi_dev(); qmi_handle_release(svc->uaudio_svc_hdl); + kfree(svc->uaudio_svc_hdl); kfree(svc); uaudio_svc = NULL; } From 29b9667982e4df2ed7744f86b1144f8bb58eb698 Mon Sep 17 00:00:00 2001 From: Maoyi Xie Date: Sun, 21 Jun 2026 23:09:07 +0800 Subject: [PATCH 273/297] ALSA: firewire: isight: bound the sample count to the packet payload isight_packet() takes the frame count from the device iso packet and checks it only against the device claimed iso length. count = be32_to_cpu(payload->sample_count); if (likely(count <= (length - 16) / 4)) isight_samples(isight, payload->samples, count); length is the iso header data_length. It can be up to 0xffff. So the gate allows a count up to about 16379. isight_samples() then copies count frames out of payload->samples into the PCM DMA buffer. payload->samples holds only 2 * MAX_FRAMES_PER_PACKET values. The device multiplexes two samples per frame. A count past MAX_FRAMES_PER_PACKET reads past the payload. A count past the buffer size writes past runtime->dma_area. The smallest PCM buffer is larger than MAX_FRAMES_PER_PACKET. Bounding the count to MAX_FRAMES_PER_PACKET keeps both the read and the write in range. A malicious or faulty Apple iSight on the FireWire bus reaches this during a normal capture. Add the MAX_FRAMES_PER_PACKET bound to the gate. Fixes: 3a691b28a0ca ("ALSA: add Apple iSight microphone driver") Suggested-by: Takashi Sakamoto Cc: stable@vger.kernel.org Signed-off-by: Maoyi Xie Link: https://patch.msgid.link/178205454729.1900991.7807310178296762772@maoyixie.com Signed-off-by: Takashi Iwai --- sound/firewire/isight.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/sound/firewire/isight.c b/sound/firewire/isight.c index 2b7f071d593b..33c9dd48b3b0 100644 --- a/sound/firewire/isight.c +++ b/sound/firewire/isight.c @@ -179,7 +179,8 @@ static void isight_packet(struct fw_iso_context *context, u32 cycle, if (likely(length >= 16 && payload->signature == cpu_to_be32(0x73676874/*"sght"*/))) { count = be32_to_cpu(payload->sample_count); - if (likely(count <= (length - 16) / 4)) { + if (likely(count <= (length - 16) / 4 && + count <= MAX_FRAMES_PER_PACKET)) { total = be32_to_cpu(payload->sample_total); if (unlikely(total != isight->total_samples)) { if (!isight->first_packet) From 16eb19f0c90af03bda6ba66586d7bb0e9cf85b43 Mon Sep 17 00:00:00 2001 From: Haoxiang Li Date: Sun, 21 Jun 2026 15:19:35 +0800 Subject: [PATCH 274/297] fbdev: pm2fb: unwind WC setup on probe failure Add arch_phys_wc_del() on error path to keep the write-combining setup balanced when later probe steps fail. Signed-off-by: Haoxiang Li Signed-off-by: Helge Deller --- drivers/video/fbdev/pm2fb.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/video/fbdev/pm2fb.c b/drivers/video/fbdev/pm2fb.c index 412ff249b5c7..058075a34c5d 100644 --- a/drivers/video/fbdev/pm2fb.c +++ b/drivers/video/fbdev/pm2fb.c @@ -1711,6 +1711,7 @@ static int pm2fb_probe(struct pci_dev *pdev, const struct pci_device_id *id) err_exit_both: kfree(info->pixmap.addr); err_exit_pixmap: + arch_phys_wc_del(default_par->wc_cookie); iounmap(info->screen_base); release_mem_region(pm2fb_fix.smem_start, pm2fb_fix.smem_len); err_exit_mmio: From f7ecfc3fe5753d10e9c4d0d7955c160ea8cbf0ea Mon Sep 17 00:00:00 2001 From: Mario Limonciello Date: Wed, 20 May 2026 23:37:14 -0500 Subject: [PATCH 275/297] platform/x86: amd-pmc: Fix S0i3 wakeup with alarmtimer MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit It was reported that suspend-then-hibernate stopped working with modern systemd versions on AMD Cezanne systems. The reason for this breakage was because systemd switched to using alarmtimer instead of the wakealarm sysfs file. On AMD Cezanne systems, amd_pmc_verify_czn_rtc() programs a secondary timer with the alarm time. This was introduced by commit 59348401ebed ("platform/x86: amd-pmc: Add special handling for timer based S0i3 wakeup"). However, this function uses rtc_read_alarm(), which only reads the aie_timer, not the next expiring timer from the timerqueue. When both alarmtimer and wakealarm are active, the first expiring timer might be the alarmtimer, but amd_pmc_verify_czn_rtc() would only see the aie_timer, potentially missing the earlier alarm. Switch to rtc_read_next_alarm() to read whichever timer will fire next. Also handle -ENOENT (no alarm pending) explicitly as a non-error case. Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/3591 Signed-off-by: Mario Limonciello Acked-by: Ilpo Järvinen Link: https://patch.msgid.link/20260521043714.1022930-3-mario.limonciello@amd.com Signed-off-by: Alexandre Belloni --- drivers/platform/x86/amd/pmc/pmc.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/drivers/platform/x86/amd/pmc/pmc.c b/drivers/platform/x86/amd/pmc/pmc.c index cae3fcafd4d7..07e51e051af3 100644 --- a/drivers/platform/x86/amd/pmc/pmc.c +++ b/drivers/platform/x86/amd/pmc/pmc.c @@ -567,9 +567,12 @@ static int amd_pmc_verify_czn_rtc(struct amd_pmc_dev *pdev, u32 *arg) rtc_device = rtc_class_open("rtc0"); if (!rtc_device) return 0; - rc = rtc_read_alarm(rtc_device, &alarm); - if (rc) - return rc; + rc = rtc_read_next_alarm(rtc_device, &alarm); + if (rc) { + if (rc == -ENOENT) + dev_dbg(pdev->dev, "no alarm pending\n"); + return rc == -ENOENT ? 0 : rc; + } if (!alarm.enabled) { dev_dbg(pdev->dev, "alarm not enabled\n"); return 0; From 3c8f28578a0d68bc7fb91d881b832d55f734270c Mon Sep 17 00:00:00 2001 From: Ethan Nelson-Moore Date: Tue, 9 Jun 2026 22:47:22 -0700 Subject: [PATCH 276/297] rtc: ds1307: update reference to removed CONFIG_RTC_DRV_DS1307_HWMON The CONFIG_RTC_DRV_DS1307_HWMON macro was removed in favor of CONFIG_HWMON in commit 6b583a64fd1e ("rtc: ds1307: simplify hwmon config"), but a reference to it remained in a comment. Correct this reference. Discovered while searching for CONFIG_* symbols referenced in code but not defined in any Kconfig file. Signed-off-by: Ethan Nelson-Moore Link: https://patch.msgid.link/20260610054723.261008-1-enelsonmoore@gmail.com Signed-off-by: Alexandre Belloni --- drivers/rtc/rtc-ds1307.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/rtc/rtc-ds1307.c b/drivers/rtc/rtc-ds1307.c index a77580c4eea7..0707ded5368b 100644 --- a/drivers/rtc/rtc-ds1307.c +++ b/drivers/rtc/rtc-ds1307.c @@ -1415,7 +1415,7 @@ static void ds1307_hwmon_register(struct ds1307 *ds1307) { } -#endif /* CONFIG_RTC_DRV_DS1307_HWMON */ +#endif /* IS_REACHABLE(CONFIG_HWMON) */ /*----------------------------------------------------------------------*/ From 64184f07e7516eb3ac1839387eb7cbe2dbeaa96f Mon Sep 17 00:00:00 2001 From: Baojun Xu Date: Thu, 25 Jun 2026 18:28:15 +0800 Subject: [PATCH 277/297] ASoC: tas2781: Update default register address to TAS2563 The previous TAS2781 address is overwritten during calibration, so switching to the TAS2563 address is required. Signed-off-by: Baojun Xu Link: https://patch.msgid.link/20260625102815.20043-1-baojun.xu@ti.com Signed-off-by: Mark Brown --- include/sound/tas2781.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/include/sound/tas2781.h b/include/sound/tas2781.h index d45f805b5d18..b763da613769 100644 --- a/include/sound/tas2781.h +++ b/include/sound/tas2781.h @@ -59,9 +59,9 @@ #define TASDEVICE_CHECKSUM_REG TASDEVICE_REG(0x0, 0x0, 0x7e) /* XM_340 */ -#define TASDEVICE_XM_A1_REG TASDEVICE_REG(0x64, 0x63, 0x3c) +#define TASDEVICE_XM_A1_REG TASDEVICE_REG(0x64, 0x02, 0x4c) /* XM_341 */ -#define TASDEVICE_XM_A2_REG TASDEVICE_REG(0x64, 0x63, 0x38) +#define TASDEVICE_XM_A2_REG TASDEVICE_REG(0x64, 0x02, 0x64) /* Volume control */ #define TAS2563_DVC_LVL TASDEVICE_REG(0x00, 0x02, 0x0c) From c5315c8dcbcb9271f59662104428cd9229c9a7cb Mon Sep 17 00:00:00 2001 From: Christian Hewitt Date: Thu, 25 Jun 2026 12:28:11 +0000 Subject: [PATCH 278/297] ASoC: codecs: pcm512x: only print info once on no sclk If sclk is not provided the driver falls back to using bclk and prints an info message in the system log. Under normal operations the message is repeated many times: [ 17.929576] pcm512x 0-004c: No SCLK, using BCLK: -2 [ 17.949172] pcm512x 0-004c: No SCLK, using BCLK: -2 [ 17.953029] pcm512x 0-004c: No SCLK, using BCLK: -2 [ 17.965059] pcm512x 0-004c: No SCLK, using BCLK: -2 [ 82.592980] pcm512x 0-004c: No SCLK, using BCLK: -2 [ 82.866293] pcm512x 0-004c: No SCLK, using BCLK: -2 Switch from dev_info to dev_info_once to reduce log noise. Signed-off-by: Christian Hewitt Link: https://patch.msgid.link/20260625122811.4056274-1-christianshewitt@gmail.com Signed-off-by: Mark Brown --- sound/soc/codecs/pcm512x.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/soc/codecs/pcm512x.c b/sound/soc/codecs/pcm512x.c index fdef98ce52f1..fe3b5011fa16 100644 --- a/sound/soc/codecs/pcm512x.c +++ b/sound/soc/codecs/pcm512x.c @@ -633,7 +633,7 @@ static int pcm512x_dai_startup_slave(struct snd_pcm_substream *substream, struct regmap *regmap = pcm512x->regmap; if (IS_ERR(pcm512x->sclk)) { - dev_info(dev, "No SCLK, using BCLK: %ld\n", + dev_info_once(dev, "No SCLK, using BCLK: %ld\n", PTR_ERR(pcm512x->sclk)); /* Disable reporting of missing SCLK as an error */ From cf6f56990ea21172e085f0588e5bbf2089ce8f58 Mon Sep 17 00:00:00 2001 From: Shengjiu Wang Date: Thu, 25 Jun 2026 18:24:16 +0800 Subject: [PATCH 279/297] ASoC: fsl_asrc_dma: fix eDMA maxburst misalignment with channel count The back-end consumes data in units of the number of channels. When the maxburst value is not evenly divisible by the channel count, the DMA transfer length does not align with the FIFO frame boundary, causing wrong data to be copied and audible noise at the end of the stream. This is specific to eDMA: eDMA only responds to DMA requests from the back-end, whereas SDMA handles requests from both the front-end and the back-end and is not affected. For eDMA, when the back-end maxburst is not evenly divisible by the channel count, align it to the nearest valid boundary: - If maxburst >= channel count, override to the channel count so each transfer corresponds to exactly one audio frame. - If maxburst < channel count, override to 1 to avoid partial-frame transfers. Retain the original maxburst for SDMA or when it already aligns with the channel count. Fixes: c05f10f28ef6 ("ASoC: fsl_asrc: Add support for imx8qm & imx8qxp") Signed-off-by: Shengjiu Wang Link: https://patch.msgid.link/20260625102416.424911-1-shengjiu.wang@oss.nxp.com Signed-off-by: Mark Brown --- sound/soc/fsl/fsl_asrc_dma.c | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) diff --git a/sound/soc/fsl/fsl_asrc_dma.c b/sound/soc/fsl/fsl_asrc_dma.c index 5aa96af994c4..38f2b7c63133 100644 --- a/sound/soc/fsl/fsl_asrc_dma.c +++ b/sound/soc/fsl/fsl_asrc_dma.c @@ -288,6 +288,26 @@ static int fsl_asrc_dma_hw_params(struct snd_soc_component *component, config_be.dst_addr_width = buswidth; config_be.dst_maxburst = dma_params_be->maxburst; + /* + * For eDMA, the back-end may report a maxburst size that is not evenly + * divisible by the channel count. This causes the DMA transfer length + * to misalign with the FIFO boundary, resulting in wrong data and + * audible noise. Align maxburst to the nearest valid boundary: + * - If maxburst >= channel count, override to the channel count so + * each transfer equals exactly one audio frame. + * - If maxburst < channel count, override to 1 to avoid partial-frame + * transfers. + */ + if (asrc->use_edma && (dma_params_be->maxburst % params_channels(params))) { + if (dma_params_be->maxburst >= params_channels(params)) { + config_be.src_maxburst = params_channels(params); + config_be.dst_maxburst = params_channels(params); + } else { + config_be.src_maxburst = 1; + config_be.dst_maxburst = 1; + } + } + memset(&audio_config, 0, sizeof(audio_config)); config_be.peripheral_config = &audio_config; config_be.peripheral_size = sizeof(audio_config); From 8fdc8c2057eea08d40ce2c8eed41ff9e451c65c2 Mon Sep 17 00:00:00 2001 From: Mingyu Wang <25181214217@stu.xidian.edu.cn> Date: Fri, 26 Jun 2026 00:03:06 +0800 Subject: [PATCH 280/297] fbdev: fbcon: fix out-of-bounds read in err_out of fbcon_do_set_font() When fbcon_do_set_font() fails (e.g., due to a memory allocation failure inside vc_resize() under heavy memory pressure), it jumps to the `err_out` label to roll back the console state. However, the current rollback logic forgets to restore the `hi_font` state, leading to a severe state machine corruption. Earlier in the function, `set_vc_hi_font()` might be called to change `vc->vc_hi_font_mask` and mutate the screen buffer. If `vc_resize()` subsequently fails, the `err_out` path restores `vc_font.charcount` but entirely skips rolling back the `vc_hi_font_mask` and the screen buffer. This mismatch leaves the terminal in a desynchronized state. Because `vc_hi_font_mask` remains set, the VT subsystem will still accept character indices greater than 255 from userspace and write them to the screen buffer. Subsequent rendering calls (e.g., `fbcon_putcs()`) will then use these inflated indices to access the reverted, 256-character font array, leading to a deterministic out-of-bounds read and potential kernel memory disclosure. Fix this by adding the missing rollback logic for the `hi_font` mask and screen buffer in the error path. Fixes: a5a923038d70 ("fbdev: fbcon: Properly revert changes when vc_resize() failed") Cc: stable@vger.kernel.org Signed-off-by: Mingyu Wang <25181214217@stu.xidian.edu.cn> Reviewed-by: Thomas Zimmermann Signed-off-by: Helge Deller --- drivers/video/fbdev/core/fbcon.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/video/fbdev/core/fbcon.c b/drivers/video/fbdev/core/fbcon.c index 9077d3b99357..37beb93045af 100644 --- a/drivers/video/fbdev/core/fbcon.c +++ b/drivers/video/fbdev/core/fbcon.c @@ -2405,6 +2405,7 @@ static int fbcon_do_set_font(struct vc_data *vc, int w, int h, int charcount, int resize, ret, old_width, old_height, old_charcount; font_data_t *old_fontdata = p->fontdata; const u8 *old_data = vc->vc_font.data; + unsigned short old_hi_font_mask = vc->vc_hi_font_mask; font_data_get(data); @@ -2451,6 +2452,12 @@ err_out: vc->vc_font.height = old_height; vc->vc_font.charcount = old_charcount; + /* Restore the hi_font state and screen buffer */ + if (old_hi_font_mask && !vc->vc_hi_font_mask) + set_vc_hi_font(vc, true); + else if (!old_hi_font_mask && vc->vc_hi_font_mask) + set_vc_hi_font(vc, false); + font_data_put(data); return ret; From a11aa7b85021f5456fad8ec81467bcbdd2ac6945 Mon Sep 17 00:00:00 2001 From: Pengpeng Hou Date: Thu, 25 Jun 2026 11:01:02 +0800 Subject: [PATCH 281/297] fbdev: goldfishfb: fail pan display on base-update timeout goldfish_fb_pan_display() waits for the device to acknowledge the new framebuffer base, but it only logs a timeout and still reports success. The probe path also ignores the initial pan-display result before registering the framebuffer. Return -ETIMEDOUT when the base-update acknowledgment does not arrive, and propagate that error from the initial probe-time base update before the framebuffer is published. Signed-off-by: Pengpeng Hou Signed-off-by: Helge Deller --- drivers/video/fbdev/goldfishfb.c | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) diff --git a/drivers/video/fbdev/goldfishfb.c b/drivers/video/fbdev/goldfishfb.c index c9871281bc1d..e5d79886ea66 100644 --- a/drivers/video/fbdev/goldfishfb.c +++ b/drivers/video/fbdev/goldfishfb.c @@ -138,10 +138,12 @@ static int goldfish_fb_pan_display(struct fb_var_screeninfo *var, writel(fb->fb.fix.smem_start + fb->fb.var.xres * 2 * var->yoffset, fb->reg_base + FB_SET_BASE); spin_unlock_irqrestore(&fb->lock, irq_flags); - wait_event_timeout(fb->wait, - fb->base_update_count != base_update_count, HZ / 15); - if (fb->base_update_count == base_update_count) + if (!wait_event_timeout(fb->wait, + fb->base_update_count != base_update_count, + HZ / 15)) { pr_err("%s: timeout waiting for base update\n", __func__); + return -ETIMEDOUT; + } return 0; } @@ -251,7 +253,9 @@ static int goldfish_fb_probe(struct platform_device *pdev) goto err_request_irq_failed; writel(FB_INT_BASE_UPDATE_DONE, fb->reg_base + FB_INT_ENABLE); - goldfish_fb_pan_display(&fb->fb.var, &fb->fb); /* updates base */ + ret = goldfish_fb_pan_display(&fb->fb.var, &fb->fb); /* updates base */ + if (ret) + goto err_pan_display_failed; ret = register_framebuffer(&fb->fb); if (ret) @@ -259,6 +263,7 @@ static int goldfish_fb_probe(struct platform_device *pdev) return 0; err_register_framebuffer_failed: +err_pan_display_failed: free_irq(fb->irq, fb); err_request_irq_failed: err_fb_set_var_failed: From 4da933bf4e7317310f32d6918c774174253483c1 Mon Sep 17 00:00:00 2001 From: Pengpeng Hou Date: Wed, 24 Jun 2026 22:43:13 +0800 Subject: [PATCH 282/297] fbdev: viafb: return an error when DMA copy times out viafb_dma_copy_out_sg() logs a VIA DMA timeout when the DONE bit is not set after the completion wait and grace delay, but still returns success to the caller. Preserve the existing cleanup sequence and return -ETIMEDOUT when the DMA engine did not report completion. Signed-off-by: Pengpeng Hou Signed-off-by: Helge Deller --- drivers/video/fbdev/via/via-core.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/video/fbdev/via/via-core.c b/drivers/video/fbdev/via/via-core.c index a8d4a3e2c65e..1632a669941a 100644 --- a/drivers/video/fbdev/via/via-core.c +++ b/drivers/video/fbdev/via/via-core.c @@ -234,6 +234,7 @@ int viafb_dma_copy_out_sg(unsigned int offset, struct scatterlist *sg, int nsg) dma_addr_t descr_handle; unsigned long flags; int i; + int ret = 0; struct scatterlist *sgentry; dma_addr_t nextdesc; @@ -290,8 +291,10 @@ int viafb_dma_copy_out_sg(unsigned int offset, struct scatterlist *sg, int nsg) */ wait_for_completion_timeout(&viafb_dma_completion, 1); msleep(1); - if ((viafb_mmio_read(VDMA_CSR0)&VDMA_C_DONE) == 0) + if ((viafb_mmio_read(VDMA_CSR0) & VDMA_C_DONE) == 0) { printk(KERN_ERR "VIA DMA timeout!\n"); + ret = -ETIMEDOUT; + } /* * Clean up and we're done. */ @@ -301,7 +304,7 @@ int viafb_dma_copy_out_sg(unsigned int offset, struct scatterlist *sg, int nsg) dma_free_coherent(&global_dev.pdev->dev, nsg*sizeof(struct viafb_vx855_dma_descr), descrpages, descr_handle); - return 0; + return ret; } EXPORT_SYMBOL_GPL(viafb_dma_copy_out_sg); #endif /* CONFIG_VIDEO_VIA_CAMERA */ From 57c10915f2c16c90e0d46ad00876bf39ece40fc2 Mon Sep 17 00:00:00 2001 From: Bryam Vargas Date: Sun, 14 Jun 2026 00:36:11 -0500 Subject: [PATCH 283/297] Input: synaptics-rmi4 - bound the F3A keymap to the GPIO count rmi_f3a_initialize() takes the GPIO count from the device query register (f3a->gpio_count = buf & RMI_F3A_GPIO_COUNT, range 0..127). rmi_f3a_map_gpios() then allocates gpio_key_map with min(gpio_count, TRACKSTICK_RANGE_END) == at most 6 entries, but rmi_f3a_attention() iterates the full gpio_count and dereferences gpio_key_map[i], and input->keycodemax is set to the full gpio_count while input->keycode points at the 6-entry allocation. A device that reports gpio_count > 6 therefore causes an out-of-bounds read of gpio_key_map[] on every attention interrupt, and out-of-bounds accesses through the input core's default keymap ioctls: EVIOCGKEYCODE reads past the buffer (leaking adjacent slab memory to user space) and EVIOCSKEYCODE writes a caller-controlled value past it, for any process able to open the evdev node, since input_default_getkeycode() and input_default_setkeycode() only bound the index against keycodemax. Size the keymap for the full gpio_count. The mapping loop is unchanged: it still assigns only the first min(gpio_count, TRACKSTICK_RANGE_END) entries; the remaining slots stay KEY_RESERVED (devm_kcalloc zero-fills) and are skipped when reporting. Fixes: 9e4c596bfd00 ("Input: synaptics-rmi4 - add support for F3A") Cc: stable@vger.kernel.org Signed-off-by: Bryam Vargas Link: https://patch.msgid.link/20260614-b4-disp-818d6bda-v1-1-cf39a3615085@proton.me Signed-off-by: Dmitry Torokhov --- drivers/input/rmi4/rmi_f3a.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/input/rmi4/rmi_f3a.c b/drivers/input/rmi4/rmi_f3a.c index 0e8baed84dbb..a0777644eef0 100644 --- a/drivers/input/rmi4/rmi_f3a.c +++ b/drivers/input/rmi4/rmi_f3a.c @@ -132,7 +132,7 @@ static int rmi_f3a_map_gpios(struct rmi_function *fn, struct f3a_data *f3a, int button_count = min_t(u8, f3a->gpio_count, TRACKSTICK_RANGE_END); f3a->gpio_key_map = devm_kcalloc(&fn->dev, - button_count, + f3a->gpio_count, sizeof(f3a->gpio_key_map[0]), GFP_KERNEL); if (!f3a->gpio_key_map) { From d577e46785d45484b2ab7e7309c49b18764bf56c Mon Sep 17 00:00:00 2001 From: Bryam Vargas Date: Sun, 14 Jun 2026 00:36:12 -0500 Subject: [PATCH 284/297] Input: synaptics-rmi4 - bound the F30 keymap to the GPIO/LED count rmi_f30_map_gpios() allocates gpioled_key_map with min(gpioled_count, TRACKSTICK_RANGE_END) == at most 6 entries, but rmi_f30_attention() iterates the full f30->gpioled_count (device query register, range 0..31) and dereferences gpioled_key_map[i], and input->keycodemax is set to the full gpioled_count while input->keycode points at the 6-entry allocation. A device that reports gpioled_count > 6 with GPIO support enabled therefore causes an out-of-bounds read on the attention interrupt and out-of-bounds read/write through the EVIOCGKEYCODE/EVIOCSKEYCODE ioctls, which bound the index only against keycodemax. This is the same defect as the F3A handler, which was copied from F30. Size the keymap for the full gpioled_count; the mapping loop still assigns only the first min(gpioled_count, TRACKSTICK_RANGE_END) entries. Fixes: 3e64fcbdbd10 ("Input: synaptics-rmi4 - limit the range of what GPIOs are buttons") Cc: stable@vger.kernel.org Signed-off-by: Bryam Vargas Link: https://patch.msgid.link/20260614-b4-disp-818d6bda-v1-2-cf39a3615085@proton.me Signed-off-by: Dmitry Torokhov --- drivers/input/rmi4/rmi_f30.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/input/rmi4/rmi_f30.c b/drivers/input/rmi4/rmi_f30.c index 35045f161dc2..b2155c8e20e7 100644 --- a/drivers/input/rmi4/rmi_f30.c +++ b/drivers/input/rmi4/rmi_f30.c @@ -233,7 +233,7 @@ static int rmi_f30_map_gpios(struct rmi_function *fn, int button_count = min_t(u8, f30->gpioled_count, TRACKSTICK_RANGE_END); f30->gpioled_key_map = devm_kcalloc(&fn->dev, - button_count, + f30->gpioled_count, sizeof(f30->gpioled_key_map[0]), GFP_KERNEL); if (!f30->gpioled_key_map) { From 9dbbe81962b973fe71592ad8615d1e6cd28451bf Mon Sep 17 00:00:00 2001 From: Oleg Kucheryavenko Date: Thu, 25 Jun 2026 16:49:55 +0300 Subject: [PATCH 285/297] ALSA: hda/realtek: Update Acer Nitro ANV15-41 quirk to enable mute LED The laptop has a microphone mute LED on the F4 key, but it was not taken in mind when the previous quirk was added in commit 00e44a68efef50f65b12854b41f098b4d50f10be ("ALSA: hda/realtek: Add quirk for Acer Nitro ANV15-41"). Replace ALC2XX_FIXUP_HEADSET_MIC with ALC245_FIXUP_ACER_MICMUTE_LED, which enables the LED and chains the previous quirk for the headset microphone. Fixes: 00e44a68efef ("ALSA: hda/realtek: Add quirk for Acer Nitro ANV15-41") Signed-off-by: Oleg Kucheryavenko Link: https://patch.msgid.link/20260625134955.27465-1-oleg.kucheryavenko2018@gmail.com Signed-off-by: Takashi Iwai --- sound/hda/codecs/realtek/alc269.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sound/hda/codecs/realtek/alc269.c b/sound/hda/codecs/realtek/alc269.c index 71625394aa99..d9e2384fc0ba 100644 --- a/sound/hda/codecs/realtek/alc269.c +++ b/sound/hda/codecs/realtek/alc269.c @@ -6813,7 +6813,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1025, 0x169a, "Acer Swift SFG16", ALC256_FIXUP_ACER_SFG16_MICMUTE_LED), SND_PCI_QUIRK(0x1025, 0x171e, "Acer Nitro ANV15-51", ALC245_FIXUP_ACER_MICMUTE_LED), SND_PCI_QUIRK(0x1025, 0x173a, "Acer Swift SFG14-73", ALC245_FIXUP_ACER_MICMUTE_LED), - SND_PCI_QUIRK(0x1025, 0x1758, "Acer Nitro ANV15-41", ALC2XX_FIXUP_HEADSET_MIC), + SND_PCI_QUIRK(0x1025, 0x1758, "Acer Nitro ANV15-41", ALC245_FIXUP_ACER_MICMUTE_LED), SND_PCI_QUIRK(0x1025, 0x1826, "Acer Helios ZPC", ALC287_FIXUP_PREDATOR_SPK_CS35L41_I2C_2), SND_PCI_QUIRK(0x1025, 0x182c, "Acer Helios ZPD", ALC287_FIXUP_PREDATOR_SPK_CS35L41_I2C_2), SND_PCI_QUIRK(0x1025, 0x1844, "Acer Helios ZPS", ALC287_FIXUP_PREDATOR_SPK_CS35L41_I2C_2), From e1e31e0ec8a609e17fd2e86b77bc00d9cbb24d7c Mon Sep 17 00:00:00 2001 From: Jiaming Zhang Date: Thu, 25 Jun 2026 21:49:33 +0800 Subject: [PATCH 286/297] ALSA: FCP: Fix NULL pointer dereference in interface lookup A malformed USB device can provide a vendor-specific interface without any endpoint descriptors. fcp_find_fc_interface() currently selects the first vendor-specific interface and reads endpoint 0 from it, without checking whether the interface actually has any endpoints. When bNumEndpoints is zero, no endpoint array is allocated for the parsed alternate setting, so get_endpoint(..., 0) yields an invalid endpoint descriptor pointer. Dereferencing it through usb_endpoint_num() then triggers a NULL pointer dereference. Skip vendor-specific interfaces that do not have any endpoints. Fixes: 46757a3e7d50 ("ALSA: FCP: Add Focusrite Control Protocol driver") Reported-by: Jiaming Zhang Closes: https://lore.kernel.org/lkml/CANypQFb1EHj0xX8bA1WxSOSK-5xca6ZNKzOQcp12=s=puY7VFw@mail.gmail.com/ Signed-off-by: Jiaming Zhang Link: https://patch.msgid.link/20260625134933.425785-1-r772577952@gmail.com Signed-off-by: Takashi Iwai --- sound/usb/fcp.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/sound/usb/fcp.c b/sound/usb/fcp.c index ea746bdb36ff..6f5dcd35e1d4 100644 --- a/sound/usb/fcp.c +++ b/sound/usb/fcp.c @@ -1083,6 +1083,8 @@ static int fcp_find_fc_interface(struct usb_mixer_interface *mixer) if (desc->bInterfaceClass != 255) continue; + if (desc->bNumEndpoints < 1) + continue; epd = get_endpoint(intf->altsetting, 0); private->bInterfaceNumber = desc->bInterfaceNumber; From 2c1c805c65fb7dc7524e20376d6987721e73a0b1 Mon Sep 17 00:00:00 2001 From: Ian Bridges Date: Thu, 25 Jun 2026 23:50:48 -0500 Subject: [PATCH 287/297] fbdev: fix use-after-free in store_modes() store_modes() replaces a framebuffer's modelist with modes from userspace. On success it frees the old modelist with fb_destroy_modelist(). Two fields still point into that freed list. One pointer is fb_display[i].mode, the mode a console is using. fbcon_new_modelist() moves these pointers to the new list. It only does so for consoles still mapped to the framebuffer. An unmapped console is skipped and keeps its stale pointer. Unbinding fbcon, for example, sets con2fb_map[i] to -1 but leaves fb_display[i].mode set. An FBIOPUT_VSCREENINFO ioctl with FB_ACTIVATE_INV_MODE later reaches fbcon_mode_deleted(). That function reads the stale fb_display[i].mode through fb_mode_is_equal(). The read is a use-after-free. The other pointer is fb_info->mode, the current mode. It is set through the mode sysfs attribute. store_modes() does not update fb_info->mode, so it is left pointing into the freed list. show_mode(), the attribute's read handler, dereferences the stale fb_info->mode through mode_string(). The read is a use-after-free. Clear both pointers before freeing the list. Commit a1f305893074 ("fbcon: Set fb_display[i]->mode to NULL when the mode is released") added the helper fbcon_delete_modelist(). It clears every fb_display[i].mode that points into a given list. So far it is called only from the unregister path. Call it from store_modes() too, and set fb_info->mode to NULL. Reported-by: syzbot+81c7c6b52649fd07299d@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=81c7c6b52649fd07299d Cc: stable@vger.kernel.org Link: https://lore.kernel.org/all/ajjoDhAi2y4ArSlz@dev/ Assisted-by: Claude:claude-opus-4-8 Signed-off-by: Ian Bridges Signed-off-by: Helge Deller --- drivers/video/fbdev/core/fbsysfs.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/drivers/video/fbdev/core/fbsysfs.c b/drivers/video/fbdev/core/fbsysfs.c index d9743ef35355..ea196603c7a8 100644 --- a/drivers/video/fbdev/core/fbsysfs.c +++ b/drivers/video/fbdev/core/fbsysfs.c @@ -10,6 +10,7 @@ #include #include "fb_internal.h" +#include "fbcon.h" static int activate(struct fb_info *fb_info, struct fb_var_screeninfo *var) { @@ -108,8 +109,15 @@ static ssize_t store_modes(struct device *device, if (fb_new_modelist(fb_info)) { fb_destroy_modelist(&fb_info->modelist); list_splice(&old_list, &fb_info->modelist); - } else + } else { + /* + * fb_display[i].mode and fb_info->mode both point into the old + * list. Clear them before it is freed. + */ + fbcon_delete_modelist(&old_list); + fb_info->mode = NULL; fb_destroy_modelist(&old_list); + } unlock_fb_info(fb_info); console_unlock(); From 5fae9a928482d4845bca169a3a098789203a1ca4 Mon Sep 17 00:00:00 2001 From: Ian Bridges Date: Wed, 24 Jun 2026 16:11:36 -0500 Subject: [PATCH 288/297] fbcon: fix NULL pointer dereference for a console without vc_data fbcon_new_modelist() runs when a framebuffer's modelist changes. For each console mapped to it with fb_display[i].mode set, it reads vc_cons[i].d and passes the vc_num to fbcon_set_disp(). This assumes a console with a mode set has a vc_data, but it can be NULL. fbcon_set_disp() sets fb_display[i].mode before it checks vc_data, and fbcon_deinit() leaves the mode set after the vc_data is freed. fbcon_new_modelist() then dereferences the NULL vc_data. Keep fb_display[i].mode set only while the console has a vc_data. Check vc_data before setting the mode in fbcon_set_disp(), and clear the mode in fbcon_deinit(). The existing mode check in fbcon_new_modelist() then skips such consoles. Reported-by: syzbot+42525d636f430fd5d983@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=42525d636f430fd5d983 Cc: stable@vger.kernel.org Assisted-by: Claude:claude-opus-4-8 Signed-off-by: Ian Bridges Signed-off-by: Helge Deller --- drivers/video/fbdev/core/fbcon.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/video/fbdev/core/fbcon.c b/drivers/video/fbdev/core/fbcon.c index 37beb93045af..9f5c4c101581 100644 --- a/drivers/video/fbdev/core/fbcon.c +++ b/drivers/video/fbdev/core/fbcon.c @@ -1273,6 +1273,7 @@ static void fbcon_deinit(struct vc_data *vc) int idx; fbcon_free_font(p); + p->mode = NULL; idx = con2fb_map[vc->vc_num]; if (idx == -1) @@ -1443,14 +1444,14 @@ static void fbcon_set_disp(struct fb_info *info, struct fb_var_screeninfo *var, p = &fb_display[unit]; - if (var_to_display(p, var, info)) - return; - vc = vc_cons[unit].d; if (!vc) return; + if (var_to_display(p, var, info)) + return; + default_mode = vc->vc_display_fg; svc = *default_mode; t = &fb_display[svc->vc_num]; From 7f08fc10fa3d3366dc3af723970bd03d7d6d10e3 Mon Sep 17 00:00:00 2001 From: Ian Bridges Date: Wed, 24 Jun 2026 23:13:12 -0500 Subject: [PATCH 289/297] fbdev: Fix fb_new_modelist to prevent null-ptr-deref in fb_videomode_to_var info->var, a framebuffer's current mode, is expected to have a matching entry in info->modelist. var_to_display() relies on this and treats a failed fb_match_mode() as "This should not happen". fb_set_var() keeps it true by adding the mode to the list on every change, and do_register_framebuffer() does the same at registration. store_modes() replaces the modelist from userspace. fb_new_modelist() validates the new modes but does not check that info->var still has a match. It relies on fbcon_new_modelist() to re-point consoles, but that only handles consoles mapped to the framebuffer. With fbcon unbound there are none, so info->var is left describing a mode that is no longer in the list. A later console takeover runs var_to_display(), where fb_match_mode() returns NULL and leaves fb_display[i].mode NULL. fbcon_switch() passes it to display_to_var(), and fb_videomode_to_var() dereferences the NULL mode. Keep the current mode in the list in fb_new_modelist(), the same way fb_set_var() does. Cc: stable@vger.kernel.org Assisted-by: Claude:claude-opus-4-8 Signed-off-by: Ian Bridges Signed-off-by: Helge Deller --- drivers/video/fbdev/core/fbmem.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/drivers/video/fbdev/core/fbmem.c b/drivers/video/fbdev/core/fbmem.c index e5221653ec2b..2f1c56e5a7a2 100644 --- a/drivers/video/fbdev/core/fbmem.c +++ b/drivers/video/fbdev/core/fbmem.c @@ -767,6 +767,18 @@ int fb_new_modelist(struct fb_info *info) if (list_empty(&info->modelist)) return 1; + /* + * The new modelist may not contain the current mode (info->var), and + * fbcon_new_modelist() below only re-points consoles mapped to this + * framebuffer. Add the current mode here so info->var keeps a match + * even when fbcon is unbound. + */ + if (!fb_match_mode(&info->var, &info->modelist)) { + fb_var_to_videomode(&mode, &info->var); + if (fb_add_videomode(&mode, &info->modelist)) + return 1; + } + fbcon_new_modelist(info); return 0; From 4fc0625cf9c6c11f1f9b09e1f2e35fa2dd46ea6a Mon Sep 17 00:00:00 2001 From: Alok Tiwari Date: Sun, 8 Feb 2026 08:49:00 -0800 Subject: [PATCH 290/297] ntb_hw_amd: Fix incorrect debug message in link disable path amd_ntb_link_disable() prints "Enabling Link" which is misleading. Update the message to reflect that the link is being disabled. Signed-off-by: Alok Tiwari Reviewed-by: Dave Jiang Signed-off-by: Jon Mason --- drivers/ntb/hw/amd/ntb_hw_amd.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/ntb/hw/amd/ntb_hw_amd.c b/drivers/ntb/hw/amd/ntb_hw_amd.c index 1a163596ddf5..df9150669ad3 100644 --- a/drivers/ntb/hw/amd/ntb_hw_amd.c +++ b/drivers/ntb/hw/amd/ntb_hw_amd.c @@ -376,7 +376,7 @@ static int amd_ntb_link_disable(struct ntb_dev *ntb) if (ndev->ntb.topo == NTB_TOPO_SEC) return -EINVAL; - dev_dbg(&ntb->pdev->dev, "Enabling Link.\n"); + dev_dbg(&ntb->pdev->dev, "Disabling Link.\n"); return 0; } From d876153680e3d721d385e554def919bce3d18c74 Mon Sep 17 00:00:00 2001 From: Koichiro Den Date: Wed, 4 Mar 2026 11:05:27 +0900 Subject: [PATCH 291/297] NTB: epf: Avoid pci_iounmap() with offset when PEER_SPAD and CONFIG share BAR When BAR_PEER_SPAD and BAR_CONFIG share one PCI BAR, the module teardown path ends up calling pci_iounmap() on the same iomem with some offset, which is unnecessary and triggers a kernel warning like the following: Trying to vunmap() nonexistent vm area (0000000069a5ffe8) WARNING: mm/vmalloc.c:3470 at vunmap+0x58/0x68, CPU#5: modprobe/2937 [...] Call trace: vunmap+0x58/0x68 (P) iounmap+0x34/0x48 pci_iounmap+0x2c/0x40 ntb_epf_pci_remove+0x44/0x80 [ntb_hw_epf] pci_device_remove+0x48/0xf8 device_remove+0x50/0x88 device_release_driver_internal+0x1c8/0x228 driver_detach+0x50/0xb0 bus_remove_driver+0x74/0x100 driver_unregister+0x34/0x68 pci_unregister_driver+0x34/0xa0 ntb_epf_pci_driver_exit+0x14/0xfe0 [ntb_hw_epf] [...] Fix it by unmapping only when PEER_SPAD and CONFIG use difference bars. Cc: stable@vger.kernel.org Fixes: e75d5ae8ab88 ("NTB: epf: Allow more flexibility in the memory BAR map method") Reviewed-by: Frank Li Signed-off-by: Koichiro Den Reviewed-by: Dave Jiang Signed-off-by: Jon Mason --- drivers/ntb/hw/epf/ntb_hw_epf.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/ntb/hw/epf/ntb_hw_epf.c b/drivers/ntb/hw/epf/ntb_hw_epf.c index d3ecf25a5162..9935da48a52e 100644 --- a/drivers/ntb/hw/epf/ntb_hw_epf.c +++ b/drivers/ntb/hw/epf/ntb_hw_epf.c @@ -646,7 +646,8 @@ static void ntb_epf_deinit_pci(struct ntb_epf_dev *ndev) struct pci_dev *pdev = ndev->ntb.pdev; pci_iounmap(pdev, ndev->ctrl_reg); - pci_iounmap(pdev, ndev->peer_spad_reg); + if (ndev->barno_map[BAR_PEER_SPAD] != ndev->barno_map[BAR_CONFIG]) + pci_iounmap(pdev, ndev->peer_spad_reg); pci_iounmap(pdev, ndev->db_reg); pci_release_regions(pdev); From 8df969463bc26a7250707f485ee3ac61426d671f Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Wed, 11 Mar 2026 22:14:15 -0700 Subject: [PATCH 292/297] NTB: fix kernel-doc warnings in ntb.h Correct a function name and function parameter name to avoid kernel-doc warnings: Warning: include/linux/ntb.h:575 expecting prototype for ntb_default_port_count(). Prototype was for ntb_default_peer_port_count() instead Warning: include/linux/ntb.h:590 function parameter 'pidx' not described in 'ntb_default_peer_port_number' Signed-off-by: Randy Dunlap Acked-by: Dave Jiang Signed-off-by: Jon Mason --- include/linux/ntb.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/include/linux/ntb.h b/include/linux/ntb.h index 879c3e89e026..ae72caa03859 100644 --- a/include/linux/ntb.h +++ b/include/linux/ntb.h @@ -567,7 +567,7 @@ void ntb_msg_event(struct ntb_dev *ntb); int ntb_default_port_number(struct ntb_dev *ntb); /** - * ntb_default_port_count() - get the default number of peer device ports + * ntb_default_peer_port_count() - get the default number of peer device ports * @ntb: NTB device context. * * By default hardware driver supports just one peer device. @@ -582,7 +582,7 @@ int ntb_default_peer_port_count(struct ntb_dev *ntb); /** * ntb_default_peer_port_number() - get the default peer port by given index * @ntb: NTB device context. - * @idx: Peer port index (should not differ from zero). + * @pidx: Peer port index (should not differ from zero). * * By default hardware driver supports just one peer device, so this method * shall return the corresponding value from enum ntb_default_port. From d1c3d45f87e89e5c1fa0769a72a48d1ad99106fc Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig=20=28The=20Capable=20Hub=29?= Date: Thu, 7 May 2026 09:41:01 +0200 Subject: [PATCH 293/297] ntb: amd: Use named initializer for pci_device_id::driver_data MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The current list initialisation depends on the well hidden two zeros in the PCI_VDEVICE macro. Instead use a named initialisation that is more robust and easier to understand. Signed-off-by: Uwe Kleine-König (The Capable Hub) Reviewed-by: Dave Jiang Signed-off-by: Jon Mason --- drivers/ntb/hw/amd/ntb_hw_amd.c | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) diff --git a/drivers/ntb/hw/amd/ntb_hw_amd.c b/drivers/ntb/hw/amd/ntb_hw_amd.c index df9150669ad3..36bee0d8ac6c 100644 --- a/drivers/ntb/hw/amd/ntb_hw_amd.c +++ b/drivers/ntb/hw/amd/ntb_hw_amd.c @@ -1328,15 +1328,15 @@ static const struct ntb_dev_data dev_data[] = { }; static const struct pci_device_id amd_ntb_pci_tbl[] = { - { PCI_VDEVICE(AMD, 0x145b), (kernel_ulong_t)&dev_data[0] }, - { PCI_VDEVICE(AMD, 0x148b), (kernel_ulong_t)&dev_data[1] }, - { PCI_VDEVICE(AMD, 0x14c0), (kernel_ulong_t)&dev_data[1] }, - { PCI_VDEVICE(AMD, 0x14c3), (kernel_ulong_t)&dev_data[1] }, - { PCI_VDEVICE(AMD, 0x155a), (kernel_ulong_t)&dev_data[1] }, - { PCI_VDEVICE(AMD, 0x17d4), (kernel_ulong_t)&dev_data[1] }, - { PCI_VDEVICE(AMD, 0x17d7), (kernel_ulong_t)&dev_data[2] }, - { PCI_VDEVICE(HYGON, 0x145b), (kernel_ulong_t)&dev_data[0] }, - { 0, } + { PCI_VDEVICE(AMD, 0x145b), .driver_data = (kernel_ulong_t)&dev_data[0] }, + { PCI_VDEVICE(AMD, 0x148b), .driver_data = (kernel_ulong_t)&dev_data[1] }, + { PCI_VDEVICE(AMD, 0x14c0), .driver_data = (kernel_ulong_t)&dev_data[1] }, + { PCI_VDEVICE(AMD, 0x14c3), .driver_data = (kernel_ulong_t)&dev_data[1] }, + { PCI_VDEVICE(AMD, 0x155a), .driver_data = (kernel_ulong_t)&dev_data[1] }, + { PCI_VDEVICE(AMD, 0x17d4), .driver_data = (kernel_ulong_t)&dev_data[1] }, + { PCI_VDEVICE(AMD, 0x17d7), .driver_data = (kernel_ulong_t)&dev_data[2] }, + { PCI_VDEVICE(HYGON, 0x145b), .driver_data = (kernel_ulong_t)&dev_data[0] }, + { } }; MODULE_DEVICE_TABLE(pci, amd_ntb_pci_tbl); From d85589879f19ad8514c508709865f064be761df5 Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Fri, 26 Jun 2026 17:42:10 -0700 Subject: [PATCH 294/297] Revert "Input: rmi4 - fix register descriptor address calculation" The register descriptor presence register is a packet register, which means its bytes share a single RMI address. It does not occupy consecutive addresses, and the register structure that follows it is located at the next RMI address (presence_address + 1), not (presence_address + presence_size). Revert the incorrect address calculation introduced in commit a98518e72439. Reported-by: "Barry K. Nathan" Tested-by: "Barry K. Nathan" Cc: stable@vger.kernel.org Signed-off-by: Dmitry Torokhov --- drivers/input/rmi4/rmi_driver.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/input/rmi4/rmi_driver.c b/drivers/input/rmi4/rmi_driver.c index 49a59da6a841..a28eef1b765e 100644 --- a/drivers/input/rmi4/rmi_driver.c +++ b/drivers/input/rmi4/rmi_driver.c @@ -643,7 +643,7 @@ int rmi_read_register_desc(struct rmi_device *d, u16 addr, ret = rmi_read_block(d, addr, buf, size_presence_reg); if (ret) return ret; - addr += size_presence_reg; + ++addr; if (buf[0] == 0) { if (size_presence_reg < 3) From 2d6d33e45dd4fb768758d5f6e747deadcd66b9fc Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Fri, 26 Jun 2026 16:33:21 -0700 Subject: [PATCH 295/297] Input: rmi4 - tolerate short register descriptor structure Some touchpads (e.g. ThinkPad T14 Gen 1) have buggy firmware that reports a register descriptor structure size that is too small for the number of registers it claims to have in the presence map. The remaining bytes in the structure are 0, which with the new strict bounds checking causes the parser to fail with -EIO, aborting the device probe. Tolerate such short reads by dropping the remaining (unparseable or 0-size) registers from the list instead of failing the probe, preventing the driver from trying to use them. Fixes: 0adb483fbf2d ("Input: rmi4 - refactor register descriptor parsing") Reported-by: Barry K. Nathan Tested-by: Barry K. Nathan Cc: stable@vger.kernel.org Assisted-by: Antigravity:gemini-3.5-flash Signed-off-by: Dmitry Torokhov --- drivers/input/rmi4/rmi_driver.c | 37 ++++++++++++++++++++++----------- 1 file changed, 25 insertions(+), 12 deletions(-) diff --git a/drivers/input/rmi4/rmi_driver.c b/drivers/input/rmi4/rmi_driver.c index a28eef1b765e..5d49a9021c7d 100644 --- a/drivers/input/rmi4/rmi_driver.c +++ b/drivers/input/rmi4/rmi_driver.c @@ -616,8 +616,8 @@ int rmi_read_register_desc(struct rmi_device *d, u16 addr, unsigned int presence_offset; unsigned int map_offset; unsigned int offset; + unsigned int num_registers; unsigned int reg; - int i; int b; int ret; @@ -657,7 +657,7 @@ int rmi_read_register_desc(struct rmi_device *d, u16 addr, memset(presence_map, 0, sizeof(presence_map)); map_offset = 0; - for (i = presence_offset; i < size_presence_reg; i++) { + for (int i = presence_offset; i < size_presence_reg; i++) { for (b = 0; b < 8; b++) { if (buf[i] & BIT(b)) { if (map_offset >= RMI_REG_DESC_PRESENCE_BITS) @@ -697,28 +697,41 @@ int rmi_read_register_desc(struct rmi_device *d, u16 addr, if (ret) return ret; - reg = find_first_bit(presence_map, RMI_REG_DESC_PRESENCE_BITS); offset = 0; - for (i = 0; i < rdesc->num_registers; i++) { - struct rmi_register_desc_item *item = &rdesc->registers[i]; + num_registers = 0; + for_each_set_bit(reg, presence_map, RMI_REG_DESC_PRESENCE_BITS) { + struct rmi_register_desc_item *item = &rdesc->registers[num_registers]; int item_size; + if (offset >= rdesc->struct_size) + break; + item_size = rmi_parse_register_desc_item(item, &struct_buf[offset], rdesc->struct_size - offset); - if (item_size < 0) - return item_size; + if (item_size < 0) { + dev_warn(&d->dev, + "%s: Failed to parse register %d descriptor, ignoring it\n", + __func__, reg); + break; + } item->reg = reg; offset += item_size; - rmi_dbg(RMI_DEBUG_CORE, &d->dev, - "%s: reg: %d reg size: %u subpackets: %d\n", __func__, - item->reg, item->reg_size, item->num_subpackets); + if (item->reg_size == 0) { + dev_warn(&d->dev, + "%s: Register %d has 0 size, ignoring it\n", + __func__, item->reg); + } else { + rmi_dbg(RMI_DEBUG_CORE, &d->dev, + "%s: reg: %d reg size: %u subpackets: %d\n", __func__, + item->reg, item->reg_size, item->num_subpackets); - reg = find_next_bit(presence_map, - RMI_REG_DESC_PRESENCE_BITS, reg + 1); + num_registers++; + } } + rdesc->num_registers = num_registers; return 0; } From d86d4f8cbb5a55a3b9b86f7b5ab8c4cdda600a3f Mon Sep 17 00:00:00 2001 From: Xu Rao Date: Wed, 24 Jun 2026 17:47:39 +0800 Subject: [PATCH 296/297] Input: gscps2 - advance receive buffer write index Commit 44f920069911 ("Input: gscps2 - use guard notation when acquiring spinlock") moved the receive loop into gscps2_read_data() and gscps2_report_data(). While moving the code, it preserved the writes to buffer[ps2port->append], but omitted the following producer index update from the original loop: ps2port->append = (ps2port->append + 1) & BUFFER_SIZE; As a result, append never advances. Since gscps2_report_data() only reports bytes while act != append, the receive buffer always appears empty and no keyboard or mouse data reaches the serio core. Restore the omitted index update. Fixes: 44f920069911 ("Input: gscps2 - use guard notation when acquiring spinlock") Cc: stable@vger.kernel.org # 6.13+ Signed-off-by: Xu Rao Link: https://patch.msgid.link/460B5655BA580C60+20260624094739.850306-1-raoxu@uniontech.com Signed-off-by: Dmitry Torokhov --- drivers/input/serio/gscps2.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/input/serio/gscps2.c b/drivers/input/serio/gscps2.c index 22b2f57fd91f..bf9b993f5733 100644 --- a/drivers/input/serio/gscps2.c +++ b/drivers/input/serio/gscps2.c @@ -219,6 +219,7 @@ static void gscps2_read_data(struct gscps2port *ps2port) ps2port->buffer[ps2port->append].str = status; ps2port->buffer[ps2port->append].data = gscps2_readb_input(ps2port->addr); + ps2port->append = (ps2port->append + 1) & BUFFER_SIZE; } while (true); } From dc59e4fea9d83f03bad6bddf3fa2e52491777482 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 28 Jun 2026 12:01:31 -0700 Subject: [PATCH 297/297] Linux 7.2-rc1 --- Makefile | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/Makefile b/Makefile index 12fd3d2d47b5..b9c5792c79e0 100644 --- a/Makefile +++ b/Makefile @@ -1,8 +1,8 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 7 -PATCHLEVEL = 1 +PATCHLEVEL = 2 SUBLEVEL = 0 -EXTRAVERSION = +EXTRAVERSION = -rc1 NAME = Baby Opossum Posse # *DOCUMENTATION*