6.1.148-rc1 review

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

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

From: Thomas Fourier <[email protected]>

[ Upstream commit cb7fa6b6fc71e0c801e271aa498e2f19e6df2931 ]

The dma_unmap_sg() functions should be called with the same nents as the dma_map_sg(), not the value the map function returned.

---
 drivers/crypto/inside-secure/safexcel_hash.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

index ecf64cc35fff..08227d44a27b 100644
@@ -249,7 +249,9 @@ static int safexcel_handle_req_result(struct safexcel_crypto_priv *priv,
 	safexcel_complete(priv, ring);
 
 	if (sreq->nents) {
-		dma_unmap_sg(priv->dev, areq->src, sreq->nents, DMA_TO_DEVICE);
+		dma_unmap_sg(priv->dev, areq->src,
+			     sg_nents_for_len(areq->src, areq->nbytes),
+			     DMA_TO_DEVICE);
 		sreq->nents = 0;
 	}
 

@@ -497,7 +499,9 @@ static int safexcel_ahash_send_req(struct crypto_async_request *async, int ring,
 			 DMA_FROM_DEVICE);
 unmap_sg:
 	if (req->nents) {
-		dma_unmap_sg(priv->dev, areq->src, req->nents, DMA_TO_DEVICE);
+		dma_unmap_sg(priv->dev, areq->src,
+			     sg_nents_for_len(areq->src, areq->nbytes),
+			     DMA_TO_DEVICE);
 		req->nents = 0;
 	}
 cdesc_rollback:

2.39.5

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

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

From: Mengbiao Xiong <[email protected]>

[ Upstream commit 181698af38d3f93381229ad89c09b5bd0496661a ]

When CONFIG_CRYPTO_DEV_CCP_DEBUGFS is enabled, rebinding the ccp device causes the following crash:

$ echo '0000:0a:00.2' > /sys/bus/pci/drivers/ccp/unbind
$ echo '0000:0a:00.2' > /sys/bus/pci/drivers/ccp/bind

[  204.976930] BUG: kernel NULL pointer dereference, address: 0000000000000098
[  204.978026] #PF: supervisor write access in kernel mode
[  204.979126] #PF: error_code(0x0002) - not-present page
[  204.980226] PGD 0 P4D 0
[  204.981317] Oops: Oops: 0002 [#1] SMP NOPTI
...
[  204.997852] Call Trace:
[  204.999074]  <TASK>
[  205.000297]  start_creating+0x9f/0x1c0
[  205.001533]  debugfs_create_dir+0x1f/0x170
[  205.002769]  ? srso_return_thunk+0x5/0x5f
[  205.004000]  ccp5_debugfs_setup+0x87/0x170 [ccp]
[  205.005241]  ccp5_init+0x8b2/0x960 [ccp]
[  205.006469]  ccp_dev_init+0xd4/0x150 [ccp]
[  205.007709]  sp_init+0x5f/0x80 [ccp]
[  205.008942]  sp_pci_probe+0x283/0x2e0 [ccp]
[  205.010165]  ? srso_return_thunk+0x5/0x5f
[  205.011376]  local_pci_probe+0x4f/0xb0
[  205.012584]  pci_device_probe+0xdb/0x230
[  205.013810]  really_probe+0xed/0x380
[  205.015024]  __driver_probe_device+0x7e/0x160
[  205.016240]  device_driver_attach+0x2f/0x60
[  205.017457]  bind_store+0x7c/0xb0
[  205.018663]  drv_attr_store+0x28/0x40
[  205.019868]  sysfs_kf_write+0x5f/0x70
[  205.021065]  kernfs_fop_write_iter+0x145/0x1d0
[  205.022267]  vfs_write+0x308/0x440
[  205.023453]  ksys_write+0x6d/0xe0
[  205.024616]  __x64_sys_write+0x1e/0x30
[  205.025778]  x64_sys_call+0x16ba/0x2150
[  205.026942]  do_syscall_64+0x56/0x1e0
[  205.028108]  entry_SYSCALL_64_after_hwframe+0x76/0x7e
[  205.029276] RIP: 0033:0x7fbc36f10104
[  205.030420] Code: 89 02 48 c7 c0 ff ff ff ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 48 8d 05 e1 08 2e 00 8b 00 85 c0 75 13 b8 01 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 54 f3 c3 66 90 41 54 55 49 89 d4 53 48 89 f5

This patch sets ccp_debugfs_dir to NULL after destroying it in ccp5_debugfs_destroy, allowing the directory dentry to be recreated when rebinding the ccp device.

Tested on AMD Ryzen 7 1700X.

---
 drivers/crypto/ccp/ccp-debugfs.c | 3 +++
 1 file changed, 3 insertions(+)

index a1055554b47a..dc26bc22c91d 100644
@@ -319,5 +319,8 @@ void ccp5_debugfs_setup(struct ccp_device *ccp)
 
 void ccp5_debugfs_destroy(void)
 {
+	mutex_lock(&ccp_debugfs_lock);
 	debugfs_remove_recursive(ccp_debugfs_dir);
+	ccp_debugfs_dir = NULL;
+	mutex_unlock(&ccp_debugfs_lock);
 }

2.39.5

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

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

From: Junxian Huang <[email protected]>

[ Upstream commit 79d56805c5068f2bc81518043e043c3dedd1c82a ]

Fix -Wframe-larger-than issue by allocating memory for qpc struct with kzalloc() instead of using stack memory.

---
 drivers/infiniband/hw/hns/hns_roce_hw_v2.c | 15 ++++++++++-----
 1 file changed, 10 insertions(+), 5 deletions(-)

index be5d7a8ab4d4..72c719805af3 100644
@@ -5331,11 +5331,10 @@ static int hns_roce_v2_modify_qp(struct ib_qp *ibqp,
 {
 	struct hns_roce_dev *hr_dev = to_hr_dev(ibqp->device);
 	struct hns_roce_qp *hr_qp = to_hr_qp(ibqp);
-	struct hns_roce_v2_qp_context ctx[2];
-	struct hns_roce_v2_qp_context *context = ctx;
-	struct hns_roce_v2_qp_context *qpc_mask = ctx + 1;
+	struct hns_roce_v2_qp_context *context;
+	struct hns_roce_v2_qp_context *qpc_mask;
 	struct ib_device *ibdev = &hr_dev->ib_dev;
-	int ret;
+	int ret = -ENOMEM;
 
 	if (attr_mask & ~IB_QP_ATTR_STANDARD_BITS)
 		return -EOPNOTSUPP;

@@ -5346,7 +5345,11 @@ static int hns_roce_v2_modify_qp(struct ib_qp *ibqp,
 	 * we should set all bits of the relevant fields in context mask to
 	 * 0 at the same time, else set them to 0x1.
 	 */
-	memset(context, 0, hr_dev->caps.qpc_sz);
+	context = kvzalloc(sizeof(*context), GFP_KERNEL);
+	qpc_mask = kvzalloc(sizeof(*qpc_mask), GFP_KERNEL);
+	if (!context || !qpc_mask)
+		goto out;
+
 	memset(qpc_mask, 0xff, hr_dev->caps.qpc_sz);
 
 	ret = hns_roce_v2_set_abs_fields(ibqp, attr, attr_mask, cur_state,

@@ -5388,6 +5391,8 @@ static int hns_roce_v2_modify_qp(struct ib_qp *ibqp,
 		clear_qp(hr_qp);
 
 out:
+	kvfree(qpc_mask);
+	kvfree(context);
 	return ret;
 }
 

2.39.5

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

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

From: Arnd Bergmann <[email protected]>

[ Upstream commit adc353c0bfb243ebfd29b6222fa3bf149169a6de ]

A CPU mask on the stack is broken for large values of CONFIG_NR_CPUS:

kernel/trace/preemptirq_delay_test.c: In function ‘preemptirq_delay_run’:
kernel/trace/preemptirq_delay_test.c:143:1: error: the frame size of 8512 bytes is larger than 1536 bytes [-Werror=frame-larger-than=]

Fall back to dynamic allocation here.

---
 kernel/trace/preemptirq_delay_test.c | 13 +++++++++----
 1 file changed, 9 insertions(+), 4 deletions(-)

index cb0871fbdb07..8af92dbe98f0 100644
@@ -119,12 +119,15 @@ static int preemptirq_delay_run(void *data)
 {
 	int i;
 	int s = MIN(burst_size, NR_TEST_FUNCS);
-	struct cpumask cpu_mask;
+	cpumask_var_t cpu_mask;
+
+	if (!alloc_cpumask_var(&cpu_mask, GFP_KERNEL))
+		return -ENOMEM;
 
 	if (cpu_affinity > -1) {
-		cpumask_clear(&cpu_mask);
-		cpumask_set_cpu(cpu_affinity, &cpu_mask);
-		if (set_cpus_allowed_ptr(current, &cpu_mask))
+		cpumask_clear(cpu_mask);
+		cpumask_set_cpu(cpu_affinity, cpu_mask);
+		if (set_cpus_allowed_ptr(current, cpu_mask))
 			pr_err("cpu_affinity:%d, failed\n", cpu_affinity);
 	}
 

@@ -141,6 +144,8 @@ static int preemptirq_delay_run(void *data)
 
 	__set_current_state(TASK_RUNNING);
 
+	free_cpumask_var(cpu_mask);
+
 	return 0;
 }
 

2.39.5

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

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

From: wangzijie <[email protected]>

[ Upstream commit ff7ec8dc1b646296f8d94c39339e8d3833d16c05 ]

Check pde->proc_ops->proc_lseek directly may cause UAF in rmmod scenario. It's a gap in proc_reg_open() after commit 654b33ada4ab("proc: fix UAF in proc_get_inode()"). Followed by AI Viro's suggestion, fix it in same manner.

---
 fs/proc/generic.c       | 2 ++
 fs/proc/inode.c         | 2 +-
 fs/proc/internal.h      | 5 +++++
 include/linux/proc_fs.h | 1 +
 4 files changed, 9 insertions(+), 1 deletion(-)

index b721bb88b4a6..c3a809e1d719 100644
@@ -568,6 +568,8 @@ static void pde_set_flags(struct proc_dir_entry *pde)
 	if (pde->proc_ops->proc_compat_ioctl)
 		pde->flags |= PROC_ENTRY_proc_compat_ioctl;
 #endif
+	if (pde->proc_ops->proc_lseek)
+		pde->flags |= PROC_ENTRY_proc_lseek;
 }
 
 struct proc_dir_entry *proc_create_data(const char *name, umode_t mode,

index bc4011901c90..623aa0d97a6d 100644
@@ -494,7 +494,7 @@ static int proc_reg_open(struct inode *inode, struct file *file)
 	typeof_member(struct proc_ops, proc_release) release;
 	struct pde_opener *pdeo;
 
-	if (!pde->proc_ops->proc_lseek)
+	if (!pde_has_proc_lseek(pde))
 		file->f_mode &= ~FMODE_LSEEK;
 
 	if (pde_is_permanent(pde)) {

index d115d22c01d4..019137261a03 100644
@@ -98,6 +98,11 @@ static inline bool pde_has_proc_compat_ioctl(const struct proc_dir_entry *pde)
 #endif
 }
 
+static inline bool pde_has_proc_lseek(const struct proc_dir_entry *pde)
+{
+	return pde->flags & PROC_ENTRY_proc_lseek;
+}
+
 extern struct kmem_cache *proc_dir_entry_cache;
 void pde_free(struct proc_dir_entry *pde);
 

index 39532c19aa28..ca9cd8a2569e 100644
@@ -27,6 +27,7 @@ enum {
 
 	PROC_ENTRY_proc_read_iter	= 1U << 1,
 	PROC_ENTRY_proc_compat_ioctl	= 1U << 2,
+	PROC_ENTRY_proc_lseek		= 1U << 3,
 };
 
 struct proc_ops {

2.39.5

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

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

From: Leo Yan <[email protected]>

[ Upstream commit 4a6cdecaa1497f1fbbd1d5307a225b6ca5a62a90 ]

Since the commit e9846f5ead26 ("perf test: In forked mode add check that fds aren't leaked"), the test "Breakpoint accounting" reports the error:

  # perf test -vvv "Breakpoint accounting"
  20: Breakpoint accounting:
  --- start ---
  test child forked, pid 373
  failed opening event 0
  failed opening event 0
  watchpoints count 4, breakpoints count 6, has_ioctl 1, share 0
  wp 0 created
  wp 1 created
  wp 2 created
  wp 3 created
  wp 0 modified to bp
  wp max created
  ---- end(0) ----
  Leak of file descriptor 7 that opened: 'anon_inode:[perf_event]'

A watchpoint's file descriptor was not properly released. This patch fixes the leak.

---
 tools/perf/tests/bp_account.c | 1 +
 1 file changed, 1 insertion(+)

index 6f921db33cf9..855b81c3326c 100644
@@ -102,6 +102,7 @@ static int bp_accounting(int wp_cnt, int share)
 		fd_wp = wp_event((void *)&the_var, &attr_new);
 		TEST_ASSERT_VAL("failed to create max wp\n", fd_wp != -1);
 		pr_debug("wp max created\n");
+		close(fd_wp);
 	}
 
 	for (i = 0; i < wp_cnt; i++)

2.39.5

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

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

From: Paul Kocialkowski <[email protected]>

[ Upstream commit e8ab346f9907a1a3aa2f0e5decf849925c06ae2e ]

The de clock is marked with CLK_SET_RATE_PARENT, which is really not necessary (as confirmed from experimentation) and significantly restricts flexibility for other clocks using the same parent.

In addition the source selection (parent) field is marked as using 2 bits, when it the documentation reports that it uses 3.

Fix both issues in the de clock definition.

---
 drivers/clk/sunxi-ng/ccu-sun8i-v3s.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

index fbb3529f0d3e..8263beac203b 100644
@@ -347,8 +347,7 @@ static SUNXI_CCU_GATE(dram_ohci_clk,	"dram-ohci",	"dram",
 
 static const char * const de_parents[] = { "pll-video", "pll-periph0" };
 static SUNXI_CCU_M_WITH_MUX_GATE(de_clk, "de", de_parents,
-				 0x104, 0, 4, 24, 2, BIT(31),
-				 CLK_SET_RATE_PARENT);
+				 0x104, 0, 4, 24, 3, BIT(31), 0);
 
 static const char * const tcon_parents[] = { "pll-video" };
 static SUNXI_CCU_M_WITH_MUX_GATE(tcon_clk, "tcon", tcon_parents,

2.39.5

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

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

From: Thomas Fourier <[email protected]>

[ Upstream commit 023a293b9cd0bb86a9b50cd7688a3d9d266826db ]

The dma_unmap_sg() functions should be called with the same nents as the dma_map_sg(), not the value the map function returned.

---
 drivers/scsi/ibmvscsi_tgt/libsrp.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

index 8a0e28aec928..0ecad398ed3d 100644
@@ -184,7 +184,8 @@ static int srp_direct_data(struct ibmvscsis_cmd *cmd, struct srp_direct_buf *md,
 	err = rdma_io(cmd, sg, nsg, md, 1, dir, len);
 
 	if (dma_map)
-		dma_unmap_sg(iue->target->dev, sg, nsg, DMA_BIDIRECTIONAL);
+		dma_unmap_sg(iue->target->dev, sg, cmd->se_cmd.t_data_nents,
+			     DMA_BIDIRECTIONAL);
 
 	return err;
 }

@@ -256,7 +257,8 @@ static int srp_indirect_data(struct ibmvscsis_cmd *cmd, struct srp_cmd *srp_cmd,
 	err = rdma_io(cmd, sg, nsg, md, nmd, dir, len);
 
 	if (dma_map)
-		dma_unmap_sg(iue->target->dev, sg, nsg, DMA_BIDIRECTIONAL);
+		dma_unmap_sg(iue->target->dev, sg, cmd->se_cmd.t_data_nents,
+			     DMA_BIDIRECTIONAL);
 
 free_mem:
 	if (token && dma_map) {

2.39.5

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

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

From: Thomas Fourier <[email protected]>

[ Upstream commit 3a988d0b65d7d1713ce7596eae288a293f3b938e ]

The dma_unmap_sg() functions should be called with the same nents as the dma_map_sg(), not the value the map function returned.

---
 drivers/scsi/elx/efct/efct_lio.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index be4b5c1ee32d..150d059e51ac 100644
@@ -396,7 +396,7 @@ efct_lio_sg_unmap(struct efct_io *io)
 		return;
 
 	dma_unmap_sg(&io->efct->pci->dev, cmd->t_data_sg,
-		     ocp->seg_map_cnt, cmd->data_direction);
+		     cmd->t_data_nents, cmd->data_direction);
 	ocp->seg_map_cnt = 0;
 }
 

2.39.5

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

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

From: Thomas Fourier <[email protected]>

[ Upstream commit 0141618727bc929fe868153d21797f10ce5bef3f ]

The dma_unmap_sg() functions should be called with the same nents as the dma_map_sg(), not the value the map function returned.

---
 drivers/scsi/mvsas/mv_sas.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

index a6867dae0e7c..1275f3be530f 100644
@@ -831,7 +831,7 @@ static int mvs_task_prep(struct sas_task *task, struct mvs_info *mvi, int is_tmf
 	dev_printk(KERN_ERR, mvi->dev, "mvsas prep failed[%d]!\n", rc);
 	if (!sas_protocol_ata(task->task_proto))
 		if (n_elem)
-			dma_unmap_sg(mvi->dev, task->scatter, n_elem,
+			dma_unmap_sg(mvi->dev, task->scatter, task->num_scatter,
 				     task->data_dir);
 prep_out:
 	return rc;

@@ -877,7 +877,7 @@ static void mvs_slot_task_free(struct mvs_info *mvi, struct sas_task *task,
 	if (!sas_protocol_ata(task->task_proto))
 		if (slot->n_elem)
 			dma_unmap_sg(mvi->dev, task->scatter,
-				     slot->n_elem, task->data_dir);
+				     task->num_scatter, task->data_dir);
 
 	switch (task->task_proto) {
 	case SAS_PROTOCOL_SMP:

2.39.5

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

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

From: Thomas Fourier <[email protected]>

[ Upstream commit 063bec4444d54e5f35d11949c5c90eaa1ff84c11 ]

The dma_unmap_sg() functions should be called with the same nents as the dma_map_sg(), not the value the map function returned.

---
 drivers/scsi/isci/request.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index 0f0732d56800..46d30a725d7e 100644
@@ -2907,7 +2907,7 @@ static void isci_request_io_request_complete(struct isci_host *ihost,
 					 task->total_xfer_len, task->data_dir);
 		else  /* unmap the sgl dma addresses */
 			dma_unmap_sg(&ihost->pdev->dev, task->scatter,
-				     request->num_sg_entries, task->data_dir);
+				     task->num_scatter, task->data_dir);
 		break;
 	case SAS_PROTOCOL_SMP: {
 		struct scatterlist *sg = &task->smp_task.smp_req;

2.39.5

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

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

From: Dan Carpenter <[email protected]>

[ Upstream commit 8b61d8ca751bc15875b50e0ff6ac3ba0cf95a529 ]

The "rec->len" value comes from the firmware. We generally do trust firmware, but it's always better to double check. If the length value is too large it would lead to memory corruption when we set "data[i] = ret;"

---
 drivers/watchdog/ziirave_wdt.c | 3 +++
 1 file changed, 3 insertions(+)

index d0e88875443a..06d59805c9c0 100644
@@ -302,6 +302,9 @@ static int ziirave_firm_verify(struct watchdog_device *wdd,
 		const u16 len = be16_to_cpu(rec->len);
 		const u32 addr = be32_to_cpu(rec->addr);
 
+		if (len > sizeof(data))
+			return -EINVAL;
+
 		if (ziirave_firm_addr_readonly(addr))
 			continue;
 

2.39.5

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

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

From: Ovidiu Panait <[email protected]>

[ Upstream commit 522a242a18adc5c63a24836715dbeec4dc3faee1 ]

Although unlikely, devm_pm_runtime_enable() call might fail, so handle the return value.

---
 drivers/char/hw_random/mtk-rng.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

index 3e00506543b6..72269d0f2a4e 100644
@@ -142,7 +142,9 @@ static int mtk_rng_probe(struct platform_device *pdev)
 	dev_set_drvdata(&pdev->dev, priv);
 	pm_runtime_set_autosuspend_delay(&pdev->dev, RNG_AUTOSUSPEND_TIMEOUT);
 	pm_runtime_use_autosuspend(&pdev->dev);
-	devm_pm_runtime_enable(&pdev->dev);
+	ret = devm_pm_runtime_enable(&pdev->dev);
+	if (ret)
+		return ret;
 
 	dev_info(&pdev->dev, "registered RNG driver\n");
 

2.39.5

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

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

From: Thomas Fourier <[email protected]>

[ Upstream commit 01951a7dc5ac1a37e5fb7d86ea7eb2dfbf96e8b6 ]

The dma_unmap_sg() functions should be called with the same nents as the dma_map_sg(), not the value the map function returned.

---
 drivers/crypto/keembay/keembay-ocs-hcu-core.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

index 0379dbf32a4c..6b46c37f00ae 100644
@@ -68,6 +68,7 @@ struct ocs_hcu_ctx {
  * @sg_data_total:  Total data in the SG list at any time.
  * @sg_data_offset: Offset into the data of the current individual SG node.
  * @sg_dma_nents:   Number of sg entries mapped in dma_list.
+ * @nents:          Number of entries in the scatterlist.
  */
 struct ocs_hcu_rctx {
 	struct ocs_hcu_dev	*hcu_dev;

@@ -91,6 +92,7 @@ struct ocs_hcu_rctx {
 	unsigned int		sg_data_total;
 	unsigned int		sg_data_offset;
 	unsigned int		sg_dma_nents;
+	unsigned int		nents;
 };
 
 /**

@@ -199,7 +201,7 @@ static void kmb_ocs_hcu_dma_cleanup(struct ahash_request *req,
 
 	/* Unmap req->src (if mapped). */
 	if (rctx->sg_dma_nents) {
-		dma_unmap_sg(dev, req->src, rctx->sg_dma_nents, DMA_TO_DEVICE);
+		dma_unmap_sg(dev, req->src, rctx->nents, DMA_TO_DEVICE);
 		rctx->sg_dma_nents = 0;
 	}
 

@@ -260,6 +262,10 @@ static int kmb_ocs_dma_prepare(struct ahash_request *req)
 			rc = -ENOMEM;
 			goto cleanup;
 		}
+
+		/* Save the value of nents to pass to dma_unmap_sg. */
+		rctx->nents = nents;
+
 		/*
 		 * The value returned by dma_map_sg() can be < nents; so update
 		 * nents accordingly.

2.39.5

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

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

From: Thomas Fourier <[email protected]>

[ Upstream commit 34b283636181ce02c52633551f594fec9876bec7 ]

The dma_unmap_sg() functions should be called with the same nents as the dma_map_sg(), not the value the map function returned.

---
 drivers/crypto/img-hash.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index 9629e98bd68b..0de49efb9ef9 100644
@@ -436,7 +436,7 @@ static int img_hash_write_via_dma_stop(struct img_hash_dev *hdev)
 	struct img_hash_request_ctx *ctx = ahash_request_ctx(hdev->req);
 
 	if (ctx->flags & DRIVER_FLAGS_SG)
-		dma_unmap_sg(hdev->dev, ctx->sg, ctx->dma_ct, DMA_TO_DEVICE);
+		dma_unmap_sg(hdev->dev, ctx->sg, 1, DMA_TO_DEVICE);
 
 	return 0;
 }

2.39.5

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

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

From: Bard Liao <[email protected]>

[ Upstream commit dba7d9dbfdc4389361ff3a910e767d3cfca22587 ]

The bus->params should be restored if the stream is failed to prepare. The issue exists since beginning. The Fixes tag just indicates the first commit that the commit can be applied to.

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

index 2624441d2fa9..3f23d9f0f726 100644
@@ -1402,7 +1402,7 @@ static int _sdw_prepare_stream(struct sdw_stream_runtime *stream,
 		if (ret < 0) {
 			dev_err(bus->dev, "Prepare port(s) failed ret = %d\n",
 				ret);
-			return ret;
+			goto restore_params;
 		}
 	}
 

2.39.5

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

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

From: Manivannan Sadhasivam <[email protected]>

[ Upstream commit 61ae7f8694fb4b57a8c02a1a8d2b601806afc999 ]

__iomem attribute is supposed to be used only with variables holding the MMIO pointer. But here, 'mw_addr' variable is just holding a 'void *' returned by pci_epf_alloc_space(). So annotating it with __iomem is clearly wrong. Hence, drop the attribute.

This also fixes the below sparse warning:

drivers/pci/endpoint/functions/pci-epf-vntb.c:524:17: warning: incorrect type in assignment (different address spaces)
drivers/pci/endpoint/functions/pci-epf-vntb.c:524:17: expected void [noderef] __iomem *mw_addr
drivers/pci/endpoint/functions/pci-epf-vntb.c:524:17: got void *
drivers/pci/endpoint/functions/pci-epf-vntb.c:530:21: warning: incorrect type in assignment (different address spaces)
drivers/pci/endpoint/functions/pci-epf-vntb.c:530:21: expected unsigned int [usertype] *epf_db
drivers/pci/endpoint/functions/pci-epf-vntb.c:530:21: got void [noderef] __iomem *mw_addr
drivers/pci/endpoint/functions/pci-epf-vntb.c:542:38: warning: incorrect type in argument 2 (different address spaces)
drivers/pci/endpoint/functions/pci-epf-vntb.c:542:38: expected void *addr
drivers/pci/endpoint/functions/pci-epf-vntb.c:542:38: got void [noderef] __iomem *mw_addr

---
 drivers/pci/endpoint/functions/pci-epf-vntb.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index 4ed0859e2397..d057537781f6 100644
@@ -534,7 +534,7 @@ static int epf_ntb_db_bar_init(struct epf_ntb *ntb)
 	struct device *dev = &ntb->epf->dev;
 	int ret;
 	struct pci_epf_bar *epf_bar;
-	void __iomem *mw_addr;
+	void *mw_addr;
 	enum pci_barno barno;
 	size_t size = 4 * ntb->db_count;
 

2.39.5

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

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

From: Dan Carpenter <[email protected]>

[ Upstream commit 2138e89cb066b40386b1d9ddd61253347d356474 ]

The do_k_string() and do_c_string() functions do essentially the same thing which is they add a string and a comma onto the end of an existing string. At the end, the caller will overwrite the last comma with a newline. Later, in orangefs_kernel_debug_init(), we add a newline to the string.

The change to do_k_string() is just cosmetic. I moved the "- 1" to the other side of the comparison and made it "+ 1". This has no effect on runtime, I just wanted the functions to match each other and the rest of the file.

However in do_c_string(), I removed the "- 2" which allows us to print two extra characters. I noticed this issue while reviewing the code and I doubt affects anything in real life. My guess is that this was double counting the comma and the newline. The "+ 1" accounts for the newline, and the caller will delete the final comma which ensures there is enough space for the newline.

Removing the "- 2" lets us print 2 more characters, but mainly it makes the code more consistent and understandable for reviewers.

---
 fs/orangefs/orangefs-debugfs.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

index fa41db088488..b57140ebfad0 100644
@@ -728,8 +728,8 @@ static void do_k_string(void *k_mask, int index)
 
 	if (*mask & s_kmod_keyword_mask_map[index].mask_val) {
 		if ((strlen(kernel_debug_string) +
-		     strlen(s_kmod_keyword_mask_map[index].keyword))
-			< ORANGEFS_MAX_DEBUG_STRING_LEN - 1) {
+		     strlen(s_kmod_keyword_mask_map[index].keyword) + 1)
+			< ORANGEFS_MAX_DEBUG_STRING_LEN) {
 				strcat(kernel_debug_string,
 				       s_kmod_keyword_mask_map[index].keyword);
 				strcat(kernel_debug_string, ",");

@@ -756,7 +756,7 @@ static void do_c_string(void *c_mask, int index)
 	    (mask->mask2 & cdm_array[index].mask2)) {
 		if ((strlen(client_debug_string) +
 		     strlen(cdm_array[index].keyword) + 1)
-			< ORANGEFS_MAX_DEBUG_STRING_LEN - 2) {
+			< ORANGEFS_MAX_DEBUG_STRING_LEN) {
 				strcat(client_debug_string,
 				       cdm_array[index].keyword);
 				strcat(client_debug_string, ",");

2.39.5

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

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

From: Thomas Fourier <[email protected]>

[ Upstream commit 60095aca6b471b7b7a79c80b7395f7e4e414b479 ]

The DMA map functions can fail and should be tested for errors.

In case of error, unmap the already mapped regions.

---
 drivers/dma/mv_xor.c | 21 +++++++++++++++++++--
 1 file changed, 19 insertions(+), 2 deletions(-)

index ea48661e87ea..ca0ba1d46283 100644
@@ -1061,8 +1061,16 @@ mv_xor_channel_add(struct mv_xor_device *xordev,
 	 */
 	mv_chan->dummy_src_addr = dma_map_single(dma_dev->dev,
 		mv_chan->dummy_src, MV_XOR_MIN_BYTE_COUNT, DMA_FROM_DEVICE);
+	if (dma_mapping_error(dma_dev->dev, mv_chan->dummy_src_addr))
+		return ERR_PTR(-ENOMEM);
+
 	mv_chan->dummy_dst_addr = dma_map_single(dma_dev->dev,
 		mv_chan->dummy_dst, MV_XOR_MIN_BYTE_COUNT, DMA_TO_DEVICE);
+	if (dma_mapping_error(dma_dev->dev, mv_chan->dummy_dst_addr)) {
+		ret = -ENOMEM;
+		goto err_unmap_src;
+	}
+
 
 	/* allocate coherent memory for hardware descriptors
 	 * note: writecombine gives slightly better performance, but

@@ -1071,8 +1079,10 @@ mv_xor_channel_add(struct mv_xor_device *xordev,
 	mv_chan->dma_desc_pool_virt =
 	  dma_alloc_wc(&pdev->dev, MV_XOR_POOL_SIZE, &mv_chan->dma_desc_pool,
 		       GFP_KERNEL);
-	if (!mv_chan->dma_desc_pool_virt)
-		return ERR_PTR(-ENOMEM);
+	if (!mv_chan->dma_desc_pool_virt) {
+		ret = -ENOMEM;
+		goto err_unmap_dst;
+	}
 
 	/* discover transaction capabilites from the platform data */
 	dma_dev->cap_mask = cap_mask;

@@ -1155,6 +1165,13 @@ mv_xor_channel_add(struct mv_xor_device *xordev,
 err_free_dma:
 	dma_free_coherent(&pdev->dev, MV_XOR_POOL_SIZE,
 			  mv_chan->dma_desc_pool_virt, mv_chan->dma_desc_pool);
+err_unmap_dst:
+	dma_unmap_single(dma_dev->dev, mv_chan->dummy_dst_addr,
+			 MV_XOR_MIN_BYTE_COUNT, DMA_TO_DEVICE);
+err_unmap_src:
+	dma_unmap_single(dma_dev->dev, mv_chan->dummy_src_addr,
+			 MV_XOR_MIN_BYTE_COUNT, DMA_FROM_DEVICE);
+
 	return ERR_PTR(ret);
 }
 

2.39.5

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

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

From: Thomas Fourier <[email protected]>

[ Upstream commit c6ee78fc8f3e653bec427cfd06fec7877ee782bd ]

The DMA map functions can fail and should be tested for errors. If the mapping fails, unmap and return an error.

---
 drivers/dma/nbpfaxi.c | 13 +++++++++++++
 1 file changed, 13 insertions(+)

index e389945e36f2..256ae956b55e 100644
@@ -712,6 +712,9 @@ static int nbpf_desc_page_alloc(struct nbpf_channel *chan)
 		list_add_tail(&ldesc->node, &lhead);
 		ldesc->hwdesc_dma_addr = dma_map_single(dchan->device->dev,
 					hwdesc, sizeof(*hwdesc), DMA_TO_DEVICE);
+		if (dma_mapping_error(dchan->device->dev,
+				      ldesc->hwdesc_dma_addr))
+			goto unmap_error;
 
 		dev_dbg(dev, "%s(): mapped 0x%p to %pad\n", __func__,
 			hwdesc, &ldesc->hwdesc_dma_addr);

@@ -738,6 +741,16 @@ static int nbpf_desc_page_alloc(struct nbpf_channel *chan)
 	spin_unlock_irq(&chan->lock);
 
 	return ARRAY_SIZE(dpage->desc);
+
+unmap_error:
+	while (i--) {
+		ldesc--; hwdesc--;
+
+		dma_unmap_single(dchan->device->dev, ldesc->hwdesc_dma_addr,
+				 sizeof(hwdesc), DMA_TO_DEVICE);
+	}
+
+	return -ENOMEM;
 }
 
 static void nbpf_desc_put(struct nbpf_desc *desc)

2.39.5

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

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

From: Ben Hutchings <[email protected]>

[ Upstream commit c32969d0362a790fbc6117e0b6a737a7e510b843 ]

arch/sh/Makefile defines and exports ld-bfd to be used by arch/sh/boot/compressed/Makefile and arch/sh/boot/romimage/Makefile. However some shells, including dash, will not pass through environment variables whose name includes a hyphen. Usually GNU make does not use a shell to recurse, but if e.g. $(srctree) contains '~' it will use a shell here.

Other instances of this problem were previously fixed by commits 2bfbe7881ee0 "kbuild: Do not use hyphen in exported variable name" and 82977af93a0d "sh: rename suffix-y to suffix_y".

Rename the variable to ld_bfd.

References: https://buildd.debian.org/status/fetch.php?pkg=linux&arch=sh4&ver=4.13%7Erc5-1%7Eexp1&stamp=1502943967&raw=0

---
 arch/sh/Makefile                 | 10 +++++-----
 arch/sh/boot/compressed/Makefile |  4 ++--
 arch/sh/boot/romimage/Makefile   |  4 ++--
 3 files changed, 9 insertions(+), 9 deletions(-)

index 5c8776482530..22c47e4ad572 100644
@@ -103,16 +103,16 @@ UTS_MACHINE		:= sh
 LDFLAGS_vmlinux		+= -e _stext
 
 ifdef CONFIG_CPU_LITTLE_ENDIAN
-ld-bfd			:= elf32-sh-linux
-LDFLAGS_vmlinux		+= --defsym jiffies=jiffies_64 --oformat $(ld-bfd)
+ld_bfd			:= elf32-sh-linux
+LDFLAGS_vmlinux		+= --defsym jiffies=jiffies_64 --oformat $(ld_bfd)
 KBUILD_LDFLAGS		+= -EL
 else
-ld-bfd			:= elf32-shbig-linux
-LDFLAGS_vmlinux		+= --defsym jiffies=jiffies_64+4 --oformat $(ld-bfd)
+ld_bfd			:= elf32-shbig-linux
+LDFLAGS_vmlinux		+= --defsym jiffies=jiffies_64+4 --oformat $(ld_bfd)
 KBUILD_LDFLAGS		+= -EB
 endif
 
-export ld-bfd
+export ld_bfd
 
 # Mach groups
 machdir-$(CONFIG_SOLUTION_ENGINE)		+= mach-se

index 591125c42d49..05542eb20136 100644
@@ -36,7 +36,7 @@ endif
 
 ccflags-remove-$(CONFIG_MCOUNT) += -pg
 
-LDFLAGS_vmlinux := --oformat $(ld-bfd) -Ttext $(IMAGE_OFFSET) -e startup \
+LDFLAGS_vmlinux := --oformat $(ld_bfd) -Ttext $(IMAGE_OFFSET) -e startup \
 		   -T $(obj)/../../kernel/vmlinux.lds
 
 KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING

@@ -60,7 +60,7 @@ $(obj)/vmlinux.bin.lzo: $(obj)/vmlinux.bin FORCE
 
 OBJCOPYFLAGS += -R .empty_zero_page
 
-LDFLAGS_piggy.o := -r --format binary --oformat $(ld-bfd) -T
+LDFLAGS_piggy.o := -r --format binary --oformat $(ld_bfd) -T
 
 $(obj)/piggy.o: $(obj)/vmlinux.scr $(obj)/vmlinux.bin.$(suffix_y) FORCE
 	$(call if_changed,ld)

index c7c8be58400c..17b03df0a8de 100644
@@ -13,7 +13,7 @@ mmcif-obj-$(CONFIG_CPU_SUBTYPE_SH7724)	:= $(obj)/mmcif-sh7724.o
 load-$(CONFIG_ROMIMAGE_MMCIF)		:= $(mmcif-load-y)
 obj-$(CONFIG_ROMIMAGE_MMCIF)		:= $(mmcif-obj-y)
 
-LDFLAGS_vmlinux := --oformat $(ld-bfd) -Ttext $(load-y) -e romstart \
+LDFLAGS_vmlinux := --oformat $(ld_bfd) -Ttext $(load-y) -e romstart \
 		   -T $(obj)/../../kernel/vmlinux.lds
 
 $(obj)/vmlinux: $(obj)/head.o $(obj-y) $(obj)/piggy.o FORCE

@@ -24,7 +24,7 @@ OBJCOPYFLAGS += -j .empty_zero_page
 $(obj)/zeropage.bin: vmlinux FORCE
 	$(call if_changed,objcopy)
 
-LDFLAGS_piggy.o := -r --format binary --oformat $(ld-bfd) -T
+LDFLAGS_piggy.o := -r --format binary --oformat $(ld_bfd) -T
 
 $(obj)/piggy.o: $(obj)/vmlinux.scr $(obj)/zeropage.bin arch/sh/boot/zImage FORCE
 	$(call if_changed,ld)

2.39.5

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

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

From: Giovanni Cabiddu <[email protected]>

[ Upstream commit 6908c5f4f066a0412c3d9a6f543a09fa7d87824b ]

The adf_ring_next() function in the QAT debug transport interface fails to correctly update the position index when reaching the end of the ring elements. This triggers the following kernel warning when reading ring files, such as /sys/kernel/debug/qat_c6xx_<D:B:D:F>/transport/bank_00/ring_00:

   [27725.022965] seq_file: buggy .next function adf_ring_next [intel_qat] did not update position index

Ensure that the *pos index is incremented before returning NULL when after the last element in the ring is found, satisfying the seq_file API requirements and preventing the warning.

---
 drivers/crypto/qat/qat_common/adf_transport_debug.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

index e2dd568b87b5..621b5d3dfcef 100644
@@ -31,8 +31,10 @@ static void *adf_ring_next(struct seq_file *sfile, void *v, loff_t *pos)
 	struct adf_etr_ring_data *ring = sfile->private;
 
 	if (*pos >= (ADF_SIZE_TO_RING_SIZE_IN_BYTES(ring->ring_size) /
-		     ADF_MSG_SIZE_TO_BYTES(ring->msg_size)))
+		     ADF_MSG_SIZE_TO_BYTES(ring->msg_size))) {
+		(*pos)++;
 		return NULL;
+	}
 
 	return ring->base_addr +
 		(ADF_MSG_SIZE_TO_BYTES(ring->msg_size) * (*pos)++);

2.39.5

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

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

From: Chenyuan Yang <[email protected]>

[ Upstream commit da11e6a30e0bb8e911288bdc443b3dc8f6a7cac7 ]

fb_add_videomode() can fail with -ENOMEM when its internal kmalloc() cannot allocate a struct fb_modelist. If that happens, the modelist stays empty but the driver continues to register. Add a check for its return value to prevent poteintial null-ptr-deref, which is similar to the commit 17186f1f90d3 ("fbdev:
Fix do_register_framebuffer to prevent null-ptr-deref in fb_videomode_to_var").

---
 drivers/video/fbdev/imxfb.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

index 32b8374abeca..3770225a0b90 100644
@@ -1011,8 +1011,13 @@ static int imxfb_probe(struct platform_device *pdev)
 	info->fix.smem_start = fbi->map_dma;
 
 	INIT_LIST_HEAD(&info->modelist);
-	for (i = 0; i < fbi->num_modes; i++)
-		fb_add_videomode(&fbi->mode[i].mode, &info->modelist);
+	for (i = 0; i < fbi->num_modes; i++) {
+		ret = fb_add_videomode(&fbi->mode[i].mode, &info->modelist);
+		if (ret) {
+			dev_err(&pdev->dev, "Failed to add videomode\n");
+			goto failed_cmap;
+		}
+	}
 
 	/*
 	 * This makes sure that our colour bitfield

2.39.5

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

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

From: Zheng Yu <[email protected]>

[ Upstream commit 856db37592021e9155384094e331e2d4589f28b1 ]

In dbAllocCtl(), read_metapage() increases the reference count of the metapage. However, when dp->tree.budmin < 0, the function returns -EIO without calling release_metapage() to decrease the reference count, leading to a memory leak.

Add release_metapage(mp) before the error return to properly manage the metapage reference count and prevent the leak.

---
 fs/jfs/jfs_dmap.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

index 32ae408ee699..c761291f59ac 100644
@@ -1809,8 +1809,10 @@ dbAllocCtl(struct bmap * bmp, s64 nblocks, int l2nb, s64 blkno, s64 * results)
 			return -EIO;
 		dp = (struct dmap *) mp->data;
 
-		if (dp->tree.budmin < 0)
+		if (dp->tree.budmin < 0) {
+			release_metapage(mp);
 			return -EIO;
+		}
 
 		/* try to allocate the blocks.
 		 */

2.39.5

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

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

From: Thomas Fourier <[email protected]>

[ Upstream commit e1e6b933c56b1e9fda93caa0b8bae39f3f421e5c ]

It seems like what was intended is to test if the dma_map of the previous line failed but the wrong dma address was passed.

Rule: add

---
 drivers/mtd/nand/raw/atmel/nand-controller.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index 41c6bd6e2d72..710d1d73eb35 100644
@@ -373,7 +373,7 @@ static int atmel_nand_dma_transfer(struct atmel_nand_controller *nc,
 	dma_cookie_t cookie;
 
 	buf_dma = dma_map_single(nc->dev, buf, len, dir);
-	if (dma_mapping_error(nc->dev, dev_dma)) {
+	if (dma_mapping_error(nc->dev, buf_dma)) {
 		dev_err(nc->dev,
 			"Failed to prepare a buffer for DMA access\n");
 		goto err;

2.39.5

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

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

From: Thomas Fourier <[email protected]>

[ Upstream commit 3b36f86dc47261828f96f826077131a35dd825fd ]

The DMA map functions can fail and should be tested for errors.

---
 drivers/mtd/nand/raw/rockchip-nand-controller.c | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

index d8456b849c13..1efe97fd6595 100644
@@ -657,9 +657,16 @@ static int rk_nfc_write_page_hwecc(struct nand_chip *chip, const u8 *buf,
 
 	dma_data = dma_map_single(nfc->dev, (void *)nfc->page_buf,
 				  mtd->writesize, DMA_TO_DEVICE);
+	if (dma_mapping_error(nfc->dev, dma_data))
+		return -ENOMEM;
+
 	dma_oob = dma_map_single(nfc->dev, nfc->oob_buf,
 				 ecc->steps * oob_step,
 				 DMA_TO_DEVICE);
+	if (dma_mapping_error(nfc->dev, dma_oob)) {
+		dma_unmap_single(nfc->dev, dma_data, mtd->writesize, DMA_TO_DEVICE);
+		return -ENOMEM;
+	}
 
 	reinit_completion(&nfc->done);
 	writel(INT_DMA, nfc->regs + nfc->cfg->int_en_off);

@@ -773,9 +780,17 @@ static int rk_nfc_read_page_hwecc(struct nand_chip *chip, u8 *buf, int oob_on,
 	dma_data = dma_map_single(nfc->dev, nfc->page_buf,
 				  mtd->writesize,
 				  DMA_FROM_DEVICE);
+	if (dma_mapping_error(nfc->dev, dma_data))
+		return -ENOMEM;
+
 	dma_oob = dma_map_single(nfc->dev, nfc->oob_buf,
 				 ecc->steps * oob_step,
 				 DMA_FROM_DEVICE);
+	if (dma_mapping_error(nfc->dev, dma_oob)) {
+		dma_unmap_single(nfc->dev, dma_data, mtd->writesize,
+				 DMA_FROM_DEVICE);
+		return -ENOMEM;
+	}
 
 	/*
 	 * The first blocks (4, 8 or 16 depending on the device)

2.39.5

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

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

From: Balamanikandan Gunasundar <[email protected]>

[ Upstream commit f552a7c7e0a14215cb8a6fd89e60fa3932a74786 ]

Setup the pmecc data setup time as 3 clock cycles for 133MHz as recommended by the datasheet.

---
 drivers/mtd/nand/raw/atmel/pmecc.c | 6 ++++++
 1 file changed, 6 insertions(+)

index 3c7dee1be21d..0b402823b619 100644
@@ -143,6 +143,7 @@ struct atmel_pmecc_caps {
 	int nstrengths;
 	int el_offset;
 	bool correct_erased_chunks;
+	bool clk_ctrl;
 };
 
 struct atmel_pmecc {

@@ -843,6 +844,10 @@ static struct atmel_pmecc *atmel_pmecc_create(struct platform_device *pdev,
 	if (IS_ERR(pmecc->regs.errloc))
 		return ERR_CAST(pmecc->regs.errloc);
 
+	/* pmecc data setup time */
+	if (caps->clk_ctrl)
+		writel(PMECC_CLK_133MHZ, pmecc->regs.base + ATMEL_PMECC_CLK);
+
 	/* Disable all interrupts before registering the PMECC handler. */
 	writel(0xffffffff, pmecc->regs.base + ATMEL_PMECC_IDR);
 	atmel_pmecc_reset(pmecc);

@@ -896,6 +901,7 @@ static struct atmel_pmecc_caps at91sam9g45_caps = {
 	.strengths = atmel_pmecc_strengths,
 	.nstrengths = 5,
 	.el_offset = 0x8c,
+	.clk_ctrl = true,
 };
 
 static struct atmel_pmecc_caps sama5d4_caps = {

2.39.5

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

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

From: Mike Christie <[email protected]>

[ Upstream commit 69cd720a8a5e9ef0f05ce5dd8c9ea6e018245c82 ]

As part of the normal initiator side scanning the guest's scsi layer will loop over all possible targets and send an inquiry. Since the max number of targets for virtio-scsi is 256, this can result in 255 error messages about targets not existing if you only have a single target. When there's more than 1 vhost-scsi device each with a single target, then you get N * 255 log messages.

It looks like the log message was added by accident in:

commit 3f8ca2e115e5 ("vhost/scsi: Extract common handling code from control queue handler")

when we added common helpers. Then in:

commit 09d7583294aa ("vhost/scsi: Use common handling code in request queue handler")

we converted the scsi command processing path to use the new helpers so we started to see the extra log messages during scanning.

The patches were just making some code common but added the vq_err call and I'm guessing the patch author forgot to enable the vq_err call (vq_err is implemented by pr_debug which defaults to off). So this patch removes the call since it's expected to hit this path during device discovery.

Message-Id: <[email protected]>

---
 drivers/vhost/scsi.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

index 87f2f56fd20a..de6f108a50a9 100644
@@ -913,10 +913,8 @@ vhost_scsi_get_req(struct vhost_virtqueue *vq, struct vhost_scsi_ctx *vc,
 			/* validated at handler entry */
 			vs_tpg = vhost_vq_get_backend(vq);
 			tpg = READ_ONCE(vs_tpg[*vc->target]);
-			if (unlikely(!tpg)) {
-				vq_err(vq, "Target 0x%x does not exist\n", *vc->target);
+			if (unlikely(!tpg))
 				goto out;
-			}
 		}
 
 		if (tpgp)

2.39.5

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

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

From: Paul Chaignon <[email protected]>

[ Upstream commit ead3d7b2b6afa5ee7958620c4329982a7d9c2b78 ]

flow_dissector_is_valid_access doesn't check that the context access is aligned. As a consequence, an unaligned access within one of the exposed field is considered valid and later rejected by flow_dissector_convert_ctx_access when we try to convert it.

The later rejection is problematic because it's reported as a verifier bug with a kernel warning and doesn't point to the right instruction in verifier logs.

---
 net/core/filter.c | 3 +++
 1 file changed, 3 insertions(+)

index 4c806ce62739..cd0c28e94979 100644
@@ -9270,6 +9270,9 @@ static bool flow_dissector_is_valid_access(int off, int size,
 	if (off < 0 || off >= sizeof(struct __sk_buff))
 		return false;
 
+	if (off % size != 0)
+		return false;
+
 	if (type == BPF_WRITE)
 		return false;
 

2.39.5

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

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

From: Ryan Lee <[email protected]>

[ Upstream commit 6c055e62560b958354625604293652753d82bcae ]

WB_HISTORY_SIZE was defined to be a value not a power of 2, despite a comment in the declaration of struct match_workbuf stating it is and a modular arithmetic usage in the inc_wb_pos macro assuming that it is. Bump WB_HISTORY_SIZE's value up to 32 and add a BUILD_BUG_ON_NOT_POWER_OF_2 line to ensure that any future changes to the value of WB_HISTORY_SIZE respect this requirement.

---
 security/apparmor/include/match.h | 3 ++-
 security/apparmor/match.c         | 1 +
 2 files changed, 3 insertions(+), 1 deletion(-)

index 884489590588..29306ec87fd1 100644
@@ -141,7 +141,8 @@ unsigned int aa_dfa_matchn_until(struct aa_dfa *dfa, unsigned int start,
 
 void aa_dfa_free_kref(struct kref *kref);
 
-#define WB_HISTORY_SIZE 24
+/* This needs to be a power of 2 */
+#define WB_HISTORY_SIZE 32
 struct match_workbuf {
 	unsigned int count;
 	unsigned int pos;

index 3e9e1eaf990e..0e683ee323e3 100644
@@ -672,6 +672,7 @@ unsigned int aa_dfa_matchn_until(struct aa_dfa *dfa, unsigned int start,
 
 #define inc_wb_pos(wb)						\
 do {								\
+	BUILD_BUG_ON_NOT_POWER_OF_2(WB_HISTORY_SIZE);			\
 	wb->pos = (wb->pos + 1) & (WB_HISTORY_SIZE - 1);		\
 	wb->len = (wb->len + 1) & (WB_HISTORY_SIZE - 1);		\
 } while (0)

2.39.5

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

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

From: Petr Pavlu <[email protected]>

[ Upstream commit bdc877ba6b7ff1b6d2ebeff11e63da4a50a54854 ]

The moduleparam code allows modules to provide their own definition of MODULE_PARAM_PREFIX, instead of using the default KBUILD_MODNAME ".".

Commit 730b69d22525 ("module: check kernel param length at compile time, not runtime") added a check to ensure the prefix doesn't exceed MODULE_NAME_LEN, as this is what param_sysfs_builtin() expects.

Later, commit 58f86cc89c33 ("VERIFY_OCTAL_PERMISSIONS: stricter checking for sysfs perms.") removed this check, but there is no indication this was intentional.

Since the check is still useful for param_sysfs_builtin() to function properly, reintroduce it in __module_param_call(), but in a modernized form using static_assert().

While here, clean up the __module_param_call() comments. In particular, remove the comment "Default value instead of permissions?", which comes from commit 9774a1f54f17 ("[PATCH] Compile-time check re world-writeable module params"). This comment was related to the test variable __param_perm_check_##name, which was removed in the previously mentioned commit 58f86cc89c33.

---
 include/linux/moduleparam.h | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

index 962cd41a2cb5..061e19c94a6b 100644
@@ -282,10 +282,9 @@ struct kparam_array
 #define __moduleparam_const const
 #endif
 
-/* This is the fundamental function for registering boot/module
-   parameters. */
+/* This is the fundamental function for registering boot/module parameters. */
 #define __module_param_call(prefix, name, ops, arg, perm, level, flags)	\
-	/* Default value instead of permissions? */			\
+	static_assert(sizeof(""prefix) - 1 <= MAX_PARAM_PREFIX_LEN);	\
 	static const char __param_str_##name[] = prefix #name;		\
 	static struct kernel_param __moduleparam_const __param_##name	\
 	__used __section("__param")					\

2.39.5

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

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

From: Uros Bizjak <[email protected]>

[ Upstream commit f8cd9193b62e92ad25def5370ca8ea2bc7585381 ]

The type of u argument of atomic_long_inc_below() should be long to avoid unwanted truncation to int.

The patch fixes the wrong argument type of an internal function to prevent unwanted argument truncation. It fixes an internal locking primitive; it should not have any direct effect on userspace.

Mark said

: AFAICT there's no problem in practice because atomic_long_inc_below() : is only used by inc_ucount(), and it looks like the value is : constrained between 0 and INT_MAX.
:
: In inc_ucount() the limit value is taken from
: user_namespace::ucount_max[], and AFAICT that's only written by : sysctls, to the table setup by setup_userns_sysctls(), where : UCOUNT_ENTRY() limits the value between 0 and INT_MAX.
:
: This is certainly a cleanup, but there might be no functional issue in : practice as above.

---
 kernel/ucount.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index ced99a4bb562..8afa2878422d 100644
@@ -212,7 +212,7 @@ void put_ucounts(struct ucounts *ucounts)
 	}
 }
 
-static inline bool atomic_long_inc_below(atomic_long_t *v, int u)
+static inline bool atomic_long_inc_below(atomic_long_t *v, long u)
 {
 	long c, old;
 	c = atomic_long_read(v);

2.39.5

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

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

From: Brian Masney <[email protected]>

[ Upstream commit cf6eb547a24af7ad7bbd2abe9c5327f956bbeae8 ]

When ds3231_clk_sqw_round_rate() is called with a requested rate higher than the highest supported rate, it currently returns 0, which disables the clock. According to the clk API, round_rate() should instead return the highest supported rate. Update the function to return the maximum supported rate in this case.

---
 drivers/rtc/rtc-ds1307.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index b7f8b3f9b059..73f2dd3af4d4 100644
@@ -1461,7 +1461,7 @@ static long ds3231_clk_sqw_round_rate(struct clk_hw *hw, unsigned long rate,
 			return ds3231_clk_sqw_rates[i];
 	}
 
-	return 0;
+	return ds3231_clk_sqw_rates[ARRAY_SIZE(ds3231_clk_sqw_rates) - 1];
 }
 
 static int ds3231_clk_sqw_set_rate(struct clk_hw *hw, unsigned long rate,

2.39.5

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

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

From: Brian Masney <[email protected]>

[ Upstream commit d0a518eb0a692a2ab8357e844970660c5ea37720 ]

When hym8563_clkout_round_rate() is called with a requested rate higher than the highest supported rate, it currently returns 0, which disables the clock. According to the clk API, round_rate() should instead return the highest supported rate. Update the function to return the maximum supported rate in this case.

---
 drivers/rtc/rtc-hym8563.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index cc710d682121..2f52aabd129a 100644
@@ -294,7 +294,7 @@ static long hym8563_clkout_round_rate(struct clk_hw *hw, unsigned long rate,
 		if (clkout_rates[i] <= rate)
 			return clkout_rates[i];
 
-	return 0;
+	return clkout_rates[0];
 }
 
 static int hym8563_clkout_set_rate(struct clk_hw *hw, unsigned long rate,

2.39.5

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

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

From: Brian Masney <[email protected]>

[ Upstream commit 437c59e4b222cd697b4cf95995d933e7d583c5f1 ]

When nct3018y_clkout_round_rate() is called with a requested rate higher than the highest supported rate, it currently returns 0, which disables the clock. According to the clk API, round_rate() should instead return the highest supported rate. Update the function to return the maximum supported rate in this case.

---
 drivers/rtc/rtc-nct3018y.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index 108eced8f003..43b01f3e640a 100644
@@ -342,7 +342,7 @@ static long nct3018y_clkout_round_rate(struct clk_hw *hw, unsigned long rate,
 		if (clkout_rates[i] <= rate)
 			return clkout_rates[i];
 
-	return 0;
+	return clkout_rates[0];
 }
 
 static int nct3018y_clkout_set_rate(struct clk_hw *hw, unsigned long rate,

2.39.5

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

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

From: Brian Masney <[email protected]>

[ Upstream commit 186ae1869880e58bb3f142d222abdb35ecb4df0f ]

When pcf85063_clkout_round_rate() is called with a requested rate higher than the highest supported rate, it currently returns 0, which disables the clock. According to the clk API, round_rate() should instead return the highest supported rate. Update the function to return the maximum supported rate in this case.

---
 drivers/rtc/rtc-pcf85063.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index 4a29b44e75e6..b095663d5ebc 100644
@@ -410,7 +410,7 @@ static long pcf85063_clkout_round_rate(struct clk_hw *hw, unsigned long rate,
 		if (clkout_rates[i] <= rate)
 			return clkout_rates[i];
 
-	return 0;
+	return clkout_rates[0];
 }
 
 static int pcf85063_clkout_set_rate(struct clk_hw *hw, unsigned long rate,

2.39.5

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

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

From: Brian Masney <[email protected]>

[ Upstream commit 906726a5efeefe0ef0103ccff5312a09080c04ae ]

When pcf8563_clkout_round_rate() is called with a requested rate higher than the highest supported rate, it currently returns 0, which disables the clock. According to the clk API, round_rate() should instead return the highest supported rate. Update the function to return the maximum supported rate in this case.

---
 drivers/rtc/rtc-pcf8563.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index 11fa9788558b..dd27acae137c 100644
@@ -386,7 +386,7 @@ static long pcf8563_clkout_round_rate(struct clk_hw *hw, unsigned long rate,
 		if (clkout_rates[i] <= rate)
 			return clkout_rates[i];
 
-	return 0;
+	return clkout_rates[0];
 }
 
 static int pcf8563_clkout_set_rate(struct clk_hw *hw, unsigned long rate,

2.39.5

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

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

From: Brian Masney <[email protected]>

[ Upstream commit b574acb3cf7591d2513a9f29f8c2021ad55fb881 ]

When rv3028_clkout_round_rate() is called with a requested rate higher than the highest supported rate, it currently returns 0, which disables the clock. According to the clk API, round_rate() should instead return the highest supported rate. Update the function to return the maximum supported rate in this case.

---
 drivers/rtc/rtc-rv3028.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index dd170e3efd83..436523605f8f 100644
@@ -738,7 +738,7 @@ static long rv3028_clkout_round_rate(struct clk_hw *hw, unsigned long rate,
 		if (clkout_rates[i] <= rate)
 			return clkout_rates[i];
 
-	return 0;
+	return clkout_rates[0];
 }
 
 static int rv3028_clkout_set_rate(struct clk_hw *hw, unsigned long rate,

2.39.5

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

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

From: Abinash Singh <[email protected]>

[ Upstream commit 154467f4ad033473e5c903a03e7b9bca7df9a0fa ]

KMSAN reported a use of uninitialized value in __is_extent_mergeable()
and __is_back_mergeable() via the read extent tree path.

The root cause is that get_read_extent_info() only initializes three fields (fofs, blk, len) of struct extent_info, leaving the remaining fields uninitialized. This leads to undefined behavior when those fields are accessed later, especially during extent merging.

Fix it by zero-initializing the extent_info struct before population.

---
 fs/f2fs/extent_cache.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index f13143efc4b1..a5c63c7da299 100644
@@ -440,7 +440,7 @@ void f2fs_init_read_extent_tree(struct inode *inode, struct page *ipage)
 	struct f2fs_extent *i_ext = &F2FS_INODE(ipage)->i_ext;
 	struct extent_tree *et;
 	struct extent_node *en;
-	struct extent_info ei;
+	struct extent_info ei = {0};
 
 	if (!__may_extent_tree(inode, EX_READ)) {
 		/* drop largest read extent */

2.39.5

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

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

From: Chao Yu <[email protected]>

[ Upstream commit 81b6ecca2f15922e8d653dc037df5871e754be6e ]

We should use "{usr,grp,prj}jquota=" to disable journaled quota, rather than using off{usr,grp,prj}jquota.

---
 Documentation/filesystems/f2fs.rst | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

index 17df9a02ccff..0625d5bce596 100644
@@ -230,9 +230,9 @@ usrjquota=<file>	 Appoint specified file and type during mount, so that quota
 grpjquota=<file>	 information can be properly updated during recovery flow,
 prjjquota=<file>	 <quota file>: must be in root directory;
 jqfmt=<quota type>	 <quota type>: [vfsold,vfsv0,vfsv1].
-offusrjquota		 Turn off user journalled quota.
-offgrpjquota		 Turn off group journalled quota.
-offprjjquota		 Turn off project journalled quota.
+usrjquota=		 Turn off user journalled quota.
+grpjquota=		 Turn off group journalled quota.
+prjjquota=		 Turn off project journalled quota.
 quota			 Enable plain user disk quota accounting.
 noquota			 Disable all plain disk quota option.
 alloc_mode=%s		 Adjust block allocation policy, which supports "reuse"

2.39.5

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

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

From: Chao Yu <[email protected]>

[ Upstream commit 7c30d79930132466f5be7d0b57add14d1a016bda ]

syzbot reported an UAF issue as below: [1] [2]

[1] https://syzkaller.appspot.com/text?tag=CrashReport&x=16594c60580000

==================================================================

BUG: KASAN: use-after-free in __list_del_entry_valid+0xa6/0x130 lib/list_debug.c:62
Read of size 8 at addr ffff888100567dc8 by task kworker/u4:0/8

CPU: 1 PID: 8 Comm: kworker/u4:0 Tainted: G        W          6.1.129-syzkaller-00017-g642656a36791 #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 02/12/2025
Workqueue: writeback wb_workfn (flush-7:0)
Call Trace:
 <TASK>
 __dump_stack lib/dump_stack.c:88 [inline]
 dump_stack_lvl+0x151/0x1b7 lib/dump_stack.c:106
 print_address_description mm/kasan/report.c:316 [inline]
 print_report+0x158/0x4e0 mm/kasan/report.c:427
 kasan_report+0x13c/0x170 mm/kasan/report.c:531
 __asan_report_load8_noabort+0x14/0x20 mm/kasan/report_generic.c:351
 __list_del_entry_valid+0xa6/0x130 lib/list_debug.c:62
 __list_del_entry include/linux/list.h:134 [inline]
 list_del_init include/linux/list.h:206 [inline]
 f2fs_inode_synced+0x100/0x2e0 fs/f2fs/super.c:1553
 f2fs_update_inode+0x72/0x1c40 fs/f2fs/inode.c:588
 f2fs_update_inode_page+0x135/0x170 fs/f2fs/inode.c:706
 f2fs_write_inode+0x416/0x790 fs/f2fs/inode.c:734
 write_inode fs/fs-writeback.c:1460 [inline]
 __writeback_single_inode+0x4cf/0xb80 fs/fs-writeback.c:1677
 writeback_sb_inodes+0xb32/0x1910 fs/fs-writeback.c:1903
 __writeback_inodes_wb+0x118/0x3f0 fs/fs-writeback.c:1974
 wb_writeback+0x3da/0xa00 fs/fs-writeback.c:2081
 wb_check_background_flush fs/fs-writeback.c:2151 [inline]
 wb_do_writeback fs/fs-writeback.c:2239 [inline]
 wb_workfn+0xbba/0x1030 fs/fs-writeback.c:2266
 process_one_work+0x73d/0xcb0 kernel/workqueue.c:2299
 worker_thread+0xa60/0x1260 kernel/workqueue.c:2446
 kthread+0x26d/0x300 kernel/kthread.c:386
 ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:295
 </TASK>

Allocated by task 298:
 kasan_save_stack mm/kasan/common.c:45 [inline]
 kasan_set_track+0x4b/0x70 mm/kasan/common.c:52
 kasan_save_alloc_info+0x1f/0x30 mm/kasan/generic.c:505
 __kasan_slab_alloc+0x6c/0x80 mm/kasan/common.c:333
 kasan_slab_alloc include/linux/kasan.h:202 [inline]
 slab_post_alloc_hook+0x53/0x2c0 mm/slab.h:768
 slab_alloc_node mm/slub.c:3421 [inline]
 slab_alloc mm/slub.c:3431 [inline]
 __kmem_cache_alloc_lru mm/slub.c:3438 [inline]
 kmem_cache_alloc_lru+0x102/0x270 mm/slub.c:3454
 alloc_inode_sb include/linux/fs.h:3255 [inline]
 f2fs_alloc_inode+0x2d/0x350 fs/f2fs/super.c:1437
 alloc_inode fs/inode.c:261 [inline]
 iget_locked+0x18c/0x7e0 fs/inode.c:1373
 f2fs_iget+0x55/0x4ca0 fs/f2fs/inode.c:486
 f2fs_lookup+0x3c1/0xb50 fs/f2fs/namei.c:484
 __lookup_slow+0x2b9/0x3e0 fs/namei.c:1689
 lookup_slow+0x5a/0x80 fs/namei.c:1706
 walk_component+0x2e7/0x410 fs/namei.c:1997
 lookup_last fs/namei.c:2454 [inline]
 path_lookupat+0x16d/0x450 fs/namei.c:2478
 filename_lookup+0x251/0x600 fs/namei.c:2507
 vfs_statx+0x107/0x4b0 fs/stat.c:229
 vfs_fstatat fs/stat.c:267 [inline]
 vfs_lstat include/linux/fs.h:3434 [inline]
 __do_sys_newlstat fs/stat.c:423 [inline]
 __se_sys_newlstat+0xda/0x7c0 fs/stat.c:417
 __x64_sys_newlstat+0x5b/0x70 fs/stat.c:417
 x64_sys_call+0x52/0x9a0 arch/x86/include/generated/asm/syscalls_64.h:7
 do_syscall_x64 arch/x86/entry/common.c:51 [inline]
 do_syscall_64+0x3b/0x80 arch/x86/entry/common.c:81
 entry_SYSCALL_64_after_hwframe+0x68/0xd2

Freed by task 0:
 kasan_save_stack mm/kasan/common.c:45 [inline]
 kasan_set_track+0x4b/0x70 mm/kasan/common.c:52
 kasan_save_free_info+0x2b/0x40 mm/kasan/generic.c:516
 ____kasan_slab_free+0x131/0x180 mm/kasan/common.c:241
 __kasan_slab_free+0x11/0x20 mm/kasan/common.c:249
 kasan_slab_free include/linux/kasan.h:178 [inline]
 slab_free_hook mm/slub.c:1745 [inline]
 slab_free_freelist_hook mm/slub.c:1771 [inline]
 slab_free mm/slub.c:3686 [inline]
 kmem_cache_free+0x291/0x560 mm/slub.c:3711
 f2fs_free_inode+0x24/0x30 fs/f2fs/super.c:1584
 i_callback+0x4b/0x70 fs/inode.c:250
 rcu_do_batch+0x552/0xbe0 kernel/rcu/tree.c:2297
 rcu_core+0x502/0xf40 kernel/rcu/tree.c:2557
 rcu_core_si+0x9/0x10 kernel/rcu/tree.c:2574
 handle_softirqs+0x1db/0x650 kernel/softirq.c:624
 __do_softirq kernel/softirq.c:662 [inline]
 invoke_softirq kernel/softirq.c:479 [inline]
 __irq_exit_rcu+0x52/0xf0 kernel/softirq.c:711
 irq_exit_rcu+0x9/0x10 kernel/softirq.c:723
 instr_sysvec_apic_timer_interrupt arch/x86/kernel/apic/apic.c:1118 [inline]
 sysvec_apic_timer_interrupt+0xa9/0xc0 arch/x86/kernel/apic/apic.c:1118
 asm_sysvec_apic_timer_interrupt+0x1b/0x20 arch/x86/include/asm/idtentry.h:691

Last potentially related work creation:
 kasan_save_stack+0x3b/0x60 mm/kasan/common.c:45
 __kasan_record_aux_stack+0xb4/0xc0 mm/kasan/generic.c:486
 kasan_record_aux_stack_noalloc+0xb/0x10 mm/kasan/generic.c:496
 __call_rcu_common kernel/rcu/tree.c:2807 [inline]
 call_rcu+0xdc/0x10f0 kernel/rcu/tree.c:2926
 destroy_inode fs/inode.c:316 [inline]
 evict+0x87d/0x930 fs/inode.c:720
 iput_final fs/inode.c:1834 [inline]
 iput+0x616/0x690 fs/inode.c:1860
 do_unlinkat+0x4e1/0x920 fs/namei.c:4396
 __do_sys_unlink fs/namei.c:4437 [inline]
 __se_sys_unlink fs/namei.c:4435 [inline]
 __x64_sys_unlink+0x49/0x50 fs/namei.c:4435
 x64_sys_call+0x289/0x9a0 arch/x86/include/generated/asm/syscalls_64.h:88
 do_syscall_x64 arch/x86/entry/common.c:51 [inline]
 do_syscall_64+0x3b/0x80 arch/x86/entry/common.c:81
 entry_SYSCALL_64_after_hwframe+0x68/0xd2

The buggy address belongs to the object at ffff888100567a10
 which belongs to the cache f2fs_inode_cache of size 1360

The buggy address is located 952 bytes inside of
1360-byte region [ffff888100567a10, ffff888100567f60)

The buggy address belongs to the physical page:
page:ffffea0004015800 refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x100560
head:ffffea0004015800 order:3 compound_mapcount:0 compound_pincount:0
flags: 0x4000000000010200(slab|head|zone=1)
raw: 4000000000010200 0000000000000000 dead000000000122 ffff8881002c4d80
raw: 0000000000000000 0000000080160016 00000001ffffffff 0000000000000000
page dumped because: kasan: bad access detected
page_owner tracks the page as allocated
page last allocated via order 3, migratetype Reclaimable, gfp_mask 0xd2050(__GFP_IO|__GFP_NOWARN|__GFP_NORETRY|__GFP_COMP|__GFP_NOMEMALLOC|__GFP_RECLAIMABLE), pid 298, tgid 298 (syz-executor330), ts 26489303743, free_ts 0
 set_page_owner include/linux/page_owner.h:33 [inline]
 post_alloc_hook+0x213/0x220 mm/page_alloc.c:2637
 prep_new_page+0x1b/0x110 mm/page_alloc.c:2644
 get_page_from_freelist+0x3a98/0x3b10 mm/page_alloc.c:4539
 __alloc_pages+0x234/0x610 mm/page_alloc.c:5837
 alloc_slab_page+0x6c/0xf0 include/linux/gfp.h:-1
 allocate_slab mm/slub.c:1962 [inline]
 new_slab+0x90/0x3e0 mm/slub.c:2015
 ___slab_alloc+0x6f9/0xb80 mm/slub.c:3203
 __slab_alloc+0x5d/0xa0 mm/slub.c:3302
 slab_alloc_node mm/slub.c:3387 [inline]
 slab_alloc mm/slub.c:3431 [inline]
 __kmem_cache_alloc_lru mm/slub.c:3438 [inline]
 kmem_cache_alloc_lru+0x149/0x270 mm/slub.c:3454
 alloc_inode_sb include/linux/fs.h:3255 [inline]
 f2fs_alloc_inode+0x2d/0x350 fs/f2fs/super.c:1437
 alloc_inode fs/inode.c:261 [inline]
 iget_locked+0x18c/0x7e0 fs/inode.c:1373
 f2fs_iget+0x55/0x4ca0 fs/f2fs/inode.c:486
 f2fs_fill_super+0x5360/0x6dc0 fs/f2fs/super.c:4488
 mount_bdev+0x282/0x3b0 fs/super.c:1445
 f2fs_mount+0x34/0x40 fs/f2fs/super.c:4743
 legacy_get_tree+0xf1/0x190 fs/fs_context.c:632

page_owner free stack trace missing

Memory state around the buggy address:
 ffff888100567c80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
 ffff888100567d00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
>ffff888100567d80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
                                              ^
 ffff888100567e00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
 ffff888100567e80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
==================================================================

[2] https://syzkaller.appspot.com/text?tag=CrashLog&x=13654c60580000

[   24.675720][   T28] audit: type=1400 audit(1745327318.732:72): avc:  denied  { write } for  pid=298 comm="syz-executor399" name="/" dev="loop0" ino=3 scontext=root:sysadm_r:sysadm_t tcontext=system_u:object_r:unlabeled_t tclass=dir permissive=1
[   24.705426][  T296] ------------[ cut here ]------------
[   24.706608][   T28] audit: type=1400 audit(1745327318.732:73): avc:  denied  { remove_name } for  pid=298 comm="syz-executor399" name="file0" dev="loop0" ino=4 scontext=root:sysadm_r:sysadm_t tcontext=system_u:object_r:unlabeled_t tclass=dir permissive=1
[   24.711550][  T296] WARNING: CPU: 0 PID: 296 at fs/f2fs/inode.c:847 f2fs_evict_inode+0x1262/0x1540
[   24.734141][   T28] audit: type=1400 audit(1745327318.732:74): avc:  denied  { rename } for  pid=298 comm="syz-executor399" name="file0" dev="loop0" ino=4 scontext=root:sysadm_r:sysadm_t tcontext=system_u:object_r:unlabeled_t tclass=dir permissive=1
[   24.742969][  T296] Modules linked in:
[   24.765201][   T28] audit: type=1400 audit(1745327318.732:75): avc:  denied  { add_name } for  pid=298 comm="syz-executor399" name="bus" scontext=root:sysadm_r:sysadm_t tcontext=system_u:object_r:unlabeled_t tclass=dir permissive=1
[   24.768847][  T296] CPU: 0 PID: 296 Comm: syz-executor399 Not tainted 6.1.129-syzkaller-00017-g642656a36791 #0
[   24.799506][  T296] Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 02/12/2025
[   24.809401][  T296] RIP: 0010:f2fs_evict_inode+0x1262/0x1540
[   24.815018][  T296] Code: 34 70 4a ff eb 0d e8 2d 70 4a ff 4d 89 e5 4c 8b 64 24 18 48 8b 5c 24 28 4c 89 e7 e8 78 38 03 00 e9 84 fc ff ff e8 0e 70 4a ff <0f> 0b 4c 89 f7 be 08 00 00 00 e8 7f 21 92 ff f0 41 80 0e 04 e9 61
[   24.834584][  T296] RSP: 0018:ffffc90000db7a40 EFLAGS: 00010293
[   24.840465][  T296] RAX: ffffffff822aca42 RBX: 0000000000000002 RCX: ffff888110948000
[   24.848291][  T296] RDX: 0000000000000000 RSI: 0000000000000002 RDI: 0000000000000000
[   24.856064][  T296] RBP: ffffc90000db7bb0 R08: ffffffff822ac6a8 R09: ffffed10200b005d
[   24.864073][  T296] R10: 0000000000000000 R11: dffffc0000000001 R12: ffff888100580000
[   24.871812][  T296] R13: dffffc0000000000 R14: ffff88810fef4078 R15: 1ffff920001b6f5c

The root cause is w/ a fuzzed image, f2fs may missed to clear FI_DIRTY_INODE flag for target inode, after f2fs_evict_inode(), the inode is still linked in sbi->inode_list[DIRTY_META] global list, once it triggers checkpoint, f2fs_sync_inode_meta() may access the released inode.

In f2fs_evict_inode(), let's always call f2fs_inode_synced() to clear FI_DIRTY_INODE flag and drop inode from global dirty list to avoid this UAF issue.

---
 fs/f2fs/inode.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

index b8296b0414fc..06f82efe8770 100644
@@ -847,8 +847,12 @@ void f2fs_evict_inode(struct inode *inode)
 	if (likely(!f2fs_cp_error(sbi) &&
 				!is_sbi_flag_set(sbi, SBI_CP_DISABLED)))
 		f2fs_bug_on(sbi, is_inode_flag_set(inode, FI_DIRTY_INODE));
-	else
-		f2fs_inode_synced(inode);
+
+	/*
+	 * anyway, it needs to remove the inode from sbi->inode_list[DIRTY_META]
+	 * list to avoid UAF in f2fs_sync_inode_meta() during checkpoint.
+	 */
+	f2fs_inode_synced(inode);
 
 	/* for the case f2fs_new_inode() was failed, .i_ino is zero, skip it */
 	if (inode->i_ino)

2.39.5

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

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

From: Chao Yu <[email protected]>

[ Upstream commit a509a55f8eecc8970b3980c6f06886bbff0e2f68 ]

As syzbot [1] reported as below:

R10: 0000000000000100 R11: 0000000000000206 R12: 00007ffe17473450
R13: 00007f28b1c10854 R14: 000000000000dae5 R15: 00007ffe17474520

 </TASK>
---[ end trace 0000000000000000 ]---
==================================================================
BUG: KASAN: use-after-free in __list_del_entry_valid+0xa6/0x130 lib/list_debug.c:62
Read of size 8 at addr ffff88812d962278 by task syz-executor/564

CPU: 1 PID: 564 Comm: syz-executor Tainted: G        W          6.1.129-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 02/12/2025
Call Trace:
 <TASK>
 __dump_stack+0x21/0x24 lib/dump_stack.c:88
 dump_stack_lvl+0xee/0x158 lib/dump_stack.c:106
 print_address_description+0x71/0x210 mm/kasan/report.c:316
 print_report+0x4a/0x60 mm/kasan/report.c:427
 kasan_report+0x122/0x150 mm/kasan/report.c:531
 __asan_report_load8_noabort+0x14/0x20 mm/kasan/report_generic.c:351
 __list_del_entry_valid+0xa6/0x130 lib/list_debug.c:62
 __list_del_entry include/linux/list.h:134 [inline]
 list_del_init include/linux/list.h:206 [inline]
 f2fs_inode_synced+0xf7/0x2e0 fs/f2fs/super.c:1531
 f2fs_update_inode+0x74/0x1c40 fs/f2fs/inode.c:585
 f2fs_update_inode_page+0x137/0x170 fs/f2fs/inode.c:703
 f2fs_write_inode+0x4ec/0x770 fs/f2fs/inode.c:731
 write_inode fs/fs-writeback.c:1460 [inline]
 __writeback_single_inode+0x4a0/0xab0 fs/fs-writeback.c:1677
 writeback_single_inode+0x221/0x8b0 fs/fs-writeback.c:1733
 sync_inode_metadata+0xb6/0x110 fs/fs-writeback.c:2789
 f2fs_sync_inode_meta+0x16d/0x2a0 fs/f2fs/checkpoint.c:1159
 block_operations fs/f2fs/checkpoint.c:1269 [inline]
 f2fs_write_checkpoint+0xca3/0x2100 fs/f2fs/checkpoint.c:1658
 kill_f2fs_super+0x231/0x390 fs/f2fs/super.c:4668
 deactivate_locked_super+0x98/0x100 fs/super.c:332
 deactivate_super+0xaf/0xe0 fs/super.c:363
 cleanup_mnt+0x45f/0x4e0 fs/namespace.c:1186
 __cleanup_mnt+0x19/0x20 fs/namespace.c:1193
 task_work_run+0x1c6/0x230 kernel/task_work.c:203
 exit_task_work include/linux/task_work.h:39 [inline]
 do_exit+0x9fb/0x2410 kernel/exit.c:871
 do_group_exit+0x210/0x2d0 kernel/exit.c:1021
 __do_sys_exit_group kernel/exit.c:1032 [inline]
 __se_sys_exit_group kernel/exit.c:1030 [inline]
 __x64_sys_exit_group+0x3f/0x40 kernel/exit.c:1030
 x64_sys_call+0x7b4/0x9a0 arch/x86/include/generated/asm/syscalls_64.h:232
 do_syscall_x64 arch/x86/entry/common.c:51 [inline]
 do_syscall_64+0x4c/0xa0 arch/x86/entry/common.c:81
 entry_SYSCALL_64_after_hwframe+0x68/0xd2
RIP: 0033:0x7f28b1b8e169
Code: Unable to access opcode bytes at 0x7f28b1b8e13f.
RSP: 002b:00007ffe174710a8 EFLAGS: 00000246 ORIG_RAX: 00000000000000e7
RAX: ffffffffffffffda RBX: 00007f28b1c10879 RCX: 00007f28b1b8e169
RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000001
RBP: 0000000000000002 R08: 00007ffe1746ee47 R09: 00007ffe17472360
R10: 0000000000000009 R11: 0000000000000246 R12: 00007ffe17472360
R13: 00007f28b1c10854 R14: 000000000000dae5 R15: 00007ffe17474520
 </TASK>

Allocated by task 569:
 kasan_save_stack mm/kasan/common.c:45 [inline]
 kasan_set_track+0x4b/0x70 mm/kasan/common.c:52
 kasan_save_alloc_info+0x25/0x30 mm/kasan/generic.c:505
 __kasan_slab_alloc+0x72/0x80 mm/kasan/common.c:328
 kasan_slab_alloc include/linux/kasan.h:201 [inline]
 slab_post_alloc_hook+0x4f/0x2c0 mm/slab.h:737
 slab_alloc_node mm/slub.c:3398 [inline]
 slab_alloc mm/slub.c:3406 [inline]
 __kmem_cache_alloc_lru mm/slub.c:3413 [inline]
 kmem_cache_alloc_lru+0x104/0x220 mm/slub.c:3429
 alloc_inode_sb include/linux/fs.h:3245 [inline]
 f2fs_alloc_inode+0x2d/0x340 fs/f2fs/super.c:1419
 alloc_inode fs/inode.c:261 [inline]
 iget_locked+0x186/0x880 fs/inode.c:1373
 f2fs_iget+0x55/0x4c60 fs/f2fs/inode.c:483
 f2fs_lookup+0x366/0xab0 fs/f2fs/namei.c:487
 __lookup_slow+0x2a3/0x3d0 fs/namei.c:1690
 lookup_slow+0x57/0x70 fs/namei.c:1707
 walk_component+0x2e6/0x410 fs/namei.c:1998
 lookup_last fs/namei.c:2455 [inline]
 path_lookupat+0x180/0x490 fs/namei.c:2479
 filename_lookup+0x1f0/0x500 fs/namei.c:2508
 vfs_statx+0x10b/0x660 fs/stat.c:229
 vfs_fstatat fs/stat.c:267 [inline]
 vfs_lstat include/linux/fs.h:3424 [inline]
 __do_sys_newlstat fs/stat.c:423 [inline]
 __se_sys_newlstat+0xd5/0x350 fs/stat.c:417
 __x64_sys_newlstat+0x5b/0x70 fs/stat.c:417
 x64_sys_call+0x393/0x9a0 arch/x86/include/generated/asm/syscalls_64.h:7
 do_syscall_x64 arch/x86/entry/common.c:51 [inline]
 do_syscall_64+0x4c/0xa0 arch/x86/entry/common.c:81
 entry_SYSCALL_64_after_hwframe+0x68/0xd2

Freed by task 13:
 kasan_save_stack mm/kasan/common.c:45 [inline]
 kasan_set_track+0x4b/0x70 mm/kasan/common.c:52
 kasan_save_free_info+0x31/0x50 mm/kasan/generic.c:516
 ____kasan_slab_free+0x132/0x180 mm/kasan/common.c:236
 __kasan_slab_free+0x11/0x20 mm/kasan/common.c:244
 kasan_slab_free include/linux/kasan.h:177 [inline]
 slab_free_hook mm/slub.c:1724 [inline]
 slab_free_freelist_hook+0xc2/0x190 mm/slub.c:1750
 slab_free mm/slub.c:3661 [inline]
 kmem_cache_free+0x12d/0x2a0 mm/slub.c:3683
 f2fs_free_inode+0x24/0x30 fs/f2fs/super.c:1562
 i_callback+0x4c/0x70 fs/inode.c:250
 rcu_do_batch+0x503/0xb80 kernel/rcu/tree.c:2297
 rcu_core+0x5a2/0xe70 kernel/rcu/tree.c:2557
 rcu_core_si+0x9/0x10 kernel/rcu/tree.c:2574
 handle_softirqs+0x178/0x500 kernel/softirq.c:578
 run_ksoftirqd+0x28/0x30 kernel/softirq.c:945
 smpboot_thread_fn+0x45a/0x8c0 kernel/smpboot.c:164
 kthread+0x270/0x310 kernel/kthread.c:376
 ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:295

Last potentially related work creation:
 kasan_save_stack+0x3a/0x60 mm/kasan/common.c:45
 __kasan_record_aux_stack+0xb6/0xc0 mm/kasan/generic.c:486
 kasan_record_aux_stack_noalloc+0xb/0x10 mm/kasan/generic.c:496
 call_rcu+0xd4/0xf70 kernel/rcu/tree.c:2845
 destroy_inode fs/inode.c:316 [inline]
 evict+0x7da/0x870 fs/inode.c:720
 iput_final fs/inode.c:1834 [inline]
 iput+0x62b/0x830 fs/inode.c:1860
 do_unlinkat+0x356/0x540 fs/namei.c:4397
 __do_sys_unlink fs/namei.c:4438 [inline]
 __se_sys_unlink fs/namei.c:4436 [inline]
 __x64_sys_unlink+0x49/0x50 fs/namei.c:4436
 x64_sys_call+0x958/0x9a0 arch/x86/include/generated/asm/syscalls_64.h:88
 do_syscall_x64 arch/x86/entry/common.c:51 [inline]
 do_syscall_64+0x4c/0xa0 arch/x86/entry/common.c:81
 entry_SYSCALL_64_after_hwframe+0x68/0xd2

The buggy address belongs to the object at ffff88812d961f20
 which belongs to the cache f2fs_inode_cache of size 1200

The buggy address is located 856 bytes inside of
1200-byte region [ffff88812d961f20, ffff88812d9623d0)

The buggy address belongs to the physical page:
page:ffffea0004b65800 refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x12d960
head:ffffea0004b65800 order:2 compound_mapcount:0 compound_pincount:0
flags: 0x4000000000010200(slab|head|zone=1)
raw: 4000000000010200 0000000000000000 dead000000000122 ffff88810a94c500
raw: 0000000000000000 00000000800c000c 00000001ffffffff 0000000000000000
page dumped because: kasan: bad access detected
page_owner tracks the page as allocated
page last allocated via order 2, migratetype Reclaimable, gfp_mask 0x1d2050(__GFP_IO|__GFP_NOWARN|__GFP_NORETRY|__GFP_COMP|__GFP_NOMEMALLOC|__GFP_HARDWALL|__GFP_RECLAIMABLE), pid 569, tgid 568 (syz.2.16), ts 55943246141, free_ts 0
 set_page_owner include/linux/page_owner.h:31 [inline]
 post_alloc_hook+0x1d0/0x1f0 mm/page_alloc.c:2532
 prep_new_page mm/page_alloc.c:2539 [inline]
 get_page_from_freelist+0x2e63/0x2ef0 mm/page_alloc.c:4328
 __alloc_pages+0x235/0x4b0 mm/page_alloc.c:5605
 alloc_slab_page include/linux/gfp.h:-1 [inline]
 allocate_slab mm/slub.c:1939 [inline]
 new_slab+0xec/0x4b0 mm/slub.c:1992
 ___slab_alloc+0x6f6/0xb50 mm/slub.c:3180
 __slab_alloc+0x5e/0xa0 mm/slub.c:3279
 slab_alloc_node mm/slub.c:3364 [inline]
 slab_alloc mm/slub.c:3406 [inline]
 __kmem_cache_alloc_lru mm/slub.c:3413 [inline]
 kmem_cache_alloc_lru+0x13f/0x220 mm/slub.c:3429
 alloc_inode_sb include/linux/fs.h:3245 [inline]
 f2fs_alloc_inode+0x2d/0x340 fs/f2fs/super.c:1419
 alloc_inode fs/inode.c:261 [inline]
 iget_locked+0x186/0x880 fs/inode.c:1373
 f2fs_iget+0x55/0x4c60 fs/f2fs/inode.c:483
 f2fs_fill_super+0x3ad7/0x6bb0 fs/f2fs/super.c:4293
 mount_bdev+0x2ae/0x3e0 fs/super.c:1443
 f2fs_mount+0x34/0x40 fs/f2fs/super.c:4642
 legacy_get_tree+0xea/0x190 fs/fs_context.c:632
 vfs_get_tree+0x89/0x260 fs/super.c:1573
 do_new_mount+0x25a/0xa20 fs/namespace.c:3056

page_owner free stack trace missing

Memory state around the buggy address:
 ffff88812d962100: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
 ffff88812d962180: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
>ffff88812d962200: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
                                                                ^
 ffff88812d962280: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
 ffff88812d962300: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
==================================================================

[1] https://syzkaller.appspot.com/x/report.txt?x=13448368580000

This bug can be reproduced w/ the reproducer [2], once we enable CONFIG_F2FS_CHECK_FS config, the reproducer will trigger panic as below, so the direct reason of this bug is the same as the one below patch [3] fixed.

kernel BUG at fs/f2fs/inode.c:857!

RIP: 0010:f2fs_evict_inode+0x1204/0x1a20
Call Trace:
 <TASK>
 evict+0x32a/0x7a0
 do_unlinkat+0x37b/0x5b0
 __x64_sys_unlink+0xad/0x100
 do_syscall_64+0x5a/0xb0
 entry_SYSCALL_64_after_hwframe+0x6e/0xd8
RIP: 0010:f2fs_evict_inode+0x1204/0x1a20

[2] https://syzkaller.appspot.com/x/repro.c?x=17495ccc580000
[3] https://lore.kernel.org/linux-f2fs-devel/[email protected]

Tracepoints before panic:

f2fs_unlink_enter: dev = (7,0), dir ino = 3, i_size = 4096, i_blocks = 8, name = file1
f2fs_unlink_exit: dev = (7,0), ino = 7, ret = 0
f2fs_evict_inode: dev = (7,0), ino = 7, pino = 3, i_mode = 0x81ed, i_size = 10, i_nlink = 0, i_blocks = 0, i_advise = 0x0
f2fs_truncate_node: dev = (7,0), ino = 7, nid = 8, block_address = 0x3c05

f2fs_unlink_enter: dev = (7,0), dir ino = 3, i_size = 4096, i_blocks = 8, name = file3
f2fs_unlink_exit: dev = (7,0), ino = 8, ret = 0
f2fs_evict_inode: dev = (7,0), ino = 8, pino = 3, i_mode = 0x81ed, i_size = 9000, i_nlink = 0, i_blocks = 24, i_advise = 0x4
f2fs_truncate: dev = (7,0), ino = 8, pino = 3, i_mode = 0x81ed, i_size = 0, i_nlink = 0, i_blocks = 24, i_advise = 0x4 f2fs_truncate_blocks_enter: dev = (7,0), ino = 8, i_size = 0, i_blocks = 24, start file offset = 0
f2fs_truncate_blocks_exit: dev = (7,0), ino = 8, ret = -2

The root cause is: in the fuzzed image, dnode #8 belongs to inode #7, after inode #7 eviction, dnode #8 was dropped.

However there is dirent that has ino #8, so, once we unlink file3, in f2fs_evict_inode(), both f2fs_truncate() and f2fs_update_inode_page() will fail due to we can not load node #8, result in we missed to call f2fs_inode_synced() to clear inode dirty status.

Let's fix this by calling f2fs_inode_synced() in error path of f2fs_evict_inode().

PS: As I verified, the reproducer [2] can trigger this bug in v6.1.129, but it failed in v6.16-rc4, this is because the testcase will stop due to other corruption has been detected by f2fs:

F2FS-fs (loop0): inconsistent node block, node_type:2, nid:8, node_footer[nid:8,ino:8,ofs:0,cpver:5013063228981249506,blkaddr:15366] F2FS-fs (loop0): f2fs_lookup: inode (ino=9) has zero i_nlink

---
 fs/f2fs/inode.c | 13 +++++++++++++
 1 file changed, 13 insertions(+)

index 06f82efe8770..c02b5ea43f07 100644
@@ -831,6 +831,19 @@ void f2fs_evict_inode(struct inode *inode)
 		f2fs_update_inode_page(inode);
 		if (dquot_initialize_needed(inode))
 			set_sbi_flag(sbi, SBI_QUOTA_NEED_REPAIR);
+
+		/*
+		 * If both f2fs_truncate() and f2fs_update_inode_page() failed
+		 * due to fuzzed corrupted inode, call f2fs_inode_synced() to
+		 * avoid triggering later f2fs_bug_on().
+		 */
+		if (is_inode_flag_set(inode, FI_DIRTY_INODE)) {
+			f2fs_warn(sbi,
+				"f2fs_evict_inode: inode is dirty, ino:%lu",
+				inode->i_ino);
+			f2fs_inode_synced(inode);
+			set_sbi_flag(sbi, SBI_NEED_FSCK);
+		}
 	}
 	if (!is_sbi_flag_set(sbi, SBI_IS_FREEZING))
 		sb_end_intwrite(inode->i_sb);

2.39.5

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

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

From: Chao Yu <[email protected]>

[ Upstream commit 5661998536af52848cc4d52a377e90368196edea ]

- touch /mnt/f2fs/012345678901234567890123456789012345678901234567890123
- truncate -s $((1024*1024*1024)) \
/mnt/f2fs/012345678901234567890123456789012345678901234567890123
- touch /mnt/f2fs/file
- truncate -s $((1024*1024*1024)) /mnt/f2fs/file
- mkfs.f2fs /mnt/f2fs/012345678901234567890123456789012345678901234567890123 \
-c /mnt/f2fs/file
- mount /mnt/f2fs/012345678901234567890123456789012345678901234567890123 \
/mnt/f2fs/loop

[16937.192225] F2FS-fs (loop0): Mount Device [ 0]: /mnt/f2fs/012345678901234567890123456789012345678901234567890123\xff\x01,      511,        0 -    3ffff
[16937.192268] F2FS-fs (loop0): Failed to find devices

If device path length equals to MAX_PATH_LEN, sbi->devs.path[] may not end up w/ null character due to path array is fully filled, So accidently, fields locate after path[] may be treated as part of device path, result in parsing wrong device path.

struct f2fs_dev_info {
...

	char path[MAX_PATH_LEN];

...
};

Let's add one byte space for sbi->devs.path[] to store null character of device path string.

---
 fs/f2fs/f2fs.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index ef9149bd398a..1ad9669666e8 100644
@@ -1226,7 +1226,7 @@ struct f2fs_bio_info {
 #define RDEV(i)				(raw_super->devs[i])
 struct f2fs_dev_info {
 	struct block_device *bdev;
-	char path[MAX_PATH_LEN];
+	char path[MAX_PATH_LEN + 1];
 	unsigned int total_segments;
 	block_t start_blk;
 	block_t end_blk;

2.39.5

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

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

From: Jan Prusakowski <[email protected]>

[ Upstream commit 08a7efc5b02a0620ae16aa9584060e980a69cb55 ]

When testing F2FS with xfstests using UFS backed virtual disks the kernel complains sometimes that f2fs_release_decomp_mem() calls vm_unmap_ram() from an invalid context. Example trace from f2fs/007 test:

f2fs/007 5s ... [12:59:38][ 8.902525] run fstests f2fs/007

[   11.468026] BUG: sleeping function called from invalid context at mm/vmalloc.c:2978
[   11.471849] in_atomic(): 1, irqs_disabled(): 1, non_block: 0, pid: 68, name: irq/22-ufshcd
[   11.475357] preempt_count: 1, expected: 0
[   11.476970] RCU nest depth: 0, expected: 0
[   11.478531] CPU: 0 UID: 0 PID: 68 Comm: irq/22-ufshcd Tainted: G        W           6.16.0-rc5-xfstests-ufs-g40f92e79b0aa #9 PREEMPT(none)
[   11.478535] Tainted: [W]=WARN
[   11.478536] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.3-debian-1.16.3-2 04/01/2014
[   11.478537] Call Trace:
[   11.478543]  <TASK>
[   11.478545]  dump_stack_lvl+0x4e/0x70
[   11.478554]  __might_resched.cold+0xaf/0xbe
[   11.478557]  vm_unmap_ram+0x21/0xb0
[   11.478560]  f2fs_release_decomp_mem+0x59/0x80
[   11.478563]  f2fs_free_dic+0x18/0x1a0
[   11.478565]  f2fs_finish_read_bio+0xd7/0x290
[   11.478570]  blk_update_request+0xec/0x3b0
[   11.478574]  ? sbitmap_queue_clear+0x3b/0x60
[   11.478576]  scsi_end_request+0x27/0x1a0
[   11.478582]  scsi_io_completion+0x40/0x300
[   11.478583]  ufshcd_mcq_poll_cqe_lock+0xa3/0xe0
[   11.478588]  ufshcd_sl_intr+0x194/0x1f0
[   11.478592]  ufshcd_threaded_intr+0x68/0xb0
[   11.478594]  ? __pfx_irq_thread_fn+0x10/0x10
[   11.478599]  irq_thread_fn+0x20/0x60
[   11.478602]  ? __pfx_irq_thread_fn+0x10/0x10
[   11.478603]  irq_thread+0xb9/0x180
[   11.478605]  ? __pfx_irq_thread_dtor+0x10/0x10
[   11.478607]  ? __pfx_irq_thread+0x10/0x10
[   11.478609]  kthread+0x10a/0x230
[   11.478614]  ? __pfx_kthread+0x10/0x10
[   11.478615]  ret_from_fork+0x7e/0xd0
[   11.478619]  ? __pfx_kthread+0x10/0x10
[   11.478621]  ret_from_fork_asm+0x1a/0x30
[   11.478623]  </TASK>

This patch modifies in_task() check inside f2fs_read_end_io() to also check if interrupts are disabled. This ensures that pages are unmapped asynchronously in an interrupt handler.

---
 fs/f2fs/data.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index 7b65766d365f..dc8f283f210c 100644
@@ -273,7 +273,7 @@ static void f2fs_read_end_io(struct bio *bio)
 {
 	struct f2fs_sb_info *sbi = F2FS_P_SB(bio_first_page_all(bio));
 	struct bio_post_read_ctx *ctx;
-	bool intask = in_task();
+	bool intask = in_task() && !irqs_disabled();
 
 	iostat_update_and_unbind_ctx(bio, 0);
 	ctx = bio->bi_private;

2.39.5

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

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

From: Chao Yu <[email protected]>

[ Upstream commit 6840faddb65683b4e7bd8196f177b038a1e19faf ]

Commit 1acd73edbbfe ("f2fs: fix to account dirty data in __get_secs_required()") missed to calculate upper_p w/ data_secs, fix it.

---
 fs/f2fs/segment.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index 5ef5a88f47a0..3f1d6cdd4ae0 100644
@@ -635,7 +635,7 @@ static inline void __get_secs_required(struct f2fs_sb_info *sbi,
 	if (lower_p)
 		*lower_p = node_secs + dent_secs + data_secs;
 	if (upper_p)
-		*upper_p = node_secs + dent_secs +
+		*upper_p = node_secs + dent_secs + data_secs +
 			(node_blocks ? 1 : 0) + (dent_blocks ? 1 : 0) +
 			(data_blocks ? 1 : 0);
 	if (curseg_p)

2.39.5

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

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

From: Chao Yu <[email protected]>

[ Upstream commit e194e140ab7de2ce2782e64b9e086a43ca6ff4f2 ]

In lfs mode, dirty data needs OPU, we'd better calculate lower_p and upper_p w/ them during has_not_enough_free_secs(), otherwise we may encounter out-of-space issue due to we missed to reclaim enough free section w/ foreground gc.

---
 fs/f2fs/segment.h | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

index 3f1d6cdd4ae0..20d4387c661d 100644
@@ -625,8 +625,7 @@ static inline void __get_secs_required(struct f2fs_sb_info *sbi,
 	unsigned int dent_blocks = total_dent_blocks % CAP_BLKS_PER_SEC(sbi);
 	unsigned int data_blocks = 0;
 
-	if (f2fs_lfs_mode(sbi) &&
-		unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) {
+	if (f2fs_lfs_mode(sbi)) {
 		total_data_blocks = get_pages(sbi, F2FS_DIRTY_DATA);
 		data_secs = total_data_blocks / CAP_BLKS_PER_SEC(sbi);
 		data_blocks = total_data_blocks % CAP_BLKS_PER_SEC(sbi);

2.39.5

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

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

From: Alex Williamson <[email protected]>

[ Upstream commit e908f58b6beb337cbe4481d52c3f5c78167b1aab ]

In the below noted Fixes commit we introduced a reflck mutex to allow better scaling between devices for open and close. The reflck was based on the hot reset granularity, device level for root bus devices which cannot support hot reset or bus/slot reset otherwise. Overlooked in this were SR-IOV VFs, where there's also no bus reset option, but the default for a non-root-bus, non-slot-based device is bus level reflck granularity.

The reflck mutex has since become the dev_set mutex (via commit 2cd8b14aaa66 ("vfio/pci: Move to the device set infrastructure")) and is our defacto serialization for various operations and ioctls. It still seems to be the case though that sets of vfio-pci devices really only need serialization relative to hot resets affecting the entire set, which is not relevant to SR-IOV VFs. As described in the Closes link below, this serialization contributes to startup latency when multiple VFs sharing the same "bus" are opened concurrently.

Mark the device itself as the basis of the dev_set for SR-IOV VFs.

---
 drivers/vfio/pci/vfio_pci_core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index aa362b434413..13c223228c31 100644
@@ -2144,7 +2144,7 @@ int vfio_pci_core_register_device(struct vfio_pci_core_device *vdev)
 		return -EBUSY;
 	}
 
-	if (pci_is_root_bus(pdev->bus)) {
+	if (pci_is_root_bus(pdev->bus) || pdev->is_virtfn) {
 		ret = vfio_assign_device_set(&vdev->vdev, vdev);
 	} else if (!pci_probe_reset_slot(pdev->slot)) {
 		ret = vfio_assign_device_set(&vdev->vdev, pdev->slot);

2.39.5

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

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

From: Tomas Henzl <[email protected]>

[ Upstream commit 3e90b38781e3bdd651edaf789585687611638862 ]

In _mpt3sas_fw_work() the fw_event reference is removed, it should also be freed in all cases.

---
 drivers/scsi/mpt3sas/mpt3sas_scsih.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

index 31768da482a5..b5b77b82d69f 100644
@@ -10819,8 +10819,7 @@ _mpt3sas_fw_work(struct MPT3SAS_ADAPTER *ioc, struct fw_event_work *fw_event)
 		break;
 	case MPI2_EVENT_PCIE_TOPOLOGY_CHANGE_LIST:
 		_scsih_pcie_topology_change_event(ioc, fw_event);
-		ioc->current_event = NULL;
-		return;
+		break;
 	}
 out:
 	fw_event_work_put(fw_event);

2.39.5

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

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

From: Li Lingfeng <[email protected]>

[ Upstream commit 7bdc68921481c19cd8c85ddf805a834211c19e61 ]

This reverts commit c577ab7ba5f3bf9062db8a58b6e89d4fe370447e.

The invocation of iscsi_put_conn() in iscsi_iter_destory_conn_fn() is used to free the initial reference counter of iscsi_cls_conn. For non-qla4xxx cases, the ->destroy_conn() callback (e.g., iscsi_conn_teardown) will call iscsi_remove_conn() and iscsi_put_conn() to remove the connection from the children list of session and free the connection at last. However for qla4xxx, it is not the case. The ->destroy_conn() callback of qla4xxx will keep the connection in the session conn_list and doesn't use iscsi_put_conn() to free the initial reference counter. Therefore, it seems necessary to keep the iscsi_put_conn() in the iscsi_iter_destroy_conn_fn(), otherwise, there will be memory leak problem.

---
 drivers/scsi/scsi_transport_iscsi.c | 2 ++
 1 file changed, 2 insertions(+)

index c44103752b69..ef20fea95957 100644
@@ -2168,6 +2168,8 @@ static int iscsi_iter_destroy_conn_fn(struct device *dev, void *data)
 		return 0;
 
 	iscsi_remove_conn(iscsi_dev_to_conn(dev));
+	iscsi_put_conn(iscsi_dev_to_conn(dev));
+
 	return 0;
 }
 

2.39.5

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

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

From: Seunghui Lee <[email protected]>

[ Upstream commit 35dabf4503b94a697bababe94678a8bc989c3223 ]

If the h8 exit fails during runtime resume process, the runtime thread enters runtime suspend immediately and the error handler operates at the same time. It becomes stuck and cannot be recovered through the error handler. To fix this, use link recovery instead of the error handler.

---
 drivers/ufs/core/ufshcd.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

index dc17ae1dfe26..f9adb1106747 100644
@@ -4125,7 +4125,7 @@ static int ufshcd_uic_pwr_ctrl(struct ufs_hba *hba, struct uic_command *cmd)
 	hba->uic_async_done = NULL;
 	if (reenable_intr)
 		ufshcd_enable_intr(hba, UIC_COMMAND_COMPL);
-	if (ret) {
+	if (ret && !hba->pm_op_in_progress) {
 		ufshcd_set_link_broken(hba);
 		ufshcd_schedule_eh_work(hba);
 	}

@@ -4133,6 +4133,14 @@ static int ufshcd_uic_pwr_ctrl(struct ufs_hba *hba, struct uic_command *cmd)
 	spin_unlock_irqrestore(hba->host->host_lock, flags);
 	mutex_unlock(&hba->uic_cmd_mutex);
 
+	/*
+	 * If the h8 exit fails during the runtime resume process, it becomes
+	 * stuck and cannot be recovered through the error handler.  To fix
+	 * this, use link recovery instead of the error handler.
+	 */
+	if (ret && hba->pm_op_in_progress)
+		ret = ufshcd_link_recovery(hba);
+
 	return ret;
 }
 

2.39.5

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

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

From: Salomon Dushimirimana <[email protected]>

[ Upstream commit 8e48727c26c4d839ff9b4b73d1cae486bea7fe19 ]

Commit aa3998dbeb3a ("ata: libata-scsi: Disable scsi device manage_system_start_stop") enabled libata EH to manage device power mode trasitions for system suspend/resume and removed the flag from ata_scsi_dev_config. However, since the sd_shutdown() function still relies on the manage_system_start_stop flag, a spin-down command is not issued to the disk with command "echo 1 > /sys/block/sdb/device/delete"

sd_shutdown() can be called for both system/runtime start stop operations, so utilize the manage_run_time_start_stop flag set in the ata_scsi_dev_config and issue a spin-down command during disk removal when the system is running. This is in addition to when the system is powering off and manage_shutdown flag is set. The manage_system_start_stop flag will still be used for drivers that still set the flag.

---
 drivers/scsi/sd.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

index c3006524eb03..3b481779af35 100644
@@ -3771,7 +3771,9 @@ static void sd_shutdown(struct device *dev)
 	if ((system_state != SYSTEM_RESTART &&
 	     sdkp->device->manage_system_start_stop) ||
 	    (system_state == SYSTEM_POWER_OFF &&
-	     sdkp->device->manage_shutdown)) {
+	     sdkp->device->manage_shutdown) ||
+	    (system_state == SYSTEM_RUNNING &&
+	     sdkp->device->manage_runtime_start_stop)) {
 		sd_printk(KERN_NOTICE, sdkp, "Stopping disk\n");
 		sd_start_stop_device(sdkp, 0);
 	}

2.39.5

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

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

From: Masahiro Yamada <[email protected]>

[ Upstream commit 721bfe583c52ba1ea74b3736a31a9dcfe6dd6d95 ]

ConfigList::updateListForAll() and ConfigList::updateListAllforAll() are identical.

Commit f9b918fae678 ("kconfig: qconf: move ConfigView::updateList(All) to ConfigList class") was a misconversion.

---
 scripts/kconfig/qconf.cc | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index 61b679f6c2f2..c31dead186cc 100644
@@ -478,7 +478,7 @@ void ConfigList::updateListAllForAll()
 	while (it.hasNext()) {
 		ConfigList *list = it.next();
 
-		list->updateList();
+		list->updateListAll();
 	}
 }
 

2.39.5

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

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

From: Timothy Pearson <[email protected]>

[ Upstream commit 4668619092554e1b95c9a5ac2941ca47ba6d548a ]

When the root of a nested PCIe bridge configuration is unplugged, the pnv_php driver leaked the allocated IRQ resources for the child bridges' hotplug event notifications, resulting in a panic.

Fix this by walking all child buses and deallocating all its IRQ resources before calling pci_hp_remove_devices().

Also modify the lifetime of the workqueue at struct pnv_php_slot::wq so that it is only destroyed in pnv_php_free_slot(), instead of pnv_php_disable_irq(). This is required since pnv_php_disable_irq() will now be called by workers triggered by hot unplug interrupts, so the workqueue needs to stay allocated.

The abridged kernel panic that occurs without this patch is as follows:

  WARNING: CPU: 0 PID: 687 at kernel/irq/msi.c:292 msi_device_data_release+0x6c/0x9c
  CPU: 0 UID: 0 PID: 687 Comm: bash Not tainted 6.14.0-rc5+ #2
  Call Trace:
   msi_device_data_release+0x34/0x9c (unreliable)
   release_nodes+0x64/0x13c
   devres_release_all+0xc0/0x140
   device_del+0x2d4/0x46c
   pci_destroy_dev+0x5c/0x194
   pci_hp_remove_devices+0x90/0x128
   pci_hp_remove_devices+0x44/0x128
   pnv_php_disable_slot+0x54/0xd4
   power_write_file+0xf8/0x18c
   pci_slot_attr_store+0x40/0x5c
   sysfs_kf_write+0x64/0x78
   kernfs_fop_write_iter+0x1b0/0x290
   vfs_write+0x3bc/0x50c
   ksys_write+0x84/0x140
   system_call_exception+0x124/0x230
   system_call_vectored_common+0x15c/0x2ec

---
 drivers/pci/hotplug/pnv_php.c | 96 ++++++++++++++++++++++++++++-------
 1 file changed, 77 insertions(+), 19 deletions(-)

index 092c9ac0d26d..6989b8a0dc6b 100644
@@ -3,6 +3,7 @@
  * PCI Hotplug Driver for PowerPC PowerNV platform.
  *
  * Copyright Gavin Shan, IBM Corporation 2016.
+ * Copyright (C) 2025 Raptor Engineering, LLC
  */
 
 #include <linux/libfdt.h>

@@ -35,8 +36,10 @@ static void pnv_php_register(struct device_node *dn);
 static void pnv_php_unregister_one(struct device_node *dn);
 static void pnv_php_unregister(struct device_node *dn);
 
+static void pnv_php_enable_irq(struct pnv_php_slot *php_slot);
+
 static void pnv_php_disable_irq(struct pnv_php_slot *php_slot,
-				bool disable_device)
+				bool disable_device, bool disable_msi)
 {
 	struct pci_dev *pdev = php_slot->pdev;
 	u16 ctrl;

@@ -52,19 +55,15 @@ static void pnv_php_disable_irq(struct pnv_php_slot *php_slot,
 		php_slot->irq = 0;
 	}
 
-	if (php_slot->wq) {
-		destroy_workqueue(php_slot->wq);
-		php_slot->wq = NULL;
-	}
-
-	if (disable_device) {
+	if (disable_device || disable_msi) {
 		if (pdev->msix_enabled)
 			pci_disable_msix(pdev);
 		else if (pdev->msi_enabled)
 			pci_disable_msi(pdev);
+	}
 
+	if (disable_device)
 		pci_disable_device(pdev);
-	}
 }
 
 static void pnv_php_free_slot(struct kref *kref)

@@ -73,7 +72,8 @@ static void pnv_php_free_slot(struct kref *kref)
 					struct pnv_php_slot, kref);
 
 	WARN_ON(!list_empty(&php_slot->children));
-	pnv_php_disable_irq(php_slot, false);
+	pnv_php_disable_irq(php_slot, false, false);
+	destroy_workqueue(php_slot->wq);
 	kfree(php_slot->name);
 	kfree(php_slot);
 }

@@ -560,8 +560,58 @@ static int pnv_php_reset_slot(struct hotplug_slot *slot, bool probe)
 static int pnv_php_enable_slot(struct hotplug_slot *slot)
 {
 	struct pnv_php_slot *php_slot = to_pnv_php_slot(slot);
+	u32 prop32;
+	int ret;
+
+	ret = pnv_php_enable(php_slot, true);
+	if (ret)
+		return ret;
+
+	/* (Re-)enable interrupt if the slot supports surprise hotplug */
+	ret = of_property_read_u32(php_slot->dn, "ibm,slot-surprise-pluggable",
+				   &prop32);
+	if (!ret && prop32)
+		pnv_php_enable_irq(php_slot);
 
-	return pnv_php_enable(php_slot, true);
+	return 0;
+}
+
+/*
+ * Disable any hotplug interrupts for all slots on the provided bus, as well as
+ * all downstream slots in preparation for a hot unplug.
+ */
+static int pnv_php_disable_all_irqs(struct pci_bus *bus)
+{
+	struct pci_bus *child_bus;
+	struct pci_slot *slot;
+
+	/* First go down child buses */
+	list_for_each_entry(child_bus, &bus->children, node)
+		pnv_php_disable_all_irqs(child_bus);
+
+	/* Disable IRQs for all pnv_php slots on this bus */
+	list_for_each_entry(slot, &bus->slots, list) {
+		struct pnv_php_slot *php_slot = to_pnv_php_slot(slot->hotplug);
+
+		pnv_php_disable_irq(php_slot, false, true);
+	}
+
+	return 0;
+}
+
+/*
+ * Disable any hotplug interrupts for all downstream slots on the provided
+ * bus in preparation for a hot unplug.
+ */
+static int pnv_php_disable_all_downstream_irqs(struct pci_bus *bus)
+{
+	struct pci_bus *child_bus;
+
+	/* Go down child buses, recursively deactivating their IRQs */
+	list_for_each_entry(child_bus, &bus->children, node)
+		pnv_php_disable_all_irqs(child_bus);
+
+	return 0;
 }
 
 static int pnv_php_disable_slot(struct hotplug_slot *slot)

@@ -578,6 +628,13 @@ static int pnv_php_disable_slot(struct hotplug_slot *slot)
 	    php_slot->state != PNV_PHP_STATE_REGISTERED)
 		return 0;
 
+	/*
+	 * Free all IRQ resources from all child slots before remove.
+	 * Note that we do not disable the root slot IRQ here as that
+	 * would also deactivate the slot hot (re)plug interrupt!
+	 */
+	pnv_php_disable_all_downstream_irqs(php_slot->bus);
+
 	/* Remove all devices behind the slot */
 	pci_lock_rescan_remove();
 	pci_hp_remove_devices(php_slot->bus);

@@ -646,6 +703,15 @@ static struct pnv_php_slot *pnv_php_alloc_slot(struct device_node *dn)
 		return NULL;
 	}
 
+	/* Allocate workqueue for this slot's interrupt handling */
+	php_slot->wq = alloc_workqueue("pciehp-%s", 0, 0, php_slot->name);
+	if (!php_slot->wq) {
+		SLOT_WARN(php_slot, "Cannot alloc workqueue\n");
+		kfree(php_slot->name);
+		kfree(php_slot);
+		return NULL;
+	}
+
 	if (dn->child && PCI_DN(dn->child))
 		php_slot->slot_no = PCI_SLOT(PCI_DN(dn->child)->devfn);
 	else

@@ -842,14 +908,6 @@ static void pnv_php_init_irq(struct pnv_php_slot *php_slot, int irq)
 	u16 sts, ctrl;
 	int ret;
 
-	/* Allocate workqueue */
-	php_slot->wq = alloc_workqueue("pciehp-%s", 0, 0, php_slot->name);
-	if (!php_slot->wq) {
-		SLOT_WARN(php_slot, "Cannot alloc workqueue\n");
-		pnv_php_disable_irq(php_slot, true);
-		return;
-	}
-
 	/* Check PDC (Presence Detection Change) is broken or not */
 	ret = of_property_read_u32(php_slot->dn, "ibm,slot-broken-pdc",
 				   &broken_pdc);

@@ -868,7 +926,7 @@ static void pnv_php_init_irq(struct pnv_php_slot *php_slot, int irq)
 	ret = request_irq(irq, pnv_php_interrupt, IRQF_SHARED,
 			  php_slot->name, php_slot);
 	if (ret) {
-		pnv_php_disable_irq(php_slot, true);
+		pnv_php_disable_irq(php_slot, true, true);
 		SLOT_WARN(php_slot, "Error %d enabling IRQ %d\n", ret, irq);
 		return;
 	}

2.39.5

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

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

From: Timothy Pearson <[email protected]>

[ Upstream commit 80f9fc2362797538ebd4fd70a1dfa838cc2c2cdb ]

The Microsemi Switchtec PM8533 PFX 48xG3 [11f8:8533] PCIe switch system was observed to incorrectly assert the Presence Detect Set bit in its capabilities when tested on a Raptor Computing Systems Blackbird system, resulting in the hot insert path never attempting a rescan of the bus and any downstream devices not being re-detected.

Work around this by additionally checking whether the PCIe data link is active or not when performing presence detection on downstream switches' ports, similar to the pciehp_hpc.c driver.

---
 drivers/pci/hotplug/pnv_php.c | 27 +++++++++++++++++++++++++++
 1 file changed, 27 insertions(+)

index 6989b8a0dc6b..d37faa53bcd8 100644
@@ -390,6 +390,20 @@ static int pnv_php_get_power_state(struct hotplug_slot *slot, u8 *state)
 	return 0;
 }
 
+static int pcie_check_link_active(struct pci_dev *pdev)
+{
+	u16 lnk_status;
+	int ret;
+
+	ret = pcie_capability_read_word(pdev, PCI_EXP_LNKSTA, &lnk_status);
+	if (ret == PCIBIOS_DEVICE_NOT_FOUND || PCI_POSSIBLE_ERROR(lnk_status))
+		return -ENODEV;
+
+	ret = !!(lnk_status & PCI_EXP_LNKSTA_DLLLA);
+
+	return ret;
+}
+
 static int pnv_php_get_adapter_state(struct hotplug_slot *slot, u8 *state)
 {
 	struct pnv_php_slot *php_slot = to_pnv_php_slot(slot);

@@ -402,6 +416,19 @@ static int pnv_php_get_adapter_state(struct hotplug_slot *slot, u8 *state)
 	 */
 	ret = pnv_pci_get_presence_state(php_slot->id, &presence);
 	if (ret >= 0) {
+		if (pci_pcie_type(php_slot->pdev) == PCI_EXP_TYPE_DOWNSTREAM &&
+			presence == OPAL_PCI_SLOT_EMPTY) {
+			/*
+			 * Similar to pciehp_hpc, check whether the Link Active
+			 * bit is set to account for broken downstream bridges
+			 * that don't properly assert Presence Detect State, as
+			 * was observed on the Microsemi Switchtec PM8533 PFX
+			 * [11f8:8533].
+			 */
+			if (pcie_check_link_active(php_slot->pdev) > 0)
+				presence = OPAL_PCI_SLOT_PRESENT;
+		}
+
 		*state = presence;
 		ret = 0;
 	} else {

2.39.5

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

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

From: Timothy Pearson <[email protected]>

[ Upstream commit e82b34eed04b0ddcff4548b62633467235672fd3 ]

The PowerNV hotplug driver needs to be able to clear any frozen PE(s) on the PHB after suprise removal of a downstream device.

Export the eeh_unfreeze_pe() symbol to allow implementation of this functionality in the php_nv module.

---
 arch/powerpc/kernel/eeh.c | 1 +
 1 file changed, 1 insertion(+)

index 2e286bba2f64..82626363a309 100644
@@ -1130,6 +1130,7 @@ int eeh_unfreeze_pe(struct eeh_pe *pe)
 
 	return ret;
 }
+EXPORT_SYMBOL_GPL(eeh_unfreeze_pe);
 
 
 static struct pci_device_id eeh_reset_ids[] = {

2.39.5

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

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

From: Maciej W. Rozycki <[email protected]>

[ Upstream commit 1541a21305ceb10fcf3f7cbb23f3e1a00bbf1789 ]

Use dev->link_active_reporting to determine whether Data Link Layer Link Active Reporting is available rather than re-retrieving the capability.

Stable-dep-of: 1010b4c012b0 ("powerpc/eeh: Make EEH driver device hotplug safe")

---
 arch/powerpc/kernel/eeh_pe.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

index e4624d789629..7d1b50599dd6 100644
@@ -671,9 +671,8 @@ static void eeh_bridge_check_link(struct eeh_dev *edev)
 	eeh_ops->write_config(edev, cap + PCI_EXP_LNKCTL, 2, val);
 
 	/* Check link */
-	eeh_ops->read_config(edev, cap + PCI_EXP_LNKCAP, 4, &val);
-	if (!(val & PCI_EXP_LNKCAP_DLLLARC)) {
-		eeh_edev_dbg(edev, "No link reporting capability (0x%08x) \n", val);
+	if (!edev->pdev->link_active_reporting) {
+		eeh_edev_dbg(edev, "No link reporting capability\n");
 		msleep(1000);
 		return;
 	}

2.39.5

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

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

From: Timothy Pearson <[email protected]>

[ Upstream commit 1010b4c012b0d78dfb9d3132b49aa2ef024a07a7 ]

Multiple race conditions existed between the PCIe hotplug driver and the EEH driver, leading to a variety of kernel oopses of the same general nature:

<pcie device unplug>
<eeh driver trigger>
<hotplug removal trigger>
<pcie tree reconfiguration>
<eeh recovery next step>
<oops in EEH driver bus iteration loop>

A second class of oops is also seen when the underlying bus disappears during device recovery.

Refactor the EEH module to be PCI rescan and remove safe. Also clean up a few minor formatting / readability issues.

---
 arch/powerpc/kernel/eeh_driver.c | 48 +++++++++++++++++++++-----------
 arch/powerpc/kernel/eeh_pe.c     | 10 ++++---
 2 files changed, 38 insertions(+), 20 deletions(-)

index f279295179bd..429abaecad41 100644
@@ -257,13 +257,12 @@ static void eeh_pe_report_edev(struct eeh_dev *edev, eeh_report_fn fn,
 	struct pci_driver *driver;
 	enum pci_ers_result new_result;
 
-	pci_lock_rescan_remove();
 	pdev = edev->pdev;
 	if (pdev)
 		get_device(&pdev->dev);
-	pci_unlock_rescan_remove();
 	if (!pdev) {
 		eeh_edev_info(edev, "no device");
+		*result = PCI_ERS_RESULT_DISCONNECT;
 		return;
 	}
 	device_lock(&pdev->dev);

@@ -304,8 +303,9 @@ static void eeh_pe_report(const char *name, struct eeh_pe *root,
 	struct eeh_dev *edev, *tmp;
 
 	pr_info("EEH: Beginning: '%s'\n", name);
-	eeh_for_each_pe(root, pe) eeh_pe_for_each_dev(pe, edev, tmp)
-		eeh_pe_report_edev(edev, fn, result);
+	eeh_for_each_pe(root, pe)
+		eeh_pe_for_each_dev(pe, edev, tmp)
+			eeh_pe_report_edev(edev, fn, result);
 	if (result)
 		pr_info("EEH: Finished:'%s' with aggregate recovery state:'%s'\n",
 			name, pci_ers_result_name(*result));

@@ -383,6 +383,8 @@ static void eeh_dev_restore_state(struct eeh_dev *edev, void *userdata)
 	if (!edev)
 		return;
 
+	pci_lock_rescan_remove();
+
 	/*
 	 * The content in the config space isn't saved because
 	 * the blocked config space on some adapters. We have

@@ -393,14 +395,19 @@ static void eeh_dev_restore_state(struct eeh_dev *edev, void *userdata)
 		if (list_is_last(&edev->entry, &edev->pe->edevs))
 			eeh_pe_restore_bars(edev->pe);
 
+		pci_unlock_rescan_remove();
 		return;
 	}
 
 	pdev = eeh_dev_to_pci_dev(edev);
-	if (!pdev)
+	if (!pdev) {
+		pci_unlock_rescan_remove();
 		return;
+	}
 
 	pci_restore_state(pdev);
+
+	pci_unlock_rescan_remove();
 }
 
 /**

@@ -647,9 +654,7 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus,
 	if (any_passed || driver_eeh_aware || (pe->type & EEH_PE_VF)) {
 		eeh_pe_dev_traverse(pe, eeh_rmv_device, rmv_data);
 	} else {
-		pci_lock_rescan_remove();
 		pci_hp_remove_devices(bus);
-		pci_unlock_rescan_remove();
 	}
 
 	/*

@@ -665,8 +670,6 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus,
 	if (rc)
 		return rc;
 
-	pci_lock_rescan_remove();
-
 	/* Restore PE */
 	eeh_ops->configure_bridge(pe);
 	eeh_pe_restore_bars(pe);

@@ -674,7 +677,6 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus,
 	/* Clear frozen state */
 	rc = eeh_clear_pe_frozen_state(pe, false);
 	if (rc) {
-		pci_unlock_rescan_remove();
 		return rc;
 	}
 

@@ -709,7 +711,6 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus,
 	pe->tstamp = tstamp;
 	pe->freeze_count = cnt;
 
-	pci_unlock_rescan_remove();
 	return 0;
 }
 

@@ -843,10 +844,13 @@ void eeh_handle_normal_event(struct eeh_pe *pe)
 		{LIST_HEAD_INIT(rmv_data.removed_vf_list), 0};
 	int devices = 0;
 
+	pci_lock_rescan_remove();
+
 	bus = eeh_pe_bus_get(pe);
 	if (!bus) {
 		pr_err("%s: Cannot find PCI bus for PHB#%x-PE#%x\n",
 			__func__, pe->phb->global_number, pe->addr);
+		pci_unlock_rescan_remove();
 		return;
 	}
 

@@ -1085,10 +1089,15 @@ void eeh_handle_normal_event(struct eeh_pe *pe)
 		eeh_pe_state_clear(pe, EEH_PE_PRI_BUS, true);
 		eeh_pe_dev_mode_mark(pe, EEH_DEV_REMOVED);
 
-		pci_lock_rescan_remove();
-		pci_hp_remove_devices(bus);
-		pci_unlock_rescan_remove();
+		bus = eeh_pe_bus_get(pe);
+		if (bus)
+			pci_hp_remove_devices(bus);
+		else
+			pr_err("%s: PCI bus for PHB#%x-PE#%x disappeared\n",
+				__func__, pe->phb->global_number, pe->addr);
+
 		/* The passed PE should no longer be used */
+		pci_unlock_rescan_remove();
 		return;
 	}
 

@@ -1105,6 +1114,8 @@ void eeh_handle_normal_event(struct eeh_pe *pe)
 			eeh_clear_slot_attention(edev->pdev);
 
 	eeh_pe_state_clear(pe, EEH_PE_RECOVERING, true);
+
+	pci_unlock_rescan_remove();
 }
 
 /**

@@ -1123,6 +1134,7 @@ void eeh_handle_special_event(void)
 	unsigned long flags;
 	int rc;
 
+	pci_lock_rescan_remove();
 
 	do {
 		rc = eeh_ops->next_error(&pe);

@@ -1162,10 +1174,12 @@ void eeh_handle_special_event(void)
 
 			break;
 		case EEH_NEXT_ERR_NONE:
+			pci_unlock_rescan_remove();
 			return;
 		default:
 			pr_warn("%s: Invalid value %d from next_error()\n",
 				__func__, rc);
+			pci_unlock_rescan_remove();
 			return;
 		}
 

@@ -1177,7 +1191,9 @@ void eeh_handle_special_event(void)
 		if (rc == EEH_NEXT_ERR_FROZEN_PE ||
 		    rc == EEH_NEXT_ERR_FENCED_PHB) {
 			eeh_pe_state_mark(pe, EEH_PE_RECOVERING);
+			pci_unlock_rescan_remove();
 			eeh_handle_normal_event(pe);
+			pci_lock_rescan_remove();
 		} else {
 			eeh_for_each_pe(pe, tmp_pe)
 				eeh_pe_for_each_dev(tmp_pe, edev, tmp_edev)

@@ -1190,7 +1206,6 @@ void eeh_handle_special_event(void)
 				"error_detected(permanent failure)", pe,
 				eeh_report_failure, NULL);
 
-			pci_lock_rescan_remove();
 			list_for_each_entry(hose, &hose_list, list_node) {
 				phb_pe = eeh_phb_pe_get(hose);
 				if (!phb_pe ||

@@ -1209,7 +1224,6 @@ void eeh_handle_special_event(void)
 				}
 				pci_hp_remove_devices(bus);
 			}
-			pci_unlock_rescan_remove();
 		}
 
 		/*

@@ -1219,4 +1233,6 @@ void eeh_handle_special_event(void)
 		if (rc == EEH_NEXT_ERR_DEAD_IOC)
 			break;
 	} while (rc != EEH_NEXT_ERR_NONE);
+
+	pci_unlock_rescan_remove();
 }

index 7d1b50599dd6..08095aeba5c9 100644
@@ -671,10 +671,12 @@ static void eeh_bridge_check_link(struct eeh_dev *edev)
 	eeh_ops->write_config(edev, cap + PCI_EXP_LNKCTL, 2, val);
 
 	/* Check link */
-	if (!edev->pdev->link_active_reporting) {
-		eeh_edev_dbg(edev, "No link reporting capability\n");
-		msleep(1000);
-		return;
+	if (edev->pdev) {
+		if (!edev->pdev->link_active_reporting) {
+			eeh_edev_dbg(edev, "No link reporting capability\n");
+			msleep(1000);
+			return;
+		}
 	}
 
 	/* Wait the link is up until timeout (5s) */

2.39.5

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

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

From: Timothy Pearson <[email protected]>

[ Upstream commit a2a2a6fc2469524caa713036297c542746d148dc ]

The existing PowerNV hotplug code did not handle surprise plug events correctly, leading to a complete failure of the hotplug system after device removal and a required reboot to detect new devices.

This comes down to two issues:

1) When a device is surprise removed, often the bridge upstream port will cause a PE freeze on the PHB. If this freeze is not cleared, the MSI interrupts from the bridge hotplug notification logic will not be received by the kernel, stalling all plug events on all slots associated with the PE.

2) When a device is removed from a slot, regardless of surprise or programmatic removal, the associated PHB/PE ls left frozen. If this freeze is not cleared via a fundamental reset, skiboot is unable to clear the freeze and cannot retrain / rescan the slot. This also requires a reboot to clear the freeze and redetect the device in the slot.

Issue the appropriate unfreeze and rescan commands on hotplug events, and don't oops on hotplug if pci_bus_to_OF_node() returns NULL.

---
 arch/powerpc/kernel/pci-hotplug.c |   3 +
 drivers/pci/hotplug/pnv_php.c     | 110 +++++++++++++++++++++++++++++-
 2 files changed, 110 insertions(+), 3 deletions(-)

index 0fe251c6ac2c..ac70e85b0df8 100644
@@ -111,6 +111,9 @@ void pci_hp_add_devices(struct pci_bus *bus)
 	struct pci_controller *phb;
 	struct device_node *dn = pci_bus_to_OF_node(bus);
 
+	if (!dn)
+		return;
+
 	phb = pci_bus_to_host(bus);
 
 	mode = PCI_PROBE_NORMAL;

2.39.5

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

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

From: Tigran Mkrtchyan <[email protected]>

[ Upstream commit f06bedfa62d57f7b67d44aacd6badad2e13a803f ]

When an applications get killed (SIGTERM/SIGINT) while pNFS client performs a connection to DS, client ends in an infinite loop of connect-disconnect. This
source of the issue, it that flexfilelayoutdev#nfs4_ff_layout_prepare_ds gets an error on nfs4_pnfs_ds_connect with status ERESTARTSYS, which is set by rpc_signal_task, but the error is treated as transient, thus retried.

The issue is reproducible with Ctrl+C the following script(there should be ~1000 files in a directory, client should must not have any connections to DSes):

```
echo 3 > /proc/sys/vm/drop_caches

for i in *
do
   head -1 $i
done
```

The change aims to propagate the nfs4_ff_layout_prepare_ds error state to the caller that can decide whatever this is a retryable error or not.

---
 fs/nfs/flexfilelayout/flexfilelayout.c    | 26 ++++++++++++++---------
 fs/nfs/flexfilelayout/flexfilelayoutdev.c |  6 +++---
 2 files changed, 19 insertions(+), 13 deletions(-)

index aa55b5df065b..5dd16f4ae74d 100644
@@ -745,14 +745,14 @@ ff_layout_choose_ds_for_read(struct pnfs_layout_segment *lseg,
 {
 	struct nfs4_ff_layout_segment *fls = FF_LAYOUT_LSEG(lseg);
 	struct nfs4_ff_layout_mirror *mirror;
-	struct nfs4_pnfs_ds *ds;
+	struct nfs4_pnfs_ds *ds = ERR_PTR(-EAGAIN);
 	u32 idx;
 
 	/* mirrors are initially sorted by efficiency */
 	for (idx = start_idx; idx < fls->mirror_array_cnt; idx++) {
 		mirror = FF_LAYOUT_COMP(lseg, idx);
 		ds = nfs4_ff_layout_prepare_ds(lseg, mirror, false);
-		if (!ds)
+		if (IS_ERR(ds))
 			continue;
 
 		if (check_device &&

@@ -760,10 +760,10 @@ ff_layout_choose_ds_for_read(struct pnfs_layout_segment *lseg,
 			continue;
 
 		*best_idx = idx;
-		return ds;
+		break;
 	}
 
-	return NULL;
+	return ds;
 }
 
 static struct nfs4_pnfs_ds *

@@ -933,7 +933,7 @@ ff_layout_pg_init_write(struct nfs_pageio_descriptor *pgio,
 	for (i = 0; i < pgio->pg_mirror_count; i++) {
 		mirror = FF_LAYOUT_COMP(pgio->pg_lseg, i);
 		ds = nfs4_ff_layout_prepare_ds(pgio->pg_lseg, mirror, true);
-		if (!ds) {
+		if (IS_ERR(ds)) {
 			if (!ff_layout_no_fallback_to_mds(pgio->pg_lseg))
 				goto out_mds;
 			pnfs_generic_pg_cleanup(pgio);

@@ -1839,6 +1839,7 @@ ff_layout_read_pagelist(struct nfs_pgio_header *hdr)
 	u32 idx = hdr->pgio_mirror_idx;
 	int vers;
 	struct nfs_fh *fh;
+	bool ds_fatal_error = false;
 
 	dprintk("--> %s ino %lu pgbase %u req %zu@%llu\n",
 		__func__, hdr->inode->i_ino,

@@ -1846,8 +1847,10 @@ ff_layout_read_pagelist(struct nfs_pgio_header *hdr)
 
 	mirror = FF_LAYOUT_COMP(lseg, idx);
 	ds = nfs4_ff_layout_prepare_ds(lseg, mirror, false);
-	if (!ds)
+	if (IS_ERR(ds)) {
+		ds_fatal_error = nfs_error_is_fatal(PTR_ERR(ds));
 		goto out_failed;
+	}
 
 	ds_clnt = nfs4_ff_find_or_create_ds_client(mirror, ds->ds_clp,
 						   hdr->inode);

@@ -1888,7 +1891,7 @@ ff_layout_read_pagelist(struct nfs_pgio_header *hdr)
 	return PNFS_ATTEMPTED;
 
 out_failed:
-	if (ff_layout_avoid_mds_available_ds(lseg))
+	if (ff_layout_avoid_mds_available_ds(lseg) && !ds_fatal_error)
 		return PNFS_TRY_AGAIN;
 	trace_pnfs_mds_fallback_read_pagelist(hdr->inode,
 			hdr->args.offset, hdr->args.count,

@@ -1909,11 +1912,14 @@ ff_layout_write_pagelist(struct nfs_pgio_header *hdr, int sync)
 	int vers;
 	struct nfs_fh *fh;
 	u32 idx = hdr->pgio_mirror_idx;
+	bool ds_fatal_error = false;
 
 	mirror = FF_LAYOUT_COMP(lseg, idx);
 	ds = nfs4_ff_layout_prepare_ds(lseg, mirror, true);
-	if (!ds)
+	if (IS_ERR(ds)) {
+		ds_fatal_error = nfs_error_is_fatal(PTR_ERR(ds));
 		goto out_failed;
+	}
 
 	ds_clnt = nfs4_ff_find_or_create_ds_client(mirror, ds->ds_clp,
 						   hdr->inode);

@@ -1956,7 +1962,7 @@ ff_layout_write_pagelist(struct nfs_pgio_header *hdr, int sync)
 	return PNFS_ATTEMPTED;
 
 out_failed:
-	if (ff_layout_avoid_mds_available_ds(lseg))
+	if (ff_layout_avoid_mds_available_ds(lseg) && !ds_fatal_error)
 		return PNFS_TRY_AGAIN;
 	trace_pnfs_mds_fallback_write_pagelist(hdr->inode,
 			hdr->args.offset, hdr->args.count,

@@ -1998,7 +2004,7 @@ static int ff_layout_initiate_commit(struct nfs_commit_data *data, int how)
 	idx = calc_ds_index_from_commit(lseg, data->ds_commit_index);
 	mirror = FF_LAYOUT_COMP(lseg, idx);
 	ds = nfs4_ff_layout_prepare_ds(lseg, mirror, true);
-	if (!ds)
+	if (IS_ERR(ds))
 		goto out_err;
 
 	ds_clnt = nfs4_ff_find_or_create_ds_client(mirror, ds->ds_clp,

index d21c5ecfbf1c..95d5dca67145 100644
@@ -370,11 +370,11 @@ nfs4_ff_layout_prepare_ds(struct pnfs_layout_segment *lseg,
 			  struct nfs4_ff_layout_mirror *mirror,
 			  bool fail_return)
 {
-	struct nfs4_pnfs_ds *ds = NULL;
+	struct nfs4_pnfs_ds *ds;
 	struct inode *ino = lseg->pls_layout->plh_inode;
 	struct nfs_server *s = NFS_SERVER(ino);
 	unsigned int max_payload;
-	int status;
+	int status = -EAGAIN;
 
 	if (!ff_layout_init_mirror_ds(lseg->pls_layout, mirror))
 		goto noconnect;

@@ -412,7 +412,7 @@ nfs4_ff_layout_prepare_ds(struct pnfs_layout_segment *lseg,
 	ff_layout_send_layouterror(lseg);
 	if (fail_return || !ff_layout_has_available_ds(lseg))
 		pnfs_error_mark_layout_for_return(ino, lseg);
-	ds = NULL;
+	ds = ERR_PTR(status);
 out:
 	return ds;
 }

2.39.5

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

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

From: NeilBrown <[email protected]>

[ Upstream commit 52d633def56c10fe3e82a2c5d88c3ecb3f4e4852 ]

There are common patterns in the kernel of using test_and_clear_bit() before wake_up_bit(), and atomic_dec_and_test() before wake_up_var().

These combinations don't need extra barriers but sometimes include them unnecessarily.

To help avoid the unnecessary barriers and to help discourage the general use of wake_up_bit/var (which is a fragile interface) introduce two combined functions which implement these patterns.

Also add store_release_wake_up() which supports the task of simply setting a non-atomic variable and sending a wakeup. This pattern requires barriers which are often omitted.

Stable-dep-of: 1db3a48e83bb ("NFS: Fix wakeup of __nfs_lookup_revalidate() in unblock_revalidate()")

---
 include/linux/wait_bit.h | 60 ++++++++++++++++++++++++++++++++++++++++
 1 file changed, 60 insertions(+)

index 7725b7579b78..2209c227e859 100644
@@ -335,4 +335,64 @@ static inline void clear_and_wake_up_bit(int bit, void *word)
 	wake_up_bit(word, bit);
 }
 
+/**
+ * test_and_clear_wake_up_bit - clear a bit if it was set: wake up anyone waiting on that bit
+ * @bit: the bit of the word being waited on
+ * @word: the address of memory containing that bit
+ *
+ * If the bit is set and can be atomically cleared, any tasks waiting in
+ * wait_on_bit() or similar will be woken.  This call has the same
+ * complete ordering semantics as test_and_clear_bit().  Any changes to
+ * memory made before this call are guaranteed to be visible after the
+ * corresponding wait_on_bit() completes.
+ *
+ * Returns %true if the bit was successfully set and the wake up was sent.
+ */
+static inline bool test_and_clear_wake_up_bit(int bit, unsigned long *word)
+{
+	if (!test_and_clear_bit(bit, word))
+		return false;
+	/* no extra barrier required */
+	wake_up_bit(word, bit);
+	return true;
+}
+
+/**
+ * atomic_dec_and_wake_up - decrement an atomic_t and if zero, wake up waiters
+ * @var: the variable to dec and test
+ *
+ * Decrements the atomic variable and if it reaches zero, send a wake_up to any
+ * processes waiting on the variable.
+ *
+ * This function has the same complete ordering semantics as atomic_dec_and_test.
+ *
+ * Returns %true is the variable reaches zero and the wake up was sent.
+ */
+
+static inline bool atomic_dec_and_wake_up(atomic_t *var)
+{
+	if (!atomic_dec_and_test(var))
+		return false;
+	/* No extra barrier required */
+	wake_up_var(var);
+	return true;
+}
+
+/**
+ * store_release_wake_up - update a variable and send a wake_up
+ * @var: the address of the variable to be updated and woken
+ * @val: the value to store in the variable.
+ *
+ * Store the given value in the variable send a wake up to any tasks
+ * waiting on the variable.  All necessary barriers are included to ensure
+ * the task calling wait_var_event() sees the new value and all values
+ * written to memory before this call.
+ */
+#define store_release_wake_up(var, val)					\
+do {									\
+	smp_store_release(var, val);					\
+	smp_mb();							\
+	wake_up_var(var);						\
+} while (0)
+
 #endif /* _LINUX_WAIT_BIT_H */

2.39.5

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

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

From: Trond Myklebust <[email protected]>

[ Upstream commit 1db3a48e83bb64a70bf27263b7002585574a9c2d ]

Use store_release_wake_up() to add the appropriate memory barrier before calling wake_up_var(&dentry->d_fsdata).

---
 fs/nfs/dir.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

index 1876978107ca..3c98049912df 100644
@@ -1825,9 +1825,7 @@ static void block_revalidate(struct dentry *dentry)
 
 static void unblock_revalidate(struct dentry *dentry)
 {
-	/* store_release ensures wait_var_event() sees the update */
-	smp_store_release(&dentry->d_fsdata, NULL);
-	wake_up_var(&dentry->d_fsdata);
+	store_release_wake_up(&dentry->d_fsdata, NULL);
 }
 
 /*

2.39.5

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

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

From: Trond Myklebust <[email protected]>

[ Upstream commit ef93a685e01a281b5e2a25ce4e3428cf9371a205 ]

The function needs to check the minimal filehandle length before it can access the embedded filehandle.

---
 fs/nfs/export.c | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

index 9fe9586a51b7..aacf6220ab44 100644
@@ -66,14 +66,21 @@ nfs_fh_to_dentry(struct super_block *sb, struct fid *fid,
 {
 	struct nfs_fattr *fattr = NULL;
 	struct nfs_fh *server_fh = nfs_exp_embedfh(fid->raw);
-	size_t fh_size = offsetof(struct nfs_fh, data) + server_fh->size;
+	size_t fh_size = offsetof(struct nfs_fh, data);
 	const struct nfs_rpc_ops *rpc_ops;
 	struct dentry *dentry;
 	struct inode *inode;
-	int len = EMBED_FH_OFF + XDR_QUADLEN(fh_size);
+	int len = EMBED_FH_OFF;
 	u32 *p = fid->raw;
 	int ret;
 
+	/* Initial check of bounds */
+	if (fh_len < len + XDR_QUADLEN(fh_size) ||
+	    fh_len > XDR_QUADLEN(NFS_MAXFHSIZE))
+		return NULL;
+	/* Calculate embedded filehandle size */
+	fh_size += server_fh->size;
+	len += XDR_QUADLEN(fh_size);
 	/* NULL translates to ESTALE */
 	if (fh_len < len || fh_type != len)
 		return NULL;

2.39.5

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

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

From: Olga Kornievskaia <[email protected]>

[ Upstream commit 9acb237deff7667b0f6b10fe6b1b70c4429ea049 ]

Currently, when the server supports NFS4.1 security labels then security.selinux label in included twice. Instead, only add it when the server doesn't possess security label support.

---
 fs/nfs/nfs4proc.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

index 29f8a2df2c11..4abac68a4f0f 100644
@@ -10635,7 +10635,7 @@ const struct nfs4_minor_version_ops *nfs_v4_minor_ops[] = {
 
 static ssize_t nfs4_listxattr(struct dentry *dentry, char *list, size_t size)
 {
-	ssize_t error, error2, error3, error4;
+	ssize_t error, error2, error3, error4 = 0;
 	size_t left = size;
 
 	error = generic_listxattr(dentry, list, left);

@@ -10663,9 +10663,11 @@ static ssize_t nfs4_listxattr(struct dentry *dentry, char *list, size_t size)
 		left -= error3;
 	}
 
-	error4 = security_inode_listsecurity(d_inode(dentry), list, left);
-	if (error4 < 0)
-		return error4;
+	if (!nfs_server_capable(d_inode(dentry), NFS_CAP_SECURITY_LABEL)) {
+		error4 = security_inode_listsecurity(d_inode(dentry), list, left);
+		if (error4 < 0)
+			return error4;
+	}
 
 	error += error2 + error3 + error4;
 	if (size && error > size)

2.39.5

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

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

From: Benjamin Coddington <[email protected]>

[ Upstream commit 99765233ab42bf7a4950377ad7894dce8a5c0e60 ]

If the NFS client is doing writeback from a workqueue context, avoid using __GFP_NORETRY for allocations if the task has set PF_MEMALLOC_NOIO or PF_MEMALLOC_NOFS. The combination of these flags makes memory allocation failures much more likely.

We've seen those allocation failures show up when the loopback driver is doing writeback from a workqueue to a file on NFS, where memory allocation failure results in errors or corruption within the loopback device's filesystem.

---
 fs/nfs/internal.h | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

index 84361674bffc..6ea10abfa851 100644
@@ -598,9 +598,12 @@ nfs_write_match_verf(const struct nfs_writeverf *verf,
 
 static inline gfp_t nfs_io_gfp_mask(void)
 {
-	if (current->flags & PF_WQ_WORKER)
-		return GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN;
-	return GFP_KERNEL;
+	gfp_t ret = current_gfp_context(GFP_KERNEL);
+
+	/* For workers __GFP_NORETRY only with __GFP_IO or __GFP_FS */
+	if ((current->flags & PF_WQ_WORKER) && ret == GFP_KERNEL)
+		ret |= __GFP_NORETRY | __GFP_NOWARN;
+	return ret;
 }
 
 /*

2.39.5

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

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

From: Jakub Kicinski <[email protected]>

[ Upstream commit 2da4def0f487f24bbb0cece3bb2bcdcb918a0b72 ]

Paolo spotted hangs in NIPA running driver tests against virtio. The tests hang in virtnet_close() -> virtnet_napi_tx_disable().

The problem is only reproducible if running multiple of our tests in sequence (I used TEST_PROGS="xdp.py ping.py netcons_basic.sh \
netpoll_basic.py stats.py"). Initial suspicion was that this is a simple case of double-disable of NAPI, but instrumenting the code reveals:

Deadlocked on NAPI ffff888007cd82c0 (virtnet_poll_tx):
state: 0x37, disabled: false, owner: 0, listed: false, weight: 64

The NAPI was not in fact disabled, owner is 0 (rather than -1), so the NAPI "thinks" it's scheduled for CPU 0 but it's not listed (!list_empty(&n->poll_list) => false). It seems odd that normal NAPI processing would wedge itself like this.

Better suspicion is that netpoll gets enabled while NAPI is polling, and also grabs the NAPI instance. This confuses napi_complete_done():

[netpoll] [normal NAPI]

                                        napi_poll()
                                          have = netpoll_poll_lock()
                                            rcu_access_pointer(dev->npinfo)
                                              return NULL # no netpoll
                                          __napi_poll()
					    ->poll(->weight)
  poll_napi()
    cmpxchg(->poll_owner, -1, cpu)
      poll_one_napi()
        set_bit(NAPI_STATE_NPSVC, ->state)
                                              napi_complete_done()
                                                if (NAPIF_STATE_NPSVC)
                                                  return false
                                           # exit without clearing SCHED

This feels very unlikely, but perhaps virtio has some interactions with the hypervisor in the NAPI ->poll that makes the race window larger?

Best I could to to prove the theory was to add and trigger this warning in napi_poll (just before netpoll_poll_unlock()):

      WARN_ONCE(!have && rcu_access_pointer(n->dev->npinfo) &&
                napi_is_scheduled(n) && list_empty(&n->poll_list),
                "NAPI race with netpoll %px", n);

If this warning hits the next virtio_close() will hang.

This patch survived 30 test iterations without a hang (without it the longest clean run was around 10). Credit for triggering this goes to Breno's recent netconsole tests.

---
 net/core/netpoll.c | 7 +++++++
 1 file changed, 7 insertions(+)

index 657abbb7d0d7..89f5358d7a1b 100644
@@ -800,6 +800,13 @@ int netpoll_setup(struct netpoll *np)
 		goto put;
 	netdev_tracker_alloc(ndev, &np->dev_tracker, GFP_KERNEL);
 	rtnl_unlock();
+
+	/* Make sure all NAPI polls which started before dev->npinfo
+	 * was visible have exited before we start calling NAPI poll.
+	 * NAPI skips locking if dev->npinfo is NULL.
+	 */
+	synchronize_rcu();
+
 	return 0;
 
 put:

2.39.5

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

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

From: Horatiu Vultur <[email protected]>

[ Upstream commit 6fb5ff63b35b7e849cc8510957f25753f87f63d2 ]

According to the 1588 standard, it is possible to use both unicast and multicast frames to send the PTP information. It was noticed that if the frames were unicast they were not processed by the analyzer meaning that they were not timestamped. Therefore fix this to match also these unicast frames.