5.4.198-rc1 review

From: Hoang Le <[email protected]>

[ Upstream commit 7f36f798f89bf32c0164049cb0e3fd1af613d0bb ]

syzbot reported uninit-value:
=====================================================

BUG: KMSAN: uninit-value in string_nocheck lib/vsprintf.c:644 [inline]
BUG: KMSAN: uninit-value in string+0x4f9/0x6f0 lib/vsprintf.c:725
 string_nocheck lib/vsprintf.c:644 [inline]
 string+0x4f9/0x6f0 lib/vsprintf.c:725
 vsnprintf+0x2222/0x3650 lib/vsprintf.c:2806
 vprintk_store+0x537/0x2150 kernel/printk/printk.c:2158
 vprintk_emit+0x28b/0xab0 kernel/printk/printk.c:2256
 vprintk_default+0x86/0xa0 kernel/printk/printk.c:2283
 vprintk+0x15f/0x180 kernel/printk/printk_safe.c:50
 _printk+0x18d/0x1cf kernel/printk/printk.c:2293
 tipc_enable_bearer net/tipc/bearer.c:371 [inline]
 __tipc_nl_bearer_enable+0x2022/0x22a0 net/tipc/bearer.c:1033
 tipc_nl_bearer_enable+0x6c/0xb0 net/tipc/bearer.c:1042
 genl_family_rcv_msg_doit net/netlink/genetlink.c:731 [inline]

- Do sanity check the attribute length for TIPC_NLA_BEARER_NAME.
- Do not use 'illegal name' in printing message.

---
 net/tipc/bearer.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

index 8bd2454cc89d..577f71dd63fb 100644
@@ -248,9 +248,8 @@ static int tipc_enable_bearer(struct net *net, const char *name,
 	u32 i;
 
 	if (!bearer_name_validate(name, &b_names)) {
-		errstr = "illegal name";
 		NL_SET_ERR_MSG(extack, "Illegal name");
-		goto rejected;
+		return res;
 	}
 
 	if (prio > TIPC_MAX_LINK_PRI && prio != TIPC_MEDIA_LINK_PRI) {

2.35.1

From: Leo Yan <[email protected]>

[ Upstream commit b24192a17337abbf3f44aaa75e15df14a2d0016e ]

The function percent_rmt_hitm_cmp() wrongly uses local HITMs for sorting remote HITMs.

Since this function is to sort cache lines for remote HITMs, this patch changes to use 'rmt_hitm' field for correct sorting.

---
 tools/perf/builtin-c2c.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

index d3e0ea06d78d..29d460c30176 100644
@@ -953,8 +953,8 @@ percent_rmt_hitm_cmp(struct perf_hpp_fmt *fmt __maybe_unused,
 	double per_left;
 	double per_right;
 
-	per_left  = PERCENT(left, lcl_hitm);
-	per_right = PERCENT(right, lcl_hitm);
+	per_left  = PERCENT(left, rmt_hitm);
+	per_right = PERCENT(right, rmt_hitm);
 
 	return per_left - per_right;
 }

2.35.1

From: Gong Yuanjun <[email protected]>

[ Upstream commit 4107fa700f314592850e2c64608f6ede4c077476 ]

Add the missing of_node_put() to release the refcount incremented by of_find_compatible_node().

---
 arch/mips/kernel/mips-cpc.c | 1 +
 1 file changed, 1 insertion(+)

index 69e3e0b556bf..1b0d4bb617a9 100644
@@ -27,6 +27,7 @@ phys_addr_t __weak mips_cpc_default_phys_base(void)
 	cpc_node = of_find_compatible_node(of_root, NULL, "mti,mips-cpc");
 	if (cpc_node) {
 		err = of_address_to_resource(cpc_node, 0, &res);
+		of_node_put(cpc_node);
 		if (!err)
 			return res.start;
 	}

2.35.1

From: Jun Miao <[email protected]>

[ Upstream commit 12025abdc8539ed9d5014e2d647a3fd1bd3de5cd ]

When setting bootparams="trace_event=initcall:initcall_start tp_printk=1" in the cmdline, the output_printk() was called, and the spin_lock_irqsave() was called in the atomic and irq disable interrupt context suitation. On the PREEMPT_RT kernel, these locks are replaced with sleepable rt-spinlock, so the stack calltrace will be triggered.
Fix it by raw_spin_lock_irqsave when PREEMPT_RT and "trace_event=initcall:initcall_start tp_printk=1" enabled.

 BUG: sleeping function called from invalid context at kernel/locking/spinlock_rt.c:46
 in_atomic(): 1, irqs_disabled(): 0, non_block: 0, pid: 1, name: swapper/0
 preempt_count: 2, expected: 0
 RCU nest depth: 0, expected: 0
 Preemption disabled at:
 [<ffffffff8992303e>] try_to_wake_up+0x7e/0xba0
 CPU: 0 PID: 1 Comm: swapper/0 Not tainted 5.17.1-rt17+ #19 34c5812404187a875f32bee7977f7367f9679ea7
 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.14.0-2 04/01/2014
 Call Trace:
  <TASK>
  dump_stack_lvl+0x60/0x8c
  dump_stack+0x10/0x12
  __might_resched.cold+0x11d/0x155
  rt_spin_lock+0x40/0x70
  trace_event_buffer_commit+0x2fa/0x4c0
  ? map_vsyscall+0x93/0x93
  trace_event_raw_event_initcall_start+0xbe/0x110
  ? perf_trace_initcall_finish+0x210/0x210
  ? probe_sched_wakeup+0x34/0x40
  ? ttwu_do_wakeup+0xda/0x310
  ? trace_hardirqs_on+0x35/0x170
  ? map_vsyscall+0x93/0x93
  do_one_initcall+0x217/0x3c0
  ? trace_event_raw_event_initcall_level+0x170/0x170
  ? push_cpu_stop+0x400/0x400
  ? cblist_init_generic+0x241/0x290
  kernel_init_freeable+0x1ac/0x347
  ? _raw_spin_unlock_irq+0x65/0x80
  ? rest_init+0xf0/0xf0
  kernel_init+0x1e/0x150
  ret_from_fork+0x22/0x30
  </TASK>

---
 kernel/trace/trace.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

index 56619766e910..ce9165de019c 100644
@@ -2537,7 +2537,7 @@ trace_event_buffer_lock_reserve(struct ring_buffer **current_rb,
 }
 EXPORT_SYMBOL_GPL(trace_event_buffer_lock_reserve);
 
-static DEFINE_SPINLOCK(tracepoint_iter_lock);
+static DEFINE_RAW_SPINLOCK(tracepoint_iter_lock);
 static DEFINE_MUTEX(tracepoint_printk_mutex);
 
 static void output_printk(struct trace_event_buffer *fbuffer)

@@ -2558,14 +2558,14 @@ static void output_printk(struct trace_event_buffer *fbuffer)
 
 	event = &fbuffer->trace_file->event_call->event;
 
-	spin_lock_irqsave(&tracepoint_iter_lock, flags);
+	raw_spin_lock_irqsave(&tracepoint_iter_lock, flags);
 	trace_seq_init(&iter->seq);
 	iter->ent = fbuffer->entry;
 	event_call->event.funcs->trace(iter, 0, event);
 	trace_seq_putc(&iter->seq, 0);
 	printk("%s", iter->seq.buffer);
 
-	spin_unlock_irqrestore(&tracepoint_iter_lock, flags);
+	raw_spin_unlock_irqrestore(&tracepoint_iter_lock, flags);
 }
 
 int tracepoint_printk_sysctl(struct ctl_table *table, int write,

2.35.1

From: Mark-PK Tsai <[email protected]>

[ Upstream commit ef9188bcc6ca1d8a2ad83e826b548e6820721061 ]

To prepare for support asynchronous tracer_init_tracefs initcall, avoid calling create_trace_option_files before __update_tracer_options. Otherwise, create_trace_option_files will show warning because some tracers in trace_types list are already in tr->topts.

For example, hwlat_tracer call register_tracer in late_initcall, and global_trace.dir is already created in tracing_init_dentry, hwlat_tracer will be put into tr->topts.
Then if the __update_tracer_options is executed after hwlat_tracer registered, create_trace_option_files find that hwlat_tracer is already in tr->topts.

---
 kernel/trace/trace.c | 7 +++++++
 1 file changed, 7 insertions(+)

index ce9165de019c..55da88f18342 100644
@@ -5638,12 +5638,18 @@ static void tracing_set_nop(struct trace_array *tr)
 	tr->current_trace = &nop_trace;
 }
 
+static bool tracer_options_updated;
+
 static void add_tracer_options(struct trace_array *tr, struct tracer *t)
 {
 	/* Only enable if the directory has been created already. */
 	if (!tr->dir)
 		return;
 
+	/* Only create trace option files after update_tracer_options finish */
+	if (!tracer_options_updated)
+		return;
+
 	create_trace_option_files(tr, t);
 }
 

@@ -8391,6 +8397,7 @@ static void __update_tracer_options(struct trace_array *tr)
 static void update_tracer_options(struct trace_array *tr)
 {
 	mutex_lock(&trace_types_lock);
+	tracer_options_updated = true;
 	__update_tracer_options(tr);
 	mutex_unlock(&trace_types_lock);
 }

2.35.1

From: Dongliang Mu <[email protected]>

[ Upstream commit dc2f78e2d4cc844a1458653d57ce1b54d4a29f21 ]

Syzbot triggers two WARNs in f2fs_is_valid_blkaddr and __is_bitmap_valid. For example, in f2fs_is_valid_blkaddr, if type is DATA_GENERIC_ENHANCE or DATA_GENERIC_ENHANCE_READ, it invokes WARN_ON if blkaddr is not in the right range. The call trace is as follows:

 f2fs_get_node_info+0x45f/0x1070
 read_node_page+0x577/0x1190
 __get_node_page.part.0+0x9e/0x10e0
 __get_node_page
 f2fs_get_node_page+0x109/0x180
 do_read_inode
 f2fs_iget+0x2a5/0x58b0
 f2fs_fill_super+0x3b39/0x7ca0

Fix these two WARNs by replacing WARN_ON with dump_stack.

---
 fs/f2fs/checkpoint.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

index 54f0d2c4c7d8..44c5110e18f0 100644
@@ -149,7 +149,7 @@ static bool __is_bitmap_valid(struct f2fs_sb_info *sbi, block_t blkaddr,
 		f2fs_err(sbi, "Inconsistent error blkaddr:%u, sit bitmap:%d",
 			 blkaddr, exist);
 		set_sbi_flag(sbi, SBI_NEED_FSCK);
-		WARN_ON(1);
+		dump_stack();
 	}
 	return exist;
 }

@@ -187,7 +187,7 @@ bool f2fs_is_valid_blkaddr(struct f2fs_sb_info *sbi,
 			f2fs_warn(sbi, "access invalid blkaddr:%u",
 				  blkaddr);
 			set_sbi_flag(sbi, SBI_NEED_FSCK);
-			WARN_ON(1);
+			dump_stack();
 			return false;
 		} else {
 			return __is_bitmap_valid(sbi, blkaddr, type);

2.35.1

From: Lucas Tanure <[email protected]>

[ Upstream commit 96789dce043f5bff8b7d62aa28d52a7c59403a84 ]

Timeout as 1 second sets an upper limit on the length of the transfer executed, but there is no maximum length of a write or read message set in i2c_adapter_quirks for this controller.

This upper limit affects devices that require sending large firmware blobs over I2C.

To remove that limitation, calculate the minimal time necessary, plus some wiggle room, for every message and use it instead of the default one second, if more than one second.

---
 drivers/i2c/busses/i2c-cadence.c | 12 ++++++++++--
 1 file changed, 10 insertions(+), 2 deletions(-)

index 17f0dd1f891e..8a3a0991bc1c 100644
@@ -506,7 +506,7 @@ static void cdns_i2c_master_reset(struct i2c_adapter *adap)
 static int cdns_i2c_process_msg(struct cdns_i2c *id, struct i2c_msg *msg,
 		struct i2c_adapter *adap)
 {
-	unsigned long time_left;
+	unsigned long time_left, msg_timeout;
 	u32 reg;
 
 	id->p_msg = msg;

@@ -531,8 +531,16 @@ static int cdns_i2c_process_msg(struct cdns_i2c *id, struct i2c_msg *msg,
 	else
 		cdns_i2c_msend(id);
 
+	/* Minimal time to execute this message */
+	msg_timeout = msecs_to_jiffies((1000 * msg->len * BITS_PER_BYTE) / id->i2c_clk);
+	/* Plus some wiggle room */
+	msg_timeout += msecs_to_jiffies(500);
+
+	if (msg_timeout < adap->timeout)
+		msg_timeout = adap->timeout;
+
 	/* Wait for the signal of completion */
-	time_left = wait_for_completion_timeout(&id->xfer_done, adap->timeout);
+	time_left = wait_for_completion_timeout(&id->xfer_done, msg_timeout);
 	if (time_left == 0) {
 		cdns_i2c_master_reset(adap);
 		dev_err(id->adap.dev.parent,

2.35.1

From: Greg Ungerer <[email protected]>

[ Upstream commit dc068f46217970d9516f16cd37972a01d50dc055 ]

The non-MMU m68k pagetable ZERO_PAGE() macro is being set to the somewhat non-sensical value of "virt_to_page(0)". The zeroth page is not in any way guaranteed to be a page full of "0". So the result is that ZERO_PAGE() will almost certainly contain random values.

We already allocate a real "empty_zero_page" in the mm setup code shared between MMU m68k and non-MMU m68k. It is just not hooked up to the ZERO_PAGE() macro for the non-MMU m68k case.

Fix ZERO_PAGE() to use the allocated "empty_zero_page" pointer.

I am not aware of any specific issues caused by the old code.

---
 arch/m68k/include/asm/pgtable_no.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

index c18165b0d904..6b0248466569 100644
@@ -42,7 +42,8 @@ extern void paging_init(void);
  * ZERO_PAGE is a global shared page that is always zero: used
  * for zero-mapped memory areas etc..
  */
-#define ZERO_PAGE(vaddr)	(virt_to_page(0))
+extern void *empty_zero_page;
+#define ZERO_PAGE(vaddr)	(virt_to_page(empty_zero_page))
 
 /*
  * All 32bit addresses are effectively valid for vmalloc...

2.35.1

From: Greg Ungerer <[email protected]>

[ Upstream commit a71b9e66fee47c59b3ec34e652b5c23bc6550794 ]

When configuring a nommu classic m68k system enabling the uboot parameter passing support (CONFIG_UBOOT) will produce the following compile error:

m68k-linux-ld: arch/m68k/kernel/uboot.o: in function `process_uboot_commandline':
uboot.c:(.init.text+0x32): undefined reference to `_init_sp'

The logic to support this option is only used on ColdFire based platforms (in its head.S startup code). So make the selection of this option depend on building for a ColdFire based platform.

---
 arch/m68k/Kconfig.machine | 1 +
 1 file changed, 1 insertion(+)

index b88a980f56f8..f0527b155c05 100644
@@ -320,6 +320,7 @@ comment "Machine Options"
 
 config UBOOT
 	bool "Support for U-Boot command line parameters"
+	depends on COLDFIRE
 	help
 	  If you say Y here kernel will try to collect command
 	  line parameters from the initial u-boot stack.

2.35.1

From: Radhey Shyam Pandey <[email protected]>

[ Upstream commit f9a9f43a62a04ec3183fb0da9226c7706eed0115 ]

In zynqmp_dma_alloc/free_chan_resources functions there is a potential overflow in the below expressions.

dma_alloc_coherent(chan->dev, (2 * chan->desc_size *

		   ZYNQMP_DMA_NUM_DESCS),
		   &chan->desc_pool_p, GFP_KERNEL);

dma_free_coherent(chan->dev,(2 * ZYNQMP_DMA_DESC_SIZE(chan) *

                 ZYNQMP_DMA_NUM_DESCS),
                chan->desc_pool_v, chan->desc_pool_p);

The arguments desc_size and ZYNQMP_DMA_NUM_DESCS were 32 bit. Though this overflow condition is not observed but it is a potential problem in the case of 32-bit multiplication. Hence fix it by changing the desc_size data type to size_t.

In addition to coverity fix it also reuse ZYNQMP_DMA_DESC_SIZE macro in dma_alloc_coherent API argument.

Addresses-Coverity: Event overflow_before_widen.

---
 drivers/dma/xilinx/zynqmp_dma.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

index 84009c5e0f33..b61d0c79dffb 100644
@@ -232,7 +232,7 @@ struct zynqmp_dma_chan {
 	bool is_dmacoherent;
 	struct tasklet_struct tasklet;
 	bool idle;
-	u32 desc_size;
+	size_t desc_size;
 	bool err;
 	u32 bus_width;
 	u32 src_burst_len;

@@ -489,7 +489,8 @@ static int zynqmp_dma_alloc_chan_resources(struct dma_chan *dchan)
 	}
 
 	chan->desc_pool_v = dma_alloc_coherent(chan->dev,
-					       (2 * chan->desc_size * ZYNQMP_DMA_NUM_DESCS),
+					       (2 * ZYNQMP_DMA_DESC_SIZE(chan) *
+					       ZYNQMP_DMA_NUM_DESCS),
 					       &chan->desc_pool_p, GFP_KERNEL);
 	if (!chan->desc_pool_v)
 		return -ENOMEM;

2.35.1

From: Trond Myklebust <[email protected]>

[ Upstream commit 6949493884fe88500de4af182588e071cf1544ee ]

When doing layoutget as part of the open() compound, we have to be careful to release the layout locks before we can call any further RPC calls, such as setattr(). The reason is that those calls could trigger a recall, which could deadlock.

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

index cf3b00751ff6..ba4a03a69fbf 100644
@@ -3041,6 +3041,10 @@ static int _nfs4_open_and_get_state(struct nfs4_opendata *opendata,
 	}
 
 out:
+	if (opendata->lgp) {
+		nfs4_lgopen_release(opendata->lgp);
+		opendata->lgp = NULL;
+	}
 	if (!opendata->cancelled)
 		nfs4_sequence_free_slot(&opendata->o_res.seq_res);
 	return ret;

2.35.1

From: Yang Yingliang <[email protected]>

[ Upstream commit d87ad457f7e1b8d2492ca5b1531eb35030a1cc8f ]

In pxa3xx_gcu_probe(), the sequence of error lable is wrong, it will leads some resource leaked, so adjust the sequence to handle the error correctly, and if pxa3xx_gcu_add_buffer() fails, pxa3xx_gcu_free_buffers() need be called.
In pxa3xx_gcu_remove(), add missing clk_disable_unpreprare().

---
 drivers/video/fbdev/pxa3xx-gcu.c | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

index 74ffb446e00c..7c4694d70dac 100644
@@ -651,6 +651,7 @@ static int pxa3xx_gcu_probe(struct platform_device *pdev)
 	for (i = 0; i < 8; i++) {
 		ret = pxa3xx_gcu_add_buffer(dev, priv);
 		if (ret) {
+			pxa3xx_gcu_free_buffers(dev, priv);
 			dev_err(dev, "failed to allocate DMA memory\n");
 			goto err_disable_clk;
 		}

@@ -667,15 +668,15 @@ static int pxa3xx_gcu_probe(struct platform_device *pdev)
 			SHARED_SIZE, irq);
 	return 0;
 
-err_free_dma:
-	dma_free_coherent(dev, SHARED_SIZE,
-			priv->shared, priv->shared_phys);
+err_disable_clk:
+	clk_disable_unprepare(priv->clk);
 
 err_misc_deregister:
 	misc_deregister(&priv->misc_dev);
 
-err_disable_clk:
-	clk_disable_unprepare(priv->clk);
+err_free_dma:
+	dma_free_coherent(dev, SHARED_SIZE,
+			  priv->shared, priv->shared_phys);
 
 	return ret;
 }

@@ -688,6 +689,7 @@ static int pxa3xx_gcu_remove(struct platform_device *pdev)
 	pxa3xx_gcu_wait_idle(priv);
 	misc_deregister(&priv->misc_dev);
 	dma_free_coherent(dev, SHARED_SIZE, priv->shared, priv->shared_phys);
+	clk_disable_unprepare(priv->clk);
 	pxa3xx_gcu_free_buffers(dev, priv);
 
 	return 0;

2.35.1

From: Kinglong Mee <[email protected]>

[ Upstream commit 11270e7ca268e8d61b5d9e5c3a54bd1550642c9c ]

When a rdma server returns a fault format reply, nfs v3 client may treats it as a bcall when bc service is not exist.

The debug message at rpcrdma_bc_receive_call are,

[56579.837169] RPC:       rpcrdma_bc_receive_call: callback XID
00000001, length=20
[56579.837174] RPC:       rpcrdma_bc_receive_call: 00 00 00 01 00 00 00

00 00 00 00 00 00 00 00 00 00 00 00 04

After that, rpcrdma_bc_receive_call will meets NULL pointer as,

[  226.057890] BUG: unable to handle kernel NULL pointer dereference at
00000000000000c8
...
[  226.058704] RIP: 0010:_raw_spin_lock+0xc/0x20
...
[  226.059732] Call Trace:
[  226.059878]  rpcrdma_bc_receive_call+0x138/0x327 [rpcrdma]
[  226.060011]  __ib_process_cq+0x89/0x170 [ib_core]
[  226.060092]  ib_cq_poll_work+0x26/0x80 [ib_core]
[  226.060257]  process_one_work+0x1a7/0x360
[  226.060367]  ? create_worker+0x1a0/0x1a0
[  226.060440]  worker_thread+0x30/0x390
[  226.060500]  ? create_worker+0x1a0/0x1a0
[  226.060574]  kthread+0x116/0x130
[  226.060661]  ? kthread_flush_work_fn+0x10/0x10
[  226.060724]  ret_from_fork+0x35/0x40

...

---
 net/sunrpc/xprtrdma/rpc_rdma.c | 5 +++++
 1 file changed, 5 insertions(+)

index c091417bd799..60aaed9457e4 100644
@@ -1042,6 +1042,7 @@ static bool
 rpcrdma_is_bcall(struct rpcrdma_xprt *r_xprt, struct rpcrdma_rep *rep)
 #if defined(CONFIG_SUNRPC_BACKCHANNEL)
 {
+	struct rpc_xprt *xprt = &r_xprt->rx_xprt;
 	struct xdr_stream *xdr = &rep->rr_stream;
 	__be32 *p;
 

@@ -1065,6 +1066,10 @@ rpcrdma_is_bcall(struct rpcrdma_xprt *r_xprt, struct rpcrdma_rep *rep)
 	if (*p != cpu_to_be32(RPC_CALL))
 		return false;
 
+	/* No bc service. */
+	if (xprt->bc_serv == NULL)
+		return false;
+
 	/* Now that we are sure this is a backchannel call,
 	 * advance to the RPC header.
 	 */

2.35.1

From: Florian Westphal <[email protected]>

[ Upstream commit 282e5f8fe907dc3f2fbf9f2103b0e62ffc3a68a5 ]

When no l3 address is given, priv->family is set to NFPROTO_INET and the evaluation function isn't called.

Call it too so l4-only rewrite can work.
Also add a test case for this.

---
 net/netfilter/nft_nat.c                      |  3 +-
 tools/testing/selftests/netfilter/nft_nat.sh | 43 ++++++++++++++++++++
 2 files changed, 45 insertions(+), 1 deletion(-)

index 17c0f75dfcdb..0c5bc3c37ecf 100644
@@ -283,7 +283,8 @@ static void nft_nat_inet_eval(const struct nft_expr *expr,
 {
 	const struct nft_nat *priv = nft_expr_priv(expr);
 
-	if (priv->family == nft_pf(pkt))
+	if (priv->family == nft_pf(pkt) ||
+	    priv->family == NFPROTO_INET)
 		nft_nat_eval(expr, regs, pkt);
 }
 

2.35.1

From: Miaoqian Lin <[email protected]>

[ Upstream commit 10d6bdf532902be1d8aa5900b3c03c5671612aa2 ]

of_find_device_by_node() takes reference, we should use put_device() to release it when not need anymore.
Add missing put_device() to avoid refcount leak.

---
 drivers/ata/pata_octeon_cf.c | 3 +++
 1 file changed, 3 insertions(+)

index ac3b1fda820f..c240d8cbfd41 100644
@@ -888,12 +888,14 @@ static int octeon_cf_probe(struct platform_device *pdev)
 				int i;
 				res_dma = platform_get_resource(dma_dev, IORESOURCE_MEM, 0);
 				if (!res_dma) {
+					put_device(&dma_dev->dev);
 					of_node_put(dma_node);
 					return -EINVAL;
 				}
 				cf_port->dma_base = (u64)devm_ioremap_nocache(&pdev->dev, res_dma->start,
 									 resource_size(res_dma));
 				if (!cf_port->dma_base) {
+					put_device(&dma_dev->dev);
 					of_node_put(dma_node);
 					return -EINVAL;
 				}

@@ -903,6 +905,7 @@ static int octeon_cf_probe(struct platform_device *pdev)
 					irq = i;
 					irq_handler = octeon_cf_interrupt;
 				}
+				put_device(&dma_dev->dev);
 			}
 			of_node_put(dma_node);
 		}

2.35.1

From: Pablo Neira Ayuso <[email protected]>

[ Upstream commit 9dd732e0bdf538b1b76dc7c157e2b5e560ff30d3 ]

Abort path release flow rule object, however, commit path does not. Update code to destroy these objects before releasing the transaction.

---
 net/netfilter/nf_tables_api.c | 6 ++++++
 1 file changed, 6 insertions(+)

index b51c192105fc..58a7d89719b1 100644
@@ -6570,6 +6570,9 @@ static void nft_commit_release(struct nft_trans *trans)
 		nf_tables_chain_destroy(&trans->ctx);
 		break;
 	case NFT_MSG_DELRULE:
+		if (trans->ctx.chain->flags & NFT_CHAIN_HW_OFFLOAD)
+			nft_flow_rule_destroy(nft_trans_flow_rule(trans));
+
 		nf_tables_rule_destroy(&trans->ctx, nft_trans_rule(trans));
 		break;
 	case NFT_MSG_DELSET:

@@ -6891,6 +6894,9 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb)
 			nf_tables_rule_notify(&trans->ctx,
 					      nft_trans_rule(trans),
 					      NFT_MSG_NEWRULE);
+			if (trans->ctx.chain->flags & NFT_CHAIN_HW_OFFLOAD)
+				nft_flow_rule_destroy(nft_trans_flow_rule(trans));
+
 			nft_trans_destroy(trans);
 			break;
 		case NFT_MSG_DELRULE:

2.35.1

From: Masahiro Yamada <[email protected]>

[ Upstream commit dbac14a5a05ff8e1ce7c0da0e1f520ce39ec62ea ]

EXPORT_SYMBOL and __init is a bad combination because the .init.text section is freed up after the initialization. Hence, modules cannot use symbols annotated __init. The access to a freed symbol may end up with kernel panic.

modpost used to detect it, but it has been broken for a decade.

Recently, I fixed modpost so it started to warn it again, then this showed up in linux-next builds.

There are two ways to fix it:

- Remove __init
- Remove EXPORT_SYMBOL

I chose the latter for this case because none of the in-tree call-sites (arch/arm/xen/enlighten.c, arch/x86/xen/grant-table.c) is compiled as modular.

---
 drivers/xen/xlate_mmu.c | 1 -
 1 file changed, 1 deletion(-)

index 7b1077f0abcb..c8aa4f5f85db 100644
@@ -261,7 +261,6 @@ int __init xen_xlate_map_ballooned_pages(xen_pfn_t **gfns, void **virt,
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(xen_xlate_map_ballooned_pages);
 
 struct remap_pfn {
 	struct mm_struct *mm;

2.35.1

From: Kuniyuki Iwashima <[email protected]>

[ Upstream commit 662a80946ce13633ae90a55379f1346c10f0c432 ]

unix_dgram_poll() calls unix_dgram_peer_wake_me() without other's lock held and check if its receive queue is full. Here we need to use unix_recvq_full_lockless() instead of unix_recvq_full(), otherwise KCSAN will report a data-race.

---
 net/unix/af_unix.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index 05470ca91bd9..f33e90bd0683 100644
@@ -440,7 +440,7 @@ static int unix_dgram_peer_wake_me(struct sock *sk, struct sock *other)
 	 * -ECONNREFUSED. Otherwise, if we haven't queued any skbs
 	 * to other and its full, we will hang waiting for POLLOUT.
 	 */
-	if (unix_recvq_full(other) && !sock_flag(other, SOCK_DEAD))
+	if (unix_recvq_full_lockless(other) && !sock_flag(other, SOCK_DEAD))
 		return 1;
 
 	if (connected)

2.35.1

From: Eric Dumazet <[email protected]>

[ Upstream commit 10f3b29c65bb2fe0d47c2945cd0b4087be1c5218 ]

syzbot reported an illegal copy_to_user() attempt
from bpf_prog_get_info_by_fd() [1]

There was no repro yet on this bug, but I think
that commit 0aef499f3172 ("mm/usercopy: Detect vmalloc overruns") is exposing a prior bug in bpf arm64.

bpf_prog_get_info_by_fd() looks at prog->jited_len to determine if the JIT image can be copied out to user space.

My theory is that syzbot managed to get a prog where prog->jited_len has been set to 43, while prog->bpf_func has ben cleared.

It is not clear why copy_to_user(uinsns, NULL, ulen) is triggering this particular warning.

I thought find_vma_area(NULL) would not find a vm_struct. As we do not hold vmap_area_lock spinlock, it might be possible that the found vm_struct was garbage.

[1]
usercopy: Kernel memory exposure attempt detected from vmalloc (offset 792633534417210172, size 43)! kernel BUG at mm/usercopy.c:101!

Internal error: Oops - BUG: 0 [#1] PREEMPT SMP
Modules linked in:
CPU: 0 PID: 25002 Comm: syz-executor.1 Not tainted 5.18.0-syzkaller-10139-g8291eaafed36 #0
Hardware name: linux,dummy-virt (DT)
pstate: 60400009 (nZCv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--)
pc : usercopy_abort+0x90/0x94 mm/usercopy.c:101
lr : usercopy_abort+0x90/0x94 mm/usercopy.c:89

sp : ffff80000b773a20
x29: ffff80000b773a30 x28: faff80000b745000 x27: ffff80000b773b48
x26: 0000000000000000 x25: 000000000000002b x24: 0000000000000000
x23: 00000000000000e0 x22: ffff80000b75db67 x21: 0000000000000001
x20: 000000000000002b x19: ffff80000b75db3c x18: 00000000fffffffd
x17: 2820636f6c6c616d x16: 76206d6f72662064 x15: 6574636574656420
x14: 74706d6574746120 x13: 2129333420657a69 x12: 73202c3237313031
x11: 3237313434333533 x10: 3336323937207465 x9 : 657275736f707865 x8 : ffff80000a30c550 x7 : ffff80000b773830 x6 : ffff80000b773830 x5 : 0000000000000000 x4 : ffff00007fbbaa10 x3 : 0000000000000000 x2 : 0000000000000000 x1 : f7ff000028fc0000 x0 : 0000000000000064

Call trace:
 usercopy_abort+0x90/0x94 mm/usercopy.c:89
 check_heap_object mm/usercopy.c:186 [inline]
 __check_object_size mm/usercopy.c:252 [inline]
 __check_object_size+0x198/0x36c mm/usercopy.c:214
 check_object_size include/linux/thread_info.h:199 [inline]
 check_copy_size include/linux/thread_info.h:235 [inline]
 copy_to_user include/linux/uaccess.h:159 [inline]
 bpf_prog_get_info_by_fd.isra.0+0xf14/0xfdc kernel/bpf/syscall.c:3993
 bpf_obj_get_info_by_fd+0x12c/0x510 kernel/bpf/syscall.c:4253
 __sys_bpf+0x900/0x2150 kernel/bpf/syscall.c:4956
 __do_sys_bpf kernel/bpf/syscall.c:5021 [inline]
 __se_sys_bpf kernel/bpf/syscall.c:5019 [inline]
 __arm64_sys_bpf+0x28/0x40 kernel/bpf/syscall.c:5019
 __invoke_syscall arch/arm64/kernel/syscall.c:38 [inline]
 invoke_syscall+0x48/0x114 arch/arm64/kernel/syscall.c:52
 el0_svc_common.constprop.0+0x44/0xec arch/arm64/kernel/syscall.c:142
 do_el0_svc+0xa0/0xc0 arch/arm64/kernel/syscall.c:206
 el0_svc+0x44/0xb0 arch/arm64/kernel/entry-common.c:624
 el0t_64_sync_handler+0x1ac/0x1b0 arch/arm64/kernel/entry-common.c:642
 el0t_64_sync+0x198/0x19c arch/arm64/kernel/entry.S:581
Code: aa0003e3 d00038c0 91248000 97fff65f (d4210000)

---
 arch/arm64/net/bpf_jit_comp.c | 1 +
 1 file changed, 1 insertion(+)

index 17a8d1484f9b..9f71ca441482 100644
@@ -973,6 +973,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 			bpf_jit_binary_free(header);
 			prog->bpf_func = NULL;
 			prog->jited = 0;
+			prog->jited_len = 0;
 			goto out_off;
 		}
 		bpf_jit_binary_lock_ro(header);

2.35.1

From: Miaoqian Lin <[email protected]>

[ Upstream commit 0737e018a05e2aa352828c52bdeed3b02cff2930 ]

Every iteration of for_each_available_child_of_node() decrements the reference count of the previous node.
when breaking early from a for_each_available_child_of_node() loop, we need to explicitly call of_node_put() on the gphy_fw_np. Add missing of_node_put() to avoid refcount leak.

---
 drivers/net/dsa/lantiq_gswip.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

index 0c191d395f8f..b546002e5fd4 100644
@@ -1958,8 +1958,10 @@ static int gswip_gphy_fw_list(struct gswip_priv *priv,
 	for_each_available_child_of_node(gphy_fw_list_np, gphy_fw_np) {
 		err = gswip_gphy_fw_probe(priv, &priv->gphy_fw[i],
 					  gphy_fw_np, i);
-		if (err)
+		if (err) {
+			of_node_put(gphy_fw_np);
 			goto remove_gphy;
+		}
 		i++;
 	}
 

2.35.1

From: Gal Pressman <[email protected]>

[ Upstream commit f5826c8c9d57210a17031af5527056eefdc2b7eb ]

The ioctl EEPROM query wrongly returns success on read failures, fix that by returning the appropriate error code.

---
 drivers/net/ethernet/mellanox/mlx4/en_ethtool.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index dd029d91bbc2..b711148a9d50 100644
@@ -2083,7 +2083,7 @@ static int mlx4_en_get_module_eeprom(struct net_device *dev,
 			en_err(priv,
 			       "mlx4_get_module_info i(%d) offset(%d) bytes_to_read(%d) - FAILED (0x%x)\n",
 			       i, offset, ee->len - i, ret);
-			return 0;
+			return ret;
 		}
 
 		i += ret;

2.35.1

From: Chuck Lever <[email protected]>

[ Upstream commit 6c254bf3b637dd4ef4f78eb78c7447419c0161d7 ]

I found that NFSD's new NFSv3 READDIRPLUS XDR encoder was screwing up right at the end of the page array. xdr_get_next_encode_buffer() does not compute the value of xdr->end correctly:

* The check to see if we're on the final available page in xdr->buf needs to account for the space consumed by @nbytes.

* The new xdr->end value needs to account for the portion of @nbytes that is to be encoded into the previous buffer.

---
 net/sunrpc/xdr.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

index 7ef37054071f..cb8740d15633 100644
@@ -608,7 +608,11 @@ static __be32 *xdr_get_next_encode_buffer(struct xdr_stream *xdr,
 	 */
 	xdr->p = (void *)p + frag2bytes;
 	space_left = xdr->buf->buflen - xdr->buf->len;
-	xdr->end = (void *)p + min_t(int, space_left, PAGE_SIZE);
+	if (space_left - nbytes >= PAGE_SIZE)
+		xdr->end = (void *)p + PAGE_SIZE;
+	else
+		xdr->end = (void *)p + space_left - frag1bytes;
+
 	xdr->buf->page_len += frag2bytes;
 	xdr->buf->len += nbytes;
 	return p;

2.35.1

From: Masahiro Yamada <[email protected]>

[ Upstream commit 35b42dce619701f1300fb8498dae82c9bb1f0263 ]

EXPORT_SYMBOL and __init is a bad combination because the .init.text section is freed up after the initialization. Hence, modules cannot use symbols annotated __init. The access to a freed symbol may end up with kernel panic.

modpost used to detect it, but it has been broken for a decade.

Recently, I fixed modpost so it started to warn it again, then this showed up in linux-next builds.

There are two ways to fix it:

- Remove __init
- Remove EXPORT_SYMBOL

I chose the latter for this case because the only in-tree call-site, drivers/net/phy/phy_device.c is never compiled as modular. (CONFIG_PHYLIB is boolean)

---
 drivers/net/phy/mdio_bus.c | 1 -
 1 file changed, 1 deletion(-)

index b0a439248ff6..05c24db507a2 100644
@@ -753,7 +753,6 @@ int __init mdio_bus_init(void)
 
 	return ret;
 }
-EXPORT_SYMBOL_GPL(mdio_bus_init);
 
 #if IS_ENABLED(CONFIG_PHYLIB)
 void mdio_bus_exit(void)

2.35.1

From: Masahiro Yamada <[email protected]>

[ Upstream commit 4a388f08d8784af48f352193d2b72aaf167a57a1 ]

EXPORT_SYMBOL and __init is a bad combination because the .init.text section is freed up after the initialization. Hence, modules cannot use symbols annotated __init. The access to a freed symbol may end up with kernel panic.

modpost used to detect it, but it has been broken for a decade.

Recently, I fixed modpost so it started to warn it again, then this showed up in linux-next builds.

There are two ways to fix it:

- Remove __init
- Remove EXPORT_SYMBOL

I chose the latter for this case because the only in-tree call-site, net/ipv4/xfrm4_policy.c is never compiled as modular. (CONFIG_XFRM is boolean)

---
 net/ipv4/xfrm4_protocol.c | 1 -
 1 file changed, 1 deletion(-)

index 8a4285712808..9031b7732fec 100644
@@ -298,4 +298,3 @@ void __init xfrm4_protocol_init(void)
 {
 	xfrm_input_register_afinfo(&xfrm4_input_afinfo);
 }
-EXPORT_SYMBOL(xfrm4_protocol_init);

2.35.1

From: Masahiro Yamada <[email protected]>

[ Upstream commit 5801f064e35181c71857a80ff18af4dbec3c5f5c ]

EXPORT_SYMBOL and __init is a bad combination because the .init.text section is freed up after the initialization. Hence, modules cannot use symbols annotated __init. The access to a freed symbol may end up with kernel panic.

modpost used to detect it, but it has been broken for a decade.

Recently, I fixed modpost so it started to warn it again, then this showed up in linux-next builds.

There are two ways to fix it:

- Remove __init
- Remove EXPORT_SYMBOL

I chose the latter for this case because the caller (net/ipv6/seg6.c) and the callee (net/ipv6/seg6_hmac.c) belong to the same module. It seems an internal function call in ipv6.ko.

---
 net/ipv6/seg6_hmac.c | 1 -
 1 file changed, 1 deletion(-)

index ffcfcd2b128f..a4cad71c4204 100644
@@ -401,7 +401,6 @@ int __init seg6_hmac_init(void)
 {
 	return seg6_hmac_init_algo();
 }
-EXPORT_SYMBOL(seg6_hmac_init);
 
 int __net_init seg6_hmac_net_init(struct net *net)
 {

2.35.1

From: Feras Daoud <[email protected]>

[ Upstream commit 8bf94e6414c9481bfa28269022688ab445d0081d ]

The current design does not arm the tracer if traces are available before the tracer string database is fully loaded, leading to an unfunctional tracer. This fix will rearm the tracer every time the FW triggers tracer event regardless of the tracer strings database status.

---
 drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

index 97359417c6e7..f8144ce7e476 100644
@@ -673,6 +673,9 @@ static void mlx5_fw_tracer_handle_traces(struct work_struct *work)
 	if (!tracer->owner)
 		return;
 
+	if (unlikely(!tracer->str_db.loaded))
+		goto arm;
+
 	block_count = tracer->buff.size / TRACER_BLOCK_SIZE_BYTE;
 	start_offset = tracer->buff.consumer_index * TRACER_BLOCK_SIZE_BYTE;
 

@@ -730,6 +733,7 @@ static void mlx5_fw_tracer_handle_traces(struct work_struct *work)
 						      &tmp_trace_block[TRACES_PER_BLOCK - 1]);
 	}
 
+arm:
 	mlx5_fw_tracer_arm(dev);
 }
 

@@ -1084,8 +1088,7 @@ static int fw_tracer_event(struct notifier_block *nb, unsigned long action, void
 			queue_work(tracer->work_queue, &tracer->ownership_change_work);
 		break;
 	case MLX5_TRACER_SUBTYPE_TRACES_AVAILABLE:
-		if (likely(tracer->str_db.loaded))
-			queue_work(tracer->work_queue, &tracer->handle_traces_work);
+		queue_work(tracer->work_queue, &tracer->handle_traces_work);
 		break;
 	default:
 		mlx5_core_dbg(dev, "FWTracer: Event with unrecognized subtype: sub_type %d\n",

2.35.1

From: Mark Bloch <[email protected]>

[ Upstream commit 8fa5e7b20e01042b14f8cd684d2da9b638460c74 ]

When combining two steering rules into one check not only do they share the same actions but those actions are also the same. This resolves an issue where when creating two different rules with the same match the actions are overwritten and one of the rules is deleted a FW syndrome can be seen in dmesg.

mlx5_core 0000:03:00.0: mlx5_cmd_check:819:(pid 2105): DEALLOC_MODIFY_HEADER_CONTEXT(0x941) op_mod(0x0) failed, status bad resource state(0x9), syndrome (0x1ab444)

---
 .../net/ethernet/mellanox/mlx5/core/fs_core.c | 35 +++++++++++++++++--
 1 file changed, 32 insertions(+), 3 deletions(-)

index 8c8b68e7abb4..41087c0618c1 100644
@@ -1450,9 +1450,22 @@ static struct mlx5_flow_rule *find_flow_rule(struct fs_fte *fte,
 	return NULL;
 }
 
-static bool check_conflicting_actions(u32 action1, u32 action2)
+static bool check_conflicting_actions_vlan(const struct mlx5_fs_vlan *vlan0,
+					   const struct mlx5_fs_vlan *vlan1)
 {
-	u32 xored_actions = action1 ^ action2;
+	return vlan0->ethtype != vlan1->ethtype ||
+	       vlan0->vid != vlan1->vid ||
+	       vlan0->prio != vlan1->prio;
+}
+
+static bool check_conflicting_actions(const struct mlx5_flow_act *act1,
+				      const struct mlx5_flow_act *act2)
+{
+	u32 action1 = act1->action;
+	u32 action2 = act2->action;
+	u32 xored_actions;
+
+	xored_actions = action1 ^ action2;
 
 	/* if one rule only wants to count, it's ok */
 	if (action1 == MLX5_FLOW_CONTEXT_ACTION_COUNT ||

@@ -1469,6 +1482,22 @@ static bool check_conflicting_actions(u32 action1, u32 action2)
 			     MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH_2))
 		return true;
 
+	if (action1 & MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT &&
+	    act1->pkt_reformat != act2->pkt_reformat)
+		return true;
+
+	if (action1 & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR &&
+	    act1->modify_hdr != act2->modify_hdr)
+		return true;
+
+	if (action1 & MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH &&
+	    check_conflicting_actions_vlan(&act1->vlan[0], &act2->vlan[0]))
+		return true;
+
+	if (action1 & MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH_2 &&
+	    check_conflicting_actions_vlan(&act1->vlan[1], &act2->vlan[1]))
+		return true;
+
 	return false;
 }
 

@@ -1476,7 +1505,7 @@ static int check_conflicting_ftes(struct fs_fte *fte,
 				  const struct mlx5_flow_context *flow_context,
 				  const struct mlx5_flow_act *flow_act)
 {
-	if (check_conflicting_actions(flow_act->action, fte->action.action)) {
+	if (check_conflicting_actions(flow_act, &fte->action)) {
 		mlx5_core_warn(get_dev(&fte->node),
 			       "Found two FTEs with conflicting actions\n");
 		return -EEXIST;

2.35.1

From: Willem de Bruijn <[email protected]>

[ Upstream commit 8d21e9963bec1aad2280cdd034c8993033ef2948 ]

GRE with TUNNEL_CSUM will apply local checksum offload on CHECKSUM_PARTIAL packets.

ipgre_xmit must validate csum_start after an optional skb_pull, else lco_csum may trigger an overflow. The original check was

	if (csum && skb_checksum_start(skb) < skb->data)
		return -EINVAL;

This had false positives when skb_checksum_start is undefined:
when ip_summed is not CHECKSUM_PARTIAL. A discussed refinement was straightforward

	if (csum && skb->ip_summed == CHECKSUM_PARTIAL &&
	    skb_checksum_start(skb) < skb->data)
		return -EINVAL;

But was eventually revised more thoroughly:
- restrict the check to the only branch where needed, in an uncommon GRE path that uses header_ops and calls skb_pull.
- test skb_transport_header, which is set along with csum_start in skb_partial_csum_set in the normal header_ops datapath.

Turns out skbs can arrive in this branch without the transport header set, e.g., through BPF redirection.

Revise the check back to check csum_start directly, and only if CHECKSUM_PARTIAL. Do leave the check in the updated location. Check field regardless of whether TUNNEL_CSUM is configured.

---
 net/ipv4/ip_gre.c | 11 +++++------
 1 file changed, 5 insertions(+), 6 deletions(-)

index 5b38d03f6d79..614410a6db44 100644
@@ -602,21 +602,20 @@ static netdev_tx_t ipgre_xmit(struct sk_buff *skb,
 	}
 
 	if (dev->header_ops) {
-		const int pull_len = tunnel->hlen + sizeof(struct iphdr);
-
 		if (skb_cow_head(skb, 0))
 			goto free_skb;
 
 		tnl_params = (const struct iphdr *)skb->data;
 
-		if (pull_len > skb_transport_offset(skb))
-			goto free_skb;
-
 		/* Pull skb since ip_tunnel_xmit() needs skb->data pointing
 		 * to gre header.
 		 */
-		skb_pull(skb, pull_len);
+		skb_pull(skb, tunnel->hlen + sizeof(struct iphdr));
 		skb_reset_mac_header(skb);
+
+		if (skb->ip_summed == CHECKSUM_PARTIAL &&
+		    skb_checksum_start(skb) < skb->data)
+			goto free_skb;
 	} else {
 		if (skb_cow_head(skb, dev->needed_headroom))
 			goto free_skb;

2.35.1

From: Miaoqian Lin <[email protected]>

[ Upstream commit 11ec18b1d8d92b9df307d31950dcba0b3dd7283c ]

Every iteration of for_each_child_of_node() decrements the reference count of the previous node.
When break from a for_each_child_of_node() loop,
we need to explicitly call of_node_put() on the child node when not need anymore.
Add missing of_node_put() to avoid refcount leak.

---
 drivers/net/ethernet/altera/altera_tse_main.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

index 1f8c3b669dc1..f36536114790 100644
@@ -163,7 +163,8 @@ static int altera_tse_mdio_create(struct net_device *dev, unsigned int id)
 	mdio = mdiobus_alloc();
 	if (mdio == NULL) {
 		netdev_err(dev, "Error allocating MDIO bus\n");
-		return -ENOMEM;
+		ret = -ENOMEM;
+		goto put_node;
 	}
 
 	mdio->name = ALTERA_TSE_RESOURCE_NAME;

@@ -180,6 +181,7 @@ static int altera_tse_mdio_create(struct net_device *dev, unsigned int id)
 			   mdio->id);
 		goto out_free_mdio;
 	}
+	of_node_put(mdio_node);
 
 	if (netif_msg_drv(priv))
 		netdev_info(dev, "MDIO bus %s: created\n", mdio->id);

@@ -189,6 +191,8 @@ static int altera_tse_mdio_create(struct net_device *dev, unsigned int id)
 out_free_mdio:
 	mdiobus_free(mdio);
 	mdio = NULL;
+put_node:
+	of_node_put(mdio_node);
 	return ret;
 }
 

2.35.1

From: Linus Torvalds <[email protected]>

[ Upstream commit 7aefd8b53815274f3ef398d370a3c9b27dd9f00c ]

Gcc-12 correctly warned about this code using a non-NULL pointer as a truth value:

drivers/gpu/drm/imx/ipuv3-crtc.c: In function ‘ipu_crtc_disable_planes’:
drivers/gpu/drm/imx/ipuv3-crtc.c:72:21: error: the comparison will always evaluate as ‘true’ for the address of ‘plane’ will never be NULL [-Werror=address]

     72 |                 if (&ipu_crtc->plane[1] && plane == &ipu_crtc->plane[1]->base)
        |                     ^

due to the extraneous '&' address-of operator.

Philipp Zabel points out that The mistake had no adverse effect since the following condition doesn't actually dereference the NULL pointer, but the intent of the code was obviously to check for it, not to take the address of the member.

---
 drivers/gpu/drm/imx/ipuv3-crtc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index 2256c9789fc2..f19264e91d4d 100644
@@ -68,7 +68,7 @@ static void ipu_crtc_disable_planes(struct ipu_crtc *ipu_crtc,
 	drm_atomic_crtc_state_for_each_plane(plane, old_crtc_state) {
 		if (plane == &ipu_crtc->plane[0]->base)
 			disable_full = true;
-		if (&ipu_crtc->plane[1] && plane == &ipu_crtc->plane[1]->base)
+		if (ipu_crtc->plane[1] && plane == &ipu_crtc->plane[1]->base)
 			disable_partial = true;
 	}
 

2.35.1

From: Xiaoke Wang <[email protected]>

[ Upstream commit ba93642188a6fed754bf7447f638bc410e05a929 ]

kstrdup() is also a memory allocation-related function, it returns NULL when some memory errors happen. So it is better to check the return value of it so to catch the memory error in time. Besides, there should have a kfree() to clear up the allocation if we get a failure later in this function to prevent memory leak.

---
 drivers/iio/dummy/iio_simple_dummy.c | 20 ++++++++++++--------
 1 file changed, 12 insertions(+), 8 deletions(-)

index 6cb02299a215..18cfe1cb7a40 100644
@@ -568,10 +568,9 @@ static struct iio_sw_device *iio_dummy_probe(const char *name)
 	struct iio_sw_device *swd;
 
 	swd = kzalloc(sizeof(*swd), GFP_KERNEL);
-	if (!swd) {
-		ret = -ENOMEM;
-		goto error_kzalloc;
-	}
+	if (!swd)
+		return ERR_PTR(-ENOMEM);
+
 	/*
 	 * Allocate an IIO device.
 	 *

@@ -583,7 +582,7 @@ static struct iio_sw_device *iio_dummy_probe(const char *name)
 	indio_dev = iio_device_alloc(sizeof(*st));
 	if (!indio_dev) {
 		ret = -ENOMEM;
-		goto error_ret;
+		goto error_free_swd;
 	}
 
 	st = iio_priv(indio_dev);

@@ -614,6 +613,10 @@ static struct iio_sw_device *iio_dummy_probe(const char *name)
 	 *    indio_dev->name = spi_get_device_id(spi)->name;
 	 */
 	indio_dev->name = kstrdup(name, GFP_KERNEL);
+	if (!indio_dev->name) {
+		ret = -ENOMEM;
+		goto error_free_device;
+	}
 
 	/* Provide description of available channels */
 	indio_dev->channels = iio_dummy_channels;

@@ -630,7 +633,7 @@ static struct iio_sw_device *iio_dummy_probe(const char *name)
 
 	ret = iio_simple_dummy_events_register(indio_dev);
 	if (ret < 0)
-		goto error_free_device;
+		goto error_free_name;
 
 	ret = iio_simple_dummy_configure_buffer(indio_dev);
 	if (ret < 0)

@@ -647,11 +650,12 @@ static struct iio_sw_device *iio_dummy_probe(const char *name)
 	iio_simple_dummy_unconfigure_buffer(indio_dev);
 error_unregister_events:
 	iio_simple_dummy_events_unregister(indio_dev);
+error_free_name:
+	kfree(indio_dev->name);
 error_free_device:
 	iio_device_free(indio_dev);
-error_ret:
+error_free_swd:
 	kfree(swd);
-error_kzalloc:
 	return ERR_PTR(ret);
 }
 

2.35.1

From: Miquel Raynal <[email protected]>

[ Upstream commit 474010127e2505fc463236470908e1ff5ddb3578 ]

Right now the (framework) mlock lock is (ab)used for multiple purposes:
1- protecting concurrent accesses over the odr local cache 2- avoid changing samplig frequency whilst buffer is running

Let's start by handling situation #1 with a local lock.

---
 .../iio/common/st_sensors/st_sensors_core.c   | 24 ++++++++++++++-----
 include/linux/iio/common/st_sensors.h         |  3 +++
 2 files changed, 21 insertions(+), 6 deletions(-)

index 364683783ae5..c25b0bc89b0c 100644
@@ -76,16 +76,18 @@ static int st_sensors_match_odr(struct st_sensor_settings *sensor_settings,
 
 int st_sensors_set_odr(struct iio_dev *indio_dev, unsigned int odr)
 {
-	int err;
+	int err = 0;
 	struct st_sensor_odr_avl odr_out = {0, 0};
 	struct st_sensor_data *sdata = iio_priv(indio_dev);
 
+	mutex_lock(&sdata->odr_lock);
+
 	if (!sdata->sensor_settings->odr.mask)
-		return 0;
+		goto unlock_mutex;
 
 	err = st_sensors_match_odr(sdata->sensor_settings, odr, &odr_out);
 	if (err < 0)
-		goto st_sensors_match_odr_error;
+		goto unlock_mutex;
 
 	if ((sdata->sensor_settings->odr.addr ==
 					sdata->sensor_settings->pw.addr) &&

@@ -108,7 +110,9 @@ int st_sensors_set_odr(struct iio_dev *indio_dev, unsigned int odr)
 	if (err >= 0)
 		sdata->odr = odr_out.hz;
 
-st_sensors_match_odr_error:
+unlock_mutex:
+	mutex_unlock(&sdata->odr_lock);
+
 	return err;
 }
 EXPORT_SYMBOL(st_sensors_set_odr);

@@ -384,6 +388,8 @@ int st_sensors_init_sensor(struct iio_dev *indio_dev,
 	struct st_sensors_platform_data *of_pdata;
 	int err = 0;
 
+	mutex_init(&sdata->odr_lock);
+
 	/* If OF/DT pdata exists, it will take precedence of anything else */
 	of_pdata = st_sensors_of_probe(indio_dev->dev.parent, pdata);
 	if (of_pdata)

@@ -575,18 +581,24 @@ int st_sensors_read_info_raw(struct iio_dev *indio_dev,
 		err = -EBUSY;
 		goto out;
 	} else {
+		mutex_lock(&sdata->odr_lock);
 		err = st_sensors_set_enable(indio_dev, true);
-		if (err < 0)
+		if (err < 0) {
+			mutex_unlock(&sdata->odr_lock);
 			goto out;
+		}
 
 		msleep((sdata->sensor_settings->bootime * 1000) / sdata->odr);
 		err = st_sensors_read_axis_data(indio_dev, ch, val);
-		if (err < 0)
+		if (err < 0) {
+			mutex_unlock(&sdata->odr_lock);
 			goto out;
+		}
 
 		*val = *val >> ch->scan_type.shift;
 
 		err = st_sensors_set_enable(indio_dev, false);
+		mutex_unlock(&sdata->odr_lock);
 	}
 out:
 	mutex_unlock(&indio_dev->mlock);

index 686be532f4cb..7816bf070f83 100644
@@ -228,6 +228,7 @@ struct st_sensor_settings {
  * @hw_irq_trigger: if we're using the hardware interrupt on the sensor.
  * @hw_timestamp: Latest timestamp from the interrupt handler, when in use.
  * @buffer_data: Data used by buffer part.
+ * @odr_lock: Local lock for preventing concurrent ODR accesses/changes
  */
 struct st_sensor_data {
 	struct device *dev;

@@ -253,6 +254,8 @@ struct st_sensor_data {
 	s64 hw_timestamp;
 
 	char buffer_data[ST_SENSORS_MAX_BUFFER_SIZE] ____cacheline_aligned;
+
+	struct mutex odr_lock;
 };
 
 #ifdef CONFIG_IIO_BUFFER

2.35.1

From: Kees Cook <[email protected]>

[ Upstream commit f387e86d3a74407bdd9c5815820ac9d060962840 ]

To be sufficiently out of range for the usercopy test to see the lifetime mismatch, expand the size of the "bad" buffer, which will let it be beyond current_stack_pointer regardless of stack growth direction. Paired with the recent addition of stack depth checking under CONFIG_HARDENED_USERCOPY=y, this will correctly start tripping again.

---
 drivers/misc/lkdtm/usercopy.c | 17 ++++++++++++++---
 1 file changed, 14 insertions(+), 3 deletions(-)

index e172719dd86d..4617c63b1026 100644
@@ -30,12 +30,12 @@ static const unsigned char test_text[] = "This is a test.\n";
  */
 static noinline unsigned char *trick_compiler(unsigned char *stack)
 {
-	return stack + 0;
+	return stack + unconst;
 }
 
 static noinline unsigned char *do_usercopy_stack_callee(int value)
 {
-	unsigned char buf[32];
+	unsigned char buf[128];
 	int i;
 
 	/* Exercise stack to avoid everything living in registers. */

@@ -43,7 +43,12 @@ static noinline unsigned char *do_usercopy_stack_callee(int value)
 		buf[i] = value & 0xff;
 	}
 
-	return trick_compiler(buf);
+	/*
+	 * Put the target buffer in the middle of stack allocation
+	 * so that we don't step on future stack users regardless
+	 * of stack growth direction.
+	 */
+	return trick_compiler(&buf[(128/2)-32]);
 }
 
 static noinline void do_usercopy_stack(bool to_user, bool bad_frame)

@@ -66,6 +71,12 @@ static noinline void do_usercopy_stack(bool to_user, bool bad_frame)
 		bad_stack -= sizeof(unsigned long);
 	}
 
+#ifdef ARCH_HAS_CURRENT_STACK_POINTER
+	pr_info("stack     : %px\n", (void *)current_stack_pointer);
+#endif
+	pr_info("good_stack: %px-%px\n", good_stack, good_stack + sizeof(good_stack));
+	pr_info("bad_stack : %px-%px\n", bad_stack, bad_stack + sizeof(good_stack));
+
 	user_addr = vm_mmap(NULL, 0, PAGE_SIZE,
 			    PROT_READ | PROT_WRITE | PROT_EXEC,
 			    MAP_ANONYMOUS | MAP_PRIVATE, 0);

2.35.1

From: Zheyu Ma <[email protected]>

[ Upstream commit 689ca31c542687709ba21ec2195c1fbce34fd029 ]

When the driver fails at alloc_hdlcdev(), and then we remove the driver module, we will get the following splat:

[   25.065966] general protection fault, probably for non-canonical address 0xdffffc0000000182: 0000 [#1] PREEMPT SMP KASAN PTI
[   25.066914] KASAN: null-ptr-deref in range [0x0000000000000c10-0x0000000000000c17]
[   25.069262] RIP: 0010:detach_hdlc_protocol+0x2a/0x3e0
[   25.077709] Call Trace:
[   25.077924]  <TASK>
[   25.078108]  unregister_hdlc_device+0x16/0x30
[   25.078481]  slgt_cleanup+0x157/0x9f0 [synclink_gt]

Fix this by checking whether the 'info->netdev' is a null pointer first.

---
 drivers/tty/synclink_gt.c | 2 ++
 1 file changed, 2 insertions(+)

index ff345a8e0fcc..b72471373c71 100644
@@ -1752,6 +1752,8 @@ static int hdlcdev_init(struct slgt_info *info)
  */
 static void hdlcdev_exit(struct slgt_info *info)
 {
+	if (!info->netdev)
+		return;
 	unregister_hdlc_device(info->netdev);
 	free_netdev(info->netdev);
 	info->netdev = NULL;

2.35.1

From: Huang Guobin <[email protected]>

[ Upstream commit ee157a79e7c82b01ae4c25de0ac75899801f322c ]

When pci_read_config_dword failed, call pci_release_regions() and pci_disable_device() to recycle the resource previously allocated.

---
 drivers/tty/serial/icom.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index 624f3d541c68..d047380259b5 100644
@@ -1499,7 +1499,7 @@ static int icom_probe(struct pci_dev *dev,
 	retval = pci_read_config_dword(dev, PCI_COMMAND, &command_reg);
 	if (retval) {
 		dev_err(&dev->dev, "PCI Config read FAILED\n");
-		return retval;
+		goto probe_exit0;
 	}
 
 	pci_write_config_dword(dev, PCI_COMMAND,

2.35.1

From: Duoming Zhou <[email protected]>

[ Upstream commit 806c7b53414934ba2a39449b31fd1a038e500273 ]

There is a deadlock in ieee80211_beacons_stop(), which is shown below:

   (Thread 1)              |      (Thread 2)
                           | ieee80211_send_beacon()
ieee80211_beacons_stop()   |  mod_timer()
 spin_lock_irqsave() //(1) |  (wait a time)
 ...                       | ieee80211_send_beacon_cb()
 del_timer_sync()          |  spin_lock_irqsave() //(2)
 (wait timer to stop)      |  ...

We hold ieee->beacon_lock in position (1) of thread 1 and use del_timer_sync() to wait timer to stop, but timer handler also need ieee->beacon_lock in position (2) of thread 2. As a result, ieee80211_beacons_stop() will block forever.

This patch extracts del_timer_sync() from the protection of spin_lock_irqsave(), which could let timer handler to obtain the needed lock.

---
 drivers/staging/rtl8192u/ieee80211/ieee80211_softmac.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index 33a6af7aad22..a869694337f7 100644
@@ -528,9 +528,9 @@ static void ieee80211_beacons_stop(struct ieee80211_device *ieee)
 	spin_lock_irqsave(&ieee->beacon_lock, flags);
 
 	ieee->beacon_txing = 0;
-	del_timer_sync(&ieee->beacon_timer);
 
 	spin_unlock_irqrestore(&ieee->beacon_lock, flags);
+	del_timer_sync(&ieee->beacon_timer);
 }
 
 void ieee80211_stop_send_beacons(struct ieee80211_device *ieee)

2.35.1

From: Duoming Zhou <[email protected]>

[ Upstream commit 9b6bdbd9337de3917945847bde262a34a87a6303 ]

There is a deadlock in rtllib_beacons_stop(), which is shown below:

   (Thread 1)              |      (Thread 2)
                           | rtllib_send_beacon()
rtllib_beacons_stop()      |  mod_timer()
 spin_lock_irqsave() //(1) |  (wait a time)
 ...                       | rtllib_send_beacon_cb()
 del_timer_sync()          |  spin_lock_irqsave() //(2)
 (wait timer to stop)      |  ...

We hold ieee->beacon_lock in position (1) of thread 1 and use del_timer_sync() to wait timer to stop, but timer handler also need ieee->beacon_lock in position (2) of thread 2. As a result, rtllib_beacons_stop() will block forever.

This patch extracts del_timer_sync() from the protection of spin_lock_irqsave(), which could let timer handler to obtain the needed lock.

---
 drivers/staging/rtl8192e/rtllib_softmac.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index 4ff8fd694c60..0154f5791b12 100644
@@ -651,9 +651,9 @@ static void rtllib_beacons_stop(struct rtllib_device *ieee)
 	spin_lock_irqsave(&ieee->beacon_lock, flags);
 
 	ieee->beacon_txing = 0;
-	del_timer_sync(&ieee->beacon_timer);
 
 	spin_unlock_irqrestore(&ieee->beacon_lock, flags);
+	del_timer_sync(&ieee->beacon_timer);
 
 }
 

2.35.1

From: Zhen Ni <[email protected]>

[ Upstream commit 134a3408c2d3f7e23eb0e4556e0a2d9f36c2614e ]

It will cause null-ptr-deref if platform_get_resource() returns NULL, we need check the return value.

---
 drivers/usb/host/isp116x-hcd.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

index a87c0b26279e..00a4e12a1f15 100644
@@ -1541,10 +1541,12 @@ static int isp116x_remove(struct platform_device *pdev)
 
 	iounmap(isp116x->data_reg);
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
-	release_mem_region(res->start, 2);
+	if (res)
+		release_mem_region(res->start, 2);
 	iounmap(isp116x->addr_reg);
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	release_mem_region(res->start, 2);
+	if (res)
+		release_mem_region(res->start, 2);
 
 	usb_put_hcd(hcd);
 	return 0;

2.35.1

From: Duoming Zhou <[email protected]>

[ Upstream commit 62b2caef400c1738b6d22f636c628d9f85cd4c4c ]

There is a deadlock in sa1100_set_termios(), which is shown below:

   (Thread 1)              |      (Thread 2)
                           | sa1100_enable_ms()
sa1100_set_termios()       |  mod_timer()
 spin_lock_irqsave() //(1) |  (wait a time)
 ...                       | sa1100_timeout()
 del_timer_sync()          |  spin_lock_irqsave() //(2)
 (wait timer to stop)      |  ...

We hold sport->port.lock in position (1) of thread 1 and use del_timer_sync() to wait timer to stop, but timer handler also need sport->port.lock in position (2) of thread 2. As a result, sa1100_set_termios() will block forever.

This patch moves del_timer_sync() before spin_lock_irqsave() in order to prevent the deadlock.

---
 drivers/tty/serial/sa1100.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

index 8e618129e65c..ff4b44bdf6b6 100644
@@ -454,6 +454,8 @@ sa1100_set_termios(struct uart_port *port, struct ktermios *termios,
 	baud = uart_get_baud_rate(port, termios, old, 0, port->uartclk/16); 
 	quot = uart_get_divisor(port, baud);
 
+	del_timer_sync(&sport->timer);
+
 	spin_lock_irqsave(&sport->port.lock, flags);
 
 	sport->port.read_status_mask &= UTSR0_TO_SM(UTSR0_TFS);

@@ -484,8 +486,6 @@ sa1100_set_termios(struct uart_port *port, struct ktermios *termios,
 				UTSR1_TO_SM(UTSR1_ROR);
 	}
 
-	del_timer_sync(&sport->timer);
-
 	/*
 	 * Update the per-port timeout.
 	 */

2.35.1

From: Duoming Zhou <[email protected]>

[ Upstream commit 4d378f2ae58138d4c55684e1d274e7dd94aa6524 ]

There is a deadlock in oxu_bus_suspend(), which is shown below:

   (Thread 1)              |      (Thread 2)
                           | timer_action()
oxu_bus_suspend()          |  mod_timer()
 spin_lock_irq() //(1)     |  (wait a time)
 ...                       | oxu_watchdog()
 del_timer_sync()          |  spin_lock_irq() //(2)
 (wait timer to stop)      |  ...

We hold oxu->lock in position (1) of thread 1, and use del_timer_sync() to wait timer to stop, but timer handler also need oxu->lock in position (2) of thread 2. As a result, oxu_bus_suspend() will block forever.

This patch extracts del_timer_sync() from the protection of spin_lock_irq(), which could let timer handler to obtain the needed lock.

---
 drivers/usb/host/oxu210hp-hcd.c | 2 ++
 1 file changed, 2 insertions(+)

index 65985247fc00..f05b6f2b0865 100644
@@ -3906,8 +3906,10 @@ static int oxu_bus_suspend(struct usb_hcd *hcd)
 		}
 	}
 
+	spin_unlock_irq(&oxu->lock);
 	/* turn off now-idle HC */
 	del_timer_sync(&oxu->watchdog);
+	spin_lock_irq(&oxu->lock);
 	ehci_halt(oxu);
 	hcd->state = HC_STATE_SUSPENDED;
 

2.35.1

From: Evan Green <[email protected]>

[ Upstream commit 63acaa8e9c65dc34dc249440216f8e977f5d2748 ]

The documentation for the freeze() method says that it "should quiesce the device so that it doesn't generate IRQs or DMA". The unspoken consequence of not doing this is that MSIs aimed at non-boot CPUs may get fully lost if they're sent during the period where the target CPU is offline.

The current callbacks for USB HCD do not fully quiesce interrupts, specifically on XHCI. Change to use the full suspend/resume flow for freeze/thaw to ensure interrupts are fully quiesced. This fixes issues where USB devices fail to thaw during hibernation because XHCI misses its interrupt and cannot recover.

---
 drivers/usb/core/hcd-pci.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

index 9e26b0143a59..db16efe293e0 100644
@@ -604,10 +604,10 @@ const struct dev_pm_ops usb_hcd_pci_pm_ops = {
 	.suspend_noirq	= hcd_pci_suspend_noirq,
 	.resume_noirq	= hcd_pci_resume_noirq,
 	.resume		= hcd_pci_resume,
-	.freeze		= check_root_hub_suspended,
+	.freeze		= hcd_pci_suspend,
 	.freeze_noirq	= check_root_hub_suspended,
 	.thaw_noirq	= NULL,
-	.thaw		= NULL,
+	.thaw		= hcd_pci_resume,
 	.poweroff	= hcd_pci_suspend,
 	.poweroff_noirq	= hcd_pci_suspend_noirq,
 	.restore_noirq	= hcd_pci_resume_noirq,

2.35.1

From: Marek Szyprowski <[email protected]>

[ Upstream commit 3120aac6d0ecd9accf56894aeac0e265f74d3d5a ]

UDC driver should not touch gadget's driver internals, especially it should not reset driver->bus. This wasn't harmful so far, but since commit fc274c1e9973 ("USB: gadget: Add a new bus for gadgets") gadget subsystem got it's own bus and messing with ->bus triggers the following NULL pointer dereference:

dwc2 12480000.hsotg: bound driver g_ether
8<--- cut here ---

Unable to handle kernel NULL pointer dereference at virtual address 00000000
[00000000] *pgd=00000000
Internal error: Oops: 5 [#1] SMP ARM
Modules linked in: ...
CPU: 0 PID: 620 Comm: modprobe Not tainted 5.18.0-rc5-next-20220504 #11862
Hardware name: Samsung Exynos (Flattened Device Tree)
PC is at module_add_driver+0x44/0xe8
LR is at sysfs_do_create_link_sd+0x84/0xe0

...
Process modprobe (pid: 620, stack limit = 0x(ptrval))
...
module_add_driver from bus_add_driver+0xf4/0x1e4 bus_add_driver from driver_register+0x78/0x10c driver_register from usb_gadget_register_driver_owner+0x40/0xb4 usb_gadget_register_driver_owner from do_one_initcall+0x44/0x1e0 do_one_initcall from do_init_module+0x44/0x1c8 do_init_module from load_module+0x19b8/0x1b9c load_module from sys_finit_module+0xdc/0xfc sys_finit_module from ret_fast_syscall+0x0/0x54

Exception stack(0xf1771fa8 to 0xf1771ff0)
...
dwc2 12480000.hsotg: new device is high-speed
---[ end trace 0000000000000000 ]---

Fix this by removing driver->bus entry reset.

---
 drivers/usb/dwc2/gadget.c | 1 -
 1 file changed, 1 deletion(-)

index 379bbf27c7ce..8fd6eefc671c 100644
@@ -4486,7 +4486,6 @@ static int dwc2_hsotg_udc_start(struct usb_gadget *gadget,
 
 	WARN_ON(hsotg->driver);
 
-	driver->driver.bus = NULL;
 	hsotg->driver = driver;
 	hsotg->gadget.dev.of_node = hsotg->dev->of_node;
 	hsotg->gadget.speed = USB_SPEED_UNKNOWN;

2.35.1

From: Shuah Khan <[email protected]>

[ Upstream commit f861d36e021e1ac4a0a2a1f6411d623809975d63 ]

rtsx_usb_probe() doesn't call usb_set_intfdata() to null out the interface pointer when probe fails. This leaves a stale pointer. Noticed the missing usb_set_intfdata() while debugging an unrelated invalid DMA mapping problem.

Fix it with a call to usb_set_intfdata(..., NULL).

---
 drivers/misc/cardreader/rtsx_usb.c | 1 +
 1 file changed, 1 insertion(+)

index a328cab11014..4aef33d07cc3 100644
@@ -667,6 +667,7 @@ static int rtsx_usb_probe(struct usb_interface *intf,
 	return 0;
 
 out_init_fail:
+	usb_set_intfdata(ucr->pusb_intf, NULL);
 	usb_free_coherent(ucr->pusb_dev, IOBUF_SIZE, ucr->iobuf,
 			ucr->iobuf_dma);
 	return ret;

2.35.1

From: bumwoo lee <[email protected]>

[ Upstream commit 5dcc2afe716d69f5112ce035cb14f007461ff189 ]

Currently, someone can invoke the sysfs such as state_show() intermittently before dev_set_drvdata() is done.
And it can be a cause of kernel Oops because of edev is Null at that time. So modified the driver registration to after setting drviver data.

- Oops's backtrace.

Backtrace:

[<c067865c>] (state_show) from [<c05222e8>] (dev_attr_show) [<c05222c0>] (dev_attr_show) from [<c02c66e0>] (sysfs_kf_seq_show) [<c02c6648>] (sysfs_kf_seq_show) from [<c02c496c>] (kernfs_seq_show) [<c02c4938>] (kernfs_seq_show) from [<c025e2a0>] (seq_read) [<c025e11c>] (seq_read) from [<c02c50a0>] (kernfs_fop_read) [<c02c5064>] (kernfs_fop_read) from [<c0231cac>] (__vfs_read) [<c0231c5c>] (__vfs_read) from [<c0231ee0>] (vfs_read) [<c0231e34>] (vfs_read) from [<c0232464>] (ksys_read) [<c02323f0>] (ksys_read) from [<c02324fc>] (sys_read) [<c02324e4>] (sys_read) from [<c00091d0>] (__sys_trace_return)

---
 drivers/extcon/extcon.c | 29 +++++++++++++++++------------
 1 file changed, 17 insertions(+), 12 deletions(-)

index 5c9e156cd086..6b905c3d30f4 100644
@@ -1230,19 +1230,14 @@ int extcon_dev_register(struct extcon_dev *edev)
 		edev->dev.type = &edev->extcon_dev_type;
 	}
 
-	ret = device_register(&edev->dev);
-	if (ret) {
-		put_device(&edev->dev);
-		goto err_dev;
-	}
-
 	spin_lock_init(&edev->lock);
-	edev->nh = devm_kcalloc(&edev->dev, edev->max_supported,
-				sizeof(*edev->nh), GFP_KERNEL);
-	if (!edev->nh) {
-		ret = -ENOMEM;
-		device_unregister(&edev->dev);
-		goto err_dev;
+	if (edev->max_supported) {
+		edev->nh = kcalloc(edev->max_supported, sizeof(*edev->nh),
+				GFP_KERNEL);
+		if (!edev->nh) {
+			ret = -ENOMEM;
+			goto err_alloc_nh;
+		}
 	}
 
 	for (index = 0; index < edev->max_supported; index++)

@@ -1253,6 +1248,12 @@ int extcon_dev_register(struct extcon_dev *edev)
 	dev_set_drvdata(&edev->dev, edev);
 	edev->state = 0;
 
+	ret = device_register(&edev->dev);
+	if (ret) {
+		put_device(&edev->dev);
+		goto err_dev;
+	}
+
 	mutex_lock(&extcon_dev_list_lock);
 	list_add(&edev->entry, &extcon_dev_list);
 	mutex_unlock(&extcon_dev_list_lock);

@@ -1260,6 +1261,9 @@ int extcon_dev_register(struct extcon_dev *edev)
 	return 0;
 
 err_dev:
+	if (edev->max_supported)
+		kfree(edev->nh);
+err_alloc_nh:
 	if (edev->max_supported)
 		kfree(edev->extcon_dev_type.groups);
 err_alloc_groups:

@@ -1320,6 +1324,7 @@ void extcon_dev_unregister(struct extcon_dev *edev)
 	if (edev->max_supported) {
 		kfree(edev->extcon_dev_type.groups);
 		kfree(edev->cables);
+		kfree(edev->nh);
 	}
 
 	put_device(&edev->dev);

2.35.1

From: Andre Przywara <[email protected]>

[ Upstream commit a98399cbc1e05f7b977419f03905501d566cf54e ]

When a machine sports more than one SP804 timer instance, we only bring up the first one, since multiple timers of the same kind are not useful to Linux. As this is intentional behaviour, we should not return an error message, as we do today:
===============

[    0.000800] Failed to initialize '/bus@8000000/motherboard-bus@8000000/iofpga-bus@300000000/timer@120000': -22

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

Replace the -EINVAL return with a debug message and return 0 instead.

Also we do not reach the init function anymore if the DT node is disabled (as this is now handled by OF_DECLARE), so remove the explicit check for that case.

This fixes a long standing bogus error when booting ARM's fastmodels.

---
 drivers/clocksource/timer-sp804.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

index 9c841980eed1..c9aa0498fb84 100644
@@ -215,6 +215,11 @@ static int __init sp804_of_init(struct device_node *np)
 	struct clk *clk1, *clk2;
 	const char *name = of_get_property(np, "compatible", NULL);
 
+	if (initialized) {
+		pr_debug("%pOF: skipping further SP804 timer device\n", np);
+		return 0;
+	}
+
 	base = of_iomap(np, 0);
 	if (!base)
 		return -ENXIO;

@@ -223,11 +228,6 @@ static int __init sp804_of_init(struct device_node *np)
 	writel(0, base + TIMER_CTRL);
 	writel(0, base + TIMER_2_BASE + TIMER_CTRL);
 
-	if (initialized || !of_device_is_available(np)) {
-		ret = -EINVAL;
-		goto err;
-	}
-
 	clk1 = of_clk_get(np, 0);
 	if (IS_ERR(clk1))
 		clk1 = NULL;

2.35.1

From: Wang Cheng <[email protected]>

[ Upstream commit d1b57669732d09da7e13ef86d058dab0cd57f6e0 ]

When r8712_usbctrl_vendorreq() returns negative, 'data' in usb_read{8,16,32} will not be initialized.

BUG: KMSAN: uninit-value in string_nocheck lib/vsprintf.c:643 [inline]
BUG: KMSAN: uninit-value in string+0x4ec/0x6f0 lib/vsprintf.c:725
 string_nocheck lib/vsprintf.c:643 [inline]
 string+0x4ec/0x6f0 lib/vsprintf.c:725
 vsnprintf+0x2222/0x3650 lib/vsprintf.c:2806
 va_format lib/vsprintf.c:1704 [inline]
 pointer+0x18e6/0x1f70 lib/vsprintf.c:2443
 vsnprintf+0x1a9b/0x3650 lib/vsprintf.c:2810
 vprintk_store+0x537/0x2150 kernel/printk/printk.c:2158
 vprintk_emit+0x28b/0xab0 kernel/printk/printk.c:2256
 dev_vprintk_emit+0x5ef/0x6d0 drivers/base/core.c:4604
 dev_printk_emit+0x1dd/0x21f drivers/base/core.c:4615
 __dev_printk+0x3be/0x440 drivers/base/core.c:4627
 _dev_info+0x1ea/0x22f drivers/base/core.c:4673
 r871xu_drv_init+0x1929/0x3070 drivers/staging/rtl8712/usb_intf.c:401
 usb_probe_interface+0xf19/0x1600 drivers/usb/core/driver.c:396
 really_probe+0x6c7/0x1350 drivers/base/dd.c:621
 __driver_probe_device+0x3e9/0x530 drivers/base/dd.c:752
 driver_probe_device drivers/base/dd.c:782 [inline]
 __device_attach_driver+0x79f/0x1120 drivers/base/dd.c:899
 bus_for_each_drv+0x2d6/0x3f0 drivers/base/bus.c:427
 __device_attach+0x593/0x8e0 drivers/base/dd.c:970
 device_initial_probe+0x4a/0x60 drivers/base/dd.c:1017
 bus_probe_device+0x17b/0x3e0 drivers/base/bus.c:487
 device_add+0x1fff/0x26e0 drivers/base/core.c:3405
 usb_set_configuration+0x37e9/0x3ed0 drivers/usb/core/message.c:2170
 usb_generic_driver_probe+0x13c/0x300 drivers/usb/core/generic.c:238
 usb_probe_device+0x309/0x570 drivers/usb/core/driver.c:293
 really_probe+0x6c7/0x1350 drivers/base/dd.c:621
 __driver_probe_device+0x3e9/0x530 drivers/base/dd.c:752
 driver_probe_device drivers/base/dd.c:782 [inline]
 __device_attach_driver+0x79f/0x1120 drivers/base/dd.c:899
 bus_for_each_drv+0x2d6/0x3f0 drivers/base/bus.c:427
 __device_attach+0x593/0x8e0 drivers/base/dd.c:970
 device_initial_probe+0x4a/0x60 drivers/base/dd.c:1017
 bus_probe_device+0x17b/0x3e0 drivers/base/bus.c:487
 device_add+0x1fff/0x26e0 drivers/base/core.c:3405
 usb_new_device+0x1b91/0x2950 drivers/usb/core/hub.c:2566
 hub_port_connect drivers/usb/core/hub.c:5363 [inline]
 hub_port_connect_change drivers/usb/core/hub.c:5507 [inline]
 port_event drivers/usb/core/hub.c:5665 [inline]
 hub_event+0x58e3/0x89e0 drivers/usb/core/hub.c:5747
 process_one_work+0xdb6/0x1820 kernel/workqueue.c:2289
 worker_thread+0x10d0/0x2240 kernel/workqueue.c:2436
 kthread+0x3c7/0x500 kernel/kthread.c:376
 ret_from_fork+0x1f/0x30

Local variable data created at:

 usb_read8+0x5d/0x130 drivers/staging/rtl8712/usb_ops.c:33
 r8712_read8+0xa5/0xd0 drivers/staging/rtl8712/rtl8712_io.c:29

KMSAN: uninit-value in r871xu_drv_init
https://syzkaller.appspot.com/bug?id=3cd92b1d85428b128503bfa7a250294c9ae00bd8

---
 drivers/staging/rtl8712/usb_ops.c | 27 ++++++++++++++++++---------
 1 file changed, 18 insertions(+), 9 deletions(-)

index e64845e6adf3..af9966d03979 100644
@@ -29,7 +29,8 @@ static u8 usb_read8(struct intf_hdl *intfhdl, u32 addr)
 	u16 wvalue;
 	u16 index;
 	u16 len;
-	__le32 data;
+	int status;
+	__le32 data = 0;
 	struct intf_priv *intfpriv = intfhdl->pintfpriv;
 
 	request = 0x05;

@@ -37,8 +38,10 @@ static u8 usb_read8(struct intf_hdl *intfhdl, u32 addr)
 	index = 0;
 	wvalue = (u16)(addr & 0x0000ffff);
 	len = 1;
-	r8712_usbctrl_vendorreq(intfpriv, request, wvalue, index, &data, len,
-				requesttype);
+	status = r8712_usbctrl_vendorreq(intfpriv, request, wvalue, index,
+					 &data, len, requesttype);
+	if (status < 0)
+		return 0;
 	return (u8)(le32_to_cpu(data) & 0x0ff);
 }
 

@@ -49,7 +52,8 @@ static u16 usb_read16(struct intf_hdl *intfhdl, u32 addr)
 	u16 wvalue;
 	u16 index;
 	u16 len;
-	__le32 data;
+	int status;
+	__le32 data = 0;
 	struct intf_priv *intfpriv = intfhdl->pintfpriv;
 
 	request = 0x05;

@@ -57,8 +61,10 @@ static u16 usb_read16(struct intf_hdl *intfhdl, u32 addr)
 	index = 0;
 	wvalue = (u16)(addr & 0x0000ffff);
 	len = 2;
-	r8712_usbctrl_vendorreq(intfpriv, request, wvalue, index, &data, len,
-				requesttype);
+	status = r8712_usbctrl_vendorreq(intfpriv, request, wvalue, index,
+					 &data, len, requesttype);
+	if (status < 0)
+		return 0;
 	return (u16)(le32_to_cpu(data) & 0xffff);
 }
 

@@ -69,7 +75,8 @@ static u32 usb_read32(struct intf_hdl *intfhdl, u32 addr)
 	u16 wvalue;
 	u16 index;
 	u16 len;
-	__le32 data;
+	int status;
+	__le32 data = 0;
 	struct intf_priv *intfpriv = intfhdl->pintfpriv;
 
 	request = 0x05;

@@ -77,8 +84,10 @@ static u32 usb_read32(struct intf_hdl *intfhdl, u32 addr)
 	index = 0;
 	wvalue = (u16)(addr & 0x0000ffff);
 	len = 4;
-	r8712_usbctrl_vendorreq(intfpriv, request, wvalue, index, &data, len,
-				requesttype);
+	status = r8712_usbctrl_vendorreq(intfpriv, request, wvalue, index,
+					 &data, len, requesttype);
+	if (status < 0)
+		return 0;
 	return le32_to_cpu(data);
 }
 

2.35.1

From: Wang Cheng <[email protected]>

[ Upstream commit 0458e5428e5e959d201a40ffe71d762a79ecedc4 ]

When 'tmpU1b' returns from r8712_read8(padapter, EE_9346CR) is 0, 'mac[6]' will not be initialized.

BUG: KMSAN: uninit-value in r871xu_drv_init+0x2d54/0x3070 drivers/staging/rtl8712/usb_intf.c:541
 r871xu_drv_init+0x2d54/0x3070 drivers/staging/rtl8712/usb_intf.c:541
 usb_probe_interface+0xf19/0x1600 drivers/usb/core/driver.c:396
 really_probe+0x653/0x14b0 drivers/base/dd.c:596
 __driver_probe_device+0x3e9/0x530 drivers/base/dd.c:752
 driver_probe_device drivers/base/dd.c:782 [inline]
 __device_attach_driver+0x79f/0x1120 drivers/base/dd.c:899
 bus_for_each_drv+0x2d6/0x3f0 drivers/base/bus.c:427
 __device_attach+0x593/0x8e0 drivers/base/dd.c:970
 device_initial_probe+0x4a/0x60 drivers/base/dd.c:1017
 bus_probe_device+0x17b/0x3e0 drivers/base/bus.c:487
 device_add+0x1fff/0x26e0 drivers/base/core.c:3405
 usb_set_configuration+0x37e9/0x3ed0 drivers/usb/core/message.c:2170
 usb_generic_driver_probe+0x13c/0x300 drivers/usb/core/generic.c:238
 usb_probe_device+0x309/0x570 drivers/usb/core/driver.c:293
 really_probe+0x653/0x14b0 drivers/base/dd.c:596
 __driver_probe_device+0x3e9/0x530 drivers/base/dd.c:752
 driver_probe_device drivers/base/dd.c:782 [inline]
 __device_attach_driver+0x79f/0x1120 drivers/base/dd.c:899
 bus_for_each_drv+0x2d6/0x3f0 drivers/base/bus.c:427
 __device_attach+0x593/0x8e0 drivers/base/dd.c:970
 device_initial_probe+0x4a/0x60 drivers/base/dd.c:1017
 bus_probe_device+0x17b/0x3e0 drivers/base/bus.c:487
 device_add+0x1fff/0x26e0 drivers/base/core.c:3405
 usb_new_device+0x1b8e/0x2950 drivers/usb/core/hub.c:2566
 hub_port_connect drivers/usb/core/hub.c:5358 [inline]
 hub_port_connect_change drivers/usb/core/hub.c:5502 [inline]
 port_event drivers/usb/core/hub.c:5660 [inline]
 hub_event+0x58e3/0x89e0 drivers/usb/core/hub.c:5742
 process_one_work+0xdb6/0x1820 kernel/workqueue.c:2307
 worker_thread+0x10b3/0x21e0 kernel/workqueue.c:2454
 kthread+0x3c7/0x500 kernel/kthread.c:377
 ret_from_fork+0x1f/0x30

Local variable mac created at:

 r871xu_drv_init+0x1771/0x3070 drivers/staging/rtl8712/usb_intf.c:394
 usb_probe_interface+0xf19/0x1600 drivers/usb/core/driver.c:396

KMSAN: uninit-value in r871xu_drv_init
https://syzkaller.appspot.com/bug?id=3cd92b1d85428b128503bfa7a250294c9ae00bd8

---
 drivers/staging/rtl8712/usb_intf.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

index 49188ab04612..f7c1258eaa39 100644
@@ -539,13 +539,13 @@ static int r871xu_drv_init(struct usb_interface *pusb_intf,
 		} else {
 			AutoloadFail = false;
 		}
-		if (((mac[0] == 0xff) && (mac[1] == 0xff) &&
+		if ((!AutoloadFail) ||
+		    ((mac[0] == 0xff) && (mac[1] == 0xff) &&
 		     (mac[2] == 0xff) && (mac[3] == 0xff) &&
 		     (mac[4] == 0xff) && (mac[5] == 0xff)) ||
 		    ((mac[0] == 0x00) && (mac[1] == 0x00) &&
 		     (mac[2] == 0x00) && (mac[3] == 0x00) &&
-		     (mac[4] == 0x00) && (mac[5] == 0x00)) ||
-		     (!AutoloadFail)) {
+		     (mac[4] == 0x00) && (mac[5] == 0x00))) {
 			mac[0] = 0x00;
 			mac[1] = 0xe0;
 			mac[2] = 0x4c;

2.35.1

From: John Ogness <[email protected]>

[ Upstream commit aabdbb1b7a5819e18c403334a31fb0cc2c06ad41 ]

__msm_console_write() assumes that interrupts are disabled, but with threaded console printers it is possible that the write() callback of the console is called with interrupts enabled.

Explicitly disable interrupts using local_irq_save() to preserve the assumed context.

---
 drivers/tty/serial/msm_serial.c | 5 +++++
 1 file changed, 5 insertions(+)

index 5129c2dfbe07..aac96659694d 100644
@@ -1579,6 +1579,7 @@ static inline struct uart_port *msm_get_port_from_line(unsigned int line)
 static void __msm_console_write(struct uart_port *port, const char *s,
 				unsigned int count, bool is_uartdm)
 {
+	unsigned long flags;
 	int i;
 	int num_newlines = 0;
 	bool replaced = false;

@@ -1596,6 +1597,8 @@ static void __msm_console_write(struct uart_port *port, const char *s,
 			num_newlines++;
 	count += num_newlines;
 
+	local_irq_save(flags);
+
 	if (port->sysrq)
 		locked = 0;
 	else if (oops_in_progress)

@@ -1641,6 +1644,8 @@ static void __msm_console_write(struct uart_port *port, const char *s,
 
 	if (locked)
 		spin_unlock(&port->lock);
+
+	local_irq_restore(flags);
 }
 
 static void msm_console_write(struct console *co, const char *s,

2.35.1

From: Hao Luo <[email protected]>

[ Upstream commit 1a702dc88e150487c9c173a249b3d236498b9183 ]

Previously the protection of kernfs_pr_cont_buf was piggy backed by rename_lock, which means that pr_cont() needs to be protected under rename_lock. This can cause potential circular lock dependencies.

If there is an OOM, we have the following call hierarchy:

-> cpuset_print_current_mems_allowed()
-> pr_cont_cgroup_name()

     -> pr_cont_kernfs_name()

pr_cont_kernfs_name() will grab rename_lock and call printk. So we have the following lock dependencies:

kernfs_rename_lock -> console_sem

Sometimes, printk does a wakeup before releasing console_sem, which has the dependence chain:

console_sem -> p->pi_lock -> rq->lock

Now, imagine one wants to read cgroup_name under rq->lock, for example, printing cgroup_name in a tracepoint in the scheduler code. They will be holding rq->lock and take rename_lock:

rq->lock -> kernfs_rename_lock

Now they will deadlock.

A prevention to this circular lock dependency is to separate the protection of pr_cont_buf from rename_lock. In principle, rename_lock is to protect the integrity of cgroup name when copying to buf. Once pr_cont_buf has got its content, rename_lock can be dropped. So it's safe to drop rename_lock after kernfs_name_locked (and kernfs_path_from_node_locked) and rely on a dedicated pr_cont_lock to protect pr_cont_buf.

---
 fs/kernfs/dir.c | 31 +++++++++++++++++++------------
 1 file changed, 19 insertions(+), 12 deletions(-)

index 7d4af6cea2a6..99ee657596b5 100644
@@ -19,7 +19,15 @@
 
 DEFINE_MUTEX(kernfs_mutex);
 static DEFINE_SPINLOCK(kernfs_rename_lock);	/* kn->parent and ->name */
-static char kernfs_pr_cont_buf[PATH_MAX];	/* protected by rename_lock */
+/*
+ * Don't use rename_lock to piggy back on pr_cont_buf. We don't want to
+ * call pr_cont() while holding rename_lock. Because sometimes pr_cont()
+ * will perform wakeups when releasing console_sem. Holding rename_lock
+ * will introduce deadlock if the scheduler reads the kernfs_name in the
+ * wakeup path.
+ */
+static DEFINE_SPINLOCK(kernfs_pr_cont_lock);
+static char kernfs_pr_cont_buf[PATH_MAX];	/* protected by pr_cont_lock */
 static DEFINE_SPINLOCK(kernfs_idr_lock);	/* root->ino_idr */
 
 #define rb_to_kn(X) rb_entry((X), struct kernfs_node, rb)

@@ -230,12 +238,12 @@ void pr_cont_kernfs_name(struct kernfs_node *kn)
 {
 	unsigned long flags;
 
-	spin_lock_irqsave(&kernfs_rename_lock, flags);
+	spin_lock_irqsave(&kernfs_pr_cont_lock, flags);
 
-	kernfs_name_locked(kn, kernfs_pr_cont_buf, sizeof(kernfs_pr_cont_buf));
+	kernfs_name(kn, kernfs_pr_cont_buf, sizeof(kernfs_pr_cont_buf));
 	pr_cont("%s", kernfs_pr_cont_buf);
 
-	spin_unlock_irqrestore(&kernfs_rename_lock, flags);
+	spin_unlock_irqrestore(&kernfs_pr_cont_lock, flags);
 }
 
 /**

@@ -249,10 +257,10 @@ void pr_cont_kernfs_path(struct kernfs_node *kn)
 	unsigned long flags;
 	int sz;
 
-	spin_lock_irqsave(&kernfs_rename_lock, flags);
+	spin_lock_irqsave(&kernfs_pr_cont_lock, flags);
 
-	sz = kernfs_path_from_node_locked(kn, NULL, kernfs_pr_cont_buf,
-					  sizeof(kernfs_pr_cont_buf));
+	sz = kernfs_path_from_node(kn, NULL, kernfs_pr_cont_buf,
+				   sizeof(kernfs_pr_cont_buf));
 	if (sz < 0) {
 		pr_cont("(error)");
 		goto out;

@@ -266,7 +274,7 @@ void pr_cont_kernfs_path(struct kernfs_node *kn)
 	pr_cont("%s", kernfs_pr_cont_buf);
 
 out:
-	spin_unlock_irqrestore(&kernfs_rename_lock, flags);
+	spin_unlock_irqrestore(&kernfs_pr_cont_lock, flags);
 }
 
 /**

@@ -870,13 +878,12 @@ static struct kernfs_node *kernfs_walk_ns(struct kernfs_node *parent,
 
 	lockdep_assert_held(&kernfs_mutex);
 
-	/* grab kernfs_rename_lock to piggy back on kernfs_pr_cont_buf */
-	spin_lock_irq(&kernfs_rename_lock);
+	spin_lock_irq(&kernfs_pr_cont_lock);
 
 	len = strlcpy(kernfs_pr_cont_buf, path, sizeof(kernfs_pr_cont_buf));
 
 	if (len >= sizeof(kernfs_pr_cont_buf)) {
-		spin_unlock_irq(&kernfs_rename_lock);
+		spin_unlock_irq(&kernfs_pr_cont_lock);
 		return NULL;
 	}
 

@@ -888,7 +895,7 @@ static struct kernfs_node *kernfs_walk_ns(struct kernfs_node *parent,
 		parent = kernfs_find_ns(parent, name, ns);
 	}
 
-	spin_unlock_irq(&kernfs_rename_lock);
+	spin_unlock_irq(&kernfs_pr_cont_lock);
 
 	return parent;
 }

2.35.1

From: Liu Xinpeng <[email protected]>

[ Upstream commit 27fdf84510a1374748904db43f6755f912736d92 ]

Executing reboot command several times on the machine "Dell PowerEdge R740", UEFI security detection stopped machine with the following prompt:

UEFI0082: The system was reset due to a timeout from the watchdog timer. Check the System Event Log (SEL) or crash dumps from Operating Sysstem to identify the source that triggered the watchdog timer reset. Update the firmware or driver for the identified device.

iDRAC has warning event: "The watchdog timer reset the system".

This patch fixes this issue by adding the reboot notifier.

---
 drivers/watchdog/wdat_wdt.c | 1 +
 1 file changed, 1 insertion(+)

index 88c5e6361aa0..fddbb39433be 100644
@@ -462,6 +462,7 @@ static int wdat_wdt_probe(struct platform_device *pdev)
 		return ret;
 
 	watchdog_set_nowayout(&wdat->wdd, nowayout);
+	watchdog_stop_on_reboot(&wdat->wdd);
 	return devm_watchdog_register_device(dev, &wdat->wdd);
 }
 

2.35.1

From: Guoqing Jiang <[email protected]>

[ Upstream commit 1e267742283a4b5a8ca65755c44166be27e9aa0f ]

Generally, the md_unregister_thread is called with reconfig_mutex, but raid_message in dm-raid doesn't hold reconfig_mutex to unregister thread, so md_unregister_thread can be called simulitaneously from two call sites in theory.

Then after previous commit which remove the protection of reconfig_mutex for md_unregister_thread completely, the potential issue could be worse than before.

Let's take pers_lock at the beginning of function to ensure reentrancy.

---
 drivers/md/md.c | 15 ++++++++++-----
 1 file changed, 10 insertions(+), 5 deletions(-)

index 4d1ef470f2fa..11fd3b32b562 100644
@@ -7777,17 +7777,22 @@ EXPORT_SYMBOL(md_register_thread);
 
 void md_unregister_thread(struct md_thread **threadp)
 {
-	struct md_thread *thread = *threadp;
-	if (!thread)
-		return;
-	pr_debug("interrupting MD-thread pid %d\n", task_pid_nr(thread->tsk));
-	/* Locking ensures that mddev_unlock does not wake_up a
+	struct md_thread *thread;
+
+	/*
+	 * Locking ensures that mddev_unlock does not wake_up a
 	 * non-existent thread
 	 */
 	spin_lock(&pers_lock);
+	thread = *threadp;
+	if (!thread) {
+		spin_unlock(&pers_lock);
+		return;
+	}
 	*threadp = NULL;
 	spin_unlock(&pers_lock);
 
+	pr_debug("interrupting MD-thread pid %d\n", task_pid_nr(thread->tsk));
 	kthread_stop(thread->tsk);
 	kfree(thread);
 }

2.35.1

From: Hannes Reinecke <[email protected]>

[ Upstream commit f9f0a46141e2e39bedb4779c88380d1b5f018c14 ]

When myrb_probe() fails the callback might not be set, so we need to validate the 'disable_intr' callback in myrb_cleanup() to not cause a null pointer exception. And while at it do not call myrb_cleanup() if we cannot enable the PCI device at all.

---
 drivers/scsi/myrb.c | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

index 539ac8ce4fcd..35b32920a94a 100644
@@ -1241,7 +1241,8 @@ static void myrb_cleanup(struct myrb_hba *cb)
 	myrb_unmap(cb);
 
 	if (cb->mmio_base) {
-		cb->disable_intr(cb->io_base);
+		if (cb->disable_intr)
+			cb->disable_intr(cb->io_base);
 		iounmap(cb->mmio_base);
 	}
 	if (cb->irq)

@@ -3516,9 +3517,13 @@ static struct myrb_hba *myrb_detect(struct pci_dev *pdev,
 	mutex_init(&cb->dcmd_mutex);
 	mutex_init(&cb->dma_mutex);
 	cb->pdev = pdev;
+	cb->host = shost;
 
-	if (pci_enable_device(pdev))
-		goto failure;
+	if (pci_enable_device(pdev)) {
+		dev_err(&pdev->dev, "Failed to enable PCI device\n");
+		scsi_host_put(shost);
+		return NULL;
+	}
 
 	if (privdata->hw_init == DAC960_PD_hw_init ||
 	    privdata->hw_init == DAC960_P_hw_init) {

2.35.1

From: Michal Kubecek <[email protected]>

[ Upstream commit 9c90c9b3e50e16d03c7f87d63e9db373974781e0 ]

This reverts commit 4dc2a5a8f6754492180741facf2a8787f2c415d7.

A non-zero return value from pfkey_broadcast() does not necessarily mean an error occurred as this function returns -ESRCH when no registered listener received the message. In particular, a call with BROADCAST_PROMISC_ONLY flag and null one_sk argument can never return zero so that this commit in fact prevents processing any PF_KEY message. One visible effect is that racoon daemon fails to find encryption algorithms like aes and refuses to start.

Excluding -ESRCH return value would fix this but it's not obvious that we really want to bail out here and most other callers of pfkey_broadcast() also ignore the return value. Also, as pointed out by Steffen Klassert, PF_KEY is kind of deprecated and newer userspace code should use netlink instead so that we should only disturb the code for really important fixes.

v2: add a comment explaining why is the return value ignored

---
 net/key/af_key.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

index dd064d5eff6e..32fe99cd01fc 100644
@@ -2830,10 +2830,12 @@ static int pfkey_process(struct sock *sk, struct sk_buff *skb, const struct sadb
 	void *ext_hdrs[SADB_EXT_MAX];
 	int err;
 
-	err = pfkey_broadcast(skb_clone(skb, GFP_KERNEL), GFP_KERNEL,
-			      BROADCAST_PROMISC_ONLY, NULL, sock_net(sk));
-	if (err)
-		return err;
+	/* Non-zero return value of pfkey_broadcast() does not always signal
+	 * an error and even on an actual error we may still want to process
+	 * the message so rather ignore the return value.
+	 */
+	pfkey_broadcast(skb_clone(skb, GFP_KERNEL), GFP_KERNEL,
+			BROADCAST_PROMISC_ONLY, NULL, sock_net(sk));
 
 	memset(ext_hdrs, 0, sizeof(ext_hdrs));
 	err = parse_exthdrs(skb, hdr, ext_hdrs);

2.35.1

From: Venky Shankar <[email protected]>

[ Upstream commit d7a2dc523085f8b8c60548ceedc696934aefeb0e ]

`rctime' has been a pain point in cephfs due to its buggy nature - inconsistent values reported and those sorts. Fixing rctime is non-trivial needing an overall redesign of the entire nested statistics infrastructure.

As a workaround, PR

     http://github.com/ceph/ceph/pull/37938

allows this extended attribute to be manually set. This allows users to "fixup" inconsistent rctime values. While this sounds messy, its probably the wisest approach allowing users/scripts to workaround buggy rctime values.

The above PR enables Ceph MDS to allow manually setting rctime extended attribute with the corresponding user-land changes. We may as well allow the same to be done via kclient for parity.

---
 fs/ceph/xattr.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

index cb18ee637cb7..4bcf0226818d 100644
@@ -316,6 +316,14 @@ static ssize_t ceph_vxattrcb_snap_btime(struct ceph_inode_info *ci, char *val,
 	}
 #define XATTR_RSTAT_FIELD(_type, _name)			\
 	XATTR_NAME_CEPH(_type, _name, VXATTR_FLAG_RSTAT)
+#define XATTR_RSTAT_FIELD_UPDATABLE(_type, _name)			\
+	{								\
+		.name = CEPH_XATTR_NAME(_type, _name),			\
+		.name_size = sizeof (CEPH_XATTR_NAME(_type, _name)),	\
+		.getxattr_cb = ceph_vxattrcb_ ## _type ## _ ## _name,	\
+		.exists_cb = NULL,					\
+		.flags = VXATTR_FLAG_RSTAT,				\
+	}
 #define XATTR_LAYOUT_FIELD(_type, _name, _field)			\
 	{								\
 		.name = CEPH_XATTR_NAME2(_type, _name, _field),	\

@@ -353,7 +361,7 @@ static struct ceph_vxattr ceph_dir_vxattrs[] = {
 	XATTR_RSTAT_FIELD(dir, rfiles),
 	XATTR_RSTAT_FIELD(dir, rsubdirs),
 	XATTR_RSTAT_FIELD(dir, rbytes),
-	XATTR_RSTAT_FIELD(dir, rctime),
+	XATTR_RSTAT_FIELD_UPDATABLE(dir, rctime),
 	{
 		.name = "ceph.dir.pin",
 		.name_size = sizeof("ceph.dir.pin"),

2.35.1

From: Gong Yuanjun <[email protected]>

[ Upstream commit a2b28708b645c5632dc93669ab06e97874c8244f ]

In radeon_fp_native_mode(), the return value of drm_mode_duplicate() is assigned to mode, which will lead to a NULL pointer dereference on failure of drm_mode_duplicate(). Add a check to avoid npd.

The failure status of drm_cvt_mode() on the other path is checked too.

---
 drivers/gpu/drm/radeon/radeon_connectors.c | 4 ++++
 1 file changed, 4 insertions(+)

index bc63f4cecf5d..ca6ccd69424e 100644
@@ -477,6 +477,8 @@ static struct drm_display_mode *radeon_fp_native_mode(struct drm_encoder *encode
 	    native_mode->vdisplay != 0 &&
 	    native_mode->clock != 0) {
 		mode = drm_mode_duplicate(dev, native_mode);
+		if (!mode)
+			return NULL;
 		mode->type = DRM_MODE_TYPE_PREFERRED | DRM_MODE_TYPE_DRIVER;
 		drm_mode_set_name(mode);
 

@@ -491,6 +493,8 @@ static struct drm_display_mode *radeon_fp_native_mode(struct drm_encoder *encode
 		 * simpler.
 		 */
 		mode = drm_cvt_mode(dev, native_mode->hdisplay, native_mode->vdisplay, 60, true, false, false);
+		if (!mode)
+			return NULL;
 		mode->type = DRM_MODE_TYPE_PREFERRED | DRM_MODE_TYPE_DRIVER;
 		DRM_DEBUG_KMS("Adding cvt approximation of native panel mode %s\n", mode->name);
 	}

2.35.1

From: Masahiro Yamada <[email protected]>

[ Upstream commit d6b732666a1bae0df3c3ae06925043bba34502b1 ]

The return value of is_arm_mapping_symbol() is unpredictable when "$" is passed in.

strchr(3) says:
The strchr() and strrchr() functions return a pointer to the matched character or NULL if the character is not found. The terminating null byte is considered part of the string, so that if c is specified as '\0', these functions return a pointer to the terminator.

When str[1] is '\0', strchr("axtd", str[1]) is not NULL, and str[2] is referenced (i.e. buffer overrun).

Test code
---------

  char str1[] = "abc";
  char str2[] = "ab";

  strcpy(str1, "$");
  strcpy(str2, "$");

  printf("test1: %d\n", is_arm_mapping_symbol(str1));
  printf("test2: %d\n", is_arm_mapping_symbol(str2));

Result
------

test1: 0
test2: 1

---
 scripts/mod/modpost.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

index 74e2052f429d..59011ddf8bb8 100644
@@ -1283,7 +1283,8 @@ static int secref_whitelist(const struct sectioncheck *mismatch,
 
 static inline int is_arm_mapping_symbol(const char *str)
 {
-	return str[0] == '$' && strchr("axtd", str[1])
+	return str[0] == '$' &&
+	       (str[1] == 'a' || str[1] == 'd' || str[1] == 't' || str[1] == 'x')
 	       && (str[2] == '\0' || str[2] == '.');
 }
 

2.35.1

From: Peter Zijlstra <[email protected]>

[ Upstream commit a6a5eb269f6f3a2fe392f725a8d9052190c731e2 ]

As x86 uses the <asm-generic/bitops/instrumented-*.h> headers, the regular forms of all bitops are instrumented with explicit calls to KASAN and KCSAN checks. As these are explicit calls, these are not suppressed by the noinstr function attribute.

This can result in calls to those check functions in noinstr code, which objtool warns about:

vmlinux.o: warning: objtool: enter_from_user_mode+0x24: call to __kcsan_check_access() leaves .noinstr.text section vmlinux.o: warning: objtool: syscall_enter_from_user_mode+0x28: call to __kcsan_check_access() leaves .noinstr.text section vmlinux.o: warning: objtool: syscall_enter_from_user_mode_prepare+0x24: call to __kcsan_check_access() leaves .noinstr.text section vmlinux.o: warning: objtool: irqentry_enter_from_user_mode+0x24: call to __kcsan_check_access() leaves .noinstr.text section

Prevent this by using the arch_*() bitops, which are the underlying bitops without explciit instrumentation.

---
 arch/x86/include/asm/cpufeature.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index 59bf91c57aa8..619c1f80a2ab 100644
@@ -49,7 +49,7 @@ extern const char * const x86_power_flags[32];
 extern const char * const x86_bug_flags[NBUGINTS*32];
 
 #define test_cpu_cap(c, bit)						\
-	 test_bit(bit, (unsigned long *)((c)->x86_capability))
+	 arch_test_bit(bit, (unsigned long *)((c)->x86_capability))
 
 /*
  * There are 32 bits/features in each mask word.  The high bits

2.35.1

From: Yu Kuai <[email protected]>

[ Upstream commit 06c4da89c24e7023ea448cadf8e9daf06a0aae6e ]

Otherwise there may be race between module removal and the handling of netlink command, which can lead to the oops as shown below:

  BUG: kernel NULL pointer dereference, address: 0000000000000098
  Oops: 0002 [#1] SMP PTI
  CPU: 1 PID: 31299 Comm: nbd-client Tainted: G            E     5.14.0-rc4
  Hardware name: QEMU Standard PC (i440FX + PIIX, 1996)
  RIP: 0010:down_write+0x1a/0x50
  Call Trace:
   start_creating+0x89/0x130
   debugfs_create_dir+0x1b/0x130
   nbd_start_device+0x13d/0x390 [nbd]
   nbd_genl_connect+0x42f/0x748 [nbd]
   genl_family_rcv_msg_doit.isra.0+0xec/0x150
   genl_rcv_msg+0xe5/0x1e0
   netlink_rcv_skb+0x55/0x100
   genl_rcv+0x29/0x40
   netlink_unicast+0x1a8/0x250
   netlink_sendmsg+0x21b/0x430
   ____sys_sendmsg+0x2a4/0x2d0
   ___sys_sendmsg+0x81/0xc0
   __sys_sendmsg+0x62/0xb0
   __x64_sys_sendmsg+0x1f/0x30
   do_syscall_64+0x3b/0xc0
   entry_SYSCALL_64_after_hwframe+0x44/0xae
  Modules linked in: nbd(E-)

---
 drivers/block/nbd.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

index 510e75435c43..f3425e51a54b 100644
@@ -2446,6 +2446,12 @@ static void __exit nbd_cleanup(void)
 	struct nbd_device *nbd;
 	LIST_HEAD(del_list);
 
+	/*
+	 * Unregister netlink interface prior to waiting
+	 * for the completion of netlink commands.
+	 */
+	genl_unregister_family(&nbd_genl_family);
+
 	nbd_dbg_close();
 
 	mutex_lock(&nbd_index_mutex);

@@ -2461,7 +2467,6 @@ static void __exit nbd_cleanup(void)
 	}
 
 	idr_destroy(&nbd_index_idr);
-	genl_unregister_family(&nbd_genl_family);
 	unregister_blkdev(NBD_MAJOR, "nbd");
 }
 

2.35.1

From: Yu Kuai <[email protected]>

[ Upstream commit c55b2b983b0fa012942c3eb16384b2b722caa810 ]

When nbd module is being removing, nbd_alloc_config() may be called concurrently by nbd_genl_connect(), although try_module_get() will return false, but nbd_alloc_config() doesn't handle it.

The race may lead to the leak of nbd_config and its related resources (e.g, recv_workq) and oops in nbd_read_stat() due to the unload of nbd module as shown below:

  BUG: kernel NULL pointer dereference, address: 0000000000000040
  Oops: 0000 [#1] SMP PTI
  CPU: 5 PID: 13840 Comm: kworker/u17:33 Not tainted 5.14.0+ #1
  Hardware name: QEMU Standard PC (i440FX + PIIX, 1996)
  Workqueue: knbd16-recv recv_work [nbd]
  RIP: 0010:nbd_read_stat.cold+0x130/0x1a4 [nbd]
  Call Trace:
   recv_work+0x3b/0xb0 [nbd]
   process_one_work+0x1ed/0x390
   worker_thread+0x4a/0x3d0
   kthread+0x12a/0x150
   ret_from_fork+0x22/0x30

Fixing it by checking the return value of try_module_get()
in nbd_alloc_config(). As nbd_alloc_config() may return ERR_PTR(-ENODEV), assign nbd->config only when nbd_alloc_config() succeeds to ensure the value of nbd->config is binary (valid or NULL).

Also adding a debug message to check the reference counter of nbd_config during module removal.

---
 drivers/block/nbd.c | 28 +++++++++++++++++++---------
 1 file changed, 19 insertions(+), 9 deletions(-)

index f3425e51a54b..ef355f14ed2c 100644
@@ -1457,15 +1457,20 @@ static struct nbd_config *nbd_alloc_config(void)
 {
 	struct nbd_config *config;
 
+	if (!try_module_get(THIS_MODULE))
+		return ERR_PTR(-ENODEV);
+
 	config = kzalloc(sizeof(struct nbd_config), GFP_NOFS);
-	if (!config)
-		return NULL;
+	if (!config) {
+		module_put(THIS_MODULE);
+		return ERR_PTR(-ENOMEM);
+	}
+
 	atomic_set(&config->recv_threads, 0);
 	init_waitqueue_head(&config->recv_wq);
 	init_waitqueue_head(&config->conn_wait);
 	config->blksize = NBD_DEF_BLKSIZE;
 	atomic_set(&config->live_connections, 0);
-	try_module_get(THIS_MODULE);
 	return config;
 }
 

@@ -1492,12 +1497,13 @@ static int nbd_open(struct block_device *bdev, fmode_t mode)
 			mutex_unlock(&nbd->config_lock);
 			goto out;
 		}
-		config = nbd->config = nbd_alloc_config();
-		if (!config) {
-			ret = -ENOMEM;
+		config = nbd_alloc_config();
+		if (IS_ERR(config)) {
+			ret = PTR_ERR(config);
 			mutex_unlock(&nbd->config_lock);
 			goto out;
 		}
+		nbd->config = config;
 		refcount_set(&nbd->config_refs, 1);
 		refcount_inc(&nbd->refs);
 		mutex_unlock(&nbd->config_lock);

@@ -1919,13 +1925,14 @@ static int nbd_genl_connect(struct sk_buff *skb, struct genl_info *info)
 		nbd_put(nbd);
 		return -EINVAL;
 	}
-	config = nbd->config = nbd_alloc_config();
-	if (!nbd->config) {
+	config = nbd_alloc_config();
+	if (IS_ERR(config)) {
 		mutex_unlock(&nbd->config_lock);
 		nbd_put(nbd);
 		printk(KERN_ERR "nbd: couldn't allocate config\n");
-		return -ENOMEM;
+		return PTR_ERR(config);
 	}
+	nbd->config = config;
 	refcount_set(&nbd->config_refs, 1);
 	set_bit(NBD_RT_BOUND, &config->runtime_flags);
 

@@ -2461,6 +2468,9 @@ static void __exit nbd_cleanup(void)
 	while (!list_empty(&del_list)) {
 		nbd = list_first_entry(&del_list, struct nbd_device, list);
 		list_del_init(&nbd->list);
+		if (refcount_read(&nbd->config_refs))
+			printk(KERN_ERR "nbd: possibly leaking nbd_config (ref %d)\n",
+					refcount_read(&nbd->config_refs));
 		if (refcount_read(&nbd->refs) != 1)
 			printk(KERN_ERR "nbd: possibly leaking a device\n");
 		nbd_put(nbd);

2.35.1

From: Yu Kuai <[email protected]>

[ Upstream commit 09dadb5985023e27d4740ebd17e6fea4640110e5 ]

In our tests, "qemu-nbd" triggers a io hung:

INFO: task qemu-nbd:11445 blocked for more than 368 seconds.
      Not tainted 5.18.0-rc3-next-20220422-00003-g2176915513ca #884
"echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
task:qemu-nbd        state:D stack:    0 pid:11445 ppid:     1 flags:0x00000000
Call Trace:
 <TASK>
 __schedule+0x480/0x1050
 ? _raw_spin_lock_irqsave+0x3e/0xb0
 schedule+0x9c/0x1b0
 blk_mq_freeze_queue_wait+0x9d/0xf0
 ? ipi_rseq+0x70/0x70
 blk_mq_freeze_queue+0x2b/0x40
 nbd_add_socket+0x6b/0x270 [nbd]
 nbd_ioctl+0x383/0x510 [nbd]
 blkdev_ioctl+0x18e/0x3e0
 __x64_sys_ioctl+0xac/0x120
 do_syscall_64+0x35/0x80
 entry_SYSCALL_64_after_hwframe+0x44/0xae
RIP: 0033:0x7fd8ff706577
RSP: 002b:00007fd8fcdfebf8 EFLAGS: 00000246 ORIG_RAX: 0000000000000010
RAX: ffffffffffffffda RBX: 0000000040000000 RCX: 00007fd8ff706577
RDX: 000000000000000d RSI: 000000000000ab00 RDI: 000000000000000f
RBP: 000000000000000f R08: 000000000000fbe8 R09: 000055fe497c62b0
R10: 00000002aff20000 R11: 0000000000000246 R12: 000000000000006d
R13: 0000000000000000 R14: 00007ffe82dc5e70 R15: 00007fd8fcdff9c0

"qemu-ndb -d" will call ioctl 'NBD_DISCONNECT' first, however, following message was found:

block nbd0: Send disconnect failed -32

Which indicate that something is wrong with the server. Then, "qemu-nbd -d" will call ioctl 'NBD_CLEAR_SOCK', however ioctl can't clear requests after commit 2516ab1543fd("nbd: only clear the queue on device teardown"). And in the meantime, request can't complete through timeout because nbd_xmit_timeout() will always return 'BLK_EH_RESET_TIMER', which means such request will never be completed in this situation.

Now that the flag 'NBD_CMD_INFLIGHT' can make sure requests won't complete multiple times, switch back to call nbd_clear_sock() in nbd_clear_sock_ioctl(), so that inflight requests can be cleared.

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

index ef355f14ed2c..09323b0510f0 100644
@@ -1344,7 +1344,7 @@ static int nbd_start_device_ioctl(struct nbd_device *nbd, struct block_device *b
 static void nbd_clear_sock_ioctl(struct nbd_device *nbd,
 				 struct block_device *bdev)
 {
-	sock_shutdown(nbd);
+	nbd_clear_sock(nbd);
 	__invalidate_device(bdev, true);
 	nbd_bdev_reset(bdev);
 	if (test_and_clear_bit(NBD_RT_HAS_CONFIG_REF,

2.35.1

From: Christian Borntraeger <[email protected]>

[ Upstream commit 6d5946274df1fff539a7eece458a43be733d1db8 ]

With large and many guest with storage keys it is possible to create large latencies or stalls during initial key setting:

rcu: INFO: rcu_sched self-detected stall on CPU
rcu:   18-....: (2099 ticks this GP) idle=54e/1/0x4000000000000002 softirq=35598716/35598716 fqs=998
       (t=2100 jiffies g=155867385 q=20879)
Task dump for CPU 18:
CPU 1/KVM       R  running task        0 1030947 256019 0x06000004
Call Trace:

sched_show_task
rcu_dump_cpu_stacks
rcu_sched_clock_irq
update_process_times
tick_sched_handle
tick_sched_timer
__hrtimer_run_queues
hrtimer_interrupt
do_IRQ
ext_int_handler
ptep_zap_key

The mmap lock is held during the page walking but since this is a semaphore scheduling is still possible. Same for the kvm srcu. To minimize overhead do this on every segment table entry or large page.

---
 arch/s390/mm/gmap.c | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

index 5e5a4e1f0e6c..19ee8355b2a7 100644
@@ -2579,6 +2579,18 @@ static int __s390_enable_skey_pte(pte_t *pte, unsigned long addr,
 	return 0;
 }
 
+/*
+ * Give a chance to schedule after setting a key to 256 pages.
+ * We only hold the mm lock, which is a rwsem and the kvm srcu.
+ * Both can sleep.
+ */
+static int __s390_enable_skey_pmd(pmd_t *pmd, unsigned long addr,
+				  unsigned long next, struct mm_walk *walk)
+{
+	cond_resched();
+	return 0;
+}
+
 static int __s390_enable_skey_hugetlb(pte_t *pte, unsigned long addr,
 				      unsigned long hmask, unsigned long next,
 				      struct mm_walk *walk)

@@ -2601,12 +2613,14 @@ static int __s390_enable_skey_hugetlb(pte_t *pte, unsigned long addr,
 	end = start + HPAGE_SIZE - 1;
 	__storage_key_init_range(start, end);
 	set_bit(PG_arch_1, &page->flags);
+	cond_resched();
 	return 0;
 }
 
 static const struct mm_walk_ops enable_skey_walk_ops = {
 	.hugetlb_entry		= __s390_enable_skey_hugetlb,
 	.pte_entry		= __s390_enable_skey_pte,
+	.pmd_entry		= __s390_enable_skey_pmd,
 };
 
 int s390_enable_skey(void)

2.35.1

From: Steve French <[email protected]>

[ Upstream commit 7ef93ffccd55fb0ba000ed16ef6a81cd7dee07b5 ]

We should not be including unused smb20 specific code when legacy support is disabled (CONFIG_CIFS_ALLOW_INSECURE_LEGACY turned off). For example smb2_operations and smb2_values aren't used in that case. Over time we can move more and more SMB1/CIFS and SMB2.0 code into the insecure legacy ifdefs

---
 fs/cifs/cifsglob.h | 4 +++-
 fs/cifs/smb2ops.c  | 7 ++++++-
 2 files changed, 9 insertions(+), 2 deletions(-)

index 9c0e348cb00f..414936989255 100644
@@ -1930,11 +1930,13 @@ extern mempool_t *cifs_mid_poolp;
 
 /* Operations for different SMB versions */
 #define SMB1_VERSION_STRING	"1.0"
+#define SMB20_VERSION_STRING    "2.0"
+#ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY
 extern struct smb_version_operations smb1_operations;
 extern struct smb_version_values smb1_values;
-#define SMB20_VERSION_STRING	"2.0"
 extern struct smb_version_operations smb20_operations;
 extern struct smb_version_values smb20_values;
+#endif /* CIFS_ALLOW_INSECURE_LEGACY */
 #define SMB21_VERSION_STRING	"2.1"
 extern struct smb_version_operations smb21_operations;
 extern struct smb_version_values smb21_values;

index 7985fe25850b..57164563eec6 100644
@@ -3487,11 +3487,13 @@ smb3_set_oplock_level(struct cifsInodeInfo *cinode, __u32 oplock,
 	}
 }
 
+#ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY
 static bool
 smb2_is_read_op(__u32 oplock)
 {
 	return oplock == SMB2_OPLOCK_LEVEL_II;
 }
+#endif /* CIFS_ALLOW_INSECURE_LEGACY */
 
 static bool
 smb21_is_read_op(__u32 oplock)

@@ -4573,7 +4575,7 @@ smb2_make_node(unsigned int xid, struct inode *inode,
 	return rc;
 }
 
-
+#ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY
 struct smb_version_operations smb20_operations = {
 	.compare_fids = smb2_compare_fids,
 	.setup_request = smb2_setup_request,

@@ -4670,6 +4672,7 @@ struct smb_version_operations smb20_operations = {
 	.fiemap = smb3_fiemap,
 	.llseek = smb3_llseek,
 };
+#endif /* CIFS_ALLOW_INSECURE_LEGACY */
 
 struct smb_version_operations smb21_operations = {
 	.compare_fids = smb2_compare_fids,

@@ -4987,6 +4990,7 @@ struct smb_version_operations smb311_operations = {
 	.llseek = smb3_llseek,
 };
 
+#ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY
 struct smb_version_values smb20_values = {
 	.version_string = SMB20_VERSION_STRING,
 	.protocol_id = SMB20_PROT_ID,

@@ -5007,6 +5011,7 @@ struct smb_version_values smb20_values = {
 	.signing_required = SMB2_NEGOTIATE_SIGNING_REQUIRED,
 	.create_lease_size = sizeof(struct create_lease),
 };
+#endif /* ALLOW_INSECURE_LEGACY */
 
 struct smb_version_values smb21_values = {
 	.version_string = SMB21_VERSION_STRING,

2.35.1

From: Kees Cook <[email protected]>

[ Upstream commit 0dfe54071d7c828a02917b595456bfde1afdddc9 ]

The nodemask routines had mixed return values that provided potentially signed return values that could never happen. This was leading to the compiler getting confusing about the range of possible return values (it was thinking things could be negative where they could not be). Fix all the nodemask routines that should be returning unsigned (or bool) values. Silences:

mm/swapfile.c: In function ‘setup_swap_info’:
mm/swapfile.c:2291:47: error: array subscript -1 is below array bounds of ‘struct plist_node[]’ [-Werror=array-bounds]

  2291 |                                 p->avail_lists[i].prio = 1;
       |                                 ~~~~~~~~~~~~~~^~~
 In file included from mm/swapfile.c:16:
 ./include/linux/swap.h:292:27: note: while referencing ‘avail_lists’
   292 |         struct plist_node avail_lists[]; /*
       |                           ^~~~~~~~~~~

---
 include/linux/nodemask.h | 38 +++++++++++++++++++-------------------
 lib/nodemask.c           |  4 ++--
 2 files changed, 21 insertions(+), 21 deletions(-)

index 8a404dfeec42..a8d79f5b9a52 100644
@@ -42,11 +42,11 @@
  * void nodes_shift_right(dst, src, n)	Shift right
  * void nodes_shift_left(dst, src, n)	Shift left
  *
- * int first_node(mask)			Number lowest set bit, or MAX_NUMNODES
- * int next_node(node, mask)		Next node past 'node', or MAX_NUMNODES
- * int next_node_in(node, mask)		Next node past 'node', or wrap to first,
+ * unsigned int first_node(mask)	Number lowest set bit, or MAX_NUMNODES
+ * unsigend int next_node(node, mask)	Next node past 'node', or MAX_NUMNODES
+ * unsigned int next_node_in(node, mask) Next node past 'node', or wrap to first,
  *					or MAX_NUMNODES
- * int first_unset_node(mask)		First node not set in mask, or 
+ * unsigned int first_unset_node(mask)	First node not set in mask, or
  *					MAX_NUMNODES
  *
  * nodemask_t nodemask_of_node(node)	Return nodemask with bit 'node' set

@@ -153,7 +153,7 @@ static inline void __nodes_clear(nodemask_t *dstp, unsigned int nbits)
 
 #define node_test_and_set(node, nodemask) \
 			__node_test_and_set((node), &(nodemask))
-static inline int __node_test_and_set(int node, nodemask_t *addr)
+static inline bool __node_test_and_set(int node, nodemask_t *addr)
 {
 	return test_and_set_bit(node, addr->bits);
 }

@@ -200,7 +200,7 @@ static inline void __nodes_complement(nodemask_t *dstp,
 
 #define nodes_equal(src1, src2) \
 			__nodes_equal(&(src1), &(src2), MAX_NUMNODES)
-static inline int __nodes_equal(const nodemask_t *src1p,
+static inline bool __nodes_equal(const nodemask_t *src1p,
 					const nodemask_t *src2p, unsigned int nbits)
 {
 	return bitmap_equal(src1p->bits, src2p->bits, nbits);

@@ -208,7 +208,7 @@ static inline int __nodes_equal(const nodemask_t *src1p,
 
 #define nodes_intersects(src1, src2) \
 			__nodes_intersects(&(src1), &(src2), MAX_NUMNODES)
-static inline int __nodes_intersects(const nodemask_t *src1p,
+static inline bool __nodes_intersects(const nodemask_t *src1p,
 					const nodemask_t *src2p, unsigned int nbits)
 {
 	return bitmap_intersects(src1p->bits, src2p->bits, nbits);

@@ -216,20 +216,20 @@ static inline int __nodes_intersects(const nodemask_t *src1p,
 
 #define nodes_subset(src1, src2) \
 			__nodes_subset(&(src1), &(src2), MAX_NUMNODES)
-static inline int __nodes_subset(const nodemask_t *src1p,
+static inline bool __nodes_subset(const nodemask_t *src1p,
 					const nodemask_t *src2p, unsigned int nbits)
 {
 	return bitmap_subset(src1p->bits, src2p->bits, nbits);
 }
 
 #define nodes_empty(src) __nodes_empty(&(src), MAX_NUMNODES)
-static inline int __nodes_empty(const nodemask_t *srcp, unsigned int nbits)
+static inline bool __nodes_empty(const nodemask_t *srcp, unsigned int nbits)
 {
 	return bitmap_empty(srcp->bits, nbits);
 }
 
 #define nodes_full(nodemask) __nodes_full(&(nodemask), MAX_NUMNODES)
-static inline int __nodes_full(const nodemask_t *srcp, unsigned int nbits)
+static inline bool __nodes_full(const nodemask_t *srcp, unsigned int nbits)
 {
 	return bitmap_full(srcp->bits, nbits);
 }

@@ -260,15 +260,15 @@ static inline void __nodes_shift_left(nodemask_t *dstp,
           > MAX_NUMNODES, then the silly min_ts could be dropped. */
 
 #define first_node(src) __first_node(&(src))
-static inline int __first_node(const nodemask_t *srcp)
+static inline unsigned int __first_node(const nodemask_t *srcp)
 {
-	return min_t(int, MAX_NUMNODES, find_first_bit(srcp->bits, MAX_NUMNODES));
+	return min_t(unsigned int, MAX_NUMNODES, find_first_bit(srcp->bits, MAX_NUMNODES));
 }
 
 #define next_node(n, src) __next_node((n), &(src))
-static inline int __next_node(int n, const nodemask_t *srcp)
+static inline unsigned int __next_node(int n, const nodemask_t *srcp)
 {
-	return min_t(int,MAX_NUMNODES,find_next_bit(srcp->bits, MAX_NUMNODES, n+1));
+	return min_t(unsigned int, MAX_NUMNODES, find_next_bit(srcp->bits, MAX_NUMNODES, n+1));
 }
 
 /*

@@ -276,7 +276,7 @@ static inline int __next_node(int n, const nodemask_t *srcp)
  * the first node in src if needed.  Returns MAX_NUMNODES if src is empty.
  */
 #define next_node_in(n, src) __next_node_in((n), &(src))
-int __next_node_in(int node, const nodemask_t *srcp);
+unsigned int __next_node_in(int node, const nodemask_t *srcp);
 
 static inline void init_nodemask_of_node(nodemask_t *mask, int node)
 {

@@ -296,9 +296,9 @@ static inline void init_nodemask_of_node(nodemask_t *mask, int node)
 })
 
 #define first_unset_node(mask) __first_unset_node(&(mask))
-static inline int __first_unset_node(const nodemask_t *maskp)
+static inline unsigned int __first_unset_node(const nodemask_t *maskp)
 {
-	return min_t(int,MAX_NUMNODES,
+	return min_t(unsigned int, MAX_NUMNODES,
 			find_first_zero_bit(maskp->bits, MAX_NUMNODES));
 }
 

@@ -434,11 +434,11 @@ static inline int num_node_state(enum node_states state)
 
 #define first_online_node	first_node(node_states[N_ONLINE])
 #define first_memory_node	first_node(node_states[N_MEMORY])
-static inline int next_online_node(int nid)
+static inline unsigned int next_online_node(int nid)
 {
 	return next_node(nid, node_states[N_ONLINE]);
 }
-static inline int next_memory_node(int nid)
+static inline unsigned int next_memory_node(int nid)
 {
 	return next_node(nid, node_states[N_MEMORY]);
 }

index 3aa454c54c0d..e22647f5181b 100644
@@ -3,9 +3,9 @@
 #include <linux/module.h>
 #include <linux/random.h>
 
-int __next_node_in(int node, const nodemask_t *srcp)
+unsigned int __next_node_in(int node, const nodemask_t *srcp)
 {
-	int ret = __next_node(node, srcp);
+	unsigned int ret = __next_node(node, srcp);
 
 	if (ret == MAX_NUMNODES)
 		ret = __first_node(srcp);

2.35.1

From: Xie Yongji <[email protected]>

[ Upstream commit dbd29e0752286af74243cf891accf472b2f3edd8 ]

We should use size of descriptor chain to test loop condition in the indirect case. And another statistical count is also introduced for indirect descriptors to avoid conflict with the statistical count of direct descriptors.

Message-Id: <[email protected]>

---
 drivers/vhost/vringh.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

index 4653de001e26..264cbe385a63 100644
@@ -264,7 +264,7 @@ __vringh_iov(struct vringh *vrh, u16 i,
 	     gfp_t gfp,
 	     int (*copy)(void *dst, const void *src, size_t len))
 {
-	int err, count = 0, up_next, desc_max;
+	int err, count = 0, indirect_count = 0, up_next, desc_max;
 	struct vring_desc desc, *descs;
 	struct vringh_range range = { -1ULL, 0 }, slowrange;
 	bool slow = false;

@@ -321,7 +321,12 @@ __vringh_iov(struct vringh *vrh, u16 i,
 			continue;
 		}
 
-		if (count++ == vrh->vring.num) {
+		if (up_next == -1)
+			count++;
+		else
+			indirect_count++;
+
+		if (count > vrh->vring.num || indirect_count > desc_max) {
 			vringh_bad("Descriptor loop in %p", descs);
 			err = -ELOOP;
 			goto fail;