5.10.236-rc1 review

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

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

From: Hou Tao <[email protected]>

[ Upstream commit b4a8b5bba712a711d8ca1f7d04646db63f9c88f5 ]

bpf_send_signal_common() uses preemptible() to check whether or not the current context is preemptible. If it is preemptible, it will use irq_work to send the signal asynchronously instead of trying to hold a spin-lock, because spin-lock is sleepable under PREEMPT_RT.

However, preemptible() depends on CONFIG_PREEMPT_COUNT. When CONFIG_PREEMPT_COUNT is turned off (e.g., CONFIG_PREEMPT_VOLUNTARY=y), !preemptible() will be evaluated as 1 and bpf_send_signal_common() will use irq_work unconditionally.

Fix it by unfolding "!preemptible()" and using "preempt_count() != 0 || irqs_disabled()" instead.

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

index 1656a7d9bb697..6957381b139ce 100644
@@ -1081,7 +1081,7 @@ static int bpf_send_signal_common(u32 sig, enum pid_type type)
 	if (unlikely(is_global_init(current)))
 		return -EPERM;
 
-	if (!preemptible()) {
+	if (preempt_count() != 0 || irqs_disabled()) {
 		/* Do an early check on signal validity. Otherwise,
 		 * the error is lost in deferred irq_work.
 		 */

2.39.5

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

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

From: Tanya Agarwal <[email protected]>

[ Upstream commit af324dc0e2b558678aec42260cce38be16cc77ca ]

The static code analysis tool "Coverity Scan" pointed the following implementation details out for further development considerations:
CID 1309755: Unused value
In sw842_compress: A value assigned to a variable is never used. (CWE-563)
returned_value: Assigning value from add_repeat_template(p, repeat_count) to ret here, but that stored value is overwritten before it can be used.

Conclusion:
Add error handling for the return value from an add_repeat_template() call.

---
 lib/842/842_compress.c | 2 ++
 1 file changed, 2 insertions(+)

index c02baa4168e16..055356508d97c 100644
@@ -532,6 +532,8 @@ int sw842_compress(const u8 *in, unsigned int ilen,
 		}
 		if (repeat_count) {
 			ret = add_repeat_template(p, repeat_count);
+			if (ret)
+				return ret;
 			repeat_count = 0;
 			if (next == last) /* reached max repeat bits */
 				goto repeat;

2.39.5

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

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

From: Fabrizio Castro <[email protected]>

[ Upstream commit abcdeb4e299a11ecb5a3ea0cce00e68e8f540375 ]

of_parse_phandle_with_fixed_args() requires its caller to call into of_node_put() on the node pointer from the output structure, but such a call is currently missing.

Call into of_node_put() to rectify that.

---
 drivers/pinctrl/renesas/pinctrl-rza2.c | 2 ++
 1 file changed, 2 insertions(+)

index ddd8ee6b604ef..1fd3191d9f8d9 100644
@@ -253,6 +253,8 @@ static int rza2_gpio_register(struct rza2_pinctrl_priv *priv)
 		return ret;
 	}
 
+	of_node_put(of_args.np);
+
 	if ((of_args.args[0] != 0) ||
 	    (of_args.args[1] != 0) ||
 	    (of_args.args[2] != priv->npins)) {

2.39.5

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

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

From: Peter Geis <[email protected]>

[ Upstream commit a9e60f1ffe1ca57d6af6a2573e2f950e76efbf5b ]

Correct the clk_ref_usb3otg parent to fix clock control for the usb3 controller on rk3328. Verified against the rk3328 trm, the rk3228h trm, and the rk3328 usb3 phy clock map.

---
 drivers/clk/rockchip/clk-rk3328.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index 2429b7c2a8b31..f021887147499 100644
@@ -200,7 +200,7 @@ PNAME(mux_aclk_peri_pre_p)	= { "cpll_peri",
 				    "gpll_peri",
 				    "hdmiphy_peri" };
 PNAME(mux_ref_usb3otg_src_p)	= { "xin24m",
-				    "clk_usb3otg_ref" };
+				    "clk_ref_usb3otg_src" };
 PNAME(mux_xin24m_32k_p)		= { "xin24m",
 				    "clk_rtc32k" };
 PNAME(mux_mac2io_src_p)		= { "clk_mac2io_src",

2.39.5

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

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

From: Maher Sanalla <[email protected]>

[ Upstream commit 37826f0a8c2f6b6add5179003b8597e32a445362 ]

The ib_post_receive_mads() function handles posting receive work requests (WRs) to MAD QPs and is called in two cases:
1) When a MAD port is opened.
2) When a receive WQE is consumed upon receiving a new MAD.

Whereas, if MADs arrive during the port open phase, a race condition might cause an extra WR to be posted, exceeding the QP’s capacity. This leads to failures such as:
infiniband mlx5_0: ib_post_recv failed: -12
infiniband mlx5_0: Couldn't post receive WRs
infiniband mlx5_0: Couldn't start port
infiniband mlx5_0: Couldn't open port 1

Fix this by checking the current receive count before posting a new WR. If the QP’s receive queue is full, do not post additional WRs.

---
 drivers/infiniband/core/mad.c | 38 ++++++++++++++++++-----------------
 1 file changed, 20 insertions(+), 18 deletions(-)

index 521c3d050be2d..19540a13cb84d 100644
@@ -2686,11 +2686,11 @@ static int ib_mad_post_receive_mads(struct ib_mad_qp_info *qp_info,
 				    struct ib_mad_private *mad)
 {
 	unsigned long flags;
-	int post, ret;
 	struct ib_mad_private *mad_priv;
 	struct ib_sge sg_list;
 	struct ib_recv_wr recv_wr;
 	struct ib_mad_queue *recv_queue = &qp_info->recv_queue;
+	int ret = 0;
 
 	/* Initialize common scatter list fields */
 	sg_list.lkey = qp_info->port_priv->pd->local_dma_lkey;

@@ -2700,7 +2700,7 @@ static int ib_mad_post_receive_mads(struct ib_mad_qp_info *qp_info,
 	recv_wr.sg_list = &sg_list;
 	recv_wr.num_sge = 1;
 
-	do {
+	while (true) {
 		/* Allocate and map receive buffer */
 		if (mad) {
 			mad_priv = mad;

@@ -2708,10 +2708,8 @@ static int ib_mad_post_receive_mads(struct ib_mad_qp_info *qp_info,
 		} else {
 			mad_priv = alloc_mad_private(port_mad_size(qp_info->port_priv),
 						     GFP_ATOMIC);
-			if (!mad_priv) {
-				ret = -ENOMEM;
-				break;
-			}
+			if (!mad_priv)
+				return -ENOMEM;
 		}
 		sg_list.length = mad_priv_dma_size(mad_priv);
 		sg_list.addr = ib_dma_map_single(qp_info->port_priv->device,

@@ -2720,37 +2718,41 @@ static int ib_mad_post_receive_mads(struct ib_mad_qp_info *qp_info,
 						 DMA_FROM_DEVICE);
 		if (unlikely(ib_dma_mapping_error(qp_info->port_priv->device,
 						  sg_list.addr))) {
-			kfree(mad_priv);
 			ret = -ENOMEM;
-			break;
+			goto free_mad_priv;
 		}
 		mad_priv->header.mapping = sg_list.addr;
 		mad_priv->header.mad_list.mad_queue = recv_queue;
 		mad_priv->header.mad_list.cqe.done = ib_mad_recv_done;
 		recv_wr.wr_cqe = &mad_priv->header.mad_list.cqe;
-
-		/* Post receive WR */
 		spin_lock_irqsave(&recv_queue->lock, flags);
-		post = (++recv_queue->count < recv_queue->max_active);
-		list_add_tail(&mad_priv->header.mad_list.list, &recv_queue->list);
+		if (recv_queue->count >= recv_queue->max_active) {
+			/* Fully populated the receive queue */
+			spin_unlock_irqrestore(&recv_queue->lock, flags);
+			break;
+		}
+		recv_queue->count++;
+		list_add_tail(&mad_priv->header.mad_list.list,
+			      &recv_queue->list);
 		spin_unlock_irqrestore(&recv_queue->lock, flags);
+
 		ret = ib_post_recv(qp_info->qp, &recv_wr, NULL);
 		if (ret) {
 			spin_lock_irqsave(&recv_queue->lock, flags);
 			list_del(&mad_priv->header.mad_list.list);
 			recv_queue->count--;
 			spin_unlock_irqrestore(&recv_queue->lock, flags);
-			ib_dma_unmap_single(qp_info->port_priv->device,
-					    mad_priv->header.mapping,
-					    mad_priv_dma_size(mad_priv),
-					    DMA_FROM_DEVICE);
-			kfree(mad_priv);
 			dev_err(&qp_info->port_priv->device->dev,
 				"ib_post_recv failed: %d\n", ret);
 			break;
 		}
-	} while (post);
+	}
 
+	ib_dma_unmap_single(qp_info->port_priv->device,
+			    mad_priv->header.mapping,
+			    mad_priv_dma_size(mad_priv), DMA_FROM_DEVICE);
+free_mad_priv:
+	kfree(mad_priv);
 	return ret;
 }
 

2.39.5

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

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

From: Prathamesh Shete <[email protected]>

[ Upstream commit 17013f0acb322e5052ff9b9d0fab0ab5a4bfd828 ]

Tegra devices have an 'sfsel' bit field that determines whether a pin operates in SFIO (Special Function I/O) or GPIO mode. Currently, tegra_pinctrl_gpio_disable_free() sets this bit when releasing a GPIO.

However, tegra_pinctrl_set_mux() can be called independently in certain code paths where gpio_disable_free() is not invoked. In such cases, failing to set the SFIO mode could lead to incorrect pin configurations, resulting in functional issues for peripherals relying on SFIO.

This patch ensures that whenever set_mux() is called, the SFIO mode is correctly set in the Mux Register if the 'sfsel' bit is present. This prevents situations where the pin remains in GPIO mode despite being configured for SFIO use.

---
 drivers/pinctrl/tegra/pinctrl-tegra.c | 3 +++
 1 file changed, 3 insertions(+)

index 195cfe557511b..90de78e4175c9 100644
@@ -270,6 +270,9 @@ static int tegra_pinctrl_set_mux(struct pinctrl_dev *pctldev,
 	val = pmx_readl(pmx, g->mux_bank, g->mux_reg);
 	val &= ~(0x3 << g->mux_bit);
 	val |= i << g->mux_bit;
+	/* Set the SFIO/GPIO selection to SFIO when under pinmux control*/
+	if (pmx->soc->sfsel_in_mux)
+		val |= (1 << g->sfsel_bit);
 	pmx_writel(pmx, val, g->mux_bank, g->mux_reg);
 
 	return 0;

2.39.5

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

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

From: Jerome Brunet <[email protected]>

[ Upstream commit 8995f8f108c3ac5ad52b12a6cfbbc7b3b32e9a58 ]

Several clocks used by both g12a and g12b use the g12a cpu A clock hw pointer as clock parent. This is incorrect on g12b since the parents of cluster A cpu clock are different. Also the hw clock provided as parent to these children is not even registered clock on g12b.

Fix the problem by reverting to the global namespace and let CCF pick the appropriate, as it is already done for other clocks, such as cpu_clk_trace_div.

---
 drivers/clk/meson/g12a.c | 36 ++++++++++++++++++++++++------------
 1 file changed, 24 insertions(+), 12 deletions(-)

index 2876bb83d9d0e..870cac6dd0453 100644
@@ -1135,8 +1135,18 @@ static struct clk_regmap g12a_cpu_clk_div16_en = {
 	.hw.init = &(struct clk_init_data) {
 		.name = "cpu_clk_div16_en",
 		.ops = &clk_regmap_gate_ro_ops,
-		.parent_hws = (const struct clk_hw *[]) {
-			&g12a_cpu_clk.hw
+		.parent_data = &(const struct clk_parent_data) {
+			/*
+			 * Note:
+			 * G12A and G12B have different cpu clocks (with
+			 * different struct clk_hw). We fallback to the global
+			 * naming string mechanism so this clock picks
+			 * up the appropriate one. Same goes for the other
+			 * clock using cpu cluster A clock output and present
+			 * on both G12 variant.
+			 */
+			.name = "cpu_clk",
+			.index = -1,
 		},
 		.num_parents = 1,
 		/*

@@ -1201,7 +1211,10 @@ static struct clk_regmap g12a_cpu_clk_apb_div = {
 	.hw.init = &(struct clk_init_data){
 		.name = "cpu_clk_apb_div",
 		.ops = &clk_regmap_divider_ro_ops,
-		.parent_hws = (const struct clk_hw *[]) { &g12a_cpu_clk.hw },
+		.parent_data = &(const struct clk_parent_data) {
+			.name = "cpu_clk",
+			.index = -1,
+		},
 		.num_parents = 1,
 	},
 };

@@ -1235,7 +1248,10 @@ static struct clk_regmap g12a_cpu_clk_atb_div = {
 	.hw.init = &(struct clk_init_data){
 		.name = "cpu_clk_atb_div",
 		.ops = &clk_regmap_divider_ro_ops,
-		.parent_hws = (const struct clk_hw *[]) { &g12a_cpu_clk.hw },
+		.parent_data = &(const struct clk_parent_data) {
+			.name = "cpu_clk",
+			.index = -1,
+		},
 		.num_parents = 1,
 	},
 };

@@ -1269,7 +1285,10 @@ static struct clk_regmap g12a_cpu_clk_axi_div = {
 	.hw.init = &(struct clk_init_data){
 		.name = "cpu_clk_axi_div",
 		.ops = &clk_regmap_divider_ro_ops,
-		.parent_hws = (const struct clk_hw *[]) { &g12a_cpu_clk.hw },
+		.parent_data = &(const struct clk_parent_data) {
+			.name = "cpu_clk",
+			.index = -1,
+		},
 		.num_parents = 1,
 	},
 };

@@ -1304,13 +1323,6 @@ static struct clk_regmap g12a_cpu_clk_trace_div = {
 		.name = "cpu_clk_trace_div",
 		.ops = &clk_regmap_divider_ro_ops,
 		.parent_data = &(const struct clk_parent_data) {
-			/*
-			 * Note:
-			 * G12A and G12B have different cpu_clks (with
-			 * different struct clk_hw). We fallback to the global
-			 * naming string mechanism so cpu_clk_trace_div picks
-			 * up the appropriate one.
-			 */
 			.name = "cpu_clk",
 			.index = -1,
 		},

2.39.5

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

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

From: Jerome Brunet <[email protected]>

[ Upstream commit 7915d7d5407c026fa9343befb4d3343f7a345f97 ]

The 32k clock reference a parent 'cts_slow_oscin' with a fixme note saying that this clock should be provided by AO controller.

The HW probably has this clock but it does not exist at the moment in any controller implementation. Furthermore, referencing clock by the global name should be avoided whenever possible.

There is no reason to keep this hack around, at least for now.

---
 drivers/clk/meson/gxbb.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

index a6428823371bf..cfdb1ce6d361c 100644
@@ -1269,14 +1269,13 @@ static struct clk_regmap gxbb_cts_i958 = {
 	},
 };
 
+/*
+ * This table skips a clock named 'cts_slow_oscin' in the documentation
+ * This clock does not exist yet in this controller or the AO one
+ */
+static u32 gxbb_32k_clk_parents_val_table[] = { 0, 2, 3 };
 static const struct clk_parent_data gxbb_32k_clk_parent_data[] = {
 	{ .fw_name = "xtal", },
-	/*
-	 * FIXME: This clock is provided by the ao clock controller but the
-	 * clock is not yet part of the binding of this controller, so string
-	 * name must be use to set this parent.
-	 */
-	{ .name = "cts_slow_oscin", .index = -1 },
 	{ .hw = &gxbb_fclk_div3.hw },
 	{ .hw = &gxbb_fclk_div5.hw },
 };

@@ -1286,6 +1285,7 @@ static struct clk_regmap gxbb_32k_clk_sel = {
 		.offset = HHI_32K_CLK_CNTL,
 		.mask = 0x3,
 		.shift = 16,
+		.table = gxbb_32k_clk_parents_val_table,
 		},
 	.hw.init = &(struct clk_init_data){
 		.name = "32k_clk_sel",

2.39.5

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

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

From: Jerome Brunet <[email protected]>

[ Upstream commit 0079e77c08de692cb20b38e408365c830a44b1ef ]

The bit index of the peripheral clock for mmc A is wrong
This was probably not a problem for mmc A as the peripheral is likely left enabled by the bootloader.

No issues has been reported so far but it could be a problem, most likely some form of conflict between the ethernet and mmc A clock, breaking ethernet on init.

Use the value provided by the documentation for mmc A before this becomes an actual problem.

---
 drivers/clk/meson/g12a.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index 870cac6dd0453..3280b7410a13f 100644
@@ -4136,7 +4136,7 @@ static MESON_GATE(g12a_spicc_1,			HHI_GCLK_MPEG0,	14);
 static MESON_GATE(g12a_hiu_reg,			HHI_GCLK_MPEG0,	19);
 static MESON_GATE(g12a_mipi_dsi_phy,		HHI_GCLK_MPEG0,	20);
 static MESON_GATE(g12a_assist_misc,		HHI_GCLK_MPEG0,	23);
-static MESON_GATE(g12a_emmc_a,			HHI_GCLK_MPEG0,	4);
+static MESON_GATE(g12a_emmc_a,			HHI_GCLK_MPEG0,	24);
 static MESON_GATE(g12a_emmc_b,			HHI_GCLK_MPEG0,	25);
 static MESON_GATE(g12a_emmc_c,			HHI_GCLK_MPEG0,	26);
 static MESON_GATE(g12a_audio_codec,		HHI_GCLK_MPEG0,	28);

2.39.5

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

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

From: Jann Horn <[email protected]>

[ Upstream commit 57e2428f8df8263275344566e02c277648a4b7f1 ]

PUSH_REGS with save_ret=1 is used by interrupt entry helper functions that initially start with a UNWIND_HINT_FUNC ORC state.

However, save_ret=1 means that we clobber the helper function's return address (and then later restore the return address further down on the stack); after that point, the only thing on the stack we can unwind through is the IRET frame, so use UNWIND_HINT_IRET_REGS until we have a full pt_regs frame.

( An alternate approach would be to move the pt_regs->di overwrite down
such that it is the final step of pt_regs setup; but I don't want to rearrange entry code just to make unwinding a tiny bit more elegant. )

---
 arch/x86/entry/calling.h | 2 ++
 1 file changed, 2 insertions(+)

index a4b357e5bbfe9..b6715c835f9fd 100644
@@ -104,6 +104,8 @@ For 32-bit we have the following conventions - kernel is built with
 	pushq	%rsi		/* pt_regs->si */
 	movq	8(%rsp), %rsi	/* temporarily store the return address in %rsi */
 	movq	%rdi, 8(%rsp)	/* pt_regs->di (overwriting original return address) */
+	/* We just clobbered the return address - use the IRET frame for unwinding: */
+	UNWIND_HINT_IRET_REGS offset=3*8
 	.else
 	pushq   %rdi		/* pt_regs->di */
 	pushq   %rsi		/* pt_regs->si */

2.39.5

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

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

From: Artur Weber <[email protected]>

[ Upstream commit 30cc7b0d0e9341d419eb7da15fb5c22406dbe499 ]

The charge input threshold voltage register on the MAX77693 PMIC accepts four values: 0x0 for 4.3v, 0x1 for 4.7v, 0x2 for 4.8v and 0x3 for 4.9v. Due to an oversight, the driver calculated the values for 4.7v and above starting from 0x0, rather than from 0x1 ([(4700000 - 4700000) / 100000] gives 0).

Add 1 to the calculation to ensure that 4.7v is converted to a register value of 0x1 and that the other two voltages are converted correctly as well.

---
 drivers/power/supply/max77693_charger.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index a2c5c9858639f..ef3482fa4023e 100644
@@ -556,7 +556,7 @@ static int max77693_set_charge_input_threshold_volt(struct max77693_charger *chg
 	case 4700000:
 	case 4800000:
 	case 4900000:
-		data = (uvolt - 4700000) / 100000;
+		data = ((uvolt - 4700000) / 100000) + 1;
 		break;
 	default:
 		dev_err(chg->dev, "Wrong value for charge input voltage regulation threshold\n");

2.39.5

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

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

From: Patrisious Haddad <[email protected]>

[ Upstream commit 5ed3b0cb3f827072e93b4c5b6e2b8106fd7cccbd ]

When cur_qp isn't NULL, in order to avoid fetching the QP from the radix tree again we check if the next cqe QP is identical to the one we already have.

The bug however is that we are checking if the QP is identical by checking the QP number inside the CQE against the QP number inside the mlx5_ib_qp, but that's wrong since the QP number from the CQE is from FW so it should be matched against mlx5_core_qp which is our FW QP number.

Otherwise we could use the wrong QP when handling a CQE which could cause the kernel trace below.

This issue is mainly noticeable over QPs 0 & 1, since for now they are the only QPs in our driver whereas the QP number inside mlx5_ib_qp doesn't match the QP number inside mlx5_core_qp.

BUG: kernel NULL pointer dereference, address: 0000000000000012
 #PF: supervisor read access in kernel mode
 #PF: error_code(0x0000) - not-present page
 PGD 0 P4D 0
 Oops: Oops: 0000 [#1] SMP
 CPU: 0 UID: 0 PID: 7927 Comm: kworker/u62:1 Not tainted 6.14.0-rc3+ #189
 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.16.3-0-ga6ed6b701f0a-prebuilt.qemu.org 04/01/2014
 Workqueue: ib-comp-unb-wq ib_cq_poll_work [ib_core]
 RIP: 0010:mlx5_ib_poll_cq+0x4c7/0xd90 [mlx5_ib]
 Code: 03 00 00 8d 58 ff 21 cb 66 39 d3 74 39 48 c7 c7 3c 89 6e a0 0f b7 db e8 b7 d2 b3 e0 49 8b 86 60 03 00 00 48 c7 c7 4a 89 6e a0 <0f> b7 5c 98 02 e8 9f d2 b3 e0 41 0f b7 86 78 03 00 00 83 e8 01 21
 RSP: 0018:ffff88810511bd60 EFLAGS: 00010046
 RAX: 0000000000000010 RBX: 0000000000000000 RCX: 0000000000000000
 RDX: 0000000000000000 RSI: ffff88885fa1b3c0 RDI: ffffffffa06e894a
 RBP: 00000000000000b0 R08: 0000000000000000 R09: ffff88810511bc10
 R10: 0000000000000001 R11: 0000000000000001 R12: ffff88810d593000
 R13: ffff88810e579108 R14: ffff888105146000 R15: 00000000000000b0
 FS:  0000000000000000(0000) GS:ffff88885fa00000(0000) knlGS:0000000000000000
 CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
 CR2: 0000000000000012 CR3: 00000001077e6001 CR4: 0000000000370eb0
 Call Trace:
  <TASK>
  ? __die+0x20/0x60
  ? page_fault_oops+0x150/0x3e0
  ? exc_page_fault+0x74/0x130
  ? asm_exc_page_fault+0x22/0x30
  ? mlx5_ib_poll_cq+0x4c7/0xd90 [mlx5_ib]
  __ib_process_cq+0x5a/0x150 [ib_core]
  ib_cq_poll_work+0x31/0x90 [ib_core]
  process_one_work+0x169/0x320
  worker_thread+0x288/0x3a0
  ? work_busy+0xb0/0xb0
  kthread+0xd7/0x1f0
  ? kthreads_online_cpu+0x130/0x130
  ? kthreads_online_cpu+0x130/0x130
  ret_from_fork+0x2d/0x50
  ? kthreads_online_cpu+0x130/0x130
  ret_from_fork_asm+0x11/0x20
  </TASK>

---
 drivers/infiniband/hw/mlx5/cq.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index 74644b6ea0ff1..e6d3ac4e10dc0 100644
@@ -481,7 +481,7 @@ static int mlx5_poll_one(struct mlx5_ib_cq *cq,
 	}
 
 	qpn = ntohl(cqe64->sop_drop_qpn) & 0xffffff;
-	if (!*cur_qp || (qpn != (*cur_qp)->ibqp.qp_num)) {
+	if (!*cur_qp || (qpn != (*cur_qp)->trans_qp.base.mqp.qpn)) {
 		/* We do not have to take the QP table lock here,
 		 * because CQs will be locked while QPs are removed
 		 * from the table.

2.39.5

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

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

From: Nikita Zhandarovich <[email protected]>

[ Upstream commit 2d8cb9ffe18c2f1e5bd07a19cbce85b26c1d0cf0 ]

If offset end up being high enough, right hand expression in functions like sm501_gpio_set() shifted left for that number of bits, may not fit in int type.

Just in case, fix that by using BIT() both as an option safe from overflow issues and to make this step look similar to other gpio drivers.

Found by Linux Verification Center (linuxtesting.org) with static analysis tool SVACE.

---
 drivers/mfd/sm501.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

index 37ad72d8cde2a..8c67fdc2af7f1 100644
@@ -920,7 +920,7 @@ static void sm501_gpio_set(struct gpio_chip *chip, unsigned offset, int value)
 {
 	struct sm501_gpio_chip *smchip = gpiochip_get_data(chip);
 	struct sm501_gpio *smgpio = smchip->ourgpio;
-	unsigned long bit = 1 << offset;
+	unsigned long bit = BIT(offset);
 	void __iomem *regs = smchip->regbase;
 	unsigned long save;
 	unsigned long val;

@@ -946,7 +946,7 @@ static int sm501_gpio_input(struct gpio_chip *chip, unsigned offset)
 	struct sm501_gpio_chip *smchip = gpiochip_get_data(chip);
 	struct sm501_gpio *smgpio = smchip->ourgpio;
 	void __iomem *regs = smchip->regbase;
-	unsigned long bit = 1 << offset;
+	unsigned long bit = BIT(offset);
 	unsigned long save;
 	unsigned long ddr;
 

@@ -971,7 +971,7 @@ static int sm501_gpio_output(struct gpio_chip *chip,
 {
 	struct sm501_gpio_chip *smchip = gpiochip_get_data(chip);
 	struct sm501_gpio *smgpio = smchip->ourgpio;
-	unsigned long bit = 1 << offset;
+	unsigned long bit = BIT(offset);
 	void __iomem *regs = smchip->regbase;
 	unsigned long save;
 	unsigned long val;

2.39.5

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

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

From: Jann Horn <[email protected]>

[ Upstream commit 2c118f50d7fd4d9aefc4533a26f83338b2906b7a ]

Commit:

2e4be0d011f2 ("x86/show_trace_log_lvl: Ensure stack pointer is aligned, again")

was intended to ensure alignment of the stack pointer; but it also moved the initialization of the "stack" variable down into the loop header.

This was likely intended as a no-op cleanup, since the commit message does not mention it; however, this caused a behavioral change because the value of "regs" is different between the two places.

Originally, get_stack_pointer() used the regs provided by the caller; after that commit, get_stack_pointer() instead uses the regs at the top of the stack frame the unwinder is looking at. Often, there are no such regs at all, and "regs" is NULL, causing get_stack_pointer() to fall back to the task's current stack pointer, which is not what we want here, but probably happens to mostly work. Other times, the original regs will point to another regs frame - in that case, the linear guess unwind logic in show_trace_log_lvl() will start unwinding too far up the stack, causing the first frame found by the proper unwinder to never be visited, resulting in a stack trace consisting purely of guess lines.

Fix it by moving the "stack = " assignment back where it belongs.

---
 arch/x86/kernel/dumpstack.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

index b9736aac20eef..cf92191de2b2a 100644
@@ -195,6 +195,7 @@ void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
 	printk("%sCall Trace:\n", log_lvl);
 
 	unwind_start(&state, task, regs, stack);
+	stack = stack ?: get_stack_pointer(task, regs);
 	regs = unwind_get_entry_regs(&state, &partial);
 
 	/*

@@ -213,9 +214,7 @@ void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
 	 * - hardirq stack
 	 * - entry stack
 	 */
-	for (stack = stack ?: get_stack_pointer(task, regs);
-	     stack;
-	     stack = stack_info.next_sp) {
+	for (; stack; stack = stack_info.next_sp) {
 		const char *stack_name;
 
 		stack = PTR_ALIGN(stack, sizeof(long));

2.39.5

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

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

From: Wenkai Lin <[email protected]>

[ Upstream commit 1b284ffc30b02808a0de698667cbcf5ce5f9144e ]

According to the HMAC RFC, the authentication key can be 0 bytes, and the hardware can handle this scenario. Therefore, remove the incorrect validation for this case.

---
 drivers/crypto/hisilicon/sec2/sec_crypto.c | 8 ++------
 1 file changed, 2 insertions(+), 6 deletions(-)

index 2dbec638cca83..ce2ff9538c8dc 100644
@@ -856,11 +856,6 @@ static int sec_aead_auth_set_key(struct sec_auth_ctx *ctx,
 	struct crypto_shash *hash_tfm = ctx->hash_tfm;
 	int blocksize, ret;
 
-	if (!keys->authkeylen) {
-		pr_err("hisi_sec2: aead auth key error!\n");
-		return -EINVAL;
-	}
-
 	blocksize = crypto_shash_blocksize(hash_tfm);
 	if (keys->authkeylen > blocksize) {
 		ret = crypto_shash_tfm_digest(hash_tfm, keys->authkey,

@@ -871,7 +866,8 @@ static int sec_aead_auth_set_key(struct sec_auth_ctx *ctx,
 		}
 		ctx->a_key_len = blocksize;
 	} else {
-		memcpy(ctx->a_key, keys->authkey, keys->authkeylen);
+		if (keys->authkeylen)
+			memcpy(ctx->a_key, keys->authkey, keys->authkeylen);
 		ctx->a_key_len = keys->authkeylen;
 	}
 

2.39.5

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

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

From: Qasim Ijaz <[email protected]>

[ Upstream commit 81a82e8f33880793029cd6f8a766fb13b737e6a7 ]

In do_isofs_readdir() when assigning the variable
"struct iso_directory_record *de" the b_data field of the buffer_head is accessed and an offset is added to it, the size of b_data is 2048 and the offset size is 2047, meaning
"de = (struct iso_directory_record *) (bh->b_data + offset);" yields the final byte of the 2048 sized b_data block.

The first byte of the directory record (de_len) is then read and found to be 31, meaning the directory record size is 31 bytes long. The directory record is defined by the structure:

struct iso_directory_record {
__u8 length; // 1 byte
__u8 ext_attr_length; // 1 byte
__u8 extent[8]; // 8 bytes
__u8 size[8]; // 8 bytes
__u8 date[7]; // 7 bytes
__u8 flags; // 1 byte
__u8 file_unit_size; // 1 byte
__u8 interleave; // 1 byte
__u8 volume_sequence_number[4]; // 4 bytes
__u8 name_len; // 1 byte
char name[]; // variable size
} __attribute__((packed));

The fixed portion of this structure occupies 33 bytes. Therefore, a valid directory record must be at least 33 bytes long (even without considering the variable-length name field). Since de_len is only 31, it is insufficient to contain the complete fixed header.

The code later hits the following sanity check that compares de_len against the sum of de->name_len and sizeof(struct iso_directory_record):

	if (de_len < de->name_len[0] + sizeof(struct iso_directory_record)) {
		...
	}

Since the fixed portion of the structure is
33 bytes (up to and including name_len member),
a valid record should have de_len of at least 33 bytes; here, however, de_len is too short, and the field de->name_len (located at offset 32) is accessed even though it lies beyond the available 31 bytes.

This access on the corrupted isofs data triggers a KASAN uninitialized memory warning. The fix would be to first verify that de_len is at least sizeof(struct iso_directory_record) before accessing any fields like de->name_len.

---
 fs/isofs/dir.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

index b9e6a7ec78be4..23c73bb56d821 100644
@@ -147,7 +147,8 @@ static int do_isofs_readdir(struct inode *inode, struct file *file,
 			de = tmpde;
 		}
 		/* Basic sanity check, whether name doesn't exceed dir entry */
-		if (de_len < de->name_len[0] +
+		if (de_len < sizeof(struct iso_directory_record) ||
+		    de_len < de->name_len[0] +
 					sizeof(struct iso_directory_record)) {
 			printk(KERN_NOTICE "iso9660: Corrupted directory entry"
 			       " in block %lu of inode %lu\n", block,

2.39.5

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

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

From: Ilkka Koskinen <[email protected]>

[ Upstream commit 0e14e062f5ff98aa15264dfa87c5f5e924028561 ]

Trying to record a trace on kernel with 64k pages resulted in -ENOMEM. This happens due to a bug in calculating the number of table pages, which returns zero. Fix the issue by rounding up.

$ perf record --kcore -e cs_etm/@tmc_etr55,cycacc,branch_broadcast/k --per-thread taskset --cpu-list 1 dd if=/dev/zero of=/dev/null
failed to mmap with 12 (Cannot allocate memory)

---
 drivers/hwtracing/coresight/coresight-catu.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index 8e19e8cdcce5e..3357e55fc5590 100644
@@ -267,7 +267,7 @@ catu_init_sg_table(struct device *catu_dev, int node,
 	 * Each table can address upto 1MB and we can have
 	 * CATU_PAGES_PER_SYSPAGE tables in a system page.
 	 */
-	nr_tpages = DIV_ROUND_UP(size, SZ_1M) / CATU_PAGES_PER_SYSPAGE;
+	nr_tpages = DIV_ROUND_UP(size, CATU_PAGES_PER_SYSPAGE * SZ_1M);
 	catu_table = tmc_alloc_sg_table(catu_dev, node, nr_tpages,
 					size >> PAGE_SHIFT, pages);
 	if (IS_ERR(catu_table))

2.39.5

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

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

From: Jonathan Cameron <[email protected]>

[ Upstream commit df330c808182a8beab5d0f84a6cbc9cff76c61fc ]

If a match was not found, then the write_raw() callback would return the odr index, not an error. Return -EINVAL if this occurs. To avoid similar issues in future, introduce j, a new indexing variable rather than using ret for this purpose.

---
 drivers/iio/accel/mma8452.c | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

index b12e804647063..760ee0685034b 100644
@@ -711,7 +711,7 @@ static int mma8452_write_raw(struct iio_dev *indio_dev,
 			     int val, int val2, long mask)
 {
 	struct mma8452_data *data = iio_priv(indio_dev);
-	int i, ret;
+	int i, j, ret;
 
 	ret = iio_device_claim_direct_mode(indio_dev);
 	if (ret)

@@ -771,14 +771,18 @@ static int mma8452_write_raw(struct iio_dev *indio_dev,
 		break;
 
 	case IIO_CHAN_INFO_OVERSAMPLING_RATIO:
-		ret = mma8452_get_odr_index(data);
+		j = mma8452_get_odr_index(data);
 
 		for (i = 0; i < ARRAY_SIZE(mma8452_os_ratio); i++) {
-			if (mma8452_os_ratio[i][ret] == val) {
+			if (mma8452_os_ratio[i][j] == val) {
 				ret = mma8452_set_power_mode(data, i);
 				break;
 			}
 		}
+		if (i == ARRAY_SIZE(mma8452_os_ratio)) {
+			ret = -EINVAL;
+			break;
+		}
 		break;
 	default:
 		ret = -EINVAL;

2.39.5

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

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

From: Arnaldo Carvalho de Melo <[email protected]>

[ Upstream commit cf67629f7f637fb988228abdb3aae46d0c1748fe ]

No need to specify the array size, let the compiler figure that out.

This addresses this compiler warning that was noticed while build testing on fedora rawhide:

31 15.81 fedora:rawhide : FAIL gcc version 15.0.1 20250225 (Red Hat 15.0.1-0) (GCC)
util/units.c: In function 'unit_number__scnprintf':
util/units.c:67:24: error: initializer-string for array of 'char' is too long [-Werror=unterminated-string-initialization]
67 | char unit[4] = "BKMG";
| ^~~~~~
cc1: all warnings being treated as errors

---
 tools/perf/util/units.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index a46762aec4c9f..24c83b8b8c980 100644
@@ -57,7 +57,7 @@ unsigned long convert_unit(unsigned long value, char *unit)
 
 int unit_number__scnprintf(char *buf, size_t size, u64 n)
 {
-	char unit[4] = "BKMG";
+	char unit[] = "BKMG";
 	int i = 0;
 
 	while (((n / 1024) > 1) && (i < 3)) {

2.39.5

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

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

From: Sourabh Jain <[email protected]>

[ Upstream commit 9986fb5164c8b21f6439cfd45ba36d8cc80c9710 ]

Patch series "powerpc/crash: use generic crashkernel reservation", v3.

Commit 0ab97169aa05 ("crash_core: add generic function to do reservation") added a generic function to reserve crashkernel memory. So let's use the same function on powerpc and remove the architecture-specific code that essentially does the same thing.

The generic crashkernel reservation also provides a way to split the crashkernel reservation into high and low memory reservations, which can be enabled for powerpc in the future.

Additionally move powerpc to use generic APIs to locate memory hole for kexec segments while loading kdump kernel.

This patch (of 7):

kexec_elf_load() loads an ELF executable and sets the address of the lowest PT_LOAD section to the address held by the lowest_load_addr function argument.

To determine the lowest PT_LOAD address, a local variable lowest_addr (type unsigned long) is initialized to UINT_MAX. After loading each PT_LOAD, its address is compared to lowest_addr. If a loaded PT_LOAD address is lower, lowest_addr is updated. However, setting lowest_addr to UINT_MAX won't work when the kernel image is loaded above 4G, as the returned lowest PT_LOAD address would be invalid. This is resolved by initializing lowest_addr to ULONG_MAX instead.

This issue was discovered while implementing crashkernel high/low reservation on the PowerPC architecture.

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

index d3689632e8b90..3a5c25b2adc94 100644
@@ -390,7 +390,7 @@ int kexec_elf_load(struct kimage *image, struct elfhdr *ehdr,
 			 struct kexec_buf *kbuf,
 			 unsigned long *lowest_load_addr)
 {
-	unsigned long lowest_addr = UINT_MAX;
+	unsigned long lowest_addr = ULONG_MAX;
 	int ret;
 	size_t i;
 

2.39.5

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

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

From: Vasiliy Kovalev <[email protected]>

[ Upstream commit a406aff8c05115119127c962cbbbbd202e1973ef ]

The l_tree_depth field is 16-bit (__le16), but the actual maximum depth is limited to OCFS2_MAX_PATH_DEPTH.

Add a check to prevent out-of-bounds access if l_tree_depth has an invalid value, which may occur when reading from a corrupted mounted disk [1].

---
 fs/ocfs2/alloc.c | 8 ++++++++
 1 file changed, 8 insertions(+)

index a9a6276ff29bd..94c7acfebe183 100644
@@ -1798,6 +1798,14 @@ static int __ocfs2_find_path(struct ocfs2_caching_info *ci,
 
 	el = root_el;
 	while (el->l_tree_depth) {
+		if (unlikely(le16_to_cpu(el->l_tree_depth) >= OCFS2_MAX_PATH_DEPTH)) {
+			ocfs2_error(ocfs2_metadata_cache_get_super(ci),
+				    "Owner %llu has invalid tree depth %u in extent list\n",
+				    (unsigned long long)ocfs2_metadata_cache_owner(ci),
+				    le16_to_cpu(el->l_tree_depth));
+			ret = -EROFS;
+			goto out;
+		}
 		if (le16_to_cpu(el->l_next_free_rec) == 0) {
 			ocfs2_error(ocfs2_metadata_cache_get_super(ci),
 				    "Owner %llu has empty extent list at depth %u\n",

2.39.5

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

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

From: Trond Myklebust <[email protected]>

[ Upstream commit 47acca884f714f41d95dc654f802845544554784 ]

The amount of looping through the list of delegations is occasionally leading to soft lockups. Avoid at least some loops by not requiring the NFSv4 state manager to scan for delegations that are marked for return-on-close. Instead, either mark them for immediate return (if possible) or else leave it up to nfs4_inode_return_delegation_on_close() to return them once the file is closed by the application.

---
 fs/nfs/delegation.c | 33 ++++++++++++++++++---------------
 1 file changed, 18 insertions(+), 15 deletions(-)

index 02d9af026ad15..dbed8d44d8053 100644
@@ -552,17 +552,6 @@ static bool nfs_delegation_need_return(struct nfs_delegation *delegation)
 
 	if (test_and_clear_bit(NFS_DELEGATION_RETURN, &delegation->flags))
 		ret = true;
-	else if (test_bit(NFS_DELEGATION_RETURN_IF_CLOSED, &delegation->flags)) {
-		struct inode *inode;
-
-		spin_lock(&delegation->lock);
-		inode = delegation->inode;
-		if (inode && list_empty(&NFS_I(inode)->open_files))
-			ret = true;
-		spin_unlock(&delegation->lock);
-	}
-	if (ret)
-		clear_bit(NFS_DELEGATION_RETURN_IF_CLOSED, &delegation->flags);
 	if (test_bit(NFS_DELEGATION_RETURNING, &delegation->flags) ||
 	    test_bit(NFS_DELEGATION_RETURN_DELAYED, &delegation->flags) ||
 	    test_bit(NFS_DELEGATION_REVOKED, &delegation->flags))

@@ -800,11 +789,25 @@ int nfs4_inode_make_writeable(struct inode *inode)
 	return nfs4_inode_return_delegation(inode);
 }
 
-static void nfs_mark_return_if_closed_delegation(struct nfs_server *server,
-		struct nfs_delegation *delegation)
+static void
+nfs_mark_return_if_closed_delegation(struct nfs_server *server,
+				     struct nfs_delegation *delegation)
 {
-	set_bit(NFS_DELEGATION_RETURN_IF_CLOSED, &delegation->flags);
-	set_bit(NFS4CLNT_DELEGRETURN, &server->nfs_client->cl_state);
+	struct inode *inode;
+
+	if (test_bit(NFS_DELEGATION_RETURN, &delegation->flags) ||
+	    test_bit(NFS_DELEGATION_RETURN_IF_CLOSED, &delegation->flags))
+		return;
+	spin_lock(&delegation->lock);
+	inode = delegation->inode;
+	if (!inode)
+		goto out;
+	if (list_empty(&NFS_I(inode)->open_files))
+		nfs_mark_return_delegation(server, delegation);
+	else
+		set_bit(NFS_DELEGATION_RETURN_IF_CLOSED, &delegation->flags);
+out:
+	spin_unlock(&delegation->lock);
 }
 
 static bool nfs_server_mark_return_all_delegations(struct nfs_server *server)

2.39.5

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

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

From: Arnaldo Carvalho de Melo <[email protected]>

[ Upstream commit 1376c195e8ad327bb9f2d32e0acc5ac39e7cb30a ]

Some old cut'n'paste error, its "ip", so the description should be "event ip", not "event type".

---
 tools/perf/util/python.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index ae8edde7c50ef..51679d8d40b1b 100644
@@ -131,7 +131,7 @@ struct pyrf_event {
 };
 
 #define sample_members \
-	sample_member_def(sample_ip, ip, T_ULONGLONG, "event type"),			 \
+	sample_member_def(sample_ip, ip, T_ULONGLONG, "event ip"),			 \
 	sample_member_def(sample_pid, pid, T_INT, "event pid"),			 \
 	sample_member_def(sample_tid, tid, T_INT, "event tid"),			 \
 	sample_member_def(sample_time, time, T_ULONGLONG, "event timestamp"),		 \

2.39.5

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

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

From: Arnaldo Carvalho de Melo <[email protected]>

[ Upstream commit 3de5a2bf5b4847f7a59a184568f969f8fe05d57f ]

To avoid a leak if we have the python object but then something happens and we need to return the operation, decrement the offset of the newly created object.

---
 tools/perf/util/python.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

index 51679d8d40b1b..ab3a444b4b868 100644
@@ -1057,6 +1057,7 @@ static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist,
 
 		evsel = perf_evlist__event2evsel(evlist, event);
 		if (!evsel) {
+			Py_DECREF(pyevent);
 			Py_INCREF(Py_None);
 			return Py_None;
 		}

@@ -1068,9 +1069,12 @@ static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist,
 		/* Consume the even only after we parsed it out. */
 		perf_mmap__consume(&md->core);
 
-		if (err)
+		if (err) {
+			Py_DECREF(pyevent);
 			return PyErr_Format(PyExc_OSError,
 					    "perf: can't parse sample, err=%d", err);
+		}
+
 		return pyevent;
 	}
 end:

2.39.5

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

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

From: Arnaldo Carvalho de Melo <[email protected]>

[ Upstream commit f3fed3ae34d606819d87a63d970cc3092a5be7ab ]

When processing tracepoints the perf python binding was parsing the event before calling perf_mmap__consume(&md->core) in pyrf_evlist__read_on_cpu().

But part of this event parsing was to set the perf_sample->raw_data pointer to the payload of the event, which then could be overwritten by other event before tracepoint fields were asked for via event.prev_comm in a python program, for instance.

This also happened with other fields, but strings were were problems were surfacing, as there is UTF-8 validation for the potentially garbled data.

This ended up showing up as (with some added debugging messages):

( field 'prev_comm' ret=0x7f7c31f65110, raw_size=68 ) ( field 'prev_pid' ret=0x7f7c23b1bed0, raw_size=68 ) ( field 'prev_prio' ret=0x7f7c239c0030, raw_size=68 ) ( field 'prev_state' ret=0x7f7c239c0250, raw_size=68 ) time 14771421785867 prev_comm= prev_pid=1919907691 prev_prio=796026219 prev_state=0x303a32313175 ==> ( XXX '��' len=16, raw_size=68) ( field 'next_comm' ret=(nil), raw_size=68 ) Traceback (most recent call last):
File "/home/acme/git/perf-tools-next/tools/perf/python/tracepoint.py", line 51, in <module>

     main()
   File "/home/acme/git/perf-tools-next/tools/perf/python/tracepoint.py", line 46, in main
     event.next_comm,
     ^^^^^^^^^^^^^^^

AttributeError: 'perf.sample_event' object has no attribute 'next_comm'

When event.next_comm was asked for, the PyUnicode_FromString() python API would fail and that tracepoint field wouldn't be available, stopping the tools/perf/python/tracepoint.py test tool.

But, since we already do a copy of the whole event in pyrf_event__new, just use it and while at it remove what was done in in e8968e654191390a ("perf python: Fix pyrf_evlist__read_on_cpu event consuming") because we don't really need to wait for parsing the sample before declaring the event as consumed.

This copy is questionable as is now, as it limits the maximum event + sample_type and tracepoint payload to sizeof(union perf_event), this all has been "working" because 'struct perf_event_mmap2', the largest entry in 'union perf_event' is:

  $ pahole -C perf_event ~/bin/perf | grep mmap2
	struct perf_record_mmap2   mmap2;              /*     0  4168 */
  $

---
 tools/perf/util/python.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

index ab3a444b4b868..b65cca0656396 100644
@@ -1064,11 +1064,9 @@ static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist,
 
 		pevent->evsel = evsel;
 
-		err = evsel__parse_sample(evsel, event, &pevent->sample);
-
-		/* Consume the even only after we parsed it out. */
 		perf_mmap__consume(&md->core);
 
+		err = evsel__parse_sample(evsel, &pevent->event, &pevent->sample);
 		if (err) {
 			Py_DECREF(pyevent);
 			return PyErr_Format(PyExc_OSError,

2.39.5

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

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

From: Arnaldo Carvalho de Melo <[email protected]>

[ Upstream commit 89aaeaf84231157288035b366cb6300c1c6cac64 ]

The pyrf_event__new() method copies the event obtained from the perf ring buffer to a structure that will then be turned into a python object for further consumption, so it copies perf_event.header.size bytes to its 'event' member:

  $ pahole -C pyrf_event /tmp/build/perf-tools-next/python/perf.cpython-312-x86_64-linux-gnu.so
  struct pyrf_event {
  	PyObject                   ob_base;              /*     0    16 */
  	struct evsel *             evsel;                /*    16     8 */
  	struct perf_sample         sample;               /*    24   312 */

/* XXX last struct has 7 bytes of padding, 2 holes */

/* --- cacheline 5 boundary (320 bytes) was 16 bytes ago --- */
union perf_event event; /* 336 4168 */

  	/* size: 4504, cachelines: 71, members: 4 */
  	/* member types with holes: 1, total: 2 */
  	/* paddings: 1, sum paddings: 7 */
  	/* last cacheline: 24 bytes */
  };

$

It was doing so without checking if the event just obtained has more than that space, fix it.

This isn't a proper, final solution, as we need to support larger events, but for the time being we at least bounds check and document it.

---
 tools/perf/util/python.c | 5 +++++
 1 file changed, 5 insertions(+)

index b65cca0656396..240f9a0a7297b 100644
@@ -558,6 +558,11 @@ static PyObject *pyrf_event__new(union perf_event *event)
 	      event->header.type == PERF_RECORD_SWITCH_CPU_WIDE))
 		return NULL;
 
+	// FIXME this better be dynamic or we need to parse everything
+	// before calling perf_mmap__consume(), including tracepoint fields.
+	if (sizeof(pevent->event) < event->header.size)
+		return NULL;
+
 	ptype = pyrf_event__type[event->header.type];
 	pevent = PyObject_New(struct pyrf_event, ptype);
 	if (pevent != NULL)

2.39.5

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

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

From: Bart Van Assche <[email protected]>

[ Upstream commit 6287fbad1cd91f0c25cdc3a580499060828a8f30 ]

proc_pid_wchan() used to report kernel addresses to user space but that is no longer the case today. Bring the comment above proc_pid_wchan() in sync with the implementation.

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

index b955ba5db72cb..b09cc9e6d5914 100644
@@ -415,7 +415,7 @@ static const struct file_operations proc_pid_cmdline_ops = {
 #ifdef CONFIG_KALLSYMS
 /*
  * Provides a wchan file via kallsyms in a proper one-value-per-file format.
- * Returns the resolved symbol.  If that fails, simply return the address.
+ * Returns the resolved symbol to user space.
  */
 static int proc_pid_wchan(struct seq_file *m, struct pid_namespace *ns,
 			  struct pid *pid, struct task_struct *task)

2.39.5

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

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

From: Josh Poimboeuf <[email protected]>

[ Upstream commit e63d465f59011dede0a0f1d21718b59a64c3ff5c ]

If dib8000_set_dds()'s call to dib8000_read32() returns zero, the result is a divide-by-zero. Prevent that from happening.

Fixes the following warning with an UBSAN kernel:

drivers/media/dvb-frontends/dib8000.o: warning: objtool: dib8000_tune() falls through to next function dib8096p_cfg_DibRx()

---
 drivers/media/dvb-frontends/dib8000.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

index 02cb48223dc67..a28cbbd9e475c 100644
@@ -2701,8 +2701,11 @@ static void dib8000_set_dds(struct dib8000_state *state, s32 offset_khz)
 	u8 ratio;
 
 	if (state->revision == 0x8090) {
+		u32 internal = dib8000_read32(state, 23) / 1000;
+
 		ratio = 4;
-		unit_khz_dds_val = (1<<26) / (dib8000_read32(state, 23) / 1000);
+
+		unit_khz_dds_val = (1<<26) / (internal ?: 1);
 		if (offset_khz < 0)
 			dds = (1 << 26) - (abs_offset_khz * unit_khz_dds_val);
 		else

2.39.5

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

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

From: Yuezhang Mo <[email protected]>

[ Upstream commit b0522303f67255926b946aa66885a0104d1b2980 ]

In exfat_find_last_cluster(), the cluster chain is traversed until the EOF cluster. If the cluster chain includes a loop due to file system corruption, the EOF cluster cannot be traversed, resulting in an infinite loop.

If the number of clusters indicated by the file size is inconsistent with the cluster chain length, exfat_find_last_cluster() will return an error, so if this inconsistency is found, the traversal can be aborted without traversing to the EOF cluster.

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

index a1481e47a7616..b6cce8225d058 100644
@@ -208,7 +208,7 @@ int exfat_find_last_cluster(struct super_block *sb, struct exfat_chain *p_chain,
 		clu = next;
 		if (exfat_ent_get(sb, clu, &next))
 			return -EIO;
-	} while (next != EXFAT_EOF_CLUSTER);
+	} while (next != EXFAT_EOF_CLUSTER && count <= p_chain->size);
 
 	if (p_chain->size != count) {
 		exfat_fs_error(sb,

2.39.5

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

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

From: Mark Zhang <[email protected]>

[ Upstream commit 23f00807619d15063d676218f36c5dfeda1eb420 ]

Commit 30aad41721e0 ("net/core: Add support for getting VF GUIDs") added support for getting VF port and node GUIDs in netlink ifinfo messages, but their size was not taken into consideration in the function that allocates the netlink message, causing the following warning when a netlink message is filled with many VF port and node GUIDs:

 # echo 64 > /sys/bus/pci/devices/0000\:08\:00.0/sriov_numvfs
 # ip link show dev ib0
 RTNETLINK answers: Message too long
 Cannot send link get request: Message too long

Kernel warning:

 ------------[ cut here ]------------
 WARNING: CPU: 2 PID: 1930 at net/core/rtnetlink.c:4151 rtnl_getlink+0x586/0x5a0
 Modules linked in: xt_conntrack xt_MASQUERADE nfnetlink xt_addrtype iptable_nat nf_nat br_netfilter overlay mlx5_ib macsec mlx5_core tls rpcrdma rdma_ucm ib_uverbs ib_iser libiscsi scsi_transport_iscsi ib_umad rdma_cm iw_cm ib_ipoib fuse ib_cm ib_core
 CPU: 2 UID: 0 PID: 1930 Comm: ip Not tainted 6.14.0-rc2+ #1
 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014
 RIP: 0010:rtnl_getlink+0x586/0x5a0
 Code: cb 82 e8 3d af 0a 00 4d 85 ff 0f 84 08 ff ff ff 4c 89 ff 41 be ea ff ff ff e8 66 63 5b ff 49 c7 07 80 4f cb 82 e9 36 fc ff ff <0f> 0b e9 16 fe ff ff e8 de a0 56 00 66 66 2e 0f 1f 84 00 00 00 00
 RSP: 0018:ffff888113557348 EFLAGS: 00010246
 RAX: 00000000ffffffa6 RBX: ffff88817e87aa34 RCX: dffffc0000000000
 RDX: 0000000000000003 RSI: 0000000000000000 RDI: ffff88817e87afb8
 RBP: 0000000000000009 R08: ffffffff821f44aa R09: 0000000000000000
 R10: ffff8881260f79a8 R11: ffff88817e87af00 R12: ffff88817e87aa00
 R13: ffffffff8563d300 R14: 00000000ffffffa6 R15: 00000000ffffffff
 FS:  00007f63a5dbf280(0000) GS:ffff88881ee00000(0000) knlGS:0000000000000000
 CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
 CR2: 00007f63a5ba4493 CR3: 00000001700fe002 CR4: 0000000000772eb0
 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
 PKRU: 55555554
 Call Trace:
  <TASK>
  ? __warn+0xa5/0x230
  ? rtnl_getlink+0x586/0x5a0
  ? report_bug+0x22d/0x240
  ? handle_bug+0x53/0xa0
  ? exc_invalid_op+0x14/0x50
  ? asm_exc_invalid_op+0x16/0x20
  ? skb_trim+0x6a/0x80
  ? rtnl_getlink+0x586/0x5a0
  ? __pfx_rtnl_getlink+0x10/0x10
  ? rtnetlink_rcv_msg+0x1e5/0x860
  ? __pfx___mutex_lock+0x10/0x10
  ? rcu_is_watching+0x34/0x60
  ? __pfx_lock_acquire+0x10/0x10
  ? stack_trace_save+0x90/0xd0
  ? filter_irq_stacks+0x1d/0x70
  ? kasan_save_stack+0x30/0x40
  ? kasan_save_stack+0x20/0x40
  ? kasan_save_track+0x10/0x30
  rtnetlink_rcv_msg+0x21c/0x860
  ? entry_SYSCALL_64_after_hwframe+0x76/0x7e
  ? __pfx_rtnetlink_rcv_msg+0x10/0x10
  ? arch_stack_walk+0x9e/0xf0
  ? rcu_is_watching+0x34/0x60
  ? lock_acquire+0xd5/0x410
  ? rcu_is_watching+0x34/0x60
  netlink_rcv_skb+0xe0/0x210
  ? __pfx_rtnetlink_rcv_msg+0x10/0x10
  ? __pfx_netlink_rcv_skb+0x10/0x10
  ? rcu_is_watching+0x34/0x60
  ? __pfx___netlink_lookup+0x10/0x10
  ? lock_release+0x62/0x200
  ? netlink_deliver_tap+0xfd/0x290
  ? rcu_is_watching+0x34/0x60
  ? lock_release+0x62/0x200
  ? netlink_deliver_tap+0x95/0x290
  netlink_unicast+0x31f/0x480
  ? __pfx_netlink_unicast+0x10/0x10
  ? rcu_is_watching+0x34/0x60
  ? lock_acquire+0xd5/0x410
  netlink_sendmsg+0x369/0x660
  ? lock_release+0x62/0x200
  ? __pfx_netlink_sendmsg+0x10/0x10
  ? import_ubuf+0xb9/0xf0
  ? __import_iovec+0x254/0x2b0
  ? lock_release+0x62/0x200
  ? __pfx_netlink_sendmsg+0x10/0x10
  ____sys_sendmsg+0x559/0x5a0
  ? __pfx_____sys_sendmsg+0x10/0x10
  ? __pfx_copy_msghdr_from_user+0x10/0x10
  ? rcu_is_watching+0x34/0x60
  ? do_read_fault+0x213/0x4a0
  ? rcu_is_watching+0x34/0x60
  ___sys_sendmsg+0xe4/0x150
  ? __pfx____sys_sendmsg+0x10/0x10
  ? do_fault+0x2cc/0x6f0
  ? handle_pte_fault+0x2e3/0x3d0
  ? __pfx_handle_pte_fault+0x10/0x10
  ? preempt_count_sub+0x14/0xc0
  ? __down_read_trylock+0x150/0x270
  ? __handle_mm_fault+0x404/0x8e0
  ? __pfx___handle_mm_fault+0x10/0x10
  ? lock_release+0x62/0x200
  ? __rcu_read_unlock+0x65/0x90
  ? rcu_is_watching+0x34/0x60
  __sys_sendmsg+0xd5/0x150
  ? __pfx___sys_sendmsg+0x10/0x10
  ? __up_read+0x192/0x480
  ? lock_release+0x62/0x200
  ? __rcu_read_unlock+0x65/0x90
  ? rcu_is_watching+0x34/0x60
  do_syscall_64+0x6d/0x140
  entry_SYSCALL_64_after_hwframe+0x76/0x7e
 RIP: 0033:0x7f63a5b13367
 Code: 0e 00 f7 d8 64 89 02 48 c7 c0 ff ff ff ff eb b9 0f 1f 00 f3 0f 1e fa 64 8b 04 25 18 00 00 00 85 c0 75 10 b8 2e 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 51 c3 48 83 ec 28 89 54 24 1c 48 89 74 24 10
 RSP: 002b:00007fff8c726bc8 EFLAGS: 00000246 ORIG_RAX: 000000000000002e
 RAX: ffffffffffffffda RBX: 0000000067b687c2 RCX: 00007f63a5b13367
 RDX: 0000000000000000 RSI: 00007fff8c726c30 RDI: 0000000000000004
 RBP: 00007fff8c726cb8 R08: 0000000000000000 R09: 0000000000000034
 R10: 00007fff8c726c7c R11: 0000000000000246 R12: 0000000000000001
 R13: 0000000000000000 R14: 00007fff8c726cd0 R15: 00007fff8c726cd0
  </TASK>
 irq event stamp: 0
 hardirqs last  enabled at (0): [<0000000000000000>] 0x0
 hardirqs last disabled at (0): [<ffffffff813f9e58>] copy_process+0xd08/0x2830
 softirqs last  enabled at (0): [<ffffffff813f9e58>] copy_process+0xd08/0x2830
 softirqs last disabled at (0): [<0000000000000000>] 0x0
 ---[ end trace 0000000000000000 ]---

Thus, when calculating ifinfo message size, take VF GUIDs sizes into account when supported.

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

index 2806b9ed63879..bc86034e17eab 100644
@@ -950,6 +950,9 @@ static inline int rtnl_vfinfo_size(const struct net_device *dev,
 				 /* IFLA_VF_STATS_TX_DROPPED */
 				 nla_total_size_64bit(sizeof(__u64)));
 		}
+		if (dev->netdev_ops->ndo_get_vf_guid)
+			size += num_vfs * 2 *
+				nla_total_size(sizeof(struct ifla_vf_guid));
 		return size;
 	} else
 		return 0;

2.39.5

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

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

From: Feng Yang <[email protected]>

[ Upstream commit c73f0b69648501978e8b3e8fa7eef7f4197d0481 ]

The calculation of bytes-dropped and bytes_dropped_nested is reversed. Although it does not affect the final calculation of total_dropped, it should still be modified.

---
 kernel/trace/ring_buffer.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

index 9a2c8727b033d..225dbe4a56413 100644
@@ -5768,9 +5768,9 @@ static __init int rb_write_something(struct rb_test_data *data, bool nested)
 		/* Ignore dropped events before test starts. */
 		if (started) {
 			if (nested)
-				data->bytes_dropped += len;
-			else
 				data->bytes_dropped_nested += len;
+			else
+				data->bytes_dropped += len;
 		}
 		return len;
 	}

2.39.5

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

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

From: Giovanni Gherdovich <[email protected]>

[ Upstream commit 9e9b893404d43894d69a18dd2fc8fcf1c36abb7e ]

Prior to commit 496121c02127 ("ACPI: processor: idle: Allow probing on platforms with one ACPI C-state"), the acpi_idle driver wouldn't load on systems without a valid C-State at least as deep as C2.

The behavior was desirable for guests on hypervisors such as VMWare ESXi, which by default don't have the _CST ACPI method, and set the C2 and C3 latencies to 101 and 1001 microseconds respectively via the FADT, to signify they're unsupported.

Since the above change though, these virtualized deployments end up loading acpi_idle, and thus entering the default C1 C-State set by acpi_processor_get_power_info_default(); this is undesirable for a system that's communicating to the OS it doesn't want C-States (missing _CST, and invalid C2/C3 in FADT).

Make acpi_processor_get_power_info_fadt() return -ENODEV in that case, so that acpi_processor_get_cstate_info() exits early and doesn't set pr->flags.power = 1.

---
 drivers/acpi/processor_idle.c | 4 ++++
 1 file changed, 4 insertions(+)

index ae07927910ca0..42c7bdb352d20 100644
@@ -270,6 +270,10 @@ static int acpi_processor_get_power_info_fadt(struct acpi_processor *pr)
 			 ACPI_CX_DESC_LEN, "ACPI P_LVL3 IOPORT 0x%x",
 			 pr->power.states[ACPI_STATE_C3].address);
 
+	if (!pr->power.states[ACPI_STATE_C2].address &&
+	    !pr->power.states[ACPI_STATE_C3].address)
+		return -ENODEV;
+
 	return 0;
 }
 

2.39.5

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

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

From: Geetha sowjanya <[email protected]>

[ Upstream commit 0fdba88a211508984eb5df62008c29688692b134 ]

When number of RVU VFs > 64, the vfs value passed to "rvu_queue_work" function is incorrect. Due to which mbox workqueue entries for VFs 0 to 63 never gets added to workqueue.

---
 drivers/net/ethernet/marvell/octeontx2/af/rvu.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index 78309821ce298..f8e86f2535635 100644
@@ -2056,7 +2056,7 @@ static irqreturn_t rvu_mbox_intr_handler(int irq, void *rvu_irq)
 		rvupf_write64(rvu, RVU_PF_VFPF_MBOX_INTX(1), intr);
 
 		rvu_queue_work(&rvu->afvf_wq_info, 64, vfs, intr);
-		vfs -= 64;
+		vfs = 64;
 	}
 
 	intr = rvupf_read64(rvu, RVU_PF_VFPF_MBOX_INTX(0));

2.39.5

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

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

From: Josh Poimboeuf <[email protected]>

[ Upstream commit 09f37f2d7b21ff35b8b533f9ab8cfad2fe8f72f6 ]

sched_smt_active() can be called from noinstr code, so it should always be inlined. The CONFIG_SCHED_SMT version already has __always_inline. Do the same for its !CONFIG_SCHED_SMT counterpart.

Fixes the following warning:

vmlinux.o: error: objtool: intel_idle_ibrs+0x13: call to sched_smt_active() leaves .noinstr.text section

---
 include/linux/sched/smt.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index 59d3736c454cf..737b50f40137b 100644
@@ -12,7 +12,7 @@ static __always_inline bool sched_smt_active(void)
 	return static_branch_likely(&sched_smt_present);
 }
 #else
-static inline bool sched_smt_active(void) { return false; }
+static __always_inline bool sched_smt_active(void) { return false; }
 #endif
 
 void arch_smt_update(void);

2.39.5

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

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

From: Johannes Berg <[email protected]>

[ Upstream commit 7774e3920029398ad49dc848b23840593f14d515 ]

The firmware dumps can be pretty big, and since we use single pages for each SG table entry, even the table itself may end up being an order-5 allocation. Build chained tables so that we need not allocate a higher-order table here.

This could be improved and cleaned up, e.g. by using the SG pool code or simply kvmalloc(), but all of that would require also updating the devcoredump first since that frees it all, so we need to be more careful. SG pool might also run against the CONFIG_ARCH_NO_SG_CHAIN limitation, which is irrelevant here.

Also use _devcd_free_sgtable() for the error paths now, much simpler especially since it's in two places now.

---
 drivers/net/wireless/intel/iwlwifi/fw/dbg.c | 86 ++++++++++++++-------
 1 file changed, 58 insertions(+), 28 deletions(-)

index 79d08e5d9a81c..558caf78a56da 100644
@@ -619,41 +619,71 @@ static void iwl_dump_prph(struct iwl_fw_runtime *fwrt,
 }
 
 /*
- * alloc_sgtable - allocates scallerlist table in the given size,
- * fills it with pages and returns it
+ * alloc_sgtable - allocates (chained) scatterlist in the given size,
+ *	fills it with pages and returns it
  * @size: the size (in bytes) of the table
-*/
-static struct scatterlist *alloc_sgtable(int size)
+ */
+static struct scatterlist *alloc_sgtable(ssize_t size)
 {
-	int alloc_size, nents, i;
-	struct page *new_page;
-	struct scatterlist *iter;
-	struct scatterlist *table;
+	struct scatterlist *result = NULL, *prev;
+	int nents, i, n_prev;
 
 	nents = DIV_ROUND_UP(size, PAGE_SIZE);
-	table = kcalloc(nents, sizeof(*table), GFP_KERNEL);
-	if (!table)
-		return NULL;
-	sg_init_table(table, nents);
-	iter = table;
-	for_each_sg(table, iter, sg_nents(table), i) {
-		new_page = alloc_page(GFP_KERNEL);
-		if (!new_page) {
-			/* release all previous allocated pages in the table */
-			iter = table;
-			for_each_sg(table, iter, sg_nents(table), i) {
-				new_page = sg_page(iter);
-				if (new_page)
-					__free_page(new_page);
-			}
-			kfree(table);
+
+#define N_ENTRIES_PER_PAGE (PAGE_SIZE / sizeof(*result))
+	/*
+	 * We need an additional entry for table chaining,
+	 * this ensures the loop can finish i.e. we can
+	 * fit at least two entries per page (obviously,
+	 * many more really fit.)
+	 */
+	BUILD_BUG_ON(N_ENTRIES_PER_PAGE < 2);
+
+	while (nents > 0) {
+		struct scatterlist *new, *iter;
+		int n_fill, n_alloc;
+
+		if (nents <= N_ENTRIES_PER_PAGE) {
+			/* last needed table */
+			n_fill = nents;
+			n_alloc = nents;
+			nents = 0;
+		} else {
+			/* fill a page with entries */
+			n_alloc = N_ENTRIES_PER_PAGE;
+			/* reserve one for chaining */
+			n_fill = n_alloc - 1;
+			nents -= n_fill;
+		}
+
+		new = kcalloc(n_alloc, sizeof(*new), GFP_KERNEL);
+		if (!new) {
+			if (result)
+				_devcd_free_sgtable(result);
 			return NULL;
 		}
-		alloc_size = min_t(int, size, PAGE_SIZE);
-		size -= PAGE_SIZE;
-		sg_set_page(iter, new_page, alloc_size, 0);
+		sg_init_table(new, n_alloc);
+
+		if (!result)
+			result = new;
+		else
+			sg_chain(prev, n_prev, new);
+		prev = new;
+		n_prev = n_alloc;
+
+		for_each_sg(new, iter, n_fill, i) {
+			struct page *new_page = alloc_page(GFP_KERNEL);
+
+			if (!new_page) {
+				_devcd_free_sgtable(result);
+				return NULL;
+			}
+
+			sg_set_page(iter, new_page, PAGE_SIZE, 0);
+		}
 	}
-	return table;
+
+	return result;
 }
 
 static void iwl_fw_get_prph_len(struct iwl_fw_runtime *fwrt,

2.39.5

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

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

From: Sagi Grimberg <[email protected]>

[ Upstream commit 8c1624b63a7d24142a2bbc3a5ee7e95f004ea36e ]

nvme_tcp_poll() may race with the send path error handler because it may complete the request while it is actively being polled for completion, resulting in a UAF panic [1]:

We should make sure to stop polling when we see an error when trying to read from the socket. Hence make sure to propagate the error so that the block layer breaks the polling cycle.

[1]:
--

[35665.692310] nvme nvme2: failed to send request -13
[35665.702265] nvme nvme2: unsupported pdu type (3)
[35665.702272] BUG: kernel NULL pointer dereference, address: 0000000000000000
[35665.702542] nvme nvme2: queue 1 receive failed:  -22
[35665.703209] #PF: supervisor write access in kernel mode
[35665.703213] #PF: error_code(0x0002) - not-present page
[35665.703214] PGD 8000003801cce067 P4D 8000003801cce067 PUD 37e6f79067 PMD 0
[35665.703220] Oops: 0002 [#1] SMP PTI
[35665.703658] nvme nvme2: starting error recovery
[35665.705809] Hardware name: Inspur aaabbb/YZMB-00882-104, BIOS 4.1.26 09/22/2022
[35665.705812] Workqueue: kblockd blk_mq_requeue_work
[35665.709172] RIP: 0010:_raw_spin_lock+0xc/0x30
[35665.715788] Call Trace:
[35665.716201]  <TASK>
[35665.716613]  ? show_trace_log_lvl+0x1c1/0x2d9
[35665.717049]  ? show_trace_log_lvl+0x1c1/0x2d9
[35665.717457]  ? blk_mq_request_bypass_insert+0x2c/0xb0
[35665.717950]  ? __die_body.cold+0x8/0xd
[35665.718361]  ? page_fault_oops+0xac/0x140
[35665.718749]  ? blk_mq_start_request+0x30/0xf0
[35665.719144]  ? nvme_tcp_queue_rq+0xc7/0x170 [nvme_tcp]
[35665.719547]  ? exc_page_fault+0x62/0x130
[35665.719938]  ? asm_exc_page_fault+0x22/0x30
[35665.720333]  ? _raw_spin_lock+0xc/0x30
[35665.720723]  blk_mq_request_bypass_insert+0x2c/0xb0
[35665.721101]  blk_mq_requeue_work+0xa5/0x180
[35665.721451]  process_one_work+0x1e8/0x390
[35665.721809]  worker_thread+0x53/0x3d0
[35665.722159]  ? process_one_work+0x390/0x390
[35665.722501]  kthread+0x124/0x150
[35665.722849]  ? set_kthread_struct+0x50/0x50
[35665.723182]  ret_from_fork+0x1f/0x30

---
 drivers/nvme/host/tcp.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

index ea4d3170acae5..93835c019b8e3 100644
@@ -2462,6 +2462,7 @@ static int nvme_tcp_poll(struct blk_mq_hw_ctx *hctx)
 {
 	struct nvme_tcp_queue *queue = hctx->driver_data;
 	struct sock *sk = queue->sock->sk;
+	int ret;
 
 	if (!test_bit(NVME_TCP_Q_LIVE, &queue->flags))
 		return 0;

@@ -2469,9 +2470,9 @@ static int nvme_tcp_poll(struct blk_mq_hw_ctx *hctx)
 	set_bit(NVME_TCP_Q_POLLING, &queue->flags);
 	if (sk_can_busy_loop(sk) && skb_queue_empty_lockless(&sk->sk_receive_queue))
 		sk_busy_loop(sk, true);
-	nvme_tcp_try_recv(queue);
+	ret = nvme_tcp_try_recv(queue);
 	clear_bit(NVME_TCP_Q_POLLING, &queue->flags);
-	return queue->nr_cqe;
+	return ret < 0 ? ret : queue->nr_cqe;
 }
 
 static const struct blk_mq_ops nvme_tcp_mq_ops = {

2.39.5

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

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

From: Icenowy Zheng <[email protected]>

[ Upstream commit 6a3572e10f740acd48e2713ef37e92186a3ce5e8 ]

CMB decoding should get disabled when the CMB block isn't successfully registered to P2P DMA subsystem.

Clean up the CMBMSC register in this error handling codepath to disable CMB decoding (and CMBLOC/CMBSZ registers).

---
 drivers/nvme/host/pci.c | 1 +
 1 file changed, 1 insertion(+)

index ae04bdce560a1..7993acdfd3185 100644
@@ -1888,6 +1888,7 @@ static void nvme_map_cmb(struct nvme_dev *dev)
 	if (pci_p2pdma_add_resource(pdev, bar, size, offset)) {
 		dev_warn(dev->ctrl.device,
 			 "failed to register the CMB\n");
+		hi_lo_writeq(0, dev->bar + NVME_REG_CMBMSC);
 		return;
 	}
 

2.39.5

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

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

From: Icenowy Zheng <[email protected]>

[ Upstream commit 56cf7ef0d490b28fad8f8629fc135c5ab7c9f54e ]

The PCI P2PDMA code will register the CMB block to the memory hot-plugging subsystem, which have an alignment requirement. Memory blocks that do not satisfy this alignment requirement (usually 2MB) will lead to a WARNING from memory hotplugging.

Verify the CMB block's address and size against the alignment and only try to send CMB blocks compatible with it to prevent this warning.

Tested on Intel DC D4502 SSD, which has a 512K CMB block that is too small for memory hotplugging (thus PCI P2PDMA).

---
 drivers/nvme/host/pci.c | 20 ++++++++++++--------
 1 file changed, 12 insertions(+), 8 deletions(-)

index 7993acdfd3185..a56baaafe79df 100644
@@ -1867,6 +1867,18 @@ static void nvme_map_cmb(struct nvme_dev *dev)
 	if (offset > bar_size)
 		return;
 
+	/*
+	 * Controllers may support a CMB size larger than their BAR, for
+	 * example, due to being behind a bridge. Reduce the CMB to the
+	 * reported size of the BAR
+	 */
+	size = min(size, bar_size - offset);
+
+	if (!IS_ALIGNED(size, memremap_compat_align()) ||
+	    !IS_ALIGNED(pci_resource_start(pdev, bar),
+			memremap_compat_align()))
+		return;
+
 	/*
 	 * Tell the controller about the host side address mapping the CMB,
 	 * and enable CMB decoding for the NVMe 1.4+ scheme:

@@ -1877,14 +1889,6 @@ static void nvme_map_cmb(struct nvme_dev *dev)
 			     dev->bar + NVME_REG_CMBMSC);
 	}
 
-	/*
-	 * Controllers may support a CMB size larger than their BAR,
-	 * for example, due to being behind a bridge. Reduce the CMB to
-	 * the reported size of the BAR
-	 */
-	if (size > bar_size - offset)
-		size = bar_size - offset;
-
 	if (pci_p2pdma_add_resource(pdev, bar, size, offset)) {
 		dev_warn(dev->ctrl.device,
 			 "failed to register the CMB\n");

2.39.5

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

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

From: Simon Tatham <[email protected]>

[ Upstream commit e4cf8ec4de4e13f156c1d61977d282d90c221085 ]

If I write a file to an OFS floppy image, and try to read it back on an emulated Amiga running Workbench 1.3, the Amiga reports a disk error trying to read the file. (That is, it's unable to read it _at all_, even to copy it to the NIL: device. It isn't a matter of getting the wrong data and being unable to parse the file format.)

This is because the 'sequence number' field in the OFS data block header is supposed to be based at 1, but affs writes it based at 0. All three locations changed by this patch were setting the sequence number to a variable 'bidx' which was previously obtained by dividing a file position by bsize, so bidx will naturally use 0 for the first block. Therefore all three should add 1 to that value before writing it into the sequence number field.

With this change, the Amiga successfully reads the file.

For data block reference: https://wiki.osdev.org/FFS_(Amiga)

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

index c3d89fa1bab77..7738fafcccfc1 100644
@@ -597,7 +597,7 @@ affs_extent_file_ofs(struct inode *inode, u32 newsize)
 		BUG_ON(tmp > bsize);
 		AFFS_DATA_HEAD(bh)->ptype = cpu_to_be32(T_DATA);
 		AFFS_DATA_HEAD(bh)->key = cpu_to_be32(inode->i_ino);
-		AFFS_DATA_HEAD(bh)->sequence = cpu_to_be32(bidx);
+		AFFS_DATA_HEAD(bh)->sequence = cpu_to_be32(bidx + 1);
 		AFFS_DATA_HEAD(bh)->size = cpu_to_be32(tmp);
 		affs_fix_checksum(sb, bh);
 		bh->b_state &= ~(1UL << BH_New);

@@ -747,7 +747,7 @@ static int affs_write_end_ofs(struct file *file, struct address_space *mapping,
 		if (buffer_new(bh)) {
 			AFFS_DATA_HEAD(bh)->ptype = cpu_to_be32(T_DATA);
 			AFFS_DATA_HEAD(bh)->key = cpu_to_be32(inode->i_ino);
-			AFFS_DATA_HEAD(bh)->sequence = cpu_to_be32(bidx);
+			AFFS_DATA_HEAD(bh)->sequence = cpu_to_be32(bidx + 1);
 			AFFS_DATA_HEAD(bh)->size = cpu_to_be32(bsize);
 			AFFS_DATA_HEAD(bh)->next = 0;
 			bh->b_state &= ~(1UL << BH_New);

@@ -781,7 +781,7 @@ static int affs_write_end_ofs(struct file *file, struct address_space *mapping,
 		if (buffer_new(bh)) {
 			AFFS_DATA_HEAD(bh)->ptype = cpu_to_be32(T_DATA);
 			AFFS_DATA_HEAD(bh)->key = cpu_to_be32(inode->i_ino);
-			AFFS_DATA_HEAD(bh)->sequence = cpu_to_be32(bidx);
+			AFFS_DATA_HEAD(bh)->sequence = cpu_to_be32(bidx + 1);
 			AFFS_DATA_HEAD(bh)->size = cpu_to_be32(tmp);
 			AFFS_DATA_HEAD(bh)->next = 0;
 			bh->b_state &= ~(1UL << BH_New);

2.39.5

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

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

From: Simon Tatham <[email protected]>

[ Upstream commit 011ea742a25a77bac3d995f457886a67d178c6f0 ]

If a data sector on an OFS floppy contains a value > 0x1e8 (the largest amount of data that fits in the sector after its header), then an Amiga reading the file can return corrupt data, by taking the overlarge size at its word and reading past the end of the buffer it read the disk sector into!

The cause: when affs_write_end_ofs() writes data to an OFS filesystem, the new size field for a data block was computed by adding the amount of data currently being written (into the block) to the existing value of the size field. This is correct if you're extending the file at the end, but if you seek backwards in the file and overwrite _existing_ data, it can lead to the size field being larger than the maximum legal value.

This commit changes the calculation so that it sets the size field to the max of its previous size and the position within the block that we just wrote up to.

---
 fs/affs/file.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

index 7738fafcccfc1..bc88ba29d393c 100644
@@ -725,7 +725,8 @@ static int affs_write_end_ofs(struct file *file, struct address_space *mapping,
 		tmp = min(bsize - boff, to - from);
 		BUG_ON(boff + tmp > bsize || tmp > bsize);
 		memcpy(AFFS_DATA(bh) + boff, data + from, tmp);
-		be32_add_cpu(&AFFS_DATA_HEAD(bh)->size, tmp);
+		AFFS_DATA_HEAD(bh)->size = cpu_to_be32(
+			max(boff + tmp, be32_to_cpu(AFFS_DATA_HEAD(bh)->size)));
 		affs_fix_checksum(sb, bh);
 		mark_buffer_dirty_inode(bh, inode);
 		written += tmp;

2.39.5

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

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

From: Dmitry Panchenko <[email protected]>

[ Upstream commit 2738d06fb4f01145b24c542fb06de538ffc56430 ]

Volume buttons on Microsoft Surface Go 4 tablet didn't send any events. Add Surface Go 4 DMI match to button_array_table to fix this.

---
 drivers/platform/x86/intel-hid.c | 7 +++++++
 1 file changed, 7 insertions(+)

index 0b0602fc43601..9bc2652b15e71 100644
@@ -100,6 +100,13 @@ static const struct dmi_system_id button_array_table[] = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "Surface Go 3"),
 		},
 	},
+	{
+		.ident = "Microsoft Surface Go 4",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Microsoft Corporation"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Surface Go 4"),
+		},
+	},
 	{ }
 };
 

2.39.5

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

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

From: Shrikanth Hegde <[email protected]>

[ Upstream commit 14672f059d83f591afb2ee1fff56858efe055e5a ]

The ftrace selftest reported a failure because writing -1 to sched_rt_runtime_us returns -EBUSY. This happens when the possible CPUs are different from active CPUs.

Active CPUs are part of one root domain, while remaining CPUs are part of def_root_domain. Since active cpumask is being used, this results in cpus=0 when a non active CPUs is used in the loop.

Fix it by looping over the online CPUs instead for validating the bandwidth calculations.

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

index d91295d3059f7..6548bd90c5c3a 100644
@@ -2577,7 +2577,7 @@ int sched_dl_global_validate(void)
 	 * cycling on root_domains... Discussion on different/better
 	 * solutions is welcome!
 	 */
-	for_each_possible_cpu(cpu) {
+	for_each_online_cpu(cpu) {
 		rcu_read_lock_sched();
 		dl_b = dl_bw_of(cpu);
 		cpus = dl_bw_cpus(cpu);

2.39.5

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

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

From: Waiman Long <[email protected]>

[ Upstream commit 85b2b9c16d053364e2004883140538e73b333cdb ]

A circular lock dependency splat has been seen involving down_trylock():

======================================================
WARNING: possible circular locking dependency detected 6.12.0-41.el10.s390x+debug
------------------------------------------------------
dd/32479 is trying to acquire lock:
0015a20accd0d4f8 ((console_sem).lock){-.-.}-{2:2}, at: down_trylock+0x26/0x90

but task is already holding lock:
000000017e461698 (&zone->lock){-.-.}-{2:2}, at: rmqueue_bulk+0xac/0x8f0

the existing dependency chain (in reverse order) is:
-> #4 (&zone->lock){-.-.}-{2:2}:
-> #3 (hrtimer_bases.lock){-.-.}-{2:2}:
-> #2 (&rq->__lock){-.-.}-{2:2}:
-> #1 (&p->pi_lock){-.-.}-{2:2}:
-> #0 ((console_sem).lock){-.-.}-{2:2}:

The console_sem -> pi_lock dependency is due to calling try_to_wake_up() while holding the console_sem raw_spinlock. This dependency can be broken by using wake_q to do the wakeup instead of calling try_to_wake_up() under the console_sem lock. This will also make the semaphore's raw_spinlock become a terminal lock without taking any further locks underneath it.

The hrtimer_bases.lock is a raw_spinlock while zone->lock is a spinlock. The hrtimer_bases.lock -> zone->lock dependency happens via the debug_objects_fill_pool() helper function in the debugobjects code.

-> #4 (&zone->lock){-.-.}-{2:2}:

         __lock_acquire+0xe86/0x1cc0
         lock_acquire.part.0+0x258/0x630
         lock_acquire+0xb8/0xe0
         _raw_spin_lock_irqsave+0xb4/0x120
         rmqueue_bulk+0xac/0x8f0
         __rmqueue_pcplist+0x580/0x830
         rmqueue_pcplist+0xfc/0x470
         rmqueue.isra.0+0xdec/0x11b0
         get_page_from_freelist+0x2ee/0xeb0
         __alloc_pages_noprof+0x2c2/0x520
         alloc_pages_mpol_noprof+0x1fc/0x4d0
         alloc_pages_noprof+0x8c/0xe0
         allocate_slab+0x320/0x460
         ___slab_alloc+0xa58/0x12b0
         __slab_alloc.isra.0+0x42/0x60
         kmem_cache_alloc_noprof+0x304/0x350
         fill_pool+0xf6/0x450
         debug_object_activate+0xfe/0x360
         enqueue_hrtimer+0x34/0x190
         __run_hrtimer+0x3c8/0x4c0
         __hrtimer_run_queues+0x1b2/0x260
         hrtimer_interrupt+0x316/0x760
         do_IRQ+0x9a/0xe0
         do_irq_async+0xf6/0x160

Normally a raw_spinlock to spinlock dependency is not legitimate and will be warned if CONFIG_PROVE_RAW_LOCK_NESTING is enabled, but debug_objects_fill_pool() is an exception as it explicitly allows this dependency for non-PREEMPT_RT kernel without causing PROVE_RAW_LOCK_NESTING lockdep splat. As a result, this dependency is legitimate and not a bug.

Anyway, semaphore is the only locking primitive left that is still using try_to_wake_up() to do wakeup inside critical section, all the other locking primitives had been migrated to use wake_q to do wakeup outside of the critical section. It is also possible that there are other circular locking dependencies involving printk/console_sem or other existing/new semaphores lurking somewhere which may show up in the future. Let just do the migration now to wake_q to avoid headache like this.

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

index 9aa855a96c4ae..aadde65402913 100644
@@ -29,6 +29,7 @@
 #include <linux/export.h>
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
+#include <linux/sched/wake_q.h>
 #include <linux/semaphore.h>
 #include <linux/spinlock.h>
 #include <linux/ftrace.h>

@@ -37,7 +38,7 @@ static noinline void __down(struct semaphore *sem);
 static noinline int __down_interruptible(struct semaphore *sem);
 static noinline int __down_killable(struct semaphore *sem);
 static noinline int __down_timeout(struct semaphore *sem, long timeout);
-static noinline void __up(struct semaphore *sem);
+static noinline void __up(struct semaphore *sem, struct wake_q_head *wake_q);
 
 /**
  * down - acquire the semaphore

@@ -178,13 +179,16 @@ EXPORT_SYMBOL(down_timeout);
 void up(struct semaphore *sem)
 {
 	unsigned long flags;
+	DEFINE_WAKE_Q(wake_q);
 
 	raw_spin_lock_irqsave(&sem->lock, flags);
 	if (likely(list_empty(&sem->wait_list)))
 		sem->count++;
 	else
-		__up(sem);
+		__up(sem, &wake_q);
 	raw_spin_unlock_irqrestore(&sem->lock, flags);
+	if (!wake_q_empty(&wake_q))
+		wake_up_q(&wake_q);
 }
 EXPORT_SYMBOL(up);
 

@@ -252,11 +256,12 @@ static noinline int __sched __down_timeout(struct semaphore *sem, long timeout)
 	return __down_common(sem, TASK_UNINTERRUPTIBLE, timeout);
 }
 
-static noinline void __sched __up(struct semaphore *sem)
+static noinline void __sched __up(struct semaphore *sem,
+				  struct wake_q_head *wake_q)
 {
 	struct semaphore_waiter *waiter = list_first_entry(&sem->wait_list,
 						struct semaphore_waiter, list);
 	list_del(&waiter->list);
 	waiter->up = true;
-	wake_up_process(waiter->task);
+	wake_q_add(wake_q, waiter->task);
 }

2.39.5

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

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

From: Navon John Lukose <[email protected]>

[ Upstream commit b11a74ac4f545626d0dc95a8ca8c41df90532bf3 ]

Add a fixup to enable the mute LED on HP Pavilion x360 Convertible 14-dy1xxx with ALC295 codec. The appropriate coefficient index and bits were identified through a brute-force method, as detailed in
https://bbs.archlinux.org/viewtopic.php?pid=2079504#p2079504.

---
 sound/pci/hda/patch_realtek.c | 21 +++++++++++++++++++++
 1 file changed, 21 insertions(+)

index f3cb24ed3a78a..3fdd2337919e1 100644
@@ -4702,6 +4702,21 @@ static void alc236_fixup_hp_coef_micmute_led(struct hda_codec *codec,
 	}
 }
 
+static void alc295_fixup_hp_mute_led_coefbit11(struct hda_codec *codec,
+				const struct hda_fixup *fix, int action)
+{
+	struct alc_spec *spec = codec->spec;
+
+	if (action == HDA_FIXUP_ACT_PRE_PROBE) {
+		spec->mute_led_polarity = 0;
+		spec->mute_led_coef.idx = 0xb;
+		spec->mute_led_coef.mask = 3 << 3;
+		spec->mute_led_coef.on = 1 << 3;
+		spec->mute_led_coef.off = 1 << 4;
+		snd_hda_gen_add_mute_led_cdev(codec, coef_mute_led_set);
+	}
+}
+
 static void alc285_fixup_hp_mute_led(struct hda_codec *codec,
 				const struct hda_fixup *fix, int action)
 {

@@ -6942,6 +6957,7 @@ enum {
 	ALC290_FIXUP_MONO_SPEAKERS_HSJACK,
 	ALC290_FIXUP_SUBWOOFER,
 	ALC290_FIXUP_SUBWOOFER_HSJACK,
+	ALC295_FIXUP_HP_MUTE_LED_COEFBIT11,
 	ALC269_FIXUP_THINKPAD_ACPI,
 	ALC269_FIXUP_DMIC_THINKPAD_ACPI,
 	ALC269VB_FIXUP_INFINIX_ZERO_BOOK_13,

@@ -8487,6 +8503,10 @@ static const struct hda_fixup alc269_fixups[] = {
 		.chained = true,
 		.chain_id = ALC283_FIXUP_INT_MIC,
 	},
+	[ALC295_FIXUP_HP_MUTE_LED_COEFBIT11] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc295_fixup_hp_mute_led_coefbit11,
+	},
 	[ALC298_FIXUP_SAMSUNG_AMP] = {
 		.type = HDA_FIXUP_FUNC,
 		.v.func = alc298_fixup_samsung_amp,

@@ -9195,6 +9215,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x103c, 0x84e7, "HP Pavilion 15", ALC269_FIXUP_HP_MUTE_LED_MIC3),
 	SND_PCI_QUIRK(0x103c, 0x8519, "HP Spectre x360 15-df0xxx", ALC285_FIXUP_HP_SPECTRE_X360),
 	SND_PCI_QUIRK(0x103c, 0x8537, "HP ProBook 440 G6", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF),
+	SND_PCI_QUIRK(0x103c, 0x85c6, "HP Pavilion x360 Convertible 14-dy1xxx", ALC295_FIXUP_HP_MUTE_LED_COEFBIT11),
 	SND_PCI_QUIRK(0x103c, 0x85de, "HP Envy x360 13-ar0xxx", ALC285_FIXUP_HP_ENVY_X360),
 	SND_PCI_QUIRK(0x103c, 0x860f, "HP ZBook 15 G6", ALC285_FIXUP_HP_GPIO_AMP_INIT),
 	SND_PCI_QUIRK(0x103c, 0x861f, "HP Elite Dragonfly G1", ALC285_FIXUP_HP_GPIO_AMP_INIT),

2.39.5

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

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

From: Oliver Hartkopp <[email protected]>

[ Upstream commit 80b5f90158d1364cbd80ad82852a757fc0692bf2 ]

In can_send() and can_receive() CAN messages and CAN filter matches are counted to be visible in the CAN procfs files.

KCSAN detected a data race within can_send() when two CAN frames have been generated by a timer event writing to the same CAN netdevice at the same time. Use atomic operations to access the statistics in the hot path to fix the KCSAN complaint.

---
 net/can/af_can.c | 12 ++++++------
 net/can/af_can.h | 12 ++++++------
 net/can/proc.c   | 46 +++++++++++++++++++++++++++-------------------
 3 files changed, 39 insertions(+), 31 deletions(-)

index de47c16b134bf..3e77a52709aaa 100644
@@ -288,8 +288,8 @@ int can_send(struct sk_buff *skb, int loop)
 		netif_rx_ni(newskb);
 
 	/* update statistics */
-	pkg_stats->tx_frames++;
-	pkg_stats->tx_frames_delta++;
+	atomic_long_inc(&pkg_stats->tx_frames);
+	atomic_long_inc(&pkg_stats->tx_frames_delta);
 
 	return 0;
 

@@ -649,8 +649,8 @@ static void can_receive(struct sk_buff *skb, struct net_device *dev)
 	int matches;
 
 	/* update statistics */
-	pkg_stats->rx_frames++;
-	pkg_stats->rx_frames_delta++;
+	atomic_long_inc(&pkg_stats->rx_frames);
+	atomic_long_inc(&pkg_stats->rx_frames_delta);
 
 	/* create non-zero unique skb identifier together with *skb */
 	while (!(can_skb_prv(skb)->skbcnt))

@@ -671,8 +671,8 @@ static void can_receive(struct sk_buff *skb, struct net_device *dev)
 	consume_skb(skb);
 
 	if (matches > 0) {
-		pkg_stats->matches++;
-		pkg_stats->matches_delta++;
+		atomic_long_inc(&pkg_stats->matches);
+		atomic_long_inc(&pkg_stats->matches_delta);
 	}
 }
 

index 7c2d9161e2245..22f3352c77fec 100644
@@ -66,9 +66,9 @@ struct receiver {
 struct can_pkg_stats {
 	unsigned long jiffies_init;
 
-	unsigned long rx_frames;
-	unsigned long tx_frames;
-	unsigned long matches;
+	atomic_long_t rx_frames;
+	atomic_long_t tx_frames;
+	atomic_long_t matches;
 
 	unsigned long total_rx_rate;
 	unsigned long total_tx_rate;

@@ -82,9 +82,9 @@ struct can_pkg_stats {
 	unsigned long max_tx_rate;
 	unsigned long max_rx_match_ratio;
 
-	unsigned long rx_frames_delta;
-	unsigned long tx_frames_delta;
-	unsigned long matches_delta;
+	atomic_long_t rx_frames_delta;
+	atomic_long_t tx_frames_delta;
+	atomic_long_t matches_delta;
 };
 
 /* persistent statistics */

2.39.5

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

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

From: Tasos Sahanidis <[email protected]>

[ Upstream commit 815f80ad20b63830949a77c816e35395d5d55144 ]

pwm_num is set to 7 for these chips, but NCT6776_REG_PWM_MODE and NCT6776_PWM_MODE_MASK only contain 6 values.

Fix this by adding another 0 to the end of each array.

---
 drivers/hwmon/nct6775.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

index 3645a19cdaf4d..71cfc1c5bd12e 100644
@@ -420,8 +420,8 @@ static const s8 NCT6776_BEEP_BITS[] = {
 static const u16 NCT6776_REG_TOLERANCE_H[] = {
 	0x10c, 0x20c, 0x30c, 0x80c, 0x90c, 0xa0c, 0xb0c };
 
-static const u8 NCT6776_REG_PWM_MODE[] = { 0x04, 0, 0, 0, 0, 0 };
-static const u8 NCT6776_PWM_MODE_MASK[] = { 0x01, 0, 0, 0, 0, 0 };
+static const u8 NCT6776_REG_PWM_MODE[] = { 0x04, 0, 0, 0, 0, 0, 0 };
+static const u8 NCT6776_PWM_MODE_MASK[] = { 0x01, 0, 0, 0, 0, 0, 0 };
 
 static const u16 NCT6776_REG_FAN_MIN[] = {
 	0x63a, 0x63c, 0x63e, 0x640, 0x642, 0x64a, 0x64c };

2.39.5

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

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

From: Al Viro <[email protected]>

[ Upstream commit d1ca8698ca1332625d83ea0d753747be66f9906d ]

It's called from spufs_fill_dir(), and caller of that will do spufs_rmdir() in case of failure. That does remove everything we'd managed to create, but... the problem dentry is still negative. IOW, it needs to be explicitly dropped.

---
 arch/powerpc/platforms/cell/spufs/inode.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

index 908e9b8e79fe6..0159bd9231ef8 100644
@@ -189,8 +189,10 @@ static int spufs_fill_dir(struct dentry *dir,
 			return -ENOMEM;
 		ret = spufs_new_file(dir->d_sb, dentry, files->ops,
 					files->mode & mode, files->size, ctx);
-		if (ret)
+		if (ret) {
+			dput(dentry);
 			return ret;
+		}
 		files++;
 	}
 	return 0;

2.39.5

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

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

From: Al Viro <[email protected]>

[ Upstream commit 0f5cce3fc55b08ee4da3372baccf4bcd36a98396 ]

Leak fixes back in 2008 missed one case - if we are trying to set affinity and spufs_mkdir() fails, we need to drop the reference to neighbor.

---
 arch/powerpc/platforms/cell/spufs/inode.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

index 0159bd9231ef8..373814bbc43d7 100644
@@ -438,8 +438,11 @@ spufs_create_context(struct inode *inode, struct dentry *dentry,
 	}
 
 	ret = spufs_mkdir(inode, dentry, flags, mode & 0777);
-	if (ret)
+	if (ret) {
+		if (neighbor)
+			put_spu_context(neighbor);
 		goto out_aff_unlock;
+	}
 
 	if (affinity) {
 		spufs_set_affinity(flags, SPUFS_I(d_inode(dentry))->i_ctx,

2.39.5

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

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

From: Yajun Deng <[email protected]>

[ Upstream commit de203da734fae00e75be50220ba5391e7beecdf9 ]

There is a kernel API ntb_mw_clear_trans() would pass 0 to both addr and size. This would make xlate_pos negative.

[   23.734156] switchtec switchtec0: MW 0: part 0 addr 0x0000000000000000 size 0x0000000000000000
[   23.734158] ================================================================================
[   23.734172] UBSAN: shift-out-of-bounds in drivers/ntb/hw/mscc/ntb_hw_switchtec.c:293:7
[   23.734418] shift exponent -1 is negative

Ensuring xlate_pos is a positive or zero before BIT.

---
 drivers/ntb/hw/mscc/ntb_hw_switchtec.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index ad09946100b56..c5c1963c699d9 100644
@@ -288,7 +288,7 @@ static int switchtec_ntb_mw_set_trans(struct ntb_dev *ntb, int pidx, int widx,
 	if (size != 0 && xlate_pos < 12)
 		return -EINVAL;
 
-	if (!IS_ALIGNED(addr, BIT_ULL(xlate_pos))) {
+	if (xlate_pos >= 0 && !IS_ALIGNED(addr, BIT_ULL(xlate_pos))) {
 		/*
 		 * In certain circumstances we can get a buffer that is
 		 * not aligned to its size. (Most of the time

2.39.5

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

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

From: Nikita Shubin <[email protected]>

[ Upstream commit 8144e9c8f30fb23bb736a5d24d5c9d46965563c4 ]

Make sure we are not using DB's which were remapped for link status.

---
 drivers/ntb/hw/intel/ntb_hw_gen3.c | 3 +++
 1 file changed, 3 insertions(+)

index ffcfc3e02c353..a5aa96a31f4a6 100644
@@ -215,6 +215,9 @@ static int gen3_init_ntb(struct intel_ntb_dev *ndev)
 	}
 
 	ndev->db_valid_mask = BIT_ULL(ndev->db_count) - 1;
+	/* Make sure we are not using DB's used for link status */
+	if (ndev->hwerr_flags & NTB_HWERR_MSIX_VECTOR32_BAD)
+		ndev->db_valid_mask &= ~ndev->db_link_mask;
 
 	ndev->reg->db_iowrite(ndev->db_valid_mask,
 			      ndev->self_mmio +

2.39.5

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

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

From: Debin Zhu <[email protected]>

[ Upstream commit 078aabd567de3d63d37d7673f714e309d369e6e2 ]

When calling netlbl_conn_setattr(), addr->sa_family is used to determine the function behavior. If sk is an IPv4 socket, but the connect function is called with an IPv6 address, the function calipso_sock_setattr() is triggered. Inside this function, the following code is executed:

sk_fullsock(__sk) ? inet_sk(__sk)->pinet6 : NULL;

Since sk is an IPv4 socket, pinet6 is NULL, leading to a null pointer dereference.

This patch fixes the issue by checking if inet6_sk(sk) returns a NULL pointer before accessing pinet6.

---
 net/ipv6/calipso.c | 21 ++++++++++++++++++---
 1 file changed, 18 insertions(+), 3 deletions(-)

index 0ea66e9db2495..e17e756bb1ad9 100644
@@ -1075,8 +1075,13 @@ static int calipso_sock_getattr(struct sock *sk,
 	struct ipv6_opt_hdr *hop;
 	int opt_len, len, ret_val = -ENOMSG, offset;
 	unsigned char *opt;
-	struct ipv6_txoptions *txopts = txopt_get(inet6_sk(sk));
+	struct ipv6_pinfo *pinfo = inet6_sk(sk);
+	struct ipv6_txoptions *txopts;
+
+	if (!pinfo)
+		return -EAFNOSUPPORT;
 
+	txopts = txopt_get(pinfo);
 	if (!txopts || !txopts->hopopt)
 		goto done;
 

@@ -1128,8 +1133,13 @@ static int calipso_sock_setattr(struct sock *sk,
 {
 	int ret_val;
 	struct ipv6_opt_hdr *old, *new;
-	struct ipv6_txoptions *txopts = txopt_get(inet6_sk(sk));
+	struct ipv6_pinfo *pinfo = inet6_sk(sk);
+	struct ipv6_txoptions *txopts;
+
+	if (!pinfo)
+		return -EAFNOSUPPORT;
 
+	txopts = txopt_get(pinfo);
 	old = NULL;
 	if (txopts)
 		old = txopts->hopopt;

@@ -1156,8 +1166,13 @@ static int calipso_sock_setattr(struct sock *sk,
 static void calipso_sock_delattr(struct sock *sk)
 {
 	struct ipv6_opt_hdr *new_hop;
-	struct ipv6_txoptions *txopts = txopt_get(inet6_sk(sk));
+	struct ipv6_pinfo *pinfo = inet6_sk(sk);
+	struct ipv6_txoptions *txopts;
+
+	if (!pinfo)
+		return;
 
+	txopts = txopt_get(pinfo);
 	if (!txopts || !txopts->hopopt)
 		goto done;
 

2.39.5

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

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

From: Cong Wang <[email protected]>

[ Upstream commit ce8fe975fd99b49c29c42e50f2441ba53112b2e8 ]

In the current implementation, skbprio enqueue/dequeue contains an assertion that fails under certain conditions when SKBPRIO is used as a child qdisc under TBF with specific parameters. The failure occurs because TBF sometimes peeks at packets in the child qdisc without actually dequeuing them when tokens are unavailable.

This peek operation creates a discrepancy between the parent and child qdisc queue length counters. When TBF later receives a high-priority packet, SKBPRIO's queue length may show a different value than what's reflected in its internal priority queue tracking, triggering the assertion.

The fix removes this overly strict assertions in SKBPRIO, they are not necessary at all.

---
 net/sched/sch_skbprio.c | 3 ---
 1 file changed, 3 deletions(-)

index df72fb83d9c7d..c9e422e466159 100644
@@ -121,8 +121,6 @@ static int skbprio_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 	/* Check to update highest and lowest priorities. */
 	if (skb_queue_empty(lp_qdisc)) {
 		if (q->lowest_prio == q->highest_prio) {
-			/* The incoming packet is the only packet in queue. */
-			BUG_ON(sch->q.qlen != 1);
 			q->lowest_prio = prio;
 			q->highest_prio = prio;
 		} else {

@@ -154,7 +152,6 @@ static struct sk_buff *skbprio_dequeue(struct Qdisc *sch)
 	/* Update highest priority field. */
 	if (skb_queue_empty(hpq)) {
 		if (q->lowest_prio == q->highest_prio) {
-			BUG_ON(sch->q.qlen);
 			q->highest_prio = 0;
 			q->lowest_prio = SKBPRIO_MAX_PRIORITY - 1;
 		} else {

2.39.5

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

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

From: Stefano Garzarella <[email protected]>

[ Upstream commit fccd2b711d9628c7ce0111d5e4938652101ee30a ]

When a peer attempts to establish a connection, vsock_connect() contains a loop that waits for the state to be TCP_ESTABLISHED. However, the other peer can be fast enough to accept the connection and close it immediately, thus moving the state to TCP_CLOSING.

When this happens, the peer in the vsock_connect() is properly woken up, but since the state is not TCP_ESTABLISHED, it goes back to sleep until the timeout expires, returning -ETIMEDOUT.

If the socket state is TCP_CLOSING, waiting for the timeout is pointless. vsock_connect() can return immediately without errors or delay since the connection actually happened. The socket will be in a closing state, but this is not an issue, and subsequent calls will fail as expected.

We discovered this issue while developing a test that accepts and immediately closes connections to stress the transport switch between two connect() calls, where the first one was interrupted by a signal (see Closes link).

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

index d7395601a0e30..fc0306ba2d43e 100644
@@ -1382,7 +1382,11 @@ static int vsock_stream_connect(struct socket *sock, struct sockaddr *addr,
 	timeout = vsk->connect_timeout;
 	prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
 
-	while (sk->sk_state != TCP_ESTABLISHED && sk->sk_err == 0) {
+	/* If the socket is already closing or it is in an error state, there
+	 * is no point in waiting.
+	 */
+	while (sk->sk_state != TCP_ESTABLISHED &&
+	       sk->sk_state != TCP_CLOSING && sk->sk_err == 0) {
 		if (flags & O_NONBLOCK) {
 			/* If we're not going to block, we schedule a timeout
 			 * function to generate a timeout on the connection

2.39.5

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

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

From: Guillaume Nault <[email protected]>

[ Upstream commit 8930424777e43257f5bf6f0f0f53defd0d30415c ]

Because skb_tunnel_check_pmtu() doesn't handle PACKET_HOST packets, commit 30a92c9e3d6b ("openvswitch: Set the skbuff pkt_type for proper pmtud support.") forced skb->pkt_type to PACKET_OUTGOING for openvswitch packets that are sent using the OVS_ACTION_ATTR_OUTPUT action. This allowed such packets to invoke the iptunnel_pmtud_check_icmp() or iptunnel_pmtud_check_icmpv6() helpers and thus trigger PMTU update on the input device.

However, this also broke other parts of PMTU discovery. Since these packets don't have the PACKET_HOST type anymore, they won't trigger the sending of ICMP Fragmentation Needed or Packet Too Big messages to remote hosts when oversized (see the skb_in->pkt_type condition in __icmp_send() for example).

These two skb->pkt_type checks are therefore incompatible as one requires skb->pkt_type to be PACKET_HOST, while the other requires it to be anything but PACKET_HOST.

It makes sense to not trigger ICMP messages for non-PACKET_HOST packets as these messages should be generated only for incoming l2-unicast packets. However there doesn't seem to be any reason for skb_tunnel_check_pmtu() to ignore PACKET_HOST packets.

Allow both cases to work by allowing skb_tunnel_check_pmtu() to work on PACKET_HOST packets and not overriding skb->pkt_type in openvswitch anymore.

---
 net/ipv4/ip_tunnel_core.c | 2 +-
 net/openvswitch/actions.c | 6 ------
 2 files changed, 1 insertion(+), 7 deletions(-)

index ba1388ba6c6e5..dad9d7db5bf6c 100644
@@ -415,7 +415,7 @@ int skb_tunnel_check_pmtu(struct sk_buff *skb, struct dst_entry *encap_dst,
 
 	skb_dst_update_pmtu_no_confirm(skb, mtu);
 
-	if (!reply || skb->pkt_type == PACKET_HOST)
+	if (!reply)
 		return 0;
 
 	if (skb->protocol == htons(ETH_P_IP))

index 4095456f413df..80fee9d118eec 100644
@@ -923,12 +923,6 @@ static void do_output(struct datapath *dp, struct sk_buff *skb, int out_port,
 				pskb_trim(skb, ovs_mac_header_len(key));
 		}
 
-		/* Need to set the pkt_type to involve the routing layer.  The
-		 * packet movement through the OVS datapath doesn't generally
-		 * use routing, but this is needed for tunnel cases.
-		 */
-		skb->pkt_type = PACKET_OUTGOING;
-
 		if (likely(!mru ||
 		           (skb->len <= mru + vport->dev->hard_header_len))) {
 			ovs_vport_send(vport, skb, ovs_key_mac_proto(key));

2.39.5

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

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

From: Lin Ma <[email protected]>

[ Upstream commit 1b755d8eb1ace3870789d48fbd94f386ad6e30be ]

When handling multiple NFTA_TUNNEL_KEY_OPTS_GENEVE attributes, the parsing logic should place every geneve_opt structure one by one compactly. Hence, when deciding the next geneve_opt position, the pointer addition should be in units of char *.

However, the current implementation erroneously does type conversion before the addition, which will lead to heap out-of-bounds write.

[    6.989857] ==================================================================
[    6.990293] BUG: KASAN: slab-out-of-bounds in nft_tunnel_obj_init+0x977/0xa70
[    6.990725] Write of size 124 at addr ffff888005f18974 by task poc/178
[    6.991162]
[    6.991259] CPU: 0 PID: 178 Comm: poc-oob-write Not tainted 6.1.132 #1
[    6.991655] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.0-0-gd239552ce722-prebuilt.qemu.org 04/01/2014
[    6.992281] Call Trace:
[    6.992423]  <TASK>
[    6.992586]  dump_stack_lvl+0x44/0x5c
[    6.992801]  print_report+0x184/0x4be
[    6.993790]  kasan_report+0xc5/0x100
[    6.994252]  kasan_check_range+0xf3/0x1a0
[    6.994486]  memcpy+0x38/0x60
[    6.994692]  nft_tunnel_obj_init+0x977/0xa70
[    6.995677]  nft_obj_init+0x10c/0x1b0
[    6.995891]  nf_tables_newobj+0x585/0x950
[    6.996922]  nfnetlink_rcv_batch+0xdf9/0x1020
[    6.998997]  nfnetlink_rcv+0x1df/0x220
[    6.999537]  netlink_unicast+0x395/0x530
[    7.000771]  netlink_sendmsg+0x3d0/0x6d0
[    7.001462]  __sock_sendmsg+0x99/0xa0
[    7.001707]  ____sys_sendmsg+0x409/0x450
[    7.002391]  ___sys_sendmsg+0xfd/0x170
[    7.003145]  __sys_sendmsg+0xea/0x170
[    7.004359]  do_syscall_64+0x5e/0x90
[    7.005817]  entry_SYSCALL_64_after_hwframe+0x6e/0xd8
[    7.006127] RIP: 0033:0x7ec756d4e407
[    7.006339] Code: 48 89 fa 4c 89 df e8 38 aa 00 00 8b 93 08 03 00 00 59 5e 48 83 f8 fc 74 1a 5b c3 0f 1f 84 00 00 00 00 00 48 8b 44 24 10 0f 05 <5b> c3 0f 1f 80 00 00 00 00 83 e2 39 83 faf
[    7.007364] RSP: 002b:00007ffed5d46760 EFLAGS: 00000202 ORIG_RAX: 000000000000002e
[    7.007827] RAX: ffffffffffffffda RBX: 00007ec756cc4740 RCX: 00007ec756d4e407
[    7.008223] RDX: 0000000000000000 RSI: 00007ffed5d467f0 RDI: 0000000000000003
[    7.008620] RBP: 00007ffed5d468a0 R08: 0000000000000000 R09: 0000000000000000
[    7.009039] R10: 0000000000000000 R11: 0000000000000202 R12: 0000000000000000
[    7.009429] R13: 00007ffed5d478b0 R14: 00007ec756ee5000 R15: 00005cbd4e655cb8

Fix this bug with correct pointer addition and conversion in parse and dump code.

---
 net/netfilter/nft_tunnel.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

index c8822fa8196d9..1b05b70497283 100644
@@ -311,7 +311,7 @@ static const struct nla_policy nft_tunnel_opts_geneve_policy[NFTA_TUNNEL_KEY_GEN
 static int nft_tunnel_obj_geneve_init(const struct nlattr *attr,
 				      struct nft_tunnel_opts *opts)
 {
-	struct geneve_opt *opt = (struct geneve_opt *)opts->u.data + opts->len;
+	struct geneve_opt *opt = (struct geneve_opt *)(opts->u.data + opts->len);
 	struct nlattr *tb[NFTA_TUNNEL_KEY_GENEVE_MAX + 1];
 	int err, data_len;
 

@@ -592,7 +592,7 @@ static int nft_tunnel_opts_dump(struct sk_buff *skb,
 		if (!inner)
 			goto failure;
 		while (opts->len > offset) {
-			opt = (struct geneve_opt *)opts->u.data + offset;
+			opt = (struct geneve_opt *)(opts->u.data + offset);
 			if (nla_put_be16(skb, NFTA_TUNNEL_KEY_GENEVE_CLASS,
 					 opt->opt_class) ||
 			    nla_put_u8(skb, NFTA_TUNNEL_KEY_GENEVE_TYPE,

2.39.5

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

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

From: Fernando Fernandez Mancera <[email protected]>

[ Upstream commit 7ac6ea4a3e0898db76aecccd68fb2c403eb7d24e ]

Using RTEXT_FILTER_SKIP_STATS is incorrectly skipping non-stats IPv6 netlink attributes on link dump. This causes issues on userspace tools, e.g iproute2 is not rendering address generation mode as it should due to missing netlink attribute.

Move the filling of IFLA_INET6_STATS and IFLA_INET6_ICMP6STATS to a helper function guarded by a flag check to avoid hitting the same situation in the future.

---
 net/ipv6/addrconf.c | 37 +++++++++++++++++++++++++------------
 1 file changed, 25 insertions(+), 12 deletions(-)

index 455bb4668407f..d38d15ccc7501 100644
@@ -5658,6 +5658,27 @@ static void snmp6_fill_stats(u64 *stats, struct inet6_dev *idev, int attrtype,
 	}
 }
 
+static int inet6_fill_ifla6_stats_attrs(struct sk_buff *skb,
+					struct inet6_dev *idev)
+{
+	struct nlattr *nla;
+
+	nla = nla_reserve(skb, IFLA_INET6_STATS, IPSTATS_MIB_MAX * sizeof(u64));
+	if (!nla)
+		goto nla_put_failure;
+	snmp6_fill_stats(nla_data(nla), idev, IFLA_INET6_STATS, nla_len(nla));
+
+	nla = nla_reserve(skb, IFLA_INET6_ICMP6STATS, ICMP6_MIB_MAX * sizeof(u64));
+	if (!nla)
+		goto nla_put_failure;
+	snmp6_fill_stats(nla_data(nla), idev, IFLA_INET6_ICMP6STATS, nla_len(nla));
+
+	return 0;
+
+nla_put_failure:
+	return -EMSGSIZE;
+}
+
 static int inet6_fill_ifla6_attrs(struct sk_buff *skb, struct inet6_dev *idev,
 				  u32 ext_filter_mask)
 {

@@ -5679,18 +5700,10 @@ static int inet6_fill_ifla6_attrs(struct sk_buff *skb, struct inet6_dev *idev,
 
 	/* XXX - MC not implemented */
 
-	if (ext_filter_mask & RTEXT_FILTER_SKIP_STATS)
-		return 0;
-
-	nla = nla_reserve(skb, IFLA_INET6_STATS, IPSTATS_MIB_MAX * sizeof(u64));
-	if (!nla)
-		goto nla_put_failure;
-	snmp6_fill_stats(nla_data(nla), idev, IFLA_INET6_STATS, nla_len(nla));
-
-	nla = nla_reserve(skb, IFLA_INET6_ICMP6STATS, ICMP6_MIB_MAX * sizeof(u64));
-	if (!nla)
-		goto nla_put_failure;
-	snmp6_fill_stats(nla_data(nla), idev, IFLA_INET6_ICMP6STATS, nla_len(nla));
+	if (!(ext_filter_mask & RTEXT_FILTER_SKIP_STATS)) {
+		if (inet6_fill_ifla6_stats_attrs(skb, idev) < 0)
+			goto nla_put_failure;
+	}
 
 	nla = nla_reserve(skb, IFLA_INET6_TOKEN, sizeof(struct in6_addr));
 	if (!nla)

2.39.5

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

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

From: David Oberhollenzer <[email protected]>

[ Upstream commit a58d882841a0750da3c482cd3d82432b1c7edb77 ]

The mv88e6xxx has an internal PPU that polls PHY state. If we want to access the internal PHYs, we need to disable the PPU first. Because that is a slow operation, a 10ms timer is used to re-enable it, canceled with every access, so bulk operations effectively only disable it once and re-enable it some 10ms after the last access.

If a PHY is accessed and then the mv88e6xxx module is removed before the 10ms are up, the PPU re-enable ends up accessing a dangling pointer.

This especially affects probing during bootup. The MDIO bus and PHY registration may succeed, but registration with the DSA framework may fail later on (e.g. because the CPU port depends on another, very slow device that isn't done probing yet, returning -EPROBE_DEFER). In this case, probe() fails, but the MDIO subsystem may already have accessed the MIDO bus or PHYs, arming the timer.

This is fixed as follows:
- If probe fails after mv88e6xxx_phy_init(), make sure we also call mv88e6xxx_phy_destroy() before returning
- In mv88e6xxx_remove(), make sure we do the teardown in the correct order, calling mv88e6xxx_phy_destroy() after unregistering the switch device.
- In mv88e6xxx_phy_destroy(), destroy both the timer and the work item that the timer might schedule, synchronously waiting in case one of the callbacks already fired and destroying the timer first, before waiting for the work item.
- Access to the PPU is guarded by a mutex, the worker acquires it with a mutex_trylock(), not proceeding with the expensive shutdown if that fails. We grab the mutex in mv88e6xxx_phy_destroy() to make sure the slow PPU shutdown is already done or won't even enter, when we wait for the work item.

---
 drivers/net/dsa/mv88e6xxx/chip.c | 11 +++++++----
 drivers/net/dsa/mv88e6xxx/phy.c  |  3 +++
 2 files changed, 10 insertions(+), 4 deletions(-)

index c7f93329ae753..4cc60135589d1 100644
@@ -5578,13 +5578,13 @@ static int mv88e6xxx_probe(struct mdio_device *mdiodev)
 	err = mv88e6xxx_switch_reset(chip);
 	mv88e6xxx_reg_unlock(chip);
 	if (err)
-		goto out;
+		goto out_phy;
 
 	if (np) {
 		chip->irq = of_irq_get(np, 0);
 		if (chip->irq == -EPROBE_DEFER) {
 			err = chip->irq;
-			goto out;
+			goto out_phy;
 		}
 	}
 

@@ -5603,7 +5603,7 @@ static int mv88e6xxx_probe(struct mdio_device *mdiodev)
 	mv88e6xxx_reg_unlock(chip);
 
 	if (err)
-		goto out;
+		goto out_phy;
 
 	if (chip->info->g2_irqs > 0) {
 		err = mv88e6xxx_g2_irq_setup(chip);

@@ -5643,6 +5643,8 @@ static int mv88e6xxx_probe(struct mdio_device *mdiodev)
 		mv88e6xxx_g1_irq_free(chip);
 	else
 		mv88e6xxx_irq_poll_free(chip);
+out_phy:
+	mv88e6xxx_phy_destroy(chip);
 out:
 	if (pdata)
 		dev_put(pdata->netdev);

@@ -5660,7 +5662,6 @@ static void mv88e6xxx_remove(struct mdio_device *mdiodev)
 		mv88e6xxx_ptp_free(chip);
 	}
 
-	mv88e6xxx_phy_destroy(chip);
 	mv88e6xxx_unregister_switch(chip);
 	mv88e6xxx_mdios_unregister(chip);
 

@@ -5674,6 +5675,8 @@ static void mv88e6xxx_remove(struct mdio_device *mdiodev)
 		mv88e6xxx_g1_irq_free(chip);
 	else
 		mv88e6xxx_irq_poll_free(chip);
+
+	mv88e6xxx_phy_destroy(chip);
 }
 
 static const struct of_device_id mv88e6xxx_of_match[] = {

index 252b5b3a3efef..d2104bd346ea2 100644
@@ -197,7 +197,10 @@ static void mv88e6xxx_phy_ppu_state_init(struct mv88e6xxx_chip *chip)
 
 static void mv88e6xxx_phy_ppu_state_destroy(struct mv88e6xxx_chip *chip)
 {
+	mutex_lock(&chip->ppu_mutex);
 	del_timer_sync(&chip->ppu_timer);
+	cancel_work_sync(&chip->ppu_work);
+	mutex_unlock(&chip->ppu_mutex);
 }
 
 int mv88e6185_phy_ppu_read(struct mv88e6xxx_chip *chip, struct mii_bus *bus,

2.39.5

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

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

From: Lin Ma <[email protected]>

[ Upstream commit b27055a08ad4b415dcf15b63034f9cb236f7fb40 ]

struct geneve_opt uses 5 bit length for each single option, which means every vary size option should be smaller than 128 bytes.

However, all current related Netlink policies cannot promise this length condition and the attacker can exploit a exact 128-byte size option to *fake* a zero length option and confuse the parsing logic, further achieve heap out-of-bounds read.

One example crash log is like below:

[    3.905425] ==================================================================
[    3.905925] BUG: KASAN: slab-out-of-bounds in nla_put+0xa9/0xe0
[    3.906255] Read of size 124 at addr ffff888005f291cc by task poc/177
[    3.906646]
[    3.906775] CPU: 0 PID: 177 Comm: poc-oob-read Not tainted 6.1.132 #1
[    3.907131] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.0-0-gd239552ce722-prebuilt.qemu.org 04/01/2014
[    3.907784] Call Trace:
[    3.907925]  <TASK>
[    3.908048]  dump_stack_lvl+0x44/0x5c
[    3.908258]  print_report+0x184/0x4be
[    3.909151]  kasan_report+0xc5/0x100
[    3.909539]  kasan_check_range+0xf3/0x1a0
[    3.909794]  memcpy+0x1f/0x60
[    3.909968]  nla_put+0xa9/0xe0
[    3.910147]  tunnel_key_dump+0x945/0xba0
[    3.911536]  tcf_action_dump_1+0x1c1/0x340
[    3.912436]  tcf_action_dump+0x101/0x180
[    3.912689]  tcf_exts_dump+0x164/0x1e0
[    3.912905]  fw_dump+0x18b/0x2d0
[    3.913483]  tcf_fill_node+0x2ee/0x460
[    3.914778]  tfilter_notify+0xf4/0x180
[    3.915208]  tc_new_tfilter+0xd51/0x10d0
[    3.918615]  rtnetlink_rcv_msg+0x4a2/0x560
[    3.919118]  netlink_rcv_skb+0xcd/0x200
[    3.919787]  netlink_unicast+0x395/0x530
[    3.921032]  netlink_sendmsg+0x3d0/0x6d0
[    3.921987]  __sock_sendmsg+0x99/0xa0
[    3.922220]  __sys_sendto+0x1b7/0x240
[    3.922682]  __x64_sys_sendto+0x72/0x90
[    3.922906]  do_syscall_64+0x5e/0x90
[    3.923814]  entry_SYSCALL_64_after_hwframe+0x6e/0xd8
[    3.924122] RIP: 0033:0x7e83eab84407
[    3.924331] Code: 48 89 fa 4c 89 df e8 38 aa 00 00 8b 93 08 03 00 00 59 5e 48 83 f8 fc 74 1a 5b c3 0f 1f 84 00 00 00 00 00 48 8b 44 24 10 0f 05 <5b> c3 0f 1f 80 00 00 00 00 83 e2 39 83 faf
[    3.925330] RSP: 002b:00007ffff505e370 EFLAGS: 00000202 ORIG_RAX: 000000000000002c
[    3.925752] RAX: ffffffffffffffda RBX: 00007e83eaafa740 RCX: 00007e83eab84407
[    3.926173] RDX: 00000000000001a8 RSI: 00007ffff505e3c0 RDI: 0000000000000003
[    3.926587] RBP: 00007ffff505f460 R08: 00007e83eace1000 R09: 000000000000000c
[    3.926977] R10: 0000000000000000 R11: 0000000000000202 R12: 00007ffff505f3c0
[    3.927367] R13: 00007ffff505f5c8 R14: 00007e83ead1b000 R15: 00005d4fbbe6dcb8

Fix these issues by enforing correct length condition in related policies.

---
 net/ipv4/ip_tunnel_core.c  | 2 +-
 net/netfilter/nft_tunnel.c | 2 +-
 net/sched/act_tunnel_key.c | 2 +-
 net/sched/cls_flower.c     | 2 +-
 4 files changed, 4 insertions(+), 4 deletions(-)

index dad9d7db5bf6c..01d362b5b8826 100644
@@ -459,7 +459,7 @@ static const struct nla_policy
 geneve_opt_policy[LWTUNNEL_IP_OPT_GENEVE_MAX + 1] = {
 	[LWTUNNEL_IP_OPT_GENEVE_CLASS]	= { .type = NLA_U16 },
 	[LWTUNNEL_IP_OPT_GENEVE_TYPE]	= { .type = NLA_U8 },
-	[LWTUNNEL_IP_OPT_GENEVE_DATA]	= { .type = NLA_BINARY, .len = 128 },
+	[LWTUNNEL_IP_OPT_GENEVE_DATA]	= { .type = NLA_BINARY, .len = 127 },
 };
 
 static const struct nla_policy

index 1b05b70497283..cfe6cf1be4217 100644
@@ -305,7 +305,7 @@ static int nft_tunnel_obj_erspan_init(const struct nlattr *attr,
 static const struct nla_policy nft_tunnel_opts_geneve_policy[NFTA_TUNNEL_KEY_GENEVE_MAX + 1] = {
 	[NFTA_TUNNEL_KEY_GENEVE_CLASS]	= { .type = NLA_U16 },
 	[NFTA_TUNNEL_KEY_GENEVE_TYPE]	= { .type = NLA_U8 },
-	[NFTA_TUNNEL_KEY_GENEVE_DATA]	= { .type = NLA_BINARY, .len = 128 },
+	[NFTA_TUNNEL_KEY_GENEVE_DATA]	= { .type = NLA_BINARY, .len = 127 },
 };
 
 static int nft_tunnel_obj_geneve_init(const struct nlattr *attr,

index 85c0d0d5b9da5..0d90349636f0e 100644
@@ -67,7 +67,7 @@ geneve_opt_policy[TCA_TUNNEL_KEY_ENC_OPT_GENEVE_MAX + 1] = {
 	[TCA_TUNNEL_KEY_ENC_OPT_GENEVE_CLASS]	   = { .type = NLA_U16 },
 	[TCA_TUNNEL_KEY_ENC_OPT_GENEVE_TYPE]	   = { .type = NLA_U8 },
 	[TCA_TUNNEL_KEY_ENC_OPT_GENEVE_DATA]	   = { .type = NLA_BINARY,
-						       .len = 128 },
+						       .len = 127 },
 };
 
 static const struct nla_policy

index 98f333aa0aac9..9f6f8430d0378 100644
@@ -717,7 +717,7 @@ geneve_opt_policy[TCA_FLOWER_KEY_ENC_OPT_GENEVE_MAX + 1] = {
 	[TCA_FLOWER_KEY_ENC_OPT_GENEVE_CLASS]      = { .type = NLA_U16 },
 	[TCA_FLOWER_KEY_ENC_OPT_GENEVE_TYPE]       = { .type = NLA_U8 },
 	[TCA_FLOWER_KEY_ENC_OPT_GENEVE_DATA]       = { .type = NLA_BINARY,
-						       .len = 128 },
+						       .len = 127 },
 };
 
 static const struct nla_policy

2.39.5

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

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

From: Henry Martin <[email protected]>

[ Upstream commit fda8c491db2a90ff3e6fbbae58e495b4ddddeca3 ]

devm_kasprintf() returns NULL when memory allocation fails. Currently, com20020pci_probe() does not check for this case, which results in a NULL pointer dereference.

Add NULL check after devm_kasprintf() to prevent this issue and ensure no resources are left allocated.

---
 drivers/net/arcnet/com20020-pci.c | 17 ++++++++++++++++-
 1 file changed, 16 insertions(+), 1 deletion(-)

index 9d9e4200064f9..00a80f0adece4 100644
@@ -250,18 +250,33 @@ static int com20020pci_probe(struct pci_dev *pdev,
 			card->tx_led.default_trigger = devm_kasprintf(&pdev->dev,
 							GFP_KERNEL, "arc%d-%d-tx",
 							dev->dev_id, i);
+			if (!card->tx_led.default_trigger) {
+				ret = -ENOMEM;
+				goto err_free_arcdev;
+			}
 			card->tx_led.name = devm_kasprintf(&pdev->dev, GFP_KERNEL,
 							"pci:green:tx:%d-%d",
 							dev->dev_id, i);
-
+			if (!card->tx_led.name) {
+				ret = -ENOMEM;
+				goto err_free_arcdev;
+			}
 			card->tx_led.dev = &dev->dev;
 			card->recon_led.brightness_set = led_recon_set;
 			card->recon_led.default_trigger = devm_kasprintf(&pdev->dev,
 							GFP_KERNEL, "arc%d-%d-recon",
 							dev->dev_id, i);
+			if (!card->recon_led.default_trigger) {
+				ret = -ENOMEM;
+				goto err_free_arcdev;
+			}
 			card->recon_led.name = devm_kasprintf(&pdev->dev, GFP_KERNEL,
 							"pci:red:recon:%d-%d",
 							dev->dev_id, i);
+			if (!card->recon_led.name) {
+				ret = -ENOMEM;
+				goto err_free_arcdev;
+			}
 			card->recon_led.dev = &dev->dev;
 
 			ret = devm_led_classdev_register(&pdev->dev, &card->tx_led);

2.39.5

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

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

From: Haibo Chen <[email protected]>

[ Upstream commit fd99d6ed20234b83d65b9c5417794343577cf3e5 ]

After a suspend/resume cycle on a down interface, it will come up as ERROR-ACTIVE.

$ ip -details -s -s a s dev flexcan0
3: flexcan0: <NOARP,ECHO> mtu 16 qdisc pfifo_fast state DOWN group default qlen 10
    link/can  promiscuity 0 allmulti 0 minmtu 0 maxmtu 0
    can state STOPPED (berr-counter tx 0 rx 0) restart-ms 1000

$ sudo systemctl suspend

$ ip -details -s -s a s dev flexcan0
3: flexcan0: <NOARP,ECHO> mtu 16 qdisc pfifo_fast state DOWN group default qlen 10
    link/can  promiscuity 0 allmulti 0 minmtu 0 maxmtu 0
    can state ERROR-ACTIVE (berr-counter tx 0 rx 0) restart-ms 1000

And only set CAN state to CAN_STATE_ERROR_ACTIVE when resume process has no issue, otherwise keep in CAN_STATE_SLEEPING as suspend did.

---
 drivers/net/can/flexcan.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

index 429950241de32..586c13d855e09 100644
@@ -2113,8 +2113,9 @@ static int __maybe_unused flexcan_suspend(struct device *device)
 		}
 		netif_stop_queue(dev);
 		netif_device_detach(dev);
+
+		priv->can.state = CAN_STATE_SLEEPING;
 	}
-	priv->can.state = CAN_STATE_SLEEPING;
 
 	return 0;
 }

@@ -2125,7 +2126,6 @@ static int __maybe_unused flexcan_resume(struct device *device)
 	struct flexcan_priv *priv = netdev_priv(dev);
 	int err;
 
-	priv->can.state = CAN_STATE_ERROR_ACTIVE;
 	if (netif_running(dev)) {
 		netif_device_attach(dev);
 		netif_start_queue(dev);

@@ -2143,6 +2143,8 @@ static int __maybe_unused flexcan_resume(struct device *device)
 			if (err)
 				return err;
 		}
+
+		priv->can.state = CAN_STATE_ERROR_ACTIVE;
 	}
 
 	return 0;

2.39.5

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

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

From: Sherry Sun <[email protected]>

[ Upstream commit d57d56e4dddfb5c92cd81abf8922055bf0fb85a4 ]

For lpuart32 platforms, UARTMODIR register is used instead of UARTMODEM. So here should configure the corresponding UARTMODIR register bits to avoid confusion.

Stable-dep-of: f5cb528d6441 ("tty: serial: fsl_lpuart: disable transmitter before changing RS485 related registers")

---
 drivers/tty/serial/fsl_lpuart.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

index b16ad6db1ef8e..5135cdc0b6644 100644
@@ -1351,7 +1351,7 @@ static int lpuart32_config_rs485(struct uart_port *port,
 			struct lpuart_port, port);
 
 	unsigned long modem = lpuart32_read(&sport->port, UARTMODIR)
-				& ~(UARTMODEM_TXRTSPOL | UARTMODEM_TXRTSE);
+				& ~(UARTMODIR_TXRTSPOL | UARTMODIR_TXRTSE);
 	lpuart32_write(&sport->port, modem, UARTMODIR);
 
 	/* clear unsupported configurations */

@@ -1361,7 +1361,7 @@ static int lpuart32_config_rs485(struct uart_port *port,
 
 	if (rs485->flags & SER_RS485_ENABLED) {
 		/* Enable auto RS-485 RTS mode */
-		modem |= UARTMODEM_TXRTSE;
+		modem |= UARTMODIR_TXRTSE;
 
 		/*
 		 * RTS needs to be logic HIGH either during transfer _or_ after

@@ -1383,9 +1383,9 @@ static int lpuart32_config_rs485(struct uart_port *port,
 		 * Note: UART is assumed to be active high.
 		 */
 		if (rs485->flags & SER_RS485_RTS_ON_SEND)
-			modem |= UARTMODEM_TXRTSPOL;
+			modem |= UARTMODIR_TXRTSPOL;
 		else if (rs485->flags & SER_RS485_RTS_AFTER_SEND)
-			modem &= ~UARTMODEM_TXRTSPOL;
+			modem &= ~UARTMODIR_TXRTSPOL;
 	}
 
 	/* Store the new configuration */

2.39.5

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

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

From: Sherry Sun <[email protected]>

[ Upstream commit f5cb528d6441eb860250a2f085773aac4f44085e ]

According to the LPUART reference manual, TXRTSE and TXRTSPOL of MODIR register only can be changed when the transmitter is disabled. So disable the transmitter before changing RS485 related registers and re-enable it after the change is done.

---
 drivers/tty/serial/fsl_lpuart.c | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)

index 5135cdc0b6644..110d98fed7260 100644
@@ -1352,6 +1352,19 @@ static int lpuart32_config_rs485(struct uart_port *port,
 
 	unsigned long modem = lpuart32_read(&sport->port, UARTMODIR)
 				& ~(UARTMODIR_TXRTSPOL | UARTMODIR_TXRTSE);
+	u32 ctrl;
+
+	/* TXRTSE and TXRTSPOL only can be changed when transmitter is disabled. */
+	ctrl = lpuart32_read(&sport->port, UARTCTRL);
+	if (ctrl & UARTCTRL_TE) {
+		/* wait for the transmit engine to complete */
+		lpuart32_wait_bit_set(&sport->port, UARTSTAT, UARTSTAT_TC);
+		lpuart32_write(&sport->port, ctrl & ~UARTCTRL_TE, UARTCTRL);
+
+		while (lpuart32_read(&sport->port, UARTCTRL) & UARTCTRL_TE)
+			cpu_relax();
+	}
+
 	lpuart32_write(&sport->port, modem, UARTMODIR);
 
 	/* clear unsupported configurations */

@@ -1392,6 +1405,10 @@ static int lpuart32_config_rs485(struct uart_port *port,
 	sport->port.rs485 = *rs485;
 
 	lpuart32_write(&sport->port, modem, UARTMODIR);
+
+	if (ctrl & UARTCTRL_TE)
+		lpuart32_write(&sport->port, ctrl, UARTCTRL);
+
 	return 0;
 }
 

2.39.5

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

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

From: Jesse Zhang <[email protected]>

commit c8c19ebf7c0b202a6a2d37a52ca112432723db5f upstream.

Avoid using the negative values
for clk_idex as an index into an array pptable->DpmDescriptor.

V2: fix clk_index return check (Tim Huang)

---
 drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c |   21 ++++++++++++++++-----
 1 file changed, 16 insertions(+), 5 deletions(-)

@@ -900,19 +900,22 @@ static int navi10_get_current_clk_freq_b
 					   value);
 }
 
-static bool navi10_is_support_fine_grained_dpm(struct smu_context *smu, enum smu_clk_type clk_type)
+static int navi10_is_support_fine_grained_dpm(struct smu_context *smu, enum smu_clk_type clk_type)
 {
 	PPTable_t *pptable = smu->smu_table.driver_pptable;
 	DpmDescriptor_t *dpm_desc = NULL;
-	uint32_t clk_index = 0;
+	int clk_index = 0;
 
 	clk_index = smu_cmn_to_asic_specific_index(smu,
 						   CMN2ASIC_MAPPING_CLK,
 						   clk_type);
+	if (clk_index < 0)
+		return clk_index;
+
 	dpm_desc = &pptable->DpmDescriptor[clk_index];
 
 	/* 0 - Fine grained DPM, 1 - Discrete DPM */
-	return dpm_desc->SnapToDiscrete == 0 ? true : false;
+	return dpm_desc->SnapToDiscrete == 0 ? 1 : 0;
 }
 
 static inline bool navi10_od_feature_is_supported(struct smu_11_0_overdrive_table *od_table, enum SMU_11_0_ODFEATURE_CAP cap)

@@ -964,7 +967,11 @@ static int navi10_print_clk_levels(struc
 		if (ret)
 			return size;
 
-		if (!navi10_is_support_fine_grained_dpm(smu, clk_type)) {
+		ret = navi10_is_support_fine_grained_dpm(smu, clk_type);
+		if (ret < 0)
+			return ret;
+
+		if (!ret) {
 			for (i = 0; i < count; i++) {
 				ret = smu_v11_0_get_dpm_freq_by_index(smu, clk_type, i, &value);
 				if (ret)

@@ -1127,7 +1134,11 @@ static int navi10_force_clk_levels(struc
 	case SMU_UCLK:
 	case SMU_FCLK:
 		/* There is only 2 levels for fine grained DPM */
-		if (navi10_is_support_fine_grained_dpm(smu, clk_type)) {
+		ret = navi10_is_support_fine_grained_dpm(smu, clk_type);
+		if (ret < 0)
+			return ret;
+
+		if (ret) {
 			soft_max_level = (soft_max_level >= 1 ? 1 : 0);
 			soft_min_level = (soft_min_level >= 1 ? 1 : 0);
 		}

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

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

From: Hersen Wu <[email protected]>

commit a54f7e866cc73a4cb71b8b24bb568ba35c8969df upstream.

[Why]
Coverity reports Memory - illegal accesses.

[How]
Skip inactive planes.