5.10.169-rc1 review

From: Pierre-Louis Bossart <[email protected]>

[ Upstream commit 324f065cdbaba1b879a63bf07e61ca156b789537 ]

The amplifier may provide hardware support for I/V feedback, or alternatively the firmware may generate an echo reference attached to the SSP and dailink used for the amplifier.

To avoid any issues with invalid/NULL substreams in the latter case, always unconditionally set dpcm_capture.

---
 sound/soc/intel/boards/sof_rt5682.c | 3 +++
 1 file changed, 3 insertions(+)

index 1f94fa5a15db6..5883d1fa3b7ed 100644
@@ -704,6 +704,9 @@ static struct snd_soc_dai_link *sof_card_dai_links_create(struct device *dev,
 		links[id].num_platforms = ARRAY_SIZE(platform_component);
 		links[id].nonatomic = true;
 		links[id].dpcm_playback = 1;
+		/* feedback stream or firmware-generated echo reference */
+		links[id].dpcm_capture = 1;
+
 		links[id].no_pcm = 1;
 		links[id].cpus = &cpus[id];
 		links[id].num_cpus = 1;

2.39.0

From: Amit Engel <[email protected]>

[ Upstream commit 0cab4404874f2de52617de8400c844891c6ea1ce ]

As part of nvmet_fc_ls_create_association there is a case where nvmet_fc_alloc_target_queue fails right after a new association with an admin queue is created. In this case, no one releases the get taken in nvmet_fc_alloc_target_assoc. This fix is adding the missing put.

---
 drivers/nvme/target/fc.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

index 640031cbda7cc..46fc44ce86712 100644
@@ -1675,8 +1675,10 @@ nvmet_fc_ls_create_association(struct nvmet_fc_tgtport *tgtport,
 		else {
 			queue = nvmet_fc_alloc_target_queue(iod->assoc, 0,
 					be16_to_cpu(rqst->assoc_cmd.sqsize));
-			if (!queue)
+			if (!queue) {
 				ret = VERR_QUEUE_ALLOC_FAIL;
+				nvmet_fc_tgt_a_put(iod->assoc);
+			}
 		}
 	}
 

2.39.0

From: Hans de Goede <[email protected]>

[ Upstream commit eecf2acd4a580e9364e5087daf0effca60a240b7 ]

Add a DMI match for the CWI501 version of the Chuwi Vi8 tablet, pointing to the same chuwi_vi8_data as the existing CWI506 version DMI match.

---
 drivers/platform/x86/touchscreen_dmi.c | 9 +++++++++
 1 file changed, 9 insertions(+)

index bc26acace2c30..b96fbc8dba09d 100644
@@ -1030,6 +1030,15 @@ const struct dmi_system_id touchscreen_dmi_table[] = {
 			DMI_MATCH(DMI_BIOS_DATE, "05/07/2016"),
 		},
 	},
+	{
+		/* Chuwi Vi8 (CWI501) */
+		.driver_data = (void *)&chuwi_vi8_data,
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Insyde"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "i86"),
+			DMI_MATCH(DMI_BIOS_VERSION, "CHUWI.W86JLBNR01"),
+		},
+	},
 	{
 		/* Chuwi Vi8 (CWI506) */
 		.driver_data = (void *)&chuwi_vi8_data,

2.39.0

From: Gaosheng Cui <[email protected]>

[ Upstream commit 5544e90c81261e82e02bbf7c6015a4b9c8c825ef ]

The type of return value of dev_set_name is int, which may return wrong result, so we add error handling for it to reclaim memory of nvmem resource, and return early when an error occurs.

Stable-dep-of: ab3428cfd9aa ("nvmem: core: fix registration vs use race")

---
 drivers/nvmem/core.c | 12 +++++++++---
 1 file changed, 9 insertions(+), 3 deletions(-)

index 48fbe49e3772b..9da4edbabfe75 100644
@@ -661,18 +661,24 @@ struct nvmem_device *nvmem_register(const struct nvmem_config *config)
 
 	switch (config->id) {
 	case NVMEM_DEVID_NONE:
-		dev_set_name(&nvmem->dev, "%s", config->name);
+		rval = dev_set_name(&nvmem->dev, "%s", config->name);
 		break;
 	case NVMEM_DEVID_AUTO:
-		dev_set_name(&nvmem->dev, "%s%d", config->name, nvmem->id);
+		rval = dev_set_name(&nvmem->dev, "%s%d", config->name, nvmem->id);
 		break;
 	default:
-		dev_set_name(&nvmem->dev, "%s%d",
+		rval = dev_set_name(&nvmem->dev, "%s%d",
 			     config->name ? : "nvmem",
 			     config->name ? config->id : nvmem->id);
 		break;
 	}
 
+	if (rval) {
+		ida_free(&nvmem_ida, nvmem->id);
+		kfree(nvmem);
+		return ERR_PTR(rval);
+	}
+
 	nvmem->read_only = device_property_present(config->dev, "read-only") ||
 			   config->read_only || !nvmem->reg_write;
 

2.39.0

From: Russell King (Oracle) <[email protected]>

[ Upstream commit 569653f022a29a1a44ea9de5308b657228303fa5 ]

No one provides wp_gpio, so let's remove it to avoid issues with the nvmem core putting this gpio.

Stable-dep-of: ab3428cfd9aa ("nvmem: core: fix registration vs use race")

---
 drivers/nvmem/core.c           | 4 +---
 include/linux/nvmem-provider.h | 2 --
 2 files changed, 1 insertion(+), 5 deletions(-)

index 9da4edbabfe75..38c05fce7d740 100644
@@ -627,9 +627,7 @@ struct nvmem_device *nvmem_register(const struct nvmem_config *config)
 
 	nvmem->id = rval;
 
-	if (config->wp_gpio)
-		nvmem->wp_gpio = config->wp_gpio;
-	else if (!config->ignore_wp)
+	if (!config->ignore_wp)
 		nvmem->wp_gpio = gpiod_get_optional(config->dev, "wp",
 						    GPIOD_OUT_HIGH);
 	if (IS_ERR(nvmem->wp_gpio)) {

index 39ec67689898b..5e07f3cfad301 100644
@@ -49,7 +49,6 @@ enum nvmem_type {
  * @word_size:	Minimum read/write access granularity.
  * @stride:	Minimum read/write access stride.
  * @priv:	User context passed to read/write callbacks.
- * @wp-gpio:	Write protect pin
  * @ignore_wp:  Write Protect pin is managed by the provider.
  *
  * Note: A default "nvmem<id>" name will be assigned to the device if

@@ -64,7 +63,6 @@ struct nvmem_config {
 	const char		*name;
 	int			id;
 	struct module		*owner;
-	struct gpio_desc	*wp_gpio;
 	const struct nvmem_cell_info	*cells;
 	int			ncells;
 	enum nvmem_type		type;

2.39.0

From: Eduard Zingerman <[email protected]>

[ Upstream commit b9fa9bc839291020b362ab5392e5f18ba79657ac ]

A testcase to check that verifier.c:copy_register_state() preserves register parentage chain and livness information.

---
 .../selftests/bpf/verifier/search_pruning.c   | 36 +++++++++++++++++++
 1 file changed, 36 insertions(+)

index 7e50cb80873a5..7e36078f8f482 100644
@@ -154,3 +154,39 @@
 	.result_unpriv = ACCEPT,
 	.insn_processed = 15,
 },
+/* The test performs a conditional 64-bit write to a stack location
+ * fp[-8], this is followed by an unconditional 8-bit write to fp[-8],
+ * then data is read from fp[-8]. This sequence is unsafe.
+ *
+ * The test would be mistakenly marked as safe w/o dst register parent
+ * preservation in verifier.c:copy_register_state() function.
+ *
+ * Note the usage of BPF_F_TEST_STATE_FREQ to force creation of the
+ * checkpoint state after conditional 64-bit assignment.
+ */
+{
+	"write tracking and register parent chain bug",
+	.insns = {
+	/* r6 = ktime_get_ns() */
+	BPF_EMIT_CALL(BPF_FUNC_ktime_get_ns),
+	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
+	/* r0 = ktime_get_ns() */
+	BPF_EMIT_CALL(BPF_FUNC_ktime_get_ns),
+	/* if r0 > r6 goto +1 */
+	BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_6, 1),
+	/* *(u64 *)(r10 - 8) = 0xdeadbeef */
+	BPF_ST_MEM(BPF_DW, BPF_REG_FP, -8, 0xdeadbeef),
+	/* r1 = 42 */
+	BPF_MOV64_IMM(BPF_REG_1, 42),
+	/* *(u8 *)(r10 - 8) = r1 */
+	BPF_STX_MEM(BPF_B, BPF_REG_FP, BPF_REG_1, -8),
+	/* r2 = *(u64 *)(r10 - 8) */
+	BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_FP, -8),
+	/* exit(0) */
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.flags = BPF_F_TEST_STATE_FREQ,
+	.errstr = "invalid read from stack off -8+1 size 8",
+	.result = REJECT,
+},

2.39.0

From: Cezary Rojewski <[email protected]>

[ Upstream commit 87978e6ad45a16835cc58234451111091be3c59a ]

Several functions that take part in codec's initialization and removal are re-used by ASoC codec drivers implementations. Drivers mimic the behavior of hda_codec_driver_probe/remove() found in sound/pci/hda/hda_bind.c with their component->probe/remove() instead.

One of the reasons for that is the expectation of snd_hda_codec_device_new() to receive a valid pointer to an instance of struct snd_card. This expectation can be met only once sound card components probing commences.

As ASoC sound card may be unbound without codec device being actually removed from the system, unsetting ->preset in snd_hda_codec_cleanup_for_unbind() interferes with module unload -> load scenario causing null-ptr-deref. Preset is assigned only once, during device/driver matching whereas ASoC codec driver's module reloading may occur several times throughout the lifetime of an audio stack.

---
 sound/pci/hda/hda_bind.c  | 2 ++
 sound/pci/hda/hda_codec.c | 1 -
 2 files changed, 2 insertions(+), 1 deletion(-)

index 4efbcc41fdfb7..0a83afa5f373c 100644
@@ -143,6 +143,7 @@ static int hda_codec_driver_probe(struct device *dev)
 
  error:
 	snd_hda_codec_cleanup_for_unbind(codec);
+	codec->preset = NULL;
 	return err;
 }
 

@@ -159,6 +160,7 @@ static int hda_codec_driver_remove(struct device *dev)
 	if (codec->patch_ops.free)
 		codec->patch_ops.free(codec);
 	snd_hda_codec_cleanup_for_unbind(codec);
+	codec->preset = NULL;
 	module_put(dev->driver->owner);
 	return 0;
 }

index 39281106477eb..fc4a64a83ff2f 100644
@@ -784,7 +784,6 @@ void snd_hda_codec_cleanup_for_unbind(struct hda_codec *codec)
 	snd_array_free(&codec->cvt_setups);
 	snd_array_free(&codec->spdif_out);
 	snd_array_free(&codec->verbs);
-	codec->preset = NULL;
 	codec->follower_dig_outs = NULL;
 	codec->spdif_status_reset = 0;
 	snd_array_free(&codec->mixers);

2.39.0

From: Arnd Bergmann <[email protected]>

[ Upstream commit e18c6da62edc780e4f4f3c9ce07bdacd69505182 ]

While looking through legacy platform data users, I noticed that the DT probing never uses data from the DT properties, as the platform_data structure gets overwritten directly after it is initialized.

There have never been any boards defining the platform_data in the mainline kernel either, so this driver so far only worked with patched kernels or with the default values.

For the benefit of possible downstream users, fix the DT probe by no longer overwriting the data.

---
 sound/soc/codecs/cs42l56.c | 6 ------
 1 file changed, 6 deletions(-)

index d41e031931061..3c5ec47a8fe64 100644
@@ -1193,18 +1193,12 @@ static int cs42l56_i2c_probe(struct i2c_client *i2c_client,
 	if (pdata) {
 		cs42l56->pdata = *pdata;
 	} else {
-		pdata = devm_kzalloc(&i2c_client->dev, sizeof(*pdata),
-				     GFP_KERNEL);
-		if (!pdata)
-			return -ENOMEM;
-
 		if (i2c_client->dev.of_node) {
 			ret = cs42l56_handle_of_data(i2c_client,
 						     &cs42l56->pdata);
 			if (ret != 0)
 				return ret;
 		}
-		cs42l56->pdata = *pdata;
 	}
 
 	if (cs42l56->pdata.gpio_nreset) {

2.39.0

From: Shunsuke Mie <[email protected]>

[ Upstream commit 3f7b75abf41cc4143aa295f62acbb060a012868d ]

Fix the build caused by missing kmsan_handle_dma() and is_power_of_2() that are used in drivers/virtio/virtio_ring.c.

Message-Id: <[email protected]>

---
 tools/virtio/linux/bug.h         |  8 +++-----
 tools/virtio/linux/build_bug.h   |  7 +++++++
 tools/virtio/linux/cpumask.h     |  7 +++++++
 tools/virtio/linux/gfp.h         |  7 +++++++
 tools/virtio/linux/kernel.h      |  1 +
 tools/virtio/linux/kmsan.h       | 12 ++++++++++++
 tools/virtio/linux/scatterlist.h |  1 +
 tools/virtio/linux/topology.h    |  7 +++++++
 8 files changed, 45 insertions(+), 5 deletions(-)
 create mode 100644 tools/virtio/linux/build_bug.h
 create mode 100644 tools/virtio/linux/cpumask.h
 create mode 100644 tools/virtio/linux/gfp.h
 create mode 100644 tools/virtio/linux/kmsan.h
 create mode 100644 tools/virtio/linux/topology.h

index b14c2c3b6b857..74aef964f5099 100644
@@ -1,11 +1,9 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-#ifndef BUG_H
-#define BUG_H
+#ifndef _LINUX_BUG_H
+#define _LINUX_BUG_H
 
 #define BUG_ON(__BUG_ON_cond) assert(!(__BUG_ON_cond))
 
-#define BUILD_BUG_ON(x)
-
 #define BUG() abort()
 
-#endif /* BUG_H */
+#endif /* _LINUX_BUG_H */

new file mode 100644
index 0000000000000..cdbb75e28a604
@@ -0,0 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_BUILD_BUG_H
+#define _LINUX_BUILD_BUG_H
+
+#define BUILD_BUG_ON(x)
+
+#endif	/* _LINUX_BUILD_BUG_H */

new file mode 100644
index 0000000000000..307da69d6b26c
@@ -0,0 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_CPUMASK_H
+#define _LINUX_CPUMASK_H
+
+#include <linux/kernel.h>
+
+#endif /* _LINUX_CPUMASK_H */

new file mode 100644
index 0000000000000..43d146f236f14
@@ -0,0 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __LINUX_GFP_H
+#define __LINUX_GFP_H
+
+#include <linux/topology.h>
+
+#endif

index 315e85cabedab..063ccc8975647 100644
@@ -10,6 +10,7 @@
 #include <stdarg.h>
 
 #include <linux/compiler.h>
+#include <linux/log2.h>
 #include <linux/types.h>
 #include <linux/list.h>
 #include <linux/printk.h>

new file mode 100644
index 0000000000000..272b5aa285d5a
@@ -0,0 +1,12 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_KMSAN_H
+#define _LINUX_KMSAN_H
+
+#include <linux/gfp.h>
+
+inline void kmsan_handle_dma(struct page *page, size_t offset, size_t size,
+			     enum dma_data_direction dir)
+{
+}
+
+#endif /* _LINUX_KMSAN_H */

index 369ee308b6686..74d9e1825748e 100644
@@ -2,6 +2,7 @@
 #ifndef SCATTERLIST_H
 #define SCATTERLIST_H
 #include <linux/kernel.h>
+#include <linux/bug.h>
 
 struct scatterlist {
 	unsigned long	page_link;

new file mode 100644
index 0000000000000..910794afb993a
@@ -0,0 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_TOPOLOGY_H
+#define _LINUX_TOPOLOGY_H
+
+#include <linux/cpumask.h>
+
+#endif /* _LINUX_TOPOLOGY_H */

2.39.0

From: Hyunwoo Kim <[email protected]>

[ Upstream commit 14caefcf9837a2be765a566005ad82cd0d2a429f ]

If you call listen() and accept() on an already connect()ed rose socket, accept() can successfully connect. This is because when the peer socket sends data to sendmsg, the skb with its own sk stored in the connected socket's sk->sk_receive_queue is connected, and rose_accept() dequeues the skb waiting in the sk->sk_receive_queue.

This creates a child socket with the sk of the parent rose socket, which can cause confusion.

Fix rose_listen() to return -EINVAL if the socket has already been successfully connected, and add lock_sock to prevent this issue.

---
 net/rose/af_rose.c | 8 ++++++++
 1 file changed, 8 insertions(+)

index 29a208ed8fb88..86c93cf1744b0 100644
@@ -487,6 +487,12 @@ static int rose_listen(struct socket *sock, int backlog)
 {
 	struct sock *sk = sock->sk;
 
+	lock_sock(sk);
+	if (sock->state != SS_UNCONNECTED) {
+		release_sock(sk);
+		return -EINVAL;
+	}
+
 	if (sk->sk_state != TCP_LISTEN) {
 		struct rose_sock *rose = rose_sk(sk);
 

@@ -496,8 +502,10 @@ static int rose_listen(struct socket *sock, int backlog)
 		memset(rose->dest_digis, 0, AX25_ADDR_LEN * ROSE_MAX_DIGIS);
 		sk->sk_max_ack_backlog = backlog;
 		sk->sk_state           = TCP_LISTEN;
+		release_sock(sk);
 		return 0;
 	}
+	release_sock(sk);
 
 	return -EOPNOTSUPP;
 }

2.39.0

From: Andrey Konovalov <[email protected]>

[ Upstream commit 54aa39a513dbf2164ca462a19f04519b2407a224 ]

Currently in phy_init_eee() the driver unconditionally configures the PHY to stop RX_CLK after entering Rx LPI state. This causes an LPI interrupt storm on my qcs404-base board.

Change the PHY initialization so that for "qcom,qcs404-ethqos" compatible device RX_CLK continues to run even in Rx LPI state.

---
 drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c | 2 ++
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c       | 3 ++-
 include/linux/stmmac.h                                  | 1 +
 3 files changed, 5 insertions(+), 1 deletion(-)

index bfc4a92f1d92b..78be62ecc9a9a 100644
@@ -505,6 +505,8 @@ static int qcom_ethqos_probe(struct platform_device *pdev)
 	plat_dat->has_gmac4 = 1;
 	plat_dat->pmt = 1;
 	plat_dat->tso_en = of_property_read_bool(np, "snps,tso");
+	if (of_device_is_compatible(np, "qcom,qcs404-ethqos"))
+		plat_dat->rx_clk_runs_in_lpi = 1;
 
 	ret = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res);
 	if (ret)

index b52ca2fe04d87..1ec000d4c7705 100644
@@ -1058,7 +1058,8 @@ static void stmmac_mac_link_up(struct phylink_config *config,
 
 	stmmac_mac_set(priv, priv->ioaddr, true);
 	if (phy && priv->dma_cap.eee) {
-		priv->eee_active = phy_init_eee(phy, 1) >= 0;
+		priv->eee_active =
+			phy_init_eee(phy, !priv->plat->rx_clk_runs_in_lpi) >= 0;
 		priv->eee_enabled = stmmac_eee_init(priv);
 		priv->tx_lpi_enabled = priv->eee_enabled;
 		stmmac_set_eee_pls(priv, priv->hw, true);

index 40df88728a6f4..abf7b8ec1fb64 100644
@@ -199,6 +199,7 @@ struct plat_stmmacenet_data {
 	int rss_en;
 	int mac_port_sel_speed;
 	bool en_tx_lpi_clockgating;
+	bool rx_clk_runs_in_lpi;
 	int has_xgmac;
 	bool vlan_fail_q_en;
 	u8 vlan_fail_q;

2.39.0

From: Kees Cook <[email protected]>

[ Upstream commit de5ca4c3852f896cacac2bf259597aab5e17d9e3 ]

Nothing was explicitly bounds checking the priority index used to access clpriop[]. WARN and bail out early if it's pathological. Seen with GCC 13:

../net/sched/sch_htb.c: In function 'htb_activate_prios':
../net/sched/sch_htb.c:437:44: warning: array subscript [0, 31] is outside array bounds of 'struct htb_prio[8]' [-Warray-bounds=]
437 | if (p->inner.clprio[prio].feed.rb_node)

      |                             ~~~~~~~~~~~~~~~^~~~~~

../net/sched/sch_htb.c:131:41: note: while referencing 'clprio'
131 | struct htb_prio clprio[TC_HTB_NUMPRIO];
| ^~~~~~

---
 net/sched/sch_htb.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

index c3ba018fd083e..c3e773d2ca419 100644
@@ -405,7 +405,10 @@ static void htb_activate_prios(struct htb_sched *q, struct htb_class *cl)
 	while (cl->cmode == HTB_MAY_BORROW && p && mask) {
 		m = mask;
 		while (m) {
-			int prio = ffz(~m);
+			unsigned int prio = ffz(~m);
+
+			if (WARN_ON_ONCE(prio > ARRAY_SIZE(p->inner.clprio)))
+				break;
 			m &= ~(1 << prio);
 
 			if (p->inner.clprio[prio].feed.rb_node)

2.39.0

From: Vasily Gorbik <[email protected]>

[ Upstream commit 7ab41c2c08a32132ba8c14624910e2fe8ce4ba4b ]

Historically calls to __decompress() didn't specify "out_len" parameter on many architectures including s390, expecting that no writes beyond uncompressed kernel image are performed. This has changed since commit 2aa14b1ab2c4 ("zstd: import usptream v1.5.2") which includes zstd library commit 6a7ede3dfccb ("Reduce size of dctx by reutilizing dst buffer (#2751)"). Now zstd decompression code might store literal buffer in the unwritten portion of the destination buffer. Since "out_len" is not set, it is considered to be unlimited and hence free to use for optimization needs. On s390 this might corrupt initrd or ipl report which are often placed right after the decompressor buffer. Luckily the size of uncompressed kernel image is already known to the decompressor, so to avoid the problem simply specify it in the "out_len" parameter.

---
 arch/s390/boot/compressed/decompressor.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index 3061b11c4d27f..8eaa1712a1c8d 100644
@@ -79,6 +79,6 @@ void *decompress_kernel(void)
 	void *output = (void *)decompress_offset;
 
 	__decompress(_compressed_start, _compressed_end - _compressed_start,
-		     NULL, NULL, output, 0, NULL, error);
+		     NULL, NULL, output, vmlinux.image_size, NULL, error);
 	return output;
 }

2.39.0

This is the start of the stable review cycle for the 5.10.169 release. There are 57 patches in this series, all will be posted as a response to this one. If anyone has any issues with these being applied, please let me know.

Responses should be made by Wed, 22 Feb 2023 13:35:35 +0000. Anything received after that time might be too late.

The whole patch series can be found in one patch at:

	https://www.kernel.org/pub/linux/kernel/v5.x/stable-review/patch-5.10.169-rc1.gz

or in the git tree and branch at:
git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git linux-5.10.y
and the diffstat can be found below.

thanks,

greg k-h

-------------
Pseudo-Shortlog of commits:

Greg Kroah-Hartman <[email protected]>

    Linux 5.10.169-rc1

Russell King (Oracle) <[email protected]>
nvmem: core: fix return value

Dan Carpenter <[email protected]>
net: sched: sch: Fix off by one in htb_activate_prios()

Pierre-Louis Bossart <[email protected]>
ASoC: SOF: Intel: hda-dai: fix possible stream_tag leak

Thomas Gleixner <[email protected]>
alarmtimer: Prevent starvation by small intervals and SIG_IGN

Greg Kroah-Hartman <[email protected]>
kvm: initialize all of the kvm_debugregs structure before sending it to userspace

Pedro Tammela <[email protected]>
net/sched: tcindex: search key must be 16 bits

Natalia Petrova <[email protected]>
i40e: Add checking for null for nlmsg_find_attr()

Pedro Tammela <[email protected]>
net/sched: act_ctinfo: use percpu stats

Baowen Zheng <[email protected]>
flow_offload: fill flags to action structure

Matt Roper <[email protected]>

    drm/i915/gen11: Wa_1408615072/Wa_1407596294 should be on GT list

Raviteja Goud Talla <[email protected]>
drm/i915/gen11: Moving WAs to icl_gt_workarounds_init()

Ryusuke Konishi <[email protected]>
nilfs2: fix underflow in second superblock position calculations

Guillaume Nault <[email protected]>
ipv6: Fix tcp socket connection with DSCP.

Guillaume Nault <[email protected]>
ipv6: Fix datagram socket connection with DSCP.

Jason Xing <[email protected]>
ixgbe: add double of VLAN header when computing the max MTU

Jakub Kicinski <[email protected]>
net: mpls: fix stale pointer if allocation fails during device rename

Cristian Ciocaltea <[email protected]>
net: stmmac: Restrict warning on disabling DMA store and fwd mode

Michael Chan <[email protected]>
bnxt_en: Fix mqprio and XDP ring checking logic

Johannes Zink <[email protected]>
net: stmmac: fix order of dwmac5 FlexPPS parametrization sequence

Hangyu Hua <[email protected]>
net: openvswitch: fix possible memory leak in ovs_meter_cmd_set()

Miko Larsson <[email protected]>
net/usb: kalmia: Don't pass act_len in usb_bulk_msg error path

Kuniyuki Iwashima <[email protected]>
dccp/tcp: Avoid negative sk_forward_alloc by ipv6_pinfo.pktoptions.

Pedro Tammela <[email protected]>
net/sched: tcindex: update imperfect hash filters respecting rcu

Pietro Borrello <[email protected]>
sctp: sctp_sock_filter(): avoid list_entry() on possibly empty list

Rafał Miłecki <[email protected]>
net: bgmac: fix BCM5358 support by setting correct flags

Jason Xing <[email protected]>
i40e: add double of VLAN header when computing the max MTU

Jason Xing <[email protected]>
ixgbe: allow to increase MTU to 3K with XDP enabled

Andrew Morton <[email protected]>
revert "squashfs: harden sanity check in squashfs_read_xattr_id_table"

Felix Riemann <[email protected]>
net: Fix unwanted sign extension in netdev_stats_to_stats64()

Aaron Thompson <[email protected]>
Revert "mm: Always release pages to the buddy allocator in memblock_free_late()."

Mike Kravetz <[email protected]>
hugetlb: check for undefined shift on 32 bit architectures

Munehisa Kamata <[email protected]>
sched/psi: Fix use-after-free in ep_remove_wait_queue()

Kailang Yang <[email protected]>
ALSA: hda/realtek - fixed wrong gpio assigned

Bo Liu <[email protected]>
ALSA: hda/conexant: add a new hda codec SN6180

Yang Yingliang <[email protected]>
mmc: mmc_spi: fix error handling in mmc_spi_probe()

Yang Yingliang <[email protected]>
mmc: sdio: fix possible resource leaks in some error paths

Paul Cercueil <[email protected]>

    mmc: jz4740: Work around bug on JZ4760(B)

Florian Westphal <[email protected]>
netfilter: nft_tproxy: restrict to prerouting hook

Amir Goldstein <[email protected]>
ovl: remove privs in ovl_fallocate()

Amir Goldstein <[email protected]>
ovl: remove privs in ovl_copyfile()

Sumanth Korikkar <[email protected]>
s390/signal: fix endless loop in do_signal

Seth Jenkins <[email protected]>
aio: fix mremap after fork null-deref

Russell King (Oracle) <[email protected]>
nvmem: core: fix registration vs use race

Russell King (Oracle) <[email protected]>
nvmem: core: fix cleanup after dev_set_name()

Russell King (Oracle) <[email protected]>
nvmem: core: remove nvmem_config wp_gpio

Gaosheng Cui <[email protected]>
nvmem: core: add error handling for dev_set_name

Hans de Goede <[email protected]>
platform/x86: touchscreen_dmi: Add Chuwi Vi8 (CWI501) DMI match

Amit Engel <[email protected]>
nvme-fc: fix a missing queue put in nvmet_fc_ls_create_association

Vasily Gorbik <[email protected]>
s390/decompressor: specify __decompress() buf len to avoid overflow

Kees Cook <[email protected]>
net: sched: sch: Bounds check priority

Andrey Konovalov <[email protected]>
net: stmmac: do not stop RX_CLK in Rx LPI state for qcs404 SoC

Hyunwoo Kim <[email protected]>
net/rose: Fix to not accept on connected socket

Shunsuke Mie <[email protected]>
tools/virtio: fix the vringh test for virtio ring changes

Arnd Bergmann <[email protected]>
ASoC: cs42l56: fix DT probe

Cezary Rojewski <[email protected]>
ALSA: hda: Do not unset preset when cleaning up codec

Eduard Zingerman <[email protected]>
selftests/bpf: Verify copy_register_state() preserves parent/live fields

Pierre-Louis Bossart <[email protected]>
ASoC: Intel: sof_rt5682: always set dpcm_capture for amplifiers

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

Diffstat:

 Makefile                                           |  4 +-
 arch/s390/boot/compressed/decompressor.c           |  2 +-
 arch/s390/kernel/signal.c                          |  2 +-
 arch/x86/kvm/x86.c                                 |  3 +-
 drivers/gpu/drm/i915/gt/intel_workarounds.c        | 32 ++++++++--------
 drivers/mmc/core/sdio_bus.c                        | 17 +++++++--
 drivers/mmc/core/sdio_cis.c                        | 12 ------
 drivers/mmc/host/jz4740_mmc.c                      | 10 +++++
 drivers/mmc/host/mmc_spi.c                         |  8 ++--
 drivers/net/ethernet/broadcom/bgmac-bcma.c         |  6 +--
 drivers/net/ethernet/broadcom/bnxt/bnxt.c          |  8 +++-
 drivers/net/ethernet/intel/i40e/i40e_main.c        |  4 +-
 drivers/net/ethernet/intel/ixgbe/ixgbe.h           |  2 +
 drivers/net/ethernet/intel/ixgbe/ixgbe_main.c      | 28 ++++++++------
 .../ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c    |  2 +
 drivers/net/ethernet/stmicro/stmmac/dwmac5.c       |  3 +-
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c  |  3 +-
 .../net/ethernet/stmicro/stmmac/stmmac_platform.c  |  2 +-
 drivers/net/usb/kalmia.c                           |  8 ++--
 drivers/nvme/target/fc.c                           |  4 +-
 drivers/nvmem/core.c                               | 43 +++++++++++-----------
 drivers/platform/x86/touchscreen_dmi.c             |  9 +++++
 fs/aio.c                                           |  4 ++
 fs/nilfs2/ioctl.c                                  |  7 ++++
 fs/nilfs2/super.c                                  |  9 +++++
 fs/nilfs2/the_nilfs.c                              |  8 +++-
 fs/overlayfs/file.c                                | 28 ++++++++++++--
 fs/squashfs/xattr_id.c                             |  2 +-
 include/linux/hugetlb.h                            |  5 ++-
 include/linux/nvmem-provider.h                     |  2 -
 include/linux/stmmac.h                             |  1 +
 include/net/sock.h                                 | 13 +++++++
 kernel/sched/psi.c                                 |  7 ++--
 kernel/time/alarmtimer.c                           | 33 +++++++++++++++--
 mm/memblock.c                                      |  8 +---
 net/core/dev.c                                     |  2 +-
 net/dccp/ipv6.c                                    |  7 +---
 net/ipv6/datagram.c                                |  2 +-
 net/ipv6/tcp_ipv6.c                                | 11 ++----
 net/mpls/af_mpls.c                                 |  4 ++
 net/netfilter/nft_tproxy.c                         |  8 ++++
 net/openvswitch/meter.c                            |  4 +-
 net/rose/af_rose.c                                 |  8 ++++
 net/sched/act_bpf.c                                |  2 +-
 net/sched/act_connmark.c                           |  2 +-
 net/sched/act_ctinfo.c                             |  6 +--
 net/sched/act_gate.c                               |  2 +-
 net/sched/act_ife.c                                |  2 +-
 net/sched/act_ipt.c                                |  2 +-
 net/sched/act_mpls.c                               |  2 +-
 net/sched/act_nat.c                                |  2 +-
 net/sched/act_pedit.c                              |  2 +-
 net/sched/act_police.c                             |  2 +-
 net/sched/act_sample.c                             |  2 +-
 net/sched/act_simple.c                             |  2 +-
 net/sched/act_skbedit.c                            |  2 +-
 net/sched/act_skbmod.c                             |  2 +-
 net/sched/cls_tcindex.c                            | 34 +++++++++++++++--
 net/sched/sch_htb.c                                |  5 ++-
 net/sctp/diag.c                                    |  4 +-
 sound/pci/hda/hda_bind.c                           |  2 +
 sound/pci/hda/hda_codec.c                          |  1 -
 sound/pci/hda/patch_conexant.c                     |  1 +
 sound/pci/hda/patch_realtek.c                      |  2 +-
 sound/soc/codecs/cs42l56.c                         |  6 ---
 sound/soc/intel/boards/sof_rt5682.c                |  3 ++
 sound/soc/sof/intel/hda-dai.c                      |  8 ++--
 .../selftests/bpf/verifier/search_pruning.c        | 36 ++++++++++++++++++
 tools/virtio/linux/bug.h                           |  8 ++--
 tools/virtio/linux/build_bug.h                     |  7 ++++
 tools/virtio/linux/cpumask.h                       |  7 ++++
 tools/virtio/linux/gfp.h                           |  7 ++++
 tools/virtio/linux/kernel.h                        |  1 +
 tools/virtio/linux/kmsan.h                         | 12 ++++++
 tools/virtio/linux/scatterlist.h                   |  1 +
 tools/virtio/linux/topology.h                      |  7 ++++
 76 files changed, 404 insertions(+), 165 deletions(-)

From: Russell King (Oracle) <[email protected]>

[ Upstream commit ab3428cfd9aa2f3463ee4b2909b5bb2193bd0c4a ]

The i.MX6 CPU frequency driver sometimes fails to register at boot time due to nvmem_cell_read_u32() sporadically returning -ENOENT.

This happens because there is a window where __nvmem_device_get() in of_nvmem_cell_get() is able to return the nvmem device, but as cells have been setup, nvmem_find_cell_entry_by_node() returns NULL.

The occurs because the nvmem core registration code violates one of the fundamental principles of kernel programming: do not publish data structures before their setup is complete.

Fix this by making nvmem core code conform with this principle.

---
 drivers/nvmem/core.c | 16 +++++++---------
 1 file changed, 7 insertions(+), 9 deletions(-)

index de356cdde4ce8..0ef7b95348b1b 100644
@@ -682,16 +682,10 @@ struct nvmem_device *nvmem_register(const struct nvmem_config *config)
 	nvmem->dev.groups = nvmem_dev_groups;
 #endif
 
-	dev_dbg(&nvmem->dev, "Registering nvmem device %s\n", config->name);
-
-	rval = device_add(&nvmem->dev);
-	if (rval)
-		goto err_put_device;
-
 	if (config->compat) {
 		rval = nvmem_sysfs_setup_compat(nvmem, config);
 		if (rval)
-			goto err_device_del;
+			goto err_put_device;
 	}
 
 	if (config->cells) {

@@ -708,6 +702,12 @@ struct nvmem_device *nvmem_register(const struct nvmem_config *config)
 	if (rval)
 		goto err_remove_cells;
 
+	dev_dbg(&nvmem->dev, "Registering nvmem device %s\n", config->name);
+
+	rval = device_add(&nvmem->dev);
+	if (rval)
+		goto err_remove_cells;
+
 	blocking_notifier_call_chain(&nvmem_notifier, NVMEM_ADD, nvmem);
 
 	return nvmem;

@@ -716,8 +716,6 @@ struct nvmem_device *nvmem_register(const struct nvmem_config *config)
 	nvmem_device_remove_all_cells(nvmem);
 	if (config->compat)
 		nvmem_sysfs_remove_compat(nvmem, config);
-err_device_del:
-	device_del(&nvmem->dev);
 err_put_device:
 	put_device(&nvmem->dev);
 

2.39.0

From: Bo Liu <[email protected]>

commit 18d7e16c917a08f08778ecf2b780d63648d5d923 upstream.

The current kernel does not support the SN6180 codec chip. Add the SN6180 codec configuration item to kernel.

---
 sound/pci/hda/patch_conexant.c |    1 +
 1 file changed, 1 insertion(+)

@@ -1117,6 +1117,7 @@ static const struct hda_device_id snd_hd
 	HDA_CODEC_ENTRY(0x14f11f86, "CX8070", patch_conexant_auto),
 	HDA_CODEC_ENTRY(0x14f12008, "CX8200", patch_conexant_auto),
 	HDA_CODEC_ENTRY(0x14f120d0, "CX11970", patch_conexant_auto),
+	HDA_CODEC_ENTRY(0x14f120d1, "SN6180", patch_conexant_auto),
 	HDA_CODEC_ENTRY(0x14f15045, "CX20549 (Venice)", patch_conexant_auto),
 	HDA_CODEC_ENTRY(0x14f15047, "CX20551 (Waikiki)", patch_conexant_auto),
 	HDA_CODEC_ENTRY(0x14f15051, "CX20561 (Hermosa)", patch_conexant_auto),

From: Kailang Yang <[email protected]>

commit 2bdccfd290d421b50df4ec6a68d832dad1310748 upstream.

GPIO2 PIN use for output. Mask Dir and Data need to assign for 0x4. Not 0x3. This fixed was for Lenovo Desktop(0x17aa1056). GPIO2 use for AMP enable.

---
 sound/pci/hda/patch_realtek.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -827,7 +827,7 @@ do_sku:
 			alc_setup_gpio(codec, 0x02);
 			break;
 		case 7:
-			alc_setup_gpio(codec, 0x03);
+			alc_setup_gpio(codec, 0x04);
 			break;
 		case 5:
 		default:

From: Munehisa Kamata <[email protected]>

commit c2dbe32d5db5c4ead121cf86dabd5ab691fb47fe upstream.

If a non-root cgroup gets removed when there is a thread that registered trigger and is polling on a pressure file within the cgroup, the polling waitqueue gets freed in the following path:

do_rmdir
cgroup_rmdir
kernfs_drain_open_files
cgroup_file_release
cgroup_pressure_release
psi_trigger_destroy

However, the polling thread still has a reference to the pressure file and will access the freed waitqueue when the file is closed or upon exit:

fput
ep_eventpoll_release
ep_free
ep_remove_wait_queue
remove_wait_queue

This results in use-after-free as pasted below.

The fundamental problem here is that cgroup_file_release() (and consequently waitqueue's lifetime) is not tied to the file's real lifetime. Using wake_up_pollfree() here might be less than ideal, but it is in line with the comment at commit 42288cb44c4b ("wait: add wake_up_pollfree()") since the waitqueue's lifetime is not tied to file's one and can be considered as another special case. While this would be fixable by somehow making cgroup_file_release() be tied to the fput(), it would require sizable refactoring at cgroups or higher layer which might be more justifiable if we identify more cases like this.

  BUG: KASAN: use-after-free in _raw_spin_lock_irqsave+0x60/0xc0
  Write of size 4 at addr ffff88810e625328 by task a.out/4404

	CPU: 19 PID: 4404 Comm: a.out Not tainted 6.2.0-rc6 #38
	Hardware name: Amazon EC2 c5a.8xlarge/, BIOS 1.0 10/16/2017
	Call Trace:
	<TASK>
	dump_stack_lvl+0x73/0xa0
	print_report+0x16c/0x4e0
	kasan_report+0xc3/0xf0
	kasan_check_range+0x2d2/0x310
	_raw_spin_lock_irqsave+0x60/0xc0
	remove_wait_queue+0x1a/0xa0
	ep_free+0x12c/0x170
	ep_eventpoll_release+0x26/0x30
	__fput+0x202/0x400
	task_work_run+0x11d/0x170
	do_exit+0x495/0x1130
	do_group_exit+0x100/0x100
	get_signal+0xd67/0xde0
	arch_do_signal_or_restart+0x2a/0x2b0
	exit_to_user_mode_prepare+0x94/0x100
	syscall_exit_to_user_mode+0x20/0x40
	do_syscall_64+0x52/0x90
	entry_SYSCALL_64_after_hwframe+0x63/0xcd
	</TASK>

 Allocated by task 4404:

	kasan_set_track+0x3d/0x60
	__kasan_kmalloc+0x85/0x90
	psi_trigger_create+0x113/0x3e0
	pressure_write+0x146/0x2e0
	cgroup_file_write+0x11c/0x250
	kernfs_fop_write_iter+0x186/0x220
	vfs_write+0x3d8/0x5c0
	ksys_write+0x90/0x110
	do_syscall_64+0x43/0x90
	entry_SYSCALL_64_after_hwframe+0x63/0xcd

 Freed by task 4407:

	kasan_set_track+0x3d/0x60
	kasan_save_free_info+0x27/0x40
	____kasan_slab_free+0x11d/0x170
	slab_free_freelist_hook+0x87/0x150
	__kmem_cache_free+0xcb/0x180
	psi_trigger_destroy+0x2e8/0x310
	cgroup_file_release+0x4f/0xb0
	kernfs_drain_open_files+0x165/0x1f0
	kernfs_drain+0x162/0x1a0
	__kernfs_remove+0x1fb/0x310
	kernfs_remove_by_name_ns+0x95/0xe0
	cgroup_addrm_files+0x67f/0x700
	cgroup_destroy_locked+0x283/0x3c0
	cgroup_rmdir+0x29/0x100
	kernfs_iop_rmdir+0xd1/0x140
	vfs_rmdir+0xfe/0x240
	do_rmdir+0x13d/0x280
	__x64_sys_rmdir+0x2c/0x30
	do_syscall_64+0x43/0x90
	entry_SYSCALL_64_after_hwframe+0x63/0xcd

---
 kernel/sched/psi.c |    7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

@@ -1158,10 +1158,11 @@ void psi_trigger_destroy(struct psi_trig
 
 	group = t->group;
 	/*
-	 * Wakeup waiters to stop polling. Can happen if cgroup is deleted
-	 * from under a polling process.
+	 * Wakeup waiters to stop polling and clear the queue to prevent it from
+	 * being accessed later. Can happen if cgroup is deleted from under a
+	 * polling process.
 	 */
-	wake_up_interruptible(&t->event_wait);
+	wake_up_pollfree(&t->event_wait);
 
 	mutex_lock(&group->trigger_lock);
 

From: Mike Kravetz <[email protected]>

commit ec4288fe63966b26d53907212ecd05dfa81dd2cc upstream.

Users can specify the hugetlb page size in the mmap, shmget and memfd_create system calls. This is done by using 6 bits within the flags argument to encode the base-2 logarithm of the desired page size. The routine hstate_sizelog() uses the log2 value to find the corresponding hugetlb hstate structure. Converting the log2 value (page_size_log) to potential hugetlb page size is the simple statement:

1UL << page_size_log

Because only 6 bits are used for page_size_log, the left shift can not be greater than 63. This is fine on 64 bit architectures where a long is 64 bits. However, if a value greater than 31 is passed on a 32 bit architecture (where long is 32 bits) the shift will result in undefined behavior. This was generally not an issue as the result of the undefined shift had to exactly match hugetlb page size to proceed.

Recent improvements in runtime checking have resulted in this undefined behavior throwing errors such as reported below.

Fix by comparing page_size_log to BITS_PER_LONG before doing shift.

---
 include/linux/hugetlb.h |    5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

@@ -542,7 +542,10 @@ static inline struct hstate *hstate_size
 	if (!page_size_log)
 		return &default_hstate;
 
-	return size_to_hstate(1UL << page_size_log);
+	if (page_size_log < BITS_PER_LONG)
+		return size_to_hstate(1UL << page_size_log);
+
+	return NULL;
 }
 
 static inline struct hstate *hstate_vma(struct vm_area_struct *vma)

From: Aaron Thompson <[email protected]>

commit 647037adcad00f2bab8828d3d41cd0553d41f3bd upstream.

This reverts commit 115d9d77bb0f9152c60b6e8646369fa7f6167593.

The pages being freed by memblock_free_late() have already been initialized, but if they are in the deferred init range, __free_one_page() might access nearby uninitialized pages when trying to coalesce buddies. This can, for example, trigger this BUG:

  BUG: unable to handle page fault for address: ffffe964c02580c8
  RIP: 0010:__list_del_entry_valid+0x3f/0x70
   <TASK>
   __free_one_page+0x139/0x410
   __free_pages_ok+0x21d/0x450
   memblock_free_late+0x8c/0xb9
   efi_free_boot_services+0x16b/0x25c
   efi_enter_virtual_mode+0x403/0x446
   start_kernel+0x678/0x714
   secondary_startup_64_no_verify+0xd2/0xdb
   </TASK>

A proper fix will be more involved so revert this change for the time being.

---
 mm/memblock.c |    8 +-------
 1 file changed, 1 insertion(+), 7 deletions(-)

@@ -1597,13 +1597,7 @@ void __init __memblock_free_late(phys_ad
 	end = PFN_DOWN(base + size);
 
 	for (; cursor < end; cursor++) {
-		/*
-		 * Reserved pages are always initialized by the end of
-		 * memblock_free_all() (by memmap_init() and, if deferred
-		 * initialization is enabled, memmap_init_reserved_pages()), so
-		 * these pages can be released directly to the buddy allocator.
-		 */
-		__free_pages_core(pfn_to_page(cursor), 0);
+		memblock_free_pages(pfn_to_page(cursor), cursor, 0);
 		totalram_pages_inc();
 	}
 }

From: Felix Riemann <[email protected]>

commit 9b55d3f0a69af649c62cbc2633e6d695bb3cc583 upstream.

When converting net_device_stats to rtnl_link_stats64 sign extension is triggered on ILP32 machines as 6c1c509778 changed the previous "ulong -> u64" conversion to "long -> u64" by accessing the net_device_stats fields through a (signed) atomic_long_t.

This causes for example the received bytes counter to jump to 16EiB after having received 2^31 bytes. Casting the atomic value to "unsigned long" beforehand converting it into u64 avoids this.

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

@@ -10326,7 +10326,7 @@ void netdev_stats_to_stats64(struct rtnl
 
 	BUILD_BUG_ON(n > sizeof(*stats64) / sizeof(u64));
 	for (i = 0; i < n; i++)
-		dst[i] = atomic_long_read(&src[i]);
+		dst[i] = (unsigned long)atomic_long_read(&src[i]);
 	/* zero out counters that only exist in rtnl_link_stats64 */
 	memset((char *)stats64 + n * sizeof(u64), 0,
 	       sizeof(*stats64) - n * sizeof(u64));

From: Andrew Morton <[email protected]>

commit a5b21d8d791cd4db609d0bbcaa9e0c7e019888d1 upstream.

This fix was nacked by Philip, for reasons identified in the email linked below.

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

@@ -76,7 +76,7 @@ __le64 *squashfs_read_xattr_id_table(str
 	/* Sanity check values */
 
 	/* there is always at least one xattr id */
-	if (*xattr_ids <= 0)
+	if (*xattr_ids == 0)
 		return ERR_PTR(-EINVAL);
 
 	len = SQUASHFS_XATTR_BLOCK_BYTES(*xattr_ids);

From: Jason Xing <[email protected]>

commit f9cd6a4418bac6a046ee78382423b1ae7565fb24 upstream.

Recently I encountered one case where I cannot increase the MTU size directly from 1500 to a much bigger value with XDP enabled if the server is equipped with IXGBE card, which happened on thousands of servers in production environment. After applying the current patch, we can set the maximum MTU size to 3K.

This patch follows the behavior of changing MTU as i40e/ice does.

[1] commit 23b44513c3e6 ("ice: allow 3k MTU for XDP")
[2] commit 0c8493d90b6b ("i40e: add XDP support for pass and drop actions")

---
 drivers/net/ethernet/intel/ixgbe/ixgbe_main.c |   25 ++++++++++++++++---------
 1 file changed, 16 insertions(+), 9 deletions(-)

@@ -6729,6 +6729,18 @@ static void ixgbe_free_all_rx_resources(
 }
 
 /**
+ * ixgbe_max_xdp_frame_size - returns the maximum allowed frame size for XDP
+ * @adapter: device handle, pointer to adapter
+ */
+static int ixgbe_max_xdp_frame_size(struct ixgbe_adapter *adapter)
+{
+	if (PAGE_SIZE >= 8192 || adapter->flags2 & IXGBE_FLAG2_RX_LEGACY)
+		return IXGBE_RXBUFFER_2K;
+	else
+		return IXGBE_RXBUFFER_3K;
+}
+
+/**
  * ixgbe_change_mtu - Change the Maximum Transfer Unit
  * @netdev: network interface device structure
  * @new_mtu: new value for maximum frame size

@@ -6739,18 +6751,13 @@ static int ixgbe_change_mtu(struct net_d
 {
 	struct ixgbe_adapter *adapter = netdev_priv(netdev);
 
-	if (adapter->xdp_prog) {
+	if (ixgbe_enabled_xdp_adapter(adapter)) {
 		int new_frame_size = new_mtu + ETH_HLEN + ETH_FCS_LEN +
 				     VLAN_HLEN;
-		int i;
-
-		for (i = 0; i < adapter->num_rx_queues; i++) {
-			struct ixgbe_ring *ring = adapter->rx_ring[i];
 
-			if (new_frame_size > ixgbe_rx_bufsz(ring)) {
-				e_warn(probe, "Requested MTU size is not supported with XDP\n");
-				return -EINVAL;
-			}
+		if (new_frame_size > ixgbe_max_xdp_frame_size(adapter)) {
+			e_warn(probe, "Requested MTU size is not supported with XDP\n");
+			return -EINVAL;
 		}
 	}
 

From: Jason Xing <[email protected]>

commit ce45ffb815e8e238f05de1630be3969b6bb15e4e upstream.

Include the second VLAN HLEN into account when computing the maximum MTU size as other drivers do.

---
 drivers/net/ethernet/intel/i40e/i40e_main.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -2788,7 +2788,7 @@ static int i40e_change_mtu(struct net_de
 	struct i40e_pf *pf = vsi->back;
 
 	if (i40e_enabled_xdp_vsi(vsi)) {
-		int frame_size = new_mtu + ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN;
+		int frame_size = new_mtu + I40E_PACKET_HDR_PAD;
 
 		if (frame_size > i40e_max_xdp_frame_size(vsi))
 			return -EINVAL;

From: Rafał Miłecki <[email protected]>

commit d61615c366a489646a1bfe5b33455f916762d5f4 upstream.

Code blocks handling BCMA_CHIP_ID_BCM5357 and BCMA_CHIP_ID_BCM53572 were incorrectly unified. Chip package values are not unique and cannot be checked independently. They are meaningful only in a context of a given chip.

Packages BCM5358 and BCM47188 share the same value but then belong to different chips. Code unification resulted in treating BCM5358 as BCM47188 and broke its initialization.

---
 drivers/net/ethernet/broadcom/bgmac-bcma.c |    6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

@@ -228,12 +228,12 @@ static int bgmac_probe(struct bcma_devic
 		bgmac->feature_flags |= BGMAC_FEAT_CLKCTLST;
 		bgmac->feature_flags |= BGMAC_FEAT_FLW_CTRL1;
 		bgmac->feature_flags |= BGMAC_FEAT_SW_TYPE_PHY;
-		if (ci->pkg == BCMA_PKG_ID_BCM47188 ||
-		    ci->pkg == BCMA_PKG_ID_BCM47186) {
+		if ((ci->id == BCMA_CHIP_ID_BCM5357 && ci->pkg == BCMA_PKG_ID_BCM47186) ||
+		    (ci->id == BCMA_CHIP_ID_BCM53572 && ci->pkg == BCMA_PKG_ID_BCM47188)) {
 			bgmac->feature_flags |= BGMAC_FEAT_SW_TYPE_RGMII;
 			bgmac->feature_flags |= BGMAC_FEAT_IOST_ATTACHED;
 		}
-		if (ci->pkg == BCMA_PKG_ID_BCM5358)
+		if (ci->id == BCMA_CHIP_ID_BCM5357 && ci->pkg == BCMA_PKG_ID_BCM5358)
 			bgmac->feature_flags |= BGMAC_FEAT_SW_TYPE_EPHYRMII;
 		break;
 	case BCMA_CHIP_ID_BCM53573:

From: Seth Jenkins <[email protected]>

commit 81e9d6f8647650a7bead74c5f926e29970e834d1 upstream.

Commit e4a0d3e720e7 ("aio: Make it possible to remap aio ring") introduced a null-deref if mremap is called on an old aio mapping after fork as mm->ioctx_table will be set to NULL.

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

@@ -335,6 +335,9 @@ static int aio_ring_mremap(struct vm_are
 	spin_lock(&mm->ioctx_lock);
 	rcu_read_lock();
 	table = rcu_dereference(mm->ioctx_table);
+	if (!table)
+		goto out_unlock;
+
 	for (i = 0; i < table->nr; i++) {
 		struct kioctx *ctx;
 

@@ -348,6 +351,7 @@ static int aio_ring_mremap(struct vm_are
 		}
 	}
 
+out_unlock:
 	rcu_read_unlock();
 	spin_unlock(&mm->ioctx_lock);
 	return res;

From: Pietro Borrello <[email protected]>

commit a1221703a0f75a9d81748c516457e0fc76951496 upstream.

Use list_is_first() to check whether tsp->asoc matches the first element of ep->asocs, as the list is not guaranteed to have an entry.

---
 net/sctp/diag.c |    4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

@@ -349,11 +349,9 @@ static int sctp_sock_filter(struct sctp_
 	struct sctp_comm_param *commp = p;
 	struct sock *sk = ep->base.sk;
 	const struct inet_diag_req_v2 *r = commp->r;
-	struct sctp_association *assoc =
-		list_entry(ep->asocs.next, struct sctp_association, asocs);
 
 	/* find the ep only once through the transports by this condition */
-	if (tsp->asoc != assoc)
+	if (!list_is_first(&tsp->asoc->asocs, &ep->asocs))
 		return 0;
 
 	if (r->sdiag_family != AF_UNSPEC && sk->sk_family != r->sdiag_family)

From: Pedro Tammela <[email protected]>

commit ee059170b1f7e94e55fa6cadee544e176a6e59c2 upstream.

The imperfect hash area can be updated while packets are traversing, which will cause a use-after-free when 'tcf_exts_exec()' is called with the destroyed tcf_ext.

CPU 0: CPU 1:
tcindex_set_parms tcindex_classify
tcindex_lookup
tcindex_lookup
tcf_exts_change
tcf_exts_exec [UAF]

Stop operating on the shared area directly, by using a local copy, and update the filter with 'rcu_replace_pointer()'. Delete the old filter version only after a rcu grace period elapsed.

---
 net/sched/cls_tcindex.c |   34 ++++++++++++++++++++++++++++++----
 1 file changed, 30 insertions(+), 4 deletions(-)

@@ -12,6 +12,7 @@
 #include <linux/errno.h>
 #include <linux/slab.h>
 #include <linux/refcount.h>
+#include <linux/rcupdate.h>
 #include <net/act_api.h>
 #include <net/netlink.h>
 #include <net/pkt_cls.h>

@@ -338,6 +339,7 @@ tcindex_set_parms(struct net *net, struc
 	struct tcf_result cr = {};
 	int err, balloc = 0;
 	struct tcf_exts e;
+	bool update_h = false;
 
 	err = tcf_exts_init(&e, net, TCA_TCINDEX_ACT, TCA_TCINDEX_POLICE);
 	if (err < 0)

@@ -455,10 +457,13 @@ tcindex_set_parms(struct net *net, struc
 		}
 	}
 
-	if (cp->perfect)
+	if (cp->perfect) {
 		r = cp->perfect + handle;
-	else
-		r = tcindex_lookup(cp, handle) ? : &new_filter_result;
+	} else {
+		/* imperfect area is updated in-place using rcu */
+		update_h = !!tcindex_lookup(cp, handle);
+		r = &new_filter_result;
+	}
 
 	if (r == &new_filter_result) {
 		f = kzalloc(sizeof(*f), GFP_KERNEL);

@@ -484,7 +489,28 @@ tcindex_set_parms(struct net *net, struc
 
 	rcu_assign_pointer(tp->root, cp);
 
-	if (r == &new_filter_result) {
+	if (update_h) {
+		struct tcindex_filter __rcu **fp;
+		struct tcindex_filter *cf;
+
+		f->result.res = r->res;
+		tcf_exts_change(&f->result.exts, &r->exts);
+
+		/* imperfect area bucket */
+		fp = cp->h + (handle % cp->hash);
+
+		/* lookup the filter, guaranteed to exist */
+		for (cf = rcu_dereference_bh_rtnl(*fp); cf;
+		     fp = &cf->next, cf = rcu_dereference_bh_rtnl(*fp))
+			if (cf->key == handle)
+				break;
+
+		f->next = cf->next;
+
+		cf = rcu_replace_pointer(*fp, f, 1);
+		tcf_exts_get_net(&cf->result.exts);
+		tcf_queue_work(&cf->rwork, tcindex_destroy_fexts_work);
+	} else if (r == &new_filter_result) {
 		struct tcindex_filter *nfp;
 		struct tcindex_filter __rcu **fp;
 

From: Kuniyuki Iwashima <[email protected]>

commit ca43ccf41224b023fc290073d5603a755fd12eed upstream.

Eric Dumazet pointed out [0] that when we call skb_set_owner_r() for ipv6_pinfo.pktoptions, sk_rmem_schedule() has not been called, resulting in a negative sk_forward_alloc.

We add a new helper which clones a skb and sets its owner only when sk_rmem_schedule() succeeds.

Note that we move skb_set_owner_r() forward in (dccp|tcp)_v6_do_rcv() because tcp_send_synack() can make sk_forward_alloc negative before ipv6_opt_accepted() in the crossed SYN-ACK or self-connect() cases.

[0]: https://lore.kernel.org/netdev/CANn89iK9oc20Jdi_41jb9URdF210r7d1Y-+uypbMSbOfY6jqrg@mail.gmail.com/

---
 include/net/sock.h  |   13 +++++++++++++
 net/dccp/ipv6.c     |    7 ++-----
 net/ipv6/tcp_ipv6.c |   10 +++-------
 3 files changed, 18 insertions(+), 12 deletions(-)

@@ -2243,6 +2243,19 @@ static inline __must_check bool skb_set_
 	return false;
 }
 
+static inline struct sk_buff *skb_clone_and_charge_r(struct sk_buff *skb, struct sock *sk)
+{
+	skb = skb_clone(skb, sk_gfp_mask(sk, GFP_ATOMIC));
+	if (skb) {
+		if (sk_rmem_schedule(sk, skb, skb->truesize)) {
+			skb_set_owner_r(skb, sk);
+			return skb;
+		}
+		__kfree_skb(skb);
+	}
+	return NULL;
+}
+
 void sk_reset_timer(struct sock *sk, struct timer_list *timer,
 		    unsigned long expires);
 

@@ -541,11 +541,9 @@ static struct sock *dccp_v6_request_recv
 	*own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash), NULL);
 	/* Clone pktoptions received with SYN, if we own the req */
 	if (*own_req && ireq->pktopts) {
-		newnp->pktoptions = skb_clone(ireq->pktopts, GFP_ATOMIC);
+		newnp->pktoptions = skb_clone_and_charge_r(ireq->pktopts, newsk);
 		consume_skb(ireq->pktopts);
 		ireq->pktopts = NULL;
-		if (newnp->pktoptions)
-			skb_set_owner_r(newnp->pktoptions, newsk);
 	}
 
 	return newsk;

@@ -605,7 +603,7 @@ static int dccp_v6_do_rcv(struct sock *s
 					       --ANK (980728)
 	 */
 	if (np->rxopt.all)
-		opt_skb = skb_clone(skb, GFP_ATOMIC);
+		opt_skb = skb_clone_and_charge_r(skb, sk);
 
 	if (sk->sk_state == DCCP_OPEN) { /* Fast path */
 		if (dccp_rcv_established(sk, skb, dccp_hdr(skb), skb->len))

@@ -669,7 +667,6 @@ ipv6_pktoptions:
 			np->flow_label = ip6_flowlabel(ipv6_hdr(opt_skb));
 		if (ipv6_opt_accepted(sk, opt_skb,
 				      &DCCP_SKB_CB(opt_skb)->header.h6)) {
-			skb_set_owner_r(opt_skb, sk);
 			memmove(IP6CB(opt_skb),
 				&DCCP_SKB_CB(opt_skb)->header.h6,
 				sizeof(struct inet6_skb_parm));

@@ -1406,14 +1406,11 @@ static struct sock *tcp_v6_syn_recv_sock
 
 		/* Clone pktoptions received with SYN, if we own the req */
 		if (ireq->pktopts) {
-			newnp->pktoptions = skb_clone(ireq->pktopts,
-						      sk_gfp_mask(sk, GFP_ATOMIC));
+			newnp->pktoptions = skb_clone_and_charge_r(ireq->pktopts, newsk);
 			consume_skb(ireq->pktopts);
 			ireq->pktopts = NULL;
-			if (newnp->pktoptions) {
+			if (newnp->pktoptions)
 				tcp_v6_restore_cb(newnp->pktoptions);
-				skb_set_owner_r(newnp->pktoptions, newsk);
-			}
 		}
 	} else {
 		if (!req_unhash && found_dup_sk) {

@@ -1481,7 +1478,7 @@ static int tcp_v6_do_rcv(struct sock *sk
 					       --ANK (980728)
 	 */
 	if (np->rxopt.all)
-		opt_skb = skb_clone(skb, sk_gfp_mask(sk, GFP_ATOMIC));
+		opt_skb = skb_clone_and_charge_r(skb, sk);
 
 	if (sk->sk_state == TCP_ESTABLISHED) { /* Fast path */
 		struct dst_entry *dst;

@@ -1563,7 +1560,6 @@ ipv6_pktoptions:
 		if (np->repflow)
 			np->flow_label = ip6_flowlabel(ipv6_hdr(opt_skb));
 		if (ipv6_opt_accepted(sk, opt_skb, &TCP_SKB_CB(opt_skb)->header.h6)) {
-			skb_set_owner_r(opt_skb, sk);
 			tcp_v6_restore_cb(opt_skb);
 			opt_skb = xchg(&np->pktoptions, opt_skb);
 		} else {

From: Miko Larsson <[email protected]>

commit c68f345b7c425b38656e1791a0486769a8797016 upstream.

syzbot reported that act_len in kalmia_send_init_packet() is uninitialized when passing it to the first usb_bulk_msg error path. Jiri Pirko noted that it's pointless to pass it in the error path, and that the value that would be printed in the second error path would be the value of act_len from the first call to usb_bulk_msg.[1]

With this in mind, let's just not pass act_len to the usb_bulk_msg error paths.

1: https://lore.kernel.org/lkml/Y9pY61y1nwTuzMOa@nanopsycho/

---
 drivers/net/usb/kalmia.c |    8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

@@ -65,8 +65,8 @@ kalmia_send_init_packet(struct usbnet *d
 		init_msg, init_msg_len, &act_len, KALMIA_USB_TIMEOUT);
 	if (status != 0) {
 		netdev_err(dev->net,
-			"Error sending init packet. Status %i, length %i\n",
-			status, act_len);
+			"Error sending init packet. Status %i\n",
+			status);
 		return status;
 	}
 	else if (act_len != init_msg_len) {

@@ -83,8 +83,8 @@ kalmia_send_init_packet(struct usbnet *d
 
 	if (status != 0)
 		netdev_err(dev->net,
-			"Error receiving init result. Status %i, length %i\n",
-			status, act_len);
+			"Error receiving init result. Status %i\n",
+			status);
 	else if (act_len != expected_len)
 		netdev_err(dev->net, "Unexpected init result length: %i\n",
 			act_len);

From: Hangyu Hua <[email protected]>

commit 2fa28f5c6fcbfc794340684f36d2581b4f2d20b5 upstream.

old_meter needs to be free after it is detached regardless of whether the new meter is successfully attached.

---
 net/openvswitch/meter.c |    4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

@@ -450,7 +450,7 @@ static int ovs_meter_cmd_set(struct sk_b
 
 	err = attach_meter(meter_tbl, meter);
 	if (err)
-		goto exit_unlock;
+		goto exit_free_old_meter;
 
 	ovs_unlock();
 

@@ -473,6 +473,8 @@ static int ovs_meter_cmd_set(struct sk_b
 	genlmsg_end(reply, ovs_reply_header);
 	return genlmsg_reply(reply, info);
 
+exit_free_old_meter:
+	ovs_meter_free(old_meter);
 exit_unlock:
 	ovs_unlock();
 	nlmsg_free(reply);

From: Johannes Zink <[email protected]>

commit 4562c65ec852067c6196abdcf2d925f08841dcbc upstream.

So far changing the period by just setting new period values while running did not work.

The order as indicated by the publicly available reference manual of the i.MX8MP [1] indicates a sequence:

* initiate the programming sequence
* set the values for PPS period and start time
* start the pulse train generation.

This is currently not used in dwmac5_flex_pps_config(), which instead does:

* initiate the programming sequence and immediately start the pulse train generation
* set the values for PPS period and start time

This caused the period values written not to take effect until the FlexPPS output was disabled and re-enabled again.

This patch fix the order and allows the period to be set immediately.

[1] https://www.nxp.com/webapp/Download?colCode=IMX8MPRM

---
 drivers/net/ethernet/stmicro/stmmac/dwmac5.c |    3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

@@ -520,9 +520,9 @@ int dwmac5_flex_pps_config(void __iomem
 		return 0;
 	}
 
-	val |= PPSCMDx(index, 0x2);
 	val |= TRGTMODSELx(index, 0x2);
 	val |= PPSEN0;
+	writel(val, ioaddr + MAC_PPS_CONTROL);
 
 	writel(cfg->start.tv_sec, ioaddr + MAC_PPSx_TARGET_TIME_SEC(index));
 

@@ -547,6 +547,7 @@ int dwmac5_flex_pps_config(void __iomem
 	writel(period - 1, ioaddr + MAC_PPSx_WIDTH(index));
 
 	/* Finally, activate it */
+	val |= PPSCMDx(index, 0x2);
 	writel(val, ioaddr + MAC_PPS_CONTROL);
 	return 0;
 }

From: Michael Chan <[email protected]>

commit 2038cc592811209de20c4e094ca08bfb1e6fbc6c upstream.

In bnxt_reserve_rings(), there is logic to check that the number of TX rings reserved is enough to cover all the mqprio TCs, but it fails to account for the TX XDP rings. So the check will always fail if there are mqprio TCs and TX XDP rings. As a result, the driver always fails to initialize after the XDP program is attached and the device will be brought down. A subsequent ifconfig up will also fail because the number of TX rings is set to an inconsistent number. Fix the check to properly account for TX XDP rings. If the check fails, set the number of TX rings back to a consistent number after calling netdev_reset_tc().

---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c |    8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

@@ -8761,10 +8761,14 @@ int bnxt_reserve_rings(struct bnxt *bp,
 		netdev_err(bp->dev, "ring reservation/IRQ init failure rc: %d\n", rc);
 		return rc;
 	}
-	if (tcs && (bp->tx_nr_rings_per_tc * tcs != bp->tx_nr_rings)) {
+	if (tcs && (bp->tx_nr_rings_per_tc * tcs !=
+		    bp->tx_nr_rings - bp->tx_nr_rings_xdp)) {
 		netdev_err(bp->dev, "tx ring reservation failure\n");
 		netdev_reset_tc(bp->dev);
-		bp->tx_nr_rings_per_tc = bp->tx_nr_rings;
+		if (bp->tx_nr_rings_xdp)
+			bp->tx_nr_rings_per_tc = bp->tx_nr_rings_xdp;
+		else
+			bp->tx_nr_rings_per_tc = bp->tx_nr_rings;
 		return -ENOMEM;
 	}
 	return 0;

From: Cristian Ciocaltea <[email protected]>

commit 05d7623a892a9da62da0e714428e38f09e4a64d8 upstream.

When setting 'snps,force_thresh_dma_mode' DT property, the following warning is always emitted, regardless the status of force_sf_dma_mode:

dwmac-starfive 10020000.ethernet: force_sf_dma_mode is ignored if force_thresh_dma_mode is set.

Do not print the rather misleading message when DMA store and forward mode is already disabled.

---
 drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -559,7 +559,7 @@ stmmac_probe_config_dt(struct platform_d
 	dma_cfg->mixed_burst = of_property_read_bool(np, "snps,mixed-burst");
 
 	plat->force_thresh_dma_mode = of_property_read_bool(np, "snps,force_thresh_dma_mode");
-	if (plat->force_thresh_dma_mode) {
+	if (plat->force_thresh_dma_mode && plat->force_sf_dma_mode) {
 		plat->force_sf_dma_mode = 0;
 		dev_warn(&pdev->dev,
 			 "force_sf_dma_mode is ignored if force_thresh_dma_mode is set.\n");

From: Jakub Kicinski <[email protected]>

commit fda6c89fe3d9aca073495a664e1d5aea28cd4377 upstream.

lianhui reports that when MPLS fails to register the sysctl table under new location (during device rename) the old pointers won't get overwritten and may be freed again (double free).

Handle this gracefully. The best option would be unregistering the MPLS from the device completely on failure, but unfortunately mpls_ifdown() can fail. So failing fully is also unreliable.

Another option is to register the new table first then only remove old one if the new one succeeds. That requires more code, changes order of notifications and two tables may be visible at the same time.

sysctl point is not used in the rest of the code - set to NULL on failures and skip unregister if already NULL.

---
 net/mpls/af_mpls.c |    4 ++++
 1 file changed, 4 insertions(+)

@@ -1427,6 +1427,7 @@ static int mpls_dev_sysctl_register(stru
 free:
 	kfree(table);
 out:
+	mdev->sysctl = NULL;
 	return -ENOBUFS;
 }
 

@@ -1436,6 +1437,9 @@ static void mpls_dev_sysctl_unregister(s
 	struct net *net = dev_net(dev);
 	struct ctl_table *table;
 
+	if (!mdev->sysctl)
+		return;
+
 	table = mdev->sysctl->ctl_table_arg;
 	unregister_net_sysctl_table(mdev->sysctl);
 	kfree(table);

From: Jason Xing <[email protected]>

commit 0967bf837784a11c65d66060623a74e65211af0b upstream.

Include the second VLAN HLEN into account when computing the maximum MTU size as other drivers do.

---
 drivers/net/ethernet/intel/ixgbe/ixgbe.h      |    2 ++
 drivers/net/ethernet/intel/ixgbe/ixgbe_main.c |    3 +--
 2 files changed, 3 insertions(+), 2 deletions(-)

@@ -67,6 +67,8 @@
 #define IXGBE_RXBUFFER_4K    4096
 #define IXGBE_MAX_RXBUFFER  16384  /* largest size for a single descriptor */
 
+#define IXGBE_PKT_HDR_PAD   (ETH_HLEN + ETH_FCS_LEN + (VLAN_HLEN * 2))
+
 /* Attempt to maximize the headroom available for incoming frames.  We
  * use a 2K buffer for receives and need 1536/1534 to store the data for
  * the frame.  This leaves us with 512 bytes of room.  From that we need

@@ -6752,8 +6752,7 @@ static int ixgbe_change_mtu(struct net_d
 	struct ixgbe_adapter *adapter = netdev_priv(netdev);
 
 	if (ixgbe_enabled_xdp_adapter(adapter)) {
-		int new_frame_size = new_mtu + ETH_HLEN + ETH_FCS_LEN +
-				     VLAN_HLEN;
+		int new_frame_size = new_mtu + IXGBE_PKT_HDR_PAD;
 
 		if (new_frame_size > ixgbe_max_xdp_frame_size(adapter)) {
 			e_warn(probe, "Requested MTU size is not supported with XDP\n");

From: Sumanth Korikkar <[email protected]>

No upstream commit exists: the problem addressed here is that 'commit 75309018a24d ("s390: add support for TIF_NOTIFY_SIGNAL")' was backported to 5.10. This commit is broken, but nobody noticed upstream, since shortly after s390 converted to generic entry with 'commit 56e62a737028 ("s390: convert to generic entry")', which implicitly fixed the problem outlined below.

Thread flag is set to TIF_NOTIFY_SIGNAL for io_uring work. The io work user or syscall calls do_signal when either one of the TIF_SIGPENDING or TIF_NOTIFY_SIGNAL flag is set. However, do_signal does consider only TIF_SIGPENDING signal and ignores TIF_NOTIFY_SIGNAL condition. This means get_signal is never invoked for TIF_NOTIFY_SIGNAL and hence the flag is not cleared, which results in an endless do_signal loop.

Reference: 'commit 788d0824269b ("io_uring: import 5.15-stable io_uring")'

---
 arch/s390/kernel/signal.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -472,7 +472,7 @@ void do_signal(struct pt_regs *regs)
 	current->thread.system_call =
 		test_pt_regs_flag(regs, PIF_SYSCALL) ? regs->int_code : 0;
 
-	if (test_thread_flag(TIF_SIGPENDING) && get_signal(&ksig)) {
+	if (get_signal(&ksig)) {
 		/* Whee!  Actually deliver the signal.  */
 		if (current->thread.system_call) {
 			regs->int_code = current->thread.system_call;

From: Guillaume Nault <[email protected]>

commit e010ae08c71fda8be3d6bda256837795a0b3ea41 upstream.

Take into account the IPV6_TCLASS socket option (DSCP) in ip6_datagram_flow_key_init(). Otherwise fib6_rule_match() can't properly match the DSCP value, resulting in invalid route lookup.

For example:

ip route add unreachable table main 2001:db8::10/124

ip route add table 100 2001:db8::10/124 dev eth0 ip -6 rule add dsfield 0x04 table 100

echo test | socat - UDP6:[2001:db8::11]:54321,ipv6-tclass=0x04

Without this patch, socat fails at connect() time ("No route to host") because the fib-rule doesn't jump to table 100 and the lookup ends up being done in the main table.

---
 net/ipv6/datagram.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -51,7 +51,7 @@ static void ip6_datagram_flow_key_init(s
 	fl6->flowi6_mark = sk->sk_mark;
 	fl6->fl6_dport = inet->inet_dport;
 	fl6->fl6_sport = inet->inet_sport;
-	fl6->flowlabel = np->flow_label;
+	fl6->flowlabel = ip6_make_flowinfo(np->tclass, np->flow_label);
 	fl6->flowi6_uid = sk->sk_uid;
 
 	if (!fl6->flowi6_oif)

From: Guillaume Nault <[email protected]>

commit 8230680f36fd1525303d1117768c8852314c488c upstream.

Take into account the IPV6_TCLASS socket option (DSCP) in tcp_v6_connect(). Otherwise fib6_rule_match() can't properly match the DSCP value, resulting in invalid route lookup.

For example:

ip route add unreachable table main 2001:db8::10/124

ip route add table 100 2001:db8::10/124 dev eth0 ip -6 rule add dsfield 0x04 table 100

echo test | socat - TCP6:[2001:db8::11]:54321,ipv6-tclass=0x04

Without this patch, socat fails at connect() time ("No route to host") because the fib-rule doesn't jump to table 100 and the lookup ends up being done in the main table.

---
 net/ipv6/tcp_ipv6.c |    1 +
 1 file changed, 1 insertion(+)

@@ -269,6 +269,7 @@ static int tcp_v6_connect(struct sock *s
 	fl6.flowi6_proto = IPPROTO_TCP;
 	fl6.daddr = sk->sk_v6_daddr;
 	fl6.saddr = saddr ? *saddr : np->saddr;
+	fl6.flowlabel = ip6_make_flowinfo(np->tclass, np->flow_label);
 	fl6.flowi6_oif = sk->sk_bound_dev_if;
 	fl6.flowi6_mark = sk->sk_mark;
 	fl6.fl6_dport = usin->sin6_port;

From: Amir Goldstein <[email protected]>

commit b306e90ffabdaa7e3b3350dbcd19b7663e71ab17 upstream.

Underlying fs doesn't remove privs because copy_range/remap_range are called with privileged mounter credentials.

This fixes some failures in fstest generic/673.

---
 fs/overlayfs/file.c |   16 ++++++++++++++--
 1 file changed, 14 insertions(+), 2 deletions(-)

@@ -687,14 +687,23 @@ static loff_t ovl_copyfile(struct file *
 	const struct cred *old_cred;
 	loff_t ret;
 
+	inode_lock(inode_out);
+	if (op != OVL_DEDUPE) {
+		/* Update mode */
+		ovl_copyattr(ovl_inode_real(inode_out), inode_out);
+		ret = file_remove_privs(file_out);
+		if (ret)
+			goto out_unlock;
+	}
+
 	ret = ovl_real_fdget(file_out, &real_out);
 	if (ret)
-		return ret;
+		goto out_unlock;
 
 	ret = ovl_real_fdget(file_in, &real_in);
 	if (ret) {
 		fdput(real_out);
-		return ret;
+		goto out_unlock;
 	}
 
 	old_cred = ovl_override_creds(file_inode(file_out)->i_sb);

@@ -723,6 +732,9 @@ static loff_t ovl_copyfile(struct file *
 	fdput(real_in);
 	fdput(real_out);
 
+out_unlock:
+	inode_unlock(inode_out);
+
 	return ret;
 }
 

From: Amir Goldstein <[email protected]>

commit 23a8ce16419a3066829ad4a8b7032a75817af65b upstream.

Underlying fs doesn't remove privs because fallocate is called with privileged mounter credentials.

This fixes some failure in fstests generic/683..687.

---
 fs/overlayfs/file.c |   12 +++++++++++-
 1 file changed, 11 insertions(+), 1 deletion(-)

@@ -531,9 +531,16 @@ static long ovl_fallocate(struct file *f
 	const struct cred *old_cred;
 	int ret;
 
+	inode_lock(inode);
+	/* Update mode */
+	ovl_copyattr(ovl_inode_real(inode), inode);
+	ret = file_remove_privs(file);
+	if (ret)
+		goto out_unlock;
+
 	ret = ovl_real_fdget(file, &real);
 	if (ret)
-		return ret;
+		goto out_unlock;
 
 	old_cred = ovl_override_creds(file_inode(file)->i_sb);
 	ret = vfs_fallocate(real.file, mode, offset, len);

@@ -544,6 +551,9 @@ static long ovl_fallocate(struct file *f
 
 	fdput(real);
 
+out_unlock:
+	inode_unlock(inode);
+
 	return ret;
 }
 

From: Florian Westphal <[email protected]>

commit 18bbc3213383a82b05383827f4b1b882e3f0a5a5 upstream.

TPROXY is only allowed from prerouting, but nft_tproxy doesn't check this. This fixes a crash (null dereference) when using tproxy from e.g. output.

---
 net/netfilter/nft_tproxy.c |    8 ++++++++
 1 file changed, 8 insertions(+)

@@ -289,6 +289,13 @@ static int nft_tproxy_dump(struct sk_buf
 	return 0;
 }
 
+static int nft_tproxy_validate(const struct nft_ctx *ctx,
+			       const struct nft_expr *expr,
+			       const struct nft_data **data)
+{
+	return nft_chain_validate_hooks(ctx->chain, 1 << NF_INET_PRE_ROUTING);
+}
+
 static struct nft_expr_type nft_tproxy_type;
 static const struct nft_expr_ops nft_tproxy_ops = {
 	.type		= &nft_tproxy_type,

@@ -296,6 +303,7 @@ static const struct nft_expr_ops nft_tpr
 	.eval		= nft_tproxy_eval,
 	.init		= nft_tproxy_init,
 	.dump		= nft_tproxy_dump,
+	.validate	= nft_tproxy_validate,
 };
 
 static struct nft_expr_type nft_tproxy_type __read_mostly = {

From: Paul Cercueil <[email protected]>

commit 3f18c5046e633cc4bbad396b74c05d46d353033d upstream.

On JZ4760 and JZ4760B, SD cards fail to run if the maximum clock rate is set to 50 MHz, even though the controller officially does support it.

Until the actual bug is found and fixed, limit the maximum clock rate to 24 MHz.

---
 drivers/mmc/host/jz4740_mmc.c |   10 ++++++++++
 1 file changed, 10 insertions(+)

@@ -1041,6 +1041,16 @@ static int jz4740_mmc_probe(struct platf
 	mmc->ops = &jz4740_mmc_ops;
 	if (!mmc->f_max)
 		mmc->f_max = JZ_MMC_CLK_RATE;
+
+	/*
+	 * There seems to be a problem with this driver on the JZ4760 and
+	 * JZ4760B SoCs. There, when using the maximum rate supported (50 MHz),
+	 * the communication fails with many SD cards.
+	 * Until this bug is sorted out, limit the maximum rate to 24 MHz.
+	 */
+	if (host->version == JZ_MMC_JZ4760 && mmc->f_max > JZ_MMC_CLK_RATE)
+		mmc->f_max = JZ_MMC_CLK_RATE;
+
 	mmc->f_min = mmc->f_max / 128;
 	mmc->ocr_avail = MMC_VDD_32_33 | MMC_VDD_33_34;
 

From: Yang Yingliang <[email protected]>

commit 605d9fb9556f8f5fb4566f4df1480f280f308ded upstream.

If sdio_add_func() or sdio_init_func() fails, sdio_remove_func() can not release the resources, because the sdio function is not presented in these two cases, it won't call of_node_put() or put_device().

To fix these leaks, make sdio_func_present() only control whether device_del() needs to be called or not, then always call of_node_put() and put_device().

In error case in sdio_init_func(), the reference of 'card->dev' is not get, to avoid redundant put in sdio_free_func_cis(), move the get_device() to sdio_alloc_func() and put_device() to sdio_release_func(), it can keep the get/put function be balanced.

Without this patch, while doing fault inject test, it can get the following leak reports, after this fix, the leak is gone.

unreferenced object 0xffff888112514000 (size 2048):
comm "kworker/3:2", pid 65, jiffies 4294741614 (age 124.774s) hex dump (first 32 bytes):

    00 e0 6f 12 81 88 ff ff 60 58 8d 06 81 88 ff ff  ..o.....`X......
    10 40 51 12 81 88 ff ff 10 40 51 12 81 88 ff ff  .@Q......@Q.....
  backtrace:
    [<000000009e5931da>] kmalloc_trace+0x21/0x110
    [<000000002f839ccb>] mmc_alloc_card+0x38/0xb0 [mmc_core]
    [<0000000004adcbf6>] mmc_sdio_init_card+0xde/0x170 [mmc_core]
    [<000000007538fea0>] mmc_attach_sdio+0xcb/0x1b0 [mmc_core]
    [<00000000d4fdeba7>] mmc_rescan+0x54a/0x640 [mmc_core]

unreferenced object 0xffff888112511000 (size 2048):
comm "kworker/3:2", pid 65, jiffies 4294741623 (age 124.766s) hex dump (first 32 bytes):

    00 40 51 12 81 88 ff ff e0 58 8d 06 81 88 ff ff  [email protected]......
    10 10 51 12 81 88 ff ff 10 10 51 12 81 88 ff ff  ..Q.......Q.....
  backtrace:
    [<000000009e5931da>] kmalloc_trace+0x21/0x110
    [<00000000fcbe706c>] sdio_alloc_func+0x35/0x100 [mmc_core]
    [<00000000c68f4b50>] mmc_attach_sdio.cold.18+0xb1/0x395 [mmc_core]
    [<00000000d4fdeba7>] mmc_rescan+0x54a/0x640 [mmc_core]

---
 drivers/mmc/core/sdio_bus.c |   17 ++++++++++++++---
 drivers/mmc/core/sdio_cis.c |   12 ------------
 2 files changed, 14 insertions(+), 15 deletions(-)

@@ -295,6 +295,12 @@ static void sdio_release_func(struct dev
 	if (!(func->card->quirks & MMC_QUIRK_NONSTD_SDIO))
 		sdio_free_func_cis(func);
 
+	/*
+	 * We have now removed the link to the tuples in the
+	 * card structure, so remove the reference.
+	 */
+	put_device(&func->card->dev);
+
 	kfree(func->info);
 	kfree(func->tmpbuf);
 	kfree(func);

@@ -325,6 +331,12 @@ struct sdio_func *sdio_alloc_func(struct
 
 	device_initialize(&func->dev);
 
+	/*
+	 * We may link to tuples in the card structure,
+	 * we need make sure we have a reference to it.
+	 */
+	get_device(&func->card->dev);
+
 	func->dev.parent = &card->dev;
 	func->dev.bus = &sdio_bus_type;
 	func->dev.release = sdio_release_func;

@@ -378,10 +390,9 @@ int sdio_add_func(struct sdio_func *func
  */
 void sdio_remove_func(struct sdio_func *func)
 {
-	if (!sdio_func_present(func))
-		return;
+	if (sdio_func_present(func))
+		device_del(&func->dev);
 
-	device_del(&func->dev);
 	of_node_put(func->dev.of_node);
 	put_device(&func->dev);
 }

@@ -392,12 +392,6 @@ int sdio_read_func_cis(struct sdio_func
 		return ret;
 
 	/*
-	 * Since we've linked to tuples in the card structure,
-	 * we must make sure we have a reference to it.
-	 */
-	get_device(&func->card->dev);
-
-	/*
 	 * Vendor/device id is optional for function CIS, so
 	 * copy it from the card structure as needed.
 	 */

@@ -422,11 +416,5 @@ void sdio_free_func_cis(struct sdio_func
 	}
 
 	func->tuples = NULL;
-
-	/*
-	 * We have now removed the link to the tuples in the
-	 * card structure, so remove the reference.
-	 */
-	put_device(&func->card->dev);
 }
 

From: Yang Yingliang <[email protected]>

commit cf4c9d2ac1e42c7d18b921bec39486896645b714 upstream.

If mmc_add_host() fails, it doesn't need to call mmc_remove_host(), or it will cause null-ptr-deref, because of deleting a not added device in mmc_remove_host().

To fix this, goto label 'fail_glue_init', if mmc_add_host() fails, and change the label 'fail_add_host' to 'fail_gpiod_request'.

---
 drivers/mmc/host/mmc_spi.c |    8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

@@ -1450,7 +1450,7 @@ static int mmc_spi_probe(struct spi_devi
 
 	status = mmc_add_host(mmc);
 	if (status != 0)
-		goto fail_add_host;
+		goto fail_glue_init;
 
 	/*
 	 * Index 0 is card detect

@@ -1458,7 +1458,7 @@ static int mmc_spi_probe(struct spi_devi
 	 */
 	status = mmc_gpiod_request_cd(mmc, NULL, 0, false, 1000);
 	if (status == -EPROBE_DEFER)
-		goto fail_add_host;
+		goto fail_gpiod_request;
 	if (!status) {
 		/*
 		 * The platform has a CD GPIO signal that may support

@@ -1473,7 +1473,7 @@ static int mmc_spi_probe(struct spi_devi
 	/* Index 1 is write protect/read only */
 	status = mmc_gpiod_request_ro(mmc, NULL, 1, 0);
 	if (status == -EPROBE_DEFER)
-		goto fail_add_host;
+		goto fail_gpiod_request;
 	if (!status)
 		has_ro = true;
 

@@ -1487,7 +1487,7 @@ static int mmc_spi_probe(struct spi_devi
 				? ", cd polling" : "");
 	return 0;
 
-fail_add_host:
+fail_gpiod_request:
 	mmc_remove_host(mmc);
 fail_glue_init:
 	mmc_spi_dma_free(host);

From: Russell King (Oracle) <[email protected]>

[ Upstream commit 560181d3ace61825f4ca9dd3481d6c0ee6709fa8 ]

If dev_set_name() fails, we leak nvmem->wp_gpio as the cleanup does not put this. While a minimal fix for this would be to add the gpiod_put() call, we can do better if we split device_register(), and use the tested nvmem_release() cleanup code by initialising the device early, and putting the device.

This results in a slightly larger fix, but results in clear code.

Note: this patch depends on "nvmem: core: initialise nvmem->id early" and "nvmem: core: remove nvmem_config wp_gpio".

Stable-dep-of: ab3428cfd9aa ("nvmem: core: fix registration vs use race")

---
 drivers/nvmem/core.c | 22 ++++++++++------------
 1 file changed, 10 insertions(+), 12 deletions(-)

index 38c05fce7d740..de356cdde4ce8 100644
@@ -627,14 +627,18 @@ struct nvmem_device *nvmem_register(const struct nvmem_config *config)
 
 	nvmem->id = rval;
 
+	nvmem->dev.type = &nvmem_provider_type;
+	nvmem->dev.bus = &nvmem_bus_type;
+	nvmem->dev.parent = config->dev;
+
+	device_initialize(&nvmem->dev);
+
 	if (!config->ignore_wp)
 		nvmem->wp_gpio = gpiod_get_optional(config->dev, "wp",
 						    GPIOD_OUT_HIGH);
 	if (IS_ERR(nvmem->wp_gpio)) {
-		ida_free(&nvmem_ida, nvmem->id);
 		rval = PTR_ERR(nvmem->wp_gpio);
-		kfree(nvmem);
-		return ERR_PTR(rval);
+		goto err_put_device;
 	}
 
 	kref_init(&nvmem->refcnt);

@@ -646,9 +650,6 @@ struct nvmem_device *nvmem_register(const struct nvmem_config *config)
 	nvmem->stride = config->stride ?: 1;
 	nvmem->word_size = config->word_size ?: 1;
 	nvmem->size = config->size;
-	nvmem->dev.type = &nvmem_provider_type;
-	nvmem->dev.bus = &nvmem_bus_type;
-	nvmem->dev.parent = config->dev;
 	nvmem->root_only = config->root_only;
 	nvmem->priv = config->priv;
 	nvmem->type = config->type;

@@ -671,11 +672,8 @@ struct nvmem_device *nvmem_register(const struct nvmem_config *config)
 		break;
 	}
 
-	if (rval) {
-		ida_free(&nvmem_ida, nvmem->id);
-		kfree(nvmem);
-		return ERR_PTR(rval);
-	}
+	if (rval)
+		goto err_put_device;
 
 	nvmem->read_only = device_property_present(config->dev, "read-only") ||
 			   config->read_only || !nvmem->reg_write;

@@ -686,7 +684,7 @@ struct nvmem_device *nvmem_register(const struct nvmem_config *config)
 
 	dev_dbg(&nvmem->dev, "Registering nvmem device %s\n", config->name);
 
-	rval = device_register(&nvmem->dev);
+	rval = device_add(&nvmem->dev);
 	if (rval)
 		goto err_put_device;
 

2.39.0

From: Raviteja Goud Talla <[email protected]>

[ Upstream commit 67b858dd89932086ae0ee2d0ce4dd070a2c88bb3 ]

Bspec page says "Reset: BUS", Accordingly moving w/a's:
Wa_1407352427,Wa_1406680159 to proper function icl_gt_workarounds_init() Which will resolve guc enabling error

v2:
- Previous patch rev2 was created by email client which caused the Build failure, This v2 is to resolve the previous broken series

Stable-dep-of: d5a1224aa68c ("drm/i915/gen11: Wa_1408615072/Wa_1407596294 should be on GT list")

---
 drivers/gpu/drm/i915/gt/intel_workarounds.c | 18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

index 4a3bde7c9f217..5c92789504d01 100644
@@ -1212,6 +1212,15 @@ icl_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal)
 		    GAMT_CHKN_BIT_REG,
 		    GAMT_CHKN_DISABLE_L3_COH_PIPE);
 
+	/* Wa_1407352427:icl,ehl */
+	wa_write_or(wal, UNSLICE_UNIT_LEVEL_CLKGATE2,
+		    PSDUNIT_CLKGATE_DIS);
+
+	/* Wa_1406680159:icl,ehl */
+	wa_write_or(wal,
+		    SUBSLICE_UNIT_LEVEL_CLKGATE,
+		    GWUNIT_CLKGATE_DIS);
+
 	/* Wa_1607087056:icl,ehl,jsl */
 	if (IS_ICELAKE(i915) ||
 	    IS_EHL_REVID(i915, EHL_REVID_A0, EHL_REVID_A0)) {

@@ -1823,15 +1832,6 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal)
 		wa_write_or(wal, UNSLICE_UNIT_LEVEL_CLKGATE,
 			    VSUNIT_CLKGATE_DIS | HSUNIT_CLKGATE_DIS);
 
-		/* Wa_1407352427:icl,ehl */
-		wa_write_or(wal, UNSLICE_UNIT_LEVEL_CLKGATE2,
-			    PSDUNIT_CLKGATE_DIS);
-
-		/* Wa_1406680159:icl,ehl */
-		wa_write_or(wal,
-			    SUBSLICE_UNIT_LEVEL_CLKGATE,
-			    GWUNIT_CLKGATE_DIS);
-
 		/*
 		 * Wa_1408767742:icl[a2..forever],ehl[all]
 		 * Wa_1605460711:icl[a0..c0]

2.39.0

From: Dan Carpenter <[email protected]>

commit 9cec2aaffe969f2a3e18b5ec105fc20bb908e475 upstream.

The > needs be >= to prevent an out of bounds access.

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

@@ -407,7 +407,7 @@ static void htb_activate_prios(struct ht
 		while (m) {
 			unsigned int prio = ffz(~m);
 
-			if (WARN_ON_ONCE(prio > ARRAY_SIZE(p->inner.clprio)))
+			if (WARN_ON_ONCE(prio >= ARRAY_SIZE(p->inner.clprio)))
 				break;
 			m &= ~(1 << prio);
 

From: Russell King (Oracle) <[email protected]>

commit 0c4862b1c1465e473bc961a02765490578bf5c20 upstream.

Dan Carpenter points out that the return code was not set in commit 60c8b4aebd8e ("nvmem: core: fix cleanup after dev_set_name()"), but this is not the only issue - we also need to zero wp_gpio to prevent gpiod_put() being called on an error value.

---
 drivers/nvmem/core.c |    1 +
 1 file changed, 1 insertion(+)

@@ -638,6 +638,7 @@ struct nvmem_device *nvmem_register(cons
 						    GPIOD_OUT_HIGH);
 	if (IS_ERR(nvmem->wp_gpio)) {
 		rval = PTR_ERR(nvmem->wp_gpio);
+		nvmem->wp_gpio = NULL;
 		goto err_put_device;
 	}
 

From: Matt Roper <[email protected]>

[ Upstream commit d5a1224aa68c8b124a4c5c390186e571815ed390 ]

The UNSLICE_UNIT_LEVEL_CLKGATE register programmed by this workaround has 'BUS' style reset, indicating that it does not lose its value on engine resets. Furthermore, this register is part of the GT forcewake domain rather than the RENDER domain, so it should not be impacted by RCS engine resets. As such, we should implement this on the GT workaround list rather than an engine list.

Bspec: 19219

---
 drivers/gpu/drm/i915/gt/intel_workarounds.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

index 5c92789504d01..ae5cf2b55e159 100644
@@ -1212,6 +1212,13 @@ icl_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal)
 		    GAMT_CHKN_BIT_REG,
 		    GAMT_CHKN_DISABLE_L3_COH_PIPE);
 
+	/*
+	 * Wa_1408615072:icl,ehl  (vsunit)
+	 * Wa_1407596294:icl,ehl  (hsunit)
+	 */
+	wa_write_or(wal, UNSLICE_UNIT_LEVEL_CLKGATE,
+		    VSUNIT_CLKGATE_DIS | HSUNIT_CLKGATE_DIS);
+
 	/* Wa_1407352427:icl,ehl */
 	wa_write_or(wal, UNSLICE_UNIT_LEVEL_CLKGATE2,
 		    PSDUNIT_CLKGATE_DIS);

@@ -1825,13 +1832,6 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal)
 		wa_masked_en(wal, GEN9_CSFE_CHICKEN1_RCS,
 			     GEN11_ENABLE_32_PLANE_MODE);
 
-		/*
-		 * Wa_1408615072:icl,ehl  (vsunit)
-		 * Wa_1407596294:icl,ehl  (hsunit)
-		 */
-		wa_write_or(wal, UNSLICE_UNIT_LEVEL_CLKGATE,
-			    VSUNIT_CLKGATE_DIS | HSUNIT_CLKGATE_DIS);
-
 		/*
 		 * Wa_1408767742:icl[a2..forever],ehl[all]
 		 * Wa_1605460711:icl[a0..c0]

2.39.0

From: Baowen Zheng <[email protected]>

[ Upstream commit 40bd094d65fc9f83941b024cde7c24516f036879 ]

Fill flags to action structure to allow user control if the action should be offloaded to hardware or not.

Stable-dep-of: 21c167aa0ba9 ("net/sched: act_ctinfo: use percpu stats")

---
 net/sched/act_bpf.c      | 2 +-
 net/sched/act_connmark.c | 2 +-
 net/sched/act_ctinfo.c   | 2 +-
 net/sched/act_gate.c     | 2 +-
 net/sched/act_ife.c      | 2 +-
 net/sched/act_ipt.c      | 2 +-
 net/sched/act_mpls.c     | 2 +-
 net/sched/act_nat.c      | 2 +-
 net/sched/act_pedit.c    | 2 +-
 net/sched/act_police.c   | 2 +-
 net/sched/act_sample.c   | 2 +-
 net/sched/act_simple.c   | 2 +-
 net/sched/act_skbedit.c  | 2 +-
 net/sched/act_skbmod.c   | 2 +-
 14 files changed, 14 insertions(+), 14 deletions(-)

index a4c7ba35a3438..78f1cd70c8d19 100644
@@ -307,7 +307,7 @@ static int tcf_bpf_init(struct net *net, struct nlattr *nla,
 	ret = tcf_idr_check_alloc(tn, &index, act, bind);
 	if (!ret) {
 		ret = tcf_idr_create(tn, index, est, act,
-				     &act_bpf_ops, bind, true, 0);
+				     &act_bpf_ops, bind, true, flags);
 		if (ret < 0) {
 			tcf_idr_cleanup(tn, index);
 			return ret;

index 31d268eedf3f9..b6576a250e851 100644
@@ -124,7 +124,7 @@ static int tcf_connmark_init(struct net *net, struct nlattr *nla,
 	ret = tcf_idr_check_alloc(tn, &index, a, bind);
 	if (!ret) {
 		ret = tcf_idr_create(tn, index, est, a,
-				     &act_connmark_ops, bind, false, 0);
+				     &act_connmark_ops, bind, false, flags);
 		if (ret) {
 			tcf_idr_cleanup(tn, index);
 			return ret;

index 06c74f22ab98b..9bde94e7bb939 100644
@@ -212,7 +212,7 @@ static int tcf_ctinfo_init(struct net *net, struct nlattr *nla,
 	err = tcf_idr_check_alloc(tn, &index, a, bind);
 	if (!err) {
 		ret = tcf_idr_create(tn, index, est, a,
-				     &act_ctinfo_ops, bind, false, 0);
+				     &act_ctinfo_ops, bind, false, flags);
 		if (ret) {
 			tcf_idr_cleanup(tn, index);
 			return ret;

index a78cb79657182..0e7568a06351b 100644
@@ -357,7 +357,7 @@ static int tcf_gate_init(struct net *net, struct nlattr *nla,
 
 	if (!err) {
 		ret = tcf_idr_create(tn, index, est, a,
-				     &act_gate_ops, bind, false, 0);
+				     &act_gate_ops, bind, false, flags);
 		if (ret) {
 			tcf_idr_cleanup(tn, index);
 			return ret;

index a2ddea04183af..99548b2a1bc83 100644
@@ -553,7 +553,7 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla,
 
 	if (!exists) {
 		ret = tcf_idr_create(tn, index, est, a, &act_ife_ops,
-				     bind, true, 0);
+				     bind, true, flags);
 		if (ret) {
 			tcf_idr_cleanup(tn, index);
 			kfree(p);

index 8dc3bec0d3258..080f2952cd536 100644
@@ -144,7 +144,7 @@ static int __tcf_ipt_init(struct net *net, unsigned int id, struct nlattr *nla,
 
 	if (!exists) {
 		ret = tcf_idr_create(tn, index, est, a, ops, bind,
-				     false, 0);
+				     false, flags);
 		if (ret) {
 			tcf_idr_cleanup(tn, index);
 			return ret;

index 09799412b2489..47b963ded4e43 100644
@@ -254,7 +254,7 @@ static int tcf_mpls_init(struct net *net, struct nlattr *nla,
 
 	if (!exists) {
 		ret = tcf_idr_create(tn, index, est, a,
-				     &act_mpls_ops, bind, true, 0);
+				     &act_mpls_ops, bind, true, flags);
 		if (ret) {
 			tcf_idr_cleanup(tn, index);
 			return ret;

index 1ebd2a86d980f..8466dc25fe397 100644
@@ -61,7 +61,7 @@ static int tcf_nat_init(struct net *net, struct nlattr *nla, struct nlattr *est,
 	err = tcf_idr_check_alloc(tn, &index, a, bind);
 	if (!err) {
 		ret = tcf_idr_create(tn, index, est, a,
-				     &act_nat_ops, bind, false, 0);
+				     &act_nat_ops, bind, false, flags);
 		if (ret) {
 			tcf_idr_cleanup(tn, index);
 			return ret;

index 0d5463ddfd62f..db0d3bff19eba 100644
@@ -189,7 +189,7 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla,
 	err = tcf_idr_check_alloc(tn, &index, a, bind);
 	if (!err) {
 		ret = tcf_idr_create(tn, index, est, a,
-				     &act_pedit_ops, bind, false, 0);
+				     &act_pedit_ops, bind, false, flags);
 		if (ret) {
 			tcf_idr_cleanup(tn, index);
 			goto out_free;

index 3807335889590..c30cd3ecb3911 100644
@@ -87,7 +87,7 @@ static int tcf_police_init(struct net *net, struct nlattr *nla,
 
 	if (!exists) {
 		ret = tcf_idr_create(tn, index, NULL, a,
-				     &act_police_ops, bind, true, 0);
+				     &act_police_ops, bind, true, flags);
 		if (ret) {
 			tcf_idr_cleanup(tn, index);
 			return ret;

index 3ebf9ede3cf10..2f0e98bcf4945 100644
@@ -69,7 +69,7 @@ static int tcf_sample_init(struct net *net, struct nlattr *nla,
 
 	if (!exists) {
 		ret = tcf_idr_create(tn, index, est, a,
-				     &act_sample_ops, bind, true, 0);
+				     &act_sample_ops, bind, true, flags);
 		if (ret) {
 			tcf_idr_cleanup(tn, index);
 			return ret;

index a4f3d0f0daa96..b9bbc87a87c5b 100644
@@ -128,7 +128,7 @@ static int tcf_simp_init(struct net *net, struct nlattr *nla,
 
 	if (!exists) {
 		ret = tcf_idr_create(tn, index, est, a,
-				     &act_simp_ops, bind, false, 0);
+				     &act_simp_ops, bind, false, flags);
 		if (ret) {
 			tcf_idr_cleanup(tn, index);
 			return ret;

index e5f3fb8b00e32..a5661f2d93e99 100644
@@ -176,7 +176,7 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla,
 
 	if (!exists) {
 		ret = tcf_idr_create(tn, index, est, a,
-				     &act_skbedit_ops, bind, true, 0);
+				     &act_skbedit_ops, bind, true, act_flags);
 		if (ret) {
 			tcf_idr_cleanup(tn, index);
 			return ret;

index 8d17a543cc9fe..aa98dcac94b95 100644
@@ -147,7 +147,7 @@ static int tcf_skbmod_init(struct net *net, struct nlattr *nla,
 
 	if (!exists) {
 		ret = tcf_idr_create(tn, index, est, a,
-				     &act_skbmod_ops, bind, true, 0);
+				     &act_skbmod_ops, bind, true, flags);
 		if (ret) {
 			tcf_idr_cleanup(tn, index);
 			return ret;

2.39.0

From: Pedro Tammela <[email protected]>

[ Upstream commit 21c167aa0ba943a7cac2f6969814f83bb701666b ]

The tc action act_ctinfo was using shared stats, fix it to use percpu stats since bstats_update() must be called with locks or with a percpu pointer argument.

tdc results:
1..12
ok 1 c826 - Add ctinfo action with default setting
ok 2 0286 - Add ctinfo action with dscp
ok 3 4938 - Add ctinfo action with valid cpmark and zone ok 4 7593 - Add ctinfo action with drop control
ok 5 2961 - Replace ctinfo action zone and action control ok 6 e567 - Delete ctinfo action with valid index
ok 7 6a91 - Delete ctinfo action with invalid index
ok 8 5232 - List ctinfo actions
ok 9 7702 - Flush ctinfo actions
ok 10 3201 - Add ctinfo action with duplicate index
ok 11 8295 - Add ctinfo action with invalid index
ok 12 3964 - Replace ctinfo action with invalid goto_chain control

---
 net/sched/act_ctinfo.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

index 9bde94e7bb939..5aa005835c066 100644
@@ -92,7 +92,7 @@ static int tcf_ctinfo_act(struct sk_buff *skb, const struct tc_action *a,
 	cp = rcu_dereference_bh(ca->params);
 
 	tcf_lastuse_update(&ca->tcf_tm);
-	bstats_update(&ca->tcf_bstats, skb);
+	tcf_action_update_bstats(&ca->common, skb);
 	action = READ_ONCE(ca->tcf_action);
 
 	wlen = skb_network_offset(skb);

@@ -211,8 +211,8 @@ static int tcf_ctinfo_init(struct net *net, struct nlattr *nla,
 	index = actparm->index;
 	err = tcf_idr_check_alloc(tn, &index, a, bind);
 	if (!err) {
-		ret = tcf_idr_create(tn, index, est, a,
-				     &act_ctinfo_ops, bind, false, flags);
+		ret = tcf_idr_create_from_flags(tn, index, est, a,
+						&act_ctinfo_ops, bind, flags);
 		if (ret) {
 			tcf_idr_cleanup(tn, index);
 			return ret;

2.39.0

From: Natalia Petrova <[email protected]>

[ Upstream commit 7fa0b526f865cb42aa33917fd02a92cb03746f4d ]

The result of nlmsg_find_attr() 'br_spec' is dereferenced in nla_for_each_nested(), but it can take NULL value in nla_find() function, which will result in an error.

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

---
 drivers/net/ethernet/intel/i40e/i40e_main.c | 2 ++
 1 file changed, 2 insertions(+)

index c4f4ee34d58a0..9e8a20a94862f 100644
@@ -12520,6 +12520,8 @@ static int i40e_ndo_bridge_setlink(struct net_device *dev,
 	}
 
 	br_spec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_AF_SPEC);
+	if (!br_spec)
+		return -EINVAL;
 
 	nla_for_each_nested(attr, br_spec, rem) {
 		__u16 mode;

2.39.0

From: Pedro Tammela <[email protected]>

[ Upstream commit 42018a322bd453e38b3ffee294982243e50a484f ]

Syzkaller found an issue where a handle greater than 16 bits would trigger a null-ptr-deref in the imperfect hash area update.

general protection fault, probably for non-canonical address
0xdffffc0000000015: 0000 [#1] PREEMPT SMP KASAN
KASAN: null-ptr-deref in range [0x00000000000000a8-0x00000000000000af]
CPU: 0 PID: 5070 Comm: syz-executor456 Not tainted
6.2.0-rc7-syzkaller-00112-gc68f345b7c42 #0
Hardware name: Google Google Compute Engine/Google Compute Engine,
BIOS Google 01/21/2023
RIP: 0010:tcindex_set_parms+0x1a6a/0x2990 net/sched/cls_tcindex.c:509
Code: 01 e9 e9 fe ff ff 4c 8b bd 28 fe ff ff e8 0e 57 7d f9 48 8d bb

a8 00 00 00 48 b8 00 00 00 00 00 fc ff df 48 89 fa 48 c1 ea 03 <80> 3c 02 00 0f 85 94 0c 00 00 48 8b 85 f8 fd ff ff 48 8b 9b a8 00
RSP: 0018:ffffc90003d3ef88 EFLAGS: 00010202
RAX: dffffc0000000000 RBX: 0000000000000000 RCX: 0000000000000000
RDX: 0000000000000015 RSI: ffffffff8803a102 RDI: 00000000000000a8
RBP: ffffc90003d3f1d8 R08: 0000000000000001 R09: 0000000000000000
R10: 0000000000000001 R11: 0000000000000000 R12: ffff88801e2b10a8
R13: dffffc0000000000 R14: 0000000000030000 R15: ffff888017b3be00
FS: 00005555569af300(0000) GS:ffff8880b9800000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 000056041c6d2000 CR3: 000000002bfca000 CR4: 00000000003506f0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400

Call Trace:
<TASK>
tcindex_change+0x1ea/0x320 net/sched/cls_tcindex.c:572
tc_new_tfilter+0x96e/0x2220 net/sched/cls_api.c:2155
rtnetlink_rcv_msg+0x959/0xca0 net/core/rtnetlink.c:6132
netlink_rcv_skb+0x165/0x440 net/netlink/af_netlink.c:2574
netlink_unicast_kernel net/netlink/af_netlink.c:1339 [inline]
netlink_unicast+0x547/0x7f0 net/netlink/af_netlink.c:1365
netlink_sendmsg+0x91b/0xe10 net/netlink/af_netlink.c:1942
sock_sendmsg_nosec net/socket.c:714 [inline]
sock_sendmsg+0xd3/0x120 net/socket.c:734
____sys_sendmsg+0x334/0x8c0 net/socket.c:2476
___sys_sendmsg+0x110/0x1b0 net/socket.c:2530
__sys_sendmmsg+0x18f/0x460 net/socket.c:2616
__do_sys_sendmmsg net/socket.c:2645 [inline]
__se_sys_sendmmsg net/socket.c:2642 [inline]
__x64_sys_sendmmsg+0x9d/0x100 net/socket.c:2642
do_syscall_x64 arch/x86/entry/common.c:50 [inline]
do_syscall_64+0x39/0xb0 arch/x86/entry/common.c:80

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

index 50bf7ec4b5b25..2c0c95204cb5a 100644
@@ -502,7 +502,7 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
 		/* lookup the filter, guaranteed to exist */
 		for (cf = rcu_dereference_bh_rtnl(*fp); cf;
 		     fp = &cf->next, cf = rcu_dereference_bh_rtnl(*fp))
-			if (cf->key == handle)
+			if (cf->key == (u16)handle)
 				break;
 
 		f->next = cf->next;

2.39.0

From: Greg Kroah-Hartman <[email protected]>

commit 2c10b61421a28e95a46ab489fd56c0f442ff6952 upstream.

When calling the KVM_GET_DEBUGREGS ioctl, on some configurations, there might be some unitialized portions of the kvm_debugregs structure that could be copied to userspace. Prevent this as is done in the other kvm ioctls, by setting the whole structure to 0 before copying anything into it.

Bonus is that this reduces the lines of code as the explicit flag setting and reserved space zeroing out can be removed.

Message-Id: <[email protected]>

---
 arch/x86/kvm/x86.c |    3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

@@ -4455,12 +4455,11 @@ static void kvm_vcpu_ioctl_x86_get_debug
 {
 	unsigned long val;
 
+	memset(dbgregs, 0, sizeof(*dbgregs));
 	memcpy(dbgregs->db, vcpu->arch.db, sizeof(vcpu->arch.db));
 	kvm_get_dr(vcpu, 6, &val);
 	dbgregs->dr6 = val;
 	dbgregs->dr7 = vcpu->arch.dr7;
-	dbgregs->flags = 0;
-	memset(&dbgregs->reserved, 0, sizeof(dbgregs->reserved));
 }
 
 static int kvm_vcpu_ioctl_x86_set_debugregs(struct kvm_vcpu *vcpu,

From: Thomas Gleixner <[email protected]>

commit d125d1349abeb46945dc5e98f7824bf688266f13 upstream.

syzbot reported a RCU stall which is caused by setting up an alarmtimer with a very small interval and ignoring the signal. The reproducer arms the alarm timer with a relative expiry of 8ns and an interval of 9ns. Not a problem per se, but that's an issue when the signal is ignored because then the timer is immediately rearmed because there is no way to delay that rearming to the signal delivery path. See posix_timer_fn() and commit 58229a189942 ("posix-timers: Prevent softirq starvation by small intervals and SIG_IGN") for details.

The reproducer does not set SIG_IGN explicitely, but it sets up the timers signal with SIGCONT. That has the same effect as explicitely setting SIG_IGN for a signal as SIGCONT is ignored if there is no handler set and the task is not ptraced.

The log clearly shows that:

[pid 5102] --- SIGCONT {si_signo=SIGCONT, si_code=SI_TIMER, si_timerid=0, si_overrun=316014, si_int=0, si_ptr=NULL} ---

It works because the tasks are traced and therefore the signal is queued so the tracer can see it, which delays the restart of the timer to the signal delivery path. But then the tracer is killed:

[pid 5087] kill(-5102, SIGKILL <unfinished ...>
...
./strace-static-x86_64: Process 5107 detached

and after it's gone the stall can be observed:

syzkaller login: [ 79.439102][ C0] hrtimer: interrupt took 68471 ns

   [  184.460538][    C1] rcu: INFO: rcu_preempt detected stalls on CPUs/tasks:
   ...
   [  184.658237][    C1] rcu: Stack dump where RCU GP kthread last ran:
   [  184.664574][    C1] Sending NMI from CPU 1 to CPUs 0:
   [  184.669821][    C0] NMI backtrace for cpu 0
   [  184.669831][    C0] CPU: 0 PID: 5108 Comm: syz-executor192 Not tainted 6.2.0-rc6-next-20230203-syzkaller #0
   ...
   [  184.670036][    C0] Call Trace:
   [  184.670041][    C0]  <IRQ>
   [  184.670045][    C0]  alarmtimer_fired+0x327/0x670

posix_timer_fn() prevents that by checking whether the interval for timers which have the signal ignored is smaller than a jiffie and artifically delay it by shifting the next expiry out by a jiffie. That's accurate vs. the overrun accounting, but slightly inaccurate vs. timer_gettimer(2).

The comment in that function says what needs to be done and there was a fix available for the regular userspace induced SIG_IGN mechanism, but that did not work due to the implicit ignore for SIGCONT and similar signals. This needs to be worked on, but for now the only available workaround is to do exactly what posix_timer_fn() does:

Increase the interval of self-rearming timers, which have their signal ignored, to at least a jiffie.

Interestingly this has been fixed before via commit ff86bf0c65f1 ("alarmtimer: Rate limit periodic intervals") already, but that fix got lost in a later rework.

---
 kernel/time/alarmtimer.c |   33 +++++++++++++++++++++++++++++----
 1 file changed, 29 insertions(+), 4 deletions(-)

@@ -470,11 +470,35 @@ u64 alarm_forward(struct alarm *alarm, k
 }
 EXPORT_SYMBOL_GPL(alarm_forward);
 
-u64 alarm_forward_now(struct alarm *alarm, ktime_t interval)
+static u64 __alarm_forward_now(struct alarm *alarm, ktime_t interval, bool throttle)
 {
 	struct alarm_base *base = &alarm_bases[alarm->type];
+	ktime_t now = base->get_ktime();
+
+	if (IS_ENABLED(CONFIG_HIGH_RES_TIMERS) && throttle) {
+		/*
+		 * Same issue as with posix_timer_fn(). Timers which are
+		 * periodic but the signal is ignored can starve the system
+		 * with a very small interval. The real fix which was
+		 * promised in the context of posix_timer_fn() never
+		 * materialized, but someone should really work on it.
+		 *
+		 * To prevent DOS fake @now to be 1 jiffie out which keeps
+		 * the overrun accounting correct but creates an
+		 * inconsistency vs. timer_gettime(2).
+		 */
+		ktime_t kj = NSEC_PER_SEC / HZ;
+
+		if (interval < kj)
+			now = ktime_add(now, kj);
+	}
+
+	return alarm_forward(alarm, now, interval);
+}
 
-	return alarm_forward(alarm, base->get_ktime(), interval);
+u64 alarm_forward_now(struct alarm *alarm, ktime_t interval)
+{
+	return __alarm_forward_now(alarm, interval, false);
 }
 EXPORT_SYMBOL_GPL(alarm_forward_now);
 

@@ -548,9 +572,10 @@ static enum alarmtimer_restart alarm_han
 	if (posix_timer_event(ptr, si_private) && ptr->it_interval) {
 		/*
 		 * Handle ignored signals and rearm the timer. This will go
-		 * away once we handle ignored signals proper.
+		 * away once we handle ignored signals proper. Ensure that
+		 * small intervals cannot starve the system.
 		 */
-		ptr->it_overrun += alarm_forward_now(alarm, ptr->it_interval);
+		ptr->it_overrun += __alarm_forward_now(alarm, ptr->it_interval, true);
 		++ptr->it_requeue_pending;
 		ptr->it_active = 1;
 		result = ALARMTIMER_RESTART;

From: Pierre-Louis Bossart <[email protected]>

commit 1f810d2b6b2fbdc5279644d8b2c140b1f7c9d43d upstream.

The HDaudio stream allocation is done first, and in a second step the LOSIDV parameter is programmed for the multi-link used by a codec.

This leads to a possible stream_tag leak, e.g. if a DisplayAudio link is not used. This would happen when a non-Intel graphics card is used and userspace unconditionally uses the Intel Display Audio PCMs without checking if they are connected to a receiver with jack controls.

We should first check that there is a valid multi-link entry to configure before allocating a stream_tag. This change aligns the dma_assign and dma_cleanup phases.

Complements: b0cd60f3e9f5 ("ALSA/ASoC: hda: clarify bus_get_link() and bus_link_get() helpers")

---
 sound/soc/sof/intel/hda-dai.c |    8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

@@ -212,6 +212,10 @@ static int hda_link_hw_params(struct snd
 	int stream_tag;
 	int ret;
 
+	link = snd_hdac_ext_bus_get_link(bus, codec_dai->component->name);
+	if (!link)
+		return -EINVAL;
+
 	/* get stored dma data if resuming from system suspend */
 	link_dev = snd_soc_dai_get_dma_data(dai, substream);
 	if (!link_dev) {

@@ -232,10 +236,6 @@ static int hda_link_hw_params(struct snd
 	if (ret < 0)
 		return ret;
 
-	link = snd_hdac_ext_bus_get_link(bus, codec_dai->component->name);
-	if (!link)
-		return -EINVAL;
-
 	/* set the hdac_stream in the codec dai */
 	snd_soc_dai_set_stream(codec_dai, hdac_stream(link_dev), substream->stream);
 

From: Ryusuke Konishi <[email protected]>

commit 99b9402a36f0799f25feee4465bfa4b8dfa74b4d upstream.

Macro NILFS_SB2_OFFSET_BYTES, which computes the position of the second superblock, underflows when the argument device size is less than 4096 bytes. Therefore, when using this macro, it is necessary to check in advance that the device size is not less than a lower limit, or at least that underflow does not occur.

The current nilfs2 implementation lacks this check, causing out-of-bound block access when mounting devices smaller than 4096 bytes:

I/O error, dev loop0, sector 36028797018963960 op 0x0:(READ) flags 0x0 phys_seg 1 prio class 2
NILFS (loop0): unable to read secondary superblock (blocksize = 1024)

In addition, when trying to resize the filesystem to a size below 4096 bytes, this underflow occurs in nilfs_resize_fs(), passing a huge number of segments to nilfs_sufile_resize(), corrupting parameters such as the number of segments in superblocks. This causes excessive loop iterations in nilfs_sufile_resize() during a subsequent resize ioctl, causing semaphore ns_segctor_sem to block for a long time and hang the writer thread:

 INFO: task segctord:5067 blocked for more than 143 seconds.
      Not tainted 6.2.0-rc8-syzkaller-00015-gf6feea56f66d #0
 "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
 task:segctord        state:D stack:23456 pid:5067  ppid:2
 flags:0x00004000
 Call Trace:
  <TASK>
  context_switch kernel/sched/core.c:5293 [inline]
  __schedule+0x1409/0x43f0 kernel/sched/core.c:6606
  schedule+0xc3/0x190 kernel/sched/core.c:6682
  rwsem_down_write_slowpath+0xfcf/0x14a0 kernel/locking/rwsem.c:1190
  nilfs_transaction_lock+0x25c/0x4f0 fs/nilfs2/segment.c:357
  nilfs_segctor_thread_construct fs/nilfs2/segment.c:2486 [inline]
  nilfs_segctor_thread+0x52f/0x1140 fs/nilfs2/segment.c:2570
  kthread+0x270/0x300 kernel/kthread.c:376
  ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:308
  </TASK>
 ...
 Call Trace:
  <TASK>
  folio_mark_accessed+0x51c/0xf00 mm/swap.c:515
  __nilfs_get_page_block fs/nilfs2/page.c:42 [inline]
  nilfs_grab_buffer+0x3d3/0x540 fs/nilfs2/page.c:61
  nilfs_mdt_submit_block+0xd7/0x8f0 fs/nilfs2/mdt.c:121
  nilfs_mdt_read_block+0xeb/0x430 fs/nilfs2/mdt.c:176
  nilfs_mdt_get_block+0x12d/0xbb0 fs/nilfs2/mdt.c:251
  nilfs_sufile_get_segment_usage_block fs/nilfs2/sufile.c:92 [inline]
  nilfs_sufile_truncate_range fs/nilfs2/sufile.c:679 [inline]
  nilfs_sufile_resize+0x7a3/0x12b0 fs/nilfs2/sufile.c:777
  nilfs_resize_fs+0x20c/0xed0 fs/nilfs2/super.c:422
  nilfs_ioctl_resize fs/nilfs2/ioctl.c:1033 [inline]
  nilfs_ioctl+0x137c/0x2440 fs/nilfs2/ioctl.c:1301
  ...

This fixes these issues by inserting appropriate minimum device size checks or anti-underflow checks, depending on where the macro is used.

---
 fs/nilfs2/ioctl.c     |    7 +++++++
 fs/nilfs2/super.c     |    9 +++++++++
 fs/nilfs2/the_nilfs.c |    8 +++++++-
 3 files changed, 23 insertions(+), 1 deletion(-)

@@ -1129,7 +1129,14 @@ static int nilfs_ioctl_set_alloc_range(s
 
 	minseg = range[0] + segbytes - 1;
 	do_div(minseg, segbytes);
+
+	if (range[1] < 4096)
+		goto out;
+
 	maxseg = NILFS_SB2_OFFSET_BYTES(range[1]);
+	if (maxseg < segbytes)
+		goto out;
+
 	do_div(maxseg, segbytes);
 	maxseg--;
 

@@ -409,6 +409,15 @@ int nilfs_resize_fs(struct super_block *
 		goto out;
 
 	/*
+	 * Prevent underflow in second superblock position calculation.
+	 * The exact minimum size check is done in nilfs_sufile_resize().
+	 */
+	if (newsize < 4096) {
+		ret = -ENOSPC;
+		goto out;
+	}
+
+	/*
 	 * Write lock is required to protect some functions depending
 	 * on the number of segments, the number of reserved segments,
 	 * and so forth.

@@ -544,9 +544,15 @@ static int nilfs_load_super_block(struct
 {
 	struct nilfs_super_block **sbp = nilfs->ns_sbp;
 	struct buffer_head **sbh = nilfs->ns_sbh;
-	u64 sb2off = NILFS_SB2_OFFSET_BYTES(nilfs->ns_bdev->bd_inode->i_size);
+	u64 sb2off, devsize = nilfs->ns_bdev->bd_inode->i_size;
 	int valid[2], swp = 0;
 
+	if (devsize < NILFS_SEG_MIN_BLOCKS * NILFS_MIN_BLOCK_SIZE + 4096) {
+		nilfs_err(sb, "device size too small");
+		return -EINVAL;
+	}
+	sb2off = NILFS_SB2_OFFSET_BYTES(devsize);
+
 	sbp[0] = nilfs_read_super_block(sb, NILFS_SB_OFFSET_BYTES, blocksize,
 					&sbh[0]);
 	sbp[1] = nilfs_read_super_block(sb, sb2off, blocksize, &sbh[1]);

Hi!

CIP testing did not find any problems here:

https://gitlab.com/cip-project/cip-testing/linux-stable-rc-ci/-/tree/linux-5.10.y

Best regards,
Pavel

DENX Software Engineering GmbH,      Managing Director: Wolfgang Denk
HRB 165235 Munich, Office: Kirchenstr.5, D-82194 Groebenzell, Germany

Results from Linaro’s test farm.
No regressions on arm64, arm, x86_64, and i386.

## Build
* kernel: 5.10.169-rc1
* git: https://gitlab.com/Linaro/lkft/mirrors/stable/linux-stable-rc
* git branch: linux-5.10.y
* git commit: 7d11e4c4fc56eb25c5b41da93748dbcf21956316
* git describe: v5.10.168-58-g7d11e4c4fc56
* test details:
https://qa-reports.linaro.org/lkft/linux-stable-rc-linux-5.10.y/build/v5.10.168-58-g7d11e4c4fc56

## Test Regressions (compared to v5.10.168)

## Metric Regressions (compared to v5.10.168)

## Test Fixes (compared to v5.10.168)

## Metric Fixes (compared to v5.10.168)

## Test result summary
total: 156525, pass: 130423, fail: 3439, skip: 22346, xfail: 317

## Build Summary
* arc: 5 total, 5 passed, 0 failed
* arm: 149 total, 148 passed, 1 failed
* arm64: 49 total, 46 passed, 3 failed
* i386: 39 total, 37 passed, 2 failed
* mips: 31 total, 29 passed, 2 failed
* parisc: 8 total, 8 passed, 0 failed
* powerpc: 32 total, 25 passed, 7 failed
* riscv: 16 total, 11 passed, 5 failed
* s390: 16 total, 16 passed, 0 failed
* sh: 14 total, 12 passed, 2 failed
* sparc: 8 total, 8 passed, 0 failed
* x86_64: 42 total, 40 passed, 2 failed

## Test suites summary
* boot
* fwts
* igt-gpu-tools
* kselftest-android
* kselftest-arm64
* kselftest-breakpoints
* kselftest-capabilities
* kselftest-cgroup
* kselftest-clone3
* kselftest-core
* kselftest-cpu-hotplug
* kselftest-cpufreq
* kselftest-drivers-dma-buf
* kselftest-efivarfs
* kselftest-filesystems
* kselftest-filesystems-binderfs
* kselftest-firmware
* kselftest-fpu
* kselftest-futex
* kselftest-gpio
* kselftest-intel_pstate
* kselftest-ipc
* kselftest-ir
* kselftest-kcmp
* kselftest-kexec
* kselftest-kvm
* kselftest-lib
* kselftest-livepatch
* kselftest-membarrier
* kselftest-memfd
* kselftest-memory-hotplug
* kselftest-mincore
* kselftest-mount
* kselftest-mqueue
* kselftest-net
* kselftest-net-forwarding
* kselftest-net-mptcp
* kselftest-netfilter
* kselftest-nsfs
* kselftest-openat2
* kselftest-pid_namespace
* kselftest-pidfd
* kselftest-proc
* kselftest-pstore
* kselftest-ptrace
* kselftest-rseq
* kselftest-rtc
* kselftest-seccomp
* kselftest-tc-testing
* kselftest-timens
* kselftest-timers
* kselftest-tmpfs
* kselftest-tpm2
* kselftest-user
* kselftest-vm
* kselftest-x86
* kselftest-zram
* kunit
* kvm-unit-tests
* libgpiod
* libhugetlbfs
* log-parser-boot
* log-parser-test
* ltp-cap_bounds
* ltp-commands
* ltp-containers
* ltp-controllers
* ltp-cpuhotplug
* ltp-crypto
* ltp-cve
* ltp-dio
* ltp-fcntl-locktests
* ltp-filecaps
* ltp-fs
* ltp-fs_bind
* ltp-fs_perms_simple
* ltp-fsx
* ltp-hugetlb
* ltp-io
* ltp-ipc
* ltp-math
* ltp-mm
* ltp-nptl
* ltp-open-posix-tests
* ltp-pty
* ltp-sched
* ltp-securebits
* ltp-smoke
* ltp-syscalls
* ltp-tracing
* network-basic-tests
* packetdrill
* perf
* rcutorture
* v4l2-compliance
* vdso

--
Linaro LKFT
https://lkft.linaro.org

All tests passing for Tegra ...

Test results for stable-v5.10:

    11 builds:	11 pass, 0 fail
    28 boots:	28 pass, 0 fail
    75 tests:	75 pass, 0 fail

Linux version: 5.10.169-rc1-g7d11e4c4fc56
Boards tested: tegra124-jetson-tk1, tegra186-p2771-0000,

                tegra194-p2972-0000, tegra194-p3509-0000+p3668-0000,
                tegra20-ventana, tegra210-p2371-2180,
                tegra210-p3450-0000, tegra30-cardhu-a04

Jon

Hi Greg,

Build test (gcc version 11.3.1 20230210):
mips: 63 configs -> no failure
arm: 104 configs -> no failure
arm64: 3 configs -> no failure
x86_64: 4 configs -> no failure alpha allmodconfig -> no failure powerpc allmodconfig -> no failure riscv allmodconfig -> no failure s390 allmodconfig -> no failure xtensa allmodconfig -> no failure

Boot test:
x86_64: Booted on my test laptop. No regression.
x86_64: Booted on qemu. No regression. [1]
arm64: Booted on rpi4b (4GB model). No regression. [2]

[1]. https://openqa.qa.codethink.co.uk/tests/2906
[2]. https://openqa.qa.codethink.co.uk/tests/2909

Regards
Sudip

Build results:

	total: 162 pass: 162 fail: 0
Qemu test results:
	total: 478 pass: 478 fail: 0

Guenter