6.1.64-rc1 review

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

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

From: Dan Williams <[email protected]>

[ Upstream commit 7592d935b7ae71e2b4ff93830743c39a9d13d113 ]

tl;dr: Clean up an unnecessary export and enable cxl_test.

An RCD (Restricted CXL Device), in contrast to a typical CXL device in a VH topology, obtains its component registers from the bottom half of the associated CXL host bridge RCRB (Root Complex Register Block). In turn this means that cxl_rcrb_to_component() needs to be called from devm_cxl_add_endpoint().

Presently devm_cxl_add_endpoint() is part of the CXL core, but the only user is the CXL mem module. Move it from cxl_core to cxl_mem to not only get rid of an unnecessary export, but to also enable its call out to cxl_rcrb_to_component(), in a subsequent patch, to be mocked by cxl_test. Recall that cxl_test can only mock exported symbols, and since cxl_rcrb_to_component() is itself inside the core, all callers must be outside of cxl_core to allow cxl_test to mock it.

Stable-dep-of: 98a04c7aced2 ("cxl/region: Fix x1 root-decoder granularity calculations")

---
 drivers/cxl/core/core.h |  8 --------
 drivers/cxl/core/port.c | 39 ---------------------------------------
 drivers/cxl/cxl.h       |  2 --
 drivers/cxl/cxlmem.h    |  9 +++++++++
 drivers/cxl/mem.c       | 38 ++++++++++++++++++++++++++++++++++++++
 5 files changed, 47 insertions(+), 49 deletions(-)

index 1d8f87be283fb..8c04672dca563 100644
@@ -58,14 +58,6 @@ extern struct rw_semaphore cxl_dpa_rwsem;
 
 bool is_switch_decoder(struct device *dev);
 struct cxl_switch_decoder *to_cxl_switch_decoder(struct device *dev);
-static inline struct cxl_ep *cxl_ep_load(struct cxl_port *port,
-					 struct cxl_memdev *cxlmd)
-{
-	if (!port)
-		return NULL;
-
-	return xa_load(&port->endpoints, (unsigned long)&cxlmd->dev);
-}
 
 int cxl_memdev_init(void);
 void cxl_memdev_exit(void);

index 93560d749aed8..585c2b43c7c7f 100644
@@ -1151,45 +1151,6 @@ static void reap_dports(struct cxl_port *port)
 	}
 }
 
-int devm_cxl_add_endpoint(struct cxl_memdev *cxlmd,
-			  struct cxl_dport *parent_dport)
-{
-	struct cxl_port *parent_port = parent_dport->port;
-	struct cxl_dev_state *cxlds = cxlmd->cxlds;
-	struct cxl_port *endpoint, *iter, *down;
-	int rc;
-
-	/*
-	 * Now that the path to the root is established record all the
-	 * intervening ports in the chain.
-	 */
-	for (iter = parent_port, down = NULL; !is_cxl_root(iter);
-	     down = iter, iter = to_cxl_port(iter->dev.parent)) {
-		struct cxl_ep *ep;
-
-		ep = cxl_ep_load(iter, cxlmd);
-		ep->next = down;
-	}
-
-	endpoint = devm_cxl_add_port(&parent_port->dev, &cxlmd->dev,
-				     cxlds->component_reg_phys, parent_dport);
-	if (IS_ERR(endpoint))
-		return PTR_ERR(endpoint);
-
-	rc = cxl_endpoint_autoremove(cxlmd, endpoint);
-	if (rc)
-		return rc;
-
-	if (!endpoint->dev.driver) {
-		dev_err(&cxlmd->dev, "%s failed probe\n",
-			dev_name(&endpoint->dev));
-		return -ENXIO;
-	}
-
-	return 0;
-}
-EXPORT_SYMBOL_NS_GPL(devm_cxl_add_endpoint, CXL);
-
 static void cxl_detach_ep(void *data)
 {
 	struct cxl_memdev *cxlmd = data;

index ac75554b5d763..8787ef1e64047 100644
@@ -562,8 +562,6 @@ struct pci_bus *cxl_port_to_pci_bus(struct cxl_port *port);
 struct cxl_port *devm_cxl_add_port(struct device *host, struct device *uport,
 				   resource_size_t component_reg_phys,
 				   struct cxl_dport *parent_dport);
-int devm_cxl_add_endpoint(struct cxl_memdev *cxlmd,
-			  struct cxl_dport *parent_dport);
 struct cxl_port *find_cxl_root(struct device *dev);
 int devm_cxl_enumerate_ports(struct cxl_memdev *cxlmd);
 int cxl_bus_rescan(void);

index 88e3a8e54b6a4..7e50b4e93ee53 100644
@@ -76,6 +76,15 @@ static inline bool is_cxl_endpoint(struct cxl_port *port)
 
 struct cxl_memdev *devm_cxl_add_memdev(struct cxl_dev_state *cxlds);
 
+static inline struct cxl_ep *cxl_ep_load(struct cxl_port *port,
+					 struct cxl_memdev *cxlmd)
+{
+	if (!port)
+		return NULL;
+
+	return xa_load(&port->endpoints, (unsigned long)&cxlmd->dev);
+}
+
 /**
  * struct cxl_mbox_cmd - A command to be submitted to hardware.
  * @opcode: (input) The command set and command submitted to hardware.

index 64ccf053d32c3..80263d12a8541 100644
@@ -45,6 +45,44 @@ static int cxl_mem_dpa_show(struct seq_file *file, void *data)
 	return 0;
 }
 
+static int devm_cxl_add_endpoint(struct cxl_memdev *cxlmd,
+				 struct cxl_dport *parent_dport)
+{
+	struct cxl_port *parent_port = parent_dport->port;
+	struct cxl_dev_state *cxlds = cxlmd->cxlds;
+	struct cxl_port *endpoint, *iter, *down;
+	int rc;
+
+	/*
+	 * Now that the path to the root is established record all the
+	 * intervening ports in the chain.
+	 */
+	for (iter = parent_port, down = NULL; !is_cxl_root(iter);
+	     down = iter, iter = to_cxl_port(iter->dev.parent)) {
+		struct cxl_ep *ep;
+
+		ep = cxl_ep_load(iter, cxlmd);
+		ep->next = down;
+	}
+
+	endpoint = devm_cxl_add_port(&parent_port->dev, &cxlmd->dev,
+				     cxlds->component_reg_phys, parent_dport);
+	if (IS_ERR(endpoint))
+		return PTR_ERR(endpoint);
+
+	rc = cxl_endpoint_autoremove(cxlmd, endpoint);
+	if (rc)
+		return rc;
+
+	if (!endpoint->dev.driver) {
+		dev_err(&cxlmd->dev, "%s failed probe\n",
+			dev_name(&endpoint->dev));
+		return -ENXIO;
+	}
+
+	return 0;
+}
+
 static int cxl_mem_probe(struct device *dev)
 {
 	struct cxl_memdev *cxlmd = to_cxl_memdev(dev);

2.42.0

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

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

From: Dan Williams <[email protected]>

[ Upstream commit 3d8f7ccaa611a743ae3a1e6f605346993d37c513 ]

Take two endpoints attached to the first switch on the first host-bridge in the cxl_test topology and define a pre-initialized region. This is a x2 interleave underneath a x1 CXL Window.

$ modprobe cxl_test
$ # cxl list -Ru
{
  "region":"region3",
  "resource":"0xf010000000",
  "size":"512.00 MiB (536.87 MB)",
  "interleave_ways":2,
  "interleave_granularity":4096,
  "decode_state":"commit"
}

Stable-dep-of: 98a04c7aced2 ("cxl/region: Fix x1 root-decoder granularity calculations")

---
 drivers/cxl/core/core.h      |   3 -
 drivers/cxl/core/hdm.c       |   3 +-
 drivers/cxl/core/port.c      |   2 +
 drivers/cxl/cxl.h            |   2 +
 drivers/cxl/cxlmem.h         |   3 +
 tools/testing/cxl/test/cxl.c | 147 ++++++++++++++++++++++++++++++++---
 6 files changed, 146 insertions(+), 14 deletions(-)

index 8c04672dca563..cbee2340f1bce 100644
@@ -56,9 +56,6 @@ resource_size_t cxl_dpa_size(struct cxl_endpoint_decoder *cxled);
 resource_size_t cxl_dpa_resource_start(struct cxl_endpoint_decoder *cxled);
 extern struct rw_semaphore cxl_dpa_rwsem;
 
-bool is_switch_decoder(struct device *dev);
-struct cxl_switch_decoder *to_cxl_switch_decoder(struct device *dev);
-
 int cxl_memdev_init(void);
 void cxl_memdev_exit(void);
 void cxl_mbox_init(void);

index 5aa0726aafe6f..8c1db4e1b816d 100644
@@ -276,7 +276,7 @@ static int __cxl_dpa_reserve(struct cxl_endpoint_decoder *cxled,
 	return 0;
 }
 
-static int devm_cxl_dpa_reserve(struct cxl_endpoint_decoder *cxled,
+int devm_cxl_dpa_reserve(struct cxl_endpoint_decoder *cxled,
 				resource_size_t base, resource_size_t len,
 				resource_size_t skipped)
 {

@@ -292,6 +292,7 @@ static int devm_cxl_dpa_reserve(struct cxl_endpoint_decoder *cxled,
 
 	return devm_add_action_or_reset(&port->dev, cxl_dpa_release, cxled);
 }
+EXPORT_SYMBOL_NS_GPL(devm_cxl_dpa_reserve, CXL);
 
 resource_size_t cxl_dpa_size(struct cxl_endpoint_decoder *cxled)
 {

index 585c2b43c7c7f..9de8336d76379 100644
@@ -455,6 +455,7 @@ bool is_switch_decoder(struct device *dev)
 {
 	return is_root_decoder(dev) || dev->type == &cxl_decoder_switch_type;
 }
+EXPORT_SYMBOL_NS_GPL(is_switch_decoder, CXL);
 
 struct cxl_decoder *to_cxl_decoder(struct device *dev)
 {

@@ -482,6 +483,7 @@ struct cxl_switch_decoder *to_cxl_switch_decoder(struct device *dev)
 		return NULL;
 	return container_of(dev, struct cxl_switch_decoder, cxld.dev);
 }
+EXPORT_SYMBOL_NS_GPL(to_cxl_switch_decoder, CXL);
 
 static void cxl_ep_release(struct cxl_ep *ep)
 {

index 8787ef1e64047..7750ccb7652db 100644
@@ -575,8 +575,10 @@ struct cxl_dport *devm_cxl_add_dport(struct cxl_port *port,
 
 struct cxl_decoder *to_cxl_decoder(struct device *dev);
 struct cxl_root_decoder *to_cxl_root_decoder(struct device *dev);
+struct cxl_switch_decoder *to_cxl_switch_decoder(struct device *dev);
 struct cxl_endpoint_decoder *to_cxl_endpoint_decoder(struct device *dev);
 bool is_root_decoder(struct device *dev);
+bool is_switch_decoder(struct device *dev);
 bool is_endpoint_decoder(struct device *dev);
 struct cxl_root_decoder *cxl_root_decoder_alloc(struct cxl_port *port,
 						unsigned int nr_targets);

index 7e50b4e93ee53..b58a5b782e5dc 100644
@@ -75,6 +75,9 @@ static inline bool is_cxl_endpoint(struct cxl_port *port)
 }
 
 struct cxl_memdev *devm_cxl_add_memdev(struct cxl_dev_state *cxlds);
+int devm_cxl_dpa_reserve(struct cxl_endpoint_decoder *cxled,
+			 resource_size_t base, resource_size_t len,
+			 resource_size_t skipped);
 
 static inline struct cxl_ep *cxl_ep_load(struct cxl_port *port,
 					 struct cxl_memdev *cxlmd)

2.42.0

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

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

From: Jim Harris <[email protected]>

[ Upstream commit 98a04c7aced2b43b3ac4befe216c4eecc7257d4b ]

Root decoder granularity must match value from CFWMS, which may not be the region's granularity for non-interleaved root decoders.

So when calculating granularities for host bridge decoders, use the region's granularity instead of the root decoder's granularity to ensure the correct granularities are set for the host bridge decoders and any downstream switch decoders.

Test configuration is 1 host bridge * 2 switches * 2 endpoints per switch.

Region created with 2048 granularity using following command line:

cxl create-region -m -d decoder0.0 -w 4 mem0 mem2 mem1 mem3 \
		  -g 2048 -s 2048M

Use "cxl list -PDE | grep granularity" to get a view of the granularity set at each level of the topology.

Before this patch:

        "interleave_granularity":2048,
        "interleave_granularity":2048,
    "interleave_granularity":512,
        "interleave_granularity":2048,
        "interleave_granularity":2048,
    "interleave_granularity":512,

"interleave_granularity":256,

After:

        "interleave_granularity":2048,
        "interleave_granularity":2048,
    "interleave_granularity":4096,
        "interleave_granularity":2048,
        "interleave_granularity":2048,
    "interleave_granularity":4096,

"interleave_granularity":2048,

---
 drivers/cxl/core/region.c    | 9 ++++++++-
 tools/testing/cxl/test/cxl.c | 2 +-
 2 files changed, 9 insertions(+), 2 deletions(-)

index 13b1b18612d3f..ebc1b028555ca 100644
@@ -1012,7 +1012,14 @@ static int cxl_port_setup_targets(struct cxl_port *port,
 	}
 
 	if (is_cxl_root(parent_port)) {
-		parent_ig = cxlrd->cxlsd.cxld.interleave_granularity;
+		/*
+		 * Root decoder IG is always set to value in CFMWS which
+		 * may be different than this region's IG.  We can use the
+		 * region's IG here since interleave_granularity_store()
+		 * does not allow interleaved host-bridges with
+		 * root IG != region IG.
+		 */
+		parent_ig = p->interleave_granularity;
 		parent_iw = cxlrd->cxlsd.cxld.interleave_ways;
 		/*
 		 * For purposes of address bit routing, use power-of-2 math for

index c43bb6774f4db..339b31a3319bf 100644
@@ -678,7 +678,7 @@ static void mock_init_hdm_decoder(struct cxl_decoder *cxld)
 			cxld->interleave_ways = 2;
 		else
 			cxld->interleave_ways = 1;
-		cxld->interleave_granularity = 256;
+		cxld->interleave_granularity = 4096;
 		cxld->hpa_range = (struct range) {
 			.start = base,
 			.end = base + size - 1,

2.42.0

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

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

From: Johnathan Mantey <[email protected]>

commit 9e2e7efbbbff69d8340abb56d375dd79d1f5770f upstream.

This reverts commit 3780bb29311eccb7a1c9641032a112eed237f7e3.

The cited commit introduced unwanted behavior.

The intent for the commit was to be able to detect carrier loss/gain for just the NIC connected to the BMC. The unwanted effect is a carrier loss for auxiliary paths also causes the BMC to lose carrier. The BMC never regains carrier despite the secondary NIC regaining a link.

This change, when merged, needs to be backported to stable kernels. 5.4-stable, 5.10-stable, 5.15-stable, 6.1-stable, 6.5-stable

---
 net/ncsi/ncsi-aen.c |    5 -----
 1 file changed, 5 deletions(-)

@@ -89,11 +89,6 @@ static int ncsi_aen_handler_lsc(struct n
 	if ((had_link == has_link) || chained)
 		return 0;
 
-	if (had_link)
-		netif_carrier_off(ndp->ndev.dev);
-	else
-		netif_carrier_on(ndp->ndev.dev);
-
 	if (!ndp->multi_package && !nc->package->multi_channel) {
 		if (had_link) {
 			ndp->flags |= NCSI_DEV_RESHUFFLE;

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

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

From: Robert Marko <[email protected]>

commit 7b211c7671212cad0b83603c674838c7e824d845 upstream.

This reverts commit 0b01392c18b9993a584f36ace1d61118772ad0ca.

Conversion of PXA to generic I2C recovery, makes the I2C bus completely lock up if recovery pinctrl is present in the DT and I2C recovery is enabled.

So, until the generic I2C recovery can also work with PXA lets revert to have working I2C and I2C recovery again.

---
 drivers/i2c/busses/i2c-pxa.c |   76 ++++++++++++++++++++++++++++++++++++++-----
 1 file changed, 68 insertions(+), 8 deletions(-)

@@ -264,6 +264,9 @@ struct pxa_i2c {
 	u32			hs_mask;
 
 	struct i2c_bus_recovery_info recovery;
+	struct pinctrl		*pinctrl;
+	struct pinctrl_state	*pinctrl_default;
+	struct pinctrl_state	*pinctrl_recovery;
 };
 
 #define _IBMR(i2c)	((i2c)->reg_ibmr)

@@ -1302,12 +1305,13 @@ static void i2c_pxa_prepare_recovery(str
 	 */
 	gpiod_set_value(i2c->recovery.scl_gpiod, ibmr & IBMR_SCLS);
 	gpiod_set_value(i2c->recovery.sda_gpiod, ibmr & IBMR_SDAS);
+
+	WARN_ON(pinctrl_select_state(i2c->pinctrl, i2c->pinctrl_recovery));
 }
 
 static void i2c_pxa_unprepare_recovery(struct i2c_adapter *adap)
 {
 	struct pxa_i2c *i2c = adap->algo_data;
-	struct i2c_bus_recovery_info *bri = adap->bus_recovery_info;
 	u32 isr;
 
 	/*

@@ -1321,7 +1325,7 @@ static void i2c_pxa_unprepare_recovery(s
 		i2c_pxa_do_reset(i2c);
 	}
 
-	WARN_ON(pinctrl_select_state(bri->pinctrl, bri->pins_default));
+	WARN_ON(pinctrl_select_state(i2c->pinctrl, i2c->pinctrl_default));
 
 	dev_dbg(&i2c->adap.dev, "recovery: IBMR 0x%08x ISR 0x%08x\n",
 	        readl(_IBMR(i2c)), readl(_ISR(i2c)));

@@ -1343,20 +1347,76 @@ static int i2c_pxa_init_recovery(struct
 	if (IS_ENABLED(CONFIG_I2C_PXA_SLAVE))
 		return 0;
 
-	bri->pinctrl = devm_pinctrl_get(dev);
-	if (PTR_ERR(bri->pinctrl) == -ENODEV) {
-		bri->pinctrl = NULL;
+	i2c->pinctrl = devm_pinctrl_get(dev);
+	if (PTR_ERR(i2c->pinctrl) == -ENODEV)
+		i2c->pinctrl = NULL;
+	if (IS_ERR(i2c->pinctrl))
+		return PTR_ERR(i2c->pinctrl);
+
+	if (!i2c->pinctrl)
+		return 0;
+
+	i2c->pinctrl_default = pinctrl_lookup_state(i2c->pinctrl,
+						    PINCTRL_STATE_DEFAULT);
+	i2c->pinctrl_recovery = pinctrl_lookup_state(i2c->pinctrl, "recovery");
+
+	if (IS_ERR(i2c->pinctrl_default) || IS_ERR(i2c->pinctrl_recovery)) {
+		dev_info(dev, "missing pinmux recovery information: %ld %ld\n",
+			 PTR_ERR(i2c->pinctrl_default),
+			 PTR_ERR(i2c->pinctrl_recovery));
+		return 0;
+	}
+
+	/*
+	 * Claiming GPIOs can influence the pinmux state, and may glitch the
+	 * I2C bus. Do this carefully.
+	 */
+	bri->scl_gpiod = devm_gpiod_get(dev, "scl", GPIOD_OUT_HIGH_OPEN_DRAIN);
+	if (bri->scl_gpiod == ERR_PTR(-EPROBE_DEFER))
+		return -EPROBE_DEFER;
+	if (IS_ERR(bri->scl_gpiod)) {
+		dev_info(dev, "missing scl gpio recovery information: %pe\n",
+			 bri->scl_gpiod);
+		return 0;
+	}
+
+	/*
+	 * We have SCL. Pull SCL low and wait a bit so that SDA glitches
+	 * have no effect.
+	 */
+	gpiod_direction_output(bri->scl_gpiod, 0);
+	udelay(10);
+	bri->sda_gpiod = devm_gpiod_get(dev, "sda", GPIOD_OUT_HIGH_OPEN_DRAIN);
+
+	/* Wait a bit in case of a SDA glitch, and then release SCL. */
+	udelay(10);
+	gpiod_direction_output(bri->scl_gpiod, 1);
+
+	if (bri->sda_gpiod == ERR_PTR(-EPROBE_DEFER))
+		return -EPROBE_DEFER;
+
+	if (IS_ERR(bri->sda_gpiod)) {
+		dev_info(dev, "missing sda gpio recovery information: %pe\n",
+			 bri->sda_gpiod);
 		return 0;
 	}
-	if (IS_ERR(bri->pinctrl))
-		return PTR_ERR(bri->pinctrl);
 
 	bri->prepare_recovery = i2c_pxa_prepare_recovery;
 	bri->unprepare_recovery = i2c_pxa_unprepare_recovery;
+	bri->recover_bus = i2c_generic_scl_recovery;
 
 	i2c->adap.bus_recovery_info = bri;
 
-	return 0;
+	/*
+	 * Claiming GPIOs can change the pinmux state, which confuses the
+	 * pinctrl since pinctrl's idea of the current setting is unaffected
+	 * by the pinmux change caused by claiming the GPIO. Work around that
+	 * by switching pinctrl to the GPIO state here. We do it this way to
+	 * avoid glitching the I2C bus.
+	 */
+	pinctrl_select_state(i2c->pinctrl, i2c->pinctrl_recovery);
+
+	return pinctrl_select_state(i2c->pinctrl, i2c->pinctrl_default);
 }
 
 static int i2c_pxa_probe(struct platform_device *dev)

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

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

From: Ondrej Mosnacek <[email protected]>

commit 866d648059d5faf53f1cd960b43fe8365ad93ea7 upstream.

1 is the return value that implements a "no-op" hook, not 0.

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

@@ -48,7 +48,7 @@ LSM_HOOK(int, 0, quota_on, struct dentry
 LSM_HOOK(int, 0, syslog, int type)
 LSM_HOOK(int, 0, settime, const struct timespec64 *ts,
 	 const struct timezone *tz)
-LSM_HOOK(int, 0, vm_enough_memory, struct mm_struct *mm, long pages)
+LSM_HOOK(int, 1, vm_enough_memory, struct mm_struct *mm, long pages)
 LSM_HOOK(int, 0, bprm_creds_for_exec, struct linux_binprm *bprm)
 LSM_HOOK(int, 0, bprm_creds_from_file, struct linux_binprm *bprm, struct file *file)
 LSM_HOOK(int, 0, bprm_check_security, struct linux_binprm *bprm)

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

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

From: Ondrej Mosnacek <[email protected]>

commit b36995b8609a5a8fe5cf259a1ee768fcaed919f8 upstream.

-EOPNOTSUPP is the return value that implements a "no-op" hook, not 0.

Without this fix having only the BPF LSM enabled (with no programs attached) can cause uninitialized variable reads in nfsd4_encode_fattr(), because the BPF hook returns 0 without touching the 'ctxlen' variable and the corresponding 'contextlen' variable in nfsd4_encode_fattr() remains uninitialized, yet being treated as valid based on the 0 return value.

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

@@ -266,7 +266,7 @@ LSM_HOOK(void, LSM_RET_VOID, release_sec
 LSM_HOOK(void, LSM_RET_VOID, inode_invalidate_secctx, struct inode *inode)
 LSM_HOOK(int, 0, inode_notifysecctx, struct inode *inode, void *ctx, u32 ctxlen)
 LSM_HOOK(int, 0, inode_setsecctx, struct dentry *dentry, void *ctx, u32 ctxlen)
-LSM_HOOK(int, 0, inode_getsecctx, struct inode *inode, void **ctx,
+LSM_HOOK(int, -EOPNOTSUPP, inode_getsecctx, struct inode *inode, void **ctx,
 	 u32 *ctxlen)
 
 #if defined(CONFIG_SECURITY) && defined(CONFIG_WATCH_QUEUE)

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

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

From: Darren Hart <[email protected]>

commit 5d6aa89bba5bd6af2580f872b57f438dab883738 upstream.

Commit abd3ac7902fb ("watchdog: sbsa: Support architecture version 1") introduced new timer math for watchdog revision 1 with the 48 bit offset register.

The gwdt->clk and timeout are u32, but the argument being calculated is u64. Without a cast, the compiler performs u32 operations, truncating intermediate steps, resulting in incorrect values.

A watchdog revision 1 implementation with a gwdt->clk of 1GHz and a timeout of 600s writes 3647256576 to the one shot watchdog instead of 300000000000, resulting in the watchdog firing in 3.6s instead of 600s.

Force u64 math by casting the first argument (gwdt->clk) as a u64. Make the order of operations explicit with parenthesis.

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

@@ -153,14 +153,14 @@ static int sbsa_gwdt_set_timeout(struct
 	timeout = clamp_t(unsigned int, timeout, 1, wdd->max_hw_heartbeat_ms / 1000);
 
 	if (action)
-		sbsa_gwdt_reg_write(gwdt->clk * timeout, gwdt);
+		sbsa_gwdt_reg_write((u64)gwdt->clk * timeout, gwdt);
 	else
 		/*
 		 * In the single stage mode, The first signal (WS0) is ignored,
 		 * the timeout is (WOR * 2), so the WOR should be configured
 		 * to half value of timeout.
 		 */
-		sbsa_gwdt_reg_write(gwdt->clk / 2 * timeout, gwdt);
+		sbsa_gwdt_reg_write(((u64)gwdt->clk / 2) * timeout, gwdt);
 
 	return 0;
 }

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

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

From: Tam Nguyen <[email protected]>

commit e8183fa10c25c7b3c20670bf2b430ddcc1ee03c0 upstream.

During SMBus block data read process, we have seen high interrupt rate because of TX_EMPTY irq status while waiting for block length byte (the first data byte after the address phase). The interrupt handler does not do anything because the internal state is kept as STATUS_WRITE_IN_PROGRESS. Hence, we should disable TX_EMPTY IRQ until I2C DesignWare receives first data byte from I2C device, then re-enable it to resume SMBus transaction.

It takes 0.789 ms for host to receive data length from slave. Without the patch, i2c_dw_isr() is called 99 times by TX_EMPTY interrupt. And it is none after applying the patch.

---
 drivers/i2c/busses/i2c-designware-master.c |   19 ++++++++++++++++---
 1 file changed, 16 insertions(+), 3 deletions(-)

@@ -456,10 +456,16 @@ i2c_dw_xfer_msg(struct dw_i2c_dev *dev)
 
 		/*
 		 * Because we don't know the buffer length in the
-		 * I2C_FUNC_SMBUS_BLOCK_DATA case, we can't stop
-		 * the transaction here.
+		 * I2C_FUNC_SMBUS_BLOCK_DATA case, we can't stop the
+		 * transaction here. Also disable the TX_EMPTY IRQ
+		 * while waiting for the data length byte to avoid the
+		 * bogus interrupts flood.
 		 */
-		if (buf_len > 0 || flags & I2C_M_RECV_LEN) {
+		if (flags & I2C_M_RECV_LEN) {
+			dev->status |= STATUS_WRITE_IN_PROGRESS;
+			intr_mask &= ~DW_IC_INTR_TX_EMPTY;
+			break;
+		} else if (buf_len > 0) {
 			/* more bytes to be written */
 			dev->status |= STATUS_WRITE_IN_PROGRESS;
 			break;

@@ -495,6 +501,13 @@ i2c_dw_recv_len(struct dw_i2c_dev *dev,
 	msgs[dev->msg_read_idx].len = len;
 	msgs[dev->msg_read_idx].flags &= ~I2C_M_RECV_LEN;
 
+	/*
+	 * Received buffer length, re-enable TX_EMPTY interrupt
+	 * to resume the SMBUS transaction.
+	 */
+	regmap_update_bits(dev->map, DW_IC_INTR_MASK, DW_IC_INTR_TX_EMPTY,
+			   DW_IC_INTR_TX_EMPTY);
+
 	return len;
 }
 

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

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

From: Harald Freudenberger <[email protected]>

commit e14aec23025eeb1f2159ba34dbc1458467c4c347 upstream.

Fix kernel crash in AP bus code caused by very early invocation of the config change callback function via SCLP.

After a fresh IML of the machine the crypto cards are still offline and will get switched online only with activation of any LPAR which has the card in it's configuration. A crypto card coming online is reported to the LPAR via SCLP and the AP bus offers a callback function to get this kind of information. However, it may happen that the callback is invoked before the AP bus init function is complete. As the callback triggers a synchronous AP bus scan, the scan may already run but some internal states are not initialized by the AP bus init function resulting in a crash like this:

  [   11.635859] Unable to handle kernel pointer dereference in virtual kernel address space
  [   11.635861] Failing address: 0000000000000000 TEID: 0000000000000887
  [   11.635862] Fault in home space mode while using kernel ASCE.
  [   11.635864] AS:00000000894c4007 R3:00000001fece8007 S:00000001fece7800 P:000000000000013d
  [   11.635879] Oops: 0004 ilc:1 [#1] SMP
  [   11.635882] Modules linked in:
  [   11.635884] CPU: 5 PID: 42 Comm: kworker/5:0 Not tainted 6.6.0-rc3-00003-g4dbf7cdc6b42 #12
  [   11.635886] Hardware name: IBM 3931 A01 751 (LPAR)
  [   11.635887] Workqueue: events_long ap_scan_bus
  [   11.635891] Krnl PSW : 0704c00180000000 0000000000000000 (0x0)
  [   11.635895]            R:0 T:1 IO:1 EX:1 Key:0 M:1 W:0 P:0 AS:3 CC:0 PM:0 RI:0 EA:3
  [   11.635897] Krnl GPRS: 0000000001000a00 0000000000000000 0000000000000006 0000000089591940
  [   11.635899]            0000000080000000 0000000000000a00 0000000000000000 0000000000000000
  [   11.635901]            0000000081870c00 0000000089591000 000000008834e4e2 0000000002625a00
  [   11.635903]            0000000081734200 0000038000913c18 000000008834c6d6 0000038000913ac8
  [   11.635906] Krnl Code:>0000000000000000: 0000                illegal
  [   11.635906]            0000000000000002: 0000                illegal
  [   11.635906]            0000000000000004: 0000                illegal
  [   11.635906]            0000000000000006: 0000                illegal
  [   11.635906]            0000000000000008: 0000                illegal
  [   11.635906]            000000000000000a: 0000                illegal
  [   11.635906]            000000000000000c: 0000                illegal
  [   11.635906]            000000000000000e: 0000                illegal
  [   11.635915] Call Trace:
  [   11.635916]  [<0000000000000000>] 0x0
  [   11.635918]  [<000000008834e4e2>] ap_queue_init_state+0x82/0xb8
  [   11.635921]  [<000000008834ba1c>] ap_scan_domains+0x6fc/0x740
  [   11.635923]  [<000000008834c092>] ap_scan_adapter+0x632/0x8b0
  [   11.635925]  [<000000008834c3e4>] ap_scan_bus+0xd4/0x288
  [   11.635927]  [<00000000879a33ba>] process_one_work+0x19a/0x410
  [   11.635930] Discipline DIAG cannot be used without z/VM
  [   11.635930]  [<00000000879a3a2c>] worker_thread+0x3fc/0x560
  [   11.635933]  [<00000000879aea60>] kthread+0x120/0x128
  [   11.635936]  [<000000008792afa4>] __ret_from_fork+0x3c/0x58
  [   11.635938]  [<00000000885ebe62>] ret_from_fork+0xa/0x30
  [   11.635942] Last Breaking-Event-Address:
  [   11.635942]  [<000000008834c6d4>] ap_wait+0xcc/0x148

This patch improves the ap_bus_force_rescan() function which is invoked by the config change callback by checking if a first initial AP bus scan has been done. If not, the force rescan request is simple ignored. Anyhow it does not make sense to trigger AP bus re-scans even before the very first bus scan is complete.

---
 drivers/s390/crypto/ap_bus.c |    4 ++++
 1 file changed, 4 insertions(+)

@@ -1012,6 +1012,10 @@ EXPORT_SYMBOL(ap_driver_unregister);
 
 void ap_bus_force_rescan(void)
 {
+	/* Only trigger AP bus scans after the initial scan is done */
+	if (atomic64_read(&ap_scan_bus_count) <= 0)
+		return;
+
 	/* processing a asynchronous bus rescan */
 	del_timer(&ap_config_timer);
 	queue_work(system_long_wq, &ap_scan_work);

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

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

From: Andrew Lunn <[email protected]>

commit f55d8e60f10909dbc5524e261041e1d28d7d20d8 upstream.

This function takes a pointer to a pointer, unlike sprintf() which is passed a plain pointer. Fix up the documentation to make this clear.

---
 include/linux/ethtool.h |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

@@ -836,10 +836,10 @@ int ethtool_get_phc_vclocks(struct net_d
 
 /**
  * ethtool_sprintf - Write formatted string to ethtool string data
- * @data: Pointer to start of string to update
+ * @data: Pointer to a pointer to the start of string to update
  * @fmt: Format of string to write
  *
- * Write formatted string to data. Update data to point at start of
+ * Write formatted string to *data. Update *data to point at start of
  * next string.
  */
 extern __printf(2, 3) void ethtool_sprintf(u8 **data, const char *fmt, ...);

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

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

From: Alexander Sverdlin <[email protected]>

commit 5a22fbcc10f3f7d94c5d88afbbffa240a3677057 upstream.

When LAN9303 is MDIO-connected two callchains exist into mdio->bus->write():

1. switch ports 1&2 ("physical" PHYs):

virtual (switch-internal) MDIO bus (lan9303_switch_ops->phy_{read|write})->
lan9303_mdio_phy_{read|write} -> mdiobus_{read|write}_nested

2. LAN9303 virtual PHY:

virtual MDIO bus (lan9303_phy_{read|write}) ->
lan9303_virt_phy_reg_{read|write} -> regmap -> lan9303_mdio_{read|write}

If the latter functions just take mutex_lock(&sw_dev->device->bus->mdio_lock) it triggers a LOCKDEP false-positive splat. It's false-positive because the first mdio_lock in the second callchain above belongs to virtual MDIO bus, the second mdio_lock belongs to physical MDIO bus.

Consequent annotation in lan9303_mdio_{read|write} as nested lock (similar to lan9303_mdio_phy_{read|write}, it's the same physical MDIO bus) prevents the following splat:

WARNING: possible circular locking dependency detected
5.15.71 #1 Not tainted
------------------------------------------------------
kworker/u4:3/609 is trying to acquire lock:
ffff000011531c68 (lan9303_mdio:131:(&lan9303_mdio_regmap_config)->lock){+.+.}-{3:3}, at: regmap_lock_mutex but task is already holding lock:
ffff0000114c44d8 (&bus->mdio_lock){+.+.}-{3:3}, at: mdiobus_read
which lock already depends on the new lock.
the existing dependency chain (in reverse order) is:
-> #1 (&bus->mdio_lock){+.+.}-{3:3}:

       lock_acquire
       __mutex_lock
       mutex_lock_nested
       lan9303_mdio_read
       _regmap_read
       regmap_read
       lan9303_probe
       lan9303_mdio_probe
       mdio_probe
       really_probe
       __driver_probe_device
       driver_probe_device
       __device_attach_driver
       bus_for_each_drv
       __device_attach
       device_initial_probe
       bus_probe_device
       deferred_probe_work_func
       process_one_work
       worker_thread
       kthread
       ret_from_fork
-> #0 (lan9303_mdio:131:(&lan9303_mdio_regmap_config)->lock){+.+.}-{3:3}:
       __lock_acquire
       lock_acquire.part.0
       lock_acquire
       __mutex_lock
       mutex_lock_nested
       regmap_lock_mutex
       regmap_read
       lan9303_phy_read
       dsa_slave_phy_read
       __mdiobus_read
       mdiobus_read
       get_phy_device
       mdiobus_scan
       __mdiobus_register
       dsa_register_switch
       lan9303_probe
       lan9303_mdio_probe
       mdio_probe
       really_probe
       __driver_probe_device
       driver_probe_device
       __device_attach_driver
       bus_for_each_drv
       __device_attach
       device_initial_probe
       bus_probe_device
       deferred_probe_work_func
       process_one_work
       worker_thread
       kthread
       ret_from_fork
other info that might help us debug this:
 Possible unsafe locking scenario:
       CPU0                    CPU1
       ----                    ----
  lock(&bus->mdio_lock);
                               lock(lan9303_mdio:131:(&lan9303_mdio_regmap_config)->lock);
                               lock(&bus->mdio_lock);
  lock(lan9303_mdio:131:(&lan9303_mdio_regmap_config)->lock);
*** DEADLOCK ***
5 locks held by kworker/u4:3/609:
 #0: ffff000002842938 ((wq_completion)events_unbound){+.+.}-{0:0}, at: process_one_work
 #1: ffff80000bacbd60 (deferred_probe_work){+.+.}-{0:0}, at: process_one_work
 #2: ffff000007645178 (&dev->mutex){....}-{3:3}, at: __device_attach
 #3: ffff8000096e6e78 (dsa2_mutex){+.+.}-{3:3}, at: dsa_register_switch
 #4: ffff0000114c44d8 (&bus->mdio_lock){+.+.}-{3:3}, at: mdiobus_read
stack backtrace:
CPU: 1 PID: 609 Comm: kworker/u4:3 Not tainted 5.15.71 #1
Workqueue: events_unbound deferred_probe_work_func
Call trace:
 dump_backtrace
 show_stack
 dump_stack_lvl
 dump_stack
 print_circular_bug
 check_noncircular
 __lock_acquire
 lock_acquire.part.0
 lock_acquire
 __mutex_lock
 mutex_lock_nested
 regmap_lock_mutex
 regmap_read
 lan9303_phy_read
 dsa_slave_phy_read
 __mdiobus_read
 mdiobus_read
 get_phy_device
 mdiobus_scan
 __mdiobus_register
 dsa_register_switch
 lan9303_probe
 lan9303_mdio_probe

...

---
 drivers/net/dsa/lan9303_mdio.c |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

@@ -32,7 +32,7 @@ static int lan9303_mdio_write(void *ctx,
 	struct lan9303_mdio *sw_dev = (struct lan9303_mdio *)ctx;
 
 	reg <<= 2; /* reg num to offset */
-	mutex_lock(&sw_dev->device->bus->mdio_lock);
+	mutex_lock_nested(&sw_dev->device->bus->mdio_lock, MDIO_MUTEX_NESTED);
 	lan9303_mdio_real_write(sw_dev->device, reg, val & 0xffff);
 	lan9303_mdio_real_write(sw_dev->device, reg + 2, (val >> 16) & 0xffff);
 	mutex_unlock(&sw_dev->device->bus->mdio_lock);

@@ -50,7 +50,7 @@ static int lan9303_mdio_read(void *ctx,
 	struct lan9303_mdio *sw_dev = (struct lan9303_mdio *)ctx;
 
 	reg <<= 2; /* reg num to offset */
-	mutex_lock(&sw_dev->device->bus->mdio_lock);
+	mutex_lock_nested(&sw_dev->device->bus->mdio_lock, MDIO_MUTEX_NESTED);
 	*val = lan9303_mdio_real_read(sw_dev->device, reg);
 	*val |= (lan9303_mdio_real_read(sw_dev->device, reg + 2) << 16);
 	mutex_unlock(&sw_dev->device->bus->mdio_lock);

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

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

From: Klaus Kudielka <[email protected]>

commit 02d5fdbf4f2b8c406f7a4c98fa52aa181a11d733 upstream.

Background: Turris Omnia (Armada 385); eth2 (mvneta) connected to SFP bus; SFP module is present, but no fiber connected, so definitely no carrier.

After booting, eth2 is down, but netdev LED trigger surprisingly reports link active. Then, after "ip link set eth2 up", the link indicator goes away - as I would have expected it from the beginning.

It turns out, that the default carrier state after netdev creation is "carrier ok". Some ethernet drivers explicitly call netif_carrier_off during probing, others (like mvneta) don't - which explains the current
behaviour: only when the device is brought up, phylink_start calls netif_carrier_off.

Fix this for all drivers using phylink, by calling netif_carrier_off in phylink_create.

---
 drivers/net/phy/phylink.c |    1 +
 1 file changed, 1 insertion(+)

@@ -1479,6 +1479,7 @@ struct phylink *phylink_create(struct ph
 	pl->config = config;
 	if (config->type == PHYLINK_NETDEV) {
 		pl->netdev = to_net_dev(config->dev);
+		netif_carrier_off(pl->netdev);
 	} else if (config->type == PHYLINK_DEV) {
 		pl->dev = config->dev;
 	} else {

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

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

From: Heiner Kallweit <[email protected]>

commit f78ca48a8ba9cdec96e8839351e49eec3233b177 upstream.

Currently we set SMBHSTCNT_LAST_BYTE only after the host has started receiving the last byte. If we get e.g. preempted before setting SMBHSTCNT_LAST_BYTE, the host may be finished with receiving the byte before SMBHSTCNT_LAST_BYTE is set.
Therefore change the code to set SMBHSTCNT_LAST_BYTE before writing SMBHSTSTS_BYTE_DONE for the byte before the last byte. Now the code is also consistent with what we do in i801_isr_byte_done().

---
 drivers/i2c/busses/i2c-i801.c |   19 +++++++++----------
 1 file changed, 9 insertions(+), 10 deletions(-)

@@ -690,15 +690,11 @@ static int i801_block_transaction_byte_b
 		return i801_check_post(priv, result ? priv->status : -ETIMEDOUT);
 	}
 
-	for (i = 1; i <= len; i++) {
-		if (i == len && read_write == I2C_SMBUS_READ)
-			smbcmd |= SMBHSTCNT_LAST_BYTE;
-		outb_p(smbcmd, SMBHSTCNT(priv));
-
-		if (i == 1)
-			outb_p(inb(SMBHSTCNT(priv)) | SMBHSTCNT_START,
-			       SMBHSTCNT(priv));
+	if (len == 1 && read_write == I2C_SMBUS_READ)
+		smbcmd |= SMBHSTCNT_LAST_BYTE;
+	outb_p(smbcmd | SMBHSTCNT_START, SMBHSTCNT(priv));
 
+	for (i = 1; i <= len; i++) {
 		status = i801_wait_byte_done(priv);
 		if (status)
 			goto exit;

@@ -721,9 +717,12 @@ static int i801_block_transaction_byte_b
 			data->block[0] = len;
 		}
 
-		/* Retrieve/store value in SMBBLKDAT */
-		if (read_write == I2C_SMBUS_READ)
+		if (read_write == I2C_SMBUS_READ) {
 			data->block[i] = inb_p(SMBBLKDAT(priv));
+			if (i == len - 1)
+				outb_p(smbcmd | SMBHSTCNT_LAST_BYTE, SMBHSTCNT(priv));
+		}
+
 		if (read_write == I2C_SMBUS_WRITE && i+1 <= len)
 			outb_p(data->block[i+1], SMBBLKDAT(priv));
 

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

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

From: Jaegeuk Kim <[email protected]>

commit 50a472bbc79ff9d5a88be8019a60e936cadf9f13 upstream.

If we return the error, there's no way to recover the status as of now, since fsck does not fix the xattr boundary issue.

---
 fs/f2fs/node.c  |    4 +++-
 fs/f2fs/xattr.c |   20 +++++++++++++-------
 2 files changed, 16 insertions(+), 8 deletions(-)

@@ -2738,7 +2738,9 @@ recover_xnid:
 	f2fs_update_inode_page(inode);
 
 	/* 3: update and set xattr node page dirty */
-	memcpy(F2FS_NODE(xpage), F2FS_NODE(page), VALID_XATTR_BLOCK_SIZE);
+	if (page)
+		memcpy(F2FS_NODE(xpage), F2FS_NODE(page),
+				VALID_XATTR_BLOCK_SIZE);
 
 	set_page_dirty(xpage);
 	f2fs_put_page(xpage, 1);

@@ -363,10 +363,10 @@ static int lookup_all_xattrs(struct inod
 
 	*xe = __find_xattr(cur_addr, last_txattr_addr, NULL, index, len, name);
 	if (!*xe) {
-		f2fs_err(F2FS_I_SB(inode), "inode (%lu) has corrupted xattr",
+		f2fs_err(F2FS_I_SB(inode), "lookup inode (%lu) has corrupted xattr",
 								inode->i_ino);
 		set_sbi_flag(F2FS_I_SB(inode), SBI_NEED_FSCK);
-		err = -EFSCORRUPTED;
+		err = -ENODATA;
 		f2fs_handle_error(F2FS_I_SB(inode),
 					ERROR_CORRUPTED_XATTR);
 		goto out;

@@ -583,13 +583,12 @@ ssize_t f2fs_listxattr(struct dentry *de
 
 		if ((void *)(entry) + sizeof(__u32) > last_base_addr ||
 			(void *)XATTR_NEXT_ENTRY(entry) > last_base_addr) {
-			f2fs_err(F2FS_I_SB(inode), "inode (%lu) has corrupted xattr",
+			f2fs_err(F2FS_I_SB(inode), "list inode (%lu) has corrupted xattr",
 						inode->i_ino);
 			set_sbi_flag(F2FS_I_SB(inode), SBI_NEED_FSCK);
-			error = -EFSCORRUPTED;
 			f2fs_handle_error(F2FS_I_SB(inode),
 						ERROR_CORRUPTED_XATTR);
-			goto cleanup;
+			break;
 		}
 
 		if (!handler || (handler->list && !handler->list(dentry)))

@@ -650,7 +649,7 @@ static int __f2fs_setxattr(struct inode
 
 	if (size > MAX_VALUE_LEN(inode))
 		return -E2BIG;
-
+retry:
 	error = read_all_xattrs(inode, ipage, &base_addr);
 	if (error)
 		return error;

@@ -660,7 +659,14 @@ static int __f2fs_setxattr(struct inode
 	/* find entry with wanted name. */
 	here = __find_xattr(base_addr, last_base_addr, NULL, index, len, name);
 	if (!here) {
-		f2fs_err(F2FS_I_SB(inode), "inode (%lu) has corrupted xattr",
+		if (!F2FS_I(inode)->i_xattr_nid) {
+			f2fs_notice(F2FS_I_SB(inode),
+				"recover xattr in inode (%lu)", inode->i_ino);
+			f2fs_recover_xattr_data(inode, NULL);
+			kfree(base_addr);
+			goto retry;
+		}
+		f2fs_err(F2FS_I_SB(inode), "set inode (%lu) has corrupted xattr",
 								inode->i_ino);
 		set_sbi_flag(F2FS_I_SB(inode), SBI_NEED_FSCK);
 		error = -EFSCORRUPTED;

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

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

From: Su Hui <[email protected]>

commit e0d4e8acb3789c5a8651061fbab62ca24a45c063 upstream.

With gcc and W=1 option, there's a warning like this:

fs/f2fs/compress.c: In function ‘f2fs_init_page_array_cache’:
fs/f2fs/compress.c:1984:47: error: ‘%u’ directive writing between 1 and 7 bytes into a region of size between 5 and 8 [-Werror=format-overflow=]
1984 | sprintf(slab_name, "f2fs_page_array_entry-%u:%u", MAJOR(dev),

		MINOR(dev));
      |                                               ^~

String "f2fs_page_array_entry-%u:%u" can up to 35. The first "%u" can up to 4 and the second "%u" can up to 7, so total size is "24 + 4 + 7 = 35". slab_name's size should be 35 rather than 32.

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

@@ -1983,7 +1983,7 @@ void f2fs_destroy_compress_inode(struct
 int f2fs_init_page_array_cache(struct f2fs_sb_info *sbi)
 {
 	dev_t dev = sbi->sb->s_bdev->bd_dev;
-	char slab_name[32];
+	char slab_name[35];
 
 	if (!f2fs_sb_has_compression(sbi))
 		return 0;

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

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

From: Sean Young <[email protected]>

commit c8a489f820179fb12251e262b50303c29de991ac upstream.

When transmitting, infrared drivers expect an odd number of samples; iow without a trailing space. No problems have been observed so far, so this is just belt and braces.

---
 drivers/media/rc/lirc_dev.c |    6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

@@ -276,7 +276,11 @@ static ssize_t lirc_transmit(struct file
 		if (ret < 0)
 			goto out_kfree_raw;
 
-		count = ret;
+		/* drop trailing space */
+		if (!(ret % 2))
+			count = ret - 1;
+		else
+			count = ret;
 
 		txbuf = kmalloc_array(count, sizeof(unsigned int), GFP_KERNEL);
 		if (!txbuf) {

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

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

From: Sean Young <[email protected]>

commit 4f7efc71891462ab7606da7039f480d7c1584a13 upstream.

The Sharp protocol[1] encoding has incorrect timings for bit space.

[1] https://www.sbprojects.net/knowledge/ir/sharp.php

---
 drivers/media/rc/ir-sharp-decoder.c |    8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

@@ -15,7 +15,9 @@
 #define SHARP_UNIT		40  /* us */
 #define SHARP_BIT_PULSE		(8    * SHARP_UNIT) /* 320us */
 #define SHARP_BIT_0_PERIOD	(25   * SHARP_UNIT) /* 1ms (680us space) */
-#define SHARP_BIT_1_PERIOD	(50   * SHARP_UNIT) /* 2ms (1680ms space) */
+#define SHARP_BIT_1_PERIOD	(50   * SHARP_UNIT) /* 2ms (1680us space) */
+#define SHARP_BIT_0_SPACE	(17   * SHARP_UNIT) /* 680us space */
+#define SHARP_BIT_1_SPACE	(42   * SHARP_UNIT) /* 1680us space */
 #define SHARP_ECHO_SPACE	(1000 * SHARP_UNIT) /* 40 ms */
 #define SHARP_TRAILER_SPACE	(125  * SHARP_UNIT) /* 5 ms (even longer) */
 

@@ -168,8 +170,8 @@ static const struct ir_raw_timings_pd ir
 	.header_pulse  = 0,
 	.header_space  = 0,
 	.bit_pulse     = SHARP_BIT_PULSE,
-	.bit_space[0]  = SHARP_BIT_0_PERIOD,
-	.bit_space[1]  = SHARP_BIT_1_PERIOD,
+	.bit_space[0]  = SHARP_BIT_0_SPACE,
+	.bit_space[1]  = SHARP_BIT_1_SPACE,
 	.trailer_pulse = SHARP_BIT_PULSE,
 	.trailer_space = SHARP_ECHO_SPACE,
 	.msb_first     = 1,

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

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

From: Vikash Garodia <[email protected]>

commit 0768a9dd809ef52440b5df7dce5a1c1c7e97abbd upstream.

Supported codec bitmask is populated from the payload from venus firmware. There is a possible case when all the bits in the codec bitmask is set. In such case, core cap for decoder is filled and MAX_CODEC_NUM is utilized. Now while filling the caps for encoder, it can lead to access the caps array beyong 32 index. Hence leading to OOB write.
The fix counts the supported encoder and decoder. If the count is more than max, then it skips accessing the caps.

---
 drivers/media/platform/qcom/venus/hfi_parser.c |    3 +++
 1 file changed, 3 insertions(+)

@@ -19,6 +19,9 @@ static void init_codecs(struct venus_cor
 	struct hfi_plat_caps *caps = core->caps, *cap;
 	unsigned long bit;
 
+	if (hweight_long(core->dec_codecs) + hweight_long(core->enc_codecs) > MAX_CODEC_NUM)
+		return;
+
 	for_each_set_bit(bit, &core->dec_codecs, MAX_CODEC_NUM) {
 		cap = &caps[core->codecs_count++];
 		cap->codec = BIT(bit);

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

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

From: Vikash Garodia <[email protected]>

commit b18e36dfd6c935da60a971310374f3dfec3c82e1 upstream.

Buffer requirement, for different buffer type, comes from video firmware. While copying these requirements, there is an OOB possibility when the payload from firmware is more than expected size. Fix the check to avoid the OOB possibility.

---
 drivers/media/platform/qcom/venus/hfi_msgs.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -374,7 +374,7 @@ session_get_prop_buf_req(struct hfi_msg_
 		memcpy(&bufreq[idx], buf_req, sizeof(*bufreq));
 		idx++;
 
-		if (idx > HFI_BUFFER_TYPE_MAX)
+		if (idx >= HFI_BUFFER_TYPE_MAX)
 			return HFI_ERR_SESSION_INVALID_PARAMETER;
 
 		req_bytes -= sizeof(struct hfi_buffer_requirements);

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

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

From: Vikash Garodia <[email protected]>

commit 8d0b89398b7ebc52103e055bf36b60b045f5258f upstream.

The hfi parser, parses the capabilities received from venus firmware and copies them to core capabilities. Consider below api, for example, fill_caps - In this api, caps in core structure gets updated with the number of capabilities received in firmware data payload. If the same api is called multiple times, there is a possibility of copying beyond the max allocated size in core caps.
Similar possibilities in fill_raw_fmts and fill_profile_level functions.

---
 drivers/media/platform/qcom/venus/hfi_parser.c |   12 ++++++++++++
 1 file changed, 12 insertions(+)

@@ -89,6 +89,9 @@ static void fill_profile_level(struct hf
 {
 	const struct hfi_profile_level *pl = data;
 
+	if (cap->num_pl + num >= HFI_MAX_PROFILE_COUNT)
+		return;
+
 	memcpy(&cap->pl[cap->num_pl], pl, num * sizeof(*pl));
 	cap->num_pl += num;
 }

@@ -114,6 +117,9 @@ fill_caps(struct hfi_plat_caps *cap, con
 {
 	const struct hfi_capability *caps = data;
 
+	if (cap->num_caps + num >= MAX_CAP_ENTRIES)
+		return;
+
 	memcpy(&cap->caps[cap->num_caps], caps, num * sizeof(*caps));
 	cap->num_caps += num;
 }

@@ -140,6 +146,9 @@ static void fill_raw_fmts(struct hfi_pla
 {
 	const struct raw_formats *formats = fmts;
 
+	if (cap->num_fmts + num_fmts >= MAX_FMT_ENTRIES)
+		return;
+
 	memcpy(&cap->fmts[cap->num_fmts], formats, num_fmts * sizeof(*formats));
 	cap->num_fmts += num_fmts;
 }

@@ -162,6 +171,9 @@ parse_raw_formats(struct venus_core *cor
 		rawfmts[i].buftype = fmt->buffer_type;
 		i++;
 
+		if (i >= MAX_FMT_ENTRIES)
+			return;
+
 		if (pinfo->num_planes > MAX_PLANES)
 			break;
 

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

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

From: Sakari Ailus <[email protected]>

commit 724ff68e968b19d786870d333f9952bdd6b119cb upstream.

Initialise the try sink compose rectangle size to the sink compose rectangle for binner and scaler sub-devices. This was missed due to the faulty condition that lead to the compose rectangles to be initialised for the pixel array sub-device where it is not relevant.

---
 drivers/media/i2c/ccs/ccs-core.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -3088,7 +3088,7 @@ static int ccs_open(struct v4l2_subdev *
 		try_fmt->code = sensor->internal_csi_format->code;
 		try_fmt->field = V4L2_FIELD_NONE;
 
-		if (ssd != sensor->pixel_array)
+		if (ssd == sensor->pixel_array)
 			continue;
 
 		try_comp = v4l2_subdev_get_try_compose(sd, fh->state, i);

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

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

From: Jani Nikula <[email protected]>

commit dab12fa8d2bd3868cf2de485ed15a3feef28a13d upstream.

The sads returned by drm_edid_to_sad() needs to be freed.

---
 drivers/gpu/drm/mediatek/mtk_dp.c |    5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

@@ -1983,7 +1983,6 @@ static struct edid *mtk_dp_get_edid(stru
 	bool enabled = mtk_dp->enabled;
 	struct edid *new_edid = NULL;
 	struct mtk_dp_audio_cfg *audio_caps = &mtk_dp->info.audio_cur_cfg;
-	struct cea_sad *sads;
 
 	if (!enabled) {
 		drm_bridge_chain_pre_enable(bridge);

@@ -2010,7 +2009,11 @@ static struct edid *mtk_dp_get_edid(stru
 	}
 
 	if (new_edid) {
+		struct cea_sad *sads;
+
 		audio_caps->sad_count = drm_edid_to_sad(new_edid, &sads);
+		kfree(sads);
+
 		audio_caps->detect_monitor = drm_detect_monitor_audio(new_edid);
 	}
 

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

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

From: Jani Nikula <[email protected]>

commit fcaf9761fd5884a64eaac48536f8c27ecfd2e6bc upstream.

Setting new_edid to NULL leaks the buffer.

---
 drivers/gpu/drm/mediatek/mtk_dp.c |    1 +
 1 file changed, 1 insertion(+)

@@ -2005,6 +2005,7 @@ static struct edid *mtk_dp_get_edid(stru
 	 */
 	if (mtk_dp_parse_capabilities(mtk_dp)) {
 		drm_err(mtk_dp->drm_dev, "Can't parse capabilities\n");
+		kfree(new_edid);
 		new_edid = NULL;
 	}
 

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

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

From: Mikulas Patocka <[email protected]>

commit 28f07f2ab4b3a2714f1fefcc58ada4bcc195f806 upstream.

The commit 5721d4e5a9cd enhanced dm-verity, so that it can verify blocks from tasklets rather than from workqueues. This reportedly improves performance significantly.

However, dm-verity was using the flag CRYPTO_TFM_REQ_MAY_SLEEP from tasklets which resulted in warnings about sleeping function being called from non-sleeping context.

BUG: sleeping function called from invalid context at crypto/internal.h:206
in_atomic(): 1, irqs_disabled(): 0, non_block: 0, pid: 14, name: ksoftirqd/0
preempt_count: 100, expected: 0
RCU nest depth: 0, expected: 0
CPU: 0 PID: 14 Comm: ksoftirqd/0 Tainted: G        W 6.7.0-rc1 #1
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.14.0-2 04/01/2014
Call Trace:
 <TASK>
 dump_stack_lvl+0x32/0x50
 __might_resched+0x110/0x160
 crypto_hash_walk_done+0x54/0xb0
 shash_ahash_update+0x51/0x60
 verity_hash_update.isra.0+0x4a/0x130 [dm_verity]
 verity_verify_io+0x165/0x550 [dm_verity]
 ? free_unref_page+0xdf/0x170
 ? psi_group_change+0x113/0x390
 verity_tasklet+0xd/0x70 [dm_verity]
 tasklet_action_common.isra.0+0xb3/0xc0
 __do_softirq+0xaf/0x1ec
 ? smpboot_thread_fn+0x1d/0x200
 ? sort_range+0x20/0x20
 run_ksoftirqd+0x15/0x30
 smpboot_thread_fn+0xed/0x200
 kthread+0xdc/0x110
 ? kthread_complete_and_exit+0x20/0x20
 ret_from_fork+0x28/0x40
 ? kthread_complete_and_exit+0x20/0x20
 ret_from_fork_asm+0x11/0x20
 </TASK>

This commit fixes dm-verity so that it doesn't use the flags CRYPTO_TFM_REQ_MAY_SLEEP and CRYPTO_TFM_REQ_MAY_BACKLOG from tasklets. The crypto API would do GFP_ATOMIC allocation instead, it could return -ENOMEM and we catch -ENOMEM in verity_tasklet and requeue the request to the workqueue.

---
 drivers/md/dm-verity-fec.c    |    4 ++--
 drivers/md/dm-verity-target.c |   23 ++++++++++++-----------
 drivers/md/dm-verity.h        |    2 +-
 3 files changed, 15 insertions(+), 14 deletions(-)

@@ -185,7 +185,7 @@ static int fec_is_erasure(struct dm_veri
 {
 	if (unlikely(verity_hash(v, verity_io_hash_req(v, io),
 				 data, 1 << v->data_dev_block_bits,
-				 verity_io_real_digest(v, io))))
+				 verity_io_real_digest(v, io), true)))
 		return 0;
 
 	return memcmp(verity_io_real_digest(v, io), want_digest,

@@ -386,7 +386,7 @@ static int fec_decode_rsb(struct dm_veri
 	/* Always re-validate the corrected block against the expected hash */
 	r = verity_hash(v, verity_io_hash_req(v, io), fio->output,
 			1 << v->data_dev_block_bits,
-			verity_io_real_digest(v, io));
+			verity_io_real_digest(v, io), true);
 	if (unlikely(r < 0))
 		return r;
 

@@ -132,20 +132,21 @@ static int verity_hash_update(struct dm_
  * Wrapper for crypto_ahash_init, which handles verity salting.
  */
 static int verity_hash_init(struct dm_verity *v, struct ahash_request *req,
-				struct crypto_wait *wait)
+				struct crypto_wait *wait, bool may_sleep)
 {
 	int r;
 
 	ahash_request_set_tfm(req, v->tfm);
-	ahash_request_set_callback(req, CRYPTO_TFM_REQ_MAY_SLEEP |
-					CRYPTO_TFM_REQ_MAY_BACKLOG,
-					crypto_req_done, (void *)wait);
+	ahash_request_set_callback(req,
+		may_sleep ? CRYPTO_TFM_REQ_MAY_SLEEP | CRYPTO_TFM_REQ_MAY_BACKLOG : 0,
+		crypto_req_done, (void *)wait);
 	crypto_init_wait(wait);
 
 	r = crypto_wait_req(crypto_ahash_init(req), wait);
 
 	if (unlikely(r < 0)) {
-		DMERR("crypto_ahash_init failed: %d", r);
+		if (r != -ENOMEM)
+			DMERR("crypto_ahash_init failed: %d", r);
 		return r;
 	}
 

@@ -176,12 +177,12 @@ out:
 }
 
 int verity_hash(struct dm_verity *v, struct ahash_request *req,
-		const u8 *data, size_t len, u8 *digest)
+		const u8 *data, size_t len, u8 *digest, bool may_sleep)
 {
 	int r;
 	struct crypto_wait wait;
 
-	r = verity_hash_init(v, req, &wait);
+	r = verity_hash_init(v, req, &wait, may_sleep);
 	if (unlikely(r < 0))
 		goto out;
 

@@ -317,7 +318,7 @@ static int verity_verify_level(struct dm
 
 		r = verity_hash(v, verity_io_hash_req(v, io),
 				data, 1 << v->hash_dev_block_bits,
-				verity_io_real_digest(v, io));
+				verity_io_real_digest(v, io), !io->in_tasklet);
 		if (unlikely(r < 0))
 			goto release_ret_r;
 

@@ -548,7 +549,7 @@ static int verity_verify_io(struct dm_ve
 			continue;
 		}
 
-		r = verity_hash_init(v, req, &wait);
+		r = verity_hash_init(v, req, &wait, !io->in_tasklet);
 		if (unlikely(r < 0))
 			return r;
 

@@ -641,7 +642,7 @@ static void verity_tasklet(unsigned long
 
 	io->in_tasklet = true;
 	err = verity_verify_io(io);
-	if (err == -EAGAIN) {
+	if (err == -EAGAIN || err == -ENOMEM) {
 		/* fallback to retrying with work-queue */
 		INIT_WORK(&io->work, verity_work);
 		queue_work(io->v->verify_wq, &io->work);

@@ -1018,7 +1019,7 @@ static int verity_alloc_zero_digest(stru
 		goto out;
 
 	r = verity_hash(v, req, zero_data, 1 << v->data_dev_block_bits,
-			v->zero_digest);
+			v->zero_digest, true);
 
 out:
 	kfree(req);

@@ -128,7 +128,7 @@ extern int verity_for_bv_block(struct dm
 					      u8 *data, size_t len));
 
 extern int verity_hash(struct dm_verity *v, struct ahash_request *req,
-		       const u8 *data, size_t len, u8 *digest);
+		       const u8 *data, size_t len, u8 *digest, bool may_sleep);
 
 extern int verity_hash_for_block(struct dm_verity *v, struct dm_verity_io *io,
 				 sector_t block, u8 *digest, bool *is_zero);

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

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

From: Mahmoud Adam <[email protected]>

commit bc1b5acb40201a0746d68a7d7cfc141899937f4f upstream.

seq_release should be called to free the allocated seq_file

---
 fs/nfsd/nfs4state.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -2799,7 +2799,7 @@ static int client_opens_release(struct i
 
 	/* XXX: alternatively, we could get/drop in seq start/stop */
 	drop_client(clp);
-	return 0;
+	return seq_release(inode, file);
 }
 
 static const struct file_operations client_states_fops = {

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

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

From: Nathan Chancellor <[email protected]>

commit 71945968d8b128c955204baa33ec03bdd91bdc26 upstream.

A recent change to the optimization pipeline in LLVM reveals some fragility around the inlining of LoongArch's __percpu functions, which manifests as a BUILD_BUG() failure:

In file included from kernel/sched/build_policy.c:17:
In file included from include/linux/sched/cputime.h:5:
In file included from include/linux/sched/signal.h:5:
In file included from include/linux/rculist.h:11:
In file included from include/linux/rcupdate.h:26:
In file included from include/linux/irqflags.h:18:
arch/loongarch/include/asm/percpu.h:97:3: error: call to '__compiletime_assert_51' declared with 'error' attribute: BUILD_BUG failed

     97 |                 BUILD_BUG();
        |                 ^
  include/linux/build_bug.h:59:21: note: expanded from macro 'BUILD_BUG'
     59 | #define BUILD_BUG() BUILD_BUG_ON_MSG(1, "BUILD_BUG failed")
        |                     ^
  include/linux/build_bug.h:39:37: note: expanded from macro 'BUILD_BUG_ON_MSG'
     39 | #define BUILD_BUG_ON_MSG(cond, msg) compiletime_assert(!(cond), msg)
        |                                     ^
  include/linux/compiler_types.h:425:2: note: expanded from macro 'compiletime_assert'
    425 |         _compiletime_assert(condition, msg, __compiletime_assert_, __COUNTER__)
        |         ^
  include/linux/compiler_types.h:413:2: note: expanded from macro '_compiletime_assert'
    413 |         __compiletime_assert(condition, msg, prefix, suffix)
        |         ^
  include/linux/compiler_types.h:406:4: note: expanded from macro '__compiletime_assert'
    406 |                         prefix ## suffix();                             \
        |                         ^
  <scratch space>:86:1: note: expanded from here
     86 | __compiletime_assert_51
        | ^

1 error generated.

If these functions are not inlined (which the compiler is free to do even with functions marked with the standard 'inline' keyword), the BUILD_BUG() in the default case cannot be eliminated since the compiler cannot prove it is never used, resulting in a build failure due to the error attribute.

Mark these functions as __always_inline to guarantee inlining so that the BUILD_BUG() only triggers when the default case genuinely cannot be eliminated due to an unexpected size.

---
 arch/loongarch/include/asm/percpu.h |   10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

@@ -28,7 +28,7 @@ static inline void set_my_cpu_offset(uns
 #define __my_cpu_offset __my_cpu_offset
 
 #define PERCPU_OP(op, asm_op, c_op)					\
-static inline unsigned long __percpu_##op(void *ptr,			\
+static __always_inline unsigned long __percpu_##op(void *ptr,		\
 			unsigned long val, int size)			\
 {									\
 	unsigned long ret;						\

@@ -59,7 +59,7 @@ PERCPU_OP(and, and, &)
 PERCPU_OP(or, or, |)
 #undef PERCPU_OP
 
-static inline unsigned long __percpu_read(void *ptr, int size)
+static __always_inline unsigned long __percpu_read(void *ptr, int size)
 {
 	unsigned long ret;
 

@@ -96,7 +96,7 @@ static inline unsigned long __percpu_rea
 	return ret;
 }
 
-static inline void __percpu_write(void *ptr, unsigned long val, int size)
+static __always_inline void __percpu_write(void *ptr, unsigned long val, int size)
 {
 	switch (size) {
 	case 1:

@@ -128,8 +128,8 @@ static inline void __percpu_write(void *
 	}
 }
 
-static inline unsigned long __percpu_xchg(void *ptr, unsigned long val,
-						int size)
+static __always_inline unsigned long __percpu_xchg(void *ptr, unsigned long val,
+						   int size)
 {
 	switch (size) {
 	case 1:

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

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

From: Song Shuai <[email protected]>

commit 559fe94a449cba5b50a7cffea60474b385598c00 upstream.

Since the commit 011f09d12052 set sv57 as default for CONFIG_64BIT, the comment of CONFIG_PAGE_OFFSET should be updated too.

---
 arch/riscv/include/asm/page.h |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

@@ -38,8 +38,8 @@
 #define PAGE_OFFSET		_AC(CONFIG_PAGE_OFFSET, UL)
 #endif
 /*
- * By default, CONFIG_PAGE_OFFSET value corresponds to SV48 address space so
- * define the PAGE_OFFSET value for SV39.
+ * By default, CONFIG_PAGE_OFFSET value corresponds to SV57 address space so
+ * define the PAGE_OFFSET value for SV48 and SV39.
  */
 #define PAGE_OFFSET_L4		_AC(0xffffaf8000000000, UL)
 #define PAGE_OFFSET_L3		_AC(0xffffffd800000000, UL)

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

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

From: Song Shuai <[email protected]>

commit e59e5e2754bf983fc58ad18f99b5eec01f1a0745 upstream.

The pt_level uses CONFIG_PGTABLE_LEVELS to display page table names. But if page mode is downgraded from kernel cmdline or restricted by the hardware in 64BIT, it will give a wrong name.

Like, using no4lvl for sv39, ptdump named the 1G-mapping as "PUD" that should be "PGD":

0xffffffd840000000-0xffffffd900000000 0x00000000c0000000 3G PUD D A G . . W R V

So select "P4D/PUD" or "PGD" via pgtable_l5/4_enabled to correct it.

---
 arch/riscv/mm/ptdump.c | 3 +++
 1 file changed, 3 insertions(+)

index 20a9f991a6d7..e9090b38f811 100644
@@ -384,6 +384,9 @@ static int __init ptdump_init(void)
 
 	kernel_ptd_info.base_addr = KERN_VIRT_START;
 
+	pg_level[1].name = pgtable_l5_enabled ? "P4D" : "PGD";
+	pg_level[2].name = pgtable_l4_enabled ? "PUD" : "PGD";
+
 	for (i = 0; i < ARRAY_SIZE(pg_level); i++)
 		for (j = 0; j < ARRAY_SIZE(pte_bits); j++)
 			pg_level[i].mask |= pte_bits[j].mask;

2.43.0

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

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

From: Nam Cao <[email protected]>

commit 8cb22bec142624d21bc85ff96b7bad10b6220e6a upstream.

Instructions can write to x0, so we should simulate these instructions normally.

Currently, the kernel hangs if an instruction who writes to x0 is simulated.

---
 arch/riscv/kernel/probes/simulate-insn.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -24,7 +24,7 @@ static inline bool rv_insn_reg_set_val(s
 				       unsigned long val)
 {
 	if (index == 0)
-		return false;
+		return true;
 	else if (index <= 31)
 		*((unsigned long *)regs + index) = val;
 	else

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

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

From: Victor Shih <[email protected]>

commit d7133797e9e1b72fd89237f68cb36d745599ed86 upstream.

When GL9750 enters ASPM L1 sub-states, it will stay at L1.1 and will not enter L1.2. The workaround is to toggle PM state to allow GL9750 to enter ASPM L1.2.

---
 drivers/mmc/host/sdhci-pci-gli.c |   14 ++++++++++++++
 1 file changed, 14 insertions(+)

@@ -24,6 +24,9 @@
 #define   GLI_9750_WT_EN_ON	    0x1
 #define   GLI_9750_WT_EN_OFF	    0x0
 
+#define PCI_GLI_9750_PM_CTRL	0xFC
+#define   PCI_GLI_9750_PM_STATE	  GENMASK(1, 0)
+
 #define SDHCI_GLI_9750_CFG2          0x848
 #define   SDHCI_GLI_9750_CFG2_L1DLY    GENMASK(28, 24)
 #define   GLI_9750_CFG2_L1DLY_VALUE    0x1F

@@ -469,8 +472,12 @@ static void sdhci_gl9750_set_clock(struc
 
 static void gl9750_hw_setting(struct sdhci_host *host)
 {
+	struct sdhci_pci_slot *slot = sdhci_priv(host);
+	struct pci_dev *pdev;
 	u32 value;
 
+	pdev = slot->chip->pdev;
+
 	gl9750_wt_on(host);
 
 	value = sdhci_readl(host, SDHCI_GLI_9750_CFG2);

@@ -480,6 +487,13 @@ static void gl9750_hw_setting(struct sdh
 			    GLI_9750_CFG2_L1DLY_VALUE);
 	sdhci_writel(host, value, SDHCI_GLI_9750_CFG2);
 
+	/* toggle PM state to allow GL9750 to enter ASPM L1.2 */
+	pci_read_config_dword(pdev, PCI_GLI_9750_PM_CTRL, &value);
+	value |= PCI_GLI_9750_PM_STATE;
+	pci_write_config_dword(pdev, PCI_GLI_9750_PM_CTRL, value);
+	value &= ~PCI_GLI_9750_PM_STATE;
+	pci_write_config_dword(pdev, PCI_GLI_9750_PM_CTRL, value);
+
 	gl9750_wt_off(host);
 }
 

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

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

From: Stefan Roesch <[email protected]>

commit a48d5bdc877b85201e42cef9c2fdf5378164c23a upstream.

While qualifiying the 6.4 release, the following warning was detected in messages:

vmstat_refresh: nr_file_hugepages -15664

The warning is caused by the incorrect updating of the NR_FILE_THPS counter in the function split_huge_page_to_list. The if case is checking for folio_test_swapbacked, but the else case is missing the check for folio_test_pmd_mappable. The other functions that manipulate the counter like __filemap_add_folio and filemap_unaccount_folio have the corresponding check.

I have a test case, which reproduces the problem. It can be found here:
https://github.com/sroeschus/testcase/blob/main/vmstat_refresh/madv.c

The test case reproduces on an XFS filesystem. Running the same test case on a BTRFS filesystem does not reproduce the problem.

AFAIK version 6.1 until 6.6 are affected by this problem.

---
 mm/huge_memory.c |   16 +++++++++-------
 1 file changed, 9 insertions(+), 7 deletions(-)

@@ -2757,13 +2757,15 @@ int split_huge_page_to_list(struct page
 			int nr = folio_nr_pages(folio);
 
 			xas_split(&xas, folio, folio_order(folio));
-			if (folio_test_swapbacked(folio)) {
-				__lruvec_stat_mod_folio(folio, NR_SHMEM_THPS,
-							-nr);
-			} else {
-				__lruvec_stat_mod_folio(folio, NR_FILE_THPS,
-							-nr);
-				filemap_nr_thps_dec(mapping);
+			if (folio_test_pmd_mappable(folio)) {
+				if (folio_test_swapbacked(folio)) {
+					__lruvec_stat_mod_folio(folio,
+							NR_SHMEM_THPS, -nr);
+				} else {
+					__lruvec_stat_mod_folio(folio,
+							NR_FILE_THPS, -nr);
+					filemap_nr_thps_dec(mapping);
+				}
 			}
 		}
 

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

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

From: Roman Gushchin <[email protected]>

commit 24948e3b7b12e0031a6edb4f49bbb9fb2ad1e4e9 upstream.

Objcg vectors attached to slab pages to store slab object ownership information are allocated using gfp flags for the original slab allocation. Depending on slab page order and the size of slab objects, objcg vector can take several pages.

If the original allocation was done with the __GFP_NOFAIL flag, it triggered a warning in the page allocation code. Indeed, order > 1 pages should not been allocated with the __GFP_NOFAIL flag.

Fix this by simply dropping the __GFP_NOFAIL flag when allocating the objcg vector. It effectively allows to skip the accounting of a single slab object under a heavy memory pressure.

An alternative would be to implement the mechanism to fallback to order-0 allocations for accounting metadata, which is also not perfect because it will increase performance penalty and memory footprint of the kernel memory accounting under memory pressure.

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

@@ -2854,7 +2854,8 @@ static void commit_charge(struct folio *
  * Moreover, it should not come from DMA buffer and is not readily
  * reclaimable. So those GFP bits should be masked off.
  */
-#define OBJCGS_CLEAR_MASK	(__GFP_DMA | __GFP_RECLAIMABLE | __GFP_ACCOUNT)
+#define OBJCGS_CLEAR_MASK	(__GFP_DMA | __GFP_RECLAIMABLE | \
+				 __GFP_ACCOUNT | __GFP_NOFAIL)
 
 /*
  * mod_objcg_mlstate() may be called with irq enabled, so

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

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

From: Paolo Abeni <[email protected]>

commit 9fce92f050f448a0d1ddd9083ef967d9930f1e52 upstream.

After the blamed commit below, the TCP sockets (and the MPTCP subflows) can build egress packets larger than 64K. That exceeds the maximum DSS data size, the length being misrepresent on the wire and the stream being corrupted, as later observed on the receiver:

  WARNING: CPU: 0 PID: 9696 at net/mptcp/protocol.c:705 __mptcp_move_skbs_from_subflow+0x2604/0x26e0
  CPU: 0 PID: 9696 Comm: syz-executor.7 Not tainted 6.6.0-rc5-gcd8bdf563d46 #45
  Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.11.0-2.el7 04/01/2014
  netlink: 8 bytes leftover after parsing attributes in process `syz-executor.4'.
  RIP: 0010:__mptcp_move_skbs_from_subflow+0x2604/0x26e0 net/mptcp/protocol.c:705
  RSP: 0018:ffffc90000006e80 EFLAGS: 00010246
  RAX: ffffffff83e9f674 RBX: ffff88802f45d870 RCX: ffff888102ad0000
  netlink: 8 bytes leftover after parsing attributes in process `syz-executor.4'.
  RDX: 0000000080000303 RSI: 0000000000013908 RDI: 0000000000003908
  RBP: ffffc90000007110 R08: ffffffff83e9e078 R09: 1ffff1100e548c8a
  R10: dffffc0000000000 R11: ffffed100e548c8b R12: 0000000000013908
  R13: dffffc0000000000 R14: 0000000000003908 R15: 000000000031cf29
  FS:  00007f239c47e700(0000) GS:ffff88811b200000(0000) knlGS:0000000000000000
  CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
  CR2: 00007f239c45cd78 CR3: 000000006a66c006 CR4: 0000000000770ef0
  DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
  DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000600
  PKRU: 55555554
  Call Trace:
   <IRQ>
   mptcp_data_ready+0x263/0xac0 net/mptcp/protocol.c:819
   subflow_data_ready+0x268/0x6d0 net/mptcp/subflow.c:1409
   tcp_data_queue+0x21a1/0x7a60 net/ipv4/tcp_input.c:5151
   tcp_rcv_established+0x950/0x1d90 net/ipv4/tcp_input.c:6098
   tcp_v6_do_rcv+0x554/0x12f0 net/ipv6/tcp_ipv6.c:1483
   tcp_v6_rcv+0x2e26/0x3810 net/ipv6/tcp_ipv6.c:1749
   ip6_protocol_deliver_rcu+0xd6b/0x1ae0 net/ipv6/ip6_input.c:438
   ip6_input+0x1c5/0x470 net/ipv6/ip6_input.c:483
   ipv6_rcv+0xef/0x2c0 include/linux/netfilter.h:304
   __netif_receive_skb+0x1ea/0x6a0 net/core/dev.c:5532
   process_backlog+0x353/0x660 net/core/dev.c:5974
   __napi_poll+0xc6/0x5a0 net/core/dev.c:6536
   net_rx_action+0x6a0/0xfd0 net/core/dev.c:6603
   __do_softirq+0x184/0x524 kernel/softirq.c:553
   do_softirq+0xdd/0x130 kernel/softirq.c:454

Address the issue explicitly bounding the maximum GSO size to what MPTCP actually allows.

---
 net/mptcp/protocol.c |    4 ++++
 1 file changed, 4 insertions(+)

@@ -1275,6 +1275,8 @@ static void mptcp_update_infinite_map(st
 	mptcp_do_fallback(ssk);
 }
 
+#define MPTCP_MAX_GSO_SIZE (GSO_LEGACY_MAX_SIZE - (MAX_TCP_HEADER + 1))
+
 static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk,
 			      struct mptcp_data_frag *dfrag,
 			      struct mptcp_sendmsg_info *info)

@@ -1301,6 +1303,8 @@ static int mptcp_sendmsg_frag(struct soc
 		return -EAGAIN;
 
 	/* compute send limit */
+	if (unlikely(ssk->sk_gso_max_size > MPTCP_MAX_GSO_SIZE))
+		ssk->sk_gso_max_size = MPTCP_MAX_GSO_SIZE;
 	info->mss_now = tcp_send_mss(ssk, &info->size_goal, info->flags);
 	copy = info->size_goal;
 

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

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

From: Geliang Tang <[email protected]>

commit 8df220b29282e8b450ea57be62e1eccd4996837c upstream.

This patch adds the validity check for sending RM_ADDRs for userspace PM in mptcp_pm_remove_addrs(), only send a RM_ADDR when the address is in the anno_list or conn_list.

---
 net/mptcp/pm_netlink.c |    5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

@@ -1557,8 +1557,9 @@ void mptcp_pm_remove_addrs(struct mptcp_
 	struct mptcp_pm_addr_entry *entry;
 
 	list_for_each_entry(entry, rm_list, list) {
-		remove_anno_list_by_saddr(msk, &entry->addr);
-		if (alist.nr < MPTCP_RM_IDS_MAX)
+		if ((remove_anno_list_by_saddr(msk, &entry->addr) ||
+		     lookup_subflow_by_saddr(&msk->conn_list, &entry->addr)) &&
+		    alist.nr < MPTCP_RM_IDS_MAX)
 			alist.ids[alist.nr++] = entry->addr.id;
 	}
 

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

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

From: Paolo Abeni <[email protected]>

commit 7679d34f97b7a09fd565f5729f79fd61b7c55329 upstream.

The MPTCP implementation of the IP_TOS socket option uses the lockless variant of the TOS manipulation helper and does not hold such lock at the helper invocation time.

Add the required locking.

---
 net/mptcp/sockopt.c |    3 +++
 1 file changed, 3 insertions(+)

@@ -735,8 +735,11 @@ static int mptcp_setsockopt_v4_set_tos(s
 	val = inet_sk(sk)->tos;
 	mptcp_for_each_subflow(msk, subflow) {
 		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
+		bool slow;
 
+		slow = lock_sock_fast(ssk);
 		__ip_sock_set_tos(ssk, val);
+		unlock_sock_fast(ssk, slow);
 	}
 	release_sock(sk);
 

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

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

From: ChunHao Lin <[email protected]>

commit 868c3b95afef4883bfb66c9397482da6840b5baf upstream.

Device that support DASH may be reseted or powered off during suspend. So driver needs to handle DASH during system suspend and resume. Or DASH firmware will influence device behavior and causes network lost.

---
 drivers/net/ethernet/realtek/r8169_main.c |    6 ++++++
 1 file changed, 6 insertions(+)

@@ -4613,10 +4613,16 @@ static void rtl8169_down(struct rtl8169_
 	rtl8169_cleanup(tp);
 	rtl_disable_exit_l1(tp);
 	rtl_prepare_power_down(tp);
+
+	if (tp->dash_type != RTL_DASH_NONE)
+		rtl8168_driver_stop(tp);
 }
 
 static void rtl8169_up(struct rtl8169_private *tp)
 {
+	if (tp->dash_type != RTL_DASH_NONE)
+		rtl8168_driver_start(tp);
+
 	pci_set_master(tp->pci_dev);
 	phy_init_hw(tp->phydev);
 	phy_resume(tp->phydev);

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

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

From: ChunHao Lin <[email protected]>

commit 0ab0c45d8aaea5192328bfa6989673aceafc767c upstream.

For devices that support DASH, even DASH is disabled, there may still exist a default firmware that will influence device behavior. So driver needs to handle DASH for devices that support DASH, no matter the DASH status is.

This patch also prepares for "fix network lost after resume on DASH systems".

---
 drivers/net/ethernet/realtek/r8169_main.c |   36 ++++++++++++++++++++----------
 1 file changed, 25 insertions(+), 11 deletions(-)

@@ -614,6 +614,7 @@ struct rtl8169_private {
 
 	unsigned supports_gmii:1;
 	unsigned aspm_manageable:1;
+	unsigned dash_enabled:1;
 	dma_addr_t counters_phys_addr;
 	struct rtl8169_counters *counters;
 	struct rtl8169_tc_offsets tc_offset;

@@ -1186,14 +1187,26 @@ static bool r8168ep_check_dash(struct rt
 	return r8168ep_ocp_read(tp, 0x128) & BIT(0);
 }
 
-static enum rtl_dash_type rtl_check_dash(struct rtl8169_private *tp)
+static bool rtl_dash_is_enabled(struct rtl8169_private *tp)
+{
+	switch (tp->dash_type) {
+	case RTL_DASH_DP:
+		return r8168dp_check_dash(tp);
+	case RTL_DASH_EP:
+		return r8168ep_check_dash(tp);
+	default:
+		return false;
+	}
+}
+
+static enum rtl_dash_type rtl_get_dash_type(struct rtl8169_private *tp)
 {
 	switch (tp->mac_version) {
 	case RTL_GIGA_MAC_VER_28:
 	case RTL_GIGA_MAC_VER_31:
-		return r8168dp_check_dash(tp) ? RTL_DASH_DP : RTL_DASH_NONE;
+		return RTL_DASH_DP;
 	case RTL_GIGA_MAC_VER_51 ... RTL_GIGA_MAC_VER_53:
-		return r8168ep_check_dash(tp) ? RTL_DASH_EP : RTL_DASH_NONE;
+		return RTL_DASH_EP;
 	default:
 		return RTL_DASH_NONE;
 	}

@@ -1383,7 +1396,7 @@ static void __rtl8169_set_wol(struct rtl
 
 	device_set_wakeup_enable(tp_to_dev(tp), wolopts);
 
-	if (tp->dash_type == RTL_DASH_NONE) {
+	if (!tp->dash_enabled) {
 		rtl_set_d3_pll_down(tp, !wolopts);
 		tp->dev->wol_enabled = wolopts ? 1 : 0;
 	}

@@ -2442,7 +2455,7 @@ static void rtl_wol_enable_rx(struct rtl
 
 static void rtl_prepare_power_down(struct rtl8169_private *tp)
 {
-	if (tp->dash_type != RTL_DASH_NONE)
+	if (tp->dash_enabled)
 		return;
 
 	if (tp->mac_version == RTL_GIGA_MAC_VER_32 ||

@@ -4840,7 +4853,7 @@ static int rtl8169_runtime_idle(struct d
 {
 	struct rtl8169_private *tp = dev_get_drvdata(device);
 
-	if (tp->dash_type != RTL_DASH_NONE)
+	if (tp->dash_enabled)
 		return -EBUSY;
 
 	if (!netif_running(tp->dev) || !netif_carrier_ok(tp->dev))

@@ -4866,8 +4879,7 @@ static void rtl_shutdown(struct pci_dev
 	/* Restore original MAC address */
 	rtl_rar_set(tp, tp->dev->perm_addr);
 
-	if (system_state == SYSTEM_POWER_OFF &&
-	    tp->dash_type == RTL_DASH_NONE) {
+	if (system_state == SYSTEM_POWER_OFF && !tp->dash_enabled) {
 		pci_wake_from_d3(pdev, tp->saved_wolopts);
 		pci_set_power_state(pdev, PCI_D3hot);
 	}

@@ -5223,7 +5235,8 @@ static int rtl_init_one(struct pci_dev *
 		rc = pci_disable_link_state(pdev, PCIE_LINK_STATE_L1);
 	tp->aspm_manageable = !rc;
 
-	tp->dash_type = rtl_check_dash(tp);
+	tp->dash_type = rtl_get_dash_type(tp);
+	tp->dash_enabled = rtl_dash_is_enabled(tp);
 
 	tp->cp_cmd = RTL_R16(tp, CPlusCmd) & CPCMD_MASK;
 

@@ -5293,7 +5306,7 @@ static int rtl_init_one(struct pci_dev *
 	/* configure chip for default features */
 	rtl8169_set_features(dev, dev->features);
 
-	if (tp->dash_type == RTL_DASH_NONE) {
+	if (!tp->dash_enabled) {
 		rtl_set_d3_pll_down(tp, true);
 	} else {
 		rtl_set_d3_pll_down(tp, false);

@@ -5333,7 +5346,8 @@ static int rtl_init_one(struct pci_dev *
 			    "ok" : "ko");
 
 	if (tp->dash_type != RTL_DASH_NONE) {
-		netdev_info(dev, "DASH enabled\n");
+		netdev_info(dev, "DASH %s\n",
+			    tp->dash_enabled ? "enabled" : "disabled");
 		rtl8168_driver_start(tp);
 	}
 

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

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

From: Victor Shih <[email protected]>

commit 015c9cbcf0ad709079117d27c2094a46e0eadcdb upstream.

Due to a flaw in the hardware design, the GL9750 replay timer frequently times out when ASPM is enabled. As a result, the warning messages will often appear in the system log when the system accesses the GL9750 PCI config. Therefore, the replay timer timeout must be masked.

---
 drivers/mmc/host/sdhci-pci-gli.c |    8 ++++++++
 1 file changed, 8 insertions(+)

@@ -27,6 +27,9 @@
 #define PCI_GLI_9750_PM_CTRL	0xFC
 #define   PCI_GLI_9750_PM_STATE	  GENMASK(1, 0)
 
+#define PCI_GLI_9750_CORRERR_MASK				0x214
+#define   PCI_GLI_9750_CORRERR_MASK_REPLAY_TIMER_TIMEOUT	  BIT(12)
+
 #define SDHCI_GLI_9750_CFG2          0x848
 #define   SDHCI_GLI_9750_CFG2_L1DLY    GENMASK(28, 24)
 #define   GLI_9750_CFG2_L1DLY_VALUE    0x1F

@@ -494,6 +497,11 @@ static void gl9750_hw_setting(struct sdh
 	value &= ~PCI_GLI_9750_PM_STATE;
 	pci_write_config_dword(pdev, PCI_GLI_9750_PM_CTRL, value);
 
+	/* mask the replay timer timeout of AER */
+	pci_read_config_dword(pdev, PCI_GLI_9750_CORRERR_MASK, &value);
+	value |= PCI_GLI_9750_CORRERR_MASK_REPLAY_TIMER_TIMEOUT;
+	pci_write_config_dword(pdev, PCI_GLI_9750_CORRERR_MASK, value);
+
 	gl9750_wt_off(host);
 }
 

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

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

From: Bryan O'Donoghue <[email protected]>

commit 7405116519ad70b8c7340359bfac8db8279e7ce4 upstream.

We need to make sure camss_configure_pd() happens before camss_register_entities() as the vfe_get() path relies on the pointer provided by camss_configure_pd().

Fix the ordering sequence in probe to ensure the pointers vfe_get() demands are present by the time camss_register_entities() runs.

In order to facilitate backporting to stable kernels I've moved the configure_pd() call pretty early on the probe() function so that irrespective of the existence of the old error handling jump labels this patch should still apply to -next circa Aug 2023 to v5.13 inclusive.

---
 drivers/media/platform/qcom/camss/camss.c |   12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

@@ -1624,6 +1624,12 @@ static int camss_probe(struct platform_d
 	if (ret < 0)
 		goto err_cleanup;
 
+	ret = camss_configure_pd(camss);
+	if (ret < 0) {
+		dev_err(dev, "Failed to configure power domains: %d\n", ret);
+		goto err_cleanup;
+	}
+
 	ret = camss_init_subdevices(camss);
 	if (ret < 0)
 		goto err_cleanup;

@@ -1676,12 +1682,6 @@ static int camss_probe(struct platform_d
 		}
 	}
 
-	ret = camss_configure_pd(camss);
-	if (ret < 0) {
-		dev_err(dev, "Failed to configure power domains: %d\n", ret);
-		return ret;
-	}
-
 	pm_runtime_enable(dev);
 
 	return 0;

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

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

From: Bryan O'Donoghue <[email protected]>

commit 26bda3da00c3edef727a6acb00ed2eb4b22f8723 upstream.

Right now it is possible to do a vfe_get() with the internal reference count at 1. If vfe_check_clock_rates() returns non-zero then we will leave the reference count as-is and

run:
- pm_runtime_put_sync()
- vfe->ops->pm_domain_off()

skip:
- camss_disable_clocks()

Subsequent vfe_put() calls will when the ref-count is non-zero unconditionally run:

- pm_runtime_put_sync()
- vfe->ops->pm_domain_off()
- camss_disable_clocks()

vfe_get() should not attempt to roll-back on error when the ref-count is non-zero as the upper layers will still do their own vfe_put() operations.

vfe_put() will drop the reference count and do the necessary power domain release, the cleanup jumps in vfe_get() should only be run when the ref-count is zero.

[   50.095796] CPU: 7 PID: 3075 Comm: cam Not tainted 6.3.2+ #80
[   50.095798] Hardware name: LENOVO 21BXCTO1WW/21BXCTO1WW, BIOS N3HET82W (1.54 ) 05/26/2023
[   50.095799] pstate: 60400005 (nZCv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--)
[   50.095802] pc : refcount_warn_saturate+0xf4/0x148
[   50.095804] lr : refcount_warn_saturate+0xf4/0x148
[   50.095805] sp : ffff80000c7cb8b0
[   50.095806] x29: ffff80000c7cb8b0 x28: ffff16ecc0e3fc10 x27: 0000000000000000
[   50.095810] x26: 0000000000000000 x25: 0000000000020802 x24: 0000000000000000
[   50.095813] x23: ffff16ecc7360640 x22: 00000000ffffffff x21: 0000000000000005
[   50.095815] x20: ffff16ed175f4400 x19: ffffb4d9852942a8 x18: ffffffffffffffff
[   50.095818] x17: ffffb4d9852d4a48 x16: ffffb4d983da5db8 x15: ffff80000c7cb320
[   50.095821] x14: 0000000000000001 x13: 2e656572662d7265 x12: 7466612d65737520
[   50.095823] x11: 00000000ffffefff x10: ffffb4d9850cebf0 x9 : ffffb4d9835cf954
[   50.095826] x8 : 0000000000017fe8 x7 : c0000000ffffefff x6 : 0000000000057fa8
[   50.095829] x5 : ffff16f813fe3d08 x4 : 0000000000000000 x3 : ffff621e8f4d2000
[   50.095832] x2 : 0000000000000000 x1 : 0000000000000000 x0 : ffff16ed32119040
[   50.095835] Call trace:
[   50.095836]  refcount_warn_saturate+0xf4/0x148
[   50.095838]  device_link_put_kref+0x84/0xc8
[   50.095843]  device_link_del+0x38/0x58
[   50.095846]  vfe_pm_domain_off+0x3c/0x50 [qcom_camss]
[   50.095860]  vfe_put+0x114/0x140 [qcom_camss]
[   50.095869]  csid_set_power+0x2c8/0x408 [qcom_camss]
[   50.095878]  pipeline_pm_power_one+0x164/0x170 [videodev]
[   50.095896]  pipeline_pm_power+0xc4/0x110 [videodev]
[   50.095909]  v4l2_pipeline_pm_use+0x5c/0xa0 [videodev]
[   50.095923]  v4l2_pipeline_pm_get+0x1c/0x30 [videodev]
[   50.095937]  video_open+0x7c/0x100 [qcom_camss]
[   50.095945]  v4l2_open+0x84/0x130 [videodev]
[   50.095960]  chrdev_open+0xc8/0x250
[   50.095964]  do_dentry_open+0x1bc/0x498
[   50.095966]  vfs_open+0x34/0x40
[   50.095968]  path_openat+0xb44/0xf20
[   50.095971]  do_filp_open+0xa4/0x160
[   50.095974]  do_sys_openat2+0xc8/0x188
[   50.095975]  __arm64_sys_openat+0x6c/0xb8
[   50.095977]  invoke_syscall+0x50/0x128
[   50.095982]  el0_svc_common.constprop.0+0x4c/0x100
[   50.095985]  do_el0_svc+0x40/0xa8
[   50.095988]  el0_svc+0x2c/0x88
[   50.095991]  el0t_64_sync_handler+0xf4/0x120
[   50.095994]  el0t_64_sync+0x190/0x198
[   50.095996] ---[ end trace 0000000000000000 ]---

---
 drivers/media/platform/qcom/camss/camss-vfe.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -611,7 +611,7 @@ int vfe_get(struct vfe_device *vfe)
 	} else {
 		ret = vfe_check_clock_rates(vfe);
 		if (ret < 0)
-			goto error_pm_runtime_get;
+			goto error_pm_domain;
 	}
 	vfe->power_count++;
 

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

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

From: Bryan O'Donoghue <[email protected]>

commit 3143ad282fc08bf995ee73e32a9e40c527bf265d upstream.

There are two problems with the current vfe_disable_output() routine.

Firstly we rightly use a spinlock to protect output->gen2.active_num everywhere except for in the IDLE timeout path of vfe_disable_output(). Even if that is not racy "in practice" somehow it is by happenstance not by design.

Secondly we do not get consistent behaviour from this routine. On sc8280xp 50% of the time I get "VFE idle timeout - resetting". In this case the subsequent capture will succeed. The other 50% of the time, we don't hit the idle timeout, never do the VFE reset and subsequent captures stall indefinitely.

Rewrite the vfe_disable_output() routine to

- Quiesce write masters with vfe_wm_stop()
- Set active_num = 0

remembering to hold the spinlock when we do so followed by

- Reset the VFE

Testing on sc8280xp and sdm845 shows this to be a valid fix.

---
 drivers/media/platform/qcom/camss/camss-vfe-170.c |   22 +++-------------------
 1 file changed, 3 insertions(+), 19 deletions(-)

@@ -7,7 +7,6 @@
  * Copyright (C) 2020-2021 Linaro Ltd.
  */
 
-#include <linux/delay.h>
 #include <linux/interrupt.h>
 #include <linux/io.h>
 #include <linux/iopoll.h>

@@ -494,35 +493,20 @@ static int vfe_enable_output(struct vfe_
 	return 0;
 }
 
-static int vfe_disable_output(struct vfe_line *line)
+static void vfe_disable_output(struct vfe_line *line)
 {
 	struct vfe_device *vfe = to_vfe(line);
 	struct vfe_output *output = &line->output;
 	unsigned long flags;
 	unsigned int i;
-	bool done;
-	int timeout = 0;
-
-	do {
-		spin_lock_irqsave(&vfe->output_lock, flags);
-		done = !output->gen2.active_num;
-		spin_unlock_irqrestore(&vfe->output_lock, flags);
-		usleep_range(10000, 20000);
-
-		if (timeout++ == 100) {
-			dev_err(vfe->camss->dev, "VFE idle timeout - resetting\n");
-			vfe_reset(vfe);
-			output->gen2.active_num = 0;
-			return 0;
-		}
-	} while (!done);
 
 	spin_lock_irqsave(&vfe->output_lock, flags);
 	for (i = 0; i < output->wm_num; i++)
 		vfe_wm_stop(vfe, output->wm_idx[i]);
+	output->gen2.active_num = 0;
 	spin_unlock_irqrestore(&vfe->output_lock, flags);
 
-	return 0;
+	vfe_reset(vfe);
 }
 
 /*

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

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

From: Bryan O'Donoghue <[email protected]>

commit 7f24d291350426d40b36dfbe6b3090617cdfd37a upstream.

vfe-480 is copied from vfe-17x and has the same racy idle timeout bug as in 17x.

Fix the vfe_disable_output() logic to no longer be racy and to conform to the 17x way of quiescing and then resetting the VFE.

---
 drivers/media/platform/qcom/camss/camss-vfe-480.c |   22 +++-------------------
 1 file changed, 3 insertions(+), 19 deletions(-)

@@ -8,7 +8,6 @@
  * Copyright (C) 2021 Jonathan Marek
  */
 
-#include <linux/delay.h>
 #include <linux/interrupt.h>
 #include <linux/io.h>
 #include <linux/iopoll.h>

@@ -311,35 +310,20 @@ static int vfe_enable_output(struct vfe_
 	return 0;
 }
 
-static int vfe_disable_output(struct vfe_line *line)
+static void vfe_disable_output(struct vfe_line *line)
 {
 	struct vfe_device *vfe = to_vfe(line);
 	struct vfe_output *output = &line->output;
 	unsigned long flags;
 	unsigned int i;
-	bool done;
-	int timeout = 0;
-
-	do {
-		spin_lock_irqsave(&vfe->output_lock, flags);
-		done = !output->gen2.active_num;
-		spin_unlock_irqrestore(&vfe->output_lock, flags);
-		usleep_range(10000, 20000);
-
-		if (timeout++ == 100) {
-			dev_err(vfe->camss->dev, "VFE idle timeout - resetting\n");
-			vfe_reset(vfe);
-			output->gen2.active_num = 0;
-			return 0;
-		}
-	} while (!done);
 
 	spin_lock_irqsave(&vfe->output_lock, flags);
 	for (i = 0; i < output->wm_num; i++)
 		vfe_wm_stop(vfe, output->wm_idx[i]);
+	output->gen2.active_num = 0;
 	spin_unlock_irqrestore(&vfe->output_lock, flags);
 
-	return 0;
+	vfe_reset(vfe);
 }
 
 /*

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

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

From: Bryan O'Donoghue <[email protected]>

commit b6e1bdca463a932c1ac02caa7d3e14bf39288e0c upstream.

check_clock doesn't account for vfe_lite which means that vfe_lite will never get validated by this routine. Add the clock name to the expected set to remediate.

---
 drivers/media/platform/qcom/camss/camss-vfe.c |    3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

@@ -535,7 +535,8 @@ static int vfe_check_clock_rates(struct
 		struct camss_clock *clock = &vfe->clock[i];
 
 		if (!strcmp(clock->name, "vfe0") ||
-		    !strcmp(clock->name, "vfe1")) {
+		    !strcmp(clock->name, "vfe1") ||
+		    !strcmp(clock->name, "vfe_lite")) {
 			u64 min_rate = 0;
 			unsigned long rate;
 

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

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

From: Bryan O'Donoghue <[email protected]>

commit d8f7e1a60d01739a1d78db2b08603089c6cf7c8e upstream.

define CSIPHY_3PH_CMN_CSI_COMMON_CTRL5_CLK_ENABLE BIT(7)

disjunction for gen2 ? BIT(7) : is a nop we are setting the same bit either way.

---
 drivers/media/platform/qcom/camss/camss-csiphy-3ph-1-0.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -476,7 +476,7 @@ static void csiphy_lanes_enable(struct c
 
 	settle_cnt = csiphy_settle_cnt_calc(link_freq, csiphy->timer_clk_rate);
 
-	val = is_gen2 ? BIT(7) : CSIPHY_3PH_CMN_CSI_COMMON_CTRL5_CLK_ENABLE;
+	val = CSIPHY_3PH_CMN_CSI_COMMON_CTRL5_CLK_ENABLE;
 	for (i = 0; i < c->num_data; i++)
 		val |= BIT(c->data[i].pos * 2);
 

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

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

From: Andrey Konovalov <[email protected]>

commit 87889f1b7ea40d2544b49c62092e6ef2792dced7 upstream.

In the current driver csid Test Pattern Generator (TPG) doesn't work. This change:
- fixes writing frame width and height values into CSID_TPG_DT_n_CFG_0
- fixes the shift by one between test_pattern control value and the actual pattern.
- drops fixed VC of 0x0a which testing showed prohibited some test patterns in the CSID to produce output.
So that TPG starts working, but with the below limitations:
- only test_pattern=9 works as it should
- test_pattern=8 and test_pattern=7 produce black frame (all zeroes)
- the rest of test_pattern's don't work (yavta doesn't get the data)
- regardless of the CFA pattern set by 'media-ctl -V' the actual pixel order is always the same (RGGB for any RAW8 or RAW10P format in 4608x2592 resolution).

Tested with:

RAW10P format, VC0:
media-ctl -V '"msm_csid0":0[fmt:SRGGB10/4608x2592 field:none]' media-ctl -V '"msm_vfe0_rdi0":0[fmt:SRGGB10/4608x2592 field:none]' media-ctl -l '"msm_csid0":1->"msm_vfe0_rdi0":0[1]'
v4l2-ctl -d /dev/v4l-subdev6 -c test_pattern=9
yavta -B capture-mplane --capture=3 -n 3 -f SRGGB10P -s 4608x2592 /dev/video0

RAW10P format, VC1:
media-ctl -V '"msm_csid0":2[fmt:SRGGB10/4608x2592 field:none]' media-ctl -V '"msm_vfe0_rdi1":0[fmt:SRGGB10/4608x2592 field:none]' media-ctl -l '"msm_csid0":2->"msm_vfe0_rdi1":0[1]'
v4l2-ctl -d /dev/v4l-subdev6 -c test_pattern=9
yavta -B capture-mplane --capture=3 -n 3 -f SRGGB10P -s 4608x2592 /dev/video1

RAW8 format, VC0:
media-ctl --reset
media-ctl -V '"msm_csid0":0[fmt:SRGGB8/4608x2592 field:none]' media-ctl -V '"msm_vfe0_rdi0":0[fmt:SRGGB8/4608x2592 field:none]' media-ctl -l '"msm_csid0":1->"msm_vfe0_rdi0":0[1]'
yavta -B capture-mplane --capture=3 -n 3 -f SRGGB8 -s 4608x2592 /dev/video0

---
 drivers/media/platform/qcom/camss/camss-csid-gen2.c |    9 +++------
 1 file changed, 3 insertions(+), 6 deletions(-)

@@ -355,9 +355,6 @@ static void csid_configure_stream(struct
 		u8 dt_id = vc * 4;
 
 		if (tg->enabled) {
-			/* Config Test Generator */
-			vc = 0xa;
-
 			/* configure one DT, infinite frames */
 			val = vc << TPG_VC_CFG0_VC_NUM;
 			val |= INTELEAVING_MODE_ONE_SHOT << TPG_VC_CFG0_LINE_INTERLEAVING_MODE;

@@ -370,14 +367,14 @@ static void csid_configure_stream(struct
 
 			writel_relaxed(0x12345678, csid->base + CSID_TPG_LFSR_SEED);
 
-			val = input_format->height & 0x1fff << TPG_DT_n_CFG_0_FRAME_HEIGHT;
-			val |= input_format->width & 0x1fff << TPG_DT_n_CFG_0_FRAME_WIDTH;
+			val = (input_format->height & 0x1fff) << TPG_DT_n_CFG_0_FRAME_HEIGHT;
+			val |= (input_format->width & 0x1fff) << TPG_DT_n_CFG_0_FRAME_WIDTH;
 			writel_relaxed(val, csid->base + CSID_TPG_DT_n_CFG_0(0));
 
 			val = format->data_type << TPG_DT_n_CFG_1_DATA_TYPE;
 			writel_relaxed(val, csid->base + CSID_TPG_DT_n_CFG_1(0));
 
-			val = tg->mode << TPG_DT_n_CFG_2_PAYLOAD_MODE;
+			val = (tg->mode - 1) << TPG_DT_n_CFG_2_PAYLOAD_MODE;
 			val |= 0xBE << TPG_DT_n_CFG_2_USER_SPECIFIED_PAYLOAD;
 			val |= format->decode_format << TPG_DT_n_CFG_2_ENCODE_FORMAT;
 			writel_relaxed(val, csid->base + CSID_TPG_DT_n_CFG_2(0));

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

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

From: Heiner Kallweit <[email protected]>

commit 6a26310273c323380da21eb23fcfd50e31140913 upstream.

This reverts commit efa5f1311c4998e9e6317c52bc5ee93b3a0f36df.

I couldn't reproduce the reported issue. What I did, based on a pcap packet log provided by the reporter:
- Used same chip version (RTL8168h)
- Set MAC address to the one used on the reporters system
- Replayed the EAPOL unicast packet that, according to the reporter, was filtered out by the mc filter.
The packet was properly received.

Therefore the root cause of the reported issue seems to be somewhere else. Disabling mc filtering completely for the most common chip version is a quite big hammer. Therefore revert the change and wait for further analysis results from the reporter.

---
 drivers/net/ethernet/realtek/r8169_main.c |    4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

@@ -2529,9 +2529,7 @@ static void rtl_set_rx_mode(struct net_d
 		rx_mode &= ~AcceptMulticast;
 	} else if (netdev_mc_count(dev) > MC_FILTER_LIMIT ||
 		   dev->flags & IFF_ALLMULTI ||
-		   tp->mac_version == RTL_GIGA_MAC_VER_35 ||
-		   tp->mac_version == RTL_GIGA_MAC_VER_46 ||
-		   tp->mac_version == RTL_GIGA_MAC_VER_48) {
+		   tp->mac_version == RTL_GIGA_MAC_VER_35) {
 		/* accept all multicasts */
 	} else if (netdev_mc_empty(dev)) {
 		rx_mode &= ~AcceptMulticast;

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

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

From: Max Kellermann <[email protected]>

commit 484fd6c1de13b336806a967908a927cc0356e312 upstream.

The function ext4_init_acl() calls posix_acl_create() which is responsible for applying the umask. But without CONFIG_EXT4_FS_POSIX_ACL, ext4_init_acl() is an empty inline function, and nobody applies the umask.

This fixes a bug which causes the umask to be ignored with O_TMPFILE on ext4:

https://github.com/MusicPlayerDaemon/MPD/issues/558
https://bugs.gentoo.org/show_bug.cgi?id=686142#c3
https://bugzilla.kernel.org/show_bug.cgi?id=203625

---
 fs/ext4/acl.h |    5 +++++
 1 file changed, 5 insertions(+)

@@ -68,6 +68,11 @@ extern int ext4_init_acl(handle_t *, str
 static inline int
 ext4_init_acl(handle_t *handle, struct inode *inode, struct inode *dir)
 {
+	/* usually, the umask is applied by posix_acl_create(), but if
+	   ext4 ACL support is disabled at compile time, we need to do
+	   it here, because posix_acl_create() will never be called */
+	inode->i_mode &= ~current_umask();
+
 	return 0;
 }
 #endif  /* CONFIG_EXT4_FS_POSIX_ACL */

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

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

From: Kemeng Shi <[email protected]>

commit 31f13421c004a420c0e9d288859c9ea9259ea0cc upstream.

Commit 0aeaa2559d6d5 ("ext4: fix corruption when online resizing a 1K bigalloc fs") found that primary superblock's offset in its group is not equal to offset of backup superblock in its group when block size is 1K and bigalloc is enabled. As group descriptor blocks are right after superblock, we can't pass block number of gdb to update_backups for the same reason.

The root casue of the issue above is that leading 1K padding block is count as data block offset for primary block while backup block has no padding block offset in its group.

Remove padding data block count to fix the issue for gdb backups.

For meta_bg case, update_backups treat blk_off as block number, do no conversion in this case.

---
 fs/ext4/resize.c |    6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

@@ -1602,6 +1602,8 @@ exit_journal:
 		int gdb_num_end = ((group + flex_gd->count - 1) /
 				   EXT4_DESC_PER_BLOCK(sb));
 		int meta_bg = ext4_has_feature_meta_bg(sb);
+		sector_t padding_blocks = meta_bg ? 0 : sbi->s_sbh->b_blocknr -
+					 ext4_group_first_block_no(sb, 0);
 		sector_t old_gdb = 0;
 
 		update_backups(sb, ext4_group_first_block_no(sb, 0),

@@ -1613,8 +1615,8 @@ exit_journal:
 						     gdb_num);
 			if (old_gdb == gdb_bh->b_blocknr)
 				continue;
-			update_backups(sb, gdb_bh->b_blocknr, gdb_bh->b_data,
-				       gdb_bh->b_size, meta_bg);
+			update_backups(sb, gdb_bh->b_blocknr - padding_blocks,
+				       gdb_bh->b_data, gdb_bh->b_size, meta_bg);
 			old_gdb = gdb_bh->b_blocknr;
 		}
 	}

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

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

From: Ojaswin Mujoo <[email protected]>

commit 2cd8bdb5efc1e0d5b11a4b7ba6b922fd2736a87f upstream.

** Short Version **

In ext4 with dioread_nolock, we could have a scenario where the bh returned by get_blocks (ext4_get_block_unwritten()) in __block_write_begin_int() has UNWRITTEN and MAPPED flag set. Since such a bh does not have NEW flag set we never zero out the range of bh that is not under write, causing whatever stale data is present in the folio at that time to be written out to disk. To fix this mark the buffer as new, in case it is unwritten, in ext4_get_block_unwritten().

** Long Version **

The issue mentioned above was resulting in two different bugs:

1. On block size < page size case in ext4, generic/269 was reliably failing with dioread_nolock. The state of the write was as follows:

* The write was extending i_size.
* The last block of the file was fallocated and had an unwritten extent
* We were near ENOSPC and hence we were switching to non-delayed alloc allocation.

In this case, the back trace that triggers the bug is as follows:

ext4_da_write_begin()

    /* switch to nodelalloc due to low space */
    ext4_write_begin()
      ext4_should_dioread_nolock() // true since mount flags still have delalloc
      __block_write_begin(..., ext4_get_block_unwritten)
        __block_write_begin_int()
          for(each buffer head in page) {
            /* first iteration, this is bh1 which contains i_size */
            if (!buffer_mapped)
              get_block() /* returns bh with only UNWRITTEN and MAPPED */
            /* second iteration, bh2 */
              if (!buffer_mapped)
                get_block() /* we fail here, could be ENOSPC */
          }
          if (err)
            /*
             * this would zero out all new buffers and mark them uptodate.
             * Since bh1 was never marked new, we skip it here which causes
             * the bug later.
             */
            folio_zero_new_buffers();
      /* ext4_wrte_begin() error handling */
      ext4_truncate_failed_write()
        ext4_truncate()
          ext4_block_truncate_page()
            __ext4_block_zero_page_range()
              if(!buffer_uptodate())
                ext4_read_bh_lock()
                  ext4_read_bh() -> ... ext4_submit_bh_wbc()
                    BUG_ON(buffer_unwritten(bh)); /* !!! */

2. The second issue is stale data exposure with page size >= blocksize with dioread_nolock. The conditions needed for it to happen are same as the previous issue ie dioread_nolock around ENOSPC condition. The issue is also similar where in __block_write_begin_int() when we call ext4_get_block_unwritten() on the buffer_head and the underlying extent is unwritten, we get an unwritten and mapped buffer head. Since it is not new, we never zero out the partial range which is not under write, thus writing stale data to disk. This can be easily observed with the following reproducer:

fallocate -l 4k testfile
xfs_io -c "pwrite 2k 2k" testfile

 # hexdump output will have stale data in from byte 0 to 2k in testfile
 hexdump -C testfile

NOTE: To trigger this, we need dioread_nolock enabled and write happening via ext4_write_begin(), which is usually used when we have -o nodealloc. Since dioread_nolock is disabled with nodelalloc, the only alternate way to call ext4_write_begin() is to ensure that delayed alloc switches to nodelalloc ie ext4_da_write_begin() calls ext4_write_begin(). This will usually happen when ext4 is almost full like the way generic/269 was triggering it in Issue 1 above. This might make the issue harder to hit. Hence, for reliable replication, I used the below patch to temporarily allow dioread_nolock with nodelalloc and then mount the disk with -o nodealloc,dioread_nolock. With this you can hit the stale data issue 100% of times:

@@ -508,8 +508,8 @@ static inline int ext4_should_dioread_nolock(struct inode *inode)
if (ext4_should_journal_data(inode))

    return 0;

/* temporary fix to prevent generic/422 test failures */
- if (!test_opt(inode->i_sb, DELALLOC))
- return 0;
+ // if (!test_opt(inode->i_sb, DELALLOC))
+ // return 0;
return 1;
}

After applying this patch to mark buffer as NEW, both the above issues are fixed.

---
 fs/ext4/inode.c |   14 +++++++++++++-
 1 file changed, 13 insertions(+), 1 deletion(-)

@@ -824,10 +824,22 @@ int ext4_get_block(struct inode *inode,
 int ext4_get_block_unwritten(struct inode *inode, sector_t iblock,
 			     struct buffer_head *bh_result, int create)
 {
+	int ret = 0;
+
 	ext4_debug("ext4_get_block_unwritten: inode %lu, create flag %d\n",
 		   inode->i_ino, create);
-	return _ext4_get_block(inode, iblock, bh_result,
+	ret = _ext4_get_block(inode, iblock, bh_result,
 			       EXT4_GET_BLOCKS_CREATE_UNWRIT_EXT);
+
+	/*
+	 * If the buffer is marked unwritten, mark it as new to make sure it is
+	 * zeroed out correctly in case of partial writes. Otherwise, there is
+	 * a chance of stale data getting exposed.
+	 */
+	if (ret == 0 && buffer_unwritten(bh_result))
+		set_buffer_new(bh_result);
+
+	return ret;
 }
 
 /* Maximum number of blocks we map for direct IO at once. */

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

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

From: Kemeng Shi <[email protected]>

commit 48f1551592c54f7d8e2befc72a99ff4e47f7dca0 upstream.

Avoid to ignore error in "err".

---
 fs/ext4/resize.c |    4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

@@ -1985,9 +1985,7 @@ static int ext4_convert_meta_bg(struct s
 
 errout:
 	ret = ext4_journal_stop(handle);
-	if (!err)
-		err = ret;
-	return ret;
+	return err ? err : ret;
 
 invalid_resize_inode:
 	ext4_error(sb, "corrupted/inconsistent resize inode");

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

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

From: Zhang Yi <[email protected]>

commit 40ea98396a3659062267d1fe5f99af4f7e4f05e3 upstream.

When big allocate feature is enabled, we need to count and update reserved clusters before removing a delayed only extent_status entry. {init|count|get}_rsvd() have already done this, but the start block number of this counting isn't correct in the following case.

lblk end

   |               |
   v               v

-------------------------
| | orig_es
-------------------------
^ ^
len1 is 0 | len2 |

If the start block of the orig_es entry founded is bigger than lblk, we passed lblk as start block to count_rsvd(), but the length is correct, finally, the range to be counted is offset. This patch fix this by passing the start blocks to 'orig_es->lblk + len1'.

---
 fs/ext4/extents_status.c |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

@@ -1365,8 +1365,8 @@ retry:
 			}
 		}
 		if (count_reserved)
-			count_rsvd(inode, lblk, orig_es.es_len - len1 - len2,
-				   &orig_es, &rc);
+			count_rsvd(inode, orig_es.es_lblk + len1,
+				   orig_es.es_len - len1 - len2, &orig_es, &rc);
 		goto out_get_reserved;
 	}
 

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

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

From: Kemeng Shi <[email protected]>

commit 40dd7953f4d606c280074f10d23046b6812708ce upstream.

Wrong check of gdb backup in meta bg as following:
first_group is the first group of meta_bg which contains target group, so target group is always >= first_group. We check if target group has gdb backup by comparing first_group with [group + 1] and [group + EXT4_DESC_PER_BLOCK(sb) - 1]. As group >= first_group, then [group + N] is

setup_new_flex_group_blocks.

No need to do gdb backup copy in meta bg from setup_new_flex_group_blocks as we always copy updated gdb block to backups at end of ext4_flex_group_add as following:

ext4_flex_group_add
/* no gdb backup copy for meta bg any more */
setup_new_flex_group_blocks

  /* update current group number */
  ext4_update_super
    sbi->s_groups_count += flex_gd->count;

/*
* if group in meta bg contains backup is added, the primary gdb block
* of the meta bg will be copy to backup in new added group here. */
for (; gdb_num <= gdb_num_end; gdb_num++)

    update_backups(...)

In summary, we can remove wrong gdb backup copy code in setup_new_flex_group_blocks.

---
 fs/ext4/resize.c |    9 ++-------
 1 file changed, 2 insertions(+), 7 deletions(-)

@@ -560,13 +560,8 @@ static int setup_new_flex_group_blocks(s
 		if (meta_bg == 0 && !ext4_bg_has_super(sb, group))
 			goto handle_itb;
 
-		if (meta_bg == 1) {
-			ext4_group_t first_group;
-			first_group = ext4_meta_bg_first_group(sb, group);
-			if (first_group != group + 1 &&
-			    first_group != group + EXT4_DESC_PER_BLOCK(sb) - 1)
-				goto handle_itb;
-		}
+		if (meta_bg == 1)
+			goto handle_itb;
 
 		block = start + ext4_bg_has_super(sb, group);
 		/* Copy all of the GDT blocks into the backup in this group */

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

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

From: Kemeng Shi <[email protected]>

commit 9adac8b01f4be28acd5838aade42b8daa4f0b642 upstream.

add missed brelse in update_backups

---
 fs/ext4/resize.c |    4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

@@ -1186,8 +1186,10 @@ static void update_backups(struct super_
 			   ext4_group_first_block_no(sb, group));
 		BUFFER_TRACE(bh, "get_write_access");
 		if ((err = ext4_journal_get_write_access(handle, sb, bh,
-							 EXT4_JTR_NONE)))
+							 EXT4_JTR_NONE))) {
+			brelse(bh);
 			break;
+		}
 		lock_buffer(bh);
 		memcpy(bh->b_data, data, size);
 		if (rest)

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

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

From: Jan Kara <[email protected]>

commit 91562895f8030cb9a0470b1db49de79346a69f91 upstream.

Gao Xiang has reported that on ext4 O_SYNC direct IO does not properly sync file size update and thus if we crash at unfortunate moment, the file can have smaller size although O_SYNC IO has reported successful completion. The problem happens because update of on-disk inode size is handled in ext4_dio_write_iter() *after* iomap_dio_rw() (and thus dio_complete() in particular) has returned and generic_file_sync() gets called by dio_complete(). Fix the problem by handling on-disk inode size update directly in our ->end_io completion handler.

References: https://lore.kernel.org/all/[email protected]

---
 fs/ext4/file.c |  153 ++++++++++++++++++++++++---------------------------------
 1 file changed, 65 insertions(+), 88 deletions(-)

@@ -296,80 +296,38 @@ out:
 }
 
 static ssize_t ext4_handle_inode_extension(struct inode *inode, loff_t offset,
-					   ssize_t written, size_t count)
+					   ssize_t count)
 {
 	handle_t *handle;
-	bool truncate = false;
-	u8 blkbits = inode->i_blkbits;
-	ext4_lblk_t written_blk, end_blk;
-	int ret;
-
-	/*
-	 * Note that EXT4_I(inode)->i_disksize can get extended up to
-	 * inode->i_size while the I/O was running due to writeback of delalloc
-	 * blocks. But, the code in ext4_iomap_alloc() is careful to use
-	 * zeroed/unwritten extents if this is possible; thus we won't leave
-	 * uninitialized blocks in a file even if we didn't succeed in writing
-	 * as much as we intended.
-	 */
-	WARN_ON_ONCE(i_size_read(inode) < EXT4_I(inode)->i_disksize);
-	if (offset + count <= EXT4_I(inode)->i_disksize) {
-		/*
-		 * We need to ensure that the inode is removed from the orphan
-		 * list if it has been added prematurely, due to writeback of
-		 * delalloc blocks.
-		 */
-		if (!list_empty(&EXT4_I(inode)->i_orphan) && inode->i_nlink) {
-			handle = ext4_journal_start(inode, EXT4_HT_INODE, 2);
-
-			if (IS_ERR(handle)) {
-				ext4_orphan_del(NULL, inode);
-				return PTR_ERR(handle);
-			}
-
-			ext4_orphan_del(handle, inode);
-			ext4_journal_stop(handle);
-		}
-
-		return written;
-	}
-
-	if (written < 0)
-		goto truncate;
 
+	lockdep_assert_held_write(&inode->i_rwsem);
 	handle = ext4_journal_start(inode, EXT4_HT_INODE, 2);
-	if (IS_ERR(handle)) {
-		written = PTR_ERR(handle);
-		goto truncate;
-	}
+	if (IS_ERR(handle))
+		return PTR_ERR(handle);
 
-	if (ext4_update_inode_size(inode, offset + written)) {
-		ret = ext4_mark_inode_dirty(handle, inode);
+	if (ext4_update_inode_size(inode, offset + count)) {
+		int ret = ext4_mark_inode_dirty(handle, inode);
 		if (unlikely(ret)) {
-			written = ret;
 			ext4_journal_stop(handle);
-			goto truncate;
+			return ret;
 		}
 	}
 
-	/*
-	 * We may need to truncate allocated but not written blocks beyond EOF.
-	 */
-	written_blk = ALIGN(offset + written, 1 << blkbits);
-	end_blk = ALIGN(offset + count, 1 << blkbits);
-	if (written_blk < end_blk && ext4_can_truncate(inode))
-		truncate = true;
-
-	/*
-	 * Remove the inode from the orphan list if it has been extended and
-	 * everything went OK.
-	 */
-	if (!truncate && inode->i_nlink)
+	if (inode->i_nlink)
 		ext4_orphan_del(handle, inode);
 	ext4_journal_stop(handle);
 
-	if (truncate) {
-truncate:
+	return count;
+}
+
+/*
+ * Clean up the inode after DIO or DAX extending write has completed and the
+ * inode size has been updated using ext4_handle_inode_extension().
+ */
+static void ext4_inode_extension_cleanup(struct inode *inode, ssize_t count)
+{
+	lockdep_assert_held_write(&inode->i_rwsem);
+	if (count < 0) {
 		ext4_truncate_failed_write(inode);
 		/*
 		 * If the truncate operation failed early, then the inode may

@@ -378,9 +336,28 @@ truncate:
 		 */
 		if (inode->i_nlink)
 			ext4_orphan_del(NULL, inode);
+		return;
 	}
+	/*
+	 * If i_disksize got extended due to writeback of delalloc blocks while
+	 * the DIO was running we could fail to cleanup the orphan list in
+	 * ext4_handle_inode_extension(). Do it now.
+	 */
+	if (!list_empty(&EXT4_I(inode)->i_orphan) && inode->i_nlink) {
+		handle_t *handle = ext4_journal_start(inode, EXT4_HT_INODE, 2);
 
-	return written;
+		if (IS_ERR(handle)) {
+			/*
+			 * The write has successfully completed. Not much to
+			 * do with the error here so just cleanup the orphan
+			 * list and hope for the best.
+			 */
+			ext4_orphan_del(NULL, inode);
+			return;
+		}
+		ext4_orphan_del(handle, inode);
+		ext4_journal_stop(handle);
+	}
 }
 
 static int ext4_dio_write_end_io(struct kiocb *iocb, ssize_t size,

@@ -389,31 +366,22 @@ static int ext4_dio_write_end_io(struct
 	loff_t pos = iocb->ki_pos;
 	struct inode *inode = file_inode(iocb->ki_filp);
 
+	if (!error && size && flags & IOMAP_DIO_UNWRITTEN)
+		error = ext4_convert_unwritten_extents(NULL, inode, pos, size);
 	if (error)
 		return error;
-
-	if (size && flags & IOMAP_DIO_UNWRITTEN) {
-		error = ext4_convert_unwritten_extents(NULL, inode, pos, size);
-		if (error < 0)
-			return error;
-	}
 	/*
-	 * If we are extending the file, we have to update i_size here before
-	 * page cache gets invalidated in iomap_dio_rw(). Otherwise racing
-	 * buffered reads could zero out too much from page cache pages. Update
-	 * of on-disk size will happen later in ext4_dio_write_iter() where
-	 * we have enough information to also perform orphan list handling etc.
-	 * Note that we perform all extending writes synchronously under
-	 * i_rwsem held exclusively so i_size update is safe here in that case.
-	 * If the write was not extending, we cannot see pos > i_size here
-	 * because operations reducing i_size like truncate wait for all
-	 * outstanding DIO before updating i_size.
+	 * Note that EXT4_I(inode)->i_disksize can get extended up to
+	 * inode->i_size while the I/O was running due to writeback of delalloc
+	 * blocks. But the code in ext4_iomap_alloc() is careful to use
+	 * zeroed/unwritten extents if this is possible; thus we won't leave
+	 * uninitialized blocks in a file even if we didn't succeed in writing
+	 * as much as we intended.
 	 */
-	pos += size;
-	if (pos > i_size_read(inode))
-		i_size_write(inode, pos);
-
-	return 0;
+	WARN_ON_ONCE(i_size_read(inode) < READ_ONCE(EXT4_I(inode)->i_disksize));
+	if (pos + size <= READ_ONCE(EXT4_I(inode)->i_disksize))
+		return size;
+	return ext4_handle_inode_extension(inode, pos, size);
 }
 
 static const struct iomap_dio_ops ext4_dio_write_ops = {

@@ -589,9 +557,16 @@ static ssize_t ext4_dio_write_iter(struc
 			   NULL, 0);
 	if (ret == -ENOTBLK)
 		ret = 0;
-
-	if (extend)
-		ret = ext4_handle_inode_extension(inode, offset, ret, count);
+	if (extend) {
+		/*
+		 * We always perform extending DIO write synchronously so by
+		 * now the IO is completed and ext4_handle_inode_extension()
+		 * was called. Cleanup the inode in case of error or race with
+		 * writeback of delalloc blocks.
+		 */
+		WARN_ON_ONCE(ret == -EIOCBQUEUED);
+		ext4_inode_extension_cleanup(inode, ret);
+	}
 
 out:
 	if (ilock_shared)

@@ -672,8 +647,10 @@ ext4_dax_write_iter(struct kiocb *iocb,
 
 	ret = dax_iomap_rw(iocb, from, &ext4_iomap_ops);
 
-	if (extend)
-		ret = ext4_handle_inode_extension(inode, offset, ret, count);
+	if (extend) {
+		ret = ext4_handle_inode_extension(inode, offset, ret);
+		ext4_inode_extension_cleanup(inode, ret);
+	}
 out:
 	inode_unlock(inode);
 	if (ret > 0)

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

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

From: Bas Nieuwenhuizen <[email protected]>

commit 08e9ebc75b5bcfec9d226f9e16bab2ab7b25a39a upstream.

The incoming strings might not be terminated by a newline or a 0.

(found while testing a program that just wrote the string
itself, causing a crash)