4.19.323-rc1 review

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

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

From: Rafael J. Wysocki <[email protected]>

[ Upstream commit dc171114926ec390ab90f46534545420ec03e458 ]

It is not particularly useful to release locks (the EC mutex and the ACPI global lock, if present) and re-acquire them immediately thereafter during EC address space accesses in acpi_ec_space_handler().

First, releasing them for a while before grabbing them again does not really help anyone because there may not be enough time for another thread to acquire them.

Second, if another thread successfully acquires them and carries out a new EC write or read in the middle if an operation region access in progress, it may confuse the EC firmware, especially after the burst mode has been enabled.

Finally, manipulating the locks after writing or reading every single byte of data is overhead that it is better to avoid.

Accordingly, modify the code to carry out EC address space accesses entirely without releasing the locks.

---
 drivers/acpi/ec.c | 55 +++++++++++++++++++++++++++++++++++++++++------
 1 file changed, 49 insertions(+), 6 deletions(-)

index 7db62dec2ee53..1d0366c2c2175 100644
@@ -807,6 +807,9 @@ static int acpi_ec_transaction_unlocked(struct acpi_ec *ec,
 	unsigned long tmp;
 	int ret = 0;
 
+	if (t->rdata)
+		memset(t->rdata, 0, t->rlen);
+
 	/* start transaction */
 	spin_lock_irqsave(&ec->lock, tmp);
 	/* Enable GPE for command processing (IBF=0/OBF=1) */

@@ -843,8 +846,6 @@ static int acpi_ec_transaction(struct acpi_ec *ec, struct transaction *t)
 
 	if (!ec || (!t) || (t->wlen && !t->wdata) || (t->rlen && !t->rdata))
 		return -EINVAL;
-	if (t->rdata)
-		memset(t->rdata, 0, t->rlen);
 
 	mutex_lock(&ec->mutex);
 	if (ec->global_lock) {

@@ -871,7 +872,7 @@ static int acpi_ec_burst_enable(struct acpi_ec *ec)
 				.wdata = NULL, .rdata = &d,
 				.wlen = 0, .rlen = 1};
 
-	return acpi_ec_transaction(ec, &t);
+	return acpi_ec_transaction_unlocked(ec, &t);
 }
 
 static int acpi_ec_burst_disable(struct acpi_ec *ec)

@@ -881,7 +882,7 @@ static int acpi_ec_burst_disable(struct acpi_ec *ec)
 				.wlen = 0, .rlen = 0};
 
 	return (acpi_ec_read_status(ec) & ACPI_EC_FLAG_BURST) ?
-				acpi_ec_transaction(ec, &t) : 0;
+				acpi_ec_transaction_unlocked(ec, &t) : 0;
 }
 
 static int acpi_ec_read(struct acpi_ec *ec, u8 address, u8 *data)

@@ -897,6 +898,19 @@ static int acpi_ec_read(struct acpi_ec *ec, u8 address, u8 *data)
 	return result;
 }
 
+static int acpi_ec_read_unlocked(struct acpi_ec *ec, u8 address, u8 *data)
+{
+	int result;
+	u8 d;
+	struct transaction t = {.command = ACPI_EC_COMMAND_READ,
+				.wdata = &address, .rdata = &d,
+				.wlen = 1, .rlen = 1};
+
+	result = acpi_ec_transaction_unlocked(ec, &t);
+	*data = d;
+	return result;
+}
+
 static int acpi_ec_write(struct acpi_ec *ec, u8 address, u8 data)
 {
 	u8 wdata[2] = { address, data };

@@ -907,6 +921,16 @@ static int acpi_ec_write(struct acpi_ec *ec, u8 address, u8 data)
 	return acpi_ec_transaction(ec, &t);
 }
 
+static int acpi_ec_write_unlocked(struct acpi_ec *ec, u8 address, u8 data)
+{
+	u8 wdata[2] = { address, data };
+	struct transaction t = {.command = ACPI_EC_COMMAND_WRITE,
+				.wdata = wdata, .rdata = NULL,
+				.wlen = 2, .rlen = 0};
+
+	return acpi_ec_transaction_unlocked(ec, &t);
+}
+
 int ec_read(u8 addr, u8 *val)
 {
 	int err;

@@ -1320,6 +1344,7 @@ acpi_ec_space_handler(u32 function, acpi_physical_address address,
 	struct acpi_ec *ec = handler_context;
 	int result = 0, i, bytes = bits / 8;
 	u8 *value = (u8 *)value64;
+	u32 glk;
 
 	if ((address > 0xFF) || !value || !handler_context)
 		return AE_BAD_PARAMETER;

@@ -1327,13 +1352,25 @@ acpi_ec_space_handler(u32 function, acpi_physical_address address,
 	if (function != ACPI_READ && function != ACPI_WRITE)
 		return AE_BAD_PARAMETER;
 
+	mutex_lock(&ec->mutex);
+
+	if (ec->global_lock) {
+		acpi_status status;
+
+		status = acpi_acquire_global_lock(ACPI_EC_UDELAY_GLK, &glk);
+		if (ACPI_FAILURE(status)) {
+			result = -ENODEV;
+			goto unlock;
+		}
+	}
+
 	if (ec->busy_polling || bits > 8)
 		acpi_ec_burst_enable(ec);
 
 	for (i = 0; i < bytes; ++i, ++address, ++value) {
 		result = (function == ACPI_READ) ?
-			acpi_ec_read(ec, address, value) :
-			acpi_ec_write(ec, address, *value);
+			acpi_ec_read_unlocked(ec, address, value) :
+			acpi_ec_write_unlocked(ec, address, *value);
 		if (result < 0)
 			break;
 	}

@@ -1341,6 +1378,12 @@ acpi_ec_space_handler(u32 function, acpi_physical_address address,
 	if (ec->busy_polling || bits > 8)
 		acpi_ec_burst_disable(ec);
 
+	if (ec->global_lock)
+		acpi_release_global_lock(glk);
+
+unlock:
+	mutex_unlock(&ec->mutex);
+
 	switch (result) {
 	case -EINVAL:
 		return AE_BAD_PARAMETER;

2.43.0

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

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

From: Pei Xiao <[email protected]>

[ Upstream commit a5242874488eba2b9062985bf13743c029821330 ]

ACPICA commit 4d4547cf13cca820ff7e0f859ba83e1a610b9fd0

ACPI_ALLOCATE_ZEROED() may fail, elements might be NULL and will cause NULL pointer dereference later.

---
 drivers/acpi/acpica/dbconvert.c | 2 ++
 1 file changed, 2 insertions(+)

index 9fd9a98a9cbe8..5255a0837c82b 100644
@@ -170,6 +170,8 @@ acpi_status acpi_db_convert_to_package(char *string, union acpi_object *object)
 	elements =
 	    ACPI_ALLOCATE_ZEROED(DB_DEFAULT_PKG_ELEMENTS *
 				 sizeof(union acpi_object));
+	if (!elements)
+		return (AE_NO_MEMORY);
 
 	this = string;
 	for (i = 0; i < (DB_DEFAULT_PKG_ELEMENTS - 1); i++) {

2.43.0

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

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

From: Simon Horman <[email protected]>

[ Upstream commit 6555a2a9212be6983d2319d65276484f7c5f431a ]

Smatch reports that copying media_name and if_name to name_parts may overwrite the destination.

.../bearer.c:166 bearer_name_validate() error: strcpy() 'media_name' too large for 'name_parts->media_name' (32 vs 16) .../bearer.c:167 bearer_name_validate() error: strcpy() 'if_name' too large for 'name_parts->if_name' (1010102 vs 16)

This does seem to be the case so guard against this possibility by using strscpy() and failing if truncation occurs.

Introduced by commit b97bf3fd8f6a ("[TIPC] Initial merge")

Compile tested only.

---
 net/tipc/bearer.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

index c7686ff00f5bc..5ceb7d489686f 100644
@@ -158,8 +158,12 @@ static int bearer_name_validate(const char *name,
 
 	/* return bearer name components, if necessary */
 	if (name_parts) {
-		strcpy(name_parts->media_name, media_name);
-		strcpy(name_parts->if_name, if_name);
+		if (strscpy(name_parts->media_name, media_name,
+			    TIPC_MAX_MEDIA_NAME) < 0)
+			return 0;
+		if (strscpy(name_parts->if_name, if_name,
+			    TIPC_MAX_IF_NAME) < 0)
+			return 0;
 	}
 	return 1;
 }

2.43.0

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

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

From: Simon Horman <[email protected]>

[ Upstream commit 91d516d4de48532d967a77967834e00c8c53dfe6 ]

Increase size of queue_name buffer from 30 to 31 to accommodate the largest string written to it. This avoids truncation in the possibly unlikely case where the string is name is the maximum size.

Flagged by gcc-14:

.../mvpp2_main.c: In function 'mvpp2_probe':
.../mvpp2_main.c:7636:32: warning: 'snprintf' output may be truncated before the last format character [-Wformat-truncation=]
7636 | "stats-wq-%s%s", netdev_name(priv->port_list[0]->dev),
| ^
.../mvpp2_main.c:7635:9: note: 'snprintf' output between 10 and 31 bytes into a destination of size 30

   7635 |         snprintf(priv->queue_name, sizeof(priv->queue_name),
        |         ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
   7636 |                  "stats-wq-%s%s", netdev_name(priv->port_list[0]->dev),
        |                  ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
   7637 |                  priv->port_count > 1 ? "+" : "");
        |                  ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

Introduced by commit 118d6298f6f0 ("net: mvpp2: add ethtool GOP statistics"). I am not flagging this as a bug as I am not aware that it is one.

Compile tested only.

---
 drivers/net/ethernet/marvell/mvpp2/mvpp2.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index 23f60bc5d48f5..57fbfef336657 100644
@@ -756,7 +756,7 @@ struct mvpp2 {
 	unsigned int max_port_rxqs;
 
 	/* Workqueue to gather hardware statistics */
-	char queue_name[30];
+	char queue_name[31];
 	struct workqueue_struct *stats_queue;
 
 	/* Debugfs root entry */

2.43.0

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

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

From: Kuniyuki Iwashima <[email protected]>

[ Upstream commit e3af3d3c5b26c33a7950e34e137584f6056c4319 ]

dev->ip_ptr could be NULL if we set an invalid MTU.

Even then, if we issue ioctl(SIOCSIFADDR) for a new IPv4 address, devinet_ioctl() allocates struct in_ifaddr and fails later in inet_set_ifa() because in_dev is NULL.

Let's move the check earlier.

---
 net/ipv4/devinet.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

index e2ab8cdb71347..e4fea3adb0652 100644
@@ -541,10 +541,6 @@ static int inet_set_ifa(struct net_device *dev, struct in_ifaddr *ifa)
 
 	ASSERT_RTNL();
 
-	if (!in_dev) {
-		inet_free_ifa(ifa);
-		return -ENOBUFS;
-	}
 	ipv4_devconf_setall(in_dev);
 	neigh_parms_data_state_setall(in_dev->arp_parms);
 	if (ifa->ifa_dev != in_dev) {

@@ -1113,6 +1109,8 @@ int devinet_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr)
 
 		if (!ifa) {
 			ret = -ENOBUFS;
+			if (!in_dev)
+				break;
 			ifa = inet_alloc_ifa();
 			if (!ifa)
 				break;

2.43.0

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

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

From: Ido Schimmel <[email protected]>

[ Upstream commit 8fed54758cd248cd311a2b5c1e180abef1866237 ]

The NETLINK_FIB_LOOKUP netlink family can be used to perform a FIB lookup according to user provided parameters and communicate the result back to user space.

However, unlike other users of the FIB lookup API, the upper DSCP bits and the ECN bits of the DS field are not masked, which can result in the wrong result being returned.

Solve this by masking the upper DSCP bits and the ECN bits using IPTOS_RT_MASK.

The structure that communicates the request and the response is not exported to user space, so it is unlikely that this netlink family is actually in use [1].

[1] https://lore.kernel.org/netdev/ZpqpB8vJU%2FQ6LSqa@debian/

---
 net/ipv4/fib_frontend.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index 9aa48b4c40960..322ba1ba2ac3b 100644
@@ -1135,7 +1135,7 @@ static void nl_fib_lookup(struct net *net, struct fib_result_nl *frn)
 	struct flowi4           fl4 = {
 		.flowi4_mark = frn->fl_mark,
 		.daddr = frn->fl_addr,
-		.flowi4_tos = frn->fl_tos,
+		.flowi4_tos = frn->fl_tos & IPTOS_RT_MASK,
 		.flowi4_scope = frn->fl_scope,
 	};
 	struct fib_table *tb;

2.43.0

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

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

From: Jason Xing <[email protected]>

[ Upstream commit 0d9e5df4a257afc3a471a82961ace9a22b88295a ]

We found that one close-wait socket was reset by the other side due to a new connection reusing the same port which is beyond our expectation, so we have to investigate the underlying reason.

The following experiment is conducted in the test environment. We limit the port range from 40000 to 40010 and delay the time to close() after receiving a fin from the active close side, which can help us easily reproduce like what happened in production.

Here are three connections captured by tcpdump:
127.0.0.1.40002 > 127.0.0.1.9999: Flags [S], seq 2965525191 127.0.0.1.9999 > 127.0.0.1.40002: Flags [S.], seq 2769915070 127.0.0.1.40002 > 127.0.0.1.9999: Flags [.], ack 1 127.0.0.1.40002 > 127.0.0.1.9999: Flags [F.], seq 1, ack 1 // a few seconds later, within 60 seconds 127.0.0.1.40002 > 127.0.0.1.9999: Flags [S], seq 2965590730 127.0.0.1.9999 > 127.0.0.1.40002: Flags [.], ack 2 127.0.0.1.40002 > 127.0.0.1.9999: Flags [R], seq 2965525193 // later, very quickly
127.0.0.1.40002 > 127.0.0.1.9999: Flags [S], seq 2965590730 127.0.0.1.9999 > 127.0.0.1.40002: Flags [S.], seq 3120990805 127.0.0.1.40002 > 127.0.0.1.9999: Flags [.], ack 1

As we can see, the first flow is reset because:
1) client starts a new connection, I mean, the second one
2) client tries to find a suitable port which is a timewait socket (its state is timewait, substate is fin_wait2)
3) client occupies that timewait port to send a SYN
4) server finds a corresponding close-wait socket in ehash table, then replies with a challenge ack
5) client sends an RST to terminate this old close-wait socket.

I don't think the port selection algo can choose a FIN_WAIT2 socket when we turn on tcp_tw_reuse because on the server side there remain unread data. In some cases, if one side haven't call close() yet, we should not consider it as expendable and treat it at will.

Even though, sometimes, the server isn't able to call close() as soon as possible like what we expect, it can not be terminated easily, especially due to a second unrelated connection happening.

After this patch, we can see the expected failure if we start a connection when all the ports are occupied in fin_wait2 state:
"Ncat: Cannot assign requested address."

---
 net/ipv4/tcp_ipv4.c | 3 +++
 1 file changed, 3 insertions(+)

index d08e9d33e4d79..1bf315e83d7b9 100644
@@ -115,6 +115,9 @@ int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp)
 	const struct tcp_timewait_sock *tcptw = tcp_twsk(sktw);
 	struct tcp_sock *tp = tcp_sk(sk);
 
+	if (tw->tw_substate == TCP_FIN_WAIT2)
+		reuse = 0;
+
 	if (reuse == 2) {
 		/* Still does not detect *everything* that goes through
 		 * lo, since we require a loopback src or dst address

2.43.0

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

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

From: Aleksandrs Vinarskis <[email protected]>

[ Upstream commit a0a2459b79414584af6c46dd8c6f866d8f1aa421 ]

ACPICA commit 6c551e2c9487067d4b085333e7fe97e965a11625

---
 drivers/acpi/acpica/exprep.c | 3 +++
 1 file changed, 3 insertions(+)

index 228feeea555f1..91143bcfe0904 100644
@@ -437,6 +437,9 @@ acpi_status acpi_ex_prep_field_value(struct acpi_create_field_info *info)
 
 		if (info->connection_node) {
 			second_desc = info->connection_node->object;
+			if (second_desc == NULL) {
+				break;
+			}
 			if (!(second_desc->common.flags & AOPOBJ_DATA_VALID)) {
 				status =
 				    acpi_ds_get_buffer_arguments(second_desc);

2.43.0

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

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

From: Gustavo A. R. Silva <[email protected]>

[ Upstream commit 498365e52bebcbc36a93279fe7e9d6aec8479cee ]

Replace one-element array with a flexible-array member in struct host_cmd_ds_802_11_scan_ext.

With this, fix the following warning:

elo 16 17:51:58 surfacebook kernel: ------------[ cut here ]------------
elo 16 17:51:58 surfacebook kernel: memcpy: detected field-spanning write (size 243) of single field "ext_scan->tlv_buffer" at drivers/net/wireless/marvell/mwifiex/scan.c:2239 (size 1) elo 16 17:51:58 surfacebook kernel: WARNING: CPU: 0 PID: 498 at drivers/net/wireless/marvell/mwifiex/scan.c:2239 mwifiex_cmd_802_11_scan_ext+0x83/0x90 [mwifiex]

---
 drivers/net/wireless/marvell/mwifiex/fw.h   | 2 +-
 drivers/net/wireless/marvell/mwifiex/scan.c | 3 +--
 2 files changed, 2 insertions(+), 3 deletions(-)

index 3e3134bcc2b06..bfa482cf464ff 100644
@@ -1590,7 +1590,7 @@ struct host_cmd_ds_802_11_scan_rsp {
 
 struct host_cmd_ds_802_11_scan_ext {
 	u32   reserved;
-	u8    tlv_buffer[1];
+	u8    tlv_buffer[];
 } __packed;
 
 struct mwifiex_ie_types_bss_mode {

index 4f0e78ae3dbd0..0cbdd5a930d83 100644
@@ -2570,8 +2570,7 @@ int mwifiex_ret_802_11_scan_ext(struct mwifiex_private *priv,
 	ext_scan_resp = &resp->params.ext_scan;
 
 	tlv = (void *)ext_scan_resp->tlv_buffer;
-	buf_left = le16_to_cpu(resp->size) - (sizeof(*ext_scan_resp) + S_DS_GEN
-					      - 1);
+	buf_left = le16_to_cpu(resp->size) - (sizeof(*ext_scan_resp) + S_DS_GEN);
 
 	while (buf_left >= sizeof(struct mwifiex_ie_types_header)) {
 		type = le16_to_cpu(tlv->type);

2.43.0

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

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

From: Thomas Gleixner <[email protected]>

[ Upstream commit 7f8af7bac5380f2d95a63a6f19964e22437166e1 ]

These really can be handled gracefully without killing the machine.

---
 kernel/signal.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

index c79b87ac10416..356bdf5c45e61 100644
@@ -1739,10 +1739,11 @@ struct sigqueue *sigqueue_alloc(void)
 
 void sigqueue_free(struct sigqueue *q)
 {
-	unsigned long flags;
 	spinlock_t *lock = &current->sighand->siglock;
+	unsigned long flags;
 
-	BUG_ON(!(q->flags & SIGQUEUE_PREALLOC));
+	if (WARN_ON_ONCE(!(q->flags & SIGQUEUE_PREALLOC)))
+		return;
 	/*
 	 * We must hold ->siglock while testing q->list
 	 * to serialize with collect_signal() or with

@@ -1770,7 +1771,10 @@ int send_sigqueue(struct sigqueue *q, struct pid *pid, enum pid_type type)
 	unsigned long flags;
 	int ret, result;
 
-	BUG_ON(!(q->flags & SIGQUEUE_PREALLOC));
+	if (WARN_ON_ONCE(!(q->flags & SIGQUEUE_PREALLOC)))
+		return 0;
+	if (WARN_ON_ONCE(q->info.si_code != SI_TIMER))
+		return 0;
 
 	ret = -1;
 	rcu_read_lock();

@@ -1789,7 +1793,6 @@ int send_sigqueue(struct sigqueue *q, struct pid *pid, enum pid_type type)
 		 * If an SI_TIMER entry is already queue just increment
 		 * the overrun count.
 		 */
-		BUG_ON(q->info.si_code != SI_TIMER);
 		q->info.si_overrun++;
 		result = TRACE_SIGNAL_ALREADY_PENDING;
 		goto out;

2.43.0

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

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

From: Takashi Iwai <[email protected]>

[ Upstream commit 7b986c7430a6bb68d523dac7bfc74cbd5b44ef96 ]

ASIHPI driver stores some values in the static array upon a response from the driver, and its index depends on the firmware. We shouldn't trust it blindly.

This patch adds a sanity check of the array index to fit in the array size.

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

index 736f45337fc70..5be1d910a5d57 100644
@@ -724,7 +724,7 @@ static u16 HPIMSGX__init(struct hpi_message *phm,
 		phr->error = HPI_ERROR_PROCESSING_MESSAGE;
 		return phr->error;
 	}
-	if (hr.error == 0) {
+	if (hr.error == 0 && hr.u.s.adapter_index < HPI_MAX_ADAPTERS) {
 		/* the adapter was created successfully
 		   save the mapping for future use */
 		hpi_entry_points[hr.u.s.adapter_index] = entry_point_func;

2.43.0

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

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

From: Takashi Iwai <[email protected]>

[ Upstream commit c01f3815453e2d5f699ccd8c8c1f93a5b8669e59 ]

The current MIDI input flush on HDSP and HDSPM drivers relies on the hardware reporting the right value. If the hardware doesn't give the proper value but returns -1, it may be stuck at an infinite loop.

Add a counter and break if the loop is unexpectedly too long.

---
 sound/pci/rme9652/hdsp.c  | 6 ++++--
 sound/pci/rme9652/hdspm.c | 6 ++++--
 2 files changed, 8 insertions(+), 4 deletions(-)

index a0797fc17d957..b2e38524b1fee 100644
@@ -1322,8 +1322,10 @@ static int snd_hdsp_midi_output_possible (struct hdsp *hdsp, int id)
 
 static void snd_hdsp_flush_midi_input (struct hdsp *hdsp, int id)
 {
-	while (snd_hdsp_midi_input_available (hdsp, id))
-		snd_hdsp_midi_read_byte (hdsp, id);
+	int count = 256;
+
+	while (snd_hdsp_midi_input_available(hdsp, id) && --count)
+		snd_hdsp_midi_read_byte(hdsp, id);
 }
 
 static int snd_hdsp_midi_output_write (struct hdsp_midi *hmidi)

index 5dfddade1bae9..cc8313913d649 100644
@@ -1846,8 +1846,10 @@ static inline int snd_hdspm_midi_output_possible (struct hdspm *hdspm, int id)
 
 static void snd_hdspm_flush_midi_input(struct hdspm *hdspm, int id)
 {
-	while (snd_hdspm_midi_input_available (hdspm, id))
-		snd_hdspm_midi_read_byte (hdspm, id);
+	int count = 256;
+
+	while (snd_hdspm_midi_input_available(hdspm, id) && --count)
+		snd_hdspm_midi_read_byte(hdspm, id);
 }
 
 static int snd_hdspm_midi_output_write (struct hdspm_midi *hmidi)

2.43.0

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

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

From: Kaixin Wang <[email protected]>

[ Upstream commit 4a6921095eb04a900e0000da83d9475eb958e61e ]

In the pxafb_probe function, it calls the pxafb_init_fbinfo function, after which &fbi->task is associated with pxafb_task. Moreover, within this pxafb_init_fbinfo function, the pxafb_blank function within the &pxafb_ops struct is capable of scheduling work.

If we remove the module which will call pxafb_remove to make cleanup, it will call unregister_framebuffer function which can call do_unregister_framebuffer to free fbi->fb through put_fb_info(fb_info), while the work mentioned above will be used. The sequence of operations that may lead to a UAF bug is as follows:

CPU0 CPU1

                                   | pxafb_task
pxafb_remove                       |
unregister_framebuffer(info)       |
do_unregister_framebuffer(fb_info) |
put_fb_info(fb_info)               |
// free fbi->fb                    | set_ctrlr_state(fbi, state)
                                   | __pxafb_lcd_power(fbi, 0)
                                   | fbi->lcd_power(on, &fbi->fb.var)
                                   | //use fbi->fb

Fix it by ensuring that the work is canceled before proceeding with the cleanup in pxafb_remove.

Note that only root user can remove the driver at runtime.

---
 drivers/video/fbdev/pxafb.c | 1 +
 1 file changed, 1 insertion(+)

index 90dee3e6f8bc7..f76da5c6c6cd6 100644
@@ -2437,6 +2437,7 @@ static int pxafb_remove(struct platform_device *dev)
 	info = &fbi->fb;
 
 	pxafb_overlay_exit(fbi);
+	cancel_work_sync(&fbi->task);
 	unregister_framebuffer(info);
 
 	pxafb_disable_controller(fbi);

2.43.0

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

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

From: Andrew Davis <[email protected]>

[ Upstream commit cf8c39b00e982fa506b16f9d76657838c09150cb ]

There may be other backup reset methods available, do not halt here so that other reset methods can be tried.

---
 drivers/power/reset/brcmstb-reboot.c | 3 ---
 1 file changed, 3 deletions(-)

index 884b53c483c09..9f8b9e5cad93a 100644
@@ -72,9 +72,6 @@ static int brcmstb_restart_handler(struct notifier_block *this,
 		return NOTIFY_DONE;
 	}
 
-	while (1)
-		;
-
 	return NOTIFY_DONE;
 }
 

2.43.0

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

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

From: Damien Le Moal <[email protected]>

[ Upstream commit 93b0f9e11ce511353c65b7f924cf5f95bd9c3aba ]

Rename the array sil_blacklist to sil_quirks as this name is more neutral and is also consistent with how this driver define quirks with the SIL_QUIRK_XXX flags.

---
 drivers/ata/sata_sil.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

index 82adaf02887fb..8613a3cf2c8a5 100644
@@ -144,7 +144,7 @@ static const struct pci_device_id sil_pci_tbl[] = {
 static const struct sil_drivelist {
 	const char *product;
 	unsigned int quirk;
-} sil_blacklist [] = {
+} sil_quirks[] = {
 	{ "ST320012AS",		SIL_QUIRK_MOD15WRITE },
 	{ "ST330013AS",		SIL_QUIRK_MOD15WRITE },
 	{ "ST340017AS",		SIL_QUIRK_MOD15WRITE },

@@ -617,8 +617,8 @@ static void sil_thaw(struct ata_port *ap)
  *	list, and apply the fixups to only the specific
  *	devices/hosts/firmwares that need it.
  *
- *	20040111 - Seagate drives affected by the Mod15Write bug are blacklisted
- *	The Maxtor quirk is in the blacklist, but I'm keeping the original
+ *	20040111 - Seagate drives affected by the Mod15Write bug are quirked
+ *	The Maxtor quirk is in sil_quirks, but I'm keeping the original
  *	pessimistic fix for the following reasons...
  *	- There seems to be less info on it, only one device gleaned off the
  *	Windows	driver, maybe only one is affected.  More info would be greatly

@@ -637,9 +637,9 @@ static void sil_dev_config(struct ata_device *dev)
 
 	ata_id_c_string(dev->id, model_num, ATA_ID_PROD, sizeof(model_num));
 
-	for (n = 0; sil_blacklist[n].product; n++)
-		if (!strcmp(sil_blacklist[n].product, model_num)) {
-			quirks = sil_blacklist[n].quirk;
+	for (n = 0; sil_quirks[n].product; n++)
+		if (!strcmp(sil_quirks[n].product, model_num)) {
+			quirks = sil_quirks[n].quirk;
 			break;
 		}
 

2.43.0

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

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

From: Remington Brasga <[email protected]>

[ Upstream commit b0b2fc815e514221f01384f39fbfbff65d897e1c ]

Fix issue with UBSAN throwing shift-out-of-bounds warning.

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

index 1128bcdf5024a..9f731847ae634 100644
@@ -3097,7 +3097,7 @@ static int dbFindBits(u32 word, int l2nb)
 
 	/* scan the word for nb free bits at nb alignments.
 	 */
-	for (bitno = 0; mask != 0; bitno += nb, mask >>= nb) {
+	for (bitno = 0; mask != 0; bitno += nb, mask = (mask >> nb)) {
 		if ((mask & word) == mask)
 			break;
 	}

2.43.0

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

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

From: Edward Adam Davis <[email protected]>

[ Upstream commit d6c1b3599b2feb5c7291f5ac3a36e5fa7cedb234 ]

[syzbot reported]
==================================================================

BUG: KASAN: slab-use-after-free in __mutex_lock_common kernel/locking/mutex.c:587 [inline]
BUG: KASAN: slab-use-after-free in __mutex_lock+0xfe/0xd70 kernel/locking/mutex.c:752
Read of size 8 at addr ffff8880229254b0 by task syz-executor357/5216

CPU: 0 UID: 0 PID: 5216 Comm: syz-executor357 Not tainted 6.11.0-rc3-syzkaller-00156-gd7a5aa4b3c00 #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 06/27/2024
Call Trace:
 <TASK>
 __dump_stack lib/dump_stack.c:93 [inline]
 dump_stack_lvl+0x241/0x360 lib/dump_stack.c:119
 print_address_description mm/kasan/report.c:377 [inline]
 print_report+0x169/0x550 mm/kasan/report.c:488
 kasan_report+0x143/0x180 mm/kasan/report.c:601
 __mutex_lock_common kernel/locking/mutex.c:587 [inline]
 __mutex_lock+0xfe/0xd70 kernel/locking/mutex.c:752
 dbFreeBits+0x7ea/0xd90 fs/jfs/jfs_dmap.c:2390
 dbFreeDmap fs/jfs/jfs_dmap.c:2089 [inline]
 dbFree+0x35b/0x680 fs/jfs/jfs_dmap.c:409
 dbDiscardAG+0x8a9/0xa20 fs/jfs/jfs_dmap.c:1650
 jfs_ioc_trim+0x433/0x670 fs/jfs/jfs_discard.c:100
 jfs_ioctl+0x2d0/0x3e0 fs/jfs/ioctl.c:131
 vfs_ioctl fs/ioctl.c:51 [inline]
 __do_sys_ioctl fs/ioctl.c:907 [inline]
 __se_sys_ioctl+0xfc/0x170 fs/ioctl.c:893
 do_syscall_x64 arch/x86/entry/common.c:52 [inline]
 do_syscall_64+0xf3/0x230 arch/x86/entry/common.c:83

Freed by task 5218:
 kasan_save_stack mm/kasan/common.c:47 [inline]
 kasan_save_track+0x3f/0x80 mm/kasan/common.c:68
 kasan_save_free_info+0x40/0x50 mm/kasan/generic.c:579
 poison_slab_object+0xe0/0x150 mm/kasan/common.c:240
 __kasan_slab_free+0x37/0x60 mm/kasan/common.c:256
 kasan_slab_free include/linux/kasan.h:184 [inline]
 slab_free_hook mm/slub.c:2252 [inline]
 slab_free mm/slub.c:4473 [inline]
 kfree+0x149/0x360 mm/slub.c:4594
 dbUnmount+0x11d/0x190 fs/jfs/jfs_dmap.c:278
 jfs_mount_rw+0x4ac/0x6a0 fs/jfs/jfs_mount.c:247
 jfs_remount+0x3d1/0x6b0 fs/jfs/super.c:454
 reconfigure_super+0x445/0x880 fs/super.c:1083
 vfs_cmd_reconfigure fs/fsopen.c:263 [inline]
 vfs_fsconfig_locked fs/fsopen.c:292 [inline]
 __do_sys_fsconfig fs/fsopen.c:473 [inline]
 __se_sys_fsconfig+0xb6e/0xf80 fs/fsopen.c:345
 do_syscall_x64 arch/x86/entry/common.c:52 [inline]
 do_syscall_64+0xf3/0x230 arch/x86/entry/common.c:83
 entry_SYSCALL_64_after_hwframe+0x77/0x7f

[Analysis]
There are two paths (dbUnmount and jfs_ioc_trim) that generate race condition when accessing bmap, which leads to the occurrence of uaf.

Use the lock s_umount to synchronize them, in order to avoid uaf caused by race condition.

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

index f76ff0a464442..9d78c427b9443 100644
@@ -78,7 +78,7 @@ void jfs_issue_discard(struct inode *ip, u64 blkno, u64 nblocks)
 int jfs_ioc_trim(struct inode *ip, struct fstrim_range *range)
 {
 	struct inode *ipbmap = JFS_SBI(ip->i_sb)->ipbmap;
-	struct bmap *bmp = JFS_SBI(ip->i_sb)->bmap;
+	struct bmap *bmp;
 	struct super_block *sb = ipbmap->i_sb;
 	int agno, agno_end;
 	u64 start, end, minlen;

@@ -96,10 +96,15 @@ int jfs_ioc_trim(struct inode *ip, struct fstrim_range *range)
 	if (minlen == 0)
 		minlen = 1;
 
+	down_read(&sb->s_umount);
+	bmp = JFS_SBI(ip->i_sb)->bmap;
+
 	if (minlen > bmp->db_agsize ||
 	    start >= bmp->db_mapsize ||
-	    range->len < sb->s_blocksize)
+	    range->len < sb->s_blocksize) {
+		up_read(&sb->s_umount);
 		return -EINVAL;
+	}
 
 	if (end >= bmp->db_mapsize)
 		end = bmp->db_mapsize - 1;

@@ -113,6 +118,8 @@ int jfs_ioc_trim(struct inode *ip, struct fstrim_range *range)
 		trimmed += dbDiscardAG(ip, agno, minlen);
 		agno++;
 	}
+
+	up_read(&sb->s_umount);
 	range->len = trimmed << sb->s_blocksize_bits;
 
 	return 0;

2.43.0

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

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

From: Edward Adam Davis <[email protected]>

[ Upstream commit d64ff0d2306713ff084d4b09f84ed1a8c75ecc32 ]

syzbot report a out of bounds in dbSplit, it because dmt_leafidx greater than num leaves per dmap tree, add a checking for dmt_leafidx in dbFindLeaf.

Shaggy:
Modified sanity check to apply to control pages as well as leaf pages.

---
 fs/jfs/jfs_dmap.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

index 9f731847ae634..21597e8b727c6 100644
@@ -3019,9 +3019,10 @@ static void dbAdjTree(dmtree_t *tp, int leafno, int newval, bool is_ctl)
 static int dbFindLeaf(dmtree_t *tp, int l2nb, int *leafidx, bool is_ctl)
 {
 	int ti, n = 0, k, x = 0;
-	int max_size;
+	int max_size, max_idx;
 
 	max_size = is_ctl ? CTLTREESIZE : TREESIZE;
+	max_idx = is_ctl ? LPERCTL : LPERDMAP;
 
 	/* first check the root of the tree to see if there is
 	 * sufficient free space.

@@ -3053,6 +3054,8 @@ static int dbFindLeaf(dmtree_t *tp, int l2nb, int *leafidx, bool is_ctl)
 		 */
 		assert(n < 4);
 	}
+	if (le32_to_cpu(tp->dmt_leafidx) >= max_idx)
+		return -ENOSPC;
 
 	/* set the return to the leftmost leaf describing sufficient
 	 * free space.

2.43.0

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

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

From: Zhao Mengmeng <[email protected]>

[ Upstream commit 2b59ffad47db1c46af25ccad157bb3b25147c35c ]

syzbot reports that lzo1x_1_do_compress is using uninit-value:

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

BUG: KMSAN: uninit-value in lzo1x_1_do_compress+0x19f9/0x2510 lib/lzo/lzo1x_compress.c:178

...

Uninit was stored to memory at:
ea_put fs/jfs/xattr.c:639 [inline]

...

Local variable ea_buf created at:

 __jfs_setxattr+0x5d/0x1ae0 fs/jfs/xattr.c:662
 __jfs_xattr_set+0xe6/0x1f0 fs/jfs/xattr.c:934

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

The reason is ea_buf->new_ea is not initialized properly.

Fix this by using memset to empty its content at the beginning in ea_get().

---
 fs/jfs/xattr.c | 2 ++
 1 file changed, 2 insertions(+)

index 37b984692ca90..bb8c4583f0655 100644
@@ -447,6 +447,8 @@ static int ea_get(struct inode *inode, struct ea_buffer *ea_buf, int min_size)
 	int rc;
 	int quota_allocation = 0;
 
+	memset(&ea_buf->new_ea, 0, sizeof(ea_buf->new_ea));
+
 	/* When fsck.jfs clears a bad ea, it doesn't clear the size */
 	if (ji->ea.flag == 0)
 		ea_size = 0;

2.43.0

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

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

From: Alex Hung <[email protected]>

[ Upstream commit 35ff747c86767937ee1e0ca987545b7eed7a0810 ]

[WHAT & HOW]
amdgpu_dm can pass a null stream to dc_is_stream_unchanged. It is necessary to check for null before dereferencing them.

This fixes 1 FORWARD_NULL issue reported by Coverity.

---
 drivers/gpu/drm/amd/display/dc/core/dc_resource.c | 2 ++
 1 file changed, 2 insertions(+)

index 8b4337794d1ef..18ebbbf67f230 100644
@@ -1569,6 +1569,8 @@ static bool are_stream_backends_same(
 bool dc_is_stream_unchanged(
 	struct dc_stream_state *old_stream, struct dc_stream_state *stream)
 {
+	if (!old_stream || !stream)
+		return false;
 
 	if (!are_stream_backends_same(old_stream, stream))
 		return false;

2.43.0

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

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

From: Srinivasan Shanmugam <[email protected]>

[ Upstream commit b7e99058eb2e86aabd7a10761e76cae33d22b49f ]

Fixes index out of bounds issue in cm_helper_translate_curve_to_degamma_hw_format function. The issue could occur when the index 'i' exceeds the number of transfer function points (TRANSFER_FUNC_POINTS).

The fix adds a check to ensure 'i' is within bounds before accessing the transfer function points. If 'i' is out of bounds the function returns false to indicate an error.

Reported by smatch:
drivers/gpu/drm/amd/amdgpu/../display/dc/dcn10/dcn10_cm_common.c:594 cm_helper_translate_curve_to_degamma_hw_format() error: buffer overflow 'output_tf->tf_pts.red' 1025 <= s32max drivers/gpu/drm/amd/amdgpu/../display/dc/dcn10/dcn10_cm_common.c:595 cm_helper_translate_curve_to_degamma_hw_format() error: buffer overflow 'output_tf->tf_pts.green' 1025 <= s32max drivers/gpu/drm/amd/amdgpu/../display/dc/dcn10/dcn10_cm_common.c:596 cm_helper_translate_curve_to_degamma_hw_format() error: buffer overflow 'output_tf->tf_pts.blue' 1025 <= s32max

---
 drivers/gpu/drm/amd/display/dc/dcn10/dcn10_cm_common.c | 2 ++
 1 file changed, 2 insertions(+)

index 67a3ba49234ee..ad42470613441 100644
@@ -482,6 +482,8 @@ bool cm_helper_translate_curve_to_degamma_hw_format(
 				i += increment) {
 			if (j == hw_points - 1)
 				break;
+			if (i >= TRANSFER_FUNC_POINTS)
+				return false;
 			rgb_resulted[j].red = output_tf->tf_pts.red[i];
 			rgb_resulted[j].green = output_tf->tf_pts.green[i];
 			rgb_resulted[j].blue = output_tf->tf_pts.blue[i];

2.43.0

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

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

From: Matthew Brost <[email protected]>

[ Upstream commit 53369581dc0c68a5700ed51e1660f44c4b2bb524 ]

We want to determine the size of the devcoredump before writing it out. To that end, we will run the devcoredump printer with NULL data to get the size, alloc data based on the generated offset, then run the devcorecump again with a valid data pointer to print. This necessitates not writing data to the data pointer on the initial pass, when it is NULL.

v5:
- Better commit message (Jonathan)
- Add kerenl doc with examples (Jani)

---
 drivers/gpu/drm/drm_print.c | 13 +++++----
 include/drm/drm_print.h     | 54 ++++++++++++++++++++++++++++++++++++-
 2 files changed, 61 insertions(+), 6 deletions(-)

index 0e7fc3e7dfb48..711a1b329879f 100644
@@ -54,8 +54,9 @@ void __drm_puts_coredump(struct drm_printer *p, const char *str)
 			copy = iterator->remain;
 
 		/* Copy out the bit of the string that we need */
-		memcpy(iterator->data,
-			str + (iterator->start - iterator->offset), copy);
+		if (iterator->data)
+			memcpy(iterator->data,
+			       str + (iterator->start - iterator->offset), copy);
 
 		iterator->offset = iterator->start + copy;
 		iterator->remain -= copy;

@@ -64,7 +65,8 @@ void __drm_puts_coredump(struct drm_printer *p, const char *str)
 
 		len = min_t(ssize_t, strlen(str), iterator->remain);
 
-		memcpy(iterator->data + pos, str, len);
+		if (iterator->data)
+			memcpy(iterator->data + pos, str, len);
 
 		iterator->offset += len;
 		iterator->remain -= len;

@@ -94,8 +96,9 @@ void __drm_printfn_coredump(struct drm_printer *p, struct va_format *vaf)
 	if ((iterator->offset >= iterator->start) && (len < iterator->remain)) {
 		ssize_t pos = iterator->offset - iterator->start;
 
-		snprintf(((char *) iterator->data) + pos,
-			iterator->remain, "%pV", vaf);
+		if (iterator->data)
+			snprintf(((char *) iterator->data) + pos,
+				 iterator->remain, "%pV", vaf);
 
 		iterator->offset += len;
 		iterator->remain -= len;

2.43.0

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

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

From: Kees Cook <[email protected]>

[ Upstream commit 6e5860b0ad4934baee8c7a202c02033b2631bb44 ]

struct aac_srb_unit contains struct aac_srb, which contains struct sgmap, which ends in a (currently) "fake" (1-element) flexible array. Converting this to a flexible array is needed so that runtime bounds checking won't think the array is fixed size (i.e. under CONFIG_FORTIFY_SOURCE=y and/or CONFIG_UBSAN_BOUNDS=y), as other parts of aacraid use struct sgmap as a flexible array.

It is not legal to have a flexible array in the middle of a structure, so it either needs to be split up or rearranged so that it is at the end of the structure. Luckily, struct aac_srb_unit, which is exclusively consumed/updated by aac_send_safw_bmic_cmd(), does not depend on member ordering.

The values set in the on-stack struct aac_srb_unit instance "srbu" by the only two callers, aac_issue_safw_bmic_identify() and aac_get_safw_ciss_luns(), do not contain anything in srbu.srb.sgmap.sg, and they both implicitly initialize srbu.srb.sgmap.count to 0 during memset(). For example:

        memset(&srbu, 0, sizeof(struct aac_srb_unit));

        srbcmd = &srbu.srb;
        srbcmd->flags   = cpu_to_le32(SRB_DataIn);
        srbcmd->cdb[0]  = CISS_REPORT_PHYSICAL_LUNS;
        srbcmd->cdb[1]  = 2; /* extended reporting */
        srbcmd->cdb[8]  = (u8)(datasize >> 8);
        srbcmd->cdb[9]  = (u8)(datasize);

        rcode = aac_send_safw_bmic_cmd(dev, &srbu, phys_luns, datasize);

During aac_send_safw_bmic_cmd(), a separate srb is mapped into DMA, and has srbu.srb copied into it:

        srb = fib_data(fibptr);
        memcpy(srb, &srbu->srb, sizeof(struct aac_srb));

Only then is srb.sgmap.count written and srb->sg populated:

        srb->count              = cpu_to_le32(xfer_len);

        sg64 = (struct sgmap64 *)&srb->sg;
        sg64->count             = cpu_to_le32(1);
        sg64->sg[0].addr[1]     = cpu_to_le32(upper_32_bits(addr));
        sg64->sg[0].addr[0]     = cpu_to_le32(lower_32_bits(addr));
        sg64->sg[0].count       = cpu_to_le32(xfer_len);

But this is happening in the DMA memory, not in srbu.srb. An attempt to copy the changes back to srbu does happen:

        /*
         * Copy the updated data for other dumping or other usage if
         * needed
         */
        memcpy(&srbu->srb, srb, sizeof(struct aac_srb));

But this was never correct: the sg64 (3 u32s) overlap of srb.sg (2 u32s) always meant that srbu.srb would have held truncated information and any attempt to walk srbu.srb.sg.sg based on the value of srbu.srb.sg.count would result in attempting to parse past the end of srbu.srb.sg.sg[0] into srbu.srb_reply.

After getting a reply from hardware, the reply is copied into srbu.srb_reply:

        srb_reply = (struct aac_srb_reply *)fib_data(fibptr);
        memcpy(&srbu->srb_reply, srb_reply, sizeof(struct aac_srb_reply));

This has always been fixed-size, so there's no issue here. It is worth noting that the two callers _never check_ srbu contents -- neither srbu.srb nor srbu.srb_reply is examined. (They depend on the mapped xfer_buf instead.)

Therefore, the ordering of members in struct aac_srb_unit does not matter, and the flexible array member can moved to the end.

(Additionally, the two memcpy()s that update srbu could be entirely removed as they are never consumed, but I left that as-is.)

---
 drivers/scsi/aacraid/aacraid.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index 074760f210145..135e3f39c895c 100644
@@ -2037,8 +2037,8 @@ struct aac_srb_reply
 };
 
 struct aac_srb_unit {
-	struct aac_srb		srb;
 	struct aac_srb_reply	srb_reply;
+	struct aac_srb		srb;
 };
 
 /*

2.43.0

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

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

From: Geert Uytterhoeven <[email protected]>

[ Upstream commit c6dbab46324b1742b50dc2fb5c1fee2c28129439 ]

With -Werror:

    In function ‘r100_cp_init_microcode’,
	inlined from ‘r100_cp_init’ at drivers/gpu/drm/radeon/r100.c:1136:7:
    include/linux/printk.h:465:44: error: ‘%s’ directive argument is null [-Werror=format-overflow=]
      465 | #define printk(fmt, ...) printk_index_wrap(_printk, fmt, ##__VA_ARGS__)
	  |                                            ^
    include/linux/printk.h:437:17: note: in definition of macro ‘printk_index_wrap’
      437 |                 _p_func(_fmt, ##__VA_ARGS__);                           \
	  |                 ^~~~~~~
    include/linux/printk.h:508:9: note: in expansion of macro ‘printk’
      508 |         printk(KERN_ERR pr_fmt(fmt), ##__VA_ARGS__)
	  |         ^~~~~~
    drivers/gpu/drm/radeon/r100.c:1062:17: note: in expansion of macro ‘pr_err’
     1062 |                 pr_err("radeon_cp: Failed to load firmware \"%s\"\n", fw_name);
	  |                 ^~~~~~

Fix this by converting the if/else if/... construct into a proper switch() statement with a default to handle the error case.

As a bonus, the generated code is ca. 100 bytes smaller (with gcc 11.4.0 targeting arm32).

---
 drivers/gpu/drm/radeon/r100.c | 70 ++++++++++++++++++++++-------------
 1 file changed, 45 insertions(+), 25 deletions(-)

index 15241b80e9d21..444a135158bdc 100644
@@ -999,45 +999,65 @@ static int r100_cp_init_microcode(struct radeon_device *rdev)
 
 	DRM_DEBUG_KMS("\n");
 
-	if ((rdev->family == CHIP_R100) || (rdev->family == CHIP_RV100) ||
-	    (rdev->family == CHIP_RV200) || (rdev->family == CHIP_RS100) ||
-	    (rdev->family == CHIP_RS200)) {
+	switch (rdev->family) {
+	case CHIP_R100:
+	case CHIP_RV100:
+	case CHIP_RV200:
+	case CHIP_RS100:
+	case CHIP_RS200:
 		DRM_INFO("Loading R100 Microcode\n");
 		fw_name = FIRMWARE_R100;
-	} else if ((rdev->family == CHIP_R200) ||
-		   (rdev->family == CHIP_RV250) ||
-		   (rdev->family == CHIP_RV280) ||
-		   (rdev->family == CHIP_RS300)) {
+		break;
+
+	case CHIP_R200:
+	case CHIP_RV250:
+	case CHIP_RV280:
+	case CHIP_RS300:
 		DRM_INFO("Loading R200 Microcode\n");
 		fw_name = FIRMWARE_R200;
-	} else if ((rdev->family == CHIP_R300) ||
-		   (rdev->family == CHIP_R350) ||
-		   (rdev->family == CHIP_RV350) ||
-		   (rdev->family == CHIP_RV380) ||
-		   (rdev->family == CHIP_RS400) ||
-		   (rdev->family == CHIP_RS480)) {
+		break;
+
+	case CHIP_R300:
+	case CHIP_R350:
+	case CHIP_RV350:
+	case CHIP_RV380:
+	case CHIP_RS400:
+	case CHIP_RS480:
 		DRM_INFO("Loading R300 Microcode\n");
 		fw_name = FIRMWARE_R300;
-	} else if ((rdev->family == CHIP_R420) ||
-		   (rdev->family == CHIP_R423) ||
-		   (rdev->family == CHIP_RV410)) {
+		break;
+
+	case CHIP_R420:
+	case CHIP_R423:
+	case CHIP_RV410:
 		DRM_INFO("Loading R400 Microcode\n");
 		fw_name = FIRMWARE_R420;
-	} else if ((rdev->family == CHIP_RS690) ||
-		   (rdev->family == CHIP_RS740)) {
+		break;
+
+	case CHIP_RS690:
+	case CHIP_RS740:
 		DRM_INFO("Loading RS690/RS740 Microcode\n");
 		fw_name = FIRMWARE_RS690;
-	} else if (rdev->family == CHIP_RS600) {
+		break;
+
+	case CHIP_RS600:
 		DRM_INFO("Loading RS600 Microcode\n");
 		fw_name = FIRMWARE_RS600;
-	} else if ((rdev->family == CHIP_RV515) ||
-		   (rdev->family == CHIP_R520) ||
-		   (rdev->family == CHIP_RV530) ||
-		   (rdev->family == CHIP_R580) ||
-		   (rdev->family == CHIP_RV560) ||
-		   (rdev->family == CHIP_RV570)) {
+		break;
+
+	case CHIP_RV515:
+	case CHIP_R520:
+	case CHIP_RV530:
+	case CHIP_R580:
+	case CHIP_RV560:
+	case CHIP_RV570:
 		DRM_INFO("Loading R500 Microcode\n");
 		fw_name = FIRMWARE_R520;
+		break;
+
+	default:
+		DRM_ERROR("Unsupported Radeon family %u\n", rdev->family);
+		return -EINVAL;
 	}
 
 	err = request_firmware(&rdev->me_fw, fw_name, rdev->dev);

2.43.0

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

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

From: Geert Uytterhoeven <[email protected]>

[ Upstream commit 39ab331ab5d377a18fbf5a0e0b228205edfcc7f4 ]

Replace two open-coded calculations of the buffer size by invocations of sizeof() on the buffer itself, to make sure the code will always use the actual buffer size.

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

index f06c9df60e34d..35d83888071ea 100644
@@ -302,8 +302,8 @@ int of_irq_parse_one(struct device_node *device, int index, struct of_phandle_ar
 	addr = of_get_property(device, "reg", &addr_len);
 
 	/* Prevent out-of-bounds read in case of longer interrupt parent address size */
-	if (addr_len > (3 * sizeof(__be32)))
-		addr_len = 3 * sizeof(__be32);
+	if (addr_len > sizeof(addr_buf))
+		addr_len = sizeof(addr_buf);
 	if (addr)
 		memcpy(addr_buf, addr, addr_len);
 

2.43.0

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

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

From: Thadeu Lima de Souza Cascardo <[email protected]>

[ Upstream commit cd69f8f9de280e331c9e6ff689ced0a688a9ce8f ]

ext4_search_dir currently returns -1 in case of a failure, while it returns 0 when the name is not found. In such failure cases, it should return an error code instead.

This becomes even more important when ext4_find_inline_entry returns an error code as well in the next commit.

-EFSCORRUPTED seems appropriate as such error code as these failures would be caused by unexpected record lengths and is in line with other instances of ext4_check_dir_entry failures.

In the case of ext4_dx_find_entry, the current use of ERR_BAD_DX_DIR was left as is to reduce the risk of regressions.

---
 fs/ext4/namei.c | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

index 8594feea2d932..d85be8255d790 100644
@@ -1334,7 +1334,7 @@ static inline bool ext4_match(const struct ext4_filename *fname,
 }
 
 /*
- * Returns 0 if not found, -1 on failure, and 1 on success
+ * Returns 0 if not found, -EFSCORRUPTED on failure, and 1 on success
  */
 int ext4_search_dir(struct buffer_head *bh, char *search_buf, int buf_size,
 		    struct inode *dir, struct ext4_filename *fname,

@@ -1355,7 +1355,7 @@ int ext4_search_dir(struct buffer_head *bh, char *search_buf, int buf_size,
 			 * a full check */
 			if (ext4_check_dir_entry(dir, NULL, de, bh, search_buf,
 						 buf_size, offset))
-				return -1;
+				return -EFSCORRUPTED;
 			*res_dir = de;
 			return 1;
 		}

@@ -1363,7 +1363,7 @@ int ext4_search_dir(struct buffer_head *bh, char *search_buf, int buf_size,
 		de_len = ext4_rec_len_from_disk(de->rec_len,
 						dir->i_sb->s_blocksize);
 		if (de_len <= 0)
-			return -1;
+			return -EFSCORRUPTED;
 		offset += de_len;
 		de = (struct ext4_dir_entry_2 *) ((char *) de + de_len);
 	}

@@ -1514,8 +1514,10 @@ static struct buffer_head *__ext4_find_entry(struct inode *dir,
 			goto cleanup_and_exit;
 		} else {
 			brelse(bh);
-			if (i < 0)
+			if (i < 0) {
+				ret = ERR_PTR(i);
 				goto cleanup_and_exit;
+			}
 		}
 	next:
 		if (++block >= nblocks)

@@ -1609,7 +1611,7 @@ static struct buffer_head * ext4_dx_find_entry(struct inode *dir,
 		if (retval == 1)
 			goto success;
 		brelse(bh);
-		if (retval == -1) {
+		if (retval < 0) {
 			bh = ERR_PTR(ERR_BAD_DX_DIR);
 			goto errout;
 		}

2.43.0

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

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

From: Artem Sadovnikov <[email protected]>

[ Upstream commit cc749e61c011c255d81b192a822db650c68b313f ]

Fuzzing reports a possible deadlock in jbd2_log_wait_commit.

This issue is triggered when an EXT4_IOC_MIGRATE ioctl is set to require synchronous updates because the file descriptor is opened with O_SYNC. This can lead to the jbd2_journal_stop() function calling jbd2_might_wait_for_commit(), potentially causing a deadlock if the EXT4_IOC_MIGRATE call races with a write(2) system call.

This problem only arises when CONFIG_PROVE_LOCKING is enabled. In this case, the jbd2_might_wait_for_commit macro locks jbd2_handle in the jbd2_journal_stop function while i_data_sem is locked. This triggers lockdep because the jbd2_journal_start function might also lock the same jbd2_handle simultaneously.

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

Rule: add

---
 fs/ext4/migrate.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index 4a72583c75593..9f73c2f7f9492 100644
@@ -678,8 +678,8 @@ int ext4_ind_migrate(struct inode *inode)
 		ei->i_data[i] = cpu_to_le32(blk++);
 	ext4_mark_inode_dirty(handle, inode);
 errout:
-	ext4_journal_stop(handle);
 	up_write(&EXT4_I(inode)->i_data_sem);
+	ext4_journal_stop(handle);
 out_unlock:
 	percpu_up_write(&sbi->s_writepages_rwsem);
 	return ret;

2.43.0

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

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

From: Ben Dooks <[email protected]>

[ Upstream commit 68a16708d2503b6303d67abd43801e2ca40c208d ]

In the s3c64xx_flush_fifo() code, the loops counter is post-decremented in the do { } while(test && loops--) condition. This means the loops is left at the unsigned equivalent of -1 if the loop times out. The test after will never pass as if tests for loops == 0.

---
 drivers/spi/spi-s3c64xx.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

index d9420561236c2..108a087a2777c 100644
@@ -211,7 +211,7 @@ static void s3c64xx_flush_fifo(struct s3c64xx_spi_driver_data *sdd)
 	loops = msecs_to_loops(1);
 	do {
 		val = readl(regs + S3C64XX_SPI_STATUS);
-	} while (TX_FIFO_LVL(val, sdd) && loops--);
+	} while (TX_FIFO_LVL(val, sdd) && --loops);
 
 	if (loops == 0)
 		dev_warn(&sdd->pdev->dev, "Timed out flushing TX FIFO\n");

@@ -224,7 +224,7 @@ static void s3c64xx_flush_fifo(struct s3c64xx_spi_driver_data *sdd)
 			readl(regs + S3C64XX_SPI_RX_DATA);
 		else
 			break;
-	} while (loops--);
+	} while (--loops);
 
 	if (loops == 0)
 		dev_warn(&sdd->pdev->dev, "Timed out flushing RX FIFO\n");

2.43.0

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

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

From: Yifei Liu <[email protected]>

[ Upstream commit c66be905cda24fb782b91053b196bd2e966f95b7 ]

step_after_suspend_test fails with device busy error while writing to /sys/power/state to start suspend. The test believes it failed to enter suspend state with

$ sudo ./step_after_suspend_test
TAP version 13
Bail out! Failed to enter Suspend state

However, in the kernel message, I indeed see the system get suspended and then wake up later.

[611172.033108] PM: suspend entry (s2idle)
[611172.044940] Filesystems sync: 0.006 seconds
[611172.052254] Freezing user space processes
[611172.059319] Freezing user space processes completed (elapsed 0.001 seconds)
[611172.067920] OOM killer disabled.
[611172.072465] Freezing remaining freezable tasks
[611172.080332] Freezing remaining freezable tasks completed (elapsed 0.001 seconds)
[611172.089724] printk: Suspending console(s) (use no_console_suspend to debug)
[611172.117126] serial 00:03: disabled
some other hardware get reconnected
[611203.136277] OOM killer enabled.
[611203.140637] Restarting tasks ...
[611203.141135] usb 1-8.1: USB disconnect, device number 7
[611203.141755] done.
[611203.155268] random: crng reseeded on system resumption
[611203.162059] PM: suspend exit

After investigation, I noticed that for the code block if (write(power_state_fd, "mem", strlen("mem")) != strlen("mem"))

	ksft_exit_fail_msg("Failed to enter Suspend state\n");

The write will return -1 and errno is set to 16 (device busy). It should be caused by the write function is not successfully returned before the system suspend and the return value get messed when waking up. As a result, It may be better to check the time passed of those few instructions to determine whether the suspend is executed correctly for it is pretty hard to execute those few lines for 5 seconds.

The timer to wake up the system is set to expire after 5 seconds and no re-arm. If the timer remaining time is 0 second and 0 nano secomd, it means the timer expired and wake the system up. Otherwise, the system could be considered to enter the suspend state failed if there is any remaining time.

After appling this patch, the test would not fail for it believes the system does not go to suspend by mistake. It now could continue to the rest part of the test after suspend.

---
 .../testing/selftests/breakpoints/step_after_suspend_test.c  | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

index f82dcc1f8841e..67a2aaf1f9d94 100644
@@ -161,7 +161,10 @@ void suspend(void)
 	if (err < 0)
 		ksft_exit_fail_msg("timerfd_settime() failed\n");
 
-	if (write(power_state_fd, "mem", strlen("mem")) != strlen("mem"))
+	system("(echo mem > /sys/power/state) 2> /dev/null");
+
+	timerfd_gettime(timerfd, &spec);
+	if (spec.it_value.tv_sec != 0 || spec.it_value.tv_nsec != 0)
 		ksft_exit_fail_msg("Failed to enter Suspend state\n");
 
 	close(timerfd);

2.43.0

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

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

From: Christophe Leroy <[email protected]>

[ Upstream commit ba83b3239e657469709d15dcea5f9b65bf9dbf34 ]

On powerpc64, following tests fail locating vDSO functions:

~ # ./vdso_test_abi
TAP version 13
1..16
# [vDSO kselftest] VDSO_VERSION: LINUX_2.6.15 # Couldn't find __kernel_gettimeofday
ok 1 # SKIP __kernel_gettimeofday
# clock_id: CLOCK_REALTIME
# Couldn't find __kernel_clock_gettime
ok 2 # SKIP __kernel_clock_gettime CLOCK_REALTIME # Couldn't find __kernel_clock_getres
ok 3 # SKIP __kernel_clock_getres CLOCK_REALTIME
...
# Couldn't find __kernel_time
ok 16 # SKIP __kernel_time
# Totals: pass:0 fail:0 xfail:0 xpass:0 skip:16 error:0

~ # ./vdso_test_getrandom
__kernel_getrandom is missing!

~ # ./vdso_test_gettimeofday
Could not find __kernel_gettimeofday

~ # ./vdso_test_getcpu
Could not find __kernel_getcpu

On powerpc64, as shown below by readelf, vDSO functions symbols have type NOTYPE, so also accept that type when looking for symbols.

$ powerpc64-linux-gnu-readelf -a arch/powerpc/kernel/vdso/vdso64.so.dbg
ELF Header:
  Magic:   7f 45 4c 46 02 02 01 00 00 00 00 00 00 00 00 00
  Class:                             ELF64
  Data:                              2's complement, big endian
  Version:                           1 (current)
  OS/ABI:                            UNIX - System V
  ABI Version:                       0
  Type:                              DYN (Shared object file)
  Machine:                           PowerPC64
  Version:                           0x1
...

Symbol table '.dynsym' contains 12 entries:

   Num:    Value          Size Type    Bind   Vis      Ndx Name
     0: 0000000000000000     0 NOTYPE  LOCAL  DEFAULT  UND
     1: 0000000000000524    84 NOTYPE  GLOBAL DEFAULT    8 __[...]@@LINUX_2.6.15
     2: 00000000000005f0    36 NOTYPE  GLOBAL DEFAULT    8 __[...]@@LINUX_2.6.15
     3: 0000000000000578    68 NOTYPE  GLOBAL DEFAULT    8 __[...]@@LINUX_2.6.15
     4: 0000000000000000     0 OBJECT  GLOBAL DEFAULT  ABS LINUX_2.6.15
     5: 00000000000006c0    48 NOTYPE  GLOBAL DEFAULT    8 __[...]@@LINUX_2.6.15
     6: 0000000000000614   172 NOTYPE  GLOBAL DEFAULT    8 __[...]@@LINUX_2.6.15
     7: 00000000000006f0    84 NOTYPE  GLOBAL DEFAULT    8 __[...]@@LINUX_2.6.15
     8: 000000000000047c    84 NOTYPE  GLOBAL DEFAULT    8 __[...]@@LINUX_2.6.15
     9: 0000000000000454    12 NOTYPE  GLOBAL DEFAULT    8 __[...]@@LINUX_2.6.15
    10: 00000000000004d0    84 NOTYPE  GLOBAL DEFAULT    8 __[...]@@LINUX_2.6.15
    11: 00000000000005bc    52 NOTYPE  GLOBAL DEFAULT    8 __[...]@@LINUX_2.6.15

Symbol table '.symtab' contains 56 entries:
Num: Value Size Type Bind Vis Ndx Name
...

    45: 0000000000000000     0 OBJECT  GLOBAL DEFAULT  ABS LINUX_2.6.15
    46: 00000000000006c0    48 NOTYPE  GLOBAL DEFAULT    8 __kernel_getcpu
    47: 0000000000000524    84 NOTYPE  GLOBAL DEFAULT    8 __kernel_clock_getres
    48: 00000000000005f0    36 NOTYPE  GLOBAL DEFAULT    8 __kernel_get_tbfreq
    49: 000000000000047c    84 NOTYPE  GLOBAL DEFAULT    8 __kernel_gettimeofday
    50: 0000000000000614   172 NOTYPE  GLOBAL DEFAULT    8 __kernel_sync_dicache
    51: 00000000000006f0    84 NOTYPE  GLOBAL DEFAULT    8 __kernel_getrandom
    52: 0000000000000454    12 NOTYPE  GLOBAL DEFAULT    8 __kernel_sigtram[...]
    53: 0000000000000578    68 NOTYPE  GLOBAL DEFAULT    8 __kernel_time
    54: 00000000000004d0    84 NOTYPE  GLOBAL DEFAULT    8 __kernel_clock_g[...]
    55: 00000000000005bc    52 NOTYPE  GLOBAL DEFAULT    8 __kernel_get_sys[...]

---
 tools/testing/selftests/vDSO/parse_vdso.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

index 9ef3ad3789c17..540f9a284e9f0 100644
@@ -238,7 +238,8 @@ void *vdso_sym(const char *version, const char *name)
 		ELF(Sym) *sym = &vdso_info.symtab[chain];
 
 		/* Check for a defined global or weak function w/ right name. */
-		if (ELF64_ST_TYPE(sym->st_info) != STT_FUNC)
+		if (ELF64_ST_TYPE(sym->st_info) != STT_FUNC &&
+		    ELF64_ST_TYPE(sym->st_info) != STT_NOTYPE)
 			continue;
 		if (ELF64_ST_BIND(sym->st_info) != STB_GLOBAL &&
 		    ELF64_ST_BIND(sym->st_info) != STB_WEAK)

2.43.0

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

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

From: Robert Hancock <[email protected]>

commit 521da1e9225450bd323db5fa5bca942b1dc485b7 upstream.

Frequently an I2C write will be followed by a read, such as a register address write followed by a read of the register value. In this driver, when the TX FIFO half empty interrupt was raised and it was determined that there was enough space in the TX FIFO to send the following read command, it would do so without waiting for the TX FIFO to actually empty.

Unfortunately it appears that in some cases this can result in a NAK that was raised by the target device on the write, such as due to an unsupported register address, being ignored and the subsequent read being done anyway. This can potentially put the I2C bus into an invalid state and/or result in invalid read data being processed.

To avoid this, once a message has been fully written to the TX FIFO, wait for the TX FIFO empty interrupt before moving on to the next message, to ensure NAKs are handled properly.

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

@@ -478,14 +478,17 @@ static irqreturn_t xiic_process(int irq,
 			goto out;
 		}
 
-		xiic_fill_tx_fifo(i2c);
-
-		/* current message sent and there is space in the fifo */
-		if (!xiic_tx_space(i2c) && xiic_tx_fifo_space(i2c) >= 2) {
+		if (xiic_tx_space(i2c)) {
+			xiic_fill_tx_fifo(i2c);
+		} else {
+			/* current message fully written */
 			dev_dbg(i2c->adap.dev.parent,
 				"%s end of message sent, nmsgs: %d\n",
 				__func__, i2c->nmsgs);
-			if (i2c->nmsgs > 1) {
+			/* Don't move onto the next message until the TX FIFO empties,
+			 * to ensure that a NAK is not missed.
+			 */
+			if (i2c->nmsgs > 1 && (pend & XIIC_INTR_TX_EMPTY_MASK)) {
 				i2c->nmsgs--;
 				i2c->tx_msg++;
 				xfer_more = 1;

@@ -496,11 +499,7 @@ static irqreturn_t xiic_process(int irq,
 					"%s Got TX IRQ but no more to do...\n",
 					__func__);
 			}
-		} else if (!xiic_tx_space(i2c) && (i2c->nmsgs == 1))
-			/* current frame is sent and is last,
-			 * make sure to disable tx half
-			 */
-			xiic_irq_dis(i2c, XIIC_INTR_TX_HALF_MASK);
+		}
 	}
 out:
 	dev_dbg(i2c->adap.dev.parent, "%s clr: 0x%x\n", __func__, clr);

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

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

From: Jinjie Ruan <[email protected]>

commit 909f34f2462a99bf876f64c5c61c653213e32fce upstream.

Add MODULE_DEVICE_TABLE(), so modules could be properly autoloaded based on the alias from platform_device_id table.

---
 drivers/spi/spi-bcm63xx.c |    1 +
 1 file changed, 1 insertion(+)

@@ -484,6 +484,7 @@ static const struct platform_device_id b
 	{
 	},
 };
+MODULE_DEVICE_TABLE(platform, bcm63xx_spi_dev_match);
 
 static const struct of_device_id bcm63xx_spi_of_match[] = {
 	{ .compatible = "brcm,bcm6348-spi", .data = &bcm6348_spi_reg_offsets },

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

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

From: Luo Gengkun <[email protected]>

commit 62c0b1061593d7012292f781f11145b2d46f43ab upstream.

In perf_adjust_period, we will first calculate period, and then use this period to calculate delta. However, when delta is less than 0, there will be a deviation compared to when delta is greater than or equal to 0. For example, when delta is in the range of [-14,-1], the range of delta = delta + 7 is between [-7,6], so the final value of delta/8 is 0. Therefore, the impact of -1 and -2 will be ignored. This is unacceptable when the target period is very short, because we will lose a lot of samples.

Here are some tests and analyzes:
before:

  # perf record -e cs -F 1000  ./a.out
  [ perf record: Woken up 1 times to write data ]
  [ perf record: Captured and wrote 0.022 MB perf.data (518 samples) ]

  # perf script
  ...
  a.out     396   257.956048:         23 cs:  ffffffff81f4eeec schedul>
  a.out     396   257.957891:         23 cs:  ffffffff81f4eeec schedul>
  a.out     396   257.959730:         23 cs:  ffffffff81f4eeec schedul>
  a.out     396   257.961545:         23 cs:  ffffffff81f4eeec schedul>
  a.out     396   257.963355:         23 cs:  ffffffff81f4eeec schedul>
  a.out     396   257.965163:         23 cs:  ffffffff81f4eeec schedul>
  a.out     396   257.966973:         23 cs:  ffffffff81f4eeec schedul>
  a.out     396   257.968785:         23 cs:  ffffffff81f4eeec schedul>
  a.out     396   257.970593:         23 cs:  ffffffff81f4eeec schedul>
  ...

after:

  # perf record -e cs -F 1000  ./a.out
  [ perf record: Woken up 1 times to write data ]
  [ perf record: Captured and wrote 0.058 MB perf.data (1466 samples) ]

  # perf script
  ...
  a.out     395    59.338813:         11 cs:  ffffffff81f4eeec schedul>
  a.out     395    59.339707:         12 cs:  ffffffff81f4eeec schedul>
  a.out     395    59.340682:         13 cs:  ffffffff81f4eeec schedul>
  a.out     395    59.341751:         13 cs:  ffffffff81f4eeec schedul>
  a.out     395    59.342799:         12 cs:  ffffffff81f4eeec schedul>
  a.out     395    59.343765:         11 cs:  ffffffff81f4eeec schedul>
  a.out     395    59.344651:         11 cs:  ffffffff81f4eeec schedul>
  a.out     395    59.345539:         12 cs:  ffffffff81f4eeec schedul>
  a.out     395    59.346502:         13 cs:  ffffffff81f4eeec schedul>
  ...

test.c

int main() {
        for (int i = 0; i < 20000; i++)
                usleep(10);

        return 0;
}

  # time ./a.out
  real    0m1.583s
  user    0m0.040s
  sys     0m0.298s

The above results were tested on x86-64 qemu with KVM enabled using test.c as test program. Ideally, we should have around 1500 samples, but the previous algorithm had only about 500, whereas the modified algorithm now has about 1400. Further more, the new version shows 1 sample per 0.001s, while the previous one is 1 sample per 0.002s.This indicates that the new algorithm is more sensitive to small negative values compared to old algorithm.

---
 kernel/events/core.c |    6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

@@ -3618,7 +3618,11 @@ static void perf_adjust_period(struct pe
 	period = perf_calculate_period(event, nsec, count);
 
 	delta = (s64)(period - hwc->sample_period);
-	delta = (delta + 7) / 8; /* low pass filter */
+	if (delta >= 0)
+		delta += 7;
+	else
+		delta -= 7;
+	delta /= 8; /* low pass filter */
 
 	sample_period = hwc->sample_period + delta;
 

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

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

From: Helge Deller <[email protected]>

commit 9542130937e9dc707dd7c6b7af73326437da2d50 upstream.

For an itlb miss when executing code above 4 Gb on ILP64 adjust the iasq/iaoq in the same way isr/ior was adjusted. This fixes signal delivery for the 64-bit static test program from
http://ftp.parisc-linux.org/src/64bit.tar.gz. Note that signals are handled by the signal trampoline code in the 64-bit VDSO which is mapped into high userspace memory region above 4GB for 64-bit processes.

---
 arch/parisc/kernel/entry.S |    6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

@@ -1089,8 +1089,7 @@ ENTRY_CFI(intr_save)		/* for os_hpmc */
 	STREG           %r16, PT_ISR(%r29)
 	STREG           %r17, PT_IOR(%r29)
 
-#if 0 && defined(CONFIG_64BIT)
-	/* Revisit when we have 64-bit code above 4Gb */
+#if defined(CONFIG_64BIT)
 	b,n		intr_save2
 
 skip_save_ior:

@@ -1098,8 +1097,7 @@ skip_save_ior:
 	 * need to adjust iasq/iaoq here in the same way we adjusted isr/ior
 	 * above.
 	 */
-	extrd,u,*	%r8,PSW_W_BIT,1,%r1
-	cmpib,COND(=),n	1,%r1,intr_save2
+	bb,COND(>=),n	%r8,PSW_W_BIT,intr_save2
 	LDREG		PT_IASQ0(%r29), %r16
 	LDREG		PT_IAOQ0(%r29), %r17
 	/* adjust iasq/iaoq */

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

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

From: Jaroslav Kysela <[email protected]>

commit d278a9de5e1837edbe57b2f1f95a104ff6c84846 upstream.

The card identifier should contain only safe ASCII characters. The isalnum() returns true also for characters for non-ASCII characters.

---
 sound/core/init.c |   14 ++++++++++----
 1 file changed, 10 insertions(+), 4 deletions(-)

@@ -548,13 +548,19 @@ int snd_card_free(struct snd_card *card)
 }
 EXPORT_SYMBOL(snd_card_free);
 
+/* check, if the character is in the valid ASCII range */
+static inline bool safe_ascii_char(char c)
+{
+	return isascii(c) && isalnum(c);
+}
+
 /* retrieve the last word of shortname or longname */
 static const char *retrieve_id_from_card_name(const char *name)
 {
 	const char *spos = name;
 
 	while (*name) {
-		if (isspace(*name) && isalnum(name[1]))
+		if (isspace(*name) && safe_ascii_char(name[1]))
 			spos = name + 1;
 		name++;
 	}

@@ -581,12 +587,12 @@ static void copy_valid_id_string(struct
 {
 	char *id = card->id;
 
-	while (*nid && !isalnum(*nid))
+	while (*nid && !safe_ascii_char(*nid))
 		nid++;
 	if (isdigit(*nid))
 		*id++ = isalpha(*src) ? *src : 'D';
 	while (*nid && (size_t)(id - card->id) < sizeof(card->id) - 1) {
-		if (isalnum(*nid))
+		if (safe_ascii_char(*nid))
 			*id++ = *nid;
 		nid++;
 	}

@@ -684,7 +690,7 @@ card_id_store_attr(struct device *dev, s
 
 	for (idx = 0; idx < copy; idx++) {
 		c = buf[idx];
-		if (!isalnum(c) && c != '_' && c != '-')
+		if (!safe_ascii_char(c) && c != '_' && c != '-')
 			return -EINVAL;
 	}
 	memcpy(buf1, buf, copy);

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

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

From: Edward Adam Davis <[email protected]>

commit 1a00a393d6a7fb1e745a41edd09019bd6a0ad64c upstream.

---
 fs/ext4/namei.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -1832,7 +1832,7 @@ static struct ext4_dir_entry_2 *do_split
 		split = count/2;
 
 	hash2 = map[split].hash;
-	continued = hash2 == map[split - 1].hash;
+	continued = split > 0 ? hash2 == map[split - 1].hash : 0;
 	dxtrace(printk(KERN_INFO "Split block %lu at %x, %i/%i\n",
 			(unsigned long)dx_get_block(frame->at),
 					hash2, split, count-split));

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

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

From: Baokun Li <[email protected]>

commit 369c944ed1d7c3fb7b35f24e4735761153afe7b3 upstream.

Even though ext4_find_extent() returns an error, ext4_insert_range() still returns 0. This may confuse the user as to why fallocate returns success, but the contents of the file are not as expected. So propagate the error returned by ext4_find_extent() to avoid inconsistencies.

---
 fs/ext4/extents.c |    1 +
 1 file changed, 1 insertion(+)

@@ -5731,6 +5731,7 @@ int ext4_insert_range(struct inode *inod
 	path = ext4_find_extent(inode, offset_lblk, NULL, 0);
 	if (IS_ERR(path)) {
 		up_write(&EXT4_I(inode)->i_data_sem);
+		ret = PTR_ERR(path);
 		goto out_stop;
 	}
 

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

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

From: Luis Henriques (SUSE) <[email protected]>

commit 972090651ee15e51abfb2160e986fa050cfc7a40 upstream.

Function __jbd2_log_wait_for_space() assumes that '0' is not a valid value for transaction IDs, which is incorrect. Don't assume that and invoke jbd2_log_wait_commit() if the journal had a committing transaction instead.

---
 fs/jbd2/checkpoint.c |    7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

@@ -137,9 +137,12 @@ void __jbd2_log_wait_for_space(journal_t
 		if (space_left < nblocks) {
 			int chkpt = journal->j_checkpoint_transactions != NULL;
 			tid_t tid = 0;
+			bool has_transaction = false;
 
-			if (journal->j_committing_transaction)
+			if (journal->j_committing_transaction) {
 				tid = journal->j_committing_transaction->t_tid;
+				has_transaction = true;
+			}
 			spin_unlock(&journal->j_list_lock);
 			write_unlock(&journal->j_state_lock);
 			if (chkpt) {

@@ -147,7 +150,7 @@ void __jbd2_log_wait_for_space(journal_t
 			} else if (jbd2_cleanup_journal_tail(journal) == 0) {
 				/* We were able to recover space; yay! */
 				;
-			} else if (tid) {
+			} else if (has_transaction) {
 				/*
 				 * jbd2_journal_commit_transaction() may want
 				 * to take the checkpoint_mutex if JBD2_FLUSHED

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

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

From: Baokun Li <[email protected]>

commit a164f3a432aae62ca23d03e6d926b122ee5b860d upstream.

As Ojaswin mentioned in Link, in ext4_ext_insert_extent(), if the path is reallocated in ext4_ext_create_new_leaf(), we'll use the stale path and cause UAF. Below is a sample trace with dummy values:

ext4_ext_insert_extent
path = *ppath = 2000
ext4_ext_create_new_leaf(ppath)

    ext4_find_extent(ppath)
      path = *ppath = 2000
      if (depth > path[0].p_maxdepth)
            kfree(path = 2000);
            *ppath = path = NULL;
      path = kcalloc() = 3000
      *ppath = 3000;
      return path;

/* here path is still 2000, UAF! */
eh = path[depth].p_hdr

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

BUG: KASAN: slab-use-after-free in ext4_ext_insert_extent+0x26d4/0x3330
Read of size 8 at addr ffff8881027bf7d0 by task kworker/u36:1/179
CPU: 3 UID: 0 PID: 179 Comm: kworker/u6:1 Not tainted 6.11.0-rc2-dirty #866
Call Trace:
 <TASK>
 ext4_ext_insert_extent+0x26d4/0x3330
 ext4_ext_map_blocks+0xe22/0x2d40
 ext4_map_blocks+0x71e/0x1700
 ext4_do_writepages+0x1290/0x2800

[...]

Allocated by task 179:
 ext4_find_extent+0x81c/0x1f70
 ext4_ext_map_blocks+0x146/0x2d40
 ext4_map_blocks+0x71e/0x1700
 ext4_do_writepages+0x1290/0x2800
 ext4_writepages+0x26d/0x4e0
 do_writepages+0x175/0x700

[...]

Freed by task 179:
 kfree+0xcb/0x240
 ext4_find_extent+0x7c0/0x1f70
 ext4_ext_insert_extent+0xa26/0x3330
 ext4_ext_map_blocks+0xe22/0x2d40
 ext4_map_blocks+0x71e/0x1700
 ext4_do_writepages+0x1290/0x2800
 ext4_writepages+0x26d/0x4e0
 do_writepages+0x175/0x700

[...]
==================================================================

So use *ppath to update the path to avoid the above problem.

---
 fs/ext4/extents.c |    1 +
 1 file changed, 1 insertion(+)

@@ -2099,6 +2099,7 @@ prepend:
 				       ppath, newext);
 	if (err)
 		goto cleanup;
+	path = *ppath;
 	depth = ext_depth(inode);
 	eh = path[depth].p_hdr;
 

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

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

From: Baokun Li <[email protected]>

commit dcaa6c31134c0f515600111c38ed7750003e1b9c upstream.

In ext4_ext_try_to_merge_up(), set path[1].p_bh to NULL after it has been released, otherwise it may be released twice. An example of what triggers this is as follows:

split2 map split1
|--------|-------|--------|

ext4_ext_map_blocks
ext4_ext_handle_unwritten_extents
ext4_split_convert_extents
// path->p_depth == 0
ext4_split_extent

     // 1. do split1
     ext4_split_extent_at
       |ext4_ext_insert_extent
       |  ext4_ext_create_new_leaf
       |    ext4_ext_grow_indepth
       |      le16_add_cpu(&neh->eh_depth, 1)
       |    ext4_find_extent
       |      // return -ENOMEM
       |// get error and try zeroout
       |path = ext4_find_extent
       |  path->p_depth = 1
       |ext4_ext_try_to_merge
       |  ext4_ext_try_to_merge_up
       |    path->p_depth = 0
       |    brelse(path[1].p_bh)  ---> not set to NULL here
       |// zeroout success
     // 2. update path
     ext4_find_extent
     // 3. do split2
     ext4_split_extent_at
       ext4_ext_insert_extent
         ext4_ext_create_new_leaf
           ext4_ext_grow_indepth
             le16_add_cpu(&neh->eh_depth, 1)
           ext4_find_extent
             path[0].p_bh = NULL;
             path->p_depth = 1
             read_extent_tree_block  ---> return err
             // path[1].p_bh is still the old value
             ext4_free_ext_path
               ext4_ext_drop_refs
                 // path->p_depth == 1
                 brelse(path[1].p_bh)  ---> brelse a buffer twice

Finally got the following WARRNING when removing the buffer from lru:

============================================
VFS: brelse: Trying to free free buffer

WARNING: CPU: 2 PID: 72 at fs/buffer.c:1241 __brelse+0x58/0x90
CPU: 2 PID: 72 Comm: kworker/u19:1 Not tainted 6.9.0-dirty #716
RIP: 0010:__brelse+0x58/0x90
Call Trace:
 <TASK>
 __find_get_block+0x6e7/0x810
 bdev_getblk+0x2b/0x480
 __ext4_get_inode_loc+0x48a/0x1240
 ext4_get_inode_loc+0xb2/0x150
 ext4_reserve_inode_write+0xb7/0x230
 __ext4_mark_inode_dirty+0x144/0x6a0
 ext4_ext_insert_extent+0x9c8/0x3230
 ext4_ext_map_blocks+0xf45/0x2dc0
 ext4_map_blocks+0x724/0x1700
 ext4_do_writepages+0x12d6/0x2a70

[...]
============================================

---
 fs/ext4/extents.c |    1 +
 1 file changed, 1 insertion(+)

@@ -1872,6 +1872,7 @@ static void ext4_ext_try_to_merge_up(han
 	path[0].p_hdr->eh_max = cpu_to_le16(max_root);
 
 	brelse(path[1].p_bh);
+	path[1].p_bh = NULL;
 	ext4_free_blocks(handle, inode, NULL, blk, 1,
 			 EXT4_FREE_BLOCKS_METADATA | EXT4_FREE_BLOCKS_FORGET);
 }

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

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

From: Luis Henriques (SUSE) <[email protected]>

commit dd589b0f1445e1ea1085b98edca6e4d5dedb98d0 upstream.

Function ext4_wait_for_tail_page_commit() assumes that '0' is not a valid value for transaction IDs, which is incorrect. Don't assume that and invoke jbd2_log_wait_commit() if the journal had a committing transaction instead.

---
 fs/ext4/inode.c |   11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

@@ -5545,8 +5545,9 @@ static void ext4_wait_for_tail_page_comm
 	struct page *page;
 	unsigned offset;
 	journal_t *journal = EXT4_SB(inode->i_sb)->s_journal;
-	tid_t commit_tid = 0;
+	tid_t commit_tid;
 	int ret;
+	bool has_transaction;
 
 	offset = inode->i_size & (PAGE_SIZE - 1);
 	/*

@@ -5571,12 +5572,14 @@ static void ext4_wait_for_tail_page_comm
 		put_page(page);
 		if (ret != -EBUSY)
 			return;
-		commit_tid = 0;
+		has_transaction = false;
 		read_lock(&journal->j_state_lock);
-		if (journal->j_committing_transaction)
+		if (journal->j_committing_transaction) {
 			commit_tid = journal->j_committing_transaction->t_tid;
+			has_transaction = true;
+		}
 		read_unlock(&journal->j_state_lock);
-		if (commit_tid)
+		if (has_transaction)
 			jbd2_log_wait_commit(journal, commit_tid);
 	}
 }

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

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

From: Helge Deller <[email protected]>

commit d24449864da5838936669618356b0e30ca2999c3 upstream.

Currently the glibc isn't yet ported to 64-bit for hppa, so there is no usable userspace available yet.
But it's possible to manually build a static 64-bit binary and run that for testing. One such 64-bit test program is available at http://ftp.parisc-linux.org/src/64bit.tar.gz
and it shows various issues with the existing 64-bit syscall path in the kernel.
This patch fixes those issues.

---
 arch/parisc/kernel/syscall.S |   14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

@@ -217,10 +217,10 @@ linux_gateway_entry:
 
 #ifdef CONFIG_64BIT
 	ldil	L%sys_call_table, %r1
-	or,=	%r2,%r2,%r2
-	addil	L%(sys_call_table64-sys_call_table), %r1
+	or,ev	%r2,%r2,%r2
+	ldil	L%sys_call_table64, %r1
 	ldo	R%sys_call_table(%r1), %r19
-	or,=	%r2,%r2,%r2
+	or,ev	%r2,%r2,%r2
 	ldo	R%sys_call_table64(%r1), %r19
 #else
 	load32	sys_call_table, %r19

@@ -355,10 +355,10 @@ tracesys_next:
 	extrd,u	%r19,63,1,%r2			/* W hidden in bottom bit */
 
 	ldil	L%sys_call_table, %r1
-	or,=	%r2,%r2,%r2
-	addil	L%(sys_call_table64-sys_call_table), %r1
+	or,ev	%r2,%r2,%r2
+	ldil	L%sys_call_table64, %r1
 	ldo	R%sys_call_table(%r1), %r19
-	or,=	%r2,%r2,%r2
+	or,ev	%r2,%r2,%r2
 	ldo	R%sys_call_table64(%r1), %r19
 #else
 	load32	sys_call_table, %r19

@@ -930,6 +930,8 @@ ENTRY(sys_call_table)
 END(sys_call_table)
 
 #ifdef CONFIG_64BIT
+#undef __SYSCALL_WITH_COMPAT
+#define __SYSCALL_WITH_COMPAT(nr, native, compat)	__SYSCALL(nr, native)
 	.align 8
 ENTRY(sys_call_table64)
 #define SYSCALL_TABLE_64BIT

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

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

From: Andrew Jones <[email protected]>

commit db8e81132cf051843c9a59b46fa5a071c45baeb3 upstream.

An 'msi-parent' property with a single entry and no accompanying '#msi-cells' property is considered the legacy definition as opposed to its definition after being expanded with commit 126b16e2ad98 ("Docs: dt: add generic MSI bindings"). However, the legacy definition is completely compatible with the current definition and, since of_phandle_iterator_next() tolerates missing and present-but- zero *cells properties since commit e42ee61017f5 ("of: Let of_for_each_phandle fallback to non-negative cell_count"), there's no need anymore to special case the legacy definition in of_msi_get_domain().

Indeed, special casing has turned out to be harmful, because, as of commit 7c025238b47a ("dt-bindings: irqchip: Describe the IMX MU block as a MSI controller"), MSI controller DT bindings have started specifying '#msi-cells' as a required property (even when the value must be zero) as an effort to make the bindings more explicit. But, since the special casing of 'msi-parent' only uses the existence of '#msi-cells' for its heuristic, and not whether or not it's also nonzero, the legacy path is not taken. Furthermore, the path to support the new, broader definition isn't taken either since that path has been restricted to the platform-msi bus.

But, neither the definition of 'msi-parent' nor the definition of '#msi-cells' is platform-msi-specific (the platform-msi bus was just the first bus that needed '#msi-cells'), so remove both the special casing and the restriction. The code removal also requires changing to of_parse_phandle_with_optional_args() in order to ensure the legacy (but compatible) use of 'msi-parent' remains supported. This not only simplifies the code but also resolves an issue with PCI devices finding their MSI controllers on riscv, as the riscv,imsics binding requires '#msi-cells=<0>'.

---
 drivers/of/irq.c |   34 +++++++---------------------------
 1 file changed, 7 insertions(+), 27 deletions(-)

@@ -641,8 +641,7 @@ struct irq_domain *of_msi_map_get_device
  * @np: device node for @dev
  * @token: bus type for this domain
  *
- * Parse the msi-parent property (both the simple and the complex
- * versions), and returns the corresponding MSI domain.
+ * Parse the msi-parent property and returns the corresponding MSI domain.
  *
  * Returns: the MSI domain for this device (or NULL on failure).
  */

@@ -650,33 +649,14 @@ struct irq_domain *of_msi_get_domain(str
 				     struct device_node *np,
 				     enum irq_domain_bus_token token)
 {
-	struct device_node *msi_np;
+	struct of_phandle_iterator it;
 	struct irq_domain *d;
+	int err;
 
-	/* Check for a single msi-parent property */
-	msi_np = of_parse_phandle(np, "msi-parent", 0);
-	if (msi_np && !of_property_read_bool(msi_np, "#msi-cells")) {
-		d = irq_find_matching_host(msi_np, token);
-		if (!d)
-			of_node_put(msi_np);
-		return d;
-	}
-
-	if (token == DOMAIN_BUS_PLATFORM_MSI) {
-		/* Check for the complex msi-parent version */
-		struct of_phandle_args args;
-		int index = 0;
-
-		while (!of_parse_phandle_with_args(np, "msi-parent",
-						   "#msi-cells",
-						   index, &args)) {
-			d = irq_find_matching_host(args.np, token);
-			if (d)
-				return d;
-
-			of_node_put(args.np);
-			index++;
-		}
+	of_for_each_phandle(&it, err, np, "msi-parent", "#msi-cells", 0) {
+		d = irq_find_matching_host(it.node, token);
+		if (d)
+			return d;
 	}
 
 	return NULL;

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

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

From: Baokun Li <[email protected]>

commit f5cacdc6f2bb2a9bf214469dd7112b43dd2dd68a upstream.

In __jbd2_log_wait_for_space(), we might call jbd2_cleanup_journal_tail() to recover some journal space. But if an error occurs while executing jbd2_cleanup_journal_tail() (e.g., an EIO), we don't stop waiting for free space right away, we try other branches, and if j_committing_transaction is NULL (i.e., the tid is 0), we will get the following complain:

============================================
JBD2: I/O error when updating journal superblock for sdd-8. __jbd2_log_wait_for_space: needed 256 blocks and only had 217 space available __jbd2_log_wait_for_space: no way to get more journal space in sdd-8

------------[ cut here ]------------
WARNING: CPU: 2 PID: 139804 at fs/jbd2/checkpoint.c:109 __jbd2_log_wait_for_space+0x251/0x2e0
Modules linked in:
CPU: 2 PID: 139804 Comm: kworker/u8:3 Not tainted 6.6.0+ #1
RIP: 0010:__jbd2_log_wait_for_space+0x251/0x2e0
Call Trace:
 <TASK>
 add_transaction_credits+0x5d1/0x5e0
 start_this_handle+0x1ef/0x6a0
 jbd2__journal_start+0x18b/0x340
 ext4_dirty_inode+0x5d/0xb0
 __mark_inode_dirty+0xe4/0x5d0
 generic_update_time+0x60/0x70

[...]
============================================

So only if jbd2_cleanup_journal_tail() returns 1, i.e., there is nothing to clean up at the moment, continue to try to reclaim free space in other ways.

Note that this fix relies on commit 6f6a6fda2945 ("jbd2: fix ocfs2 corrupt when updating journal superblock fails") to make jbd2_cleanup_journal_tail return the correct error code.

---
 fs/jbd2/checkpoint.c |    7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

@@ -147,8 +147,11 @@ void __jbd2_log_wait_for_space(journal_t
 			write_unlock(&journal->j_state_lock);
 			if (chkpt) {
 				jbd2_log_do_checkpoint(journal);
-			} else if (jbd2_cleanup_journal_tail(journal) == 0) {
-				/* We were able to recover space; yay! */
+			} else if (jbd2_cleanup_journal_tail(journal) <= 0) {
+				/*
+				 * We were able to recover space or the
+				 * journal was aborted due to an error.
+				 */
 				;
 			} else if (has_transaction) {
 				/*

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

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

From: Heming Zhao <[email protected]>

commit dfe6c5692fb525e5e90cefe306ee0dffae13d35f upstream.

This bug has existed since the initial OCFS2 code. The code logic in ocfs2_sync_local_to_main() is wrong, as it ignores the last contiguous free bits, which causes an OCFS2 volume to lose the last free clusters of LA window on each umount command.

---
 fs/ocfs2/localalloc.c |   19 +++++++++++++++++++
 1 file changed, 19 insertions(+)

@@ -1026,6 +1026,25 @@ static int ocfs2_sync_local_to_main(stru
 		start = bit_off + 1;
 	}
 
+	/* clear the contiguous bits until the end boundary */
+	if (count) {
+		blkno = la_start_blk +
+			ocfs2_clusters_to_blocks(osb->sb,
+					start - count);
+
+		trace_ocfs2_sync_local_to_main_free(
+				count, start - count,
+				(unsigned long long)la_start_blk,
+				(unsigned long long)blkno);
+
+		status = ocfs2_release_clusters(handle,
+				main_bm_inode,
+				main_bm_bh, blkno,
+				count);
+		if (status < 0)
+			mlog_errno(status);
+	}
+
 bail:
 	if (status)
 		mlog_errno(status);

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

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

From: Joseph Qi <[email protected]>

commit 2af148ef8549a12f8025286b8825c2833ee6bcb8 upstream.

syzbot reported an uninit-value BUG:

BUG: KMSAN: uninit-value in ocfs2_get_block+0xed2/0x2710 fs/ocfs2/aops.c:159
ocfs2_get_block+0xed2/0x2710 fs/ocfs2/aops.c:159
do_mpage_readpage+0xc45/0x2780 fs/mpage.c:225
mpage_readahead+0x43f/0x840 fs/mpage.c:374
ocfs2_readahead+0x269/0x320 fs/ocfs2/aops.c:381
read_pages+0x193/0x1110 mm/readahead.c:160
page_cache_ra_unbounded+0x901/0x9f0 mm/readahead.c:273
do_page_cache_ra mm/readahead.c:303 [inline]
force_page_cache_ra+0x3b1/0x4b0 mm/readahead.c:332
force_page_cache_readahead mm/internal.h:347 [inline]
generic_fadvise+0x6b0/0xa90 mm/fadvise.c:106
vfs_fadvise mm/fadvise.c:185 [inline]
ksys_fadvise64_64 mm/fadvise.c:199 [inline]
__do_sys_fadvise64 mm/fadvise.c:214 [inline]
__se_sys_fadvise64 mm/fadvise.c:212 [inline]
__x64_sys_fadvise64+0x1fb/0x3a0 mm/fadvise.c:212
x64_sys_call+0xe11/0x3ba0
arch/x86/include/generated/asm/syscalls_64.h:222
do_syscall_x64 arch/x86/entry/common.c:52 [inline]
do_syscall_64+0xcd/0x1e0 arch/x86/entry/common.c:83
entry_SYSCALL_64_after_hwframe+0x77/0x7f

This is because when ocfs2_extent_map_get_blocks() fails, p_blkno is uninitialized. So the error log will trigger the above uninit-value access.

The error log is out-of-date since get_blocks() was removed long time ago. And the error code will be logged in ocfs2_extent_map_get_blocks() once ocfs2_get_cluster() fails, so fix this by only logging inode and block.

---
 fs/ocfs2/aops.c |    5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

@@ -172,9 +172,8 @@ int ocfs2_get_block(struct inode *inode,
 	err = ocfs2_extent_map_get_blocks(inode, iblock, &p_blkno, &count,
 					  &ext_flags);
 	if (err) {
-		mlog(ML_ERROR, "Error %d from get_blocks(0x%p, %llu, 1, "
-		     "%llu, NULL)\n", err, inode, (unsigned long long)iblock,
-		     (unsigned long long)p_blkno);
+		mlog(ML_ERROR, "get_blocks() failed, inode: 0x%p, "
+		     "block: %llu\n", inode, (unsigned long long)iblock);
 		goto bail;
 	}
 

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

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

From: Gautham Ananthakrishna <[email protected]>

commit 5ca60b86f57a4d9648f68418a725b3a7de2816b0 upstream.

One of our customers reported a crash and a corrupted ocfs2 filesystem. The crash was due to the detection of corruption. Upon troubleshooting, the fsck -fn output showed the below corruption

[EXTENT_LIST_FREE] Extent list in owner 33080590 claims 230 as the next free chain record, but fsck believes the largest valid value is 227. Clamp the next record value? n

The stat output from the debugfs.ocfs2 showed the following corruption where the "Next Free Rec:" had overshot the "Count:" in the root metadata block.

        Inode: 33080590   Mode: 0640   Generation: 2619713622 (0x9c25a856)
        FS Generation: 904309833 (0x35e6ac49)
        CRC32: 00000000   ECC: 0000
        Type: Regular   Attr: 0x0   Flags: Valid
        Dynamic Features: (0x16) HasXattr InlineXattr Refcounted
        Extended Attributes Block: 0  Extended Attributes Inline Size: 256
        User: 0 (root)   Group: 0 (root)   Size: 281320357888
        Links: 1   Clusters: 141738
        ctime: 0x66911b56 0x316edcb8 -- Fri Jul 12 06:02:30.829349048 2024
        atime: 0x66911d6b 0x7f7a28d -- Fri Jul 12 06:11:23.133669517 2024
        mtime: 0x66911b56 0x12ed75d7 -- Fri Jul 12 06:02:30.317552087 2024
        dtime: 0x0 -- Wed Dec 31 17:00:00 1969
        Refcount Block: 2777346
        Last Extblk: 2886943   Orphan Slot: 0
        Sub Alloc Slot: 0   Sub Alloc Bit: 14
        Tree Depth: 1   Count: 227   Next Free Rec: 230
        ## Offset        Clusters       Block#
        0  0             2310           2776351
        1  2310          2139           2777375
        2  4449          1221           2778399
        3  5670          731            2779423
        4  6401          566            2780447
        .......          ....           .......
        .......          ....           .......

The issue was in the reflink workfow while reserving space for inline xattr. The problematic function is ocfs2_reflink_xattr_inline(). By the time this function is called the reflink tree is already recreated at the destination inode from the source inode. At this point, this function reserves space for inline xattrs at the destination inode without even checking if there is space at the root metadata block. It simply reduces the l_count from 243 to 227 thereby making space of 256 bytes for inline xattr whereas the inode already has extents beyond this index (in this case up to 230), thereby causing corruption.

The fix for this is to reserve space for inline metadata at the destination inode before the reflink tree gets recreated. The customer has verified the fix.

---
 fs/ocfs2/refcounttree.c |   26 ++++++++++++++++++++++++--
 fs/ocfs2/xattr.c        |   11 +----------
 2 files changed, 25 insertions(+), 12 deletions(-)

@@ -35,6 +35,7 @@
 #include "namei.h"
 #include "ocfs2_trace.h"
 #include "file.h"
+#include "symlink.h"
 
 #include <linux/bio.h>
 #include <linux/blkdev.h>

@@ -4192,8 +4193,9 @@ static int __ocfs2_reflink(struct dentry
 	int ret;
 	struct inode *inode = d_inode(old_dentry);
 	struct buffer_head *new_bh = NULL;
+	struct ocfs2_inode_info *oi = OCFS2_I(inode);
 
-	if (OCFS2_I(inode)->ip_flags & OCFS2_INODE_SYSTEM_FILE) {
+	if (oi->ip_flags & OCFS2_INODE_SYSTEM_FILE) {
 		ret = -EINVAL;
 		mlog_errno(ret);
 		goto out;

@@ -4219,6 +4221,26 @@ static int __ocfs2_reflink(struct dentry
 		goto out_unlock;
 	}
 
+	if ((oi->ip_dyn_features & OCFS2_HAS_XATTR_FL) &&
+	    (oi->ip_dyn_features & OCFS2_INLINE_XATTR_FL)) {
+		/*
+		 * Adjust extent record count to reserve space for extended attribute.
+		 * Inline data count had been adjusted in ocfs2_duplicate_inline_data().
+		 */
+		struct ocfs2_inode_info *new_oi = OCFS2_I(new_inode);
+
+		if (!(new_oi->ip_dyn_features & OCFS2_INLINE_DATA_FL) &&
+		    !(ocfs2_inode_is_fast_symlink(new_inode))) {
+			struct ocfs2_dinode *new_di = (struct ocfs2_dinode *)new_bh->b_data;
+			struct ocfs2_dinode *old_di = (struct ocfs2_dinode *)old_bh->b_data;
+			struct ocfs2_extent_list *el = &new_di->id2.i_list;
+			int inline_size = le16_to_cpu(old_di->i_xattr_inline_size);
+
+			le16_add_cpu(&el->l_count, -(inline_size /
+					sizeof(struct ocfs2_extent_rec)));
+		}
+	}
+
 	ret = ocfs2_create_reflink_node(inode, old_bh,
 					new_inode, new_bh, preserve);
 	if (ret) {

@@ -4226,7 +4248,7 @@ static int __ocfs2_reflink(struct dentry
 		goto inode_unlock;
 	}
 
-	if (OCFS2_I(inode)->ip_dyn_features & OCFS2_HAS_XATTR_FL) {
+	if (oi->ip_dyn_features & OCFS2_HAS_XATTR_FL) {
 		ret = ocfs2_reflink_xattrs(inode, old_bh,
 					   new_inode, new_bh,
 					   preserve);

@@ -6534,16 +6534,7 @@ static int ocfs2_reflink_xattr_inline(st
 	}
 
 	new_oi = OCFS2_I(args->new_inode);
-	/*
-	 * Adjust extent record count to reserve space for extended attribute.
-	 * Inline data count had been adjusted in ocfs2_duplicate_inline_data().
-	 */
-	if (!(new_oi->ip_dyn_features & OCFS2_INLINE_DATA_FL) &&
-	    !(ocfs2_inode_is_fast_symlink(args->new_inode))) {
-		struct ocfs2_extent_list *el = &new_di->id2.i_list;
-		le16_add_cpu(&el->l_count, -(inline_size /
-					sizeof(struct ocfs2_extent_rec)));
-	}
+
 	spin_lock(&new_oi->ip_lock);
 	new_oi->ip_dyn_features |= OCFS2_HAS_XATTR_FL | OCFS2_INLINE_XATTR_FL;
 	new_di->i_dyn_features = cpu_to_le16(new_oi->ip_dyn_features);

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

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

From: Joseph Qi <[email protected]>

commit 35fccce29feb3706f649726d410122dd81b92c18 upstream.

ocfs2_global_read_info() will initialize and schedule dqi_sync_work at the end, if error occurs after successfully reading global quota, it will trigger the following warning with CONFIG_DEBUG_OBJECTS_* enabled:

ODEBUG: free active (active state 0) object: 00000000d8b0ce28 object type: timer_list hint: qsync_work_fn+0x0/0x16c

This reports that there is an active delayed work when freeing oinfo in error handling, so cancel dqi_sync_work first. BTW, return status instead of -1 when .read_file_info fails.

---
 fs/ocfs2/quota_local.c |    8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

@@ -689,7 +689,7 @@ static int ocfs2_local_read_info(struct
 	int status;
 	struct buffer_head *bh = NULL;
 	struct ocfs2_quota_recovery *rec;
-	int locked = 0;
+	int locked = 0, global_read = 0;
 
 	info->dqi_max_spc_limit = 0x7fffffffffffffffLL;
 	info->dqi_max_ino_limit = 0x7fffffffffffffffLL;

@@ -697,6 +697,7 @@ static int ocfs2_local_read_info(struct
 	if (!oinfo) {
 		mlog(ML_ERROR, "failed to allocate memory for ocfs2 quota"
 			       " info.");
+		status = -ENOMEM;
 		goto out_err;
 	}
 	info->dqi_priv = oinfo;

@@ -709,6 +710,7 @@ static int ocfs2_local_read_info(struct
 	status = ocfs2_global_read_info(sb, type);
 	if (status < 0)
 		goto out_err;
+	global_read = 1;
 
 	status = ocfs2_inode_lock(lqinode, &oinfo->dqi_lqi_bh, 1);
 	if (status < 0) {

@@ -779,10 +781,12 @@ out_err:
 		if (locked)
 			ocfs2_inode_unlock(lqinode, 1);
 		ocfs2_release_local_quota_bitmaps(&oinfo->dqi_chunk);
+		if (global_read)
+			cancel_delayed_work_sync(&oinfo->dqi_sync_work);
 		kfree(oinfo);
 	}
 	brelse(bh);
-	return -1;
+	return status;
 }
 
 /* Write local info to quota file */

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

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

From: Lizhi Xu <[email protected]>

commit c03a82b4a0c935774afa01fd6d128b444fd930a1 upstream.

Patch series "Misc fixes for ocfs2_read_blocks", v5.

This series contains 2 fixes for ocfs2_read_blocks(). The first patch fix the issue reported by syzbot, which detects bad unlock balance in ocfs2_read_blocks(). The second patch fixes an issue reported by Heming Zhao when reviewing above fix.

This patch (of 2):

There was a lock release before exiting, so remove the unreasonable unlock.

---
 fs/ocfs2/buffer_head_io.c |    1 -
 1 file changed, 1 deletion(-)

@@ -251,7 +251,6 @@ int ocfs2_read_blocks(struct ocfs2_cachi
 		if (bhs[i] == NULL) {
 			bhs[i] = sb_getblk(sb, block++);
 			if (bhs[i] == NULL) {
-				ocfs2_metadata_cache_io_unlock(ci);
 				status = -ENOMEM;
 				mlog_errno(status);
 				/* Don't forget to put previous bh! */

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

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

From: Julian Sun <[email protected]>

commit 5784d9fcfd43bd853654bb80c87ef293b9e8e80a upstream.

During the mounting process, if journal_reset() fails because of too short journal, then lead to jbd2_journal_load() fails with NULL j_sb_buffer. Subsequently, ocfs2_journal_shutdown() calls jbd2_journal_flush()->jbd2_cleanup_journal_tail()-> __jbd2_update_log_tail()->jbd2_journal_update_sb_log_tail() ->lock_buffer(journal->j_sb_buffer), resulting in a null-pointer dereference error.

To resolve this issue, we should check the JBD2_LOADED flag to ensure the journal was properly loaded. Additionally, use journal instead of osb->journal directly to simplify the code.

---
 fs/ocfs2/journal.c |    7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

@@ -989,7 +989,7 @@ void ocfs2_journal_shutdown(struct ocfs2
 	if (!igrab(inode))
 		BUG();
 
-	num_running_trans = atomic_read(&(osb->journal->j_num_trans));
+	num_running_trans = atomic_read(&(journal->j_num_trans));
 	trace_ocfs2_journal_shutdown(num_running_trans);
 
 	/* Do a commit_cache here. It will flush our journal, *and*

@@ -1008,9 +1008,10 @@ void ocfs2_journal_shutdown(struct ocfs2
 		osb->commit_task = NULL;
 	}
 
-	BUG_ON(atomic_read(&(osb->journal->j_num_trans)) != 0);
+	BUG_ON(atomic_read(&(journal->j_num_trans)) != 0);
 
-	if (ocfs2_mount_local(osb)) {
+	if (ocfs2_mount_local(osb) &&
+	    (journal->j_journal->j_flags & JBD2_LOADED)) {
 		jbd2_journal_lock_updates(journal->j_journal);
 		status = jbd2_journal_flush(journal->j_journal);
 		jbd2_journal_unlock_updates(journal->j_journal);

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

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

From: Lizhi Xu <[email protected]>

commit 33b525cef4cff49e216e4133cc48452e11c0391e upstream.

When doing cleanup, if flags without OCFS2_BH_READAHEAD, it may trigger NULL pointer dereference in the following ocfs2_set_buffer_uptodate() if bh is NULL.

---
 fs/ocfs2/buffer_head_io.c |    3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

@@ -404,7 +404,8 @@ read_failure:
 		/* Always set the buffer in the cache, even if it was
 		 * a forced read, or read-ahead which hasn't yet
 		 * completed. */
-		ocfs2_set_buffer_uptodate(ci, bh);
+		if (bh)
+			ocfs2_set_buffer_uptodate(ci, bh);
 	}
 	ocfs2_metadata_cache_io_unlock(ci);
 

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

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

From: Jisheng Zhang <[email protected]>

commit 5c178472af247c7b50f962495bb7462ba453b9fb upstream.

This is used in poison.h for poison pointer offset. Based on current SV39, SV48 and SV57 vm layout, 0xdead000000000000 is a proper value that is not mappable, this can avoid potentially turning an oops to an expolit.

---
 arch/riscv/Kconfig |    5 +++++
 1 file changed, 5 insertions(+)

@@ -84,6 +84,11 @@ config GENERIC_CSUM
 config GENERIC_HWEIGHT
 	def_bool y
 
+config ILLEGAL_POINTER_VALUE
+	hex
+	default 0 if 32BIT
+	default 0xdead000000000000 if 64BIT
+
 config PGTABLE_LEVELS
 	int
 	default 3 if 64BIT

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

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

From: Chun-Yi Lee <[email protected]>

commit 6d6e54fc71ad1ab0a87047fd9c211e75d86084a3 upstream.

For fixing CVE-2023-6270, f98364e92662 ("aoe: fix the potential use-after-free problem in aoecmd_cfg_pkts") makes tx() calling dev_put() instead of doing in aoecmd_cfg_pkts(). It avoids that the tx() runs into use-after-free.

Then Nicolai Stange found more places in aoe have potential use-after-free problem with tx(). e.g. revalidate(), aoecmd_ata_rw(), resend(), probe() and aoecmd_cfg_rsp(). Those functions also use aoenet_xmit() to push packet to tx queue. So they should also use dev_hold() to increase the refcnt of skb->dev.

On the other hand, moving dev_put() to tx() causes that the refcnt of skb->dev be reduced to a negative value, because corresponding dev_hold() are not called in revalidate(), aoecmd_ata_rw(), resend(), probe(), and aoecmd_cfg_rsp(). This patch fixed this issue.

---
 drivers/block/aoe/aoecmd.c |   13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)

@@ -362,6 +362,7 @@ ata_rw_frameinit(struct frame *f)
 	}
 
 	ah->cmdstat = ATA_CMD_PIO_READ | writebit | extbit;
+	dev_hold(t->ifp->nd);
 	skb->dev = t->ifp->nd;
 }
 

@@ -402,6 +403,8 @@ aoecmd_ata_rw(struct aoedev *d)
 		__skb_queue_head_init(&queue);
 		__skb_queue_tail(&queue, skb);
 		aoenet_xmit(&queue);
+	} else {
+		dev_put(f->t->ifp->nd);
 	}
 	return 1;
 }

@@ -484,10 +487,13 @@ resend(struct aoedev *d, struct frame *f
 	memcpy(h->dst, t->addr, sizeof h->dst);
 	memcpy(h->src, t->ifp->nd->dev_addr, sizeof h->src);
 
+	dev_hold(t->ifp->nd);
 	skb->dev = t->ifp->nd;
 	skb = skb_clone(skb, GFP_ATOMIC);
-	if (skb == NULL)
+	if (skb == NULL) {
+		dev_put(t->ifp->nd);
 		return;
+	}
 	f->sent = ktime_get();
 	__skb_queue_head_init(&queue);
 	__skb_queue_tail(&queue, skb);

@@ -618,6 +624,8 @@ probe(struct aoetgt *t)
 		__skb_queue_head_init(&queue);
 		__skb_queue_tail(&queue, skb);
 		aoenet_xmit(&queue);
+	} else {
+		dev_put(f->t->ifp->nd);
 	}
 }
 

@@ -1407,6 +1415,7 @@ aoecmd_ata_id(struct aoedev *d)
 	ah->cmdstat = ATA_CMD_ID_ATA;
 	ah->lba3 = 0xa0;
 
+	dev_hold(t->ifp->nd);
 	skb->dev = t->ifp->nd;
 
 	d->rttavg = RTTAVG_INIT;

@@ -1416,6 +1425,8 @@ aoecmd_ata_id(struct aoedev *d)
 	skb = skb_clone(skb, GFP_ATOMIC);
 	if (skb)
 		f->sent = ktime_get();
+	else
+		dev_put(t->ifp->nd);
 
 	return skb;
 }

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

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

From: Sebastian Reichel <[email protected]>

commit 12fd64babaca4dc09d072f63eda76ba44119816a upstream.

There is a clk == NULL check after the switch to check for unsupported clk types. Since clk is re-assigned in a loop, this check is useless right now for anything but the first round. Let's fix this up by assigning clk = NULL in the loop before the switch statement.

---
 drivers/clk/rockchip/clk.c |    3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

@@ -444,12 +444,13 @@ void __init rockchip_clk_register_branch
 				      struct rockchip_clk_branch *list,
 				      unsigned int nr_clk)
 {
-	struct clk *clk = NULL;
+	struct clk *clk;
 	unsigned int idx;
 	unsigned long flags;
 
 	for (idx = 0; idx < nr_clk; idx++, list++) {
 		flags = list->flags;
+		clk = NULL;
 
 		/* catch simple muxes */
 		switch (list->branch_type) {

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

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

From: Hans Verkuil <[email protected]>

commit 599f6899051cb70c4e0aa9fd591b9ee220cb6f14 upstream.

The cec_msg_set_reply_to() helper function never zeroed the struct cec_msg flags field, this can cause unexpected behavior if flags was uninitialized to begin with.

---
 include/uapi/linux/cec.h |    6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

@@ -132,6 +132,8 @@ static inline void cec_msg_init(struct c
  * Set the msg destination to the orig initiator and the msg initiator to the
  * orig destination. Note that msg and orig may be the same pointer, in which
  * case the change is done in place.
+ *
+ * It also zeroes the reply, timeout and flags fields.
  */
 static inline void cec_msg_set_reply_to(struct cec_msg *msg,
 					struct cec_msg *orig)

@@ -139,7 +141,9 @@ static inline void cec_msg_set_reply_to(
 	/* The destination becomes the initiator and vice versa */
 	msg->msg[0] = (cec_msg_destination(orig) << 4) |
 		      cec_msg_initiator(orig);
-	msg->reply = msg->timeout = 0;
+	msg->reply = 0;
+	msg->timeout = 0;
+	msg->flags = 0;
 }
 
 /* cec_msg flags field */

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

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

From: Zheng Wang <[email protected]>

commit c5a85ed88e043474161bbfe54002c89c1cb50ee2 upstream.

in venus_probe, core->work is bound with venus_sys_error_handler, which is used to handle error. The code use core->sys_err_done to make sync work. The core->work is started in venus_event_notify.

If we call venus_remove, there might be an unfished work. The possible sequence is as follows:

CPU0 CPU1

|venus_sys_error_handler
venus_remove |
hfi_destroy |
venus_hfi_destroy |
kfree(hdev); |

                     |hfi_reinit
					 |venus_hfi_queues_reinit
                     |//use hdev

Fix it by canceling the work in venus_remove.

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

@@ -348,6 +348,7 @@ static int venus_remove(struct platform_
 	struct device *dev = core->dev;
 	int ret;
 
+	cancel_delayed_work_sync(&core->work);
 	ret = pm_runtime_get_sync(dev);
 	WARN_ON(ret < 0);
 

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

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

From: Barnabás Czémán <[email protected]>

commit 129464e86c7445a858b790ac2d28d35f58256bbe upstream.

Move ST2 reading with overflow handling after measurement data reading.
ST2 register read have to be read after read measurment data, because it means end of the reading and realease the lock on the data. Remove ST2 read skip on interrupt based waiting because ST2 required to be read out at and of the axis read.

---
 drivers/iio/magnetometer/ak8975.c |   32 ++++++++++++++++----------------
 1 file changed, 16 insertions(+), 16 deletions(-)

@@ -673,22 +673,8 @@ static int ak8975_start_read_axis(struct
 	if (ret < 0)
 		return ret;
 
-	/* This will be executed only for non-interrupt based waiting case */
-	if (ret & data->def->ctrl_masks[ST1_DRDY]) {
-		ret = i2c_smbus_read_byte_data(client,
-					       data->def->ctrl_regs[ST2]);
-		if (ret < 0) {
-			dev_err(&client->dev, "Error in reading ST2\n");
-			return ret;
-		}
-		if (ret & (data->def->ctrl_masks[ST2_DERR] |
-			   data->def->ctrl_masks[ST2_HOFL])) {
-			dev_err(&client->dev, "ST2 status error 0x%x\n", ret);
-			return -EINVAL;
-		}
-	}
-
-	return 0;
+	/* Return with zero if the data is ready. */
+	return !data->def->ctrl_regs[ST1_DRDY];
 }
 
 /* Retrieve raw flux value for one of the x, y, or z axis.  */

@@ -715,6 +701,20 @@ static int ak8975_read_axis(struct iio_d
 	if (ret < 0)
 		goto exit;
 
+	/* Read out ST2 for release lock on measurment data. */
+	ret = i2c_smbus_read_byte_data(client, data->def->ctrl_regs[ST2]);
+	if (ret < 0) {
+		dev_err(&client->dev, "Error in reading ST2\n");
+		goto exit;
+	}
+
+	if (ret & (data->def->ctrl_masks[ST2_DERR] |
+		   data->def->ctrl_masks[ST2_HOFL])) {
+		dev_err(&client->dev, "ST2 status error 0x%x\n", ret);
+		ret = -EINVAL;
+		goto exit;
+	}
+
 	mutex_unlock(&data->lock);
 
 	pm_runtime_mark_last_busy(&data->client->dev);

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

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

From: Tetsuo Handa <[email protected]>

commit ada1986d07976d60bed5017aa38b7f7cf27883f7 upstream.

Alfred Agrell found that TOMOYO cannot handle execveat(AT_EMPTY_PATH) inside chroot environment where /dev and /proc are not mounted, for commit 51f39a1f0cea ("syscalls: implement execveat() system call") missed that TOMOYO tries to canonicalize argv[0] when the filename fed to the executed program as argv[0] is supplied using potentially nonexistent pathname.

Since "/dev/fd/<fd>" already lost symlink information used for obtaining that <fd>, it is too late to reconstruct symlink's pathname. Although <filename> part of "/dev/fd/<fd>/<filename>" might not be canonicalized, TOMOYO cannot use tomoyo_realpath_nofollow() when /dev or /proc is not mounted. Therefore, fallback to tomoyo_realpath_from_path() when tomoyo_realpath_nofollow() failed.

---
 security/tomoyo/domain.c |    9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

@@ -701,10 +701,13 @@ int tomoyo_find_next_domain(struct linux
 	ee->r.obj = &ee->obj;
 	ee->obj.path1 = bprm->file->f_path;
 	/* Get symlink's pathname of program. */
-	retval = -ENOENT;
 	exename.name = tomoyo_realpath_nofollow(original_name);
-	if (!exename.name)
-		goto out;
+	if (!exename.name) {
+		/* Fallback to realpath if symlink's pathname does not exist. */
+		exename.name = tomoyo_realpath_from_path(&bprm->file->f_path);
+		if (!exename.name)
+			goto out;
+	}
 	tomoyo_fill_path_info(&exename);
 retry:
 	/* Check 'aggregator' directive. */

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

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

From: Nuno Sa <[email protected]>

commit c684771630e64bc39bddffeb65dd8a6612a6b249 upstream.

The adp5589 seems to have the same behavior as similar devices as explained in commit 910a9f5636f5 ("Input: adp5588-keys - get value from data out when dir is out").

Basically, when the gpio is set as output we need to get the value from ADP5589_GPO_DATA_OUT_A register instead of ADP5589_GPI_STATUS_A.

---
 drivers/input/keyboard/adp5589-keys.c |   13 ++++++++++---
 1 file changed, 10 insertions(+), 3 deletions(-)

@@ -390,10 +390,17 @@ static int adp5589_gpio_get_value(struct
 	struct adp5589_kpad *kpad = gpiochip_get_data(chip);
 	unsigned int bank = kpad->var->bank(kpad->gpiomap[off]);
 	unsigned int bit = kpad->var->bit(kpad->gpiomap[off]);
+	int val;
 
-	return !!(adp5589_read(kpad->client,
-			       kpad->var->reg(ADP5589_GPI_STATUS_A) + bank) &
-			       bit);
+	mutex_lock(&kpad->gpio_lock);
+	if (kpad->dir[bank] & bit)
+		val = kpad->dat_out[bank];
+	else
+		val = adp5589_read(kpad->client,
+				   kpad->var->reg(ADP5589_GPI_STATUS_A) + bank);
+	mutex_unlock(&kpad->gpio_lock);
+
+	return !!(val & bit);
 }
 
 static void adp5589_gpio_set_value(struct gpio_chip *chip,

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

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

From: Filipe Manana <[email protected]>

commit 41fd1e94066a815a7ab0a7025359e9b40e4b3576 upstream.

During unmount, at close_ctree(), we have the following steps in this order:

1) Park the cleaner kthread - this doesn't destroy the kthread, it basically halts its execution (wake ups against it work but do nothing);

2) We stop the cleaner kthread - this results in freeing the respective struct task_struct;

3) We call btrfs_stop_all_workers() which waits for any jobs running in all the work queues and then free the work queues.

Syzbot reported a case where a fixup worker resulted in a crash when doing a delayed iput on its inode while attempting to wake up the cleaner at btrfs_add_delayed_iput(), because the task_struct of the cleaner kthread was already freed. This can happen during unmount because we don't wait for any fixup workers still running before we call kthread_stop() against the cleaner kthread, which stops and free all its resources.

Fix this by waiting for any fixup workers at close_ctree() before we call kthread_stop() against the cleaner and run pending delayed iputs.

The stack traces reported by syzbot were the following:

  BUG: KASAN: slab-use-after-free in __lock_acquire+0x77/0x2050 kernel/locking/lockdep.c:5065
  Read of size 8 at addr ffff8880272a8a18 by task kworker/u8:3/52

  CPU: 1 UID: 0 PID: 52 Comm: kworker/u8:3 Not tainted 6.12.0-rc1-syzkaller #0
  Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 09/13/2024
  Workqueue: btrfs-fixup btrfs_work_helper
  Call Trace:
   <TASK>
   __dump_stack lib/dump_stack.c:94 [inline]
   dump_stack_lvl+0x241/0x360 lib/dump_stack.c:120
   print_address_description mm/kasan/report.c:377 [inline]
   print_report+0x169/0x550 mm/kasan/report.c:488
   kasan_report+0x143/0x180 mm/kasan/report.c:601
   __lock_acquire+0x77/0x2050 kernel/locking/lockdep.c:5065
   lock_acquire+0x1ed/0x550 kernel/locking/lockdep.c:5825
   __raw_spin_lock_irqsave include/linux/spinlock_api_smp.h:110 [inline]
   _raw_spin_lock_irqsave+0xd5/0x120 kernel/locking/spinlock.c:162
   class_raw_spinlock_irqsave_constructor include/linux/spinlock.h:551 [inline]
   try_to_wake_up+0xb0/0x1480 kernel/sched/core.c:4154
   btrfs_writepage_fixup_worker+0xc16/0xdf0 fs/btrfs/inode.c:2842
   btrfs_work_helper+0x390/0xc50 fs/btrfs/async-thread.c:314
   process_one_work kernel/workqueue.c:3229 [inline]
   process_scheduled_works+0xa63/0x1850 kernel/workqueue.c:3310
   worker_thread+0x870/0xd30 kernel/workqueue.c:3391
   kthread+0x2f0/0x390 kernel/kthread.c:389
   ret_from_fork+0x4b/0x80 arch/x86/kernel/process.c:147
   ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:244
   </TASK>

  Allocated by task 2:
   kasan_save_stack mm/kasan/common.c:47 [inline]
   kasan_save_track+0x3f/0x80 mm/kasan/common.c:68
   unpoison_slab_object mm/kasan/common.c:319 [inline]
   __kasan_slab_alloc+0x66/0x80 mm/kasan/common.c:345
   kasan_slab_alloc include/linux/kasan.h:247 [inline]
   slab_post_alloc_hook mm/slub.c:4086 [inline]
   slab_alloc_node mm/slub.c:4135 [inline]
   kmem_cache_alloc_node_noprof+0x16b/0x320 mm/slub.c:4187
   alloc_task_struct_node kernel/fork.c:180 [inline]
   dup_task_struct+0x57/0x8c0 kernel/fork.c:1107
   copy_process+0x5d1/0x3d50 kernel/fork.c:2206
   kernel_clone+0x223/0x880 kernel/fork.c:2787
   kernel_thread+0x1bc/0x240 kernel/fork.c:2849
   create_kthread kernel/kthread.c:412 [inline]
   kthreadd+0x60d/0x810 kernel/kthread.c:765
   ret_from_fork+0x4b/0x80 arch/x86/kernel/process.c:147
   ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:244

  Freed by task 61:
   kasan_save_stack mm/kasan/common.c:47 [inline]
   kasan_save_track+0x3f/0x80 mm/kasan/common.c:68
   kasan_save_free_info+0x40/0x50 mm/kasan/generic.c:579
   poison_slab_object mm/kasan/common.c:247 [inline]
   __kasan_slab_free+0x59/0x70 mm/kasan/common.c:264
   kasan_slab_free include/linux/kasan.h:230 [inline]
   slab_free_hook mm/slub.c:2343 [inline]
   slab_free mm/slub.c:4580 [inline]
   kmem_cache_free+0x1a2/0x420 mm/slub.c:4682
   put_task_struct include/linux/sched/task.h:144 [inline]
   delayed_put_task_struct+0x125/0x300 kernel/exit.c:228
   rcu_do_batch kernel/rcu/tree.c:2567 [inline]
   rcu_core+0xaaa/0x17a0 kernel/rcu/tree.c:2823
   handle_softirqs+0x2c5/0x980 kernel/softirq.c:554
   __do_softirq kernel/softirq.c:588 [inline]
   invoke_softirq kernel/softirq.c:428 [inline]
   __irq_exit_rcu+0xf4/0x1c0 kernel/softirq.c:637
   irq_exit_rcu+0x9/0x30 kernel/softirq.c:649
   instr_sysvec_apic_timer_interrupt arch/x86/kernel/apic/apic.c:1037 [inline]
   sysvec_apic_timer_interrupt+0xa6/0xc0 arch/x86/kernel/apic/apic.c:1037
   asm_sysvec_apic_timer_interrupt+0x1a/0x20 arch/x86/include/asm/idtentry.h:702

  Last potentially related work creation:
   kasan_save_stack+0x3f/0x60 mm/kasan/common.c:47
   __kasan_record_aux_stack+0xac/0xc0 mm/kasan/generic.c:541
   __call_rcu_common kernel/rcu/tree.c:3086 [inline]
   call_rcu+0x167/0xa70 kernel/rcu/tree.c:3190
   context_switch kernel/sched/core.c:5318 [inline]
   __schedule+0x184b/0x4ae0 kernel/sched/core.c:6675
   schedule_idle+0x56/0x90 kernel/sched/core.c:6793
   do_idle+0x56a/0x5d0 kernel/sched/idle.c:354
   cpu_startup_entry+0x42/0x60 kernel/sched/idle.c:424
   start_secondary+0x102/0x110 arch/x86/kernel/smpboot.c:314
   common_startup_64+0x13e/0x147

  The buggy address belongs to the object at ffff8880272a8000
   which belongs to the cache task_struct of size 7424
  The buggy address is located 2584 bytes inside of
   freed 7424-byte region [ffff8880272a8000, ffff8880272a9d00)

  The buggy address belongs to the physical page:
  page: refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x272a8
  head: order:3 mapcount:0 entire_mapcount:0 nr_pages_mapped:0 pincount:0
  flags: 0xfff00000000040(head|node=0|zone=1|lastcpupid=0x7ff)
  page_type: f5(slab)
  raw: 00fff00000000040 ffff88801bafa500 dead000000000122 0000000000000000
  raw: 0000000000000000 0000000080040004 00000001f5000000 0000000000000000
  head: 00fff00000000040 ffff88801bafa500 dead000000000122 0000000000000000
  head: 0000000000000000 0000000080040004 00000001f5000000 0000000000000000
  head: 00fff00000000003 ffffea00009caa01 ffffffffffffffff 0000000000000000
  head: 0000000000000008 0000000000000000 00000000ffffffff 0000000000000000
  page dumped because: kasan: bad access detected
  page_owner tracks the page as allocated
  page last allocated via order 3, migratetype Unmovable, gfp_mask 0xd20c0(__GFP_IO|__GFP_FS|__GFP_NOWARN|__GFP_NORETRY|__GFP_COMP|__GFP_NOMEMALLOC), pid 2, tgid 2 (kthreadd), ts 71247381401, free_ts 71214998153
   set_page_owner include/linux/page_owner.h:32 [inline]
   post_alloc_hook+0x1f3/0x230 mm/page_alloc.c:1537
   prep_new_page mm/page_alloc.c:1545 [inline]
   get_page_from_freelist+0x3039/0x3180 mm/page_alloc.c:3457
   __alloc_pages_noprof+0x256/0x6c0 mm/page_alloc.c:4733
   alloc_pages_mpol_noprof+0x3e8/0x680 mm/mempolicy.c:2265
   alloc_slab_page+0x6a/0x120 mm/slub.c:2413
   allocate_slab+0x5a/0x2f0 mm/slub.c:2579
   new_slab mm/slub.c:2632 [inline]
   ___slab_alloc+0xcd1/0x14b0 mm/slub.c:3819
   __slab_alloc+0x58/0xa0 mm/slub.c:3909
   __slab_alloc_node mm/slub.c:3962 [inline]
   slab_alloc_node mm/slub.c:4123 [inline]
   kmem_cache_alloc_node_noprof+0x1fe/0x320 mm/slub.c:4187
   alloc_task_struct_node kernel/fork.c:180 [inline]
   dup_task_struct+0x57/0x8c0 kernel/fork.c:1107
   copy_process+0x5d1/0x3d50 kernel/fork.c:2206
   kernel_clone+0x223/0x880 kernel/fork.c:2787
   kernel_thread+0x1bc/0x240 kernel/fork.c:2849
   create_kthread kernel/kthread.c:412 [inline]
   kthreadd+0x60d/0x810 kernel/kthread.c:765
   ret_from_fork+0x4b/0x80 arch/x86/kernel/process.c:147
   ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:244
  page last free pid 5230 tgid 5230 stack trace:
   reset_page_owner include/linux/page_owner.h:25 [inline]
   free_pages_prepare mm/page_alloc.c:1108 [inline]
   free_unref_page+0xcd0/0xf00 mm/page_alloc.c:2638
   discard_slab mm/slub.c:2678 [inline]
   __put_partials+0xeb/0x130 mm/slub.c:3146
   put_cpu_partial+0x17c/0x250 mm/slub.c:3221
   __slab_free+0x2ea/0x3d0 mm/slub.c:4450
   qlink_free mm/kasan/quarantine.c:163 [inline]
   qlist_free_all+0x9a/0x140 mm/kasan/quarantine.c:179
   kasan_quarantine_reduce+0x14f/0x170 mm/kasan/quarantine.c:286
   __kasan_slab_alloc+0x23/0x80 mm/kasan/common.c:329
   kasan_slab_alloc include/linux/kasan.h:247 [inline]
   slab_post_alloc_hook mm/slub.c:4086 [inline]
   slab_alloc_node mm/slub.c:4135 [inline]
   kmem_cache_alloc_noprof+0x135/0x2a0 mm/slub.c:4142
   getname_flags+0xb7/0x540 fs/namei.c:139
   do_sys_openat2+0xd2/0x1d0 fs/open.c:1409
   do_sys_open fs/open.c:1430 [inline]
   __do_sys_openat fs/open.c:1446 [inline]
   __se_sys_openat fs/open.c:1441 [inline]
   __x64_sys_openat+0x247/0x2a0 fs/open.c:1441
   do_syscall_x64 arch/x86/entry/common.c:52 [inline]
   do_syscall_64+0xf3/0x230 arch/x86/entry/common.c:83
   entry_SYSCALL_64_after_hwframe+0x77/0x7f

  Memory state around the buggy address:
   ffff8880272a8900: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
   ffff8880272a8980: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
  >ffff8880272a8a00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
                              ^
   ffff8880272a8a80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
   ffff8880272a8b00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
  ==================================================================

---
 fs/btrfs/disk-io.c |   11 +++++++++++
 1 file changed, 11 insertions(+)

@@ -4245,6 +4245,17 @@ static void btrfs_destroy_all_ordered_ex
 	spin_unlock(&fs_info->ordered_root_lock);
 
 	/*
+	 * Wait for any fixup workers to complete.
+	 * If we don't wait for them here and they are still running by the time
+	 * we call kthread_stop() against the cleaner kthread further below, we
+	 * get an use-after-free on the cleaner because the fixup worker adds an
+	 * inode to the list of delayed iputs and then attempts to wakeup the
+	 * cleaner kthread, which was already stopped and destroyed. We parked
+	 * already the cleaner, but below we run all pending delayed iputs.
+	 */
+	btrfs_flush_workqueue(fs_info->fixup_workers);
+
+	/*
 	 * We need this here because if we've been flipped read-only we won't
 	 * get sync() from the umount, so we need to make sure any ordered
 	 * extents that haven't had their dirty pages IO start writeout yet

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

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

From: Emanuele Ghidoli <[email protected]>

commit 3360d41f4ac490282fddc3ccc0b58679aa5c065d upstream.

On a few platforms such as TI's AM69 device, disable_irq() fails to keep track of the interrupts that happen between disable_irq() and enable_irq() and those interrupts are missed. Use the ->irq_unmask() and ->irq_mask() methods instead of ->irq_enable() and ->irq_disable() to correctly keep track of edges when disable_irq is called.

This solves the issue of disable_irq() not working as expected on such platforms.

---
 drivers/gpio/gpio-davinci.c |    8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

@@ -294,7 +294,7 @@ err:
  * serve as EDMA event triggers.
  */
 
-static void gpio_irq_disable(struct irq_data *d)
+static void gpio_irq_mask(struct irq_data *d)
 {
 	struct davinci_gpio_regs __iomem *g = irq2regs(d);
 	u32 mask = (u32) irq_data_get_irq_handler_data(d);

@@ -303,7 +303,7 @@ static void gpio_irq_disable(struct irq_
 	writel_relaxed(mask, &g->clr_rising);
 }
 
-static void gpio_irq_enable(struct irq_data *d)
+static void gpio_irq_unmask(struct irq_data *d)
 {
 	struct davinci_gpio_regs __iomem *g = irq2regs(d);
 	u32 mask = (u32) irq_data_get_irq_handler_data(d);

@@ -329,8 +329,8 @@ static int gpio_irq_type(struct irq_data
 
 static struct irq_chip gpio_irqchip = {
 	.name		= "GPIO",
-	.irq_enable	= gpio_irq_enable,
-	.irq_disable	= gpio_irq_disable,
+	.irq_unmask	= gpio_irq_unmask,
+	.irq_mask	= gpio_irq_mask,
 	.irq_set_type	= gpio_irq_type,
 	.flags		= IRQCHIP_SET_TYPE_MASKED | IRQCHIP_SKIP_SET_WAKE,
 };

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

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

From: Theodore Ts'o <[email protected]>

[ Upstream commit 73c384c0cdaa8ea9ca9ef2d0cff6a25930f1648e ]

We can't fail in the truncate path without requiring an fsck. Add work around for this by using a combination of retry loops and the __GFP_NOFAIL flag.

From: Theodore Ts'o <[email protected]>

Stable-dep-of: c26ab35702f8 ("ext4: fix slab-use-after-free in ext4_split_extent_at()")

---
 fs/ext4/ext4.h    |  1 +
 fs/ext4/extents.c | 43 +++++++++++++++++++++++++++++++++----------
 2 files changed, 34 insertions(+), 10 deletions(-)

index fa2579abea7df..3871df6b67322 100644
@@ -629,6 +629,7 @@ enum {
  */
 #define EXT4_EX_NOCACHE				0x40000000
 #define EXT4_EX_FORCE_CACHE			0x20000000
+#define EXT4_EX_NOFAIL				0x10000000
 
 /*
  * Flags used by ext4_free_blocks

2.43.0

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

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

From: Baokun Li <[email protected]>

[ Upstream commit c26ab35702f8cd0cdc78f96aa5856bfb77be798f ]

We hit the following use-after-free:

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

BUG: KASAN: slab-use-after-free in ext4_split_extent_at+0xba8/0xcc0
Read of size 2 at addr ffff88810548ed08 by task kworker/u20:0/40
CPU: 0 PID: 40 Comm: kworker/u20:0 Not tainted 6.9.0-dirty #724
Call Trace:
 <TASK>
 kasan_report+0x93/0xc0
 ext4_split_extent_at+0xba8/0xcc0
 ext4_split_extent.isra.0+0x18f/0x500
 ext4_split_convert_extents+0x275/0x750
 ext4_ext_handle_unwritten_extents+0x73e/0x1580
 ext4_ext_map_blocks+0xe20/0x2dc0
 ext4_map_blocks+0x724/0x1700
 ext4_do_writepages+0x12d6/0x2a70

[...]

Allocated by task 40:
 __kmalloc_noprof+0x1ac/0x480
 ext4_find_extent+0xf3b/0x1e70
 ext4_ext_map_blocks+0x188/0x2dc0
 ext4_map_blocks+0x724/0x1700
 ext4_do_writepages+0x12d6/0x2a70

[...]

Freed by task 40:
 kfree+0xf1/0x2b0
 ext4_find_extent+0xa71/0x1e70
 ext4_ext_insert_extent+0xa22/0x3260
 ext4_split_extent_at+0x3ef/0xcc0
 ext4_split_extent.isra.0+0x18f/0x500
 ext4_split_convert_extents+0x275/0x750
 ext4_ext_handle_unwritten_extents+0x73e/0x1580
 ext4_ext_map_blocks+0xe20/0x2dc0
 ext4_map_blocks+0x724/0x1700
 ext4_do_writepages+0x12d6/0x2a70

[...]
==================================================================

The flow of issue triggering is as follows:

ext4_split_extent_at
path = *ppath ext4_ext_insert_extent(ppath)
ext4_ext_create_new_leaf(ppath)
ext4_find_extent(orig_path)
path = *orig_path read_extent_tree_block
// return -ENOMEM or -EIO
ext4_free_ext_path(path)
kfree(path)
*orig_path = NULL
a. If err is -ENOMEM:
ext4_ext_dirty(path + path->p_depth)
// path use-after-free !!!
b. If err is -EIO and we have EXT_DEBUG defined:
ext4_ext_show_leaf(path)
eh = path[depth].p_hdr
// path also use-after-free !!!

So when trying to zeroout or fix the extent length, call ext4_find_extent() to update the path.

In addition we use *ppath directly as an ext4_ext_show_leaf() input to avoid possible use-after-free when EXT_DEBUG is defined, and to avoid unnecessary path updates.