6.1.134-rc1 review

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

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

From: Ido Schimmel <[email protected]>

[ Upstream commit 4d0ab3a6885e3e9040310a8d8f54503366083626 ]

Cited commit transitioned IPv6 path selection to use hash-threshold instead of modulo-N. With hash-threshold, each nexthop is assigned a region boundary in the multipath hash function's output space and a nexthop is chosen if the calculated hash is smaller than the nexthop's region boundary.

Hash-threshold does not work correctly if path selection does not start with the first nexthop. For example, if fib6_select_path() is always passed the last nexthop in the group, then it will always be chosen because its region boundary covers the entire hash function's output space.

Fix this by starting the selection process from the first nexthop and do not consider nexthops for which rt6_score_route() provided a negative score.

---
 net/ipv6/route.c | 38 +++++++++++++++++++++++++++++++++++---
 1 file changed, 35 insertions(+), 3 deletions(-)

index 5cf6e824c0dff..2cfef1c971093 100644
@@ -416,11 +416,35 @@ static bool rt6_check_expired(const struct rt6_info *rt)
 	return false;
 }
 
+static struct fib6_info *
+rt6_multipath_first_sibling_rcu(const struct fib6_info *rt)
+{
+	struct fib6_info *iter;
+	struct fib6_node *fn;
+
+	fn = rcu_dereference(rt->fib6_node);
+	if (!fn)
+		goto out;
+	iter = rcu_dereference(fn->leaf);
+	if (!iter)
+		goto out;
+
+	while (iter) {
+		if (iter->fib6_metric == rt->fib6_metric &&
+		    rt6_qualify_for_ecmp(iter))
+			return iter;
+		iter = rcu_dereference(iter->fib6_next);
+	}
+
+out:
+	return NULL;
+}
+
 void fib6_select_path(const struct net *net, struct fib6_result *res,
 		      struct flowi6 *fl6, int oif, bool have_oif_match,
 		      const struct sk_buff *skb, int strict)
 {
-	struct fib6_info *match = res->f6i;
+	struct fib6_info *first, *match = res->f6i;
 	struct fib6_info *sibling;
 
 	if (!match->nh && (!match->fib6_nsiblings || have_oif_match))

@@ -444,10 +468,18 @@ void fib6_select_path(const struct net *net, struct fib6_result *res,
 		return;
 	}
 
-	if (fl6->mp_hash <= atomic_read(&match->fib6_nh->fib_nh_upper_bound))
+	first = rt6_multipath_first_sibling_rcu(match);
+	if (!first)
 		goto out;
 
-	list_for_each_entry_rcu(sibling, &match->fib6_siblings,
+	if (fl6->mp_hash <= atomic_read(&first->fib6_nh->fib_nh_upper_bound) &&
+	    rt6_score_route(first->fib6_nh, first->fib6_flags, oif,
+			    strict) >= 0) {
+		match = first;
+		goto out;
+	}
+
+	list_for_each_entry_rcu(sibling, &first->fib6_siblings,
 				fib6_siblings) {
 		const struct fib6_nh *nh = sibling->fib6_nh;
 		int nh_upper_bound;

2.39.5

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

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

From: Ido Schimmel <[email protected]>

[ Upstream commit 8b8e0dd357165e0258d9f9cdab5366720ed2f619 ]

Nexthops whose link is down are not supposed to be considered during path selection when the "ignore_routes_with_linkdown" sysctl is set. This is done by assigning them a negative region boundary.

However, when comparing the computed hash (unsigned) with the region boundary (signed), the negative region boundary is treated as unsigned, resulting in incorrect nexthop selection.

Fix by treating the computed hash as signed. Note that the computed hash is always in range of [0, 2^31 - 1].

---
 net/ipv6/route.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

index 2cfef1c971093..d6de164720a05 100644
@@ -446,6 +446,7 @@ void fib6_select_path(const struct net *net, struct fib6_result *res,
 {
 	struct fib6_info *first, *match = res->f6i;
 	struct fib6_info *sibling;
+	int hash;
 
 	if (!match->nh && (!match->fib6_nsiblings || have_oif_match))
 		goto out;

@@ -472,7 +473,8 @@ void fib6_select_path(const struct net *net, struct fib6_result *res,
 	if (!first)
 		goto out;
 
-	if (fl6->mp_hash <= atomic_read(&first->fib6_nh->fib_nh_upper_bound) &&
+	hash = fl6->mp_hash;
+	if (hash <= atomic_read(&first->fib6_nh->fib_nh_upper_bound) &&
 	    rt6_score_route(first->fib6_nh, first->fib6_flags, oif,
 			    strict) >= 0) {
 		match = first;

@@ -485,7 +487,7 @@ void fib6_select_path(const struct net *net, struct fib6_result *res,
 		int nh_upper_bound;
 
 		nh_upper_bound = atomic_read(&nh->fib_nh_upper_bound);
-		if (fl6->mp_hash > nh_upper_bound)
+		if (hash > nh_upper_bound)
 			continue;
 		if (rt6_score_route(nh, sibling->fib6_flags, oif, strict) < 0)
 			break;

2.39.5

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

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

From: Henry Martin <[email protected]>

[ Upstream commit fda8c491db2a90ff3e6fbbae58e495b4ddddeca3 ]

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

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

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

index 7b5c8bb02f119..e7db6a4e4dc9d 100644
@@ -250,18 +250,33 @@ static int com20020pci_probe(struct pci_dev *pdev,
 			card->tx_led.default_trigger = devm_kasprintf(&pdev->dev,
 							GFP_KERNEL, "arc%d-%d-tx",
 							dev->dev_id, i);
+			if (!card->tx_led.default_trigger) {
+				ret = -ENOMEM;
+				goto err_free_arcdev;
+			}
 			card->tx_led.name = devm_kasprintf(&pdev->dev, GFP_KERNEL,
 							"pci:green:tx:%d-%d",
 							dev->dev_id, i);
-
+			if (!card->tx_led.name) {
+				ret = -ENOMEM;
+				goto err_free_arcdev;
+			}
 			card->tx_led.dev = &dev->dev;
 			card->recon_led.brightness_set = led_recon_set;
 			card->recon_led.default_trigger = devm_kasprintf(&pdev->dev,
 							GFP_KERNEL, "arc%d-%d-recon",
 							dev->dev_id, i);
+			if (!card->recon_led.default_trigger) {
+				ret = -ENOMEM;
+				goto err_free_arcdev;
+			}
 			card->recon_led.name = devm_kasprintf(&pdev->dev, GFP_KERNEL,
 							"pci:red:recon:%d-%d",
 							dev->dev_id, i);
+			if (!card->recon_led.name) {
+				ret = -ENOMEM;
+				goto err_free_arcdev;
+			}
 			card->recon_led.dev = &dev->dev;
 
 			ret = devm_led_classdev_register(&pdev->dev, &card->tx_led);

2.39.5

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

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

From: Jens Axboe <[email protected]>

No upstream patch exists for this issue, as it was introduced by a stable backport.

A previous backport relied on other code changes in the io_uring file table and resource node handling, which means that sometimes a resource node switch can get missed. For 6.1-stable, that code is still in io_install_fixed_file(), so ensure we fall-through to that case for the success path too.

---
 io_uring/filetable.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -98,7 +98,7 @@ static int io_install_fixed_file(struct
 	*io_get_tag_slot(ctx->file_data, slot_index) = 0;
 	io_fixed_file_set(file_slot, file);
 	io_file_bitmap_set(&ctx->file_table, slot_index);
-	return 0;
+	ret = 0;
 err:
 	if (needs_switch)
 		io_rsrc_node_switch(ctx, ctx->file_data);

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

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

From: Alex Deucher <[email protected]>

[ Upstream commit 4161050d47e1b083a7e1b0b875c9907e1a6f1f1f ]

GC11 only has 1 mec.

---
 drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index c76895cca4d9a..61e869839641e 100644
@@ -1301,7 +1301,7 @@ static int gfx_v11_0_sw_init(void *handle)
 		adev->gfx.me.num_me = 1;
 		adev->gfx.me.num_pipe_per_me = 1;
 		adev->gfx.me.num_queue_per_pipe = 1;
-		adev->gfx.mec.num_mec = 2;
+		adev->gfx.mec.num_mec = 1;
 		adev->gfx.mec.num_pipe_per_mec = 4;
 		adev->gfx.mec.num_queue_per_pipe = 4;
 		break;

2.39.5

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

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

From: Sherry Sun <[email protected]>

[ Upstream commit d57d56e4dddfb5c92cd81abf8922055bf0fb85a4 ]

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

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

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

index f94c782638686..e96354edff6e9 100644
@@ -1394,12 +1394,12 @@ static int lpuart32_config_rs485(struct uart_port *port, struct ktermios *termio
 			struct lpuart_port, port);
 
 	unsigned long modem = lpuart32_read(&sport->port, UARTMODIR)
-				& ~(UARTMODEM_TXRTSPOL | UARTMODEM_TXRTSE);
+				& ~(UARTMODIR_TXRTSPOL | UARTMODIR_TXRTSE);
 	lpuart32_write(&sport->port, modem, UARTMODIR);
 
 	if (rs485->flags & SER_RS485_ENABLED) {
 		/* Enable auto RS-485 RTS mode */
-		modem |= UARTMODEM_TXRTSE;
+		modem |= UARTMODIR_TXRTSE;
 
 		/*
 		 * The hardware defaults to RTS logic HIGH while transfer.

@@ -1408,9 +1408,9 @@ static int lpuart32_config_rs485(struct uart_port *port, struct ktermios *termio
 		 * Note: UART is assumed to be active high.
 		 */
 		if (rs485->flags & SER_RS485_RTS_ON_SEND)
-			modem |= UARTMODEM_TXRTSPOL;
+			modem |= UARTMODIR_TXRTSPOL;
 		else if (rs485->flags & SER_RS485_RTS_AFTER_SEND)
-			modem &= ~UARTMODEM_TXRTSPOL;
+			modem &= ~UARTMODIR_TXRTSPOL;
 	}
 
 	lpuart32_write(&sport->port, modem, UARTMODIR);

2.39.5

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

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

From: Sherry Sun <[email protected]>

[ Upstream commit f5cb528d6441eb860250a2f085773aac4f44085e ]

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

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

index e96354edff6e9..011f175936132 100644
@@ -1395,6 +1395,19 @@ static int lpuart32_config_rs485(struct uart_port *port, struct ktermios *termio
 
 	unsigned long modem = lpuart32_read(&sport->port, UARTMODIR)
 				& ~(UARTMODIR_TXRTSPOL | UARTMODIR_TXRTSE);
+	u32 ctrl;
+
+	/* TXRTSE and TXRTSPOL only can be changed when transmitter is disabled. */
+	ctrl = lpuart32_read(&sport->port, UARTCTRL);
+	if (ctrl & UARTCTRL_TE) {
+		/* wait for the transmit engine to complete */
+		lpuart32_wait_bit_set(&sport->port, UARTSTAT, UARTSTAT_TC);
+		lpuart32_write(&sport->port, ctrl & ~UARTCTRL_TE, UARTCTRL);
+
+		while (lpuart32_read(&sport->port, UARTCTRL) & UARTCTRL_TE)
+			cpu_relax();
+	}
+
 	lpuart32_write(&sport->port, modem, UARTMODIR);
 
 	if (rs485->flags & SER_RS485_ENABLED) {

@@ -1414,6 +1427,10 @@ static int lpuart32_config_rs485(struct uart_port *port, struct ktermios *termio
 	}
 
 	lpuart32_write(&sport->port, modem, UARTMODIR);
+
+	if (ctrl & UARTCTRL_TE)
+		lpuart32_write(&sport->port, ctrl, UARTCTRL);
+
 	return 0;
 }
 

2.39.5

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

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

From: Ying Lu <[email protected]>

commit 51de3600093429e3b712e5f091d767babc5dd6df upstream.

Missing usbnet_going_away Check in Critical Path. The usb_submit_urb function lacks a usbnet_going_away validation, whereas __usbnet_queue_skb includes this check.

This inconsistency creates a race condition where:
A URB request may succeed, but the corresponding SKB data fails to be queued.

Subsequent processes:
(e.g., rx_complete → defer_bh → __skb_unlink(skb, list)) attempt to access skb->next, triggering a NULL pointer dereference (Kernel Panic).

---
 drivers/net/usb/usbnet.c |    6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

@@ -530,7 +530,8 @@ static int rx_submit (struct usbnet *dev
 	    netif_device_present (dev->net) &&
 	    test_bit(EVENT_DEV_OPEN, &dev->flags) &&
 	    !test_bit (EVENT_RX_HALT, &dev->flags) &&
-	    !test_bit (EVENT_DEV_ASLEEP, &dev->flags)) {
+	    !test_bit (EVENT_DEV_ASLEEP, &dev->flags) &&
+	    !usbnet_going_away(dev)) {
 		switch (retval = usb_submit_urb (urb, GFP_ATOMIC)) {
 		case -EPIPE:
 			usbnet_defer_kevent (dev, EVENT_RX_HALT);

@@ -551,8 +552,7 @@ static int rx_submit (struct usbnet *dev
 			tasklet_schedule (&dev->bh);
 			break;
 		case 0:
-			if (!usbnet_going_away(dev))
-				__usbnet_queue_skb(&dev->rxq, skb, rx_start);
+			__usbnet_queue_skb(&dev->rxq, skb, rx_start);
 		}
 	} else {
 		netif_dbg(dev, ifdown, dev->net, "rx: stopped\n");

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

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

From: Huacai Chen <[email protected]>

commit 4103cfe9dcb88010ae4911d3ff417457d1b6a720 upstream.

ARCH_DMA_MINALIGN is 1 by default, but some LoongArch-specific devices (such as APBDMA) require 16 bytes alignment. When the data buffer length is too small, the hardware may make an error writing cacheline. Thus, it is dangerous to allocate a small memory buffer for DMA. It's always safe to define ARCH_DMA_MINALIGN as L1_CACHE_BYTES but unnecessary (kmalloc() need small memory objects). Therefore, just increase it to 16.

---
 arch/loongarch/include/asm/cache.h |    2 ++
 1 file changed, 2 insertions(+)

@@ -8,6 +8,8 @@
 #define L1_CACHE_SHIFT		CONFIG_L1_CACHE_SHIFT
 #define L1_CACHE_BYTES		(1 << L1_CACHE_SHIFT)
 
+#define ARCH_DMA_MINALIGN	(16)
+
 #define __read_mostly __section(".data..read_mostly")
 
 #endif /* _ASM_CACHE_H */

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

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

From: Hengqi Chen <[email protected]>

commit 7e2586991e36663c9bc48c828b83eab180ad30a9 upstream.

Vincent reported that running BPF progs with tailcalls on LoongArch causes kernel hard lockup. Debugging the issues shows that the JITed image missing a jirl instruction at the end of the epilogue.

There are two passes in JIT compiling, the first pass set the flags and the second pass generates JIT code based on those flags. With BPF progs mixing bpf2bpf and tailcalls, build_prologue() generates N insns in the first pass and then generates N+1 insns in the second pass. This makes epilogue_offset off by one and we will jump to some unexpected insn and cause lockup. Fix this by inserting a nop insn.

---
 arch/loongarch/net/bpf_jit.c |    2 ++
 arch/loongarch/net/bpf_jit.h |    5 +++++
 2 files changed, 7 insertions(+)

@@ -142,6 +142,8 @@ static void build_prologue(struct jit_ct
 	 */
 	if (seen_tail_call(ctx) && seen_call(ctx))
 		move_reg(ctx, TCC_SAVED, REG_TCC);
+	else
+		emit_insn(ctx, nop);
 
 	ctx->stack_size = stack_adjust;
 }

@@ -25,6 +25,11 @@ struct jit_data {
 	struct jit_ctx ctx;
 };
 
+static inline void emit_nop(union loongarch_instruction *insn)
+{
+	insn->word = INSN_NOP;
+}
+
 #define emit_insn(ctx, func, ...)						\
 do {										\
 	if (ctx->image != NULL) {						\

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

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

From: Hengqi Chen <[email protected]>

commit 52266f1015a8b5aabec7d127f83d105f702b388e upstream.

Vincent reported that running XDP synproxy program on LoongArch results in the following error:

JIT doesn't support bpf-to-bpf calls

With dmesg:

    multi-func JIT bug 1391 != 1390

The root cause is that verifier will refill the imm with the correct addresses of bpf_calls for BPF_PSEUDO_FUNC instructions and then run the last pass of JIT. So we generate different JIT code for the same instruction in two passes (one for placeholder and the other for the real address). Let's use move_addr() instead.

See commit 64f50f6575721ef0 ("LoongArch, bpf: Use 4 instructions for function address in JIT") for a similar fix.

---
 arch/loongarch/net/bpf_jit.c |    5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

@@ -810,7 +810,10 @@ static int build_insn(const struct bpf_i
 	{
 		const u64 imm64 = (u64)(insn + 1)->imm << 32 | (u32)insn->imm;
 
-		move_imm(ctx, dst, imm64, is32);
+		if (bpf_pseudo_func(insn))
+			move_addr(ctx, dst, imm64);
+		else
+			move_imm(ctx, dst, imm64, is32);
 		return 1;
 	}
 

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

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

From: Srinivas Pandruvada <[email protected]>

commit 9462e74c5c983cce34019bfb27f734552bebe59f upstream.

After resume/online turbo limit ratio (TRL) is restored partially if the admin explicitly changed TRL from user space.

A hash table is used to store SST mail box and MSR settings when modified to restore those settings after resume or online. This uses a struct isst_cmd field "data" to store these settings. This is a 64 bit field. But isst_store_new_cmd() is only assigning as u32. This results in truncation of 32 bits.

Change the argument to u64 from u32.

---
 drivers/platform/x86/intel/speed_select_if/isst_if_common.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -77,7 +77,7 @@ static DECLARE_HASHTABLE(isst_hash, 8);
 static DEFINE_MUTEX(isst_hash_lock);
 
 static int isst_store_new_cmd(int cmd, u32 cpu, int mbox_cmd_type, u32 param,
-			      u32 data)
+			      u64 data)
 {
 	struct isst_cmd *sst_cmd;
 

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

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

From: Markus Elfring <[email protected]>

commit 4279e72cab31dd3eb8c89591eb9d2affa90ab6aa upstream.

The function call “dmaengine_unmap_put(unmap)” was used in an if branch. The same call was immediately triggered by a subsequent goto statement. Thus avoid such a call repetition.

This issue was detected by using the Coccinelle software.

---
 drivers/ntb/test/ntb_perf.c |    4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

@@ -839,10 +839,8 @@ static int perf_copy_chunk(struct perf_t
 	dma_set_unmap(tx, unmap);
 
 	ret = dma_submit_error(dmaengine_submit(tx));
-	if (ret) {
-		dmaengine_unmap_put(unmap);
+	if (ret)
 		goto err_free_resource;
-	}
 
 	dmaengine_unmap_put(unmap);
 

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

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

From: Peter Zijlstra (Intel) <[email protected]>

commit 314dfe10576912e1d786b13c5d4eee8c51b63caa upstream.

The x86_pmu_drain_pebs static call was introduced in commit 7c9903c9bf71 ("x86/perf, static_call: Optimize x86_pmu methods"), but it's not really used to replace the old method.

Apply the static call for drain_pebs.

---
 arch/x86/events/intel/core.c |    2 +-
 arch/x86/events/intel/ds.c   |    2 +-
 arch/x86/events/perf_event.h |    1 +
 3 files changed, 3 insertions(+), 2 deletions(-)

@@ -2975,7 +2975,7 @@ static int handle_pmi_common(struct pt_r
 
 		handled++;
 		x86_pmu_handle_guest_pebs(regs, &data);
-		x86_pmu.drain_pebs(regs, &data);
+		static_call(x86_pmu_drain_pebs)(regs, &data);
 		status &= intel_ctrl | GLOBAL_STATUS_TRACE_TOPAPMI;
 
 		/*

@@ -793,7 +793,7 @@ static inline void intel_pmu_drain_pebs_
 {
 	struct perf_sample_data data;
 
-	x86_pmu.drain_pebs(NULL, &data);
+	static_call(x86_pmu_drain_pebs)(NULL, &data);
 }
 
 /*

@@ -1047,6 +1047,7 @@ extern struct x86_pmu x86_pmu __read_mos
 
 DECLARE_STATIC_CALL(x86_pmu_set_period, *x86_pmu.set_period);
 DECLARE_STATIC_CALL(x86_pmu_update,     *x86_pmu.update);
+DECLARE_STATIC_CALL(x86_pmu_drain_pebs,	*x86_pmu.drain_pebs);
 
 static __always_inline struct x86_perf_task_context_opt *task_context_opt(void *ctx)
 {

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

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

From: Kan Liang <[email protected]>

commit f9bdf1f953392c9edd69a7f884f78c0390127029 upstream.

The WARN_ON(this_cpu_read(cpu_hw_events.enabled)) in the intel_pmu_save_and_restart_reload() is triggered, when sampling read topdown events.

In a NMI handler, the cpu_hw_events.enabled is set and used to indicate the status of core PMU. The generic pmu->pmu_disable_count, updated in the perf_pmu_disable/enable pair, is not touched.
However, the perf_pmu_disable/enable pair is invoked when sampling read in a NMI handler. The cpuc->enabled is mistakenly set by the perf_pmu_enable().

Avoid disabling PMU if the core PMU is already disabled. Merge the logic together.

---
 arch/x86/events/intel/core.c |   41 +++++++++++++++++++++++------------------
 arch/x86/events/intel/ds.c   |   11 +----------
 arch/x86/events/perf_event.h |    2 +-
 3 files changed, 25 insertions(+), 29 deletions(-)

@@ -2689,28 +2689,33 @@ static u64 adl_update_topdown_event(stru
 
 DEFINE_STATIC_CALL(intel_pmu_update_topdown_event, x86_perf_event_update);
 
-static void intel_pmu_read_topdown_event(struct perf_event *event)
+static void intel_pmu_read_event(struct perf_event *event)
 {
-	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+	if (event->hw.flags & (PERF_X86_EVENT_AUTO_RELOAD | PERF_X86_EVENT_TOPDOWN)) {
+		struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+		bool pmu_enabled = cpuc->enabled;
+
+		/* Only need to call update_topdown_event() once for group read. */
+		if (is_metric_event(event) && (cpuc->txn_flags & PERF_PMU_TXN_READ))
+			return;
+
+		cpuc->enabled = 0;
+		if (pmu_enabled)
+			intel_pmu_disable_all();
+
+		if (is_topdown_event(event))
+			static_call(intel_pmu_update_topdown_event)(event);
+		else
+			intel_pmu_drain_pebs_buffer();
+
+		cpuc->enabled = pmu_enabled;
+		if (pmu_enabled)
+			intel_pmu_enable_all(0);
 
-	/* Only need to call update_topdown_event() once for group read. */
-	if ((cpuc->txn_flags & PERF_PMU_TXN_READ) &&
-	    !is_slots_event(event))
 		return;
+	}
 
-	perf_pmu_disable(event->pmu);
-	static_call(intel_pmu_update_topdown_event)(event);
-	perf_pmu_enable(event->pmu);
-}
-
-static void intel_pmu_read_event(struct perf_event *event)
-{
-	if (event->hw.flags & PERF_X86_EVENT_AUTO_RELOAD)
-		intel_pmu_auto_reload_read(event);
-	else if (is_topdown_count(event))
-		intel_pmu_read_topdown_event(event);
-	else
-		x86_perf_event_update(event);
+	x86_perf_event_update(event);
 }
 
 static void intel_pmu_enable_fixed(struct perf_event *event)

@@ -789,7 +789,7 @@ unlock:
 	return 1;
 }
 
-static inline void intel_pmu_drain_pebs_buffer(void)
+void intel_pmu_drain_pebs_buffer(void)
 {
 	struct perf_sample_data data;
 

@@ -1902,15 +1902,6 @@ get_next_pebs_record_by_bit(void *base,
 	return NULL;
 }
 
-void intel_pmu_auto_reload_read(struct perf_event *event)
-{
-	WARN_ON(!(event->hw.flags & PERF_X86_EVENT_AUTO_RELOAD));
-
-	perf_pmu_disable(event->pmu);
-	intel_pmu_drain_pebs_buffer();
-	perf_pmu_enable(event->pmu);
-}
-
 /*
  * Special variant of intel_pmu_save_and_restart() for auto-reload.
  */

@@ -1536,7 +1536,7 @@ void intel_pmu_pebs_disable_all(void);
 
 void intel_pmu_pebs_sched_task(struct perf_event_context *ctx, bool sched_in);
 
-void intel_pmu_auto_reload_read(struct perf_event *event);
+void intel_pmu_drain_pebs_buffer(void);
 
 void intel_pmu_store_pebs_lbrs(struct lbr_entry *lbr);
 

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

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

From: Ivan Orlov <[email protected]>

commit 92e9bac18124682c4b99ede9ee3bcdd68f121e92 upstream.

The 'device_name' array doesn't exist out of the 'overflow_allocation_test' function scope. However, it is being used as a driver name when calling 'kunit_driver_create' from 'kunit_device_register'. It produces the kernel panic with KASAN enabled.

Since this variable is used in one place only, remove it and pass the device name into kunit_device_register directly as an ascii string.

---
 lib/overflow_kunit.c |    3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

@@ -608,7 +608,6 @@ DEFINE_TEST_ALLOC(devm_kzalloc,  devm_kf
 
 static void overflow_allocation_test(struct kunit *test)
 {
-	const char device_name[] = "overflow-test";
 	struct device *dev;
 	int count = 0;
 

@@ -618,7 +617,7 @@ static void overflow_allocation_test(str
 } while (0)
 
 	/* Create dummy device for devm_kmalloc()-family tests. */
-	dev = root_device_register(device_name);
+	dev = root_device_register("overflow-test");
 	KUNIT_ASSERT_FALSE_MSG(test, IS_ERR(dev),
 			       "Cannot register test device\n");
 

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

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

From: Josef Bacik <[email protected]>

commit 5eb178f373b4f16f3b42d55ff88fc94dd95b93b1 upstream.

In walk_up_proc() we BUG_ON(ret) from btrfs_dec_ref(). This is incorrect, we have proper error handling here, return the error.

---
 fs/btrfs/extent-tree.c |    5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

@@ -5575,7 +5575,10 @@ static noinline int walk_up_proc(struct
 				ret = btrfs_dec_ref(trans, root, eb, 1);
 			else
 				ret = btrfs_dec_ref(trans, root, eb, 0);
-			BUG_ON(ret); /* -ENOMEM */
+			if (ret) {
+				btrfs_abort_transaction(trans, ret);
+				return ret;
+			}
 			if (is_fstree(root->root_key.objectid)) {
 				ret = btrfs_qgroup_trace_leaf_items(trans, eb);
 				if (ret) {

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

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

From: Guilherme G. Piccoli <[email protected]>

commit d90c9de9de2f1712df56de6e4f7d6982d358cabe upstream.

TSC could be reset in deep ACPI sleep states, even with invariant TSC.

That's the reason we have sched_clock() save/restore functions, to deal with this situation. But what happens is that such functions are guarded with a check for the stability of sched_clock - if not considered stable, the save/restore routines aren't executed.

On top of that, we have a clear comment in native_sched_clock() saying that *even* with TSC unstable, we continue using TSC for sched_clock due to its speed.

In other words, if we have a situation of TSC getting detected as unstable, it marks the sched_clock as unstable as well, so subsequent S3 sleep cycles could bring bogus sched_clock values due to the lack of the save/restore mechanism, causing warnings like this:

  [22.954918] ------------[ cut here ]------------
  [22.954923] Delta way too big! 18446743750843854390 ts=18446744072977390405 before=322133536015 after=322133536015 write stamp=18446744072977390405
  [22.954923] If you just came from a suspend/resume,
  [22.954923] please switch to the trace global clock:
  [22.954923]   echo global > /sys/kernel/tracing/trace_clock
  [22.954923] or add trace_clock=global to the kernel command line
  [22.954937] WARNING: CPU: 2 PID: 5728 at kernel/trace/ring_buffer.c:2890 rb_add_timestamp+0x193/0x1c0

Notice that the above was reproduced even with "trace_clock=global".

The fix for that is to _always_ save/restore the sched_clock on suspend cycle _if TSC is used_ as sched_clock - only if we fallback to jiffies the sched_clock_stable() check becomes relevant to save/restore the sched_clock.

---
 arch/x86/kernel/tsc.c |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

@@ -920,7 +920,7 @@ static unsigned long long cyc2ns_suspend
 
 void tsc_save_sched_clock_state(void)
 {
-	if (!sched_clock_stable())
+	if (!static_branch_likely(&__use_tsc) && !sched_clock_stable())
 		return;
 
 	cyc2ns_suspend = sched_clock();

@@ -940,7 +940,7 @@ void tsc_restore_sched_clock_state(void)
 	unsigned long flags;
 	int cpu;
 
-	if (!sched_clock_stable())
+	if (!static_branch_likely(&__use_tsc) && !sched_clock_stable())
 		return;
 
 	local_irq_save(flags);

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

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

From: Jann Horn <[email protected]>

commit 3ef938c3503563bfc2ac15083557f880d29c2e64 upstream.

On the following path, flush_tlb_range() can be used for zapping normal PMD entries (PMD entries that point to page tables) together with the PTE entries in the pointed-to page table:

collapse_pte_mapped_thp
pmdp_collapse_flush
flush_tlb_range

The arm64 version of flush_tlb_range() has a comment describing that it can be used for page table removal, and does not use any last-level invalidation optimizations. Fix the X86 version by making it behave the same way.

Currently, X86 only uses this information for the following two purposes, which I think means the issue doesn't have much impact:

- In native_flush_tlb_multi() for checking if lazy TLB CPUs need to be IPI'd to avoid issues with speculative page table walks.
- In Hyper-V TLB paravirtualization, again for lazy TLB stuff.

The patch "x86/mm: only invalidate final translations with INVLPGB" which is currently under review (see
<https://lore.kernel.org/all/[email protected]/>)
would probably be making the impact of this a lot worse.

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

@@ -228,7 +228,7 @@ void flush_tlb_multi(const struct cpumas
 	flush_tlb_mm_range((vma)->vm_mm, start, end,			\
 			   ((vma)->vm_flags & VM_HUGETLB)		\
 				? huge_page_shift(hstate_vma(vma))	\
-				: PAGE_SHIFT, false)
+				: PAGE_SHIFT, true)
 
 extern void flush_tlb_all(void);
 extern void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,

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

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

From: Murad Masimov <[email protected]>

commit 2ff0e408db36c21ed3fa5e3c1e0e687c82cf132f upstream.

Syzkaller has reported a warning in to_nfit_bus_uuid(): "only secondary bus families can be translated". This warning is emited if the argument is equal to NVDIMM_BUS_FAMILY_NFIT == 0. Function acpi_nfit_ctl() first verifies that a user-provided value call_pkg->nd_family of type u64 is not equal to 0. Then the value is converted to int, and only after that is compared to NVDIMM_BUS_FAMILY_MAX. This can lead to passing an invalid argument to acpi_nfit_ctl(), if call_pkg->nd_family is non-zero, while the lower 32 bits are zero.

Furthermore, it is best to return EINVAL immediately upon seeing the invalid user input. The WARNING is insufficient to prevent further undefined behavior based on other invalid user input.

All checks of the input value should be applied to the original variable call_pkg->nd_family.

[iweiny: update commit message]

---
 drivers/acpi/nfit/core.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -485,7 +485,7 @@ int acpi_nfit_ctl(struct nvdimm_bus_desc
 		cmd_mask = nd_desc->cmd_mask;
 		if (cmd == ND_CMD_CALL && call_pkg->nd_family) {
 			family = call_pkg->nd_family;
-			if (family > NVDIMM_BUS_FAMILY_MAX ||
+			if (call_pkg->nd_family > NVDIMM_BUS_FAMILY_MAX ||
 			    !test_bit(family, &nd_desc->bus_family_mask))
 				return -EINVAL;
 			family = array_index_nospec(family,

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

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

From: Paul Menzel <[email protected]>

commit 2da31ea2a085cd189857f2db0f7b78d0162db87a upstream.

Like the ASUS Vivobook X1504VAP and Vivobook X1704VAP, the ASUS Vivobook 14 X1404VAP has its keyboard IRQ (1) described as ActiveLow in the DSDT, which the kernel overrides to EdgeHigh breaking the keyboard.

    $ sudo dmidecode
    […]
    System Information
            Manufacturer: ASUSTeK COMPUTER INC.
            Product Name: ASUS Vivobook 14 X1404VAP_X1404VA
    […]
    $ grep -A 30 PS2K dsdt.dsl | grep IRQ -A 1
                 IRQ (Level, ActiveLow, Exclusive, )
                     {1}

Add the X1404VAP to the irq1_level_low_skip_override[] quirk table to fix this.

---
 drivers/acpi/resource.c |    7 +++++++
 1 file changed, 7 insertions(+)

@@ -440,6 +440,13 @@ static const struct dmi_system_id asus_l
 		},
 	},
 	{
+		/* Asus Vivobook X1404VAP */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_BOARD_NAME, "X1404VAP"),
+		},
+	},
+	{
 		/* Asus Vivobook X1504VAP */
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),

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

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

From: Karel Balej <[email protected]>

commit a41fcca4b342811b473bbaa4b44f1d34d87fcce6 upstream.

Set the MMC_CAP_NEED_RSP_BUSY capability for the sdhci-pxav3 host to prevent conversion of R1B responses to R1. Without this, the eMMC card in the samsung,coreprimevelte smartphone using the Marvell PXA1908 SoC with this mmc host doesn't probe with the ETIMEDOUT error originating in __mmc_poll_for_busy.

Note that the other issues reported for this phone and host, namely floods of "Tuning failed, falling back to fixed sampling clock" dmesg messages for the eMMC and unstable SDIO are not mitigated by this change.

---
 drivers/mmc/host/sdhci-pxav3.c |    1 +
 1 file changed, 1 insertion(+)

@@ -401,6 +401,7 @@ static int sdhci_pxav3_probe(struct plat
 	if (!IS_ERR(pxa->clk_core))
 		clk_prepare_enable(pxa->clk_core);
 
+	host->mmc->caps |= MMC_CAP_NEED_RSP_BUSY;
 	/* enable 1/8V DDR capable */
 	host->mmc->caps |= MMC_CAP_1_8V_DDR;
 

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

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

From: Ulf Hansson <[email protected]>

commit 49d162635151d0dd04935070d7cf67137ab863aa upstream.

We have received reports about cards can become corrupt related to the aggressive PM support. Let's make a partial revert of the change that enabled the feature.

---
 drivers/mmc/host/sdhci-omap.c |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

@@ -1340,8 +1340,8 @@ static int sdhci_omap_probe(struct platf
 	/* R1B responses is required to properly manage HW busy detection. */
 	mmc->caps |= MMC_CAP_NEED_RSP_BUSY;
 
-	/* Allow card power off and runtime PM for eMMC/SD card devices */
-	mmc->caps |= MMC_CAP_POWER_OFF_CARD | MMC_CAP_AGGRESSIVE_PM;
+	/*  Enable SDIO card power off. */
+	mmc->caps |= MMC_CAP_POWER_OFF_CARD;
 
 	ret = sdhci_setup_host(host);
 	if (ret)

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

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

From: Norbert Szetei <[email protected]>

commit bab703ed8472aa9d109c5f8c1863921533363dae upstream.

Add missing bounds check for create lease context.

---
 fs/smb/server/oplock.c |    8 ++++++++
 1 file changed, 8 insertions(+)

@@ -1534,6 +1534,10 @@ struct lease_ctx_info *parse_lease_state
 	if (sizeof(struct lease_context_v2) == le32_to_cpu(cc->DataLength)) {
 		struct create_lease_v2 *lc = (struct create_lease_v2 *)cc;
 
+		if (le16_to_cpu(cc->DataOffset) + le32_to_cpu(cc->DataLength) <
+		    sizeof(struct create_lease_v2) - 4)
+			return NULL;
+
 		memcpy(lreq->lease_key, lc->lcontext.LeaseKey, SMB2_LEASE_KEY_SIZE);
 		if (is_dir) {
 			lreq->req_state = lc->lcontext.LeaseState &

@@ -1551,6 +1555,10 @@ struct lease_ctx_info *parse_lease_state
 	} else {
 		struct create_lease *lc = (struct create_lease *)cc;
 
+		if (le16_to_cpu(cc->DataOffset) + le32_to_cpu(cc->DataLength) <
+		    sizeof(struct create_lease))
+			return NULL;
+
 		memcpy(lreq->lease_key, lc->lcontext.LeaseKey, SMB2_LEASE_KEY_SIZE);
 		lreq->req_state = lc->lcontext.LeaseState;
 		lreq->flags = lc->lcontext.LeaseFlags;

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

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

From: Namjae Jeon <[email protected]>

commit 15a9605f8d69dc85005b1a00c31a050b8625e1aa upstream.

In multichannel mode, UAF issue can occur in session_deregister when the second channel sets up a session through the connection of the first channel. session that is freed through the global session table can be accessed again through ->sessions of connection.

---
 fs/smb/server/mgmt/user_session.c |    3 +++
 1 file changed, 3 insertions(+)

@@ -229,6 +229,9 @@ void ksmbd_sessions_deregister(struct ks
 			if (!ksmbd_chann_del(conn, sess) &&
 			    xa_empty(&sess->ksmbd_chann_list)) {
 				hash_del(&sess->hlist);
+				down_write(&conn->session_lock);
+				xa_erase(&conn->sessions, sess->id);
+				up_write(&conn->session_lock);
 				ksmbd_session_destroy(sess);
 			}
 		}

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

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

From: Namjae Jeon <[email protected]>

commit fa4cdb8cbca7d6cb6aa13e4d8d83d1103f6345db upstream.

There is a race condition between session setup and ksmbd_sessions_deregister. The session can be freed before the connection is added to channel list of session.
This patch check reference count of session before freeing it.

---
 fs/smb/server/auth.c              |    4 ++--
 fs/smb/server/mgmt/user_session.c |   14 ++++++++------
 fs/smb/server/smb2pdu.c           |    7 ++++---
 3 files changed, 14 insertions(+), 11 deletions(-)

@@ -1010,9 +1010,9 @@ static int ksmbd_get_encryption_key(stru
 
 	ses_enc_key = enc ? sess->smb3encryptionkey :
 		sess->smb3decryptionkey;
-	if (enc)
-		ksmbd_user_session_get(sess);
 	memcpy(key, ses_enc_key, SMB3_ENC_DEC_KEY_SIZE);
+	if (!enc)
+		ksmbd_user_session_put(sess);
 
 	return 0;
 }

@@ -180,7 +180,7 @@ static void ksmbd_expire_session(struct
 	down_write(&sessions_table_lock);
 	down_write(&conn->session_lock);
 	xa_for_each(&conn->sessions, id, sess) {
-		if (atomic_read(&sess->refcnt) == 0 &&
+		if (atomic_read(&sess->refcnt) <= 1 &&
 		    (sess->state != SMB2_SESSION_VALID ||
 		     time_after(jiffies,
 			       sess->last_active + SMB2_SESSION_TIMEOUT))) {

@@ -232,7 +232,8 @@ void ksmbd_sessions_deregister(struct ks
 				down_write(&conn->session_lock);
 				xa_erase(&conn->sessions, sess->id);
 				up_write(&conn->session_lock);
-				ksmbd_session_destroy(sess);
+				if (atomic_dec_and_test(&sess->refcnt))
+					ksmbd_session_destroy(sess);
 			}
 		}
 	}

@@ -251,7 +252,8 @@ void ksmbd_sessions_deregister(struct ks
 		if (xa_empty(&sess->ksmbd_chann_list)) {
 			xa_erase(&conn->sessions, sess->id);
 			hash_del(&sess->hlist);
-			ksmbd_session_destroy(sess);
+			if (atomic_dec_and_test(&sess->refcnt))
+				ksmbd_session_destroy(sess);
 		}
 	}
 	up_write(&conn->session_lock);

@@ -327,8 +329,8 @@ void ksmbd_user_session_put(struct ksmbd
 
 	if (atomic_read(&sess->refcnt) <= 0)
 		WARN_ON(1);
-	else
-		atomic_dec(&sess->refcnt);
+	else if (atomic_dec_and_test(&sess->refcnt))
+		ksmbd_session_destroy(sess);
 }
 
 struct preauth_session *ksmbd_preauth_session_alloc(struct ksmbd_conn *conn,

@@ -399,7 +401,7 @@ static struct ksmbd_session *__session_c
 	xa_init(&sess->rpc_handle_list);
 	sess->sequence_number = 1;
 	rwlock_init(&sess->tree_conns_lock);
-	atomic_set(&sess->refcnt, 1);
+	atomic_set(&sess->refcnt, 2);
 
 	ret = __init_smb2_session(sess);
 	if (ret)

@@ -2242,13 +2242,14 @@ int smb2_session_logoff(struct ksmbd_wor
 		return -ENOENT;
 	}
 
-	ksmbd_destroy_file_table(&sess->file_table);
 	down_write(&conn->session_lock);
 	sess->state = SMB2_SESSION_EXPIRED;
 	up_write(&conn->session_lock);
 
-	ksmbd_free_user(sess->user);
-	sess->user = NULL;
+	if (sess->user) {
+		ksmbd_free_user(sess->user);
+		sess->user = NULL;
+	}
 	ksmbd_all_conn_set_status(sess_id, KSMBD_SESS_NEED_NEGOTIATE);
 
 	rsp->StructureSize = cpu_to_le16(4);

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

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

From: Norbert Szetei <[email protected]>

commit bf21e29d78cd2c2371023953d9c82dfef82ebb36 upstream.

Access psid->sub_auth[psid->num_subauth - 1] without checking if num_subauth is non-zero leads to an out-of-bounds read. This patch adds a validation step to ensure num_subauth != 0 before sub_auth is accessed.

---
 fs/smb/server/smbacl.c |    5 +++++
 1 file changed, 5 insertions(+)

@@ -270,6 +270,11 @@ static int sid_to_id(struct user_namespa
 		return -EIO;
 	}
 
+	if (psid->num_subauth == 0) {
+		pr_err("%s: zero subauthorities!\n", __func__);
+		return -EIO;
+	}
+
 	if (sidtype == SIDOWNER) {
 		kuid_t uid;
 		uid_t id;

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

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

From: Tengda Wu <[email protected]>

commit 7f81f27b1093e4895e87b74143c59c055c3b1906 upstream.

Kairui reported a UAF issue in print_graph_function_flags() during ftrace stress testing [1]. This issue can be reproduced if puting a 'mdelay(10)' after 'mutex_unlock(&trace_types_lock)' in s_start(), and executing the following script:

  $ echo function_graph > current_tracer
  $ cat trace > /dev/null &
  $ sleep 5  # Ensure the 'cat' reaches the 'mdelay(10)' point
  $ echo timerlat > current_tracer

The root cause lies in the two calls to print_graph_function_flags within print_trace_line during each s_show():

* One through 'iter->trace->print_line()';
* Another through 'event->funcs->trace()', which is hidden in print_trace_fmt() before print_trace_line returns.

Tracer switching only updates the former, while the latter continues to use the print_line function of the old tracer, which in the script above is print_graph_function_flags.

Moreover, when switching from the 'function_graph' tracer to the 'timerlat' tracer, s_start only calls graph_trace_close of the 'function_graph' tracer to free 'iter->private', but does not set it to NULL. This provides an opportunity for 'event->funcs->trace()' to use an invalid 'iter->private'.

To fix this issue, set 'iter->private' to NULL immediately after freeing it in graph_trace_close(), ensuring that an invalid pointer is not passed to other tracers. Additionally, clean up the unnecessary 'iter->private = NULL' during each 'cat trace' when using wakeup and irqsoff tracers.

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

---
 kernel/trace/trace_functions_graph.c |    1 +
 kernel/trace/trace_irqsoff.c         |    2 --
 kernel/trace/trace_sched_wakeup.c    |    2 --
 3 files changed, 1 insertion(+), 4 deletions(-)

@@ -1244,6 +1244,7 @@ void graph_trace_close(struct trace_iter
 	if (data) {
 		free_percpu(data->cpu_data);
 		kfree(data);
+		iter->private = NULL;
 	}
 }
 

@@ -231,8 +231,6 @@ static void irqsoff_trace_open(struct tr
 {
 	if (is_graph(iter->tr))
 		graph_trace_open(iter);
-	else
-		iter->private = NULL;
 }
 
 static void irqsoff_trace_close(struct trace_iterator *iter)

@@ -168,8 +168,6 @@ static void wakeup_trace_open(struct tra
 {
 	if (is_graph(iter->tr))
 		graph_trace_open(iter);
-	else
-		iter->private = NULL;
 }
 
 static void wakeup_trace_close(struct trace_iterator *iter)

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

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

From: Douglas Raillard <[email protected]>

commit 21581dd4e7ff6c07d0ab577e3c32b13a74b31522 upstream.

Currently, using synth_event_delete() will fail if the event is being used (tracing in progress), but that is normally done in the module exit function. At that stage, failing is problematic as returning a non-zero status means the module will become locked (impossible to unload or reload again).

Instead, ensure the module exit function does not get called in the first place by increasing the module refcnt when the event is enabled.

---
 kernel/trace/trace_events_synth.c |   30 +++++++++++++++++++++++++++++-
 1 file changed, 29 insertions(+), 1 deletion(-)

@@ -875,6 +875,34 @@ static struct trace_event_fields synth_e
 	{}
 };
 
+static int synth_event_reg(struct trace_event_call *call,
+		    enum trace_reg type, void *data)
+{
+	struct synth_event *event = container_of(call, struct synth_event, call);
+
+	switch (type) {
+	case TRACE_REG_REGISTER:
+	case TRACE_REG_PERF_REGISTER:
+		if (!try_module_get(event->mod))
+			return -EBUSY;
+		break;
+	default:
+		break;
+	}
+
+	int ret = trace_event_reg(call, type, data);
+
+	switch (type) {
+	case TRACE_REG_UNREGISTER:
+	case TRACE_REG_PERF_UNREGISTER:
+		module_put(event->mod);
+		break;
+	default:
+		break;
+	}
+	return ret;
+}
+
 static int register_synth_event(struct synth_event *event)
 {
 	struct trace_event_call *call = &event->call;

@@ -904,7 +932,7 @@ static int register_synth_event(struct s
 		goto out;
 	}
 	call->flags = TRACE_EVENT_FL_TRACEPOINT;
-	call->class->reg = trace_event_reg;
+	call->class->reg = synth_event_reg;
 	call->class->probe = trace_event_raw_event_synth;
 	call->data = event;
 	call->tp = event->tp;

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

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

From: Douglas Raillard <[email protected]>

commit 4d38328eb442dc06aec4350fd9594ffa6488af02 upstream.

The printk format for synth event uses "%.*s" to print string fields, but then only passes the pointer part as var arg.

Replace %.*s with %s as the C string is guaranteed to be null-terminated.

The output in print fmt should never have been updated as __get_str() handles the string limit because it can access the length of the string in the string meta data that is saved in the ring buffer.

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

@@ -312,7 +312,7 @@ static const char *synth_field_fmt(char
 	else if (strcmp(type, "gfp_t") == 0)
 		fmt = "%x";
 	else if (synth_field_is_string(type))
-		fmt = "%.*s";
+		fmt = "%s";
 	else if (synth_field_is_stack(type))
 		fmt = "%s";
 

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

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

From: Ran Xiaokai <[email protected]>

commit 7e6b3fcc9c5294aeafed0dbe1a09a1bc899bd0f2 upstream.

Lockdep reports this deadlock log:

osnoise: could not start sampling thread
============================================
WARNING: possible recursive locking detected
--------------------------------------------

       CPU0
       ----

lock(cpu_hotplug_lock);
lock(cpu_hotplug_lock);

 Call Trace:
  <TASK>
  print_deadlock_bug+0x282/0x3c0
  __lock_acquire+0x1610/0x29a0
  lock_acquire+0xcb/0x2d0
  cpus_read_lock+0x49/0x120
  stop_per_cpu_kthreads+0x7/0x60
  start_kthread+0x103/0x120
  osnoise_hotplug_workfn+0x5e/0x90
  process_one_work+0x44f/0xb30
  worker_thread+0x33e/0x5e0
  kthread+0x206/0x3b0
  ret_from_fork+0x31/0x50
  ret_from_fork_asm+0x11/0x20
  </TASK>

This is the deadlock scenario:
osnoise_hotplug_workfn()
guard(cpus_read_lock)(); // first lock call
start_kthread(cpu)

    if (IS_ERR(kthread)) {
      stop_per_cpu_kthreads(); {
        cpus_read_lock();      // second lock call. Cause the AA deadlock
      }
    }

It is not necessary to call stop_per_cpu_kthreads() which stops osnoise kthread for every other CPUs in the system if a failure occurs during hotplug of a certain CPU.
For start_per_cpu_kthreads(), if the start_kthread() call fails, this function calls stop_per_cpu_kthreads() to handle the error. Therefore, similarly, there is no need to call stop_per_cpu_kthreads() again within start_kthread().
So just remove stop_per_cpu_kthreads() from start_kthread to solve this issue.

---
 kernel/trace/trace_osnoise.c |    1 -
 1 file changed, 1 deletion(-)

@@ -1756,7 +1756,6 @@ static int start_kthread(unsigned int cp
 
 	if (IS_ERR(kthread)) {
 		pr_err(BANNER "could not start sampling thread\n");
-		stop_per_cpu_kthreads();
 		return -ENOMEM;
 	}
 

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

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

From: Angelos Oikonomopoulos <[email protected]>

commit c28f31deeacda307acfee2f18c0ad904e5123aac upstream.

do_alignment_t32_to_handler() only fixes up alignment faults for specific instructions; it returns NULL otherwise (e.g. LDREX). When that's the case, signal to the caller that it needs to proceed with the regular alignment fault handling (i.e. SIGBUS). Without this patch, the kernel panics:

  Unable to handle kernel NULL pointer dereference at virtual address 0000000000000000
  Mem abort info:
    ESR = 0x0000000086000006
    EC = 0x21: IABT (current EL), IL = 32 bits
    SET = 0, FnV = 0
    EA = 0, S1PTW = 0
    FSC = 0x06: level 2 translation fault
  user pgtable: 4k pages, 48-bit VAs, pgdp=00000800164aa000
  [0000000000000000] pgd=0800081fdbd22003, p4d=0800081fdbd22003, pud=08000815d51c6003, pmd=0000000000000000
  Internal error: Oops: 0000000086000006 [#1] SMP
  Modules linked in: cfg80211 rfkill xt_nat xt_tcpudp xt_conntrack nft_chain_nat xt_MASQUERADE nf_nat nf_conntrack_netlink nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 xfrm_user xfrm_algo xt_addrtype nft_compat br_netfilter veth nvme_fa>
   libcrc32c crc32c_generic raid0 multipath linear dm_mod dax raid1 md_mod xhci_pci nvme xhci_hcd nvme_core t10_pi usbcore igb crc64_rocksoft crc64 crc_t10dif crct10dif_generic crct10dif_ce crct10dif_common usb_common i2c_algo_bit i2c>
  CPU: 2 PID: 3932954 Comm: WPEWebProcess Not tainted 6.1.0-31-arm64 #1  Debian 6.1.128-1
  Hardware name: GIGABYTE MP32-AR1-00/MP32-AR1-00, BIOS F18v (SCP: 1.08.20211002) 12/01/2021
  pstate: 80400009 (Nzcv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--)
  pc : 0x0
  lr : do_compat_alignment_fixup+0xd8/0x3dc
  sp : ffff80000f973dd0
  x29: ffff80000f973dd0 x28: ffff081b42526180 x27: 0000000000000000
  x26: 0000000000000000 x25: 0000000000000000 x24: 0000000000000000
  x23: 0000000000000004 x22: 0000000000000000 x21: 0000000000000001
  x20: 00000000e8551f00 x19: ffff80000f973eb0 x18: 0000000000000000
  x17: 0000000000000000 x16: 0000000000000000 x15: 0000000000000000
  x14: 0000000000000000 x13: 0000000000000000 x12: 0000000000000000
  x11: 0000000000000000 x10: 0000000000000000 x9 : ffffaebc949bc488
  x8 : 0000000000000000 x7 : 0000000000000000 x6 : 0000000000000000
  x5 : 0000000000400000 x4 : 0000fffffffffffe x3 : 0000000000000000
  x2 : ffff80000f973eb0 x1 : 00000000e8551f00 x0 : 0000000000000001
  Call trace:
   0x0
   do_alignment_fault+0x40/0x50
   do_mem_abort+0x4c/0xa0
   el0_da+0x48/0xf0
   el0t_32_sync_handler+0x110/0x140
   el0t_32_sync+0x190/0x194
  Code: bad PC value
  ---[ end trace 0000000000000000 ]---

---
 arch/arm64/kernel/compat_alignment.c | 2 ++
 1 file changed, 2 insertions(+)

index deff21bfa680..b68e1d328d4c 100644
@@ -368,6 +368,8 @@ int do_compat_alignment_fixup(unsigned long addr, struct pt_regs *regs)
 		return 1;
 	}
 
+	if (!handler)
+		return 1;
 	type = handler(addr, instr, regs);
 
 	if (type == TYPE_ERROR || type == TYPE_FAULT)

2.49.0

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

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

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

commit f87d3af7419307ae26e705a2b2db36140db367a2 upstream.

This fixes an analogus bug that was fixed in xfs in commit 4b8d867ca6e2 ("xfs: don't over-report free space or inodes in statvfs") where statfs can report misleading / incorrect information where project quota is enabled, and the free space is less than the remaining quota.

This commit will resolve a test failure in generic/762 which tests for this bug.

---
 fs/ext4/super.c |   27 +++++++++++++++++----------
 1 file changed, 17 insertions(+), 10 deletions(-)

@@ -6685,22 +6685,29 @@ static int ext4_statfs_project(struct su
 			     dquot->dq_dqb.dqb_bhardlimit);
 	limit >>= sb->s_blocksize_bits;
 
-	if (limit && buf->f_blocks > limit) {
+	if (limit) {
+		uint64_t	remaining = 0;
+
 		curblock = (dquot->dq_dqb.dqb_curspace +
 			    dquot->dq_dqb.dqb_rsvspace) >> sb->s_blocksize_bits;
-		buf->f_blocks = limit;
-		buf->f_bfree = buf->f_bavail =
-			(buf->f_blocks > curblock) ?
-			 (buf->f_blocks - curblock) : 0;
+		if (limit > curblock)
+			remaining = limit - curblock;
+
+		buf->f_blocks = min(buf->f_blocks, limit);
+		buf->f_bfree = min(buf->f_bfree, remaining);
+		buf->f_bavail = min(buf->f_bavail, remaining);
 	}
 
 	limit = min_not_zero(dquot->dq_dqb.dqb_isoftlimit,
 			     dquot->dq_dqb.dqb_ihardlimit);
-	if (limit && buf->f_files > limit) {
-		buf->f_files = limit;
-		buf->f_ffree =
-			(buf->f_files > dquot->dq_dqb.dqb_curinodes) ?
-			 (buf->f_files - dquot->dq_dqb.dqb_curinodes) : 0;
+	if (limit) {
+		uint64_t	remaining = 0;
+
+		if (limit > dquot->dq_dqb.dqb_curinodes)
+			remaining = limit - dquot->dq_dqb.dqb_curinodes;
+
+		buf->f_files = min(buf->f_files, limit);
+		buf->f_ffree = min(buf->f_ffree, remaining);
 	}
 
 	spin_unlock(&dquot->dq_dqb_lock);

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

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

From: Acs, Jakub <[email protected]>

commit d5e206778e96e8667d3bde695ad372c296dc9353 upstream.

Mounting a corrupted filesystem with directory which contains '.' dir entry with rec_len == block size results in out-of-bounds read (later on, when the corrupted directory is removed).

ext4_empty_dir() assumes every ext4 directory contains at least '.' and '..' as directory entries in the first data block. It first loads the '.' dir entry, performs sanity checks by calling ext4_check_dir_entry() and then uses its rec_len member to compute the location of '..' dir entry (in ext4_next_entry). It assumes the '..' dir entry fits into the same data block.

If the rec_len of '.' is precisely one block (4KB), it slips through the sanity checks (it is considered the last directory entry in the data block) and leaves "struct ext4_dir_entry_2 *de" point exactly past the memory slot allocated to the data block. The following call to ext4_check_dir_entry() on new value of de then dereferences this pointer which results in out-of-bounds mem access.

Fix this by extending __ext4_check_dir_entry() to check for '.' dir entries that reach the end of data block. Make sure to ignore the phony dir entries for checksum (by checking name_len for non-zero).

Note: This is reported by KASAN as use-after-free in case another structure was recently freed from the slot past the bound, but it is really an OOB read.

This issue was found by syzkaller tool.

Call Trace:
[   38.594108] BUG: KASAN: slab-use-after-free in __ext4_check_dir_entry+0x67e/0x710
[   38.594649] Read of size 2 at addr ffff88802b41a004 by task syz-executor/5375
[   38.595158]
[   38.595288] CPU: 0 UID: 0 PID: 5375 Comm: syz-executor Not tainted 6.14.0-rc7 #1
[   38.595298] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.3-0-ga6ed6b701f0a-prebuilt.qemu.org 04/01/2014
[   38.595304] Call Trace:
[   38.595308]  <TASK>
[   38.595311]  dump_stack_lvl+0xa7/0xd0
[   38.595325]  print_address_description.constprop.0+0x2c/0x3f0
[   38.595339]  ? __ext4_check_dir_entry+0x67e/0x710
[   38.595349]  print_report+0xaa/0x250
[   38.595359]  ? __ext4_check_dir_entry+0x67e/0x710
[   38.595368]  ? kasan_addr_to_slab+0x9/0x90
[   38.595378]  kasan_report+0xab/0xe0
[   38.595389]  ? __ext4_check_dir_entry+0x67e/0x710
[   38.595400]  __ext4_check_dir_entry+0x67e/0x710
[   38.595410]  ext4_empty_dir+0x465/0x990
[   38.595421]  ? __pfx_ext4_empty_dir+0x10/0x10
[   38.595432]  ext4_rmdir.part.0+0x29a/0xd10
[   38.595441]  ? __dquot_initialize+0x2a7/0xbf0
[   38.595455]  ? __pfx_ext4_rmdir.part.0+0x10/0x10
[   38.595464]  ? __pfx___dquot_initialize+0x10/0x10
[   38.595478]  ? down_write+0xdb/0x140
[   38.595487]  ? __pfx_down_write+0x10/0x10
[   38.595497]  ext4_rmdir+0xee/0x140
[   38.595506]  vfs_rmdir+0x209/0x670
[   38.595517]  ? lookup_one_qstr_excl+0x3b/0x190
[   38.595529]  do_rmdir+0x363/0x3c0
[   38.595537]  ? __pfx_do_rmdir+0x10/0x10
[   38.595544]  ? strncpy_from_user+0x1ff/0x2e0
[   38.595561]  __x64_sys_unlinkat+0xf0/0x130
[   38.595570]  do_syscall_64+0x5b/0x180
[   38.595583]  entry_SYSCALL_64_after_hwframe+0x76/0x7e

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

@@ -104,6 +104,9 @@ int __ext4_check_dir_entry(const char *f
 	else if (unlikely(le32_to_cpu(de->inode) >
 			le32_to_cpu(EXT4_SB(dir->i_sb)->s_es->s_inodes_count)))
 		error_msg = "inode out of bounds";
+	else if (unlikely(next_offset == size && de->name_len == 1 &&
+			  de->name[0] == '.'))
+		error_msg = "'.' directory cannot be the last in data block";
 	else
 		return 0;
 

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

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

From: Qasim Ijaz <[email protected]>

commit fdf480da5837c23b146c4743c18de97202fcab37 upstream.

During the "size_check" label in ea_get(), the code checks if the extended attribute list (xattr) size matches ea_size. If not, it logs "ea_get: invalid extended attribute" and calls print_hex_dump().

Here, EALIST_SIZE(ea_buf->xattr) returns 4110417968, which exceeds INT_MAX (2,147,483,647). Then ea_size is clamped:

	int size = clamp_t(int, ea_size, 0, EALIST_SIZE(ea_buf->xattr));

Although clamp_t aims to bound ea_size between 0 and 4110417968, the upper limit is treated as an int, causing an overflow above 2^31 - 1. This leads "size" to wrap around and become negative (-184549328).

The "size" is then passed to print_hex_dump() (called "len" in print_hex_dump()), it is passed as type size_t (an unsigned type), this is then stored inside a variable called "int remaining", which is then assigned to "int linelen" which is then passed to hex_dump_to_buffer(). In print_hex_dump() the for loop, iterates through 0 to len-1, where len is 18446744073525002176, calling hex_dump_to_buffer() on each iteration:

	for (i = 0; i < len; i += rowsize) {
		linelen = min(remaining, rowsize);
		remaining -= rowsize;

		hex_dump_to_buffer(ptr + i, linelen, rowsize, groupsize,
				   linebuf, sizeof(linebuf), ascii);

		...
	}

The expected stopping condition (i < len) is effectively broken since len is corrupted and very large. This eventually leads to the "ptr+i" being passed to hex_dump_to_buffer() to get closer to the end of the actual bounds of "ptr", eventually an out of bounds access is done in hex_dump_to_buffer() in the following for loop:

	for (j = 0; j < len; j++) {
			if (linebuflen < lx + 2)
				goto overflow2;
			ch = ptr[j];
		...
	}

To fix this we should validate "EALIST_SIZE(ea_buf->xattr)" before it is utilised.

---
 fs/jfs/xattr.c |   13 +++++++++----
 1 file changed, 9 insertions(+), 4 deletions(-)

@@ -559,11 +559,16 @@ static int ea_get(struct inode *inode, s
 
       size_check:
 	if (EALIST_SIZE(ea_buf->xattr) != ea_size) {
-		int size = clamp_t(int, ea_size, 0, EALIST_SIZE(ea_buf->xattr));
+		if (unlikely(EALIST_SIZE(ea_buf->xattr) > INT_MAX)) {
+			printk(KERN_ERR "ea_get: extended attribute size too large: %u > INT_MAX\n",
+			       EALIST_SIZE(ea_buf->xattr));
+		} else {
+			int size = clamp_t(int, ea_size, 0, EALIST_SIZE(ea_buf->xattr));
 
-		printk(KERN_ERR "ea_get: invalid extended attribute\n");
-		print_hex_dump(KERN_ERR, "", DUMP_PREFIX_ADDRESS, 16, 1,
-				     ea_buf->xattr, size, 1);
+			printk(KERN_ERR "ea_get: invalid extended attribute\n");
+			print_hex_dump(KERN_ERR, "", DUMP_PREFIX_ADDRESS, 16, 1,
+				       ea_buf->xattr, size, 1);
+		}
 		ea_release(inode, ea_buf);
 		rc = -EIO;
 		goto clean_up;

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

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

From: Roman Smirnov <[email protected]>

commit a8dfb2168906944ea61acfc87846b816eeab882d upstream.

If the file system is corrupted, the header.stblindex variable may become greater than 127. Because of this, an array access out of bounds may occur:

------------[ cut here ]------------
UBSAN: array-index-out-of-bounds in fs/jfs/jfs_dtree.c:3096:10
index 237 is out of range for type 'struct dtslot[128]'
CPU: 0 UID: 0 PID: 5822 Comm: syz-executor740 Not tainted 6.13.0-rc4-syzkaller-00110-g4099a71718b0 #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 09/13/2024
Call Trace:
 <TASK>
 __dump_stack lib/dump_stack.c:94 [inline]
 dump_stack_lvl+0x241/0x360 lib/dump_stack.c:120
 ubsan_epilogue lib/ubsan.c:231 [inline]
 __ubsan_handle_out_of_bounds+0x121/0x150 lib/ubsan.c:429
 dtReadFirst+0x622/0xc50 fs/jfs/jfs_dtree.c:3096
 dtReadNext fs/jfs/jfs_dtree.c:3147 [inline]
 jfs_readdir+0x9aa/0x3c50 fs/jfs/jfs_dtree.c:2862
 wrap_directory_iterator+0x91/0xd0 fs/readdir.c:65
 iterate_dir+0x571/0x800 fs/readdir.c:108
 __do_sys_getdents64 fs/readdir.c:403 [inline]
 __se_sys_getdents64+0x1e2/0x4b0 fs/readdir.c:389
 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
 </TASK>
---[ end trace ]---

Add a stblindex check for corruption.

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

@@ -117,7 +117,8 @@ do {									\
 	if (!(RC)) {							\
 		if (((P)->header.nextindex >				\
 		     (((BN) == 0) ? DTROOTMAXSLOT : (P)->header.maxslot)) || \
-		    ((BN) && ((P)->header.maxslot > DTPAGEMAXSLOT))) {	\
+		    ((BN) && (((P)->header.maxslot > DTPAGEMAXSLOT) ||	\
+		    ((P)->header.stblindex >= DTPAGEMAXSLOT)))) {	\
 			BT_PUTPAGE(MP);					\
 			jfs_error((IP)->i_sb,				\
 				  "DT_GETPAGE: dtree page corrupt\n");	\

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

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

From: Murad Masimov <[email protected]>

commit f656cfbc7a293a039d6a0c7100e1c846845148c1 upstream.

Syzkaller has reported a general protection fault at function ir_raw_event_store_with_filter(). This crash is caused by a NULL pointer dereference of dev->raw pointer, even though it is checked for NULL in the same function, which means there is a race condition. It occurs due to the incorrect order of actions in the streamzap_disconnect() function:
rc_unregister_device() is called before usb_kill_urb(). The dev->raw pointer is freed and set to NULL in rc_unregister_device(), and only after that usb_kill_urb() waits for in-progress requests to finish.

If rc_unregister_device() is called while streamzap_callback() handler is not finished, this can lead to accessing freed resources. Thus rc_unregister_device() should be called after usb_kill_urb().

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

---
 drivers/media/rc/streamzap.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -385,8 +385,8 @@ static void streamzap_disconnect(struct
 	if (!sz)
 		return;
 
-	rc_unregister_device(sz->rdev);
 	usb_kill_urb(sz->urb_in);
+	rc_unregister_device(sz->rdev);
 	usb_free_urb(sz->urb_in);
 	usb_free_coherent(usbdev, sz->buf_in_len, sz->buf_in, sz->dma_in);
 

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

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

From: Li Lingfeng <[email protected]>

commit 230ca758453c63bd38e4d9f4a21db698f7abada8 upstream.

Before calling nfsd4_run_cb to queue dl_recall to the callback_wq, we increment the reference count of dl_stid.
We expect that after the corresponding work_struct is processed, the reference count of dl_stid will be decremented through the callback function nfsd4_cb_recall_release.
However, if the call to nfsd4_run_cb fails, the incremented reference count of dl_stid will not be decremented correspondingly, leading to the following nfs4_stid leak:
unreferenced object 0xffff88812067b578 (size 344):
comm "nfsd", pid 2761, jiffies 4295044002 (age 5541.241s) hex dump (first 32 bytes):

    01 00 00 00 6b 6b 6b 6b b8 02 c0 e2 81 88 ff ff  ....kkkk........
    00 6b 6b 6b 6b 6b 6b 6b 00 00 00 00 ad 4e ad de  .kkkkkkk.....N..
  backtrace:
    kmem_cache_alloc+0x4b9/0x700
    nfsd4_process_open1+0x34/0x300
    nfsd4_open+0x2d1/0x9d0
    nfsd4_proc_compound+0x7a2/0xe30
    nfsd_dispatch+0x241/0x3e0
    svc_process_common+0x5d3/0xcc0
    svc_process+0x2a3/0x320
    nfsd+0x180/0x2e0
    kthread+0x199/0x1d0
    ret_from_fork+0x30/0x50
    ret_from_fork_asm+0x1b/0x30
unreferenced object 0xffff8881499f4d28 (size 368):
  comm "nfsd", pid 2761, jiffies 4295044005 (age 5541.239s)
  hex dump (first 32 bytes):
    01 00 00 00 00 00 00 00 30 4d 9f 49 81 88 ff ff  ........0M.I....
    30 4d 9f 49 81 88 ff ff 20 00 00 00 01 00 00 00  0M.I.... .......
  backtrace:
    kmem_cache_alloc+0x4b9/0x700
    nfs4_alloc_stid+0x29/0x210
    alloc_init_deleg+0x92/0x2e0
    nfs4_set_delegation+0x284/0xc00
    nfs4_open_delegation+0x216/0x3f0
    nfsd4_process_open2+0x2b3/0xee0
    nfsd4_open+0x770/0x9d0
    nfsd4_proc_compound+0x7a2/0xe30
    nfsd_dispatch+0x241/0x3e0
    svc_process_common+0x5d3/0xcc0
    svc_process+0x2a3/0x320
    nfsd+0x180/0x2e0
    kthread+0x199/0x1d0
    ret_from_fork+0x30/0x50
    ret_from_fork_asm+0x1b/0x30

Fix it by checking the result of nfsd4_run_cb and call nfs4_put_stid if fail to queue dl_recall.

---
 fs/nfsd/nfs4state.c |   12 +++++++++++-
 1 file changed, 11 insertions(+), 1 deletion(-)

@@ -1069,6 +1069,12 @@ static struct nfs4_ol_stateid * nfs4_all
 	return openlockstateid(stid);
 }
 
+/*
+ * As the sc_free callback of deleg, this may be called by nfs4_put_stid
+ * in nfsd_break_one_deleg.
+ * Considering nfsd_break_one_deleg is called with the flc->flc_lock held,
+ * this function mustn't ever sleep.
+ */
 static void nfs4_free_deleg(struct nfs4_stid *stid)
 {
 	struct nfs4_delegation *dp = delegstateid(stid);

@@ -4923,6 +4929,7 @@ static const struct nfsd4_callback_ops n
 
 static void nfsd_break_one_deleg(struct nfs4_delegation *dp)
 {
+	bool queued;
 	/*
 	 * We're assuming the state code never drops its reference
 	 * without first removing the lease.  Since we're in this lease

@@ -4931,7 +4938,10 @@ static void nfsd_break_one_deleg(struct
 	 * we know it's safe to take a reference.
 	 */
 	refcount_inc(&dp->dl_stid.sc_count);
-	WARN_ON_ONCE(!nfsd4_run_cb(&dp->dl_recall));
+	queued = nfsd4_run_cb(&dp->dl_recall);
+	WARN_ON_ONCE(!queued);
+	if (!queued)
+		nfs4_put_stid(&dp->dl_stid);
 }
 
 /* Called from break_lease() with flc_lock held. */

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

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

From: Chuck Lever <[email protected]>

commit 8a388c1fabeb6606e16467b23242416c0dbeffad upstream.

NFSD sends CB_RECALL_ANY to clients when the server is low on memory or that client has a large number of delegations outstanding.

We've seen cases where NFSD attempts to send CB_RECALL_ANY requests to disconnected clients, and gets confused. These calls never go anywhere if a backchannel transport to the target client isn't available. Before the server can send any backchannel operation, the client has to connect first and then do a BIND_CONN_TO_SESSION.

This patch doesn't address the root cause of the confusion, but there's no need to queue up these optional operations if they can't go anywhere.

---
 fs/nfsd/nfs4state.c |   19 ++++++++++++-------
 1 file changed, 12 insertions(+), 7 deletions(-)

@@ -6247,14 +6247,19 @@ deleg_reaper(struct nfsd_net *nn)
 	spin_lock(&nn->client_lock);
 	list_for_each_safe(pos, next, &nn->client_lru) {
 		clp = list_entry(pos, struct nfs4_client, cl_lru);
-		if (clp->cl_state != NFSD4_ACTIVE ||
-			list_empty(&clp->cl_delegations) ||
-			atomic_read(&clp->cl_delegs_in_recall) ||
-			test_bit(NFSD4_CLIENT_CB_RECALL_ANY, &clp->cl_flags) ||
-			(ktime_get_boottime_seconds() -
-				clp->cl_ra_time < 5)) {
+
+		if (clp->cl_state != NFSD4_ACTIVE)
+			continue;
+		if (list_empty(&clp->cl_delegations))
+			continue;
+		if (atomic_read(&clp->cl_delegs_in_recall))
+			continue;
+		if (test_bit(NFSD4_CLIENT_CB_RECALL_ANY, &clp->cl_flags))
+			continue;
+		if (ktime_get_boottime_seconds() - clp->cl_ra_time < 5)
+			continue;
+		if (clp->cl_cb_state != NFSD4_CB_UP)
 			continue;
-		}
 		list_add(&clp->cl_ra_cblist, &cblist);
 
 		/* release in nfsd4_cb_recall_any_release */

Hi!

CIP testing did not find any problems here:

https://gitlab.com/cip-project/cip-testing/linux-stable-rc-ci/-/tree/linux-6.1.y

Best regards,
Pavel

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

On ARCH_BRCMSTB using 32-bit and 64-bit ARM kernels, build tested on BMIPS_GENERIC:

Florian

Am 08.04.2025 um 12:48 schrieb Greg Kroah-Hartman:

Builds, boots and works on my 2-socket Ivy Bridge Xeon E5-2697 v2 server. No dmesg oddities or regressions found.

Beste Grüße,
Peter Schneider

Climb the mountain not to plant your flag, but to embrace the challenge,
enjoy the air and behold the view. Climb it so you can see the world,
not so the world can see you.                    -- David McCullough Jr.

OpenPGP:  0xA3828BD796CCE11A8CADE8866E3A92C92C3FF244
Download: https://www.peters-netzplatz.de/download/pschneider1968_pub.asc
https://keys.mailvelope.com/pks/lookup?op=get&[email protected]
https://keys.mailvelope.com/pks/lookup?op=get&[email protected]

Hello,

This rc kernel passes DAMON functionality test[1] on my test machine. Attaching the test results summary below. Please note that I retrieved the kernel from linux-stable-rc tree[2].

[1] https://github.com/damonitor/damon-tests/tree/next/corr
[2] 41c273b7c6e5 ("Linux 6.1.134-rc1")

Thanks,
SJ

[...]

---

ok 1 selftests: damon: debugfs_attrs.sh
ok 2 selftests: damon: debugfs_schemes.sh
ok 3 selftests: damon: debugfs_target_ids.sh
ok 4 selftests: damon: debugfs_empty_targets.sh
ok 5 selftests: damon: debugfs_huge_count_read_write.sh
ok 6 selftests: damon: debugfs_duplicate_context_creation.sh
ok 7 selftests: damon: sysfs.sh
ok 1 selftests: damon-tests: kunit.sh
ok 2 selftests: damon-tests: huge_count_read_write.sh
ok 3 selftests: damon-tests: buffer_overflow.sh
ok 4 selftests: damon-tests: rm_contexts.sh
ok 5 selftests: damon-tests: record_null_deref.sh
ok 6 selftests: damon-tests: dbgfs_target_ids_read_before_terminate_race.sh ok 7 selftests: damon-tests: dbgfs_target_ids_pid_leak.sh
ok 8 selftests: damon-tests: damo_tests.sh
ok 9 selftests: damon-tests: masim-record.sh
ok 10 selftests: damon-tests: build_i386.sh
ok 11 selftests: damon-tests: build_arm64.sh # SKIP
ok 12 selftests: damon-tests: build_m68k.sh # SKIP
ok 13 selftests: damon-tests: build_i386_idle_flag.sh
ok 14 selftests: damon-tests: build_i386_highpte.sh
ok 15 selftests: damon-tests: build_nomemcg.sh
[33m
[92mPASS [39m

Built and booted successfully on RISC-V RV64 (HiFive Unmatched).

All tests passing for Tegra ...

Test results for stable-v6.1:

    10 builds:	10 pass, 0 fail
    28 boots:	28 pass, 0 fail
    115 tests:	115 pass, 0 fail

Linux version: 6.1.134-rc1-g41c273b7c6e5
Boards tested: tegra124-jetson-tk1, tegra186-p2771-0000,

                tegra186-p3509-0000+p3636-0001, tegra194-p2972-0000,
                tegra194-p3509-0000+p3668-0000, tegra20-ventana,
                tegra210-p2371-2180, tegra210-p3450-0000,
                tegra30-cardhu-a04

Jon

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

## Build
* kernel: 6.1.134-rc1
* git: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git
* git commit: 41c273b7c6e5686866a063a29a03f95e3970fd7f
* git describe: v6.1.133-205-g41c273b7c6e5
* test details:
https://qa-reports.linaro.org/lkft/linux-stable-rc-linux-6.1.y/build/v6.1.133-205-g41c273b7c6e5

## Test Regressions (compared to v6.1.131-221-g819efe388d47)

## Metric Regressions (compared to v6.1.131-221-g819efe388d47)

## Test Fixes (compared to v6.1.131-221-g819efe388d47)

## Metric Fixes (compared to v6.1.131-221-g819efe388d47)

## Test result summary
total: 79336, pass: 60518, fail: 4593, skip: 13917, xfail: 308

## Build Summary
* arc: 5 total, 5 passed, 0 failed
* arm: 135 total, 133 passed, 2 failed
* arm64: 43 total, 42 passed, 1 failed
* i386: 27 total, 23 passed, 4 failed
* mips: 26 total, 25 passed, 1 failed
* parisc: 4 total, 4 passed, 0 failed
* powerpc: 32 total, 29 passed, 3 failed
* riscv: 11 total, 11 passed, 0 failed
* s390: 14 total, 12 passed, 2 failed
* sh: 10 total, 10 passed, 0 failed
* sparc: 7 total, 7 passed, 0 failed
* x86_64: 35 total, 34 passed, 1 failed

## Test suites summary
* boot
* commands
* kselftest-arm64
* kselftest-breakpoints
* kselftest-capabilities
* kselftest-cgroup
* kselftest-clone3
* kselftest-core
* kselftest-cpu-hotplug
* kselftest-cpufreq
* kselftest-efivarfs
* kselftest-exec
* kselftest-fpu
* kselftest-ftrace
* kselftest-futex
* kselftest-gpio
* kselftest-intel_pstate
* kselftest-ipc
* kselftest-kcmp
* kselftest-kvm
* kselftest-livepatch
* kselftest-membarrier
* kselftest-memfd
* kselftest-mincore
* kselftest-mqueue
* kselftest-net
* kselftest-net-mptcp
* kselftest-openat2
* kselftest-ptrace
* kselftest-rseq
* kselftest-rtc
* kselftest-seccomp
* kselftest-sigaltstack
* kselftest-size
* kselftest-tc-testing
* kselftest-timers
* kselftest-tmpfs
* kselftest-tpm2
* kselftest-user_events
* kselftest-vDSO
* kselftest-x86
* kunit
* kvm-unit-tests
* libgpiod
* libhugetlbfs
* log-parser-boot
* log-parser-build-clang
* log-parser-build-gcc
* log-parser-test
* ltp-capability
* ltp-commands
* ltp-containers
* ltp-controllers
* ltp-cpuhotplug
* ltp-crypto
* ltp-cve
* ltp-dio
* ltp-fcntl-locktests
* ltp-fs
* ltp-fs_bind
* ltp-fs_perms_simple
* ltp-hugetlb
* ltp-ipc
* ltp-math
* ltp-mm
* ltp-nptl
* ltp-pty
* ltp-sched
* ltp-smoke
* ltp-syscalls
* ltp-tracing
* perf
* rcutorture

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