6.12.23-rc1 review

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

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

From: Juhan Jin <[email protected]>

[ Upstream commit 5f1a58ed91a040d4625d854f9bb3dd4995919202 ]

This patch adds parentheses to parameters caller and callee of macros make_call_t0 and make_call_ra. Every existing invocation of these two macros uses a single variable for each argument, so the absence of the parentheses seems okay. However, future invocations might use more complex expressions as arguments. For example, a future invocation might look like this: make_call_t0(a - b, c, call). Without parentheses in the macro definition, the macro invocation expands to:

...
unsigned int offset = (unsigned long) c - (unsigned long) a - b;
...

which is clearly wrong.

The use of parentheses ensures arguments are correctly evaluated and potentially saves future users of make_call_t0 and make_call_ra debugging trouble.

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

index 2cddd79ff21b1..f253c8dae878e 100644
@@ -92,7 +92,7 @@ struct dyn_arch_ftrace {
 #define make_call_t0(caller, callee, call)				\
 do {									\
 	unsigned int offset =						\
-		(unsigned long) callee - (unsigned long) caller;	\
+		(unsigned long) (callee) - (unsigned long) (caller);	\
 	call[0] = to_auipc_t0(offset);					\
 	call[1] = to_jalr_t0(offset);					\
 } while (0)

@@ -108,7 +108,7 @@ do {									\
 #define make_call_ra(caller, callee, call)				\
 do {									\
 	unsigned int offset =						\
-		(unsigned long) callee - (unsigned long) caller;	\
+		(unsigned long) (callee) - (unsigned long) (caller);	\
 	call[0] = to_auipc_ra(offset);					\
 	call[1] = to_jalr_ra(offset);					\
 } while (0)

2.39.5

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

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

From: Yajun Deng <[email protected]>

[ Upstream commit de203da734fae00e75be50220ba5391e7beecdf9 ]

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

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

Ensuring xlate_pos is a positive or zero before BIT.

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

index ad1786be2554b..f851397b65d6e 100644
@@ -288,7 +288,7 @@ static int switchtec_ntb_mw_set_trans(struct ntb_dev *ntb, int pidx, int widx,
 	if (size != 0 && xlate_pos < 12)
 		return -EINVAL;
 
-	if (!IS_ALIGNED(addr, BIT_ULL(xlate_pos))) {
+	if (xlate_pos >= 0 && !IS_ALIGNED(addr, BIT_ULL(xlate_pos))) {
 		/*
 		 * In certain circumstances we can get a buffer that is
 		 * not aligned to its size. (Most of the time

2.39.5

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

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

From: Nikita Shubin <[email protected]>

[ Upstream commit 8144e9c8f30fb23bb736a5d24d5c9d46965563c4 ]

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

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

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

2.39.5

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

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

From: Richard Fitzgerald <[email protected]>

[ Upstream commit 2593f7e0dc93a898a84220b3fb180d86f1ca8c60 ]

Set ret = 0 on successful completion of the processing loop in cs_dsp_load() and cs_dsp_load_coeff() to ensure that the function returns 0 on success.

All normal firmware files will have at least one data block, and processing this block will set ret == 0, from the result of either regmap_raw_write() or cs_dsp_parse_coeff().

The kunit tests create a dummy firmware file that contains only the header, without any data blocks. This gives cs_dsp a file to "load" that will not cause any side-effects. As there aren't any data blocks, the processing loop will not set ret == 0.

Originally there was a line after the processing loop:

    ret = regmap_async_complete(regmap);

which would set ret == 0 before the function returned.

Commit fe08b7d5085a ("firmware: cs_dsp: Remove async regmap writes") changed the regmap write to a normal sync write, so the call to regmap_async_complete() wasn't necessary and was removed. It was overlooked that the ret here wasn't only to check the result of regmap_async_complete(), it also set the final return value of the function.

---
 drivers/firmware/cirrus/cs_dsp.c | 2 ++
 1 file changed, 2 insertions(+)

index bd1ea99c3b475..ea452f1908542 100644
@@ -1631,6 +1631,7 @@ static int cs_dsp_load(struct cs_dsp *dsp, const struct firmware *firmware,
 
 	cs_dsp_debugfs_save_wmfwname(dsp, file);
 
+	ret = 0;
 out_fw:
 	cs_dsp_buf_free(&buf_list);
 

@@ -2338,6 +2339,7 @@ static int cs_dsp_load_coeff(struct cs_dsp *dsp, const struct firmware *firmware
 
 	cs_dsp_debugfs_save_binname(dsp, file);
 
+	ret = 0;
 out_fw:
 	cs_dsp_buf_free(&buf_list);
 

2.39.5

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

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

From: Takashi Iwai <[email protected]>

[ Upstream commit 84c3c08f5a6c2e2209428b76156bcaf349c3a62d ]

ASUS VivoBook X515JA with PCI SSID 1043:14f2 also hits the same issue as other VivoBook model about the mic pin assignment, and the same workaround is required to apply ALC256_FIXUP_ASUS_MIC_NO_PRESENCE quirk.

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

index 23dd0bf7f6657..1e2059035d5b1 100644
@@ -10676,6 +10676,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1043, 0x1493, "ASUS GV601VV/VU/VJ/VQ/VI", ALC285_FIXUP_ASUS_HEADSET_MIC),
 	SND_PCI_QUIRK(0x1043, 0x14d3, "ASUS G614JY/JZ/JG", ALC245_FIXUP_CS35L41_SPI_2),
 	SND_PCI_QUIRK(0x1043, 0x14e3, "ASUS G513PI/PU/PV", ALC287_FIXUP_CS35L41_I2C_2),
+	SND_PCI_QUIRK(0x1043, 0x14f2, "ASUS VivoBook X515JA", ALC256_FIXUP_ASUS_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1043, 0x1503, "ASUS G733PY/PZ/PZV/PYV", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x1043, 0x1517, "Asus Zenbook UX31A", ALC269VB_FIXUP_ASUS_ZENBOOK_UX31A),
 	SND_PCI_QUIRK(0x1043, 0x1533, "ASUS GV302XA/XJ/XQ/XU/XV/XI", ALC287_FIXUP_CS35L41_I2C_2),

2.39.5

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

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

From: Palmer Dabbelt <[email protected]>

[ Upstream commit bb58e1579f431d42469b6aed0f03eff383ba6db5 ]

We're trying to mix non-PIC/PIE objects into the otherwise-PIE relocatable kernels, to avoid GOT/PLT references during early boot alternative resolution (which happens before the GOT/PLT are set up).

riscv64-unknown-linux-gnu-ld: arch/riscv/errata/sifive/errata.o: relocation R_RISCV_HI20 against tlb_flush_all_threshold' can not be used when making a shared object; recompile with -fPIC riscv64-unknown-linux-gnu-ld: arch/riscv/errata/thead/errata.o: relocation R_RISCV_HI20 against riscv_cbom_block_size' can not be used when making a shared object; recompile with -fPIC

---
 arch/riscv/errata/Makefile | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

index f0da9d7b39c37..bc6c77ba837d2 100644
@@ -1,5 +1,9 @@
 ifdef CONFIG_RELOCATABLE
-KBUILD_CFLAGS += -fno-pie
+# We can't use PIC/PIE when handling early-boot errata parsing, as the kernel
+# doesn't have a GOT setup at that point.  So instead just use medany: it's
+# usually position-independent, so it should be good enough for the errata
+# handling.
+KBUILD_CFLAGS += -fno-pie -mcmodel=medany
 endif
 
 ifdef CONFIG_RISCV_ALTERNATIVE_EARLY

2.39.5

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

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

From: Herton R. Krzesinski <[email protected]>

[ Upstream commit b5322b6ec06a6c58650f52abcd2492000396363b ]

History of the performance regression:
======================================

Since the following series of user copy updates were merged upstream ~2 years ago via:

a5624566431d ("Merge branch 'x86-rep-insns': x86 user copy clarifications")

.. copy_user_generic() on x86_64 stopped doing alignment of the writes to the destination to a 8 byte boundary for the non FSRM case.

Previously, this was done through the ALIGN_DESTINATION macro that was used in the now removed copy_user_generic_unrolled function.

Turns out this change causes some loss of performance/throughput on some use cases and specific CPU/platforms without FSRM and ERMS.

Lately I got two reports of performance/throughput issues after a RHEL 9 kernel pulled the same upstream series with updates to user copy functions. Both reports consisted of running specific networking/TCP related testing using iperf3.

Partial upstream fix
====================

The first report was related to a Linux Bridge testing using VMs on a specific machine with an AMD CPU (EPYC 7402), and after a brief investigation it turned out that the later change via:

ca96b162bfd2 ("x86: bring back rep movsq for user access on CPUs without ERMS")

... helped/fixed the performance issue.

However, after the later commit/fix was applied, then I got another regression reported in a multistream TCP test on a 100Gbit mlx5 nic, also running on an AMD based platform (AMD EPYC 7302 CPU), again that was using iperf3 to run the test. That regression was after applying the later fix/commit, but only this didn't help in telling the whole history.

Testing performed to pinpoint residual regression
=================================================

So I narrowed down the second regression use case, but running it without traffic through a NIC, on localhost, in trying to narrow down CPU usage and not being limited by other factor like network bandwidth. I used another system also with an AMD CPU (AMD EPYC 7742). Basically, I run iperf3 in server and client mode in the same system, for example:

- Start the server binding it to CPU core/thread 19:

   $ taskset -c 19 iperf3 -D -s -B 127.0.0.1 -p 12000

- Start the client always binding/running on CPU core/thread 17, using perf to get statistics:

   $ perf stat -o stat.txt taskset -c 17 iperf3 -c 127.0.0.1 -b 0/1000 -V \
       -n 50G --repeating-payload -l 16384 -p 12000 --cport 12001 2>&1 \
       > stat-19.txt

For the client, always running/pinned to CPU 17. But for the iperf3 in server mode, I did test runs using CPUs 19, 21, 23 or not pinned to any specific CPU. So it basically consisted with four runs of the same commands, just changing the CPU which the server is pinned, or without pinning by removing the taskset call before the server command. The CPUs were chosen based on NUMA node they were on, this is the relevant output of lscpu on the system:

  $ lscpu
  ...
    Model name:             AMD EPYC 7742 64-Core Processor
  ...
  Caches (sum of all):
    L1d:                    2 MiB (64 instances)
    L1i:                    2 MiB (64 instances)
    L2:                     32 MiB (64 instances)
    L3:                     256 MiB (16 instances)
  NUMA:
    NUMA node(s):           4
    NUMA node0 CPU(s):      0,1,8,9,16,17,24,25,32,33,40,41,48,49,56,57,64,65,72,73,80,81,88,89,96,97,104,105,112,113,120,121
    NUMA node1 CPU(s):      2,3,10,11,18,19,26,27,34,35,42,43,50,51,58,59,66,67,74,75,82,83,90,91,98,99,106,107,114,115,122,123
    NUMA node2 CPU(s):      4,5,12,13,20,21,28,29,36,37,44,45,52,53,60,61,68,69,76,77,84,85,92,93,100,101,108,109,116,117,124,125
    NUMA node3 CPU(s):      6,7,14,15,22,23,30,31,38,39,46,47,54,55,62,63,70,71,78,79,86,87,94,95,102,103,110,111,118,119,126,127
  ...

So for the server run, when picking a CPU, I chose CPUs to be not on the same node. The reason is with that I was able to get/measure relevant performance differences when changing the alignment of the writes to the destination in copy_user_generic.

Testing shows up to +81% performance improvement under iperf3
=============================================================

Here's a summary of the iperf3 runs:

# Vanilla upstream alignment:

		     CPU      RATE          SYS          TIME     sender-receiver
	Server bind   19: 13.0Gbits/sec 28.371851000 33.233499566 86.9%-70.8%
	Server bind   21: 12.9Gbits/sec 28.283381000 33.586486621 85.8%-69.9%
	Server bind   23: 11.1Gbits/sec 33.660190000 39.012243176 87.7%-64.5%
	Server bind none: 18.9Gbits/sec 19.215339000 22.875117865 86.0%-80.5%

# With the attached patch (aligning writes in non ERMS/FSRM case):

		     CPU      RATE          SYS          TIME     sender-receiver
	Server bind   19: 20.8Gbits/sec 14.897284000 20.811101382 75.7%-89.0%
	Server bind   21: 20.4Gbits/sec 15.205055000 21.263165909 75.4%-89.7%
	Server bind   23: 20.2Gbits/sec 15.433801000 21.456175000 75.5%-89.8%
	Server bind none: 26.1Gbits/sec 12.534022000 16.632447315 79.8%-89.6%

So I consistently got better results when aligning the write. The results above were run on 6.14.0-rc6/rc7 based kernels. The sys is sys time and then the total time to run/transfer 50G of data. The last field is the CPU usage of sender/receiver iperf3 process. It's also worth to note that each pair of iperf3 runs may get slightly different results on each run, but I always got consistent higher results with the write alignment for this specific test of running the processes on CPUs in different NUMA nodes.

Linus Torvalds helped/provided this version of the patch. Initially I proposed a version which aligned writes for all cases in rep_movs_alternative, however it used two extra registers and thus Linus provided an enhanced version that only aligns the write on the large_movsq case, which is sufficient since the problem happens only on those AMD CPUs like ones mentioned above without ERMS/FSRM, and also doesn't require using extra registers. Also, I validated that aligning only on large_movsq case is really enough for getting the performance back.

I also tested this patch on an old Intel based non-ERMS/FRMS system (with Xeon E5-2667 - Sandy Bridge based) and didn't get any problems:
no performance enhancement but also no regression either, using the same iperf3 based benchmark. Also newer Intel processors after Sandy Bridge usually have ERMS and should not be affected by this change.

[ mingo: Updated the changelog. ]

---
 arch/x86/lib/copy_user_64.S | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)

index fc9fb5d061744..b8f74d80f35c6 100644
@@ -74,6 +74,24 @@ SYM_FUNC_START(rep_movs_alternative)
 	_ASM_EXTABLE_UA( 0b, 1b)
 
 .Llarge_movsq:
+	/* Do the first possibly unaligned word */
+0:	movq (%rsi),%rax
+1:	movq %rax,(%rdi)
+
+	_ASM_EXTABLE_UA( 0b, .Lcopy_user_tail)
+	_ASM_EXTABLE_UA( 1b, .Lcopy_user_tail)
+
+	/* What would be the offset to the aligned destination? */
+	leaq 8(%rdi),%rax
+	andq $-8,%rax
+	subq %rdi,%rax
+
+	/* .. and update pointers and count to match */
+	addq %rax,%rdi
+	addq %rax,%rsi
+	subq %rax,%rcx
+
+	/* make %rcx contain the number of words, %rax the remainder */
 	movq %rcx,%rax
 	shrq $3,%rcx
 	andl $7,%eax

2.39.5

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

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

From: Ming Lei <[email protected]>

[ Upstream commit 8741d0737921ec1c03cf59aebf4d01400c2b461a ]

Now ublk driver depends on ubq->canceling for deciding if the request can be dispatched via uring_cmd & io_uring_cmd_complete_in_task().

Once ubq->canceling is set, the uring_cmd can be done via ublk_cancel_cmd() and io_uring_cmd_done().

So set ubq->canceling when queue is frozen, this way makes sure that the flag can be observed from ublk_queue_rq() reliably, and avoids use-after-free on uring_cmd.

---
 drivers/block/ublk_drv.c | 39 +++++++++++++++++++++++++++++----------
 1 file changed, 29 insertions(+), 10 deletions(-)

index c7d728d686e5a..79b7bd8bfd458 100644
@@ -1416,17 +1416,27 @@ static void ublk_abort_queue(struct ublk_device *ub, struct ublk_queue *ubq)
 	}
 }
 
+/* Must be called when queue is frozen */
+static bool ublk_mark_queue_canceling(struct ublk_queue *ubq)
+{
+	bool canceled;
+
+	spin_lock(&ubq->cancel_lock);
+	canceled = ubq->canceling;
+	if (!canceled)
+		ubq->canceling = true;
+	spin_unlock(&ubq->cancel_lock);
+
+	return canceled;
+}
+
 static bool ublk_abort_requests(struct ublk_device *ub, struct ublk_queue *ubq)
 {
+	bool was_canceled = ubq->canceling;
 	struct gendisk *disk;
 
-	spin_lock(&ubq->cancel_lock);
-	if (ubq->canceling) {
-		spin_unlock(&ubq->cancel_lock);
+	if (was_canceled)
 		return false;
-	}
-	ubq->canceling = true;
-	spin_unlock(&ubq->cancel_lock);
 
 	spin_lock(&ub->lock);
 	disk = ub->ub_disk;

@@ -1438,14 +1448,23 @@ static bool ublk_abort_requests(struct ublk_device *ub, struct ublk_queue *ubq)
 	if (!disk)
 		return false;
 
-	/* Now we are serialized with ublk_queue_rq() */
+	/*
+	 * Now we are serialized with ublk_queue_rq()
+	 *
+	 * Make sure that ubq->canceling is set when queue is frozen,
+	 * because ublk_queue_rq() has to rely on this flag for avoiding to
+	 * touch completed uring_cmd
+	 */
 	blk_mq_quiesce_queue(disk->queue);
-	/* abort queue is for making forward progress */
-	ublk_abort_queue(ub, ubq);
+	was_canceled = ublk_mark_queue_canceling(ubq);
+	if (!was_canceled) {
+		/* abort queue is for making forward progress */
+		ublk_abort_queue(ub, ubq);
+	}
 	blk_mq_unquiesce_queue(disk->queue);
 	put_device(disk_to_dev(disk));
 
-	return true;
+	return !was_canceled;
 }
 
 static void ublk_cancel_cmd(struct ublk_queue *ubq, struct ublk_io *io,

2.39.5

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

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

From: Sven Schnelle <[email protected]>

[ Upstream commit 121df45b37a1016ee6828c2ca3ba825f3e18a8c1 ]

When lowcore relocation is enabled, the machine check handler doesn't use the lowcore address when setting _CIF_MCCK_GUEST. Fix this by adding the missing base register.

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

index 594da4cba707a..a7de838f80318 100644
@@ -501,7 +501,7 @@ SYM_CODE_START(mcck_int_handler)
 	clgrjl	%r9,%r14, 4f
 	larl	%r14,.Lsie_leave
 	clgrjhe	%r9,%r14, 4f
-	lg	%r10,__LC_PCPU
+	lg	%r10,__LC_PCPU(%r13)
 	oi	__PCPU_FLAGS+7(%r10), _CIF_MCCK_GUEST
 4:	BPENTER	__SF_SIE_FLAGS(%r15),_TIF_ISOLATE_BP_GUEST
 	SIEEXIT __SF_SIE_CONTROL(%r15),%r13

2.39.5

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

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

From: Christophe JAILLET <[email protected]>

[ Upstream commit 1ebd4944266e86a7ce274f197847f5a6399651e8 ]

Should an error occur after a successful regulator_bulk_enable() call, regulator_bulk_disable() should be called, as already done in the remove function.

Instead of adding an error handling path in the probe, switch from devm_regulator_bulk_get() to devm_regulator_bulk_get_enable() and simplify the remove function and some other places accordingly.

Finally, add a missing const when defining rt5665_supply_names to please checkpatch and constify a few bytes.

---
 sound/soc/codecs/rt5665.c | 24 ++++--------------------
 1 file changed, 4 insertions(+), 20 deletions(-)

index 47df14ba52784..4f0236b34a2d9 100644
@@ -31,9 +31,7 @@
 #include "rl6231.h"
 #include "rt5665.h"
 
-#define RT5665_NUM_SUPPLIES 3
-
-static const char *rt5665_supply_names[RT5665_NUM_SUPPLIES] = {
+static const char * const rt5665_supply_names[] = {
 	"AVDD",
 	"MICVDD",
 	"VBAT",

@@ -46,7 +44,6 @@ struct rt5665_priv {
 	struct gpio_desc *gpiod_ldo1_en;
 	struct gpio_desc *gpiod_reset;
 	struct snd_soc_jack *hs_jack;
-	struct regulator_bulk_data supplies[RT5665_NUM_SUPPLIES];
 	struct delayed_work jack_detect_work;
 	struct delayed_work calibrate_work;
 	struct delayed_work jd_check_work;

@@ -4471,8 +4468,6 @@ static void rt5665_remove(struct snd_soc_component *component)
 	struct rt5665_priv *rt5665 = snd_soc_component_get_drvdata(component);
 
 	regmap_write(rt5665->regmap, RT5665_RESET, 0);
-
-	regulator_bulk_disable(ARRAY_SIZE(rt5665->supplies), rt5665->supplies);
 }
 
 #ifdef CONFIG_PM

@@ -4758,7 +4753,7 @@ static int rt5665_i2c_probe(struct i2c_client *i2c)
 {
 	struct rt5665_platform_data *pdata = dev_get_platdata(&i2c->dev);
 	struct rt5665_priv *rt5665;
-	int i, ret;
+	int ret;
 	unsigned int val;
 
 	rt5665 = devm_kzalloc(&i2c->dev, sizeof(struct rt5665_priv),

@@ -4774,24 +4769,13 @@ static int rt5665_i2c_probe(struct i2c_client *i2c)
 	else
 		rt5665_parse_dt(rt5665, &i2c->dev);
 
-	for (i = 0; i < ARRAY_SIZE(rt5665->supplies); i++)
-		rt5665->supplies[i].supply = rt5665_supply_names[i];
-
-	ret = devm_regulator_bulk_get(&i2c->dev, ARRAY_SIZE(rt5665->supplies),
-				      rt5665->supplies);
+	ret = devm_regulator_bulk_get_enable(&i2c->dev, ARRAY_SIZE(rt5665_supply_names),
+					     rt5665_supply_names);
 	if (ret != 0) {
 		dev_err(&i2c->dev, "Failed to request supplies: %d\n", ret);
 		return ret;
 	}
 
-	ret = regulator_bulk_enable(ARRAY_SIZE(rt5665->supplies),
-				    rt5665->supplies);
-	if (ret != 0) {
-		dev_err(&i2c->dev, "Failed to enable supplies: %d\n", ret);
-		return ret;
-	}
-
-
 	rt5665->gpiod_ldo1_en = devm_gpiod_get_optional(&i2c->dev,
 							"realtek,ldo1-en",
 							GPIOD_OUT_HIGH);

2.39.5

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

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

From: Josh Poimboeuf <[email protected]>

[ Upstream commit 7ba0847fa1c22e7801cebfe5f7b75aee4fae317e ]

If requested_clk > 128, cdns_mrvl_xspi_setup_clock() iterates over the entire cdns_mrvl_xspi_clk_div_list array without breaking out early, causing 'i' to go beyond the array bounds.

Fix that by stopping the loop when it gets to the last entry, clamping the clock to the minimum 6.25 MHz.

Fixes the following warning with an UBSAN kernel:

vmlinux.o: warning: objtool: cdns_mrvl_xspi_setup_clock: unexpected end of section .text.cdns_mrvl_xspi_setup_clock

---
 drivers/spi/spi-cadence-xspi.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index aed98ab143346..6dcba0e0ddaa3 100644
@@ -432,7 +432,7 @@ static bool cdns_mrvl_xspi_setup_clock(struct cdns_xspi_dev *cdns_xspi,
 	u32 clk_reg;
 	bool update_clk = false;
 
-	while (i < ARRAY_SIZE(cdns_mrvl_xspi_clk_div_list)) {
+	while (i < (ARRAY_SIZE(cdns_mrvl_xspi_clk_div_list) - 1)) {
 		clk_val = MRVL_XSPI_CLOCK_DIVIDED(
 				cdns_mrvl_xspi_clk_div_list[i]);
 		if (clk_val <= requested_clk)

2.39.5

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

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

From: Alexandre Ghiti <[email protected]>

[ Upstream commit 83d78ac677b9fdd8ea763507c6fe02d6bf415f3a ]

Ryan sent a fix [1] for arm64 that applies to riscv too: in some hugetlb functions, we must not use the pte value to get the size of a mapping because the pte may not be present.

So use the already present size parameter for huge_pte_clear() and the newly introduced size parameter for huge_ptep_get_and_clear(). And make sure to gather A/D bits only on present ptes.

---
 arch/riscv/mm/hugetlbpage.c | 76 ++++++++++++++++++++++---------------
 1 file changed, 45 insertions(+), 31 deletions(-)

index b4a78a4b35cff..375dd96bb4a0d 100644
@@ -148,22 +148,25 @@ unsigned long hugetlb_mask_last_page(struct hstate *h)
 static pte_t get_clear_contig(struct mm_struct *mm,
 			      unsigned long addr,
 			      pte_t *ptep,
-			      unsigned long pte_num)
+			      unsigned long ncontig)
 {
-	pte_t orig_pte = ptep_get(ptep);
-	unsigned long i;
-
-	for (i = 0; i < pte_num; i++, addr += PAGE_SIZE, ptep++) {
-		pte_t pte = ptep_get_and_clear(mm, addr, ptep);
-
-		if (pte_dirty(pte))
-			orig_pte = pte_mkdirty(orig_pte);
-
-		if (pte_young(pte))
-			orig_pte = pte_mkyoung(orig_pte);
+	pte_t pte, tmp_pte;
+	bool present;
+
+	pte = ptep_get_and_clear(mm, addr, ptep);
+	present = pte_present(pte);
+	while (--ncontig) {
+		ptep++;
+		addr += PAGE_SIZE;
+		tmp_pte = ptep_get_and_clear(mm, addr, ptep);
+		if (present) {
+			if (pte_dirty(tmp_pte))
+				pte = pte_mkdirty(pte);
+			if (pte_young(tmp_pte))
+				pte = pte_mkyoung(pte);
+		}
 	}
-
-	return orig_pte;
+	return pte;
 }
 
 static pte_t get_clear_contig_flush(struct mm_struct *mm,

@@ -212,6 +215,26 @@ static void clear_flush(struct mm_struct *mm,
 	flush_tlb_range(&vma, saddr, addr);
 }
 
+static int num_contig_ptes_from_size(unsigned long sz, size_t *pgsize)
+{
+	unsigned long hugepage_shift;
+
+	if (sz >= PGDIR_SIZE)
+		hugepage_shift = PGDIR_SHIFT;
+	else if (sz >= P4D_SIZE)
+		hugepage_shift = P4D_SHIFT;
+	else if (sz >= PUD_SIZE)
+		hugepage_shift = PUD_SHIFT;
+	else if (sz >= PMD_SIZE)
+		hugepage_shift = PMD_SHIFT;
+	else
+		hugepage_shift = PAGE_SHIFT;
+
+	*pgsize = 1 << hugepage_shift;
+
+	return sz >> hugepage_shift;
+}
+
 /*
  * When dealing with NAPOT mappings, the privileged specification indicates that
  * "if an update needs to be made, the OS generally should first mark all of the

@@ -226,22 +249,10 @@ void set_huge_pte_at(struct mm_struct *mm,
 		     pte_t pte,
 		     unsigned long sz)
 {
-	unsigned long hugepage_shift, pgsize;
+	size_t pgsize;
 	int i, pte_num;
 
-	if (sz >= PGDIR_SIZE)
-		hugepage_shift = PGDIR_SHIFT;
-	else if (sz >= P4D_SIZE)
-		hugepage_shift = P4D_SHIFT;
-	else if (sz >= PUD_SIZE)
-		hugepage_shift = PUD_SHIFT;
-	else if (sz >= PMD_SIZE)
-		hugepage_shift = PMD_SHIFT;
-	else
-		hugepage_shift = PAGE_SHIFT;
-
-	pte_num = sz >> hugepage_shift;
-	pgsize = 1 << hugepage_shift;
+	pte_num = num_contig_ptes_from_size(sz, &pgsize);
 
 	if (!pte_present(pte)) {
 		for (i = 0; i < pte_num; i++, ptep++, addr += pgsize)

@@ -295,13 +306,14 @@ pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
 			      unsigned long addr,
 			      pte_t *ptep, unsigned long sz)
 {
+	size_t pgsize;
 	pte_t orig_pte = ptep_get(ptep);
 	int pte_num;
 
 	if (!pte_napot(orig_pte))
 		return ptep_get_and_clear(mm, addr, ptep);
 
-	pte_num = napot_pte_num(napot_cont_order(orig_pte));
+	pte_num = num_contig_ptes_from_size(sz, &pgsize);
 
 	return get_clear_contig(mm, addr, ptep, pte_num);
 }

@@ -351,6 +363,7 @@ void huge_pte_clear(struct mm_struct *mm,
 		    pte_t *ptep,
 		    unsigned long sz)
 {
+	size_t pgsize;
 	pte_t pte = ptep_get(ptep);
 	int i, pte_num;
 

@@ -359,8 +372,9 @@ void huge_pte_clear(struct mm_struct *mm,
 		return;
 	}
 
-	pte_num = napot_pte_num(napot_cont_order(pte));
-	for (i = 0; i < pte_num; i++, addr += PAGE_SIZE, ptep++)
+	pte_num = num_contig_ptes_from_size(sz, &pgsize);
+
+	for (i = 0; i < pte_num; i++, addr += pgsize, ptep++)
 		pte_clear(mm, addr, ptep);
 }
 

2.39.5

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

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

From: Yao Zi <[email protected]>

[ Upstream commit 28093cfef5dd62f4cbd537f2bdf6f0bf85309c45 ]

Commit 58ff537109ac ("riscv: Omit optimized string routines when using KASAN") introduced calls to EXPORT_SYMBOL() in assembly string routines, which result in R_RISCV_64 relocations against .export_symbol section. As these rountines are reused by RISC-V purgatory and our relocator doesn't recognize these relocations, this fails kexec-file-load with dmesg like

	[   11.344251] kexec_image: Unknown rela relocation: 2
	[   11.345972] kexec_image: Error loading purgatory ret=-8

Let's support R_RISCV_64 relocation to fix kexec on 64-bit RISC-V. 32-bit variant isn't covered since KEXEC_FILE and KEXEC_PURGATORY isn't available.

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

index 3c37661801f95..e783a72d051f4 100644
@@ -468,6 +468,9 @@ int arch_kexec_apply_relocations_add(struct purgatory_info *pi,
 		case R_RISCV_ALIGN:
 		case R_RISCV_RELAX:
 			break;
+		case R_RISCV_64:
+			*(u64 *)loc = val;
+			break;
 		default:
 			pr_err("Unknown rela relocation: %d\n", r_type);
 			return -ENOEXEC;

2.39.5

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

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

From: Björn Töpel <[email protected]>

[ Upstream commit 3f7023171df43641a8a8a1c9a12124501e589010 ]

When a crashkernel is launched on RISC-V, the entry to purgatory is done by trapping via the stvec CSR. From riscv_kexec_norelocate():

  |  ...
  |  /*
  |   * Switch to physical addressing
  |   * This will also trigger a jump to CSR_STVEC
  |   * which in this case is the address of the new
  |   * kernel.
  |   */
  |  csrw    CSR_STVEC, a2
  |  csrw    CSR_SATP, zero

stvec requires that the address is 4B aligned, which was not the case, e.g.:

| Loaded purgatory at 0xffffc000
| kexec_file: kexec_file_load: type:1, start:0xffffd232 head:0x4 flags:0x6

The address 0xffffd232 not 4B aligned.

Correct by adding proper function alignment.

With this change, crashkernels loaded with kexec-file will be able to properly enter the purgatory.

---
 arch/riscv/purgatory/entry.S | 1 +
 1 file changed, 1 insertion(+)

index 0e6ca6d5ae4b4..c5db2f072c341 100644
@@ -12,6 +12,7 @@
 
 .text
 
+.align	2
 SYM_CODE_START(purgatory_start)
 
 	lla	sp, .Lstack

2.39.5

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

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

From: Caleb Sander Mateos <[email protected]>

[ Upstream commit eada75467fca0b016b9b22212637c07216135c20 ]

The vectorized io_uring NVMe passthru opcodes don't yet support fixed buffers. But since userspace can trigger this condition based on the io_uring SQE parameters, it shouldn't cause a kernel warning.

---
 drivers/nvme/host/ioctl.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index e4daac9c24401..a1b3c538a4bd2 100644
@@ -141,7 +141,7 @@ static int nvme_map_user_request(struct request *req, u64 ubuffer,
 		struct iov_iter iter;
 
 		/* fixedbufs is only for non-vectored io */
-		if (WARN_ON_ONCE(flags & NVME_IOCTL_VEC)) {
+		if (flags & NVME_IOCTL_VEC) {
 			ret = -EINVAL;
 			goto out;
 		}

2.39.5

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

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

From: Henry Martin <[email protected]>

[ Upstream commit 93d34608fd162f725172e780b1c60cc93a920719 ]

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

Add NULL check after devm_kasprintf() to prevent this issue.

---
 sound/soc/fsl/imx-card.c | 4 ++++
 1 file changed, 4 insertions(+)

index a7215bad64845..93dbe40008c00 100644
@@ -738,6 +738,8 @@ static int imx_card_probe(struct platform_device *pdev)
 				data->dapm_routes[i].sink =
 					devm_kasprintf(&pdev->dev, GFP_KERNEL, "%d %s",
 						       i + 1, "Playback");
+				if (!data->dapm_routes[i].sink)
+					return -ENOMEM;
 				data->dapm_routes[i].source = "CPU-Playback";
 			}
 		}

@@ -755,6 +757,8 @@ static int imx_card_probe(struct platform_device *pdev)
 				data->dapm_routes[i].source =
 					devm_kasprintf(&pdev->dev, GFP_KERNEL, "%d %s",
 						       i + 1, "Capture");
+				if (!data->dapm_routes[i].source)
+					return -ENOMEM;
 				data->dapm_routes[i].sink = "CPU-Capture";
 			}
 		}

2.39.5

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

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

From: Florian Fainelli <[email protected]>

[ Upstream commit d6691010523fe1016f482a1e1defcc6289eeea48 ]

If we are unable to lookup the chip-select GPIO, the error path will call bcm2835_spi_cleanup() which unconditionally calls gpiod_put() on the cs->gpio variable which we just determined was invalid.

---
 drivers/spi/spi-bcm2835.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

index e1b9b12357877..a5d621b94d5e3 100644
@@ -1162,7 +1162,8 @@ static void bcm2835_spi_cleanup(struct spi_device *spi)
 				 sizeof(u32),
 				 DMA_TO_DEVICE);
 
-	gpiod_put(bs->cs_gpio);
+	if (!IS_ERR(bs->cs_gpio))
+		gpiod_put(bs->cs_gpio);
 	spi_set_csgpiod(spi, 0, NULL);
 
 	kfree(target);

2.39.5

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

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

From: Takashi Iwai <[email protected]>

[ Upstream commit 8983dc1b66c0e1928a263b8af0bb06f6cb9229c4 ]

There is another VivoBook model which built-in mic got broken recently by the fix of the pin sort. Apply the correct quirk ALC256_FIXUP_ASUS_MIC_NO_PRESENCE to this model for addressing the regression, too.

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

index 1e2059035d5b1..59e59fdc38f2c 100644
@@ -10716,6 +10716,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1043, 0x1c43, "ASUS UX8406MA", ALC245_FIXUP_CS35L41_SPI_2),
 	SND_PCI_QUIRK(0x1043, 0x1c62, "ASUS GU603", ALC289_FIXUP_ASUS_GA401),
 	SND_PCI_QUIRK(0x1043, 0x1c63, "ASUS GU605M", ALC285_FIXUP_ASUS_GU605_SPI_SPEAKER2_TO_DAC1),
+	SND_PCI_QUIRK(0x1043, 0x1c80, "ASUS VivoBook TP401", ALC256_FIXUP_ASUS_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1043, 0x1c92, "ASUS ROG Strix G15", ALC285_FIXUP_ASUS_G533Z_PINS),
 	SND_PCI_QUIRK(0x1043, 0x1c9f, "ASUS G614JU/JV/JI", ALC285_FIXUP_ASUS_HEADSET_MIC),
 	SND_PCI_QUIRK(0x1043, 0x1caf, "ASUS G634JY/JZ/JI/JG", ALC285_FIXUP_ASUS_SPI_REAR_SPEAKERS),

2.39.5

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

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

From: Florian Fainelli <[email protected]>

[ Upstream commit e19c1272c80a5ecce387c1b0c3b995f4edf9c525 ]

The lookup table forces the use of the "pinctrl-bcm2835" GPIO chip provider and essentially assumes that there is going to be such a provider, and if not, we will fail to set-up the SPI device.

While this is true on Raspberry Pi based systems (2835/36/37, 2711, 2712), this is not true on 7712/77122 Broadcom STB systems which use the SPI driver, but not the GPIO driver.

There used to be an early check:

       chip = gpiochip_find("pinctrl-bcm2835", chip_match_name);
       if (!chip)
               return 0;

which would accomplish that nicely, bring something similar back by checking for the compatible strings matched by the pinctrl-bcm2835.c driver, if there is no Device Tree node matching those compatible strings, then we won't find any GPIO provider registered by the "pinctrl-bcm2835" driver.

---
 drivers/spi/spi-bcm2835.c | 15 ++++++++++++++-
 1 file changed, 14 insertions(+), 1 deletion(-)

index a5d621b94d5e3..5926e004d9a65 100644
@@ -1226,7 +1226,12 @@ static int bcm2835_spi_setup(struct spi_device *spi)
 	struct bcm2835_spi *bs = spi_controller_get_devdata(ctlr);
 	struct bcm2835_spidev *target = spi_get_ctldata(spi);
 	struct gpiod_lookup_table *lookup __free(kfree) = NULL;
-	int ret;
+	const char *pinctrl_compats[] = {
+		"brcm,bcm2835-gpio",
+		"brcm,bcm2711-gpio",
+		"brcm,bcm7211-gpio",
+	};
+	int ret, i;
 	u32 cs;
 
 	if (!target) {

@@ -1291,6 +1296,14 @@ static int bcm2835_spi_setup(struct spi_device *spi)
 		goto err_cleanup;
 	}
 
+	for (i = 0; i < ARRAY_SIZE(pinctrl_compats); i++) {
+		if (of_find_compatible_node(NULL, NULL, pinctrl_compats[i]))
+			break;
+	}
+
+	if (i == ARRAY_SIZE(pinctrl_compats))
+		return 0;
+
 	/*
 	 * TODO: The code below is a slightly better alternative to the utter
 	 * abuse of the GPIO API that I found here before. It creates a

2.39.5

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

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

From: Vitaly Lifshits <[email protected]>

[ Upstream commit efaaf344bc2917cbfa5997633bc18a05d3aed27f ]

Starting from Meteor Lake, the Kumeran interface between the integrated MAC and the I219 PHY works at a different frequency. This causes sporadic MDI errors when accessing the PHY, and in rare circumstances could lead to packet corruption.

To overcome this, introduce minor changes to the Kumeran idle state (K1) parameters during device initialization. Hardware reset reverts this configuration, therefore it needs to be applied in a few places.

---
 drivers/net/ethernet/intel/e1000e/defines.h |  3 +
 drivers/net/ethernet/intel/e1000e/ich8lan.c | 80 +++++++++++++++++++--
 drivers/net/ethernet/intel/e1000e/ich8lan.h |  4 ++
 3 files changed, 82 insertions(+), 5 deletions(-)

index 5e2cfa73f8891..8294a7c4f122c 100644
@@ -803,4 +803,7 @@
 /* SerDes Control */
 #define E1000_GEN_POLL_TIMEOUT          640
 
+#define E1000_FEXTNVM12_PHYPD_CTRL_MASK	0x00C00000
+#define E1000_FEXTNVM12_PHYPD_CTRL_P1	0x00800000
+
 #endif /* _E1000_DEFINES_H_ */

index 2504b11c3169f..5feb589a9b5ff 100644
@@ -219,6 +219,10 @@
 #define I217_PLL_CLOCK_GATE_REG	PHY_REG(772, 28)
 #define I217_PLL_CLOCK_GATE_MASK	0x07FF
 
+/* PHY Timeouts */
+#define I217_PHY_TIMEOUTS_REG                   PHY_REG(770, 21)
+#define I217_PHY_TIMEOUTS_K1_EXIT_TO_MASK       0x0FC0
+
 #define SW_FLAG_TIMEOUT		1000	/* SW Semaphore flag timeout in ms */
 
 /* Inband Control */

2.39.5

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

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

From: Emil Tantilov <[email protected]>

[ Upstream commit 4c9106f4906a85f6b13542d862e423bcdc118cc3 ]

With SRIOV enabled, idpf ends up calling into idpf_remove() twice. First via idpf_shutdown() and then again when idpf_remove() calls into sriov_disable(), because the VF devices use the idpf driver, hence the same remove routine. When that happens, it is possible for the adapter to be NULL from the first call to idpf_remove(), leading to a NULL pointer dereference.

echo 1 > /sys/class/net/<netif>/device/sriov_numvfs reboot

BUG: kernel NULL pointer dereference, address: 0000000000000020
...
RIP: 0010:idpf_remove+0x22/0x1f0 [idpf]
...
? idpf_remove+0x22/0x1f0 [idpf]
? idpf_remove+0x1e4/0x1f0 [idpf]
pci_device_remove+0x3f/0xb0
device_release_driver_internal+0x19f/0x200
pci_stop_bus_device+0x6d/0x90
pci_stop_and_remove_bus_device+0x12/0x20
pci_iov_remove_virtfn+0xbe/0x120
sriov_disable+0x34/0xe0
idpf_sriov_configure+0x58/0x140 [idpf]
idpf_remove+0x1b9/0x1f0 [idpf]
idpf_shutdown+0x12/0x30 [idpf]
pci_device_shutdown+0x35/0x60
device_shutdown+0x156/0x200

...

Replace the direct idpf_remove() call in idpf_shutdown() with idpf_vc_core_deinit() and idpf_deinit_dflt_mbx(), which perform the bulk of the cleanup, such as stopping the init task, freeing IRQs, destroying the vports and freeing the mailbox. This avoids the calls to sriov_disable() in addition to a small netdev cleanup, and destroying workqueues, which don't seem to be required on shutdown.

---
 drivers/net/ethernet/intel/idpf/idpf_main.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

index dfd56fc5ff655..7557bb6694c09 100644
@@ -87,7 +87,11 @@ static void idpf_remove(struct pci_dev *pdev)
  */
 static void idpf_shutdown(struct pci_dev *pdev)
 {
-	idpf_remove(pdev);
+	struct idpf_adapter *adapter = pci_get_drvdata(pdev);
+
+	cancel_delayed_work_sync(&adapter->vc_event_task);
+	idpf_vc_core_deinit(adapter);
+	idpf_deinit_dflt_mbx(adapter);
 
 	if (system_state == SYSTEM_POWER_OFF)
 		pci_set_power_state(pdev, PCI_D3hot);

2.39.5

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

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

From: Pablo Neira Ayuso <[email protected]>

[ Upstream commit 9d74da1177c800eb3d51c13f9821b7b0683845a5 ]

conncount has its own GC handler which determines when to reap stale elements, this is convenient for dynamic sets. However, this also reaps non-dynamic sets with static configurations coming from control plane. Always run connlimit gc handler but honor feedback to reap element if this set is dynamic.

---
 net/netfilter/nft_set_hash.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

index b93f046ac7d1e..4b3452dff2ec0 100644
@@ -309,7 +309,8 @@ static bool nft_rhash_expr_needs_gc_run(const struct nft_set *set,
 
 	nft_setelem_expr_foreach(expr, elem_expr, size) {
 		if (expr->ops->gc &&
-		    expr->ops->gc(read_pnet(&set->net), expr))
+		    expr->ops->gc(read_pnet(&set->net), expr) &&
+		    set->flags & NFT_SET_EVAL)
 			return true;
 	}
 

2.39.5

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

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

From: Florian Westphal <[email protected]>

[ Upstream commit 688c15017d5cd5aac882400782e7213d40dc3556 ]

When nf_tables_updchain encounters an error, hook registration needs to be rolled back.

This should only be done if the hook has been registered, which won't happen when the table is flagged as dormant (inactive).

Just move the assignment into the registration block.

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

index eb3a6f96b094d..bdee187bc5dd4 100644
@@ -2732,11 +2732,11 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy,
 			err = nft_netdev_register_hooks(ctx->net, &hook.list);
 			if (err < 0)
 				goto err_hooks;
+
+			unregister = true;
 		}
 	}
 
-	unregister = true;
-
 	if (nla[NFTA_CHAIN_COUNTERS]) {
 		if (!nft_is_base_chain(chain)) {
 			err = -EOPNOTSUPP;

2.39.5

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

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

From: Debin Zhu <[email protected]>

[ Upstream commit 078aabd567de3d63d37d7673f714e309d369e6e2 ]

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

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

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

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

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

index dbcea9fee6262..62618a058b8fa 100644
@@ -1072,8 +1072,13 @@ static int calipso_sock_getattr(struct sock *sk,
 	struct ipv6_opt_hdr *hop;
 	int opt_len, len, ret_val = -ENOMSG, offset;
 	unsigned char *opt;
-	struct ipv6_txoptions *txopts = txopt_get(inet6_sk(sk));
+	struct ipv6_pinfo *pinfo = inet6_sk(sk);
+	struct ipv6_txoptions *txopts;
+
+	if (!pinfo)
+		return -EAFNOSUPPORT;
 
+	txopts = txopt_get(pinfo);
 	if (!txopts || !txopts->hopopt)
 		goto done;
 

@@ -1125,8 +1130,13 @@ static int calipso_sock_setattr(struct sock *sk,
 {
 	int ret_val;
 	struct ipv6_opt_hdr *old, *new;
-	struct ipv6_txoptions *txopts = txopt_get(inet6_sk(sk));
+	struct ipv6_pinfo *pinfo = inet6_sk(sk);
+	struct ipv6_txoptions *txopts;
+
+	if (!pinfo)
+		return -EAFNOSUPPORT;
 
+	txopts = txopt_get(pinfo);
 	old = NULL;
 	if (txopts)
 		old = txopts->hopopt;

@@ -1153,8 +1163,13 @@ static int calipso_sock_setattr(struct sock *sk,
 static void calipso_sock_delattr(struct sock *sk)
 {
 	struct ipv6_opt_hdr *new_hop;
-	struct ipv6_txoptions *txopts = txopt_get(inet6_sk(sk));
+	struct ipv6_pinfo *pinfo = inet6_sk(sk);
+	struct ipv6_txoptions *txopts;
+
+	if (!pinfo)
+		return;
 
+	txopts = txopt_get(pinfo);
 	if (!txopts || !txopts->hopopt)
 		goto done;
 

2.39.5

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

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

From: Cong Wang <[email protected]>

[ Upstream commit ce8fe975fd99b49c29c42e50f2441ba53112b2e8 ]

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

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

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

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

index 20ff7386b74bd..f485f62ab721a 100644
@@ -123,8 +123,6 @@ static int skbprio_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 	/* Check to update highest and lowest priorities. */
 	if (skb_queue_empty(lp_qdisc)) {
 		if (q->lowest_prio == q->highest_prio) {
-			/* The incoming packet is the only packet in queue. */
-			BUG_ON(sch->q.qlen != 1);
 			q->lowest_prio = prio;
 			q->highest_prio = prio;
 		} else {

@@ -156,7 +154,6 @@ static struct sk_buff *skbprio_dequeue(struct Qdisc *sch)
 	/* Update highest priority field. */
 	if (skb_queue_empty(hpq)) {
 		if (q->lowest_prio == q->highest_prio) {
-			BUG_ON(sch->q.qlen);
 			q->highest_prio = 0;
 			q->lowest_prio = SKBPRIO_MAX_PRIORITY - 1;
 		} else {

2.39.5

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

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

From: Eric Dumazet <[email protected]>

[ Upstream commit 10206302af856791fbcc27a33ed3c3eb09b2793d ]

We must serialize calls to sctp_udp_sock_stop() and sctp_udp_sock_start() or risk a crash as syzbot reported:

Oops: general protection fault, probably for non-canonical address 0xdffffc000000000d: 0000 [#1] SMP KASAN PTI
KASAN: null-ptr-deref in range [0x0000000000000068-0x000000000000006f]
CPU: 1 UID: 0 PID: 6551 Comm: syz.1.44 Not tainted 6.14.0-syzkaller-g7f2ff7b62617 #0 PREEMPT(full)
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 02/12/2025
 RIP: 0010:kernel_sock_shutdown+0x47/0x70 net/socket.c:3653
Call Trace:
 <TASK>
  udp_tunnel_sock_release+0x68/0x80 net/ipv4/udp_tunnel_core.c:181
  sctp_udp_sock_stop+0x71/0x160 net/sctp/protocol.c:930
  proc_sctp_do_udp_port+0x264/0x450 net/sctp/sysctl.c:553
  proc_sys_call_handler+0x3d0/0x5b0 fs/proc/proc_sysctl.c:601
  iter_file_splice_write+0x91c/0x1150 fs/splice.c:738
  do_splice_from fs/splice.c:935 [inline]
  direct_splice_actor+0x18f/0x6c0 fs/splice.c:1158
  splice_direct_to_actor+0x342/0xa30 fs/splice.c:1102
  do_splice_direct_actor fs/splice.c:1201 [inline]
  do_splice_direct+0x174/0x240 fs/splice.c:1227
  do_sendfile+0xafd/0xe50 fs/read_write.c:1368
  __do_sys_sendfile64 fs/read_write.c:1429 [inline]
  __se_sys_sendfile64 fs/read_write.c:1415 [inline]
  __x64_sys_sendfile64+0x1d8/0x220 fs/read_write.c:1415
  do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline]

---
 net/sctp/sysctl.c | 4 ++++
 1 file changed, 4 insertions(+)

index 8e1e97be4df79..ee3eac338a9de 100644
@@ -525,6 +525,8 @@ static int proc_sctp_do_auth(const struct ctl_table *ctl, int write,
 	return ret;
 }
 
+static DEFINE_MUTEX(sctp_sysctl_mutex);
+
 static int proc_sctp_do_udp_port(const struct ctl_table *ctl, int write,
 				 void *buffer, size_t *lenp, loff_t *ppos)
 {

@@ -549,6 +551,7 @@ static int proc_sctp_do_udp_port(const struct ctl_table *ctl, int write,
 		if (new_value > max || new_value < min)
 			return -EINVAL;
 
+		mutex_lock(&sctp_sysctl_mutex);
 		net->sctp.udp_port = new_value;
 		sctp_udp_sock_stop(net);
 		if (new_value) {

@@ -561,6 +564,7 @@ static int proc_sctp_do_udp_port(const struct ctl_table *ctl, int write,
 		lock_sock(sk);
 		sctp_sk(sk)->udp_port = htons(net->sctp.udp_port);
 		release_sock(sk);
+		mutex_unlock(&sctp_sysctl_mutex);
 	}
 
 	return ret;

2.39.5

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

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

From: Tobias Waldekranz <[email protected]>

[ Upstream commit 96844075226b49af25a69a1d084b648ec2d9b08d ]

Protect the parser TCAM/SRAM memory, and the cached (shadow) SRAM information, from concurrent modifications.

Both the TCAM and SRAM tables are indirectly accessed by configuring an index register that selects the row to read or write to. This means that operations must be atomic in order to, e.g., avoid spreading writes across multiple rows. Since the shadow SRAM array is used to find free rows in the hardware table, it must also be protected in order to avoid TOCTOU errors where multiple cores allocate the same row.

This issue was detected in a situation where mvpp2_set_rx_mode() ran concurrently on two CPUs. In this particular case the MVPP2_PE_MAC_UC_PROMISCUOUS entry was corrupted, causing the classifier unit to drop all incoming unicast - indicated by the rx_classifier_drops counter.

---
 drivers/net/ethernet/marvell/mvpp2/mvpp2.h    |   3 +
 .../net/ethernet/marvell/mvpp2/mvpp2_main.c   |   3 +-
 .../net/ethernet/marvell/mvpp2/mvpp2_prs.c    | 201 ++++++++++++------
 3 files changed, 140 insertions(+), 67 deletions(-)

index 9e02e4367bec8..9bd3d76b5fe2a 100644
@@ -1108,6 +1108,9 @@ struct mvpp2 {
 
 	/* Spinlocks for CM3 shared memory configuration */
 	spinlock_t mss_spinlock;
+
+	/* Spinlock for shared PRS parser memory and shadow table */
+	spinlock_t prs_spinlock;
 };
 
 struct mvpp2_pcpu_stats {

index 3880dcc0418b2..66b5a80c9c28a 100644
@@ -7640,8 +7640,9 @@ static int mvpp2_probe(struct platform_device *pdev)
 	if (mvpp2_read(priv, MVPP2_VER_ID_REG) == MVPP2_VER_PP23)
 		priv->hw_version = MVPP23;
 
-	/* Init mss lock */
+	/* Init locks for shared packet processor resources */
 	spin_lock_init(&priv->mss_spinlock);
+	spin_lock_init(&priv->prs_spinlock);
 
 	/* Initialize network controller */
 	err = mvpp2_init(pdev, priv);

2.39.5

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

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

From: Kuniyuki Iwashima <[email protected]>

[ Upstream commit 5a465a0da13ee9fbd7d3cd0b2893309b0fe4b7e3 ]

__udp_enqueue_schedule_skb() has the following condition:

if (atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf)

          goto drop;

sk->sk_rcvbuf is initialised by net.core.rmem_default and later can be configured by SO_RCVBUF, which is limited by net.core.rmem_max, or SO_RCVBUFFORCE.

If we set INT_MAX to sk->sk_rcvbuf, the condition is always false as sk->sk_rmem_alloc is also signed int.

Then, the size of the incoming skb is added to sk->sk_rmem_alloc unconditionally.

This results in integer overflow (possibly multiple times) on sk->sk_rmem_alloc and allows a single socket to have skb up to net.core.udp_mem[1].

For example, if we set a large value to udp_mem[1] and INT_MAX to sk->sk_rcvbuf and flood packets to the socket, we can see multiple overflows:

  # cat /proc/net/sockstat | grep UDP:
  UDP: inuse 3 mem 7956736  <-- (7956736 << 12) bytes > INT_MAX * 15
                                             ^- PAGE_SHIFT
  # ss -uam
  State  Recv-Q      ...
  UNCONN -1757018048 ...    <-- flipping the sign repeatedly
         skmem:(r2537949248,rb2147483646,t0,tb212992,f1984,w0,o0,bl0,d0)

Previously, we had a boundary check for INT_MAX, which was removed by commit 6a1f12dd85a8 ("udp: relax atomic operation on sk->sk_rmem_alloc").

A complete fix would be to revert it and cap the right operand by INT_MAX:

  rmem = atomic_add_return(size, &sk->sk_rmem_alloc);
  if (rmem > min(size + (unsigned int)sk->sk_rcvbuf, INT_MAX))
          goto uncharge_drop;

but we do not want to add the expensive atomic_add_return() back just for the corner case.

Casting rmem to unsigned int prevents multiple wraparounds, but we still allow a single wraparound.

  # cat /proc/net/sockstat | grep UDP:
  UDP: inuse 3 mem 524288  <-- (INT_MAX + 1) >> 12

  # ss -uam
  State  Recv-Q      ...
  UNCONN -2147482816 ...   <-- INT_MAX + 831 bytes
         skmem:(r2147484480,rb2147483646,t0,tb212992,f3264,w0,o0,bl0,d14468947)

So, let's define rmem and rcvbuf as unsigned int and check skb->truesize only when rcvbuf is large enough to lower the overflow possibility.

Note that we still have a small chance to see overflow if multiple skbs to the same socket are processed on different core at the same time and each size does not exceed the limit but the total size does.

Note also that we must ignore skb->truesize for a small buffer as explained in commit 363dc73acacb ("udp: be less conservative with sock rmem accounting").

---
 net/ipv4/udp.c | 26 +++++++++++++++++---------
 1 file changed, 17 insertions(+), 9 deletions(-)

index 8da74dc63061c..4f52d220f4d0c 100644
@@ -1570,17 +1570,25 @@ static int udp_rmem_schedule(struct sock *sk, int size)
 int __udp_enqueue_schedule_skb(struct sock *sk, struct sk_buff *skb)
 {
 	struct sk_buff_head *list = &sk->sk_receive_queue;
-	int rmem, err = -ENOMEM;
+	unsigned int rmem, rcvbuf;
 	spinlock_t *busy = NULL;
-	int size, rcvbuf;
+	int size, err = -ENOMEM;
 
-	/* Immediately drop when the receive queue is full.
-	 * Always allow at least one packet.
-	 */
 	rmem = atomic_read(&sk->sk_rmem_alloc);
 	rcvbuf = READ_ONCE(sk->sk_rcvbuf);
-	if (rmem > rcvbuf)
-		goto drop;
+	size = skb->truesize;
+
+	/* Immediately drop when the receive queue is full.
+	 * Cast to unsigned int performs the boundary check for INT_MAX.
+	 */
+	if (rmem + size > rcvbuf) {
+		if (rcvbuf > INT_MAX >> 1)
+			goto drop;
+
+		/* Always allow at least one packet for small buffer. */
+		if (rmem > rcvbuf)
+			goto drop;
+	}
 
 	/* Under mem pressure, it might be helpful to help udp_recvmsg()
 	 * having linear skbs :

@@ -1590,10 +1598,10 @@ int __udp_enqueue_schedule_skb(struct sock *sk, struct sk_buff *skb)
 	 */
 	if (rmem > (rcvbuf >> 1)) {
 		skb_condense(skb);
-
+		size = skb->truesize;
 		busy = busylock_acquire(sk);
 	}
-	size = skb->truesize;
+
 	udp_set_dev_scratch(skb);
 
 	atomic_add(size, &sk->sk_rmem_alloc);

2.39.5

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

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

From: Kuniyuki Iwashima <[email protected]>

[ Upstream commit df207de9d9e7a4d92f8567e2c539d9c8c12fd99d ]

Matt Dowling reported a weird UDP memory usage issue.

Under normal operation, the UDP memory usage reported in /proc/net/sockstat remains close to zero. However, it occasionally spiked to 524,288 pages and never dropped. Moreover, the value doubled when the application was terminated. Finally, it caused intermittent packet drops.

We can reproduce the issue with the script below [0]:

1. /proc/net/sockstat reports 0 pages

    # cat /proc/net/sockstat | grep UDP:
    UDP: inuse 1 mem 0

2. Run the script till the report reaches 524,288

    # python3 test.py & sleep 5
    # cat /proc/net/sockstat | grep UDP:
    UDP: inuse 3 mem 524288  <-- (INT_MAX + 1) >> PAGE_SHIFT

3. Kill the socket and confirm the number never drops

    # pkill python3 && sleep 5
    # cat /proc/net/sockstat | grep UDP:
    UDP: inuse 1 mem 524288

4. (necessary since v6.0) Trigger proto_memory_pcpu_drain()

    # python3 test.py & sleep 1 && pkill python3

5. The number doubles

    # cat /proc/net/sockstat | grep UDP:
    UDP: inuse 1 mem 1048577

The application set INT_MAX to SO_RCVBUF, which triggered an integer overflow in udp_rmem_release().

When a socket is close()d, udp_destruct_common() purges its receive queue and sums up skb->truesize in the queue. This total is calculated and stored in a local unsigned integer variable.

The total size is then passed to udp_rmem_release() to adjust memory accounting. However, because the function takes a signed integer argument, the total size can wrap around, causing an overflow.

Then, the released amount is calculated as follows:

1) Add size to sk->sk_forward_alloc.
2) Round down sk->sk_forward_alloc to the nearest lower multiple of PAGE_SIZE and assign it to amount.
3) Subtract amount from sk->sk_forward_alloc.
4) Pass amount >> PAGE_SHIFT to __sk_mem_reduce_allocated().

When the issue occurred, the total in udp_destruct_common() was 2147484480 (INT_MAX + 833), which was cast to -2147482816 in udp_rmem_release().

At 1) sk->sk_forward_alloc is changed from 3264 to -2147479552, and
2) sets -2147479552 to amount. 3) reverts the wraparound, so we don't see a warning in inet_sock_destruct(). However, udp_memory_allocated ends up doubling at 4).

Since commit 3cd3399dd7a8 ("net: implement per-cpu reserves for memory_allocated"), memory usage no longer doubles immediately after a socket is close()d because __sk_mem_reduce_allocated() caches the amount in udp_memory_per_cpu_fw_alloc. However, the next time a UDP socket receives a packet, the subtraction takes effect, causing UDP memory usage to double.

This issue makes further memory allocation fail once the socket's sk->sk_rmem_alloc exceeds net.ipv4.udp_rmem_min, resulting in packet drops.

To prevent this issue, let's use unsigned int for the calculation and call sk_forward_alloc_add() only once for the small delta.

Note that first_packet_length() also potentially has the same problem.

[0]:
from socket import *

SO_RCVBUFFORCE = 33
INT_MAX = (2 ** 31) - 1

s = socket(AF_INET, SOCK_DGRAM)
s.bind(('', 0))
s.setsockopt(SOL_SOCKET, SO_RCVBUFFORCE, INT_MAX)

c = socket(AF_INET, SOCK_DGRAM)
c.connect(s.getsockname())

data = b'a' * 100

while True:
c.send(data)

---
 net/ipv4/udp.c | 16 +++++++---------
 1 file changed, 7 insertions(+), 9 deletions(-)

index 4f52d220f4d0c..f4e24fc878fab 100644
@@ -1470,12 +1470,12 @@ static bool udp_skb_has_head_state(struct sk_buff *skb)
 }
 
 /* fully reclaim rmem/fwd memory allocated for skb */
-static void udp_rmem_release(struct sock *sk, int size, int partial,
-			     bool rx_queue_lock_held)
+static void udp_rmem_release(struct sock *sk, unsigned int size,
+			     int partial, bool rx_queue_lock_held)
 {
 	struct udp_sock *up = udp_sk(sk);
 	struct sk_buff_head *sk_queue;
-	int amt;
+	unsigned int amt;
 
 	if (likely(partial)) {
 		up->forward_deficit += size;

@@ -1495,10 +1495,8 @@ static void udp_rmem_release(struct sock *sk, int size, int partial,
 	if (!rx_queue_lock_held)
 		spin_lock(&sk_queue->lock);
 
-
-	sk_forward_alloc_add(sk, size);
-	amt = (sk->sk_forward_alloc - partial) & ~(PAGE_SIZE - 1);
-	sk_forward_alloc_add(sk, -amt);
+	amt = (size + sk->sk_forward_alloc - partial) & ~(PAGE_SIZE - 1);
+	sk_forward_alloc_add(sk, size - amt);
 
 	if (amt)
 		__sk_mem_reduce_allocated(sk, amt >> PAGE_SHIFT);

@@ -1688,7 +1686,7 @@ EXPORT_SYMBOL_GPL(skb_consume_udp);
 
 static struct sk_buff *__first_packet_length(struct sock *sk,
 					     struct sk_buff_head *rcvq,
-					     int *total)
+					     unsigned int *total)
 {
 	struct sk_buff *skb;
 

@@ -1721,8 +1719,8 @@ static int first_packet_length(struct sock *sk)
 {
 	struct sk_buff_head *rcvq = &udp_sk(sk)->reader_queue;
 	struct sk_buff_head *sk_queue = &sk->sk_receive_queue;
+	unsigned int total = 0;
 	struct sk_buff *skb;
-	int total = 0;
 	int res;
 
 	spin_lock_bh(&rcvq->lock);

2.39.5

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

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

From: Stefano Garzarella <[email protected]>

[ Upstream commit fccd2b711d9628c7ce0111d5e4938652101ee30a ]

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

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

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

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

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

index eb6ea26b390ee..d08f205b33dcc 100644
@@ -1551,7 +1551,11 @@ static int vsock_connect(struct socket *sock, struct sockaddr *addr,
 	timeout = vsk->connect_timeout;
 	prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
 
-	while (sk->sk_state != TCP_ESTABLISHED && sk->sk_err == 0) {
+	/* If the socket is already closing or it is in an error state, there
+	 * is no point in waiting.
+	 */
+	while (sk->sk_state != TCP_ESTABLISHED &&
+	       sk->sk_state != TCP_CLOSING && sk->sk_err == 0) {
 		if (flags & O_NONBLOCK) {
 			/* If we're not going to block, we schedule a timeout
 			 * function to generate a timeout on the connection

2.39.5

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

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

From: Guillaume Nault <[email protected]>

[ Upstream commit 8930424777e43257f5bf6f0f0f53defd0d30415c ]

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

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

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

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

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

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

index a3676155be78b..364ea798511ea 100644
@@ -416,7 +416,7 @@ int skb_tunnel_check_pmtu(struct sk_buff *skb, struct dst_entry *encap_dst,
 
 	skb_dst_update_pmtu_no_confirm(skb, mtu);
 
-	if (!reply || skb->pkt_type == PACKET_HOST)
+	if (!reply)
 		return 0;
 
 	if (skb->protocol == htons(ETH_P_IP))

index 704c858cf2093..61fea7baae5d5 100644
@@ -947,12 +947,6 @@ static void do_output(struct datapath *dp, struct sk_buff *skb, int out_port,
 				pskb_trim(skb, ovs_mac_header_len(key));
 		}
 
-		/* Need to set the pkt_type to involve the routing layer.  The
-		 * packet movement through the OVS datapath doesn't generally
-		 * use routing, but this is needed for tunnel cases.
-		 */
-		skb->pkt_type = PACKET_OUTGOING;
-
 		if (likely(!mru ||
 		           (skb->len <= mru + vport->dev->hard_header_len))) {
 			ovs_vport_send(vport, skb, ovs_key_mac_proto(key));

2.39.5

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

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

From: Antoine Tenart <[email protected]>

[ Upstream commit 3a0a3ff6593d670af2451ec363ccb7b18aec0c0a ]

Upstream fix ac888d58869b ("net: do not delay dst_entries_add() in dst_release()") moved decrementing the dst count from dst_destroy to dst_release to avoid accessing already freed data in case of netns dismantle. However in case CONFIG_DST_CACHE is enabled and OvS+tunnels are used, this fix is incomplete as the same issue will be seen for cached dsts:

  Unable to handle kernel paging request at virtual address ffff5aabf6b5c000
  Call trace:
   percpu_counter_add_batch+0x3c/0x160 (P)
   dst_release+0xec/0x108
   dst_cache_destroy+0x68/0xd8
   dst_destroy+0x13c/0x168
   dst_destroy_rcu+0x1c/0xb0
   rcu_do_batch+0x18c/0x7d0
   rcu_core+0x174/0x378
   rcu_core_si+0x18/0x30

Fix this by invalidating the cache, and thus decrementing cached dst counters, in dst_release too.

---
 net/core/dst.c | 8 ++++++++
 1 file changed, 8 insertions(+)

index 9552a90d4772d..6d76b799ce645 100644
@@ -165,6 +165,14 @@ static void dst_count_dec(struct dst_entry *dst)
 void dst_release(struct dst_entry *dst)
 {
 	if (dst && rcuref_put(&dst->__rcuref)) {
+#ifdef CONFIG_DST_CACHE
+		if (dst->flags & DST_METADATA) {
+			struct metadata_dst *md_dst = (struct metadata_dst *)dst;
+
+			if (md_dst->type == METADATA_IP_TUNNEL)
+				dst_cache_reset_now(&md_dst->u.tun_info.dst_cache);
+		}
+#endif
 		dst_count_dec(dst);
 		call_rcu_hurry(&dst->rcu_head, dst_destroy_rcu);
 	}

2.39.5

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

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

From: Lin Ma <[email protected]>

[ Upstream commit 1b755d8eb1ace3870789d48fbd94f386ad6e30be ]

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

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

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

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

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

index 5c6ed68cc6e05..52d76b8d15db2 100644
@@ -341,7 +341,7 @@ static const struct nla_policy nft_tunnel_opts_geneve_policy[NFTA_TUNNEL_KEY_GEN
 static int nft_tunnel_obj_geneve_init(const struct nlattr *attr,
 				      struct nft_tunnel_opts *opts)
 {
-	struct geneve_opt *opt = (struct geneve_opt *)opts->u.data + opts->len;
+	struct geneve_opt *opt = (struct geneve_opt *)(opts->u.data + opts->len);
 	struct nlattr *tb[NFTA_TUNNEL_KEY_GENEVE_MAX + 1];
 	int err, data_len;
 

@@ -628,7 +628,7 @@ static int nft_tunnel_opts_dump(struct sk_buff *skb,
 		if (!inner)
 			goto failure;
 		while (opts->len > offset) {
-			opt = (struct geneve_opt *)opts->u.data + offset;
+			opt = (struct geneve_opt *)(opts->u.data + offset);
 			if (nla_put_be16(skb, NFTA_TUNNEL_KEY_GENEVE_CLASS,
 					 opt->opt_class) ||
 			    nla_put_u8(skb, NFTA_TUNNEL_KEY_GENEVE_TYPE,

2.39.5

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

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

From: Fernando Fernandez Mancera <[email protected]>

[ Upstream commit 7ac6ea4a3e0898db76aecccd68fb2c403eb7d24e ]

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

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

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

index f7c17388ff6aa..f5d49162f7983 100644
@@ -5807,6 +5807,27 @@ static void snmp6_fill_stats(u64 *stats, struct inet6_dev *idev, int attrtype,
 	}
 }
 
+static int inet6_fill_ifla6_stats_attrs(struct sk_buff *skb,
+					struct inet6_dev *idev)
+{
+	struct nlattr *nla;
+
+	nla = nla_reserve(skb, IFLA_INET6_STATS, IPSTATS_MIB_MAX * sizeof(u64));
+	if (!nla)
+		goto nla_put_failure;
+	snmp6_fill_stats(nla_data(nla), idev, IFLA_INET6_STATS, nla_len(nla));
+
+	nla = nla_reserve(skb, IFLA_INET6_ICMP6STATS, ICMP6_MIB_MAX * sizeof(u64));
+	if (!nla)
+		goto nla_put_failure;
+	snmp6_fill_stats(nla_data(nla), idev, IFLA_INET6_ICMP6STATS, nla_len(nla));
+
+	return 0;
+
+nla_put_failure:
+	return -EMSGSIZE;
+}
+
 static int inet6_fill_ifla6_attrs(struct sk_buff *skb, struct inet6_dev *idev,
 				  u32 ext_filter_mask)
 {

@@ -5829,18 +5850,10 @@ static int inet6_fill_ifla6_attrs(struct sk_buff *skb, struct inet6_dev *idev,
 
 	/* XXX - MC not implemented */
 
-	if (ext_filter_mask & RTEXT_FILTER_SKIP_STATS)
-		return 0;
-
-	nla = nla_reserve(skb, IFLA_INET6_STATS, IPSTATS_MIB_MAX * sizeof(u64));
-	if (!nla)
-		goto nla_put_failure;
-	snmp6_fill_stats(nla_data(nla), idev, IFLA_INET6_STATS, nla_len(nla));
-
-	nla = nla_reserve(skb, IFLA_INET6_ICMP6STATS, ICMP6_MIB_MAX * sizeof(u64));
-	if (!nla)
-		goto nla_put_failure;
-	snmp6_fill_stats(nla_data(nla), idev, IFLA_INET6_ICMP6STATS, nla_len(nla));
+	if (!(ext_filter_mask & RTEXT_FILTER_SKIP_STATS)) {
+		if (inet6_fill_ifla6_stats_attrs(skb, idev) < 0)
+			goto nla_put_failure;
+	}
 
 	nla = nla_reserve(skb, IFLA_INET6_TOKEN, sizeof(struct in6_addr));
 	if (!nla)

2.39.5

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

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

From: David Oberhollenzer <[email protected]>

[ Upstream commit a58d882841a0750da3c482cd3d82432b1c7edb77 ]

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

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

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

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

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

index 5aeecfab96306..5935100e7d65f 100644
@@ -7301,13 +7301,13 @@ static int mv88e6xxx_probe(struct mdio_device *mdiodev)
 	err = mv88e6xxx_switch_reset(chip);
 	mv88e6xxx_reg_unlock(chip);
 	if (err)
-		goto out;
+		goto out_phy;
 
 	if (np) {
 		chip->irq = of_irq_get(np, 0);
 		if (chip->irq == -EPROBE_DEFER) {
 			err = chip->irq;
-			goto out;
+			goto out_phy;
 		}
 	}
 

@@ -7326,7 +7326,7 @@ static int mv88e6xxx_probe(struct mdio_device *mdiodev)
 	mv88e6xxx_reg_unlock(chip);
 
 	if (err)
-		goto out;
+		goto out_phy;
 
 	if (chip->info->g2_irqs > 0) {
 		err = mv88e6xxx_g2_irq_setup(chip);

@@ -7360,6 +7360,8 @@ static int mv88e6xxx_probe(struct mdio_device *mdiodev)
 		mv88e6xxx_g1_irq_free(chip);
 	else
 		mv88e6xxx_irq_poll_free(chip);
+out_phy:
+	mv88e6xxx_phy_destroy(chip);
 out:
 	if (pdata)
 		dev_put(pdata->netdev);

@@ -7382,7 +7384,6 @@ static void mv88e6xxx_remove(struct mdio_device *mdiodev)
 		mv88e6xxx_ptp_free(chip);
 	}
 
-	mv88e6xxx_phy_destroy(chip);
 	mv88e6xxx_unregister_switch(chip);
 
 	mv88e6xxx_g1_vtu_prob_irq_free(chip);

@@ -7395,6 +7396,8 @@ static void mv88e6xxx_remove(struct mdio_device *mdiodev)
 		mv88e6xxx_g1_irq_free(chip);
 	else
 		mv88e6xxx_irq_poll_free(chip);
+
+	mv88e6xxx_phy_destroy(chip);
 }
 
 static void mv88e6xxx_shutdown(struct mdio_device *mdiodev)

index 8bb88b3d900db..ee9e5d7e52770 100644
@@ -229,7 +229,10 @@ static void mv88e6xxx_phy_ppu_state_init(struct mv88e6xxx_chip *chip)
 
 static void mv88e6xxx_phy_ppu_state_destroy(struct mv88e6xxx_chip *chip)
 {
+	mutex_lock(&chip->ppu_mutex);
 	del_timer_sync(&chip->ppu_timer);
+	cancel_work_sync(&chip->ppu_work);
+	mutex_unlock(&chip->ppu_mutex);
 }
 
 int mv88e6185_phy_ppu_read(struct mv88e6xxx_chip *chip, struct mii_bus *bus,

2.39.5

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

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

From: Lin Ma <[email protected]>

[ Upstream commit b27055a08ad4b415dcf15b63034f9cb236f7fb40 ]

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

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

One example crash log is like below:

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

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

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

index 364ea798511ea..f65d2f7273813 100644
@@ -451,7 +451,7 @@ static const struct nla_policy
 geneve_opt_policy[LWTUNNEL_IP_OPT_GENEVE_MAX + 1] = {
 	[LWTUNNEL_IP_OPT_GENEVE_CLASS]	= { .type = NLA_U16 },
 	[LWTUNNEL_IP_OPT_GENEVE_TYPE]	= { .type = NLA_U8 },
-	[LWTUNNEL_IP_OPT_GENEVE_DATA]	= { .type = NLA_BINARY, .len = 128 },
+	[LWTUNNEL_IP_OPT_GENEVE_DATA]	= { .type = NLA_BINARY, .len = 127 },
 };
 
 static const struct nla_policy

index 52d76b8d15db2..0d99786c322e8 100644
@@ -335,7 +335,7 @@ static int nft_tunnel_obj_erspan_init(const struct nlattr *attr,
 static const struct nla_policy nft_tunnel_opts_geneve_policy[NFTA_TUNNEL_KEY_GENEVE_MAX + 1] = {
 	[NFTA_TUNNEL_KEY_GENEVE_CLASS]	= { .type = NLA_U16 },
 	[NFTA_TUNNEL_KEY_GENEVE_TYPE]	= { .type = NLA_U8 },
-	[NFTA_TUNNEL_KEY_GENEVE_DATA]	= { .type = NLA_BINARY, .len = 128 },
+	[NFTA_TUNNEL_KEY_GENEVE_DATA]	= { .type = NLA_BINARY, .len = 127 },
 };
 
 static int nft_tunnel_obj_geneve_init(const struct nlattr *attr,

index af7c998459488..e296714803dc0 100644
@@ -68,7 +68,7 @@ geneve_opt_policy[TCA_TUNNEL_KEY_ENC_OPT_GENEVE_MAX + 1] = {
 	[TCA_TUNNEL_KEY_ENC_OPT_GENEVE_CLASS]	   = { .type = NLA_U16 },
 	[TCA_TUNNEL_KEY_ENC_OPT_GENEVE_TYPE]	   = { .type = NLA_U8 },
 	[TCA_TUNNEL_KEY_ENC_OPT_GENEVE_DATA]	   = { .type = NLA_BINARY,
-						       .len = 128 },
+						       .len = 127 },
 };
 
 static const struct nla_policy

index 03505673d5234..099ff6a3e1f51 100644
@@ -766,7 +766,7 @@ geneve_opt_policy[TCA_FLOWER_KEY_ENC_OPT_GENEVE_MAX + 1] = {
 	[TCA_FLOWER_KEY_ENC_OPT_GENEVE_CLASS]      = { .type = NLA_U16 },
 	[TCA_FLOWER_KEY_ENC_OPT_GENEVE_TYPE]       = { .type = NLA_U8 },
 	[TCA_FLOWER_KEY_ENC_OPT_GENEVE_DATA]       = { .type = NLA_BINARY,
-						       .len = 128 },
+						       .len = 127 },
 };
 
 static const struct nla_policy

2.39.5

6.12-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 b393c37d24245..54ce948835a09 100644
@@ -412,11 +412,35 @@ 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))

@@ -440,10 +464,18 @@ 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

6.12-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 54ce948835a09..987492dcb07ca 100644
@@ -442,6 +442,7 @@ 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;

@@ -468,7 +469,8 @@ 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;

@@ -481,7 +483,7 @@ 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

6.12-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 c5e571ec94c99..0472bcdff1307 100644
@@ -251,18 +251,33 @@ 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

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

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

From: Dave Marquardt <[email protected]>

[ Upstream commit 053f3ff67d7feefc75797863f3d84b47ad47086f ]

v2:
- Created a single error handling unlock and exit in veth_pool_store
- Greatly expanded commit message with previous explanatory-only text

Summary: Use rtnl_mutex to synchronize veth_pool_store with itself, ibmveth_close and ibmveth_open, preventing multiple calls in a row to napi_disable.

Background: Two (or more) threads could call veth_pool_store through writing to /sys/devices/vio/30000002/pool*/*. You can do this easily with a little shell script. This causes a hang.

I configured LOCKDEP, compiled ibmveth.c with DEBUG, and built a new kernel. I ran this test again and saw:

    Setting pool0/active to 0
    Setting pool1/active to 1
    [   73.911067][ T4365] ibmveth 30000002 eth0: close starting
    Setting pool1/active to 1
    Setting pool1/active to 0
    [   73.911367][ T4366] ibmveth 30000002 eth0: close starting
    [   73.916056][ T4365] ibmveth 30000002 eth0: close complete
    [   73.916064][ T4365] ibmveth 30000002 eth0: open starting
    [  110.808564][  T712] systemd-journald[712]: Sent WATCHDOG=1 notification.
    [  230.808495][  T712] systemd-journald[712]: Sent WATCHDOG=1 notification.
    [  243.683786][  T123] INFO: task stress.sh:4365 blocked for more than 122 seconds.
    [  243.683827][  T123]       Not tainted 6.14.0-01103-g2df0c02dab82-dirty #8
    [  243.683833][  T123] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
    [  243.683838][  T123] task:stress.sh       state:D stack:28096 pid:4365  tgid:4365  ppid:4364   task_flags:0x400040 flags:0x00042000
    [  243.683852][  T123] Call Trace:
    [  243.683857][  T123] [c00000000c38f690] [0000000000000001] 0x1 (unreliable)
    [  243.683868][  T123] [c00000000c38f840] [c00000000001f908] __switch_to+0x318/0x4e0
    [  243.683878][  T123] [c00000000c38f8a0] [c000000001549a70] __schedule+0x500/0x12a0
    [  243.683888][  T123] [c00000000c38f9a0] [c00000000154a878] schedule+0x68/0x210
    [  243.683896][  T123] [c00000000c38f9d0] [c00000000154ac80] schedule_preempt_disabled+0x30/0x50
    [  243.683904][  T123] [c00000000c38fa00] [c00000000154dbb0] __mutex_lock+0x730/0x10f0
    [  243.683913][  T123] [c00000000c38fb10] [c000000001154d40] napi_enable+0x30/0x60
    [  243.683921][  T123] [c00000000c38fb40] [c000000000f4ae94] ibmveth_open+0x68/0x5dc
    [  243.683928][  T123] [c00000000c38fbe0] [c000000000f4aa20] veth_pool_store+0x220/0x270
    [  243.683936][  T123] [c00000000c38fc70] [c000000000826278] sysfs_kf_write+0x68/0xb0
    [  243.683944][  T123] [c00000000c38fcb0] [c0000000008240b8] kernfs_fop_write_iter+0x198/0x2d0
    [  243.683951][  T123] [c00000000c38fd00] [c00000000071b9ac] vfs_write+0x34c/0x650
    [  243.683958][  T123] [c00000000c38fdc0] [c00000000071bea8] ksys_write+0x88/0x150
    [  243.683966][  T123] [c00000000c38fe10] [c0000000000317f4] system_call_exception+0x124/0x340
    [  243.683973][  T123] [c00000000c38fe50] [c00000000000d05c] system_call_vectored_common+0x15c/0x2ec
    ...
    [  243.684087][  T123] Showing all locks held in the system:
    [  243.684095][  T123] 1 lock held by khungtaskd/123:
    [  243.684099][  T123]  #0: c00000000278e370 (rcu_read_lock){....}-{1:2}, at: debug_show_all_locks+0x50/0x248
    [  243.684114][  T123] 4 locks held by stress.sh/4365:
    [  243.684119][  T123]  #0: c00000003a4cd3f8 (sb_writers#3){.+.+}-{0:0}, at: ksys_write+0x88/0x150
    [  243.684132][  T123]  #1: c000000041aea888 (&of->mutex#2){+.+.}-{3:3}, at: kernfs_fop_write_iter+0x154/0x2d0
    [  243.684143][  T123]  #2: c0000000366fb9a8 (kn->active#64){.+.+}-{0:0}, at: kernfs_fop_write_iter+0x160/0x2d0
    [  243.684155][  T123]  #3: c000000035ff4cb8 (&dev->lock){+.+.}-{3:3}, at: napi_enable+0x30/0x60
    [  243.684166][  T123] 5 locks held by stress.sh/4366:
    [  243.684170][  T123]  #0: c00000003a4cd3f8 (sb_writers#3){.+.+}-{0:0}, at: ksys_write+0x88/0x150
    [  243.684183][  T123]  #1: c00000000aee2288 (&of->mutex#2){+.+.}-{3:3}, at: kernfs_fop_write_iter+0x154/0x2d0
    [  243.684194][  T123]  #2: c0000000366f4ba8 (kn->active#64){.+.+}-{0:0}, at: kernfs_fop_write_iter+0x160/0x2d0
    [  243.684205][  T123]  #3: c000000035ff4cb8 (&dev->lock){+.+.}-{3:3}, at: napi_disable+0x30/0x60
    [  243.684216][  T123]  #4: c0000003ff9bbf18 (&rq->__lock){-.-.}-{2:2}, at: __schedule+0x138/0x12a0

calls ibmveth_close and ibmveth_open. Here's the sequence:

T4365 T4366
----------------- ----------------- ---------
veth_pool_store veth_pool_store
ibmveth_close
ibmveth_close
napi_disable
napi_disable
ibmveth_open
napi_enable <- HANG

ibmveth_close calls napi_disable at the top and ibmveth_open calls napi_enable at the top.

https://docs.kernel.org/networking/napi.html]] says

The control APIs are not idempotent. Control API calls are safe against concurrent use of datapath APIs but an incorrect sequence of control API calls may result in crashes, deadlocks, or race conditions. For example, calling napi_disable() multiple times in a row will deadlock.

In the normal open and close paths, rtnl_mutex is acquired to prevent other callers. This is missing from veth_pool_store. Use rtnl_mutex in veth_pool_store fixes these hangs.

---
 drivers/net/ethernet/ibm/ibmveth.c | 39 +++++++++++++++++++++---------
 1 file changed, 27 insertions(+), 12 deletions(-)

index b619a3ec245b2..04192190bebab 100644
@@ -1802,18 +1802,22 @@ static ssize_t veth_pool_store(struct kobject *kobj, struct attribute *attr,
 	long value = simple_strtol(buf, NULL, 10);
 	long rc;
 
+	rtnl_lock();
+
 	if (attr == &veth_active_attr) {
 		if (value && !pool->active) {
 			if (netif_running(netdev)) {
 				if (ibmveth_alloc_buffer_pool(pool)) {
 					netdev_err(netdev,
 						   "unable to alloc pool\n");
-					return -ENOMEM;
+					rc = -ENOMEM;
+					goto unlock_err;
 				}
 				pool->active = 1;
 				ibmveth_close(netdev);
-				if ((rc = ibmveth_open(netdev)))
-					return rc;
+				rc = ibmveth_open(netdev);
+				if (rc)
+					goto unlock_err;
 			} else {
 				pool->active = 1;
 			}

@@ -1833,48 +1837,59 @@ static ssize_t veth_pool_store(struct kobject *kobj, struct attribute *attr,
 
 			if (i == IBMVETH_NUM_BUFF_POOLS) {
 				netdev_err(netdev, "no active pool >= MTU\n");
-				return -EPERM;
+				rc = -EPERM;
+				goto unlock_err;
 			}
 
 			if (netif_running(netdev)) {
 				ibmveth_close(netdev);
 				pool->active = 0;
-				if ((rc = ibmveth_open(netdev)))
-					return rc;
+				rc = ibmveth_open(netdev);
+				if (rc)
+					goto unlock_err;
 			}
 			pool->active = 0;
 		}
 	} else if (attr == &veth_num_attr) {
 		if (value <= 0 || value > IBMVETH_MAX_POOL_COUNT) {
-			return -EINVAL;
+			rc = -EINVAL;
+			goto unlock_err;
 		} else {
 			if (netif_running(netdev)) {
 				ibmveth_close(netdev);
 				pool->size = value;
-				if ((rc = ibmveth_open(netdev)))
-					return rc;
+				rc = ibmveth_open(netdev);
+				if (rc)
+					goto unlock_err;
 			} else {
 				pool->size = value;
 			}
 		}
 	} else if (attr == &veth_size_attr) {
 		if (value <= IBMVETH_BUFF_OH || value > IBMVETH_MAX_BUF_SIZE) {
-			return -EINVAL;
+			rc = -EINVAL;
+			goto unlock_err;
 		} else {
 			if (netif_running(netdev)) {
 				ibmveth_close(netdev);
 				pool->buff_size = value;
-				if ((rc = ibmveth_open(netdev)))
-					return rc;
+				rc = ibmveth_open(netdev);
+				if (rc)
+					goto unlock_err;
 			} else {
 				pool->buff_size = value;
 			}
 		}
 	}
+	rtnl_unlock();
 
 	/* kick the interrupt handler to allocate/deallocate pools */
 	ibmveth_interrupt(netdev->irq, netdev);
 	return count;
+
+unlock_err:
+	rtnl_unlock();
+	return rc;
 }
 
 

2.39.5

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

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

From: Alexandru Gagniuc <[email protected]>

[ Upstream commit 62604063621fb075c7966286bdddcb057d883fa8 ]

In ThinPro, we use the convention <upstream_ver>+hp<patchlevel> for the kernel package. This does not have a dash in the name or version. This is built by editing ".version" before a build, and setting EXTRAVERSION="+hp" and KDEB_PKGVERSION make variables:

    echo 68 > .version
    make -j<n> EXTRAVERSION="+hp" bindeb-pkg KDEB_PKGVERSION=6.12.2+hp69

    .deb name: linux-image-6.12.2+hp_6.12.2+hp69_amd64.deb

Since commit 7d4f07d5cb71 ("kbuild: deb-pkg: squash scripts/package/deb-build-option to debian/rules"), this no longer works. The deb build logic changed, even though, the commit message implies that the logic should be unmodified.

Before, KBUILD_BUILD_VERSION was not set if the KDEB_PKGVERSION did not contain a dash. After the change KBUILD_BUILD_VERSION is always set to KDEB_PKGVERSION. Since this determines UTS_VERSION, the uname output to look off:

    (now)      uname -a: version 6.12.2+hp ... #6.12.2+hp69
    (expected) uname -a: version 6.12.2+hp ... #69

Update the debian/rules logic to restore the original behavior.

---
 scripts/package/debian/rules | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

index ca07243bd5cdf..2b3f9a0bd6c40 100755
@@ -21,9 +21,11 @@ ifeq ($(origin KBUILD_VERBOSE),undefined)
     endif
 endif
 
-revision = $(lastword $(subst -, ,$(shell dpkg-parsechangelog -S Version)))
+revision = $(shell dpkg-parsechangelog -S Version | sed -n 's/.*-//p')
 CROSS_COMPILE ?= $(filter-out $(DEB_BUILD_GNU_TYPE)-, $(DEB_HOST_GNU_TYPE)-)
-make-opts = ARCH=$(ARCH) KERNELRELEASE=$(KERNELRELEASE) KBUILD_BUILD_VERSION=$(revision) $(addprefix CROSS_COMPILE=,$(CROSS_COMPILE))
+make-opts = ARCH=$(ARCH) KERNELRELEASE=$(KERNELRELEASE) \
+    $(addprefix KBUILD_BUILD_VERSION=,$(revision)) \
+    $(addprefix CROSS_COMPILE=,$(CROSS_COMPILE))
 
 binary-targets := $(addprefix binary-, image image-dbg headers libc-dev)
 

2.39.5

6.12-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 d3e8be82a1727..84cf5fd297b7f 100644
@@ -1549,7 +1549,7 @@ 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

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

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

From: Alex Deucher <[email protected]>

[ Upstream commit dce8bd9137b88735dd0efc4e2693213d98c15913 ]

GC12 only has 1 mec.

---
 drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index d3798a333d1f8..b259e217930c7 100644
@@ -1332,7 +1332,7 @@ static int gfx_v12_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 = 2;
 		adev->gfx.mec.num_queue_per_pipe = 4;
 		break;

2.39.5

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

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

From: Yeoreum Yun <[email protected]>

[ Upstream commit a3c3c66670cee11eb13aa43905904bf29cb92d32 ]

The perf events code fails to account for total_time_enabled of inactive events.

Here is a failure case for accounting total_time_enabled for CPU PMU events:

  sudo ./perf stat -vvv -e armv8_pmuv3_0/event=0x08/ -e armv8_pmuv3_1/event=0x08/ -- stress-ng --pthread=2 -t 2s
  ...

armv8_pmuv3_0/event=0x08/: 1138698008 2289429840 2174835740 armv8_pmuv3_1/event=0x08/: 1826791390 1950025700 847648440

                             `          `          `
                             `          `          > total_time_running with child
                             `          > total_time_enabled with child

> count with child

Performance counter stats for 'stress-ng --pthread=2 -t 2s':

       1,138,698,008      armv8_pmuv3_0/event=0x08/                                               (94.99%)
       1,826,791,390      armv8_pmuv3_1/event=0x08/                                               (43.47%)

The two events above are opened on two different CPU PMUs, for example, each event is opened for a cluster in an Arm big.LITTLE system, they will never run on the same CPU. In theory, the total enabled time should be same for both events, as two events are opened and closed together.

As the result show, the two events' total enabled time including child event is different (2289429840 vs 1950025700).

This is because child events are not accounted properly if a event is INACTIVE state when the task exits:

perf_event_exit_event()
`> perf_remove_from_context()

     `> __perf_remove_from_context()
       `> perf_child_detach()   -> Accumulate child_total_time_enabled
         `> list_del_event()    -> Update child event's time

The problem is the time accumulation happens prior to child event's time updating. Thus, it misses to account the last period's time when the event exits.

The perf core layer follows the rule that timekeeping is tied to state change. To address the issue, make __perf_remove_from_context() handle the task exit case by passing 'DETACH_EXIT' to it and invoke perf_event_state() for state alongside with accounting the time.

Then, perf_child_detach() populates the time into the parent's time metrics.

After this patch, the bug is fixed:

  sudo ./perf stat -vvv -e armv8_pmuv3_0/event=0x08/ -e armv8_pmuv3_1/event=0x08/ -- stress-ng --pthread=2 -t 10s
  ...
  armv8_pmuv3_0/event=0x08/: 15396770398 32157963940 21898169000
  armv8_pmuv3_1/event=0x08/: 22428964974 32157963940 10259794940

Performance counter stats for 'stress-ng --pthread=2 -t 10s':

      15,396,770,398      armv8_pmuv3_0/event=0x08/                                               (68.10%)
      22,428,964,974      armv8_pmuv3_1/event=0x08/                                               (31.90%)

[ mingo: Clarified the changelog. ]

---
 kernel/events/core.c | 18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

index cf2ec0a1582fd..b5ccf52bb71ba 100644
@@ -2407,6 +2407,7 @@ ctx_time_update_event(struct perf_event_context *ctx, struct perf_event *event)
 #define DETACH_GROUP	0x01UL
 #define DETACH_CHILD	0x02UL
 #define DETACH_DEAD	0x04UL
+#define DETACH_EXIT	0x08UL
 
 /*
  * Cross CPU call to remove a performance event

@@ -2421,6 +2422,7 @@ __perf_remove_from_context(struct perf_event *event,
 			   void *info)
 {
 	struct perf_event_pmu_context *pmu_ctx = event->pmu_ctx;
+	enum perf_event_state state = PERF_EVENT_STATE_OFF;
 	unsigned long flags = (unsigned long)info;
 
 	ctx_time_update(cpuctx, ctx);

@@ -2429,16 +2431,19 @@ __perf_remove_from_context(struct perf_event *event,
 	 * Ensure event_sched_out() switches to OFF, at the very least
 	 * this avoids raising perf_pending_task() at this time.
 	 */
-	if (flags & DETACH_DEAD)
+	if (flags & DETACH_EXIT)
+		state = PERF_EVENT_STATE_EXIT;
+	if (flags & DETACH_DEAD) {
 		event->pending_disable = 1;
+		state = PERF_EVENT_STATE_DEAD;
+	}
 	event_sched_out(event, ctx);
+	perf_event_set_state(event, min(event->state, state));
 	if (flags & DETACH_GROUP)
 		perf_group_detach(event);
 	if (flags & DETACH_CHILD)
 		perf_child_detach(event);
 	list_del_event(event, ctx);
-	if (flags & DETACH_DEAD)
-		event->state = PERF_EVENT_STATE_DEAD;
 
 	if (!pmu_ctx->nr_events) {
 		pmu_ctx->rotate_necessary = 0;

@@ -13343,12 +13348,7 @@ perf_event_exit_event(struct perf_event *event, struct perf_event_context *ctx)
 		mutex_lock(&parent_event->child_mutex);
 	}
 
-	perf_remove_from_context(event, detach_flags);
-
-	raw_spin_lock_irq(&ctx->lock);
-	if (event->state > PERF_EVENT_STATE_EXIT)
-		perf_event_set_state(event, PERF_EVENT_STATE_EXIT);
-	raw_spin_unlock_irq(&ctx->lock);
+	perf_remove_from_context(event, detach_flags | DETACH_EXIT);
 
 	/*
 	 * Child events can be freed.

2.39.5

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

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

From: Len Brown <[email protected]>

[ Upstream commit f729775f79a9c942c6c82ed6b44bd030afe10423 ]

The CoreThr column displays total thermal throttling events since boot time.

Change it to report events during the measurement interval.

This is more useful for showing a user the current conditions. Total events since boot time are still available to the user via /sys/devices/system/cpu/cpu*/thermal_throttle/*

Document CoreThr on turbostat.8

---
 tools/power/x86/turbostat/turbostat.8 | 2 ++
 tools/power/x86/turbostat/turbostat.c | 2 +-
 2 files changed, 3 insertions(+), 1 deletion(-)

index 56c7ff6efcdab..a3cf1d17163ae 100644
@@ -168,6 +168,8 @@ The system configuration dump (if --quiet is not used) is followed by statistics
 .PP
 \fBPkgTmp\fP Degrees Celsius reported by the per-package Package Thermal Monitor.
 .PP
+\fBCoreThr\fP Core Thermal Throttling events during the measurement interval.  Note that events since boot can be find in /sys/devices/system/cpu/cpu*/thermal_throttle/*
+.PP
 \fBGFX%rc6\fP The percentage of time the GPU is in the "render C6" state, rc6, during the measurement interval. From /sys/class/drm/card0/power/rc6_residency_ms or /sys/class/drm/card0/gt/gt0/rc6_residency_ms or /sys/class/drm/card0/device/tile0/gtN/gtidle/idle_residency_ms depending on the graphics driver being used.
 .PP
 \fBGFXMHz\fP Instantaneous snapshot of what sysfs presents at the end of the measurement interval. From /sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz or /sys/class/drm/card0/gt_cur_freq_mhz or /sys/class/drm/card0/gt/gt0/rps_cur_freq_mhz or /sys/class/drm/card0/device/tile0/gtN/freq0/cur_freq depending on the graphics driver being used.

index 235e82fe7d0a5..77ef60980ee58 100644
@@ -3242,7 +3242,7 @@ void delta_core(struct core_data *new, struct core_data *old)
 	old->c6 = new->c6 - old->c6;
 	old->c7 = new->c7 - old->c7;
 	old->core_temp_c = new->core_temp_c;
-	old->core_throt_cnt = new->core_throt_cnt;
+	old->core_throt_cnt = new->core_throt_cnt - old->core_throt_cnt;
 	old->mc6_us = new->mc6_us - old->mc6_us;
 
 	DELTA_WRAP32(new->core_energy.raw_value, old->core_energy.raw_value);

2.39.5

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

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

From: Steven Rostedt <[email protected]>

[ Upstream commit 2b36a97aeeb71b1e4a48bfedc7f21f44aeb1e6fb ]

There are a couple functions in trace_events_hist.c that have "goto out" or equivalent on error in order to release locks that were taken. This can be error prone or just simply make the code more complex.

Switch every location that ends with unlocking a mutex on error over to using the guard(mutex)() infrastructure to let the compiler worry about releasing locks. This makes the code easier to read and understand.

Stable-dep-of: 0b4ffbe4888a ("tracing: Correct the refcount if the hist/hist_debug file fails to open")

---
 kernel/trace/trace_events_hist.c | 32 ++++++++++----------------------
 1 file changed, 10 insertions(+), 22 deletions(-)

index 31f5ad322fab0..5d344bc690d99 100644
@@ -5597,25 +5597,19 @@ static int hist_show(struct seq_file *m, void *v)
 {
 	struct event_trigger_data *data;
 	struct trace_event_file *event_file;
-	int n = 0, ret = 0;
+	int n = 0;
 
-	mutex_lock(&event_mutex);
+	guard(mutex)(&event_mutex);
 
 	event_file = event_file_file(m->private);
-	if (unlikely(!event_file)) {
-		ret = -ENODEV;
-		goto out_unlock;
-	}
+	if (unlikely(!event_file))
+		return -ENODEV;
 
 	list_for_each_entry(data, &event_file->triggers, list) {
 		if (data->cmd_ops->trigger_type == ETT_EVENT_HIST)
 			hist_trigger_show(m, data, n++);
 	}
-
- out_unlock:
-	mutex_unlock(&event_mutex);
-
-	return ret;
+	return 0;
 }
 
 static int event_hist_open(struct inode *inode, struct file *file)

@@ -5876,25 +5870,19 @@ static int hist_debug_show(struct seq_file *m, void *v)
 {
 	struct event_trigger_data *data;
 	struct trace_event_file *event_file;
-	int n = 0, ret = 0;
+	int n = 0;
 
-	mutex_lock(&event_mutex);
+	guard(mutex)(&event_mutex);
 
 	event_file = event_file_file(m->private);
-	if (unlikely(!event_file)) {
-		ret = -ENODEV;
-		goto out_unlock;
-	}
+	if (unlikely(!event_file))
+		return -ENODEV;
 
 	list_for_each_entry(data, &event_file->triggers, list) {
 		if (data->cmd_ops->trigger_type == ETT_EVENT_HIST)
 			hist_trigger_debug_show(m, data, n++);
 	}
-
- out_unlock:
-	mutex_unlock(&event_mutex);
-
-	return ret;
+	return 0;
 }
 
 static int event_hist_debug_open(struct inode *inode, struct file *file)

2.39.5

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

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

From: Masami Hiramatsu (Google) <[email protected]>

[ Upstream commit 1bd13edbbed6e7e396f1aab92b224a4775218e68 ]

Add poll syscall support on the hist file. The Waiter will be waken up when the histogram is updated with POLLIN.

Currently, there is no way to wait for a specific event in userspace. So user needs to peek the trace periodicaly, or wait on trace_pipe. But it is not a good idea to peek at the trace for an event that randomly happens. And trace_pipe is not coming back until a page is filled with events.

This allows a user to wait for a specific event on the hist file. User can set a histogram trigger on the event which they want to monitor and poll() on its hist file. Since this poll() returns POLLIN, the next poll() will return soon unless a read() happens on that hist file.

NOTE: To read the hist file again, you must set the file offset to 0, but just for monitoring the event, you may not need to read the histogram.

Stable-dep-of: 0b4ffbe4888a ("tracing: Correct the refcount if the hist/hist_debug file fails to open")

---
 include/linux/trace_events.h     | 14 +++++++
 kernel/trace/trace_events.c      | 14 +++++++
 kernel/trace/trace_events_hist.c | 70 ++++++++++++++++++++++++++++++--
 3 files changed, 95 insertions(+), 3 deletions(-)

index 77769ff505444..fcf5a64d5cfe2 100644
@@ -689,6 +689,20 @@ struct trace_event_file {
 	atomic_t		tm_ref;	/* trigger-mode reference counter */
 };
 
+#ifdef CONFIG_HIST_TRIGGERS
+extern struct irq_work hist_poll_work;
+extern wait_queue_head_t hist_poll_wq;
+
+static inline void hist_poll_wakeup(void)
+{
+	if (wq_has_sleeper(&hist_poll_wq))
+		irq_work_queue(&hist_poll_work);
+}
+
+#define hist_poll_wait(file, wait)	\
+	poll_wait(file, &hist_poll_wq, wait)
+#endif
+
 #define __TRACE_EVENT_FLAGS(name, value)				\
 	static int __init trace_init_flags_##name(void)			\
 	{								\

index ea9b44847ce6b..29eba68e07859 100644
@@ -3111,6 +3111,20 @@ static bool event_in_systems(struct trace_event_call *call,
 	return !*p || isspace(*p) || *p == ',';
 }
 
+#ifdef CONFIG_HIST_TRIGGERS
+/*
+ * Wake up waiter on the hist_poll_wq from irq_work because the hist trigger
+ * may happen in any context.
+ */
+static void hist_poll_event_irq_work(struct irq_work *work)
+{
+	wake_up_all(&hist_poll_wq);
+}
+
+DEFINE_IRQ_WORK(hist_poll_work, hist_poll_event_irq_work);
+DECLARE_WAIT_QUEUE_HEAD(hist_poll_wq);
+#endif
+
 static struct trace_event_file *
 trace_create_new_event(struct trace_event_call *call,
 		       struct trace_array *tr)

2.39.5

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

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

From: Masami Hiramatsu (Google) <[email protected]>

[ Upstream commit 66fc6f521a0b91051ce6968a216a30bc52267bf8 ]

Since POLLIN will not be flushed until the hist file is read, the user needs to repeatedly read() and poll() on the hist file for monitoring the event continuously. But the read() is somewhat redundant when the user is only monitoring for event updates.

Add POLLPRI poll event on the hist file so the event returns when a histogram is updated after open(), poll() or read(). Thus it is possible to wait for the next event without having to issue a read().

Stable-dep-of: 0b4ffbe4888a ("tracing: Correct the refcount if the hist/hist_debug file fails to open")

---
 kernel/trace/trace_events_hist.c | 29 ++++++++++++++++++++++++++---
 1 file changed, 26 insertions(+), 3 deletions(-)

index 9e33cd2a73b5c..e07d75adab8e3 100644
@@ -5598,6 +5598,7 @@ static void hist_trigger_show(struct seq_file *m,
 struct hist_file_data {
 	struct file *file;
 	u64 last_read;
+	u64 last_act;
 };
 
 static u64 get_hist_hit_count(struct trace_event_file *event_file)

@@ -5633,6 +5634,11 @@ static int hist_show(struct seq_file *m, void *v)
 			hist_trigger_show(m, data, n++);
 	}
 	hist_file->last_read = get_hist_hit_count(event_file);
+	/*
+	 * Update last_act too so that poll()/POLLPRI can wait for the next
+	 * event after any syscall on hist file.
+	 */
+	hist_file->last_act = hist_file->last_read;
 
 	return 0;
 }

@@ -5642,6 +5648,8 @@ static __poll_t event_hist_poll(struct file *file, struct poll_table_struct *wai
 	struct trace_event_file *event_file;
 	struct seq_file *m = file->private_data;
 	struct hist_file_data *hist_file = m->private;
+	__poll_t ret = 0;
+	u64 cnt;
 
 	guard(mutex)(&event_mutex);
 

@@ -5651,10 +5659,15 @@ static __poll_t event_hist_poll(struct file *file, struct poll_table_struct *wai
 
 	hist_poll_wait(file, wait);
 
-	if (hist_file->last_read != get_hist_hit_count(event_file))
-		return EPOLLIN | EPOLLRDNORM;
+	cnt = get_hist_hit_count(event_file);
+	if (hist_file->last_read != cnt)
+		ret |= EPOLLIN | EPOLLRDNORM;
+	if (hist_file->last_act != cnt) {
+		hist_file->last_act = cnt;
+		ret |= EPOLLPRI;
+	}
 
-	return 0;
+	return ret;
 }
 
 static int event_hist_release(struct inode *inode, struct file *file)

@@ -5668,6 +5681,7 @@ static int event_hist_release(struct inode *inode, struct file *file)
 
 static int event_hist_open(struct inode *inode, struct file *file)
 {
+	struct trace_event_file *event_file;
 	struct hist_file_data *hist_file;
 	int ret;
 

@@ -5675,16 +5689,25 @@ static int event_hist_open(struct inode *inode, struct file *file)
 	if (ret)
 		return ret;
 
+	guard(mutex)(&event_mutex);
+
+	event_file = event_file_data(file);
+	if (!event_file)
+		return -ENODEV;
+
 	hist_file = kzalloc(sizeof(*hist_file), GFP_KERNEL);
 	if (!hist_file)
 		return -ENOMEM;
+
 	hist_file->file = file;
+	hist_file->last_act = get_hist_hit_count(event_file);
 
 	/* Clear private_data to avoid warning in single_open() */
 	file->private_data = NULL;
 	ret = single_open(file, hist_show, hist_file);
 	if (ret)
 		kfree(hist_file);
+
 	return ret;
 }
 

2.39.5

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

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

From: Tengda Wu <[email protected]>

[ Upstream commit 0b4ffbe4888a2c71185eaf5c1a02dd3586a9bc04 ]

The function event_{hist,hist_debug}_open() maintains the refcount of 'file->tr' and 'file' through tracing_open_file_tr(). However, it does not roll back these counts on subsequent failure paths, resulting in a refcount leak.

A very obvious case is that if the hist/hist_debug file belongs to a specific instance, the refcount leak will prevent the deletion of that instance, as it relies on the condition 'tr->ref == 1' within __remove_instance().

Fix this by calling tracing_release_file_tr() on all failure paths in event_{hist,hist_debug}_open() to correct the refcount.

---
 kernel/trace/trace_events_hist.c | 24 ++++++++++++++++++------
 1 file changed, 18 insertions(+), 6 deletions(-)

index e07d75adab8e3..4ebafc655223a 100644
@@ -5692,12 +5692,16 @@ static int event_hist_open(struct inode *inode, struct file *file)
 	guard(mutex)(&event_mutex);
 
 	event_file = event_file_data(file);
-	if (!event_file)
-		return -ENODEV;
+	if (!event_file) {
+		ret = -ENODEV;
+		goto err;
+	}
 
 	hist_file = kzalloc(sizeof(*hist_file), GFP_KERNEL);
-	if (!hist_file)
-		return -ENOMEM;
+	if (!hist_file) {
+		ret = -ENOMEM;
+		goto err;
+	}
 
 	hist_file->file = file;
 	hist_file->last_act = get_hist_hit_count(event_file);

@@ -5705,9 +5709,14 @@ static int event_hist_open(struct inode *inode, struct file *file)
 	/* Clear private_data to avoid warning in single_open() */
 	file->private_data = NULL;
 	ret = single_open(file, hist_show, hist_file);
-	if (ret)
+	if (ret) {
 		kfree(hist_file);
+		goto err;
+	}
 
+	return 0;
+err:
+	tracing_release_file_tr(inode, file);
 	return ret;
 }
 

@@ -5982,7 +5991,10 @@ static int event_hist_debug_open(struct inode *inode, struct file *file)
 
 	/* Clear private_data to avoid warning in single_open() */
 	file->private_data = NULL;
-	return single_open(file, hist_debug_show, file);
+	ret = single_open(file, hist_debug_show, file);
+	if (ret)
+		tracing_release_file_tr(inode, file);
+	return ret;
 }
 
 const struct file_operations event_hist_debug_fops = {

2.39.5

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

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

From: Dragan Simic <[email protected]>

[ Upstream commit ffcef3df680c437ca33ff434be18ec24d72907c2 ]

Add missing "vpcie0v9-supply" and "vpcie1v8-supply" properties to the "pcie0" node in the Pine64 RockPro64 board dtsi file. This eliminates the following warnings from the kernel log:

rockchip-pcie f8000000.pcie: supply vpcie1v8 not found, using dummy regulator rockchip-pcie f8000000.pcie: supply vpcie0v9 not found, using dummy regulator

These additions improve the accuracy of hardware description of the RockPro64 and, in theory, they should result in no functional changes to the way board works after the changes, because the "vcca_0v9" and "vcca_1v8" regulators are always enabled. [1][2] However, extended reliability testing, performed by Chris, [3] has proven that the age-old issues with some PCI Express cards, when used with a Pine64 RockPro64, are also resolved.

Those issues were already mentioned in the commit 43853e843aa6 (arm64: dts:
rockchip: Remove unsupported node from the Pinebook Pro dts, 2024-04-01), together with a brief description of the out-of-tree enumeration delay patch that reportedly resolves those issues. In a nutshell, booting a RockPro64 with some PCI Express cards attached to it caused a kernel oops. [4]

Symptomatically enough, to the commit author's best knowledge, only the Pine64 RockPro64, out of all RK3399-based boards and devices supported upstream, has been reported to suffer from those PCI Express issues, and only the RockPro64 had some of the PCI Express supplies missing in its DT. Thus, perhaps some weird timing issues exist that caused the "vcca_1v8" always-on regulator, which is part of the RK808 PMIC, to actually not be enabled before the PCI Express is initialized and enumerated on the RockPro64, causing oopses with some PCIe cards, and the aforementioned enumeration delay patch [4] probably acted as just a workaround for the underlying timing issue.

Admittedly, the Pine64 RockPro64 is a bit specific board by having a standard PCI Express slot, allowing use of various standard cards, but pretty much standard PCI Express cards have been attached to other RK3399 boards as well, and the commit author is unaware ot such issues reported for them.

It's quite hard to be sure that the PCI Express issues are fully resolved by these additions to the DT, without some really extensive and time-consuming testing. However, these additions to the DT can result in good things and improvements anyway, making them perfectly safe from the standpoint of being unable to do any harm or cause some unforeseen regressions.

These changes apply to the both supported hardware revisions of the Pine64 RockPro64, i.e. to the production-run revisions 2.0 and 2.1. [1][2]

[1] https://files.pine64.org/doc/rockpro64/rockpro64_v21-SCH.pdf
[2] https://files.pine64.org/doc/rockpro64/rockpro64_v20-SCH.pdf
[3] https://z9.de/hedgedoc/s/nF4d5G7rg#reboot-tests-for-PCIe-improvements
[4] https://lore.kernel.org/lkml/[email protected]/T/#u

---
 arch/arm64/boot/dts/rockchip/rk3399-rockpro64.dtsi | 2 ++
 1 file changed, 2 insertions(+)

index 11d99d8b34a2b..fd8296c1d3fad 100644
@@ -661,6 +661,8 @@ &pcie0 {
 	num-lanes = <4>;
 	pinctrl-names = "default";
 	pinctrl-0 = <&pcie_perst>;
+	vpcie0v9-supply = <&vcca_0v9>;
+	vpcie1v8-supply = <&vcca_1v8>;
 	vpcie12v-supply = <&vcc12v_dcin>;
 	vpcie3v3-supply = <&vcc3v3_pcie>;
 	status = "okay";

2.39.5

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

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

From: Joshua Hahn <[email protected]>

[ Upstream commit aefa398d93d5db7c555be78a605ff015357f127d ]

Cgroup-level CPU statistics currently include time spent on user/system processes, but do not include niced CPU time (despite already being tracked). This patch exposes niced CPU time to the userspace, allowing users to get a better understanding of their hardware limits and can facilitate more informed workload distribution.

A new field 'ntime' is added to struct cgroup_base_stat as opposed to struct task_cputime to minimize footprint.

Stable-dep-of: c4af66a95aa3 ("cgroup/rstat: Fix forceidle time in cpu.stat")

---
 include/linux/cgroup-defs.h |  1 +
 kernel/cgroup/rstat.c       | 19 ++++++++++++++-----
 2 files changed, 15 insertions(+), 5 deletions(-)

index a32eebcd23da4..38b2af336e4a0 100644
@@ -324,6 +324,7 @@ struct cgroup_base_stat {
 #ifdef CONFIG_SCHED_CORE
 	u64 forceidle_sum;
 #endif
+	u64 ntime;
 };
 
 /*

index ce295b73c0a36..aac91466279f1 100644
@@ -444,6 +444,7 @@ static void cgroup_base_stat_add(struct cgroup_base_stat *dst_bstat,
 #ifdef CONFIG_SCHED_CORE
 	dst_bstat->forceidle_sum += src_bstat->forceidle_sum;
 #endif
+	dst_bstat->ntime += src_bstat->ntime;
 }
 
 static void cgroup_base_stat_sub(struct cgroup_base_stat *dst_bstat,

@@ -455,6 +456,7 @@ static void cgroup_base_stat_sub(struct cgroup_base_stat *dst_bstat,
 #ifdef CONFIG_SCHED_CORE
 	dst_bstat->forceidle_sum -= src_bstat->forceidle_sum;
 #endif
+	dst_bstat->ntime -= src_bstat->ntime;
 }
 
 static void cgroup_base_stat_flush(struct cgroup *cgrp, int cpu)

@@ -534,8 +536,10 @@ void __cgroup_account_cputime_field(struct cgroup *cgrp,
 	rstatc = cgroup_base_stat_cputime_account_begin(cgrp, &flags);
 
 	switch (index) {
-	case CPUTIME_USER:
 	case CPUTIME_NICE:
+		rstatc->bstat.ntime += delta_exec;
+		fallthrough;
+	case CPUTIME_USER:
 		rstatc->bstat.cputime.utime += delta_exec;
 		break;
 	case CPUTIME_SYSTEM:

@@ -590,6 +594,7 @@ static void root_cgroup_cputime(struct cgroup_base_stat *bstat)
 #ifdef CONFIG_SCHED_CORE
 		bstat->forceidle_sum += cpustat[CPUTIME_FORCEIDLE];
 #endif
+		bstat->ntime += cpustat[CPUTIME_NICE];
 	}
 }
 

@@ -607,13 +612,14 @@ static void cgroup_force_idle_show(struct seq_file *seq, struct cgroup_base_stat
 void cgroup_base_stat_cputime_show(struct seq_file *seq)
 {
 	struct cgroup *cgrp = seq_css(seq)->cgroup;
-	u64 usage, utime, stime;
+	u64 usage, utime, stime, ntime;
 
 	if (cgroup_parent(cgrp)) {
 		cgroup_rstat_flush_hold(cgrp);
 		usage = cgrp->bstat.cputime.sum_exec_runtime;
 		cputime_adjust(&cgrp->bstat.cputime, &cgrp->prev_cputime,
 			       &utime, &stime);
+		ntime = cgrp->bstat.ntime;
 		cgroup_rstat_flush_release(cgrp);
 	} else {
 		/* cgrp->bstat of root is not actually used, reuse it */

@@ -621,16 +627,19 @@ void cgroup_base_stat_cputime_show(struct seq_file *seq)
 		usage = cgrp->bstat.cputime.sum_exec_runtime;
 		utime = cgrp->bstat.cputime.utime;
 		stime = cgrp->bstat.cputime.stime;
+		ntime = cgrp->bstat.ntime;
 	}
 
 	do_div(usage, NSEC_PER_USEC);
 	do_div(utime, NSEC_PER_USEC);
 	do_div(stime, NSEC_PER_USEC);
+	do_div(ntime, NSEC_PER_USEC);
 
 	seq_printf(seq, "usage_usec %llu\n"
-		   "user_usec %llu\n"
-		   "system_usec %llu\n",
-		   usage, utime, stime);
+			"user_usec %llu\n"
+			"system_usec %llu\n"
+			"nice_usec %llu\n",
+			usage, utime, stime, ntime);
 
 	cgroup_force_idle_show(seq, &cgrp->bstat);
 }

2.39.5

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

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

From: Abel Wu <[email protected]>

[ Upstream commit c4af66a95aa3bc1d4f607ebd4eea524fb58946e3 ]

The commit b824766504e4 ("cgroup/rstat: add force idle show helper") retrieves forceidle_time outside cgroup_rstat_lock for non-root cgroups which can be potentially inconsistent with other stats.

Rather than reverting that commit, fix it in a way that retains the effort of cleaning up the ifdef-messes.

---
 kernel/cgroup/rstat.c | 29 +++++++++++++----------------
 1 file changed, 13 insertions(+), 16 deletions(-)

index aac91466279f1..3e01781aeb7bd 100644
@@ -612,36 +612,33 @@ static void cgroup_force_idle_show(struct seq_file *seq, struct cgroup_base_stat
 void cgroup_base_stat_cputime_show(struct seq_file *seq)
 {
 	struct cgroup *cgrp = seq_css(seq)->cgroup;
-	u64 usage, utime, stime, ntime;
+	struct cgroup_base_stat bstat;
 
 	if (cgroup_parent(cgrp)) {
 		cgroup_rstat_flush_hold(cgrp);
-		usage = cgrp->bstat.cputime.sum_exec_runtime;
+		bstat = cgrp->bstat;
 		cputime_adjust(&cgrp->bstat.cputime, &cgrp->prev_cputime,
-			       &utime, &stime);
-		ntime = cgrp->bstat.ntime;
+			       &bstat.cputime.utime, &bstat.cputime.stime);
 		cgroup_rstat_flush_release(cgrp);
 	} else {
-		/* cgrp->bstat of root is not actually used, reuse it */
-		root_cgroup_cputime(&cgrp->bstat);
-		usage = cgrp->bstat.cputime.sum_exec_runtime;
-		utime = cgrp->bstat.cputime.utime;
-		stime = cgrp->bstat.cputime.stime;
-		ntime = cgrp->bstat.ntime;
+		root_cgroup_cputime(&bstat);
 	}
 
-	do_div(usage, NSEC_PER_USEC);
-	do_div(utime, NSEC_PER_USEC);
-	do_div(stime, NSEC_PER_USEC);
-	do_div(ntime, NSEC_PER_USEC);
+	do_div(bstat.cputime.sum_exec_runtime, NSEC_PER_USEC);
+	do_div(bstat.cputime.utime, NSEC_PER_USEC);
+	do_div(bstat.cputime.stime, NSEC_PER_USEC);
+	do_div(bstat.ntime, NSEC_PER_USEC);
 
 	seq_printf(seq, "usage_usec %llu\n"
 			"user_usec %llu\n"
 			"system_usec %llu\n"
 			"nice_usec %llu\n",
-			usage, utime, stime, ntime);
+			bstat.cputime.sum_exec_runtime,
+			bstat.cputime.utime,
+			bstat.cputime.stime,
+			bstat.ntime);
 
-	cgroup_force_idle_show(seq, &cgrp->bstat);
+	cgroup_force_idle_show(seq, &bstat);
 }
 
 /* Add bpf kfuncs for cgroup_rstat_updated() and cgroup_rstat_flush() */

2.39.5

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

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

From: Sherry Sun <[email protected]>

[ Upstream commit b6a8f6ab2c53e5ea3c7f2a3978db378a89bb7595 ]

Use u32 and u8 rather than unsigned long or unsigned char for register variables for clarity and consistency.

Stable-dep-of: e98ab45ec518 ("tty: serial: lpuart: only disable CTS instead of overwriting the whole UARTMODIR register")

---
 drivers/tty/serial/fsl_lpuart.c | 93 ++++++++++++++++-----------------
 1 file changed, 46 insertions(+), 47 deletions(-)

index 9f9fc733eb2c1..e86fb9c60f1c3 100644
@@ -440,7 +440,7 @@ static unsigned int lpuart_get_baud_clk_rate(struct lpuart_port *sport)
 
 static void lpuart_stop_tx(struct uart_port *port)
 {
-	unsigned char temp;
+	u8 temp;
 
 	temp = readb(port->membase + UARTCR2);
 	temp &= ~(UARTCR2_TIE | UARTCR2_TCIE);

@@ -449,7 +449,7 @@ static void lpuart_stop_tx(struct uart_port *port)
 
 static void lpuart32_stop_tx(struct uart_port *port)
 {
-	unsigned long temp;
+	u32 temp;
 
 	temp = lpuart32_read(port, UARTCTRL);
 	temp &= ~(UARTCTRL_TIE | UARTCTRL_TCIE);

@@ -458,7 +458,7 @@ static void lpuart32_stop_tx(struct uart_port *port)
 
 static void lpuart_stop_rx(struct uart_port *port)
 {
-	unsigned char temp;
+	u8 temp;
 
 	temp = readb(port->membase + UARTCR2);
 	writeb(temp & ~UARTCR2_RE, port->membase + UARTCR2);

@@ -466,7 +466,7 @@ static void lpuart_stop_rx(struct uart_port *port)
 
 static void lpuart32_stop_rx(struct uart_port *port)
 {
-	unsigned long temp;
+	u32 temp;
 
 	temp = lpuart32_read(port, UARTCTRL);
 	lpuart32_write(port, temp & ~UARTCTRL_RE, UARTCTRL);

@@ -641,7 +641,7 @@ static int lpuart_poll_init(struct uart_port *port)
 	struct lpuart_port *sport = container_of(port,
 					struct lpuart_port, port);
 	unsigned long flags;
-	unsigned char temp;
+	u8 temp;
 
 	sport->port.fifosize = 0;
 

@@ -751,7 +751,7 @@ static inline void lpuart_transmit_buffer(struct lpuart_port *sport)
 static inline void lpuart32_transmit_buffer(struct lpuart_port *sport)
 {
 	struct tty_port *tport = &sport->port.state->port;
-	unsigned long txcnt;
+	u32 txcnt;
 	unsigned char c;
 
 	if (sport->port.x_char) {

@@ -788,7 +788,7 @@ static void lpuart_start_tx(struct uart_port *port)
 {
 	struct lpuart_port *sport = container_of(port,
 			struct lpuart_port, port);
-	unsigned char temp;
+	u8 temp;
 
 	temp = readb(port->membase + UARTCR2);
 	writeb(temp | UARTCR2_TIE, port->membase + UARTCR2);

@@ -805,7 +805,7 @@ static void lpuart_start_tx(struct uart_port *port)
 static void lpuart32_start_tx(struct uart_port *port)
 {
 	struct lpuart_port *sport = container_of(port, struct lpuart_port, port);
-	unsigned long temp;
+	u32 temp;
 
 	if (sport->lpuart_dma_tx_use) {
 		if (!lpuart_stopped_or_empty(port))

@@ -838,8 +838,8 @@ static unsigned int lpuart_tx_empty(struct uart_port *port)
 {
 	struct lpuart_port *sport = container_of(port,
 			struct lpuart_port, port);
-	unsigned char sr1 = readb(port->membase + UARTSR1);
-	unsigned char sfifo = readb(port->membase + UARTSFIFO);
+	u8 sr1 = readb(port->membase + UARTSR1);
+	u8 sfifo = readb(port->membase + UARTSFIFO);
 
 	if (sport->dma_tx_in_progress)
 		return 0;

@@ -854,9 +854,9 @@ static unsigned int lpuart32_tx_empty(struct uart_port *port)
 {
 	struct lpuart_port *sport = container_of(port,
 			struct lpuart_port, port);
-	unsigned long stat = lpuart32_read(port, UARTSTAT);
-	unsigned long sfifo = lpuart32_read(port, UARTFIFO);
-	unsigned long ctrl = lpuart32_read(port, UARTCTRL);
+	u32 stat = lpuart32_read(port, UARTSTAT);
+	u32 sfifo = lpuart32_read(port, UARTFIFO);
+	u32 ctrl = lpuart32_read(port, UARTCTRL);
 
 	if (sport->dma_tx_in_progress)
 		return 0;

@@ -883,7 +883,7 @@ static void lpuart_rxint(struct lpuart_port *sport)
 {
 	unsigned int flg, ignored = 0, overrun = 0;
 	struct tty_port *port = &sport->port.state->port;
-	unsigned char rx, sr;
+	u8 rx, sr;
 
 	uart_port_lock(&sport->port);
 

@@ -960,7 +960,7 @@ static void lpuart32_rxint(struct lpuart_port *sport)
 {
 	unsigned int flg, ignored = 0;
 	struct tty_port *port = &sport->port.state->port;
-	unsigned long rx, sr;
+	u32 rx, sr;
 	bool is_break;
 
 	uart_port_lock(&sport->port);

@@ -1038,7 +1038,7 @@ static void lpuart32_rxint(struct lpuart_port *sport)
 static irqreturn_t lpuart_int(int irq, void *dev_id)
 {
 	struct lpuart_port *sport = dev_id;
-	unsigned char sts;
+	u8 sts;
 
 	sts = readb(sport->port.membase + UARTSR1);
 

@@ -1112,7 +1112,7 @@ static void lpuart_copy_rx_to_tty(struct lpuart_port *sport)
 	int count, copied;
 
 	if (lpuart_is_32(sport)) {
-		unsigned long sr = lpuart32_read(&sport->port, UARTSTAT);
+		u32 sr = lpuart32_read(&sport->port, UARTSTAT);
 
 		if (sr & (UARTSTAT_PE | UARTSTAT_FE)) {
 			/* Clear the error flags */

@@ -1124,10 +1124,10 @@ static void lpuart_copy_rx_to_tty(struct lpuart_port *sport)
 				sport->port.icount.frame++;
 		}
 	} else {
-		unsigned char sr = readb(sport->port.membase + UARTSR1);
+		u8 sr = readb(sport->port.membase + UARTSR1);
 
 		if (sr & (UARTSR1_PE | UARTSR1_FE)) {
-			unsigned char cr2;
+			u8 cr2;
 
 			/* Disable receiver during this operation... */
 			cr2 = readb(sport->port.membase + UARTCR2);

@@ -1278,7 +1278,7 @@ static void lpuart32_dma_idleint(struct lpuart_port *sport)
 static irqreturn_t lpuart32_int(int irq, void *dev_id)
 {
 	struct lpuart_port *sport = dev_id;
-	unsigned long sts, rxcount;
+	u32 sts, rxcount;
 
 	sts = lpuart32_read(&sport->port, UARTSTAT);
 	rxcount = lpuart32_read(&sport->port, UARTWATER);

@@ -1410,12 +1410,12 @@ static inline int lpuart_start_rx_dma(struct lpuart_port *sport)
 	dma_async_issue_pending(chan);
 
 	if (lpuart_is_32(sport)) {
-		unsigned long temp = lpuart32_read(&sport->port, UARTBAUD);
+		u32 temp = lpuart32_read(&sport->port, UARTBAUD);
 
 		lpuart32_write(&sport->port, temp | UARTBAUD_RDMAE, UARTBAUD);
 
 		if (sport->dma_idle_int) {
-			unsigned long ctrl = lpuart32_read(&sport->port, UARTCTRL);
+			u32 ctrl = lpuart32_read(&sport->port, UARTCTRL);
 
 			lpuart32_write(&sport->port, ctrl | UARTCTRL_ILIE, UARTCTRL);
 		}