6.11.3-rc1 review

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

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

From: Luo Gengkun <[email protected]>

commit 62c0b1061593d7012292f781f11145b2d46f43ab upstream.

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

Here are some tests and analyzes:
before:

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

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

after:

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

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

test.c

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

        return 0;
}

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

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

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

@@ -4097,7 +4097,11 @@ static void perf_adjust_period(struct pe
 	period = perf_calculate_period(event, nsec, count);
 
 	delta = (s64)(period - hwc->sample_period);
-	delta = (delta + 7) / 8; /* low pass filter */
+	if (delta >= 0)
+		delta += 7;
+	else
+		delta -= 7;
+	delta /= 8; /* low pass filter */
 
 	sample_period = hwc->sample_period + delta;
 

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

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

From: Tvrtko Ursulin <[email protected]>

commit f32b5128d2c440368b5bf3a7a356823e235caabb upstream.

Check that the number of perfmons userspace is passing in the copy and reset extensions is not greater than the internal kernel storage where the ids will be copied into.

---
 drivers/gpu/drm/v3d/v3d_submit.c |    6 ++++++
 1 file changed, 6 insertions(+)

@@ -671,6 +671,9 @@ v3d_get_cpu_reset_performance_params(str
 	if (reset.nperfmons > V3D_MAX_PERFMONS)
 		return -EINVAL;
 
+	if (reset.nperfmons > V3D_MAX_PERFMONS)
+		return -EINVAL;
+
 	job->job_type = V3D_CPU_JOB_TYPE_RESET_PERFORMANCE_QUERY;
 
 	job->performance_query.queries = kvmalloc_array(reset.count,

@@ -753,6 +756,9 @@ v3d_get_cpu_copy_performance_query_param
 		return -EINVAL;
 
 	if (copy.nperfmons > V3D_MAX_PERFMONS)
+		return -EINVAL;
+
+	if (copy.nperfmons > V3D_MAX_PERFMONS)
 		return -EINVAL;
 
 	job->job_type = V3D_CPU_JOB_TYPE_COPY_PERFORMANCE_QUERY;

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

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

From: Helge Deller <[email protected]>

commit 9542130937e9dc707dd7c6b7af73326437da2d50 upstream.

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

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

@@ -1051,8 +1051,7 @@ ENTRY_CFI(intr_save)		/* for os_hpmc */
 	STREG           %r16, PT_ISR(%r29)
 	STREG           %r17, PT_IOR(%r29)
 
-#if 0 && defined(CONFIG_64BIT)
-	/* Revisit when we have 64-bit code above 4Gb */
+#if defined(CONFIG_64BIT)
 	b,n		intr_save2
 
 skip_save_ior:

@@ -1060,8 +1059,7 @@ skip_save_ior:
 	 * need to adjust iasq/iaoq here in the same way we adjusted isr/ior
 	 * above.
 	 */
-	extrd,u,*	%r8,PSW_W_BIT,1,%r1
-	cmpib,COND(=),n	1,%r1,intr_save2
+	bb,COND(>=),n	%r8,PSW_W_BIT,intr_save2
 	LDREG		PT_IASQ0(%r29), %r16
 	LDREG		PT_IAOQ0(%r29), %r17
 	/* adjust iasq/iaoq */

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

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

From: Javier Carrasco <[email protected]>

commit 5beb6fba25db235b52eab34bde8112f07bb31d75 upstream.

Error paths that exit for_each_child_of_node() need to call of_node_put() to decerement the child refcount and avoid memory leaks.

Add the missing of_node_put().

---
 drivers/gpu/drm/mediatek/mtk_disp_ovl_adaptor.c |    4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

@@ -523,8 +523,10 @@ static int ovl_adaptor_comp_init(struct
 		}
 
 		comp_pdev = of_find_device_by_node(node);
-		if (!comp_pdev)
+		if (!comp_pdev) {
+			of_node_put(node);
 			return -EPROBE_DEFER;
+		}
 
 		priv->ovl_adaptor_comp[id] = &comp_pdev->dev;
 

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

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

From: Thomas Zimmermann <[email protected]>

commit 8b0d2f61545545ab5eef923ed6e59fc3be2385e0 upstream.

FB_DAMAGE_CLIPS is a plane property for damage handling. Its UAPI should only use UAPI types. Hence replace struct drm_rect with struct drm_mode_rect in drm_atomic_plane_set_property(). Both types are identical in practice, so there's no change in behavior.

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

@@ -543,7 +543,7 @@ static int drm_atomic_plane_set_property
 					&state->fb_damage_clips,
 					val,
 					-1,
-					sizeof(struct drm_rect),
+					sizeof(struct drm_mode_rect),
 					&replaced);
 		return ret;
 	} else if (property == plane->scaling_filter_property) {

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

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

From: Baojun Xu <[email protected]>

commit 49f5ee951f11f4d6a124f00f71b2590507811a55 upstream.

Add new vendor_id and subsystem_id in quirk for Lenovo Y990 Laptop.

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

@@ -10892,6 +10892,7 @@ static const struct snd_pci_quirk alc269
 	SND_PCI_QUIRK(0x17aa, 0x38cd, "Y790 VECO DUAL", ALC287_FIXUP_TAS2781_I2C),
 	SND_PCI_QUIRK(0x17aa, 0x38d2, "Lenovo Yoga 9 14IMH9", ALC287_FIXUP_YOGA9_14IMH9_BASS_SPK_PIN),
 	SND_PCI_QUIRK(0x17aa, 0x38d7, "Lenovo Yoga 9 14IMH9", ALC287_FIXUP_YOGA9_14IMH9_BASS_SPK_PIN),
+	SND_PCI_QUIRK(0x17aa, 0x38df, "Y990 YG DUAL", ALC287_FIXUP_TAS2781_I2C),
 	SND_PCI_QUIRK(0x17aa, 0x38f9, "Thinkbook 16P Gen5", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x17aa, 0x38fa, "Thinkbook 16P Gen5", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x17aa, 0x3902, "Lenovo E50-80", ALC269_FIXUP_DMIC_THINKPAD_ACPI),

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

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

From: Jaroslav Kysela <[email protected]>

commit d278a9de5e1837edbe57b2f1f95a104ff6c84846 upstream.

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

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

@@ -654,13 +654,19 @@ void snd_card_free(struct snd_card *card
 }
 EXPORT_SYMBOL(snd_card_free);
 
+/* check, if the character is in the valid ASCII range */
+static inline bool safe_ascii_char(char c)
+{
+	return isascii(c) && isalnum(c);
+}
+
 /* retrieve the last word of shortname or longname */
 static const char *retrieve_id_from_card_name(const char *name)
 {
 	const char *spos = name;
 
 	while (*name) {
-		if (isspace(*name) && isalnum(name[1]))
+		if (isspace(*name) && safe_ascii_char(name[1]))
 			spos = name + 1;
 		name++;
 	}

@@ -687,12 +693,12 @@ static void copy_valid_id_string(struct
 {
 	char *id = card->id;
 
-	while (*nid && !isalnum(*nid))
+	while (*nid && !safe_ascii_char(*nid))
 		nid++;
 	if (isdigit(*nid))
 		*id++ = isalpha(*src) ? *src : 'D';
 	while (*nid && (size_t)(id - card->id) < sizeof(card->id) - 1) {
-		if (isalnum(*nid))
+		if (safe_ascii_char(*nid))
 			*id++ = *nid;
 		nid++;
 	}

@@ -787,7 +793,7 @@ static ssize_t id_store(struct device *d
 
 	for (idx = 0; idx < copy; idx++) {
 		c = buf[idx];
-		if (!isalnum(c) && c != '_' && c != '-')
+		if (!safe_ascii_char(c) && c != '_' && c != '-')
 			return -EINVAL;
 	}
 	memcpy(buf1, buf, copy);

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

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

From: Lianqin Hu <[email protected]>

commit 73385f3e0d8088b715ae8f3f66d533c482a376ab upstream.

Audio control requests that sets sampling frequency sometimes fail on this card. Adding delay between control messages eliminates that problem.

---
 sound/usb/quirks.c |    2 ++
 1 file changed, 2 insertions(+)

@@ -2279,6 +2279,8 @@ static const struct usb_audio_quirk_flag
 		   QUIRK_FLAG_GENERIC_IMPLICIT_FB),
 	DEVICE_FLG(0x2b53, 0x0031, /* Fiero SC-01 (firmware v1.1.0) */
 		   QUIRK_FLAG_GENERIC_IMPLICIT_FB),
+	DEVICE_FLG(0x2d95, 0x8011, /* VIVO USB-C HEADSET */
+		   QUIRK_FLAG_CTL_MSG_DELAY_1M),
 	DEVICE_FLG(0x2d95, 0x8021, /* VIVO USB-C-XE710 HEADSET */
 		   QUIRK_FLAG_CTL_MSG_DELAY_1M),
 	DEVICE_FLG(0x30be, 0x0101, /* Schiit Hel */

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

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

From: Jan Lalinsky <[email protected]>

commit 6b0bde5d8d4078ca5feec72fd2d828f0e5cf115d upstream.

Add native DSD support for Luxman D-08u DAC, by adding the PID/VID 1852:5062. This makes DSD playback work, and also sound quality when playing PCM files is improved, crackling sounds are gone.

---
 sound/usb/quirks.c |    2 ++
 1 file changed, 2 insertions(+)

@@ -2221,6 +2221,8 @@ static const struct usb_audio_quirk_flag
 		   QUIRK_FLAG_DISABLE_AUTOSUSPEND),
 	DEVICE_FLG(0x17aa, 0x104d, /* Lenovo ThinkStation P620 Internal Speaker + Front Headset */
 		   QUIRK_FLAG_DISABLE_AUTOSUSPEND),
+	DEVICE_FLG(0x1852, 0x5062, /* Luxman D-08u */
+		   QUIRK_FLAG_ITF_USB_DSD_DAC | QUIRK_FLAG_CTL_MSG_DELAY),
 	DEVICE_FLG(0x1852, 0x5065, /* Luxman DA-06 */
 		   QUIRK_FLAG_ITF_USB_DSD_DAC | QUIRK_FLAG_CTL_MSG_DELAY),
 	DEVICE_FLG(0x1901, 0x0191, /* GE B850V3 CP2114 audio interface */

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

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

From: Hans P. Moller <[email protected]>

commit 703235a244e533652346844cfa42623afb36eed1 upstream.

Add hw monitor volume control for POD HD500X. This is done adding LINE6_CAP_HWMON_CTL to the capabilities

---
 sound/usb/line6/podhd.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -507,7 +507,7 @@ static const struct line6_properties pod
 	[LINE6_PODHD500X] = {
 		.id = "PODHD500X",
 		.name = "POD HD500X",
-		.capabilities	= LINE6_CAP_CONTROL
+		.capabilities	= LINE6_CAP_CONTROL | LINE6_CAP_HWMON_CTL
 				| LINE6_CAP_PCM | LINE6_CAP_HWMON,
 		.altsetting = 1,
 		.ep_ctrl_r = 0x81,

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

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

From: Nikolai Afanasenkov <[email protected]>

commit cb2deca056d579fe008c8d0a4ceb04d2b368fe42 upstream.

The HP Elite mt645 G8 Mobile Thin Client uses an ALC236 codec and needs the ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF quirk to enable the mute and micmute LED functionality.

This patch adds the system ID of the HP Elite mt645 G8 to the alc269_fixup_tbl in patch_realtek.c to enable the required quirk.

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

@@ -10529,6 +10529,7 @@ static const struct snd_pci_quirk alc269
 	SND_PCI_QUIRK(0x103c, 0x8ca2, "HP ZBook Power", ALC236_FIXUP_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8ca4, "HP ZBook Fury", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8ca7, "HP ZBook Fury", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
+	SND_PCI_QUIRK(0x103c, 0x8caf, "HP Elite mt645 G8 Mobile Thin Client", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF),
 	SND_PCI_QUIRK(0x103c, 0x8cbd, "HP Pavilion Aero Laptop 13-bg0xxx", ALC245_FIXUP_HP_X360_MUTE_LEDS),
 	SND_PCI_QUIRK(0x103c, 0x8cdd, "HP Spectre", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x103c, 0x8cde, "HP Spectre", ALC287_FIXUP_CS35L41_I2C_2),

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

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

From: Ai Chao <[email protected]>

commit dee476950cbd83125655a3f49e00d63b79f6114e upstream.

The headset mic requires a fixup to be properly detected/used.

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

@@ -10930,6 +10930,7 @@ static const struct snd_pci_quirk alc269
 	SND_PCI_QUIRK(0x1854, 0x048a, "LG gram 17 (17ZD90R)", ALC298_FIXUP_SAMSUNG_AMP_V2_4_AMPS),
 	SND_PCI_QUIRK(0x19e5, 0x3204, "Huawei MACH-WX9", ALC256_FIXUP_HUAWEI_MACH_WX9_PINS),
 	SND_PCI_QUIRK(0x19e5, 0x320f, "Huawei WRT-WX9 ", ALC256_FIXUP_ASUS_MIC_NO_PRESENCE),
+	SND_PCI_QUIRK(0x19e5, 0x3212, "Huawei KLV-WX9 ", ALC256_FIXUP_ACER_HEADSET_MIC),
 	SND_PCI_QUIRK(0x1b35, 0x1235, "CZC B20", ALC269_FIXUP_CZC_B20),
 	SND_PCI_QUIRK(0x1b35, 0x1236, "CZC TMI", ALC269_FIXUP_CZC_TMI),
 	SND_PCI_QUIRK(0x1b35, 0x1237, "CZC L101", ALC269_FIXUP_CZC_L101),

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

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

From: Abhishek Tamboli <[email protected]>

commit d75dba49744478c32f6ce1c16b5f391c2d5cef5f upstream.

Add the quirk for HP Pavilion Gaming laptop 15z-ec200 for enabling the mute led. The fix apply the ALC285_FIXUP_HP_MUTE_LED quirk for this model.

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

@@ -10388,6 +10388,7 @@ static const struct snd_pci_quirk alc269
 	SND_PCI_QUIRK(0x103c, 0x8896, "HP EliteBook 855 G8 Notebook PC", ALC285_FIXUP_HP_MUTE_LED),
 	SND_PCI_QUIRK(0x103c, 0x8898, "HP EliteBook 845 G8 Notebook PC", ALC285_FIXUP_HP_LIMIT_INT_MIC_BOOST),
 	SND_PCI_QUIRK(0x103c, 0x88d0, "HP Pavilion 15-eh1xxx (mainboard 88D0)", ALC287_FIXUP_HP_GPIO_LED),
+	SND_PCI_QUIRK(0x103c, 0x88dd, "HP Pavilion 15z-ec200", ALC285_FIXUP_HP_MUTE_LED),
 	SND_PCI_QUIRK(0x103c, 0x8902, "HP OMEN 16", ALC285_FIXUP_HP_MUTE_LED),
 	SND_PCI_QUIRK(0x103c, 0x890e, "HP 255 G8 Notebook PC", ALC236_FIXUP_HP_MUTE_LED_COEFBIT2),
 	SND_PCI_QUIRK(0x103c, 0x8919, "HP Pavilion Aero Laptop 13-be0xxx", ALC287_FIXUP_HP_GPIO_LED),

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

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

From: Edward Adam Davis <[email protected]>

commit 1a00a393d6a7fb1e745a41edd09019bd6a0ad64c upstream.

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

@@ -2001,7 +2001,7 @@ static struct ext4_dir_entry_2 *do_split
 		split = count/2;
 
 	hash2 = map[split].hash;
-	continued = hash2 == map[split - 1].hash;
+	continued = split > 0 ? hash2 == map[split - 1].hash : 0;
 	dxtrace(printk(KERN_INFO "Split block %lu at %x, %i/%i\n",
 			(unsigned long)dx_get_block(frame->at),
 					hash2, split, count-split));

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

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

From: yao.ly <[email protected]>

commit 70dd7b573afeba9b8f8a33f2ae1e4a9a2ec8c1ec upstream.

EXT4_DIRENT_HASH and EXT4_DIRENT_MINOR_HASH will access struct ext4_dir_entry_hash followed ext4_dir_entry. But there is no ext4_dir_entry_hash followed when inode is encrypted and not casefolded

---
 fs/ext4/dir.c |   14 +++++++++++---
 1 file changed, 11 insertions(+), 3 deletions(-)

@@ -279,12 +279,20 @@ static int ext4_readdir(struct file *fil
 					struct fscrypt_str de_name =
 							FSTR_INIT(de->name,
 								de->name_len);
+					u32 hash;
+					u32 minor_hash;
+
+					if (IS_CASEFOLDED(inode)) {
+						hash = EXT4_DIRENT_HASH(de);
+						minor_hash = EXT4_DIRENT_MINOR_HASH(de);
+					} else {
+						hash = 0;
+						minor_hash = 0;
+					}
 
 					/* Directory is encrypted */
 					err = fscrypt_fname_disk_to_usr(inode,
-						EXT4_DIRENT_HASH(de),
-						EXT4_DIRENT_MINOR_HASH(de),
-						&de_name, &fstr);
+						hash, minor_hash, &de_name, &fstr);
 					de_name = fstr;
 					fstr.len = save_len;
 					if (err)

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

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

From: Baokun Li <[email protected]>

commit c26ab35702f8cd0cdc78f96aa5856bfb77be798f upstream.

We hit the following use-after-free:

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

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

[...]

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

[...]

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

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

The flow of issue triggering is as follows:

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

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

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

---
 fs/ext4/extents.c |   21 ++++++++++++++++++++-
 1 file changed, 20 insertions(+), 1 deletion(-)

@@ -3230,6 +3230,25 @@ static int ext4_split_extent_at(handle_t
 	if (err != -ENOSPC && err != -EDQUOT && err != -ENOMEM)
 		goto out;
 
+	/*
+	 * Update path is required because previous ext4_ext_insert_extent()
+	 * may have freed or reallocated the path. Using EXT4_EX_NOFAIL
+	 * guarantees that ext4_find_extent() will not return -ENOMEM,
+	 * otherwise -ENOMEM will cause a retry in do_writepages(), and a
+	 * WARN_ON may be triggered in ext4_da_update_reserve_space() due to
+	 * an incorrect ee_len causing the i_reserved_data_blocks exception.
+	 */
+	path = ext4_find_extent(inode, ee_block, ppath,
+				flags | EXT4_EX_NOFAIL);
+	if (IS_ERR(path)) {
+		EXT4_ERROR_INODE(inode, "Failed split extent on %u, err %ld",
+				 split, PTR_ERR(path));
+		return PTR_ERR(path);
+	}
+	depth = ext_depth(inode);
+	ex = path[depth].p_ext;
+	*ppath = path;
+
 	if (EXT4_EXT_MAY_ZEROOUT & split_flag) {
 		if (split_flag & (EXT4_EXT_DATA_VALID1|EXT4_EXT_DATA_VALID2)) {
 			if (split_flag & EXT4_EXT_DATA_VALID1) {

@@ -3282,7 +3301,7 @@ fix_extent_len:
 	ext4_ext_dirty(handle, inode, path + path->p_depth);
 	return err;
 out:
-	ext4_ext_show_leaf(inode, path);
+	ext4_ext_show_leaf(inode, *ppath);
 	return err;
 }
 

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

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

From: Baokun Li <[email protected]>

commit 369c944ed1d7c3fb7b35f24e4735761153afe7b3 upstream.

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

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

@@ -5553,6 +5553,7 @@ static int ext4_insert_range(struct file
 	path = ext4_find_extent(inode, offset_lblk, NULL, 0);
 	if (IS_ERR(path)) {
 		up_write(&EXT4_I(inode)->i_data_sem);
+		ret = PTR_ERR(path);
 		goto out_stop;
 	}
 

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

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

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

commit ebc4b2c1ac92fc0f8bf3f5a9c285a871d5084a6b upstream.

Function jbd2_journal_shrink_checkpoint_list() assumes that '0' is not a valid value for transaction IDs, which is incorrect.

Furthermore, the sbi->s_fc_ineligible_tid handling also makes the same assumption by being initialised to '0'. Fortunately, the sb flag EXT4_MF_FC_INELIGIBLE can be used to check whether sbi->s_fc_ineligible_tid has been previously set instead of comparing it with '0'.

---
 fs/ext4/fast_commit.c |   15 +++++++++++----
 1 file changed, 11 insertions(+), 4 deletions(-)

@@ -339,22 +339,29 @@ void ext4_fc_mark_ineligible(struct supe
 {
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	tid_t tid;
+	bool has_transaction = true;
+	bool is_ineligible;
 
 	if (ext4_fc_disabled(sb))
 		return;
 
-	ext4_set_mount_flag(sb, EXT4_MF_FC_INELIGIBLE);
 	if (handle && !IS_ERR(handle))
 		tid = handle->h_transaction->t_tid;
 	else {
 		read_lock(&sbi->s_journal->j_state_lock);
-		tid = sbi->s_journal->j_running_transaction ?
-				sbi->s_journal->j_running_transaction->t_tid : 0;
+		if (sbi->s_journal->j_running_transaction)
+			tid = sbi->s_journal->j_running_transaction->t_tid;
+		else
+			has_transaction = false;
 		read_unlock(&sbi->s_journal->j_state_lock);
 	}
 	spin_lock(&sbi->s_fc_lock);
-	if (tid_gt(tid, sbi->s_fc_ineligible_tid))
+	is_ineligible = ext4_test_mount_flag(sb, EXT4_MF_FC_INELIGIBLE);
+	if (has_transaction &&
+	    (!is_ineligible ||
+	     (is_ineligible && tid_gt(tid, sbi->s_fc_ineligible_tid))))
 		sbi->s_fc_ineligible_tid = tid;
+	ext4_set_mount_flag(sb, EXT4_MF_FC_INELIGIBLE);
 	spin_unlock(&sbi->s_fc_lock);
 	WARN_ON(reason >= EXT4_FC_REASON_MAX);
 	sbi->s_fc_stats.fc_ineligible_reason_count[reason]++;

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

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

From: Zhihao Cheng <[email protected]>

commit dda898d7ffe85931f9cca6d702a51f33717c501e upstream.

The dax_iomap_rw() does two things in each iteration: map written blocks and copy user data to blocks. If the process is killed by user(See signal handling in dax_iomap_iter()), the copied data will be returned and added on inode size, which means that the length of written extents may exceed the inode size, then fsck will fail. An example is given as:

dd if=/dev/urandom of=file bs=4M count=1
dax_iomap_rw
iomap_iter // round 1
ext4_iomap_begin
ext4_iomap_alloc // allocate 0~2M extents(written flag)
dax_iomap_iter // copy 2M data
iomap_iter // round 2
iomap_iter_advance

    iter->pos += iter->processed // iter->pos = 2M

ext4_iomap_begin
ext4_iomap_alloc // allocate 2~4M extents(written flag)
dax_iomap_iter
fatal_signal_pending
done = iter->pos - iocb->ki_pos // done = 2M
ext4_handle_inode_extension
ext4_update_inode_size // inode size = 2M

fsck reports: Inode 13, i_size is 2097152, should be 4194304. Fix?

Fix the problem by truncating extents if the written length is smaller than expected.

---
 fs/ext4/file.c |    8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

@@ -334,10 +334,10 @@ static ssize_t ext4_handle_inode_extensi
  * Clean up the inode after DIO or DAX extending write has completed and the
  * inode size has been updated using ext4_handle_inode_extension().
  */
-static void ext4_inode_extension_cleanup(struct inode *inode, ssize_t count)
+static void ext4_inode_extension_cleanup(struct inode *inode, bool need_trunc)
 {
 	lockdep_assert_held_write(&inode->i_rwsem);
-	if (count < 0) {
+	if (need_trunc) {
 		ext4_truncate_failed_write(inode);
 		/*
 		 * If the truncate operation failed early, then the inode may

@@ -586,7 +586,7 @@ static ssize_t ext4_dio_write_iter(struc
 		 * writeback of delalloc blocks.
 		 */
 		WARN_ON_ONCE(ret == -EIOCBQUEUED);
-		ext4_inode_extension_cleanup(inode, ret);
+		ext4_inode_extension_cleanup(inode, ret < 0);
 	}
 
 out:

@@ -670,7 +670,7 @@ ext4_dax_write_iter(struct kiocb *iocb,
 
 	if (extend) {
 		ret = ext4_handle_inode_extension(inode, offset, ret);
-		ext4_inode_extension_cleanup(inode, ret);
+		ext4_inode_extension_cleanup(inode, ret < (ssize_t)count);
 	}
 out:
 	inode_unlock(inode);

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

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

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

commit 972090651ee15e51abfb2160e986fa050cfc7a40 upstream.

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

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

@@ -79,9 +79,12 @@ __releases(&journal->j_state_lock)
 		if (space_left < nblocks) {
 			int chkpt = journal->j_checkpoint_transactions != NULL;
 			tid_t tid = 0;
+			bool has_transaction = false;
 
-			if (journal->j_committing_transaction)
+			if (journal->j_committing_transaction) {
 				tid = journal->j_committing_transaction->t_tid;
+				has_transaction = true;
+			}
 			spin_unlock(&journal->j_list_lock);
 			write_unlock(&journal->j_state_lock);
 			if (chkpt) {

@@ -89,7 +92,7 @@ __releases(&journal->j_state_lock)
 			} else if (jbd2_cleanup_journal_tail(journal) == 0) {
 				/* We were able to recover space; yay! */
 				;
-			} else if (tid) {
+			} else if (has_transaction) {
 				/*
 				 * jbd2_journal_commit_transaction() may want
 				 * to take the checkpoint_mutex if JBD2_FLUSHED

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

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

From: Baokun Li <[email protected]>

commit 5c0f4cc84d3a601c99bc5e6e6eb1cbda542cce95 upstream.

When calling ext4_force_split_extent_at() in ext4_ext_replay_update_ex(), the 'ppath' is updated but it is the 'path' that is freed, thus potentially triggering a double-free in the following process:

ext4_ext_replay_update_ex
ppath = path
ext4_force_split_extent_at(&ppath)

    ext4_split_extent_at
      ext4_ext_insert_extent
        ext4_ext_create_new_leaf
          ext4_ext_grow_indepth
            ext4_find_extent
              if (depth > path[0].p_maxdepth)
                kfree(path)                 ---> path First freed
                *orig_path = path = NULL    ---> null ppath

kfree(path) ---> path double-free !!!

So drop the unnecessary ppath and use path directly to avoid this problem. And use ext4_find_extent() directly to update path, avoiding unnecessary memory allocation and freeing. Also, propagate the error returned by ext4_find_extent() instead of using strange error codes.

---
 fs/ext4/extents.c |   21 ++++++++++-----------
 1 file changed, 10 insertions(+), 11 deletions(-)

@@ -5899,7 +5899,7 @@ out:
 int ext4_ext_replay_update_ex(struct inode *inode, ext4_lblk_t start,
 			      int len, int unwritten, ext4_fsblk_t pblk)
 {
-	struct ext4_ext_path *path = NULL, *ppath;
+	struct ext4_ext_path *path;
 	struct ext4_extent *ex;
 	int ret;
 

@@ -5915,30 +5915,29 @@ int ext4_ext_replay_update_ex(struct ino
 	if (le32_to_cpu(ex->ee_block) != start ||
 		ext4_ext_get_actual_len(ex) != len) {
 		/* We need to split this extent to match our extent first */
-		ppath = path;
 		down_write(&EXT4_I(inode)->i_data_sem);
-		ret = ext4_force_split_extent_at(NULL, inode, &ppath, start, 1);
+		ret = ext4_force_split_extent_at(NULL, inode, &path, start, 1);
 		up_write(&EXT4_I(inode)->i_data_sem);
 		if (ret)
 			goto out;
-		kfree(path);
-		path = ext4_find_extent(inode, start, NULL, 0);
+
+		path = ext4_find_extent(inode, start, &path, 0);
 		if (IS_ERR(path))
-			return -1;
-		ppath = path;
+			return PTR_ERR(path);
 		ex = path[path->p_depth].p_ext;
 		WARN_ON(le32_to_cpu(ex->ee_block) != start);
+
 		if (ext4_ext_get_actual_len(ex) != len) {
 			down_write(&EXT4_I(inode)->i_data_sem);
-			ret = ext4_force_split_extent_at(NULL, inode, &ppath,
+			ret = ext4_force_split_extent_at(NULL, inode, &path,
 							 start + len, 1);
 			up_write(&EXT4_I(inode)->i_data_sem);
 			if (ret)
 				goto out;
-			kfree(path);
-			path = ext4_find_extent(inode, start, NULL, 0);
+
+			path = ext4_find_extent(inode, start, &path, 0);
 			if (IS_ERR(path))
-				return -EINVAL;
+				return PTR_ERR(path);
 			ex = path[path->p_depth].p_ext;
 		}
 	}

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

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

From: Baokun Li <[email protected]>

commit a164f3a432aae62ca23d03e6d926b122ee5b860d upstream.

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

ext4_ext_insert_extent
path = *ppath = 2000
ext4_ext_create_new_leaf(ppath)

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

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

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

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

[...]

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

[...]

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

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

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

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

@@ -2103,6 +2103,7 @@ prepend:
 				       ppath, newext);
 	if (err)
 		goto cleanup;
+	path = *ppath;
 	depth = ext_depth(inode);
 	eh = path[depth].p_hdr;
 

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

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

From: Baokun Li <[email protected]>

commit dcaa6c31134c0f515600111c38ed7750003e1b9c upstream.

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

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

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

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

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

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

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

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

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

@@ -1877,6 +1877,7 @@ static void ext4_ext_try_to_merge_up(han
 	path[0].p_hdr->eh_max = cpu_to_le16(max_root);
 
 	brelse(path[1].p_bh);
+	path[1].p_bh = NULL;
 	ext4_free_blocks(handle, inode, NULL, blk, 1,
 			 EXT4_FREE_BLOCKS_METADATA | EXT4_FREE_BLOCKS_FORGET);
 }

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

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

From: Xiaxi Shen <[email protected]>

commit 0ce160c5bdb67081a62293028dc85758a8efb22a upstream.

Syzbot has found an ODEBUG bug in ext4_fill_super

The del_timer_sync function cancels the s_err_report timer, which reminds about filesystem errors daily. We should guarantee the timer is no longer active before kfree(sbi).

When filesystem mounting fails, the flow goes to failed_mount3, where an error occurs when ext4_stop_mmpd is called, causing a read I/O failure. This triggers the ext4_handle_error function that ultimately re-arms the timer,
leaving the s_err_report timer active before kfree(sbi) is called.

Fix the issue by canceling the s_err_report timer after calling ext4_stop_mmpd.

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

@@ -5635,8 +5635,8 @@ failed_mount3a:
 failed_mount3:
 	/* flush s_sb_upd_work before sbi destroy */
 	flush_work(&sbi->s_sb_upd_work);
-	del_timer_sync(&sbi->s_err_report);
 	ext4_stop_mmpd(sbi);
+	del_timer_sync(&sbi->s_err_report);
 	ext4_group_desc_free(sbi);
 failed_mount:
 	if (sbi->s_chksum_driver)

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

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

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

commit 23dfdb56581ad92a9967bcd720c8c23356af74c1 upstream.

The following kernel trace can be triggered with fstest generic/629 when executed against a filesystem with fast-commit feature enabled:

INFO: trying to register non-static key.
The code is fine but needs lockdep annotation, or maybe you didn't initialize this object before use? turning off the locking correctness validator.

CPU: 0 PID: 866 Comm: mount Not tainted 6.10.0+ #11
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.2-3-gd478f380-prebuilt.qemu.org 04/01/2014
Call Trace:
 <TASK>
 dump_stack_lvl+0x66/0x90
 register_lock_class+0x759/0x7d0
 __lock_acquire+0x85/0x2630
 ? __find_get_block+0xb4/0x380
 lock_acquire+0xd1/0x2d0
 ? __ext4_journal_get_write_access+0xd5/0x160
 _raw_spin_lock+0x33/0x40
 ? __ext4_journal_get_write_access+0xd5/0x160
 __ext4_journal_get_write_access+0xd5/0x160
 ext4_reserve_inode_write+0x61/0xb0
 __ext4_mark_inode_dirty+0x79/0x270
 ? ext4_ext_replay_set_iblocks+0x2f8/0x450
 ext4_ext_replay_set_iblocks+0x330/0x450
 ext4_fc_replay+0x14c8/0x1540
 ? jread+0x88/0x2e0
 ? rcu_is_watching+0x11/0x40
 do_one_pass+0x447/0xd00
 jbd2_journal_recover+0x139/0x1b0
 jbd2_journal_load+0x96/0x390
 ext4_load_and_init_journal+0x253/0xd40
 ext4_fill_super+0x2cc6/0x3180

...

In the replay path there's an attempt to lock sbi->s_bdev_wb_lock in function ext4_check_bdev_write_error(). Unfortunately, at this point this spinlock has not been initialized yet. Moving it's initialization to an earlier point in __ext4_fill_super() fixes this splat.

---
 fs/ext4/super.c |    3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

@@ -5334,6 +5334,8 @@ static int __ext4_fill_super(struct fs_c
 	INIT_LIST_HEAD(&sbi->s_orphan); /* unlinked but open files */
 	mutex_init(&sbi->s_orphan_lock);
 
+	spin_lock_init(&sbi->s_bdev_wb_lock);
+
 	ext4_fast_commit_init(sb);
 
 	sb->s_root = NULL;

@@ -5555,7 +5557,6 @@ static int __ext4_fill_super(struct fs_c
 	 * Save the original bdev mapping's wb_err value which could be
 	 * used to detect the metadata async write error.
 	 */
-	spin_lock_init(&sbi->s_bdev_wb_lock);
 	errseq_check_and_advance(&sb->s_bdev->bd_mapping->wb_err,
 				 &sbi->s_bdev_wb_err);
 	EXT4_SB(sb)->s_mount_state |= EXT4_ORPHAN_FS;

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

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

From: Baokun Li <[email protected]>

commit 5b4b2dcace35f618fe361a87bae6f0d13af31bc1 upstream.

In ext4_find_extent(), if the path is not big enough, we free it and set *orig_path to NULL. But after reallocating and successfully initializing the path, we don't update *orig_path, in which case the caller gets a valid path but a NULL ppath, and this may cause a NULL pointer dereference or a path memory leak. For example:

ext4_split_extent
path = *ppath = 2000
ext4_find_extent

    if (depth > path[0].p_maxdepth)
      kfree(path = 2000);
      *orig_path = path = NULL;
      path = kcalloc() = 3000
  ext4_split_extent_at(*ppath = NULL)
    path = *ppath;
    ex = path[depth].p_ext;
    // NULL pointer dereference!

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

BUG: kernel NULL pointer dereference, address: 0000000000000010
CPU: 6 UID: 0 PID: 576 Comm: fsstress Not tainted 6.11.0-rc2-dirty #847
RIP: 0010:ext4_split_extent_at+0x6d/0x560
Call Trace:
 <TASK>
 ext4_split_extent.isra.0+0xcb/0x1b0
 ext4_ext_convert_to_initialized+0x168/0x6c0
 ext4_ext_handle_unwritten_extents+0x325/0x4d0
 ext4_ext_map_blocks+0x520/0xdb0
 ext4_map_blocks+0x2b0/0x690
 ext4_iomap_begin+0x20e/0x2c0

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

Therefore, *orig_path is updated when the extent lookup succeeds, so that the caller can safely use path or *ppath.

---
 fs/ext4/extents.c     |    3 ++-
 fs/ext4/move_extent.c |    1 -
 2 files changed, 2 insertions(+), 2 deletions(-)

@@ -957,6 +957,8 @@ ext4_find_extent(struct inode *inode, ex
 
 	ext4_ext_show_path(inode, path);
 
+	if (orig_path)
+		*orig_path = path;
 	return path;
 
 err:

@@ -3249,7 +3251,6 @@ static int ext4_split_extent_at(handle_t
 	}
 	depth = ext_depth(inode);
 	ex = path[depth].p_ext;
-	*ppath = path;
 
 	if (EXT4_EXT_MAY_ZEROOUT & split_flag) {
 		if (split_flag & (EXT4_EXT_DATA_VALID1|EXT4_EXT_DATA_VALID2)) {

@@ -36,7 +36,6 @@ get_ext_path(struct inode *inode, ext4_l
 		*ppath = NULL;
 		return -ENODATA;
 	}
-	*ppath = path;
 	return 0;
 }
 

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

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

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

commit dd589b0f1445e1ea1085b98edca6e4d5dedb98d0 upstream.

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

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

@@ -5279,8 +5279,9 @@ static void ext4_wait_for_tail_page_comm
 {
 	unsigned offset;
 	journal_t *journal = EXT4_SB(inode->i_sb)->s_journal;
-	tid_t commit_tid = 0;
+	tid_t commit_tid;
 	int ret;
+	bool has_transaction;
 
 	offset = inode->i_size & (PAGE_SIZE - 1);
 	/*

@@ -5305,12 +5306,14 @@ static void ext4_wait_for_tail_page_comm
 		folio_put(folio);
 		if (ret != -EBUSY)
 			return;
-		commit_tid = 0;
+		has_transaction = false;
 		read_lock(&journal->j_state_lock);
-		if (journal->j_committing_transaction)
+		if (journal->j_committing_transaction) {
 			commit_tid = journal->j_committing_transaction->t_tid;
+			has_transaction = true;
+		}
 		read_unlock(&journal->j_state_lock);
-		if (commit_tid)
+		if (has_transaction)
 			jbd2_log_wait_commit(journal, commit_tid);
 	}
 }

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

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

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

commit 7a6443e1dad70281f99f0bd394d7fd342481a632 upstream.

Function jbd2_journal_shrink_checkpoint_list() assumes that '0' is not a valid value for transaction IDs, which is incorrect. Don't assume that and use two extra boolean variables to control the loop iterations and keep track of the first and last tid.

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

@@ -410,6 +410,7 @@ unsigned long jbd2_journal_shrink_checkp
 	tid_t tid = 0;
 	unsigned long nr_freed = 0;
 	unsigned long freed;
+	bool first_set = false;
 
 again:
 	spin_lock(&journal->j_list_lock);

@@ -429,8 +430,10 @@ again:
 	else
 		transaction = journal->j_checkpoint_transactions;
 
-	if (!first_tid)
+	if (!first_set) {
 		first_tid = transaction->t_tid;
+		first_set = true;
+	}
 	last_transaction = journal->j_checkpoint_transactions->t_cpprev;
 	next_transaction = transaction;
 	last_tid = last_transaction->t_tid;

@@ -460,7 +463,7 @@ again:
 	spin_unlock(&journal->j_list_lock);
 	cond_resched();
 
-	if (*nr_to_scan && next_tid)
+	if (*nr_to_scan && journal->j_shrink_transaction)
 		goto again;
 out:
 	trace_jbd2_shrink_checkpoint_list(journal, first_tid, tid, last_tid,

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

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

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

commit 6db3c1575a750fd417a70e0178bdf6efa0dd5037 upstream.

When a full journal commit is on-going, any fast commit has to be enqueued into a different queue: FC_Q_STAGING instead of FC_Q_MAIN. This enqueueing is done only once, i.e. if an inode is already queued in a previous fast commit entry it won't be enqueued again. However, if a full commit starts _after_ the inode is enqueued into FC_Q_MAIN, the next fast commit needs to be done into FC_Q_STAGING. And this is not being done in function ext4_fc_track_template().

This patch fixes the issue by re-enqueuing an inode into the STAGING queue during the fast commit clean-up callback when doing a full commit. However, to prevent a race with a fast-commit, the clean-up callback has to be called with the journal locked.

This bug was found using fstest generic/047. This test creates several 32k bytes files, sync'ing each of them after it's creation, and then shutting down the filesystem. Some data may be loss in this operation; for example a file may have it's size truncated to zero.

---
 fs/ext4/fast_commit.c |   15 ++++++++++++++-
 fs/jbd2/journal.c     |    2 +-
 2 files changed, 15 insertions(+), 2 deletions(-)

@@ -1295,8 +1295,21 @@ static void ext4_fc_cleanup(journal_t *j
 		list_del_init(&iter->i_fc_list);
 		ext4_clear_inode_state(&iter->vfs_inode,
 				       EXT4_STATE_FC_COMMITTING);
-		if (tid_geq(tid, iter->i_sync_tid))
+		if (tid_geq(tid, iter->i_sync_tid)) {
 			ext4_fc_reset_inode(&iter->vfs_inode);
+		} else if (full) {
+			/*
+			 * We are called after a full commit, inode has been
+			 * modified while the commit was running. Re-enqueue
+			 * the inode into STAGING, which will then be splice
+			 * back into MAIN. This cannot happen during
+			 * fastcommit because the journal is locked all the
+			 * time in that case (and tid doesn't increase so
+			 * tid check above isn't reliable).
+			 */
+			list_add_tail(&EXT4_I(&iter->vfs_inode)->i_fc_list,
+				      &sbi->s_fc_q[FC_Q_STAGING]);
+		}
 		/* Make sure EXT4_STATE_FC_COMMITTING bit is clear */
 		smp_mb();
 #if (BITS_PER_LONG < 64)

@@ -740,9 +740,9 @@ EXPORT_SYMBOL(jbd2_fc_begin_commit);
  */
 static int __jbd2_fc_end_commit(journal_t *journal, tid_t tid, bool fallback)
 {
-	jbd2_journal_unlock_updates(journal);
 	if (journal->j_fc_cleanup_callback)
 		journal->j_fc_cleanup_callback(journal, 0, tid);
+	jbd2_journal_unlock_updates(journal);
 	write_lock(&journal->j_state_lock);
 	journal->j_flags &= ~JBD2_FAST_COMMIT_ONGOING;
 	if (fallback)

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

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

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

commit faab35a0370fd6e0821c7a8dd213492946fc776f upstream.

Calling ext4_fc_mark_ineligible() with a NULL handle is racy and may result in a fast-commit being done before the filesystem is effectively marked as ineligible. This patch fixes the calls to this function in __track_dentry_update() by adding an extra parameter to the callback used in ext4_fc_track_template().

---
 fs/ext4/fast_commit.c |   19 +++++++++++--------
 1 file changed, 11 insertions(+), 8 deletions(-)

@@ -379,7 +379,7 @@ void ext4_fc_mark_ineligible(struct supe
  */
 static int ext4_fc_track_template(
 	handle_t *handle, struct inode *inode,
-	int (*__fc_track_fn)(struct inode *, void *, bool),
+	int (*__fc_track_fn)(handle_t *handle, struct inode *, void *, bool),
 	void *args, int enqueue)
 {
 	bool update = false;

@@ -396,7 +396,7 @@ static int ext4_fc_track_template(
 		ext4_fc_reset_inode(inode);
 		ei->i_sync_tid = tid;
 	}
-	ret = __fc_track_fn(inode, args, update);
+	ret = __fc_track_fn(handle, inode, args, update);
 	mutex_unlock(&ei->i_fc_lock);
 
 	if (!enqueue)

@@ -420,7 +420,8 @@ struct __track_dentry_update_args {
 };
 
 /* __track_fn for directory entry updates. Called with ei->i_fc_lock. */
-static int __track_dentry_update(struct inode *inode, void *arg, bool update)
+static int __track_dentry_update(handle_t *handle, struct inode *inode,
+				 void *arg, bool update)
 {
 	struct ext4_fc_dentry_update *node;
 	struct ext4_inode_info *ei = EXT4_I(inode);

@@ -435,14 +436,14 @@ static int __track_dentry_update(struct
 
 	if (IS_ENCRYPTED(dir)) {
 		ext4_fc_mark_ineligible(sb, EXT4_FC_REASON_ENCRYPTED_FILENAME,
-					NULL);
+					handle);
 		mutex_lock(&ei->i_fc_lock);
 		return -EOPNOTSUPP;
 	}
 
 	node = kmem_cache_alloc(ext4_fc_dentry_cachep, GFP_NOFS);
 	if (!node) {
-		ext4_fc_mark_ineligible(sb, EXT4_FC_REASON_NOMEM, NULL);
+		ext4_fc_mark_ineligible(sb, EXT4_FC_REASON_NOMEM, handle);
 		mutex_lock(&ei->i_fc_lock);
 		return -ENOMEM;
 	}

@@ -454,7 +455,7 @@ static int __track_dentry_update(struct
 		node->fcd_name.name = kmalloc(dentry->d_name.len, GFP_NOFS);
 		if (!node->fcd_name.name) {
 			kmem_cache_free(ext4_fc_dentry_cachep, node);
-			ext4_fc_mark_ineligible(sb, EXT4_FC_REASON_NOMEM, NULL);
+			ext4_fc_mark_ineligible(sb, EXT4_FC_REASON_NOMEM, handle);
 			mutex_lock(&ei->i_fc_lock);
 			return -ENOMEM;
 		}

@@ -576,7 +577,8 @@ void ext4_fc_track_create(handle_t *hand
 }
 
 /* __track_fn for inode tracking */
-static int __track_inode(struct inode *inode, void *arg, bool update)
+static int __track_inode(handle_t *handle, struct inode *inode, void *arg,
+			 bool update)
 {
 	if (update)
 		return -EEXIST;

@@ -614,7 +616,8 @@ struct __track_range_args {
 };
 
 /* __track_fn for tracking data updates */
-static int __track_range(struct inode *inode, void *arg, bool update)
+static int __track_range(handle_t *handle, struct inode *inode, void *arg,
+			 bool update)
 {
 	struct ext4_inode_info *ei = EXT4_I(inode);
 	ext4_lblk_t oldstart;

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

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

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

commit 04e6ce8f06d161399e5afde3df5dcfa9455b4952 upstream.

Calling ext4_fc_mark_ineligible() with a NULL handle is racy and may result in a fast-commit being done before the filesystem is effectively marked as ineligible. This patch moves the call to this function so that an handle can be used. If a transaction fails to start, then there's not point in trying to mark the filesystem as ineligible, and an error will eventually be returned to user-space.

---
 fs/ext4/xattr.c |    3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

@@ -2559,6 +2559,8 @@ retry:
 
 		error = ext4_xattr_set_handle(handle, inode, name_index, name,
 					      value, value_len, flags);
+		ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_XATTR,
+					handle);
 		error2 = ext4_journal_stop(handle);
 		if (error == -ENOSPC &&
 		    ext4_should_retry_alloc(sb, &retries))

@@ -2566,7 +2568,6 @@ retry:
 		if (error == 0)
 			error = error2;
 	}
-	ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_XATTR, NULL);
 
 	return error;
 }

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

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

From: Baokun Li <[email protected]>

commit 6121258c2b33ceac3d21f6a221452692c465df88 upstream.

Wesley reported an issue:

==================================================================
EXT4-fs (dm-5): resizing filesystem from 7168 to 786432 blocks

------------[ cut here ]------------
kernel BUG at fs/ext4/resize.c:324!
CPU: 9 UID: 0 PID: 3576 Comm: resize2fs Not tainted 6.11.0+ #27
RIP: 0010:ext4_resize_fs+0x1212/0x12d0
Call Trace:
 __ext4_ioctl+0x4e0/0x1800
 ext4_ioctl+0x12/0x20
 __x64_sys_ioctl+0x99/0xd0
 x64_sys_call+0x1206/0x20d0
 do_syscall_64+0x72/0x110
 entry_SYSCALL_64_after_hwframe+0x76/0x7e
==================================================================

While reviewing the patch, Honza found that when adjusting resize_bg in alloc_flex_gd(), it was possible for flex_gd->resize_bg to be bigger than flexbg_size.

The reproduction of the problem requires the following:

o_group = flexbg_size * 2 * n;
o_size = (o_group + 1) * group_size;
n_group: [o_group + flexbg_size, o_group + flexbg_size * 2) o_size = (n_group + 1) * group_size;

Take n=0,flexbg_size=16 as an example:

              last:15
|o---------------|--------------n-|
o_group:0    resize to      n_group:30

The corresponding reproducer is:

img=test.img
rm -f $img
truncate -s 600M $img
mkfs.ext4 -F $img -b 1024 -G 16 8M
dev=losetup -f --show $img
mkdir -p /tmp/test
mount $dev /tmp/test
resize2fs $dev 248M

Delete the problematic plus 1 to fix the issue, and add a WARN_ON_ONCE() to prevent the issue from happening again.

[ Note: another reproucer which this commit fixes is:

  img=test.img
  rm -f $img
  truncate -s 25MiB $img
  mkfs.ext4 -b 4096 -E nodiscard,lazy_itable_init=0,lazy_journal_init=0 $img
  truncate -s 3GiB $img
  dev=`losetup -f --show $img`
  mkdir -p /tmp/test
  mount $dev /tmp/test
  resize2fs $dev 3G
  umount $dev
  losetup -d $dev

-- TYT ]

---
 fs/ext4/resize.c |   18 ++++++++++--------
 1 file changed, 10 insertions(+), 8 deletions(-)

@@ -230,8 +230,8 @@ struct ext4_new_flex_group_data {
 #define MAX_RESIZE_BG				16384
 
 /*
- * alloc_flex_gd() allocates a ext4_new_flex_group_data with size of
- * @flexbg_size.
+ * alloc_flex_gd() allocates an ext4_new_flex_group_data that satisfies the
+ * resizing from @o_group to @n_group, its size is typically @flexbg_size.
  *
  * Returns NULL on failure otherwise address of the allocated structure.
  */

@@ -239,25 +239,27 @@ static struct ext4_new_flex_group_data *
 				ext4_group_t o_group, ext4_group_t n_group)
 {
 	ext4_group_t last_group;
+	unsigned int max_resize_bg;
 	struct ext4_new_flex_group_data *flex_gd;
 
 	flex_gd = kmalloc(sizeof(*flex_gd), GFP_NOFS);
 	if (flex_gd == NULL)
 		goto out3;
 
-	if (unlikely(flexbg_size > MAX_RESIZE_BG))
-		flex_gd->resize_bg = MAX_RESIZE_BG;
-	else
-		flex_gd->resize_bg = flexbg_size;
+	max_resize_bg = umin(flexbg_size, MAX_RESIZE_BG);
+	flex_gd->resize_bg = max_resize_bg;
 
 	/* Avoid allocating large 'groups' array if not needed */
 	last_group = o_group | (flex_gd->resize_bg - 1);
 	if (n_group <= last_group)
-		flex_gd->resize_bg = 1 << fls(n_group - o_group + 1);
+		flex_gd->resize_bg = 1 << fls(n_group - o_group);
 	else if (n_group - last_group < flex_gd->resize_bg)
-		flex_gd->resize_bg = 1 << max(fls(last_group - o_group + 1),
+		flex_gd->resize_bg = 1 << max(fls(last_group - o_group),
 					      fls(n_group - last_group));
 
+	if (WARN_ON_ONCE(flex_gd->resize_bg > max_resize_bg))
+		flex_gd->resize_bg = max_resize_bg;
+
 	flex_gd->groups = kmalloc_array(flex_gd->resize_bg,
 					sizeof(struct ext4_new_group_data),
 					GFP_NOFS);

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

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

From: Lucas De Marchi <[email protected]>

commit ea74bf9ccba9ae80fc0766c07c4abaef927e9e63 upstream.

Instead of keep adding more dependencies as WAs are needed in different places of the driver, just add a rule with all the objects so the code generation happens before anything else.

While at it, group lines related to wa_oob in the Makefile.

v2: Prefix $(obj) when declaring dependency

---
 drivers/gpu/drm/xe/Makefile |   24 ++++--------------------
 1 file changed, 4 insertions(+), 20 deletions(-)

@@ -12,34 +12,15 @@ subdir-ccflags-$(CONFIG_DRM_XE_WERROR) +
 subdir-ccflags-y += -I$(obj) -I$(src)
 
 # generated sources
-hostprogs := xe_gen_wa_oob
 
+hostprogs := xe_gen_wa_oob
 generated_oob := $(obj)/generated/xe_wa_oob.c $(obj)/generated/xe_wa_oob.h
-
 quiet_cmd_wa_oob = GEN     $(notdir $(generated_oob))
       cmd_wa_oob = mkdir -p $(@D); $^ $(generated_oob)
-
 $(obj)/generated/%_wa_oob.c $(obj)/generated/%_wa_oob.h: $(obj)/xe_gen_wa_oob \
 		 $(src)/xe_wa_oob.rules
 	$(call cmd,wa_oob)
 
-uses_generated_oob := \
-	$(obj)/xe_ggtt.o \
-	$(obj)/xe_device.o \
-	$(obj)/xe_gsc.o \
-	$(obj)/xe_gt.o \
-	$(obj)/xe_guc.o \
-	$(obj)/xe_guc_ads.o \
-	$(obj)/xe_guc_pc.o \
-	$(obj)/xe_migrate.o \
-	$(obj)/xe_pat.o \
-	$(obj)/xe_ring_ops.o \
-	$(obj)/xe_vm.o \
-	$(obj)/xe_wa.o \
-	$(obj)/xe_ttm_stolen_mgr.o
-
-$(uses_generated_oob): $(generated_oob)
-
 # Please keep these build lists sorted!
 
 # core driver code

@@ -322,3 +303,6 @@ quiet_cmd_hdrtest = HDRTEST $(patsubst %
 
 $(obj)/%.hdrtest: $(src)/%.h FORCE
 	$(call if_changed_dep,hdrtest)
+
+uses_generated_oob := $(addprefix $(obj)/, $(xe-y))
+$(uses_generated_oob): $(obj)/generated/xe_wa_oob.h

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

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

From: Helge Deller <[email protected]>

commit d24449864da5838936669618356b0e30ca2999c3 upstream.

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

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

@@ -243,10 +243,10 @@ linux_gateway_entry:
 
 #ifdef CONFIG_64BIT
 	ldil	L%sys_call_table, %r1
-	or,=	%r2,%r2,%r2
-	addil	L%(sys_call_table64-sys_call_table), %r1
+	or,ev	%r2,%r2,%r2
+	ldil	L%sys_call_table64, %r1
 	ldo	R%sys_call_table(%r1), %r19
-	or,=	%r2,%r2,%r2
+	or,ev	%r2,%r2,%r2
 	ldo	R%sys_call_table64(%r1), %r19
 #else
 	load32	sys_call_table, %r19

@@ -379,10 +379,10 @@ tracesys_next:
 	extrd,u	%r19,63,1,%r2			/* W hidden in bottom bit */
 
 	ldil	L%sys_call_table, %r1
-	or,=	%r2,%r2,%r2
-	addil	L%(sys_call_table64-sys_call_table), %r1
+	or,ev	%r2,%r2,%r2
+	ldil	L%sys_call_table64, %r1
 	ldo	R%sys_call_table(%r1), %r19
-	or,=	%r2,%r2,%r2
+	or,ev	%r2,%r2,%r2
 	ldo	R%sys_call_table64(%r1), %r19
 #else
 	load32	sys_call_table, %r19

@@ -1327,6 +1327,8 @@ ENTRY(sys_call_table)
 END(sys_call_table)
 
 #ifdef CONFIG_64BIT
+#undef __SYSCALL_WITH_COMPAT
+#define __SYSCALL_WITH_COMPAT(nr, native, compat)	__SYSCALL(nr, native)
 	.align 8
 ENTRY(sys_call_table64)
 #include <asm/syscall_table_64.h>    /* 64-bit syscalls */

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

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

From: Helge Deller <[email protected]>

commit 5d698966fa7b452035c44c937d704910bf3440dd upstream.

When userspace allocates memory with mmap() in order to be used for stack, allow this memory region to automatically expand upwards up until the current maximum process stack size.
The fault handler checks if the VM_GROWSUP bit is set in the vm_flags field of a memory area before it allows it to expand.
This patch modifies the parisc specific code only.
A RFC for a generic patch to modify mmap() for all architectures was sent to the mailing list but did not get enough Acks.

---
 arch/parisc/include/asm/mman.h |   14 ++++++++++++++
 1 file changed, 14 insertions(+)

@@ -11,4 +11,18 @@ static inline bool arch_memory_deny_writ
 }
 #define arch_memory_deny_write_exec_supported arch_memory_deny_write_exec_supported
 
+static inline unsigned long arch_calc_vm_flag_bits(unsigned long flags)
+{
+	/*
+	 * The stack on parisc grows upwards, so if userspace requests memory
+	 * for a stack, mark it with VM_GROWSUP so that the stack expansion in
+	 * the fault handler will work.
+	 */
+	if (flags & MAP_STACK)
+		return VM_GROWSUP;
+
+	return 0;
+}
+#define arch_calc_vm_flag_bits(flags) arch_calc_vm_flag_bits(flags)
+
 #endif /* __ASM_MMAN_H__ */

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

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

From: Helge Deller <[email protected]>

commit f31b256994acec6929306dfa86ac29716e7503d6 upstream.

Fix the stack start address calculation for the parisc architecture in setup_arg_pages() when address randomization is disabled. When the ADDR_NO_RANDOMIZE process personality is disabled there is no need to add additional space for the stack.
Note that this patch touches code inside an #ifdef CONFIG_STACK_GROWSUP hunk, which is why only the parisc architecture is affected since it's the only Linux architecture where the stack grows upwards.

Without this patch you will find the stack in the middle of some mapped libaries and suddenly limited to 6MB instead of 8MB:

root@parisc:~# setarch -R /bin/bash -c "cat /proc/self/maps"
00010000-00019000 r-xp 00000000 08:05 1182034           /usr/bin/cat
00019000-0001a000 rwxp 00009000 08:05 1182034           /usr/bin/cat
0001a000-0003b000 rwxp 00000000 00:00 0                 [heap]
f90c4000-f9283000 r-xp 00000000 08:05 1573004           /usr/lib/hppa-linux-gnu/libc.so.6
f9283000-f9285000 r--p 001bf000 08:05 1573004           /usr/lib/hppa-linux-gnu/libc.so.6
f9285000-f928a000 rwxp 001c1000 08:05 1573004           /usr/lib/hppa-linux-gnu/libc.so.6
f928a000-f9294000 rwxp 00000000 00:00 0
f9301000-f9323000 rwxp 00000000 00:00 0                 [stack]
f98b4000-f98e4000 r-xp 00000000 08:05 1572869           /usr/lib/hppa-linux-gnu/ld.so.1
f98e4000-f98e5000 r--p 00030000 08:05 1572869           /usr/lib/hppa-linux-gnu/ld.so.1
f98e5000-f98e9000 rwxp 00031000 08:05 1572869           /usr/lib/hppa-linux-gnu/ld.so.1
f9ad8000-f9b00000 rw-p 00000000 00:00 0
f9b00000-f9b01000 r-xp 00000000 00:00 0                 [vdso]

With the patch the stack gets correctly mapped at the end of the process memory map:

root@panama:~# setarch -R /bin/bash -c "cat /proc/self/maps"
00010000-00019000 r-xp 00000000 08:13 16385582          /usr/bin/cat
00019000-0001a000 rwxp 00009000 08:13 16385582          /usr/bin/cat
0001a000-0003b000 rwxp 00000000 00:00 0                 [heap]
fef29000-ff0eb000 r-xp 00000000 08:13 16122400          /usr/lib/hppa-linux-gnu/libc.so.6
ff0eb000-ff0ed000 r--p 001c2000 08:13 16122400          /usr/lib/hppa-linux-gnu/libc.so.6
ff0ed000-ff0f2000 rwxp 001c4000 08:13 16122400          /usr/lib/hppa-linux-gnu/libc.so.6
ff0f2000-ff0fc000 rwxp 00000000 00:00 0
ff4b4000-ff4e4000 r-xp 00000000 08:13 16121913          /usr/lib/hppa-linux-gnu/ld.so.1
ff4e4000-ff4e6000 r--p 00030000 08:13 16121913          /usr/lib/hppa-linux-gnu/ld.so.1
ff4e6000-ff4ea000 rwxp 00032000 08:13 16121913          /usr/lib/hppa-linux-gnu/ld.so.1
ff6d7000-ff6ff000 rw-p 00000000 00:00 0
ff6ff000-ff700000 r-xp 00000000 00:00 0                 [vdso]
ff700000-ff722000 rwxp 00000000 00:00 0                 [stack]

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

@@ -811,7 +811,8 @@ int setup_arg_pages(struct linux_binprm
 	stack_base = calc_max_stack_size(stack_base);
 
 	/* Add space for stack randomization. */
-	stack_base += (STACK_RND_MASK << PAGE_SHIFT);
+	if (current->flags & PF_RANDOMIZE)
+		stack_base += (STACK_RND_MASK << PAGE_SHIFT);
 
 	/* Make sure we didn't let the argument array grow too large. */
 	if (vma->vm_end - vma->vm_start > stack_base)

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

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

From: Val Packett <[email protected]>

commit 6b44aa559d6c7f4ea591ef9d2352a7250138d62a upstream.

The RK3066 VOP sets a dma_stop bit when it's done scanning out a frame and needs the driver to acknowledge that by clearing the bit.

Unless we clear it "between" frames, the RGB output only shows noise instead of the picture. atomic_flush is the place for it that least affects other code (doing it on vblank would require converting all other usages of the reg_lock to spin_(un)lock_irq, which would affect performance for everyone).

This seems to be a redundant synchronization mechanism that was removed in later iterations of the VOP hardware block.

---
 drivers/gpu/drm/rockchip/rockchip_drm_vop.c |    4 ++++
 drivers/gpu/drm/rockchip/rockchip_drm_vop.h |    1 +
 drivers/gpu/drm/rockchip/rockchip_vop_reg.c |    1 +
 3 files changed, 6 insertions(+)

@@ -1583,6 +1583,10 @@ static void vop_crtc_atomic_flush(struct
 	VOP_AFBC_SET(vop, enable, s->enable_afbc);
 	vop_cfg_done(vop);
 
+	/* Ack the DMA transfer of the previous frame (RK3066). */
+	if (VOP_HAS_REG(vop, common, dma_stop))
+		VOP_REG_SET(vop, common, dma_stop, 0);
+
 	spin_unlock(&vop->reg_lock);
 
 	/*

@@ -122,6 +122,7 @@ struct vop_common {
 	struct vop_reg lut_buffer_index;
 	struct vop_reg gate_en;
 	struct vop_reg mmu_en;
+	struct vop_reg dma_stop;
 	struct vop_reg out_mode;
 	struct vop_reg standby;
 };

@@ -466,6 +466,7 @@ static const struct vop_output rk3066_ou
 };
 
 static const struct vop_common rk3066_common = {
+	.dma_stop = VOP_REG(RK3066_SYS_CTRL0, 0x1, 0),
 	.standby = VOP_REG(RK3066_SYS_CTRL0, 0x1, 1),
 	.out_mode = VOP_REG(RK3066_DSP_CTRL0, 0xf, 0),
 	.cfg_done = VOP_REG(RK3066_REG_CFG_DONE, 0x1, 0),

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

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

From: Thomas Weißschuh <[email protected]>

commit 000f6d588a8f3d128f89351058dc04d38e54a327 upstream.

The members "start" and "end" of struct resource are of type "resource_size_t" which can be 32bit wide.
Values read from OF however are always 64bit wide.
Avoid silently truncating the value and instead return an error value.

This can happen on real systems when the DT was created for a PAE-enabled kernel and a non-PAE kernel is actually running. For example with an arm defconfig and "qemu-system-arm -M virt".

---
 drivers/of/address.c |    5 +++++
 1 file changed, 5 insertions(+)

@@ -8,6 +8,7 @@
 #include <linux/logic_pio.h>
 #include <linux/module.h>
 #include <linux/of_address.h>
+#include <linux/overflow.h>
 #include <linux/pci.h>
 #include <linux/pci_regs.h>
 #include <linux/sizes.h>

@@ -1061,7 +1062,11 @@ static int __of_address_to_resource(stru
 	if (of_mmio_is_nonposted(dev))
 		flags |= IORESOURCE_MEM_NONPOSTED;
 
+	if (overflows_type(taddr, r->start))
+		return -EOVERFLOW;
 	r->start = taddr;
+	if (overflows_type(taddr + size - 1, r->end))
+		return -EOVERFLOW;
 	r->end = taddr + size - 1;
 	r->flags = flags;
 	r->name = name ? name : dev->full_name;

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

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

From: Andrew Jones <[email protected]>

commit db8e81132cf051843c9a59b46fa5a071c45baeb3 upstream.

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

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

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

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

@@ -716,8 +716,7 @@ struct irq_domain *of_msi_map_get_device
  * @np: device node for @dev
  * @token: bus type for this domain
  *
- * Parse the msi-parent property (both the simple and the complex
- * versions), and returns the corresponding MSI domain.
+ * Parse the msi-parent property and returns the corresponding MSI domain.
  *
  * Returns: the MSI domain for this device (or NULL on failure).
  */

@@ -725,33 +724,14 @@ struct irq_domain *of_msi_get_domain(str
 				     struct device_node *np,
 				     enum irq_domain_bus_token token)
 {
-	struct device_node *msi_np;
+	struct of_phandle_iterator it;
 	struct irq_domain *d;
+	int err;
 
-	/* Check for a single msi-parent property */
-	msi_np = of_parse_phandle(np, "msi-parent", 0);
-	if (msi_np && !of_property_read_bool(msi_np, "#msi-cells")) {
-		d = irq_find_matching_host(msi_np, token);
-		if (!d)
-			of_node_put(msi_np);
-		return d;
-	}
-
-	if (token == DOMAIN_BUS_PLATFORM_MSI) {
-		/* Check for the complex msi-parent version */
-		struct of_phandle_args args;
-		int index = 0;
-
-		while (!of_parse_phandle_with_args(np, "msi-parent",
-						   "#msi-cells",
-						   index, &args)) {
-			d = irq_find_matching_host(args.np, token);
-			if (d)
-				return d;
-
-			of_node_put(args.np);
-			index++;
-		}
+	of_for_each_phandle(&it, err, np, "msi-parent", "#msi-cells", 0) {
+		d = irq_find_matching_host(it.node, token);
+		if (d)
+			return d;
 	}
 
 	return NULL;

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

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

From: Ma Ke <[email protected]>

commit e794b7b9b92977365c693760a259f8eef940c536 upstream.

As it may return NULL pointer and cause NULL pointer dereference. Add check for the return value of alloc_ordered_workqueue.

---
 drivers/gpu/drm/omapdrm/omap_drv.c |    5 +++++
 1 file changed, 5 insertions(+)

@@ -695,6 +695,10 @@ static int omapdrm_init(struct omap_drm_
 	soc = soc_device_match(omapdrm_soc_devices);
 	priv->omaprev = soc ? (uintptr_t)soc->data : 0;
 	priv->wq = alloc_ordered_workqueue("omapdrm", 0);
+	if (!priv->wq) {
+		ret = -ENOMEM;
+		goto err_alloc_workqueue;
+	}
 
 	mutex_init(&priv->list_lock);
 	INIT_LIST_HEAD(&priv->obj_list);

@@ -753,6 +757,7 @@ err_gem_deinit:
 	drm_mode_config_cleanup(ddev);
 	omap_gem_deinit(ddev);
 	destroy_workqueue(priv->wq);
+err_alloc_workqueue:
 	omap_disconnect_pipelines(ddev);
 	drm_dev_put(ddev);
 	return ret;

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

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

From: Huang Ying <[email protected]>

commit b4afe4183ec77f230851ea139d91e5cf2644c68b upstream.

On a system with CXL memory, the resource tree (/proc/iomem) related to CXL memory may look like something as follows.

490000000-50fffffff : CXL Window 0
490000000-50fffffff : region0

    490000000-50fffffff : dax0.0
      490000000-50fffffff : System RAM (kmem)

Because drivers/dax/kmem.c calls add_memory_driver_managed() during onlining CXL memory, which makes "System RAM (kmem)" a descendant of "CXL Window X". This confuses region_intersects(), which expects all "System RAM" resources to be at the top level of iomem_resource. This can lead to bugs.

For example, when the following command line is executed to write some memory in CXL memory range via /dev/mem,

 $ dd if=data of=/dev/mem bs=$((1 << 10)) seek=$((0x490000000 >> 10)) count=1
 dd: error writing '/dev/mem': Bad address
 1+0 records in
 0+0 records out
 0 bytes copied, 0.0283507 s, 0.0 kB/s

the command fails as expected. However, the error code is wrong. It should be "Operation not permitted" instead of "Bad address". More seriously, the /dev/mem permission checking in devmem_is_allowed() passes incorrectly. Although the accessing is prevented later because ioremap() isn't allowed to map system RAM, it is a potential security issue. During command executing, the following warning is reported in the kernel log for calling ioremap() on system RAM.

ioremap on RAM at 0x0000000490000000 - 0x0000000490000fff

 WARNING: CPU: 2 PID: 416 at arch/x86/mm/ioremap.c:216 __ioremap_caller.constprop.0+0x131/0x35d
 Call Trace:
  memremap+0xcb/0x184
  xlate_dev_mem_ptr+0x25/0x2f
  write_mem+0x94/0xfb
  vfs_write+0x128/0x26d
  ksys_write+0xac/0xfe
  do_syscall_64+0x9a/0xfd
  entry_SYSCALL_64_after_hwframe+0x4b/0x53

The details of command execution process are as follows. In the above resource tree, "System RAM" is a descendant of "CXL Window 0" instead of a top level resource. So, region_intersects() will report no System RAM resources in the CXL memory region incorrectly, because it only checks the top level resources. Consequently, devmem_is_allowed() will return 1 (allow access via /dev/mem) for CXL memory region incorrectly. Fortunately, ioremap() doesn't allow to map System RAM and reject the access.

So, region_intersects() needs to be fixed to work correctly with the resource tree with "System RAM" not at top level as above. To fix it, if we found a unmatched resource in the top level, we will continue to search matched resources in its descendant resources. So, we will not miss any matched resources in resource tree anymore.

In the new implementation, an example resource tree

|------------- "CXL Window 0" ------------|
|-- "System RAM" --|

will behave similar as the following fake resource tree for region_intersects(, IORESOURCE_SYSTEM_RAM, ),

|-- "System RAM" --||-- "CXL Window 0a" --|

Where "CXL Window 0a" is part of the original "CXL Window 0" that isn't covered by "System RAM".

---
 kernel/resource.c |   58 ++++++++++++++++++++++++++++++++++++++++++++++--------
 1 file changed, 50 insertions(+), 8 deletions(-)

@@ -540,20 +540,62 @@ static int __region_intersects(struct re
 			       size_t size, unsigned long flags,
 			       unsigned long desc)
 {
-	struct resource res;
+	resource_size_t ostart, oend;
 	int type = 0; int other = 0;
-	struct resource *p;
+	struct resource *p, *dp;
+	bool is_type, covered;
+	struct resource res;
 
 	res.start = start;
 	res.end = start + size - 1;
 
 	for (p = parent->child; p ; p = p->sibling) {
-		bool is_type = (((p->flags & flags) == flags) &&
-				((desc == IORES_DESC_NONE) ||
-				 (desc == p->desc)));
-
-		if (resource_overlaps(p, &res))
-			is_type ? type++ : other++;
+		if (!resource_overlaps(p, &res))
+			continue;
+		is_type = (p->flags & flags) == flags &&
+			(desc == IORES_DESC_NONE || desc == p->desc);
+		if (is_type) {
+			type++;
+			continue;
+		}
+		/*
+		 * Continue to search in descendant resources as if the
+		 * matched descendant resources cover some ranges of 'p'.
+		 *
+		 * |------------- "CXL Window 0" ------------|
+		 * |-- "System RAM" --|
+		 *
+		 * will behave similar as the following fake resource
+		 * tree when searching "System RAM".
+		 *
+		 * |-- "System RAM" --||-- "CXL Window 0a" --|
+		 */
+		covered = false;
+		ostart = max(res.start, p->start);
+		oend = min(res.end, p->end);
+		for_each_resource(p, dp, false) {
+			if (!resource_overlaps(dp, &res))
+				continue;
+			is_type = (dp->flags & flags) == flags &&
+				(desc == IORES_DESC_NONE || desc == dp->desc);
+			if (is_type) {
+				type++;
+				/*
+				 * Range from 'ostart' to 'dp->start'
+				 * isn't covered by matched resource.
+				 */
+				if (dp->start > ostart)
+					break;
+				if (dp->end >= oend) {
+					covered = true;
+					break;
+				}
+				/* Remove covered range */
+				ostart = max(ostart, dp->end + 1);
+			}
+		}
+		if (!covered)
+			other++;
 	}
 
 	if (type == 0)

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

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

From: Andrii Nakryiko <[email protected]>

commit 905415ff3ffb1d7e5afa62bacabd79776bd24606 upstream.

Harden build ID parsing logic, adding explicit READ_ONCE() where it's important to have a consistent value read and validated just once.

Also, as pointed out by Andi Kleen, we need to make sure that entire ELF note is within a page bounds, so move the overflow check up and add an extra note_size boundaries validation.

Fixes tag below points to the code that moved this code into lib/buildid.c, and then subsequently was used in perf subsystem, making this code exposed to perf_event_open() users in v5.12+.

---
 lib/buildid.c |   76 +++++++++++++++++++++++++++++++++-------------------------
 1 file changed, 44 insertions(+), 32 deletions(-)

@@ -18,31 +18,37 @@ static int parse_build_id_buf(unsigned c
 			      const void *note_start,
 			      Elf32_Word note_size)
 {
-	Elf32_Word note_offs = 0, new_offs;
-
-	while (note_offs + sizeof(Elf32_Nhdr) < note_size) {
-		Elf32_Nhdr *nhdr = (Elf32_Nhdr *)(note_start + note_offs);
+	const char note_name[] = "GNU";
+	const size_t note_name_sz = sizeof(note_name);
+	u64 note_off = 0, new_off, name_sz, desc_sz;
+	const char *data;
+
+	while (note_off + sizeof(Elf32_Nhdr) < note_size &&
+	       note_off + sizeof(Elf32_Nhdr) > note_off /* overflow */) {
+		Elf32_Nhdr *nhdr = (Elf32_Nhdr *)(note_start + note_off);
+
+		name_sz = READ_ONCE(nhdr->n_namesz);
+		desc_sz = READ_ONCE(nhdr->n_descsz);
+
+		new_off = note_off + sizeof(Elf32_Nhdr);
+		if (check_add_overflow(new_off, ALIGN(name_sz, 4), &new_off) ||
+		    check_add_overflow(new_off, ALIGN(desc_sz, 4), &new_off) ||
+		    new_off > note_size)
+			break;
 
 		if (nhdr->n_type == BUILD_ID &&
-		    nhdr->n_namesz == sizeof("GNU") &&
-		    !strcmp((char *)(nhdr + 1), "GNU") &&
-		    nhdr->n_descsz > 0 &&
-		    nhdr->n_descsz <= BUILD_ID_SIZE_MAX) {
-			memcpy(build_id,
-			       note_start + note_offs +
-			       ALIGN(sizeof("GNU"), 4) + sizeof(Elf32_Nhdr),
-			       nhdr->n_descsz);
-			memset(build_id + nhdr->n_descsz, 0,
-			       BUILD_ID_SIZE_MAX - nhdr->n_descsz);
+		    name_sz == note_name_sz &&
+		    memcmp(nhdr + 1, note_name, note_name_sz) == 0 &&
+		    desc_sz > 0 && desc_sz <= BUILD_ID_SIZE_MAX) {
+			data = note_start + note_off + ALIGN(note_name_sz, 4);
+			memcpy(build_id, data, desc_sz);
+			memset(build_id + desc_sz, 0, BUILD_ID_SIZE_MAX - desc_sz);
 			if (size)
-				*size = nhdr->n_descsz;
+				*size = desc_sz;
 			return 0;
 		}
-		new_offs = note_offs + sizeof(Elf32_Nhdr) +
-			ALIGN(nhdr->n_namesz, 4) + ALIGN(nhdr->n_descsz, 4);
-		if (new_offs <= note_offs)  /* overflow */
-			break;
-		note_offs = new_offs;
+
+		note_off = new_off;
 	}
 
 	return -EINVAL;

@@ -71,7 +77,7 @@ static int get_build_id_32(const void *p
 {
 	Elf32_Ehdr *ehdr = (Elf32_Ehdr *)page_addr;
 	Elf32_Phdr *phdr;
-	int i;
+	__u32 i, phnum;
 
 	/*
 	 * FIXME

@@ -80,18 +86,19 @@ static int get_build_id_32(const void *p
 	 */
 	if (ehdr->e_phoff != sizeof(Elf32_Ehdr))
 		return -EINVAL;
+
+	phnum = READ_ONCE(ehdr->e_phnum);
 	/* only supports phdr that fits in one page */
-	if (ehdr->e_phnum >
-	    (PAGE_SIZE - sizeof(Elf32_Ehdr)) / sizeof(Elf32_Phdr))
+	if (phnum > (PAGE_SIZE - sizeof(Elf32_Ehdr)) / sizeof(Elf32_Phdr))
 		return -EINVAL;
 
 	phdr = (Elf32_Phdr *)(page_addr + sizeof(Elf32_Ehdr));
 
-	for (i = 0; i < ehdr->e_phnum; ++i) {
+	for (i = 0; i < phnum; ++i) {
 		if (phdr[i].p_type == PT_NOTE &&
 		    !parse_build_id(page_addr, build_id, size,
-				    page_addr + phdr[i].p_offset,
-				    phdr[i].p_filesz))
+				    page_addr + READ_ONCE(phdr[i].p_offset),
+				    READ_ONCE(phdr[i].p_filesz)))
 			return 0;
 	}
 	return -EINVAL;

@@ -103,7 +110,7 @@ static int get_build_id_64(const void *p
 {
 	Elf64_Ehdr *ehdr = (Elf64_Ehdr *)page_addr;
 	Elf64_Phdr *phdr;
-	int i;
+	__u32 i, phnum;
 
 	/*
 	 * FIXME

@@ -112,18 +119,19 @@ static int get_build_id_64(const void *p
 	 */
 	if (ehdr->e_phoff != sizeof(Elf64_Ehdr))
 		return -EINVAL;
+
+	phnum = READ_ONCE(ehdr->e_phnum);
 	/* only supports phdr that fits in one page */
-	if (ehdr->e_phnum >
-	    (PAGE_SIZE - sizeof(Elf64_Ehdr)) / sizeof(Elf64_Phdr))
+	if (phnum > (PAGE_SIZE - sizeof(Elf64_Ehdr)) / sizeof(Elf64_Phdr))
 		return -EINVAL;
 
 	phdr = (Elf64_Phdr *)(page_addr + sizeof(Elf64_Ehdr));
 
-	for (i = 0; i < ehdr->e_phnum; ++i) {
+	for (i = 0; i < phnum; ++i) {
 		if (phdr[i].p_type == PT_NOTE &&
 		    !parse_build_id(page_addr, build_id, size,
-				    page_addr + phdr[i].p_offset,
-				    phdr[i].p_filesz))
+				    page_addr + READ_ONCE(phdr[i].p_offset),
+				    READ_ONCE(phdr[i].p_filesz)))
 			return 0;
 	}
 	return -EINVAL;

@@ -152,6 +160,10 @@ int build_id_parse(struct vm_area_struct
 	page = find_get_page(vma->vm_file->f_mapping, 0);
 	if (!page)
 		return -EFAULT;	/* page not mapped */
+	if (!PageUptodate(page)) {
+		put_page(page);
+		return -EFAULT;
+	}
 
 	ret = -EINVAL;
 	page_addr = kmap_local_page(page);

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

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

From: Baokun Li <[email protected]>

commit f5cacdc6f2bb2a9bf214469dd7112b43dd2dd68a upstream.

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

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

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

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

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

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

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

@@ -89,8 +89,11 @@ __releases(&journal->j_state_lock)
 			write_unlock(&journal->j_state_lock);
 			if (chkpt) {
 				jbd2_log_do_checkpoint(journal);
-			} else if (jbd2_cleanup_journal_tail(journal) == 0) {
-				/* We were able to recover space; yay! */
+			} else if (jbd2_cleanup_journal_tail(journal) <= 0) {
+				/*
+				 * We were able to recover space or the
+				 * journal was aborted due to an error.
+				 */
 				;
 			} else if (has_transaction) {
 				/*

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

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

From: Kemeng Shi <[email protected]>

commit f0e3c14802515f60a47e6ef347ea59c2733402aa upstream.

Use tid_geq to compare tids to work over sequence number wraps.

---
 fs/jbd2/journal.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -710,7 +710,7 @@ int jbd2_fc_begin_commit(journal_t *jour
 		return -EINVAL;
 
 	write_lock(&journal->j_state_lock);
-	if (tid <= journal->j_commit_sequence) {
+	if (tid_geq(journal->j_commit_sequence, tid)) {
 		write_unlock(&journal->j_state_lock);
 		return -EALREADY;
 	}

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

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

From: Danilo Krummrich <[email protected]>

commit 1a83a716ec233990e1fd5b6fbb1200ade63bf450 upstream.

As long as krealloc() is called with __GFP_ZERO consistently, starting with the initial memory allocation, __GFP_ZERO should be fully honored.

However, if for an existing allocation krealloc() is called with a decreased size, it is not ensured that the spare portion the allocation is zeroed. Thus, if krealloc() is subsequently called with a larger size again, __GFP_ZERO can't be fully honored, since we don't know the previous size, but only the bucket size.

Example:

	buf = kzalloc(64, GFP_KERNEL);
	memset(buf, 0xff, 64);

	buf = krealloc(buf, 48, GFP_KERNEL | __GFP_ZERO);

	/* After this call the last 16 bytes are still 0xff. */
	buf = krealloc(buf, 64, GFP_KERNEL | __GFP_ZERO);

Fix this, by explicitly setting spare memory to zero, when shrinking an allocation with __GFP_ZERO flag set or init_on_alloc enabled.

---
 mm/slab_common.c |    7 +++++++
 1 file changed, 7 insertions(+)

@@ -1273,6 +1273,13 @@ __do_krealloc(const void *p, size_t new_
 
 	/* If the object still fits, repoison it precisely. */
 	if (ks >= new_size) {
+		/* Zero out spare memory. */
+		if (want_init_on_alloc(flags)) {
+			kasan_disable_current();
+			memset((void *)p + new_size, 0, ks - new_size);
+			kasan_enable_current();
+		}
+
 		p = kasan_krealloc((void *)p, new_size, flags);
 		return (void *)p;
 	}

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

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

From: Heming Zhao <[email protected]>

commit dfe6c5692fb525e5e90cefe306ee0dffae13d35f upstream.

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

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

@@ -1002,6 +1002,25 @@ static int ocfs2_sync_local_to_main(stru
 		start = bit_off + 1;
 	}
 
+	/* clear the contiguous bits until the end boundary */
+	if (count) {
+		blkno = la_start_blk +
+			ocfs2_clusters_to_blocks(osb->sb,
+					start - count);
+
+		trace_ocfs2_sync_local_to_main_free(
+				count, start - count,
+				(unsigned long long)la_start_blk,
+				(unsigned long long)blkno);
+
+		status = ocfs2_release_clusters(handle,
+				main_bm_inode,
+				main_bm_bh, blkno,
+				count);
+		if (status < 0)
+			mlog_errno(status);
+	}
+
 bail:
 	if (status)
 		mlog_errno(status);

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

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

From: Joseph Qi <[email protected]>

commit 2af148ef8549a12f8025286b8825c2833ee6bcb8 upstream.

syzbot reported an uninit-value BUG:

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

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

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

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

@@ -156,9 +156,8 @@ int ocfs2_get_block(struct inode *inode,
 	err = ocfs2_extent_map_get_blocks(inode, iblock, &p_blkno, &count,
 					  &ext_flags);
 	if (err) {
-		mlog(ML_ERROR, "Error %d from get_blocks(0x%p, %llu, 1, "
-		     "%llu, NULL)\n", err, inode, (unsigned long long)iblock,
-		     (unsigned long long)p_blkno);
+		mlog(ML_ERROR, "get_blocks() failed, inode: 0x%p, "
+		     "block: %llu\n", inode, (unsigned long long)iblock);
 		goto bail;
 	}
 

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

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

From: Gautham Ananthakrishna <[email protected]>

commit 5ca60b86f57a4d9648f68418a725b3a7de2816b0 upstream.

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

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

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

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

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

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

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

@@ -25,6 +25,7 @@
 #include "namei.h"
 #include "ocfs2_trace.h"
 #include "file.h"
+#include "symlink.h"
 
 #include <linux/bio.h>
 #include <linux/blkdev.h>

@@ -4155,8 +4156,9 @@ static int __ocfs2_reflink(struct dentry
 	int ret;
 	struct inode *inode = d_inode(old_dentry);
 	struct buffer_head *new_bh = NULL;
+	struct ocfs2_inode_info *oi = OCFS2_I(inode);
 
-	if (OCFS2_I(inode)->ip_flags & OCFS2_INODE_SYSTEM_FILE) {
+	if (oi->ip_flags & OCFS2_INODE_SYSTEM_FILE) {
 		ret = -EINVAL;
 		mlog_errno(ret);
 		goto out;

@@ -4182,6 +4184,26 @@ static int __ocfs2_reflink(struct dentry
 		goto out_unlock;
 	}
 
+	if ((oi->ip_dyn_features & OCFS2_HAS_XATTR_FL) &&
+	    (oi->ip_dyn_features & OCFS2_INLINE_XATTR_FL)) {
+		/*
+		 * Adjust extent record count to reserve space for extended attribute.
+		 * Inline data count had been adjusted in ocfs2_duplicate_inline_data().
+		 */
+		struct ocfs2_inode_info *new_oi = OCFS2_I(new_inode);
+
+		if (!(new_oi->ip_dyn_features & OCFS2_INLINE_DATA_FL) &&
+		    !(ocfs2_inode_is_fast_symlink(new_inode))) {
+			struct ocfs2_dinode *new_di = (struct ocfs2_dinode *)new_bh->b_data;
+			struct ocfs2_dinode *old_di = (struct ocfs2_dinode *)old_bh->b_data;
+			struct ocfs2_extent_list *el = &new_di->id2.i_list;
+			int inline_size = le16_to_cpu(old_di->i_xattr_inline_size);
+
+			le16_add_cpu(&el->l_count, -(inline_size /
+					sizeof(struct ocfs2_extent_rec)));
+		}
+	}
+
 	ret = ocfs2_create_reflink_node(inode, old_bh,
 					new_inode, new_bh, preserve);
 	if (ret) {

@@ -4189,7 +4211,7 @@ static int __ocfs2_reflink(struct dentry
 		goto inode_unlock;
 	}
 
-	if (OCFS2_I(inode)->ip_dyn_features & OCFS2_HAS_XATTR_FL) {
+	if (oi->ip_dyn_features & OCFS2_HAS_XATTR_FL) {
 		ret = ocfs2_reflink_xattrs(inode, old_bh,
 					   new_inode, new_bh,
 					   preserve);

@@ -6520,16 +6520,7 @@ static int ocfs2_reflink_xattr_inline(st
 	}
 
 	new_oi = OCFS2_I(args->new_inode);
-	/*
-	 * Adjust extent record count to reserve space for extended attribute.
-	 * Inline data count had been adjusted in ocfs2_duplicate_inline_data().
-	 */
-	if (!(new_oi->ip_dyn_features & OCFS2_INLINE_DATA_FL) &&
-	    !(ocfs2_inode_is_fast_symlink(args->new_inode))) {
-		struct ocfs2_extent_list *el = &new_di->id2.i_list;
-		le16_add_cpu(&el->l_count, -(inline_size /
-					sizeof(struct ocfs2_extent_rec)));
-	}
+
 	spin_lock(&new_oi->ip_lock);
 	new_oi->ip_dyn_features |= OCFS2_HAS_XATTR_FL | OCFS2_INLINE_XATTR_FL;
 	new_di->i_dyn_features = cpu_to_le16(new_oi->ip_dyn_features);

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

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

From: Joseph Qi <[email protected]>

commit 35fccce29feb3706f649726d410122dd81b92c18 upstream.

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

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

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

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

@@ -692,7 +692,7 @@ static int ocfs2_local_read_info(struct
 	int status;
 	struct buffer_head *bh = NULL;
 	struct ocfs2_quota_recovery *rec;
-	int locked = 0;
+	int locked = 0, global_read = 0;
 
 	info->dqi_max_spc_limit = 0x7fffffffffffffffLL;
 	info->dqi_max_ino_limit = 0x7fffffffffffffffLL;

@@ -700,6 +700,7 @@ static int ocfs2_local_read_info(struct
 	if (!oinfo) {
 		mlog(ML_ERROR, "failed to allocate memory for ocfs2 quota"
 			       " info.");
+		status = -ENOMEM;
 		goto out_err;
 	}
 	info->dqi_priv = oinfo;

@@ -712,6 +713,7 @@ static int ocfs2_local_read_info(struct
 	status = ocfs2_global_read_info(sb, type);
 	if (status < 0)
 		goto out_err;
+	global_read = 1;
 
 	status = ocfs2_inode_lock(lqinode, &oinfo->dqi_lqi_bh, 1);
 	if (status < 0) {

@@ -782,10 +784,12 @@ out_err:
 		if (locked)
 			ocfs2_inode_unlock(lqinode, 1);
 		ocfs2_release_local_quota_bitmaps(&oinfo->dqi_chunk);
+		if (global_read)
+			cancel_delayed_work_sync(&oinfo->dqi_sync_work);
 		kfree(oinfo);
 	}
 	brelse(bh);
-	return -1;
+	return status;
 }
 
 /* Write local info to quota file */

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

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

From: Lizhi Xu <[email protected]>

commit c03a82b4a0c935774afa01fd6d128b444fd930a1 upstream.

Patch series "Misc fixes for ocfs2_read_blocks", v5.

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

This patch (of 2):

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

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

@@ -235,7 +235,6 @@ int ocfs2_read_blocks(struct ocfs2_cachi
 		if (bhs[i] == NULL) {
 			bhs[i] = sb_getblk(sb, block++);
 			if (bhs[i] == NULL) {
-				ocfs2_metadata_cache_io_unlock(ci);
 				status = -ENOMEM;
 				mlog_errno(status);
 				/* Don't forget to put previous bh! */

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

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

From: Julian Sun <[email protected]>

commit 5784d9fcfd43bd853654bb80c87ef293b9e8e80a upstream.

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

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

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

@@ -1055,7 +1055,7 @@ void ocfs2_journal_shutdown(struct ocfs2
 	if (!igrab(inode))
 		BUG();
 
-	num_running_trans = atomic_read(&(osb->journal->j_num_trans));
+	num_running_trans = atomic_read(&(journal->j_num_trans));
 	trace_ocfs2_journal_shutdown(num_running_trans);
 
 	/* Do a commit_cache here. It will flush our journal, *and*

@@ -1074,9 +1074,10 @@ void ocfs2_journal_shutdown(struct ocfs2
 		osb->commit_task = NULL;
 	}
 
-	BUG_ON(atomic_read(&(osb->journal->j_num_trans)) != 0);
+	BUG_ON(atomic_read(&(journal->j_num_trans)) != 0);
 
-	if (ocfs2_mount_local(osb)) {
+	if (ocfs2_mount_local(osb) &&
+	    (journal->j_journal->j_flags & JBD2_LOADED)) {
 		jbd2_journal_lock_updates(journal->j_journal);
 		status = jbd2_journal_flush(journal->j_journal, 0);
 		jbd2_journal_unlock_updates(journal->j_journal);

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

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

From: Lizhi Xu <[email protected]>

commit 33b525cef4cff49e216e4133cc48452e11c0391e upstream.

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

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

@@ -388,7 +388,8 @@ read_failure:
 		/* Always set the buffer in the cache, even if it was
 		 * a forced read, or read-ahead which hasn't yet
 		 * completed. */
-		ocfs2_set_buffer_uptodate(ci, bh);
+		if (bh)
+			ocfs2_set_buffer_uptodate(ci, bh);
 	}
 	ocfs2_metadata_cache_io_unlock(ci);
 

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

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

From: Kuan-Ying Lee <[email protected]>

commit a633a4b8001a7f2a12584f267a3280990d9ababa upstream.

Patch series "Fix some GDB command error and add some GDB commands", v3.

Fix some GDB command errors and add some useful GDB commands.

This patch (of 5):

Commit 7988e5ae2be7 ("tick: Split nohz and highres features from nohz_mode") and commit 7988e5ae2be7 ("tick: Split nohz and highres features from nohz_mode") move 'tick_stopped' and 'nohz_mode' to flags field which will break the gdb lx-mounts command:

(gdb) lx-timerlist
Python Exception <class 'gdb.error'>: There is no member named nohz_mode. Error occurred in Python: There is no member named nohz_mode.

(gdb) lx-timerlist
Python Exception <class 'gdb.error'>: There is no member named tick_stopped. Error occurred in Python: There is no member named tick_stopped.

We move 'tick_stopped' and 'nohz_mode' to flags field instead.

---
 scripts/gdb/linux/timerlist.py |   31 ++++++++++++++++---------------
 1 file changed, 16 insertions(+), 15 deletions(-)

@@ -87,21 +87,22 @@ def print_cpu(hrtimer_bases, cpu, max_cl
             text += "\n"
 
         if constants.LX_CONFIG_TICK_ONESHOT:
-            fmts = [("  .{}      : {}", 'nohz_mode'),
-                    ("  .{}      : {} nsecs", 'last_tick'),
-                    ("  .{}   : {}", 'tick_stopped'),
-                    ("  .{}   : {}", 'idle_jiffies'),
-                    ("  .{}     : {}", 'idle_calls'),
-                    ("  .{}    : {}", 'idle_sleeps'),
-                    ("  .{} : {} nsecs", 'idle_entrytime'),
-                    ("  .{}  : {} nsecs", 'idle_waketime'),
-                    ("  .{}  : {} nsecs", 'idle_exittime'),
-                    ("  .{} : {} nsecs", 'idle_sleeptime'),
-                    ("  .{}: {} nsecs", 'iowait_sleeptime'),
-                    ("  .{}   : {}", 'last_jiffies'),
-                    ("  .{}     : {}", 'next_timer'),
-                    ("  .{}   : {} nsecs", 'idle_expires')]
-            text += "\n".join([s.format(f, ts[f]) for s, f in fmts])
+            TS_FLAG_STOPPED = 1 << 1
+            TS_FLAG_NOHZ = 1 << 4
+            text += f"  .{'nohz':15s}: {int(bool(ts['flags'] & TS_FLAG_NOHZ))}\n"
+            text += f"  .{'last_tick':15s}: {ts['last_tick']}\n"
+            text += f"  .{'tick_stopped':15s}: {int(bool(ts['flags'] & TS_FLAG_STOPPED))}\n"
+            text += f"  .{'idle_jiffies':15s}: {ts['idle_jiffies']}\n"
+            text += f"  .{'idle_calls':15s}: {ts['idle_calls']}\n"
+            text += f"  .{'idle_sleeps':15s}: {ts['idle_sleeps']}\n"
+            text += f"  .{'idle_entrytime':15s}: {ts['idle_entrytime']} nsecs\n"
+            text += f"  .{'idle_waketime':15s}: {ts['idle_waketime']} nsecs\n"
+            text += f"  .{'idle_exittime':15s}: {ts['idle_exittime']} nsecs\n"
+            text += f"  .{'idle_sleeptime':15s}: {ts['idle_sleeptime']} nsecs\n"
+            text += f"  .{'iowait_sleeptime':15s}: {ts['iowait_sleeptime']} nsecs\n"
+            text += f"  .{'last_jiffies':15s}: {ts['last_jiffies']}\n"
+            text += f"  .{'next_timer':15s}: {ts['next_timer']}\n"
+            text += f"  .{'idle_expires':15s}: {ts['idle_expires']} nsecs\n"
             text += "\njiffies: {}\n".format(jiffies)
 
         text += "\n"

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

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

From: Kuan-Ying Lee <[email protected]>

commit 0c77e103c45fa1b119f5d3bb4625eee081c1a6cf upstream.

Add inorder iteration function for rbtree usage.

This is a preparation patch for the next patch to fix the gdb mounts issue.

---
 scripts/gdb/linux/rbtree.py |   12 ++++++++++++
 1 file changed, 12 insertions(+)

@@ -9,6 +9,18 @@ from linux import utils
 rb_root_type = utils.CachedType("struct rb_root")
 rb_node_type = utils.CachedType("struct rb_node")
 
+def rb_inorder_for_each(root):
+    def inorder(node):
+        if node:
+            yield from inorder(node['rb_left'])
+            yield node
+            yield from inorder(node['rb_right'])
+
+    yield from inorder(root['rb_node'])
+
+def rb_inorder_for_each_entry(root, gdbtype, member):
+    for node in rb_inorder_for_each(root):
+        yield utils.container_of(node, gdbtype, member)
 
 def rb_first(root):
     if root.type == rb_root_type.get_type():

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

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

From: Kuan-Ying Lee <[email protected]>

commit 4b183f613924ad536be2f8bd12b307e9c5a96bf6 upstream.

(gdb) lx-mounts
mount super_block devname pathname fstype options
Python Exception <class 'gdb.error'>: There is no member named list. Error occurred in Python: There is no member named list.

We encounter the above issue after commit 2eea9ce4310d ("mounts: keep list of mounts in an rbtree"). The commit move a mount from list into rbtree.

So we can instead use rbtree to iterate all mounts information.

---
 scripts/gdb/linux/proc.py |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

@@ -18,6 +18,7 @@ from linux import utils
 from linux import tasks
 from linux import lists
 from linux import vfs
+from linux import rbtree
 from struct import *
 
 

@@ -172,8 +173,7 @@ values of that process namespace"""
         gdb.write("{:^18} {:^15} {:>9} {} {} options\n".format(
                   "mount", "super_block", "devname", "pathname", "fstype"))
 
-        for mnt in lists.list_for_each_entry(namespace['list'],
-                                             mount_ptr_type, "mnt_list"):
+        for mnt in rbtree.rb_inorder_for_each_entry(namespace['mounts'], mount_ptr_type, "mnt_node"):
             devname = mnt['mnt_devname'].string()
             devname = devname if devname else "none"
 

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

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

From: Mark Rutland <[email protected]>

commit b3d6121eaeb22aee8a02f46706745b1968cc0292 upstream.

The Kconfig logic to select HAVE_DYNAMIC_FTRACE_WITH_ARGS is incorrect, and HAVE_DYNAMIC_FTRACE_WITH_ARGS may be selected when it is not supported by the combination of clang and GNU LD, resulting in link-time errors:

aarch64-linux-gnu-ld: .init.data has both ordered [__patchable_function_entries' in init/main.o] and unordered [.meminit.data' in mm/sparse.o] sections
aarch64-linux-gnu-ld: final link failed: bad value

... which can be seen when building with CC=clang using a binutils version older than 2.36.

We originally fixed that in commit:

45bd8951806eb5e8 ("arm64: Improve HAVE_DYNAMIC_FTRACE_WITH_REGS selection for clang")

... by splitting the "select HAVE_DYNAMIC_FTRACE_WITH_ARGS" statement into separete CLANG_SUPPORTS_DYNAMIC_FTRACE_WITH_ARGS and GCC_SUPPORTS_DYNAMIC_FTRACE_WITH_ARGS options which individually select HAVE_DYNAMIC_FTRACE_WITH_ARGS.

Subsequently we accidentally re-introduced the common "select HAVE_DYNAMIC_FTRACE_WITH_ARGS" statement in commit:

26299b3f6ba26bfc ("ftrace: arm64: move from REGS to ARGS")

... then we removed it again in commit:

68a63a412d18bd2e ("arm64: Fix build with CC=clang, CONFIG_FTRACE=y and CONFIG_STACK_TRACER=y")

... then we accidentally re-introduced it again in commit:

2aa6ac03516d078c ("arm64: ftrace: Add direct call support")

Fix this for the third time by keeping the unified select statement and making this depend onf either GCC_SUPPORTS_DYNAMIC_FTRACE_WITH_ARGS or CLANG_SUPPORTS_DYNAMIC_FTRACE_WITH_ARGS. This is more consistent with usual style and less likely to go wrong in future.

---
 arch/arm64/Kconfig |    5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

@@ -196,7 +196,8 @@ config ARM64
 	select HAVE_DMA_CONTIGUOUS
 	select HAVE_DYNAMIC_FTRACE
 	select HAVE_DYNAMIC_FTRACE_WITH_ARGS \
-		if $(cc-option,-fpatchable-function-entry=2)
+		if (GCC_SUPPORTS_DYNAMIC_FTRACE_WITH_ARGS || \
+		    CLANG_SUPPORTS_DYNAMIC_FTRACE_WITH_ARGS)
 	select HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS \
 		if DYNAMIC_FTRACE_WITH_ARGS && DYNAMIC_FTRACE_WITH_CALL_OPS
 	select HAVE_DYNAMIC_FTRACE_WITH_CALL_OPS \

@@ -269,12 +270,10 @@ config CLANG_SUPPORTS_DYNAMIC_FTRACE_WIT
 	def_bool CC_IS_CLANG
 	# https://github.com/ClangBuiltLinux/linux/issues/1507
 	depends on AS_IS_GNU || (AS_IS_LLVM && (LD_IS_LLD || LD_VERSION >= 23600))
-	select HAVE_DYNAMIC_FTRACE_WITH_ARGS
 
 config GCC_SUPPORTS_DYNAMIC_FTRACE_WITH_ARGS
 	def_bool CC_IS_GCC
 	depends on $(cc-option,-fpatchable-function-entry=2)
-	select HAVE_DYNAMIC_FTRACE_WITH_ARGS
 
 config 64BIT
 	def_bool y

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

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

From: Easwar Hariharan <[email protected]>

commit 3eddb108abe3de6723cc4b77e8558ce1b3047987 upstream.

Add the Microsoft Azure Cobalt 100 CPU to the list of CPUs suffering from erratum 3194386 added in commit 75b3c43eab59 ("arm64: errata:
Expand speculative SSBS workaround")

---
 Documentation/arch/arm64/silicon-errata.rst |    2 ++
 arch/arm64/kernel/cpu_errata.c              |    1 +
 2 files changed, 3 insertions(+)

@@ -289,3 +289,5 @@ stable kernels.
 +----------------+-----------------+-----------------+-----------------------------+
 | Microsoft      | Azure Cobalt 100| #2253138        | ARM64_ERRATUM_2253138       |
 +----------------+-----------------+-----------------+-----------------------------+
+| Microsoft      | Azure Cobalt 100| #3324339        | ARM64_ERRATUM_3194386       |
++----------------+-----------------+-----------------+-----------------------------+

@@ -447,6 +447,7 @@ static const struct midr_range erratum_s
 	MIDR_ALL_VERSIONS(MIDR_CORTEX_X3),
 	MIDR_ALL_VERSIONS(MIDR_CORTEX_X4),
 	MIDR_ALL_VERSIONS(MIDR_CORTEX_X925),
+	MIDR_ALL_VERSIONS(MIDR_MICROSOFT_AZURE_COBALT_100),
 	MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N1),
 	MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N2),
 	MIDR_ALL_VERSIONS(MIDR_NEOVERSE_V1),

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

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

From: Matthew Auld <[email protected]>

commit 2d2be279f1ca9e7288282d4214f16eea8a727cdb upstream.

We currently do stuff like queuing the final destruction step on a random system wq, which will outlive the driver instance. With bad timing we can teardown the driver with one or more work workqueue still being alive leading to various UAF splats. Add a fini step to ensure user queues are properly torn down. At this point GuC should already be nuked so queue itself should no longer be referenced from hw pov.

v2 (Matt B)
- Looks much safer to use a waitqueue and then just wait for the xa_array to become empty before triggering the drain.

---
 drivers/gpu/drm/xe/xe_device.c       |    6 +++++-
 drivers/gpu/drm/xe/xe_device_types.h |    3 +++
 drivers/gpu/drm/xe/xe_guc_submit.c   |   26 +++++++++++++++++++++++++-
 drivers/gpu/drm/xe/xe_guc_types.h    |    2 ++
 4 files changed, 35 insertions(+), 2 deletions(-)

@@ -285,6 +285,9 @@ static void xe_device_destroy(struct drm
 	if (xe->unordered_wq)
 		destroy_workqueue(xe->unordered_wq);
 
+	if (xe->destroy_wq)
+		destroy_workqueue(xe->destroy_wq);
+
 	ttm_device_fini(&xe->ttm);
 }
 

@@ -350,8 +353,9 @@ struct xe_device *xe_device_create(struc
 	xe->preempt_fence_wq = alloc_ordered_workqueue("xe-preempt-fence-wq", 0);
 	xe->ordered_wq = alloc_ordered_workqueue("xe-ordered-wq", 0);
 	xe->unordered_wq = alloc_workqueue("xe-unordered-wq", 0, 0);
+	xe->destroy_wq = alloc_workqueue("xe-destroy-wq", 0, 0);
 	if (!xe->ordered_wq || !xe->unordered_wq ||
-	    !xe->preempt_fence_wq) {
+	    !xe->preempt_fence_wq || !xe->destroy_wq) {
 		/*
 		 * Cleanup done in xe_device_destroy via
 		 * drmm_add_action_or_reset register above

@@ -392,6 +392,9 @@ struct xe_device {
 	/** @unordered_wq: used to serialize unordered work, mostly display */
 	struct workqueue_struct *unordered_wq;
 
+	/** @destroy_wq: used to serialize user destroy work, like queue */
+	struct workqueue_struct *destroy_wq;
+
 	/** @tiles: device tiles */
 	struct xe_tile tiles[XE_MAX_TILES_PER_DEVICE];
 

@@ -276,10 +276,26 @@ static struct workqueue_struct *get_subm
 }
 #endif
 
+static void xe_guc_submit_fini(struct xe_guc *guc)
+{
+	struct xe_device *xe = guc_to_xe(guc);
+	struct xe_gt *gt = guc_to_gt(guc);
+	int ret;
+
+	ret = wait_event_timeout(guc->submission_state.fini_wq,
+				 xa_empty(&guc->submission_state.exec_queue_lookup),
+				 HZ * 5);
+
+	drain_workqueue(xe->destroy_wq);
+
+	xe_gt_assert(gt, ret);
+}
+
 static void guc_submit_fini(struct drm_device *drm, void *arg)
 {
 	struct xe_guc *guc = arg;
 
+	xe_guc_submit_fini(guc);
 	xa_destroy(&guc->submission_state.exec_queue_lookup);
 	free_submit_wq(guc);
 }