Skip to contentSkip to conversation

5.10.241-rc1 review

PATCH In review Greg Kroah-Hartman 7 participants 531 messages Aug 26, 2025 – Aug 28, 2025 Page 2 of 4

Subsystems (6)
lore
Share & tools
lore
author maintainer
#139 lore raw

PATCH 139/523 dmaengine: nbpfaxi: Add missing check after DMA map

In reply to Greg Kroah-Hartman

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

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

From: Thomas Fourier <[email protected]>

[ Upstream commit c6ee78fc8f3e653bec427cfd06fec7877ee782bd ]

The DMA map functions can fail and should be tested for errors. If the mapping fails, unmap and return an error.

Fixes b45b262cefd5 ("dmaengine: add a driver for AMBA AXI NBPF DMAC IP cores")
---
 drivers/dma/nbpfaxi.c | 13 +++++++++++++
 1 file changed, 13 insertions(+)
drivers/dma/nbpfaxi.c +13 -0
index bbedf57e3612..94e7e3290691 100644
@@ -712,6 +712,9 @@ static int nbpf_desc_page_alloc(struct nbpf_channel *chan)
 		list_add_tail(&ldesc->node, &lhead);
 		ldesc->hwdesc_dma_addr = dma_map_single(dchan->device->dev,
 					hwdesc, sizeof(*hwdesc), DMA_TO_DEVICE);
+		if (dma_mapping_error(dchan->device->dev,
+				      ldesc->hwdesc_dma_addr))
+			goto unmap_error;
 
 		dev_dbg(dev, "%s(): mapped 0x%p to %pad\n", __func__,
 			hwdesc, &ldesc->hwdesc_dma_addr);
@@ -738,6 +741,16 @@ static int nbpf_desc_page_alloc(struct nbpf_channel *chan)
 	spin_unlock_irq(&chan->lock);
 
 	return ARRAY_SIZE(dpage->desc);
+
+unmap_error:
+	while (i--) {
+		ldesc--; hwdesc--;
+
+		dma_unmap_single(dchan->device->dev, ldesc->hwdesc_dma_addr,
+				 sizeof(hwdesc), DMA_TO_DEVICE);
+	}
+
+	return -ENOMEM;
 }
 
 static void nbpf_desc_put(struct nbpf_desc *desc)
Signature · 1 line
2.39.5
author maintainer
#140 lore raw

PATCH 140/523 sh: Do not use hyphen in exported variable name

In reply to Greg Kroah-Hartman

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

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

From: Ben Hutchings <[email protected]>

[ Upstream commit c32969d0362a790fbc6117e0b6a737a7e510b843 ]

arch/sh/Makefile defines and exports ld-bfd to be used by arch/sh/boot/compressed/Makefile and arch/sh/boot/romimage/Makefile. However some shells, including dash, will not pass through environment variables whose name includes a hyphen. Usually GNU make does not use a shell to recurse, but if e.g. $(srctree) contains '~' it will use a shell here.

Other instances of this problem were previously fixed by commits 2bfbe7881ee0 "kbuild: Do not use hyphen in exported variable name" and 82977af93a0d "sh: rename suffix-y to suffix_y".

Rename the variable to ld_bfd.

References: https://buildd.debian.org/status/fetch.php?pkg=linux&arch=sh4&ver=4.13%7Erc5-1%7Eexp1&stamp=1502943967&raw=0

Fixes 7b022d07a0fd ("sh: Tidy up the ldscript output format specifier.")
---
 arch/sh/Makefile                 | 10 +++++-----
 arch/sh/boot/compressed/Makefile |  4 ++--
 arch/sh/boot/romimage/Makefile   |  4 ++--
 3 files changed, 9 insertions(+), 9 deletions(-)
arch/sh/Makefile +5 -5
index 2faebfd72eca..8e8e24227fff 100644
@@ -103,16 +103,16 @@ UTS_MACHINE		:= sh
 LDFLAGS_vmlinux		+= -e _stext
 
 ifdef CONFIG_CPU_LITTLE_ENDIAN
-ld-bfd			:= elf32-sh-linux
-LDFLAGS_vmlinux		+= --defsym jiffies=jiffies_64 --oformat $(ld-bfd)
+ld_bfd			:= elf32-sh-linux
+LDFLAGS_vmlinux		+= --defsym jiffies=jiffies_64 --oformat $(ld_bfd)
 KBUILD_LDFLAGS		+= -EL
 else
-ld-bfd			:= elf32-shbig-linux
-LDFLAGS_vmlinux		+= --defsym jiffies=jiffies_64+4 --oformat $(ld-bfd)
+ld_bfd			:= elf32-shbig-linux
+LDFLAGS_vmlinux		+= --defsym jiffies=jiffies_64+4 --oformat $(ld_bfd)
 KBUILD_LDFLAGS		+= -EB
 endif
 
-export ld-bfd
+export ld_bfd
 
 head-y	:= arch/sh/kernel/head_32.o
 
arch/sh/boot/compressed/Makefile +2 -2
index 589d2d8a573d..d4baaaace17f 100644
@@ -30,7 +30,7 @@ endif
 
 ccflags-remove-$(CONFIG_MCOUNT) += -pg
 
-LDFLAGS_vmlinux := --oformat $(ld-bfd) -Ttext $(IMAGE_OFFSET) -e startup \
+LDFLAGS_vmlinux := --oformat $(ld_bfd) -Ttext $(IMAGE_OFFSET) -e startup \
 		   -T $(obj)/../../kernel/vmlinux.lds
 
 #
@@ -68,7 +68,7 @@ $(obj)/vmlinux.bin.lzo: $(vmlinux.bin.all-y) FORCE
 
 OBJCOPYFLAGS += -R .empty_zero_page
 
-LDFLAGS_piggy.o := -r --format binary --oformat $(ld-bfd) -T
+LDFLAGS_piggy.o := -r --format binary --oformat $(ld_bfd) -T
 
 $(obj)/piggy.o: $(obj)/vmlinux.scr $(obj)/vmlinux.bin.$(suffix-y) FORCE
 	$(call if_changed,ld)
arch/sh/boot/romimage/Makefile +2 -2
index c7c8be58400c..17b03df0a8de 100644
@@ -13,7 +13,7 @@ mmcif-obj-$(CONFIG_CPU_SUBTYPE_SH7724)	:= $(obj)/mmcif-sh7724.o
 load-$(CONFIG_ROMIMAGE_MMCIF)		:= $(mmcif-load-y)
 obj-$(CONFIG_ROMIMAGE_MMCIF)		:= $(mmcif-obj-y)
 
-LDFLAGS_vmlinux := --oformat $(ld-bfd) -Ttext $(load-y) -e romstart \
+LDFLAGS_vmlinux := --oformat $(ld_bfd) -Ttext $(load-y) -e romstart \
 		   -T $(obj)/../../kernel/vmlinux.lds
 
 $(obj)/vmlinux: $(obj)/head.o $(obj-y) $(obj)/piggy.o FORCE
@@ -24,7 +24,7 @@ OBJCOPYFLAGS += -j .empty_zero_page
 $(obj)/zeropage.bin: vmlinux FORCE
 	$(call if_changed,objcopy)
 
-LDFLAGS_piggy.o := -r --format binary --oformat $(ld-bfd) -T
+LDFLAGS_piggy.o := -r --format binary --oformat $(ld_bfd) -T
 
 $(obj)/piggy.o: $(obj)/vmlinux.scr $(obj)/zeropage.bin arch/sh/boot/zImage FORCE
 	$(call if_changed,ld)
Signature · 1 line
2.39.5
author maintainer
#141 lore raw

PATCH 141/523 crypto: qat - fix seq_file position update in adf_ring_next()

In reply to Greg Kroah-Hartman

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

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

From: Giovanni Cabiddu <[email protected]>

[ Upstream commit 6908c5f4f066a0412c3d9a6f543a09fa7d87824b ]

The adf_ring_next() function in the QAT debug transport interface fails to correctly update the position index when reaching the end of the ring elements. This triggers the following kernel warning when reading ring files, such as /sys/kernel/debug/qat_c6xx_<D:B:D:F>/transport/bank_00/ring_00:

   [27725.022965] seq_file: buggy .next function adf_ring_next [intel_qat] did not update position index

Ensure that the *pos index is incremented before returning NULL when after the last element in the ring is found, satisfying the seq_file API requirements and preventing the warning.

Fixes a672a9dc872e ("crypto: qat - Intel(R) QAT transport code")
---
 drivers/crypto/qat/qat_common/adf_transport_debug.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)
drivers/crypto/qat/qat_common/adf_transport_debug.c +3 -1
index e6bdbd3c9b1f..b0a553d680dc 100644
@@ -31,8 +31,10 @@ static void *adf_ring_next(struct seq_file *sfile, void *v, loff_t *pos)
 	struct adf_etr_ring_data *ring = sfile->private;
 
 	if (*pos >= (ADF_SIZE_TO_RING_SIZE_IN_BYTES(ring->ring_size) /
-		     ADF_MSG_SIZE_TO_BYTES(ring->msg_size)))
+		     ADF_MSG_SIZE_TO_BYTES(ring->msg_size))) {
+		(*pos)++;
 		return NULL;
+	}
 
 	return ring->base_addr +
 		(ADF_MSG_SIZE_TO_BYTES(ring->msg_size) * (*pos)++);
Signature · 1 line
2.39.5
author maintainer
#142 lore raw

PATCH 142/523 fbdev: imxfb: Check fb_add_videomode to prevent null-ptr-deref

In reply to Greg Kroah-Hartman

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

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

From: Chenyuan Yang <[email protected]>

[ Upstream commit da11e6a30e0bb8e911288bdc443b3dc8f6a7cac7 ]

fb_add_videomode() can fail with -ENOMEM when its internal kmalloc() cannot allocate a struct fb_modelist. If that happens, the modelist stays empty but the driver continues to register. Add a check for its return value to prevent poteintial null-ptr-deref, which is similar to the commit 17186f1f90d3 ("fbdev:
Fix do_register_framebuffer to prevent null-ptr-deref in fb_videomode_to_var").

Fixes 1b6c79361ba5 ("video: imxfb: Add DT support")
---
 drivers/video/fbdev/imxfb.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)
drivers/video/fbdev/imxfb.c +7 -2
index d663e080b157..91f041f3a56f 100644
@@ -1007,8 +1007,13 @@ static int imxfb_probe(struct platform_device *pdev)
 
 
 	INIT_LIST_HEAD(&info->modelist);
-	for (i = 0; i < fbi->num_modes; i++)
-		fb_add_videomode(&fbi->mode[i].mode, &info->modelist);
+	for (i = 0; i < fbi->num_modes; i++) {
+		ret = fb_add_videomode(&fbi->mode[i].mode, &info->modelist);
+		if (ret) {
+			dev_err(&pdev->dev, "Failed to add videomode\n");
+			goto failed_cmap;
+		}
+	}
 
 	/*
 	 * This makes sure that our colour bitfield
Signature · 1 line
2.39.5
author maintainer
#143 lore raw

PATCH 143/523 jfs: fix metapage reference count leak in dbAllocCtl

In reply to Greg Kroah-Hartman

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

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

From: Zheng Yu <[email protected]>

[ Upstream commit 856db37592021e9155384094e331e2d4589f28b1 ]

In dbAllocCtl(), read_metapage() increases the reference count of the metapage. However, when dp->tree.budmin < 0, the function returns -EIO without calling release_metapage() to decrease the reference count, leading to a memory leak.

Add release_metapage(mp) before the error return to properly manage the metapage reference count and prevent the leak.

Fixes a5f5e4698f8abbb25fe4959814093fb5bfa1aa9d ("jfs: fix shift-out-of-bounds in dbSplit")
---
 fs/jfs/jfs_dmap.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)
fs/jfs/jfs_dmap.c +3 -1
index 37888187b977..234b7cc4acfa 100644
@@ -1877,8 +1877,10 @@ dbAllocCtl(struct bmap * bmp, s64 nblocks, int l2nb, s64 blkno, s64 * results)
 			return -EIO;
 		dp = (struct dmap *) mp->data;
 
-		if (dp->tree.budmin < 0)
+		if (dp->tree.budmin < 0) {
+			release_metapage(mp);
 			return -EIO;
+		}
 
 		/* try to allocate the blocks.
 		 */
Signature · 1 line
2.39.5
author maintainer
#144 lore raw

PATCH 144/523 mtd: rawnand: atmel: Fix dma_mapping_error() address

In reply to Greg Kroah-Hartman

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

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

From: Thomas Fourier <[email protected]>

[ Upstream commit e1e6b933c56b1e9fda93caa0b8bae39f3f421e5c ]

It seems like what was intended is to test if the dma_map of the previous line failed but the wrong dma address was passed.

Fixes f88fc122cc34 ("mtd: nand: Cleanup/rework the atmel_nand driver")

Rule: add

---
 drivers/mtd/nand/raw/atmel/nand-controller.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/mtd/nand/raw/atmel/nand-controller.c +1 -1
index 0d84f8156d8e..3468cc329399 100644
@@ -373,7 +373,7 @@ static int atmel_nand_dma_transfer(struct atmel_nand_controller *nc,
 	dma_cookie_t cookie;
 
 	buf_dma = dma_map_single(nc->dev, buf, len, dir);
-	if (dma_mapping_error(nc->dev, dev_dma)) {
+	if (dma_mapping_error(nc->dev, buf_dma)) {
 		dev_err(nc->dev,
 			"Failed to prepare a buffer for DMA access\n");
 		goto err;
Signature · 1 line
2.39.5
author maintainer
#145 lore raw

PATCH 145/523 mtd: rawnand: atmel: set pmecc data setup time

In reply to Greg Kroah-Hartman

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

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

From: Balamanikandan Gunasundar <[email protected]>

[ Upstream commit f552a7c7e0a14215cb8a6fd89e60fa3932a74786 ]

Setup the pmecc data setup time as 3 clock cycles for 133MHz as recommended by the datasheet.

---
 drivers/mtd/nand/raw/atmel/pmecc.c | 6 ++++++
 1 file changed, 6 insertions(+)
drivers/mtd/nand/raw/atmel/pmecc.c +6 -0
index d1ed5878b3b1..28ed65dd3d43 100644
@@ -143,6 +143,7 @@ struct atmel_pmecc_caps {
 	int nstrengths;
 	int el_offset;
 	bool correct_erased_chunks;
+	bool clk_ctrl;
 };
 
 struct atmel_pmecc {
@@ -846,6 +847,10 @@ static struct atmel_pmecc *atmel_pmecc_create(struct platform_device *pdev,
 	if (IS_ERR(pmecc->regs.errloc))
 		return ERR_CAST(pmecc->regs.errloc);
 
+	/* pmecc data setup time */
+	if (caps->clk_ctrl)
+		writel(PMECC_CLK_133MHZ, pmecc->regs.base + ATMEL_PMECC_CLK);
+
 	/* Disable all interrupts before registering the PMECC handler. */
 	writel(0xffffffff, pmecc->regs.base + ATMEL_PMECC_IDR);
 	atmel_pmecc_reset(pmecc);
@@ -899,6 +904,7 @@ static struct atmel_pmecc_caps at91sam9g45_caps = {
 	.strengths = atmel_pmecc_strengths,
 	.nstrengths = 5,
 	.el_offset = 0x8c,
+	.clk_ctrl = true,
 };
 
 static struct atmel_pmecc_caps sama5d4_caps = {
Signature · 1 line
2.39.5
author maintainer
#146 lore raw

PATCH 146/523 vhost-scsi: Fix log flooding with target does not exist errors

In reply to Greg Kroah-Hartman

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

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

From: Mike Christie <[email protected]>

[ Upstream commit 69cd720a8a5e9ef0f05ce5dd8c9ea6e018245c82 ]

As part of the normal initiator side scanning the guest's scsi layer will loop over all possible targets and send an inquiry. Since the max number of targets for virtio-scsi is 256, this can result in 255 error messages about targets not existing if you only have a single target. When there's more than 1 vhost-scsi device each with a single target, then you get N * 255 log messages.

It looks like the log message was added by accident in:

commit 3f8ca2e115e5 ("vhost/scsi: Extract common handling code from control queue handler")

when we added common helpers. Then in:

commit 09d7583294aa ("vhost/scsi: Use common handling code in request queue handler")

we converted the scsi command processing path to use the new helpers so we started to see the extra log messages during scanning.

The patches were just making some code common but added the vq_err call and I'm guessing the patch author forgot to enable the vq_err call (vq_err is implemented by pr_debug which defaults to off). So this patch removes the call since it's expected to hit this path during device discovery.

Fixes 09d7583294aa ("vhost/scsi: Use common handling code in request queue handler")

Message-Id: <[email protected]>

---
 drivers/vhost/scsi.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)
drivers/vhost/scsi.c +1 -3
index fcde3752b4f1..6956b4e0b9be 100644
@@ -927,10 +927,8 @@ vhost_scsi_get_req(struct vhost_virtqueue *vq, struct vhost_scsi_ctx *vc,
 			/* validated at handler entry */
 			vs_tpg = vhost_vq_get_backend(vq);
 			tpg = READ_ONCE(vs_tpg[*vc->target]);
-			if (unlikely(!tpg)) {
-				vq_err(vq, "Target 0x%x does not exist\n", *vc->target);
+			if (unlikely(!tpg))
 				goto out;
-			}
 		}
 
 		if (tpgp)
Signature · 1 line
2.39.5
author maintainer
#147 lore raw

PATCH 147/523 bpf: Check flow_dissector ctx accesses are aligned

In reply to Greg Kroah-Hartman

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

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

From: Paul Chaignon <[email protected]>

[ Upstream commit ead3d7b2b6afa5ee7958620c4329982a7d9c2b78 ]

flow_dissector_is_valid_access doesn't check that the context access is aligned. As a consequence, an unaligned access within one of the exposed field is considered valid and later rejected by flow_dissector_convert_ctx_access when we try to convert it.

The later rejection is problematic because it's reported as a verifier bug with a kernel warning and doesn't point to the right instruction in verifier logs.

---
 net/core/filter.c | 3 +++
 1 file changed, 3 insertions(+)
net/core/filter.c +3 -0
index 2018001d16bf..076b317c3594 100644
@@ -8318,6 +8318,9 @@ static bool flow_dissector_is_valid_access(int off, int size,
 	if (off < 0 || off >= sizeof(struct __sk_buff))
 		return false;
 
+	if (off % size != 0)
+		return false;
+
 	if (type == BPF_WRITE)
 		return false;
 
Signature · 1 line
2.39.5
author maintainer
#148 lore raw

PATCH 148/523 apparmor: ensure WB_HISTORY_SIZE value is a power of 2

In reply to Greg Kroah-Hartman

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

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

From: Ryan Lee <[email protected]>

[ Upstream commit 6c055e62560b958354625604293652753d82bcae ]

WB_HISTORY_SIZE was defined to be a value not a power of 2, despite a comment in the declaration of struct match_workbuf stating it is and a modular arithmetic usage in the inc_wb_pos macro assuming that it is. Bump WB_HISTORY_SIZE's value up to 32 and add a BUILD_BUG_ON_NOT_POWER_OF_2 line to ensure that any future changes to the value of WB_HISTORY_SIZE respect this requirement.

Fixes 136db994852a ("apparmor: increase left match history buffer size")
---
 security/apparmor/include/match.h | 3 ++-
 security/apparmor/match.c         | 1 +
 2 files changed, 3 insertions(+), 1 deletion(-)
security/apparmor/include/match.h +2 -1
index 884489590588..29306ec87fd1 100644
@@ -141,7 +141,8 @@ unsigned int aa_dfa_matchn_until(struct aa_dfa *dfa, unsigned int start,
 
 void aa_dfa_free_kref(struct kref *kref);
 
-#define WB_HISTORY_SIZE 24
+/* This needs to be a power of 2 */
+#define WB_HISTORY_SIZE 32
 struct match_workbuf {
 	unsigned int count;
 	unsigned int pos;
security/apparmor/match.c +1 -0
index 3e9e1eaf990e..0e683ee323e3 100644
@@ -672,6 +672,7 @@ unsigned int aa_dfa_matchn_until(struct aa_dfa *dfa, unsigned int start,
 
 #define inc_wb_pos(wb)						\
 do {								\
+	BUILD_BUG_ON_NOT_POWER_OF_2(WB_HISTORY_SIZE);			\
 	wb->pos = (wb->pos + 1) & (WB_HISTORY_SIZE - 1);		\
 	wb->len = (wb->len + 1) & (WB_HISTORY_SIZE - 1);		\
 } while (0)
Signature · 1 line
2.39.5
author maintainer
#149 lore raw

PATCH 149/523 module: Restore the moduleparam prefix length check

In reply to Greg Kroah-Hartman

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

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

From: Petr Pavlu <[email protected]>

[ Upstream commit bdc877ba6b7ff1b6d2ebeff11e63da4a50a54854 ]

The moduleparam code allows modules to provide their own definition of MODULE_PARAM_PREFIX, instead of using the default KBUILD_MODNAME ".".

Commit 730b69d22525 ("module: check kernel param length at compile time, not runtime") added a check to ensure the prefix doesn't exceed MODULE_NAME_LEN, as this is what param_sysfs_builtin() expects.

Later, commit 58f86cc89c33 ("VERIFY_OCTAL_PERMISSIONS: stricter checking for sysfs perms.") removed this check, but there is no indication this was intentional.

Since the check is still useful for param_sysfs_builtin() to function properly, reintroduce it in __module_param_call(), but in a modernized form using static_assert().

While here, clean up the __module_param_call() comments. In particular, remove the comment "Default value instead of permissions?", which comes from commit 9774a1f54f17 ("[PATCH] Compile-time check re world-writeable module params"). This comment was related to the test variable __param_perm_check_##name, which was removed in the previously mentioned commit 58f86cc89c33.

Fixes 58f86cc89c33 ("VERIFY_OCTAL_PERMISSIONS: stricter checking for sysfs perms.")
---
 include/linux/moduleparam.h | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)
include/linux/moduleparam.h +2 -3
index f25a1c484390..2c9d43eed9c7 100644
@@ -282,10 +282,9 @@ struct kparam_array
 #define __moduleparam_const const
 #endif
 
-/* This is the fundamental function for registering boot/module
-   parameters. */
+/* This is the fundamental function for registering boot/module parameters. */
 #define __module_param_call(prefix, name, ops, arg, perm, level, flags)	\
-	/* Default value instead of permissions? */			\
+	static_assert(sizeof(""prefix) - 1 <= MAX_PARAM_PREFIX_LEN);	\
 	static const char __param_str_##name[] = prefix #name;		\
 	static struct kernel_param __moduleparam_const __param_##name	\
 	__used								\
Signature · 1 line
2.39.5
author maintainer
#150 lore raw

PATCH 150/523 rtc: ds1307: fix incorrect maximum clock rate handling

In reply to Greg Kroah-Hartman

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

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

From: Brian Masney <[email protected]>

[ Upstream commit cf6eb547a24af7ad7bbd2abe9c5327f956bbeae8 ]

When ds3231_clk_sqw_round_rate() is called with a requested rate higher than the highest supported rate, it currently returns 0, which disables the clock. According to the clk API, round_rate() should instead return the highest supported rate. Update the function to return the maximum supported rate in this case.

Fixes 6c6ff145b3346 ("rtc: ds1307: add clock provider support for DS3231")
---
 drivers/rtc/rtc-ds1307.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/rtc/rtc-ds1307.c +1 -1
index 3a2401ce2ec9..ba420201505c 100644
@@ -1518,7 +1518,7 @@ static long ds3231_clk_sqw_round_rate(struct clk_hw *hw, unsigned long rate,
 			return ds3231_clk_sqw_rates[i];
 	}
 
-	return 0;
+	return ds3231_clk_sqw_rates[ARRAY_SIZE(ds3231_clk_sqw_rates) - 1];
 }
 
 static int ds3231_clk_sqw_set_rate(struct clk_hw *hw, unsigned long rate,
Signature · 1 line
2.39.5
author maintainer
#151 lore raw

PATCH 151/523 rtc: hym8563: fix incorrect maximum clock rate handling

In reply to Greg Kroah-Hartman

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

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

From: Brian Masney <[email protected]>

[ Upstream commit d0a518eb0a692a2ab8357e844970660c5ea37720 ]

When hym8563_clkout_round_rate() is called with a requested rate higher than the highest supported rate, it currently returns 0, which disables the clock. According to the clk API, round_rate() should instead return the highest supported rate. Update the function to return the maximum supported rate in this case.

---
 drivers/rtc/rtc-hym8563.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/rtc/rtc-hym8563.c +1 -1
index 0fb79c4afb46..b5e76d6ee64b 100644
@@ -312,7 +312,7 @@ static long hym8563_clkout_round_rate(struct clk_hw *hw, unsigned long rate,
 		if (clkout_rates[i] <= rate)
 			return clkout_rates[i];
 
-	return 0;
+	return clkout_rates[0];
 }
 
 static int hym8563_clkout_set_rate(struct clk_hw *hw, unsigned long rate,
Signature · 1 line
2.39.5
author maintainer
#152 lore raw

PATCH 152/523 rtc: pcf85063: fix incorrect maximum clock rate handling

In reply to Greg Kroah-Hartman

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

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

From: Brian Masney <[email protected]>

[ Upstream commit 186ae1869880e58bb3f142d222abdb35ecb4df0f ]

When pcf85063_clkout_round_rate() is called with a requested rate higher than the highest supported rate, it currently returns 0, which disables the clock. According to the clk API, round_rate() should instead return the highest supported rate. Update the function to return the maximum supported rate in this case.

Fixes 8c229ab6048b7 ("rtc: pcf85063: Add pcf85063 clkout control to common clock framework")
---
 drivers/rtc/rtc-pcf85063.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/rtc/rtc-pcf85063.c +1 -1
index dd3336cbb792..0c957144e8ec 100644
@@ -415,7 +415,7 @@ static long pcf85063_clkout_round_rate(struct clk_hw *hw, unsigned long rate,
 		if (clkout_rates[i] <= rate)
 			return clkout_rates[i];
 
-	return 0;
+	return clkout_rates[0];
 }
 
 static int pcf85063_clkout_set_rate(struct clk_hw *hw, unsigned long rate,
Signature · 1 line
2.39.5
author maintainer
#153 lore raw

PATCH 153/523 rtc: pcf8563: fix incorrect maximum clock rate handling

In reply to Greg Kroah-Hartman

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

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

From: Brian Masney <[email protected]>

[ Upstream commit 906726a5efeefe0ef0103ccff5312a09080c04ae ]

When pcf8563_clkout_round_rate() is called with a requested rate higher than the highest supported rate, it currently returns 0, which disables the clock. According to the clk API, round_rate() should instead return the highest supported rate. Update the function to return the maximum supported rate in this case.

Fixes a39a6405d5f94 ("rtc: pcf8563: add CLKOUT to common clock framework")
---
 drivers/rtc/rtc-pcf8563.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/rtc/rtc-pcf8563.c +1 -1
index 2dc30eafa639..129bd2f51779 100644
@@ -399,7 +399,7 @@ static long pcf8563_clkout_round_rate(struct clk_hw *hw, unsigned long rate,
 		if (clkout_rates[i] <= rate)
 			return clkout_rates[i];
 
-	return 0;
+	return clkout_rates[0];
 }
 
 static int pcf8563_clkout_set_rate(struct clk_hw *hw, unsigned long rate,
Signature · 1 line
2.39.5
author maintainer
#154 lore raw

PATCH 154/523 rtc: rv3028: fix incorrect maximum clock rate handling

In reply to Greg Kroah-Hartman

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

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

From: Brian Masney <[email protected]>

[ Upstream commit b574acb3cf7591d2513a9f29f8c2021ad55fb881 ]

When rv3028_clkout_round_rate() is called with a requested rate higher than the highest supported rate, it currently returns 0, which disables the clock. According to the clk API, round_rate() should instead return the highest supported rate. Update the function to return the maximum supported rate in this case.

---
 drivers/rtc/rtc-rv3028.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/rtc/rtc-rv3028.c +1 -1
index fa226f0fe67d..56fa66b6cadf 100644
@@ -672,7 +672,7 @@ static long rv3028_clkout_round_rate(struct clk_hw *hw, unsigned long rate,
 		if (clkout_rates[i] <= rate)
 			return clkout_rates[i];
 
-	return 0;
+	return clkout_rates[0];
 }
 
 static int rv3028_clkout_set_rate(struct clk_hw *hw, unsigned long rate,
Signature · 1 line
2.39.5
author maintainer
#155 lore raw

PATCH 155/523 f2fs: doc: fix wrong quota mount option description

In reply to Greg Kroah-Hartman

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

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

From: Chao Yu <[email protected]>

[ Upstream commit 81b6ecca2f15922e8d653dc037df5871e754be6e ]

We should use "{usr,grp,prj}jquota=" to disable journaled quota, rather than using off{usr,grp,prj}jquota.

Fixes 4b2414d04e99 ("f2fs: support journalled quota")
---
 Documentation/filesystems/f2fs.rst | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)
Documentation/filesystems/f2fs.rst +3 -3
index de2bacc418fe..483573166ac9 100644
@@ -203,9 +203,9 @@ usrjquota=<file>	 Appoint specified file and type during mount, so that quota
 grpjquota=<file>	 information can be properly updated during recovery flow,
 prjjquota=<file>	 <quota file>: must be in root directory;
 jqfmt=<quota type>	 <quota type>: [vfsold,vfsv0,vfsv1].
-offusrjquota		 Turn off user journalled quota.
-offgrpjquota		 Turn off group journalled quota.
-offprjjquota		 Turn off project journalled quota.
+usrjquota=		 Turn off user journalled quota.
+grpjquota=		 Turn off group journalled quota.
+prjjquota=		 Turn off project journalled quota.
 quota			 Enable plain user disk quota accounting.
 noquota			 Disable all plain disk quota option.
 whint_mode=%s		 Control which write hints are passed down to block
Signature · 1 line
2.39.5
author maintainer
#156 lore raw

PATCH 156/523 f2fs: fix to avoid UAF in f2fs_sync_inode_meta()

In reply to Greg Kroah-Hartman

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

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

From: Chao Yu <[email protected]>

[ Upstream commit 7c30d79930132466f5be7d0b57add14d1a016bda ]

syzbot reported an UAF issue as below: [1] [2]

[1] https://syzkaller.appspot.com/text?tag=CrashReport&x=16594c60580000

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

BUG: KASAN: use-after-free in __list_del_entry_valid+0xa6/0x130 lib/list_debug.c:62
Read of size 8 at addr ffff888100567dc8 by task kworker/u4:0/8

CPU: 1 PID: 8 Comm: kworker/u4:0 Tainted: G        W          6.1.129-syzkaller-00017-g642656a36791 #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 02/12/2025
Workqueue: writeback wb_workfn (flush-7:0)
Call Trace:
 <TASK>
 __dump_stack lib/dump_stack.c:88 [inline]
 dump_stack_lvl+0x151/0x1b7 lib/dump_stack.c:106
 print_address_description mm/kasan/report.c:316 [inline]
 print_report+0x158/0x4e0 mm/kasan/report.c:427
 kasan_report+0x13c/0x170 mm/kasan/report.c:531
 __asan_report_load8_noabort+0x14/0x20 mm/kasan/report_generic.c:351
 __list_del_entry_valid+0xa6/0x130 lib/list_debug.c:62
 __list_del_entry include/linux/list.h:134 [inline]
 list_del_init include/linux/list.h:206 [inline]
 f2fs_inode_synced+0x100/0x2e0 fs/f2fs/super.c:1553
 f2fs_update_inode+0x72/0x1c40 fs/f2fs/inode.c:588
 f2fs_update_inode_page+0x135/0x170 fs/f2fs/inode.c:706
 f2fs_write_inode+0x416/0x790 fs/f2fs/inode.c:734
 write_inode fs/fs-writeback.c:1460 [inline]
 __writeback_single_inode+0x4cf/0xb80 fs/fs-writeback.c:1677
 writeback_sb_inodes+0xb32/0x1910 fs/fs-writeback.c:1903
 __writeback_inodes_wb+0x118/0x3f0 fs/fs-writeback.c:1974
 wb_writeback+0x3da/0xa00 fs/fs-writeback.c:2081
 wb_check_background_flush fs/fs-writeback.c:2151 [inline]
 wb_do_writeback fs/fs-writeback.c:2239 [inline]
 wb_workfn+0xbba/0x1030 fs/fs-writeback.c:2266
 process_one_work+0x73d/0xcb0 kernel/workqueue.c:2299
 worker_thread+0xa60/0x1260 kernel/workqueue.c:2446
 kthread+0x26d/0x300 kernel/kthread.c:386
 ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:295
 </TASK>

Allocated by task 298:
 kasan_save_stack mm/kasan/common.c:45 [inline]
 kasan_set_track+0x4b/0x70 mm/kasan/common.c:52
 kasan_save_alloc_info+0x1f/0x30 mm/kasan/generic.c:505
 __kasan_slab_alloc+0x6c/0x80 mm/kasan/common.c:333
 kasan_slab_alloc include/linux/kasan.h:202 [inline]
 slab_post_alloc_hook+0x53/0x2c0 mm/slab.h:768
 slab_alloc_node mm/slub.c:3421 [inline]
 slab_alloc mm/slub.c:3431 [inline]
 __kmem_cache_alloc_lru mm/slub.c:3438 [inline]
 kmem_cache_alloc_lru+0x102/0x270 mm/slub.c:3454
 alloc_inode_sb include/linux/fs.h:3255 [inline]
 f2fs_alloc_inode+0x2d/0x350 fs/f2fs/super.c:1437
 alloc_inode fs/inode.c:261 [inline]
 iget_locked+0x18c/0x7e0 fs/inode.c:1373
 f2fs_iget+0x55/0x4ca0 fs/f2fs/inode.c:486
 f2fs_lookup+0x3c1/0xb50 fs/f2fs/namei.c:484
 __lookup_slow+0x2b9/0x3e0 fs/namei.c:1689
 lookup_slow+0x5a/0x80 fs/namei.c:1706
 walk_component+0x2e7/0x410 fs/namei.c:1997
 lookup_last fs/namei.c:2454 [inline]
 path_lookupat+0x16d/0x450 fs/namei.c:2478
 filename_lookup+0x251/0x600 fs/namei.c:2507
 vfs_statx+0x107/0x4b0 fs/stat.c:229
 vfs_fstatat fs/stat.c:267 [inline]
 vfs_lstat include/linux/fs.h:3434 [inline]
 __do_sys_newlstat fs/stat.c:423 [inline]
 __se_sys_newlstat+0xda/0x7c0 fs/stat.c:417
 __x64_sys_newlstat+0x5b/0x70 fs/stat.c:417
 x64_sys_call+0x52/0x9a0 arch/x86/include/generated/asm/syscalls_64.h:7
 do_syscall_x64 arch/x86/entry/common.c:51 [inline]
 do_syscall_64+0x3b/0x80 arch/x86/entry/common.c:81
 entry_SYSCALL_64_after_hwframe+0x68/0xd2

Freed by task 0:
 kasan_save_stack mm/kasan/common.c:45 [inline]
 kasan_set_track+0x4b/0x70 mm/kasan/common.c:52
 kasan_save_free_info+0x2b/0x40 mm/kasan/generic.c:516
 ____kasan_slab_free+0x131/0x180 mm/kasan/common.c:241
 __kasan_slab_free+0x11/0x20 mm/kasan/common.c:249
 kasan_slab_free include/linux/kasan.h:178 [inline]
 slab_free_hook mm/slub.c:1745 [inline]
 slab_free_freelist_hook mm/slub.c:1771 [inline]
 slab_free mm/slub.c:3686 [inline]
 kmem_cache_free+0x291/0x560 mm/slub.c:3711
 f2fs_free_inode+0x24/0x30 fs/f2fs/super.c:1584
 i_callback+0x4b/0x70 fs/inode.c:250
 rcu_do_batch+0x552/0xbe0 kernel/rcu/tree.c:2297
 rcu_core+0x502/0xf40 kernel/rcu/tree.c:2557
 rcu_core_si+0x9/0x10 kernel/rcu/tree.c:2574
 handle_softirqs+0x1db/0x650 kernel/softirq.c:624
 __do_softirq kernel/softirq.c:662 [inline]
 invoke_softirq kernel/softirq.c:479 [inline]
 __irq_exit_rcu+0x52/0xf0 kernel/softirq.c:711
 irq_exit_rcu+0x9/0x10 kernel/softirq.c:723
 instr_sysvec_apic_timer_interrupt arch/x86/kernel/apic/apic.c:1118 [inline]
 sysvec_apic_timer_interrupt+0xa9/0xc0 arch/x86/kernel/apic/apic.c:1118
 asm_sysvec_apic_timer_interrupt+0x1b/0x20 arch/x86/include/asm/idtentry.h:691

Last potentially related work creation:
 kasan_save_stack+0x3b/0x60 mm/kasan/common.c:45
 __kasan_record_aux_stack+0xb4/0xc0 mm/kasan/generic.c:486
 kasan_record_aux_stack_noalloc+0xb/0x10 mm/kasan/generic.c:496
 __call_rcu_common kernel/rcu/tree.c:2807 [inline]
 call_rcu+0xdc/0x10f0 kernel/rcu/tree.c:2926
 destroy_inode fs/inode.c:316 [inline]
 evict+0x87d/0x930 fs/inode.c:720
 iput_final fs/inode.c:1834 [inline]
 iput+0x616/0x690 fs/inode.c:1860
 do_unlinkat+0x4e1/0x920 fs/namei.c:4396
 __do_sys_unlink fs/namei.c:4437 [inline]
 __se_sys_unlink fs/namei.c:4435 [inline]
 __x64_sys_unlink+0x49/0x50 fs/namei.c:4435
 x64_sys_call+0x289/0x9a0 arch/x86/include/generated/asm/syscalls_64.h:88
 do_syscall_x64 arch/x86/entry/common.c:51 [inline]
 do_syscall_64+0x3b/0x80 arch/x86/entry/common.c:81
 entry_SYSCALL_64_after_hwframe+0x68/0xd2

The buggy address belongs to the object at ffff888100567a10
 which belongs to the cache f2fs_inode_cache of size 1360

The buggy address is located 952 bytes inside of
1360-byte region [ffff888100567a10, ffff888100567f60)

The buggy address belongs to the physical page:
page:ffffea0004015800 refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x100560
head:ffffea0004015800 order:3 compound_mapcount:0 compound_pincount:0
flags: 0x4000000000010200(slab|head|zone=1)
raw: 4000000000010200 0000000000000000 dead000000000122 ffff8881002c4d80
raw: 0000000000000000 0000000080160016 00000001ffffffff 0000000000000000
page dumped because: kasan: bad access detected
page_owner tracks the page as allocated
page last allocated via order 3, migratetype Reclaimable, gfp_mask 0xd2050(__GFP_IO|__GFP_NOWARN|__GFP_NORETRY|__GFP_COMP|__GFP_NOMEMALLOC|__GFP_RECLAIMABLE), pid 298, tgid 298 (syz-executor330), ts 26489303743, free_ts 0
 set_page_owner include/linux/page_owner.h:33 [inline]
 post_alloc_hook+0x213/0x220 mm/page_alloc.c:2637
 prep_new_page+0x1b/0x110 mm/page_alloc.c:2644
 get_page_from_freelist+0x3a98/0x3b10 mm/page_alloc.c:4539
 __alloc_pages+0x234/0x610 mm/page_alloc.c:5837
 alloc_slab_page+0x6c/0xf0 include/linux/gfp.h:-1
 allocate_slab mm/slub.c:1962 [inline]
 new_slab+0x90/0x3e0 mm/slub.c:2015
 ___slab_alloc+0x6f9/0xb80 mm/slub.c:3203
 __slab_alloc+0x5d/0xa0 mm/slub.c:3302
 slab_alloc_node mm/slub.c:3387 [inline]
 slab_alloc mm/slub.c:3431 [inline]
 __kmem_cache_alloc_lru mm/slub.c:3438 [inline]
 kmem_cache_alloc_lru+0x149/0x270 mm/slub.c:3454
 alloc_inode_sb include/linux/fs.h:3255 [inline]
 f2fs_alloc_inode+0x2d/0x350 fs/f2fs/super.c:1437
 alloc_inode fs/inode.c:261 [inline]
 iget_locked+0x18c/0x7e0 fs/inode.c:1373
 f2fs_iget+0x55/0x4ca0 fs/f2fs/inode.c:486
 f2fs_fill_super+0x5360/0x6dc0 fs/f2fs/super.c:4488
 mount_bdev+0x282/0x3b0 fs/super.c:1445
 f2fs_mount+0x34/0x40 fs/f2fs/super.c:4743
 legacy_get_tree+0xf1/0x190 fs/fs_context.c:632

page_owner free stack trace missing

Memory state around the buggy address:
 ffff888100567c80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
 ffff888100567d00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
>ffff888100567d80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
                                              ^
 ffff888100567e00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
 ffff888100567e80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
==================================================================

[2] https://syzkaller.appspot.com/text?tag=CrashLog&x=13654c60580000

[   24.675720][   T28] audit: type=1400 audit(1745327318.732:72): avc:  denied  { write } for  pid=298 comm="syz-executor399" name="/" dev="loop0" ino=3 scontext=root:sysadm_r:sysadm_t tcontext=system_u:object_r:unlabeled_t tclass=dir permissive=1
[   24.705426][  T296] ------------[ cut here ]------------
[   24.706608][   T28] audit: type=1400 audit(1745327318.732:73): avc:  denied  { remove_name } for  pid=298 comm="syz-executor399" name="file0" dev="loop0" ino=4 scontext=root:sysadm_r:sysadm_t tcontext=system_u:object_r:unlabeled_t tclass=dir permissive=1
[   24.711550][  T296] WARNING: CPU: 0 PID: 296 at fs/f2fs/inode.c:847 f2fs_evict_inode+0x1262/0x1540
[   24.734141][   T28] audit: type=1400 audit(1745327318.732:74): avc:  denied  { rename } for  pid=298 comm="syz-executor399" name="file0" dev="loop0" ino=4 scontext=root:sysadm_r:sysadm_t tcontext=system_u:object_r:unlabeled_t tclass=dir permissive=1
[   24.742969][  T296] Modules linked in:
[   24.765201][   T28] audit: type=1400 audit(1745327318.732:75): avc:  denied  { add_name } for  pid=298 comm="syz-executor399" name="bus" scontext=root:sysadm_r:sysadm_t tcontext=system_u:object_r:unlabeled_t tclass=dir permissive=1
[   24.768847][  T296] CPU: 0 PID: 296 Comm: syz-executor399 Not tainted 6.1.129-syzkaller-00017-g642656a36791 #0
[   24.799506][  T296] Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 02/12/2025
[   24.809401][  T296] RIP: 0010:f2fs_evict_inode+0x1262/0x1540
[   24.815018][  T296] Code: 34 70 4a ff eb 0d e8 2d 70 4a ff 4d 89 e5 4c 8b 64 24 18 48 8b 5c 24 28 4c 89 e7 e8 78 38 03 00 e9 84 fc ff ff e8 0e 70 4a ff <0f> 0b 4c 89 f7 be 08 00 00 00 e8 7f 21 92 ff f0 41 80 0e 04 e9 61
[   24.834584][  T296] RSP: 0018:ffffc90000db7a40 EFLAGS: 00010293
[   24.840465][  T296] RAX: ffffffff822aca42 RBX: 0000000000000002 RCX: ffff888110948000
[   24.848291][  T296] RDX: 0000000000000000 RSI: 0000000000000002 RDI: 0000000000000000
[   24.856064][  T296] RBP: ffffc90000db7bb0 R08: ffffffff822ac6a8 R09: ffffed10200b005d
[   24.864073][  T296] R10: 0000000000000000 R11: dffffc0000000001 R12: ffff888100580000
[   24.871812][  T296] R13: dffffc0000000000 R14: ffff88810fef4078 R15: 1ffff920001b6f5c

The root cause is w/ a fuzzed image, f2fs may missed to clear FI_DIRTY_INODE flag for target inode, after f2fs_evict_inode(), the inode is still linked in sbi->inode_list[DIRTY_META] global list, once it triggers checkpoint, f2fs_sync_inode_meta() may access the released inode.

In f2fs_evict_inode(), let's always call f2fs_inode_synced() to clear FI_DIRTY_INODE flag and drop inode from global dirty list to avoid this UAF issue.

Fixes 0f18b462b2e5 ("f2fs: flush inode metadata when checkpoint is doing")
---
 fs/f2fs/inode.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)
fs/f2fs/inode.c +6 -2
index 452c0240cc11..c858a354a19f 100644
@@ -813,8 +813,12 @@ void f2fs_evict_inode(struct inode *inode)
 	if (likely(!f2fs_cp_error(sbi) &&
 				!is_sbi_flag_set(sbi, SBI_CP_DISABLED)))
 		f2fs_bug_on(sbi, is_inode_flag_set(inode, FI_DIRTY_INODE));
-	else
-		f2fs_inode_synced(inode);
+
+	/*
+	 * anyway, it needs to remove the inode from sbi->inode_list[DIRTY_META]
+	 * list to avoid UAF in f2fs_sync_inode_meta() during checkpoint.
+	 */
+	f2fs_inode_synced(inode);
 
 	/* for the case f2fs_new_inode() was failed, .i_ino is zero, skip it */
 	if (inode->i_ino)
Signature · 1 line
2.39.5
author maintainer
#157 lore raw

PATCH 157/523 f2fs: fix to avoid panic in f2fs_evict_inode

In reply to Greg Kroah-Hartman

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

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

From: Chao Yu <[email protected]>

[ Upstream commit a509a55f8eecc8970b3980c6f06886bbff0e2f68 ]

As syzbot [1] reported as below:

R10: 0000000000000100 R11: 0000000000000206 R12: 00007ffe17473450
R13: 00007f28b1c10854 R14: 000000000000dae5 R15: 00007ffe17474520

 </TASK>
---[ end trace 0000000000000000 ]---
==================================================================
BUG: KASAN: use-after-free in __list_del_entry_valid+0xa6/0x130 lib/list_debug.c:62
Read of size 8 at addr ffff88812d962278 by task syz-executor/564

CPU: 1 PID: 564 Comm: syz-executor Tainted: G        W          6.1.129-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 02/12/2025
Call Trace:
 <TASK>
 __dump_stack+0x21/0x24 lib/dump_stack.c:88
 dump_stack_lvl+0xee/0x158 lib/dump_stack.c:106
 print_address_description+0x71/0x210 mm/kasan/report.c:316
 print_report+0x4a/0x60 mm/kasan/report.c:427
 kasan_report+0x122/0x150 mm/kasan/report.c:531
 __asan_report_load8_noabort+0x14/0x20 mm/kasan/report_generic.c:351
 __list_del_entry_valid+0xa6/0x130 lib/list_debug.c:62
 __list_del_entry include/linux/list.h:134 [inline]
 list_del_init include/linux/list.h:206 [inline]
 f2fs_inode_synced+0xf7/0x2e0 fs/f2fs/super.c:1531
 f2fs_update_inode+0x74/0x1c40 fs/f2fs/inode.c:585
 f2fs_update_inode_page+0x137/0x170 fs/f2fs/inode.c:703
 f2fs_write_inode+0x4ec/0x770 fs/f2fs/inode.c:731
 write_inode fs/fs-writeback.c:1460 [inline]
 __writeback_single_inode+0x4a0/0xab0 fs/fs-writeback.c:1677
 writeback_single_inode+0x221/0x8b0 fs/fs-writeback.c:1733
 sync_inode_metadata+0xb6/0x110 fs/fs-writeback.c:2789
 f2fs_sync_inode_meta+0x16d/0x2a0 fs/f2fs/checkpoint.c:1159
 block_operations fs/f2fs/checkpoint.c:1269 [inline]
 f2fs_write_checkpoint+0xca3/0x2100 fs/f2fs/checkpoint.c:1658
 kill_f2fs_super+0x231/0x390 fs/f2fs/super.c:4668
 deactivate_locked_super+0x98/0x100 fs/super.c:332
 deactivate_super+0xaf/0xe0 fs/super.c:363
 cleanup_mnt+0x45f/0x4e0 fs/namespace.c:1186
 __cleanup_mnt+0x19/0x20 fs/namespace.c:1193
 task_work_run+0x1c6/0x230 kernel/task_work.c:203
 exit_task_work include/linux/task_work.h:39 [inline]
 do_exit+0x9fb/0x2410 kernel/exit.c:871
 do_group_exit+0x210/0x2d0 kernel/exit.c:1021
 __do_sys_exit_group kernel/exit.c:1032 [inline]
 __se_sys_exit_group kernel/exit.c:1030 [inline]
 __x64_sys_exit_group+0x3f/0x40 kernel/exit.c:1030
 x64_sys_call+0x7b4/0x9a0 arch/x86/include/generated/asm/syscalls_64.h:232
 do_syscall_x64 arch/x86/entry/common.c:51 [inline]
 do_syscall_64+0x4c/0xa0 arch/x86/entry/common.c:81
 entry_SYSCALL_64_after_hwframe+0x68/0xd2
RIP: 0033:0x7f28b1b8e169
Code: Unable to access opcode bytes at 0x7f28b1b8e13f.
RSP: 002b:00007ffe174710a8 EFLAGS: 00000246 ORIG_RAX: 00000000000000e7
RAX: ffffffffffffffda RBX: 00007f28b1c10879 RCX: 00007f28b1b8e169
RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000001
RBP: 0000000000000002 R08: 00007ffe1746ee47 R09: 00007ffe17472360
R10: 0000000000000009 R11: 0000000000000246 R12: 00007ffe17472360
R13: 00007f28b1c10854 R14: 000000000000dae5 R15: 00007ffe17474520
 </TASK>

Allocated by task 569:
 kasan_save_stack mm/kasan/common.c:45 [inline]
 kasan_set_track+0x4b/0x70 mm/kasan/common.c:52
 kasan_save_alloc_info+0x25/0x30 mm/kasan/generic.c:505
 __kasan_slab_alloc+0x72/0x80 mm/kasan/common.c:328
 kasan_slab_alloc include/linux/kasan.h:201 [inline]
 slab_post_alloc_hook+0x4f/0x2c0 mm/slab.h:737
 slab_alloc_node mm/slub.c:3398 [inline]
 slab_alloc mm/slub.c:3406 [inline]
 __kmem_cache_alloc_lru mm/slub.c:3413 [inline]
 kmem_cache_alloc_lru+0x104/0x220 mm/slub.c:3429
 alloc_inode_sb include/linux/fs.h:3245 [inline]
 f2fs_alloc_inode+0x2d/0x340 fs/f2fs/super.c:1419
 alloc_inode fs/inode.c:261 [inline]
 iget_locked+0x186/0x880 fs/inode.c:1373
 f2fs_iget+0x55/0x4c60 fs/f2fs/inode.c:483
 f2fs_lookup+0x366/0xab0 fs/f2fs/namei.c:487
 __lookup_slow+0x2a3/0x3d0 fs/namei.c:1690
 lookup_slow+0x57/0x70 fs/namei.c:1707
 walk_component+0x2e6/0x410 fs/namei.c:1998
 lookup_last fs/namei.c:2455 [inline]
 path_lookupat+0x180/0x490 fs/namei.c:2479
 filename_lookup+0x1f0/0x500 fs/namei.c:2508
 vfs_statx+0x10b/0x660 fs/stat.c:229
 vfs_fstatat fs/stat.c:267 [inline]
 vfs_lstat include/linux/fs.h:3424 [inline]
 __do_sys_newlstat fs/stat.c:423 [inline]
 __se_sys_newlstat+0xd5/0x350 fs/stat.c:417
 __x64_sys_newlstat+0x5b/0x70 fs/stat.c:417
 x64_sys_call+0x393/0x9a0 arch/x86/include/generated/asm/syscalls_64.h:7
 do_syscall_x64 arch/x86/entry/common.c:51 [inline]
 do_syscall_64+0x4c/0xa0 arch/x86/entry/common.c:81
 entry_SYSCALL_64_after_hwframe+0x68/0xd2

Freed by task 13:
 kasan_save_stack mm/kasan/common.c:45 [inline]
 kasan_set_track+0x4b/0x70 mm/kasan/common.c:52
 kasan_save_free_info+0x31/0x50 mm/kasan/generic.c:516
 ____kasan_slab_free+0x132/0x180 mm/kasan/common.c:236
 __kasan_slab_free+0x11/0x20 mm/kasan/common.c:244
 kasan_slab_free include/linux/kasan.h:177 [inline]
 slab_free_hook mm/slub.c:1724 [inline]
 slab_free_freelist_hook+0xc2/0x190 mm/slub.c:1750
 slab_free mm/slub.c:3661 [inline]
 kmem_cache_free+0x12d/0x2a0 mm/slub.c:3683
 f2fs_free_inode+0x24/0x30 fs/f2fs/super.c:1562
 i_callback+0x4c/0x70 fs/inode.c:250
 rcu_do_batch+0x503/0xb80 kernel/rcu/tree.c:2297
 rcu_core+0x5a2/0xe70 kernel/rcu/tree.c:2557
 rcu_core_si+0x9/0x10 kernel/rcu/tree.c:2574
 handle_softirqs+0x178/0x500 kernel/softirq.c:578
 run_ksoftirqd+0x28/0x30 kernel/softirq.c:945
 smpboot_thread_fn+0x45a/0x8c0 kernel/smpboot.c:164
 kthread+0x270/0x310 kernel/kthread.c:376
 ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:295

Last potentially related work creation:
 kasan_save_stack+0x3a/0x60 mm/kasan/common.c:45
 __kasan_record_aux_stack+0xb6/0xc0 mm/kasan/generic.c:486
 kasan_record_aux_stack_noalloc+0xb/0x10 mm/kasan/generic.c:496
 call_rcu+0xd4/0xf70 kernel/rcu/tree.c:2845
 destroy_inode fs/inode.c:316 [inline]
 evict+0x7da/0x870 fs/inode.c:720
 iput_final fs/inode.c:1834 [inline]
 iput+0x62b/0x830 fs/inode.c:1860
 do_unlinkat+0x356/0x540 fs/namei.c:4397
 __do_sys_unlink fs/namei.c:4438 [inline]
 __se_sys_unlink fs/namei.c:4436 [inline]
 __x64_sys_unlink+0x49/0x50 fs/namei.c:4436
 x64_sys_call+0x958/0x9a0 arch/x86/include/generated/asm/syscalls_64.h:88
 do_syscall_x64 arch/x86/entry/common.c:51 [inline]
 do_syscall_64+0x4c/0xa0 arch/x86/entry/common.c:81
 entry_SYSCALL_64_after_hwframe+0x68/0xd2

The buggy address belongs to the object at ffff88812d961f20
 which belongs to the cache f2fs_inode_cache of size 1200

The buggy address is located 856 bytes inside of
1200-byte region [ffff88812d961f20, ffff88812d9623d0)

The buggy address belongs to the physical page:
page:ffffea0004b65800 refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x12d960
head:ffffea0004b65800 order:2 compound_mapcount:0 compound_pincount:0
flags: 0x4000000000010200(slab|head|zone=1)
raw: 4000000000010200 0000000000000000 dead000000000122 ffff88810a94c500
raw: 0000000000000000 00000000800c000c 00000001ffffffff 0000000000000000
page dumped because: kasan: bad access detected
page_owner tracks the page as allocated
page last allocated via order 2, migratetype Reclaimable, gfp_mask 0x1d2050(__GFP_IO|__GFP_NOWARN|__GFP_NORETRY|__GFP_COMP|__GFP_NOMEMALLOC|__GFP_HARDWALL|__GFP_RECLAIMABLE), pid 569, tgid 568 (syz.2.16), ts 55943246141, free_ts 0
 set_page_owner include/linux/page_owner.h:31 [inline]
 post_alloc_hook+0x1d0/0x1f0 mm/page_alloc.c:2532
 prep_new_page mm/page_alloc.c:2539 [inline]
 get_page_from_freelist+0x2e63/0x2ef0 mm/page_alloc.c:4328
 __alloc_pages+0x235/0x4b0 mm/page_alloc.c:5605
 alloc_slab_page include/linux/gfp.h:-1 [inline]
 allocate_slab mm/slub.c:1939 [inline]
 new_slab+0xec/0x4b0 mm/slub.c:1992
 ___slab_alloc+0x6f6/0xb50 mm/slub.c:3180
 __slab_alloc+0x5e/0xa0 mm/slub.c:3279
 slab_alloc_node mm/slub.c:3364 [inline]
 slab_alloc mm/slub.c:3406 [inline]
 __kmem_cache_alloc_lru mm/slub.c:3413 [inline]
 kmem_cache_alloc_lru+0x13f/0x220 mm/slub.c:3429
 alloc_inode_sb include/linux/fs.h:3245 [inline]
 f2fs_alloc_inode+0x2d/0x340 fs/f2fs/super.c:1419
 alloc_inode fs/inode.c:261 [inline]
 iget_locked+0x186/0x880 fs/inode.c:1373
 f2fs_iget+0x55/0x4c60 fs/f2fs/inode.c:483
 f2fs_fill_super+0x3ad7/0x6bb0 fs/f2fs/super.c:4293
 mount_bdev+0x2ae/0x3e0 fs/super.c:1443
 f2fs_mount+0x34/0x40 fs/f2fs/super.c:4642
 legacy_get_tree+0xea/0x190 fs/fs_context.c:632
 vfs_get_tree+0x89/0x260 fs/super.c:1573
 do_new_mount+0x25a/0xa20 fs/namespace.c:3056

page_owner free stack trace missing

Memory state around the buggy address:
 ffff88812d962100: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
 ffff88812d962180: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
>ffff88812d962200: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
                                                                ^
 ffff88812d962280: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
 ffff88812d962300: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
==================================================================

[1] https://syzkaller.appspot.com/x/report.txt?x=13448368580000

This bug can be reproduced w/ the reproducer [2], once we enable CONFIG_F2FS_CHECK_FS config, the reproducer will trigger panic as below, so the direct reason of this bug is the same as the one below patch [3] fixed.

kernel BUG at fs/f2fs/inode.c:857!

RIP: 0010:f2fs_evict_inode+0x1204/0x1a20
Call Trace:
 <TASK>
 evict+0x32a/0x7a0
 do_unlinkat+0x37b/0x5b0
 __x64_sys_unlink+0xad/0x100
 do_syscall_64+0x5a/0xb0
 entry_SYSCALL_64_after_hwframe+0x6e/0xd8
RIP: 0010:f2fs_evict_inode+0x1204/0x1a20

[2] https://syzkaller.appspot.com/x/repro.c?x=17495ccc580000
[3] https://lore.kernel.org/linux-f2fs-devel/[email protected]

Tracepoints before panic:

f2fs_unlink_enter: dev = (7,0), dir ino = 3, i_size = 4096, i_blocks = 8, name = file1
f2fs_unlink_exit: dev = (7,0), ino = 7, ret = 0
f2fs_evict_inode: dev = (7,0), ino = 7, pino = 3, i_mode = 0x81ed, i_size = 10, i_nlink = 0, i_blocks = 0, i_advise = 0x0
f2fs_truncate_node: dev = (7,0), ino = 7, nid = 8, block_address = 0x3c05

f2fs_unlink_enter: dev = (7,0), dir ino = 3, i_size = 4096, i_blocks = 8, name = file3
f2fs_unlink_exit: dev = (7,0), ino = 8, ret = 0
f2fs_evict_inode: dev = (7,0), ino = 8, pino = 3, i_mode = 0x81ed, i_size = 9000, i_nlink = 0, i_blocks = 24, i_advise = 0x4
f2fs_truncate: dev = (7,0), ino = 8, pino = 3, i_mode = 0x81ed, i_size = 0, i_nlink = 0, i_blocks = 24, i_advise = 0x4 f2fs_truncate_blocks_enter: dev = (7,0), ino = 8, i_size = 0, i_blocks = 24, start file offset = 0
f2fs_truncate_blocks_exit: dev = (7,0), ino = 8, ret = -2

The root cause is: in the fuzzed image, dnode #8 belongs to inode #7, after inode #7 eviction, dnode #8 was dropped.

However there is dirent that has ino #8, so, once we unlink file3, in f2fs_evict_inode(), both f2fs_truncate() and f2fs_update_inode_page() will fail due to we can not load node #8, result in we missed to call f2fs_inode_synced() to clear inode dirty status.

Let's fix this by calling f2fs_inode_synced() in error path of f2fs_evict_inode().

PS: As I verified, the reproducer [2] can trigger this bug in v6.1.129, but it failed in v6.16-rc4, this is because the testcase will stop due to other corruption has been detected by f2fs:

F2FS-fs (loop0): inconsistent node block, node_type:2, nid:8, node_footer[nid:8,ino:8,ofs:0,cpver:5013063228981249506,blkaddr:15366] F2FS-fs (loop0): f2fs_lookup: inode (ino=9) has zero i_nlink

Fixes 0f18b462b2e5 ("f2fs: flush inode metadata when checkpoint is doing")
---
 fs/f2fs/inode.c | 13 +++++++++++++
 1 file changed, 13 insertions(+)
fs/f2fs/inode.c +13 -0
index c858a354a19f..a3bcf19cd586 100644
@@ -798,6 +798,19 @@ void f2fs_evict_inode(struct inode *inode)
 		f2fs_update_inode_page(inode);
 		if (dquot_initialize_needed(inode))
 			set_sbi_flag(sbi, SBI_QUOTA_NEED_REPAIR);
+
+		/*
+		 * If both f2fs_truncate() and f2fs_update_inode_page() failed
+		 * due to fuzzed corrupted inode, call f2fs_inode_synced() to
+		 * avoid triggering later f2fs_bug_on().
+		 */
+		if (is_inode_flag_set(inode, FI_DIRTY_INODE)) {
+			f2fs_warn(sbi,
+				"f2fs_evict_inode: inode is dirty, ino:%lu",
+				inode->i_ino);
+			f2fs_inode_synced(inode);
+			set_sbi_flag(sbi, SBI_NEED_FSCK);
+		}
 	}
 	sb_end_intwrite(inode->i_sb);
 no_delete:
Signature · 1 line
2.39.5
author maintainer
#158 lore raw

PATCH 158/523 f2fs: fix to avoid out-of-boundary access in devs.path

In reply to Greg Kroah-Hartman

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

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

From: Chao Yu <[email protected]>

[ Upstream commit 5661998536af52848cc4d52a377e90368196edea ]

- touch /mnt/f2fs/012345678901234567890123456789012345678901234567890123
- truncate -s $((1024*1024*1024)) \
/mnt/f2fs/012345678901234567890123456789012345678901234567890123
- touch /mnt/f2fs/file
- truncate -s $((1024*1024*1024)) /mnt/f2fs/file
- mkfs.f2fs /mnt/f2fs/012345678901234567890123456789012345678901234567890123 \
-c /mnt/f2fs/file
- mount /mnt/f2fs/012345678901234567890123456789012345678901234567890123 \
/mnt/f2fs/loop

[16937.192225] F2FS-fs (loop0): Mount Device [ 0]: /mnt/f2fs/012345678901234567890123456789012345678901234567890123\xff\x01,      511,        0 -    3ffff
[16937.192268] F2FS-fs (loop0): Failed to find devices

If device path length equals to MAX_PATH_LEN, sbi->devs.path[] may not end up w/ null character due to path array is fully filled, So accidently, fields locate after path[] may be treated as part of device path, result in parsing wrong device path.

struct f2fs_dev_info {
...

	char path[MAX_PATH_LEN];

...
};

Let's add one byte space for sbi->devs.path[] to store null character of device path string.

Fixes 3c62be17d4f5 ("f2fs: support multiple devices")
---
 fs/f2fs/f2fs.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
fs/f2fs/f2fs.h +1 -1
index 4e42ca56da86..622e8a816f7e 100644
@@ -1154,7 +1154,7 @@ struct f2fs_bio_info {
 #define RDEV(i)				(raw_super->devs[i])
 struct f2fs_dev_info {
 	struct block_device *bdev;
-	char path[MAX_PATH_LEN];
+	char path[MAX_PATH_LEN + 1];
 	unsigned int total_segments;
 	block_t start_blk;
 	block_t end_blk;
Signature · 1 line
2.39.5
author maintainer
#159 lore raw

PATCH 159/523 scsi: ufs: core: Use link recovery when h8 exit fails during runtime resume

In reply to Greg Kroah-Hartman

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

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

From: Seunghui Lee <[email protected]>

[ Upstream commit 35dabf4503b94a697bababe94678a8bc989c3223 ]

If the h8 exit fails during runtime resume process, the runtime thread enters runtime suspend immediately and the error handler operates at the same time. It becomes stuck and cannot be recovered through the error handler. To fix this, use link recovery instead of the error handler.

Fixes 4db7a2360597 ("scsi: ufs: Fix concurrency of error handler and other error recovery paths")
---
 drivers/scsi/ufs/ufshcd.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)
drivers/scsi/ufs/ufshcd.c +9 -1
index a4c70fbc809f..a212e6ad11d5 100644
@@ -3872,7 +3872,7 @@ static int ufshcd_uic_pwr_ctrl(struct ufs_hba *hba, struct uic_command *cmd)
 	hba->uic_async_done = NULL;
 	if (reenable_intr)
 		ufshcd_enable_intr(hba, UIC_COMMAND_COMPL);
-	if (ret) {
+	if (ret && !hba->pm_op_in_progress) {
 		ufshcd_set_link_broken(hba);
 		ufshcd_schedule_eh_work(hba);
 	}
@@ -3880,6 +3880,14 @@ static int ufshcd_uic_pwr_ctrl(struct ufs_hba *hba, struct uic_command *cmd)
 	spin_unlock_irqrestore(hba->host->host_lock, flags);
 	mutex_unlock(&hba->uic_cmd_mutex);
 
+	/*
+	 * If the h8 exit fails during the runtime resume process, it becomes
+	 * stuck and cannot be recovered through the error handler.  To fix
+	 * this, use link recovery instead of the error handler.
+	 */
+	if (ret && hba->pm_op_in_progress)
+		ret = ufshcd_link_recovery(hba);
+
 	return ret;
 }
 
Signature · 1 line
2.39.5
author maintainer
#160 lore raw

PATCH 160/523 kconfig: qconf: fix ConfigList::updateListAllforAll()

In reply to Greg Kroah-Hartman

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

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

From: Masahiro Yamada <[email protected]>

[ Upstream commit 721bfe583c52ba1ea74b3736a31a9dcfe6dd6d95 ]

ConfigList::updateListForAll() and ConfigList::updateListAllforAll() are identical.

Commit f9b918fae678 ("kconfig: qconf: move ConfigView::updateList(All) to ConfigList class") was a misconversion.

Fixes f9b918fae678 ("kconfig: qconf: move ConfigView::updateList(All) to ConfigList class")
---
 scripts/kconfig/qconf.cc | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
scripts/kconfig/qconf.cc +1 -1
index b889fe604e42..1c44c83f61a6 100644
@@ -476,7 +476,7 @@ void ConfigList::updateListAllForAll()
 	while (it.hasNext()) {
 		ConfigList *list = it.next();
 
-		list->updateList();
+		list->updateListAll();
 	}
 }
 
Signature · 1 line
2.39.5
author maintainer
#161 lore raw

PATCH 161/523 PCI: pnv_php: Clean up allocated IRQs on unplug

In reply to Greg Kroah-Hartman

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

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

From: Timothy Pearson <[email protected]>

[ Upstream commit 4668619092554e1b95c9a5ac2941ca47ba6d548a ]

When the root of a nested PCIe bridge configuration is unplugged, the pnv_php driver leaked the allocated IRQ resources for the child bridges' hotplug event notifications, resulting in a panic.

Fix this by walking all child buses and deallocating all its IRQ resources before calling pci_hp_remove_devices().

Also modify the lifetime of the workqueue at struct pnv_php_slot::wq so that it is only destroyed in pnv_php_free_slot(), instead of pnv_php_disable_irq(). This is required since pnv_php_disable_irq() will now be called by workers triggered by hot unplug interrupts, so the workqueue needs to stay allocated.

The abridged kernel panic that occurs without this patch is as follows:

  WARNING: CPU: 0 PID: 687 at kernel/irq/msi.c:292 msi_device_data_release+0x6c/0x9c
  CPU: 0 UID: 0 PID: 687 Comm: bash Not tainted 6.14.0-rc5+ #2
  Call Trace:
   msi_device_data_release+0x34/0x9c (unreliable)
   release_nodes+0x64/0x13c
   devres_release_all+0xc0/0x140
   device_del+0x2d4/0x46c
   pci_destroy_dev+0x5c/0x194
   pci_hp_remove_devices+0x90/0x128
   pci_hp_remove_devices+0x44/0x128
   pnv_php_disable_slot+0x54/0xd4
   power_write_file+0xf8/0x18c
   pci_slot_attr_store+0x40/0x5c
   sysfs_kf_write+0x64/0x78
   kernfs_fop_write_iter+0x1b0/0x290
   vfs_write+0x3bc/0x50c
   ksys_write+0x84/0x140
   system_call_exception+0x124/0x230
   system_call_vectored_common+0x15c/0x2ec
---
 drivers/pci/hotplug/pnv_php.c | 96 ++++++++++++++++++++++++++++-------
 1 file changed, 77 insertions(+), 19 deletions(-)
drivers/pci/hotplug/pnv_php.c +77 -19
index cf9c0e75f0be..1ccd8a8e7c71 100644
@@ -3,6 +3,7 @@
  * PCI Hotplug Driver for PowerPC PowerNV platform.
  *
  * Copyright Gavin Shan, IBM Corporation 2016.
+ * Copyright (C) 2025 Raptor Engineering, LLC
  */
 
 #include <linux/libfdt.h>
@@ -34,8 +35,10 @@ static void pnv_php_register(struct device_node *dn);
 static void pnv_php_unregister_one(struct device_node *dn);
 static void pnv_php_unregister(struct device_node *dn);
 
+static void pnv_php_enable_irq(struct pnv_php_slot *php_slot);
+
 static void pnv_php_disable_irq(struct pnv_php_slot *php_slot,
-				bool disable_device)
+				bool disable_device, bool disable_msi)
 {
 	struct pci_dev *pdev = php_slot->pdev;
 	u16 ctrl;
@@ -51,19 +54,15 @@ static void pnv_php_disable_irq(struct pnv_php_slot *php_slot,
 		php_slot->irq = 0;
 	}
 
-	if (php_slot->wq) {
-		destroy_workqueue(php_slot->wq);
-		php_slot->wq = NULL;
-	}
-
-	if (disable_device) {
+	if (disable_device || disable_msi) {
 		if (pdev->msix_enabled)
 			pci_disable_msix(pdev);
 		else if (pdev->msi_enabled)
 			pci_disable_msi(pdev);
+	}
 
+	if (disable_device)
 		pci_disable_device(pdev);
-	}
 }
 
 static void pnv_php_free_slot(struct kref *kref)
@@ -72,7 +71,8 @@ static void pnv_php_free_slot(struct kref *kref)
 					struct pnv_php_slot, kref);
 
 	WARN_ON(!list_empty(&php_slot->children));
-	pnv_php_disable_irq(php_slot, false);
+	pnv_php_disable_irq(php_slot, false, false);
+	destroy_workqueue(php_slot->wq);
 	kfree(php_slot->name);
 	kfree(php_slot);
 }
@@ -559,8 +559,58 @@ static int pnv_php_reset_slot(struct hotplug_slot *slot, int probe)
 static int pnv_php_enable_slot(struct hotplug_slot *slot)
 {
 	struct pnv_php_slot *php_slot = to_pnv_php_slot(slot);
+	u32 prop32;
+	int ret;
+
+	ret = pnv_php_enable(php_slot, true);
+	if (ret)
+		return ret;
+
+	/* (Re-)enable interrupt if the slot supports surprise hotplug */
+	ret = of_property_read_u32(php_slot->dn, "ibm,slot-surprise-pluggable",
+				   &prop32);
+	if (!ret && prop32)
+		pnv_php_enable_irq(php_slot);
 
-	return pnv_php_enable(php_slot, true);
+	return 0;
+}
+
+/*
+ * Disable any hotplug interrupts for all slots on the provided bus, as well as
+ * all downstream slots in preparation for a hot unplug.
+ */
+static int pnv_php_disable_all_irqs(struct pci_bus *bus)
+{
+	struct pci_bus *child_bus;
+	struct pci_slot *slot;
+
+	/* First go down child buses */
+	list_for_each_entry(child_bus, &bus->children, node)
+		pnv_php_disable_all_irqs(child_bus);
+
+	/* Disable IRQs for all pnv_php slots on this bus */
+	list_for_each_entry(slot, &bus->slots, list) {
+		struct pnv_php_slot *php_slot = to_pnv_php_slot(slot->hotplug);
+
+		pnv_php_disable_irq(php_slot, false, true);
+	}
+
+	return 0;
+}
+
+/*
+ * Disable any hotplug interrupts for all downstream slots on the provided
+ * bus in preparation for a hot unplug.
+ */
+static int pnv_php_disable_all_downstream_irqs(struct pci_bus *bus)
+{
+	struct pci_bus *child_bus;
+
+	/* Go down child buses, recursively deactivating their IRQs */
+	list_for_each_entry(child_bus, &bus->children, node)
+		pnv_php_disable_all_irqs(child_bus);
+
+	return 0;
 }
 
 static int pnv_php_disable_slot(struct hotplug_slot *slot)
@@ -577,6 +627,13 @@ static int pnv_php_disable_slot(struct hotplug_slot *slot)
 	    php_slot->state != PNV_PHP_STATE_REGISTERED)
 		return 0;
 
+	/*
+	 * Free all IRQ resources from all child slots before remove.
+	 * Note that we do not disable the root slot IRQ here as that
+	 * would also deactivate the slot hot (re)plug interrupt!
+	 */
+	pnv_php_disable_all_downstream_irqs(php_slot->bus);
+
 	/* Remove all devices behind the slot */
 	pci_lock_rescan_remove();
 	pci_hp_remove_devices(php_slot->bus);
@@ -645,6 +702,15 @@ static struct pnv_php_slot *pnv_php_alloc_slot(struct device_node *dn)
 		return NULL;
 	}
 
+	/* Allocate workqueue for this slot's interrupt handling */
+	php_slot->wq = alloc_workqueue("pciehp-%s", 0, 0, php_slot->name);
+	if (!php_slot->wq) {
+		SLOT_WARN(php_slot, "Cannot alloc workqueue\n");
+		kfree(php_slot->name);
+		kfree(php_slot);
+		return NULL;
+	}
+
 	if (dn->child && PCI_DN(dn->child))
 		php_slot->slot_no = PCI_SLOT(PCI_DN(dn->child)->devfn);
 	else
@@ -841,14 +907,6 @@ static void pnv_php_init_irq(struct pnv_php_slot *php_slot, int irq)
 	u16 sts, ctrl;
 	int ret;
 
-	/* Allocate workqueue */
-	php_slot->wq = alloc_workqueue("pciehp-%s", 0, 0, php_slot->name);
-	if (!php_slot->wq) {
-		SLOT_WARN(php_slot, "Cannot alloc workqueue\n");
-		pnv_php_disable_irq(php_slot, true);
-		return;
-	}
-
 	/* Check PDC (Presence Detection Change) is broken or not */
 	ret = of_property_read_u32(php_slot->dn, "ibm,slot-broken-pdc",
 				   &broken_pdc);
@@ -867,7 +925,7 @@ static void pnv_php_init_irq(struct pnv_php_slot *php_slot, int irq)
 	ret = request_irq(irq, pnv_php_interrupt, IRQF_SHARED,
 			  php_slot->name, php_slot);
 	if (ret) {
-		pnv_php_disable_irq(php_slot, true);
+		pnv_php_disable_irq(php_slot, true, true);
 		SLOT_WARN(php_slot, "Error %d enabling IRQ %d\n", ret, irq);
 		return;
 	}
Signature · 1 line
2.39.5
author maintainer
#162 lore raw

PATCH 162/523 PCI: pnv_php: Work around switches with broken presence detection

In reply to Greg Kroah-Hartman

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

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

From: Timothy Pearson <[email protected]>

[ Upstream commit 80f9fc2362797538ebd4fd70a1dfa838cc2c2cdb ]

The Microsemi Switchtec PM8533 PFX 48xG3 [11f8:8533] PCIe switch system was observed to incorrectly assert the Presence Detect Set bit in its capabilities when tested on a Raptor Computing Systems Blackbird system, resulting in the hot insert path never attempting a rescan of the bus and any downstream devices not being re-detected.

Work around this by additionally checking whether the PCIe data link is active or not when performing presence detection on downstream switches' ports, similar to the pciehp_hpc.c driver.

---
 drivers/pci/hotplug/pnv_php.c | 27 +++++++++++++++++++++++++++
 1 file changed, 27 insertions(+)
drivers/pci/hotplug/pnv_php.c +27 -0
index 1ccd8a8e7c71..7fa92cb51451 100644
@@ -389,6 +389,20 @@ static int pnv_php_get_power_state(struct hotplug_slot *slot, u8 *state)
 	return 0;
 }
 
+static int pcie_check_link_active(struct pci_dev *pdev)
+{
+	u16 lnk_status;
+	int ret;
+
+	ret = pcie_capability_read_word(pdev, PCI_EXP_LNKSTA, &lnk_status);
+	if (ret == PCIBIOS_DEVICE_NOT_FOUND || PCI_POSSIBLE_ERROR(lnk_status))
+		return -ENODEV;
+
+	ret = !!(lnk_status & PCI_EXP_LNKSTA_DLLLA);
+
+	return ret;
+}
+
 static int pnv_php_get_adapter_state(struct hotplug_slot *slot, u8 *state)
 {
 	struct pnv_php_slot *php_slot = to_pnv_php_slot(slot);
@@ -401,6 +415,19 @@ static int pnv_php_get_adapter_state(struct hotplug_slot *slot, u8 *state)
 	 */
 	ret = pnv_pci_get_presence_state(php_slot->id, &presence);
 	if (ret >= 0) {
+		if (pci_pcie_type(php_slot->pdev) == PCI_EXP_TYPE_DOWNSTREAM &&
+			presence == OPAL_PCI_SLOT_EMPTY) {
+			/*
+			 * Similar to pciehp_hpc, check whether the Link Active
+			 * bit is set to account for broken downstream bridges
+			 * that don't properly assert Presence Detect State, as
+			 * was observed on the Microsemi Switchtec PM8533 PFX
+			 * [11f8:8533].
+			 */
+			if (pcie_check_link_active(php_slot->pdev) > 0)
+				presence = OPAL_PCI_SLOT_PRESENT;
+		}
+
 		*state = presence;
 		ret = 0;
 	} else {
Signature · 1 line
2.39.5
author maintainer
#163 lore raw

PATCH 163/523 powerpc/eeh: Export eeh_unfreeze_pe()

In reply to Greg Kroah-Hartman

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

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

From: Timothy Pearson <[email protected]>

[ Upstream commit e82b34eed04b0ddcff4548b62633467235672fd3 ]

The PowerNV hotplug driver needs to be able to clear any frozen PE(s) on the PHB after suprise removal of a downstream device.

Export the eeh_unfreeze_pe() symbol to allow implementation of this functionality in the php_nv module.

---
 arch/powerpc/kernel/eeh.c | 1 +
 1 file changed, 1 insertion(+)
arch/powerpc/kernel/eeh.c +1 -0
index fbc6eaaf10e1..cd5364e8fe3d 100644
@@ -1140,6 +1140,7 @@ int eeh_unfreeze_pe(struct eeh_pe *pe)
 
 	return ret;
 }
+EXPORT_SYMBOL_GPL(eeh_unfreeze_pe);
 
 
 static struct pci_device_id eeh_reset_ids[] = {
Signature · 1 line
2.39.5
author maintainer
#164 lore raw

PATCH 164/523 powerpc/eeh: Rely on dev->link_active_reporting

In reply to Greg Kroah-Hartman

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

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

From: Maciej W. Rozycki <[email protected]>

[ Upstream commit 1541a21305ceb10fcf3f7cbb23f3e1a00bbf1789 ]

Use dev->link_active_reporting to determine whether Data Link Layer Link Active Reporting is available rather than re-retrieving the capability.

---
 arch/powerpc/kernel/eeh_pe.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)
arch/powerpc/kernel/eeh_pe.c +2 -3
index a856d9ba42d2..3f55e372f259 100644
@@ -670,9 +670,8 @@ static void eeh_bridge_check_link(struct eeh_dev *edev)
 	eeh_ops->write_config(edev, cap + PCI_EXP_LNKCTL, 2, val);
 
 	/* Check link */
-	eeh_ops->read_config(edev, cap + PCI_EXP_LNKCAP, 4, &val);
-	if (!(val & PCI_EXP_LNKCAP_DLLLARC)) {
-		eeh_edev_dbg(edev, "No link reporting capability (0x%08x) \n", val);
+	if (!edev->pdev->link_active_reporting) {
+		eeh_edev_dbg(edev, "No link reporting capability\n");
 		msleep(1000);
 		return;
 	}
Signature · 1 line
2.39.5
author maintainer
#165 lore raw

PATCH 165/523 powerpc/eeh: Make EEH driver device hotplug safe

In reply to Greg Kroah-Hartman

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

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

From: Timothy Pearson <[email protected]>

[ Upstream commit 1010b4c012b0d78dfb9d3132b49aa2ef024a07a7 ]

Multiple race conditions existed between the PCIe hotplug driver and the EEH driver, leading to a variety of kernel oopses of the same general nature:

<pcie device unplug>
<eeh driver trigger>
<hotplug removal trigger>
<pcie tree reconfiguration>
<eeh recovery next step>
<oops in EEH driver bus iteration loop>

A second class of oops is also seen when the underlying bus disappears during device recovery.

Refactor the EEH module to be PCI rescan and remove safe. Also clean up a few minor formatting / readability issues.

---
 arch/powerpc/kernel/eeh_driver.c | 48 +++++++++++++++++++++-----------
 arch/powerpc/kernel/eeh_pe.c     | 10 ++++---
 2 files changed, 38 insertions(+), 20 deletions(-)
arch/powerpc/kernel/eeh_driver.c +32 -16
index 665d847ef9b5..ed5be1bff60c 100644
@@ -258,13 +258,12 @@ static void eeh_pe_report_edev(struct eeh_dev *edev, eeh_report_fn fn,
 	struct pci_driver *driver;
 	enum pci_ers_result new_result;
 
-	pci_lock_rescan_remove();
 	pdev = edev->pdev;
 	if (pdev)
 		get_device(&pdev->dev);
-	pci_unlock_rescan_remove();
 	if (!pdev) {
 		eeh_edev_info(edev, "no device");
+		*result = PCI_ERS_RESULT_DISCONNECT;
 		return;
 	}
 	device_lock(&pdev->dev);
@@ -305,8 +304,9 @@ static void eeh_pe_report(const char *name, struct eeh_pe *root,
 	struct eeh_dev *edev, *tmp;
 
 	pr_info("EEH: Beginning: '%s'\n", name);
-	eeh_for_each_pe(root, pe) eeh_pe_for_each_dev(pe, edev, tmp)
-		eeh_pe_report_edev(edev, fn, result);
+	eeh_for_each_pe(root, pe)
+		eeh_pe_for_each_dev(pe, edev, tmp)
+			eeh_pe_report_edev(edev, fn, result);
 	if (result)
 		pr_info("EEH: Finished:'%s' with aggregate recovery state:'%s'\n",
 			name, pci_ers_result_name(*result));
@@ -384,6 +384,8 @@ static void eeh_dev_restore_state(struct eeh_dev *edev, void *userdata)
 	if (!edev)
 		return;
 
+	pci_lock_rescan_remove();
+
 	/*
 	 * The content in the config space isn't saved because
 	 * the blocked config space on some adapters. We have
@@ -394,14 +396,19 @@ static void eeh_dev_restore_state(struct eeh_dev *edev, void *userdata)
 		if (list_is_last(&edev->entry, &edev->pe->edevs))
 			eeh_pe_restore_bars(edev->pe);
 
+		pci_unlock_rescan_remove();
 		return;
 	}
 
 	pdev = eeh_dev_to_pci_dev(edev);
-	if (!pdev)
+	if (!pdev) {
+		pci_unlock_rescan_remove();
 		return;
+	}
 
 	pci_restore_state(pdev);
+
+	pci_unlock_rescan_remove();
 }
 
 /**
@@ -648,9 +655,7 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus,
 	if (any_passed || driver_eeh_aware || (pe->type & EEH_PE_VF)) {
 		eeh_pe_dev_traverse(pe, eeh_rmv_device, rmv_data);
 	} else {
-		pci_lock_rescan_remove();
 		pci_hp_remove_devices(bus);
-		pci_unlock_rescan_remove();
 	}
 
 	/*
@@ -666,8 +671,6 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus,
 	if (rc)
 		return rc;
 
-	pci_lock_rescan_remove();
-
 	/* Restore PE */
 	eeh_ops->configure_bridge(pe);
 	eeh_pe_restore_bars(pe);
@@ -675,7 +678,6 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus,
 	/* Clear frozen state */
 	rc = eeh_clear_pe_frozen_state(pe, false);
 	if (rc) {
-		pci_unlock_rescan_remove();
 		return rc;
 	}
 
@@ -710,7 +712,6 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus,
 	pe->tstamp = tstamp;
 	pe->freeze_count = cnt;
 
-	pci_unlock_rescan_remove();
 	return 0;
 }
 
@@ -844,10 +845,13 @@ void eeh_handle_normal_event(struct eeh_pe *pe)
 		{LIST_HEAD_INIT(rmv_data.removed_vf_list), 0};
 	int devices = 0;
 
+	pci_lock_rescan_remove();
+
 	bus = eeh_pe_bus_get(pe);
 	if (!bus) {
 		pr_err("%s: Cannot find PCI bus for PHB#%x-PE#%x\n",
 			__func__, pe->phb->global_number, pe->addr);
+		pci_unlock_rescan_remove();
 		return;
 	}
 
@@ -1089,10 +1093,15 @@ void eeh_handle_normal_event(struct eeh_pe *pe)
 		eeh_pe_state_clear(pe, EEH_PE_PRI_BUS, true);
 		eeh_pe_dev_mode_mark(pe, EEH_DEV_REMOVED);
 
-		pci_lock_rescan_remove();
-		pci_hp_remove_devices(bus);
-		pci_unlock_rescan_remove();
+		bus = eeh_pe_bus_get(pe);
+		if (bus)
+			pci_hp_remove_devices(bus);
+		else
+			pr_err("%s: PCI bus for PHB#%x-PE#%x disappeared\n",
+				__func__, pe->phb->global_number, pe->addr);
+
 		/* The passed PE should no longer be used */
+		pci_unlock_rescan_remove();
 		return;
 	}
 
@@ -1109,6 +1118,8 @@ void eeh_handle_normal_event(struct eeh_pe *pe)
 			eeh_clear_slot_attention(edev->pdev);
 
 	eeh_pe_state_clear(pe, EEH_PE_RECOVERING, true);
+
+	pci_unlock_rescan_remove();
 }
 
 /**
@@ -1127,6 +1138,7 @@ void eeh_handle_special_event(void)
 	unsigned long flags;
 	int rc;
 
+	pci_lock_rescan_remove();
 
 	do {
 		rc = eeh_ops->next_error(&pe);
@@ -1166,10 +1178,12 @@ void eeh_handle_special_event(void)
 
 			break;
 		case EEH_NEXT_ERR_NONE:
+			pci_unlock_rescan_remove();
 			return;
 		default:
 			pr_warn("%s: Invalid value %d from next_error()\n",
 				__func__, rc);
+			pci_unlock_rescan_remove();
 			return;
 		}
 
@@ -1181,7 +1195,9 @@ void eeh_handle_special_event(void)
 		if (rc == EEH_NEXT_ERR_FROZEN_PE ||
 		    rc == EEH_NEXT_ERR_FENCED_PHB) {
 			eeh_pe_state_mark(pe, EEH_PE_RECOVERING);
+			pci_unlock_rescan_remove();
 			eeh_handle_normal_event(pe);
+			pci_lock_rescan_remove();
 		} else {
 			eeh_for_each_pe(pe, tmp_pe)
 				eeh_pe_for_each_dev(tmp_pe, edev, tmp_edev)
@@ -1194,7 +1210,6 @@ void eeh_handle_special_event(void)
 				eeh_report_failure, NULL);
 			eeh_set_channel_state(pe, pci_channel_io_perm_failure);
 
-			pci_lock_rescan_remove();
 			list_for_each_entry(hose, &hose_list, list_node) {
 				phb_pe = eeh_phb_pe_get(hose);
 				if (!phb_pe ||
@@ -1213,7 +1228,6 @@ void eeh_handle_special_event(void)
 				}
 				pci_hp_remove_devices(bus);
 			}
-			pci_unlock_rescan_remove();
 		}
 
 		/*
@@ -1223,4 +1237,6 @@ void eeh_handle_special_event(void)
 		if (rc == EEH_NEXT_ERR_DEAD_IOC)
 			break;
 	} while (rc != EEH_NEXT_ERR_NONE);
+
+	pci_unlock_rescan_remove();
 }
arch/powerpc/kernel/eeh_pe.c +6 -4
index 3f55e372f259..fea58e9546f9 100644
@@ -670,10 +670,12 @@ static void eeh_bridge_check_link(struct eeh_dev *edev)
 	eeh_ops->write_config(edev, cap + PCI_EXP_LNKCTL, 2, val);
 
 	/* Check link */
-	if (!edev->pdev->link_active_reporting) {
-		eeh_edev_dbg(edev, "No link reporting capability\n");
-		msleep(1000);
-		return;
+	if (edev->pdev) {
+		if (!edev->pdev->link_active_reporting) {
+			eeh_edev_dbg(edev, "No link reporting capability\n");
+			msleep(1000);
+			return;
+		}
 	}
 
 	/* Wait the link is up until timeout (5s) */
Signature · 1 line
2.39.5
author maintainer
#166 lore raw

PATCH 166/523 PCI: pnv_php: Fix surprise plug detection and recovery

In reply to Greg Kroah-Hartman

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

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

From: Timothy Pearson <[email protected]>

[ Upstream commit a2a2a6fc2469524caa713036297c542746d148dc ]

The existing PowerNV hotplug code did not handle surprise plug events correctly, leading to a complete failure of the hotplug system after device removal and a required reboot to detect new devices.

This comes down to two issues:

1) When a device is surprise removed, often the bridge upstream port will cause a PE freeze on the PHB. If this freeze is not cleared, the MSI interrupts from the bridge hotplug notification logic will not be received by the kernel, stalling all plug events on all slots associated with the PE.

2) When a device is removed from a slot, regardless of surprise or programmatic removal, the associated PHB/PE ls left frozen. If this freeze is not cleared via a fundamental reset, skiboot is unable to clear the freeze and cannot retrain / rescan the slot. This also requires a reboot to clear the freeze and redetect the device in the slot.

Issue the appropriate unfreeze and rescan commands on hotplug events, and don't oops on hotplug if pci_bus_to_OF_node() returns NULL.

---
 arch/powerpc/kernel/pci-hotplug.c |   3 +
 drivers/pci/hotplug/pnv_php.c     | 110 +++++++++++++++++++++++++++++-
 2 files changed, 110 insertions(+), 3 deletions(-)
arch/powerpc/kernel/pci-hotplug.c +3 -0
index 2fc12198ec07..62de678f9f50 100644
@@ -110,6 +110,9 @@ void pci_hp_add_devices(struct pci_bus *bus)
 	struct pci_controller *phb;
 	struct device_node *dn = pci_bus_to_OF_node(bus);
 
+	if (!dn)
+		return;
+
 	phb = pci_bus_to_host(bus);
 
 	mode = PCI_PROBE_NORMAL;
drivers/pci/hotplug/pnv_php.c +107 -3

147 lines not on this page · raw message

Signature · 1 line
2.39.5
author maintainer
#167 lore raw

PATCH 167/523 pNFS/flexfiles: Avoid spurious layout returns in ff_layout_choose_ds_for_read

In reply to Greg Kroah-Hartman

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

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

From: Trond Myklebust <[email protected]>

[ Upstream commit 9bfffea3524b49d0268d01f8e7967f06c4d0a942 ]

The callers of ff_layout_choose_ds_for_read() should decide whether or not they want to return the layout on error. Sometimes, we may just want to retry from the beginning.

Stable-dep-of: f06bedfa62d5 ("pNFS/flexfiles: don't attempt pnfs on fatal DS errors")

---
 fs/nfs/flexfilelayout/flexfilelayout.c | 6 +-----
 1 file changed, 1 insertion(+), 5 deletions(-)
fs/nfs/flexfilelayout/flexfilelayout.c +1 -5
index f8962eaec87b..a053dd05057f 100644
@@ -740,16 +740,12 @@ ff_layout_choose_ds_for_read(struct pnfs_layout_segment *lseg,
 	struct nfs4_ff_layout_segment *fls = FF_LAYOUT_LSEG(lseg);
 	struct nfs4_ff_layout_mirror *mirror;
 	struct nfs4_pnfs_ds *ds;
-	bool fail_return = false;
 	u32 idx;
 
 	/* mirrors are initially sorted by efficiency */
 	for (idx = start_idx; idx < fls->mirror_array_cnt; idx++) {
-		if (idx+1 == fls->mirror_array_cnt)
-			fail_return = !check_device;
-
 		mirror = FF_LAYOUT_COMP(lseg, idx);
-		ds = nfs4_ff_layout_prepare_ds(lseg, mirror, fail_return);
+		ds = nfs4_ff_layout_prepare_ds(lseg, mirror, false);
 		if (!ds)
 			continue;
 
Signature · 1 line
2.39.5
author maintainer
#168 lore raw

PATCH 168/523 pNFS/flexfiles: dont attempt pnfs on fatal DS errors

In reply to Greg Kroah-Hartman

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

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

From: Tigran Mkrtchyan <[email protected]>

[ Upstream commit f06bedfa62d57f7b67d44aacd6badad2e13a803f ]

When an applications get killed (SIGTERM/SIGINT) while pNFS client performs a connection to DS, client ends in an infinite loop of connect-disconnect. This
source of the issue, it that flexfilelayoutdev#nfs4_ff_layout_prepare_ds gets an error on nfs4_pnfs_ds_connect with status ERESTARTSYS, which is set by rpc_signal_task, but the error is treated as transient, thus retried.

The issue is reproducible with Ctrl+C the following script(there should be ~1000 files in a directory, client should must not have any connections to DSes):

```
echo 3 > /proc/sys/vm/drop_caches

for i in *
do
   head -1 $i
done
```

The change aims to propagate the nfs4_ff_layout_prepare_ds error state to the caller that can decide whatever this is a retryable error or not.

Fixes 260f32adb88d ("pNFS/flexfiles: Check the result of nfs4_pnfs_ds_connect")
---
 fs/nfs/flexfilelayout/flexfilelayout.c    | 26 ++++++++++++++---------
 fs/nfs/flexfilelayout/flexfilelayoutdev.c |  6 +++---
 2 files changed, 19 insertions(+), 13 deletions(-)
fs/nfs/flexfilelayout/flexfilelayout.c +16 -10
index a053dd05057f..57150b27c0fd 100644
@@ -739,14 +739,14 @@ ff_layout_choose_ds_for_read(struct pnfs_layout_segment *lseg,
 {
 	struct nfs4_ff_layout_segment *fls = FF_LAYOUT_LSEG(lseg);
 	struct nfs4_ff_layout_mirror *mirror;
-	struct nfs4_pnfs_ds *ds;
+	struct nfs4_pnfs_ds *ds = ERR_PTR(-EAGAIN);
 	u32 idx;
 
 	/* mirrors are initially sorted by efficiency */
 	for (idx = start_idx; idx < fls->mirror_array_cnt; idx++) {
 		mirror = FF_LAYOUT_COMP(lseg, idx);
 		ds = nfs4_ff_layout_prepare_ds(lseg, mirror, false);
-		if (!ds)
+		if (IS_ERR(ds))
 			continue;
 
 		if (check_device &&
@@ -754,10 +754,10 @@ ff_layout_choose_ds_for_read(struct pnfs_layout_segment *lseg,
 			continue;
 
 		*best_idx = idx;
-		return ds;
+		break;
 	}
 
-	return NULL;
+	return ds;
 }
 
 static struct nfs4_pnfs_ds *
@@ -933,7 +933,7 @@ ff_layout_pg_init_write(struct nfs_pageio_descriptor *pgio,
 	for (i = 0; i < pgio->pg_mirror_count; i++) {
 		mirror = FF_LAYOUT_COMP(pgio->pg_lseg, i);
 		ds = nfs4_ff_layout_prepare_ds(pgio->pg_lseg, mirror, true);
-		if (!ds) {
+		if (IS_ERR(ds)) {
 			if (!ff_layout_no_fallback_to_mds(pgio->pg_lseg))
 				goto out_mds;
 			pnfs_generic_pg_cleanup(pgio);
@@ -1820,6 +1820,7 @@ ff_layout_read_pagelist(struct nfs_pgio_header *hdr)
 	u32 idx = hdr->pgio_mirror_idx;
 	int vers;
 	struct nfs_fh *fh;
+	bool ds_fatal_error = false;
 
 	dprintk("--> %s ino %lu pgbase %u req %zu@%llu\n",
 		__func__, hdr->inode->i_ino,
@@ -1827,8 +1828,10 @@ ff_layout_read_pagelist(struct nfs_pgio_header *hdr)
 
 	mirror = FF_LAYOUT_COMP(lseg, idx);
 	ds = nfs4_ff_layout_prepare_ds(lseg, mirror, false);
-	if (!ds)
+	if (IS_ERR(ds)) {
+		ds_fatal_error = nfs_error_is_fatal(PTR_ERR(ds));
 		goto out_failed;
+	}
 
 	ds_clnt = nfs4_ff_find_or_create_ds_client(mirror, ds->ds_clp,
 						   hdr->inode);
@@ -1869,7 +1872,7 @@ ff_layout_read_pagelist(struct nfs_pgio_header *hdr)
 	return PNFS_ATTEMPTED;
 
 out_failed:
-	if (ff_layout_avoid_mds_available_ds(lseg))
+	if (ff_layout_avoid_mds_available_ds(lseg) && !ds_fatal_error)
 		return PNFS_TRY_AGAIN;
 	trace_pnfs_mds_fallback_read_pagelist(hdr->inode,
 			hdr->args.offset, hdr->args.count,
@@ -1890,11 +1893,14 @@ ff_layout_write_pagelist(struct nfs_pgio_header *hdr, int sync)
 	int vers;
 	struct nfs_fh *fh;
 	u32 idx = hdr->pgio_mirror_idx;
+	bool ds_fatal_error = false;
 
 	mirror = FF_LAYOUT_COMP(lseg, idx);
 	ds = nfs4_ff_layout_prepare_ds(lseg, mirror, true);
-	if (!ds)
+	if (IS_ERR(ds)) {
+		ds_fatal_error = nfs_error_is_fatal(PTR_ERR(ds));
 		goto out_failed;
+	}
 
 	ds_clnt = nfs4_ff_find_or_create_ds_client(mirror, ds->ds_clp,
 						   hdr->inode);
@@ -1937,7 +1943,7 @@ ff_layout_write_pagelist(struct nfs_pgio_header *hdr, int sync)
 	return PNFS_ATTEMPTED;
 
 out_failed:
-	if (ff_layout_avoid_mds_available_ds(lseg))
+	if (ff_layout_avoid_mds_available_ds(lseg) && !ds_fatal_error)
 		return PNFS_TRY_AGAIN;
 	trace_pnfs_mds_fallback_write_pagelist(hdr->inode,
 			hdr->args.offset, hdr->args.count,
@@ -1979,7 +1985,7 @@ static int ff_layout_initiate_commit(struct nfs_commit_data *data, int how)
 	idx = calc_ds_index_from_commit(lseg, data->ds_commit_index);
 	mirror = FF_LAYOUT_COMP(lseg, idx);
 	ds = nfs4_ff_layout_prepare_ds(lseg, mirror, true);
-	if (!ds)
+	if (IS_ERR(ds))
 		goto out_err;
 
 	ds_clnt = nfs4_ff_find_or_create_ds_client(mirror, ds->ds_clp,
fs/nfs/flexfilelayout/flexfilelayoutdev.c +3 -3
index 4b0cdddce6eb..11777d33a85e 100644
@@ -368,11 +368,11 @@ nfs4_ff_layout_prepare_ds(struct pnfs_layout_segment *lseg,
 			  struct nfs4_ff_layout_mirror *mirror,
 			  bool fail_return)
 {
-	struct nfs4_pnfs_ds *ds = NULL;
+	struct nfs4_pnfs_ds *ds;
 	struct inode *ino = lseg->pls_layout->plh_inode;
 	struct nfs_server *s = NFS_SERVER(ino);
 	unsigned int max_payload;
-	int status;
+	int status = -EAGAIN;
 
 	if (!ff_layout_init_mirror_ds(lseg->pls_layout, mirror))
 		goto noconnect;
@@ -410,7 +410,7 @@ nfs4_ff_layout_prepare_ds(struct pnfs_layout_segment *lseg,
 	ff_layout_send_layouterror(lseg);
 	if (fail_return || !ff_layout_has_available_ds(lseg))
 		pnfs_error_mark_layout_for_return(ino, lseg);
-	ds = NULL;
+	ds = ERR_PTR(status);
 out:
 	return ds;
 }
Signature · 1 line
2.39.5
#169 lore raw

Re: [PATCH 5.10 168/523] pNFS/flexfiles: dont attempt pnfs on fatal DS errors

Hi Greg,

I just got a report that the proposed fix has a bug in one of the error paths. I am trying to fix that, so you might want to wait with the backport.

Sorry about that,
Tigran.

----- Original Message -----

Quoted 193 lines

From: "Greg Kroah-Hartman" <[email protected]>
To: "stable" <[email protected]>
Cc: "Greg Kroah-Hartman" <[email protected]>, [email protected], "Tigran Mkrtchyan" <[email protected]>, "Trond Myklebust" <[email protected]>, "Sasha Levin" <[email protected]>
Sent: Tuesday, 26 August, 2025 13:06:18
Subject: [PATCH 5.10 168/523] pNFS/flexfiles: dont attempt pnfs on fatal DS errors

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

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

From: Tigran Mkrtchyan <[email protected]>

[ Upstream commit f06bedfa62d57f7b67d44aacd6badad2e13a803f ]

When an applications get killed (SIGTERM/SIGINT) while pNFS client performs a connection
to DS, client ends in an infinite loop of connect-disconnect. This source of the issue, it that flexfilelayoutdev#nfs4_ff_layout_prepare_ds gets an error
on nfs4_pnfs_ds_connect with status ERESTARTSYS, which is set by rpc_signal_task, but
the error is treated as transient, thus retried.

The issue is reproducible with Ctrl+C the following script(there should be ~1000 files in
a directory, client should must not have any connections to DSes):

```
echo 3 > /proc/sys/vm/drop_caches

for i in *
do
  head -1 $i
done
```

The change aims to propagate the nfs4_ff_layout_prepare_ds error state to the caller that can decide whatever this is a retryable error or not.

Fixes 260f32adb88d ("pNFS/flexfiles: Check the result of nfs4_pnfs_ds_connect")

---
fs/nfs/flexfilelayout/flexfilelayout.c | 26 ++++++++++++++---------
fs/nfs/flexfilelayout/flexfilelayoutdev.c | 6 +++---

2 files changed, 19 insertions(+), 13 deletions(-)
fs/nfs/flexfilelayout/flexfilelayout.c +2 -2
index a053dd05057f..57150b27c0fd 100644
@@ -739,14 +739,14 @@ ff_layout_choose_ds_for_read(struct pnfs_layout_segment
 *lseg,
 {
 	struct nfs4_ff_layout_segment *fls = FF_LAYOUT_LSEG(lseg);
 	struct nfs4_ff_layout_mirror *mirror;
-	struct nfs4_pnfs_ds *ds;
+	struct nfs4_pnfs_ds *ds = ERR_PTR(-EAGAIN);
 	u32 idx;
 
 	/* mirrors are initially sorted by efficiency */
 	for (idx = start_idx; idx < fls->mirror_array_cnt; idx++) {
 		mirror = FF_LAYOUT_COMP(lseg, idx);
 		ds = nfs4_ff_layout_prepare_ds(lseg, mirror, false);
-		if (!ds)
+		if (IS_ERR(ds))
 			continue;
 
		if (check_device &&
fs/nfs/flexfilelayout/flexfilelayout.c +2 -2
@@ -754,10 +754,10 @@ ff_layout_choose_ds_for_read(struct pnfs_layout_segment
 *lseg,
 			continue;
 
 		*best_idx = idx;
-		return ds;
+		break;
 	}
 
-	return NULL;
+	return ds;
 }
 

static struct nfs4_pnfs_ds *

fs/nfs/flexfilelayout/flexfilelayout.c +5 -2
@@ -933,7 +933,7 @@ ff_layout_pg_init_write(struct nfs_pageio_descriptor *pgio,
 	for (i = 0; i < pgio->pg_mirror_count; i++) {
 		mirror = FF_LAYOUT_COMP(pgio->pg_lseg, i);
 		ds = nfs4_ff_layout_prepare_ds(pgio->pg_lseg, mirror, true);
-		if (!ds) {
+		if (IS_ERR(ds)) {
 			if (!ff_layout_no_fallback_to_mds(pgio->pg_lseg))
 				goto out_mds;
 			pnfs_generic_pg_cleanup(pgio);
@@ -1820,6 +1820,7 @@ ff_layout_read_pagelist(struct nfs_pgio_header *hdr)
 	u32 idx = hdr->pgio_mirror_idx;
 	int vers;
 	struct nfs_fh *fh;
+	bool ds_fatal_error = false;
 
 	dprintk("--> %s ino %lu pgbase %u req %zu@%llu\n",
 		__func__, hdr->inode->i_ino,
@@ -1827,8 +1828,10 @@ ff_layout_read_pagelist(struct nfs_pgio_header *hdr)
 
 	mirror = FF_LAYOUT_COMP(lseg, idx);
 	ds = nfs4_ff_layout_prepare_ds(lseg, mirror, false);
-	if (!ds)
+	if (IS_ERR(ds)) {
+		ds_fatal_error = nfs_error_is_fatal(PTR_ERR(ds));
 		goto out_failed;
+	}
 
 	ds_clnt = nfs4_ff_find_or_create_ds_client(mirror, ds->ds_clp,
 						   hdr->inode);
@@ -1869,7 +1872,7 @@ ff_layout_read_pagelist(struct nfs_pgio_header *hdr)
 	return PNFS_ATTEMPTED;
 

out_failed:

fs/nfs/flexfilelayout/flexfilelayout.c +1 -1
-	if (ff_layout_avoid_mds_available_ds(lseg))
+	if (ff_layout_avoid_mds_available_ds(lseg) && !ds_fatal_error)
		return PNFS_TRY_AGAIN;
	trace_pnfs_mds_fallback_read_pagelist(hdr->inode,
			hdr->args.offset, hdr->args.count,
fs/nfs/flexfilelayout/flexfilelayout.c +4 -1
@@ -1890,11 +1893,14 @@ ff_layout_write_pagelist(struct nfs_pgio_header *hdr,
 int sync)
 	int vers;
 	struct nfs_fh *fh;
 	u32 idx = hdr->pgio_mirror_idx;
+	bool ds_fatal_error = false;
 
 	mirror = FF_LAYOUT_COMP(lseg, idx);
 	ds = nfs4_ff_layout_prepare_ds(lseg, mirror, true);
-	if (!ds)
+	if (IS_ERR(ds)) {
+		ds_fatal_error = nfs_error_is_fatal(PTR_ERR(ds));
 		goto out_failed;
+	}
 
 	ds_clnt = nfs4_ff_find_or_create_ds_client(mirror, ds->ds_clp,
						   hdr->inode);
fs/nfs/flexfilelayout/flexfilelayout.c +0 -0
@@ -1937,7 +1943,7 @@ ff_layout_write_pagelist(struct nfs_pgio_header *hdr, int
 sync)
 	return PNFS_ATTEMPTED;
 

out_failed:

fs/nfs/flexfilelayout/flexfilelayout.c +1 -1
-	if (ff_layout_avoid_mds_available_ds(lseg))
+	if (ff_layout_avoid_mds_available_ds(lseg) && !ds_fatal_error)
		return PNFS_TRY_AGAIN;
	trace_pnfs_mds_fallback_write_pagelist(hdr->inode,
			hdr->args.offset, hdr->args.count,
fs/nfs/flexfilelayout/flexfilelayout.c +1 -1
@@ -1979,7 +1985,7 @@ static int ff_layout_initiate_commit(struct
 nfs_commit_data *data, int how)
 	idx = calc_ds_index_from_commit(lseg, data->ds_commit_index);
 	mirror = FF_LAYOUT_COMP(lseg, idx);
 	ds = nfs4_ff_layout_prepare_ds(lseg, mirror, true);
-	if (!ds)
+	if (IS_ERR(ds))
 		goto out_err;
 
	ds_clnt = nfs4_ff_find_or_create_ds_client(mirror, ds->ds_clp,
fs/nfs/flexfilelayout/flexfilelayoutdev.c +2 -2
index 4b0cdddce6eb..11777d33a85e 100644
@@ -368,11 +368,11 @@ nfs4_ff_layout_prepare_ds(struct pnfs_layout_segment
 *lseg,
 			  struct nfs4_ff_layout_mirror *mirror,
 			  bool fail_return)
 {
-	struct nfs4_pnfs_ds *ds = NULL;
+	struct nfs4_pnfs_ds *ds;
 	struct inode *ino = lseg->pls_layout->plh_inode;
 	struct nfs_server *s = NFS_SERVER(ino);
 	unsigned int max_payload;
-	int status;
+	int status = -EAGAIN;
 
 	if (!ff_layout_init_mirror_ds(lseg->pls_layout, mirror))
		goto noconnect;
fs/nfs/flexfilelayout/flexfilelayoutdev.c +1 -1
@@ -410,7 +410,7 @@ nfs4_ff_layout_prepare_ds(struct pnfs_layout_segment *lseg,
 	ff_layout_send_layouterror(lseg);
 	if (fail_return || !ff_layout_has_available_ds(lseg))
 		pnfs_error_mark_layout_for_return(ino, lseg);
-	ds = NULL;
+	ds = ERR_PTR(status);

out:

	return ds;
}

--
2.39.5

author maintainer
#170 lore raw

Re: [PATCH 5.10 168/523] pNFS/flexfiles: dont attempt pnfs on fatal DS errors

Quoted 5 lines · Tigran

Hi Greg,

I just got a report that the proposed fix has a bug in one of the error paths. I am trying to fix that, so you might want to wait with the backport.

As it's already in many other released kernels, we are going to have to apply whatever fix you come up with to them, so this should be ok for now. Being "bug compatible" with other stable kernel releases is a feature :)

thanks,

greg k-h

author maintainer
#171 lore raw

PATCH 169/523 NFS: Fix filehandle bounds checking in nfs_fh_to_dentry()

In reply to Greg Kroah-Hartman

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

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

From: Trond Myklebust <[email protected]>

[ Upstream commit ef93a685e01a281b5e2a25ce4e3428cf9371a205 ]

The function needs to check the minimal filehandle length before it can access the embedded filehandle.

Fixes 20fa19027286 ("nfs: add export operations")
---
 fs/nfs/export.c | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)
fs/nfs/export.c +9 -2
index 993be63ab301..784d0f1cfb93 100644
@@ -67,14 +67,21 @@ nfs_fh_to_dentry(struct super_block *sb, struct fid *fid,
 	struct nfs4_label *label = NULL;
 	struct nfs_fattr *fattr = NULL;
 	struct nfs_fh *server_fh = nfs_exp_embedfh(fid->raw);
-	size_t fh_size = offsetof(struct nfs_fh, data) + server_fh->size;
+	size_t fh_size = offsetof(struct nfs_fh, data);
 	const struct nfs_rpc_ops *rpc_ops;
 	struct dentry *dentry;
 	struct inode *inode;
-	int len = EMBED_FH_OFF + XDR_QUADLEN(fh_size);
+	int len = EMBED_FH_OFF;
 	u32 *p = fid->raw;
 	int ret;
 
+	/* Initial check of bounds */
+	if (fh_len < len + XDR_QUADLEN(fh_size) ||
+	    fh_len > XDR_QUADLEN(NFS_MAXFHSIZE))
+		return NULL;
+	/* Calculate embedded filehandle size */
+	fh_size += server_fh->size;
+	len += XDR_QUADLEN(fh_size);
 	/* NULL translates to ESTALE */
 	if (fh_len < len || fh_type != len)
 		return NULL;
Signature · 1 line
2.39.5
author maintainer
#172 lore raw

PATCH 170/523 NFSv4.2: another fix for listxattr

In reply to Greg Kroah-Hartman

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

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

From: Olga Kornievskaia <[email protected]>

[ Upstream commit 9acb237deff7667b0f6b10fe6b1b70c4429ea049 ]

Currently, when the server supports NFS4.1 security labels then security.selinux label in included twice. Instead, only add it when the server doesn't possess security label support.

Fixes 243fea134633 ("NFSv4.2: fix listxattr to return selinux security label")
---
 fs/nfs/nfs4proc.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)
fs/nfs/nfs4proc.c +6 -4
index 77cc1c4219e1..97b5ff9c5c3e 100644
@@ -10378,7 +10378,7 @@ const struct nfs4_minor_version_ops *nfs_v4_minor_ops[] = {
 
 static ssize_t nfs4_listxattr(struct dentry *dentry, char *list, size_t size)
 {
-	ssize_t error, error2, error3, error4;
+	ssize_t error, error2, error3, error4 = 0;
 	size_t left = size;
 
 	error = generic_listxattr(dentry, list, left);
@@ -10406,9 +10406,11 @@ static ssize_t nfs4_listxattr(struct dentry *dentry, char *list, size_t size)
 		left -= error3;
 	}
 
-	error4 = security_inode_listsecurity(d_inode(dentry), list, left);
-	if (error4 < 0)
-		return error4;
+	if (!nfs_server_capable(d_inode(dentry), NFS_CAP_SECURITY_LABEL)) {
+		error4 = security_inode_listsecurity(d_inode(dentry), list, left);
+		if (error4 < 0)
+			return error4;
+	}
 
 	error += error2 + error3 + error4;
 	if (size && error > size)
Signature · 1 line
2.39.5
author maintainer
#173 lore raw

PATCH 171/523 mm: extract might_alloc() debug check

In reply to Greg Kroah-Hartman

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

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

From: Daniel Vetter <[email protected]>

[ Upstream commit 95d6c701f4ca7c44dc148d664f604541266a2333 ]

Extracted from slab.h, which seems to have the most complete version including the correct might_sleep() check. Roll it out to slob.c.

Motivated by a discussion with Paul about possibly changing call_rcu behaviour to allocate memory, but only roughly every 500th call.

There are a lot fewer places in the kernel that care about whether allocating memory is allowed or not (due to deadlocks with reclaim code) than places that care whether sleeping is allowed. But debugging these also tends to be a lot harder, so nice descriptive checks could come in handy. I might have some use eventually for annotations in drivers/gpu.

Note that unlike fs_reclaim_acquire/release gfpflags_allow_blocking does not consult the PF_MEMALLOC flags. But there is no flag equivalent for GFP_NOWAIT, hence this check can't go wrong due to memalloc_no*_save/restore contexts. Willy is working on a patch series which might change this:

https://lore.kernel.org/linux-mm/[email protected]/

I think best would be if that updates gfpflags_allow_blocking(), since there's a ton of callers all over the place for that already.

Cc Randy Dunlap <[email protected]>
Cc Paul E. McKenney <[email protected]>
Cc Christoph Lameter <[email protected]>
Cc Pekka Enberg <[email protected]>
Cc David Rientjes <[email protected]>
Cc Joonsoo Kim <[email protected]>
Cc Peter Zijlstra <[email protected]>
Cc Ingo Molnar <[email protected]>
Cc Vlastimil Babka <[email protected]>
Cc Mathieu Desnoyers <[email protected]>
Cc Sebastian Andrzej Siewior <[email protected]>
Cc Michel Lespinasse <[email protected]>
Cc Daniel Vetter <[email protected]>
Cc Waiman Long <[email protected]>
Cc Thomas Gleixner <[email protected]>
Cc Randy Dunlap <[email protected]>
Cc Dave Chinner <[email protected]>
Cc Qian Cai <[email protected]>
Cc "Matthew Wilcox (Oracle)" <[email protected]>
Cc Christian König <[email protected]>
Cc Ingo Molnar <[email protected]>
Cc Jason Gunthorpe <[email protected]>
Cc Maarten Lankhorst <[email protected]>
Cc Thomas Hellström (Intel) <[email protected]>
Cc Will Deacon <[email protected]>

Stable-dep-of: 99765233ab42 ("NFS: Fixup allocation flags for nfsiod's __GFP_NORETRY")

---
 include/linux/sched/mm.h | 16 ++++++++++++++++
 mm/slab.h                |  5 +----
 mm/slob.c                |  6 ++----
 3 files changed, 19 insertions(+), 8 deletions(-)
include/linux/sched/mm.h +16 -0
index e3e5e149b00e..a856c4478d8c 100644
@@ -189,6 +189,22 @@ static inline void fs_reclaim_acquire(gfp_t gfp_mask) { }
 static inline void fs_reclaim_release(gfp_t gfp_mask) { }
 #endif
 
+/**
+ * might_alloc - Mark possible allocation sites
+ * @gfp_mask: gfp_t flags that would be used to allocate
+ *
+ * Similar to might_sleep() and other annotations, this can be used in functions
+ * that might allocate, but often don't. Compiles to nothing without
+ * CONFIG_LOCKDEP. Includes a conditional might_sleep() if @gfp allows blocking.
+ */
+static inline void might_alloc(gfp_t gfp_mask)
+{
+	fs_reclaim_acquire(gfp_mask);
+	fs_reclaim_release(gfp_mask);
+
+	might_sleep_if(gfpflags_allow_blocking(gfp_mask));
+}
+
 /**
  * memalloc_noio_save - Marks implicit GFP_NOIO allocation scope.
  *
mm/slab.h +1 -4
index 6952e10cf33b..4b70cf4493e6 100644
@@ -507,10 +507,7 @@ static inline struct kmem_cache *slab_pre_alloc_hook(struct kmem_cache *s,
 {
 	flags &= gfp_allowed_mask;
 
-	fs_reclaim_acquire(flags);
-	fs_reclaim_release(flags);
-
-	might_sleep_if(gfpflags_allow_blocking(flags));
+	might_alloc(flags);
 
 	if (should_failslab(s, flags))
 		return NULL;
mm/slob.c +2 -4
index 7cc9805c8091..8d4bfa46247f 100644
@@ -474,8 +474,7 @@ __do_kmalloc_node(size_t size, gfp_t gfp, int node, unsigned long caller)
 
 	gfp &= gfp_allowed_mask;
 
-	fs_reclaim_acquire(gfp);
-	fs_reclaim_release(gfp);
+	might_alloc(gfp);
 
 	if (size < PAGE_SIZE - minalign) {
 		int align = minalign;
@@ -597,8 +596,7 @@ static void *slob_alloc_node(struct kmem_cache *c, gfp_t flags, int node)
 
 	flags &= gfp_allowed_mask;
 
-	fs_reclaim_acquire(flags);
-	fs_reclaim_release(flags);
+	might_alloc(flags);
 
 	if (c->size < PAGE_SIZE) {
 		b = slob_alloc(c->size, flags, c->align, node, 0);
Signature · 1 line
2.39.5
author maintainer
#174 lore raw

PATCH 172/523 XArray: Add calls to might_alloc()

In reply to Greg Kroah-Hartman

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

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

From: Matthew Wilcox (Oracle) <[email protected]>

[ Upstream commit 1dd685c414a7b9fdb3d23aca3aedae84f0b998ae ]

Catch bogus GFP flags deterministically, instead of occasionally when we actually have to allocate memory.

Stable-dep-of: 99765233ab42 ("NFS: Fixup allocation flags for nfsiod's __GFP_NORETRY")

---
 include/linux/xarray.h         | 15 +++++++++++++++
 tools/include/linux/sched/mm.h |  2 ++
 2 files changed, 17 insertions(+)
include/linux/xarray.h +15 -0
index 92c0160b3352..05c025c5c100 100644
@@ -15,6 +15,7 @@
 #include <linux/kconfig.h>
 #include <linux/kernel.h>
 #include <linux/rcupdate.h>
+#include <linux/sched/mm.h>
 #include <linux/spinlock.h>
 #include <linux/types.h>
 
@@ -583,6 +584,7 @@ static inline void *xa_store_bh(struct xarray *xa, unsigned long index,
 {
 	void *curr;
 
+	might_alloc(gfp);
 	xa_lock_bh(xa);
 	curr = __xa_store(xa, index, entry, gfp);
 	xa_unlock_bh(xa);
@@ -609,6 +611,7 @@ static inline void *xa_store_irq(struct xarray *xa, unsigned long index,
 {
 	void *curr;
 
+	might_alloc(gfp);
 	xa_lock_irq(xa);
 	curr = __xa_store(xa, index, entry, gfp);
 	xa_unlock_irq(xa);
@@ -684,6 +687,7 @@ static inline void *xa_cmpxchg(struct xarray *xa, unsigned long index,
 {
 	void *curr;
 
+	might_alloc(gfp);
 	xa_lock(xa);
 	curr = __xa_cmpxchg(xa, index, old, entry, gfp);
 	xa_unlock(xa);
@@ -711,6 +715,7 @@ static inline void *xa_cmpxchg_bh(struct xarray *xa, unsigned long index,
 {
 	void *curr;
 
+	might_alloc(gfp);
 	xa_lock_bh(xa);
 	curr = __xa_cmpxchg(xa, index, old, entry, gfp);
 	xa_unlock_bh(xa);
@@ -738,6 +743,7 @@ static inline void *xa_cmpxchg_irq(struct xarray *xa, unsigned long index,
 {
 	void *curr;
 
+	might_alloc(gfp);
 	xa_lock_irq(xa);
 	curr = __xa_cmpxchg(xa, index, old, entry, gfp);
 	xa_unlock_irq(xa);
@@ -767,6 +773,7 @@ static inline int __must_check xa_insert(struct xarray *xa,
 {
 	int err;
 
+	might_alloc(gfp);
 	xa_lock(xa);
 	err = __xa_insert(xa, index, entry, gfp);
 	xa_unlock(xa);
@@ -796,6 +803,7 @@ static inline int __must_check xa_insert_bh(struct xarray *xa,
 {
 	int err;
 
+	might_alloc(gfp);
 	xa_lock_bh(xa);
 	err = __xa_insert(xa, index, entry, gfp);
 	xa_unlock_bh(xa);
@@ -825,6 +833,7 @@ static inline int __must_check xa_insert_irq(struct xarray *xa,
 {
 	int err;
 
+	might_alloc(gfp);
 	xa_lock_irq(xa);
 	err = __xa_insert(xa, index, entry, gfp);
 	xa_unlock_irq(xa);
@@ -854,6 +863,7 @@ static inline __must_check int xa_alloc(struct xarray *xa, u32 *id,
 {
 	int err;
 
+	might_alloc(gfp);
 	xa_lock(xa);
 	err = __xa_alloc(xa, id, entry, limit, gfp);
 	xa_unlock(xa);
@@ -883,6 +893,7 @@ static inline int __must_check xa_alloc_bh(struct xarray *xa, u32 *id,
 {
 	int err;
 
+	might_alloc(gfp);
 	xa_lock_bh(xa);
 	err = __xa_alloc(xa, id, entry, limit, gfp);
 	xa_unlock_bh(xa);
@@ -912,6 +923,7 @@ static inline int __must_check xa_alloc_irq(struct xarray *xa, u32 *id,
 {
 	int err;
 
+	might_alloc(gfp);
 	xa_lock_irq(xa);
 	err = __xa_alloc(xa, id, entry, limit, gfp);
 	xa_unlock_irq(xa);
@@ -945,6 +957,7 @@ static inline int xa_alloc_cyclic(struct xarray *xa, u32 *id, void *entry,
 {
 	int err;
 
+	might_alloc(gfp);
 	xa_lock(xa);
 	err = __xa_alloc_cyclic(xa, id, entry, limit, next, gfp);
 	xa_unlock(xa);
@@ -978,6 +991,7 @@ static inline int xa_alloc_cyclic_bh(struct xarray *xa, u32 *id, void *entry,
 {
 	int err;
 
+	might_alloc(gfp);
 	xa_lock_bh(xa);
 	err = __xa_alloc_cyclic(xa, id, entry, limit, next, gfp);
 	xa_unlock_bh(xa);
@@ -1011,6 +1025,7 @@ static inline int xa_alloc_cyclic_irq(struct xarray *xa, u32 *id, void *entry,
 {
 	int err;
 
+	might_alloc(gfp);
 	xa_lock_irq(xa);
 	err = __xa_alloc_cyclic(xa, id, entry, limit, next, gfp);
 	xa_unlock_irq(xa);
tools/include/linux/sched/mm.h +2 -0
index c8d9f19c1f35..967294b8edcf 100644
@@ -1,4 +1,6 @@
 #ifndef _TOOLS_PERF_LINUX_SCHED_MM_H
 #define _TOOLS_PERF_LINUX_SCHED_MM_H
 
+#define might_alloc(gfp)	do { } while (0)
+
 #endif  /* _TOOLS_PERF_LINUX_SCHED_MM_H */
Signature · 1 line
2.39.5
author maintainer
#175 lore raw

PATCH 173/523 NFS: Fixup allocation flags for nfsiods __GFP_NORETRY

In reply to Greg Kroah-Hartman

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

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

From: Benjamin Coddington <[email protected]>

[ Upstream commit 99765233ab42bf7a4950377ad7894dce8a5c0e60 ]

If the NFS client is doing writeback from a workqueue context, avoid using __GFP_NORETRY for allocations if the task has set PF_MEMALLOC_NOIO or PF_MEMALLOC_NOFS. The combination of these flags makes memory allocation failures much more likely.

We've seen those allocation failures show up when the loopback driver is doing writeback from a workqueue to a file on NFS, where memory allocation failure results in errors or corruption within the loopback device's filesystem.

---
 fs/nfs/internal.h | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)
fs/nfs/internal.h +6 -3
index 2fdc7c2a17fe..8af263a30fc0 100644
@@ -588,9 +588,12 @@ nfs_write_match_verf(const struct nfs_writeverf *verf,
 
 static inline gfp_t nfs_io_gfp_mask(void)
 {
-	if (current->flags & PF_WQ_WORKER)
-		return GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN;
-	return GFP_KERNEL;
+	gfp_t ret = current_gfp_context(GFP_KERNEL);
+
+	/* For workers __GFP_NORETRY only with __GFP_IO or __GFP_FS */
+	if ((current->flags & PF_WQ_WORKER) && ret == GFP_KERNEL)
+		ret |= __GFP_NORETRY | __GFP_NOWARN;
+	return ret;
 }
 
 /* unlink.c */
Signature · 1 line
2.39.5
author maintainer
#176 lore raw

PATCH 174/523 netpoll: prevent hanging NAPI when netcons gets enabled

In reply to Greg Kroah-Hartman

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

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

From: Jakub Kicinski <[email protected]>

[ Upstream commit 2da4def0f487f24bbb0cece3bb2bcdcb918a0b72 ]

Paolo spotted hangs in NIPA running driver tests against virtio. The tests hang in virtnet_close() -> virtnet_napi_tx_disable().

The problem is only reproducible if running multiple of our tests in sequence (I used TEST_PROGS="xdp.py ping.py netcons_basic.sh \
netpoll_basic.py stats.py"). Initial suspicion was that this is a simple case of double-disable of NAPI, but instrumenting the code reveals:

Deadlocked on NAPI ffff888007cd82c0 (virtnet_poll_tx):
state: 0x37, disabled: false, owner: 0, listed: false, weight: 64

The NAPI was not in fact disabled, owner is 0 (rather than -1), so the NAPI "thinks" it's scheduled for CPU 0 but it's not listed (!list_empty(&n->poll_list) => false). It seems odd that normal NAPI processing would wedge itself like this.

Better suspicion is that netpoll gets enabled while NAPI is polling, and also grabs the NAPI instance. This confuses napi_complete_done():

[netpoll] [normal NAPI]

                                        napi_poll()
                                          have = netpoll_poll_lock()
                                            rcu_access_pointer(dev->npinfo)
                                              return NULL # no netpoll
                                          __napi_poll()
					    ->poll(->weight)
  poll_napi()
    cmpxchg(->poll_owner, -1, cpu)
      poll_one_napi()
        set_bit(NAPI_STATE_NPSVC, ->state)
                                              napi_complete_done()
                                                if (NAPIF_STATE_NPSVC)
                                                  return false
                                           # exit without clearing SCHED

This feels very unlikely, but perhaps virtio has some interactions with the hypervisor in the NAPI ->poll that makes the race window larger?

Best I could to to prove the theory was to add and trigger this warning in napi_poll (just before netpoll_poll_unlock()):

      WARN_ONCE(!have && rcu_access_pointer(n->dev->npinfo) &&
                napi_is_scheduled(n) && list_empty(&n->poll_list),
                "NAPI race with netpoll %px", n);

If this warning hits the next virtio_close() will hang.

This patch survived 30 test iterations without a hang (without it the longest clean run was around 10). Credit for triggering this goes to Breno's recent netconsole tests.

---
 net/core/netpoll.c | 7 +++++++
 1 file changed, 7 insertions(+)
net/core/netpoll.c +7 -0
index 66a6f6241239..db18154aa238 100644
@@ -812,6 +812,13 @@ int netpoll_setup(struct netpoll *np)
 		goto put;
 
 	rtnl_unlock();
+
+	/* Make sure all NAPI polls which started before dev->npinfo
+	 * was visible have exited before we start calling NAPI poll.
+	 * NAPI skips locking if dev->npinfo is NULL.
+	 */
+	synchronize_rcu();
+
 	return 0;
 
 put:
Signature · 1 line
2.39.5
author maintainer
#177 lore raw

PATCH 175/523 phy: mscc: Fix parsing of unicast frames

In reply to Greg Kroah-Hartman

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

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

From: Horatiu Vultur <[email protected]>

[ Upstream commit 6fb5ff63b35b7e849cc8510957f25753f87f63d2 ]

According to the 1588 standard, it is possible to use both unicast and multicast frames to send the PTP information. It was noticed that if the frames were unicast they were not processed by the analyzer meaning that they were not timestamped. Therefore fix this to match also these unicast frames.

Fixes ab2bf9339357 ("net: phy: mscc: 1588 block initialization")
---
 drivers/net/phy/mscc/mscc_ptp.c | 1 +
 drivers/net/phy/mscc/mscc_ptp.h | 1 +
 2 files changed, 2 insertions(+)
drivers/net/phy/mscc/mscc_ptp.c +1 -0
index 85102e895665..4a00b82d3ca5 100644
@@ -897,6 +897,7 @@ static int vsc85xx_eth1_conf(struct phy_device *phydev, enum ts_blk blk,
 				     get_unaligned_be32(ptp_multicast));
 	} else {
 		val |= ANA_ETH1_FLOW_ADDR_MATCH2_ANY_MULTICAST;
+		val |= ANA_ETH1_FLOW_ADDR_MATCH2_ANY_UNICAST;
 		vsc85xx_ts_write_csr(phydev, blk,
 				     MSCC_ANA_ETH1_FLOW_ADDR_MATCH2(0), val);
 		vsc85xx_ts_write_csr(phydev, blk,
drivers/net/phy/mscc/mscc_ptp.h +1 -0
index 3ea163af0f4f..7e3809e4aa5f 100644
@@ -98,6 +98,7 @@
 #define MSCC_ANA_ETH1_FLOW_ADDR_MATCH2(x) (MSCC_ANA_ETH1_FLOW_ENA(x) + 3)
 #define ANA_ETH1_FLOW_ADDR_MATCH2_MASK_MASK	GENMASK(22, 20)
 #define ANA_ETH1_FLOW_ADDR_MATCH2_ANY_MULTICAST	0x400000
+#define ANA_ETH1_FLOW_ADDR_MATCH2_ANY_UNICAST	0x200000
 #define ANA_ETH1_FLOW_ADDR_MATCH2_FULL_ADDR	0x100000
 #define ANA_ETH1_FLOW_ADDR_MATCH2_SRC_DEST_MASK	GENMASK(17, 16)
 #define ANA_ETH1_FLOW_ADDR_MATCH2_SRC_DEST	0x020000
Signature · 1 line
2.39.5
author maintainer
#178 lore raw

PATCH 176/523 pptp: ensure minimal skb length in pptp_xmit()

In reply to Greg Kroah-Hartman

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

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

From: Eric Dumazet <[email protected]>

[ Upstream commit de9c4861fb42f0cd72da844c3c34f692d5895b7b ]

Commit aabc6596ffb3 ("net: ppp: Add bound checking for skb data on ppp_sync_txmung") fixed ppp_sync_txmunge()

We need a similar fix in pptp_xmit(), otherwise we might read uninit data as reported by syzbot.

BUG: KMSAN: uninit-value in pptp_xmit+0xc34/0x2720 drivers/net/ppp/pptp.c:193
  pptp_xmit+0xc34/0x2720 drivers/net/ppp/pptp.c:193
  ppp_channel_bridge_input drivers/net/ppp/ppp_generic.c:2290 [inline]
  ppp_input+0x1d6/0xe60 drivers/net/ppp/ppp_generic.c:2314
  pppoe_rcv_core+0x1e8/0x760 drivers/net/ppp/pppoe.c:379
  sk_backlog_rcv+0x142/0x420 include/net/sock.h:1148
  __release_sock+0x1d3/0x330 net/core/sock.c:3213
  release_sock+0x6b/0x270 net/core/sock.c:3767
  pppoe_sendmsg+0x15d/0xcb0 drivers/net/ppp/pppoe.c:904
  sock_sendmsg_nosec net/socket.c:712 [inline]
  __sock_sendmsg+0x330/0x3d0 net/socket.c:727
  ____sys_sendmsg+0x893/0xd80 net/socket.c:2566
  ___sys_sendmsg+0x271/0x3b0 net/socket.c:2620
  __sys_sendmmsg+0x2d9/0x7c0 net/socket.c:2709
---
 drivers/net/ppp/pptp.c | 15 +++++++++------
 1 file changed, 9 insertions(+), 6 deletions(-)
drivers/net/ppp/pptp.c +9 -6
index 05a75b5a8b68..1b306562f916 100644
@@ -159,9 +159,7 @@ static int pptp_xmit(struct ppp_channel *chan, struct sk_buff *skb)
 	int len;
 	unsigned char *data;
 	__u32 seq_recv;
-
-
-	struct rtable *rt;
+	struct rtable *rt = NULL;
 	struct net_device *tdev;
 	struct iphdr  *iph;
 	int    max_headroom;
@@ -179,16 +177,20 @@ static int pptp_xmit(struct ppp_channel *chan, struct sk_buff *skb)
 
 	if (skb_headroom(skb) < max_headroom || skb_cloned(skb) || skb_shared(skb)) {
 		struct sk_buff *new_skb = skb_realloc_headroom(skb, max_headroom);
-		if (!new_skb) {
-			ip_rt_put(rt);
+
+		if (!new_skb)
 			goto tx_error;
-		}
+
 		if (skb->sk)
 			skb_set_owner_w(new_skb, skb->sk);
 		consume_skb(skb);
 		skb = new_skb;
 	}
 
+	/* Ensure we can safely access protocol field and LCP code */
+	if (!pskb_may_pull(skb, 3))
+		goto tx_error;
+
 	data = skb->data;
 	islcp = ((data[0] << 8) + data[1]) == PPP_LCP && 1 <= data[2] && data[2] <= 7;
 
@@ -262,6 +264,7 @@ static int pptp_xmit(struct ppp_channel *chan, struct sk_buff *skb)
 	return 1;
 
 tx_error:
+	ip_rt_put(rt);
 	kfree_skb(skb);
 	return 1;
 }
Signature · 1 line
2.39.5
author maintainer
#179 lore raw

PATCH 177/523 ipv6: reject malicious packets in ipv6_gso_segment()

In reply to Greg Kroah-Hartman

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

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

From: Eric Dumazet <[email protected]>

[ Upstream commit d45cf1e7d7180256e17c9ce88e32e8061a7887fe ]

syzbot was able to craft a packet with very long IPv6 extension headers leading to an overflow of skb->transport_header.

This 16bit field has a limited range.

Add skb_reset_transport_header_careful() helper and use it from ipv6_gso_segment()

WARNING: CPU: 0 PID: 5871 at ./include/linux/skbuff.h:3032 skb_reset_transport_header include/linux/skbuff.h:3032 [inline]
WARNING: CPU: 0 PID: 5871 at ./include/linux/skbuff.h:3032 ipv6_gso_segment+0x15e2/0x21e0 net/ipv6/ip6_offload.c:151
Modules linked in:
CPU: 0 UID: 0 PID: 5871 Comm: syz-executor211 Not tainted 6.16.0-rc6-syzkaller-g7abc678e3084 #0 PREEMPT(full)
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 07/12/2025
 RIP: 0010:skb_reset_transport_header include/linux/skbuff.h:3032 [inline]
 RIP: 0010:ipv6_gso_segment+0x15e2/0x21e0 net/ipv6/ip6_offload.c:151
Call Trace:
 <TASK>
  skb_mac_gso_segment+0x31c/0x640 net/core/gso.c:53
  nsh_gso_segment+0x54a/0xe10 net/nsh/nsh.c:110
  skb_mac_gso_segment+0x31c/0x640 net/core/gso.c:53
  __skb_gso_segment+0x342/0x510 net/core/gso.c:124
  skb_gso_segment include/net/gso.h:83 [inline]
  validate_xmit_skb+0x857/0x11b0 net/core/dev.c:3950
  validate_xmit_skb_list+0x84/0x120 net/core/dev.c:4000
  sch_direct_xmit+0xd3/0x4b0 net/sched/sch_generic.c:329
  __dev_xmit_skb net/core/dev.c:4102 [inline]
  __dev_queue_xmit+0x17b6/0x3a70 net/core/dev.c:4679
---
 include/linux/skbuff.h | 23 +++++++++++++++++++++++
 net/ipv6/ip6_offload.c |  4 +++-
 2 files changed, 26 insertions(+), 1 deletion(-)
include/linux/skbuff.h +23 -0
index 3248e4aeec03..ca7f2a2c3e3f 100644
@@ -2519,6 +2519,29 @@ static inline void skb_reset_transport_header(struct sk_buff *skb)
 	skb->transport_header = skb->data - skb->head;
 }
 
+/**
+ * skb_reset_transport_header_careful - conditionally reset transport header
+ * @skb: buffer to alter
+ *
+ * Hardened version of skb_reset_transport_header().
+ *
+ * Returns: true if the operation was a success.
+ */
+static inline bool __must_check
+skb_reset_transport_header_careful(struct sk_buff *skb)
+{
+	long offset = skb->data - skb->head;
+
+	if (unlikely(offset != (typeof(skb->transport_header))offset))
+		return false;
+
+	if (unlikely(offset == (typeof(skb->transport_header))~0U))
+		return false;
+
+	skb->transport_header = offset;
+	return true;
+}
+
 static inline void skb_set_transport_header(struct sk_buff *skb,
 					    const int offset)
 {
net/ipv6/ip6_offload.c +3 -1
index 673f02ea62aa..c145be2fd6e4 100644
@@ -111,7 +111,9 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
 
 	ops = rcu_dereference(inet6_offloads[proto]);
 	if (likely(ops && ops->callbacks.gso_segment)) {
-		skb_reset_transport_header(skb);
+		if (!skb_reset_transport_header_careful(skb))
+			goto out;
+
 		segs = ops->callbacks.gso_segment(skb, features);
 		if (!segs)
 			skb->network_header = skb_mac_header(skb) + nhoff - skb->head;
Signature · 1 line
2.39.5
author maintainer
#180 lore raw

PATCH 178/523 net: drop UFO packets in udp_rcv_segment()

In reply to Greg Kroah-Hartman

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

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

From: Wang Liang <[email protected]>

[ Upstream commit d46e51f1c78b9ab9323610feb14238d06d46d519 ]

When sending a packet with virtio_net_hdr to tun device, if the gso_type in virtio_net_hdr is SKB_GSO_UDP and the gso_size is less than udphdr size, below crash may happen.

  ------------[ cut here ]------------
  kernel BUG at net/core/skbuff.c:4572!
  Oops: invalid opcode: 0000 [#1] SMP NOPTI
  CPU: 0 UID: 0 PID: 62 Comm: mytest Not tainted 6.16.0-rc7 #203 PREEMPT(voluntary)
  Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.15.0-1 04/01/2014
  RIP: 0010:skb_pull_rcsum+0x8e/0xa0
  Code: 00 00 5b c3 cc cc cc cc 8b 93 88 00 00 00 f7 da e8 37 44 38 00 f7 d8 89 83 88 00 00 00 48 8b 83 c8 00 00 00 5b c3 cc cc cc cc <0f> 0b 0f 0b 66 66 2e 0f 1f 84 00 000
  RSP: 0018:ffffc900001fba38 EFLAGS: 00000297
  RAX: 0000000000000004 RBX: ffff8880040c1000 RCX: ffffc900001fb948
  RDX: ffff888003e6d700 RSI: 0000000000000008 RDI: ffff88800411a062
  RBP: ffff8880040c1000 R08: 0000000000000000 R09: 0000000000000001
  R10: ffff888003606c00 R11: 0000000000000001 R12: 0000000000000000
  R13: ffff888004060900 R14: ffff888004050000 R15: ffff888004060900
  FS:  000000002406d3c0(0000) GS:ffff888084a19000(0000) knlGS:0000000000000000
  CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
  CR2: 0000000020000040 CR3: 0000000004007000 CR4: 00000000000006f0
  Call Trace:
   <TASK>
   udp_queue_rcv_one_skb+0x176/0x4b0 net/ipv4/udp.c:2445
   udp_queue_rcv_skb+0x155/0x1f0 net/ipv4/udp.c:2475
   udp_unicast_rcv_skb+0x71/0x90 net/ipv4/udp.c:2626
   __udp4_lib_rcv+0x433/0xb00 net/ipv4/udp.c:2690
   ip_protocol_deliver_rcu+0xa6/0x160 net/ipv4/ip_input.c:205
   ip_local_deliver_finish+0x72/0x90 net/ipv4/ip_input.c:233
   ip_sublist_rcv_finish+0x5f/0x70 net/ipv4/ip_input.c:579
   ip_sublist_rcv+0x122/0x1b0 net/ipv4/ip_input.c:636
   ip_list_rcv+0xf7/0x130 net/ipv4/ip_input.c:670
   __netif_receive_skb_list_core+0x21d/0x240 net/core/dev.c:6067
   netif_receive_skb_list_internal+0x186/0x2b0 net/core/dev.c:6210
   napi_complete_done+0x78/0x180 net/core/dev.c:6580
   tun_get_user+0xa63/0x1120 drivers/net/tun.c:1909
   tun_chr_write_iter+0x65/0xb0 drivers/net/tun.c:1984
   vfs_write+0x300/0x420 fs/read_write.c:593
   ksys_write+0x60/0xd0 fs/read_write.c:686
   do_syscall_64+0x50/0x1c0 arch/x86/entry/syscall_64.c:63
   </TASK>

To trigger gso segment in udp_queue_rcv_skb(), we should also set option UDP_ENCAP_ESPINUDP to enable udp_sk(sk)->encap_rcv. When the encap_rcv hook return 1 in udp_queue_rcv_one_skb(), udp_csum_pull_header() will try to pull udphdr, but the skb size has been segmented to gso size, which leads to this crash.

Previous commit cf329aa42b66 ("udp: cope with UDP GRO packet misdirection") introduces segmentation in UDP receive path only for GRO, which was never intended to be used for UFO, so drop UFO packets in udp_rcv_segment().

---
 include/net/udp.h | 24 ++++++++++++++++++------
 1 file changed, 18 insertions(+), 6 deletions(-)
include/net/udp.h +18 -6
index db599b15b630..5e5e8c7c6777 100644
@@ -479,6 +479,16 @@ static inline struct sk_buff *udp_rcv_segment(struct sock *sk,
 {
 	netdev_features_t features = NETIF_F_SG;
 	struct sk_buff *segs;
+	int drop_count;
+
+	/*
+	 * Segmentation in UDP receive path is only for UDP GRO, drop udp
+	 * fragmentation offload (UFO) packets.
+	 */
+	if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP) {
+		drop_count = 1;
+		goto drop;
+	}
 
 	/* Avoid csum recalculation by skb_segment unless userspace explicitly
 	 * asks for the final checksum values
@@ -502,16 +512,18 @@ static inline struct sk_buff *udp_rcv_segment(struct sock *sk,
 	 */
 	segs = __skb_gso_segment(skb, features, false);
 	if (IS_ERR_OR_NULL(segs)) {
-		int segs_nr = skb_shinfo(skb)->gso_segs;
-
-		atomic_add(segs_nr, &sk->sk_drops);
-		SNMP_ADD_STATS(__UDPX_MIB(sk, ipv4), UDP_MIB_INERRORS, segs_nr);
-		kfree_skb(skb);
-		return NULL;
+		drop_count = skb_shinfo(skb)->gso_segs;
+		goto drop;
 	}
 
 	consume_skb(skb);
 	return segs;
+
+drop:
+	atomic_add(drop_count, &sk->sk_drops);
+	SNMP_ADD_STATS(__UDPX_MIB(sk, ipv4), UDP_MIB_INERRORS, drop_count);
+	kfree_skb(skb);
+	return NULL;
 }
 
 #ifdef CONFIG_BPF_SYSCALL
Signature · 1 line
2.39.5
author maintainer
#181 lore raw

PATCH 179/523 benet: fix BUG when creating VFs

In reply to Greg Kroah-Hartman

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

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

From: Michal Schmidt <[email protected]>

[ Upstream commit 5a40f8af2ba1b9bdf46e2db10e8c9710538fbc63 ]

benet crashes as soon as SRIOV VFs are created:

kernel BUG at mm/vmalloc.c:3457!

 Oops: invalid opcode: 0000 [#1] SMP KASAN NOPTI
 CPU: 4 UID: 0 PID: 7408 Comm: test.sh Kdump: loaded Not tainted 6.16.0+ #1 PREEMPT(voluntary)
 [...]
 RIP: 0010:vunmap+0x5f/0x70
 [...]
 Call Trace:
  <TASK>
  __iommu_dma_free+0xe8/0x1c0
  be_cmd_set_mac_list+0x3fe/0x640 [be2net]
  be_cmd_set_mac+0xaf/0x110 [be2net]
  be_vf_eth_addr_config+0x19f/0x330 [be2net]
  be_vf_setup+0x4f7/0x990 [be2net]
  be_pci_sriov_configure+0x3a1/0x470 [be2net]
  sriov_numvfs_store+0x20b/0x380
  kernfs_fop_write_iter+0x354/0x530
  vfs_write+0x9b9/0xf60
  ksys_write+0xf3/0x1d0
  do_syscall_64+0x8c/0x3d0

be_cmd_set_mac_list() calls dma_free_coherent() under a spin_lock_bh. Fix it by freeing only after the lock has been released.

Fixes 1a82d19ca2d6 ("be2net: fix sleeping while atomic bugs in be_ndo_bridge_getlink")
---
 drivers/net/ethernet/emulex/benet/be_cmds.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/net/ethernet/emulex/benet/be_cmds.c +1 -1
index d9bceb26f4e5..d6984c179bae 100644
@@ -3851,8 +3851,8 @@ int be_cmd_set_mac_list(struct be_adapter *adapter, u8 *mac_array,
 	status = be_mcc_notify_wait(adapter);
 
 err:
-	dma_free_coherent(&adapter->pdev->dev, cmd.size, cmd.va, cmd.dma);
 	spin_unlock_bh(&adapter->mcc_lock);
+	dma_free_coherent(&adapter->pdev->dev, cmd.size, cmd.va, cmd.dma);
 	return status;
 }
 
Signature · 1 line
2.39.5
author maintainer
#182 lore raw

PATCH 180/523 ALSA: hda/ca0132: Fix missing error handling in ca0132_alt_select_out()

In reply to Greg Kroah-Hartman

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

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

From: Takashi Iwai <[email protected]>

[ Upstream commit 9f320dfb0ffc555aa2eac8331dee0c2c16f67633 ]

There are a couple of cases where the error is ignored or the error code isn't propagated in ca0132_alt_select_out(). Fix those.

Fixes def3f0a5c700 ("ALSA: hda/ca0132 - Add quirk output selection structures.")
---
 sound/pci/hda/patch_ca0132.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)
sound/pci/hda/patch_ca0132.c +4 -1
index 6d67cca4cfa6..b9d88b156f40 100644
@@ -4671,7 +4671,8 @@ static int ca0132_alt_select_out(struct hda_codec *codec)
 	if (err < 0)
 		goto exit;
 
-	if (ca0132_alt_select_out_quirk_set(codec) < 0)
+	err = ca0132_alt_select_out_quirk_set(codec);
+	if (err < 0)
 		goto exit;
 
 	switch (spec->cur_out_type) {
@@ -4761,6 +4762,8 @@ static int ca0132_alt_select_out(struct hda_codec *codec)
 				spec->bass_redirection_val);
 	else
 		err = ca0132_alt_surround_set_bass_redirection(codec, 0);
+	if (err < 0)
+		goto exit;
 
 	/* Unmute DSP now that we're done with output selection. */
 	err = dspio_set_uint_param(codec, 0x96,
Signature · 1 line
2.39.5
author maintainer
#183 lore raw

PATCH 181/523 smb: client: let recv_done() cleanup before notifying the callers.

In reply to Greg Kroah-Hartman

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

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

From: Stefan Metzmacher <[email protected]>

[ Upstream commit bdd7afc6dca5e0ebbb75583484aa6ea9e03fbb13 ]

We should call put_receive_buffer() before waking up the callers.

For the internal error case of response->type being unexpected, we now also call smbd_disconnect_rdma_connection() instead of not waking up the callers at all.

Note that the SMBD_TRANSFER_DATA case still has problems, which will be addressed in the next commit in order to make it easier to review this one.

Cc Steve French <[email protected]>
Cc Tom Talpey <[email protected]>
Cc Long Li <[email protected]>
Fixes f198186aa9bb ("CIFS: SMBD: Establish SMB Direct connection")
---
 fs/cifs/smbdirect.c | 14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)
fs/cifs/smbdirect.c +8 -6
index 7d18b9268817..ae332f3771f6 100644
@@ -454,7 +454,6 @@ static void recv_done(struct ib_cq *cq, struct ib_wc *wc)
 	if (wc->status != IB_WC_SUCCESS || wc->opcode != IB_WC_RECV) {
 		log_rdma_recv(INFO, "wc->status=%d opcode=%d\n",
 			wc->status, wc->opcode);
-		smbd_disconnect_rdma_connection(info);
 		goto error;
 	}
 
@@ -471,8 +470,9 @@ static void recv_done(struct ib_cq *cq, struct ib_wc *wc)
 		info->full_packet_received = true;
 		info->negotiate_done =
 			process_negotiation_response(response, wc->byte_len);
+		put_receive_buffer(info, response);
 		complete(&info->negotiate_completion);
-		break;
+		return;
 
 	/* SMBD data transfer packet */
 	case SMBD_TRANSFER_DATA:
@@ -529,14 +529,16 @@ static void recv_done(struct ib_cq *cq, struct ib_wc *wc)
 		}
 
 		return;
-
-	default:
-		log_rdma_recv(ERR,
-			"unexpected response type=%d\n", response->type);
 	}
 
+	/*
+	 * This is an internal error!
+	 */
+	log_rdma_recv(ERR, "unexpected response type=%d\n", response->type);
+	WARN_ON_ONCE(response->type != SMBD_TRANSFER_DATA);
 error:
 	put_receive_buffer(info, response);
+	smbd_disconnect_rdma_connection(info);
 }
 
 static struct rdma_cm_id *smbd_create_id(
Signature · 1 line
2.39.5
author maintainer
#184 lore raw

PATCH 182/523 pptp: fix pptp_xmit() error path

In reply to Greg Kroah-Hartman

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

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

From: Eric Dumazet <[email protected]>

[ Upstream commit ae633388cae349886f1a3cfb27aa092854b24c1b ]

I accidentally added a bug in pptp_xmit() that syzbot caught for us.

Only call ip_rt_put() if a route has been allocated.

BUG: unable to handle page fault for address: ffffffffffffffdb
PGD df3b067 P4D df3b067 PUD df3d067 PMD 0
Oops: Oops: 0002 [#1] SMP KASAN PTI
CPU: 1 UID: 0 PID: 6346 Comm: syz.0.336 Not tainted 6.16.0-next-20250804-syzkaller #0 PREEMPT(full)
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 07/12/2025
RIP: 0010:arch_atomic_add_return arch/x86/include/asm/atomic.h:85 [inline]
RIP: 0010:raw_atomic_sub_return_release include/linux/atomic/atomic-arch-fallback.h:846 [inline]
RIP: 0010:atomic_sub_return_release include/linux/atomic/atomic-instrumented.h:327 [inline]
RIP: 0010:__rcuref_put include/linux/rcuref.h:109 [inline]
RIP: 0010:rcuref_put+0x172/0x210 include/linux/rcuref.h:173
Call Trace:
 <TASK>
 dst_release+0x24/0x1b0 net/core/dst.c:167
 ip_rt_put include/net/route.h:285 [inline]
 pptp_xmit+0x14b/0x1a90 drivers/net/ppp/pptp.c:267
 __ppp_channel_push+0xf2/0x1c0 drivers/net/ppp/ppp_generic.c:2166
 ppp_channel_push+0x123/0x660 drivers/net/ppp/ppp_generic.c:2198
 ppp_write+0x2b0/0x400 drivers/net/ppp/ppp_generic.c:544
 vfs_write+0x27b/0xb30 fs/read_write.c:684
 ksys_write+0x145/0x250 fs/read_write.c:738
 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline]
 do_syscall_64+0xfa/0x3b0 arch/x86/entry/syscall_64.c:94
 entry_SYSCALL_64_after_hwframe+0x77/0x7f
---
 drivers/net/ppp/pptp.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)
drivers/net/ppp/pptp.c +4 -3
index 1b306562f916..3c1e7155e2bf 100644
@@ -159,17 +159,17 @@ static int pptp_xmit(struct ppp_channel *chan, struct sk_buff *skb)
 	int len;
 	unsigned char *data;
 	__u32 seq_recv;
-	struct rtable *rt = NULL;
+	struct rtable *rt;
 	struct net_device *tdev;
 	struct iphdr  *iph;
 	int    max_headroom;
 
 	if (sk_pppox(po)->sk_state & PPPOX_DEAD)
-		goto tx_error;
+		goto tx_drop;
 
 	rt = pptp_route_output(po, &fl4);
 	if (IS_ERR(rt))
-		goto tx_error;
+		goto tx_drop;
 
 	tdev = rt->dst.dev;
 
@@ -265,6 +265,7 @@ static int pptp_xmit(struct ppp_channel *chan, struct sk_buff *skb)
 
 tx_error:
 	ip_rt_put(rt);
+tx_drop:
 	kfree_skb(skb);
 	return 1;
 }
Signature · 1 line
2.39.5
author maintainer
#185 lore raw

PATCH 183/523 perf/core: Dont leak AUX buffer refcount on allocation failure

In reply to Greg Kroah-Hartman

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

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

From: Thomas Gleixner <[email protected]>

commit 5468c0fbccbb9d156522c50832244a8b722374fb upstream.

Failure of the AUX buffer allocation leaks the reference count.

Set the reference count to 1 only when the allocation succeeds.

Fixes 45bfb2e50471 ("perf/core: Add AUX area to ring buffer for raw data streams")
---
 kernel/events/core.c |    7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)
kernel/events/core.c +4 -3
@@ -6290,9 +6290,7 @@ static int perf_mmap(struct file *file,
 			goto unlock;
 		}
 
-		atomic_set(&rb->aux_mmap_count, 1);
 		user_extra = nr_pages;
-
 		goto accounting;
 	}
 
@@ -6394,8 +6392,10 @@ accounting:
 	} else {
 		ret = rb_alloc_aux(rb, event, vma->vm_pgoff, nr_pages,
 				   event->attr.aux_watermark, flags);
-		if (!ret)
+		if (!ret) {
+			atomic_set(&rb->aux_mmap_count, 1);
 			rb->aux_mmap_locked = extra;
+		}
 	}
 
 unlock:
@@ -6405,6 +6405,7 @@ unlock:
 
 		atomic_inc(&event->mmap_count);
 	} else if (rb) {
+		/* AUX allocation failed */
 		atomic_dec(&rb->mmap_count);
 	}
 aux_unlock:
author maintainer
#186 lore raw

PATCH 184/523 perf/core: Exit early on perf_mmap() fail

In reply to Greg Kroah-Hartman

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

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

From: Thomas Gleixner <[email protected]>

commit 07091aade394f690e7b655578140ef84d0e8d7b0 upstream.

When perf_mmap() fails to allocate a buffer, it still invokes the event_mapped() callback of the related event. On X86 this might increase the perf_rdpmc_allowed reference counter. But nothing undoes this as perf_mmap_close() is never called in this case, which causes another reference count leak.

Return early on failure to prevent that.

Fixes 1e0fb9ec679c ("perf/core: Add pmu callbacks to track event mapping and unmapping")
---
 kernel/events/core.c |    3 +++
 1 file changed, 3 insertions(+)
kernel/events/core.c +3 -0
@@ -6413,6 +6413,9 @@ aux_unlock:
 		mutex_unlock(aux_mutex);
 	mutex_unlock(&event->mmap_mutex);
 
+	if (ret)
+		return ret;
+
 	/*
 	 * Since pinned accounting is per vm we cannot allow fork() to copy our
 	 * vma.
author maintainer
#187 lore raw

PATCH 185/523 perf/core: Prevent VMA split of buffer mappings

In reply to Greg Kroah-Hartman

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

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

From: Thomas Gleixner <[email protected]>

commit b024d7b56c77191cde544f838debb7f8451cd0d6 upstream.

The perf mmap code is careful about mmap()'ing the user page with the ringbuffer and additionally the auxiliary buffer, when the event supports it. Once the first mapping is established, subsequent mapping have to use the same offset and the same size in both cases. The reference counting for the ringbuffer and the auxiliary buffer depends on this being correct.

Though perf does not prevent that a related mapping is split via mmap(2), munmap(2) or mremap(2). A split of a VMA results in perf_mmap_open() calls, which take reference counts, but then the subsequent perf_mmap_close() calls are not longer fulfilling the offset and size checks. This leads to reference count leaks.

As perf already has the requirement for subsequent mappings to match the initial mapping, the obvious consequence is that VMA splits, caused by resizing of a mapping or partial unmapping, have to be prevented.

Implement the vm_operations_struct::may_split() callback and return unconditionally -EINVAL.

That ensures that the mapping offsets and sizes cannot be changed after the fact. Remapping to a different fixed address with the same size is still possible as it takes the references for the new mapping and drops those of the old mapping.

---
 kernel/events/core.c |   10 ++++++++++
 1 file changed, 10 insertions(+)
kernel/events/core.c +10 -0
@@ -6194,11 +6194,21 @@ out_put:
 	ring_buffer_put(rb); /* could be last */
 }
 
+static int perf_mmap_may_split(struct vm_area_struct *vma, unsigned long addr)
+{
+	/*
+	 * Forbid splitting perf mappings to prevent refcount leaks due to
+	 * the resulting non-matching offsets and sizes. See open()/close().
+	 */
+	return -EINVAL;
+}
+
 static const struct vm_operations_struct perf_mmap_vmops = {
 	.open		= perf_mmap_open,
 	.close		= perf_mmap_close, /* non mergeable */
 	.fault		= perf_mmap_fault,
 	.page_mkwrite	= perf_mmap_fault,
+	.split		= perf_mmap_may_split,
 };
 
 static int perf_mmap(struct file *file, struct vm_area_struct *vma)
author maintainer
#188 lore raw

PATCH 186/523 net/packet: fix a race in packet_set_ring() and packet_notifier()

In reply to Greg Kroah-Hartman

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

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

From: Quang Le <[email protected]>

commit 01d3c8417b9c1b884a8a981a3b886da556512f36 upstream.

When packet_set_ring() releases po->bind_lock, another thread can run packet_notifier() and process an NETDEV_UP event.

This race and the fix are both similar to that of commit 15fe076edea7 ("net/packet: fix a race in packet_bind() and packet_notifier()").

There too the packet_notifier NETDEV_UP event managed to run while a po->bind_lock critical section had to be temporarily released. And the fix was similarly to temporarily set po->num to zero to keep the socket unhooked until the lock is retaken.

The po->bind_lock in packet_set_ring and packet_notifier precede the introduction of git history.

---
 net/packet/af_packet.c |   12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)
net/packet/af_packet.c +6 -6
@@ -4514,10 +4514,10 @@ static int packet_set_ring(struct sock *
 	spin_lock(&po->bind_lock);
 	was_running = po->running;
 	num = po->num;
-	if (was_running) {
-		WRITE_ONCE(po->num, 0);
+	WRITE_ONCE(po->num, 0);
+	if (was_running)
 		__unregister_prot_hook(sk, false);
-	}
+
 	spin_unlock(&po->bind_lock);
 
 	synchronize_net();
@@ -4549,10 +4549,10 @@ static int packet_set_ring(struct sock *
 	mutex_unlock(&po->pg_vec_lock);
 
 	spin_lock(&po->bind_lock);
-	if (was_running) {
-		WRITE_ONCE(po->num, num);
+	WRITE_ONCE(po->num, num);
+	if (was_running)
 		register_prot_hook(sk);
-	}
+
 	spin_unlock(&po->bind_lock);
 	if (pg_vec && (po->tp_version > TPACKET_V2)) {
 		/* Because we don't support block-based V3 on tx-ring */
author maintainer
#189 lore raw

PATCH 187/523 vsock: Do not allow binding to VMADDR_PORT_ANY

In reply to Greg Kroah-Hartman

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

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

From: Budimir Markovic <[email protected]>

commit aba0c94f61ec05315fa7815d21aefa4c87f6a9f4 upstream.

It is possible for a vsock to autobind to VMADDR_PORT_ANY. This can cause a use-after-free when a connection is made to the bound socket. The socket returned by accept() also has port VMADDR_PORT_ANY but is not on the list of unbound sockets. Binding it will result in an extra refcount decrement similar to the one fixed in fcdd2242c023 (vsock: Keep the binding until socket destruction).

Modify the check in __vsock_bind_connectible() to also prevent binding to VMADDR_PORT_ANY.

---
 net/vmw_vsock/af_vsock.c |    3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)
net/vmw_vsock/af_vsock.c +2 -1
@@ -674,7 +674,8 @@ static int __vsock_bind_stream(struct vs
 		unsigned int i;
 
 		for (i = 0; i < MAX_PORT_RETRIES; i++) {
-			if (port <= LAST_RESERVED_PORT)
+			if (port == VMADDR_PORT_ANY ||
+			    port <= LAST_RESERVED_PORT)
 				port = LAST_RESERVED_PORT + 1;
 
 			new_addr.svm_port = port++;
author maintainer
#190 lore raw

PATCH 188/523 USB: serial: option: add Foxconn T99W709

In reply to Greg Kroah-Hartman

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

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

From: Slark Xiao <[email protected]>

commit ad1244e1ce18f8c1a5ebad8074bfcf10eacb0311 upstream.

T99W709 is designed based on MTK T300(5G redcap) chip. There are 7 serial ports to be enumerated: AP_LOG, GNSS, AP_META, AT, MD_META, NPT, DBG. RSVD(5) for ADB port.

test evidence as below:

T:  Bus=01 Lev=02 Prnt=02 Port=00 Cnt=01 Dev#=  7 Spd=480 MxCh= 0
D:  Ver= 2.10 Cls=ef(misc ) Sub=02 Prot=01 MxPS=64 #Cfgs=  1
P:  Vendor=0489 ProdID=e15f Rev=00.01
S:  Manufacturer=MediaTek Inc.
S:  Product=USB DATA CARD
S:  SerialNumber=355511220000399
C:  #Ifs=10 Cfg#= 1 Atr=a0 MxPwr=500mA
I:  If#=0x0 Alt= 0 #EPs= 1 Cls=02(commc) Sub=0e Prot=00 Driver=cdc_mbim
I:  If#=0x1 Alt= 1 #EPs= 2 Cls=0a(data ) Sub=00 Prot=02 Driver=cdc_mbim
I:  If#=0x2 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
I:  If#=0x3 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
I:  If#=0x4 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
I:  If#=0x5 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=42 Prot=01 Driver=usbfs
I:  If#=0x6 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
I:  If#=0x7 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
I:  If#=0x8 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
I:  If#=0x9 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
---
 drivers/usb/serial/option.c |    2 ++
 1 file changed, 2 insertions(+)
drivers/usb/serial/option.c +2 -0
@@ -2346,6 +2346,8 @@ static const struct usb_device_id option
 	  .driver_info = RSVD(3) },
 	{ USB_DEVICE_INTERFACE_CLASS(0x0489, 0xe145, 0xff),			/* Foxconn T99W651 RNDIS */
 	  .driver_info = RSVD(5) | RSVD(6) },
+	{ USB_DEVICE_INTERFACE_CLASS(0x0489, 0xe15f, 0xff),                     /* Foxconn T99W709 */
+	  .driver_info = RSVD(5) },
 	{ USB_DEVICE_INTERFACE_CLASS(0x0489, 0xe167, 0xff),                     /* Foxconn T99W640 MBIM */
 	  .driver_info = RSVD(3) },
 	{ USB_DEVICE(0x1508, 0x1001),						/* Fibocom NL668 (IOT version) */
author maintainer
#191 lore raw

PATCH 189/523 MIPS: mm: tlb-r4k: Uniquify TLB entries on init

In reply to Greg Kroah-Hartman

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

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

From: Jiaxun Yang <[email protected]>

commit 35ad7e181541aa5757f9f316768d3e64403ec843 upstream.

Hardware or bootloader will initialize TLB entries to any value, which may collide with kernel's UNIQUE_ENTRYHI value. On MIPS microAptiv/M5150 family of cores this will trigger machine check exception and cause boot failure. On M5150 simulation this could happen 7 times out of 1000 boots.

Replace local_flush_tlb_all() with r4k_tlb_uniquify() which probes each TLB ENTRIHI unique value for collisions before it's written, and in case of collision try a different ASID.

---
 arch/mips/mm/tlb-r4k.c |   56 ++++++++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 55 insertions(+), 1 deletion(-)
arch/mips/mm/tlb-r4k.c +55 -1
@@ -498,6 +498,60 @@ static int __init set_ntlb(char *str)
 
 __setup("ntlb=", set_ntlb);
 
+/* Initialise all TLB entries with unique values */
+static void r4k_tlb_uniquify(void)
+{
+	int entry = num_wired_entries();
+
+	htw_stop();
+	write_c0_entrylo0(0);
+	write_c0_entrylo1(0);
+
+	while (entry < current_cpu_data.tlbsize) {
+		unsigned long asid_mask = cpu_asid_mask(&current_cpu_data);
+		unsigned long asid = 0;
+		int idx;
+
+		/* Skip wired MMID to make ginvt_mmid work */
+		if (cpu_has_mmid)
+			asid = MMID_KERNEL_WIRED + 1;
+
+		/* Check for match before using UNIQUE_ENTRYHI */
+		do {
+			if (cpu_has_mmid) {
+				write_c0_memorymapid(asid);
+				write_c0_entryhi(UNIQUE_ENTRYHI(entry));
+			} else {
+				write_c0_entryhi(UNIQUE_ENTRYHI(entry) | asid);
+			}
+			mtc0_tlbw_hazard();
+			tlb_probe();
+			tlb_probe_hazard();
+			idx = read_c0_index();
+			/* No match or match is on current entry */
+			if (idx < 0 || idx == entry)
+				break;
+			/*
+			 * If we hit a match, we need to try again with
+			 * a different ASID.
+			 */
+			asid++;
+		} while (asid < asid_mask);
+
+		if (idx >= 0 && idx != entry)
+			panic("Unable to uniquify TLB entry %d", idx);
+
+		write_c0_index(entry);
+		mtc0_tlbw_hazard();
+		tlb_write_indexed();
+		entry++;
+	}
+
+	tlbw_use_hazard();
+	htw_start();
+	flush_micro_tlb();
+}
+
 /*
  * Configure TLB (for init or after a CPU has been powered off).
  */
@@ -537,7 +591,7 @@ static void r4k_tlb_configure(void)
 	temp_tlb_entry = current_cpu_data.tlbsize - 1;
 
 	/* From this point on the ARC firmware is dead.	 */
-	local_flush_tlb_all();
+	r4k_tlb_uniquify();
 
 	/* Did I tell you that ARC SUCKS?  */
 }
author maintainer
#192 lore raw

PATCH 190/523 mm/hmm: move pmd_to_hmm_pfn_flags() to the respective #ifdeffery

In reply to Greg Kroah-Hartman

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

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

From: Andy Shevchenko <[email protected]>

commit 188cb385bbf04d486df3e52f28c47b3961f5f0c0 upstream.

When pmd_to_hmm_pfn_flags() is unused, it prevents kernel builds with clang, make W=1 and CONFIG_TRANSPARENT_HUGEPAGE=n:

mm/hmm.c:186:29: warning: unused function 'pmd_to_hmm_pfn_flags' [-Wunused-function]

Fix this by moving the function to the respective existing ifdeffery for its the only user.

See also:

6863f5643dd7 ("kbuild: allow Clang to find unused static inline functions for W=1 build")

Fixes 992de9a8b751 ("mm/hmm: allow to mirror vma of a file on a DAX backed filesystem")
Cc Andriy Shevchenko <[email protected]>
Cc Bill Wendling <[email protected]>
Cc Jerome Glisse <[email protected]>
Cc Justin Stitt <[email protected]>
Cc Nathan Chancellor <[email protected]>
---
 mm/hmm.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
mm/hmm.c +1 -1
@@ -171,6 +171,7 @@ static inline unsigned long hmm_pfn_flag
 	return order << HMM_PFN_ORDER_SHIFT;
 }
 
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
 static inline unsigned long pmd_to_hmm_pfn_flags(struct hmm_range *range,
 						 pmd_t pmd)
 {
@@ -181,7 +182,6 @@ static inline unsigned long pmd_to_hmm_p
 	       hmm_pfn_flags_order(PMD_SHIFT - PAGE_SHIFT);
 }
 
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
 static int hmm_vma_handle_pmd(struct mm_walk *walk, unsigned long addr,
 			      unsigned long end, unsigned long hmm_pfns[],
 			      pmd_t pmd)
author maintainer
#193 lore raw

PATCH 191/523 usb: gadget : fix use-after-free in composite_dev_cleanup()

In reply to Greg Kroah-Hartman

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

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

From: Tao Xue <[email protected]>

commit 151c0aa896c47a4459e07fee7d4843f44c1bb18e upstream.

1. In func configfs_composite_bind() -> composite_os_desc_req_prepare():
if kmalloc fails, the pointer cdev->os_desc_req will be freed but not set to NULL. Then it will return a failure to the upper-level function.
2. in func configfs_composite_bind() -> composite_dev_cleanup():
it will checks whether cdev->os_desc_req is NULL. If it is not NULL, it will attempt to use it.This will lead to a use-after-free issue.

BUG: KASAN: use-after-free in composite_dev_cleanup+0xf4/0x2c0
Read of size 8 at addr 0000004827837a00 by task init/1

CPU: 10 PID: 1 Comm: init Tainted: G           O      5.10.97-oh #1
 kasan_report+0x188/0x1cc
 __asan_load8+0xb4/0xbc
 composite_dev_cleanup+0xf4/0x2c0
 configfs_composite_bind+0x210/0x7ac
 udc_bind_to_driver+0xb4/0x1ec
 usb_gadget_probe_driver+0xec/0x21c
 gadget_dev_desc_UDC_store+0x264/0x27c
Fixes 37a3a533429e ("usb: gadget: OS Feature Descriptors support")
Cc stable <[email protected]>
---
 drivers/usb/gadget/composite.c |    5 +++++
 1 file changed, 5 insertions(+)
drivers/usb/gadget/composite.c +5 -0
@@ -2241,6 +2241,11 @@ int composite_os_desc_req_prepare(struct
 	if (!cdev->os_desc_req->buf) {
 		ret = -ENOMEM;
 		usb_ep_free_request(ep0, cdev->os_desc_req);
+		/*
+		 * Set os_desc_req to NULL so that composite_dev_cleanup()
+		 * will not try to free it again.
+		 */
+		cdev->os_desc_req = NULL;
 		goto end;
 	}
 	cdev->os_desc_req->context = cdev;
author maintainer
#194 lore raw

PATCH 192/523 io_uring: dont use int for ABI

In reply to Greg Kroah-Hartman

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

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

From: Pavel Begunkov <[email protected]>

commit cf73d9970ea4f8cace5d8f02d2565a2723003112 upstream.

__kernel_rwf_t is defined as int, the actual size of which is implementation defined. It won't go well if some compiler / archs ever defines it as i64, so replace it with __u32, hoping that there is no one using i16 for it.

---
 include/uapi/linux/io_uring.h |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
include/uapi/linux/io_uring.h +1 -1
@@ -29,7 +29,7 @@ struct io_uring_sqe {
 	};
 	__u32	len;		/* buffer size or number of iovecs */
 	union {
-		__kernel_rwf_t	rw_flags;
+		__u32		rw_flags;
 		__u32		fsync_flags;
 		__u16		poll_events;	/* compatibility */
 		__u32		poll32_events;	/* word-reversed for BE */
author maintainer
#195 lore raw

PATCH 193/523 ALSA: usb-audio: Validate UAC3 power domain descriptors, too

In reply to Greg Kroah-Hartman

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

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

From: Takashi Iwai <[email protected]>

commit d832ccbc301fbd9e5a1d691bdcf461cdb514595f upstream.

UAC3 power domain descriptors need to be verified with its variable bLength for avoiding the unexpected OOB accesses by malicious firmware, too.

Fixes 9a2fe9b801f5 ("ALSA: usb: initial USB Audio Device Class 3.0 support")
Reported-and-tested-by Youngjun Lee <[email protected]>
---
 sound/usb/validate.c |   12 ++++++++++++
 1 file changed, 12 insertions(+)
sound/usb/validate.c +12 -0
@@ -221,6 +221,17 @@ static bool validate_uac3_feature_unit(c
 	return d->bLength >= sizeof(*d) + 4 + 2;
 }
 
+static bool validate_uac3_power_domain_unit(const void *p,
+					    const struct usb_desc_validator *v)
+{
+	const struct uac3_power_domain_descriptor *d = p;
+
+	if (d->bLength < sizeof(*d))
+		return false;
+	/* baEntities[] + wPDomainDescrStr */
+	return d->bLength >= sizeof(*d) + d->bNrEntities + 2;
+}
+
 static bool validate_midi_out_jack(const void *p,
 				   const struct usb_desc_validator *v)
 {
@@ -285,6 +296,7 @@ static const struct usb_desc_validator a
 	      struct uac3_clock_multiplier_descriptor),
 	/* UAC_VERSION_3, UAC3_SAMPLE_RATE_CONVERTER: not implemented yet */
 	/* UAC_VERSION_3, UAC3_CONNECTORS: not implemented yet */
+	FUNC(UAC_VERSION_3, UAC3_POWER_DOMAIN, validate_uac3_power_domain_unit),
 	{ } /* terminator */
 };
 
author maintainer
#196 lore raw

PATCH 194/523 ALSA: usb-audio: Validate UAC3 cluster segment descriptors

In reply to Greg Kroah-Hartman

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

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

From: Takashi Iwai <[email protected]>

commit ecfd41166b72b67d3bdeb88d224ff445f6163869 upstream.

UAC3 class segment descriptors need to be verified whether their sizes match with the declared lengths and whether they fit with the allocated buffer sizes, too. Otherwise malicious firmware may lead to the unexpected OOB accesses.

Fixes 11785ef53228 ("ALSA: usb-audio: Initial Power Domain support")
Reported-and-tested-by Youngjun Lee <[email protected]>
---
 sound/usb/stream.c |   25 ++++++++++++++++++++++---
 1 file changed, 22 insertions(+), 3 deletions(-)
sound/usb/stream.c +22 -3
@@ -342,20 +342,28 @@ snd_pcm_chmap_elem *convert_chmap_v3(str
 
 	len = le16_to_cpu(cluster->wLength);
 	c = 0;
-	p += sizeof(struct uac3_cluster_header_descriptor);
+	p += sizeof(*cluster);
+	len -= sizeof(*cluster);
 
-	while (((p - (void *)cluster) < len) && (c < channels)) {
+	while (len > 0 && (c < channels)) {
 		struct uac3_cluster_segment_descriptor *cs_desc = p;
 		u16 cs_len;
 		u8 cs_type;
 
+		if (len < sizeof(*p))
+			break;
 		cs_len = le16_to_cpu(cs_desc->wLength);
+		if (len < cs_len)
+			break;
 		cs_type = cs_desc->bSegmentType;
 
 		if (cs_type == UAC3_CHANNEL_INFORMATION) {
 			struct uac3_cluster_information_segment_descriptor *is = p;
 			unsigned char map;
 
+			if (cs_len < sizeof(*is))
+				break;
+
 			/*
 			 * TODO: this conversion is not complete, update it
 			 * after adding UAC3 values to asound.h
@@ -457,6 +465,7 @@ snd_pcm_chmap_elem *convert_chmap_v3(str
 			chmap->map[c++] = map;
 		}
 		p += cs_len;
+		len -= cs_len;
 	}
 
 	if (channels < c)
@@ -877,7 +886,7 @@ snd_usb_get_audioformat_uac3(struct snd_
 	u64 badd_formats = 0;
 	unsigned int num_channels;
 	struct audioformat *fp;
-	u16 cluster_id, wLength;
+	u16 cluster_id, wLength, cluster_wLength;
 	int clock = 0;
 	int err;
 
@@ -1004,6 +1013,16 @@ snd_usb_get_audioformat_uac3(struct snd_
 			iface_no, altno);
 		kfree(cluster);
 		return ERR_PTR(-EIO);
+	}
+
+	cluster_wLength = le16_to_cpu(cluster->wLength);
+	if (cluster_wLength < sizeof(*cluster) ||
+	    cluster_wLength > wLength) {
+		dev_err(&dev->dev,
+			"%u:%d : invalid Cluster Descriptor size\n",
+			iface_no, altno);
+		kfree(cluster);
+		return ERR_PTR(-EIO);
 	}
 
 	num_channels = cluster->bNrChannels;
author maintainer
#197 lore raw

PATCH 195/523 netlink: avoid infinite retry looping in netlink_unicast()

In reply to Greg Kroah-Hartman

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

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

From: Fedor Pchelkin <[email protected]>

commit 759dfc7d04bab1b0b86113f1164dc1fec192b859 upstream.

netlink_attachskb() checks for the socket's read memory allocation constraints. Firstly, it has:

rmem < READ_ONCE(sk->sk_rcvbuf)

to check if the just increased rmem value fits into the socket's receive buffer. If not, it proceeds and tries to wait for the memory under:

rmem + skb->truesize > READ_ONCE(sk->sk_rcvbuf)

The checks don't cover the case when skb->truesize + sk->sk_rmem_alloc is equal to sk->sk_rcvbuf. Thus the function neither successfully accepts these conditions, nor manages to reschedule the task - and is called in retry loop for indefinite time which is caught as:

  rcu: INFO: rcu_sched self-detected stall on CPU
  rcu:     0-....: (25999 ticks this GP) idle=ef2/1/0x4000000000000000 softirq=262269/262269 fqs=6212
  (t=26000 jiffies g=230833 q=259957)
  NMI backtrace for cpu 0
  CPU: 0 PID: 22 Comm: kauditd Not tainted 5.10.240 #68
  Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.17.0-4.fc42 04/01/2014
  Call Trace:
  <IRQ>
  dump_stack lib/dump_stack.c:120
  nmi_cpu_backtrace.cold lib/nmi_backtrace.c:105
  nmi_trigger_cpumask_backtrace lib/nmi_backtrace.c:62
  rcu_dump_cpu_stacks kernel/rcu/tree_stall.h:335
  rcu_sched_clock_irq.cold kernel/rcu/tree.c:2590
  update_process_times kernel/time/timer.c:1953
  tick_sched_handle kernel/time/tick-sched.c:227
  tick_sched_timer kernel/time/tick-sched.c:1399
  __hrtimer_run_queues kernel/time/hrtimer.c:1652
  hrtimer_interrupt kernel/time/hrtimer.c:1717
  __sysvec_apic_timer_interrupt arch/x86/kernel/apic/apic.c:1113
  asm_call_irq_on_stack arch/x86/entry/entry_64.S:808
  </IRQ>

  netlink_attachskb net/netlink/af_netlink.c:1234
  netlink_unicast net/netlink/af_netlink.c:1349
  kauditd_send_queue kernel/audit.c:776
  kauditd_thread kernel/audit.c:897
  kthread kernel/kthread.c:328
  ret_from_fork arch/x86/entry/entry_64.S:304

Restore the original behavior of the check which commit in Fixes accidentally missed when restructuring the code.

Found by Linux Verification Center (linuxtesting.org).

---
 net/netlink/af_netlink.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
net/netlink/af_netlink.c +1 -1
@@ -1213,7 +1213,7 @@ int netlink_attachskb(struct sock *sk, s
 	nlk = nlk_sk(sk);
 	rmem = atomic_add_return(skb->truesize, &sk->sk_rmem_alloc);
 
-	if ((rmem == skb->truesize || rmem < READ_ONCE(sk->sk_rcvbuf)) &&
+	if ((rmem == skb->truesize || rmem <= READ_ONCE(sk->sk_rcvbuf)) &&
 	    !test_bit(NETLINK_S_CONGESTED, &nlk->state)) {
 		netlink_skb_set_owner_r(skb, sk);
 		return 0;
author maintainer
#198 lore raw

PATCH 196/523 net: gianfar: fix device leak when querying time stamp info

In reply to Greg Kroah-Hartman

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

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

From: Johan Hovold <[email protected]>

commit da717540acd34e5056e3fa35791d50f6b3303f55 upstream.

Make sure to drop the reference to the ptp device taken by of_find_device_by_node() when querying the time stamping capabilities.

Note that holding a reference to the ptp device does not prevent its driver data from going away.

Fixes 7349a74ea75c ("net: ethernet: gianfar_ethtool: get phc index through drvdata")
Cc Yangbo Lu <[email protected]>
---
 drivers/net/ethernet/freescale/gianfar_ethtool.c |    4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)
drivers/net/ethernet/freescale/gianfar_ethtool.c +3 -1
@@ -1457,8 +1457,10 @@ static int gfar_get_ts_info(struct net_d
 	if (ptp_node) {
 		ptp_dev = of_find_device_by_node(ptp_node);
 		of_node_put(ptp_node);
-		if (ptp_dev)
+		if (ptp_dev) {
 			ptp = platform_get_drvdata(ptp_dev);
+			put_device(&ptp_dev->dev);
+		}
 	}
 
 	if (ptp)
author maintainer
#199 lore raw

PATCH 197/523 net: dpaa: fix device leak when querying time stamp info

In reply to Greg Kroah-Hartman

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

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

From: Johan Hovold <[email protected]>

commit 3fa840230f534385b34a4f39c8dd313fbe723f05 upstream.

Make sure to drop the reference to the ptp device taken by of_find_device_by_node() when querying the time stamping capabilities.

Note that holding a reference to the ptp device does not prevent its driver data from going away.

Fixes 17ae0b0ee9db ("dpaa_eth: add the get_ts_info interface for ethtool")
Cc Yangbo Lu <[email protected]>
---
 drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c |    4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)
drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c +3 -1
@@ -499,8 +499,10 @@ static int dpaa_get_ts_info(struct net_d
 		of_node_put(ptp_node);
 	}
 
-	if (ptp_dev)
+	if (ptp_dev) {
 		ptp = platform_get_drvdata(ptp_dev);
+		put_device(&ptp_dev->dev);
+	}
 
 	if (ptp)
 		info->phc_index = ptp->phc_index;
author maintainer
#200 lore raw

PATCH 198/523 nfsd: handle get_client_locked() failure in nfsd4_setclientid_confirm()

In reply to Greg Kroah-Hartman

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

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

From: Jeff Layton <[email protected]>

commit 908e4ead7f757504d8b345452730636e298cbf68 upstream.

Lei Lu recently reported that nfsd4_setclientid_confirm() did not check the return value from get_client_locked(). a SETCLIENTID_CONFIRM could race with a confirmed client expiring and fail to get a reference. That could later lead to a UAF.

Fix this by getting a reference early in the case where there is an extant confirmed client. If that fails then treat it as if there were no confirmed client found at all.

In the case where the unconfirmed client is expiring, just fail and return the result from get_client_locked().

---
 fs/nfsd/nfs4state.c |   20 +++++++++++++++-----
 1 file changed, 15 insertions(+), 5 deletions(-)
fs/nfsd/nfs4state.c +15 -5
@@ -4284,10 +4284,16 @@ nfsd4_setclientid_confirm(struct svc_rqs
 	}
 	status = nfs_ok;
 	if (conf) {
-		old = unconf;
-		unhash_client_locked(old);
-		nfsd4_change_callback(conf, &unconf->cl_cb_conn);
-	} else {
+		if (get_client_locked(conf) == nfs_ok) {
+			old = unconf;
+			unhash_client_locked(old);
+			nfsd4_change_callback(conf, &unconf->cl_cb_conn);
+		} else {
+			conf = NULL;
+		}
+	}
+
+	if (!conf) {
 		old = find_confirmed_client_by_name(&unconf->cl_name, nn);
 		if (old) {
 			status = nfserr_clid_inuse;
@@ -4304,10 +4310,14 @@ nfsd4_setclientid_confirm(struct svc_rqs
 			}
 			trace_nfsd_clid_replaced(&old->cl_clientid);
 		}
+		status = get_client_locked(unconf);
+		if (status != nfs_ok) {
+			old = NULL;
+			goto out;
+		}
 		move_to_confirmed(unconf);
 		conf = unconf;
 	}
-	get_client_locked(conf);
 	spin_unlock(&nn->client_lock);
 	if (conf == unconf)
 		fsnotify_dentry(conf->cl_nfsd_info_dentry, FS_MODIFY);
author maintainer
#201 lore raw

PATCH 199/523 NFSD: detect mismatch of file handle and delegation stateid in OPEN op

In reply to Greg Kroah-Hartman

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

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

From: Dai Ngo <[email protected]>

commit 9c65001c57164033ad08b654c8b5ae35512ddf4a upstream.

When the client sends an OPEN with claim type CLAIM_DELEG_CUR_FH or CLAIM_DELEGATION_CUR, the delegation stateid and the file handle must belong to the same file, otherwise return NFS4ERR_INVAL.

Note that RFC8881, section 8.2.4, mandates the server to return NFS4ERR_BAD_STATEID if the selected table entry does not match the current filehandle. However returning NFS4ERR_BAD_STATEID in the OPEN causes the client to retry the operation and therefor get the client into a loop. To avoid this situation we return NFS4ERR_INVAL instead.

Fixes c44c5eeb2c02 ("[PATCH] nfsd4: add open state code for CLAIM_DELEGATE_CUR")
---
 fs/nfsd/nfs4state.c |   14 ++++++++++++++
 1 file changed, 14 insertions(+)
fs/nfsd/nfs4state.c +14 -0
@@ -5732,6 +5732,20 @@ nfsd4_process_open2(struct svc_rqst *rqs
 		status = nfs4_check_deleg(cl, open, &dp);
 		if (status)
 			goto out;
+		if (dp && nfsd4_is_deleg_cur(open) &&
+				(dp->dl_stid.sc_file != fp)) {
+			/*
+			 * RFC8881 section 8.2.4 mandates the server to return
+			 * NFS4ERR_BAD_STATEID if the selected table entry does
+			 * not match the current filehandle. However returning
+			 * NFS4ERR_BAD_STATEID in the OPEN can cause the client
+			 * to repeatedly retry the operation with the same
+			 * stateid, since the stateid itself is valid. To avoid
+			 * this situation NFSD returns NFS4ERR_INVAL instead.
+			 */
+			status = nfserr_inval;
+			goto out;
+		}
 		stp = nfsd4_find_and_lock_existing_open(fp, open);
 	} else {
 		open->op_file = NULL;
author maintainer
#202 lore raw

PATCH 200/523 sunvdc: Balance device refcount in vdc_port_mpgroup_check

In reply to Greg Kroah-Hartman

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

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

From: Ma Ke <[email protected]>

commit 63ce53724637e2e7ba51fe3a4f78351715049905 upstream.

Using device_find_child() to locate a probed virtual-device-port node causes a device refcount imbalance, as device_find_child() internally calls get_device() to increment the device’s reference count before returning its pointer. vdc_port_mpgroup_check() directly returns true upon finding a matching device without releasing the reference via put_device(). We should call put_device() to decrement refcount.

As comment of device_find_child() says, 'NOTE: you will need to drop the reference with put_device() after use'.

Found by code review.

Fixes 3ee70591d6c4 ("sunvdc: prevent sunvdc panic when mpgroup disk added to guest domain")
---
 drivers/block/sunvdc.c |    4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)
drivers/block/sunvdc.c +3 -1
@@ -968,8 +968,10 @@ static bool vdc_port_mpgroup_check(struc
 	dev = device_find_child(vdev->dev.parent, &port_data,
 				vdc_device_probed);
 
-	if (dev)
+	if (dev) {
+		put_device(dev);
 		return true;
+	}
 
 	return false;
 }
author maintainer
#203 lore raw

PATCH 201/523 fs: Prevent file descriptor table allocations exceeding INT_MAX

In reply to Greg Kroah-Hartman

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

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

From: Sasha Levin <[email protected]>

commit 04a2c4b4511d186b0fce685da21085a5d4acd370 upstream.

When sysctl_nr_open is set to a very high value (for example, 1073741816 as set by systemd), processes attempting to use file descriptors near the limit can trigger massive memory allocation attempts that exceed INT_MAX, resulting in a WARNING in mm/slub.c:

  WARNING: CPU: 0 PID: 44 at mm/slub.c:5027 __kvmalloc_node_noprof+0x21a/0x288

This happens because kvmalloc_array() and kvmalloc() check if the requested size exceeds INT_MAX and emit a warning when the allocation is not flagged with __GFP_NOWARN.

Specifically, when nr_open is set to 1073741816 (0x3ffffff8) and a process calls dup2(oldfd, 1073741880), the kernel attempts to allocate:
- File descriptor array: 1073741880 * 8 bytes = 8,589,935,040 bytes
- Multiple bitmaps: ~400MB
- Total allocation size: > 8GB (exceeding INT_MAX = 2,147,483,647)

Reproducer:
1. Set /proc/sys/fs/nr_open to 1073741816:

   # echo 1073741816 > /proc/sys/fs/nr_open

2. Run a program that uses a high file descriptor:
#include <unistd.h>
#include <sys/resource.h>

   int main() {
       struct rlimit rlim = {1073741824, 1073741824};
       setrlimit(RLIMIT_NOFILE, &rlim);
       dup2(2, 1073741880);  // Triggers the warning
       return 0;
   }

3. Observe WARNING in dmesg at mm/slub.c:5027

systemd commit a8b627a introduced automatic bumping of fs.nr_open to the maximum possible value. The rationale was that systems with memory control groups (memcg) no longer need separate file descriptor limits since memory is properly accounted. However, this change overlooked that:

1. The kernel's allocation functions still enforce INT_MAX as a maximum size regardless of memcg accounting
2. Programs and tests that legitimately test file descriptor limits can inadvertently trigger massive allocations
3. The resulting allocations (>8GB) are impractical and will always fail

systemd's algorithm starts with INT_MAX and keeps halving the value until the kernel accepts it. On most systems, this results in nr_open being set to 1073741816 (0x3ffffff8), which is just under 1GB of file descriptors.

While processes rarely use file descriptors near this limit in normal operation, certain selftests (like tools/testing/selftests/core/unshare_test.c) and programs that test file descriptor limits can trigger this issue.

Fix this by adding a check in alloc_fdtable() to ensure the requested allocation size does not exceed INT_MAX. This causes the operation to fail with -EMFILE instead of triggering a kernel warning and avoids the impractical >8GB memory allocation request.

Fixes 9cfe015aa424 ("get rid of NR_OPEN and introduce a sysctl_nr_open")
---
 fs/file.c |   15 +++++++++++++++
 1 file changed, 15 insertions(+)
fs/file.c +15 -0
@@ -126,6 +126,21 @@ static struct fdtable * alloc_fdtable(un
 	if (unlikely(nr > sysctl_nr_open))
 		nr = ((sysctl_nr_open - 1) | (BITS_PER_LONG - 1)) + 1;
 
+	/*
+	 * Check if the allocation size would exceed INT_MAX. kvmalloc_array()
+	 * and kvmalloc() will warn if the allocation size is greater than
+	 * INT_MAX, as filp_cachep objects are not __GFP_NOWARN.
+	 *
+	 * This can happen when sysctl_nr_open is set to a very high value and
+	 * a process tries to use a file descriptor near that limit. For example,
+	 * if sysctl_nr_open is set to 1073741816 (0x3ffffff8) - which is what
+	 * systemd typically sets it to - then trying to use a file descriptor
+	 * close to that value will require allocating a file descriptor table
+	 * that exceeds 8GB in size.
+	 */
+	if (unlikely(nr > INT_MAX / sizeof(struct file *)))
+		return ERR_PTR(-EMFILE);
+
 	fdt = kmalloc(sizeof(struct fdtable), GFP_KERNEL_ACCOUNT);
 	if (!fdt)
 		goto out;
author maintainer
#204 lore raw

PATCH 202/523 Documentation: ACPI: Fix parent device references

In reply to Greg Kroah-Hartman

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

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

From: Andy Shevchenko <[email protected]>

commit e65cb011349e653ded541dddd6469c2ca813edcf upstream.

The _CRS resources in many cases want to have ResourceSource field to be a type of ACPI String. This means that to compile properly we need to enclosure the name path into double quotes. This will in practice defer the interpretation to a run-time stage, However, this may be interpreted differently on different OSes and ACPI interpreter implementations. In particular ACPICA might not correctly recognize the leading '^' (caret) character and will not resolve the relative name path properly. On top of that, this piece may be used in SSDTs which are loaded after the DSDT and on itself may also not resolve relative name paths outside of their own scopes. With this all said, fix documentation to use fully-qualified name paths always to avoid any misinterpretations, which is proven to work.

---
 Documentation/firmware-guide/acpi/i2c-muxes.rst |    8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)
Documentation/firmware-guide/acpi/i2c-muxes.rst +4 -4
@@ -14,7 +14,7 @@ Consider this topology::
     |      |   | 0x70 |--CH01--> i2c client B (0x50)
     +------+   +------+
 
-which corresponds to the following ASL::
+which corresponds to the following ASL (in the scope of \_SB)::
 
     Device (SMB1)
     {
@@ -24,7 +24,7 @@ which corresponds to the following ASL::
             Name (_HID, ...)
             Name (_CRS, ResourceTemplate () {
                 I2cSerialBus (0x70, ControllerInitiated, I2C_SPEED,
-                            AddressingMode7Bit, "^SMB1", 0x00,
+                            AddressingMode7Bit, "\\_SB.SMB1", 0x00,
                             ResourceConsumer,,)
             }
 
@@ -37,7 +37,7 @@ which corresponds to the following ASL::
                     Name (_HID, ...)
                     Name (_CRS, ResourceTemplate () {
                         I2cSerialBus (0x50, ControllerInitiated, I2C_SPEED,
-                                    AddressingMode7Bit, "^CH00", 0x00,
+                                    AddressingMode7Bit, "\\_SB.SMB1.CH00", 0x00,
                                     ResourceConsumer,,)
                     }
                 }
@@ -52,7 +52,7 @@ which corresponds to the following ASL::
                     Name (_HID, ...)
                     Name (_CRS, ResourceTemplate () {
                         I2cSerialBus (0x50, ControllerInitiated, I2C_SPEED,
-                                    AddressingMode7Bit, "^CH01", 0x00,
+                                    AddressingMode7Bit, "\\_SB.SMB1.CH01", 0x00,
                                     ResourceConsumer,,)
                     }
                 }
author maintainer
#205 lore raw

PATCH 203/523 ACPI: processor: perflib: Fix initial _PPC limit application

In reply to Greg Kroah-Hartman

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

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

From: Jiayi Li <[email protected]>

commit d33bd88ac0ebb49e7f7c8f29a8c7ee9eae85d765 upstream.

If the BIOS sets a _PPC frequency limit upfront, it will fail to take effect due to a call ordering issue. Namely, freq_qos_update_request() is called before freq_qos_add_request() for the given request causing the constraint update to be ignored. The call sequence in question is as follows:

cpufreq_policy_online()
acpi_cpufreq_cpu_init()
acpi_processor_register_performance()
acpi_processor_get_performance_info()
acpi_processor_get_platform_limit()
freq_qos_update_request(&perflib_req) <- inactive QoS request
blocking_notifier_call_chain(&cpufreq_policy_notifier_list,
CPUFREQ_CREATE_POLICY)
acpi_processor_notifier()
acpi_processor_ppc_init()
freq_qos_add_request(&perflib_req) <- QoS request activation

Address this by adding an acpi_processor_get_platform_limit() call to acpi_processor_ppc_init(), after the perflib_req activation via freq_qos_add_request(), which causes the initial _PPC limit to be picked up as appropriate. However, also ensure that the _PPC limit will not be picked up in the cases when the cpufreq driver does not call acpi_processor_register_performance() by adding a pr->performance check to the related_cpus loop in acpi_processor_ppc_init().

Fixes d15ce412737a ("ACPI: cpufreq: Switch to QoS requests instead of cpufreq notifier")
[ rjw: Consolidate pr-related checks in acpi_processor_ppc_init() ]
[ rjw: Subject and changelog adjustments ]
Cc 5.4+ <[email protected]> # 5.4+: 2d8b39a62a5d ACPI: processor: Avoid NULL pointer dereferences at init time
Cc 5.4+ <[email protected]> # 5.4+: 3000ce3c52f8 cpufreq: Use per-policy frequency QoS
Cc 5.4+ <[email protected]> # 5.4+: a1bb46c36ce3 ACPI: processor: Add QoS requests for all CPUs
Cc 5.4+ <[email protected]> # 5.4+
---
 drivers/acpi/processor_perflib.c |   10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)
drivers/acpi/processor_perflib.c +9 -1
@@ -176,11 +176,14 @@ void acpi_processor_ppc_init(struct cpuf
 {
 	unsigned int cpu;
 
+	if (ignore_ppc == 1)
+		return;
+
 	for_each_cpu(cpu, policy->related_cpus) {
 		struct acpi_processor *pr = per_cpu(processors, cpu);
 		int ret;
 
-		if (!pr)
+		if (!pr || !pr->performance)
 			continue;
 
 		/*
@@ -196,6 +199,11 @@ void acpi_processor_ppc_init(struct cpuf
 		if (ret < 0)
 			pr_err("Failed to add freq constraint for CPU%d (%d)\n",
 			       cpu, ret);
+
+		ret = acpi_processor_get_platform_limit(pr);
+		if (ret)
+			pr_err("Failed to update freq constraint for CPU%d (%d)\n",
+			       cpu, ret);
 	}
 }
 
author maintainer
#206 lore raw

PATCH 204/523 ACPI: processor: perflib: Move problematic pr->performance check

In reply to Greg Kroah-Hartman

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

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

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

commit d405ec23df13e6df599f5bd965a55d13420366b8 upstream.

Commit d33bd88ac0eb ("ACPI: processor: perflib: Fix initial _PPC limit application") added a pr->performance check that prevents the frequency QoS request from being added when the given processor has no performance object. Unfortunately, this causes a WARN() in freq_qos_remove_request() to trigger on an attempt to take the given CPU offline later because the frequency QoS object has not been added for it due to the missing performance object.

Address this by moving the pr->performance check before calling acpi_processor_get_platform_limit() so it only prevents a limit from being set for the CPU if the performance object is not present. This way, the frequency QoS request is added as it was before the above commit and it is present all the time along with the CPU's cpufreq policy regardless of whether or not the CPU is online.

Fixes d33bd88ac0eb ("ACPI: processor: perflib: Fix initial _PPC limit application")
Cc 5.4+ <[email protected]> # 5.4+
---
 drivers/acpi/processor_perflib.c |    5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)
drivers/acpi/processor_perflib.c +4 -1
@@ -183,7 +183,7 @@ void acpi_processor_ppc_init(struct cpuf
 		struct acpi_processor *pr = per_cpu(processors, cpu);
 		int ret;
 
-		if (!pr || !pr->performance)
+		if (!pr)
 			continue;
 
 		/*
@@ -200,6 +200,9 @@ void acpi_processor_ppc_init(struct cpuf
 			pr_err("Failed to add freq constraint for CPU%d (%d)\n",
 			       cpu, ret);
 
+		if (!pr->performance)
+			continue;
+
 		ret = acpi_processor_get_platform_limit(pr);
 		if (ret)
 			pr_err("Failed to update freq constraint for CPU%d (%d)\n",
author maintainer
#207 lore raw

PATCH 205/523 udp: also consider secpath when evaluating ipsec use for checksumming

In reply to Greg Kroah-Hartman

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

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

From: Sabrina Dubroca <[email protected]>

[ Upstream commit 1118aaa3b35157777890fffab91d8c1da841b20b ]

Commit b40c5f4fde22 ("udp: disable inner UDP checksum offloads in IPsec case") tried to fix checksumming in UFO when the packets are going through IPsec, so that we can't rely on offloads because the UDP header and payload will be encrypted.

But when doing a TCP test over VXLAN going through IPsec transport mode with GSO enabled (esp4_offload module loaded), I'm seeing broken UDP checksums on the encap after successful decryption.

The skbs get to udp4_ufo_fragment/__skb_udp_tunnel_segment via __dev_queue_xmit -> validate_xmit_skb -> skb_gso_segment and at this point we've already dropped the dst (unless the device sets IFF_XMIT_DST_RELEASE, which is not common), so need_ipsec is false and we proceed with checksum offload.

Make need_ipsec also check the secpath, which is not dropped on this callpath.

Fixes b40c5f4fde22 ("udp: disable inner UDP checksum offloads in IPsec case")
---
 net/ipv4/udp_offload.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
net/ipv4/udp_offload.c +1 -1
index 73beaa7e2d70..5d4413fe4195 100644
@@ -58,7 +58,7 @@ static struct sk_buff *__skb_udp_tunnel_segment(struct sk_buff *skb,
 	remcsum = !!(skb_shinfo(skb)->gso_type & SKB_GSO_TUNNEL_REMCSUM);
 	skb->remcsum_offload = remcsum;
 
-	need_ipsec = skb_dst(skb) && dst_xfrm(skb_dst(skb));
+	need_ipsec = (skb_dst(skb) && dst_xfrm(skb_dst(skb))) || skb_sec_path(skb);
 	/* Try to offload checksum if possible */
 	offload_csum = !!(need_csum &&
 			  !need_ipsec &&
Signature · 1 line
2.50.1
author maintainer
#208 lore raw

PATCH 206/523 netfilter: ctnetlink: fix refcount leak on table dump

In reply to Greg Kroah-Hartman

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

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

From: Florian Westphal <[email protected]>

[ Upstream commit de788b2e6227462b6dcd0e07474e72c089008f74 ]

There is a reference count leak in ctnetlink_dump_table():

      if (res < 0) {
                nf_conntrack_get(&ct->ct_general); // HERE
                cb->args[1] = (unsigned long)ct;
                ...

While its very unlikely, its possible that ct == last. If this happens, then the refcount of ct was already incremented. This 2nd increment is never undone.

This prevents the conntrack object from being released, which in turn keeps prevents cnet->count from dropping back to 0.

This will then block the netns dismantle (or conntrack rmmod) as nf_conntrack_cleanup_net_list() will wait forever.

This can be reproduced by running conntrack_resize.sh selftest in a loop. It takes ~20 minutes for me on a preemptible kernel on average before I see a runaway kworker spinning in nf_conntrack_cleanup_net_list.

One fix would to change this to:

        if (res < 0) {
		if (ct != last)
	                nf_conntrack_get(&ct->ct_general);

But this reference counting isn't needed in the first place. We can just store a cookie value instead.

A followup patch will do the same for ctnetlink_exp_dump_table, it looks to me as if this has the same problem and like ctnetlink_dump_table, we only need a 'skip hint', not the actual object so we can apply the same cookie strategy there as well.

Fixes d205dc40798d ("[NETFILTER]: ctnetlink: fix deadlock in table dumping")
---
 net/netfilter/nf_conntrack_netlink.c | 24 +++++++++++++-----------
 1 file changed, 13 insertions(+), 11 deletions(-)
net/netfilter/nf_conntrack_netlink.c +13 -11
index b2b06033ef2c..f622fcad3f50 100644
@@ -839,8 +839,6 @@ ctnetlink_conntrack_event(unsigned int events, struct nf_ct_event *item)
 
 static int ctnetlink_done(struct netlink_callback *cb)
 {
-	if (cb->args[1])
-		nf_ct_put((struct nf_conn *)cb->args[1]);
 	kfree(cb->data);
 	return 0;
 }
@@ -1112,19 +1110,26 @@ static int ctnetlink_filter_match(struct nf_conn *ct, void *data)
 	return 0;
 }
 
+static unsigned long ctnetlink_get_id(const struct nf_conn *ct)
+{
+	unsigned long id = nf_ct_get_id(ct);
+
+	return id ? id : 1;
+}
+
 static int
 ctnetlink_dump_table(struct sk_buff *skb, struct netlink_callback *cb)
 {
 	unsigned int flags = cb->data ? NLM_F_DUMP_FILTERED : 0;
 	struct net *net = sock_net(skb->sk);
-	struct nf_conn *ct, *last;
+	unsigned long last_id = cb->args[1];
 	struct nf_conntrack_tuple_hash *h;
 	struct hlist_nulls_node *n;
 	struct nf_conn *nf_ct_evict[8];
+	struct nf_conn *ct;
 	int res, i;
 	spinlock_t *lockp;
 
-	last = (struct nf_conn *)cb->args[1];
 	i = 0;
 
 	local_bh_disable();
@@ -1160,7 +1165,7 @@ ctnetlink_dump_table(struct sk_buff *skb, struct netlink_callback *cb)
 				continue;
 
 			if (cb->args[1]) {
-				if (ct != last)
+				if (ctnetlink_get_id(ct) != last_id)
 					continue;
 				cb->args[1] = 0;
 			}
@@ -1173,8 +1178,7 @@ ctnetlink_dump_table(struct sk_buff *skb, struct netlink_callback *cb)
 					    NFNL_MSG_TYPE(cb->nlh->nlmsg_type),
 					    ct, true, flags);
 			if (res < 0) {
-				nf_conntrack_get(&ct->ct_general);
-				cb->args[1] = (unsigned long)ct;
+				cb->args[1] = ctnetlink_get_id(ct);
 				spin_unlock(lockp);
 				goto out;
 			}
@@ -1187,12 +1191,10 @@ ctnetlink_dump_table(struct sk_buff *skb, struct netlink_callback *cb)
 	}
 out:
 	local_bh_enable();
-	if (last) {
+	if (last_id) {
 		/* nf ct hash resize happened, now clear the leftover. */
-		if ((struct nf_conn *)cb->args[1] == last)
+		if (cb->args[1] == last_id)
 			cb->args[1] = 0;
-
-		nf_ct_put(last);
 	}
 
 	while (i) {
Signature · 1 line
2.50.1
author maintainer
#209 lore raw

PATCH 207/523 sctp: linearize cloned gso packets in sctp_rcv

In reply to Greg Kroah-Hartman

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

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

From: Xin Long <[email protected]>

[ Upstream commit fd60d8a086191fe33c2d719732d2482052fa6805 ]

A cloned head skb still shares these frag skbs in fraglist with the original head skb. It's not safe to access these frag skbs.

syzbot reported two use-of-uninitialized-memory bugs caused by this:

  BUG: KMSAN: uninit-value in sctp_inq_pop+0x15b7/0x1920 net/sctp/inqueue.c:211
   sctp_inq_pop+0x15b7/0x1920 net/sctp/inqueue.c:211
   sctp_assoc_bh_rcv+0x1a7/0xc50 net/sctp/associola.c:998
   sctp_inq_push+0x2ef/0x380 net/sctp/inqueue.c:88
   sctp_backlog_rcv+0x397/0xdb0 net/sctp/input.c:331
   sk_backlog_rcv+0x13b/0x420 include/net/sock.h:1122
   __release_sock+0x1da/0x330 net/core/sock.c:3106
   release_sock+0x6b/0x250 net/core/sock.c:3660
   sctp_wait_for_connect+0x487/0x820 net/sctp/socket.c:9360
   sctp_sendmsg_to_asoc+0x1ec1/0x1f00 net/sctp/socket.c:1885
   sctp_sendmsg+0x32b9/0x4a80 net/sctp/socket.c:2031
   inet_sendmsg+0x25a/0x280 net/ipv4/af_inet.c:851
   sock_sendmsg_nosec net/socket.c:718 [inline]

and

  BUG: KMSAN: uninit-value in sctp_assoc_bh_rcv+0x34e/0xbc0 net/sctp/associola.c:987
   sctp_assoc_bh_rcv+0x34e/0xbc0 net/sctp/associola.c:987
   sctp_inq_push+0x2a3/0x350 net/sctp/inqueue.c:88
   sctp_backlog_rcv+0x3c7/0xda0 net/sctp/input.c:331
   sk_backlog_rcv+0x142/0x420 include/net/sock.h:1148
   __release_sock+0x1d3/0x330 net/core/sock.c:3213
   release_sock+0x6b/0x270 net/core/sock.c:3767
   sctp_wait_for_connect+0x458/0x820 net/sctp/socket.c:9367
   sctp_sendmsg_to_asoc+0x223a/0x2260 net/sctp/socket.c:1886
   sctp_sendmsg+0x3910/0x49f0 net/sctp/socket.c:2032
   inet_sendmsg+0x269/0x2a0 net/ipv4/af_inet.c:851
   sock_sendmsg_nosec net/socket.c:712 [inline]

This patch fixes it by linearizing cloned gso packets in sctp_rcv().

---
 net/sctp/input.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
net/sctp/input.c +1 -1
index 8fe1a74f0618..079b1bfc7d31 100644
@@ -114,7 +114,7 @@ int sctp_rcv(struct sk_buff *skb)
 	 * it's better to just linearize it otherwise crc computing
 	 * takes longer.
 	 */
-	if ((!is_gso && skb_linearize(skb)) ||
+	if (((!is_gso || skb_cloned(skb)) && skb_linearize(skb)) ||
 	    !pskb_may_pull(skb, sizeof(struct sctphdr)))
 		goto discard_it;
 
Signature · 1 line
2.50.1
author maintainer
#210 lore raw

PATCH 208/523 intel_idle: Allow loading ACPI tables for any family

In reply to Greg Kroah-Hartman

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

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

From: Len Brown <[email protected]>

[ Upstream commit e91a158b694d7f4bd937763dde79ed0afa472d8a ]

There is no reason to limit intel_idle's loading of ACPI tables to family 6. Upcoming Intel processors are not in family 6.

Below "Fixes" really means "applies cleanly until". That syntax commit didn't change the previous logic, but shows this patch applies back 5-years.

---
 drivers/idle/intel_idle.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/idle/intel_idle.c +1 -1
index 1cead368f961..f6a2211ca4ef 100644
@@ -1154,7 +1154,7 @@ static const struct x86_cpu_id intel_idle_ids[] __initconst = {
 };
 
 static const struct x86_cpu_id intel_mwait_ids[] __initconst = {
-	X86_MATCH_VENDOR_FAM_FEATURE(INTEL, 6, X86_FEATURE_MWAIT, NULL),
+	X86_MATCH_VENDOR_FAM_FEATURE(INTEL, X86_FAMILY_ANY, X86_FEATURE_MWAIT, NULL),
 	{}
 };
 
Signature · 1 line
2.50.1
author maintainer
#211 lore raw

PATCH 209/523 cpuidle: governors: menu: Avoid using invalid recent intervals data

In reply to Greg Kroah-Hartman

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

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

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

[ Upstream commit fa3fa55de0d6177fdcaf6fc254f13cc8f33c3eed ]

Marc has reported that commit 85975daeaa4d ("cpuidle: menu: Avoid discarding useful information") caused the number of wakeup interrupts to increase on an idle system [1], which was not expected to happen after merely allowing shallower idle states to be selected by the governor in some cases.

However, on the system in question, all of the idle states deeper than WFI are rejected by the driver due to a firmware issue [2]. This causes the governor to only consider the recent interval duriation data corresponding to attempts to enter WFI that are successful and the recent invervals table is filled with values lower than the scheduler tick period. Consequently, the governor predicts an idle duration below the scheduler tick period length and avoids stopping the tick more often which leads to the observed symptom.

Address it by modifying the governor to update the recent intervals table also when entering the previously selected idle state fails, so it knows that the short idle intervals might have been the minority had the selected idle states been actually entered every time.

---
 drivers/cpuidle/governors/menu.c | 21 +++++++++++++++++----
 1 file changed, 17 insertions(+), 4 deletions(-)
drivers/cpuidle/governors/menu.c +17 -4
index a95cc8f024fd..d34463f96848 100644
@@ -158,6 +158,14 @@ static inline int performance_multiplier(unsigned long nr_iowaiters)
 
 static DEFINE_PER_CPU(struct menu_device, menu_devices);
 
+static void menu_update_intervals(struct menu_device *data, unsigned int interval_us)
+{
+	/* Update the repeating-pattern data. */
+	data->intervals[data->interval_ptr++] = interval_us;
+	if (data->interval_ptr >= INTERVALS)
+		data->interval_ptr = 0;
+}
+
 static void menu_update(struct cpuidle_driver *drv, struct cpuidle_device *dev);
 
 /*
@@ -288,6 +296,14 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 	if (data->needs_update) {
 		menu_update(drv, dev);
 		data->needs_update = 0;
+	} else if (!dev->last_residency_ns) {
+		/*
+		 * This happens when the driver rejects the previously selected
+		 * idle state and returns an error, so update the recent
+		 * intervals table to prevent invalid information from being
+		 * used going forward.
+		 */
+		menu_update_intervals(data, UINT_MAX);
 	}
 
 	/* determine the expected residency time, round up */
@@ -537,10 +553,7 @@ static void menu_update(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 
 	data->correction_factor[data->bucket] = new_factor;
 
-	/* update the repeating-pattern data */
-	data->intervals[data->interval_ptr++] = ktime_to_us(measured_ns);
-	if (data->interval_ptr >= INTERVALS)
-		data->interval_ptr = 0;
+	menu_update_intervals(data, ktime_to_us(measured_ns));
 }
 
 /**
Signature · 1 line
2.50.1
author maintainer
#212 lore raw

PATCH 210/523 hfs: fix slab-out-of-bounds in hfs_bnode_read()

In reply to Greg Kroah-Hartman

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

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

From: Viacheslav Dubeyko <[email protected]>

[ Upstream commit a431930c9bac518bf99d6b1da526a7f37ddee8d8 ]

This patch introduces is_bnode_offset_valid() method that checks the requested offset value. Also, it introduces check_and_correct_requested_length() method that checks and correct the requested length (if it is necessary). These methods are used in hfs_bnode_read(), hfs_bnode_write(), hfs_bnode_clear(), hfs_bnode_copy(), and hfs_bnode_move() with the goal to prevent the access out of allocated memory and triggering the crash.

---
 fs/hfs/bnode.c | 92 ++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 92 insertions(+)
fs/hfs/bnode.c +92 -0
index 2251286cd83f..2039cb6d5f66 100644
@@ -15,6 +15,48 @@
 
 #include "btree.h"
 
+static inline
+bool is_bnode_offset_valid(struct hfs_bnode *node, int off)
+{
+	bool is_valid = off < node->tree->node_size;
+
+	if (!is_valid) {
+		pr_err("requested invalid offset: "
+		       "NODE: id %u, type %#x, height %u, "
+		       "node_size %u, offset %d\n",
+		       node->this, node->type, node->height,
+		       node->tree->node_size, off);
+	}
+
+	return is_valid;
+}
+
+static inline
+int check_and_correct_requested_length(struct hfs_bnode *node, int off, int len)
+{
+	unsigned int node_size;
+
+	if (!is_bnode_offset_valid(node, off))
+		return 0;
+
+	node_size = node->tree->node_size;
+
+	if ((off + len) > node_size) {
+		int new_len = (int)node_size - off;
+
+		pr_err("requested length has been corrected: "
+		       "NODE: id %u, type %#x, height %u, "
+		       "node_size %u, offset %d, "
+		       "requested_len %d, corrected_len %d\n",
+		       node->this, node->type, node->height,
+		       node->tree->node_size, off, len, new_len);
+
+		return new_len;
+	}
+
+	return len;
+}
+
 void hfs_bnode_read(struct hfs_bnode *node, void *buf, int off, int len)
 {
 	struct page *page;
@@ -23,6 +65,20 @@ void hfs_bnode_read(struct hfs_bnode *node, void *buf, int off, int len)
 	int bytes_to_read;
 	void *vaddr;
 
+	if (!is_bnode_offset_valid(node, off))
+		return;
+
+	if (len == 0) {
+		pr_err("requested zero length: "
+		       "NODE: id %u, type %#x, height %u, "
+		       "node_size %u, offset %d, len %d\n",
+		       node->this, node->type, node->height,
+		       node->tree->node_size, off, len);
+		return;
+	}
+
+	len = check_and_correct_requested_length(node, off, len);
+
 	off += node->page_offset;
 	pagenum = off >> PAGE_SHIFT;
 	off &= ~PAGE_MASK; /* compute page offset for the first page */
@@ -83,6 +139,20 @@ void hfs_bnode_write(struct hfs_bnode *node, void *buf, int off, int len)
 {
 	struct page *page;
 
+	if (!is_bnode_offset_valid(node, off))
+		return;
+
+	if (len == 0) {
+		pr_err("requested zero length: "
+		       "NODE: id %u, type %#x, height %u, "
+		       "node_size %u, offset %d, len %d\n",
+		       node->this, node->type, node->height,
+		       node->tree->node_size, off, len);
+		return;
+	}
+
+	len = check_and_correct_requested_length(node, off, len);
+
 	off += node->page_offset;
 	page = node->page[0];
 
@@ -108,6 +178,20 @@ void hfs_bnode_clear(struct hfs_bnode *node, int off, int len)
 {
 	struct page *page;
 
+	if (!is_bnode_offset_valid(node, off))
+		return;
+
+	if (len == 0) {
+		pr_err("requested zero length: "
+		       "NODE: id %u, type %#x, height %u, "
+		       "node_size %u, offset %d, len %d\n",
+		       node->this, node->type, node->height,
+		       node->tree->node_size, off, len);
+		return;
+	}
+
+	len = check_and_correct_requested_length(node, off, len);
+
 	off += node->page_offset;
 	page = node->page[0];
 
@@ -124,6 +208,10 @@ void hfs_bnode_copy(struct hfs_bnode *dst_node, int dst,
 	hfs_dbg(BNODE_MOD, "copybytes: %u,%u,%u\n", dst, src, len);
 	if (!len)
 		return;
+
+	len = check_and_correct_requested_length(src_node, src, len);
+	len = check_and_correct_requested_length(dst_node, dst, len);
+
 	src += src_node->page_offset;
 	dst += dst_node->page_offset;
 	src_page = src_node->page[0];
@@ -143,6 +231,10 @@ void hfs_bnode_move(struct hfs_bnode *node, int dst, int src, int len)
 	hfs_dbg(BNODE_MOD, "movebytes: %u,%u,%u\n", dst, src, len);
 	if (!len)
 		return;
+
+	len = check_and_correct_requested_length(node, src, len);
+	len = check_and_correct_requested_length(node, dst, len);
+
 	src += node->page_offset;
 	dst += node->page_offset;
 	page = node->page[0];
Signature · 1 line
2.39.5
author maintainer
#213 lore raw

PATCH 211/523 hfsplus: fix slab-out-of-bounds in hfsplus_bnode_read()

In reply to Greg Kroah-Hartman

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

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

From: Viacheslav Dubeyko <[email protected]>

[ Upstream commit c80aa2aaaa5e69d5219c6af8ef7e754114bd08d2 ]

The hfsplus_bnode_read() method can trigger the issue:

[  174.852007][ T9784] ==================================================================
[  174.852709][ T9784] BUG: KASAN: slab-out-of-bounds in hfsplus_bnode_read+0x2f4/0x360
[  174.853412][ T9784] Read of size 8 at addr ffff88810b5fc6c0 by task repro/9784
[  174.854059][ T9784]
[  174.854272][ T9784] CPU: 1 UID: 0 PID: 9784 Comm: repro Not tainted 6.16.0-rc3 #7 PREEMPT(full)
[  174.854281][ T9784] Hardware name: QEMU Ubuntu 24.04 PC (i440FX + PIIX, 1996), BIOS 1.16.3-debian-1.16.3-2 04/01/2014
[  174.854286][ T9784] Call Trace:
[  174.854289][ T9784]  <TASK>
[  174.854292][ T9784]  dump_stack_lvl+0x10e/0x1f0
[  174.854305][ T9784]  print_report+0xd0/0x660
[  174.854315][ T9784]  ? __virt_addr_valid+0x81/0x610
[  174.854323][ T9784]  ? __phys_addr+0xe8/0x180
[  174.854330][ T9784]  ? hfsplus_bnode_read+0x2f4/0x360
[  174.854337][ T9784]  kasan_report+0xc6/0x100
[  174.854346][ T9784]  ? hfsplus_bnode_read+0x2f4/0x360
[  174.854354][ T9784]  hfsplus_bnode_read+0x2f4/0x360
[  174.854362][ T9784]  hfsplus_bnode_dump+0x2ec/0x380
[  174.854370][ T9784]  ? __pfx_hfsplus_bnode_dump+0x10/0x10
[  174.854377][ T9784]  ? hfsplus_bnode_write_u16+0x83/0xb0
[  174.854385][ T9784]  ? srcu_gp_start+0xd0/0x310
[  174.854393][ T9784]  ? __mark_inode_dirty+0x29e/0xe40
[  174.854402][ T9784]  hfsplus_brec_remove+0x3d2/0x4e0
[  174.854411][ T9784]  __hfsplus_delete_attr+0x290/0x3a0
[  174.854419][ T9784]  ? __pfx_hfs_find_1st_rec_by_cnid+0x10/0x10
[  174.854427][ T9784]  ? __pfx___hfsplus_delete_attr+0x10/0x10
[  174.854436][ T9784]  ? __asan_memset+0x23/0x50
[  174.854450][ T9784]  hfsplus_delete_all_attrs+0x262/0x320
[  174.854459][ T9784]  ? __pfx_hfsplus_delete_all_attrs+0x10/0x10
[  174.854469][ T9784]  ? rcu_is_watching+0x12/0xc0
[  174.854476][ T9784]  ? __mark_inode_dirty+0x29e/0xe40
[  174.854483][ T9784]  hfsplus_delete_cat+0x845/0xde0
[  174.854493][ T9784]  ? __pfx_hfsplus_delete_cat+0x10/0x10
[  174.854507][ T9784]  hfsplus_unlink+0x1ca/0x7c0
[  174.854516][ T9784]  ? __pfx_hfsplus_unlink+0x10/0x10
[  174.854525][ T9784]  ? down_write+0x148/0x200
[  174.854532][ T9784]  ? __pfx_down_write+0x10/0x10
[  174.854540][ T9784]  vfs_unlink+0x2fe/0x9b0
[  174.854549][ T9784]  do_unlinkat+0x490/0x670
[  174.854557][ T9784]  ? __pfx_do_unlinkat+0x10/0x10
[  174.854565][ T9784]  ? __might_fault+0xbc/0x130
[  174.854576][ T9784]  ? getname_flags.part.0+0x1c5/0x550
[  174.854584][ T9784]  __x64_sys_unlink+0xc5/0x110
[  174.854592][ T9784]  do_syscall_64+0xc9/0x480
[  174.854600][ T9784]  entry_SYSCALL_64_after_hwframe+0x77/0x7f
[  174.854608][ T9784] RIP: 0033:0x7f6fdf4c3167
[  174.854614][ T9784] Code: f0 ff ff 73 01 c3 48 8b 0d 26 0d 0e 00 f7 d8 64 89 01 48 83 c8 ff c3 66 2e 0f 1f 84 00 00 00 00 08
[  174.854622][ T9784] RSP: 002b:00007ffcb948bca8 EFLAGS: 00000206 ORIG_RAX: 0000000000000057
[  174.854630][ T9784] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f6fdf4c3167
[  174.854636][ T9784] RDX: 00007ffcb948bcc0 RSI: 00007ffcb948bcc0 RDI: 00007ffcb948bd50
[  174.854641][ T9784] RBP: 00007ffcb948cd90 R08: 0000000000000001 R09: 00007ffcb948bb40
[  174.854645][ T9784] R10: 00007f6fdf564fc0 R11: 0000000000000206 R12: 0000561e1bc9c2d0
[  174.854650][ T9784] R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000
[  174.854658][ T9784]  </TASK>
[  174.854661][ T9784]
[  174.879281][ T9784] Allocated by task 9784:
[  174.879664][ T9784]  kasan_save_stack+0x20/0x40
[  174.880082][ T9784]  kasan_save_track+0x14/0x30
[  174.880500][ T9784]  __kasan_kmalloc+0xaa/0xb0
[  174.880908][ T9784]  __kmalloc_noprof+0x205/0x550
[  174.881337][ T9784]  __hfs_bnode_create+0x107/0x890
[  174.881779][ T9784]  hfsplus_bnode_find+0x2d0/0xd10
[  174.882222][ T9784]  hfsplus_brec_find+0x2b0/0x520
[  174.882659][ T9784]  hfsplus_delete_all_attrs+0x23b/0x320
[  174.883144][ T9784]  hfsplus_delete_cat+0x845/0xde0
[  174.883595][ T9784]  hfsplus_rmdir+0x106/0x1b0
[  174.884004][ T9784]  vfs_rmdir+0x206/0x690
[  174.884379][ T9784]  do_rmdir+0x2b7/0x390
[  174.884751][ T9784]  __x64_sys_rmdir+0xc5/0x110
[  174.885167][ T9784]  do_syscall_64+0xc9/0x480
[  174.885568][ T9784]  entry_SYSCALL_64_after_hwframe+0x77/0x7f
[  174.886083][ T9784]
[  174.886293][ T9784] The buggy address belongs to the object at ffff88810b5fc600
[  174.886293][ T9784]  which belongs to the cache kmalloc-192 of size 192
[  174.887507][ T9784] The buggy address is located 40 bytes to the right of
[  174.887507][ T9784]  allocated 152-byte region [ffff88810b5fc600, ffff88810b5fc698)
[  174.888766][ T9784]
[  174.888976][ T9784] The buggy address belongs to the physical page:
[  174.889533][ T9784] page: refcount:0 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x10b5fc
[  174.890295][ T9784] flags: 0x57ff00000000000(node=1|zone=2|lastcpupid=0x7ff)
[  174.890927][ T9784] page_type: f5(slab)
[  174.891284][ T9784] raw: 057ff00000000000 ffff88801b4423c0 ffffea000426dc80 dead000000000002
[  174.892032][ T9784] raw: 0000000000000000 0000000080100010 00000000f5000000 0000000000000000
[  174.892774][ T9784] page dumped because: kasan: bad access detected
[  174.893327][ T9784] page_owner tracks the page as allocated
[  174.893825][ T9784] page last allocated via order 0, migratetype Unmovable, gfp_mask 0x52c00(GFP_NOIO|__GFP_NOWARN|__GFP_NO1
[  174.895373][ T9784]  post_alloc_hook+0x1c0/0x230
[  174.895801][ T9784]  get_page_from_freelist+0xdeb/0x3b30
[  174.896284][ T9784]  __alloc_frozen_pages_noprof+0x25c/0x2460
[  174.896810][ T9784]  alloc_pages_mpol+0x1fb/0x550
[  174.897242][ T9784]  new_slab+0x23b/0x340
[  174.897614][ T9784]  ___slab_alloc+0xd81/0x1960
[  174.898028][ T9784]  __slab_alloc.isra.0+0x56/0xb0
[  174.898468][ T9784]  __kmalloc_noprof+0x2b0/0x550
[  174.898896][ T9784]  usb_alloc_urb+0x73/0xa0
[  174.899289][ T9784]  usb_control_msg+0x1cb/0x4a0
[  174.899718][ T9784]  usb_get_string+0xab/0x1a0
[  174.900133][ T9784]  usb_string_sub+0x107/0x3c0
[  174.900549][ T9784]  usb_string+0x307/0x670
[  174.900933][ T9784]  usb_cache_string+0x80/0x150
[  174.901355][ T9784]  usb_new_device+0x1d0/0x19d0
[  174.901786][ T9784]  register_root_hub+0x299/0x730
[  174.902231][ T9784] page last free pid 10 tgid 10 stack trace:
[  174.902757][ T9784]  __free_frozen_pages+0x80c/0x1250
[  174.903217][ T9784]  vfree.part.0+0x12b/0xab0
[  174.903645][ T9784]  delayed_vfree_work+0x93/0xd0
[  174.904073][ T9784]  process_one_work+0x9b5/0x1b80
[  174.904519][ T9784]  worker_thread+0x630/0xe60
[  174.904927][ T9784]  kthread+0x3a8/0x770
[  174.905291][ T9784]  ret_from_fork+0x517/0x6e0
[  174.905709][ T9784]  ret_from_fork_asm+0x1a/0x30
[  174.906128][ T9784]
[  174.906338][ T9784] Memory state around the buggy address:
[  174.906828][ T9784]  ffff88810b5fc580: fb fb fb fb fb fb fb fb fc fc fc fc fc fc fc fc
[  174.907528][ T9784]  ffff88810b5fc600: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
[  174.908222][ T9784] >ffff88810b5fc680: 00 00 00 fc fc fc fc fc fc fc fc fc fc fc fc fc
[  174.908917][ T9784]                                            ^
[  174.909481][ T9784]  ffff88810b5fc700: fa fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
[  174.910432][ T9784]  ffff88810b5fc780: fb fb fb fb fb fb fb fb fc fc fc fc fc fc fc fc
[  174.911401][ T9784] ==================================================================

The reason of the issue that code doesn't check the correctness of the requested offset and length. As a result, incorrect value of offset or/and length could result in access out of allocated memory.

This patch introduces is_bnode_offset_valid() method that checks the requested offset value. Also, it introduces check_and_correct_requested_length() method that checks and correct the requested length (if it is necessary). These methods are used in hfsplus_bnode_read(), hfsplus_bnode_write(), hfsplus_bnode_clear(), hfsplus_bnode_copy(), and hfsplus_bnode_move() with the goal to prevent the access out of allocated memory and triggering the crash.

---
 fs/hfsplus/bnode.c | 92 ++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 92 insertions(+)
fs/hfsplus/bnode.c +92 -0
index cf6e5de7b9da..c9c38fddf505 100644
@@ -18,12 +18,68 @@
 #include "hfsplus_fs.h"
 #include "hfsplus_raw.h"
 
+static inline
+bool is_bnode_offset_valid(struct hfs_bnode *node, int off)
+{
+	bool is_valid = off < node->tree->node_size;
+
+	if (!is_valid) {
+		pr_err("requested invalid offset: "
+		       "NODE: id %u, type %#x, height %u, "
+		       "node_size %u, offset %d\n",
+		       node->this, node->type, node->height,
+		       node->tree->node_size, off);
+	}
+
+	return is_valid;
+}
+
+static inline
+int check_and_correct_requested_length(struct hfs_bnode *node, int off, int len)
+{
+	unsigned int node_size;
+
+	if (!is_bnode_offset_valid(node, off))
+		return 0;
+
+	node_size = node->tree->node_size;
+
+	if ((off + len) > node_size) {
+		int new_len = (int)node_size - off;
+
+		pr_err("requested length has been corrected: "
+		       "NODE: id %u, type %#x, height %u, "
+		       "node_size %u, offset %d, "
+		       "requested_len %d, corrected_len %d\n",
+		       node->this, node->type, node->height,
+		       node->tree->node_size, off, len, new_len);
+
+		return new_len;
+	}
+
+	return len;
+}
+
 /* Copy a specified range of bytes from the raw data of a node */
 void hfs_bnode_read(struct hfs_bnode *node, void *buf, int off, int len)
 {
 	struct page **pagep;
 	int l;
 
+	if (!is_bnode_offset_valid(node, off))
+		return;
+
+	if (len == 0) {
+		pr_err("requested zero length: "
+		       "NODE: id %u, type %#x, height %u, "
+		       "node_size %u, offset %d, len %d\n",
+		       node->this, node->type, node->height,
+		       node->tree->node_size, off, len);
+		return;
+	}
+
+	len = check_and_correct_requested_length(node, off, len);
+
 	off += node->page_offset;
 	pagep = node->page + (off >> PAGE_SHIFT);
 	off &= ~PAGE_MASK;
@@ -83,6 +139,20 @@ void hfs_bnode_write(struct hfs_bnode *node, void *buf, int off, int len)
 	struct page **pagep;
 	int l;
 
+	if (!is_bnode_offset_valid(node, off))
+		return;
+
+	if (len == 0) {
+		pr_err("requested zero length: "
+		       "NODE: id %u, type %#x, height %u, "
+		       "node_size %u, offset %d, len %d\n",
+		       node->this, node->type, node->height,
+		       node->tree->node_size, off, len);
+		return;
+	}
+
+	len = check_and_correct_requested_length(node, off, len);
+
 	off += node->page_offset;
 	pagep = node->page + (off >> PAGE_SHIFT);
 	off &= ~PAGE_MASK;
@@ -113,6 +183,20 @@ void hfs_bnode_clear(struct hfs_bnode *node, int off, int len)
 	struct page **pagep;
 	int l;
 
+	if (!is_bnode_offset_valid(node, off))
+		return;
+
+	if (len == 0) {
+		pr_err("requested zero length: "
+		       "NODE: id %u, type %#x, height %u, "
+		       "node_size %u, offset %d, len %d\n",
+		       node->this, node->type, node->height,
+		       node->tree->node_size, off, len);
+		return;
+	}
+
+	len = check_and_correct_requested_length(node, off, len);
+
 	off += node->page_offset;
 	pagep = node->page + (off >> PAGE_SHIFT);
 	off &= ~PAGE_MASK;
@@ -139,6 +223,10 @@ void hfs_bnode_copy(struct hfs_bnode *dst_node, int dst,
 	hfs_dbg(BNODE_MOD, "copybytes: %u,%u,%u\n", dst, src, len);
 	if (!len)
 		return;
+
+	len = check_and_correct_requested_length(src_node, src, len);
+	len = check_and_correct_requested_length(dst_node, dst, len);
+
 	src += src_node->page_offset;
 	dst += dst_node->page_offset;
 	src_page = src_node->page + (src >> PAGE_SHIFT);
@@ -196,6 +284,10 @@ void hfs_bnode_move(struct hfs_bnode *node, int dst, int src, int len)
 	hfs_dbg(BNODE_MOD, "movebytes: %u,%u,%u\n", dst, src, len);
 	if (!len)
 		return;
+
+	len = check_and_correct_requested_length(node, src, len);
+	len = check_and_correct_requested_length(node, dst, len);
+
 	src += node->page_offset;
 	dst += node->page_offset;
 	if (dst > src) {
Signature · 1 line
2.39.5
author maintainer
#214 lore raw

PATCH 212/523 hfsplus: fix slab-out-of-bounds read in hfsplus_uni2asc()

In reply to Greg Kroah-Hartman

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

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

From: Viacheslav Dubeyko <[email protected]>

[ Upstream commit 94458781aee6045bd3d0ad4b80b02886b9e2219b ]

The hfsplus_readdir() method is capable to crash by calling hfsplus_uni2asc():

[  667.121659][ T9805] ==================================================================
[  667.122651][ T9805] BUG: KASAN: slab-out-of-bounds in hfsplus_uni2asc+0x902/0xa10
[  667.123627][ T9805] Read of size 2 at addr ffff88802592f40c by task repro/9805
[  667.124578][ T9805]
[  667.124876][ T9805] CPU: 3 UID: 0 PID: 9805 Comm: repro Not tainted 6.16.0-rc3 #1 PREEMPT(full)
[  667.124886][ T9805] Hardware name: QEMU Ubuntu 24.04 PC (i440FX + PIIX, 1996), BIOS 1.16.3-debian-1.16.3-2 04/01/2014
[  667.124890][ T9805] Call Trace:
[  667.124893][ T9805]  <TASK>
[  667.124896][ T9805]  dump_stack_lvl+0x10e/0x1f0
[  667.124911][ T9805]  print_report+0xd0/0x660
[  667.124920][ T9805]  ? __virt_addr_valid+0x81/0x610
[  667.124928][ T9805]  ? __phys_addr+0xe8/0x180
[  667.124934][ T9805]  ? hfsplus_uni2asc+0x902/0xa10
[  667.124942][ T9805]  kasan_report+0xc6/0x100
[  667.124950][ T9805]  ? hfsplus_uni2asc+0x902/0xa10
[  667.124959][ T9805]  hfsplus_uni2asc+0x902/0xa10
[  667.124966][ T9805]  ? hfsplus_bnode_read+0x14b/0x360
[  667.124974][ T9805]  hfsplus_readdir+0x845/0xfc0
[  667.124984][ T9805]  ? __pfx_hfsplus_readdir+0x10/0x10
[  667.124994][ T9805]  ? stack_trace_save+0x8e/0xc0
[  667.125008][ T9805]  ? iterate_dir+0x18b/0xb20
[  667.125015][ T9805]  ? trace_lock_acquire+0x85/0xd0
[  667.125022][ T9805]  ? lock_acquire+0x30/0x80
[  667.125029][ T9805]  ? iterate_dir+0x18b/0xb20
[  667.125037][ T9805]  ? down_read_killable+0x1ed/0x4c0
[  667.125044][ T9805]  ? putname+0x154/0x1a0
[  667.125051][ T9805]  ? __pfx_down_read_killable+0x10/0x10
[  667.125058][ T9805]  ? apparmor_file_permission+0x239/0x3e0
[  667.125069][ T9805]  iterate_dir+0x296/0xb20
[  667.125076][ T9805]  __x64_sys_getdents64+0x13c/0x2c0
[  667.125084][ T9805]  ? __pfx___x64_sys_getdents64+0x10/0x10
[  667.125091][ T9805]  ? __x64_sys_openat+0x141/0x200
[  667.125126][ T9805]  ? __pfx_filldir64+0x10/0x10
[  667.125134][ T9805]  ? do_user_addr_fault+0x7fe/0x12f0
[  667.125143][ T9805]  do_syscall_64+0xc9/0x480
[  667.125151][ T9805]  entry_SYSCALL_64_after_hwframe+0x77/0x7f
[  667.125158][ T9805] RIP: 0033:0x7fa8753b2fc9
[  667.125164][ T9805] Code: 00 c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 48
[  667.125172][ T9805] RSP: 002b:00007ffe96f8e0f8 EFLAGS: 00000217 ORIG_RAX: 00000000000000d9
[  667.125181][ T9805] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007fa8753b2fc9
[  667.125185][ T9805] RDX: 0000000000000400 RSI: 00002000000063c0 RDI: 0000000000000004
[  667.125190][ T9805] RBP: 00007ffe96f8e110 R08: 00007ffe96f8e110 R09: 00007ffe96f8e110
[  667.125195][ T9805] R10: 0000000000000000 R11: 0000000000000217 R12: 0000556b1e3b4260
[  667.125199][ T9805] R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000
[  667.125207][ T9805]  </TASK>
[  667.125210][ T9805]
[  667.145632][ T9805] Allocated by task 9805:
[  667.145991][ T9805]  kasan_save_stack+0x20/0x40
[  667.146352][ T9805]  kasan_save_track+0x14/0x30
[  667.146717][ T9805]  __kasan_kmalloc+0xaa/0xb0
[  667.147065][ T9805]  __kmalloc_noprof+0x205/0x550
[  667.147448][ T9805]  hfsplus_find_init+0x95/0x1f0
[  667.147813][ T9805]  hfsplus_readdir+0x220/0xfc0
[  667.148174][ T9805]  iterate_dir+0x296/0xb20
[  667.148549][ T9805]  __x64_sys_getdents64+0x13c/0x2c0
[  667.148937][ T9805]  do_syscall_64+0xc9/0x480
[  667.149291][ T9805]  entry_SYSCALL_64_after_hwframe+0x77/0x7f
[  667.149809][ T9805]
[  667.150030][ T9805] The buggy address belongs to the object at ffff88802592f000
[  667.150030][ T9805]  which belongs to the cache kmalloc-2k of size 2048
[  667.151282][ T9805] The buggy address is located 0 bytes to the right of
[  667.151282][ T9805]  allocated 1036-byte region [ffff88802592f000, ffff88802592f40c)
[  667.152580][ T9805]
[  667.152798][ T9805] The buggy address belongs to the physical page:
[  667.153373][ T9805] page: refcount:0 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x25928
[  667.154157][ T9805] head: order:3 mapcount:0 entire_mapcount:0 nr_pages_mapped:0 pincount:0
[  667.154916][ T9805] anon flags: 0xfff00000000040(head|node=0|zone=1|lastcpupid=0x7ff)
[  667.155631][ T9805] page_type: f5(slab)
[  667.155997][ T9805] raw: 00fff00000000040 ffff88801b442f00 0000000000000000 dead000000000001
[  667.156770][ T9805] raw: 0000000000000000 0000000080080008 00000000f5000000 0000000000000000
[  667.157536][ T9805] head: 00fff00000000040 ffff88801b442f00 0000000000000000 dead000000000001
[  667.158317][ T9805] head: 0000000000000000 0000000080080008 00000000f5000000 0000000000000000
[  667.159088][ T9805] head: 00fff00000000003 ffffea0000964a01 00000000ffffffff 00000000ffffffff
[  667.159865][ T9805] head: ffffffffffffffff 0000000000000000 00000000ffffffff 0000000000000008
[  667.160643][ T9805] page dumped because: kasan: bad access detected
[  667.161216][ T9805] page_owner tracks the page as allocated
[  667.161732][ T9805] page last allocated via order 3, migratetype Unmovable, gfp_mask 0xd20c0(__GFP_IO|__GFP_FS|__GFP_NOWARN9
[  667.163566][ T9805]  post_alloc_hook+0x1c0/0x230
[  667.164003][ T9805]  get_page_from_freelist+0xdeb/0x3b30
[  667.164503][ T9805]  __alloc_frozen_pages_noprof+0x25c/0x2460
[  667.165040][ T9805]  alloc_pages_mpol+0x1fb/0x550
[  667.165489][ T9805]  new_slab+0x23b/0x340
[  667.165872][ T9805]  ___slab_alloc+0xd81/0x1960
[  667.166313][ T9805]  __slab_alloc.isra.0+0x56/0xb0
[  667.166767][ T9805]  __kmalloc_cache_noprof+0x255/0x3e0
[  667.167255][ T9805]  psi_cgroup_alloc+0x52/0x2d0
[  667.167693][ T9805]  cgroup_mkdir+0x694/0x1210
[  667.168118][ T9805]  kernfs_iop_mkdir+0x111/0x190
[  667.168568][ T9805]  vfs_mkdir+0x59b/0x8d0
[  667.168956][ T9805]  do_mkdirat+0x2ed/0x3d0
[  667.169353][ T9805]  __x64_sys_mkdir+0xef/0x140
[  667.169784][ T9805]  do_syscall_64+0xc9/0x480
[  667.170195][ T9805]  entry_SYSCALL_64_after_hwframe+0x77/0x7f
[  667.170730][ T9805] page last free pid 1257 tgid 1257 stack trace:
[  667.171304][ T9805]  __free_frozen_pages+0x80c/0x1250
[  667.171770][ T9805]  vfree.part.0+0x12b/0xab0
[  667.172182][ T9805]  delayed_vfree_work+0x93/0xd0
[  667.172612][ T9805]  process_one_work+0x9b5/0x1b80
[  667.173067][ T9805]  worker_thread+0x630/0xe60
[  667.173486][ T9805]  kthread+0x3a8/0x770
[  667.173857][ T9805]  ret_from_fork+0x517/0x6e0
[  667.174278][ T9805]  ret_from_fork_asm+0x1a/0x30
[  667.174703][ T9805]
[  667.174917][ T9805] Memory state around the buggy address:
[  667.175411][ T9805]  ffff88802592f300: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
[  667.176114][ T9805]  ffff88802592f380: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
[  667.176830][ T9805] >ffff88802592f400: 00 04 fc fc fc fc fc fc fc fc fc fc fc fc fc fc
[  667.177547][ T9805]                       ^
[  667.177933][ T9805]  ffff88802592f480: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
[  667.178640][ T9805]  ffff88802592f500: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
[  667.179350][ T9805] ==================================================================

The hfsplus_uni2asc() method operates by struct hfsplus_unistr:

struct hfsplus_unistr {
	__be16 length;
	hfsplus_unichr unicode[HFSPLUS_MAX_STRLEN];
} __packed;

where HFSPLUS_MAX_STRLEN is 255 bytes. The issue happens if length of the structure instance has value bigger than 255 (for example, 65283). In such case, pointer on unicode buffer is going beyond of the allocated memory.

The patch fixes the issue by checking the length value of hfsplus_unistr instance and using 255 value in the case if length value is bigger than HFSPLUS_MAX_STRLEN. Potential reason of such situation could be a corruption of Catalog File b-tree's node.

---
 fs/hfsplus/unicode.c | 7 +++++++
 1 file changed, 7 insertions(+)
fs/hfsplus/unicode.c +7 -0
index 73342c925a4b..36b6cf2a3abb 100644
@@ -132,7 +132,14 @@ int hfsplus_uni2asc(struct super_block *sb,
 
 	op = astr;
 	ip = ustr->unicode;
+
 	ustrlen = be16_to_cpu(ustr->length);
+	if (ustrlen > HFSPLUS_MAX_STRLEN) {
+		ustrlen = HFSPLUS_MAX_STRLEN;
+		pr_err("invalid length %u has been corrected to %d\n",
+			be16_to_cpu(ustr->length), ustrlen);
+	}
+
 	len = *len_p;
 	ce1 = NULL;
 	compose = !test_bit(HFSPLUS_SB_NODECOMPOSE, &HFSPLUS_SB(sb)->flags);
Signature · 1 line
2.39.5
author maintainer
#215 lore raw

PATCH 213/523 hfsplus: dont use BUG_ON() in hfsplus_create_attributes_file()

In reply to Greg Kroah-Hartman

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

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

From: Tetsuo Handa <[email protected]>

[ Upstream commit c7c6363ca186747ebc2df10c8a1a51e66e0e32d9 ]

When the volume header contains erroneous values that do not reflect the actual state of the filesystem, hfsplus_fill_super() assumes that the attributes file is not yet created, which later results in hitting BUG_ON() when hfsplus_create_attributes_file() is called. Replace this BUG_ON() with -EIO error with a message to suggest running fsck tool.

---
 fs/hfsplus/xattr.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)
fs/hfsplus/xattr.c +5 -1
index d91f76ef18d9..2438cd759620 100644
@@ -172,7 +172,11 @@ static int hfsplus_create_attributes_file(struct super_block *sb)
 		return PTR_ERR(attr_file);
 	}
 
-	BUG_ON(i_size_read(attr_file) != 0);
+	if (i_size_read(attr_file) != 0) {
+		err = -EIO;
+		pr_err("detected inconsistent attributes file, running fsck.hfsplus is recommended.\n");
+		goto end_attr_file_creation;
+	}
 
 	hip = HFSPLUS_I(attr_file);
 
Signature · 1 line
2.39.5
author maintainer
#216 lore raw

PATCH 214/523 arm64: Handle KCOV __init vs inline mismatches

In reply to Greg Kroah-Hartman

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

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

From: Kees Cook <[email protected]>

[ Upstream commit 65c430906efffee9bd7551d474f01a6b1197df90 ]

GCC appears to have kind of fragile inlining heuristics, in the sense that it can change whether or not it inlines something based on optimizations. It looks like the kcov instrumentation being added (or in this case, removed) from a function changes the optimization results, and some functions marked "inline" are _not_ inlined. In that case, we end up with __init code calling a function not marked __init, and we get the build warnings I'm trying to eliminate in the coming patch that adds __no_sanitize_coverage to __init functions:

WARNING: modpost: vmlinux: section mismatch in reference: acpi_get_enable_method+0x1c (section: .text.unlikely) -> acpi_psci_present (section: .init.text)

This problem is somewhat fragile (though using either __always_inline or __init will deterministically solve it), but we've tripped over this before with GCC and the solution has usually been to just use __always_inline and move on.

For arm64 this requires forcing one ACPI function to be inlined with __always_inline.

---
 arch/arm64/include/asm/acpi.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
arch/arm64/include/asm/acpi.h +1 -1
index 702587fda70c..8cbbd08cc8c5 100644
@@ -128,7 +128,7 @@ acpi_set_mailbox_entry(int cpu, struct acpi_madt_generic_interrupt *processor)
 {}
 #endif
 
-static inline const char *acpi_get_enable_method(int cpu)
+static __always_inline const char *acpi_get_enable_method(int cpu)
 {
 	if (acpi_psci_present())
 		return "psci";
Signature · 1 line
2.39.5
author maintainer
#217 lore raw

PATCH 215/523 udf: Verify partition map count

In reply to Greg Kroah-Hartman

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

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

From: Jan Kara <[email protected]>

[ Upstream commit 1a11201668e8635602577dcf06f2e96c591d8819 ]

Verify that number of partition maps isn't insanely high which can lead to large allocation in udf_sb_alloc_partition_maps(). All partition maps have to fit in the LVD which is in a single block.

---
 fs/udf/super.c | 13 +++++++++++--
 1 file changed, 11 insertions(+), 2 deletions(-)
fs/udf/super.c +11 -2
index 8dae5e73a00b..723184b1201f 100644
@@ -1410,7 +1410,7 @@ static int udf_load_logicalvol(struct super_block *sb, sector_t block,
 	struct genericPartitionMap *gpm;
 	uint16_t ident;
 	struct buffer_head *bh;
-	unsigned int table_len;
+	unsigned int table_len, part_map_count;
 	int ret;
 
 	bh = udf_read_tagged(sb, block, block, &ident);
@@ -1431,7 +1431,16 @@ static int udf_load_logicalvol(struct super_block *sb, sector_t block,
 					   "logical volume");
 	if (ret)
 		goto out_bh;
-	ret = udf_sb_alloc_partition_maps(sb, le32_to_cpu(lvd->numPartitionMaps));
+
+	part_map_count = le32_to_cpu(lvd->numPartitionMaps);
+	if (part_map_count > table_len / sizeof(struct genericPartitionMap1)) {
+		udf_err(sb, "error loading logical volume descriptor: "
+			"Too many partition maps (%u > %u)\n", part_map_count,
+			table_len / (unsigned)sizeof(struct genericPartitionMap1));
+		ret = -EIO;
+		goto out_bh;
+	}
+	ret = udf_sb_alloc_partition_maps(sb, part_map_count);
 	if (ret)
 		goto out_bh;
 
Signature · 1 line
2.39.5
author maintainer
#218 lore raw

PATCH 216/523 drbd: add missing kref_get in handle_write_conflicts

In reply to Greg Kroah-Hartman

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

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

From: Sarah Newman <[email protected]>

[ Upstream commit 00c9c9628b49e368d140cfa61d7df9b8922ec2a8 ]

With two-primaries enabled, DRBD tries to detect "concurrent" writes and handle write conflicts, so that even if you write to the same sector simultaneously on both nodes, they end up with the identical data once the writes are completed.

In handling "superseeded" writes, we forgot a kref_get, resulting in a premature drbd_destroy_device and use after free, and further to kernel crashes with symptoms.

Relevance: No one should use DRBD as a random data generator, and apparently all users of "two-primaries" handle concurrent writes correctly on layer up. That is cluster file systems use some distributed lock manager, and live migration in virtualization environments stops writes on one node before starting writes on the other node.

Which means that other than for "test cases",
this code path is never taken in real life.

FYI, in DRBD 9, things are handled differently nowadays. We still detect "write conflicts", but no longer try to be smart about them.
We decided to disconnect hard instead: upper layers must not submit concurrent writes. If they do, that's their fault.

---
 drivers/block/drbd/drbd_receiver.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)
drivers/block/drbd/drbd_receiver.c +5 -1
index 405e09575f08..b4d4e4a41b08 100644
@@ -2532,7 +2532,11 @@ static int handle_write_conflicts(struct drbd_device *device,
 			peer_req->w.cb = superseded ? e_send_superseded :
 						   e_send_retry_write;
 			list_add_tail(&peer_req->w.list, &device->done_ee);
-			queue_work(connection->ack_sender, &peer_req->peer_device->send_acks_work);
+			/* put is in drbd_send_acks_wf() */
+			kref_get(&device->kref);
+			if (!queue_work(connection->ack_sender,
+					&peer_req->peer_device->send_acks_work))
+				kref_put(&device->kref, drbd_destroy_device);
 
 			err = -ENOENT;
 			goto out;
Signature · 1 line
2.39.5
author maintainer
#219 lore raw

PATCH 217/523 hfs: fix not erasing deleted b-tree node issue

In reply to Greg Kroah-Hartman

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

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

From: Viacheslav Dubeyko <[email protected]>

[ Upstream commit d3ed6d6981f4756f145766753c872482bc3b28d3 ]

The generic/001 test of xfstests suite fails and corrupts the HFS volume:

sudo ./check generic/001

FSTYP         -- hfs
PLATFORM      -- Linux/x86_64 hfsplus-testing-0001 6.15.0-rc2+ #3 SMP PREEMPT_DYNAMIC Fri Apr 25 17:13:00 PDT 2>
MKFS_OPTIONS  -- /dev/loop51

MOUNT_OPTIONS -- /dev/loop51 /mnt/scratch

generic/001 32s ... _check_generic_filesystem: filesystem on /dev/loop50 is inconsistent (see /home/slavad/XFSTESTS-2/xfstests-dev/results//generic/001.full for details)

Ran: generic/001
Failures: generic/001
Failed 1 of 1 tests

fsck.hfs -d -n ./test-image.bin
** ./test-image.bin (NO WRITE)
Using cacheBlockSize=32K cacheTotalBlock=1024 cacheSize=32768K.
Executing fsck_hfs (version 540.1-Linux).
** Checking HFS volume.
The volume name is untitled
** Checking extents overflow file.
** Checking catalog file.
Unused node is not erased (node = 2)
Unused node is not erased (node = 4)
<skipped>
Unused node is not erased (node = 253)
Unused node is not erased (node = 254)
Unused node is not erased (node = 255)
Unused node is not erased (node = 256)
** Checking catalog hierarchy.
** Checking volume bitmap.
** Checking volume information.
Verify Status: VIStat = 0x0000, ABTStat = 0x0000 EBTStat = 0x0000

                  CBTStat = 0x0004 CatStat = 0x00000000
** The volume untitled was found corrupt and needs to be repaired.
	volume type is HFS
	primary MDB is at block 2 0x02
	alternate MDB is at block 20971518 0x13ffffe
	primary VHB is at block 0 0x00
	alternate VHB is at block 0 0x00
	sector size = 512 0x200
	VolumeObject flags = 0x19
	total sectors for volume = 20971520 0x1400000
	total sectors for embedded volume = 0 0x00

This patch adds logic of clearing the deleted b-tree node.

sudo ./check generic/001

FSTYP         -- hfs
PLATFORM      -- Linux/x86_64 hfsplus-testing-0001 6.15.0-rc2+ #3 SMP PREEMPT_DYNAMIC Fri Apr 25 17:13:00 PDT 2025
MKFS_OPTIONS  -- /dev/loop51

MOUNT_OPTIONS -- /dev/loop51 /mnt/scratch

generic/001 9s ... 32s
Ran: generic/001
Passed all 1 tests

fsck.hfs -d -n ./test-image.bin
** ./test-image.bin (NO WRITE)
Using cacheBlockSize=32K cacheTotalBlock=1024 cacheSize=32768K.
Executing fsck_hfs (version 540.1-Linux).
** Checking HFS volume.
The volume name is untitled
** Checking extents overflow file.
** Checking catalog file.
** Checking catalog hierarchy.
** Checking volume bitmap.
** Checking volume information.
** The volume untitled appears to be OK.

---
 fs/hfs/bnode.c | 1 +
 1 file changed, 1 insertion(+)
fs/hfs/bnode.c +1 -0
index 2039cb6d5f66..219e3b8fd6a8 100644
@@ -586,6 +586,7 @@ void hfs_bnode_put(struct hfs_bnode *node)
 		if (test_bit(HFS_BNODE_DELETED, &node->flags)) {
 			hfs_bnode_unhash(node);
 			spin_unlock(&tree->hash_lock);
+			hfs_bnode_clear(node, 0, tree->node_size);
 			hfs_bmap_free(node);
 			hfs_bnode_free(node);
 			return;
Signature · 1 line
2.39.5
author maintainer
#220 lore raw

PATCH 218/523 better lockdep annotations for simple_recursive_removal()

In reply to Greg Kroah-Hartman

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

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

From: Al Viro <[email protected]>

[ Upstream commit 2a8061ee5e41034eb14170ec4517b5583dbeff9f ]

We want a class that nests outside of I_MUTEX_NORMAL (for the sake of callbacks that might want to lock the victim) and inside I_MUTEX_PARENT (so that a variant of that could be used with parent of the victim held locked by the caller).

In reality, simple_recursive_removal()
* never holds two locks at once
* holds the lock on parent of dentry passed to callback
* is used only on the trees with fixed topology, so the depths
are not changing.

So the locking order is actually fine.

AFAICS, the best solution is to assign I_MUTEX_CHILD to the locks grabbed by that thing.

---
 fs/libfs.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)
fs/libfs.c +2 -2
index aa0fbd720409..c6ed6c58dee6 100644
@@ -272,7 +272,7 @@ void simple_recursive_removal(struct dentry *dentry,
 		struct dentry *victim = NULL, *child;
 		struct inode *inode = this->d_inode;
 
-		inode_lock(inode);
+		inode_lock_nested(inode, I_MUTEX_CHILD);
 		if (d_is_dir(this))
 			inode->i_flags |= S_DEAD;
 		while ((child = find_next_child(this, victim)) == NULL) {
@@ -284,7 +284,7 @@ void simple_recursive_removal(struct dentry *dentry,
 			victim = this;
 			this = this->d_parent;
 			inode = this->d_inode;
-			inode_lock(inode);
+			inode_lock_nested(inode, I_MUTEX_CHILD);
 			if (simple_positive(victim)) {
 				d_invalidate(victim);	// avoid lost mounts
 				if (d_is_dir(victim))
Signature · 1 line
2.39.5
author maintainer
#221 lore raw

PATCH 219/523 ata: libata-sata: Disallow changing LPM state if not supported

In reply to Greg Kroah-Hartman

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

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

From: Damien Le Moal <[email protected]>

[ Upstream commit 413e800cadbf67550d76c77c230b2ecd96bce83a ]

Modify ata_scsi_lpm_store() to return an error if a user attempts to set a link power management policy for a port that does not support LPM, that is, ports flagged with ATA_FLAG_NO_LPM.

---
 drivers/ata/libata-sata.c | 5 +++++
 1 file changed, 5 insertions(+)
drivers/ata/libata-sata.c +5 -0
index 45656067c547..d5c97dba2dd4 100644
@@ -815,6 +815,11 @@ static ssize_t ata_scsi_lpm_store(struct device *device,
 
 	spin_lock_irqsave(ap->lock, flags);
 
+	if (ap->flags & ATA_FLAG_NO_LPM) {
+		count = -EOPNOTSUPP;
+		goto out_unlock;
+	}
+
 	ata_for_each_link(link, ap, EDGE) {
 		ata_for_each_dev(dev, &ap->link, ENABLED) {
 			if (dev->horkage & ATA_HORKAGE_NOLPM) {
Signature · 1 line
2.39.5
author maintainer
#222 lore raw

PATCH 220/523 securityfs: dont pin dentries twice, once is enough...

In reply to Greg Kroah-Hartman

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

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

From: Al Viro <[email protected]>

[ Upstream commit 27cd1bf1240d482e4f02ca4f9812e748f3106e4f ]

incidentally, securityfs_recursive_remove() is broken without that - it leaks dentries, since simple_recursive_removal() does not expect anything of that sort. It could be worked around by dput() in remove_one() callback, but it's easier to just drop that double-get stuff.

---
 security/inode.c | 2 --
 1 file changed, 2 deletions(-)
security/inode.c +0 -2
index 6c326939750d..e6e07787eec9 100644
@@ -159,7 +159,6 @@ static struct dentry *securityfs_create_dentry(const char *name, umode_t mode,
 		inode->i_fop = fops;
 	}
 	d_instantiate(dentry, inode);
-	dget(dentry);
 	inode_unlock(dir);
 	return dentry;
 
@@ -306,7 +305,6 @@ void securityfs_remove(struct dentry *dentry)
 			simple_rmdir(dir, dentry);
 		else
 			simple_unlink(dir, dentry);
-		dput(dentry);
 	}
 	inode_unlock(dir);
 	simple_release_fs(&mount, &mount_count);
Signature · 1 line
2.39.5
author maintainer
#223 lore raw

PATCH 221/523 usb: xhci: print xhci->xhc_state when queue_command failed

In reply to Greg Kroah-Hartman

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

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

From: Su Hui <[email protected]>

[ Upstream commit 7919407eca2ef562fa6c98c41cfdf6f6cdd69d92 ]

When encounters some errors like these:
xhci_hcd 0000:4a:00.2: xHCI dying or halted, can't queue_command xhci_hcd 0000:4a:00.2: FIXME: allocate a command ring segment usb usb5-port6: couldn't allocate usb_device

It's hard to know whether xhc_state is dying or halted. So it's better to print xhc_state's value which can help locate the resaon of the bug.

---
 drivers/usb/host/xhci-ring.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)
drivers/usb/host/xhci-ring.c +2 -1
index 954cd962e113..c026e7cc0af1 100644
@@ -4183,7 +4183,8 @@ static int queue_command(struct xhci_hcd *xhci, struct xhci_command *cmd,
 
 	if ((xhci->xhc_state & XHCI_STATE_DYING) ||
 		(xhci->xhc_state & XHCI_STATE_HALTED)) {
-		xhci_dbg(xhci, "xHCI dying or halted, can't queue_command\n");
+		xhci_dbg(xhci, "xHCI dying or halted, can't queue_command. state: 0x%x\n",
+			 xhci->xhc_state);
 		return -ESHUTDOWN;
 	}
 
Signature · 1 line
2.39.5
author maintainer
#224 lore raw

PATCH 222/523 cpufreq: CPPC: Mark driver with NEED_UPDATE_LIMITS flag

In reply to Greg Kroah-Hartman

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

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

From: Prashant Malani <[email protected]>

[ Upstream commit 0a1416a49e63c320f6e6c1c8d07e1b58c0d4a3f3 ]

AMU counters on certain CPPC-based platforms tend to yield inaccurate delivered performance measurements on systems that are idle/mostly idle. This results in an inaccurate frequency being stored by cpufreq in its policy structure when the CPU is brought online. [1]

Consequently, if the userspace governor tries to set the frequency to a new value, there is a possibility that it would be the erroneous value stored earlier. In such a scenario, cpufreq would assume that the requested frequency has already been set and return early, resulting in the correct/new frequency request never making it to the hardware.

Since the operating frequency is liable to this sort of inconsistency, mark the CPPC driver with CPUFREQ_NEED_UPDATE_LIMITS so that it is always invoked when a target frequency update is requested.

---
 drivers/cpufreq/cppc_cpufreq.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/cpufreq/cppc_cpufreq.c +1 -1
index f29e8d0553a8..17e712651090 100644
@@ -396,7 +396,7 @@ static int cppc_cpufreq_set_boost(struct cpufreq_policy *policy, int state)
 }
 
 static struct cpufreq_driver cppc_cpufreq_driver = {
-	.flags = CPUFREQ_CONST_LOOPS,
+	.flags = CPUFREQ_CONST_LOOPS | CPUFREQ_NEED_UPDATE_LIMITS,
 	.verify = cppc_verify_policy,
 	.target = cppc_cpufreq_set_target,
 	.get = cppc_cpufreq_get_rate,
Signature · 1 line
2.39.5
author maintainer
#225 lore raw

PATCH 223/523 selftests/futex: Define SYS_futex on 32-bit architectures with 64-bit time_t

In reply to Greg Kroah-Hartman

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

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

From: Cynthia Huang <[email protected]>

[ Upstream commit 04850819c65c8242072818655d4341e70ae998b5 ]

The kernel does not provide sys_futex() on 32-bit architectures that do not support 32-bit time representations, such as riscv32.

As a result, glibc cannot define SYS_futex, causing compilation failures in tests that rely on this syscall. Define SYS_futex as SYS_futex_time64 in such cases to ensure successful compilation and compatibility.

---
 tools/testing/selftests/futex/include/futextest.h | 11 +++++++++++
 1 file changed, 11 insertions(+)
tools/testing/selftests/futex/include/futextest.h +11 -0
index ddbcfc9b7bac..7a5fd1d5355e 100644
@@ -47,6 +47,17 @@ typedef volatile u_int32_t futex_t;
 					 FUTEX_PRIVATE_FLAG)
 #endif
 
+/*
+ * SYS_futex is expected from system C library, in glibc some 32-bit
+ * architectures (e.g. RV32) are using 64-bit time_t, therefore it doesn't have
+ * SYS_futex defined but just SYS_futex_time64. Define SYS_futex as
+ * SYS_futex_time64 in this situation to ensure the compilation and the
+ * compatibility.
+ */
+#if !defined(SYS_futex) && defined(SYS_futex_time64)
+#define SYS_futex SYS_futex_time64
+#endif
+
 /**
  * futex() - SYS_futex syscall wrapper
  * @uaddr:	address of first futex
Signature · 1 line
2.39.5
author maintainer
#226 lore raw

PATCH 224/523 usb: typec: ucsi: psy: Set current max to 100mA for BC 1.2 and Default

In reply to Greg Kroah-Hartman

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

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

From: Benson Leung <[email protected]>

[ Upstream commit af833e7f7db3cf4c82f063668e1b52297a30ec18 ]

ucsi_psy_get_current_max would return 0mA as the maximum current if UCSI detected a BC or a Default USB Power sporce.

The comment in this function is true that we can't tell the difference between DCP/CDP or SDP chargers, but we can guarantee that at least 1-unit of USB 1.1/2.0 power is available, which is 100mA, which is a better fallback value than 0, which causes some userspaces, including the ChromeOS power manager, to regard this as a power source that is not providing any power.

In reality, 100mA is guaranteed from all sources in these classes.

---
 drivers/usb/typec/ucsi/psy.c  | 2 +-
 drivers/usb/typec/ucsi/ucsi.h | 7 ++++---
 2 files changed, 5 insertions(+), 4 deletions(-)
drivers/usb/typec/ucsi/psy.c +1 -1
index 571a51e16234..ba5f797156dc 100644
@@ -142,7 +142,7 @@ static int ucsi_psy_get_current_max(struct ucsi_connector *con,
 	case UCSI_CONSTAT_PWR_OPMODE_DEFAULT:
 	/* UCSI can't tell b/w DCP/CDP or USB2/3x1/3x2 SDP chargers */
 	default:
-		val->intval = 0;
+		val->intval = UCSI_TYPEC_DEFAULT_CURRENT * 1000;
 		break;
 	}
 	return 0;
drivers/usb/typec/ucsi/ucsi.h +4 -3
index f75b1e2c05fe..ed8fcd7ecf21 100644
@@ -305,9 +305,10 @@ struct ucsi {
 #define UCSI_MAX_SVID		5
 #define UCSI_MAX_ALTMODES	(UCSI_MAX_SVID * 6)
 
-#define UCSI_TYPEC_VSAFE5V	5000
-#define UCSI_TYPEC_1_5_CURRENT	1500
-#define UCSI_TYPEC_3_0_CURRENT	3000
+#define UCSI_TYPEC_VSAFE5V		5000
+#define UCSI_TYPEC_DEFAULT_CURRENT	 100
+#define UCSI_TYPEC_1_5_CURRENT		1500
+#define UCSI_TYPEC_3_0_CURRENT		3000
 
 struct ucsi_connector {
 	int num;
Signature · 1 line
2.39.5
author maintainer
#227 lore raw

PATCH 225/523 usb: xhci: Avoid showing warnings for dying controller

In reply to Greg Kroah-Hartman

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

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

From: Mario Limonciello <[email protected]>

[ Upstream commit 65fc0fc137b5da3ee1f4ca4f61050fcb203d7582 ]

When a USB4 dock is unplugged from a system it won't respond to ring events. The PCI core handles the surprise removal event and notifies all PCI drivers. The XHCI PCI driver sets a flag that the device is being removed, and when the device stops responding a flag is also added to indicate it's dying.

When that flag is set don't bother to show warnings about a missing controller.

---
 drivers/usb/host/xhci.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)
drivers/usb/host/xhci.c +4 -2
index 908445cff24f..235824d1822a 100644
@@ -118,7 +118,8 @@ int xhci_halt(struct xhci_hcd *xhci)
 	ret = xhci_handshake(&xhci->op_regs->status,
 			STS_HALT, STS_HALT, XHCI_MAX_HALT_USEC);
 	if (ret) {
-		xhci_warn(xhci, "Host halt failed, %d\n", ret);
+		if (!(xhci->xhc_state & XHCI_STATE_DYING))
+			xhci_warn(xhci, "Host halt failed, %d\n", ret);
 		return ret;
 	}
 	xhci->xhc_state |= XHCI_STATE_HALTED;
@@ -175,7 +176,8 @@ int xhci_reset(struct xhci_hcd *xhci, u64 timeout_us)
 	state = readl(&xhci->op_regs->status);
 
 	if (state == ~(u32)0) {
-		xhci_warn(xhci, "Host not accessible, reset failed.\n");
+		if (!(xhci->xhc_state & XHCI_STATE_DYING))
+			xhci_warn(xhci, "Host not accessible, reset failed.\n");
 		return -ENODEV;
 	}
 
Signature · 1 line
2.39.5
author maintainer
#228 lore raw

PATCH 226/523 usb: xhci: Set avg_trb_len = 8 for EP0 during Address Device Command

In reply to Greg Kroah-Hartman

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

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

From: Jay Chen <[email protected]>

[ Upstream commit f72b9aa821a2bfe4b6dfec4be19f264d0673b008 ]

There is a subtle contradiction between sections of the xHCI 1.2 spec regarding the initialization of Input Endpoint Context fields. Section 4.8.2 ("Endpoint Context Initialization") states that all fields should be initialized to 0. However, Section 6.2.3 ("Endpoint Context", p.453) specifies that the Average TRB Length (avg_trb_len) field shall be greater than 0, and explicitly notes (p.454): "Software shall set Average TRB Length to '8' for control endpoints."

Strictly setting all fields to 0 during initialization conflicts with the specific recommendation for control endpoints. In practice, setting avg_trb_len = 0 is not meaningful for the hardware/firmware, as the value is used for bandwidth calculation.

Motivation: Our company is developing a custom Virtual xHC hardware platform that strictly follows the xHCI spec and its recommendations. During validation, we observed that enumeration fails and a parameter error (TRB Completion Code = 5) is reported if avg_trb_len for EP0 is not set to 8 as recommended by Section 6.2.3. This demonstrates the importance of assigning a meaningful, non-zero value to avg_trb_len, even in virtualized or emulated environments.

This patch explicitly sets avg_trb_len to 8 for EP0 in xhci_setup_addressable_virt_dev(), as recommended in Section 6.2.3, to prevent potential issues with xHCI host controllers that enforce the spec strictly.

---
 drivers/usb/host/xhci-mem.c | 2 ++
 1 file changed, 2 insertions(+)
drivers/usb/host/xhci-mem.c +2 -0
index 5b0e00978322..1874a81d9766 100644
@@ -1227,6 +1227,8 @@ int xhci_setup_addressable_virt_dev(struct xhci_hcd *xhci, struct usb_device *ud
 	ep0_ctx->deq = cpu_to_le64(dev->eps[0].ring->first_seg->dma |
 				   dev->eps[0].ring->cycle_state);
 
+	ep0_ctx->tx_info = cpu_to_le32(EP_AVG_TRB_LENGTH(8));
+
 	trace_xhci_setup_addressable_virt_device(dev);
 
 	/* Steps 7 and 8 were done in xhci_alloc_virt_device() */
Signature · 1 line
2.39.5
author maintainer
#229 lore raw

PATCH 227/523 usb: xhci: Avoid showing errors during surprise removal

In reply to Greg Kroah-Hartman

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

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

From: Mario Limonciello <[email protected]>

[ Upstream commit 4b9c60e440525b729ac5f071e00bcee12e0a7e84 ]

When a USB4 dock is unplugged from a system it won't respond to ring events. The PCI core handles the surprise removal event and notifies all PCI drivers. The XHCI PCI driver sets a flag that the device is being removed as well.

When that flag is set don't show messages in the cleanup path for marking the controller dead.

---
 drivers/usb/host/xhci-ring.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)
drivers/usb/host/xhci-ring.c +5 -2
index c026e7cc0af1..a65ad8e760d0 100644
@@ -1094,12 +1094,15 @@ static void xhci_kill_endpoint_urbs(struct xhci_hcd *xhci,
  */
 void xhci_hc_died(struct xhci_hcd *xhci)
 {
+	bool notify;
 	int i, j;
 
 	if (xhci->xhc_state & XHCI_STATE_DYING)
 		return;
 
-	xhci_err(xhci, "xHCI host controller not responding, assume dead\n");
+	notify = !(xhci->xhc_state & XHCI_STATE_REMOVING);
+	if (notify)
+		xhci_err(xhci, "xHCI host controller not responding, assume dead\n");
 	xhci->xhc_state |= XHCI_STATE_DYING;
 
 	xhci_cleanup_command_queue(xhci);
@@ -1113,7 +1116,7 @@ void xhci_hc_died(struct xhci_hcd *xhci)
 	}
 
 	/* inform usb core hc died if PCI remove isn't already handling it */
-	if (!(xhci->xhc_state & XHCI_STATE_REMOVING))
+	if (notify)
 		usb_hc_died(xhci_to_hcd(xhci));
 }
 
Signature · 1 line
2.39.5
author maintainer
#230 lore raw

PATCH 228/523 gpio: wcd934x: check the return value of regmap_update_bits()

In reply to Greg Kroah-Hartman

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

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

From: Bartosz Golaszewski <[email protected]>

[ Upstream commit ff0f0d7c6587e38c308be9905e36f86e98fb9c1f ]

regmap_update_bits() can fail so check its return value in wcd_gpio_direction_output() for consistency with the rest of the code and propagate any errors.

---
 drivers/gpio/gpio-wcd934x.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)
drivers/gpio/gpio-wcd934x.c +5 -2
index 97e6caedf1f3..c00968ce7a56 100644
@@ -45,9 +45,12 @@ static int wcd_gpio_direction_output(struct gpio_chip *chip, unsigned int pin,
 				     int val)
 {
 	struct wcd_gpio_data *data = gpiochip_get_data(chip);
+	int ret;
 
-	regmap_update_bits(data->map, WCD_REG_DIR_CTL_OFFSET,
-			   WCD_PIN_MASK(pin), WCD_PIN_MASK(pin));
+	ret = regmap_update_bits(data->map, WCD_REG_DIR_CTL_OFFSET,
+				 WCD_PIN_MASK(pin), WCD_PIN_MASK(pin));
+	if (ret)
+		return ret;
 
 	return regmap_update_bits(data->map, WCD_REG_VAL_CTL_OFFSET,
 				  WCD_PIN_MASK(pin),
Signature · 1 line
2.39.5
author maintainer
#231 lore raw

PATCH 229/523 cpufreq: Exit governor when failed to start old governor

In reply to Greg Kroah-Hartman

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

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

From: Lifeng Zheng <[email protected]>

[ Upstream commit 0ae204405095abfbc2d694ee0fbb49bcbbe55c57 ]

Detect the result of starting old governor in cpufreq_set_policy(). If it fails, exit the governor and clear policy->governor.

---
 drivers/cpufreq/cpufreq.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)
drivers/cpufreq/cpufreq.c +5 -3
index d1277f98d1fd..149ba2e39a96 100644
@@ -2545,10 +2545,12 @@ static int cpufreq_set_policy(struct cpufreq_policy *policy,
 	pr_debug("starting governor %s failed\n", policy->governor->name);
 	if (old_gov) {
 		policy->governor = old_gov;
-		if (cpufreq_init_governor(policy))
+		if (cpufreq_init_governor(policy)) {
 			policy->governor = NULL;
-		else
-			cpufreq_start_governor(policy);
+		} else if (cpufreq_start_governor(policy)) {
+			cpufreq_exit_governor(policy);
+			policy->governor = NULL;
+		}
 	}
 
 	return ret;
Signature · 1 line
2.39.5
author maintainer
#232 lore raw

PATCH 230/523 ARM: rockchip: fix kernel hang during smp initialization

In reply to Greg Kroah-Hartman

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

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

From: Alexander Kochetkov <[email protected]>

[ Upstream commit 7cdb433bb44cdc87dc5260cdf15bf03cc1cd1814 ]

In order to bring up secondary CPUs main CPU write trampoline code to SRAM. The trampoline code is written while secondary CPUs are powered on (at least that true for RK3188 CPU). Sometimes that leads to kernel hang. Probably because secondary CPU execute trampoline code while kernel doesn't expect.

The patch moves SRAM initialization step to the point where all secondary CPUs are powered down.

That fixes rarely hangs on RK3188:

[    0.091568] CPU0: thread -1, cpu 0, socket 0, mpidr 80000000
[    0.091996] rockchip_smp_prepare_cpus: ncores 4
---
 arch/arm/mach-rockchip/platsmp.c | 15 +++++++++------
 1 file changed, 9 insertions(+), 6 deletions(-)
arch/arm/mach-rockchip/platsmp.c +9 -6
index d60856898d97..17aee4701e81 100644
@@ -279,11 +279,6 @@ static void __init rockchip_smp_prepare_cpus(unsigned int max_cpus)
 	}
 
 	if (read_cpuid_part() == ARM_CPU_PART_CORTEX_A9) {
-		if (rockchip_smp_prepare_sram(node)) {
-			of_node_put(node);
-			return;
-		}
-
 		/* enable the SCU power domain */
 		pmu_set_power_domain(PMU_PWRDN_SCU, true);
 
@@ -316,11 +311,19 @@ static void __init rockchip_smp_prepare_cpus(unsigned int max_cpus)
 		asm ("mrc p15, 1, %0, c9, c0, 2\n" : "=r" (l2ctlr));
 		ncores = ((l2ctlr >> 24) & 0x3) + 1;
 	}
-	of_node_put(node);
 
 	/* Make sure that all cores except the first are really off */
 	for (i = 1; i < ncores; i++)
 		pmu_set_power_domain(0 + i, false);
+
+	if (read_cpuid_part() == ARM_CPU_PART_CORTEX_A9) {
+		if (rockchip_smp_prepare_sram(node)) {
+			of_node_put(node);
+			return;
+		}
+	}
+
+	of_node_put(node);
 }
 
 static void __init rk3036_smp_prepare_cpus(unsigned int max_cpus)
Signature · 1 line
2.39.5
author maintainer
#233 lore raw

PATCH 231/523 PM / devfreq: governor: Replace sscanf() with kstrtoul() in set_freq_store()

In reply to Greg Kroah-Hartman

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

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

From: Lifeng Zheng <[email protected]>

[ Upstream commit 914cc799b28f17d369d5b4db3b941957d18157e8 ]

Replace sscanf() with kstrtoul() in set_freq_store() and check the result to avoid invalid input.

---
 drivers/devfreq/governor_userspace.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)
drivers/devfreq/governor_userspace.c +5 -1
index 8a9cf8220808..82c60dedcffd 100644
@@ -9,6 +9,7 @@
 #include <linux/slab.h>
 #include <linux/device.h>
 #include <linux/devfreq.h>
+#include <linux/kstrtox.h>
 #include <linux/pm.h>
 #include <linux/mutex.h>
 #include <linux/module.h>
@@ -39,10 +40,13 @@ static ssize_t store_freq(struct device *dev, struct device_attribute *attr,
 	unsigned long wanted;
 	int err = 0;
 
+	err = kstrtoul(buf, 0, &wanted);
+	if (err)
+		return err;
+
 	mutex_lock(&devfreq->lock);
 	data = devfreq->governor_data;
 
-	sscanf(buf, "%lu", &wanted);
 	data->user_frequency = wanted;
 	data->valid = true;
 	err = update_devfreq(devfreq);
Signature · 1 line
2.39.5
author maintainer
#234 lore raw

PATCH 232/523 ASoC: soc-dapm: set bias_level if snd_soc_dapm_set_bias_level() was successed

In reply to Greg Kroah-Hartman

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

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

From: Kuninori Morimoto <[email protected]>

[ Upstream commit f40ecc2743652c0b0f19935f81baf57c601eb7f0 ]

ASoC has 2 functions to set bias level.

	(A) snd_soc_dapm_force_bias_level()
	(B) snd_soc_dapm_set_bias_level()

snd_soc_dapm_force_bias_level() (A) will set dapm->bias_level (a) if successed.

(A) int snd_soc_dapm_force_bias_level(...)

	{
		...
		if (ret == 0)
(a)			dapm->bias_level = level;
		...
	}

snd_soc_dapm_set_bias_level() (B) is also a function that sets bias_level. It will call snd_soc_dapm_force_bias_level() (A) inside, but doesn't set dapm->bias_level by itself. One note is that (A) might not be called.

(B) static int snd_soc_dapm_set_bias_level(...)

	{
		...
		ret = snd_soc_card_set_bias_level(...);
		...
		if (dapm != &card->dapm)
(A)			ret = snd_soc_dapm_force_bias_level(...);
		...
		ret = snd_soc_card_set_bias_level_post(...);
		...
	}

dapm->bias_level will be set if (A) was called, but might not be set if (B) was called, even though it calles set_bias_level() function.

We should set dapm->bias_level if we calls
snd_soc_dapm_set_bias_level() (B), too.

---
 sound/soc/soc-dapm.c | 4 ++++
 1 file changed, 4 insertions(+)
sound/soc/soc-dapm.c +4 -0
index acb46e1f9c0a..175c8c264b62 100644
@@ -743,6 +743,10 @@ static int snd_soc_dapm_set_bias_level(struct snd_soc_dapm_context *dapm,
 out:
 	trace_snd_soc_bias_level_done(card, level);
 
+	/* success */
+	if (ret == 0)
+		snd_soc_dapm_init_bias_level(dapm, level);
+
 	return ret;
 }
 
Signature · 1 line
2.39.5
author maintainer
#235 lore raw

PATCH 233/523 gpio: tps65912: check the return value of regmap_update_bits()

In reply to Greg Kroah-Hartman

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

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

From: Bartosz Golaszewski <[email protected]>

[ Upstream commit a0b2a6bbff8c26aafdecd320f38f52c341d5cafa ]

regmap_update_bits() can fail, check its return value like we do elsewhere in the driver.

---
 drivers/gpio/gpio-tps65912.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)
drivers/gpio/gpio-tps65912.c +5 -2
index 510d9ed9fd2a..a8a2ad13e09e 100644
@@ -49,10 +49,13 @@ static int tps65912_gpio_direction_output(struct gpio_chip *gc,
 					  unsigned offset, int value)
 {
 	struct tps65912_gpio *gpio = gpiochip_get_data(gc);
+	int ret;
 
 	/* Set the initial value */
-	regmap_update_bits(gpio->tps->regmap, TPS65912_GPIO1 + offset,
-			   GPIO_SET_MASK, value ? GPIO_SET_MASK : 0);
+	ret = regmap_update_bits(gpio->tps->regmap, TPS65912_GPIO1 + offset,
+				 GPIO_SET_MASK, value ? GPIO_SET_MASK : 0);
+	if (ret)
+		return ret;
 
 	return regmap_update_bits(gpio->tps->regmap, TPS65912_GPIO1 + offset,
 				  GPIO_CFG_MASK, GPIO_CFG_MASK);
Signature · 1 line
2.39.5
author maintainer
#236 lore raw

PATCH 234/523 ARM: tegra: Use I/O memcpy to write to IRAM

In reply to Greg Kroah-Hartman

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

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

From: Aaron Kling <[email protected]>

[ Upstream commit 398e67e0f5ae04b29bcc9cbf342e339fe9d3f6f1 ]

Kasan crashes the kernel trying to check boundaries when using the normal memcpy.

---
 arch/arm/mach-tegra/reset.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
arch/arm/mach-tegra/reset.c +1 -1
index d5c805adf7a8..ea706fac6358 100644
@@ -63,7 +63,7 @@ static void __init tegra_cpu_reset_handler_enable(void)
 	BUG_ON(is_enabled);
 	BUG_ON(tegra_cpu_reset_handler_size > TEGRA_IRAM_RESET_HANDLER_SIZE);
 
-	memcpy(iram_base, (void *)__tegra_cpu_reset_handler_start,
+	memcpy_toio(iram_base, (void *)__tegra_cpu_reset_handler_start,
 			tegra_cpu_reset_handler_size);
 
 	err = call_firmware_op(set_cpu_boot_addr, 0, reset_address);
Signature · 1 line
2.39.5
author maintainer
#237 lore raw

PATCH 235/523 selftests: tracing: Use mutex_unlock for testing glob filter

In reply to Greg Kroah-Hartman

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

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

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

[ Upstream commit a089bb2822a49b0c5777a8936f82c1f8629231fb ]

Since commit c5b6ababd21a ("locking/mutex: implement mutex_trylock_nested") makes mutex_trylock() as an inlined function if CONFIG_DEBUG_LOCK_ALLOC=y, we can not use mutex_trylock() for testing the glob filter of ftrace.

Use mutex_unlock instead.

---
 .../testing/selftests/ftrace/test.d/ftrace/func-filter-glob.tc  | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
tools/testing/selftests/ftrace/test.d/ftrace/func-filter-glob.tc +1 -1
index 4b994b6df5ac..ed81eaf2afd6 100644
@@ -29,7 +29,7 @@ ftrace_filter_check 'schedule*' '^schedule.*$'
 ftrace_filter_check '*pin*lock' '.*pin.*lock$'
 
 # filter by start*mid*
-ftrace_filter_check 'mutex*try*' '^mutex.*try.*'
+ftrace_filter_check 'mutex*unl*' '^mutex.*unl.*'
 
 # Advanced full-glob matching feature is recently supported.
 # Skip the tests if we are sure the kernel does not support it.
Signature · 1 line
2.39.5
author maintainer
#238 lore raw

PATCH 236/523 PM: runtime: Clear power.needs_force_resume in pm_runtime_reinit()

In reply to Greg Kroah-Hartman

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

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

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

[ Upstream commit 89d9cec3b1e9c49bae9375a2db6dc49bc7468af0 ]

Clear power.needs_force_resume in pm_runtime_reinit() in case it has been set by pm_runtime_force_suspend() invoked from a driver remove callback.

---
 drivers/base/power/runtime.c | 5 +++++
 1 file changed, 5 insertions(+)
drivers/base/power/runtime.c +5 -0
index 58d376b1cd68..7e912d2ed427 100644
@@ -1716,6 +1716,11 @@ void pm_runtime_reinit(struct device *dev)
 				pm_runtime_put(dev->parent);
 		}
 	}
+	/*
+	 * Clear power.needs_force_resume in case it has been set by
+	 * pm_runtime_force_suspend() invoked from a driver remove callback.
+	 */
+	dev->power.needs_force_resume = false;
 }
 
 /**
Signature · 1 line
2.39.5
author maintainer
#239 lore raw

PATCH 237/523 thermal: sysfs: Return ENODATA instead of EAGAIN for reads

In reply to Greg Kroah-Hartman

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

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

From: Hsin-Te Yuan <[email protected]>

[ Upstream commit 1a4aabc27e95674837f2e25f4ef340c0469e6203 ]

According to POSIX spec, EAGAIN returned by read with O_NONBLOCK set means the read would block. Hence, the common implementation in nonblocking model will poll the file when the nonblocking read returns EAGAIN. However, when the target file is thermal zone, this mechanism will totally malfunction because thermal zone doesn't implement sysfs notification and thus the poll will never return.

For example, the read in Golang implemnts such method and sometimes hangs at reading some thermal zones via sysfs.

Change to return -ENODATA instead of -EAGAIN to userspace.

---
 drivers/thermal/thermal_sysfs.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)
drivers/thermal/thermal_sysfs.c +6 -3
index 05e9a3de80b5..d64af62abcc6 100644
@@ -39,10 +39,13 @@ temp_show(struct device *dev, struct device_attribute *attr, char *buf)
 
 	ret = thermal_zone_get_temp(tz, &temperature);
 
-	if (ret)
-		return ret;
+	if (!ret)
+		return sprintf(buf, "%d\n", temperature);
 
-	return sprintf(buf, "%d\n", temperature);
+	if (ret == -EAGAIN)
+		return -ENODATA;
+
+	return ret;
 }
 
 static ssize_t
Signature · 1 line
2.39.5
author maintainer
#240 lore raw

PATCH 238/523 PM: sleep: console: Fix the black screen issue

In reply to Greg Kroah-Hartman

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

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

From: tuhaowen <[email protected]>

[ Upstream commit 4266e8fa56d3d982bf451d382a410b9db432015c ]

When the computer enters sleep status without a monitor connected, the system switches the console to the virtual terminal tty63(SUSPEND_CONSOLE).

If a monitor is subsequently connected before waking up, the system skips the required VT restoration process during wake-up, leaving the console on tty63 instead of switching back to tty1.

To fix this issue, a global flag vt_switch_done is introduced to record whether the system has successfully switched to the suspend console via vt_move_to_console() during suspend.

If the switch was completed, vt_switch_done is set to 1. Later during resume, this flag is checked to ensure that the original console is restored properly by calling vt_move_to_console(orig_fgconsole, 0).

This prevents scenarios where the resume logic skips console restoration due to incorrect detection of the console state, especially when a monitor is reconnected before waking up.

---
 kernel/power/console.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)
kernel/power/console.c +6 -1
index fcdf0e14a47d..19c48aa5355d 100644
@@ -16,6 +16,7 @@
 #define SUSPEND_CONSOLE	(MAX_NR_CONSOLES-1)
 
 static int orig_fgconsole, orig_kmsg;
+static bool vt_switch_done;
 
 static DEFINE_MUTEX(vt_switch_mutex);
 
@@ -136,17 +137,21 @@ void pm_prepare_console(void)
 	if (orig_fgconsole < 0)
 		return;
 
+	vt_switch_done = true;
+
 	orig_kmsg = vt_kmsg_redirect(SUSPEND_CONSOLE);
 	return;
 }
 
 void pm_restore_console(void)
 {
-	if (!pm_vt_switch())
+	if (!pm_vt_switch() && !vt_switch_done)
 		return;
 
 	if (orig_fgconsole >= 0) {
 		vt_move_to_console(orig_fgconsole, 0);
 		vt_kmsg_redirect(orig_kmsg);
 	}
+
+	vt_switch_done = false;
 }
Signature · 1 line
2.39.5
author maintainer
#241 lore raw

PATCH 239/523 ACPI: processor: fix acpi_object initialization

In reply to Greg Kroah-Hartman

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

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

From: Sebastian Ott <[email protected]>

[ Upstream commit 13edf7539211d8f7d0068ce3ed143005f1da3547 ]

Initialization of the local acpi_object in acpi_processor_get_info() only sets the first 4 bytes to zero and is thus incomplete. This is indicated by messages like:

	acpi ACPI0007:be: Invalid PBLK length [166288104]

Fix this by initializing all 16 bytes of the processor member of that union.

---
 drivers/acpi/acpi_processor.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/acpi/acpi_processor.c +1 -1
index 707b2c37e5ee..74e949d340a1 100644
@@ -228,7 +228,7 @@ static inline int acpi_processor_hotadd_init(struct acpi_processor *pr)
 
 static int acpi_processor_get_info(struct acpi_device *device)
 {
-	union acpi_object object = { 0 };
+	union acpi_object object = { .processor = { 0 } };
 	struct acpi_buffer buffer = { sizeof(union acpi_object), &object };
 	struct acpi_processor *pr = acpi_driver_data(device);
 	int device_declaration = 0;
Signature · 1 line
2.39.5
author maintainer
#242 lore raw

PATCH 240/523 mmc: sdhci-msm: Ensure SD card power isnt ON when card removed

In reply to Greg Kroah-Hartman

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

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

From: Sarthak Garg <[email protected]>

[ Upstream commit db58532188ebf51d52b1d7693d9e94c76b926e9f ]

Many mobile phones feature multi-card tray designs, where the same tray is used for both SD and SIM cards. If the SD card is placed at the outermost location in the tray, the SIM card may come in contact with SD card power-supply while removing the tray, possibly resulting in SIM damage.

To prevent that, make sure the SD card is really inserted by reading the Card Detect pin state. If it's not, turn off the power in sdhci_msm_check_power_status() and also set the BUS_FAIL power state on the controller as part of pwr_irq handling for BUS_ON request.

---
 drivers/mmc/host/sdhci-msm.c | 14 ++++++++++++++
 1 file changed, 14 insertions(+)
drivers/mmc/host/sdhci-msm.c +14 -0
index c9298a986ef0..183617d56b44 100644
@@ -1544,6 +1544,7 @@ static void sdhci_msm_check_power_status(struct sdhci_host *host, u32 req_type)
 {
 	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
 	struct sdhci_msm_host *msm_host = sdhci_pltfm_priv(pltfm_host);
+	struct mmc_host *mmc = host->mmc;
 	bool done = false;
 	u32 val = SWITCHABLE_SIGNALING_VOLTAGE;
 	const struct sdhci_msm_offset *msm_offset =
@@ -1601,6 +1602,12 @@ static void sdhci_msm_check_power_status(struct sdhci_host *host, u32 req_type)
 				 "%s: pwr_irq for req: (%d) timed out\n",
 				 mmc_hostname(host->mmc), req_type);
 	}
+
+	if ((req_type & REQ_BUS_ON) && mmc->card && !mmc->ops->get_cd(mmc)) {
+		sdhci_writeb(host, 0, SDHCI_POWER_CONTROL);
+		host->pwr = 0;
+	}
+
 	pr_debug("%s: %s: request %d done\n", mmc_hostname(host->mmc),
 			__func__, req_type);
 }
@@ -1659,6 +1666,13 @@ static void sdhci_msm_handle_pwr_irq(struct sdhci_host *host, int irq)
 		udelay(10);
 	}
 
+	if ((irq_status & CORE_PWRCTL_BUS_ON) && mmc->card &&
+	    !mmc->ops->get_cd(mmc)) {
+		msm_host_writel(msm_host, CORE_PWRCTL_BUS_FAIL, host,
+				msm_offset->core_pwrctl_ctl);
+		return;
+	}
+
 	/* Handle BUS ON/OFF*/
 	if (irq_status & CORE_PWRCTL_BUS_ON) {
 		pwr_state = REQ_BUS_ON;
Signature · 1 line
2.39.5
author maintainer
#243 lore raw

PATCH 241/523 ACPI: APEI: GHES: add TAINT_MACHINE_CHECK on GHES panic path

In reply to Greg Kroah-Hartman

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

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

From: Breno Leitao <[email protected]>

[ Upstream commit 4734c8b46b901cff2feda8b82abc710b65dc31c1 ]

When a GHES (Generic Hardware Error Source) triggers a panic, add the TAINT_MACHINE_CHECK taint flag to the kernel. This explicitly marks the kernel as tainted due to a machine check event, improving diagnostics and post-mortem analysis. The taint is set with LOCKDEP_STILL_OK to indicate lockdep remains valid.

At large scale deployment, this helps to quickly determine panics that are coming due to hardware failures.

---
 drivers/acpi/apei/ghes.c | 2 ++
 1 file changed, 2 insertions(+)
drivers/acpi/apei/ghes.c +2 -0
index 72087e05b5a5..250ea9ec5f0c 100644
@@ -860,6 +860,8 @@ static void __ghes_panic(struct ghes *ghes,
 
 	__ghes_print_estatus(KERN_EMERG, ghes->generic, estatus);
 
+	add_taint(TAINT_MACHINE_CHECK, LOCKDEP_STILL_OK);
+
 	ghes_clear_estatus(ghes, estatus, buf_paddr, fixmap_idx);
 
 	if (!panic_timeout)
Signature · 1 line
2.39.5
author maintainer
#244 lore raw

PATCH 242/523 reset: brcmstb: Enable reset drivers for ARCH_BCM2835

In reply to Greg Kroah-Hartman

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

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

From: Peter Robinson <[email protected]>

[ Upstream commit 1d99f92f71b6b4b2eee776562c991428490f71ef ]

The BRCMSTB and BRCMSTB_RESCAL reset drivers are also used in the BCM2712, AKA the RPi5. The RPi platforms have typically used the ARCH_BCM2835, and the PCIe support for this SoC can use this config which depends on these drivers so enable building them when just that arch option is enabled to ensure the platform works as expected.

---
 drivers/reset/Kconfig | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)
drivers/reset/Kconfig +5 -5
index 147543ad303f..315324dcdac4 100644
@@ -43,8 +43,8 @@ config RESET_BERLIN
 
 config RESET_BRCMSTB
 	tristate "Broadcom STB reset controller"
-	depends on ARCH_BRCMSTB || COMPILE_TEST
-	default ARCH_BRCMSTB
+	depends on ARCH_BRCMSTB || ARCH_BCM2835 || COMPILE_TEST
+	default ARCH_BRCMSTB || ARCH_BCM2835
 	help
 	  This enables the reset controller driver for Broadcom STB SoCs using
 	  a SUN_TOP_CTRL_SW_INIT style controller.
@@ -52,11 +52,11 @@ config RESET_BRCMSTB
 config RESET_BRCMSTB_RESCAL
 	bool "Broadcom STB RESCAL reset controller"
 	depends on HAS_IOMEM
-	depends on ARCH_BRCMSTB || COMPILE_TEST
-	default ARCH_BRCMSTB
+	depends on ARCH_BRCMSTB || ARCH_BCM2835 || COMPILE_TEST
+	default ARCH_BRCMSTB || ARCH_BCM2835
 	help
 	  This enables the RESCAL reset controller for SATA, PCIe0, or PCIe1 on
-	  BCM7216.
+	  BCM7216 or the BCM2712.
 
 config RESET_HSDK
 	bool "Synopsys HSDK Reset Driver"
Signature · 1 line
2.39.5
author maintainer
#245 lore raw

PATCH 243/523 mmc: rtsx_usb_sdmmc: Fix error-path in sd_set_power_mode()

In reply to Greg Kroah-Hartman

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

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

From: Ulf Hansson <[email protected]>

[ Upstream commit 47a255f7d2eabee06cfbf5b1c2379749442fd01d ]

In the error path of sd_set_power_mode() we don't update host->power_mode, which could lead to an imbalance of the runtime PM usage count. Fix this by always updating host->power_mode.

---
 drivers/mmc/host/rtsx_usb_sdmmc.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)
drivers/mmc/host/rtsx_usb_sdmmc.c +1 -3
index 1be3a355f10d..ab7023d956eb 100644
@@ -1032,9 +1032,7 @@ static int sd_set_power_mode(struct rtsx_usb_sdmmc *host,
 		err = sd_power_on(host);
 	}
 
-	if (!err)
-		host->power_mode = power_mode;
-
+	host->power_mode = power_mode;
 	return err;
 }
 
Signature · 1 line
2.39.5
author maintainer
#246 lore raw

PATCH 244/523 x86/bugs: Avoid warning when overriding return thunk

In reply to Greg Kroah-Hartman

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

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

From: Pawan Gupta <[email protected]>

[ Upstream commit 9f85fdb9fc5a1bd308a10a0a7d7e34f2712ba58b ]

The purpose of the warning is to prevent an unexpected change to the return thunk mitigation. However, there are legitimate cases where the return thunk is intentionally set more than once. For example, ITS and SRSO both can set the return thunk after retbleed has set it. In both the cases retbleed is still mitigated.

Replace the warning with an info about the active return thunk.

---
 arch/x86/kernel/cpu/bugs.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)
arch/x86/kernel/cpu/bugs.c +2 -3
index 7c269dcb7cec..6ff9fd836d87 100644
@@ -67,10 +67,9 @@ void (*x86_return_thunk)(void) __ro_after_init = &__x86_return_thunk;
 
 static void __init set_return_thunk(void *thunk)
 {
-	if (x86_return_thunk != __x86_return_thunk)
-		pr_warn("x86/bugs: return thunk changed\n");
-
 	x86_return_thunk = thunk;
+
+	pr_info("active return thunk: %ps\n", thunk);
 }
 
 /* Update SPEC_CTRL MSR and its cached copy unconditionally */
Signature · 1 line
2.39.5
author maintainer
#247 lore raw

PATCH 245/523 ASoC: hdac_hdmi: Rate limit logging on connection and disconnection

In reply to Greg Kroah-Hartman

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

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

From: Mark Brown <[email protected]>

[ Upstream commit c4ca928a6db1593802cd945f075a7e21dd0430c1 ]

We currently log parse failures for ELD data and some disconnection events as errors without rate limiting. These log messages can be triggered very frequently in some situations, especially ELD parsing when there is nothing connected to a HDMI port which will generate:

hdmi-audio-codec hdmi-audio-codec.1.auto: HDMI: Unknown ELD version 0

While there's doubtless work that could be done on reducing the number of connection notification callbacks it's possible these may be legitimately generated by poor quality physical connections so let's use rate limiting to mitigate the log spam for the parse errors and lower the severity for disconnect logging to debug level.

---
 sound/soc/codecs/hdac_hdmi.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)
sound/soc/codecs/hdac_hdmi.c +6 -4
index 6de3e47b92d8..76e06c88f279 100644
@@ -1230,7 +1230,8 @@ static int hdac_hdmi_parse_eld(struct hdac_device *hdev,
 						>> DRM_ELD_VER_SHIFT;
 
 	if (ver != ELD_VER_CEA_861D && ver != ELD_VER_PARTIAL) {
-		dev_err(&hdev->dev, "HDMI: Unknown ELD version %d\n", ver);
+		dev_err_ratelimited(&hdev->dev,
+				    "HDMI: Unknown ELD version %d\n", ver);
 		return -EINVAL;
 	}
 
@@ -1238,7 +1239,8 @@ static int hdac_hdmi_parse_eld(struct hdac_device *hdev,
 		DRM_ELD_MNL_MASK) >> DRM_ELD_MNL_SHIFT;
 
 	if (mnl > ELD_MAX_MNL) {
-		dev_err(&hdev->dev, "HDMI: MNL Invalid %d\n", mnl);
+		dev_err_ratelimited(&hdev->dev,
+				    "HDMI: MNL Invalid %d\n", mnl);
 		return -EINVAL;
 	}
 
@@ -1297,8 +1299,8 @@ static void hdac_hdmi_present_sense(struct hdac_hdmi_pin *pin,
 
 	if (!port->eld.monitor_present || !port->eld.eld_valid) {
 
-		dev_err(&hdev->dev, "%s: disconnect for pin:port %d:%d\n",
-						__func__, pin->nid, port->id);
+		dev_dbg(&hdev->dev, "%s: disconnect for pin:port %d:%d\n",
+			__func__, pin->nid, port->id);
 
 		/*
 		 * PCMs are not registered during device probe, so don't
Signature · 1 line
2.39.5
author maintainer
#248 lore raw

PATCH 246/523 ALSA: intel8x0: Fix incorrect codec index usage in mixer for ICH4

In reply to Greg Kroah-Hartman

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

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

From: Alok Tiwari <[email protected]>

[ Upstream commit 87aafc8580acf87fcaf1a7e30ed858d8c8d37d81 ]

code mistakenly used a hardcoded index (codec[1]) instead of iterating, over the codec array using the loop variable i. Use codec[i] instead of codec[1] to match the loop iteration.

---
 sound/pci/intel8x0.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
sound/pci/intel8x0.c +1 -1
index 3707dc27324d..324d9df7f111 100644
@@ -2270,7 +2270,7 @@ static int snd_intel8x0_mixer(struct intel8x0 *chip, int ac97_clock,
 			tmp |= chip->ac97_sdin[0] << ICH_DI1L_SHIFT;
 			for (i = 1; i < 4; i++) {
 				if (pcm->r[0].codec[i]) {
-					tmp |= chip->ac97_sdin[pcm->r[0].codec[1]->num] << ICH_DI2L_SHIFT;
+					tmp |= chip->ac97_sdin[pcm->r[0].codec[i]->num] << ICH_DI2L_SHIFT;
 					break;
 				}
 			}
Signature · 1 line
2.39.5
author maintainer
#249 lore raw

PATCH 247/523 ASoC: core: Check for rtd == NULL in snd_soc_remove_pcm_runtime()

In reply to Greg Kroah-Hartman

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

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

From: Peter Ujfalusi <[email protected]>

[ Upstream commit 2d91cb261cac6d885954b8f5da28b5c176c18131 ]

snd_soc_remove_pcm_runtime() might be called with rtd == NULL which will leads to null pointer dereference.
This was reproduced with topology loading and marking a link as ignore due to missing hardware component on the system.
On module removal the soc_tplg_remove_link() would call snd_soc_remove_pcm_runtime() with rtd == NULL since the link was ignored, no runtime was created.

---
 sound/soc/soc-core.c | 3 +++
 1 file changed, 3 insertions(+)
sound/soc/soc-core.c +3 -0
index e9da95ebccc8..1120d669fe2e 100644
@@ -958,6 +958,9 @@ static int soc_dai_link_sanity_check(struct snd_soc_card *card,
 void snd_soc_remove_pcm_runtime(struct snd_soc_card *card,
 				struct snd_soc_pcm_runtime *rtd)
 {
+	if (!rtd)
+		return;
+
 	lockdep_assert_held(&client_mutex);
 
 	/* release machine specific resources */
Signature · 1 line
2.39.5
author maintainer
#250 lore raw

PATCH 248/523 usb: typec: intel_pmc_mux: Defer probe if SCU IPC isnt present

In reply to Greg Kroah-Hartman

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

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

From: Tomasz Michalec <[email protected]>

[ Upstream commit df9a825f330e76c72d1985bc9bdc4b8981e3d15f ]

If pmc_usb_probe is called before SCU IPC is registered, pmc_usb_probe will fail.

Return -EPROBE_DEFER when pmc_usb_probe doesn't get SCU IPC device, so the probe function can be called again after SCU IPC is initialized.

---
 drivers/usb/typec/mux/intel_pmc_mux.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/usb/typec/mux/intel_pmc_mux.c +1 -1
index 1276112edeff..9b4963450fe8 100644
@@ -644,7 +644,7 @@ static int pmc_usb_probe(struct platform_device *pdev)
 
 	pmc->ipc = devm_intel_scu_ipc_dev_get(&pdev->dev);
 	if (!pmc->ipc)
-		return -ENODEV;
+		return -EPROBE_DEFER;
 
 	pmc->dev = &pdev->dev;
 
Signature · 1 line
2.39.5
author maintainer
#251 lore raw

PATCH 249/523 usb: core: usb_submit_urb: downgrade type check

In reply to Greg Kroah-Hartman

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

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

From: Oliver Neukum <[email protected]>

[ Upstream commit 503bbde34cc3dd2acd231f277ba70c3f9ed22e59 ]

Checking for the endpoint type is no reason for a WARN, as that can cause a reboot. A driver not checking the endpoint type must not cause a reboot, as there is just no point in this. We cannot prevent a device from doing something incorrect as a reaction to a transfer. Hence warning for a mere assumption being wrong is not sensible.

---
 drivers/usb/core/urb.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/usb/core/urb.c +1 -1
index 9c285026f827..c41b25bc585c 100644
@@ -490,7 +490,7 @@ int usb_submit_urb(struct urb *urb, gfp_t mem_flags)
 
 	/* Check that the pipe's type matches the endpoint's type */
 	if (usb_pipe_type_check(urb->dev, urb->pipe))
-		dev_WARN(&dev->dev, "BOGUS urb xfer, pipe %x != type %x\n",
+		dev_warn_once(&dev->dev, "BOGUS urb xfer, pipe %x != type %x\n",
 			usb_pipetype(urb->pipe), pipetypes[xfertype]);
 
 	/* Check against a simple/standard policy */
Signature · 1 line
2.39.5
author maintainer
#252 lore raw

PATCH 250/523 pm: cpupower: Fix the snapshot-order of tsc,mperf, clock in mperf_stop()

In reply to Greg Kroah-Hartman

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

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

From: Gautham R. Shenoy <[email protected]>

[ Upstream commit cda7ac8ce7de84cf32a3871ba5f318aa3b79381e ]

In the function mperf_start(), mperf_monitor snapshots the time, tsc and finally the aperf,mperf MSRs. However, this order of snapshotting in is reversed in mperf_stop(). As a result, the C0 residency (which is computed as delta_mperf * 100 / delta_tsc) is under-reported on CPUs that is 100% busy.

Fix this by snapshotting time, tsc and then aperf,mperf in mperf_stop() in the same order as in mperf_start().

---
 tools/power/cpupower/utils/idle_monitor/mperf_monitor.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)
tools/power/cpupower/utils/idle_monitor/mperf_monitor.c +2 -2
index 08a399b0be28..6ab9139f16af 100644
@@ -240,9 +240,9 @@ static int mperf_stop(void)
 	int cpu;
 
 	for (cpu = 0; cpu < cpu_count; cpu++) {
-		mperf_measure_stats(cpu);
-		mperf_get_tsc(&tsc_at_measure_end[cpu]);
 		clock_gettime(CLOCK_REALTIME, &time_end[cpu]);
+		mperf_get_tsc(&tsc_at_measure_end[cpu]);
+		mperf_measure_stats(cpu);
 	}
 
 	return 0;
Signature · 1 line
2.39.5
author maintainer
#253 lore raw

PATCH 251/523 platform/x86: thinkpad_acpi: Handle KCOV __init vs inline mismatches

In reply to Greg Kroah-Hartman

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

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

From: Kees Cook <[email protected]>

[ Upstream commit 6418a8504187dc7f5b6f9d0649c03e362cb0664b ]

When KCOV is enabled all functions get instrumented, unless the __no_sanitize_coverage attribute is used. To prepare for __no_sanitize_coverage being applied to __init functions[1], we have to handle differences in how GCC's inline optimizations get resolved. For thinkpad_acpi routines, this means forcing two functions to be inline with __always_inline.

---
 drivers/platform/x86/thinkpad_acpi.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)
drivers/platform/x86/thinkpad_acpi.c +2 -2
index 5a8434da60e7..d18b6ddba982 100644
@@ -515,12 +515,12 @@ static unsigned long __init tpacpi_check_quirks(
 	return 0;
 }
 
-static inline bool __pure __init tpacpi_is_lenovo(void)
+static __always_inline bool __pure __init tpacpi_is_lenovo(void)
 {
 	return thinkpad_id.vendor == PCI_VENDOR_ID_LENOVO;
 }
 
-static inline bool __pure __init tpacpi_is_ibm(void)
+static __always_inline bool __pure __init tpacpi_is_ibm(void)
 {
 	return thinkpad_id.vendor == PCI_VENDOR_ID_IBM;
 }
Signature · 1 line
2.39.5
author maintainer
#254 lore raw

PATCH 252/523 platform/chrome: cros_ec_typec: Defer probe on missing EC parent

In reply to Greg Kroah-Hartman

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

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

From: Tomasz Michalec <[email protected]>

[ Upstream commit 8866f4e557eba43e991f99711515217a95f62d2e ]

If cros_typec_probe is called before EC device is registered, cros_typec_probe will fail. It may happen when cros-ec-typec.ko is loaded before EC bus layer module (e.g. cros_ec_lpcs.ko, cros_ec_spi.ko).

Return -EPROBE_DEFER when cros_typec_probe doesn't get EC device, so the probe function can be called again after EC device is registered.

---
 drivers/platform/chrome/cros_ec_typec.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)
drivers/platform/chrome/cros_ec_typec.c +2 -2
index 983daa220ee3..137f99c1848e 100644
@@ -716,8 +716,8 @@ static int cros_typec_probe(struct platform_device *pdev)
 
 	typec->ec = dev_get_drvdata(pdev->dev.parent);
 	if (!typec->ec) {
-		dev_err(dev, "couldn't find parent EC device\n");
-		return -ENODEV;
+		dev_warn(dev, "couldn't find parent EC device\n");
+		return -EPROBE_DEFER;
 	}
 
 	platform_set_drvdata(pdev, typec);
Signature · 1 line
2.39.5
author maintainer
#255 lore raw

PATCH 253/523 ALSA: hda/ca0132: Fix buffer overflow in add_tuning_control

In reply to Greg Kroah-Hartman

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

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

From: Lucy Thrun <[email protected]>

[ Upstream commit a409c60111e6bb98fcabab2aeaa069daa9434ca0 ]

The 'sprintf' call in 'add_tuning_control' may exceed the 44-byte buffer if either string argument is too long. This triggers a compiler warning.
Replaced 'sprintf' with 'snprintf' to limit string lengths to prevent overflow.

---
 sound/pci/hda/patch_ca0132.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
sound/pci/hda/patch_ca0132.c +1 -1
index b9d88b156f40..3acb4066b5ea 100644
@@ -4279,7 +4279,7 @@ static int add_tuning_control(struct hda_codec *codec,
 	}
 	knew.private_value =
 		HDA_COMPOSE_AMP_VAL(nid, 1, 0, type);
-	sprintf(namestr, "%s %s Volume", name, dirstr[dir]);
+	snprintf(namestr, sizeof(namestr), "%s %s Volume", name, dirstr[dir]);
 	return snd_hda_ctl_add(codec, nid, snd_ctl_new1(&knew, codec));
 }
 
Signature · 1 line
2.39.5
author maintainer
#256 lore raw

PATCH 254/523 ALSA: pcm: Rewrite recalculate_boundary() to avoid costly loop

In reply to Greg Kroah-Hartman

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

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

From: Christophe Leroy <[email protected]>

[ Upstream commit 92f59aeb13252265c20e7aef1379a8080c57e0a2 ]

At the time being recalculate_boundary() is implemented with a loop which shows up as costly in a perf profile, as depicted by the annotate below:

    0.00 :   c057e934:       3d 40 7f ff     lis     r10,32767
    0.03 :   c057e938:       61 4a ff ff     ori     r10,r10,65535
    0.21 :   c057e93c:       7d 49 50 50     subf    r10,r9,r10
    5.39 :   c057e940:       7d 3c 4b 78     mr      r28,r9
    2.11 :   c057e944:       55 29 08 3c     slwi    r9,r9,1
    3.04 :   c057e948:       7c 09 50 40     cmplw   r9,r10
    2.47 :   c057e94c:       40 81 ff f4     ble     c057e940 <snd_pcm_ioctl+0xee0>

Total: 13.2% on that simple loop.

But what the loop does is to multiply the boundary by 2 until it is over the wanted border. This can be avoided by using fls() to get the boundary value order and shift it by the appropriate number of bits at once.

This change provides the following profile:

    0.04 :   c057f6e8:       3d 20 7f ff     lis     r9,32767
    0.02 :   c057f6ec:       61 29 ff ff     ori     r9,r9,65535
    0.34 :   c057f6f0:       7d 5a 48 50     subf    r10,r26,r9
    0.23 :   c057f6f4:       7c 1a 50 40     cmplw   r26,r10
    0.02 :   c057f6f8:       41 81 00 20     bgt     c057f718 <snd_pcm_ioctl+0xf08>
    0.26 :   c057f6fc:       7f 47 00 34     cntlzw  r7,r26
    0.09 :   c057f700:       7d 48 00 34     cntlzw  r8,r10
    0.22 :   c057f704:       7d 08 38 50     subf    r8,r8,r7
    0.04 :   c057f708:       7f 5a 40 30     slw     r26,r26,r8
    0.35 :   c057f70c:       7c 0a d0 40     cmplw   r10,r26
    0.13 :   c057f710:       40 80 05 f8     bge     c057fd08 <snd_pcm_ioctl+0x14f8>
    0.00 :   c057f714:       57 5a f8 7e     srwi    r26,r26,1

Total: 1.7% with that loopless alternative.

---
 sound/core/pcm_native.c | 19 +++++++++++++++----
 1 file changed, 15 insertions(+), 4 deletions(-)
sound/core/pcm_native.c +15 -4
index 98bd6fe850d3..145e5157515f 100644
@@ -24,6 +24,7 @@
 #include <sound/minors.h>
 #include <linux/uio.h>
 #include <linux/delay.h>
+#include <linux/bitops.h>
 
 #include "pcm_local.h"
 
@@ -3094,13 +3095,23 @@ struct snd_pcm_sync_ptr32 {
 static snd_pcm_uframes_t recalculate_boundary(struct snd_pcm_runtime *runtime)
 {
 	snd_pcm_uframes_t boundary;
+	snd_pcm_uframes_t border;
+	int order;
 
 	if (! runtime->buffer_size)
 		return 0;
-	boundary = runtime->buffer_size;
-	while (boundary * 2 <= 0x7fffffffUL - runtime->buffer_size)
-		boundary *= 2;
-	return boundary;
+
+	border = 0x7fffffffUL - runtime->buffer_size;
+	if (runtime->buffer_size > border)
+		return runtime->buffer_size;
+
+	order = __fls(border) - __fls(runtime->buffer_size);
+	boundary = runtime->buffer_size << order;
+
+	if (boundary <= border)
+		return boundary;
+	else
+		return boundary / 2;
 }
 
 static int snd_pcm_ioctl_sync_ptr_compat(struct snd_pcm_substream *substream,
Signature · 1 line
2.39.5
author maintainer
#257 lore raw

PATCH 255/523 ALSA: usb-audio: Avoid precedence issues in mixer_quirks macros

In reply to Greg Kroah-Hartman

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

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

From: Cristian Ciocaltea <[email protected]>

[ Upstream commit fd3ab72e42e9871a9902b945a2bf8bb87b49c718 ]

Fix all macro related issues identified by checkpatch.pl:

CHECK: Macro argument 'x' may be better as '(x)' to avoid precedence issues

---
 sound/usb/mixer_quirks.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)
sound/usb/mixer_quirks.c +7 -7
index eee5a3ce9471..c0948922562b 100644
@@ -1991,15 +1991,15 @@ static int dell_dock_mixer_init(struct usb_mixer_interface *mixer)
 #define SND_RME_CLK_FREQMUL_SHIFT		18
 #define SND_RME_CLK_FREQMUL_MASK		0x7
 #define SND_RME_CLK_SYSTEM(x) \
-	((x >> SND_RME_CLK_SYSTEM_SHIFT) & SND_RME_CLK_SYSTEM_MASK)
+	(((x) >> SND_RME_CLK_SYSTEM_SHIFT) & SND_RME_CLK_SYSTEM_MASK)
 #define SND_RME_CLK_AES(x) \
-	((x >> SND_RME_CLK_AES_SHIFT) & SND_RME_CLK_AES_SPDIF_MASK)
+	(((x) >> SND_RME_CLK_AES_SHIFT) & SND_RME_CLK_AES_SPDIF_MASK)
 #define SND_RME_CLK_SPDIF(x) \
-	((x >> SND_RME_CLK_SPDIF_SHIFT) & SND_RME_CLK_AES_SPDIF_MASK)
+	(((x) >> SND_RME_CLK_SPDIF_SHIFT) & SND_RME_CLK_AES_SPDIF_MASK)
 #define SND_RME_CLK_SYNC(x) \
-	((x >> SND_RME_CLK_SYNC_SHIFT) & SND_RME_CLK_SYNC_MASK)
+	(((x) >> SND_RME_CLK_SYNC_SHIFT) & SND_RME_CLK_SYNC_MASK)
 #define SND_RME_CLK_FREQMUL(x) \
-	((x >> SND_RME_CLK_FREQMUL_SHIFT) & SND_RME_CLK_FREQMUL_MASK)
+	(((x) >> SND_RME_CLK_FREQMUL_SHIFT) & SND_RME_CLK_FREQMUL_MASK)
 #define SND_RME_CLK_AES_LOCK			0x1
 #define SND_RME_CLK_AES_SYNC			0x4
 #define SND_RME_CLK_SPDIF_LOCK			0x2
@@ -2008,9 +2008,9 @@ static int dell_dock_mixer_init(struct usb_mixer_interface *mixer)
 #define SND_RME_SPDIF_FORMAT_SHIFT		5
 #define SND_RME_BINARY_MASK			0x1
 #define SND_RME_SPDIF_IF(x) \
-	((x >> SND_RME_SPDIF_IF_SHIFT) & SND_RME_BINARY_MASK)
+	(((x) >> SND_RME_SPDIF_IF_SHIFT) & SND_RME_BINARY_MASK)
 #define SND_RME_SPDIF_FORMAT(x) \
-	((x >> SND_RME_SPDIF_FORMAT_SHIFT) & SND_RME_BINARY_MASK)
+	(((x) >> SND_RME_SPDIF_FORMAT_SHIFT) & SND_RME_BINARY_MASK)
 
 static const u32 snd_rme_rate_table[] = {
 	32000, 44100, 48000, 50000,
Signature · 1 line
2.39.5
author maintainer
#258 lore raw

PATCH 256/523 iio: adc: ad7768-1: Ensure SYNC_IN pulse minimum timing requirement

In reply to Greg Kroah-Hartman

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

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

From: Jonathan Santos <[email protected]>

[ Upstream commit 7e54d932873d91a55d1b89b7389876d78aeeab32 ]

The SYNC_IN pulse width must be at least 1.5 x Tmclk, corresponding to ~2.5 µs at the lowest supported MCLK frequency. Add a 3 µs delay to ensure reliable synchronization timing even for the worst-case scenario.

---
 drivers/iio/adc/ad7768-1.c | 23 +++++++++++++++++++----
 1 file changed, 19 insertions(+), 4 deletions(-)
drivers/iio/adc/ad7768-1.c +19 -4
index 9580a7f7f73d..883399ad80e0 100644
@@ -202,6 +202,24 @@ static int ad7768_spi_reg_write(struct ad7768_state *st,
 	return spi_write(st->spi, st->data.d8, 2);
 }
 
+static int ad7768_send_sync_pulse(struct ad7768_state *st)
+{
+	/*
+	 * The datasheet specifies a minimum SYNC_IN pulse width of 1.5 × Tmclk,
+	 * where Tmclk is the MCLK period. The supported MCLK frequencies range
+	 * from 0.6 MHz to 17 MHz, which corresponds to a minimum SYNC_IN pulse
+	 * width of approximately 2.5 µs in the worst-case scenario (0.6 MHz).
+	 *
+	 * Add a delay to ensure the pulse width is always sufficient to
+	 * trigger synchronization.
+	 */
+	gpiod_set_value_cansleep(st->gpio_sync_in, 1);
+	fsleep(3);
+	gpiod_set_value_cansleep(st->gpio_sync_in, 0);
+
+	return 0;
+}
+
 static int ad7768_set_mode(struct ad7768_state *st,
 			   enum ad7768_conv_mode mode)
 {
@@ -287,10 +305,7 @@ static int ad7768_set_dig_fil(struct ad7768_state *st,
 		return ret;
 
 	/* A sync-in pulse is required every time the filter dec rate changes */
-	gpiod_set_value(st->gpio_sync_in, 1);
-	gpiod_set_value(st->gpio_sync_in, 0);
-
-	return 0;
+	return ad7768_send_sync_pulse(st);
 }
 
 static int ad7768_set_freq(struct ad7768_state *st,
Signature · 1 line
2.39.5
author maintainer
#259 lore raw

PATCH 257/523 ASoC: codecs: rt5640: Retry DEVICE_ID verification

In reply to Greg Kroah-Hartman

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

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

From: Xinxin Wan <[email protected]>

[ Upstream commit 19f971057b2d7b99c80530ec1052b45de236a8da ]

To be more resilient to codec-detection failures when the hardware powers on slowly, add retry mechanism to the device verification check. Similar pattern is found throughout a number of Realtek codecs. Our tests show that 60ms delay is sufficient to address readiness issues on rt5640 chip.

---
 sound/soc/codecs/rt5640.c | 5 +++++
 1 file changed, 5 insertions(+)
sound/soc/codecs/rt5640.c +5 -0
index a5674c227b3a..c12966025cfa 100644
@@ -2810,6 +2810,11 @@ static int rt5640_i2c_probe(struct i2c_client *i2c,
 	}
 
 	regmap_read(rt5640->regmap, RT5640_VENDOR_ID2, &val);
+	if (val != RT5640_DEVICE_ID) {
+		usleep_range(60000, 100000);
+		regmap_read(rt5640->regmap, RT5640_VENDOR_ID2, &val);
+	}
+
 	if (val != RT5640_DEVICE_ID) {
 		dev_err(&i2c->dev,
 			"Device with ID register %#x is not rt5640/39\n", val);
Signature · 1 line
2.39.5
author maintainer
#260 lore raw

PATCH 258/523 xen/netfront: Fix TX response spurious interrupts

In reply to Greg Kroah-Hartman

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

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

From: Anthoine Bourgeois <[email protected]>

[ Upstream commit 114a2de6fa86d99ed9546cc9113a3cad58beef79 ]

We found at Vates that there are lot of spurious interrupts when benchmarking the xen-net PV driver frontend. This issue appeared with a patch that addresses security issue XSA-391 (b27d47950e48 "xen/netfront:
harden netfront against event channel storms"). On an iperf benchmark, spurious interrupts can represent up to 50% of the interrupts.

Spurious interrupts are interrupts that are rised for nothing, there is no work to do. This appends because the function that handles the interrupts ("xennet_tx_buf_gc") is also called at the end of the request path to garbage collect the responses received during the transmission load.

The request path is doing the work that the interrupt handler should have done otherwise. This is particurary true when there is more than one vcpu and get worse linearly with the number of vcpu/queue.

Moreover, this problem is amplifyed by the penalty imposed by a spurious interrupt. When an interrupt is found spurious the interrupt chip will delay the EOI to slowdown the backend. This delay will allow more responses to be handled by the request path and then there will be more chance the next interrupt will not find any work to do, creating a new spurious interrupt.

This causes performance issue. The solution here is to remove the calls from the request path and let the interrupt handler do the processing of the responses. This approch removes most of the spurious interrupts (<0.05%) and also has the benefit of freeing up cycles in the request path, allowing it to process more work, which improves performance compared to masking the spurious interrupt one way or another.

This optimization changes a part of the code that is present since the net frontend driver was upstreamed. There is no similar pattern in the other xen PV drivers. Since the first commit of xen-netfront is a blob that doesn't explain all the design choices I can only guess why this specific mecanism was here. This could have been introduce to compensate a slow backend at the time (maybe the backend was fixed or optimize later) or a small queue. In 18 years, both frontend and backend gain lot of features and optimizations that could have obsolete the feature of reaping completions from the TX path.

Some vif throughput performance figures from a 8 vCPUs, 4GB of RAM HVM guest(s):

Without this patch on the :
vm -> dom0: 4.5Gb/s
vm -> vm: 7.0Gb/s

Without XSA-391 patch (revert of b27d47950e48):
vm -> dom0: 8.3Gb/s
vm -> vm: 8.7Gb/s

With XSA-391 and this patch:
vm -> dom0: 11.5Gb/s
vm -> vm: 12.6Gb/s

v2:
- add revewed and tested by tags
- resend with the maintainers in the recipients list

v3:
- remove Fixes tag but keep the commit ref in the explanation
- add a paragraph on why this code was here

Message-ID: <[email protected]>

---
 drivers/net/xen-netfront.c | 5 -----
 1 file changed, 5 deletions(-)
drivers/net/xen-netfront.c +0 -5
index bad9e549d533..34c4770bf555 100644
@@ -638,8 +638,6 @@ static int xennet_xdp_xmit_one(struct net_device *dev,
 	tx_stats->packets++;
 	u64_stats_update_end(&tx_stats->syncp);
 
-	xennet_tx_buf_gc(queue);
-
 	return 0;
 }
 
@@ -851,9 +849,6 @@ static netdev_tx_t xennet_start_xmit(struct sk_buff *skb, struct net_device *dev
 	tx_stats->packets++;
 	u64_stats_update_end(&tx_stats->syncp);
 
-	/* Note: It is not safe to access skb after xennet_tx_buf_gc()! */
-	xennet_tx_buf_gc(queue);
-
 	if (!netfront_tx_slot_available(queue))
 		netif_tx_stop_queue(netdev_get_tx_queue(dev, queue->id));
 
Signature · 1 line
2.39.5
author maintainer
#261 lore raw

PATCH 259/523 ktest.pl: Prevent recursion of default variable options

In reply to Greg Kroah-Hartman

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

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

From: Steven Rostedt <[email protected]>

[ Upstream commit 61f7e318e99d3b398670518dd3f4f8510d1800fc ]

If a default variable contains itself, do not recurse on it.

For example:

  ADD_CONFIG := ${CONFIG_DIR}/temp_config
  DEFAULTS
  ADD_CONFIG = ${CONFIG_DIR}/default_config ${ADD_CONFIG}

The above works because the temp variable ADD_CONFIG (is a temp because it is created with ":=") is already defined, it will be substituted in the variable option. But if it gets commented out:

  # ADD_CONFIG := ${CONFIG_DIR}/temp_config
  DEFAULTS
  ADD_CONFIG = ${CONFIG_DIR}/default_config ${ADD_CONFIG}

Then the above will go into a recursive loop where ${ADD_CONFIG} will get replaced with the current definition of ADD_CONFIG which contains the ${ADD_CONFIG} and that will also try to get converted. ktest.pl will error after 100 attempts of recursion and fail.

When replacing a variable with the default variable, if the default variable contains itself, do not replace it.

---
 tools/testing/ktest/ktest.pl | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)
tools/testing/ktest/ktest.pl +4 -1
index 8ac30e2ac3ac..512a3cc586fd 100755
@@ -1291,7 +1291,10 @@ sub __eval_option {
 	# If a variable contains itself, use the default var
 	if (($var eq $name) && defined($opt{$var})) {
 	    $o = $opt{$var};
-	    $retval = "$retval$o";
+	    # Only append if the default doesn't contain itself
+	    if ($o !~ m/\$\{$var\}/) {
+		$retval = "$retval$o";
+	    }
 	} elsif (defined($opt{$o})) {
 	    $o = $opt{$o};
 	    $retval = "$retval$o";
Signature · 1 line
2.39.5
author maintainer
#262 lore raw

PATCH 260/523 wifi: cfg80211: reject HTC bit for management frames

In reply to Greg Kroah-Hartman

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

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

From: Johannes Berg <[email protected]>

[ Upstream commit be06a8c7313943109fa870715356503c4c709cbc ]

Management frames sent by userspace should never have the order/HTC bit set, reject that. It could also cause some confusion with the length of the buffer and the header so the validation might end up wrong.

---
 net/wireless/mlme.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)
net/wireless/mlme.c +2 -1
index 6dcfc5a34874..8fce621a3f01 100644
@@ -657,7 +657,8 @@ int cfg80211_mlme_mgmt_tx(struct cfg80211_registered_device *rdev,
 
 	mgmt = (const struct ieee80211_mgmt *)params->buf;
 
-	if (!ieee80211_is_mgmt(mgmt->frame_control))
+	if (!ieee80211_is_mgmt(mgmt->frame_control) ||
+	    ieee80211_has_order(mgmt->frame_control))
 		return -EINVAL;
 
 	stype = le16_to_cpu(mgmt->frame_control) & IEEE80211_FCTL_STYPE;
Signature · 1 line
2.39.5
author maintainer
#263 lore raw

PATCH 261/523 s390/time: Use monotonic clock in get_cycles()

In reply to Greg Kroah-Hartman

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

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

From: Sven Schnelle <[email protected]>

[ Upstream commit 09e7e29d2b49ba84bcefb3dc1657726d2de5bb24 ]

Otherwise the code might not work correctly when the clock is changed.

---
 arch/s390/include/asm/timex.h | 13 ++++++-------
 1 file changed, 6 insertions(+), 7 deletions(-)
arch/s390/include/asm/timex.h +6 -7
index 588aa0f2c842..d0260a1ec298 100644
@@ -167,13 +167,6 @@ static inline unsigned long long get_tod_clock_fast(void)
 	return get_tod_clock();
 #endif
 }
-
-static inline cycles_t get_cycles(void)
-{
-	return (cycles_t) get_tod_clock() >> 2;
-}
-#define get_cycles get_cycles
-
 int get_phys_clock(unsigned long *clock);
 void init_cpu_timer(void);
 
@@ -196,6 +189,12 @@ static inline unsigned long long get_tod_clock_monotonic(void)
 	return tod;
 }
 
+static inline cycles_t get_cycles(void)
+{
+	return (cycles_t)get_tod_clock_monotonic() >> 2;
+}
+#define get_cycles get_cycles
+
 /**
  * tod_to_ns - convert a TOD format value to nanoseconds
  * @todval: to be converted TOD format value
Signature · 1 line
2.39.5
author maintainer
#264 lore raw

PATCH 262/523 be2net: Use correct byte order and format string for TCP seq and ack_seq

In reply to Greg Kroah-Hartman

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

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

From: Alok Tiwari <[email protected]>

[ Upstream commit 4701ee5044fb3992f1c910630a9673c2dc600ce5 ]

The TCP header fields seq and ack_seq are 32-bit values in network byte order as (__be32). these fields were earlier printed using ntohs(), which converts only 16-bit values and produces incorrect results for 32-bit fields. This patch is changeing the conversion to ntohl(), ensuring correct interpretation of these sequence numbers.

Notably, the format specifier is updated from %d to %u to reflect the unsigned nature of these fields.

improves the accuracy of debug log messages for TCP sequence and acknowledgment numbers during TX timeouts.

---
 drivers/net/ethernet/emulex/benet/be_main.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)
drivers/net/ethernet/emulex/benet/be_main.c +4 -4
index ff3ea24d2e3f..97cbe7737eb4 100644
@@ -1466,10 +1466,10 @@ static void be_tx_timeout(struct net_device *netdev, unsigned int txqueue)
 						 ntohs(tcphdr->source));
 					dev_info(dev, "TCP dest port %d\n",
 						 ntohs(tcphdr->dest));
-					dev_info(dev, "TCP sequence num %d\n",
-						 ntohs(tcphdr->seq));
-					dev_info(dev, "TCP ack_seq %d\n",
-						 ntohs(tcphdr->ack_seq));
+					dev_info(dev, "TCP sequence num %u\n",
+						 ntohl(tcphdr->seq));
+					dev_info(dev, "TCP ack_seq %u\n",
+						 ntohl(tcphdr->ack_seq));
 				} else if (ip_hdr(skb)->protocol ==
 					   IPPROTO_UDP) {
 					udphdr = udp_hdr(skb);
Signature · 1 line
2.39.5
author maintainer
#265 lore raw

PATCH 263/523 et131x: Add missing check after DMA map

In reply to Greg Kroah-Hartman

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

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

From: Thomas Fourier <[email protected]>

[ Upstream commit d61f6cb6f6ef3c70d2ccc0d9c85c508cb8017da9 ]

The DMA map functions can fail and should be tested for errors. If the mapping fails, unmap and return an error.

---
 drivers/net/ethernet/agere/et131x.c | 36 +++++++++++++++++++++++++++++
 1 file changed, 36 insertions(+)
drivers/net/ethernet/agere/et131x.c +36 -0
index 41f8821f792d..fa04e37de089 100644
@@ -2460,6 +2460,10 @@ static int nic_send_packet(struct et131x_adapter *adapter, struct tcb *tcb)
 							  skb->data,
 							  skb_headlen(skb),
 							  DMA_TO_DEVICE);
+				if (dma_mapping_error(&adapter->pdev->dev,
+						      dma_addr))
+					return -ENOMEM;
+
 				desc[frag].addr_lo = lower_32_bits(dma_addr);
 				desc[frag].addr_hi = upper_32_bits(dma_addr);
 				frag++;
@@ -2469,6 +2473,10 @@ static int nic_send_packet(struct et131x_adapter *adapter, struct tcb *tcb)
 							  skb->data,
 							  skb_headlen(skb) / 2,
 							  DMA_TO_DEVICE);
+				if (dma_mapping_error(&adapter->pdev->dev,
+						      dma_addr))
+					return -ENOMEM;
+
 				desc[frag].addr_lo = lower_32_bits(dma_addr);
 				desc[frag].addr_hi = upper_32_bits(dma_addr);
 				frag++;
@@ -2479,6 +2487,10 @@ static int nic_send_packet(struct et131x_adapter *adapter, struct tcb *tcb)
 							  skb_headlen(skb) / 2,
 							  skb_headlen(skb) / 2,
 							  DMA_TO_DEVICE);
+				if (dma_mapping_error(&adapter->pdev->dev,
+						      dma_addr))
+					goto unmap_first_out;
+
 				desc[frag].addr_lo = lower_32_bits(dma_addr);
 				desc[frag].addr_hi = upper_32_bits(dma_addr);
 				frag++;
@@ -2490,6 +2502,9 @@ static int nic_send_packet(struct et131x_adapter *adapter, struct tcb *tcb)
 						    0,
 						    desc[frag].len_vlan,
 						    DMA_TO_DEVICE);
+			if (dma_mapping_error(&adapter->pdev->dev, dma_addr))
+				goto unmap_out;
+
 			desc[frag].addr_lo = lower_32_bits(dma_addr);
 			desc[frag].addr_hi = upper_32_bits(dma_addr);
 			frag++;
@@ -2579,6 +2594,27 @@ static int nic_send_packet(struct et131x_adapter *adapter, struct tcb *tcb)
 		       &adapter->regs->global.watchdog_timer);
 	}
 	return 0;
+
+unmap_out:
+	// Unmap the body of the packet with map_page
+	while (--i) {
+		frag--;
+		dma_addr = desc[frag].addr_lo;
+		dma_addr |= (u64)desc[frag].addr_hi << 32;
+		dma_unmap_page(&adapter->pdev->dev, dma_addr,
+			       desc[frag].len_vlan, DMA_TO_DEVICE);
+	}
+
+unmap_first_out:
+	// Unmap the header with map_single
+	while (frag--) {
+		dma_addr = desc[frag].addr_lo;
+		dma_addr |= (u64)desc[frag].addr_hi << 32;
+		dma_unmap_single(&adapter->pdev->dev, dma_addr,
+				 desc[frag].len_vlan, DMA_TO_DEVICE);
+	}
+
+	return -ENOMEM;
 }
 
 static int send_packet(struct sk_buff *skb, struct et131x_adapter *adapter)
Signature · 1 line
2.39.5
author maintainer
#266 lore raw

PATCH 264/523 net: ag71xx: Add missing check after DMA map

In reply to Greg Kroah-Hartman

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

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

From: Thomas Fourier <[email protected]>

[ Upstream commit 96a1e15e60216b52da0e6da5336b6d7f5b0188b0 ]

The DMA map functions can fail and should be tested for errors.

---
 drivers/net/ethernet/atheros/ag71xx.c | 9 +++++++++
 1 file changed, 9 insertions(+)
drivers/net/ethernet/atheros/ag71xx.c +9 -0
index fe3ca3af431a..67409a53d510 100644
@@ -1275,6 +1275,11 @@ static bool ag71xx_fill_rx_buf(struct ag71xx *ag, struct ag71xx_buf *buf,
 	buf->rx.rx_buf = data;
 	buf->rx.dma_addr = dma_map_single(&ag->pdev->dev, data, ag->rx_buf_size,
 					  DMA_FROM_DEVICE);
+	if (dma_mapping_error(&ag->pdev->dev, buf->rx.dma_addr)) {
+		skb_free_frag(data);
+		buf->rx.rx_buf = NULL;
+		return false;
+	}
 	desc->data = (u32)buf->rx.dma_addr + offset;
 	return true;
 }
@@ -1573,6 +1578,10 @@ static netdev_tx_t ag71xx_hard_start_xmit(struct sk_buff *skb,
 
 	dma_addr = dma_map_single(&ag->pdev->dev, skb->data, skb->len,
 				  DMA_TO_DEVICE);
+	if (dma_mapping_error(&ag->pdev->dev, dma_addr)) {
+		netif_dbg(ag, tx_err, ndev, "DMA mapping error\n");
+		goto err_drop;
+	}
 
 	i = ring->curr & ring_mask;
 	desc = ag71xx_ring_desc(ring, i);
Signature · 1 line
2.39.5
author maintainer
#267 lore raw

PATCH 265/523 rcu: Protect ->defer_qs_iw_pending from data race

In reply to Greg Kroah-Hartman

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

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

From: Paul E. McKenney <[email protected]>

[ Upstream commit 90c09d57caeca94e6f3f87c49e96a91edd40cbfd ]

On kernels built with CONFIG_IRQ_WORK=y, when rcu_read_unlock() is invoked within an interrupts-disabled region of code [1], it will invoke rcu_read_unlock_special(), which uses an irq-work handler to force the system to notice when the RCU read-side critical section actually ends. That end won't happen until interrupts are enabled at the soonest.

In some kernels, such as those booted with rcutree.use_softirq=y, the irq-work handler is used unconditionally.

The per-CPU rcu_data structure's ->defer_qs_iw_pending field is updated by the irq-work handler and is both read and updated by rcu_read_unlock_special(). This resulted in the following KCSAN splat:

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

BUG: KCSAN: data-race in rcu_preempt_deferred_qs_handler / rcu_read_unlock_special

read to 0xffff96b95f42d8d8 of 1 bytes by task 90 on cpu 8:

 rcu_read_unlock_special+0x175/0x260
 __rcu_read_unlock+0x92/0xa0
 rt_spin_unlock+0x9b/0xc0
 __local_bh_enable+0x10d/0x170
 __local_bh_enable_ip+0xfb/0x150
 rcu_do_batch+0x595/0xc40
 rcu_cpu_kthread+0x4e9/0x830
 smpboot_thread_fn+0x24d/0x3b0
 kthread+0x3bd/0x410
 ret_from_fork+0x35/0x40
 ret_from_fork_asm+0x1a/0x30

write to 0xffff96b95f42d8d8 of 1 bytes by task 88 on cpu 8:

 rcu_preempt_deferred_qs_handler+0x1e/0x30
 irq_work_single+0xaf/0x160
 run_irq_workd+0x91/0xc0
 smpboot_thread_fn+0x24d/0x3b0
 kthread+0x3bd/0x410
 ret_from_fork+0x35/0x40
 ret_from_fork_asm+0x1a/0x30

no locks held by irq_work/8/88.

irq event stamp: 200272
hardirqs last  enabled at (200272): [<ffffffffb0f56121>] finish_task_switch+0x131/0x320
hardirqs last disabled at (200271): [<ffffffffb25c7859>] __schedule+0x129/0xd70
softirqs last  enabled at (0): [<ffffffffb0ee093f>] copy_process+0x4df/0x1cc0
softirqs last disabled at (0): [<0000000000000000>] 0x0

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

The problem is that irq-work handlers run with interrupts enabled, which means that rcu_preempt_deferred_qs_handler() could be interrupted, and that interrupt handler might contain an RCU read-side critical section, which might invoke rcu_read_unlock_special(). In the strict KCSAN mode of operation used by RCU, this constitutes a data race on the ->defer_qs_iw_pending field.

This commit therefore disables interrupts across the portion of the rcu_preempt_deferred_qs_handler() that updates the ->defer_qs_iw_pending field. This suffices because this handler is not a fast path.

---
 kernel/rcu/tree_plugin.h | 3 +++
 1 file changed, 3 insertions(+)
kernel/rcu/tree_plugin.h +3 -0
index c07a84197173..ed17deba8b18 100644
@@ -585,10 +585,13 @@ static void rcu_preempt_deferred_qs(struct task_struct *t)
  */
 static void rcu_preempt_deferred_qs_handler(struct irq_work *iwp)
 {
+	unsigned long flags;
 	struct rcu_data *rdp;
 
 	rdp = container_of(iwp, struct rcu_data, defer_qs_iw);
+	local_irq_save(flags);
 	rdp->defer_qs_iw_pending = false;
+	local_irq_restore(flags);
 }
 
 /*
Signature · 1 line
2.39.5
author maintainer
#268 lore raw

PATCH 266/523 wifi: cfg80211: Fix interface type validation

In reply to Greg Kroah-Hartman

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

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

From: Ilan Peer <[email protected]>

[ Upstream commit 14450be2332a49445106403492a367412b8c23f4 ]

Fix a condition that verified valid values of interface types.

---
 include/net/cfg80211.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
include/net/cfg80211.h +1 -1
index 4536a122c4bc..5595c2a94939 100644
@@ -510,7 +510,7 @@ ieee80211_get_sband_iftype_data(const struct ieee80211_supported_band *sband,
 {
 	int i;
 
-	if (WARN_ON(iftype >= NL80211_IFTYPE_MAX))
+	if (WARN_ON(iftype >= NUM_NL80211_IFTYPES))
 		return NULL;
 
 	if (iftype == NL80211_IFTYPE_AP_VLAN)
Signature · 1 line
2.39.5
author maintainer
#269 lore raw

PATCH 267/523 net: ipv4: fix incorrect MTU in broadcast routes

In reply to Greg Kroah-Hartman

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

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

From: Oscar Maes <[email protected]>

[ Upstream commit 9e30ecf23b1b8f091f7d08b27968dea83aae7908 ]

Currently, __mkroute_output overrules the MTU value configured for broadcast routes.

This buggy behaviour can be reproduced with:

ip link set dev eth1 mtu 9000
ip route del broadcast 192.168.0.255 dev eth1 proto kernel scope link src 192.168.0.2 ip route add broadcast 192.168.0.255 dev eth1 proto kernel scope link src 192.168.0.2 mtu 1500

The maximum packet size should be 1500, but it is actually 8000:

ping -b 192.168.0.255 -s 8000

Fix __mkroute_output to allow MTU values to be configured for for broadcast routes (to support a mixed-MTU local-area-network).

---
 net/ipv4/route.c | 1 -
 1 file changed, 1 deletion(-)
net/ipv4/route.c +0 -1
index 815b6b0089c2..7c4479adbf32 100644
@@ -2465,7 +2465,6 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
 	do_cache = true;
 	if (type == RTN_BROADCAST) {
 		flags |= RTCF_BROADCAST | RTCF_LOCAL;
-		fi = NULL;
 	} else if (type == RTN_MULTICAST) {
 		flags |= RTCF_MULTICAST | RTCF_LOCAL;
 		if (!ip_check_mc_rcu(in_dev, fl4->daddr, fl4->saddr,
Signature · 1 line
2.39.5
author maintainer
#270 lore raw

PATCH 268/523 net: thunderx: Fix format-truncation warning in bgx_acpi_match_id()

In reply to Greg Kroah-Hartman

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

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

From: Alok Tiwari <[email protected]>

[ Upstream commit 53d20606c40678d425cc03f0978c614dca51f25e ]

The buffer bgx_sel used in snprintf() was too small to safely hold the formatted string "BGX%d" for all valid bgx_id values. This caused a -Wformat-truncation warning with Werror enabled during build.

Increase the buffer size from 5 to 7 and use sizeof(bgx_sel) in snprintf() to ensure safety and suppress the warning.

Build warning:
CC drivers/net/ethernet/cavium/thunder/thunder_bgx.o
drivers/net/ethernet/cavium/thunder/thunder_bgx.c: In function
‘bgx_acpi_match_id’:
drivers/net/ethernet/cavium/thunder/thunder_bgx.c:1434:27: error: ‘%d’
directive output may be truncated writing between 1 and 3 bytes into a region of size 2 [-Werror=format-truncation=]

    snprintf(bgx_sel, 5, "BGX%d", bgx->bgx_id);
                             ^~
  drivers/net/ethernet/cavium/thunder/thunder_bgx.c:1434:23: note:
directive argument in the range [0, 255]
    snprintf(bgx_sel, 5, "BGX%d", bgx->bgx_id);
                         ^~~~~~~
  drivers/net/ethernet/cavium/thunder/thunder_bgx.c:1434:2: note:
‘snprintf’ output between 5 and 7 bytes into a destination of size 5
    snprintf(bgx_sel, 5, "BGX%d", bgx->bgx_id);

compiler warning due to insufficient snprintf buffer size.

---
 drivers/net/ethernet/cavium/thunder/thunder_bgx.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)
drivers/net/ethernet/cavium/thunder/thunder_bgx.c +2 -2
index f0e48b9373d6..0a71909bb2ee 100644
@@ -1430,9 +1430,9 @@ static acpi_status bgx_acpi_match_id(acpi_handle handle, u32 lvl,
 {
 	struct acpi_buffer string = { ACPI_ALLOCATE_BUFFER, NULL };
 	struct bgx *bgx = context;
-	char bgx_sel[5];
+	char bgx_sel[7];
 
-	snprintf(bgx_sel, 5, "BGX%d", bgx->bgx_id);
+	snprintf(bgx_sel, sizeof(bgx_sel), "BGX%d", bgx->bgx_id);
 	if (ACPI_FAILURE(acpi_get_name(handle, ACPI_SINGLE_NAME, &string))) {
 		pr_warn("Invalid link device\n");
 		return AE_OK;
Signature · 1 line
2.39.5
author maintainer
#271 lore raw

PATCH 269/523 wifi: iwlwifi: mvm: fix scan request validation

In reply to Greg Kroah-Hartman

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

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

From: Avraham Stern <[email protected]>

[ Upstream commit 7c2f3ec7707188d8d5269ae2dce97d7be3e9f261 ]

The scan request validation function uses bitwise and instead of logical and. Fix it.

---
 drivers/net/wireless/intel/iwlwifi/mvm/scan.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/net/wireless/intel/iwlwifi/mvm/scan.c +1 -1
index a52af491eed5..6e6325717c0a 100644
@@ -876,7 +876,7 @@ static inline bool iwl_mvm_scan_fits(struct iwl_mvm *mvm, int n_ssids,
 				     int n_channels)
 {
 	return ((n_ssids <= PROBE_OPTION_MAX) &&
-		(n_channels <= mvm->fw->ucode_capa.n_scan_channels) &
+		(n_channels <= mvm->fw->ucode_capa.n_scan_channels) &&
 		(ies->common_ie_len +
 		 ies->len[NL80211_BAND_2GHZ] +
 		 ies->len[NL80211_BAND_5GHZ] <=
Signature · 1 line
2.39.5
author maintainer
#272 lore raw

PATCH 270/523 s390/stp: Remove udelay from stp_sync_clock()

In reply to Greg Kroah-Hartman

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

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

From: Sven Schnelle <[email protected]>

[ Upstream commit b367017cdac21781a74eff4e208d3d38e1f38d3f ]

When an stp sync check is handled on a system with multiple cpus each cpu gets a machine check but only the first one actually handles the sync operation. All other CPUs spin waiting for the first one to finish with a short udelay(). But udelay can't be used here as the first CPU modifies tod_clock_base before performing the sync op. During this timeframe get_tod_clock_monotonic() might return a non-monotonic time.

The time spent waiting should be very short and udelay is a busy loop anyways, therefore simply remove the udelay.

---
 arch/s390/kernel/time.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
arch/s390/kernel/time.c +1 -1
index b6517453fa23..cd79e9cd785f 100644
@@ -587,7 +587,7 @@ static int stp_sync_clock(void *data)
 		atomic_dec(&sync->cpus);
 		/* Wait for in_sync to be set. */
 		while (READ_ONCE(sync->in_sync) == 0)
-			__udelay(1);
+			;
 	}
 	if (sync->in_sync != 1)
 		/* Didn't work. Clear per-cpu in sync bit again. */
Signature · 1 line
2.39.5
author maintainer
#273 lore raw

PATCH 271/523 (powerpc/512) Fix possible `dma_unmap_single()` on uninitialized pointer

In reply to Greg Kroah-Hartman

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

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

From: Thomas Fourier <[email protected]>

[ Upstream commit 760b9b4f6de9a33ca56a05f950cabe82138d25bd ]

If the device configuration fails (if dma_dev->device_config()), sg_dma_address(&sg) is not initialized and the jump to err_dma_prep leads to calling dma_unmap_single() on sg_dma_address(&sg).

---
 arch/powerpc/platforms/512x/mpc512x_lpbfifo.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)
arch/powerpc/platforms/512x/mpc512x_lpbfifo.c +2 -4
index 04bf6ecf7d55..85e0fa7d902b 100644
@@ -240,10 +240,8 @@ static int mpc512x_lpbfifo_kick(void)
 	dma_conf.src_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;
 
 	/* Make DMA channel work with LPB FIFO data register */
-	if (dma_dev->device_config(lpbfifo.chan, &dma_conf)) {
-		ret = -EINVAL;
-		goto err_dma_prep;
-	}
+	if (dma_dev->device_config(lpbfifo.chan, &dma_conf))
+		return -EINVAL;
 
 	sg_init_table(&sg, 1);
 
Signature · 1 line
2.39.5
author maintainer
#274 lore raw

PATCH 272/523 net: fec: allow disable coalescing

In reply to Greg Kroah-Hartman

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

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

From: Jonas Rebmann <[email protected]>

[ Upstream commit b7ad21258f9e9a7f58b19595d5ceed2cde3bed68 ]

In the current implementation, IP coalescing is always enabled and cannot be disabled.

As setting maximum frames to 0 or 1, or setting delay to zero implies immediate delivery of single packets/IRQs, disable coalescing in hardware in these cases.

This also guarantees that coalescing is never enabled with ICFT or ICTT set to zero, a configuration that could lead to unpredictable behaviour according to i.MX8MP reference manual.

---
 drivers/net/ethernet/freescale/fec_main.c | 34 +++++++++++------------
 1 file changed, 16 insertions(+), 18 deletions(-)
drivers/net/ethernet/freescale/fec_main.c +16 -18
index 805434ba3035..adf70a1650f4 100644
@@ -2630,27 +2630,25 @@ static int fec_enet_us_to_itr_clock(struct net_device *ndev, int us)
 static void fec_enet_itr_coal_set(struct net_device *ndev)
 {
 	struct fec_enet_private *fep = netdev_priv(ndev);
-	int rx_itr, tx_itr;
+	u32 rx_itr = 0, tx_itr = 0;
+	int rx_ictt, tx_ictt;
 
-	/* Must be greater than zero to avoid unpredictable behavior */
-	if (!fep->rx_time_itr || !fep->rx_pkts_itr ||
-	    !fep->tx_time_itr || !fep->tx_pkts_itr)
-		return;
-
-	/* Select enet system clock as Interrupt Coalescing
-	 * timer Clock Source
-	 */
-	rx_itr = FEC_ITR_CLK_SEL;
-	tx_itr = FEC_ITR_CLK_SEL;
+	rx_ictt = fec_enet_us_to_itr_clock(ndev, fep->rx_time_itr);
+	tx_ictt = fec_enet_us_to_itr_clock(ndev, fep->tx_time_itr);
 
-	/* set ICFT and ICTT */
-	rx_itr |= FEC_ITR_ICFT(fep->rx_pkts_itr);
-	rx_itr |= FEC_ITR_ICTT(fec_enet_us_to_itr_clock(ndev, fep->rx_time_itr));
-	tx_itr |= FEC_ITR_ICFT(fep->tx_pkts_itr);
-	tx_itr |= FEC_ITR_ICTT(fec_enet_us_to_itr_clock(ndev, fep->tx_time_itr));
+	if (rx_ictt > 0 && fep->rx_pkts_itr > 1) {
+		/* Enable with enet system clock as Interrupt Coalescing timer Clock Source */
+		rx_itr = FEC_ITR_EN | FEC_ITR_CLK_SEL;
+		rx_itr |= FEC_ITR_ICFT(fep->rx_pkts_itr);
+		rx_itr |= FEC_ITR_ICTT(rx_ictt);
+	}
 
-	rx_itr |= FEC_ITR_EN;
-	tx_itr |= FEC_ITR_EN;
+	if (tx_ictt > 0 && fep->tx_pkts_itr > 1) {
+		/* Enable with enet system clock as Interrupt Coalescing timer Clock Source */
+		tx_itr = FEC_ITR_EN | FEC_ITR_CLK_SEL;
+		tx_itr |= FEC_ITR_ICFT(fep->tx_pkts_itr);
+		tx_itr |= FEC_ITR_ICTT(tx_ictt);
+	}
 
 	writel(tx_itr, fep->hwp + FEC_TXIC0);
 	writel(rx_itr, fep->hwp + FEC_RXIC0);
Signature · 1 line
2.39.5
author maintainer
#275 lore raw

PATCH 273/523 drm/amd/display: Separate set_gsl from set_gsl_source_select

In reply to Greg Kroah-Hartman

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

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

From: Ilya Bakoulin <[email protected]>

[ Upstream commit 660a467a5e7366cd6642de61f1aaeaf0d253ee68 ]

[Why/How]
Separate the checks for set_gsl and set_gsl_source_select, since source_select may not be implemented/necessary.

---
 drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)
drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c +4 -5
index c6c4888c6665..b6dc99317d7f 100644
@@ -159,14 +159,13 @@ static void dcn20_setup_gsl_group_as_lock(
 	}
 
 	/* at this point we want to program whether it's to enable or disable */
-	if (pipe_ctx->stream_res.tg->funcs->set_gsl != NULL &&
-		pipe_ctx->stream_res.tg->funcs->set_gsl_source_select != NULL) {
+	if (pipe_ctx->stream_res.tg->funcs->set_gsl != NULL) {
 		pipe_ctx->stream_res.tg->funcs->set_gsl(
 			pipe_ctx->stream_res.tg,
 			&gsl);
-
-		pipe_ctx->stream_res.tg->funcs->set_gsl_source_select(
-			pipe_ctx->stream_res.tg, group_idx,	enable ? 4 : 0);
+		if (pipe_ctx->stream_res.tg->funcs->set_gsl_source_select != NULL)
+			pipe_ctx->stream_res.tg->funcs->set_gsl_source_select(
+				pipe_ctx->stream_res.tg, group_idx, enable ? 4 : 0);
 	} else
 		BREAK_TO_DEBUGGER();
 }
Signature · 1 line
2.39.5
author maintainer
#276 lore raw

PATCH 274/523 wifi: iwlwifi: dvm: fix potential overflow in rs_fill_link_cmd()

In reply to Greg Kroah-Hartman

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

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

From: Rand Deeb <[email protected]>

[ Upstream commit e3ad987e9dc7d1e12e3f2f1e623f0e174cd0ca78 ]

The 'index' variable in the rs_fill_link_cmd() function can reach LINK_QUAL_MAX_RETRY_NUM during the execution of the inner loop. This variable is used as an index for the lq_cmd->rs_table array, which has a size of LINK_QUAL_MAX_RETRY_NUM, without proper validation.

Modify the condition of the inner loop to ensure that the 'index' variable does not exceed LINK_QUAL_MAX_RETRY_NUM - 1, thereby preventing any potential overflow issues.

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

---
 drivers/net/wireless/intel/iwlwifi/dvm/rs.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/net/wireless/intel/iwlwifi/dvm/rs.c +1 -1
index 958bfc38d390..f44448a13172 100644
@@ -2926,7 +2926,7 @@ static void rs_fill_link_cmd(struct iwl_priv *priv,
 		/* Repeat initial/next rate.
 		 * For legacy IWL_NUMBER_TRY == 1, this loop will not execute.
 		 * For HT IWL_HT_NUMBER_TRY == 3, this executes twice. */
-		while (repeat_rate > 0 && (index < LINK_QUAL_MAX_RETRY_NUM)) {
+		while (repeat_rate > 0 && index < (LINK_QUAL_MAX_RETRY_NUM - 1)) {
 			if (is_legacy(tbl_type.lq_type)) {
 				if (ant_toggle_cnt < NUM_TRY_BEFORE_ANT_TOGGLE)
 					ant_toggle_cnt++;
Signature · 1 line
2.39.5
author maintainer
#277 lore raw

PATCH 275/523 wifi: iwlwifi: fw: Fix possible memory leak in iwl_fw_dbg_collect

In reply to Greg Kroah-Hartman

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

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

From: Pagadala Yesu Anjaneyulu <[email protected]>

[ Upstream commit cc8d9cbf269dab363c768bfa9312265bc807fca5 ]

Ensure descriptor is freed on error to avoid memory leak.

---
 drivers/net/wireless/intel/iwlwifi/fw/dbg.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)
drivers/net/wireless/intel/iwlwifi/fw/dbg.c +6 -1
index 558caf78a56d..37c1158b9225 100644
@@ -2507,6 +2507,7 @@ int iwl_fw_dbg_collect(struct iwl_fw_runtime *fwrt,
 	struct iwl_fw_dump_desc *desc;
 	unsigned int delay = 0;
 	bool monitor_only = false;
+	int ret;
 
 	if (trigger) {
 		u16 occurrences = le16_to_cpu(trigger->occurrences) - 1;
@@ -2537,7 +2538,11 @@ int iwl_fw_dbg_collect(struct iwl_fw_runtime *fwrt,
 	desc->trig_desc.type = cpu_to_le32(trig);
 	memcpy(desc->trig_desc.data, str, len);
 
-	return iwl_fw_dbg_collect_desc(fwrt, desc, monitor_only, delay);
+	ret = iwl_fw_dbg_collect_desc(fwrt, desc, monitor_only, delay);
+	if (ret)
+		kfree(desc);
+
+	return ret;
 }
 IWL_EXPORT_SYMBOL(iwl_fw_dbg_collect);
 
Signature · 1 line
2.39.5
author maintainer
#278 lore raw

PATCH 276/523 drm/amd/display: Fix failed to blank crtc!

In reply to Greg Kroah-Hartman

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

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

From: Wen Chen <[email protected]>

[ Upstream commit 01f60348d8fb6b3fbcdfc7bdde5d669f95b009a4 ]

[why]
DCN35 is having “DC: failed to blank crtc!” when running HPO test cases. It's caused by not having sufficient udelay time.

[how]
Replace the old wait_for_blank_complete function with fsleep function to sleep just until the next frame should come up. This way it doesn't poll in case the pixel clock or other clock was bugged or until vactive and the vblank are hit again.

---
 drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c +1 -1
index b6dc99317d7f..402d65759e73 100644
@@ -735,7 +735,7 @@ enum dc_status dcn20_enable_stream_timing(
 		return DC_ERROR_UNEXPECTED;
 	}
 
-	hws->funcs.wait_for_blank_complete(pipe_ctx->stream_res.opp);
+	fsleep(stream->timing.v_total * (stream->timing.h_total * 10000u / stream->timing.pix_clk_100hz));
 
 	params.vertical_total_min = stream->adjust.v_total_min;
 	params.vertical_total_max = stream->adjust.v_total_max;
Signature · 1 line
2.39.5
author maintainer
#279 lore raw

PATCH 277/523 wifi: rtlwifi: fix possible skb memory leak in `_rtl_pci_rx_interrupt()`.

In reply to Greg Kroah-Hartman

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

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

From: Thomas Fourier <[email protected]>

[ Upstream commit 44c0e191004f0e3aa1bdee3be248be14dbe5b020 ]

The function _rtl_pci_init_one_rxdesc() can fail even when the new skb is passed because of a DMA mapping error. If it fails, the skb is not saved in the rx ringbuffer and thus lost.

Compile tested only

---
 drivers/net/wireless/realtek/rtlwifi/pci.c | 18 ++++++++++++------
 1 file changed, 12 insertions(+), 6 deletions(-)
drivers/net/wireless/realtek/rtlwifi/pci.c +12 -6
index f024533d34a9..bccb959d8210 100644
@@ -803,13 +803,19 @@ static void _rtl_pci_rx_interrupt(struct ieee80211_hw *hw)
 		skb = new_skb;
 no_new:
 		if (rtlpriv->use_new_trx_flow) {
-			_rtl_pci_init_one_rxdesc(hw, skb, (u8 *)buffer_desc,
-						 rxring_idx,
-						 rtlpci->rx_ring[rxring_idx].idx);
+			if (!_rtl_pci_init_one_rxdesc(hw, skb, (u8 *)buffer_desc,
+						      rxring_idx,
+						      rtlpci->rx_ring[rxring_idx].idx)) {
+				if (new_skb)
+					dev_kfree_skb_any(skb);
+			}
 		} else {
-			_rtl_pci_init_one_rxdesc(hw, skb, (u8 *)pdesc,
-						 rxring_idx,
-						 rtlpci->rx_ring[rxring_idx].idx);
+			if (!_rtl_pci_init_one_rxdesc(hw, skb, (u8 *)pdesc,
+						      rxring_idx,
+						      rtlpci->rx_ring[rxring_idx].idx)) {
+				if (new_skb)
+					dev_kfree_skb_any(skb);
+			}
 			if (rtlpci->rx_ring[rxring_idx].idx ==
 			    rtlpci->rxringcount - 1)
 				rtlpriv->cfg->ops->set_desc(hw, (u8 *)pdesc,
Signature · 1 line
2.39.5
author maintainer
#280 lore raw

PATCH 278/523 netmem: fix skb_frag_address_safe with unreadable skbs

In reply to Greg Kroah-Hartman

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

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

From: Mina Almasry <[email protected]>

[ Upstream commit 4672aec56d2e8edabcb74c3e2320301d106a377e ]

skb_frag_address_safe() needs a check that the skb_frag_page exists check similar to skb_frag_address().

---
 include/linux/skbuff.h | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)
include/linux/skbuff.h +7 -1
index ca7f2a2c3e3f..4b5731245bf1 100644
@@ -3104,7 +3104,13 @@ static inline void *skb_frag_address(const skb_frag_t *frag)
  */
 static inline void *skb_frag_address_safe(const skb_frag_t *frag)
 {
-	void *ptr = page_address(skb_frag_page(frag));
+	struct page *page = skb_frag_page(frag);
+	void *ptr;
+
+	if (!page)
+		return NULL;
+
+	ptr = page_address(page);
 	if (unlikely(!ptr))
 		return NULL;
 
Signature · 1 line
2.39.5
author maintainer
#281 lore raw

PATCH 279/523 wifi: iwlegacy: Check rate_idx range after addition

In reply to Greg Kroah-Hartman

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

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

From: Stanislaw Gruszka <[email protected]>

[ Upstream commit 0de19d5ae0b2c5b18b88c5c7f0442f707a207409 ]

Limit rate_idx to IL_LAST_OFDM_RATE for 5GHz band for thinkable case the index is incorrect.

---
 drivers/net/wireless/intel/iwlegacy/4965-mac.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)
drivers/net/wireless/intel/iwlegacy/4965-mac.c +4 -1
index 2549902552e1..6e5decf79a06 100644
@@ -1574,8 +1574,11 @@ il4965_tx_cmd_build_rate(struct il_priv *il,
 	    || rate_idx > RATE_COUNT_LEGACY)
 		rate_idx = rate_lowest_index(&il->bands[info->band], sta);
 	/* For 5 GHZ band, remap mac80211 rate indices into driver indices */
-	if (info->band == NL80211_BAND_5GHZ)
+	if (info->band == NL80211_BAND_5GHZ) {
 		rate_idx += IL_FIRST_OFDM_RATE;
+		if (rate_idx > IL_LAST_OFDM_RATE)
+			rate_idx = IL_LAST_OFDM_RATE;
+	}
 	/* Get PLCP rate for tx_cmd->rate_n_flags */
 	rate_plcp = il_rates[rate_idx].plcp;
 	/* Zero out flags for this packet */
Signature · 1 line
2.39.5
author maintainer
#282 lore raw

PATCH 280/523 net: vlan: Replace BUG() with WARN_ON_ONCE() in vlan_dev_* stubs

In reply to Greg Kroah-Hartman

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

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

From: Gal Pressman <[email protected]>

[ Upstream commit 60a8b1a5d0824afda869f18dc0ecfe72f8dfda42 ]

When CONFIG_VLAN_8021Q=n, a set of stub helpers are used, three of these helpers use BUG() unconditionally.

This code should not be reached, as callers of these functions should always check for is_vlan_dev() first, but the usage of BUG() is not recommended, replace it with WARN_ON() instead.

---
 include/linux/if_vlan.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)
include/linux/if_vlan.h +3 -3
index 64cfe7cd292c..3728e3978f83 100644
@@ -248,19 +248,19 @@ vlan_for_each(struct net_device *dev,
 
 static inline struct net_device *vlan_dev_real_dev(const struct net_device *dev)
 {
-	BUG();
+	WARN_ON_ONCE(1);
 	return NULL;
 }
 
 static inline u16 vlan_dev_vlan_id(const struct net_device *dev)
 {
-	BUG();
+	WARN_ON_ONCE(1);
 	return 0;
 }
 
 static inline __be16 vlan_dev_vlan_proto(const struct net_device *dev)
 {
-	BUG();
+	WARN_ON_ONCE(1);
 	return 0;
 }
 
Signature · 1 line
2.39.5
author maintainer
#283 lore raw

PATCH 281/523 gve: Return error for unknown admin queue command

In reply to Greg Kroah-Hartman

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

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

From: Alok Tiwari <[email protected]>

[ Upstream commit b11344f63fdd9e8c5121148a6965b41079071dd2 ]

In gve_adminq_issue_cmd(), return -EINVAL instead of 0 when an unknown admin queue command opcode is encountered.

This prevents the function from silently succeeding on invalid input and prevents undefined behavior by ensuring the function fails gracefully when an unrecognized opcode is provided.

These changes improve error handling.

---
 drivers/net/ethernet/google/gve/gve_adminq.c | 1 +
 1 file changed, 1 insertion(+)
drivers/net/ethernet/google/gve/gve_adminq.c +1 -0
index 67f2b9a61463..f02b3f01a557 100644
@@ -246,6 +246,7 @@ static int gve_adminq_issue_cmd(struct gve_priv *priv,
 		break;
 	default:
 		dev_err(&priv->pdev->dev, "unknown AQ command opcode %d\n", opcode);
+		return -EINVAL;
 	}
 
 	return 0;
Signature · 1 line
2.39.5
author maintainer
#284 lore raw

PATCH 282/523 net: dsa: b53: fix b53_imp_vlan_setup for BCM5325

In reply to Greg Kroah-Hartman

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

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

From: Álvaro Fernández Rojas <[email protected]>

[ Upstream commit c00df1018791185ea398f78af415a2a0aaa0c79c ]

CPU port should be B53_CPU_PORT instead of B53_CPU_PORT_25 for B53_PVLAN_PORT_MASK register.

---
 drivers/net/dsa/b53/b53_common.c | 4 ++++
 1 file changed, 4 insertions(+)
drivers/net/dsa/b53/b53_common.c +4 -0
index 39a56cedbc1f..971c134cd71a 100644
@@ -504,6 +504,10 @@ void b53_imp_vlan_setup(struct dsa_switch *ds, int cpu_port)
 	unsigned int i;
 	u16 pvlan;
 
+	/* BCM5325 CPU port is at 8 */
+	if ((is5325(dev) || is5365(dev)) && cpu_port == B53_CPU_PORT_25)
+		cpu_port = B53_CPU_PORT;
+
 	/* Enable the IMP port to be in the same VLAN as the other ports
 	 * on a per-port basis such that we only have Port i and IMP in
 	 * the same VLAN.
Signature · 1 line
2.39.5
author maintainer
#285 lore raw

PATCH 283/523 net: dsa: b53: prevent GMII_PORT_OVERRIDE_CTRL access on BCM5325

In reply to Greg Kroah-Hartman

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

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

From: Álvaro Fernández Rojas <[email protected]>

[ Upstream commit 37883bbc45a8555d6eca88d3a9730504d2dac86c ]

BCM5325 doesn't implement GMII_PORT_OVERRIDE_CTRL register so we should avoid reading or writing it.
PORT_OVERRIDE_RX_FLOW and PORT_OVERRIDE_TX_FLOW aren't defined on BCM5325 and we should use PORT_OVERRIDE_LP_FLOW_25 instead.

---
 drivers/net/dsa/b53/b53_common.c | 21 +++++++++++++++++----
 drivers/net/dsa/b53/b53_regs.h   |  1 +
 2 files changed, 18 insertions(+), 4 deletions(-)
drivers/net/dsa/b53/b53_common.c +17 -4
index 971c134cd71a..5840001ea3e7 100644
@@ -1106,6 +1106,8 @@ static void b53_force_link(struct b53_device *dev, int port, int link)
 	if (port == dev->imp_port) {
 		off = B53_PORT_OVERRIDE_CTRL;
 		val = PORT_OVERRIDE_EN;
+	} else if (is5325(dev)) {
+		return;
 	} else {
 		off = B53_GMII_PORT_OVERRIDE_CTRL(port);
 		val = GMII_PO_EN;
@@ -1130,6 +1132,8 @@ static void b53_force_port_config(struct b53_device *dev, int port,
 	if (port == dev->imp_port) {
 		off = B53_PORT_OVERRIDE_CTRL;
 		val = PORT_OVERRIDE_EN;
+	} else if (is5325(dev)) {
+		return;
 	} else {
 		off = B53_GMII_PORT_OVERRIDE_CTRL(port);
 		val = GMII_PO_EN;
@@ -1160,10 +1164,19 @@ static void b53_force_port_config(struct b53_device *dev, int port,
 		return;
 	}
 
-	if (rx_pause)
-		reg |= PORT_OVERRIDE_RX_FLOW;
-	if (tx_pause)
-		reg |= PORT_OVERRIDE_TX_FLOW;
+	if (rx_pause) {
+		if (is5325(dev))
+			reg |= PORT_OVERRIDE_LP_FLOW_25;
+		else
+			reg |= PORT_OVERRIDE_RX_FLOW;
+	}
+
+	if (tx_pause) {
+		if (is5325(dev))
+			reg |= PORT_OVERRIDE_LP_FLOW_25;
+		else
+			reg |= PORT_OVERRIDE_TX_FLOW;
+	}
 
 	b53_write8(dev, B53_CTRL_PAGE, off, reg);
 }
drivers/net/dsa/b53/b53_regs.h +1 -0
index b2c539a42154..e5776545a8a0 100644
@@ -92,6 +92,7 @@
 #define   PORT_OVERRIDE_SPEED_10M	(0 << PORT_OVERRIDE_SPEED_S)
 #define   PORT_OVERRIDE_SPEED_100M	(1 << PORT_OVERRIDE_SPEED_S)
 #define   PORT_OVERRIDE_SPEED_1000M	(2 << PORT_OVERRIDE_SPEED_S)
+#define   PORT_OVERRIDE_LP_FLOW_25	BIT(3) /* BCM5325 only */
 #define   PORT_OVERRIDE_RV_MII_25	BIT(4) /* BCM5325 only */
 #define   PORT_OVERRIDE_RX_FLOW		BIT(4)
 #define   PORT_OVERRIDE_TX_FLOW		BIT(5)
Signature · 1 line
2.39.5
author maintainer
#286 lore raw

PATCH 284/523 net: dsa: b53: prevent SWITCH_CTRL access on BCM5325

In reply to Greg Kroah-Hartman

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

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

From: Álvaro Fernández Rojas <[email protected]>

[ Upstream commit 22ccaaca43440e90a3b68d2183045b42247dc4be ]

BCM5325 doesn't implement SWITCH_CTRL register so we should avoid reading or writing it.

---
 drivers/net/dsa/b53/b53_common.c | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)
drivers/net/dsa/b53/b53_common.c +6 -5
index 5840001ea3e7..cb341a4d7540 100644
@@ -339,11 +339,12 @@ static void b53_set_forwarding(struct b53_device *dev, int enable)
 
 	b53_write8(dev, B53_CTRL_PAGE, B53_SWITCH_MODE, mgmt);
 
-	/* Include IMP port in dumb forwarding mode
-	 */
-	b53_read8(dev, B53_CTRL_PAGE, B53_SWITCH_CTRL, &mgmt);
-	mgmt |= B53_MII_DUMB_FWDG_EN;
-	b53_write8(dev, B53_CTRL_PAGE, B53_SWITCH_CTRL, mgmt);
+	if (!is5325(dev)) {
+		/* Include IMP port in dumb forwarding mode */
+		b53_read8(dev, B53_CTRL_PAGE, B53_SWITCH_CTRL, &mgmt);
+		mgmt |= B53_MII_DUMB_FWDG_EN;
+		b53_write8(dev, B53_CTRL_PAGE, B53_SWITCH_CTRL, mgmt);
+	}
 
 	/* Look at B53_UC_FWD_EN and B53_MC_FWD_EN to decide whether
 	 * frames should be flooded or not.
Signature · 1 line
2.39.5
author maintainer
#287 lore raw

PATCH 285/523 wifi: rtlwifi: fix possible skb memory leak in _rtl_pci_init_one_rxdesc()

In reply to Greg Kroah-Hartman

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

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

From: Thomas Fourier <[email protected]>

[ Upstream commit 76b3e5078d76f0eeadb7aacf9845399f8473da0d ]

When dma_mapping_error() is true, if a new skb has been allocated, then it must be de-allocated.

Compile tested only

---
 drivers/net/wireless/realtek/rtlwifi/pci.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)
drivers/net/wireless/realtek/rtlwifi/pci.c +4 -1
index bccb959d8210..02821588673e 100644
@@ -573,8 +573,11 @@ static int _rtl_pci_init_one_rxdesc(struct ieee80211_hw *hw,
 		dma_map_single(&rtlpci->pdev->dev, skb_tail_pointer(skb),
 			       rtlpci->rxbuffersize, DMA_FROM_DEVICE);
 	bufferaddress = *((dma_addr_t *)skb->cb);
-	if (dma_mapping_error(&rtlpci->pdev->dev, bufferaddress))
+	if (dma_mapping_error(&rtlpci->pdev->dev, bufferaddress)) {
+		if (!new_skb)
+			kfree_skb(skb);
 		return 0;
+	}
 	rtlpci->rx_ring[rxring_idx].rx_buf[desc_idx] = skb;
 	if (rtlpriv->use_new_trx_flow) {
 		/* skb->cb may be 64 bit address */
Signature · 1 line
2.39.5
author maintainer
#288 lore raw

PATCH 286/523 net: ncsi: Fix buffer overflow in fetching version id

In reply to Greg Kroah-Hartman

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

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

From: Hari Kalavakunta <[email protected]>

[ Upstream commit 8e16170ae972c7fed132bc928914a2ffb94690fc ]

In NC-SI spec v1.2 section 8.4.44.2, the firmware name doesn't need to be null terminated while its size occupies the full size of the field. Fix the buffer overflow issue by adding one additional byte for null terminator.

---
 net/ncsi/internal.h | 2 +-
 net/ncsi/ncsi-rsp.c | 1 +
 2 files changed, 2 insertions(+), 1 deletion(-)
net/ncsi/internal.h +1 -1
index c61d2e2e93ad..6ebf9e55c046 100644
@@ -107,7 +107,7 @@ struct ncsi_channel_version {
 	u8   update;		/* NCSI version update */
 	char alpha1;		/* NCSI version alpha1 */
 	char alpha2;		/* NCSI version alpha2 */
-	u8  fw_name[12];	/* Firmware name string                */
+	u8  fw_name[12 + 1];	/* Firmware name string                */
 	u32 fw_version;		/* Firmware version                   */
 	u16 pci_ids[4];		/* PCI identification                 */
 	u32 mf_id;		/* Manufacture ID                     */
net/ncsi/ncsi-rsp.c +1 -0
index 88fb86cf7b20..c1d42bbfdc7e 100644
@@ -782,6 +782,7 @@ static int ncsi_rsp_handler_gvi(struct ncsi_request *nr)
 	ncv->alpha1 = rsp->alpha1;
 	ncv->alpha2 = rsp->alpha2;
 	memcpy(ncv->fw_name, rsp->fw_name, 12);
+	ncv->fw_name[12] = '\0';
 	ncv->fw_version = ntohl(rsp->fw_version);
 	for (i = 0; i < ARRAY_SIZE(ncv->pci_ids); i++)
 		ncv->pci_ids[i] = ntohs(rsp->pci_ids[i]);
Signature · 1 line
2.39.5
author maintainer
#289 lore raw

PATCH 287/523 drm/ttm: Should to return the evict error

In reply to Greg Kroah-Hartman

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

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

From: Emily Deng <[email protected]>

[ Upstream commit 4e16a9a00239db5d819197b9a00f70665951bf50 ]

For the evict fail case, the evict error should be returned.

v2: Consider ENOENT case.

v3: Abort directly when the eviction failed for some reason (except for -ENOENT)
and not wait for the move to finish

---
 drivers/gpu/drm/ttm/ttm_resource.c | 3 +++
 1 file changed, 3 insertions(+)
drivers/gpu/drm/ttm/ttm_resource.c +3 -0
index b325b9264203..e6db512ff581 100644
@@ -113,6 +113,9 @@ int ttm_resource_manager_force_list_clean(struct ttm_bo_device *bdev,
 	}
 	spin_unlock(&glob->lru_lock);
 
+	if (ret && ret != -ENOENT)
+		return ret;
+
 	spin_lock(&man->move_lock);
 	fence = dma_fence_get(man->move);
 	spin_unlock(&man->move_lock);
Signature · 1 line
2.39.5
author maintainer
#290 lore raw

PATCH 288/523 uapi: in6: restore visibility of most IPv6 socket options

In reply to Greg Kroah-Hartman

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

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

From: Jakub Kicinski <[email protected]>

[ Upstream commit 31557b3487b349464daf42bc4366153743c1e727 ]

A decade ago commit 6d08acd2d32e ("in6: fix conflict with glibc") hid the definitions of IPV6 options, because GCC was complaining about duplicates. The commit did not list the warnings seen, but trying to recreate them now I think they are (building iproute2):

In file included from ./include/uapi/rdma/rdma_user_cm.h:39,

                 from rdma.h:16,
                 from res.h:9,
                 from res-ctx.c:7:
../include/uapi/linux/in6.h:171:9: warning: ‘IPV6_ADD_MEMBERSHIP’ redefined
  171 | #define IPV6_ADD_MEMBERSHIP     20
      |         ^~~~~~~~~~~~~~~~~~~
In file included from /usr/include/netinet/in.h:37,
                 from rdma.h:13:
/usr/include/bits/in.h:233:10: note: this is the location of the previous definition
  233 | # define IPV6_ADD_MEMBERSHIP    IPV6_JOIN_GROUP
      |          ^~~~~~~~~~~~~~~~~~~
../include/uapi/linux/in6.h:172:9: warning: ‘IPV6_DROP_MEMBERSHIP’ redefined
  172 | #define IPV6_DROP_MEMBERSHIP    21
      |         ^~~~~~~~~~~~~~~~~~~~
/usr/include/bits/in.h:234:10: note: this is the location of the previous definition
  234 | # define IPV6_DROP_MEMBERSHIP   IPV6_LEAVE_GROUP
      |          ^~~~~~~~~~~~~~~~~~~~

Compilers don't complain about redefinition if the defines are identical, but here we have the kernel using the literal value, and glibc using an indirection (defining to a name of another define, with the same numerical value).

Problem is, the commit in question hid all the IPV6 socket options, and glibc has a pretty sparse list. For instance it lacks Flow Label related options. Willem called this out in commit 3fb321fde22d ("selftests/net: ipv6 flowlabel"):

  /* uapi/glibc weirdness may leave this undefined */
  #ifndef IPV6_FLOWINFO
  #define IPV6_FLOWINFO 11
  #endif

More interestingly some applications (socat) use a #ifdef IPV6_FLOWINFO to gate compilation of thier rudimentary flow label support. (For added confusion socat misspells it as IPV4_FLOWINFO in some places.)

Hide only the two defines we know glibc has a problem with. If we discover more warnings we can hide more but we should avoid covering the entire block of defines for "IPV6 socket options".

---
 include/uapi/linux/in6.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)
include/uapi/linux/in6.h +2 -2
index 5ad396a57eb3..327fd76c0962 100644
@@ -151,7 +151,6 @@ struct in6_flowlabel_req {
 /*
  *	IPV6 socket options
  */
-#if __UAPI_DEF_IPV6_OPTIONS
 #define IPV6_ADDRFORM		1
 #define IPV6_2292PKTINFO	2
 #define IPV6_2292HOPOPTS	3
@@ -168,8 +167,10 @@ struct in6_flowlabel_req {
 #define IPV6_MULTICAST_IF	17
 #define IPV6_MULTICAST_HOPS	18
 #define IPV6_MULTICAST_LOOP	19
+#if __UAPI_DEF_IPV6_OPTIONS
 #define IPV6_ADD_MEMBERSHIP	20
 #define IPV6_DROP_MEMBERSHIP	21
+#endif
 #define IPV6_ROUTER_ALERT	22
 #define IPV6_MTU_DISCOVER	23
 #define IPV6_MTU		24
@@ -202,7 +203,6 @@ struct in6_flowlabel_req {
 #define IPV6_IPSEC_POLICY	34
 #define IPV6_XFRM_POLICY	35
 #define IPV6_HDRINCL		36
-#endif
 
 /*
  * Multicast:
Signature · 1 line
2.39.5
author maintainer
#291 lore raw

PATCH 289/523 net: dsa: b53: fix IP_MULTICAST_CTRL on BCM5325

In reply to Greg Kroah-Hartman

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

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

From: Álvaro Fernández Rojas <[email protected]>

[ Upstream commit 044d5ce2788b165798bfd173548e61bf7b6baf4d ]

BCM5325 doesn't implement B53_UC_FWD_EN, B53_MC_FWD_EN or B53_IPMC_FWD_EN.

---
 drivers/net/dsa/b53/b53_common.c | 18 +++++++++++-------
 drivers/net/dsa/b53/b53_regs.h   |  1 +
 2 files changed, 12 insertions(+), 7 deletions(-)
drivers/net/dsa/b53/b53_common.c +11 -7
index cb341a4d7540..361f9be65386 100644
@@ -344,14 +344,18 @@ static void b53_set_forwarding(struct b53_device *dev, int enable)
 		b53_read8(dev, B53_CTRL_PAGE, B53_SWITCH_CTRL, &mgmt);
 		mgmt |= B53_MII_DUMB_FWDG_EN;
 		b53_write8(dev, B53_CTRL_PAGE, B53_SWITCH_CTRL, mgmt);
-	}
 
-	/* Look at B53_UC_FWD_EN and B53_MC_FWD_EN to decide whether
-	 * frames should be flooded or not.
-	 */
-	b53_read8(dev, B53_CTRL_PAGE, B53_IP_MULTICAST_CTRL, &mgmt);
-	mgmt |= B53_UC_FWD_EN | B53_MC_FWD_EN | B53_IPMC_FWD_EN;
-	b53_write8(dev, B53_CTRL_PAGE, B53_IP_MULTICAST_CTRL, mgmt);
+		/* Look at B53_UC_FWD_EN and B53_MC_FWD_EN to decide whether
+		 * frames should be flooded or not.
+		 */
+		b53_read8(dev, B53_CTRL_PAGE, B53_IP_MULTICAST_CTRL, &mgmt);
+		mgmt |= B53_UC_FWD_EN | B53_MC_FWD_EN | B53_IPMC_FWD_EN;
+		b53_write8(dev, B53_CTRL_PAGE, B53_IP_MULTICAST_CTRL, mgmt);
+	} else {
+		b53_read8(dev, B53_CTRL_PAGE, B53_IP_MULTICAST_CTRL, &mgmt);
+		mgmt |= B53_IP_MCAST_25;
+		b53_write8(dev, B53_CTRL_PAGE, B53_IP_MULTICAST_CTRL, mgmt);
+	}
 }
 
 static void b53_enable_vlan(struct b53_device *dev, bool enable,
drivers/net/dsa/b53/b53_regs.h +1 -0
index e5776545a8a0..77fb7ae660b8 100644
@@ -104,6 +104,7 @@
 
 /* IP Multicast control (8 bit) */
 #define B53_IP_MULTICAST_CTRL		0x21
+#define  B53_IP_MCAST_25		BIT(0)
 #define  B53_IPMC_FWD_EN		BIT(1)
 #define  B53_UC_FWD_EN			BIT(6)
 #define  B53_MC_FWD_EN			BIT(7)
Signature · 1 line
2.39.5
author maintainer
#292 lore raw

PATCH 290/523 vhost: fail early when __vhost_add_used() fails

In reply to Greg Kroah-Hartman

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

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

From: Jason Wang <[email protected]>

[ Upstream commit b4ba1207d45adaafa2982c035898b36af2d3e518 ]

This patch fails vhost_add_used_n() early when __vhost_add_used() fails to make sure used idx is not updated with stale used ring information.

Message-Id: <[email protected]>

---
 drivers/vhost/vhost.c | 3 +++
 1 file changed, 3 insertions(+)
drivers/vhost/vhost.c +3 -0
index 8ed9c9b63eb1..97e00c481870 100644
@@ -2416,6 +2416,9 @@ int vhost_add_used_n(struct vhost_virtqueue *vq, struct vring_used_elem *heads,
 	}
 	r = __vhost_add_used_n(vq, heads, count);
 
+	if (r < 0)
+		return r;
+
 	/* Make sure buffer is written before we update index. */
 	smp_wmb();
 	if (vhost_put_used_idx(vq)) {
Signature · 1 line
2.39.5
author maintainer
#293 lore raw

PATCH 291/523 cifs: Fix calling CIFSFindFirst() for root path without msearch

In reply to Greg Kroah-Hartman

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

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

From: Pali Rohár <[email protected]>

[ Upstream commit b460249b9a1dab7a9f58483e5349d045ad6d585c ]

To query root path (without msearch wildcard) it is needed to send pattern '\' instead of '' (empty string).

This allows to use CIFSFindFirst() to query information about root path which is being used in followup changes.

This change fixes the stat() syscall called on the root path on the mount. It is because stat() syscall uses the cifs_query_path_info() function and it can fallback to the CIFSFindFirst() usage with msearch=false.

---
 fs/cifs/cifssmb.c | 10 ++++++++++
 1 file changed, 10 insertions(+)
fs/cifs/cifssmb.c +10 -0
index 95992c93bbe3..a19e5e7c7d0f 100644
@@ -4470,6 +4470,12 @@ CIFSFindFirst(const unsigned int xid, struct cifs_tcon *tcon,
 			pSMB->FileName[name_len] = 0;
 			pSMB->FileName[name_len+1] = 0;
 			name_len += 2;
+		} else if (!searchName[0]) {
+			pSMB->FileName[0] = CIFS_DIR_SEP(cifs_sb);
+			pSMB->FileName[1] = 0;
+			pSMB->FileName[2] = 0;
+			pSMB->FileName[3] = 0;
+			name_len = 4;
 		}
 	} else {
 		name_len = copy_path_name(pSMB->FileName, searchName);
@@ -4481,6 +4487,10 @@ CIFSFindFirst(const unsigned int xid, struct cifs_tcon *tcon,
 			pSMB->FileName[name_len] = '*';
 			pSMB->FileName[name_len+1] = 0;
 			name_len += 2;
+		} else if (!searchName[0]) {
+			pSMB->FileName[0] = CIFS_DIR_SEP(cifs_sb);
+			pSMB->FileName[1] = 0;
+			name_len = 2;
 		}
 	}
 
Signature · 1 line
2.39.5
author maintainer
#294 lore raw

PATCH 292/523 ext4: do not BUG when INLINE_DATA_FL lacks system.data xattr

In reply to Greg Kroah-Hartman

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

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

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

[ Upstream commit 099b847ccc6c1ad2f805d13cfbcc83f5b6d4bc42 ]

A syzbot fuzzed image triggered a BUG_ON in ext4_update_inline_data() when an inode had the INLINE_DATA_FL flag set but was missing the system.data extended attribute.

Since this can happen due to a maiciouly fuzzed file system, we shouldn't BUG, but rather, report it as a corrupted file system.

Add similar replacements of BUG_ON with EXT4_ERROR_INODE() ii ext4_create_inline_data() and ext4_inline_data_truncate().

---
 fs/ext4/inline.c | 19 ++++++++++++++++---
 1 file changed, 16 insertions(+), 3 deletions(-)
fs/ext4/inline.c +16 -3
index 8ccbb3703954..f02fcaa62804 100644
@@ -296,7 +296,11 @@ static int ext4_create_inline_data(handle_t *handle,
 	if (error)
 		goto out;
 
-	BUG_ON(!is.s.not_found);
+	if (!is.s.not_found) {
+		EXT4_ERROR_INODE(inode, "unexpected inline data xattr");
+		error = -EFSCORRUPTED;
+		goto out;
+	}
 
 	error = ext4_xattr_ibody_set(handle, inode, &i, &is);
 	if (error) {
@@ -347,7 +351,11 @@ static int ext4_update_inline_data(handle_t *handle, struct inode *inode,
 	if (error)
 		goto out;
 
-	BUG_ON(is.s.not_found);
+	if (is.s.not_found) {
+		EXT4_ERROR_INODE(inode, "missing inline data xattr");
+		error = -EFSCORRUPTED;
+		goto out;
+	}
 
 	len -= EXT4_MIN_INLINE_DATA_SIZE;
 	value = kzalloc(len, GFP_NOFS);
@@ -1939,7 +1947,12 @@ int ext4_inline_data_truncate(struct inode *inode, int *has_inline)
 			if ((err = ext4_xattr_ibody_find(inode, &i, &is)) != 0)
 				goto out_error;
 
-			BUG_ON(is.s.not_found);
+			if (is.s.not_found) {
+				EXT4_ERROR_INODE(inode,
+						 "missing inline data xattr");
+				err = -EFSCORRUPTED;
+				goto out_error;
+			}
 
 			value_len = le32_to_cpu(is.s.here->e_value_size);
 			value = kmalloc(value_len, GFP_NOFS);
Signature · 1 line
2.39.5
author maintainer
#295 lore raw

PATCH 293/523 scsi: libiscsi: Initialize iscsi_conn->dd_data only if memory is allocated

In reply to Greg Kroah-Hartman

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

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

From: Showrya M N <[email protected]>

[ Upstream commit 3ea3a256ed81f95ab0f3281a0e234b01a9cae605 ]

In case of an ib_fast_reg_mr allocation failure during iSER setup, the machine hits a panic because iscsi_conn->dd_data is initialized unconditionally, even when no memory is allocated (dd_size == 0). This leads invalid pointer dereference during connection teardown.

Fix by setting iscsi_conn->dd_data only if memory is actually allocated.

Panic trace:
------------
iser: iser_create_fastreg_desc: Failed to allocate ib_fast_reg_mr err=-12
iser: iser_alloc_rx_descriptors: failed allocating rx descriptors / data buffers

 BUG: unable to handle page fault for address: fffffffffffffff8
 RIP: 0010:swake_up_locked.part.5+0xa/0x40
 Call Trace:
  complete+0x31/0x40
  iscsi_iser_conn_stop+0x88/0xb0 [ib_iser]
  iscsi_stop_conn+0x66/0xc0 [scsi_transport_iscsi]
  iscsi_if_stop_conn+0x14a/0x150 [scsi_transport_iscsi]
  iscsi_if_rx+0x1135/0x1834 [scsi_transport_iscsi]
  ? netlink_lookup+0x12f/0x1b0
  ? netlink_deliver_tap+0x2c/0x200
  netlink_unicast+0x1ab/0x280
  netlink_sendmsg+0x257/0x4f0
  ? _copy_from_user+0x29/0x60
  sock_sendmsg+0x5f/0x70
---
 drivers/scsi/libiscsi.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)
drivers/scsi/libiscsi.c +2 -1
index 05799b41974d..bad5730bf7ab 100644
@@ -2949,7 +2949,8 @@ iscsi_conn_setup(struct iscsi_cls_session *cls_session, int dd_size,
 	conn = cls_conn->dd_data;
 	memset(conn, 0, sizeof(*conn) + dd_size);
 
-	conn->dd_data = cls_conn->dd_data + sizeof(*conn);
+	if (dd_size)
+		conn->dd_data = cls_conn->dd_data + sizeof(*conn);
 	conn->session = session;
 	conn->cls_conn = cls_conn;
 	conn->c_stage = ISCSI_CONN_INITIAL_STAGE;
Signature · 1 line
2.39.5
author maintainer
#296 lore raw

PATCH 294/523 fs/orangefs: use snprintf() instead of sprintf()

In reply to Greg Kroah-Hartman

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

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

From: Amir Mohammad Jahangirzad <[email protected]>

[ Upstream commit cdfa1304657d6f23be8fd2bb0516380a3c89034e ]

sprintf() is discouraged for use with bounded destination buffers as it does not prevent buffer overflows when the formatted output exceeds the destination buffer size. snprintf() is a safer alternative as it limits the number of bytes written and ensures NUL-termination.

Replace sprintf() with snprintf() for copying the debug string into a temporary buffer, using ORANGEFS_MAX_DEBUG_STRING_LEN as the maximum size to ensure safe formatting and prevent memory corruption in edge cases.

EDIT: After this patch sat on linux-next for a few days, Dan Carpenter saw it and suggested that I use scnprintf instead of snprintf. I made the change and retested.

---
 fs/orangefs/orangefs-debugfs.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
fs/orangefs/orangefs-debugfs.c +1 -1
index b57140ebfad0..cd4bfd92ebd6 100644
@@ -354,7 +354,7 @@ static ssize_t orangefs_debug_read(struct file *file,
 		goto out;
 
 	mutex_lock(&orangefs_debug_lock);
-	sprintf_ret = sprintf(buf, "%s", (char *)file->private_data);
+	sprintf_ret = scnprintf(buf, ORANGEFS_MAX_DEBUG_STRING_LEN, "%s", (char *)file->private_data);
 	mutex_unlock(&orangefs_debug_lock);
 
 	read_ret = simple_read_from_buffer(ubuf, count, ppos, buf, sprintf_ret);
Signature · 1 line
2.39.5
author maintainer
#297 lore raw

PATCH 295/523 watchdog: dw_wdt: Fix default timeout

In reply to Greg Kroah-Hartman

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

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

From: Sebastian Reichel <[email protected]>

[ Upstream commit ac3dbb91e0167d017f44701dd51c1efe30d0c256 ]

The Synopsys Watchdog driver sets the default timeout to 30 seconds, but on some devices this is not a valid timeout. E.g. on RK3588 the actual timeout being used is 44 seconds instead.

Once the watchdog is started the value is updated accordingly, but it would be better to expose a sensible timeout to userspace without the need to first start the watchdog.

---
 drivers/watchdog/dw_wdt.c | 2 ++
 1 file changed, 2 insertions(+)
drivers/watchdog/dw_wdt.c +2 -0
index 3cd118281980..d18530bafc4e 100644
@@ -661,6 +661,8 @@ static int dw_wdt_drv_probe(struct platform_device *pdev)
 	} else {
 		wdd->timeout = DW_WDT_DEFAULT_SECONDS;
 		watchdog_init_timeout(wdd, 0, dev);
+		/* Limit timeout value to hardware constraints. */
+		dw_wdt_set_timeout(wdd, wdd->timeout);
 	}
 
 	platform_set_drvdata(pdev, dw_wdt);
Signature · 1 line
2.39.5
author maintainer
#298 lore raw

PATCH 296/523 MIPS: vpe-mt: add missing prototypes for vpe_{alloc,start,stop,free}

In reply to Greg Kroah-Hartman

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

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

From: Shiji Yang <[email protected]>

[ Upstream commit 844615dd0f2d95c018ec66b943e08af22b62aff3 ]

These functions are exported but their prototypes are not defined. This patch adds the missing function prototypes to fix the following compilation warnings:

arch/mips/kernel/vpe-mt.c:180:7: error: no previous prototype for 'vpe_alloc' [-Werror=missing-prototypes]
180 | void *vpe_alloc(void)

      |       ^~~~~~~~~
arch/mips/kernel/vpe-mt.c:198:5: error: no previous prototype for 'vpe_start' [-Werror=missing-prototypes]
  198 | int vpe_start(void *vpe, unsigned long start)
      |     ^~~~~~~~~
arch/mips/kernel/vpe-mt.c:208:5: error: no previous prototype for 'vpe_stop' [-Werror=missing-prototypes]
  208 | int vpe_stop(void *vpe)
      |     ^~~~~~~~
arch/mips/kernel/vpe-mt.c:229:5: error: no previous prototype for 'vpe_free' [-Werror=missing-prototypes]
  229 | int vpe_free(void *vpe)
      |     ^~~~~~~~
---
 arch/mips/include/asm/vpe.h | 8 ++++++++
 1 file changed, 8 insertions(+)
arch/mips/include/asm/vpe.h +8 -0
index 012731546cf6..3de6b0ff1627 100644
@@ -126,4 +126,12 @@ void cleanup_tc(struct tc *tc);
 
 int __init vpe_module_init(void);
 void __exit vpe_module_exit(void);
+
+#ifdef CONFIG_MIPS_VPE_LOADER_MT
+void *vpe_alloc(void);
+int vpe_start(void *vpe, unsigned long start);
+int vpe_stop(void *vpe);
+int vpe_free(void *vpe);
+#endif /* CONFIG_MIPS_VPE_LOADER_MT */
+
 #endif /* _ASM_VPE_H */
Signature · 1 line
2.39.5
author maintainer
#299 lore raw

PATCH 297/523 scsi: bfa: Double-free fix

In reply to Greg Kroah-Hartman

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

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

From: jackysliu <[email protected]>

[ Upstream commit add4c4850363d7c1b72e8fce9ccb21fdd2cf5dc9 ]

When the bfad_im_probe() function fails during initialization, the memory pointed to by bfad->im is freed without setting bfad->im to NULL.

Subsequently, during driver uninstallation, when the state machine enters the bfad_sm_stopping state and calls the bfad_im_probe_undo() function, it attempts to free the memory pointed to by bfad->im again, thereby triggering a double-free vulnerability.

Set bfad->im to NULL if probing fails.

---
 drivers/scsi/bfa/bfad_im.c | 1 +
 1 file changed, 1 insertion(+)
drivers/scsi/bfa/bfad_im.c +1 -0
index 22f06be2606f..6dcf1094e01b 100644
@@ -707,6 +707,7 @@ bfad_im_probe(struct bfad_s *bfad)
 
 	if (bfad_thread_workq(bfad) != BFA_STATUS_OK) {
 		kfree(im);
+		bfad->im = NULL;
 		return BFA_STATUS_FAILED;
 	}
 
Signature · 1 line
2.39.5
author maintainer
#300 lore raw

PATCH 298/523 jfs: truncate good inode pages when hard link is 0

In reply to Greg Kroah-Hartman

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

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

From: Lizhi Xu <[email protected]>

[ Upstream commit 2d91b3765cd05016335cd5df5e5c6a29708ec058 ]

The fileset value of the inode copy from the disk by the reproducer is AGGR_RESERVED_I. When executing evict, its hard link number is 0, so its inode pages are not truncated. This causes the bugon to be triggered when executing clear_inode() because nrpages is greater than 0.

---
 fs/jfs/inode.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
fs/jfs/inode.c +1 -1
index 980aa3300f10..2472b33e3a2d 100644
@@ -145,9 +145,9 @@ void jfs_evict_inode(struct inode *inode)
 	if (!inode->i_nlink && !is_bad_inode(inode)) {
 		dquot_initialize(inode);
 
+		truncate_inode_pages_final(&inode->i_data);
 		if (JFS_IP(inode)->fileset == FILESYSTEM_I) {
 			struct inode *ipimap = JFS_SBI(inode->i_sb)->ipimap;
-			truncate_inode_pages_final(&inode->i_data);
 
 			if (test_cflag(COMMIT_Freewmap, inode))
 				jfs_free_zero_link(inode);
Signature · 1 line
2.39.5
author maintainer
#301 lore raw

PATCH 299/523 jfs: Regular file corruption check

In reply to Greg Kroah-Hartman

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

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

From: Edward Adam Davis <[email protected]>

[ Upstream commit 2d04df8116426b6c7b9f8b9b371250f666a2a2fb ]

The reproducer builds a corrupted file on disk with a negative i_size value. Add a check when opening this file to avoid subsequent operation failures.

---
 fs/jfs/file.c | 3 +++
 1 file changed, 3 insertions(+)
fs/jfs/file.c +3 -0
index 930d2701f206..44872daeca01 100644
@@ -44,6 +44,9 @@ static int jfs_open(struct inode *inode, struct file *file)
 {
 	int rc;
 
+	if (S_ISREG(inode->i_mode) && inode->i_size < 0)
+		return -EIO;
+
 	if ((rc = dquot_file_open(inode, file)))
 		return rc;
 
Signature · 1 line
2.39.5
author maintainer
#302 lore raw

PATCH 300/523 jfs: upper bound check of tree index in dbAllocAG

In reply to Greg Kroah-Hartman

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

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

From: Arnaud Lecomte <[email protected]>

[ Upstream commit c214006856ff52a8ff17ed8da52d50601d54f9ce ]

When computing the tree index in dbAllocAG, we never check if we are out of bounds realative to the size of the stree.
This could happen in a scenario where the filesystem metadata are corrupted.

---
 fs/jfs/jfs_dmap.c | 6 ++++++
 1 file changed, 6 insertions(+)
fs/jfs/jfs_dmap.c +6 -0
index 234b7cc4acfa..f34025cc9b05 100644
@@ -1457,6 +1457,12 @@ dbAllocAG(struct bmap * bmp, int agno, s64 nblocks, int l2nb, s64 * results)
 	    (1 << (L2LPERCTL - (bmp->db_agheight << 1))) / bmp->db_agwidth;
 	ti = bmp->db_agstart + bmp->db_agwidth * (agno & (agperlev - 1));
 
+	if (ti < 0 || ti >= le32_to_cpu(dcp->nleafs)) {
+		jfs_error(bmp->db_ipbmap->i_sb, "Corrupt dmapctl page\n");
+		release_metapage(mp);
+		return -EIO;
+	}
+
 	/* dmap control page trees fan-out by 4 and a single allocation
 	 * group may be described by 1 or 2 subtrees within the ag level
 	 * dmap control page, depending upon the ag size. examine the ag's
Signature · 1 line
2.39.5
author maintainer
#303 lore raw

PATCH 301/523 MIPS: Dont crash in stack_top() for tasks without ABI or vDSO

In reply to Greg Kroah-Hartman

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

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

From: Thomas Weißschuh <[email protected]>

[ Upstream commit e9f4a6b3421e936c3ee9d74710243897d74dbaa2 ]

Not all tasks have an ABI associated or vDSO mapped,
for example kthreads never do.
If such a task ever ends up calling stack_top(), it will derefence the NULL ABI pointer and crash.

This can for example happen when using kunit:

    mips_stack_top+0x28/0xc0
    arch_pick_mmap_layout+0x190/0x220
    kunit_vm_mmap_init+0xf8/0x138
    __kunit_add_resource+0x40/0xa8
    kunit_vm_mmap+0x88/0xd8
    usercopy_test_init+0xb8/0x240
    kunit_try_run_case+0x5c/0x1a8
    kunit_generic_run_threadfn_adapter+0x28/0x50
    kthread+0x118/0x240
    ret_from_kernel_thread+0x14/0x1c

Only dereference the ABI point if it is set.

The GIC page is also included as it is specific to the vDSO. Also move the randomization adjustment into the same conditional.

---
 arch/mips/kernel/process.c | 16 +++++++++-------
 1 file changed, 9 insertions(+), 7 deletions(-)
arch/mips/kernel/process.c +9 -7
index 98ecaf6f3edb..0a5710a4d696 100644
@@ -675,18 +675,20 @@ unsigned long mips_stack_top(void)
 	}
 
 	/* Space for the VDSO, data page & GIC user page */
-	top -= PAGE_ALIGN(current->thread.abi->vdso->size);
-	top -= PAGE_SIZE;
-	top -= mips_gic_present() ? PAGE_SIZE : 0;
+	if (current->thread.abi) {
+		top -= PAGE_ALIGN(current->thread.abi->vdso->size);
+		top -= PAGE_SIZE;
+		top -= mips_gic_present() ? PAGE_SIZE : 0;
+
+		/* Space to randomize the VDSO base */
+		if (current->flags & PF_RANDOMIZE)
+			top -= VDSO_RANDOMIZE_SIZE;
+	}
 
 	/* Space for cache colour alignment */
 	if (cpu_has_dc_aliases)
 		top -= shm_align_mask + 1;
 
-	/* Space to randomize the VDSO base */
-	if (current->flags & PF_RANDOMIZE)
-		top -= VDSO_RANDOMIZE_SIZE;
-
 	return top;
 }
 
Signature · 1 line
2.39.5
author maintainer
#304 lore raw

PATCH 302/523 leds: leds-lp50xx: Handle reg to get correct multi_index

In reply to Greg Kroah-Hartman

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

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

From: Johan Adolfsson <[email protected]>

[ Upstream commit 2e84a5e5374232e6f356ce5c079a5658d7e4af2c ]

mc_subled used for multi_index needs well defined array indexes, to guarantee the desired result, use reg for that.

If devicetree child nodes is processed in random or reverse order you may end up with multi_index "blue green red" instead of the expected "red green blue".
If user space apps uses multi_index to deduce how to control the leds they would most likely be broken without this patch if devicetree processing is reversed (which it appears to be).

arch/arm/boot/dts/aspeed/aspeed-bmc-facebook-fuji.dts has reg set but I don't see how it can have worked without this change.

If reg is not set, an error is returned,
If reg is out of range, an error is returned.
reg within led child nodes starts with 0, to map to the iout in each bank.

---
 drivers/leds/leds-lp50xx.c | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)
drivers/leds/leds-lp50xx.c +10 -1
index d4529082935b..279f3958e0ab 100644
@@ -493,6 +493,7 @@ static int lp50xx_probe_dt(struct lp50xx *priv)
 		}
 
 		fwnode_for_each_child_node(child, led_node) {
+			int multi_index;
 			ret = fwnode_property_read_u32(led_node, "color",
 						       &color_id);
 			if (ret) {
@@ -500,8 +501,16 @@ static int lp50xx_probe_dt(struct lp50xx *priv)
 				dev_err(priv->dev, "Cannot read color\n");
 				goto child_out;
 			}
+			ret = fwnode_property_read_u32(led_node, "reg", &multi_index);
+			if (ret != 0) {
+				dev_err(priv->dev, "reg must be set\n");
+				return -EINVAL;
+			} else if (multi_index >= LP50XX_LEDS_PER_MODULE) {
+				dev_err(priv->dev, "reg %i out of range\n", multi_index);
+				return -EINVAL;
+			}
 
-			mc_led_info[num_colors].color_index = color_id;
+			mc_led_info[multi_index].color_index = color_id;
 			num_colors++;
 		}
 
Signature · 1 line
2.39.5