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

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

From: Pavel Begunkov asml.silence@gmail.com

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.

Cc: stable@vger.kernel.org Fixes: 2b188cc1bb857 ("Add io_uring IO interface") Signed-off-by: Pavel Begunkov asml.silence@gmail.com Link: https://lore.kernel.org/r/47c666c4ee1df2018863af3a2028af18feef11ed.175141251... Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- include/uapi/linux/io_uring.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -38,7 +38,7 @@ 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 */

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

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

From: Takashi Iwai tiwai@suse.de

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 yjjuny.lee@samsung.com Cc: stable@vger.kernel.org Link: https://patch.msgid.link/20250814081245.8902-2-tiwai@suse.de Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- sound/usb/stream.c | 25 ++++++++++++++++++++++--- 1 file changed, 22 insertions(+), 3 deletions(-)

--- a/sound/usb/stream.c +++ b/sound/usb/stream.c @@ -341,20 +341,28 @@ 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 @@ -456,6 +464,7 @@ snd_pcm_chmap_elem *convert_chmap_v3(str chmap->map[c++] = map; } p += cs_len; + len -= cs_len; }

if (channels < c) @@ -876,7 +885,7 @@ 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;

@@ -1003,6 +1012,16 @@ 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;

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

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

From: Christopher Eby kreed@kreed.org

commit 0db77eccd964b11ab2b757031d1354fcc5a025ea upstream.

Framework Laptop 13 (AMD Ryzen AI 300) requires the same quirk for headset detection as other Framework 13 models.

Signed-off-by: Christopher Eby kreed@kreed.org Cc: stable@vger.kernel.org Link: https://patch.msgid.link/20250810030006.9060-1-kreed@kreed.org Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- sound/pci/hda/patch_realtek.c | 1 + 1 file changed, 1 insertion(+)

--- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -10456,6 +10456,7 @@ static const struct snd_pci_quirk alc269 SND_PCI_QUIRK(0xf111, 0x0001, "Framework Laptop", ALC295_FIXUP_FRAMEWORK_LAPTOP_MIC_NO_PRESENCE), SND_PCI_QUIRK(0xf111, 0x0006, "Framework Laptop", ALC295_FIXUP_FRAMEWORK_LAPTOP_MIC_NO_PRESENCE), SND_PCI_QUIRK(0xf111, 0x0009, "Framework Laptop", ALC295_FIXUP_FRAMEWORK_LAPTOP_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0xf111, 0x000b, "Framework Laptop", ALC295_FIXUP_FRAMEWORK_LAPTOP_MIC_NO_PRESENCE), SND_PCI_QUIRK(0xf111, 0x000c, "Framework Laptop", ALC295_FIXUP_FRAMEWORK_LAPTOP_MIC_NO_PRESENCE),

#if 0

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

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

From: Wang Zhaolong wangzhaolong@huaweicloud.com

commit e19d8dd694d261ac26adb2a26121a37c107c81ad upstream.

Commit 34331d7beed7 ("smb: client: fix first command failure during re-negotiation") addressed a race condition by updating lstrp before entering negotiate state. However, this approach may have some unintended side effects.

The lstrp field is documented as "when we got last response from this server", and updating it before actually receiving a server response could potentially affect other mechanisms that rely on this timestamp. For example, the SMB echo detection logic also uses lstrp as a reference point. In scenarios with frequent user operations during reconnect states, the repeated calls to cifs_negotiate_protocol() might continuously update lstrp, which could interfere with the echo detection timing.

Additionally, commit 266b5d02e14f ("smb: client: fix race condition in negotiate timeout by using more precise timing") introduced a dedicated neg_start field specifically for tracking negotiate start time. This provides a more precise solution for the original race condition while preserving the intended semantics of lstrp.

Since the race condition is now properly handled by the neg_start mechanism, the lstrp update in cifs_negotiate_protocol() is no longer necessary and can be safely removed.

Fixes: 266b5d02e14f ("smb: client: fix race condition in negotiate timeout by using more precise timing") Cc: stable@vger.kernel.org Acked-by: Paulo Alcantara (Red Hat) pc@manguebit.org Signed-off-by: Wang Zhaolong wangzhaolong@huaweicloud.com Signed-off-by: Steve French stfrench@microsoft.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/smb/client/connect.c | 1 - 1 file changed, 1 deletion(-)

--- a/fs/smb/client/connect.c +++ b/fs/smb/client/connect.c @@ -4217,7 +4217,6 @@ retry: return 0; }

- server->lstrp = jiffies; server->tcpStatus = CifsInNegotiate; server->neg_start = jiffies; spin_unlock(&server->srv_lock);

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

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

From: David Thompson davthompson@nvidia.com

commit 63c7bc53a35e785accdc2ceab8f72d94501931ab upstream.

The gpio-mlxbf2 driver interfaces with four GPIO controllers, device instances 0-3. There are two IRQ resources shared between the four controllers, and they are found in the ACPI table for instances 0 and 3. The driver should not use platform_get_irq(), otherwise this error is logged when probing instances 1 and 2: mlxbf2_gpio MLNXBF22:01: error -ENXIO: IRQ index 0 not found

Fixes: 2b725265cb08 ("gpio: mlxbf2: Introduce IRQ support") Cc: stable@vger.kernel.org Signed-off-by: David Thompson davthompson@nvidia.com Reviewed-by: Shravan Kumar Ramani shravankr@nvidia.com Reviewed-by: Mika Westerberg mika.westerberg@linux.intel.com Link: https://lore.kernel.org/r/20250728144619.29894-1-davthompson@nvidia.com Signed-off-by: Bartosz Golaszewski bartosz.golaszewski@linaro.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/gpio/gpio-mlxbf2.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/drivers/gpio/gpio-mlxbf2.c +++ b/drivers/gpio/gpio-mlxbf2.c @@ -374,7 +374,7 @@ mlxbf2_gpio_probe(struct platform_device gc->ngpio = npins; gc->owner = THIS_MODULE;

- irq = platform_get_irq(pdev, 0); + irq = platform_get_irq_optional(pdev, 0); if (irq >= 0) { gs->irq_chip.name = name; gs->irq_chip.irq_set_type = mlxbf2_gpio_irq_set_type;

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

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

From: Florian Larysch fl@n621.de

commit 49db61c27c4bbd24364086dc0892bd3e14c1502e upstream.

Commit 21b688dabecb ("net: phy: micrel: Cable Diag feature for lan8814 phy") introduced cable_test support for the LAN8814 that reuses parts of the KSZ886x logic and introduced the cable_diag_reg and pair_mask parameters to account for differences between those chips.

However, it did not update the ksz8081_type struct, so those members are now 0, causing no pairs to be tested in ksz886x_cable_test_get_status and ksz886x_cable_test_wait_for_completion to poll the wrong register for the affected PHYs (Basic Control/Reset, which is 0 in normal operation) and exit immediately.

Fix this by setting both struct members accordingly.

Fixes: 21b688dabecb ("net: phy: micrel: Cable Diag feature for lan8814 phy") Cc: stable@vger.kernel.org Signed-off-by: Florian Larysch fl@n621.de Link: https://patch.msgid.link/20250723222250.13960-1-fl@n621.de Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/phy/micrel.c | 2 ++ 1 file changed, 2 insertions(+)

--- a/drivers/net/phy/micrel.c +++ b/drivers/net/phy/micrel.c @@ -356,6 +356,8 @@ static const struct kszphy_type ksz8051_

static const struct kszphy_type ksz8081_type = { .led_mode_reg = MII_KSZPHY_CTRL_2, + .cable_diag_reg = KSZ8081_LMD, + .pair_mask = KSZPHY_WIRE_PAIR_MASK, .has_broadcast_disable = true, .has_nand_tree_disable = true, .has_rmii_ref_clk_sel = true,

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

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

From: Johan Hovold johan@kernel.org

commit 3e13274ca8750823e8b68181bdf185d238febe0d upstream.

The reference count to the WED devices has already been incremented when looking them up using of_find_device_by_node() so drop the bogus additional reference taken during probe.

Fixes: 804775dfc288 ("net: ethernet: mtk_eth_soc: add support for Wireless Ethernet Dispatch (WED)") Cc: stable@vger.kernel.org # 5.19 Cc: Felix Fietkau nbd@nbd.name Signed-off-by: Johan Hovold johan@kernel.org Reviewed-by: Simon Horman horms@kernel.org Link: https://patch.msgid.link/20250725171213.880-5-johan@kernel.org Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/mediatek/mtk_wed.c | 1 - 1 file changed, 1 deletion(-)

--- a/drivers/net/ethernet/mediatek/mtk_wed.c +++ b/drivers/net/ethernet/mediatek/mtk_wed.c @@ -1074,7 +1074,6 @@ void mtk_wed_add_hw(struct device_node * if (!pdev) goto err_of_node_put;

- get_device(&pdev->dev); irq = platform_get_irq(pdev, 0); if (irq < 0) goto err_put_device;

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

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

From: Xu Yang xu.yang_2@nxp.com

commit 4faff70959d51078f9ee8372f8cff0d7045e4114 upstream.

Without setting phy_mask for ax88772 mdio bus, current driver may create at most 32 mdio phy devices with phy address range from 0x00 ~ 0x1f. DLink DUB-E100 H/W Ver B1 is such a device. However, only one main phy device will bind to net phy driver. This is creating issue during system suspend/resume since phy_polling_mode() in phy_state_machine() will directly deference member of phydev->drv for non-main phy devices. Then NULL pointer dereference issue will occur. Due to only external phy or internal phy is necessary, add phy_mask for ax88772 mdio bus to workarnoud the issue.

Closes: https://lore.kernel.org/netdev/20250806082931.3289134-1-xu.yang_2@nxp.com Fixes: e532a096be0e ("net: usb: asix: ax88772: add phylib support") Cc: stable@vger.kernel.org Signed-off-by: Xu Yang xu.yang_2@nxp.com Tested-by: Oleksij Rempel o.rempel@pengutronix.de Reviewed-by: Oleksij Rempel o.rempel@pengutronix.de Link: https://patch.msgid.link/20250811092931.860333-1-xu.yang_2@nxp.com Signed-off-by: Paolo Abeni pabeni@redhat.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/usb/asix_devices.c | 1 + 1 file changed, 1 insertion(+)

--- a/drivers/net/usb/asix_devices.c +++ b/drivers/net/usb/asix_devices.c @@ -676,6 +676,7 @@ static int ax88772_init_mdio(struct usbn priv->mdio->read = &asix_mdio_bus_read; priv->mdio->write = &asix_mdio_bus_write; priv->mdio->name = "Asix MDIO Bus"; + priv->mdio->phy_mask = ~(BIT(priv->phy_addr) | BIT(AX_EMBD_PHY_ADDR)); /* mii bus name is usb-<usb bus number>-<usb device number> */ snprintf(priv->mdio->id, MII_BUS_ID_SIZE, "usb-%03d:%03d", dev->udev->bus->busnum, dev->udev->devnum);

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

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

From: Dai Ngo dai.ngo@oracle.com

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.

Reported-by: Petro Pavlov petro.pavlov@vastdata.com Fixes: c44c5eeb2c02 ("[PATCH] nfsd4: add open state code for CLAIM_DELEGATE_CUR") Cc: stable@vger.kernel.org Signed-off-by: Dai Ngo dai.ngo@oracle.com Reviewed-by: Jeff Layton jlayton@kernel.org Signed-off-by: Chuck Lever chuck.lever@oracle.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/nfsd/nfs4state.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+)

--- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -5733,6 +5733,20 @@ 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;

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

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

From: Huacai Chen chenhuacai@loongson.cn

commit a02fd05661d73a8507dd70dd820e9b984490c545 upstream.

Like s390 and the jailhouse hypervisor, LoongArch's PCI architecture allows passing isolated PCI functions to a guest OS instance. So it is possible that there is a multi-function device without function 0 for the host or guest.

Allow probing such functions by adding a IS_ENABLED(CONFIG_LOONGARCH) case in the hypervisor_isolated_pci_functions() helper.

This is similar to commit 189c6c33ff42 ("PCI: Extend isolated function probing to s390").

Signed-off-by: Huacai Chen chenhuacai@loongson.cn Signed-off-by: Bjorn Helgaas bhelgaas@google.com Cc: stable@vger.kernel.org Link: https://patch.msgid.link/20250624062927.4037734-1-chenhuacai@loongson.cn Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- include/linux/hypervisor.h | 3 +++ 1 file changed, 3 insertions(+)

--- a/include/linux/hypervisor.h +++ b/include/linux/hypervisor.h @@ -37,6 +37,9 @@ static inline bool hypervisor_isolated_p if (IS_ENABLED(CONFIG_S390)) return true;

+ if (IS_ENABLED(CONFIG_LOONGARCH)) + return true; + return jailhouse_paravirt(); }

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

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

From: Ma Ke make24@iscas.ac.cn

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.

Cc: stable@vger.kernel.org Fixes: 3ee70591d6c4 ("sunvdc: prevent sunvdc panic when mpgroup disk added to guest domain") Signed-off-by: Ma Ke make24@iscas.ac.cn Link: https://lore.kernel.org/r/20250719075856.3447953-1-make24@iscas.ac.cn Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/block/sunvdc.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

--- a/drivers/block/sunvdc.c +++ b/drivers/block/sunvdc.c @@ -956,8 +956,10 @@ 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; }

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

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

From: Jann Horn jannh@google.com

commit f2e467a48287c868818085aa35389a224d226732 upstream.

Ensure that epoll instances can never form a graph deeper than EP_MAX_NESTS+1 links.

Currently, ep_loop_check_proc() ensures that the graph is loop-free and does some recursion depth checks, but those recursion depth checks don't limit the depth of the resulting tree for two reasons:

- They don't look upwards in the tree. - If there are multiple downwards paths of different lengths, only one of the paths is actually considered for the depth check since commit 28d82dc1c4ed ("epoll: limit paths").

Essentially, the current recursion depth check in ep_loop_check_proc() just serves to prevent it from recursing too deeply while checking for loops.

A more thorough check is done in reverse_path_check() after the new graph edge has already been created; this checks, among other things, that no paths going upwards from any non-epoll file with a length of more than 5 edges exist. However, this check does not apply to non-epoll files.

As a result, it is possible to recurse to a depth of at least roughly 500, tested on v6.15. (I am unsure if deeper recursion is possible; and this may have changed with commit 8c44dac8add7 ("eventpoll: Fix priority inversion problem").)

To fix it:

1. In ep_loop_check_proc(), note the subtree depth of each visited node, and use subtree depths for the total depth calculation even when a subtree has already been visited. 2. Add ep_get_upwards_depth_proc() for similarly determining the maximum depth of an upwards walk. 3. In ep_loop_check(), use these values to limit the total path length between epoll nodes to EP_MAX_NESTS edges.

Fixes: 22bacca48a17 ("epoll: prevent creating circular epoll structures") Cc: stable@vger.kernel.org Signed-off-by: Jann Horn jannh@google.com Link: https://lore.kernel.org/20250711-epoll-recursion-fix-v1-1-fb2457c33292@googl... Signed-off-by: Christian Brauner brauner@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/eventpoll.c | 60 +++++++++++++++++++++++++++++++++++++++++++-------------- 1 file changed, 46 insertions(+), 14 deletions(-)

--- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -216,6 +216,7 @@ struct eventpoll { /* used to optimize loop detection check */ u64 gen; struct hlist_head refs; + u8 loop_check_depth;

#ifdef CONFIG_NET_RX_BUSY_POLL /* used to track busy poll napi_id */ @@ -1951,23 +1952,24 @@ static int ep_poll(struct eventpoll *ep, }

/** - * ep_loop_check_proc - verify that adding an epoll file inside another - * epoll structure does not violate the constraints, in - * terms of closed loops, or too deep chains (which can - * result in excessive stack usage). + * ep_loop_check_proc - verify that adding an epoll file @ep inside another + * epoll file does not create closed loops, and + * determine the depth of the subtree starting at @ep * * @ep: the &struct eventpoll to be currently checked. * @depth: Current depth of the path being checked. * - * Return: %zero if adding the epoll @file inside current epoll - * structure @ep does not violate the constraints, or %-1 otherwise. + * Return: depth of the subtree, or INT_MAX if we found a loop or went too deep. */ static int ep_loop_check_proc(struct eventpoll *ep, int depth) { - int error = 0; + int result = 0; struct rb_node *rbp; struct epitem *epi;

+ if (ep->gen == loop_check_gen) + return ep->loop_check_depth; + mutex_lock_nested(&ep->mtx, depth + 1); ep->gen = loop_check_gen; for (rbp = rb_first_cached(&ep->rbr); rbp; rbp = rb_next(rbp)) { @@ -1975,13 +1977,11 @@ static int ep_loop_check_proc(struct eve if (unlikely(is_file_epoll(epi->ffd.file))) { struct eventpoll *ep_tovisit; ep_tovisit = epi->ffd.file->private_data; - if (ep_tovisit->gen == loop_check_gen) - continue; if (ep_tovisit == inserting_into || depth > EP_MAX_NESTS) - error = -1; + result = INT_MAX; else - error = ep_loop_check_proc(ep_tovisit, depth + 1); - if (error != 0) + result = max(result, ep_loop_check_proc(ep_tovisit, depth + 1) + 1); + if (result > EP_MAX_NESTS) break; } else { /* @@ -1995,9 +1995,27 @@ static int ep_loop_check_proc(struct eve list_file(epi->ffd.file); } } + ep->loop_check_depth = result; mutex_unlock(&ep->mtx);

- return error; + return result; +} + +/** + * ep_get_upwards_depth_proc - determine depth of @ep when traversed upwards + */ +static int ep_get_upwards_depth_proc(struct eventpoll *ep, int depth) +{ + int result = 0; + struct epitem *epi; + + if (ep->gen == loop_check_gen) + return ep->loop_check_depth; + hlist_for_each_entry_rcu(epi, &ep->refs, fllink) + result = max(result, ep_get_upwards_depth_proc(epi->ep, depth + 1) + 1); + ep->gen = loop_check_gen; + ep->loop_check_depth = result; + return result; }

/** @@ -2013,8 +2031,22 @@ static int ep_loop_check_proc(struct eve */ static int ep_loop_check(struct eventpoll *ep, struct eventpoll *to) { + int depth, upwards_depth; + inserting_into = ep; - return ep_loop_check_proc(to, 0); + /* + * Check how deep down we can get from @to, and whether it is possible + * to loop up to @ep. + */ + depth = ep_loop_check_proc(to, 0); + if (depth > EP_MAX_NESTS) + return -1; + /* Check how far up we can go from @ep. */ + rcu_read_lock(); + upwards_depth = ep_get_upwards_depth_proc(ep, 0); + rcu_read_unlock(); + + return (depth+1+upwards_depth > EP_MAX_NESTS) ? -1 : 0; }

static void clear_tfile_check_list(void)

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

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

From: Jiayi Li lijiayi@kylinos.cn

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") Signed-off-by: Jiayi Li lijiayi@kylinos.cn Link: https://patch.msgid.link/20250721032606.3459369-1-lijiayi@kylinos.cn [ rjw: Consolidate pr-related checks in acpi_processor_ppc_init() ] [ rjw: Subject and changelog adjustments ] Cc: 5.4+ stable@vger.kernel.org # 5.4+: 2d8b39a62a5d ACPI: processor: Avoid NULL pointer dereferences at init time Cc: 5.4+ stable@vger.kernel.org # 5.4+: 3000ce3c52f8 cpufreq: Use per-policy frequency QoS Cc: 5.4+ stable@vger.kernel.org # 5.4+: a1bb46c36ce3 ACPI: processor: Add QoS requests for all CPUs Cc: 5.4+ stable@vger.kernel.org # 5.4+ Signed-off-by: Rafael J. Wysocki rafael.j.wysocki@intel.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/acpi/processor_perflib.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-)

--- a/drivers/acpi/processor_perflib.c +++ b/drivers/acpi/processor_perflib.c @@ -173,11 +173,14 @@ 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;

/* @@ -193,6 +196,11 @@ 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); } }

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

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

From: Sean Christopherson seanjc@google.com

[ Upstream commit be45bc4eff33d9a7dae84a2150f242a91a617402 ]

Enable/disable local IRQs, i.e. set/clear RFLAGS.IF, in the common svm_vcpu_enter_exit() just after/before guest_state_{enter,exit}_irqoff() so that VMRUN is not executed in an STI shadow. AMD CPUs have a quirk (some would say "bug"), where the STI shadow bleeds into the guest's intr_state field if a #VMEXIT occurs during injection of an event, i.e. if the VMRUN doesn't complete before the subsequent #VMEXIT.

The spurious "interrupts masked" state is relatively benign, as it only occurs during event injection and is transient. Because KVM is already injecting an event, the guest can't be in HLT, and if KVM is querying IRQ blocking for injection, then KVM would need to force an immediate exit anyways since injecting multiple events is impossible.

However, because KVM copies int_state verbatim from vmcb02 to vmcb12, the spurious STI shadow is visible to L1 when running a nested VM, which can trip sanity checks, e.g. in VMware's VMM.

Hoist the STI+CLI all the way to C code, as the aforementioned calls to guest_state_{enter,exit}_irqoff() already inform lockdep that IRQs are enabled/disabled, and taking a fault on VMRUN with RFLAGS.IF=1 is already possible. I.e. if there's kernel code that is confused by running with RFLAGS.IF=1, then it's already a problem. In practice, since GIF=0 also blocks NMIs, the only change in exposure to non-KVM code (relative to surrounding VMRUN with STI+CLI) is exception handling code, and except for the kvm_rebooting=1 case, all exception in the core VM-Enter/VM-Exit path are fatal.

Use the "raw" variants to enable/disable IRQs to avoid tracing in the "no instrumentation" code; the guest state helpers also take care of tracing IRQ state.

Oppurtunstically document why KVM needs to do STI in the first place.

Reported-by: Doug Covelli doug.covelli@broadcom.com Closes: https://lore.kernel.org/all/CADH9ctBs1YPmE4aCfGPNBwA10cA8RuAk2gO7542DjMZgs4u... Fixes: f14eec0a3203 ("KVM: SVM: move more vmentry code to assembly") Cc: stable@vger.kernel.org Reviewed-by: Jim Mattson jmattson@google.com Link: https://lore.kernel.org/r/20250224165442.2338294-2-seanjc@google.com Signed-off-by: Sean Christopherson seanjc@google.com [sean: resolve minor syntatic conflict in __svm_sev_es_vcpu_run()] Signed-off-by: Sean Christopherson seanjc@google.com Signed-off-by: Sasha Levin sashal@kernel.org --- arch/x86/kvm/svm/svm.c | 14 ++++++++++++++ arch/x86/kvm/svm/vmenter.S | 9 +-------- 2 files changed, 15 insertions(+), 8 deletions(-)

diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index b6bbd0dc4e65..c95a84afc35f 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -3982,6 +3982,18 @@ static noinstr void svm_vcpu_enter_exit(struct kvm_vcpu *vcpu, bool spec_ctrl_in

guest_state_enter_irqoff();

+ /* + * Set RFLAGS.IF prior to VMRUN, as the host's RFLAGS.IF at the time of + * VMRUN controls whether or not physical IRQs are masked (KVM always + * runs with V_INTR_MASKING_MASK). Toggle RFLAGS.IF here to avoid the + * temptation to do STI+VMRUN+CLI, as AMD CPUs bleed the STI shadow + * into guest state if delivery of an event during VMRUN triggers a + * #VMEXIT, and the guest_state transitions already tell lockdep that + * IRQs are being enabled/disabled. Note! GIF=0 for the entirety of + * this path, so IRQs aren't actually unmasked while running host code. + */ + raw_local_irq_enable(); + amd_clear_divider();

if (sev_es_guest(vcpu->kvm)) @@ -3989,6 +4001,8 @@ static noinstr void svm_vcpu_enter_exit(struct kvm_vcpu *vcpu, bool spec_ctrl_in else __svm_vcpu_run(svm, spec_ctrl_intercepted);

+ raw_local_irq_disable(); + guest_state_exit_irqoff(); }

diff --git a/arch/x86/kvm/svm/vmenter.S b/arch/x86/kvm/svm/vmenter.S index 42824f9b06a2..48b72625cc45 100644 --- a/arch/x86/kvm/svm/vmenter.S +++ b/arch/x86/kvm/svm/vmenter.S @@ -170,12 +170,8 @@ SYM_FUNC_START(__svm_vcpu_run) VM_CLEAR_CPU_BUFFERS

/* Enter guest mode */ - sti - 3: vmrun %_ASM_AX 4: - cli - /* Pop @svm to RAX while it's the only available register. */ pop %_ASM_AX

@@ -343,11 +339,8 @@ SYM_FUNC_START(__svm_sev_es_vcpu_run) VM_CLEAR_CPU_BUFFERS

/* Enter guest mode */ - sti - 1: vmrun %_ASM_AX - -2: cli +2:

/* Pop @svm to RDI, guest registers have been saved already. */ pop %_ASM_DI

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

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

From: Sean Christopherson seanjc@google.com

[ Upstream commit 76bce9f10162cd4b36ac0b7889649b22baf70ebd ]

Pass the target vCPU to the hwapic_isr_update() vendor hook so that VMX can defer the update until after nested VM-Exit if an EOI for L1's vAPIC occurs while L2 is active.

Note, commit d39850f57d21 ("KVM: x86: Drop @vcpu parameter from kvm_x86_ops.hwapic_isr_update()") removed the parameter with the justification that doing so "allows for a decent amount of (future) cleanup in the APIC code", but it's not at all clear what cleanup was intended, or if it was ever realized.

No functional change intended.

Cc: stable@vger.kernel.org Reviewed-by: Chao Gao chao.gao@intel.com Tested-by: Chao Gao chao.gao@intel.com Link: https://lore.kernel.org/r/20241128000010.4051275-2-seanjc@google.com Signed-off-by: Sean Christopherson seanjc@google.com [sean: account for lack of kvm_x86_call(), drop vmx/x86_ops.h change] Signed-off-by: Sean Christopherson seanjc@google.com Signed-off-by: Sasha Levin sashal@kernel.org --- arch/x86/include/asm/kvm_host.h | 2 +- arch/x86/kvm/lapic.c | 8 ++++---- arch/x86/kvm/vmx/vmx.c | 2 +- 3 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 17b4e61a52b9..6db42ee82032 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1552,7 +1552,7 @@ struct kvm_x86_ops { bool (*check_apicv_inhibit_reasons)(enum kvm_apicv_inhibit reason); void (*refresh_apicv_exec_ctrl)(struct kvm_vcpu *vcpu); void (*hwapic_irr_update)(struct kvm_vcpu *vcpu, int max_irr); - void (*hwapic_isr_update)(int isr); + void (*hwapic_isr_update)(struct kvm_vcpu *vcpu, int isr); bool (*guest_apic_has_interrupt)(struct kvm_vcpu *vcpu); void (*load_eoi_exitmap)(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap); void (*set_virtual_apic_mode)(struct kvm_vcpu *vcpu); diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 42eec987ac3d..3d65d6a023c9 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -587,7 +587,7 @@ static inline void apic_set_isr(int vec, struct kvm_lapic *apic) * just set SVI. */ if (unlikely(apic->apicv_active)) - static_call_cond(kvm_x86_hwapic_isr_update)(vec); + static_call_cond(kvm_x86_hwapic_isr_update)(apic->vcpu, vec); else { ++apic->isr_count; BUG_ON(apic->isr_count > MAX_APIC_VECTOR); @@ -632,7 +632,7 @@ static inline void apic_clear_isr(int vec, struct kvm_lapic *apic) * and must be left alone. */ if (unlikely(apic->apicv_active)) - static_call_cond(kvm_x86_hwapic_isr_update)(apic_find_highest_isr(apic)); + static_call_cond(kvm_x86_hwapic_isr_update)(apic->vcpu, apic_find_highest_isr(apic)); else { --apic->isr_count; BUG_ON(apic->isr_count < 0); @@ -2554,7 +2554,7 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event) if (apic->apicv_active) { static_call_cond(kvm_x86_apicv_post_state_restore)(vcpu); static_call_cond(kvm_x86_hwapic_irr_update)(vcpu, -1); - static_call_cond(kvm_x86_hwapic_isr_update)(-1); + static_call_cond(kvm_x86_hwapic_isr_update)(vcpu, -1); }

vcpu->arch.apic_arb_prio = 0; @@ -2847,7 +2847,7 @@ int kvm_apic_set_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s) if (apic->apicv_active) { static_call_cond(kvm_x86_apicv_post_state_restore)(vcpu); static_call_cond(kvm_x86_hwapic_irr_update)(vcpu, apic_find_highest_irr(apic)); - static_call_cond(kvm_x86_hwapic_isr_update)(apic_find_highest_isr(apic)); + static_call_cond(kvm_x86_hwapic_isr_update)(vcpu, apic_find_highest_isr(apic)); } kvm_make_request(KVM_REQ_EVENT, vcpu); if (ioapic_in_kernel(vcpu->kvm)) diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 9a5cb896229f..721ba6ddb121 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -6708,7 +6708,7 @@ static void vmx_set_apic_access_page_addr(struct kvm_vcpu *vcpu) put_page(page); }

-static void vmx_hwapic_isr_update(int max_isr) +static void vmx_hwapic_isr_update(struct kvm_vcpu *vcpu, int max_isr) { u16 status; u8 old;

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

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

From: Sean Christopherson seanjc@google.com

[ Upstream commit fb71c795935652fa20eaf9517ca9547f5af99a76 ]

Move KVM's snapshot of DEBUGCTL to kvm_vcpu_arch and take the snapshot in common x86, so that SVM can also use the snapshot.

Opportunistically change the field to a u64. While bits 63:32 are reserved on AMD, not mentioned at all in Intel's SDM, and managed as an "unsigned long" by the kernel, DEBUGCTL is an MSR and therefore a 64-bit value.

Reviewed-by: Xiaoyao Li xiaoyao.li@intel.com Cc: stable@vger.kernel.org Reviewed-and-tested-by: Ravi Bangoria ravi.bangoria@amd.com Link: https://lore.kernel.org/r/20250227222411.3490595-4-seanjc@google.com Signed-off-by: Sean Christopherson seanjc@google.com [sean: resolve minor syntatic conflict in vmx_vcpu_load()] Signed-off-by: Sean Christopherson seanjc@google.com Signed-off-by: Sasha Levin sashal@kernel.org --- arch/x86/include/asm/kvm_host.h | 1 + arch/x86/kvm/vmx/vmx.c | 8 ++------ arch/x86/kvm/vmx/vmx.h | 2 -- arch/x86/kvm/x86.c | 1 + 4 files changed, 4 insertions(+), 8 deletions(-)

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 6db42ee82032..555c7bf35e28 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -677,6 +677,7 @@ struct kvm_vcpu_arch { u32 pkru; u32 hflags; u64 efer; + u64 host_debugctl; u64 apic_base; struct kvm_lapic *apic; /* kernel irqchip context */ bool load_eoi_exitmap_pending; diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 7b87fbc69b21..c24da2cff208 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -1418,13 +1418,9 @@ void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu, */ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu) { - struct vcpu_vmx *vmx = to_vmx(vcpu); - vmx_vcpu_load_vmcs(vcpu, cpu, NULL);

vmx_vcpu_pi_load(vcpu, cpu); - - vmx->host_debugctlmsr = get_debugctlmsr(); }

static void vmx_vcpu_put(struct kvm_vcpu *vcpu) @@ -7275,8 +7271,8 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu) }

/* MSR_IA32_DEBUGCTLMSR is zeroed on vmexit. Restore it if needed */ - if (vmx->host_debugctlmsr) - update_debugctlmsr(vmx->host_debugctlmsr); + if (vcpu->arch.host_debugctl) + update_debugctlmsr(vcpu->arch.host_debugctl);

#ifndef CONFIG_X86_64 /* diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index 8b4b149bd9c1..357819872d80 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -352,8 +352,6 @@ struct vcpu_vmx { /* apic deadline value in host tsc */ u64 hv_deadline_tsc;

- unsigned long host_debugctlmsr; - /* * Only bits masked by msr_ia32_feature_control_valid_bits can be set in * msr_ia32_feature_control. FEAT_CTL_LOCKED is always included diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index a6dc8f662fa4..ba24bb50af57 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -4742,6 +4742,7 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)

/* Save host pkru register if supported */ vcpu->arch.host_pkru = read_pkru(); + vcpu->arch.host_debugctl = get_debugctlmsr();

/* Apply any externally detected TSC adjustments (due to suspend) */ if (unlikely(vcpu->arch.tsc_offset_adjustment)) {

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

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

From: Sean Christopherson seanjc@google.com

[ Upstream commit e76ae52747a82a548742107b4100e90da41a624d ]

Add helpers to print unimplemented MSR accesses and condition all such prints on report_ignored_msrs, i.e. honor userspace's request to not print unimplemented MSRs. Even though vcpu_unimpl() is ratelimited, printing can still be problematic, e.g. if a print gets stalled when host userspace is writing MSRs during live migration, an effective stall can result in very noticeable disruption in the guest.

E.g. the profile below was taken while calling KVM_SET_MSRS on the PMU counters while the PMU was disabled in KVM.

- 99.75% 0.00% [.] __ioctl - __ioctl - 99.74% entry_SYSCALL_64_after_hwframe do_syscall_64 sys_ioctl - do_vfs_ioctl - 92.48% kvm_vcpu_ioctl - kvm_arch_vcpu_ioctl - 85.12% kvm_set_msr_ignored_check svm_set_msr kvm_set_msr_common printk vprintk_func vprintk_default vprintk_emit console_unlock call_console_drivers univ8250_console_write serial8250_console_write uart_console_write

Reported-by: Aaron Lewis aaronlewis@google.com Reviewed-by: Vitaly Kuznetsov vkuznets@redhat.com Link: https://lore.kernel.org/r/20230124234905.3774678-3-seanjc@google.com Stable-dep-of: 7d0cce6cbe71 ("KVM: VMX: Wrap all accesses to IA32_DEBUGCTL with getter/setter APIs") Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Sean Christopherson seanjc@google.com Signed-off-by: Sasha Levin sashal@kernel.org --- arch/x86/kvm/hyperv.c | 10 ++++------ arch/x86/kvm/svm/svm.c | 5 ++--- arch/x86/kvm/vmx/vmx.c | 4 +--- arch/x86/kvm/x86.c | 18 +++++------------- arch/x86/kvm/x86.h | 12 ++++++++++++ 5 files changed, 24 insertions(+), 25 deletions(-)

diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index 28555bbd52e8..cb0a531e13c5 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -1406,8 +1406,7 @@ static int kvm_hv_set_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data, case HV_X64_MSR_SYNDBG_CONTROL ... HV_X64_MSR_SYNDBG_PENDING_BUFFER: return syndbg_set_msr(vcpu, msr, data, host); default: - vcpu_unimpl(vcpu, "Hyper-V unhandled wrmsr: 0x%x data 0x%llx\n", - msr, data); + kvm_pr_unimpl_wrmsr(vcpu, msr, data); return 1; } return 0; @@ -1528,8 +1527,7 @@ static int kvm_hv_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host) return 1; break; default: - vcpu_unimpl(vcpu, "Hyper-V unhandled wrmsr: 0x%x data 0x%llx\n", - msr, data); + kvm_pr_unimpl_wrmsr(vcpu, msr, data); return 1; }

@@ -1581,7 +1579,7 @@ static int kvm_hv_get_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata, case HV_X64_MSR_SYNDBG_CONTROL ... HV_X64_MSR_SYNDBG_PENDING_BUFFER: return syndbg_get_msr(vcpu, msr, pdata, host); default: - vcpu_unimpl(vcpu, "Hyper-V unhandled rdmsr: 0x%x\n", msr); + kvm_pr_unimpl_rdmsr(vcpu, msr); return 1; }

@@ -1646,7 +1644,7 @@ static int kvm_hv_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata, data = APIC_BUS_FREQUENCY; break; default: - vcpu_unimpl(vcpu, "Hyper-V unhandled rdmsr: 0x%x\n", msr); + kvm_pr_unimpl_rdmsr(vcpu, msr); return 1; } *pdata = data; diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index b922f31d1415..2c0f9c7d1242 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -3035,8 +3035,7 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) break; case MSR_IA32_DEBUGCTLMSR: if (!lbrv) { - vcpu_unimpl(vcpu, "%s: MSR_IA32_DEBUGCTL 0x%llx, nop\n", - __func__, data); + kvm_pr_unimpl_wrmsr(vcpu, ecx, data); break; }

@@ -3077,7 +3076,7 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) case MSR_VM_CR: return svm_set_vm_cr(vcpu, data); case MSR_VM_IGNNE: - vcpu_unimpl(vcpu, "unimplemented wrmsr: 0x%x data 0x%llx\n", ecx, data); + kvm_pr_unimpl_wrmsr(vcpu, ecx, data); break; case MSR_AMD64_DE_CFG: { struct kvm_msr_entry msr_entry; diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index c24da2cff208..390af16d9a67 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -2140,9 +2140,7 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)

invalid = data & ~vmx_get_supported_debugctl(vcpu, msr_info->host_initiated); if (invalid & (DEBUGCTLMSR_BTF|DEBUGCTLMSR_LBR)) { - if (report_ignored_msrs) - vcpu_unimpl(vcpu, "%s: BTF|LBR in IA32_DEBUGCTLMSR 0x%llx, nop\n", - __func__, data); + kvm_pr_unimpl_wrmsr(vcpu, msr_index, data); data &= ~(DEBUGCTLMSR_BTF|DEBUGCTLMSR_LBR); invalid &= ~(DEBUGCTLMSR_BTF|DEBUGCTLMSR_LBR); } diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index b0ae61ba9b99..d224180c56f5 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -3573,7 +3573,6 @@ static void record_steal_time(struct kvm_vcpu *vcpu)

int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) { - bool pr = false; u32 msr = msr_info->index; u64 data = msr_info->data;

@@ -3625,15 +3624,13 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (data == BIT_ULL(18)) { vcpu->arch.msr_hwcr = data; } else if (data != 0) { - vcpu_unimpl(vcpu, "unimplemented HWCR wrmsr: 0x%llx\n", - data); + kvm_pr_unimpl_wrmsr(vcpu, msr, data); return 1; } break; case MSR_FAM10H_MMIO_CONF_BASE: if (data != 0) { - vcpu_unimpl(vcpu, "unimplemented MMIO_CONF_BASE wrmsr: " - "0x%llx\n", data); + kvm_pr_unimpl_wrmsr(vcpu, msr, data); return 1; } break; @@ -3813,16 +3810,13 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)

case MSR_K7_PERFCTR0 ... MSR_K7_PERFCTR3: case MSR_P6_PERFCTR0 ... MSR_P6_PERFCTR1: - pr = true; - fallthrough; case MSR_K7_EVNTSEL0 ... MSR_K7_EVNTSEL3: case MSR_P6_EVNTSEL0 ... MSR_P6_EVNTSEL1: if (kvm_pmu_is_valid_msr(vcpu, msr)) return kvm_pmu_set_msr(vcpu, msr_info);

- if (pr || data != 0) - vcpu_unimpl(vcpu, "disabled perfctr wrmsr: " - "0x%x data 0x%llx\n", msr, data); + if (data) + kvm_pr_unimpl_wrmsr(vcpu, msr, data); break; case MSR_K7_CLK_CTL: /* @@ -3849,9 +3843,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) /* Drop writes to this legacy MSR -- see rdmsr * counterpart for further detail. */ - if (report_ignored_msrs) - vcpu_unimpl(vcpu, "ignored wrmsr: 0x%x data 0x%llx\n", - msr, data); + kvm_pr_unimpl_wrmsr(vcpu, msr, data); break; case MSR_AMD64_OSVW_ID_LENGTH: if (!guest_cpuid_has(vcpu, X86_FEATURE_OSVW)) diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index 9de72586f406..f3554bf05201 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -331,6 +331,18 @@ extern bool report_ignored_msrs;

extern bool eager_page_split;

+static inline void kvm_pr_unimpl_wrmsr(struct kvm_vcpu *vcpu, u32 msr, u64 data) +{ + if (report_ignored_msrs) + vcpu_unimpl(vcpu, "Unhandled WRMSR(0x%x) = 0x%llx\n", msr, data); +} + +static inline void kvm_pr_unimpl_rdmsr(struct kvm_vcpu *vcpu, u32 msr) +{ + if (report_ignored_msrs) + vcpu_unimpl(vcpu, "Unhandled RDMSR(0x%x)\n", msr); +} + static inline u64 nsec_to_cycles(struct kvm_vcpu *vcpu, u64 nsec) { return pvclock_scale_delta(nsec, vcpu->arch.virtual_tsc_mult,

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

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

From: Sean Christopherson seanjc@google.com

[ Upstream commit e6b5d16bbd2d4c8259ad76aa33de80d561aba5f9 ]

Re-enter the guest in the fast path if VMX preeemption timer VM-Exit was "spurious", i.e. if KVM "soft disabled" the timer by writing -1u and by some miracle the timer expired before any other VM-Exit occurred. This is just an intermediate step to cleaning up the preemption timer handling, optimizing these types of spurious VM-Exits is not interesting as they are extremely rare/infrequent.

Link: https://lore.kernel.org/r/20240110012705.506918-3-seanjc@google.com Signed-off-by: Sean Christopherson seanjc@google.com Signed-off-by: Sasha Levin sashal@kernel.org --- arch/x86/kvm/vmx/vmx.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 0b495979a02b..96bbccd9477c 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -5933,8 +5933,15 @@ static fastpath_t handle_fastpath_preemption_timer(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu);

- if (!vmx->req_immediate_exit && - !unlikely(vmx->loaded_vmcs->hv_timer_soft_disabled)) { + /* + * In the *extremely* unlikely scenario that this is a spurious VM-Exit + * due to the timer expiring while it was "soft" disabled, just eat the + * exit and re-enter the guest. + */ + if (unlikely(vmx->loaded_vmcs->hv_timer_soft_disabled)) + return EXIT_FASTPATH_REENTER_GUEST; + + if (!vmx->req_immediate_exit) { kvm_lapic_expired_hv_timer(vcpu); return EXIT_FASTPATH_REENTER_GUEST; }

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

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

From: Sean Christopherson seanjc@google.com

[ Upstream commit bf1a49436ea37b98dd2f37c57608951d0e28eecc ]

Let the fastpath code decide which exits can/can't be handled in the fastpath when L2 is active, e.g. when KVM generates a VMX preemption timer exit to forcefully regain control, there is no "work" to be done and so such exits can be handled in the fastpath regardless of whether L1 or L2 is active.

Moving the is_guest_mode() check into the fastpath code also makes it easier to see that L2 isn't allowed to use the fastpath in most cases, e.g. it's not immediately obvious why handle_fastpath_preemption_timer() is called from the fastpath and the normal path.

Link: https://lore.kernel.org/r/20240110012705.506918-5-seanjc@google.com Signed-off-by: Sean Christopherson seanjc@google.com [sean: resolve syntactic conflict in svm_exit_handlers_fastpath()] Signed-off-by: Sean Christopherson seanjc@google.com Signed-off-by: Sasha Levin sashal@kernel.org --- arch/x86/kvm/svm/svm.c | 6 +++--- arch/x86/kvm/vmx/vmx.c | 6 +++--- 2 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index b4283c2358a6..337a304d211b 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -3964,6 +3964,9 @@ static fastpath_t svm_exit_handlers_fastpath(struct kvm_vcpu *vcpu) { struct vmcb_control_area *control = &to_svm(vcpu)->vmcb->control;

+ if (is_guest_mode(vcpu)) + return EXIT_FASTPATH_NONE; + /* * Note, the next RIP must be provided as SRCU isn't held, i.e. KVM * can't read guest memory (dereference memslots) to decode the WRMSR. @@ -4127,9 +4130,6 @@ static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu,

svm_complete_interrupts(vcpu);

- if (is_guest_mode(vcpu)) - return EXIT_FASTPATH_NONE; - return svm_exit_handlers_fastpath(vcpu); }

diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index c804ad001a79..18ceed9046a9 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -7138,6 +7138,9 @@ void noinstr vmx_spec_ctrl_restore_host(struct vcpu_vmx *vmx,

static fastpath_t vmx_exit_handlers_fastpath(struct kvm_vcpu *vcpu) { + if (is_guest_mode(vcpu)) + return EXIT_FASTPATH_NONE; + switch (to_vmx(vcpu)->exit_reason.basic) { case EXIT_REASON_MSR_WRITE: return handle_fastpath_set_msr_irqoff(vcpu); @@ -7337,9 +7340,6 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu, bool force_immediate_exit) vmx_recover_nmi_blocking(vmx); vmx_complete_interrupts(vmx);

- if (is_guest_mode(vcpu)) - return EXIT_FASTPATH_NONE; - return vmx_exit_handlers_fastpath(vcpu); }

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

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

From: Sean Christopherson seanjc@google.com

[ Upstream commit 0ec3d6d1f169baa7fc512ae4b78d17e7c94b7763 ]

Now that vmx->req_immediate_exit is used only in the scope of vmx_vcpu_run(), use force_immediate_exit to detect that KVM should usurp the VMX preemption to force a VM-Exit and let vendor code fully handle forcing a VM-Exit.

Opportunsitically drop __kvm_request_immediate_exit() and just have vendor code call smp_send_reschedule() directly. SVM already does this when injecting an event while also trying to single-step an IRET, i.e. it's not exactly secret knowledge that KVM uses a reschedule IPI to force an exit.

Link: https://lore.kernel.org/r/20240110012705.506918-7-seanjc@google.com Signed-off-by: Sean Christopherson seanjc@google.com [sean: resolve absurd conflict due to funky kvm_x86_ops.sched_in prototype] Signed-off-by: Sean Christopherson seanjc@google.com Signed-off-by: Sasha Levin sashal@kernel.org --- arch/x86/include/asm/kvm-x86-ops.h | 1 - arch/x86/include/asm/kvm_host.h | 3 --- arch/x86/kvm/svm/svm.c | 7 ++++--- arch/x86/kvm/vmx/vmx.c | 32 +++++++++++++----------------- arch/x86/kvm/vmx/vmx.h | 2 -- arch/x86/kvm/x86.c | 10 +--------- 6 files changed, 19 insertions(+), 36 deletions(-)

diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h index 29bef25ac77c..0e5ae3b0c867 100644 --- a/arch/x86/include/asm/kvm-x86-ops.h +++ b/arch/x86/include/asm/kvm-x86-ops.h @@ -100,7 +100,6 @@ KVM_X86_OP(write_tsc_multiplier) KVM_X86_OP(get_exit_info) KVM_X86_OP(check_intercept) KVM_X86_OP(handle_exit_irqoff) -KVM_X86_OP(request_immediate_exit) KVM_X86_OP(sched_in) KVM_X86_OP_OPTIONAL(update_cpu_dirty_logging) KVM_X86_OP_OPTIONAL(vcpu_blocking) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 93f523762854..86f3bd6601e7 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1590,8 +1590,6 @@ struct kvm_x86_ops { struct x86_exception *exception); void (*handle_exit_irqoff)(struct kvm_vcpu *vcpu);

- void (*request_immediate_exit)(struct kvm_vcpu *vcpu); - void (*sched_in)(struct kvm_vcpu *kvm, int cpu);

/* @@ -2059,7 +2057,6 @@ extern bool kvm_find_async_pf_gfn(struct kvm_vcpu *vcpu, gfn_t gfn);

int kvm_skip_emulated_instruction(struct kvm_vcpu *vcpu); int kvm_complete_insn_gp(struct kvm_vcpu *vcpu, int err); -void __kvm_request_immediate_exit(struct kvm_vcpu *vcpu);

void __user *__x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size); diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 337a304d211b..12de50db401f 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -4033,9 +4033,12 @@ static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu, * is enough to force an immediate vmexit. */ disable_nmi_singlestep(svm); - smp_send_reschedule(vcpu->cpu); + force_immediate_exit = true; }

+ if (force_immediate_exit) + smp_send_reschedule(vcpu->cpu); + pre_svm_run(vcpu);

sync_lapic_to_cr8(vcpu); @@ -4874,8 +4877,6 @@ static struct kvm_x86_ops svm_x86_ops __initdata = { .check_intercept = svm_check_intercept, .handle_exit_irqoff = svm_handle_exit_irqoff,

- .request_immediate_exit = __kvm_request_immediate_exit, - .sched_in = svm_sched_in,

.nested_ops = &svm_nested_ops, diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 4db9d41d988c..179747d04edc 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -49,6 +49,8 @@ #include <asm/virtext.h> #include <asm/vmx.h>

+#include <trace/events/ipi.h> + #include "capabilities.h" #include "cpuid.h" #include "evmcs.h" @@ -1223,8 +1225,6 @@ void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu) u16 fs_sel, gs_sel; int i;

- vmx->req_immediate_exit = false; - /* * Note that guest MSRs to be saved/restored can also be changed * when guest state is loaded. This happens when guest transitions @@ -5929,7 +5929,8 @@ static int handle_pml_full(struct kvm_vcpu *vcpu) return 1; }

-static fastpath_t handle_fastpath_preemption_timer(struct kvm_vcpu *vcpu) +static fastpath_t handle_fastpath_preemption_timer(struct kvm_vcpu *vcpu, + bool force_immediate_exit) { struct vcpu_vmx *vmx = to_vmx(vcpu);

@@ -5945,7 +5946,7 @@ static fastpath_t handle_fastpath_preemption_timer(struct kvm_vcpu *vcpu) * If the timer expired because KVM used it to force an immediate exit, * then mission accomplished. */ - if (vmx->req_immediate_exit) + if (force_immediate_exit) return EXIT_FASTPATH_EXIT_HANDLED;

/* @@ -7090,13 +7091,13 @@ static void atomic_switch_perf_msrs(struct vcpu_vmx *vmx) msrs[i].host, false); }

-static void vmx_update_hv_timer(struct kvm_vcpu *vcpu) +static void vmx_update_hv_timer(struct kvm_vcpu *vcpu, bool force_immediate_exit) { struct vcpu_vmx *vmx = to_vmx(vcpu); u64 tscl; u32 delta_tsc;

- if (vmx->req_immediate_exit) { + if (force_immediate_exit) { vmcs_write32(VMX_PREEMPTION_TIMER_VALUE, 0); vmx->loaded_vmcs->hv_timer_soft_disabled = false; } else if (vmx->hv_deadline_tsc != -1) { @@ -7149,7 +7150,8 @@ void noinstr vmx_spec_ctrl_restore_host(struct vcpu_vmx *vmx, barrier_nospec(); }

-static fastpath_t vmx_exit_handlers_fastpath(struct kvm_vcpu *vcpu) +static fastpath_t vmx_exit_handlers_fastpath(struct kvm_vcpu *vcpu, + bool force_immediate_exit) { /* * If L2 is active, some VMX preemption timer exits can be handled in @@ -7163,7 +7165,7 @@ static fastpath_t vmx_exit_handlers_fastpath(struct kvm_vcpu *vcpu) case EXIT_REASON_MSR_WRITE: return handle_fastpath_set_msr_irqoff(vcpu); case EXIT_REASON_PREEMPTION_TIMER: - return handle_fastpath_preemption_timer(vcpu); + return handle_fastpath_preemption_timer(vcpu, force_immediate_exit); default: return EXIT_FASTPATH_NONE; } @@ -7284,7 +7286,9 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu, bool force_immediate_exit) vmx_passthrough_lbr_msrs(vcpu);

if (enable_preemption_timer) - vmx_update_hv_timer(vcpu); + vmx_update_hv_timer(vcpu, force_immediate_exit); + else if (force_immediate_exit) + smp_send_reschedule(vcpu->cpu);

kvm_wait_lapic_expire(vcpu);

@@ -7358,7 +7362,7 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu, bool force_immediate_exit) vmx_recover_nmi_blocking(vmx); vmx_complete_interrupts(vmx);

- return vmx_exit_handlers_fastpath(vcpu); + return vmx_exit_handlers_fastpath(vcpu, force_immediate_exit); }

static void vmx_vcpu_free(struct kvm_vcpu *vcpu) @@ -7865,11 +7869,6 @@ static __init void vmx_set_cpu_caps(void) kvm_cpu_cap_check_and_set(X86_FEATURE_WAITPKG); }

-static void vmx_request_immediate_exit(struct kvm_vcpu *vcpu) -{ - to_vmx(vcpu)->req_immediate_exit = true; -} - static int vmx_check_intercept_io(struct kvm_vcpu *vcpu, struct x86_instruction_info *info) { @@ -8275,8 +8274,6 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = { .check_intercept = vmx_check_intercept, .handle_exit_irqoff = vmx_handle_exit_irqoff,

- .request_immediate_exit = vmx_request_immediate_exit, - .sched_in = vmx_sched_in,

.cpu_dirty_log_size = PML_ENTITY_NUM, @@ -8533,7 +8530,6 @@ static __init int hardware_setup(void) if (!enable_preemption_timer) { vmx_x86_ops.set_hv_timer = NULL; vmx_x86_ops.cancel_hv_timer = NULL; - vmx_x86_ops.request_immediate_exit = __kvm_request_immediate_exit; }

kvm_caps.supported_mce_cap |= MCG_LMCE_P; diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index 357819872d80..ddbe73958d7f 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -343,8 +343,6 @@ struct vcpu_vmx { unsigned int ple_window; bool ple_window_dirty;

- bool req_immediate_exit; - /* Support for PML */ #define PML_ENTITY_NUM 512 struct page *pml_pg; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 08c3da88f402..400a6e9fb0be 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -10578,12 +10578,6 @@ static void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu) static_call_cond(kvm_x86_set_apic_access_page_addr)(vcpu); }

-void __kvm_request_immediate_exit(struct kvm_vcpu *vcpu) -{ - smp_send_reschedule(vcpu->cpu); -} -EXPORT_SYMBOL_GPL(__kvm_request_immediate_exit); - /* * Called within kvm->srcu read side. * Returns 1 to let vcpu_run() continue the guest execution loop without @@ -10817,10 +10811,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) goto cancel_injection; }

- if (req_immediate_exit) { + if (req_immediate_exit) kvm_make_request(KVM_REQ_EVENT, vcpu); - static_call(kvm_x86_request_immediate_exit)(vcpu); - }

fpregs_assert_state_consistent(); if (test_thread_flag(TIF_NEED_FPU_LOAD))

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

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

From: Sean Christopherson seanjc@google.com

[ Upstream commit 80c64c7afea1da6a93ebe88d3d29d8a60377ef80 ]

Instruct vendor code to load the guest's DR6 into hardware via a new KVM_RUN flag, and remove kvm_x86_ops.set_dr6(), whose sole purpose was to load vcpu->arch.dr6 into hardware when DR6 can be read/written directly by the guest.

Note, TDX already WARNs on any run_flag being set, i.e. will yell if KVM thinks DR6 needs to be reloaded. TDX vCPUs force KVM_DEBUGREG_AUTO_SWITCH and never clear the flag, i.e. should never observe KVM_RUN_LOAD_GUEST_DR6.

Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20250610232010.162191-4-seanjc@google.com Signed-off-by: Sean Christopherson seanjc@google.com [sean: account for lack of vmx/main.c] Signed-off-by: Sean Christopherson seanjc@google.com Signed-off-by: Sasha Levin sashal@kernel.org --- arch/x86/include/asm/kvm-x86-ops.h | 1 - arch/x86/include/asm/kvm_host.h | 2 +- arch/x86/kvm/svm/svm.c | 10 ++++++---- arch/x86/kvm/vmx/vmx.c | 10 +++------- arch/x86/kvm/x86.c | 2 +- 5 files changed, 11 insertions(+), 14 deletions(-)

diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h index 0e5ae3b0c867..c068565fe954 100644 --- a/arch/x86/include/asm/kvm-x86-ops.h +++ b/arch/x86/include/asm/kvm-x86-ops.h @@ -47,7 +47,6 @@ KVM_X86_OP(set_idt) KVM_X86_OP(get_gdt) KVM_X86_OP(set_gdt) KVM_X86_OP(sync_dirty_debug_regs) -KVM_X86_OP(set_dr6) KVM_X86_OP(set_dr7) KVM_X86_OP(cache_reg) KVM_X86_OP(get_rflags) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 1383f5e5238a..c8fc4f2acf69 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1458,6 +1458,7 @@ static inline u16 kvm_lapic_irq_dest_mode(bool dest_mode_logical)

enum kvm_x86_run_flags { KVM_RUN_FORCE_IMMEDIATE_EXIT = BIT(0), + KVM_RUN_LOAD_GUEST_DR6 = BIT(1), };

struct kvm_x86_ops { @@ -1504,7 +1505,6 @@ struct kvm_x86_ops { void (*get_gdt)(struct kvm_vcpu *vcpu, struct desc_ptr *dt); void (*set_gdt)(struct kvm_vcpu *vcpu, struct desc_ptr *dt); void (*sync_dirty_debug_regs)(struct kvm_vcpu *vcpu); - void (*set_dr6)(struct kvm_vcpu *vcpu, unsigned long value); void (*set_dr7)(struct kvm_vcpu *vcpu, unsigned long value); void (*cache_reg)(struct kvm_vcpu *vcpu, enum kvm_reg reg); unsigned long (*get_rflags)(struct kvm_vcpu *vcpu); diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index dc8a1b72d8ec..5a6bd9d5cceb 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -4052,10 +4052,13 @@ static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu, u64 run_flags) svm_hv_update_vp_id(svm->vmcb, vcpu);

/* - * Run with all-zero DR6 unless needed, so that we can get the exact cause - * of a #DB. + * Run with all-zero DR6 unless the guest can write DR6 freely, so that + * KVM can get the exact cause of a #DB. Note, loading guest DR6 from + * KVM's snapshot is only necessary when DR accesses won't exit. */ - if (likely(!(vcpu->arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT))) + if (unlikely(run_flags & KVM_RUN_LOAD_GUEST_DR6)) + svm_set_dr6(vcpu, vcpu->arch.dr6); + else if (likely(!(vcpu->arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT))) svm_set_dr6(vcpu, DR6_ACTIVE_LOW);

clgi(); @@ -4822,7 +4825,6 @@ static struct kvm_x86_ops svm_x86_ops __initdata = { .set_idt = svm_set_idt, .get_gdt = svm_get_gdt, .set_gdt = svm_set_gdt, - .set_dr6 = svm_set_dr6, .set_dr7 = svm_set_dr7, .sync_dirty_debug_regs = svm_sync_dirty_debug_regs, .cache_reg = svm_cache_reg, diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 382f42200688..60d1ff3fca45 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -5530,12 +5530,6 @@ static void vmx_sync_dirty_debug_regs(struct kvm_vcpu *vcpu) set_debugreg(DR6_RESERVED, 6); }

-static void vmx_set_dr6(struct kvm_vcpu *vcpu, unsigned long val) -{ - lockdep_assert_irqs_disabled(); - set_debugreg(vcpu->arch.dr6, 6); -} - static void vmx_set_dr7(struct kvm_vcpu *vcpu, unsigned long val) { vmcs_writel(GUEST_DR7, val); @@ -7251,6 +7245,9 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu, u64 run_flags) vmcs_writel(GUEST_RIP, vcpu->arch.regs[VCPU_REGS_RIP]); vcpu->arch.regs_dirty = 0;

+ if (run_flags & KVM_RUN_LOAD_GUEST_DR6) + set_debugreg(vcpu->arch.dr6, 6); + /* * Refresh vmcs.HOST_CR3 if necessary. This must be done immediately * prior to VM-Enter, as the kernel may load a new ASID (PCID) any time @@ -8208,7 +8205,6 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = { .set_idt = vmx_set_idt, .get_gdt = vmx_get_gdt, .set_gdt = vmx_set_gdt, - .set_dr6 = vmx_set_dr6, .set_dr7 = vmx_set_dr7, .sync_dirty_debug_regs = vmx_sync_dirty_debug_regs, .cache_reg = vmx_cache_reg, diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 83e5e823cbae..9d66830d594c 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -10833,7 +10833,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) set_debugreg(vcpu->arch.eff_db[3], 3); /* When KVM_DEBUGREG_WONT_EXIT, dr6 is accessible in guest. */ if (unlikely(vcpu->arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT)) - static_call(kvm_x86_set_dr6)(vcpu, vcpu->arch.dr6); + run_flags |= KVM_RUN_LOAD_GUEST_DR6; } else if (unlikely(hw_breakpoint_active())) { set_debugreg(0, 7); }

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

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

From: Sean Christopherson seanjc@google.com

[ Upstream commit 8a4351ac302cd8c19729ba2636acfd0467c22ae8 ]

Move VMX's logic to check DEBUGCTL values into a standalone helper so that the code can be used by nested VM-Enter to apply the same logic to the value being loaded from vmcs12.

KVM needs to explicitly check vmcs12->guest_ia32_debugctl on nested VM-Enter, as hardware may support features that KVM does not, i.e. relying on hardware to detect invalid guest state will result in false negatives. Unfortunately, that means applying KVM's funky suppression of BTF and LBR to vmcs12 so as not to break existing guests.

No functional change intended.

Reviewed-by: Dapeng Mi dapeng1.mi@linux.intel.com Link: https://lore.kernel.org/r/20250610232010.162191-6-seanjc@google.com Stable-dep-of: 7d0cce6cbe71 ("KVM: VMX: Wrap all accesses to IA32_DEBUGCTL with getter/setter APIs") Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Sean Christopherson seanjc@google.com Signed-off-by: Sasha Levin sashal@kernel.org --- arch/x86/kvm/vmx/vmx.c | 29 +++++++++++++++++------------ 1 file changed, 17 insertions(+), 12 deletions(-)

diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 9445def2b3d2..6517b9d929bf 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -2071,6 +2071,19 @@ static u64 vmx_get_supported_debugctl(struct kvm_vcpu *vcpu, bool host_initiated return debugctl; }

+static bool vmx_is_valid_debugctl(struct kvm_vcpu *vcpu, u64 data, + bool host_initiated) +{ + u64 invalid; + + invalid = data & ~vmx_get_supported_debugctl(vcpu, host_initiated); + if (invalid & (DEBUGCTLMSR_BTF | DEBUGCTLMSR_LBR)) { + kvm_pr_unimpl_wrmsr(vcpu, MSR_IA32_DEBUGCTLMSR, data); + invalid &= ~(DEBUGCTLMSR_BTF | DEBUGCTLMSR_LBR); + } + return !invalid; +} + /* * Writes msr value into the appropriate "register". * Returns 0 on success, non-0 otherwise. @@ -2139,19 +2152,12 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) } vmcs_writel(GUEST_SYSENTER_ESP, data); break; - case MSR_IA32_DEBUGCTLMSR: { - u64 invalid; - - invalid = data & ~vmx_get_supported_debugctl(vcpu, msr_info->host_initiated); - if (invalid & (DEBUGCTLMSR_BTF|DEBUGCTLMSR_LBR)) { - kvm_pr_unimpl_wrmsr(vcpu, msr_index, data); - data &= ~(DEBUGCTLMSR_BTF|DEBUGCTLMSR_LBR); - invalid &= ~(DEBUGCTLMSR_BTF|DEBUGCTLMSR_LBR); - } - - if (invalid) + case MSR_IA32_DEBUGCTLMSR: + if (!vmx_is_valid_debugctl(vcpu, data, msr_info->host_initiated)) return 1;

+ data &= vmx_get_supported_debugctl(vcpu, msr_info->host_initiated); + if (is_guest_mode(vcpu) && get_vmcs12(vcpu)->vm_exit_controls & VM_EXIT_SAVE_DEBUG_CONTROLS) get_vmcs12(vcpu)->guest_ia32_debugctl = data; @@ -2161,7 +2167,6 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) (data & DEBUGCTLMSR_LBR)) intel_pmu_create_guest_lbr_event(vcpu); return 0; - } case MSR_IA32_BNDCFGS: if (!kvm_mpx_supported() || (!msr_info->host_initiated &&

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

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

From: Maxim Levitsky mlevitsk@redhat.com

[ Upstream commit 7d0cce6cbe71af6e9c1831bff101a2b9c249c4a2 ]

Introduce vmx_guest_debugctl_{read,write}() to handle all accesses to vmcs.GUEST_IA32_DEBUGCTL. This will allow stuffing FREEZE_IN_SMM into GUEST_IA32_DEBUGCTL based on the host setting without bleeding the state into the guest, and without needing to copy+paste the FREEZE_IN_SMM logic into every patch that accesses GUEST_IA32_DEBUGCTL.

No functional change intended.

Cc: stable@vger.kernel.org Signed-off-by: Maxim Levitsky mlevitsk@redhat.com [sean: massage changelog, make inline, use in all prepare_vmcs02() cases] Reviewed-by: Dapeng Mi dapeng1.mi@linux.intel.com Link: https://lore.kernel.org/r/20250610232010.162191-8-seanjc@google.com Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Sean Christopherson seanjc@google.com Signed-off-by: Sasha Levin sashal@kernel.org --- arch/x86/kvm/vmx/nested.c | 10 +++++----- arch/x86/kvm/vmx/pmu_intel.c | 8 ++++---- arch/x86/kvm/vmx/vmx.c | 8 +++++--- arch/x86/kvm/vmx/vmx.h | 10 ++++++++++ 4 files changed, 24 insertions(+), 12 deletions(-)

diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index da129e12cff9..a220770644e1 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -2532,11 +2532,11 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, if (vmx->nested.nested_run_pending && (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS)) { kvm_set_dr(vcpu, 7, vmcs12->guest_dr7); - vmcs_write64(GUEST_IA32_DEBUGCTL, vmcs12->guest_ia32_debugctl & - vmx_get_supported_debugctl(vcpu, false)); + vmx_guest_debugctl_write(vcpu, vmcs12->guest_ia32_debugctl & + vmx_get_supported_debugctl(vcpu, false)); } else { kvm_set_dr(vcpu, 7, vcpu->arch.dr7); - vmcs_write64(GUEST_IA32_DEBUGCTL, vmx->nested.pre_vmenter_debugctl); + vmx_guest_debugctl_write(vcpu, vmx->nested.pre_vmenter_debugctl); } if (kvm_mpx_supported() && (!vmx->nested.nested_run_pending || !(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS))) @@ -3404,7 +3404,7 @@ enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu,

if (!vmx->nested.nested_run_pending || !(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS)) - vmx->nested.pre_vmenter_debugctl = vmcs_read64(GUEST_IA32_DEBUGCTL); + vmx->nested.pre_vmenter_debugctl = vmx_guest_debugctl_read(); if (kvm_mpx_supported() && (!vmx->nested.nested_run_pending || !(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS))) @@ -4572,7 +4572,7 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, __vmx_set_segment(vcpu, &seg, VCPU_SREG_LDTR);

kvm_set_dr(vcpu, 7, 0x400); - vmcs_write64(GUEST_IA32_DEBUGCTL, 0); + vmx_guest_debugctl_write(vcpu, 0);

if (nested_vmx_load_msr(vcpu, vmcs12->vm_exit_msr_load_addr, vmcs12->vm_exit_msr_load_count)) diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c index 220cdbe1e286..76d3ed8abf6a 100644 --- a/arch/x86/kvm/vmx/pmu_intel.c +++ b/arch/x86/kvm/vmx/pmu_intel.c @@ -672,11 +672,11 @@ static void intel_pmu_reset(struct kvm_vcpu *vcpu) */ static void intel_pmu_legacy_freezing_lbrs_on_pmi(struct kvm_vcpu *vcpu) { - u64 data = vmcs_read64(GUEST_IA32_DEBUGCTL); + u64 data = vmx_guest_debugctl_read();

if (data & DEBUGCTLMSR_FREEZE_LBRS_ON_PMI) { data &= ~DEBUGCTLMSR_LBR; - vmcs_write64(GUEST_IA32_DEBUGCTL, data); + vmx_guest_debugctl_write(vcpu, data); } }

@@ -746,7 +746,7 @@ void vmx_passthrough_lbr_msrs(struct kvm_vcpu *vcpu)

if (!lbr_desc->event) { vmx_disable_lbr_msrs_passthrough(vcpu); - if (vmcs_read64(GUEST_IA32_DEBUGCTL) & DEBUGCTLMSR_LBR) + if (vmx_guest_debugctl_read() & DEBUGCTLMSR_LBR) goto warn; if (test_bit(INTEL_PMC_IDX_FIXED_VLBR, pmu->pmc_in_use)) goto warn; @@ -769,7 +769,7 @@ void vmx_passthrough_lbr_msrs(struct kvm_vcpu *vcpu)

static void intel_pmu_cleanup(struct kvm_vcpu *vcpu) { - if (!(vmcs_read64(GUEST_IA32_DEBUGCTL) & DEBUGCTLMSR_LBR)) + if (!(vmx_guest_debugctl_read() & DEBUGCTLMSR_LBR)) intel_pmu_release_guest_lbr_event(vcpu); }

diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 0b37e21d55b1..e470a294b22d 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -2027,7 +2027,7 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) msr_info->data = vmx->pt_desc.guest.addr_a[index / 2]; break; case MSR_IA32_DEBUGCTLMSR: - msr_info->data = vmcs_read64(GUEST_IA32_DEBUGCTL); + msr_info->data = vmx_guest_debugctl_read(); break; default: find_uret_msr: @@ -2161,7 +2161,8 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) VM_EXIT_SAVE_DEBUG_CONTROLS) get_vmcs12(vcpu)->guest_ia32_debugctl = data;

- vmcs_write64(GUEST_IA32_DEBUGCTL, data); + vmx_guest_debugctl_write(vcpu, data); + if (intel_pmu_lbr_is_enabled(vcpu) && !to_vmx(vcpu)->lbr_desc.event && (data & DEBUGCTLMSR_LBR)) intel_pmu_create_guest_lbr_event(vcpu); @@ -4751,7 +4752,8 @@ static void init_vmcs(struct vcpu_vmx *vmx) vmcs_write32(GUEST_SYSENTER_CS, 0); vmcs_writel(GUEST_SYSENTER_ESP, 0); vmcs_writel(GUEST_SYSENTER_EIP, 0); - vmcs_write64(GUEST_IA32_DEBUGCTL, 0); + + vmx_guest_debugctl_write(&vmx->vcpu, 0);

if (cpu_has_vmx_tpr_shadow()) { vmcs_write64(VIRTUAL_APIC_PAGE_ADDR, 0); diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index 99e3f46de2ec..b7ae263cde7b 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -445,6 +445,16 @@ void vmx_update_cpu_dirty_logging(struct kvm_vcpu *vcpu); u64 vmx_get_supported_debugctl(struct kvm_vcpu *vcpu, bool host_initiated); bool vmx_is_valid_debugctl(struct kvm_vcpu *vcpu, u64 data, bool host_initiated);

+static inline void vmx_guest_debugctl_write(struct kvm_vcpu *vcpu, u64 val) +{ + vmcs_write64(GUEST_IA32_DEBUGCTL, val); +} + +static inline u64 vmx_guest_debugctl_read(void) +{ + return vmcs_read64(GUEST_IA32_DEBUGCTL); +} + /* * Note, early Intel manuals have the write-low and read-high bitmap offsets * the wrong way round. The bitmaps control MSRs 0x00000000-0x00001fff and

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

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

From: Sabrina Dubroca sd@queasysnail.net

[ 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") Signed-off-by: Sabrina Dubroca sd@queasysnail.net Signed-off-by: Steffen Klassert steffen.klassert@secunet.com Signed-off-by: Sasha Levin sashal@kernel.org --- net/ipv4/udp_offload.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index 1a51c4b44c00..593108049ab7 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -60,7 +60,7 @@ 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 &&

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

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

From: Viacheslav Dubeyko slava@dubeyko.com

[ 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.

Signed-off-by: Viacheslav Dubeyko slava@dubeyko.com Link: https://lore.kernel.org/r/20250703214912.244138-1-slava@dubeyko.com Signed-off-by: Viacheslav Dubeyko slava@dubeyko.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/hfs/bnode.c | 92 ++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 92 insertions(+)

diff --git a/fs/hfs/bnode.c b/fs/hfs/bnode.c index cb823a8a6ba9..1dac5d9c055f 100644 --- a/fs/hfs/bnode.c +++ b/fs/hfs/bnode.c @@ -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; @@ -22,6 +64,20 @@ void hfs_bnode_read(struct hfs_bnode *node, void *buf, int off, int len) int bytes_read; int bytes_to_read;

+ 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 */ @@ -80,6 +136,20 @@ 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];

@@ -104,6 +174,20 @@ 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];

@@ -119,6 +203,10 @@ 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]; @@ -136,6 +224,10 @@ 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];

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

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

From: Viacheslav Dubeyko slava@dubeyko.com

[ 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.

Reported-by: Wenzhi Wang wenzhi.wang@uwaterloo.ca Signed-off-by: Liu Shixin liushixin2@huawei.com Signed-off-by: Viacheslav Dubeyko slava@dubeyko.com cc: John Paul Adrian Glaubitz glaubitz@physik.fu-berlin.de cc: Yangtao Li frank.li@vivo.com cc: linux-fsdevel@vger.kernel.org Reviewed-by: Yangtao Li frank.li@vivo.com Link: https://lore.kernel.org/r/20250710230830.110500-1-slava@dubeyko.com Signed-off-by: Viacheslav Dubeyko slava@dubeyko.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/hfsplus/unicode.c | 7 +++++++ 1 file changed, 7 insertions(+)

diff --git a/fs/hfsplus/unicode.c b/fs/hfsplus/unicode.c index 73342c925a4b..36b6cf2a3abb 100644 --- a/fs/hfsplus/unicode.c +++ b/fs/hfsplus/unicode.c @@ -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);

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

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

From: Kees Cook kees@kernel.org

[ 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.

Link: https://lore.kernel.org/r/20250724055029.3623499-1-kees@kernel.org Signed-off-by: Kees Cook kees@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- arch/arm64/include/asm/acpi.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/arm64/include/asm/acpi.h b/arch/arm64/include/asm/acpi.h index 702587fda70c..8cbbd08cc8c5 100644 --- a/arch/arm64/include/asm/acpi.h +++ b/arch/arm64/include/asm/acpi.h @@ -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";

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

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

From: Jan Kara jack@suse.cz

[ 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.

Reported-by: syzbot+478f2c1a6f0f447a46bb@syzkaller.appspotmail.com Signed-off-by: Jan Kara jack@suse.cz Signed-off-by: Sasha Levin sashal@kernel.org --- fs/udf/super.c | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-)

diff --git a/fs/udf/super.c b/fs/udf/super.c index fa790be4f19f..a186d2418b50 100644 --- a/fs/udf/super.c +++ b/fs/udf/super.c @@ -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;

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

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

From: Viacheslav Dubeyko slava@dubeyko.com

[ 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.

Signed-off-by: Viacheslav Dubeyko slava@dubeyko.com Reviewed-by: Johannes Thumshirn johannes.thumshirn@wdc.com Link: https://lore.kernel.org/r/20250430001211.1912533-1-slava@dubeyko.com Signed-off-by: Viacheslav Dubeyko slava@dubeyko.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/hfs/bnode.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/fs/hfs/bnode.c b/fs/hfs/bnode.c index 1dac5d9c055f..e8cd1a31f247 100644 --- a/fs/hfs/bnode.c +++ b/fs/hfs/bnode.c @@ -574,6 +574,7 @@ 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;

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

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

From: Damien Le Moal dlemoal@kernel.org

[ 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.

Signed-off-by: Damien Le Moal dlemoal@kernel.org Reviewed-by: Niklas Cassel cassel@kernel.org Reviewed-by: Hannes Reinecke hare@suse.de Link: https://lore.kernel.org/r/20250701125321.69496-6-dlemoal@kernel.org Signed-off-by: Niklas Cassel cassel@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/ata/libata-sata.c | 5 +++++ 1 file changed, 5 insertions(+)

diff --git a/drivers/ata/libata-sata.c b/drivers/ata/libata-sata.c index 71a00842eb5e..b75999388bf0 100644 --- a/drivers/ata/libata-sata.c +++ b/drivers/ata/libata-sata.c @@ -812,6 +812,11 @@ 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) {

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

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

From: Rong Zhang ulin0208@gmail.com

[ Upstream commit b1e9d89408f402858c00103f9831b25ffa0994d3 ]

After applying this patch, could correctly create symlink:

ln -s "relative/path/to/file" symlink

Signed-off-by: Rong Zhang ulin0208@gmail.com [almaz.alexandrovich@paragon-software.com: added cpu_to_le32 macro to rs->Flags assignment] Signed-off-by: Konstantin Komarov almaz.alexandrovich@paragon-software.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/ntfs3/inode.c | 31 ++++++++++++++++++------------- 1 file changed, 18 insertions(+), 13 deletions(-)

diff --git a/fs/ntfs3/inode.c b/fs/ntfs3/inode.c index 5baf6a2b3d48..844113c3175c 100644 --- a/fs/ntfs3/inode.c +++ b/fs/ntfs3/inode.c @@ -1114,10 +1114,10 @@ int inode_write_data(struct inode *inode, const void *data, size_t bytes) * Number of bytes for REPARSE_DATA_BUFFER(IO_REPARSE_TAG_SYMLINK) * for unicode string of @uni_len length. */ -static inline u32 ntfs_reparse_bytes(u32 uni_len) +static inline u32 ntfs_reparse_bytes(u32 uni_len, bool is_absolute) { /* Header + unicode string + decorated unicode string. */ - return sizeof(short) * (2 * uni_len + 4) + + return sizeof(short) * (2 * uni_len + (is_absolute ? 4 : 0)) + offsetof(struct REPARSE_DATA_BUFFER, SymbolicLinkReparseBuffer.PathBuffer); } @@ -1130,8 +1130,11 @@ ntfs_create_reparse_buffer(struct ntfs_sb_info *sbi, const char *symname, struct REPARSE_DATA_BUFFER *rp; __le16 *rp_name; typeof(rp->SymbolicLinkReparseBuffer) *rs; + bool is_absolute;

- rp = kzalloc(ntfs_reparse_bytes(2 * size + 2), GFP_NOFS); + is_absolute = (strlen(symname) > 1 && symname[1] == ':'); + + rp = kzalloc(ntfs_reparse_bytes(2 * size + 2, is_absolute), GFP_NOFS); if (!rp) return ERR_PTR(-ENOMEM);

@@ -1146,7 +1149,7 @@ ntfs_create_reparse_buffer(struct ntfs_sb_info *sbi, const char *symname, goto out;

/* err = the length of unicode name of symlink. */ - *nsize = ntfs_reparse_bytes(err); + *nsize = ntfs_reparse_bytes(err, is_absolute);

if (*nsize > sbi->reparse.max_size) { err = -EFBIG; @@ -1166,7 +1169,7 @@ ntfs_create_reparse_buffer(struct ntfs_sb_info *sbi, const char *symname,

/* PrintName + SubstituteName. */ rs->SubstituteNameOffset = cpu_to_le16(sizeof(short) * err); - rs->SubstituteNameLength = cpu_to_le16(sizeof(short) * err + 8); + rs->SubstituteNameLength = cpu_to_le16(sizeof(short) * err + (is_absolute ? 8 : 0)); rs->PrintNameLength = rs->SubstituteNameOffset;

/* @@ -1174,16 +1177,18 @@ ntfs_create_reparse_buffer(struct ntfs_sb_info *sbi, const char *symname, * parse this path. * 0-absolute path 1- relative path (SYMLINK_FLAG_RELATIVE). */ - rs->Flags = 0; + rs->Flags = cpu_to_le32(is_absolute ? 0 : SYMLINK_FLAG_RELATIVE);

- memmove(rp_name + err + 4, rp_name, sizeof(short) * err); + memmove(rp_name + err + (is_absolute ? 4 : 0), rp_name, sizeof(short) * err);

- /* Decorate SubstituteName. */ - rp_name += err; - rp_name[0] = cpu_to_le16('\'); - rp_name[1] = cpu_to_le16('?'); - rp_name[2] = cpu_to_le16('?'); - rp_name[3] = cpu_to_le16('\'); + if (is_absolute) { + /* Decorate SubstituteName. */ + rp_name += err; + rp_name[0] = cpu_to_le16('\'); + rp_name[1] = cpu_to_le16('?'); + rp_name[2] = cpu_to_le16('?'); + rp_name[3] = cpu_to_le16('\'); + }

return rp; out:

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

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

From: Al Viro viro@zeniv.linux.org.uk

[ Upstream commit 2c58d42de71f9c73e40afacc9d062892d2cc8862 ]

We used to need securityfs_remove() to undo simple_pin_fs() done when the file had been created and to drop the second extra reference taken at the same time. Now that neither is needed (or done by securityfs_remove()), we can simply call simple_unlink() and be done with that - the broken games with locking had been there only for the sake of securityfs_remove().

Signed-off-by: Al Viro viro@zeniv.linux.org.uk Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/virt/coco/efi_secret/efi_secret.c | 10 +--------- 1 file changed, 1 insertion(+), 9 deletions(-)

diff --git a/drivers/virt/coco/efi_secret/efi_secret.c b/drivers/virt/coco/efi_secret/efi_secret.c index e700a5ef7043..d996feb0509a 100644 --- a/drivers/virt/coco/efi_secret/efi_secret.c +++ b/drivers/virt/coco/efi_secret/efi_secret.c @@ -136,15 +136,7 @@ static int efi_secret_unlink(struct inode *dir, struct dentry *dentry) if (s->fs_files[i] == dentry) s->fs_files[i] = NULL;

- /* - * securityfs_remove tries to lock the directory's inode, but we reach - * the unlink callback when it's already locked - */ - inode_unlock(dir); - securityfs_remove(dentry); - inode_lock(dir); - - return 0; + return simple_unlink(inode, dentry); }

static const struct inode_operations efi_secret_dir_inode_operations = {

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

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

From: Su Hui suhui@nfschina.com

[ 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.

Signed-off-by: Su Hui suhui@nfschina.com Link: https://lore.kernel.org/r/20250725060117.1773770-1-suhui@nfschina.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/usb/host/xhci-ring.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c index 0862fdd3e568..c4880b22f359 100644 --- a/drivers/usb/host/xhci-ring.c +++ b/drivers/usb/host/xhci-ring.c @@ -4421,7 +4421,8 @@ 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; }

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

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

From: Cynthia Huang cynthia@andestech.com

[ 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.

Signed-off-by: Cynthia Huang cynthia@andestech.com Signed-off-by: Ben Zong-You Xie ben717@andestech.com Signed-off-by: Thomas Gleixner tglx@linutronix.de Reviewed-by: Muhammad Usama Anjum usama.anjum@collabora.com Link: https://lore.kernel.org/all/20250710103630.3156130-1-ben717@andestech.com Signed-off-by: Sasha Levin sashal@kernel.org --- tools/testing/selftests/futex/include/futextest.h | 11 +++++++++++ 1 file changed, 11 insertions(+)

diff --git a/tools/testing/selftests/futex/include/futextest.h b/tools/testing/selftests/futex/include/futextest.h index ddbcfc9b7bac..7a5fd1d5355e 100644 --- a/tools/testing/selftests/futex/include/futextest.h +++ b/tools/testing/selftests/futex/include/futextest.h @@ -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

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

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

From: Mario Limonciello mario.limonciello@amd.com

[ 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.

Signed-off-by: Mario Limonciello mario.limonciello@amd.com Signed-off-by: Mathias Nyman mathias.nyman@linux.intel.com Acked-by: Mathias Nyman mathias.nyman@linux.intel.com Link: https://lore.kernel.org/r/20250717073107.488599-3-mathias.nyman@linux.intel.... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/usb/host/xhci.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c index e726c5edee03..a5ce544860b8 100644 --- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -119,7 +119,8 @@ 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; }

@@ -178,7 +179,8 @@ 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; }

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

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

From: Mario Limonciello mario.limonciello@amd.com

[ 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.

Signed-off-by: Mario Limonciello mario.limonciello@amd.com Signed-off-by: Mathias Nyman mathias.nyman@linux.intel.com Acked-by: Mathias Nyman mathias.nyman@linux.intel.com Link: https://lore.kernel.org/r/20250717073107.488599-2-mathias.nyman@linux.intel.... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/usb/host/xhci-ring.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c index c4880b22f359..c8e1ead0c09e 100644 --- a/drivers/usb/host/xhci-ring.c +++ b/drivers/usb/host/xhci-ring.c @@ -1289,12 +1289,15 @@ 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); @@ -1308,7 +1311,7 @@ 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)); }

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

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

From: Bartosz Golaszewski bartosz.golaszewski@linaro.org

[ 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.

Link: https://lore.kernel.org/r/20250709-gpiochip-set-rv-gpio-remaining-v1-2-b8950... Signed-off-by: Bartosz Golaszewski bartosz.golaszewski@linaro.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpio/gpio-wcd934x.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/gpio/gpio-wcd934x.c b/drivers/gpio/gpio-wcd934x.c index 97e6caedf1f3..c00968ce7a56 100644 --- a/drivers/gpio/gpio-wcd934x.c +++ b/drivers/gpio/gpio-wcd934x.c @@ -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),

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

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

From: Alexander Kochetkov al.kochet@gmail.com

[ 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

Signed-off-by: Alexander Kochetkov al.kochet@gmail.com Link: https://lore.kernel.org/r/20250703140453.1273027-1-al.kochet@gmail.com Signed-off-by: Heiko Stuebner heiko@sntech.de Signed-off-by: Sasha Levin sashal@kernel.org --- arch/arm/mach-rockchip/platsmp.c | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-)

diff --git a/arch/arm/mach-rockchip/platsmp.c b/arch/arm/mach-rockchip/platsmp.c index 36915a073c23..f432d22bfed8 100644 --- a/arch/arm/mach-rockchip/platsmp.c +++ b/arch/arm/mach-rockchip/platsmp.c @@ -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)

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

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

From: Shubhrajyoti Datta shubhrajyoti.datta@amd.com

[ Upstream commit b1dc7f097b78eb8d25b071ead2384b07a549692b ]

Clear the ECC error and counter registers during initialization/probe to avoid reporting stale errors that may have occurred before EDAC registration.

For that, unify the Zynq and ZynqMP ECC state reading paths and simplify the code.

[ bp: Massage commit message. Fix an -Wsometimes-uninitialized warning as reported by Reported-by: kernel test robot lkp@intel.com Closes: https://lore.kernel.org/oe-kbuild-all/202507141048.obUv3ZUm-lkp@intel.com ]

Signed-off-by: Shubhrajyoti Datta shubhrajyoti.datta@amd.com Signed-off-by: Borislav Petkov (AMD) bp@alien8.de Link: https://lore.kernel.org/20250713050753.7042-1-shubhrajyoti.datta@amd.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/edac/synopsys_edac.c | 97 +++++++++++++++++------------------- 1 file changed, 46 insertions(+), 51 deletions(-)

diff --git a/drivers/edac/synopsys_edac.c b/drivers/edac/synopsys_edac.c index e7c18bb61f81..c02ad4f984ad 100644 --- a/drivers/edac/synopsys_edac.c +++ b/drivers/edac/synopsys_edac.c @@ -333,20 +333,26 @@ struct synps_edac_priv { #endif };

+enum synps_platform_type { + ZYNQ, + ZYNQMP, + SYNPS, +}; + /** * struct synps_platform_data - synps platform data structure. + * @platform: Identifies the target hardware platform * @get_error_info: Get EDAC error info. * @get_mtype: Get mtype. * @get_dtype: Get dtype. - * @get_ecc_state: Get ECC state. * @get_mem_info: Get EDAC memory info * @quirks: To differentiate IPs. */ struct synps_platform_data { + enum synps_platform_type platform; int (*get_error_info)(struct synps_edac_priv *priv); enum mem_type (*get_mtype)(const void __iomem *base); enum dev_type (*get_dtype)(const void __iomem *base); - bool (*get_ecc_state)(void __iomem *base); #ifdef CONFIG_EDAC_DEBUG u64 (*get_mem_info)(struct synps_edac_priv *priv); #endif @@ -721,51 +727,38 @@ static enum dev_type zynqmp_get_dtype(const void __iomem *base) return dt; }

-/** - * zynq_get_ecc_state - Return the controller ECC enable/disable status. - * @base: DDR memory controller base address. - * - * Get the ECC enable/disable status of the controller. - * - * Return: true if enabled, otherwise false. - */ -static bool zynq_get_ecc_state(void __iomem *base) +static bool get_ecc_state(struct synps_edac_priv *priv) { + u32 ecctype, clearval; enum dev_type dt; - u32 ecctype; - - dt = zynq_get_dtype(base); - if (dt == DEV_UNKNOWN) - return false;

- ecctype = readl(base + SCRUB_OFST) & SCRUB_MODE_MASK; - if ((ecctype == SCRUB_MODE_SECDED) && (dt == DEV_X2)) - return true; - - return false; -} - -/** - * zynqmp_get_ecc_state - Return the controller ECC enable/disable status. - * @base: DDR memory controller base address. - * - * Get the ECC enable/disable status for the controller. - * - * Return: a ECC status boolean i.e true/false - enabled/disabled. - */ -static bool zynqmp_get_ecc_state(void __iomem *base) -{ - enum dev_type dt; - u32 ecctype; - - dt = zynqmp_get_dtype(base); - if (dt == DEV_UNKNOWN) - return false; - - ecctype = readl(base + ECC_CFG0_OFST) & SCRUB_MODE_MASK; - if ((ecctype == SCRUB_MODE_SECDED) && - ((dt == DEV_X2) || (dt == DEV_X4) || (dt == DEV_X8))) - return true; + if (priv->p_data->platform == ZYNQ) { + dt = zynq_get_dtype(priv->baseaddr); + if (dt == DEV_UNKNOWN) + return false; + + ecctype = readl(priv->baseaddr + SCRUB_OFST) & SCRUB_MODE_MASK; + if (ecctype == SCRUB_MODE_SECDED && dt == DEV_X2) { + clearval = ECC_CTRL_CLR_CE_ERR | ECC_CTRL_CLR_UE_ERR; + writel(clearval, priv->baseaddr + ECC_CTRL_OFST); + writel(0x0, priv->baseaddr + ECC_CTRL_OFST); + return true; + } + } else { + dt = zynqmp_get_dtype(priv->baseaddr); + if (dt == DEV_UNKNOWN) + return false; + + ecctype = readl(priv->baseaddr + ECC_CFG0_OFST) & SCRUB_MODE_MASK; + if (ecctype == SCRUB_MODE_SECDED && + (dt == DEV_X2 || dt == DEV_X4 || dt == DEV_X8)) { + clearval = readl(priv->baseaddr + ECC_CLR_OFST) | + ECC_CTRL_CLR_CE_ERR | ECC_CTRL_CLR_CE_ERRCNT | + ECC_CTRL_CLR_UE_ERR | ECC_CTRL_CLR_UE_ERRCNT; + writel(clearval, priv->baseaddr + ECC_CLR_OFST); + return true; + } + }

return false; } @@ -935,18 +928,18 @@ static int setup_irq(struct mem_ctl_info *mci, }

static const struct synps_platform_data zynq_edac_def = { + .platform = ZYNQ, .get_error_info = zynq_get_error_info, .get_mtype = zynq_get_mtype, .get_dtype = zynq_get_dtype, - .get_ecc_state = zynq_get_ecc_state, .quirks = 0, };

static const struct synps_platform_data zynqmp_edac_def = { + .platform = ZYNQMP, .get_error_info = zynqmp_get_error_info, .get_mtype = zynqmp_get_mtype, .get_dtype = zynqmp_get_dtype, - .get_ecc_state = zynqmp_get_ecc_state, #ifdef CONFIG_EDAC_DEBUG .get_mem_info = zynqmp_get_mem_info, #endif @@ -958,10 +951,10 @@ static const struct synps_platform_data zynqmp_edac_def = { };

static const struct synps_platform_data synopsys_edac_def = { + .platform = SYNPS, .get_error_info = zynqmp_get_error_info, .get_mtype = zynqmp_get_mtype, .get_dtype = zynqmp_get_dtype, - .get_ecc_state = zynqmp_get_ecc_state, .quirks = (DDR_ECC_INTR_SUPPORT | DDR_ECC_INTR_SELF_CLEAR #ifdef CONFIG_EDAC_DEBUG | DDR_ECC_DATA_POISON_SUPPORT @@ -1393,10 +1386,6 @@ static int mc_probe(struct platform_device *pdev) if (!p_data) return -ENODEV;

- if (!p_data->get_ecc_state(baseaddr)) { - edac_printk(KERN_INFO, EDAC_MC, "ECC not enabled\n"); - return -ENXIO; - }

layers[0].type = EDAC_MC_LAYER_CHIP_SELECT; layers[0].size = SYNPS_EDAC_NR_CSROWS; @@ -1416,6 +1405,12 @@ static int mc_probe(struct platform_device *pdev) priv = mci->pvt_info; priv->baseaddr = baseaddr; priv->p_data = p_data; + if (!get_ecc_state(priv)) { + edac_printk(KERN_INFO, EDAC_MC, "ECC not enabled\n"); + rc = -ENODEV; + goto free_edac_mc; + } + spin_lock_init(&priv->reglock);

mc_init(mci, pdev);

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

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

From: David Collins david.collins@oss.qualcomm.com

[ Upstream commit f8e157ff2df46ddabd930815d196895976227831 ]

Certain TEMP_ALARM GEN2 PMIC peripherals need over-temperature stage 2 automatic PMIC partial shutdown. This will ensure that in the event of reaching the hotter stage 3 over-temperature threshold, repeated faults will be avoided during the automatic PMIC hardware full shutdown. Modify the stage 2 shutdown control logic to ensure that stage 2 shutdown is enabled on all affected PMICs. Read the digital major and minor revision registers to identify these PMICs.

Signed-off-by: David Collins david.collins@oss.qualcomm.com Signed-off-by: Anjelique Melendez anjelique.melendez@oss.qualcomm.com Link: https://lore.kernel.org/r/20250710224555.3047790-2-anjelique.melendez@oss.qu... Signed-off-by: Daniel Lezcano daniel.lezcano@linaro.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/thermal/qcom/qcom-spmi-temp-alarm.c | 43 ++++++++++++++++----- 1 file changed, 34 insertions(+), 9 deletions(-)

diff --git a/drivers/thermal/qcom/qcom-spmi-temp-alarm.c b/drivers/thermal/qcom/qcom-spmi-temp-alarm.c index ad84978109e6..ccd082bf6fdc 100644 --- a/drivers/thermal/qcom/qcom-spmi-temp-alarm.c +++ b/drivers/thermal/qcom/qcom-spmi-temp-alarm.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (c) 2011-2015, 2017, 2020, The Linux Foundation. All rights reserved. + * Copyright (c) Qualcomm Technologies, Inc. and/or its subsidiaries. */

#include <linux/bitops.h> @@ -18,6 +19,7 @@ #include "../thermal_core.h" #include "../thermal_hwmon.h"

+#define QPNP_TM_REG_DIG_MINOR 0x00 #define QPNP_TM_REG_DIG_MAJOR 0x01 #define QPNP_TM_REG_TYPE 0x04 #define QPNP_TM_REG_SUBTYPE 0x05 @@ -33,7 +35,7 @@ #define STATUS_GEN2_STATE_MASK GENMASK(6, 4) #define STATUS_GEN2_STATE_SHIFT 4

-#define SHUTDOWN_CTRL1_OVERRIDE_S2 BIT(6) +#define SHUTDOWN_CTRL1_OVERRIDE_STAGE2 BIT(6) #define SHUTDOWN_CTRL1_THRESHOLD_MASK GENMASK(1, 0)

#define SHUTDOWN_CTRL1_RATE_25HZ BIT(3) @@ -81,6 +83,7 @@ struct qpnp_tm_chip { /* protects .thresh, .stage and chip registers */ struct mutex lock; bool initialized; + bool require_stage2_shutdown;

struct iio_channel *adc; const long (*temp_map)[THRESH_COUNT][STAGE_COUNT]; @@ -223,13 +226,13 @@ static int qpnp_tm_update_critical_trip_temp(struct qpnp_tm_chip *chip, { long stage2_threshold_min = (*chip->temp_map)[THRESH_MIN][1]; long stage2_threshold_max = (*chip->temp_map)[THRESH_MAX][1]; - bool disable_s2_shutdown = false; + bool disable_stage2_shutdown = false; u8 reg;

WARN_ON(!mutex_is_locked(&chip->lock));

/* - * Default: S2 and S3 shutdown enabled, thresholds at + * Default: Stage 2 and Stage 3 shutdown enabled, thresholds at * lowest threshold set, monitoring at 25Hz */ reg = SHUTDOWN_CTRL1_RATE_25HZ; @@ -244,12 +247,12 @@ static int qpnp_tm_update_critical_trip_temp(struct qpnp_tm_chip *chip, chip->thresh = THRESH_MAX - ((stage2_threshold_max - temp) / TEMP_THRESH_STEP); - disable_s2_shutdown = true; + disable_stage2_shutdown = true; } else { chip->thresh = THRESH_MAX;

if (chip->adc) - disable_s2_shutdown = true; + disable_stage2_shutdown = true; else dev_warn(chip->dev, "No ADC is configured and critical temperature %d mC is above the maximum stage 2 threshold of %ld mC! Configuring stage 2 shutdown at %ld mC.\n", @@ -258,8 +261,8 @@ static int qpnp_tm_update_critical_trip_temp(struct qpnp_tm_chip *chip,

skip: reg |= chip->thresh; - if (disable_s2_shutdown) - reg |= SHUTDOWN_CTRL1_OVERRIDE_S2; + if (disable_stage2_shutdown && !chip->require_stage2_shutdown) + reg |= SHUTDOWN_CTRL1_OVERRIDE_STAGE2;

return qpnp_tm_write(chip, QPNP_TM_REG_SHUTDOWN_CTRL1, reg); } @@ -373,8 +376,8 @@ static int qpnp_tm_probe(struct platform_device *pdev) { struct qpnp_tm_chip *chip; struct device_node *node; - u8 type, subtype, dig_major; - u32 res; + u8 type, subtype, dig_major, dig_minor; + u32 res, dig_revision; int ret, irq;

node = pdev->dev.of_node; @@ -429,6 +432,11 @@ static int qpnp_tm_probe(struct platform_device *pdev) return ret; }

+ ret = qpnp_tm_read(chip, QPNP_TM_REG_DIG_MINOR, &dig_minor); + if (ret < 0) + return dev_err_probe(&pdev->dev, ret, + "could not read dig_minor\n"); + if (type != QPNP_TM_TYPE || (subtype != QPNP_TM_SUBTYPE_GEN1 && subtype != QPNP_TM_SUBTYPE_GEN2)) { dev_err(&pdev->dev, "invalid type 0x%02x or subtype 0x%02x\n", @@ -442,6 +450,23 @@ static int qpnp_tm_probe(struct platform_device *pdev) else chip->temp_map = &temp_map_gen1;

+ if (chip->subtype == QPNP_TM_SUBTYPE_GEN2) { + dig_revision = (dig_major << 8) | dig_minor; + /* + * Check if stage 2 automatic partial shutdown must remain + * enabled to avoid potential repeated faults upon reaching + * over-temperature stage 3. + */ + switch (dig_revision) { + case 0x0001: + case 0x0002: + case 0x0100: + case 0x0101: + chip->require_stage2_shutdown = true; + break; + } + } + /* * Register the sensor before initializing the hardware to be able to * read the trip points. get_temp() returns the default temperature

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

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

From: David Lechner dlechner@baylibre.com

[ Upstream commit 5a2f15c5a8e017d0951e6dc62aa7b5b634f56881 ]

Fix overallocating the size of the scan buffer by converting bits to bytes. The size is meant to be in bytes, so scanbits needs to be divided by 8.

Signed-off-by: David Lechner dlechner@baylibre.com Reviewed-by: Andy Shevchenko andriy.shevchenko@linux.intel.com Reviewed-by: Nuno Sá nuno.sa@analog.com Link: https://patch.msgid.link/20250701-iio-adc-ad7173-add-spi-offload-support-v3-... Signed-off-by: Jonathan Cameron Jonathan.Cameron@huawei.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/iio/adc/ad_sigma_delta.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/iio/adc/ad_sigma_delta.c b/drivers/iio/adc/ad_sigma_delta.c index 533667eefe41..71e775a10a91 100644 --- a/drivers/iio/adc/ad_sigma_delta.c +++ b/drivers/iio/adc/ad_sigma_delta.c @@ -378,7 +378,7 @@ static int ad_sd_buffer_postenable(struct iio_dev *indio_dev) return ret; }

- samples_buf_size = ALIGN(slot * indio_dev->channels[0].scan_type.storagebits, 8); + samples_buf_size = ALIGN(slot * indio_dev->channels[0].scan_type.storagebits / 8, 8); samples_buf_size += sizeof(int64_t); samples_buf = devm_krealloc(&sigma_delta->spi->dev, sigma_delta->samples_buf, samples_buf_size, GFP_KERNEL);

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

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

From: Aaron Kling webgeek1234@gmail.com

[ Upstream commit 398e67e0f5ae04b29bcc9cbf342e339fe9d3f6f1 ]

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

Signed-off-by: Aaron Kling webgeek1234@gmail.com Link: https://lore.kernel.org/r/20250522-mach-tegra-kasan-v1-1-419041b8addb@gmail.... Signed-off-by: Thierry Reding treding@nvidia.com Signed-off-by: Sasha Levin sashal@kernel.org --- arch/arm/mach-tegra/reset.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/arm/mach-tegra/reset.c b/arch/arm/mach-tegra/reset.c index d5c805adf7a8..ea706fac6358 100644 --- a/arch/arm/mach-tegra/reset.c +++ b/arch/arm/mach-tegra/reset.c @@ -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);

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

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

From: Masami Hiramatsu (Google) mhiramat@kernel.org

[ 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.

Link: https://lore.kernel.org/r/175151680309.2149615.9795104805153538717.stgit@mhi... Signed-off-by: Masami Hiramatsu (Google) mhiramat@kernel.org Acked-by: Steven Rostedt (Google) rostedt@goodmis.org Signed-off-by: Shuah Khan skhan@linuxfoundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- .../testing/selftests/ftrace/test.d/ftrace/func-filter-glob.tc | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-glob.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-glob.tc index 4b994b6df5ac..ed81eaf2afd6 100644 --- a/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-glob.tc +++ b/tools/testing/selftests/ftrace/test.d/ftrace/func-filter-glob.tc @@ -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.

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

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

From: Rafael J. Wysocki rafael.j.wysocki@intel.com

[ 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.

Suggested-by: Ulf Hansson ulf.hansson@linaro.org Signed-off-by: Rafael J. Wysocki rafael.j.wysocki@intel.com Reviewed-by: Ulf Hansson ulf.hansson@linaro.org Link: https://patch.msgid.link/9495163.CDJkKcVGEf@rjwysocki.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/base/power/runtime.c | 5 +++++ 1 file changed, 5 insertions(+)

diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c index 313ccb7e7764..61d8ebc2de59 100644 --- a/drivers/base/power/runtime.c +++ b/drivers/base/power/runtime.c @@ -1753,6 +1753,11 @@ 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; }

/**

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

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

From: tuhaowen tuhaowen@uniontech.com

[ 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.

Signed-off-by: tuhaowen tuhaowen@uniontech.com Link: https://patch.msgid.link/20250611032345.29962-1-tuhaowen@uniontech.com Signed-off-by: Rafael J. Wysocki rafael.j.wysocki@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- kernel/power/console.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/kernel/power/console.c b/kernel/power/console.c index fcdf0e14a47d..19c48aa5355d 100644 --- a/kernel/power/console.c +++ b/kernel/power/console.c @@ -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; }

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

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

From: Sarthak Garg quic_sartgarg@quicinc.com

[ 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.

Signed-off-by: Sarthak Garg quic_sartgarg@quicinc.com Acked-by: Adrian Hunter adrian.hunter@intel.com Link: https://lore.kernel.org/r/20250701100659.3310386-1-quic_sartgarg@quicinc.com Signed-off-by: Ulf Hansson ulf.hansson@linaro.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/mmc/host/sdhci-msm.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+)

diff --git a/drivers/mmc/host/sdhci-msm.c b/drivers/mmc/host/sdhci-msm.c index c8488b8e2073..f507fa491c58 100644 --- a/drivers/mmc/host/sdhci-msm.c +++ b/drivers/mmc/host/sdhci-msm.c @@ -1560,6 +1560,7 @@ 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 = @@ -1617,6 +1618,12 @@ 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); } @@ -1675,6 +1682,13 @@ 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;

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

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

From: Eliav Farber farbere@amazon.com

[ Upstream commit 6bca1e955830808dc90e0506b2951b4256b81bbb ]

The interrupt handler in pps_gpio_probe() is registered after calling pps_register_source() using devm_request_irq(). However, in the corresponding remove function, pps_unregister_source() is called before the IRQ is freed, since devm-managed resources are released after the remove function completes.

This creates a potential race condition where an interrupt may occur after the PPS source is unregistered but before the handler is removed, possibly leading to a kernel panic.

To prevent this, switch from devm-managed IRQ registration to manual management by using request_irq() and calling free_irq() explicitly in the remove path before unregistering the PPS source. This ensures the interrupt handler is safely removed before deactivating the PPS source.

Signed-off-by: Eliav Farber farbere@amazon.com Link: https://lore.kernel.org/r/20250527053355.37185-1-farbere@amazon.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/pps/clients/pps-gpio.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/pps/clients/pps-gpio.c b/drivers/pps/clients/pps-gpio.c index bf3b6f1aa984..41e1fdbcda16 100644 --- a/drivers/pps/clients/pps-gpio.c +++ b/drivers/pps/clients/pps-gpio.c @@ -206,8 +206,8 @@ static int pps_gpio_probe(struct platform_device *pdev) }

/* register IRQ interrupt handler */ - ret = devm_request_irq(dev, data->irq, pps_gpio_irq_handler, - get_irqf_trigger_flags(data), data->info.name, data); + ret = request_irq(data->irq, pps_gpio_irq_handler, + get_irqf_trigger_flags(data), data->info.name, data); if (ret) { pps_unregister_source(data->pps); dev_err(dev, "failed to acquire IRQ %d\n", data->irq); @@ -224,6 +224,7 @@ static int pps_gpio_remove(struct platform_device *pdev) { struct pps_gpio_device_data *data = platform_get_drvdata(pdev);

+ free_irq(data->irq, data); pps_unregister_source(data->pps); del_timer_sync(&data->echo_timer); /* reset echo pin in any case */

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

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

From: Hans de Goede hansg@kernel.org

[ Upstream commit 35e8a426b16adbecae7a4e0e3c00fc8d0273db53 ]

mei_cl_bus_dev_release() also frees the mei-client (struct mei_cl) belonging to the device being released.

If there are bugs like the just fixed bug in the ACE/CSI2 mei drivers, the mei-client being freed might still be part of the mei_device's file_list and iterating over this list after the freeing will then trigger a use-afer-free bug.

Add a check to mei_cl_bus_dev_release() to make sure that the to-be-freed mei-client is not on the mei_device's file_list.

Signed-off-by: Hans de Goede hansg@kernel.org Link: https://lore.kernel.org/r/20250623085052.12347-11-hansg@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/misc/mei/bus.c | 6 ++++++ 1 file changed, 6 insertions(+)

diff --git a/drivers/misc/mei/bus.c b/drivers/misc/mei/bus.c index 7b7f4190cd02..19bc1e9eeb7f 100644 --- a/drivers/misc/mei/bus.c +++ b/drivers/misc/mei/bus.c @@ -1113,6 +1113,8 @@ static void mei_dev_bus_put(struct mei_device *bus) static void mei_cl_bus_dev_release(struct device *dev) { struct mei_cl_device *cldev = to_mei_cl_device(dev); + struct mei_device *mdev = cldev->cl->dev; + struct mei_cl *cl;

if (!cldev) return; @@ -1120,6 +1122,10 @@ static void mei_cl_bus_dev_release(struct device *dev) mei_cl_flush_queues(cldev->cl, NULL); mei_me_cl_put(cldev->me_cl); mei_dev_bus_put(cldev->bus); + + list_for_each_entry(cl, &mdev->file_list, link) + WARN_ON(cl == cldev->cl); + kfree(cldev->cl); kfree(cldev); }

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

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

From: Takashi Iwai tiwai@suse.de

[ Upstream commit 5f7e54b23e4d253eff3b10b12d6fa92d28d7dddc ]

We used to call directly hda_jackpoll_work() from a couple of places for updating the jack and notify to user-space, but this makes rather the code flow fragile. Namely, because of those direct calls, hda_jackpoll_work() uses snd_hda_power_up_pm() and *_down_pm() calls instead of the standard snd_hda_power_up() and *_down() calls. The latter pair assures the runtime PM resume sync, so it can avoid the race against the PM callbacks gracefully, while the former pair may continue if called concurrently, hence it may race (by design).

In this patch, we change the call pattern of hda_jackpoll_work(); now all callers are replaced with the standard snd_hda_jack_report_sync() and the additional schedule_delayed_work().

Since hda_jackpoll_work() is called only from the associated work, it's always outside the PM code path, and we can safely use snd_hda_power_up() and *_down() there instead. This allows us to remove the racy check of power-state in hda_jackpoll_work(), as well as the tricky cancel_delayed_work() and rescheduling at hda_codec_runtime_suspend().

Reported-by: Joakim Zhang joakim.zhang@cixtech.com Closes: https://lore.kernel.org/20250619020844.2974160-1-joakim.zhang@cixtech.com Tested-by: Joakim Zhang joakim.zhang@cixtech.com Signed-off-by: Takashi Iwai tiwai@suse.de Link: https://patch.msgid.link/20250623131437.10670-4-tiwai@suse.de Signed-off-by: Sasha Levin sashal@kernel.org --- sound/pci/hda/hda_codec.c | 41 +++++++++++++-------------------------- 1 file changed, 14 insertions(+), 27 deletions(-)

diff --git a/sound/pci/hda/hda_codec.c b/sound/pci/hda/hda_codec.c index 9d7d99b584fe..94b3732e6cb2 100644 --- a/sound/pci/hda/hda_codec.c +++ b/sound/pci/hda/hda_codec.c @@ -641,24 +641,16 @@ static void hda_jackpoll_work(struct work_struct *work) struct hda_codec *codec = container_of(work, struct hda_codec, jackpoll_work.work);

- /* for non-polling trigger: we need nothing if already powered on */ - if (!codec->jackpoll_interval && snd_hdac_is_power_on(&codec->core)) + if (!codec->jackpoll_interval) return;

/* the power-up/down sequence triggers the runtime resume */ - snd_hda_power_up_pm(codec); + snd_hda_power_up(codec); /* update jacks manually if polling is required, too */ - if (codec->jackpoll_interval) { - snd_hda_jack_set_dirty_all(codec); - snd_hda_jack_poll_all(codec); - } - snd_hda_power_down_pm(codec); - - if (!codec->jackpoll_interval) - return; - - schedule_delayed_work(&codec->jackpoll_work, - codec->jackpoll_interval); + snd_hda_jack_set_dirty_all(codec); + snd_hda_jack_poll_all(codec); + schedule_delayed_work(&codec->jackpoll_work, codec->jackpoll_interval); + snd_hda_power_down(codec); }

/* release all pincfg lists */ @@ -2922,12 +2914,12 @@ static void hda_call_codec_resume(struct hda_codec *codec) snd_hda_regmap_sync(codec); }

- if (codec->jackpoll_interval) - hda_jackpoll_work(&codec->jackpoll_work.work); - else - snd_hda_jack_report_sync(codec); + snd_hda_jack_report_sync(codec); codec->core.dev.power.power_state = PMSG_ON; snd_hdac_leave_pm(&codec->core); + if (codec->jackpoll_interval) + schedule_delayed_work(&codec->jackpoll_work, + codec->jackpoll_interval); }

static int hda_codec_runtime_suspend(struct device *dev) @@ -2939,8 +2931,6 @@ static int hda_codec_runtime_suspend(struct device *dev) if (!codec->card) return 0;

- cancel_delayed_work_sync(&codec->jackpoll_work); - state = hda_call_codec_suspend(codec); if (codec->link_down_at_suspend || (codec_has_clkstop(codec) && codec_has_epss(codec) && @@ -2948,10 +2938,6 @@ static int hda_codec_runtime_suspend(struct device *dev) snd_hdac_codec_link_down(&codec->core); snd_hda_codec_display_power(codec, false);

- if (codec->bus->jackpoll_in_suspend && - (dev->power.power_state.event != PM_EVENT_SUSPEND)) - schedule_delayed_work(&codec->jackpoll_work, - codec->jackpoll_interval); return 0; }

@@ -3120,10 +3106,11 @@ int snd_hda_codec_build_controls(struct hda_codec *codec) if (err < 0) return err;

+ snd_hda_jack_report_sync(codec); /* call at the last init point */ if (codec->jackpoll_interval) - hda_jackpoll_work(&codec->jackpoll_work.work); - else - snd_hda_jack_report_sync(codec); /* call at the last init point */ + schedule_delayed_work(&codec->jackpoll_work, + codec->jackpoll_interval); + sync_power_up_states(codec); return 0; }

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

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

From: Pawan Gupta pawan.kumar.gupta@linux.intel.com

[ 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.

Suggested-by: Borislav Petkov bp@alien8.de Signed-off-by: Pawan Gupta pawan.kumar.gupta@linux.intel.com Signed-off-by: Borislav Petkov (AMD) bp@alien8.de Link: https://lore.kernel.org/20250611-eibrs-fix-v4-3-5ff86cac6c61@linux.intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- arch/x86/kernel/cpu/bugs.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index dba5262e1509..4fbb5b15ab75 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -70,10 +70,9 @@ 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 */

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

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

From: Alok Tiwari alok.a.tiwari@oracle.com

[ 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.

Signed-off-by: Alok Tiwari alok.a.tiwari@oracle.com Link: https://patch.msgid.link/20250621185233.4081094-1-alok.a.tiwari@oracle.com Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Sasha Levin sashal@kernel.org --- sound/pci/intel8x0.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/pci/intel8x0.c b/sound/pci/intel8x0.c index ae285c0a629c..f3df6fe2b7f1 100644 --- a/sound/pci/intel8x0.c +++ b/sound/pci/intel8x0.c @@ -2252,7 +2252,7 @@ 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; } }

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

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

From: Tomasz Michalec tmichalec@google.com

[ 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.

Signed-off-by: Tomasz Michalec tmichalec@google.com Reviewed-by: Heikki Krogerus heikki.krogerus@linux.intel.com Link: https://lore.kernel.org/r/20250610154058.1859812-1-tmichalec@google.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/usb/typec/mux/intel_pmc_mux.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/usb/typec/mux/intel_pmc_mux.c b/drivers/usb/typec/mux/intel_pmc_mux.c index 87e2c9130607..a6936fc59d1e 100644 --- a/drivers/usb/typec/mux/intel_pmc_mux.c +++ b/drivers/usb/typec/mux/intel_pmc_mux.c @@ -667,7 +667,7 @@ 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;

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

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

From: Gautham R. Shenoy gautham.shenoy@amd.com

[ 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().

Link: https://lore.kernel.org/r/20250612122355.19629-2-gautham.shenoy@amd.com Signed-off-by: Gautham R. Shenoy gautham.shenoy@amd.com Signed-off-by: Shuah Khan skhan@linuxfoundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- tools/power/cpupower/utils/idle_monitor/mperf_monitor.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/power/cpupower/utils/idle_monitor/mperf_monitor.c b/tools/power/cpupower/utils/idle_monitor/mperf_monitor.c index 08a399b0be28..6ab9139f16af 100644 --- a/tools/power/cpupower/utils/idle_monitor/mperf_monitor.c +++ b/tools/power/cpupower/utils/idle_monitor/mperf_monitor.c @@ -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;

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

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

From: Tomasz Michalec tmichalec@google.com

[ 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.

Signed-off-by: Tomasz Michalec tmichalec@google.com Reviewed-by: Abhishek Pandit-Subedi abhishekpandit@chromium.org Link: https://lore.kernel.org/r/20250610153748.1858519-1-tmichalec@google.com Signed-off-by: Tzung-Bi Shih tzungbi@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/platform/chrome/cros_ec_typec.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/platform/chrome/cros_ec_typec.c b/drivers/platform/chrome/cros_ec_typec.c index 51b98f6c7b39..748efa73378c 100644 --- a/drivers/platform/chrome/cros_ec_typec.c +++ b/drivers/platform/chrome/cros_ec_typec.c @@ -1194,8 +1194,8 @@ 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);

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

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

From: Christophe Leroy christophe.leroy@csgroup.eu

[ 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.

Signed-off-by: Christophe Leroy christophe.leroy@csgroup.eu Link: https://patch.msgid.link/4836e2cde653eebaf2709ebe30eec736bb8c67fd.1749202237... Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Sasha Levin sashal@kernel.org --- sound/core/pcm_native.c | 19 +++++++++++++++---- 1 file changed, 15 insertions(+), 4 deletions(-)

diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c index bf752b188b05..900525df53f0 100644 --- a/sound/core/pcm_native.c +++ b/sound/core/pcm_native.c @@ -24,6 +24,7 @@ #include <sound/minors.h> #include <linux/uio.h> #include <linux/delay.h> +#include <linux/bitops.h>

#include "pcm_local.h"

@@ -3123,13 +3124,23 @@ 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,

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

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

From: Jonathan Santos Jonathan.Santos@analog.com

[ 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.

Signed-off-by: Jonathan Santos Jonathan.Santos@analog.com Reviewed-by: David Lechner dlechner@baylibre.com Reviewed-by: Andy Shevchenko andriy.shevchenko@linux.intel.com Link: https://patch.msgid.link/d3ee92a533cd1207cf5c5cc4d7bdbb5c6c267f68.1749063024... Signed-off-by: Jonathan Cameron Jonathan.Cameron@huawei.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/iio/adc/ad7768-1.c | 23 +++++++++++++++++++---- 1 file changed, 19 insertions(+), 4 deletions(-)

diff --git a/drivers/iio/adc/ad7768-1.c b/drivers/iio/adc/ad7768-1.c index 967f06cd3f94..e147eaf1a3b1 100644 --- a/drivers/iio/adc/ad7768-1.c +++ b/drivers/iio/adc/ad7768-1.c @@ -203,6 +203,24 @@ 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) { @@ -288,10 +306,7 @@ 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,

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

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

From: Anthoine Bourgeois anthoine.bourgeois@vates.tech

[ 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

Signed-off-by: Anthoine Bourgeois anthoine.bourgeois@vates.tech Reviewed-by: Juergen Gross jgross@suse.com Tested-by: Elliott Mitchell ehem+xen@m5p.com Signed-off-by: Juergen Gross jgross@suse.com Message-ID: 20250721093316.23560-1-anthoine.bourgeois@vates.tech Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/xen-netfront.c | 5 ----- 1 file changed, 5 deletions(-)

diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c index 69ef50fb2e1b..74925e166462 100644 --- a/drivers/net/xen-netfront.c +++ b/drivers/net/xen-netfront.c @@ -637,8 +637,6 @@ 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; }

@@ -848,9 +846,6 @@ 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));

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

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

From: Steven Rostedt rostedt@goodmis.org

[ 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.

Cc: "John Warthog9 Hawley" warthog9@kernel.org Cc: Dhaval Giani dhaval.giani@gmail.com Cc: Greg KH gregkh@linuxfoundation.org Link: https://lore.kernel.org/20250718202053.732189428@kernel.org Signed-off-by: Steven Rostedt rostedt@goodmis.org Signed-off-by: Sasha Levin sashal@kernel.org --- tools/testing/ktest/ktest.pl | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/tools/testing/ktest/ktest.pl b/tools/testing/ktest/ktest.pl index 2109bd42c144..26544bba3f8f 100755 --- a/tools/testing/ktest/ktest.pl +++ b/tools/testing/ktest/ktest.pl @@ -1351,7 +1351,10 @@ 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";

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

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

From: Sven Schnelle svens@linux.ibm.com

[ Upstream commit 09e7e29d2b49ba84bcefb3dc1657726d2de5bb24 ]

Otherwise the code might not work correctly when the clock is changed.

Signed-off-by: Sven Schnelle svens@linux.ibm.com Reviewed-by: Heiko Carstens hca@linux.ibm.com Signed-off-by: Alexander Gordeev agordeev@linux.ibm.com Signed-off-by: Sasha Levin sashal@kernel.org --- arch/s390/include/asm/timex.h | 13 ++++++------- 1 file changed, 6 insertions(+), 7 deletions(-)

diff --git a/arch/s390/include/asm/timex.h b/arch/s390/include/asm/timex.h index ce878e85b6e4..d0255aa5b36e 100644 --- a/arch/s390/include/asm/timex.h +++ b/arch/s390/include/asm/timex.h @@ -192,13 +192,6 @@ static inline unsigned long get_tod_clock_fast(void) asm volatile("stckf %0" : "=Q" (clk) : : "cc"); return clk; } - -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);

@@ -221,6 +214,12 @@ static inline unsigned 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

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

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

From: Bitterblue Smith rtl8821cerfe2@gmail.com

[ Upstream commit 671be46afd1f03de9dc6e4679c88e1a7a81cdff6 ]

This read_poll_timeout_atomic() with a delay of 1 µs and a timeout of 1000000 µs can take ~250 seconds in the worst case because sending a USB control message takes ~250 µs.

Lower the timeout to 4000 for USB in order to reduce the maximum polling time to ~1 second.

This problem was observed with RTL8851BU while suspending to RAM with WOWLAN enabled. The computer sat for 4 minutes with a black screen before suspending.

Signed-off-by: Bitterblue Smith rtl8821cerfe2@gmail.com Signed-off-by: Ping-Ke Shih pkshih@realtek.com Link: https://patch.msgid.link/09313da6-c865-4e91-b758-4cb38a878796@gmail.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/wireless/realtek/rtw89/fw.c | 9 +++++++-- drivers/net/wireless/realtek/rtw89/fw.h | 2 ++ 2 files changed, 9 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/fw.c b/drivers/net/wireless/realtek/rtw89/fw.c index 0f022a5192ac..977aadfdf997 100644 --- a/drivers/net/wireless/realtek/rtw89/fw.c +++ b/drivers/net/wireless/realtek/rtw89/fw.c @@ -2397,13 +2397,18 @@ static int rtw89_fw_read_c2h_reg(struct rtw89_dev *rtwdev, { const struct rtw89_chip_info *chip = rtwdev->chip; const u32 *c2h_reg = chip->c2h_regs; - u32 ret; + u32 ret, timeout; u8 i, val;

info->id = RTW89_FWCMD_C2HREG_FUNC_NULL;

+ if (rtwdev->hci.type == RTW89_HCI_TYPE_USB) + timeout = RTW89_C2H_TIMEOUT_USB; + else + timeout = RTW89_C2H_TIMEOUT; + ret = read_poll_timeout_atomic(rtw89_read8, val, val, 1, - RTW89_C2H_TIMEOUT, false, rtwdev, + timeout, false, rtwdev, chip->c2h_ctrl_reg); if (ret) { rtw89_warn(rtwdev, "c2h reg timeout\n"); diff --git a/drivers/net/wireless/realtek/rtw89/fw.h b/drivers/net/wireless/realtek/rtw89/fw.h index 0047d5d0e9b1..d0f2c5b22513 100644 --- a/drivers/net/wireless/realtek/rtw89/fw.h +++ b/drivers/net/wireless/realtek/rtw89/fw.h @@ -33,6 +33,8 @@ enum rtw89_fw_dl_status { #define RTW89_C2HREG_HDR_LEN 2 #define RTW89_H2CREG_HDR_LEN 2 #define RTW89_C2H_TIMEOUT 1000000 +#define RTW89_C2H_TIMEOUT_USB 4000 + struct rtw89_mac_c2h_info { u8 id; u8 content_len;

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

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

From: Thomas Fourier fourier.thomas@gmail.com

[ Upstream commit 96a1e15e60216b52da0e6da5336b6d7f5b0188b0 ]

The DMA map functions can fail and should be tested for errors.

Signed-off-by: Thomas Fourier fourier.thomas@gmail.com Reviewed-by: Simon Horman horms@kernel.org Link: https://patch.msgid.link/20250716095733.37452-3-fourier.thomas@gmail.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/atheros/ag71xx.c | 9 +++++++++ 1 file changed, 9 insertions(+)

diff --git a/drivers/net/ethernet/atheros/ag71xx.c b/drivers/net/ethernet/atheros/ag71xx.c index 4a1efe9b37d0..ff93b00dcd61 100644 --- a/drivers/net/ethernet/atheros/ag71xx.c +++ b/drivers/net/ethernet/atheros/ag71xx.c @@ -1234,6 +1234,11 @@ 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; } @@ -1532,6 +1537,10 @@ 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);

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

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

From: Breno Leitao leitao@debian.org

[ Upstream commit d7ce7e3a84642aadf7c4787f7ec4f58eb163d129 ]

Set TAINT_MACHINE_CHECK when SError or Synchronous External Abort (SEA) interrupts trigger a panic to flag potential hardware faults. This tainting mechanism aids in debugging and enables correlation of hardware-related crashes in large-scale deployments.

This change aligns with similar patches[1] that mark machine check events when the system crashes due to hardware errors.

Link: https://lore.kernel.org/all/20250702-add_tain-v1-1-9187b10914b9@debian.org/ [1] Signed-off-by: Breno Leitao leitao@debian.org Acked-by: Mark Rutland mark.rutland@arm.com Link: https://lore.kernel.org/r/20250716-vmcore_hw_error-v2-1-f187f7d62aba@debian.... Signed-off-by: Will Deacon will@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- arch/arm64/kernel/traps.c | 1 + arch/arm64/mm/fault.c | 1 + 2 files changed, 2 insertions(+)

diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c index 23d281ed7621..09489e92ff94 100644 --- a/arch/arm64/kernel/traps.c +++ b/arch/arm64/kernel/traps.c @@ -911,6 +911,7 @@ void panic_bad_stack(struct pt_regs *regs, unsigned long esr, unsigned long far)

void __noreturn arm64_serror_panic(struct pt_regs *regs, unsigned long esr) { + add_taint(TAINT_MACHINE_CHECK, LOCKDEP_STILL_OK); console_verbose();

pr_crit("SError Interrupt on CPU%d, code 0x%016lx -- %s\n", diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 6b6b8a82f294..0776c98ad27f 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -710,6 +710,7 @@ static int do_sea(unsigned long far, unsigned long esr, struct pt_regs *regs) */ siaddr = untagged_addr(far); } + add_taint(TAINT_MACHINE_CHECK, LOCKDEP_STILL_OK); arm64_notify_die(inf->name, regs, inf->sig, inf->code, siaddr, esr);

return 0;

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

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

From: Matt Johnston matt@codeconstruct.com.au

[ Upstream commit 3954502377ec05a1b37e2dc9bef0bacd4bbd71b2 ]

Disallow bind() calls that have the same arguments as existing bound sockets. Previously multiple sockets could bind() to the same type/local address, with an arbitrary socket receiving matched messages.

This is only a partial fix, a future commit will define precedence order for MCTP_ADDR_ANY versus specific EID bind(), which are allowed to exist together.

Signed-off-by: Matt Johnston matt@codeconstruct.com.au Link: https://patch.msgid.link/20250710-mctp-bind-v4-2-8ec2f6460c56@codeconstruct.... Signed-off-by: Paolo Abeni pabeni@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- net/mctp/af_mctp.c | 26 +++++++++++++++++++++++--- 1 file changed, 23 insertions(+), 3 deletions(-)

diff --git a/net/mctp/af_mctp.c b/net/mctp/af_mctp.c index 6a963eac1cc2..0f49b41570f5 100644 --- a/net/mctp/af_mctp.c +++ b/net/mctp/af_mctp.c @@ -73,7 +73,6 @@ static int mctp_bind(struct socket *sock, struct sockaddr *addr, int addrlen)

lock_sock(sk);

- /* TODO: allow rebind */ if (sk_hashed(sk)) { rc = -EADDRINUSE; goto out_release; @@ -550,15 +549,36 @@ static void mctp_sk_close(struct sock *sk, long timeout) static int mctp_sk_hash(struct sock *sk) { struct net *net = sock_net(sk); + struct sock *existing; + struct mctp_sock *msk; + int rc; + + msk = container_of(sk, struct mctp_sock, sk);

/* Bind lookup runs under RCU, remain live during that. */ sock_set_flag(sk, SOCK_RCU_FREE);

mutex_lock(&net->mctp.bind_lock); + + /* Prevent duplicate binds. */ + sk_for_each(existing, &net->mctp.binds) { + struct mctp_sock *mex = + container_of(existing, struct mctp_sock, sk); + + if (mex->bind_type == msk->bind_type && + mex->bind_addr == msk->bind_addr && + mex->bind_net == msk->bind_net) { + rc = -EADDRINUSE; + goto out; + } + } + sk_add_node_rcu(sk, &net->mctp.binds); - mutex_unlock(&net->mctp.bind_lock); + rc = 0;

- return 0; +out: + mutex_unlock(&net->mctp.bind_lock); + return rc; }

static void mctp_sk_unhash(struct sock *sk)

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

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

From: Oscar Maes oscmaes92@gmail.com

[ 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).

Signed-off-by: Oscar Maes oscmaes92@gmail.com Link: https://patch.msgid.link/20250710142714.12986-1-oscmaes92@gmail.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- net/ipv4/route.c | 1 - 1 file changed, 1 deletion(-)

diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 870108101017..c57a1cee98e2 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -2562,7 +2562,6 @@ 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,

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

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

From: Thomas Weißschuh thomas.weissschuh@linutronix.de

[ Upstream commit b9e2f2246eb2b5617d53af7b5e4e1b8c916f26a8 ]

The thread flags may change during their processing. For example a task_work can queue a new signal to be sent. This signal should be delivered before returning to usespace again.

Evaluate the flags repeatedly similar to other architectures.

Signed-off-by: Thomas Weißschuh thomas.weissschuh@linutronix.de Reviewed-by: Nam Cao namcao@linutronix.de Link: https://patch.msgid.link/20250704-uml-thread_flags-v1-1-0e293fd8d627@linutro... Signed-off-by: Johannes Berg johannes.berg@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- arch/um/include/asm/thread_info.h | 4 ++++ arch/um/kernel/process.c | 20 ++++++++++++-------- 2 files changed, 16 insertions(+), 8 deletions(-)

diff --git a/arch/um/include/asm/thread_info.h b/arch/um/include/asm/thread_info.h index c7b4b49826a2..40d823f36c09 100644 --- a/arch/um/include/asm/thread_info.h +++ b/arch/um/include/asm/thread_info.h @@ -68,7 +68,11 @@ static inline struct thread_info *current_thread_info(void) #define _TIF_NOTIFY_SIGNAL (1 << TIF_NOTIFY_SIGNAL) #define _TIF_MEMDIE (1 << TIF_MEMDIE) #define _TIF_SYSCALL_AUDIT (1 << TIF_SYSCALL_AUDIT) +#define _TIF_NOTIFY_RESUME (1 << TIF_NOTIFY_RESUME) #define _TIF_SECCOMP (1 << TIF_SECCOMP) #define _TIF_SINGLESTEP (1 << TIF_SINGLESTEP)

+#define _TIF_WORK_MASK (_TIF_NEED_RESCHED | _TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL | \ + _TIF_NOTIFY_RESUME) + #endif diff --git a/arch/um/kernel/process.c b/arch/um/kernel/process.c index c5281ce31685..d8c274d99390 100644 --- a/arch/um/kernel/process.c +++ b/arch/um/kernel/process.c @@ -97,14 +97,18 @@ void *__switch_to(struct task_struct *from, struct task_struct *to) void interrupt_end(void) { struct pt_regs *regs = &current->thread.regs; - - if (need_resched()) - schedule(); - if (test_thread_flag(TIF_SIGPENDING) || - test_thread_flag(TIF_NOTIFY_SIGNAL)) - do_signal(regs); - if (test_thread_flag(TIF_NOTIFY_RESUME)) - resume_user_mode_work(regs); + unsigned long thread_flags; + + thread_flags = read_thread_flags(); + while (thread_flags & _TIF_WORK_MASK) { + if (thread_flags & _TIF_NEED_RESCHED) + schedule(); + if (thread_flags & (_TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL)) + do_signal(regs); + if (thread_flags & _TIF_NOTIFY_RESUME) + resume_user_mode_work(regs); + thread_flags = read_thread_flags(); + } }

int get_current_pid(void)

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

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

From: Sven Schnelle svens@linux.ibm.com

[ 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.

Reviewed-by: Heiko Carstens hca@linux.ibm.com Signed-off-by: Sven Schnelle svens@linux.ibm.com Signed-off-by: Alexander Gordeev agordeev@linux.ibm.com Signed-off-by: Sasha Levin sashal@kernel.org --- arch/s390/kernel/time.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c index 6b7b6d5e3632..add2862e835b 100644 --- a/arch/s390/kernel/time.c +++ b/arch/s390/kernel/time.c @@ -574,7 +574,7 @@ 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. */

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

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

From: Johannes Berg johannes.berg@intel.com

[ Upstream commit 6b04716cdcac37bdbacde34def08bc6fdb5fc4e2 ]

When SAE commit is sent and received in response, there's no ordering for the SAE confirm messages. As such, don't call drivers to stop listening on the channel when the confirm message is still expected.

This fixes an issue if the local confirm is transmitted later than the AP's confirm, for iwlwifi (and possibly mt76) the AP's confirm would then get lost since the device isn't on the channel at the time the AP transmit the confirm.

For iwlwifi at least, this also improves the overall timing of the authentication handshake (by about 15ms according to the report), likely since the session protection won't be aborted and rescheduled.

Note that even before this, mgd_complete_tx() wasn't always called for each call to mgd_prepare_tx() (e.g. in the case of WEP key shared authentication), and the current drivers that have the complete callback don't seem to mind. Document this as well though.

Reported-by: Jan Hendrik Farr kernel@jfarr.cc Closes: https://lore.kernel.org/all/aB30Ea2kRG24LINR@archlinux/ Signed-off-by: Johannes Berg johannes.berg@intel.com Signed-off-by: Miri Korenblit miriam.rachel.korenblit@intel.com Link: https://patch.msgid.link/20250609213232.12691580e140.I3f1d3127acabcd58348a11... Signed-off-by: Johannes Berg johannes.berg@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- include/net/mac80211.h | 2 ++ net/mac80211/mlme.c | 9 ++++++++- 2 files changed, 10 insertions(+), 1 deletion(-)

diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 6ef8348b5e93..28a9b9c00e6b 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -4011,6 +4011,8 @@ struct ieee80211_prep_tx_info { * @mgd_complete_tx: Notify the driver that the response frame for a previously * transmitted frame announced with @mgd_prepare_tx was received, the data * is filled similarly to @mgd_prepare_tx though the duration is not used. + * Note that this isn't always called for each mgd_prepare_tx() call, for + * example for SAE the 'confirm' messages can be on the air in any order. * * @mgd_protect_tdls_discover: Protect a TDLS discovery session. After sending * a TDLS discovery-request, we expect a reply to arrive on the AP's diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index b300972c3150..cc47d6b88f04 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -3595,6 +3595,7 @@ static void ieee80211_rx_mgmt_auth(struct ieee80211_sub_if_data *sdata, struct ieee80211_prep_tx_info info = { .subtype = IEEE80211_STYPE_AUTH, }; + bool sae_need_confirm = false;

sdata_assert_lock(sdata);

@@ -3638,6 +3639,8 @@ static void ieee80211_rx_mgmt_auth(struct ieee80211_sub_if_data *sdata, jiffies + IEEE80211_AUTH_WAIT_SAE_RETRY; ifmgd->auth_data->timeout_started = true; run_again(sdata, ifmgd->auth_data->timeout); + if (auth_transaction == 1) + sae_need_confirm = true; goto notify_driver; }

@@ -3680,6 +3683,9 @@ static void ieee80211_rx_mgmt_auth(struct ieee80211_sub_if_data *sdata, ifmgd->auth_data->expected_transaction == 2)) { if (!ieee80211_mark_sta_auth(sdata)) return; /* ignore frame -- wait for timeout */ + } else if (ifmgd->auth_data->algorithm == WLAN_AUTH_SAE && + auth_transaction == 1) { + sae_need_confirm = true; } else if (ifmgd->auth_data->algorithm == WLAN_AUTH_SAE && auth_transaction == 2) { sdata_info(sdata, "SAE peer confirmed\n"); @@ -3688,7 +3694,8 @@ static void ieee80211_rx_mgmt_auth(struct ieee80211_sub_if_data *sdata,

cfg80211_rx_mlme_mgmt(sdata->dev, (u8 *)mgmt, len); notify_driver: - drv_mgd_complete_tx(sdata->local, sdata, &info); + if (!sae_need_confirm) + drv_mgd_complete_tx(sdata->local, sdata, &info); }

#define case_WLAN(type) \

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

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

From: Kuniyuki Iwashima kuniyu@google.com

[ Upstream commit dbd40f318cf2f59759bd170c401adc20ba360a3e ]

Since commit 63ed8de4be81 ("mld: add mc_lock for protecting per-interface mld data"), every multicast resource is protected by inet6_dev->mc_lock.

RTNL is unnecessary in terms of protection but still needed for synchronisation between addrconf_ifdown() and __ipv6_dev_mc_inc().

Once we removed RTNL, there would be a race below, where we could add a multicast address to a dead inet6_dev.

CPU1 CPU2 ==== ==== addrconf_ifdown() __ipv6_dev_mc_inc() if (idev->dead) <-- false dead = true return -ENODEV; ipv6_mc_destroy_dev() / ipv6_mc_down() mutex_lock(&idev->mc_lock) ... mutex_unlock(&idev->mc_lock) mutex_lock(&idev->mc_lock) ... mutex_unlock(&idev->mc_lock)

The race window can be easily closed by checking inet6_dev->dead under inet6_dev->mc_lock in __ipv6_dev_mc_inc() as addrconf_ifdown() will acquire it after marking inet6_dev dead.

Let's check inet6_dev->dead under mc_lock in __ipv6_dev_mc_inc().

Note that now __ipv6_dev_mc_inc() no longer depends on RTNL and we can remove ASSERT_RTNL() there and the RTNL comment above addrconf_join_solict().

Signed-off-by: Kuniyuki Iwashima kuniyu@google.com Reviewed-by: Eric Dumazet edumazet@google.com Link: https://patch.msgid.link/20250702230210.3115355-4-kuni1840@gmail.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- net/ipv6/addrconf.c | 7 +++---- net/ipv6/mcast.c | 11 +++++------ 2 files changed, 8 insertions(+), 10 deletions(-)

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 69915bb8b96d..cbdb510b40ea 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -2185,13 +2185,12 @@ void addrconf_dad_failure(struct sk_buff *skb, struct inet6_ifaddr *ifp) in6_ifa_put(ifp); }

-/* Join to solicited addr multicast group. - * caller must hold RTNL */ +/* Join to solicited addr multicast group. */ void addrconf_join_solict(struct net_device *dev, const struct in6_addr *addr) { struct in6_addr maddr;

- if (dev->flags&(IFF_LOOPBACK|IFF_NOARP)) + if (READ_ONCE(dev->flags) & (IFF_LOOPBACK | IFF_NOARP)) return;

addrconf_addr_solict_mult(addr, &maddr); @@ -3807,7 +3806,7 @@ static int addrconf_ifdown(struct net_device *dev, bool unregister) * Do not dev_put! */ if (unregister) { - idev->dead = 1; + WRITE_ONCE(idev->dead, 1);

/* protected by rtnl_lock */ RCU_INIT_POINTER(dev->ip6_ptr, NULL); diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index e9e59a83ba9b..e7f569875e71 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -906,23 +906,22 @@ static struct ifmcaddr6 *mca_alloc(struct inet6_dev *idev, static int __ipv6_dev_mc_inc(struct net_device *dev, const struct in6_addr *addr, unsigned int mode) { - struct ifmcaddr6 *mc; struct inet6_dev *idev; - - ASSERT_RTNL(); + struct ifmcaddr6 *mc;

/* we need to take a reference on idev */ idev = in6_dev_get(dev); - if (!idev) return -EINVAL;

- if (idev->dead) { + mutex_lock(&idev->mc_lock); + + if (READ_ONCE(idev->dead)) { + mutex_unlock(&idev->mc_lock); in6_dev_put(idev); return -ENODEV; }

- mutex_lock(&idev->mc_lock); for_each_mc_mclock(idev, mc) { if (ipv6_addr_equal(&mc->mca_addr, addr)) { mc->mca_users++;

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

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

From: Bitterblue Smith rtl8821cerfe2@gmail.com

[ Upstream commit e2b71603333a9dd73ee88347d8894fffc3456ac1 ]

Clear some bits in some registers in order to allow RTL8851BU to power on. This is done both when powering on and when powering off because that's what the vendor driver does.

Also tested with RTL8832BU and RTL8832CU.

Signed-off-by: Bitterblue Smith rtl8821cerfe2@gmail.com Acked-by: Ping-Ke Shih pkshih@realtek.com Signed-off-by: Ping-Ke Shih pkshih@realtek.com Link: https://patch.msgid.link/a39da939-d640-4486-ad38-f658f220afc8@gmail.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/wireless/realtek/rtw89/mac.c | 19 +++++++++++++++++++ drivers/net/wireless/realtek/rtw89/reg.h | 1 + 2 files changed, 20 insertions(+)

diff --git a/drivers/net/wireless/realtek/rtw89/mac.c b/drivers/net/wireless/realtek/rtw89/mac.c index 4a1c9e18c530..f15a2c6874cb 100644 --- a/drivers/net/wireless/realtek/rtw89/mac.c +++ b/drivers/net/wireless/realtek/rtw89/mac.c @@ -1093,6 +1093,23 @@ void rtw89_mac_notify_wake(struct rtw89_dev *rtwdev) rtw89_mac_send_rpwm(rtwdev, state, true); }

+static void rtw89_mac_power_switch_boot_mode(struct rtw89_dev *rtwdev) +{ + u32 boot_mode; + + if (rtwdev->hci.type != RTW89_HCI_TYPE_USB) + return; + + boot_mode = rtw89_read32_mask(rtwdev, R_AX_GPIO_MUXCFG, B_AX_BOOT_MODE); + if (!boot_mode) + return; + + rtw89_write32_clr(rtwdev, R_AX_SYS_PW_CTRL, B_AX_APFN_ONMAC); + rtw89_write32_clr(rtwdev, R_AX_SYS_STATUS1, B_AX_AUTO_WLPON); + rtw89_write32_clr(rtwdev, R_AX_GPIO_MUXCFG, B_AX_BOOT_MODE); + rtw89_write32_clr(rtwdev, R_AX_RSV_CTRL, B_AX_R_DIS_PRST); +} + static int rtw89_mac_power_switch(struct rtw89_dev *rtwdev, bool on) { #define PWR_ACT 1 @@ -1102,6 +1119,8 @@ static int rtw89_mac_power_switch(struct rtw89_dev *rtwdev, bool on) int ret; u8 val;

+ rtw89_mac_power_switch_boot_mode(rtwdev); + if (on) { cfg_seq = chip->pwr_on_seq; cfg_func = chip->ops->pwr_on_func; diff --git a/drivers/net/wireless/realtek/rtw89/reg.h b/drivers/net/wireless/realtek/rtw89/reg.h index 0291aff94016..52dd24a6216d 100644 --- a/drivers/net/wireless/realtek/rtw89/reg.h +++ b/drivers/net/wireless/realtek/rtw89/reg.h @@ -157,6 +157,7 @@

#define R_AX_SYS_STATUS1 0x00F4 #define B_AX_SEL_0XC0_MASK GENMASK(17, 16) +#define B_AX_AUTO_WLPON BIT(10) #define B_AX_PAD_HCI_SEL_V2_MASK GENMASK(5, 3) #define MAC_AX_HCI_SEL_SDIO_UART 0 #define MAC_AX_HCI_SEL_MULTI_USB 1

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

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

From: Mark Brown broonie@kernel.org

[ Upstream commit 9e8ebfe677f9101bbfe1f75d548a5aec581e8213 ]

Since f916dd32a943 ("arm64/fpsimd: ptrace: Mandate SVE payload for streaming-mode state") we reject attempts to write to the streaming mode regset even if there is no register data supplied, causing the tests for setting vector lengths and setting SVE_VL_INHERIT in sve-ptrace to spuriously fail. Set the flag to avoid the issue, we still support not supplying register data.

Acked-by: Mark Rutland mark.rutland@arm.com Signed-off-by: Mark Brown broonie@kernel.org Link: https://lore.kernel.org/r/20250609-kselftest-arm64-ssve-fixups-v2-3-998fcfa6... Signed-off-by: Catalin Marinas catalin.marinas@arm.com Signed-off-by: Sasha Levin sashal@kernel.org --- tools/testing/selftests/arm64/fp/sve-ptrace.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/arm64/fp/sve-ptrace.c b/tools/testing/selftests/arm64/fp/sve-ptrace.c index 91dd31629ffe..9f5461cd5b8f 100644 --- a/tools/testing/selftests/arm64/fp/sve-ptrace.c +++ b/tools/testing/selftests/arm64/fp/sve-ptrace.c @@ -158,7 +158,7 @@ static void ptrace_set_get_inherit(pid_t child, const struct vec_type *type) memset(&sve, 0, sizeof(sve)); sve.size = sizeof(sve); sve.vl = sve_vl_from_vq(SVE_VQ_MIN); - sve.flags = SVE_PT_VL_INHERIT; + sve.flags = SVE_PT_VL_INHERIT | SVE_PT_REGS_SVE; ret = set_sve(child, type, &sve); if (ret != 0) { ksft_test_result_fail("Failed to set %s SVE_PT_VL_INHERIT\n", @@ -223,6 +223,7 @@ static void ptrace_set_get_vl(pid_t child, const struct vec_type *type, /* Set the VL by doing a set with no register payload */ memset(&sve, 0, sizeof(sve)); sve.size = sizeof(sve); + sve.flags = SVE_PT_REGS_SVE; sve.vl = vl; ret = set_sve(child, type, &sve); if (ret != 0) {

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

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

From: zhangjianrong zhangjianrong5@huawei.com

[ Upstream commit 8ec31cb17cd355cea25cdb8496d9b3fbf1321647 ]

According to the description of tb_xdomain_enable_paths(), the third parameter represents the transmit ring and the fifth parameter represents the receive ring. tb_xdomain_disable_paths() is the same case.

[Jakub] Mika says: it works now because both rings ->hop is the same

Acked-by: Mika Westerberg mika.westerberg@linux.intel.com Link: https://lore.kernel.org/20250625051149.GD2824380@black.fi.intel.com Signed-off-by: zhangjianrong zhangjianrong5@huawei.com Link: https://patch.msgid.link/20250628094920.656658-1-zhangjianrong5@huawei.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/thunderbolt.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/thunderbolt.c b/drivers/net/thunderbolt.c index 6b184f6b7273..ef13aa36e55e 100644 --- a/drivers/net/thunderbolt.c +++ b/drivers/net/thunderbolt.c @@ -386,9 +386,9 @@ static void tbnet_tear_down(struct tbnet *net, bool send_logout)

ret = tb_xdomain_disable_paths(net->xd, net->local_transmit_path, - net->rx_ring.ring->hop, + net->tx_ring.ring->hop, net->remote_transmit_path, - net->tx_ring.ring->hop); + net->rx_ring.ring->hop); if (ret) netdev_warn(net->dev, "failed to disable DMA paths\n");

@@ -637,9 +637,9 @@ static void tbnet_connected_work(struct work_struct *work) goto err_free_rx_buffers;

ret = tb_xdomain_enable_paths(net->xd, net->local_transmit_path, - net->rx_ring.ring->hop, + net->tx_ring.ring->hop, net->remote_transmit_path, - net->tx_ring.ring->hop); + net->rx_ring.ring->hop); if (ret) { netdev_err(net->dev, "failed to enable DMA paths\n"); goto err_free_tx_buffers;

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

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

From: Jonas Rebmann jre@pengutronix.de

[ 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.

Signed-off-by: Jonas Rebmann jre@pengutronix.de Reviewed-by: Wei Fang wei.fang@nxp.com Link: https://patch.msgid.link/20250626-fec_deactivate_coalescing-v2-1-0b217f2e80d... Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/freescale/fec_main.c | 34 +++++++++++------------ 1 file changed, 16 insertions(+), 18 deletions(-)

diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 4a513dba8f53..d10db5d6d226 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -2831,27 +2831,25 @@ 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);