From: Benedict Wong benedictwong@google.com

[ Upstream commit b0355dbbf13c0052931dd14c38c789efed64d3de ]

This change adds support for nested IPsec tunnels by ensuring that XFRM-I verifies existing policies before decapsulating a subsequent policies. Addtionally, this clears the secpath entries after policies are verified, ensuring that previous tunnels with no-longer-valid do not pollute subsequent policy checks.

This is necessary especially for nested tunnels, as the IP addresses, protocol and ports may all change, thus not matching the previous policies. In order to ensure that packets match the relevant inbound templates, the xfrm_policy_check should be done before handing off to the inner XFRM protocol to decrypt and decapsulate.

Notably, raw ESP/AH packets did not perform policy checks inherently, whereas all other encapsulated packets (UDP, TCP encapsulated) do policy checks after calling xfrm_input handling in the respective encapsulation layer.

Test: Verified with additional Android Kernel Unit tests Signed-off-by: Benedict Wong benedictwong@google.com Signed-off-by: Steffen Klassert steffen.klassert@secunet.com Signed-off-by: Sasha Levin sashal@kernel.org --- net/xfrm/xfrm_interface.c | 54 ++++++++++++++++++++++++++++++++++++--- net/xfrm/xfrm_policy.c | 3 +++ 2 files changed, 53 insertions(+), 4 deletions(-)

diff --git a/net/xfrm/xfrm_interface.c b/net/xfrm/xfrm_interface.c index da518b4ca84c6..e4f21a6924153 100644 --- a/net/xfrm/xfrm_interface.c +++ b/net/xfrm/xfrm_interface.c @@ -207,6 +207,52 @@ static void xfrmi_scrub_packet(struct sk_buff *skb, bool xnet) skb->mark = 0; }

+static int xfrmi_input(struct sk_buff *skb, int nexthdr, __be32 spi, + int encap_type, unsigned short family) +{ + struct sec_path *sp; + + sp = skb_sec_path(skb); + if (sp && (sp->len || sp->olen) && + !xfrm_policy_check(NULL, XFRM_POLICY_IN, skb, family)) + goto discard; + + XFRM_SPI_SKB_CB(skb)->family = family; + if (family == AF_INET) { + XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct iphdr, daddr); + XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = NULL; + } else { + XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct ipv6hdr, daddr); + XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6 = NULL; + } + + return xfrm_input(skb, nexthdr, spi, encap_type); +discard: + kfree_skb(skb); + return 0; +} + +static int xfrmi4_rcv(struct sk_buff *skb) +{ + return xfrmi_input(skb, ip_hdr(skb)->protocol, 0, 0, AF_INET); +} + +static int xfrmi6_rcv(struct sk_buff *skb) +{ + return xfrmi_input(skb, skb_network_header(skb)[IP6CB(skb)->nhoff], + 0, 0, AF_INET6); +} + +static int xfrmi4_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) +{ + return xfrmi_input(skb, nexthdr, spi, encap_type, AF_INET); +} + +static int xfrmi6_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) +{ + return xfrmi_input(skb, nexthdr, spi, encap_type, AF_INET6); +} + static int xfrmi_rcv_cb(struct sk_buff *skb, int err) { const struct xfrm_mode *inner_mode; @@ -780,8 +826,8 @@ static struct pernet_operations xfrmi_net_ops = { };

static struct xfrm6_protocol xfrmi_esp6_protocol __read_mostly = { - .handler = xfrm6_rcv, - .input_handler = xfrm_input, + .handler = xfrmi6_rcv, + .input_handler = xfrmi6_input, .cb_handler = xfrmi_rcv_cb, .err_handler = xfrmi6_err, .priority = 10, @@ -831,8 +877,8 @@ static struct xfrm6_tunnel xfrmi_ip6ip_handler __read_mostly = { #endif

static struct xfrm4_protocol xfrmi_esp4_protocol __read_mostly = { - .handler = xfrm4_rcv, - .input_handler = xfrm_input, + .handler = xfrmi4_rcv, + .input_handler = xfrmi4_input, .cb_handler = xfrmi_rcv_cb, .err_handler = xfrmi4_err, .priority = 10, diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 0d12bdf59d4cc..d15aa62887de0 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -3710,6 +3710,9 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, goto reject; }

+ if (if_id) + secpath_reset(skb); + xfrm_pols_put(pols, npols); return 1; }

From: Johan Jonker jbx6244@gmail.com

[ Upstream commit 80422339a75088322b4d3884bd12fa0fe5d11050 ]

The clocks in the Rockchip rk3288 DisplayPort node are included in the power-domain@RK3288_PD_VIO logic, but the power-domains property in the dp node is missing, so fix it.

Signed-off-by: Johan Jonker jbx6244@gmail.com Link: https://lore.kernel.org/r/dab85bfb-9f55-86a1-5cd5-7388c43e0ec5@gmail.com Signed-off-by: Heiko Stuebner heiko@sntech.de Signed-off-by: Sasha Levin sashal@kernel.org --- arch/arm/boot/dts/rk3288.dtsi | 1 + 1 file changed, 1 insertion(+)

diff --git a/arch/arm/boot/dts/rk3288.dtsi b/arch/arm/boot/dts/rk3288.dtsi index 9051fb4a267d4..aab28161b9ae9 100644 --- a/arch/arm/boot/dts/rk3288.dtsi +++ b/arch/arm/boot/dts/rk3288.dtsi @@ -1203,6 +1203,7 @@ edp: dp@ff970000 { clock-names = "dp", "pclk"; phys = <&edp_phy>; phy-names = "dp"; + power-domains = <&power RK3288_PD_VIO>; resets = <&cru SRST_EDP>; reset-names = "dp"; rockchip,grf = <&grf>;

From: David Sterba dsterba@suse.com

[ Upstream commit 33e17b3f5ab74af12aca58c515bc8424ff69a343 ]

The arg->clone_sources_count is u64 and can trigger a warning when a huge value is passed from user space and a huge array is allocated. Limit the allocated memory to 8MiB (can be increased if needed), which in turn limits the number of clone sources to 8M / sizeof(struct clone_root) = 8M / 40 = 209715. Real world number of clones is from tens to hundreds, so this is future proof.

Reported-by: syzbot+4376a9a073770c173269@syzkaller.appspotmail.com Signed-off-by: David Sterba dsterba@suse.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/btrfs/send.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index 4a6ba0997e399..b081b61e97c8d 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -7276,10 +7276,10 @@ long btrfs_ioctl_send(struct file *mnt_file, struct btrfs_ioctl_send_args *arg) /* * Check that we don't overflow at later allocations, we request * clone_sources_count + 1 items, and compare to unsigned long inside - * access_ok. + * access_ok. Also set an upper limit for allocation size so this can't + * easily exhaust memory. Max number of clone sources is about 200K. */ - if (arg->clone_sources_count > - ULONG_MAX / sizeof(struct clone_root) - 1) { + if (arg->clone_sources_count > SZ_8M / sizeof(struct clone_root)) { ret = -EINVAL; goto out; }

From: Julian Anastasov ja@ssi.bg

[ Upstream commit c1d2ecdf5e38e3489ce8328238b558b3b2866fe1 ]

Entries can linger in cache without timer for days, thanks to the gc_thresh1 limit. As result, without traffic, the confirmed time can be outdated and to appear to be in the future. Later, on traffic, NUD_STALE entries can switch to NUD_DELAY and start the timer which can see the invalid confirmed time and wrongly switch to NUD_REACHABLE state instead of NUD_PROBE. As result, timer is set many days in the future. This is more visible on 32-bit platforms, with higher HZ value.

Why this is a problem? While we expect unused entries to expire, such entries stay in REACHABLE state for too long, locked in cache. They are not expired normally, only when cache is full.

Problem and the wrong state change reported by Zhang Changzhong:

172.16.1.18 dev bond0 lladdr 0a:0e:0f:01:12:01 ref 1 used 350521/15994171/350520 probes 4 REACHABLE

350520 seconds have elapsed since this entry was last updated, but it is still in the REACHABLE state (base_reachable_time_ms is 30000), preventing lladdr from being updated through probe.

Fix it by ensuring timer is started with valid used/confirmed times. Considering the valid time range is LONG_MAX jiffies, we try not to go too much in the past while we are in DELAY/PROBE state. There are also places that need used/updated times to be validated while timer is not running.

Reported-by: Zhang Changzhong zhangchangzhong@huawei.com Signed-off-by: Julian Anastasov ja@ssi.bg Tested-by: Zhang Changzhong zhangchangzhong@huawei.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/core/neighbour.c | 18 +++++++++++++++--- 1 file changed, 15 insertions(+), 3 deletions(-)

diff --git a/net/core/neighbour.c b/net/core/neighbour.c index f6f580e9d2820..82ccc3eebe71d 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -242,7 +242,7 @@ static int neigh_forced_gc(struct neigh_table *tbl) (n->nud_state == NUD_NOARP) || (tbl->is_multicast && tbl->is_multicast(n->primary_key)) || - time_after(tref, n->updated)) + !time_in_range(n->updated, tref, jiffies)) remove = true; write_unlock(&n->lock);

@@ -262,7 +262,17 @@ static int neigh_forced_gc(struct neigh_table *tbl)

static void neigh_add_timer(struct neighbour *n, unsigned long when) { + /* Use safe distance from the jiffies - LONG_MAX point while timer + * is running in DELAY/PROBE state but still show to user space + * large times in the past. + */ + unsigned long mint = jiffies - (LONG_MAX - 86400 * HZ); + neigh_hold(n); + if (!time_in_range(n->confirmed, mint, jiffies)) + n->confirmed = mint; + if (time_before(n->used, n->confirmed)) + n->used = n->confirmed; if (unlikely(mod_timer(&n->timer, when))) { printk("NEIGH: BUG, double timer add, state is %x\n", n->nud_state); @@ -948,12 +958,14 @@ static void neigh_periodic_work(struct work_struct *work) goto next_elt; }

- if (time_before(n->used, n->confirmed)) + if (time_before(n->used, n->confirmed) && + time_is_before_eq_jiffies(n->confirmed)) n->used = n->confirmed;

if (refcount_read(&n->refcnt) == 1 && (state == NUD_FAILED || - time_after(jiffies, n->used + NEIGH_VAR(n->parms, GC_STALETIME)))) { + !time_in_range_open(jiffies, n->used, + n->used + NEIGH_VAR(n->parms, GC_STALETIME)))) { *np = n->next; neigh_mark_dead(n); write_unlock(&n->lock);

From: Martin KaFai Lau martin.lau@kernel.org

commit 1fe4850b34ab512ff911e2c035c75fb6438f7307 upstream.

The bpf_fib_lookup() helper does not only look up the fib (ie. route) but it also looks up the neigh. Before returning the neigh, the helper does not check for NUD_VALID. When a neigh state (neigh->nud_state) is in NUD_FAILED, its dmac (neigh->ha) could be all zeros. The helper still returns SUCCESS instead of NO_NEIGH in this case. Because of the SUCCESS return value, the bpf prog directly uses the returned dmac and ends up filling all zero in the eth header.

This patch checks for NUD_VALID and returns NO_NEIGH if the neigh is not valid.

Signed-off-by: Martin KaFai Lau martin.lau@kernel.org Signed-off-by: Daniel Borkmann daniel@iogearbox.net Link: https://lore.kernel.org/bpf/20230217004150.2980689-3-martin.lau@linux.dev Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/core/filter.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

--- a/net/core/filter.c +++ b/net/core/filter.c @@ -5401,7 +5401,7 @@ static int bpf_ipv4_fib_lookup(struct ne neigh = __ipv6_neigh_lookup_noref_stub(dev, dst); }

- if (!neigh) + if (!neigh || !(neigh->nud_state & NUD_VALID)) return BPF_FIB_LKUP_RET_NO_NEIGH;

return bpf_fib_set_fwd_params(params, neigh, dev); @@ -5514,7 +5514,7 @@ static int bpf_ipv6_fib_lookup(struct ne * not needed here. */ neigh = __ipv6_neigh_lookup_noref_stub(dev, dst); - if (!neigh) + if (!neigh || !(neigh->nud_state & NUD_VALID)) return BPF_FIB_LKUP_RET_NO_NEIGH;

return bpf_fib_set_fwd_params(params, neigh, dev);

From: Thomas Weißschuh linux@weissschuh.net

commit ae3419fbac845b4d3f3a9fae4cc80c68d82cdf6e upstream.

Commit 226fae124b2d ("vc_screen: move load of struct vc_data pointer in vcs_read() to avoid UAF") moved the call to vcs_vc() into the loop.

While doing this it also moved the unconditional assignment of

ret = -ENXIO;

This unconditional assignment was valid outside the loop but within it it clobbers the actual value of ret.

To avoid this only assign "ret = -ENXIO" when actually needed.

[ Also, the 'goto unlock_out" needs to be just a "break", so that it does the right thing when it exits on later iterations when partial success has happened - Linus ]

Reported-by: Storm Dragon stormdragon2976@gmail.com Link: https://lore.kernel.org/lkml/Y%2FKS6vdql2pIsCiI@hotmail.com/ Fixes: 226fae124b2d ("vc_screen: move load of struct vc_data pointer in vcs_read() to avoid UAF") Signed-off-by: Thomas Weißschuh linux@weissschuh.net Link: https://lore.kernel.org/lkml/64981d94-d00c-4b31-9063-43ad0a384bde@t-8ch.de/ Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/tty/vt/vc_screen.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-)

--- a/drivers/tty/vt/vc_screen.c +++ b/drivers/tty/vt/vc_screen.c @@ -403,10 +403,11 @@ vcs_read(struct file *file, char __user unsigned int this_round, skip = 0; int size;

- ret = -ENXIO; vc = vcs_vc(inode, &viewed); - if (!vc) - goto unlock_out; + if (!vc) { + ret = -ENXIO; + break; + }

/* Check whether we are above size each round, * as copy_to_user at the end of this loop

From: Cristian Ciocaltea cristian.ciocaltea@collabora.com

commit 7394d2ebb651a9f62e08c6ab864aac015d27c64d upstream.

When COMPILED_SOURCE is set, running

make ARCH=x86_64 COMPILED_SOURCE=1 cscope tags

could throw the following errors:

scripts/tags.sh: line 98: /usr/bin/realpath: Argument list too long cscope: no source files found scripts/tags.sh: line 98: /usr/bin/realpath: Argument list too long ctags: No files specified. Try "ctags --help".

This is most likely to happen when the kernel is configured to build a large number of modules, which has the consequence of passing too many arguments when calling 'realpath' in 'all_compiled_sources()'.

Let's improve this by invoking 'realpath' through 'xargs', which takes care of properly limiting the argument list.

Signed-off-by: Cristian Ciocaltea cristian.ciocaltea@collabora.com Link: https://lore.kernel.org/r/20220516234646.531208-1-cristian.ciocaltea@collabo... Cc: Carlos Llamas cmllamas@google.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- scripts/tags.sh | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-)

--- a/scripts/tags.sh +++ b/scripts/tags.sh @@ -95,10 +95,13 @@ all_sources()

all_compiled_sources() { - realpath -es $([ -z "$KBUILD_ABS_SRCTREE" ] && echo --relative-to=.) \ - include/generated/autoconf.h $(find $ignore -name "*.cmd" -exec \ - grep -Poh '(?(?=^source_.* \K).*|(?=^ \K\S).*(?= \))' {} + | - awk '!a[$0]++') | sort -u + { + echo include/generated/autoconf.h + find $ignore -name "*.cmd" -exec \ + grep -Poh '(?(?=^source_.* \K).*|(?=^ \K\S).*(?= \))' {} + | + awk '!a[$0]++' + } | xargs realpath -es $([ -z "$KBUILD_ABS_SRCTREE" ] && echo --relative-to=.) | + sort -u }

all_target_sources()

From: Miaoqian Lin linmq006@gmail.com

commit c24968734abfed81c8f93dc5f44a7b7a9aecadfa upstream.

Since drm_prime_pages_to_sg() function return error pointers. The drm_gem_shmem_get_sg_table() function returns error pointers too. Using IS_ERR() to check the return value to fix this.

Fixes: 2f2aa13724d5 ("drm/virtio: move virtio_gpu_mem_entry initialization to new function") Signed-off-by: Miaoqian Lin linmq006@gmail.com Link: http://patchwork.freedesktop.org/patch/msgid/20220602104223.54527-1-linmq006... Signed-off-by: Gerd Hoffmann kraxel@redhat.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Ovidiu Panait ovidiu.panait@windriver.com --- drivers/gpu/drm/virtio/virtgpu_object.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

--- a/drivers/gpu/drm/virtio/virtgpu_object.c +++ b/drivers/gpu/drm/virtio/virtgpu_object.c @@ -157,9 +157,9 @@ static int virtio_gpu_object_shmem_init( * since virtio_gpu doesn't support dma-buf import from other devices. */ shmem->pages = drm_gem_shmem_get_sg_table(&bo->base.base); - if (!shmem->pages) { + if (IS_ERR(shmem->pages)) { drm_gem_shmem_unpin(&bo->base.base); - return -EINVAL; + return PTR_ERR(shmem->pages); }

if (use_dma_api) {

From: Florian Zumbiehl florz@florz.de

commit 617c331d91077f896111044628c096802551dc66 upstream.

Add support for VW/Skoda "Carstick LTE"

D: Ver= 2.00 Cls=00(>ifc ) Sub=00 Prot=00 MxPS=64 #Cfgs= 1 P: Vendor=1c9e ProdID=7605 Rev=02.00 S: Manufacturer=USB Modem S: Product=USB Modem C: #Ifs= 4 Cfg#= 1 Atr=e0 MxPwr=500mA I: If#=0x0 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=(none) I: If#=0x1 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=(none) I: If#=0x2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=(none) I: If#=0x3 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=(none)

The stick has AT command interfaces on interfaces 1, 2, and 3, and does PPP on interface 3.

Signed-off-by: Florian Zumbiehl florz@florz.de Cc: stable@vger.kernel.org Signed-off-by: Johan Hovold johan@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/usb/serial/option.c | 4 ++++ 1 file changed, 4 insertions(+)

--- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -402,6 +402,8 @@ static void option_instat_callback(struc #define LONGCHEER_VENDOR_ID 0x1c9e

/* 4G Systems products */ +/* This one was sold as the VW and Skoda "Carstick LTE" */ +#define FOUR_G_SYSTEMS_PRODUCT_CARSTICK_LTE 0x7605 /* This is the 4G XS Stick W14 a.k.a. Mobilcom Debitel Surf-Stick * * It seems to contain a Qualcomm QSC6240/6290 chipset */ #define FOUR_G_SYSTEMS_PRODUCT_W14 0x9603 @@ -1976,6 +1978,8 @@ static const struct usb_device_id option .driver_info = RSVD(2) }, { USB_DEVICE(AIRPLUS_VENDOR_ID, AIRPLUS_PRODUCT_MCD650) }, { USB_DEVICE(TLAYTECH_VENDOR_ID, TLAYTECH_PRODUCT_TEU800) }, + { USB_DEVICE(LONGCHEER_VENDOR_ID, FOUR_G_SYSTEMS_PRODUCT_CARSTICK_LTE), + .driver_info = RSVD(0) }, { USB_DEVICE(LONGCHEER_VENDOR_ID, FOUR_G_SYSTEMS_PRODUCT_W14), .driver_info = NCTRL(0) | NCTRL(1) }, { USB_DEVICE(LONGCHEER_VENDOR_ID, FOUR_G_SYSTEMS_PRODUCT_W100),

From: Alan Stern stern@rowland.harvard.edu

commit 45bf39f8df7f05efb83b302c65ae3b9bc92b7065 upstream.

Ever since commit 83e83ecb79a8 ("usb: core: get config and string descriptors for unauthorized devices") was merged in 2013, there has been no mechanism for reallocating the rawdescriptors buffers in struct usb_device after the initial enumeration. Before that commit, the buffers would be deallocated when a device was deauthorized and reallocated when it was authorized and enumerated.

This means that the locking in the read_descriptors() routine is not needed, since the buffers it reads will never be reallocated while the routine is running. This locking can interfere with user programs trying to read a hub's descriptors via sysfs while new child devices of the hub are being initialized, since the hub is locked during this procedure.

Since the locking in read_descriptors() hasn't been needed for over nine years, we can remove it.

Reported-and-tested-by: Troels Liebe Bentsen troels@connectedcars.dk Signed-off-by: Alan Stern stern@rowland.harvard.edu CC: stable@vger.kernel.org Link: https://lore.kernel.org/r/Y9l+wDTRbuZABzsE@rowland.harvard.edu Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/usb/core/hub.c | 5 ++--- drivers/usb/core/sysfs.c | 5 ----- 2 files changed, 2 insertions(+), 8 deletions(-)

--- a/drivers/usb/core/hub.c +++ b/drivers/usb/core/hub.c @@ -2380,9 +2380,8 @@ static int usb_enumerate_device_otg(stru * usb_enumerate_device - Read device configs/intfs/otg (usbcore-internal) * @udev: newly addressed device (in ADDRESS state) * - * This is only called by usb_new_device() and usb_authorize_device() - * and FIXME -- all comments that apply to them apply here wrt to - * environment. + * This is only called by usb_new_device() -- all comments that apply there + * apply here wrt to environment. * * If the device is WUSB and not authorized, we don't attempt to read * the string descriptors, as they will be errored out by the device --- a/drivers/usb/core/sysfs.c +++ b/drivers/usb/core/sysfs.c @@ -889,11 +889,7 @@ read_descriptors(struct file *filp, stru size_t srclen, n; int cfgno; void *src; - int retval;

- retval = usb_lock_device_interruptible(udev); - if (retval < 0) - return -EINTR; /* The binary attribute begins with the device descriptor. * Following that are the raw descriptor entries for all the * configurations (config plus subsidiary descriptors). @@ -918,7 +914,6 @@ read_descriptors(struct file *filp, stru off -= srclen; } } - usb_unlock_device(udev); return count - nleft; }