From: Sasha Levin sashal@kernel.org

In a few months, SUBLEVEL will overflow, and some userspace may start treating 4.19.256 as 4.20. While out of tree modules have different ways of extracting the version number (and we're generally ok with breaking them), we do care about breaking userspace and it would appear that this overflow might do just that.

Our rules around userspace ABI in the stable kernel are pretty simple: we don't break it. Thus, while userspace may be checking major/minor, it shouldn't be doing anything with sublevel.

This patch applies a big band-aid to the 4.19 kernel in the form of clamping the sublevel to 255.

The clamp is done for the purpose of LINUX_VERSION_CODE only, and extracting the version number from the Makefile or "make kernelversion" will continue to work as intended.

We might need to do it later in newer trees, but maybe we'll have a better solution by then, so I'm ignoring that problem for now.

Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/Makefile +++ b/Makefile @@ -1158,7 +1158,7 @@ endef

define filechk_version.h (echo #define LINUX_VERSION_CODE $(shell \ - expr $(VERSION) * 65536 + 0$(PATCHLEVEL) * 256 + 0$(SUBLEVEL)); \ + expr $(VERSION) * 65536 + 0$(PATCHLEVEL) * 256 + 255); \ echo '#define KERNEL_VERSION(a,b,c) (((a) << 16) + ((b) << 8) + (c))';) endef

From: Philip Chen philipchen@chromium.org

[ Upstream commit cd92cc187c053ab010a1570e2d61d68394a5c725 ]

If "data_lanes" property of the dsi output endpoint is missing in the DT, num_data_lanes would be 0 by default, which could cause dsi_host_attach() to fail if dsi->lanes is set to a non-zero value by the bridge driver.

According to the binding document of msm dsi controller, the input/output endpoint of the controller is expected to have 4 lanes. So let's set num_data_lanes to 4 by default.

Signed-off-by: Philip Chen philipchen@chromium.org Reviewed-by: Douglas Anderson dianders@chromium.org Reviewed-by: Stephen Boyd swboyd@chromium.org Link: https://lore.kernel.org/r/20211030100812.1.I6cd9af36b723fed277d34539d3b2ba4c... Signed-off-by: Rob Clark robdclark@chromium.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpu/drm/msm/dsi/dsi_host.c | 2 ++ 1 file changed, 2 insertions(+)

diff --git a/drivers/gpu/drm/msm/dsi/dsi_host.c b/drivers/gpu/drm/msm/dsi/dsi_host.c index 77dae147caf90..9abfb19ea7ede 100644 --- a/drivers/gpu/drm/msm/dsi/dsi_host.c +++ b/drivers/gpu/drm/msm/dsi/dsi_host.c @@ -1677,6 +1677,8 @@ static int dsi_host_parse_lane_data(struct msm_dsi_host *msm_host, if (!prop) { dev_dbg(dev, "failed to find data lane mapping, using default\n"); + /* Set the number of date lanes to 4 by default. */ + msm_host->num_data_lanes = 4; return 0; }

From: Helge Deller deller@gmx.de

[ Upstream commit 8d88382b7436551a9ebb78475c546b670790cbf6 ]

Signed-off-by: Helge Deller deller@gmx.de Reported-by: kernel test robot lkp@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/char/agp/parisc-agp.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/char/agp/parisc-agp.c b/drivers/char/agp/parisc-agp.c index 15f2e7025b78e..1d5510cb6db4e 100644 --- a/drivers/char/agp/parisc-agp.c +++ b/drivers/char/agp/parisc-agp.c @@ -285,7 +285,7 @@ agp_ioc_init(void __iomem *ioc_regs) return 0; }

-static int +static int __init lba_find_capability(int cap) { struct _parisc_agp_info *info = &parisc_agp_info; @@ -370,7 +370,7 @@ parisc_agp_setup(void __iomem *ioc_hpa, void __iomem *lba_hpa) return error; }

-static int +static int __init find_quicksilver(struct device *dev, void *data) { struct parisc_device **lba = data; @@ -382,7 +382,7 @@ find_quicksilver(struct device *dev, void *data) return 0; }

-static int +static int __init parisc_agp_init(void) { extern struct sba_device *sba_list;

From: Harshit Mogalapalli harshit.m.mogalapalli@oracle.com

[ Upstream commit f123cffdd8fe8ea6c7fded4b88516a42798797d0 ]

Adding a check on len parameter to avoid empty skb. This prevents a division error in netem_enqueue function which is caused when skb->len=0 and skb->data_len=0 in the randomized corruption step as shown below.

skb->data[prandom_u32() % skb_headlen(skb)] ^= 1<<(prandom_u32() % 8);

Crash Report: [ 343.170349] netdevsim netdevsim0 netdevsim3: set [1, 0] type 2 family 0 port 6081 - 0 [ 343.216110] netem: version 1.3 [ 343.235841] divide error: 0000 [#1] PREEMPT SMP KASAN NOPTI [ 343.236680] CPU: 3 PID: 4288 Comm: reproducer Not tainted 5.16.0-rc1+ [ 343.237569] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.11.0-2.el7 04/01/2014 [ 343.238707] RIP: 0010:netem_enqueue+0x1590/0x33c0 [sch_netem] [ 343.239499] Code: 89 85 58 ff ff ff e8 5f 5d e9 d3 48 8b b5 48 ff ff ff 8b 8d 50 ff ff ff 8b 85 58 ff ff ff 48 8b bd 70 ff ff ff 31 d2 2b 4f 74 <f7> f1 48 b8 00 00 00 00 00 fc ff df 49 01 d5 4c 89 e9 48 c1 e9 03 [ 343.241883] RSP: 0018:ffff88800bcd7368 EFLAGS: 00010246 [ 343.242589] RAX: 00000000ba7c0a9c RBX: 0000000000000001 RCX: 0000000000000000 [ 343.243542] RDX: 0000000000000000 RSI: ffff88800f8edb10 RDI: ffff88800f8eda40 [ 343.244474] RBP: ffff88800bcd7458 R08: 0000000000000000 R09: ffffffff94fb8445 [ 343.245403] R10: ffffffff94fb8336 R11: ffffffff94fb8445 R12: 0000000000000000 [ 343.246355] R13: ffff88800a5a7000 R14: ffff88800a5b5800 R15: 0000000000000020 [ 343.247291] FS: 00007fdde2bd7700(0000) GS:ffff888109780000(0000) knlGS:0000000000000000 [ 343.248350] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 343.249120] CR2: 00000000200000c0 CR3: 000000000ef4c000 CR4: 00000000000006e0 [ 343.250076] Call Trace: [ 343.250423] <TASK> [ 343.250713] ? memcpy+0x4d/0x60 [ 343.251162] ? netem_init+0xa0/0xa0 [sch_netem] [ 343.251795] ? __sanitizer_cov_trace_pc+0x21/0x60 [ 343.252443] netem_enqueue+0xe28/0x33c0 [sch_netem] [ 343.253102] ? stack_trace_save+0x87/0xb0 [ 343.253655] ? filter_irq_stacks+0xb0/0xb0 [ 343.254220] ? netem_init+0xa0/0xa0 [sch_netem] [ 343.254837] ? __kasan_check_write+0x14/0x20 [ 343.255418] ? _raw_spin_lock+0x88/0xd6 [ 343.255953] dev_qdisc_enqueue+0x50/0x180 [ 343.256508] __dev_queue_xmit+0x1a7e/0x3090 [ 343.257083] ? netdev_core_pick_tx+0x300/0x300 [ 343.257690] ? check_kcov_mode+0x10/0x40 [ 343.258219] ? _raw_spin_unlock_irqrestore+0x29/0x40 [ 343.258899] ? __kasan_init_slab_obj+0x24/0x30 [ 343.259529] ? setup_object.isra.71+0x23/0x90 [ 343.260121] ? new_slab+0x26e/0x4b0 [ 343.260609] ? kasan_poison+0x3a/0x50 [ 343.261118] ? kasan_unpoison+0x28/0x50 [ 343.261637] ? __kasan_slab_alloc+0x71/0x90 [ 343.262214] ? memcpy+0x4d/0x60 [ 343.262674] ? write_comp_data+0x2f/0x90 [ 343.263209] ? __kasan_check_write+0x14/0x20 [ 343.263802] ? __skb_clone+0x5d6/0x840 [ 343.264329] ? __sanitizer_cov_trace_pc+0x21/0x60 [ 343.264958] dev_queue_xmit+0x1c/0x20 [ 343.265470] netlink_deliver_tap+0x652/0x9c0 [ 343.266067] netlink_unicast+0x5a0/0x7f0 [ 343.266608] ? netlink_attachskb+0x860/0x860 [ 343.267183] ? __sanitizer_cov_trace_pc+0x21/0x60 [ 343.267820] ? write_comp_data+0x2f/0x90 [ 343.268367] netlink_sendmsg+0x922/0xe80 [ 343.268899] ? netlink_unicast+0x7f0/0x7f0 [ 343.269472] ? __sanitizer_cov_trace_pc+0x21/0x60 [ 343.270099] ? write_comp_data+0x2f/0x90 [ 343.270644] ? netlink_unicast+0x7f0/0x7f0 [ 343.271210] sock_sendmsg+0x155/0x190 [ 343.271721] ____sys_sendmsg+0x75f/0x8f0 [ 343.272262] ? kernel_sendmsg+0x60/0x60 [ 343.272788] ? write_comp_data+0x2f/0x90 [ 343.273332] ? write_comp_data+0x2f/0x90 [ 343.273869] ___sys_sendmsg+0x10f/0x190 [ 343.274405] ? sendmsg_copy_msghdr+0x80/0x80 [ 343.274984] ? slab_post_alloc_hook+0x70/0x230 [ 343.275597] ? futex_wait_setup+0x240/0x240 [ 343.276175] ? security_file_alloc+0x3e/0x170 [ 343.276779] ? write_comp_data+0x2f/0x90 [ 343.277313] ? __sanitizer_cov_trace_pc+0x21/0x60 [ 343.277969] ? write_comp_data+0x2f/0x90 [ 343.278515] ? __fget_files+0x1ad/0x260 [ 343.279048] ? __sanitizer_cov_trace_pc+0x21/0x60 [ 343.279685] ? write_comp_data+0x2f/0x90 [ 343.280234] ? __sanitizer_cov_trace_pc+0x21/0x60 [ 343.280874] ? sockfd_lookup_light+0xd1/0x190 [ 343.281481] __sys_sendmsg+0x118/0x200 [ 343.281998] ? __sys_sendmsg_sock+0x40/0x40 [ 343.282578] ? alloc_fd+0x229/0x5e0 [ 343.283070] ? write_comp_data+0x2f/0x90 [ 343.283610] ? write_comp_data+0x2f/0x90 [ 343.284135] ? __sanitizer_cov_trace_pc+0x21/0x60 [ 343.284776] ? ktime_get_coarse_real_ts64+0xb8/0xf0 [ 343.285450] __x64_sys_sendmsg+0x7d/0xc0 [ 343.285981] ? syscall_enter_from_user_mode+0x4d/0x70 [ 343.286664] do_syscall_64+0x3a/0x80 [ 343.287158] entry_SYSCALL_64_after_hwframe+0x44/0xae [ 343.287850] RIP: 0033:0x7fdde24cf289 [ 343.288344] Code: 01 00 48 81 c4 80 00 00 00 e9 f1 fe ff ff 0f 1f 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d b7 db 2c 00 f7 d8 64 89 01 48 [ 343.290729] RSP: 002b:00007fdde2bd6d98 EFLAGS: 00000246 ORIG_RAX: 000000000000002e [ 343.291730] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007fdde24cf289 [ 343.292673] RDX: 0000000000000000 RSI: 00000000200000c0 RDI: 0000000000000004 [ 343.293618] RBP: 00007fdde2bd6e20 R08: 0000000100000001 R09: 0000000000000000 [ 343.294557] R10: 0000000100000001 R11: 0000000000000246 R12: 0000000000000000 [ 343.295493] R13: 0000000000021000 R14: 0000000000000000 R15: 00007fdde2bd7700 [ 343.296432] </TASK> [ 343.296735] Modules linked in: sch_netem ip6_vti ip_vti ip_gre ipip sit ip_tunnel geneve macsec macvtap tap ipvlan macvlan 8021q garp mrp hsr wireguard libchacha20poly1305 chacha_x86_64 poly1305_x86_64 ip6_udp_tunnel udp_tunnel libblake2s blake2s_x86_64 libblake2s_generic curve25519_x86_64 libcurve25519_generic libchacha xfrm_interface xfrm6_tunnel tunnel4 veth netdevsim psample batman_adv nlmon dummy team bonding tls vcan ip6_gre ip6_tunnel tunnel6 gre tun ip6t_rpfilter ipt_REJECT nf_reject_ipv4 ip6t_REJECT nf_reject_ipv6 xt_conntrack ip_set ebtable_nat ebtable_broute ip6table_nat ip6table_mangle ip6table_security ip6table_raw iptable_nat nf_nat nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 iptable_mangle iptable_security iptable_raw ebtable_filter ebtables rfkill ip6table_filter ip6_tables iptable_filter ppdev bochs drm_vram_helper drm_ttm_helper ttm drm_kms_helper cec parport_pc drm joydev floppy parport sg syscopyarea sysfillrect sysimgblt i2c_piix4 qemu_fw_cfg fb_sys_fops pcspkr [ 343.297459] ip_tables xfs virtio_net net_failover failover sd_mod sr_mod cdrom t10_pi ata_generic pata_acpi ata_piix libata virtio_pci virtio_pci_legacy_dev serio_raw virtio_pci_modern_dev dm_mirror dm_region_hash dm_log dm_mod [ 343.311074] Dumping ftrace buffer: [ 343.311532] (ftrace buffer empty) [ 343.312040] ---[ end trace a2e3db5a6ae05099 ]--- [ 343.312691] RIP: 0010:netem_enqueue+0x1590/0x33c0 [sch_netem] [ 343.313481] Code: 89 85 58 ff ff ff e8 5f 5d e9 d3 48 8b b5 48 ff ff ff 8b 8d 50 ff ff ff 8b 85 58 ff ff ff 48 8b bd 70 ff ff ff 31 d2 2b 4f 74 <f7> f1 48 b8 00 00 00 00 00 fc ff df 49 01 d5 4c 89 e9 48 c1 e9 03 [ 343.315893] RSP: 0018:ffff88800bcd7368 EFLAGS: 00010246 [ 343.316622] RAX: 00000000ba7c0a9c RBX: 0000000000000001 RCX: 0000000000000000 [ 343.317585] RDX: 0000000000000000 RSI: ffff88800f8edb10 RDI: ffff88800f8eda40 [ 343.318549] RBP: ffff88800bcd7458 R08: 0000000000000000 R09: ffffffff94fb8445 [ 343.319503] R10: ffffffff94fb8336 R11: ffffffff94fb8445 R12: 0000000000000000 [ 343.320455] R13: ffff88800a5a7000 R14: ffff88800a5b5800 R15: 0000000000000020 [ 343.321414] FS: 00007fdde2bd7700(0000) GS:ffff888109780000(0000) knlGS:0000000000000000 [ 343.322489] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 343.323283] CR2: 00000000200000c0 CR3: 000000000ef4c000 CR4: 00000000000006e0 [ 343.324264] Kernel panic - not syncing: Fatal exception in interrupt [ 343.333717] Dumping ftrace buffer: [ 343.334175] (ftrace buffer empty) [ 343.334653] Kernel Offset: 0x13600000 from 0xffffffff81000000 (relocation range: 0xffffffff80000000-0xffffffffbfffffff) [ 343.336027] Rebooting in 86400 seconds..

Reported-by: syzkaller syzkaller@googlegroups.com Signed-off-by: Harshit Mogalapalli harshit.m.mogalapalli@oracle.com Link: https://lore.kernel.org/r/20211129175328.55339-1-harshit.m.mogalapalli@oracl... Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- net/netlink/af_netlink.c | 5 +++++ 1 file changed, 5 insertions(+)

diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index dd4e4289d0d2a..a7497361e4d78 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -1853,6 +1853,11 @@ static int netlink_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) if (msg->msg_flags&MSG_OOB) return -EOPNOTSUPP;

+ if (len == 0) { + pr_warn_once("Zero length message leads to an empty skb\n"); + return -ENODATA; + } + err = scm_send(sock, msg, &scm, true); if (err < 0) return err;

From: Armin Wolf W_Armin@gmx.de

commit dbd3e6eaf3d813939b28e8a66e29d81cdc836445 upstream.

The removal function is called regardless of whether /proc/i8k was created successfully or not, the later causing a WARN() on module removal. Fix that by only registering the removal function if /proc/i8k was created successfully.

Tested on a Inspiron 3505.

Fixes: 039ae58503f3 ("hwmon: Allow to compile dell-smm-hwmon driver without /proc/i8k") Signed-off-by: Armin Wolf W_Armin@gmx.de Acked-by: Pali Rohár pali@kernel.org Link: https://lore.kernel.org/r/20211112171440.59006-1-W_Armin@gmx.de Signed-off-by: Guenter Roeck linux@roeck-us.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/hwmon/dell-smm-hwmon.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-)

--- a/drivers/hwmon/dell-smm-hwmon.c +++ b/drivers/hwmon/dell-smm-hwmon.c @@ -591,15 +591,18 @@ static const struct file_operations i8k_ .unlocked_ioctl = i8k_ioctl, };

+static struct proc_dir_entry *entry; + static void __init i8k_init_procfs(void) { /* Register the proc entry */ - proc_create("i8k", 0, NULL, &i8k_fops); + entry = proc_create("i8k", 0, NULL, &i8k_fops); }

static void __exit i8k_exit_procfs(void) { - remove_proc_entry("i8k", NULL); + if (entry) + remove_proc_entry("i8k", NULL); }

#else

From: Jerome Marchand jmarchan@redhat.com

commit 85bf17b28f97ca2749968d8786dc423db320d9c2 upstream.

On s390, recordmcount.pl is looking for "bcrl 0,<xxx>" instructions in the objdump -d outpout. However since binutils 2.37, objdump -d display "jgnop <xxx>" for the same instruction. Update the mcount_regex so that it accepts both.

Signed-off-by: Jerome Marchand jmarchan@redhat.com Reviewed-by: Miroslav Benes mbenes@suse.cz Acked-by: Steven Rostedt (VMware) rostedt@goodmis.org Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20211210093827.1623286-1-jmarchan@redhat.com Signed-off-by: Heiko Carstens hca@linux.ibm.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- scripts/recordmcount.pl | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/scripts/recordmcount.pl +++ b/scripts/recordmcount.pl @@ -252,7 +252,7 @@ if ($arch eq "x86_64") {

} elsif ($arch eq "s390" && $bits == 64) { if ($cc =~ /-DCC_USING_HOTPATCH/) { - $mcount_regex = "^\s*([0-9a-fA-F]+):\s*c0 04 00 00 00 00\s*brcl\s*0,[0-9a-f]+ <([^+]*)>$"; + $mcount_regex = "^\s*([0-9a-fA-F]+):\s*c0 04 00 00 00 00\s*(bcrl\s*0,|jgnop\s*)[0-9a-f]+ <([^+]*)>$"; $mcount_adjust = 0; } else { $mcount_regex = "^\s*([0-9a-fA-F]+):\s*R_390_(PC|PLT)32DBL\s+_mcount\+0x2$";

From: Paul Moore paul@paul-moore.com

commit f4b3ee3c85551d2d343a3ba159304066523f730f upstream.

If the audit daemon were ever to get stuck in a stopped state the kernel's kauditd_thread() could get blocked attempting to send audit records to the userspace audit daemon. With the kernel thread blocked it is possible that the audit queue could grow unbounded as certain audit record generating events must be exempt from the queue limits else the system enter a deadlock state.

This patch resolves this problem by lowering the kernel thread's socket sending timeout from MAX_SCHEDULE_TIMEOUT to HZ/10 and tweaks the kauditd_send_queue() function to better manage the various audit queues when connection problems occur between the kernel and the audit daemon. With this patch, the backlog may temporarily grow beyond the defined limits when the audit daemon is stopped and the system is under heavy audit pressure, but kauditd_thread() will continue to make progress and drain the queues as it would for other connection problems. For example, with the audit daemon put into a stopped state and the system configured to audit every syscall it was still possible to shutdown the system without a kernel panic, deadlock, etc.; granted, the system was slow to shutdown but that is to be expected given the extreme pressure of recording every syscall.

The timeout value of HZ/10 was chosen primarily through experimentation and this developer's "gut feeling". There is likely no one perfect value, but as this scenario is limited in scope (root privileges would be needed to send SIGSTOP to the audit daemon), it is likely not worth exposing this as a tunable at present. This can always be done at a later date if it proves necessary.

Cc: stable@vger.kernel.org Fixes: 5b52330bbfe63 ("audit: fix auditd/kernel connection state tracking") Reported-by: Gaosheng Cui cuigaosheng1@huawei.com Tested-by: Gaosheng Cui cuigaosheng1@huawei.com Reviewed-by: Richard Guy Briggs rgb@redhat.com Signed-off-by: Paul Moore paul@paul-moore.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- kernel/audit.c | 21 ++++++++++----------- 1 file changed, 10 insertions(+), 11 deletions(-)

--- a/kernel/audit.c +++ b/kernel/audit.c @@ -726,7 +726,7 @@ static int kauditd_send_queue(struct soc { int rc = 0; struct sk_buff *skb; - static unsigned int failed = 0; + unsigned int failed = 0;

/* NOTE: kauditd_thread takes care of all our locking, we just use * the netlink info passed to us (e.g. sk and portid) */ @@ -743,32 +743,30 @@ static int kauditd_send_queue(struct soc continue; }

+retry: /* grab an extra skb reference in case of error */ skb_get(skb); rc = netlink_unicast(sk, skb, portid, 0); if (rc < 0) { - /* fatal failure for our queue flush attempt? */ + /* send failed - try a few times unless fatal error */ if (++failed >= retry_limit || rc == -ECONNREFUSED || rc == -EPERM) { - /* yes - error processing for the queue */ sk = NULL; if (err_hook) (*err_hook)(skb); - if (!skb_hook) - goto out; - /* keep processing with the skb_hook */ + if (rc == -EAGAIN) + rc = 0; + /* continue to drain the queue */ continue; } else - /* no - requeue to preserve ordering */ - skb_queue_head(queue, skb); + goto retry; } else { - /* it worked - drop the extra reference and continue */ + /* skb sent - drop the extra reference and continue */ consume_skb(skb); failed = 0; } }

-out: return (rc >= 0 ? 0 : rc); }

@@ -1557,7 +1555,8 @@ static int __net_init audit_net_init(str audit_panic("cannot initialize netlink socket in namespace"); return -ENOMEM; } - aunet->sk->sk_sndtimeo = MAX_SCHEDULE_TIMEOUT; + /* limit the timeout in case auditd is blocked/stopped */ + aunet->sk->sk_sndtimeo = HZ / 10;

return 0; }

From: Ard Biesheuvel ard.biesheuvel@linaro.org

commit ce9084ba0d1d8030adee7038ace32f8d9d423d0f upstream.

Turn ARCH_USE_MEMREMAP_PROT into a generic Kconfig symbol, and fix the dependency expression to reflect that AMD_MEM_ENCRYPT depends on it, instead of the other way around. This will permit ARCH_USE_MEMREMAP_PROT to be selected by other architectures.

Note that the encryption related early memremap routines in arch/x86/mm/ioremap.c cannot be built for 32-bit x86 without triggering the following warning:

arch/x86//mm/ioremap.c: In function 'early_memremap_encrypted':

...

arch/x86/include/asm/pgtable_types.h:193:27: warning: conversion from

'long long unsigned int' to 'long unsigned int' changes value from '9223372036854776163' to '355' [-Woverflow] #define __PAGE_KERNEL_ENC (__PAGE_KERNEL | _PAGE_ENC) ^~~~~~~~~~~~~~~~~~~~~~~~~~~ arch/x86//mm/ioremap.c:713:46: note: in expansion of macro '__PAGE_KERNEL_ENC' return early_memremap_prot(phys_addr, size, __PAGE_KERNEL_ENC);

which essentially means they are 64-bit only anyway. However, we cannot make them dependent on CONFIG_ARCH_HAS_MEM_ENCRYPT, since that is always defined, even for i386 (and changing that results in a slew of build errors)

So instead, build those routines only if CONFIG_AMD_MEM_ENCRYPT is defined.

Signed-off-by: Ard Biesheuvel ard.biesheuvel@linaro.org Cc: AKASHI Takahiro takahiro.akashi@linaro.org Cc: Alexander Graf agraf@suse.de Cc: Bjorn Andersson bjorn.andersson@linaro.org Cc: Borislav Petkov bp@alien8.de Cc: Heinrich Schuchardt xypron.glpk@gmx.de Cc: Jeffrey Hugo jhugo@codeaurora.org Cc: Lee Jones lee.jones@linaro.org Cc: Leif Lindholm leif.lindholm@linaro.org Cc: Linus Torvalds torvalds@linux-foundation.org Cc: Matt Fleming matt@codeblueprint.co.uk Cc: Peter Jones pjones@redhat.com Cc: Peter Zijlstra peterz@infradead.org Cc: Sai Praneeth Prakhya sai.praneeth.prakhya@intel.com Cc: Thomas Gleixner tglx@linutronix.de Cc: linux-efi@vger.kernel.org Link: http://lkml.kernel.org/r/20190202094119.13230-9-ard.biesheuvel@linaro.org Signed-off-by: Ingo Molnar mingo@kernel.org Cc: Tom Lendacky thomas.lendacky@amd.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/Kconfig | 3 +++ arch/x86/Kconfig | 5 +---- arch/x86/mm/ioremap.c | 4 ++-- 3 files changed, 6 insertions(+), 6 deletions(-)

--- a/arch/Kconfig +++ b/arch/Kconfig @@ -870,6 +870,9 @@ config HAVE_ARCH_PREL32_RELOCATIONS architectures, and don't require runtime relocation on relocatable kernels.

+config ARCH_USE_MEMREMAP_PROT + bool + source "kernel/gcov/Kconfig"

source "scripts/gcc-plugins/Kconfig" --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -1489,6 +1489,7 @@ config AMD_MEM_ENCRYPT bool "AMD Secure Memory Encryption (SME) support" depends on X86_64 && CPU_SUP_AMD select DYNAMIC_PHYSICAL_MASK + select ARCH_USE_MEMREMAP_PROT ---help--- Say yes to enable support for the encryption of system memory. This requires an AMD processor that supports Secure Memory @@ -1507,10 +1508,6 @@ config AMD_MEM_ENCRYPT_ACTIVE_BY_DEFAULT If set to N, then the encryption of system memory can be activated with the mem_encrypt=on command line option.

-config ARCH_USE_MEMREMAP_PROT - def_bool y - depends on AMD_MEM_ENCRYPT - # Common NUMA Features config NUMA bool "Numa Memory Allocation and Scheduler Support" --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -697,7 +697,7 @@ bool phys_mem_access_encrypted(unsigned return arch_memremap_can_ram_remap(phys_addr, size, 0); }

-#ifdef CONFIG_ARCH_USE_MEMREMAP_PROT +#ifdef CONFIG_AMD_MEM_ENCRYPT /* Remap memory with encryption */ void __init *early_memremap_encrypted(resource_size_t phys_addr, unsigned long size) @@ -739,7 +739,7 @@ void __init *early_memremap_decrypted_wp

return early_memremap_prot(phys_addr, size, __PAGE_KERNEL_NOENC_WP); } -#endif /* CONFIG_ARCH_USE_MEMREMAP_PROT */ +#endif /* CONFIG_AMD_MEM_ENCRYPT */

static pte_t bm_pte[PAGE_SIZE/sizeof(pte_t)] __page_aligned_bss;

From: Johannes Berg johannes.berg@intel.com

[ Upstream commit d5e568c3a4ec2ddd23e7dc5ad5b0c64e4f22981a ]

For admission control, obviously all of that only works for QoS data frames, otherwise we cannot even access the QoS field in the header.

Syzbot reported (see below) an uninitialized value here due to a status of a non-QoS nullfunc packet, which isn't even long enough to contain the QoS header.

Fix this to only do anything for QoS data packets.

Reported-by: syzbot+614e82b88a1a4973e534@syzkaller.appspotmail.com Fixes: 02219b3abca5 ("mac80211: add WMM admission control support") Link: https://lore.kernel.org/r/20211122124737.dad29e65902a.Ieb04587afacb27c14e0de... Signed-off-by: Johannes Berg johannes.berg@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- net/mac80211/mlme.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-)

diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index cbcb60face2c5..e5c4a72f8e571 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -2351,11 +2351,18 @@ static void ieee80211_sta_tx_wmm_ac_notify(struct ieee80211_sub_if_data *sdata, u16 tx_time) { struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; - u16 tid = ieee80211_get_tid(hdr); - int ac = ieee80211_ac_from_tid(tid); - struct ieee80211_sta_tx_tspec *tx_tspec = &ifmgd->tx_tspec[ac]; + u16 tid; + int ac; + struct ieee80211_sta_tx_tspec *tx_tspec; unsigned long now = jiffies;

+ if (!ieee80211_is_data_qos(hdr->frame_control)) + return; + + tid = ieee80211_get_tid(hdr); + ac = ieee80211_ac_from_tid(tid); + tx_tspec = &ifmgd->tx_tspec[ac]; + if (likely(!tx_tspec->admitted_time)) return;

From: Eric Dumazet edumazet@google.com

[ Upstream commit ab443c53916730862cec202078d36fd4008bea79 ]

qdiscs are not supposed to call their own destroy() method from init(), because core stack already does that.

syzbot was able to trigger use after free:

DEBUG_LOCKS_WARN_ON(lock->magic != lock) WARNING: CPU: 0 PID: 21902 at kernel/locking/mutex.c:586 __mutex_lock_common kernel/locking/mutex.c:586 [inline] WARNING: CPU: 0 PID: 21902 at kernel/locking/mutex.c:586 __mutex_lock+0x9ec/0x12f0 kernel/locking/mutex.c:740 Modules linked in: CPU: 0 PID: 21902 Comm: syz-executor189 Not tainted 5.16.0-rc4-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 RIP: 0010:__mutex_lock_common kernel/locking/mutex.c:586 [inline] RIP: 0010:__mutex_lock+0x9ec/0x12f0 kernel/locking/mutex.c:740 Code: 08 84 d2 0f 85 19 08 00 00 8b 05 97 38 4b 04 85 c0 0f 85 27 f7 ff ff 48 c7 c6 20 00 ac 89 48 c7 c7 a0 fe ab 89 e8 bf 76 ba ff <0f> 0b e9 0d f7 ff ff 48 8b 44 24 40 48 8d b8 c8 08 00 00 48 89 f8 RSP: 0018:ffffc9000627f290 EFLAGS: 00010282 RAX: 0000000000000000 RBX: 0000000000000000 RCX: 0000000000000000 RDX: ffff88802315d700 RSI: ffffffff815f1db8 RDI: fffff52000c4fe44 RBP: ffff88818f28e000 R08: 0000000000000000 R09: 0000000000000000 R10: ffffffff815ebb5e R11: 0000000000000000 R12: 0000000000000000 R13: dffffc0000000000 R14: ffffc9000627f458 R15: 0000000093c30000 FS: 0000555556abc400(0000) GS:ffff8880b9c00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007fda689c3303 CR3: 000000001cfbb000 CR4: 0000000000350ef0 Call Trace: <TASK> tcf_chain0_head_change_cb_del+0x2e/0x3d0 net/sched/cls_api.c:810 tcf_block_put_ext net/sched/cls_api.c:1381 [inline] tcf_block_put_ext net/sched/cls_api.c:1376 [inline] tcf_block_put+0xbc/0x130 net/sched/cls_api.c:1394 cake_destroy+0x3f/0x80 net/sched/sch_cake.c:2695 qdisc_create.constprop.0+0x9da/0x10f0 net/sched/sch_api.c:1293 tc_modify_qdisc+0x4c5/0x1980 net/sched/sch_api.c:1660 rtnetlink_rcv_msg+0x413/0xb80 net/core/rtnetlink.c:5571 netlink_rcv_skb+0x153/0x420 net/netlink/af_netlink.c:2496 netlink_unicast_kernel net/netlink/af_netlink.c:1319 [inline] netlink_unicast+0x533/0x7d0 net/netlink/af_netlink.c:1345 netlink_sendmsg+0x904/0xdf0 net/netlink/af_netlink.c:1921 sock_sendmsg_nosec net/socket.c:704 [inline] sock_sendmsg+0xcf/0x120 net/socket.c:724 ____sys_sendmsg+0x6e8/0x810 net/socket.c:2409 ___sys_sendmsg+0xf3/0x170 net/socket.c:2463 __sys_sendmsg+0xe5/0x1b0 net/socket.c:2492 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x35/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae RIP: 0033:0x7f1bb06badb9 Code: Unable to access opcode bytes at RIP 0x7f1bb06bad8f. RSP: 002b:00007fff3012a658 EFLAGS: 00000246 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 0000000000000003 RCX: 00007f1bb06badb9 RDX: 0000000000000000 RSI: 00000000200007c0 RDI: 0000000000000003 RBP: 0000000000000000 R08: 0000000000000003 R09: 0000000000000003 R10: 0000000000000003 R11: 0000000000000246 R12: 00007fff3012a688 R13: 00007fff3012a6a0 R14: 00007fff3012a6e0 R15: 00000000000013c2 </TASK>

Fixes: 046f6fd5daef ("sched: Add Common Applications Kept Enhanced (cake) qdisc") Signed-off-by: Eric Dumazet edumazet@google.com Reported-by: syzbot syzkaller@googlegroups.com Acked-by: Toke Høiland-Jørgensen toke@toke.dk Link: https://lore.kernel.org/r/20211210142046.698336-1-eric.dumazet@gmail.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- net/sched/sch_cake.c | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-)

diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c index 2025f0f559deb..18c207b85d513 100644 --- a/net/sched/sch_cake.c +++ b/net/sched/sch_cake.c @@ -2675,7 +2675,7 @@ static int cake_init(struct Qdisc *sch, struct nlattr *opt, q->tins = kvcalloc(CAKE_MAX_TINS, sizeof(struct cake_tin_data), GFP_KERNEL); if (!q->tins) - goto nomem; + return -ENOMEM;

for (i = 0; i < CAKE_MAX_TINS; i++) { struct cake_tin_data *b = q->tins + i; @@ -2705,10 +2705,6 @@ static int cake_init(struct Qdisc *sch, struct nlattr *opt, q->min_netlen = ~0; q->min_adjlen = ~0; return 0; - -nomem: - cake_destroy(sch); - return -ENOMEM; }

static int cake_dump(struct Qdisc *sch, struct sk_buff *skb)

From: Hangyu Hua hbh25y@gmail.com

[ Upstream commit 5f9562ebe710c307adc5f666bf1a2162ee7977c0 ]

__rds_conn_create() did not release conn->c_path when loop_trans != 0 and trans->t_prefer_loopback != 0 and is_outgoing == 0.

Fixes: aced3ce57cd3 ("RDS tcp loopback connection can hang") Signed-off-by: Hangyu Hua hbh25y@gmail.com Reviewed-by: Sharath Srinivasan sharath.srinivasan@oracle.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/rds/connection.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/net/rds/connection.c b/net/rds/connection.c index ac3300b204a6f..af9f7d1840037 100644 --- a/net/rds/connection.c +++ b/net/rds/connection.c @@ -250,6 +250,7 @@ static struct rds_connection *__rds_conn_create(struct net *net, * should end up here, but if it * does, reset/destroy the connection. */ + kfree(conn->c_path); kmem_cache_free(rds_conn_slab, conn); conn = ERR_PTR(-EOPNOTSUPP); goto out;

From: Karen Sornek karen.sornek@intel.com

[ Upstream commit 584af82154f56e6b2740160fcc84a2966d969e15 ]

Move checking condition of VF MAC filter before clearing or adding MAC filter to VF to prevent potential blackout caused by removal of necessary and working VF's MAC filter.

Fixes: 1b8b062a99dc ("igb: add VF trust infrastructure") Signed-off-by: Karen Sornek karen.sornek@intel.com Tested-by: Konrad Jankowski konrad0.jankowski@intel.com Signed-off-by: Tony Nguyen anthony.l.nguyen@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/intel/igb/igb_main.c | 28 +++++++++++------------ 1 file changed, 14 insertions(+), 14 deletions(-)

diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 6221dafc76b95..74b50f17832d1 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -7406,6 +7406,20 @@ static int igb_set_vf_mac_filter(struct igb_adapter *adapter, const int vf, struct vf_mac_filter *entry = NULL; int ret = 0;

+ if ((vf_data->flags & IGB_VF_FLAG_PF_SET_MAC) && + !vf_data->trusted) { + dev_warn(&pdev->dev, + "VF %d requested MAC filter but is administratively denied\n", + vf); + return -EINVAL; + } + if (!is_valid_ether_addr(addr)) { + dev_warn(&pdev->dev, + "VF %d attempted to set invalid MAC filter\n", + vf); + return -EINVAL; + } + switch (info) { case E1000_VF_MAC_FILTER_CLR: /* remove all unicast MAC filters related to the current VF */ @@ -7419,20 +7433,6 @@ static int igb_set_vf_mac_filter(struct igb_adapter *adapter, const int vf, } break; case E1000_VF_MAC_FILTER_ADD: - if ((vf_data->flags & IGB_VF_FLAG_PF_SET_MAC) && - !vf_data->trusted) { - dev_warn(&pdev->dev, - "VF %d requested MAC filter but is administratively denied\n", - vf); - return -EINVAL; - } - if (!is_valid_ether_addr(addr)) { - dev_warn(&pdev->dev, - "VF %d attempted to set invalid MAC filter\n", - vf); - return -EINVAL; - } - /* try to find empty slot in the list */ list_for_each(pos, &adapter->vf_macs.l) { entry = list_entry(pos, struct vf_mac_filter, l);

From: Cyril Novikov cnovikov@lynx.com

[ Upstream commit bf0a375055bd1afbbf02a0ef45f7655da7b71317 ]

The MDIO bus speed must be initialized before talking to the PHY the first time in order to avoid talking to it using a speed that the PHY doesn't support.

This fixes HW initialization error -17 (IXGBE_ERR_PHY_ADDR_INVALID) on Denverton CPUs (a.k.a. the Atom C3000 family) on ports with a 10Gb network plugged in. On those devices, HLREG0[MDCSPD] resets to 1, which combined with the 10Gb network results in a 24MHz MDIO speed, which is apparently too fast for the connected PHY. PHY register reads over MDIO bus return garbage, leading to initialization failure.

Reproduced with Linux kernel 4.19 and 5.15-rc7. Can be reproduced using the following setup:

* Use an Atom C3000 family system with at least one X552 LAN on the SoC * Disable PXE or other BIOS network initialization if possible (the interface must not be initialized before Linux boots) * Connect a live 10Gb Ethernet cable to an X550 port * Power cycle (not reset, doesn't always work) the system and boot Linux * Observe: ixgbe interfaces w/ 10GbE cables plugged in fail with error -17

Fixes: e84db7272798 ("ixgbe: Introduce function to control MDIO speed") Signed-off-by: Cyril Novikov cnovikov@lynx.com Reviewed-by: Andrew Lunn andrew@lunn.ch Signed-off-by: Tony Nguyen anthony.l.nguyen@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c | 3 +++ 1 file changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c index 9772016222c30..9277d57c4a70b 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c @@ -3391,6 +3391,9 @@ static s32 ixgbe_reset_hw_X550em(struct ixgbe_hw *hw) /* flush pending Tx transactions */ ixgbe_clear_tx_pending(hw);

+ /* set MDIO speed before talking to the PHY in case it's the 1st time */ + ixgbe_set_mdio_speed(hw); + /* PHY ops must be identified and initialized prior to reset */ status = hw->phy.ops.init(hw); if (status == IXGBE_ERR_SFP_NOT_SUPPORTED ||

From: Willem de Bruijn willemb@google.com

[ Upstream commit ec6af094ea28f0f2dda1a6a33b14cd57e36a9755 ]

Packet sockets may switch ring versions. Avoid misinterpreting state between versions, whose fields share a union. rx_owner_map is only allocated with a packet ring (pg_vec) and both are swapped together. If pg_vec is NULL, meaning no packet ring was allocated, then neither was rx_owner_map. And the field may be old state from a tpacket_v3.

Fixes: 61fad6816fc1 ("net/packet: tpacket_rcv: avoid a producer race condition") Reported-by: Syzbot syzbot+1ac0994a0a0c55151121@syzkaller.appspotmail.com Signed-off-by: Willem de Bruijn willemb@google.com Reviewed-by: Eric Dumazet edumazet@google.com Link: https://lore.kernel.org/r/20211215143937.106178-1-willemdebruijn.kernel@gmai... Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- net/packet/af_packet.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 8d9005019ef78..1309161032d50 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -4439,9 +4439,10 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, }

out_free_pg_vec: - bitmap_free(rx_owner_map); - if (pg_vec) + if (pg_vec) { + bitmap_free(rx_owner_map); free_pg_vec(pg_vec, order, req->tp_block_nr); + } out: return err; }

From: Greg Kroah-Hartman gregkh@linuxfoundation.org

[ Upstream commit f08adf5add9a071160c68bb2a61d697f39ab0758 ]

Szymon rightly pointed out that the previous check for the endpoint direction in bRequestType was not looking at only the bit involved, but rather the whole value. Normally this is ok, but for some request types, bits other than bit 8 could be set and the check for the endpoint length could not stall correctly.

Fix that up by only checking the single bit.

Fixes: 153a2d7e3350 ("USB: gadget: detect too-big endpoint 0 requests") Cc: Felipe Balbi balbi@kernel.org Reported-by: Szymon Heidrich szymon.heidrich@gmail.com Link: https://lore.kernel.org/r/20211214184621.385828-1-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/usb/gadget/composite.c | 6 +++--- drivers/usb/gadget/legacy/dbgp.c | 6 +++--- drivers/usb/gadget/legacy/inode.c | 6 +++--- 3 files changed, 9 insertions(+), 9 deletions(-)

diff --git a/drivers/usb/gadget/composite.c b/drivers/usb/gadget/composite.c index 99550c9eb33ed..748f8fede5c23 100644 --- a/drivers/usb/gadget/composite.c +++ b/drivers/usb/gadget/composite.c @@ -1635,14 +1635,14 @@ composite_setup(struct usb_gadget *gadget, const struct usb_ctrlrequest *ctrl) u8 endp;

if (w_length > USB_COMP_EP0_BUFSIZ) { - if (ctrl->bRequestType == USB_DIR_OUT) { - goto done; - } else { + if (ctrl->bRequestType & USB_DIR_IN) { /* Cast away the const, we are going to overwrite on purpose. */ __le16 *temp = (__le16 *)&ctrl->wLength;

*temp = cpu_to_le16(USB_COMP_EP0_BUFSIZ); w_length = USB_COMP_EP0_BUFSIZ; + } else { + goto done; } }

diff --git a/drivers/usb/gadget/legacy/dbgp.c b/drivers/usb/gadget/legacy/dbgp.c index 355bc7dab9d5f..6bcbad3825802 100644 --- a/drivers/usb/gadget/legacy/dbgp.c +++ b/drivers/usb/gadget/legacy/dbgp.c @@ -346,14 +346,14 @@ static int dbgp_setup(struct usb_gadget *gadget, u16 len = 0;

if (length > DBGP_REQ_LEN) { - if (ctrl->bRequestType == USB_DIR_OUT) { - return err; - } else { + if (ctrl->bRequestType & USB_DIR_IN) { /* Cast away the const, we are going to overwrite on purpose. */ __le16 *temp = (__le16 *)&ctrl->wLength;

*temp = cpu_to_le16(DBGP_REQ_LEN); length = DBGP_REQ_LEN; + } else { + return err; } }

diff --git a/drivers/usb/gadget/legacy/inode.c b/drivers/usb/gadget/legacy/inode.c index 848562222015d..a456267b6b784 100644 --- a/drivers/usb/gadget/legacy/inode.c +++ b/drivers/usb/gadget/legacy/inode.c @@ -1335,14 +1335,14 @@ gadgetfs_setup (struct usb_gadget *gadget, const struct usb_ctrlrequest *ctrl) u16 w_length = le16_to_cpu(ctrl->wLength);

if (w_length > RBUF_SIZE) { - if (ctrl->bRequestType == USB_DIR_OUT) { - return value; - } else { + if (ctrl->bRequestType & USB_DIR_IN) { /* Cast away the const, we are going to overwrite on purpose. */ __le16 *temp = (__le16 *)&ctrl->wLength;

*temp = cpu_to_le16(RBUF_SIZE); w_length = RBUF_SIZE; + } else { + return value; } }

From: Thomas Gleixner tglx@linutronix.de

commit 94185adbfad56815c2c8401e16d81bdb74a79201 upstream.

PCI_MSIX_FLAGS_MASKALL is set in the MSI-X control register at MSI-X interrupt setup time. It's cleared on success, but the error handling path only clears the PCI_MSIX_FLAGS_ENABLE bit.

That's incorrect as the reset state of the PCI_MSIX_FLAGS_MASKALL bit is zero. That can be observed via lspci:

Capabilities: [b0] MSI-X: Enable- Count=67 Masked+

Clear the bit in the error path to restore the reset state.

Fixes: 438553958ba1 ("PCI/MSI: Enable and mask MSI-X early") Reported-by: Stefan Roese sr@denx.de Signed-off-by: Thomas Gleixner tglx@linutronix.de Tested-by: Stefan Roese sr@denx.de Cc: linux-pci@vger.kernel.org Cc: Bjorn Helgaas bhelgaas@google.com Cc: Michal Simek michal.simek@xilinx.com Cc: Marek Vasut marex@denx.de Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/87tufevoqx.ffs@tglx Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/pci/msi.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/drivers/pci/msi.c +++ b/drivers/pci/msi.c @@ -850,7 +850,7 @@ out_free: free_msi_irqs(dev);

out_disable: - pci_msix_clear_and_set_ctrl(dev, PCI_MSIX_FLAGS_ENABLE, 0); + pci_msix_clear_and_set_ctrl(dev, PCI_MSIX_FLAGS_MASKALL | PCI_MSIX_FLAGS_ENABLE, 0);

return ret; }

From: Johan Hovold johan@kernel.org

commit 83b67041f3eaf33f98a075249aa7f4c7617c2f85 upstream.

When generalising GPIO support and adding support for CP2102N, the GPIO registration for some CP2105 devices accidentally broke. Specifically, when all the pins of a port are in "modem" mode, and thus unavailable for GPIO use, the GPIO chip would now be registered without having initialised the number of GPIO lines. This would in turn be rejected by gpiolib and some errors messages would be printed (but importantly probe would still succeed).

Fix this by initialising the number of GPIO lines before registering the GPIO chip.

Note that as for the other device types, and as when all CP2105 pins are muxed for LED function, the GPIO chip is registered also when no pins are available for GPIO use.

Reported-by: Maarten Brock m.brock@vanmierlo.com Link: https://lore.kernel.org/r/5eb560c81d2ea1a2b4602a92d9f48a89@vanmierlo.com Fixes: c8acfe0aadbe ("USB: serial: cp210x: implement GPIO support for CP2102N") Cc: stable@vger.kernel.org # 4.19 Cc: Karoly Pados pados@pados.hu Link: https://lore.kernel.org/r/20211126094348.31698-1-johan@kernel.org Reviewed-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Tested-by: Maarten Brock m.brock@vanmierlo.com Signed-off-by: Johan Hovold johan@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/usb/serial/cp210x.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-)

--- a/drivers/usb/serial/cp210x.c +++ b/drivers/usb/serial/cp210x.c @@ -1535,6 +1535,8 @@ static int cp2105_gpioconf_init(struct u

/* 2 banks of GPIO - One for the pins taken from each serial port */ if (intf_num == 0) { + priv->gc.ngpio = 2; + if (mode.eci == CP210X_PIN_MODE_MODEM) { /* mark all GPIOs of this interface as reserved */ priv->gpio_altfunc = 0xff; @@ -1545,8 +1547,9 @@ static int cp2105_gpioconf_init(struct u priv->gpio_pushpull = (u8)((le16_to_cpu(config.gpio_mode) & CP210X_ECI_GPIO_MODE_MASK) >> CP210X_ECI_GPIO_MODE_OFFSET); - priv->gc.ngpio = 2; } else if (intf_num == 1) { + priv->gc.ngpio = 3; + if (mode.sci == CP210X_PIN_MODE_MODEM) { /* mark all GPIOs of this interface as reserved */ priv->gpio_altfunc = 0xff; @@ -1557,7 +1560,6 @@ static int cp2105_gpioconf_init(struct u priv->gpio_pushpull = (u8)((le16_to_cpu(config.gpio_mode) & CP210X_SCI_GPIO_MODE_MASK) >> CP210X_SCI_GPIO_MODE_OFFSET); - priv->gc.ngpio = 3; } else { return -ENODEV; }

From: Yu Liao liaoyu15@huawei.com

commit 4e8c11b6b3f0b6a283e898344f154641eda94266 upstream.

Even after commit e1d7ba873555 ("time: Always make sure wall_to_monotonic isn't positive") it is still possible to make wall_to_monotonic positive by running the following code:

int main(void) { struct timespec time;

clock_gettime(CLOCK_MONOTONIC, &time); time.tv_nsec = 0; clock_settime(CLOCK_REALTIME, &time); return 0; }

The reason is that the second parameter of timespec64_compare(), ts_delta, may be unnormalized because the delta is calculated with an open coded substraction which causes the comparison of tv_sec to yield the wrong result:

wall_to_monotonic = { .tv_sec = -10, .tv_nsec = 900000000 } ts_delta = { .tv_sec = -9, .tv_nsec = -900000000 }

That makes timespec64_compare() claim that wall_to_monotonic < ts_delta, but actually the result should be wall_to_monotonic > ts_delta.

After normalization, the result of timespec64_compare() is correct because the tv_sec comparison is not longer misleading:

wall_to_monotonic = { .tv_sec = -10, .tv_nsec = 900000000 } ts_delta = { .tv_sec = -10, .tv_nsec = 100000000 }

Use timespec64_sub() to ensure that ts_delta is normalized, which fixes the issue.

Fixes: e1d7ba873555 ("time: Always make sure wall_to_monotonic isn't positive") Signed-off-by: Yu Liao liaoyu15@huawei.com Signed-off-by: Thomas Gleixner tglx@linutronix.de Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20211213135727.1656662-1-liaoyu15@huawei.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- kernel/time/timekeeping.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-)

--- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -1235,8 +1235,7 @@ int do_settimeofday64(const struct times timekeeping_forward_now(tk);

xt = tk_xtime(tk); - ts_delta.tv_sec = ts->tv_sec - xt.tv_sec; - ts_delta.tv_nsec = ts->tv_nsec - xt.tv_nsec; + ts_delta = timespec64_sub(*ts, xt);

if (timespec64_compare(&tk->wall_to_monotonic, &ts_delta) > 0) { ret = -EINVAL;

From: Le Ma le.ma@amd.com

commit f3a8076eb28cae1553958c629aecec479394bbe2 upstream.

should count on GC IP base address

Signed-off-by: Le Ma le.ma@amd.com Signed-off-by: Hawking Zhang Hawking.Zhang@amd.com Reviewed-by: Hawking Zhang Hawking.Zhang@amd.com Signed-off-by: Alex Deucher alexander.deucher@amd.com Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c @@ -2198,8 +2198,8 @@ static void gfx_v9_0_init_pg(struct amdg AMD_PG_SUPPORT_CP | AMD_PG_SUPPORT_GDS | AMD_PG_SUPPORT_RLC_SMU_HS)) { - WREG32(mmRLC_JUMP_TABLE_RESTORE, - adev->gfx.rlc.cp_table_gpu_addr >> 8); + WREG32_SOC15(GC, 0, mmRLC_JUMP_TABLE_RESTORE, + adev->gfx.rlc.cp_table_gpu_addr >> 8); gfx_v9_0_init_gfx_power_gating(adev); } }

From: Johannes Berg johannes.berg@intel.com

commit 768c0b19b50665e337c96858aa2b7928d6dcf756 upstream.

Before attempting to parse an extended element, verify that the extended element ID is present.

Fixes: 41cbb0f5a295 ("mac80211: add support for HE") Reported-by: syzbot+59bdff68edce82e393b6@syzkaller.appspotmail.com Link: https://lore.kernel.org/r/20211211201023.f30a1b128c07.I5cacc176da94ba316877c... Cc: stable@vger.kernel.org Signed-off-by: Johannes Berg johannes.berg@intel.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/mac80211/util.c | 2 ++ 1 file changed, 2 insertions(+)

--- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -1102,6 +1102,8 @@ u32 ieee802_11_parse_elems_crc(const u8 elems->max_idle_period_ie = (void *)pos; break; case WLAN_EID_EXTENSION: + if (!elen) + break; if (pos[0] == WLAN_EID_EXT_HE_MU_EDCA && elen >= (sizeof(*elems->mu_edca_param_set) + 1)) { elems->mu_edca_param_set = (void *)&pos[1];

From: Nicolas Pitre nicolas.pitre@linaro.org

commit b99afae1390140f5b0039e6b37a7380de31ae874 upstream.

The naked attribute is known to confuse some old gcc versions when function arguments aren't explicitly listed as inline assembly operands despite the gcc documentation. That resulted in commit 9a40ac86152c ("ARM: 6164/1: Add kto and kfrom to input operands list.").

Yet that commit has problems of its own by having assembly operand constraints completely wrong. If the generated code has been OK since then, it is due to luck rather than correctness. So this patch also provides proper assembly operand constraints, and removes two instances of redundant register usages in the implementation while at it.

Inspection of the generated code with this patch doesn't show any obvious quality degradation either, so not relying on __naked at all will make the code less fragile, and avoid some issues with clang.

The only remaining __naked instances (excluding the kprobes test cases) are exynos_pm_power_up_setup(), tc2_pm_power_up_setup() and

cci_enable_port_for_self(. But in the first two cases, only the function address is used by the compiler with no chance of inlining it by mistake, and the third case is called from assembly code only. And the fact that no stack is available when the corresponding code is executed does warrant the __naked usage in those cases.

Signed-off-by: Nicolas Pitre nico@linaro.org Reviewed-by: Stefan Agner stefan@agner.ch Tested-by: Stefan Agner stefan@agner.ch Signed-off-by: Russell King rmk+kernel@armlinux.org.uk Signed-off-by: Anders Roxell anders.roxell@linaro.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/arm/mm/copypage-fa.c | 35 ++++++-------- arch/arm/mm/copypage-feroceon.c | 98 +++++++++++++++++++--------------------- arch/arm/mm/copypage-v4mc.c | 19 +++---- arch/arm/mm/copypage-v4wb.c | 41 ++++++++-------- arch/arm/mm/copypage-v4wt.c | 37 +++++++-------- arch/arm/mm/copypage-xsc3.c | 71 ++++++++++++---------------- arch/arm/mm/copypage-xscale.c | 71 ++++++++++++++-------------- 7 files changed, 178 insertions(+), 194 deletions(-)

--- a/arch/arm/mm/copypage-fa.c +++ b/arch/arm/mm/copypage-fa.c @@ -17,26 +17,25 @@ /* * Faraday optimised copy_user_page */ -static void __naked -fa_copy_user_page(void *kto, const void *kfrom) +static void fa_copy_user_page(void *kto, const void *kfrom) { - asm("\ - stmfd sp!, {r4, lr} @ 2\n\ - mov r2, %0 @ 1\n\ -1: ldmia r1!, {r3, r4, ip, lr} @ 4\n\ - stmia r0, {r3, r4, ip, lr} @ 4\n\ - mcr p15, 0, r0, c7, c14, 1 @ 1 clean and invalidate D line\n\ - add r0, r0, #16 @ 1\n\ - ldmia r1!, {r3, r4, ip, lr} @ 4\n\ - stmia r0, {r3, r4, ip, lr} @ 4\n\ - mcr p15, 0, r0, c7, c14, 1 @ 1 clean and invalidate D line\n\ - add r0, r0, #16 @ 1\n\ - subs r2, r2, #1 @ 1\n\ + int tmp; + + asm volatile ("\ +1: ldmia %1!, {r3, r4, ip, lr} @ 4\n\ + stmia %0, {r3, r4, ip, lr} @ 4\n\ + mcr p15, 0, %0, c7, c14, 1 @ 1 clean and invalidate D line\n\ + add %0, %0, #16 @ 1\n\ + ldmia %1!, {r3, r4, ip, lr} @ 4\n\ + stmia %0, {r3, r4, ip, lr} @ 4\n\ + mcr p15, 0, %0, c7, c14, 1 @ 1 clean and invalidate D line\n\ + add %0, %0, #16 @ 1\n\ + subs %2, %2, #1 @ 1\n\ bne 1b @ 1\n\ - mcr p15, 0, r2, c7, c10, 4 @ 1 drain WB\n\ - ldmfd sp!, {r4, pc} @ 3" - : - : "I" (PAGE_SIZE / 32)); + mcr p15, 0, %2, c7, c10, 4 @ 1 drain WB" + : "+&r" (kto), "+&r" (kfrom), "=&r" (tmp) + : "2" (PAGE_SIZE / 32) + : "r3", "r4", "ip", "lr"); }

void fa_copy_user_highpage(struct page *to, struct page *from, --- a/arch/arm/mm/copypage-feroceon.c +++ b/arch/arm/mm/copypage-feroceon.c @@ -13,58 +13,56 @@ #include <linux/init.h> #include <linux/highmem.h>

-static void __naked -feroceon_copy_user_page(void *kto, const void *kfrom) +static void feroceon_copy_user_page(void *kto, const void *kfrom) { - asm("\ - stmfd sp!, {r4-r9, lr} \n\ - mov ip, %2 \n\ -1: mov lr, r1 \n\ - ldmia r1!, {r2 - r9} \n\ - pld [lr, #32] \n\ - pld [lr, #64] \n\ - pld [lr, #96] \n\ - pld [lr, #128] \n\ - pld [lr, #160] \n\ - pld [lr, #192] \n\ - pld [lr, #224] \n\ - stmia r0, {r2 - r9} \n\ - ldmia r1!, {r2 - r9} \n\ - mcr p15, 0, r0, c7, c14, 1 @ clean and invalidate D line\n\ - add r0, r0, #32 \n\ - stmia r0, {r2 - r9} \n\ - ldmia r1!, {r2 - r9} \n\ - mcr p15, 0, r0, c7, c14, 1 @ clean and invalidate D line\n\ - add r0, r0, #32 \n\ - stmia r0, {r2 - r9} \n\ - ldmia r1!, {r2 - r9} \n\ - mcr p15, 0, r0, c7, c14, 1 @ clean and invalidate D line\n\ - add r0, r0, #32 \n\ - stmia r0, {r2 - r9} \n\ - ldmia r1!, {r2 - r9} \n\ - mcr p15, 0, r0, c7, c14, 1 @ clean and invalidate D line\n\ - add r0, r0, #32 \n\ - stmia r0, {r2 - r9} \n\ - ldmia r1!, {r2 - r9} \n\ - mcr p15, 0, r0, c7, c14, 1 @ clean and invalidate D line\n\ - add r0, r0, #32 \n\ - stmia r0, {r2 - r9} \n\ - ldmia r1!, {r2 - r9} \n\ - mcr p15, 0, r0, c7, c14, 1 @ clean and invalidate D line\n\ - add r0, r0, #32 \n\ - stmia r0, {r2 - r9} \n\ - ldmia r1!, {r2 - r9} \n\ - mcr p15, 0, r0, c7, c14, 1 @ clean and invalidate D line\n\ - add r0, r0, #32 \n\ - stmia r0, {r2 - r9} \n\ - subs ip, ip, #(32 * 8) \n\ - mcr p15, 0, r0, c7, c14, 1 @ clean and invalidate D line\n\ - add r0, r0, #32 \n\ + int tmp; + + asm volatile ("\ +1: ldmia %1!, {r2 - r7, ip, lr} \n\ + pld [%1, #0] \n\ + pld [%1, #32] \n\ + pld [%1, #64] \n\ + pld [%1, #96] \n\ + pld [%1, #128] \n\ + pld [%1, #160] \n\ + pld [%1, #192] \n\ + stmia %0, {r2 - r7, ip, lr} \n\ + ldmia %1!, {r2 - r7, ip, lr} \n\ + mcr p15, 0, %0, c7, c14, 1 @ clean and invalidate D line\n\ + add %0, %0, #32 \n\ + stmia %0, {r2 - r7, ip, lr} \n\ + ldmia %1!, {r2 - r7, ip, lr} \n\ + mcr p15, 0, %0, c7, c14, 1 @ clean and invalidate D line\n\ + add %0, %0, #32 \n\ + stmia %0, {r2 - r7, ip, lr} \n\ + ldmia %1!, {r2 - r7, ip, lr} \n\ + mcr p15, 0, %0, c7, c14, 1 @ clean and invalidate D line\n\ + add %0, %0, #32 \n\ + stmia %0, {r2 - r7, ip, lr} \n\ + ldmia %1!, {r2 - r7, ip, lr} \n\ + mcr p15, 0, %0, c7, c14, 1 @ clean and invalidate D line\n\ + add %0, %0, #32 \n\ + stmia %0, {r2 - r7, ip, lr} \n\ + ldmia %1!, {r2 - r7, ip, lr} \n\ + mcr p15, 0, %0, c7, c14, 1 @ clean and invalidate D line\n\ + add %0, %0, #32 \n\ + stmia %0, {r2 - r7, ip, lr} \n\ + ldmia %1!, {r2 - r7, ip, lr} \n\ + mcr p15, 0, %0, c7, c14, 1 @ clean and invalidate D line\n\ + add %0, %0, #32 \n\ + stmia %0, {r2 - r7, ip, lr} \n\ + ldmia %1!, {r2 - r7, ip, lr} \n\ + mcr p15, 0, %0, c7, c14, 1 @ clean and invalidate D line\n\ + add %0, %0, #32 \n\ + stmia %0, {r2 - r7, ip, lr} \n\ + subs %2, %2, #(32 * 8) \n\ + mcr p15, 0, %0, c7, c14, 1 @ clean and invalidate D line\n\ + add %0, %0, #32 \n\ bne 1b \n\ - mcr p15, 0, ip, c7, c10, 4 @ drain WB\n\ - ldmfd sp!, {r4-r9, pc}" - : - : "r" (kto), "r" (kfrom), "I" (PAGE_SIZE)); + mcr p15, 0, %2, c7, c10, 4 @ drain WB" + : "+&r" (kto), "+&r" (kfrom), "=&r" (tmp) + : "2" (PAGE_SIZE) + : "r2", "r3", "r4", "r5", "r6", "r7", "ip", "lr"); }

void feroceon_copy_user_highpage(struct page *to, struct page *from, --- a/arch/arm/mm/copypage-v4mc.c +++ b/arch/arm/mm/copypage-v4mc.c @@ -40,12 +40,11 @@ static DEFINE_RAW_SPINLOCK(minicache_loc * instruction. If your processor does not supply this, you have to write your * own copy_user_highpage that does the right thing. */ -static void __naked -mc_copy_user_page(void *from, void *to) +static void mc_copy_user_page(void *from, void *to) { - asm volatile( - "stmfd sp!, {r4, lr} @ 2\n\ - mov r4, %2 @ 1\n\ + int tmp; + + asm volatile ("\ ldmia %0!, {r2, r3, ip, lr} @ 4\n\ 1: mcr p15, 0, %1, c7, c6, 1 @ 1 invalidate D line\n\ stmia %1!, {r2, r3, ip, lr} @ 4\n\ @@ -55,13 +54,13 @@ mc_copy_user_page(void *from, void *to) mcr p15, 0, %1, c7, c6, 1 @ 1 invalidate D line\n\ stmia %1!, {r2, r3, ip, lr} @ 4\n\ ldmia %0!, {r2, r3, ip, lr} @ 4\n\ - subs r4, r4, #1 @ 1\n\ + subs %2, %2, #1 @ 1\n\ stmia %1!, {r2, r3, ip, lr} @ 4\n\ ldmneia %0!, {r2, r3, ip, lr} @ 4\n\ - bne 1b @ 1\n\ - ldmfd sp!, {r4, pc} @ 3" - : - : "r" (from), "r" (to), "I" (PAGE_SIZE / 64)); + bne 1b @ " + : "+&r" (from), "+&r" (to), "=&r" (tmp) + : "2" (PAGE_SIZE / 64) + : "r2", "r3", "ip", "lr"); }

void v4_mc_copy_user_highpage(struct page *to, struct page *from, --- a/arch/arm/mm/copypage-v4wb.c +++ b/arch/arm/mm/copypage-v4wb.c @@ -22,29 +22,28 @@ * instruction. If your processor does not supply this, you have to write your * own copy_user_highpage that does the right thing. */ -static void __naked -v4wb_copy_user_page(void *kto, const void *kfrom) +static void v4wb_copy_user_page(void *kto, const void *kfrom) { - asm("\ - stmfd sp!, {r4, lr} @ 2\n\ - mov r2, %2 @ 1\n\ - ldmia r1!, {r3, r4, ip, lr} @ 4\n\ -1: mcr p15, 0, r0, c7, c6, 1 @ 1 invalidate D line\n\ - stmia r0!, {r3, r4, ip, lr} @ 4\n\ - ldmia r1!, {r3, r4, ip, lr} @ 4+1\n\ - stmia r0!, {r3, r4, ip, lr} @ 4\n\ - ldmia r1!, {r3, r4, ip, lr} @ 4\n\ - mcr p15, 0, r0, c7, c6, 1 @ 1 invalidate D line\n\ - stmia r0!, {r3, r4, ip, lr} @ 4\n\ - ldmia r1!, {r3, r4, ip, lr} @ 4\n\ - subs r2, r2, #1 @ 1\n\ - stmia r0!, {r3, r4, ip, lr} @ 4\n\ - ldmneia r1!, {r3, r4, ip, lr} @ 4\n\ + int tmp; + + asm volatile ("\ + ldmia %1!, {r3, r4, ip, lr} @ 4\n\ +1: mcr p15, 0, %0, c7, c6, 1 @ 1 invalidate D line\n\ + stmia %0!, {r3, r4, ip, lr} @ 4\n\ + ldmia %1!, {r3, r4, ip, lr} @ 4+1\n\ + stmia %0!, {r3, r4, ip, lr} @ 4\n\ + ldmia %1!, {r3, r4, ip, lr} @ 4\n\ + mcr p15, 0, %0, c7, c6, 1 @ 1 invalidate D line\n\ + stmia %0!, {r3, r4, ip, lr} @ 4\n\ + ldmia %1!, {r3, r4, ip, lr} @ 4\n\ + subs %2, %2, #1 @ 1\n\ + stmia %0!, {r3, r4, ip, lr} @ 4\n\ + ldmneia %1!, {r3, r4, ip, lr} @ 4\n\ bne 1b @ 1\n\ - mcr p15, 0, r1, c7, c10, 4 @ 1 drain WB\n\ - ldmfd sp!, {r4, pc} @ 3" - : - : "r" (kto), "r" (kfrom), "I" (PAGE_SIZE / 64)); + mcr p15, 0, %1, c7, c10, 4 @ 1 drain WB" + : "+&r" (kto), "+&r" (kfrom), "=&r" (tmp) + : "2" (PAGE_SIZE / 64) + : "r3", "r4", "ip", "lr"); }

void v4wb_copy_user_highpage(struct page *to, struct page *from, --- a/arch/arm/mm/copypage-v4wt.c +++ b/arch/arm/mm/copypage-v4wt.c @@ -20,27 +20,26 @@ * dirty data in the cache. However, we do have to ensure that * subsequent reads are up to date. */ -static void __naked -v4wt_copy_user_page(void *kto, const void *kfrom) +static void v4wt_copy_user_page(void *kto, const void *kfrom) { - asm("\ - stmfd sp!, {r4, lr} @ 2\n\ - mov r2, %2 @ 1\n\ - ldmia r1!, {r3, r4, ip, lr} @ 4\n\ -1: stmia r0!, {r3, r4, ip, lr} @ 4\n\ - ldmia r1!, {r3, r4, ip, lr} @ 4+1\n\ - stmia r0!, {r3, r4, ip, lr} @ 4\n\ - ldmia r1!, {r3, r4, ip, lr} @ 4\n\ - stmia r0!, {r3, r4, ip, lr} @ 4\n\ - ldmia r1!, {r3, r4, ip, lr} @ 4\n\ - subs r2, r2, #1 @ 1\n\ - stmia r0!, {r3, r4, ip, lr} @ 4\n\ - ldmneia r1!, {r3, r4, ip, lr} @ 4\n\ + int tmp; + + asm volatile ("\ + ldmia %1!, {r3, r4, ip, lr} @ 4\n\ +1: stmia %0!, {r3, r4, ip, lr} @ 4\n\ + ldmia %1!, {r3, r4, ip, lr} @ 4+1\n\ + stmia %0!, {r3, r4, ip, lr} @ 4\n\ + ldmia %1!, {r3, r4, ip, lr} @ 4\n\ + stmia %0!, {r3, r4, ip, lr} @ 4\n\ + ldmia %1!, {r3, r4, ip, lr} @ 4\n\ + subs %2, %2, #1 @ 1\n\ + stmia %0!, {r3, r4, ip, lr} @ 4\n\ + ldmneia %1!, {r3, r4, ip, lr} @ 4\n\ bne 1b @ 1\n\ - mcr p15, 0, r2, c7, c7, 0 @ flush ID cache\n\ - ldmfd sp!, {r4, pc} @ 3" - : - : "r" (kto), "r" (kfrom), "I" (PAGE_SIZE / 64)); + mcr p15, 0, %2, c7, c7, 0 @ flush ID cache" + : "+&r" (kto), "+&r" (kfrom), "=&r" (tmp) + : "2" (PAGE_SIZE / 64) + : "r3", "r4", "ip", "lr"); }

void v4wt_copy_user_highpage(struct page *to, struct page *from, --- a/arch/arm/mm/copypage-xsc3.c +++ b/arch/arm/mm/copypage-xsc3.c @@ -21,53 +21,46 @@

/* * XSC3 optimised copy_user_highpage - * r0 = destination - * r1 = source * * The source page may have some clean entries in the cache already, but we * can safely ignore them - break_cow() will flush them out of the cache * if we eventually end up using our copied page. * */ -static void __naked -xsc3_mc_copy_user_page(void *kto, const void *kfrom) +static void xsc3_mc_copy_user_page(void *kto, const void *kfrom) { - asm("\ - stmfd sp!, {r4, r5, lr} \n\ - mov lr, %2 \n\ - \n\ - pld [r1, #0] \n\ - pld [r1, #32] \n\ -1: pld [r1, #64] \n\ - pld [r1, #96] \n\ + int tmp; + + asm volatile ("\ + pld [%1, #0] \n\ + pld [%1, #32] \n\ +1: pld [%1, #64] \n\ + pld [%1, #96] \n\ \n\ -2: ldrd r2, [r1], #8 \n\ - mov ip, r0 \n\ - ldrd r4, [r1], #8 \n\ - mcr p15, 0, ip, c7, c6, 1 @ invalidate\n\ - strd r2, [r0], #8 \n\ - ldrd r2, [r1], #8 \n\ - strd r4, [r0], #8 \n\ - ldrd r4, [r1], #8 \n\ - strd r2, [r0], #8 \n\ - strd r4, [r0], #8 \n\ - ldrd r2, [r1], #8 \n\ - mov ip, r0 \n\ - ldrd r4, [r1], #8 \n\ - mcr p15, 0, ip, c7, c6, 1 @ invalidate\n\ - strd r2, [r0], #8 \n\ - ldrd r2, [r1], #8 \n\ - subs lr, lr, #1 \n\ - strd r4, [r0], #8 \n\ - ldrd r4, [r1], #8 \n\ - strd r2, [r0], #8 \n\ - strd r4, [r0], #8 \n\ +2: ldrd r2, [%1], #8 \n\ + ldrd r4, [%1], #8 \n\ + mcr p15, 0, %0, c7, c6, 1 @ invalidate\n\ + strd r2, [%0], #8 \n\ + ldrd r2, [%1], #8 \n\ + strd r4, [%0], #8 \n\ + ldrd r4, [%1], #8 \n\ + strd r2, [%0], #8 \n\ + strd r4, [%0], #8 \n\ + ldrd r2, [%1], #8 \n\ + ldrd r4, [%1], #8 \n\ + mcr p15, 0, %0, c7, c6, 1 @ invalidate\n\ + strd r2, [%0], #8 \n\ + ldrd r2, [%1], #8 \n\ + subs %2, %2, #1 \n\ + strd r4, [%0], #8 \n\ + ldrd r4, [%1], #8 \n\ + strd r2, [%0], #8 \n\ + strd r4, [%0], #8 \n\ bgt 1b \n\ - beq 2b \n\ - \n\ - ldmfd sp!, {r4, r5, pc}" - : - : "r" (kto), "r" (kfrom), "I" (PAGE_SIZE / 64 - 1)); + beq 2b " + : "+&r" (kto), "+&r" (kfrom), "=&r" (tmp) + : "2" (PAGE_SIZE / 64 - 1) + : "r2", "r3", "r4", "r5"); }

void xsc3_mc_copy_user_highpage(struct page *to, struct page *from, @@ -85,8 +78,6 @@ void xsc3_mc_copy_user_highpage(struct p

/* * XScale optimised clear_user_page - * r0 = destination - * r1 = virtual user address of ultimate destination page */ void xsc3_mc_clear_user_highpage(struct page *page, unsigned long vaddr) { --- a/arch/arm/mm/copypage-xscale.c +++ b/arch/arm/mm/copypage-xscale.c @@ -36,52 +36,51 @@ static DEFINE_RAW_SPINLOCK(minicache_loc * Dcache aliasing issue. The writes will be forwarded to the write buffer, * and merged as appropriate. */ -static void __naked -mc_copy_user_page(void *from, void *to) +static void mc_copy_user_page(void *from, void *to) { + int tmp; + /* * Strangely enough, best performance is achieved * when prefetching destination as well. (NP) */ - asm volatile( - "stmfd sp!, {r4, r5, lr} \n\ - mov lr, %2 \n\ - pld [r0, #0] \n\ - pld [r0, #32] \n\ - pld [r1, #0] \n\ - pld [r1, #32] \n\ -1: pld [r0, #64] \n\ - pld [r0, #96] \n\ - pld [r1, #64] \n\ - pld [r1, #96] \n\ -2: ldrd r2, [r0], #8 \n\ - ldrd r4, [r0], #8 \n\ - mov ip, r1 \n\ - strd r2, [r1], #8 \n\ - ldrd r2, [r0], #8 \n\ - strd r4, [r1], #8 \n\ - ldrd r4, [r0], #8 \n\ - strd r2, [r1], #8 \n\ - strd r4, [r1], #8 \n\ + asm volatile ("\ + pld [%0, #0] \n\ + pld [%0, #32] \n\ + pld [%1, #0] \n\ + pld [%1, #32] \n\ +1: pld [%0, #64] \n\ + pld [%0, #96] \n\ + pld [%1, #64] \n\ + pld [%1, #96] \n\ +2: ldrd r2, [%0], #8 \n\ + ldrd r4, [%0], #8 \n\ + mov ip, %1 \n\ + strd r2, [%1], #8 \n\ + ldrd r2, [%0], #8 \n\ + strd r4, [%1], #8 \n\ + ldrd r4, [%0], #8 \n\ + strd r2, [%1], #8 \n\ + strd r4, [%1], #8 \n\ mcr p15, 0, ip, c7, c10, 1 @ clean D line\n\ - ldrd r2, [r0], #8 \n\ + ldrd r2, [%0], #8 \n\ mcr p15, 0, ip, c7, c6, 1 @ invalidate D line\n\ - ldrd r4, [r0], #8 \n\ - mov ip, r1 \n\ - strd r2, [r1], #8 \n\ - ldrd r2, [r0], #8 \n\ - strd r4, [r1], #8 \n\ - ldrd r4, [r0], #8 \n\ - strd r2, [r1], #8 \n\ - strd r4, [r1], #8 \n\ + ldrd r4, [%0], #8 \n\ + mov ip, %1 \n\ + strd r2, [%1], #8 \n\ + ldrd r2, [%0], #8 \n\ + strd r4, [%1], #8 \n\ + ldrd r4, [%0], #8 \n\ + strd r2, [%1], #8 \n\ + strd r4, [%1], #8 \n\ mcr p15, 0, ip, c7, c10, 1 @ clean D line\n\ - subs lr, lr, #1 \n\ + subs %2, %2, #1 \n\ mcr p15, 0, ip, c7, c6, 1 @ invalidate D line\n\ bgt 1b \n\ - beq 2b \n\ - ldmfd sp!, {r4, r5, pc} " - : - : "r" (from), "r" (to), "I" (PAGE_SIZE / 64 - 1)); + beq 2b " + : "+&r" (from), "+&r" (to), "=&r" (tmp) + : "2" (PAGE_SIZE / 64 - 1) + : "r2", "r3", "r4", "r5", "ip"); }

void xscale_mc_copy_user_highpage(struct page *to, struct page *from,

From: Stefan Agner stefan@agner.ch

commit f9b58e8c7d031b0daa5c9a9ee27f5a4028ba53ac upstream.

While in theory multiple unwinders could be compiled in, it does not make sense in practise. Use a choice to make the unwinder selection mutually exclusive and mandatory.

Already before this commit it has not been possible to deselect FRAME_POINTER. Remove the obsolete comment.

Furthermore, to produce a meaningful backtrace with FRAME_POINTER enabled the kernel needs a specific function prologue: mov ip, sp stmfd sp!, {fp, ip, lr, pc} sub fp, ip, #4

To get to the required prologue gcc uses apcs and no-sched-prolog. This compiler options are not available on clang, and clang is not able to generate the required prologue. Make the FRAME_POINTER config symbol depending on !clang.

Suggested-by: Arnd Bergmann arnd@arndb.de Signed-off-by: Stefan Agner stefan@agner.ch Reviewed-by: Arnd Bergmann arnd@arndb.de Signed-off-by: Russell King rmk+kernel@armlinux.org.uk Signed-off-by: Anders Roxell anders.roxell@linaro.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/arm/Kconfig.debug | 44 ++++++++++++++++++++++++++++---------------- lib/Kconfig.debug | 6 +++--- 2 files changed, 31 insertions(+), 19 deletions(-)

--- a/arch/arm/Kconfig.debug +++ b/arch/arm/Kconfig.debug @@ -45,30 +45,42 @@ config DEBUG_WX

If in doubt, say "Y".

-# RMK wants arm kernels compiled with frame pointers or stack unwinding. -# If you know what you are doing and are willing to live without stack -# traces, you can get a slightly smaller kernel by setting this option to -# n, but then RMK will have to kill you ;). -config FRAME_POINTER - bool - depends on !THUMB2_KERNEL - default y if !ARM_UNWIND || FUNCTION_GRAPH_TRACER +choice + prompt "Choose kernel unwinder" + default UNWINDER_ARM if AEABI && !FUNCTION_GRAPH_TRACER + default UNWINDER_FRAME_POINTER if !AEABI || FUNCTION_GRAPH_TRACER help - If you say N here, the resulting kernel will be slightly smaller and - faster. However, if neither FRAME_POINTER nor ARM_UNWIND are enabled, - when a problem occurs with the kernel, the information that is - reported is severely limited. + This determines which method will be used for unwinding kernel stack + traces for panics, oopses, bugs, warnings, perf, /proc/<pid>/stack, + livepatch, lockdep, and more.

-config ARM_UNWIND - bool "Enable stack unwinding support (EXPERIMENTAL)" +config UNWINDER_FRAME_POINTER + bool "Frame pointer unwinder" + depends on !THUMB2_KERNEL && !CC_IS_CLANG + select ARCH_WANT_FRAME_POINTERS + select FRAME_POINTER + help + This option enables the frame pointer unwinder for unwinding + kernel stack traces. + +config UNWINDER_ARM + bool "ARM EABI stack unwinder" depends on AEABI - default y + select ARM_UNWIND help This option enables stack unwinding support in the kernel using the information automatically generated by the compiler. The resulting kernel image is slightly bigger but the performance is not affected. Currently, this feature - only works with EABI compilers. If unsure say Y. + only works with EABI compilers. + +endchoice + +config ARM_UNWIND + bool + +config FRAME_POINTER + bool

config OLD_MCOUNT bool --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -1178,7 +1178,7 @@ config LOCKDEP bool depends on DEBUG_KERNEL && LOCK_DEBUGGING_SUPPORT select STACKTRACE - select FRAME_POINTER if !MIPS && !PPC && !ARM_UNWIND && !S390 && !MICROBLAZE && !ARC && !X86 + select FRAME_POINTER if !MIPS && !PPC && !ARM && !S390 && !MICROBLAZE && !ARC && !X86 select KALLSYMS select KALLSYMS_ALL

@@ -1589,7 +1589,7 @@ config FAULT_INJECTION_STACKTRACE_FILTER depends on FAULT_INJECTION_DEBUG_FS && STACKTRACE_SUPPORT depends on !X86_64 select STACKTRACE - select FRAME_POINTER if !MIPS && !PPC && !S390 && !MICROBLAZE && !ARM_UNWIND && !ARC && !X86 + select FRAME_POINTER if !MIPS && !PPC && !S390 && !MICROBLAZE && !ARM && !ARC && !X86 help Provide stacktrace filter for fault-injection capabilities

@@ -1598,7 +1598,7 @@ config LATENCYTOP depends on DEBUG_KERNEL depends on STACKTRACE_SUPPORT depends on PROC_FS - select FRAME_POINTER if !MIPS && !PPC && !S390 && !MICROBLAZE && !ARM_UNWIND && !ARC && !X86 + select FRAME_POINTER if !MIPS && !PPC && !S390 && !MICROBLAZE && !ARM && !ARC && !X86 select KALLSYMS select KALLSYMS_ALL select STACKTRACE

From: Sudeep Holla sudeep.holla@arm.com

commit 865ed67ab955428b9aa771d8b4f1e4fb7fd08945 upstream.

Without the bound checks for scpi_pd->name, it could result in the buffer overflow when copying the SCPI device name from the corresponding device tree node as the name string is set at maximum size of 30.

Let us fix it by using devm_kasprintf so that the string buffer is allocated dynamically.

Fixes: 8bec4337ad40 ("firmware: scpi: add device power domain support using genpd") Reported-by: Pedro Batista pedbap.g@gmail.com Signed-off-by: Sudeep Holla sudeep.holla@arm.com Cc: stable@vger.kernel.org Cc: Cristian Marussi cristian.marussi@arm.com Link: https://lore.kernel.org/r/20211209120456.696879-1-sudeep.holla@arm.com' Signed-off-by: Arnd Bergmann arnd@arndb.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/firmware/scpi_pm_domain.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-)

--- a/drivers/firmware/scpi_pm_domain.c +++ b/drivers/firmware/scpi_pm_domain.c @@ -27,7 +27,6 @@ struct scpi_pm_domain { struct generic_pm_domain genpd; struct scpi_ops *ops; u32 domain; - char name[30]; };

/* @@ -121,8 +120,13 @@ static int scpi_pm_domain_probe(struct p

scpi_pd->domain = i; scpi_pd->ops = scpi_ops; - sprintf(scpi_pd->name, "%s.%d", np->name, i); - scpi_pd->genpd.name = scpi_pd->name; + scpi_pd->genpd.name = devm_kasprintf(dev, GFP_KERNEL, + "%s.%d", np->name, i); + if (!scpi_pd->genpd.name) { + dev_err(dev, "Failed to allocate genpd name:%s.%d\n", + np->name, i); + continue; + } scpi_pd->genpd.power_off = scpi_pd_power_off; scpi_pd->genpd.power_on = scpi_pd_power_on;

From: Pavel Skripkin paskripkin@gmail.com

commit 44870a9e7a3c24acbb3f888b2a7cc22c9bdf7e7f upstream.

Syzbot reported, that mxl111sf_ctrl_msg() uses uninitialized mutex. The problem was in wrong mutex_init() location.

Previous mutex_init(&state->msg_lock) call was in ->init() function, but dvb_usbv2_init() has this order of calls:

dvb_usbv2_init() dvb_usbv2_adapter_init() dvb_usbv2_adapter_frontend_init() props->frontend_attach()

props->init()

Since mxl111sf_* devices call mxl111sf_ctrl_msg() in ->frontend_attach() internally we need to initialize state->msg_lock before frontend_attach(). To achieve it, ->probe() call added to all mxl111sf_* devices, which will simply initiaize mutex.

Reported-and-tested-by: syzbot+5ca0bf339f13c4243001@syzkaller.appspotmail.com

Fixes: 8572211842af ("[media] mxl111sf: convert to new DVB USB") Signed-off-by: Pavel Skripkin paskripkin@gmail.com Signed-off-by: Sean Young sean@mess.org Signed-off-by: Mauro Carvalho Chehab mchehab+huawei@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/media/usb/dvb-usb-v2/mxl111sf.c | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-)

--- a/drivers/media/usb/dvb-usb-v2/mxl111sf.c +++ b/drivers/media/usb/dvb-usb-v2/mxl111sf.c @@ -932,8 +932,6 @@ static int mxl111sf_init(struct dvb_usb_ .len = sizeof(eeprom), .buf = eeprom }, };

- mutex_init(&state->msg_lock); - ret = get_chip_info(state); if (mxl_fail(ret)) pr_err("failed to get chip info during probe"); @@ -1075,6 +1073,14 @@ static int mxl111sf_get_stream_config_dv return 0; }

+static int mxl111sf_probe(struct dvb_usb_device *dev) +{ + struct mxl111sf_state *state = d_to_priv(dev); + + mutex_init(&state->msg_lock); + return 0; +} + static struct dvb_usb_device_properties mxl111sf_props_dvbt = { .driver_name = KBUILD_MODNAME, .owner = THIS_MODULE, @@ -1084,6 +1090,7 @@ static struct dvb_usb_device_properties .generic_bulk_ctrl_endpoint = 0x02, .generic_bulk_ctrl_endpoint_response = 0x81,

+ .probe = mxl111sf_probe, .i2c_algo = &mxl111sf_i2c_algo, .frontend_attach = mxl111sf_frontend_attach_dvbt, .tuner_attach = mxl111sf_attach_tuner, @@ -1125,6 +1132,7 @@ static struct dvb_usb_device_properties .generic_bulk_ctrl_endpoint = 0x02, .generic_bulk_ctrl_endpoint_response = 0x81,

+ .probe = mxl111sf_probe, .i2c_algo = &mxl111sf_i2c_algo, .frontend_attach = mxl111sf_frontend_attach_atsc, .tuner_attach = mxl111sf_attach_tuner, @@ -1166,6 +1174,7 @@ static struct dvb_usb_device_properties .generic_bulk_ctrl_endpoint = 0x02, .generic_bulk_ctrl_endpoint_response = 0x81,

+ .probe = mxl111sf_probe, .i2c_algo = &mxl111sf_i2c_algo, .frontend_attach = mxl111sf_frontend_attach_mh, .tuner_attach = mxl111sf_attach_tuner, @@ -1234,6 +1243,7 @@ static struct dvb_usb_device_properties .generic_bulk_ctrl_endpoint = 0x02, .generic_bulk_ctrl_endpoint_response = 0x81,

+ .probe = mxl111sf_probe, .i2c_algo = &mxl111sf_i2c_algo, .frontend_attach = mxl111sf_frontend_attach_atsc_mh, .tuner_attach = mxl111sf_attach_tuner, @@ -1312,6 +1322,7 @@ static struct dvb_usb_device_properties .generic_bulk_ctrl_endpoint = 0x02, .generic_bulk_ctrl_endpoint_response = 0x81,

+ .probe = mxl111sf_probe, .i2c_algo = &mxl111sf_i2c_algo, .frontend_attach = mxl111sf_frontend_attach_mercury, .tuner_attach = mxl111sf_attach_tuner, @@ -1382,6 +1393,7 @@ static struct dvb_usb_device_properties .generic_bulk_ctrl_endpoint = 0x02, .generic_bulk_ctrl_endpoint_response = 0x81,

+ .probe = mxl111sf_probe, .i2c_algo = &mxl111sf_i2c_algo, .frontend_attach = mxl111sf_frontend_attach_mercury_mh, .tuner_attach = mxl111sf_attach_tuner,

From: Miklos Szeredi mszeredi@redhat.com

commit 1f5573cfe7a7056e80a92c7a037a3e69f3a13d1c upstream.

Syzbot triggered the following warning in ovl_workdir_create() -> ovl_create_real():

if (!err && WARN_ON(!newdentry->d_inode)) {

The reason is that the cgroup2 filesystem returns from mkdir without instantiating the new dentry.

Weird filesystems such as this will be rejected by overlayfs at a later stage during setup, but to prevent such a warning, call ovl_mkdir_real() directly from ovl_workdir_create() and reject this case early.

Reported-and-tested-by: syzbot+75eab84fd0af9e8bf66b@syzkaller.appspotmail.com Signed-off-by: Miklos Szeredi mszeredi@redhat.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/overlayfs/dir.c | 3 +-- fs/overlayfs/overlayfs.h | 1 + fs/overlayfs/super.c | 12 ++++++++---- 3 files changed, 10 insertions(+), 6 deletions(-)

--- a/fs/overlayfs/dir.c +++ b/fs/overlayfs/dir.c @@ -116,8 +116,7 @@ kill_whiteout: goto out; }

-static int ovl_mkdir_real(struct inode *dir, struct dentry **newdentry, - umode_t mode) +int ovl_mkdir_real(struct inode *dir, struct dentry **newdentry, umode_t mode) { int err; struct dentry *d, *dentry = *newdentry; --- a/fs/overlayfs/overlayfs.h +++ b/fs/overlayfs/overlayfs.h @@ -402,6 +402,7 @@ struct ovl_cattr {

#define OVL_CATTR(m) (&(struct ovl_cattr) { .mode = (m) })

+int ovl_mkdir_real(struct inode *dir, struct dentry **newdentry, umode_t mode); struct dentry *ovl_create_real(struct inode *dir, struct dentry *newdentry, struct ovl_cattr *attr); int ovl_cleanup(struct inode *dir, struct dentry *dentry); --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -654,10 +654,14 @@ retry: goto retry; }

- work = ovl_create_real(dir, work, OVL_CATTR(attr.ia_mode)); - err = PTR_ERR(work); - if (IS_ERR(work)) - goto out_err; + err = ovl_mkdir_real(dir, &work, attr.ia_mode); + if (err) + goto out_dput; + + /* Weird filesystem returning with hashed negative (kernfs)? */ + err = -EINVAL; + if (d_really_is_negative(work)) + goto out_dput;

/* * Try to remove POSIX ACL xattrs from workdir. We are good if:

From: Juergen Gross jgross@suse.com

commit 0fd08a34e8e3b67ec9bd8287ac0facf8374b844a upstream.

The Xen blkfront driver is still vulnerable for an attack via excessive number of events sent by the backend. Fix that by using lateeoi event channels.

This is part of XSA-391

Signed-off-by: Juergen Gross jgross@suse.com Reviewed-by: Jan Beulich jbeulich@suse.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/block/xen-blkfront.c | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-)

--- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -1565,9 +1565,12 @@ static irqreturn_t blkif_interrupt(int i unsigned long flags; struct blkfront_ring_info *rinfo = (struct blkfront_ring_info *)dev_id; struct blkfront_info *info = rinfo->dev_info; + unsigned int eoiflag = XEN_EOI_FLAG_SPURIOUS;

- if (unlikely(info->connected != BLKIF_STATE_CONNECTED)) + if (unlikely(info->connected != BLKIF_STATE_CONNECTED)) { + xen_irq_lateeoi(irq, XEN_EOI_FLAG_SPURIOUS); return IRQ_HANDLED; + }

spin_lock_irqsave(&rinfo->ring_lock, flags); again: @@ -1583,6 +1586,8 @@ static irqreturn_t blkif_interrupt(int i unsigned long id; unsigned int op;

+ eoiflag = 0; + RING_COPY_RESPONSE(&rinfo->ring, i, &bret); id = bret.id;

@@ -1698,6 +1703,8 @@ static irqreturn_t blkif_interrupt(int i

spin_unlock_irqrestore(&rinfo->ring_lock, flags);

+ xen_irq_lateeoi(irq, eoiflag); + return IRQ_HANDLED;

err: @@ -1705,6 +1712,8 @@ static irqreturn_t blkif_interrupt(int i

spin_unlock_irqrestore(&rinfo->ring_lock, flags);

+ /* No EOI in order to avoid further interrupts. */ + pr_alert("%s disabled for further use\n", info->gd->disk_name); return IRQ_HANDLED; } @@ -1744,8 +1753,8 @@ static int setup_blkring(struct xenbus_d if (err) goto fail;

- err = bind_evtchn_to_irqhandler(rinfo->evtchn, blkif_interrupt, 0, - "blkif", rinfo); + err = bind_evtchn_to_irqhandler_lateeoi(rinfo->evtchn, blkif_interrupt, + 0, "blkif", rinfo); if (err <= 0) { xenbus_dev_fatal(dev, err, "bind_evtchn_to_irqhandler failed");

From: Juergen Gross jgross@suse.com

This is commit fe415186b43df0db1f17fa3a46275fd92107fe71 upstream.

The Xen console driver is still vulnerable for an attack via excessive number of events sent by the backend. Fix that by using a lateeoi event channel.

For the normal domU initial console this requires the introduction of bind_evtchn_to_irq_lateeoi() as there is no xenbus device available at the time the event channel is bound to the irq.

As the decision whether an interrupt was spurious or not requires to test for bytes having been read from the backend, move sending the event into the if statement, as sending an event without having found any bytes to be read is making no sense at all.

This is part of XSA-391

Signed-off-by: Juergen Gross jgross@suse.com Reviewed-by: Jan Beulich jbeulich@suse.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/tty/hvc/hvc_xen.c | 30 +++++++++++++++++++++++++++--- 1 file changed, 27 insertions(+), 3 deletions(-)

--- a/drivers/tty/hvc/hvc_xen.c +++ b/drivers/tty/hvc/hvc_xen.c @@ -37,6 +37,8 @@ struct xencons_info { struct xenbus_device *xbdev; struct xencons_interface *intf; unsigned int evtchn; + XENCONS_RING_IDX out_cons; + unsigned int out_cons_same; struct hvc_struct *hvc; int irq; int vtermno; @@ -138,6 +140,8 @@ static int domU_read_console(uint32_t vt XENCONS_RING_IDX cons, prod; int recv = 0; struct xencons_info *xencons = vtermno_to_xencons(vtermno); + unsigned int eoiflag = 0; + if (xencons == NULL) return -EINVAL; intf = xencons->intf; @@ -157,7 +161,27 @@ static int domU_read_console(uint32_t vt mb(); /* read ring before consuming */ intf->in_cons = cons;

- notify_daemon(xencons); + /* + * When to mark interrupt having been spurious: + * - there was no new data to be read, and + * - the backend did not consume some output bytes, and + * - the previous round with no read data didn't see consumed bytes + * (we might have a race with an interrupt being in flight while + * updating xencons->out_cons, so account for that by allowing one + * round without any visible reason) + */ + if (intf->out_cons != xencons->out_cons) { + xencons->out_cons = intf->out_cons; + xencons->out_cons_same = 0; + } + if (recv) { + notify_daemon(xencons); + } else if (xencons->out_cons_same++ > 1) { + eoiflag = XEN_EOI_FLAG_SPURIOUS; + } + + xen_irq_lateeoi(xencons->irq, eoiflag); + return recv; }

@@ -386,7 +410,7 @@ static int xencons_connect_backend(struc if (ret) return ret; info->evtchn = evtchn; - irq = bind_evtchn_to_irq(evtchn); + irq = bind_interdomain_evtchn_to_irq_lateeoi(dev->otherend_id, evtchn); if (irq < 0) return irq; info->irq = irq; @@ -550,7 +574,7 @@ static int __init xen_hvc_init(void) return r;

info = vtermno_to_xencons(HVC_COOKIE); - info->irq = bind_evtchn_to_irq(info->evtchn); + info->irq = bind_evtchn_to_irq_lateeoi(info->evtchn); } if (info->irq < 0) info->irq = 0; /* NO_IRQ */

From: Juergen Gross jgross@suse.com

commit be81992f9086b230623ae3ebbc85ecee4d00a3d3 upstream.

In case a guest isn't consuming incoming network traffic as fast as it is coming in, xen-netback is buffering network packages in unlimited numbers today. This can result in host OOM situations.

Commit f48da8b14d04ca8 ("xen-netback: fix unlimited guest Rx internal queue and carrier flapping") meant to introduce a mechanism to limit the amount of buffered data by stopping the Tx queue when reaching the data limit, but this doesn't work for cases like UDP.

When hitting the limit don't queue further SKBs, but drop them instead. In order to be able to tell Rx packages have been dropped increment the rx_dropped statistics counter in this case.

It should be noted that the old solution to continue queueing SKBs had the additional problem of an overflow of the 32-bit rx_queue_len value would result in intermittent Tx queue enabling.

This is part of XSA-392

Fixes: f48da8b14d04ca8 ("xen-netback: fix unlimited guest Rx internal queue and carrier flapping") Signed-off-by: Juergen Gross jgross@suse.com Reviewed-by: Jan Beulich jbeulich@suse.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/xen-netback/rx.c | 18 +++++++++++------- 1 file changed, 11 insertions(+), 7 deletions(-)

--- a/drivers/net/xen-netback/rx.c +++ b/drivers/net/xen-netback/rx.c @@ -88,16 +88,19 @@ void xenvif_rx_queue_tail(struct xenvif_

spin_lock_irqsave(&queue->rx_queue.lock, flags);

- if (skb_queue_empty(&queue->rx_queue)) - xenvif_update_needed_slots(queue, skb); - - __skb_queue_tail(&queue->rx_queue, skb); - - queue->rx_queue_len += skb->len; - if (queue->rx_queue_len > queue->rx_queue_max) { + if (queue->rx_queue_len >= queue->rx_queue_max) { struct net_device *dev = queue->vif->dev;

netif_tx_stop_queue(netdev_get_tx_queue(dev, queue->id)); + kfree_skb(skb); + queue->vif->dev->stats.rx_dropped++; + } else { + if (skb_queue_empty(&queue->rx_queue)) + xenvif_update_needed_slots(queue, skb); + + __skb_queue_tail(&queue->rx_queue, skb); + + queue->rx_queue_len += skb->len; }

spin_unlock_irqrestore(&queue->rx_queue.lock, flags); @@ -147,6 +150,7 @@ static void xenvif_rx_queue_drop_expired break; xenvif_rx_dequeue(queue); kfree_skb(skb); + queue->vif->dev->stats.rx_dropped++; } }