From: Nicolas Dichtel nicolas.dichtel@6wind.com

commit 3b0dc529f56b5f2328244130683210be98f16f7f upstream.

When routes corresponding to addresses are restored by fixup_permanent_addr(), the dst_nopolicy parameter was not set. The typical use case is a user that configures an address on a down interface and then put this interface up.

Let's take care of this flag in addrconf_f6i_alloc(), so that every callers benefit ont it.

CC: stable@kernel.org CC: David Forster dforster@brocade.com Fixes: df789fe75206 ("ipv6: Provide ipv6 version of "disable_policy" sysctl") Reported-by: Siwar Zitouni siwar.zitouni@6wind.com Signed-off-by: Nicolas Dichtel nicolas.dichtel@6wind.com Reviewed-by: David Ahern dsahern@kernel.org Link: https://lore.kernel.org/r/20220623120015.32640-1-nicolas.dichtel@6wind.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/ipv6/addrconf.c | 4 ---- net/ipv6/route.c | 9 ++++++++- 2 files changed, 8 insertions(+), 5 deletions(-)

--- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -1102,10 +1102,6 @@ ipv6_add_addr(struct inet6_dev *idev, st goto out; }

- if (net->ipv6.devconf_all->disable_policy || - idev->cnf.disable_policy) - f6i->dst_nopolicy = true; - neigh_parms_data_state_setall(idev->nd_parms);

ifa->addr = *cfg->pfx; --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -4483,8 +4483,15 @@ struct fib6_info *addrconf_f6i_alloc(str }

f6i = ip6_route_info_create(&cfg, gfp_flags, NULL); - if (!IS_ERR(f6i)) + if (!IS_ERR(f6i)) { f6i->dst_nocount = true; + + if (!anycast && + (net->ipv6.devconf_all->disable_policy || + idev->cnf.disable_policy)) + f6i->dst_nopolicy = true; + } + return f6i; }

From: Liam Howlett liam.howlett@oracle.com

commit 6886da5f49e6d86aad76807a93f3eef5e4f01b10 upstream.

When searching for config options, use the KCONFIG_CONFIG shell variable so that builds using non-standard config locations work.

Fixes: 26deb04342e3 ("powerpc: prepare string/mem functions for KASAN") Cc: stable@vger.kernel.org # v5.2+ Signed-off-by: Liam R. Howlett Liam.Howlett@oracle.com Signed-off-by: Michael Ellerman mpe@ellerman.id.au Link: https://lore.kernel.org/r/20220624011745.4060795-1-Liam.Howlett@oracle.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/powerpc/kernel/prom_init_check.sh | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/arch/powerpc/kernel/prom_init_check.sh +++ b/arch/powerpc/kernel/prom_init_check.sh @@ -13,7 +13,7 @@ # If you really need to reference something from prom_init.o add # it to the list below:

-grep "^CONFIG_KASAN=y$" .config >/dev/null +grep "^CONFIG_KASAN=y$" ${KCONFIG_CONFIG} >/dev/null if [ $? -eq 0 ] then MEM_FUNCS="__memcpy __memset"

From: Heinz Mauelshagen heinzm@redhat.com

commit 332bd0778775d0cf105c4b9e03e460b590749916 upstream.

On dm-raid table load (using raid_ctr), dm-raid allocates an array rs->devs[rs->raid_disks] for the raid device members. rs->raid_disks is defined by the number of raid metadata and image tupples passed into the target's constructor.

In the case of RAID layout changes being requested, that number can be different from the current number of members for existing raid sets as defined in their superblocks. Example RAID layout changes include: - raid1 legs being added/removed - raid4/5/6/10 number of stripes changed (stripe reshaping) - takeover to higher raid level (e.g. raid5 -> raid6)

When accessing array members, rs->raid_disks must be used in control loops instead of the potentially larger value in rs->md.raid_disks. Otherwise it will cause memory access beyond the end of the rs->devs array.

Fix this by changing code that is prone to out-of-bounds access. Also fix validate_raid_redundancy() to validate all devices that are added. Also, use braces to help clean up raid_iterate_devices().

The out-of-bounds memory accesses was discovered using KASAN.

This commit was verified to pass all LVM2 RAID tests (with KASAN enabled).

Cc: stable@vger.kernel.org Signed-off-by: Heinz Mauelshagen heinzm@redhat.com Signed-off-by: Mike Snitzer snitzer@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/md/dm-raid.c | 34 ++++++++++++++++++---------------- 1 file changed, 18 insertions(+), 16 deletions(-)

--- a/drivers/md/dm-raid.c +++ b/drivers/md/dm-raid.c @@ -998,12 +998,13 @@ static int validate_region_size(struct r static int validate_raid_redundancy(struct raid_set *rs) { unsigned int i, rebuild_cnt = 0; - unsigned int rebuilds_per_group = 0, copies; + unsigned int rebuilds_per_group = 0, copies, raid_disks; unsigned int group_size, last_group_start;

- for (i = 0; i < rs->md.raid_disks; i++) - if (!test_bit(In_sync, &rs->dev[i].rdev.flags) || - !rs->dev[i].rdev.sb_page) + for (i = 0; i < rs->raid_disks; i++) + if (!test_bit(FirstUse, &rs->dev[i].rdev.flags) && + ((!test_bit(In_sync, &rs->dev[i].rdev.flags) || + !rs->dev[i].rdev.sb_page))) rebuild_cnt++;

switch (rs->md.level) { @@ -1043,8 +1044,9 @@ static int validate_raid_redundancy(stru * A A B B C * C D D E E */ + raid_disks = min(rs->raid_disks, rs->md.raid_disks); if (__is_raid10_near(rs->md.new_layout)) { - for (i = 0; i < rs->md.raid_disks; i++) { + for (i = 0; i < raid_disks; i++) { if (!(i % copies)) rebuilds_per_group = 0; if ((!rs->dev[i].rdev.sb_page || @@ -1067,10 +1069,10 @@ static int validate_raid_redundancy(stru * results in the need to treat the last (potentially larger) * set differently. */ - group_size = (rs->md.raid_disks / copies); - last_group_start = (rs->md.raid_disks / group_size) - 1; + group_size = (raid_disks / copies); + last_group_start = (raid_disks / group_size) - 1; last_group_start *= group_size; - for (i = 0; i < rs->md.raid_disks; i++) { + for (i = 0; i < raid_disks; i++) { if (!(i % copies) && !(i > last_group_start)) rebuilds_per_group = 0; if ((!rs->dev[i].rdev.sb_page || @@ -1585,7 +1587,7 @@ static sector_t __rdev_sectors(struct ra { int i;

- for (i = 0; i < rs->md.raid_disks; i++) { + for (i = 0; i < rs->raid_disks; i++) { struct md_rdev *rdev = &rs->dev[i].rdev;

if (!test_bit(Journal, &rdev->flags) && @@ -3746,13 +3748,13 @@ static int raid_iterate_devices(struct d unsigned int i; int r = 0;

- for (i = 0; !r && i < rs->md.raid_disks; i++) - if (rs->dev[i].data_dev) - r = fn(ti, - rs->dev[i].data_dev, - 0, /* No offset on data devs */ - rs->md.dev_sectors, - data); + for (i = 0; !r && i < rs->raid_disks; i++) { + if (rs->dev[i].data_dev) { + r = fn(ti, rs->dev[i].data_dev, + 0, /* No offset on data devs */ + rs->md.dev_sectors, data); + } + }

return r; }

From: Jason A. Donenfeld Jason@zx2c4.com

commit e4f74400308cb8abde5fdc9cad609c2aba32110c upstream.

s390x appears to present two RNG interfaces: - a "TRNG" that gathers entropy using some hardware function; and - a "DRBG" that takes in a seed and expands it.

Previously, the TRNG was wired up to arch_get_random_{long,int}(), but it was observed that this was being called really frequently, resulting in high overhead. So it was changed to be wired up to arch_get_random_ seed_{long,int}(), which was a reasonable decision. Later on, the DRBG was then wired up to arch_get_random_{long,int}(), with a complicated buffer filling thread, to control overhead and rate.

Fortunately, none of the performance issues matter much now. The RNG always attempts to use arch_get_random_seed_{long,int}() first, which means a complicated implementation of arch_get_random_{long,int}() isn't really valuable or useful to have around. And it's only used when reseeding, which means it won't hit the high throughput complications that were faced before.

So this commit returns to an earlier design of just calling the TRNG in arch_get_random_seed_{long,int}(), and returning false in arch_get_ random_{long,int}().

Part of what makes the simplification possible is that the RNG now seeds itself using the TRNG at bootup. But this only works if the TRNG is detected early in boot, before random_init() is called. So this commit also causes that check to happen in setup_arch().

Cc: stable@vger.kernel.org Cc: Harald Freudenberger freude@linux.ibm.com Cc: Ingo Franzki ifranzki@linux.ibm.com Cc: Juergen Christ jchrist@linux.ibm.com Cc: Heiko Carstens hca@linux.ibm.com Signed-off-by: Jason A. Donenfeld Jason@zx2c4.com Link: https://lore.kernel.org/r/20220610222023.378448-1-Jason@zx2c4.com Reviewed-by: Harald Freudenberger freude@linux.ibm.com Acked-by: Heiko Carstens hca@linux.ibm.com Signed-off-by: Alexander Gordeev agordeev@linux.ibm.com Signed-off-by: Jason A. Donenfeld Jason@zx2c4.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/s390/crypto/arch_random.c | 111 ------------------------------------- arch/s390/include/asm/archrandom.h | 21 ++++--- arch/s390/kernel/setup.c | 5 + 3 files changed, 18 insertions(+), 119 deletions(-)

--- a/arch/s390/crypto/arch_random.c +++ b/arch/s390/crypto/arch_random.c @@ -2,126 +2,17 @@ /* * s390 arch random implementation. * - * Copyright IBM Corp. 2017, 2018 + * Copyright IBM Corp. 2017, 2020 * Author(s): Harald Freudenberger - * - * The s390_arch_random_generate() function may be called from random.c - * in interrupt context. So this implementation does the best to be very - * fast. There is a buffer of random data which is asynchronously checked - * and filled by a workqueue thread. - * If there are enough bytes in the buffer the s390_arch_random_generate() - * just delivers these bytes. Otherwise false is returned until the - * worker thread refills the buffer. - * The worker fills the rng buffer by pulling fresh entropy from the - * high quality (but slow) true hardware random generator. This entropy - * is then spread over the buffer with an pseudo random generator PRNG. - * As the arch_get_random_seed_long() fetches 8 bytes and the calling - * function add_interrupt_randomness() counts this as 1 bit entropy the - * distribution needs to make sure there is in fact 1 bit entropy contained - * in 8 bytes of the buffer. The current values pull 32 byte entropy - * and scatter this into a 2048 byte buffer. So 8 byte in the buffer - * will contain 1 bit of entropy. - * The worker thread is rescheduled based on the charge level of the - * buffer but at least with 500 ms delay to avoid too much CPU consumption. - * So the max. amount of rng data delivered via arch_get_random_seed is - * limited to 4k bytes per second. */

#include <linux/kernel.h> #include <linux/atomic.h> #include <linux/random.h> -#include <linux/slab.h> #include <linux/static_key.h> -#include <linux/workqueue.h> #include <asm/cpacf.h>

DEFINE_STATIC_KEY_FALSE(s390_arch_random_available);

atomic64_t s390_arch_random_counter = ATOMIC64_INIT(0); EXPORT_SYMBOL(s390_arch_random_counter); - -#define ARCH_REFILL_TICKS (HZ/2) -#define ARCH_PRNG_SEED_SIZE 32 -#define ARCH_RNG_BUF_SIZE 2048 - -static DEFINE_SPINLOCK(arch_rng_lock); -static u8 *arch_rng_buf; -static unsigned int arch_rng_buf_idx; - -static void arch_rng_refill_buffer(struct work_struct *); -static DECLARE_DELAYED_WORK(arch_rng_work, arch_rng_refill_buffer); - -bool s390_arch_random_generate(u8 *buf, unsigned int nbytes) -{ - /* max hunk is ARCH_RNG_BUF_SIZE */ - if (nbytes > ARCH_RNG_BUF_SIZE) - return false; - - /* lock rng buffer */ - if (!spin_trylock(&arch_rng_lock)) - return false; - - /* try to resolve the requested amount of bytes from the buffer */ - arch_rng_buf_idx -= nbytes; - if (arch_rng_buf_idx < ARCH_RNG_BUF_SIZE) { - memcpy(buf, arch_rng_buf + arch_rng_buf_idx, nbytes); - atomic64_add(nbytes, &s390_arch_random_counter); - spin_unlock(&arch_rng_lock); - return true; - } - - /* not enough bytes in rng buffer, refill is done asynchronously */ - spin_unlock(&arch_rng_lock); - - return false; -} -EXPORT_SYMBOL(s390_arch_random_generate); - -static void arch_rng_refill_buffer(struct work_struct *unused) -{ - unsigned int delay = ARCH_REFILL_TICKS; - - spin_lock(&arch_rng_lock); - if (arch_rng_buf_idx > ARCH_RNG_BUF_SIZE) { - /* buffer is exhausted and needs refill */ - u8 seed[ARCH_PRNG_SEED_SIZE]; - u8 prng_wa[240]; - /* fetch ARCH_PRNG_SEED_SIZE bytes of entropy */ - cpacf_trng(NULL, 0, seed, sizeof(seed)); - /* blow this entropy up to ARCH_RNG_BUF_SIZE with PRNG */ - memset(prng_wa, 0, sizeof(prng_wa)); - cpacf_prno(CPACF_PRNO_SHA512_DRNG_SEED, - &prng_wa, NULL, 0, seed, sizeof(seed)); - cpacf_prno(CPACF_PRNO_SHA512_DRNG_GEN, - &prng_wa, arch_rng_buf, ARCH_RNG_BUF_SIZE, NULL, 0); - arch_rng_buf_idx = ARCH_RNG_BUF_SIZE; - } - delay += (ARCH_REFILL_TICKS * arch_rng_buf_idx) / ARCH_RNG_BUF_SIZE; - spin_unlock(&arch_rng_lock); - - /* kick next check */ - queue_delayed_work(system_long_wq, &arch_rng_work, delay); -} - -static int __init s390_arch_random_init(void) -{ - /* all the needed PRNO subfunctions available ? */ - if (cpacf_query_func(CPACF_PRNO, CPACF_PRNO_TRNG) && - cpacf_query_func(CPACF_PRNO, CPACF_PRNO_SHA512_DRNG_GEN)) { - - /* alloc arch random working buffer */ - arch_rng_buf = kmalloc(ARCH_RNG_BUF_SIZE, GFP_KERNEL); - if (!arch_rng_buf) - return -ENOMEM; - - /* kick worker queue job to fill the random buffer */ - queue_delayed_work(system_long_wq, - &arch_rng_work, ARCH_REFILL_TICKS); - - /* enable arch random to the outside world */ - static_branch_enable(&s390_arch_random_available); - } - - return 0; -} -arch_initcall(s390_arch_random_init); --- a/arch/s390/include/asm/archrandom.h +++ b/arch/s390/include/asm/archrandom.h @@ -2,7 +2,7 @@ /* * Kernel interface for the s390 arch_random_* functions * - * Copyright IBM Corp. 2017 + * Copyright IBM Corp. 2017, 2020 * * Author: Harald Freudenberger freude@de.ibm.com * @@ -15,34 +15,37 @@

#include <linux/static_key.h> #include <linux/atomic.h> +#include <asm/cpacf.h>

DECLARE_STATIC_KEY_FALSE(s390_arch_random_available); extern atomic64_t s390_arch_random_counter;

-bool s390_arch_random_generate(u8 *buf, unsigned int nbytes); - -static inline bool arch_get_random_long(unsigned long *v) +static inline bool __must_check arch_get_random_long(unsigned long *v) { return false; }

-static inline bool arch_get_random_int(unsigned int *v) +static inline bool __must_check arch_get_random_int(unsigned int *v) { return false; }

-static inline bool arch_get_random_seed_long(unsigned long *v) +static inline bool __must_check arch_get_random_seed_long(unsigned long *v) { if (static_branch_likely(&s390_arch_random_available)) { - return s390_arch_random_generate((u8 *)v, sizeof(*v)); + cpacf_trng(NULL, 0, (u8 *)v, sizeof(*v)); + atomic64_add(sizeof(*v), &s390_arch_random_counter); + return true; } return false; }

-static inline bool arch_get_random_seed_int(unsigned int *v) +static inline bool __must_check arch_get_random_seed_int(unsigned int *v) { if (static_branch_likely(&s390_arch_random_available)) { - return s390_arch_random_generate((u8 *)v, sizeof(*v)); + cpacf_trng(NULL, 0, (u8 *)v, sizeof(*v)); + atomic64_add(sizeof(*v), &s390_arch_random_counter); + return true; } return false; } --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -1005,6 +1005,11 @@ static void __init setup_randomness(void if (stsi(vmms, 3, 2, 2) == 0 && vmms->count) add_device_randomness(&vmms->vm, sizeof(vmms->vm[0]) * vmms->count); memblock_free((unsigned long) vmms, PAGE_SIZE); + +#ifdef CONFIG_ARCH_RANDOM + if (cpacf_query_func(CPACF_PRNO, CPACF_PRNO_TRNG)) + static_branch_enable(&s390_arch_random_available); +#endif }

/*

From: Duoming Zhou duoming@zju.edu.cn

commit 9cc02ede696272c5271a401e4f27c262359bc2f6 upstream.

There are UAF bugs in rose_heartbeat_expiry(), rose_timer_expiry() and rose_idletimer_expiry(). The root cause is that del_timer() could not stop the timer handler that is running and the refcount of sock is not managed properly.

One of the UAF bugs is shown below:

(thread 1) | (thread 2) | rose_bind | rose_connect | rose_start_heartbeat rose_release | (wait a time) case ROSE_STATE_0 | rose_destroy_socket | rose_heartbeat_expiry rose_stop_heartbeat | sock_put(sk) | ... sock_put(sk) // FREE | | bh_lock_sock(sk) // USE

The sock is deallocated by sock_put() in rose_release() and then used by bh_lock_sock() in rose_heartbeat_expiry().

Although rose_destroy_socket() calls rose_stop_heartbeat(), it could not stop the timer that is running.

The KASAN report triggered by POC is shown below:

BUG: KASAN: use-after-free in _raw_spin_lock+0x5a/0x110 Write of size 4 at addr ffff88800ae59098 by task swapper/3/0 ... Call Trace: <IRQ> dump_stack_lvl+0xbf/0xee print_address_description+0x7b/0x440 print_report+0x101/0x230 ? irq_work_single+0xbb/0x140 ? _raw_spin_lock+0x5a/0x110 kasan_report+0xed/0x120 ? _raw_spin_lock+0x5a/0x110 kasan_check_range+0x2bd/0x2e0 _raw_spin_lock+0x5a/0x110 rose_heartbeat_expiry+0x39/0x370 ? rose_start_heartbeat+0xb0/0xb0 call_timer_fn+0x2d/0x1c0 ? rose_start_heartbeat+0xb0/0xb0 expire_timers+0x1f3/0x320 __run_timers+0x3ff/0x4d0 run_timer_softirq+0x41/0x80 __do_softirq+0x233/0x544 irq_exit_rcu+0x41/0xa0 sysvec_apic_timer_interrupt+0x8c/0xb0 </IRQ> <TASK> asm_sysvec_apic_timer_interrupt+0x1b/0x20 RIP: 0010:default_idle+0xb/0x10 RSP: 0018:ffffc9000012fea0 EFLAGS: 00000202 RAX: 000000000000bcae RBX: ffff888006660f00 RCX: 000000000000bcae RDX: 0000000000000001 RSI: ffffffff843a11c0 RDI: ffffffff843a1180 RBP: dffffc0000000000 R08: dffffc0000000000 R09: ffffed100da36d46 R10: dfffe9100da36d47 R11: ffffffff83cf0950 R12: 0000000000000000 R13: 1ffff11000ccc1e0 R14: ffffffff8542af28 R15: dffffc0000000000 ... Allocated by task 146: __kasan_kmalloc+0xc4/0xf0 sk_prot_alloc+0xdd/0x1a0 sk_alloc+0x2d/0x4e0 rose_create+0x7b/0x330 __sock_create+0x2dd/0x640 __sys_socket+0xc7/0x270 __x64_sys_socket+0x71/0x80 do_syscall_64+0x43/0x90 entry_SYSCALL_64_after_hwframe+0x46/0xb0

Freed by task 152: kasan_set_track+0x4c/0x70 kasan_set_free_info+0x1f/0x40 ____kasan_slab_free+0x124/0x190 kfree+0xd3/0x270 __sk_destruct+0x314/0x460 rose_release+0x2fa/0x3b0 sock_close+0xcb/0x230 __fput+0x2d9/0x650 task_work_run+0xd6/0x160 exit_to_user_mode_loop+0xc7/0xd0 exit_to_user_mode_prepare+0x4e/0x80 syscall_exit_to_user_mode+0x20/0x40 do_syscall_64+0x4f/0x90 entry_SYSCALL_64_after_hwframe+0x46/0xb0

This patch adds refcount of sock when we use functions such as rose_start_heartbeat() and so on to start timer, and decreases the refcount of sock when timer is finished or deleted by functions such as rose_stop_heartbeat() and so on. As a result, the UAF bugs could be mitigated.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Duoming Zhou duoming@zju.edu.cn Tested-by: Duoming Zhou duoming@zju.edu.cn Link: https://lore.kernel.org/r/20220629002640.5693-1-duoming@zju.edu.cn Signed-off-by: Paolo Abeni pabeni@redhat.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/rose/rose_timer.c | 34 +++++++++++++++++++--------------- 1 file changed, 19 insertions(+), 15 deletions(-)

--- a/net/rose/rose_timer.c +++ b/net/rose/rose_timer.c @@ -31,89 +31,89 @@ static void rose_idletimer_expiry(struct

void rose_start_heartbeat(struct sock *sk) { - del_timer(&sk->sk_timer); + sk_stop_timer(sk, &sk->sk_timer);

sk->sk_timer.function = rose_heartbeat_expiry; sk->sk_timer.expires = jiffies + 5 * HZ;

- add_timer(&sk->sk_timer); + sk_reset_timer(sk, &sk->sk_timer, sk->sk_timer.expires); }

void rose_start_t1timer(struct sock *sk) { struct rose_sock *rose = rose_sk(sk);

- del_timer(&rose->timer); + sk_stop_timer(sk, &rose->timer);

rose->timer.function = rose_timer_expiry; rose->timer.expires = jiffies + rose->t1;

- add_timer(&rose->timer); + sk_reset_timer(sk, &rose->timer, rose->timer.expires); }

void rose_start_t2timer(struct sock *sk) { struct rose_sock *rose = rose_sk(sk);

- del_timer(&rose->timer); + sk_stop_timer(sk, &rose->timer);

rose->timer.function = rose_timer_expiry; rose->timer.expires = jiffies + rose->t2;

- add_timer(&rose->timer); + sk_reset_timer(sk, &rose->timer, rose->timer.expires); }

void rose_start_t3timer(struct sock *sk) { struct rose_sock *rose = rose_sk(sk);

- del_timer(&rose->timer); + sk_stop_timer(sk, &rose->timer);

rose->timer.function = rose_timer_expiry; rose->timer.expires = jiffies + rose->t3;

- add_timer(&rose->timer); + sk_reset_timer(sk, &rose->timer, rose->timer.expires); }

void rose_start_hbtimer(struct sock *sk) { struct rose_sock *rose = rose_sk(sk);

- del_timer(&rose->timer); + sk_stop_timer(sk, &rose->timer);

rose->timer.function = rose_timer_expiry; rose->timer.expires = jiffies + rose->hb;

- add_timer(&rose->timer); + sk_reset_timer(sk, &rose->timer, rose->timer.expires); }

void rose_start_idletimer(struct sock *sk) { struct rose_sock *rose = rose_sk(sk);

- del_timer(&rose->idletimer); + sk_stop_timer(sk, &rose->idletimer);

if (rose->idle > 0) { rose->idletimer.function = rose_idletimer_expiry; rose->idletimer.expires = jiffies + rose->idle;

- add_timer(&rose->idletimer); + sk_reset_timer(sk, &rose->idletimer, rose->idletimer.expires); } }

void rose_stop_heartbeat(struct sock *sk) { - del_timer(&sk->sk_timer); + sk_stop_timer(sk, &sk->sk_timer); }

void rose_stop_timer(struct sock *sk) { - del_timer(&rose_sk(sk)->timer); + sk_stop_timer(sk, &rose_sk(sk)->timer); }

void rose_stop_idletimer(struct sock *sk) { - del_timer(&rose_sk(sk)->idletimer); + sk_stop_timer(sk, &rose_sk(sk)->idletimer); }

static void rose_heartbeat_expiry(struct timer_list *t) @@ -130,6 +130,7 @@ static void rose_heartbeat_expiry(struct (sk->sk_state == TCP_LISTEN && sock_flag(sk, SOCK_DEAD))) { bh_unlock_sock(sk); rose_destroy_socket(sk); + sock_put(sk); return; } break; @@ -152,6 +153,7 @@ static void rose_heartbeat_expiry(struct

rose_start_heartbeat(sk); bh_unlock_sock(sk); + sock_put(sk); }

static void rose_timer_expiry(struct timer_list *t) @@ -181,6 +183,7 @@ static void rose_timer_expiry(struct tim break; } bh_unlock_sock(sk); + sock_put(sk); }

static void rose_idletimer_expiry(struct timer_list *t) @@ -205,4 +208,5 @@ static void rose_idletimer_expiry(struct sock_set_flag(sk, SOCK_DEAD); } bh_unlock_sock(sk); + sock_put(sk); }

From: Jason Wang jasowang@redhat.com

commit 50c0ada627f56c92f5953a8bf9158b045ad026a1 upstream.

We currently call virtio_device_ready() after netdev registration. Since ndo_open() can be called immediately after register_netdev, this means there exists a race between ndo_open() and virtio_device_ready(): the driver may start to use the device before DRIVER_OK which violates the spec.

Fix this by switching to use register_netdevice() and protect the virtio_device_ready() with rtnl_lock() to make sure ndo_open() can only be called after virtio_device_ready().

Fixes: 4baf1e33d0842 ("virtio_net: enable VQs early") Signed-off-by: Jason Wang jasowang@redhat.com Message-Id: 20220617072949.30734-1-jasowang@redhat.com Signed-off-by: Michael S. Tsirkin mst@redhat.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/virtio_net.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-)

--- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -3219,14 +3219,20 @@ static int virtnet_probe(struct virtio_d } }

- err = register_netdev(dev); + /* serialize netdev register + virtio_device_ready() with ndo_open() */ + rtnl_lock(); + + err = register_netdevice(dev); if (err) { pr_debug("virtio_net: registering device failed\n"); + rtnl_unlock(); goto free_failover; }

virtio_device_ready(vdev);

+ rtnl_unlock(); + err = virtnet_cpu_notif_add(vi); if (err) { pr_debug("virtio_net: registering cpu notifier failed\n");

From: Jakub Kicinski kuba@kernel.org

commit 3b9bc84d311104906d2b4995a9a02d7b7ddab2db upstream.

Syzbot found a race between tun file and device destruction. NAPIs live in struct tun_file which can get destroyed before the netdev so we have to del them explicitly. The current code is missing deleting the NAPI if the queue was detached first.

Fixes: 943170998b20 ("tun: enable NAPI for TUN/TAP driver") Reported-by: syzbot+b75c138e9286ac742647@syzkaller.appspotmail.com Link: https://lore.kernel.org/r/20220623042039.2274708-1-kuba@kernel.org Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/tun.c | 1 + 1 file changed, 1 insertion(+)

--- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -783,6 +783,7 @@ static void tun_detach_all(struct net_de sock_put(&tfile->sk); } list_for_each_entry_safe(tfile, tmp, &tun->disabled, next) { + tun_napi_del(tfile); tun_enable_queue(tfile); tun_queue_purge(tfile); xdp_rxq_info_unreg(&tfile->xdp_rxq);

From: Kamal Heib kamalheib1@gmail.com

commit 118f767413ada4eef7825fbd4af7c0866f883441 upstream.

Make sure to save the passed QP timeout attribute when the QP gets modified, so when calling query QP the right value is reported and not the converted value that is required by the firmware. This issue was found while running the pyverbs tests.

Fixes: cecbcddf6461 ("qedr: Add support for QP verbs") Link: https://lore.kernel.org/r/20220525132029.84813-1-kamalheib1@gmail.com Signed-off-by: Kamal Heib kamalheib1@gmail.com Acked-by: Michal Kalderon michal.kalderon@marvell.com Signed-off-by: Leon Romanovsky leonro@nvidia.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/infiniband/hw/qedr/qedr.h | 1 + drivers/infiniband/hw/qedr/verbs.c | 4 +++- 2 files changed, 4 insertions(+), 1 deletion(-)

--- a/drivers/infiniband/hw/qedr/qedr.h +++ b/drivers/infiniband/hw/qedr/qedr.h @@ -416,6 +416,7 @@ struct qedr_qp { u32 sq_psn; u32 qkey; u32 dest_qp_num; + u8 timeout;

/* Relevant to qps created from kernel space only (ULPs) */ u8 prev_wqe_size; --- a/drivers/infiniband/hw/qedr/verbs.c +++ b/drivers/infiniband/hw/qedr/verbs.c @@ -2259,6 +2259,8 @@ int qedr_modify_qp(struct ib_qp *ibqp, s 1 << max_t(int, attr->timeout - 8, 0); else qp_params.ack_timeout = 0; + + qp->timeout = attr->timeout; }

if (attr_mask & IB_QP_RETRY_CNT) { @@ -2418,7 +2420,7 @@ int qedr_query_qp(struct ib_qp *ibqp, rdma_ah_set_dgid_raw(&qp_attr->ah_attr, &params.dgid.bytes[0]); rdma_ah_set_port_num(&qp_attr->ah_attr, 1); rdma_ah_set_sl(&qp_attr->ah_attr, 0); - qp_attr->timeout = params.timeout; + qp_attr->timeout = qp->timeout; qp_attr->rnr_retry = params.rnr_retry; qp_attr->retry_cnt = params.retry_cnt; qp_attr->min_rnr_timer = params.min_rnr_nak_timer;

From: Oliver Neukum oneukum@suse.com

commit e65af5403e462ccd7dff6a045a886c64da598c2e upstream.

usbnet provides some helper functions that are also used in the context of reset() operations. During a reset the other drivers on a device are unable to operate. As that can be block drivers, a driver for another interface cannot use paging in its memory allocations without risking a deadlock. Use GFP_NOIO in the helpers.

Fixes: 877bd862f32b8 ("usbnet: introduce usbnet 3 command helpers") Signed-off-by: Oliver Neukum oneukum@suse.com Link: https://lore.kernel.org/r/20220628093517.7469-1-oneukum@suse.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/usb/usbnet.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

--- a/drivers/net/usb/usbnet.c +++ b/drivers/net/usb/usbnet.c @@ -1987,7 +1987,7 @@ static int __usbnet_read_cmd(struct usbn cmd, reqtype, value, index, size);

if (size) { - buf = kmalloc(size, GFP_KERNEL); + buf = kmalloc(size, GFP_NOIO); if (!buf) goto out; } @@ -2019,7 +2019,7 @@ static int __usbnet_write_cmd(struct usb cmd, reqtype, value, index, size);

if (data) { - buf = kmemdup(data, size, GFP_KERNEL); + buf = kmemdup(data, size, GFP_NOIO); if (!buf) goto out; } else {

From: Jason Wang jasowang@redhat.com

commit 11a37eb66812ce6a06b79223ad530eb0e1d7294d upstream.

We currently depend on probe() calling virtio_device_ready() - which happens after netdev registration. Since ndo_open() can be called immediately after register_netdev, this means there exists a race between ndo_open() and virtio_device_ready(): the driver may start to use the device (e.g. TX) before DRIVER_OK which violates the spec.

Fix this by switching to use register_netdevice() and protect the virtio_device_ready() with rtnl_lock() to make sure ndo_open() can only be called after virtio_device_ready().

Fixes: 0d2e1a2926b18 ("caif_virtio: Introduce caif over virtio") Signed-off-by: Jason Wang jasowang@redhat.com Message-Id: 20220620051115.3142-3-jasowang@redhat.com Signed-off-by: Michael S. Tsirkin mst@redhat.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/caif/caif_virtio.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-)

--- a/drivers/net/caif/caif_virtio.c +++ b/drivers/net/caif/caif_virtio.c @@ -723,13 +723,21 @@ static int cfv_probe(struct virtio_devic /* Carrier is off until netdevice is opened */ netif_carrier_off(netdev);

+ /* serialize netdev register + virtio_device_ready() with ndo_open() */ + rtnl_lock(); + /* register Netdev */ - err = register_netdev(netdev); + err = register_netdevice(netdev); if (err) { + rtnl_unlock(); dev_err(&vdev->dev, "Unable to register netdev (%d)\n", err); goto err; }

+ virtio_device_ready(vdev); + + rtnl_unlock(); + debugfs_init(cfv);

return 0;

From: Masahiro Yamada masahiroy@kernel.org

commit 25deecb21c18ee29e3be8ac6177b2a9504c33d2d upstream.

Since commit 4c0f032d4963 ("s390/purgatory: Omit use of bin2c"), s390 builds the purgatory without using bin2c.

Remove 'select BUILD_BIN2C' to avoid the unneeded build of bin2c.

Fixes: 4c0f032d4963 ("s390/purgatory: Omit use of bin2c") Signed-off-by: Masahiro Yamada masahiroy@kernel.org Link: https://lore.kernel.org/r/20220613170902.1775211-1-masahiroy@kernel.org Signed-off-by: Alexander Gordeev agordeev@linux.ibm.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/s390/Kconfig | 1 - 1 file changed, 1 deletion(-)

--- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -541,7 +541,6 @@ config KEXEC config KEXEC_FILE bool "kexec file based system call" select KEXEC_CORE - select BUILD_BIN2C depends on CRYPTO depends on CRYPTO_SHA256 depends on CRYPTO_SHA256_S390

From: Victor Nogueira victor@mojatatu.com

commit 76b39b94382f9e0a639e1c70c3253de248cc4c83 upstream.

If during an action flush operation one of the actions is still being referenced, the flush operation is aborted and the kernel returns to user space with an error. However, if the kernel was able to flush, for example, 3 actions and failed on the fourth, the kernel will not notify user space that it deleted 3 actions before failing.

This patch fixes that behaviour by notifying user space of how many actions were deleted before flush failed and by setting extack with a message describing what happened.

Fixes: 55334a5db5cd ("net_sched: act: refuse to remove bound action outside") Signed-off-by: Victor Nogueira victor@mojatatu.com Acked-by: Jamal Hadi Salim jhs@mojatatu.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/sched/act_api.c | 22 ++++++++++++++-------- 1 file changed, 14 insertions(+), 8 deletions(-)

--- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -287,7 +287,8 @@ static int tcf_idr_release_unsafe(struct }

static int tcf_del_walker(struct tcf_idrinfo *idrinfo, struct sk_buff *skb, - const struct tc_action_ops *ops) + const struct tc_action_ops *ops, + struct netlink_ext_ack *extack) { struct nlattr *nest; int n_i = 0; @@ -303,20 +304,25 @@ static int tcf_del_walker(struct tcf_idr if (nla_put_string(skb, TCA_KIND, ops->kind)) goto nla_put_failure;

+ ret = 0; mutex_lock(&idrinfo->lock); idr_for_each_entry_ul(idr, p, tmp, id) { if (IS_ERR(p)) continue; ret = tcf_idr_release_unsafe(p); - if (ret == ACT_P_DELETED) { + if (ret == ACT_P_DELETED) module_put(ops->owner); - n_i++; - } else if (ret < 0) { - mutex_unlock(&idrinfo->lock); - goto nla_put_failure; - } + else if (ret < 0) + break; + n_i++; } mutex_unlock(&idrinfo->lock); + if (ret < 0) { + if (n_i) + NL_SET_ERR_MSG(extack, "Unable to flush all TC actions"); + else + goto nla_put_failure; + }

ret = nla_put_u32(skb, TCA_FCNT, n_i); if (ret) @@ -337,7 +343,7 @@ int tcf_generic_walker(struct tc_action_ struct tcf_idrinfo *idrinfo = tn->idrinfo;

if (type == RTM_DELACTION) { - return tcf_del_walker(idrinfo, skb, ops); + return tcf_del_walker(idrinfo, skb, ops, extack); } else if (type == RTM_GETACTION) { return tcf_dump_walker(idrinfo, skb, cb); } else {

From: Yevhen Orlov yevhen.orlov@plvision.eu

commit 050133e1aa2cb49bb17be847d48a4431598ef562 upstream.

commit 0622cab0341c ("bonding: fix 802.3ad aggregator reselection"), resolve case, when there is several aggregation groups in the same bond. bond_3ad_unbind_slave will invalidate (clear) aggregator when __agg_active_ports return zero. So, ad_clear_agg can be executed even, when num_of_ports!=0. Than bond_3ad_unbind_slave can be executed again for, previously cleared aggregator. NOTE: at this time bond_3ad_unbind_slave will not update slave ports list, because lag_ports==NULL. So, here we got slave ports, pointing to freed aggregator memory.

Fix with checking actual number of ports in group (as was before commit 0622cab0341c ("bonding: fix 802.3ad aggregator reselection") ), before ad_clear_agg().

The KASAN logs are as follows:

[ 767.617392] ================================================================== [ 767.630776] BUG: KASAN: use-after-free in bond_3ad_state_machine_handler+0x13dc/0x1470 [ 767.638764] Read of size 2 at addr ffff00011ba9d430 by task kworker/u8:7/767 [ 767.647361] CPU: 3 PID: 767 Comm: kworker/u8:7 Tainted: G O 5.15.11 #15 [ 767.655329] Hardware name: DNI AmazonGo1 A7040 board (DT) [ 767.660760] Workqueue: lacp_1 bond_3ad_state_machine_handler [ 767.666468] Call trace: [ 767.668930] dump_backtrace+0x0/0x2d0 [ 767.672625] show_stack+0x24/0x30 [ 767.675965] dump_stack_lvl+0x68/0x84 [ 767.679659] print_address_description.constprop.0+0x74/0x2b8 [ 767.685451] kasan_report+0x1f0/0x260 [ 767.689148] __asan_load2+0x94/0xd0 [ 767.692667] bond_3ad_state_machine_handler+0x13dc/0x1470

Fixes: 0622cab0341c ("bonding: fix 802.3ad aggregator reselection") Co-developed-by: Maksym Glubokiy maksym.glubokiy@plvision.eu Signed-off-by: Maksym Glubokiy maksym.glubokiy@plvision.eu Signed-off-by: Yevhen Orlov yevhen.orlov@plvision.eu Acked-by: Jay Vosburgh jay.vosburgh@canonical.com Link: https://lore.kernel.org/r/20220629012914.361-1-yevhen.orlov@plvision.eu Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/bonding/bond_3ad.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

--- a/drivers/net/bonding/bond_3ad.c +++ b/drivers/net/bonding/bond_3ad.c @@ -2218,7 +2218,8 @@ void bond_3ad_unbind_slave(struct slave temp_aggregator->num_of_ports--; if (__agg_active_ports(temp_aggregator) == 0) { select_new_active_agg = temp_aggregator->is_active; - ad_clear_agg(temp_aggregator); + if (temp_aggregator->num_of_ports == 0) + ad_clear_agg(temp_aggregator); if (select_new_active_agg) { slave_info(bond->dev, slave->dev, "Removing an active aggregator\n"); /* select new active aggregator */

From: Michael Walle michael@walle.cc

commit eddd95b9423946aaacb55cac6a9b2cea8ab944fc upstream.

There are packets which doesn't have a payload. In that case, the second i2c_master_read() will have a zero length. But because the NFC controller doesn't have any data left, it will NACK the I2C read and -ENXIO will be returned. In case there is no payload, just skip the second i2c master read.

Fixes: 6be88670fc59 ("NFC: nxp-nci_i2c: Add I2C support to NXP NCI driver") Signed-off-by: Michael Walle michael@walle.cc Reviewed-by: Krzysztof Kozlowski krzysztof.kozlowski@linaro.org Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/nfc/nxp-nci/i2c.c | 3 +++ 1 file changed, 3 insertions(+)

--- a/drivers/nfc/nxp-nci/i2c.c +++ b/drivers/nfc/nxp-nci/i2c.c @@ -162,6 +162,9 @@ static int nxp_nci_i2c_nci_read(struct n

skb_put_data(*skb, (void *)&header, NCI_CTRL_HDR_SIZE);

+ if (!header.plen) + return 0; + r = i2c_master_recv(client, skb_put(*skb, header.plen), header.plen); if (r != header.plen) { nfc_err(&client->dev,

From: Demi Marie Obenour demi@invisiblethingslab.com

commit dbe97cff7dd9f0f75c524afdd55ad46be3d15295 upstream.

unmap_grant_pages() currently waits for the pages to no longer be used. In https://github.com/QubesOS/qubes-issues/issues/7481, this lead to a deadlock against i915: i915 was waiting for gntdev's MMU notifier to finish, while gntdev was waiting for i915 to free its pages. I also believe this is responsible for various deadlocks I have experienced in the past.

Avoid these problems by making unmap_grant_pages async. This requires making it return void, as any errors will not be available when the function returns. Fortunately, the only use of the return value is a WARN_ON(), which can be replaced by a WARN_ON when the error is detected. Additionally, a failed call will not prevent further calls from being made, but this is harmless.

Because unmap_grant_pages is now async, the grant handle will be sent to INVALID_GRANT_HANDLE too late to prevent multiple unmaps of the same handle. Instead, a separate bool array is allocated for this purpose. This wastes memory, but stuffing this information in padding bytes is too fragile. Furthermore, it is necessary to grab a reference to the map before making the asynchronous call, and release the reference when the call returns.

It is also necessary to guard against reentrancy in gntdev_map_put(), and to handle the case where userspace tries to map a mapping whose contents have not all been freed yet.

Fixes: 745282256c75 ("xen/gntdev: safely unmap grants in case they are still in use") Cc: stable@vger.kernel.org Signed-off-by: Demi Marie Obenour demi@invisiblethingslab.com Reviewed-by: Juergen Gross jgross@suse.com Link: https://lore.kernel.org/r/20220622022726.2538-1-demi@invisiblethingslab.com Signed-off-by: Juergen Gross jgross@suse.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/xen/gntdev-common.h | 8 ++ drivers/xen/gntdev.c | 147 ++++++++++++++++++++++++++++++-------------- 2 files changed, 110 insertions(+), 45 deletions(-)

--- a/drivers/xen/gntdev-common.h +++ b/drivers/xen/gntdev-common.h @@ -15,6 +15,8 @@ #include <linux/mman.h> #include <linux/mmu_notifier.h> #include <linux/types.h> +#include <xen/interface/event_channel.h> +#include <xen/grant_table.h>

struct gntdev_dmabuf_priv;

@@ -61,6 +63,7 @@ struct gntdev_grant_map { struct gnttab_unmap_grant_ref *unmap_ops; struct gnttab_map_grant_ref *kmap_ops; struct gnttab_unmap_grant_ref *kunmap_ops; + bool *being_removed; struct page **pages; unsigned long pages_vm_start;

@@ -78,6 +81,11 @@ struct gntdev_grant_map { /* Needed to avoid allocation in gnttab_dma_free_pages(). */ xen_pfn_t *frames; #endif + + /* Number of live grants */ + atomic_t live_grants; + /* Needed to avoid allocation in __unmap_grant_pages */ + struct gntab_unmap_queue_data unmap_data; };

struct gntdev_grant_map *gntdev_alloc_map(struct gntdev_priv *priv, int count, --- a/drivers/xen/gntdev.c +++ b/drivers/xen/gntdev.c @@ -35,6 +35,7 @@ #include <linux/slab.h> #include <linux/highmem.h> #include <linux/refcount.h> +#include <linux/workqueue.h>

#include <xen/xen.h> #include <xen/grant_table.h> @@ -62,11 +63,12 @@ MODULE_PARM_DESC(limit, "Maximum number

static atomic_t pages_mapped = ATOMIC_INIT(0);

+/* True in PV mode, false otherwise */ static int use_ptemod; #define populate_freeable_maps use_ptemod

-static int unmap_grant_pages(struct gntdev_grant_map *map, - int offset, int pages); +static void unmap_grant_pages(struct gntdev_grant_map *map, + int offset, int pages);

static struct miscdevice gntdev_miscdev;

@@ -123,6 +125,7 @@ static void gntdev_free_map(struct gntde kfree(map->unmap_ops); kfree(map->kmap_ops); kfree(map->kunmap_ops); + kfree(map->being_removed); kfree(map); }

@@ -142,12 +145,15 @@ struct gntdev_grant_map *gntdev_alloc_ma add->kmap_ops = kcalloc(count, sizeof(add->kmap_ops[0]), GFP_KERNEL); add->kunmap_ops = kcalloc(count, sizeof(add->kunmap_ops[0]), GFP_KERNEL); add->pages = kcalloc(count, sizeof(add->pages[0]), GFP_KERNEL); + add->being_removed = + kcalloc(count, sizeof(add->being_removed[0]), GFP_KERNEL); if (NULL == add->grants || NULL == add->map_ops || NULL == add->unmap_ops || NULL == add->kmap_ops || NULL == add->kunmap_ops || - NULL == add->pages) + NULL == add->pages || + NULL == add->being_removed) goto err;

#ifdef CONFIG_XEN_GRANT_DMA_ALLOC @@ -243,6 +249,35 @@ void gntdev_put_map(struct gntdev_priv * return;

atomic_sub(map->count, &pages_mapped); + if (map->pages && !use_ptemod) { + /* + * Increment the reference count. This ensures that the + * subsequent call to unmap_grant_pages() will not wind up + * re-entering itself. It *can* wind up calling + * gntdev_put_map() recursively, but such calls will be with a + * reference count greater than 1, so they will return before + * this code is reached. The recursion depth is thus limited to + * 1. Do NOT use refcount_inc() here, as it will detect that + * the reference count is zero and WARN(). + */ + refcount_set(&map->users, 1); + + /* + * Unmap the grants. This may or may not be asynchronous, so it + * is possible that the reference count is 1 on return, but it + * could also be greater than 1. + */ + unmap_grant_pages(map, 0, map->count); + + /* Check if the memory now needs to be freed */ + if (!refcount_dec_and_test(&map->users)) + return; + + /* + * All pages have been returned to the hypervisor, so free the + * map. + */ + }

if (map->notify.flags & UNMAP_NOTIFY_SEND_EVENT) { notify_remote_via_evtchn(map->notify.event); @@ -298,6 +333,7 @@ static int set_grant_ptes_as_special(pte

int gntdev_map_grant_pages(struct gntdev_grant_map *map) { + size_t alloced = 0; int i, err = 0;

if (!use_ptemod) { @@ -346,87 +382,109 @@ int gntdev_map_grant_pages(struct gntdev map->pages, map->count);

for (i = 0; i < map->count; i++) { - if (map->map_ops[i].status == GNTST_okay) + if (map->map_ops[i].status == GNTST_okay) { map->unmap_ops[i].handle = map->map_ops[i].handle; - else if (!err) + if (!use_ptemod) + alloced++; + } else if (!err) err = -EINVAL;

if (map->flags & GNTMAP_device_map) map->unmap_ops[i].dev_bus_addr = map->map_ops[i].dev_bus_addr;

if (use_ptemod) { - if (map->kmap_ops[i].status == GNTST_okay) + if (map->kmap_ops[i].status == GNTST_okay) { + if (map->map_ops[i].status == GNTST_okay) + alloced++; map->kunmap_ops[i].handle = map->kmap_ops[i].handle; - else if (!err) + } else if (!err) err = -EINVAL; } } + atomic_add(alloced, &map->live_grants); return err; }

-static int __unmap_grant_pages(struct gntdev_grant_map *map, int offset, - int pages) +static void __unmap_grant_pages_done(int result, + struct gntab_unmap_queue_data *data) { - int i, err = 0; - struct gntab_unmap_queue_data unmap_data; + unsigned int i; + struct gntdev_grant_map *map = data->data; + unsigned int offset = data->unmap_ops - map->unmap_ops; + + for (i = 0; i < data->count; i++) { + WARN_ON(map->unmap_ops[offset+i].status); + pr_debug("unmap handle=%d st=%d\n", + map->unmap_ops[offset+i].handle, + map->unmap_ops[offset+i].status); + map->unmap_ops[offset+i].handle = -1; + } + /* + * Decrease the live-grant counter. This must happen after the loop to + * prevent premature reuse of the grants by gnttab_mmap(). + */ + atomic_sub(data->count, &map->live_grants);

+ /* Release reference taken by __unmap_grant_pages */ + gntdev_put_map(NULL, map); +} + +static void __unmap_grant_pages(struct gntdev_grant_map *map, int offset, + int pages) +{ if (map->notify.flags & UNMAP_NOTIFY_CLEAR_BYTE) { int pgno = (map->notify.addr >> PAGE_SHIFT); + if (pgno >= offset && pgno < offset + pages) { /* No need for kmap, pages are in lowmem */ uint8_t *tmp = pfn_to_kaddr(page_to_pfn(map->pages[pgno])); + tmp[map->notify.addr & (PAGE_SIZE-1)] = 0; map->notify.flags &= ~UNMAP_NOTIFY_CLEAR_BYTE; } }

- unmap_data.unmap_ops = map->unmap_ops + offset; - unmap_data.kunmap_ops = use_ptemod ? map->kunmap_ops + offset : NULL; - unmap_data.pages = map->pages + offset; - unmap_data.count = pages; + map->unmap_data.unmap_ops = map->unmap_ops + offset; + map->unmap_data.kunmap_ops = use_ptemod ? map->kunmap_ops + offset : NULL; + map->unmap_data.pages = map->pages + offset; + map->unmap_data.count = pages; + map->unmap_data.done = __unmap_grant_pages_done; + map->unmap_data.data = map; + refcount_inc(&map->users); /* to keep map alive during async call below */

- err = gnttab_unmap_refs_sync(&unmap_data); - if (err) - return err; - - for (i = 0; i < pages; i++) { - if (map->unmap_ops[offset+i].status) - err = -EINVAL; - pr_debug("unmap handle=%d st=%d\n", - map->unmap_ops[offset+i].handle, - map->unmap_ops[offset+i].status); - map->unmap_ops[offset+i].handle = -1; - } - return err; + gnttab_unmap_refs_async(&map->unmap_data); }

-static int unmap_grant_pages(struct gntdev_grant_map *map, int offset, - int pages) +static void unmap_grant_pages(struct gntdev_grant_map *map, int offset, + int pages) { - int range, err = 0; + int range; + + if (atomic_read(&map->live_grants) == 0) + return; /* Nothing to do */

pr_debug("unmap %d+%d [%d+%d]\n", map->index, map->count, offset, pages);

/* It is possible the requested range will have a "hole" where we * already unmapped some of the grants. Only unmap valid ranges. */ - while (pages && !err) { - while (pages && map->unmap_ops[offset].handle == -1) { + while (pages) { + while (pages && map->being_removed[offset]) { offset++; pages--; } range = 0; while (range < pages) { - if (map->unmap_ops[offset+range].handle == -1) + if (map->being_removed[offset + range]) break; + map->being_removed[offset + range] = true; range++; } - err = __unmap_grant_pages(map, offset, range); + if (range) + __unmap_grant_pages(map, offset, range); offset += range; pages -= range; } - - return err; }

/* ------------------------------------------------------------------ */ @@ -496,7 +554,6 @@ static int unmap_if_in_range(struct gntd bool blockable) { unsigned long mstart, mend; - int err;

if (!in_range(map, start, end)) return 0; @@ -510,10 +567,9 @@ static int unmap_if_in_range(struct gntd map->index, map->count, map->vma->vm_start, map->vma->vm_end, start, end, mstart, mend); - err = unmap_grant_pages(map, + unmap_grant_pages(map, (mstart - map->vma->vm_start) >> PAGE_SHIFT, (mend - mstart) >> PAGE_SHIFT); - WARN_ON(err);

return 0; } @@ -554,7 +610,6 @@ static void mn_release(struct mmu_notifi { struct gntdev_priv *priv = container_of(mn, struct gntdev_priv, mn); struct gntdev_grant_map *map; - int err;

mutex_lock(&priv->lock); list_for_each_entry(map, &priv->maps, next) { @@ -563,8 +618,7 @@ static void mn_release(struct mmu_notifi pr_debug("map %d+%d (%lx %lx)\n", map->index, map->count, map->vma->vm_start, map->vma->vm_end); - err = unmap_grant_pages(map, /* offset */ 0, map->count); - WARN_ON(err); + unmap_grant_pages(map, /* offset */ 0, map->count); } list_for_each_entry(map, &priv->freeable_maps, next) { if (!map->vma) @@ -572,8 +626,7 @@ static void mn_release(struct mmu_notifi pr_debug("map %d+%d (%lx %lx)\n", map->index, map->count, map->vma->vm_start, map->vma->vm_end); - err = unmap_grant_pages(map, /* offset */ 0, map->count); - WARN_ON(err); + unmap_grant_pages(map, /* offset */ 0, map->count); } mutex_unlock(&priv->lock); } @@ -1102,6 +1155,10 @@ static int gntdev_mmap(struct file *flip goto unlock_out; }

+ if (atomic_read(&map->live_grants)) { + err = -EAGAIN; + goto unlock_out; + } refcount_inc(&map->users);

vma->vm_ops = &gntdev_vmops;

From: Doug Berger opendmb@gmail.com

commit 7c97bc0128b2eecc703106112679a69d446d1a12 upstream.

The pause settings reported by the PHY should also be applied to the GMII port status override otherwise the switch will not generate pause frames towards the link partner despite the advertisement saying otherwise.

Fixes: 246d7f773c13 ("net: dsa: add Broadcom SF2 switch driver") Signed-off-by: Doug Berger opendmb@gmail.com Signed-off-by: Florian Fainelli f.fainelli@gmail.com Link: https://lore.kernel.org/r/20220623030204.1966851-1-f.fainelli@gmail.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/dsa/bcm_sf2.c | 5 +++++ 1 file changed, 5 insertions(+)

--- a/drivers/net/dsa/bcm_sf2.c +++ b/drivers/net/dsa/bcm_sf2.c @@ -602,6 +602,11 @@ force_link: reg |= LINK_STS; if (state->duplex == DUPLEX_FULL) reg |= DUPLX_MODE; + if (state->pause & MLO_PAUSE_TXRX_MASK) { + if (state->pause & MLO_PAUSE_TX) + reg |= TXFLOW_CNTL; + reg |= RXFLOW_CNTL; + }

core_writel(priv, reg, offset); }

From: katrinzhou katrinzhou@tencent.com

commit adabdd8f6acabc0c3fdbba2e7f5a2edd9c5ef22d upstream.

When kcalloc fails, ipip6_tunnel_get_prl() should return -ENOMEM. Move the position of label "out" to return correctly.

Addresses-Coverity: ("Unused value") Fixes: 300aaeeaab5f ("[IPV6] SIT: Add SIOCGETPRL ioctl to get/dump PRL.") Signed-off-by: katrinzhou katrinzhou@tencent.com Reviewed-by: Eric Dumazetedumazet@google.com Reviewed-by: David Ahern dsahern@kernel.org Link: https://lore.kernel.org/r/20220628035030.1039171-1-zys.zljxml@gmail.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/ipv6/sit.c | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-)

--- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -310,8 +310,6 @@ static int ipip6_tunnel_get_prl(struct i kcalloc(cmax, sizeof(*kp), GFP_KERNEL | __GFP_NOWARN) : NULL;

- rcu_read_lock(); - ca = min(t->prl_count, cmax);

if (!kp) { @@ -327,7 +325,7 @@ static int ipip6_tunnel_get_prl(struct i } }

- c = 0; + rcu_read_lock(); for_each_prl_rcu(t->prl) { if (c >= cmax) break; @@ -339,7 +337,7 @@ static int ipip6_tunnel_get_prl(struct i if (kprl.addr != htonl(INADDR_ANY)) break; } -out: + rcu_read_unlock();

len = sizeof(*kp) * c; @@ -348,7 +346,7 @@ out: ret = -EFAULT;

kfree(kp); - +out: return ret; }

From: Shuah Khan skhan@linuxfoundation.org

commit 07ad4f7629d4802ff0d962b0ac23ea6445964e2a upstream.

ARRAY_SIZE is defined in several selftests. Remove definitions from individual test files and include header file for the define instead. ARRAY_SIZE define is added in a separate patch to prepare for this change.

Remove ARRAY_SIZE from rseq tests and pickup the one defined in kselftest.h.

Signed-off-by: Shuah Khan skhan@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- tools/testing/selftests/rseq/basic_percpu_ops_test.c | 3 +-- tools/testing/selftests/rseq/rseq.c | 3 +-- 2 files changed, 2 insertions(+), 4 deletions(-)

--- a/tools/testing/selftests/rseq/basic_percpu_ops_test.c +++ b/tools/testing/selftests/rseq/basic_percpu_ops_test.c @@ -9,10 +9,9 @@ #include <string.h> #include <stddef.h>

+#include "../kselftest.h" #include "rseq.h"

-#define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0])) - struct percpu_lock_entry { intptr_t v; } __attribute__((aligned(128))); --- a/tools/testing/selftests/rseq/rseq.c +++ b/tools/testing/selftests/rseq/rseq.c @@ -27,10 +27,9 @@ #include <signal.h> #include <limits.h>

+#include "../kselftest.h" #include "rseq.h"

-#define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0])) - __thread volatile struct rseq __rseq_abi = { .cpu_id = RSEQ_CPU_ID_UNINITIALIZED, };

From: Mathieu Desnoyers mathieu.desnoyers@efficios.com

commit 930378d056eac2c96407b02aafe4938d0ac9cc37 upstream.

Signed-off-by: Mathieu Desnoyers mathieu.desnoyers@efficios.com Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Link: https://lkml.kernel.org/r/20220124171253.22072-4-mathieu.desnoyers@efficios.... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- tools/testing/selftests/rseq/param_test.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-)

--- a/tools/testing/selftests/rseq/param_test.c +++ b/tools/testing/selftests/rseq/param_test.c @@ -366,9 +366,7 @@ void *test_percpu_spinlock_thread(void * abort(); reps = thread_data->reps; for (i = 0; i < reps; i++) { - int cpu = rseq_cpu_start(); - - cpu = rseq_this_cpu_lock(&data->lock); + int cpu = rseq_this_cpu_lock(&data->lock); data->c[cpu].count++; rseq_percpu_unlock(&data->lock, cpu); #ifndef BENCHMARK

From: Mathieu Desnoyers mathieu.desnoyers@efficios.com

commit e546cd48ccc456074ddb8920732aef4af65d7ca7 upstream.

This is done in preparation for the selftest uplift to become compatible with glibc-2.35.

glibc-2.35 exposes the rseq per-thread data in the TCB, accessible at an offset from the thread pointer, rather than through an actual Thread-Local Storage (TLS) variable, as the kernel selftests initially expected.

Introduce a rseq_get_abi() helper, initially using the __rseq_abi TLS variable, in preparation for changing this userspace ABI for one which is compatible with glibc-2.35.

Note that the __rseq_abi TLS and glibc-2.35's ABI for per-thread data cannot actively coexist in a process, because the kernel supports only a single rseq registration per thread.

Signed-off-by: Mathieu Desnoyers mathieu.desnoyers@efficios.com Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Link: https://lkml.kernel.org/r/20220124171253.22072-6-mathieu.desnoyers@efficios.... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- tools/testing/selftests/rseq/rseq-arm.h | 32 +++++++++++++++--------------- tools/testing/selftests/rseq/rseq-arm64.h | 32 +++++++++++++++--------------- tools/testing/selftests/rseq/rseq-mips.h | 32 +++++++++++++++--------------- tools/testing/selftests/rseq/rseq-ppc.h | 32 +++++++++++++++--------------- tools/testing/selftests/rseq/rseq-s390.h | 24 +++++++++++----------- tools/testing/selftests/rseq/rseq-x86.h | 30 ++++++++++++++-------------- tools/testing/selftests/rseq/rseq.h | 11 +++++++--- 7 files changed, 99 insertions(+), 94 deletions(-)

--- a/tools/testing/selftests/rseq/rseq-arm.h +++ b/tools/testing/selftests/rseq/rseq-arm.h @@ -185,8 +185,8 @@ int rseq_cmpeqv_storev(intptr_t *v, intp "5:\n\t" : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs), [v] "m" (*v), [expect] "r" (expect), [newv] "r" (newv) @@ -255,8 +255,8 @@ int rseq_cmpnev_storeoffp_load(intptr_t "5:\n\t" : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs), /* final store input */ [v] "m" (*v), [expectnot] "r" (expectnot), @@ -316,8 +316,8 @@ int rseq_addv(intptr_t *v, intptr_t coun "5:\n\t" : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs), [v] "m" (*v), [count] "Ir" (count) RSEQ_INJECT_INPUT @@ -381,8 +381,8 @@ int rseq_cmpeqv_trystorev_storev(intptr_ "5:\n\t" : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs), /* try store input */ [v2] "m" (*v2), [newv2] "r" (newv2), @@ -457,8 +457,8 @@ int rseq_cmpeqv_trystorev_storev_release "5:\n\t" : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs), /* try store input */ [v2] "m" (*v2), [newv2] "r" (newv2), @@ -537,8 +537,8 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t * "5:\n\t" : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs), /* cmp2 input */ [v2] "m" (*v2), [expect2] "r" (expect2), @@ -657,8 +657,8 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_ "8:\n\t" : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs), /* final store input */ [v] "m" (*v), [expect] "r" (expect), @@ -782,8 +782,8 @@ int rseq_cmpeqv_trymemcpy_storev_release "8:\n\t" : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs), /* final store input */ [v] "m" (*v), [expect] "r" (expect), --- a/tools/testing/selftests/rseq/rseq-arm64.h +++ b/tools/testing/selftests/rseq/rseq-arm64.h @@ -230,8 +230,8 @@ int rseq_cmpeqv_storev(intptr_t *v, intp RSEQ_ASM_DEFINE_ABORT(4, abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "Qo" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "Qo" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs), [v] "Qo" (*v), [expect] "r" (expect), [newv] "r" (newv) @@ -287,8 +287,8 @@ int rseq_cmpnev_storeoffp_load(intptr_t RSEQ_ASM_DEFINE_ABORT(4, abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "Qo" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "Qo" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs), [v] "Qo" (*v), [expectnot] "r" (expectnot), [load] "Qo" (*load), @@ -337,8 +337,8 @@ int rseq_addv(intptr_t *v, intptr_t coun RSEQ_ASM_DEFINE_ABORT(4, abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "Qo" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "Qo" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs), [v] "Qo" (*v), [count] "r" (count) RSEQ_INJECT_INPUT @@ -388,8 +388,8 @@ int rseq_cmpeqv_trystorev_storev(intptr_ RSEQ_ASM_DEFINE_ABORT(4, abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "Qo" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "Qo" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs), [expect] "r" (expect), [v] "Qo" (*v), [newv] "r" (newv), @@ -447,8 +447,8 @@ int rseq_cmpeqv_trystorev_storev_release RSEQ_ASM_DEFINE_ABORT(4, abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "Qo" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "Qo" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs), [expect] "r" (expect), [v] "Qo" (*v), [newv] "r" (newv), @@ -508,8 +508,8 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t * RSEQ_ASM_DEFINE_ABORT(4, abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "Qo" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "Qo" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs), [v] "Qo" (*v), [expect] "r" (expect), [v2] "Qo" (*v2), @@ -569,8 +569,8 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_ RSEQ_ASM_DEFINE_ABORT(4, abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "Qo" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "Qo" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs), [expect] "r" (expect), [v] "Qo" (*v), [newv] "r" (newv), @@ -629,8 +629,8 @@ int rseq_cmpeqv_trymemcpy_storev_release RSEQ_ASM_DEFINE_ABORT(4, abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "Qo" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "Qo" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs), [expect] "r" (expect), [v] "Qo" (*v), [newv] "r" (newv), --- a/tools/testing/selftests/rseq/rseq-mips.h +++ b/tools/testing/selftests/rseq/rseq-mips.h @@ -190,8 +190,8 @@ int rseq_cmpeqv_storev(intptr_t *v, intp "5:\n\t" : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs), [v] "m" (*v), [expect] "r" (expect), [newv] "r" (newv) @@ -258,8 +258,8 @@ int rseq_cmpnev_storeoffp_load(intptr_t "5:\n\t" : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs), /* final store input */ [v] "m" (*v), [expectnot] "r" (expectnot), @@ -319,8 +319,8 @@ int rseq_addv(intptr_t *v, intptr_t coun "5:\n\t" : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs), [v] "m" (*v), [count] "Ir" (count) RSEQ_INJECT_INPUT @@ -382,8 +382,8 @@ int rseq_cmpeqv_trystorev_storev(intptr_ "5:\n\t" : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs), /* try store input */ [v2] "m" (*v2), [newv2] "r" (newv2), @@ -456,8 +456,8 @@ int rseq_cmpeqv_trystorev_storev_release "5:\n\t" : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs), /* try store input */ [v2] "m" (*v2), [newv2] "r" (newv2), @@ -532,8 +532,8 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t * "5:\n\t" : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs), /* cmp2 input */ [v2] "m" (*v2), [expect2] "r" (expect2), @@ -649,8 +649,8 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_ "8:\n\t" : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs), /* final store input */ [v] "m" (*v), [expect] "r" (expect), @@ -771,8 +771,8 @@ int rseq_cmpeqv_trymemcpy_storev_release "8:\n\t" : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs), /* final store input */ [v] "m" (*v), [expect] "r" (expect), --- a/tools/testing/selftests/rseq/rseq-ppc.h +++ b/tools/testing/selftests/rseq/rseq-ppc.h @@ -235,8 +235,8 @@ int rseq_cmpeqv_storev(intptr_t *v, intp RSEQ_ASM_DEFINE_ABORT(4, abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs), [v] "m" (*v), [expect] "r" (expect), [newv] "r" (newv) @@ -301,8 +301,8 @@ int rseq_cmpnev_storeoffp_load(intptr_t RSEQ_ASM_DEFINE_ABORT(4, abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs), /* final store input */ [v] "m" (*v), [expectnot] "r" (expectnot), @@ -359,8 +359,8 @@ int rseq_addv(intptr_t *v, intptr_t coun RSEQ_ASM_DEFINE_ABORT(4, abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs), /* final store input */ [v] "m" (*v), [count] "r" (count) @@ -419,8 +419,8 @@ int rseq_cmpeqv_trystorev_storev(intptr_ RSEQ_ASM_DEFINE_ABORT(4, abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs), /* try store input */ [v2] "m" (*v2), [newv2] "r" (newv2), @@ -489,8 +489,8 @@ int rseq_cmpeqv_trystorev_storev_release RSEQ_ASM_DEFINE_ABORT(4, abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs), /* try store input */ [v2] "m" (*v2), [newv2] "r" (newv2), @@ -560,8 +560,8 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t * RSEQ_ASM_DEFINE_ABORT(4, abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs), /* cmp2 input */ [v2] "m" (*v2), [expect2] "r" (expect2), @@ -635,8 +635,8 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_ RSEQ_ASM_DEFINE_ABORT(4, abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs), /* final store input */ [v] "m" (*v), [expect] "r" (expect), @@ -711,8 +711,8 @@ int rseq_cmpeqv_trymemcpy_storev_release RSEQ_ASM_DEFINE_ABORT(4, abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs), /* final store input */ [v] "m" (*v), [expect] "r" (expect), --- a/tools/testing/selftests/rseq/rseq-s390.h +++ b/tools/testing/selftests/rseq/rseq-s390.h @@ -165,8 +165,8 @@ int rseq_cmpeqv_storev(intptr_t *v, intp RSEQ_ASM_DEFINE_ABORT(4, "", abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs), [v] "m" (*v), [expect] "r" (expect), [newv] "r" (newv) @@ -233,8 +233,8 @@ int rseq_cmpnev_storeoffp_load(intptr_t RSEQ_ASM_DEFINE_ABORT(4, "", abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs), /* final store input */ [v] "m" (*v), [expectnot] "r" (expectnot), @@ -288,8 +288,8 @@ int rseq_addv(intptr_t *v, intptr_t coun RSEQ_ASM_DEFINE_ABORT(4, "", abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs), /* final store input */ [v] "m" (*v), [count] "r" (count) @@ -347,8 +347,8 @@ int rseq_cmpeqv_trystorev_storev(intptr_ RSEQ_ASM_DEFINE_ABORT(4, "", abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs), /* try store input */ [v2] "m" (*v2), [newv2] "r" (newv2), @@ -426,8 +426,8 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t * RSEQ_ASM_DEFINE_ABORT(4, "", abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs), /* cmp2 input */ [v2] "m" (*v2), [expect2] "r" (expect2), @@ -534,8 +534,8 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_ #endif : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs), /* final store input */ [v] "m" (*v), [expect] "r" (expect), --- a/tools/testing/selftests/rseq/rseq-x86.h +++ b/tools/testing/selftests/rseq/rseq-x86.h @@ -141,7 +141,7 @@ int rseq_cmpeqv_storev(intptr_t *v, intp RSEQ_ASM_DEFINE_ABORT(4, "", abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [rseq_abi] "r" (&__rseq_abi), + [rseq_abi] "r" (rseq_get_abi()), [v] "m" (*v), [expect] "r" (expect), [newv] "r" (newv) @@ -207,7 +207,7 @@ int rseq_cmpnev_storeoffp_load(intptr_t RSEQ_ASM_DEFINE_ABORT(4, "", abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [rseq_abi] "r" (&__rseq_abi), + [rseq_abi] "r" (rseq_get_abi()), /* final store input */ [v] "m" (*v), [expectnot] "r" (expectnot), @@ -258,7 +258,7 @@ int rseq_addv(intptr_t *v, intptr_t coun RSEQ_ASM_DEFINE_ABORT(4, "", abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [rseq_abi] "r" (&__rseq_abi), + [rseq_abi] "r" (rseq_get_abi()), /* final store input */ [v] "m" (*v), [count] "er" (count) @@ -314,7 +314,7 @@ int rseq_offset_deref_addv(intptr_t *ptr RSEQ_ASM_DEFINE_ABORT(4, "", abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [rseq_abi] "r" (&__rseq_abi), + [rseq_abi] "r" (rseq_get_abi()), /* final store input */ [ptr] "m" (*ptr), [off] "er" (off), @@ -372,7 +372,7 @@ int rseq_cmpeqv_trystorev_storev(intptr_ RSEQ_ASM_DEFINE_ABORT(4, "", abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [rseq_abi] "r" (&__rseq_abi), + [rseq_abi] "r" (rseq_get_abi()), /* try store input */ [v2] "m" (*v2), [newv2] "r" (newv2), @@ -449,7 +449,7 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t * RSEQ_ASM_DEFINE_ABORT(4, "", abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [rseq_abi] "r" (&__rseq_abi), + [rseq_abi] "r" (rseq_get_abi()), /* cmp2 input */ [v2] "m" (*v2), [expect2] "r" (expect2), @@ -555,7 +555,7 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_ #endif : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [rseq_abi] "r" (&__rseq_abi), + [rseq_abi] "r" (rseq_get_abi()), /* final store input */ [v] "m" (*v), [expect] "r" (expect), @@ -719,7 +719,7 @@ int rseq_cmpeqv_storev(intptr_t *v, intp RSEQ_ASM_DEFINE_ABORT(4, "", abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [rseq_abi] "r" (&__rseq_abi), + [rseq_abi] "r" (rseq_get_abi()), [v] "m" (*v), [expect] "r" (expect), [newv] "r" (newv) @@ -785,7 +785,7 @@ int rseq_cmpnev_storeoffp_load(intptr_t RSEQ_ASM_DEFINE_ABORT(4, "", abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [rseq_abi] "r" (&__rseq_abi), + [rseq_abi] "r" (rseq_get_abi()), /* final store input */ [v] "m" (*v), [expectnot] "r" (expectnot), @@ -836,7 +836,7 @@ int rseq_addv(intptr_t *v, intptr_t coun RSEQ_ASM_DEFINE_ABORT(4, "", abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [rseq_abi] "r" (&__rseq_abi), + [rseq_abi] "r" (rseq_get_abi()), /* final store input */ [v] "m" (*v), [count] "ir" (count) @@ -894,7 +894,7 @@ int rseq_cmpeqv_trystorev_storev(intptr_ RSEQ_ASM_DEFINE_ABORT(4, "", abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [rseq_abi] "r" (&__rseq_abi), + [rseq_abi] "r" (rseq_get_abi()), /* try store input */ [v2] "m" (*v2), [newv2] "m" (newv2), @@ -962,7 +962,7 @@ int rseq_cmpeqv_trystorev_storev_release RSEQ_ASM_DEFINE_ABORT(4, "", abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [rseq_abi] "r" (&__rseq_abi), + [rseq_abi] "r" (rseq_get_abi()), /* try store input */ [v2] "m" (*v2), [newv2] "r" (newv2), @@ -1032,7 +1032,7 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t * RSEQ_ASM_DEFINE_ABORT(4, "", abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [rseq_abi] "r" (&__rseq_abi), + [rseq_abi] "r" (rseq_get_abi()), /* cmp2 input */ [v2] "m" (*v2), [expect2] "r" (expect2), @@ -1142,7 +1142,7 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_ #endif : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [rseq_abi] "r" (&__rseq_abi), + [rseq_abi] "r" (rseq_get_abi()), /* final store input */ [v] "m" (*v), [expect] "m" (expect), @@ -1255,7 +1255,7 @@ int rseq_cmpeqv_trymemcpy_storev_release #endif : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [rseq_abi] "r" (&__rseq_abi), + [rseq_abi] "r" (rseq_get_abi()), /* final store input */ [v] "m" (*v), [expect] "m" (expect), --- a/tools/testing/selftests/rseq/rseq.h +++ b/tools/testing/selftests/rseq/rseq.h @@ -46,6 +46,11 @@ extern __thread struct rseq_abi __rseq_abi; extern int __rseq_handled;

+static inline struct rseq_abi *rseq_get_abi(void) +{ + return &__rseq_abi; +} + #define rseq_likely(x) __builtin_expect(!!(x), 1) #define rseq_unlikely(x) __builtin_expect(!!(x), 0) #define rseq_barrier() __asm__ __volatile__("" : : : "memory") @@ -108,7 +113,7 @@ int32_t rseq_fallback_current_cpu(void); */ static inline int32_t rseq_current_cpu_raw(void) { - return RSEQ_ACCESS_ONCE(__rseq_abi.cpu_id); + return RSEQ_ACCESS_ONCE(rseq_get_abi()->cpu_id); }

/* @@ -124,7 +129,7 @@ static inline int32_t rseq_current_cpu_r */ static inline uint32_t rseq_cpu_start(void) { - return RSEQ_ACCESS_ONCE(__rseq_abi.cpu_id_start); + return RSEQ_ACCESS_ONCE(rseq_get_abi()->cpu_id_start); }

static inline uint32_t rseq_current_cpu(void) @@ -139,7 +144,7 @@ static inline uint32_t rseq_current_cpu(

static inline void rseq_clear_rseq_cs(void) { - RSEQ_WRITE_ONCE(__rseq_abi.rseq_cs.arch.ptr, 0); + RSEQ_WRITE_ONCE(rseq_get_abi()->rseq_cs.arch.ptr, 0); }

/*

From: Mathieu Desnoyers mathieu.desnoyers@efficios.com

commit 233e667e1ae3e348686bd9dd0172e62a09d852e1 upstream.

glibc-2.35 (upcoming release date 2022-02-01) exposes the rseq per-thread data in the TCB, accessible at an offset from the thread pointer, rather than through an actual Thread-Local Storage (TLS) variable, as the Linux kernel selftests initially expected.

The __rseq_abi TLS and glibc-2.35's ABI for per-thread data cannot actively coexist in a process, because the kernel supports only a single rseq registration per thread.

Here is the scheme introduced to ensure selftests can work both with an older glibc and with glibc-2.35+:

- librseq exposes its own "rseq_offset, rseq_size, rseq_flags" ABI.

- librseq queries for glibc rseq ABI (__rseq_offset, __rseq_size, __rseq_flags) using dlsym() in a librseq library constructor. If those are found, copy their values into rseq_offset, rseq_size, and rseq_flags.

- Else, if those glibc symbols are not found, handle rseq registration from librseq and use its own IE-model TLS to implement the rseq ABI per-thread storage.

Signed-off-by: Mathieu Desnoyers mathieu.desnoyers@efficios.com Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Link: https://lkml.kernel.org/r/20220124171253.22072-8-mathieu.desnoyers@efficios.... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- tools/testing/selftests/rseq/Makefile | 2 tools/testing/selftests/rseq/rseq.c | 161 ++++++++++++++++------------------ tools/testing/selftests/rseq/rseq.h | 13 ++ 3 files changed, 88 insertions(+), 88 deletions(-)

--- a/tools/testing/selftests/rseq/Makefile +++ b/tools/testing/selftests/rseq/Makefile @@ -6,7 +6,7 @@ endif

CFLAGS += -O2 -Wall -g -I./ -I../../../../usr/include/ -L$(OUTPUT) -Wl,-rpath=./ \ $(CLANG_FLAGS) -LDLIBS += -lpthread +LDLIBS += -lpthread -ldl

# Own dependencies because we only want to build against 1st prerequisite, but # still track changes to header files and depend on shared object. --- a/tools/testing/selftests/rseq/rseq.c +++ b/tools/testing/selftests/rseq/rseq.c @@ -26,103 +26,113 @@ #include <assert.h> #include <signal.h> #include <limits.h> +#include <dlfcn.h>

#include "../kselftest.h" #include "rseq.h"

-__thread struct rseq_abi __rseq_abi = { - .cpu_id = RSEQ_ABI_CPU_ID_UNINITIALIZED, -}; +static const int *libc_rseq_offset_p; +static const unsigned int *libc_rseq_size_p; +static const unsigned int *libc_rseq_flags_p; + +/* Offset from the thread pointer to the rseq area. */ +int rseq_offset; + +/* Size of the registered rseq area. 0 if the registration was + unsuccessful. */ +unsigned int rseq_size = -1U;

-/* - * Shared with other libraries. This library may take rseq ownership if it is - * still 0 when executing the library constructor. Set to 1 by library - * constructor when handling rseq. Set to 0 in destructor if handling rseq. - */ -int __rseq_handled; +/* Flags used during rseq registration. */ +unsigned int rseq_flags;

-/* Whether this library have ownership of rseq registration. */ static int rseq_ownership;

-static __thread volatile uint32_t __rseq_refcount; +static +__thread struct rseq_abi __rseq_abi __attribute__((tls_model("initial-exec"))) = { + .cpu_id = RSEQ_ABI_CPU_ID_UNINITIALIZED, +};

-static void signal_off_save(sigset_t *oldset) +static int sys_rseq(struct rseq_abi *rseq_abi, uint32_t rseq_len, + int flags, uint32_t sig) { - sigset_t set; - int ret; - - sigfillset(&set); - ret = pthread_sigmask(SIG_BLOCK, &set, oldset); - if (ret) - abort(); + return syscall(__NR_rseq, rseq_abi, rseq_len, flags, sig); }

-static void signal_restore(sigset_t oldset) +int rseq_available(void) { - int ret; + int rc;

- ret = pthread_sigmask(SIG_SETMASK, &oldset, NULL); - if (ret) + rc = sys_rseq(NULL, 0, 0, 0); + if (rc != -1) abort(); -} - -static int sys_rseq(volatile struct rseq_abi *rseq_abi, uint32_t rseq_len, - int flags, uint32_t sig) -{ - return syscall(__NR_rseq, rseq_abi, rseq_len, flags, sig); + switch (errno) { + case ENOSYS: + return 0; + case EINVAL: + return 1; + default: + abort(); + } }

int rseq_register_current_thread(void) { - int rc, ret = 0; - sigset_t oldset; + int rc;

- if (!rseq_ownership) + if (!rseq_ownership) { + /* Treat libc's ownership as a successful registration. */ return 0; - signal_off_save(&oldset); - if (__rseq_refcount == UINT_MAX) { - ret = -1; - goto end; } - if (__rseq_refcount++) - goto end; rc = sys_rseq(&__rseq_abi, sizeof(struct rseq_abi), 0, RSEQ_SIG); - if (!rc) { - assert(rseq_current_cpu_raw() >= 0); - goto end; - } - if (errno != EBUSY) - RSEQ_WRITE_ONCE(__rseq_abi.cpu_id, RSEQ_ABI_CPU_ID_REGISTRATION_FAILED); - ret = -1; - __rseq_refcount--; -end: - signal_restore(oldset); - return ret; + if (rc) + return -1; + assert(rseq_current_cpu_raw() >= 0); + return 0; }

int rseq_unregister_current_thread(void) { - int rc, ret = 0; - sigset_t oldset; + int rc;

- if (!rseq_ownership) + if (!rseq_ownership) { + /* Treat libc's ownership as a successful unregistration. */ return 0; - signal_off_save(&oldset); - if (!__rseq_refcount) { - ret = -1; - goto end; } - if (--__rseq_refcount) - goto end; - rc = sys_rseq(&__rseq_abi, sizeof(struct rseq_abi), - RSEQ_ABI_FLAG_UNREGISTER, RSEQ_SIG); - if (!rc) - goto end; - __rseq_refcount = 1; - ret = -1; -end: - signal_restore(oldset); - return ret; + rc = sys_rseq(&__rseq_abi, sizeof(struct rseq_abi), RSEQ_ABI_FLAG_UNREGISTER, RSEQ_SIG); + if (rc) + return -1; + return 0; +} + +static __attribute__((constructor)) +void rseq_init(void) +{ + libc_rseq_offset_p = dlsym(RTLD_NEXT, "__rseq_offset"); + libc_rseq_size_p = dlsym(RTLD_NEXT, "__rseq_size"); + libc_rseq_flags_p = dlsym(RTLD_NEXT, "__rseq_flags"); + if (libc_rseq_size_p && libc_rseq_offset_p && libc_rseq_flags_p) { + /* rseq registration owned by glibc */ + rseq_offset = *libc_rseq_offset_p; + rseq_size = *libc_rseq_size_p; + rseq_flags = *libc_rseq_flags_p; + return; + } + if (!rseq_available()) + return; + rseq_ownership = 1; + rseq_offset = (void *)&__rseq_abi - rseq_thread_pointer(); + rseq_size = sizeof(struct rseq_abi); + rseq_flags = 0; +} + +static __attribute__((destructor)) +void rseq_exit(void) +{ + if (!rseq_ownership) + return; + rseq_offset = 0; + rseq_size = -1U; + rseq_ownership = 0; }

int32_t rseq_fallback_current_cpu(void) @@ -136,20 +146,3 @@ int32_t rseq_fallback_current_cpu(void) } return cpu; } - -void __attribute__((constructor)) rseq_init(void) -{ - /* Check whether rseq is handled by another library. */ - if (__rseq_handled) - return; - __rseq_handled = 1; - rseq_ownership = 1; -} - -void __attribute__((destructor)) rseq_fini(void) -{ - if (!rseq_ownership) - return; - __rseq_handled = 0; - rseq_ownership = 0; -} --- a/tools/testing/selftests/rseq/rseq.h +++ b/tools/testing/selftests/rseq/rseq.h @@ -43,12 +43,19 @@ #define RSEQ_INJECT_FAILED #endif

-extern __thread struct rseq_abi __rseq_abi; -extern int __rseq_handled; +#include "rseq-thread-pointer.h" + +/* Offset from the thread pointer to the rseq area. */ +extern int rseq_offset; +/* Size of the registered rseq area. 0 if the registration was + unsuccessful. */ +extern unsigned int rseq_size; +/* Flags used during rseq registration. */ +extern unsigned int rseq_flags;

static inline struct rseq_abi *rseq_get_abi(void) { - return &__rseq_abi; + return (struct rseq_abi *) ((uintptr_t) rseq_thread_pointer() + rseq_offset); }

#define rseq_likely(x) __builtin_expect(!!(x), 1)

From: Mathieu Desnoyers mathieu.desnoyers@efficios.com

commit de6b52a21420a18dc8a36438d581efd1313d5fe3 upstream.

Building the rseq basic test with gcc version 5.4.0 20160609 (Ubuntu 5.4.0-6ubuntu1~16.04.12) Target: powerpc-linux-gnu

leads to these errors:

/tmp/ccieEWxU.s: Assembler messages: /tmp/ccieEWxU.s:118: Error: syntax error; found `,', expected `(' /tmp/ccieEWxU.s:118: Error: junk at end of line: `,8' /tmp/ccieEWxU.s:121: Error: syntax error; found `,', expected `(' /tmp/ccieEWxU.s:121: Error: junk at end of line: `,8' /tmp/ccieEWxU.s:626: Error: syntax error; found `,', expected `(' /tmp/ccieEWxU.s:626: Error: junk at end of line: `,8' /tmp/ccieEWxU.s:629: Error: syntax error; found `,', expected `(' /tmp/ccieEWxU.s:629: Error: junk at end of line: `,8' /tmp/ccieEWxU.s:735: Error: syntax error; found `,', expected `(' /tmp/ccieEWxU.s:735: Error: junk at end of line: `,8' /tmp/ccieEWxU.s:738: Error: syntax error; found `,', expected `(' /tmp/ccieEWxU.s:738: Error: junk at end of line: `,8' /tmp/ccieEWxU.s:741: Error: syntax error; found `,', expected `(' /tmp/ccieEWxU.s:741: Error: junk at end of line: `,8' Makefile:581: recipe for target 'basic_percpu_ops_test.o' failed

Based on discussion with Linux powerpc maintainers and review of the use of the "m" operand in powerpc kernel code, add the missing %Un%Xn (where n is operand number) to the lwz, stw, ld, and std instructions when used with "m" operands.

Using "WORD" to mean either a 32-bit or 64-bit type depending on the architecture is misleading. The term "WORD" really means a 32-bit type in both 32-bit and 64-bit powerpc assembler. The intent here is to wrap load/store to intptr_t into common macros for both 32-bit and 64-bit.

Rename the macros with a RSEQ_ prefix, and use the terms "INT" for always 32-bit type, and "LONG" for architecture bitness-sized type.

Signed-off-by: Mathieu Desnoyers mathieu.desnoyers@efficios.com Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Link: https://lkml.kernel.org/r/20220124171253.22072-10-mathieu.desnoyers@efficios... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- tools/testing/selftests/rseq/rseq-ppc.h | 55 ++++++++++++++++---------------- 1 file changed, 28 insertions(+), 27 deletions(-)

--- a/tools/testing/selftests/rseq/rseq-ppc.h +++ b/tools/testing/selftests/rseq/rseq-ppc.h @@ -47,10 +47,13 @@ do { \

#ifdef __PPC64__

-#define STORE_WORD "std " -#define LOAD_WORD "ld " -#define LOADX_WORD "ldx " -#define CMP_WORD "cmpd " +#define RSEQ_STORE_LONG(arg) "std%U[" __rseq_str(arg) "]%X[" __rseq_str(arg) "] " /* To memory ("m" constraint) */ +#define RSEQ_STORE_INT(arg) "stw%U[" __rseq_str(arg) "]%X[" __rseq_str(arg) "] " /* To memory ("m" constraint) */ +#define RSEQ_LOAD_LONG(arg) "ld%U[" __rseq_str(arg) "]%X[" __rseq_str(arg) "] " /* From memory ("m" constraint) */ +#define RSEQ_LOAD_INT(arg) "lwz%U[" __rseq_str(arg) "]%X[" __rseq_str(arg) "] " /* From memory ("m" constraint) */ +#define RSEQ_LOADX_LONG "ldx " /* From base register ("b" constraint) */ +#define RSEQ_CMP_LONG "cmpd " +#define RSEQ_CMP_LONG_INT "cmpdi "

#define __RSEQ_ASM_DEFINE_TABLE(label, version, flags, \ start_ip, post_commit_offset, abort_ip) \ @@ -89,10 +92,13 @@ do { \

#else /* #ifdef __PPC64__ */

-#define STORE_WORD "stw " -#define LOAD_WORD "lwz " -#define LOADX_WORD "lwzx " -#define CMP_WORD "cmpw " +#define RSEQ_STORE_LONG(arg) "stw%U[" __rseq_str(arg) "]%X[" __rseq_str(arg) "] " /* To memory ("m" constraint) */ +#define RSEQ_STORE_INT(arg) RSEQ_STORE_LONG(arg) /* To memory ("m" constraint) */ +#define RSEQ_LOAD_LONG(arg) "lwz%U[" __rseq_str(arg) "]%X[" __rseq_str(arg) "] " /* From memory ("m" constraint) */ +#define RSEQ_LOAD_INT(arg) RSEQ_LOAD_LONG(arg) /* From memory ("m" constraint) */ +#define RSEQ_LOADX_LONG "lwzx " /* From base register ("b" constraint) */ +#define RSEQ_CMP_LONG "cmpw " +#define RSEQ_CMP_LONG_INT "cmpwi "

#define __RSEQ_ASM_DEFINE_TABLE(label, version, flags, \ start_ip, post_commit_offset, abort_ip) \ @@ -125,7 +131,7 @@ do { \ RSEQ_INJECT_ASM(1) \ "lis %%r17, (" __rseq_str(cs_label) ")@ha\n\t" \ "addi %%r17, %%r17, (" __rseq_str(cs_label) ")@l\n\t" \ - "stw %%r17, %[" __rseq_str(rseq_cs) "]\n\t" \ + RSEQ_STORE_INT(rseq_cs) "%%r17, %[" __rseq_str(rseq_cs) "]\n\t" \ __rseq_str(label) ":\n\t"

#endif /* #ifdef __PPC64__ */ @@ -136,7 +142,7 @@ do { \

#define RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, label) \ RSEQ_INJECT_ASM(2) \ - "lwz %%r17, %[" __rseq_str(current_cpu_id) "]\n\t" \ + RSEQ_LOAD_INT(current_cpu_id) "%%r17, %[" __rseq_str(current_cpu_id) "]\n\t" \ "cmpw cr7, %[" __rseq_str(cpu_id) "], %%r17\n\t" \ "bne- cr7, " __rseq_str(label) "\n\t"

@@ -153,25 +159,25 @@ do { \ * RSEQ_ASM_OP_* (else): doesn't have hard-code registers(unless cr7) */ #define RSEQ_ASM_OP_CMPEQ(var, expect, label) \ - LOAD_WORD "%%r17, %[" __rseq_str(var) "]\n\t" \ - CMP_WORD "cr7, %%r17, %[" __rseq_str(expect) "]\n\t" \ + RSEQ_LOAD_LONG(var) "%%r17, %[" __rseq_str(var) "]\n\t" \ + RSEQ_CMP_LONG "cr7, %%r17, %[" __rseq_str(expect) "]\n\t" \ "bne- cr7, " __rseq_str(label) "\n\t"

#define RSEQ_ASM_OP_CMPNE(var, expectnot, label) \ - LOAD_WORD "%%r17, %[" __rseq_str(var) "]\n\t" \ - CMP_WORD "cr7, %%r17, %[" __rseq_str(expectnot) "]\n\t" \ + RSEQ_LOAD_LONG(var) "%%r17, %[" __rseq_str(var) "]\n\t" \ + RSEQ_CMP_LONG "cr7, %%r17, %[" __rseq_str(expectnot) "]\n\t" \ "beq- cr7, " __rseq_str(label) "\n\t"

#define RSEQ_ASM_OP_STORE(value, var) \ - STORE_WORD "%[" __rseq_str(value) "], %[" __rseq_str(var) "]\n\t" + RSEQ_STORE_LONG(var) "%[" __rseq_str(value) "], %[" __rseq_str(var) "]\n\t"

/* Load @var to r17 */ #define RSEQ_ASM_OP_R_LOAD(var) \ - LOAD_WORD "%%r17, %[" __rseq_str(var) "]\n\t" + RSEQ_LOAD_LONG(var) "%%r17, %[" __rseq_str(var) "]\n\t"

/* Store r17 to @var */ #define RSEQ_ASM_OP_R_STORE(var) \ - STORE_WORD "%%r17, %[" __rseq_str(var) "]\n\t" + RSEQ_STORE_LONG(var) "%%r17, %[" __rseq_str(var) "]\n\t"

/* Add @count to r17 */ #define RSEQ_ASM_OP_R_ADD(count) \ @@ -179,11 +185,11 @@ do { \

/* Load (r17 + voffp) to r17 */ #define RSEQ_ASM_OP_R_LOADX(voffp) \ - LOADX_WORD "%%r17, %[" __rseq_str(voffp) "], %%r17\n\t" + RSEQ_LOADX_LONG "%%r17, %[" __rseq_str(voffp) "], %%r17\n\t"

/* TODO: implement a faster memcpy. */ #define RSEQ_ASM_OP_R_MEMCPY() \ - "cmpdi %%r19, 0\n\t" \ + RSEQ_CMP_LONG_INT "%%r19, 0\n\t" \ "beq 333f\n\t" \ "addi %%r20, %%r20, -1\n\t" \ "addi %%r21, %%r21, -1\n\t" \ @@ -191,16 +197,16 @@ do { \ "lbzu %%r18, 1(%%r20)\n\t" \ "stbu %%r18, 1(%%r21)\n\t" \ "addi %%r19, %%r19, -1\n\t" \ - "cmpdi %%r19, 0\n\t" \ + RSEQ_CMP_LONG_INT "%%r19, 0\n\t" \ "bne 222b\n\t" \ "333:\n\t" \

#define RSEQ_ASM_OP_R_FINAL_STORE(var, post_commit_label) \ - STORE_WORD "%%r17, %[" __rseq_str(var) "]\n\t" \ + RSEQ_STORE_LONG(var) "%%r17, %[" __rseq_str(var) "]\n\t" \ __rseq_str(post_commit_label) ":\n\t"

#define RSEQ_ASM_OP_FINAL_STORE(value, var, post_commit_label) \ - STORE_WORD "%[" __rseq_str(value) "], %[" __rseq_str(var) "]\n\t" \ + RSEQ_STORE_LONG(var) "%[" __rseq_str(value) "], %[" __rseq_str(var) "]\n\t" \ __rseq_str(post_commit_label) ":\n\t"

static inline __attribute__((always_inline)) @@ -743,9 +749,4 @@ error2: #endif }

-#undef STORE_WORD -#undef LOAD_WORD -#undef LOADX_WORD -#undef CMP_WORD - #endif /* !RSEQ_SKIP_FASTPATH */

From: Mathieu Desnoyers mathieu.desnoyers@efficios.com

commit d7ed99ade3e62b755584eea07b4e499e79240527 upstream.

Signed-off-by: Mathieu Desnoyers mathieu.desnoyers@efficios.com Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Link: https://lkml.kernel.org/r/20220124171253.22072-12-mathieu.desnoyers@efficios... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- tools/testing/selftests/rseq/param_test.c | 2 +- tools/testing/selftests/rseq/rseq-x86.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-)

--- a/tools/testing/selftests/rseq/param_test.c +++ b/tools/testing/selftests/rseq/param_test.c @@ -159,7 +159,7 @@ unsigned int yield_mod_cnt, nr_abort; " cbnz " INJECT_ASM_REG ", 222b\n" \ "333:\n"

-#elif __PPC__ +#elif defined(__PPC__)

#define RSEQ_INJECT_INPUT \ , [loop_cnt_1]"m"(loop_cnt[1]) \ --- a/tools/testing/selftests/rseq/rseq-x86.h +++ b/tools/testing/selftests/rseq/rseq-x86.h @@ -600,7 +600,7 @@ int rseq_cmpeqv_trymemcpy_storev_release

#endif /* !RSEQ_SKIP_FASTPATH */

-#elif __i386__ +#elif defined(__i386__)

#define rseq_smp_mb() \ __asm__ __volatile__ ("lock; addl $0,-128(%%esp)" ::: "memory", "cc")

From: Mathieu Desnoyers mathieu.desnoyers@efficios.com

commit b53823fb2ef854222853be164f3b1e815f315144 upstream.

gcc and clang each have their own compiler bugs with respect to asm goto. Implement a work-around for compiler versions known to have those bugs.

gcc prior to 4.8.2 miscompiles asm goto. https://gcc.gnu.org/bugzilla/show_bug.cgi?id=58670

gcc prior to 8.1.0 miscompiles asm goto at O1. https://gcc.gnu.org/bugzilla/show_bug.cgi?id=103908

clang prior to version 13.0.1 miscompiles asm goto at O2. https://github.com/llvm/llvm-project/issues/52735

Work around these issues by adding a volatile inline asm with memory clobber in the fallthrough after the asm goto and at each label target. Emit this for all compilers in case other similar issues are found in the future.

Signed-off-by: Mathieu Desnoyers mathieu.desnoyers@efficios.com Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Link: https://lkml.kernel.org/r/20220124171253.22072-14-mathieu.desnoyers@efficios... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- tools/testing/selftests/rseq/compiler.h | 30 +++++++++++++ tools/testing/selftests/rseq/rseq-arm.h | 39 +++++++++++++++++ tools/testing/selftests/rseq/rseq-arm64.h | 45 +++++++++++++++++-- tools/testing/selftests/rseq/rseq-ppc.h | 39 +++++++++++++++++ tools/testing/selftests/rseq/rseq-s390.h | 29 ++++++++++++ tools/testing/selftests/rseq/rseq-x86.h | 68 ++++++++++++++++++++++++++++++ tools/testing/selftests/rseq/rseq.h | 1 7 files changed, 245 insertions(+), 6 deletions(-) create mode 100644 tools/testing/selftests/rseq/compiler.h

--- /dev/null +++ b/tools/testing/selftests/rseq/compiler.h @@ -0,0 +1,30 @@ +/* SPDX-License-Identifier: LGPL-2.1-only OR MIT */ +/* + * rseq/compiler.h + * + * Work-around asm goto compiler bugs. + * + * (C) Copyright 2021 - Mathieu Desnoyers mathieu.desnoyers@efficios.com + */ + +#ifndef RSEQ_COMPILER_H +#define RSEQ_COMPILER_H + +/* + * gcc prior to 4.8.2 miscompiles asm goto. + * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=58670 + * + * gcc prior to 8.1.0 miscompiles asm goto at O1. + * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=103908 + * + * clang prior to version 13.0.1 miscompiles asm goto at O2. + * https://github.com/llvm/llvm-project/issues/52735 + * + * Work around these issues by adding a volatile inline asm with + * memory clobber in the fallthrough after the asm goto and at each + * label target. Emit this for all compilers in case other similar + * issues are found in the future. + */ +#define rseq_after_asm_goto() asm volatile ("" : : : "memory") + +#endif /* RSEQ_COMPILER_H_ */ --- a/tools/testing/selftests/rseq/rseq-arm.h +++ b/tools/testing/selftests/rseq/rseq-arm.h @@ -195,16 +195,21 @@ int rseq_cmpeqv_storev(intptr_t *v, intp , error1, error2 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } @@ -263,16 +268,21 @@ int rseq_cmpnev_storeoffp_load(intptr_t , error1, error2 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } @@ -317,12 +327,15 @@ int rseq_addv(intptr_t *v, intptr_t coun , error1 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); #endif } @@ -384,16 +397,21 @@ int rseq_cmpeqv_trystorev_storev(intptr_ , error1, error2 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } @@ -456,16 +474,21 @@ int rseq_cmpeqv_trystorev_storev_release , error1, error2 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } @@ -532,18 +555,24 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t * , error1, error2, error3 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("1st expected value comparison failed"); error3: + rseq_after_asm_goto(); rseq_bug("2nd expected value comparison failed"); #endif } @@ -652,16 +681,21 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_ , error1, error2 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } @@ -771,16 +805,21 @@ int rseq_cmpeqv_trymemcpy_storev_release , error1, error2 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } --- a/tools/testing/selftests/rseq/rseq-arm64.h +++ b/tools/testing/selftests/rseq/rseq-arm64.h @@ -242,17 +242,21 @@ int rseq_cmpeqv_storev(intptr_t *v, intp , error1, error2 #endif ); - + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } @@ -300,16 +304,21 @@ int rseq_cmpnev_storeoffp_load(intptr_t , error1, error2 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } @@ -348,12 +357,15 @@ int rseq_addv(intptr_t *v, intptr_t coun , error1 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); #endif } @@ -402,17 +414,21 @@ int rseq_cmpeqv_trystorev_storev(intptr_ , error1, error2 #endif ); - + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } @@ -461,17 +477,21 @@ int rseq_cmpeqv_trystorev_storev_release , error1, error2 #endif ); - + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } @@ -522,19 +542,24 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t * , error1, error2, error3 #endif ); - + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); error3: + rseq_after_asm_goto(); rseq_bug("2nd expected value comparison failed"); #endif } @@ -584,17 +609,21 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_ , error1, error2 #endif ); - + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } @@ -644,17 +673,21 @@ int rseq_cmpeqv_trymemcpy_storev_release , error1, error2 #endif ); - + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } --- a/tools/testing/selftests/rseq/rseq-ppc.h +++ b/tools/testing/selftests/rseq/rseq-ppc.h @@ -254,16 +254,21 @@ int rseq_cmpeqv_storev(intptr_t *v, intp , error1, error2 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } @@ -322,16 +327,21 @@ int rseq_cmpnev_storeoffp_load(intptr_t , error1, error2 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } @@ -378,12 +388,15 @@ int rseq_addv(intptr_t *v, intptr_t coun , error1 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); #endif } @@ -442,16 +455,21 @@ int rseq_cmpeqv_trystorev_storev(intptr_ , error1, error2 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } @@ -512,16 +530,21 @@ int rseq_cmpeqv_trystorev_storev_release , error1, error2 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } @@ -583,18 +606,24 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t * , error1, error2, error3 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("1st expected value comparison failed"); error3: + rseq_after_asm_goto(); rseq_bug("2nd expected value comparison failed"); #endif } @@ -659,16 +688,21 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_ , error1, error2 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } @@ -735,16 +769,21 @@ int rseq_cmpeqv_trymemcpy_storev_release , error1, error2 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } --- a/tools/testing/selftests/rseq/rseq-s390.h +++ b/tools/testing/selftests/rseq/rseq-s390.h @@ -178,16 +178,21 @@ int rseq_cmpeqv_storev(intptr_t *v, intp , error1, error2 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } @@ -248,16 +253,21 @@ int rseq_cmpnev_storeoffp_load(intptr_t , error1, error2 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } @@ -301,12 +311,15 @@ int rseq_addv(intptr_t *v, intptr_t coun , error1 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); #endif } @@ -364,16 +377,21 @@ int rseq_cmpeqv_trystorev_storev(intptr_ , error1, error2 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } @@ -443,18 +461,24 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t * , error1, error2, error3 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("1st expected value comparison failed"); error3: + rseq_after_asm_goto(); rseq_bug("2nd expected value comparison failed"); #endif } @@ -555,16 +579,21 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_ , error1, error2 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } --- a/tools/testing/selftests/rseq/rseq-x86.h +++ b/tools/testing/selftests/rseq/rseq-x86.h @@ -152,16 +152,21 @@ int rseq_cmpeqv_storev(intptr_t *v, intp , error1, error2 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } @@ -220,16 +225,21 @@ int rseq_cmpnev_storeoffp_load(intptr_t , error1, error2 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } @@ -269,12 +279,15 @@ int rseq_addv(intptr_t *v, intptr_t coun , error1 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); #endif } @@ -387,16 +400,21 @@ int rseq_cmpeqv_trystorev_storev(intptr_ , error1, error2 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } @@ -464,18 +482,24 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t * , error1, error2, error3 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("1st expected value comparison failed"); error3: + rseq_after_asm_goto(); rseq_bug("2nd expected value comparison failed"); #endif } @@ -574,16 +598,21 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_ , error1, error2 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } @@ -730,16 +759,21 @@ int rseq_cmpeqv_storev(intptr_t *v, intp , error1, error2 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } @@ -798,16 +832,21 @@ int rseq_cmpnev_storeoffp_load(intptr_t , error1, error2 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } @@ -847,12 +886,15 @@ int rseq_addv(intptr_t *v, intptr_t coun , error1 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); #endif } @@ -909,16 +951,21 @@ int rseq_cmpeqv_trystorev_storev(intptr_ , error1, error2 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } @@ -977,16 +1024,21 @@ int rseq_cmpeqv_trystorev_storev_release , error1, error2 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif

@@ -1047,18 +1099,24 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t * , error1, error2, error3 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("1st expected value comparison failed"); error3: + rseq_after_asm_goto(); rseq_bug("2nd expected value comparison failed"); #endif } @@ -1161,16 +1219,21 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_ , error1, error2 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } @@ -1274,16 +1337,21 @@ int rseq_cmpeqv_trymemcpy_storev_release , error1, error2 #endif ); + rseq_after_asm_goto(); return 0; abort: + rseq_after_asm_goto(); RSEQ_INJECT_FAILED return -1; cmpfail: + rseq_after_asm_goto(); return 1; #ifdef RSEQ_COMPARE_TWICE error1: + rseq_after_asm_goto(); rseq_bug("cpu_id comparison failed"); error2: + rseq_after_asm_goto(); rseq_bug("expected value comparison failed"); #endif } --- a/tools/testing/selftests/rseq/rseq.h +++ b/tools/testing/selftests/rseq/rseq.h @@ -17,6 +17,7 @@ #include <stdio.h> #include <stdlib.h> #include "rseq-abi.h" +#include "compiler.h"

/* * Empty code injection macros, override when testing.

From: Mathieu Desnoyers mathieu.desnoyers@efficios.com

commit 127b6429d235ab7c358223bbfd8a8b8d8cc799b6 upstream.

Rather than use rseq_get_abi() and pass its result through a register to the inline assembler, directly access the per-thread rseq area through a memory reference combining the %gs segment selector, the constant offset of the field in struct rseq, and the rseq_offset value (in a register).

Signed-off-by: Mathieu Desnoyers mathieu.desnoyers@efficios.com Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Link: https://lkml.kernel.org/r/20220124171253.22072-16-mathieu.desnoyers@efficios... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- tools/testing/selftests/rseq/rseq-x86.h | 66 ++++++++++++++++---------------- 1 file changed, 34 insertions(+), 32 deletions(-)

--- a/tools/testing/selftests/rseq/rseq-x86.h +++ b/tools/testing/selftests/rseq/rseq-x86.h @@ -633,6 +633,8 @@ int rseq_cmpeqv_trymemcpy_storev_release

#elif defined(__i386__)

+#define RSEQ_ASM_TP_SEGMENT %%gs + #define rseq_smp_mb() \ __asm__ __volatile__ ("lock; addl $0,-128(%%esp)" ::: "memory", "cc") #define rseq_smp_rmb() \ @@ -732,14 +734,14 @@ int rseq_cmpeqv_storev(intptr_t *v, intp RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error2]) #endif /* Start rseq by storing table entry pointer into rseq_cs. */ - RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi])) - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f) + RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset])) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f) RSEQ_INJECT_ASM(3) "cmpl %[v], %[expect]\n\t" "jnz %l[cmpfail]\n\t" RSEQ_INJECT_ASM(4) #ifdef RSEQ_COMPARE_TWICE - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), %l[error1]) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), %l[error1]) "cmpl %[v], %[expect]\n\t" "jnz %l[error2]\n\t" #endif @@ -750,7 +752,7 @@ int rseq_cmpeqv_storev(intptr_t *v, intp RSEQ_ASM_DEFINE_ABORT(4, "", abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [rseq_abi] "r" (rseq_get_abi()), + [rseq_offset] "r" (rseq_offset), [v] "m" (*v), [expect] "r" (expect), [newv] "r" (newv) @@ -798,15 +800,15 @@ int rseq_cmpnev_storeoffp_load(intptr_t RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error2]) #endif /* Start rseq by storing table entry pointer into rseq_cs. */ - RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi])) - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f) + RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset])) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f) RSEQ_INJECT_ASM(3) "movl %[v], %%ebx\n\t" "cmpl %%ebx, %[expectnot]\n\t" "je %l[cmpfail]\n\t" RSEQ_INJECT_ASM(4) #ifdef RSEQ_COMPARE_TWICE - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), %l[error1]) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), %l[error1]) "movl %[v], %%ebx\n\t" "cmpl %%ebx, %[expectnot]\n\t" "je %l[error2]\n\t" @@ -821,7 +823,7 @@ int rseq_cmpnev_storeoffp_load(intptr_t RSEQ_ASM_DEFINE_ABORT(4, "", abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [rseq_abi] "r" (rseq_get_abi()), + [rseq_offset] "r" (rseq_offset), /* final store input */ [v] "m" (*v), [expectnot] "r" (expectnot), @@ -864,11 +866,11 @@ int rseq_addv(intptr_t *v, intptr_t coun RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error1]) #endif /* Start rseq by storing table entry pointer into rseq_cs. */ - RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi])) - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f) + RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset])) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f) RSEQ_INJECT_ASM(3) #ifdef RSEQ_COMPARE_TWICE - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), %l[error1]) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), %l[error1]) #endif /* final store */ "addl %[count], %[v]\n\t" @@ -877,7 +879,7 @@ int rseq_addv(intptr_t *v, intptr_t coun RSEQ_ASM_DEFINE_ABORT(4, "", abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [rseq_abi] "r" (rseq_get_abi()), + [rseq_offset] "r" (rseq_offset), /* final store input */ [v] "m" (*v), [count] "ir" (count) @@ -916,14 +918,14 @@ int rseq_cmpeqv_trystorev_storev(intptr_ RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error2]) #endif /* Start rseq by storing table entry pointer into rseq_cs. */ - RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi])) - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f) + RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset])) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f) RSEQ_INJECT_ASM(3) "cmpl %[v], %[expect]\n\t" "jnz %l[cmpfail]\n\t" RSEQ_INJECT_ASM(4) #ifdef RSEQ_COMPARE_TWICE - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), %l[error1]) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), %l[error1]) "cmpl %[v], %[expect]\n\t" "jnz %l[error2]\n\t" #endif @@ -938,7 +940,7 @@ int rseq_cmpeqv_trystorev_storev(intptr_ RSEQ_ASM_DEFINE_ABORT(4, "", abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [rseq_abi] "r" (rseq_get_abi()), + [rseq_offset] "r" (rseq_offset), /* try store input */ [v2] "m" (*v2), [newv2] "m" (newv2), @@ -987,15 +989,15 @@ int rseq_cmpeqv_trystorev_storev_release RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error2]) #endif /* Start rseq by storing table entry pointer into rseq_cs. */ - RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi])) - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f) + RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset])) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f) RSEQ_INJECT_ASM(3) "movl %[expect], %%eax\n\t" "cmpl %[v], %%eax\n\t" "jnz %l[cmpfail]\n\t" RSEQ_INJECT_ASM(4) #ifdef RSEQ_COMPARE_TWICE - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), %l[error1]) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), %l[error1]) "movl %[expect], %%eax\n\t" "cmpl %[v], %%eax\n\t" "jnz %l[error2]\n\t" @@ -1011,7 +1013,7 @@ int rseq_cmpeqv_trystorev_storev_release RSEQ_ASM_DEFINE_ABORT(4, "", abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [rseq_abi] "r" (rseq_get_abi()), + [rseq_offset] "r" (rseq_offset), /* try store input */ [v2] "m" (*v2), [newv2] "r" (newv2), @@ -1062,8 +1064,8 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t * RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error3]) #endif /* Start rseq by storing table entry pointer into rseq_cs. */ - RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi])) - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f) + RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset])) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f) RSEQ_INJECT_ASM(3) "cmpl %[v], %[expect]\n\t" "jnz %l[cmpfail]\n\t" @@ -1072,7 +1074,7 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t * "jnz %l[cmpfail]\n\t" RSEQ_INJECT_ASM(5) #ifdef RSEQ_COMPARE_TWICE - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), %l[error1]) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), %l[error1]) "cmpl %[v], %[expect]\n\t" "jnz %l[error2]\n\t" "cmpl %[expect2], %[v2]\n\t" @@ -1086,7 +1088,7 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t * RSEQ_ASM_DEFINE_ABORT(4, "", abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [rseq_abi] "r" (rseq_get_abi()), + [rseq_offset] "r" (rseq_offset), /* cmp2 input */ [v2] "m" (*v2), [expect2] "r" (expect2), @@ -1144,15 +1146,15 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_ "movl %[dst], %[rseq_scratch1]\n\t" "movl %[len], %[rseq_scratch2]\n\t" /* Start rseq by storing table entry pointer into rseq_cs. */ - RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi])) - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f) + RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset])) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f) RSEQ_INJECT_ASM(3) "movl %[expect], %%eax\n\t" "cmpl %%eax, %[v]\n\t" "jnz 5f\n\t" RSEQ_INJECT_ASM(4) #ifdef RSEQ_COMPARE_TWICE - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 6f) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 6f) "movl %[expect], %%eax\n\t" "cmpl %%eax, %[v]\n\t" "jnz 7f\n\t" @@ -1202,7 +1204,7 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_ #endif : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [rseq_abi] "r" (rseq_get_abi()), + [rseq_offset] "r" (rseq_offset), /* final store input */ [v] "m" (*v), [expect] "m" (expect), @@ -1261,15 +1263,15 @@ int rseq_cmpeqv_trymemcpy_storev_release "movl %[dst], %[rseq_scratch1]\n\t" "movl %[len], %[rseq_scratch2]\n\t" /* Start rseq by storing table entry pointer into rseq_cs. */ - RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi])) - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f) + RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset])) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f) RSEQ_INJECT_ASM(3) "movl %[expect], %%eax\n\t" "cmpl %%eax, %[v]\n\t" "jnz 5f\n\t" RSEQ_INJECT_ASM(4) #ifdef RSEQ_COMPARE_TWICE - RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 6f) + RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 6f) "movl %[expect], %%eax\n\t" "cmpl %%eax, %[v]\n\t" "jnz 7f\n\t" @@ -1320,7 +1322,7 @@ int rseq_cmpeqv_trymemcpy_storev_release #endif : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [rseq_abi] "r" (rseq_get_abi()), + [rseq_offset] "r" (rseq_offset), /* final store input */ [v] "m" (*v), [expect] "m" (expect),

From: Roger Pau Monne roger.pau@citrix.com

commit 2f446ffe9d737e9a844b97887919c4fda18246e7 upstream.

When allocating pages to be used for shared communication with the backend always zero them, this avoids leaking unintended data present on the pages.

This is CVE-2022-26365, part of XSA-403.

Signed-off-by: Roger Pau Monné roger.pau@citrix.com Reviewed-by: Jan Beulich jbeulich@suse.com Reviewed-by: Juergen Gross jgross@suse.com Signed-off-by: Juergen Gross jgross@suse.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/block/xen-blkfront.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-)

--- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -301,7 +301,7 @@ static int fill_grant_buffer(struct blkf goto out_of_memory;

if (info->feature_persistent) { - granted_page = alloc_page(GFP_NOIO); + granted_page = alloc_page(GFP_NOIO | __GFP_ZERO); if (!granted_page) { kfree(gnt_list_entry); goto out_of_memory; @@ -1744,7 +1744,7 @@ static int setup_blkring(struct xenbus_d for (i = 0; i < info->nr_ring_pages; i++) rinfo->ring_ref[i] = GRANT_INVALID_REF;

- sring = alloc_pages_exact(ring_size, GFP_NOIO); + sring = alloc_pages_exact(ring_size, GFP_NOIO | __GFP_ZERO); if (!sring) { xenbus_dev_fatal(dev, -ENOMEM, "allocating shared ring"); return -ENOMEM; @@ -2283,7 +2283,8 @@ static int blkfront_setup_indirect(struc

BUG_ON(!list_empty(&rinfo->indirect_pages)); for (i = 0; i < num; i++) { - struct page *indirect_page = alloc_page(GFP_KERNEL); + struct page *indirect_page = alloc_page(GFP_KERNEL | + __GFP_ZERO); if (!indirect_page) goto out_of_memory; list_add(&indirect_page->lru, &rinfo->indirect_pages);

From: Roger Pau Monne roger.pau@citrix.com

commit 4491001c2e0fa69efbb748c96ec96b100a5cdb7e upstream.

Bounce all data on the skbs to be transmitted into zeroed pages if the backend is untrusted. This avoids leaking data present in the pages shared with the backend but not part of the skb fragments. This requires introducing a new helper in order to allocate skbs with a size multiple of XEN_PAGE_SIZE so we don't leak contiguous data on the granted pages.

Reporting whether the backend is to be trusted can be done using a module parameter, or from the xenstore frontend path as set by the toolstack when adding the device.

This is CVE-2022-33741, part of XSA-403.

Signed-off-by: Roger Pau Monné roger.pau@citrix.com Reviewed-by: Juergen Gross jgross@suse.com Signed-off-by: Juergen Gross jgross@suse.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/xen-netfront.c | 50 +++++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 48 insertions(+), 2 deletions(-)

--- a/drivers/net/xen-netfront.c +++ b/drivers/net/xen-netfront.c @@ -63,6 +63,10 @@ module_param_named(max_queues, xennet_ma MODULE_PARM_DESC(max_queues, "Maximum number of queues per virtual interface");

+static bool __read_mostly xennet_trusted = true; +module_param_named(trusted, xennet_trusted, bool, 0644); +MODULE_PARM_DESC(trusted, "Is the backend trusted"); + #define XENNET_TIMEOUT (5 * HZ)

static const struct ethtool_ops xennet_ethtool_ops; @@ -163,6 +167,9 @@ struct netfront_info { /* Is device behaving sane? */ bool broken;

+ /* Should skbs be bounced into a zeroed buffer? */ + bool bounce; + atomic_t rx_gso_checksum_fixup; };

@@ -590,6 +597,34 @@ static void xennet_mark_tx_pending(struc queue->tx_link[i] = TX_PENDING; }

+struct sk_buff *bounce_skb(const struct sk_buff *skb) +{ + unsigned int headerlen = skb_headroom(skb); + /* Align size to allocate full pages and avoid contiguous data leaks */ + unsigned int size = ALIGN(skb_end_offset(skb) + skb->data_len, + XEN_PAGE_SIZE); + struct sk_buff *n = alloc_skb(size, GFP_ATOMIC | __GFP_ZERO); + + if (!n) + return NULL; + + if (!IS_ALIGNED((uintptr_t)n->head, XEN_PAGE_SIZE)) { + WARN_ONCE(1, "misaligned skb allocated\n"); + kfree_skb(n); + return NULL; + } + + /* Set the data pointer */ + skb_reserve(n, headerlen); + /* Set the tail pointer and length */ + skb_put(n, skb->len); + + BUG_ON(skb_copy_bits(skb, -headerlen, n->head, headerlen + skb->len)); + + skb_copy_header(n, skb); + return n; +} + #define MAX_XEN_SKB_FRAGS (65536 / XEN_PAGE_SIZE + 1)

static netdev_tx_t xennet_start_xmit(struct sk_buff *skb, struct net_device *dev) @@ -642,9 +677,13 @@ static netdev_tx_t xennet_start_xmit(str

/* The first req should be at least ETH_HLEN size or the packet will be * dropped by netback. + * + * If the backend is not trusted bounce all data to zeroed pages to + * avoid exposing contiguous data on the granted page not belonging to + * the skb. */ - if (unlikely(PAGE_SIZE - offset < ETH_HLEN)) { - nskb = skb_copy(skb, GFP_ATOMIC); + if (np->bounce || unlikely(PAGE_SIZE - offset < ETH_HLEN)) { + nskb = bounce_skb(skb); if (!nskb) goto drop; dev_consume_skb_any(skb); @@ -1950,6 +1989,10 @@ static int talk_to_netback(struct xenbus

info->netdev->irq = 0;

+ /* Check if backend is trusted. */ + info->bounce = !xennet_trusted || + !xenbus_read_unsigned(dev->nodename, "trusted", 1); + /* Check if backend supports multiple queues */ max_queues = xenbus_read_unsigned(info->xbdev->otherend, "multi-queue-max-queues", 1); @@ -2103,6 +2146,9 @@ static int xennet_connect(struct net_dev err = talk_to_netback(np->xbdev, np); if (err) return err; + if (np->bounce) + dev_info(&np->xbdev->dev, + "bouncing transmitted data to zeroed pages\n");

/* talk_to_netback() sets the correct number of queues */ num_queues = dev->real_num_tx_queues;

From: Oleksandr Tyshchenko oleksandr_tyshchenko@epam.com

commit b75cd218274e01d026dc5240e86fdeb44bbed0c8 upstream.

During the PV driver life cycle the mappings are added to the RB-tree by set_foreign_p2m_mapping(), which is called from gnttab_map_refs() and are removed by clear_foreign_p2m_mapping() which is called from gnttab_unmap_refs(). As both functions end up calling __set_phys_to_machine_multi() which updates the RB-tree, this function can be called concurrently.

There is already a "p2m_lock" to protect against concurrent accesses, but the problem is that the first read of "phys_to_mach.rb_node" in __set_phys_to_machine_multi() is not covered by it, so this might lead to the incorrect mappings update (removing in our case) in RB-tree.

In my environment the related issue happens rarely and only when PV net backend is running, the xen_add_phys_to_mach_entry() claims that it cannot add new pfn <-> mfn mapping to the tree since it is already exists which results in a failure when mapping foreign pages.

But there might be other bad consequences related to the non-protected root reads such use-after-free, etc.

While at it, also fix the similar usage in __pfn_to_mfn(), so initialize "struct rb_node *n" with the "p2m_lock" held in both functions to avoid possible bad consequences.

This is CVE-2022-33744 / XSA-406.

Signed-off-by: Oleksandr Tyshchenko oleksandr_tyshchenko@epam.com Reviewed-by: Stefano Stabellini sstabellini@kernel.org Signed-off-by: Juergen Gross jgross@suse.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/arm/xen/p2m.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-)

--- a/arch/arm/xen/p2m.c +++ b/arch/arm/xen/p2m.c @@ -62,11 +62,12 @@ out:

unsigned long __pfn_to_mfn(unsigned long pfn) { - struct rb_node *n = phys_to_mach.rb_node; + struct rb_node *n; struct xen_p2m_entry *entry; unsigned long irqflags;

read_lock_irqsave(&p2m_lock, irqflags); + n = phys_to_mach.rb_node; while (n) { entry = rb_entry(n, struct xen_p2m_entry, rbnode_phys); if (entry->pfn <= pfn && @@ -153,10 +154,11 @@ bool __set_phys_to_machine_multi(unsigne int rc; unsigned long irqflags; struct xen_p2m_entry *p2m_entry; - struct rb_node *n = phys_to_mach.rb_node; + struct rb_node *n;

if (mfn == INVALID_P2M_ENTRY) { write_lock_irqsave(&p2m_lock, irqflags); + n = phys_to_mach.rb_node; while (n) { p2m_entry = rb_entry(n, struct xen_p2m_entry, rbnode_phys); if (p2m_entry->pfn <= pfn &&

From: Daniele Palmas dnlplm@gmail.com

commit 94f2a444f28a649926c410eb9a38afb13a83ebe0 upstream.

Add the following Telit FN990 composition:

0x1070: tty, adb, rmnet, tty, tty, tty, tty

Signed-off-by: Daniele Palmas dnlplm@gmail.com Acked-by: Bjørn Mork bjorn@mork.no Link: https://lore.kernel.org/r/20211210095722.22269-1-dnlplm@gmail.com Signed-off-by: Jakub Kicinski kuba@kernel.org Cc: Fabio Porcedda fabio.porcedda@gmail.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/usb/qmi_wwan.c | 1 + 1 file changed, 1 insertion(+)

--- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -1316,6 +1316,7 @@ static const struct usb_device_id produc {QMI_QUIRK_SET_DTR(0x1bc7, 0x1040, 2)}, /* Telit LE922A */ {QMI_QUIRK_SET_DTR(0x1bc7, 0x1050, 2)}, /* Telit FN980 */ {QMI_QUIRK_SET_DTR(0x1bc7, 0x1060, 2)}, /* Telit LN920 */ + {QMI_QUIRK_SET_DTR(0x1bc7, 0x1070, 2)}, /* Telit FN990 */ {QMI_FIXED_INTF(0x1bc7, 0x1100, 3)}, /* Telit ME910 */ {QMI_FIXED_INTF(0x1bc7, 0x1101, 3)}, /* Telit ME910 dual modem */ {QMI_FIXED_INTF(0x1bc7, 0x1200, 5)}, /* Telit LE920 */