From: Willy Tarreau w@1wt.eu

commit f227e3ec3b5cad859ad15666874405e8c1bbc1d4 upstream.

This modifies the first 32 bits out of the 128 bits of a random CPU's net_rand_state on interrupt or CPU activity to complicate remote observations that could lead to guessing the network RNG's internal state.

Note that depending on some network devices' interrupt rate moderation or binding, this re-seeding might happen on every packet or even almost never.

In addition, with NOHZ some CPUs might not even get timer interrupts, leaving their local state rarely updated, while they are running networked processes making use of the random state. For this reason, we also perform this update in update_process_times() in order to at least update the state when there is user or system activity, since it's the only case we care about.

Reported-by: Amit Klein aksecurity@gmail.com Suggested-by: Linus Torvalds torvalds@linux-foundation.org Cc: Eric Dumazet edumazet@google.com Cc: "Jason A. Donenfeld" Jason@zx2c4.com Cc: Andy Lutomirski luto@kernel.org Cc: Kees Cook keescook@chromium.org Cc: Thomas Gleixner tglx@linutronix.de Cc: Peter Zijlstra peterz@infradead.org Cc: stable@vger.kernel.org Signed-off-by: Willy Tarreau w@1wt.eu Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- drivers/char/random.c | 1 + include/linux/random.h | 3 +++ kernel/time/timer.c | 8 ++++++++ lib/random32.c | 2 +- 4 files changed, 13 insertions(+), 1 deletion(-)

--- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -1330,6 +1330,7 @@ void add_interrupt_randomness(int irq, i

fast_mix(fast_pool); add_interrupt_bench(cycles); + this_cpu_add(net_rand_state.s1, fast_pool->pool[cycles & 3]);

if (unlikely(crng_init == 0)) { if ((fast_pool->count >= 64) && --- a/include/linux/random.h +++ b/include/linux/random.h @@ -9,6 +9,7 @@

#include <linux/list.h> #include <linux/once.h> +#include <linux/percpu.h>

#include <uapi/linux/random.h>

@@ -117,6 +118,8 @@ struct rnd_state { __u32 s1, s2, s3, s4; };

+DECLARE_PER_CPU(struct rnd_state, net_rand_state) __latent_entropy; + u32 prandom_u32_state(struct rnd_state *state); void prandom_bytes_state(struct rnd_state *state, void *buf, size_t nbytes); void prandom_seed_full_state(struct rnd_state __percpu *pcpu_state); --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -43,6 +43,7 @@ #include <linux/sched/debug.h> #include <linux/slab.h> #include <linux/compat.h> +#include <linux/random.h>

#include <linux/uaccess.h> #include <asm/unistd.h> @@ -1742,6 +1743,13 @@ void update_process_times(int user_tick) scheduler_tick(); if (IS_ENABLED(CONFIG_POSIX_TIMERS)) run_posix_cpu_timers(); + + /* The current CPU might make use of net randoms without receiving IRQs + * to renew them often enough. Let's update the net_rand_state from a + * non-constant value that's not affine to the number of calls to make + * sure it's updated when there's some activity (we don't care in idle). + */ + this_cpu_add(net_rand_state.s1, rol32(jiffies, 24) + user_tick); }

/** --- a/lib/random32.c +++ b/lib/random32.c @@ -48,7 +48,7 @@ static inline void prandom_state_selftes } #endif

-static DEFINE_PER_CPU(struct rnd_state, net_rand_state) __latent_entropy; +DEFINE_PER_CPU(struct rnd_state, net_rand_state) __latent_entropy;

/** * prandom_u32_state - seeded pseudo-random number generator.

From: Willy Tarreau w@1wt.eu

commit 1c9df907da83812e4f33b59d3d142c864d9da57f upstream.

Daniel Díaz and Kees Cook independently reported that commit f227e3ec3b5c ("random32: update the net random state on interrupt and activity") broke arm64 due to a circular dependency on include files since the addition of percpu.h in random.h.

The correct fix would definitely be to move all the prandom32 stuff out of random.h but for backporting, a smaller solution is preferred.

This one replaces linux/percpu.h with asm/percpu.h, and this fixes the problem on x86_64, arm64, arm, and mips. Note that moving percpu.h around didn't change anything and that removing it entirely broke differently. When backporting, such options might still be considered if this patch fails to help.

[ It turns out that an alternate fix seems to be to just remove the troublesome <asm/pointer_auth.h> remove from the arm64 <asm/smp.h> that causes the circular dependency.

But we might as well do the whole belt-and-suspenders thing, and minimize inclusion in <linux/random.h> too. Either will fix the problem, and both are good changes. - Linus ]

Reported-by: Daniel Díaz daniel.diaz@linaro.org Reported-by: Kees Cook keescook@chromium.org Tested-by: Marc Zyngier maz@kernel.org Fixes: f227e3ec3b5c Cc: Stephen Rothwell sfr@canb.auug.org.au Signed-off-by: Willy Tarreau w@1wt.eu Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- include/linux/random.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/include/linux/random.h +++ b/include/linux/random.h @@ -9,7 +9,7 @@

#include <linux/list.h> #include <linux/once.h> -#include <linux/percpu.h> +#include <asm/percpu.h>

#include <uapi/linux/random.h>

From: Linus Torvalds torvalds@linux-foundation.org

commit c0842fbc1b18c7a044e6ff3e8fa78bfa822c7d1a upstream.

The addition of percpu.h to the list of includes in random.h revealed some circular dependencies on arm64 and possibly other platforms. This include was added solely for the pseudo-random definitions, which have nothing to do with the rest of the definitions in this file but are still there for legacy reasons.

This patch moves the pseudo-random parts to linux/prandom.h and the percpu.h include with it, which is now guarded by _LINUX_PRANDOM_H and protected against recursive inclusion.

A further cleanup step would be to remove this from <linux/random.h> entirely, and make people who use the prandom infrastructure include just the new header file. That's a bit of a churn patch, but grepping for "prandom_" and "next_pseudo_random32" "struct rnd_state" should catch most users.

But it turns out that that nice cleanup step is fairly painful, because a _lot_ of code currently seems to depend on the implicit include of <linux/random.h>, which can currently come in a lot of ways, including such fairly core headfers as <linux/net.h>.

So the "nice cleanup" part may or may never happen.

Fixes: 1c9df907da83 ("random: fix circular include dependency on arm64 after addition of percpu.h") Tested-by: Guenter Roeck linux@roeck-us.net Acked-by: Willy Tarreau w@1wt.eu Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- include/linux/prandom.h | 78 ++++++++++++++++++++++++++++++++++++++++++++++++ include/linux/random.h | 66 ++-------------------------------------- 2 files changed, 82 insertions(+), 62 deletions(-)

--- /dev/null +++ b/include/linux/prandom.h @@ -0,0 +1,78 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * include/linux/prandom.h + * + * Include file for the fast pseudo-random 32-bit + * generation. + */ +#ifndef _LINUX_PRANDOM_H +#define _LINUX_PRANDOM_H + +#include <linux/types.h> +#include <linux/percpu.h> + +u32 prandom_u32(void); +void prandom_bytes(void *buf, size_t nbytes); +void prandom_seed(u32 seed); +void prandom_reseed_late(void); + +struct rnd_state { + __u32 s1, s2, s3, s4; +}; + +DECLARE_PER_CPU(struct rnd_state, net_rand_state); + +u32 prandom_u32_state(struct rnd_state *state); +void prandom_bytes_state(struct rnd_state *state, void *buf, size_t nbytes); +void prandom_seed_full_state(struct rnd_state __percpu *pcpu_state); + +#define prandom_init_once(pcpu_state) \ + DO_ONCE(prandom_seed_full_state, (pcpu_state)) + +/** + * prandom_u32_max - returns a pseudo-random number in interval [0, ep_ro) + * @ep_ro: right open interval endpoint + * + * Returns a pseudo-random number that is in interval [0, ep_ro). Note + * that the result depends on PRNG being well distributed in [0, ~0U] + * u32 space. Here we use maximally equidistributed combined Tausworthe + * generator, that is, prandom_u32(). This is useful when requesting a + * random index of an array containing ep_ro elements, for example. + * + * Returns: pseudo-random number in interval [0, ep_ro) + */ +static inline u32 prandom_u32_max(u32 ep_ro) +{ + return (u32)(((u64) prandom_u32() * ep_ro) >> 32); +} + +/* + * Handle minimum values for seeds + */ +static inline u32 __seed(u32 x, u32 m) +{ + return (x < m) ? x + m : x; +} + +/** + * prandom_seed_state - set seed for prandom_u32_state(). + * @state: pointer to state structure to receive the seed. + * @seed: arbitrary 64-bit value to use as a seed. + */ +static inline void prandom_seed_state(struct rnd_state *state, u64 seed) +{ + u32 i = (seed >> 32) ^ (seed << 10) ^ seed; + + state->s1 = __seed(i, 2U); + state->s2 = __seed(i, 8U); + state->s3 = __seed(i, 16U); + state->s4 = __seed(i, 128U); +} + +/* Pseudo random number generator from numerical recipes. */ +static inline u32 next_pseudo_random32(u32 seed) +{ + return seed * 1664525 + 1013904223; +} + +#endif --- a/include/linux/random.h +++ b/include/linux/random.h @@ -9,7 +9,6 @@

#include <linux/list.h> #include <linux/once.h> -#include <asm/percpu.h>

#include <uapi/linux/random.h>

@@ -109,63 +108,12 @@ declare_get_random_var_wait(long)

unsigned long randomize_page(unsigned long start, unsigned long range);

-u32 prandom_u32(void); -void prandom_bytes(void *buf, size_t nbytes); -void prandom_seed(u32 seed); -void prandom_reseed_late(void); - -struct rnd_state { - __u32 s1, s2, s3, s4; -}; - -DECLARE_PER_CPU(struct rnd_state, net_rand_state); - -u32 prandom_u32_state(struct rnd_state *state); -void prandom_bytes_state(struct rnd_state *state, void *buf, size_t nbytes); -void prandom_seed_full_state(struct rnd_state __percpu *pcpu_state); - -#define prandom_init_once(pcpu_state) \ - DO_ONCE(prandom_seed_full_state, (pcpu_state)) - -/** - * prandom_u32_max - returns a pseudo-random number in interval [0, ep_ro) - * @ep_ro: right open interval endpoint - * - * Returns a pseudo-random number that is in interval [0, ep_ro). Note - * that the result depends on PRNG being well distributed in [0, ~0U] - * u32 space. Here we use maximally equidistributed combined Tausworthe - * generator, that is, prandom_u32(). This is useful when requesting a - * random index of an array containing ep_ro elements, for example. - * - * Returns: pseudo-random number in interval [0, ep_ro) - */ -static inline u32 prandom_u32_max(u32 ep_ro) -{ - return (u32)(((u64) prandom_u32() * ep_ro) >> 32); -} - /* - * Handle minimum values for seeds - */ -static inline u32 __seed(u32 x, u32 m) -{ - return (x < m) ? x + m : x; -} - -/** - * prandom_seed_state - set seed for prandom_u32_state(). - * @state: pointer to state structure to receive the seed. - * @seed: arbitrary 64-bit value to use as a seed. + * This is designed to be standalone for just prandom + * users, but for now we include it from <linux/random.h> + * for legacy reasons. */ -static inline void prandom_seed_state(struct rnd_state *state, u64 seed) -{ - u32 i = (seed >> 32) ^ (seed << 10) ^ seed; - - state->s1 = __seed(i, 2U); - state->s2 = __seed(i, 8U); - state->s3 = __seed(i, 16U); - state->s4 = __seed(i, 128U); -} +#include <linux/prandom.h>

#ifdef CONFIG_ARCH_RANDOM # include <asm/archrandom.h> @@ -196,10 +144,4 @@ static inline bool arch_has_random_seed( } #endif

-/* Pseudo random number generator from numerical recipes. */ -static inline u32 next_pseudo_random32(u32 seed) -{ - return seed * 1664525 + 1013904223; -} - #endif /* _LINUX_RANDOM_H */

From: Jiang Ying jiangying8582@126.com

This patch is used to fix ext4 direct I/O read error when the read size is not aligned with block size.

Then, I will use a test to explain the error.

(1) Make a file that is not aligned with block size: $dd if=/dev/zero of=./test.jar bs=1000 count=3

(2) I wrote a source file named "direct_io_read_file.c" as following:

#include <stdio.h> #include <stdlib.h> #include <unistd.h> #include <sys/file.h> #include <sys/types.h> #include <sys/stat.h> #include <string.h> #define BUF_SIZE 1024

int main() { int fd; int ret;

unsigned char *buf; ret = posix_memalign((void **)&buf, 512, BUF_SIZE); if (ret) { perror("posix_memalign failed"); exit(1); } fd = open("./test.jar", O_RDONLY | O_DIRECT, 0755); if (fd < 0){ perror("open ./test.jar failed"); exit(1); }

do { ret = read(fd, buf, BUF_SIZE); printf("ret=%d\n",ret); if (ret < 0) { perror("write test.jar failed"); } } while (ret > 0);

free(buf); close(fd); }

(3) Compile the source file: $gcc direct_io_read_file.c -D_GNU_SOURCE

(4) Run the test program: $./a.out

The result is as following: ret=1024 ret=1024 ret=952 ret=-1 write test.jar failed: Invalid argument.

I have tested this program on XFS filesystem, XFS does not have this problem, because XFS use iomap_dio_rw() to do direct I/O read. And the comparing between read offset and file size is done in iomap_dio_rw(), the code is as following:

if (pos < size) { retval = filemap_write_and_wait_range(mapping, pos, pos + iov_length(iov, nr_segs) - 1);

if (!retval) { retval = mapping->a_ops->direct_IO(READ, iocb, iov, pos, nr_segs); } ... }

...only when "pos < size", direct I/O can be done, or 0 will be return.

I have tested the fix patch on Ext4, it is up to the mustard of EINVAL in man2(read) as following: #include <unistd.h> ssize_t read(int fd, void *buf, size_t count);

EINVAL fd is attached to an object which is unsuitable for reading; or the file was opened with the O_DIRECT flag, and either the address specified in buf, the value specified in count, or the current file offset is not suitably aligned.

So I think this patch can be applied to fix ext4 direct I/O error.

However Ext4 introduces direct I/O read using iomap infrastructure on kernel 5.5, the patch is commit <b1b4705d54ab> ("ext4: introduce direct I/O read using iomap infrastructure"), then Ext4 will be the same as XFS, they all use iomap_dio_rw() to do direct I/O read. So this problem does not exist on kernel 5.5 for Ext4.

From above description, we can see this problem exists on all the kernel

versions between kernel 3.14 and kernel 5.4. It will cause the Applications to fail to read. For example, when the search service downloads a new full index file, the search engine is loading the previous index file and is processing the search request, it can not use buffer io that may squeeze the previous index file in use from pagecache, so the serch service must use direct I/O read.

Please apply this patch on these kernel versions, or please use the method on kernel 5.5 to fix this problem.

Fixes: 9fe55eea7e4b ("Fix race when checking i_size on direct i/o read") Reviewed-by: Jan Kara jack@suse.cz Co-developed-by: Wang Long wanglong19@meituan.com Signed-off-by: Wang Long wanglong19@meituan.com Signed-off-by: Jiang Ying jiangying8582@126.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- fs/ext4/inode.c | 5 +++++ 1 file changed, 5 insertions(+)

--- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -3836,6 +3836,11 @@ static ssize_t ext4_direct_IO_read(struc struct inode *inode = mapping->host; size_t count = iov_iter_count(iter); ssize_t ret; + loff_t offset = iocb->ki_pos; + loff_t size = i_size_read(inode); + + if (offset >= size) + return 0;

/* * Shared inode_lock is enough for us - it protects against concurrent

From: Lorenz Bauer lmb@cloudflare.com

commit bb0de3131f4c60a9bf976681e0fe4d1e55c7a821 upstream.

The sockmap code currently ignores the value of attach_bpf_fd when detaching a program. This is contrary to the usual behaviour of checking that attach_bpf_fd represents the currently attached program.

Ensure that attach_bpf_fd is indeed the currently attached program. It turns out that all sockmap selftests already do this, which indicates that this is unlikely to cause breakage.

Fixes: 604326b41a6f ("bpf, sockmap: convert to generic sk_msg interface") Signed-off-by: Lorenz Bauer lmb@cloudflare.com Signed-off-by: Alexei Starovoitov ast@kernel.org Link: https://lore.kernel.org/bpf/20200629095630.7933-5-lmb@cloudflare.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

--- include/linux/bpf.h | 13 +++++++++++-- include/linux/skmsg.h | 13 +++++++++++++ kernel/bpf/syscall.c | 4 ++-- net/core/sock_map.c | 50 +++++++++++++++++++++++++++++++++++++++++++++----- 4 files changed, 71 insertions(+), 9 deletions(-)

--- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -956,11 +956,14 @@ static inline void bpf_map_offload_map_f #endif /* CONFIG_NET && CONFIG_BPF_SYSCALL */

#if defined(CONFIG_BPF_STREAM_PARSER) -int sock_map_prog_update(struct bpf_map *map, struct bpf_prog *prog, u32 which); +int sock_map_prog_update(struct bpf_map *map, struct bpf_prog *prog, + struct bpf_prog *old, u32 which); int sock_map_get_from_fd(const union bpf_attr *attr, struct bpf_prog *prog); +int sock_map_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype); #else static inline int sock_map_prog_update(struct bpf_map *map, - struct bpf_prog *prog, u32 which) + struct bpf_prog *prog, + struct bpf_prog *old, u32 which) { return -EOPNOTSUPP; } @@ -970,6 +973,12 @@ static inline int sock_map_get_from_fd(c { return -EINVAL; } + +static inline int sock_map_prog_detach(const union bpf_attr *attr, + enum bpf_prog_type ptype) +{ + return -EOPNOTSUPP; +} #endif

#if defined(CONFIG_XDP_SOCKETS) --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -450,6 +450,19 @@ static inline void psock_set_prog(struct bpf_prog_put(prog); }

+static inline int psock_replace_prog(struct bpf_prog **pprog, + struct bpf_prog *prog, + struct bpf_prog *old) +{ + if (cmpxchg(pprog, old, prog) != old) + return -ENOENT; + + if (old) + bpf_prog_put(old); + + return 0; +} + static inline void psock_progs_drop(struct sk_psock_progs *progs) { psock_set_prog(&progs->msg_parser, NULL); --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -2029,10 +2029,10 @@ static int bpf_prog_detach(const union b ptype = BPF_PROG_TYPE_CGROUP_DEVICE; break; case BPF_SK_MSG_VERDICT: - return sock_map_get_from_fd(attr, NULL); + return sock_map_prog_detach(attr, BPF_PROG_TYPE_SK_MSG); case BPF_SK_SKB_STREAM_PARSER: case BPF_SK_SKB_STREAM_VERDICT: - return sock_map_get_from_fd(attr, NULL); + return sock_map_prog_detach(attr, BPF_PROG_TYPE_SK_SKB); case BPF_LIRC_MODE2: return lirc_prog_detach(attr); case BPF_FLOW_DISSECTOR: --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -71,7 +71,42 @@ int sock_map_get_from_fd(const union bpf map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); - ret = sock_map_prog_update(map, prog, attr->attach_type); + ret = sock_map_prog_update(map, prog, NULL, attr->attach_type); + fdput(f); + return ret; +} + +int sock_map_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype) +{ + u32 ufd = attr->target_fd; + struct bpf_prog *prog; + struct bpf_map *map; + struct fd f; + int ret; + + if (attr->attach_flags) + return -EINVAL; + + f = fdget(ufd); + map = __bpf_map_get(f); + if (IS_ERR(map)) + return PTR_ERR(map); + + prog = bpf_prog_get(attr->attach_bpf_fd); + if (IS_ERR(prog)) { + ret = PTR_ERR(prog); + goto put_map; + } + + if (prog->type != ptype) { + ret = -EINVAL; + goto put_prog; + } + + ret = sock_map_prog_update(map, NULL, prog, attr->attach_type); +put_prog: + bpf_prog_put(prog); +put_map: fdput(f); return ret; } @@ -1015,27 +1050,32 @@ static struct sk_psock_progs *sock_map_p }

int sock_map_prog_update(struct bpf_map *map, struct bpf_prog *prog, - u32 which) + struct bpf_prog *old, u32 which) { struct sk_psock_progs *progs = sock_map_progs(map); + struct bpf_prog **pprog;

if (!progs) return -EOPNOTSUPP;

switch (which) { case BPF_SK_MSG_VERDICT: - psock_set_prog(&progs->msg_parser, prog); + pprog = &progs->msg_parser; break; case BPF_SK_SKB_STREAM_PARSER: - psock_set_prog(&progs->skb_parser, prog); + pprog = &progs->skb_parser; break; case BPF_SK_SKB_STREAM_VERDICT: - psock_set_prog(&progs->skb_verdict, prog); + pprog = &progs->skb_verdict; break; default: return -EOPNOTSUPP; }

+ if (old) + return psock_replace_prog(pprog, prog, old); + + psock_set_prog(pprog, prog); return 0; }