[ Upstream commit 7e5a206ab686f098367b61aca989f5cdfa8114a3 ]

The old code reads the "opsize" variable from out-of-bounds memory (first
byte behind the segment) if a broken TCP segment ends directly after an
opcode that is neither EOL nor NOP.

The result of the read isn't used for anything, so the worst thing that
could theoretically happen is a pagefault; and since the physmap is usually
mostly contiguous, even that seems pretty unlikely.

The following C reproducer triggers the uninitialized read - however, you
can't actually see anything happen unless you put something like a
pr_warn() in tcp_parse_md5sig_option() to print the opsize.

====================================
#define _GNU_SOURCE
#include <arpa/inet.h>
#include <stdlib.h>
#include <errno.h>
#include <stdarg.h>
#include <net/if.h>
#include <linux/if.h>
#include <linux/ip.h>
#include <linux/tcp.h>
#include <linux/in.h>
#include <linux/if_tun.h>
#include <err.h>
#include <sys/types.h>
#include <sys/stat.h>
#include <fcntl.h>
#include <string.h>
#include <stdio.h>
#include <unistd.h>
#include <sys/ioctl.h>
#include <assert.h>

void systemf(const char *command, ...) {
  char *full_command;
  va_list ap;
  va_start(ap, command);
  if (vasprintf(&full_command, command, ap) == -1)
    err(1, "vasprintf");
  va_end(ap);
  printf("systemf: <<<%s>>>\n", full_command);
  system(full_command);
}

char *devname;

int tun_alloc(char *name) {
  int fd = open("/dev/net/tun", O_RDWR);
  if (fd == -1)
    err(1, "open tun dev");
  static struct ifreq req = { .ifr_flags = IFF_TUN|IFF_NO_PI };
  strcpy(req.ifr_name, name);
  if (ioctl(fd, TUNSETIFF, &req))
    err(1, "TUNSETIFF");
  devname = req.ifr_name;
  printf("device name: %s\n", devname);
  return fd;
}

#define IPADDR(a,b,c,d) (((a)<<0)+((b)<<8)+((c)<<16)+((d)<<24))

void sum_accumulate(unsigned int *sum, void *data, int len) {
  assert((len&2)==0);
  for (int i=0; i<len/2; i++) {
    *sum += ntohs(((unsigned short *)data)[i]);
  }
}

unsigned short sum_final(unsigned int sum) {
  sum = (sum >> 16) + (sum & 0xffff);
  sum = (sum >> 16) + (sum & 0xffff);
  return htons(~sum);
}

void fix_ip_sum(struct iphdr *ip) {
  unsigned int sum = 0;
  sum_accumulate(&sum, ip, sizeof(*ip));
  ip->check = sum_final(sum);
}

void fix_tcp_sum(struct iphdr *ip, struct tcphdr *tcp) {
  unsigned int sum = 0;
  struct {
    unsigned int saddr;
    unsigned int daddr;
    unsigned char pad;
    unsigned char proto_num;
    unsigned short tcp_len;
  } fakehdr = {
    .saddr = ip->saddr,
    .daddr = ip->daddr,
    .proto_num = ip->protocol,
    .tcp_len = htons(ntohs(ip->tot_len) - ip->ihl*4)
  };
  sum_accumulate(&sum, &fakehdr, sizeof(fakehdr));
  sum_accumulate(&sum, tcp, tcp->doff*4);
  tcp->check = sum_final(sum);
}

int main(void) {
  int tun_fd = tun_alloc("inject_dev%d");
  systemf("ip link set %s up", devname);
  systemf("ip addr add 192.168.42.1/24 dev %s", devname);

  struct {
    struct iphdr ip;
    struct tcphdr tcp;
    unsigned char tcp_opts[20];
  } __attribute__((packed)) syn_packet = {
    .ip = {
      .ihl = sizeof(struct iphdr)/4,
      .version = 4,
      .tot_len = htons(sizeof(syn_packet)),
      .ttl = 30,
      .protocol = IPPROTO_TCP,
      /* FIXUP check */
      .saddr = IPADDR(192,168,42,2),
      .daddr = IPADDR(192,168,42,1)
    },
    .tcp = {
      .source = htons(1),
      .dest = htons(1337),
      .seq = 0x12345678,
      .doff = (sizeof(syn_packet.tcp)+sizeof(syn_packet.tcp_opts))/4,
      .syn = 1,
      .window = htons(64),
      .check = 0 /*FIXUP*/
    },
    .tcp_opts = {
      /* INVALID: trailing MD5SIG opcode after NOPs */
      1, 1, 1, 1, 1,
      1, 1, 1, 1, 1,
      1, 1, 1, 1, 1,
      1, 1, 1, 1, 19
    }
  };
  fix_ip_sum(&syn_packet.ip);
  fix_tcp_sum(&syn_packet.ip, &syn_packet.tcp);
  while (1) {
    int write_res = write(tun_fd, &syn_packet, sizeof(syn_packet));
    if (write_res != sizeof(syn_packet))
      err(1, "packet write failed");
  }
}
====================================

Fixes: cfb6eeb4c860 ("[TCP]: MD5 Signature Option (RFC2385) support.")
Signed-off-by: Jann Horn <jannh@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <alexander.levin@microsoft.com>

[ Upstream commit 0f9fa831aecfc297b7b45d4f046759bcefcf87f0 ]

When using TCP FastOpen for an active session, we send one wakeup event
from tcp_finish_connect(), right before the data eventually contained in
the received SYNACK is queued to sk->sk_receive_queue.

This means that depending on machine load or luck, poll() users
might receive POLLOUT events instead of POLLIN|POLLOUT

To fix this, we need to move the call to sk->sk_state_change()
after the (optional) call to tcp_rcv_fastopen_synack()

Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <alexander.levin@microsoft.com>

[ Upstream commit 56d806222ace4c3aeae516cd7a855340fb2839d8 ]

sock_reset_flag() maps to __clear_bit() not the atomic version clear_bit().
Thus, we need smp_mb(), smp_mb__after_atomic() is not sufficient.

Fixes: 3c7151275c0c ("tcp: add memory barriers to write space paths")
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Jason Baron <jbaron@akamai.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Reported-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <alexander.levin@microsoft.com>

[ Upstream commit 15bb7745e94a665caf42bfaabf0ce062845b533b ]

icsk_ack.lrcvtime has a 0 value at socket creation time.

tcpi_last_data_recv can have bogus value if no payload is ever received.

This patch initializes icsk_ack.lrcvtime for active sessions
in tcp_finish_connect(), and for passive sessions in
tcp_create_openreq_child()

Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <alexander.levin@microsoft.com>

[ Upstream commit cdbeb633ca71a02b7b63bfeb94994bf4e1a0b894 ]

In some situations tcp_send_loss_probe() can realize that it's unable
to send a loss probe (TLP), and falls back to calling tcp_rearm_rto()
to schedule an RTO timer. In such cases, sometimes tcp_rearm_rto()
realizes that the RTO was eligible to fire immediately or at some
point in the past (delta_us <= 0). Previously in such cases
tcp_rearm_rto() was scheduling such "overdue" RTOs to happen at now +
icsk_rto, which caused needless delays of hundreds of milliseconds
(and non-linear behavior that made reproducible testing
difficult). This commit changes the logic to schedule "overdue" RTOs
ASAP, rather than at now + icsk_rto.

Fixes: 6ba8a3b19e76 ("tcp: Tail loss probe (TLP)")
Suggested-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>

[ Upstream commit ed254971edea92c3ac5c67c6a05247a92aa6075e ]

If the sender switches the congestion control during ECN-triggered
cwnd-reduction state (CA_CWR), upon exiting recovery cwnd is set to
the ssthresh value calculated by the previous congestion control. If
the previous congestion control is BBR that always keep ssthresh
to TCP_INIFINITE_SSTHRESH, cwnd ends up being infinite. The safe
step is to avoid assigning invalid ssthresh value when recovery ends.

Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>

[ Upstream commit bafbb9c73241760023d8981191ddd30bb1c6dbac ]

tcp_ack() can call tcp_fragment() which may dededuct the
value tp->fackets_out when MSS changes. When prior_fackets
is larger than tp->fackets_out, tcp_clean_rtx_queue() can
invoke tcp_update_reordering() with negative values. This
results in absurd tp->reodering values higher than
sysctl_tcp_max_reordering.

Note that tcp_update_reordering indeeds sets tp->reordering
to min(sysctl_tcp_max_reordering, metric), but because
the comparison is signed, a negative metric always wins.

Fixes: c7caf8d3ed7a ("[TCP]: Fix reord detection due to snd_una covered holes")
Reported-by: Rebecca Isaacs <risaacs@google.com>
Signed-off-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>

[ Upstream commit b451e5d24ba6687c6f0e7319c727a709a1846c06 ]

This patch fixes a bug in splitting an SKB during SACK
processing. Specifically if an skb contains multiple
packets and is only partially sacked in the higher sequences,
tcp_match_sack_to_skb() splits the skb and marks the second fragment
as SACKed.

The current code further attempts rounding up the first fragment
to MSS boundaries. But it misses a boundary condition when the
rounded-up fragment size (pkt_len) is exactly skb size.  Spliting
such an skb is pointless and causses a kernel warning and aborts
the SACK processing. This patch universally checks such over-split
before calling tcp_fragment to prevent these unnecessary warnings.

Fixes: adb92db857ee ("tcp: Make SACK code to split only at mss boundaries")
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Soheil Hassas Yeganeh <soheil@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>

[ Upstream commit 083ae308280d13d187512b9babe3454342a7987e ]

The per-socket rate limit for 'challenge acks' was introduced in the
context of limiting ack loops:

commit f2b2c582e824 ("tcp: mitigate ACK loops for connections as tcp_sock")

And I think it can be extended to rate limit all 'challenge acks' on a
per-socket basis.

Since we have the global tcp_challenge_ack_limit, this patch allows for
tcp_challenge_ack_limit to be set to a large value and effectively rely on
the per-socket limit, or set tcp_challenge_ack_limit to a lower value and
still prevents a single connections from consuming the entire challenge ack
quota.

It further moves in the direction of eliminating the global limit at some
point, as Eric Dumazet has suggested. This a follow-up to:
Subject: tcp: make challenge acks less predictable

Cc: Eric Dumazet <edumazet@google.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Neal Cardwell <ncardwell@google.com>
Cc: Yuchung Cheng <ycheng@google.com>
Cc: Yue Cao <ycao009@ucr.edu>
Signed-off-by: Jason Baron <jbaron@akamai.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>

[ Upstream commit 75ff39ccc1bd5d3c455b6822ab09e533c551f758 ]

Yue Cao claims that current host rate limiting of challenge ACKS
(RFC 5961) could leak enough information to allow a patient attacker
to hijack TCP sessions. He will soon provide details in an academic
paper.

This patch increases the default limit from 100 to 1000, and adds
some randomization so that the attacker can no longer hijack
sessions without spending a considerable amount of probes.

Based on initial analysis and patch from Linus.

Note that we also have per socket rate limiting, so it is tempting
to remove the host limit in the future.

v2: randomize the count of challenge acks per second, not the period.

Fixes: 282f23c6ee34 ("tcp: implement RFC 5961 3.2")
Reported-by: Yue Cao <ycao009@ucr.edu>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Yuchung Cheng <ycheng@google.com>
Cc: Neal Cardwell <ncardwell@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <alexander.levin@verizon.com>