Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next

Pull networking updates from David Miller:

 1) Support ipv6 checksum offload in sunvnet driver, from Shannon
    Nelson.

 2) Move to RB-tree instead of custom AVL code in inetpeer, from Eric
    Dumazet.

 3) Allow generic XDP to work on virtual devices, from John Fastabend.

 4) Add bpf device maps and XDP_REDIRECT, which can be used to build
    arbitrary switching frameworks using XDP. From John Fastabend.

 5) Remove UFO offloads from the tree, gave us little other than bugs.

 6) Remove the IPSEC flow cache, from Florian Westphal.

 7) Support ipv6 route offload in mlxsw driver.

 8) Support VF representors in bnxt_en, from Sathya Perla.

 9) Add support for forward error correction modes to ethtool, from
    Vidya Sagar Ravipati.

10) Add time filter for packet scheduler action dumping, from Jamal Hadi
    Salim.

11) Extend the zerocopy sendmsg() used by virtio and tap to regular
    sockets via MSG_ZEROCOPY. From Willem de Bruijn.

12) Significantly rework value tracking in the BPF verifier, from Edward
    Cree.

13) Add new jump instructions to eBPF, from Daniel Borkmann.

14) Rework rtnetlink plumbing so that operations can be run without
    taking the RTNL semaphore. From Florian Westphal.

15) Support XDP in tap driver, from Jason Wang.

16) Add 32-bit eBPF JIT for ARM, from Shubham Bansal.

17) Add Huawei hinic ethernet driver.

18) Allow to report MD5 keys in TCP inet_diag dumps, from Ivan
    Delalande.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1780 commits)
  i40e: point wb_desc at the nvm_wb_desc during i40e_read_nvm_aq
  i40e: avoid NVM acquire deadlock during NVM update
  drivers: net: xgene: Remove return statement from void function
  drivers: net: xgene: Configure tx/rx delay for ACPI
  drivers: net: xgene: Read tx/rx delay for ACPI
  rocker: fix kcalloc parameter order
  rds: Fix non-atomic operation on shared flag variable
  net: sched: don't use GFP_KERNEL under spin lock
  vhost_net: correctly check tx avail during rx busy polling
  net: mdio-mux: add mdio_mux parameter to mdio_mux_init()
  rxrpc: Make service connection lookup always check for retry
  net: stmmac: Delete dead code for MDIO registration
  gianfar: Fix Tx flow control deactivation
  cxgb4: Ignore MPS_TX_INT_CAUSE[Bubble] for T6
  cxgb4: Fix pause frame count in t4_get_port_stats
  cxgb4: fix memory leak
  tun: rename generic_xdp to skb_xdp
  tun: reserve extra headroom only when XDP is set
  net: dsa: bcm_sf2: Configure IMP port TC2QOS mapping
  net: dsa: bcm_sf2: Advertise number of egress queues
  ...

1 files changed, 51 insertions, 2 deletions

diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index 74d9a86eccc0..9c4eef20301c 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -559,11 +559,29 @@ static DECLARE_BITMAP(enabled_perf_exit_syscalls, NR_syscalls);
 static int sys_perf_refcount_enter;
 static int sys_perf_refcount_exit;
 
+static int perf_call_bpf_enter(struct bpf_prog *prog, struct pt_regs *regs,
+                              struct syscall_metadata *sys_data,
+                              struct syscall_trace_enter *rec) {
+        struct syscall_tp_t {
+                unsigned long long regs;
+                unsigned long syscall_nr;
+                unsigned long args[sys_data->nb_args];
+        } param;
+        int i;
+
+        *(struct pt_regs **)&param = regs;
+        param.syscall_nr = rec->nr;
+        for (i = 0; i < sys_data->nb_args; i++)
+                param.args[i] = rec->args[i];
+        return trace_call_bpf(prog, &param);
+}
+
 static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id)
 {
         struct syscall_metadata *sys_data;
         struct syscall_trace_enter *rec;
         struct hlist_head *head;
+        struct bpf_prog *prog;
         int syscall_nr;
         int rctx;
         int size;
@@ -578,8 +596,9 @@ static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id)
         if (!sys_data)
                 return;
 
+        prog = READ_ONCE(sys_data->enter_event->prog);
         head = this_cpu_ptr(sys_data->enter_event->perf_events);
-        if (hlist_empty(head))
+        if (!prog && hlist_empty(head))
                 return;
 
         /* get the size after alignment with the u32 buffer size field */
@@ -594,6 +613,13 @@ static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id)
         rec->nr = syscall_nr;
         syscall_get_arguments(current, regs, 0, sys_data->nb_args,
                                (unsigned long *)&rec->args);
+
+        if ((prog && !perf_call_bpf_enter(prog, regs, sys_data, rec)) ||
+            hlist_empty(head)) {
+                perf_swevent_put_recursion_context(rctx);
+                return;
+        }
+
         perf_trace_buf_submit(rec, size, rctx,
                               sys_data->enter_event->event.type, 1, regs,
                               head, NULL, NULL);
@@ -633,11 +659,26 @@ static void perf_sysenter_disable(struct trace_event_call *call)
         mutex_unlock(&syscall_trace_lock);
 }
 
+static int perf_call_bpf_exit(struct bpf_prog *prog, struct pt_regs *regs,
+                              struct syscall_trace_exit *rec) {
+        struct syscall_tp_t {
+                unsigned long long regs;
+                unsigned long syscall_nr;
+                unsigned long ret;
+        } param;
+
+        *(struct pt_regs **)&param = regs;
+        param.syscall_nr = rec->nr;
+        param.ret = rec->ret;
+        return trace_call_bpf(prog, &param);
+}
+
 static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
 {
         struct syscall_metadata *sys_data;
         struct syscall_trace_exit *rec;
         struct hlist_head *head;
+        struct bpf_prog *prog;
         int syscall_nr;
         int rctx;
         int size;
@@ -652,8 +693,9 @@ static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
         if (!sys_data)
                 return;
 
+        prog = READ_ONCE(sys_data->exit_event->prog);
         head = this_cpu_ptr(sys_data->exit_event->perf_events);
-        if (hlist_empty(head))
+        if (!prog && hlist_empty(head))
                 return;
 
         /* We can probably do that at build time */
@@ -666,6 +708,13 @@ static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
 
         rec->nr = syscall_nr;
         rec->ret = syscall_get_return_value(current, regs);
+
+        if ((prog && !perf_call_bpf_exit(prog, regs, rec)) ||
+            hlist_empty(head)) {
+                perf_swevent_put_recursion_context(rctx);
+                return;
+        }
+
         perf_trace_buf_submit(rec, size, rctx, sys_data->exit_event->event.type,
                               1, regs, head, NULL, NULL);
 }