From c3086637b0d7dbee0925697f8dbee2bcf9637b9f Mon Sep 17 00:00:00 2001 From: Michael Heimpold Date: Wed, 11 Jul 2018 23:10:55 +0200 Subject: net: ethtool: fix spelling mistake: "tubale" -> "tunable" Signed-off-by: Michael Heimpold Signed-off-by: David S. Miller --- include/uapi/linux/ethtool.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index 4ca65b56084f..7363f18e65a5 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -226,7 +226,7 @@ enum tunable_id { ETHTOOL_TX_COPYBREAK, ETHTOOL_PFC_PREVENTION_TOUT, /* timeout in msecs */ /* - * Add your fresh new tubale attribute above and remember to update + * Add your fresh new tunable attribute above and remember to update * tunable_strings[] in net/core/ethtool.c */ __ETHTOOL_TUNABLE_COUNT, -- cgit v1.2.3 From 31048d7aedf31bf0f69c54a662944632f29d82f2 Mon Sep 17 00:00:00 2001 From: Stefan Baranoff Date: Sun, 15 Jul 2018 11:36:37 -0400 Subject: tcp: Fix broken repair socket window probe patch Correct previous bad attempt at allowing sockets to come out of TCP repair without sending window probes. To avoid changing size of the repair variable in struct tcp_sock, this lets the decision for sending probes or not to be made when coming out of repair by introducing two ways to turn it off. v2: * Remove erroneous comment; defines now make behavior clear Fixes: 70b7ff130224 ("tcp: allow user to create repair socket without window probes") Signed-off-by: Stefan Baranoff Signed-off-by: Eric Dumazet Acked-by: Andrei Vagin Signed-off-by: David S. Miller --- include/uapi/linux/tcp.h | 4 ++++ net/ipv4/tcp.c | 13 +++++++------ 2 files changed, 11 insertions(+), 6 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h index 29eb659aa77a..e3f6ed8a7064 100644 --- a/include/uapi/linux/tcp.h +++ b/include/uapi/linux/tcp.h @@ -127,6 +127,10 @@ enum { #define TCP_CM_INQ TCP_INQ +#define TCP_REPAIR_ON 1 +#define TCP_REPAIR_OFF 0 +#define TCP_REPAIR_OFF_NO_WP -1 /* Turn off without window probes */ + struct tcp_repair_opt { __u32 opt_code; __u32 opt_val; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 8e5e2ca9ab1b..ec2186e3087f 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2823,16 +2823,17 @@ static int do_tcp_setsockopt(struct sock *sk, int level, case TCP_REPAIR: if (!tcp_can_repair_sock(sk)) err = -EPERM; - /* 1 for normal repair, 2 for no window probes */ - else if (val == 1 || val == 2) { - tp->repair = val; + else if (val == TCP_REPAIR_ON) { + tp->repair = 1; sk->sk_reuse = SK_FORCE_REUSE; tp->repair_queue = TCP_NO_QUEUE; - } else if (val == 0) { + } else if (val == TCP_REPAIR_OFF) { + tp->repair = 0; + sk->sk_reuse = SK_NO_REUSE; + tcp_send_window_probe(sk); + } else if (val == TCP_REPAIR_OFF_NO_WP) { tp->repair = 0; sk->sk_reuse = SK_NO_REUSE; - if (tp->repair == 1) - tcp_send_window_probe(sk); } else err = -EINVAL; -- cgit v1.2.3 From 9ba546c01976a426292af99e682a557075d6c010 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 11 Jul 2018 15:48:46 +0200 Subject: aio: don't expose __aio_sigset in uapi glibc uses a different defintion of sigset_t than the kernel does, and the current version would pull in both. To fix this just do not expose the type at all - this somewhat mirrors pselect() where we do not even have a type for the magic sigmask argument, but just use pointer arithmetics. Fixes: 7a074e96 ("aio: implement io_pgetevents") Signed-off-by: Christoph Hellwig Reported-by: Adrian Reber Signed-off-by: Al Viro --- fs/aio.c | 5 +++++ include/linux/syscalls.h | 1 + include/uapi/linux/aio_abi.h | 6 ------ 3 files changed, 6 insertions(+), 6 deletions(-) (limited to 'include/uapi') diff --git a/fs/aio.c b/fs/aio.c index e1d20124ec0e..b1a42e45698b 100644 --- a/fs/aio.c +++ b/fs/aio.c @@ -2042,6 +2042,11 @@ SYSCALL_DEFINE5(io_getevents, aio_context_t, ctx_id, return ret; } +struct __aio_sigset { + const sigset_t __user *sigmask; + size_t sigsetsize; +}; + SYSCALL_DEFINE6(io_pgetevents, aio_context_t, ctx_id, long, min_nr, diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 73810808cdf2..b06b5eeda8e8 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -11,6 +11,7 @@ #ifndef _LINUX_SYSCALLS_H #define _LINUX_SYSCALLS_H +struct __aio_sigset; struct epoll_event; struct iattr; struct inode; diff --git a/include/uapi/linux/aio_abi.h b/include/uapi/linux/aio_abi.h index d00221345c19..ce43d340f010 100644 --- a/include/uapi/linux/aio_abi.h +++ b/include/uapi/linux/aio_abi.h @@ -29,7 +29,6 @@ #include #include -#include #include typedef __kernel_ulong_t aio_context_t; @@ -108,10 +107,5 @@ struct iocb { #undef IFBIG #undef IFLITTLE -struct __aio_sigset { - const sigset_t __user *sigmask; - size_t sigsetsize; -}; - #endif /* __LINUX__AIO_ABI_H */ -- cgit v1.2.3 From 36fc3c8c282c01ad1570bd864de52f128d731b75 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Thu, 19 Jul 2018 22:14:31 -0700 Subject: bpf: btf: Clean up BTF_INT_BITS() in uapi btf.h This patch shrinks the BTF_INT_BITS() mask. The current btf_int_check_meta() ensures the nr_bits of an integer cannot exceed 64. Hence, it is mostly an uapi cleanup. The actual btf usage (i.e. seq_show()) is also modified to use u8 instead of u16. The verification (e.g. btf_int_check_meta()) path stays as is to deal with invalid BTF situation. Fixes: 69b693f0aefa ("bpf: btf: Introduce BPF Type Format (BTF)") Signed-off-by: Martin KaFai Lau Signed-off-by: Daniel Borkmann --- include/uapi/linux/btf.h | 2 +- kernel/bpf/btf.c | 16 ++++++++++------ 2 files changed, 11 insertions(+), 7 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/btf.h b/include/uapi/linux/btf.h index 0b5ddbe135a4..972265f32871 100644 --- a/include/uapi/linux/btf.h +++ b/include/uapi/linux/btf.h @@ -76,7 +76,7 @@ struct btf_type { */ #define BTF_INT_ENCODING(VAL) (((VAL) & 0x0f000000) >> 24) #define BTF_INT_OFFSET(VAL) (((VAL & 0x00ff0000)) >> 16) -#define BTF_INT_BITS(VAL) ((VAL) & 0x0000ffff) +#define BTF_INT_BITS(VAL) ((VAL) & 0x000000ff) /* Attributes stored in the BTF_INT_ENCODING */ #define BTF_INT_SIGNED (1 << 0) diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index e016ac3afa24..9704934252b3 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -450,7 +450,7 @@ static const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id) */ static bool btf_type_int_is_regular(const struct btf_type *t) { - u16 nr_bits, nr_bytes; + u8 nr_bits, nr_bytes; u32 int_data; int_data = btf_type_int(t); @@ -993,12 +993,16 @@ static void btf_int_bits_seq_show(const struct btf *btf, { u16 left_shift_bits, right_shift_bits; u32 int_data = btf_type_int(t); - u16 nr_bits = BTF_INT_BITS(int_data); - u16 total_bits_offset; - u16 nr_copy_bytes; - u16 nr_copy_bits; + u8 nr_bits = BTF_INT_BITS(int_data); + u8 total_bits_offset; + u8 nr_copy_bytes; + u8 nr_copy_bits; u64 print_num; + /* + * bits_offset is at most 7. + * BTF_INT_OFFSET() cannot exceed 64 bits. + */ total_bits_offset = bits_offset + BTF_INT_OFFSET(int_data); data += BITS_ROUNDDOWN_BYTES(total_bits_offset); bits_offset = BITS_PER_BYTE_MASKED(total_bits_offset); @@ -1028,7 +1032,7 @@ static void btf_int_seq_show(const struct btf *btf, const struct btf_type *t, u32 int_data = btf_type_int(t); u8 encoding = BTF_INT_ENCODING(int_data); bool sign = encoding & BTF_INT_SIGNED; - u32 nr_bits = BTF_INT_BITS(int_data); + u8 nr_bits = BTF_INT_BITS(int_data); if (bits_offset || BTF_INT_OFFSET(int_data) || BITS_PER_BYTE_MASKED(nr_bits)) { -- cgit v1.2.3 From 6cbc304f2f360f25cc8607817239d6f4a2fd3dc5 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 10 May 2018 15:48:41 +0200 Subject: perf/x86/intel: Fix unwind errors from PEBS entries (mk-II) Vince reported the perf_fuzzer giving various unwinder warnings and Josh reported: > Deja vu. Most of these are related to perf PEBS, similar to the > following issue: > > b8000586c90b ("perf/x86/intel: Cure bogus unwind from PEBS entries") > > This is basically the ORC version of that. setup_pebs_sample_data() is > assembling a franken-pt_regs which ORC isn't happy about. RIP is > inconsistent with some of the other registers (like RSP and RBP). And where the previous unwinder only needed BP,SP ORC also requires IP. But we cannot spoof IP because then the sample will get displaced, entirely negating the point of PEBS. So cure the whole thing differently by doing the unwind early; this does however require a means to communicate we did the unwind early. We (ab)use an unused sample_type bit for this, which we set on events that fill out the data->callchain before the normal perf_prepare_sample(). Debugged-by: Josh Poimboeuf Reported-by: Vince Weaver Tested-by: Josh Poimboeuf Tested-by: Prashant Bhole Signed-off-by: Peter Zijlstra (Intel) Cc: Alexander Shishkin Cc: Andy Lutomirski Cc: Arnaldo Carvalho de Melo Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Thomas Gleixner Signed-off-by: Ingo Molnar --- arch/x86/events/intel/core.c | 3 +++ arch/x86/events/intel/ds.c | 25 +++++++++++-------------- include/linux/perf_event.h | 1 + include/uapi/linux/perf_event.h | 2 ++ kernel/events/core.c | 6 ++++-- 5 files changed, 21 insertions(+), 16 deletions(-) (limited to 'include/uapi') diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 707b2a96e516..86f0c15dcc2d 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -2997,6 +2997,9 @@ static int intel_pmu_hw_config(struct perf_event *event) } if (x86_pmu.pebs_aliases) x86_pmu.pebs_aliases(event); + + if (event->attr.sample_type & PERF_SAMPLE_CALLCHAIN) + event->attr.sample_type |= __PERF_SAMPLE_CALLCHAIN_EARLY; } if (needs_branch_stack(event)) { diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index 8cf03f101938..8dbba77e0518 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -1185,17 +1185,21 @@ static void setup_pebs_sample_data(struct perf_event *event, data->data_src.val = val; } + /* + * We must however always use iregs for the unwinder to stay sane; the + * record BP,SP,IP can point into thin air when the record is from a + * previous PMI context or an (I)RET happend between the record and + * PMI. + */ + if (sample_type & PERF_SAMPLE_CALLCHAIN) + data->callchain = perf_callchain(event, iregs); + /* * We use the interrupt regs as a base because the PEBS record does not * contain a full regs set, specifically it seems to lack segment * descriptors, which get used by things like user_mode(). * * In the simple case fix up only the IP for PERF_SAMPLE_IP. - * - * We must however always use BP,SP from iregs for the unwinder to stay - * sane; the record BP,SP can point into thin air when the record is - * from a previous PMI context or an (I)RET happend between the record - * and PMI. */ *regs = *iregs; @@ -1214,15 +1218,8 @@ static void setup_pebs_sample_data(struct perf_event *event, regs->si = pebs->si; regs->di = pebs->di; - /* - * Per the above; only set BP,SP if we don't need callchains. - * - * XXX: does this make sense? - */ - if (!(sample_type & PERF_SAMPLE_CALLCHAIN)) { - regs->bp = pebs->bp; - regs->sp = pebs->sp; - } + regs->bp = pebs->bp; + regs->sp = pebs->sp; #ifndef CONFIG_X86_32 regs->r8 = pebs->r8; diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 1fa12887ec02..87f6db437e4a 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -1130,6 +1130,7 @@ extern void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct extern struct perf_callchain_entry * get_perf_callchain(struct pt_regs *regs, u32 init_nr, bool kernel, bool user, u32 max_stack, bool crosstask, bool add_mark); +extern struct perf_callchain_entry *perf_callchain(struct perf_event *event, struct pt_regs *regs); extern int get_callchain_buffers(int max_stack); extern void put_callchain_buffers(void); diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index b8e288a1f740..eeb787b1c53c 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -143,6 +143,8 @@ enum perf_event_sample_format { PERF_SAMPLE_PHYS_ADDR = 1U << 19, PERF_SAMPLE_MAX = 1U << 20, /* non-ABI */ + + __PERF_SAMPLE_CALLCHAIN_EARLY = 1ULL << 63, }; /* diff --git a/kernel/events/core.c b/kernel/events/core.c index 8f0434a9951a..cdb32cf8e33c 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -6343,7 +6343,7 @@ static u64 perf_virt_to_phys(u64 virt) static struct perf_callchain_entry __empty_callchain = { .nr = 0, }; -static struct perf_callchain_entry * +struct perf_callchain_entry * perf_callchain(struct perf_event *event, struct pt_regs *regs) { bool kernel = !event->attr.exclude_callchain_kernel; @@ -6382,7 +6382,9 @@ void perf_prepare_sample(struct perf_event_header *header, if (sample_type & PERF_SAMPLE_CALLCHAIN) { int size = 1; - data->callchain = perf_callchain(event, regs); + if (!(sample_type & __PERF_SAMPLE_CALLCHAIN_EARLY)) + data->callchain = perf_callchain(event, regs); + size += data->callchain->nr; header->size += size * sizeof(u64); -- cgit v1.2.3