From c3a6cf19e695c8b0a9bf8b5933f863e12d878b7c Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Fri, 18 Oct 2019 10:31:43 +0100 Subject: export: avoid code duplication in include/linux/export.h include/linux/export.h has lots of code duplication between EXPORT_SYMBOL and EXPORT_SYMBOL_NS. To improve the maintainability and readability, unify the implementation. When the symbol has no namespace, pass the empty string "" to the 'ns' parameter. The drawback of this change is, it grows the code size. When the symbol has no namespace, sym->namespace was previously NULL, but it is now an empty string "". So, it increases 1 byte for every no namespace EXPORT_SYMBOL. A typical kernel configuration has 10K exported symbols, so it increases 10KB in rough estimation. I did not come up with a good idea to refactor it without increasing the code size. I am not sure how big a deal it is, but at least include/linux/export.h looks nicer. Reviewed-by: Greg Kroah-Hartman Signed-off-by: Masahiro Yamada [maennich: rebase on top of 3 fixes for the namespace feature] Signed-off-by: Matthias Maennich Signed-off-by: Jessica Yu --- kernel/module.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/module.c b/kernel/module.c index ff2d7359a418..26c13173da3d 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -1400,7 +1400,7 @@ static int verify_namespace_is_imported(const struct load_info *info, char *imported_namespace; namespace = kernel_symbol_namespace(sym); - if (namespace) { + if (namespace && namespace[0]) { imported_namespace = get_modinfo(info, "import_ns"); while (imported_namespace) { if (strcmp(namespace, imported_namespace) == 0) -- cgit v1.2.3 From 56144737e67329c9aaed15f942d46a6302e2e3d8 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 6 Nov 2019 09:48:04 -0800 Subject: hrtimer: Annotate lockless access to timer->state syzbot reported various data-race caused by hrtimer_is_queued() reading timer->state. A READ_ONCE() is required there to silence the warning. Also add the corresponding WRITE_ONCE() when timer->state is set. In remove_hrtimer() the hrtimer_is_queued() helper is open coded to avoid loading timer->state twice. KCSAN reported these cases: BUG: KCSAN: data-race in __remove_hrtimer / tcp_pacing_check write to 0xffff8880b2a7d388 of 1 bytes by interrupt on cpu 0: __remove_hrtimer+0x52/0x130 kernel/time/hrtimer.c:991 __run_hrtimer kernel/time/hrtimer.c:1496 [inline] __hrtimer_run_queues+0x250/0x600 kernel/time/hrtimer.c:1576 hrtimer_run_softirq+0x10e/0x150 kernel/time/hrtimer.c:1593 __do_softirq+0x115/0x33f kernel/softirq.c:292 run_ksoftirqd+0x46/0x60 kernel/softirq.c:603 smpboot_thread_fn+0x37d/0x4a0 kernel/smpboot.c:165 kthread+0x1d4/0x200 drivers/block/aoe/aoecmd.c:1253 ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:352 read to 0xffff8880b2a7d388 of 1 bytes by task 24652 on cpu 1: tcp_pacing_check net/ipv4/tcp_output.c:2235 [inline] tcp_pacing_check+0xba/0x130 net/ipv4/tcp_output.c:2225 tcp_xmit_retransmit_queue+0x32c/0x5a0 net/ipv4/tcp_output.c:3044 tcp_xmit_recovery+0x7c/0x120 net/ipv4/tcp_input.c:3558 tcp_ack+0x17b6/0x3170 net/ipv4/tcp_input.c:3717 tcp_rcv_established+0x37e/0xf50 net/ipv4/tcp_input.c:5696 tcp_v4_do_rcv+0x381/0x4e0 net/ipv4/tcp_ipv4.c:1561 sk_backlog_rcv include/net/sock.h:945 [inline] __release_sock+0x135/0x1e0 net/core/sock.c:2435 release_sock+0x61/0x160 net/core/sock.c:2951 sk_stream_wait_memory+0x3d7/0x7c0 net/core/stream.c:145 tcp_sendmsg_locked+0xb47/0x1f30 net/ipv4/tcp.c:1393 tcp_sendmsg+0x39/0x60 net/ipv4/tcp.c:1434 inet_sendmsg+0x6d/0x90 net/ipv4/af_inet.c:807 sock_sendmsg_nosec net/socket.c:637 [inline] sock_sendmsg+0x9f/0xc0 net/socket.c:657 BUG: KCSAN: data-race in __remove_hrtimer / __tcp_ack_snd_check write to 0xffff8880a3a65588 of 1 bytes by interrupt on cpu 0: __remove_hrtimer+0x52/0x130 kernel/time/hrtimer.c:991 __run_hrtimer kernel/time/hrtimer.c:1496 [inline] __hrtimer_run_queues+0x250/0x600 kernel/time/hrtimer.c:1576 hrtimer_run_softirq+0x10e/0x150 kernel/time/hrtimer.c:1593 __do_softirq+0x115/0x33f kernel/softirq.c:292 invoke_softirq kernel/softirq.c:373 [inline] irq_exit+0xbb/0xe0 kernel/softirq.c:413 exiting_irq arch/x86/include/asm/apic.h:536 [inline] smp_apic_timer_interrupt+0xe6/0x280 arch/x86/kernel/apic/apic.c:1137 apic_timer_interrupt+0xf/0x20 arch/x86/entry/entry_64.S:830 read to 0xffff8880a3a65588 of 1 bytes by task 22891 on cpu 1: __tcp_ack_snd_check+0x415/0x4f0 net/ipv4/tcp_input.c:5265 tcp_ack_snd_check net/ipv4/tcp_input.c:5287 [inline] tcp_rcv_established+0x750/0xf50 net/ipv4/tcp_input.c:5708 tcp_v4_do_rcv+0x381/0x4e0 net/ipv4/tcp_ipv4.c:1561 sk_backlog_rcv include/net/sock.h:945 [inline] __release_sock+0x135/0x1e0 net/core/sock.c:2435 release_sock+0x61/0x160 net/core/sock.c:2951 sk_stream_wait_memory+0x3d7/0x7c0 net/core/stream.c:145 tcp_sendmsg_locked+0xb47/0x1f30 net/ipv4/tcp.c:1393 tcp_sendmsg+0x39/0x60 net/ipv4/tcp.c:1434 inet_sendmsg+0x6d/0x90 net/ipv4/af_inet.c:807 sock_sendmsg_nosec net/socket.c:637 [inline] sock_sendmsg+0x9f/0xc0 net/socket.c:657 __sys_sendto+0x21f/0x320 net/socket.c:1952 __do_sys_sendto net/socket.c:1964 [inline] __se_sys_sendto net/socket.c:1960 [inline] __x64_sys_sendto+0x89/0xb0 net/socket.c:1960 do_syscall_64+0xcc/0x370 arch/x86/entry/common.c:290 Reported by Kernel Concurrency Sanitizer on: CPU: 1 PID: 24652 Comm: syz-executor.3 Not tainted 5.4.0-rc3+ #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 [ tglx: Added comments ] Reported-by: syzbot Signed-off-by: Eric Dumazet Signed-off-by: Thomas Gleixner Link: https://lkml.kernel.org/r/20191106174804.74723-1-edumazet@google.com --- kernel/time/hrtimer.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) (limited to 'kernel') diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index 65605530ee34..7f31932216a1 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -966,7 +966,8 @@ static int enqueue_hrtimer(struct hrtimer *timer, base->cpu_base->active_bases |= 1 << base->index; - timer->state = HRTIMER_STATE_ENQUEUED; + /* Pairs with the lockless read in hrtimer_is_queued() */ + WRITE_ONCE(timer->state, HRTIMER_STATE_ENQUEUED); return timerqueue_add(&base->active, &timer->node); } @@ -988,7 +989,8 @@ static void __remove_hrtimer(struct hrtimer *timer, struct hrtimer_cpu_base *cpu_base = base->cpu_base; u8 state = timer->state; - timer->state = newstate; + /* Pairs with the lockless read in hrtimer_is_queued() */ + WRITE_ONCE(timer->state, newstate); if (!(state & HRTIMER_STATE_ENQUEUED)) return; @@ -1013,8 +1015,9 @@ static void __remove_hrtimer(struct hrtimer *timer, static inline int remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base, bool restart) { - if (hrtimer_is_queued(timer)) { - u8 state = timer->state; + u8 state = timer->state; + + if (state & HRTIMER_STATE_ENQUEUED) { int reprogram; /* -- cgit v1.2.3 From 3f6ec871e1c2b360aaf022e90bb99dcc016b3874 Mon Sep 17 00:00:00 2001 From: Amit Kucheria Date: Mon, 21 Oct 2019 17:45:12 +0530 Subject: cpufreq: Initialize the governors in core_initcall Initialize the cpufreq governors earlier to allow for earlier performance control during the boot process. Signed-off-by: Amit Kucheria Acked-by: Viresh Kumar Reviewed-by: Rafael J. Wysocki Signed-off-by: Daniel Lezcano Link: https://lore.kernel.org/r/b98eae9b44eb2f034d7f5d12a161f5f831be1eb7.1571656015.git.amit.kucheria@linaro.org --- kernel/sched/cpufreq_schedutil.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c index 86800b4d5453..322ca8860f54 100644 --- a/kernel/sched/cpufreq_schedutil.c +++ b/kernel/sched/cpufreq_schedutil.c @@ -915,7 +915,7 @@ static int __init sugov_register(void) { return cpufreq_register_governor(&schedutil_gov); } -fs_initcall(sugov_register); +core_initcall(sugov_register); #ifdef CONFIG_ENERGY_MODEL extern bool sched_energy_update; -- cgit v1.2.3 From 153bedbac2ebd475e1c7c2d2fa0c042f5525927d Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Fri, 8 Nov 2019 17:08:55 +0100 Subject: irq_work: Convert flags to atomic_t We need to convert flags to atomic_t in order to later fix an ordering issue on atomic_cmpxchg() failure. This will allow us to use atomic_fetch_or(). Also clarify the nature of those flags. [ mingo: Converted two more usage site the original patch missed. ] Signed-off-by: Frederic Weisbecker Cc: Linus Torvalds Cc: Paul E . McKenney Cc: Peter Zijlstra Cc: Thomas Gleixner Link: https://lkml.kernel.org/r/20191108160858.31665-2-frederic@kernel.org Signed-off-by: Ingo Molnar --- kernel/bpf/stackmap.c | 2 +- kernel/irq_work.c | 18 +++++++++--------- kernel/printk/printk.c | 2 +- kernel/trace/bpf_trace.c | 2 +- 4 files changed, 12 insertions(+), 12 deletions(-) (limited to 'kernel') diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c index 052580c33d26..4d31284095e2 100644 --- a/kernel/bpf/stackmap.c +++ b/kernel/bpf/stackmap.c @@ -289,7 +289,7 @@ static void stack_map_get_build_id_offset(struct bpf_stack_build_id *id_offs, if (in_nmi()) { work = this_cpu_ptr(&up_read_work); - if (work->irq_work.flags & IRQ_WORK_BUSY) + if (atomic_read(&work->irq_work.flags) & IRQ_WORK_BUSY) /* cannot queue more up_read, fallback */ irq_work_busy = true; } diff --git a/kernel/irq_work.c b/kernel/irq_work.c index d42acaf81886..df0dbf4d859b 100644 --- a/kernel/irq_work.c +++ b/kernel/irq_work.c @@ -29,16 +29,16 @@ static DEFINE_PER_CPU(struct llist_head, lazy_list); */ static bool irq_work_claim(struct irq_work *work) { - unsigned long flags, oflags, nflags; + int flags, oflags, nflags; /* * Start with our best wish as a premise but only trust any * flag value after cmpxchg() result. */ - flags = work->flags & ~IRQ_WORK_PENDING; + flags = atomic_read(&work->flags) & ~IRQ_WORK_PENDING; for (;;) { nflags = flags | IRQ_WORK_CLAIMED; - oflags = cmpxchg(&work->flags, flags, nflags); + oflags = atomic_cmpxchg(&work->flags, flags, nflags); if (oflags == flags) break; if (oflags & IRQ_WORK_PENDING) @@ -61,7 +61,7 @@ void __weak arch_irq_work_raise(void) static void __irq_work_queue_local(struct irq_work *work) { /* If the work is "lazy", handle it from next tick if any */ - if (work->flags & IRQ_WORK_LAZY) { + if (atomic_read(&work->flags) & IRQ_WORK_LAZY) { if (llist_add(&work->llnode, this_cpu_ptr(&lazy_list)) && tick_nohz_tick_stopped()) arch_irq_work_raise(); @@ -143,7 +143,7 @@ static void irq_work_run_list(struct llist_head *list) { struct irq_work *work, *tmp; struct llist_node *llnode; - unsigned long flags; + int flags; BUG_ON(!irqs_disabled()); @@ -159,15 +159,15 @@ static void irq_work_run_list(struct llist_head *list) * to claim that work don't rely on us to handle their data * while we are in the middle of the func. */ - flags = work->flags & ~IRQ_WORK_PENDING; - xchg(&work->flags, flags); + flags = atomic_read(&work->flags) & ~IRQ_WORK_PENDING; + atomic_xchg(&work->flags, flags); work->func(work); /* * Clear the BUSY bit and return to the free state if * no-one else claimed it meanwhile. */ - (void)cmpxchg(&work->flags, flags, flags & ~IRQ_WORK_BUSY); + (void)atomic_cmpxchg(&work->flags, flags, flags & ~IRQ_WORK_BUSY); } } @@ -199,7 +199,7 @@ void irq_work_sync(struct irq_work *work) { lockdep_assert_irqs_enabled(); - while (work->flags & IRQ_WORK_BUSY) + while (atomic_read(&work->flags) & IRQ_WORK_BUSY) cpu_relax(); } EXPORT_SYMBOL_GPL(irq_work_sync); diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index ca65327a6de8..865727373a3b 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -2961,7 +2961,7 @@ static void wake_up_klogd_work_func(struct irq_work *irq_work) static DEFINE_PER_CPU(struct irq_work, wake_up_klogd_work) = { .func = wake_up_klogd_work_func, - .flags = IRQ_WORK_LAZY, + .flags = ATOMIC_INIT(IRQ_WORK_LAZY), }; void wake_up_klogd(void) diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 44bd08f2443b..ff467a4e2639 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -660,7 +660,7 @@ BPF_CALL_1(bpf_send_signal, u32, sig) return -EINVAL; work = this_cpu_ptr(&send_signal_work); - if (work->irq_work.flags & IRQ_WORK_BUSY) + if (atomic_read(&work->irq_work.flags) & IRQ_WORK_BUSY) return -EBUSY; /* Add the current task, which is the target of sending signal, -- cgit v1.2.3 From 25269871db1ad0cbbaafd5098cbdb40c8db4ccb9 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Fri, 8 Nov 2019 17:08:56 +0100 Subject: irq_work: Fix irq_work_claim() memory ordering When irq_work_claim() finds IRQ_WORK_PENDING flag already set, we just return and don't raise a new IPI. We expect the destination to see and handle our latest updades thanks to the pairing atomic_xchg() in irq_work_run_list(). But cmpxchg() doesn't guarantee a full memory barrier upon failure. So it's possible that the destination misses our latest updates. So use atomic_fetch_or() instead that is unconditionally fully ordered and also performs exactly what we want here and simplify the code. Signed-off-by: Frederic Weisbecker Cc: Linus Torvalds Cc: Paul E . McKenney Cc: Peter Zijlstra Cc: Thomas Gleixner Link: https://lkml.kernel.org/r/20191108160858.31665-3-frederic@kernel.org Signed-off-by: Ingo Molnar --- kernel/irq_work.c | 22 +++++++--------------- 1 file changed, 7 insertions(+), 15 deletions(-) (limited to 'kernel') diff --git a/kernel/irq_work.c b/kernel/irq_work.c index df0dbf4d859b..255454a48346 100644 --- a/kernel/irq_work.c +++ b/kernel/irq_work.c @@ -29,24 +29,16 @@ static DEFINE_PER_CPU(struct llist_head, lazy_list); */ static bool irq_work_claim(struct irq_work *work) { - int flags, oflags, nflags; + int oflags; + oflags = atomic_fetch_or(IRQ_WORK_CLAIMED, &work->flags); /* - * Start with our best wish as a premise but only trust any - * flag value after cmpxchg() result. + * If the work is already pending, no need to raise the IPI. + * The pairing atomic_xchg() in irq_work_run() makes sure + * everything we did before is visible. */ - flags = atomic_read(&work->flags) & ~IRQ_WORK_PENDING; - for (;;) { - nflags = flags | IRQ_WORK_CLAIMED; - oflags = atomic_cmpxchg(&work->flags, flags, nflags); - if (oflags == flags) - break; - if (oflags & IRQ_WORK_PENDING) - return false; - flags = oflags; - cpu_relax(); - } - + if (oflags & IRQ_WORK_PENDING) + return false; return true; } -- cgit v1.2.3 From feb4a51323babe13315c3b783ea7f1cf25368918 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Fri, 8 Nov 2019 17:08:57 +0100 Subject: irq_work: Slightly simplify IRQ_WORK_PENDING clearing Instead of fetching the value of flags and perform an xchg() to clear a bit, just use atomic_fetch_andnot() that is more suitable to do that job in one operation while keeping the full ordering. Signed-off-by: Frederic Weisbecker Cc: Linus Torvalds Cc: Paul E . McKenney Cc: Peter Zijlstra Cc: Thomas Gleixner Link: https://lkml.kernel.org/r/20191108160858.31665-4-frederic@kernel.org Signed-off-by: Ingo Molnar --- kernel/irq_work.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) (limited to 'kernel') diff --git a/kernel/irq_work.c b/kernel/irq_work.c index 255454a48346..49c53f80a13a 100644 --- a/kernel/irq_work.c +++ b/kernel/irq_work.c @@ -34,7 +34,7 @@ static bool irq_work_claim(struct irq_work *work) oflags = atomic_fetch_or(IRQ_WORK_CLAIMED, &work->flags); /* * If the work is already pending, no need to raise the IPI. - * The pairing atomic_xchg() in irq_work_run() makes sure + * The pairing atomic_fetch_andnot() in irq_work_run() makes sure * everything we did before is visible. */ if (oflags & IRQ_WORK_PENDING) @@ -135,7 +135,6 @@ static void irq_work_run_list(struct llist_head *list) { struct irq_work *work, *tmp; struct llist_node *llnode; - int flags; BUG_ON(!irqs_disabled()); @@ -144,6 +143,7 @@ static void irq_work_run_list(struct llist_head *list) llnode = llist_del_all(list); llist_for_each_entry_safe(work, tmp, llnode, llnode) { + int flags; /* * Clear the PENDING bit, after this point the @work * can be re-used. @@ -151,8 +151,7 @@ static void irq_work_run_list(struct llist_head *list) * to claim that work don't rely on us to handle their data * while we are in the middle of the func. */ - flags = atomic_read(&work->flags) & ~IRQ_WORK_PENDING; - atomic_xchg(&work->flags, flags); + flags = atomic_fetch_andnot(IRQ_WORK_PENDING, &work->flags); work->func(work); /* -- cgit v1.2.3 From 9a066357184485784f782719093ff804d05b85db Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Tue, 8 Oct 2019 21:05:52 +0900 Subject: kheaders: remove unneeded 'cat' command piped to 'head' / 'tail' The 'head' and 'tail' commands can take a file path directly. So, you do not need to run 'cat'. cat kernel/kheaders.md5 | head -1 ... is equivalent to: head -1 kernel/kheaders.md5 and the latter saves forking one process. While I was here, I replaced 'head -1' with 'head -n 1'. I also replaced '==' with '=' since we do not have a good reason to use the bashism. Signed-off-by: Masahiro Yamada --- kernel/gen_kheaders.sh | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'kernel') diff --git a/kernel/gen_kheaders.sh b/kernel/gen_kheaders.sh index 5a0fc0b0403a..b8054b0d5010 100755 --- a/kernel/gen_kheaders.sh +++ b/kernel/gen_kheaders.sh @@ -41,10 +41,10 @@ obj_files_md5="$(find $dir_list -name "*.h" | this_file_md5="$(ls -l $sfile | md5sum | cut -d ' ' -f1)" if [ -f $tarfile ]; then tarfile_md5="$(md5sum $tarfile | cut -d ' ' -f1)"; fi if [ -f kernel/kheaders.md5 ] && - [ "$(cat kernel/kheaders.md5|head -1)" == "$src_files_md5" ] && - [ "$(cat kernel/kheaders.md5|head -2|tail -1)" == "$obj_files_md5" ] && - [ "$(cat kernel/kheaders.md5|head -3|tail -1)" == "$this_file_md5" ] && - [ "$(cat kernel/kheaders.md5|tail -1)" == "$tarfile_md5" ]; then + [ "$(head -n 1 kernel/kheaders.md5)" = "$src_files_md5" ] && + [ "$(head -n 2 kernel/kheaders.md5 | tail -n 1)" = "$obj_files_md5" ] && + [ "$(head -n 3 kernel/kheaders.md5 | tail -n 1)" = "$this_file_md5" ] && + [ "$(tail -n 1 kernel/kheaders.md5)" = "$tarfile_md5" ]; then exit fi -- cgit v1.2.3 From 0e11773e76098729552b750ccff79374d1e62002 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Tue, 8 Oct 2019 21:05:53 +0900 Subject: kheaders: optimize md5sum calculation for in-tree builds This script computes md5sum of headers in srctree and in objtree. However, when we are building in-tree, we know the srctree and the objtree are the same. That is, we end up with the same computation twice. In fact, the first two lines of kernel/kheaders.md5 are always the same for in-tree builds. Unify the two md5sum calculations. For in-tree builds ($building_out_of_srctree is empty), we check only two directories, "include", and "arch/$SRCARCH/include". For out-of-tree builds ($building_out_of_srctree is 1), we check 4 directories, "$srctree/include", "$srctree/arch/$SRCARCH/include", "include", and "arch/$SRCARCH/include" since we know they are all different. Signed-off-by: Masahiro Yamada --- kernel/gen_kheaders.sh | 32 ++++++++++++++++---------------- 1 file changed, 16 insertions(+), 16 deletions(-) (limited to 'kernel') diff --git a/kernel/gen_kheaders.sh b/kernel/gen_kheaders.sh index b8054b0d5010..6ff86e62787f 100755 --- a/kernel/gen_kheaders.sh +++ b/kernel/gen_kheaders.sh @@ -21,29 +21,30 @@ arch/$SRCARCH/include/ # Uncomment it for debugging. # if [ ! -f /tmp/iter ]; then iter=1; echo 1 > /tmp/iter; # else iter=$(($(cat /tmp/iter) + 1)); echo $iter > /tmp/iter; fi -# find $src_file_list -name "*.h" | xargs ls -l > /tmp/src-ls-$iter -# find $obj_file_list -name "*.h" | xargs ls -l > /tmp/obj-ls-$iter +# find $all_dirs -name "*.h" | xargs ls -l > /tmp/ls-$iter + +all_dirs= +if [ "$building_out_of_srctree" ]; then + for d in $dir_list; do + all_dirs="$all_dirs $srctree/$d" + done +fi +all_dirs="$all_dirs $dir_list" # include/generated/compile.h is ignored because it is touched even when none # of the source files changed. This causes pointless regeneration, so let us # ignore them for md5 calculation. -pushd $srctree > /dev/null -src_files_md5="$(find $dir_list -name "*.h" | - grep -v "include/generated/compile.h" | - grep -v "include/generated/autoconf.h" | - xargs ls -l | md5sum | cut -d ' ' -f1)" -popd > /dev/null -obj_files_md5="$(find $dir_list -name "*.h" | - grep -v "include/generated/compile.h" | - grep -v "include/generated/autoconf.h" | +headers_md5="$(find $all_dirs -name "*.h" | + grep -v "include/generated/compile.h" | + grep -v "include/generated/autoconf.h" | xargs ls -l | md5sum | cut -d ' ' -f1)" + # Any changes to this script will also cause a rebuild of the archive. this_file_md5="$(ls -l $sfile | md5sum | cut -d ' ' -f1)" if [ -f $tarfile ]; then tarfile_md5="$(md5sum $tarfile | cut -d ' ' -f1)"; fi if [ -f kernel/kheaders.md5 ] && - [ "$(head -n 1 kernel/kheaders.md5)" = "$src_files_md5" ] && - [ "$(head -n 2 kernel/kheaders.md5 | tail -n 1)" = "$obj_files_md5" ] && - [ "$(head -n 3 kernel/kheaders.md5 | tail -n 1)" = "$this_file_md5" ] && + [ "$(head -n 1 kernel/kheaders.md5)" = "$headers_md5" ] && + [ "$(head -n 2 kernel/kheaders.md5 | tail -n 1)" = "$this_file_md5" ] && [ "$(tail -n 1 kernel/kheaders.md5)" = "$tarfile_md5" ]; then exit fi @@ -79,8 +80,7 @@ find $cpio_dir -printf "./%P\n" | LC_ALL=C sort | \ --owner=0 --group=0 --numeric-owner --no-recursion \ -Jcf $tarfile -C $cpio_dir/ -T - > /dev/null -echo "$src_files_md5" > kernel/kheaders.md5 -echo "$obj_files_md5" >> kernel/kheaders.md5 +echo $headers_md5 > kernel/kheaders.md5 echo "$this_file_md5" >> kernel/kheaders.md5 echo "$(md5sum $tarfile | cut -d ' ' -f1)" >> kernel/kheaders.md5 -- cgit v1.2.3 From ea79e5168be644fdaf7d4e6a73eceaf07b3da76a Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Tue, 8 Oct 2019 21:05:54 +0900 Subject: kheaders: optimize header copy for in-tree builds This script copies headers by the cpio command twice; first from srctree, and then from objtree. However, when we building in-tree, we know the srctree and the objtree are the same. That is, all the headers copied by the first cpio are overwritten by the second one. Skip the first cpio when we are building in-tree. Signed-off-by: Masahiro Yamada --- kernel/gen_kheaders.sh | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) (limited to 'kernel') diff --git a/kernel/gen_kheaders.sh b/kernel/gen_kheaders.sh index 6ff86e62787f..0f7752dd93a6 100755 --- a/kernel/gen_kheaders.sh +++ b/kernel/gen_kheaders.sh @@ -56,14 +56,16 @@ fi rm -rf $cpio_dir mkdir $cpio_dir -pushd $srctree > /dev/null -for f in $dir_list; - do find "$f" -name "*.h"; -done | cpio --quiet -pd $cpio_dir -popd > /dev/null +if [ "$building_out_of_srctree" ]; then + pushd $srctree > /dev/null + for f in $dir_list + do find "$f" -name "*.h"; + done | cpio --quiet -pd $cpio_dir + popd > /dev/null +fi -# The second CPIO can complain if files already exist which can -# happen with out of tree builds. Just silence CPIO for now. +# The second CPIO can complain if files already exist which can happen with out +# of tree builds having stale headers in srctree. Just silence CPIO for now. for f in $dir_list; do find "$f" -name "*.h"; done | cpio --quiet -pd $cpio_dir >/dev/null 2>&1 -- cgit v1.2.3 From 1463f74f492eea7191f0178e01f3d38371a48210 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Tue, 8 Oct 2019 21:05:55 +0900 Subject: kheaders: remove the last bashism to allow sh to run it 'pushd' ... 'popd' is the last bash-specific code in this script. One way to avoid it is to run the code in a sub-shell. With that addressed, you can run this script with sh. I replaced $(BASH) with $(CONFIG_SHELL), and I changed the hashbang to #!/bin/sh. Signed-off-by: Masahiro Yamada --- kernel/Makefile | 2 +- kernel/gen_kheaders.sh | 13 +++++++------ 2 files changed, 8 insertions(+), 7 deletions(-) (limited to 'kernel') diff --git a/kernel/Makefile b/kernel/Makefile index daad787fb795..42557f251fea 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -128,7 +128,7 @@ $(obj)/config_data.gz: $(KCONFIG_CONFIG) FORCE $(obj)/kheaders.o: $(obj)/kheaders_data.tar.xz quiet_cmd_genikh = CHK $(obj)/kheaders_data.tar.xz - cmd_genikh = $(BASH) $(srctree)/kernel/gen_kheaders.sh $@ + cmd_genikh = $(CONFIG_SHELL) $(srctree)/kernel/gen_kheaders.sh $@ $(obj)/kheaders_data.tar.xz: FORCE $(call cmd,genikh) diff --git a/kernel/gen_kheaders.sh b/kernel/gen_kheaders.sh index 0f7752dd93a6..dc5744b93f8c 100755 --- a/kernel/gen_kheaders.sh +++ b/kernel/gen_kheaders.sh @@ -1,4 +1,4 @@ -#!/bin/bash +#!/bin/sh # SPDX-License-Identifier: GPL-2.0 # This script generates an archive consisting of kernel headers @@ -57,11 +57,12 @@ rm -rf $cpio_dir mkdir $cpio_dir if [ "$building_out_of_srctree" ]; then - pushd $srctree > /dev/null - for f in $dir_list - do find "$f" -name "*.h"; - done | cpio --quiet -pd $cpio_dir - popd > /dev/null + ( + cd $srctree + for f in $dir_list + do find "$f" -name "*.h"; + done | cpio --quiet -pd $cpio_dir + ) fi # The second CPIO can complain if files already exist which can happen with out -- cgit v1.2.3 From f276031b4e2f4c961ed6d8a42f0f0124ccac2e09 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Tue, 8 Oct 2019 21:05:56 +0900 Subject: kheaders: explain why include/config/autoconf.h is excluded from md5sum This comment block explains why include/generated/compile.h is omitted, but nothing about include/generated/autoconf.h, which might be more difficult to understand. Add more comments. Signed-off-by: Masahiro Yamada --- kernel/gen_kheaders.sh | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/gen_kheaders.sh b/kernel/gen_kheaders.sh index dc5744b93f8c..e13ca842eb7e 100755 --- a/kernel/gen_kheaders.sh +++ b/kernel/gen_kheaders.sh @@ -32,8 +32,15 @@ fi all_dirs="$all_dirs $dir_list" # include/generated/compile.h is ignored because it is touched even when none -# of the source files changed. This causes pointless regeneration, so let us -# ignore them for md5 calculation. +# of the source files changed. +# +# When Kconfig regenerates include/generated/autoconf.h, its timestamp is +# updated, but the contents might be still the same. When any CONFIG option is +# changed, Kconfig touches the corresponding timestamp file include/config/*.h. +# Hence, the md5sum detects the configuration change anyway. We do not need to +# check include/generated/autoconf.h explicitly. +# +# Ignore them for md5 calculation to avoid pointless regeneration. headers_md5="$(find $all_dirs -name "*.h" | grep -v "include/generated/compile.h" | grep -v "include/generated/autoconf.h" | -- cgit v1.2.3 From 20d087368d38c7350a4519a3b316ef7eb2504692 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 8 Nov 2019 21:34:25 +0100 Subject: time: Optimize ns_to_timespec64() ns_to_timespec64() calls div_s64_rem(), which is a rather slow function on 32-bit architectures, as it cannot take advantage of the do_div() optimizations for constant arguments. Open-code the div_s64_rem() function in ns_to_timespec64(), so a constant divider can be passed into the optimized div_u64_rem() function. Signed-off-by: Arnd Bergmann Signed-off-by: Thomas Gleixner Link: https://lkml.kernel.org/r/20191108203435.112759-3-arnd@arndb.de --- kernel/time/time.c | 21 ++++++++++++--------- 1 file changed, 12 insertions(+), 9 deletions(-) (limited to 'kernel') diff --git a/kernel/time/time.c b/kernel/time/time.c index 5c54ca632d08..45a358953f09 100644 --- a/kernel/time/time.c +++ b/kernel/time/time.c @@ -550,18 +550,21 @@ EXPORT_SYMBOL(set_normalized_timespec64); */ struct timespec64 ns_to_timespec64(const s64 nsec) { - struct timespec64 ts; + struct timespec64 ts = { 0, 0 }; s32 rem; - if (!nsec) - return (struct timespec64) {0, 0}; - - ts.tv_sec = div_s64_rem(nsec, NSEC_PER_SEC, &rem); - if (unlikely(rem < 0)) { - ts.tv_sec--; - rem += NSEC_PER_SEC; + if (likely(nsec > 0)) { + ts.tv_sec = div_u64_rem(nsec, NSEC_PER_SEC, &rem); + ts.tv_nsec = rem; + } else if (nsec < 0) { + /* + * With negative times, tv_sec points to the earlier + * second, and tv_nsec counts the nanoseconds since + * then, so tv_nsec is always a positive number. + */ + ts.tv_sec = -div_u64_rem(-nsec - 1, NSEC_PER_SEC, &rem) - 1; + ts.tv_nsec = NSEC_PER_SEC - rem - 1; } - ts.tv_nsec = rem; return ts; } -- cgit v1.2.3 From 1d6acc18fee71a0db6e4fbbfbdb247e0bd5b0655 Mon Sep 17 00:00:00 2001 From: Mukesh Ojha Date: Tue, 15 Oct 2019 13:03:39 +0530 Subject: time: Fix spelling mistake in comment witin => within Signed-off-by: Mukesh Ojha Signed-off-by: Thomas Gleixner Link: https://lkml.kernel.org/r/1571124819-9639-1-git-send-email-mojha@codeaurora.org --- kernel/time/time.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/time/time.c b/kernel/time/time.c index 45a358953f09..ea6e7e47cc37 100644 --- a/kernel/time/time.c +++ b/kernel/time/time.c @@ -179,7 +179,7 @@ int do_sys_settimeofday64(const struct timespec64 *tv, const struct timezone *tz return error; if (tz) { - /* Verify we're witin the +-15 hrs range */ + /* Verify we're within the +-15 hrs range */ if (tz->tz_minuteswest > 15*60 || tz->tz_minuteswest < -15*60) return -EINVAL; -- cgit v1.2.3 From cf25e24db61cc9df42c47485a2ec2bff4e9a3692 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 7 Nov 2019 11:07:58 +0100 Subject: time: Rename tsk->real_start_time to ->start_boottime Since it stores CLOCK_BOOTTIME, not, as the name suggests, CLOCK_REALTIME, let's rename ->real_start_time to ->start_bootime. Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar --- kernel/fork.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/fork.c b/kernel/fork.c index bcdf53125210..1392ee8f4848 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -2130,7 +2130,7 @@ static __latent_entropy struct task_struct *copy_process( */ p->start_time = ktime_get_ns(); - p->real_start_time = ktime_get_boottime_ns(); + p->start_boottime = ktime_get_boottime_ns(); /* * Make it visible to the rest of the system, but dont wake it up yet. -- cgit v1.2.3 From e9838bd51169af87ae248336d4c3fc59184a0e46 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Wed, 13 Nov 2019 18:12:01 +0100 Subject: irq_work: Fix IRQ_WORK_BUSY bit clearing While attempting to clear the busy bit at the end of a work execution, atomic_cmpxchg() expects the value of the flags with the pending bit cleared as the old value. However by mistake the value of the flags is passed without clearing the pending bit first. As a result, clearing the busy bit fails and irq_work_sync() may stall: watchdog: BUG: soft lockup - CPU#0 stuck for 22s! [blktrace:4948] CPU: 0 PID: 4948 Comm: blktrace Not tainted 5.4.0-rc7-00003-gfeb4a51323bab #1 RIP: 0010:irq_work_sync+0x4/0x10 Call Trace: relay_close_buf+0x19/0x50 relay_close+0x64/0x100 blk_trace_free+0x1f/0x50 __blk_trace_remove+0x1e/0x30 blk_trace_ioctl+0x11b/0x140 blkdev_ioctl+0x6c1/0xa40 block_ioctl+0x39/0x40 do_vfs_ioctl+0xa5/0x700 ksys_ioctl+0x70/0x80 __x64_sys_ioctl+0x16/0x20 do_syscall_64+0x5b/0x1d0 entry_SYSCALL_64_after_hwframe+0x44/0xa9 So clear the appropriate bit before passing the old flags to cmpxchg(). Fixes: feb4a51323ba ("irq_work: Slightly simplify IRQ_WORK_PENDING clearing") Reported-by: kernel test robot Reported-by: Leonard Crestez Signed-off-by: Frederic Weisbecker Signed-off-by: Thomas Gleixner Tested-by: Leonard Crestez Link: https://lkml.kernel.org/r/20191113171201.14032-1-frederic@kernel.org --- kernel/irq_work.c | 1 + 1 file changed, 1 insertion(+) (limited to 'kernel') diff --git a/kernel/irq_work.c b/kernel/irq_work.c index 49c53f80a13a..828cc30774bc 100644 --- a/kernel/irq_work.c +++ b/kernel/irq_work.c @@ -158,6 +158,7 @@ static void irq_work_run_list(struct llist_head *list) * Clear the BUSY bit and return to the free state if * no-one else claimed it meanwhile. */ + flags &= ~IRQ_WORK_PENDING; (void)atomic_cmpxchg(&work->flags, flags, flags & ~IRQ_WORK_BUSY); } } -- cgit v1.2.3 From 20a15ee040f23bd553d4e6bbb1f8724ccd282abc Mon Sep 17 00:00:00 2001 From: luanshi Date: Wed, 13 Nov 2019 22:41:33 +0800 Subject: genirq: Fix function documentation of __irq_alloc_descs() The function got renamed at some point, but the kernel-doc was not updated. Signed-off-by: Liguang Zhang Signed-off-by: Thomas Gleixner Link: https://lkml.kernel.org/r/1573656093-8643-1-git-send-email-zhangliguang@linux.alibaba.com --- kernel/irq/irqdesc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c index 9be995fc3c5a..5b8fdd659e54 100644 --- a/kernel/irq/irqdesc.c +++ b/kernel/irq/irqdesc.c @@ -750,7 +750,7 @@ void irq_free_descs(unsigned int from, unsigned int cnt) EXPORT_SYMBOL_GPL(irq_free_descs); /** - * irq_alloc_descs - allocate and initialize a range of irq descriptors + * __irq_alloc_descs - allocate and initialize a range of irq descriptors * @irq: Allocate for specific irq number if irq >= 0 * @from: Start the search from this irq number * @cnt: Number of consecutive irqs to allocate. -- cgit v1.2.3 From 5d603311615f612320bb77bd2a82553ef1ced5b7 Mon Sep 17 00:00:00 2001 From: Konstantin Khorenko Date: Wed, 13 Nov 2019 12:29:50 +0300 Subject: kernel/module.c: wakeup processes in module_wq on module unload Fix the race between load and unload a kernel module. sys_delete_module() try_stop_module() mod->state = _GOING add_unformed_module() old = find_module_all() (old->state == _GOING => wait_event_interruptible()) During pre-condition finished_loading() rets 0 schedule() (never gets waken up later) free_module() mod->state = _UNFORMED list_del_rcu(&mod->list) (dels mod from "modules" list) return The race above leads to modprobe hanging forever on loading a module. Error paths on loading module call wake_up_all(&module_wq) after freeing module, so let's do the same on straight module unload. Fixes: 6e6de3dee51a ("kernel/module.c: Only return -EEXIST for modules that have finished loading") Reviewed-by: Prarit Bhargava Signed-off-by: Konstantin Khorenko Signed-off-by: Jessica Yu --- kernel/module.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'kernel') diff --git a/kernel/module.c b/kernel/module.c index 26c13173da3d..bdbf95726cb7 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -1033,6 +1033,8 @@ SYSCALL_DEFINE2(delete_module, const char __user *, name_user, strlcpy(last_unloaded_module, mod->name, sizeof(last_unloaded_module)); free_module(mod); + /* someone could wait for the module in add_unformed_module() */ + wake_up_all(&module_wq); return 0; out: mutex_unlock(&module_mutex); -- cgit v1.2.3 From 4a169a95d885fe5c050bac1a21d43c86ba955bcf Mon Sep 17 00:00:00 2001 From: Maulik Shah Date: Fri, 15 Nov 2019 15:11:49 -0700 Subject: genirq: Introduce irq_chip_get/set_parent_state calls On certain QTI chipsets some GPIOs are direct-connect interrupts to the GIC to be used as regular interrupt lines. When the GPIOs are not used for interrupt generation the interrupt line is disabled. But disabling the interrupt at GIC does not prevent the interrupt to be reported as pending at GIC_ISPEND. Later, when drivers call enable_irq() on the interrupt, an unwanted interrupt occurs. Introduce get and set methods for irqchip's parent to clear it's pending irq state. This then can be invoked by the GPIO interrupt controller on the parents in it hierarchy to clear the interrupt before enabling the interrupt. Signed-off-by: Maulik Shah Signed-off-by: Lina Iyer Signed-off-by: Marc Zyngier Reviewed-by: Stephen Boyd Link: https://lore.kernel.org/r/1573855915-9841-7-git-send-email-ilina@codeaurora.org [updated commit text and minor code fixes] --- kernel/irq/chip.c | 44 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 44 insertions(+) (limited to 'kernel') diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index b76703b2c0af..b3fa2d87d2f3 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -1297,6 +1297,50 @@ EXPORT_SYMBOL_GPL(handle_fasteoi_mask_irq); #endif /* CONFIG_IRQ_FASTEOI_HIERARCHY_HANDLERS */ +/** + * irq_chip_set_parent_state - set the state of a parent interrupt. + * + * @data: Pointer to interrupt specific data + * @which: State to be restored (one of IRQCHIP_STATE_*) + * @val: Value corresponding to @which + * + * Conditional success, if the underlying irqchip does not implement it. + */ +int irq_chip_set_parent_state(struct irq_data *data, + enum irqchip_irq_state which, + bool val) +{ + data = data->parent_data; + + if (!data || !data->chip->irq_set_irqchip_state) + return 0; + + return data->chip->irq_set_irqchip_state(data, which, val); +} +EXPORT_SYMBOL_GPL(irq_chip_set_parent_state); + +/** + * irq_chip_get_parent_state - get the state of a parent interrupt. + * + * @data: Pointer to interrupt specific data + * @which: one of IRQCHIP_STATE_* the caller wants to know + * @state: a pointer to a boolean where the state is to be stored + * + * Conditional success, if the underlying irqchip does not implement it. + */ +int irq_chip_get_parent_state(struct irq_data *data, + enum irqchip_irq_state which, + bool *state) +{ + data = data->parent_data; + + if (!data || !data->chip->irq_get_irqchip_state) + return 0; + + return data->chip->irq_get_irqchip_state(data, which, state); +} +EXPORT_SYMBOL_GPL(irq_chip_get_parent_state); + /** * irq_chip_enable_parent - Enable the parent interrupt (defaults to unmask if * NULL) -- cgit v1.2.3 From 7b8474466ed97be458c825f34a85f2c2b84c3f95 Mon Sep 17 00:00:00 2001 From: Dmitry Safonov Date: Thu, 21 Nov 2019 00:03:03 +0000 Subject: time: Zero the upper 32-bits in __kernel_timespec on 32-bit On compat interfaces, the high order bits of nanoseconds should be zeroed out. This is because the application code or the libc do not guarantee zeroing of these. If used without zeroing, kernel might be at risk of using timespec values incorrectly. Originally it was handled correctly, but lost during is_compat_syscall() cleanup. Revert the condition back to check CONFIG_64BIT. Fixes: 98f76206b335 ("compat: Cleanup in_compat_syscall() callers") Reported-by: Ben Hutchings Signed-off-by: Dmitry Safonov Signed-off-by: Thomas Gleixner Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20191121000303.126523-1-dima@arista.com --- kernel/time/time.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/time/time.c b/kernel/time/time.c index 5c54ca632d08..83f403e7a15c 100644 --- a/kernel/time/time.c +++ b/kernel/time/time.c @@ -881,7 +881,8 @@ int get_timespec64(struct timespec64 *ts, ts->tv_sec = kts.tv_sec; /* Zero out the padding for 32 bit systems or in compat mode */ - if (IS_ENABLED(CONFIG_64BIT_TIME) && in_compat_syscall()) + if (IS_ENABLED(CONFIG_64BIT_TIME) && (!IS_ENABLED(CONFIG_64BIT) || + in_compat_syscall())) kts.tv_nsec &= 0xFFFFFFFFUL; ts->tv_nsec = kts.tv_nsec; -- cgit v1.2.3 From d0f010434124598988ba1c97fbb0e4e820ff5d8c Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Tue, 26 Nov 2019 15:01:06 -0800 Subject: bpf: Fix static checker warning kernel/bpf/btf.c:4023 btf_distill_func_proto() error: potentially dereferencing uninitialized 't'. kernel/bpf/btf.c 4012 nargs = btf_type_vlen(func); 4013 if (nargs >= MAX_BPF_FUNC_ARGS) { 4014 bpf_log(log, 4015 "The function %s has %d arguments. Too many.\n", 4016 tname, nargs); 4017 return -EINVAL; 4018 } 4019 ret = __get_type_size(btf, func->type, &t); ^^ t isn't initialized for the first -EINVAL return This is unlikely path, since BTF should have been validated at this point. Fix it by returning 'void' BTF. Reported-by: Dan Carpenter Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20191126230106.237179-1-ast@kernel.org --- kernel/bpf/btf.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 40efde5eedcb..bd5e11881ba3 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -3976,8 +3976,10 @@ static int __get_type_size(struct btf *btf, u32 btf_id, t = btf_type_by_id(btf, btf_id); while (t && btf_type_is_modifier(t)) t = btf_type_by_id(btf, t->type); - if (!t) + if (!t) { + *bad_type = btf->types[0]; return -EINVAL; + } if (btf_type_is_ptr(t)) /* kernel size of pointer. Not BPF's size of pointer*/ return sizeof(void *); -- cgit v1.2.3 From ce27709b8162e5c501bc54292b8bf6bdecc4bbd4 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Wed, 27 Nov 2019 20:35:08 -0800 Subject: bpf: Fix build in minimal configurations Some kconfigs can have BPF enabled without a single valid program type. In such configurations the build will fail with: ./kernel/bpf/btf.c:3466:1: error: empty enum is invalid Fix it by adding unused value to the enum. Reported-by: Randy Dunlap Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann Acked-by: Randy Dunlap # build-tested Link: https://lore.kernel.org/bpf/20191128043508.2346723-1-ast@kernel.org --- kernel/bpf/btf.c | 1 + 1 file changed, 1 insertion(+) (limited to 'kernel') diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index bd5e11881ba3..7d40da240891 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -3463,6 +3463,7 @@ enum { __ctx_convert##_id, #include #undef BPF_PROG_TYPE + __ctx_convert_unused, /* to avoid empty enum in extreme .config */ }; static u8 bpf_ctx_convert_map[] = { #define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type) \ -- cgit v1.2.3 From 36a8015f89e40f7c9c91cc7e6d028fa288dad27b Mon Sep 17 00:00:00 2001 From: Leonard Crestez Date: Tue, 26 Nov 2019 17:17:13 +0200 Subject: PM / QoS: Restore DEV_PM_QOS_MIN/MAX_FREQUENCY Support for adding per-device frequency limits was removed in commit 2aac8bdf7a0f ("PM: QoS: Drop frequency QoS types from device PM QoS") after cpufreq switched to use a new "freq_constraints" construct. Restore support for per-device freq limits but base this upon freq_constraints. This is primarily meant to be used by the devfreq subsystem. This removes the "static" marking on freq_qos_apply but does not export it for modules. Signed-off-by: Leonard Crestez Reviewed-by: Matthias Kaehlcke Tested-by: Matthias Kaehlcke Signed-off-by: Rafael J. Wysocki --- kernel/power/qos.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/power/qos.c b/kernel/power/qos.c index a45cba7df0ae..83edf8698118 100644 --- a/kernel/power/qos.c +++ b/kernel/power/qos.c @@ -714,8 +714,10 @@ s32 freq_qos_read_value(struct freq_constraints *qos, * @req: Constraint request to apply. * @action: Action to perform (add/update/remove). * @value: Value to assign to the QoS request. + * + * This is only meant to be called from inside pm_qos, not drivers. */ -static int freq_qos_apply(struct freq_qos_request *req, +int freq_qos_apply(struct freq_qos_request *req, enum pm_qos_req_action action, s32 value) { int ret; -- cgit v1.2.3 From 6c3edaf9fd6a3be7fb5bc6931897c24cd3848f84 Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Fri, 29 Nov 2019 20:52:18 -0800 Subject: tracing: Introduce trace event injection We have been trying to use rasdaemon to monitor hardware errors like correctable memory errors. rasdaemon uses trace events to monitor various hardware errors. In order to test it, we have to inject some hardware errors, unfortunately not all of them provide error injections. MCE does provide a way to inject MCE errors, but errors like PCI error and devlink error don't, it is not easy to add error injection to each of them. Instead, it is relatively easier to just allow users to inject trace events in a generic way so that all trace events can be injected. This patch introduces trace event injection, where a new 'inject' is added to each tracepoint directory. Users could write into this file with key=value pairs to specify the value of each fields of the trace event, all unspecified fields are set to zero values by default. For example, for the net/net_dev_queue tracepoint, we can inject: INJECT=/sys/kernel/debug/tracing/events/net/net_dev_queue/inject echo "" > $INJECT echo "name='test'" > $INJECT echo "name='test' len=1024" > $INJECT cat /sys/kernel/debug/tracing/trace ... <...>-614 [000] .... 36.571483: net_dev_queue: dev= skbaddr=00000000fbf338c2 len=0 <...>-614 [001] .... 136.588252: net_dev_queue: dev=test skbaddr=00000000fbf338c2 len=0 <...>-614 [001] .N.. 208.431878: net_dev_queue: dev=test skbaddr=00000000fbf338c2 len=1024 Triggers could be triggered as usual too: echo "stacktrace if len == 1025" > /sys/kernel/debug/tracing/events/net/net_dev_queue/trigger echo "len=1025" > $INJECT cat /sys/kernel/debug/tracing/trace ... bash-614 [000] .... 36.571483: net_dev_queue: dev= skbaddr=00000000fbf338c2 len=0 bash-614 [001] .... 136.588252: net_dev_queue: dev=test skbaddr=00000000fbf338c2 len=0 bash-614 [001] .N.. 208.431878: net_dev_queue: dev=test skbaddr=00000000fbf338c2 len=1024 bash-614 [001] .N.1 284.236349: => event_inject_write => vfs_write => ksys_write => do_syscall_64 => entry_SYSCALL_64_after_hwframe The only thing that can't be injected is string pointers as they require constant string pointers, this can't be done at run time. Link: http://lkml.kernel.org/r/20191130045218.18979-1-xiyou.wangcong@gmail.com Cc: Ingo Molnar Signed-off-by: Cong Wang Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/Kconfig | 9 + kernel/trace/Makefile | 1 + kernel/trace/trace.h | 1 + kernel/trace/trace_events.c | 6 + kernel/trace/trace_events_inject.c | 331 +++++++++++++++++++++++++++++++++++++ 5 files changed, 348 insertions(+) create mode 100644 kernel/trace/trace_events_inject.c (limited to 'kernel') diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index f67620499faa..29a9c5058b62 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -672,6 +672,15 @@ config HIST_TRIGGERS See Documentation/trace/histogram.rst. If in doubt, say N. +config TRACE_EVENT_INJECT + bool "Trace event injection" + depends on TRACING + help + Allow user-space to inject a specific trace event into the ring + buffer. This is mainly used for testing purpose. + + If unsure, say N. + config MMIOTRACE_TEST tristate "Test module for mmiotrace" depends on MMIOTRACE && m diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile index c2b2148bb1d2..0e63db62225f 100644 --- a/kernel/trace/Makefile +++ b/kernel/trace/Makefile @@ -69,6 +69,7 @@ obj-$(CONFIG_EVENT_TRACING) += trace_event_perf.o endif obj-$(CONFIG_EVENT_TRACING) += trace_events_filter.o obj-$(CONFIG_EVENT_TRACING) += trace_events_trigger.o +obj-$(CONFIG_TRACE_EVENT_INJECT) += trace_events_inject.o obj-$(CONFIG_HIST_TRIGGERS) += trace_events_hist.o obj-$(CONFIG_BPF_EVENTS) += bpf_trace.o obj-$(CONFIG_KPROBE_EVENTS) += trace_kprobe.o diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index ca7fccafbcbb..63bf60f79398 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -1601,6 +1601,7 @@ extern struct list_head ftrace_events; extern const struct file_operations event_trigger_fops; extern const struct file_operations event_hist_fops; +extern const struct file_operations event_inject_fops; #ifdef CONFIG_HIST_TRIGGERS extern int register_trigger_hist_cmd(void); diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 6b3a69e9aa6a..c6de3cebc127 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -2044,6 +2044,12 @@ event_create_dir(struct dentry *parent, struct trace_event_file *file) trace_create_file("format", 0444, file->dir, call, &ftrace_event_format_fops); +#ifdef CONFIG_TRACE_EVENT_INJECT + if (call->event.type && call->class->reg) + trace_create_file("inject", 0200, file->dir, file, + &event_inject_fops); +#endif + return 0; } diff --git a/kernel/trace/trace_events_inject.c b/kernel/trace/trace_events_inject.c new file mode 100644 index 000000000000..d43710718ee5 --- /dev/null +++ b/kernel/trace/trace_events_inject.c @@ -0,0 +1,331 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * trace_events_inject - trace event injection + * + * Copyright (C) 2019 Cong Wang + */ + +#include +#include +#include +#include +#include + +#include "trace.h" + +static int +trace_inject_entry(struct trace_event_file *file, void *rec, int len) +{ + struct trace_event_buffer fbuffer; + struct ring_buffer *buffer; + int written = 0; + void *entry; + + rcu_read_lock_sched(); + buffer = file->tr->trace_buffer.buffer; + entry = trace_event_buffer_reserve(&fbuffer, file, len); + if (entry) { + memcpy(entry, rec, len); + written = len; + trace_event_buffer_commit(&fbuffer); + } + rcu_read_unlock_sched(); + + return written; +} + +static int +parse_field(char *str, struct trace_event_call *call, + struct ftrace_event_field **pf, u64 *pv) +{ + struct ftrace_event_field *field; + char *field_name; + int s, i = 0; + int len; + u64 val; + + if (!str[i]) + return 0; + /* First find the field to associate to */ + while (isspace(str[i])) + i++; + s = i; + while (isalnum(str[i]) || str[i] == '_') + i++; + len = i - s; + if (!len) + return -EINVAL; + + field_name = kmemdup_nul(str + s, len, GFP_KERNEL); + if (!field_name) + return -ENOMEM; + field = trace_find_event_field(call, field_name); + kfree(field_name); + if (!field) + return -ENOENT; + + *pf = field; + while (isspace(str[i])) + i++; + if (str[i] != '=') + return -EINVAL; + i++; + while (isspace(str[i])) + i++; + s = i; + if (isdigit(str[i]) || str[i] == '-') { + char *num, c; + int ret; + + /* Make sure the field is not a string */ + if (is_string_field(field)) + return -EINVAL; + + if (str[i] == '-') + i++; + + /* We allow 0xDEADBEEF */ + while (isalnum(str[i])) + i++; + num = str + s; + c = str[i]; + if (c != '\0' && !isspace(c)) + return -EINVAL; + str[i] = '\0'; + /* Make sure it is a value */ + if (field->is_signed) + ret = kstrtoll(num, 0, &val); + else + ret = kstrtoull(num, 0, &val); + str[i] = c; + if (ret) + return ret; + + *pv = val; + return i; + } else if (str[i] == '\'' || str[i] == '"') { + char q = str[i]; + + /* Make sure the field is OK for strings */ + if (!is_string_field(field)) + return -EINVAL; + + for (i++; str[i]; i++) { + if (str[i] == '\\' && str[i + 1]) { + i++; + continue; + } + if (str[i] == q) + break; + } + if (!str[i]) + return -EINVAL; + + /* Skip quotes */ + s++; + len = i - s; + if (len >= MAX_FILTER_STR_VAL) + return -EINVAL; + + *pv = (unsigned long)(str + s); + str[i] = 0; + /* go past the last quote */ + i++; + return i; + } + + return -EINVAL; +} + +static int trace_get_entry_size(struct trace_event_call *call) +{ + struct ftrace_event_field *field; + struct list_head *head; + int size = 0; + + head = trace_get_fields(call); + list_for_each_entry(field, head, link) { + if (field->size + field->offset > size) + size = field->size + field->offset; + } + + return size; +} + +static void *trace_alloc_entry(struct trace_event_call *call, int *size) +{ + int entry_size = trace_get_entry_size(call); + struct ftrace_event_field *field; + struct list_head *head; + void *entry = NULL; + + /* We need an extra '\0' at the end. */ + entry = kzalloc(entry_size + 1, GFP_KERNEL); + if (!entry) + return NULL; + + head = trace_get_fields(call); + list_for_each_entry(field, head, link) { + if (!is_string_field(field)) + continue; + if (field->filter_type == FILTER_STATIC_STRING) + continue; + if (field->filter_type == FILTER_DYN_STRING) { + u32 *str_item; + int str_loc = entry_size & 0xffff; + + str_item = (u32 *)(entry + field->offset); + *str_item = str_loc; /* string length is 0. */ + } else { + char **paddr; + + paddr = (char **)(entry + field->offset); + *paddr = ""; + } + } + + *size = entry_size + 1; + return entry; +} + +#define INJECT_STRING "STATIC STRING CAN NOT BE INJECTED" + +/* Caller is responsible to free the *pentry. */ +static int parse_entry(char *str, struct trace_event_call *call, void **pentry) +{ + struct ftrace_event_field *field; + unsigned long irq_flags; + void *entry = NULL; + int entry_size; + u64 val; + int len; + + entry = trace_alloc_entry(call, &entry_size); + *pentry = entry; + if (!entry) + return -ENOMEM; + + local_save_flags(irq_flags); + tracing_generic_entry_update(entry, call->event.type, irq_flags, + preempt_count()); + + while ((len = parse_field(str, call, &field, &val)) > 0) { + if (is_function_field(field)) + return -EINVAL; + + if (is_string_field(field)) { + char *addr = (char *)(unsigned long) val; + + if (field->filter_type == FILTER_STATIC_STRING) { + strlcpy(entry + field->offset, addr, field->size); + } else if (field->filter_type == FILTER_DYN_STRING) { + int str_len = strlen(addr) + 1; + int str_loc = entry_size & 0xffff; + u32 *str_item; + + entry_size += str_len; + *pentry = krealloc(entry, entry_size, GFP_KERNEL); + if (!*pentry) { + kfree(entry); + return -ENOMEM; + } + entry = *pentry; + + strlcpy(entry + (entry_size - str_len), addr, str_len); + str_item = (u32 *)(entry + field->offset); + *str_item = (str_len << 16) | str_loc; + } else { + char **paddr; + + paddr = (char **)(entry + field->offset); + *paddr = INJECT_STRING; + } + } else { + switch (field->size) { + case 1: { + u8 tmp = (u8) val; + + memcpy(entry + field->offset, &tmp, 1); + break; + } + case 2: { + u16 tmp = (u16) val; + + memcpy(entry + field->offset, &tmp, 2); + break; + } + case 4: { + u32 tmp = (u32) val; + + memcpy(entry + field->offset, &tmp, 4); + break; + } + case 8: + memcpy(entry + field->offset, &val, 8); + break; + default: + return -EINVAL; + } + } + + str += len; + } + + if (len < 0) + return len; + + return entry_size; +} + +static ssize_t +event_inject_write(struct file *filp, const char __user *ubuf, size_t cnt, + loff_t *ppos) +{ + struct trace_event_call *call; + struct trace_event_file *file; + int err = -ENODEV, size; + void *entry = NULL; + char *buf; + + if (cnt >= PAGE_SIZE) + return -EINVAL; + + buf = memdup_user_nul(ubuf, cnt); + if (IS_ERR(buf)) + return PTR_ERR(buf); + strim(buf); + + mutex_lock(&event_mutex); + file = event_file_data(filp); + if (file) { + call = file->event_call; + size = parse_entry(buf, call, &entry); + if (size < 0) + err = size; + else + err = trace_inject_entry(file, entry, size); + } + mutex_unlock(&event_mutex); + + kfree(entry); + kfree(buf); + + if (err < 0) + return err; + + *ppos += err; + return cnt; +} + +static ssize_t +event_inject_read(struct file *file, char __user *buf, size_t size, + loff_t *ppos) +{ + return -EPERM; +} + +const struct file_operations event_inject_fops = { + .open = tracing_open_generic, + .read = event_inject_read, + .write = event_inject_write, +}; -- cgit v1.2.3 From a356646a56857c2e5ad875beec734d7145ecd49a Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Mon, 2 Dec 2019 16:25:27 -0500 Subject: tracing: Do not create directories if lockdown is in affect If lockdown is disabling tracing on boot up, it prevents the tracing files from even bering created. But when that happens, there's several places that will give a warning that the files were not created as that is usually a sign of a bug. Add in strategic locations where a check is made to see if tracing is disabled by lockdown, and if it is, do not go further, and fail silently (but print that tracing is disabled by lockdown, without doing a WARN_ON()). Cc: Matthew Garrett Fixes: 17911ff38aa5 ("tracing: Add locked_down checks to the open calls of files created for tracefs") Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/ring_buffer.c | 6 ++++++ kernel/trace/trace.c | 17 +++++++++++++++++ 2 files changed, 23 insertions(+) (limited to 'kernel') diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 66358d66c933..4bf050fcfe3b 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -11,6 +11,7 @@ #include #include #include +#include #include #include #include /* for self test */ @@ -5068,6 +5069,11 @@ static __init int test_ringbuffer(void) int cpu; int ret = 0; + if (security_locked_down(LOCKDOWN_TRACEFS)) { + pr_warning("Lockdown is enabled, skipping ring buffer tests\n"); + return 0; + } + pr_info("Running ring buffer tests...\n"); buffer = ring_buffer_alloc(RB_TEST_BUFFER_SIZE, RB_FL_OVERWRITE); diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 02a23a6e5e00..23459d53d576 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -1888,6 +1888,12 @@ int __init register_tracer(struct tracer *type) return -1; } + if (security_locked_down(LOCKDOWN_TRACEFS)) { + pr_warning("Can not register tracer %s due to lockdown\n", + type->name); + return -EPERM; + } + mutex_lock(&trace_types_lock); tracing_selftest_running = true; @@ -8789,6 +8795,11 @@ struct dentry *tracing_init_dentry(void) { struct trace_array *tr = &global_trace; + if (security_locked_down(LOCKDOWN_TRACEFS)) { + pr_warning("Tracing disabled due to lockdown\n"); + return ERR_PTR(-EPERM); + } + /* The top level trace array uses NULL as parent */ if (tr->dir) return NULL; @@ -9231,6 +9242,12 @@ __init static int tracer_alloc_buffers(void) int ring_buf_size; int ret = -ENOMEM; + + if (security_locked_down(LOCKDOWN_TRACEFS)) { + pr_warning("Tracing disabled due to lockdown\n"); + return -EPERM; + } + /* * Make sure we don't accidently add more trace options * than we have bits for. -- cgit v1.2.3 From 1a50cb80f219c44adb6265f5071b81fc3c1deced Mon Sep 17 00:00:00 2001 From: Xiaoming Ni Date: Wed, 4 Dec 2019 16:50:39 -0800 Subject: kernel/notifier.c: intercept duplicate registrations to avoid infinite loops Registering the same notifier to a hook repeatedly can cause the hook list to form a ring or lose other members of the list. case1: An infinite loop in notifier_chain_register() can cause soft lockup atomic_notifier_chain_register(&test_notifier_list, &test1); atomic_notifier_chain_register(&test_notifier_list, &test1); atomic_notifier_chain_register(&test_notifier_list, &test2); case2: An infinite loop in notifier_chain_register() can cause soft lockup atomic_notifier_chain_register(&test_notifier_list, &test1); atomic_notifier_chain_register(&test_notifier_list, &test1); atomic_notifier_call_chain(&test_notifier_list, 0, NULL); case3: lose other hook test2 atomic_notifier_chain_register(&test_notifier_list, &test1); atomic_notifier_chain_register(&test_notifier_list, &test2); atomic_notifier_chain_register(&test_notifier_list, &test1); case4: Unregister returns 0, but the hook is still in the linked list, and it is not really registered. If you call notifier_call_chain after ko is unloaded, it will trigger oops. If the system is configured with softlockup_panic and the same hook is repeatedly registered on the panic_notifier_list, it will cause a loop panic. Add a check in notifier_chain_register(), intercepting duplicate registrations to avoid infinite loops Link: http://lkml.kernel.org/r/1568861888-34045-2-git-send-email-nixiaoming@huawei.com Signed-off-by: Xiaoming Ni Reviewed-by: Vasily Averin Reviewed-by: Andrew Morton Cc: Alexey Dobriyan Cc: Anna Schumaker Cc: Arjan van de Ven Cc: J. Bruce Fields Cc: Chuck Lever Cc: David S. Miller Cc: Jeff Layton Cc: Andy Lutomirski Cc: Ingo Molnar Cc: Nadia Derbey Cc: "Paul E. McKenney" Cc: Sam Protsenko Cc: Alan Stern Cc: Thomas Gleixner Cc: Trond Myklebust Cc: Viresh Kumar Cc: Xiaoming Ni Cc: YueHaibing Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/notifier.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/notifier.c b/kernel/notifier.c index d9f5081d578d..30bedb8be6dd 100644 --- a/kernel/notifier.c +++ b/kernel/notifier.c @@ -23,7 +23,10 @@ static int notifier_chain_register(struct notifier_block **nl, struct notifier_block *n) { while ((*nl) != NULL) { - WARN_ONCE(((*nl) == n), "double register detected"); + if (unlikely((*nl) == n)) { + WARN(1, "double register detected"); + return 0; + } if (n->priority > (*nl)->priority) break; nl = &((*nl)