From 29bd03596e9511fa2f1a199d3a7603da28b32899 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Sat, 24 Sep 2016 23:29:51 +0200 Subject: Fix build warning in kernel/cpuset.c > 2 ../kernel/cpuset.c:2101:11: warning: initialization from incompatible pointer type [-Wincompatible-pointer-types] > 1 ../kernel/cpuset.c:2101:2: warning: initialization from incompatible pointer type > 1 ../kernel/cpuset.c:2101:2: warning: (near initialization for 'cpuset_cgrp_subsys.fork') This got introduced by 06ec7a1d7646 ("cpuset: make sure new tasks conform to the current config of the cpuset"). In the upstream kernel, the function prototype was changed as of b53202e63089 ("cgroup: kill cgrp_ss_priv[CGROUP_CANFORK_COUNT] and friends"). That patch is not suitable for stable kernels, and fortunately the warning seems harmless as the prototypes only differ in the second argument that is unused. Adding that argument gets rid of the warning: Signed-off-by: Greg Kroah-Hartman --- kernel/cpuset.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/cpuset.c b/kernel/cpuset.c index e120bd983ad0..b9279a2844d8 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -2079,7 +2079,7 @@ static void cpuset_bind(struct cgroup_subsys_state *root_css) * which could have been changed by cpuset just after it inherits the * state from the parent and before it sits on the cgroup's task list. */ -void cpuset_fork(struct task_struct *task) +void cpuset_fork(struct task_struct *task, void *priv) { if (task_css_is_root(task, cpuset_cgrp_id)) return; -- cgit v1.2.3 From a52031beb067ed3318c3ef226af5fa7223a7787d Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 28 Jul 2016 22:30:43 -0400 Subject: Makefile: Mute warning for __builtin_return_address(>0) for tracing only commit 377ccbb483738f84400ddf5840c7dd8825716985 upstream. With the latest gcc compilers, they give a warning if __builtin_return_address() parameter is greater than 0. That is because if it is used by a function called by a top level function (or in the case of the kernel, by assembly), it can try to access stack frames outside the stack and crash the system. The tracing system uses __builtin_return_address() of up to 2! But it is well aware of the dangers that it may have, and has even added precautions to protect against it (see the thunk code in arch/x86/entry/thunk*.S) Linus originally added KBUILD_CFLAGS that would suppress the warning for the entire kernel, as simply adding KBUILD_CFLAGS to the tracing directory wouldn't work. The tracing directory plays a bit with the CFLAGS and requires a little more logic. This adds that special logic to only suppress the warning for the tracing directory. If it is used anywhere else outside of tracing, the warning will still be triggered. Link: http://lkml.kernel.org/r/20160728223043.51996267@grimm.local.home Tested-by: Linus Torvalds Signed-off-by: Steven Rostedt Signed-off-by: Greg Kroah-Hartman --- kernel/trace/Makefile | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'kernel') diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile index 9b1044e936a6..05ea5167e6bb 100644 --- a/kernel/trace/Makefile +++ b/kernel/trace/Makefile @@ -1,4 +1,8 @@ +# We are fully aware of the dangers of __builtin_return_address() +FRAME_CFLAGS := $(call cc-disable-warning,frame-address) +KBUILD_CFLAGS += $(FRAME_CFLAGS) + # Do not instrument the tracer itself: ifdef CONFIG_FUNCTION_TRACER -- cgit v1.2.3 From 369796a8843ec9fce05129c6a80bee9e4b90978b Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 17 Sep 2016 18:31:46 -0400 Subject: fix memory leaks in tracing_buffers_splice_read() commit 1ae2293dd6d2f5c823cf97e60b70d03631cd622f upstream. Signed-off-by: Al Viro Signed-off-by: Greg Kroah-Hartman --- kernel/trace/trace.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 8305cbb2d5a2..3a44903169ec 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -5766,9 +5766,6 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos, return -EBUSY; #endif - if (splice_grow_spd(pipe, &spd)) - return -ENOMEM; - if (*ppos & (PAGE_SIZE - 1)) return -EINVAL; @@ -5778,6 +5775,9 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos, len &= PAGE_MASK; } + if (splice_grow_spd(pipe, &spd)) + return -ENOMEM; + again: trace_access_lock(iter->cpu_file); entries = ring_buffer_entries_cpu(iter->trace_buffer->buffer, iter->cpu_file); @@ -5835,19 +5835,21 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos, /* did we read anything? */ if (!spd.nr_pages) { if (ret) - return ret; + goto out; + ret = -EAGAIN; if ((file->f_flags & O_NONBLOCK) || (flags & SPLICE_F_NONBLOCK)) - return -EAGAIN; + goto out; ret = wait_on_pipe(iter, true); if (ret) - return ret; + goto out; goto again; } ret = splice_to_pipe(pipe, &spd); +out: splice_shrink_spd(&spd); return ret; -- cgit v1.2.3 From 8b275b4522af2b19072df7aee87fd659e09d29bc Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Red Hat)" Date: Fri, 23 Sep 2016 22:57:13 -0400 Subject: tracing: Move mutex to protect against resetting of seq data commit 1245800c0f96eb6ebb368593e251d66c01e61022 upstream. The iter->seq can be reset outside the protection of the mutex. So can reading of user data. Move the mutex up to the beginning of the function. Fixes: d7350c3f45694 ("tracing/core: make the read callbacks reentrants") Reported-by: Al Viro Signed-off-by: Steven Rostedt Signed-off-by: Greg Kroah-Hartman --- kernel/trace/trace.c | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 3a44903169ec..059233abcfcf 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -4727,19 +4727,20 @@ tracing_read_pipe(struct file *filp, char __user *ubuf, struct trace_iterator *iter = filp->private_data; ssize_t sret; - /* return any leftover data */ - sret = trace_seq_to_user(&iter->seq, ubuf, cnt); - if (sret != -EBUSY) - return sret; - - trace_seq_init(&iter->seq); - /* * Avoid more than one consumer on a single file descriptor * This is just a matter of traces coherency, the ring buffer itself * is protected. */ mutex_lock(&iter->mutex); + + /* return any leftover data */ + sret = trace_seq_to_user(&iter->seq, ubuf, cnt); + if (sret != -EBUSY) + goto out; + + trace_seq_init(&iter->seq); + if (iter->trace->read) { sret = iter->trace->read(iter, filp, ubuf, cnt, ppos); if (sret) -- cgit v1.2.3 From 119c348a8ef2765fb19c96f76480d4aaefdcae23 Mon Sep 17 00:00:00 2001 From: Thomas Garnier Date: Thu, 11 Aug 2016 14:49:29 -0700 Subject: PM / hibernate: Restore processor state before using per-CPU variables commit 62822e2ec4ad091ba31f823f577ef80db52e3c2c upstream. Restore the processor state before calling any other functions to ensure per-CPU variables can be used with KASLR memory randomization. Tracing functions use per-CPU variables (GS based on x86) and one was called just before restoring the processor state fully. It resulted in a double fault when both the tracing & the exception handler functions tried to use a per-CPU variable. Fixes: bb3632c6101b (PM / sleep: trace events for suspend/resume) Reported-and-tested-by: Borislav Petkov Reported-by: Jiri Kosina Tested-by: Rafael J. Wysocki Tested-by: Jiri Kosina Signed-off-by: Thomas Garnier Acked-by: Pavel Machek Signed-off-by: Rafael J. Wysocki Signed-off-by: Greg Kroah-Hartman --- kernel/power/hibernate.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c index b7dd5718836e..3124cebaec31 100644 --- a/kernel/power/hibernate.c +++ b/kernel/power/hibernate.c @@ -299,12 +299,12 @@ static int create_image(int platform_mode) save_processor_state(); trace_suspend_resume(TPS("machine_suspend"), PM_EVENT_HIBERNATE, true); error = swsusp_arch_suspend(); + /* Restore control flow magically appears here */ + restore_processor_state(); trace_suspend_resume(TPS("machine_suspend"), PM_EVENT_HIBERNATE, false); if (error) printk(KERN_ERR "PM: Error %d creating hibernation image\n", error); - /* Restore control flow magically appears here */ - restore_processor_state(); if (!in_suspend) events_check_enabled = false; -- cgit v1.2.3 From 116fcd882e3b6dc3aeb0fd29f7c93b5628337bc3 Mon Sep 17 00:00:00 2001 From: James Morse Date: Tue, 16 Aug 2016 10:46:38 +0100 Subject: PM / hibernate: Fix rtree_next_node() to avoid walking off list ends commit 924d8696751c4b9e58263bc82efdafcf875596a6 upstream. rtree_next_node() walks the linked list of leaf nodes to find the next block of pages in the struct memory_bitmap. If it walks off the end of the list of nodes, it walks the list of memory zones to find the next region of memory. If it walks off the end of the list of zones, it returns false. This leaves the struct bm_position's node and zone pointers pointing at their respective struct list_heads in struct mem_zone_bm_rtree. memory_bm_find_bit() uses struct bm_position's node and zone pointers to avoid walking lists and trees if the next bit appears in the same node/zone. It handles these values being stale. Swap rtree_next_node()s 'step then test' to 'test-next then step', this means if we reach the end of memory we return false and leave the node and zone pointers as they were. This fixes a panic on resume using AMD Seattle with 64K pages: [ 6.868732] Freezing user space processes ... (elapsed 0.000 seconds) done. [ 6.875753] Double checking all user space processes after OOM killer disable... (elapsed 0.000 seconds) [ 6.896453] PM: Using 3 thread(s) for decompression. [ 6.896453] PM: Loading and decompressing image data (5339 pages)... [ 7.318890] PM: Image loading progress: 0% [ 7.323395] Unable to handle kernel paging request at virtual address 00800040 [ 7.330611] pgd = ffff000008df0000 [ 7.334003] [00800040] *pgd=00000083fffe0003, *pud=00000083fffe0003, *pmd=00000083fffd0003, *pte=0000000000000000 [ 7.344266] Internal error: Oops: 96000005 [#1] PREEMPT SMP [ 7.349825] Modules linked in: [ 7.352871] CPU: 2 PID: 1 Comm: swapper/0 Tainted: G W I 4.8.0-rc1 #4737 [ 7.360512] Hardware name: AMD Overdrive/Supercharger/Default string, BIOS ROD1002C 04/08/2016 [ 7.369109] task: ffff8003c0220000 task.stack: ffff8003c0280000 [ 7.375020] PC is at set_bit+0x18/0x30 [ 7.378758] LR is at memory_bm_set_bit+0x24/0x30 [ 7.383362] pc : [] lr : [] pstate: 60000045 [ 7.390743] sp : ffff8003c0283b00 [ 7.473551] [ 7.475031] Process swapper/0 (pid: 1, stack limit = 0xffff8003c0280020) [ 7.481718] Stack: (0xffff8003c0283b00 to 0xffff8003c0284000) [ 7.800075] Call trace: [ 7.887097] [] set_bit+0x18/0x30 [ 7.891876] [] duplicate_memory_bitmap.constprop.38+0x54/0x70 [ 7.899172] [] snapshot_write_next+0x22c/0x47c [ 7.905166] [] load_image_lzo+0x754/0xa88 [ 7.910725] [] swsusp_read+0x144/0x230 [ 7.916025] [] load_image_and_restore+0x58/0x90 [ 7.922105] [] software_resume+0x2f0/0x338 [ 7.927752] [] do_one_initcall+0x38/0x11c [ 7.933314] [] kernel_init_freeable+0x14c/0x1ec [ 7.939395] [] kernel_init+0x10/0xfc [ 7.944520] [] ret_from_fork+0x10/0x40 [ 7.949820] Code: d2800022 8b400c21 f9800031 9ac32043 (c85f7c22) [ 7.955909] ---[ end trace 0024a5986e6ff323 ]--- [ 7.960529] Kernel panic - not syncing: Attempted to kill init! exitcode=0x0000000b Here struct mem_zone_bm_rtree's start_pfn has been returned instead of struct rtree_node's addr as the node/zone pointers are corrupt after we walked off the end of the lists during mark_unsafe_pages(). This behaviour was exposed by commit 6dbecfd345a6 ("PM / hibernate: Simplify mark_unsafe_pages()"), which caused mark_unsafe_pages() to call duplicate_memory_bitmap(), which uses memory_bm_find_bit() after walking off the end of the memory bitmap. Fixes: 3a20cb177961 (PM / Hibernate: Implement position keeping in radix tree) Signed-off-by: James Morse [ rjw: Subject ] Signed-off-by: Rafael J. Wysocki Signed-off-by: Greg Kroah-Hartman --- kernel/power/snapshot.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'kernel') diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c index 3a970604308f..f155c62f1f2c 100644 --- a/kernel/power/snapshot.c +++ b/kernel/power/snapshot.c @@ -765,9 +765,9 @@ static bool memory_bm_pfn_present(struct memory_bitmap *bm, unsigned long pfn) */ static bool rtree_next_node(struct memory_bitmap *bm) { - bm->cur.node = list_entry(bm->cur.node->list.next, - struct rtree_node, list); - if (&bm->cur.node->list != &bm->cur.zone->leaves) { + if (!list_is_last(&bm->cur.node->list, &bm->cur.zone->leaves)) { + bm->cur.node = list_entry(bm->cur.node->list.next, + struct rtree_node, list); bm->cur.node_pfn += BM_BITS_PER_BLOCK; bm->cur.node_bit = 0; touch_softlockup_watchdog(); @@ -775,9 +775,9 @@ static bool rtree_next_node(struct memory_bitmap *bm) } /* No more nodes, goto next zone */ - bm->cur.zone = list_entry(bm->cur.zone->list.next, + if (!list_is_last(&bm->cur.zone->list, &bm->zones)) { + bm->cur.zone = list_entry(bm->cur.zone->list.next, struct mem_zone_bm_rtree, list); - if (&bm->cur.zone->list != &bm->zones) { bm->cur.node = list_entry(bm->cur.zone->leaves.next, struct rtree_node, list); bm->cur.node_pfn = 0; -- cgit v1.2.3