From eae31bc183db0281c51e09a2830d70ca20e22562 Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Wed, 14 Dec 2016 15:04:10 -0800 Subject: signals: avoid unnecessary taking of sighand->siglock commit c7be96af89d4b53211862d8599b2430e8900ed92 upstream. When running certain database workload on a high-end system with many CPUs, it was found that spinlock contention in the sigprocmask syscalls became a significant portion of the overall CPU cycles as shown below. 9.30% 9.30% 905387 dataserver /proc/kcore 0x7fff8163f4d2 [k] _raw_spin_lock_irq | ---_raw_spin_lock_irq | |--99.34%-- __set_current_blocked | sigprocmask | sys_rt_sigprocmask | system_call_fastpath | | | |--50.63%-- __swapcontext | | | | | |--99.91%-- upsleepgeneric | | | |--49.36%-- __setcontext | | ktskRun Looking further into the swapcontext function in glibc, it was found that the function always call sigprocmask() without checking if there are changes in the signal mask. A check was added to the __set_current_blocked() function to avoid taking the sighand->siglock spinlock if there is no change in the signal mask. This will prevent unneeded spinlock contention when many threads are trying to call sigprocmask(). With this patch applied, the spinlock contention in sigprocmask() was gone. Link: http://lkml.kernel.org/r/1474979209-11867-1-git-send-email-Waiman.Long@hpe.com Signed-off-by: Waiman Long Acked-by: Oleg Nesterov Cc: Ingo Molnar Cc: Thomas Gleixner Cc: Stas Sergeev Cc: Scott J Norton Cc: Douglas Hatch Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Mel Gorman Signed-off-by: Greg Kroah-Hartman --- include/linux/signal.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include/linux') diff --git a/include/linux/signal.h b/include/linux/signal.h index d80259afb9e5..bcc094cb697c 100644 --- a/include/linux/signal.h +++ b/include/linux/signal.h @@ -97,6 +97,23 @@ static inline int sigisemptyset(sigset_t *set) } } +static inline int sigequalsets(const sigset_t *set1, const sigset_t *set2) +{ + switch (_NSIG_WORDS) { + case 4: + return (set1->sig[3] == set2->sig[3]) && + (set1->sig[2] == set2->sig[2]) && + (set1->sig[1] == set2->sig[1]) && + (set1->sig[0] == set2->sig[0]); + case 2: + return (set1->sig[1] == set2->sig[1]) && + (set1->sig[0] == set2->sig[0]); + case 1: + return set1->sig[0] == set2->sig[0]; + } + return 0; +} + #define sigmask(sig) (1UL << ((sig) - 1)) #ifndef __HAVE_ARCH_SIG_SETOPS -- cgit v1.2.3 From 5f1d5f781555718ceebded2d9a7659d3766d86b8 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Fri, 4 May 2018 07:59:58 +0200 Subject: efi: Avoid potential crashes, fix the 'struct efi_pci_io_protocol_32' definition for mixed mode commit 0b3225ab9407f557a8e20f23f37aa7236c10a9b1 upstream. Mixed mode allows a kernel built for x86_64 to interact with 32-bit EFI firmware, but requires us to define all struct definitions carefully when it comes to pointer sizes. 'struct efi_pci_io_protocol_32' currently uses a 'void *' for the 'romimage' field, which will be interpreted as a 64-bit field on such kernels, potentially resulting in bogus memory references and subsequent crashes. Tested-by: Hans de Goede Signed-off-by: Ard Biesheuvel Cc: Cc: Linus Torvalds Cc: Matt Fleming Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-efi@vger.kernel.org Link: http://lkml.kernel.org/r/20180504060003.19618-13-ard.biesheuvel@linaro.org Signed-off-by: Ingo Molnar Signed-off-by: Greg Kroah-Hartman --- include/linux/efi.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/efi.h b/include/linux/efi.h index 47be3ad7d3e5..7af95b58ebf3 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -364,8 +364,8 @@ typedef struct { u32 attributes; u32 get_bar_attributes; u32 set_bar_attributes; - uint64_t romsize; - void *romimage; + u64 romsize; + u32 romimage; } efi_pci_io_protocol_32; typedef struct { @@ -384,8 +384,8 @@ typedef struct { u64 attributes; u64 get_bar_attributes; u64 set_bar_attributes; - uint64_t romsize; - void *romimage; + u64 romsize; + u64 romimage; } efi_pci_io_protocol_64; typedef struct { -- cgit v1.2.3 From 92cffdc98efb1dea5d6f6911616f05dc6338d75f Mon Sep 17 00:00:00 2001 From: Vinod Koul Date: Tue, 12 Apr 2016 21:07:06 +0530 Subject: dmaengine: ensure dmaengine helpers check valid callback commit 757d12e5849be549076901b0d33c60d5f360269c upstream. dmaengine has various device callbacks and exposes helper functions to invoke these. These helpers should check if channel, device and callback is valid or not before invoking them. Reported-by: Jon Hunter Signed-off-by: Vinod Koul Signed-off-by: Fabrizio Castro Signed-off-by: Jianming Qiao Signed-off-by: Greg Kroah-Hartman --- include/linux/dmaengine.h | 20 +++++++++++++++++++- 1 file changed, 19 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index c47c68e535e8..a16d1851cfb1 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -767,6 +767,9 @@ static inline struct dma_async_tx_descriptor *dmaengine_prep_slave_single( sg_dma_address(&sg) = buf; sg_dma_len(&sg) = len; + if (!chan || !chan->device || !chan->device->device_prep_slave_sg) + return NULL; + return chan->device->device_prep_slave_sg(chan, &sg, 1, dir, flags, NULL); } @@ -775,6 +778,9 @@ static inline struct dma_async_tx_descriptor *dmaengine_prep_slave_sg( struct dma_chan *chan, struct scatterlist *sgl, unsigned int sg_len, enum dma_transfer_direction dir, unsigned long flags) { + if (!chan || !chan->device || !chan->device->device_prep_slave_sg) + return NULL; + return chan->device->device_prep_slave_sg(chan, sgl, sg_len, dir, flags, NULL); } @@ -786,6 +792,9 @@ static inline struct dma_async_tx_descriptor *dmaengine_prep_rio_sg( enum dma_transfer_direction dir, unsigned long flags, struct rio_dma_ext *rio_ext) { + if (!chan || !chan->device || !chan->device->device_prep_slave_sg) + return NULL; + return chan->device->device_prep_slave_sg(chan, sgl, sg_len, dir, flags, rio_ext); } @@ -796,6 +805,9 @@ static inline struct dma_async_tx_descriptor *dmaengine_prep_dma_cyclic( size_t period_len, enum dma_transfer_direction dir, unsigned long flags) { + if (!chan || !chan->device || !chan->device->device_prep_dma_cyclic) + return NULL; + return chan->device->device_prep_dma_cyclic(chan, buf_addr, buf_len, period_len, dir, flags); } @@ -804,6 +816,9 @@ static inline struct dma_async_tx_descriptor *dmaengine_prep_interleaved_dma( struct dma_chan *chan, struct dma_interleaved_template *xt, unsigned long flags) { + if (!chan || !chan->device || !chan->device->device_prep_interleaved_dma) + return NULL; + return chan->device->device_prep_interleaved_dma(chan, xt, flags); } @@ -811,7 +826,7 @@ static inline struct dma_async_tx_descriptor *dmaengine_prep_dma_memset( struct dma_chan *chan, dma_addr_t dest, int value, size_t len, unsigned long flags) { - if (!chan || !chan->device) + if (!chan || !chan->device || !chan->device->device_prep_dma_memset) return NULL; return chan->device->device_prep_dma_memset(chan, dest, value, @@ -824,6 +839,9 @@ static inline struct dma_async_tx_descriptor *dmaengine_prep_dma_sg( struct scatterlist *src_sg, unsigned int src_nents, unsigned long flags) { + if (!chan || !chan->device || !chan->device->device_prep_dma_sg) + return NULL; + return chan->device->device_prep_dma_sg(chan, dst_sg, dst_nents, src_sg, src_nents, flags); } -- cgit v1.2.3 From 09f7ebaa436c9bdad4a21c24fed5057604e709c1 Mon Sep 17 00:00:00 2001 From: John Stultz Date: Thu, 8 Jun 2017 16:44:21 -0700 Subject: time: Fix CLOCK_MONOTONIC_RAW sub-nanosecond accounting commit 3d88d56c5873f6eebe23e05c3da701960146b801 upstream. Due to how the MONOTONIC_RAW accumulation logic was handled, there is the potential for a 1ns discontinuity when we do accumulations. This small discontinuity has for the most part gone un-noticed, but since ARM64 enabled CLOCK_MONOTONIC_RAW in their vDSO clock_gettime implementation, we've seen failures with the inconsistency-check test in kselftest. This patch addresses the issue by using the same sub-ns accumulation handling that CLOCK_MONOTONIC uses, which avoids the issue for in-kernel users. Since the ARM64 vDSO implementation has its own clock_gettime calculation logic, this patch reduces the frequency of errors, but failures are still seen. The ARM64 vDSO will need to be updated to include the sub-nanosecond xtime_nsec values in its calculation for this issue to be completely fixed. Signed-off-by: John Stultz Tested-by: Daniel Mentz Cc: Prarit Bhargava Cc: Kevin Brodsky Cc: Richard Cochran Cc: Stephen Boyd Cc: Will Deacon Cc: "stable #4 . 8+" Cc: Miroslav Lichvar Link: http://lkml.kernel.org/r/1496965462-20003-3-git-send-email-john.stultz@linaro.org Signed-off-by: Thomas Gleixner [fabrizio: cherry-pick to 4.4. Kept cycle_t type for function logarithmic_accumulation local variable "interval". Dropped casting of "interval" variable] Signed-off-by: Fabrizio Castro Signed-off-by: Biju Das Signed-off-by: Greg Kroah-Hartman --- include/linux/timekeeper_internal.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/timekeeper_internal.h b/include/linux/timekeeper_internal.h index f0f1793cfa49..115216ec7cfe 100644 --- a/include/linux/timekeeper_internal.h +++ b/include/linux/timekeeper_internal.h @@ -56,7 +56,7 @@ struct tk_read_base { * interval. * @xtime_remainder: Shifted nano seconds left over when rounding * @cycle_interval - * @raw_interval: Raw nano seconds accumulated per NTP interval. + * @raw_interval: Shifted raw nano seconds accumulated per NTP interval. * @ntp_error: Difference between accumulated time and NTP time in ntp * shifted nano seconds. * @ntp_error_shift: Shift conversion between clock shifted nano seconds and @@ -97,7 +97,7 @@ struct timekeeper { cycle_t cycle_interval; u64 xtime_interval; s64 xtime_remainder; - u32 raw_interval; + u64 raw_interval; /* The ntp_tick_length() value currently being used. * This cached copy ensures we consistently apply the tick * length for an entire tick, as ntp_tick_length may change -- cgit v1.2.3