From 99b77fef3c6c69bb7664f1ac97a69d5b17968dae Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Wed, 31 Oct 2018 12:20:28 +0200 Subject: net/mlx5: Fix XRC SRQ umem valid bits Adapt XRC SRQ to the latest HW specification with fixed definition around umem valid bits. The previous definition relied on a bit which was taken for other purposes in legacy FW. Fixes: bd37197554eb ("net/mlx5: Update mlx5_ifc with DEVX UID bits") Signed-off-by: Yishai Hadas Reviewed-by: Artemy Kovalyov Signed-off-by: Leon Romanovsky --- include/linux/mlx5/mlx5_ifc.h | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index dbff9ff28f2c..34e17e6f8942 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -2473,14 +2473,15 @@ struct mlx5_ifc_xrc_srqc_bits { u8 wq_signature[0x1]; u8 cont_srq[0x1]; - u8 dbr_umem_valid[0x1]; + u8 reserved_at_22[0x1]; u8 rlky[0x1]; u8 basic_cyclic_rcv_wqe[0x1]; u8 log_rq_stride[0x3]; u8 xrcd[0x18]; u8 page_offset[0x6]; - u8 reserved_at_46[0x2]; + u8 reserved_at_46[0x1]; + u8 dbr_umem_valid[0x1]; u8 cqn[0x18]; u8 reserved_at_60[0x20]; @@ -6689,9 +6690,12 @@ struct mlx5_ifc_create_xrc_srq_in_bits { struct mlx5_ifc_xrc_srqc_bits xrc_srq_context_entry; - u8 reserved_at_280[0x40]; + u8 reserved_at_280[0x60]; + u8 xrc_srq_umem_valid[0x1]; - u8 reserved_at_2c1[0x5bf]; + u8 reserved_at_2e1[0x1f]; + + u8 reserved_at_300[0x580]; u8 pas[0][0x40]; }; -- cgit v1.2.3 From d19f9130b814d33c03118493c17454f7d90075d1 Mon Sep 17 00:00:00 2001 From: Elvira Khabirova Date: Sat, 10 Nov 2018 04:22:09 +0100 Subject: x86/ptrace: Fix documentation for tracehook_report_syscall_entry() tracehook_report_syscall_entry() is called not only if %TIF_SYSCALL_TRACE is set, but also if %TIF_SYSCALL_EMU is set, as appears from x86's entry code. Signed-off-by: Elvira Khabirova Cc: Borislav Petkov Cc: H. Peter Anvin Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: ldv@altlinux.org Cc: oleg@redhat.com Cc: rostedt@goodmis.org Link: http://lkml.kernel.org/r/20181110042209.26333972@akathisia Signed-off-by: Ingo Molnar --- include/linux/tracehook.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h index 40b0b4c1bf7b..df20f8bdbfa3 100644 --- a/include/linux/tracehook.h +++ b/include/linux/tracehook.h @@ -83,8 +83,8 @@ static inline int ptrace_report_syscall(struct pt_regs *regs) * tracehook_report_syscall_entry - task is about to attempt a system call * @regs: user register state of current task * - * This will be called if %TIF_SYSCALL_TRACE has been set, when the - * current task has just entered the kernel for a system call. + * This will be called if %TIF_SYSCALL_TRACE or %TIF_SYSCALL_EMU have been set, + * when the current task has just entered the kernel for a system call. * Full user register state is available here. Changing the values * in @regs can affect the system call number and arguments to be tried. * It is safe to block here, preventing the system call from beginning. -- cgit v1.2.3 From 0145b50566e7de5637e80ecba96c7f0e6fff1aad Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Wed, 31 Oct 2018 15:20:05 +0100 Subject: iio/hid-sensors: Fix IIO_CHAN_INFO_RAW returning wrong values for signed numbers Before this commit sensor_hub_input_attr_get_raw_value() failed to take the signedness of 16 and 8 bit values into account, returning e.g. 65436 instead of -100 for the z-axis reading of an accelerometer. This commit adds a new is_signed parameter to the function and makes all callers pass the appropriate value for this. While at it, this commit also fixes up some neighboring lines where statements were needlessly split over 2 lines to improve readability. Signed-off-by: Hans de Goede Acked-by: Srinivas Pandruvada Acked-by: Benjamin Tissoires Cc: Signed-off-by: Jonathan Cameron --- include/linux/hid-sensor-hub.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/hid-sensor-hub.h b/include/linux/hid-sensor-hub.h index 331dc377c275..dc12f5c4b076 100644 --- a/include/linux/hid-sensor-hub.h +++ b/include/linux/hid-sensor-hub.h @@ -177,6 +177,7 @@ int sensor_hub_input_get_attribute_info(struct hid_sensor_hub_device *hsdev, * @attr_usage_id: Attribute usage id as per spec * @report_id: Report id to look for * @flag: Synchronous or asynchronous read +* @is_signed: If true then fields < 32 bits will be sign-extended * * Issues a synchronous or asynchronous read request for an input attribute. * Returns data upto 32 bits. @@ -190,7 +191,8 @@ enum sensor_hub_read_flags { int sensor_hub_input_attr_get_raw_value(struct hid_sensor_hub_device *hsdev, u32 usage_id, u32 attr_usage_id, u32 report_id, - enum sensor_hub_read_flags flag + enum sensor_hub_read_flags flag, + bool is_signed ); /** -- cgit v1.2.3 From 786a9ab1330169f2602238822b4df5d5c4c98f6c Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Wed, 21 Nov 2018 10:35:17 +0100 Subject: gpio: davinci: restore a way to manually specify the GPIO base Commit 587f7a694f01 ("gpio: davinci: Use dev name for label and automatic base selection") broke the network support in legacy boot mode for da850-evm since we can no longer request the MDIO clock GPIO. Other boards may be broken too, which I haven't tested. The problem is in the fact that most board files still use the legacy GPIO API where lines are requested by numbers rather than descriptors. While this should be fixed eventually, in order to unbreak the board for now - provide a way to manually specify the GPIO base in platform data. Fixes: 587f7a694f01 ("gpio: davinci: Use dev name for label and automatic base selection") Cc: stable@vger.kernel.org Signed-off-by: Bartosz Golaszewski Acked-by: Linus Walleij Signed-off-by: Sekhar Nori --- include/linux/platform_data/gpio-davinci.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/platform_data/gpio-davinci.h b/include/linux/platform_data/gpio-davinci.h index f92a47e18034..a93841bfb9f7 100644 --- a/include/linux/platform_data/gpio-davinci.h +++ b/include/linux/platform_data/gpio-davinci.h @@ -17,6 +17,8 @@ #define __DAVINCI_GPIO_PLATFORM_H struct davinci_gpio_platform_data { + bool no_auto_base; + u32 base; u32 ngpio; u32 gpio_unbanked; }; -- cgit v1.2.3 From 8114865ff82e200b383e46821c25cb0625b842b5 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Sun, 18 Nov 2018 17:10:15 -0500 Subject: function_graph: Create function_graph_enter() to consolidate architecture code Currently all the architectures do basically the same thing in preparing the function graph tracer on entry to a function. This code can be pulled into a generic location and then this will allow the function graph tracer to be fixed, as well as extended. Create a new function graph helper function_graph_enter() that will call the hook function (ftrace_graph_entry) and the shadow stack operation (ftrace_push_return_trace), and remove the need of the architecture code to manage the shadow stack. This is needed to prepare for a fix of a design bug on how the curr_ret_stack is used. Cc: stable@kernel.org Fixes: 03274a3ffb449 ("tracing/fgraph: Adjust fgraph depth before calling trace return callback") Reviewed-by: Masami Hiramatsu Signed-off-by: Steven Rostedt (VMware) --- include/linux/ftrace.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index a397907e8d72..5717e8f81c59 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -779,6 +779,9 @@ extern void return_to_handler(void); extern int ftrace_push_return_trace(unsigned long ret, unsigned long func, int *depth, unsigned long frame_pointer, unsigned long *retp); +extern int +function_graph_enter(unsigned long ret, unsigned long func, + unsigned long frame_pointer, unsigned long *retp); unsigned long ftrace_graph_ret_addr(struct task_struct *task, int *idx, unsigned long ret, unsigned long *retp); -- cgit v1.2.3 From d125f3f866df88da5a85df00291f88f0baa89f7c Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Mon, 19 Nov 2018 07:40:39 -0500 Subject: function_graph: Make ftrace_push_return_trace() static As all architectures now call function_graph_enter() to do the entry work, no architecture should ever call ftrace_push_return_trace(). Make it static. This is needed to prepare for a fix of a design bug on how the curr_ret_stack is used. Cc: stable@kernel.org Fixes: 03274a3ffb449 ("tracing/fgraph: Adjust fgraph depth before calling trace return callback") Reviewed-by: Masami Hiramatsu Signed-off-by: Steven Rostedt (VMware) --- include/linux/ftrace.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 5717e8f81c59..dd16e8218db3 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -776,9 +776,6 @@ struct ftrace_ret_stack { */ extern void return_to_handler(void); -extern int -ftrace_push_return_trace(unsigned long ret, unsigned long func, int *depth, - unsigned long frame_pointer, unsigned long *retp); extern int function_graph_enter(unsigned long ret, unsigned long func, unsigned long frame_pointer, unsigned long *retp); -- cgit v1.2.3 From 39eb456dacb543de90d3bc6a8e0ac5cf51ac475e Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Mon, 19 Nov 2018 08:07:12 -0500 Subject: function_graph: Use new curr_ret_depth to manage depth instead of curr_ret_stack Currently, the depth of the ret_stack is determined by curr_ret_stack index. The issue is that there's a race between setting of the curr_ret_stack and calling of the callback attached to the return of the function. Commit 03274a3ffb44 ("tracing/fgraph: Adjust fgraph depth before calling trace return callback") moved the calling of the callback to after the setting of the curr_ret_stack, even stating that it was safe to do so, when in fact, it was the reason there was a barrier() there (yes, I should have commented that barrier()). Not only does the curr_ret_stack keep track of the current call graph depth, it also keeps the ret_stack content from being overwritten by new data. The function profiler, uses the "subtime" variable of ret_stack structure and by moving the curr_ret_stack, it allows for interrupts to use the same structure it was using, corrupting the data, and breaking the profiler. To fix this, there needs to be two variables to handle the call stack depth and the pointer to where the ret_stack is being used, as they need to change at two different locations. Cc: stable@kernel.org Fixes: 03274a3ffb449 ("tracing/fgraph: Adjust fgraph depth before calling trace return callback") Reviewed-by: Masami Hiramatsu Signed-off-by: Steven Rostedt (VMware) --- include/linux/sched.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index a51c13c2b1a0..d6183a55e8eb 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1116,6 +1116,7 @@ struct task_struct { #ifdef CONFIG_FUNCTION_GRAPH_TRACER /* Index of current stored address in ret_stack: */ int curr_ret_stack; + int curr_ret_depth; /* Stack of return addresses for return function tracing: */ struct ftrace_ret_stack *ret_stack; -- cgit v1.2.3 From 321a874a7ef85655e93b3206d0f36b4a6097f948 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sun, 25 Nov 2018 19:33:38 +0100 Subject: sched/smt: Expose sched_smt_present static key Make the scheduler's 'sched_smt_present' static key globaly available, so it can be used in the x86 speculation control code. Provide a query function and a stub for the CONFIG_SMP=n case. Signed-off-by: Thomas Gleixner Reviewed-by: Ingo Molnar Cc: Peter Zijlstra Cc: Andy Lutomirski Cc: Linus Torvalds Cc: Jiri Kosina Cc: Tom Lendacky Cc: Josh Poimboeuf Cc: Andrea Arcangeli Cc: David Woodhouse Cc: Tim Chen Cc: Andi Kleen Cc: Dave Hansen Cc: Casey Schaufler Cc: Asit Mallick Cc: Arjan van de Ven Cc: Jon Masters Cc: Waiman Long Cc: Greg KH Cc: Dave Stewart Cc: Kees Cook Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/20181125185004.430168326@linutronix.de --- include/linux/sched/smt.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) create mode 100644 include/linux/sched/smt.h (limited to 'include/linux') diff --git a/include/linux/sched/smt.h b/include/linux/sched/smt.h new file mode 100644 index 000000000000..c9e0be514110 --- /dev/null +++ b/include/linux/sched/smt.h @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_SCHED_SMT_H +#define _LINUX_SCHED_SMT_H + +#include + +#ifdef CONFIG_SCHED_SMT +extern struct static_key_false sched_smt_present; + +static __always_inline bool sched_smt_active(void) +{ + return static_branch_likely(&sched_smt_present); +} +#else +static inline bool sched_smt_active(void) { return false; } +#endif + +#endif -- cgit v1.2.3 From a74cfffb03b73d41e08f84c2e5c87dec0ce3db9f Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sun, 25 Nov 2018 19:33:39 +0100 Subject: x86/speculation: Rework SMT state change arch_smt_update() is only called when the sysfs SMT control knob is changed. This means that when SMT is enabled in the sysfs control knob the system is considered to have SMT active even if all siblings are offline. To allow finegrained control of the speculation mitigations, the actual SMT state is more interesting than the fact that siblings could be enabled. Rework the code, so arch_smt_update() is invoked from each individual CPU hotplug function, and simplify the update function while at it. Signed-off-by: Thomas Gleixner Reviewed-by: Ingo Molnar Cc: Peter Zijlstra Cc: Andy Lutomirski Cc: Linus Torvalds Cc: Jiri Kosina Cc: Tom Lendacky Cc: Josh Poimboeuf Cc: Andrea Arcangeli Cc: David Woodhouse Cc: Tim Chen Cc: Andi Kleen Cc: Dave Hansen Cc: Casey Schaufler Cc: Asit Mallick Cc: Arjan van de Ven Cc: Jon Masters Cc: Waiman Long Cc: Greg KH Cc: Dave Stewart Cc: Kees Cook Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/20181125185004.521974984@linutronix.de --- include/linux/sched/smt.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched/smt.h b/include/linux/sched/smt.h index c9e0be514110..59d3736c454c 100644 --- a/include/linux/sched/smt.h +++ b/include/linux/sched/smt.h @@ -15,4 +15,6 @@ static __always_inline bool sched_smt_active(void) static inline bool sched_smt_active(void) { return false; } #endif +void arch_smt_update(void); + #endif -- cgit v1.2.3 From 46f7ecb1e7359f183f5bbd1e08b90e10e52164f9 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sun, 25 Nov 2018 19:33:50 +0100 Subject: ptrace: Remove unused ptrace_may_access_sched() and MODE_IBRS The IBPB control code in x86 removed the usage. Remove the functionality which was introduced for this. Signed-off-by: Thomas Gleixner Reviewed-by: Ingo Molnar Cc: Peter Zijlstra Cc: Andy Lutomirski Cc: Linus Torvalds Cc: Jiri Kosina Cc: Tom Lendacky Cc: Josh Poimboeuf Cc: Andrea Arcangeli Cc: David Woodhouse Cc: Tim Chen Cc: Andi Kleen Cc: Dave Hansen Cc: Casey Schaufler Cc: Asit Mallick Cc: Arjan van de Ven Cc: Jon Masters Cc: Waiman Long Cc: Greg KH Cc: Dave Stewart Cc: Kees Cook Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/20181125185005.559149393@linutronix.de --- include/linux/ptrace.h | 17 ----------------- 1 file changed, 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index 6c2ffed907f5..de20ede2c5c8 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -64,15 +64,12 @@ extern void exit_ptrace(struct task_struct *tracer, struct list_head *dead); #define PTRACE_MODE_NOAUDIT 0x04 #define PTRACE_MODE_FSCREDS 0x08 #define PTRACE_MODE_REALCREDS 0x10 -#define PTRACE_MODE_SCHED 0x20 -#define PTRACE_MODE_IBPB 0x40 /* shorthands for READ/ATTACH and FSCREDS/REALCREDS combinations */ #define PTRACE_MODE_READ_FSCREDS (PTRACE_MODE_READ | PTRACE_MODE_FSCREDS) #define PTRACE_MODE_READ_REALCREDS (PTRACE_MODE_READ | PTRACE_MODE_REALCREDS) #define PTRACE_MODE_ATTACH_FSCREDS (PTRACE_MODE_ATTACH | PTRACE_MODE_FSCREDS) #define PTRACE_MODE_ATTACH_REALCREDS (PTRACE_MODE_ATTACH | PTRACE_MODE_REALCREDS) -#define PTRACE_MODE_SPEC_IBPB (PTRACE_MODE_ATTACH_REALCREDS | PTRACE_MODE_IBPB) /** * ptrace_may_access - check whether the caller is permitted to access @@ -90,20 +87,6 @@ extern void exit_ptrace(struct task_struct *tracer, struct list_head *dead); */ extern bool ptrace_may_access(struct task_struct *task, unsigned int mode); -/** - * ptrace_may_access - check whether the caller is permitted to access - * a target task. - * @task: target task - * @mode: selects type of access and caller credentials - * - * Returns true on success, false on denial. - * - * Similar to ptrace_may_access(). Only to be called from context switch - * code. Does not call into audit and the regular LSM hooks due to locking - * constraints. - */ -extern bool ptrace_may_access_sched(struct task_struct *task, unsigned int mode); - static inline int ptrace_reparented(struct task_struct *child) { return !same_thread_group(child->real_parent, child->parent); -- cgit v1.2.3 From 9137bb27e60e554dab694eafa4cca241fa3a694f Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sun, 25 Nov 2018 19:33:53 +0100 Subject: x86/speculation: Add prctl() control for indirect branch speculation Add the PR_SPEC_INDIRECT_BRANCH option for the PR_GET_SPECULATION_CTRL and PR_SET_SPECULATION_CTRL prctls to allow fine grained per task control of indirect branch speculation via STIBP and IBPB. Invocations: Check indirect branch speculation status with - prctl(PR_GET_SPECULATION_CTRL, PR_SPEC_INDIRECT_BRANCH, 0, 0, 0); Enable indirect branch speculation with - prctl(PR_SET_SPECULATION_CTRL, PR_SPEC_INDIRECT_BRANCH, PR_SPEC_ENABLE, 0, 0); Disable indirect branch speculation with - prctl(PR_SET_SPECULATION_CTRL, PR_SPEC_INDIRECT_BRANCH, PR_SPEC_DISABLE, 0, 0); Force disable indirect branch speculation with - prctl(PR_SET_SPECULATION_CTRL, PR_SPEC_INDIRECT_BRANCH, PR_SPEC_FORCE_DISABLE, 0, 0); See Documentation/userspace-api/spec_ctrl.rst. Signed-off-by: Tim Chen Signed-off-by: Thomas Gleixner Reviewed-by: Ingo Molnar Cc: Peter Zijlstra Cc: Andy Lutomirski Cc: Linus Torvalds Cc: Jiri Kosina Cc: Tom Lendacky Cc: Josh Poimboeuf Cc: Andrea Arcangeli Cc: David Woodhouse Cc: Andi Kleen Cc: Dave Hansen Cc: Casey Schaufler Cc: Asit Mallick Cc: Arjan van de Ven Cc: Jon Masters Cc: Waiman Long Cc: Greg KH Cc: Dave Stewart Cc: Kees Cook Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/20181125185005.866780996@linutronix.de --- include/linux/sched.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index a51c13c2b1a0..d607db5fcc6a 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1453,6 +1453,8 @@ static inline bool is_percpu_thread(void) #define PFA_SPREAD_SLAB 2 /* Spread some slab caches over cpuset */ #define PFA_SPEC_SSB_DISABLE 3 /* Speculative Store Bypass disabled */ #define PFA_SPEC_SSB_FORCE_DISABLE 4 /* Speculative Store Bypass force disabled*/ +#define PFA_SPEC_IB_DISABLE 5 /* Indirect branch speculation restricted */ +#define PFA_SPEC_IB_FORCE_DISABLE 6 /* Indirect branch speculation permanently restricted */ #define TASK_PFA_TEST(name, func) \ static inline bool task_##func(struct task_struct *p) \ @@ -1484,6 +1486,13 @@ TASK_PFA_CLEAR(SPEC_SSB_DISABLE, spec_ssb_disable) TASK_PFA_TEST(SPEC_SSB_FORCE_DISABLE, spec_ssb_force_disable) TASK_PFA_SET(SPEC_SSB_FORCE_DISABLE, spec_ssb_force_disable) +TASK_PFA_TEST(SPEC_IB_DISABLE, spec_ib_disable) +TASK_PFA_SET(SPEC_IB_DISABLE, spec_ib_disable) +TASK_PFA_CLEAR(SPEC_IB_DISABLE, spec_ib_disable) + +TASK_PFA_TEST(SPEC_IB_FORCE_DISABLE, spec_ib_force_disable) +TASK_PFA_SET(SPEC_IB_FORCE_DISABLE, spec_ib_force_disable) + static inline void current_restore_flags(unsigned long orig_flags, unsigned long flags) { -- cgit v1.2.3 From 3f2b7b9035107d6096ea438ea3d97dcf0481b6d2 Mon Sep 17 00:00:00 2001 From: "kiran.modukuri" Date: Mon, 26 Nov 2018 15:41:48 +0000 Subject: fscache: Fix race in fscache_op_complete() due to split atomic_sub & read The code in fscache_retrieval_complete is using atomic_sub followed by an atomic_read: atomic_sub(n_pages, &op->n_pages); if (atomic_read(&op->n_pages) <= 0) fscache_op_complete(&op->op, true); This causes two threads doing a decrement of n_pages to race with each other seeing the op->refcount 0 at same time - and they end up calling fscache_op_complete() in both the threads leading to an assertion failure. Fix this by using atomic_sub_return_relaxed() instead of two calls. Note that I'm using 'relaxed' rather than, say, 'release' as there aren't multiple variables that appear to need ordering across the release. The oops looks something like: FS-Cache: Assertion failed FS-Cache: 0 > 0 is false ... kernel BUG at /usr/src/linux-4.4.0/fs/fscache/operation.c:449! ... Workqueue: fscache_operation fscache_op_work_func [fscache] ... RIP: 0010:[] fscache_op_complete+0x10d/0x180 [fscache] ... Call Trace: [] cachefiles_read_copier+0x3a9/0x410 [cachefiles] [] fscache_op_work_func+0x22/0x50 [fscache] [] process_one_work+0x150/0x3f0 [] worker_thread+0x11a/0x470 [] ? __schedule+0x359/0x980 [] ? rescuer_thread+0x310/0x310 [] kthread+0xd6/0xf0 [] ? kthread_park+0x60/0x60 [] ret_from_fork+0x3f/0x70 [] ? kthread_park+0x60/0x60 This seen this in 4.4.x kernels and the same bug affects fscache in latest upstreams kernels. Fixes: 1bb4b7f98f36 ("FS-Cache: The retrieval remaining-pages counter needs to be atomic_t") Signed-off-by: Kiran Kumar Modukuri Signed-off-by: David Howells --- include/linux/fscache-cache.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fscache-cache.h b/include/linux/fscache-cache.h index 34cf0fdd7dc7..610815e3f1aa 100644 --- a/include/linux/fscache-cache.h +++ b/include/linux/fscache-cache.h @@ -196,8 +196,7 @@ static inline void fscache_enqueue_retrieval(struct fscache_retrieval *op) static inline void fscache_retrieval_complete(struct fscache_retrieval *op, int n_pages) { - atomic_sub(n_pages, &op->n_pages); - if (atomic_read(&op->n_pages) <= 0) + if (atomic_sub_return_relaxed(n_pages, &op->n_pages) <= 0) fscache_op_complete(&op->op, false); } -- cgit v1.2.3 From 90230968f102acbe103fbf7c03d41addfef5f153 Mon Sep 17 00:00:00 2001 From: Baruch Siach Date: Thu, 29 Nov 2018 12:00:05 +0200 Subject: net: phy: sfp: correct location of SFP standards SFP standards are now available from the SNIA (Storage Networking Industry Association) website. Cc: Andrew Lunn Cc: Florian Fainelli Signed-off-by: Baruch Siach Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/sfp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sfp.h b/include/linux/sfp.h index d37518e89db2..d9d9de3fcf8e 100644 --- a/include/linux/sfp.h +++ b/include/linux/sfp.h @@ -224,7 +224,7 @@ struct sfp_eeprom_ext { * * See the SFF-8472 specification and related documents for the definition * of these structure members. This can be obtained from - * ftp://ftp.seagate.com/sff + * https://www.snia.org/technology-communities/sff/specifications */ struct sfp_eeprom_id { struct sfp_eeprom_base base; -- cgit v1.2.3 From 89d328f637b9904b6d4c9af73c8a608b8dd4d6f8 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Thu, 1 Nov 2018 16:17:22 -0700 Subject: pstore/ram: Correctly calculate usable PRZ bytes The actual number of bytes stored in a PRZ is smaller than the bytes requested by platform data, since there is a header on each PRZ. Additionally, if ECC is enabled, there are trailing bytes used as well. Normally this mismatch doesn't matter since PRZs are circular buffers and the leading "overflow" bytes are just thrown away. However, in the case of a compressed record, this rather badly corrupts the results. This corruption was visible with "ramoops.mem_size=204800 ramoops.ecc=1". Any stored crashes would not be uncompressable (producing a pstorefs "dmesg-*.enc.z" file), and triggering errors at boot: [ 2.790759] pstore: crypto_comp_decompress failed, ret = -22! Backporting this depends on commit 70ad35db3321 ("pstore: Convert console write to use ->write_buf") Reported-by: Joel Fernandes Fixes: b0aad7a99c1d ("pstore: Add compression support to pstore") Signed-off-by: Kees Cook Reviewed-by: Joel Fernandes (Google) --- include/linux/pstore.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pstore.h b/include/linux/pstore.h index a15bc4d48752..30fcec375a3a 100644 --- a/include/linux/pstore.h +++ b/include/linux/pstore.h @@ -90,7 +90,10 @@ struct pstore_record { * * @buf_lock: spinlock to serialize access to @buf * @buf: preallocated crash dump buffer - * @bufsize: size of @buf available for crash dump writes + * @bufsize: size of @buf available for crash dump bytes (must match + * smallest number of bytes available for writing to a + * backend entry, since compressed bytes don't take kindly + * to being truncated) * * @read_mutex: serializes @open, @read, @close, and @erase callbacks * @flags: bitfield of frontends the backend can accept writes for -- cgit v1.2.3 From 0c7a52e4d4b5c4d35b31f3c3ad32af814f1bf491 Mon Sep 17 00:00:00 2001 From: Zenghui Yu Date: Wed, 28 Nov 2018 03:35:23 +0000 Subject: tracepoint: Use __idx instead of idx in DO_TRACE macro to make it unique After enabling KVM event tracing, almost all of trace_kvm_exit()'s printk shows "kvm_exit: IRQ: ..." even if the actual exception_type is NOT IRQ. More specifically, trace_kvm_exit() is defined in virt/kvm/arm/trace.h by TRACE_EVENT. This slight problem may have existed after commit e6753f23d961 ("tracepoint: Make rcuidle tracepoint callers use SRCU"). There are two variables in trace_kvm_exit() and __DO_TRACE() which have the same name, *idx*. Thus the actual value of *idx* will be overwritten when tracing. Fix it by adding a simple prefix. Cc: Joel Fernandes Cc: Wang Haibin Cc: linux-trace-devel@vger.kernel.org Cc: stable@vger.kernel.org Fixes: e6753f23d961 ("tracepoint: Make rcuidle tracepoint callers use SRCU") Reviewed-by: Joel Fernandes (Google) Signed-off-by: Zenghui Yu Signed-off-by: Steven Rostedt (VMware) --- include/linux/tracepoint.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index 538ba1a58f5b..e9de8ad0bad7 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -166,7 +166,7 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) struct tracepoint_func *it_func_ptr; \ void *it_func; \ void *__data; \ - int __maybe_unused idx = 0; \ + int __maybe_unused __idx = 0; \ \ if (!(cond)) \ return; \ @@ -182,7 +182,7 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) * doesn't work from the idle path. \ */ \ if (rcuidle) { \ - idx = srcu_read_lock_notrace(&tracepoint_srcu); \ + __idx = srcu_read_lock_notrace(&tracepoint_srcu);\ rcu_irq_enter_irqson(); \ } \ \ @@ -198,7 +198,7 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) \ if (rcuidle) { \ rcu_irq_exit_irqson(); \ - srcu_read_unlock_notrace(&tracepoint_srcu, idx);\ + srcu_read_unlock_notrace(&tracepoint_srcu, __idx);\ } \ \ preempt_enable_notrace(); \ -- cgit v1.2.3 From e0c274472d5d27f277af722e017525e0b33784cd Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Fri, 30 Nov 2018 14:09:58 -0800 Subject: psi: make disabling/enabling easier for vendor kernels Mel Gorman reports a hackbench regression with psi that would prohibit shipping the suse kernel with it default-enabled, but he'd still like users to be able to opt in at little to no cost to others. With the current combination of CONFIG_PSI and the psi_disabled bool set from the commandline, this is a challenge. Do the following things to make it easier: 1. Add a config option CONFIG_PSI_DEFAULT_DISABLED that allows distros to enable CONFIG_PSI in their kernel but leave the feature disabled unless a user requests it at boot-time. To avoid double negatives, rename psi_disabled= to psi=. 2. Make psi_disabled a static branch to eliminate any branch costs when the feature is disabled. In terms of numbers before and after this patch, Mel says: : The following is a comparision using CONFIG_PSI=n as a baseline against : your patch and a vanilla kernel : : 4.20.0-rc4 4.20.0-rc4 4.20.0-rc4 : kconfigdisable-v1r1 vanilla psidisable-v1r1 : Amean 1 1.3100 ( 0.00%) 1.3923 ( -6.28%) 1.3427 ( -2.49%) : Amean 3 3.8860 ( 0.00%) 4.1230 * -6.10%* 3.8860 ( -0.00%) : Amean 5 6.8847 ( 0.00%) 8.0390 * -16.77%* 6.7727 ( 1.63%) : Amean 7 9.9310 ( 0.00%) 10.8367 * -9.12%* 9.9910 ( -0.60%) : Amean 12 16.6577 ( 0.00%) 18.2363 * -9.48%* 17.1083 ( -2.71%) : Amean 18 26.5133 ( 0.00%) 27.8833 * -5.17%* 25.7663 ( 2.82%) : Amean 24 34.3003 ( 0.00%) 34.6830 ( -1.12%) 32.0450 ( 6.58%) : Amean 30 40.0063 ( 0.00%) 40.5800 ( -1.43%) 41.5087 ( -3.76%) : Amean 32 40.1407 ( 0.00%) 41.2273 ( -2.71%) 39.9417 ( 0.50%) : : It's showing that the vanilla kernel takes a hit (as the bisection : indicated it would) and that disabling PSI by default is reasonably : close in terms of performance for this particular workload on this : particular machine so; Link: http://lkml.kernel.org/r/20181127165329.GA29728@cmpxchg.org Signed-off-by: Johannes Weiner Tested-by: Mel Gorman Reported-by: Mel Gorman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/psi.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/psi.h b/include/linux/psi.h index 8e0725aac0aa..7006008d5b72 100644 --- a/include/linux/psi.h +++ b/include/linux/psi.h @@ -1,6 +1,7 @@ #ifndef _LINUX_PSI_H #define _LINUX_PSI_H +#include #include #include @@ -9,7 +10,7 @@ struct css_set; #ifdef CONFIG_PSI -extern bool psi_disabled; +extern struct static_key_false psi_disabled; void psi_init(void); -- cgit v1.2.3 From b7df9ada9a7700dbcca1ba53d217c01e3d48179c Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Sat, 1 Dec 2018 01:18:53 +0100 Subject: bpf: fix pointer offsets in context for 32 bit Currently, pointer offsets in three BPF context structures are broken in two scenarios: i) 32 bit compiled applications running on 64 bit kernels, and ii) LLVM compiled BPF programs running on 32 bit kernels. The latter is due to BPF target machine being strictly 64 bit. So in each of the cases the offsets will mismatch in verifier when checking / rewriting context access. Fix this by providing a helper macro __bpf_md_ptr() that will enforce padding up to 64 bit and proper alignment, and for context access a macro bpf_ctx_range_ptr() which will cover full 64 bit member range on 32 bit archs. For flow_keys, we additionally need to force the size check to sizeof(__u64) as with other pointer types. Fixes: d58e468b1112 ("flow_dissector: implements flow dissector BPF hook") Fixes: 4f738adba30a ("bpf: create tcp_bpf_ulp allowing BPF to monitor socket TX/RX data") Fixes: 2dbb9b9e6df6 ("bpf: Introduce BPF_PROG_TYPE_SK_REUSEPORT") Reported-by: David S. Miller Signed-off-by: Daniel Borkmann Acked-by: David S. Miller Tested-by: David S. Miller Signed-off-by: Alexei Starovoitov --- include/linux/filter.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index 448dcc448f1f..795ff0b869bb 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -449,6 +449,13 @@ struct sock_reuseport; offsetof(TYPE, MEMBER) ... offsetofend(TYPE, MEMBER) - 1 #define bpf_ctx_range_till(TYPE, MEMBER1, MEMBER2) \ offsetof(TYPE, MEMBER1) ... offsetofend(TYPE, MEMBER2) - 1 +#if BITS_PER_LONG == 64 +# define bpf_ctx_range_ptr(TYPE, MEMBER) \ + offsetof(TYPE, MEMBER) ... offsetofend(TYPE, MEMBER) - 1 +#else +# define bpf_ctx_range_ptr(TYPE, MEMBER) \ + offsetof(TYPE, MEMBER) ... offsetof(TYPE, MEMBER) + 8 - 1 +#endif /* BITS_PER_LONG == 64 */ #define bpf_target_off(TYPE, MEMBER, SIZE, PTR_SIZE) \ ({ \ -- cgit v1.2.3 From 71700bb96047f68a0aae3932466fc7c9ad5ce6c0 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 30 Nov 2018 16:11:15 -0500 Subject: SUNRPC: Fix a memory leak in call_encode() If we retransmit an RPC request, we currently end up clobbering the value of req->rq_rcv_buf.bvec that was allocated by the initial call to xprt_request_prepare(req). Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xdr.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h index 43106ffa6788..2ec128060239 100644 --- a/include/linux/sunrpc/xdr.h +++ b/include/linux/sunrpc/xdr.h @@ -72,7 +72,6 @@ xdr_buf_init(struct xdr_buf *buf, void *start, size_t len) buf->head[0].iov_base = start; buf->head[0].iov_len = len; buf->tail[0].iov_len = 0; - buf->bvec = NULL; buf->pages = NULL; buf->page_len = 0; buf->flags = 0; -- cgit v1.2.3 From 37c2578c0c40e286bc0d30bdc05290b2058cf66e Mon Sep 17 00:00:00 2001 From: Dexuan Cui Date: Mon, 3 Dec 2018 00:54:35 +0000 Subject: Drivers: hv: vmbus: Offload the handling of channels to two workqueues vmbus_process_offer() mustn't call channel->sc_creation_callback() directly for sub-channels, because sc_creation_callback() -> vmbus_open() may never get the host's response to the OPEN_CHANNEL message (the host may rescind a channel at any time, e.g. in the case of hot removing a NIC), and vmbus_onoffer_rescind() may not wake up the vmbus_open() as it's blocked due to a non-zero vmbus_connection.offer_in_progress, and finally we have a deadlock. The above is also true for primary channels, if the related device drivers use sync probing mode by default. And, usually the handling of primary channels and sub-channels can depend on each other, so we should offload them to different workqueues to avoid possible deadlock, e.g. in sync-probing mode, NIC1's netvsc_subchan_work() can race with NIC2's netvsc_probe() -> rtnl_lock(), and causes deadlock: the former gets the rtnl_lock and waits for all the sub-channels to appear, but the latter can't get the rtnl_lock and this blocks the handling of sub-channels. The patch can fix the multiple-NIC deadlock described above for v3.x kernels (e.g. RHEL 7.x) which don't support async-probing of devices, and v4.4, v4.9, v4.14 and v4.18 which support async-probing but don't enable async-probing for Hyper-V drivers (yet). The patch can also fix the hang issue in sub-channel's handling described above for all versions of kernels, including v4.19 and v4.20-rc4. So actually the patch should be applied to all the existing kernels, not only the kernels that have 8195b1396ec8. Fixes: 8195b1396ec8 ("hv_netvsc: fix deadlock on hotplug") Cc: stable@vger.kernel.org Cc: Stephen Hemminger Cc: K. Y. Srinivasan Cc: Haiyang Zhang Signed-off-by: Dexuan Cui Signed-off-by: K. Y. Srinivasan Signed-off-by: Greg Kroah-Hartman --- include/linux/hyperv.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index b3e24368930a..14131b6fae68 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -905,6 +905,13 @@ struct vmbus_channel { bool probe_done; + /* + * We must offload the handling of the primary/sub channels + * from the single-threaded vmbus_connection.work_queue to + * two different workqueue, otherwise we can block + * vmbus_connection.work_queue and hang: see vmbus_process_offer(). + */ + struct work_struct add_channel_work; }; static inline bool is_hvsock_channel(const struct vmbus_channel *c) -- cgit v1.2.3 From 27359fd6e5f3c5db8fe544b63238b6170e8806d8 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Fri, 30 Nov 2018 11:05:06 -0500 Subject: dax: Fix unlock mismatch with updated API Internal to dax_unlock_mapping_entry(), dax_unlock_entry() is used to store a replacement entry in the Xarray at the given xas-index with the DAX_LOCKED bit clear. When called, dax_unlock_entry() expects the unlocked value of the entry relative to the current Xarray state to be specified. In most contexts dax_unlock_entry() is operating in the same scope as the matched dax_lock_entry(). However, in the dax_unlock_mapping_entry() case the implementation needs to recall the original entry. In the case where the original entry is a 'pmd' entry it is possible that the pfn performed to do the lookup is misaligned to the value retrieved in the Xarray. Change the api to return the unlock cookie from dax_lock_page() and pass it to dax_unlock_page(). This fixes a bug where dax_unlock_page() was assuming that the page was PMD-aligned if the entry was a PMD entry with signatures like: WARNING: CPU: 38 PID: 1396 at fs/dax.c:340 dax_insert_entry+0x2b2/0x2d0 RIP: 0010:dax_insert_entry+0x2b2/0x2d0 [..] Call Trace: dax_iomap_pte_fault.isra.41+0x791/0xde0 ext4_dax_huge_fault+0x16f/0x1f0 ? up_read+0x1c/0xa0 __do_fault+0x1f/0x160 __handle_mm_fault+0x1033/0x1490 handle_mm_fault+0x18b/0x3d0 Link: https://lkml.kernel.org/r/20181130154902.GL10377@bombadil.infradead.org Fixes: 9f32d221301c ("dax: Convert dax_lock_mapping_entry to XArray") Reported-by: Dan Williams Signed-off-by: Matthew Wilcox Tested-by: Dan Williams Reviewed-by: Jan Kara Signed-off-by: Dan Williams --- include/linux/dax.h | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dax.h b/include/linux/dax.h index 450b28db9533..0dd316a74a29 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -7,6 +7,8 @@ #include #include +typedef unsigned long dax_entry_t; + struct iomap_ops; struct dax_device; struct dax_operations { @@ -88,8 +90,8 @@ int dax_writeback_mapping_range(struct address_space *mapping, struct block_device *bdev, struct writeback_control *wbc); struct page *dax_layout_busy_page(struct address_space *mapping); -bool dax_lock_mapping_entry(struct page *page); -void dax_unlock_mapping_entry(struct page *page); +dax_entry_t dax_lock_page(struct page *page); +void dax_unlock_page(struct page *page, dax_entry_t cookie); #else static inline bool bdev_dax_supported(struct block_device *bdev, int blocksize) @@ -122,14 +124,14 @@ static inline int dax_writeback_mapping_range(struct address_space *mapping, return -EOPNOTSUPP; } -static inline bool dax_lock_mapping_entry(struct page *page) +static inline dax_entry_t dax_lock_page(struct page *page) { if (IS_DAX(page->mapping->host)) - return true; - return false; + return ~0UL; + return 0; } -static inline void dax_unlock_mapping_entry(struct page *page) +static inline void dax_unlock_page(struct page *page, dax_entry_t cookie) { } #endif -- cgit v1.2.3 From f51ccf46217c28758b1f3b5bc0ccfc00eca658b2 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Tue, 4 Dec 2018 17:00:36 +0100 Subject: USB: serial: console: fix reported terminal settings The USB-serial console implementation has never reported the actual terminal settings used. Despite storing the corresponding cflags in its struct console, these were never honoured on later tty open() where the tty termios would be left initialised to the driver defaults. Unlike the serial console implementation, the USB-serial code calls subdriver open() already at console setup. While calling set_termios() and write() before open() looks like it could work for some USB-serial drivers, others definitely do not expect this, so modelling this after serial core is going to be intrusive, if at all possible. Instead, use a (renamed) tty helper to save the termios data used at console setup so that the tty termios reflects the actual terminal settings after a subsequent tty open(). Note that the calls to tty_init_termios() (tty_driver_install()) and tty_save_termios() are serialised using the disconnect mutex. This specifically fixes a regression that was triggered by a recent change adding software flow control to the pl2303 driver: a getty trying to disable flow control while leaving the baud rate unchanged would now also set the baud rate to the driver default (prior to the flow-control change this had been a noop). Fixes: 7041d9c3f01b ("USB: serial: pl2303: add support for tx xon/xoff flow control") Cc: stable # 4.18 Cc: Florian Zumbiehl Reported-by: Jarkko Nikula Tested-by: Jarkko Nikula Acked-by: Greg Kroah-Hartman Signed-off-by: Johan Hovold --- include/linux/tty.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index 414db2bce715..392138fe59b6 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -556,6 +556,7 @@ extern struct tty_struct *tty_init_dev(struct tty_driver *driver, int idx); extern void tty_release_struct(struct tty_struct *tty, int idx); extern int tty_release(struct inode *inode, struct file *filp); extern void tty_init_termios(struct tty_struct *tty); +extern void tty_save_termios(struct tty_struct *tty); extern int tty_standard_install(struct tty_driver *driver, struct tty_struct *tty); -- cgit v1.2.3 From 704620afc70cf47abb9d6a1a57f3825d2bca49cf Mon Sep 17 00:00:00 2001 From: Mathias Payer Date: Wed, 5 Dec 2018 21:19:59 +0100 Subject: USB: check usb_get_extra_descriptor for proper size When reading an extra descriptor, we need to properly check the minimum and maximum size allowed, to prevent from invalid data being sent by a device. Reported-by: Hui Peng Reported-by: Mathias Payer Co-developed-by: Linus Torvalds Signed-off-by: Hui Peng Signed-off-by: Mathias Payer Signed-off-by: Linus Torvalds Cc: stable Signed-off-by: Greg Kroah-Hartman --- include/linux/usb.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb.h b/include/linux/usb.h index 4cdd515a4385..5e49e82c4368 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -407,11 +407,11 @@ struct usb_host_bos { }; int __usb_get_extra_descriptor(char *buffer, unsigned size, - unsigned char type, void **ptr); + unsigned char type, void **ptr, size_t min); #define usb_get_extra_descriptor(ifpoint, type, ptr) \ __usb_get_extra_descriptor((ifpoint)->extra, \ (ifpoint)->extralen, \ - type, (void **)ptr) + type, (void **)ptr, sizeof(**(ptr))) /* ----------------------------------------------------------------------- */ -- cgit v1.2.3 From 2f0799a0ffc033bf3cc82d5032acc3ec633464c2 Mon Sep 17 00:00:00 2001 From: David Rientjes Date: Wed, 5 Dec 2018 15:45:54 -0800 Subject: mm, thp: restore node-local hugepage allocations This is a full revert of ac5b2c18911f ("mm: thp: relax __GFP_THISNODE for MADV_HUGEPAGE mappings") and a partial revert of 89c83fb539f9 ("mm, thp: consolidate THP gfp handling into alloc_hugepage_direct_gfpmask"). By not setting __GFP_THISNODE, applications can allocate remote hugepages when the local node is fragmented or low on memory when either the thp defrag setting is "always" or the vma has been madvised with MADV_HUGEPAGE. Remote access to hugepages often has much higher latency than local pages of the native page size. On Haswell, ac5b2c18911f was shown to have a 13.9% access regression after this commit for binaries that remap their text segment to be backed by transparent hugepages. The intent of ac5b2c18911f is to address an issue where a local node is low on memory or fragmented such that a hugepage cannot be allocated. In every scenario where this was described as a fix, there is abundant and unfragmented remote memory available to allocate from, even with a greater access latency. If remote memory is also low or fragmented, not setting __GFP_THISNODE was also measured on Haswell to have a 40% regression in allocation latency. Restore __GFP_THISNODE for thp allocations. Fixes: ac5b2c18911f ("mm: thp: relax __GFP_THISNODE for MADV_HUGEPAGE mappings") Fixes: 89c83fb539f9 ("mm, thp: consolidate THP gfp handling into alloc_hugepage_direct_gfpmask") Cc: Andrea Arcangeli Cc: Mel Gorman Cc: Vlastimil Babka Cc: Michal Hocko Cc: Andrew Morton Signed-off-by: David Rientjes Signed-off-by: Linus Torvalds --- include/linux/mempolicy.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h index bac395f1d00a..5228c62af416 100644 --- a/include/linux/mempolicy.h +++ b/include/linux/mempolicy.h @@ -139,8 +139,6 @@ struct mempolicy *mpol_shared_policy_lookup(struct shared_policy *sp, struct mempolicy *get_task_policy(struct task_struct *p); struct mempolicy *__get_vma_policy(struct vm_area_struct *vma, unsigned long addr); -struct mempolicy *get_vma_policy(struct vm_area_struct *vma, - unsigned long addr); bool vma_policy_mof(struct vm_area_struct *vma); extern void numa_default_policy(void); -- cgit v1.2.3 From 356ff8a9a78fb35d6482584d260c3754dcbdf669 Mon Sep 17 00:00:00 2001 From: David Rientjes Date: Fri, 7 Dec 2018 14:50:16 -0800 Subject: Revert "mm, thp: consolidate THP gfp handling into alloc_hugepage_direct_gfpmask" This reverts commit 89c83fb539f95491be80cdd5158e6f0ce329e317. This should have been done as part of 2f0799a0ffc0 ("mm, thp: restore node-local hugepage allocations"). The movement of the thp allocation policy from alloc_pages_vma() to alloc_hugepage_direct_gfpmask() was intended to only set __GFP_THISNODE for mempolicies that are not MPOL_BIND whereas the revert could set this regardless of mempolicy. While the check for MPOL_BIND between alloc_hugepage_direct_gfpmask() and alloc_pages_vma() was racy, that has since been removed since the revert. What is left is the possibility to use __GFP_THISNODE in policy_node() when it is unexpected because the special handling for hugepages in alloc_pages_vma() was removed as part of the consolidation. Secondly, prior to 89c83fb539f9, alloc_pages_vma() implemented a somewhat different policy for hugepage allocations, which were allocated through alloc_hugepage_vma(). For hugepage allocations, if the allocating process's node is in the set of allowed nodes, allocate with __GFP_THISNODE for that node (for MPOL_PREFERRED, use that node with __GFP_THISNODE instead). This was changed for shmem_alloc_hugepage() to allow fallback to other nodes in 89c83fb539f9 as it did for new_page() in mm/mempolicy.c which is functionally different behavior and removes the requirement to only allocate hugepages locally. So this commit does a full revert of 89c83fb539f9 instead of the partial revert that was done in 2f0799a0ffc0. The result is the same thp allocation policy for 4.20 that was in 4.19. Fixes: 89c83fb539f9 ("mm, thp: consolidate THP gfp handling into alloc_hugepage_direct_gfpmask") Fixes: 2f0799a0ffc0 ("mm, thp: restore node-local hugepage allocations") Signed-off-by: David Rientjes Acked-by: Vlastimil Babka Cc: Andrea Arcangeli Cc: Mel Gorman Cc: Michal Hocko Cc: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 76f8db0b0e71..0705164f928c 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -510,18 +510,22 @@ alloc_pages(gfp_t gfp_mask, unsigned int order) } extern struct page *alloc_pages_vma(gfp_t gfp_mask, int order, struct vm_area_struct *vma, unsigned long addr, - int node); + int node, bool hugepage); +#define alloc_hugepage_vma(gfp_mask, vma, addr, order) \ + alloc_pages_vma(gfp_mask, order, vma, addr, numa_node_id(), true) #else #define alloc_pages(gfp_mask, order) \ alloc_pages_node(numa_node_id(), gfp_mask, order) -#define alloc_pages_vma(gfp_mask, order, vma, addr, node)\ +#define alloc_pages_vma(gfp_mask, order, vma, addr, node, false)\ + alloc_pages(gfp_mask, order) +#define alloc_hugepage_vma(gfp_mask, vma, addr, order) \ alloc_pages(gfp_mask, order) #endif #define alloc_page(gfp_mask) alloc_pages(gfp_mask, 0) #define alloc_page_vma(gfp_mask, vma, addr) \ - alloc_pages_vma(gfp_mask, 0, vma, addr, numa_node_id()) + alloc_pages_vma(gfp_mask, 0, vma, addr, numa_node_id(), false) #define alloc_page_vma_node(gfp_mask, vma, addr, node) \ - alloc_pages_vma(gfp_mask, 0, vma, addr, node) + alloc_pages_vma(gfp_mask, 0, vma, addr, node, false) extern unsigned long __get_free_pages(gfp_t gfp_mask, unsigned int order); extern unsigned long get_zeroed_page(gfp_t gfp_mask); -- cgit v1.2.3