From 800977f6f32e452cba6b04ef21d2f5383ca29209 Mon Sep 17 00:00:00 2001 From: Cai Huoqing Date: Fri, 14 Jan 2022 14:02:52 -0800 Subject: kthread: add the helper function kthread_run_on_cpu() Add a new helper function kthread_run_on_cpu(), which includes kthread_create_on_cpu/wake_up_process(). In some cases, use kthread_run_on_cpu() directly instead of kthread_create_on_node/kthread_bind/wake_up_process() or kthread_create_on_cpu/wake_up_process() or kthreadd_create/kthread_bind/wake_up_process() to simplify the code. [akpm@linux-foundation.org: export kthread_create_on_cpu to modules] Link: https://lkml.kernel.org/r/20211022025711.3673-2-caihuoqing@baidu.com Signed-off-by: Cai Huoqing Cc: Bernard Metzler Cc: Cai Huoqing Cc: Daniel Bristot de Oliveira Cc: Davidlohr Bueso Cc: Doug Ledford Cc: Ingo Molnar Cc: Jason Gunthorpe Cc: Joel Fernandes (Google) Cc: Josh Triplett Cc: Lai Jiangshan Cc: Mathieu Desnoyers Cc: "Paul E . McKenney" Cc: Steven Rostedt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/kthread.c | 1 + 1 file changed, 1 insertion(+) (limited to 'kernel') diff --git a/kernel/kthread.c b/kernel/kthread.c index 7113003fab63..4ed9e7bce9e8 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -523,6 +523,7 @@ struct task_struct *kthread_create_on_cpu(int (*threadfn)(void *data), to_kthread(p)->cpu = cpu; return p; } +EXPORT_SYMBOL(kthread_create_on_cpu); void kthread_set_per_cpu(struct task_struct *k, int cpu) { -- cgit v1.2.3 From 64ed3a049e3e81b801e7c5bb052416152443f585 Mon Sep 17 00:00:00 2001 From: Cai Huoqing Date: Fri, 14 Jan 2022 14:02:59 -0800 Subject: ring-buffer: make use of the helper function kthread_run_on_cpu() Replace kthread_create/kthread_bind/wake_up_process() with kthread_run_on_cpu() to simplify the code. Link: https://lkml.kernel.org/r/20211022025711.3673-4-caihuoqing@baidu.com Signed-off-by: Cai Huoqing Cc: Bernard Metzler Cc: Daniel Bristot de Oliveira Cc: Davidlohr Bueso Cc: Doug Ledford Cc: Ingo Molnar Cc: Jason Gunthorpe Cc: Joel Fernandes (Google) Cc: Josh Triplett Cc: Lai Jiangshan Cc: Mathieu Desnoyers Cc: "Paul E . McKenney" Cc: Steven Rostedt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/trace/ring_buffer.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 2699e9e562b1..05dfc7a12d3d 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -5898,16 +5898,13 @@ static __init int test_ringbuffer(void) rb_data[cpu].buffer = buffer; rb_data[cpu].cpu = cpu; rb_data[cpu].cnt = cpu; - rb_threads[cpu] = kthread_create(rb_test, &rb_data[cpu], - "rbtester/%d", cpu); + rb_threads[cpu] = kthread_run_on_cpu(rb_test, &rb_data[cpu], + cpu, "rbtester/%u"); if (WARN_ON(IS_ERR(rb_threads[cpu]))) { pr_cont("FAILED\n"); ret = PTR_ERR(rb_threads[cpu]); goto out_free; } - - kthread_bind(rb_threads[cpu], cpu); - wake_up_process(rb_threads[cpu]); } /* Now create the rb hammer! */ -- cgit v1.2.3 From 3b9cb4ba4b54ecc6cf7d04ea9085d2ad2be48733 Mon Sep 17 00:00:00 2001 From: Cai Huoqing Date: Fri, 14 Jan 2022 14:03:02 -0800 Subject: rcutorture: make use of the helper function kthread_run_on_cpu() Replace kthread_create_on_node/kthread_bind/wake_up_process() with kthread_run_on_cpu() to simplify the code. Link: https://lkml.kernel.org/r/20211022025711.3673-5-caihuoqing@baidu.com Signed-off-by: Cai Huoqing Cc: Bernard Metzler Cc: Daniel Bristot de Oliveira Cc: Davidlohr Bueso Cc: Doug Ledford Cc: Ingo Molnar Cc: Jason Gunthorpe Cc: Joel Fernandes (Google) Cc: Josh Triplett Cc: Lai Jiangshan Cc: Mathieu Desnoyers Cc: "Paul E . McKenney" Cc: Steven Rostedt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/rcu/rcutorture.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) (limited to 'kernel') diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c index 8b410d982990..42bc66a2f170 100644 --- a/kernel/rcu/rcutorture.c +++ b/kernel/rcu/rcutorture.c @@ -1992,9 +1992,8 @@ static int rcutorture_booster_init(unsigned int cpu) mutex_lock(&boost_mutex); rcu_torture_disable_rt_throttle(); VERBOSE_TOROUT_STRING("Creating rcu_torture_boost task"); - boost_tasks[cpu] = kthread_create_on_node(rcu_torture_boost, NULL, - cpu_to_node(cpu), - "rcu_torture_boost"); + boost_tasks[cpu] = kthread_run_on_cpu(rcu_torture_boost, NULL, + cpu, "rcu_torture_boost_%u"); if (IS_ERR(boost_tasks[cpu])) { retval = PTR_ERR(boost_tasks[cpu]); VERBOSE_TOROUT_STRING("rcu_torture_boost task create failed"); @@ -2003,8 +2002,6 @@ static int rcutorture_booster_init(unsigned int cpu) mutex_unlock(&boost_mutex); return retval; } - kthread_bind(boost_tasks[cpu], cpu); - wake_up_process(boost_tasks[cpu]); mutex_unlock(&boost_mutex); return 0; } -- cgit v1.2.3 From 11e4e3523da98c065a6c249013ace0d388e41c25 Mon Sep 17 00:00:00 2001 From: Cai Huoqing Date: Fri, 14 Jan 2022 14:03:06 -0800 Subject: trace/osnoise: make use of the helper function kthread_run_on_cpu() Replace kthread_create_on_cpu/wake_up_process() with kthread_run_on_cpu() to simplify the code. Link: https://lkml.kernel.org/r/20211022025711.3673-6-caihuoqing@baidu.com Signed-off-by: Cai Huoqing Cc: Bernard Metzler Cc: Daniel Bristot de Oliveira Cc: Davidlohr Bueso Cc: Doug Ledford Cc: Ingo Molnar Cc: Jason Gunthorpe Cc: Joel Fernandes (Google) Cc: Josh Triplett Cc: Lai Jiangshan Cc: Mathieu Desnoyers Cc: "Paul E . McKenney" Cc: Steven Rostedt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/trace/trace_osnoise.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/trace_osnoise.c b/kernel/trace/trace_osnoise.c index 7520d43aed55..89d6cbac6f10 100644 --- a/kernel/trace/trace_osnoise.c +++ b/kernel/trace/trace_osnoise.c @@ -1701,7 +1701,7 @@ static int start_kthread(unsigned int cpu) snprintf(comm, 24, "osnoise/%d", cpu); } - kthread = kthread_create_on_cpu(main, NULL, cpu, comm); + kthread = kthread_run_on_cpu(main, NULL, cpu, comm); if (IS_ERR(kthread)) { pr_err(BANNER "could not start sampling thread\n"); @@ -1710,7 +1710,6 @@ static int start_kthread(unsigned int cpu) } per_cpu(per_cpu_osnoise_var, cpu).kthread = kthread; - wake_up_process(kthread); return 0; } -- cgit v1.2.3 From ff78f6679d2e223e073fcbdc8f70b6bc0abadf99 Mon Sep 17 00:00:00 2001 From: Cai Huoqing Date: Fri, 14 Jan 2022 14:03:10 -0800 Subject: trace/hwlat: make use of the helper function kthread_run_on_cpu() Replace kthread_create_on_cpu/wake_up_process() with kthread_run_on_cpu() to simplify the code. Link: https://lkml.kernel.org/r/20211022025711.3673-7-caihuoqing@baidu.com Signed-off-by: Cai Huoqing Cc: Bernard Metzler Cc: Daniel Bristot de Oliveira Cc: Davidlohr Bueso Cc: Doug Ledford Cc: Ingo Molnar Cc: Jason Gunthorpe Cc: Joel Fernandes (Google) Cc: Josh Triplett Cc: Lai Jiangshan Cc: Mathieu Desnoyers Cc: "Paul E . McKenney" Cc: Steven Rostedt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/trace/trace_hwlat.c | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/trace_hwlat.c b/kernel/trace/trace_hwlat.c index 56bb7b890578..d440ddd5fd8b 100644 --- a/kernel/trace/trace_hwlat.c +++ b/kernel/trace/trace_hwlat.c @@ -491,18 +491,14 @@ static void stop_per_cpu_kthreads(void) static int start_cpu_kthread(unsigned int cpu) { struct task_struct *kthread; - char comm[24]; - snprintf(comm, 24, "hwlatd/%d", cpu); - - kthread = kthread_create_on_cpu(kthread_fn, NULL, cpu, comm); + kthread = kthread_run_on_cpu(kthread_fn, NULL, cpu, "hwlatd/%u"); if (IS_ERR(kthread)) { pr_err(BANNER "could not start sampling thread\n"); return -ENOMEM; } per_cpu(hwlat_per_cpu_data, cpu).kthread = kthread; - wake_up_process(kthread); return 0; } -- cgit v1.2.3 From 9a10064f5625d5572c3626c1516e0bebc6c9fe9b Mon Sep 17 00:00:00 2001 From: Colin Cross Date: Fri, 14 Jan 2022 14:05:59 -0800 Subject: mm: add a field to store names for private anonymous memory In many userspace applications, and especially in VM based applications like Android uses heavily, there are multiple different allocators in use. At a minimum there is libc malloc and the stack, and in many cases there are libc malloc, the stack, direct syscalls to mmap anonymous memory, and multiple VM heaps (one for small objects, one for big objects, etc.). Each of these layers usually has its own tools to inspect its usage; malloc by compiling a debug version, the VM through heap inspection tools, and for direct syscalls there is usually no way to track them. On Android we heavily use a set of tools that use an extended version of the logic covered in Documentation/vm/pagemap.txt to walk all pages mapped in userspace and slice their usage by process, shared (COW) vs. unique mappings, backing, etc. This can account for real physical memory usage even in cases like fork without exec (which Android uses heavily to share as many private COW pages as possible between processes), Kernel SamePage Merging, and clean zero pages. It produces a measurement of the pages that only exist in that process (USS, for unique), and a measurement of the physical memory usage of that process with the cost of shared pages being evenly split between processes that share them (PSS). If all anonymous memory is indistinguishable then figuring out the real physical memory usage (PSS) of each heap requires either a pagemap walking tool that can understand the heap debugging of every layer, or for every layer's heap debugging tools to implement the pagemap walking logic, in which case it is hard to get a consistent view of memory across the whole system. Tracking the information in userspace leads to all sorts of problems. It either needs to be stored inside the process, which means every process has to have an API to export its current heap information upon request, or it has to be stored externally in a filesystem that somebody needs to clean up on crashes. It needs to be readable while the process is still running, so it has to have some sort of synchronization with every layer of userspace. Efficiently tracking the ranges requires reimplementing something like the kernel vma trees, and linking to it from every layer of userspace. It requires more memory, more syscalls, more runtime cost, and more complexity to separately track regions that the kernel is already tracking. This patch adds a field to /proc/pid/maps and /proc/pid/smaps to show a userspace-provided name for anonymous vmas. The names of named anonymous vmas are shown in /proc/pid/maps and /proc/pid/smaps as [anon:]. Userspace can set the name for a region of memory by calling prctl(PR_SET_VMA, PR_SET_VMA_ANON_NAME, start, len, (unsigned long)name) Setting the name to NULL clears it. The name length limit is 80 bytes including NUL-terminator and is checked to contain only printable ascii characters (including space), except '[',']','\','$' and '`'. Ascii strings are being used to have a descriptive identifiers for vmas, which can be understood by the users reading /proc/pid/maps or /proc/pid/smaps. Names can be standardized for a given system and they can include some variable parts such as the name of the allocator or a library, tid of the thread using it, etc. The name is stored in a pointer in the shared union in vm_area_struct that points to a null terminated string. Anonymous vmas with the same name (equivalent strings) and are otherwise mergeable will be merged. The name pointers are not shared between vmas even if they contain the same name. The name pointer is stored in a union with fields that are only used on file-backed mappings, so it does not increase memory usage. CONFIG_ANON_VMA_NAME kernel configuration is introduced to enable this feature. It keeps the feature disabled by default to prevent any additional memory overhead and to avoid confusing procfs parsers on systems which are not ready to support named anonymous vmas. The patch is based on the original patch developed by Colin Cross, more specifically on its latest version [1] posted upstream by Sumit Semwal. It used a userspace pointer to store vma names. In that design, name pointers could be shared between vmas. However during the last upstreaming attempt, Kees Cook raised concerns [2] about this approach and suggested to copy the name into kernel memory space, perform validity checks [3] and store as a string referenced from vm_area_struct. One big concern is about fork() performance which would need to strdup anonymous vma names. Dave Hansen suggested experimenting with worst-case scenario of forking a process with 64k vmas having longest possible names [4]. I ran this experiment on an ARM64 Android device and recorded a worst-case regression of almost 40% when forking such a process. This regression is addressed in the followup patch which replaces the pointer to a name with a refcounted structure that allows sharing the name pointer between vmas of the same name. Instead of duplicating the string during fork() or when splitting a vma it increments the refcount. [1] https://lore.kernel.org/linux-mm/20200901161459.11772-4-sumit.semwal@linaro.org/ [2] https://lore.kernel.org/linux-mm/202009031031.D32EF57ED@keescook/ [3] https://lore.kernel.org/linux-mm/202009031022.3834F692@keescook/ [4] https://lore.kernel.org/linux-mm/5d0358ab-8c47-2f5f-8e43-23b89d6a8e95@intel.com/ Changes for prctl(2) manual page (in the options section): PR_SET_VMA Sets an attribute specified in arg2 for virtual memory areas starting from the address specified in arg3 and spanning the size specified in arg4. arg5 specifies the value of the attribute to be set. Note that assigning an attribute to a virtual memory area might prevent it from being merged with adjacent virtual memory areas due to the difference in that attribute's value. Currently, arg2 must be one of: PR_SET_VMA_ANON_NAME Set a name for anonymous virtual memory areas. arg5 should be a pointer to a null-terminated string containing the name. The name length including null byte cannot exceed 80 bytes. If arg5 is NULL, the name of the appropriate anonymous virtual memory areas will be reset. The name can contain only printable ascii characters (including space), except '[',']','\','$' and '`'. This feature is available only if the kernel is built with the CONFIG_ANON_VMA_NAME option enabled. [surenb@google.com: docs: proc.rst: /proc/PID/maps: fix malformed table] Link: https://lkml.kernel.org/r/20211123185928.2513763-1-surenb@google.com [surenb: rebased over v5.15-rc6, replaced userpointer with a kernel copy, added input sanitization and CONFIG_ANON_VMA_NAME config. The bulk of the work here was done by Colin Cross, therefore, with his permission, keeping him as the author] Link: https://lkml.kernel.org/r/20211019215511.3771969-2-surenb@google.com Signed-off-by: Colin Cross Signed-off-by: Suren Baghdasaryan Reviewed-by: Kees Cook Cc: Stephen Rothwell Cc: Al Viro Cc: Cyrill Gorcunov Cc: Dave Hansen Cc: David Rientjes Cc: "Eric W. Biederman" Cc: Hugh Dickins Cc: Ingo Molnar Cc: Jan Glauber Cc: Johannes Weiner Cc: John Stultz Cc: Mel Gorman Cc: Minchan Kim Cc: Oleg Nesterov Cc: Pekka Enberg Cc: Peter Zijlstra Cc: Rob Landley Cc: "Serge E. Hallyn" Cc: Shaohua Li Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/fork.c | 2 ++ kernel/sys.c | 63 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 65 insertions(+) (limited to 'kernel') diff --git a/kernel/fork.c b/kernel/fork.c index 3244cc56b697..4cf20b5f2da3 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -365,12 +365,14 @@ struct vm_area_struct *vm_area_dup(struct vm_area_struct *orig) *new = data_race(*orig); INIT_LIST_HEAD(&new->anon_vma_chain); new->vm_next = new->vm_prev = NULL; + dup_vma_anon_name(orig, new); } return new; } void vm_area_free(struct vm_area_struct *vma) { + free_vma_anon_name(vma); kmem_cache_free(vm_area_cachep, vma); } diff --git a/kernel/sys.c b/kernel/sys.c index 8fdac0d90504..2450a9f33cb0 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -2261,6 +2261,66 @@ int __weak arch_prctl_spec_ctrl_set(struct task_struct *t, unsigned long which, #define PR_IO_FLUSHER (PF_MEMALLOC_NOIO | PF_LOCAL_THROTTLE) +#ifdef CONFIG_ANON_VMA_NAME + +#define ANON_VMA_NAME_MAX_LEN 80 +#define ANON_VMA_NAME_INVALID_CHARS "\\`$[]" + +static inline bool is_valid_name_char(char ch) +{ + /* printable ascii characters, excluding ANON_VMA_NAME_INVALID_CHARS */ + return ch > 0x1f && ch < 0x7f && + !strchr(ANON_VMA_NAME_INVALID_CHARS, ch); +} + +static int prctl_set_vma(unsigned long opt, unsigned long addr, + unsigned long size, unsigned long arg) +{ + struct mm_struct *mm = current->mm; + const char __user *uname; + char *name, *pch; + int error; + + switch (opt) { + case PR_SET_VMA_ANON_NAME: + uname = (const char __user *)arg; + if (uname) { + name = strndup_user(uname, ANON_VMA_NAME_MAX_LEN); + + if (IS_ERR(name)) + return PTR_ERR(name); + + for (pch = name; *pch != '\0'; pch++) { + if (!is_valid_name_char(*pch)) { + kfree(name); + return -EINVAL; + } + } + } else { + /* Reset the name */ + name = NULL; + } + + mmap_write_lock(mm); + error = madvise_set_anon_name(mm, addr, size, name); + mmap_write_unlock(mm); + kfree(name); + break; + default: + error = -EINVAL; + } + + return error; +} + +#else /* CONFIG_ANON_VMA_NAME */ +static int prctl_set_vma(unsigned long opt, unsigned long start, + unsigned long size, unsigned long arg) +{ + return -EINVAL; +} +#endif /* CONFIG_ANON_VMA_NAME */ + SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, unsigned long, arg4, unsigned long, arg5) { @@ -2530,6 +2590,9 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, error = sched_core_share_pid(arg2, arg3, arg4, arg5); break; #endif + case PR_SET_VMA: + error = prctl_set_vma(arg2, arg3, arg4, arg5); + break; default: error = -EINVAL; break; -- cgit v1.2.3 From 17fca131cee21724ee953a17c185c14e9533af5b Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 14 Jan 2022 14:06:07 -0800 Subject: mm: move anon_vma declarations to linux/mm_inline.h The patch to add anonymous vma names causes a build failure in some configurations: include/linux/mm_types.h: In function 'is_same_vma_anon_name': include/linux/mm_types.h:924:37: error: implicit declaration of function 'strcmp' [-Werror=implicit-function-declaration] 924 | return name && vma_name && !strcmp(name, vma_name); | ^~~~~~ include/linux/mm_types.h:22:1: note: 'strcmp' is defined in header ''; did you forget to '#include '? This should not really be part of linux/mm_types.h in the first place, as that header is meant to only contain structure defintions and need a minimum set of indirect includes itself. While the header clearly includes more than it should at this point, let's not make it worse by including string.h as well, which would pull in the expensive (compile-speed wise) fortify-string logic. Move the new functions into a separate header that only needs to be included in a couple of locations. Link: https://lkml.kernel.org/r/20211207125710.2503446-1-arnd@kernel.org Fixes: "mm: add a field to store names for private anonymous memory" Signed-off-by: Arnd Bergmann Cc: Al Viro Cc: Colin Cross Cc: Eric Biederman Cc: Kees Cook Cc: Matthew Wilcox (Oracle) Cc: Peter Xu Cc: Peter Zijlstra (Intel) Cc: Stephen Rothwell Cc: Suren Baghdasaryan Cc: Vlastimil Babka Cc: Yu Zhao Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/fork.c | 1 + 1 file changed, 1 insertion(+) (limited to 'kernel') diff --git a/kernel/fork.c b/kernel/fork.c index 4cf20b5f2da3..75737e566441 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -42,6 +42,7 @@ #include #include #include +#include #include #include #include -- cgit v1.2.3 From 39c65a94cd9661532be150e88f8b02f4a6844a35 Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Fri, 14 Jan 2022 14:07:17 -0800 Subject: mm/pagealloc: sysctl: change watermark_scale_factor max limit to 30% For embedded systems with low total memory, having to run applications with relatively large memory requirements, 10% max limitation for watermark_scale_factor poses an issue of triggering direct reclaim every time such application is started. This results in slow application startup times and bad end-user experience. By increasing watermark_scale_factor max limit we allow vendors more flexibility to choose the right level of kswapd aggressiveness for their device and workload requirements. Link: https://lkml.kernel.org/r/20211124193604.2758863-1-surenb@google.com Signed-off-by: Suren Baghdasaryan Acked-by: Johannes Weiner Cc: Michal Hocko Cc: Lukas Middendorf Cc: Antti Palosaari Cc: Luis Chamberlain Cc: Kees Cook Cc: Iurii Zaikin Cc: Dave Hansen Cc: Vlastimil Babka Cc: Mel Gorman Cc: Jonathan Corbet Cc: Zhang Yi Cc: Fengfei Xi Cc: Mike Rapoport Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/sysctl.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 083be6af29d7..2ab4edb6e450 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -122,6 +122,7 @@ static unsigned long long_max = LONG_MAX; static int one_hundred = 100; static int two_hundred = 200; static int one_thousand = 1000; +static int three_thousand = 3000; #ifdef CONFIG_PRINTK static int ten_thousand = 10000; #endif @@ -2959,7 +2960,7 @@ static struct ctl_table vm_table[] = { .mode = 0644, .proc_handler = watermark_scale_factor_sysctl_handler, .extra1 = SYSCTL_ONE, - .extra2 = &one_thousand, + .extra2 = &three_thousand, }, { .procname = "percpu_pagelist_high_fraction", -- cgit v1.2.3 From a674e48c5443d12a8a43c3ac42367aa39505d506 Mon Sep 17 00:00:00 2001 From: Baoquan He Date: Fri, 14 Jan 2022 14:07:41 -0800 Subject: dma/pool: create dma atomic pool only if dma zone has managed pages Currently three dma atomic pools are initialized as long as the relevant kernel codes are built in. While in kdump kernel of x86_64, this is not right when trying to create atomic_pool_dma, because there's no managed pages in DMA zone. In the case, DMA zone only has low 1M memory presented and locked down by memblock allocator. So no pages are added into buddy of DMA zone. Please check commit f1d4d47c5851 ("x86/setup: Always reserve the first 1M of RAM"). Then in kdump kernel of x86_64, it always prints below failure message: DMA: preallocated 128 KiB GFP_KERNEL pool for atomic allocations swapper/0: page allocation failure: order:5, mode:0xcc1(GFP_KERNEL|GFP_DMA), nodemask=(null),cpuset=/,mems_allowed=0 CPU: 0 PID: 1 Comm: swapper/0 Not tainted 5.13.0-0.rc5.20210611git929d931f2b40.42.fc35.x86_64 #1 Hardware name: Dell Inc. PowerEdge R910/0P658H, BIOS 2.12.0 06/04/2018 Call Trace: dump_stack+0x7f/0xa1 warn_alloc.cold+0x72/0xd6 __alloc_pages_slowpath.constprop.0+0xf29/0xf50 __alloc_pages+0x24d/0x2c0 alloc_page_interleave+0x13/0xb0 atomic_pool_expand+0x118/0x210 __dma_atomic_pool_init+0x45/0x93 dma_atomic_pool_init+0xdb/0x176 do_one_initcall+0x67/0x320 kernel_init_freeable+0x290/0x2dc kernel_init+0xa/0x111 ret_from_fork+0x22/0x30 Mem-Info: ...... DMA: failed to allocate 128 KiB GFP_KERNEL|GFP_DMA pool for atomic allocation DMA: preallocated 128 KiB GFP_KERNEL|GFP_DMA32 pool for atomic allocations Here, let's check if DMA zone has managed pages, then create atomic_pool_dma if yes. Otherwise just skip it. Link: https://lkml.kernel.org/r/20211223094435.248523-3-bhe@redhat.com Fixes: 6f599d84231f ("x86/kdump: Always reserve the low 1M when the crashkernel option is specified") Signed-off-by: Baoquan He Reviewed-by: Christoph Hellwig Acked-by: John Donnelly Reviewed-by: David Hildenbrand Cc: Marek Szyprowski Cc: Robin Murphy Cc: Borislav Petkov Cc: Christoph Lameter Cc: David Laight Cc: David Rientjes Cc: Hyeonggon Yoo <42.hyeyoo@gmail.com> Cc: Joonsoo Kim Cc: Pekka Enberg Cc: Vlastimil Babka Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/dma/pool.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/dma/pool.c b/kernel/dma/pool.c index 5f84e6cdb78e..4d40dcce7604 100644 --- a/kernel/dma/pool.c +++ b/kernel/dma/pool.c @@ -203,7 +203,7 @@ static int __init dma_atomic_pool_init(void) GFP_KERNEL); if (!atomic_pool_kernel) ret = -ENOMEM; - if (IS_ENABLED(CONFIG_ZONE_DMA)) { + if (has_managed_dma()) { atomic_pool_dma = __dma_atomic_pool_init(atomic_pool_size, GFP_KERNEL | GFP_DMA); if (!atomic_pool_dma) @@ -226,7 +226,7 @@ static inline struct gen_pool *dma_guess_pool(struct gen_pool *prev, gfp_t gfp) if (prev == NULL) { if (IS_ENABLED(CONFIG_ZONE_DMA32) && (gfp & GFP_DMA32)) return atomic_pool_dma32; - if (IS_ENABLED(CONFIG_ZONE_DMA) && (gfp & GFP_DMA)) + if (atomic_pool_dma && (gfp & GFP_DMA)) return atomic_pool_dma; return atomic_pool_kernel; } -- cgit v1.2.3 From 21b084fdf2a49ca1634e8e360e9ab6f9ff0dee11 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Fri, 14 Jan 2022 14:08:21 -0800 Subject: mm/mempolicy: wire up syscall set_mempolicy_home_node Link: https://lkml.kernel.org/r/20211202123810.267175-4-aneesh.kumar@linux.ibm.com Signed-off-by: Aneesh Kumar K.V Cc: Ben Widawsky Cc: Dave Hansen Cc: Feng Tang Cc: Michal Hocko Cc: Andrea Arcangeli Cc: Mel Gorman Cc: Mike Kravetz Cc: Randy Dunlap Cc: Vlastimil Babka Cc: Andi Kleen Cc: Dan Williams Cc: Huang Ying Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/sys_ni.c | 1 + 1 file changed, 1 insertion(+) (limited to 'kernel') diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c index d1944258cfc0..a492f159624f 100644 --- a/kernel/sys_ni.c +++ b/kernel/sys_ni.c @@ -297,6 +297,7 @@ COND_SYSCALL(get_mempolicy); COND_SYSCALL(set_mempolicy); COND_SYSCALL(migrate_pages); COND_SYSCALL(move_pages); +COND_SYSCALL(set_mempolicy_home_node); COND_SYSCALL(perf_event_open); COND_SYSCALL(accept4); -- cgit v1.2.3