From 90edaac62729d3b9cbb97756261a0049a7fdd6a0 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Fri, 27 Oct 2017 10:03:13 +0200 Subject: Revert "x86/mm: Limit mmap() of /dev/mem to valid physical addresses" This reverts commit ce56a86e2ade45d052b3228cdfebe913a1ae7381. There's unanticipated interaction with some boot parameters like 'mem=', which now cause the new checks via valid_mmap_phys_addr_range() to be too restrictive, crashing a Qemu bootup in fact, as reported by Fengguang Wu. So while the motivation of the change is still entirely valid, we need a few more rounds of testing to get it right - it's way too late after -rc6, so revert it for now. Reported-by: Fengguang Wu Signed-off-by: Ingo Molnar Acked-by: Craig Bergstrom Cc: Andrew Morton Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Josh Poimboeuf Cc: Linus Torvalds Cc: Luis R. Rodriguez Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Toshi Kani Cc: dsafonov@virtuozzo.com Cc: kirill.shutemov@linux.intel.com Cc: mhocko@suse.com Cc: oleg@redhat.com Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar --- arch/x86/mm/mmap.c | 12 ------------ 1 file changed, 12 deletions(-) (limited to 'arch/x86/mm') diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c index 320c623..a996798 100644 --- a/arch/x86/mm/mmap.c +++ b/arch/x86/mm/mmap.c @@ -174,15 +174,3 @@ const char *arch_vma_name(struct vm_area_struct *vma) return "[mpx]"; return NULL; } - -int valid_phys_addr_range(phys_addr_t addr, size_t count) -{ - return addr + count <= __pa(high_memory); -} - -int valid_mmap_phys_addr_range(unsigned long pfn, size_t count) -{ - phys_addr_t addr = (phys_addr_t)pfn << PAGE_SHIFT; - - return valid_phys_addr_range(addr, count); -} -- cgit v1.1 From cb0631fd3cf9e989cd48293fe631cbc402aec9a9 Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Wed, 1 Nov 2017 08:21:25 +0100 Subject: x86/mm: fix use-after-free of vma during userfaultfd fault Syzkaller with KASAN has reported a use-after-free of vma->vm_flags in __do_page_fault() with the following reproducer: mmap(&(0x7f0000000000/0xfff000)=nil, 0xfff000, 0x3, 0x32, 0xffffffffffffffff, 0x0) mmap(&(0x7f0000011000/0x3000)=nil, 0x3000, 0x1, 0x32, 0xffffffffffffffff, 0x0) r0 = userfaultfd(0x0) ioctl$UFFDIO_API(r0, 0xc018aa3f, &(0x7f0000002000-0x18)={0xaa, 0x0, 0x0}) ioctl$UFFDIO_REGISTER(r0, 0xc020aa00, &(0x7f0000019000)={{&(0x7f0000012000/0x2000)=nil, 0x2000}, 0x1, 0x0}) r1 = gettid() syz_open_dev$evdev(&(0x7f0000013000-0x12)="2f6465762f696e7075742f6576656e742300", 0x0, 0x0) tkill(r1, 0x7) The vma should be pinned by mmap_sem, but handle_userfault() might (in a return to userspace scenario) release it and then acquire again, so when we return to __do_page_fault() (with other result than VM_FAULT_RETRY), the vma might be gone. Specifically, per Andrea the scenario is "A return to userland to repeat the page fault later with a VM_FAULT_NOPAGE retval (potentially after handling any pending signal during the return to userland). The return to userland is identified whenever FAULT_FLAG_USER|FAULT_FLAG_KILLABLE are both set in vmf->flags" However, since commit a3c4fb7c9c2e ("x86/mm: Fix fault error path using unsafe vma pointer") there is a vma_pkey() read of vma->vm_flags after that point, which can thus become use-after-free. Fix this by moving the read before calling handle_mm_fault(). Reported-by: syzbot Reported-by: Dmitry Vyukov Suggested-by: Kirill A. Shutemov Fixes: 3c4fb7c9c2e ("x86/mm: Fix fault error path using unsafe vma pointer") Reviewed-by: Andrea Arcangeli Signed-off-by: Vlastimil Babka Signed-off-by: Linus Torvalds --- arch/x86/mm/fault.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) (limited to 'arch/x86/mm') diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index e2baeaa..7101c28 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -1440,7 +1440,17 @@ good_area: * make sure we exit gracefully rather than endlessly redo * the fault. Since we never set FAULT_FLAG_RETRY_NOWAIT, if * we get VM_FAULT_RETRY back, the mmap_sem has been unlocked. + * + * Note that handle_userfault() may also release and reacquire mmap_sem + * (and not return with VM_FAULT_RETRY), when returning to userland to + * repeat the page fault later with a VM_FAULT_NOPAGE retval + * (potentially after handling any pending signal during the return to + * userland). The return to userland is identified whenever + * FAULT_FLAG_USER|FAULT_FLAG_KILLABLE are both set in flags. + * Thus we have to be careful about not touching vma after handling the + * fault, so we read the pkey beforehand. */ + pkey = vma_pkey(vma); fault = handle_mm_fault(vma, address, flags); major |= fault & VM_FAULT_MAJOR; @@ -1467,7 +1477,6 @@ good_area: return; } - pkey = vma_pkey(vma); up_read(&mm->mmap_sem); if (unlikely(fault & VM_FAULT_ERROR)) { mm_fault_error(regs, error_code, address, &pkey, fault); -- cgit v1.1 From b24413180f5600bcb3bb70fbed5cf186b60864bd Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 1 Nov 2017 15:07:57 +0100 Subject: License cleanup: add SPDX GPL-2.0 license identifier to files with no license Many source files in the tree are missing licensing information, which makes it harder for compliance tools to determine the correct license. By default all files without license information are under the default license of the kernel, which is GPL version 2. Update the files which contain no license information with the 'GPL-2.0' SPDX license identifier. The SPDX identifier is a legally binding shorthand, which can be used instead of the full boiler plate text. This patch is based on work done by Thomas Gleixner and Kate Stewart and Philippe Ombredanne. How this work was done: Patches were generated and checked against linux-4.14-rc6 for a subset of the use cases: - file had no licensing information it it. - file was a */uapi/* one with no licensing information in it, - file was a */uapi/* one with existing licensing information, Further patches will be generated in subsequent months to fix up cases where non-standard license headers were used, and references to license had to be inferred by heuristics based on keywords. The analysis to determine which SPDX License Identifier to be applied to a file was done in a spreadsheet of side by side results from of the output of two independent scanners (ScanCode & Windriver) producing SPDX tag:value files created by Philippe Ombredanne. Philippe prepared the base worksheet, and did an initial spot review of a few 1000 files. The 4.13 kernel was the starting point of the analysis with 60,537 files assessed. Kate Stewart did a file by file comparison of the scanner results in the spreadsheet to determine which SPDX license identifier(s) to be applied to the file. She confirmed any determination that was not immediately clear with lawyers working with the Linux Foundation. Criteria used to select files for SPDX license identifier tagging was: - Files considered eligible had to be source code files. - Make and config files were included as candidates if they contained >5 lines of source - File already had some variant of a license header in it (even if <5 lines). All documentation files were explicitly excluded. The following heuristics were used to determine which SPDX license identifiers to apply. - when both scanners couldn't find any license traces, file was considered to have no license information in it, and the top level COPYING file license applied. For non */uapi/* files that summary was: SPDX license identifier # files ---------------------------------------------------|------- GPL-2.0 11139 and resulted in the first patch in this series. If that file was a */uapi/* path one, it was "GPL-2.0 WITH Linux-syscall-note" otherwise it was "GPL-2.0". Results of that was: SPDX license identifier # files ---------------------------------------------------|------- GPL-2.0 WITH Linux-syscall-note 930 and resulted in the second patch in this series. - if a file had some form of licensing information in it, and was one of the */uapi/* ones, it was denoted with the Linux-syscall-note if any GPL family license was found in the file or had no licensing in it (per prior point). Results summary: SPDX license identifier # files ---------------------------------------------------|------ GPL-2.0 WITH Linux-syscall-note 270 GPL-2.0+ WITH Linux-syscall-note 169 ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) 21 ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) 17 LGPL-2.1+ WITH Linux-syscall-note 15 GPL-1.0+ WITH Linux-syscall-note 14 ((GPL-2.0+ WITH Linux-syscall-note) OR BSD-3-Clause) 5 LGPL-2.0+ WITH Linux-syscall-note 4 LGPL-2.1 WITH Linux-syscall-note 3 ((GPL-2.0 WITH Linux-syscall-note) OR MIT) 3 ((GPL-2.0 WITH Linux-syscall-note) AND MIT) 1 and that resulted in the third patch in this series. - when the two scanners agreed on the detected license(s), that became the concluded license(s). - when there was disagreement between the two scanners (one detected a license but the other didn't, or they both detected different licenses) a manual inspection of the file occurred. - In most cases a manual inspection of the information in the file resulted in a clear resolution of the license that should apply (and which scanner probably needed to revisit its heuristics). - When it was not immediately clear, the license identifier was confirmed with lawyers working with the Linux Foundation. - If there was any question as to the appropriate license identifier, the file was flagged for further research and to be revisited later in time. In total, over 70 hours of logged manual review was done on the spreadsheet to determine the SPDX license identifiers to apply to the source files by Kate, Philippe, Thomas and, in some cases, confirmation by lawyers working with the Linux Foundation. Kate also obtained a third independent scan of the 4.13 code base from FOSSology, and compared selected files where the other two scanners disagreed against that SPDX file, to see if there was new insights. The Windriver scanner is based on an older version of FOSSology in part, so they are related. Thomas did random spot checks in about 500 files from the spreadsheets for the uapi headers and agreed with SPDX license identifier in the files he inspected. For the non-uapi files Thomas did random spot checks in about 15000 files. In initial set of patches against 4.14-rc6, 3 files were found to have copy/paste license identifier errors, and have been fixed to reflect the correct identifier. Additionally Philippe spent 10 hours this week doing a detailed manual inspection and review of the 12,461 patched files from the initial patch version early this week with: - a full scancode scan run, collecting the matched texts, detected license ids and scores - reviewing anything where there was a license detected (about 500+ files) to ensure that the applied SPDX license was correct - reviewing anything where there was no detection but the patch license was not GPL-2.0 WITH Linux-syscall-note to ensure that the applied SPDX license was correct This produced a worksheet with 20 files needing minor correction. This worksheet was then exported into 3 different .csv files for the different types of files to be modified. These .csv files were then reviewed by Greg. Thomas wrote a script to parse the csv files and add the proper SPDX tag to the file, in the format that the file expected. This script was further refined by Greg based on the output to detect more types of files automatically and to distinguish between header and source .c files (which need different comment types.) Finally Greg ran the script using the .csv files to generate the patches. Reviewed-by: Kate Stewart Reviewed-by: Philippe Ombredanne Reviewed-by: Thomas Gleixner Signed-off-by: Greg Kroah-Hartman --- arch/x86/mm/Makefile | 1 + arch/x86/mm/amdtopology.c | 1 + arch/x86/mm/fault.c | 1 + arch/x86/mm/hugetlbpage.c | 1 + arch/x86/mm/ident_map.c | 1 + arch/x86/mm/kasan_init_64.c | 1 + arch/x86/mm/kaslr.c | 1 + arch/x86/mm/kmemcheck/error.c | 1 + arch/x86/mm/kmemcheck/error.h | 1 + arch/x86/mm/kmemcheck/opcode.c | 1 + arch/x86/mm/kmemcheck/opcode.h | 1 + arch/x86/mm/kmemcheck/pte.c | 1 + arch/x86/mm/kmemcheck/pte.h | 1 + arch/x86/mm/kmemcheck/selftest.c | 1 + arch/x86/mm/kmemcheck/selftest.h | 1 + arch/x86/mm/kmemcheck/shadow.h | 1 + arch/x86/mm/kmmio.c | 1 + arch/x86/mm/mm_internal.h | 1 + arch/x86/mm/mpx.c | 1 + arch/x86/mm/numa_64.c | 1 + arch/x86/mm/numa_emulation.c | 1 + arch/x86/mm/numa_internal.h | 1 + arch/x86/mm/pageattr-test.c | 1 + arch/x86/mm/pat_internal.h | 1 + arch/x86/mm/pat_rbtree.c | 1 + arch/x86/mm/pgtable.c | 1 + arch/x86/mm/pgtable_32.c | 1 + arch/x86/mm/physaddr.c | 1 + arch/x86/mm/physaddr.h | 1 + arch/x86/mm/setup_nx.c | 1 + arch/x86/mm/srat.c | 1 + 31 files changed, 31 insertions(+) (limited to 'arch/x86/mm') diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile index e1f0958..7ba7f3d 100644 --- a/arch/x86/mm/Makefile +++ b/arch/x86/mm/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 # Kernel does not boot with instrumentation of tlb.c and mem_encrypt.c KCOV_INSTRUMENT_tlb.o := n KCOV_INSTRUMENT_mem_encrypt.o := n diff --git a/arch/x86/mm/amdtopology.c b/arch/x86/mm/amdtopology.c index 91f501b..048c761 100644 --- a/arch/x86/mm/amdtopology.c +++ b/arch/x86/mm/amdtopology.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * AMD NUMA support. * Discover the memory map and associated nodes. diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index e2baeaa..f5ff142 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 1995 Linus Torvalds * Copyright (C) 2001, 2002 Andi Kleen, SuSE Labs. diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c index 6d06cf3..8ae0000 100644 --- a/arch/x86/mm/hugetlbpage.c +++ b/arch/x86/mm/hugetlbpage.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * IA-32 Huge TLB Page Support for Kernel. * diff --git a/arch/x86/mm/ident_map.c b/arch/x86/mm/ident_map.c index 31cea98..ab33a32 100644 --- a/arch/x86/mm/ident_map.c +++ b/arch/x86/mm/ident_map.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Helper routines for building identity mapping page tables. This is * included by both the compressed kernel and the regular kernel. diff --git a/arch/x86/mm/kasan_init_64.c b/arch/x86/mm/kasan_init_64.c index bc84b73..8f5be3e 100644 --- a/arch/x86/mm/kasan_init_64.c +++ b/arch/x86/mm/kasan_init_64.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #define DISABLE_BRANCH_PROFILING #define pr_fmt(fmt) "kasan: " fmt #include diff --git a/arch/x86/mm/kaslr.c b/arch/x86/mm/kaslr.c index af59916..879ef93 100644 --- a/arch/x86/mm/kaslr.c +++ b/arch/x86/mm/kaslr.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * This file implements KASLR memory randomization for x86_64. It randomizes * the virtual address space of kernel memory regions (physical memory diff --git a/arch/x86/mm/kmemcheck/error.c b/arch/x86/mm/kmemcheck/error.c index dab4187..872ec41 100644 --- a/arch/x86/mm/kmemcheck/error.c +++ b/arch/x86/mm/kmemcheck/error.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include #include #include diff --git a/arch/x86/mm/kmemcheck/error.h b/arch/x86/mm/kmemcheck/error.h index 0efc2e8..39f80d7 100644 --- a/arch/x86/mm/kmemcheck/error.h +++ b/arch/x86/mm/kmemcheck/error.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef ARCH__X86__MM__KMEMCHECK__ERROR_H #define ARCH__X86__MM__KMEMCHECK__ERROR_H diff --git a/arch/x86/mm/kmemcheck/opcode.c b/arch/x86/mm/kmemcheck/opcode.c index 324aa3f..df8109d 100644 --- a/arch/x86/mm/kmemcheck/opcode.c +++ b/arch/x86/mm/kmemcheck/opcode.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include #include "opcode.h" diff --git a/arch/x86/mm/kmemcheck/opcode.h b/arch/x86/mm/kmemcheck/opcode.h index 6956aad..51a1ce9 100644 --- a/arch/x86/mm/kmemcheck/opcode.h +++ b/arch/x86/mm/kmemcheck/opcode.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef ARCH__X86__MM__KMEMCHECK__OPCODE_H #define ARCH__X86__MM__KMEMCHECK__OPCODE_H diff --git a/arch/x86/mm/kmemcheck/pte.c b/arch/x86/mm/kmemcheck/pte.c index 4ead26e..8a03be9 100644 --- a/arch/x86/mm/kmemcheck/pte.c +++ b/arch/x86/mm/kmemcheck/pte.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include #include diff --git a/arch/x86/mm/kmemcheck/pte.h b/arch/x86/mm/kmemcheck/pte.h index 9f59664..b595612 100644 --- a/arch/x86/mm/kmemcheck/pte.h +++ b/arch/x86/mm/kmemcheck/pte.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef ARCH__X86__MM__KMEMCHECK__PTE_H #define ARCH__X86__MM__KMEMCHECK__PTE_H diff --git a/arch/x86/mm/kmemcheck/selftest.c b/arch/x86/mm/kmemcheck/selftest.c index aef7140..7ce0be1 100644 --- a/arch/x86/mm/kmemcheck/selftest.c +++ b/arch/x86/mm/kmemcheck/selftest.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include #include diff --git a/arch/x86/mm/kmemcheck/selftest.h b/arch/x86/mm/kmemcheck/selftest.h index 8fed4fe..8d759aa 100644 --- a/arch/x86/mm/kmemcheck/selftest.h +++ b/arch/x86/mm/kmemcheck/selftest.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef ARCH_X86_MM_KMEMCHECK_SELFTEST_H #define ARCH_X86_MM_KMEMCHECK_SELFTEST_H diff --git a/arch/x86/mm/kmemcheck/shadow.h b/arch/x86/mm/kmemcheck/shadow.h index ff0b2f7..49768dc 100644 --- a/arch/x86/mm/kmemcheck/shadow.h +++ b/arch/x86/mm/kmemcheck/shadow.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef ARCH__X86__MM__KMEMCHECK__SHADOW_H #define ARCH__X86__MM__KMEMCHECK__SHADOW_H diff --git a/arch/x86/mm/kmmio.c b/arch/x86/mm/kmmio.c index afc47f5..c21c2ed 100644 --- a/arch/x86/mm/kmmio.c +++ b/arch/x86/mm/kmmio.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* Support for MMIO probes. * Benfit many code from kprobes * (C) 2002 Louis Zhuang . diff --git a/arch/x86/mm/mm_internal.h b/arch/x86/mm/mm_internal.h index 62474ba..4e1f6e1 100644 --- a/arch/x86/mm/mm_internal.h +++ b/arch/x86/mm/mm_internal.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __X86_MM_INTERNAL_H #define __X86_MM_INTERNAL_H diff --git a/arch/x86/mm/mpx.c b/arch/x86/mm/mpx.c index 9ceaa95..7eb0670 100644 --- a/arch/x86/mm/mpx.c +++ b/arch/x86/mm/mpx.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * mpx.c - Memory Protection eXtensions * diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c index 9405ffc..066f351 100644 --- a/arch/x86/mm/numa_64.c +++ b/arch/x86/mm/numa_64.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Generic VM initialization for x86-64 NUMA setups. * Copyright 2002,2003 Andi Kleen, SuSE Labs. diff --git a/arch/x86/mm/numa_emulation.c b/arch/x86/mm/numa_emulation.c index d805162..34a2a3b 100644 --- a/arch/x86/mm/numa_emulation.c +++ b/arch/x86/mm/numa_emulation.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * NUMA emulation */ diff --git a/arch/x86/mm/numa_internal.h b/arch/x86/mm/numa_internal.h index ad86ec9..86860f2 100644 --- a/arch/x86/mm/numa_internal.h +++ b/arch/x86/mm/numa_internal.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __X86_MM_NUMA_INTERNAL_H #define __X86_MM_NUMA_INTERNAL_H diff --git a/arch/x86/mm/pageattr-test.c b/arch/x86/mm/pageattr-test.c index 5f169d5..a25588a 100644 --- a/arch/x86/mm/pageattr-test.c +++ b/arch/x86/mm/pageattr-test.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * self test for change_page_attr. * diff --git a/arch/x86/mm/pat_internal.h b/arch/x86/mm/pat_internal.h index a739bfc..eeb5cae 100644 --- a/arch/x86/mm/pat_internal.h +++ b/arch/x86/mm/pat_internal.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __PAT_INTERNAL_H_ #define __PAT_INTERNAL_H_ diff --git a/arch/x86/mm/pat_rbtree.c b/arch/x86/mm/pat_rbtree.c index d76485b..fa16036 100644 --- a/arch/x86/mm/pat_rbtree.c +++ b/arch/x86/mm/pat_rbtree.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Handle caching attributes in page tables (PAT) * diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index b372f34..17ebc5a 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include #include #include diff --git a/arch/x86/mm/pgtable_32.c b/arch/x86/mm/pgtable_32.c index b9bd5b8..6b9bf02 100644 --- a/arch/x86/mm/pgtable_32.c +++ b/arch/x86/mm/pgtable_32.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include #include #include diff --git a/arch/x86/mm/physaddr.c b/arch/x86/mm/physaddr.c index cfc3b91..7f9acb6 100644 --- a/arch/x86/mm/physaddr.c +++ b/arch/x86/mm/physaddr.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include #include #include diff --git a/arch/x86/mm/physaddr.h b/arch/x86/mm/physaddr.h index a3cd5a0..9f6419c 100644 --- a/arch/x86/mm/physaddr.h +++ b/arch/x86/mm/physaddr.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #include static inline int phys_addr_valid(resource_size_t addr) diff --git a/arch/x86/mm/setup_nx.c b/arch/x86/mm/setup_nx.c index f65a33f..adb3c57 100644 --- a/arch/x86/mm/setup_nx.c +++ b/arch/x86/mm/setup_nx.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include #include #include diff --git a/arch/x86/mm/srat.c b/arch/x86/mm/srat.c index 3ea20d6..dac07e4 100644 --- a/arch/x86/mm/srat.c +++ b/arch/x86/mm/srat.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * ACPI 3.0 based NUMA setup * Copyright 2004 Andi Kleen, SuSE Labs. -- cgit v1.1 From 675357362aeba19688440eb1aaa7991067f73b12 Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Sat, 4 Nov 2017 04:16:12 -0700 Subject: Revert "x86/mm: Stop calling leave_mm() in idle code" This reverts commit 43858b4f25cf0adc5c2ca9cf5ce5fdf2532941e5. The reason I removed the leave_mm() calls in question is because the heuristic wasn't needed after that patch. With the original version of my PCID series, we never flushed a "lazy cpu" (i.e. a CPU running kernel thread) due a flush on the loaded mm. Unfortunately, that caused architectural issues, so now I've reinstated these flushes on non-PCID systems in: commit b956575bed91 ("x86/mm: Flush more aggressively in lazy TLB mode"). That, in turn, gives us a power management and occasionally performance regression as compared to old kernels: a process that goes into a deep idle state on a given CPU and gets its mm flushed due to activity on a different CPU will wake the idle CPU. Reinstate the old ugly heuristic: if a CPU goes into ACPI C3 or an intel_idle state that is likely to cause a TLB flush gets its mm switched to init_mm before going idle. FWIW, this heuristic is lousy. Whether we should change CR3 before idle isn't a good hint except insofar as the performance hit is a bit lower if the TLB is getting flushed by the idle code anyway. What we really want to know is whether we anticipate being idle long enough that the mm is likely to be flushed before we wake up. This is more a matter of the expected latency than the idle state that gets chosen. This heuristic also completely fails on systems that don't know whether the TLB will be flushed (e.g. AMD systems?). OTOH it may be a bit obsolete anyway -- PCID systems don't presently benefit from this heuristic at all. We also shouldn't do this callback from innermost bit of the idle code due to the RCU nastiness it causes. All the information need is available before rcu_idle_enter() needs to happen. Signed-off-by: Andy Lutomirski Cc: Borislav Petkov Cc: Borislav Petkov Cc: Brian Gerst Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Josh Poimboeuf Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Fixes: 43858b4f25cf "x86/mm: Stop calling leave_mm() in idle code" Link: http://lkml.kernel.org/r/c513bbd4e653747213e05bc7062de000bf0202a5.1509793738.git.luto@kernel.org Signed-off-by: Ingo Molnar --- arch/x86/mm/tlb.c | 17 ++++++++++++++--- 1 file changed, 14 insertions(+), 3 deletions(-) (limited to 'arch/x86/mm') diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 0f3d0ce..3118392cd 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -85,6 +85,7 @@ void leave_mm(int cpu) switch_mm(NULL, &init_mm, NULL); } +EXPORT_SYMBOL_GPL(leave_mm); void switch_mm(struct mm_struct *prev, struct mm_struct *next, struct task_struct *tsk) @@ -195,12 +196,22 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, this_cpu_write(cpu_tlbstate.ctxs[new_asid].ctx_id, next->context.ctx_id); this_cpu_write(cpu_tlbstate.ctxs[new_asid].tlb_gen, next_tlb_gen); write_cr3(build_cr3(next, new_asid)); - trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, - TLB_FLUSH_ALL); + + /* + * NB: This gets called via leave_mm() in the idle path + * where RCU functions differently. Tracing normally + * uses RCU, so we need to use the _rcuidle variant. + * + * (There is no good reason for this. The idle code should + * be rearranged to call this before rcu_idle_enter().) + */ + trace_tlb_flush_rcuidle(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL); } else { /* The new ASID is already up to date. */ write_cr3(build_cr3_noflush(next, new_asid)); - trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, 0); + + /* See above wrt _rcuidle. */ + trace_tlb_flush_rcuidle(TLB_FLUSH_ON_TASK_SWITCH, 0); } this_cpu_write(cpu_tlbstate.loaded_mm, next); -- cgit v1.1