diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 0315407f5f57..13f13fdd4731 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -1594,6 +1594,23 @@ Documentation/admin-guide/mm/hugetlbpage.rst. Format: size[KMG] + hugetlb_free_vmemmap= + [KNL] Reguires CONFIG_HUGETLB_PAGE_FREE_VMEMMAP + enabled. + Allows heavy hugetlb users to free up some more + memory (6 * PAGE_SIZE for each 2MB hugetlb page). + Format: { on | off (default) } + + on: enable the feature + off: disable the feature + + Built with CONFIG_HUGETLB_PAGE_FREE_VMEMMAP_DEFAULT_ON=y, + the default is on. + + This is not compatible with memory_hotplug.memmap_on_memory. + If both parameters are enabled, hugetlb_free_vmemmap takes + precedence over memory_hotplug.memmap_on_memory. + hung_task_panic= [KNL] Should the hung task detector generate panics. Format: 0 | 1 @@ -2860,6 +2877,10 @@ Note that even when enabled, there are a few cases where the feature is not effective. + This is not compatible with hugetlb_free_vmemmap. If + both parameters are enabled, hugetlb_free_vmemmap takes + precedence over memory_hotplug.memmap_on_memory. + memtest= [KNL,X86,ARM,PPC,RISCV] Enable memtest Format: default : 0 diff --git a/Documentation/admin-guide/mm/hugetlbpage.rst b/Documentation/admin-guide/mm/hugetlbpage.rst index f7b1c7462991..8abaeb144e44 100644 --- a/Documentation/admin-guide/mm/hugetlbpage.rst +++ b/Documentation/admin-guide/mm/hugetlbpage.rst @@ -60,6 +60,10 @@ HugePages_Surp the pool above the value in ``/proc/sys/vm/nr_hugepages``. The maximum number of surplus huge pages is controlled by ``/proc/sys/vm/nr_overcommit_hugepages``. + Note: When the feature of freeing unused vmemmap pages associated + with each hugetlb page is enabled, the number of surplus huge pages + may be temporarily larger than the maximum number of surplus huge + pages when the system is under memory pressure. Hugepagesize is the default hugepage size (in Kb). Hugetlb @@ -80,6 +84,10 @@ returned to the huge page pool when freed by a task. A user with root privileges can dynamically allocate more or free some persistent huge pages by increasing or decreasing the value of ``nr_hugepages``. +Note: When the feature of freeing unused vmemmap pages associated with each +hugetlb page is enabled, we can fail to free the huge pages triggered by +the user when ths system is under memory pressure. Please try again later. + Pages that are used as huge pages are reserved inside the kernel and cannot be used for other purposes. Huge pages cannot be swapped out under memory pressure. @@ -145,6 +153,9 @@ default_hugepagesz will all result in 256 2M huge pages being allocated. Valid default huge page size is architecture dependent. +hugetlb_free_vmemmap + When CONFIG_HUGETLB_PAGE_FREE_VMEMMAP is set, this enables freeing + unused vmemmap pages associated with each HugeTLB page. When multiple huge page sizes are supported, ``/proc/sys/vm/nr_hugepages`` indicates the current number of pre-allocated huge pages of the default size. diff --git a/Documentation/admin-guide/mm/memory-hotplug.rst b/Documentation/admin-guide/mm/memory-hotplug.rst index 05d51d2d8beb..c6bae2d77160 100644 --- a/Documentation/admin-guide/mm/memory-hotplug.rst +++ b/Documentation/admin-guide/mm/memory-hotplug.rst @@ -357,6 +357,19 @@ creates ZONE_MOVABLE as following. Unfortunately, there is no information to show which memory block belongs to ZONE_MOVABLE. This is TBD. + Memory offlining can fail when dissolving a free huge page on ZONE_MOVABLE + and the feature of freeing unused vmemmap pages associated with each hugetlb + page is enabled. + + This can happen when we have plenty of ZONE_MOVABLE memory, but not enough + kernel memory to allocate vmemmmap pages. We may even be able to migrate + huge page contents, but will not be able to dissolve the source huge page. + This will prevent an offline operation and is unfortunate as memory offlining + is expected to succeed on movable zones. Users that depend on memory hotplug + to succeed for movable zones should carefully consider whether the memory + savings gained from this feature are worth the risk of possibly not being + able to offline memory in certain situations. + .. note:: Techniques that rely on long-term pinnings of memory (especially, RDMA and vfio) are fundamentally problematic with ZONE_MOVABLE and, therefore, memory diff --git a/Documentation/admin-guide/mm/pagemap.rst b/Documentation/admin-guide/mm/pagemap.rst index 340a5aee9b80..fb578fbbb76c 100644 --- a/Documentation/admin-guide/mm/pagemap.rst +++ b/Documentation/admin-guide/mm/pagemap.rst @@ -21,6 +21,8 @@ There are four components to pagemap: * Bit 55 pte is soft-dirty (see :ref:`Documentation/admin-guide/mm/soft-dirty.rst `) * Bit 56 page exclusively mapped (since 4.2) + * Bit 57 pte is uffd-wp write-protected (since 5.13) (see + :ref:`Documentation/admin-guide/mm/userfaultfd.rst `) * Bits 57-60 zero * Bit 61 page is file-page or shared-anon (since 3.5) * Bit 62 page swapped diff --git a/Documentation/admin-guide/mm/userfaultfd.rst b/Documentation/admin-guide/mm/userfaultfd.rst index 3aa38e8b8361..6528036093e1 100644 --- a/Documentation/admin-guide/mm/userfaultfd.rst +++ b/Documentation/admin-guide/mm/userfaultfd.rst @@ -77,7 +77,8 @@ events, except page fault notifications, may be generated: - ``UFFD_FEATURE_MINOR_HUGETLBFS`` indicates that the kernel supports ``UFFDIO_REGISTER_MODE_MINOR`` registration for hugetlbfs virtual memory - areas. + areas. ``UFFD_FEATURE_MINOR_SHMEM`` is the analogous feature indicating + support for shmem virtual memory areas. The userland application should set the feature flags it intends to use when invoking the ``UFFDIO_API`` ioctl, to request that those features be diff --git a/Documentation/core-api/kernel-api.rst b/Documentation/core-api/kernel-api.rst index 741aa37dc181..2a7444e3a4c2 100644 --- a/Documentation/core-api/kernel-api.rst +++ b/Documentation/core-api/kernel-api.rst @@ -24,11 +24,8 @@ String Conversions .. kernel-doc:: lib/vsprintf.c :export: -.. kernel-doc:: include/linux/kernel.h - :functions: kstrtol - -.. kernel-doc:: include/linux/kernel.h - :functions: kstrtoul +.. kernel-doc:: include/linux/kstrtox.h + :functions: kstrtol kstrtoul .. kernel-doc:: lib/kstrtox.c :export: diff --git a/Documentation/filesystems/proc.rst b/Documentation/filesystems/proc.rst index 81bfe3c800cc..042c418f4090 100644 --- a/Documentation/filesystems/proc.rst +++ b/Documentation/filesystems/proc.rst @@ -933,8 +933,15 @@ meminfo ~~~~~~~ Provides information about distribution and utilization of memory. This -varies by architecture and compile options. The following is from a -16GB PIII, which has highmem enabled. You may not have all of these fields. +varies by architecture and compile options. Some of the counters reported +here overlap. The memory reported by the non overlapping counters may not +add up to the overall memory usage and the difference for some workloads +can be substantial. In many cases there are other means to find out +additional memory using subsystem specific interfaces, for instance +/proc/net/sockstat for TCP memory allocations. + +The following is from a 16GB PIII, which has highmem enabled. +You may not have all of these fields. :: @@ -1913,18 +1920,20 @@ if precise results are needed. 3.8 /proc//fdinfo/ - Information about opened file --------------------------------------------------------------- This file provides information associated with an opened file. The regular -files have at least three fields -- 'pos', 'flags' and 'mnt_id'. The 'pos' -represents the current offset of the opened file in decimal form [see lseek(2) -for details], 'flags' denotes the octal O_xxx mask the file has been -created with [see open(2) for details] and 'mnt_id' represents mount ID of -the file system containing the opened file [see 3.5 /proc//mountinfo -for details]. +files have at least four fields -- 'pos', 'flags', 'mnt_id' and 'ino'. +The 'pos' represents the current offset of the opened file in decimal +form [see lseek(2) for details], 'flags' denotes the octal O_xxx mask the +file has been created with [see open(2) for details] and 'mnt_id' represents +mount ID of the file system containing the opened file [see 3.5 +/proc//mountinfo for details]. 'ino' represents the inode number of +the file. A typical output is:: pos: 0 flags: 0100002 mnt_id: 19 + ino: 63107 All locks associated with a file descriptor are shown in its fdinfo too:: @@ -1941,6 +1950,7 @@ Eventfd files pos: 0 flags: 04002 mnt_id: 9 + ino: 63107 eventfd-count: 5a where 'eventfd-count' is hex value of a counter. @@ -1953,6 +1963,7 @@ Signalfd files pos: 0 flags: 04002 mnt_id: 9 + ino: 63107 sigmask: 0000000000000200 where 'sigmask' is hex value of the signal mask associated @@ -1966,6 +1977,7 @@ Epoll files pos: 0 flags: 02 mnt_id: 9 + ino: 63107 tfd: 5 events: 1d data: ffffffffffffffff pos:0 ino:61af sdev:7 where 'tfd' is a target file descriptor number in decimal form, @@ -1982,6 +1994,8 @@ For inotify files the format is the following:: pos: 0 flags: 02000000 + mnt_id: 9 + ino: 63107 inotify wd:3 ino:9e7e sdev:800013 mask:800afce ignored_mask:0 fhandle-bytes:8 fhandle-type:1 f_handle:7e9e0000640d1b6d where 'wd' is a watch descriptor in decimal form, i.e. a target file @@ -2004,6 +2018,7 @@ For fanotify files the format is:: pos: 0 flags: 02 mnt_id: 9 + ino: 63107 fanotify flags:10 event-flags:0 fanotify mnt_id:12 mflags:40 mask:38 ignored_mask:40000003 fanotify ino:4f969 sdev:800013 mflags:0 mask:3b ignored_mask:40000000 fhandle-bytes:8 fhandle-type:1 f_handle:69f90400c275b5b4 @@ -2028,6 +2043,7 @@ Timerfd files pos: 0 flags: 02 mnt_id: 9 + ino: 63107 clockid: 0 ticks: 0 settime flags: 01 @@ -2042,6 +2058,22 @@ details]. 'it_value' is remaining time until the timer expiration. with TIMER_ABSTIME option which will be shown in 'settime flags', but 'it_value' still exhibits timer's remaining time. +DMA Buffer files +~~~~~~~~~~~~~~~~ + +:: + + pos: 0 + flags: 04002 + mnt_id: 9 + ino: 63107 + size: 32768 + count: 2 + exp_name: system-heap + +where 'size' is the size of the DMA buffer in bytes. 'count' is the file count of +the DMA buffer file. 'exp_name' is the name of the DMA buffer exporter. + 3.9 /proc//map_files - Information about memory mapped files --------------------------------------------------------------------- This directory contains symbolic links which represent memory mapped files diff --git a/Documentation/vm/hmm.rst b/Documentation/vm/hmm.rst index 09e28507f5b2..a14c2938e7af 100644 --- a/Documentation/vm/hmm.rst +++ b/Documentation/vm/hmm.rst @@ -332,7 +332,7 @@ between device driver specific code and shared common code: walks to fill in the ``args->src`` array with PFNs to be migrated. The ``invalidate_range_start()`` callback is passed a ``struct mmu_notifier_range`` with the ``event`` field set to - ``MMU_NOTIFY_MIGRATE`` and the ``migrate_pgmap_owner`` field set to + ``MMU_NOTIFY_MIGRATE`` and the ``owner`` field set to the ``args->pgmap_owner`` field passed to migrate_vma_setup(). This is allows the device driver to skip the invalidation callback and only invalidate device private MMU mappings that are actually migrating. @@ -405,6 +405,23 @@ between device driver specific code and shared common code: The lock can now be released. +Exclusive access memory +======================= + +Some devices have features such as atomic PTE bits that can be used to implement +atomic access to system memory. To support atomic operations to a shared virtual +memory page such a device needs access to that page which is exclusive of any +userspace access from the CPU. The ``make_device_exclusive_range()`` function +can be used to make a memory range inaccessible from userspace. + +This replaces all mappings for pages in the given range with special swap +entries. Any attempt to access the swap entry results in a fault which is +resovled by replacing the entry with the original mapping. A driver gets +notified that the mapping has been changed by MMU notifiers, after which point +it will no longer have exclusive access to the page. Exclusive access is +guranteed to last until the driver drops the page lock and page reference, at +which point any CPU faults on the page may proceed as described. + Memory cgroup (memcg) and rss accounting ======================================== diff --git a/Documentation/vm/unevictable-lru.rst b/Documentation/vm/unevictable-lru.rst index 0e1490524f53..eae3af17f2d9 100644 --- a/Documentation/vm/unevictable-lru.rst +++ b/Documentation/vm/unevictable-lru.rst @@ -389,14 +389,14 @@ mlocked, munlock_vma_page() updates that zone statistics for the number of mlocked pages. Note, however, that at this point we haven't checked whether the page is mapped by other VM_LOCKED VMAs. -We can't call try_to_munlock(), the function that walks the reverse map to +We can't call page_mlock(), the function that walks the reverse map to check for other VM_LOCKED VMAs, without first isolating the page from the LRU. -try_to_munlock() is a variant of try_to_unmap() and thus requires that the page +page_mlock() is a variant of try_to_unmap() and thus requires that the page not be on an LRU list [more on these below]. However, the call to -isolate_lru_page() could fail, in which case we couldn't try_to_munlock(). So, +isolate_lru_page() could fail, in which case we can't call page_mlock(). So, we go ahead and clear PG_mlocked up front, as this might be the only chance we -have. If we can successfully isolate the page, we go ahead and -try_to_munlock(), which will restore the PG_mlocked flag and update the zone +have. If we can successfully isolate the page, we go ahead and call +page_mlock(), which will restore the PG_mlocked flag and update the zone page statistics if it finds another VMA holding the page mlocked. If we fail to isolate the page, we'll have left a potentially mlocked page on the LRU. This is fine, because we'll catch it later if and if vmscan tries to reclaim @@ -545,31 +545,24 @@ munlock or munmap system calls, mm teardown (munlock_vma_pages_all), reclaim, holepunching, and truncation of file pages and their anonymous COWed pages. -try_to_munlock() Reverse Map Scan +page_mlock() Reverse Map Scan --------------------------------- -.. warning:: - [!] TODO/FIXME: a better name might be page_mlocked() - analogous to the - page_referenced() reverse map walker. - When munlock_vma_page() [see section :ref:`munlock()/munlockall() System Call Handling ` above] tries to munlock a page, it needs to determine whether or not the page is mapped by any VM_LOCKED VMA without actually attempting to unmap all PTEs from the page. For this purpose, the unevictable/mlock infrastructure -introduced a variant of try_to_unmap() called try_to_munlock(). +introduced a variant of try_to_unmap() called page_mlock(). -try_to_munlock() calls the same functions as try_to_unmap() for anonymous and -mapped file and KSM pages with a flag argument specifying unlock versus unmap -processing. Again, these functions walk the respective reverse maps looking -for VM_LOCKED VMAs. When such a VMA is found, as in the try_to_unmap() case, -the functions mlock the page via mlock_vma_page() and return SWAP_MLOCK. This -undoes the pre-clearing of the page's PG_mlocked done by munlock_vma_page. +page_mlock() walks the respective reverse maps looking for VM_LOCKED VMAs. When +such a VMA is found the page is mlocked via mlock_vma_page(). This undoes the +pre-clearing of the page's PG_mlocked done by munlock_vma_page. -Note that try_to_munlock()'s reverse map walk must visit every VMA in a page's +Note that page_mlock()'s reverse map walk must visit every VMA in a page's reverse map to determine that a page is NOT mapped into any VM_LOCKED VMA. However, the scan can terminate when it encounters a VM_LOCKED VMA. -Although try_to_munlock() might be called a great many times when munlocking a +Although page_mlock() might be called a great many times when munlocking a large region or tearing down a large address space that has been mlocked via mlockall(), overall this is a fairly rare event. @@ -602,7 +595,7 @@ inactive lists to the appropriate node's unevictable list. shrink_inactive_list() should only see SHM_LOCK'd pages that became SHM_LOCK'd after shrink_active_list() had moved them to the inactive list, or pages mapped into VM_LOCKED VMAs that munlock_vma_page() couldn't isolate from the LRU to -recheck via try_to_munlock(). shrink_inactive_list() won't notice the latter, +recheck via page_mlock(). shrink_inactive_list() won't notice the latter, but will pass on to shrink_page_list(). shrink_page_list() again culls obviously unevictable pages that it could diff --git a/MAINTAINERS b/MAINTAINERS index e5891bbf5443..0d9d8fbd9e92 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -7704,6 +7704,14 @@ L: linux-input@vger.kernel.org S: Maintained F: drivers/input/touchscreen/resistive-adc-touch.c +GENERIC STRING LIBRARY +R: Andy Shevchenko +S: Maintained +F: lib/string.c +F: lib/string_helpers.c +F: lib/test_string.c +F: lib/test-string_helpers.c + GENERIC UIO DRIVER FOR PCI DEVICES M: "Michael S. Tsirkin" L: kvm@vger.kernel.org @@ -11900,6 +11908,7 @@ F: include/linux/mmzone.h F: include/linux/pagewalk.h F: include/linux/vmalloc.h F: mm/ +F: tools/testing/selftests/vm/ MEMORY TECHNOLOGY DEVICES (MTD) M: Miquel Raynal @@ -20307,7 +20316,6 @@ M: Seth Jennings M: Dan Streetman L: linux-mm@kvack.org S: Maintained -F: include/linux/zbud.h F: mm/zbud.c ZD1211RW WIRELESS DRIVER diff --git a/arch/alpha/Kconfig b/arch/alpha/Kconfig index 8954216b9956..77d3280dc678 100644 --- a/arch/alpha/Kconfig +++ b/arch/alpha/Kconfig @@ -40,6 +40,7 @@ config ALPHA select MMU_GATHER_NO_RANGE select SET_FS select SPARSEMEM_EXTREME if SPARSEMEM + select ZONE_DMA help The Alpha is a 64-bit general-purpose processor designed and marketed by the Digital Equipment Corporation of blessed memory, @@ -65,10 +66,6 @@ config GENERIC_CALIBRATE_DELAY bool default y -config ZONE_DMA - bool - default y - config GENERIC_ISA_DMA bool default y diff --git a/arch/alpha/include/asm/pgalloc.h b/arch/alpha/include/asm/pgalloc.h index 9c6a24fe493d..68be7adbfe58 100644 --- a/arch/alpha/include/asm/pgalloc.h +++ b/arch/alpha/include/asm/pgalloc.h @@ -18,7 +18,6 @@ pmd_populate(struct mm_struct *mm, pmd_t *pmd, pgtable_t pte) { pmd_set(pmd, (pte_t *)(page_to_pa(pte) + PAGE_OFFSET)); } -#define pmd_pgtable(pmd) pmd_page(pmd) static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd, pte_t *pte) diff --git a/arch/alpha/include/asm/pgtable.h b/arch/alpha/include/asm/pgtable.h index e1757b7cfe3d..ff690846465e 100644 --- a/arch/alpha/include/asm/pgtable.h +++ b/arch/alpha/include/asm/pgtable.h @@ -46,7 +46,6 @@ struct vm_area_struct; #define PTRS_PER_PMD (1UL << (PAGE_SHIFT-3)) #define PTRS_PER_PGD (1UL << (PAGE_SHIFT-3)) #define USER_PTRS_PER_PGD (TASK_SIZE / PGDIR_SIZE) -#define FIRST_USER_ADDRESS 0UL /* Number of pointers that fit on a page: this will go away. */ #define PTRS_PER_PAGE (1UL << (PAGE_SHIFT-3)) diff --git a/arch/alpha/include/uapi/asm/mman.h b/arch/alpha/include/uapi/asm/mman.h index a18ec7f63888..56b4ee5a6c9e 100644 --- a/arch/alpha/include/uapi/asm/mman.h +++ b/arch/alpha/include/uapi/asm/mman.h @@ -71,6 +71,9 @@ #define MADV_COLD 20 /* deactivate these pages */ #define MADV_PAGEOUT 21 /* reclaim these pages */ +#define MADV_POPULATE_READ 22 /* populate (prefault) page tables readable */ +#define MADV_POPULATE_WRITE 23 /* populate (prefault) page tables writable */ + /* compatibility flags */ #define MAP_FILE 0 diff --git a/arch/alpha/kernel/setup.c b/arch/alpha/kernel/setup.c index 5f6858e9dc28..7d56c217b235 100644 --- a/arch/alpha/kernel/setup.c +++ b/arch/alpha/kernel/setup.c @@ -28,6 +28,7 @@ #include #include #include +#include #include #include #include @@ -46,7 +47,6 @@ #include #include -extern struct atomic_notifier_head panic_notifier_list; static int alpha_panic_event(struct notifier_block *, unsigned long, void *); static struct notifier_block alpha_panic_block = { alpha_panic_event, diff --git a/arch/arc/include/asm/pgalloc.h b/arch/arc/include/asm/pgalloc.h index 6147db925248..a32ca3104ced 100644 --- a/arch/arc/include/asm/pgalloc.h +++ b/arch/arc/include/asm/pgalloc.h @@ -129,6 +129,4 @@ static inline void pte_free(struct mm_struct *mm, pgtable_t ptep) #define __pte_free_tlb(tlb, pte, addr) pte_free((tlb)->mm, pte) -#define pmd_pgtable(pmd) ((pgtable_t) pmd_page_vaddr(pmd)) - #endif /* _ASM_ARC_PGALLOC_H */ diff --git a/arch/arc/include/asm/pgtable.h b/arch/arc/include/asm/pgtable.h index 5878846f00cf..320cc0ae8a08 100644 --- a/arch/arc/include/asm/pgtable.h +++ b/arch/arc/include/asm/pgtable.h @@ -222,12 +222,6 @@ */ #define USER_PTRS_PER_PGD (TASK_SIZE / PGDIR_SIZE) -/* - * No special requirements for lowest virtual address we permit any user space - * mapping to be mapped at. - */ -#define FIRST_USER_ADDRESS 0UL - /**************************************************************** * Bucket load of VM Helpers @@ -356,6 +350,8 @@ void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, #define kern_addr_valid(addr) (1) +#define pmd_pgtable(pmd) ((pgtable_t) pmd_page_vaddr(pmd)) + /* * remap a physical page `pfn' of size `size' with page protection `prot' * into virtual address `from' diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 809317b5a6c6..06b6187b67af 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -218,9 +218,6 @@ config GENERIC_CALIBRATE_DELAY config ARCH_MAY_HAVE_PC_FDC bool -config ZONE_DMA - bool - config ARCH_SUPPORTS_UPROBES def_bool y diff --git a/arch/arm/include/asm/pgalloc.h b/arch/arm/include/asm/pgalloc.h index fdee1f04f4f3..a17f01235c29 100644 --- a/arch/arm/include/asm/pgalloc.h +++ b/arch/arm/include/asm/pgalloc.h @@ -143,7 +143,6 @@ pmd_populate(struct mm_struct *mm, pmd_t *pmdp, pgtable_t ptep) __pmd_populate(pmdp, page_to_phys(ptep), prot); } -#define pmd_pgtable(pmd) pmd_page(pmd) #endif /* CONFIG_MMU */ diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index be9083882f97..e07e7de9ac49 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -42,6 +42,7 @@ config ARM64 select ARCH_HAS_SYSCALL_WRAPPER select ARCH_HAS_TEARDOWN_DMA_OPS if IOMMU_SUPPORT select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST + select ARCH_HAS_ZONE_DMA_SET if EXPERT select ARCH_HAVE_ELF_PROT select ARCH_HAVE_NMI_SAFE_CMPXCHG select ARCH_INLINE_READ_LOCK if !PREEMPTION @@ -155,7 +156,6 @@ config ARM64 select HAVE_ARCH_KGDB select HAVE_ARCH_MMAP_RND_BITS select HAVE_ARCH_MMAP_RND_COMPAT_BITS if COMPAT - select HAVE_ARCH_PFN_VALID select HAVE_ARCH_PREL32_RELOCATIONS select HAVE_ARCH_RANDOMIZE_KSTACK_OFFSET select HAVE_ARCH_SECCOMP_FILTER @@ -308,14 +308,6 @@ config GENERIC_CSUM config GENERIC_CALIBRATE_DELAY def_bool y -config ZONE_DMA - bool "Support DMA zone" if EXPERT - default y - -config ZONE_DMA32 - bool "Support DMA32 zone" if EXPERT - default y - config ARCH_MHP_MEMMAP_ON_MEMORY_ENABLE def_bool y @@ -1053,9 +1045,6 @@ config NEED_PER_CPU_EMBED_FIRST_CHUNK def_bool y depends on NUMA -config HOLES_IN_ZONE - def_bool y - source "kernel/Kconfig.hz" config ARCH_SPARSEMEM_ENABLE diff --git a/arch/arm64/include/asm/hugetlb.h b/arch/arm64/include/asm/hugetlb.h index 5abf91e3494c..1242f71937f8 100644 --- a/arch/arm64/include/asm/hugetlb.h +++ b/arch/arm64/include/asm/hugetlb.h @@ -23,8 +23,7 @@ static inline void arch_clear_hugepage_flags(struct page *page) } #define arch_clear_hugepage_flags arch_clear_hugepage_flags -extern pte_t arch_make_huge_pte(pte_t entry, struct vm_area_struct *vma, - struct page *page, int writable); +pte_t arch_make_huge_pte(pte_t entry, unsigned int shift, vm_flags_t flags); #define arch_make_huge_pte arch_make_huge_pte #define __HAVE_ARCH_HUGE_SET_HUGE_PTE_AT extern void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h index 1a35a4473598..824a3655dd93 100644 --- a/arch/arm64/include/asm/memory.h +++ b/arch/arm64/include/asm/memory.h @@ -351,7 +351,7 @@ static inline void *phys_to_virt(phys_addr_t x) #define virt_addr_valid(addr) ({ \ __typeof__(addr) __addr = __tag_reset(addr); \ - __is_lm_address(__addr) && pfn_valid(virt_to_pfn(__addr)); \ + __is_lm_address(__addr) && pfn_is_map_memory(virt_to_pfn(__addr)); \ }) void dump_mem_limit(void); diff --git a/arch/arm64/include/asm/page.h b/arch/arm64/include/asm/page.h index ed1b9dcf12b2..993a27ea6f54 100644 --- a/arch/arm64/include/asm/page.h +++ b/arch/arm64/include/asm/page.h @@ -41,7 +41,7 @@ void tag_clear_highpage(struct page *to); typedef struct page *pgtable_t; -extern int pfn_valid(unsigned long); +int pfn_is_map_memory(unsigned long pfn); #include diff --git a/arch/arm64/include/asm/pgalloc.h b/arch/arm64/include/asm/pgalloc.h index 31fbab3d6f99..8433a2058eb1 100644 --- a/arch/arm64/include/asm/pgalloc.h +++ b/arch/arm64/include/asm/pgalloc.h @@ -86,6 +86,5 @@ pmd_populate(struct mm_struct *mm, pmd_t *pmdp, pgtable_t ptep) VM_BUG_ON(mm == &init_mm); __pmd_populate(pmdp, page_to_phys(ptep), PMD_TYPE_TABLE | PMD_TABLE_PXN); } -#define pmd_pgtable(pmd) pmd_page(pmd) #endif diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index c0ba8cdfa10a..508c7ffad515 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -26,8 +26,6 @@ #define vmemmap ((struct page *)VMEMMAP_START - (memstart_addr >> PAGE_SHIFT)) -#define FIRST_USER_ADDRESS 0UL - #ifndef __ASSEMBLY__ #include diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c index 8ed66142b088..880f40bae60e 100644 --- a/arch/arm64/kernel/setup.c +++ b/arch/arm64/kernel/setup.c @@ -23,6 +23,7 @@ #include #include #include +#include #include #include #include diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c index f23dfa06433b..3155c9e778f0 100644 --- a/arch/arm64/kvm/mmu.c +++ b/arch/arm64/kvm/mmu.c @@ -85,7 +85,7 @@ void kvm_flush_remote_tlbs(struct kvm *kvm) static bool kvm_is_device_pfn(unsigned long pfn) { - return !pfn_valid(pfn); + return !pfn_is_map_memory(pfn); } static void *stage2_memcache_zalloc_page(void *arg) diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c index 58987a98e179..23505fc35324 100644 --- a/arch/arm64/mm/hugetlbpage.c +++ b/arch/arm64/mm/hugetlbpage.c @@ -339,10 +339,9 @@ pte_t *huge_pte_offset(struct mm_struct *mm, return NULL; } -pte_t arch_make_huge_pte(pte_t entry, struct vm_area_struct *vma, - struct page *page, int writable) +pte_t arch_make_huge_pte(pte_t entry, unsigned int shift, vm_flags_t flags) { - size_t pagesize = huge_page_size(hstate_vma(vma)); + size_t pagesize = 1UL << shift; if (pagesize == CONT_PTE_SIZE) { entry = pte_mkcont(entry); diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index 6e1ca044ca90..8490ed2917ff 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -219,42 +219,17 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max) free_area_init(max_zone_pfns); } -int pfn_valid(unsigned long pfn) +int pfn_is_map_memory(unsigned long pfn) { phys_addr_t addr = PFN_PHYS(pfn); - struct mem_section *ms; - /* - * Ensure the upper PAGE_SHIFT bits are clear in the - * pfn. Else it might lead to false positives when - * some of the upper bits are set, but the lower bits - * match a valid pfn. - */ + /* avoid false positives for bogus PFNs, see comment in pfn_valid() */ if (PHYS_PFN(addr) != pfn) return 0; - if (pfn_to_section_nr(pfn) >= NR_MEM_SECTIONS) - return 0; - - ms = __pfn_to_section(pfn); - if (!valid_section(ms)) - return 0; - - /* - * ZONE_DEVICE memory does not have the memblock entries. - * memblock_is_map_memory() check for ZONE_DEVICE based - * addresses will always fail. Even the normal hotplugged - * memory will never have MEMBLOCK_NOMAP flag set in their - * memblock entries. Skip memblock search for all non early - * memory sections covering all of hotplug memory including - * both normal and ZONE_DEVICE based. - */ - if (!early_section(ms)) - return pfn_section_valid(ms, pfn); - return memblock_is_map_memory(addr); } -EXPORT_SYMBOL(pfn_valid); +EXPORT_SYMBOL(pfn_is_map_memory); static phys_addr_t memory_limit = PHYS_ADDR_MAX; diff --git a/arch/arm64/mm/ioremap.c b/arch/arm64/mm/ioremap.c index b5e83c46b23e..b7c81dacabf0 100644 --- a/arch/arm64/mm/ioremap.c +++ b/arch/arm64/mm/ioremap.c @@ -43,7 +43,7 @@ static void __iomem *__ioremap_caller(phys_addr_t phys_addr, size_t size, /* * Don't allow RAM to be mapped. */ - if (WARN_ON(pfn_valid(__phys_to_pfn(phys_addr)))) + if (WARN_ON(pfn_is_map_memory(__phys_to_pfn(phys_addr)))) return NULL; area = get_vm_area_caller(size, VM_IOREMAP, caller); @@ -84,7 +84,7 @@ EXPORT_SYMBOL(iounmap); void __iomem *ioremap_cache(phys_addr_t phys_addr, size_t size) { /* For normal memory we already have a cacheable mapping. */ - if (pfn_valid(__phys_to_pfn(phys_addr))) + if (pfn_is_map_memory(__phys_to_pfn(phys_addr))) return (void __iomem *)__phys_to_virt(phys_addr); return __ioremap_caller(phys_addr, size, __pgprot(PROT_NORMAL), diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 0b28cc218091..595fde9a47dd 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -82,7 +82,7 @@ void set_swapper_pgd(pgd_t *pgdp, pgd_t pgd) pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, unsigned long size, pgprot_t vma_prot) { - if (!pfn_valid(pfn)) + if (!pfn_is_map_memory(pfn)) return pgprot_noncached(vma_prot); else if (file->f_flags & O_SYNC) return pgprot_writecombine(vma_prot); @@ -1339,6 +1339,7 @@ void *__init fixmap_remap_fdt(phys_addr_t dt_phys, int *size, pgprot_t prot) return dt_virt; } +#if CONFIG_PGTABLE_LEVELS > 3 int pud_set_huge(pud_t *pudp, phys_addr_t phys, pgprot_t prot) { pud_t new_pud = pfn_pud(__phys_to_pfn(phys), mk_pud_sect_prot(prot)); @@ -1353,6 +1354,16 @@ int pud_set_huge(pud_t *pudp, phys_addr_t phys, pgprot_t prot) return 1; } +int pud_clear_huge(pud_t *pudp) +{ + if (!pud_sect(READ_ONCE(*pudp))) + return 0; + pud_clear(pudp); + return 1; +} +#endif + +#if CONFIG_PGTABLE_LEVELS > 2 int pmd_set_huge(pmd_t *pmdp, phys_addr_t phys, pgprot_t prot) { pmd_t new_pmd = pfn_pmd(__phys_to_pfn(phys), mk_pmd_sect_prot(prot)); @@ -1367,14 +1378,6 @@ int pmd_set_huge(pmd_t *pmdp, phys_addr_t phys, pgprot_t prot) return 1; } -int pud_clear_huge(pud_t *pudp) -{ - if (!pud_sect(READ_ONCE(*pudp))) - return 0; - pud_clear(pudp); - return 1; -} - int pmd_clear_huge(pmd_t *pmdp) { if (!pmd_sect(READ_ONCE(*pmdp))) @@ -1382,6 +1385,7 @@ int pmd_clear_huge(pmd_t *pmdp) pmd_clear(pmdp); return 1; } +#endif int pmd_free_pte_page(pmd_t *pmdp, unsigned long addr) { diff --git a/arch/csky/include/asm/pgalloc.h b/arch/csky/include/asm/pgalloc.h index cd211aabbefd..bbbd0698b397 100644 --- a/arch/csky/include/asm/pgalloc.h +++ b/arch/csky/include/asm/pgalloc.h @@ -22,8 +22,6 @@ static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd, set_pmd(pmd, __pmd(__pa(page_address(pte)))); } -#define pmd_pgtable(pmd) pmd_page(pmd) - extern void pgd_init(unsigned long *p); static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm) diff --git a/arch/csky/include/asm/pgtable.h b/arch/csky/include/asm/pgtable.h index 0d60367b6bfa..151607ed5158 100644 --- a/arch/csky/include/asm/pgtable.h +++ b/arch/csky/include/asm/pgtable.h @@ -14,7 +14,6 @@ #define PGDIR_MASK (~(PGDIR_SIZE-1)) #define USER_PTRS_PER_PGD (PAGE_OFFSET/PGDIR_SIZE) -#define FIRST_USER_ADDRESS 0UL /* * C-SKY is two-level paging structure: diff --git a/arch/hexagon/include/asm/pgtable.h b/arch/hexagon/include/asm/pgtable.h index dbb22b80b8c4..18cd6ea9ab23 100644 --- a/arch/hexagon/include/asm/pgtable.h +++ b/arch/hexagon/include/asm/pgtable.h @@ -155,9 +155,6 @@ extern unsigned long _dflt_cache_att; extern pgd_t swapper_pg_dir[PTRS_PER_PGD]; /* located in head.S */ -/* Seems to be zero even in architectures where the zero page is firewalled? */ -#define FIRST_USER_ADDRESS 0UL - /* HUGETLB not working currently */ #ifdef CONFIG_HUGETLB_PAGE #define pte_mkhuge(pte) __pte((pte_val(pte) & ~0x3) | HVM_HUGEPAGE_SIZE) @@ -242,7 +239,6 @@ static inline int pmd_bad(pmd_t pmd) * pmd_page - converts a PMD entry to a page pointer */ #define pmd_page(pmd) (pfn_to_page(pmd_val(pmd) >> PAGE_SHIFT)) -#define pmd_pgtable(pmd) pmd_page(pmd) /** * pte_none - check if pte is mapped diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig index da22a35e6f03..cf425c2c63af 100644 --- a/arch/ia64/Kconfig +++ b/arch/ia64/Kconfig @@ -60,6 +60,7 @@ config IA64 select NUMA if !FLATMEM select PCI_MSI_ARCH_FALLBACKS if PCI_MSI select SET_FS + select ZONE_DMA32 default y help The Itanium Processor Family is Intel's 64-bit successor to @@ -72,9 +73,6 @@ config 64BIT select ATA_NONSTANDARD if ATA default y -config ZONE_DMA32 - def_bool y - config MMU bool default y @@ -308,9 +306,6 @@ config NODES_SHIFT MAX_NUMNODES will be 2^(This value). If in doubt, use the default. -config HOLES_IN_ZONE - bool - config HAVE_ARCH_NODEDATA_EXTENSION def_bool y depends on NUMA diff --git a/arch/ia64/include/asm/pal.h b/arch/ia64/include/asm/pal.h index 5c51fceedaf9..e6b652f9e45e 100644 --- a/arch/ia64/include/asm/pal.h +++ b/arch/ia64/include/asm/pal.h @@ -99,6 +99,7 @@ #include #include +#include /* * Data types needed to pass information into PAL procedures and diff --git a/arch/ia64/include/asm/pgalloc.h b/arch/ia64/include/asm/pgalloc.h index 9601cfe83c94..0fb2b6291d58 100644 --- a/arch/ia64/include/asm/pgalloc.h +++ b/arch/ia64/include/asm/pgalloc.h @@ -52,7 +52,6 @@ pmd_populate(struct mm_struct *mm, pmd_t * pmd_entry, pgtable_t pte) { pmd_val(*pmd_entry) = page_to_phys(pte); } -#define pmd_pgtable(pmd) pmd_page(pmd) static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t * pmd_entry, pte_t * pte) diff --git a/arch/ia64/include/asm/pgtable.h b/arch/ia64/include/asm/pgtable.h index d765fd948fae..3f5dbbd8b9d8 100644 --- a/arch/ia64/include/asm/pgtable.h +++ b/arch/ia64/include/asm/pgtable.h @@ -128,7 +128,6 @@ #define PTRS_PER_PGD_SHIFT PTRS_PER_PTD_SHIFT #define PTRS_PER_PGD (1UL << PTRS_PER_PGD_SHIFT) #define USER_PTRS_PER_PGD (5*PTRS_PER_PGD/8) /* regions 0-4 are user regions */ -#define FIRST_USER_ADDRESS 0UL /* * All the normal masks have the "page accessed" bits on, as any time diff --git a/arch/m68k/Kconfig b/arch/m68k/Kconfig index 372e4e69c43a..05a729c6ad7f 100644 --- a/arch/m68k/Kconfig +++ b/arch/m68k/Kconfig @@ -34,6 +34,7 @@ config M68K select SET_FS select UACCESS_MEMCPY if !MMU select VIRT_TO_BUS + select ZONE_DMA config CPU_BIG_ENDIAN def_bool y @@ -62,10 +63,6 @@ config TIME_LOW_RES config NO_IOPORT_MAP def_bool y -config ZONE_DMA - bool - default y - config HZ int default 1000 if CLEOPATRA diff --git a/arch/m68k/include/asm/mcf_pgalloc.h b/arch/m68k/include/asm/mcf_pgalloc.h index bc1228e00518..5c2c0a864524 100644 --- a/arch/m68k/include/asm/mcf_pgalloc.h +++ b/arch/m68k/include/asm/mcf_pgalloc.h @@ -32,8 +32,6 @@ extern inline pmd_t *pmd_alloc_kernel(pgd_t *pgd, unsigned long address) #define pmd_populate_kernel pmd_populate -#define pmd_pgtable(pmd) pfn_to_virt(pmd_val(pmd) >> PAGE_SHIFT) - static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pgtable, unsigned long address) { diff --git a/arch/m68k/include/asm/mcf_pgtable.h b/arch/m68k/include/asm/mcf_pgtable.h index 8d4ec05996c5..6f2b87d7a50d 100644 --- a/arch/m68k/include/asm/mcf_pgtable.h +++ b/arch/m68k/include/asm/mcf_pgtable.h @@ -150,6 +150,8 @@ #ifndef __ASSEMBLY__ +#define pmd_pgtable(pmd) pfn_to_virt(pmd_val(pmd) >> PAGE_SHIFT) + /* * Conversion functions: convert a page and protection to a page entry, * and a page entry and page directory to the page they refer to. diff --git a/arch/m68k/include/asm/motorola_pgalloc.h b/arch/m68k/include/asm/motorola_pgalloc.h index b4fc3b4f6bb3..74a817d9387f 100644 --- a/arch/m68k/include/asm/motorola_pgalloc.h +++ b/arch/m68k/include/asm/motorola_pgalloc.h @@ -88,7 +88,6 @@ static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd, pgtable_t page { pmd_set(pmd, page); } -#define pmd_pgtable(pmd) ((pgtable_t)pmd_page_vaddr(pmd)) static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd) { diff --git a/arch/m68k/include/asm/motorola_pgtable.h b/arch/m68k/include/asm/motorola_pgtable.h index 8076467eff4b..a2908164ee6f 100644 --- a/arch/m68k/include/asm/motorola_pgtable.h +++ b/arch/m68k/include/asm/motorola_pgtable.h @@ -105,6 +105,8 @@ extern unsigned long mm_cachebits; #define __S110 PAGE_SHARED_C #define __S111 PAGE_SHARED_C +#define pmd_pgtable(pmd) ((pgtable_t)pmd_page_vaddr(pmd)) + /* * Conversion functions: convert a page and protection to a page entry, * and a page entry and page directory to the page they refer to. diff --git a/arch/m68k/include/asm/pgtable_mm.h b/arch/m68k/include/asm/pgtable_mm.h index aca22c2c1ee2..143ba7de9bda 100644 --- a/arch/m68k/include/asm/pgtable_mm.h +++ b/arch/m68k/include/asm/pgtable_mm.h @@ -72,7 +72,6 @@ #define PTRS_PER_PGD 128 #endif #define USER_PTRS_PER_PGD (TASK_SIZE/PGDIR_SIZE) -#define FIRST_USER_ADDRESS 0UL /* Virtual address region for use by kernel_map() */ #ifdef CONFIG_SUN3 diff --git a/arch/m68k/include/asm/sun3_pgalloc.h b/arch/m68k/include/asm/sun3_pgalloc.h index 000f64869b91..198036aff519 100644 --- a/arch/m68k/include/asm/sun3_pgalloc.h +++ b/arch/m68k/include/asm/sun3_pgalloc.h @@ -32,7 +32,6 @@ static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd, pgtable_t page { pmd_val(*pmd) = __pa((unsigned long)page_address(page)); } -#define pmd_pgtable(pmd) pmd_page(pmd) /* * allocating and freeing a pmd is trivial: the 1-entry pmd is diff --git a/arch/microblaze/Kconfig b/arch/microblaze/Kconfig index 0660f47012bc..14a67a42fcae 100644 --- a/arch/microblaze/Kconfig +++ b/arch/microblaze/Kconfig @@ -43,6 +43,7 @@ config MICROBLAZE select MMU_GATHER_NO_RANGE select SPARSE_IRQ select SET_FS + select ZONE_DMA # Endianness selection choice @@ -60,9 +61,6 @@ config CPU_LITTLE_ENDIAN endchoice -config ZONE_DMA - def_bool y - config ARCH_HAS_ILOG2_U32 def_bool n diff --git a/arch/microblaze/include/asm/pgalloc.h b/arch/microblaze/include/asm/pgalloc.h index d56b9f670ad1..6c33b05f730f 100644 --- a/arch/microblaze/include/asm/pgalloc.h +++ b/arch/microblaze/include/asm/pgalloc.h @@ -28,8 +28,6 @@ static inline pgd_t *get_pgd(void) #define pgd_alloc(mm) get_pgd() -#define pmd_pgtable(pmd) pmd_page(pmd) - extern pte_t *pte_alloc_one_kernel(struct mm_struct *mm); #define __pte_free_tlb(tlb, pte, addr) pte_free((tlb)->mm, (pte)) diff --git a/arch/microblaze/include/asm/pgtable.h b/arch/microblaze/include/asm/pgtable.h index 9ae8d2c17dd5..71cd547655d9 100644 --- a/arch/microblaze/include/asm/pgtable.h +++ b/arch/microblaze/include/asm/pgtable.h @@ -25,8 +25,6 @@ extern int mem_init_done; #include #include -#define FIRST_USER_ADDRESS 0UL - extern unsigned long va_to_phys(unsigned long address); extern pte_t *va_to_pte(unsigned long address); diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index e039e7d542c4..cee6087cd686 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -3274,13 +3274,6 @@ config I8253 select CLKSRC_I8253 select CLKEVT_I8253 select MIPS_EXTERNAL_TIMER - -config ZONE_DMA - bool - -config ZONE_DMA32 - bool - endmenu config TRAD_SIGNALS diff --git a/arch/mips/include/asm/pgalloc.h b/arch/mips/include/asm/pgalloc.h index d0cf997b4ba8..4b2567d6b2df 100644 --- a/arch/mips/include/asm/pgalloc.h +++ b/arch/mips/include/asm/pgalloc.h @@ -28,7 +28,6 @@ static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd, { set_pmd(pmd, __pmd((unsigned long)page_address(pte))); } -#define pmd_pgtable(pmd) pmd_page(pmd) /* * Initialize a new pmd table with invalid pointers. diff --git a/arch/mips/include/asm/pgtable-32.h b/arch/mips/include/asm/pgtable-32.h index 6c0532d7b211..95df9c293d8d 100644 --- a/arch/mips/include/asm/pgtable-32.h +++ b/arch/mips/include/asm/pgtable-32.h @@ -93,7 +93,6 @@ extern int add_temporary_entry(unsigned long entrylo0, unsigned long entrylo1, #endif #define USER_PTRS_PER_PGD (0x80000000UL/PGDIR_SIZE) -#define FIRST_USER_ADDRESS 0UL #define VMALLOC_START MAP_BASE diff --git a/arch/mips/include/asm/pgtable-64.h b/arch/mips/include/asm/pgtable-64.h index 1e7d6ce9d8d6..046465906c82 100644 --- a/arch/mips/include/asm/pgtable-64.h +++ b/arch/mips/include/asm/pgtable-64.h @@ -137,7 +137,6 @@ #define PTRS_PER_PTE ((PAGE_SIZE << PTE_ORDER) / sizeof(pte_t)) #define USER_PTRS_PER_PGD ((TASK_SIZE64 / PGDIR_SIZE)?(TASK_SIZE64 / PGDIR_SIZE):1) -#define FIRST_USER_ADDRESS 0UL /* * TLB refill handlers also map the vmalloc area into xuseg. Avoid diff --git a/arch/mips/include/uapi/asm/mman.h b/arch/mips/include/uapi/asm/mman.h index 57dc2ac4f8bd..40b210c65a5a 100644 --- a/arch/mips/include/uapi/asm/mman.h +++ b/arch/mips/include/uapi/asm/mman.h @@ -98,6 +98,9 @@ #define MADV_COLD 20 /* deactivate these pages */ #define MADV_PAGEOUT 21 /* reclaim these pages */ +#define MADV_POPULATE_READ 22 /* populate (prefault) page tables readable */ +#define MADV_POPULATE_WRITE 23 /* populate (prefault) page tables writable */ + /* compatibility flags */ #define MAP_FILE 0 diff --git a/arch/mips/kernel/relocate.c b/arch/mips/kernel/relocate.c index 499a5357c09f..56b51de2dc51 100644 --- a/arch/mips/kernel/relocate.c +++ b/arch/mips/kernel/relocate.c @@ -18,6 +18,7 @@ #include #include #include +#include #include #include #include diff --git a/arch/mips/sgi-ip22/ip22-reset.c b/arch/mips/sgi-ip22/ip22-reset.c index c374f3ceec38..9028dbbb45dd 100644 --- a/arch/mips/sgi-ip22/ip22-reset.c +++ b/arch/mips/sgi-ip22/ip22-reset.c @@ -12,6 +12,7 @@ #include #include #include +#include #include #include diff --git a/arch/mips/sgi-ip32/ip32-reset.c b/arch/mips/sgi-ip32/ip32-reset.c index 20d8637340be..18d1c115cd53 100644 --- a/arch/mips/sgi-ip32/ip32-reset.c +++ b/arch/mips/sgi-ip32/ip32-reset.c @@ -12,6 +12,7 @@ #include #include #include +#include #include #include #include diff --git a/arch/nds32/include/asm/pgalloc.h b/arch/nds32/include/asm/pgalloc.h index 85c117347c86..a08e1ebca70e 100644 --- a/arch/nds32/include/asm/pgalloc.h +++ b/arch/nds32/include/asm/pgalloc.h @@ -12,11 +12,6 @@ #define __HAVE_ARCH_PTE_ALLOC_ONE #include /* for pte_{alloc,free}_one */ -/* - * Since we have only two-level page tables, these are trivial - */ -#define pmd_pgtable(pmd) pmd_page(pmd) - extern pgd_t *pgd_alloc(struct mm_struct *mm); extern void pgd_free(struct mm_struct *mm, pgd_t * pgd); diff --git a/arch/nios2/include/asm/pgalloc.h b/arch/nios2/include/asm/pgalloc.h index e6600d2a5ae0..3c4ae74d5798 100644 --- a/arch/nios2/include/asm/pgalloc.h +++ b/arch/nios2/include/asm/pgalloc.h @@ -25,7 +25,6 @@ static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd, { set_pmd(pmd, __pmd((unsigned long)page_address(pte))); } -#define pmd_pgtable(pmd) pmd_page(pmd) /* * Initialize a new pmd table with invalid pointers. diff --git a/arch/nios2/include/asm/pgtable.h b/arch/nios2/include/asm/pgtable.h index 2600d76c310c..4a995fa628ee 100644 --- a/arch/nios2/include/asm/pgtable.h +++ b/arch/nios2/include/asm/pgtable.h @@ -24,8 +24,6 @@ #include #include -#define FIRST_USER_ADDRESS 0UL - #define VMALLOC_START CONFIG_NIOS2_KERNEL_MMU_REGION_BASE #define VMALLOC_END (CONFIG_NIOS2_KERNEL_REGION_BASE - 1) diff --git a/arch/openrisc/include/asm/pgalloc.h b/arch/openrisc/include/asm/pgalloc.h index 88820299ecc4..b7b2b8d16fad 100644 --- a/arch/openrisc/include/asm/pgalloc.h +++ b/arch/openrisc/include/asm/pgalloc.h @@ -72,6 +72,4 @@ do { \ tlb_remove_page((tlb), (pte)); \ } while (0) -#define pmd_pgtable(pmd) pmd_page(pmd) - #endif diff --git a/arch/openrisc/include/asm/pgtable.h b/arch/openrisc/include/asm/pgtable.h index 9425bedab4fc..4ac591c9ca33 100644 --- a/arch/openrisc/include/asm/pgtable.h +++ b/arch/openrisc/include/asm/pgtable.h @@ -73,7 +73,6 @@ extern void paging_init(void); */ #define USER_PTRS_PER_PGD (TASK_SIZE/PGDIR_SIZE) -#define FIRST_USER_ADDRESS 0UL /* * Kernels own virtual memory area. diff --git a/arch/parisc/include/asm/pgalloc.h b/arch/parisc/include/asm/pgalloc.h index dda557085311..6a7e98e71f1d 100644 --- a/arch/parisc/include/asm/pgalloc.h +++ b/arch/parisc/include/asm/pgalloc.h @@ -69,6 +69,5 @@ pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd, pte_t *pte) #define pmd_populate(mm, pmd, pte_page) \ pmd_populate_kernel(mm, pmd, page_address(pte_page)) -#define pmd_pgtable(pmd) pmd_page(pmd) #endif diff --git a/arch/parisc/include/asm/pgtable.h b/arch/parisc/include/asm/pgtable.h index 39017210dbf0..7f33c29764cc 100644 --- a/arch/parisc/include/asm/pgtable.h +++ b/arch/parisc/include/asm/pgtable.h @@ -171,8 +171,6 @@ static inline void purge_tlb_entries(struct mm_struct *mm, unsigned long addr) * pgd entries used up by user/kernel: */ -#define FIRST_USER_ADDRESS 0UL - /* NB: The tlb miss handlers make certain assumptions about the order */ /* of the following bits, so be careful (One example, bits 25-31 */ /* are moved together in one instruction). */ diff --git a/arch/parisc/include/uapi/asm/mman.h b/arch/parisc/include/uapi/asm/mman.h index ab78cba446ed..9e3c010c0f61 100644 --- a/arch/parisc/include/uapi/asm/mman.h +++ b/arch/parisc/include/uapi/asm/mman.h @@ -52,6 +52,9 @@ #define MADV_COLD 20 /* deactivate these pages */ #define MADV_PAGEOUT 21 /* reclaim these pages */ +#define MADV_POPULATE_READ 22 /* populate (prefault) page tables readable */ +#define MADV_POPULATE_WRITE 23 /* populate (prefault) page tables writable */ + #define MADV_MERGEABLE 65 /* KSM may merge identical pages */ #define MADV_UNMERGEABLE 66 /* KSM may not merge identical pages */ diff --git a/arch/parisc/kernel/pdc_chassis.c b/arch/parisc/kernel/pdc_chassis.c index 75ae88d13909..da154406d368 100644 --- a/arch/parisc/kernel/pdc_chassis.c +++ b/arch/parisc/kernel/pdc_chassis.c @@ -20,6 +20,7 @@ #include #include #include +#include #include #include #include diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 14b132cf95e2..df46324d5090 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -187,7 +187,7 @@ config PPC select GENERIC_VDSO_TIME_NS select HAVE_ARCH_AUDITSYSCALL select HAVE_ARCH_HUGE_VMALLOC if HAVE_ARCH_HUGE_VMAP - select HAVE_ARCH_HUGE_VMAP if PPC_BOOK3S_64 && PPC_RADIX_MMU + select HAVE_ARCH_HUGE_VMAP if PPC_RADIX_MMU || PPC_8xx select HAVE_ARCH_JUMP_LABEL select HAVE_ARCH_JUMP_LABEL_RELATIVE select HAVE_ARCH_KASAN if PPC32 && PPC_PAGE_SHIFT <= 14 @@ -403,10 +403,6 @@ config PPC_ADV_DEBUG_DAC_RANGE config PPC_DAWR bool -config ZONE_DMA - bool - default y if PPC_BOOK3E_64 - config PGTABLE_LEVELS int default 2 if !PPC64 diff --git a/arch/powerpc/include/asm/book3s/pgtable.h b/arch/powerpc/include/asm/book3s/pgtable.h index 0e1263455d73..ad130e15a126 100644 --- a/arch/powerpc/include/asm/book3s/pgtable.h +++ b/arch/powerpc/include/asm/book3s/pgtable.h @@ -8,7 +8,6 @@ #include #endif -#define FIRST_USER_ADDRESS 0UL #ifndef __ASSEMBLY__ /* Insert a PTE, top-level function is out of line. It uses an inline * low level function in the respective pgtable-* files diff --git a/arch/powerpc/include/asm/nohash/32/hugetlb-8xx.h b/arch/powerpc/include/asm/nohash/32/hugetlb-8xx.h index 39be9aea86db..64b6c608eca4 100644 --- a/arch/powerpc/include/asm/nohash/32/hugetlb-8xx.h +++ b/arch/powerpc/include/asm/nohash/32/hugetlb-8xx.h @@ -66,10 +66,9 @@ static inline void huge_ptep_set_wrprotect(struct mm_struct *mm, } #ifdef CONFIG_PPC_4K_PAGES -static inline pte_t arch_make_huge_pte(pte_t entry, struct vm_area_struct *vma, - struct page *page, int writable) +static inline pte_t arch_make_huge_pte(pte_t entry, unsigned int shift, vm_flags_t flags) { - size_t size = huge_page_size(hstate_vma(vma)); + size_t size = 1UL << shift; if (size == SZ_16K) return __pte(pte_val(entry) & ~_PAGE_HUGE); diff --git a/arch/powerpc/include/asm/nohash/32/mmu-8xx.h b/arch/powerpc/include/asm/nohash/32/mmu-8xx.h index 6e4faa0a9b35..997cec973406 100644 --- a/arch/powerpc/include/asm/nohash/32/mmu-8xx.h +++ b/arch/powerpc/include/asm/nohash/32/mmu-8xx.h @@ -178,6 +178,7 @@ #ifndef __ASSEMBLY__ #include +#include void mmu_pin_tlb(unsigned long top, bool readonly); @@ -225,6 +226,48 @@ static inline unsigned int mmu_psize_to_shift(unsigned int mmu_psize) BUG(); } +static inline bool arch_vmap_try_size(unsigned long addr, unsigned long end, u64 pfn, + unsigned int max_page_shift, unsigned long size) +{ + if (end - addr < size) + return false; + + if ((1UL << max_page_shift) < size) + return false; + + if (!IS_ALIGNED(addr, size)) + return false; + + if (!IS_ALIGNED(PFN_PHYS(pfn), size)) + return false; + + return true; +} + +static inline unsigned long arch_vmap_pte_range_map_size(unsigned long addr, unsigned long end, + u64 pfn, unsigned int max_page_shift) +{ + if (arch_vmap_try_size(addr, end, pfn, max_page_shift, SZ_512K)) + return SZ_512K; + if (PAGE_SIZE == SZ_16K) + return SZ_16K; + if (arch_vmap_try_size(addr, end, pfn, max_page_shift, SZ_16K)) + return SZ_16K; + return PAGE_SIZE; +} +#define arch_vmap_pte_range_map_size arch_vmap_pte_range_map_size + +static inline int arch_vmap_pte_supported_shift(unsigned long size) +{ + if (size >= SZ_512K) + return 19; + else if (size >= SZ_16K) + return 14; + else + return PAGE_SHIFT; +} +#define arch_vmap_pte_supported_shift arch_vmap_pte_supported_shift + /* patch sites */ extern s32 patch__itlbmiss_exit_1, patch__dtlbmiss_exit_1; extern s32 patch__itlbmiss_perf, patch__dtlbmiss_perf; diff --git a/arch/powerpc/include/asm/nohash/32/pgtable.h b/arch/powerpc/include/asm/nohash/32/pgtable.h index 96522f7f0618..f06ae00f2a65 100644 --- a/arch/powerpc/include/asm/nohash/32/pgtable.h +++ b/arch/powerpc/include/asm/nohash/32/pgtable.h @@ -54,7 +54,6 @@ extern int icache_44x_need_flush; #define PGD_MASKED_BITS 0 #define USER_PTRS_PER_PGD (TASK_SIZE / PGDIR_SIZE) -#define FIRST_USER_ADDRESS 0UL #define pte_ERROR(e) \ pr_err("%s:%d: bad pte %llx.\n", __FILE__, __LINE__, \ diff --git a/arch/powerpc/include/asm/nohash/64/pgtable.h b/arch/powerpc/include/asm/nohash/64/pgtable.h index 57cd3892bfe0..53fbfdfac93d 100644 --- a/arch/powerpc/include/asm/nohash/64/pgtable.h +++ b/arch/powerpc/include/asm/nohash/64/pgtable.h @@ -12,8 +12,6 @@ #include #include -#define FIRST_USER_ADDRESS 0UL - /* * Size of EA range mapped by our pagetables. */ diff --git a/arch/powerpc/include/asm/pgalloc.h b/arch/powerpc/include/asm/pgalloc.h index 6dd78a2dc03a..3360cad78ace 100644 --- a/arch/powerpc/include/asm/pgalloc.h +++ b/arch/powerpc/include/asm/pgalloc.h @@ -70,9 +70,4 @@ extern struct kmem_cache *pgtable_cache[]; #include #endif -static inline pgtable_t pmd_pgtable(pmd_t pmd) -{ - return (pgtable_t)pmd_page_vaddr(pmd); -} - #endif /* _ASM_POWERPC_PGALLOC_H */ diff --git a/arch/powerpc/include/asm/pgtable.h b/arch/powerpc/include/asm/pgtable.h index c6a676714f04..5969743719bc 100644 --- a/arch/powerpc/include/asm/pgtable.h +++ b/arch/powerpc/include/asm/pgtable.h @@ -152,6 +152,12 @@ static inline bool p4d_is_leaf(p4d_t p4d) } #endif +#define pmd_pgtable pmd_pgtable +static inline pgtable_t pmd_pgtable(pmd_t pmd) +{ + return (pgtable_t)pmd_page_vaddr(pmd); +} + #ifdef CONFIG_PPC64 #define is_ioremap_addr is_ioremap_addr static inline bool is_ioremap_addr(const void *x) diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index 74a98fff2c2f..046fe21b5c3b 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -9,6 +9,7 @@ #undef DEBUG #include +#include #include #include #include diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype index f998e655b570..7d271de8fcbd 100644 --- a/arch/powerpc/platforms/Kconfig.cputype +++ b/arch/powerpc/platforms/Kconfig.cputype @@ -111,6 +111,7 @@ config PPC_BOOK3E_64 select PPC_FPU # Make it a choice ? select PPC_SMP_MUXED_IPI select PPC_DOORBELL + select ZONE_DMA endchoice diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index 15f9490a7aad..469a70bd8da6 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -104,6 +104,7 @@ config RISCV select SYSCTL_EXCEPTION_TRACE select THREAD_INFO_IN_TASK select UACCESS_MEMCPY if !MMU + select ZONE_DMA32 if 64BIT config ARCH_MMAP_RND_BITS_MIN default 18 if 64BIT @@ -133,10 +134,6 @@ config MMU Select if you want MMU-based virtualised addressing space support by paged memory management. If unsure, say 'Y'. -config ZONE_DMA32 - bool - default y if 64BIT - config VA_BITS int default 32 if 32BIT diff --git a/arch/riscv/include/asm/pgalloc.h b/arch/riscv/include/asm/pgalloc.h index 23b1544e0ca5..0af6933a7100 100644 --- a/arch/riscv/include/asm/pgalloc.h +++ b/arch/riscv/include/asm/pgalloc.h @@ -38,8 +38,6 @@ static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd) } #endif /* __PAGETABLE_PMD_FOLDED */ -#define pmd_pgtable(pmd) pmd_page(pmd) - static inline pgd_t *pgd_alloc(struct mm_struct *mm) { pgd_t *pgd; diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h index 380cd3a7e548..62f3fe7368f3 100644 --- a/arch/riscv/include/asm/pgtable.h +++ b/arch/riscv/include/asm/pgtable.h @@ -536,8 +536,6 @@ void setup_bootmem(void); void paging_init(void); void misc_mem_init(void); -#define FIRST_USER_ADDRESS 0 - /* * ZERO_PAGE is a global shared page that is always zero, * used for zero-mapped memory areas, etc. diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index a49971647f81..c448567b18ca 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -2,9 +2,6 @@ config MMU def_bool y -config ZONE_DMA - def_bool y - config CPU_BIG_ENDIAN def_bool y @@ -62,7 +59,7 @@ config S390 select ARCH_BINFMT_ELF_STATE select ARCH_ENABLE_MEMORY_HOTPLUG if SPARSEMEM select ARCH_ENABLE_MEMORY_HOTREMOVE - select ARCH_ENABLE_SPLIT_PMD_PTLOCK + select ARCH_ENABLE_SPLIT_PMD_PTLOCK if PGTABLE_LEVELS > 2 select ARCH_HAS_DEBUG_VM_PGTABLE select ARCH_HAS_DEBUG_WX select ARCH_HAS_DEVMEM_IS_ALLOWED @@ -211,6 +208,7 @@ config S390 select THREAD_INFO_IN_TASK select TTY select VIRT_CPU_ACCOUNTING + select ZONE_DMA # Note: keep the above list sorted alphabetically config SCHED_OMIT_FRAME_POINTER diff --git a/arch/s390/include/asm/pgalloc.h b/arch/s390/include/asm/pgalloc.h index 6b187cd72251..f14a555eff74 100644 --- a/arch/s390/include/asm/pgalloc.h +++ b/arch/s390/include/asm/pgalloc.h @@ -134,9 +134,6 @@ static inline void pmd_populate(struct mm_struct *mm, #define pmd_populate_kernel(mm, pmd, pte) pmd_populate(mm, pmd, pte) -#define pmd_pgtable(pmd) \ - ((pgtable_t)__va(pmd_val(pmd) & -sizeof(pte_t)*PTRS_PER_PTE)) - /* * page table entry allocation/free routines. */ diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index b38f7b781564..1f8f5da53262 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -65,8 +65,6 @@ extern unsigned long zero_page_mask; /* TODO: s390 cannot support io_remap_pfn_range... */ -#define FIRST_USER_ADDRESS 0UL - #define pte_ERROR(e) \ printk("%s:%d: bad pte %p.\n", __FILE__, __LINE__, (void *) pte_val(e)) #define pmd_ERROR(e) \ @@ -1711,4 +1709,7 @@ extern void s390_reset_cmma(struct mm_struct *mm); #define HAVE_ARCH_UNMAPPED_AREA #define HAVE_ARCH_UNMAPPED_AREA_TOPDOWN +#define pmd_pgtable(pmd) \ + ((pgtable_t)__va(pmd_val(pmd) & -sizeof(pte_t)*PTRS_PER_PTE)) + #endif /* _S390_PAGE_H */ diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c index dba04fbc37a2..36f870dc944f 100644 --- a/arch/s390/kernel/ipl.c +++ b/arch/s390/kernel/ipl.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #include #include diff --git a/arch/s390/kernel/kprobes.c b/arch/s390/kernel/kprobes.c index 74b0bd2c24d4..528bb31815c3 100644 --- a/arch/s390/kernel/kprobes.c +++ b/arch/s390/kernel/kprobes.c @@ -44,11 +44,6 @@ void *alloc_insn_page(void) return page; } -void free_insn_page(void *page) -{ - module_memfree(page); -} - static void *alloc_s390_insn_page(void) { if (xchg(&insn_page_in_use, 1) == 1) diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c index 18205f851c24..eec3a9d7176e 100644 --- a/arch/s390/mm/pgtable.c +++ b/arch/s390/mm/pgtable.c @@ -691,7 +691,7 @@ static void ptep_zap_swap_entry(struct mm_struct *mm, swp_entry_t entry) if (!non_swap_entry(entry)) dec_mm_counter(mm, MM_SWAPENTS); else if (is_migration_entry(entry)) { - struct page *page = migration_entry_to_page(entry); + struct page *page = pfn_swap_entry_to_page(entry); dec_mm_counter(mm, mm_counter(page)); } diff --git a/arch/sh/include/asm/pgalloc.h b/arch/sh/include/asm/pgalloc.h index 0e6b0be25e33..a9e98233c4d4 100644 --- a/arch/sh/include/asm/pgalloc.h +++ b/arch/sh/include/asm/pgalloc.h @@ -30,7 +30,6 @@ static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd, { set_pmd(pmd, __pmd((unsigned long)page_address(pte))); } -#define pmd_pgtable(pmd) pmd_page(pmd) #define __pte_free_tlb(tlb,pte,addr) \ do { \ diff --git a/arch/sh/include/asm/pgtable.h b/arch/sh/include/asm/pgtable.h index 27751e9470df..d7ddb1ec86a0 100644 --- a/arch/sh/include/asm/pgtable.h +++ b/arch/sh/include/asm/pgtable.h @@ -59,8 +59,6 @@ static inline unsigned long long neff_sign_extend(unsigned long val) /* Entries per level */ #define PTRS_PER_PTE (PAGE_SIZE / (1 << PTE_MAGNITUDE)) -#define FIRST_USER_ADDRESS 0UL - #define PHYS_ADDR_MASK29 0x1fffffff #define PHYS_ADDR_MASK32 0xffffffff diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index c72f52c704cd..c5fa7932b550 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -59,6 +59,7 @@ config SPARC32 select CLZ_TAB select HAVE_UID16 select OLD_SIGACTION + select ZONE_DMA config SPARC64 def_bool 64BIT @@ -141,10 +142,6 @@ config HIGHMEM default y if SPARC32 select KMAP_LOCAL -config ZONE_DMA - bool - default y if SPARC32 - config GENERIC_ISA_DMA bool default y if SPARC32 diff --git a/arch/sparc/include/asm/pgalloc_32.h b/arch/sparc/include/asm/pgalloc_32.h index 9d353e6dc5a9..4f73e87b22a3 100644 --- a/arch/sparc/include/asm/pgalloc_32.h +++ b/arch/sparc/include/asm/pgalloc_32.h @@ -51,7 +51,6 @@ static inline void free_pmd_fast(pmd_t * pmd) #define __pmd_free_tlb(tlb, pmd, addr) pmd_free((tlb)->mm, pmd) #define pmd_populate(mm, pmd, pte) pmd_set(pmd, pte) -#define pmd_pgtable(pmd) (pgtable_t)__pmd_page(pmd) void pmd_set(pmd_t *pmdp, pte_t *ptep); #define pmd_populate_kernel pmd_populate diff --git a/arch/sparc/include/asm/pgalloc_64.h b/arch/sparc/include/asm/pgalloc_64.h index a8dafc550985..7b5561d17ab1 100644 --- a/arch/sparc/include/asm/pgalloc_64.h +++ b/arch/sparc/include/asm/pgalloc_64.h @@ -67,7 +67,6 @@ void pte_free(struct mm_struct *mm, pgtable_t ptepage); #define pmd_populate_kernel(MM, PMD, PTE) pmd_set(MM, PMD, PTE) #define pmd_populate(MM, PMD, PTE) pmd_set(MM, PMD, PTE) -#define pmd_pgtable(PMD) ((pte_t *)pmd_page_vaddr(PMD)) void pgtable_free(void *table, bool is_page); diff --git a/arch/sparc/include/asm/pgtable_32.h b/arch/sparc/include/asm/pgtable_32.h index a5cf79c149fe..ebaf374b55ab 100644 --- a/arch/sparc/include/asm/pgtable_32.h +++ b/arch/sparc/include/asm/pgtable_32.h @@ -48,7 +48,6 @@ unsigned long __init bootmem_init(unsigned long *pages_avail); #define PTRS_PER_PMD 64 #define PTRS_PER_PGD 256 #define USER_PTRS_PER_PGD PAGE_OFFSET / PGDIR_SIZE -#define FIRST_USER_ADDRESS 0UL #define PTE_SIZE (PTRS_PER_PTE*4) #define PAGE_NONE SRMMU_PAGE_NONE @@ -433,4 +432,6 @@ static inline int io_remap_pfn_range(struct vm_area_struct *vma, /* We provide our own get_unmapped_area to cope with VA holes for userland */ #define HAVE_ARCH_UNMAPPED_AREA +#define pmd_pgtable(pmd) ((pgtable_t)__pmd_page(pmd)) + #endif /* !(_SPARC_PGTABLE_H) */ diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h index 550d3904de65..e0ee48ec3903 100644 --- a/arch/sparc/include/asm/pgtable_64.h +++ b/arch/sparc/include/asm/pgtable_64.h @@ -95,9 +95,6 @@ bool kern_addr_valid(unsigned long addr); #define PTRS_PER_PUD (1UL << PUD_BITS) #define PTRS_PER_PGD (1UL << PGDIR_BITS) -/* Kernel has a separate 44bit address space. */ -#define FIRST_USER_ADDRESS 0UL - #define pmd_ERROR(e) \ pr_err("%s:%d: bad pmd %p(%016lx) seen at (%pS)\n", \ __FILE__, __LINE__, &(e), pmd_val(e), __builtin_return_address(0)) @@ -377,8 +374,7 @@ static inline pgprot_t pgprot_noncached(pgprot_t prot) #define pgprot_noncached pgprot_noncached #if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE) -extern pte_t arch_make_huge_pte(pte_t entry, struct vm_area_struct *vma, - struct page *page, int writable); +pte_t arch_make_huge_pte(pte_t entry, unsigned int shift, vm_flags_t flags); #define arch_make_huge_pte arch_make_huge_pte static inline unsigned long __pte_default_huge_mask(void) { @@ -1121,6 +1117,8 @@ extern unsigned long cmdline_memory_size; asmlinkage void do_sparc64_fault(struct pt_regs *regs); +#define pmd_pgtable(PMD) ((pte_t *)pmd_page_vaddr(PMD)) + #ifdef CONFIG_HUGETLB_PAGE #define pud_leaf_size pud_leaf_size diff --git a/arch/sparc/kernel/sstate.c b/arch/sparc/kernel/sstate.c index ac8677c3841e..3bcc4ddc6911 100644 --- a/arch/sparc/kernel/sstate.c +++ b/arch/sparc/kernel/sstate.c @@ -6,6 +6,7 @@ #include #include +#include #include #include diff --git a/arch/sparc/mm/hugetlbpage.c b/arch/sparc/mm/hugetlbpage.c index 04d8790f6c32..0f49fada2093 100644 --- a/arch/sparc/mm/hugetlbpage.c +++ b/arch/sparc/mm/hugetlbpage.c @@ -177,10 +177,8 @@ static pte_t hugepage_shift_to_tte(pte_t entry, unsigned int shift) return sun4u_hugepage_shift_to_tte(entry, shift); } -pte_t arch_make_huge_pte(pte_t entry, struct vm_area_struct *vma, - struct page *page, int writeable) +pte_t arch_make_huge_pte(pte_t entry, unsigned int shift, vm_flags_t flags) { - unsigned int shift = huge_page_shift(hstate_vma(vma)); pte_t pte; pte = hugepage_shift_to_tte(entry, shift); @@ -188,7 +186,7 @@ pte_t arch_make_huge_pte(pte_t entry, struct vm_area_struct *vma, #ifdef CONFIG_SPARC64 /* If this vma has ADI enabled on it, turn on TTE.mcd */ - if (vma->vm_flags & VM_SPARC_ADI) + if (flags & VM_SPARC_ADI) return pte_mkmcd(pte); else return pte_mknotmcd(pte); diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c index 06e938d03f3b..1b23639e2fcd 100644 --- a/arch/sparc/mm/init_64.c +++ b/arch/sparc/mm/init_64.c @@ -27,6 +27,7 @@ #include #include #include +#include #include #include diff --git a/arch/um/drivers/mconsole_kern.c b/arch/um/drivers/mconsole_kern.c index 6d00af25ec6b..328b16f99b30 100644 --- a/arch/um/drivers/mconsole_kern.c +++ b/arch/um/drivers/mconsole_kern.c @@ -12,6 +12,7 @@ #include #include #include +#include #include #include #include diff --git a/arch/um/include/asm/pgalloc.h b/arch/um/include/asm/pgalloc.h index 2bbf28cf3aa9..8ec7cd46dd96 100644 --- a/arch/um/include/asm/pgalloc.h +++ b/arch/um/include/asm/pgalloc.h @@ -19,7 +19,6 @@ set_pmd(pmd, __pmd(_PAGE_TABLE + \ ((unsigned long long)page_to_pfn(pte) << \ (unsigned long long) PAGE_SHIFT))) -#define pmd_pgtable(pmd) pmd_page(pmd) /* * Allocate and free page tables. diff --git a/arch/um/include/asm/pgtable-2level.h b/arch/um/include/asm/pgtable-2level.h index 32106d31e4ab..8256ecc5b919 100644 --- a/arch/um/include/asm/pgtable-2level.h +++ b/arch/um/include/asm/pgtable-2level.h @@ -23,7 +23,6 @@ #define PTRS_PER_PTE 1024 #define USER_PTRS_PER_PGD ((TASK_SIZE + (PGDIR_SIZE - 1)) / PGDIR_SIZE) #define PTRS_PER_PGD 1024 -#define FIRST_USER_ADDRESS 0UL #define pte_ERROR(e) \ printk("%s:%d: bad pte %p(%08lx).\n", __FILE__, __LINE__, &(e), \ diff --git a/arch/um/include/asm/pgtable-3level.h b/arch/um/include/asm/pgtable-3level.h index 7e6a4180db9d..9289a86643a9 100644 --- a/arch/um/include/asm/pgtable-3level.h +++ b/arch/um/include/asm/pgtable-3level.h @@ -41,7 +41,6 @@ #endif #define USER_PTRS_PER_PGD ((TASK_SIZE + (PGDIR_SIZE - 1)) / PGDIR_SIZE) -#define FIRST_USER_ADDRESS 0UL #define pte_ERROR(e) \ printk("%s:%d: bad pte %p(%016lx).\n", __FILE__, __LINE__, &(e), \ diff --git a/arch/um/kernel/um_arch.c b/arch/um/kernel/um_arch.c index 74e07e748a9b..9512253947d5 100644 --- a/arch/um/kernel/um_arch.c +++ b/arch/um/kernel/um_arch.c @@ -7,6 +7,7 @@ #include #include #include +#include #include #include #include diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 867e7936dbc5..49270655e827 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -33,6 +33,7 @@ config X86_64 select NEED_DMA_MAP_STATE select SWIOTLB select ARCH_HAS_ELFCORE_COMPAT + select ZONE_DMA32 config FORCE_DYNAMIC_FTRACE def_bool y @@ -63,7 +64,7 @@ config X86 select ARCH_ENABLE_HUGEPAGE_MIGRATION if X86_64 && HUGETLB_PAGE && MIGRATION select ARCH_ENABLE_MEMORY_HOTPLUG if X86_64 || (X86_32 && HIGHMEM) select ARCH_ENABLE_MEMORY_HOTREMOVE if MEMORY_HOTPLUG - select ARCH_ENABLE_SPLIT_PMD_PTLOCK if X86_64 || X86_PAE + select ARCH_ENABLE_SPLIT_PMD_PTLOCK if (PGTABLE_LEVELS > 2) && (X86_64 || X86_PAE) select ARCH_ENABLE_THP_MIGRATION if X86_64 && TRANSPARENT_HUGEPAGE select ARCH_HAS_ACPI_TABLE_UPGRADE if ACPI select ARCH_HAS_CACHE_LINE_SIZE @@ -93,6 +94,7 @@ config X86 select ARCH_HAS_SYSCALL_WRAPPER select ARCH_HAS_UBSAN_SANITIZE_ALL select ARCH_HAS_DEBUG_WX + select ARCH_HAS_ZONE_DMA_SET if EXPERT select ARCH_HAVE_NMI_SAFE_CMPXCHG select ARCH_MIGHT_HAVE_ACPI_PDC if ACPI select ARCH_MIGHT_HAVE_PC_PARPORT @@ -344,9 +346,6 @@ config ARCH_SUSPEND_POSSIBLE config ARCH_WANT_GENERAL_HUGETLB def_bool y -config ZONE_DMA32 - def_bool y if X86_64 - config AUDIT_ARCH def_bool y if X86_64 @@ -394,16 +393,6 @@ config CC_HAS_SANE_STACKPROTECTOR menu "Processor type and features" -config ZONE_DMA - bool "DMA memory allocation support" if EXPERT - default y - help - DMA memory allocation support allows devices with less than 32-bit - addressing to allocate within the first 16MB of address space. - Disable if no such devices will be used. - - If unsure, say Y. - config SMP bool "Symmetric multi-processing support" help diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h index e63cf582201f..ab97b22ac04a 100644 --- a/arch/x86/include/asm/desc.h +++ b/arch/x86/include/asm/desc.h @@ -9,6 +9,7 @@ #include #include +#include #include #include diff --git a/arch/x86/include/asm/pgalloc.h b/arch/x86/include/asm/pgalloc.h index 62ad61d6fefc..c7ec5bb88334 100644 --- a/arch/x86/include/asm/pgalloc.h +++ b/arch/x86/include/asm/pgalloc.h @@ -84,8 +84,6 @@ static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd, set_pmd(pmd, __pmd(((pteval_t)pfn << PAGE_SHIFT) | _PAGE_TABLE)); } -#define pmd_pgtable(pmd) pmd_page(pmd) - #if CONFIG_PGTABLE_LEVELS > 2 extern void ___pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd); diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index f24d7ef8fffa..40497a9020c6 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -7,8 +7,6 @@ #include -#define FIRST_USER_ADDRESS 0UL - #define _PAGE_BIT_PRESENT 0 /* is present */ #define _PAGE_BIT_RW 1 /* writeable */ #define _PAGE_BIT_USER 2 /* userspace addressable */ diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index 01ca94f42e4e..cc8f1773deca 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -17,6 +17,7 @@ #include #include #include +#include #include #include #include diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index c492ad3001ca..b6e046e4b289 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -422,12 +422,6 @@ void *alloc_insn_page(void) return page; } -/* Recover page to RW mode before releasing it */ -void free_insn_page(void *page) -{ - module_memfree(page); -} - /* Kprobe x86 instruction emulation - only regs->ip or IF flag modifiers */ static void kprobe_emulate_ifmodifiers(struct kprobe *p, struct pt_regs *regs) diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 85acd22f8022..9f1d9215a9fb 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -14,6 +14,7 @@ #include #include #include +#include #include #include #include diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index e527d829e1ed..65ea58527176 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -33,6 +33,7 @@ #include #include #include +#include #include #include @@ -1269,7 +1270,7 @@ static struct kcore_list kcore_vsyscall; static void __init register_page_bootmem_info(void) { -#ifdef CONFIG_NUMA +#if defined(CONFIG_NUMA) || defined(CONFIG_HUGETLB_PAGE_FREE_VMEMMAP) int i; for_each_online_node(i) @@ -1623,7 +1624,7 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node, return err; } -#if defined(CONFIG_MEMORY_HOTPLUG_SPARSE) && defined(CONFIG_HAVE_BOOTMEM_INFO_NODE) +#ifdef CONFIG_HAVE_BOOTMEM_INFO_NODE void register_page_bootmem_memmap(unsigned long section_nr, struct page *start_page, unsigned long nr_pages) { diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index d27cf69e811d..1303ff6ef7be 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -682,6 +682,7 @@ int p4d_clear_huge(p4d_t *p4d) } #endif +#if CONFIG_PGTABLE_LEVELS > 3 /** * pud_set_huge - setup kernel PUD mapping * @@ -720,6 +721,23 @@ int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot) return 1; } +/** + * pud_clear_huge - clear kernel PUD mapping when it is set + * + * Returns 1 on success and 0 on failure (no PUD map is found). + */ +int pud_clear_huge(pud_t *pud) +{ + if (pud_large(*pud)) { + pud_clear(pud); + return 1; + } + + return 0; +} +#endif + +#if CONFIG_PGTABLE_LEVELS > 2 /** * pmd_set_huge - setup kernel PMD mapping * @@ -750,21 +768,6 @@ int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot) return 1; } -/** - * pud_clear_huge - clear kernel PUD mapping when it is set - * - * Returns 1 on success and 0 on failure (no PUD map is found). - */ -int pud_clear_huge(pud_t *pud) -{ - if (pud_large(*pud)) { - pud_clear(pud); - return 1; - } - - return 0; -} - /** * pmd_clear_huge - clear kernel PMD mapping when it is set * @@ -779,6 +782,7 @@ int pmd_clear_huge(pmd_t *pmd) return 0; } +#endif #ifdef CONFIG_X86_64 /** diff --git a/arch/x86/purgatory/purgatory.c b/arch/x86/purgatory/purgatory.c index f03b64d9cb51..7558139920f8 100644 --- a/arch/x86/purgatory/purgatory.c +++ b/arch/x86/purgatory/purgatory.c @@ -9,6 +9,8 @@ */ #include +#include +#include #include #include diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index aa9f50fccc5d..c79bd0af2e8c 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -6,6 +6,7 @@ #include #include #include +#include #include #include diff --git a/arch/xtensa/include/asm/pgalloc.h b/arch/xtensa/include/asm/pgalloc.h index d3a22da4d2c9..eeb2de3a89e5 100644 --- a/arch/xtensa/include/asm/pgalloc.h +++ b/arch/xtensa/include/asm/pgalloc.h @@ -25,7 +25,6 @@ (pmd_val(*(pmdp)) = ((unsigned long)ptep)) #define pmd_populate(mm, pmdp, page) \ (pmd_val(*(pmdp)) = ((unsigned long)page_to_virt(page))) -#define pmd_pgtable(pmd) pmd_page(pmd) static inline pgd_t* pgd_alloc(struct mm_struct *mm) @@ -63,7 +62,6 @@ static inline pgtable_t pte_alloc_one(struct mm_struct *mm) return page; } -#define pmd_pgtable(pmd) pmd_page(pmd) #endif /* CONFIG_MMU */ #endif /* _XTENSA_PGALLOC_H */ diff --git a/arch/xtensa/include/asm/pgtable.h b/arch/xtensa/include/asm/pgtable.h index d7fc45c920c2..bd5aeb795567 100644 --- a/arch/xtensa/include/asm/pgtable.h +++ b/arch/xtensa/include/asm/pgtable.h @@ -59,7 +59,6 @@ #define PTRS_PER_PGD 1024 #define PGD_ORDER 0 #define USER_PTRS_PER_PGD (TASK_SIZE/PGDIR_SIZE) -#define FIRST_USER_ADDRESS 0UL #define FIRST_USER_PGD_NR (FIRST_USER_ADDRESS >> PGDIR_SHIFT) #ifdef CONFIG_MMU diff --git a/arch/xtensa/include/uapi/asm/mman.h b/arch/xtensa/include/uapi/asm/mman.h index e5e643752947..b3a22095371b 100644 --- a/arch/xtensa/include/uapi/asm/mman.h +++ b/arch/xtensa/include/uapi/asm/mman.h @@ -106,6 +106,9 @@ #define MADV_COLD 20 /* deactivate these pages */ #define MADV_PAGEOUT 21 /* reclaim these pages */ +#define MADV_POPULATE_READ 22 /* populate (prefault) page tables readable */ +#define MADV_POPULATE_WRITE 23 /* populate (prefault) page tables writable */ + /* compatibility flags */ #define MAP_FILE 0 diff --git a/arch/xtensa/platforms/iss/setup.c b/arch/xtensa/platforms/iss/setup.c index ed519aee0ec8..d3433e1bb94e 100644 --- a/arch/xtensa/platforms/iss/setup.c +++ b/arch/xtensa/platforms/iss/setup.c @@ -14,6 +14,7 @@ #include #include #include +#include #include #include diff --git a/drivers/block/zram/zram_drv.h b/drivers/block/zram/zram_drv.h index 74c411911b6e..80c3b43b4828 100644 --- a/drivers/block/zram/zram_drv.h +++ b/drivers/block/zram/zram_drv.h @@ -113,8 +113,8 @@ struct zram { * zram is claimed so open request will be failed */ bool claim; /* Protected by disk->open_mutex */ - struct file *backing_dev; #ifdef CONFIG_ZRAM_WRITEBACK + struct file *backing_dev; spinlock_t wb_limit_lock; bool wb_limit_enable; u64 bd_wb_limit; diff --git a/drivers/bus/brcmstb_gisb.c b/drivers/bus/brcmstb_gisb.c index 7355fa2cb439..6551286a60cc 100644 --- a/drivers/bus/brcmstb_gisb.c +++ b/drivers/bus/brcmstb_gisb.c @@ -6,6 +6,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/char/ipmi/ipmi_msghandler.c b/drivers/char/ipmi/ipmi_msghandler.c index 8a0e97b33cae..e96cb5c4f97a 100644 --- a/drivers/char/ipmi/ipmi_msghandler.c +++ b/drivers/char/ipmi/ipmi_msghandler.c @@ -16,6 +16,7 @@ #include #include +#include #include #include #include diff --git a/drivers/clk/analogbits/wrpll-cln28hpc.c b/drivers/clk/analogbits/wrpll-cln28hpc.c index 3b1947575dcc..09ca82356399 100644 --- a/drivers/clk/analogbits/wrpll-cln28hpc.c +++ b/drivers/clk/analogbits/wrpll-cln28hpc.c @@ -23,8 +23,12 @@ #include #include +#include #include #include +#include +#include + #include /* MIN_INPUT_FREQ: minimum input clock frequency, in Hz (Fref_min) */ diff --git a/drivers/edac/altera_edac.c b/drivers/edac/altera_edac.c index 5f7fd79ec82f..61c21bd880a4 100644 --- a/drivers/edac/altera_edac.c +++ b/drivers/edac/altera_edac.c @@ -20,6 +20,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/firmware/google/gsmi.c b/drivers/firmware/google/gsmi.c index bb6e77ee3898..adaa492c3d2d 100644 --- a/drivers/firmware/google/gsmi.c +++ b/drivers/firmware/google/gsmi.c @@ -19,6 +19,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/gpu/drm/nouveau/include/nvif/if000c.h b/drivers/gpu/drm/nouveau/include/nvif/if000c.h index d6dd40f21eed..9c7ff56831c5 100644 --- a/drivers/gpu/drm/nouveau/include/nvif/if000c.h +++ b/drivers/gpu/drm/nouveau/include/nvif/if000c.h @@ -77,6 +77,7 @@ struct nvif_vmm_pfnmap_v0 { #define NVIF_VMM_PFNMAP_V0_APER 0x00000000000000f0ULL #define NVIF_VMM_PFNMAP_V0_HOST 0x0000000000000000ULL #define NVIF_VMM_PFNMAP_V0_VRAM 0x0000000000000010ULL +#define NVIF_VMM_PFNMAP_V0_A 0x0000000000000004ULL #define NVIF_VMM_PFNMAP_V0_W 0x0000000000000002ULL #define NVIF_VMM_PFNMAP_V0_V 0x0000000000000001ULL #define NVIF_VMM_PFNMAP_V0_NONE 0x0000000000000000ULL diff --git a/drivers/gpu/drm/nouveau/nouveau_svm.c b/drivers/gpu/drm/nouveau/nouveau_svm.c index 1c3f890377d2..82b583f5fca8 100644 --- a/drivers/gpu/drm/nouveau/nouveau_svm.c +++ b/drivers/gpu/drm/nouveau/nouveau_svm.c @@ -35,6 +35,7 @@ #include #include #include +#include struct nouveau_svm { struct nouveau_drm *drm; @@ -67,6 +68,11 @@ struct nouveau_svm { } buffer[1]; }; +#define FAULT_ACCESS_READ 0 +#define FAULT_ACCESS_WRITE 1 +#define FAULT_ACCESS_ATOMIC 2 +#define FAULT_ACCESS_PREFETCH 3 + #define SVM_DBG(s,f,a...) NV_DEBUG((s)->drm, "svm: "f"\n", ##a) #define SVM_ERR(s,f,a...) NV_WARN((s)->drm, "svm: "f"\n", ##a) @@ -265,7 +271,7 @@ nouveau_svmm_invalidate_range_start(struct mmu_notifier *mn, * the invalidation is handled as part of the migration process. */ if (update->event == MMU_NOTIFY_MIGRATE && - update->migrate_pgmap_owner == svmm->vmm->cli->drm->dev) + update->owner == svmm->vmm->cli->drm->dev) goto out; if (limit > svmm->unmanaged.start && start < svmm->unmanaged.limit) { @@ -411,6 +417,24 @@ nouveau_svm_fault_cancel_fault(struct nouveau_svm *svm, fault->client); } +static int +nouveau_svm_fault_priority(u8 fault) +{ + switch (fault) { + case FAULT_ACCESS_PREFETCH: + return 0; + case FAULT_ACCESS_READ: + return 1; + case FAULT_ACCESS_WRITE: + return 2; + case FAULT_ACCESS_ATOMIC: + return 3; + default: + WARN_ON_ONCE(1); + return -1; + } +} + static int nouveau_svm_fault_cmp(const void *a, const void *b) { @@ -421,9 +445,8 @@ nouveau_svm_fault_cmp(const void *a, const void *b) return ret; if ((ret = (s64)fa->addr - fb->addr)) return ret; - /*XXX: atomic? */ - return (fa->access == 0 || fa->access == 3) - - (fb->access == 0 || fb->access == 3); + return nouveau_svm_fault_priority(fa->access) - + nouveau_svm_fault_priority(fb->access); } static void @@ -487,6 +510,10 @@ static bool nouveau_svm_range_invalidate(struct mmu_interval_notifier *mni, struct svm_notifier *sn = container_of(mni, struct svm_notifier, notifier); + if (range->event == MMU_NOTIFY_EXCLUSIVE && + range->owner == sn->svmm->vmm->cli->drm->dev) + return true; + /* * serializes the update to mni->invalidate_seq done by caller and * prevents invalidation of the PTE from progressing while HW is being @@ -555,6 +582,71 @@ static void nouveau_hmm_convert_pfn(struct nouveau_drm *drm, args->p.phys[0] |= NVIF_VMM_PFNMAP_V0_W; } +static int nouveau_atomic_range_fault(struct nouveau_svmm *svmm, + struct nouveau_drm *drm, + struct nouveau_pfnmap_args *args, u32 size, + struct svm_notifier *notifier) +{ + unsigned long timeout = + jiffies + msecs_to_jiffies(HMM_RANGE_DEFAULT_TIMEOUT); + struct mm_struct *mm = svmm->notifier.mm; + struct page *page; + unsigned long start = args->p.addr; + unsigned long notifier_seq; + int ret = 0; + + ret = mmu_interval_notifier_insert(¬ifier->notifier, mm, + args->p.addr, args->p.size, + &nouveau_svm_mni_ops); + if (ret) + return ret; + + while (true) { + if (time_after(jiffies, timeout)) { + ret = -EBUSY; + goto out; + } + + notifier_seq = mmu_interval_read_begin(¬ifier->notifier); + mmap_read_lock(mm); + ret = make_device_exclusive_range(mm, start, start + PAGE_SIZE, + &page, drm->dev); + mmap_read_unlock(mm); + if (ret <= 0 || !page) { + ret = -EINVAL; + goto out; + } + + mutex_lock(&svmm->mutex); + if (!mmu_interval_read_retry(¬ifier->notifier, + notifier_seq)) + break; + mutex_unlock(&svmm->mutex); + } + + /* Map the page on the GPU. */ + args->p.page = 12; + args->p.size = PAGE_SIZE; + args->p.addr = start; + args->p.phys[0] = page_to_phys(page) | + NVIF_VMM_PFNMAP_V0_V | + NVIF_VMM_PFNMAP_V0_W | + NVIF_VMM_PFNMAP_V0_A | + NVIF_VMM_PFNMAP_V0_HOST; + + svmm->vmm->vmm.object.client->super = true; + ret = nvif_object_ioctl(&svmm->vmm->vmm.object, args, size, NULL); + svmm->vmm->vmm.object.client->super = false; + mutex_unlock(&svmm->mutex); + + unlock_page(page); + put_page(page); + +out: + mmu_interval_notifier_remove(¬ifier->notifier); + return ret; +} + static int nouveau_range_fault(struct nouveau_svmm *svmm, struct nouveau_drm *drm, struct nouveau_pfnmap_args *args, u32 size, @@ -567,18 +659,27 @@ static int nouveau_range_fault(struct nouveau_svmm *svmm, unsigned long hmm_pfns[1]; struct hmm_range range = { .notifier = ¬ifier->notifier, - .start = notifier->notifier.interval_tree.start, - .end = notifier->notifier.interval_tree.last + 1, .default_flags = hmm_flags, .hmm_pfns = hmm_pfns, .dev_private_owner = drm->dev, }; - struct mm_struct *mm = notifier->notifier.mm; + struct mm_struct *mm = svmm->notifier.mm; int ret; + ret = mmu_interval_notifier_insert(¬ifier->notifier, mm, + args->p.addr, args->p.size, + &nouveau_svm_mni_ops); + if (ret) + return ret; + + range.start = notifier->notifier.interval_tree.start; + range.end = notifier->notifier.interval_tree.last + 1; + while (true) { - if (time_after(jiffies, timeout)) - return -EBUSY; + if (time_after(jiffies, timeout)) { + ret = -EBUSY; + goto out; + } range.notifier_seq = mmu_interval_read_begin(range.notifier); mmap_read_lock(mm); @@ -587,7 +688,7 @@ static int nouveau_range_fault(struct nouveau_svmm *svmm, if (ret) { if (ret == -EBUSY) continue; - return ret; + goto out; } mutex_lock(&svmm->mutex); @@ -606,6 +707,9 @@ static int nouveau_range_fault(struct nouveau_svmm *svmm, svmm->vmm->vmm.object.client->super = false; mutex_unlock(&svmm->mutex); +out: + mmu_interval_notifier_remove(¬ifier->notifier); + return ret; } @@ -625,7 +729,7 @@ nouveau_svm_fault(struct nvif_notify *notify) unsigned long hmm_flags; u64 inst, start, limit; int fi, fn; - int replay = 0, ret; + int replay = 0, atomic = 0, ret; /* Parse available fault buffer entries into a cache, and update * the GET pointer so HW can reuse the entries. @@ -706,12 +810,14 @@ nouveau_svm_fault(struct nvif_notify *notify) /* * Determine required permissions based on GPU fault * access flags. - * XXX: atomic? */ switch (buffer->fault[fi]->access) { case 0: /* READ. */ hmm_flags = HMM_PFN_REQ_FAULT; break; + case 2: /* ATOMIC. */ + atomic = true; + break; case 3: /* PREFETCH. */ hmm_flags = 0; break; @@ -727,14 +833,14 @@ nouveau_svm_fault(struct nvif_notify *notify) } notifier.svmm = svmm; - ret = mmu_interval_notifier_insert(¬ifier.notifier, mm, - args.i.p.addr, args.i.p.size, - &nouveau_svm_mni_ops); - if (!ret) { + if (atomic) + ret = nouveau_atomic_range_fault(svmm, svm->drm, + &args.i, sizeof(args), + ¬ifier); + else ret = nouveau_range_fault(svmm, svm->drm, &args.i, - sizeof(args), hmm_flags, ¬ifier); - mmu_interval_notifier_remove(¬ifier.notifier); - } + sizeof(args), hmm_flags, + ¬ifier); mmput(mm); limit = args.i.p.addr + args.i.p.size; @@ -750,11 +856,15 @@ nouveau_svm_fault(struct nvif_notify *notify) */ if (buffer->fault[fn]->svmm != svmm || buffer->fault[fn]->addr >= limit || - (buffer->fault[fi]->access == 0 /* READ. */ && + (buffer->fault[fi]->access == FAULT_ACCESS_READ && !(args.phys[0] & NVIF_VMM_PFNMAP_V0_V)) || - (buffer->fault[fi]->access != 0 /* READ. */ && - buffer->fault[fi]->access != 3 /* PREFETCH. */ && - !(args.phys[0] & NVIF_VMM_PFNMAP_V0_W))) + (buffer->fault[fi]->access != FAULT_ACCESS_READ && + buffer->fault[fi]->access != FAULT_ACCESS_PREFETCH && + !(args.phys[0] & NVIF_VMM_PFNMAP_V0_W)) || + (buffer->fault[fi]->access != FAULT_ACCESS_READ && + buffer->fault[fi]->access != FAULT_ACCESS_WRITE && + buffer->fault[fi]->access != FAULT_ACCESS_PREFETCH && + !(args.phys[0] & NVIF_VMM_PFNMAP_V0_A))) break; } diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmm.h b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmm.h index a2b179568970..f6188aa9171c 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmm.h +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmm.h @@ -178,6 +178,7 @@ void nvkm_vmm_unmap_region(struct nvkm_vmm *, struct nvkm_vma *); #define NVKM_VMM_PFN_APER 0x00000000000000f0ULL #define NVKM_VMM_PFN_HOST 0x0000000000000000ULL #define NVKM_VMM_PFN_VRAM 0x0000000000000010ULL +#define NVKM_VMM_PFN_A 0x0000000000000004ULL #define NVKM_VMM_PFN_W 0x0000000000000002ULL #define NVKM_VMM_PFN_V 0x0000000000000001ULL #define NVKM_VMM_PFN_NONE 0x0000000000000000ULL diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmmgp100.c b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmmgp100.c index 236db5570771..f02abd9cb4dd 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmmgp100.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmmgp100.c @@ -88,6 +88,9 @@ gp100_vmm_pgt_pfn(struct nvkm_vmm *vmm, struct nvkm_mmu_pt *pt, if (!(*map->pfn & NVKM_VMM_PFN_W)) data |= BIT_ULL(6); /* RO. */ + if (!(*map->pfn & NVKM_VMM_PFN_A)) + data |= BIT_ULL(7); /* Atomic disable. */ + if (!(*map->pfn & NVKM_VMM_PFN_VRAM)) { addr = *map->pfn >> NVKM_VMM_PFN_ADDR_SHIFT; addr = dma_map_page(dev, pfn_to_page(addr), 0, @@ -322,6 +325,9 @@ gp100_vmm_pd0_pfn(struct nvkm_vmm *vmm, struct nvkm_mmu_pt *pt, if (!(*map->pfn & NVKM_VMM_PFN_W)) data |= BIT_ULL(6); /* RO. */ + if (!(*map->pfn & NVKM_VMM_PFN_A)) + data |= BIT_ULL(7); /* Atomic disable. */ + if (!(*map->pfn & NVKM_VMM_PFN_VRAM)) { addr = *map->pfn >> NVKM_VMM_PFN_ADDR_SHIFT; addr = dma_map_page(dev, pfn_to_page(addr), 0, diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c index 92cb3f7d21d9..57bbbaa4e8f7 100644 --- a/drivers/hv/vmbus_drv.c +++ b/drivers/hv/vmbus_drv.c @@ -25,6 +25,7 @@ #include #include +#include #include #include #include diff --git a/drivers/hwtracing/coresight/coresight-cpu-debug.c b/drivers/hwtracing/coresight/coresight-cpu-debug.c index 2dcf13de751f..9731d3a96073 100644 --- a/drivers/hwtracing/coresight/coresight-cpu-debug.c +++ b/drivers/hwtracing/coresight/coresight-cpu-debug.c @@ -17,6 +17,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/leds/trigger/ledtrig-activity.c b/drivers/leds/trigger/ledtrig-activity.c index 14ba7faaed9e..30bc9df03636 100644 --- a/drivers/leds/trigger/ledtrig-activity.c +++ b/drivers/leds/trigger/ledtrig-activity.c @@ -11,6 +11,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/leds/trigger/ledtrig-heartbeat.c b/drivers/leds/trigger/ledtrig-heartbeat.c index 36b6709afe9f..7fe0a05574d2 100644 --- a/drivers/leds/trigger/ledtrig-heartbeat.c +++ b/drivers/leds/trigger/ledtrig-heartbeat.c @@ -11,6 +11,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/leds/trigger/ledtrig-panic.c b/drivers/leds/trigger/ledtrig-panic.c index 5751cd032f9d..64abf2e91608 100644 --- a/drivers/leds/trigger/ledtrig-panic.c +++ b/drivers/leds/trigger/ledtrig-panic.c @@ -8,6 +8,7 @@ #include #include #include +#include #include #include "../leds.h" diff --git a/drivers/misc/bcm-vk/bcm_vk_dev.c b/drivers/misc/bcm-vk/bcm_vk_dev.c index 6bfea3210389..ad639ee85b2a 100644 --- a/drivers/misc/bcm-vk/bcm_vk_dev.c +++ b/drivers/misc/bcm-vk/bcm_vk_dev.c @@ -9,6 +9,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/misc/ibmasm/heartbeat.c b/drivers/misc/ibmasm/heartbeat.c index 4f5f3bdc814d..59c9a0d95659 100644 --- a/drivers/misc/ibmasm/heartbeat.c +++ b/drivers/misc/ibmasm/heartbeat.c @@ -9,6 +9,7 @@ */ #include +#include #include "ibmasm.h" #include "dot_command.h" #include "lowlevel.h" diff --git a/drivers/misc/pvpanic/pvpanic.c b/drivers/misc/pvpanic/pvpanic.c index 65f70a4da8c0..793ea0c01193 100644 --- a/drivers/misc/pvpanic/pvpanic.c +++ b/drivers/misc/pvpanic/pvpanic.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/net/ipa/ipa_smp2p.c b/drivers/net/ipa/ipa_smp2p.c index cf709df70d28..93270e50b6b3 100644 --- a/drivers/net/ipa/ipa_smp2p.c +++ b/drivers/net/ipa/ipa_smp2p.c @@ -8,6 +8,7 @@ #include #include #include +#include #include #include diff --git a/drivers/parisc/power.c b/drivers/parisc/power.c index ebaf6867b457..456776bd8ee6 100644 --- a/drivers/parisc/power.c +++ b/drivers/parisc/power.c @@ -38,6 +38,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/power/reset/ltc2952-poweroff.c b/drivers/power/reset/ltc2952-poweroff.c index d1495af30081..8688c8ba8894 100644 --- a/drivers/power/reset/ltc2952-poweroff.c +++ b/drivers/power/reset/ltc2952-poweroff.c @@ -52,6 +52,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/remoteproc/remoteproc_core.c b/drivers/remoteproc/remoteproc_core.c index 626a6b90fba2..76dd8e2b1e7e 100644 --- a/drivers/remoteproc/remoteproc_core.c +++ b/drivers/remoteproc/remoteproc_core.c @@ -20,6 +20,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/s390/char/con3215.c b/drivers/s390/char/con3215.c index 1fd5bca9fa20..02523f4e29f4 100644 --- a/drivers/s390/char/con3215.c +++ b/drivers/s390/char/con3215.c @@ -19,6 +19,7 @@ #include #include #include +#include #include #include /* ASYNC_* flags */ #include diff --git a/drivers/s390/char/con3270.c b/drivers/s390/char/con3270.c index e21962c0fd94..87cdbace1453 100644 --- a/drivers/s390/char/con3270.c +++ b/drivers/s390/char/con3270.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/s390/char/sclp.c b/drivers/s390/char/sclp.c index 986bbbc23d0a..6627820a5eb9 100644 --- a/drivers/s390/char/sclp.c +++ b/drivers/s390/char/sclp.c @@ -11,6 +11,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/s390/char/sclp_con.c b/drivers/s390/char/sclp_con.c index 9b852a47ccc1..cc01a7b8595d 100644 --- a/drivers/s390/char/sclp_con.c +++ b/drivers/s390/char/sclp_con.c @@ -10,6 +10,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/s390/char/sclp_vt220.c b/drivers/s390/char/sclp_vt220.c index 7f4445b0f819..5b8a7b090a97 100644 --- a/drivers/s390/char/sclp_vt220.c +++ b/drivers/s390/char/sclp_vt220.c @@ -9,6 +9,7 @@ #include #include +#include #include #include #include diff --git a/drivers/s390/char/zcore.c b/drivers/s390/char/zcore.c index bd3c724bf695..b5b0848da93b 100644 --- a/drivers/s390/char/zcore.c +++ b/drivers/s390/char/zcore.c @@ -15,6 +15,7 @@ #include #include #include +#include #include #include diff --git a/drivers/soc/bcm/brcmstb/pm/pm-arm.c b/drivers/soc/bcm/brcmstb/pm/pm-arm.c index a673fdffe216..3cbb165d6e30 100644 --- a/drivers/soc/bcm/brcmstb/pm/pm-arm.c +++ b/drivers/soc/bcm/brcmstb/pm/pm-arm.c @@ -28,6 +28,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/staging/olpc_dcon/olpc_dcon.c b/drivers/staging/olpc_dcon/olpc_dcon.c index 6d8e9a481786..7284cb4ac395 100644 --- a/drivers/staging/olpc_dcon/olpc_dcon.c +++ b/drivers/staging/olpc_dcon/olpc_dcon.c @@ -22,6 +22,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/video/fbdev/hyperv_fb.c b/drivers/video/fbdev/hyperv_fb.c index a7e6eea2c4a1..23999df52739 100644 --- a/drivers/video/fbdev/hyperv_fb.c +++ b/drivers/video/fbdev/hyperv_fb.c @@ -52,6 +52,7 @@ #include #include #include +#include #include #include diff --git a/drivers/virtio/virtio_mem.c b/drivers/virtio/virtio_mem.c index 10ec60d81e84..dc2a2e2b2ff8 100644 --- a/drivers/virtio/virtio_mem.c +++ b/drivers/virtio/virtio_mem.c @@ -1065,6 +1065,7 @@ static int virtio_mem_memory_notifier_cb(struct notifier_block *nb, static void virtio_mem_set_fake_offline(unsigned long pfn, unsigned long nr_pages, bool onlined) { + page_offline_begin(); for (; nr_pages--; pfn++) { struct page *page = pfn_to_page(pfn); @@ -1075,6 +1076,7 @@ static void virtio_mem_set_fake_offline(unsigned long pfn, ClearPageReserved(page); } } + page_offline_end(); } /* diff --git a/fs/Kconfig b/fs/Kconfig index 141a856c50e7..a7749c126b8e 100644 --- a/fs/Kconfig +++ b/fs/Kconfig @@ -240,6 +240,21 @@ config HUGETLBFS config HUGETLB_PAGE def_bool HUGETLBFS +config HUGETLB_PAGE_FREE_VMEMMAP + def_bool HUGETLB_PAGE + depends on X86_64 + depends on SPARSEMEM_VMEMMAP + +config HUGETLB_PAGE_FREE_VMEMMAP_DEFAULT_ON + bool "Default freeing vmemmap pages of HugeTLB to on" + default n + depends on HUGETLB_PAGE_FREE_VMEMMAP + help + When using HUGETLB_PAGE_FREE_VMEMMAP, the freeing unused vmemmap + pages associated with each HugeTLB page is default off. Say Y here + to enable freeing vmemmap pages of HugeTLB by default. It can then + be disabled on the command line via hugetlb_free_vmemmap=off. + config MEMFD_CREATE def_bool TMPFS || HUGETLBFS diff --git a/fs/exec.c b/fs/exec.c index f2bcdbeb3afb..38f63451b928 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -84,9 +84,6 @@ static DEFINE_RWLOCK(binfmt_lock); void __register_binfmt(struct linux_binfmt * fmt, int insert) { - BUG_ON(!fmt); - if (WARN_ON(!fmt->load_binary)) - return; write_lock(&binfmt_lock); insert ? list_add(&fmt->lh, &formats) : list_add_tail(&fmt->lh, &formats); diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c index 70e8374ddac4..6fef67c2a9f0 100644 --- a/fs/hfsplus/inode.c +++ b/fs/hfsplus/inode.c @@ -281,6 +281,11 @@ int hfsplus_getattr(struct user_namespace *mnt_userns, const struct path *path, struct inode *inode = d_inode(path->dentry); struct hfsplus_inode_info *hip = HFSPLUS_I(inode); + if (request_mask & STATX_BTIME) { + stat->result_mask |= STATX_BTIME; + stat->btime = hfsp_mt2ut(hip->create_date); + } + if (inode->i_flags & S_APPEND) stat->attributes |= STATX_ATTR_APPEND; if (inode->i_flags & S_IMMUTABLE) diff --git a/fs/hfsplus/xattr.c b/fs/hfsplus/xattr.c index 4d169c5a2673..e2855ceefd39 100644 --- a/fs/hfsplus/xattr.c +++ b/fs/hfsplus/xattr.c @@ -204,7 +204,6 @@ static int hfsplus_create_attributes_file(struct super_block *sb) buf = kzalloc(node_size, GFP_NOFS); if (!buf) { - pr_err("failed to allocate memory for header node\n"); err = -ENOMEM; goto end_attr_file_creation; } diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index b517a8794400..cd5eac2ba054 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -2351,7 +2351,7 @@ static struct nfs4_client *get_nfsdfs_clp(struct inode *inode) static void seq_quote_mem(struct seq_file *m, char *data, int len) { seq_printf(m, "\""); - seq_escape_mem_ascii(m, data, len); + seq_escape_mem(m, data, len, ESCAPE_HEX | ESCAPE_NAP | ESCAPE_APPEND, "\"\\"); seq_printf(m, "\""); } diff --git a/fs/nilfs2/btree.c b/fs/nilfs2/btree.c index f42ab57201e7..ab9ec073330f 100644 --- a/fs/nilfs2/btree.c +++ b/fs/nilfs2/btree.c @@ -738,7 +738,6 @@ static int nilfs_btree_lookup_contig(const struct nilfs_bmap *btree, if (ptr2 != ptr + cnt || ++cnt == maxblocks) goto end; index++; - continue; } if (level == maxlevel) break; diff --git a/fs/open.c b/fs/open.c index 53bc0573c0ec..1a325b3194df 100644 --- a/fs/open.c +++ b/fs/open.c @@ -852,8 +852,17 @@ static int do_dentry_open(struct file *f, * XXX: Huge page cache doesn't support writing yet. Drop all page * cache for this file before processing writes. */ - if ((f->f_mode & FMODE_WRITE) && filemap_nr_thps(inode->i_mapping)) - truncate_pagecache(inode, 0); + if (f->f_mode & FMODE_WRITE) { + /* + * Paired with smp_mb() in collapse_file() to ensure nr_thps + * is up to date and the update to i_writecount by + * get_write_access() is visible. Ensures subsequent insertion + * of THPs into the page cache will fail. + */ + smp_mb(); + if (filemap_nr_thps(inode->i_mapping)) + truncate_pagecache(inode, 0); + } return 0; diff --git a/fs/proc/base.c b/fs/proc/base.c index 9cbd915025ad..e5b5f7709d48 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -854,7 +854,7 @@ static ssize_t mem_rw(struct file *file, char __user *buf, flags = FOLL_FORCE | (write ? FOLL_WRITE : 0); while (count > 0) { - int this_len = min_t(int, count, PAGE_SIZE); + size_t this_len = min_t(size_t, count, PAGE_SIZE); if (write && copy_from_user(page, buf, this_len)) { copied = -EFAULT; @@ -3172,7 +3172,7 @@ static const struct pid_entry tgid_base_stuff[] = { DIR("task", S_IRUGO|S_IXUGO, proc_task_inode_operations, proc_task_operations), DIR("fd", S_IRUSR|S_IXUSR, proc_fd_inode_operations, proc_fd_operations), DIR("map_files", S_IRUSR|S_IXUSR, proc_map_files_inode_operations, proc_map_files_operations), - DIR("fdinfo", S_IRUSR|S_IXUSR, proc_fdinfo_inode_operations, proc_fdinfo_operations), + DIR("fdinfo", S_IRUGO|S_IXUGO, proc_fdinfo_inode_operations, proc_fdinfo_operations), DIR("ns", S_IRUSR|S_IXUGO, proc_ns_dir_inode_operations, proc_ns_dir_operations), #ifdef CONFIG_NET DIR("net", S_IRUGO|S_IXUGO, proc_net_inode_operations, proc_net_operations), @@ -3517,7 +3517,7 @@ static const struct inode_operations proc_tid_comm_inode_operations = { */ static const struct pid_entry tid_base_stuff[] = { DIR("fd", S_IRUSR|S_IXUSR, proc_fd_inode_operations, proc_fd_operations), - DIR("fdinfo", S_IRUSR|S_IXUSR, proc_fdinfo_inode_operations, proc_fdinfo_operations), + DIR("fdinfo", S_IRUGO|S_IXUGO, proc_fdinfo_inode_operations, proc_fdinfo_operations), DIR("ns", S_IRUSR|S_IXUGO, proc_ns_dir_inode_operations, proc_ns_dir_operations), #ifdef CONFIG_NET DIR("net", S_IRUGO|S_IXUGO, proc_net_inode_operations, proc_net_operations), diff --git a/fs/proc/fd.c b/fs/proc/fd.c index 07fc4fad2602..172c86270b31 100644 --- a/fs/proc/fd.c +++ b/fs/proc/fd.c @@ -6,6 +6,7 @@ #include #include #include +#include #include #include #include @@ -53,9 +54,10 @@ static int seq_show(struct seq_file *m, void *v) if (ret) return ret; - seq_printf(m, "pos:\t%lli\nflags:\t0%o\nmnt_id:\t%i\n", + seq_printf(m, "pos:\t%lli\nflags:\t0%o\nmnt_id:\t%i\nino:\t%lu\n", (long long)file->f_pos, f_flags, - real_mount(file->f_path.mnt)->mnt_id); + real_mount(file->f_path.mnt)->mnt_id, + file_inode(file)->i_ino); /* show_fd_locks() never deferences files so a stale value is safe */ show_fd_locks(m, file, files); @@ -72,6 +74,18 @@ static int seq_show(struct seq_file *m, void *v) static int seq_fdinfo_open(struct inode *inode, struct file *file) { + bool allowed = false; + struct task_struct *task = get_proc_task(inode); + + if (!task) + return -ESRCH; + + allowed = ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS); + put_task_struct(task); + + if (!allowed) + return -EACCES; + return single_open(file, seq_show, inode); } @@ -308,7 +322,7 @@ static struct dentry *proc_fdinfo_instantiate(struct dentry *dentry, struct proc_inode *ei; struct inode *inode; - inode = proc_pid_make_inode(dentry->d_sb, task, S_IFREG | S_IRUSR); + inode = proc_pid_make_inode(dentry->d_sb, task, S_IFREG | S_IRUGO); if (!inode) return ERR_PTR(-ENOENT); diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c index 4d2e64e9016c..982e694aae77 100644 --- a/fs/proc/kcore.c +++ b/fs/proc/kcore.c @@ -313,6 +313,7 @@ read_kcore(struct file *file, char __user *buffer, size_t buflen, loff_t *fpos) { char *buf = file->private_data; size_t phdrs_offset, notes_offset, data_offset; + size_t page_offline_frozen = 1; size_t phdrs_len, notes_len; struct kcore_list *m; size_t tsz; @@ -322,6 +323,11 @@ read_kcore(struct file *file, char __user *buffer, size_t buflen, loff_t *fpos) int ret = 0; down_read(&kclist_lock); + /* + * Don't race against drivers that set PageOffline() and expect no + * further page access. + */ + page_offline_freeze(); get_kcore_size(&nphdr, &phdrs_len, ¬es_len, &data_offset); phdrs_offset = sizeof(struct elfhdr); @@ -380,11 +386,8 @@ read_kcore(struct file *file, char __user *buffer, size_t buflen, loff_t *fpos) phdr->p_type = PT_LOAD; phdr->p_flags = PF_R | PF_W | PF_X; phdr->p_offset = kc_vaddr_to_offset(m->addr) + data_offset; - if (m->type == KCORE_REMAP) - phdr->p_vaddr = (size_t)m->vaddr; - else - phdr->p_vaddr = (size_t)m->addr; - if (m->type == KCORE_RAM || m->type == KCORE_REMAP) + phdr->p_vaddr = (size_t)m->addr; + if (m->type == KCORE_RAM) phdr->p_paddr = __pa(m->addr); else if (m->type == KCORE_TEXT) phdr->p_paddr = __pa_symbol(m->addr); @@ -468,6 +471,9 @@ read_kcore(struct file *file, char __user *buffer, size_t buflen, loff_t *fpos) m = NULL; while (buflen) { + struct page *page; + unsigned long pfn; + /* * If this is the first iteration or the address is not within * the previous entry, search for a matching entry. @@ -480,31 +486,57 @@ read_kcore(struct file *file, char __user *buffer, size_t buflen, loff_t *fpos) } } + if (page_offline_frozen++ % MAX_ORDER_NR_PAGES == 0) { + page_offline_thaw(); + cond_resched(); + page_offline_freeze(); + } + if (&m->list == &kclist_head) { if (clear_user(buffer, tsz)) { ret = -EFAULT; goto out; } m = NULL; /* skip the list anchor */ - } else if (!pfn_is_ram(__pa(start) >> PAGE_SHIFT)) { - if (clear_user(buffer, tsz)) { - ret = -EFAULT; - goto out; - } - } else if (m->type == KCORE_VMALLOC) { + goto skip; + } + + switch (m->type) { + case KCORE_VMALLOC: vread(buf, (char *)start, tsz); /* we have to zero-fill user buffer even if no read */ if (copy_to_user(buffer, buf, tsz)) { ret = -EFAULT; goto out; } - } else if (m->type == KCORE_USER) { + break; + case KCORE_USER: /* User page is handled prior to normal kernel page: */ if (copy_to_user(buffer, (char *)start, tsz)) { ret = -EFAULT; goto out; } - } else { + break; + case KCORE_RAM: + pfn = __pa(start) >> PAGE_SHIFT; + page = pfn_to_online_page(pfn); + + /* + * Don't read offline sections, logically offline pages + * (e.g., inflated in a balloon), hwpoisoned pages, + * and explicitly excluded physical ranges. + */ + if (!page || PageOffline(page) || + is_page_hwpoison(page) || !pfn_is_ram(pfn)) { + if (clear_user(buffer, tsz)) { + ret = -EFAULT; + goto out; + } + break; + } + fallthrough; + case KCORE_VMEMMAP: + case KCORE_TEXT: if (kern_addr_valid(start)) { /* * Using bounce buffer to bypass the @@ -528,7 +560,15 @@ read_kcore(struct file *file, char __user *buffer, size_t buflen, loff_t *fpos) goto out; } } + break; + default: + pr_warn_once("Unhandled KCORE type: %d\n", m->type); + if (clear_user(buffer, tsz)) { + ret = -EFAULT; + goto out; + } } +skip: buflen -= tsz; *fpos += tsz; buffer += tsz; @@ -537,6 +577,7 @@ read_kcore(struct file *file, char __user *buffer, size_t buflen, loff_t *fpos) } out: + page_offline_thaw(); up_read(&kclist_lock); if (ret) return ret; diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 66965ad88d8b..eb97468dfe4c 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -514,10 +514,8 @@ static void smaps_pte_entry(pte_t *pte, unsigned long addr, } else { mss->swap_pss += (u64)PAGE_SIZE << PSS_SHIFT; } - } else if (is_migration_entry(swpent)) - page = migration_entry_to_page(swpent); - else if (is_device_private_entry(swpent)) - page = device_private_entry_to_page(swpent); + } else if (is_pfn_swap_entry(swpent)) + page = pfn_swap_entry_to_page(swpent); } else if (unlikely(IS_ENABLED(CONFIG_SHMEM) && mss->check_shmem_swap && pte_none(*pte))) { page = xa_load(&vma->vm_file->f_mapping->i_pages, @@ -549,7 +547,7 @@ static void smaps_pmd_entry(pmd_t *pmd, unsigned long addr, swp_entry_t entry = pmd_to_swp_entry(*pmd); if (is_migration_entry(entry)) - page = migration_entry_to_page(entry); + page = pfn_swap_entry_to_page(entry); } if (IS_ERR_OR_NULL(page)) return; @@ -694,10 +692,8 @@ static int smaps_hugetlb_range(pte_t *pte, unsigned long hmask, } else if (is_swap_pte(*pte)) { swp_entry_t swpent = pte_to_swp_entry(*pte); - if (is_migration_entry(swpent)) - page = migration_entry_to_page(swpent); - else if (is_device_private_entry(swpent)) - page = device_private_entry_to_page(swpent); + if (is_pfn_swap_entry(swpent)) + page = pfn_swap_entry_to_page(swpent); } if (page) { int mapcount = page_mapcount(page); @@ -832,7 +828,7 @@ static int show_smap(struct seq_file *m, void *v) __show_smap(m, &mss, false); seq_printf(m, "THPeligible: %d\n", - transparent_hugepage_enabled(vma)); + transparent_hugepage_active(vma)); if (arch_pkeys_enabled()) seq_printf(m, "ProtectionKey: %8u\n", vma_pkey(vma)); @@ -1302,6 +1298,7 @@ struct pagemapread { #define PM_PFRAME_MASK GENMASK_ULL(PM_PFRAME_BITS - 1, 0) #define PM_SOFT_DIRTY BIT_ULL(55) #define PM_MMAP_EXCLUSIVE BIT_ULL(56) +#define PM_UFFD_WP BIT_ULL(57) #define PM_FILE BIT_ULL(61) #define PM_SWAP BIT_ULL(62) #define PM_PRESENT BIT_ULL(63) @@ -1375,20 +1372,21 @@ static pagemap_entry_t pte_to_pagemap_entry(struct pagemapread *pm, page = vm_normal_page(vma, addr, pte); if (pte_soft_dirty(pte)) flags |= PM_SOFT_DIRTY; + if (pte_uffd_wp(pte)) + flags |= PM_UFFD_WP; } else if (is_swap_pte(pte)) { swp_entry_t entry; if (pte_swp_soft_dirty(pte)) flags |= PM_SOFT_DIRTY; + if (pte_swp_uffd_wp(pte)) + flags |= PM_UFFD_WP; entry = pte_to_swp_entry(pte); if (pm->show_pfn) frame = swp_type(entry) | (swp_offset(entry) << MAX_SWAPFILES_SHIFT); flags |= PM_SWAP; - if (is_migration_entry(entry)) - page = migration_entry_to_page(entry); - - if (is_device_private_entry(entry)) - page = device_private_entry_to_page(entry); + if (is_pfn_swap_entry(entry)) + page = pfn_swap_entry_to_page(entry); } if (page && !PageAnon(page)) @@ -1426,6 +1424,8 @@ static int pagemap_pmd_range(pmd_t *pmdp, unsigned long addr, unsigned long end, flags |= PM_PRESENT; if (pmd_soft_dirty(pmd)) flags |= PM_SOFT_DIRTY; + if (pmd_uffd_wp(pmd)) + flags |= PM_UFFD_WP; if (pm->show_pfn) frame = pmd_pfn(pmd) + ((addr & ~PMD_MASK) >> PAGE_SHIFT); @@ -1444,8 +1444,10 @@ static int pagemap_pmd_range(pmd_t *pmdp, unsigned long addr, unsigned long end, flags |= PM_SWAP; if (pmd_swp_soft_dirty(pmd)) flags |= PM_SOFT_DIRTY; + if (pmd_swp_uffd_wp(pmd)) + flags |= PM_UFFD_WP; VM_BUG_ON(!is_pmd_migration_entry(pmd)); - page = migration_entry_to_page(entry); + page = pfn_swap_entry_to_page(entry); } #endif diff --git a/fs/seq_file.c b/fs/seq_file.c index 5059248f2d64..b117b212ef28 100644 --- a/fs/seq_file.c +++ b/fs/seq_file.c @@ -355,6 +355,31 @@ int seq_release(struct inode *inode, struct file *file) } EXPORT_SYMBOL(seq_release); +/** + * seq_escape_mem - print data into buffer, escaping some characters + * @m: target buffer + * @src: source buffer + * @len: size of source buffer + * @flags: flags to pass to string_escape_mem() + * @esc: set of characters that need escaping + * + * Puts data into buffer, replacing each occurrence of character from + * given class (defined by @flags and @esc) with printable escaped sequence. + * + * Use seq_has_overflowed() to check for errors. + */ +void seq_escape_mem(struct seq_file *m, const char *src, size_t len, + unsigned int flags, const char *esc) +{ + char *buf; + size_t size = seq_get_buf(m, &buf); + int ret; + + ret = string_escape_mem(src, len, buf, size, flags, esc); + seq_commit(m, ret < size ? ret : -1); +} +EXPORT_SYMBOL(seq_escape_mem); + /** * seq_escape - print string into buffer, escaping some characters * @m: target buffer @@ -367,26 +392,10 @@ EXPORT_SYMBOL(seq_release); */ void seq_escape(struct seq_file *m, const char *s, const char *esc) { - char *buf; - size_t size = seq_get_buf(m, &buf); - int ret; - - ret = string_escape_str(s, buf, size, ESCAPE_OCTAL, esc); - seq_commit(m, ret < size ? ret : -1); + seq_escape_str(m, s, ESCAPE_OCTAL, esc); } EXPORT_SYMBOL(seq_escape); -void seq_escape_mem_ascii(struct seq_file *m, const char *src, size_t isz) -{ - char *buf; - size_t size = seq_get_buf(m, &buf); - int ret; - - ret = string_escape_mem_ascii(src, isz, buf, size); - seq_commit(m, ret < size ? ret : -1); -} -EXPORT_SYMBOL(seq_escape_mem_ascii); - void seq_vprintf(struct seq_file *m, const char *f, va_list args) { int len; diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index dd7a6c62b56f..f6e0f0c0d0e5 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -1267,8 +1267,7 @@ static inline bool vma_can_userfault(struct vm_area_struct *vma, } if (vm_flags & VM_UFFD_MINOR) { - /* FIXME: Add minor fault interception for shmem. */ - if (!is_vm_hugetlb_page(vma)) + if (!(is_vm_hugetlb_page(vma) || vma_is_shmem(vma))) return false; } @@ -1304,8 +1303,12 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx, vm_flags = 0; if (uffdio_register.mode & UFFDIO_REGISTER_MODE_MISSING) vm_flags |= VM_UFFD_MISSING; - if (uffdio_register.mode & UFFDIO_REGISTER_MODE_WP) + if (uffdio_register.mode & UFFDIO_REGISTER_MODE_WP) { +#ifndef CONFIG_HAVE_ARCH_USERFAULTFD_WP + goto out; +#endif vm_flags |= VM_UFFD_WP; + } if (uffdio_register.mode & UFFDIO_REGISTER_MODE_MINOR) { #ifndef CONFIG_HAVE_ARCH_USERFAULTFD_MINOR goto out; @@ -1941,7 +1944,11 @@ static int userfaultfd_api(struct userfaultfd_ctx *ctx, /* report all available features and ioctls to userland */ uffdio_api.features = UFFD_API_FEATURES; #ifndef CONFIG_HAVE_ARCH_USERFAULTFD_MINOR - uffdio_api.features &= ~UFFD_FEATURE_MINOR_HUGETLBFS; + uffdio_api.features &= + ~(UFFD_FEATURE_MINOR_HUGETLBFS | UFFD_FEATURE_MINOR_SHMEM); +#endif +#ifndef CONFIG_HAVE_ARCH_USERFAULTFD_WP + uffdio_api.features &= ~UFFD_FEATURE_PAGEFAULT_FLAG_WP; #endif uffdio_api.ioctls = UFFD_API_IOCTLS; ret = -EFAULT; diff --git a/include/asm-generic/bug.h b/include/asm-generic/bug.h index bafc51f483c4..edb0e2a602a8 100644 --- a/include/asm-generic/bug.h +++ b/include/asm-generic/bug.h @@ -18,7 +18,8 @@ #endif #ifndef __ASSEMBLY__ -#include +#include +#include #ifdef CONFIG_BUG diff --git a/include/linux/ascii85.h b/include/linux/ascii85.h index 4cc40201273e..83ad775ad0aa 100644 --- a/include/linux/ascii85.h +++ b/include/linux/ascii85.h @@ -8,7 +8,8 @@ #ifndef _ASCII85_H_ #define _ASCII85_H_ -#include +#include +#include #define ASCII85_BUFSZ 6 diff --git a/include/linux/bootmem_info.h b/include/linux/bootmem_info.h new file mode 100644 index 000000000000..2bc8b1f69c93 --- /dev/null +++ b/include/linux/bootmem_info.h @@ -0,0 +1,66 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LINUX_BOOTMEM_INFO_H +#define __LINUX_BOOTMEM_INFO_H + +#include + +/* + * Types for free bootmem stored in page->lru.next. These have to be in + * some random range in unsigned long space for debugging purposes. + */ +enum { + MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE = 12, + SECTION_INFO = MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE, + MIX_SECTION_INFO, + NODE_INFO, + MEMORY_HOTPLUG_MAX_BOOTMEM_TYPE = NODE_INFO, +}; + +#ifdef CONFIG_HAVE_BOOTMEM_INFO_NODE +void __init register_page_bootmem_info_node(struct pglist_data *pgdat); + +void get_page_bootmem(unsigned long info, struct page *page, + unsigned long type); +void put_page_bootmem(struct page *page); + +/* + * Any memory allocated via the memblock allocator and not via the + * buddy will be marked reserved already in the memmap. For those + * pages, we can call this function to free it to buddy allocator. + */ +static inline void free_bootmem_page(struct page *page) +{ + unsigned long magic = (unsigned long)page->freelist; + + /* + * The reserve_bootmem_region sets the reserved flag on bootmem + * pages. + */ + VM_BUG_ON_PAGE(page_ref_count(page) != 2, page); + + if (magic == SECTION_INFO || magic == MIX_SECTION_INFO) + put_page_bootmem(page); + else + VM_BUG_ON_PAGE(1, page); +} +#else +static inline void register_page_bootmem_info_node(struct pglist_data *pgdat) +{ +} + +static inline void put_page_bootmem(struct page *page) +{ +} + +static inline void get_page_bootmem(unsigned long info, struct page *page, + unsigned long type) +{ +} + +static inline void free_bootmem_page(struct page *page) +{ + free_reserved_page(page); +} +#endif + +#endif /* __LINUX_BOOTMEM_INFO_H */ diff --git a/include/linux/compat.h b/include/linux/compat.h index 8855b1b702b2..c270124e4402 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -532,8 +532,6 @@ int __compat_save_altstack(compat_stack_t __user *, unsigned long); &__uss->ss_sp, label); \ unsafe_put_user(t->sas_ss_flags, &__uss->ss_flags, label); \ unsafe_put_user(t->sas_ss_size, &__uss->ss_size, label); \ - if (t->sas_ss_flags & SS_AUTODISARM) \ - sas_ss_reset(t); \ } while (0); /* diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h index adbe76b203e2..49b0ac8b6fd3 100644 --- a/include/linux/compiler-clang.h +++ b/include/linux/compiler-clang.h @@ -13,6 +13,12 @@ /* all clang versions usable with the kernel support KASAN ABI version 5 */ #define KASAN_ABI_VERSION 5 +/* + * Note: Checking __has_feature(*_sanitizer) is only true if the feature is + * enabled. Therefore it is not required to additionally check defined(CONFIG_*) + * to avoid adding redundant attributes in other configurations. + */ + #if __has_feature(address_sanitizer) || __has_feature(hwaddress_sanitizer) /* Emulate GCC's __SANITIZE_ADDRESS__ flag */ #define __SANITIZE_ADDRESS__ @@ -45,6 +51,17 @@ #define __no_sanitize_undefined #endif +/* + * Support for __has_feature(coverage_sanitizer) was added in Clang 13 together + * with no_sanitize("coverage"). Prior versions of Clang support coverage + * instrumentation, but cannot be queried for support by the preprocessor. + */ +#if __has_feature(coverage_sanitizer) +#define __no_sanitize_coverage __attribute__((no_sanitize("coverage"))) +#else +#define __no_sanitize_coverage +#endif + /* * Not all versions of clang implement the type-generic versions * of the builtin overflow checkers. Fortunately, clang implements diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index 5d97ef738a57..cb9217fc60af 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -122,6 +122,12 @@ #define __no_sanitize_undefined #endif +#if defined(CONFIG_KCOV) && __has_attribute(__no_sanitize_coverage__) +#define __no_sanitize_coverage __attribute__((no_sanitize_coverage)) +#else +#define __no_sanitize_coverage +#endif + #if GCC_VERSION >= 50100 #define COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW 1 #endif diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index d509169860f1..e4ea86fc584d 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -210,7 +210,7 @@ struct ftrace_likely_data { /* Section for code which can't be instrumented at all */ #define noinstr \ noinline notrace __attribute((__section__(".noinstr.text"))) \ - __no_kcsan __no_sanitize_address __no_profile + __no_kcsan __no_sanitize_address __no_profile __no_sanitize_coverage #endif /* __KERNEL__ */ diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 2a8ebe6c222e..f123e15d966e 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -10,8 +10,8 @@ vm_fault_t do_huge_pmd_anonymous_page(struct vm_fault *vmf); int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm, pmd_t *dst_pmd, pmd_t *src_pmd, unsigned long addr, - struct vm_area_struct *vma); -void huge_pmd_set_accessed(struct vm_fault *vmf, pmd_t orig_pmd); + struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma); +void huge_pmd_set_accessed(struct vm_fault *vmf); int copy_huge_pud(struct mm_struct *dst_mm, struct mm_struct *src_mm, pud_t *dst_pud, pud_t *src_pud, unsigned long addr, struct vm_area_struct *vma); @@ -24,7 +24,7 @@ static inline void huge_pud_set_accessed(struct vm_fault *vmf, pud_t orig_pud) } #endif -vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf, pmd_t orig_pmd); +vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf); struct page *follow_trans_huge_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd, unsigned int flags); @@ -115,9 +115,34 @@ extern struct kobj_attribute shmem_enabled_attr; extern unsigned long transparent_hugepage_flags; +static inline bool transhuge_vma_suitable(struct vm_area_struct *vma, + unsigned long haddr) +{ + /* Don't have to check pgoff for anonymous vma */ + if (!vma_is_anonymous(vma)) { + if (!IS_ALIGNED((vma->vm_start >> PAGE_SHIFT) - vma->vm_pgoff, + HPAGE_PMD_NR)) + return false; + } + + if (haddr < vma->vm_start || haddr + HPAGE_PMD_SIZE > vma->vm_end) + return false; + return true; +} + +static inline bool transhuge_vma_enabled(struct vm_area_struct *vma, + unsigned long vm_flags) +{ + /* Explicitly disabled through madvise. */ + if ((vm_flags & VM_NOHUGEPAGE) || + test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags)) + return false; + return true; +} + /* * to be used on vmas which are known to support THP. - * Use transparent_hugepage_enabled otherwise + * Use transparent_hugepage_active otherwise */ static inline bool __transparent_hugepage_enabled(struct vm_area_struct *vma) { @@ -128,15 +153,12 @@ static inline bool __transparent_hugepage_enabled(struct vm_area_struct *vma) if (transparent_hugepage_flags & (1 << TRANSPARENT_HUGEPAGE_NEVER_DAX)) return false; - if (vma->vm_flags & VM_NOHUGEPAGE) + if (!transhuge_vma_enabled(vma, vma->vm_flags)) return false; if (vma_is_temporary_stack(vma)) return false; - if (test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags)) - return false; - if (transparent_hugepage_flags & (1 << TRANSPARENT_HUGEPAGE_FLAG)) return true; @@ -150,24 +172,7 @@ static inline bool __transparent_hugepage_enabled(struct vm_area_struct *vma) return false; } -bool transparent_hugepage_enabled(struct vm_area_struct *vma); - -#define HPAGE_CACHE_INDEX_MASK (HPAGE_PMD_NR - 1) - -static inline bool transhuge_vma_suitable(struct vm_area_struct *vma, - unsigned long haddr) -{ - /* Don't have to check pgoff for anonymous vma */ - if (!vma_is_anonymous(vma)) { - if (((vma->vm_start >> PAGE_SHIFT) & HPAGE_CACHE_INDEX_MASK) != - (vma->vm_pgoff & HPAGE_CACHE_INDEX_MASK)) - return false; - } - - if (haddr < vma->vm_start || haddr + HPAGE_PMD_SIZE > vma->vm_end) - return false; - return true; -} +bool transparent_hugepage_active(struct vm_area_struct *vma); #define transparent_hugepage_use_zero_page() \ (transparent_hugepage_flags & \ @@ -283,7 +288,7 @@ struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr, struct page *follow_devmap_pud(struct vm_area_struct *vma, unsigned long addr, pud_t *pud, int flags, struct dev_pagemap **pgmap); -vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t orig_pmd); +vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf); extern struct page *huge_zero_page; extern unsigned long huge_zero_pfn; @@ -354,7 +359,7 @@ static inline bool __transparent_hugepage_enabled(struct vm_area_struct *vma) return false; } -static inline bool transparent_hugepage_enabled(struct vm_area_struct *vma) +static inline bool transparent_hugepage_active(struct vm_area_struct *vma) { return false; } @@ -365,6 +370,12 @@ static inline bool transhuge_vma_suitable(struct vm_area_struct *vma, return false; } +static inline bool transhuge_vma_enabled(struct vm_area_struct *vma, + unsigned long vm_flags) +{ + return false; +} + static inline void prep_transhuge_page(struct page *page) {} static inline bool is_transparent_hugepage(struct page *page) @@ -430,8 +441,7 @@ static inline spinlock_t *pud_trans_huge_lock(pud_t *pud, return NULL; } -static inline vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf, - pmd_t orig_pmd) +static inline vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf) { return 0; } diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 8ba79dc64ab8..8e0f32f935bd 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -29,6 +29,23 @@ typedef struct { unsigned long pd; } hugepd_t; #include #include +/* + * For HugeTLB page, there are more metadata to save in the struct page. But + * the head struct page cannot meet our needs, so we have to abuse other tail + * struct page to store the metadata. In order to avoid conflicts caused by + * subsequent use of more tail struct pages, we gather these discrete indexes + * of tail struct page here. + */ +enum { + SUBPAGE_INDEX_SUBPOOL = 1, /* reuse page->private */ +#ifdef CONFIG_CGROUP_HUGETLB + SUBPAGE_INDEX_CGROUP, /* reuse page->private */ + SUBPAGE_INDEX_CGROUP_RSVD, /* reuse page->private */ + __MAX_CGROUP_SUBPAGE_INDEX = SUBPAGE_INDEX_CGROUP_RSVD, +#endif + __NR_USED_SUBPAGE, +}; + struct hugepage_subpool { spinlock_t lock; long count; @@ -515,12 +532,14 @@ unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr, * modifications require hugetlb_lock. * HPG_freed - Set when page is on the free lists. * Synchronization: hugetlb_lock held for examination and modification. + * HPG_vmemmap_optimized - Set when the vmemmap pages of the page are freed. */ enum hugetlb_page_flags { HPG_restore_reserve = 0, HPG_migratable, HPG_temporary, HPG_freed, + HPG_vmemmap_optimized, __NR_HPAGEFLAGS, }; @@ -566,6 +585,7 @@ HPAGEFLAG(RestoreReserve, restore_reserve) HPAGEFLAG(Migratable, migratable) HPAGEFLAG(Temporary, temporary) HPAGEFLAG(Freed, freed) +HPAGEFLAG(VmemmapOptimized, vmemmap_optimized) #ifdef CONFIG_HUGETLB_PAGE @@ -588,6 +608,9 @@ struct hstate { unsigned int nr_huge_pages_node[MAX_NUMNODES]; unsigned int free_huge_pages_node[MAX_NUMNODES]; unsigned int surplus_huge_pages_node[MAX_NUMNODES]; +#ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP + unsigned int nr_free_vmemmap_pages; +#endif #ifdef CONFIG_CGROUP_HUGETLB /* cgroup control files */ struct cftype cgroup_files_dfl[7]; @@ -635,13 +658,13 @@ extern unsigned int default_hstate_idx; */ static inline struct hugepage_subpool *hugetlb_page_subpool(struct page *hpage) { - return (struct hugepage_subpool *)(hpage+1)->private; + return (void *)page_private(hpage + SUBPAGE_INDEX_SUBPOOL); } static inline void hugetlb_set_page_subpool(struct page *hpage, struct hugepage_subpool *subpool) { - set_page_private(hpage+1, (unsigned long)subpool); + set_page_private(hpage + SUBPAGE_INDEX_SUBPOOL, (unsigned long)subpool); } static inline struct hstate *hstate_file(struct file *f) @@ -718,8 +741,8 @@ static inline void arch_clear_hugepage_flags(struct page *page) { } #endif #ifndef arch_make_huge_pte -static inline pte_t arch_make_huge_pte(pte_t entry, struct vm_area_struct *vma, - struct page *page, int writable) +static inline pte_t arch_make_huge_pte(pte_t entry, unsigned int shift, + vm_flags_t flags) { return entry; } @@ -875,6 +898,11 @@ static inline void huge_ptep_modify_prot_commit(struct vm_area_struct *vma, #else /* CONFIG_HUGETLB_PAGE */ struct hstate {}; +static inline struct hugepage_subpool *hugetlb_page_subpool(struct page *hpage) +{ + return NULL; +} + static inline int isolate_or_dissolve_huge_page(struct page *page, struct list_head *list) { @@ -1028,6 +1056,12 @@ static inline void set_huge_swap_pte_at(struct mm_struct *mm, unsigned long addr } #endif /* CONFIG_HUGETLB_PAGE */ +#ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP +extern bool hugetlb_free_vmemmap_enabled; +#else +#define hugetlb_free_vmemmap_enabled false +#endif + static inline spinlock_t *huge_pte_lock(struct hstate *h, struct mm_struct *mm, pte_t *pte) { diff --git a/include/linux/hugetlb_cgroup.h b/include/linux/hugetlb_cgroup.h index 0bff345c4bc6..0b8d1fdda3a1 100644 --- a/include/linux/hugetlb_cgroup.h +++ b/include/linux/hugetlb_cgroup.h @@ -21,15 +21,16 @@ struct hugetlb_cgroup; struct resv_map; struct file_region; +#ifdef CONFIG_CGROUP_HUGETLB /* * Minimum page order trackable by hugetlb cgroup. * At least 4 pages are necessary for all the tracking information. - * The second tail page (hpage[2]) is the fault usage cgroup. - * The third tail page (hpage[3]) is the reservation usage cgroup. + * The second tail page (hpage[SUBPAGE_INDEX_CGROUP]) is the fault + * usage cgroup. The third tail page (hpage[SUBPAGE_INDEX_CGROUP_RSVD]) + * is the reservation usage cgroup. */ -#define HUGETLB_CGROUP_MIN_ORDER 2 +#define HUGETLB_CGROUP_MIN_ORDER order_base_2(__MAX_CGROUP_SUBPAGE_INDEX + 1) -#ifdef CONFIG_CGROUP_HUGETLB enum hugetlb_memory_event { HUGETLB_MAX, HUGETLB_NR_MEMORY_EVENTS, @@ -66,9 +67,9 @@ __hugetlb_cgroup_from_page(struct page *page, bool rsvd) if (compound_order(page) < HUGETLB_CGROUP_MIN_ORDER) return NULL; if (rsvd) - return (struct hugetlb_cgroup *)page[3].private; + return (void *)page_private(page + SUBPAGE_INDEX_CGROUP_RSVD); else - return (struct hugetlb_cgroup *)page[2].private; + return (void *)page_private(page + SUBPAGE_INDEX_CGROUP); } static inline struct hugetlb_cgroup *hugetlb_cgroup_from_page(struct page *page) @@ -90,9 +91,11 @@ static inline int __set_hugetlb_cgroup(struct page *page, if (compound_order(page) < HUGETLB_CGROUP_MIN_ORDER) return -1; if (rsvd) - page[3].private = (unsigned long)h_cg; + set_page_private(page + SUBPAGE_INDEX_CGROUP_RSVD, + (unsigned long)h_cg); else - page[2].private = (unsigned long)h_cg; + set_page_private(page + SUBPAGE_INDEX_CGROUP, + (unsigned long)h_cg); return 0; } diff --git a/include/linux/kcore.h b/include/linux/kcore.h index da676cdbd727..86c0f1d18998 100644 --- a/include/linux/kcore.h +++ b/include/linux/kcore.h @@ -11,14 +11,11 @@ enum kcore_type { KCORE_RAM, KCORE_VMEMMAP, KCORE_USER, - KCORE_OTHER, - KCORE_REMAP, }; struct kcore_list { struct list_head list; unsigned long addr; - unsigned long vaddr; size_t size; int type; }; diff --git a/include/linux/kernel.h b/include/linux/kernel.h index f2ad8a53f71f..1b2f0a7e00d6 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -10,10 +10,12 @@ #include #include #include +#include #include #include #include #include +#include #include #include #include @@ -84,7 +86,6 @@ #define lower_16_bits(n) ((u16)((n) & 0xffff)) struct completion; -struct pt_regs; struct user; #ifdef CONFIG_PREEMPT_VOLUNTARY @@ -189,159 +190,9 @@ void __might_fault(const char *file, int line); static inline void might_fault(void) { } #endif -extern struct atomic_notifier_head panic_notifier_list; -extern long (*panic_blink)(int state); -__printf(1, 2) -void panic(const char *fmt, ...) __noreturn __cold; -void nmi_panic(struct pt_regs *regs, const char *msg); -extern void oops_enter(void); -extern void oops_exit(void); -extern bool oops_may_print(void); void do_exit(long error_code) __noreturn; void complete_and_exit(struct completion *, long) __noreturn; -/* Internal, do not use. */ -int __must_check _kstrtoul(const char *s, unsigned int base, unsigned long *res); -int __must_check _kstrtol(const char *s, unsigned int base, long *res); - -int __must_check kstrtoull(const char *s, unsigned int base, unsigned long long *res); -int __must_check kstrtoll(const char *s, unsigned int base, long long *res); - -/** - * kstrtoul - convert a string to an unsigned long - * @s: The start of the string. The string must be null-terminated, and may also - * include a single newline before its terminating null. The first character - * may also be a plus sign, but not a minus sign. - * @base: The number base to use. The maximum supported base is 16. If base is - * given as 0, then the base of the string is automatically detected with the - * conventional semantics - If it begins with 0x the number will be parsed as a - * hexadecimal (case insensitive), if it otherwise begins with 0, it will be - * parsed as an octal number. Otherwise it will be parsed as a decimal. - * @res: Where to write the result of the conversion on success. - * - * Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error. - * Preferred over simple_strtoul(). Return code must be checked. -*/ -static inline int __must_check kstrtoul(const char *s, unsigned int base, unsigned long *res) -{ - /* - * We want to shortcut function call, but - * __builtin_types_compatible_p(unsigned long, unsigned long long) = 0. - */ - if (sizeof(unsigned long) == sizeof(unsigned long long) && - __alignof__(unsigned long) == __alignof__(unsigned long long)) - return kstrtoull(s, base, (unsigned long long *)res); - else - return _kstrtoul(s, base, res); -} - -/** - * kstrtol - convert a string to a long - * @s: The start of the string. The string must be null-terminated, and may also - * include a single newline before its terminating null. The first character - * may also be a plus sign or a minus sign. - * @base: The number base to use. The maximum supported base is 16. If base is - * given as 0, then the base of the string is automatically detected with the - * conventional semantics - If it begins with 0x the number will be parsed as a - * hexadecimal (case insensitive), if it otherwise begins with 0, it will be - * parsed as an octal number. Otherwise it will be parsed as a decimal. - * @res: Where to write the result of the conversion on success. - * - * Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error. - * Preferred over simple_strtol(). Return code must be checked. - */ -static inline int __must_check kstrtol(const char *s, unsigned int base, long *res) -{ - /* - * We want to shortcut function call, but - * __builtin_types_compatible_p(long, long long) = 0. - */ - if (sizeof(long) == sizeof(long long) && - __alignof__(long) == __alignof__(long long)) - return kstrtoll(s, base, (long long *)res); - else - return _kstrtol(s, base, res); -} - -int __must_check kstrtouint(const char *s, unsigned int base, unsigned int *res); -int __must_check kstrtoint(const char *s, unsigned int base, int *res); - -static inline int __must_check kstrtou64(const char *s, unsigned int base, u64 *res) -{ - return kstrtoull(s, base, res); -} - -static inline int __must_check kstrtos64(const char *s, unsigned int base, s64 *res) -{ - return kstrtoll(s, base, res); -} - -static inline int __must_check kstrtou32(const char *s, unsigned int base, u32 *res) -{ - return kstrtouint(s, base, res); -} - -static inline int __must_check kstrtos32(const char *s, unsigned int base, s32 *res) -{ - return kstrtoint(s, base, res); -} - -int __must_check kstrtou16(const char *s, unsigned int base, u16 *res); -int __must_check kstrtos16(const char *s, unsigned int base, s16 *res); -int __must_check kstrtou8(const char *s, unsigned int base, u8 *res); -int __must_check kstrtos8(const char *s, unsigned int base, s8 *res); -int __must_check kstrtobool(const char *s, bool *res); - -int __must_check kstrtoull_from_user(const char __user *s, size_t count, unsigned int base, unsigned long long *res); -int __must_check kstrtoll_from_user(const char __user *s, size_t count, unsigned int base, long long *res); -int __must_check kstrtoul_from_user(const char __user *s, size_t count, unsigned int base, unsigned long *res); -int __must_check kstrtol_from_user(const char __user *s, size_t count, unsigned int base, long *res); -int __must_check kstrtouint_from_user(const char __user *s, size_t count, unsigned int base, unsigned int *res); -int __must_check kstrtoint_from_user(const char __user *s, size_t count, unsigned int base, int *res); -int __must_check kstrtou16_from_user(const char __user *s, size_t count, unsigned int base, u16 *res); -int __must_check kstrtos16_from_user(const char __user *s, size_t count, unsigned int base, s16 *res); -int __must_check kstrtou8_from_user(const char __user *s, size_t count, unsigned int base, u8 *res); -int __must_check kstrtos8_from_user(const char __user *s, size_t count, unsigned int base, s8 *res); -int __must_check kstrtobool_from_user(const char __user *s, size_t count, bool *res); - -static inline int __must_check kstrtou64_from_user(const char __user *s, size_t count, unsigned int base, u64 *res) -{ - return kstrtoull_from_user(s, count, base, res); -} - -static inline int __must_check kstrtos64_from_user(const char __user *s, size_t count, unsigned int base, s64 *res) -{ - return kstrtoll_from_user(s, count, base, res); -} - -static inline int __must_check kstrtou32_from_user(const char __user *s, size_t count, unsigned int base, u32 *res) -{ - return kstrtouint_from_user(s, count, base, res); -} - -static inline int __must_check kstrtos32_from_user(const char __user *s, size_t count, unsigned int base, s32 *res) -{ - return kstrtoint_from_user(s, count, base, res); -} - -/* - * Use kstrto instead. - * - * NOTE: simple_strto does not check for the range overflow and, - * depending on the input, may give interesting results. - * - * Use these functions if and only if you cannot use kstrto, because - * the conversion ends on the first non-digit character, which may be far - * beyond the supported range. It might be useful to parse the strings like - * 10x50 or 12:21 without altering original string or temporary buffer in use. - * Keep in mind above caveat. - */ - -extern unsigned long simple_strtoul(const char *,char **,unsigned int); -extern long simple_strtol(const char *,char **,unsigned int); -extern unsigned long long simple_strtoull(const char *,char **,unsigned int); -extern long long simple_strtoll(const char *,char **,unsigned int); - extern int num_to_str(char *buf, int size, unsigned long long num, unsigned int width); @@ -384,52 +235,8 @@ extern int __kernel_text_address(unsigned long addr); extern int kernel_text_address(unsigned long addr); extern int func_ptr_is_kernel_text(void *ptr); -#ifdef CONFIG_SMP -extern unsigned int sysctl_oops_all_cpu_backtrace; -#else -#define sysctl_oops_all_cpu_backtrace 0 -#endif /* CONFIG_SMP */ - extern void bust_spinlocks(int yes); -extern int panic_timeout; -extern unsigned long panic_print; -extern int panic_on_oops; -extern int panic_on_unrecovered_nmi; -extern int panic_on_io_nmi; -extern int panic_on_warn; -extern unsigned long panic_on_taint; -extern bool panic_on_taint_nousertaint; -extern int sysctl_panic_on_rcu_stall; -extern int sysctl_max_rcu_stall_to_panic; -extern int sysctl_panic_on_stackoverflow; -extern bool crash_kexec_post_notifiers; - -/* - * panic_cpu is used for synchronizing panic() and crash_kexec() execution. It - * holds a CPU number which is executing panic() currently. A value of - * PANIC_CPU_INVALID means no CPU has entered panic() or crash_kexec(). - */ -extern atomic_t panic_cpu; -#define PANIC_CPU_INVALID -1 - -/* - * Only to be used by arch init code. If the user over-wrote the default - * CONFIG_PANIC_TIMEOUT, honor it. - */ -static inline void set_arch_panic_timeout(int timeout, int arch_default_timeout) -{ - if (panic_timeout == arch_default_timeout) - panic_timeout = timeout; -} -extern const char *print_tainted(void); -enum lockdep_ok { - LOCKDEP_STILL_OK, - LOCKDEP_NOW_UNRELIABLE -}; -extern void add_taint(unsigned flag, enum lockdep_ok); -extern int test_taint(unsigned flag); -extern unsigned long get_taint(void); extern int root_mountflags; extern bool early_boot_irqs_disabled; @@ -448,36 +255,6 @@ extern enum system_states { SYSTEM_SUSPEND, } system_state; -/* This cannot be an enum because some may be used in assembly source. */ -#define TAINT_PROPRIETARY_MODULE 0 -#define TAINT_FORCED_MODULE 1 -#define TAINT_CPU_OUT_OF_SPEC 2 -#define TAINT_FORCED_RMMOD 3 -#define TAINT_MACHINE_CHECK 4 -#define TAINT_BAD_PAGE 5 -#define TAINT_USER 6 -#define TAINT_DIE 7 -#define TAINT_OVERRIDDEN_ACPI_TABLE 8 -#define TAINT_WARN 9 -#define TAINT_CRAP 10 -#define TAINT_FIRMWARE_WORKAROUND 11 -#define TAINT_OOT_MODULE 12 -#define TAINT_UNSIGNED_MODULE 13 -#define TAINT_SOFTLOCKUP 14 -#define TAINT_LIVEPATCH 15 -#define TAINT_AUX 16 -#define TAINT_RANDSTRUCT 17 -#define TAINT_FLAGS_COUNT 18 -#define TAINT_FLAGS_MAX ((1UL << TAINT_FLAGS_COUNT) - 1) - -struct taint_flag { - char c_true; /* character printed when tainted */ - char c_false; /* character printed when not tainted */ - bool module; /* also show as a per-module taint flag */ -}; - -extern const struct taint_flag taint_flags[TAINT_FLAGS_COUNT]; - extern const char hex_asc[]; #define hex_asc_lo(x) hex_asc[((x) & 0x0f)] #define hex_asc_hi(x) hex_asc[((x) & 0xf0) >> 4] diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index 523ffc7bc3a8..4d0c28c2ba12 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -399,7 +399,6 @@ int enable_kprobe(struct kprobe *kp); void dump_kprobe(struct kprobe *kp); void *alloc_insn_page(void); -void free_insn_page(void *page); int kprobe_get_kallsym(unsigned int symnum, unsigned long *value, char *type, char *sym); diff --git a/include/linux/kstrtox.h b/include/linux/kstrtox.h new file mode 100644 index 000000000000..529974e22ea7 --- /dev/null +++ b/include/linux/kstrtox.h @@ -0,0 +1,155 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_KSTRTOX_H +#define _LINUX_KSTRTOX_H + +#include +#include + +/* Internal, do not use. */ +int __must_check _kstrtoul(const char *s, unsigned int base, unsigned long *res); +int __must_check _kstrtol(const char *s, unsigned int base, long *res); + +int __must_check kstrtoull(const char *s, unsigned int base, unsigned long long *res); +int __must_check kstrtoll(const char *s, unsigned int base, long long *res); + +/** + * kstrtoul - convert a string to an unsigned long + * @s: The start of the string. The string must be null-terminated, and may also + * include a single newline before its terminating null. The first character + * may also be a plus sign, but not a minus sign. + * @base: The number base to use. The maximum supported base is 16. If base is + * given as 0, then the base of the string is automatically detected with the + * conventional semantics - If it begins with 0x the number will be parsed as a + * hexadecimal (case insensitive), if it otherwise begins with 0, it will be + * parsed as an octal number. Otherwise it will be parsed as a decimal. + * @res: Where to write the result of the conversion on success. + * + * Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error. + * Preferred over simple_strtoul(). Return code must be checked. +*/ +static inline int __must_check kstrtoul(const char *s, unsigned int base, unsigned long *res) +{ + /* + * We want to shortcut function call, but + * __builtin_types_compatible_p(unsigned long, unsigned long long) = 0. + */ + if (sizeof(unsigned long) == sizeof(unsigned long long) && + __alignof__(unsigned long) == __alignof__(unsigned long long)) + return kstrtoull(s, base, (unsigned long long *)res); + else + return _kstrtoul(s, base, res); +} + +/** + * kstrtol - convert a string to a long + * @s: The start of the string. The string must be null-terminated, and may also + * include a single newline before its terminating null. The first character + * may also be a plus sign or a minus sign. + * @base: The number base to use. The maximum supported base is 16. If base is + * given as 0, then the base of the string is automatically detected with the + * conventional semantics - If it begins with 0x the number will be parsed as a + * hexadecimal (case insensitive), if it otherwise begins with 0, it will be + * parsed as an octal number. Otherwise it will be parsed as a decimal. + * @res: Where to write the result of the conversion on success. + * + * Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error. + * Preferred over simple_strtol(). Return code must be checked. + */ +static inline int __must_check kstrtol(const char *s, unsigned int base, long *res) +{ + /* + * We want to shortcut function call, but + * __builtin_types_compatible_p(long, long long) = 0. + */ + if (sizeof(long) == sizeof(long long) && + __alignof__(long) == __alignof__(long long)) + return kstrtoll(s, base, (long long *)res); + else + return _kstrtol(s, base, res); +} + +int __must_check kstrtouint(const char *s, unsigned int base, unsigned int *res); +int __must_check kstrtoint(const char *s, unsigned int base, int *res); + +static inline int __must_check kstrtou64(const char *s, unsigned int base, u64 *res) +{ + return kstrtoull(s, base, res); +} + +static inline int __must_check kstrtos64(const char *s, unsigned int base, s64 *res) +{ + return kstrtoll(s, base, res); +} + +static inline int __must_check kstrtou32(const char *s, unsigned int base, u32 *res) +{ + return kstrtouint(s, base, res); +} + +static inline int __must_check kstrtos32(const char *s, unsigned int base, s32 *res) +{ + return kstrtoint(s, base, res); +} + +int __must_check kstrtou16(const char *s, unsigned int base, u16 *res); +int __must_check kstrtos16(const char *s, unsigned int base, s16 *res); +int __must_check kstrtou8(const char *s, unsigned int base, u8 *res); +int __must_check kstrtos8(const char *s, unsigned int base, s8 *res); +int __must_check kstrtobool(const char *s, bool *res); + +int __must_check kstrtoull_from_user(const char __user *s, size_t count, unsigned int base, unsigned long long *res); +int __must_check kstrtoll_from_user(const char __user *s, size_t count, unsigned int base, long long *res); +int __must_check kstrtoul_from_user(const char __user *s, size_t count, unsigned int base, unsigned long *res); +int __must_check kstrtol_from_user(const char __user *s, size_t count, unsigned int base, long *res); +int __must_check kstrtouint_from_user(const char __user *s, size_t count, unsigned int base, unsigned int *res); +int __must_check kstrtoint_from_user(const char __user *s, size_t count, unsigned int base, int *res); +int __must_check kstrtou16_from_user(const char __user *s, size_t count, unsigned int base, u16 *res); +int __must_check kstrtos16_from_user(const char __user *s, size_t count, unsigned int base, s16 *res); +int __must_check kstrtou8_from_user(const char __user *s, size_t count, unsigned int base, u8 *res); +int __must_check kstrtos8_from_user(const char __user *s, size_t count, unsigned int base, s8 *res); +int __must_check kstrtobool_from_user(const char __user *s, size_t count, bool *res); + +static inline int __must_check kstrtou64_from_user(const char __user *s, size_t count, unsigned int base, u64 *res) +{ + return kstrtoull_from_user(s, count, base, res); +} + +static inline int __must_check kstrtos64_from_user(const char __user *s, size_t count, unsigned int base, s64 *res) +{ + return kstrtoll_from_user(s, count, base, res); +} + +static inline int __must_check kstrtou32_from_user(const char __user *s, size_t count, unsigned int base, u32 *res) +{ + return kstrtouint_from_user(s, count, base, res); +} + +static inline int __must_check kstrtos32_from_user(const char __user *s, size_t count, unsigned int base, s32 *res) +{ + return kstrtoint_from_user(s, count, base, res); +} + +/* + * Use kstrto instead. + * + * NOTE: simple_strto does not check for the range overflow and, + * depending on the input, may give interesting results. + * + * Use these functions if and only if you cannot use kstrto, because + * the conversion ends on the first non-digit character, which may be far + * beyond the supported range. It might be useful to parse the strings like + * 10x50 or 12:21 without altering original string or temporary buffer in use. + * Keep in mind above caveat. + */ + +extern unsigned long simple_strtoul(const char *,char **,unsigned int); +extern long simple_strtol(const char *,char **,unsigned int); +extern unsigned long long simple_strtoull(const char *,char **,unsigned int); +extern long long simple_strtoll(const char *,char **,unsigned int); + +static inline int strtobool(const char *s, bool *res) +{ + return kstrtobool(s, res); +} + +#endif /* _LINUX_KSTRTOX_H */ diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 552309342c38..cbf46f56d105 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -30,7 +30,9 @@ extern unsigned long long max_possible_pfn; * @MEMBLOCK_NONE: no special request * @MEMBLOCK_HOTPLUG: hotpluggable region * @MEMBLOCK_MIRROR: mirrored region - * @MEMBLOCK_NOMAP: don't add to kernel direct mapping + * @MEMBLOCK_NOMAP: don't add to kernel direct mapping and treat as + * reserved in the memory map; refer to memblock_mark_nomap() description + * for further details */ enum memblock_flags { MEMBLOCK_NONE = 0x0, /* No special request */ diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 28f32fd00fe9..a7fd2c3ccb77 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -18,18 +18,6 @@ struct vmem_altmap; #ifdef CONFIG_MEMORY_HOTPLUG struct page *pfn_to_online_page(unsigned long pfn); -/* - * Types for free bootmem stored in page->lru.next. These have to be in - * some random range in unsigned long space for debugging purposes. - */ -enum { - MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE = 12, - SECTION_INFO = MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE, - MIX_SECTION_INFO, - NODE_INFO, - MEMORY_HOTPLUG_MAX_BOOTMEM_TYPE = NODE_INFO, -}; - /* Types for control the zone type of onlined and offlined memory */ enum { /* Offline the memory. */ @@ -222,17 +210,6 @@ static inline void arch_refresh_nodedata(int nid, pg_data_t *pgdat) #endif /* CONFIG_NUMA */ #endif /* CONFIG_HAVE_ARCH_NODEDATA_EXTENSION */ -#ifdef CONFIG_HAVE_BOOTMEM_INFO_NODE -extern void __init register_page_bootmem_info_node(struct pglist_data *pgdat); -#else -static inline void register_page_bootmem_info_node(struct pglist_data *pgdat) -{ -} -#endif -extern void put_page_bootmem(struct page *page); -extern void get_page_bootmem(unsigned long ingo, struct page *page, - unsigned long type); - void get_online_mems(void); void put_online_mems(void); @@ -260,10 +237,6 @@ static inline void zone_span_writelock(struct zone *zone) {} static inline void zone_span_writeunlock(struct zone *zone) {} static inline void zone_seqlock_init(struct zone *zone) {} -static inline void register_page_bootmem_info_node(struct pglist_data *pgdat) -{ -} - static inline int try_online_node(int nid) { return 0; diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h index 5f1c74df264d..0aaf91b496e2 100644 --- a/include/linux/mempolicy.h +++ b/include/linux/mempolicy.h @@ -46,11 +46,8 @@ struct mempolicy { atomic_t refcnt; unsigned short mode; /* See MPOL_* above */ unsigned short flags; /* See set_mempolicy() MPOL_F_* above */ - union { - short preferred_node; /* preferred */ - nodemask_t nodes; /* interleave/bind */ - /* undefined for default */ - } v; + nodemask_t nodes; /* interleave/bind/perfer */ + union { nodemask_t cpuset_mems_allowed; /* relative to these nodes */ nodemask_t user_nodemask; /* nodemask passed by user */ @@ -150,7 +147,7 @@ extern int huge_node(struct vm_area_struct *vma, unsigned long addr, gfp_t gfp_flags, struct mempolicy **mpol, nodemask_t **nodemask); extern bool init_nodemask_of_mempolicy(nodemask_t *mask); -extern bool mempolicy_nodemask_intersects(struct task_struct *tsk, +extern bool mempolicy_in_oom_domain(struct task_struct *tsk, const nodemask_t *mask); extern nodemask_t *policy_nodemask(gfp_t gfp, struct mempolicy *policy); diff --git a/include/linux/memremap.h b/include/linux/memremap.h index 45a79da89c5f..c0e9d35889e8 100644 --- a/include/linux/memremap.h +++ b/include/linux/memremap.h @@ -26,7 +26,7 @@ struct vmem_altmap { }; /* - * Specialize ZONE_DEVICE memory into multiple types each having differents + * Specialize ZONE_DEVICE memory into multiple types each has a different * usage. * * MEMORY_DEVICE_PRIVATE: diff --git a/include/linux/migrate.h b/include/linux/migrate.h index 4bb4e519e3f5..9b7b7cd3bae9 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -51,6 +51,7 @@ extern int migrate_huge_page_move_mapping(struct address_space *mapping, struct page *newpage, struct page *page); extern int migrate_page_move_mapping(struct address_space *mapping, struct page *newpage, struct page *page, int extra_count); +extern void copy_huge_page(struct page *dst, struct page *src); #else static inline void putback_movable_pages(struct list_head *l) {} @@ -77,6 +78,9 @@ static inline int migrate_huge_page_move_mapping(struct address_space *mapping, return -ENOSYS; } +static inline void copy_huge_page(struct page *dst, struct page *src) +{ +} #endif /* CONFIG_MIGRATION */ #ifdef CONFIG_COMPACTION @@ -95,14 +99,9 @@ static inline void __ClearPageMovable(struct page *page) #endif #ifdef CONFIG_NUMA_BALANCING -extern bool pmd_trans_migrating(pmd_t pmd); extern int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma, int node); #else -static inline bool pmd_trans_migrating(pmd_t pmd) -{ - return false; -} static inline int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma, int node) { @@ -110,24 +109,6 @@ static inline int migrate_misplaced_page(struct page *page, } #endif /* CONFIG_NUMA_BALANCING */ -#if defined(CONFIG_NUMA_BALANCING) && defined(CONFIG_TRANSPARENT_HUGEPAGE) -extern int migrate_misplaced_transhuge_page(struct mm_struct *mm, - struct vm_area_struct *vma, - pmd_t *pmd, pmd_t entry, - unsigned long address, - struct page *page, int node); -#else -static inline int migrate_misplaced_transhuge_page(struct mm_struct *mm, - struct vm_area_struct *vma, - pmd_t *pmd, pmd_t entry, - unsigned long address, - struct page *page, int node) -{ - return -EAGAIN; -} -#endif /* CONFIG_NUMA_BALANCING && CONFIG_TRANSPARENT_HUGEPAGE*/ - - #ifdef CONFIG_MIGRATION /* diff --git a/include/linux/mm.h b/include/linux/mm.h index b8bc39237dac..788a0b1323d0 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -145,7 +145,7 @@ extern int mmap_rnd_compat_bits __read_mostly; /* This function must be updated when the size of struct page grows above 80 * or reduces below 56. The idea that compiler optimizes out switch() * statement, and only leaves move/store instructions. Also the compiler can - * combine write statments if they are both assignments and can be reordered, + * combine write statements if they are both assignments and can be reordered, * this can result in several of the writes here being dropped. */ #define mm_zero_struct_page(pp) __mm_zero_struct_page(pp) @@ -540,7 +540,12 @@ struct vm_fault { pud_t *pud; /* Pointer to pud entry matching * the 'address' */ - pte_t orig_pte; /* Value of PTE at the time of fault */ + union { + pte_t orig_pte; /* Value of PTE at the time of fault */ + pmd_t orig_pmd; /* Value of PMD at the time of fault, + * used by PMD fault only. + */ + }; struct page *cow_page; /* Page handler may use for COW fault */ struct page *page; /* ->fault handlers should return a @@ -3067,6 +3072,11 @@ static inline void print_vma_addr(char *prefix, unsigned long rip) } #endif +int vmemmap_remap_free(unsigned long start, unsigned long end, + unsigned long reuse); +int vmemmap_remap_alloc(unsigned long start, unsigned long end, + unsigned long reuse, gfp_t gfp_mask); + void *sparse_buffer_alloc(unsigned long size); struct page * __populate_section_memmap(unsigned long pfn, unsigned long nr_pages, int nid, struct vmem_altmap *altmap); diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index d33d97c69da9..52bbd2b7cb46 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -404,7 +404,7 @@ struct mm_struct { unsigned long mmap_base; /* base of mmap area */ unsigned long mmap_legacy_base; /* base of mmap area in bottom-up allocations */ #ifdef CONFIG_HAVE_ARCH_COMPAT_MMAP_BASES - /* Base adresses for compatible mmap() */ + /* Base addresses for compatible mmap() */ unsigned long mmap_compat_base; unsigned long mmap_compat_legacy_base; #endif diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h index 1a6a9eb6d3fa..6692da8d121d 100644 --- a/include/linux/mmu_notifier.h +++ b/include/linux/mmu_notifier.h @@ -41,7 +41,12 @@ struct mmu_interval_notifier; * * @MMU_NOTIFY_MIGRATE: used during migrate_vma_collect() invalidate to signal * a device driver to possibly ignore the invalidation if the - * migrate_pgmap_owner field matches the driver's device private pgmap owner. + * owner field matches the driver's device private pgmap owner. + * + * @MMU_NOTIFY_EXCLUSIVE: to signal a device driver that the device will no + * longer have exclusive access to the page. When sent during creation of an + * exclusive range the owner will be initialised to the value provided by the + * caller of make_device_exclusive_range(), otherwise the owner will be NULL. */ enum mmu_notifier_event { MMU_NOTIFY_UNMAP = 0, @@ -51,6 +56,7 @@ enum mmu_notifier_event { MMU_NOTIFY_SOFT_DIRTY, MMU_NOTIFY_RELEASE, MMU_NOTIFY_MIGRATE, + MMU_NOTIFY_EXCLUSIVE, }; #define MMU_NOTIFIER_RANGE_BLOCKABLE (1 << 0) @@ -269,7 +275,7 @@ struct mmu_notifier_range { unsigned long end; unsigned flags; enum mmu_notifier_event event; - void *migrate_pgmap_owner; + void *owner; }; static inline int mm_has_notifiers(struct mm_struct *mm) @@ -521,14 +527,14 @@ static inline void mmu_notifier_range_init(struct mmu_notifier_range *range, range->flags = flags; } -static inline void mmu_notifier_range_init_migrate( - struct mmu_notifier_range *range, unsigned int flags, +static inline void mmu_notifier_range_init_owner( + struct mmu_notifier_range *range, + enum mmu_notifier_event event, unsigned int flags, struct vm_area_struct *vma, struct mm_struct *mm, - unsigned long start, unsigned long end, void *pgmap) + unsigned long start, unsigned long end, void *owner) { - mmu_notifier_range_init(range, MMU_NOTIFY_MIGRATE, flags, vma, mm, - start, end); - range->migrate_pgmap_owner = pgmap; + mmu_notifier_range_init(range, event, flags, vma, mm, start, end); + range->owner = owner; } #define ptep_clear_flush_young_notify(__vma, __address, __ptep) \ @@ -655,8 +661,8 @@ static inline void _mmu_notifier_range_init(struct mmu_notifier_range *range, #define mmu_notifier_range_init(range,event,flags,vma,mm,start,end) \ _mmu_notifier_range_init(range, start, end) -#define mmu_notifier_range_init_migrate(range, flags, vma, mm, start, end, \ - pgmap) \ +#define mmu_notifier_range_init_owner(range, event, flags, vma, mm, start, \ + end, owner) \ _mmu_notifier_range_init(range, start, end) static inline bool diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 265a32e1ff74..fcb535560028 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -114,7 +114,7 @@ static inline bool free_area_empty(struct free_area *area, int migratetype) struct pglist_data; /* - * Add a wild amount of padding here to ensure datas fall into separate + * Add a wild amount of padding here to ensure data fall into separate * cachelines. There are very few zone structures in the machine, so space * consumption is not a concern here. */ @@ -1064,7 +1064,10 @@ extern char numa_zonelist_order[]; #ifndef CONFIG_NUMA extern struct pglist_data contig_page_data; -#define NODE_DATA(nid) (&contig_page_data) +static inline struct pglist_data *NODE_DATA(int nid) +{ + return &contig_page_data; +} #define NODE_MEM_MAP(nid) mem_map #else /* CONFIG_NUMA */ @@ -1445,10 +1448,30 @@ static inline int pfn_section_valid(struct mem_section *ms, unsigned long pfn) #endif #ifndef CONFIG_HAVE_ARCH_PFN_VALID +/** + * pfn_valid - check if there is a valid memory map entry for a PFN + * @pfn: the page frame number to check + * + * Check if there is a valid memory map entry aka struct page for the @pfn. + * Note, that availability of the memory map entry does not imply that + * there is actual usable memory at that @pfn. The struct page may + * represent a hole or an unusable page frame. + * + * Return: 1 for PFNs that have memory map entries and 0 otherwise + */ static inline int pfn_valid(unsigned long pfn) { struct mem_section *ms; + /* + * Ensure the upper PAGE_SHIFT bits are clear in the + * pfn. Else it might lead to false positives when + * some of the upper bits are set, but the lower bits + * match a valid pfn. + */ + if (PHYS_PFN(PFN_PHYS(pfn)) != pfn) + return 0; + if (pfn_to_section_nr(pfn) >= NR_MEM_SECTIONS) return 0; ms = __nr_to_section(pfn_to_section_nr(pfn)); diff --git a/include/linux/mpi.h b/include/linux/mpi.h index 3e5358f4de2f..eb0d1c1db208 100644 --- a/include/linux/mpi.h +++ b/include/linux/mpi.h @@ -200,7 +200,7 @@ struct mpi_ec_ctx { unsigned int nbits; /* Number of bits. */ /* Domain parameters. Note that they may not all be set and if set - * the MPIs may be flaged as constant. + * the MPIs may be flagged as constant. */ MPI p; /* Prime specifying the field GF(p). */ MPI a; /* First coefficient of the Weierstrass equation. */ @@ -267,7 +267,7 @@ int mpi_ec_curve_point(MPI_POINT point, struct mpi_ec_ctx *ctx); /** * mpi_get_size() - returns max size required to store the number * - * @a: A multi precision integer for which we want to allocate a bufer + * @a: A multi precision integer for which we want to allocate a buffer * * Return: size required to store the number */ diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 458696550028..5922031ffab6 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -703,6 +703,18 @@ PAGEFLAG_FALSE(DoubleMap) TESTSCFLAG_FALSE(DoubleMap) #endif +/* + * Check if a page is currently marked HWPoisoned. Note that this check is + * best effort only and inherently racy: there is no way to synchronize with + * failing hardware. + */ +static inline bool is_page_hwpoison(struct page *page) +{ + if (PageHWPoison(page)) + return true; + return PageHuge(page) && PageHWPoison(compound_head(page)); +} + /* * For pages that are never mapped to userspace (and aren't PageSlab), * page_type may be used. Because it is initialised to -1, we invert the @@ -766,9 +778,19 @@ PAGE_TYPE_OPS(Buddy, buddy) * relies on this feature is aware that re-onlining the memory block will * require to re-set the pages PageOffline() and not giving them to the * buddy via online_page_callback_t. + * + * There are drivers that mark a page PageOffline() and expect there won't be + * any further access to page content. PFN walkers that read content of random + * pages should check PageOffline() and synchronize with such drivers using + * page_offline_freeze()/page_offline_thaw(). */ PAGE_TYPE_OPS(Offline, offline) +extern void page_offline_freeze(void); +extern void page_offline_thaw(void); +extern void page_offline_begin(void); +extern void page_offline_end(void); + /* * Marks pages in use as page tables. */ diff --git a/include/linux/panic.h b/include/linux/panic.h new file mode 100644 index 000000000000..f5844908a089 --- /dev/null +++ b/include/linux/panic.h @@ -0,0 +1,98 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_PANIC_H +#define _LINUX_PANIC_H + +#include +#include + +struct pt_regs; + +extern long (*panic_blink)(int state); +__printf(1, 2) +void panic(const char *fmt, ...) __noreturn __cold; +void nmi_panic(struct pt_regs *regs, const char *msg); +extern void oops_enter(void); +extern void oops_exit(void); +extern bool oops_may_print(void); + +#ifdef CONFIG_SMP +extern unsigned int sysctl_oops_all_cpu_backtrace; +#else +#define sysctl_oops_all_cpu_backtrace 0 +#endif /* CONFIG_SMP */ + +extern int panic_timeout; +extern unsigned long panic_print; +extern int panic_on_oops; +extern int panic_on_unrecovered_nmi; +extern int panic_on_io_nmi; +extern int panic_on_warn; + +extern unsigned long panic_on_taint; +extern bool panic_on_taint_nousertaint; + +extern int sysctl_panic_on_rcu_stall; +extern int sysctl_max_rcu_stall_to_panic; +extern int sysctl_panic_on_stackoverflow; + +extern bool crash_kexec_post_notifiers; + +/* + * panic_cpu is used for synchronizing panic() and crash_kexec() execution. It + * holds a CPU number which is executing panic() currently. A value of + * PANIC_CPU_INVALID means no CPU has entered panic() or crash_kexec(). + */ +extern atomic_t panic_cpu; +#define PANIC_CPU_INVALID -1 + +/* + * Only to be used by arch init code. If the user over-wrote the default + * CONFIG_PANIC_TIMEOUT, honor it. + */ +static inline void set_arch_panic_timeout(int timeout, int arch_default_timeout) +{ + if (panic_timeout == arch_default_timeout) + panic_timeout = timeout; +} + +/* This cannot be an enum because some may be used in assembly source. */ +#define TAINT_PROPRIETARY_MODULE 0 +#define TAINT_FORCED_MODULE 1 +#define TAINT_CPU_OUT_OF_SPEC 2 +#define TAINT_FORCED_RMMOD 3 +#define TAINT_MACHINE_CHECK 4 +#define TAINT_BAD_PAGE 5 +#define TAINT_USER 6 +#define TAINT_DIE 7 +#define TAINT_OVERRIDDEN_ACPI_TABLE 8 +#define TAINT_WARN 9 +#define TAINT_CRAP 10 +#define TAINT_FIRMWARE_WORKAROUND 11 +#define TAINT_OOT_MODULE 12 +#define TAINT_UNSIGNED_MODULE 13 +#define TAINT_SOFTLOCKUP 14 +#define TAINT_LIVEPATCH 15 +#define TAINT_AUX 16 +#define TAINT_RANDSTRUCT 17 +#define TAINT_FLAGS_COUNT 18 +#define TAINT_FLAGS_MAX ((1UL << TAINT_FLAGS_COUNT) - 1) + +struct taint_flag { + char c_true; /* character printed when tainted */ + char c_false; /* character printed when not tainted */ + bool module; /* also show as a per-module taint flag */ +}; + +extern const struct taint_flag taint_flags[TAINT_FLAGS_COUNT]; + +enum lockdep_ok { + LOCKDEP_STILL_OK, + LOCKDEP_NOW_UNRELIABLE, +}; + +extern const char *print_tainted(void); +extern void add_taint(unsigned flag, enum lockdep_ok); +extern int test_taint(unsigned flag); +extern unsigned long get_taint(void); + +#endif /* _LINUX_PANIC_H */ diff --git a/include/linux/panic_notifier.h b/include/linux/panic_notifier.h new file mode 100644 index 000000000000..41e32483d7a7 --- /dev/null +++ b/include/linux/panic_notifier.h @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_PANIC_NOTIFIERS_H +#define _LINUX_PANIC_NOTIFIERS_H + +#include +#include + +extern struct atomic_notifier_head panic_notifier_list; + +extern bool crash_kexec_post_notifiers; + +#endif /* _LINUX_PANIC_NOTIFIERS_H */ diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index c32600c9e1ad..e82660f7b9e4 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -28,6 +28,24 @@ #define USER_PGTABLES_CEILING 0UL #endif +/* + * This defines the first usable user address. Platforms + * can override its value with custom FIRST_USER_ADDRESS + * defined in their respective . + */ +#ifndef FIRST_USER_ADDRESS +#define FIRST_USER_ADDRESS 0UL +#endif + +/* + * This defines the generic helper for accessing PMD page + * table page. Although platforms can still override this + * via their respective . + */ +#ifndef pmd_pgtable +#define pmd_pgtable(pmd) pmd_page(pmd) +#endif + /* * A page table page can be thought of an array like this: pXd_t[PTRS_PER_PxD] * @@ -1379,10 +1397,34 @@ static inline int p4d_clear_huge(p4d_t *p4d) } #endif /* !__PAGETABLE_P4D_FOLDED */ +#ifndef __PAGETABLE_PUD_FOLDED int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot); -int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot); int pud_clear_huge(pud_t *pud); +#else +static inline int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot) +{ + return 0; +} +static inline int pud_clear_huge(pud_t *pud) +{ + return 0; +} +#endif /* !__PAGETABLE_PUD_FOLDED */ + +#ifndef __PAGETABLE_PMD_FOLDED +int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot); int pmd_clear_huge(pmd_t *pmd); +#else +static inline int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot) +{ + return 0; +} +static inline int pmd_clear_huge(pmd_t *pmd) +{ + return 0; +} +#endif /* !__PAGETABLE_PMD_FOLDED */ + int p4d_free_pud_page(p4d_t *p4d, unsigned long addr); int pud_free_pmd_page(pud_t *pud, unsigned long addr); int pmd_free_pte_page(pmd_t *pmd, unsigned long addr); diff --git a/include/linux/rmap.h b/include/linux/rmap.h index 8d04e7deedc6..83fb86133fe1 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -86,9 +86,6 @@ struct anon_vma_chain { }; enum ttu_flags { - TTU_MIGRATION = 0x1, /* migration mode */ - TTU_MUNLOCK = 0x2, /* munlock mode */ - TTU_SPLIT_HUGE_PMD = 0x4, /* split huge PMD if any */ TTU_IGNORE_MLOCK = 0x8, /* ignore mlock */ TTU_SYNC = 0x10, /* avoid racy checks with PVMW_SYNC */ @@ -98,7 +95,6 @@ enum ttu_flags { * do a final flush if necessary */ TTU_RMAP_LOCKED = 0x80, /* do not grab rmap lock: * caller holds it */ - TTU_SPLIT_FREEZE = 0x100, /* freeze pte under splitting thp */ }; #ifdef CONFIG_MMU @@ -195,7 +191,12 @@ static inline void page_dup_rmap(struct page *page, bool compound) int page_referenced(struct page *, int is_locked, struct mem_cgroup *memcg, unsigned long *vm_flags); -bool try_to_unmap(struct page *, enum ttu_flags flags); +void try_to_migrate(struct page *page, enum ttu_flags flags); +void try_to_unmap(struct page *, enum ttu_flags flags); + +int make_device_exclusive_range(struct mm_struct *mm, unsigned long start, + unsigned long end, struct page **pages, + void *arg); /* Avoid racy checks */ #define PVMW_SYNC (1 << 0) @@ -240,7 +241,7 @@ int page_mkclean(struct page *); * called in munlock()/munmap() path to check for other vmas holding * the page mlocked. */ -void try_to_munlock(struct page *); +void page_mlock(struct page *page); void remove_migration_ptes(struct page *old, struct page *new, bool locked); diff --git a/include/linux/seq_file.h b/include/linux/seq_file.h index 723b1fa1177e..dd99569595fd 100644 --- a/include/linux/seq_file.h +++ b/include/linux/seq_file.h @@ -126,8 +126,16 @@ void seq_put_decimal_ll(struct seq_file *m, const char *delimiter, long long num void seq_put_hex_ll(struct seq_file *m, const char *delimiter, unsigned long long v, unsigned int width); +void seq_escape_mem(struct seq_file *m, const char *src, size_t len, + unsigned int flags, const char *esc); + +static inline void seq_escape_str(struct seq_file *m, const char *src, + unsigned int flags, const char *esc) +{ + seq_escape_mem(m, src, strlen(src), flags, esc); +} + void seq_escape(struct seq_file *m, const char *s, const char *esc); -void seq_escape_mem_ascii(struct seq_file *m, const char *src, size_t isz); void seq_hex_dump(struct seq_file *m, const char *prefix_str, int prefix_type, int rowsize, int groupsize, const void *buf, size_t len, diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index aa77dcd1646f..8e775ce517bb 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -122,21 +122,18 @@ static inline bool shmem_file(struct file *file) extern bool shmem_charge(struct inode *inode, long pages); extern void shmem_uncharge(struct inode *inode, long pages); +#ifdef CONFIG_USERFAULTFD #ifdef CONFIG_SHMEM -extern int shmem_mcopy_atomic_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd, +extern int shmem_mfill_atomic_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd, struct vm_area_struct *dst_vma, unsigned long dst_addr, unsigned long src_addr, + bool zeropage, struct page **pagep); -extern int shmem_mfill_zeropage_pte(struct mm_struct *dst_mm, - pmd_t *dst_pmd, - struct vm_area_struct *dst_vma, - unsigned long dst_addr); -#else -#define shmem_mcopy_atomic_pte(dst_mm, dst_pte, dst_vma, dst_addr, \ - src_addr, pagep) ({ BUG(); 0; }) -#define shmem_mfill_zeropage_pte(dst_mm, dst_pmd, dst_vma, \ - dst_addr) ({ BUG(); 0; }) -#endif +#else /* !CONFIG_SHMEM */ +#define shmem_mfill_atomic_pte(dst_mm, dst_pmd, dst_vma, dst_addr, \ + src_addr, zeropage, pagep) ({ BUG(); 0; }) +#endif /* CONFIG_SHMEM */ +#endif /* CONFIG_USERFAULTFD */ #endif diff --git a/include/linux/signal.h b/include/linux/signal.h index 5160fd45e5ca..3454c7ff0778 100644 --- a/include/linux/signal.h +++ b/include/linux/signal.h @@ -462,8 +462,6 @@ int __save_altstack(stack_t __user *, unsigned long); unsafe_put_user((void __user *)t->sas_ss_sp, &__uss->ss_sp, label); \ unsafe_put_user(t->sas_ss_flags, &__uss->ss_flags, label); \ unsafe_put_user(t->sas_ss_size, &__uss->ss_size, label); \ - if (t->sas_ss_flags & SS_AUTODISARM) \ - sas_ss_reset(t); \ } while (0); #ifdef CONFIG_PROC_FS diff --git a/include/linux/string.h b/include/linux/string.h index 9521d8cab18e..b48d2d28e0b1 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -2,7 +2,6 @@ #ifndef _LINUX_STRING_H_ #define _LINUX_STRING_H_ - #include /* for inline */ #include /* for size_t */ #include /* for NULL */ @@ -184,12 +183,6 @@ extern char **argv_split(gfp_t gfp, const char *str, int *argcp); extern void argv_free(char **argv); extern bool sysfs_streq(const char *s1, const char *s2); -extern int kstrtobool(const char *s, bool *res); -static inline int strtobool(const char *s, bool *res) -{ - return kstrtobool(s, res); -} - int match_string(const char * const *array, size_t n, const char *string); int __sysfs_match_string(const char * const *array, size_t n, const char *s); diff --git a/include/linux/string_helpers.h b/include/linux/string_helpers.h index fa06dcdc481e..68189c4a2eb1 100644 --- a/include/linux/string_helpers.h +++ b/include/linux/string_helpers.h @@ -2,6 +2,7 @@ #ifndef _LINUX_STRING_HELPERS_H_ #define _LINUX_STRING_HELPERS_H_ +#include #include #include @@ -18,13 +19,15 @@ enum string_size_units { void string_get_size(u64 size, u64 blk_size, enum string_size_units units, char *buf, int len); -#define UNESCAPE_SPACE 0x01 -#define UNESCAPE_OCTAL 0x02 -#define UNESCAPE_HEX 0x04 -#define UNESCAPE_SPECIAL 0x08 +#define UNESCAPE_SPACE BIT(0) +#define UNESCAPE_OCTAL BIT(1) +#define UNESCAPE_HEX BIT(2) +#define UNESCAPE_SPECIAL BIT(3) #define UNESCAPE_ANY \ (UNESCAPE_SPACE | UNESCAPE_OCTAL | UNESCAPE_HEX | UNESCAPE_SPECIAL) +#define UNESCAPE_ALL_MASK GENMASK(3, 0) + int string_unescape(char *src, char *dst, size_t size, unsigned int flags); static inline int string_unescape_inplace(char *buf, unsigned int flags) @@ -42,22 +45,24 @@ static inline int string_unescape_any_inplace(char *buf) return string_unescape_any(buf, buf, 0); } -#define ESCAPE_SPACE 0x01 -#define ESCAPE_SPECIAL 0x02 -#define ESCAPE_NULL 0x04 -#define ESCAPE_OCTAL 0x08 +#define ESCAPE_SPACE BIT(0) +#define ESCAPE_SPECIAL BIT(1) +#define ESCAPE_NULL BIT(2) +#define ESCAPE_OCTAL BIT(3) #define ESCAPE_ANY \ (ESCAPE_SPACE | ESCAPE_OCTAL | ESCAPE_SPECIAL | ESCAPE_NULL) -#define ESCAPE_NP 0x10 +#define ESCAPE_NP BIT(4) #define ESCAPE_ANY_NP (ESCAPE_ANY | ESCAPE_NP) -#define ESCAPE_HEX 0x20 +#define ESCAPE_HEX BIT(5) +#define ESCAPE_NA BIT(6) +#define ESCAPE_NAP BIT(7) +#define ESCAPE_APPEND BIT(8) + +#define ESCAPE_ALL_MASK GENMASK(8, 0) int string_escape_mem(const char *src, size_t isz, char *dst, size_t osz, unsigned int flags, const char *only); -int string_escape_mem_ascii(const char *src, size_t isz, char *dst, - size_t osz); - static inline int string_escape_mem_any_np(const char *src, size_t isz, char *dst, size_t osz, const char *only) { diff --git a/include/linux/sunrpc/cache.h b/include/linux/sunrpc/cache.h index d0965e2997b0..b134b2b3371c 100644 --- a/include/linux/sunrpc/cache.h +++ b/include/linux/sunrpc/cache.h @@ -14,6 +14,7 @@ #include #include #include +#include #include /* diff --git a/include/linux/swap.h b/include/linux/swap.h index 49b1dd2c100b..6f5a43251593 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -62,12 +62,17 @@ static inline int current_is_kswapd(void) * migrate part of a process memory to device memory. * * When a page is migrated from CPU to device, we set the CPU page table entry - * to a special SWP_DEVICE_* entry. + * to a special SWP_DEVICE_{READ|WRITE} entry. + * + * When a page is mapped by the device for exclusive access we set the CPU page + * table entries to special SWP_DEVICE_EXCLUSIVE_* entries. */ #ifdef CONFIG_DEVICE_PRIVATE -#define SWP_DEVICE_NUM 2 +#define SWP_DEVICE_NUM 4 #define SWP_DEVICE_WRITE (MAX_SWAPFILES+SWP_HWPOISON_NUM+SWP_MIGRATION_NUM) #define SWP_DEVICE_READ (MAX_SWAPFILES+SWP_HWPOISON_NUM+SWP_MIGRATION_NUM+1) +#define SWP_DEVICE_EXCLUSIVE_WRITE (MAX_SWAPFILES+SWP_HWPOISON_NUM+SWP_MIGRATION_NUM+2) +#define SWP_DEVICE_EXCLUSIVE_READ (MAX_SWAPFILES+SWP_HWPOISON_NUM+SWP_MIGRATION_NUM+3) #else #define SWP_DEVICE_NUM 0 #endif @@ -537,7 +542,11 @@ static inline void put_swap_device(struct swap_info_struct *si) { } -#define swap_address_space(entry) (NULL) +static inline struct address_space *swap_address_space(swp_entry_t entry) +{ + return NULL; +} + #define get_nr_swap_pages() 0L #define total_swap_pages 0L #define total_swapcache_pages() 0UL @@ -560,8 +569,8 @@ static inline void show_swap_cache_info(void) { } -#define free_swap_and_cache(e) ({(is_migration_entry(e) || is_device_private_entry(e));}) -#define swapcache_prepare(e) ({(is_migration_entry(e) || is_device_private_entry(e));}) +/* used to sanity check ptes in zap_pte_range when CONFIG_SWAP=0 */ +#define free_swap_and_cache(e) is_pfn_swap_entry(e) static inline int add_swap_count_continuation(swp_entry_t swp, gfp_t gfp_mask) { diff --git a/include/linux/swapops.h b/include/linux/swapops.h index 5907205c712c..d356ab4047f7 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -107,10 +107,14 @@ static inline void *swp_to_radix_entry(swp_entry_t entry) } #if IS_ENABLED(CONFIG_DEVICE_PRIVATE) -static inline swp_entry_t make_device_private_entry(struct page *page, bool write) +static inline swp_entry_t make_readable_device_private_entry(pgoff_t offset) { - return swp_entry(write ? SWP_DEVICE_WRITE : SWP_DEVICE_READ, - page_to_pfn(page)); + return swp_entry(SWP_DEVICE_READ, offset); +} + +static inline swp_entry_t make_writable_device_private_entry(pgoff_t offset) +{ + return swp_entry(SWP_DEVICE_WRITE, offset); } static inline bool is_device_private_entry(swp_entry_t entry) @@ -119,33 +123,40 @@ static inline bool is_device_private_entry(swp_entry_t entry) return type == SWP_DEVICE_READ || type == SWP_DEVICE_WRITE; } -static inline void make_device_private_entry_read(swp_entry_t *entry) -{ - *entry = swp_entry(SWP_DEVICE_READ, swp_offset(*entry)); -} - -static inline bool is_write_device_private_entry(swp_entry_t entry) +static inline bool is_writable_device_private_entry(swp_entry_t entry) { return unlikely(swp_type(entry) == SWP_DEVICE_WRITE); } -static inline unsigned long device_private_entry_to_pfn(swp_entry_t entry) +static inline swp_entry_t make_readable_device_exclusive_entry(pgoff_t offset) { - return swp_offset(entry); + return swp_entry(SWP_DEVICE_EXCLUSIVE_READ, offset); } -static inline struct page *device_private_entry_to_page(swp_entry_t entry) +static inline swp_entry_t make_writable_device_exclusive_entry(pgoff_t offset) { - return pfn_to_page(swp_offset(entry)); + return swp_entry(SWP_DEVICE_EXCLUSIVE_WRITE, offset); +} + +static inline bool is_device_exclusive_entry(swp_entry_t entry) +{ + return swp_type(entry) == SWP_DEVICE_EXCLUSIVE_READ || + swp_type(entry) == SWP_DEVICE_EXCLUSIVE_WRITE; +} + +static inline bool is_writable_device_exclusive_entry(swp_entry_t entry) +{ + return unlikely(swp_type(entry) == SWP_DEVICE_EXCLUSIVE_WRITE); } #else /* CONFIG_DEVICE_PRIVATE */ -static inline swp_entry_t make_device_private_entry(struct page *page, bool write) +static inline swp_entry_t make_readable_device_private_entry(pgoff_t offset) { return swp_entry(0, 0); } -static inline void make_device_private_entry_read(swp_entry_t *entry) +static inline swp_entry_t make_writable_device_private_entry(pgoff_t offset) { + return swp_entry(0, 0); } static inline bool is_device_private_entry(swp_entry_t entry) @@ -153,61 +164,52 @@ static inline bool is_device_private_entry(swp_entry_t entry) return false; } -static inline bool is_write_device_private_entry(swp_entry_t entry) +static inline bool is_writable_device_private_entry(swp_entry_t entry) { return false; } -static inline unsigned long device_private_entry_to_pfn(swp_entry_t entry) +static inline swp_entry_t make_readable_device_exclusive_entry(pgoff_t offset) { - return 0; + return swp_entry(0, 0); } -static inline struct page *device_private_entry_to_page(swp_entry_t entry) +static inline swp_entry_t make_writable_device_exclusive_entry(pgoff_t offset) { - return NULL; + return swp_entry(0, 0); +} + +static inline bool is_device_exclusive_entry(swp_entry_t entry) +{ + return false; +} + +static inline bool is_writable_device_exclusive_entry(swp_entry_t entry) +{ + return false; } #endif /* CONFIG_DEVICE_PRIVATE */ #ifdef CONFIG_MIGRATION -static inline swp_entry_t make_migration_entry(struct page *page, int write) -{ - BUG_ON(!PageLocked(compound_head(page))); - - return swp_entry(write ? SWP_MIGRATION_WRITE : SWP_MIGRATION_READ, - page_to_pfn(page)); -} - static inline int is_migration_entry(swp_entry_t entry) { return unlikely(swp_type(entry) == SWP_MIGRATION_READ || swp_type(entry) == SWP_MIGRATION_WRITE); } -static inline int is_write_migration_entry(swp_entry_t entry) +static inline int is_writable_migration_entry(swp_entry_t entry) { return unlikely(swp_type(entry) == SWP_MIGRATION_WRITE); } -static inline unsigned long migration_entry_to_pfn(swp_entry_t entry) +static inline swp_entry_t make_readable_migration_entry(pgoff_t offset) { - return swp_offset(entry); + return swp_entry(SWP_MIGRATION_READ, offset); } -static inline struct page *migration_entry_to_page(swp_entry_t entry) +static inline swp_entry_t make_writable_migration_entry(pgoff_t offset) { - struct page *p = pfn_to_page(swp_offset(entry)); - /* - * Any use of migration entries may only occur while the - * corresponding page is locked - */ - BUG_ON(!PageLocked(compound_head(p))); - return p; -} - -static inline void make_migration_entry_read(swp_entry_t *entry) -{ - *entry = swp_entry(SWP_MIGRATION_READ, swp_offset(*entry)); + return swp_entry(SWP_MIGRATION_WRITE, offset); } extern void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep, @@ -217,37 +219,58 @@ extern void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd, extern void migration_entry_wait_huge(struct vm_area_struct *vma, struct mm_struct *mm, pte_t *pte); #else +static inline swp_entry_t make_readable_migration_entry(pgoff_t offset) +{ + return swp_entry(0, 0); +} + +static inline swp_entry_t make_writable_migration_entry(pgoff_t offset) +{ + return swp_entry(0, 0); +} -#define make_migration_entry(page, write) swp_entry(0, 0) static inline int is_migration_entry(swp_entry_t swp) { return 0; } -static inline unsigned long migration_entry_to_pfn(swp_entry_t entry) -{ - return 0; -} - -static inline struct page *migration_entry_to_page(swp_entry_t entry) -{ - return NULL; -} - -static inline void make_migration_entry_read(swp_entry_t *entryp) { } static inline void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep, spinlock_t *ptl) { } static inline void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd, unsigned long address) { } static inline void migration_entry_wait_huge(struct vm_area_struct *vma, struct mm_struct *mm, pte_t *pte) { } -static inline int is_write_migration_entry(swp_entry_t entry) +static inline int is_writable_migration_entry(swp_entry_t entry) { return 0; } #endif +static inline struct page *pfn_swap_entry_to_page(swp_entry_t entry) +{ + struct page *p = pfn_to_page(swp_offset(entry)); + + /* + * Any use of migration entries may only occur while the + * corresponding page is locked + */ + BUG_ON(is_migration_entry(entry) && !PageLocked(p)); + + return p; +} + +/* + * A pfn swap entry is a special type of swap entry that always has a pfn stored + * in the swap offset. They are used to represent unaddressable device memory + * and to restrict access to a page undergoing migration. + */ +static inline bool is_pfn_swap_entry(swp_entry_t entry) +{ + return is_migration_entry(entry) || is_device_private_entry(entry) || + is_device_exclusive_entry(entry); +} + struct page_vma_mapped_walk; #ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION @@ -265,6 +288,8 @@ static inline swp_entry_t pmd_to_swp_entry(pmd_t pmd) if (pmd_swp_soft_dirty(pmd)) pmd = pmd_swp_clear_soft_dirty(pmd); + if (pmd_swp_uffd_wp(pmd)) + pmd = pmd_swp_clear_uffd_wp(pmd); arch_entry = __pmd_to_swp_entry(pmd); return swp_entry(__swp_type(arch_entry), __swp_offset(arch_entry)); } diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h index 157762db9d4b..0999f6317978 100644 --- a/include/linux/thread_info.h +++ b/include/linux/thread_info.h @@ -9,6 +9,7 @@ #define _LINUX_THREAD_INFO_H #include +#include #include #include #include diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h index 794d1538b8ba..331d2ccf0bcc 100644 --- a/include/linux/userfaultfd_k.h +++ b/include/linux/userfaultfd_k.h @@ -53,6 +53,11 @@ enum mcopy_atomic_mode { MCOPY_ATOMIC_CONTINUE, }; +extern int mfill_atomic_install_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd, + struct vm_area_struct *dst_vma, + unsigned long dst_addr, struct page *page, + bool newly_allocated, bool wp_copy); + extern ssize_t mcopy_atomic(struct mm_struct *dst_mm, unsigned long dst_start, unsigned long src_start, unsigned long len, bool *mmap_changing, __u64 mode); diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index bfaaf0b6fa76..1dabd6f22486 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -104,6 +104,21 @@ static inline bool arch_vmap_pmd_supported(pgprot_t prot) } #endif +#ifndef arch_vmap_pte_range_map_size +static inline unsigned long arch_vmap_pte_range_map_size(unsigned long addr, unsigned long end, + u64 pfn, unsigned int max_page_shift) +{ + return PAGE_SIZE; +} +#endif + +#ifndef arch_vmap_pte_supported_shift +static inline int arch_vmap_pte_supported_shift(unsigned long size) +{ + return PAGE_SHIFT; +} +#endif + /* * Highlevel APIs for driver use */ diff --git a/include/linux/zbud.h b/include/linux/zbud.h deleted file mode 100644 index b1eaf6e31735..000000000000 --- a/include/linux/zbud.h +++ /dev/null @@ -1,23 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _ZBUD_H_ -#define _ZBUD_H_ - -#include - -struct zbud_pool; - -struct zbud_ops { - int (*evict)(struct zbud_pool *pool, unsigned long handle); -}; - -struct zbud_pool *zbud_create_pool(gfp_t gfp, const struct zbud_ops *ops); -void zbud_destroy_pool(struct zbud_pool *pool); -int zbud_alloc(struct zbud_pool *pool, size_t size, gfp_t gfp, - unsigned long *handle); -void zbud_free(struct zbud_pool *pool, unsigned long handle); -int zbud_reclaim_page(struct zbud_pool *pool, unsigned int retries); -void *zbud_map(struct zbud_pool *pool, unsigned long handle); -void zbud_unmap(struct zbud_pool *pool, unsigned long handle); -u64 zbud_get_pool_size(struct zbud_pool *pool); - -#endif /* _ZBUD_H_ */ diff --git a/include/trace/events/vmscan.h b/include/trace/events/vmscan.h index 00d1180527d8..88faf2400ec2 100644 --- a/include/trace/events/vmscan.h +++ b/include/trace/events/vmscan.h @@ -423,47 +423,6 @@ TRACE_EVENT(mm_vmscan_lru_shrink_active, show_reclaim_flags(__entry->reclaim_flags)) ); -TRACE_EVENT(mm_vmscan_inactive_list_is_low, - - TP_PROTO(int nid, int reclaim_idx, - unsigned long total_inactive, unsigned long inactive, - unsigned long total_active, unsigned long active, - unsigned long ratio, int file), - - TP_ARGS(nid, reclaim_idx, total_inactive, inactive, total_active, active, ratio, file), - - TP_STRUCT__entry( - __field(int, nid) - __field(int, reclaim_idx) - __field(unsigned long, total_inactive) - __field(unsigned long, inactive) - __field(unsigned long, total_active) - __field(unsigned long, active) - __field(unsigned long, ratio) - __field(int, reclaim_flags) - ), - - TP_fast_assign( - __entry->nid = nid; - __entry->reclaim_idx = reclaim_idx; - __entry->total_inactive = total_inactive; - __entry->inactive = inactive; - __entry->total_active = total_active; - __entry->active = active; - __entry->ratio = ratio; - __entry->reclaim_flags = trace_reclaim_flags(file) & - RECLAIM_WB_LRU; - ), - - TP_printk("nid=%d reclaim_idx=%d total_inactive=%ld inactive=%ld total_active=%ld active=%ld ratio=%ld flags=%s", - __entry->nid, - __entry->reclaim_idx, - __entry->total_inactive, __entry->inactive, - __entry->total_active, __entry->active, - __entry->ratio, - show_reclaim_flags(__entry->reclaim_flags)) -); - TRACE_EVENT(mm_vmscan_node_reclaim_begin, TP_PROTO(int nid, int order, gfp_t gfp_flags), diff --git a/include/uapi/asm-generic/mman-common.h b/include/uapi/asm-generic/mman-common.h index f94f65d429be..1567a3294c3d 100644 --- a/include/uapi/asm-generic/mman-common.h +++ b/include/uapi/asm-generic/mman-common.h @@ -72,6 +72,9 @@ #define MADV_COLD 20 /* deactivate these pages */ #define MADV_PAGEOUT 21 /* reclaim these pages */ +#define MADV_POPULATE_READ 22 /* populate (prefault) page tables readable */ +#define MADV_POPULATE_WRITE 23 /* populate (prefault) page tables writable */ + /* compatibility flags */ #define MAP_FILE 0 diff --git a/include/uapi/linux/mempolicy.h b/include/uapi/linux/mempolicy.h index 4832fd0b5642..19a00bc7fe86 100644 --- a/include/uapi/linux/mempolicy.h +++ b/include/uapi/linux/mempolicy.h @@ -60,7 +60,6 @@ enum { * are never OR'ed into the mode in mempolicy API arguments. */ #define MPOL_F_SHARED (1 << 0) /* identify shared policies */ -#define MPOL_F_LOCAL (1 << 1) /* preferred local allocation */ #define MPOL_F_MOF (1 << 3) /* this policy wants migrate on fault */ #define MPOL_F_MORON (1 << 4) /* Migrate On protnone Reference On Node */ diff --git a/include/uapi/linux/userfaultfd.h b/include/uapi/linux/userfaultfd.h index 650480f41f1d..05b31d60acf6 100644 --- a/include/uapi/linux/userfaultfd.h +++ b/include/uapi/linux/userfaultfd.h @@ -31,7 +31,8 @@ UFFD_FEATURE_MISSING_SHMEM | \ UFFD_FEATURE_SIGBUS | \ UFFD_FEATURE_THREAD_ID | \ - UFFD_FEATURE_MINOR_HUGETLBFS) + UFFD_FEATURE_MINOR_HUGETLBFS | \ + UFFD_FEATURE_MINOR_SHMEM) #define UFFD_API_IOCTLS \ ((__u64)1 << _UFFDIO_REGISTER | \ (__u64)1 << _UFFDIO_UNREGISTER | \ @@ -185,6 +186,9 @@ struct uffdio_api { * UFFD_FEATURE_MINOR_HUGETLBFS indicates that minor faults * can be intercepted (via REGISTER_MODE_MINOR) for * hugetlbfs-backed pages. + * + * UFFD_FEATURE_MINOR_SHMEM indicates the same support as + * UFFD_FEATURE_MINOR_HUGETLBFS, but for shmem-backed pages instead. */ #define UFFD_FEATURE_PAGEFAULT_FLAG_WP (1<<0) #define UFFD_FEATURE_EVENT_FORK (1<<1) @@ -196,6 +200,7 @@ struct uffdio_api { #define UFFD_FEATURE_SIGBUS (1<<7) #define UFFD_FEATURE_THREAD_ID (1<<8) #define UFFD_FEATURE_MINOR_HUGETLBFS (1<<9) +#define UFFD_FEATURE_MINOR_SHMEM (1<<10) __u64 features; __u64 ioctls; diff --git a/init/main.c b/init/main.c index 359358500e54..f88d896c0123 100644 --- a/init/main.c +++ b/init/main.c @@ -873,6 +873,47 @@ void __init __weak arch_call_rest_init(void) rest_init(); } +static void __init print_unknown_bootoptions(void) +{ + char *unknown_options; + char *end; + const char *const *p; + size_t len; + + if (panic_later || (!argv_init[1] && !envp_init[2])) + return; + + /* + * Determine how many options we have to print out, plus a space + * before each + */ + len = 1; /* null terminator */ + for (p = &argv_init[1]; *p; p++) { + len++; + len += strlen(*p); + } + for (p = &envp_init[2]; *p; p++) { + len++; + len += strlen(*p); + } + + unknown_options = memblock_alloc(len, SMP_CACHE_BYTES); + if (!unknown_options) { + pr_err("%s: Failed to allocate %zu bytes\n", + __func__, len); + return; + } + end = unknown_options; + + for (p = &argv_init[1]; *p; p++) + end += sprintf(end, " %s", *p); + for (p = &envp_init[2]; *p; p++) + end += sprintf(end, " %s", *p); + + pr_notice("Unknown command line parameters:%s\n", unknown_options); + memblock_free(__pa(unknown_options), len); +} + asmlinkage __visible void __init __no_sanitize_address start_kernel(void) { char *command_line; @@ -914,6 +955,7 @@ asmlinkage __visible void __init __no_sanitize_address start_kernel(void) static_command_line, __start___param, __stop___param - __start___param, -1, -1, NULL, &unknown_bootoption); + print_unknown_bootoptions(); if (!IS_ERR_OR_NULL(after_dashes)) parse_args("Setting init args", after_dashes, NULL, 0, -1, -1, NULL, set_init_arg); diff --git a/ipc/msg.c b/ipc/msg.c index 6e6c8e0c9380..6810276d6bb9 100644 --- a/ipc/msg.c +++ b/ipc/msg.c @@ -130,7 +130,7 @@ static void msg_rcu_free(struct rcu_head *head) struct msg_queue *msq = container_of(p, struct msg_queue, q_perm); security_msg_queue_free(&msq->q_perm); - kvfree(msq); + kfree(msq); } /** @@ -147,7 +147,7 @@ static int newque(struct ipc_namespace *ns, struct ipc_params *params) key_t key = params->key; int msgflg = params->flg; - msq = kvmalloc(sizeof(*msq), GFP_KERNEL); + msq = kmalloc(sizeof(*msq), GFP_KERNEL); if (unlikely(!msq)) return -ENOMEM; @@ -157,7 +157,7 @@ static int newque(struct ipc_namespace *ns, struct ipc_params *params) msq->q_perm.security = NULL; retval = security_msg_queue_alloc(&msq->q_perm); if (retval) { - kvfree(msq); + kfree(msq); return retval; } diff --git a/ipc/sem.c b/ipc/sem.c index bf534c74293e..971e75d28364 100644 --- a/ipc/sem.c +++ b/ipc/sem.c @@ -217,6 +217,8 @@ static int sysvipc_sem_proc_show(struct seq_file *s, void *it); * this smp_load_acquire(), this is guaranteed because the smp_load_acquire() * is inside a spin_lock() and after a write from 0 to non-zero a * spin_lock()+spin_unlock() is done. + * To prevent the compiler/cpu temporarily writing 0 to use_global_lock, + * READ_ONCE()/WRITE_ONCE() is used. * * 2) queue.status: (SEM_BARRIER_2) * Initialization is done while holding sem_lock(), so no further barrier is @@ -342,10 +344,10 @@ static void complexmode_enter(struct sem_array *sma) * Nothing to do, just reset the * counter until we return to simple mode. */ - sma->use_global_lock = USE_GLOBAL_LOCK_HYSTERESIS; + WRITE_ONCE(sma->use_global_lock, USE_GLOBAL_LOCK_HYSTERESIS); return; } - sma->use_global_lock = USE_GLOBAL_LOCK_HYSTERESIS; + WRITE_ONCE(sma->use_global_lock, USE_GLOBAL_LOCK_HYSTERESIS); for (i = 0; i < sma->sem_nsems; i++) { sem = &sma->sems[i]; @@ -371,7 +373,8 @@ static void complexmode_tryleave(struct sem_array *sma) /* See SEM_BARRIER_1 for purpose/pairing */ smp_store_release(&sma->use_global_lock, 0); } else { - sma->use_global_lock--; + WRITE_ONCE(sma->use_global_lock, + sma->use_global_lock-1); } } @@ -412,7 +415,7 @@ static inline int sem_lock(struct sem_array *sma, struct sembuf *sops, * Initial check for use_global_lock. Just an optimization, * no locking, no memory barrier. */ - if (!sma->use_global_lock) { + if (!READ_ONCE(sma->use_global_lock)) { /* * It appears that no complex operation is around. * Acquire the per-semaphore lock. @@ -1154,7 +1157,7 @@ static void freeary(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp) un->semid = -1; list_del_rcu(&un->list_proc); spin_unlock(&un->ulp->lock); - kfree_rcu(un, rcu); + kvfree_rcu(un, rcu); } /* Wake up all pending processes and let them fail with EIDRM. */ @@ -1937,7 +1940,8 @@ static struct sem_undo *find_alloc_undo(struct ipc_namespace *ns, int semid) rcu_read_unlock(); /* step 2: allocate new undo structure */ - new = kzalloc(sizeof(struct sem_undo) + sizeof(short)*nsems, GFP_KERNEL); + new = kvzalloc(sizeof(struct sem_undo) + sizeof(short)*nsems, + GFP_KERNEL); if (!new) { ipc_rcu_putref(&sma->sem_perm, sem_rcu_free); return ERR_PTR(-ENOMEM); @@ -1949,7 +1953,7 @@ static struct sem_undo *find_alloc_undo(struct ipc_namespace *ns, int semid) if (!ipc_valid_object(&sma->sem_perm)) { sem_unlock(sma, -1); rcu_read_unlock(); - kfree(new); + kvfree(new); un = ERR_PTR(-EIDRM); goto out; } @@ -1960,7 +1964,7 @@ static struct sem_undo *find_alloc_undo(struct ipc_namespace *ns, int semid) */ un = lookup_undo(ulp, semid); if (un) { - kfree(new); + kvfree(new); goto success; } /* step 5: initialize & link new undo structure */ @@ -2420,7 +2424,7 @@ void exit_sem(struct task_struct *tsk) rcu_read_unlock(); wake_up_q(&wake_q); - kfree_rcu(un, rcu); + kvfree_rcu(un, rcu); } kfree(ulp); } @@ -2435,7 +2439,8 @@ static int sysvipc_sem_proc_show(struct seq_file *s, void *it) /* * The proc interface isn't aware of sem_lock(), it calls - * ipc_lock_object() directly (in sysvipc_find_ipc). + * ipc_lock_object(), i.e. spin_lock(&sma->sem_perm.lock). + * (in sysvipc_find_ipc) * In order to stay compatible with sem_lock(), we must * enter / leave complex_mode. */ diff --git a/ipc/shm.c b/ipc/shm.c index 003234fbbd17..748933e376ca 100644 --- a/ipc/shm.c +++ b/ipc/shm.c @@ -222,7 +222,7 @@ static void shm_rcu_free(struct rcu_head *head) struct shmid_kernel *shp = container_of(ptr, struct shmid_kernel, shm_perm); security_shm_free(&shp->shm_perm); - kvfree(shp); + kfree(shp); } static inline void shm_rmid(struct ipc_namespace *ns, struct shmid_kernel *s) @@ -619,7 +619,7 @@ static int newseg(struct ipc_namespace *ns, struct ipc_params *params) ns->shm_tot + numpages > ns->shm_ctlall) return -ENOSPC; - shp = kvmalloc(sizeof(*shp), GFP_KERNEL); + shp = kmalloc(sizeof(*shp), GFP_KERNEL); if (unlikely(!shp)) return -ENOMEM; @@ -630,7 +630,7 @@ static int newseg(struct ipc_namespace *ns, struct ipc_params *params) shp->shm_perm.security = NULL; error = security_shm_alloc(&shp->shm_perm); if (error) { - kvfree(shp); + kfree(shp); return error; } diff --git a/ipc/util.c b/ipc/util.c index cfa0045e748d..0027e47626b7 100644 --- a/ipc/util.c +++ b/ipc/util.c @@ -64,6 +64,7 @@ #include #include #include +#include #include @@ -450,6 +451,41 @@ static void ipc_kht_remove(struct ipc_ids *ids, struct kern_ipc_perm *ipcp) ipc_kht_params); } +/** + * ipc_search_maxidx - search for the highest assigned index + * @ids: ipc identifier set + * @limit: known upper limit for highest assigned index + * + * The function determines the highest assigned index in @ids. It is intended + * to be called when ids->max_idx needs to be updated. + * Updating ids->max_idx is necessary when the current highest index ipc + * object is deleted. + * If no ipc object is allocated, then -1 is returned. + * + * ipc_ids.rwsem needs to be held by the caller. + */ +static int ipc_search_maxidx(struct ipc_ids *ids, int limit) +{ + int tmpidx; + int i; + int retval; + + i = ilog2(limit+1); + + retval = 0; + for (; i >= 0; i--) { + tmpidx = retval | (1<ipcs_idr, &tmpidx)) + retval |= (1<deleted = true; if (unlikely(idx == ids->max_idx)) { - do { - idx--; - if (idx == -1) - break; - } while (!idr_find(&ids->ipcs_idr, idx)); + idx = ids->max_idx-1; + if (idx >= 0) + idx = ipc_search_maxidx(ids, idx); ids->max_idx = idx; } } diff --git a/ipc/util.h b/ipc/util.h index 5766c61aed0e..2dd7ce0416d8 100644 --- a/ipc/util.h +++ b/ipc/util.h @@ -145,6 +145,9 @@ int ipcperms(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp, short flg); * ipc_get_maxidx - get the highest assigned index * @ids: ipc identifier set * + * The function returns the highest assigned index for @ids. The function + * doesn't scan the idr tree, it uses a cached value. + * * Called with ipc_ids.rwsem held for reading. */ static inline int ipc_get_maxidx(struct ipc_ids *ids) diff --git a/kernel/hung_task.c b/kernel/hung_task.c index b0ce8b3f3822..9888e2bc8c76 100644 --- a/kernel/hung_task.c +++ b/kernel/hung_task.c @@ -15,6 +15,7 @@ #include #include #include +#include #include #include #include diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c index f099baee3578..4b34a9aa32bc 100644 --- a/kernel/kexec_core.c +++ b/kernel/kexec_core.c @@ -26,6 +26,7 @@ #include #include #include +#include #include #include #include diff --git a/kernel/kprobes.c b/kernel/kprobes.c index e41385afe79d..297dc8bbe333 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -106,7 +106,7 @@ void __weak *alloc_insn_page(void) return module_alloc(PAGE_SIZE); } -void __weak free_insn_page(void *page) +static void free_insn_page(void *page) { module_memfree(page); } diff --git a/kernel/panic.c b/kernel/panic.c index 332736a72a58..edad89660a2b 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -23,6 +23,7 @@ #include #include #include +#include #include #include #include diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 8e78b2430c16..f12056beb916 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -32,6 +32,8 @@ #include #include #include +#include +#include #include #include #include diff --git a/kernel/signal.c b/kernel/signal.c index de0920353d30..f6371dfa1f89 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -2830,6 +2830,8 @@ static void signal_delivered(struct ksignal *ksig, int stepping) if (!(ksig->ka.sa.sa_flags & SA_NODEFER)) sigaddset(&blocked, ksig->sig); set_current_blocked(&blocked); + if (current->sas_ss_flags & SS_AUTODISARM) + sas_ss_reset(current); tracehook_signal_handler(stepping); } @@ -4148,11 +4150,7 @@ int __save_altstack(stack_t __user *uss, unsigned long sp) int err = __put_user((void __user *)t->sas_ss_sp, &uss->ss_sp) | __put_user(t->sas_ss_flags, &uss->ss_flags) | __put_user(t->sas_ss_size, &uss->ss_size); - if (err) - return err; - if (t->sas_ss_flags & SS_AUTODISARM) - sas_ss_reset(t); - return 0; + return err; } #ifdef CONFIG_COMPAT @@ -4207,11 +4205,7 @@ int __compat_save_altstack(compat_stack_t __user *uss, unsigned long sp) &uss->ss_sp) | __put_user(t->sas_ss_flags, &uss->ss_flags) | __put_user(t->sas_ss_size, &uss->ss_size); - if (err) - return err; - if (t->sas_ss_flags & SS_AUTODISARM) - sas_ss_reset(t); - return 0; + return err; } #endif diff --git a/kernel/sysctl.c b/kernel/sysctl.c index e1aa24e1545c..272f4a272f8c 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -27,6 +27,7 @@ #include #include #include +#include #include #include #include @@ -1495,7 +1496,6 @@ int proc_do_large_bitmap(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int err = 0; - bool first = 1; size_t left = *lenp; unsigned long bitmap_len = table->maxlen; unsigned long *bitmap = *(unsigned long **) table->data; @@ -1580,12 +1580,12 @@ int proc_do_large_bitmap(struct ctl_table *table, int write, } bitmap_set(tmp_bitmap, val_a, val_b - val_a + 1); - first = 0; proc_skip_char(&p, &left, '\n'); } left += skipped; } else { unsigned long bit_a, bit_b = 0; + bool first = 1; while (left) { bit_a = find_next_bit(bitmap, bitmap_len, bit_b); diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index d23a09d3eb37..3c1384bc5c5a 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -39,6 +39,7 @@ #include #include #include +#include #include #include #include diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 1c9857fdb1a0..ae62debfd8bf 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -2446,6 +2446,18 @@ config SLUB_KUNIT_TEST If unsure, say N. +config RATIONAL_KUNIT_TEST + tristate "KUnit test for rational.c" if !KUNIT_ALL_TESTS + depends on KUNIT + select RATIONAL + default KUNIT_ALL_TESTS + help + This builds the rational math unit test. + For more information on KUnit and unit tests in general please refer + to the KUnit documentation in Documentation/dev-tools/kunit/. + + If unsure, say N. + config TEST_UDELAY tristate "udelay test driver" help diff --git a/lib/decompress_bunzip2.c b/lib/decompress_bunzip2.c index c72c865032fa..3518e7394eca 100644 --- a/lib/decompress_bunzip2.c +++ b/lib/decompress_bunzip2.c @@ -80,7 +80,7 @@ /* This is what we know about each Huffman coding group */ struct group_data { - /* We have an extra slot at the end of limit[] for a sentinal value. */ + /* We have an extra slot at the end of limit[] for a sentinel value. */ int limit[MAX_HUFCODE_BITS+1]; int base[MAX_HUFCODE_BITS]; int permute[MAX_SYMBOLS]; @@ -337,7 +337,7 @@ static int INIT get_next_block(struct bunzip_data *bd) pp <<= 1; base[i+1] = pp-(t += temp[i]); } - limit[maxLen+1] = INT_MAX; /* Sentinal value for + limit[maxLen+1] = INT_MAX; /* Sentinel value for * reading next sym. */ limit[maxLen] = pp+temp[maxLen]-1; base[minLen] = 0; @@ -385,7 +385,7 @@ static int INIT get_next_block(struct bunzip_data *bd) bd->inbufBits = (bd->inbufBits << 8)|bd->inbuf[bd->inbufPos++]; bd->inbufBitCount += 8; - }; + } bd->inbufBitCount -= hufGroup->maxLen; j = (bd->inbufBits >> bd->inbufBitCount)& ((1 << hufGroup->maxLen)-1); diff --git a/lib/decompress_unlz4.c b/lib/decompress_unlz4.c index c0cfcfd486be..e6327391b6b6 100644 --- a/lib/decompress_unlz4.c +++ b/lib/decompress_unlz4.c @@ -112,6 +112,9 @@ STATIC inline int INIT unlz4(u8 *input, long in_len, error("data corrupted"); goto exit_2; } + } else if (size < 4) { + /* empty or end-of-file */ + goto exit_3; } chunksize = get_unaligned_le32(inp); @@ -125,6 +128,10 @@ STATIC inline int INIT unlz4(u8 *input, long in_len, continue; } + if (!fill && chunksize == 0) { + /* empty or end-of-file */ + goto exit_3; + } if (posp) *posp += 4; @@ -184,6 +191,7 @@ STATIC inline int INIT unlz4(u8 *input, long in_len, } } +exit_3: ret = 0; exit_2: if (!input) diff --git a/lib/decompress_unlzo.c b/lib/decompress_unlzo.c index 1f439a622076..64c1358500ce 100644 --- a/lib/decompress_unlzo.c +++ b/lib/decompress_unlzo.c @@ -43,7 +43,6 @@ STATIC inline long INIT parse_header(u8 *input, long *skip, long in_len) int l; u8 *parse = input; u8 *end = input + in_len; - u8 level = 0; u16 version; /* @@ -65,7 +64,7 @@ STATIC inline long INIT parse_header(u8 *input, long *skip, long in_len) version = get_unaligned_be16(parse); parse += 7; if (version >= 0x0940) - level = *parse++; + parse++; if (get_unaligned_be32(parse) & HEADER_HAS_FILTER) parse += 8; /* flags + filter info */ else diff --git a/lib/decompress_unxz.c b/lib/decompress_unxz.c index 25d59a95bd66..a2f38e23004a 100644 --- a/lib/decompress_unxz.c +++ b/lib/decompress_unxz.c @@ -23,7 +23,7 @@ * uncompressible. Thus, we must look for worst-case expansion when the * compressor is encoding uncompressible data. * - * The structure of the .xz file in case of a compresed kernel is as follows. + * The structure of the .xz file in case of a compressed kernel is as follows. * Sizes (as bytes) of the fields are in parenthesis. * * Stream Header (12) diff --git a/lib/decompress_unzstd.c b/lib/decompress_unzstd.c index 790abc472f5b..6b629ab31c1e 100644 --- a/lib/decompress_unzstd.c +++ b/lib/decompress_unzstd.c @@ -16,7 +16,7 @@ * uncompressible. Thus, we must look for worst-case expansion when the * compressor is encoding uncompressible data. * - * The structure of the .zst file in case of a compresed kernel is as follows. + * The structure of the .zst file in case of a compressed kernel is as follows. * Maximum sizes (as bytes) of the fields are in parenthesis. * * Frame Header: (18) @@ -56,7 +56,7 @@ /* * Preboot environments #include "path/to/decompress_unzstd.c". * All of the source files we depend on must be #included. - * zstd's only source dependeny is xxhash, which has no source + * zstd's only source dependency is xxhash, which has no source * dependencies. * * When UNZSTD_PREBOOT is defined we declare __decompress(), which is diff --git a/lib/kstrtox.c b/lib/kstrtox.c index 0b5fe8b41173..059b8b00dc53 100644 --- a/lib/kstrtox.c +++ b/lib/kstrtox.c @@ -14,11 +14,12 @@ */ #include #include -#include -#include #include +#include +#include #include #include + #include "kstrtox.h" const char *_parse_integer_fixup_radix(const char *s, unsigned int *base) diff --git a/lib/lz4/lz4_decompress.c b/lib/lz4/lz4_decompress.c index 8a7724a6ce2f..926f4823d5ea 100644 --- a/lib/lz4/lz4_decompress.c +++ b/lib/lz4/lz4_decompress.c @@ -481,7 +481,7 @@ int LZ4_decompress_fast(const char *source, char *dest, int originalSize) /* ===== Instantiate a few more decoding cases, used more than once. ===== */ -int LZ4_decompress_safe_withPrefix64k(const char *source, char *dest, +static int LZ4_decompress_safe_withPrefix64k(const char *source, char *dest, int compressedSize, int maxOutputSize) { return LZ4_decompress_generic(source, dest, diff --git a/lib/math/Makefile b/lib/math/Makefile index 7456edb864fc..bfac26ddfc22 100644 --- a/lib/math/Makefile +++ b/lib/math/Makefile @@ -6,3 +6,4 @@ obj-$(CONFIG_PRIME_NUMBERS) += prime_numbers.o obj-$(CONFIG_RATIONAL) += rational.o obj-$(CONFIG_TEST_DIV64) += test_div64.o +obj-$(CONFIG_RATIONAL_KUNIT_TEST) += rational-test.o diff --git a/lib/math/rational-test.c b/lib/math/rational-test.c new file mode 100644 index 000000000000..01611ddff420 --- /dev/null +++ b/lib/math/rational-test.c @@ -0,0 +1,56 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include + +#include + +struct rational_test_param { + unsigned long num, den; + unsigned long max_num, max_den; + unsigned long exp_num, exp_den; + + const char *name; +}; + +static const struct rational_test_param test_parameters[] = { + { 1230, 10, 100, 20, 100, 1, "Exceeds bounds, semi-convergent term > 1/2 last term" }, + { 34567,100, 120, 20, 120, 1, "Exceeds bounds, semi-convergent term < 1/2 last term" }, + { 1, 30, 100, 10, 0, 1, "Closest to zero" }, + { 1, 19, 100, 10, 1, 10, "Closest to smallest non-zero" }, + { 27,32, 16, 16, 11, 13, "Use convergent" }, + { 1155, 7735, 255, 255, 33, 221, "Exact answer" }, + { 87, 32, 70, 32, 68, 25, "Semiconvergent, numerator limit" }, + { 14533, 4626, 15000, 2400, 7433, 2366, "Semiconvergent, denominator limit" }, +}; + +static void get_desc(const struct rational_test_param *param, char *desc) +{ + strscpy(desc, param->name, KUNIT_PARAM_DESC_SIZE); +} + +/* Creates function rational_gen_params */ +KUNIT_ARRAY_PARAM(rational, test_parameters, get_desc); + +static void rational_test(struct kunit *test) +{ + const struct rational_test_param *param = (const struct rational_test_param *)test->param_value; + unsigned long n = 0, d = 0; + + rational_best_approximation(param->num, param->den, param->max_num, param->max_den, &n, &d); + KUNIT_EXPECT_EQ(test, n, param->exp_num); + KUNIT_EXPECT_EQ(test, d, param->exp_den); +} + +static struct kunit_case rational_test_cases[] = { + KUNIT_CASE_PARAM(rational_test, rational_gen_params), + {} +}; + +static struct kunit_suite rational_test_suite = { + .name = "rational", + .test_cases = rational_test_cases, +}; + +kunit_test_suites(&rational_test_suite); + +MODULE_LICENSE("GPL v2"); diff --git a/lib/math/rational.c b/lib/math/rational.c index 9781d521963d..c0ab51d8fbb9 100644 --- a/lib/math/rational.c +++ b/lib/math/rational.c @@ -12,6 +12,7 @@ #include #include #include +#include /* * calculate best rational approximation for a given fraction @@ -78,13 +79,18 @@ void rational_best_approximation( * found below as 't'. */ if ((n2 > max_numerator) || (d2 > max_denominator)) { - unsigned long t = min((max_numerator - n0) / n1, - (max_denominator - d0) / d1); + unsigned long t = ULONG_MAX; - /* This tests if the semi-convergent is closer - * than the previous convergent. + if (d1) + t = (max_denominator - d0) / d1; + if (n1) + t = min(t, (max_numerator - n0) / n1); + + /* This tests if the semi-convergent is closer than the previous + * convergent. If d1 is zero there is no previous convergent as this + * is the 1st iteration, so always choose the semi-convergent. */ - if (2u * t > a || (2u * t == a && d0 * dp > d1 * d)) { + if (!d1 || 2u * t > a || (2u * t == a && d0 * dp > d1 * d)) { n1 = n0 + t * n1; d1 = d0 + t * d1; } diff --git a/lib/mpi/longlong.h b/lib/mpi/longlong.h index afbd99987cf8..b6fa1d08fb55 100644 --- a/lib/mpi/longlong.h +++ b/lib/mpi/longlong.h @@ -48,8 +48,8 @@ /* Define auxiliary asm macros. * - * 1) umul_ppmm(high_prod, low_prod, multipler, multiplicand) multiplies two - * UWtype integers MULTIPLER and MULTIPLICAND, and generates a two UWtype + * 1) umul_ppmm(high_prod, low_prod, multiplier, multiplicand) multiplies two + * UWtype integers MULTIPLIER and MULTIPLICAND, and generates a two UWtype * word product in HIGH_PROD and LOW_PROD. * * 2) __umulsidi3(a,b) multiplies two UWtype integers A and B, and returns a diff --git a/lib/mpi/mpicoder.c b/lib/mpi/mpicoder.c index 7ea225b2204f..39c4c6731094 100644 --- a/lib/mpi/mpicoder.c +++ b/lib/mpi/mpicoder.c @@ -234,11 +234,11 @@ static int count_lzeros(MPI a) } /** - * mpi_read_buffer() - read MPI to a bufer provided by user (msb first) + * mpi_read_buffer() - read MPI to a buffer provided by user (msb first) * * @a: a multi precision integer - * @buf: bufer to which the output will be written to. Needs to be at - * leaset mpi_get_size(a) long. + * @buf: buffer to which the output will be written to. Needs to be at + * least mpi_get_size(a) long. * @buf_len: size of the buf. * @nbytes: receives the actual length of the data written on success and * the data to-be-written on -EOVERFLOW in case buf_len was too diff --git a/lib/mpi/mpiutil.c b/lib/mpi/mpiutil.c index 3c63710c20c6..9a75ca3f7edf 100644 --- a/lib/mpi/mpiutil.c +++ b/lib/mpi/mpiutil.c @@ -80,7 +80,7 @@ EXPORT_SYMBOL_GPL(mpi_const); /**************** * Note: It was a bad idea to use the number of limbs to allocate * because on a alpha the limbs are large but we normally need - * integers of n bits - So we should chnage this to bits (or bytes). + * integers of n bits - So we should change this to bits (or bytes). * * But mpi_alloc is used in a lot of places :-) */ diff --git a/lib/parser.c b/lib/parser.c index f1a6d90b8c34..bcb23484100e 100644 --- a/lib/parser.c +++ b/lib/parser.c @@ -6,6 +6,7 @@ #include #include #include +#include #include #include #include diff --git a/lib/string.c b/lib/string.c index 7548eb715ddb..77bd0b1d3296 100644 --- a/lib/string.c +++ b/lib/string.c @@ -977,7 +977,7 @@ void *memscan(void *addr, int c, size_t size) unsigned char *p = addr; while (size) { - if (*p == c) + if (*p == (unsigned char)c) return (void *)p; p++; size--; diff --git a/lib/string_helpers.c b/lib/string_helpers.c index 7f2d5fbaf243..5a35c7e16e96 100644 --- a/lib/string_helpers.c +++ b/lib/string_helpers.c @@ -452,18 +452,20 @@ static bool escape_hex(unsigned char c, char **dst, char *end) * The process of escaping byte buffer includes several parts. They are applied * in the following sequence. * - * 1. The character is matched to the printable class, if asked, and in - * case of match it passes through to the output. - * 2. The character is not matched to the one from @only string and thus + * 1. The character is not matched to the one from @only string and thus * must go as-is to the output. - * 3. The character is checked if it falls into the class given by @flags. + * 2. The character is matched to the printable and ASCII classes, if asked, + * and in case of match it passes through to the output. + * 3. The character is matched to the printable or ASCII class, if asked, + * and in case of match it passes through to the output. + * 4. The character is checked if it falls into the class given by @flags. * %ESCAPE_OCTAL and %ESCAPE_HEX are going last since they cover any * character. Note that they actually can't go together, otherwise * %ESCAPE_HEX will be ignored. * * Caller must provide valid source and destination pointers. Be aware that * destination buffer will not be NULL-terminated, thus caller have to append - * it if needs. The supported flags are:: + * it if needs. The supported flags are:: * * %ESCAPE_SPACE: (special white space, not space itself) * '\f' - form feed @@ -482,11 +484,27 @@ static bool escape_hex(unsigned char c, char **dst, char *end) * %ESCAPE_ANY: * all previous together * %ESCAPE_NP: - * escape only non-printable characters (checked by isprint) + * escape only non-printable characters, checked by isprint() * %ESCAPE_ANY_NP: * all previous together * %ESCAPE_HEX: * '\xHH' - byte with hexadecimal value HH (2 digits) + * %ESCAPE_NA: + * escape only non-ascii characters, checked by isascii() + * %ESCAPE_NAP: + * escape only non-printable or non-ascii characters + * %ESCAPE_APPEND: + * append characters from @only to be escaped by the given classes + * + * %ESCAPE_APPEND would help to pass additional characters to the escaped, when + * one of %ESCAPE_NP, %ESCAPE_NA, or %ESCAPE_NAP is provided. + * + * One notable caveat, the %ESCAPE_NAP, %ESCAPE_NP and %ESCAPE_NA have the + * higher priority than the rest of the flags (%ESCAPE_NAP is the highest). + * It doesn't make much sense to use either of them without %ESCAPE_OCTAL + * or %ESCAPE_HEX, because they cover most of the other character classes. + * %ESCAPE_NAP can utilize %ESCAPE_SPACE or %ESCAPE_SPECIAL in addition to + * the above. * * Return: * The total size of the escaped output that would be generated for @@ -500,41 +518,62 @@ int string_escape_mem(const char *src, size_t isz, char *dst, size_t osz, char *p = dst; char *end = p + osz; bool is_dict = only && *only; + bool is_append = flags & ESCAPE_APPEND; while (isz--) { unsigned char c = *src++; + bool in_dict = is_dict && strchr(only, c); /* * Apply rules in the following sequence: - * - the character is printable, when @flags has - * %ESCAPE_NP bit set * - the @only string is supplied and does not contain a * character under question + * - the character is printable and ASCII, when @flags has + * %ESCAPE_NAP bit set + * - the character is printable, when @flags has + * %ESCAPE_NP bit set + * - the character is ASCII, when @flags has + * %ESCAPE_NA bit set * - the character doesn't fall into a class of symbols * defined by given @flags * In these cases we just pass through a character to the * output buffer. + * + * When %ESCAPE_APPEND is passed, the characters from @only + * have been excluded from the %ESCAPE_NAP, %ESCAPE_NP, and + * %ESCAPE_NA cases. */ - if ((flags & ESCAPE_NP && isprint(c)) || - (is_dict && !strchr(only, c))) { - /* do nothing */ - } else { - if (flags & ESCAPE_SPACE && escape_space(c, &p, end)) - continue; + if (!(is_append || in_dict) && is_dict && + escape_passthrough(c, &p, end)) + continue; - if (flags & ESCAPE_SPECIAL && escape_special(c, &p, end)) - continue; + if (!(is_append && in_dict) && isascii(c) && isprint(c) && + flags & ESCAPE_NAP && escape_passthrough(c, &p, end)) + continue; - if (flags & ESCAPE_NULL && escape_null(c, &p, end)) - continue; + if (!(is_append && in_dict) && isprint(c) && + flags & ESCAPE_NP && escape_passthrough(c, &p, end)) + continue; - /* ESCAPE_OCTAL and ESCAPE_HEX always go last */ - if (flags & ESCAPE_OCTAL && escape_octal(c, &p, end)) - continue; + if (!(is_append && in_dict) && isascii(c) && + flags & ESCAPE_NA && escape_passthrough(c, &p, end)) + continue; - if (flags & ESCAPE_HEX && escape_hex(c, &p, end)) - continue; - } + if (flags & ESCAPE_SPACE && escape_space(c, &p, end)) + continue; + + if (flags & ESCAPE_SPECIAL && escape_special(c, &p, end)) + continue; + + if (flags & ESCAPE_NULL && escape_null(c, &p, end)) + continue; + + /* ESCAPE_OCTAL and ESCAPE_HEX always go last */ + if (flags & ESCAPE_OCTAL && escape_octal(c, &p, end)) + continue; + + if (flags & ESCAPE_HEX && escape_hex(c, &p, end)) + continue; escape_passthrough(c, &p, end); } @@ -543,25 +582,6 @@ int string_escape_mem(const char *src, size_t isz, char *dst, size_t osz, } EXPORT_SYMBOL(string_escape_mem); -int string_escape_mem_ascii(const char *src, size_t isz, char *dst, - size_t osz) -{ - char *p = dst; - char *end = p + osz; - - while (isz--) { - unsigned char c = *src++; - - if (!isprint(c) || !isascii(c) || c == '"' || c == '\\') - escape_hex(c, &p, end); - else - escape_passthrough(c, &p, end); - } - - return p - dst; -} -EXPORT_SYMBOL(string_escape_mem_ascii); - /* * Return an allocated string that has been escaped of special characters * and double quotes, making it safe to log in quotes. diff --git a/lib/test-string_helpers.c b/lib/test-string_helpers.c index 10360d4ea273..2185d71704f0 100644 --- a/lib/test-string_helpers.c +++ b/lib/test-string_helpers.c @@ -19,7 +19,7 @@ static __init bool test_string_check_buf(const char *name, unsigned int flags, if (q_real == q_test && !memcmp(out_test, out_real, q_test)) return true; - pr_warn("Test '%s' failed: flags = %u\n", name, flags); + pr_warn("Test '%s' failed: flags = %#x\n", name, flags); print_hex_dump(KERN_WARNING, "Input: ", DUMP_PREFIX_NONE, 16, 1, in, p, true); @@ -136,7 +136,7 @@ static const struct test_string_2 escape0[] __initconst = {{ .flags = ESCAPE_SPACE | ESCAPE_HEX, },{ /* terminator */ - }}, + }} },{ .in = "\\h\\\"\a\e\\", .s1 = {{ @@ -150,7 +150,7 @@ static const struct test_string_2 escape0[] __initconst = {{ .flags = ESCAPE_SPECIAL | ESCAPE_HEX, },{ /* terminator */ - }}, + }} },{ .in = "\eb \\C\007\"\x90\r]", .s1 = {{ @@ -201,12 +201,26 @@ static const struct test_string_2 escape0[] __initconst = {{ .flags = ESCAPE_NP | ESCAPE_HEX, },{ /* terminator */ - }}, + }} +},{ + .in = "\007 \eb\"\x90\xCF\r", + .s1 = {{ + .out = "\007 \eb\"\\220\\317\r", + .flags = ESCAPE_OCTAL | ESCAPE_NA, + },{ + .out = "\007 \eb\"\\x90\\xcf\r", + .flags = ESCAPE_HEX | ESCAPE_NA, + },{ + .out = "\007 \eb\"\x90\xCF\r", + .flags = ESCAPE_NA, + },{ + /* terminator */ + }} },{ /* terminator */ }}; -#define TEST_STRING_2_DICT_1 "b\\ \t\r" +#define TEST_STRING_2_DICT_1 "b\\ \t\r\xCF" static const struct test_string_2 escape1[] __initconst = {{ .in = "\f\\ \n\r\t\v", .s1 = {{ @@ -216,16 +230,40 @@ static const struct test_string_2 escape1[] __initconst = {{ .out = "\f\\x5c\\x20\n\\x0d\\x09\v", .flags = ESCAPE_HEX, },{ - /* terminator */ - }}, -},{ - .in = "\\h\\\"\a\e\\", - .s1 = {{ - .out = "\\134h\\134\"\a\e\\134", - .flags = ESCAPE_OCTAL, + .out = "\f\\134\\040\n\\015\\011\v", + .flags = ESCAPE_ANY | ESCAPE_APPEND, + },{ + .out = "\\014\\134\\040\\012\\015\\011\\013", + .flags = ESCAPE_OCTAL | ESCAPE_APPEND | ESCAPE_NAP, + },{ + .out = "\\x0c\\x5c\\x20\\x0a\\x0d\\x09\\x0b", + .flags = ESCAPE_HEX | ESCAPE_APPEND | ESCAPE_NAP, + },{ + .out = "\f\\134\\040\n\\015\\011\v", + .flags = ESCAPE_OCTAL | ESCAPE_APPEND | ESCAPE_NA, + },{ + .out = "\f\\x5c\\x20\n\\x0d\\x09\v", + .flags = ESCAPE_HEX | ESCAPE_APPEND | ESCAPE_NA, },{ /* terminator */ - }}, + }} +},{ + .in = "\\h\\\"\a\xCF\e\\", + .s1 = {{ + .out = "\\134h\\134\"\a\\317\e\\134", + .flags = ESCAPE_OCTAL, + },{ + .out = "\\134h\\134\"\a\\317\e\\134", + .flags = ESCAPE_ANY | ESCAPE_APPEND, + },{ + .out = "\\134h\\134\"\\007\\317\\033\\134", + .flags = ESCAPE_OCTAL | ESCAPE_APPEND | ESCAPE_NAP, + },{ + .out = "\\134h\\134\"\a\\317\e\\134", + .flags = ESCAPE_OCTAL | ESCAPE_APPEND | ESCAPE_NA, + },{ + /* terminator */ + }} },{ .in = "\eb \\C\007\"\x90\r]", .s1 = {{ @@ -233,7 +271,89 @@ static const struct test_string_2 escape1[] __initconst = {{ .flags = ESCAPE_OCTAL, },{ /* terminator */ - }}, + }} +},{ + .in = "\007 \eb\"\x90\xCF\r", + .s1 = {{ + .out = "\007 \eb\"\x90\xCF\r", + .flags = ESCAPE_NA, + },{ + .out = "\007 \eb\"\x90\xCF\r", + .flags = ESCAPE_SPACE | ESCAPE_NA, + },{ + .out = "\007 \eb\"\x90\xCF\r", + .flags = ESCAPE_SPECIAL | ESCAPE_NA, + },{ + .out = "\007 \eb\"\x90\xCF\r", + .flags = ESCAPE_SPACE | ESCAPE_SPECIAL | ESCAPE_NA, + },{ + .out = "\007 \eb\"\x90\\317\r", + .flags = ESCAPE_OCTAL | ESCAPE_NA, + },{ + .out = "\007 \eb\"\x90\\317\r", + .flags = ESCAPE_SPACE | ESCAPE_OCTAL | ESCAPE_NA, + },{ + .out = "\007 \eb\"\x90\\317\r", + .flags = ESCAPE_SPECIAL | ESCAPE_OCTAL | ESCAPE_NA, + },{ + .out = "\007 \eb\"\x90\\317\r", + .flags = ESCAPE_ANY | ESCAPE_NA, + },{ + .out = "\007 \eb\"\x90\\xcf\r", + .flags = ESCAPE_HEX | ESCAPE_NA, + },{ + .out = "\007 \eb\"\x90\\xcf\r", + .flags = ESCAPE_SPACE | ESCAPE_HEX | ESCAPE_NA, + },{ + .out = "\007 \eb\"\x90\\xcf\r", + .flags = ESCAPE_SPECIAL | ESCAPE_HEX | ESCAPE_NA, + },{ + .out = "\007 \eb\"\x90\\xcf\r", + .flags = ESCAPE_SPACE | ESCAPE_SPECIAL | ESCAPE_HEX | ESCAPE_NA, + },{ + /* terminator */ + }} +},{ + .in = "\007 \eb\"\x90\xCF\r", + .s1 = {{ + .out = "\007 \eb\"\x90\xCF\r", + .flags = ESCAPE_NAP, + },{ + .out = "\007 \eb\"\x90\xCF\\r", + .flags = ESCAPE_SPACE | ESCAPE_NAP, + },{ + .out = "\007 \eb\"\x90\xCF\r", + .flags = ESCAPE_SPECIAL | ESCAPE_NAP, + },{ + .out = "\007 \eb\"\x90\xCF\\r", + .flags = ESCAPE_SPACE | ESCAPE_SPECIAL | ESCAPE_NAP, + },{ + .out = "\007 \eb\"\x90\\317\\015", + .flags = ESCAPE_OCTAL | ESCAPE_NAP, + },{ + .out = "\007 \eb\"\x90\\317\\r", + .flags = ESCAPE_SPACE | ESCAPE_OCTAL | ESCAPE_NAP, + },{ + .out = "\007 \eb\"\x90\\317\\015", + .flags = ESCAPE_SPECIAL | ESCAPE_OCTAL | ESCAPE_NAP, + },{ + .out = "\007 \eb\"\x90\\317\r", + .flags = ESCAPE_ANY | ESCAPE_NAP, + },{ + .out = "\007 \eb\"\x90\\xcf\\x0d", + .flags = ESCAPE_HEX | ESCAPE_NAP, + },{ + .out = "\007 \eb\"\x90\\xcf\\r", + .flags = ESCAPE_SPACE | ESCAPE_HEX | ESCAPE_NAP, + },{ + .out = "\007 \eb\"\x90\\xcf\\x0d", + .flags = ESCAPE_SPECIAL | ESCAPE_HEX | ESCAPE_NAP, + },{ + .out = "\007 \eb\"\x90\\xcf\\r", + .flags = ESCAPE_SPACE | ESCAPE_SPECIAL | ESCAPE_HEX | ESCAPE_NAP, + },{ + /* terminator */ + }} },{ /* terminator */ }}; @@ -290,7 +410,7 @@ test_string_escape_overflow(const char *in, int p, unsigned int flags, const cha q_real = string_escape_mem(in, p, NULL, 0, flags, esc); if (q_real != q_test) - pr_warn("Test '%s' failed: flags = %u, osz = 0, expected %d, got %d\n", + pr_warn("Test '%s' failed: flags = %#x, osz = 0, expected %d, got %d\n", name, flags, q_test, q_real); } @@ -315,8 +435,13 @@ static __init void test_string_escape(const char *name, /* NULL injection */ if (flags & ESCAPE_NULL) { in[p++] = '\0'; - out_test[q_test++] = '\\'; - out_test[q_test++] = '0'; + /* '\0' passes isascii() test */ + if (flags & ESCAPE_NA && !(flags & ESCAPE_APPEND && esc)) { + out_test[q_test++] = '\0'; + } else { + out_test[q_test++] = '\\'; + out_test[q_test++] = '0'; + } } /* Don't try strings that have no output */ @@ -459,17 +584,17 @@ static int __init test_string_helpers_init(void) unsigned int i; pr_info("Running tests...\n"); - for (i = 0; i < UNESCAPE_ANY + 1; i++) + for (i = 0; i < UNESCAPE_ALL_MASK + 1; i++) test_string_unescape("unescape", i, false); test_string_unescape("unescape inplace", get_random_int() % (UNESCAPE_ANY + 1), true); /* Without dictionary */ - for (i = 0; i < (ESCAPE_ANY_NP | ESCAPE_HEX) + 1; i++) + for (i = 0; i < ESCAPE_ALL_MASK + 1; i++) test_string_escape("escape 0", escape0, i, TEST_STRING_2_DICT_0); /* With dictionary */ - for (i = 0; i < (ESCAPE_ANY_NP | ESCAPE_HEX) + 1; i++) + for (i = 0; i < ESCAPE_ALL_MASK + 1; i++) test_string_escape("escape 1", escape1, i, TEST_STRING_2_DICT_1); /* Test string_get_size() */ diff --git a/lib/test_hmm.c b/lib/test_hmm.c index 15f2e2db77bc..8c55c4723692 100644 --- a/lib/test_hmm.c +++ b/lib/test_hmm.c @@ -25,6 +25,7 @@ #include #include #include +#include #include "test_hmm_uapi.h" @@ -46,6 +47,7 @@ struct dmirror_bounce { unsigned long cpages; }; +#define DPT_XA_TAG_ATOMIC 1UL #define DPT_XA_TAG_WRITE 3UL /* @@ -218,7 +220,7 @@ static bool dmirror_interval_invalidate(struct mmu_interval_notifier *mni, * the invalidation is handled as part of the migration process. */ if (range->event == MMU_NOTIFY_MIGRATE && - range->migrate_pgmap_owner == dmirror->mdevice) + range->owner == dmirror->mdevice) return true; if (mmu_notifier_range_blockable(range)) @@ -619,6 +621,54 @@ static void dmirror_migrate_alloc_and_copy(struct migrate_vma *args, } } +static int dmirror_check_atomic(struct dmirror *dmirror, unsigned long start, + unsigned long end) +{ + unsigned long pfn; + + for (pfn = start >> PAGE_SHIFT; pfn < (end >> PAGE_SHIFT); pfn++) { + void *entry; + struct page *page; + + entry = xa_load(&dmirror->pt, pfn); + page = xa_untag_pointer(entry); + if (xa_pointer_tag(entry) == DPT_XA_TAG_ATOMIC) + return -EPERM; + } + + return 0; +} + +static int dmirror_atomic_map(unsigned long start, unsigned long end, + struct page **pages, struct dmirror *dmirror) +{ + unsigned long pfn, mapped = 0; + int i; + + /* Map the migrated pages into the device's page tables. */ + mutex_lock(&dmirror->mutex); + + for (i = 0, pfn = start >> PAGE_SHIFT; pfn < (end >> PAGE_SHIFT); pfn++, i++) { + void *entry; + + if (!pages[i]) + continue; + + entry = pages[i]; + entry = xa_tag_pointer(entry, DPT_XA_TAG_ATOMIC); + entry = xa_store(&dmirror->pt, pfn, entry, GFP_ATOMIC); + if (xa_is_err(entry)) { + mutex_unlock(&dmirror->mutex); + return xa_err(entry); + } + + mapped++; + } + + mutex_unlock(&dmirror->mutex); + return mapped; +} + static int dmirror_migrate_finalize_and_map(struct migrate_vma *args, struct dmirror *dmirror) { @@ -661,6 +711,72 @@ static int dmirror_migrate_finalize_and_map(struct migrate_vma *args, return 0; } +static int dmirror_exclusive(struct dmirror *dmirror, + struct hmm_dmirror_cmd *cmd) +{ + unsigned long start, end, addr; + unsigned long size = cmd->npages << PAGE_SHIFT; + struct mm_struct *mm = dmirror->notifier.mm; + struct page *pages[64]; + struct dmirror_bounce bounce; + unsigned long next; + int ret; + + start = cmd->addr; + end = start + size; + if (end < start) + return -EINVAL; + + /* Since the mm is for the mirrored process, get a reference first. */ + if (!mmget_not_zero(mm)) + return -EINVAL; + + mmap_read_lock(mm); + for (addr = start; addr < end; addr = next) { + unsigned long mapped; + int i; + + if (end < addr + (ARRAY_SIZE(pages) << PAGE_SHIFT)) + next = end; + else + next = addr + (ARRAY_SIZE(pages) << PAGE_SHIFT); + + ret = make_device_exclusive_range(mm, addr, next, pages, NULL); + mapped = dmirror_atomic_map(addr, next, pages, dmirror); + for (i = 0; i < ret; i++) { + if (pages[i]) { + unlock_page(pages[i]); + put_page(pages[i]); + } + } + + if (addr + (mapped << PAGE_SHIFT) < next) { + mmap_read_unlock(mm); + mmput(mm); + return -EBUSY; + } + } + mmap_read_unlock(mm); + mmput(mm); + + /* Return the migrated data for verification. */ + ret = dmirror_bounce_init(&bounce, start, size); + if (ret) + return ret; + mutex_lock(&dmirror->mutex); + ret = dmirror_do_read(dmirror, start, end, &bounce); + mutex_unlock(&dmirror->mutex); + if (ret == 0) { + if (copy_to_user(u64_to_user_ptr(cmd->ptr), bounce.ptr, + bounce.size)) + ret = -EFAULT; + } + + cmd->cpages = bounce.cpages; + dmirror_bounce_fini(&bounce); + return ret; +} + static int dmirror_migrate(struct dmirror *dmirror, struct hmm_dmirror_cmd *cmd) { @@ -948,6 +1064,15 @@ static long dmirror_fops_unlocked_ioctl(struct file *filp, ret = dmirror_migrate(dmirror, &cmd); break; + case HMM_DMIRROR_EXCLUSIVE: + ret = dmirror_exclusive(dmirror, &cmd); + break; + + case HMM_DMIRROR_CHECK_EXCLUSIVE: + ret = dmirror_check_atomic(dmirror, cmd.addr, + cmd.addr + (cmd.npages << PAGE_SHIFT)); + break; + case HMM_DMIRROR_SNAPSHOT: ret = dmirror_snapshot(dmirror, &cmd); break; diff --git a/lib/test_hmm_uapi.h b/lib/test_hmm_uapi.h index 670b4ef2a5b6..f14dea5dcd06 100644 --- a/lib/test_hmm_uapi.h +++ b/lib/test_hmm_uapi.h @@ -33,6 +33,8 @@ struct hmm_dmirror_cmd { #define HMM_DMIRROR_WRITE _IOWR('H', 0x01, struct hmm_dmirror_cmd) #define HMM_DMIRROR_MIGRATE _IOWR('H', 0x02, struct hmm_dmirror_cmd) #define HMM_DMIRROR_SNAPSHOT _IOWR('H', 0x03, struct hmm_dmirror_cmd) +#define HMM_DMIRROR_EXCLUSIVE _IOWR('H', 0x04, struct hmm_dmirror_cmd) +#define HMM_DMIRROR_CHECK_EXCLUSIVE _IOWR('H', 0x05, struct hmm_dmirror_cmd) /* * Values returned in hmm_dmirror_cmd.ptr for HMM_DMIRROR_SNAPSHOT. diff --git a/lib/test_string.c b/lib/test_string.c index 7b31f4a505bf..9dfd6f52de92 100644 --- a/lib/test_string.c +++ b/lib/test_string.c @@ -179,6 +179,10 @@ static __init int strnchr_selftest(void) return 0; } +static __exit void string_selftest_remove(void) +{ +} + static __init int string_selftest_init(void) { int test, subtest; @@ -216,4 +220,5 @@ static __init int string_selftest_init(void) } module_init(string_selftest_init); +module_exit(string_selftest_remove); MODULE_LICENSE("GPL v2"); diff --git a/lib/vsprintf.c b/lib/vsprintf.c index e5c7afbf7405..2926cc27623f 100644 --- a/lib/vsprintf.c +++ b/lib/vsprintf.c @@ -86,6 +86,7 @@ static unsigned long long simple_strntoull(const char *startp, size_t max_chars, * * This function has caveats. Please use kstrtoull instead. */ +noinline unsigned long long simple_strtoull(const char *cp, char **endp, unsigned int base) { return simple_strntoull(cp, INT_MAX, endp, base); diff --git a/lib/xz/xz_dec_bcj.c b/lib/xz/xz_dec_bcj.c index 72ddac6ef2ec..ef449e97d1a1 100644 --- a/lib/xz/xz_dec_bcj.c +++ b/lib/xz/xz_dec_bcj.c @@ -422,7 +422,7 @@ XZ_EXTERN enum xz_ret xz_dec_bcj_run(struct xz_dec_bcj *s, /* * Flush pending already filtered data to the output buffer. Return - * immediatelly if we couldn't flush everything, or if the next + * immediately if we couldn't flush everything, or if the next * filter in the chain had already returned XZ_STREAM_END. */ if (s->temp.filtered > 0) { diff --git a/lib/xz/xz_dec_lzma2.c b/lib/xz/xz_dec_lzma2.c index ca2603abee08..7a6781e3f47b 100644 --- a/lib/xz/xz_dec_lzma2.c +++ b/lib/xz/xz_dec_lzma2.c @@ -147,8 +147,8 @@ struct lzma_dec { /* * LZMA properties or related bit masks (number of literal - * context bits, a mask dervied from the number of literal - * position bits, and a mask dervied from the number + * context bits, a mask derived from the number of literal + * position bits, and a mask derived from the number * position bits) */ uint32_t lc; @@ -484,7 +484,7 @@ static __always_inline void rc_normalize(struct rc_dec *rc) } /* - * Decode one bit. In some versions, this function has been splitted in three + * Decode one bit. In some versions, this function has been split in three * functions so that the compiler is supposed to be able to more easily avoid * an extra branch. In this particular version of the LZMA decoder, this * doesn't seem to be a good idea (tested with GCC 3.3.6, 3.4.6, and 4.3.3 @@ -761,7 +761,7 @@ static bool lzma_main(struct xz_dec_lzma2 *s) } /* - * Reset the LZMA decoder and range decoder state. Dictionary is nore reset + * Reset the LZMA decoder and range decoder state. Dictionary is not reset * here, because LZMA state may be reset without resetting the dictionary. */ static void lzma_reset(struct xz_dec_lzma2 *s) diff --git a/lib/zlib_inflate/inffast.c b/lib/zlib_inflate/inffast.c index ed1f3df27260..f19c4fbe1be7 100644 --- a/lib/zlib_inflate/inffast.c +++ b/lib/zlib_inflate/inffast.c @@ -15,7 +15,7 @@ union uu { unsigned char b[2]; }; -/* Endian independed version */ +/* Endian independent version */ static inline unsigned short get_unaligned16(const unsigned short *p) { diff --git a/lib/zstd/huf.h b/lib/zstd/huf.h index 2143da28d952..923218d12e28 100644 --- a/lib/zstd/huf.h +++ b/lib/zstd/huf.h @@ -134,7 +134,7 @@ typedef enum { HUF_repeat_none, /**< Cannot use the previous table */ HUF_repeat_check, /**< Can use the previous table but it must be checked. Note : The previous table must have been constructed by HUF_compress{1, 4}X_repeat */ - HUF_repeat_valid /**< Can use the previous table and it is asumed to be valid */ + HUF_repeat_valid /**< Can use the previous table and it is assumed to be valid */ } HUF_repeat; /** HUF_compress4X_repeat() : * Same as HUF_compress4X_wksp(), but considers using hufTable if *repeat != HUF_repeat_none. diff --git a/mm/Kconfig b/mm/Kconfig index ded98fb859ab..a02498c0e13d 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -96,6 +96,9 @@ config HAVE_FAST_GUP depends on MMU bool +config HOLES_IN_ZONE + bool + # Don't discard allocated memory used to track "memory" and "reserved" memblocks # after early boot, so it can still be used to test for validity of memory. # Also, memblocks are updated with memory hot(un)plug. @@ -671,6 +674,7 @@ config ZPOOL config ZBUD tristate "Low (Up to 2x) density storage for compressed pages" + depends on ZPOOL help A special purpose allocator for storing compressed pages. It is designed to store up to two compressed pages per physical @@ -757,6 +761,18 @@ config ARCH_HAS_CACHE_LINE_SIZE config ARCH_HAS_PTE_DEVMAP bool +config ARCH_HAS_ZONE_DMA_SET + bool + +config ZONE_DMA + bool "Support DMA zone" if ARCH_HAS_ZONE_DMA_SET + default y if ARM64 || X86 + +config ZONE_DMA32 + bool "Support DMA32 zone" if ARCH_HAS_ZONE_DMA_SET + depends on !X86_32 + default y if ARM64 + config ZONE_DEVICE bool "Device memory (pmem, HMM, etc...) hotplug support" depends on MEMORY_HOTPLUG diff --git a/mm/Makefile b/mm/Makefile index bf71e295e9f6..74b47c354682 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -75,6 +75,7 @@ obj-$(CONFIG_FRONTSWAP) += frontswap.o obj-$(CONFIG_ZSWAP) += zswap.o obj-$(CONFIG_HAS_DMA) += dmapool.o obj-$(CONFIG_HUGETLBFS) += hugetlb.o +obj-$(CONFIG_HUGETLB_PAGE_FREE_VMEMMAP) += hugetlb_vmemmap.o obj-$(CONFIG_NUMA) += mempolicy.o obj-$(CONFIG_SPARSEMEM) += sparse.o obj-$(CONFIG_SPARSEMEM_VMEMMAP) += sparse-vmemmap.o @@ -125,3 +126,4 @@ obj-$(CONFIG_MAPPING_DIRTY_HELPERS) += mapping_dirty_helpers.o obj-$(CONFIG_PTDUMP_CORE) += ptdump.o obj-$(CONFIG_PAGE_REPORTING) += page_reporting.o obj-$(CONFIG_IO_MAPPING) += io-mapping.o +obj-$(CONFIG_HAVE_BOOTMEM_INFO_NODE) += bootmem_info.o diff --git a/mm/bootmem_info.c b/mm/bootmem_info.c new file mode 100644 index 000000000000..5b152dba7344 --- /dev/null +++ b/mm/bootmem_info.c @@ -0,0 +1,127 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Bootmem core functions. + * + * Copyright (c) 2020, Bytedance. + * + * Author: Muchun Song + * + */ +#include +#include +#include +#include +#include + +void get_page_bootmem(unsigned long info, struct page *page, unsigned long type) +{ + page->freelist = (void *)type; + SetPagePrivate(page); + set_page_private(page, info); + page_ref_inc(page); +} + +void put_page_bootmem(struct page *page) +{ + unsigned long type; + + type = (unsigned long) page->freelist; + BUG_ON(type < MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE || + type > MEMORY_HOTPLUG_MAX_BOOTMEM_TYPE); + + if (page_ref_dec_return(page) == 1) { + page->freelist = NULL; + ClearPagePrivate(page); + set_page_private(page, 0); + INIT_LIST_HEAD(&page->lru); + free_reserved_page(page); + } +} + +#ifndef CONFIG_SPARSEMEM_VMEMMAP +static void register_page_bootmem_info_section(unsigned long start_pfn) +{ + unsigned long mapsize, section_nr, i; + struct mem_section *ms; + struct page *page, *memmap; + struct mem_section_usage *usage; + + section_nr = pfn_to_section_nr(start_pfn); + ms = __nr_to_section(section_nr); + + /* Get section's memmap address */ + memmap = sparse_decode_mem_map(ms->section_mem_map, section_nr); + + /* + * Get page for the memmap's phys address + * XXX: need more consideration for sparse_vmemmap... + */ + page = virt_to_page(memmap); + mapsize = sizeof(struct page) * PAGES_PER_SECTION; + mapsize = PAGE_ALIGN(mapsize) >> PAGE_SHIFT; + + /* remember memmap's page */ + for (i = 0; i < mapsize; i++, page++) + get_page_bootmem(section_nr, page, SECTION_INFO); + + usage = ms->usage; + page = virt_to_page(usage); + + mapsize = PAGE_ALIGN(mem_section_usage_size()) >> PAGE_SHIFT; + + for (i = 0; i < mapsize; i++, page++) + get_page_bootmem(section_nr, page, MIX_SECTION_INFO); + +} +#else /* CONFIG_SPARSEMEM_VMEMMAP */ +static void register_page_bootmem_info_section(unsigned long start_pfn) +{ + unsigned long mapsize, section_nr, i; + struct mem_section *ms; + struct page *page, *memmap; + struct mem_section_usage *usage; + + section_nr = pfn_to_section_nr(start_pfn); + ms = __nr_to_section(section_nr); + + memmap = sparse_decode_mem_map(ms->section_mem_map, section_nr); + + register_page_bootmem_memmap(section_nr, memmap, PAGES_PER_SECTION); + + usage = ms->usage; + page = virt_to_page(usage); + + mapsize = PAGE_ALIGN(mem_section_usage_size()) >> PAGE_SHIFT; + + for (i = 0; i < mapsize; i++, page++) + get_page_bootmem(section_nr, page, MIX_SECTION_INFO); +} +#endif /* !CONFIG_SPARSEMEM_VMEMMAP */ + +void __init register_page_bootmem_info_node(struct pglist_data *pgdat) +{ + unsigned long i, pfn, end_pfn, nr_pages; + int node = pgdat->node_id; + struct page *page; + + nr_pages = PAGE_ALIGN(sizeof(struct pglist_data)) >> PAGE_SHIFT; + page = virt_to_page(pgdat); + + for (i = 0; i < nr_pages; i++, page++) + get_page_bootmem(node, page, NODE_INFO); + + pfn = pgdat->node_start_pfn; + end_pfn = pgdat_end_pfn(pgdat); + + /* register section info */ + for (; pfn < end_pfn; pfn += PAGES_PER_SECTION) { + /* + * Some platforms can assign the same pfn to multiple nodes - on + * node0 as well as nodeN. To avoid registering a pfn against + * multiple nodes we check that this pfn does not already + * reside in some other nodes. + */ + if (pfn_valid(pfn) && (early_pfn_to_nid(pfn) == node)) + register_page_bootmem_info_section(pfn); + } +} diff --git a/mm/compaction.c b/mm/compaction.c index 3a509fbf2bea..621508e0ecd5 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -1297,8 +1297,7 @@ move_freelist_head(struct list_head *freelist, struct page *freepage) if (!list_is_last(freelist, &freepage->lru)) { list_cut_before(&sublist, freelist, &freepage->lru); - if (!list_empty(&sublist)) - list_splice_tail(&sublist, freelist); + list_splice_tail(&sublist, freelist); } } @@ -1315,8 +1314,7 @@ move_freelist_tail(struct list_head *freelist, struct page *freepage) if (!list_is_first(freelist, &freepage->lru)) { list_cut_position(&sublist, freelist, &freepage->lru); - if (!list_empty(&sublist)) - list_splice_tail(&sublist, freelist); + list_splice_tail(&sublist, freelist); } } @@ -1380,7 +1378,7 @@ static int next_search_order(struct compact_control *cc, int order) static unsigned long fast_isolate_freepages(struct compact_control *cc) { - unsigned int limit = min(1U, freelist_scan_limit(cc) >> 1); + unsigned int limit = max(1U, freelist_scan_limit(cc) >> 1); unsigned int nr_scanned = 0; unsigned long low_pfn, min_pfn, highest = 0; unsigned long nr_isolated = 0; @@ -1492,11 +1490,11 @@ fast_isolate_freepages(struct compact_control *cc) spin_unlock_irqrestore(&cc->zone->lock, flags); /* - * Smaller scan on next order so the total scan ig related + * Smaller scan on next order so the total scan is related * to freelist_scan_limit. */ if (order_scanned >= limit) - limit = min(1U, limit >> 1); + limit = max(1U, limit >> 1); } if (!page) { @@ -2722,9 +2720,9 @@ int sysctl_compaction_handler(struct ctl_table *table, int write, } #if defined(CONFIG_SYSFS) && defined(CONFIG_NUMA) -static ssize_t sysfs_compact_node(struct device *dev, - struct device_attribute *attr, - const char *buf, size_t count) +static ssize_t compact_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) { int nid = dev->id; @@ -2737,7 +2735,7 @@ static ssize_t sysfs_compact_node(struct device *dev, return count; } -static DEVICE_ATTR(compact, 0200, NULL, sysfs_compact_node); +static DEVICE_ATTR_WO(compact); int compaction_register_node(struct node *node) { diff --git a/mm/debug_vm_pgtable.c b/mm/debug_vm_pgtable.c index 92bfc37300df..1c922691aa61 100644 --- a/mm/debug_vm_pgtable.c +++ b/mm/debug_vm_pgtable.c @@ -91,7 +91,7 @@ static void __init pte_advanced_tests(struct mm_struct *mm, unsigned long pfn, unsigned long vaddr, pgprot_t prot) { - pte_t pte = pfn_pte(pfn, prot); + pte_t pte; /* * Architectures optimize set_pte_at by avoiding TLB flush. @@ -248,29 +248,6 @@ static void __init pmd_leaf_tests(unsigned long pfn, pgprot_t prot) WARN_ON(!pmd_leaf(pmd)); } -#ifdef CONFIG_HAVE_ARCH_HUGE_VMAP -static void __init pmd_huge_tests(pmd_t *pmdp, unsigned long pfn, pgprot_t prot) -{ - pmd_t pmd; - - if (!arch_vmap_pmd_supported(prot)) - return; - - pr_debug("Validating PMD huge\n"); - /* - * X86 defined pmd_set_huge() verifies that the given - * PMD is not a populated non-leaf entry. - */ - WRITE_ONCE(*pmdp, __pmd(0)); - WARN_ON(!pmd_set_huge(pmdp, __pfn_to_phys(pfn), prot)); - WARN_ON(!pmd_clear_huge(pmdp)); - pmd = READ_ONCE(*pmdp); - WARN_ON(!pmd_none(pmd)); -} -#else /* CONFIG_HAVE_ARCH_HUGE_VMAP */ -static void __init pmd_huge_tests(pmd_t *pmdp, unsigned long pfn, pgprot_t prot) { } -#endif /* CONFIG_HAVE_ARCH_HUGE_VMAP */ - static void __init pmd_savedwrite_tests(unsigned long pfn, pgprot_t prot) { pmd_t pmd; @@ -395,8 +372,56 @@ static void __init pud_leaf_tests(unsigned long pfn, pgprot_t prot) pud = pud_mkhuge(pud); WARN_ON(!pud_leaf(pud)); } +#else /* !CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */ +static void __init pud_basic_tests(struct mm_struct *mm, unsigned long pfn, int idx) { } +static void __init pud_advanced_tests(struct mm_struct *mm, + struct vm_area_struct *vma, pud_t *pudp, + unsigned long pfn, unsigned long vaddr, + pgprot_t prot) +{ +} +static void __init pud_leaf_tests(unsigned long pfn, pgprot_t prot) { } +#endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */ +#else /* !CONFIG_TRANSPARENT_HUGEPAGE */ +static void __init pmd_basic_tests(unsigned long pfn, int idx) { } +static void __init pud_basic_tests(struct mm_struct *mm, unsigned long pfn, int idx) { } +static void __init pmd_advanced_tests(struct mm_struct *mm, + struct vm_area_struct *vma, pmd_t *pmdp, + unsigned long pfn, unsigned long vaddr, + pgprot_t prot, pgtable_t pgtable) +{ +} +static void __init pud_advanced_tests(struct mm_struct *mm, + struct vm_area_struct *vma, pud_t *pudp, + unsigned long pfn, unsigned long vaddr, + pgprot_t prot) +{ +} +static void __init pmd_leaf_tests(unsigned long pfn, pgprot_t prot) { } +static void __init pud_leaf_tests(unsigned long pfn, pgprot_t prot) { } +static void __init pmd_savedwrite_tests(unsigned long pfn, pgprot_t prot) { } +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #ifdef CONFIG_HAVE_ARCH_HUGE_VMAP +static void __init pmd_huge_tests(pmd_t *pmdp, unsigned long pfn, pgprot_t prot) +{ + pmd_t pmd; + + if (!arch_vmap_pmd_supported(prot)) + return; + + pr_debug("Validating PMD huge\n"); + /* + * X86 defined pmd_set_huge() verifies that the given + * PMD is not a populated non-leaf entry. + */ + WRITE_ONCE(*pmdp, __pmd(0)); + WARN_ON(!pmd_set_huge(pmdp, __pfn_to_phys(pfn), prot)); + WARN_ON(!pmd_clear_huge(pmdp)); + pmd = READ_ONCE(*pmdp); + WARN_ON(!pmd_none(pmd)); +} + static void __init pud_huge_tests(pud_t *pudp, unsigned long pfn, pgprot_t prot) { pud_t pud; @@ -416,47 +441,9 @@ static void __init pud_huge_tests(pud_t *pudp, unsigned long pfn, pgprot_t prot) WARN_ON(!pud_none(pud)); } #else /* !CONFIG_HAVE_ARCH_HUGE_VMAP */ +static void __init pmd_huge_tests(pmd_t *pmdp, unsigned long pfn, pgprot_t prot) { } static void __init pud_huge_tests(pud_t *pudp, unsigned long pfn, pgprot_t prot) { } -#endif /* !CONFIG_HAVE_ARCH_HUGE_VMAP */ - -#else /* !CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */ -static void __init pud_basic_tests(struct mm_struct *mm, unsigned long pfn, int idx) { } -static void __init pud_advanced_tests(struct mm_struct *mm, - struct vm_area_struct *vma, pud_t *pudp, - unsigned long pfn, unsigned long vaddr, - pgprot_t prot) -{ -} -static void __init pud_leaf_tests(unsigned long pfn, pgprot_t prot) { } -static void __init pud_huge_tests(pud_t *pudp, unsigned long pfn, pgprot_t prot) -{ -} -#endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */ -#else /* !CONFIG_TRANSPARENT_HUGEPAGE */ -static void __init pmd_basic_tests(unsigned long pfn, int idx) { } -static void __init pud_basic_tests(struct mm_struct *mm, unsigned long pfn, int idx) { } -static void __init pmd_advanced_tests(struct mm_struct *mm, - struct vm_area_struct *vma, pmd_t *pmdp, - unsigned long pfn, unsigned long vaddr, - pgprot_t prot, pgtable_t pgtable) -{ -} -static void __init pud_advanced_tests(struct mm_struct *mm, - struct vm_area_struct *vma, pud_t *pudp, - unsigned long pfn, unsigned long vaddr, - pgprot_t prot) -{ -} -static void __init pmd_leaf_tests(unsigned long pfn, pgprot_t prot) { } -static void __init pud_leaf_tests(unsigned long pfn, pgprot_t prot) { } -static void __init pmd_huge_tests(pmd_t *pmdp, unsigned long pfn, pgprot_t prot) -{ -} -static void __init pud_huge_tests(pud_t *pudp, unsigned long pfn, pgprot_t prot) -{ -} -static void __init pmd_savedwrite_tests(unsigned long pfn, pgprot_t prot) { } -#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ +#endif /* CONFIG_HAVE_ARCH_HUGE_VMAP */ static void __init p4d_basic_tests(unsigned long pfn, pgprot_t prot) { @@ -791,12 +778,12 @@ static void __init pmd_swap_soft_dirty_tests(unsigned long pfn, pgprot_t prot) WARN_ON(!pmd_swp_soft_dirty(pmd_swp_mksoft_dirty(pmd))); WARN_ON(pmd_swp_soft_dirty(pmd_swp_clear_soft_dirty(pmd))); } -#else /* !CONFIG_ARCH_HAS_PTE_DEVMAP */ +#else /* !CONFIG_TRANSPARENT_HUGEPAGE */ static void __init pmd_soft_dirty_tests(unsigned long pfn, pgprot_t prot) { } static void __init pmd_swap_soft_dirty_tests(unsigned long pfn, pgprot_t prot) { } -#endif /* CONFIG_ARCH_HAS_PTE_DEVMAP */ +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ static void __init pte_swap_tests(unsigned long pfn, pgprot_t prot) { @@ -856,17 +843,17 @@ static void __init swap_migration_tests(void) * locked, otherwise it stumbles upon a BUG_ON(). */ __SetPageLocked(page); - swp = make_migration_entry(page, 1); + swp = make_writable_migration_entry(page_to_pfn(page)); WARN_ON(!is_migration_entry(swp)); - WARN_ON(!is_write_migration_entry(swp)); + WARN_ON(!is_writable_migration_entry(swp)); - make_migration_entry_read(&swp); + swp = make_readable_migration_entry(swp_offset(swp)); WARN_ON(!is_migration_entry(swp)); - WARN_ON(is_write_migration_entry(swp)); + WARN_ON(is_writable_migration_entry(swp)); - swp = make_migration_entry(page, 0); + swp = make_readable_migration_entry(page_to_pfn(page)); WARN_ON(!is_migration_entry(swp)); - WARN_ON(is_write_migration_entry(swp)); + WARN_ON(is_writable_migration_entry(swp)); __ClearPageLocked(page); __free_page(page); } diff --git a/mm/gup.c b/mm/gup.c index 8651309f8ec3..728d996767cb 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -1500,6 +1500,64 @@ long populate_vma_page_range(struct vm_area_struct *vma, NULL, NULL, locked); } +/* + * faultin_vma_page_range() - populate (prefault) page tables inside the + * given VMA range readable/writable + * + * This takes care of mlocking the pages, too, if VM_LOCKED is set. + * + * @vma: target vma + * @start: start address + * @end: end address + * @write: whether to prefault readable or writable + * @locked: whether the mmap_lock is still held + * + * Returns either number of processed pages in the vma, or a negative error + * code on error (see __get_user_pages()). + * + * vma->vm_mm->mmap_lock must be held. The range must be page-aligned and + * covered by the VMA. + * + * If @locked is NULL, it may be held for read or write and will be unperturbed. + * + * If @locked is non-NULL, it must held for read only and may be released. If + * it's released, *@locked will be set to 0. + */ +long faultin_vma_page_range(struct vm_area_struct *vma, unsigned long start, + unsigned long end, bool write, int *locked) +{ + struct mm_struct *mm = vma->vm_mm; + unsigned long nr_pages = (end - start) / PAGE_SIZE; + int gup_flags; + + VM_BUG_ON(!PAGE_ALIGNED(start)); + VM_BUG_ON(!PAGE_ALIGNED(end)); + VM_BUG_ON_VMA(start < vma->vm_start, vma); + VM_BUG_ON_VMA(end > vma->vm_end, vma); + mmap_assert_locked(mm); + + /* + * FOLL_TOUCH: Mark page accessed and thereby young; will also mark + * the page dirty with FOLL_WRITE -- which doesn't make a + * difference with !FOLL_FORCE, because the page is writable + * in the page table. + * FOLL_HWPOISON: Return -EHWPOISON instead of -EFAULT when we hit + * a poisoned page. + * FOLL_POPULATE: Always populate memory with VM_LOCKONFAULT. + * !FOLL_FORCE: Require proper access permissions. + */ + gup_flags = FOLL_TOUCH | FOLL_POPULATE | FOLL_MLOCK | FOLL_HWPOISON; + if (write) + gup_flags |= FOLL_WRITE; + + /* + * See check_vma_flags(): Will return -EFAULT on incompatible mappings + * or with insufficient permissions. + */ + return __get_user_pages(mm, start, nr_pages, gup_flags, + NULL, NULL, locked); +} + /* * __mm_populate - populate and/or mlock pages within a range of address space. * diff --git a/mm/hmm.c b/mm/hmm.c index 943cb2ba4442..fad6be2bf072 100644 --- a/mm/hmm.c +++ b/mm/hmm.c @@ -26,6 +26,8 @@ #include #include +#include "internal.h" + struct hmm_vma_walk { struct hmm_range *range; unsigned long last; @@ -214,7 +216,7 @@ static inline bool hmm_is_device_private_entry(struct hmm_range *range, swp_entry_t entry) { return is_device_private_entry(entry) && - device_private_entry_to_page(entry)->pgmap->owner == + pfn_swap_entry_to_page(entry)->pgmap->owner == range->dev_private_owner; } @@ -255,10 +257,9 @@ static int hmm_vma_handle_pte(struct mm_walk *walk, unsigned long addr, */ if (hmm_is_device_private_entry(range, entry)) { cpu_flags = HMM_PFN_VALID; - if (is_write_device_private_entry(entry)) + if (is_writable_device_private_entry(entry)) cpu_flags |= HMM_PFN_WRITE; - *hmm_pfn = device_private_entry_to_pfn(entry) | - cpu_flags; + *hmm_pfn = swp_offset(entry) | cpu_flags; return 0; } @@ -272,6 +273,9 @@ static int hmm_vma_handle_pte(struct mm_walk *walk, unsigned long addr, if (!non_swap_entry(entry)) goto fault; + if (is_device_exclusive_entry(entry)) + goto fault; + if (is_migration_entry(entry)) { pte_unmap(ptep); hmm_vma_walk->last = addr; diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 6d2a0119fc58..8b731d53e9f4 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -64,7 +64,14 @@ static atomic_t huge_zero_refcount; struct page *huge_zero_page __read_mostly; unsigned long huge_zero_pfn __read_mostly = ~0UL; -bool transparent_hugepage_enabled(struct vm_area_struct *vma) +static inline bool file_thp_enabled(struct vm_area_struct *vma) +{ + return transhuge_vma_enabled(vma, vma->vm_flags) && vma->vm_file && + !inode_is_open_for_write(vma->vm_file->f_inode) && + (vma->vm_flags & VM_EXEC); +} + +bool transparent_hugepage_active(struct vm_area_struct *vma) { /* The addr is used to check if the vma size fits */ unsigned long addr = (vma->vm_end & HPAGE_PMD_MASK) - HPAGE_PMD_SIZE; @@ -75,6 +82,8 @@ bool transparent_hugepage_enabled(struct vm_area_struct *vma) return __transparent_hugepage_enabled(vma); if (vma_is_shmem(vma)) return shmem_huge_enabled(vma); + if (IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS)) + return file_thp_enabled(vma); return false; } @@ -1017,7 +1026,7 @@ struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr, int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm, pmd_t *dst_pmd, pmd_t *src_pmd, unsigned long addr, - struct vm_area_struct *vma) + struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma) { spinlock_t *dst_ptl, *src_ptl; struct page *src_page; @@ -1026,7 +1035,7 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm, int ret = -ENOMEM; /* Skip if can be re-fill on fault */ - if (!vma_is_anonymous(vma)) + if (!vma_is_anonymous(dst_vma)) return 0; pgtable = pte_alloc_one(dst_mm); @@ -1040,29 +1049,26 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm, ret = -EAGAIN; pmd = *src_pmd; - /* - * Make sure the _PAGE_UFFD_WP bit is cleared if the new VMA - * does not have the VM_UFFD_WP, which means that the uffd - * fork event is not enabled. - */ - if (!(vma->vm_flags & VM_UFFD_WP)) - pmd = pmd_clear_uffd_wp(pmd); - #ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION if (unlikely(is_swap_pmd(pmd))) { swp_entry_t entry = pmd_to_swp_entry(pmd); VM_BUG_ON(!is_pmd_migration_entry(pmd)); - if (is_write_migration_entry(entry)) { - make_migration_entry_read(&entry); + if (is_writable_migration_entry(entry)) { + entry = make_readable_migration_entry( + swp_offset(entry)); pmd = swp_entry_to_pmd(entry); if (pmd_swp_soft_dirty(*src_pmd)) pmd = pmd_swp_mksoft_dirty(pmd); + if (pmd_swp_uffd_wp(*src_pmd)) + pmd = pmd_swp_mkuffd_wp(pmd); set_pmd_at(src_mm, addr, src_pmd, pmd); } add_mm_counter(dst_mm, MM_ANONPAGES, HPAGE_PMD_NR); mm_inc_nr_ptes(dst_mm); pgtable_trans_huge_deposit(dst_mm, dst_pmd, pgtable); + if (!userfaultfd_wp(dst_vma)) + pmd = pmd_swp_clear_uffd_wp(pmd); set_pmd_at(dst_mm, addr, dst_pmd, pmd); ret = 0; goto out_unlock; @@ -1079,17 +1085,13 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm, * a page table. */ if (is_huge_zero_pmd(pmd)) { - struct page *zero_page; /* * get_huge_zero_page() will never allocate a new page here, * since we already have a zero page to copy. It just takes a * reference. */ - zero_page = mm_get_huge_zero_page(dst_mm); - set_huge_zero_page(pgtable, dst_mm, vma, addr, dst_pmd, - zero_page); - ret = 0; - goto out_unlock; + mm_get_huge_zero_page(dst_mm); + goto out_zero_page; } src_page = pmd_page(pmd); @@ -1102,21 +1104,23 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm, * best effort that the pinned pages won't be replaced by another * random page during the coming copy-on-write. */ - if (unlikely(page_needs_cow_for_dma(vma, src_page))) { + if (unlikely(page_needs_cow_for_dma(src_vma, src_page))) { pte_free(dst_mm, pgtable); spin_unlock(src_ptl); spin_unlock(dst_ptl); - __split_huge_pmd(vma, src_pmd, addr, false, NULL); + __split_huge_pmd(src_vma, src_pmd, addr, false, NULL); return -EAGAIN; } get_page(src_page); page_dup_rmap(src_page, true); add_mm_counter(dst_mm, MM_ANONPAGES, HPAGE_PMD_NR); +out_zero_page: mm_inc_nr_ptes(dst_mm); pgtable_trans_huge_deposit(dst_mm, dst_pmd, pgtable); - pmdp_set_wrprotect(src_mm, addr, src_pmd); + if (!userfaultfd_wp(dst_vma)) + pmd = pmd_clear_uffd_wp(pmd); pmd = pmd_mkold(pmd_wrprotect(pmd)); set_pmd_at(dst_mm, addr, dst_pmd, pmd); @@ -1254,11 +1258,12 @@ void huge_pud_set_accessed(struct vm_fault *vmf, pud_t orig_pud) } #endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */ -void huge_pmd_set_accessed(struct vm_fault *vmf, pmd_t orig_pmd) +void huge_pmd_set_accessed(struct vm_fault *vmf) { pmd_t entry; unsigned long haddr; bool write = vmf->flags & FAULT_FLAG_WRITE; + pmd_t orig_pmd = vmf->orig_pmd; vmf->ptl = pmd_lock(vmf->vma->vm_mm, vmf->pmd); if (unlikely(!pmd_same(*vmf->pmd, orig_pmd))) @@ -1275,11 +1280,12 @@ void huge_pmd_set_accessed(struct vm_fault *vmf, pmd_t orig_pmd) spin_unlock(vmf->ptl); } -vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf, pmd_t orig_pmd) +vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; struct page *page; unsigned long haddr = vmf->address & HPAGE_PMD_MASK; + pmd_t orig_pmd = vmf->orig_pmd; vmf->ptl = pmd_lockptr(vma->vm_mm, vmf->pmd); VM_BUG_ON_VMA(!vma->anon_vma, vma); @@ -1415,96 +1421,25 @@ struct page *follow_trans_huge_pmd(struct vm_area_struct *vma, } /* NUMA hinting page fault entry point for trans huge pmds */ -vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t pmd) +vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; - struct anon_vma *anon_vma = NULL; + pmd_t oldpmd = vmf->orig_pmd; + pmd_t pmd; struct page *page; unsigned long haddr = vmf->address & HPAGE_PMD_MASK; - int page_nid = NUMA_NO_NODE, this_nid = numa_node_id(); + int page_nid = NUMA_NO_NODE; int target_nid, last_cpupid = -1; - bool page_locked; bool migrated = false; - bool was_writable; + bool was_writable = pmd_savedwrite(oldpmd); int flags = 0; vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd); - if (unlikely(!pmd_same(pmd, *vmf->pmd))) - goto out_unlock; - - /* - * If there are potential migrations, wait for completion and retry - * without disrupting NUMA hinting information. Do not relock and - * check_same as the page may no longer be mapped. - */ - if (unlikely(pmd_trans_migrating(*vmf->pmd))) { - page = pmd_page(*vmf->pmd); - if (!get_page_unless_zero(page)) - goto out_unlock; + if (unlikely(!pmd_same(oldpmd, *vmf->pmd))) { spin_unlock(vmf->ptl); - put_and_wait_on_page_locked(page, TASK_UNINTERRUPTIBLE); goto out; } - page = pmd_page(pmd); - BUG_ON(is_huge_zero_page(page)); - page_nid = page_to_nid(page); - last_cpupid = page_cpupid_last(page); - count_vm_numa_event(NUMA_HINT_FAULTS); - if (page_nid == this_nid) { - count_vm_numa_event(NUMA_HINT_FAULTS_LOCAL); - flags |= TNF_FAULT_LOCAL; - } - - /* See similar comment in do_numa_page for explanation */ - if (!pmd_savedwrite(pmd)) - flags |= TNF_NO_GROUP; - - /* - * Acquire the page lock to serialise THP migrations but avoid dropping - * page_table_lock if at all possible - */ - page_locked = trylock_page(page); - target_nid = mpol_misplaced(page, vma, haddr); - /* Migration could have started since the pmd_trans_migrating check */ - if (!page_locked) { - page_nid = NUMA_NO_NODE; - if (!get_page_unless_zero(page)) - goto out_unlock; - spin_unlock(vmf->ptl); - put_and_wait_on_page_locked(page, TASK_UNINTERRUPTIBLE); - goto out; - } else if (target_nid == NUMA_NO_NODE) { - /* There are no parallel migrations and page is in the right - * node. Clear the numa hinting info in this pmd. - */ - goto clear_pmdnuma; - } - - /* - * Page is misplaced. Page lock serialises migrations. Acquire anon_vma - * to serialises splits - */ - get_page(page); - spin_unlock(vmf->ptl); - anon_vma = page_lock_anon_vma_read(page); - - /* Confirm the PMD did not change while page_table_lock was released */ - spin_lock(vmf->ptl); - if (unlikely(!pmd_same(pmd, *vmf->pmd))) { - unlock_page(page); - put_page(page); - page_nid = NUMA_NO_NODE; - goto out_unlock; - } - - /* Bail if we fail to protect against THP splits for any reason */ - if (unlikely(!anon_vma)) { - put_page(page); - page_nid = NUMA_NO_NODE; - goto clear_pmdnuma; - } - /* * Since we took the NUMA fault, we must have observed the !accessible * bit. Make sure all other CPUs agree with that, to avoid them @@ -1531,43 +1466,58 @@ vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t pmd) haddr + HPAGE_PMD_SIZE); } - /* - * Migrate the THP to the requested node, returns with page unlocked - * and access rights restored. - */ + pmd = pmd_modify(oldpmd, vma->vm_page_prot); + page = vm_normal_page_pmd(vma, haddr, pmd); + if (!page) + goto out_map; + + /* See similar comment in do_numa_page for explanation */ + if (!was_writable) + flags |= TNF_NO_GROUP; + + page_nid = page_to_nid(page); + last_cpupid = page_cpupid_last(page); + target_nid = numa_migrate_prep(page, vma, haddr, page_nid, + &flags); + + if (target_nid == NUMA_NO_NODE) { + put_page(page); + goto out_map; + } + spin_unlock(vmf->ptl); - migrated = migrate_misplaced_transhuge_page(vma->vm_mm, vma, - vmf->pmd, pmd, vmf->address, page, target_nid); + migrated = migrate_misplaced_page(page, vma, target_nid); if (migrated) { flags |= TNF_MIGRATED; page_nid = target_nid; - } else + } else { flags |= TNF_MIGRATE_FAIL; - - goto out; -clear_pmdnuma: - BUG_ON(!PageLocked(page)); - was_writable = pmd_savedwrite(pmd); - pmd = pmd_modify(pmd, vma->vm_page_prot); - pmd = pmd_mkyoung(pmd); - if (was_writable) - pmd = pmd_mkwrite(pmd); - set_pmd_at(vma->vm_mm, haddr, vmf->pmd, pmd); - update_mmu_cache_pmd(vma, vmf->address, vmf->pmd); - unlock_page(page); -out_unlock: - spin_unlock(vmf->ptl); + vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd); + if (unlikely(!pmd_same(oldpmd, *vmf->pmd))) { + spin_unlock(vmf->ptl); + goto out; + } + goto out_map; + } out: - if (anon_vma) - page_unlock_anon_vma_read(anon_vma); - if (page_nid != NUMA_NO_NODE) task_numa_fault(last_cpupid, page_nid, HPAGE_PMD_NR, flags); return 0; + +out_map: + /* Restore the PMD */ + pmd = pmd_modify(oldpmd, vma->vm_page_prot); + pmd = pmd_mkyoung(pmd); + if (was_writable) + pmd = pmd_mkwrite(pmd); + set_pmd_at(vma->vm_mm, haddr, vmf->pmd, pmd); + update_mmu_cache_pmd(vma, vmf->address, vmf->pmd); + spin_unlock(vmf->ptl); + goto out; } /* @@ -1604,7 +1554,7 @@ bool madvise_free_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, * If other processes are mapping this page, we couldn't discard * the page unless they all do MADV_FREE so let's skip the page. */ - if (page_mapcount(page) != 1) + if (total_mapcount(page) != 1) goto out; if (!trylock_page(page)) @@ -1677,12 +1627,9 @@ int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, if (arch_needs_pgtable_deposit()) zap_deposited_table(tlb->mm, pmd); spin_unlock(ptl); - if (is_huge_zero_pmd(orig_pmd)) - tlb_remove_page_size(tlb, pmd_page(orig_pmd), HPAGE_PMD_SIZE); } else if (is_huge_zero_pmd(orig_pmd)) { zap_deposited_table(tlb->mm, pmd); spin_unlock(ptl); - tlb_remove_page_size(tlb, pmd_page(orig_pmd), HPAGE_PMD_SIZE); } else { struct page *page = NULL; int flush_needed = 1; @@ -1697,7 +1644,7 @@ int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, VM_BUG_ON(!is_pmd_migration_entry(orig_pmd)); entry = pmd_to_swp_entry(orig_pmd); - page = migration_entry_to_page(entry); + page = pfn_swap_entry_to_page(entry); flush_needed = 0; } else WARN_ONCE(1, "Non present huge pmd without pmd migration enabled!"); @@ -1796,6 +1743,7 @@ bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr, * Returns * - 0 if PMD could not be locked * - 1 if PMD was locked but protections unchanged and TLB flush unnecessary + * or if prot_numa but THP migration is not supported * - HPAGE_PMD_NR if protections changed and TLB flush necessary */ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, @@ -1810,6 +1758,9 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, bool uffd_wp = cp_flags & MM_CP_UFFD_WP; bool uffd_wp_resolve = cp_flags & MM_CP_UFFD_WP_RESOLVE; + if (prot_numa && !thp_migration_supported()) + return 1; + ptl = __pmd_trans_huge_lock(pmd, vma); if (!ptl) return 0; @@ -1822,16 +1773,19 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, swp_entry_t entry = pmd_to_swp_entry(*pmd); VM_BUG_ON(!is_pmd_migration_entry(*pmd)); - if (is_write_migration_entry(entry)) { + if (is_writable_migration_entry(entry)) { pmd_t newpmd; /* * A protection check is difficult so * just be safe and disable write */ - make_migration_entry_read(&entry); + entry = make_readable_migration_entry( + swp_offset(entry)); newpmd = swp_entry_to_pmd(entry); if (pmd_swp_soft_dirty(*pmd)) newpmd = pmd_swp_mksoft_dirty(newpmd); + if (pmd_swp_uffd_wp(*pmd)) + newpmd = pmd_swp_mkuffd_wp(newpmd); set_pmd_at(mm, addr, pmd, newpmd); } goto unlock; @@ -2060,7 +2014,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, swp_entry_t entry; entry = pmd_to_swp_entry(old_pmd); - page = migration_entry_to_page(entry); + page = pfn_swap_entry_to_page(entry); } else { page = pmd_page(old_pmd); if (!PageDirty(page) && pmd_dirty(old_pmd)) @@ -2114,8 +2068,8 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, swp_entry_t entry; entry = pmd_to_swp_entry(old_pmd); - page = migration_entry_to_page(entry); - write = is_write_migration_entry(entry); + page = pfn_swap_entry_to_page(entry); + write = is_writable_migration_entry(entry); young = false; soft_dirty = pmd_swp_soft_dirty(old_pmd); uffd_wp = pmd_swp_uffd_wp(old_pmd); @@ -2147,7 +2101,12 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, */ if (freeze || pmd_migration) { swp_entry_t swp_entry; - swp_entry = make_migration_entry(page + i, write); + if (write) + swp_entry = make_writable_migration_entry( + page_to_pfn(page + i)); + else + swp_entry = make_readable_migration_entry( + page_to_pfn(page + i)); entry = swp_entry_to_pte(swp_entry); if (soft_dirty) entry = pte_swp_mksoft_dirty(entry); @@ -2350,15 +2309,20 @@ void vma_adjust_trans_huge(struct vm_area_struct *vma, static void unmap_page(struct page *page) { - enum ttu_flags ttu_flags = TTU_IGNORE_MLOCK | TTU_SYNC | - TTU_RMAP_LOCKED | TTU_SPLIT_HUGE_PMD; + enum ttu_flags ttu_flags = TTU_RMAP_LOCKED | TTU_SPLIT_HUGE_PMD | + TTU_SYNC; VM_BUG_ON_PAGE(!PageHead(page), page); + /* + * Anon pages need migration entries to preserve them, but file + * pages can simply be left unmapped, then faulted back on demand. + * If that is ever changed (perhaps for mlock), update remap_page(). + */ if (PageAnon(page)) - ttu_flags |= TTU_SPLIT_FREEZE; - - try_to_unmap(page, ttu_flags); + try_to_migrate(page, ttu_flags); + else + try_to_unmap(page, ttu_flags | TTU_IGNORE_MLOCK); VM_WARN_ON_ONCE_PAGE(page_mapped(page), page); } @@ -2366,6 +2330,10 @@ static void unmap_page(struct page *page) static void remap_page(struct page *page, unsigned int nr) { int i; + + /* If TTU_SPLIT_FREEZE is ever extended to file, remove this check */ + if (!PageAnon(page)) + return; if (PageTransHuge(page)) { remove_migration_ptes(page, page, true); } else { @@ -2870,7 +2838,7 @@ static unsigned long deferred_split_scan(struct shrinker *shrink, spin_lock_irqsave(&ds_queue->split_queue_lock, flags); /* Take pin on all head pages to avoid freeing them under us */ list_for_each_safe(pos, next, &ds_queue->split_queue) { - page = list_entry((void *)pos, struct page, mapping); + page = list_entry((void *)pos, struct page, deferred_list); page = compound_head(page); if (get_page_unless_zero(page)) { list_move(page_deferred_list(page), &list); @@ -2885,7 +2853,7 @@ static unsigned long deferred_split_scan(struct shrinker *shrink, spin_unlock_irqrestore(&ds_queue->split_queue_lock, flags); list_for_each_safe(pos, next, &list) { - page = list_entry((void *)pos, struct page, mapping); + page = list_entry((void *)pos, struct page, deferred_list); if (!trylock_page(page)) goto next; /* split_huge_page() removes page from list on success */ @@ -3144,7 +3112,7 @@ static ssize_t split_huge_pages_write(struct file *file, const char __user *buf, tok = strsep(&buf, ","); if (tok) { - strncpy(file_path, tok, MAX_INPUT_BUF_SZ); + strcpy(file_path, tok); } else { ret = -EINVAL; goto out; @@ -3214,7 +3182,10 @@ void set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw, pmdval = pmdp_invalidate(vma, address, pvmw->pmd); if (pmd_dirty(pmdval)) set_page_dirty(page); - entry = make_migration_entry(page, pmd_write(pmdval)); + if (pmd_write(pmdval)) + entry = make_writable_migration_entry(page_to_pfn(page)); + else + entry = make_readable_migration_entry(page_to_pfn(page)); pmdswp = swp_entry_to_pmd(entry); if (pmd_soft_dirty(pmdval)) pmdswp = pmd_swp_mksoft_dirty(pmdswp); @@ -3240,8 +3211,10 @@ void remove_migration_pmd(struct page_vma_mapped_walk *pvmw, struct page *new) pmde = pmd_mkold(mk_huge_pmd(new, vma->vm_page_prot)); if (pmd_swp_soft_dirty(*pvmw->pmd)) pmde = pmd_mksoft_dirty(pmde); - if (is_write_migration_entry(entry)) + if (is_writable_migration_entry(entry)) pmde = maybe_pmd_mkwrite(pmde, vma); + if (pmd_swp_uffd_wp(*pvmw->pmd)) + pmde = pmd_wrprotect(pmd_mkuffd_wp(pmde)); flush_cache_range(vma, mmun_start, mmun_start + HPAGE_PMD_SIZE); if (PageAnon(new)) diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 103f1187043f..924553aa8f78 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -30,6 +30,7 @@ #include #include #include +#include #include #include @@ -41,6 +42,7 @@ #include #include #include "internal.h" +#include "hugetlb_vmemmap.h" int hugetlb_max_hstate __read_mostly; unsigned int default_hstate_idx; @@ -1318,8 +1320,6 @@ static struct page *alloc_gigantic_page(struct hstate *h, gfp_t gfp_mask, return alloc_contig_pages(nr_pages, gfp_mask, nid, nodemask); } -static void prep_new_huge_page(struct hstate *h, struct page *page, int nid); -static void prep_compound_gigantic_page(struct page *page, unsigned int order); #else /* !CONFIG_CONTIG_ALLOC */ static struct page *alloc_gigantic_page(struct hstate *h, gfp_t gfp_mask, int nid, nodemask_t *nodemask) @@ -1375,7 +1375,40 @@ static void remove_hugetlb_page(struct hstate *h, struct page *page, h->nr_huge_pages_node[nid]--; } -static void update_and_free_page(struct hstate *h, struct page *page) +static void add_hugetlb_page(struct hstate *h, struct page *page, + bool adjust_surplus) +{ + int zeroed; + int nid = page_to_nid(page); + + VM_BUG_ON_PAGE(!HPageVmemmapOptimized(page), page); + + lockdep_assert_held(&hugetlb_lock); + + INIT_LIST_HEAD(&page->lru); + h->nr_huge_pages++; + h->nr_huge_pages_node[nid]++; + + if (adjust_surplus) { + h->surplus_huge_pages++; + h->surplus_huge_pages_node[nid]++; + } + + set_compound_page_dtor(page, HUGETLB_PAGE_DTOR); + set_page_private(page, 0); + SetHPageVmemmapOptimized(page); + + /* + * This page is now managed by the hugetlb allocator and has + * no users -- drop the last reference. + */ + zeroed = put_page_testzero(page); + VM_BUG_ON_PAGE(!zeroed, page); + arch_clear_hugepage_flags(page); + enqueue_huge_page(h, page); +} + +static void __update_and_free_page(struct hstate *h, struct page *page) { int i; struct page *subpage = page; @@ -1383,6 +1416,18 @@ static void update_and_free_page(struct hstate *h, struct page *page) if (hstate_is_gigantic(h) && !gigantic_page_runtime_supported()) return; + if (alloc_huge_page_vmemmap(h, page)) { + spin_lock_irq(&hugetlb_lock); + /* + * If we cannot allocate vmemmap pages, just refuse to free the + * page and put the page back on the hugetlb free list and treat + * as a surplus page. + */ + add_hugetlb_page(h, page, true); + spin_unlock_irq(&hugetlb_lock); + return; + } + for (i = 0; i < pages_per_huge_page(h); i++, subpage = mem_map_next(subpage, page, i)) { subpage->flags &= ~(1 << PG_locked | 1 << PG_error | @@ -1398,12 +1443,79 @@ static void update_and_free_page(struct hstate *h, struct page *page) } } +/* + * As update_and_free_page() can be called under any context, so we cannot + * use GFP_KERNEL to allocate vmemmap pages. However, we can defer the + * actual freeing in a workqueue to prevent from using GFP_ATOMIC to allocate + * the vmemmap pages. + * + * free_hpage_workfn() locklessly retrieves the linked list of pages to be + * freed and frees them one-by-one. As the page->mapping pointer is going + * to be cleared in free_hpage_workfn() anyway, it is reused as the llist_node + * structure of a lockless linked list of huge pages to be freed. + */ +static LLIST_HEAD(hpage_freelist); + +static void free_hpage_workfn(struct work_struct *work) +{ + struct llist_node *node; + + node = llist_del_all(&hpage_freelist); + + while (node) { + struct page *page; + struct hstate *h; + + page = container_of((struct address_space **)node, + struct page, mapping); + node = node->next; + page->mapping = NULL; + /* + * The VM_BUG_ON_PAGE(!PageHuge(page), page) in page_hstate() + * is going to trigger because a previous call to + * remove_hugetlb_page() will set_compound_page_dtor(page, + * NULL_COMPOUND_DTOR), so do not use page_hstate() directly. + */ + h = size_to_hstate(page_size(page)); + + __update_and_free_page(h, page); + + cond_resched(); + } +} +static DECLARE_WORK(free_hpage_work, free_hpage_workfn); + +static inline void flush_free_hpage_work(struct hstate *h) +{ + if (free_vmemmap_pages_per_hpage(h)) + flush_work(&free_hpage_work); +} + +static void update_and_free_page(struct hstate *h, struct page *page, + bool atomic) +{ + if (!HPageVmemmapOptimized(page) || !atomic) { + __update_and_free_page(h, page); + return; + } + + /* + * Defer freeing to avoid using GFP_ATOMIC to allocate vmemmap pages. + * + * Only call schedule_work() if hpage_freelist is previously + * empty. Otherwise, schedule_work() had been called but the workfn + * hasn't retrieved the list yet. + */ + if (llist_add((struct llist_node *)&page->mapping, &hpage_freelist)) + schedule_work(&free_hpage_work); +} + static void update_and_free_pages_bulk(struct hstate *h, struct list_head *list) { struct page *page, *t_page; list_for_each_entry_safe(page, t_page, list, lru) { - update_and_free_page(h, page); + update_and_free_page(h, page, false); cond_resched(); } } @@ -1470,12 +1582,12 @@ void free_huge_page(struct page *page) if (HPageTemporary(page)) { remove_hugetlb_page(h, page, false); spin_unlock_irqrestore(&hugetlb_lock, flags); - update_and_free_page(h, page); + update_and_free_page(h, page, true); } else if (h->surplus_huge_pages_node[nid]) { /* remove the page from active list */ remove_hugetlb_page(h, page, true); spin_unlock_irqrestore(&hugetlb_lock, flags); - update_and_free_page(h, page); + update_and_free_page(h, page, true); } else { arch_clear_hugepage_flags(page); enqueue_huge_page(h, page); @@ -1493,8 +1605,9 @@ static void __prep_account_new_huge_page(struct hstate *h, int nid) h->nr_huge_pages_node[nid]++; } -static void __prep_new_huge_page(struct page *page) +static void __prep_new_huge_page(struct hstate *h, struct page *page) { + free_huge_page_vmemmap(h, page); INIT_LIST_HEAD(&page->lru); set_compound_page_dtor(page, HUGETLB_PAGE_DTOR); hugetlb_set_page_subpool(page, NULL); @@ -1504,15 +1617,15 @@ static void __prep_new_huge_page(struct page *page) static void prep_new_huge_page(struct hstate *h, struct page *page, int nid) { - __prep_new_huge_page(page); + __prep_new_huge_page(h, page); spin_lock_irq(&hugetlb_lock); __prep_account_new_huge_page(h, nid); spin_unlock_irq(&hugetlb_lock); } -static void prep_compound_gigantic_page(struct page *page, unsigned int order) +static bool prep_compound_gigantic_page(struct page *page, unsigned int order) { - int i; + int i, j; int nr_pages = 1 << order; struct page *p = page + 1; @@ -1534,11 +1647,48 @@ static void prep_compound_gigantic_page(struct page *page, unsigned int order) * after get_user_pages(). */ __ClearPageReserved(p); + /* + * Subtle and very unlikely + * + * Gigantic 'page allocators' such as memblock or cma will + * return a set of pages with each page ref counted. We need + * to turn this set of pages into a compound page with tail + * page ref counts set to zero. Code such as speculative page + * cache adding could take a ref on a 'to be' tail page. + * We need to respect any increased ref count, and only set + * the ref count to zero if count is currently 1. If count + * is not 1, we call synchronize_rcu in the hope that a rcu + * grace period will cause ref count to drop and then retry. + * If count is still inflated on retry we return an error and + * must discard the pages. + */ + if (!page_ref_freeze(p, 1)) { + pr_info("HugeTLB unexpected inflated ref count on freshly allocated page\n"); + synchronize_rcu(); + if (!page_ref_freeze(p, 1)) + goto out_error; + } set_page_count(p, 0); set_compound_head(p, page); } atomic_set(compound_mapcount_ptr(page), -1); atomic_set(compound_pincount_ptr(page), 0); + return true; + +out_error: + /* undo tail page modifications made above */ + p = page + 1; + for (j = 1; j < i; j++, p = mem_map_next(p, page, j)) { + clear_compound_head(p); + set_page_refcounted(p); + } + /* need to clear PG_reserved on remaining tail pages */ + for (; j < nr_pages; j++, p = mem_map_next(p, page, j)) + __ClearPageReserved(p); + set_compound_order(page, 0); + page[1].compound_nr = 0; + __ClearPageHead(page); + return false; } /* @@ -1658,7 +1808,9 @@ static struct page *alloc_fresh_huge_page(struct hstate *h, nodemask_t *node_alloc_noretry) { struct page *page; + bool retry = false; +retry: if (hstate_is_gigantic(h)) page = alloc_gigantic_page(h, gfp_mask, nid, nmask); else @@ -1667,8 +1819,21 @@ static struct page *alloc_fresh_huge_page(struct hstate *h, if (!page) return NULL; - if (hstate_is_gigantic(h)) - prep_compound_gigantic_page(page, huge_page_order(h)); + if (hstate_is_gigantic(h)) { + if (!prep_compound_gigantic_page(page, huge_page_order(h))) { + /* + * Rare failure to convert pages to compound page. + * Free pages and try again - ONCE! + */ + free_gigantic_page(page, huge_page_order(h)); + if (!retry) { + retry = true; + goto retry; + } + pr_warn("HugeTLB page can not be used due to unexpected inflated ref count\n"); + return NULL; + } + } prep_new_huge_page(h, page, page_to_nid(page)); return page; @@ -1737,10 +1902,14 @@ static struct page *remove_pool_huge_page(struct hstate *h, * nothing for in-use hugepages and non-hugepages. * This function returns values like below: * - * -EBUSY: failed to dissolved free hugepages or the hugepage is in-use - * (allocated or reserved.) - * 0: successfully dissolved free hugepages or the page is not a - * hugepage (considered as already dissolved) + * -ENOMEM: failed to allocate vmemmap pages to free the freed hugepages + * when the system is under memory pressure and the feature of + * freeing unused vmemmap pages associated with each hugetlb page + * is enabled. + * -EBUSY: failed to dissolved free hugepages or the hugepage is in-use + * (allocated or reserved.) + * 0: successfully dissolved free hugepages or the page is not a + * hugepage (considered as already dissolved) */ int dissolve_free_huge_page(struct page *page) { @@ -1782,19 +1951,38 @@ int dissolve_free_huge_page(struct page *page) goto retry; } - /* - * Move PageHWPoison flag from head page to the raw error page, - * which makes any subpages rather than the error page reusable. - */ - if (PageHWPoison(head) && page != head) { - SetPageHWPoison(page); - ClearPageHWPoison(head); - } remove_hugetlb_page(h, head, false); h->max_huge_pages--; spin_unlock_irq(&hugetlb_lock); - update_and_free_page(h, head); - return 0; + + /* + * Normally update_and_free_page will allocate required vmemmmap + * before freeing the page. update_and_free_page will fail to + * free the page if it can not allocate required vmemmap. We + * need to adjust max_huge_pages if the page is not freed. + * Attempt to allocate vmemmmap here so that we can take + * appropriate action on failure. + */ + rc = alloc_huge_page_vmemmap(h, head); + if (!rc) { + /* + * Move PageHWPoison flag from head page to the raw + * error page, which makes any subpages rather than + * the error page reusable. + */ + if (PageHWPoison(head) && page != head) { + SetPageHWPoison(page); + ClearPageHWPoison(head); + } + update_and_free_page(h, head, false); + } else { + spin_lock_irq(&hugetlb_lock); + add_hugetlb_page(h, head, false); + h->max_huge_pages++; + spin_unlock_irq(&hugetlb_lock); + } + + return rc; } out: spin_unlock_irq(&hugetlb_lock); @@ -2351,14 +2539,15 @@ static int alloc_and_dissolve_huge_page(struct hstate *h, struct page *old_page, /* * Before dissolving the page, we need to allocate a new one for the - * pool to remain stable. Using alloc_buddy_huge_page() allows us to - * not having to deal with prep_new_huge_page() and avoids dealing of any - * counters. This simplifies and let us do the whole thing under the - * lock. + * pool to remain stable. Here, we allocate the page and 'prep' it + * by doing everything but actually updating counters and adding to + * the pool. This simplifies and let us do most of the processing + * under the lock. */ new_page = alloc_buddy_huge_page(h, gfp_mask, nid, NULL, NULL); if (!new_page) return -ENOMEM; + __prep_new_huge_page(h, new_page); retry: spin_lock_irq(&hugetlb_lock); @@ -2397,14 +2586,9 @@ static int alloc_and_dissolve_huge_page(struct hstate *h, struct page *old_page, remove_hugetlb_page(h, old_page, false); /* - * new_page needs to be initialized with the standard hugetlb - * state. This is normally done by prep_new_huge_page() but - * that takes hugetlb_lock which is already held so we need to - * open code it here. * Reference count trick is needed because allocator gives us * referenced page but the pool requires pages with 0 refcount. */ - __prep_new_huge_page(new_page); __prep_account_new_huge_page(h, nid); page_ref_dec(new_page); enqueue_huge_page(h, new_page); @@ -2413,14 +2597,14 @@ static int alloc_and_dissolve_huge_page(struct hstate *h, struct page *old_page, * Pages have been replaced, we can safely free the old one. */ spin_unlock_irq(&hugetlb_lock); - update_and_free_page(h, old_page); + update_and_free_page(h, old_page, false); } return ret; free_new: spin_unlock_irq(&hugetlb_lock); - __free_pages(new_page, huge_page_order(h)); + update_and_free_page(h, new_page, false); return ret; } @@ -2625,16 +2809,10 @@ int __alloc_bootmem_huge_page(struct hstate *h) return 1; } -static void __init prep_compound_huge_page(struct page *page, - unsigned int order) -{ - if (unlikely(order > (MAX_ORDER - 1))) - prep_compound_gigantic_page(page, order); - else - prep_compound_page(page, order); -} - -/* Put bootmem huge pages into the standard lists after mem_map is up */ +/* + * Put bootmem huge pages into the standard lists after mem_map is up. + * Note: This only applies to gigantic (order > MAX_ORDER) pages. + */ static void __init gather_bootmem_prealloc(void) { struct huge_bootmem_page *m; @@ -2643,20 +2821,23 @@ static void __init gather_bootmem_prealloc(void) struct page *page = virt_to_page(m); struct hstate *h = m->hstate; + VM_BUG_ON(!hstate_is_gigantic(h)); WARN_ON(page_count(page) != 1); - prep_compound_huge_page(page, huge_page_order(h)); - WARN_ON(PageReserved(page)); - prep_new_huge_page(h, page, page_to_nid(page)); - put_page(page); /* free it into the hugepage allocator */ + if (prep_compound_gigantic_page(page, huge_page_order(h))) { + WARN_ON(PageReserved(page)); + prep_new_huge_page(h, page, page_to_nid(page)); + put_page(page); /* add to the hugepage allocator */ + } else { + free_gigantic_page(page, huge_page_order(h)); + pr_warn("HugeTLB page can not be used due to unexpected inflated ref count\n"); + } /* - * If we had gigantic hugepages allocated at boot time, we need - * to restore the 'stolen' pages to totalram_pages in order to - * fix confusing memory reports from free(1) and another - * side-effects, like CommitLimit going negative. + * We need to restore the 'stolen' pages to totalram_pages + * in order to fix confusing memory reports from free(1) and + * other side-effects, like CommitLimit going negative. */ - if (hstate_is_gigantic(h)) - adjust_managed_page_count(page, pages_per_huge_page(h)); + adjust_managed_page_count(page, pages_per_huge_page(h)); cond_resched(); } } @@ -2834,6 +3015,7 @@ static int set_max_huge_pages(struct hstate *h, unsigned long count, int nid, * pages in hstate via the proc/sysfs interfaces. */ mutex_lock(&h->resize_lock); + flush_free_hpage_work(h); spin_lock_irq(&hugetlb_lock); /* @@ -2943,6 +3125,7 @@ static int set_max_huge_pages(struct hstate *h, unsigned long count, int nid, /* free the pages after dropping lock */ spin_unlock_irq(&hugetlb_lock); update_and_free_pages_bulk(h, &page_list); + flush_free_hpage_work(h); spin_lock_irq(&hugetlb_lock); while (count < persistent_huge_pages(h)) { @@ -3450,6 +3633,7 @@ void __init hugetlb_add_hstate(unsigned int order) h->next_nid_to_free = first_memory_node; snprintf(h->name, HSTATE_NAME_LEN, "hugepages-%lukB", huge_page_size(h)/1024); + hugetlb_vmemmap_init(h); parsed_hstate = h; } @@ -3924,6 +4108,7 @@ static pte_t make_huge_pte(struct vm_area_struct *vma, struct page *page, int writable) { pte_t entry; + unsigned int shift = huge_page_shift(hstate_vma(vma)); if (writable) { entry = huge_pte_mkwrite(huge_pte_mkdirty(mk_huge_pte(page, @@ -3934,7 +4119,7 @@ static pte_t make_huge_pte(struct vm_area_struct *vma, struct page *page, } entry = pte_mkyoung(entry); entry = pte_mkhuge(entry); - entry = arch_make_huge_pte(entry, vma, page, writable); + entry = arch_make_huge_pte(entry, shift, vma->vm_flags); return entry; } @@ -4057,12 +4242,13 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src, is_hugetlb_entry_hwpoisoned(entry))) { swp_entry_t swp_entry = pte_to_swp_entry(entry); - if (is_write_migration_entry(swp_entry) && cow) { + if (is_writable_migration_entry(swp_entry) && cow) { /* * COW mappings require pages in both * parent and child to be set to read. */ - make_migration_entry_read(&swp_entry); + swp_entry = make_readable_migration_entry( + swp_offset(swp_entry)); entry = swp_entry_to_pte(swp_entry); set_huge_swap_pte_at(src, addr, src_pte, entry, sz); @@ -4939,20 +5125,17 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm, struct page **pagep) { bool is_continue = (mode == MCOPY_ATOMIC_CONTINUE); - struct address_space *mapping; - pgoff_t idx; + struct hstate *h = hstate_vma(dst_vma); + struct address_space *mapping = dst_vma->vm_file->f_mapping; + pgoff_t idx = vma_hugecache_offset(h, dst_vma, dst_addr); unsigned long size; int vm_shared = dst_vma->vm_flags & VM_SHARED; - struct hstate *h = hstate_vma(dst_vma); pte_t _dst_pte; spinlock_t *ptl; - int ret; + int ret = -ENOMEM; struct page *page; int writable; - mapping = dst_vma->vm_file->f_mapping; - idx = vma_hugecache_offset(h, dst_vma, dst_addr); - if (is_continue) { ret = -EFAULT; page = find_lock_page(mapping, idx); @@ -4981,12 +5164,44 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm, /* fallback to copy_from_user outside mmap_lock */ if (unlikely(ret)) { ret = -ENOENT; + /* Free the allocated page which may have + * consumed a reservation. + */ + restore_reserve_on_error(h, dst_vma, dst_addr, page); + put_page(page); + + /* Allocate a temporary page to hold the copied + * contents. + */ + page = alloc_huge_page_vma(h, dst_vma, dst_addr); + if (!page) { + ret = -ENOMEM; + goto out; + } *pagep = page; - /* don't free the page */ + /* Set the outparam pagep and return to the caller to + * copy the contents outside the lock. Don't free the + * page. + */ goto out; } } else { - page = *pagep; + if (vm_shared && + hugetlbfs_pagecache_present(h, dst_vma, dst_addr)) { + put_page(*pagep); + ret = -EEXIST; + *pagep = NULL; + goto out; + } + + page = alloc_huge_page(dst_vma, dst_addr, 0); + if (IS_ERR(page)) { + ret = -ENOMEM; + *pagep = NULL; + goto out; + } + copy_huge_page(page, *pagep); + put_page(*pagep); *pagep = NULL; } @@ -5318,10 +5533,11 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma, if (unlikely(is_hugetlb_entry_migration(pte))) { swp_entry_t entry = pte_to_swp_entry(pte); - if (is_write_migration_entry(entry)) { + if (is_writable_migration_entry(entry)) { pte_t newpte; - make_migration_entry_read(&entry); + entry = make_readable_migration_entry( + swp_offset(entry)); newpte = swp_entry_to_pte(entry); set_huge_swap_pte_at(mm, address, ptep, newpte, huge_page_size(h)); @@ -5332,10 +5548,11 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma, } if (!huge_pte_none(pte)) { pte_t old_pte; + unsigned int shift = huge_page_shift(hstate_vma(vma)); old_pte = huge_ptep_modify_prot_start(vma, address, ptep); pte = pte_mkhuge(huge_pte_modify(old_pte, newprot)); - pte = arch_make_huge_pte(pte, vma, NULL, 0); + pte = arch_make_huge_pte(pte, shift, vma->vm_flags); huge_ptep_modify_prot_commit(vma, address, ptep, old_pte, pte); pages++; } diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c new file mode 100644 index 000000000000..c540c21e26f5 --- /dev/null +++ b/mm/hugetlb_vmemmap.c @@ -0,0 +1,298 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Free some vmemmap pages of HugeTLB + * + * Copyright (c) 2020, Bytedance. All rights reserved. + * + * Author: Muchun Song + * + * The struct page structures (page structs) are used to describe a physical + * page frame. By default, there is a one-to-one mapping from a page frame to + * it's corresponding page struct. + * + * HugeTLB pages consist of multiple base page size pages and is supported by + * many architectures. See hugetlbpage.rst in the Documentation directory for + * more details. On the x86-64 architecture, HugeTLB pages of size 2MB and 1GB + * are currently supported. Since the base page size on x86 is 4KB, a 2MB + * HugeTLB page consists of 512 base pages and a 1GB HugeTLB page consists of + * 4096 base pages. For each base page, there is a corresponding page struct. + * + * Within the HugeTLB subsystem, only the first 4 page structs are used to + * contain unique information about a HugeTLB page. __NR_USED_SUBPAGE provides + * this upper limit. The only 'useful' information in the remaining page structs + * is the compound_head field, and this field is the same for all tail pages. + * + * By removing redundant page structs for HugeTLB pages, memory can be returned + * to the buddy allocator for other uses. + * + * Different architectures support different HugeTLB pages. For example, the + * following table is the HugeTLB page size supported by x86 and arm64 + * architectures. Because arm64 supports 4k, 16k, and 64k base pages and + * supports contiguous entries, so it supports many kinds of sizes of HugeTLB + * page. + * + * +--------------+-----------+-----------------------------------------------+ + * | Architecture | Page Size | HugeTLB Page Size | + * +--------------+-----------+-----------+-----------+-----------+-----------+ + * | x86-64 | 4KB | 2MB | 1GB | | | + * +--------------+-----------+-----------+-----------+-----------+-----------+ + * | | 4KB | 64KB | 2MB | 32MB | 1GB | + * | +-----------+-----------+-----------+-----------+-----------+ + * | arm64 | 16KB | 2MB | 32MB | 1GB | | + * | +-----------+-----------+-----------+-----------+-----------+ + * | | 64KB | 2MB | 512MB | 16GB | | + * +--------------+-----------+-----------+-----------+-----------+-----------+ + * + * When the system boot up, every HugeTLB page has more than one struct page + * structs which size is (unit: pages): + * + * struct_size = HugeTLB_Size / PAGE_SIZE * sizeof(struct page) / PAGE_SIZE + * + * Where HugeTLB_Size is the size of the HugeTLB page. We know that the size + * of the HugeTLB page is always n times PAGE_SIZE. So we can get the following + * relationship. + * + * HugeTLB_Size = n * PAGE_SIZE + * + * Then, + * + * struct_size = n * PAGE_SIZE / PAGE_SIZE * sizeof(struct page) / PAGE_SIZE + * = n * sizeof(struct page) / PAGE_SIZE + * + * We can use huge mapping at the pud/pmd level for the HugeTLB page. + * + * For the HugeTLB page of the pmd level mapping, then + * + * struct_size = n * sizeof(struct page) / PAGE_SIZE + * = PAGE_SIZE / sizeof(pte_t) * sizeof(struct page) / PAGE_SIZE + * = sizeof(struct page) / sizeof(pte_t) + * = 64 / 8 + * = 8 (pages) + * + * Where n is how many pte entries which one page can contains. So the value of + * n is (PAGE_SIZE / sizeof(pte_t)). + * + * This optimization only supports 64-bit system, so the value of sizeof(pte_t) + * is 8. And this optimization also applicable only when the size of struct page + * is a power of two. In most cases, the size of struct page is 64 bytes (e.g. + * x86-64 and arm64). So if we use pmd level mapping for a HugeTLB page, the + * size of struct page structs of it is 8 page frames which size depends on the + * size of the base page. + * + * For the HugeTLB page of the pud level mapping, then + * + * struct_size = PAGE_SIZE / sizeof(pmd_t) * struct_size(pmd) + * = PAGE_SIZE / 8 * 8 (pages) + * = PAGE_SIZE (pages) + * + * Where the struct_size(pmd) is the size of the struct page structs of a + * HugeTLB page of the pmd level mapping. + * + * E.g.: A 2MB HugeTLB page on x86_64 consists in 8 page frames while 1GB + * HugeTLB page consists in 4096. + * + * Next, we take the pmd level mapping of the HugeTLB page as an example to + * show the internal implementation of this optimization. There are 8 pages + * struct page structs associated with a HugeTLB page which is pmd mapped. + * + * Here is how things look before optimization. + * + * HugeTLB struct pages(8 pages) page frame(8 pages) + * +-----------+ ---virt_to_page---> +-----------+ mapping to +-----------+ + * | | | 0 | -------------> | 0 | + * | | +-----------+ +-----------+ + * | | | 1 | -------------> | 1 | + * | | +-----------+ +-----------+ + * | | | 2 | -------------> | 2 | + * | | +-----------+ +-----------+ + * | | | 3 | -------------> | 3 | + * | | +-----------+ +-----------+ + * | | | 4 | -------------> | 4 | + * | PMD | +-----------+ +-----------+ + * | level | | 5 | -------------> | 5 | + * | mapping | +-----------+ +-----------+ + * | | | 6 | -------------> | 6 | + * | | +-----------+ +-----------+ + * | | | 7 | -------------> | 7 | + * | | +-----------+ +-----------+ + * | | + * | | + * | | + * +-----------+ + * + * The value of page->compound_head is the same for all tail pages. The first + * page of page structs (page 0) associated with the HugeTLB page contains the 4 + * page structs necessary to describe the HugeTLB. The only use of the remaining + * pages of page structs (page 1 to page 7) is to point to page->compound_head. + * Therefore, we can remap pages 2 to 7 to page 1. Only 2 pages of page structs + * will be used for each HugeTLB page. This will allow us to free the remaining + * 6 pages to the buddy allocator. + * + * Here is how things look after remapping. + * + * HugeTLB struct pages(8 pages) page frame(8 pages) + * +-----------+ ---virt_to_page---> +-----------+ mapping to +-----------+ + * | | | 0 | -------------> | 0 | + * | | +-----------+ +-----------+ + * | | | 1 | -------------> | 1 | + * | | +-----------+ +-----------+ + * | | | 2 | ----------------^ ^ ^ ^ ^ ^ + * | | +-----------+ | | | | | + * | | | 3 | ------------------+ | | | | + * | | +-----------+ | | | | + * | | | 4 | --------------------+ | | | + * | PMD | +-----------+ | | | + * | level | | 5 | ----------------------+ | | + * | mapping | +-----------+ | | + * | | | 6 | ------------------------+ | + * | | +-----------+ | + * | | | 7 | --------------------------+ + * | | +-----------+ + * | | + * | | + * | | + * +-----------+ + * + * When a HugeTLB is freed to the buddy system, we should allocate 6 pages for + * vmemmap pages and restore the previous mapping relationship. + * + * For the HugeTLB page of the pud level mapping. It is similar to the former. + * We also can use this approach to free (PAGE_SIZE - 2) vmemmap pages. + * + * Apart from the HugeTLB page of the pmd/pud level mapping, some architectures + * (e.g. aarch64) provides a contiguous bit in the translation table entries + * that hints to the MMU to indicate that it is one of a contiguous set of + * entries that can be cached in a single TLB entry. + * + * The contiguous bit is used to increase the mapping size at the pmd and pte + * (last) level. So this type of HugeTLB page can be optimized only when its + * size of the struct page structs is greater than 2 pages. + */ +#define pr_fmt(fmt) "HugeTLB: " fmt + +#include "hugetlb_vmemmap.h" + +/* + * There are a lot of struct page structures associated with each HugeTLB page. + * For tail pages, the value of compound_head is the same. So we can reuse first + * page of tail page structures. We map the virtual addresses of the remaining + * pages of tail page structures to the first tail page struct, and then free + * these page frames. Therefore, we need to reserve two pages as vmemmap areas. + */ +#define RESERVE_VMEMMAP_NR 2U +#define RESERVE_VMEMMAP_SIZE (RESERVE_VMEMMAP_NR << PAGE_SHIFT) + +bool hugetlb_free_vmemmap_enabled = IS_ENABLED(CONFIG_HUGETLB_PAGE_FREE_VMEMMAP_DEFAULT_ON); + +static int __init early_hugetlb_free_vmemmap_param(char *buf) +{ + /* We cannot optimize if a "struct page" crosses page boundaries. */ + if ((!is_power_of_2(sizeof(struct page)))) { + pr_warn("cannot free vmemmap pages because \"struct page\" crosses page boundaries\n"); + return 0; + } + + if (!buf) + return -EINVAL; + + if (!strcmp(buf, "on")) + hugetlb_free_vmemmap_enabled = true; + else if (!strcmp(buf, "off")) + hugetlb_free_vmemmap_enabled = false; + else + return -EINVAL; + + return 0; +} +early_param("hugetlb_free_vmemmap", early_hugetlb_free_vmemmap_param); + +static inline unsigned long free_vmemmap_pages_size_per_hpage(struct hstate *h) +{ + return (unsigned long)free_vmemmap_pages_per_hpage(h) << PAGE_SHIFT; +} + +/* + * Previously discarded vmemmap pages will be allocated and remapping + * after this function returns zero. + */ +int alloc_huge_page_vmemmap(struct hstate *h, struct page *head) +{ + int ret; + unsigned long vmemmap_addr = (unsigned long)head; + unsigned long vmemmap_end, vmemmap_reuse; + + if (!HPageVmemmapOptimized(head)) + return 0; + + vmemmap_addr += RESERVE_VMEMMAP_SIZE; + vmemmap_end = vmemmap_addr + free_vmemmap_pages_size_per_hpage(h); + vmemmap_reuse = vmemmap_addr - PAGE_SIZE; + /* + * The pages which the vmemmap virtual address range [@vmemmap_addr, + * @vmemmap_end) are mapped to are freed to the buddy allocator, and + * the range is mapped to the page which @vmemmap_reuse is mapped to. + * When a HugeTLB page is freed to the buddy allocator, previously + * discarded vmemmap pages must be allocated and remapping. + */ + ret = vmemmap_remap_alloc(vmemmap_addr, vmemmap_end, vmemmap_reuse, + GFP_KERNEL | __GFP_NORETRY | __GFP_THISNODE); + + if (!ret) + ClearHPageVmemmapOptimized(head); + + return ret; +} + +void free_huge_page_vmemmap(struct hstate *h, struct page *head) +{ + unsigned long vmemmap_addr = (unsigned long)head; + unsigned long vmemmap_end, vmemmap_reuse; + + if (!free_vmemmap_pages_per_hpage(h)) + return; + + vmemmap_addr += RESERVE_VMEMMAP_SIZE; + vmemmap_end = vmemmap_addr + free_vmemmap_pages_size_per_hpage(h); + vmemmap_reuse = vmemmap_addr - PAGE_SIZE; + + /* + * Remap the vmemmap virtual address range [@vmemmap_addr, @vmemmap_end) + * to the page which @vmemmap_reuse is mapped to, then free the pages + * which the range [@vmemmap_addr, @vmemmap_end] is mapped to. + */ + if (!vmemmap_remap_free(vmemmap_addr, vmemmap_end, vmemmap_reuse)) + SetHPageVmemmapOptimized(head); +} + +void __init hugetlb_vmemmap_init(struct hstate *h) +{ + unsigned int nr_pages = pages_per_huge_page(h); + unsigned int vmemmap_pages; + + /* + * There are only (RESERVE_VMEMMAP_SIZE / sizeof(struct page)) struct + * page structs that can be used when CONFIG_HUGETLB_PAGE_FREE_VMEMMAP, + * so add a BUILD_BUG_ON to catch invalid usage of the tail struct page. + */ + BUILD_BUG_ON(__NR_USED_SUBPAGE >= + RESERVE_VMEMMAP_SIZE / sizeof(struct page)); + + if (!hugetlb_free_vmemmap_enabled) + return; + + vmemmap_pages = (nr_pages * sizeof(struct page)) >> PAGE_SHIFT; + /* + * The head page and the first tail page are not to be freed to buddy + * allocator, the other pages will map to the first tail page, so they + * can be freed. + * + * Could RESERVE_VMEMMAP_NR be greater than @vmemmap_pages? It is true + * on some architectures (e.g. aarch64). See Documentation/arm64/ + * hugetlbpage.rst for more details. + */ + if (likely(vmemmap_pages > RESERVE_VMEMMAP_NR)) + h->nr_free_vmemmap_pages = vmemmap_pages - RESERVE_VMEMMAP_NR; + + pr_info("can free %d vmemmap pages for %s\n", h->nr_free_vmemmap_pages, + h->name); +} diff --git a/mm/hugetlb_vmemmap.h b/mm/hugetlb_vmemmap.h new file mode 100644 index 000000000000..cb2bef8f9e73 --- /dev/null +++ b/mm/hugetlb_vmemmap.h @@ -0,0 +1,45 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Free some vmemmap pages of HugeTLB + * + * Copyright (c) 2020, Bytedance. All rights reserved. + * + * Author: Muchun Song + */ +#ifndef _LINUX_HUGETLB_VMEMMAP_H +#define _LINUX_HUGETLB_VMEMMAP_H +#include + +#ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP +int alloc_huge_page_vmemmap(struct hstate *h, struct page *head); +void free_huge_page_vmemmap(struct hstate *h, struct page *head); +void hugetlb_vmemmap_init(struct hstate *h); + +/* + * How many vmemmap pages associated with a HugeTLB page that can be freed + * to the buddy allocator. + */ +static inline unsigned int free_vmemmap_pages_per_hpage(struct hstate *h) +{ + return h->nr_free_vmemmap_pages; +} +#else +static inline int alloc_huge_page_vmemmap(struct hstate *h, struct page *head) +{ + return 0; +} + +static inline void free_huge_page_vmemmap(struct hstate *h, struct page *head) +{ +} + +static inline void hugetlb_vmemmap_init(struct hstate *h) +{ +} + +static inline unsigned int free_vmemmap_pages_per_hpage(struct hstate *h) +{ + return 0; +} +#endif /* CONFIG_HUGETLB_PAGE_FREE_VMEMMAP */ +#endif /* _LINUX_HUGETLB_VMEMMAP_H */ diff --git a/mm/internal.h b/mm/internal.h index 6ec2cea9926b..2d7c9a2e0118 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -274,11 +274,10 @@ isolate_freepages_range(struct compact_control *cc, int isolate_migratepages_range(struct compact_control *cc, unsigned long low_pfn, unsigned long end_pfn); +#endif int find_suitable_fallback(struct free_area *area, unsigned int order, int migratetype, bool only_stealable, bool *can_steal); -#endif - /* * This function returns the order of a free page in the buddy system. In * general, page_zone(page)->lock must be held by the caller to prevent the @@ -344,7 +343,10 @@ void __vma_unlink_list(struct mm_struct *mm, struct vm_area_struct *vma); #ifdef CONFIG_MMU extern long populate_vma_page_range(struct vm_area_struct *vma, - unsigned long start, unsigned long end, int *nonblocking); + unsigned long start, unsigned long end, int *locked); +extern long faultin_vma_page_range(struct vm_area_struct *vma, + unsigned long start, unsigned long end, + bool write, int *locked); extern void munlock_vma_pages_range(struct vm_area_struct *vma, unsigned long start, unsigned long end); static inline void munlock_vma_pages_all(struct vm_area_struct *vma) @@ -369,23 +371,6 @@ extern unsigned int munlock_vma_page(struct page *page); */ extern void clear_page_mlock(struct page *page); -/* - * mlock_migrate_page - called only from migrate_misplaced_transhuge_page() - * (because that does not go through the full procedure of migration ptes): - * to migrate the Mlocked page flag; update statistics. - */ -static inline void mlock_migrate_page(struct page *newpage, struct page *page) -{ - if (TestClearPageMlocked(page)) { - int nr_pages = thp_nr_pages(page); - - /* Holding pmd lock, no change in irq context: __mod is safe */ - __mod_zone_page_state(page_zone(page), NR_MLOCK, -nr_pages); - SetPageMlocked(newpage); - __mod_zone_page_state(page_zone(newpage), NR_MLOCK, nr_pages); - } -} - extern pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma); /* @@ -461,7 +446,6 @@ static inline struct file *maybe_unlock_mmap_for_io(struct vm_fault *vmf, #else /* !CONFIG_MMU */ static inline void clear_page_mlock(struct page *page) { } static inline void mlock_vma_page(struct page *page) { } -static inline void mlock_migrate_page(struct page *new, struct page *old) { } static inline void vunmap_range_noflush(unsigned long start, unsigned long end) { } @@ -672,4 +656,7 @@ int vmap_pages_range_noflush(unsigned long addr, unsigned long end, void vunmap_range_noflush(unsigned long start, unsigned long end); +int numa_migrate_prep(struct page *page, struct vm_area_struct *vma, + unsigned long addr, int page_nid, int *flags); + #endif /* __MM_INTERNAL_H */ diff --git a/mm/kfence/core.c b/mm/kfence/core.c index 4d21ac44d5d3..d7666ace9d2e 100644 --- a/mm/kfence/core.c +++ b/mm/kfence/core.c @@ -636,7 +636,7 @@ static void toggle_allocation_gate(struct work_struct *work) /* Disable static key and reset timer. */ static_branch_disable(&kfence_allocation_key); #endif - queue_delayed_work(system_power_efficient_wq, &kfence_timer, + queue_delayed_work(system_unbound_wq, &kfence_timer, msecs_to_jiffies(kfence_sample_interval)); } static DECLARE_DELAYED_WORK(kfence_timer, toggle_allocation_gate); @@ -666,7 +666,7 @@ void __init kfence_init(void) } WRITE_ONCE(kfence_enabled, true); - queue_delayed_work(system_power_efficient_wq, &kfence_timer, 0); + queue_delayed_work(system_unbound_wq, &kfence_timer, 0); pr_info("initialized - using %lu bytes for %d objects at 0x%p-0x%p\n", KFENCE_POOL_SIZE, CONFIG_KFENCE_NUM_OBJECTS, (void *)__kfence_pool, (void *)(__kfence_pool + KFENCE_POOL_SIZE)); diff --git a/mm/khugepaged.c b/mm/khugepaged.c index 6c0185fdd815..b0412be08fa2 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -442,9 +442,7 @@ static inline int khugepaged_test_exit(struct mm_struct *mm) static bool hugepage_vma_check(struct vm_area_struct *vma, unsigned long vm_flags) { - /* Explicitly disabled through madvise. */ - if ((vm_flags & VM_NOHUGEPAGE) || - test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags)) + if (!transhuge_vma_enabled(vma, vm_flags)) return false; /* Enabled via shmem mount options or sysfs settings. */ @@ -459,7 +457,8 @@ static bool hugepage_vma_check(struct vm_area_struct *vma, /* Read-only file mappings need to be aligned for THP to work. */ if (IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS) && vma->vm_file && - (vm_flags & VM_DENYWRITE)) { + !inode_is_open_for_write(vma->vm_file->f_inode) && + (vm_flags & VM_EXEC)) { return IS_ALIGNED((vma->vm_start >> PAGE_SHIFT) - vma->vm_pgoff, HPAGE_PMD_NR); } @@ -1864,6 +1863,19 @@ static void collapse_file(struct mm_struct *mm, else { __mod_lruvec_page_state(new_page, NR_FILE_THPS, nr); filemap_nr_thps_inc(mapping); + /* + * Paired with smp_mb() in do_dentry_open() to ensure + * i_writecount is up to date and the update to nr_thps is + * visible. Ensures the page cache will be truncated if the + * file is opened writable. + */ + smp_mb(); + if (inode_is_open_for_write(mapping->host)) { + result = SCAN_FAIL; + __mod_lruvec_page_state(new_page, NR_FILE_THPS, -nr); + filemap_nr_thps_dec(mapping); + goto xa_locked; + } } if (nr_none) { diff --git a/mm/madvise.c b/mm/madvise.c index 63e489e5bfdb..6d3d348b17f4 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -53,6 +53,8 @@ static int madvise_need_mmap_write(int behavior) case MADV_COLD: case MADV_PAGEOUT: case MADV_FREE: + case MADV_POPULATE_READ: + case MADV_POPULATE_WRITE: return 0; default: /* be safe, default to 1. list exceptions explicitly */ @@ -822,6 +824,61 @@ static long madvise_dontneed_free(struct vm_area_struct *vma, return -EINVAL; } +static long madvise_populate(struct vm_area_struct *vma, + struct vm_area_struct **prev, + unsigned long start, unsigned long end, + int behavior) +{ + const bool write = behavior == MADV_POPULATE_WRITE; + struct mm_struct *mm = vma->vm_mm; + unsigned long tmp_end; + int locked = 1; + long pages; + + *prev = vma; + + while (start < end) { + /* + * We might have temporarily dropped the lock. For example, + * our VMA might have been split. + */ + if (!vma || start >= vma->vm_end) { + vma = find_vma(mm, start); + if (!vma || start < vma->vm_start) + return -ENOMEM; + } + + tmp_end = min_t(unsigned long, end, vma->vm_end); + /* Populate (prefault) page tables readable/writable. */ + pages = faultin_vma_page_range(vma, start, tmp_end, write, + &locked); + if (!locked) { + mmap_read_lock(mm); + locked = 1; + *prev = NULL; + vma = NULL; + } + if (pages < 0) { + switch (pages) { + case -EINTR: + return -EINTR; + case -EFAULT: /* Incompatible mappings / permissions. */ + return -EINVAL; + case -EHWPOISON: + return -EHWPOISON; + default: + pr_warn_once("%s: unhandled return value: %ld\n", + __func__, pages); + fallthrough; + case -ENOMEM: + return -ENOMEM; + } + } + start += pages * PAGE_SIZE; + } + return 0; +} + /* * Application wants to free up the pages and associated backing store. * This is effectively punching a hole into the middle of a file. @@ -935,6 +992,9 @@ madvise_vma(struct vm_area_struct *vma, struct vm_area_struct **prev, case MADV_FREE: case MADV_DONTNEED: return madvise_dontneed_free(vma, prev, start, end, behavior); + case MADV_POPULATE_READ: + case MADV_POPULATE_WRITE: + return madvise_populate(vma, prev, start, end, behavior); default: return madvise_behavior(vma, prev, start, end, behavior); } @@ -955,6 +1015,8 @@ madvise_behavior_valid(int behavior) case MADV_FREE: case MADV_COLD: case MADV_PAGEOUT: + case MADV_POPULATE_READ: + case MADV_POPULATE_WRITE: #ifdef CONFIG_KSM case MADV_MERGEABLE: case MADV_UNMERGEABLE: @@ -1042,6 +1104,10 @@ process_madvise_behavior_valid(int behavior) * easily if memory pressure happens. * MADV_PAGEOUT - the application is not expected to use this memory soon, * page out the pages in this range immediately. + * MADV_POPULATE_READ - populate (prefault) page tables readable by + * triggering read faults if required + * MADV_POPULATE_WRITE - populate (prefault) page tables writable by + * triggering write faults if required * * return values: * zero - success diff --git a/mm/mapping_dirty_helpers.c b/mm/mapping_dirty_helpers.c index b890854ec761..ea734f248fce 100644 --- a/mm/mapping_dirty_helpers.c +++ b/mm/mapping_dirty_helpers.c @@ -317,7 +317,7 @@ EXPORT_SYMBOL_GPL(wp_shared_mapping_range); * pfn_mkwrite(). And then after a TLB flush following the write-protection * pick up all dirty bits. * - * Note: This function currently skips transhuge page-table entries, since + * This function currently skips transhuge page-table entries, since * it's intended for dirty-tracking on the PTE level. It will warn on * encountering transhuge dirty entries, though, and can easily be extended * to handle them as well. diff --git a/mm/memblock.c b/mm/memblock.c index 123feef5259d..3e4acbf03ab7 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -906,6 +906,11 @@ int __init_memblock memblock_mark_mirror(phys_addr_t base, phys_addr_t size) * @base: the base phys addr of the region * @size: the size of the region * + * The memory regions marked with %MEMBLOCK_NOMAP will not be added to the + * direct mapping of the physical memory. These regions will still be + * covered by the memory map. The struct page representing NOMAP memory + * frames in the memory map will be PageReserved() + * * Return: 0 on success, -errno on failure. */ int __init_memblock memblock_mark_nomap(phys_addr_t base, phys_addr_t size) @@ -2002,6 +2007,26 @@ static unsigned long __init __free_memory_core(phys_addr_t start, return end_pfn - start_pfn; } +static void __init memmap_init_reserved_pages(void) +{ + struct memblock_region *region; + phys_addr_t start, end; + u64 i; + + /* initialize struct pages for the reserved regions */ + for_each_reserved_mem_range(i, &start, &end) + reserve_bootmem_region(start, end); + + /* and also treat struct pages for the NOMAP regions as PageReserved */ + for_each_mem_region(region) { + if (memblock_is_nomap(region)) { + start = region->base; + end = start + region->size; + reserve_bootmem_region(start, end); + } + } +} + static unsigned long __init free_low_memory_core_early(void) { unsigned long count = 0; @@ -2010,8 +2035,7 @@ static unsigned long __init free_low_memory_core_early(void) memblock_clear_hotplug(0, -1); - for_each_reserved_mem_range(i, &start, &end) - reserve_bootmem_region(start, end); + memmap_init_reserved_pages(); /* * We need to use NUMA_NO_NODE instead of NODE_DATA(0)->node_id diff --git a/mm/memcontrol.c b/mm/memcontrol.c index b80aae448a49..ae1f5d0cb581 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -5537,7 +5537,7 @@ static struct page *mc_handle_swap_pte(struct vm_area_struct *vma, * as special swap entry in the CPU page table. */ if (is_device_private_entry(ent)) { - page = device_private_entry_to_page(ent); + page = pfn_swap_entry_to_page(ent); /* * MEMORY_DEVICE_PRIVATE means ZONE_DEVICE page and which have * a refcount of 1 when free (unlike normal page) @@ -6644,7 +6644,7 @@ static unsigned long effective_protection(unsigned long usage, } /** - * mem_cgroup_protected - check if memory consumption is in the normal range + * mem_cgroup_calculate_protection - check if memory consumption is in the normal range * @root: the top ancestor of the sub-tree being checked * @memcg: the memory cgroup to check * diff --git a/mm/memory-failure.c b/mm/memory-failure.c index e5a1531f7f4e..eefd823deb67 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -66,6 +66,19 @@ int sysctl_memory_failure_recovery __read_mostly = 1; atomic_long_t num_poisoned_pages __read_mostly = ATOMIC_LONG_INIT(0); +static bool __page_handle_poison(struct page *page) +{ + bool ret; + + zone_pcp_disable(page_zone(page)); + ret = dissolve_free_huge_page(page); + if (!ret) + ret = take_page_off_buddy(page); + zone_pcp_enable(page_zone(page)); + + return ret; +} + static bool page_handle_poison(struct page *page, bool hugepage_or_freepage, bool release) { if (hugepage_or_freepage) { @@ -73,7 +86,7 @@ static bool page_handle_poison(struct page *page, bool hugepage_or_freepage, boo * Doing this check for free pages is also fine since dissolve_free_huge_page * returns 0 for non-hugetlb pages as well. */ - if (dissolve_free_huge_page(page) || !take_page_off_buddy(page)) + if (!__page_handle_poison(page)) /* * We could fail to take off the target page from buddy * for example due to racy page allocation, but that's @@ -985,7 +998,7 @@ static int me_huge_page(struct page *p, unsigned long pfn) */ if (PageAnon(hpage)) put_page(hpage); - if (!dissolve_free_huge_page(p) && take_page_off_buddy(p)) { + if (__page_handle_poison(p)) { page_ref_inc(p); res = MF_RECOVERED; } @@ -1253,10 +1266,10 @@ static int get_hwpoison_page(struct page *p, unsigned long flags) static bool hwpoison_user_mappings(struct page *p, unsigned long pfn, int flags, struct page **hpagep) { - enum ttu_flags ttu = TTU_IGNORE_MLOCK; + enum ttu_flags ttu = TTU_IGNORE_MLOCK | TTU_SYNC; struct address_space *mapping; LIST_HEAD(tokill); - bool unmap_success = true; + bool unmap_success; int kill = 1, forcekill; struct page *hpage = *hpagep; bool mlocked = PageMlocked(hpage); @@ -1319,7 +1332,7 @@ static bool hwpoison_user_mappings(struct page *p, unsigned long pfn, collect_procs(hpage, &tokill, flags & MF_ACTION_REQUIRED); if (!PageHuge(hpage)) { - unmap_success = try_to_unmap(hpage, ttu); + try_to_unmap(hpage, ttu); } else { if (!PageAnon(hpage)) { /* @@ -1327,21 +1340,20 @@ static bool hwpoison_user_mappings(struct page *p, unsigned long pfn, * could potentially call huge_pmd_unshare. Because of * this, take semaphore in write mode here and set * TTU_RMAP_LOCKED to indicate we have taken the lock - * at this higer level. + * at this higher level. */ mapping = hugetlb_page_mapping_lock_write(hpage); if (mapping) { - unmap_success = try_to_unmap(hpage, - ttu|TTU_RMAP_LOCKED); + try_to_unmap(hpage, ttu|TTU_RMAP_LOCKED); i_mmap_unlock_write(mapping); - } else { + } else pr_info("Memory failure: %#lx: could not lock mapping for mapped huge page\n", pfn); - unmap_success = false; - } } else { - unmap_success = try_to_unmap(hpage, ttu); + try_to_unmap(hpage, ttu); } } + + unmap_success = !page_mapped(hpage); if (!unmap_success) pr_err("Memory failure: %#lx: failed to unmap page (mapcount=%d)\n", pfn, page_mapcount(hpage)); @@ -1446,7 +1458,7 @@ static int memory_failure_hugetlb(unsigned long pfn, int flags) } unlock_page(head); res = MF_FAILED; - if (!dissolve_free_huge_page(p) && take_page_off_buddy(p)) { + if (__page_handle_poison(p)) { page_ref_inc(p); res = MF_RECOVERED; } diff --git a/mm/memory.c b/mm/memory.c index 48c4576df898..747a01d495f2 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -699,6 +699,68 @@ struct page *vm_normal_page_pmd(struct vm_area_struct *vma, unsigned long addr, } #endif +static void restore_exclusive_pte(struct vm_area_struct *vma, + struct page *page, unsigned long address, + pte_t *ptep) +{ + pte_t pte; + swp_entry_t entry; + + pte = pte_mkold(mk_pte(page, READ_ONCE(vma->vm_page_prot))); + if (pte_swp_soft_dirty(*ptep)) + pte = pte_mksoft_dirty(pte); + + entry = pte_to_swp_entry(*ptep); + if (pte_swp_uffd_wp(*ptep)) + pte = pte_mkuffd_wp(pte); + else if (is_writable_device_exclusive_entry(entry)) + pte = maybe_mkwrite(pte_mkdirty(pte), vma); + + set_pte_at(vma->vm_mm, address, ptep, pte); + + /* + * No need to take a page reference as one was already + * created when the swap entry was made. + */ + if (PageAnon(page)) + page_add_anon_rmap(page, vma, address, false); + else + /* + * Currently device exclusive access only supports anonymous + * memory so the entry shouldn't point to a filebacked page. + */ + WARN_ON_ONCE(!PageAnon(page)); + + if (vma->vm_flags & VM_LOCKED) + mlock_vma_page(page); + + /* + * No need to invalidate - it was non-present before. However + * secondary CPUs may have mappings that need invalidating. + */ + update_mmu_cache(vma, address, ptep); +} + +/* + * Tries to restore an exclusive pte if the page lock can be acquired without + * sleeping. + */ +static int +try_restore_exclusive_pte(pte_t *src_pte, struct vm_area_struct *vma, + unsigned long addr) +{ + swp_entry_t entry = pte_to_swp_entry(*src_pte); + struct page *page = pfn_swap_entry_to_page(entry); + + if (trylock_page(page)) { + restore_exclusive_pte(vma, page, addr, src_pte); + unlock_page(page); + return 0; + } + + return -EBUSY; +} + /* * copy one vm_area from one task to the other. Assumes the page tables * already present in the new task to be cleared in the whole range @@ -707,17 +769,17 @@ struct page *vm_normal_page_pmd(struct vm_area_struct *vma, unsigned long addr, static unsigned long copy_nonpresent_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm, - pte_t *dst_pte, pte_t *src_pte, struct vm_area_struct *vma, - unsigned long addr, int *rss) + pte_t *dst_pte, pte_t *src_pte, struct vm_area_struct *dst_vma, + struct vm_area_struct *src_vma, unsigned long addr, int *rss) { - unsigned long vm_flags = vma->vm_flags; + unsigned long vm_flags = dst_vma->vm_flags; pte_t pte = *src_pte; struct page *page; swp_entry_t entry = pte_to_swp_entry(pte); if (likely(!non_swap_entry(entry))) { if (swap_duplicate(entry) < 0) - return entry.val; + return -EIO; /* make sure dst_mm is on swapoff's mmlist. */ if (unlikely(list_empty(&dst_mm->mmlist))) { @@ -729,17 +791,18 @@ copy_nonpresent_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm, } rss[MM_SWAPENTS]++; } else if (is_migration_entry(entry)) { - page = migration_entry_to_page(entry); + page = pfn_swap_entry_to_page(entry); rss[mm_counter(page)]++; - if (is_write_migration_entry(entry) && + if (is_writable_migration_entry(entry) && is_cow_mapping(vm_flags)) { /* * COW mappings require pages in both * parent and child to be set to read. */ - make_migration_entry_read(&entry); + entry = make_readable_migration_entry( + swp_offset(entry)); pte = swp_entry_to_pte(entry); if (pte_swp_soft_dirty(*src_pte)) pte = pte_swp_mksoft_dirty(pte); @@ -748,7 +811,7 @@ copy_nonpresent_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm, set_pte_at(src_mm, addr, src_pte, pte); } } else if (is_device_private_entry(entry)) { - page = device_private_entry_to_page(entry); + page = pfn_swap_entry_to_page(entry); /* * Update rss count even for unaddressable pages, as @@ -770,15 +833,29 @@ copy_nonpresent_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm, * when a device driver is involved (you cannot easily * save and restore device driver state). */ - if (is_write_device_private_entry(entry) && + if (is_writable_device_private_entry(entry) && is_cow_mapping(vm_flags)) { - make_device_private_entry_read(&entry); + entry = make_readable_device_private_entry( + swp_offset(entry)); pte = swp_entry_to_pte(entry); if (pte_swp_uffd_wp(*src_pte)) pte = pte_swp_mkuffd_wp(pte); set_pte_at(src_mm, addr, src_pte, pte); } + } else if (is_device_exclusive_entry(entry)) { + /* + * Make device exclusive entries present by restoring the + * original entry then copying as for a present pte. Device + * exclusive entries currently only support private writable + * (ie. COW) mappings. + */ + VM_BUG_ON(!is_cow_mapping(src_vma->vm_flags)); + if (try_restore_exclusive_pte(src_pte, src_vma, addr)) + return -EBUSY; + return -ENOENT; } + if (!userfaultfd_wp(dst_vma)) + pte = pte_swp_clear_uffd_wp(pte); set_pte_at(dst_mm, addr, dst_pte, pte); return 0; } @@ -844,6 +921,9 @@ copy_present_page(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma /* All done, just insert the new page copy in the child */ pte = mk_pte(new_page, dst_vma->vm_page_prot); pte = maybe_mkwrite(pte_mkdirty(pte), dst_vma); + if (userfaultfd_pte_wp(dst_vma, *src_pte)) + /* Uffd-wp needs to be delivered to dest pte as well */ + pte = pte_wrprotect(pte_mkuffd_wp(pte)); set_pte_at(dst_vma->vm_mm, addr, dst_pte, pte); return 0; } @@ -893,12 +973,7 @@ copy_present_pte(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, pte = pte_mkclean(pte); pte = pte_mkold(pte); - /* - * Make sure the _PAGE_UFFD_WP bit is cleared if the new VMA - * does not have the VM_UFFD_WP, which means that the uffd - * fork event is not enabled. - */ - if (!(vm_flags & VM_UFFD_WP)) + if (!userfaultfd_wp(dst_vma)) pte = pte_clear_uffd_wp(pte); set_pte_at(dst_vma->vm_mm, addr, dst_pte, pte); @@ -971,13 +1046,25 @@ copy_pte_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, continue; } if (unlikely(!pte_present(*src_pte))) { - entry.val = copy_nonpresent_pte(dst_mm, src_mm, - dst_pte, src_pte, - src_vma, addr, rss); - if (entry.val) + ret = copy_nonpresent_pte(dst_mm, src_mm, + dst_pte, src_pte, + dst_vma, src_vma, + addr, rss); + if (ret == -EIO) { + entry = pte_to_swp_entry(*src_pte); break; - progress += 8; - continue; + } else if (ret == -EBUSY) { + break; + } else if (!ret) { + progress += 8; + continue; + } + + /* + * Device exclusive entry restored, continue by copying + * the now present pte. + */ + WARN_ON_ONCE(ret != -ENOENT); } /* copy_present_pte() will clear `*prealloc' if consumed */ ret = copy_present_pte(dst_vma, src_vma, dst_pte, src_pte, @@ -1008,20 +1095,26 @@ copy_pte_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, pte_unmap_unlock(orig_dst_pte, dst_ptl); cond_resched(); - if (entry.val) { + if (ret == -EIO) { + VM_WARN_ON_ONCE(!entry.val); if (add_swap_count_continuation(entry, GFP_KERNEL) < 0) { ret = -ENOMEM; goto out; } entry.val = 0; - } else if (ret) { - WARN_ON_ONCE(ret != -EAGAIN); + } else if (ret == -EBUSY) { + goto out; + } else if (ret == -EAGAIN) { prealloc = page_copy_prealloc(src_mm, src_vma, addr); if (!prealloc) return -ENOMEM; - /* We've captured and resolved the error. Reset, try again. */ - ret = 0; + } else if (ret) { + VM_WARN_ON_ONCE(1); } + + /* We've captured and resolved the error. Reset, try again. */ + ret = 0; + if (addr != end) goto again; out: @@ -1050,8 +1143,8 @@ copy_pmd_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, || pmd_devmap(*src_pmd)) { int err; VM_BUG_ON_VMA(next-addr != HPAGE_PMD_SIZE, src_vma); - err = copy_huge_pmd(dst_mm, src_mm, - dst_pmd, src_pmd, addr, src_vma); + err = copy_huge_pmd(dst_mm, src_mm, dst_pmd, src_pmd, + addr, dst_vma, src_vma); if (err == -ENOMEM) return -ENOMEM; if (!err) @@ -1278,8 +1371,9 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb, } entry = pte_to_swp_entry(ptent); - if (is_device_private_entry(entry)) { - struct page *page = device_private_entry_to_page(entry); + if (is_device_private_entry(entry) || + is_device_exclusive_entry(entry)) { + struct page *page = pfn_swap_entry_to_page(entry); if (unlikely(details && details->check_mapping)) { /* @@ -1294,7 +1388,10 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb, pte_clear_not_present_full(mm, addr, pte, tlb->fullmm); rss[mm_counter(page)]--; - page_remove_rmap(page, false); + + if (is_device_private_entry(entry)) + page_remove_rmap(page, false); + put_page(page); continue; } @@ -1308,7 +1405,7 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb, else if (is_migration_entry(entry)) { struct page *page; - page = migration_entry_to_page(entry); + page = pfn_swap_entry_to_page(entry); rss[mm_counter(page)]--; } if (unlikely(!free_swap_and_cache(entry))) @@ -3342,6 +3439,34 @@ void unmap_mapping_range(struct address_space *mapping, } EXPORT_SYMBOL(unmap_mapping_range); +/* + * Restore a potential device exclusive pte to a working pte entry + */ +static vm_fault_t remove_device_exclusive_entry(struct vm_fault *vmf) +{ + struct page *page = vmf->page; + struct vm_area_struct *vma = vmf->vma; + struct mmu_notifier_range range; + + if (!lock_page_or_retry(page, vma->vm_mm, vmf->flags)) + return VM_FAULT_RETRY; + mmu_notifier_range_init_owner(&range, MMU_NOTIFY_EXCLUSIVE, 0, vma, + vma->vm_mm, vmf->address & PAGE_MASK, + (vmf->address & PAGE_MASK) + PAGE_SIZE, NULL); + mmu_notifier_invalidate_range_start(&range); + + vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address, + &vmf->ptl); + if (likely(pte_same(*vmf->pte, vmf->orig_pte))) + restore_exclusive_pte(vma, page, vmf->address, vmf->pte); + + pte_unmap_unlock(vmf->pte, vmf->ptl); + unlock_page(page); + + mmu_notifier_invalidate_range_end(&range); + return 0; +} + /* * We enter with non-exclusive mmap_lock (to exclude vma changes, * but allow concurrent faults), and pte mapped but not yet locked. @@ -3370,8 +3495,11 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) if (is_migration_entry(entry)) { migration_entry_wait(vma->vm_mm, vmf->pmd, vmf->address); + } else if (is_device_exclusive_entry(entry)) { + vmf->page = pfn_swap_entry_to_page(entry); + ret = remove_device_exclusive_entry(vmf); } else if (is_device_private_entry(entry)) { - vmf->page = device_private_entry_to_page(entry); + vmf->page = pfn_swap_entry_to_page(entry); ret = vmf->page->pgmap->ops->migrate_to_ram(vmf); } else if (is_hwpoison_entry(entry)) { ret = VM_FAULT_HWPOISON; @@ -4025,9 +4153,11 @@ static vm_fault_t do_read_fault(struct vm_fault *vmf) * something). */ if (vma->vm_ops->map_pages && fault_around_bytes >> PAGE_SHIFT > 1) { - ret = do_fault_around(vmf); - if (ret) - return ret; + if (likely(!userfaultfd_minor(vmf->vma))) { + ret = do_fault_around(vmf); + if (ret) + return ret; + } } ret = __do_fault(vmf); @@ -4172,9 +4302,8 @@ static vm_fault_t do_fault(struct vm_fault *vmf) return ret; } -static int numa_migrate_prep(struct page *page, struct vm_area_struct *vma, - unsigned long addr, int page_nid, - int *flags) +int numa_migrate_prep(struct page *page, struct vm_area_struct *vma, + unsigned long addr, int page_nid, int *flags) { get_page(page); @@ -4295,12 +4424,12 @@ static inline vm_fault_t create_huge_pmd(struct vm_fault *vmf) } /* `inline' is required to avoid gcc 4.1.2 build error */ -static inline vm_fault_t wp_huge_pmd(struct vm_fault *vmf, pmd_t orig_pmd) +static inline vm_fault_t wp_huge_pmd(struct vm_fault *vmf) { if (vma_is_anonymous(vmf->vma)) { - if (userfaultfd_huge_pmd_wp(vmf->vma, orig_pmd)) + if (userfaultfd_huge_pmd_wp(vmf->vma, vmf->orig_pmd)) return handle_userfault(vmf, VM_UFFD_WP); - return do_huge_pmd_wp_page(vmf, orig_pmd); + return do_huge_pmd_wp_page(vmf); } if (vmf->vma->vm_ops->huge_fault) { vm_fault_t ret = vmf->vma->vm_ops->huge_fault(vmf, PE_SIZE_PMD); @@ -4527,26 +4656,26 @@ static vm_fault_t __handle_mm_fault(struct vm_area_struct *vma, if (!(ret & VM_FAULT_FALLBACK)) return ret; } else { - pmd_t orig_pmd = *vmf.pmd; + vmf.orig_pmd = *vmf.pmd; barrier(); - if (unlikely(is_swap_pmd(orig_pmd))) { + if (unlikely(is_swap_pmd(vmf.orig_pmd))) { VM_BUG_ON(thp_migration_supported() && - !is_pmd_migration_entry(orig_pmd)); - if (is_pmd_migration_entry(orig_pmd)) + !is_pmd_migration_entry(vmf.orig_pmd)); + if (is_pmd_migration_entry(vmf.orig_pmd)) pmd_migration_entry_wait(mm, vmf.pmd); return 0; } - if (pmd_trans_huge(orig_pmd) || pmd_devmap(orig_pmd)) { - if (pmd_protnone(orig_pmd) && vma_is_accessible(vma)) - return do_huge_pmd_numa_page(&vmf, orig_pmd); + if (pmd_trans_huge(vmf.orig_pmd) || pmd_devmap(vmf.orig_pmd)) { + if (pmd_protnone(vmf.orig_pmd) && vma_is_accessible(vma)) + return do_huge_pmd_numa_page(&vmf); - if (dirty && !pmd_write(orig_pmd)) { - ret = wp_huge_pmd(&vmf, orig_pmd); + if (dirty && !pmd_write(vmf.orig_pmd)) { + ret = wp_huge_pmd(&vmf); if (!(ret & VM_FAULT_FALLBACK)) return ret; } else { - huge_pmd_set_accessed(&vmf, orig_pmd); + huge_pmd_set_accessed(&vmf); return 0; } } diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 974a565797d8..8cb75b26ea4f 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -154,122 +154,6 @@ static void release_memory_resource(struct resource *res) } #ifdef CONFIG_MEMORY_HOTPLUG_SPARSE -void get_page_bootmem(unsigned long info, struct page *page, - unsigned long type) -{ - page->freelist = (void *)type; - SetPagePrivate(page); - set_page_private(page, info); - page_ref_inc(page); -} - -void put_page_bootmem(struct page *page) -{ - unsigned long type; - - type = (unsigned long) page->freelist; - BUG_ON(type < MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE || - type > MEMORY_HOTPLUG_MAX_BOOTMEM_TYPE); - - if (page_ref_dec_return(page) == 1) { - page->freelist = NULL; - ClearPagePrivate(page); - set_page_private(page, 0); - INIT_LIST_HEAD(&page->lru); - free_reserved_page(page); - } -} - -#ifdef CONFIG_HAVE_BOOTMEM_INFO_NODE -#ifndef CONFIG_SPARSEMEM_VMEMMAP -static void register_page_bootmem_info_section(unsigned long start_pfn) -{ - unsigned long mapsize, section_nr, i; - struct mem_section *ms; - struct page *page, *memmap; - struct mem_section_usage *usage; - - section_nr = pfn_to_section_nr(start_pfn); - ms = __nr_to_section(section_nr); - - /* Get section's memmap address */ - memmap = sparse_decode_mem_map(ms->section_mem_map, section_nr); - - /* - * Get page for the memmap's phys address - * XXX: need more consideration for sparse_vmemmap... - */ - page = virt_to_page(memmap); - mapsize = sizeof(struct page) * PAGES_PER_SECTION; - mapsize = PAGE_ALIGN(mapsize) >> PAGE_SHIFT; - - /* remember memmap's page */ - for (i = 0; i < mapsize; i++, page++) - get_page_bootmem(section_nr, page, SECTION_INFO); - - usage = ms->usage; - page = virt_to_page(usage); - - mapsize = PAGE_ALIGN(mem_section_usage_size()) >> PAGE_SHIFT; - - for (i = 0; i < mapsize; i++, page++) - get_page_bootmem(section_nr, page, MIX_SECTION_INFO); - -} -#else /* CONFIG_SPARSEMEM_VMEMMAP */ -static void register_page_bootmem_info_section(unsigned long start_pfn) -{ - unsigned long mapsize, section_nr, i; - struct mem_section *ms; - struct page *page, *memmap; - struct mem_section_usage *usage; - - section_nr = pfn_to_section_nr(start_pfn); - ms = __nr_to_section(section_nr); - - memmap = sparse_decode_mem_map(ms->section_mem_map, section_nr); - - register_page_bootmem_memmap(section_nr, memmap, PAGES_PER_SECTION); - - usage = ms->usage; - page = virt_to_page(usage); - - mapsize = PAGE_ALIGN(mem_section_usage_size()) >> PAGE_SHIFT; - - for (i = 0; i < mapsize; i++, page++) - get_page_bootmem(section_nr, page, MIX_SECTION_INFO); -} -#endif /* !CONFIG_SPARSEMEM_VMEMMAP */ - -void __init register_page_bootmem_info_node(struct pglist_data *pgdat) -{ - unsigned long i, pfn, end_pfn, nr_pages; - int node = pgdat->node_id; - struct page *page; - - nr_pages = PAGE_ALIGN(sizeof(struct pglist_data)) >> PAGE_SHIFT; - page = virt_to_page(pgdat); - - for (i = 0; i < nr_pages; i++, page++) - get_page_bootmem(node, page, NODE_INFO); - - pfn = pgdat->node_start_pfn; - end_pfn = pgdat_end_pfn(pgdat); - - /* register section info */ - for (; pfn < end_pfn; pfn += PAGES_PER_SECTION) { - /* - * Some platforms can assign the same pfn to multiple nodes - on - * node0 as well as nodeN. To avoid registering a pfn against - * multiple nodes we check that this pfn does not already - * reside in some other nodes. - */ - if (pfn_valid(pfn) && (early_pfn_to_nid(pfn) == node)) - register_page_bootmem_info_section(pfn); - } -} -#endif /* CONFIG_HAVE_BOOTMEM_INFO_NODE */ - static int check_pfn_span(unsigned long pfn, unsigned long nr_pages, const char *reason) { @@ -445,7 +329,6 @@ static void shrink_zone_span(struct zone *zone, unsigned long start_pfn, unsigned long pfn; int nid = zone_to_nid(zone); - zone_span_writelock(zone); if (zone->zone_start_pfn == start_pfn) { /* * If the section is smallest section in the zone, it need @@ -478,7 +361,6 @@ static void shrink_zone_span(struct zone *zone, unsigned long start_pfn, zone->spanned_pages = 0; } } - zone_span_writeunlock(zone); } static void update_pgdat_span(struct pglist_data *pgdat) @@ -515,7 +397,7 @@ void __ref remove_pfn_range_from_zone(struct zone *zone, { const unsigned long end_pfn = start_pfn + nr_pages; struct pglist_data *pgdat = zone->zone_pgdat; - unsigned long pfn, cur_nr_pages, flags; + unsigned long pfn, cur_nr_pages; /* Poison struct pages because they are now uninitialized again. */ for (pfn = start_pfn; pfn < end_pfn; pfn += cur_nr_pages) { @@ -540,10 +422,8 @@ void __ref remove_pfn_range_from_zone(struct zone *zone, clear_zone_contiguous(zone); - pgdat_resize_lock(zone->zone_pgdat, &flags); shrink_zone_span(zone, start_pfn, start_pfn + nr_pages); update_pgdat_span(pgdat); - pgdat_resize_unlock(zone->zone_pgdat, &flags); set_zone_contiguous(zone); } @@ -750,19 +630,13 @@ void __ref move_pfn_range_to_zone(struct zone *zone, unsigned long start_pfn, { struct pglist_data *pgdat = zone->zone_pgdat; int nid = pgdat->node_id; - unsigned long flags; clear_zone_contiguous(zone); - /* TODO Huh pgdat is irqsave while zone is not. It used to be like that before */ - pgdat_resize_lock(pgdat, &flags); - zone_span_writelock(zone); if (zone_is_empty(zone)) init_currently_empty_zone(zone, start_pfn, nr_pages); resize_zone_range(zone, start_pfn, nr_pages); - zone_span_writeunlock(zone); resize_pgdat_range(pgdat, start_pfn, nr_pages); - pgdat_resize_unlock(pgdat, &flags); /* * Subsection population requires care in pfn_to_online_page(). @@ -852,12 +726,8 @@ struct zone *zone_for_pfn_range(int online_type, int nid, unsigned start_pfn, */ void adjust_present_page_count(struct zone *zone, long nr_pages) { - unsigned long flags; - zone->present_pages += nr_pages; - pgdat_resize_lock(zone->zone_pgdat, &flags); zone->zone_pgdat->node_present_pages += nr_pages; - pgdat_resize_unlock(zone->zone_pgdat, &flags); } int mhp_init_memmap_on_memory(unsigned long pfn, unsigned long nr_pages, @@ -913,7 +783,7 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, struct zone *z /* * {on,off}lining is constrained to full memory sections (or more - * precisly to memory blocks from the user space POV). + * precisely to memory blocks from the user space POV). * memmap_on_memory is an exception because it reserves initial part * of the physical memory space for vmemmaps. That space is pageblock * aligned. @@ -1072,8 +942,8 @@ static void rollback_node_hotadd(int nid) } -/** - * try_online_node - online a node if offlined +/* + * __try_online_node - online a node if offlined * @nid: the node ID * @set_node_online: Whether we want to online the node * called by cpu_up() to online a node without onlined memory. @@ -1172,6 +1042,7 @@ bool mhp_supports_memmap_on_memory(unsigned long size) * populate a single PMD. */ return memmap_on_memory && + !hugetlb_free_vmemmap_enabled && IS_ENABLED(CONFIG_MHP_MEMMAP_ON_MEMORY) && size == memory_block_size_bytes() && IS_ALIGNED(vmemmap_size, PMD_SIZE) && @@ -1521,6 +1392,8 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn) struct page *page, *head; int ret = 0; LIST_HEAD(source); + static DEFINE_RATELIMIT_STATE(migrate_rs, DEFAULT_RATELIMIT_INTERVAL, + DEFAULT_RATELIMIT_BURST); for (pfn = start_pfn; pfn < end_pfn; pfn++) { if (!pfn_valid(pfn)) @@ -1567,8 +1440,10 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn) page_is_file_lru(page)); } else { - pr_warn("failed to isolate pfn %lx\n", pfn); - dump_page(page, "isolation failed"); + if (__ratelimit(&migrate_rs)) { + pr_warn("failed to isolate pfn %lx\n", pfn); + dump_page(page, "isolation failed"); + } } put_page(page); } @@ -1597,9 +1472,11 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn) (unsigned long)&mtc, MIGRATE_SYNC, MR_MEMORY_HOTPLUG); if (ret) { list_for_each_entry(page, &source, lru) { - pr_warn("migrating pfn %lx failed ret:%d ", - page_to_pfn(page), ret); - dump_page(page, "migration failure"); + if (__ratelimit(&migrate_rs)) { + pr_warn("migrating pfn %lx failed ret:%d\n", + page_to_pfn(page), ret); + dump_page(page, "migration failure"); + } } putback_movable_pages(&source); } @@ -1703,7 +1580,7 @@ int __ref offline_pages(unsigned long start_pfn, unsigned long nr_pages) /* * {on,off}lining is constrained to full memory sections (or more - * precisly to memory blocks from the user space POV). + * precisely to memory blocks from the user space POV). * memmap_on_memory is an exception because it reserves initial part * of the physical memory space for vmemmaps. That space is pageblock * aligned. @@ -2031,7 +1908,7 @@ static int __ref try_remove_memory(int nid, u64 start, u64 size) } /** - * remove_memory + * __remove_memory - Remove memory if every memory block is offline * @nid: the node ID * @start: physical address of the region to remove * @size: size of the region to remove diff --git a/mm/mempolicy.c b/mm/mempolicy.c index b5d95bf1025d..e32360e90274 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -121,8 +121,7 @@ enum zone_type policy_zone = 0; */ static struct mempolicy default_policy = { .refcnt = ATOMIC_INIT(1), /* never free it */ - .mode = MPOL_PREFERRED, - .flags = MPOL_F_LOCAL, + .mode = MPOL_LOCAL, }; static struct mempolicy preferred_node_policy[MAX_NUMNODES]; @@ -194,18 +193,17 @@ static int mpol_new_interleave(struct mempolicy *pol, const nodemask_t *nodes) { if (nodes_empty(*nodes)) return -EINVAL; - pol->v.nodes = *nodes; + pol->nodes = *nodes; return 0; } static int mpol_new_preferred(struct mempolicy *pol, const nodemask_t *nodes) { - if (!nodes) - pol->flags |= MPOL_F_LOCAL; /* local allocation */ - else if (nodes_empty(*nodes)) - return -EINVAL; /* no allowed nodes */ - else - pol->v.preferred_node = first_node(*nodes); + if (nodes_empty(*nodes)) + return -EINVAL; + + nodes_clear(pol->nodes); + node_set(first_node(*nodes), pol->nodes); return 0; } @@ -213,15 +211,14 @@ static int mpol_new_bind(struct mempolicy *pol, const nodemask_t *nodes) { if (nodes_empty(*nodes)) return -EINVAL; - pol->v.nodes = *nodes; + pol->nodes = *nodes; return 0; } /* * mpol_set_nodemask is called after mpol_new() to set up the nodemask, if * any, for the new policy. mpol_new() has already validated the nodes - * parameter with respect to the policy mode and flags. But, we need to - * handle an empty nodemask with MPOL_PREFERRED here. + * parameter with respect to the policy mode and flags. * * Must be called holding task's alloc_lock to protect task's mems_allowed * and mempolicy. May also be called holding the mmap_lock for write. @@ -231,33 +228,31 @@ static int mpol_set_nodemask(struct mempolicy *pol, { int ret; - /* if mode is MPOL_DEFAULT, pol is NULL. This is right. */ - if (pol == NULL) + /* + * Default (pol==NULL) resp. local memory policies are not a + * subject of any remapping. They also do not need any special + * constructor. + */ + if (!pol || pol->mode == MPOL_LOCAL) return 0; + /* Check N_MEMORY */ nodes_and(nsc->mask1, cpuset_current_mems_allowed, node_states[N_MEMORY]); VM_BUG_ON(!nodes); - if (pol->mode == MPOL_PREFERRED && nodes_empty(*nodes)) - nodes = NULL; /* explicit local allocation */ - else { - if (pol->flags & MPOL_F_RELATIVE_NODES) - mpol_relative_nodemask(&nsc->mask2, nodes, &nsc->mask1); - else - nodes_and(nsc->mask2, *nodes, nsc->mask1); - if (mpol_store_user_nodemask(pol)) - pol->w.user_nodemask = *nodes; - else - pol->w.cpuset_mems_allowed = - cpuset_current_mems_allowed; - } - - if (nodes) - ret = mpol_ops[pol->mode].create(pol, &nsc->mask2); + if (pol->flags & MPOL_F_RELATIVE_NODES) + mpol_relative_nodemask(&nsc->mask2, nodes, &nsc->mask1); else - ret = mpol_ops[pol->mode].create(pol, NULL); + nodes_and(nsc->mask2, *nodes, nsc->mask1); + + if (mpol_store_user_nodemask(pol)) + pol->w.user_nodemask = *nodes; + else + pol->w.cpuset_mems_allowed = cpuset_current_mems_allowed; + + ret = mpol_ops[pol->mode].create(pol, &nsc->mask2); return ret; } @@ -290,13 +285,14 @@ static struct mempolicy *mpol_new(unsigned short mode, unsigned short flags, if (((flags & MPOL_F_STATIC_NODES) || (flags & MPOL_F_RELATIVE_NODES))) return ERR_PTR(-EINVAL); + + mode = MPOL_LOCAL; } } else if (mode == MPOL_LOCAL) { if (!nodes_empty(*nodes) || (flags & MPOL_F_STATIC_NODES) || (flags & MPOL_F_RELATIVE_NODES)) return ERR_PTR(-EINVAL); - mode = MPOL_PREFERRED; } else if (nodes_empty(*nodes)) return ERR_PTR(-EINVAL); policy = kmem_cache_alloc(policy_cache, GFP_KERNEL); @@ -330,7 +326,7 @@ static void mpol_rebind_nodemask(struct mempolicy *pol, const nodemask_t *nodes) else if (pol->flags & MPOL_F_RELATIVE_NODES) mpol_relative_nodemask(&tmp, &pol->w.user_nodemask, nodes); else { - nodes_remap(tmp, pol->v.nodes, pol->w.cpuset_mems_allowed, + nodes_remap(tmp, pol->nodes, pol->w.cpuset_mems_allowed, *nodes); pol->w.cpuset_mems_allowed = *nodes; } @@ -338,31 +334,13 @@ static void mpol_rebind_nodemask(struct mempolicy *pol, const nodemask_t *nodes) if (nodes_empty(tmp)) tmp = *nodes; - pol->v.nodes = tmp; + pol->nodes = tmp; } static void mpol_rebind_preferred(struct mempolicy *pol, const nodemask_t *nodes) { - nodemask_t tmp; - - if (pol->flags & MPOL_F_STATIC_NODES) { - int node = first_node(pol->w.user_nodemask); - - if (node_isset(node, *nodes)) { - pol->v.preferred_node = node; - pol->flags &= ~MPOL_F_LOCAL; - } else - pol->flags |= MPOL_F_LOCAL; - } else if (pol->flags & MPOL_F_RELATIVE_NODES) { - mpol_relative_nodemask(&tmp, &pol->w.user_nodemask, nodes); - pol->v.preferred_node = first_node(tmp); - } else if (!(pol->flags & MPOL_F_LOCAL)) { - pol->v.preferred_node = node_remap(pol->v.preferred_node, - pol->w.cpuset_mems_allowed, - *nodes); - pol->w.cpuset_mems_allowed = *nodes; - } + pol->w.cpuset_mems_allowed = *nodes; } /* @@ -376,7 +354,7 @@ static void mpol_rebind_policy(struct mempolicy *pol, const nodemask_t *newmask) { if (!pol) return; - if (!mpol_store_user_nodemask(pol) && !(pol->flags & MPOL_F_LOCAL) && + if (!mpol_store_user_nodemask(pol) && nodes_equal(pol->w.cpuset_mems_allowed, *newmask)) return; @@ -427,6 +405,9 @@ static const struct mempolicy_operations mpol_ops[MPOL_MAX] = { .create = mpol_new_bind, .rebind = mpol_rebind_nodemask, }, + [MPOL_LOCAL] = { + .rebind = mpol_rebind_default, + }, }; static int migrate_page_add(struct page *page, struct list_head *pagelist, @@ -458,7 +439,8 @@ static inline bool queue_pages_required(struct page *page, /* * queue_pages_pmd() has four possible return values: - * 0 - pages are placed on the right node or queued successfully. + * 0 - pages are placed on the right node or queued successfully, or + * special page is met, i.e. huge zero page. * 1 - there is unmovable page, and MPOL_MF_MOVE* & MPOL_MF_STRICT were * specified. * 2 - THP was split. @@ -482,8 +464,7 @@ static int queue_pages_pmd(pmd_t *pmd, spinlock_t *ptl, unsigned long addr, page = pmd_page(*pmd); if (is_huge_zero_page(page)) { spin_unlock(ptl); - __split_huge_pmd(walk->vma, pmd, addr, false, NULL); - ret = 2; + walk->action = ACTION_CONTINUE; goto out; } if (!queue_pages_required(page, qp)) @@ -510,7 +491,8 @@ static int queue_pages_pmd(pmd_t *pmd, spinlock_t *ptl, unsigned long addr, * and move them to the pagelist if they do. * * queue_pages_pte_range() has three possible return values: - * 0 - pages are placed on the right node or queued successfully. + * 0 - pages are placed on the right node or queued successfully, or + * special page is met, i.e. zero page. * 1 - there is unmovable page, and MPOL_MF_MOVE* & MPOL_MF_STRICT were * specified. * -EIO - only MPOL_MF_STRICT was specified and an existing page was already @@ -917,12 +899,11 @@ static void get_policy_nodemask(struct mempolicy *p, nodemask_t *nodes) switch (p->mode) { case MPOL_BIND: case MPOL_INTERLEAVE: - *nodes = p->v.nodes; - break; case MPOL_PREFERRED: - if (!(p->flags & MPOL_F_LOCAL)) - node_set(p->v.preferred_node, *nodes); - /* else return empty node mask for local allocation */ + *nodes = p->nodes; + break; + case MPOL_LOCAL: + /* return empty node mask for local allocation */ break; default: BUG(); @@ -1007,7 +988,7 @@ static long do_get_mempolicy(int *policy, nodemask_t *nmask, *policy = err; } else if (pol == current->mempolicy && pol->mode == MPOL_INTERLEAVE) { - *policy = next_node_in(current->il_prev, pol->v.nodes); + *policy = next_node_in(current->il_prev, pol->nodes); } else { err = -EINVAL; goto out; @@ -1460,26 +1441,38 @@ static int copy_nodes_to_user(unsigned long __user *mask, unsigned long maxnode, return copy_to_user(mask, nodes_addr(*nodes), copy) ? -EFAULT : 0; } +/* Basic parameter sanity check used by both mbind() and set_mempolicy() */ +static inline int sanitize_mpol_flags(int *mode, unsigned short *flags) +{ + *flags = *mode & MPOL_MODE_FLAGS; + *mode &= ~MPOL_MODE_FLAGS; + if ((unsigned int)(*mode) >= MPOL_MAX) + return -EINVAL; + if ((*flags & MPOL_F_STATIC_NODES) && (*flags & MPOL_F_RELATIVE_NODES)) + return -EINVAL; + + return 0; +} + static long kernel_mbind(unsigned long start, unsigned long len, unsigned long mode, const unsigned long __user *nmask, unsigned long maxnode, unsigned int flags) { - nodemask_t nodes; - int err; unsigned short mode_flags; + nodemask_t nodes; + int lmode = mode; + int err; start = untagged_addr(start); - mode_flags = mode & MPOL_MODE_FLAGS; - mode &= ~MPOL_MODE_FLAGS; - if (mode >= MPOL_MAX) - return -EINVAL; - if ((mode_flags & MPOL_F_STATIC_NODES) && - (mode_flags & MPOL_F_RELATIVE_NODES)) - return -EINVAL; + err = sanitize_mpol_flags(&lmode, &mode_flags); + if (err) + return err; + err = get_nodes(&nodes, nmask, maxnode); if (err) return err; - return do_mbind(start, len, mode, mode_flags, &nodes, flags); + + return do_mbind(start, len, lmode, mode_flags, &nodes, flags); } SYSCALL_DEFINE6(mbind, unsigned long, start, unsigned long, len, @@ -1493,20 +1486,20 @@ SYSCALL_DEFINE6(mbind, unsigned long, start, unsigned long, len, static long kernel_set_mempolicy(int mode, const unsigned long __user *nmask, unsigned long maxnode) { - int err; + unsigned short mode_flags; nodemask_t nodes; - unsigned short flags; + int lmode = mode; + int err; + + err = sanitize_mpol_flags(&lmode, &mode_flags); + if (err) + return err; - flags = mode & MPOL_MODE_FLAGS; - mode &= ~MPOL_MODE_FLAGS; - if ((unsigned int)mode >= MPOL_MAX) - return -EINVAL; - if ((flags & MPOL_F_STATIC_NODES) && (flags & MPOL_F_RELATIVE_NODES)) - return -EINVAL; err = get_nodes(&nodes, nmask, maxnode); if (err) return err; - return do_set_mempolicy(mode, flags, &nodes); + + return do_set_mempolicy(lmode, mode_flags, &nodes); } SYSCALL_DEFINE3(set_mempolicy, int, mode, const unsigned long __user *, nmask, @@ -1863,14 +1856,14 @@ static int apply_policy_zone(struct mempolicy *policy, enum zone_type zone) BUG_ON(dynamic_policy_zone == ZONE_MOVABLE); /* - * if policy->v.nodes has movable memory only, + * if policy->nodes has movable memory only, * we apply policy when gfp_zone(gfp) = ZONE_MOVABLE only. * - * policy->v.nodes is intersect with node_states[N_MEMORY]. + * policy->nodes is intersect with node_states[N_MEMORY]. * so if the following test fails, it implies - * policy->v.nodes has movable memory only. + * policy->nodes has movable memory only. */ - if (!nodes_intersects(policy->v.nodes, node_states[N_HIGH_MEMORY])) + if (!nodes_intersects(policy->nodes, node_states[N_HIGH_MEMORY])) dynamic_policy_zone = ZONE_MOVABLE; return zone >= dynamic_policy_zone; @@ -1885,8 +1878,8 @@ nodemask_t *policy_nodemask(gfp_t gfp, struct mempolicy *policy) /* Lower zones don't get a nodemask applied for MPOL_BIND */ if (unlikely(policy->mode == MPOL_BIND) && apply_policy_zone(policy, gfp_zone(gfp)) && - cpuset_nodemask_valid_mems_allowed(&policy->v.nodes)) - return &policy->v.nodes; + cpuset_nodemask_valid_mems_allowed(&policy->nodes)) + return &policy->nodes; return NULL; } @@ -1894,9 +1887,9 @@ nodemask_t *policy_nodemask(gfp_t gfp, struct mempolicy *policy) /* Return the node id preferred by the given mempolicy, or the given id */ static int policy_node(gfp_t gfp, struct mempolicy *policy, int nd) { - if (policy->mode == MPOL_PREFERRED && !(policy->flags & MPOL_F_LOCAL)) - nd = policy->v.preferred_node; - else { + if (policy->mode == MPOL_PREFERRED) { + nd = first_node(policy->nodes); + } else { /* * __GFP_THISNODE shouldn't even be used with the bind policy * because we might easily break the expectation to stay on the @@ -1914,7 +1907,7 @@ static unsigned interleave_nodes(struct mempolicy *policy) unsigned next; struct task_struct *me = current; - next = next_node_in(me->il_prev, policy->v.nodes); + next = next_node_in(me->il_prev, policy->nodes); if (next < MAX_NUMNODES) me->il_prev = next; return next; @@ -1933,15 +1926,12 @@ unsigned int mempolicy_slab_node(void) return node; policy = current->mempolicy; - if (!policy || policy->flags & MPOL_F_LOCAL) + if (!policy) return node; switch (policy->mode) { case MPOL_PREFERRED: - /* - * handled MPOL_F_LOCAL above - */ - return policy->v.preferred_node; + return first_node(policy->nodes); case MPOL_INTERLEAVE: return interleave_nodes(policy); @@ -1957,9 +1947,11 @@ unsigned int mempolicy_slab_node(void) enum zone_type highest_zoneidx = gfp_zone(GFP_KERNEL); zonelist = &NODE_DATA(node)->node_zonelists[ZONELIST_FALLBACK]; z = first_zones_zonelist(zonelist, highest_zoneidx, - &policy->v.nodes); + &policy->nodes); return z->zone ? zone_to_nid(z->zone) : node; } + case MPOL_LOCAL: + return node; default: BUG(); @@ -1968,12 +1960,12 @@ unsigned int mempolicy_slab_node(void) /* * Do static interleaving for a VMA with known offset @n. Returns the n'th - * node in pol->v.nodes (starting from n=0), wrapping around if n exceeds the + * node in pol->nodes (starting from n=0), wrapping around if n exceeds the * number of present nodes. */ static unsigned offset_il_node(struct mempolicy *pol, unsigned long n) { - unsigned nnodes = nodes_weight(pol->v.nodes); + unsigned nnodes = nodes_weight(pol->nodes); unsigned target; int i; int nid; @@ -1981,9 +1973,9 @@ static unsigned offset_il_node(struct mempolicy *pol, unsigned long n) if (!nnodes) return numa_node_id(); target = (unsigned int)n % nnodes; - nid = first_node(pol->v.nodes); + nid = first_node(pol->nodes); for (i = 0; i < target; i++) - nid = next_node(nid, pol->v.nodes); + nid = next_node(nid, pol->nodes); return nid; } @@ -2039,7 +2031,7 @@ int huge_node(struct vm_area_struct *vma, unsigned long addr, gfp_t gfp_flags, } else { nid = policy_node(gfp_flags, *mpol, numa_node_id()); if ((*mpol)->mode == MPOL_BIND) - *nodemask = &(*mpol)->v.nodes; + *nodemask = &(*mpol)->nodes; } return nid; } @@ -2063,7 +2055,6 @@ int huge_node(struct vm_area_struct *vma, unsigned long addr, gfp_t gfp_flags, bool init_nodemask_of_mempolicy(nodemask_t *mask) { struct mempolicy *mempolicy; - int nid; if (!(mask && current->mempolicy)) return false; @@ -2072,16 +2063,13 @@ bool init_nodemask_of_mempolicy(nodemask_t *mask) mempolicy = current->mempolicy; switch (mempolicy->mode) { case MPOL_PREFERRED: - if (mempolicy->flags & MPOL_F_LOCAL) - nid = numa_node_id(); - else - nid = mempolicy->v.preferred_node; - init_nodemask_of_node(mask, nid); - break; - case MPOL_BIND: case MPOL_INTERLEAVE: - *mask = mempolicy->v.nodes; + *mask = mempolicy->nodes; + break; + + case MPOL_LOCAL: + init_nodemask_of_node(mask, numa_node_id()); break; default: @@ -2094,16 +2082,16 @@ bool init_nodemask_of_mempolicy(nodemask_t *mask) #endif /* - * mempolicy_nodemask_intersects + * mempolicy_in_oom_domain * - * If tsk's mempolicy is "default" [NULL], return 'true' to indicate default - * policy. Otherwise, check for intersection between mask and the policy - * nodemask for 'bind' or 'interleave' policy. For 'preferred' or 'local' - * policy, always return true since it may allocate elsewhere on fallback. + * If tsk's mempolicy is "bind", check for intersection between mask and + * the policy nodemask. Otherwise, return true for all other policies + * including "interleave", as a tsk with "interleave" policy may have + * memory allocated from all nodes in system. * * Takes task_lock(tsk) to prevent freeing of its mempolicy. */ -bool mempolicy_nodemask_intersects(struct task_struct *tsk, +bool mempolicy_in_oom_domain(struct task_struct *tsk, const nodemask_t *mask) { struct mempolicy *mempolicy; @@ -2111,29 +2099,13 @@ bool mempolicy_nodemask_intersects(struct task_struct *tsk, if (!mask) return ret; + task_lock(tsk); mempolicy = tsk->mempolicy; - if (!mempolicy) - goto out; - - switch (mempolicy->mode) { - case MPOL_PREFERRED: - /* - * MPOL_PREFERRED and MPOL_F_LOCAL are only preferred nodes to - * allocate from, they may fallback to other nodes when oom. - * Thus, it's possible for tsk to have allocated memory from - * nodes in mask. - */ - break; - case MPOL_BIND: - case MPOL_INTERLEAVE: - ret = nodes_intersects(mempolicy->v.nodes, *mask); - break; - default: - BUG(); - } -out: + if (mempolicy && mempolicy->mode == MPOL_BIND) + ret = nodes_intersects(mempolicy->nodes, *mask); task_unlock(tsk); + return ret; } @@ -2204,8 +2176,8 @@ struct page *alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma, * If the policy is interleave, or does not allow the current * node in its nodemask, we allocate the standard way. */ - if (pol->mode == MPOL_PREFERRED && !(pol->flags & MPOL_F_LOCAL)) - hpage_node = pol->v.preferred_node; + if (pol->mode == MPOL_PREFERRED) + hpage_node = first_node(pol->nodes); nmask = policy_nodemask(gfp, pol); if (!nmask || node_isset(hpage_node, *nmask)) { @@ -2338,12 +2310,10 @@ bool __mpol_equal(struct mempolicy *a, struct mempolicy *b) switch (a->mode) { case MPOL_BIND: case MPOL_INTERLEAVE: - return !!nodes_equal(a->v.nodes, b->v.nodes); case MPOL_PREFERRED: - /* a's ->flags is the same as b's */ - if (a->flags & MPOL_F_LOCAL) - return true; - return a->v.preferred_node == b->v.preferred_node; + return !!nodes_equal(a->nodes, b->nodes); + case MPOL_LOCAL: + return true; default: BUG(); return false; @@ -2481,16 +2451,17 @@ int mpol_misplaced(struct page *page, struct vm_area_struct *vma, unsigned long break; case MPOL_PREFERRED: - if (pol->flags & MPOL_F_LOCAL) - polnid = numa_node_id(); - else - polnid = pol->v.preferred_node; + polnid = first_node(pol->nodes); + break; + + case MPOL_LOCAL: + polnid = numa_node_id(); break; case MPOL_BIND: /* Optimize placement among multiple nodes via NUMA balancing */ if (pol->flags & MPOL_F_MORON) { - if (node_isset(thisnid, pol->v.nodes)) + if (node_isset(thisnid, pol->nodes)) break; goto out; } @@ -2501,12 +2472,12 @@ int mpol_misplaced(struct page *page, struct vm_area_struct *vma, unsigned long * else select nearest allowed node, if any. * If no allowed nodes, use current [!misplaced]. */ - if (node_isset(curnid, pol->v.nodes)) + if (node_isset(curnid, pol->nodes)) goto out; z = first_zones_zonelist( node_zonelist(numa_node_id(), GFP_HIGHUSER), gfp_zone(GFP_HIGHUSER), - &pol->v.nodes); + &pol->nodes); polnid = zone_to_nid(z->zone); break; @@ -2709,7 +2680,7 @@ int mpol_set_shared_policy(struct shared_policy *info, vma->vm_pgoff, sz, npol ? npol->mode : -1, npol ? npol->flags : -1, - npol ? nodes_addr(npol->v.nodes)[0] : NUMA_NO_NODE); + npol ? nodes_addr(npol->nodes)[0] : NUMA_NO_NODE); if (npol) { new = sp_alloc(vma->vm_pgoff, vma->vm_pgoff + sz, npol); @@ -2807,7 +2778,7 @@ void __init numa_policy_init(void) .refcnt = ATOMIC_INIT(1), .mode = MPOL_PREFERRED, .flags = MPOL_F_MOF | MPOL_F_MORON, - .v = { .preferred_node = nid, }, + .nodes = nodemask_of_node(nid), }; } @@ -2851,9 +2822,6 @@ void numa_default_policy(void) * Parse and format mempolicy from/to strings */ -/* - * "local" is implemented internally by MPOL_PREFERRED with MPOL_F_LOCAL flag. - */ static const char * const policy_modes[] = { [MPOL_DEFAULT] = "default", @@ -2931,7 +2899,6 @@ int mpol_parse_str(char *str, struct mempolicy **mpol) */ if (nodelist) goto out; - mode = MPOL_PREFERRED; break; case MPOL_DEFAULT: /* @@ -2970,12 +2937,14 @@ int mpol_parse_str(char *str, struct mempolicy **mpol) * Save nodes for mpol_to_str() to show the tmpfs mount options * for /proc/mounts, /proc/pid/mounts and /proc/pid/mountinfo. */ - if (mode != MPOL_PREFERRED) - new->v.nodes = nodes; - else if (nodelist) - new->v.preferred_node = first_node(nodes); - else - new->flags |= MPOL_F_LOCAL; + if (mode != MPOL_PREFERRED) { + new->nodes = nodes; + } else if (nodelist) { + nodes_clear(new->nodes); + node_set(first_node(nodes), new->nodes); + } else { + new->mode = MPOL_LOCAL; + } /* * Save nodes for contextualization: this will be used to "clone" @@ -3021,16 +2990,12 @@ void mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol) switch (mode) { case MPOL_DEFAULT: + case MPOL_LOCAL: break; case MPOL_PREFERRED: - if (flags & MPOL_F_LOCAL) - mode = MPOL_LOCAL; - else - node_set(pol->v.preferred_node, nodes); - break; case MPOL_BIND: case MPOL_INTERLEAVE: - nodes = pol->v.nodes; + nodes = pol->nodes; break; default: WARN_ON_ONCE(1); diff --git a/mm/migrate.c b/mm/migrate.c index 380ca57b9031..23cbd9de030b 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -210,13 +210,18 @@ static bool remove_migration_pte(struct page *page, struct vm_area_struct *vma, * Recheck VMA as permissions can change since migration started */ entry = pte_to_swp_entry(*pvmw.pte); - if (is_write_migration_entry(entry)) + if (is_writable_migration_entry(entry)) pte = maybe_mkwrite(pte, vma); else if (pte_swp_uffd_wp(*pvmw.pte)) pte = pte_mkuffd_wp(pte); if (unlikely(is_device_private_page(new))) { - entry = make_device_private_entry(new, pte_write(pte)); + if (pte_write(pte)) + entry = make_writable_device_private_entry( + page_to_pfn(new)); + else + entry = make_readable_device_private_entry( + page_to_pfn(new)); pte = swp_entry_to_pte(entry); if (pte_swp_soft_dirty(*pvmw.pte)) pte = pte_swp_mksoft_dirty(pte); @@ -226,8 +231,10 @@ static bool remove_migration_pte(struct page *page, struct vm_area_struct *vma, #ifdef CONFIG_HUGETLB_PAGE if (PageHuge(new)) { + unsigned int shift = huge_page_shift(hstate_vma(vma)); + pte = pte_mkhuge(pte); - pte = arch_make_huge_pte(pte, vma, new, 0); + pte = arch_make_huge_pte(pte, shift, vma->vm_flags); set_huge_pte_at(vma->vm_mm, pvmw.address, pvmw.pte, pte); if (PageAnon(new)) hugepage_add_anon_rmap(new, vma, pvmw.address); @@ -294,7 +301,7 @@ void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep, if (!is_migration_entry(entry)) goto out; - page = migration_entry_to_page(entry); + page = pfn_swap_entry_to_page(entry); page = compound_head(page); /* @@ -335,7 +342,7 @@ void pmd_migration_entry_wait(struct mm_struct *mm, pmd_t *pmd) ptl = pmd_lock(mm, pmd); if (!is_pmd_migration_entry(*pmd)) goto unlock; - page = migration_entry_to_page(pmd_to_swp_entry(*pmd)); + page = pfn_swap_entry_to_page(pmd_to_swp_entry(*pmd)); if (!get_page_unless_zero(page)) goto unlock; spin_unlock(ptl); @@ -551,7 +558,7 @@ static void __copy_gigantic_page(struct page *dst, struct page *src, } } -static void copy_huge_page(struct page *dst, struct page *src) +void copy_huge_page(struct page *dst, struct page *src) { int i; int nr_pages; @@ -626,7 +633,10 @@ void migrate_page_states(struct page *newpage, struct page *page) if (PageSwapCache(page)) ClearPageSwapCache(page); ClearPagePrivate(page); - set_page_private(page, 0); + + /* page->private contains hugetlb specific flags */ + if (!PageHuge(page)) + set_page_private(page, 0); /* * If any waiters have accumulated on the new page then @@ -1099,7 +1109,7 @@ static int __unmap_and_move(struct page *page, struct page *newpage, /* Establish migration ptes */ VM_BUG_ON_PAGE(PageAnon(page) && !PageKsm(page) && !anon_vma, page); - try_to_unmap(page, TTU_MIGRATION|TTU_IGNORE_MLOCK); + try_to_migrate(page, 0); page_was_mapped = 1; } @@ -1288,7 +1298,7 @@ static int unmap_and_move_huge_page(new_page_t get_new_page, * page_mapping() set, hugetlbfs specific move page routine will not * be called and we could leak usage counts for subpools. */ - if (page_private(hpage) && !page_mapping(hpage)) { + if (hugetlb_page_subpool(hpage) && !page_mapping(hpage)) { rc = -EBUSY; goto out_unlock; } @@ -1301,7 +1311,7 @@ static int unmap_and_move_huge_page(new_page_t get_new_page, if (page_mapped(hpage)) { bool mapping_locked = false; - enum ttu_flags ttu = TTU_MIGRATION|TTU_IGNORE_MLOCK; + enum ttu_flags ttu = 0; if (!PageAnon(hpage)) { /* @@ -1318,7 +1328,7 @@ static int unmap_and_move_huge_page(new_page_t get_new_page, ttu |= TTU_RMAP_LOCKED; } - try_to_unmap(hpage, ttu); + try_to_migrate(hpage, ttu); page_was_mapped = 1; if (mapping_locked) @@ -1418,6 +1428,7 @@ int migrate_pages(struct list_head *from, new_page_t get_new_page, int swapwrite = current->flags & PF_SWAPWRITE; int rc, nr_subpages; LIST_HEAD(ret_pages); + bool nosplit = (reason == MR_NUMA_MISPLACED); trace_mm_migrate_pages_start(mode, reason); @@ -1489,8 +1500,9 @@ int migrate_pages(struct list_head *from, new_page_t get_new_page, /* * When memory is low, don't bother to try to migrate * other pages, just exit. + * THP NUMA faulting doesn't split THP to retry. */ - if (is_thp) { + if (is_thp && !nosplit) { if (!try_split_thp(page, &page2, from)) { nr_thp_split++; goto retry; @@ -2043,12 +2055,33 @@ static struct page *alloc_misplaced_dst_page(struct page *page, return newpage; } +static struct page *alloc_misplaced_dst_page_thp(struct page *page, + unsigned long data) +{ + int nid = (int) data; + struct page *newpage; + + newpage = alloc_pages_node(nid, (GFP_TRANSHUGE_LIGHT | __GFP_THISNODE), + HPAGE_PMD_ORDER); + if (!newpage) + goto out; + + prep_transhuge_page(newpage); + +out: + return newpage; +} + static int numamigrate_isolate_page(pg_data_t *pgdat, struct page *page) { int page_lru; VM_BUG_ON_PAGE(compound_order(page) && !PageTransHuge(page), page); + /* Do not migrate THP mapped by multiple processes */ + if (PageTransHuge(page) && total_mapcount(page) > 1) + return 0; + /* Avoid migrating to a node that is nearly full */ if (!migrate_balanced_pgdat(pgdat, compound_nr(page))) return 0; @@ -2056,18 +2089,6 @@ static int numamigrate_isolate_page(pg_data_t *pgdat, struct page *page) if (isolate_lru_page(page)) return 0; - /* - * migrate_misplaced_transhuge_page() skips page migration's usual - * check on page_count(), so we must do it here, now that the page - * has been isolated: a GUP pin, or any other pin, prevents migration. - * The expected page count is 3: 1 for page's mapcount and 1 for the - * caller's pin and 1 for the reference taken by isolate_lru_page(). - */ - if (PageTransHuge(page) && page_count(page) != 3) { - putback_lru_page(page); - return 0; - } - page_lru = page_is_file_lru(page); mod_node_page_state(page_pgdat(page), NR_ISOLATED_ANON + page_lru, thp_nr_pages(page)); @@ -2081,12 +2102,6 @@ static int numamigrate_isolate_page(pg_data_t *pgdat, struct page *page) return 1; } -bool pmd_trans_migrating(pmd_t pmd) -{ - struct page *page = pmd_page(pmd); - return PageLocked(page); -} - /* * Attempt to migrate a misplaced page to the specified destination * node. Caller is expected to have an elevated reference count on @@ -2099,6 +2114,21 @@ int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma, int isolated; int nr_remaining; LIST_HEAD(migratepages); + new_page_t *new; + bool compound; + unsigned int nr_pages = thp_nr_pages(page); + + /* + * PTE mapped THP or HugeTLB page can't reach here so the page could + * be either base page or THP. And it must be head page if it is + * THP. + */ + compound = PageTransHuge(page); + + if (compound) + new = alloc_misplaced_dst_page_thp; + else + new = alloc_misplaced_dst_page; /* * Don't migrate file pages that are mapped in multiple processes @@ -2120,19 +2150,18 @@ int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma, goto out; list_add(&page->lru, &migratepages); - nr_remaining = migrate_pages(&migratepages, alloc_misplaced_dst_page, - NULL, node, MIGRATE_ASYNC, - MR_NUMA_MISPLACED); + nr_remaining = migrate_pages(&migratepages, *new, NULL, node, + MIGRATE_ASYNC, MR_NUMA_MISPLACED); if (nr_remaining) { if (!list_empty(&migratepages)) { list_del(&page->lru); - dec_node_page_state(page, NR_ISOLATED_ANON + - page_is_file_lru(page)); + mod_node_page_state(page_pgdat(page), NR_ISOLATED_ANON + + page_is_file_lru(page), -nr_pages); putback_lru_page(page); } isolated = 0; } else - count_vm_numa_event(NUMA_PAGE_MIGRATE); + count_vm_numa_events(NUMA_PAGE_MIGRATE, nr_pages); BUG_ON(!list_empty(&migratepages)); return isolated; @@ -2141,141 +2170,6 @@ int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma, return 0; } #endif /* CONFIG_NUMA_BALANCING */ - -#if defined(CONFIG_NUMA_BALANCING) && defined(CONFIG_TRANSPARENT_HUGEPAGE) -/* - * Migrates a THP to a given target node. page must be locked and is unlocked - * before returning. - */ -int migrate_misplaced_transhuge_page(struct mm_struct *mm, - struct vm_area_struct *vma, - pmd_t *pmd, pmd_t entry, - unsigned long address, - struct page *page, int node) -{ - spinlock_t *ptl; - pg_data_t *pgdat = NODE_DATA(node); - int isolated = 0; - struct page *new_page = NULL; - int page_lru = page_is_file_lru(page); - unsigned long start = address & HPAGE_PMD_MASK; - - new_page = alloc_pages_node(node, - (GFP_TRANSHUGE_LIGHT | __GFP_THISNODE), - HPAGE_PMD_ORDER); - if (!new_page) - goto out_fail; - prep_transhuge_page(new_page); - - isolated = numamigrate_isolate_page(pgdat, page); - if (!isolated) { - put_page(new_page); - goto out_fail; - } - - /* Prepare a page as a migration target */ - __SetPageLocked(new_page); - if (PageSwapBacked(page)) - __SetPageSwapBacked(new_page); - - /* anon mapping, we can simply copy page->mapping to the new page: */ - new_page->mapping = page->mapping; - new_page->index = page->index; - /* flush the cache before copying using the kernel virtual address */ - flush_cache_range(vma, start, start + HPAGE_PMD_SIZE); - migrate_page_copy(new_page, page); - WARN_ON(PageLRU(new_page)); - - /* Recheck the target PMD */ - ptl = pmd_lock(mm, pmd); - if (unlikely(!pmd_same(*pmd, entry) || !page_ref_freeze(page, 2))) { - spin_unlock(ptl); - - /* Reverse changes made by migrate_page_copy() */ - if (TestClearPageActive(new_page)) - SetPageActive(page); - if (TestClearPageUnevictable(new_page)) - SetPageUnevictable(page); - - unlock_page(new_page); - put_page(new_page); /* Free it */ - - /* Retake the callers reference and putback on LRU */ - get_page(page); - putback_lru_page(page); - mod_node_page_state(page_pgdat(page), - NR_ISOLATED_ANON + page_lru, -HPAGE_PMD_NR); - - goto out_unlock; - } - - entry = mk_huge_pmd(new_page, vma->vm_page_prot); - entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); - - /* - * Overwrite the old entry under pagetable lock and establish - * the new PTE. Any parallel GUP will either observe the old - * page blocking on the page lock, block on the page table - * lock or observe the new page. The SetPageUptodate on the - * new page and page_add_new_anon_rmap guarantee the copy is - * visible before the pagetable update. - */ - page_add_anon_rmap(new_page, vma, start, true); - /* - * At this point the pmd is numa/protnone (i.e. non present) and the TLB - * has already been flushed globally. So no TLB can be currently - * caching this non present pmd mapping. There's no need to clear the - * pmd before doing set_pmd_at(), nor to flush the TLB after - * set_pmd_at(). Clearing the pmd here would introduce a race - * condition against MADV_DONTNEED, because MADV_DONTNEED only holds the - * mmap_lock for reading. If the pmd is set to NULL at any given time, - * MADV_DONTNEED won't wait on the pmd lock and it'll skip clearing this - * pmd. - */ - set_pmd_at(mm, start, pmd, entry); - update_mmu_cache_pmd(vma, address, &entry); - - page_ref_unfreeze(page, 2); - mlock_migrate_page(new_page, page); - page_remove_rmap(page, true); - set_page_owner_migrate_reason(new_page, MR_NUMA_MISPLACED); - - spin_unlock(ptl); - - /* Take an "isolate" reference and put new page on the LRU. */ - get_page(new_page); - putback_lru_page(new_page); - - unlock_page(new_page); - unlock_page(page); - put_page(page); /* Drop the rmap reference */ - put_page(page); /* Drop the LRU isolation reference */ - - count_vm_events(PGMIGRATE_SUCCESS, HPAGE_PMD_NR); - count_vm_numa_events(NUMA_PAGE_MIGRATE, HPAGE_PMD_NR); - - mod_node_page_state(page_pgdat(page), - NR_ISOLATED_ANON + page_lru, - -HPAGE_PMD_NR); - return isolated; - -out_fail: - count_vm_events(PGMIGRATE_FAIL, HPAGE_PMD_NR); - ptl = pmd_lock(mm, pmd); - if (pmd_same(*pmd, entry)) { - entry = pmd_modify(entry, vma->vm_page_prot); - set_pmd_at(mm, start, pmd, entry); - update_mmu_cache_pmd(vma, address, &entry); - } - spin_unlock(ptl); - -out_unlock: - unlock_page(page); - put_page(page); - return 0; -} -#endif /* CONFIG_NUMA_BALANCING */ - #endif /* CONFIG_NUMA */ #ifdef CONFIG_DEVICE_PRIVATE @@ -2400,7 +2294,7 @@ static int migrate_vma_collect_pmd(pmd_t *pmdp, if (!is_device_private_entry(entry)) goto next; - page = device_private_entry_to_page(entry); + page = pfn_swap_entry_to_page(entry); if (!(migrate->flags & MIGRATE_VMA_SELECT_DEVICE_PRIVATE) || page->pgmap->owner != migrate->pgmap_owner) @@ -2408,7 +2302,7 @@ static int migrate_vma_collect_pmd(pmd_t *pmdp, mpfn = migrate_pfn(page_to_pfn(page)) | MIGRATE_PFN_MIGRATE; - if (is_write_device_private_entry(entry)) + if (is_writable_device_private_entry(entry)) mpfn |= MIGRATE_PFN_WRITE; } else { if (!(migrate->flags & MIGRATE_VMA_SELECT_SYSTEM)) @@ -2454,8 +2348,12 @@ static int migrate_vma_collect_pmd(pmd_t *pmdp, ptep_get_and_clear(mm, addr, ptep); /* Setup special migration page table entry */ - entry = make_migration_entry(page, mpfn & - MIGRATE_PFN_WRITE); + if (mpfn & MIGRATE_PFN_WRITE) + entry = make_writable_migration_entry( + page_to_pfn(page)); + else + entry = make_readable_migration_entry( + page_to_pfn(page)); swp_pte = swp_entry_to_pte(entry); if (pte_present(pte)) { if (pte_soft_dirty(pte)) @@ -2518,8 +2416,8 @@ static void migrate_vma_collect(struct migrate_vma *migrate) * that the registered device driver can skip invalidating device * private page mappings that won't be migrated. */ - mmu_notifier_range_init_migrate(&range, 0, migrate->vma, - migrate->vma->vm_mm, migrate->start, migrate->end, + mmu_notifier_range_init_owner(&range, MMU_NOTIFY_MIGRATE, 0, + migrate->vma, migrate->vma->vm_mm, migrate->start, migrate->end, migrate->pgmap_owner); mmu_notifier_invalidate_range_start(&range); @@ -2704,7 +2602,6 @@ static void migrate_vma_prepare(struct migrate_vma *migrate) */ static void migrate_vma_unmap(struct migrate_vma *migrate) { - int flags = TTU_MIGRATION | TTU_IGNORE_MLOCK; const unsigned long npages = migrate->npages; const unsigned long start = migrate->start; unsigned long addr, i, restore = 0; @@ -2716,7 +2613,7 @@ static void migrate_vma_unmap(struct migrate_vma *migrate) continue; if (page_mapped(page)) { - try_to_unmap(page, flags); + try_to_migrate(page, 0); if (page_mapped(page)) goto restore; } @@ -2928,7 +2825,12 @@ static void migrate_vma_insert_page(struct migrate_vma *migrate, if (is_device_private_page(page)) { swp_entry_t swp_entry; - swp_entry = make_device_private_entry(page, vma->vm_flags & VM_WRITE); + if (vma->vm_flags & VM_WRITE) + swp_entry = make_writable_device_private_entry( + page_to_pfn(page)); + else + swp_entry = make_readable_device_private_entry( + page_to_pfn(page)); entry = swp_entry_to_pte(swp_entry); } else { /* @@ -3025,9 +2927,9 @@ void migrate_vma_pages(struct migrate_vma *migrate) if (!notified) { notified = true; - mmu_notifier_range_init_migrate(&range, 0, - migrate->vma, migrate->vma->vm_mm, - addr, migrate->end, + mmu_notifier_range_init_owner(&range, + MMU_NOTIFY_MIGRATE, 0, migrate->vma, + migrate->vma->vm_mm, addr, migrate->end, migrate->pgmap_owner); mmu_notifier_invalidate_range_start(&range); } diff --git a/mm/mlock.c b/mm/mlock.c index e338ebc4ad29..0d639bf48794 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -108,7 +108,7 @@ void mlock_vma_page(struct page *page) /* * Finish munlock after successful page isolation * - * Page must be locked. This is a wrapper for try_to_munlock() + * Page must be locked. This is a wrapper for page_mlock() * and putback_lru_page() with munlock accounting. */ static void __munlock_isolated_page(struct page *page) @@ -118,7 +118,7 @@ static void __munlock_isolated_page(struct page *page) * and we don't need to check all the other vmas. */ if (page_mapcount(page) > 1) - try_to_munlock(page); + page_mlock(page); /* Did try_to_unlock() succeed or punt? */ if (!PageMlocked(page)) @@ -158,7 +158,7 @@ static void __munlock_isolation_failed(struct page *page) * munlock()ed or munmap()ed, we want to check whether other vmas hold the * page locked so that we can leave it on the unevictable lru list and not * bother vmscan with it. However, to walk the page's rmap list in - * try_to_munlock() we must isolate the page from the LRU. If some other + * page_mlock() we must isolate the page from the LRU. If some other * task has removed the page from the LRU, we won't be able to do that. * So we clear the PageMlocked as we might not get another chance. If we * can't isolate the page, we leave it for putback_lru_page() and vmscan @@ -168,7 +168,7 @@ unsigned int munlock_vma_page(struct page *page) { int nr_pages; - /* For try_to_munlock() and to serialize with page migration */ + /* For page_mlock() and to serialize with page migration */ BUG_ON(!PageLocked(page)); VM_BUG_ON_PAGE(PageTail(page), page); @@ -205,7 +205,7 @@ static int __mlock_posix_error_return(long retval) * * The fast path is available only for evictable pages with single mapping. * Then we can bypass the per-cpu pvec and get better performance. - * when mapcount > 1 we need try_to_munlock() which can fail. + * when mapcount > 1 we need page_mlock() which can fail. * when !page_evictable(), we need the full redo logic of putback_lru_page to * avoid leaving evictable page in unevictable list. * @@ -414,7 +414,7 @@ static unsigned long __munlock_pagevec_fill(struct pagevec *pvec, * * We don't save and restore VM_LOCKED here because pages are * still on lru. In unmap path, pages might be scanned by reclaim - * and re-mlocked by try_to_{munlock|unmap} before we unmap and + * and re-mlocked by page_mlock/try_to_unmap before we unmap and * free them. This will result in freeing mlocked pages. */ void munlock_vma_pages_range(struct vm_area_struct *vma, diff --git a/mm/mmap_lock.c b/mm/mmap_lock.c index 2ae3f33b85b1..f5852a058ce0 100644 --- a/mm/mmap_lock.c +++ b/mm/mmap_lock.c @@ -153,6 +153,37 @@ static inline void put_memcg_path_buf(void) rcu_read_unlock(); } +#define TRACE_MMAP_LOCK_EVENT(type, mm, ...) \ + do { \ + const char *memcg_path; \ + preempt_disable(); \ + memcg_path = get_mm_memcg_path(mm); \ + trace_mmap_lock_##type(mm, \ + memcg_path != NULL ? memcg_path : "", \ + ##__VA_ARGS__); \ + if (likely(memcg_path != NULL)) \ + put_memcg_path_buf(); \ + preempt_enable(); \ + } while (0) + +#else /* !CONFIG_MEMCG */ + +int trace_mmap_lock_reg(void) +{ + return 0; +} + +void trace_mmap_lock_unreg(void) +{ +} + +#define TRACE_MMAP_LOCK_EVENT(type, mm, ...) \ + trace_mmap_lock_##type(mm, "", ##__VA_ARGS__) + +#endif /* CONFIG_MEMCG */ + +#ifdef CONFIG_TRACING +#ifdef CONFIG_MEMCG /* * Write the given mm_struct's memcg path to a percpu buffer, and return a * pointer to it. If the path cannot be determined, or no buffer was available @@ -187,33 +218,6 @@ static const char *get_mm_memcg_path(struct mm_struct *mm) return buf; } -#define TRACE_MMAP_LOCK_EVENT(type, mm, ...) \ - do { \ - const char *memcg_path; \ - local_lock(&memcg_paths.lock); \ - memcg_path = get_mm_memcg_path(mm); \ - trace_mmap_lock_##type(mm, \ - memcg_path != NULL ? memcg_path : "", \ - ##__VA_ARGS__); \ - if (likely(memcg_path != NULL)) \ - put_memcg_path_buf(); \ - local_unlock(&memcg_paths.lock); \ - } while (0) - -#else /* !CONFIG_MEMCG */ - -int trace_mmap_lock_reg(void) -{ - return 0; -} - -void trace_mmap_lock_unreg(void) -{ -} - -#define TRACE_MMAP_LOCK_EVENT(type, mm, ...) \ - trace_mmap_lock_##type(mm, "", ##__VA_ARGS__) - #endif /* CONFIG_MEMCG */ /* @@ -239,3 +243,4 @@ void __mmap_lock_do_trace_released(struct mm_struct *mm, bool write) TRACE_MMAP_LOCK_EVENT(released, mm, write); } EXPORT_SYMBOL(__mmap_lock_do_trace_released); +#endif /* CONFIG_TRACING */ diff --git a/mm/mprotect.c b/mm/mprotect.c index e7a443157988..883e2cc85cad 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -143,26 +143,36 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd, swp_entry_t entry = pte_to_swp_entry(oldpte); pte_t newpte; - if (is_write_migration_entry(entry)) { + if (is_writable_migration_entry(entry)) { /* * A protection check is difficult so * just be safe and disable write */ - make_migration_entry_read(&entry); + entry = make_readable_migration_entry( + swp_offset(entry)); newpte = swp_entry_to_pte(entry); if (pte_swp_soft_dirty(oldpte)) newpte = pte_swp_mksoft_dirty(newpte); if (pte_swp_uffd_wp(oldpte)) newpte = pte_swp_mkuffd_wp(newpte); - } else if (is_write_device_private_entry(entry)) { + } else if (is_writable_device_private_entry(entry)) { /* * We do not preserve soft-dirtiness. See * copy_one_pte() for explanation. */ - make_device_private_entry_read(&entry); + entry = make_readable_device_private_entry( + swp_offset(entry)); newpte = swp_entry_to_pte(entry); if (pte_swp_uffd_wp(oldpte)) newpte = pte_swp_mkuffd_wp(newpte); + } else if (is_writable_device_exclusive_entry(entry)) { + entry = make_readable_device_exclusive_entry( + swp_offset(entry)); + newpte = swp_entry_to_pte(entry); + if (pte_swp_soft_dirty(oldpte)) + newpte = pte_swp_mksoft_dirty(newpte); + if (pte_swp_uffd_wp(oldpte)) + newpte = pte_swp_mkuffd_wp(newpte); } else { newpte = oldpte; } diff --git a/mm/nommu.c b/mm/nommu.c index affda71641ca..3a93d4054810 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -223,7 +223,7 @@ long vread(char *buf, char *addr, unsigned long count) */ void *vmalloc(unsigned long size) { - return __vmalloc(size, GFP_KERNEL | __GFP_HIGHMEM); + return __vmalloc(size, GFP_KERNEL); } EXPORT_SYMBOL(vmalloc); @@ -241,7 +241,7 @@ EXPORT_SYMBOL(vmalloc); */ void *vzalloc(unsigned long size) { - return __vmalloc(size, GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO); + return __vmalloc(size, GFP_KERNEL | __GFP_ZERO); } EXPORT_SYMBOL(vzalloc); @@ -1501,7 +1501,6 @@ int do_munmap(struct mm_struct *mm, unsigned long start, size_t len, struct list delete_vma(mm, vma); return 0; } -EXPORT_SYMBOL(do_munmap); int vm_munmap(unsigned long addr, size_t len) { diff --git a/mm/oom_kill.c b/mm/oom_kill.c index eefd3f5fde46..fcc29e9a3064 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -104,7 +104,7 @@ static bool oom_cpuset_eligible(struct task_struct *start, * mempolicy intersects current, otherwise it may be * needlessly killed. */ - ret = mempolicy_nodemask_intersects(tsk, mask); + ret = mempolicy_in_oom_domain(tsk, mask); } else { /* * This is not a mempolicy constrained oom, so only diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 0817d88383d5..d6e94cc8066c 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -749,7 +749,6 @@ void prep_compound_page(struct page *page, unsigned int order) __SetPageHead(page); for (i = 1; i < nr_pages; i++) { struct page *p = page + i; - set_page_count(p, 0); p->mapping = TAIL_MAPPING; set_compound_head(p, page); } @@ -3193,7 +3192,7 @@ static void __drain_all_pages(struct zone *zone, bool force_all_cpus) int cpu; /* - * Allocate in the BSS so we wont require allocation in + * Allocate in the BSS so we won't require allocation in * direct reclaim path for CONFIG_CPUMASK_OFFSTACK=y */ static cpumask_t cpus_with_pcps; @@ -3832,7 +3831,7 @@ static inline bool __should_fail_alloc_page(gfp_t gfp_mask, unsigned int order) #endif /* CONFIG_FAIL_PAGE_ALLOC */ -noinline bool should_fail_alloc_page(gfp_t gfp_mask, unsigned int order) +static noinline bool should_fail_alloc_page(gfp_t gfp_mask, unsigned int order) { return __should_fail_alloc_page(gfp_mask, order); } diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c index a4435311754b..f7b331081791 100644 --- a/mm/page_vma_mapped.c +++ b/mm/page_vma_mapped.c @@ -41,7 +41,8 @@ static bool map_pte(struct page_vma_mapped_walk *pvmw) /* Handle un-addressable ZONE_DEVICE memory */ entry = pte_to_swp_entry(*pvmw->pte); - if (!is_device_private_entry(entry)) + if (!is_device_private_entry(entry) && + !is_device_exclusive_entry(entry)) return false; } else if (!pte_present(*pvmw->pte)) return false; @@ -93,19 +94,21 @@ static bool check_pte(struct page_vma_mapped_walk *pvmw) return false; entry = pte_to_swp_entry(*pvmw->pte); - if (!is_migration_entry(entry)) + if (!is_migration_entry(entry) && + !is_device_exclusive_entry(entry)) return false; - pfn = migration_entry_to_pfn(entry); + pfn = swp_offset(entry); } else if (is_swap_pte(*pvmw->pte)) { swp_entry_t entry; /* Handle un-addressable ZONE_DEVICE memory */ entry = pte_to_swp_entry(*pvmw->pte); - if (!is_device_private_entry(entry)) + if (!is_device_private_entry(entry) && + !is_device_exclusive_entry(entry)) return false; - pfn = device_private_entry_to_pfn(entry); + pfn = swp_offset(entry); } else { if (!pte_present(*pvmw->pte)) return false; @@ -233,7 +236,7 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw) return not_found(pvmw); entry = pmd_to_swp_entry(pmde); if (!is_migration_entry(entry) || - migration_entry_to_page(entry) != page) + pfn_swap_entry_to_page(entry) != page) return not_found(pvmw); return true; } diff --git a/mm/rmap.c b/mm/rmap.c index e05c300048e6..37c24672125c 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1405,24 +1405,14 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, /* * When racing against e.g. zap_pte_range() on another cpu, * in between its ptep_get_and_clear_full() and page_remove_rmap(), - * try_to_unmap() may return false when it is about to become true, + * try_to_unmap() may return before page_mapped() has become false, * if page table locking is skipped: use TTU_SYNC to wait for that. */ if (flags & TTU_SYNC) pvmw.flags = PVMW_SYNC; - /* munlock has nothing to gain from examining un-locked vmas */ - if ((flags & TTU_MUNLOCK) && !(vma->vm_flags & VM_LOCKED)) - return true; - - if (IS_ENABLED(CONFIG_MIGRATION) && (flags & TTU_MIGRATION) && - is_zone_device_page(page) && !is_device_private_page(page)) - return true; - - if (flags & TTU_SPLIT_HUGE_PMD) { - split_huge_pmd_address(vma, address, - flags & TTU_SPLIT_FREEZE, page); - } + if (flags & TTU_SPLIT_HUGE_PMD) + split_huge_pmd_address(vma, address, false, page); /* * For THP, we have to assume the worse case ie pmd for invalidation. @@ -1447,16 +1437,6 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, mmu_notifier_invalidate_range_start(&range); while (page_vma_mapped_walk(&pvmw)) { -#ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION - /* PMD-mapped THP migration entry */ - if (!pvmw.pte && (flags & TTU_MIGRATION)) { - VM_BUG_ON_PAGE(PageHuge(page) || !PageTransCompound(page), page); - - set_pmd_migration_entry(&pvmw, page); - continue; - } -#endif - /* * If the page is mlock()d, we cannot swap it out. * If it's recently referenced (perhaps page_referenced @@ -1476,8 +1456,6 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, page_vma_mapped_walk_done(&pvmw); break; } - if (flags & TTU_MUNLOCK) - continue; } /* Unexpected PMD-mapped THP? */ @@ -1520,46 +1498,6 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, } } - if (IS_ENABLED(CONFIG_MIGRATION) && - (flags & TTU_MIGRATION) && - is_zone_device_page(page)) { - swp_entry_t entry; - pte_t swp_pte; - - pteval = ptep_get_and_clear(mm, pvmw.address, pvmw.pte); - - /* - * Store the pfn of the page in a special migration - * pte. do_swap_page() will wait until the migration - * pte is removed and then restart fault handling. - */ - entry = make_migration_entry(page, 0); - swp_pte = swp_entry_to_pte(entry); - - /* - * pteval maps a zone device page and is therefore - * a swap pte. - */ - if (pte_swp_soft_dirty(pteval)) - swp_pte = pte_swp_mksoft_dirty(swp_pte); - if (pte_swp_uffd_wp(pteval)) - swp_pte = pte_swp_mkuffd_wp(swp_pte); - set_pte_at(mm, pvmw.address, pvmw.pte, swp_pte); - /* - * No need to invalidate here it will synchronize on - * against the special swap migration pte. - * - * The assignment to subpage above was computed from a - * swap PTE which results in an invalid pointer. - * Since only PAGE_SIZE pages can currently be - * migrated, just set it to page. This will need to be - * changed when hugepage migrations to device private - * memory are supported. - */ - subpage = page; - goto discard; - } - /* Nuke the page table entry. */ flush_cache_page(vma, address, pte_pfn(*pvmw.pte)); if (should_defer_flush(mm, flags)) { @@ -1612,35 +1550,6 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, /* We have to invalidate as we cleared the pte */ mmu_notifier_invalidate_range(mm, address, address + PAGE_SIZE); - } else if (IS_ENABLED(CONFIG_MIGRATION) && - (flags & (TTU_MIGRATION|TTU_SPLIT_FREEZE))) { - swp_entry_t entry; - pte_t swp_pte; - - if (arch_unmap_one(mm, vma, address, pteval) < 0) { - set_pte_at(mm, address, pvmw.pte, pteval); - ret = false; - page_vma_mapped_walk_done(&pvmw); - break; - } - - /* - * Store the pfn of the page in a special migration - * pte. do_swap_page() will wait until the migration - * pte is removed and then restart fault handling. - */ - entry = make_migration_entry(subpage, - pte_write(pteval)); - swp_pte = swp_entry_to_pte(entry); - if (pte_soft_dirty(pteval)) - swp_pte = pte_swp_mksoft_dirty(swp_pte); - if (pte_uffd_wp(pteval)) - swp_pte = pte_swp_mkuffd_wp(swp_pte); - set_pte_at(mm, address, pvmw.pte, swp_pte); - /* - * No need to invalidate here it will synchronize on - * against the special swap migration pte. - */ } else if (PageAnon(page)) { swp_entry_t entry = { .val = page_private(subpage) }; pte_t swp_pte; @@ -1756,9 +1665,10 @@ static int page_not_mapped(struct page *page) * Tries to remove all the page table entries which are mapping this * page, used in the pageout path. Caller must hold the page lock. * - * If unmap is successful, return true. Otherwise, false. + * It is the caller's responsibility to check if the page is still + * mapped when needed (use TTU_SYNC to prevent accounting races). */ -bool try_to_unmap(struct page *page, enum ttu_flags flags) +void try_to_unmap(struct page *page, enum ttu_flags flags) { struct rmap_walk_control rwc = { .rmap_one = try_to_unmap_one, @@ -1767,6 +1677,277 @@ bool try_to_unmap(struct page *page, enum ttu_flags flags) .anon_lock = page_lock_anon_vma_read, }; + if (flags & TTU_RMAP_LOCKED) + rmap_walk_locked(page, &rwc); + else + rmap_walk(page, &rwc); +} + +/* + * @arg: enum ttu_flags will be passed to this argument. + * + * If TTU_SPLIT_HUGE_PMD is specified any PMD mappings will be split into PTEs + * containing migration entries. This and TTU_RMAP_LOCKED are the only supported + * flags. + */ +static bool try_to_migrate_one(struct page *page, struct vm_area_struct *vma, + unsigned long address, void *arg) +{ + struct mm_struct *mm = vma->vm_mm; + struct page_vma_mapped_walk pvmw = { + .page = page, + .vma = vma, + .address = address, + }; + pte_t pteval; + struct page *subpage; + bool ret = true; + struct mmu_notifier_range range; + enum ttu_flags flags = (enum ttu_flags)(long)arg; + + if (is_zone_device_page(page) && !is_device_private_page(page)) + return true; + + /* + * When racing against e.g. zap_pte_range() on another cpu, + * in between its ptep_get_and_clear_full() and page_remove_rmap(), + * try_to_migrate() may return before page_mapped() has become false, + * if page table locking is skipped: use TTU_SYNC to wait for that. + */ + if (flags & TTU_SYNC) + pvmw.flags = PVMW_SYNC; + + /* + * unmap_page() in mm/huge_memory.c is the only user of migration with + * TTU_SPLIT_HUGE_PMD and it wants to freeze. + */ + if (flags & TTU_SPLIT_HUGE_PMD) + split_huge_pmd_address(vma, address, true, page); + + /* + * For THP, we have to assume the worse case ie pmd for invalidation. + * For hugetlb, it could be much worse if we need to do pud + * invalidation in the case of pmd sharing. + * + * Note that the page can not be free in this function as call of + * try_to_unmap() must hold a reference on the page. + */ + range.end = PageKsm(page) ? + address + PAGE_SIZE : vma_address_end(page, vma); + mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, vma->vm_mm, + address, range.end); + if (PageHuge(page)) { + /* + * If sharing is possible, start and end will be adjusted + * accordingly. + */ + adjust_range_if_pmd_sharing_possible(vma, &range.start, + &range.end); + } + mmu_notifier_invalidate_range_start(&range); + + while (page_vma_mapped_walk(&pvmw)) { +#ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION + /* PMD-mapped THP migration entry */ + if (!pvmw.pte) { + VM_BUG_ON_PAGE(PageHuge(page) || + !PageTransCompound(page), page); + + set_pmd_migration_entry(&pvmw, page); + continue; + } +#endif + + /* Unexpected PMD-mapped THP? */ + VM_BUG_ON_PAGE(!pvmw.pte, page); + + subpage = page - page_to_pfn(page) + pte_pfn(*pvmw.pte); + address = pvmw.address; + + if (PageHuge(page) && !PageAnon(page)) { + /* + * To call huge_pmd_unshare, i_mmap_rwsem must be + * held in write mode. Caller needs to explicitly + * do this outside rmap routines. + */ + VM_BUG_ON(!(flags & TTU_RMAP_LOCKED)); + if (huge_pmd_unshare(mm, vma, &address, pvmw.pte)) { + /* + * huge_pmd_unshare unmapped an entire PMD + * page. There is no way of knowing exactly + * which PMDs may be cached for this mm, so + * we must flush them all. start/end were + * already adjusted above to cover this range. + */ + flush_cache_range(vma, range.start, range.end); + flush_tlb_range(vma, range.start, range.end); + mmu_notifier_invalidate_range(mm, range.start, + range.end); + + /* + * The ref count of the PMD page was dropped + * which is part of the way map counting + * is done for shared PMDs. Return 'true' + * here. When there is no other sharing, + * huge_pmd_unshare returns false and we will + * unmap the actual page and drop map count + * to zero. + */ + page_vma_mapped_walk_done(&pvmw); + break; + } + } + + /* Nuke the page table entry. */ + flush_cache_page(vma, address, pte_pfn(*pvmw.pte)); + pteval = ptep_clear_flush(vma, address, pvmw.pte); + + /* Move the dirty bit to the page. Now the pte is gone. */ + if (pte_dirty(pteval)) + set_page_dirty(page); + + /* Update high watermark before we lower rss */ + update_hiwater_rss(mm); + + if (is_zone_device_page(page)) { + swp_entry_t entry; + pte_t swp_pte; + + /* + * Store the pfn of the page in a special migration + * pte. do_swap_page() will wait until the migration + * pte is removed and then restart fault handling. + */ + entry = make_readable_migration_entry( + page_to_pfn(page)); + swp_pte = swp_entry_to_pte(entry); + + /* + * pteval maps a zone device page and is therefore + * a swap pte. + */ + if (pte_swp_soft_dirty(pteval)) + swp_pte = pte_swp_mksoft_dirty(swp_pte); + if (pte_swp_uffd_wp(pteval)) + swp_pte = pte_swp_mkuffd_wp(swp_pte); + set_pte_at(mm, pvmw.address, pvmw.pte, swp_pte); + /* + * No need to invalidate here it will synchronize on + * against the special swap migration pte. + * + * The assignment to subpage above was computed from a + * swap PTE which results in an invalid pointer. + * Since only PAGE_SIZE pages can currently be + * migrated, just set it to page. This will need to be + * changed when hugepage migrations to device private + * memory are supported. + */ + subpage = page; + } else if (PageHWPoison(page)) { + pteval = swp_entry_to_pte(make_hwpoison_entry(subpage)); + if (PageHuge(page)) { + hugetlb_count_sub(compound_nr(page), mm); + set_huge_swap_pte_at(mm, address, + pvmw.pte, pteval, + vma_mmu_pagesize(vma)); + } else { + dec_mm_counter(mm, mm_counter(page)); + set_pte_at(mm, address, pvmw.pte, pteval); + } + + } else if (pte_unused(pteval) && !userfaultfd_armed(vma)) { + /* + * The guest indicated that the page content is of no + * interest anymore. Simply discard the pte, vmscan + * will take care of the rest. + * A future reference will then fault in a new zero + * page. When userfaultfd is active, we must not drop + * this page though, as its main user (postcopy + * migration) will not expect userfaults on already + * copied pages. + */ + dec_mm_counter(mm, mm_counter(page)); + /* We have to invalidate as we cleared the pte */ + mmu_notifier_invalidate_range(mm, address, + address + PAGE_SIZE); + } else { + swp_entry_t entry; + pte_t swp_pte; + + if (arch_unmap_one(mm, vma, address, pteval) < 0) { + set_pte_at(mm, address, pvmw.pte, pteval); + ret = false; + page_vma_mapped_walk_done(&pvmw); + break; + } + + /* + * Store the pfn of the page in a special migration + * pte. do_swap_page() will wait until the migration + * pte is removed and then restart fault handling. + */ + if (pte_write(pteval)) + entry = make_writable_migration_entry( + page_to_pfn(subpage)); + else + entry = make_readable_migration_entry( + page_to_pfn(subpage)); + + swp_pte = swp_entry_to_pte(entry); + if (pte_soft_dirty(pteval)) + swp_pte = pte_swp_mksoft_dirty(swp_pte); + if (pte_uffd_wp(pteval)) + swp_pte = pte_swp_mkuffd_wp(swp_pte); + set_pte_at(mm, address, pvmw.pte, swp_pte); + /* + * No need to invalidate here it will synchronize on + * against the special swap migration pte. + */ + } + + /* + * No need to call mmu_notifier_invalidate_range() it has be + * done above for all cases requiring it to happen under page + * table lock before mmu_notifier_invalidate_range_end() + * + * See Documentation/vm/mmu_notifier.rst + */ + page_remove_rmap(subpage, PageHuge(page)); + put_page(page); + } + + mmu_notifier_invalidate_range_end(&range); + + return ret; +} + +/** + * try_to_migrate - try to replace all page table mappings with swap entries + * @page: the page to replace page table entries for + * @flags: action and flags + * + * Tries to remove all the page table entries which are mapping this page and + * replace them with special swap entries. Caller must hold the page lock. + * + * If is successful, return true. Otherwise, false. + */ +void try_to_migrate(struct page *page, enum ttu_flags flags) +{ + struct rmap_walk_control rwc = { + .rmap_one = try_to_migrate_one, + .arg = (void *)flags, + .done = page_not_mapped, + .anon_lock = page_lock_anon_vma_read, + }; + + /* + * Migration always ignores mlock and only supports TTU_RMAP_LOCKED and + * TTU_SPLIT_HUGE_PMD and TTU_SYNC flags. + */ + if (WARN_ON_ONCE(flags & ~(TTU_RMAP_LOCKED | TTU_SPLIT_HUGE_PMD | + TTU_SYNC))) + return; + /* * During exec, a temporary VMA is setup and later moved. * The VMA is moved under the anon_vma lock but not the @@ -1775,38 +1956,67 @@ bool try_to_unmap(struct page *page, enum ttu_flags flags) * locking requirements of exec(), migration skips * temporary VMAs until after exec() completes. */ - if ((flags & (TTU_MIGRATION|TTU_SPLIT_FREEZE)) - && !PageKsm(page) && PageAnon(page)) + if (!PageKsm(page) && PageAnon(page)) rwc.invalid_vma = invalid_migration_vma; if (flags & TTU_RMAP_LOCKED) rmap_walk_locked(page, &rwc); else rmap_walk(page, &rwc); +} - /* - * When racing against e.g. zap_pte_range() on another cpu, - * in between its ptep_get_and_clear_full() and page_remove_rmap(), - * try_to_unmap() may return false when it is about to become true, - * if page table locking is skipped: use TTU_SYNC to wait for that. - */ - return !page_mapcount(page); +/* + * Walks the vma's mapping a page and mlocks the page if any locked vma's are + * found. Once one is found the page is locked and the scan can be terminated. + */ +static bool page_mlock_one(struct page *page, struct vm_area_struct *vma, + unsigned long address, void *unused) +{ + struct page_vma_mapped_walk pvmw = { + .page = page, + .vma = vma, + .address = address, + }; + + /* An un-locked vma doesn't have any pages to lock, continue the scan */ + if (!(vma->vm_flags & VM_LOCKED)) + return true; + + while (page_vma_mapped_walk(&pvmw)) { + /* + * Need to recheck under the ptl to serialise with + * __munlock_pagevec_fill() after VM_LOCKED is cleared in + * munlock_vma_pages_range(). + */ + if (vma->vm_flags & VM_LOCKED) { + /* PTE-mapped THP are never mlocked */ + if (!PageTransCompound(page)) + mlock_vma_page(page); + page_vma_mapped_walk_done(&pvmw); + } + + /* + * no need to continue scanning other vma's if the page has + * been locked. + */ + return false; + } + + return true; } /** - * try_to_munlock - try to munlock a page - * @page: the page to be munlocked + * page_mlock - try to mlock a page + * @page: the page to be mlocked * - * Called from munlock code. Checks all of the VMAs mapping the page - * to make sure nobody else has this page mlocked. The page will be - * returned with PG_mlocked cleared if no other vmas have it mlocked. + * Called from munlock code. Checks all of the VMAs mapping the page and mlocks + * the page if any are found. The page will be returned with PG_mlocked cleared + * if it is not mapped by any locked vmas. */ - -void try_to_munlock(struct page *page) +void page_mlock(struct page *page) { struct rmap_walk_control rwc = { - .rmap_one = try_to_unmap_one, - .arg = (void *)TTU_MUNLOCK, + .rmap_one = page_mlock_one, .done = page_not_mapped, .anon_lock = page_lock_anon_vma_read, @@ -1818,6 +2028,192 @@ void try_to_munlock(struct page *page) rmap_walk(page, &rwc); } +#ifdef CONFIG_DEVICE_PRIVATE +struct make_exclusive_args { + struct mm_struct *mm; + unsigned long address; + void *owner; + bool valid; +}; + +static bool page_make_device_exclusive_one(struct page *page, + struct vm_area_struct *vma, unsigned long address, void *priv) +{ + struct mm_struct *mm = vma->vm_mm; + struct page_vma_mapped_walk pvmw = { + .page = page, + .vma = vma, + .address = address, + }; + struct make_exclusive_args *args = priv; + pte_t pteval; + struct page *subpage; + bool ret = true; + struct mmu_notifier_range range; + swp_entry_t entry; + pte_t swp_pte; + + mmu_notifier_range_init_owner(&range, MMU_NOTIFY_EXCLUSIVE, 0, vma, + vma->vm_mm, address, min(vma->vm_end, + address + page_size(page)), args->owner); + mmu_notifier_invalidate_range_start(&range); + + while (page_vma_mapped_walk(&pvmw)) { + /* Unexpected PMD-mapped THP? */ + VM_BUG_ON_PAGE(!pvmw.pte, page); + + if (!pte_present(*pvmw.pte)) { + ret = false; + page_vma_mapped_walk_done(&pvmw); + break; + } + + subpage = page - page_to_pfn(page) + pte_pfn(*pvmw.pte); + address = pvmw.address; + + /* Nuke the page table entry. */ + flush_cache_page(vma, address, pte_pfn(*pvmw.pte)); + pteval = ptep_clear_flush(vma, address, pvmw.pte); + + /* Move the dirty bit to the page. Now the pte is gone. */ + if (pte_dirty(pteval)) + set_page_dirty(page); + + /* + * Check that our target page is still mapped at the expected + * address. + */ + if (args->mm == mm && args->address == address && + pte_write(pteval)) + args->valid = true; + + /* + * Store the pfn of the page in a special migration + * pte. do_swap_page() will wait until the migration + * pte is removed and then restart fault handling. + */ + if (pte_write(pteval)) + entry = make_writable_device_exclusive_entry( + page_to_pfn(subpage)); + else + entry = make_readable_device_exclusive_entry( + page_to_pfn(subpage)); + swp_pte = swp_entry_to_pte(entry); + if (pte_soft_dirty(pteval)) + swp_pte = pte_swp_mksoft_dirty(swp_pte); + if (pte_uffd_wp(pteval)) + swp_pte = pte_swp_mkuffd_wp(swp_pte); + + set_pte_at(mm, address, pvmw.pte, swp_pte); + + /* + * There is a reference on the page for the swap entry which has + * been removed, so shouldn't take another. + */ + page_remove_rmap(subpage, false); + } + + mmu_notifier_invalidate_range_end(&range); + + return ret; +} + +/** + * page_make_device_exclusive - mark the page exclusively owned by a device + * @page: the page to replace page table entries for + * @mm: the mm_struct where the page is expected to be mapped + * @address: address where the page is expected to be mapped + * @owner: passed to MMU_NOTIFY_EXCLUSIVE range notifier callbacks + * + * Tries to remove all the page table entries which are mapping this page and + * replace them with special device exclusive swap entries to grant a device + * exclusive access to the page. Caller must hold the page lock. + * + * Returns false if the page is still mapped, or if it could not be unmapped + * from the expected address. Otherwise returns true (success). + */ +static bool page_make_device_exclusive(struct page *page, struct mm_struct *mm, + unsigned long address, void *owner) +{ + struct make_exclusive_args args = { + .mm = mm, + .address = address, + .owner = owner, + .valid = false, + }; + struct rmap_walk_control rwc = { + .rmap_one = page_make_device_exclusive_one, + .done = page_not_mapped, + .anon_lock = page_lock_anon_vma_read, + .arg = &args, + }; + + /* + * Restrict to anonymous pages for now to avoid potential writeback + * issues. Also tail pages shouldn't be passed to rmap_walk so skip + * those. + */ + if (!PageAnon(page) || PageTail(page)) + return false; + + rmap_walk(page, &rwc); + + return args.valid && !page_mapcount(page); +} + +/** + * make_device_exclusive_range() - Mark a range for exclusive use by a device + * @mm: mm_struct of assoicated target process + * @start: start of the region to mark for exclusive device access + * @end: end address of region + * @pages: returns the pages which were successfully marked for exclusive access + * @owner: passed to MMU_NOTIFY_EXCLUSIVE range notifier to allow filtering + * + * Returns: number of pages found in the range by GUP. A page is marked for + * exclusive access only if the page pointer is non-NULL. + * + * This function finds ptes mapping page(s) to the given address range, locks + * them and replaces mappings with special swap entries preventing userspace CPU + * access. On fault these entries are replaced with the original mapping after + * calling MMU notifiers. + * + * A driver using this to program access from a device must use a mmu notifier + * critical section to hold a device specific lock during programming. Once + * programming is complete it should drop the page lock and reference after + * which point CPU access to the page will revoke the exclusive access. + */ +int make_device_exclusive_range(struct mm_struct *mm, unsigned long start, + unsigned long end, struct page **pages, + void *owner) +{ + long npages = (end - start) >> PAGE_SHIFT; + long i; + + npages = get_user_pages_remote(mm, start, npages, + FOLL_GET | FOLL_WRITE | FOLL_SPLIT_PMD, + pages, NULL, NULL); + if (npages < 0) + return npages; + + for (i = 0; i < npages; i++, start += PAGE_SIZE) { + if (!trylock_page(pages[i])) { + put_page(pages[i]); + pages[i] = NULL; + continue; + } + + if (!page_make_device_exclusive(pages[i], mm, start, owner)) { + unlock_page(pages[i]); + put_page(pages[i]); + pages[i] = NULL; + } + } + + return npages; +} +EXPORT_SYMBOL_GPL(make_device_exclusive_range); +#endif + void __put_anon_vma(struct anon_vma *anon_vma) { struct anon_vma *root = anon_vma->root; @@ -1858,7 +2254,7 @@ static struct anon_vma *rmap_walk_anon_lock(struct page *page, * Find all the mappings of a page using the mapping pointer and the vma chains * contained in the anon_vma struct it points to. * - * When called from try_to_munlock(), the mmap_lock of the mm containing the vma + * When called from page_mlock(), the mmap_lock of the mm containing the vma * where the page was found will be held for write. So, we won't recheck * vm_flags for that VMA. That should be OK, because that vma shouldn't be * LOCKED. @@ -1911,7 +2307,7 @@ static void rmap_walk_anon(struct page *page, struct rmap_walk_control *rwc, * Find all the mappings of a page using the mapping pointer and the vma chains * contained in the address_space struct it points to. * - * When called from try_to_munlock(), the mmap_lock of the mm containing the vma + * When called from page_mlock(), the mmap_lock of the mm containing the vma * where the page was found will be held for write. So, we won't recheck * vm_flags for that VMA. That should be OK, because that vma shouldn't be * LOCKED. diff --git a/mm/shmem.c b/mm/shmem.c index 6268b9b4e41a..70d9ce294bb4 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1797,7 +1797,7 @@ static int shmem_swapin_page(struct inode *inode, pgoff_t index, * vm. If we swap it in we mark it dirty since we also free the swap * entry since a page cannot live in both the swap and page cache. * - * vmf and fault_type are only supplied by shmem_fault: + * vma, vmf, and fault_type are only supplied by shmem_fault: * otherwise they are NULL. */ static int shmem_getpage_gfp(struct inode *inode, pgoff_t index, @@ -1832,6 +1832,16 @@ static int shmem_getpage_gfp(struct inode *inode, pgoff_t index, page = pagecache_get_page(mapping, index, FGP_ENTRY | FGP_HEAD | FGP_LOCK, 0); + + if (page && vma && userfaultfd_minor(vma)) { + if (!xa_is_value(page)) { + unlock_page(page); + put_page(page); + } + *fault_type = handle_userfault(vmf, VM_UFFD_MINOR); + return 0; + } + if (xa_is_value(page)) { error = shmem_swapin_page(inode, index, &page, sgp, gfp, vma, fault_type); @@ -2352,27 +2362,25 @@ static struct inode *shmem_get_inode(struct super_block *sb, const struct inode return inode; } -static int shmem_mfill_atomic_pte(struct mm_struct *dst_mm, - pmd_t *dst_pmd, - struct vm_area_struct *dst_vma, - unsigned long dst_addr, - unsigned long src_addr, - bool zeropage, - struct page **pagep) +#ifdef CONFIG_USERFAULTFD +int shmem_mfill_atomic_pte(struct mm_struct *dst_mm, + pmd_t *dst_pmd, + struct vm_area_struct *dst_vma, + unsigned long dst_addr, + unsigned long src_addr, + bool zeropage, + struct page **pagep) { struct inode *inode = file_inode(dst_vma->vm_file); struct shmem_inode_info *info = SHMEM_I(inode); struct address_space *mapping = inode->i_mapping; gfp_t gfp = mapping_gfp_mask(mapping); pgoff_t pgoff = linear_page_index(dst_vma, dst_addr); - spinlock_t *ptl; void *page_kaddr; struct page *page; - pte_t _dst_pte, *dst_pte; int ret; - pgoff_t offset, max_off; + pgoff_t max_off; - ret = -ENOMEM; if (!shmem_inode_acct_block(inode, 1)) { /* * We may have got a page, returned -ENOENT triggering a retry, @@ -2383,15 +2391,16 @@ static int shmem_mfill_atomic_pte(struct mm_struct *dst_mm, put_page(*pagep); *pagep = NULL; } - goto out; + return -ENOMEM; } if (!*pagep) { + ret = -ENOMEM; page = shmem_alloc_page(gfp, info, pgoff); if (!page) goto out_unacct_blocks; - if (!zeropage) { /* mcopy_atomic */ + if (!zeropage) { /* COPY */ page_kaddr = kmap_atomic(page); ret = copy_from_user(page_kaddr, (const void __user *)src_addr, @@ -2401,11 +2410,11 @@ static int shmem_mfill_atomic_pte(struct mm_struct *dst_mm, /* fallback to copy_from_user outside mmap_lock */ if (unlikely(ret)) { *pagep = page; - shmem_inode_unacct_blocks(inode, 1); + ret = -ENOENT; /* don't free the page */ - return -ENOENT; + goto out_unacct_blocks; } - } else { /* mfill_zeropage_atomic */ + } else { /* ZEROPAGE */ clear_highpage(page); } } else { @@ -2413,15 +2422,15 @@ static int shmem_mfill_atomic_pte(struct mm_struct *dst_mm, *pagep = NULL; } - VM_BUG_ON(PageLocked(page) || PageSwapBacked(page)); + VM_BUG_ON(PageLocked(page)); + VM_BUG_ON(PageSwapBacked(page)); __SetPageLocked(page); __SetPageSwapBacked(page); __SetPageUptodate(page); ret = -EFAULT; - offset = linear_page_index(dst_vma, dst_addr); max_off = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE); - if (unlikely(offset >= max_off)) + if (unlikely(pgoff >= max_off)) goto out_release; ret = shmem_add_to_page_cache(page, mapping, pgoff, NULL, @@ -2429,32 +2438,10 @@ static int shmem_mfill_atomic_pte(struct mm_struct *dst_mm, if (ret) goto out_release; - _dst_pte = mk_pte(page, dst_vma->vm_page_prot); - if (dst_vma->vm_flags & VM_WRITE) - _dst_pte = pte_mkwrite(pte_mkdirty(_dst_pte)); - else { - /* - * We don't set the pte dirty if the vma has no - * VM_WRITE permission, so mark the page dirty or it - * could be freed from under us. We could do it - * unconditionally before unlock_page(), but doing it - * only if VM_WRITE is not set is faster. - */ - set_page_dirty(page); - } - - dst_pte = pte_offset_map_lock(dst_mm, dst_pmd, dst_addr, &ptl); - - ret = -EFAULT; - max_off = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE); - if (unlikely(offset >= max_off)) - goto out_release_unlock; - - ret = -EEXIST; - if (!pte_none(*dst_pte)) - goto out_release_unlock; - - lru_cache_add(page); + ret = mfill_atomic_install_pte(dst_mm, dst_pmd, dst_vma, dst_addr, + page, true, false); + if (ret) + goto out_delete_from_cache; spin_lock_irq(&info->lock); info->alloced++; @@ -2462,50 +2449,19 @@ static int shmem_mfill_atomic_pte(struct mm_struct *dst_mm, shmem_recalc_inode(inode); spin_unlock_irq(&info->lock); - inc_mm_counter(dst_mm, mm_counter_file(page)); - page_add_file_rmap(page, false); - set_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte); - - /* No need to invalidate - it was non-present before */ - update_mmu_cache(dst_vma, dst_addr, dst_pte); - pte_unmap_unlock(dst_pte, ptl); + SetPageDirty(page); unlock_page(page); - ret = 0; -out: - return ret; -out_release_unlock: - pte_unmap_unlock(dst_pte, ptl); - ClearPageDirty(page); + return 0; +out_delete_from_cache: delete_from_page_cache(page); out_release: unlock_page(page); put_page(page); out_unacct_blocks: shmem_inode_unacct_blocks(inode, 1); - goto out; -} - -int shmem_mcopy_atomic_pte(struct mm_struct *dst_mm, - pmd_t *dst_pmd, - struct vm_area_struct *dst_vma, - unsigned long dst_addr, - unsigned long src_addr, - struct page **pagep) -{ - return shmem_mfill_atomic_pte(dst_mm, dst_pmd, dst_vma, - dst_addr, src_addr, false, pagep); -} - -int shmem_mfill_zeropage_pte(struct mm_struct *dst_mm, - pmd_t *dst_pmd, - struct vm_area_struct *dst_vma, - unsigned long dst_addr) -{ - struct page *page = NULL; - - return shmem_mfill_atomic_pte(dst_mm, dst_pmd, dst_vma, - dst_addr, 0, true, &page); + return ret; } +#endif /* CONFIG_USERFAULTFD */ #ifdef CONFIG_TMPFS static const struct inode_operations shmem_symlink_inode_operations; @@ -4040,8 +3996,7 @@ bool shmem_huge_enabled(struct vm_area_struct *vma) loff_t i_size; pgoff_t off; - if ((vma->vm_flags & VM_NOHUGEPAGE) || - test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags)) + if (!transhuge_vma_enabled(vma, vma->vm_flags)) return false; if (shmem_huge == SHMEM_HUGE_FORCE) return true; diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c index 16183d85a7d5..bdce883f9286 100644 --- a/mm/sparse-vmemmap.c +++ b/mm/sparse-vmemmap.c @@ -27,8 +27,362 @@ #include #include #include +#include +#include + #include #include +#include + +/** + * struct vmemmap_remap_walk - walk vmemmap page table + * + * @remap_pte: called for each lowest-level entry (PTE). + * @nr_walked: the number of walked pte. + * @reuse_page: the page which is reused for the tail vmemmap pages. + * @reuse_addr: the virtual address of the @reuse_page page. + * @vmemmap_pages: the list head of the vmemmap pages that can be freed + * or is mapped from. + */ +struct vmemmap_remap_walk { + void (*remap_pte)(pte_t *pte, unsigned long addr, + struct vmemmap_remap_walk *walk); + unsigned long nr_walked; + struct page *reuse_page; + unsigned long reuse_addr; + struct list_head *vmemmap_pages; +}; + +static int split_vmemmap_huge_pmd(pmd_t *pmd, unsigned long start, + struct vmemmap_remap_walk *walk) +{ + pmd_t __pmd; + int i; + unsigned long addr = start; + struct page *page = pmd_page(*pmd); + pte_t *pgtable = pte_alloc_one_kernel(&init_mm); + + if (!pgtable) + return -ENOMEM; + + pmd_populate_kernel(&init_mm, &__pmd, pgtable); + + for (i = 0; i < PMD_SIZE / PAGE_SIZE; i++, addr += PAGE_SIZE) { + pte_t entry, *pte; + pgprot_t pgprot = PAGE_KERNEL; + + entry = mk_pte(page + i, pgprot); + pte = pte_offset_kernel(&__pmd, addr); + set_pte_at(&init_mm, addr, pte, entry); + } + + /* Make pte visible before pmd. See comment in __pte_alloc(). */ + smp_wmb(); + pmd_populate_kernel(&init_mm, pmd, pgtable); + + flush_tlb_kernel_range(start, start + PMD_SIZE); + + return 0; +} + +static void vmemmap_pte_range(pmd_t *pmd, unsigned long addr, + unsigned long end, + struct vmemmap_remap_walk *walk) +{ + pte_t *pte = pte_offset_kernel(pmd, addr); + + /* + * The reuse_page is found 'first' in table walk before we start + * remapping (which is calling @walk->remap_pte). + */ + if (!walk->reuse_page) { + walk->reuse_page = pte_page(*pte); + /* + * Because the reuse address is part of the range that we are + * walking, skip the reuse address range. + */ + addr += PAGE_SIZE; + pte++; + walk->nr_walked++; + } + + for (; addr != end; addr += PAGE_SIZE, pte++) { + walk->remap_pte(pte, addr, walk); + walk->nr_walked++; + } +} + +static int vmemmap_pmd_range(pud_t *pud, unsigned long addr, + unsigned long end, + struct vmemmap_remap_walk *walk) +{ + pmd_t *pmd; + unsigned long next; + + pmd = pmd_offset(pud, addr); + do { + if (pmd_leaf(*pmd)) { + int ret; + + ret = split_vmemmap_huge_pmd(pmd, addr & PMD_MASK, walk); + if (ret) + return ret; + } + next = pmd_addr_end(addr, end); + vmemmap_pte_range(pmd, addr, next, walk); + } while (pmd++, addr = next, addr != end); + + return 0; +} + +static int vmemmap_pud_range(p4d_t *p4d, unsigned long addr, + unsigned long end, + struct vmemmap_remap_walk *walk) +{ + pud_t *pud; + unsigned long next; + + pud = pud_offset(p4d, addr); + do { + int ret; + + next = pud_addr_end(addr, end); + ret = vmemmap_pmd_range(pud, addr, next, walk); + if (ret) + return ret; + } while (pud++, addr = next, addr != end); + + return 0; +} + +static int vmemmap_p4d_range(pgd_t *pgd, unsigned long addr, + unsigned long end, + struct vmemmap_remap_walk *walk) +{ + p4d_t *p4d; + unsigned long next; + + p4d = p4d_offset(pgd, addr); + do { + int ret; + + next = p4d_addr_end(addr, end); + ret = vmemmap_pud_range(p4d, addr, next, walk); + if (ret) + return ret; + } while (p4d++, addr = next, addr != end); + + return 0; +} + +static int vmemmap_remap_range(unsigned long start, unsigned long end, + struct vmemmap_remap_walk *walk) +{ + unsigned long addr = start; + unsigned long next; + pgd_t *pgd; + + VM_BUG_ON(!IS_ALIGNED(start, PAGE_SIZE)); + VM_BUG_ON(!IS_ALIGNED(end, PAGE_SIZE)); + + pgd = pgd_offset_k(addr); + do { + int ret; + + next = pgd_addr_end(addr, end); + ret = vmemmap_p4d_range(pgd, addr, next, walk); + if (ret) + return ret; + } while (pgd++, addr = next, addr != end); + + /* + * We only change the mapping of the vmemmap virtual address range + * [@start + PAGE_SIZE, end), so we only need to flush the TLB which + * belongs to the range. + */ + flush_tlb_kernel_range(start + PAGE_SIZE, end); + + return 0; +} + +/* + * Free a vmemmap page. A vmemmap page can be allocated from the memblock + * allocator or buddy allocator. If the PG_reserved flag is set, it means + * that it allocated from the memblock allocator, just free it via the + * free_bootmem_page(). Otherwise, use __free_page(). + */ +static inline void free_vmemmap_page(struct page *page) +{ + if (PageReserved(page)) + free_bootmem_page(page); + else + __free_page(page); +} + +/* Free a list of the vmemmap pages */ +static void free_vmemmap_page_list(struct list_head *list) +{ + struct page *page, *next; + + list_for_each_entry_safe(page, next, list, lru) { + list_del(&page->lru); + free_vmemmap_page(page); + } +} + +static void vmemmap_remap_pte(pte_t *pte, unsigned long addr, + struct vmemmap_remap_walk *walk) +{ + /* + * Remap the tail pages as read-only to catch illegal write operation + * to the tail pages. + */ + pgprot_t pgprot = PAGE_KERNEL_RO; + pte_t entry = mk_pte(walk->reuse_page, pgprot); + struct page *page = pte_page(*pte); + + list_add_tail(&page->lru, walk->vmemmap_pages); + set_pte_at(&init_mm, addr, pte, entry); +} + +static void vmemmap_restore_pte(pte_t *pte, unsigned long addr, + struct vmemmap_remap_walk *walk) +{ + pgprot_t pgprot = PAGE_KERNEL; + struct page *page; + void *to; + + BUG_ON(pte_page(*pte) != walk->reuse_page); + + page = list_first_entry(walk->vmemmap_pages, struct page, lru); + list_del(&page->lru); + to = page_to_virt(page); + copy_page(to, (void *)walk->reuse_addr); + + set_pte_at(&init_mm, addr, pte, mk_pte(page, pgprot)); +} + +/** + * vmemmap_remap_free - remap the vmemmap virtual address range [@start, @end) + * to the page which @reuse is mapped to, then free vmemmap + * which the range are mapped to. + * @start: start address of the vmemmap virtual address range that we want + * to remap. + * @end: end address of the vmemmap virtual address range that we want to + * remap. + * @reuse: reuse address. + * + * Return: %0 on success, negative error code otherwise. + */ +int vmemmap_remap_free(unsigned long start, unsigned long end, + unsigned long reuse) +{ + int ret; + LIST_HEAD(vmemmap_pages); + struct vmemmap_remap_walk walk = { + .remap_pte = vmemmap_remap_pte, + .reuse_addr = reuse, + .vmemmap_pages = &vmemmap_pages, + }; + + /* + * In order to make remapping routine most efficient for the huge pages, + * the routine of vmemmap page table walking has the following rules + * (see more details from the vmemmap_pte_range()): + * + * - The range [@start, @end) and the range [@reuse, @reuse + PAGE_SIZE) + * should be continuous. + * - The @reuse address is part of the range [@reuse, @end) that we are + * walking which is passed to vmemmap_remap_range(). + * - The @reuse address is the first in the complete range. + * + * So we need to make sure that @start and @reuse meet the above rules. + */ + BUG_ON(start - reuse != PAGE_SIZE); + + mmap_write_lock(&init_mm); + ret = vmemmap_remap_range(reuse, end, &walk); + mmap_write_downgrade(&init_mm); + + if (ret && walk.nr_walked) { + end = reuse + walk.nr_walked * PAGE_SIZE; + /* + * vmemmap_pages contains pages from the previous + * vmemmap_remap_range call which failed. These + * are pages which were removed from the vmemmap. + * They will be restored in the following call. + */ + walk = (struct vmemmap_remap_walk) { + .remap_pte = vmemmap_restore_pte, + .reuse_addr = reuse, + .vmemmap_pages = &vmemmap_pages, + }; + + vmemmap_remap_range(reuse, end, &walk); + } + mmap_read_unlock(&init_mm); + + free_vmemmap_page_list(&vmemmap_pages); + + return ret; +} + +static int alloc_vmemmap_page_list(unsigned long start, unsigned long end, + gfp_t gfp_mask, struct list_head *list) +{ + unsigned long nr_pages = (end - start) >> PAGE_SHIFT; + int nid = page_to_nid((struct page *)start); + struct page *page, *next; + + while (nr_pages--) { + page = alloc_pages_node(nid, gfp_mask, 0); + if (!page) + goto out; + list_add_tail(&page->lru, list); + } + + return 0; +out: + list_for_each_entry_safe(page, next, list, lru) + __free_pages(page, 0); + return -ENOMEM; +} + +/** + * vmemmap_remap_alloc - remap the vmemmap virtual address range [@start, end) + * to the page which is from the @vmemmap_pages + * respectively. + * @start: start address of the vmemmap virtual address range that we want + * to remap. + * @end: end address of the vmemmap virtual address range that we want to + * remap. + * @reuse: reuse address. + * @gfp_mask: GFP flag for allocating vmemmap pages. + * + * Return: %0 on success, negative error code otherwise. + */ +int vmemmap_remap_alloc(unsigned long start, unsigned long end, + unsigned long reuse, gfp_t gfp_mask) +{ + LIST_HEAD(vmemmap_pages); + struct vmemmap_remap_walk walk = { + .remap_pte = vmemmap_restore_pte, + .reuse_addr = reuse, + .vmemmap_pages = &vmemmap_pages, + }; + + /* See the comment in the vmemmap_remap_free(). */ + BUG_ON(start - reuse != PAGE_SIZE); + + if (alloc_vmemmap_page_list(start, end, gfp_mask, &vmemmap_pages)) + return -ENOMEM; + + mmap_read_lock(&init_mm); + vmemmap_remap_range(reuse, end, &walk); + mmap_read_unlock(&init_mm); + + return 0; +} /* * Allocate a block of memory to be used to back the virtual memory map diff --git a/mm/sparse.c b/mm/sparse.c index 7272f7a1449d..6326cdf36c4f 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -13,6 +13,7 @@ #include #include #include +#include #include "internal.h" #include diff --git a/mm/swap.c b/mm/swap.c index 6c11db780467..19600430e536 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -554,7 +554,7 @@ static void lru_deactivate_file_fn(struct page *page, struct lruvec *lruvec) } else { /* * The page's writeback ends up during pagevec - * We moves tha page into tail of inactive. + * We move that page into tail of inactive. */ add_page_to_lru_list_tail(page, lruvec); __count_vm_events(PGROTATED, nr_pages); diff --git a/mm/swapfile.c b/mm/swapfile.c index e898c879a434..1e07d1c776f2 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -2967,7 +2967,7 @@ static unsigned long read_swap_header(struct swap_info_struct *p, return 0; } - /* swap partition endianess hack... */ + /* swap partition endianness hack... */ if (swab32(swap_header->info.version) == 1) { swab32s(&swap_header->info.version); swab32s(&swap_header->info.last_page); diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index 63a73e164d55..0e2132834bc7 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -48,6 +48,78 @@ struct vm_area_struct *find_dst_vma(struct mm_struct *dst_mm, return dst_vma; } +/* + * Install PTEs, to map dst_addr (within dst_vma) to page. + * + * This function handles both MCOPY_ATOMIC_NORMAL and _CONTINUE for both shmem + * and anon, and for both shared and private VMAs. + */ +int mfill_atomic_install_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd, + struct vm_area_struct *dst_vma, + unsigned long dst_addr, struct page *page, + bool newly_allocated, bool wp_copy) +{ + int ret; + pte_t _dst_pte, *dst_pte; + bool writable = dst_vma->vm_flags & VM_WRITE; + bool vm_shared = dst_vma->vm_flags & VM_SHARED; + bool page_in_cache = page->mapping; + spinlock_t *ptl; + struct inode *inode; + pgoff_t offset, max_off; + + _dst_pte = mk_pte(page, dst_vma->vm_page_prot); + if (page_in_cache && !vm_shared) + writable = false; + if (writable || !page_in_cache) + _dst_pte = pte_mkdirty(_dst_pte); + if (writable) { + if (wp_copy) + _dst_pte = pte_mkuffd_wp(_dst_pte); + else + _dst_pte = pte_mkwrite(_dst_pte); + } + + dst_pte = pte_offset_map_lock(dst_mm, dst_pmd, dst_addr, &ptl); + + if (vma_is_shmem(dst_vma)) { + /* serialize against truncate with the page table lock */ + inode = dst_vma->vm_file->f_inode; + offset = linear_page_index(dst_vma, dst_addr); + max_off = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE); + ret = -EFAULT; + if (unlikely(offset >= max_off)) + goto out_unlock; + } + + ret = -EEXIST; + if (!pte_none(*dst_pte)) + goto out_unlock; + + if (page_in_cache) + page_add_file_rmap(page, false); + else + page_add_new_anon_rmap(page, dst_vma, dst_addr, false); + + /* + * Must happen after rmap, as mm_counter() checks mapping (via + * PageAnon()), which is set by __page_set_anon_rmap(). + */ + inc_mm_counter(dst_mm, mm_counter(page)); + + if (newly_allocated) + lru_cache_add_inactive_or_unevictable(page, dst_vma); + + set_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte); + + /* No need to invalidate - it was non-present before */ + update_mmu_cache(dst_vma, dst_addr, dst_pte); + ret = 0; +out_unlock: + pte_unmap_unlock(dst_pte, ptl); + return ret; +} + static int mcopy_atomic_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd, struct vm_area_struct *dst_vma, @@ -56,13 +128,9 @@ static int mcopy_atomic_pte(struct mm_struct *dst_mm, struct page **pagep, bool wp_copy) { - pte_t _dst_pte, *dst_pte; - spinlock_t *ptl; void *page_kaddr; int ret; struct page *page; - pgoff_t offset, max_off; - struct inode *inode; if (!*pagep) { ret = -ENOMEM; @@ -99,43 +167,12 @@ static int mcopy_atomic_pte(struct mm_struct *dst_mm, if (mem_cgroup_charge(page, dst_mm, GFP_KERNEL)) goto out_release; - _dst_pte = pte_mkdirty(mk_pte(page, dst_vma->vm_page_prot)); - if (dst_vma->vm_flags & VM_WRITE) { - if (wp_copy) - _dst_pte = pte_mkuffd_wp(_dst_pte); - else - _dst_pte = pte_mkwrite(_dst_pte); - } - - dst_pte = pte_offset_map_lock(dst_mm, dst_pmd, dst_addr, &ptl); - if (dst_vma->vm_file) { - /* the shmem MAP_PRIVATE case requires checking the i_size */ - inode = dst_vma->vm_file->f_inode; - offset = linear_page_index(dst_vma, dst_addr); - max_off = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE); - ret = -EFAULT; - if (unlikely(offset >= max_off)) - goto out_release_uncharge_unlock; - } - ret = -EEXIST; - if (!pte_none(*dst_pte)) - goto out_release_uncharge_unlock; - - inc_mm_counter(dst_mm, MM_ANONPAGES); - page_add_new_anon_rmap(page, dst_vma, dst_addr, false); - lru_cache_add_inactive_or_unevictable(page, dst_vma); - - set_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte); - - /* No need to invalidate - it was non-present before */ - update_mmu_cache(dst_vma, dst_addr, dst_pte); - - pte_unmap_unlock(dst_pte, ptl); - ret = 0; + ret = mfill_atomic_install_pte(dst_mm, dst_pmd, dst_vma, dst_addr, + page, true, wp_copy); + if (ret) + goto out_release; out: return ret; -out_release_uncharge_unlock: - pte_unmap_unlock(dst_pte, ptl); out_release: put_page(page); goto out; @@ -176,6 +213,41 @@ static int mfill_zeropage_pte(struct mm_struct *dst_mm, return ret; } +/* Handles UFFDIO_CONTINUE for all shmem VMAs (shared or private). */ +static int mcontinue_atomic_pte(struct mm_struct *dst_mm, + pmd_t *dst_pmd, + struct vm_area_struct *dst_vma, + unsigned long dst_addr, + bool wp_copy) +{ + struct inode *inode = file_inode(dst_vma->vm_file); + pgoff_t pgoff = linear_page_index(dst_vma, dst_addr); + struct page *page; + int ret; + + ret = shmem_getpage(inode, pgoff, &page, SGP_READ); + if (ret) + goto out; + if (!page) { + ret = -EFAULT; + goto out; + } + + ret = mfill_atomic_install_pte(dst_mm, dst_pmd, dst_vma, dst_addr, + page, false, wp_copy); + if (ret) + goto out_release; + + unlock_page(page); + ret = 0; +out: + return ret; +out_release: + unlock_page(page); + put_page(page); + goto out; +} + static pmd_t *mm_alloc_pmd(struct mm_struct *mm, unsigned long address) { pgd_t *pgd; @@ -209,7 +281,6 @@ static __always_inline ssize_t __mcopy_atomic_hugetlb(struct mm_struct *dst_mm, unsigned long len, enum mcopy_atomic_mode mode) { - int vm_alloc_shared = dst_vma->vm_flags & VM_SHARED; int vm_shared = dst_vma->vm_flags & VM_SHARED; ssize_t err; pte_t *dst_pte; @@ -308,7 +379,6 @@ static __always_inline ssize_t __mcopy_atomic_hugetlb(struct mm_struct *dst_mm, mutex_unlock(&hugetlb_fault_mutex_table[hash]); i_mmap_unlock_read(mapping); - vm_alloc_shared = vm_shared; cond_resched(); @@ -346,54 +416,8 @@ static __always_inline ssize_t __mcopy_atomic_hugetlb(struct mm_struct *dst_mm, out_unlock: mmap_read_unlock(dst_mm); out: - if (page) { - /* - * We encountered an error and are about to free a newly - * allocated huge page. - * - * Reservation handling is very subtle, and is different for - * private and shared mappings. See the routine - * restore_reserve_on_error for details. Unfortunately, we - * can not call restore_reserve_on_error now as it would - * require holding mmap_lock. - * - * If a reservation for the page existed in the reservation - * map of a private mapping, the map was modified to indicate - * the reservation was consumed when the page was allocated. - * We clear the HPageRestoreReserve flag now so that the global - * reserve count will not be incremented in free_huge_page. - * The reservation map will still indicate the reservation - * was consumed and possibly prevent later page allocation. - * This is better than leaking a global reservation. If no - * reservation existed, it is still safe to clear - * HPageRestoreReserve as no adjustments to reservation counts - * were made during allocation. - * - * The reservation map for shared mappings indicates which - * pages have reservations. When a huge page is allocated - * for an address with a reservation, no change is made to - * the reserve map. In this case HPageRestoreReserve will be - * set to indicate that the global reservation count should be - * incremented when the page is freed. This is the desired - * behavior. However, when a huge page is allocated for an - * address without a reservation a reservation entry is added - * to the reservation map, and HPageRestoreReserve will not be - * set. When the page is freed, the global reserve count will - * NOT be incremented and it will appear as though we have - * leaked reserved page. In this case, set HPageRestoreReserve - * so that the global reserve count will be incremented to - * match the reservation map entry which was created. - * - * Note that vm_alloc_shared is based on the flags of the vma - * for which the page was originally allocated. dst_vma could - * be different or NULL on error. - */ - if (vm_alloc_shared) - SetHPageRestoreReserve(page); - else - ClearHPageRestoreReserve(page); + if (page) put_page(page); - } BUG_ON(copied < 0); BUG_ON(err > 0); BUG_ON(!copied && !err); @@ -415,11 +439,16 @@ static __always_inline ssize_t mfill_atomic_pte(struct mm_struct *dst_mm, unsigned long dst_addr, unsigned long src_addr, struct page **page, - bool zeropage, + enum mcopy_atomic_mode mode, bool wp_copy) { ssize_t err; + if (mode == MCOPY_ATOMIC_CONTINUE) { + return mcontinue_atomic_pte(dst_mm, dst_pmd, dst_vma, dst_addr, + wp_copy); + } + /* * The normal page fault path for a shmem will invoke the * fault, fill the hole in the file and COW it right away. The @@ -431,7 +460,7 @@ static __always_inline ssize_t mfill_atomic_pte(struct mm_struct *dst_mm, * and not in the radix tree. */ if (!(dst_vma->vm_flags & VM_SHARED)) { - if (!zeropage) + if (mode == MCOPY_ATOMIC_NORMAL) err = mcopy_atomic_pte(dst_mm, dst_pmd, dst_vma, dst_addr, src_addr, page, wp_copy); @@ -440,13 +469,10 @@ static __always_inline ssize_t mfill_atomic_pte(struct mm_struct *dst_mm, dst_vma, dst_addr); } else { VM_WARN_ON_ONCE(wp_copy); - if (!zeropage) - err = shmem_mcopy_atomic_pte(dst_mm, dst_pmd, - dst_vma, dst_addr, - src_addr, page); - else - err = shmem_mfill_zeropage_pte(dst_mm, dst_pmd, - dst_vma, dst_addr); + err = shmem_mfill_atomic_pte(dst_mm, dst_pmd, dst_vma, + dst_addr, src_addr, + mode != MCOPY_ATOMIC_NORMAL, + page); } return err; @@ -467,7 +493,6 @@ static __always_inline ssize_t __mcopy_atomic(struct mm_struct *dst_mm, long copied; struct page *page; bool wp_copy; - bool zeropage = (mcopy_mode == MCOPY_ATOMIC_ZEROPAGE); /* * Sanitize the command parameters: @@ -530,7 +555,7 @@ static __always_inline ssize_t __mcopy_atomic(struct mm_struct *dst_mm, if (!vma_is_anonymous(dst_vma) && !vma_is_shmem(dst_vma)) goto out_unlock; - if (mcopy_mode == MCOPY_ATOMIC_CONTINUE) + if (!vma_is_shmem(dst_vma) && mcopy_mode == MCOPY_ATOMIC_CONTINUE) goto out_unlock; /* @@ -578,7 +603,7 @@ static __always_inline ssize_t __mcopy_atomic(struct mm_struct *dst_mm, BUG_ON(pmd_trans_huge(*dst_pmd)); err = mfill_atomic_pte(dst_mm, dst_pmd, dst_vma, dst_addr, - src_addr, &page, zeropage, wp_copy); + src_addr, &page, mcopy_mode, wp_copy); cond_resched(); if (unlikely(err == -ENOENT)) { diff --git a/mm/util.c b/mm/util.c index a8bf17f18a81..a034525e7ba2 100644 --- a/mm/util.c +++ b/mm/util.c @@ -1010,3 +1010,43 @@ void mem_dump_obj(void *object) } EXPORT_SYMBOL_GPL(mem_dump_obj); #endif + +/* + * A driver might set a page logically offline -- PageOffline() -- and + * turn the page inaccessible in the hypervisor; after that, access to page + * content can be fatal. + * + * Some special PFN walkers -- i.e., /proc/kcore -- read content of random + * pages after checking PageOffline(); however, these PFN walkers can race + * with drivers that set PageOffline(). + * + * page_offline_freeze()/page_offline_thaw() allows for a subsystem to + * synchronize with such drivers, achieving that a page cannot be set + * PageOffline() while frozen. + * + * page_offline_begin()/page_offline_end() is used by drivers that care about + * such races when setting a page PageOffline(). + */ +static DECLARE_RWSEM(page_offline_rwsem); + +void page_offline_freeze(void) +{ + down_read(&page_offline_rwsem); +} + +void page_offline_thaw(void) +{ + up_read(&page_offline_rwsem); +} + +void page_offline_begin(void) +{ + down_write(&page_offline_rwsem); +} +EXPORT_SYMBOL(page_offline_begin); + +void page_offline_end(void) +{ + up_write(&page_offline_rwsem); +} +EXPORT_SYMBOL(page_offline_end); diff --git a/mm/vmalloc.c b/mm/vmalloc.c index b2ec7f751bd0..d5cd52805149 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -25,6 +25,7 @@ #include #include #include +#include #include #include #include @@ -36,6 +37,7 @@ #include #include #include +#include #include #include @@ -83,10 +85,11 @@ static void free_work(struct work_struct *w) /*** Page table manipulation functions ***/ static int vmap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, phys_addr_t phys_addr, pgprot_t prot, - pgtbl_mod_mask *mask) + unsigned int max_page_shift, pgtbl_mod_mask *mask) { pte_t *pte; u64 pfn; + unsigned long size = PAGE_SIZE; pfn = phys_addr >> PAGE_SHIFT; pte = pte_alloc_kernel_track(pmd, addr, mask); @@ -94,9 +97,22 @@ static int vmap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, return -ENOMEM; do { BUG_ON(!pte_none(*pte)); + +#ifdef CONFIG_HUGETLB_PAGE + size = arch_vmap_pte_range_map_size(addr, end, pfn, max_page_shift); + if (size != PAGE_SIZE) { + pte_t entry = pfn_pte(pfn, prot); + + entry = pte_mkhuge(entry); + entry = arch_make_huge_pte(entry, ilog2(size), 0); + set_huge_pte_at(&init_mm, addr, pte, entry); + pfn += PFN_DOWN(size); + continue; + } +#endif set_pte_at(&init_mm, addr, pte, pfn_pte(pfn, prot)); pfn++; - } while (pte++, addr += PAGE_SIZE, addr != end); + } while (pte += PFN_DOWN(size), addr += size, addr != end); *mask |= PGTBL_PTE_MODIFIED; return 0; } @@ -145,7 +161,7 @@ static int vmap_pmd_range(pud_t *pud, unsigned long addr, unsigned long end, continue; } - if (vmap_pte_range(pmd, addr, next, phys_addr, prot, mask)) + if (vmap_pte_range(pmd, addr, next, phys_addr, prot, max_page_shift, mask)) return -ENOMEM; } while (pmd++, phys_addr += (next - addr), addr = next, addr != end); return 0; @@ -1592,6 +1608,7 @@ static DEFINE_MUTEX(vmap_purge_lock); /* for per-CPU blocks */ static void purge_fragmented_blocks_allcpus(void); +#ifdef CONFIG_X86_64 /* * called before a call to iounmap() if the caller wants vm_area_struct's * immediately freed. @@ -1600,6 +1617,7 @@ void set_iounmap_nonlazy(void) { atomic_long_set(&vmap_lazy_nr, lazy_max_pages()+1); } +#endif /* CONFIG_X86_64 */ /* * Purges all lazily-freed vmap areas. @@ -2912,8 +2930,7 @@ void *__vmalloc_node_range(unsigned long size, unsigned long align, return NULL; } - if (vmap_allow_huge && !(vm_flags & VM_NO_HUGE_VMAP) && - arch_vmap_pmd_supported(prot)) { + if (vmap_allow_huge && !(vm_flags & VM_NO_HUGE_VMAP)) { unsigned long size_per_node; /* @@ -2926,11 +2943,13 @@ void *__vmalloc_node_range(unsigned long size, unsigned long align, size_per_node = size; if (node == NUMA_NO_NODE) size_per_node /= num_online_nodes(); - if (size_per_node >= PMD_SIZE) { + if (arch_vmap_pmd_supported(prot) && size_per_node >= PMD_SIZE) shift = PMD_SHIFT; - align = max(real_align, 1UL << shift); - size = ALIGN(real_size, 1UL << shift); - } + else + shift = arch_vmap_pte_supported_shift(size_per_node); + + align = max(real_align, 1UL << shift); + size = ALIGN(real_size, 1UL << shift); } again: diff --git a/mm/vmscan.c b/mm/vmscan.c index d7c3cb8688dd..4620df62f0ff 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1499,7 +1499,8 @@ static unsigned int shrink_page_list(struct list_head *page_list, if (unlikely(PageTransHuge(page))) flags |= TTU_SPLIT_HUGE_PMD; - if (!try_to_unmap(page, flags)) { + try_to_unmap(page, flags); + if (page_mapped(page)) { stat->nr_unmap_fail += nr_pages; if (!was_swapbacked && PageSwapBacked(page)) stat->nr_lazyfree_fail += nr_pages; @@ -1701,6 +1702,7 @@ unsigned int reclaim_clean_pages_from_list(struct zone *zone, unsigned int nr_reclaimed; struct page *page, *next; LIST_HEAD(clean_pages); + unsigned int noreclaim_flag; list_for_each_entry_safe(page, next, page_list, lru) { if (!PageHuge(page) && page_is_file_lru(page) && @@ -1711,8 +1713,17 @@ unsigned int reclaim_clean_pages_from_list(struct zone *zone, } } + /* + * We should be safe here since we are only dealing with file pages and + * we are not kswapd and therefore cannot write dirty file pages. But + * call memalloc_noreclaim_save() anyway, just in case these conditions + * change in the future. + */ + noreclaim_flag = memalloc_noreclaim_save(); nr_reclaimed = shrink_page_list(&clean_pages, zone->zone_pgdat, &sc, &stat, true); + memalloc_noreclaim_restore(noreclaim_flag); + list_splice(&clean_pages, page_list); mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_FILE, -(long)nr_reclaimed); @@ -1810,7 +1821,7 @@ static __always_inline void update_lru_sizes(struct lruvec *lruvec, } -/** +/* * Isolating page from the lruvec to fill in @dst list by nr_to_scan times. * * lruvec->lru_lock is heavily contended. Some of the functions that @@ -2306,6 +2317,7 @@ unsigned long reclaim_pages(struct list_head *page_list) LIST_HEAD(node_page_list); struct reclaim_stat dummy_stat; struct page *page; + unsigned int noreclaim_flag; struct scan_control sc = { .gfp_mask = GFP_KERNEL, .priority = DEF_PRIORITY, @@ -2314,6 +2326,8 @@ unsigned long reclaim_pages(struct list_head *page_list) .may_swap = 1, }; + noreclaim_flag = memalloc_noreclaim_save(); + while (!list_empty(page_list)) { page = lru_to_page(page_list); if (nid == NUMA_NO_NODE) { @@ -2350,6 +2364,8 @@ unsigned long reclaim_pages(struct list_head *page_list) } } + memalloc_noreclaim_restore(noreclaim_flag); + return nr_reclaimed; } diff --git a/mm/workingset.c b/mm/workingset.c index 4f7a306ce75a..5ba3e42446fa 100644 --- a/mm/workingset.c +++ b/mm/workingset.c @@ -168,8 +168,10 @@ * refault distance will immediately activate the refaulting page. */ +#define WORKINGSET_SHIFT 1 #define EVICTION_SHIFT ((BITS_PER_LONG - BITS_PER_XA_VALUE) + \ - 1 + NODES_SHIFT + MEM_CGROUP_ID_SHIFT) + WORKINGSET_SHIFT + NODES_SHIFT + \ + MEM_CGROUP_ID_SHIFT) #define EVICTION_MASK (~0UL >> EVICTION_SHIFT) /* @@ -189,7 +191,7 @@ static void *pack_shadow(int memcgid, pg_data_t *pgdat, unsigned long eviction, eviction &= EVICTION_MASK; eviction = (eviction << MEM_CGROUP_ID_SHIFT) | memcgid; eviction = (eviction << NODES_SHIFT) | pgdat->node_id; - eviction = (eviction << 1) | workingset; + eviction = (eviction << WORKINGSET_SHIFT) | workingset; return xa_mk_value(eviction); } @@ -201,8 +203,8 @@ static void unpack_shadow(void *shadow, int *memcgidp, pg_data_t **pgdat, int memcgid, nid; bool workingset; - workingset = entry & 1; - entry >>= 1; + workingset = entry & ((1UL << WORKINGSET_SHIFT) - 1); + entry >>= WORKINGSET_SHIFT; nid = entry & ((1UL << NODES_SHIFT) - 1); entry >>= NODES_SHIFT; memcgid = entry & ((1UL << MEM_CGROUP_ID_SHIFT) - 1); diff --git a/mm/z3fold.c b/mm/z3fold.c index 7fe7adaaad01..b3c0577b8095 100644 --- a/mm/z3fold.c +++ b/mm/z3fold.c @@ -62,7 +62,7 @@ #define ZHDR_SIZE_ALIGNED round_up(sizeof(struct z3fold_header), CHUNK_SIZE) #define ZHDR_CHUNKS (ZHDR_SIZE_ALIGNED >> CHUNK_SHIFT) #define TOTAL_CHUNKS (PAGE_SIZE >> CHUNK_SHIFT) -#define NCHUNKS ((PAGE_SIZE - ZHDR_SIZE_ALIGNED) >> CHUNK_SHIFT) +#define NCHUNKS (TOTAL_CHUNKS - ZHDR_CHUNKS) #define BUDDY_MASK (0x3) #define BUDDY_SHIFT 2 @@ -144,6 +144,8 @@ struct z3fold_header { * @c_handle: cache for z3fold_buddy_slots allocation * @ops: pointer to a structure of user defined operations specified at * pool creation time. + * @zpool: zpool driver + * @zpool_ops: zpool operations structure with an evict callback * @compact_wq: workqueue for page layout background optimization * @release_wq: workqueue for safe page release * @work: work_struct for safe page release @@ -253,9 +255,8 @@ static inline void z3fold_page_unlock(struct z3fold_header *zhdr) spin_unlock(&zhdr->page_lock); } - -static inline struct z3fold_header *__get_z3fold_header(unsigned long handle, - bool lock) +/* return locked z3fold page if it's not headless */ +static inline struct z3fold_header *get_z3fold_header(unsigned long handle) { struct z3fold_buddy_slots *slots; struct z3fold_header *zhdr; @@ -269,13 +270,12 @@ static inline struct z3fold_header *__get_z3fold_header(unsigned long handle, read_lock(&slots->lock); addr = *(unsigned long *)handle; zhdr = (struct z3fold_header *)(addr & PAGE_MASK); - if (lock) - locked = z3fold_page_trylock(zhdr); + locked = z3fold_page_trylock(zhdr); read_unlock(&slots->lock); if (locked) break; cpu_relax(); - } while (lock); + } while (true); } else { zhdr = (struct z3fold_header *)(handle & PAGE_MASK); } @@ -283,18 +283,6 @@ static inline struct z3fold_header *__get_z3fold_header(unsigned long handle, return zhdr; } -/* Returns the z3fold page where a given handle is stored */ -static inline struct z3fold_header *handle_to_z3fold_header(unsigned long h) -{ - return __get_z3fold_header(h, false); -} - -/* return locked z3fold page if it's not headless */ -static inline struct z3fold_header *get_z3fold_header(unsigned long h) -{ - return __get_z3fold_header(h, true); -} - static inline void put_z3fold_header(struct z3fold_header *zhdr) { struct page *page = virt_to_page(zhdr); @@ -998,7 +986,8 @@ static struct z3fold_pool *z3fold_create_pool(const char *name, gfp_t gfp, goto out_c; spin_lock_init(&pool->lock); spin_lock_init(&pool->stale_lock); - pool->unbuddied = __alloc_percpu(sizeof(struct list_head)*NCHUNKS, 2); + pool->unbuddied = __alloc_percpu(sizeof(struct list_head) * NCHUNKS, + __alignof__(struct list_head)); if (!pool->unbuddied) goto out_pool; for_each_possible_cpu(cpu) { @@ -1059,6 +1048,7 @@ static void z3fold_destroy_pool(struct z3fold_pool *pool) destroy_workqueue(pool->compact_wq); destroy_workqueue(pool->release_wq); z3fold_unregister_migration(pool); + free_percpu(pool->unbuddied); kfree(pool); } @@ -1382,7 +1372,7 @@ static int z3fold_reclaim_page(struct z3fold_pool *pool, unsigned int retries) if (zhdr->foreign_handles || test_and_set_bit(PAGE_CLAIMED, &page->private)) { if (kref_put(&zhdr->refcount, - release_z3fold_page)) + release_z3fold_page_locked)) atomic64_dec(&pool->pages_nr); else z3fold_page_unlock(zhdr); @@ -1803,8 +1793,11 @@ static int __init init_z3fold(void) { int ret; - /* Make sure the z3fold header is not larger than the page size */ - BUILD_BUG_ON(ZHDR_SIZE_ALIGNED > PAGE_SIZE); + /* + * Make sure the z3fold header is not larger than the page size and + * there has remaining spaces for its buddy. + */ + BUILD_BUG_ON(ZHDR_SIZE_ALIGNED > PAGE_SIZE - CHUNK_SIZE); ret = z3fold_mount(); if (ret) return ret; diff --git a/mm/zbud.c b/mm/zbud.c index 7ec5f27a68b0..6348932430b8 100644 --- a/mm/zbud.c +++ b/mm/zbud.c @@ -51,7 +51,6 @@ #include #include #include -#include #include /***************** @@ -73,6 +72,12 @@ #define ZHDR_SIZE_ALIGNED CHUNK_SIZE #define NCHUNKS ((PAGE_SIZE - ZHDR_SIZE_ALIGNED) >> CHUNK_SHIFT) +struct zbud_pool; + +struct zbud_ops { + int (*evict)(struct zbud_pool *pool, unsigned long handle); +}; + /** * struct zbud_pool - stores metadata for each zbud pool * @lock: protects all pool fields and first|last_chunk fields of any @@ -87,21 +92,27 @@ * @pages_nr: number of zbud pages in the pool. * @ops: pointer to a structure of user defined operations specified at * pool creation time. + * @zpool: zpool driver + * @zpool_ops: zpool operations structure with an evict callback * * This structure is allocated at pool creation time and maintains metadata * pertaining to a particular zbud pool. */ struct zbud_pool { spinlock_t lock; - struct list_head unbuddied[NCHUNKS]; - struct list_head buddied; + union { + /* + * Reuse unbuddied[0] as buddied on the ground that + * unbuddied[0] is unused. + */ + struct list_head buddied; + struct list_head unbuddied[NCHUNKS]; + }; struct list_head lru; u64 pages_nr; const struct zbud_ops *ops; -#ifdef CONFIG_ZPOOL struct zpool *zpool; const struct zpool_ops *zpool_ops; -#endif }; /* @@ -120,12 +131,399 @@ struct zbud_header { bool under_reclaim; }; +/***************** + * Helpers +*****************/ +/* Just to make the code easier to read */ +enum buddy { + FIRST, + LAST +}; + +/* Converts an allocation size in bytes to size in zbud chunks */ +static int size_to_chunks(size_t size) +{ + return (size + CHUNK_SIZE - 1) >> CHUNK_SHIFT; +} + +#define for_each_unbuddied_list(_iter, _begin) \ + for ((_iter) = (_begin); (_iter) < NCHUNKS; (_iter)++) + +/* Initializes the zbud header of a newly allocated zbud page */ +static struct zbud_header *init_zbud_page(struct page *page) +{ + struct zbud_header *zhdr = page_address(page); + zhdr->first_chunks = 0; + zhdr->last_chunks = 0; + INIT_LIST_HEAD(&zhdr->buddy); + INIT_LIST_HEAD(&zhdr->lru); + zhdr->under_reclaim = false; + return zhdr; +} + +/* Resets the struct page fields and frees the page */ +static void free_zbud_page(struct zbud_header *zhdr) +{ + __free_page(virt_to_page(zhdr)); +} + +/* + * Encodes the handle of a particular buddy within a zbud page + * Pool lock should be held as this function accesses first|last_chunks + */ +static unsigned long encode_handle(struct zbud_header *zhdr, enum buddy bud) +{ + unsigned long handle; + + /* + * For now, the encoded handle is actually just the pointer to the data + * but this might not always be the case. A little information hiding. + * Add CHUNK_SIZE to the handle if it is the first allocation to jump + * over the zbud header in the first chunk. + */ + handle = (unsigned long)zhdr; + if (bud == FIRST) + /* skip over zbud header */ + handle += ZHDR_SIZE_ALIGNED; + else /* bud == LAST */ + handle += PAGE_SIZE - (zhdr->last_chunks << CHUNK_SHIFT); + return handle; +} + +/* Returns the zbud page where a given handle is stored */ +static struct zbud_header *handle_to_zbud_header(unsigned long handle) +{ + return (struct zbud_header *)(handle & PAGE_MASK); +} + +/* Returns the number of free chunks in a zbud page */ +static int num_free_chunks(struct zbud_header *zhdr) +{ + /* + * Rather than branch for different situations, just use the fact that + * free buddies have a length of zero to simplify everything. + */ + return NCHUNKS - zhdr->first_chunks - zhdr->last_chunks; +} + +/***************** + * API Functions +*****************/ +/** + * zbud_create_pool() - create a new zbud pool + * @gfp: gfp flags when allocating the zbud pool structure + * @ops: user-defined operations for the zbud pool + * + * Return: pointer to the new zbud pool or NULL if the metadata allocation + * failed. + */ +static struct zbud_pool *zbud_create_pool(gfp_t gfp, const struct zbud_ops *ops) +{ + struct zbud_pool *pool; + int i; + + pool = kzalloc(sizeof(struct zbud_pool), gfp); + if (!pool) + return NULL; + spin_lock_init(&pool->lock); + for_each_unbuddied_list(i, 0) + INIT_LIST_HEAD(&pool->unbuddied[i]); + INIT_LIST_HEAD(&pool->buddied); + INIT_LIST_HEAD(&pool->lru); + pool->pages_nr = 0; + pool->ops = ops; + return pool; +} + +/** + * zbud_destroy_pool() - destroys an existing zbud pool + * @pool: the zbud pool to be destroyed + * + * The pool should be emptied before this function is called. + */ +static void zbud_destroy_pool(struct zbud_pool *pool) +{ + kfree(pool); +} + +/** + * zbud_alloc() - allocates a region of a given size + * @pool: zbud pool from which to allocate + * @size: size in bytes of the desired allocation + * @gfp: gfp flags used if the pool needs to grow + * @handle: handle of the new allocation + * + * This function will attempt to find a free region in the pool large enough to + * satisfy the allocation request. A search of the unbuddied lists is + * performed first. If no suitable free region is found, then a new page is + * allocated and added to the pool to satisfy the request. + * + * gfp should not set __GFP_HIGHMEM as highmem pages cannot be used + * as zbud pool pages. + * + * Return: 0 if success and handle is set, otherwise -EINVAL if the size or + * gfp arguments are invalid or -ENOMEM if the pool was unable to allocate + * a new page. + */ +static int zbud_alloc(struct zbud_pool *pool, size_t size, gfp_t gfp, + unsigned long *handle) +{ + int chunks, i, freechunks; + struct zbud_header *zhdr = NULL; + enum buddy bud; + struct page *page; + + if (!size || (gfp & __GFP_HIGHMEM)) + return -EINVAL; + if (size > PAGE_SIZE - ZHDR_SIZE_ALIGNED - CHUNK_SIZE) + return -ENOSPC; + chunks = size_to_chunks(size); + spin_lock(&pool->lock); + + /* First, try to find an unbuddied zbud page. */ + for_each_unbuddied_list(i, chunks) { + if (!list_empty(&pool->unbuddied[i])) { + zhdr = list_first_entry(&pool->unbuddied[i], + struct zbud_header, buddy); + list_del(&zhdr->buddy); + if (zhdr->first_chunks == 0) + bud = FIRST; + else + bud = LAST; + goto found; + } + } + + /* Couldn't find unbuddied zbud page, create new one */ + spin_unlock(&pool->lock); + page = alloc_page(gfp); + if (!page) + return -ENOMEM; + spin_lock(&pool->lock); + pool->pages_nr++; + zhdr = init_zbud_page(page); + bud = FIRST; + +found: + if (bud == FIRST) + zhdr->first_chunks = chunks; + else + zhdr->last_chunks = chunks; + + if (zhdr->first_chunks == 0 || zhdr->last_chunks == 0) { + /* Add to unbuddied list */ + freechunks = num_free_chunks(zhdr); + list_add(&zhdr->buddy, &pool->unbuddied[freechunks]); + } else { + /* Add to buddied list */ + list_add(&zhdr->buddy, &pool->buddied); + } + + /* Add/move zbud page to beginning of LRU */ + if (!list_empty(&zhdr->lru)) + list_del(&zhdr->lru); + list_add(&zhdr->lru, &pool->lru); + + *handle = encode_handle(zhdr, bud); + spin_unlock(&pool->lock); + + return 0; +} + +/** + * zbud_free() - frees the allocation associated with the given handle + * @pool: pool in which the allocation resided + * @handle: handle associated with the allocation returned by zbud_alloc() + * + * In the case that the zbud page in which the allocation resides is under + * reclaim, as indicated by the PG_reclaim flag being set, this function + * only sets the first|last_chunks to 0. The page is actually freed + * once both buddies are evicted (see zbud_reclaim_page() below). + */ +static void zbud_free(struct zbud_pool *pool, unsigned long handle) +{ + struct zbud_header *zhdr; + int freechunks; + + spin_lock(&pool->lock); + zhdr = handle_to_zbud_header(handle); + + /* If first buddy, handle will be page aligned */ + if ((handle - ZHDR_SIZE_ALIGNED) & ~PAGE_MASK) + zhdr->last_chunks = 0; + else + zhdr->first_chunks = 0; + + if (zhdr->under_reclaim) { + /* zbud page is under reclaim, reclaim will free */ + spin_unlock(&pool->lock); + return; + } + + /* Remove from existing buddy list */ + list_del(&zhdr->buddy); + + if (zhdr->first_chunks == 0 && zhdr->last_chunks == 0) { + /* zbud page is empty, free */ + list_del(&zhdr->lru); + free_zbud_page(zhdr); + pool->pages_nr--; + } else { + /* Add to unbuddied list */ + freechunks = num_free_chunks(zhdr); + list_add(&zhdr->buddy, &pool->unbuddied[freechunks]); + } + + spin_unlock(&pool->lock); +} + +/** + * zbud_reclaim_page() - evicts allocations from a pool page and frees it + * @pool: pool from which a page will attempt to be evicted + * @retries: number of pages on the LRU list for which eviction will + * be attempted before failing + * + * zbud reclaim is different from normal system reclaim in that the reclaim is + * done from the bottom, up. This is because only the bottom layer, zbud, has + * information on how the allocations are organized within each zbud page. This + * has the potential to create interesting locking situations between zbud and + * the user, however. + * + * To avoid these, this is how zbud_reclaim_page() should be called: + * + * The user detects a page should be reclaimed and calls zbud_reclaim_page(). + * zbud_reclaim_page() will remove a zbud page from the pool LRU list and call + * the user-defined eviction handler with the pool and handle as arguments. + * + * If the handle can not be evicted, the eviction handler should return + * non-zero. zbud_reclaim_page() will add the zbud page back to the + * appropriate list and try the next zbud page on the LRU up to + * a user defined number of retries. + * + * If the handle is successfully evicted, the eviction handler should + * return 0 _and_ should have called zbud_free() on the handle. zbud_free() + * contains logic to delay freeing the page if the page is under reclaim, + * as indicated by the setting of the PG_reclaim flag on the underlying page. + * + * If all buddies in the zbud page are successfully evicted, then the + * zbud page can be freed. + * + * Returns: 0 if page is successfully freed, otherwise -EINVAL if there are + * no pages to evict or an eviction handler is not registered, -EAGAIN if + * the retry limit was hit. + */ +static int zbud_reclaim_page(struct zbud_pool *pool, unsigned int retries) +{ + int i, ret, freechunks; + struct zbud_header *zhdr; + unsigned long first_handle = 0, last_handle = 0; + + spin_lock(&pool->lock); + if (!pool->ops || !pool->ops->evict || list_empty(&pool->lru) || + retries == 0) { + spin_unlock(&pool->lock); + return -EINVAL; + } + for (i = 0; i < retries; i++) { + zhdr = list_last_entry(&pool->lru, struct zbud_header, lru); + list_del(&zhdr->lru); + list_del(&zhdr->buddy); + /* Protect zbud page against free */ + zhdr->under_reclaim = true; + /* + * We need encode the handles before unlocking, since we can + * race with free that will set (first|last)_chunks to 0 + */ + first_handle = 0; + last_handle = 0; + if (zhdr->first_chunks) + first_handle = encode_handle(zhdr, FIRST); + if (zhdr->last_chunks) + last_handle = encode_handle(zhdr, LAST); + spin_unlock(&pool->lock); + + /* Issue the eviction callback(s) */ + if (first_handle) { + ret = pool->ops->evict(pool, first_handle); + if (ret) + goto next; + } + if (last_handle) { + ret = pool->ops->evict(pool, last_handle); + if (ret) + goto next; + } +next: + spin_lock(&pool->lock); + zhdr->under_reclaim = false; + if (zhdr->first_chunks == 0 && zhdr->last_chunks == 0) { + /* + * Both buddies are now free, free the zbud page and + * return success. + */ + free_zbud_page(zhdr); + pool->pages_nr--; + spin_unlock(&pool->lock); + return 0; + } else if (zhdr->first_chunks == 0 || + zhdr->last_chunks == 0) { + /* add to unbuddied list */ + freechunks = num_free_chunks(zhdr); + list_add(&zhdr->buddy, &pool->unbuddied[freechunks]); + } else { + /* add to buddied list */ + list_add(&zhdr->buddy, &pool->buddied); + } + + /* add to beginning of LRU */ + list_add(&zhdr->lru, &pool->lru); + } + spin_unlock(&pool->lock); + return -EAGAIN; +} + +/** + * zbud_map() - maps the allocation associated with the given handle + * @pool: pool in which the allocation resides + * @handle: handle associated with the allocation to be mapped + * + * While trivial for zbud, the mapping functions for others allocators + * implementing this allocation API could have more complex information encoded + * in the handle and could create temporary mappings to make the data + * accessible to the user. + * + * Returns: a pointer to the mapped allocation + */ +static void *zbud_map(struct zbud_pool *pool, unsigned long handle) +{ + return (void *)(handle); +} + +/** + * zbud_unmap() - maps the allocation associated with the given handle + * @pool: pool in which the allocation resides + * @handle: handle associated with the allocation to be unmapped + */ +static void zbud_unmap(struct zbud_pool *pool, unsigned long handle) +{ +} + +/** + * zbud_get_pool_size() - gets the zbud pool size in pages + * @pool: pool whose size is being queried + * + * Returns: size in pages of the given pool. The pool lock need not be + * taken to access pages_nr. + */ +static u64 zbud_get_pool_size(struct zbud_pool *pool) +{ + return pool->pages_nr; +} + /***************** * zpool ****************/ -#ifdef CONFIG_ZPOOL - static int zbud_zpool_evict(struct zbud_pool *pool, unsigned long handle) { if (pool->zpool && pool->zpool_ops && pool->zpool_ops->evict) @@ -216,396 +614,6 @@ static struct zpool_driver zbud_zpool_driver = { }; MODULE_ALIAS("zpool-zbud"); -#endif /* CONFIG_ZPOOL */ - -/***************** - * Helpers -*****************/ -/* Just to make the code easier to read */ -enum buddy { - FIRST, - LAST -}; - -/* Converts an allocation size in bytes to size in zbud chunks */ -static int size_to_chunks(size_t size) -{ - return (size + CHUNK_SIZE - 1) >> CHUNK_SHIFT; -} - -#define for_each_unbuddied_list(_iter, _begin) \ - for ((_iter) = (_begin); (_iter) < NCHUNKS; (_iter)++) - -/* Initializes the zbud header of a newly allocated zbud page */ -static struct zbud_header *init_zbud_page(struct page *page) -{ - struct zbud_header *zhdr = page_address(page); - zhdr->first_chunks = 0; - zhdr->last_chunks = 0; - INIT_LIST_HEAD(&zhdr->buddy); - INIT_LIST_HEAD(&zhdr->lru); - zhdr->under_reclaim = false; - return zhdr; -} - -/* Resets the struct page fields and frees the page */ -static void free_zbud_page(struct zbud_header *zhdr) -{ - __free_page(virt_to_page(zhdr)); -} - -/* - * Encodes the handle of a particular buddy within a zbud page - * Pool lock should be held as this function accesses first|last_chunks - */ -static unsigned long encode_handle(struct zbud_header *zhdr, enum buddy bud) -{ - unsigned long handle; - - /* - * For now, the encoded handle is actually just the pointer to the data - * but this might not always be the case. A little information hiding. - * Add CHUNK_SIZE to the handle if it is the first allocation to jump - * over the zbud header in the first chunk. - */ - handle = (unsigned long)zhdr; - if (bud == FIRST) - /* skip over zbud header */ - handle += ZHDR_SIZE_ALIGNED; - else /* bud == LAST */ - handle += PAGE_SIZE - (zhdr->last_chunks << CHUNK_SHIFT); - return handle; -} - -/* Returns the zbud page where a given handle is stored */ -static struct zbud_header *handle_to_zbud_header(unsigned long handle) -{ - return (struct zbud_header *)(handle & PAGE_MASK); -} - -/* Returns the number of free chunks in a zbud page */ -static int num_free_chunks(struct zbud_header *zhdr) -{ - /* - * Rather than branch for different situations, just use the fact that - * free buddies have a length of zero to simplify everything. - */ - return NCHUNKS - zhdr->first_chunks - zhdr->last_chunks; -} - -/***************** - * API Functions -*****************/ -/** - * zbud_create_pool() - create a new zbud pool - * @gfp: gfp flags when allocating the zbud pool structure - * @ops: user-defined operations for the zbud pool - * - * Return: pointer to the new zbud pool or NULL if the metadata allocation - * failed. - */ -struct zbud_pool *zbud_create_pool(gfp_t gfp, const struct zbud_ops *ops) -{ - struct zbud_pool *pool; - int i; - - pool = kzalloc(sizeof(struct zbud_pool), gfp); - if (!pool) - return NULL; - spin_lock_init(&pool->lock); - for_each_unbuddied_list(i, 0) - INIT_LIST_HEAD(&pool->unbuddied[i]); - INIT_LIST_HEAD(&pool->buddied); - INIT_LIST_HEAD(&pool->lru); - pool->pages_nr = 0; - pool->ops = ops; - return pool; -} - -/** - * zbud_destroy_pool() - destroys an existing zbud pool - * @pool: the zbud pool to be destroyed - * - * The pool should be emptied before this function is called. - */ -void zbud_destroy_pool(struct zbud_pool *pool) -{ - kfree(pool); -} - -/** - * zbud_alloc() - allocates a region of a given size - * @pool: zbud pool from which to allocate - * @size: size in bytes of the desired allocation - * @gfp: gfp flags used if the pool needs to grow - * @handle: handle of the new allocation - * - * This function will attempt to find a free region in the pool large enough to - * satisfy the allocation request. A search of the unbuddied lists is - * performed first. If no suitable free region is found, then a new page is - * allocated and added to the pool to satisfy the request. - * - * gfp should not set __GFP_HIGHMEM as highmem pages cannot be used - * as zbud pool pages. - * - * Return: 0 if success and handle is set, otherwise -EINVAL if the size or - * gfp arguments are invalid or -ENOMEM if the pool was unable to allocate - * a new page. - */ -int zbud_alloc(struct zbud_pool *pool, size_t size, gfp_t gfp, - unsigned long *handle) -{ - int chunks, i, freechunks; - struct zbud_header *zhdr = NULL; - enum buddy bud; - struct page *page; - - if (!size || (gfp & __GFP_HIGHMEM)) - return -EINVAL; - if (size > PAGE_SIZE - ZHDR_SIZE_ALIGNED - CHUNK_SIZE) - return -ENOSPC; - chunks = size_to_chunks(size); - spin_lock(&pool->lock); - - /* First, try to find an unbuddied zbud page. */ - for_each_unbuddied_list(i, chunks) { - if (!list_empty(&pool->unbuddied[i])) { - zhdr = list_first_entry(&pool->unbuddied[i], - struct zbud_header, buddy); - list_del(&zhdr->buddy); - if (zhdr->first_chunks == 0) - bud = FIRST; - else - bud = LAST; - goto found; - } - } - - /* Couldn't find unbuddied zbud page, create new one */ - spin_unlock(&pool->lock); - page = alloc_page(gfp); - if (!page) - return -ENOMEM; - spin_lock(&pool->lock); - pool->pages_nr++; - zhdr = init_zbud_page(page); - bud = FIRST; - -found: - if (bud == FIRST) - zhdr->first_chunks = chunks; - else - zhdr->last_chunks = chunks; - - if (zhdr->first_chunks == 0 || zhdr->last_chunks == 0) { - /* Add to unbuddied list */ - freechunks = num_free_chunks(zhdr); - list_add(&zhdr->buddy, &pool->unbuddied[freechunks]); - } else { - /* Add to buddied list */ - list_add(&zhdr->buddy, &pool->buddied); - } - - /* Add/move zbud page to beginning of LRU */ - if (!list_empty(&zhdr->lru)) - list_del(&zhdr->lru); - list_add(&zhdr->lru, &pool->lru); - - *handle = encode_handle(zhdr, bud); - spin_unlock(&pool->lock); - - return 0; -} - -/** - * zbud_free() - frees the allocation associated with the given handle - * @pool: pool in which the allocation resided - * @handle: handle associated with the allocation returned by zbud_alloc() - * - * In the case that the zbud page in which the allocation resides is under - * reclaim, as indicated by the PG_reclaim flag being set, this function - * only sets the first|last_chunks to 0. The page is actually freed - * once both buddies are evicted (see zbud_reclaim_page() below). - */ -void zbud_free(struct zbud_pool *pool, unsigned long handle) -{ - struct zbud_header *zhdr; - int freechunks; - - spin_lock(&pool->lock); - zhdr = handle_to_zbud_header(handle); - - /* If first buddy, handle will be page aligned */ - if ((handle - ZHDR_SIZE_ALIGNED) & ~PAGE_MASK) - zhdr->last_chunks = 0; - else - zhdr->first_chunks = 0; - - if (zhdr->under_reclaim) { - /* zbud page is under reclaim, reclaim will free */ - spin_unlock(&pool->lock); - return; - } - - /* Remove from existing buddy list */ - list_del(&zhdr->buddy); - - if (zhdr->first_chunks == 0 && zhdr->last_chunks == 0) { - /* zbud page is empty, free */ - list_del(&zhdr->lru); - free_zbud_page(zhdr); - pool->pages_nr--; - } else { - /* Add to unbuddied list */ - freechunks = num_free_chunks(zhdr); - list_add(&zhdr->buddy, &pool->unbuddied[freechunks]); - } - - spin_unlock(&pool->lock); -} - -/** - * zbud_reclaim_page() - evicts allocations from a pool page and frees it - * @pool: pool from which a page will attempt to be evicted - * @retries: number of pages on the LRU list for which eviction will - * be attempted before failing - * - * zbud reclaim is different from normal system reclaim in that the reclaim is - * done from the bottom, up. This is because only the bottom layer, zbud, has - * information on how the allocations are organized within each zbud page. This - * has the potential to create interesting locking situations between zbud and - * the user, however. - * - * To avoid these, this is how zbud_reclaim_page() should be called: - * - * The user detects a page should be reclaimed and calls zbud_reclaim_page(). - * zbud_reclaim_page() will remove a zbud page from the pool LRU list and call - * the user-defined eviction handler with the pool and handle as arguments. - * - * If the handle can not be evicted, the eviction handler should return - * non-zero. zbud_reclaim_page() will add the zbud page back to the - * appropriate list and try the next zbud page on the LRU up to - * a user defined number of retries. - * - * If the handle is successfully evicted, the eviction handler should - * return 0 _and_ should have called zbud_free() on the handle. zbud_free() - * contains logic to delay freeing the page if the page is under reclaim, - * as indicated by the setting of the PG_reclaim flag on the underlying page. - * - * If all buddies in the zbud page are successfully evicted, then the - * zbud page can be freed. - * - * Returns: 0 if page is successfully freed, otherwise -EINVAL if there are - * no pages to evict or an eviction handler is not registered, -EAGAIN if - * the retry limit was hit. - */ -int zbud_reclaim_page(struct zbud_pool *pool, unsigned int retries) -{ - int i, ret, freechunks; - struct zbud_header *zhdr; - unsigned long first_handle = 0, last_handle = 0; - - spin_lock(&pool->lock); - if (!pool->ops || !pool->ops->evict || list_empty(&pool->lru) || - retries == 0) { - spin_unlock(&pool->lock); - return -EINVAL; - } - for (i = 0; i < retries; i++) { - zhdr = list_last_entry(&pool->lru, struct zbud_header, lru); - list_del(&zhdr->lru); - list_del(&zhdr->buddy); - /* Protect zbud page against free */ - zhdr->under_reclaim = true; - /* - * We need encode the handles before unlocking, since we can - * race with free that will set (first|last)_chunks to 0 - */ - first_handle = 0; - last_handle = 0; - if (zhdr->first_chunks) - first_handle = encode_handle(zhdr, FIRST); - if (zhdr->last_chunks) - last_handle = encode_handle(zhdr, LAST); - spin_unlock(&pool->lock); - - /* Issue the eviction callback(s) */ - if (first_handle) { - ret = pool->ops->evict(pool, first_handle); - if (ret) - goto next; - } - if (last_handle) { - ret = pool->ops->evict(pool, last_handle); - if (ret) - goto next; - } -next: - spin_lock(&pool->lock); - zhdr->under_reclaim = false; - if (zhdr->first_chunks == 0 && zhdr->last_chunks == 0) { - /* - * Both buddies are now free, free the zbud page and - * return success. - */ - free_zbud_page(zhdr); - pool->pages_nr--; - spin_unlock(&pool->lock); - return 0; - } else if (zhdr->first_chunks == 0 || - zhdr->last_chunks == 0) { - /* add to unbuddied list */ - freechunks = num_free_chunks(zhdr); - list_add(&zhdr->buddy, &pool->unbuddied[freechunks]); - } else { - /* add to buddied list */ - list_add(&zhdr->buddy, &pool->buddied); - } - - /* add to beginning of LRU */ - list_add(&zhdr->lru, &pool->lru); - } - spin_unlock(&pool->lock); - return -EAGAIN; -} - -/** - * zbud_map() - maps the allocation associated with the given handle - * @pool: pool in which the allocation resides - * @handle: handle associated with the allocation to be mapped - * - * While trivial for zbud, the mapping functions for others allocators - * implementing this allocation API could have more complex information encoded - * in the handle and could create temporary mappings to make the data - * accessible to the user. - * - * Returns: a pointer to the mapped allocation - */ -void *zbud_map(struct zbud_pool *pool, unsigned long handle) -{ - return (void *)(handle); -} - -/** - * zbud_unmap() - maps the allocation associated with the given handle - * @pool: pool in which the allocation resides - * @handle: handle associated with the allocation to be unmapped - */ -void zbud_unmap(struct zbud_pool *pool, unsigned long handle) -{ -} - -/** - * zbud_get_pool_size() - gets the zbud pool size in pages - * @pool: pool whose size is being queried - * - * Returns: size in pages of the given pool. The pool lock need not be - * taken to access pages_nr. - */ -u64 zbud_get_pool_size(struct zbud_pool *pool) -{ - return pool->pages_nr; -} static int __init init_zbud(void) { @@ -613,19 +621,14 @@ static int __init init_zbud(void) BUILD_BUG_ON(sizeof(struct zbud_header) > ZHDR_SIZE_ALIGNED); pr_info("loaded\n"); -#ifdef CONFIG_ZPOOL zpool_register_driver(&zbud_zpool_driver); -#endif return 0; } static void __exit exit_zbud(void) { -#ifdef CONFIG_ZPOOL zpool_unregister_driver(&zbud_zpool_driver); -#endif - pr_info("unloaded\n"); } diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c index 19b563bc6c48..68e8831068f4 100644 --- a/mm/zsmalloc.c +++ b/mm/zsmalloc.c @@ -1471,7 +1471,6 @@ static void obj_free(struct size_class *class, unsigned long obj) unsigned int f_objidx; void *vaddr; - obj &= ~OBJ_ALLOCATED_TAG; obj_to_location(obj, &f_page, &f_objidx); f_offset = (class->size * f_objidx) & ~PAGE_MASK; zspage = get_zspage(f_page); @@ -2163,7 +2162,7 @@ static void async_free_zspage(struct work_struct *work) VM_BUG_ON(fullness != ZS_EMPTY); class = pool->size_class[class_idx]; spin_lock(&class->lock); - __free_zspage(pool, pool->size_class[class_idx], zspage); + __free_zspage(pool, class, zspage); spin_unlock(&class->lock); } }; diff --git a/mm/zswap.c b/mm/zswap.c index 20763267a219..7944e3e57e78 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -967,6 +967,13 @@ static int zswap_writeback_entry(struct zpool *pool, unsigned long handle) spin_unlock(&tree->lock); BUG_ON(offset != entry->offset); + src = (u8 *)zhdr + sizeof(struct zswap_header); + if (!zpool_can_sleep_mapped(pool)) { + memcpy(tmp, src, entry->length); + src = tmp; + zpool_unmap_handle(pool, handle); + } + /* try to allocate swap cache page */ switch (zswap_get_swap_cache_page(swpentry, &page)) { case ZSWAP_SWAPCACHE_FAIL: /* no memory or invalidate happened */ @@ -982,17 +989,7 @@ static int zswap_writeback_entry(struct zpool *pool, unsigned long handle) case ZSWAP_SWAPCACHE_NEW: /* page is locked */ /* decompress */ acomp_ctx = raw_cpu_ptr(entry->pool->acomp_ctx); - dlen = PAGE_SIZE; - src = (u8 *)zhdr + sizeof(struct zswap_header); - - if (!zpool_can_sleep_mapped(pool)) { - - memcpy(tmp, src, entry->length); - src = tmp; - - zpool_unmap_handle(pool, handle); - } mutex_lock(acomp_ctx->mutex); sg_init_one(&input, src, entry->length); @@ -1203,7 +1200,7 @@ static int zswap_frontswap_store(unsigned type, pgoff_t offset, zswap_reject_alloc_fail++; goto put_dstmem; } - buf = zpool_map_handle(entry->pool->zpool, handle, ZPOOL_MM_RW); + buf = zpool_map_handle(entry->pool->zpool, handle, ZPOOL_MM_WO); memcpy(buf, &zhdr, hlen); memcpy(buf + hlen, dst, dlen); zpool_unmap_handle(entry->pool->zpool, handle); @@ -1427,18 +1424,11 @@ static int __init zswap_debugfs_init(void) return 0; } - -static void __exit zswap_debugfs_exit(void) -{ - debugfs_remove_recursive(zswap_debugfs_root); -} #else static int __init zswap_debugfs_init(void) { return 0; } - -static void __exit zswap_debugfs_exit(void) { } #endif /********************************* diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl index 23697a6b1eaa..461d4221e4a4 100755 --- a/scripts/checkpatch.pl +++ b/scripts/checkpatch.pl @@ -1084,10 +1084,10 @@ sub is_maintained_obsolete { sub is_SPDX_License_valid { my ($license) = @_; - return 1 if (!$tree || which("python") eq "" || !(-e "$root/scripts/spdxcheck.py") || !(-e "$gitroot")); + return 1 if (!$tree || which("python3") eq "" || !(-x "$root/scripts/spdxcheck.py") || !(-e "$gitroot")); my $root_path = abs_path($root); - my $status = `cd "$root_path"; echo "$license" | python scripts/spdxcheck.py -`; + my $status = `cd "$root_path"; echo "$license" | scripts/spdxcheck.py -`; return 0 if ($status ne ""); return 1; } @@ -5361,9 +5361,13 @@ sub process { } } -#goto labels aren't indented, allow a single space however - if ($line=~/^.\s+[A-Za-z\d_]+:(?![0-9]+)/ and - !($line=~/^. [A-Za-z\d_]+:/) and !($line=~/^.\s+default:/)) { +# check that goto labels aren't indented (allow a single space indentation) +# and ignore bitfield definitions like foo:1 +# Strictly, labels can have whitespace after the identifier and before the : +# but this is not allowed here as many ?: uses would appear to be labels + if ($sline =~ /^.\s+[A-Za-z_][A-Za-z\d_]*:(?!\s*\d+)/ && + $sline !~ /^. [A-Za-z\d_][A-Za-z\d_]*:/ && + $sline !~ /^.\s+default:/) { if (WARN("INDENTED_LABEL", "labels should not be indented\n" . $herecurr) && $fix) { @@ -5458,7 +5462,7 @@ sub process { # Return of what appears to be an errno should normally be negative if ($sline =~ /\breturn(?:\s*\(+\s*|\s+)(E[A-Z]+)(?:\s*\)+\s*|\s*)[;:,]/) { my $name = $1; - if ($name ne 'EOF' && $name ne 'ERROR') { + if ($name ne 'EOF' && $name ne 'ERROR' && $name !~ /^EPOLL/) { WARN("USE_NEGATIVE_ERRNO", "return of an errno should typically be negative (ie: return -$1)\n" . $herecurr); } diff --git a/tools/testing/selftests/vm/.gitignore b/tools/testing/selftests/vm/.gitignore index 1f651e85ed60..d683a49d07d5 100644 --- a/tools/testing/selftests/vm/.gitignore +++ b/tools/testing/selftests/vm/.gitignore @@ -12,6 +12,9 @@ mremap_test on-fault-limit transhuge-stress protection_keys +protection_keys_32 +protection_keys_64 +madv_populate userfaultfd mlock-intersect-test mlock-random-test diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile index 73e1cc96d7c2..812bc03e3142 100644 --- a/tools/testing/selftests/vm/Makefile +++ b/tools/testing/selftests/vm/Makefile @@ -31,6 +31,7 @@ TEST_GEN_FILES += hmm-tests TEST_GEN_FILES += hugepage-mmap TEST_GEN_FILES += hugepage-shm TEST_GEN_FILES += khugepaged +TEST_GEN_FILES += madv_populate TEST_GEN_FILES += map_fixed_noreplace TEST_GEN_FILES += map_hugetlb TEST_GEN_FILES += map_populate @@ -100,7 +101,7 @@ $(1) $(1)_64: $(OUTPUT)/$(1)_64 endef ifeq ($(CAN_BUILD_I386),1) -$(BINARIES_32): CFLAGS += -m32 +$(BINARIES_32): CFLAGS += -m32 -mxsave $(BINARIES_32): LDLIBS += -lrt -ldl -lm $(BINARIES_32): $(OUTPUT)/%_32: %.c $(CC) $(CFLAGS) $(EXTRA_CFLAGS) $(notdir $^) $(LDLIBS) -o $@ @@ -108,7 +109,7 @@ $(foreach t,$(TARGETS),$(eval $(call gen-target-rule-32,$(t)))) endif ifeq ($(CAN_BUILD_X86_64),1) -$(BINARIES_64): CFLAGS += -m64 +$(BINARIES_64): CFLAGS += -m64 -mxsave $(BINARIES_64): LDLIBS += -lrt -ldl $(BINARIES_64): $(OUTPUT)/%_64: %.c $(CC) $(CFLAGS) $(EXTRA_CFLAGS) $(notdir $^) $(LDLIBS) -o $@ diff --git a/tools/testing/selftests/vm/hmm-tests.c b/tools/testing/selftests/vm/hmm-tests.c index 5d1ac691b9f4..864f126ffd78 100644 --- a/tools/testing/selftests/vm/hmm-tests.c +++ b/tools/testing/selftests/vm/hmm-tests.c @@ -1485,4 +1485,162 @@ TEST_F(hmm2, double_map) hmm_buffer_free(buffer); } +/* + * Basic check of exclusive faulting. + */ +TEST_F(hmm, exclusive) +{ + struct hmm_buffer *buffer; + unsigned long npages; + unsigned long size; + unsigned long i; + int *ptr; + int ret; + + npages = ALIGN(HMM_BUFFER_SIZE, self->page_size) >> self->page_shift; + ASSERT_NE(npages, 0); + size = npages << self->page_shift; + + buffer = malloc(sizeof(*buffer)); + ASSERT_NE(buffer, NULL); + + buffer->fd = -1; + buffer->size = size; + buffer->mirror = malloc(size); + ASSERT_NE(buffer->mirror, NULL); + + buffer->ptr = mmap(NULL, size, + PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS, + buffer->fd, 0); + ASSERT_NE(buffer->ptr, MAP_FAILED); + + /* Initialize buffer in system memory. */ + for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i) + ptr[i] = i; + + /* Map memory exclusively for device access. */ + ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_EXCLUSIVE, buffer, npages); + ASSERT_EQ(ret, 0); + ASSERT_EQ(buffer->cpages, npages); + + /* Check what the device read. */ + for (i = 0, ptr = buffer->mirror; i < size / sizeof(*ptr); ++i) + ASSERT_EQ(ptr[i], i); + + /* Fault pages back to system memory and check them. */ + for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i) + ASSERT_EQ(ptr[i]++, i); + + for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i) + ASSERT_EQ(ptr[i], i+1); + + /* Check atomic access revoked */ + ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_CHECK_EXCLUSIVE, buffer, npages); + ASSERT_EQ(ret, 0); + + hmm_buffer_free(buffer); +} + +TEST_F(hmm, exclusive_mprotect) +{ + struct hmm_buffer *buffer; + unsigned long npages; + unsigned long size; + unsigned long i; + int *ptr; + int ret; + + npages = ALIGN(HMM_BUFFER_SIZE, self->page_size) >> self->page_shift; + ASSERT_NE(npages, 0); + size = npages << self->page_shift; + + buffer = malloc(sizeof(*buffer)); + ASSERT_NE(buffer, NULL); + + buffer->fd = -1; + buffer->size = size; + buffer->mirror = malloc(size); + ASSERT_NE(buffer->mirror, NULL); + + buffer->ptr = mmap(NULL, size, + PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS, + buffer->fd, 0); + ASSERT_NE(buffer->ptr, MAP_FAILED); + + /* Initialize buffer in system memory. */ + for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i) + ptr[i] = i; + + /* Map memory exclusively for device access. */ + ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_EXCLUSIVE, buffer, npages); + ASSERT_EQ(ret, 0); + ASSERT_EQ(buffer->cpages, npages); + + /* Check what the device read. */ + for (i = 0, ptr = buffer->mirror; i < size / sizeof(*ptr); ++i) + ASSERT_EQ(ptr[i], i); + + ret = mprotect(buffer->ptr, size, PROT_READ); + ASSERT_EQ(ret, 0); + + /* Simulate a device writing system memory. */ + ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_WRITE, buffer, npages); + ASSERT_EQ(ret, -EPERM); + + hmm_buffer_free(buffer); +} + +/* + * Check copy-on-write works. + */ +TEST_F(hmm, exclusive_cow) +{ + struct hmm_buffer *buffer; + unsigned long npages; + unsigned long size; + unsigned long i; + int *ptr; + int ret; + + npages = ALIGN(HMM_BUFFER_SIZE, self->page_size) >> self->page_shift; + ASSERT_NE(npages, 0); + size = npages << self->page_shift; + + buffer = malloc(sizeof(*buffer)); + ASSERT_NE(buffer, NULL); + + buffer->fd = -1; + buffer->size = size; + buffer->mirror = malloc(size); + ASSERT_NE(buffer->mirror, NULL); + + buffer->ptr = mmap(NULL, size, + PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS, + buffer->fd, 0); + ASSERT_NE(buffer->ptr, MAP_FAILED); + + /* Initialize buffer in system memory. */ + for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i) + ptr[i] = i; + + /* Map memory exclusively for device access. */ + ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_EXCLUSIVE, buffer, npages); + ASSERT_EQ(ret, 0); + ASSERT_EQ(buffer->cpages, npages); + + fork(); + + /* Fault pages back to system memory and check them. */ + for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i) + ASSERT_EQ(ptr[i]++, i); + + for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i) + ASSERT_EQ(ptr[i], i+1); + + hmm_buffer_free(buffer); +} + TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/vm/khugepaged.c b/tools/testing/selftests/vm/khugepaged.c index 8b75821302a7..155120b67a16 100644 --- a/tools/testing/selftests/vm/khugepaged.c +++ b/tools/testing/selftests/vm/khugepaged.c @@ -86,7 +86,6 @@ struct settings { enum thp_enabled thp_enabled; enum thp_defrag thp_defrag; enum shmem_enabled shmem_enabled; - bool debug_cow; bool use_zero_page; struct khugepaged_settings khugepaged; }; @@ -95,7 +94,6 @@ static struct settings default_settings = { .thp_enabled = THP_MADVISE, .thp_defrag = THP_DEFRAG_ALWAYS, .shmem_enabled = SHMEM_NEVER, - .debug_cow = 0, .use_zero_page = 0, .khugepaged = { .defrag = 1, @@ -268,7 +266,6 @@ static void write_settings(struct settings *settings) write_string("defrag", thp_defrag_strings[settings->thp_defrag]); write_string("shmem_enabled", shmem_enabled_strings[settings->shmem_enabled]); - write_num("debug_cow", settings->debug_cow); write_num("use_zero_page", settings->use_zero_page); write_num("khugepaged/defrag", khugepaged->defrag); @@ -304,7 +301,6 @@ static void save_settings(void) .thp_defrag = read_string("defrag", thp_defrag_strings), .shmem_enabled = read_string("shmem_enabled", shmem_enabled_strings), - .debug_cow = read_num("debug_cow"), .use_zero_page = read_num("use_zero_page"), }; saved_settings.khugepaged = (struct khugepaged_settings) { diff --git a/tools/testing/selftests/vm/madv_populate.c b/tools/testing/selftests/vm/madv_populate.c new file mode 100644 index 000000000000..b959e4ebdad4 --- /dev/null +++ b/tools/testing/selftests/vm/madv_populate.c @@ -0,0 +1,342 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * MADV_POPULATE_READ and MADV_POPULATE_WRITE tests + * + * Copyright 2021, Red Hat, Inc. + * + * Author(s): David Hildenbrand + */ +#define _GNU_SOURCE +#include +#include +#include +#include +#include +#include +#include +#include + +#include "../kselftest.h" + +#if defined(MADV_POPULATE_READ) && defined(MADV_POPULATE_WRITE) + +/* + * For now, we're using 2 MiB of private anonymous memory for all tests. + */ +#define SIZE (2 * 1024 * 1024) + +static size_t pagesize; + +static uint64_t pagemap_get_entry(int fd, char *start) +{ + const unsigned long pfn = (unsigned long)start / pagesize; + uint64_t entry; + int ret; + + ret = pread(fd, &entry, sizeof(entry), pfn * sizeof(entry)); + if (ret != sizeof(entry)) + ksft_exit_fail_msg("reading pagemap failed\n"); + return entry; +} + +static bool pagemap_is_populated(int fd, char *start) +{ + uint64_t entry = pagemap_get_entry(fd, start); + + /* Present or swapped. */ + return entry & 0xc000000000000000ull; +} + +static bool pagemap_is_softdirty(int fd, char *start) +{ + uint64_t entry = pagemap_get_entry(fd, start); + + return entry & 0x0080000000000000ull; +} + +static void sense_support(void) +{ + char *addr; + int ret; + + addr = mmap(0, pagesize, PROT_READ | PROT_WRITE, + MAP_ANONYMOUS | MAP_PRIVATE, 0, 0); + if (!addr) + ksft_exit_fail_msg("mmap failed\n"); + + ret = madvise(addr, pagesize, MADV_POPULATE_READ); + if (ret) + ksft_exit_skip("MADV_POPULATE_READ is not available\n"); + + ret = madvise(addr, pagesize, MADV_POPULATE_WRITE); + if (ret) + ksft_exit_skip("MADV_POPULATE_WRITE is not available\n"); + + munmap(addr, pagesize); +} + +static void test_prot_read(void) +{ + char *addr; + int ret; + + ksft_print_msg("[RUN] %s\n", __func__); + + addr = mmap(0, SIZE, PROT_READ, MAP_ANONYMOUS | MAP_PRIVATE, 0, 0); + if (addr == MAP_FAILED) + ksft_exit_fail_msg("mmap failed\n"); + + ret = madvise(addr, SIZE, MADV_POPULATE_READ); + ksft_test_result(!ret, "MADV_POPULATE_READ with PROT_READ\n"); + + ret = madvise(addr, SIZE, MADV_POPULATE_WRITE); + ksft_test_result(ret == -1 && errno == EINVAL, + "MADV_POPULATE_WRITE with PROT_READ\n"); + + munmap(addr, SIZE); +} + +static void test_prot_write(void) +{ + char *addr; + int ret; + + ksft_print_msg("[RUN] %s\n", __func__); + + addr = mmap(0, SIZE, PROT_WRITE, MAP_ANONYMOUS | MAP_PRIVATE, 0, 0); + if (addr == MAP_FAILED) + ksft_exit_fail_msg("mmap failed\n"); + + ret = madvise(addr, SIZE, MADV_POPULATE_READ); + ksft_test_result(ret == -1 && errno == EINVAL, + "MADV_POPULATE_READ with PROT_WRITE\n"); + + ret = madvise(addr, SIZE, MADV_POPULATE_WRITE); + ksft_test_result(!ret, "MADV_POPULATE_WRITE with PROT_WRITE\n"); + + munmap(addr, SIZE); +} + +static void test_holes(void) +{ + char *addr; + int ret; + + ksft_print_msg("[RUN] %s\n", __func__); + + addr = mmap(0, SIZE, PROT_READ | PROT_WRITE, + MAP_ANONYMOUS | MAP_PRIVATE, 0, 0); + if (addr == MAP_FAILED) + ksft_exit_fail_msg("mmap failed\n"); + ret = munmap(addr + pagesize, pagesize); + if (ret) + ksft_exit_fail_msg("munmap failed\n"); + + /* Hole in the middle */ + ret = madvise(addr, SIZE, MADV_POPULATE_READ); + ksft_test_result(ret == -1 && errno == ENOMEM, + "MADV_POPULATE_READ with holes in the middle\n"); + ret = madvise(addr, SIZE, MADV_POPULATE_WRITE); + ksft_test_result(ret == -1 && errno == ENOMEM, + "MADV_POPULATE_WRITE with holes in the middle\n"); + + /* Hole at end */ + ret = madvise(addr, 2 * pagesize, MADV_POPULATE_READ); + ksft_test_result(ret == -1 && errno == ENOMEM, + "MADV_POPULATE_READ with holes at the end\n"); + ret = madvise(addr, 2 * pagesize, MADV_POPULATE_WRITE); + ksft_test_result(ret == -1 && errno == ENOMEM, + "MADV_POPULATE_WRITE with holes at the end\n"); + + /* Hole at beginning */ + ret = madvise(addr + pagesize, pagesize, MADV_POPULATE_READ); + ksft_test_result(ret == -1 && errno == ENOMEM, + "MADV_POPULATE_READ with holes at the beginning\n"); + ret = madvise(addr + pagesize, pagesize, MADV_POPULATE_WRITE); + ksft_test_result(ret == -1 && errno == ENOMEM, + "MADV_POPULATE_WRITE with holes at the beginning\n"); + + munmap(addr, SIZE); +} + +static bool range_is_populated(char *start, ssize_t size) +{ + int fd = open("/proc/self/pagemap", O_RDONLY); + bool ret = true; + + if (fd < 0) + ksft_exit_fail_msg("opening pagemap failed\n"); + for (; size > 0 && ret; size -= pagesize, start += pagesize) + if (!pagemap_is_populated(fd, start)) + ret = false; + close(fd); + return ret; +} + +static bool range_is_not_populated(char *start, ssize_t size) +{ + int fd = open("/proc/self/pagemap", O_RDONLY); + bool ret = true; + + if (fd < 0) + ksft_exit_fail_msg("opening pagemap failed\n"); + for (; size > 0 && ret; size -= pagesize, start += pagesize) + if (pagemap_is_populated(fd, start)) + ret = false; + close(fd); + return ret; +} + +static void test_populate_read(void) +{ + char *addr; + int ret; + + ksft_print_msg("[RUN] %s\n", __func__); + + addr = mmap(0, SIZE, PROT_READ | PROT_WRITE, + MAP_ANONYMOUS | MAP_PRIVATE, 0, 0); + if (addr == MAP_FAILED) + ksft_exit_fail_msg("mmap failed\n"); + ksft_test_result(range_is_not_populated(addr, SIZE), + "range initially not populated\n"); + + ret = madvise(addr, SIZE, MADV_POPULATE_READ); + ksft_test_result(!ret, "MADV_POPULATE_READ\n"); + ksft_test_result(range_is_populated(addr, SIZE), + "range is populated\n"); + + munmap(addr, SIZE); +} + +static void test_populate_write(void) +{ + char *addr; + int ret; + + ksft_print_msg("[RUN] %s\n", __func__); + + addr = mmap(0, SIZE, PROT_READ | PROT_WRITE, + MAP_ANONYMOUS | MAP_PRIVATE, 0, 0); + if (addr == MAP_FAILED) + ksft_exit_fail_msg("mmap failed\n"); + ksft_test_result(range_is_not_populated(addr, SIZE), + "range initially not populated\n"); + + ret = madvise(addr, SIZE, MADV_POPULATE_WRITE); + ksft_test_result(!ret, "MADV_POPULATE_WRITE\n"); + ksft_test_result(range_is_populated(addr, SIZE), + "range is populated\n"); + + munmap(addr, SIZE); +} + +static bool range_is_softdirty(char *start, ssize_t size) +{ + int fd = open("/proc/self/pagemap", O_RDONLY); + bool ret = true; + + if (fd < 0) + ksft_exit_fail_msg("opening pagemap failed\n"); + for (; size > 0 && ret; size -= pagesize, start += pagesize) + if (!pagemap_is_softdirty(fd, start)) + ret = false; + close(fd); + return ret; +} + +static bool range_is_not_softdirty(char *start, ssize_t size) +{ + int fd = open("/proc/self/pagemap", O_RDONLY); + bool ret = true; + + if (fd < 0) + ksft_exit_fail_msg("opening pagemap failed\n"); + for (; size > 0 && ret; size -= pagesize, start += pagesize) + if (pagemap_is_softdirty(fd, start)) + ret = false; + close(fd); + return ret; +} + +static void clear_softdirty(void) +{ + int fd = open("/proc/self/clear_refs", O_WRONLY); + const char *ctrl = "4"; + int ret; + + if (fd < 0) + ksft_exit_fail_msg("opening clear_refs failed\n"); + ret = write(fd, ctrl, strlen(ctrl)); + if (ret != strlen(ctrl)) + ksft_exit_fail_msg("writing clear_refs failed\n"); + close(fd); +} + +static void test_softdirty(void) +{ + char *addr; + int ret; + + ksft_print_msg("[RUN] %s\n", __func__); + + addr = mmap(0, SIZE, PROT_READ | PROT_WRITE, + MAP_ANONYMOUS | MAP_PRIVATE, 0, 0); + if (addr == MAP_FAILED) + ksft_exit_fail_msg("mmap failed\n"); + + /* Clear any softdirty bits. */ + clear_softdirty(); + ksft_test_result(range_is_not_softdirty(addr, SIZE), + "range is not softdirty\n"); + + /* Populating READ should set softdirty. */ + ret = madvise(addr, SIZE, MADV_POPULATE_READ); + ksft_test_result(!ret, "MADV_POPULATE_READ\n"); + ksft_test_result(range_is_not_softdirty(addr, SIZE), + "range is not softdirty\n"); + + /* Populating WRITE should set softdirty. */ + ret = madvise(addr, SIZE, MADV_POPULATE_WRITE); + ksft_test_result(!ret, "MADV_POPULATE_WRITE\n"); + ksft_test_result(range_is_softdirty(addr, SIZE), + "range is softdirty\n"); + + munmap(addr, SIZE); +} + +int main(int argc, char **argv) +{ + int err; + + pagesize = getpagesize(); + + ksft_print_header(); + ksft_set_plan(21); + + sense_support(); + test_prot_read(); + test_prot_write(); + test_holes(); + test_populate_read(); + test_populate_write(); + test_softdirty(); + + err = ksft_get_fail_cnt(); + if (err) + ksft_exit_fail_msg("%d out of %d tests failed\n", + err, ksft_test_num()); + return ksft_exit_pass(); +} + +#else /* defined(MADV_POPULATE_READ) && defined(MADV_POPULATE_WRITE) */ + +#warning "missing MADV_POPULATE_READ or MADV_POPULATE_WRITE definition" + +int main(int argc, char **argv) +{ + ksft_print_header(); + ksft_exit_skip("MADV_POPULATE_READ or MADV_POPULATE_WRITE not defined\n"); +} + +#endif /* defined(MADV_POPULATE_READ) && defined(MADV_POPULATE_WRITE) */ diff --git a/tools/testing/selftests/vm/pkey-x86.h b/tools/testing/selftests/vm/pkey-x86.h index 3be20f5d5275..e4a4ce2b826d 100644 --- a/tools/testing/selftests/vm/pkey-x86.h +++ b/tools/testing/selftests/vm/pkey-x86.h @@ -126,6 +126,7 @@ static inline u32 pkey_bit_position(int pkey) #define XSTATE_PKEY_BIT (9) #define XSTATE_PKEY 0x200 +#define XSTATE_BV_OFFSET 512 int pkey_reg_xstate_offset(void) { diff --git a/tools/testing/selftests/vm/protection_keys.c b/tools/testing/selftests/vm/protection_keys.c index fdbb602ecf32..2d0ae88665db 100644 --- a/tools/testing/selftests/vm/protection_keys.c +++ b/tools/testing/selftests/vm/protection_keys.c @@ -510,7 +510,7 @@ int alloc_pkey(void) " shadow: 0x%016llx\n", __func__, __LINE__, ret, __read_pkey_reg(), shadow_pkey_reg); - if (ret) { + if (ret > 0) { /* clear both the bits: */ shadow_pkey_reg = set_pkey_bits(shadow_pkey_reg, ret, ~PKEY_MASK); @@ -561,7 +561,6 @@ int alloc_random_pkey(void) int nr_alloced = 0; int random_index; memset(alloced_pkeys, 0, sizeof(alloced_pkeys)); - srand((unsigned int)time(NULL)); /* allocate every possible key and make a note of which ones we got */ max_nr_pkey_allocs = NR_PKEYS; @@ -1278,6 +1277,78 @@ void test_pkey_alloc_exhaust(int *ptr, u16 pkey) } } +void arch_force_pkey_reg_init(void) +{ +#if defined(__i386__) || defined(__x86_64__) /* arch */ + u64 *buf; + + /* + * All keys should be allocated and set to allow reads and + * writes, so the register should be all 0. If not, just + * skip the test. + */ + if (read_pkey_reg()) + return; + + /* + * Just allocate an absurd about of memory rather than + * doing the XSAVE size enumeration dance. + */ + buf = mmap(NULL, 1*MB, PROT_READ|PROT_WRITE, MAP_ANONYMOUS|MAP_PRIVATE, -1, 0); + + /* These __builtins require compiling with -mxsave */ + + /* XSAVE to build a valid buffer: */ + __builtin_ia32_xsave(buf, XSTATE_PKEY); + /* Clear XSTATE_BV[PKRU]: */ + buf[XSTATE_BV_OFFSET/sizeof(u64)] &= ~XSTATE_PKEY; + /* XRSTOR will likely get PKRU back to the init state: */ + __builtin_ia32_xrstor(buf, XSTATE_PKEY); + + munmap(buf, 1*MB); +#endif +} + + +/* + * This is mostly useless on ppc for now. But it will not + * hurt anything and should give some better coverage as + * a long-running test that continually checks the pkey + * register. + */ +void test_pkey_init_state(int *ptr, u16 pkey) +{ + int err; + int allocated_pkeys[NR_PKEYS] = {0}; + int nr_allocated_pkeys = 0; + int i; + + for (i = 0; i < NR_PKEYS; i++) { + int new_pkey = alloc_pkey(); + + if (new_pkey < 0) + continue; + allocated_pkeys[nr_allocated_pkeys++] = new_pkey; + } + + dprintf3("%s()::%d\n", __func__, __LINE__); + + arch_force_pkey_reg_init(); + + /* + * Loop for a bit, hoping to get exercise the kernel + * context switch code. + */ + for (i = 0; i < 1000000; i++) + read_pkey_reg(); + + for (i = 0; i < nr_allocated_pkeys; i++) { + err = sys_pkey_free(allocated_pkeys[i]); + pkey_assert(!err); + read_pkey_reg(); /* for shadow checking */ + } +} + /* * pkey 0 is special. It is allocated by default, so you do not * have to call pkey_alloc() to use it first. Make sure that it @@ -1449,6 +1520,13 @@ void test_implicit_mprotect_exec_only_memory(int *ptr, u16 pkey) ret = mprotect(p1, PAGE_SIZE, PROT_EXEC); pkey_assert(!ret); + /* + * Reset the shadow, assuming that the above mprotect() + * correctly changed PKRU, but to an unknown value since + * the actual alllocated pkey is unknown. + */ + shadow_pkey_reg = __read_pkey_reg(); + dprintf2("pkey_reg: %016llx\n", read_pkey_reg()); /* Make sure this is an *instruction* fault */ @@ -1502,6 +1580,7 @@ void (*pkey_tests[])(int *ptr, u16 pkey) = { test_implicit_mprotect_exec_only_memory, test_mprotect_with_pkey_0, test_ptrace_of_child, + test_pkey_init_state, test_pkey_syscalls_on_non_allocated_pkey, test_pkey_syscalls_bad_args, test_pkey_alloc_exhaust, @@ -1552,6 +1631,8 @@ int main(void) int nr_iterations = 22; int pkeys_supported = is_pkeys_supported(); + srand((unsigned int)time(NULL)); + setup_handlers(); printf("has pkeys: %d\n", pkeys_supported); diff --git a/tools/testing/selftests/vm/run_vmtests.sh b/tools/testing/selftests/vm/run_vmtests.sh index e953f3cd9664..955782d138ab 100755 --- a/tools/testing/selftests/vm/run_vmtests.sh +++ b/tools/testing/selftests/vm/run_vmtests.sh @@ -346,4 +346,20 @@ else exitcode=1 fi +echo "--------------------------------------------------------" +echo "running MADV_POPULATE_READ and MADV_POPULATE_WRITE tests" +echo "--------------------------------------------------------" +./madv_populate +ret_val=$? + +if [ $ret_val -eq 0 ]; then + echo "[PASS]" +elif [ $ret_val -eq $ksft_skip ]; then + echo "[SKIP]" + exitcode=$ksft_skip +else + echo "[FAIL]" + exitcode=1 +fi + exit $exitcode diff --git a/tools/testing/selftests/vm/userfaultfd.c b/tools/testing/selftests/vm/userfaultfd.c index f5ab5e0312e7..e363bdaff59d 100644 --- a/tools/testing/selftests/vm/userfaultfd.c +++ b/tools/testing/selftests/vm/userfaultfd.c @@ -85,10 +85,12 @@ static bool test_uffdio_wp = false; static bool test_uffdio_minor = false; static bool map_shared; +static int shm_fd; static int huge_fd; static char *huge_fd_off0; static unsigned long long *count_verify; -static int uffd, uffd_flags, finished, *pipefd; +static int uffd = -1; +static int uffd_flags, finished, *pipefd; static char *area_src, *area_src_alias, *area_dst, *area_dst_alias; static char *zeropage; pthread_attr_t attr; @@ -140,11 +142,18 @@ static void usage(void) exit(1); } -#define uffd_error(code, fmt, ...) \ - do { \ - fprintf(stderr, fmt, ##__VA_ARGS__); \ - fprintf(stderr, ": %" PRId64 "\n", (int64_t)(code)); \ - exit(1); \ +#define _err(fmt, ...) \ + do { \ + int ret = errno; \ + fprintf(stderr, "ERROR: " fmt, ##__VA_ARGS__); \ + fprintf(stderr, " (errno=%d, line=%d)\n", \ + ret, __LINE__); \ + } while (0) + +#define err(fmt, ...) \ + do { \ + _err(fmt, ##__VA_ARGS__); \ + exit(1); \ } while (0) static void uffd_stats_reset(struct uffd_stats *uffd_stats, @@ -171,56 +180,50 @@ static void uffd_stats_report(struct uffd_stats *stats, int n_cpus) minor_total += stats[i].minor_faults; } - printf("userfaults: %llu missing (", miss_total); - for (i = 0; i < n_cpus; i++) - printf("%lu+", stats[i].missing_faults); - printf("\b), %llu wp (", wp_total); - for (i = 0; i < n_cpus; i++) - printf("%lu+", stats[i].wp_faults); - printf("\b), %llu minor (", minor_total); - for (i = 0; i < n_cpus; i++) - printf("%lu+", stats[i].minor_faults); - printf("\b)\n"); + printf("userfaults: "); + if (miss_total) { + printf("%llu missing (", miss_total); + for (i = 0; i < n_cpus; i++) + printf("%lu+", stats[i].missing_faults); + printf("\b) "); + } + if (wp_total) { + printf("%llu wp (", wp_total); + for (i = 0; i < n_cpus; i++) + printf("%lu+", stats[i].wp_faults); + printf("\b) "); + } + if (minor_total) { + printf("%llu minor (", minor_total); + for (i = 0; i < n_cpus; i++) + printf("%lu+", stats[i].minor_faults); + printf("\b)"); + } + printf("\n"); } -static int anon_release_pages(char *rel_area) +static void anon_release_pages(char *rel_area) { - int ret = 0; - - if (madvise(rel_area, nr_pages * page_size, MADV_DONTNEED)) { - perror("madvise"); - ret = 1; - } - - return ret; + if (madvise(rel_area, nr_pages * page_size, MADV_DONTNEED)) + err("madvise(MADV_DONTNEED) failed"); } static void anon_allocate_area(void **alloc_area) { - if (posix_memalign(alloc_area, page_size, nr_pages * page_size)) { - fprintf(stderr, "out of memory\n"); - *alloc_area = NULL; - } + if (posix_memalign(alloc_area, page_size, nr_pages * page_size)) + err("posix_memalign() failed"); } static void noop_alias_mapping(__u64 *start, size_t len, unsigned long offset) { } -/* HugeTLB memory */ -static int hugetlb_release_pages(char *rel_area) +static void hugetlb_release_pages(char *rel_area) { - int ret = 0; - if (fallocate(huge_fd, FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE, - rel_area == huge_fd_off0 ? 0 : - nr_pages * page_size, - nr_pages * page_size)) { - perror("fallocate"); - ret = 1; - } - - return ret; + rel_area == huge_fd_off0 ? 0 : nr_pages * page_size, + nr_pages * page_size)) + err("fallocate() failed"); } static void hugetlb_allocate_area(void **alloc_area) @@ -233,20 +236,16 @@ static void hugetlb_allocate_area(void **alloc_area) MAP_HUGETLB, huge_fd, *alloc_area == area_src ? 0 : nr_pages * page_size); - if (*alloc_area == MAP_FAILED) { - perror("mmap of hugetlbfs file failed"); - goto fail; - } + if (*alloc_area == MAP_FAILED) + err("mmap of hugetlbfs file failed"); if (map_shared) { area_alias = mmap(NULL, nr_pages * page_size, PROT_READ | PROT_WRITE, MAP_SHARED | MAP_HUGETLB, huge_fd, *alloc_area == area_src ? 0 : nr_pages * page_size); - if (area_alias == MAP_FAILED) { - perror("mmap of hugetlb file alias failed"); - goto fail_munmap; - } + if (area_alias == MAP_FAILED) + err("mmap of hugetlb file alias failed"); } if (*alloc_area == area_src) { @@ -257,16 +256,6 @@ static void hugetlb_allocate_area(void **alloc_area) } if (area_alias) *alloc_area_alias = area_alias; - - return; - -fail_munmap: - if (munmap(*alloc_area, nr_pages * page_size) < 0) { - perror("hugetlb munmap"); - exit(1); - } -fail: - *alloc_area = NULL; } static void hugetlb_alias_mapping(__u64 *start, size_t len, unsigned long offset) @@ -282,33 +271,43 @@ static void hugetlb_alias_mapping(__u64 *start, size_t len, unsigned long offset *start = (unsigned long) area_dst_alias + offset; } -/* Shared memory */ -static int shmem_release_pages(char *rel_area) +static void shmem_release_pages(char *rel_area) { - int ret = 0; - - if (madvise(rel_area, nr_pages * page_size, MADV_REMOVE)) { - perror("madvise"); - ret = 1; - } - - return ret; + if (madvise(rel_area, nr_pages * page_size, MADV_REMOVE)) + err("madvise(MADV_REMOVE) failed"); } static void shmem_allocate_area(void **alloc_area) { + void *area_alias = NULL; + bool is_src = alloc_area == (void **)&area_src; + unsigned long offset = is_src ? 0 : nr_pages * page_size; + *alloc_area = mmap(NULL, nr_pages * page_size, PROT_READ | PROT_WRITE, - MAP_ANONYMOUS | MAP_SHARED, -1, 0); - if (*alloc_area == MAP_FAILED) { - fprintf(stderr, "shared memory mmap failed\n"); - *alloc_area = NULL; - } + MAP_SHARED, shm_fd, offset); + if (*alloc_area == MAP_FAILED) + err("mmap of memfd failed"); + + area_alias = mmap(NULL, nr_pages * page_size, PROT_READ | PROT_WRITE, + MAP_SHARED, shm_fd, offset); + if (area_alias == MAP_FAILED) + err("mmap of memfd alias failed"); + + if (is_src) + area_src_alias = area_alias; + else + area_dst_alias = area_alias; +} + +static void shmem_alias_mapping(__u64 *start, size_t len, unsigned long offset) +{ + *start = (unsigned long)area_dst_alias + offset; } struct uffd_test_ops { unsigned long expected_ioctls; void (*allocate_area)(void **alloc_area); - int (*release_pages)(char *rel_area); + void (*release_pages)(char *rel_area); void (*alias_mapping)(__u64 *start, size_t len, unsigned long offset); }; @@ -332,7 +331,7 @@ static struct uffd_test_ops shmem_uffd_test_ops = { .expected_ioctls = SHMEM_EXPECTED_IOCTLS, .allocate_area = shmem_allocate_area, .release_pages = shmem_release_pages, - .alias_mapping = noop_alias_mapping, + .alias_mapping = shmem_alias_mapping, }; static struct uffd_test_ops hugetlb_uffd_test_ops = { @@ -344,6 +343,111 @@ static struct uffd_test_ops hugetlb_uffd_test_ops = { static struct uffd_test_ops *uffd_test_ops; +static void userfaultfd_open(uint64_t *features) +{ + struct uffdio_api uffdio_api; + + uffd = syscall(__NR_userfaultfd, O_CLOEXEC | O_NONBLOCK | UFFD_USER_MODE_ONLY); + if (uffd < 0) + err("userfaultfd syscall not available in this kernel"); + uffd_flags = fcntl(uffd, F_GETFD, NULL); + + uffdio_api.api = UFFD_API; + uffdio_api.features = *features; + if (ioctl(uffd, UFFDIO_API, &uffdio_api)) + err("UFFDIO_API failed.\nPlease make sure to " + "run with either root or ptrace capability."); + if (uffdio_api.api != UFFD_API) + err("UFFDIO_API error: %" PRIu64, (uint64_t)uffdio_api.api); + + *features = uffdio_api.features; +} + +static inline void munmap_area(void **area) +{ + if (*area) + if (munmap(*area, nr_pages * page_size)) + err("munmap"); + + *area = NULL; +} + +static void uffd_test_ctx_clear(void) +{ + size_t i; + + if (pipefd) { + for (i = 0; i < nr_cpus * 2; ++i) { + if (close(pipefd[i])) + err("close pipefd"); + } + free(pipefd); + pipefd = NULL; + } + + if (count_verify) { + free(count_verify); + count_verify = NULL; + } + + if (uffd != -1) { + if (close(uffd)) + err("close uffd"); + uffd = -1; + } + + huge_fd_off0 = NULL; + munmap_area((void **)&area_src); + munmap_area((void **)&area_src_alias); + munmap_area((void **)&area_dst); + munmap_area((void **)&area_dst_alias); +} + +static void uffd_test_ctx_init_ext(uint64_t *features) +{ + unsigned long nr, cpu; + + uffd_test_ctx_clear(); + + uffd_test_ops->allocate_area((void **)&area_src); + uffd_test_ops->allocate_area((void **)&area_dst); + + uffd_test_ops->release_pages(area_src); + uffd_test_ops->release_pages(area_dst); + + userfaultfd_open(features); + + count_verify = malloc(nr_pages * sizeof(unsigned long long)); + if (!count_verify) + err("count_verify"); + + for (nr = 0; nr < nr_pages; nr++) { + *area_mutex(area_src, nr) = + (pthread_mutex_t)PTHREAD_MUTEX_INITIALIZER; + count_verify[nr] = *area_count(area_src, nr) = 1; + /* + * In the transition between 255 to 256, powerpc will + * read out of order in my_bcmp and see both bytes as + * zero, so leave a placeholder below always non-zero + * after the count, to avoid my_bcmp to trigger false + * positives. + */ + *(area_count(area_src, nr) + 1) = 1; + } + + pipefd = malloc(sizeof(int) * nr_cpus * 2); + if (!pipefd) + err("pipefd"); + for (cpu = 0; cpu < nr_cpus; cpu++) + if (pipe2(&pipefd[cpu * 2], O_CLOEXEC | O_NONBLOCK)) + err("pipe"); +} + +static inline void uffd_test_ctx_init(uint64_t features) +{ + uffd_test_ctx_init_ext(&features); +} + static int my_bcmp(char *str1, char *str2, size_t n) { unsigned long i; @@ -363,27 +467,33 @@ static void wp_range(int ufd, __u64 start, __u64 len, bool wp) /* Undo write-protect, do wakeup after that */ prms.mode = wp ? UFFDIO_WRITEPROTECT_MODE_WP : 0; - if (ioctl(ufd, UFFDIO_WRITEPROTECT, &prms)) { - fprintf(stderr, "clear WP failed for address 0x%" PRIx64 "\n", - (uint64_t)start); - exit(1); - } + if (ioctl(ufd, UFFDIO_WRITEPROTECT, &prms)) + err("clear WP failed: address=0x%"PRIx64, (uint64_t)start); } static void continue_range(int ufd, __u64 start, __u64 len) { struct uffdio_continue req; + int ret; req.range.start = start; req.range.len = len; req.mode = 0; - if (ioctl(ufd, UFFDIO_CONTINUE, &req)) { - fprintf(stderr, - "UFFDIO_CONTINUE failed for address 0x%" PRIx64 "\n", - (uint64_t)start); - exit(1); - } + if (ioctl(ufd, UFFDIO_CONTINUE, &req)) + err("UFFDIO_CONTINUE failed for address 0x%" PRIx64, + (uint64_t)start); + + /* + * Error handling within the kernel for continue is subtly different + * from copy or zeropage, so it may be a source of bugs. Trigger an + * error (-EEXIST) on purpose, to verify doing so doesn't cause a BUG. + */ + req.mapped = 0; + ret = ioctl(ufd, UFFDIO_CONTINUE, &req); + if (ret >= 0 || req.mapped != -EEXIST) + err("failed to exercise UFFDIO_CONTINUE error handling, ret=%d, mapped=%" PRId64, + ret, (int64_t) req.mapped); } static void *locking_thread(void *arg) @@ -395,7 +505,6 @@ static void *locking_thread(void *arg) unsigned long long count; char randstate[64]; unsigned int seed; - time_t start; if (bounces & BOUNCE_RANDOM) { seed = (unsigned int) time(NULL) - bounces; @@ -403,10 +512,8 @@ static void *locking_thread(void *arg) seed += cpu; bzero(&rand, sizeof(rand)); bzero(&randstate, sizeof(randstate)); - if (initstate_r(seed, randstate, sizeof(randstate), &rand)) { - fprintf(stderr, "srandom_r error\n"); - exit(1); - } + if (initstate_r(seed, randstate, sizeof(randstate), &rand)) + err("initstate_r failed"); } else { page_nr = -bounces; if (!(bounces & BOUNCE_RACINGFAULTS)) @@ -415,92 +522,26 @@ static void *locking_thread(void *arg) while (!finished) { if (bounces & BOUNCE_RANDOM) { - if (random_r(&rand, &rand_nr)) { - fprintf(stderr, "random_r 1 error\n"); - exit(1); - } + if (random_r(&rand, &rand_nr)) + err("random_r failed"); page_nr = rand_nr; if (sizeof(page_nr) > sizeof(rand_nr)) { - if (random_r(&rand, &rand_nr)) { - fprintf(stderr, "random_r 2 error\n"); - exit(1); - } + if (random_r(&rand, &rand_nr)) + err("random_r failed"); page_nr |= (((unsigned long) rand_nr) << 16) << 16; } } else page_nr += 1; page_nr %= nr_pages; - - start = time(NULL); - if (bounces & BOUNCE_VERIFY) { - count = *area_count(area_dst, page_nr); - if (!count) { - fprintf(stderr, - "page_nr %lu wrong count %Lu %Lu\n", - page_nr, count, - count_verify[page_nr]); - exit(1); - } - - - /* - * We can't use bcmp (or memcmp) because that - * returns 0 erroneously if the memory is - * changing under it (even if the end of the - * page is never changing and always - * different). - */ -#if 1 - if (!my_bcmp(area_dst + page_nr * page_size, zeropage, - page_size)) { - fprintf(stderr, - "my_bcmp page_nr %lu wrong count %Lu %Lu\n", - page_nr, count, count_verify[page_nr]); - exit(1); - } -#else - unsigned long loops; - - loops = 0; - /* uncomment the below line to test with mutex */ - /* pthread_mutex_lock(area_mutex(area_dst, page_nr)); */ - while (!bcmp(area_dst + page_nr * page_size, zeropage, - page_size)) { - loops += 1; - if (loops > 10) - break; - } - /* uncomment below line to test with mutex */ - /* pthread_mutex_unlock(area_mutex(area_dst, page_nr)); */ - if (loops) { - fprintf(stderr, - "page_nr %lu all zero thread %lu %p %lu\n", - page_nr, cpu, area_dst + page_nr * page_size, - loops); - if (loops > 10) - exit(1); - } -#endif - } - pthread_mutex_lock(area_mutex(area_dst, page_nr)); count = *area_count(area_dst, page_nr); - if (count != count_verify[page_nr]) { - fprintf(stderr, - "page_nr %lu memory corruption %Lu %Lu\n", - page_nr, count, - count_verify[page_nr]); exit(1); - } + if (count != count_verify[page_nr]) + err("page_nr %lu memory corruption %llu %llu", + page_nr, count, count_verify[page_nr]); count++; *area_count(area_dst, page_nr) = count_verify[page_nr] = count; pthread_mutex_unlock(area_mutex(area_dst, page_nr)); - - if (time(NULL) - start > 1) - fprintf(stderr, - "userfault too slow %ld " - "possible false positive with overcommit\n", - time(NULL) - start); } return NULL; @@ -514,22 +555,21 @@ static void retry_copy_page(int ufd, struct uffdio_copy *uffdio_copy, offset); if (ioctl(ufd, UFFDIO_COPY, uffdio_copy)) { /* real retval in ufdio_copy.copy */ - if (uffdio_copy->copy != -EEXIST) { - uffd_error(uffdio_copy->copy, - "UFFDIO_COPY retry error"); - } - } else - uffd_error(uffdio_copy->copy, "UFFDIO_COPY retry unexpected"); + if (uffdio_copy->copy != -EEXIST) + err("UFFDIO_COPY retry error: %"PRId64, + (int64_t)uffdio_copy->copy); + } else { + err("UFFDIO_COPY retry unexpected: %"PRId64, + (int64_t)uffdio_copy->copy); + } } static int __copy_page(int ufd, unsigned long offset, bool retry) { struct uffdio_copy uffdio_copy; - if (offset >= nr_pages * page_size) { - fprintf(stderr, "unexpected offset %lu\n", offset); - exit(1); - } + if (offset >= nr_pages * page_size) + err("unexpected offset %lu\n", offset); uffdio_copy.dst = (unsigned long) area_dst + offset; uffdio_copy.src = (unsigned long) area_src + offset; uffdio_copy.len = page_size; @@ -541,9 +581,10 @@ static int __copy_page(int ufd, unsigned long offset, bool retry) if (ioctl(ufd, UFFDIO_COPY, &uffdio_copy)) { /* real retval in ufdio_copy.copy */ if (uffdio_copy.copy != -EEXIST) - uffd_error(uffdio_copy.copy, "UFFDIO_COPY error"); + err("UFFDIO_COPY error: %"PRId64, + (int64_t)uffdio_copy.copy); } else if (uffdio_copy.copy != page_size) { - uffd_error(uffdio_copy.copy, "UFFDIO_COPY unexpected copy"); + err("UFFDIO_COPY error: %"PRId64, (int64_t)uffdio_copy.copy); } else { if (test_uffdio_copy_eexist && retry) { test_uffdio_copy_eexist = false; @@ -572,11 +613,10 @@ static int uffd_read_msg(int ufd, struct uffd_msg *msg) if (ret < 0) { if (errno == EAGAIN) return 1; - perror("blocking read error"); + err("blocking read error"); } else { - fprintf(stderr, "short read\n"); + err("short read"); } - exit(1); } return 0; @@ -587,10 +627,8 @@ static void uffd_handle_page_fault(struct uffd_msg *msg, { unsigned long offset; - if (msg->event != UFFD_EVENT_PAGEFAULT) { - fprintf(stderr, "unexpected msg event %u\n", msg->event); - exit(1); - } + if (msg->event != UFFD_EVENT_PAGEFAULT) + err("unexpected msg event %u", msg->event); if (msg->arg.pagefault.flags & UFFD_PAGEFAULT_FLAG_WP) { /* Write protect page faults */ @@ -621,11 +659,8 @@ static void uffd_handle_page_fault(struct uffd_msg *msg, stats->minor_faults++; } else { /* Missing page faults */ - if (bounces & BOUNCE_VERIFY && - msg->arg.pagefault.flags & UFFD_PAGEFAULT_FLAG_WRITE) { - fprintf(stderr, "unexpected write fault\n"); - exit(1); - } + if (msg->arg.pagefault.flags & UFFD_PAGEFAULT_FLAG_WRITE) + err("unexpected write fault"); offset = (char *)(unsigned long)msg->arg.pagefault.address - area_dst; offset &= ~(page_size-1); @@ -652,32 +687,20 @@ static void *uffd_poll_thread(void *arg) for (;;) { ret = poll(pollfd, 2, -1); - if (!ret) { - fprintf(stderr, "poll error %d\n", ret); - exit(1); - } - if (ret < 0) { - perror("poll"); - exit(1); - } + if (ret <= 0) + err("poll error: %d", ret); if (pollfd[1].revents & POLLIN) { - if (read(pollfd[1].fd, &tmp_chr, 1) != 1) { - fprintf(stderr, "read pipefd error\n"); - exit(1); - } + if (read(pollfd[1].fd, &tmp_chr, 1) != 1) + err("read pipefd error"); break; } - if (!(pollfd[0].revents & POLLIN)) { - fprintf(stderr, "pollfd[0].revents %d\n", - pollfd[0].revents); - exit(1); - } + if (!(pollfd[0].revents & POLLIN)) + err("pollfd[0].revents %d", pollfd[0].revents); if (uffd_read_msg(uffd, &msg)) continue; switch (msg.event) { default: - fprintf(stderr, "unexpected msg event %u\n", - msg.event); exit(1); + err("unexpected msg event %u\n", msg.event); break; case UFFD_EVENT_PAGEFAULT: uffd_handle_page_fault(&msg, stats); @@ -691,10 +714,8 @@ static void *uffd_poll_thread(void *arg) uffd_reg.range.start = msg.arg.remove.start; uffd_reg.range.len = msg.arg.remove.end - msg.arg.remove.start; - if (ioctl(uffd, UFFDIO_UNREGISTER, &uffd_reg.range)) { - fprintf(stderr, "remove failure\n"); - exit(1); - } + if (ioctl(uffd, UFFDIO_UNREGISTER, &uffd_reg.range)) + err("remove failure"); break; case UFFD_EVENT_REMAP: area_dst = (char *)(unsigned long)msg.arg.remap.to; @@ -797,9 +818,7 @@ static int stress(struct uffd_stats *uffd_stats) * UFFDIO_COPY without writing zero pages into area_dst * because the background threads already completed). */ - if (uffd_test_ops->release_pages(area_src)) - return 1; - + uffd_test_ops->release_pages(area_src); finished = 1; for (cpu = 0; cpu < nr_cpus; cpu++) @@ -809,10 +828,8 @@ static int stress(struct uffd_stats *uffd_stats) for (cpu = 0; cpu < nr_cpus; cpu++) { char c; if (bounces & BOUNCE_POLL) { - if (write(pipefd[cpu*2+1], &c, 1) != 1) { - fprintf(stderr, "pipefd write error\n"); - return 1; - } + if (write(pipefd[cpu*2+1], &c, 1) != 1) + err("pipefd write error"); if (pthread_join(uffd_threads[cpu], (void *)&uffd_stats[cpu])) return 1; @@ -827,40 +844,6 @@ static int stress(struct uffd_stats *uffd_stats) return 0; } -static int userfaultfd_open_ext(uint64_t *features) -{ - struct uffdio_api uffdio_api; - - uffd = syscall(__NR_userfaultfd, O_CLOEXEC | O_NONBLOCK); - if (uffd < 0) { - fprintf(stderr, - "userfaultfd syscall not available in this kernel\n"); - return 1; - } - uffd_flags = fcntl(uffd, F_GETFD, NULL); - - uffdio_api.api = UFFD_API; - uffdio_api.features = *features; - if (ioctl(uffd, UFFDIO_API, &uffdio_api)) { - fprintf(stderr, "UFFDIO_API failed.\nPlease make sure to " - "run with either root or ptrace capability.\n"); - return 1; - } - if (uffdio_api.api != UFFD_API) { - fprintf(stderr, "UFFDIO_API error: %" PRIu64 "\n", - (uint64_t)uffdio_api.api); - return 1; - } - - *features = uffdio_api.features; - return 0; -} - -static int userfaultfd_open(uint64_t features) -{ - return userfaultfd_open_ext(&features); -} - sigjmp_buf jbuf, *sigbuf; static void sighndl(int sig, siginfo_t *siginfo, void *ptr) @@ -912,10 +895,8 @@ static int faulting_process(int signal_test) memset(&act, 0, sizeof(act)); act.sa_sigaction = sighndl; act.sa_flags = SA_SIGINFO; - if (sigaction(SIGBUS, &act, 0)) { - perror("sigaction"); - return 1; - } + if (sigaction(SIGBUS, &act, 0)) + err("sigaction"); lastnr = (unsigned long)-1; } @@ -925,10 +906,8 @@ static int faulting_process(int signal_test) if (signal_test) { if (sigsetjmp(*sigbuf, 1) != 0) { - if (steps == 1 && nr == lastnr) { - fprintf(stderr, "Signal repeated\n"); - return 1; - } + if (steps == 1 && nr == lastnr) + err("Signal repeated"); lastnr = nr; if (signal_test == 1) { @@ -953,12 +932,9 @@ static int faulting_process(int signal_test) } count = *area_count(area_dst, nr); - if (count != count_verify[nr]) { - fprintf(stderr, - "nr %lu memory corruption %Lu %Lu\n", - nr, count, - count_verify[nr]); - } + if (count != count_verify[nr]) + err("nr %lu memory corruption %llu %llu\n", + nr, count, count_verify[nr]); /* * Trigger write protection if there is by writing * the same value back. @@ -974,18 +950,16 @@ static int faulting_process(int signal_test) area_dst = mremap(area_dst, nr_pages * page_size, nr_pages * page_size, MREMAP_MAYMOVE | MREMAP_FIXED, area_src); - if (area_dst == MAP_FAILED) { - perror("mremap"); - exit(1); - } + if (area_dst == MAP_FAILED) + err("mremap"); + /* Reset area_src since we just clobbered it */ + area_src = NULL; for (; nr < nr_pages; nr++) { count = *area_count(area_dst, nr); if (count != count_verify[nr]) { - fprintf(stderr, - "nr %lu memory corruption %Lu %Lu\n", - nr, count, - count_verify[nr]); exit(1); + err("nr %lu memory corruption %llu %llu\n", + nr, count, count_verify[nr]); } /* * Trigger write protection if there is by writing @@ -994,15 +968,11 @@ static int faulting_process(int signal_test) *area_count(area_dst, nr) = count; } - if (uffd_test_ops->release_pages(area_dst)) - return 1; + uffd_test_ops->release_pages(area_dst); - for (nr = 0; nr < nr_pages; nr++) { - if (my_bcmp(area_dst + nr * page_size, zeropage, page_size)) { - fprintf(stderr, "nr %lu is not zero\n", nr); - exit(1); - } - } + for (nr = 0; nr < nr_pages; nr++) + if (my_bcmp(area_dst + nr * page_size, zeropage, page_size)) + err("nr %lu is not zero", nr); return 0; } @@ -1015,13 +985,12 @@ static void retry_uffdio_zeropage(int ufd, uffdio_zeropage->range.len, offset); if (ioctl(ufd, UFFDIO_ZEROPAGE, uffdio_zeropage)) { - if (uffdio_zeropage->zeropage != -EEXIST) { - uffd_error(uffdio_zeropage->zeropage, - "UFFDIO_ZEROPAGE retry error"); - } + if (uffdio_zeropage->zeropage != -EEXIST) + err("UFFDIO_ZEROPAGE error: %"PRId64, + (int64_t)uffdio_zeropage->zeropage); } else { - uffd_error(uffdio_zeropage->zeropage, - "UFFDIO_ZEROPAGE retry unexpected"); + err("UFFDIO_ZEROPAGE error: %"PRId64, + (int64_t)uffdio_zeropage->zeropage); } } @@ -1034,10 +1003,8 @@ static int __uffdio_zeropage(int ufd, unsigned long offset, bool retry) has_zeropage = uffd_test_ops->expected_ioctls & (1 << _UFFDIO_ZEROPAGE); - if (offset >= nr_pages * page_size) { - fprintf(stderr, "unexpected offset %lu\n", offset); - exit(1); - } + if (offset >= nr_pages * page_size) + err("unexpected offset %lu", offset); uffdio_zeropage.range.start = (unsigned long) area_dst + offset; uffdio_zeropage.range.len = page_size; uffdio_zeropage.mode = 0; @@ -1045,14 +1012,13 @@ static int __uffdio_zeropage(int ufd, unsigned long offset, bool retry) res = uffdio_zeropage.zeropage; if (ret) { /* real retval in ufdio_zeropage.zeropage */ - if (has_zeropage) { - uffd_error(res, "UFFDIO_ZEROPAGE %s", - res == -EEXIST ? "-EEXIST" : "error"); - } else if (res != -EINVAL) - uffd_error(res, "UFFDIO_ZEROPAGE not -EINVAL"); + if (has_zeropage) + err("UFFDIO_ZEROPAGE error: %"PRId64, (int64_t)res); + else if (res != -EINVAL) + err("UFFDIO_ZEROPAGE not -EINVAL"); } else if (has_zeropage) { if (res != page_size) { - uffd_error(res, "UFFDIO_ZEROPAGE unexpected"); + err("UFFDIO_ZEROPAGE unexpected size"); } else { if (test_uffdio_zeropage_eexist && retry) { test_uffdio_zeropage_eexist = false; @@ -1062,7 +1028,7 @@ static int __uffdio_zeropage(int ufd, unsigned long offset, bool retry) return 1; } } else - uffd_error(res, "UFFDIO_ZEROPAGE succeeded"); + err("UFFDIO_ZEROPAGE succeeded"); return 0; } @@ -1081,37 +1047,24 @@ static int userfaultfd_zeropage_test(void) printf("testing UFFDIO_ZEROPAGE: "); fflush(stdout); - if (uffd_test_ops->release_pages(area_dst)) - return 1; + uffd_test_ctx_init(0); - if (userfaultfd_open(0)) - return 1; uffdio_register.range.start = (unsigned long) area_dst; uffdio_register.range.len = nr_pages * page_size; uffdio_register.mode = UFFDIO_REGISTER_MODE_MISSING; if (test_uffdio_wp) uffdio_register.mode |= UFFDIO_REGISTER_MODE_WP; - if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register)) { - fprintf(stderr, "register failure\n"); - exit(1); - } + if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register)) + err("register failure"); expected_ioctls = uffd_test_ops->expected_ioctls; - if ((uffdio_register.ioctls & expected_ioctls) != - expected_ioctls) { - fprintf(stderr, - "unexpected missing ioctl for anon memory\n"); - exit(1); - } + if ((uffdio_register.ioctls & expected_ioctls) != expected_ioctls) + err("unexpected missing ioctl for anon memory"); - if (uffdio_zeropage(uffd, 0)) { - if (my_bcmp(area_dst, zeropage, page_size)) { - fprintf(stderr, "zeropage is not zero\n"); - exit(1); - } - } + if (uffdio_zeropage(uffd, 0)) + if (my_bcmp(area_dst, zeropage, page_size)) + err("zeropage is not zero"); - close(uffd); printf("done.\n"); return 0; } @@ -1129,13 +1082,10 @@ static int userfaultfd_events_test(void) printf("testing events (fork, remap, remove): "); fflush(stdout); - if (uffd_test_ops->release_pages(area_dst)) - return 1; - features = UFFD_FEATURE_EVENT_FORK | UFFD_FEATURE_EVENT_REMAP | UFFD_FEATURE_EVENT_REMOVE; - if (userfaultfd_open(features)) - return 1; + uffd_test_ctx_init(features); + fcntl(uffd, F_SETFL, uffd_flags | O_NONBLOCK); uffdio_register.range.start = (unsigned long) area_dst; @@ -1143,46 +1093,31 @@ static int userfaultfd_events_test(void) uffdio_register.mode = UFFDIO_REGISTER_MODE_MISSING; if (test_uffdio_wp) uffdio_register.mode |= UFFDIO_REGISTER_MODE_WP; - if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register)) { - fprintf(stderr, "register failure\n"); - exit(1); - } + if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register)) + err("register failure"); expected_ioctls = uffd_test_ops->expected_ioctls; - if ((uffdio_register.ioctls & expected_ioctls) != expected_ioctls) { - fprintf(stderr, "unexpected missing ioctl for anon memory\n"); - exit(1); - } + if ((uffdio_register.ioctls & expected_ioctls) != expected_ioctls) + err("unexpected missing ioctl for anon memory"); - if (pthread_create(&uffd_mon, &attr, uffd_poll_thread, &stats)) { - perror("uffd_poll_thread create"); - exit(1); - } + if (pthread_create(&uffd_mon, &attr, uffd_poll_thread, &stats)) + err("uffd_poll_thread create"); pid = fork(); - if (pid < 0) { - perror("fork"); - exit(1); - } + if (pid < 0) + err("fork"); if (!pid) exit(faulting_process(0)); waitpid(pid, &err, 0); - if (err) { - fprintf(stderr, "faulting process failed\n"); - exit(1); - } - - if (write(pipefd[1], &c, sizeof(c)) != sizeof(c)) { - perror("pipe write"); - exit(1); - } + if (err) + err("faulting process failed"); + if (write(pipefd[1], &c, sizeof(c)) != sizeof(c)) + err("pipe write"); if (pthread_join(uffd_mon, NULL)) return 1; - close(uffd); - uffd_stats_report(&stats, 1); return stats.missing_faults != nr_pages; @@ -1202,12 +1137,9 @@ static int userfaultfd_sig_test(void) printf("testing signal delivery: "); fflush(stdout); - if (uffd_test_ops->release_pages(area_dst)) - return 1; - features = UFFD_FEATURE_EVENT_FORK|UFFD_FEATURE_SIGBUS; - if (userfaultfd_open(features)) - return 1; + uffd_test_ctx_init(features); + fcntl(uffd, F_SETFL, uffd_flags | O_NONBLOCK); uffdio_register.range.start = (unsigned long) area_dst; @@ -1215,57 +1147,40 @@ static int userfaultfd_sig_test(void) uffdio_register.mode = UFFDIO_REGISTER_MODE_MISSING; if (test_uffdio_wp) uffdio_register.mode |= UFFDIO_REGISTER_MODE_WP; - if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register)) { - fprintf(stderr, "register failure\n"); - exit(1); - } + if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register)) + err("register failure"); expected_ioctls = uffd_test_ops->expected_ioctls; - if ((uffdio_register.ioctls & expected_ioctls) != expected_ioctls) { - fprintf(stderr, "unexpected missing ioctl for anon memory\n"); - exit(1); - } + if ((uffdio_register.ioctls & expected_ioctls) != expected_ioctls) + err("unexpected missing ioctl for anon memory"); - if (faulting_process(1)) { - fprintf(stderr, "faulting process failed\n"); - exit(1); - } + if (faulting_process(1)) + err("faulting process failed"); - if (uffd_test_ops->release_pages(area_dst)) - return 1; + uffd_test_ops->release_pages(area_dst); - if (pthread_create(&uffd_mon, &attr, uffd_poll_thread, &stats)) { - perror("uffd_poll_thread create"); - exit(1); - } + if (pthread_create(&uffd_mon, &attr, uffd_poll_thread, &stats)) + err("uffd_poll_thread create"); pid = fork(); - if (pid < 0) { - perror("fork"); - exit(1); - } + if (pid < 0) + err("fork"); if (!pid) exit(faulting_process(2)); waitpid(pid, &err, 0); - if (err) { - fprintf(stderr, "faulting process failed\n"); - exit(1); - } - - if (write(pipefd[1], &c, sizeof(c)) != sizeof(c)) { - perror("pipe write"); - exit(1); - } + if (err) + err("faulting process failed"); + if (write(pipefd[1], &c, sizeof(c)) != sizeof(c)) + err("pipe write"); if (pthread_join(uffd_mon, (void **)&userfaults)) return 1; printf("done.\n"); if (userfaults) - fprintf(stderr, "Signal test failed, userfaults: %ld\n", - userfaults); - close(uffd); + err("Signal test failed, userfaults: %ld", userfaults); + return userfaults != 0; } @@ -1279,7 +1194,7 @@ static int userfaultfd_minor_test(void) void *expected_page; char c; struct uffd_stats stats = { 0 }; - uint64_t features = UFFD_FEATURE_MINOR_HUGETLBFS; + uint64_t req_features, features_out; if (!test_uffdio_minor) return 0; @@ -1287,13 +1202,17 @@ static int userfaultfd_minor_test(void) printf("testing minor faults: "); fflush(stdout); - if (uffd_test_ops->release_pages(area_dst)) + if (test_type == TEST_HUGETLB) + req_features = UFFD_FEATURE_MINOR_HUGETLBFS; + else if (test_type == TEST_SHMEM) + req_features = UFFD_FEATURE_MINOR_SHMEM; + else return 1; - if (userfaultfd_open_ext(&features)) - return 1; - /* If kernel reports the feature isn't supported, skip the test. */ - if (!(features & UFFD_FEATURE_MINOR_HUGETLBFS)) { + features_out = req_features; + uffd_test_ctx_init_ext(&features_out); + /* If kernel reports required features aren't supported, skip test. */ + if ((features_out & req_features) != req_features) { printf("skipping test due to lack of feature support\n"); fflush(stdout); return 0; @@ -1302,17 +1221,13 @@ static int userfaultfd_minor_test(void) uffdio_register.range.start = (unsigned long)area_dst_alias; uffdio_register.range.len = nr_pages * page_size; uffdio_register.mode = UFFDIO_REGISTER_MODE_MINOR; - if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register)) { - fprintf(stderr, "register failure\n"); - exit(1); - } + if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register)) + err("register failure"); expected_ioctls = uffd_test_ops->expected_ioctls; expected_ioctls |= 1 << _UFFDIO_CONTINUE; - if ((uffdio_register.ioctls & expected_ioctls) != expected_ioctls) { - fprintf(stderr, "unexpected missing ioctl(s)\n"); - exit(1); - } + if ((uffdio_register.ioctls & expected_ioctls) != expected_ioctls) + err("unexpected missing ioctl(s)"); /* * After registering with UFFD, populate the non-UFFD-registered side of @@ -1323,10 +1238,8 @@ static int userfaultfd_minor_test(void) page_size); } - if (pthread_create(&uffd_mon, &attr, uffd_poll_thread, &stats)) { - perror("uffd_poll_thread create"); - exit(1); - } + if (pthread_create(&uffd_mon, &attr, uffd_poll_thread, &stats)) + err("uffd_poll_thread create"); /* * Read each of the pages back using the UFFD-registered mapping. We @@ -1335,92 +1248,173 @@ static int userfaultfd_minor_test(void) * page's contents, and then issuing a CONTINUE ioctl. */ - if (posix_memalign(&expected_page, page_size, page_size)) { - fprintf(stderr, "out of memory\n"); - return 1; - } + if (posix_memalign(&expected_page, page_size, page_size)) + err("out of memory"); for (p = 0; p < nr_pages; ++p) { expected_byte = ~((uint8_t)(p % ((uint8_t)-1))); memset(expected_page, expected_byte, page_size); if (my_bcmp(expected_page, area_dst_alias + (p * page_size), - page_size)) { - fprintf(stderr, - "unexpected page contents after minor fault\n"); - exit(1); - } + page_size)) + err("unexpected page contents after minor fault"); } - if (write(pipefd[1], &c, sizeof(c)) != sizeof(c)) { - perror("pipe write"); - exit(1); - } + if (write(pipefd[1], &c, sizeof(c)) != sizeof(c)) + err("pipe write"); if (pthread_join(uffd_mon, NULL)) return 1; - close(uffd); - uffd_stats_report(&stats, 1); return stats.missing_faults != 0 || stats.minor_faults != nr_pages; } +#define BIT_ULL(nr) (1ULL << (nr)) +#define PM_SOFT_DIRTY BIT_ULL(55) +#define PM_MMAP_EXCLUSIVE BIT_ULL(56) +#define PM_UFFD_WP BIT_ULL(57) +#define PM_FILE BIT_ULL(61) +#define PM_SWAP BIT_ULL(62) +#define PM_PRESENT BIT_ULL(63) + +static int pagemap_open(void) +{ + int fd = open("/proc/self/pagemap", O_RDONLY); + + if (fd < 0) + err("open pagemap"); + + return fd; +} + +static uint64_t pagemap_read_vaddr(int fd, void *vaddr) +{ + uint64_t value; + int ret; + + ret = pread(fd, &value, sizeof(uint64_t), + ((uint64_t)vaddr >> 12) * sizeof(uint64_t)); + if (ret != sizeof(uint64_t)) + err("pread() on pagemap failed"); + + return value; +} + +/* This macro let __LINE__ works in err() */ +#define pagemap_check_wp(value, wp) do { \ + if (!!(value & PM_UFFD_WP) != wp) \ + err("pagemap uffd-wp bit error: 0x%"PRIx64, value); \ + } while (0) + +static int pagemap_test_fork(bool present) +{ + pid_t child = fork(); + uint64_t value; + int fd, result; + + if (!child) { + /* Open the pagemap fd of the child itself */ + fd = pagemap_open(); + value = pagemap_read_vaddr(fd, area_dst); + /* + * After fork() uffd-wp bit should be gone as long as we're + * without UFFD_FEATURE_EVENT_FORK + */ + pagemap_check_wp(value, false); + /* Succeed */ + exit(0); + } + waitpid(child, &result, 0); + return result; +} + +static void userfaultfd_pagemap_test(unsigned int test_pgsize) +{ + struct uffdio_register uffdio_register; + int pagemap_fd; + uint64_t value; + + /* Pagemap tests uffd-wp only */ + if (!test_uffdio_wp) + return; + + /* Not enough memory to test this page size */ + if (test_pgsize > nr_pages * page_size) + return; + + printf("testing uffd-wp with pagemap (pgsize=%u): ", test_pgsize); + /* Flush so it doesn't flush twice in parent/child later */ + fflush(stdout); + + uffd_test_ctx_init(0); + + if (test_pgsize > page_size) { + /* This is a thp test */ + if (madvise(area_dst, nr_pages * page_size, MADV_HUGEPAGE)) + err("madvise(MADV_HUGEPAGE) failed"); + } else if (test_pgsize == page_size) { + /* This is normal page test; force no thp */ + if (madvise(area_dst, nr_pages * page_size, MADV_NOHUGEPAGE)) + err("madvise(MADV_NOHUGEPAGE) failed"); + } + + uffdio_register.range.start = (unsigned long) area_dst; + uffdio_register.range.len = nr_pages * page_size; + uffdio_register.mode = UFFDIO_REGISTER_MODE_WP; + if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register)) + err("register failed"); + + pagemap_fd = pagemap_open(); + + /* Touch the page */ + *area_dst = 1; + wp_range(uffd, (uint64_t)area_dst, test_pgsize, true); + value = pagemap_read_vaddr(pagemap_fd, area_dst); + pagemap_check_wp(value, true); + /* Make sure uffd-wp bit dropped when fork */ + if (pagemap_test_fork(true)) + err("Detected stall uffd-wp bit in child"); + + /* Exclusive required or PAGEOUT won't work */ + if (!(value & PM_MMAP_EXCLUSIVE)) + err("multiple mapping detected: 0x%"PRIx64, value); + + if (madvise(area_dst, test_pgsize, MADV_PAGEOUT)) + err("madvise(MADV_PAGEOUT) failed"); + + /* Uffd-wp should persist even swapped out */ + value = pagemap_read_vaddr(pagemap_fd, area_dst); + pagemap_check_wp(value, true); + /* Make sure uffd-wp bit dropped when fork */ + if (pagemap_test_fork(false)) + err("Detected stall uffd-wp bit in child"); + + /* Unprotect; this tests swap pte modifications */ + wp_range(uffd, (uint64_t)area_dst, page_size, false); + value = pagemap_read_vaddr(pagemap_fd, area_dst); + pagemap_check_wp(value, false); + + /* Fault in the page from disk */ + *area_dst = 2; + value = pagemap_read_vaddr(pagemap_fd, area_dst); + pagemap_check_wp(value, false); + + close(pagemap_fd); + printf("done\n"); +} + static int userfaultfd_stress(void) { void *area; char *tmp_area; unsigned long nr; struct uffdio_register uffdio_register; - unsigned long cpu; - int err; struct uffd_stats uffd_stats[nr_cpus]; - uffd_test_ops->allocate_area((void **)&area_src); - if (!area_src) - return 1; - uffd_test_ops->allocate_area((void **)&area_dst); - if (!area_dst) - return 1; + uffd_test_ctx_init(0); - if (userfaultfd_open(0)) - return 1; - - count_verify = malloc(nr_pages * sizeof(unsigned long long)); - if (!count_verify) { - perror("count_verify"); - return 1; - } - - for (nr = 0; nr < nr_pages; nr++) { - *area_mutex(area_src, nr) = (pthread_mutex_t) - PTHREAD_MUTEX_INITIALIZER; - count_verify[nr] = *area_count(area_src, nr) = 1; - /* - * In the transition between 255 to 256, powerpc will - * read out of order in my_bcmp and see both bytes as - * zero, so leave a placeholder below always non-zero - * after the count, to avoid my_bcmp to trigger false - * positives. - */ - *(area_count(area_src, nr) + 1) = 1; - } - - pipefd = malloc(sizeof(int) * nr_cpus * 2); - if (!pipefd) { - perror("pipefd"); - return 1; - } - for (cpu = 0; cpu < nr_cpus; cpu++) { - if (pipe2(&pipefd[cpu*2], O_CLOEXEC | O_NONBLOCK)) { - perror("pipe"); - return 1; - } - } - - if (posix_memalign(&area, page_size, page_size)) { - fprintf(stderr, "out of memory\n"); - return 1; - } + if (posix_memalign(&area, page_size, page_size)) + err("out of memory"); zeropage = area; bzero(zeropage, page_size); @@ -1429,7 +1423,6 @@ static int userfaultfd_stress(void) pthread_attr_init(&attr); pthread_attr_setstacksize(&attr, 16*1024*1024); - err = 0; while (bounces--) { unsigned long expected_ioctls; @@ -1458,25 +1451,18 @@ static int userfaultfd_stress(void) uffdio_register.mode = UFFDIO_REGISTER_MODE_MISSING; if (test_uffdio_wp) uffdio_register.mode |= UFFDIO_REGISTER_MODE_WP; - if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register)) { - fprintf(stderr, "register failure\n"); - return 1; - } + if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register)) + err("register failure"); expected_ioctls = uffd_test_ops->expected_ioctls; if ((uffdio_register.ioctls & expected_ioctls) != - expected_ioctls) { - fprintf(stderr, - "unexpected missing ioctl for anon memory\n"); - return 1; - } + expected_ioctls) + err("unexpected missing ioctl for anon memory"); if (area_dst_alias) { uffdio_register.range.start = (unsigned long) area_dst_alias; - if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register)) { - fprintf(stderr, "register failure alias\n"); - return 1; - } + if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register)) + err("register failure alias"); } /* @@ -1503,8 +1489,7 @@ static int userfaultfd_stress(void) * MADV_DONTNEED only after the UFFDIO_REGISTER, so it's * required to MADV_DONTNEED here. */ - if (uffd_test_ops->release_pages(area_dst)) - return 1; + uffd_test_ops->release_pages(area_dst); uffd_stats_reset(uffd_stats, nr_cpus); @@ -1518,33 +1503,22 @@ static int userfaultfd_stress(void) nr_pages * page_size, false); /* unregister */ - if (ioctl(uffd, UFFDIO_UNREGISTER, &uffdio_register.range)) { - fprintf(stderr, "unregister failure\n"); - return 1; - } + if (ioctl(uffd, UFFDIO_UNREGISTER, &uffdio_register.range)) + err("unregister failure"); if (area_dst_alias) { uffdio_register.range.start = (unsigned long) area_dst; if (ioctl(uffd, UFFDIO_UNREGISTER, - &uffdio_register.range)) { - fprintf(stderr, "unregister failure alias\n"); - return 1; - } + &uffdio_register.range)) + err("unregister failure alias"); } /* verification */ - if (bounces & BOUNCE_VERIFY) { - for (nr = 0; nr < nr_pages; nr++) { - if (*area_count(area_dst, nr) != count_verify[nr]) { - fprintf(stderr, - "error area_count %Lu %Lu %lu\n", - *area_count(area_src, nr), - count_verify[nr], - nr); - err = 1; - bounces = 0; - } - } - } + if (bounces & BOUNCE_VERIFY) + for (nr = 0; nr < nr_pages; nr++) + if (*area_count(area_dst, nr) != count_verify[nr]) + err("error area_count %llu %llu %lu\n", + *area_count(area_src, nr), + count_verify[nr], nr); /* prepare next bounce */ tmp_area = area_src; @@ -1558,10 +1532,21 @@ static int userfaultfd_stress(void) uffd_stats_report(uffd_stats, nr_cpus); } - if (err) - return err; + if (test_type == TEST_ANON) { + /* + * shmem/hugetlb won't be able to run since they have different + * behavior on fork() (file-backed memory normally drops ptes + * directly when fork), meanwhile the pagemap test will verify + * pgtable entry of fork()ed child. + */ + userfaultfd_pagemap_test(page_size); + /* + * Hard-code for x86_64 for now for 2M THP, as x86_64 is + * currently the only one that supports uffd-wp + */ + userfaultfd_pagemap_test(page_size * 512); + } - close(uffd); return userfaultfd_zeropage_test() || userfaultfd_sig_test() || userfaultfd_events_test() || userfaultfd_minor_test(); } @@ -1610,8 +1595,9 @@ static void set_test_type(const char *type) map_shared = true; test_type = TEST_SHMEM; uffd_test_ops = &shmem_uffd_test_ops; + test_uffdio_minor = true; } else { - fprintf(stderr, "Unknown test type: %s\n", type); exit(1); + err("Unknown test type: %s", type); } if (test_type == TEST_HUGETLB) @@ -1619,15 +1605,11 @@ static void set_test_type(const char *type) else page_size = sysconf(_SC_PAGE_SIZE); - if (!page_size) { - fprintf(stderr, "Unable to determine page size\n"); - exit(2); - } + if (!page_size) + err("Unable to determine page size"); if ((unsigned long) area_count(NULL, 0) + sizeof(unsigned long long) * 2 - > page_size) { - fprintf(stderr, "Impossible to run this test\n"); - exit(2); - } + > page_size) + err("Impossible to run this test"); } static void sigalrm(int sig) @@ -1644,10 +1626,8 @@ int main(int argc, char **argv) if (argc < 4) usage(); - if (signal(SIGALRM, sigalrm) == SIG_ERR) { - fprintf(stderr, "failed to arm SIGALRM"); - exit(1); - } + if (signal(SIGALRM, sigalrm) == SIG_ERR) + err("failed to arm SIGALRM"); alarm(ALARM_INTERVAL_SECS); set_test_type(argv[1]); @@ -1656,13 +1636,13 @@ int main(int argc, char **argv) nr_pages_per_cpu = atol(argv[2]) * 1024*1024 / page_size / nr_cpus; if (!nr_pages_per_cpu) { - fprintf(stderr, "invalid MiB\n"); + _err("invalid MiB"); usage(); } bounces = atoi(argv[3]); if (bounces <= 0) { - fprintf(stderr, "invalid bounces\n"); + _err("invalid bounces"); usage(); } nr_pages = nr_pages_per_cpu * nr_cpus; @@ -1671,16 +1651,20 @@ int main(int argc, char **argv) if (argc < 5) usage(); huge_fd = open(argv[4], O_CREAT | O_RDWR, 0755); - if (huge_fd < 0) { - fprintf(stderr, "Open of %s failed", argv[3]); - perror("open"); - exit(1); - } - if (ftruncate(huge_fd, 0)) { - fprintf(stderr, "ftruncate %s to size 0 failed", argv[3]); - perror("ftruncate"); - exit(1); - } + if (huge_fd < 0) + err("Open of %s failed", argv[4]); + if (ftruncate(huge_fd, 0)) + err("ftruncate %s to size 0 failed", argv[4]); + } else if (test_type == TEST_SHMEM) { + shm_fd = memfd_create(argv[0], 0); + if (shm_fd < 0) + err("memfd_create"); + if (ftruncate(shm_fd, nr_pages * page_size * 2)) + err("ftruncate"); + if (fallocate(shm_fd, + FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE, 0, + nr_pages * page_size * 2)) + err("fallocate"); } printf("nr_pages: %lu, nr_pages_per_cpu: %lu\n", nr_pages, nr_pages_per_cpu);