diff options
172 files changed, 1766 insertions, 2820 deletions
diff --git a/Documentation/vm/cleancache.rst b/Documentation/vm/cleancache.rst deleted file mode 100644 index 68cba9131c31..000000000000 --- a/Documentation/vm/cleancache.rst +++ /dev/null @@ -1,296 +0,0 @@ -.. _cleancache: - -========== -Cleancache -========== - -Motivation -========== - -Cleancache is a new optional feature provided by the VFS layer that -potentially dramatically increases page cache effectiveness for -many workloads in many environments at a negligible cost. - -Cleancache can be thought of as a page-granularity victim cache for clean -pages that the kernel's pageframe replacement algorithm (PFRA) would like -to keep around, but can't since there isn't enough memory. So when the -PFRA "evicts" a page, it first attempts to use cleancache code to -put the data contained in that page into "transcendent memory", memory -that is not directly accessible or addressable by the kernel and is -of unknown and possibly time-varying size. - -Later, when a cleancache-enabled filesystem wishes to access a page -in a file on disk, it first checks cleancache to see if it already -contains it; if it does, the page of data is copied into the kernel -and a disk access is avoided. - -Transcendent memory "drivers" for cleancache are currently implemented -in Xen (using hypervisor memory) and zcache (using in-kernel compressed -memory) and other implementations are in development. - -:ref:`FAQs <faq>` are included below. - -Implementation Overview -======================= - -A cleancache "backend" that provides transcendent memory registers itself -to the kernel's cleancache "frontend" by calling cleancache_register_ops, -passing a pointer to a cleancache_ops structure with funcs set appropriately. -The functions provided must conform to certain semantics as follows: - -Most important, cleancache is "ephemeral". Pages which are copied into -cleancache have an indefinite lifetime which is completely unknowable -by the kernel and so may or may not still be in cleancache at any later time. -Thus, as its name implies, cleancache is not suitable for dirty pages. -Cleancache has complete discretion over what pages to preserve and what -pages to discard and when. - -Mounting a cleancache-enabled filesystem should call "init_fs" to obtain a -pool id which, if positive, must be saved in the filesystem's superblock; -a negative return value indicates failure. A "put_page" will copy a -(presumably about-to-be-evicted) page into cleancache and associate it with -the pool id, a file key, and a page index into the file. (The combination -of a pool id, a file key, and an index is sometimes called a "handle".) -A "get_page" will copy the page, if found, from cleancache into kernel memory. -An "invalidate_page" will ensure the page no longer is present in cleancache; -an "invalidate_inode" will invalidate all pages associated with the specified -file; and, when a filesystem is unmounted, an "invalidate_fs" will invalidate -all pages in all files specified by the given pool id and also surrender -the pool id. - -An "init_shared_fs", like init_fs, obtains a pool id but tells cleancache -to treat the pool as shared using a 128-bit UUID as a key. On systems -that may run multiple kernels (such as hard partitioned or virtualized -systems) that may share a clustered filesystem, and where cleancache -may be shared among those kernels, calls to init_shared_fs that specify the -same UUID will receive the same pool id, thus allowing the pages to -be shared. Note that any security requirements must be imposed outside -of the kernel (e.g. by "tools" that control cleancache). Or a -cleancache implementation can simply disable shared_init by always -returning a negative value. - -If a get_page is successful on a non-shared pool, the page is invalidated -(thus making cleancache an "exclusive" cache). On a shared pool, the page -is NOT invalidated on a successful get_page so that it remains accessible to -other sharers. The kernel is responsible for ensuring coherency between -cleancache (shared or not), the page cache, and the filesystem, using -cleancache invalidate operations as required. - -Note that cleancache must enforce put-put-get coherency and get-get -coherency. For the former, if two puts are made to the same handle but -with different data, say AAA by the first put and BBB by the second, a -subsequent get can never return the stale data (AAA). For get-get coherency, -if a get for a given handle fails, subsequent gets for that handle will -never succeed unless preceded by a successful put with that handle. - -Last, cleancache provides no SMP serialization guarantees; if two -different Linux threads are simultaneously putting and invalidating a page -with the same handle, the results are indeterminate. Callers must -lock the page to ensure serial behavior. - -Cleancache Performance Metrics -============================== - -If properly configured, monitoring of cleancache is done via debugfs in -the `/sys/kernel/debug/cleancache` directory. The effectiveness of cleancache -can be measured (across all filesystems) with: - -``succ_gets`` - number of gets that were successful - -``failed_gets`` - number of gets that failed - -``puts`` - number of puts attempted (all "succeed") - -``invalidates`` - number of invalidates attempted - -A backend implementation may provide additional metrics. - -.. _faq: - -FAQ -=== - -* Where's the value? (Andrew Morton) - -Cleancache provides a significant performance benefit to many workloads -in many environments with negligible overhead by improving the -effectiveness of the pagecache. Clean pagecache pages are -saved in transcendent memory (RAM that is otherwise not directly -addressable to the kernel); fetching those pages later avoids "refaults" -and thus disk reads. - -Cleancache (and its sister code "frontswap") provide interfaces for -this transcendent memory (aka "tmem"), which conceptually lies between -fast kernel-directly-addressable RAM and slower DMA/asynchronous devices. -Disallowing direct kernel or userland reads/writes to tmem -is ideal when data is transformed to a different form and size (such -as with compression) or secretly moved (as might be useful for write- -balancing for some RAM-like devices). Evicted page-cache pages (and -swap pages) are a great use for this kind of slower-than-RAM-but-much- -faster-than-disk transcendent memory, and the cleancache (and frontswap) -"page-object-oriented" specification provides a nice way to read and -write -- and indirectly "name" -- the pages. - -In the virtual case, the whole point of virtualization is to statistically -multiplex physical resources across the varying demands of multiple -virtual machines. This is really hard to do with RAM and efforts to -do it well with no kernel change have essentially failed (except in some -well-publicized special-case workloads). Cleancache -- and frontswap -- -with a fairly small impact on the kernel, provide a huge amount -of flexibility for more dynamic, flexible RAM multiplexing. -Specifically, the Xen Transcendent Memory backend allows otherwise -"fallow" hypervisor-owned RAM to not only be "time-shared" between multiple -virtual machines, but the pages can be compressed and deduplicated to -optimize RAM utilization. And when guest OS's are induced to surrender -underutilized RAM (e.g. with "self-ballooning"), page cache pages -are the first to go, and cleancache allows those pages to be -saved and reclaimed if overall host system memory conditions allow. - -And the identical interface used for cleancache can be used in -physical systems as well. The zcache driver acts as a memory-hungry -device that stores pages of data in a compressed state. And -the proposed "RAMster" driver shares RAM across multiple physical -systems. - -* Why does cleancache have its sticky fingers so deep inside the - filesystems and VFS? (Andrew Morton and Christoph Hellwig) - -The core hooks for cleancache in VFS are in most cases a single line -and the minimum set are placed precisely where needed to maintain -coherency (via cleancache_invalidate operations) between cleancache, -the page cache, and disk. All hooks compile into nothingness if -cleancache is config'ed off and turn into a function-pointer- -compare-to-NULL if config'ed on but no backend claims the ops -functions, or to a compare-struct-element-to-negative if a -backend claims the ops functions but a filesystem doesn't enable -cleancache. - -Some filesystems are built entirely on top of VFS and the hooks -in VFS are sufficient, so don't require an "init_fs" hook; the -initial implementation of cleancache didn't provide this hook. -But for some filesystems (such as btrfs), the VFS hooks are -incomplete and one or more hooks in fs-specific code are required. -And for some other filesystems, such as tmpfs, cleancache may -be counterproductive. So it seemed prudent to require a filesystem -to "opt in" to use cleancache, which requires adding a hook in -each filesystem. Not all filesystems are supported by cleancache -only because they haven't been tested. The existing set should -be sufficient to validate the concept, the opt-in approach means -that untested filesystems are not affected, and the hooks in the -existing filesystems should make it very easy to add more -filesystems in the future. - -The total impact of the hooks to existing fs and mm files is only -about 40 lines added (not counting comments and blank lines). - -* Why not make cleancache asynchronous and batched so it can more - easily interface with real devices with DMA instead of copying each - individual page? (Minchan Kim) - -The one-page-at-a-time copy semantics simplifies the implementation -on both the frontend and backend and also allows the backend to -do fancy things on-the-fly like page compression and -page deduplication. And since the data is "gone" (copied into/out -of the pageframe) before the cleancache get/put call returns, -a great deal of race conditions and potential coherency issues -are avoided. While the interface seems odd for a "real device" -or for real kernel-addressable RAM, it makes perfect sense for -transcendent memory. - -* Why is non-shared cleancache "exclusive"? And where is the - page "invalidated" after a "get"? (Minchan Kim) - -The main reason is to free up space in transcendent memory and -to avoid unnecessary cleancache_invalidate calls. If you want inclusive, -the page can be "put" immediately following the "get". If -put-after-get for inclusive becomes common, the interface could -be easily extended to add a "get_no_invalidate" call. - -The invalidate is done by the cleancache backend implementation. - -* What's the performance impact? - -Performance analysis has been presented at OLS'09 and LCA'10. -Briefly, performance gains can be significant on most workloads, -especially when memory pressure is high (e.g. when RAM is -overcommitted in a virtual workload); and because the hooks are -invoked primarily in place of or in addition to a disk read/write, -overhead is negligible even in worst case workloads. Basically -cleancache replaces I/O with memory-copy-CPU-overhead; on older -single-core systems with slow memory-copy speeds, cleancache -has little value, but in newer multicore machines, especially -consolidated/virtualized machines, it has great value. - -* How do I add cleancache support for filesystem X? (Boaz Harrash) - -Filesystems that are well-behaved and conform to certain -restrictions can utilize cleancache simply by making a call to -cleancache_init_fs at mount time. Unusual, misbehaving, or -poorly layered filesystems must either add additional hooks -and/or undergo extensive additional testing... or should just -not enable the optional cleancache. - -Some points for a filesystem to consider: - - - The FS should be block-device-based (e.g. a ram-based FS such - as tmpfs should not enable cleancache) - - To ensure coherency/correctness, the FS must ensure that all - file removal or truncation operations either go through VFS or - add hooks to do the equivalent cleancache "invalidate" operations - - To ensure coherency/correctness, either inode numbers must - be unique across the lifetime of the on-disk file OR the - FS must provide an "encode_fh" function. - - The FS must call the VFS superblock alloc and deactivate routines - or add hooks to do the equivalent cleancache calls done there. - - To maximize performance, all pages fetched from the FS should - go through the do_mpag_readpage routine or the FS should add - hooks to do the equivalent (cf. btrfs) - - Currently, the FS blocksize must be the same as PAGESIZE. This - is not an architectural restriction, but no backends currently - support anything different. - - A clustered FS should invoke the "shared_init_fs" cleancache - hook to get best performance for some backends. - -* Why not use the KVA of the inode as the key? (Christoph Hellwig) - -If cleancache would use the inode virtual address instead of -inode/filehandle, the pool id could be eliminated. But, this -won't work because cleancache retains pagecache data pages -persistently even when the inode has been pruned from the -inode unused list, and only invalidates the data page if the file -gets removed/truncated. So if cleancache used the inode kva, -there would be potential coherency issues if/when the inode -kva is reused for a different file. Alternately, if cleancache -invalidated the pages when the inode kva was freed, much of the value -of cleancache would be lost because the cache of pages in cleanache -is potentially much larger than the kernel pagecache and is most -useful if the pages survive inode cache removal. - -* Why is a global variable required? - -The cleancache_enabled flag is checked in all of the frequently-used -cleancache hooks. The alternative is a function call to check a static -variable. Since cleancache is enabled dynamically at runtime, systems -that don't enable cleancache would suffer thousands (possibly -tens-of-thousands) of unnecessary function calls per second. So the -global variable allows cleancache to be enabled by default at compile -time, but have insignificant performance impact when cleancache remains -disabled at runtime. - -* Does cleanache work with KVM? - -The memory model of KVM is sufficiently different that a cleancache -backend may have less value for KVM. This remains to be tested, -especially in an overcommitted system. - -* Does cleancache work in userspace? It sounds useful for - memory hungry caches like web browsers. (Jamie Lokier) - -No plans yet, though we agree it sounds useful, at least for -apps that bypass the page cache (e.g. O_DIRECT). - -Last updated: Dan Magenheimer, April 13 2011 diff --git a/Documentation/vm/frontswap.rst b/Documentation/vm/frontswap.rst index 1979f430c1c5..feecc5e24477 100644 --- a/Documentation/vm/frontswap.rst +++ b/Documentation/vm/frontswap.rst @@ -8,12 +8,6 @@ Frontswap provides a "transcendent memory" interface for swap pages. In some environments, dramatic performance savings may be obtained because swapped pages are saved in RAM (or a RAM-like device) instead of a swap disk. -(Note, frontswap -- and :ref:`cleancache` (merged at 3.0) -- are the "frontends" -and the only necessary changes to the core kernel for transcendent memory; -all other supporting code -- the "backends" -- is implemented as drivers. -See the LWN.net article `Transcendent memory in a nutshell`_ -for a detailed overview of frontswap and related kernel parts) - .. _Transcendent memory in a nutshell: https://lwn.net/Articles/454795/ Frontswap is so named because it can be thought of as the opposite of @@ -45,12 +39,6 @@ a disk write and, if the data is later read back, a disk read are avoided. If a store returns failure, transcendent memory has rejected the data, and the page can be written to swap as usual. -If a backend chooses, frontswap can be configured as a "writethrough -cache" by calling frontswap_writethrough(). In this mode, the reduction -in swap device writes is lost (and also a non-trivial performance advantage) -in order to allow the backend to arbitrarily "reclaim" space used to -store frontswap pages to more completely manage its memory usage. - Note that if a page is stored and the page already exists in transcendent memory (a "duplicate" store), either the store succeeds and the data is overwritten, or the store fails AND the page is invalidated. This ensures stale data may @@ -87,11 +75,9 @@ This interface is ideal when data is transformed to a different form and size (such as with compression) or secretly moved (as might be useful for write-balancing for some RAM-like devices). Swap pages (and evicted page-cache pages) are a great use for this kind of slower-than-RAM- -but-much-faster-than-disk "pseudo-RAM device" and the frontswap (and -cleancache) interface to transcendent memory provides a nice way to read -and write -- and indirectly "name" -- the pages. +but-much-faster-than-disk "pseudo-RAM device". -Frontswap -- and cleancache -- with a fairly small impact on the kernel, +Frontswap with a fairly small impact on the kernel, provides a huge amount of flexibility for more dynamic, flexible RAM utilization in various system configurations: @@ -269,19 +255,6 @@ the old data and ensure that it is no longer accessible. Since the swap subsystem then writes the new data to the read swap device, this is the correct course of action to ensure coherency. -* What is frontswap_shrink for? - -When the (non-frontswap) swap subsystem swaps out a page to a real -swap device, that page is only taking up low-value pre-allocated disk -space. But if frontswap has placed a page in transcendent memory, that -page may be taking up valuable real estate. The frontswap_shrink -routine allows code outside of the swap subsystem to force pages out -of the memory managed by frontswap and back into kernel-addressable memory. -For example, in RAMster, a "suction driver" thread will attempt -to "repatriate" pages sent to a remote machine back to the local machine; -this is driven using the frontswap_shrink mechanism when memory pressure -subsides. - * Why does the frontswap patch create the new include file swapfile.h? The frontswap code depends on some swap-subsystem-internal data diff --git a/Documentation/vm/index.rst b/Documentation/vm/index.rst index 932440805453..44365c4574a3 100644 --- a/Documentation/vm/index.rst +++ b/Documentation/vm/index.rst @@ -15,7 +15,6 @@ algorithms. If you are looking for advice on simply allocating memory, see the active_mm arch_pgtable_helpers balance - cleancache damon/index free_page_reporting frontswap diff --git a/MAINTAINERS b/MAINTAINERS index 6c08cbe953fe..45f8750f6e30 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -4705,13 +4705,6 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux.git for-next/cla F: include/linux/cfi.h F: kernel/cfi.c -CLEANCACHE API -M: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> -L: linux-kernel@vger.kernel.org -S: Maintained -F: include/linux/cleancache.h -F: mm/cleancache.c - CLK API M: Russell King <linux@armlinux.org.uk> L: linux-clk@vger.kernel.org diff --git a/arch/alpha/kernel/srm_env.c b/arch/alpha/kernel/srm_env.c index 528d2be58182..217b4dca51dd 100644 --- a/arch/alpha/kernel/srm_env.c +++ b/arch/alpha/kernel/srm_env.c @@ -83,14 +83,14 @@ static int srm_env_proc_show(struct seq_file *m, void *v) static int srm_env_proc_open(struct inode *inode, struct file *file) { - return single_open(file, srm_env_proc_show, PDE_DATA(inode)); + return single_open(file, srm_env_proc_show, pde_data(inode)); } static ssize_t srm_env_proc_write(struct file *file, const char __user *buffer, size_t count, loff_t *pos) { int res; - unsigned long id = (unsigned long)PDE_DATA(file_inode(file)); + unsigned long id = (unsigned long)pde_data(file_inode(file)); char *buf = (char *) __get_free_page(GFP_USER); unsigned long ret1, ret2; diff --git a/arch/arm/configs/bcm2835_defconfig b/arch/arm/configs/bcm2835_defconfig index 383c632eba7b..a9ed79b7f871 100644 --- a/arch/arm/configs/bcm2835_defconfig +++ b/arch/arm/configs/bcm2835_defconfig @@ -31,7 +31,6 @@ CONFIG_ARCH_BCM2835=y CONFIG_PREEMPT_VOLUNTARY=y CONFIG_AEABI=y CONFIG_KSM=y -CONFIG_CLEANCACHE=y CONFIG_CMA=y CONFIG_SECCOMP=y CONFIG_KEXEC=y diff --git a/arch/arm/configs/qcom_defconfig b/arch/arm/configs/qcom_defconfig index 0daa9c0d298e..9981566f2096 100644 --- a/arch/arm/configs/qcom_defconfig +++ b/arch/arm/configs/qcom_defconfig @@ -27,7 +27,6 @@ CONFIG_PCIE_QCOM=y CONFIG_SMP=y CONFIG_PREEMPT=y CONFIG_HIGHMEM=y -CONFIG_CLEANCACHE=y CONFIG_ARM_APPENDED_DTB=y CONFIG_ARM_ATAG_DTB_COMPAT=y CONFIG_CPU_IDLE=y diff --git a/arch/arm/kernel/atags_proc.c b/arch/arm/kernel/atags_proc.c index 3c2faf2bd124..3ec2afe78423 100644 --- a/arch/arm/kernel/atags_proc.c +++ b/arch/arm/kernel/atags_proc.c @@ -13,7 +13,7 @@ struct buffer { static ssize_t atags_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { - struct buffer *b = PDE_DATA(file_inode(file)); + struct buffer *b = pde_data(file_inode(file)); return simple_read_from_buffer(buf, count, ppos, b->data, b->size); } diff --git a/arch/arm/mm/alignment.c b/arch/arm/mm/alignment.c index adbb3817d0be..6f499559d193 100644 --- a/arch/arm/mm/alignment.c +++ b/arch/arm/mm/alignment.c @@ -1005,7 +1005,7 @@ static int __init noalign_setup(char *__unused) __setup("noalign", noalign_setup); /* - * This needs to be done after sysctl_init, otherwise sys/ will be + * This needs to be done after sysctl_init_bases(), otherwise sys/ will be * overwritten. Actually, this shouldn't be in sys/ at all since * it isn't a sysctl, and it doesn't contain sysctl information. * We now locate it in /proc/cpu/alignment instead. diff --git a/arch/ia64/kernel/salinfo.c b/arch/ia64/kernel/salinfo.c index a25ab9b37953..bd3ba276e69c 100644 --- a/arch/ia64/kernel/salinfo.c +++ b/arch/ia64/kernel/salinfo.c @@ -282,7 +282,7 @@ salinfo_event_open(struct inode *inode, struct file *file) static ssize_t salinfo_event_read(struct file *file, char __user *buffer, size_t count, loff_t *ppos) { - struct salinfo_data *data = PDE_DATA(file_inode(file)); + struct salinfo_data *data = pde_data(file_inode(file)); char cmd[32]; size_t size; int i, n, cpu = -1; @@ -340,7 +340,7 @@ static const struct proc_ops salinfo_event_proc_ops = { static int salinfo_log_open(struct inode *inode, struct file *file) { - struct salinfo_data *data = PDE_DATA(inode); + struct salinfo_data *data = pde_data(inode); if (!capable(CAP_SYS_ADMIN)) return -EPERM; @@ -365,7 +365,7 @@ salinfo_log_open(struct inode *inode, struct file *file) static int salinfo_log_release(struct inode *inode, struct file *file) { - struct salinfo_data *data = PDE_DATA(inode); + struct salinfo_data *data = pde_data(inode); if (data->state == STATE_NO_DATA) { vfree(data->log_buffer); @@ -433,7 +433,7 @@ retry: static ssize_t salinfo_log_read(struct file *file, char __user *buffer, size_t count, loff_t *ppos) { - struct salinfo_data *data = PDE_DATA(file_inode(file)); + struct salinfo_data *data = pde_data(file_inode(file)); u8 *buf; u64 bufsize; @@ -494,7 +494,7 @@ salinfo_log_clear(struct salinfo_data *data, int cpu) static ssize_t salinfo_log_write(struct file *file, const char __user *buffer, size_t count, loff_t *ppos) { - struct salinfo_data *data = PDE_DATA(file_inode(file)); + struct salinfo_data *data = pde_data(file_inode(file)); char cmd[32]; size_t size; u32 offset; diff --git a/arch/m68k/configs/amiga_defconfig b/arch/m68k/configs/amiga_defconfig index a4b6c7108465..bc9952f8be66 100644 --- a/arch/m68k/configs/amiga_defconfig +++ b/arch/m68k/configs/amiga_defconfig @@ -45,7 +45,6 @@ CONFIG_IOSCHED_BFQ=m CONFIG_BINFMT_AOUT=m CONFIG_BINFMT_MISC=m # CONFIG_COMPACTION is not set -CONFIG_CLEANCACHE=y CONFIG_ZPOOL=m CONFIG_NET=y CONFIG_PACKET=y diff --git a/arch/m68k/configs/apollo_defconfig b/arch/m68k/configs/apollo_defconfig index 2db721965520..a77269c6e5ba 100644 --- a/arch/m68k/configs/apollo_defconfig +++ b/arch/m68k/configs/apollo_defconfig @@ -41,7 +41,6 @@ CONFIG_IOSCHED_BFQ=m CONFIG_BINFMT_AOUT=m CONFIG_BINFMT_MISC=m # CONFIG_COMPACTION is not set -CONFIG_CLEANCACHE=y CONFIG_ZPOOL=m CONFIG_NET=y CONFIG_PACKET=y diff --git a/arch/m68k/configs/atari_defconfig b/arch/m68k/configs/atari_defconfig index c266a704eecd..7a74efa6b9a1 100644 --- a/arch/m68k/configs/atari_defconfig +++ b/arch/m68k/configs/atari_defconfig @@ -48,7 +48,6 @@ CONFIG_IOSCHED_BFQ=m CONFIG_BINFMT_AOUT=m CONFIG_BINFMT_MISC=m # CONFIG_COMPACTION is not set -CONFIG_CLEANCACHE=y CONFIG_ZPOOL=m CONFIG_NET=y CONFIG_PACKET=y diff --git a/arch/m68k/configs/bvme6000_defconfig b/arch/m68k/configs/bvme6000_defconfig index f644f08dd6ed..a5323bf2eb33 100644 --- a/arch/m68k/configs/bvme6000_defconfig +++ b/arch/m68k/configs/bvme6000_defconfig @@ -38,7 +38,6 @@ CONFIG_IOSCHED_BFQ=m CONFIG_BINFMT_AOUT=m CONFIG_BINFMT_MISC=m # CONFIG_COMPACTION is not set -CONFIG_CLEANCACHE=y CONFIG_ZPOOL=m CONFIG_NET=y CONFIG_PACKET=y diff --git a/arch/m68k/configs/hp300_defconfig b/arch/m68k/configs/hp300_defconfig index e4924650b687..5e80aa0869d5 100644 --- a/arch/m68k/configs/hp300_defconfig +++ b/arch/m68k/configs/hp300_defconfig @@ -40,7 +40,6 @@ CONFIG_IOSCHED_BFQ=m CONFIG_BINFMT_AOUT=m CONFIG_BINFMT_MISC=m # CONFIG_COMPACTION is not set -CONFIG_CLEANCACHE=y CONFIG_ZPOOL=m CONFIG_NET=y CONFIG_PACKET=y diff --git a/arch/m68k/configs/mac_defconfig b/arch/m68k/configs/mac_defconfig index 24113871ea76..e84326a3f62d 100644 --- a/arch/m68k/configs/mac_defconfig +++ b/arch/m68k/configs/mac_defconfig @@ -39,7 +39,6 @@ CONFIG_IOSCHED_BFQ=m CONFIG_BINFMT_AOUT=m CONFIG_BINFMT_MISC=m # CONFIG_COMPACTION is not set -CONFIG_CLEANCACHE=y CONFIG_ZPOOL=m CONFIG_NET=y CONFIG_PACKET=y diff --git a/arch/m68k/configs/multi_defconfig b/arch/m68k/configs/multi_defconfig index 6a7e4be70eea..337552f43339 100644 --- a/arch/m68k/configs/multi_defconfig +++ b/arch/m68k/configs/multi_defconfig @@ -59,7 +59,6 @@ CONFIG_IOSCHED_BFQ=m CONFIG_BINFMT_AOUT=m CONFIG_BINFMT_MISC=m # CONFIG_COMPACTION is not set -CONFIG_CLEANCACHE=y CONFIG_ZPOOL=m CONFIG_NET=y CONFIG_PACKET=y diff --git a/arch/m68k/configs/mvme147_defconfig b/arch/m68k/configs/mvme147_defconfig index 1d223247aff0..7b688f7d272a 100644 --- a/arch/m68k/configs/mvme147_defconfig +++ b/arch/m68k/configs/mvme147_defconfig @@ -37,7 +37,6 @@ CONFIG_IOSCHED_BFQ=m CONFIG_BINFMT_AOUT=m CONFIG_BINFMT_MISC=m # CONFIG_COMPACTION is not set -CONFIG_CLEANCACHE=y CONFIG_ZPOOL=m CONFIG_NET=y CONFIG_PACKET=y diff --git a/arch/m68k/configs/mvme16x_defconfig b/arch/m68k/configs/mvme16x_defconfig index 961f789f96c9..7c2cb31d63dd 100644 --- a/arch/m68k/configs/mvme16x_defconfig +++ b/arch/m68k/configs/mvme16x_defconfig @@ -38,7 +38,6 @@ CONFIG_IOSCHED_BFQ=m CONFIG_BINFMT_AOUT=m CONFIG_BINFMT_MISC=m # CONFIG_COMPACTION is not set -CONFIG_CLEANCACHE=y CONFIG_ZPOOL=m CONFIG_NET=y CONFIG_PACKET=y diff --git a/arch/m68k/configs/q40_defconfig b/arch/m68k/configs/q40_defconfig index ff4b5e469390..ca43897af26d 100644 --- a/arch/m68k/configs/q40_defconfig +++ b/arch/m68k/configs/q40_defconfig @@ -39,7 +39,6 @@ CONFIG_IOSCHED_BFQ=m CONFIG_BINFMT_AOUT=m CONFIG_BINFMT_MISC=m # CONFIG_COMPACTION is not set -CONFIG_CLEANCACHE=y CONFIG_ZPOOL=m CONFIG_NET=y CONFIG_PACKET=y diff --git a/arch/m68k/configs/sun3_defconfig b/arch/m68k/configs/sun3_defconfig index 5f228621d0cc..e3d515f37144 100644 --- a/arch/m68k/configs/sun3_defconfig +++ b/arch/m68k/configs/sun3_defconfig @@ -35,7 +35,6 @@ CONFIG_IOSCHED_BFQ=m CONFIG_BINFMT_AOUT=m CONFIG_BINFMT_MISC=m # CONFIG_COMPACTION is not set -CONFIG_CLEANCACHE=y CONFIG_ZPOOL=m CONFIG_NET=y CONFIG_PACKET=y diff --git a/arch/m68k/configs/sun3x_defconfig b/arch/m68k/configs/sun3x_defconfig index a600cb9e68c2..d601606c969b 100644 --- a/arch/m68k/configs/sun3x_defconfig +++ b/arch/m68k/configs/sun3x_defconfig @@ -35,7 +35,6 @@ CONFIG_IOSCHED_BFQ=m CONFIG_BINFMT_AOUT=m CONFIG_BINFMT_MISC=m # CONFIG_COMPACTION is not set -CONFIG_CLEANCACHE=y CONFIG_ZPOOL=m CONFIG_NET=y CONFIG_PACKET=y diff --git a/arch/powerpc/kernel/proc_powerpc.c b/arch/powerpc/kernel/proc_powerpc.c index 877817471e3c..6a029f2378e1 100644 --- a/arch/powerpc/kernel/proc_powerpc.c +++ b/arch/powerpc/kernel/proc_powerpc.c @@ -25,7 +25,7 @@ static ssize_t page_map_read( struct file *file, char __user *buf, size_t nbytes loff_t *ppos) { return simple_read_from_buffer(buf, nbytes, ppos, - PDE_DATA(file_inode(file)), PAGE_SIZE); + pde_data(file_inode(file)), PAGE_SIZE); } static int page_map_mmap( struct file *file, struct vm_area_struct *vma ) @@ -34,7 +34,7 @@ static int page_map_mmap( struct file *file, struct vm_area_struct *vma ) return -EINVAL; remap_pfn_range(vma, vma->vm_start, - __pa(PDE_DATA(file_inode(file))) >> PAGE_SHIFT, + __pa(pde_data(file_inode(file))) >> PAGE_SHIFT, PAGE_SIZE, vma->vm_page_prot); return 0; } diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig index 354e51dcb3e2..7fe8975b49ec 100644 --- a/arch/s390/configs/debug_defconfig +++ b/arch/s390/configs/debug_defconfig @@ -96,7 +96,6 @@ CONFIG_MEMORY_HOTPLUG=y CONFIG_MEMORY_HOTREMOVE=y CONFIG_KSM=y CONFIG_TRANSPARENT_HUGEPAGE=y -CONFIG_CLEANCACHE=y CONFIG_FRONTSWAP=y CONFIG_CMA_DEBUG=y CONFIG_CMA_DEBUGFS=y diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig index 8dee6c3782f3..466780c465f5 100644 --- a/arch/s390/configs/defconfig +++ b/arch/s390/configs/defconfig @@ -91,7 +91,6 @@ CONFIG_MEMORY_HOTPLUG=y CONFIG_MEMORY_HOTREMOVE=y CONFIG_KSM=y CONFIG_TRANSPARENT_HUGEPAGE=y -CONFIG_CLEANCACHE=y CONFIG_FRONTSWAP=y CONFIG_CMA_SYSFS=y CONFIG_CMA_AREAS=7 diff --git a/arch/sh/mm/alignment.c b/arch/sh/mm/alignment.c index fb517b82a87b..3a76a766f423 100644 --- a/arch/sh/mm/alignment.c +++ b/arch/sh/mm/alignment.c @@ -140,7 +140,7 @@ static int alignment_proc_open(struct inode *inode, struct file *file) static ssize_t alignment_proc_write(struct file *file, const char __user *buffer, size_t count, loff_t *pos) { - int *data = PDE_DATA(file_inode(file)); + int *data = pde_data(file_inode(file)); char mode; if (count > 0) { @@ -161,7 +161,7 @@ static const struct proc_ops alignment_proc_ops = { }; /* - * This needs to be done after sysctl_init, otherwise sys/ will be + * This needs to be done after sysctl_init_bases(), otherwise sys/ will be * overwritten. Actually, this shouldn't be in sys/ at all since * it isn't a sysctl, and it doesn't contain sysctl information. * We now locate it in /proc/cpu/alignment instead. diff --git a/arch/xtensa/platforms/iss/simdisk.c b/arch/xtensa/platforms/iss/simdisk.c index 07b642c1916a..8eb6ad1a3a1d 100644 --- a/arch/xtensa/platforms/iss/simdisk.c +++ b/arch/xtensa/platforms/iss/simdisk.c @@ -208,7 +208,7 @@ static int simdisk_detach(struct simdisk *dev) static ssize_t proc_read_simdisk(struct file *file, char __user *buf, size_t size, loff_t *ppos) { - struct simdisk *dev = PDE_DATA(file_inode(file)); + struct simdisk *dev = pde_data(file_inode(file)); const char *s = dev->filename; if (s) { ssize_t n = simple_read_from_buffer(buf, size, ppos, @@ -225,7 +225,7 @@ static ssize_t proc_write_simdisk(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { char *tmp = memdup_user_nul(buf, count); - struct simdisk *dev = PDE_DATA(file_inode(file)); + struct simdisk *dev = pde_data(file_inode(file)); int err; if (IS_ERR(tmp)) diff --git a/block/bdev.c b/block/bdev.c index 8bf93a19041b..102837a37051 100644 --- a/block/bdev.c +++ b/block/bdev.c @@ -24,7 +24,6 @@ #include <linux/pseudo_fs.h> #include <linux/uio.h> #include <linux/namei.h> -#include <linux/cleancache.h> #include <linux/part_stat.h> #include <linux/uaccess.h> #include "../fs/internal.h" @@ -88,10 +87,6 @@ void invalidate_bdev(struct block_device *bdev) lru_add_drain_all(); /* make sure all lru add caches are flushed */ invalidate_mapping_pages(mapping, 0, -1); } - /* 99% of the time, we don't need to flush the cleancache on the bdev. - * But, for the strange corners, lets be cautious - */ - cleancache_invalidate_inode(mapping); } EXPORT_SYMBOL(invalidate_bdev); diff --git a/drivers/acpi/proc.c b/drivers/acpi/proc.c index 0cca7991f186..4322f2da6d10 100644 --- a/drivers/acpi/proc.c +++ b/drivers/acpi/proc.c @@ -127,7 +127,7 @@ static int acpi_system_wakeup_device_open_fs(struct inode *inode, struct file *file) { return single_open(file, acpi_system_wakeup_device_seq_show, - PDE_DATA(inode)); + pde_data(inode)); } static const struct proc_ops acpi_system_wakeup_device_proc_ops = { diff --git a/drivers/base/firmware_loader/fallback.c b/drivers/base/firmware_loader/fallback.c index d7d63c1aa993..4afb0e9312c0 100644 --- a/drivers/base/firmware_loader/fallback.c +++ b/drivers/base/firmware_loader/fallback.c @@ -199,11 +199,16 @@ static struct class firmware_class = { int register_sysfs_loader(void) { - return class_register(&firmware_class); + int ret = class_register(&firmware_class); + + if (ret != 0) + return ret; + return register_firmware_config_sysctl(); } void unregister_sysfs_loader(void) { + unregister_firmware_config_sysctl(); class_unregister(&firmware_class); } diff --git a/drivers/base/firmware_loader/fallback.h b/drivers/base/firmware_loader/fallback.h index 3af7205b302f..9f3055d3b4ca 100644 --- a/drivers/base/firmware_loader/fallback.h +++ b/drivers/base/firmware_loader/fallback.h @@ -42,6 +42,17 @@ void fw_fallback_set_default_timeout(void); int register_sysfs_loader(void); void unregister_sysfs_loader(void); +#ifdef CONFIG_SYSCTL +extern int register_firmware_config_sysctl(void); +extern void unregister_firmware_config_sysctl(void); +#else +static inline int register_firmware_config_sysctl(void) +{ + return 0; +} +static inline void unregister_firmware_config_sysctl(void) { } +#endif /* CONFIG_SYSCTL */ + #else /* CONFIG_FW_LOADER_USER_HELPER */ static inline int firmware_fallback_sysfs(struct firmware *fw, const char *name, struct device *device, diff --git a/drivers/base/firmware_loader/fallback_table.c b/drivers/base/firmware_loader/fallback_table.c index 46a731dede6f..e5ac098d0742 100644 --- a/drivers/base/firmware_loader/fallback_table.c +++ b/drivers/base/firmware_loader/fallback_table.c @@ -4,6 +4,7 @@ #include <linux/kconfig.h> #include <linux/list.h> #include <linux/slab.h> +#include <linux/export.h> #include <linux/security.h> #include <linux/highmem.h> #include <linux/umh.h> @@ -24,7 +25,7 @@ struct firmware_fallback_config fw_fallback_config = { EXPORT_SYMBOL_NS_GPL(fw_fallback_config, FIRMWARE_LOADER_PRIVATE); #ifdef CONFIG_SYSCTL -struct ctl_table firmware_config_table[] = { +static struct ctl_table firmware_config_table[] = { { .procname = "force_sysfs_fallback", .data = &fw_fallback_config.force_sysfs_fallback, @@ -45,4 +46,24 @@ struct ctl_table firmware_config_table[] = { }, { } }; -#endif + +static struct ctl_table_header *firmware_config_sysct_table_header; +int register_firmware_config_sysctl(void) +{ + firmware_config_sysct_table_header = + register_sysctl("kernel/firmware_config", + firmware_config_table); + if (!firmware_config_sysct_table_header) + return -ENOMEM; + return 0; +} +EXPORT_SYMBOL_NS_GPL(register_firmware_config_sysctl, FIRMWARE_LOADER_PRIVATE); + +void unregister_firmware_config_sysctl(void) +{ + unregister_sysctl_table(firmware_config_sysct_table_header); + firmware_config_sysct_table_header = NULL; +} +EXPORT_SYMBOL_NS_GPL(unregister_firmware_config_sysctl, FIRMWARE_LOADER_PRIVATE); + +#endif /* CONFIG_SYSCTL */ diff --git a/drivers/cdrom/cdrom.c b/drivers/cdrom/cdrom.c index 9877e413fce3..1b57d4666e43 100644 --- a/drivers/cdrom/cdrom.c +++ b/drivers/cdrom/cdrom.c @@ -3691,27 +3691,6 @@ static struct ctl_table cdrom_table[] = { }, { } }; - -static struct ctl_table cdrom_cdrom_table[] = { - { - .procname = "cdrom", - .maxlen = 0, - .mode = 0555, - .child = cdrom_table, - }, - { } -}; - -/* Make sure that /proc/sys/dev is there */ -static struct ctl_table cdrom_root_table[] = { - { - .procname = "dev", - .maxlen = 0, - .mode = 0555, - .child = cdrom_cdrom_table, - }, - { } -}; static struct ctl_table_header *cdrom_sysctl_header; static void cdrom_sysctl_register(void) @@ -3721,7 +3700,7 @@ static void cdrom_sysctl_register(void) if (!atomic_add_unless(&initialized, 1, 1)) return; - cdrom_sysctl_header = register_sysctl_table(cdrom_root_table); + cdrom_sysctl_header = register_sysctl("dev/cdrom", cdrom_table); /* set the defaults */ cdrom_sysctl_settings.autoclose = autoclose; diff --git a/drivers/char/hpet.c b/drivers/char/hpet.c index 4e5431f01450..563dfae3b8da 100644 --- a/drivers/char/hpet.c +++ b/drivers/char/hpet.c @@ -746,26 +746,6 @@ static struct ctl_table hpet_table[] = { {} }; -static struct ctl_table hpet_root[] = { - { - .procname = "hpet", - .maxlen = 0, - .mode = 0555, - .child = hpet_table, - }, - {} -}; - -static struct ctl_table dev_root[] = { - { - .procname = "dev", - .maxlen = 0, - .mode = 0555, - .child = hpet_root, - }, - {} -}; - static struct ctl_table_header *sysctl_header; /* @@ -1061,7 +1041,7 @@ static int __init hpet_init(void) if (result < 0) return -ENODEV; - sysctl_header = register_sysctl_table(dev_root); + sysctl_header = register_sysctl("dev/hpet", hpet_table); result = acpi_bus_register_driver(&hpet_acpi_driver); if (result < 0) { diff --git a/drivers/char/random.c b/drivers/char/random.c index b411182df6f6..68613f0b6887 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -1992,8 +1992,7 @@ static int proc_do_entropy(struct ctl_table *table, int write, void *buffer, } static int sysctl_poolsize = POOL_BITS; -extern struct ctl_table random_table[]; -struct ctl_table random_table[] = { +static struct ctl_table random_table[] = { { .procname = "poolsize", .data = &sysctl_poolsize, @@ -2055,6 +2054,17 @@ struct ctl_table random_table[] = { #endif { } }; + +/* + * rand_initialize() is called before sysctl_init(), + * so we cannot call register_sysctl_init() in rand_initialize() + */ +static int __init random_sysctls_init(void) +{ + register_sysctl_init("kernel/random", random_table); + return 0; +} +device_initcall(random_sysctls_init); #endif /* CONFIG_SYSCTL */ struct batched_entropy { diff --git a/drivers/gpu/drm/drm_dp_mst_topology.c b/drivers/gpu/drm/drm_dp_mst_topology.c index f3d79eda94bb..8b3822142fed 100644 --- a/drivers/gpu/drm/drm_dp_mst_topology.c +++ b/drivers/gpu/drm/drm_dp_mst_topology.c @@ -5511,6 +5511,7 @@ int drm_dp_mst_topology_mgr_init(struct drm_dp_mst_topology_mgr *mgr, mutex_init(&mgr->probe_lock); #if IS_ENABLED(CONFIG_DRM_DEBUG_DP_MST_TOPOLOGY_REFS) mutex_init(&mgr->topology_ref_history_lock); + stack_depot_init(); #endif INIT_LIST_HEAD(&mgr->tx_msg_downq); INIT_LIST_HEAD(&mgr->destroy_port_list); diff --git a/drivers/gpu/drm/drm_mm.c b/drivers/gpu/drm/drm_mm.c index 7d1c578388d3..8257f9d4f619 100644 --- a/drivers/gpu/drm/drm_mm.c +++ b/drivers/gpu/drm/drm_mm.c @@ -980,6 +980,10 @@ void drm_mm_init(struct drm_mm *mm, u64 start, u64 size) add_hole(&mm->head_node); mm->scan_active = 0; + +#ifdef CONFIG_DRM_DEBUG_MM + stack_depot_init(); +#endif } EXPORT_SYMBOL(drm_mm_init); diff --git a/drivers/gpu/drm/drm_modeset_lock.c b/drivers/gpu/drm/drm_modeset_lock.c index c97323365675..918065982db4 100644 --- a/drivers/gpu/drm/drm_modeset_lock.c +++ b/drivers/gpu/drm/drm_modeset_lock.c @@ -107,6 +107,11 @@ static void __drm_stack_depot_print(depot_stack_handle_t stack_depot) kfree(buf); } + +static void __drm_stack_depot_init(void) +{ + stack_depot_init(); +} #else /* CONFIG_DRM_DEBUG_MODESET_LOCK */ static depot_stack_handle_t __drm_stack_depot_save(void) { @@ -115,6 +120,9 @@ static depot_stack_handle_t __drm_stack_depot_save(void) static void __drm_stack_depot_print(depot_stack_handle_t stack_depot) { } +static void __drm_stack_depot_init(void) +{ +} #endif /* CONFIG_DRM_DEBUG_MODESET_LOCK */ /** @@ -359,6 +367,7 @@ void drm_modeset_lock_init(struct drm_modeset_lock *lock) { ww_mutex_init(&lock->mutex, &crtc_ww_class); INIT_LIST_HEAD(&lock->head); + __drm_stack_depot_init(); } EXPORT_SYMBOL(drm_modeset_lock_init); diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c index 170bba913c30..e27f3b7cf094 100644 --- a/drivers/gpu/drm/i915/i915_perf.c +++ b/drivers/gpu/drm/i915/i915_perf.c @@ -4273,26 +4273,6 @@ static struct ctl_table oa_table[] = { {} }; -static struct ctl_table i915_root[] = { - { - .procname = "i915", - .maxlen = 0, - .mode = 0555, - .child = oa_table, - }, - {} -}; - -static struct ctl_table dev_root[] = { - { - .procname = "dev", - .maxlen = 0, - .mode = 0555, - .child = i915_root, - }, - {} -}; - static void oa_init_supported_formats(struct i915_perf *perf) { struct drm_i915_private *i915 = perf->i915; @@ -4488,7 +4468,7 @@ static int destroy_config(int id, void *p, void *data) int i915_perf_sysctl_register(void) { - sysctl_header = register_sysctl_table(dev_root); + sysctl_header = register_sysctl("dev/i915", oa_table); return 0; } diff --git a/drivers/gpu/drm/i915/intel_runtime_pm.c b/drivers/gpu/drm/i915/intel_runtime_pm.c index 22dab36afcb6..53f1ccb78849 100644 --- a/drivers/gpu/drm/i915/intel_runtime_pm.c +++ b/drivers/gpu/drm/i915/intel_runtime_pm.c @@ -68,6 +68,9 @@ static noinline depot_stack_handle_t __save_depot_stack(void) static void init_intel_runtime_pm_wakeref(struct intel_runtime_pm *rpm) { spin_lock_init(&rpm->debug.lock); + + if (rpm->available) + stack_depot_init(); } static noinline depot_stack_handle_t diff --git a/drivers/hwmon/dell-smm-hwmon.c b/drivers/hwmon/dell-smm-hwmon.c index d401f9acf450..9949eeb79378 100644 --- a/drivers/hwmon/dell-smm-hwmon.c +++ b/drivers/hwmon/dell-smm-hwmon.c @@ -451,7 +451,7 @@ static int i8k_get_power_status(void) static long i8k_ioctl(struct file *fp, unsigned int cmd, unsigned long arg) { - struct dell_smm_data *data = PDE_DATA(file_inode(fp)); + struct dell_smm_data *data = pde_data(file_inode(fp)); int __user *argp = (int __user *)arg; int speed, err; int val = 0; @@ -585,7 +585,7 @@ static int i8k_proc_show(struct seq_file *seq, void *offset) static int i8k_open_fs(struct inode *inode, struct file *file) { - return single_open(file, i8k_proc_show, PDE_DATA(inode)); + return single_open(file, i8k_proc_show, pde_data(inode)); } static const struct proc_ops i8k_proc_ops = { diff --git a/drivers/macintosh/mac_hid.c b/drivers/macintosh/mac_hid.c index 28b8581b44dd..d8c4d5664145 100644 --- a/drivers/macintosh/mac_hid.c +++ b/drivers/macintosh/mac_hid.c @@ -239,33 +239,11 @@ static struct ctl_table mac_hid_files[] = { { } }; -/* dir in /proc/sys/dev */ -static struct ctl_table mac_hid_dir[] = { - { - .procname = "mac_hid", - .maxlen = 0, - .mode = 0555, - .child = mac_hid_files, - }, - { } -}; - -/* /proc/sys/dev itself, in case that is not there yet */ -static struct ctl_table mac_hid_root_dir[] = { - { - .procname = "dev", - .maxlen = 0, - .mode = 0555, - .child = mac_hid_dir, - }, - { } -}; - static struct ctl_table_header *mac_hid_sysctl_header; static int __init mac_hid_init(void) { - mac_hid_sysctl_header = register_sysctl_table(mac_hid_root_dir); + mac_hid_sysctl_header = register_sysctl("dev/mac_hid", mac_hid_files); if (!mac_hid_sysctl_header) return -ENOMEM; diff --git a/drivers/net/bonding/bond_procfs.c b/drivers/net/bonding/bond_procfs.c index 2ec11af5f0cc..46b150e6289e 100644 --- a/drivers/net/bonding/bond_procfs.c +++ b/drivers/net/bonding/bond_procfs.c @@ -11,7 +11,7 @@ static void *bond_info_seq_start(struct seq_file *seq, loff_t *pos) __acquires(RCU) { - struct bonding *bond = PDE_DATA(file_inode(seq->file)); + struct bonding *bond = pde_data(file_inode(seq->file)); struct list_head *iter; struct slave *slave; loff_t off = 0; @@ -30,7 +30,7 @@ static void *bond_info_seq_start(struct seq_file *seq, loff_t *pos) static void *bond_info_seq_next(struct seq_file *seq, void *v, loff_t *pos) { - struct bonding *bond = PDE_DATA(file_inode(seq->file)); + struct bonding *bond = pde_data(file_inode(seq->file)); struct list_head *iter; struct slave *slave; bool found = false; @@ -57,7 +57,7 @@ static void bond_info_seq_stop(struct seq_file *seq, void *v) static void bond_info_show_master(struct seq_file *seq) { - struct bonding *bond = PDE_DATA(file_inode(seq->file)); + struct bonding *bond = pde_data(file_inode(seq->file)); const struct bond_opt_value *optval; struct slave *curr, *primary; int i; @@ -175,7 +175,7 @@ static void bond_info_show_master(struct seq_file *seq) static void bond_info_show_slave(struct seq_file *seq, const struct slave *slave) { - struct bonding *bond = PDE_DATA(file_inode(seq->file)); + struct bonding *bond = pde_data(file_inode(seq->file)); seq_printf(seq, "\nSlave Interface: %s\n", slave->dev->name); seq_printf(seq, "MII Status: %s\n", bond_slave_link_status(slave->link)); diff --git a/drivers/net/wireless/cisco/airo.c b/drivers/net/wireless/cisco/airo.c index 45594f003ef7..452d08545d31 100644 --- a/drivers/net/wireless/cisco/airo.c +++ b/drivers/net/wireless/cisco/airo.c @@ -4672,7 +4672,7 @@ static ssize_t proc_write(struct file *file, static int proc_status_open(struct inode *inode, struct file *file) { struct proc_data *data; - struct net_device *dev = PDE_DATA(inode); + struct net_device *dev = pde_data(inode); struct airo_info *apriv = dev->ml_priv; CapabilityRid cap_rid; StatusRid status_rid; @@ -4756,7 +4756,7 @@ static int proc_stats_rid_open(struct inode *inode, u16 rid) { struct proc_data *data; - struct net_device *dev = PDE_DATA(inode); + struct net_device *dev = pde_data(inode); struct airo_info *apriv = dev->ml_priv; StatsRid stats; int i, j; @@ -4819,7 +4819,7 @@ static inline int sniffing_mode(struct airo_info *ai) static void proc_config_on_close(struct inode *inode, struct file *file) { struct proc_data *data = file->private_data; - struct net_device *dev = PDE_DATA(inode); + struct net_device *dev = pde_data(inode); struct airo_info *ai = dev->ml_priv; char *line; @@ -5030,7 +5030,7 @@ static const char *get_rmode(__le16 mode) static int proc_config_open(struct inode *inode, struct file *file) { struct proc_data *data; - struct net_device *dev = PDE_DATA(inode); + struct net_device *dev = pde_data(inode); struct airo_info *ai = dev->ml_priv; int i; __le16 mode; @@ -5120,7 +5120,7 @@ static int proc_config_open(struct inode *inode, struct file *file) static void proc_SSID_on_close(struct inode *inode, struct file *file) { struct proc_data *data = file->private_data; - struct net_device *dev = PDE_DATA(inode); + struct net_device *dev = pde_data(inode); struct airo_info *ai = dev->ml_priv; SsidRid SSID_rid; int i; @@ -5156,7 +5156,7 @@ static void proc_SSID_on_close(struct inode *inode, struct file *file) static void proc_APList_on_close(struct inode *inode, struct file *file) { struct proc_data *data = file->private_data; - struct net_device *dev = PDE_DATA(inode); + struct net_device *dev = pde_data(inode); struct airo_info *ai = dev->ml_priv; APListRid *APList_rid = &ai->APList; int i; @@ -5280,7 +5280,7 @@ static int set_wep_tx_idx(struct airo_info *ai, u16 index, int perm, int lock) static void proc_wepkey_on_close(struct inode *inode, struct file *file) { struct proc_data *data; - struct net_device *dev = PDE_DATA(inode); + struct net_device *dev = pde_data(inode); struct airo_info *ai = dev->ml_priv; int i, rc; char key[16]; @@ -5331,7 +5331,7 @@ static void proc_wepkey_on_close(struct inode *inode, struct file *file) static int proc_wepkey_open(struct inode *inode, struct file *file) { struct proc_data *data; - struct net_device *dev = PDE_DATA(inode); + struct net_device *dev = pde_data(inode); struct airo_info *ai = dev->ml_priv; char *ptr; WepKeyRid wkr; @@ -5379,7 +5379,7 @@ static int proc_wepkey_open(struct inode *inode, struct file *file) static int proc_SSID_open(struct inode *inode, struct file *file) { struct proc_data *data; - struct net_device *dev = PDE_DATA(inode); + struct net_device *dev = pde_data(inode); struct airo_info *ai = dev->ml_priv; int i; char *ptr; @@ -5423,7 +5423,7 @@ static int proc_SSID_open(struct inode *inode, struct file *file) static int proc_APList_open(struct inode *inode, struct file *file) { struct proc_data *data; - struct net_device *dev = PDE_DATA(inode); + struct net_device *dev = pde_data(inode); struct airo_info *ai = dev->ml_priv; int i; char *ptr; @@ -5462,7 +5462,7 @@ static int proc_APList_open(struct inode *inode, struct file *file) static int proc_BSSList_open(struct inode *inode, struct file *file) { struct proc_data *data; - struct net_device *dev = PDE_DATA(inode); + struct net_device *dev = pde_data(inode); struct airo_info *ai = dev->ml_priv; char *ptr; BSSListRid BSSList_rid; diff --git a/drivers/net/wireless/intersil/hostap/hostap_ap.c b/drivers/net/wireless/intersil/hostap/hostap_ap.c index 8bcc1cdcb75b..462ccc7d7d1a 100644 --- a/drivers/net/wireless/intersil/hostap/hostap_ap.c +++ b/drivers/net/wireless/intersil/hostap/hostap_ap.c @@ -69,7 +69,7 @@ static void prism2_send_mgmt(struct net_device *dev, #if !defined(PRISM2_NO_PROCFS_DEBUG) && defined(CONFIG_PROC_FS) static int ap_debug_proc_show(struct seq_file *m, void *v) { - struct ap_data *ap = PDE_DATA(file_inode(m->file)); + struct ap_data *ap = pde_data(file_inode(m->file)); seq_printf(m, "BridgedUnicastFrames=%u\n", ap->bridged_unicast); seq_printf(m, "BridgedMulticastFrames=%u\n", ap->bridged_multicast); @@ -320,7 +320,7 @@ void hostap_deauth_all_stas(struct net_device *dev, struct ap_data *ap, static int ap_control_proc_show(struct seq_file *m, void *v) { - struct ap_data *ap = PDE_DATA(file_inode(m->file)); + struct ap_data *ap = pde_data(file_inode(m->file)); char *policy_txt; struct mac_entry *entry; @@ -352,20 +352,20 @@ static int ap_control_proc_show(struct seq_file *m, void *v) static void *ap_control_proc_start(struct seq_file *m, loff_t *_pos) { - struct ap_data *ap = PDE_DATA(file_inode(m->file)); + struct ap_data *ap = pde_data(file_inode(m->file)); spin_lock_bh(&ap->mac_restrictions.lock); return seq_list_start_head(&ap->mac_restrictions.mac_list, *_pos); } static void *ap_control_proc_next(struct seq_file *m, void *v, loff_t *_pos) { - struct ap_data *ap = PDE_DATA(file_inode(m->file)); + struct ap_data *ap = pde_data(file_inode(m->file)); return seq_list_next(v, &ap->mac_restrictions.mac_list, _pos); } static void ap_control_proc_stop(struct seq_file *m, void *v) { - struct ap_data *ap = PDE_DATA(file_inode(m->file)); + struct ap_data *ap = pde_data(file_inode(m->file)); spin_unlock_bh(&ap->mac_restrictions.lock); } @@ -554,20 +554,20 @@ static int prism2_ap_proc_show(struct seq_file *m, void *v) static void *prism2_ap_proc_start(struct seq_file *m, loff_t *_pos) { - struct ap_data *ap = PDE_DATA(file_inode(m->file)); + struct ap_data *ap = pde_data(file_inode(m->file)); spin_lock_bh(&ap->sta_table_lock); return seq_list_start_head(&ap->sta_list, *_pos); } static void *prism2_ap_proc_next(struct seq_file *m, void *v, loff_t *_pos) { - struct ap_data *ap = PDE_DATA(file_inode(m->file)); + struct ap_data *ap = pde_data(file_inode(m->file)); return seq_list_next(v, &ap->sta_list, _pos); } static void prism2_ap_proc_stop(struct seq_file *m, void *v) { - struct ap_data *ap = PDE_DATA(file_inode(m->file)); + struct ap_data *ap = pde_data(file_inode(m->file)); spin_unlock_bh(&ap->sta_table_lock); } diff --git a/drivers/net/wireless/intersil/hostap/hostap_download.c b/drivers/net/wireless/intersil/hostap/hostap_download.c index 7c6a5a6d1d45..3672291ced5c 100644 --- a/drivers/net/wireless/intersil/hostap/hostap_download.c +++ b/drivers/net/wireless/intersil/hostap/hostap_download.c @@ -227,7 +227,7 @@ static int prism2_download_aux_dump_proc_open(struct inode *inode, struct file * sizeof(struct prism2_download_aux_dump)); if (ret == 0) { struct seq_file *m = file->private_data; - m->private = PDE_DATA(inode); + m->private = pde_data(inode); } return ret; } diff --git a/drivers/net/wireless/intersil/hostap/hostap_proc.c b/drivers/net/wireless/intersil/hostap/hostap_proc.c index 51c847d98755..61f68786056f 100644 --- a/drivers/net/wireless/intersil/hostap/hostap_proc.c +++ b/drivers/net/wireless/intersil/hostap/hostap_proc.c @@ -97,20 +97,20 @@ static int prism2_wds_proc_show(struct seq_file *m, void *v) static void *prism2_wds_proc_start(struct seq_file *m, loff_t *_pos) { - local_info_t *local = PDE_DATA(file_inode(m->file)); + local_info_t *local = pde_data(file_inode(m->file)); read_lock_bh(&local->iface_lock); return seq_list_start(&local->hostap_interfaces, *_pos); } static void *prism2_wds_proc_next(struct seq_file *m, void *v, loff_t *_pos) { - local_info_t *local = PDE_DATA(file_inode(m->file)); + local_info_t *local = pde_data(file_inode(m->file)); return seq_list_next(v, &local->hostap_interfaces, _pos); } static void prism2_wds_proc_stop(struct seq_file *m, void *v) { - local_info_t *local = PDE_DATA(file_inode(m->file)); + local_info_t *local = pde_data(file_inode(m->file)); read_unlock_bh(&local->iface_lock); } @@ -123,7 +123,7 @@ static const struct seq_operations prism2_wds_proc_seqops = { static int prism2_bss_list_proc_show(struct seq_file *m, void *v) { - local_info_t *local = PDE_DATA(file_inode(m->file)); + local_info_t *local = pde_data(file_inode(m->file)); struct list_head *ptr = v; struct hostap_bss_info *bss; @@ -151,21 +151,21 @@ static int prism2_bss_list_proc_show(struct seq_file *m, void *v) static void *prism2_bss_list_proc_start(struct seq_file *m, loff_t *_pos) __acquires(&local->lock) { - local_info_t *local = PDE_DATA(file_inode(m->file)); + local_info_t *local = pde_data(file_inode(m->file)); spin_lock_bh(&local->lock); return seq_list_start_head(&local->bss_list, *_pos); } static void *prism2_bss_list_proc_next(struct seq_file *m, void *v, loff_t *_pos) { - local_info_t *local = PDE_DATA(file_inode(m->file)); + local_info_t *local = pde_data(file_inode(m->file)); return seq_list_next(v, &local->bss_list, _pos); } static void prism2_bss_list_proc_stop(struct seq_file *m, void *v) __releases(&local->lock) { - local_info_t *local = PDE_DATA(file_inode(m->file)); + local_info_t *local = pde_data(file_inode(m->file)); spin_unlock_bh(&local->lock); } @@ -198,7 +198,7 @@ static int prism2_crypt_proc_show(struct seq_file *m, void *v) static ssize_t prism2_pda_proc_read(struct file *file, char __user *buf, size_t count, loff_t *_pos) { - local_info_t *local = PDE_DATA(file_inode(file)); + local_info_t *local = pde_data(file_inode(file)); size_t off; if (local->pda == NULL || *_pos >= PRISM2_PDA_SIZE) @@ -272,7 +272,7 @@ static int prism2_io_debug_proc_read(char *page, char **start, off_t off, #ifndef PRISM2_NO_STATION_MODES static int prism2_scan_results_proc_show(struct seq_file *m, void *v) { - local_info_t *local = PDE_DATA(file_inode(m->file)); + local_info_t *local = pde_data(file_inode(m->file)); unsigned long entry; int i, len; struct hfa384x_hostscan_result *scanres; @@ -322,7 +322,7 @@ static int prism2_scan_results_proc_show(struct seq_file *m, void *v) static void *prism2_scan_results_proc_start(struct seq_file *m, loff_t *_pos) { - local_info_t *local = PDE_DATA(file_inode(m->file)); + local_info_t *local = pde_data(file_inode(m->file)); spin_lock_bh(&local->lock); /* We have a header (pos 0) + N results to show (pos 1...N) */ @@ -333,7 +333,7 @@ static void *prism2_scan_results_proc_start(struct seq_file *m, loff_t *_pos) static void *prism2_scan_results_proc_next(struct seq_file *m, void *v, loff_t *_pos) { - local_info_t *local = PDE_DATA(file_inode(m->file)); + local_info_t *local = pde_data(file_inode(m->file)); ++*_pos; if (*_pos > local->last_scan_results_count) @@ -343,7 +343,7 @@ static void *prism2_scan_results_proc_next(struct seq_file *m, void *v, loff_t * static void prism2_scan_results_proc_stop(struct seq_file *m, void *v) { - local_info_t *local = PDE_DATA(file_inode(m->file)); + local_info_t *local = pde_data(file_inode(m->file)); spin_unlock_bh(&local->lock); } diff --git a/drivers/net/wireless/ray_cs.c b/drivers/net/wireless/ray_cs.c index e3a3dc3e45b4..2987ad9271f6 100644 --- a/drivers/net/wireless/ray_cs.c +++ b/drivers/net/wireless/ray_cs.c @@ -2746,7 +2746,7 @@ static ssize_t int_proc_write(struct file *file, const char __user *buffer, nr = nr * 10 + c; p++; } while (--len); - *(int *)PDE_DATA(file_inode(file)) = nr; + *(int *)pde_data(file_inode(file)) = nr; return count; } diff --git a/drivers/nubus/proc.c b/drivers/nubus/proc.c index 88e1f9a0faaf..1fd667852271 100644 --- a/drivers/nubus/proc.c +++ b/drivers/nubus/proc.c @@ -93,30 +93,30 @@ struct nubus_proc_pde_data { static struct nubus_proc_pde_data * nubus_proc_alloc_pde_data(unsigned char *ptr, unsigned int size) { - struct nubus_proc_pde_data *pde_data; + struct nubus_proc_pde_data *pded; - pde_data = kmalloc(sizeof(*pde_data), GFP_KERNEL); - if (!pde_data) + pded = kmalloc(sizeof(*pded), GFP_KERNEL); + if (!pded) return NULL; - pde_data->res_ptr = ptr; - pde_data->res_size = size; - return pde_data; + pded->res_ptr = ptr; + pded->res_size = size; + return pded; } static int nubus_proc_rsrc_show(struct seq_file *m, void *v) { struct inode *inode = m->private; - struct nubus_proc_pde_data *pde_data; + struct nubus_proc_pde_data *pded; - pde_data = PDE_DATA(inode); - if (!pde_data) + pded = pde_data(inode); + if (!pded) return 0; - if (pde_data->res_size > m->size) + if (pded->res_size > m->size) return -EFBIG; - if (pde_data->res_size) { + if (pded->res_size) { int lanes = (int)proc_get_parent_data(inode); struct nubus_dirent ent; @@ -124,11 +124,11 @@ static int nubus_proc_rsrc_show(struct seq_file *m, void *v) return 0; ent.mask = lanes; - ent.base = pde_data->res_ptr; + ent.base = pded->res_ptr; ent.data = 0; - nubus_seq_write_rsrc_mem(m, &ent, pde_data->res_size); + nubus_seq_write_rsrc_mem(m, &ent, pded->res_size); } else { - unsigned int data = (unsigned int)pde_data->res_ptr; + unsigned int data = (unsigned int)pded->res_ptr; seq_putc(m, data >> 16); seq_putc(m, data >> 8); @@ -142,18 +142,18 @@ void nubus_proc_add_rsrc_mem(struct proc_dir_entry *procdir, unsigned int size) { char name[9]; - struct nubus_proc_pde_data *pde_data; + struct nubus_proc_pde_data *pded; if (!procdir) return; snprintf(name, sizeof(name), "%x", ent->type); if (size) - pde_data = nubus_proc_alloc_pde_data(nubus_dirptr(ent), size); + pded = nubus_proc_alloc_pde_data(nubus_dirptr(ent), size); else - pde_data = NULL; + pded = NULL; proc_create_single_data(name, S_IFREG | 0444, procdir, - nubus_proc_rsrc_show, pde_data); + nubus_proc_rsrc_show, pded); } void nubus_proc_add_rsrc(struct proc_dir_entry *procdir, diff --git a/drivers/parisc/led.c b/drivers/parisc/led.c index cf91cb024be3..1e4a5663d011 100644 --- a/drivers/parisc/led.c +++ b/drivers/parisc/led.c @@ -168,14 +168,14 @@ static int led_proc_show(struct seq_file *m, void *v) static int led_proc_open(struct inode *inode, struct file *file) { - return single_open(file, led_proc_show, PDE_DATA(inode)); + return single_open(file, led_proc_show, pde_data(inode)); } static ssize_t led_proc_write(struct file *file, const char __user *buf, size_t count, loff_t *pos) { - void *data = PDE_DATA(file_inode(file)); + void *data = pde_data(file_inode(file)); char *cur, lbuf[32]; int d; diff --git a/drivers/pci/proc.c b/drivers/pci/proc.c index cb18f8a13ab6..9c7edec64f7e 100644 --- a/drivers/pci/proc.c +++ b/drivers/pci/proc.c @@ -21,14 +21,14 @@ static int proc_initialized; /* = 0 */ static loff_t proc_bus_pci_lseek(struct file *file, loff_t off, int whence) { - struct pci_dev *dev = PDE_DATA(file_inode(file)); + struct pci_dev *dev = pde_data(file_inode(file)); return fixed_size_llseek(file, off, whence, dev->cfg_size); } static ssize_t proc_bus_pci_read(struct file *file, char __user *buf, size_t nbytes, loff_t *ppos) { - struct pci_dev *dev = PDE_DATA(file_inode(file)); + struct pci_dev *dev = pde_data(file_inode(file)); unsigned int pos = *ppos; unsigned int cnt, size; @@ -114,7 +114,7 @@ static ssize_t proc_bus_pci_write(struct file *file, const char __user *buf, size_t nbytes, loff_t *ppos) { struct inode *ino = file_inode(file); - struct pci_dev *dev = PDE_DATA(ino); + struct pci_dev *dev = pde_data(ino); int pos = *ppos; int size = dev->cfg_size; int cnt, ret; @@ -196,7 +196,7 @@ struct pci_filp_private { static long proc_bus_pci_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { - struct pci_dev *dev = PDE_DATA(file_inode(file)); + struct pci_dev *dev = pde_data(file_inode(file)); #ifdef HAVE_PCI_MMAP struct pci_filp_private *fpriv = file->private_data; #endif /* HAVE_PCI_MMAP */ @@ -244,7 +244,7 @@ static long proc_bus_pci_ioctl(struct file *file, unsigned int cmd, #ifdef HAVE_PCI_MMAP static int proc_bus_pci_mmap(struct file *file, struct vm_area_struct *vma) { - struct pci_dev *dev = PDE_DATA(file_inode(file)); + struct pci_dev *dev = pde_data(file_inode(file)); struct pci_filp_private *fpriv = file->private_data; int i, ret, write_combine = 0, res_bit = IORESOURCE_MEM; diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c index 82fa6148216c..098180fb1cfc 100644 --- a/drivers/platform/x86/thinkpad_acpi.c +++ b/drivers/platform/x86/thinkpad_acpi.c @@ -880,14 +880,14 @@ static int dispatch_proc_show(struct seq_file *m, void *v) static int dispatch_proc_open(struct inode *inode, struct file *file) { - return single_open(file, dispatch_proc_show, PDE_DATA(inode)); + return single_open(file, dispatch_proc_show, pde_data(inode)); } static ssize_t dispatch_proc_write(struct file *file, const char __user *userbuf, size_t count, loff_t *pos) { - struct ibm_struct *ibm = PDE_DATA(file_inode(file)); + struct ibm_struct *ibm = pde_data(file_inode(file)); char *kernbuf; int ret; diff --git a/drivers/platform/x86/toshiba_acpi.c b/drivers/platform/x86/toshiba_acpi.c index 352508d30467..f113dec98e21 100644 --- a/drivers/platform/x86/toshiba_acpi.c +++ b/drivers/platform/x86/toshiba_acpi.c @@ -1368,7 +1368,7 @@ static int lcd_proc_show(struct seq_file *m, void *v) static int lcd_proc_open(struct inode *inode, struct file *file) { - return single_open(file, lcd_proc_show, PDE_DATA(inode)); + return single_open(file, lcd_proc_show, pde_data(inode)); } static int set_lcd_brightness(struct toshiba_acpi_dev *dev, int value) @@ -1404,7 +1404,7 @@ static int set_lcd_status(struct backlight_device *bd) static ssize_t lcd_proc_write(struct file *file, const char __user *buf, size_t count, loff_t *pos) { - struct toshiba_acpi_dev *dev = PDE_DATA(file_inode(file)); + struct toshiba_acpi_dev *dev = pde_data(file_inode(file)); char cmd[42]; size_t len; int levels; @@ -1469,13 +1469,13 @@ static int video_proc_show(struct seq_file *m, void *v) static int video_proc_open(struct inode *inode, struct file *file) { - return single_open(file, video_proc_show, PDE_DATA(inode)); + return single_open(file, video_proc_show, pde_data(inode)); } static ssize_t video_proc_write(struct file *file, const char __user *buf, size_t count, loff_t *pos) { - struct toshiba_acpi_dev *dev = PDE_DATA(file_inode(file)); + struct toshiba_acpi_dev *dev = pde_data(file_inode(file)); char *buffer; char *cmd; int lcd_out = -1, crt_out = -1, tv_out = -1; @@ -1580,13 +1580,13 @@ static int fan_proc_show(struct seq_file *m, void *v) static int fan_proc_open(struct inode *inode, struct file *file) { - return single_open(file, fan_proc_show, PDE_DATA(inode)); + return single_open(file, fan_proc_show, pde_data(inode)); } static ssize_t fan_proc_write(struct file *file, const char __user *buf, size_t count, loff_t *pos) { - struct toshiba_acpi_dev *dev = PDE_DATA(file_inode(file)); + struct toshiba_acpi_dev *dev = pde_data(file_inode(file)); char cmd[42]; size_t len; int value; @@ -1628,13 +1628,13 @@ static int keys_proc_show(struct seq_file *m, void *v) static int keys_proc_open(struct inode *inode, struct file *file) { - return single_open(file, keys_proc_show, PDE_DATA(inode)); + return single_open(file, keys_proc_show, pde_data(inode)); } static ssize_t keys_proc_write(struct file *file, const char __user *buf, size_t count, loff_t *pos) { - struct toshiba_acpi_dev *dev = PDE_DATA(file_inode(file)); + struct toshiba_acpi_dev *dev = pde_data(file_inode(file)); char cmd[42]; size_t len; int value; diff --git a/drivers/pnp/isapnp/proc.c b/drivers/pnp/isapnp/proc.c index 1ae458c02656..55ae72a2818b 100644 --- a/drivers/pnp/isapnp/proc.c +++ b/drivers/pnp/isapnp/proc.c @@ -22,7 +22,7 @@ static loff_t isapnp_proc_bus_lseek(struct file *file, loff_t off, int whence) static ssize_t isapnp_proc_bus_read(struct file *file, char __user * buf, size_t nbytes, loff_t * ppos) { - struct pnp_dev *dev = PDE_DATA(file_inode(file)); + struct pnp_dev *dev = pde_data(file_inode(file)); int pos = *ppos; int cnt, size = 256; diff --git a/drivers/pnp/pnpbios/proc.c b/drivers/pnp/pnpbios/proc.c index a806830e3a40..0f0d819b157f 100644 --- a/drivers/pnp/pnpbios/proc.c +++ b/drivers/pnp/pnpbios/proc.c @@ -173,13 +173,13 @@ static int pnpbios_proc_show(struct seq_file *m, void *v) static int pnpbios_proc_open(struct inode *inode, struct file *file) { - return single_open(file, pnpbios_proc_show, PDE_DATA(inode)); + return single_open(file, pnpbios_proc_show, pde_data(inode)); } static ssize_t pnpbios_proc_write(struct file *file, const char __user *buf, size_t count, loff_t *pos) { - void *data = PDE_DATA(file_inode(file)); + void *data = pde_data(file_inode(file)); struct pnp_bios_node *node; int boot = (long)data >> 8; u8 nodenum = (long)data; diff --git a/drivers/scsi/scsi_proc.c b/drivers/scsi/scsi_proc.c index d6982d355739..95aee1ad1383 100644 --- a/drivers/scsi/scsi_proc.c +++ b/drivers/scsi/scsi_proc.c @@ -49,7 +49,7 @@ static DEFINE_MUTEX(global_host_template_mutex); static ssize_t proc_scsi_host_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { - struct Scsi_Host *shost = PDE_DATA(file_inode(file)); + struct Scsi_Host *shost = pde_data(file_inode(file)); ssize_t ret = -ENOMEM; char *page; @@ -79,7 +79,7 @@ static int proc_scsi_show(struct seq_file *m, void *v) static int proc_scsi_host_open(struct inode *inode, struct file *file) { - return single_open_size(file, proc_scsi_show, PDE_DATA(inode), + return single_open_size(file, proc_scsi_show, pde_data(inode), 4 * PAGE_SIZE); } diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c index ad12b3261845..6b43e97bd417 100644 --- a/drivers/scsi/sg.c +++ b/drivers/scsi/sg.c @@ -77,7 +77,7 @@ static int sg_proc_init(void); #define SG_DEFAULT_TIMEOUT mult_frac(SG_DEFAULT_TIMEOUT_USER, HZ, USER_HZ) -int sg_big_buff = SG_DEF_RESERVED_SIZE; +static int sg_big_buff = SG_DEF_RESERVED_SIZE; /* N.B. This variable is readable and writeable via /proc/scsi/sg/def_reserved_size . Each time sg_open() is called a buffer of this size (or less if there is not enough memory) will be reserved @@ -1634,6 +1634,37 @@ MODULE_PARM_DESC(scatter_elem_sz, "scatter gather element " MODULE_PARM_DESC(def_reserved_size, "size of buffer reserved for each fd"); MODULE_PARM_DESC(allow_dio, "allow direct I/O (default: 0 (disallow))"); +#ifdef CONFIG_SYSCTL +#include <linux/sysctl.h> + +static struct ctl_table sg_sysctls[] = { + { + .procname = "sg-big-buff", + .data = &sg_big_buff, + .maxlen = sizeof(int), + .mode = 0444, + .proc_handler = proc_dointvec, + }, + {} +}; + +static struct ctl_table_header *hdr; +static void register_sg_sysctls(void) +{ + if (!hdr) + hdr = register_sysctl("kernel", sg_sysctls); +} + +static void unregister_sg_sysctls(void) +{ + if (hdr) + unregister_sysctl_table(hdr); +} +#else +#define register_sg_sysctls() do { } while (0) +#define unregister_sg_sysctls() do { } while (0) +#endif /* CONFIG_SYSCTL */ + static int __init init_sg(void) { @@ -1666,6 +1697,7 @@ init_sg(void) return 0; } class_destroy(sg_sysfs_class); + register_sg_sysctls(); err_out: unregister_chrdev_region(MKDEV(SCSI_GENERIC_MAJOR, 0), SG_MAX_DEVS); return rc; @@ -1674,6 +1706,7 @@ err_out: static void __exit exit_sg(void) { + unregister_sg_sysctls(); #ifdef CONFIG_SCSI_PROC_FS remove_proc_subtree("scsi/sg", NULL); #endif /* CONFIG_SCSI_PROC_FS */ diff --git a/drivers/usb/gadget/function/rndis.c b/drivers/usb/gadget/function/rndis.c index 64de9f1b874c..431d5a7d737e 100644 --- a/drivers/usb/gadget/function/rndis.c +++ b/drivers/usb/gadget/function/rndis.c @@ -1117,7 +1117,7 @@ static int rndis_proc_show(struct seq_file *m, void *v) static ssize_t rndis_proc_write(struct file *file, const char __user *buffer, size_t count, loff_t *ppos) { - rndis_params *p = PDE_DATA(file_inode(file)); + rndis_params *p = pde_data(file_inode(file)); u32 speed = 0; int i, fl_speed = 0; @@ -1161,7 +1161,7 @@ static ssize_t rndis_proc_write(struct file *file, const char __user *buffer, static int rndis_proc_open(struct inode *inode, struct file *file) { - return single_open(file, rndis_proc_show, PDE_DATA(inode)); + return single_open(file, rndis_proc_show, pde_data(inode)); } static const struct proc_ops rndis_proc_ops = { diff --git a/drivers/zorro/proc.c b/drivers/zorro/proc.c index 1c9ae08225d8..f916bf60b312 100644 --- a/drivers/zorro/proc.c +++ b/drivers/zorro/proc.c @@ -30,7 +30,7 @@ proc_bus_zorro_lseek(struct file *file, loff_t off, int whence) static ssize_t proc_bus_zorro_read(struct file *file, char __user *buf, size_t nbytes, loff_t *ppos) { - struct zorro_dev *z = PDE_DATA(file_inode(file)); + struct zorro_dev *z = pde_data(file_inode(file)); struct ConfigDev cd; loff_t pos = *ppos; diff --git a/fs/Makefile b/fs/Makefile index 84c5e4cdfee5..dab324aea08f 100644 --- a/fs/Makefile +++ b/fs/Makefile @@ -6,6 +6,8 @@ # Rewritten to use lists instead of if-statements. # +obj-$(CONFIG_SYSCTL) += sysctls.o + obj-y := open.o read_write.o file_table.o super.o \ char_dev.o stat.o exec.o pipe.o namei.o fcntl.o \ ioctl.o readdir.o select.o dcache.o inode.o \ diff --git a/fs/afs/proc.c b/fs/afs/proc.c index 065a28bfa3f1..e1b863449296 100644 --- a/fs/afs/proc.c +++ b/fs/afs/proc.c @@ -227,7 +227,7 @@ static int afs_proc_cell_volumes_show(struct seq_file *m, void *v) static void *afs_proc_cell_volumes_start(struct seq_file *m, loff_t *_pos) __acquires(cell->proc_lock) { - struct afs_cell *cell = PDE_DATA(file_inode(m->file)); + struct afs_cell *cell = pde_data(file_inode(m->file)); rcu_read_lock(); return seq_hlist_start_head_rcu(&cell->proc_volumes, *_pos); @@ -236,7 +236,7 @@ static void *afs_proc_cell_volumes_start(struct seq_file *m, loff_t *_pos) static void *afs_proc_cell_volumes_next(struct seq_file *m, void *v, loff_t *_pos) { - struct afs_cell *cell = PDE_DATA(file_inode(m->file)); + struct afs_cell *cell = pde_data(file_inode(m->file)); return seq_hlist_next_rcu(v, &cell->proc_volumes, _pos); } @@ -322,7 +322,7 @@ static void *afs_proc_cell_vlservers_start(struct seq_file *m, loff_t *_pos) { struct afs_vl_seq_net_private *priv = m->private; struct afs_vlserver_list *vllist; - struct afs_cell *cell = PDE_DATA(file_inode(m->file)); + struct afs_cell *cell = pde_data(file_inode(m->file)); loff_t pos = *_pos; rcu_read_lock(); @@ -220,9 +220,35 @@ struct aio_kiocb { /*------ sysctl variables----*/ static DEFINE_SPINLOCK(aio_nr_lock); -unsigned long aio_nr; /* current system wide number of aio requests */ -unsigned long aio_max_nr = 0x10000; /* system wide maximum number of aio requests */ +static unsigned long aio_nr; /* current system wide number of aio requests */ +static unsigned long aio_max_nr = 0x10000; /* system wide maximum number of aio requests */ /*----end sysctl variables---*/ +#ifdef CONFIG_SYSCTL +static struct ctl_table aio_sysctls[] = { + { + .procname = "aio-nr", + .data = &aio_nr, + .maxlen = sizeof(aio_nr), + .mode = 0444, + .proc_handler = proc_doulongvec_minmax, + }, + { + .procname = "aio-max-nr", + .data = &aio_max_nr, + .maxlen = sizeof(aio_max_nr), + .mode = 0644, + .proc_handler = proc_doulongvec_minmax, + }, + {} +}; + +static void __init aio_sysctl_init(void) +{ + register_sysctl_init("fs", aio_sysctls); +} +#else +#define aio_sysctl_init() do { } while (0) +#endif static struct kmem_cache *kiocb_cachep; static struct kmem_cache *kioctx_cachep; @@ -275,6 +301,7 @@ static int __init aio_setup(void) kiocb_cachep = KMEM_CACHE(aio_kiocb, SLAB_HWCACHE_ALIGN|SLAB_PANIC); kioctx_cachep = KMEM_CACHE(kioctx,SLAB_HWCACHE_ALIGN|SLAB_PANIC); + aio_sysctl_init(); return 0; } __initcall(aio_setup); diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c index e1eae7ea823a..ddea6acbddde 100644 --- a/fs/binfmt_misc.c +++ b/fs/binfmt_misc.c @@ -822,7 +822,11 @@ static int __init init_misc_binfmt(void) int err = register_filesystem(&bm_fs_type); if (!err) insert_binfmt(&misc_format); - return err; + if (!register_sysctl_mount_point("fs/binfmt_misc")) { + pr_warn("Failed to create fs/binfmt_misc sysctl mount point"); + return -ENOMEM; + } + return 0; } static void __exit exit_misc_binfmt(void) diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index d6d48ecf823c..409bad3928db 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -12,7 +12,6 @@ #include <linux/writeback.h> #include <linux/pagevec.h> #include <linux/prefetch.h> -#include <linux/cleancache.h> #include <linux/fsverity.h> #include "misc.h" #include "extent_io.h" @@ -3578,15 +3577,6 @@ int btrfs_do_readpage(struct page *page, struct extent_map **em_cached, goto out; } - if (!PageUptodate(page)) { - if (cleancache_get_page(page) == 0) { - BUG_ON(blocksize != PAGE_SIZE); - unlock_extent(tree, start, end); - unlock_page(page); - goto out; - } - } - if (page->index == last_byte >> PAGE_SHIFT) { size_t zero_offset = offset_in_page(last_byte); diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 0ec09fe01be6..4d947ba32da9 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -23,7 +23,6 @@ #include <linux/miscdevice.h> #include <linux/magic.h> #include <linux/slab.h> -#include <linux/cleancache.h> #include <linux/ratelimit.h> #include <linux/crc32c.h> #include <linux/btrfs.h> @@ -1374,7 +1373,6 @@ static int btrfs_fill_super(struct super_block *sb, goto fail_close; } - cleancache_init_fs(sb); sb->s_flags |= SB_ACTIVE; return 0; diff --git a/fs/coredump.c b/fs/coredump.c index 7dece20b162b..1c060c0a2d72 100644 --- a/fs/coredump.c +++ b/fs/coredump.c @@ -41,6 +41,7 @@ #include <linux/fs.h> #include <linux/path.h> #include <linux/timekeeping.h> +#include <linux/sysctl.h> #include <linux/uaccess.h> #include <asm/mmu_context.h> @@ -52,9 +53,9 @@ #include <trace/events/sched.h> -int core_uses_pid; -unsigned int core_pipe_limit; -char core_pattern[CORENAME_MAX_SIZE] = "core"; +static int core_uses_pid; +static unsigned int core_pipe_limit; +static char core_pattern[CORENAME_MAX_SIZE] = "core"; static int core_name_size = CORENAME_MAX_SIZE; struct core_name { @@ -62,8 +63,6 @@ struct core_name { int used, size; }; -/* The maximal length of core_pattern is also specified in sysctl.c */ - static int expand_corename(struct core_name *cn, int size) { char *corename = krealloc(cn->corename, size, GFP_KERNEL); @@ -893,6 +892,63 @@ int dump_align(struct coredump_params *cprm, int align) } EXPORT_SYMBOL(dump_align); +#ifdef CONFIG_SYSCTL + +void validate_coredump_safety(void) +{ + if (suid_dumpable == SUID_DUMP_ROOT && + core_pattern[0] != '/' && core_pattern[0] != '|') { + pr_warn( +"Unsafe core_pattern used with fs.suid_dumpable=2.\n" +"Pipe handler or fully qualified core dump path required.\n" +"Set kernel.core_pattern before fs.suid_dumpable.\n" + ); + } +} + +static int proc_dostring_coredump(struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos) +{ + int error = proc_dostring(table, write, buffer, lenp, ppos); + + if (!error) + validate_coredump_safety(); + return error; +} + +static struct ctl_table coredump_sysctls[] = { + { + .procname = "core_uses_pid", + .data = &core_uses_pid, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .procname = "core_pattern", + .data = core_pattern, + .maxlen = CORENAME_MAX_SIZE, + .mode = 0644, + .proc_handler = proc_dostring_coredump, + }, + { + .procname = "core_pipe_limit", + .data = &core_pipe_limit, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { } +}; + +static int __init init_fs_coredump_sysctls(void) +{ + register_sysctl_init("kernel", coredump_sysctls); + return 0; +} +fs_initcall(init_fs_coredump_sysctls); +#endif /* CONFIG_SYSCTL */ + /* * The purpose of always_dump_vma() is to make sure that special kernel mappings * that are useful for post-mortem analysis are included in every core dump. diff --git a/fs/dcache.c b/fs/dcache.c index cf871a81f4fd..c84269c6e8bf 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -115,10 +115,13 @@ static inline struct hlist_bl_head *in_lookup_hash(const struct dentry *parent, return in_lookup_hashtable + hash_32(hash, IN_LOOKUP_SHIFT); } - -/* Statistics gathering. */ -struct dentry_stat_t dentry_stat = { - .age_limit = 45, +struct dentry_stat_t { + long nr_dentry; + long nr_unused; + long age_limit; /* age in seconds */ + long want_pages; /* pages requested by system */ + long nr_negative; /* # of unused negative dentries */ + long dummy; /* Reserved for future use */ }; static DEFINE_PER_CPU(long, nr_dentry); @@ -126,6 +129,10 @@ static DEFINE_PER_CPU(long, nr_dentry_unused); static DEFINE_PER_CPU(long, nr_dentry_negative); #if defined(CONFIG_SYSCTL) && defined(CONFIG_PROC_FS) +/* Statistics gathering. */ +static struct dentry_stat_t dentry_stat = { + .age_limit = 45, +}; /* * Here we resort to our own counters instead of using generic per-cpu counters @@ -167,14 +174,32 @@ static long get_nr_dentry_negative(void) return sum < 0 ? 0 : sum; } -int proc_nr_dentry(struct ctl_table *table, int write, void *buffer, - size_t *lenp, loff_t *ppos) +static int proc_nr_dentry(struct ctl_table *table, int write, void *buffer, + size_t *lenp, loff_t *ppos) { dentry_stat.nr_dentry = get_nr_dentry(); dentry_stat.nr_unused = get_nr_dentry_unused(); dentry_stat.nr_negative = get_nr_dentry_negative(); return proc_doulongvec_minmax(table, write, buffer, lenp, ppos); } + +static struct ctl_table fs_dcache_sysctls[] = { + { + .procname = "dentry-state", + .data = &dentry_stat, + .maxlen = 6*sizeof(long), + .mode = 0444, + .proc_handler = proc_nr_dentry, + }, + { } +}; + +static int __init init_fs_dcache_sysctls(void) +{ + register_sysctl_init("fs", fs_dcache_sysctls); + return 0; +} +fs_initcall(init_fs_dcache_sysctls); #endif /* diff --git a/fs/eventpoll.c b/fs/eventpoll.c index 06f4c5ae1451..e2daa940ebce 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -307,7 +307,7 @@ static void unlist_file(struct epitems_head *head) static long long_zero; static long long_max = LONG_MAX; -struct ctl_table epoll_table[] = { +static struct ctl_table epoll_table[] = { { .procname = "max_user_watches", .data = &max_user_watches, @@ -319,6 +319,13 @@ struct ctl_table epoll_table[] = { }, { } }; + +static void __init epoll_sysctls_init(void) +{ + register_sysctl("fs/epoll", epoll_table); +} +#else +#define epoll_sysctls_init() do { } while (0) #endif /* CONFIG_SYSCTL */ static const struct file_operations eventpoll_fops; @@ -2378,6 +2385,7 @@ static int __init eventpoll_init(void) /* Allocates slab cache used to allocate "struct eppoll_entry" */ pwq_cache = kmem_cache_create("eventpoll_pwq", sizeof(struct eppoll_entry), 0, SLAB_PANIC|SLAB_ACCOUNT, NULL); + epoll_sysctls_init(); ephead_cache = kmem_cache_create("ep_head", sizeof(struct epitems_head), 0, SLAB_PANIC|SLAB_ACCOUNT, NULL); diff --git a/fs/exec.c b/fs/exec.c index 3c3c366a9bcf..79f2c9483302 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -65,6 +65,7 @@ #include <linux/vmalloc.h> #include <linux/io_uring.h> #include <linux/syscall_user_dispatch.h> +#include <linux/coredump.h> #include <linux/uaccess.h> #include <asm/mmu_context.h> @@ -2099,3 +2100,37 @@ COMPAT_SYSCALL_DEFINE5(execveat, int, fd, argv, envp, flags); } #endif + +#ifdef CONFIG_SYSCTL + +static int proc_dointvec_minmax_coredump(struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos) +{ + int error = proc_dointvec_minmax(table, write, buffer, lenp, ppos); + + if (!error) + validate_coredump_safety(); + return error; +} + +static struct ctl_table fs_exec_sysctls[] = { + { + .procname = "suid_dumpable", + .data = &suid_dumpable, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax_coredump, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_TWO, + }, + { } +}; + +static int __init init_fs_exec_sysctls(void) +{ + register_sysctl_init("fs", fs_exec_sysctls); + return 0; +} + +fs_initcall(init_fs_exec_sysctls); +#endif /* CONFIG_SYSCTL */ diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index cf2fd9fc7d98..9f86dd947032 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -2834,7 +2834,7 @@ out: static void *ext4_mb_seq_groups_start(struct seq_file *seq, loff_t *pos) { - struct super_block *sb = PDE_DATA(file_inode(seq->file)); + struct super_block *sb = pde_data(file_inode(seq->file)); ext4_group_t group; if (*pos < 0 || *pos >= ext4_get_groups_count(sb)) @@ -2845,7 +2845,7 @@ static void *ext4_mb_seq_groups_start(struct seq_file *seq, loff_t *pos) static void *ext4_mb_seq_groups_next(struct seq_file *seq, void *v, loff_t *pos) { - struct super_block *sb = PDE_DATA(file_inode(seq->file)); + struct super_block *sb = pde_data(file_inode(seq->file)); ext4_group_t group; ++*pos; @@ -2857,7 +2857,7 @@ static void *ext4_mb_seq_groups_next(struct seq_file *seq, void *v, loff_t *pos) static int ext4_mb_seq_groups_show(struct seq_file *seq, void *v) { - struct super_block *sb = PDE_DATA(file_inode(seq->file)); + struct super_block *sb = pde_data(file_inode(seq->file)); ext4_group_t group = (ext4_group_t) ((unsigned long) v); int i; int err, buddy_loaded = 0; @@ -2985,7 +2985,7 @@ int ext4_seq_mb_stats_show(struct seq_file *seq, void *offset) static void *ext4_mb_seq_structs_summary_start(struct seq_file *seq, loff_t *pos) __acquires(&EXT4_SB(sb)->s_mb_rb_lock) { - struct super_block *sb = PDE_DATA(file_inode(seq->file)); + struct super_block *sb = pde_data(file_inode(seq->file)); unsigned long position; read_lock(&EXT4_SB(sb)->s_mb_rb_lock); @@ -2998,7 +2998,7 @@ __acquires(&EXT4_SB(sb)->s_mb_rb_lock) static void *ext4_mb_seq_structs_summary_next(struct seq_file *seq, void *v, loff_t *pos) { - struct super_block *sb = PDE_DATA(file_inode(seq->file)); + struct super_block *sb = pde_data(file_inode(seq->file)); unsigned long position; ++*pos; @@ -3010,7 +3010,7 @@ static void *ext4_mb_seq_structs_summary_next(struct seq_file *seq, void *v, lof static int ext4_mb_seq_structs_summary_show(struct seq_file *seq, void *v) { - struct super_block *sb = PDE_DATA(file_inode(seq->file)); + struct super_block *sb = pde_data(file_inode(seq->file)); struct ext4_sb_info *sbi = EXT4_SB(sb); unsigned long position = ((unsigned long) v); struct ext4_group_info *grp; @@ -3058,7 +3058,7 @@ static int ext4_mb_seq_structs_summary_show(struct seq_file *seq, void *v) static void ext4_mb_seq_structs_summary_stop(struct seq_file *seq, void *v) __releases(&EXT4_SB(sb)->s_mb_rb_lock) { - struct super_block *sb = PDE_DATA(file_inode(seq->file)); + struct super_block *sb = pde_data(file_inode(seq->file)); read_unlock(&EXT4_SB(sb)->s_mb_rb_lock); } diff --git a/fs/ext4/readpage.c b/fs/ext4/readpage.c index 3db923403505..4cd62f1d848c 100644 --- a/fs/ext4/readpage.c +++ b/fs/ext4/readpage.c @@ -43,7 +43,6 @@ #include <linux/writeback.h> #include <linux/backing-dev.h> #include <linux/pagevec.h> -#include <linux/cleancache.h> #include "ext4.h" @@ -350,11 +349,6 @@ int ext4_mpage_readpages(struct inode *inode, } else if (fully_mapped) { SetPageMappedToDisk(page); } - if (fully_mapped && blocks_per_page == 1 && - !PageUptodate(page) && cleancache_get_page(page) == 0) { - SetPageUptodate(page); - goto confused; - } /* * This page will go to BIO. Do we need to send this diff --git a/fs/ext4/super.c b/fs/ext4/super.c index db9fe4843529..eee0d9ebfa6c 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -39,7 +39,6 @@ #include <linux/log2.h> #include <linux/crc16.h> #include <linux/dax.h> -#include <linux/cleancache.h> #include <linux/uaccess.h> #include <linux/iversion.h> #include <linux/unicode.h> @@ -3149,8 +3148,6 @@ done: EXT4_BLOCKS_PER_GROUP(sb), EXT4_INODES_PER_GROUP(sb), sbi->s_mount_opt, sbi->s_mount_opt2); - - cleancache_init_fs(sb); return err; } diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index 0a1d236212f8..8c417864c66a 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -18,7 +18,6 @@ #include <linux/swap.h> #include <linux/prefetch.h> #include <linux/uio.h> -#include <linux/cleancache.h> #include <linux/sched/signal.h> #include <linux/fiemap.h> #include <linux/iomap.h> @@ -2035,12 +2034,6 @@ got_it: block_nr = map->m_pblk + block_in_file - map->m_lblk; SetPageMappedToDisk(page); - if (!PageUptodate(page) && (!PageSwapCache(page) && - !cleancache_get_page(page))) { - SetPageUptodate(page); - goto confused; - } - if (!f2fs_is_valid_blkaddr(F2FS_I_SB(inode), block_nr, DATA_GENERIC_ENHANCE_READ)) { ret = -EFSCORRUPTED; @@ -2096,12 +2089,6 @@ submit_and_realloc: ClearPageError(page); *last_block_in_bio = block_nr; goto out; -confused: - if (bio) { - __submit_bio(F2FS_I_SB(inode), bio, DATA); - bio = NULL; - } - unlock_page(page); out: *bio_ret = bio; return ret; diff --git a/fs/file_table.c b/fs/file_table.c index 45437f8e1003..57edef16dce4 100644 --- a/fs/file_table.c +++ b/fs/file_table.c @@ -33,7 +33,7 @@ #include "internal.h" /* sysctl tunables... */ -struct files_stat_struct files_stat = { +static struct files_stat_struct files_stat = { .max_files = NR_FILE }; @@ -75,22 +75,53 @@ unsigned long get_max_files(void) } EXPORT_SYMBOL_GPL(get_max_files); +#if defined(CONFIG_SYSCTL) && defined(CONFIG_PROC_FS) + /* * Handle nr_files sysctl */ -#if defined(CONFIG_SYSCTL) && defined(CONFIG_PROC_FS) -int proc_nr_files(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos) +static int proc_nr_files(struct ctl_table *table, int write, void *buffer, + size_t *lenp, loff_t *ppos) { files_stat.nr_files = get_nr_files(); return proc_doulongvec_minmax(table, write, buffer, lenp, ppos); } -#else -int proc_nr_files(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos) + +static struct ctl_table fs_stat_sysctls[] = { + { + .procname = "file-nr", + .data = &files_stat, + .maxlen = sizeof(files_stat), + .mode = 0444, + .proc_handler = proc_nr_files, + }, + { + .procname = "file-max", + .data = &files_stat.max_files, + .maxlen = sizeof(files_stat.max_files), + .mode = 0644, + .proc_handler = proc_doulongvec_minmax, + .extra1 = SYSCTL_LONG_ZERO, + .extra2 = SYSCTL_LONG_MAX, + }, + { + .procname = "nr_open", + .data = &sysctl_nr_open, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &sysctl_nr_open_min, + .extra2 = &sysctl_nr_open_max, + }, + { } +}; + +static int __init init_fs_stat_sysctls(void) { - return -ENOSYS; + register_sysctl_init("fs", fs_stat_sysctls); + return 0; } +fs_initcall(init_fs_stat_sysctls); #endif static struct file *__alloc_file(int flags, const struct cred *cred) diff --git a/fs/inode.c b/fs/inode.c index 980e7b7a5460..63324df6fa27 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -67,11 +67,6 @@ const struct address_space_operations empty_aops = { }; EXPORT_SYMBOL(empty_aops); -/* - * Statistics gathering.. - */ -struct inodes_stat_t inodes_stat; - static DEFINE_PER_CPU(unsigned long, nr_inodes); static DEFINE_PER_CPU(unsigned long, nr_unused); @@ -106,13 +101,43 @@ long get_nr_dirty_inodes(void) * Handle nr_inode sysctl */ #ifdef CONFIG_SYSCTL -int proc_nr_inodes(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos) +/* + * Statistics gathering.. + */ +static struct inodes_stat_t inodes_stat; + +static int proc_nr_inodes(struct ctl_table *table, int write, void *buffer, + size_t *lenp, loff_t *ppos) { inodes_stat.nr_inodes = get_nr_inodes(); inodes_stat.nr_unused = get_nr_inodes_unused(); return proc_doulongvec_minmax(table, write, buffer, lenp, ppos); } + +static struct ctl_table inodes_sysctls[] = { + { + .procname = "inode-nr", + .data = &inodes_stat, + .maxlen = 2*sizeof(long), + .mode = 0444, + .proc_handler = proc_nr_inodes, + }, + { + .procname = "inode-state", + .data = &inodes_stat, + .maxlen = 7*sizeof(long), + .mode = 0444, + .proc_handler = proc_nr_inodes, + }, + { } +}; + +static int __init init_fs_inode_sysctls(void) +{ + register_sysctl_init("fs", inodes_sysctls); + return 0; +} +early_initcall(init_fs_inode_sysctls); #endif static int no_open(struct inode *inode, struct file *file) diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index 0b86a4365b66..f13d548e4a7f 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -1212,7 +1212,7 @@ static const struct seq_operations jbd2_seq_info_ops = { static int jbd2_seq_info_open(struct inode *inode, struct file *file) { - journal_t *journal = PDE_DATA(inode); + journal_t *journal = pde_data(inode); struct jbd2_stats_proc_session *s; int rc, size; diff --git a/fs/locks.c b/fs/locks.c index 0fca9d680978..8c6df10cd9ed 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -62,6 +62,7 @@ #include <linux/pid_namespace.h> #include <linux/hashtable.h> #include <linux/percpu.h> +#include <linux/sysctl.h> #define CREATE_TRACE_POINTS #include <trace/events/filelock.h> @@ -88,8 +89,37 @@ static int target_leasetype(struct file_lock *fl) return fl->fl_type; } -int leases_enable = 1; -int lease_break_time = 45; +static int leases_enable = 1; +static int lease_break_time = 45; + +#ifdef CONFIG_SYSCTL +static struct ctl_table locks_sysctls[] = { + { + .procname = "leases-enable", + .data = &leases_enable, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, +#ifdef CONFIG_MMU + { + .procname = "lease-break-time", + .data = &lease_break_time, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, +#endif /* CONFIG_MMU */ + {} +}; + +static int __init init_fs_locks_sysctls(void) +{ + register_sysctl_init("fs", locks_sysctls); + return 0; +} +early_initcall(init_fs_locks_sysctls); +#endif /* CONFIG_SYSCTL */ /* * The global file_lock_list is only used for displaying /proc/locks, so we diff --git a/fs/mpage.c b/fs/mpage.c index 334e7d09aa65..87f5cfef6caa 100644 --- a/fs/mpage.c +++ b/fs/mpage.c @@ -29,7 +29,6 @@ #include <linux/writeback.h> #include <linux/backing-dev.h> #include <linux/pagevec.h> -#include <linux/cleancache.h> #include "internal.h" /* @@ -284,12 +283,6 @@ static struct bio *do_mpage_readpage(struct mpage_readpage_args *args) SetPageMappedToDisk(page); } - if (fully_mapped && blocks_per_page == 1 && !PageUptodate(page) && - cleancache_get_page(page) == 0) { - SetPageUptodate(page); - goto confused; - } - /* * This page will go to BIO. Do we need to send this BIO off first? */ diff --git a/fs/namei.c b/fs/namei.c index d81f04f8d818..b867a92c078e 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -1020,10 +1020,60 @@ static inline void put_link(struct nameidata *nd) path_put(&last->link); } -int sysctl_protected_symlinks __read_mostly = 0; -int sysctl_protected_hardlinks __read_mostly = 0; -int sysctl_protected_fifos __read_mostly; -int sysctl_protected_regular __read_mostly; +static int sysctl_protected_symlinks __read_mostly; +static int sysctl_protected_hardlinks __read_mostly; +static int sysctl_protected_fifos __read_mostly; +static int sysctl_protected_regular __read_mostly; + +#ifdef CONFIG_SYSCTL +static struct ctl_table namei_sysctls[] = { + { + .procname = "protected_symlinks", + .data = &sysctl_protected_symlinks, + .maxlen = sizeof(int), + .mode = 0600, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, + { + .procname = "protected_hardlinks", + .data = &sysctl_protected_hardlinks, + .maxlen = sizeof(int), + .mode = 0600, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, + { + .procname = "protected_fifos", + .data = &sysctl_protected_fifos, + .maxlen = sizeof(int), + .mode = 0600, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_TWO, + }, + { + .procname = "protected_regular", + .data = &sysctl_protected_regular, + .maxlen = sizeof(int), + .mode = 0600, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_TWO, + }, + { } +}; + +static int __init init_fs_namei_sysctls(void) +{ + register_sysctl_init("fs", namei_sysctls); + return 0; +} +fs_initcall(init_fs_namei_sysctls); + +#endif /* CONFIG_SYSCTL */ /** * may_follow_link - Check symlink following for unsafe situations diff --git a/fs/namespace.c b/fs/namespace.c index dc31ad6b370f..40b994a29e90 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -37,7 +37,7 @@ #include "internal.h" /* Maximum number of mounts in a mount namespace */ -unsigned int sysctl_mount_max __read_mostly = 100000; +static unsigned int sysctl_mount_max __read_mostly = 100000; static unsigned int m_hash_mask __read_mostly; static unsigned int m_hash_shift __read_mostly; @@ -4620,3 +4620,25 @@ const struct proc_ns_operations mntns_operations = { .install = mntns_install, .owner = mntns_owner, }; + +#ifdef CONFIG_SYSCTL +static struct ctl_table fs_namespace_sysctls[] = { + { + .procname = "mount-max", + .data = &sysctl_mount_max, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ONE, + }, + { } +}; + +static int __init init_fs_namespace_sysctls(void) +{ + register_sysctl_init("fs", fs_namespace_sysctls); + return 0; +} +fs_initcall(init_fs_namespace_sysctls); + +#endif /* CONFIG_SYSCTL */ diff --git a/fs/notify/dnotify/dnotify.c b/fs/notify/dnotify/dnotify.c index d5ebebb034ff..829dd4a61b66 100644 --- a/fs/notify/dnotify/dnotify.c +++ b/fs/notify/dnotify/dnotify.c @@ -19,7 +19,25 @@ #include <linux/fdtable.h> #include <linux/fsnotify_backend.h> -int dir_notify_enable __read_mostly = 1; +static int dir_notify_enable __read_mostly = 1; +#ifdef CONFIG_SYSCTL +static struct ctl_table dnotify_sysctls[] = { + { + .procname = "dir-notify-enable", + .data = &dir_notify_enable, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + {} +}; +static void __init dnotify_sysctl_init(void) +{ + register_sysctl_init("fs", dnotify_sysctls); +} +#else +#define dnotify_sysctl_init() do { } while (0) +#endif static struct kmem_cache *dnotify_struct_cache __read_mostly; static struct kmem_cache *dnotify_mark_cache __read_mostly; @@ -386,6 +404,7 @@ static int __init dnotify_init(void) dnotify_group = fsnotify_alloc_group(&dnotify_fsnotify_ops); if (IS_ERR(dnotify_group)) panic("unable to allocate fsnotify group for dnotify\n"); + dnotify_sysctl_init(); return 0; } diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index 73a3e939c921..73b1615f9d96 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -59,7 +59,7 @@ static int fanotify_max_queued_events __read_mostly; static long ft_zero = 0; static long ft_int_max = INT_MAX; -struct ctl_table fanotify_table[] = { +static struct ctl_table fanotify_table[] = { { .procname = "max_user_groups", .data = &init_user_ns.ucount_max[UCOUNT_FANOTIFY_GROUPS], @@ -88,6 +88,13 @@ struct ctl_table fanotify_table[] = { }, { } }; + +static void __init fanotify_sysctls_init(void) +{ + register_sysctl("fs/fanotify", fanotify_table); +} +#else +#define fanotify_sysctls_init() do { } while (0) #endif /* CONFIG_SYSCTL */ /* @@ -1743,6 +1750,7 @@ static int __init fanotify_user_setup(void) init_user_ns.ucount_max[UCOUNT_FANOTIFY_GROUPS] = FANOTIFY_DEFAULT_MAX_GROUPS; init_user_ns.ucount_max[UCOUNT_FANOTIFY_MARKS] = max_marks; + fanotify_sysctls_init(); return 0; } diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c index 29fca3284bb5..54583f62dc44 100644 --- a/fs/notify/inotify/inotify_user.c +++ b/fs/notify/inotify/inotify_user.c @@ -58,7 +58,7 @@ struct kmem_cache *inotify_inode_mark_cachep __read_mostly; static long it_zero = 0; static long it_int_max = INT_MAX; -struct ctl_table inotify_table[] = { +static struct ctl_table inotify_table[] = { { .procname = "max_user_instances", .data = &init_user_ns.ucount_max[UCOUNT_INOTIFY_INSTANCES], @@ -87,6 +87,14 @@ struct ctl_table inotify_table[] = { }, { } }; + +static void __init inotify_sysctls_init(void) +{ + register_sysctl("fs/inotify", inotify_table); +} + +#else +#define inotify_sysctls_init() do { } while (0) #endif /* CONFIG_SYSCTL */ static inline __u32 inotify_arg_to_mask(struct inode *inode, u32 arg) @@ -849,6 +857,7 @@ static int __init inotify_user_setup(void) inotify_max_queued_events = 16384; init_user_ns.ucount_max[UCOUNT_INOTIFY_INSTANCES] = 128; init_user_ns.ucount_max[UCOUNT_INOTIFY_WATCHES] = watches_max; + inotify_sysctls_init(); return 0; } diff --git a/fs/ntfs3/ntfs_fs.h b/fs/ntfs3/ntfs_fs.h index 8aaec7e0804e..fb825059d488 100644 --- a/fs/ntfs3/ntfs_fs.h +++ b/fs/ntfs3/ntfs_fs.h @@ -11,7 +11,6 @@ #include <linux/blkdev.h> #include <linux/buffer_head.h> -#include <linux/cleancache.h> #include <linux/fs.h> #include <linux/highmem.h> #include <linux/kernel.h> diff --git a/fs/ocfs2/stackglue.c b/fs/ocfs2/stackglue.c index 16f1bfc407f2..731558a6f27d 100644 --- a/fs/ocfs2/stackglue.c +++ b/fs/ocfs2/stackglue.c @@ -672,31 +672,8 @@ static struct ctl_table ocfs2_mod_table[] = { { } }; -static struct ctl_table ocfs2_kern_table[] = { - { - .procname = "ocfs2", - .data = NULL, - .maxlen = 0, - .mode = 0555, - .child = ocfs2_mod_table - }, - { } -}; - -static struct ctl_table ocfs2_root_table[] = { - { - .procname = "fs", - .data = NULL, - .maxlen = 0, - .mode = 0555, - .child = ocfs2_kern_table - }, - { } -}; - static struct ctl_table_header *ocfs2_table_header; - /* * Initialization */ @@ -705,7 +682,7 @@ static int __init ocfs2_stack_glue_init(void) { strcpy(cluster_stack_name, OCFS2_STACK_PLUGIN_O2CB); - ocfs2_table_header = register_sysctl_table(ocfs2_root_table); + ocfs2_table_header = register_sysctl("fs/ocfs2", ocfs2_mod_table); if (!ocfs2_table_header) { printk(KERN_ERR "ocfs2 stack glue: unable to register sysctl\n"); diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c index 1286b88b6fa1..2772dec9dcea 100644 --- a/fs/ocfs2/super.c +++ b/fs/ocfs2/super.c @@ -25,7 +25,6 @@ #include <linux/mount.h> #include <linux/seq_file.h> #include <linux/quotaops.h> -#include <linux/cleancache.h> #include <linux/signal.h> #define CREATE_TRACE_POINTS @@ -2283,7 +2282,6 @@ static int ocfs2_initialize_super(struct super_block *sb, mlog_errno(status); goto bail; } - cleancache_init_shared_fs(sb); osb->ocfs2_wq = alloc_ordered_workqueue("ocfs2_wq", WQ_MEM_RECLAIM); if (!osb->ocfs2_wq) { diff --git a/fs/pipe.c b/fs/pipe.c index 6d4342bad9f1..cc28623a67b6 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -25,6 +25,7 @@ #include <linux/fcntl.h> #include <linux/memcontrol.h> #include <linux/watch_queue.h> +#include <linux/sysctl.h> #include <linux/uaccess.h> #include <asm/ioctls.h> @@ -50,13 +51,13 @@ * The max size that a non-root user is allowed to grow the pipe. Can * be set by root in /proc/sys/fs/pipe-max-size */ -unsigned int pipe_max_size = 1048576; +static unsigned int pipe_max_size = 1048576; /* Maximum allocatable pages per user. Hard limit is unset by default, soft * matches default values. */ -unsigned long pipe_user_pages_hard; -unsigned long pipe_user_pages_soft = PIPE_DEF_BUFFERS * INR_OPEN_CUR; +static unsigned long pipe_user_pages_hard; +static unsigned long pipe_user_pages_soft = PIPE_DEF_BUFFERS * INR_OPEN_CUR; /* * We use head and tail indices that aren't masked off, except at the point of @@ -1428,6 +1429,60 @@ static struct file_system_type pipe_fs_type = { .kill_sb = kill_anon_super, }; +#ifdef CONFIG_SYSCTL +static int do_proc_dopipe_max_size_conv(unsigned long *lvalp, + unsigned int *valp, + int write, void *data) +{ + if (write) { + unsigned int val; + + val = round_pipe_size(*lvalp); + if (val == 0) + return -EINVAL; + + *valp = val; + } else { + unsigned int val = *valp; + *lvalp = (unsigned long) val; + } + + return 0; +} + +static int proc_dopipe_max_size(struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos) +{ + return do_proc_douintvec(table, write, buffer, lenp, ppos, + do_proc_dopipe_max_size_conv, NULL); +} + +static struct ctl_table fs_pipe_sysctls[] = { + { + .procname = "pipe-max-size", + .data = &pipe_max_size, + .maxlen = sizeof(pipe_max_size), + .mode = 0644, + .proc_handler = proc_dopipe_max_size, + }, + { + .procname = "pipe-user-pages-hard", + .data = &pipe_user_pages_hard, + .maxlen = sizeof(pipe_user_pages_hard), + .mode = 0644, + .proc_handler = proc_doulongvec_minmax, + }, + { + .procname = "pipe-user-pages-soft", + .data = &pipe_user_pages_soft, + .maxlen = sizeof(pipe_user_pages_soft), + .mode = 0644, + .proc_handler = proc_doulongvec_minmax, + }, + { } +}; +#endif + static int __init init_pipe_fs(void) { int err = register_filesystem(&pipe_fs_type); @@ -1439,6 +1494,9 @@ static int __init init_pipe_fs(void) unregister_filesystem(&pipe_fs_type); } } +#ifdef CONFIG_SYSCTL + register_sysctl_init("fs", fs_pipe_sysctls); +#endif return err; } diff --git a/fs/proc/generic.c b/fs/proc/generic.c index 5b78739e60e4..f2132407e133 100644 --- a/fs/proc/generic.c +++ b/fs/proc/generic.c @@ -791,12 +791,6 @@ void proc_remove(struct proc_dir_entry *de) } EXPORT_SYMBOL(proc_remove); -void *PDE_DATA(const struct inode *inode) -{ - return __PDE_DATA(inode); -} -EXPORT_SYMBOL(PDE_DATA); - /* * Pull a user buffer into memory and pass it to the file's write handler if * one is supplied. The ->write() method is permitted to modify the diff --git a/fs/proc/inode.c b/fs/proc/inode.c index 599eb724ff2d..f84355c5a36d 100644 --- a/fs/proc/inode.c +++ b/fs/proc/inode.c @@ -650,6 +650,7 @@ struct inode *proc_get_inode(struct super_block *sb, struct proc_dir_entry *de) return NULL; } + inode->i_private = de->data; inode->i_ino = de->low_ino; inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode); PROC_I(inode)->pde = de; diff --git a/fs/proc/internal.h b/fs/proc/internal.h index 03415f3fb3a8..06a80f78433d 100644 --- a/fs/proc/internal.h +++ b/fs/proc/internal.h @@ -115,11 +115,6 @@ static inline struct proc_dir_entry *PDE(const struct inode *inode) return PROC_I(inode)->pde; } -static inline void *__PDE_DATA(const struct inode *inode) -{ - return PDE(inode)->data; -} - static inline struct pid *proc_pid(const struct inode *inode) { return PROC_I(inode)->pid; diff --git a/fs/proc/proc_net.c b/fs/proc/proc_net.c index 39b823ab2564..e1cfeda397f3 100644 --- a/fs/proc/proc_net.c +++ b/fs/proc/proc_net.c @@ -138,7 +138,7 @@ EXPORT_SYMBOL_GPL(proc_create_net_data); * @parent: The parent directory in which to create. * @ops: The seq_file ops with which to read the file. * @write: The write method with which to 'modify' the file. - * @data: Data for retrieval by PDE_DATA(). + * @data: Data for retrieval by pde_data(). * * Create a network namespaced proc file in the @parent directory with the * specified @name and @mode that allows reading of a file that displays a @@ -153,7 +153,7 @@ EXPORT_SYMBOL_GPL(proc_create_net_data); * modified by the @write function. @write should return 0 on success. * * The @data value is accessible from the @show and @write functions by calling - * PDE_DATA() on the file inode. The network namespace must be accessed by + * pde_data() on the file inode. The network namespace must be accessed by * calling seq_file_net() on the seq_file struct. */ struct proc_dir_entry *proc_create_net_data_write(const char *name, umode_t mode, @@ -230,7 +230,7 @@ EXPORT_SYMBOL_GPL(proc_create_net_single); * @parent: The parent directory in which to create. * @show: The seqfile show method with which to read the file. * @write: The write method with which to 'modify' the file. - * @data: Data for retrieval by PDE_DATA(). + * @data: Data for retrieval by pde_data(). * * Create a network-namespaced proc file in the @parent directory with the * specified @name and @mode that allows reading of a file that displays a @@ -245,7 +245,7 @@ EXPORT_SYMBOL_GPL(proc_create_net_single); * modified by the @write function. @write should return 0 on success. * * The @data value is accessible from the @show and @write functions by calling - * PDE_DATA() on the file inode. The network namespace must be accessed by + * pde_data() on the file inode. The network namespace must be accessed by * calling seq_file_single_net() on the seq_file struct. */ struct proc_dir_entry *proc_create_net_single_write(const char *name, umode_t mode, diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index 389e1e42e7d9..7d9cfc730bd4 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -16,6 +16,7 @@ #include <linux/module.h> #include <linux/bpf-cgroup.h> #include <linux/mount.h> +#include <linux/kmemleak.h> #include "internal.h" static const struct dentry_operations proc_sys_dentry_operations; @@ -25,15 +26,32 @@ static const struct file_operations proc_sys_dir_file_operations; static const struct inode_operations proc_sys_dir_operations; /* shared constants to be used in various sysctls */ -const int sysctl_vals[] = { 0, 1, INT_MAX }; +const int sysctl_vals[] = { -1, 0, 1, 2, 4, 100, 200, 1000, 3000, INT_MAX, 65535 }; EXPORT_SYMBOL(sysctl_vals); +const unsigned long sysctl_long_vals[] = { 0, 1, LONG_MAX }; +EXPORT_SYMBOL_GPL(sysctl_long_vals); + /* Support for permanently empty directories */ struct ctl_table sysctl_mount_point[] = { { } }; +/** + * register_sysctl_mount_point() - registers a sysctl mount point + * @path: path for the mount point + * + * Used to create a permanently empty directory to serve as mount point. + * There are some subtle but important permission checks this allows in the + * case of unprivileged mounts. + */ +struct ctl_table_header *register_sysctl_mount_point(const char *path) +{ + return register_sysctl(path, sysctl_mount_point); +} +EXPORT_SYMBOL(register_sysctl_mount_point); + static bool is_empty_dir(struct ctl_table_header *head) { return head->ctl_table[0].child == sysctl_mount_point; @@ -1383,6 +1401,38 @@ struct ctl_table_header *register_sysctl(const char *path, struct ctl_table *tab } EXPORT_SYMBOL(register_sysctl); +/** + * __register_sysctl_init() - register sysctl table to path + * @path: path name for sysctl base + * @table: This is the sysctl table that needs to be registered to the path + * @table_name: The name of sysctl table, only used for log printing when + * registration fails + * + * The sysctl interface is used by userspace to query or modify at runtime + * a predefined value set on a variable. These variables however have default + * values pre-set. Code which depends on these variables will always work even + * if register_sysctl() fails. If register_sysctl() fails you'd just loose the + * ability to query or modify the sysctls dynamically at run time. Chances of + * register_sysctl() failing on init are extremely low, and so for both reasons + * this function does not return any error as it is used by initialization code. + * + * Context: Can only be called after your respective sysctl base path has been + * registered. So for instance, most base directories are registered early on + * init before init levels are processed through proc_sys_init() and + * sysctl_init_bases(). + */ +void __init __register_sysctl_init(const char *path, struct ctl_table *table, + const char *table_name) +{ + struct ctl_table_header *hdr = register_sysctl(path, table); + + if (unlikely(!hdr)) { + pr_err("failed when register_sysctl %s to %s\n", table_name, path); + return; + } + kmemleak_not_leak(hdr); +} + static char *append_path(const char *path, char *pos, const char *name) { int namelen; @@ -1596,6 +1646,15 @@ struct ctl_table_header *register_sysctl_table(struct ctl_table *table) } EXPORT_SYMBOL(register_sysctl_table); +int __register_sysctl_base(struct ctl_table *base_table) +{ + struct ctl_table_header *hdr; + + hdr = register_sysctl_table(base_table); + kmemleak_not_leak(hdr); + return 0; +} + static void put_links(struct ctl_table_header *header) { struct ctl_table_set *root_set = &sysctl_table_root.default_set; @@ -1709,7 +1768,7 @@ int __init proc_sys_init(void) proc_sys_root->proc_dir_ops = &proc_sys_dir_file_operations; proc_sys_root->nlink = 0; - return sysctl_init(); + return sysctl_init_bases(); } struct sysctl_alias { diff --git a/fs/super.c b/fs/super.c index a6405d44d4ca..7af820ba5ad5 100644 --- a/fs/super.c +++ b/fs/super.c @@ -31,7 +31,6 @@ #include <linux/mutex.h> #include <linux/backing-dev.h> #include <linux/rculist_bl.h> -#include <linux/cleancache.h> #include <linux/fscrypt.h> #include <linux/fsnotify.h> #include <linux/lockdep.h> @@ -260,7 +259,6 @@ static struct super_block *alloc_super(struct file_system_type *type, int flags, s->s_time_gran = 1000000000; s->s_time_min = TIME64_MIN; s->s_time_max = TIME64_MAX; - s->cleancache_poolid = CLEANCACHE_NO_POOL; s->s_shrink.seeks = DEFAULT_SEEKS; s->s_shrink.scan_objects = super_cache_scan; @@ -330,7 +328,6 @@ void deactivate_locked_super(struct super_block *s) { struct file_system_type *fs = s->s_type; if (atomic_dec_and_test(&s->s_active)) { - cleancache_invalidate_fs(s); unregister_shrinker(&s->s_shrink); fs->kill_sb(s); diff --git a/fs/sysctls.c b/fs/sysctls.c new file mode 100644 index 000000000000..c701273c9432 --- /dev/null +++ b/fs/sysctls.c @@ -0,0 +1,39 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * /proc/sys/fs shared sysctls + * + * These sysctls are shared between different filesystems. + */ +#include <linux/init.h> +#include <linux/sysctl.h> + +static struct ctl_table fs_shared_sysctls[] = { + { + .procname = "overflowuid", + .data = &fs_overflowuid, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_MAXOLDUID, + }, + { + .procname = "overflowgid", + .data = &fs_overflowgid, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_MAXOLDUID, + }, + { } +}; + +DECLARE_SYSCTL_BASE(fs, fs_shared_sysctls); + +static int __init init_fs_sysctls(void) +{ + return register_sysctl_base(fs); +} + +early_initcall(init_fs_sysctls); diff --git a/include/linux/aio.h b/include/linux/aio.h index b83e68dd006f..86892a4fe7c8 100644 --- a/include/linux/aio.h +++ b/include/linux/aio.h @@ -20,8 +20,4 @@ static inline void kiocb_set_cancel_fn(struct kiocb *req, kiocb_cancel_fn *cancel) { } #endif /* CONFIG_AIO */ -/* for sysctl: */ -extern unsigned long aio_nr; -extern unsigned long aio_max_nr; - #endif /* __LINUX__AIO_H */ diff --git a/include/linux/cleancache.h b/include/linux/cleancache.h deleted file mode 100644 index 5f5730c1d324..000000000000 --- a/include/linux/cleancache.h +++ /dev/null @@ -1,124 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _LINUX_CLEANCACHE_H -#define _LINUX_CLEANCACHE_H - -#include <linux/fs.h> -#include <linux/exportfs.h> -#include <linux/mm.h> - -#define CLEANCACHE_NO_POOL -1 -#define CLEANCACHE_NO_BACKEND -2 -#define CLEANCACHE_NO_BACKEND_SHARED -3 - -#define CLEANCACHE_KEY_MAX 6 - -/* - * cleancache requires every file with a page in cleancache to have a - * unique key unless/until the file is removed/truncated. For some - * filesystems, the inode number is unique, but for "modern" filesystems - * an exportable filehandle is required (see exportfs.h) - */ -struct cleancache_filekey { - union { - ino_t ino; - __u32 fh[CLEANCACHE_KEY_MAX]; - u32 key[CLEANCACHE_KEY_MAX]; - } u; -}; - -struct cleancache_ops { - int (*init_fs)(size_t); - int (*init_shared_fs)(uuid_t *uuid, size_t); - int (*get_page)(int, struct cleancache_filekey, - pgoff_t, struct page *); - void (*put_page)(int, struct cleancache_filekey, - pgoff_t, struct page *); - void (*invalidate_page)(int, struct cleancache_filekey, pgoff_t); - void (*invalidate_inode)(int, struct cleancache_filekey); - void (*invalidate_fs)(int); -}; - -extern int cleancache_register_ops(const struct cleancache_ops *ops); -extern void __cleancache_init_fs(struct super_block *); -extern void __cleancache_init_shared_fs(struct super_block *); -extern int __cleancache_get_page(struct page *); -extern void __cleancache_put_page(struct page *); -extern void __cleancache_invalidate_page(struct address_space *, struct page *); -extern void __cleancache_invalidate_inode(struct address_space *); -extern void __cleancache_invalidate_fs(struct super_block *); - -#ifdef CONFIG_CLEANCACHE -#define cleancache_enabled (1) -static inline bool cleancache_fs_enabled_mapping(struct address_space *mapping) -{ - return mapping->host->i_sb->cleancache_poolid >= 0; -} -static inline bool cleancache_fs_enabled(struct page *page) -{ - return cleancache_fs_enabled_mapping(page->mapping); -} -#else -#define cleancache_enabled (0) -#define cleancache_fs_enabled(_page) (0) -#define cleancache_fs_enabled_mapping(_page) (0) -#endif - -/* - * The shim layer provided by these inline functions allows the compiler - * to reduce all cleancache hooks to nothingness if CONFIG_CLEANCACHE - * is disabled, to a single global variable check if CONFIG_CLEANCACHE - * is enabled but no cleancache "backend" has dynamically enabled it, - * and, for the most frequent cleancache ops, to a single global variable - * check plus a superblock element comparison if CONFIG_CLEANCACHE is enabled - * and a cleancache backend has dynamically enabled cleancache, but the - * filesystem referenced by that cleancache op has not enabled cleancache. - * As a result, CONFIG_CLEANCACHE can be enabled by default with essentially - * no measurable performance impact. - */ - -static inline void cleancache_init_fs(struct super_block *sb) -{ - if (cleancache_enabled) - __cleancache_init_fs(sb); -} - -static inline void cleancache_init_shared_fs(struct super_block *sb) -{ - if (cleancache_enabled) - __cleancache_init_shared_fs(sb); -} - -static inline int cleancache_get_page(struct page *page) -{ - if (cleancache_enabled && cleancache_fs_enabled(page)) - return __cleancache_get_page(page); - return -1; -} - -static inline void cleancache_put_page(struct page *page) -{ - if (cleancache_enabled && cleancache_fs_enabled(page)) - __cleancache_put_page(page); -} - -static inline void cleancache_invalidate_page(struct address_space *mapping, - struct page *page) -{ - /* careful... page->mapping is NULL sometimes when this is called */ - if (cleancache_enabled && cleancache_fs_enabled_mapping(mapping)) - __cleancache_invalidate_page(mapping, page); -} - -static inline void cleancache_invalidate_inode(struct address_space *mapping) -{ - if (cleancache_enabled && cleancache_fs_enabled_mapping(mapping)) - __cleancache_invalidate_inode(mapping); -} - -static inline void cleancache_invalidate_fs(struct super_block *sb) -{ - if (cleancache_enabled) - __cleancache_invalidate_fs(sb); -} - -#endif /* _LINUX_CLEANCACHE_H */ diff --git a/include/linux/coredump.h b/include/linux/coredump.h index 78fcd776b185..248a68c668b4 100644 --- a/include/linux/coredump.h +++ b/include/linux/coredump.h @@ -14,10 +14,6 @@ struct core_vma_metadata { unsigned long dump_size; }; -extern int core_uses_pid; -extern char core_pattern[]; -extern unsigned int core_pipe_limit; - /* * These are the only things you should do on a core-file: use only these * functions to write out all the necessary info. @@ -37,4 +33,10 @@ extern void do_coredump(const kernel_siginfo_t *siginfo); static inline void do_coredump(const kernel_siginfo_t *siginfo) {} #endif +#if defined(CONFIG_COREDUMP) && defined(CONFIG_SYSCTL) +extern void validate_coredump_safety(void); +#else +static inline void validate_coredump_safety(void) {} +#endif + #endif /* _LINUX_COREDUMP_H */ diff --git a/include/linux/dcache.h b/include/linux/dcache.h index 9e23d33bb6f1..f5bba51480b2 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -61,16 +61,6 @@ extern const struct qstr empty_name; extern const struct qstr slash_name; extern const struct qstr dotdot_name; -struct dentry_stat_t { - long nr_dentry; - long nr_unused; - long age_limit; /* age in seconds */ - long want_pages; /* pages requested by system */ - long nr_negative; /* # of unused negative dentries */ - long dummy; /* Reserved for future use */ -}; -extern struct dentry_stat_t dentry_stat; - /* * Try to keep struct dentry aligned on 64 byte cachelines (this will * give reasonable cacheline footprint with larger lines without the diff --git a/include/linux/dnotify.h b/include/linux/dnotify.h index b87c3b85a166..b1d26f9f1c9f 100644 --- a/include/linux/dnotify.h +++ b/include/linux/dnotify.h @@ -29,7 +29,6 @@ struct dnotify_struct { FS_CREATE | FS_RENAME |\ FS_MOVED_FROM | FS_MOVED_TO) -extern int dir_notify_enable; extern void dnotify_flush(struct file *, fl_owner_t); extern int fcntl_dirnotify(int, struct file *, unsigned long); diff --git a/include/linux/fanotify.h b/include/linux/fanotify.h index 3afdf339d53c..419cadcd7ff5 100644 --- a/include/linux/fanotify.h +++ b/include/linux/fanotify.h @@ -5,8 +5,6 @@ #include <linux/sysctl.h> #include <uapi/linux/fanotify.h> -extern struct ctl_table fanotify_table[]; /* for sysctl */ - #define FAN_GROUP_FLAG(group, flag) \ ((group)->fanotify_data.flags & (flag)) diff --git a/include/linux/frontswap.h b/include/linux/frontswap.h index b07d88c92bb2..a631bac12220 100644 --- a/include/linux/frontswap.h +++ b/include/linux/frontswap.h @@ -7,31 +7,17 @@ #include <linux/bitops.h> #include <linux/jump_label.h> -/* - * Return code to denote that requested number of - * frontswap pages are unused(moved to page cache). - * Used in shmem_unuse and try_to_unuse. - */ -#define FRONTSWAP_PAGES_UNUSED 2 - struct frontswap_ops { void (*init)(unsigned); /* this swap type was just swapon'ed */ int (*store)(unsigned, pgoff_t, struct page *); /* store a page */ int (*load)(unsigned, pgoff_t, struct page *); /* load a page */ void (*invalidate_page)(unsigned, pgoff_t); /* page no longer needed */ void (*invalidate_area)(unsigned); /* swap type just swapoff'ed */ - struct frontswap_ops *next; /* private pointer to next ops */ }; -extern void frontswap_register_ops(struct frontswap_ops *ops); -extern void frontswap_shrink(unsigned long); -extern unsigned long frontswap_curr_pages(void); -extern void frontswap_writethrough(bool); -#define FRONTSWAP_HAS_EXCLUSIVE_GETS -extern void frontswap_tmem_exclusive_gets(bool); +int frontswap_register_ops(const struct frontswap_ops *ops); -extern bool __frontswap_test(struct swap_info_struct *, pgoff_t); -extern void __frontswap_init(unsigned type, unsigned long *map); +extern void frontswap_init(unsigned type, unsigned long *map); extern int __frontswap_store(struct page *page); extern int __frontswap_load(struct page *page); extern void __frontswap_invalidate_page(unsigned, pgoff_t); @@ -45,11 +31,6 @@ static inline bool frontswap_enabled(void) return static_branch_unlikely(&frontswap_enabled_key); } -static inline bool frontswap_test(struct swap_info_struct *sis, pgoff_t offset) -{ - return __frontswap_test(sis, offset); -} - static inline void frontswap_map_set(struct swap_info_struct *p, unsigned long *map) { @@ -68,11 +49,6 @@ static inline bool frontswap_enabled(void) return false; } -static inline bool frontswap_test(struct swap_info_struct *sis, pgoff_t offset) -{ - return false; -} - static inline void frontswap_map_set(struct swap_info_struct *p, unsigned long *map) { @@ -112,11 +88,4 @@ static inline void frontswap_invalidate_area(unsigned type) __frontswap_invalidate_area(type); } -static inline void frontswap_init(unsigned type, unsigned long *map) -{ -#ifdef CONFIG_FRONTSWAP - __frontswap_init(type, map); -#endif -} - #endif /* _LINUX_FRONTSWAP_H */ diff --git a/include/linux/fs.h b/include/linux/fs.h index c8510da6cc6d..f3daaea16554 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -79,15 +79,8 @@ extern void __init inode_init_early(void); extern void __init files_init(void); extern void __init files_maxfiles_init(void); -extern struct files_stat_struct files_stat; extern unsigned long get_max_files(void); extern unsigned int sysctl_nr_open; -extern struct inodes_stat_t inodes_stat; -extern int leases_enable, lease_break_time; -extern int sysctl_protected_symlinks; -extern int sysctl_protected_hardlinks; -extern int sysctl_protected_fifos; -extern int sysctl_protected_regular; typedef __kernel_rwf_t rwf_t; @@ -1542,11 +1535,6 @@ struct super_block { const struct dentry_operations *s_d_op; /* default d_op for dentries */ - /* - * Saved pool identifier for cleancache (-1 means none) - */ - int cleancache_poolid; - struct shrinker s_shrink; /* per-sb shrinker handle */ /* Number of inodes with nlink == 0 but still referenced */ @@ -3533,12 +3521,6 @@ ssize_t simple_attr_write(struct file *file, const char __user *buf, size_t len, loff_t *ppos); struct ctl_table; -int proc_nr_files(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos); -int proc_nr_dentry(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos); -int proc_nr_inodes(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos); int __init list_bdev_fs_names(char *buf, size_t size); #define __FMODE_EXEC ((__force int) FMODE_EXEC) diff --git a/include/linux/inotify.h b/include/linux/inotify.h index 6a24905f6e1e..8d20caa1b268 100644 --- a/include/linux/inotify.h +++ b/include/linux/inotify.h @@ -7,11 +7,8 @@ #ifndef _LINUX_INOTIFY_H #define _LINUX_INOTIFY_H -#include <linux/sysctl.h> #include <uapi/linux/inotify.h> -extern struct ctl_table inotify_table[]; /* for sysctl */ - #define ALL_INOTIFY_BITS (IN_ACCESS | IN_MODIFY | IN_ATTRIB | IN_CLOSE_WRITE | \ IN_CLOSE_NOWRITE | IN_OPEN | IN_MOVED_FROM | \ IN_MOVED_TO | IN_CREATE | IN_DELETE | \ diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index 8c8f7a4d93af..19b884353b15 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -348,12 +348,6 @@ extern void opt_pre_handler(struct kprobe *p, struct pt_regs *regs); DEFINE_INSN_CACHE_OPS(optinsn); -#ifdef CONFIG_SYSCTL -extern int sysctl_kprobes_optimization; -extern int proc_kprobes_optimization_handler(struct ctl_table *table, - int write, void *buffer, - size_t *length, loff_t *ppos); -#endif /* CONFIG_SYSCTL */ extern void wait_for_kprobe_optimizer(void); #else /* !CONFIG_OPTPROBES */ static inline void wait_for_kprobe_optimizer(void) { } diff --git a/include/linux/migrate.h b/include/linux/migrate.h index 4850cc5bf813..db96e10eb8da 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -40,6 +40,8 @@ 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); +void migration_entry_wait_on_locked(swp_entry_t entry, pte_t *ptep, + spinlock_t *ptl); void folio_migrate_flags(struct folio *newfolio, struct folio *folio); void folio_migrate_copy(struct folio *newfolio, struct folio *folio); int folio_migrate_mapping(struct address_space *mapping, diff --git a/include/linux/mount.h b/include/linux/mount.h index 5d92a7e1a742..7f18a7555dff 100644 --- a/include/linux/mount.h +++ b/include/linux/mount.h @@ -113,9 +113,6 @@ extern void mnt_set_expiry(struct vfsmount *mnt, struct list_head *expiry_list); extern void mark_mounts_for_expiry(struct list_head *mounts); extern dev_t name_to_dev_t(const char *name); - -extern unsigned int sysctl_mount_max; - extern bool path_is_mountpoint(const struct path *path); extern void kern_unmount_array(struct vfsmount *mnt[], unsigned int num); diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h index fc5642431b92..c00c618ef290 100644 --- a/include/linux/pipe_fs_i.h +++ b/include/linux/pipe_fs_i.h @@ -238,10 +238,6 @@ void pipe_lock(struct pipe_inode_info *); void pipe_unlock(struct pipe_inode_info *); void pipe_double_lock(struct pipe_inode_info *, struct pipe_inode_info *); -extern unsigned int pipe_max_size; -extern unsigned long pipe_user_pages_hard; -extern unsigned long pipe_user_pages_soft; - /* Wait for a pipe to be readable/writable while dropping the pipe lock */ void pipe_wait_readable(struct pipe_inode_info *); void pipe_wait_writable(struct pipe_inode_info *); diff --git a/include/linux/poll.h b/include/linux/poll.h index 1cdc32b1f1b0..a9e0e1c2d1f2 100644 --- a/include/linux/poll.h +++ b/include/linux/poll.h @@ -8,12 +8,10 @@ #include <linux/wait.h> #include <linux/string.h> #include <linux/fs.h> -#include <linux/sysctl.h> #include <linux/uaccess.h> #include <uapi/linux/poll.h> #include <uapi/linux/eventpoll.h> -extern struct ctl_table epoll_table[]; /* for sysctl */ /* ~832 bytes of stack space used max in sys_select/sys_poll before allocating additional memory. */ #ifdef __clang__ diff --git a/include/linux/printk.h b/include/linux/printk.h index 9497f6b98339..1522df223c0f 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -183,10 +183,6 @@ extern bool printk_timed_ratelimit(unsigned long *caller_jiffies, extern int printk_delay_msec; extern int dmesg_restrict; -extern int -devkmsg_sysctl_set_loglvl(struct ctl_table *table, int write, void *buf, - size_t *lenp, loff_t *ppos); - extern void wake_up_klogd(void); char *log_buf_addr_get(void); diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index 01b9268451a8..81d6e4ec2294 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -110,7 +110,16 @@ extern struct proc_dir_entry *proc_create_data(const char *, umode_t, struct proc_dir_entry *proc_create(const char *name, umode_t mode, struct proc_dir_entry *parent, const struct proc_ops *proc_ops); extern void proc_set_size(struct proc_dir_entry *, loff_t); extern void proc_set_user(struct proc_dir_entry *, kuid_t, kgid_t); -extern void *PDE_DATA(const struct inode *); + +/* + * Obtain the private data passed by user through proc_create_data() or + * related. + */ +static inline void *pde_data(const struct inode *inode) +{ + return inode->i_private; +} + extern void *proc_get_parent_data(const struct inode *); extern void proc_remove(struct proc_dir_entry *); extern void remove_proc_entry(const char *, struct proc_dir_entry *); @@ -191,7 +200,7 @@ proc_create_data(const char *name, umode_t mode, struct proc_dir_entry *parent, static inline void proc_set_size(struct proc_dir_entry *de, loff_t size) {} static inline void proc_set_user(struct proc_dir_entry *de, kuid_t uid, kgid_t gid) {} -static inline void *PDE_DATA(const struct inode *inode) {BUG(); return NULL;} +static inline void *pde_data(const struct inode *inode) {BUG(); return NULL;} static inline void *proc_get_parent_data(const struct inode *inode) { BUG(); return NULL; } static inline void proc_remove(struct proc_dir_entry *de) {} diff --git a/include/linux/ref_tracker.h b/include/linux/ref_tracker.h index c11c9db5825c..60f3453be23e 100644 --- a/include/linux/ref_tracker.h +++ b/include/linux/ref_tracker.h @@ -4,6 +4,7 @@ #include <linux/refcount.h> #include <linux/types.h> #include <linux/spinlock.h> +#include <linux/stackdepot.h> struct ref_tracker; @@ -26,6 +27,7 @@ static inline void ref_tracker_dir_init(struct ref_tracker_dir *dir, spin_lock_init(&dir->lock); dir->quarantine_avail = quarantine_count; refcount_set(&dir->untracked, 1); + stack_depot_init(); } void ref_tracker_dir_exit(struct ref_tracker_dir *dir); diff --git a/include/linux/rwlock.h b/include/linux/rwlock.h index 2c0ad417ce3c..8f416c5e929e 100644 --- a/include/linux/rwlock.h +++ b/include/linux/rwlock.h @@ -55,6 +55,12 @@ do { \ #define write_lock(lock) _raw_write_lock(lock) #define read_lock(lock) _raw_read_lock(lock) +#ifdef CONFIG_DEBUG_LOCK_ALLOC +#define write_lock_nested(lock, subclass) _raw_write_lock_nested(lock, subclass) +#else +#define write_lock_nested(lock, subclass) _raw_write_lock(lock) +#endif + #if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) #define read_lock_irqsave(lock, flags) \ diff --git a/include/linux/rwlock_api_smp.h b/include/linux/rwlock_api_smp.h index f1db6f17c4fb..dceb0a59b692 100644 --- a/include/linux/rwlock_api_smp.h +++ b/include/linux/rwlock_api_smp.h @@ -17,6 +17,7 @@ void __lockfunc _raw_read_lock(rwlock_t *lock) __acquires(lock); void __lockfunc _raw_write_lock(rwlock_t *lock) __acquires(lock); +void __lockfunc _raw_write_lock_nested(rwlock_t *lock, int subclass) __acquires(lock); void __lockfunc _raw_read_lock_bh(rwlock_t *lock) __acquires(lock); void __lockfunc _raw_write_lock_bh(rwlock_t *lock) __acquires(lock); void __lockfunc _raw_read_lock_irq(rwlock_t *lock) __acquires(lock); @@ -209,6 +210,13 @@ static inline void __raw_write_lock(rwlock_t *lock) LOCK_CONTENDED(lock, do_raw_write_trylock, do_raw_write_lock); } +static inline void __raw_write_lock_nested(rwlock_t *lock, int subclass) +{ + preempt_disable(); + rwlock_acquire(&lock->dep_map, subclass, 0, _RET_IP_); + LOCK_CONTENDED(lock, do_raw_write_trylock, do_raw_write_lock); +} + #endif /* !CONFIG_GENERIC_LOCKBREAK || CONFIG_DEBUG_LOCK_ALLOC */ static inline void __raw_write_unlock(rwlock_t *lock) diff --git a/include/linux/rwlock_rt.h b/include/linux/rwlock_rt.h index 49c1f3842ed5..8544ff05e594 100644 --- a/include/linux/rwlock_rt.h +++ b/include/linux/rwlock_rt.h @@ -28,6 +28,7 @@ extern void rt_read_lock(rwlock_t *rwlock); extern int rt_read_trylock(rwlock_t *rwlock); extern void rt_read_unlock(rwlock_t *rwlock); extern void rt_write_lock(rwlock_t *rwlock); +extern void rt_write_lock_nested(rwlock_t *rwlock, int subclass); extern int rt_write_trylock(rwlock_t *rwlock); extern void rt_write_unlock(rwlock_t *rwlock); @@ -83,6 +84,15 @@ static __always_inline void write_lock(rwlock_t *rwlock) rt_write_lock(rwlock); } +#ifdef CONFIG_DEBUG_LOCK_ALLOC +static __always_inline void write_lock_nested(rwlock_t *rwlock, int subclass) +{ + rt_write_lock_nested(rwlock, subclass); +} +#else +#define write_lock_nested(lock, subclass) rt_write_lock(((void)(subclass), (lock))) +#endif + static __always_inline void write_lock_bh(rwlock_t *rwlock) { local_bh_disable(); diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h index 304f431178fd..c19dd5a2c05c 100644 --- a/include/linux/sched/sysctl.h +++ b/include/linux/sched/sysctl.h @@ -7,20 +7,8 @@ struct ctl_table; #ifdef CONFIG_DETECT_HUNG_TASK - -#ifdef CONFIG_SMP -extern unsigned int sysctl_hung_task_all_cpu_backtrace; -#else -#define sysctl_hung_task_all_cpu_backtrace 0 -#endif /* CONFIG_SMP */ - -extern int sysctl_hung_task_check_count; -extern unsigned int sysctl_hung_task_panic; +/* used for hung_task and block/ */ extern unsigned long sysctl_hung_task_timeout_secs; -extern unsigned long sysctl_hung_task_check_interval_secs; -extern int sysctl_hung_task_warnings; -int proc_dohung_task_timeout_secs(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos); #else /* Avoid need for ifdefs elsewhere in the code */ enum { sysctl_hung_task_timeout_secs = 0 }; diff --git a/include/linux/seq_file.h b/include/linux/seq_file.h index 72dbb44a4573..88cc16444b43 100644 --- a/include/linux/seq_file.h +++ b/include/linux/seq_file.h @@ -209,7 +209,7 @@ static const struct file_operations __name ## _fops = { \ #define DEFINE_PROC_SHOW_ATTRIBUTE(__name) \ static int __name ## _open(struct inode *inode, struct file *file) \ { \ - return single_open(file, __name ## _show, PDE_DATA(inode)); \ + return single_open(file, __name ## _show, pde_data(inode)); \ } \ \ static const struct proc_ops __name ## _proc_ops = { \ diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index 166158b6e917..e65b80ed09e7 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -83,8 +83,7 @@ extern void shmem_unlock_mapping(struct address_space *mapping); extern struct page *shmem_read_mapping_page_gfp(struct address_space *mapping, pgoff_t index, gfp_t gfp_mask); extern void shmem_truncate_range(struct inode *inode, loff_t start, loff_t end); -extern int shmem_unuse(unsigned int type, bool frontswap, - unsigned long *fs_pages_to_unuse); +int shmem_unuse(unsigned int type); extern bool shmem_is_huge(struct vm_area_struct *vma, struct inode *inode, pgoff_t index); diff --git a/include/linux/spinlock_api_up.h b/include/linux/spinlock_api_up.h index d0d188861ad6..b8ba00ccccde 100644 --- a/include/linux/spinlock_api_up.h +++ b/include/linux/spinlock_api_up.h @@ -59,6 +59,7 @@ #define _raw_spin_lock_nested(lock, subclass) __LOCK(lock) #define _raw_read_lock(lock) __LOCK(lock) #define _raw_write_lock(lock) __LOCK(lock) +#define _raw_write_lock_nested(lock, subclass) __LOCK(lock) #define _raw_spin_lock_bh(lock) __LOCK_BH(lock) #define _raw_read_lock_bh(lock) __LOCK_BH(lock) #define _raw_write_lock_bh(lock) __LOCK_BH(lock) diff --git a/include/linux/stackdepot.h b/include/linux/stackdepot.h index c34b55a6e554..17f992fe6355 100644 --- a/include/linux/stackdepot.h +++ b/include/linux/stackdepot.h @@ -19,6 +19,22 @@ depot_stack_handle_t __stack_depot_save(unsigned long *entries, unsigned int nr_entries, gfp_t gfp_flags, bool can_alloc); +/* + * Every user of stack depot has to call this during its own init when it's + * decided that it will be calling stack_depot_save() later. + * + * The alternative is to select STACKDEPOT_ALWAYS_INIT to have stack depot + * enabled as part of mm_init(), for subsystems where it's known at compile time + * that stack depot will be used. + */ +int stack_depot_init(void); + +#ifdef CONFIG_STACKDEPOT_ALWAYS_INIT +static inline int stack_depot_early_init(void) { return stack_depot_init(); } +#else +static inline int stack_depot_early_init(void) { return 0; } +#endif + depot_stack_handle_t stack_depot_save(unsigned long *entries, unsigned int nr_entries, gfp_t gfp_flags); @@ -30,13 +46,4 @@ int stack_depot_snprint(depot_stack_handle_t handle, char *buf, size_t size, void stack_depot_print(depot_stack_handle_t stack); -#ifdef CONFIG_STACKDEPOT -int stack_depot_init(void); -#else -static inline int stack_depot_init(void) -{ - return 0; -} -#endif /* CONFIG_STACKDEPOT */ - #endif diff --git a/include/linux/stackleak.h b/include/linux/stackleak.h index a59db2f08e76..ccaab2043fcd 100644 --- a/include/linux/stackleak.h +++ b/include/linux/stackleak.h @@ -23,11 +23,6 @@ static inline void stackleak_task_init(struct task_struct *t) # endif } -#ifdef CONFIG_STACKLEAK_RUNTIME_DISABLE -int stack_erasing_sysctl(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos); -#endif - #else /* !CONFIG_GCC_PLUGIN_STACKLEAK */ static inline void stackleak_task_init(struct task_struct *t) { } #endif diff --git a/include/linux/swapfile.h b/include/linux/swapfile.h index e06febf62978..54078542134c 100644 --- a/include/linux/swapfile.h +++ b/include/linux/swapfile.h @@ -6,10 +6,7 @@ * these were static in swapfile.c but frontswap.c needs them and we don't * want to expose them to the dozens of source files that include swap.h */ -extern spinlock_t swap_lock; -extern struct plist_head swap_active_head; extern struct swap_info_struct *swap_info[]; -extern int try_to_unuse(unsigned int, bool, unsigned long); extern unsigned long generic_max_swapfile_size(void); extern unsigned long max_swapfile_size(void); diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index 1fa2b69c6fc3..180adf7da785 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -38,12 +38,28 @@ struct ctl_table_header; struct ctl_dir; /* Keep the same order as in fs/proc/proc_sysctl.c */ -#define SYSCTL_ZERO ((void *)&sysctl_vals[0]) -#define SYSCTL_ONE ((void *)&sysctl_vals[1]) -#define SYSCTL_INT_MAX ((void *)&sysctl_vals[2]) +#define SYSCTL_NEG_ONE ((void *)&sysctl_vals[0]) +#define SYSCTL_ZERO ((void *)&sysctl_vals[1]) +#define SYSCTL_ONE ((void *)&sysctl_vals[2]) +#define SYSCTL_TWO ((void *)&sysctl_vals[3]) +#define SYSCTL_FOUR ((void *)&sysctl_vals[4]) +#define SYSCTL_ONE_HUNDRED ((void *)&sysctl_vals[5]) +#define SYSCTL_TWO_HUNDRED ((void *)&sysctl_vals[6]) +#define SYSCTL_ONE_THOUSAND ((void *)&sysctl_vals[7]) +#define SYSCTL_THREE_THOUSAND ((void *)&sysctl_vals[8]) +#define SYSCTL_INT_MAX ((void *)&sysctl_vals[9]) + +/* this is needed for the proc_dointvec_minmax for [fs_]overflow UID and GID */ +#define SYSCTL_MAXOLDUID ((void *)&sysctl_vals[10]) extern const int sysctl_vals[]; +#define SYSCTL_LONG_ZERO ((void *)&sysctl_long_vals[0]) +#define SYSCTL_LONG_ONE ((void *)&sysctl_long_vals[1]) +#define SYSCTL_LONG_MAX ((void *)&sysctl_long_vals[2]) + +extern const unsigned long sysctl_long_vals[]; + typedef int proc_handler(struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos); @@ -178,6 +194,20 @@ struct ctl_path { #ifdef CONFIG_SYSCTL +#define DECLARE_SYSCTL_BASE(_name, _table) \ +static struct ctl_table _name##_base_table[] = { \ + { \ + .procname = #_name, \ + .mode = 0555, \ + .child = _table, \ + }, \ + { }, \ +} + +extern int __register_sysctl_base(struct ctl_table *base_table); + +#define register_sysctl_base(_name) __register_sysctl_base(_name##_base_table) + void proc_sys_poll_notify(struct ctl_table_poll *poll); extern void setup_sysctl_set(struct ctl_table_set *p, @@ -198,8 +228,19 @@ struct ctl_table_header *register_sysctl_paths(const struct ctl_path *path, void unregister_sysctl_table(struct ctl_table_header * table); -extern int sysctl_init(void); +extern int sysctl_init_bases(void); +extern void __register_sysctl_init(const char *path, struct ctl_table *table, + const char *table_name); +#define register_sysctl_init(path, table) __register_sysctl_init(path, table, #table) +extern struct ctl_table_header *register_sysctl_mount_point(const char *path); + void do_sysctl_args(void); +int do_proc_douintvec(struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos, + int (*conv)(unsigned long *lvalp, + unsigned int *valp, + int write, void *data), + void *data); extern int pwrsw_enabled; extern int unaligned_enabled; @@ -207,16 +248,28 @@ extern int unaligned_dump_stack; extern int no_unaligned_warning; extern struct ctl_table sysctl_mount_point[]; -extern struct ctl_table random_table[]; -extern struct ctl_table firmware_config_table[]; -extern struct ctl_table epoll_table[]; #else /* CONFIG_SYSCTL */ + +#define DECLARE_SYSCTL_BASE(_name, _table) + +static inline int __register_sysctl_base(struct ctl_table *base_table) +{ + return 0; +} + +#define register_sysctl_base(table) __register_sysctl_base(table) + static inline struct ctl_table_header *register_sysctl_table(struct ctl_table * table) { return NULL; } +static inline struct sysctl_header *register_sysctl_mount_point(const char *path) +{ + return NULL; +} + static inline struct ctl_table_header *register_sysctl_paths( const struct ctl_path *path, struct ctl_table *table) { diff --git a/include/scsi/sg.h b/include/scsi/sg.h index 843cefb8efce..068e35d36557 100644 --- a/include/scsi/sg.h +++ b/include/scsi/sg.h @@ -29,10 +29,6 @@ * For utility and test programs see: http://sg.danny.cz/sg/sg3_utils.html */ -#ifdef __KERNEL__ -extern int sg_big_buff; /* for sysctl */ -#endif - typedef struct sg_iovec /* same structure as used by readv() Linux system */ { /* call. It defines one scatter-gather element. */ diff --git a/init/main.c b/init/main.c index bb984ed79de0..65fa2e41a9c0 100644 --- a/init/main.c +++ b/init/main.c @@ -834,12 +834,15 @@ static void __init mm_init(void) init_mem_debugging_and_hardening(); kfence_alloc_pool(); report_meminit(); - stack_depot_init(); + stack_depot_early_init(); mem_init(); mem_init_print_info(); - /* page_owner must be initialized after buddy is ready */ - page_ext_init_flatmem_late(); kmem_cache_init(); + /* + * page_owner must be initialized after buddy is ready, and also after + * slab is ready so that stack_depot_init() works properly + */ + page_ext_init_flatmem_late(); kmemleak_init(); pgtable_init(); debug_objects_mem_init(); diff --git a/ipc/util.c b/ipc/util.c index fa2d86ef3fb8..a2208d0f26b2 100644 --- a/ipc/util.c +++ b/ipc/util.c @@ -894,7 +894,7 @@ static int sysvipc_proc_open(struct inode *inode, struct file *file) if (!iter) return -ENOMEM; - iter->iface = PDE_DATA(inode); + iter->iface = pde_data(inode); iter->ns = get_ipc_ns(current->nsproxy->ipc_ns); iter->pid_ns = get_pid_ns(task_active_pid_ns(current)); diff --git a/kernel/hung_task.c b/kernel/hung_task.c index 9888e2bc8c76..52501e5f7655 100644 --- a/kernel/hung_task.c +++ b/kernel/hung_task.c @@ -63,7 +63,9 @@ static struct task_struct *watchdog_task; * Should we dump all CPUs backtraces in a hung task event? * Defaults to 0, can be changed via sysctl. */ -unsigned int __read_mostly sysctl_hung_task_all_cpu_backtrace; +static unsigned int __read_mostly sysctl_hung_task_all_cpu_backtrace; +#else +#define sysctl_hung_task_all_cpu_backtrace 0 #endif /* CONFIG_SMP */ /* @@ -222,11 +224,13 @@ static long hung_timeout_jiffies(unsigned long last_checked, MAX_SCHEDULE_TIMEOUT; } +#ifdef CONFIG_SYSCTL /* * Process updating of timeout sysctl */ -int proc_dohung_task_timeout_secs(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos) +static int proc_dohung_task_timeout_secs(struct ctl_table *table, int write, + void __user *buffer, + size_t *lenp, loff_t *ppos) { int ret; @@ -241,6 +245,76 @@ int proc_dohung_task_timeout_secs(struct ctl_table *table, int write, return ret; } +/* + * This is needed for proc_doulongvec_minmax of sysctl_hung_task_timeout_secs + * and hung_task_check_interval_secs + */ +static const unsigned long hung_task_timeout_max = (LONG_MAX / HZ); +static struct ctl_table hung_task_sysctls[] = { +#ifdef CONFIG_SMP + { + .procname = "hung_task_all_cpu_backtrace", + .data = &sysctl_hung_task_all_cpu_backtrace, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, +#endif /* CONFIG_SMP */ + { + .procname = "hung_task_panic", + .data = &sysctl_hung_task_panic, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, + { + .procname = "hung_task_check_count", + .data = &sysctl_hung_task_check_count, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + }, + { + .procname = "hung_task_timeout_secs", + .data = &sysctl_hung_task_timeout_secs, + .maxlen = sizeof(unsigned long), + .mode = 0644, + .proc_handler = proc_dohung_task_timeout_secs, + .extra2 = (void *)&hung_task_timeout_max, + }, + { + .procname = "hung_task_check_interval_secs", + .data = &sysctl_hung_task_check_interval_secs, + .maxlen = sizeof(unsigned long), + .mode = 0644, + .proc_handler = proc_dohung_task_timeout_secs, + .extra2 = (void *)&hung_task_timeout_max, + }, + { + .procname = "hung_task_warnings", + .data = &sysctl_hung_task_warnings, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_NEG_ONE, + }, + {} +}; + +static void __init hung_task_sysctl_init(void) +{ + register_sysctl_init("kernel", hung_task_sysctls); +} +#else +#define hung_task_sysctl_init() do { } while (0) +#endif /* CONFIG_SYSCTL */ + + static atomic_t reset_hung_task = ATOMIC_INIT(0); void reset_hung_task_detector(void) @@ -310,6 +384,7 @@ static int __init hung_task_init(void) pm_notifier(hungtask_pm_notify, 0); watchdog_task = kthread_run(watchdog, NULL, "khungtaskd"); + hung_task_sysctl_init(); return 0; } diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c index ee595ec09778..623b8136e9af 100644 --- a/kernel/irq/proc.c +++ b/kernel/irq/proc.c @@ -137,7 +137,7 @@ static inline int irq_select_affinity_usr(unsigned int irq) static ssize_t write_irq_affinity(int type, struct file *file, const char __user *buffer, size_t count, loff_t *pos) { - unsigned int irq = (int)(long)PDE_DATA(file_inode(file)); + unsigned int irq = (int)(long)pde_data(file_inode(file)); cpumask_var_t new_value; int err; @@ -190,12 +190,12 @@ static ssize_t irq_affinity_list_proc_write(struct file *file, static int irq_affinity_proc_open(struct inode *inode, struct file *file) { - return single_open(file, irq_affinity_proc_show, PDE_DATA(inode)); + return single_open(file, irq_affinity_proc_show, pde_data(inode)); } static int irq_affinity_list_proc_open(struct inode *inode, struct file *file) { - return single_open(file, irq_affinity_list_proc_show, PDE_DATA(inode)); + return single_open(file, irq_affinity_list_proc_show, pde_data(inode)); } static const struct proc_ops irq_affinity_proc_ops = { @@ -265,7 +265,7 @@ out: static int default_affinity_open(struct inode *inode, struct file *file) { - return single_open(file, default_affinity_show, PDE_DATA(inode)); + return single_open(file, default_affinity_show, pde_data(inode)); } static const struct proc_ops default_affinity_proc_ops = { diff --git a/kernel/kprobes.c b/kernel/kprobes.c index 21eccc961bba..94cab8c9ce56 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -48,6 +48,9 @@ #define KPROBE_HASH_BITS 6 #define KPROBE_TABLE_SIZE (1 << KPROBE_HASH_BITS) +#if !defined(CONFIG_OPTPROBES) || !defined(CONFIG_SYSCTL) +#define kprobe_sysctls_init() do { } while (0) +#endif static int kprobes_initialized; /* kprobe_table can be accessed by @@ -938,10 +941,10 @@ static void unoptimize_all_kprobes(void) } static DEFINE_MUTEX(kprobe_sysctl_mutex); -int sysctl_kprobes_optimization; -int proc_kprobes_optimization_handler(struct ctl_table *table, int write, - void *buffer, size_t *length, - loff_t *ppos) +static int sysctl_kprobes_optimization; +static int proc_kprobes_optimization_handler(struct ctl_table *table, + int write, void *buffer, + size_t *length, loff_t *ppos) { int ret; @@ -957,6 +960,24 @@ int proc_kprobes_optimization_handler(struct ctl_table *table, int write, return ret; } + +static struct ctl_table kprobe_sysctls[] = { + { + .procname = "kprobes-optimization", + .data = &sysctl_kprobes_optimization, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_kprobes_optimization_handler, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, + {} +}; + +static void __init kprobe_sysctls_init(void) +{ + register_sysctl_init("debug", kprobe_sysctls); +} #endif /* CONFIG_SYSCTL */ /* Put a breakpoint for a probe. */ @@ -2584,6 +2605,7 @@ static int __init init_kprobes(void) err = register_module_notifier(&kprobe_module_nb); kprobes_initialized = (err == 0); + kprobe_sysctls_init(); return err; } early_initcall(init_kprobes); diff --git a/kernel/locking/spinlock.c b/kernel/locking/spinlock.c index b562f9289372..7f49baaa4979 100644 --- a/kernel/locking/spinlock.c +++ b/kernel/locking/spinlock.c @@ -300,6 +300,16 @@ void __lockfunc _raw_write_lock(rwlock_t *lock) __raw_write_lock(lock); } EXPORT_SYMBOL(_raw_write_lock); + +#ifndef CONFIG_DEBUG_LOCK_ALLOC +#define __raw_write_lock_nested(lock, subclass) __raw_write_lock(((void)(subclass), (lock))) +#endif + +void __lockfunc _raw_write_lock_nested(rwlock_t *lock, int subclass) +{ + __raw_write_lock_nested(lock, subclass); +} +EXPORT_SYMBOL(_raw_write_lock_nested); #endif #ifndef CONFIG_INLINE_WRITE_LOCK_IRQSAVE diff --git a/kernel/locking/spinlock_rt.c b/kernel/locking/spinlock_rt.c index 9e396a09fe0f..48a19ed8486d 100644 --- a/kernel/locking/spinlock_rt.c +++ b/kernel/locking/spinlock_rt.c @@ -239,6 +239,18 @@ void __sched rt_write_lock(rwlock_t *rwlock) } EXPORT_SYMBOL(rt_write_lock); +#ifdef CONFIG_DEBUG_LOCK_ALLOC +void __sched rt_write_lock_nested(rwlock_t *rwlock, int subclass) +{ + rtlock_might_resched(); + rwlock_acquire(&rwlock->dep_map, subclass, 0, _RET_IP_); + rwbase_write_lock(&rwlock->rwbase, TASK_RTLOCK_WAIT); + rcu_read_lock(); + migrate_disable(); +} +EXPORT_SYMBOL(rt_write_lock_nested); +#endif + void __sched rt_read_unlock(rwlock_t *rwlock) { rwlock_release(&rwlock->dep_map, _RET_IP_); diff --git a/kernel/printk/Makefile b/kernel/printk/Makefile index d118739874c0..f5b388e810b9 100644 --- a/kernel/printk/Makefile +++ b/kernel/printk/Makefile @@ -2,5 +2,8 @@ obj-y = printk.o obj-$(CONFIG_PRINTK) += printk_safe.o obj-$(CONFIG_A11Y_BRAILLE_CONSOLE) += braille.o -obj-$(CONFIG_PRINTK) += printk_ringbuffer.o obj-$(CONFIG_PRINTK_INDEX) += index.o + +obj-$(CONFIG_PRINTK) += printk_support.o +printk_support-y := printk_ringbuffer.o +printk_support-$(CONFIG_SYSCTL) += sysctl.o diff --git a/kernel/printk/internal.h b/kernel/printk/internal.h index 9f3ed2fdb721..d947ca6c84f9 100644 --- a/kernel/printk/internal.h +++ b/kernel/printk/internal.h @@ -4,6 +4,14 @@ */ #include <linux/percpu.h> +#if defined(CONFIG_PRINTK) && defined(CONFIG_SYSCTL) +void __init printk_sysctl_init(void); +int devkmsg_sysctl_set_loglvl(struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos); +#else +#define printk_sysctl_init() do { } while (0) +#endif + #ifdef CONFIG_PRINTK /* Flags for a single printk record. */ diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index 155229f0cf0f..82abfaf3c2aa 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -171,7 +171,7 @@ static int __init control_devkmsg(char *str) __setup("printk.devkmsg=", control_devkmsg); char devkmsg_log_str[DEVKMSG_STR_MAX_SIZE] = "ratelimit"; - +#if defined(CONFIG_PRINTK) && defined(CONFIG_SYSCTL) int devkmsg_sysctl_set_loglvl(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { @@ -210,6 +210,7 @@ int devkmsg_sysctl_set_loglvl(struct ctl_table *table, int write, return 0; } +#endif /* CONFIG_PRINTK && CONFIG_SYSCTL */ /* Number of registered extended console drivers. */ static int nr_ext_console_drivers; @@ -3211,6 +3212,7 @@ static int __init printk_late_init(void) ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "printk:online", console_cpu_notify, NULL); WARN_ON(ret < 0); + printk_sysctl_init(); return 0; } late_initcall(printk_late_init); diff --git a/kernel/printk/sysctl.c b/kernel/printk/sysctl.c new file mode 100644 index 000000000000..653ae04aab7f --- /dev/null +++ b/kernel/printk/sysctl.c @@ -0,0 +1,85 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * sysctl.c: General linux system control interface + */ + +#include <linux/sysctl.h> +#include <linux/printk.h> +#include <linux/capability.h> +#include <linux/ratelimit.h> +#include "internal.h" + +static const int ten_thousand = 10000; + +static int proc_dointvec_minmax_sysadmin(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + if (write && !capable(CAP_SYS_ADMIN)) + return -EPERM; + + return proc_dointvec_minmax(table, write, buffer, lenp, ppos); +} + +static struct ctl_table printk_sysctls[] = { + { + .procname = "printk", + .data = &console_loglevel, + .maxlen = 4*sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .procname = "printk_ratelimit", + .data = &printk_ratelimit_state.interval, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + }, + { + .procname = "printk_ratelimit_burst", + .data = &printk_ratelimit_state.burst, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .procname = "printk_delay", + .data = &printk_delay_msec, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = (void *)&ten_thousand, + }, + { + .procname = "printk_devkmsg", + .data = devkmsg_log_str, + .maxlen = DEVKMSG_STR_MAX_SIZE, + .mode = 0644, + .proc_handler = devkmsg_sysctl_set_loglvl, + }, + { + .procname = "dmesg_restrict", + .data = &dmesg_restrict, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax_sysadmin, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, + { + .procname = "kptr_restrict", + .data = &kptr_restrict, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax_sysadmin, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_TWO, + }, + {} +}; + +void __init printk_sysctl_init(void) +{ + register_sysctl_init("kernel", printk_sysctls); +} diff --git a/kernel/resource.c b/kernel/resource.c index 5ad3eba619ba..9c08d6e9eef2 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -99,7 +99,7 @@ enum { MAX_IORES_LEVEL = 5 }; static void *r_start(struct seq_file *m, loff_t *pos) __acquires(resource_lock) { - struct resource *p = PDE_DATA(file_inode(m->file)); + struct resource *p = pde_data(file_inode(m->file)); loff_t l = 0; read_lock(&resource_lock); for (p = p->child; p && l < *pos; p = r_next(m, p, &l)) @@ -115,7 +115,7 @@ static void r_stop(struct seq_file *m, void *v) static int r_show(struct seq_file *m, void *v) { - struct resource *root = PDE_DATA(file_inode(m->file)); + struct resource *root = pde_data(file_inode(m->file)); struct resource *r = v, *p; unsigned long long start, end; int width = root->end < 0x10000 ? 4 : 8; diff --git a/kernel/stackleak.c b/kernel/stackleak.c index ce161a8e8d97..66b8af394e58 100644 --- a/kernel/stackleak.c +++ b/kernel/stackleak.c @@ -16,11 +16,13 @@ #ifdef CONFIG_STACKLEAK_RUNTIME_DISABLE #include <linux/jump_label.h> #include <linux/sysctl.h> +#include <linux/init.h> static DEFINE_STATIC_KEY_FALSE(stack_erasing_bypass); -int stack_erasing_sysctl(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos) +#ifdef CONFIG_SYSCTL +static int stack_erasing_sysctl(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) { int ret = 0; int state = !static_branch_unlikely(&stack_erasing_bypass); @@ -42,6 +44,26 @@ int stack_erasing_sysctl(struct ctl_table *table, int write, state ? "enabled" : "disabled"); return ret; } +static struct ctl_table stackleak_sysctls[] = { + { + .procname = "stack_erasing", + .data = NULL, + .maxlen = sizeof(int), + .mode = 0600, + .proc_handler = stack_erasing_sysctl, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, + {} +}; + +static int __init stackleak_sysctls_init(void) +{ + register_sysctl_init("kernel", stackleak_sysctls); + return 0; +} +late_initcall(stackleak_sysctls_init); +#endif /* CONFIG_SYSCTL */ #define skip_erasing() static_branch_unlikely(&stack_erasing_bypass) #else diff --git a/kernel/sysctl.c b/kernel/sysctl.c index ef77be575d87..5ae443b2882e 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -20,7 +20,6 @@ */ #include <linux/module.h> -#include <linux/aio.h> #include <linux/mm.h> #include <linux/swap.h> #include <linux/slab.h> @@ -50,7 +49,6 @@ #include <linux/times.h> #include <linux/limits.h> #include <linux/dcache.h> -#include <linux/dnotify.h> #include <linux/syscalls.h> #include <linux/vmstat.h> #include <linux/nfs_fs.h> @@ -58,19 +56,15 @@ #include <linux/reboot.h> #include <linux/ftrace.h> #include <linux/perf_event.h> -#include <linux/kprobes.h> -#include <linux/pipe_fs_i.h> #include <linux/oom.h> #include <linux/kmod.h> #include <linux/capability.h> #include <linux/binfmts.h> #include <linux/sched/sysctl.h> -#include <linux/sched/coredump.h> #include <linux/kexec.h> #include <linux/bpf.h> #include <linux/mount.h> #include <linux/userfaultfd_k.h> -#include <linux/coredump.h> #include <linux/latencytop.h> #include <linux/pid.h> #include <linux/delayacct.h> @@ -97,65 +91,21 @@ #if defined(CONFIG_PROVE_LOCKING) || defined(CONFIG_LOCK_STAT) #include <linux/lockdep.h> #endif -#ifdef CONFIG_CHR_DEV_SG -#include <scsi/sg.h> -#endif -#ifdef CONFIG_STACKLEAK_RUNTIME_DISABLE -#include <linux/stackleak.h> -#endif -#ifdef CONFIG_LOCKUP_DETECTOR -#include <linux/nmi.h> -#endif #if defined(CONFIG_SYSCTL) /* Constants used for minimum and maximum */ -#ifdef CONFIG_LOCKUP_DETECTOR -static int sixty = 60; -#endif - -static int __maybe_unused neg_one = -1; -static int __maybe_unused two = 2; -static int __maybe_unused four = 4; -static unsigned long zero_ul; -static unsigned long one_ul = 1; -static unsigned long long_max = LONG_MAX; -static int one_hundred = 100; -static int two_hundred = 200; -static int one_thousand = 1000; -static int three_thousand = 3000; -#ifdef CONFIG_PRINTK -static int ten_thousand = 10000; -#endif + #ifdef CONFIG_PERF_EVENTS -static int six_hundred_forty_kb = 640 * 1024; +static const int six_hundred_forty_kb = 640 * 1024; #endif /* this is needed for the proc_doulongvec_minmax of vm_dirty_bytes */ -static unsigned long dirty_bytes_min = 2 * PAGE_SIZE; - -/* this is needed for the proc_dointvec_minmax for [fs_]overflow UID and GID */ -static int maxolduid = 65535; -static int minolduid; +static const unsigned long dirty_bytes_min = 2 * PAGE_SIZE; -static int ngroups_max = NGROUPS_MAX; +static const int ngroups_max = NGROUPS_MAX; static const int cap_last_cap = CAP_LAST_CAP; -/* - * This is needed for proc_doulongvec_minmax of sysctl_hung_task_timeout_secs - * and hung_task_check_interval_secs - */ -#ifdef CONFIG_DETECT_HUNG_TASK -static unsigned long hung_task_timeout_max = (LONG_MAX/HZ); -#endif - -#ifdef CONFIG_INOTIFY_USER -#include <linux/inotify.h> -#endif -#ifdef CONFIG_FANOTIFY -#include <linux/fanotify.h> -#endif - #ifdef CONFIG_PROC_SYSCTL /** @@ -192,8 +142,8 @@ int sysctl_legacy_va_layout; #endif #ifdef CONFIG_COMPACTION -static int min_extfrag_threshold; -static int max_extfrag_threshold = 1000; +/* min_extfrag_threshold is SYSCTL_ZERO */; +static const int max_extfrag_threshold = 1000; #endif #endif /* CONFIG_SYSCTL */ @@ -804,12 +754,12 @@ static int __do_proc_douintvec(void *tbl_data, struct ctl_table *table, return do_proc_douintvec_r(i, buffer, lenp, ppos, conv, data); } -static int do_proc_douintvec(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos, - int (*conv)(unsigned long *lvalp, - unsigned int *valp, - int write, void *data), - void *data) +int do_proc_douintvec(struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos, + int (*conv)(unsigned long *lvalp, + unsigned int *valp, + int write, void *data), + void *data) { return __do_proc_douintvec(table->data, table, write, buffer, lenp, ppos, conv, data); @@ -938,17 +888,6 @@ static int proc_taint(struct ctl_table *table, int write, return err; } -#ifdef CONFIG_PRINTK -static int proc_dointvec_minmax_sysadmin(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos) -{ - if (write && !capable(CAP_SYS_ADMIN)) - return -EPERM; - - return proc_dointvec_minmax(table, write, buffer, lenp, ppos); -} -#endif - /** * struct do_proc_dointvec_minmax_conv_param - proc_dointvec_minmax() range checking structure * @min: pointer to minimum allowable value @@ -1144,67 +1083,6 @@ int proc_dou8vec_minmax(struct ctl_table *table, int write, } EXPORT_SYMBOL_GPL(proc_dou8vec_minmax); -static int do_proc_dopipe_max_size_conv(unsigned long *lvalp, - unsigned int *valp, - int write, void *data) -{ - if (write) { - unsigned int val; - - val = round_pipe_size(*lvalp); - if (val == 0) - return -EINVAL; - - *valp = val; - } else { - unsigned int val = *valp; - *lvalp = (unsigned long) val; - } - - return 0; -} - -static int proc_dopipe_max_size(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos) -{ - return do_proc_douintvec(table, write, buffer, lenp, ppos, - do_proc_dopipe_max_size_conv, NULL); -} - -static void validate_coredump_safety(void) -{ -#ifdef CONFIG_COREDUMP - if (suid_dumpable == SUID_DUMP_ROOT && - core_pattern[0] != '/' && core_pattern[0] != '|') { - printk(KERN_WARNING -"Unsafe core_pattern used with fs.suid_dumpable=2.\n" -"Pipe handler or fully qualified core dump path required.\n" -"Set kernel.core_pattern before fs.suid_dumpable.\n" - ); - } -#endif -} - -static int proc_dointvec_minmax_coredump(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos) -{ - int error = proc_dointvec_minmax(table, write, buffer, lenp, ppos); - if (!error) - validate_coredump_safety(); - return error; -} - -#ifdef CONFIG_COREDUMP -static int proc_dostring_coredump(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos) -{ - int error = proc_dostring(table, write, buffer, lenp, ppos); - if (!error) - validate_coredump_safety(); - return error; -} -#endif - #ifdef CONFIG_MAGIC_SYSRQ static int sysrq_sysctl_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) @@ -1267,10 +1145,11 @@ static int __do_proc_doulongvec_minmax(void *data, struct ctl_table *table, err = proc_get_long(&p, &left, &val, &neg, proc_wspace_sep, sizeof(proc_wspace_sep), NULL); - if (err) + if (err || neg) { + err = -EINVAL; break; - if (neg) - continue; + } + val = convmul * val / convdiv; if ((min && val < *min) || (max && val > *max)) { err = -EINVAL; @@ -1928,29 +1807,6 @@ static struct ctl_table kern_table[] = { .mode = 0644, .proc_handler = proc_dointvec, }, -#ifdef CONFIG_COREDUMP - { - .procname = "core_uses_pid", - .data = &core_uses_pid, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, - { - .procname = "core_pattern", - .data = core_pattern, - .maxlen = CORENAME_MAX_SIZE, - .mode = 0644, - .proc_handler = proc_dostring_coredump, - }, - { - .procname = "core_pipe_limit", - .data = &core_pipe_limit, - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, -#endif #ifdef CONFIG_PROC_SYSCTL { .procname = "tainted", @@ -1964,7 +1820,7 @@ static struct ctl_table kern_table[] = { .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = &neg_one, + .extra1 = SYSCTL_NEG_ONE, .extra2 = SYSCTL_ONE, }, #endif @@ -2131,15 +1987,6 @@ static struct ctl_table kern_table[] = { .proc_handler = proc_dostring, }, #endif -#ifdef CONFIG_CHR_DEV_SG - { - .procname = "sg-big-buff", - .data = &sg_big_buff, - .maxlen = sizeof (int), - .mode = 0444, - .proc_handler = proc_dointvec, - }, -#endif #ifdef CONFIG_BSD_PROCESS_ACCT { .procname = "acct", @@ -2175,30 +2022,18 @@ static struct ctl_table kern_table[] = { .proc_handler = sysctl_max_threads, }, { - .procname = "random", - .mode = 0555, - .child = random_table, - }, - { .procname = "usermodehelper", .mode = 0555, .child = usermodehelper_table, }, -#ifdef CONFIG_FW_LOADER_USER_HELPER - { - .procname = "firmware_config", - .mode = 0555, - .child = firmware_config_table, - }, -#endif { .procname = "overflowuid", .data = &overflowuid, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = &minolduid, - .extra2 = &maxolduid, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_MAXOLDUID, }, { .procname = "overflowgid", @@ -2206,8 +2041,8 @@ static struct ctl_table kern_table[] = { .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = &minolduid, - .extra2 = &maxolduid, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_MAXOLDUID, }, #ifdef CONFIG_S390 { @@ -2252,66 +2087,9 @@ static struct ctl_table kern_table[] = { .mode = 0644, .proc_handler = proc_doulongvec_minmax, }, -#if defined CONFIG_PRINTK - { - .procname = "printk", - .data = &console_loglevel, - .maxlen = 4*sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, - { - .procname = "printk_ratelimit", - .data = &printk_ratelimit_state.interval, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, - { - .procname = "printk_ratelimit_burst", - .data = &printk_ratelimit_state.burst, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, - { - .procname = "printk_delay", - .data = &printk_delay_msec, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = SYSCTL_ZERO, - .extra2 = &ten_thousand, - }, - { - .procname = "printk_devkmsg", - .data = devkmsg_log_str, - .maxlen = DEVKMSG_STR_MAX_SIZE, - .mode = 0644, - .proc_handler = devkmsg_sysctl_set_loglvl, - }, - { - .procname = "dmesg_restrict", - .data = &dmesg_restrict, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax_sysadmin, - .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_ONE, - }, - { - .procname = "kptr_restrict", - .data = &kptr_restrict, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax_sysadmin, - .extra1 = SYSCTL_ZERO, - .extra2 = &two, - }, -#endif { .procname = "ngroups_max", - .data = &ngroups_max, + .data = (void *)&ngroups_max, .maxlen = sizeof (int), .mode = 0444, .proc_handler = proc_dointvec, @@ -2323,96 +2101,6 @@ static struct ctl_table kern_table[] = { .mode = 0444, .proc_handler = proc_dointvec, }, -#if defined(CONFIG_LOCKUP_DETECTOR) - { - .procname = "watchdog", - .data = &watchdog_user_enabled, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_watchdog, - .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_ONE, - }, - { - .procname = "watchdog_thresh", - .data = &watchdog_thresh, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_watchdog_thresh, - .extra1 = SYSCTL_ZERO, - .extra2 = &sixty, - }, - { - .procname = "nmi_watchdog", - .data = &nmi_watchdog_user_enabled, - .maxlen = sizeof(int), - .mode = NMI_WATCHDOG_SYSCTL_PERM, - .proc_handler = proc_nmi_watchdog, - .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_ONE, - }, - { - .procname = "watchdog_cpumask", - .data = &watchdog_cpumask_bits, - .maxlen = NR_CPUS, - .mode = 0644, - .proc_handler = proc_watchdog_cpumask, - }, -#ifdef CONFIG_SOFTLOCKUP_DETECTOR - { - .procname = "soft_watchdog", - .data = &soft_watchdog_user_enabled, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_soft_watchdog, - .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_ONE, - }, - { - .procname = "softlockup_panic", - .data = &softlockup_panic, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_ONE, - }, -#ifdef CONFIG_SMP - { - .procname = "softlockup_all_cpu_backtrace", - .data = &sysctl_softlockup_all_cpu_backtrace, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_ONE, - }, -#endif /* CONFIG_SMP */ -#endif -#ifdef CONFIG_HARDLOCKUP_DETECTOR - { - .procname = "hardlockup_panic", - .data = &hardlockup_panic, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_ONE, - }, -#ifdef CONFIG_SMP - { - .procname = "hardlockup_all_cpu_backtrace", - .data = &sysctl_hardlockup_all_cpu_backtrace, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_ONE, - }, -#endif /* CONFIG_SMP */ -#endif -#endif - #if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86) { .procname = "unknown_nmi_panic", @@ -2515,60 +2203,6 @@ static struct ctl_table kern_table[] = { .proc_handler = proc_dointvec, }, #endif -#ifdef CONFIG_DETECT_HUNG_TASK -#ifdef CONFIG_SMP - { - .procname = "hung_task_all_cpu_backtrace", - .data = &sysctl_hung_task_all_cpu_backtrace, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_ONE, - }, -#endif /* CONFIG_SMP */ - { - .procname = "hung_task_panic", - .data = &sysctl_hung_task_panic, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_ONE, - }, - { - .procname = "hung_task_check_count", - .data = &sysctl_hung_task_check_count, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = SYSCTL_ZERO, - }, - { - .procname = "hung_task_timeout_secs", - .data = &sysctl_hung_task_timeout_secs, - .maxlen = sizeof(unsigned long), - .mode = 0644, - .proc_handler = proc_dohung_task_timeout_secs, - .extra2 = &hung_task_timeout_max, - }, - { - .procname = "hung_task_check_interval_secs", - .data = &sysctl_hung_task_check_interval_secs, - .maxlen = sizeof(unsigned long), - .mode = 0644, - .proc_handler = proc_dohung_task_timeout_secs, - .extra2 = &hung_task_timeout_max, - }, - { - .procname = "hung_task_warnings", - .data = &sysctl_hung_task_warnings, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = &neg_one, - }, -#endif #ifdef CONFIG_RT_MUTEXES { .procname = "max_lock_depth", @@ -2628,7 +2262,7 @@ static struct ctl_table kern_table[] = { .mode = 0644, .proc_handler = perf_cpu_time_max_percent_handler, .extra1 = SYSCTL_ZERO, - .extra2 = &one_hundred, + .extra2 = SYSCTL_ONE_HUNDRED, }, { .procname = "perf_event_max_stack", @@ -2637,7 +2271,7 @@ static struct ctl_table kern_table[] = { .mode = 0644, .proc_handler = perf_event_max_stack_handler, .extra1 = SYSCTL_ZERO, - .extra2 = &six_hundred_forty_kb, + .extra2 = (void *)&six_hundred_forty_kb, }, { .procname = "perf_event_max_contexts_per_stack", @@ -2646,7 +2280,7 @@ static struct ctl_table kern_table[] = { .mode = 0644, .proc_handler = perf_event_max_stack_handler, .extra1 = SYSCTL_ZERO, - .extra2 = &one_thousand, + .extra2 = SYSCTL_ONE_THOUSAND, }, #endif { @@ -2677,7 +2311,7 @@ static struct ctl_table kern_table[] = { .mode = 0644, .proc_handler = bpf_unpriv_handler, .extra1 = SYSCTL_ZERO, - .extra2 = &two, + .extra2 = SYSCTL_TWO, }, { .procname = "bpf_stats_enabled", @@ -2709,17 +2343,6 @@ static struct ctl_table kern_table[] = { .extra2 = SYSCTL_INT_MAX, }, #endif -#ifdef CONFIG_STACKLEAK_RUNTIME_DISABLE - { - .procname = "stack_erasing", - .data = NULL, - .maxlen = sizeof(int), - .mode = 0600, - .proc_handler = stack_erasing_sysctl, - .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_ONE, - }, -#endif { } }; @@ -2731,7 +2354,7 @@ static struct ctl_table vm_table[] = { .mode = 0644, .proc_handler = overcommit_policy_handler, .extra1 = SYSCTL_ZERO, - .extra2 = &two, + .extra2 = SYSCTL_TWO, }, { .procname = "panic_on_oom", @@ -2740,7 +2363,7 @@ static struct ctl_table vm_table[] = { .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, - .extra2 = &two, + .extra2 = SYSCTL_TWO, }, { .procname = "oom_kill_allocating_task", @@ -2785,7 +2408,7 @@ static struct ctl_table vm_table[] = { .mode = 0644, .proc_handler = dirty_background_ratio_handler, .extra1 = SYSCTL_ZERO, - .extra2 = &one_hundred, + .extra2 = SYSCTL_ONE_HUNDRED, }, { .procname = "dirty_background_bytes", @@ -2793,7 +2416,7 @@ static struct ctl_table vm_table[] = { .maxlen = sizeof(dirty_background_bytes), .mode = 0644, .proc_handler = dirty_background_bytes_handler, - .extra1 = &one_ul, + .extra1 = SYSCTL_LONG_ONE, }, { .procname = "dirty_ratio", @@ -2802,7 +2425,7 @@ static struct ctl_table vm_table[] = { .mode = 0644, .proc_handler = dirty_ratio_handler, .extra1 = SYSCTL_ZERO, - .extra2 = &one_hundred, + .extra2 = SYSCTL_ONE_HUNDRED, }, { .procname = "dirty_bytes", @@ -2810,7 +2433,7 @@ static struct ctl_table vm_table[] = { .maxlen = sizeof(vm_dirty_bytes), .mode = 0644, .proc_handler = dirty_bytes_handler, - .extra1 = &dirty_bytes_min, + .extra1 = (void *)&dirty_bytes_min, }, { .procname = "dirty_writeback_centisecs", @@ -2842,7 +2465,7 @@ static struct ctl_table vm_table[] = { .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, - .extra2 = &two_hundred, + .extra2 = SYSCTL_TWO_HUNDRED, }, #ifdef CONFIG_HUGETLB_PAGE { @@ -2899,7 +2522,7 @@ static struct ctl_table vm_table[] = { .mode = 0200, .proc_handler = drop_caches_sysctl_handler, .extra1 = SYSCTL_ONE, - .extra2 = &four, + .extra2 = SYSCTL_FOUR, }, #ifdef CONFIG_COMPACTION { @@ -2916,7 +2539,7 @@ static struct ctl_table vm_table[] = { .mode = 0644, .proc_handler = compaction_proactiveness_sysctl_handler, .extra1 = SYSCTL_ZERO, - .extra2 = &one_hundred, + .extra2 = SYSCTL_ONE_HUNDRED, }, { .procname = "extfrag_threshold", @@ -2924,8 +2547,8 @@ static struct ctl_table vm_table[] = { .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = &min_extfrag_threshold, - .extra2 = &max_extfrag_threshold, + .extra1 = SYSCTL_ZERO, + .extra2 = (void *)&max_extfrag_threshold, }, { .procname = "compact_unevictable_allowed", @@ -2961,7 +2584,7 @@ static struct ctl_table vm_table[] = { .mode = 0644, .proc_handler = watermark_scale_factor_sysctl_handler, .extra1 = SYSCTL_ONE, - .extra2 = &three_thousand, + .extra2 = SYSCTL_THREE_THOUSAND, }, { .procname = "percpu_pagelist_high_fraction", @@ -3040,7 +2663,7 @@ static struct ctl_table vm_table[] = { .mode = 0644, .proc_handler = sysctl_min_unmapped_ratio_sysctl_handler, .extra1 = SYSCTL_ZERO, - .extra2 = &one_hundred, + .extra2 = SYSCTL_ONE_HUNDRED, }, { .procname = "min_slab_ratio", @@ -3049,7 +2672,7 @@ static struct ctl_table vm_table[] = { .mode = 0644, .proc_handler = sysctl_min_slab_ratio_sysctl_handler, .extra1 = SYSCTL_ZERO, - .extra2 = &one_hundred, + .extra2 = SYSCTL_ONE_HUNDRED, }, #endif #ifdef CONFIG_SMP @@ -3183,221 +2806,6 @@ static struct ctl_table vm_table[] = { { } }; -static struct ctl_table fs_table[] = { - { - .procname = "inode-nr", - .data = &inodes_stat, - .maxlen = 2*sizeof(long), - .mode = 0444, - .proc_handler = proc_nr_inodes, - }, - { - .procname = "inode-state", - .data = &inodes_stat, - .maxlen = 7*sizeof(long), - .mode = 0444, - .proc_handler = proc_nr_inodes, - }, - { - .procname = "file-nr", - .data = &files_stat, - .maxlen = sizeof(files_stat), - .mode = 0444, - .proc_handler = proc_nr_files, - }, - { - .procname = "file-max", - .data = &files_stat.max_files, - .maxlen = sizeof(files_stat.max_files), - .mode = 0644, - .proc_handler = proc_doulongvec_minmax, - .extra1 = &zero_ul, - .extra2 = &long_max, - }, - { - .procname = "nr_open", - .data = &sysctl_nr_open, - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = &sysctl_nr_open_min, - .extra2 = &sysctl_nr_open_max, - }, - { - .procname = "dentry-state", - .data = &dentry_stat, - .maxlen = 6*sizeof(long), - .mode = 0444, - .proc_handler = proc_nr_dentry, - }, - { - .procname = "overflowuid", - .data = &fs_overflowuid, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = &minolduid, - .extra2 = &maxolduid, - }, - { - .procname = "overflowgid", - .data = &fs_overflowgid, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = &minolduid, - .extra2 = &maxolduid, - }, -#ifdef CONFIG_FILE_LOCKING - { - .procname = "leases-enable", - .data = &leases_enable, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, -#endif -#ifdef CONFIG_DNOTIFY - { - .procname = "dir-notify-enable", - .data = &dir_notify_enable, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, -#endif -#ifdef CONFIG_MMU -#ifdef CONFIG_FILE_LOCKING - { - .procname = "lease-break-time", - .data = &lease_break_time, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, -#endif -#ifdef CONFIG_AIO - { - .procname = "aio-nr", - .data = &aio_nr, - .maxlen = sizeof(aio_nr), - .mode = 0444, - .proc_handler = proc_doulongvec_minmax, - }, - { - .procname = "aio-max-nr", - .data = &aio_max_nr, - .maxlen = sizeof(aio_max_nr), - .mode = 0644, - .proc_handler = proc_doulongvec_minmax, - }, -#endif /* CONFIG_AIO */ -#ifdef CONFIG_INOTIFY_USER - { - .procname = "inotify", - .mode = 0555, - .child = inotify_table, - }, -#endif -#ifdef CONFIG_FANOTIFY - { - .procname = "fanotify", - .mode = 0555, - .child = fanotify_table, - }, -#endif -#ifdef CONFIG_EPOLL - { - .procname = "epoll", - .mode = 0555, - .child = epoll_table, - }, -#endif -#endif - { - .procname = "protected_symlinks", - .data = &sysctl_protected_symlinks, - .maxlen = sizeof(int), - .mode = 0600, - .proc_handler = proc_dointvec_minmax, - .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_ONE, - }, - { - .procname = "protected_hardlinks", - .data = &sysctl_protected_hardlinks, - .maxlen = sizeof(int), - .mode = 0600, - .proc_handler = proc_dointvec_minmax, - .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_ONE, - }, - { - .procname = "protected_fifos", - .data = &sysctl_protected_fifos, - .maxlen = sizeof(int), - .mode = 0600, - .proc_handler = proc_dointvec_minmax, - .extra1 = SYSCTL_ZERO, - .extra2 = &two, - }, - { - .procname = "protected_regular", - .data = &sysctl_protected_regular, - .maxlen = sizeof(int), - .mode = 0600, - .proc_handler = proc_dointvec_minmax, - .extra1 = SYSCTL_ZERO, - .extra2 = &two, - }, - { - .procname = "suid_dumpable", - .data = &suid_dumpable, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax_coredump, - .extra1 = SYSCTL_ZERO, - .extra2 = &two, - }, -#if defined(CONFIG_BINFMT_MISC) || defined(CONFIG_BINFMT_MISC_MODULE) - { - .procname = "binfmt_misc", - .mode = 0555, - .child = sysctl_mount_point, - }, -#endif - { - .procname = "pipe-max-size", - .data = &pipe_max_size, - .maxlen = sizeof(pipe_max_size), - .mode = 0644, - .proc_handler = proc_dopipe_max_size, - }, - { - .procname = "pipe-user-pages-hard", - .data = &pipe_user_pages_hard, - .maxlen = sizeof(pipe_user_pages_hard), - .mode = 0644, - .proc_handler = proc_doulongvec_minmax, - }, - { - .procname = "pipe-user-pages-soft", - .data = &pipe_user_pages_soft, - .maxlen = sizeof(pipe_user_pages_soft), - .mode = 0644, - .proc_handler = proc_doulongvec_minmax, - }, - { - .procname = "mount-max", - .data = &sysctl_mount_max, - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = SYSCTL_ONE, - }, - { } -}; - static struct ctl_table debug_table[] = { #ifdef CONFIG_SYSCTL_EXCEPTION_TRACE { @@ -3408,17 +2816,6 @@ static struct ctl_table debug_table[] = { .proc_handler = proc_dointvec }, #endif -#if defined(CONFIG_OPTPROBES) - { - .procname = "kprobes-optimization", - .data = &sysctl_kprobes_optimization, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_kprobes_optimization_handler, - .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_ONE, - }, -#endif { } }; @@ -3426,41 +2823,18 @@ static struct ctl_table dev_table[] = { { } }; -static struct ctl_table sysctl_base_table[] = { - { - .procname = "kernel", - .mode = 0555, - .child = kern_table, - }, - { - .procname = "vm", - .mode = 0555, - .child = vm_table, - }, - { - .procname = "fs", - .mode = 0555, - .child = fs_table, - }, - { - .procname = "debug", - .mode = 0555, - .child = debug_table, - }, - { - .procname = "dev", - .mode = 0555, - .child = dev_table, - }, - { } -}; +DECLARE_SYSCTL_BASE(kernel, kern_table); +DECLARE_SYSCTL_BASE(vm, vm_table); +DECLARE_SYSCTL_BASE(debug, debug_table); +DECLARE_SYSCTL_BASE(dev, dev_table); -int __init sysctl_init(void) +int __init sysctl_init_bases(void) { - struct ctl_table_header *hdr; + register_sysctl_base(kernel); + register_sysctl_base(vm); + register_sysctl_base(debug); + register_sysctl_base(dev); - hdr = register_sysctl_table(sysctl_base_table); - kmemleak_not_leak(hdr); return 0; } #endif /* CONFIG_SYSCTL */ diff --git a/kernel/watchdog.c b/kernel/watchdog.c index ad912511a0c0..99afb88d2e85 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -740,6 +740,106 @@ int proc_watchdog_cpumask(struct ctl_table *table, int write, mutex_unlock(&watchdog_mutex); return err; } + +static const int sixty = 60; + +static struct ctl_table watchdog_sysctls[] = { + { + .procname = "watchdog", + .data = &watchdog_user_enabled, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_watchdog, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, + { + .procname = "watchdog_thresh", + .data = &watchdog_thresh, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_watchdog_thresh, + .extra1 = SYSCTL_ZERO, + .extra2 = (void *)&sixty, + }, + { + .procname = "nmi_watchdog", + .data = &nmi_watchdog_user_enabled, + .maxlen = sizeof(int), + .mode = NMI_WATCHDOG_SYSCTL_PERM, + .proc_handler = proc_nmi_watchdog, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, + { + .procname = "watchdog_cpumask", + .data = &watchdog_cpumask_bits, + .maxlen = NR_CPUS, + .mode = 0644, + .proc_handler = proc_watchdog_cpumask, + }, +#ifdef CONFIG_SOFTLOCKUP_DETECTOR + { + .procname = "soft_watchdog", + .data = &soft_watchdog_user_enabled, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_soft_watchdog, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, + { + .procname = "softlockup_panic", + .data = &softlockup_panic, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, +#ifdef CONFIG_SMP + { + .procname = "softlockup_all_cpu_backtrace", + .data = &sysctl_softlockup_all_cpu_backtrace, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, +#endif /* CONFIG_SMP */ +#endif +#ifdef CONFIG_HARDLOCKUP_DETECTOR + { + .procname = "hardlockup_panic", + .data = &hardlockup_panic, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, +#ifdef CONFIG_SMP + { + .procname = "hardlockup_all_cpu_backtrace", + .data = &sysctl_hardlockup_all_cpu_backtrace, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, +#endif /* CONFIG_SMP */ +#endif + {} +}; + +static void __init watchdog_sysctl_init(void) +{ + register_sysctl_init("kernel", watchdog_sysctls); +} +#else +#define watchdog_sysctl_init() do { } while (0) #endif /* CONFIG_SYSCTL */ void __init lockup_detector_init(void) @@ -753,4 +853,5 @@ void __init lockup_detector_init(void) if (!watchdog_nmi_probe()) nmi_watchdog_available = true; lockup_detector_setup(); + watchdog_sysctl_init(); } diff --git a/lib/Kconfig b/lib/Kconfig index c20b68ad2bc3..51c368a50b16 100644 --- a/lib/Kconfig +++ b/lib/Kconfig @@ -673,6 +673,10 @@ config STACKDEPOT bool select STACKTRACE +config STACKDEPOT_ALWAYS_INIT + bool + select STACKDEPOT + config STACK_HASH_ORDER int "stack depot hash size (12 => 4KB, 20 => 1024KB)" range 12 20 diff --git a/lib/Kconfig.kasan b/lib/Kconfig.kasan index cdc842d090db..879757b6dd14 100644 --- a/lib/Kconfig.kasan +++ b/lib/Kconfig.kasan @@ -38,7 +38,7 @@ menuconfig KASAN CC_HAS_WORKING_NOSANITIZE_ADDRESS) || \ HAVE_ARCH_KASAN_HW_TAGS depends on (SLUB && SYSFS) || (SLAB && !DEBUG_SLAB) - select STACKDEPOT + select STACKDEPOT_ALWAYS_INIT help Enables KASAN (KernelAddressSANitizer) - runtime memory debugger, designed to find out-of-bounds accesses and use-after-free bugs. diff --git a/lib/stackdepot.c b/lib/stackdepot.c index b437ae79aca1..bf5ba9af0500 100644 --- a/lib/stackdepot.c +++ b/lib/stackdepot.c @@ -23,6 +23,7 @@ #include <linux/jhash.h> #include <linux/kernel.h> #include <linux/mm.h> +#include <linux/mutex.h> #include <linux/percpu.h> #include <linux/printk.h> #include <linux/slab.h> @@ -161,18 +162,40 @@ static int __init is_stack_depot_disabled(char *str) } early_param("stack_depot_disable", is_stack_depot_disabled); -int __init stack_depot_init(void) +/* + * __ref because of memblock_alloc(), which will not be actually called after + * the __init code is gone, because at that point slab_is_available() is true + */ +__ref int stack_depot_init(void) { - if (!stack_depot_disable) { + static DEFINE_MUTEX(stack_depot_init_mutex); + + mutex_lock(&stack_depot_init_mutex); + if (!stack_depot_disable && !stack_table) { size_t size = (STACK_HASH_SIZE * sizeof(struct stack_record *)); int i; - stack_table = memblock_alloc(size, size); - for (i = 0; i < STACK_HASH_SIZE; i++) - stack_table[i] = NULL; + if (slab_is_available()) { + pr_info("Stack Depot allocating hash table with kvmalloc\n"); + stack_table = kvmalloc(size, GFP_KERNEL); + } else { + pr_info("Stack Depot allocating hash table with memblock_alloc\n"); + stack_table = memblock_alloc(size, SMP_CACHE_BYTES); + } + if (stack_table) { + for (i = 0; i < STACK_HASH_SIZE; i++) + stack_table[i] = NULL; + } else { + pr_err("Stack Depot hash table allocation failed, disabling\n"); + stack_depot_disable = true; + mutex_unlock(&stack_depot_init_mutex); + return -ENOMEM; + } } + mutex_unlock(&stack_depot_init_mutex); return 0; } +EXPORT_SYMBOL_GPL(stack_depot_init); /* Calculate hash for a stack */ static inline u32 hash_stack(unsigned long *entries, unsigned int size) @@ -305,6 +328,9 @@ EXPORT_SYMBOL_GPL(stack_depot_fetch); * (allocates using GFP flags of @alloc_flags). If @can_alloc is %false, avoids * any allocations and will fail if no space is left to store the stack trace. * + * If the stack trace in @entries is from an interrupt, only the portion up to + * interrupt entry is saved. + * * Context: Any context, but setting @can_alloc to %false is required if * alloc_pages() cannot be used from the current context. Currently * this is the case from contexts where neither %GFP_ATOMIC nor @@ -323,6 +349,16 @@ depot_stack_handle_t __stack_depot_save(unsigned long *entries, unsigned long flags; u32 hash; + /* + * If this stack trace is from an interrupt, including anything before + * interrupt entry usually leads to unbounded stackdepot growth. + * + * Because use of filter_irq_stacks() is a requirement to ensure + * stackdepot can efficiently deduplicate interrupt stacks, always + * filter_irq_stacks() to simplify all callers' use of stackdepot. + */ + nr_entries = filter_irq_stacks(entries, nr_entries); + if (unlikely(nr_entries == 0) || stack_depot_disable) goto fast_exit; diff --git a/lib/test_sysctl.c b/lib/test_sysctl.c index 3750323973f4..a5a3d6c27e1f 100644 --- a/lib/test_sysctl.c +++ b/lib/test_sysctl.c @@ -128,26 +128,6 @@ static struct ctl_table test_table[] = { { } }; -static struct ctl_table test_sysctl_table[] = { - { - .procname = "test_sysctl", - .maxlen = 0, - .mode = 0555, - .child = test_table, - }, - { } -}; - -static struct ctl_table test_sysctl_root_table[] = { - { - .procname = "debug", - .maxlen = 0, - .mode = 0555, - .child = test_sysctl_table, - }, - { } -}; - static struct ctl_table_header *test_sysctl_header; static int __init test_sysctl_init(void) @@ -155,7 +135,7 @@ static int __init test_sysctl_init(void) test_data.bitmap_0001 = kzalloc(SYSCTL_TEST_BITMAP_SIZE/8, GFP_KERNEL); if (!test_data.bitmap_0001) return -ENOMEM; - test_sysctl_header = register_sysctl_table(test_sysctl_root_table); + test_sysctl_header = register_sysctl("debug/test_sysctl", test_table); if (!test_sysctl_header) { kfree(test_data.bitmap_0001); return -ENOMEM; diff --git a/mm/Kconfig b/mm/Kconfig index a99bd499ef51..3326ee3903f3 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -444,43 +444,8 @@ config USE_PERCPU_NUMA_NODE_ID config HAVE_SETUP_PER_CPU_AREA bool -config CLEANCACHE - bool "Enable cleancache driver to cache clean pages if tmem is present" - help - Cleancache can be thought of as a page-granularity victim cache - for clean pages that the kernel's pageframe replacement algorithm - (PFRA) would like to keep around, but can't since there isn't enough - memory. So when the PFRA "evicts" a page, it first attempts to use - cleancache code to put the data contained in that page into - "transcendent memory", memory that is not directly accessible or - addressable by the kernel and is of unknown and possibly - time-varying size. And when a cleancache-enabled - filesystem wishes to access a page in a file on disk, it first - checks cleancache to see if it already contains it; if it does, - the page is copied into the kernel and a disk access is avoided. - When a transcendent memory driver is available (such as zcache or - Xen transcendent memory), a significant I/O reduction - may be achieved. When none is available, all cleancache calls - are reduced to a single pointer-compare-against-NULL resulting - in a negligible performance hit. - - If unsure, say Y to enable cleancache - config FRONTSWAP - bool "Enable frontswap to cache swap pages if tmem is present" - depends on SWAP - help - Frontswap is so named because it can be thought of as the opposite - of a "backing" store for a swap device. The data is stored into - "transcendent memory", memory that is not directly accessible or - addressable by the kernel and is of unknown and possibly - time-varying size. When space in transcendent memory is available, - a significant swap I/O reduction may be achieved. When none is - available, all frontswap calls are reduced to a single pointer- - compare-against-NULL resulting in a negligible performance hit - and swap data is stored as normal on the matching swap device. - - If unsure, say Y to enable frontswap. + bool config CMA bool "Contiguous Memory Allocator" @@ -545,7 +510,8 @@ config MEM_SOFT_DIRTY config ZSWAP bool "Compressed cache for swap pages (EXPERIMENTAL)" - depends on FRONTSWAP && CRYPTO=y + depends on SWAP && CRYPTO=y + select FRONTSWAP select ZPOOL help A lightweight compressed cache for swap pages. It takes diff --git a/mm/Makefile b/mm/Makefile index 588d3113f3b0..70d4309c9ce3 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -104,7 +104,6 @@ obj-$(CONFIG_DEBUG_KMEMLEAK) += kmemleak.o obj-$(CONFIG_DEBUG_RODATA_TEST) += rodata_test.o obj-$(CONFIG_DEBUG_VM_PGTABLE) += debug_vm_pgtable.o obj-$(CONFIG_PAGE_OWNER) += page_owner.o -obj-$(CONFIG_CLEANCACHE) += cleancache.o obj-$(CONFIG_MEMORY_ISOLATION) += page_isolation.o obj-$(CONFIG_ZPOOL) += zpool.o obj-$(CONFIG_ZBUD) += zbud.o diff --git a/mm/cleancache.c b/mm/cleancache.c deleted file mode 100644 index db7eee9c0886..000000000000 --- a/mm/cleancache.c +++ /dev/null @@ -1,315 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Cleancache frontend - * - * This code provides the generic "frontend" layer to call a matching - * "backend" driver implementation of cleancache. See - * Documentation/vm/cleancache.rst for more information. - * - * Copyright (C) 2009-2010 Oracle Corp. All rights reserved. - * Author: Dan Magenheimer - */ - -#include <linux/module.h> -#include <linux/fs.h> -#include <linux/exportfs.h> -#include <linux/mm.h> -#include <linux/debugfs.h> -#include <linux/cleancache.h> - -/* - * cleancache_ops is set by cleancache_register_ops to contain the pointers - * to the cleancache "backend" implementation functions. - */ -static const struct cleancache_ops *cleancache_ops __read_mostly; - -/* - * Counters available via /sys/kernel/debug/cleancache (if debugfs is - * properly configured. These are for information only so are not protected - * against increment races. - */ -static u64 cleancache_succ_gets; -static u64 cleancache_failed_gets; -static u64 cleancache_puts; -static u64 cleancache_invalidates; - -static void cleancache_register_ops_sb(struct super_block *sb, void *unused) -{ - switch (sb->cleancache_poolid) { - case CLEANCACHE_NO_BACKEND: - __cleancache_init_fs(sb); - break; - case CLEANCACHE_NO_BACKEND_SHARED: - __cleancache_init_shared_fs(sb); - break; - } -} - -/* - * Register operations for cleancache. Returns 0 on success. - */ -int cleancache_register_ops(const struct cleancache_ops *ops) -{ - if (cmpxchg(&cleancache_ops, NULL, ops)) - return -EBUSY; - - /* - * A cleancache backend can be built as a module and hence loaded after - * a cleancache enabled filesystem has called cleancache_init_fs. To - * handle such a scenario, here we call ->init_fs or ->init_shared_fs - * for each active super block. To differentiate between local and - * shared filesystems, we temporarily initialize sb->cleancache_poolid - * to CLEANCACHE_NO_BACKEND or CLEANCACHE_NO_BACKEND_SHARED - * respectively in case there is no backend registered at the time - * cleancache_init_fs or cleancache_init_shared_fs is called. - * - * Since filesystems can be mounted concurrently with cleancache - * backend registration, we have to be careful to guarantee that all - * cleancache enabled filesystems that has been mounted by the time - * cleancache_register_ops is called has got and all mounted later will - * get cleancache_poolid. This is assured by the following statements - * tied together: - * - * a) iterate_supers skips only those super blocks that has started - * ->kill_sb - * - * b) if iterate_supers encounters a super block that has not finished - * ->mount yet, it waits until it is finished - * - * c) cleancache_init_fs is called from ->mount and - * cleancache_invalidate_fs is called from ->kill_sb - * - * d) we call iterate_supers after cleancache_ops has been set - * - * From a) it follows that if iterate_supers skips a super block, then - * either the super block is already dead, in which case we do not need - * to bother initializing cleancache for it, or it was mounted after we - * initiated iterate_supers. In the latter case, it must have seen - * cleancache_ops set according to d) and initialized cleancache from - * ->mount by itself according to c). This proves that we call - * ->init_fs at least once for each active super block. - * - * From b) and c) it follows that if iterate_supers encounters a super - * block that has already started ->init_fs, it will wait until ->mount - * and hence ->init_fs has finished, then check cleancache_poolid, see - * that it has already been set and therefore do nothing. This proves - * that we call ->init_fs no more than once for each super block. - * - * Combined together, the last two paragraphs prove the function - * correctness. - * - * Note that various cleancache callbacks may proceed before this - * function is called or even concurrently with it, but since - * CLEANCACHE_NO_BACKEND is negative, they will all result in a noop - * until the corresponding ->init_fs has been actually called and - * cleancache_ops has been set. - */ - iterate_supers(cleancache_register_ops_sb, NULL); - return 0; -} -EXPORT_SYMBOL(cleancache_register_ops); - -/* Called by a cleancache-enabled filesystem at time of mount */ -void __cleancache_init_fs(struct super_block *sb) -{ - int pool_id = CLEANCACHE_NO_BACKEND; - - if (cleancache_ops) { - pool_id = cleancache_ops->init_fs(PAGE_SIZE); - if (pool_id < 0) - pool_id = CLEANCACHE_NO_POOL; - } - sb->cleancache_poolid = pool_id; -} -EXPORT_SYMBOL(__cleancache_init_fs); - -/* Called by a cleancache-enabled clustered filesystem at time of mount */ -void __cleancache_init_shared_fs(struct super_block *sb) -{ - int pool_id = CLEANCACHE_NO_BACKEND_SHARED; - - if (cleancache_ops) { - pool_id = cleancache_ops->init_shared_fs(&sb->s_uuid, PAGE_SIZE); - if (pool_id < 0) - pool_id = CLEANCACHE_NO_POOL; - } - sb->cleancache_poolid = pool_id; -} -EXPORT_SYMBOL(__cleancache_init_shared_fs); - -/* - * If the filesystem uses exportable filehandles, use the filehandle as - * the key, else use the inode number. - */ -static int cleancache_get_key(struct inode *inode, - struct cleancache_filekey *key) -{ - int (*fhfn)(struct inode *, __u32 *fh, int *, struct inode *); - int len = 0, maxlen = CLEANCACHE_KEY_MAX; - struct super_block *sb = inode->i_sb; - - key->u.ino = inode->i_ino; - if (sb->s_export_op != NULL) { - fhfn = sb->s_export_op->encode_fh; - if (fhfn) { - len = (*fhfn)(inode, &key->u.fh[0], &maxlen, NULL); - if (len <= FILEID_ROOT || len == FILEID_INVALID) - return -1; - if (maxlen > CLEANCACHE_KEY_MAX) - return -1; - } - } - return 0; -} - -/* - * "Get" data from cleancache associated with the poolid/inode/index - * that were specified when the data was put to cleanache and, if - * successful, use it to fill the specified page with data and return 0. - * The pageframe is unchanged and returns -1 if the get fails. - * Page must be locked by caller. - * - * The function has two checks before any action is taken - whether - * a backend is registered and whether the sb->cleancache_poolid - * is correct. - */ -int __cleancache_get_page(struct page *page) -{ - int ret = -1; - int pool_id; - struct cleancache_filekey key = { .u.key = { 0 } }; - - if (!cleancache_ops) { - cleancache_failed_gets++; - goto out; - } - - VM_BUG_ON_PAGE(!PageLocked(page), page); - pool_id = page->mapping->host->i_sb->cleancache_poolid; - if (pool_id < 0) - goto out; - - if (cleancache_get_key(page->mapping->host, &key) < 0) - goto out; - - ret = cleancache_ops->get_page(pool_id, key, page->index, page); - if (ret == 0) - cleancache_succ_gets++; - else - cleancache_failed_gets++; -out: - return ret; -} -EXPORT_SYMBOL(__cleancache_get_page); - -/* - * "Put" data from a page to cleancache and associate it with the - * (previously-obtained per-filesystem) poolid and the page's, - * inode and page index. Page must be locked. Note that a put_page - * always "succeeds", though a subsequent get_page may succeed or fail. - * - * The function has two checks before any action is taken - whether - * a backend is registered and whether the sb->cleancache_poolid - * is correct. - */ -void __cleancache_put_page(struct page *page) -{ - int pool_id; - struct cleancache_filekey key = { .u.key = { 0 } }; - - if (!cleancache_ops) { - cleancache_puts++; - return; - } - - VM_BUG_ON_PAGE(!PageLocked(page), page); - pool_id = page->mapping->host->i_sb->cleancache_poolid; - if (pool_id >= 0 && - cleancache_get_key(page->mapping->host, &key) >= 0) { - cleancache_ops->put_page(pool_id, key, page->index, page); - cleancache_puts++; - } -} -EXPORT_SYMBOL(__cleancache_put_page); - -/* - * Invalidate any data from cleancache associated with the poolid and the - * page's inode and page index so that a subsequent "get" will fail. - * - * The function has two checks before any action is taken - whether - * a backend is registered and whether the sb->cleancache_poolid - * is correct. - */ -void __cleancache_invalidate_page(struct address_space *mapping, - struct page *page) -{ - /* careful... page->mapping is NULL sometimes when this is called */ - int pool_id = mapping->host->i_sb->cleancache_poolid; - struct cleancache_filekey key = { .u.key = { 0 } }; - - if (!cleancache_ops) - return; - - if (pool_id >= 0) { - VM_BUG_ON_PAGE(!PageLocked(page), page); - if (cleancache_get_key(mapping->host, &key) >= 0) { - cleancache_ops->invalidate_page(pool_id, - key, page->index); - cleancache_invalidates++; - } - } -} -EXPORT_SYMBOL(__cleancache_invalidate_page); - -/* - * Invalidate all data from cleancache associated with the poolid and the - * mappings's inode so that all subsequent gets to this poolid/inode - * will fail. - * - * The function has two checks before any action is taken - whether - * a backend is registered and whether the sb->cleancache_poolid - * is correct. - */ -void __cleancache_invalidate_inode(struct address_space *mapping) -{ - int pool_id = mapping->host->i_sb->cleancache_poolid; - struct cleancache_filekey key = { .u.key = { 0 } }; - - if (!cleancache_ops) - return; - - if (pool_id >= 0 && cleancache_get_key(mapping->host, &key) >= 0) - cleancache_ops->invalidate_inode(pool_id, key); -} -EXPORT_SYMBOL(__cleancache_invalidate_inode); - -/* - * Called by any cleancache-enabled filesystem at time of unmount; - * note that pool_id is surrendered and may be returned by a subsequent - * cleancache_init_fs or cleancache_init_shared_fs. - */ -void __cleancache_invalidate_fs(struct super_block *sb) -{ - int pool_id; - - pool_id = sb->cleancache_poolid; - sb->cleancache_poolid = CLEANCACHE_NO_POOL; - - if (cleancache_ops && pool_id >= 0) - cleancache_ops->invalidate_fs(pool_id); -} -EXPORT_SYMBOL(__cleancache_invalidate_fs); - -static int __init init_cleancache(void) -{ -#ifdef CONFIG_DEBUG_FS - struct dentry *root = debugfs_create_dir("cleancache", NULL); - - debugfs_create_u64("succ_gets", 0444, root, &cleancache_succ_gets); - debugfs_create_u64("failed_gets", 0444, root, &cleancache_failed_gets); - debugfs_create_u64("puts", 0444, root, &cleancache_puts); - debugfs_create_u64("invalidates", 0444, root, &cleancache_invalidates); -#endif - return 0; -} -module_init(init_cleancache) diff --git a/mm/filemap.c b/mm/filemap.c index afc8f5ca85ac..ad8c39d90bf9 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -21,6 +21,7 @@ #include <linux/gfp.h> #include <linux/mm.h> #include <linux/swap.h> +#include <linux/swapops.h> #include <linux/mman.h> #include <linux/pagemap.h> #include <linux/file.h> @@ -34,13 +35,13 @@ #include <linux/cpuset.h> #include <linux/hugetlb.h> #include <linux/memcontrol.h> -#include <linux/cleancache.h> #include <linux/shmem_fs.h> #include <linux/rmap.h> #include <linux/delayacct.h> #include <linux/psi.h> #include <linux/ramfs.h> #include <linux/page_idle.h> +#include <linux/migrate.h> #include <asm/pgalloc.h> #include <asm/tlbflush.h> #include "internal.h" @@ -149,16 +150,6 @@ static void filemap_unaccount_folio(struct address_space *mapping, { long nr; - /* - * if we're uptodate, flush out into the cleancache, otherwise - * invalidate any existing cleancache entries. We can't leave - * stale data around in the cleancache once our page is gone - */ - if (folio_test_uptodate(folio) && folio_test_mappedtodisk(folio)) - cleancache_put_page(&folio->page); - else - cleancache_invalidate_page(mapping, &folio->page); - VM_BUG_ON_FOLIO(folio_mapped(folio), folio); if (!IS_ENABLED(CONFIG_DEBUG_VM) && unlikely(folio_mapped(folio))) { int mapcount; @@ -1386,6 +1377,95 @@ repeat: return wait->flags & WQ_FLAG_WOKEN ? 0 : -EINTR; } +#ifdef CONFIG_MIGRATION +/** + * migration_entry_wait_on_locked - Wait for a migration entry to be removed + * @entry: migration swap entry. + * @ptep: mapped pte pointer. Will return with the ptep unmapped. Only required + * for pte entries, pass NULL for pmd entries. + * @ptl: already locked ptl. This function will drop the lock. + * + * Wait for a migration entry referencing the given page to be removed. This is + * equivalent to put_and_wait_on_page_locked(page, TASK_UNINTERRUPTIBLE) except + * this can be called without taking a reference on the page. Instead this + * should be called while holding the ptl for the migration entry referencing + * the page. + * + * Returns after unmapping and unlocking the pte/ptl with pte_unmap_unlock(). + * + * This follows the same logic as folio_wait_bit_common() so see the comments + * there. + */ +void migration_entry_wait_on_locked(swp_entry_t entry, pte_t *ptep, + spinlock_t *ptl) +{ + struct wait_page_queue wait_page; + wait_queue_entry_t *wait = &wait_page.wait; + bool thrashing = false; + bool delayacct = false; + unsigned long pflags; + wait_queue_head_t *q; + struct folio *folio = page_folio(pfn_swap_entry_to_page(entry)); + + q = folio_waitqueue(folio); + if (!folio_test_uptodate(folio) && folio_test_workingset(folio)) { + if (!folio_test_swapbacked(folio)) { + delayacct_thrashing_start(); + delayacct = true; + } + psi_memstall_enter(&pflags); + thrashing = true; + } + + init_wait(wait); + wait->func = wake_page_function; + wait_page.folio = folio; + wait_page.bit_nr = PG_locked; + wait->flags = 0; + + spin_lock_irq(&q->lock); + folio_set_waiters(folio); + if (!folio_trylock_flag(folio, PG_locked, wait)) + __add_wait_queue_entry_tail(q, wait); + spin_unlock_irq(&q->lock); + + /* + * If a migration entry exists for the page the migration path must hold + * a valid reference to the page, and it must take the ptl to remove the + * migration entry. So the page is valid until the ptl is dropped. + */ + if (ptep) + pte_unmap_unlock(ptep, ptl); + else + spin_unlock(ptl); + + for (;;) { + unsigned int flags; + + set_current_state(TASK_UNINTERRUPTIBLE); + + /* Loop until we've been woken or interrupted */ + flags = smp_load_acquire(&wait->flags); + if (!(flags & WQ_FLAG_WOKEN)) { + if (signal_pending_state(TASK_UNINTERRUPTIBLE, current)) + break; + + io_schedule(); + continue; + } + break; + } + + finish_wait(q, wait); + + if (thrashing) { + if (delayacct) + delayacct_thrashing_end(); + psi_memstall_leave(&pflags); + } +} +#endif + void folio_wait_bit(struct folio *folio, int bit_nr) { folio_wait_bit_common(folio, bit_nr, TASK_UNINTERRUPTIBLE, SHARED); diff --git a/mm/frontswap.c b/mm/frontswap.c index 6bed12260dea..6f69b044a8cc 100644 --- a/mm/frontswap.c +++ b/mm/frontswap.c @@ -27,27 +27,7 @@ DEFINE_STATIC_KEY_FALSE(frontswap_enabled_key); * may be registered, but implementations can never deregister. This * is a simple singly-linked list of all registered implementations. */ -static struct frontswap_ops *frontswap_ops __read_mostly; - -#define for_each_frontswap_ops(ops) \ - for ((ops) = frontswap_ops; (ops); (ops) = (ops)->next) - -/* - * If enabled, frontswap_store will return failure even on success. As - * a result, the swap subsystem will always write the page to swap, in - * effect converting frontswap into a writethrough cache. In this mode, - * there is no direct reduction in swap writes, but a frontswap backend - * can unilaterally "reclaim" any pages in use with no data loss, thus - * providing increases control over maximum memory usage due to frontswap. - */ -static bool frontswap_writethrough_enabled __read_mostly; - -/* - * If enabled, the underlying tmem implementation is capable of doing - * exclusive gets, so frontswap_load, on a successful tmem_get must - * mark the page as no longer in frontswap AND mark it dirty. - */ -static bool frontswap_tmem_exclusive_gets_enabled __read_mostly; +static const struct frontswap_ops *frontswap_ops __read_mostly; #ifdef CONFIG_DEBUG_FS /* @@ -114,87 +94,22 @@ static inline void inc_frontswap_invalidates(void) { } /* * Register operations for frontswap */ -void frontswap_register_ops(struct frontswap_ops *ops) +int frontswap_register_ops(const struct frontswap_ops *ops) { - DECLARE_BITMAP(a, MAX_SWAPFILES); - DECLARE_BITMAP(b, MAX_SWAPFILES); - struct swap_info_struct *si; - unsigned int i; - - bitmap_zero(a, MAX_SWAPFILES); - bitmap_zero(b, MAX_SWAPFILES); - - spin_lock(&swap_lock); - plist_for_each_entry(si, &swap_active_head, list) { - if (!WARN_ON(!si->frontswap_map)) - __set_bit(si->type, a); - } - spin_unlock(&swap_lock); - - /* the new ops needs to know the currently active swap devices */ - for_each_set_bit(i, a, MAX_SWAPFILES) - ops->init(i); - - /* - * Setting frontswap_ops must happen after the ops->init() calls - * above; cmpxchg implies smp_mb() which will ensure the init is - * complete at this point. - */ - do { - ops->next = frontswap_ops; - } while (cmpxchg(&frontswap_ops, ops->next, ops) != ops->next); + if (frontswap_ops) + return -EINVAL; + frontswap_ops = ops; static_branch_inc(&frontswap_enabled_key); - - spin_lock(&swap_lock); - plist_for_each_entry(si, &swap_active_head, list) { - if (si->frontswap_map) - __set_bit(si->type, b); - } - spin_unlock(&swap_lock); - - /* - * On the very unlikely chance that a swap device was added or - * removed between setting the "a" list bits and the ops init - * calls, we re-check and do init or invalidate for any changed - * bits. - */ - if (unlikely(!bitmap_equal(a, b, MAX_SWAPFILES))) { - for (i = 0; i < MAX_SWAPFILES; i++) { - if (!test_bit(i, a) && test_bit(i, b)) - ops->init(i); - else if (test_bit(i, a) && !test_bit(i, b)) - ops->invalidate_area(i); - } - } -} -EXPORT_SYMBOL(frontswap_register_ops); - -/* - * Enable/disable frontswap writethrough (see above). - */ -void frontswap_writethrough(bool enable) -{ - frontswap_writethrough_enabled = enable; -} -EXPORT_SYMBOL(frontswap_writethrough); - -/* - * Enable/disable frontswap exclusive gets (see above). - */ -void frontswap_tmem_exclusive_gets(bool enable) -{ - frontswap_tmem_exclusive_gets_enabled = enable; + return 0; } -EXPORT_SYMBOL(frontswap_tmem_exclusive_gets); /* * Called when a swap device is swapon'd. */ -void __frontswap_init(unsigned type, unsigned long *map) +void frontswap_init(unsigned type, unsigned long *map) { struct swap_info_struct *sis = swap_info[type]; - struct frontswap_ops *ops; VM_BUG_ON(sis == NULL); @@ -210,20 +125,16 @@ void __frontswap_init(unsigned type, unsigned long *map) * p->frontswap set to something valid to work properly. */ frontswap_map_set(sis, map); - - for_each_frontswap_ops(ops) - ops->init(type); + frontswap_ops->init(type); } -EXPORT_SYMBOL(__frontswap_init); -bool __frontswap_test(struct swap_info_struct *sis, +static bool __frontswap_test(struct swap_info_struct *sis, pgoff_t offset) { if (sis->frontswap_map) return test_bit(offset, sis->frontswap_map); return false; } -EXPORT_SYMBOL(__frontswap_test); static inline void __frontswap_set(struct swap_info_struct *sis, pgoff_t offset) @@ -253,7 +164,6 @@ int __frontswap_store(struct page *page) int type = swp_type(entry); struct swap_info_struct *sis = swap_info[type]; pgoff_t offset = swp_offset(entry); - struct frontswap_ops *ops; VM_BUG_ON(!frontswap_ops); VM_BUG_ON(!PageLocked(page)); @@ -267,28 +177,19 @@ int __frontswap_store(struct page *page) */ if (__frontswap_test(sis, offset)) { __frontswap_clear(sis, offset); - for_each_frontswap_ops(ops) - ops->invalidate_page(type, offset); + frontswap_ops->invalidate_page(type, offset); } - /* Try to store in each implementation, until one succeeds. */ - for_each_frontswap_ops(ops) { - ret = ops->store(type, offset, page); - if (!ret) /* successful store */ - break; - } + ret = frontswap_ops->store(type, offset, page); if (ret == 0) { __frontswap_set(sis, offset); inc_frontswap_succ_stores(); } else { inc_frontswap_failed_stores(); } - if (frontswap_writethrough_enabled) - /* report failure so swap also writes to swap device */ - ret = -1; + return ret; } -EXPORT_SYMBOL(__frontswap_store); /* * "Get" data from frontswap associated with swaptype and offset that were @@ -302,7 +203,6 @@ int __frontswap_load(struct page *page) int type = swp_type(entry); struct swap_info_struct *sis = swap_info[type]; pgoff_t offset = swp_offset(entry); - struct frontswap_ops *ops; VM_BUG_ON(!frontswap_ops); VM_BUG_ON(!PageLocked(page)); @@ -312,21 +212,11 @@ int __frontswap_load(struct page *page) return -1; /* Try loading from each implementation, until one succeeds. */ - for_each_frontswap_ops(ops) { - ret = ops->load(type, offset, page); - if (!ret) /* successful load */ - break; - } - if (ret == 0) { + ret = frontswap_ops->load(type, offset, page); + if (ret == 0) inc_frontswap_loads(); - if (frontswap_tmem_exclusive_gets_enabled) { - SetPageDirty(page); - __frontswap_clear(sis, offset); - } - } return ret; } -EXPORT_SYMBOL(__frontswap_load); /* * Invalidate any data from frontswap associated with the specified swaptype @@ -335,7 +225,6 @@ EXPORT_SYMBOL(__frontswap_load); void __frontswap_invalidate_page(unsigned type, pgoff_t offset) { struct swap_info_struct *sis = swap_info[type]; - struct frontswap_ops *ops; VM_BUG_ON(!frontswap_ops); VM_BUG_ON(sis == NULL); @@ -343,12 +232,10 @@ void __frontswap_invalidate_page(unsigned type, pgoff_t offset) if (!__frontswap_test(sis, offset)) return; - for_each_frontswap_ops(ops) - ops->invalidate_page(type, offset); + frontswap_ops->invalidate_page(type, offset); __frontswap_clear(sis, offset); inc_frontswap_invalidates(); } -EXPORT_SYMBOL(__frontswap_invalidate_page); /* * Invalidate all data from frontswap associated with all offsets for the @@ -357,7 +244,6 @@ EXPORT_SYMBOL(__frontswap_invalidate_page); void __frontswap_invalidate_area(unsigned type) { struct swap_info_struct *sis = swap_info[type]; - struct frontswap_ops *ops; VM_BUG_ON(!frontswap_ops); VM_BUG_ON(sis == NULL); @@ -365,123 +251,10 @@ void __frontswap_invalidate_area(unsigned type) if (sis->frontswap_map == NULL) return; - for_each_frontswap_ops(ops) - ops->invalidate_area(type); + frontswap_ops->invalidate_area(type); atomic_set(&sis->frontswap_pages, 0); bitmap_zero(sis->frontswap_map, sis->max); } -EXPORT_SYMBOL(__frontswap_invalidate_area); - -static unsigned long __frontswap_curr_pages(void) -{ - unsigned long totalpages = 0; - struct swap_info_struct *si = NULL; - - assert_spin_locked(&swap_lock); - plist_for_each_entry(si, &swap_active_head, list) - totalpages += atomic_read(&si->frontswap_pages); - return totalpages; -} - -static int __frontswap_unuse_pages(unsigned long total, unsigned long *unused, - int *swapid) -{ - int ret = -EINVAL; - struct swap_info_struct *si = NULL; - int si_frontswap_pages; - unsigned long total_pages_to_unuse = total; - unsigned long pages = 0, pages_to_unuse = 0; - - assert_spin_locked(&swap_lock); - plist_for_each_entry(si, &swap_active_head, list) { - si_frontswap_pages = atomic_read(&si->frontswap_pages); - if (total_pages_to_unuse < si_frontswap_pages) { - pages = pages_to_unuse = total_pages_to_unuse; - } else { - pages = si_frontswap_pages; - pages_to_unuse = 0; /* unuse all */ - } - /* ensure there is enough RAM to fetch pages from frontswap */ - if (security_vm_enough_memory_mm(current->mm, pages)) { - ret = -ENOMEM; - continue; - } - vm_unacct_memory(pages); - *unused = pages_to_unuse; - *swapid = si->type; - ret = 0; - break; - } - - return ret; -} - -/* - * Used to check if it's necessary and feasible to unuse pages. - * Return 1 when nothing to do, 0 when need to shrink pages, - * error code when there is an error. - */ -static int __frontswap_shrink(unsigned long target_pages, - unsigned long *pages_to_unuse, - int *type) -{ - unsigned long total_pages = 0, total_pages_to_unuse; - - assert_spin_locked(&swap_lock); - - total_pages = __frontswap_curr_pages(); - if (total_pages <= target_pages) { - /* Nothing to do */ - *pages_to_unuse = 0; - return 1; - } - total_pages_to_unuse = total_pages - target_pages; - return __frontswap_unuse_pages(total_pages_to_unuse, pages_to_unuse, type); -} - -/* - * Frontswap, like a true swap device, may unnecessarily retain pages - * under certain circumstances; "shrink" frontswap is essentially a - * "partial swapoff" and works by calling try_to_unuse to attempt to - * unuse enough frontswap pages to attempt to -- subject to memory - * constraints -- reduce the number of pages in frontswap to the - * number given in the parameter target_pages. - */ -void frontswap_shrink(unsigned long target_pages) -{ - unsigned long pages_to_unuse = 0; - int type, ret; - - /* - * we don't want to hold swap_lock while doing a very - * lengthy try_to_unuse, but swap_list may change - * so restart scan from swap_active_head each time - */ - spin_lock(&swap_lock); - ret = __frontswap_shrink(target_pages, &pages_to_unuse, &type); - spin_unlock(&swap_lock); - if (ret == 0) - try_to_unuse(type, true, pages_to_unuse); - return; -} -EXPORT_SYMBOL(frontswap_shrink); - -/* - * Count and return the number of frontswap pages across all - * swap devices. This is exported so that backend drivers can - * determine current usage without reading debugfs. - */ -unsigned long frontswap_curr_pages(void) -{ - unsigned long totalpages = 0; - - spin_lock(&swap_lock); - totalpages = __frontswap_curr_pages(); - spin_unlock(&swap_lock); - - return totalpages; -} -EXPORT_SYMBOL(frontswap_curr_pages); static int __init init_frontswap(void) { diff --git a/mm/kasan/common.c b/mm/kasan/common.c index 7c06db78a76c..92196562687b 100644 --- a/mm/kasan/common.c +++ b/mm/kasan/common.c @@ -36,7 +36,6 @@ depot_stack_handle_t kasan_save_stack(gfp_t flags, bool can_alloc) unsigned int nr_entries; nr_entries = stack_trace_save(entries, ARRAY_SIZE(entries), 0); - nr_entries = filter_irq_stacks(entries, nr_entries); return __stack_depot_save(entries, nr_entries, flags, can_alloc); } diff --git a/mm/migrate.c b/mm/migrate.c index 18ce840914f0..c7da064b4781 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -291,7 +291,6 @@ void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep, { pte_t pte; swp_entry_t entry; - struct folio *folio; spin_lock(ptl); pte = *ptep; @@ -302,17 +301,7 @@ void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep, if (!is_migration_entry(entry)) goto out; - folio = page_folio(pfn_swap_entry_to_page(entry)); - - /* - * Once page cache replacement of page migration started, page_count - * is zero; but we must not call folio_put_wait_locked() without - * a ref. Use folio_try_get(), and just fault again if it fails. - */ - if (!folio_try_get(folio)) - goto out; - pte_unmap_unlock(ptep, ptl); - folio_put_wait_locked(folio, TASK_UNINTERRUPTIBLE); + migration_entry_wait_on_locked(entry, ptep, ptl); return; out: pte_unmap_unlock(ptep, ptl); @@ -337,16 +326,11 @@ void migration_entry_wait_huge(struct vm_area_struct *vma, void pmd_migration_entry_wait(struct mm_struct *mm, pmd_t *pmd) { spinlock_t *ptl; - struct folio *folio; ptl = pmd_lock(mm, pmd); if (!is_pmd_migration_entry(*pmd)) goto unlock; - folio = page_folio(pfn_swap_entry_to_page(pmd_to_swp_entry(*pmd))); - if (!folio_try_get(folio)) - goto unlock; - spin_unlock(ptl); - folio_put_wait_locked(folio, TASK_UNINTERRUPTIBLE); + migration_entry_wait_on_locked(pmd_to_swp_entry(*pmd), NULL, ptl); return; unlock: spin_unlock(ptl); @@ -2431,22 +2415,8 @@ static bool migrate_vma_check_page(struct page *page) return false; /* Page from ZONE_DEVICE have one extra reference */ - if (is_zone_device_page(page)) { - /* - * Private page can never be pin as they have no valid pte and - * GUP will fail for those. Yet if there is a pending migration - * a thread might try to wait on the pte migration entry and - * will bump the page reference count. Sadly there is no way to - * differentiate a regular pin from migration wait. Hence to - * avoid 2 racing thread trying to migrate back to CPU to enter - * infinite loop (one stopping migration because the other is - * waiting on pte migration entry). We always return true here. - * - * FIXME proper solution is to rework migration_entry_wait() so - * it does not need to take a reference on page. - */ - return is_device_private_page(page); - } + if (is_zone_device_page(page)) + extra++; /* For file back page */ if (page_mapping(page)) diff --git a/mm/page_owner.c b/mm/page_owner.c index 5eea061bb1e5..99e360df9465 100644 --- a/mm/page_owner.c +++ b/mm/page_owner.c @@ -80,6 +80,8 @@ static __init void init_page_owner(void) if (!page_owner_enabled) return; + stack_depot_init(); + register_dummy_stack(); register_failure_stack(); register_early_stack(); diff --git a/mm/shmem.c b/mm/shmem.c index 66909efd0a1b..a09b29ec2b45 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -36,7 +36,6 @@ #include <linux/uio.h> #include <linux/khugepaged.h> #include <linux/hugetlb.h> -#include <linux/frontswap.h> #include <linux/fs_parser.h> #include <linux/swapfile.h> @@ -1152,7 +1151,7 @@ static void shmem_evict_inode(struct inode *inode) static int shmem_find_swap_entries(struct address_space *mapping, pgoff_t start, unsigned int nr_entries, struct page **entries, pgoff_t *indices, - unsigned int type, bool frontswap) + unsigned int type) { XA_STATE(xas, &mapping->i_pages, start); struct page *page; @@ -1173,9 +1172,6 @@ static int shmem_find_swap_entries(struct address_space *mapping, entry = radix_to_swp_entry(page); if (swp_type(entry) != type) continue; - if (frontswap && - !frontswap_test(swap_info[type], swp_offset(entry))) - continue; indices[ret] = xas.xa_index; entries[ret] = page; @@ -1228,26 +1224,20 @@ static int shmem_unuse_swap_entries(struct inode *inode, struct pagevec pvec, /* * If swap found in inode, free it and move page from swapcache to filecache. */ -static int shmem_unuse_inode(struct inode *inode, unsigned int type, - bool frontswap, unsigned long *fs_pages_to_unuse) +static int shmem_unuse_inode(struct inode *inode, unsigned int type) { struct address_space *mapping = inode->i_mapping; pgoff_t start = 0; struct pagevec pvec; pgoff_t indices[PAGEVEC_SIZE]; - bool frontswap_partial = (frontswap && *fs_pages_to_unuse > 0); int ret = 0; pagevec_init(&pvec); do { unsigned int nr_entries = PAGEVEC_SIZE; - if (frontswap_partial && *fs_pages_to_unuse < PAGEVEC_SIZE) - nr_entries = *fs_pages_to_unuse; - pvec.nr = shmem_find_swap_entries(mapping, start, nr_entries, - pvec.pages, indices, - type, frontswap); + pvec.pages, indices, type); if (pvec.nr == 0) { ret = 0; break; @@ -1257,14 +1247,6 @@ static int shmem_unuse_inode(struct inode *inode, unsigned int type, if (ret < 0) break; - if (frontswap_partial) { - *fs_pages_to_unuse -= ret; - if (*fs_pages_to_unuse == 0) { - ret = FRONTSWAP_PAGES_UNUSED; - break; - } - } - start = indices[pvec.nr - 1]; } while (true); @@ -1276,8 +1258,7 @@ static int shmem_unuse_inode(struct inode *inode, unsigned int type, * device 'type' back into memory, so the swap device can be * unused. */ -int shmem_unuse(unsigned int type, bool frontswap, - unsigned long *fs_pages_to_unuse) +int shmem_unuse(unsigned int type) { struct shmem_inode_info *info, *next; int error = 0; @@ -1300,8 +1281,7 @@ int shmem_unuse(unsigned int type, bool frontswap, atomic_inc(&info->stop_eviction); mutex_unlock(&shmem_swaplist_mutex); - error = shmem_unuse_inode(&info->vfs_inode, type, frontswap, - fs_pages_to_unuse); + error = shmem_unuse_inode(&info->vfs_inode, type); cond_resched(); mutex_lock(&shmem_swaplist_mutex); @@ -4015,8 +3995,7 @@ int __init shmem_init(void) return 0; } -int shmem_unuse(unsigned int type, bool frontswap, - unsigned long *fs_pages_to_unuse) +int shmem_unuse(unsigned int type) { return 0; } diff --git a/mm/swapfile.c b/mm/swapfile.c index caa9f81a0d15..bf0df7aa7158 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -49,7 +49,7 @@ static bool swap_count_continued(struct swap_info_struct *, pgoff_t, unsigned char); static void free_swap_count_continuations(struct swap_info_struct *); -DEFINE_SPINLOCK(swap_lock); +static DEFINE_SPINLOCK(swap_lock); static unsigned int nr_swapfiles; atomic_long_t nr_swap_pages; /* @@ -71,7 +71,7 @@ static const char Unused_offset[] = "Unused swap offset entry "; * all active swap_info_structs * protected with swap_lock, and ordered by priority. */ -PLIST_HEAD(swap_active_head); +static PLIST_HEAD(swap_active_head); /* * all available (active, not full) swap_info_structs @@ -1923,8 +1923,7 @@ out: static int unuse_pte_range(struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, unsigned long end, - unsigned int type, bool frontswap, - unsigned long *fs_pages_to_unuse) + unsigned int type) { struct page *page; swp_entry_t entry; @@ -1945,9 +1944,6 @@ static int unuse_pte_range(struct vm_area_struct *vma, pmd_t *pmd, continue; offset = swp_offset(entry); - if (frontswap && !frontswap_test(si, offset)) - continue; - pte_unmap(pte); swap_map = &si->swap_map[offset]; page = lookup_swap_cache(entry, vma, addr); @@ -1979,11 +1975,6 @@ static int unuse_pte_range(struct vm_area_struct *vma, pmd_t *pmd, try_to_free_swap(page); unlock_page(page); put_page(page); - - if (*fs_pages_to_unuse && !--(*fs_pages_to_unuse)) { - ret = FRONTSWAP_PAGES_UNUSED; - goto out; - } try_next: pte = pte_offset_map(pmd, addr); } while (pte++, addr += PAGE_SIZE, addr != end); @@ -1996,8 +1987,7 @@ out: static inline int unuse_pmd_range(struct vm_area_struct *vma, pud_t *pud, unsigned long addr, unsigned long end, - unsigned int type, bool frontswap, - unsigned long *fs_pages_to_unuse) + unsigned int type) { pmd_t *pmd; unsigned long next; @@ -2009,8 +1999,7 @@ static inline int unuse_pmd_range(struct vm_area_struct *vma, pud_t *pud, next = pmd_addr_end(addr, end); if (pmd_none_or_trans_huge_or_clear_bad(pmd)) continue; - ret = unuse_pte_range(vma, pmd, addr, next, type, - frontswap, fs_pages_to_unuse); + ret = unuse_pte_range(vma, pmd, addr, next, type); if (ret) return ret; } while (pmd++, addr = next, addr != end); @@ -2019,8 +2008,7 @@ static inline int unuse_pmd_range(struct vm_area_struct *vma, pud_t *pud, static inline int unuse_pud_range(struct vm_area_struct *vma, p4d_t *p4d, unsigned long addr, unsigned long end, - unsigned int type, bool frontswap, - unsigned long *fs_pages_to_unuse) + unsigned int type) { pud_t *pud; unsigned long next; @@ -2031,8 +2019,7 @@ static inline int unuse_pud_range(struct vm_area_struct *vma, p4d_t *p4d, next = pud_addr_end(addr, end); if (pud_none_or_clear_bad(pud)) continue; - ret = unuse_pmd_range(vma, pud, addr, next, type, - frontswap, fs_pages_to_unuse); + ret = unuse_pmd_range(vma, pud, addr, next, type); if (ret) return ret; } while (pud++, addr = next, addr != end); @@ -2041,8 +2028,7 @@ static inline int unuse_pud_range(struct vm_area_struct *vma, p4d_t *p4d, static inline int unuse_p4d_range(struct vm_area_struct *vma, pgd_t *pgd, unsigned long addr, unsigned long end, - unsigned int type, bool frontswap, - unsigned long *fs_pages_to_unuse) + unsigned int type) { p4d_t *p4d; unsigned long next; @@ -2053,16 +2039,14 @@ static inline int unuse_p4d_range(struct vm_area_struct *vma, pgd_t *pgd, next = p4d_addr_end(addr, end); if (p4d_none_or_clear_bad(p4d)) continue; - ret = unuse_pud_range(vma, p4d, addr, next, type, - frontswap, fs_pages_to_unuse); + ret = unuse_pud_range(vma, p4d, addr, next, type); if (ret) return ret; } while (p4d++, addr = next, addr != end); return 0; } -static int unuse_vma(struct vm_area_struct *vma, unsigned int type, - bool frontswap, unsigned long *fs_pages_to_unuse) +static int unuse_vma(struct vm_area_struct *vma, unsigned int type) { pgd_t *pgd; unsigned long addr, end, next; @@ -2076,16 +2060,14 @@ static int unuse_vma(struct vm_area_struct *vma, unsigned int type, next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(pgd)) continue; - ret = unuse_p4d_range(vma, pgd, addr, next, type, - frontswap, fs_pages_to_unuse); + ret = unuse_p4d_range(vma, pgd, addr, next, type); if (ret) return ret; } while (pgd++, addr = next, addr != end); return 0; } -static int unuse_mm(struct mm_struct *mm, unsigned int type, - bool frontswap, unsigned long *fs_pages_to_unuse) +static int unuse_mm(struct mm_struct *mm, unsigned int type) { struct vm_area_struct *vma; int ret = 0; @@ -2093,8 +2075,7 @@ static int unuse_mm(struct mm_struct *mm, unsigned int type, mmap_read_lock(mm); for (vma = mm->mmap; vma; vma = vma->vm_next) { if (vma->anon_vma) { - ret = unuse_vma(vma, type, frontswap, - fs_pages_to_unuse); + ret = unuse_vma(vma, type); if (ret) break; } @@ -2110,7 +2091,7 @@ static int unuse_mm(struct mm_struct *mm, unsigned int type, * if there are no inuse entries after prev till end of the map. */ static unsigned int find_next_to_unuse(struct swap_info_struct *si, - unsigned int prev, bool frontswap) + unsigned int prev) { unsigned int i; unsigned char count; @@ -2124,8 +2105,7 @@ static unsigned int find_next_to_unuse(struct swap_info_struct *si, for (i = prev + 1; i < si->max; i++) { count = READ_ONCE(si->swap_map[i]); if (count && swap_count(count) != SWAP_MAP_BAD) - if (!frontswap || frontswap_test(si, i)) - break; + break; if ((i % LATENCY_LIMIT) == 0) cond_resched(); } @@ -2136,12 +2116,7 @@ static unsigned int find_next_to_unuse(struct swap_info_struct *si, return i; } -/* - * If the boolean frontswap is true, only unuse pages_to_unuse pages; - * pages_to_unuse==0 means all pages; ignored if frontswap is false - */ -int try_to_unuse(unsigned int type, bool frontswap, - unsigned long pages_to_unuse) +static int try_to_unuse(unsigned int type) { struct mm_struct *prev_mm; struct mm_struct *mm; @@ -2155,13 +2130,10 @@ int try_to_unuse(unsigned int type, bool frontswap, if (!READ_ONCE(si->inuse_pages)) return 0; - if (!frontswap) - pages_to_unuse = 0; - retry: - retval = shmem_unuse(type, frontswap, &pages_to_unuse); + retval = shmem_unuse(type); if (retval) - goto out; + return retval; prev_mm = &init_mm; mmget(prev_mm); @@ -2178,11 +2150,10 @@ retry: spin_unlock(&mmlist_lock); mmput(prev_mm); prev_mm = mm; - retval = unuse_mm(mm, type, frontswap, &pages_to_unuse); - + retval = unuse_mm(mm, type); if (retval) { mmput(prev_mm); - goto out; + return retval; } /* @@ -2199,7 +2170,7 @@ retry: i = 0; while (READ_ONCE(si->inuse_pages) && !signal_pending(current) && - (i = find_next_to_unuse(si, i, frontswap)) != 0) { + (i = find_next_to_unuse(si, i)) != 0) { entry = swp_entry(type, i); page = find_get_page(swap_address_space(entry), i); @@ -2217,14 +2188,6 @@ retry: try_to_free_swap(page); unlock_page(page); put_page(page); - - /* - * For frontswap, we just need to unuse pages_to_unuse, if - * it was specified. Need not check frontswap again here as - * we already zeroed out pages_to_unuse if not frontswap. - */ - if (pages_to_unuse && --pages_to_unuse == 0) - goto out; } /* @@ -2242,10 +2205,10 @@ retry: if (READ_ONCE(si->inuse_pages)) { if (!signal_pending(current)) goto retry; - retval = -EINTR; + return -EINTR; } -out: - return (retval == FRONTSWAP_PAGES_UNUSED) ? 0 : retval; + + return 0; } /* @@ -2463,7 +2426,8 @@ static void enable_swap_info(struct swap_info_struct *p, int prio, struct swap_cluster_info *cluster_info, unsigned long *frontswap_map) { - frontswap_init(p->type, frontswap_map); + if (IS_ENABLED(CONFIG_FRONTSWAP)) + frontswap_init(p->type, frontswap_map); spin_lock(&swap_lock); spin_lock(&p->lock); setup_swap_info(p, prio, swap_map, cluster_info); @@ -2576,7 +2540,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) disable_swap_slots_cache_lock(); set_current_oom_origin(); - err = try_to_unuse(p->type, false, 0); /* force unuse all pages */ + err = try_to_unuse(p->type); clear_current_oom_origin(); if (err) { diff --git a/mm/truncate.c b/mm/truncate.c index 5e243d7269c0..9dbf0b75da5d 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -22,7 +22,6 @@ #include <linux/buffer_head.h> /* grr. try_to_release_page, do_invalidatepage */ #include <linux/shmem_fs.h> -#include <linux/cleancache.h> #include <linux/rmap.h> #include "internal.h" @@ -264,7 +263,6 @@ bool truncate_inode_partial_folio(struct folio *folio, loff_t start, loff_t end) */ folio_zero_range(folio, offset, length); - cleancache_invalidate_page(folio->mapping, &folio->page); if (folio_has_private(folio)) do_invalidatepage(&folio->page, offset, length); if (!folio_test_large(folio)) @@ -351,7 +349,7 @@ void truncate_inode_pages_range(struct address_space *mapping, bool same_folio; if (mapping_empty(mapping)) - goto out; + return; /* * 'start' and 'end' always covers the range of pages to be fully @@ -442,9 +440,6 @@ void truncate_inode_pages_range(struct address_space *mapping, folio_batch_release(&fbatch); index++; } - -out: - cleancache_invalidate_inode(mapping); } EXPORT_SYMBOL(truncate_inode_pages_range); @@ -498,10 +493,6 @@ void truncate_inode_pages_final(struct address_space *mapping) xa_unlock_irq(&mapping->i_pages); } - /* - * Cleancache needs notification even if there are no pages or shadow - * entries. - */ truncate_inode_pages(mapping, 0); } EXPORT_SYMBOL(truncate_inode_pages_final); @@ -661,7 +652,7 @@ int invalidate_inode_pages2_range(struct address_space *mapping, int did_range_unmap = 0; if (mapping_empty(mapping)) - goto out; + return 0; folio_batch_init(&fbatch); index = start; @@ -725,8 +716,6 @@ int invalidate_inode_pages2_range(struct address_space *mapping, if (dax_mapping(mapping)) { unmap_mapping_pages(mapping, start, end - start + 1, false); } -out: - cleancache_invalidate_inode(mapping); return ret; } EXPORT_SYMBOL_GPL(invalidate_inode_pages2_range); diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c index 0d3b65939016..9152fbde33b5 100644 --- a/mm/zsmalloc.c +++ b/mm/zsmalloc.c @@ -30,6 +30,14 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +/* + * lock ordering: + * page_lock + * pool->migrate_lock + * class->lock + * zspage->lock + */ + #include <linux/module.h> #include <linux/kernel.h> #include <linux/sched.h> @@ -57,6 +65,7 @@ #include <linux/wait.h> #include <linux/pagemap.h> #include <linux/fs.h> +#include <linux/local_lock.h> #define ZSPAGE_MAGIC 0x58 @@ -101,15 +110,6 @@ #define _PFN_BITS (MAX_POSSIBLE_PHYSMEM_BITS - PAGE_SHIFT) /* - * Memory for allocating for handle keeps object position by - * encoding <page, obj_idx> and the encoded value has a room - * in least bit(ie, look at obj_to_location). - * We use the bit to synchronize between object access by - * user and migration. - */ -#define HANDLE_PIN_BIT 0 - -/* * Head in allocated object should have OBJ_ALLOCATED_TAG * to identify the object was allocated or not. * It's okay to add the status bit in the least bit because @@ -121,6 +121,7 @@ #define OBJ_INDEX_BITS (BITS_PER_LONG - _PFN_BITS - OBJ_TAG_BITS) #define OBJ_INDEX_MASK ((_AC(1, UL) << OBJ_INDEX_BITS) - 1) +#define HUGE_BITS 1 #define FULLNESS_BITS 2 #define CLASS_BITS 8 #define ISOLATED_BITS 3 @@ -158,7 +159,7 @@ enum fullness_group { NR_ZS_FULLNESS, }; -enum zs_stat_type { +enum class_stat_type { CLASS_EMPTY, CLASS_ALMOST_EMPTY, CLASS_ALMOST_FULL, @@ -213,22 +214,6 @@ struct size_class { struct zs_size_stat stats; }; -/* huge object: pages_per_zspage == 1 && maxobj_per_zspage == 1 */ -static void SetPageHugeObject(struct page *page) -{ - SetPageOwnerPriv1(page); -} - -static void ClearPageHugeObject(struct page *page) -{ - ClearPageOwnerPriv1(page); -} - -static int PageHugeObject(struct page *page) -{ - return PageOwnerPriv1(page); -} - /* * Placed within free objects to form a singly linked list. * For every zspage, zspage->freeobj gives head of this list. @@ -269,15 +254,14 @@ struct zs_pool { #ifdef CONFIG_COMPACTION struct inode *inode; struct work_struct free_work; - /* A wait queue for when migration races with async_free_zspage() */ - struct wait_queue_head migration_wait; - atomic_long_t isolated_pages; - bool destroying; #endif + /* protect page/zspage migration */ + rwlock_t migrate_lock; }; struct zspage { struct { + unsigned int huge:HUGE_BITS; unsigned int fullness:FULLNESS_BITS; unsigned int class:CLASS_BITS + 1; unsigned int isolated:ISOLATED_BITS; @@ -293,17 +277,32 @@ struct zspage { }; struct mapping_area { + local_lock_t lock; char *vm_buf; /* copy buffer for objects that span pages */ char *vm_addr; /* address of kmap_atomic()'ed pages */ enum zs_mapmode vm_mm; /* mapping mode */ }; +/* huge object: pages_per_zspage == 1 && maxobj_per_zspage == 1 */ +static void SetZsHugePage(struct zspage *zspage) +{ + zspage->huge = 1; +} + +static bool ZsHugePage(struct zspage *zspage) +{ + return zspage->huge; +} + #ifdef CONFIG_COMPACTION static int zs_register_migration(struct zs_pool *pool); static void zs_unregister_migration(struct zs_pool *pool); static void migrate_lock_init(struct zspage *zspage); static void migrate_read_lock(struct zspage *zspage); static void migrate_read_unlock(struct zspage *zspage); +static void migrate_write_lock(struct zspage *zspage); +static void migrate_write_lock_nested(struct zspage *zspage); +static void migrate_write_unlock(struct zspage *zspage); static void kick_deferred_free(struct zs_pool *pool); static void init_deferred_free(struct zs_pool *pool); static void SetZsPageMovable(struct zs_pool *pool, struct zspage *zspage); @@ -315,6 +314,9 @@ static void zs_unregister_migration(struct zs_pool *pool) {} static void migrate_lock_init(struct zspage *zspage) {} static void migrate_read_lock(struct zspage *zspage) {} static void migrate_read_unlock(struct zspage *zspage) {} +static void migrate_write_lock(struct zspage *zspage) {} +static void migrate_write_lock_nested(struct zspage *zspage) {} +static void migrate_write_unlock(struct zspage *zspage) {} static void kick_deferred_free(struct zs_pool *pool) {} static void init_deferred_free(struct zs_pool *pool) {} static void SetZsPageMovable(struct zs_pool *pool, struct zspage *zspage) {} @@ -366,14 +368,10 @@ static void cache_free_zspage(struct zs_pool *pool, struct zspage *zspage) kmem_cache_free(pool->zspage_cachep, zspage); } +/* class->lock(which owns the handle) synchronizes races */ static void record_obj(unsigned long handle, unsigned long obj) { - /* - * lsb of @obj represents handle lock while other bits - * represent object value the handle is pointing so - * updating shouldn't do store tearing. - */ - WRITE_ONCE(*(unsigned long *)handle, obj); + *(unsigned long *)handle = obj; } /* zpool driver */ @@ -455,12 +453,9 @@ MODULE_ALIAS("zpool-zsmalloc"); #endif /* CONFIG_ZPOOL */ /* per-cpu VM mapping areas for zspage accesses that cross page boundaries */ -static DEFINE_PER_CPU(struct mapping_area, zs_map_area); - -static bool is_zspage_isolated(struct zspage *zspage) -{ - return zspage->isolated; -} +static DEFINE_PER_CPU(struct mapping_area, zs_map_area) = { + .lock = INIT_LOCAL_LOCK(lock), +}; static __maybe_unused int is_first_page(struct page *page) { @@ -517,6 +512,12 @@ static void get_zspage_mapping(struct zspage *zspage, *class_idx = zspage->class; } +static struct size_class *zspage_class(struct zs_pool *pool, + struct zspage *zspage) +{ + return pool->size_class[zspage->class]; +} + static void set_zspage_mapping(struct zspage *zspage, unsigned int class_idx, enum fullness_group fullness) @@ -543,21 +544,21 @@ static int get_size_class_index(int size) return min_t(int, ZS_SIZE_CLASSES - 1, idx); } -/* type can be of enum type zs_stat_type or fullness_group */ -static inline void zs_stat_inc(struct size_class *class, +/* type can be of enum type class_stat_type or fullness_group */ +static inline void class_stat_inc(struct size_class *class, int type, unsigned long cnt) { class->stats.objs[type] += cnt; } -/* type can be of enum type zs_stat_type or fullness_group */ -static inline void zs_stat_dec(struct size_class *class, +/* type can be of enum type class_stat_type or fullness_group */ +static inline void class_stat_dec(struct size_class *class, int type, unsigned long cnt) { class->stats.objs[type] -= cnt; } -/* type can be of enum type zs_stat_type or fullness_group */ +/* type can be of enum type class_stat_type or fullness_group */ static inline unsigned long zs_stat_get(struct size_class *class, int type) { @@ -719,7 +720,7 @@ static void insert_zspage(struct size_class *class, { struct zspage *head; - zs_stat_inc(class, fullness, 1); + class_stat_inc(class, fullness, 1); head = list_first_entry_or_null(&class->fullness_list[fullness], struct zspage, list); /* @@ -741,10 +742,9 @@ static void remove_zspage(struct size_class *class, enum fullness_group fullness) { VM_BUG_ON(list_empty(&class->fullness_list[fullness])); - VM_BUG_ON(is_zspage_isolated(zspage)); list_del_init(&zspage->list); - zs_stat_dec(class, fullness, 1); + class_stat_dec(class, fullness, 1); } /* @@ -767,13 +767,9 @@ static enum fullness_group fix_fullness_group(struct size_class *class, if (newfg == currfg) goto out; - if (!is_zspage_isolated(zspage)) { - remove_zspage(class, zspage, currfg); - insert_zspage(class, zspage, newfg); - } - + remove_zspage(class, zspage, currfg); + insert_zspage(class, zspage, newfg); set_zspage_mapping(zspage, class_idx, newfg); - out: return newfg; } @@ -824,7 +820,9 @@ static struct zspage *get_zspage(struct page *page) static struct page *get_next_page(struct page *page) { - if (unlikely(PageHugeObject(page))) + struct zspage *zspage = get_zspage(page); + + if (unlikely(ZsHugePage(zspage))) return NULL; return (struct page *)page->index; @@ -844,6 +842,12 @@ static void obj_to_location(unsigned long obj, struct page **page, *obj_idx = (obj & OBJ_INDEX_MASK); } +static void obj_to_page(unsigned long obj, struct page **page) +{ + obj >>= OBJ_TAG_BITS; + *page = pfn_to_page(obj >> OBJ_INDEX_BITS); +} + /** * location_to_obj - get obj value encoded from (<page>, <obj_idx>) * @page: page object resides in zspage @@ -865,33 +869,22 @@ static unsigned long handle_to_obj(unsigned long handle) return *(unsigned long *)handle; } -static unsigned long obj_to_head(struct page *page, void *obj) +static bool obj_allocated(struct page *page, void *obj, unsigned long *phandle) { - if (unlikely(PageHugeObject(page))) { + unsigned long handle; + struct zspage *zspage = get_zspage(page); + + if (unlikely(ZsHugePage(zspage))) { VM_BUG_ON_PAGE(!is_first_page(page), page); - return page->index; + handle = page->index; } else - return *(unsigned long *)obj; -} - -static inline int testpin_tag(unsigned long handle) -{ - return bit_spin_is_locked(HANDLE_PIN_BIT, (unsigned long *)handle); -} - -static inline int trypin_tag(unsigned long handle) -{ - return bit_spin_trylock(HANDLE_PIN_BIT, (unsigned long *)handle); -} + handle = *(unsigned long *)obj; -static void pin_tag(unsigned long handle) __acquires(bitlock) -{ - bit_spin_lock(HANDLE_PIN_BIT, (unsigned long *)handle); -} + if (!(handle & OBJ_ALLOCATED_TAG)) + return false; -static void unpin_tag(unsigned long handle) __releases(bitlock) -{ - bit_spin_unlock(HANDLE_PIN_BIT, (unsigned long *)handle); + *phandle = handle & ~OBJ_ALLOCATED_TAG; + return true; } static void reset_page(struct page *page) @@ -900,7 +893,6 @@ static void reset_page(struct page *page) ClearPagePrivate(page); set_page_private(page, 0); page_mapcount_reset(page); - ClearPageHugeObject(page); page->index = 0; } @@ -952,7 +944,7 @@ static void __free_zspage(struct zs_pool *pool, struct size_class *class, cache_free_zspage(pool, zspage); - zs_stat_dec(class, OBJ_ALLOCATED, class->objs_per_zspage); + class_stat_dec(class, OBJ_ALLOCATED, class->objs_per_zspage); atomic_long_sub(class->pages_per_zspage, &pool->pages_allocated); } @@ -963,6 +955,11 @@ static void free_zspage(struct zs_pool *pool, struct size_class *class, VM_BUG_ON(get_zspage_inuse(zspage)); VM_BUG_ON(list_empty(&zspage->list)); + /* + * Since zs_free couldn't be sleepable, this function cannot call + * lock_page. The page locks trylock_zspage got will be released + * by __free_zspage. + */ if (!trylock_zspage(zspage)) { kick_deferred_free(pool); return; @@ -1042,7 +1039,7 @@ static void create_page_chain(struct size_class *class, struct zspage *zspage, SetPagePrivate(page); if (unlikely(class->objs_per_zspage == 1 && class->pages_per_zspage == 1)) - SetPageHugeObject(page); + SetZsHugePage(zspage); } else { prev_page->index = (unsigned long)page; } @@ -1246,8 +1243,6 @@ void *zs_map_object(struct zs_pool *pool, unsigned long handle, unsigned long obj, off; unsigned int obj_idx; - unsigned int class_idx; - enum fullness_group fg; struct size_class *class; struct mapping_area *area; struct page *pages[2]; @@ -1260,21 +1255,26 @@ void *zs_map_object(struct zs_pool *pool, unsigned long handle, */ BUG_ON(in_interrupt()); - /* From now on, migration cannot move the object */ - pin_tag(handle); - + /* It guarantees it can get zspage from handle safely */ + read_lock(&pool->migrate_lock); obj = handle_to_obj(handle); obj_to_location(obj, &page, &obj_idx); zspage = get_zspage(page); - /* migration cannot move any subpage in this zspage */ + /* + * migration cannot move any zpages in this zspage. Here, class->lock + * is too heavy since callers would take some time until they calls + * zs_unmap_object API so delegate the locking from class to zspage + * which is smaller granularity. + */ migrate_read_lock(zspage); + read_unlock(&pool->migrate_lock); - get_zspage_mapping(zspage, &class_idx, &fg); - class = pool->size_class[class_idx]; + class = zspage_class(pool, zspage); off = (class->size * obj_idx) & ~PAGE_MASK; - area = &get_cpu_var(zs_map_area); + local_lock(&zs_map_area.lock); + area = this_cpu_ptr(&zs_map_area); area->vm_mm = mm; if (off + class->size <= PAGE_SIZE) { /* this object is contained entirely within a page */ @@ -1290,7 +1290,7 @@ void *zs_map_object(struct zs_pool *pool, unsigned long handle, ret = __zs_map_object(area, pages, off, class->size); out: - if (likely(!PageHugeObject(page))) + if (likely(!ZsHugePage(zspage))) ret += ZS_HANDLE_SIZE; return ret; @@ -1304,16 +1304,13 @@ void zs_unmap_object(struct zs_pool *pool, unsigned long handle) unsigned long obj, off; unsigned int obj_idx; - unsigned int class_idx; - enum fullness_group fg; struct size_class *class; struct mapping_area *area; obj = handle_to_obj(handle); obj_to_location(obj, &page, &obj_idx); zspage = get_zspage(page); - get_zspage_mapping(zspage, &class_idx, &fg); - class = pool->size_class[class_idx]; + class = zspage_class(pool, zspage); off = (class->size * obj_idx) & ~PAGE_MASK; area = this_cpu_ptr(&zs_map_area); @@ -1328,10 +1325,9 @@ void zs_unmap_object(struct zs_pool *pool, unsigned long handle) __zs_unmap_object(area, pages, off, class->size); } - put_cpu_var(zs_map_area); + local_unlock(&zs_map_area.lock); migrate_read_unlock(zspage); - unpin_tag(handle); } EXPORT_SYMBOL_GPL(zs_unmap_object); @@ -1354,17 +1350,19 @@ size_t zs_huge_class_size(struct zs_pool *pool) } EXPORT_SYMBOL_GPL(zs_huge_class_size); -static unsigned long obj_malloc(struct size_class *class, +static unsigned long obj_malloc(struct zs_pool *pool, struct zspage *zspage, unsigned long handle) { int i, nr_page, offset; unsigned long obj; struct link_free *link; + struct size_class *class; struct page *m_page; unsigned long m_offset; void *vaddr; + class = pool->size_class[zspage->class]; handle |= OBJ_ALLOCATED_TAG; obj = get_freeobj(zspage); @@ -1379,7 +1377,7 @@ static unsigned long obj_malloc(struct size_class *class, vaddr = kmap_atomic(m_page); link = (struct link_free *)vaddr + m_offset / sizeof(*link); set_freeobj(zspage, link->next >> OBJ_TAG_BITS); - if (likely(!PageHugeObject(m_page))) + if (likely(!ZsHugePage(zspage))) /* record handle in the header of allocated chunk */ link->handle = handle; else @@ -1388,7 +1386,6 @@ static unsigned long obj_malloc(struct size_class *class, kunmap_atomic(vaddr); mod_zspage_inuse(zspage, 1); - zs_stat_inc(class, OBJ_USED, 1); obj = location_to_obj(m_page, obj); @@ -1424,13 +1421,15 @@ unsigned long zs_malloc(struct zs_pool *pool, size_t size, gfp_t gfp) size += ZS_HANDLE_SIZE; class = pool->size_class[get_size_class_index(size)]; + /* class->lock effectively protects the zpage migration */ spin_lock(&class->lock); zspage = find_get_zspage(class); if (likely(zspage)) { - obj = obj_malloc(class, zspage, handle); + obj = obj_malloc(pool, zspage, handle); /* Now move the zspage to another fullness group, if required */ fix_fullness_group(class, zspage); record_obj(handle, obj); + class_stat_inc(class, OBJ_USED, 1); spin_unlock(&class->lock); return handle; @@ -1445,14 +1444,15 @@ unsigned long zs_malloc(struct zs_pool *pool, size_t size, gfp_t gfp) } spin_lock(&class->lock); - obj = obj_malloc(class, zspage, handle); + obj = obj_malloc(pool, zspage, handle); newfg = get_fullness_group(class, zspage); insert_zspage(class, zspage, newfg); set_zspage_mapping(zspage, class->index, newfg); record_obj(handle, obj); atomic_long_add(class->pages_per_zspage, &pool->pages_allocated); - zs_stat_inc(class, OBJ_ALLOCATED, class->objs_per_zspage); + class_stat_inc(class, OBJ_ALLOCATED, class->objs_per_zspage); + class_stat_inc(class, OBJ_USED, 1); /* We completely set up zspage so mark them as movable */ SetZsPageMovable(pool, zspage); @@ -1462,7 +1462,7 @@ unsigned long zs_malloc(struct zs_pool *pool, size_t size, gfp_t gfp) } EXPORT_SYMBOL_GPL(zs_malloc); -static void obj_free(struct size_class *class, unsigned long obj) +static void obj_free(int class_size, unsigned long obj) { struct link_free *link; struct zspage *zspage; @@ -1472,18 +1472,20 @@ static void obj_free(struct size_class *class, unsigned long obj) void *vaddr; obj_to_location(obj, &f_page, &f_objidx); - f_offset = (class->size * f_objidx) & ~PAGE_MASK; + f_offset = (class_size * f_objidx) & ~PAGE_MASK; zspage = get_zspage(f_page); vaddr = kmap_atomic(f_page); /* Insert this object in containing zspage's freelist */ link = (struct link_free *)(vaddr + f_offset); - link->next = get_freeobj(zspage) << OBJ_TAG_BITS; + if (likely(!ZsHugePage(zspage))) + link->next = get_freeobj(zspage) << OBJ_TAG_BITS; + else + f_page->index = 0; kunmap_atomic(vaddr); set_freeobj(zspage, f_objidx); mod_zspage_inuse(zspage, -1); - zs_stat_dec(class, OBJ_USED, 1); } void zs_free(struct zs_pool *pool, unsigned long handle) @@ -1491,42 +1493,33 @@ void zs_free(struct zs_pool *pool, unsigned long handle) struct zspage *zspage; struct page *f_page; unsigned long obj; - unsigned int f_objidx; - int class_idx; struct size_class *class; enum fullness_group fullness; - bool isolated; if (unlikely(!handle)) return; - pin_tag(handle); + /* + * The pool->migrate_lock protects the race with zpage's migration + * so it's safe to get the page from handle. + */ + read_lock(&pool->migrate_lock); obj = handle_to_obj(handle); - obj_to_location(obj, &f_page, &f_objidx); + obj_to_page(obj, &f_page); zspage = get_zspage(f_page); - - migrate_read_lock(zspage); - - get_zspage_mapping(zspage, &class_idx, &fullness); - class = pool->size_class[class_idx]; - + class = zspage_class(pool, zspage); spin_lock(&class->lock); - obj_free(class, obj); + read_unlock(&pool->migrate_lock); + + obj_free(class->size, obj); + class_stat_dec(class, OBJ_USED, 1); fullness = fix_fullness_group(class, zspage); - if (fullness != ZS_EMPTY) { - migrate_read_unlock(zspage); + if (fullness != ZS_EMPTY) goto out; - } - isolated = is_zspage_isolated(zspage); - migrate_read_unlock(zspage); - /* If zspage is isolated, zs_page_putback will free the zspage */ - if (likely(!isolated)) - free_zspage(pool, class, zspage); + free_zspage(pool, class, zspage); out: - spin_unlock(&class->lock); - unpin_tag(handle); cache_free_handle(pool, handle); } EXPORT_SYMBOL_GPL(zs_free); @@ -1601,7 +1594,6 @@ static void zs_object_copy(struct size_class *class, unsigned long dst, static unsigned long find_alloced_obj(struct size_class *class, struct page *page, int *obj_idx) { - unsigned long head; int offset = 0; int index = *obj_idx; unsigned long handle = 0; @@ -1611,13 +1603,8 @@ static unsigned long find_alloced_obj(struct size_class *class, offset += class->size * index; while (offset < PAGE_SIZE) { - head = obj_to_head(page, addr + offset); - if (head & OBJ_ALLOCATED_TAG) { - handle = head & ~OBJ_ALLOCATED_TAG; - if (trypin_tag(handle)) - break; - handle = 0; - } + if (obj_allocated(page, addr + offset, &handle)) + break; offset += class->size; index++; @@ -1663,25 +1650,16 @@ static int migrate_zspage(struct zs_pool *pool, struct size_class *class, /* Stop if there is no more space */ if (zspage_full(class, get_zspage(d_page))) { - unpin_tag(handle); ret = -ENOMEM; break; } used_obj = handle_to_obj(handle); - free_obj = obj_malloc(class, get_zspage(d_page), handle); + free_obj = obj_malloc(pool, get_zspage(d_page), handle); zs_object_copy(class, free_obj, used_obj); obj_idx++; - /* - * record_obj updates handle's value to free_obj and it will - * invalidate lock bit(ie, HANDLE_PIN_BIT) of handle, which - * breaks synchronization using pin_tag(e,g, zs_free) so - * let's keep the lock bit. - */ - free_obj |= BIT(HANDLE_PIN_BIT); record_obj(handle, free_obj); - unpin_tag(handle); - obj_free(class, used_obj); + obj_free(class->size, used_obj); } /* Remember last position in this iteration */ @@ -1706,7 +1684,6 @@ static struct zspage *isolate_zspage(struct size_class *class, bool source) zspage = list_first_entry_or_null(&class->fullness_list[fg[i]], struct zspage, list); if (zspage) { - VM_BUG_ON(is_zspage_isolated(zspage)); remove_zspage(class, zspage, fg[i]); return zspage; } @@ -1727,8 +1704,6 @@ static enum fullness_group putback_zspage(struct size_class *class, { enum fullness_group fullness; - VM_BUG_ON(is_zspage_isolated(zspage)); - fullness = get_fullness_group(class, zspage); insert_zspage(class, zspage, fullness); set_zspage_mapping(zspage, class->index, fullness); @@ -1797,6 +1772,11 @@ static void migrate_write_lock(struct zspage *zspage) write_lock(&zspage->lock); } +static void migrate_write_lock_nested(struct zspage *zspage) +{ + write_lock_nested(&zspage->lock, SINGLE_DEPTH_NESTING); +} + static void migrate_write_unlock(struct zspage *zspage) { write_unlock(&zspage->lock); @@ -1810,35 +1790,10 @@ static void inc_zspage_isolation(struct zspage *zspage) static void dec_zspage_isolation(struct zspage *zspage) { + VM_BUG_ON(zspage->isolated == 0); zspage->isolated--; } -static void putback_zspage_deferred(struct zs_pool *pool, - struct size_class *class, - struct zspage *zspage) -{ - enum fullness_group fg; - - fg = putback_zspage(class, zspage); - if (fg == ZS_EMPTY) - schedule_work(&pool->free_work); - -} - -static inline void zs_pool_dec_isolated(struct zs_pool *pool) -{ - VM_BUG_ON(atomic_long_read(&pool->isolated_pages) <= 0); - atomic_long_dec(&pool->isolated_pages); - /* - * Checking pool->destroying must happen after atomic_long_dec() - * for pool->isolated_pages above. Paired with the smp_mb() in - * zs_unregister_migration(). - */ - smp_mb__after_atomic(); - if (atomic_long_read(&pool->isolated_pages) == 0 && pool->destroying) - wake_up_all(&pool->migration_wait); -} - static void replace_sub_page(struct size_class *class, struct zspage *zspage, struct page *newpage, struct page *oldpage) { @@ -1857,19 +1812,14 @@ static void replace_sub_page(struct size_class *class, struct zspage *zspage, create_page_chain(class, zspage, pages); set_first_obj_offset(newpage, get_first_obj_offset(oldpage)); - if (unlikely(PageHugeObject(oldpage))) + if (unlikely(ZsHugePage(zspage))) newpage->index = oldpage->index; __SetPageMovable(newpage, page_mapping(oldpage)); } static bool zs_page_isolate(struct page *page, isolate_mode_t mode) { - struct zs_pool *pool; - struct size_class *class; - int class_idx; - enum fullness_group fullness; struct zspage *zspage; - struct address_space *mapping; /* * Page is locked so zspage couldn't be destroyed. For detail, look at @@ -1879,41 +1829,9 @@ static bool zs_page_isolate(struct page *page, isolate_mode_t mode) VM_BUG_ON_PAGE(PageIsolated(page), page); zspage = get_zspage(page); - - /* - * Without class lock, fullness could be stale while class_idx is okay - * because class_idx is constant unless page is freed so we should get - * fullness again under class lock. - */ - get_zspage_mapping(zspage, &class_idx, &fullness); - mapping = page_mapping(page); - pool = mapping->private_data; - class = pool->size_class[class_idx]; - - spin_lock(&class->lock); - if (get_zspage_inuse(zspage) == 0) { - spin_unlock(&class->lock); - return false; - } - - /* zspage is isolated for object migration */ - if (list_empty(&zspage->list) && !is_zspage_isolated(zspage)) { - spin_unlock(&class->lock); - return false; - } - - /* - * If this is first time isolation for the zspage, isolate zspage from - * size_class to prevent further object allocation from the zspage. - */ - if (!list_empty(&zspage->list) && !is_zspage_isolated(zspage)) { - get_zspage_mapping(zspage, &class_idx, &fullness); - atomic_long_inc(&pool->isolated_pages); - remove_zspage(class, zspage, fullness); - } - + migrate_write_lock(zspage); inc_zspage_isolation(zspage); - spin_unlock(&class->lock); + migrate_write_unlock(zspage); return true; } @@ -1923,16 +1841,13 @@ static int zs_page_migrate(struct address_space *mapping, struct page *newpage, { struct zs_pool *pool; struct size_class *class; - int class_idx; - enum fullness_group fullness; struct zspage *zspage; struct page *dummy; void *s_addr, *d_addr, *addr; - int offset, pos; - unsigned long handle, head; + int offset; + unsigned long handle; unsigned long old_obj, new_obj; unsigned int obj_idx; - int ret = -EAGAIN; /* * We cannot support the _NO_COPY case here, because copy needs to @@ -1945,35 +1860,25 @@ static int zs_page_migrate(struct address_space *mapping, struct page *newpage, VM_BUG_ON_PAGE(!PageMovable(page), page); VM_BUG_ON_PAGE(!PageIsolated(page), page); - zspage = get_zspage(page); - - /* Concurrent compactor cannot migrate any subpage in zspage */ - migrate_write_lock(zspage); - get_zspage_mapping(zspage, &class_idx, &fullness); pool = mapping->private_data; - class = pool->size_class[class_idx]; - offset = get_first_obj_offset(page); + /* + * The pool migrate_lock protects the race between zpage migration + * and zs_free. + */ + write_lock(&pool->migrate_lock); + zspage = get_zspage(page); + class = zspage_class(pool, zspage); + + /* + * the class lock protects zpage alloc/free in the zspage. + */ spin_lock(&class->lock); - if (!get_zspage_inuse(zspage)) { - /* - * Set "offset" to end of the page so that every loops - * skips unnecessary object scanning. - */ - offset = PAGE_SIZE; - } + /* the migrate_write_lock protects zpage access via zs_map_object */ + migrate_write_lock(zspage); - pos = offset; + offset = get_first_obj_offset(page); s_addr = kmap_atomic(page); - while (pos < PAGE_SIZE) { - head = obj_to_head(page, s_addr + pos); - if (head & OBJ_ALLOCATED_TAG) { - handle = head & ~OBJ_ALLOCATED_TAG; - if (!trypin_tag(handle)) - goto unpin_objects; - } - pos += class->size; - } /* * Here, any user cannot access all objects in the zspage so let's move. @@ -1982,42 +1887,30 @@ static int zs_page_migrate(struct address_space *mapping, struct page *newpage, memcpy(d_addr, s_addr, PAGE_SIZE); kunmap_atomic(d_addr); - for (addr = s_addr + offset; addr < s_addr + pos; + for (addr = s_addr + offset; addr < s_addr + PAGE_SIZE; addr += class->size) { - head = obj_to_head(page, addr); - if (head & OBJ_ALLOCATED_TAG) { - handle = head & ~OBJ_ALLOCATED_TAG; - BUG_ON(!testpin_tag(handle)); + if (obj_allocated(page, addr, &handle)) { old_obj = handle_to_obj(handle); obj_to_location(old_obj, &dummy, &obj_idx); new_obj = (unsigned long)location_to_obj(newpage, obj_idx); - new_obj |= BIT(HANDLE_PIN_BIT); record_obj(handle, new_obj); } } + kunmap_atomic(s_addr); replace_sub_page(class, zspage, newpage, page); - get_page(newpage); - - dec_zspage_isolation(zspage); - /* - * Page migration is done so let's putback isolated zspage to - * the list if @page is final isolated subpage in the zspage. + * Since we complete the data copy and set up new zspage structure, + * it's okay to release migration_lock. */ - if (!is_zspage_isolated(zspage)) { - /* - * We cannot race with zs_destroy_pool() here because we wait - * for isolation to hit zero before we start destroying. - * Also, we ensure that everyone can see pool->destroying before - * we start waiting. - */ - putback_zspage_deferred(pool, class, zspage); - zs_pool_dec_isolated(pool); - } + write_unlock(&pool->migrate_lock); + spin_unlock(&class->lock); + dec_zspage_isolation(zspage); + migrate_write_unlock(zspage); + get_page(newpage); if (page_zone(newpage) != page_zone(page)) { dec_zone_page_state(page, NR_ZSPAGES); inc_zone_page_state(newpage, NR_ZSPAGES); @@ -2025,55 +1918,21 @@ static int zs_page_migrate(struct address_space *mapping, struct page *newpage, reset_page(page); put_page(page); - page = newpage; - - ret = MIGRATEPAGE_SUCCESS; -unpin_objects: - for (addr = s_addr + offset; addr < s_addr + pos; - addr += class->size) { - head = obj_to_head(page, addr); - if (head & OBJ_ALLOCATED_TAG) { - handle = head & ~OBJ_ALLOCATED_TAG; - BUG_ON(!testpin_tag(handle)); - unpin_tag(handle); - } - } - kunmap_atomic(s_addr); - spin_unlock(&class->lock); - migrate_write_unlock(zspage); - return ret; + return MIGRATEPAGE_SUCCESS; } static void zs_page_putback(struct page *page) { - struct zs_pool *pool; - struct size_class *class; - int class_idx; - enum fullness_group fg; - struct address_space *mapping; struct zspage *zspage; VM_BUG_ON_PAGE(!PageMovable(page), page); VM_BUG_ON_PAGE(!PageIsolated(page), page); zspage = get_zspage(page); - get_zspage_mapping(zspage, &class_idx, &fg); - mapping = page_mapping(page); - pool = mapping->private_data; - class = pool->size_class[class_idx]; - - spin_lock(&class->lock); + migrate_write_lock(zspage); dec_zspage_isolation(zspage); - if (!is_zspage_isolated(zspage)) { - /* - * Due to page_lock, we cannot free zspage immediately - * so let's defer. - */ - putback_zspage_deferred(pool, class, zspage); - zs_pool_dec_isolated(pool); - } - spin_unlock(&class->lock); + migrate_write_unlock(zspage); } static const struct address_space_operations zsmalloc_aops = { @@ -2095,36 +1954,8 @@ static int zs_register_migration(struct zs_pool *pool) return 0; } -static bool pool_isolated_are_drained(struct zs_pool *pool) -{ - return atomic_long_read(&pool->isolated_pages) == 0; -} - -/* Function for resolving migration */ -static void wait_for_isolated_drain(struct zs_pool *pool) -{ - - /* - * We're in the process of destroying the pool, so there are no - * active allocations. zs_page_isolate() fails for completely free - * zspages, so we need only wait for the zs_pool's isolated - * count to hit zero. - */ - wait_event(pool->migration_wait, - pool_isolated_are_drained(pool)); -} - static void zs_unregister_migration(struct zs_pool *pool) { - pool->destroying = true; - /* - * We need a memory barrier here to ensure global visibility of - * pool->destroying. Thus pool->isolated pages will either be 0 in which - * case we don't care, or it will be > 0 and pool->destroying will - * ensure that we wake up once isolation hits 0. - */ - smp_mb(); - wait_for_isolated_drain(pool); /* This can block */ flush_work(&pool->free_work); iput(pool->inode); } @@ -2154,7 +1985,6 @@ static void async_free_zspage(struct work_struct *work) spin_unlock(&class->lock); } - list_for_each_entry_safe(zspage, tmp, &free_pages, list) { list_del(&zspage->list); lock_zspage(zspage); @@ -2218,8 +2048,13 @@ static unsigned long __zs_compact(struct zs_pool *pool, struct zspage *dst_zspage = NULL; unsigned long pages_freed = 0; + /* protect the race between zpage migration and zs_free */ + write_lock(&pool->migrate_lock); + /* protect zpage allocation/free */ spin_lock(&class->lock); while ((src_zspage = isolate_zspage(class, true))) { + /* protect someone accessing the zspage(i.e., zs_map_object) */ + migrate_write_lock(src_zspage); if (!zs_can_compact(class)) break; @@ -2228,6 +2063,8 @@ static unsigned long __zs_compact(struct zs_pool *pool, cc.s_page = get_first_page(src_zspage); while ((dst_zspage = isolate_zspage(class, false))) { + migrate_write_lock_nested(dst_zspage); + cc.d_page = get_first_page(dst_zspage); /* * If there is no more space in dst_page, resched @@ -2237,6 +2074,10 @@ static unsigned long __zs_compact(struct zs_pool *pool, break; putback_zspage(class, dst_zspage); + migrate_write_unlock(dst_zspage); + dst_zspage = NULL; + if (rwlock_is_contended(&pool->migrate_lock)) + break; } /* Stop if we couldn't find slot */ @@ -2244,19 +2085,28 @@ static unsigned long __zs_compact(struct zs_pool *pool, break; putback_zspage(class, dst_zspage); + migrate_write_unlock(dst_zspage); + if (putback_zspage(class, src_zspage) == ZS_EMPTY) { + migrate_write_unlock(src_zspage); free_zspage(pool, class, src_zspage); pages_freed += class->pages_per_zspage; - } + } else + migrate_write_unlock(src_zspage); spin_unlock(&class->lock); + write_unlock(&pool->migrate_lock); cond_resched(); + write_lock(&pool->migrate_lock); spin_lock(&class->lock); } - if (src_zspage) + if (src_zspage) { putback_zspage(class, src_zspage); + migrate_write_unlock(src_zspage); + } spin_unlock(&class->lock); + write_unlock(&pool->migrate_lock); return pages_freed; } @@ -2362,15 +2212,12 @@ struct zs_pool *zs_create_pool(const char *name) return NULL; init_deferred_free(pool); + rwlock_init(&pool->migrate_lock); pool->name = kstrdup(name, GFP_KERNEL); if (!pool->name) goto err; -#ifdef CONFIG_COMPACTION - init_waitqueue_head(&pool->migration_wait); -#endif - if (create_cache(pool)) goto err; diff --git a/mm/zswap.c b/mm/zswap.c index 7944e3e57e78..cdf6950fcb2e 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -1378,7 +1378,7 @@ static void zswap_frontswap_init(unsigned type) zswap_trees[type] = tree; } -static struct frontswap_ops zswap_frontswap_ops = { +static const struct frontswap_ops zswap_frontswap_ops = { .store = zswap_frontswap_store, .load = zswap_frontswap_load, .invalidate_page = zswap_frontswap_invalidate_page, @@ -1475,11 +1475,15 @@ static int __init init_zswap(void) if (!shrink_wq) goto fallback_fail; - frontswap_register_ops(&zswap_frontswap_ops); + ret = frontswap_register_ops(&zswap_frontswap_ops); + if (ret) + goto destroy_wq; if (zswap_debugfs_init()) pr_warn("debugfs initialization failed\n"); return 0; +destroy_wq: + destroy_workqueue(shrink_wq); fallback_fail: if (pool) zswap_pool_destroy(pool); diff --git a/net/atm/proc.c b/net/atm/proc.c index 4369ffa3302a..9bf736290e48 100644 --- a/net/atm/proc.c +++ b/net/atm/proc.c @@ -108,7 +108,7 @@ out: static inline void *vcc_walk(struct seq_file *seq, loff_t l) { struct vcc_state *state = seq->private; - int family = (uintptr_t)(PDE_DATA(file_inode(seq->file))); + int family = (uintptr_t)(pde_data(file_inode(seq->file))); return __vcc_walk(&state->sk, family, &state->bucket, l) ? state : NULL; @@ -324,7 +324,7 @@ static ssize_t proc_dev_atm_read(struct file *file, char __user *buf, page = get_zeroed_page(GFP_KERNEL); if (!page) return -ENOMEM; - dev = PDE_DATA(file_inode(file)); + dev = pde_data(file_inode(file)); if (!dev->ops->proc_read) length = -EINVAL; else { diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c index 1661979b6a6e..ee319779781e 100644 --- a/net/bluetooth/af_bluetooth.c +++ b/net/bluetooth/af_bluetooth.c @@ -611,7 +611,7 @@ EXPORT_SYMBOL(bt_sock_wait_ready); static void *bt_seq_start(struct seq_file *seq, loff_t *pos) __acquires(seq->private->l->lock) { - struct bt_sock_list *l = PDE_DATA(file_inode(seq->file)); + struct bt_sock_list *l = pde_data(file_inode(seq->file)); read_lock(&l->lock); return seq_hlist_start_head(&l->head, *pos); @@ -619,7 +619,7 @@ static void *bt_seq_start(struct seq_file *seq, loff_t *pos) static void *bt_seq_next(struct seq_file *seq, void *v, loff_t *pos) { - struct bt_sock_list *l = PDE_DATA(file_inode(seq->file)); + struct bt_sock_list *l = pde_data(file_inode(seq->file)); return seq_hlist_next(v, &l->head, pos); } @@ -627,14 +627,14 @@ static void *bt_seq_next(struct seq_file *seq, void *v, loff_t *pos) static void bt_seq_stop(struct seq_file *seq, void *v) __releases(seq->private->l->lock) { - struct bt_sock_list *l = PDE_DATA(file_inode(seq->file)); + struct bt_sock_list *l = pde_data(file_inode(seq->file)); read_unlock(&l->lock); } static int bt_seq_show(struct seq_file *seq, void *v) { - struct bt_sock_list *l = PDE_DATA(file_inode(seq->file)); + struct bt_sock_list *l = pde_data(file_inode(seq->file)); if (v == SEQ_START_TOKEN) { seq_puts(seq, "sk RefCnt Rmem Wmem User Inode Parent"); diff --git a/net/can/bcm.c b/net/can/bcm.c index bc88d901a1c0..95d209b52e6a 100644 --- a/net/can/bcm.c +++ b/net/can/bcm.c @@ -193,7 +193,7 @@ static int bcm_proc_show(struct seq_file *m, void *v) { char ifname[IFNAMSIZ]; struct net *net = m->private; - struct sock *sk = (struct sock *)PDE_DATA(m->file->f_inode); + struct sock *sk = (struct sock *)pde_data(m->file->f_inode); struct bcm_sock *bo = bcm_sk(sk); struct bcm_op *op; diff --git a/net/can/proc.c b/net/can/proc.c index b3099f0a3cb8..bbce97825f13 100644 --- a/net/can/proc.c +++ b/net/can/proc.c @@ -305,7 +305,7 @@ static inline void can_rcvlist_proc_show_one(struct seq_file *m, int idx, static int can_rcvlist_proc_show(struct seq_file *m, void *v) { /* double cast to prevent GCC warning */ - int idx = (int)(long)PDE_DATA(m->file->f_inode); + int idx = (int)(long)pde_data(m->file->f_inode); struct net_device *dev; struct can_dev_rcv_lists *dev_rcv_lists; struct net *net = m->private; diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 213cb7b26b7a..6c2016f7f3d1 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -3364,7 +3364,7 @@ EXPORT_SYMBOL(neigh_seq_stop); static void *neigh_stat_seq_start(struct seq_file *seq, loff_t *pos) { - struct neigh_table *tbl = PDE_DATA(file_inode(seq->file)); + struct neigh_table *tbl = pde_data(file_inode(seq->file)); int cpu; if (*pos == 0) @@ -3381,7 +3381,7 @@ static void *neigh_stat_seq_start(struct seq_file *seq, loff_t *pos) static void *neigh_stat_seq_next(struct seq_file *seq, void *v, loff_t *pos) { - struct neigh_table *tbl = PDE_DATA(file_inode(seq->file)); + struct neigh_table *tbl = pde_data(file_inode(seq->file)); int cpu; for (cpu = *pos; cpu < nr_cpu_ids; ++cpu) { @@ -3401,7 +3401,7 @@ static void neigh_stat_seq_stop(struct seq_file *seq, void *v) static int neigh_stat_seq_show(struct seq_file *seq, void *v) { - struct neigh_table *tbl = PDE_DATA(file_inode(seq->file)); + struct neigh_table *tbl = pde_data(file_inode(seq->file)); struct neigh_statistics *st = v; if (v == SEQ_START_TOKEN) { diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 560a5e712dc3..84b62cd7bc57 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -546,7 +546,7 @@ static ssize_t pgctrl_write(struct file *file, const char __user *buf, static int pgctrl_open(struct inode *inode, struct file *file) { - return single_open(file, pgctrl_show, PDE_DATA(inode)); + return single_open(file, pgctrl_show, pde_data(inode)); } static const struct proc_ops pktgen_proc_ops = { @@ -1811,7 +1811,7 @@ static ssize_t pktgen_if_write(struct file *file, static int pktgen_if_open(struct inode *inode, struct file *file) { - return single_open(file, pktgen_if_show, PDE_DATA(inode)); + return single_open(file, pktgen_if_show, pde_data(inode)); } static const struct proc_ops pktgen_if_proc_ops = { @@ -1948,7 +1948,7 @@ out: static int pktgen_thread_open(struct inode *inode, struct file *file) { - return single_open(file, pktgen_thread_show, PDE_DATA(inode)); + return single_open(file, pktgen_thread_show, pde_data(inode)); } static const struct proc_ops pktgen_thread_proc_ops = { diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c index b518f20c9a24..f8e176c77d1c 100644 --- a/net/ipv4/netfilter/ipt_CLUSTERIP.c +++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c @@ -776,7 +776,7 @@ static int clusterip_proc_open(struct inode *inode, struct file *file) if (!ret) { struct seq_file *sf = file->private_data; - struct clusterip_config *c = PDE_DATA(inode); + struct clusterip_config *c = pde_data(inode); sf->private = c; @@ -788,7 +788,7 @@ static int clusterip_proc_open(struct inode *inode, struct file *file) static int clusterip_proc_release(struct inode *inode, struct file *file) { - struct clusterip_config *c = PDE_DATA(inode); + struct clusterip_config *c = pde_data(inode); int ret; ret = seq_release(inode, file); @@ -802,7 +802,7 @@ static int clusterip_proc_release(struct inode *inode, struct file *file) static ssize_t clusterip_proc_write(struct file *file, const char __user *input, size_t size, loff_t *ofs) { - struct clusterip_config *c = PDE_DATA(file_inode(file)); + struct clusterip_config *c = pde_data(file_inode(file)); #define PROC_WRITELEN 10 char buffer[PROC_WRITELEN+1]; unsigned long nodenum; diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index a53f256bf9d3..9eb5fc247868 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -971,7 +971,7 @@ struct proto raw_prot = { static struct sock *raw_get_first(struct seq_file *seq) { struct sock *sk; - struct raw_hashinfo *h = PDE_DATA(file_inode(seq->file)); + struct raw_hashinfo *h = pde_data(file_inode(seq->file)); struct raw_iter_state *state = raw_seq_private(seq); for (state->bucket = 0; state->bucket < RAW_HTABLE_SIZE; @@ -987,7 +987,7 @@ found: static struct sock *raw_get_next(struct seq_file *seq, struct sock *sk) { - struct raw_hashinfo *h = PDE_DATA(file_inode(seq->file)); + struct raw_hashinfo *h = pde_data(file_inode(seq->file)); struct raw_iter_state *state = raw_seq_private(seq); do { @@ -1016,7 +1016,7 @@ static struct sock *raw_get_idx(struct seq_file *seq, loff_t pos) void *raw_seq_start(struct seq_file *seq, loff_t *pos) __acquires(&h->lock) { - struct raw_hashinfo *h = PDE_DATA(file_inode(seq->file)); + struct raw_hashinfo *h = pde_data(file_inode(seq->file)); read_lock(&h->lock); return *pos ? raw_get_idx(seq, *pos - 1) : SEQ_START_TOKEN; @@ -1039,7 +1039,7 @@ EXPORT_SYMBOL_GPL(raw_seq_next); void raw_seq_stop(struct seq_file *seq, void *v) __releases(&h->lock) { - struct raw_hashinfo *h = PDE_DATA(file_inode(seq->file)); + struct raw_hashinfo *h = pde_data(file_inode(seq->file)); read_unlock(&h->lock); } diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index b3f34e366b27..b53476e78c84 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -3002,7 +3002,7 @@ static unsigned short seq_file_family(const struct seq_file *seq) #endif /* Iterated from proc fs */ - afinfo = PDE_DATA(file_inode(seq->file)); + afinfo = pde_data(file_inode(seq->file)); return afinfo->family; } diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 464590ea922e..090360939401 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -2960,7 +2960,7 @@ static struct sock *udp_get_first(struct seq_file *seq, int start) if (state->bpf_seq_afinfo) afinfo = state->bpf_seq_afinfo; else - afinfo = PDE_DATA(file_inode(seq->file)); + afinfo = pde_data(file_inode(seq->file)); for (state->bucket = start; state->bucket <= afinfo->udp_table->mask; ++state->bucket) { @@ -2993,7 +2993,7 @@ static struct sock *udp_get_next(struct seq_file *seq, struct sock *sk) if (state->bpf_seq_afinfo) afinfo = state->bpf_seq_afinfo; else - afinfo = PDE_DATA(file_inode(seq->file)); + afinfo = pde_data(file_inode(seq->file)); do { sk = sk_next(sk); @@ -3050,7 +3050,7 @@ void udp_seq_stop(struct seq_file *seq, void *v) if (state->bpf_seq_afinfo) afinfo = state->bpf_seq_afinfo; else - afinfo = PDE_DATA(file_inode(seq->file)); + afinfo = pde_data(file_inode(seq->file)); if (state->bucket <= afinfo->udp_table->mask) spin_unlock_bh(&afinfo->udp_table->hash[state->bucket].lock); diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index 25524e393349..54a489f16b17 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -1517,7 +1517,7 @@ EXPORT_SYMBOL_GPL(xt_unregister_table); #ifdef CONFIG_PROC_FS static void *xt_table_seq_start(struct seq_file *seq, loff_t *pos) { - u8 af = (unsigned long)PDE_DATA(file_inode(seq->file)); + u8 af = (unsigned long)pde_data(file_inode(seq->file)); struct net *net = seq_file_net(seq); struct xt_pernet *xt_net; @@ -1529,7 +1529,7 @@ static void *xt_table_seq_start(struct seq_file *seq, loff_t *pos) static void *xt_table_seq_next(struct seq_file *seq, void *v, loff_t *pos) { - u8 af = (unsigned long)PDE_DATA(file_inode(seq->file)); + u8 af = (unsigned long)pde_data(file_inode(seq->file)); struct net *net = seq_file_net(seq); struct xt_pernet *xt_net; @@ -1540,7 +1540,7 @@ static void *xt_table_seq_next(struct seq_file *seq, void *v, loff_t *pos) static void xt_table_seq_stop(struct seq_file *seq, void *v) { - u_int8_t af = (unsigned long)PDE_DATA(file_inode(seq->file)); + u_int8_t af = (unsigned long)pde_data(file_inode(seq->file)); mutex_unlock(&xt[af].mutex); } @@ -1584,7 +1584,7 @@ static void *xt_mttg_seq_next(struct seq_file *seq, void *v, loff_t *ppos, [MTTG_TRAV_NFP_UNSPEC] = MTTG_TRAV_NFP_SPEC, [MTTG_TRAV_NFP_SPEC] = MTTG_TRAV_DONE, }; - uint8_t nfproto = (unsigned long)PDE_DATA(file_inode(seq->file)); + uint8_t nfproto = (unsigned long)pde_data(file_inode(seq->file)); struct nf_mttg_trav *trav = seq->private; if (ppos != NULL) @@ -1633,7 +1633,7 @@ static void *xt_mttg_seq_start(struct seq_file *seq, loff_t *pos, static void xt_mttg_seq_stop(struct seq_file *seq, void *v) { - uint8_t nfproto = (unsigned long)PDE_DATA(file_inode(seq->file)); + uint8_t nfproto = (unsigned long)pde_data(file_inode(seq->file)); struct nf_mttg_trav *trav = seq->private; switch (trav->class) { diff --git a/net/netfilter/xt_hashlimit.c b/net/netfilter/xt_hashlimit.c index 9c5cfd74a0ee..0859b8f76764 100644 --- a/net/netfilter/xt_hashlimit.c +++ b/net/netfilter/xt_hashlimit.c @@ -1052,7 +1052,7 @@ static struct xt_match hashlimit_mt_reg[] __read_mostly = { static void *dl_seq_start(struct seq_file *s, loff_t *pos) __acquires(htable->lock) { - struct xt_hashlimit_htable *htable = PDE_DATA(file_inode(s->file)); + struct xt_hashlimit_htable *htable = pde_data(file_inode(s->file)); unsigned int *bucket; spin_lock_bh(&htable->lock); @@ -1069,7 +1069,7 @@ static void *dl_seq_start(struct seq_file *s, loff_t *pos) static void *dl_seq_next(struct seq_file *s, void *v, loff_t *pos) { - struct xt_hashlimit_htable *htable = PDE_DATA(file_inode(s->file)); + struct xt_hashlimit_htable *htable = pde_data(file_inode(s->file)); unsigned int *bucket = v; *pos = ++(*bucket); @@ -1083,7 +1083,7 @@ static void *dl_seq_next(struct seq_file *s, void *v, loff_t *pos) static void dl_seq_stop(struct seq_file *s, void *v) __releases(htable->lock) { - struct xt_hashlimit_htable *htable = PDE_DATA(file_inode(s->file)); + struct xt_hashlimit_htable *htable = pde_data(file_inode(s->file)); unsigned int *bucket = v; if (!IS_ERR(bucket)) @@ -1125,7 +1125,7 @@ static void dl_seq_print(struct dsthash_ent *ent, u_int8_t family, static int dl_seq_real_show_v2(struct dsthash_ent *ent, u_int8_t family, struct seq_file *s) { - struct xt_hashlimit_htable *ht = PDE_DATA(file_inode(s->file)); + struct xt_hashlimit_htable *ht = pde_data(file_inode(s->file)); spin_lock(&ent->lock); /* recalculate to show accurate numbers */ @@ -1140,7 +1140,7 @@ static int dl_seq_real_show_v2(struct dsthash_ent *ent, u_int8_t family, static int dl_seq_real_show_v1(struct dsthash_ent *ent, u_int8_t family, struct seq_file *s) { - struct xt_hashlimit_htable *ht = PDE_DATA(file_inode(s->file)); + struct xt_hashlimit_htable *ht = pde_data(file_inode(s->file)); spin_lock(&ent->lock); /* recalculate to show accurate numbers */ @@ -1155,7 +1155,7 @@ static int dl_seq_real_show_v1(struct dsthash_ent *ent, u_int8_t family, static int dl_seq_real_show(struct dsthash_ent *ent, u_int8_t family, struct seq_file *s) { - struct xt_hashlimit_htable *ht = PDE_DATA(file_inode(s->file)); + struct xt_hashlimit_htable *ht = pde_data(file_inode(s->file)); spin_lock(&ent->lock); /* recalculate to show accurate numbers */ @@ -1169,7 +1169,7 @@ static int dl_seq_real_show(struct dsthash_ent *ent, u_int8_t family, static int dl_seq_show_v2(struct seq_file *s, void *v) { - struct xt_hashlimit_htable *htable = PDE_DATA(file_inode(s->file)); + struct xt_hashlimit_htable *htable = pde_data(file_inode(s->file)); unsigned int *bucket = (unsigned int *)v; struct dsthash_ent *ent; @@ -1183,7 +1183,7 @@ static int dl_seq_show_v2(struct seq_file *s, void *v) static int dl_seq_show_v1(struct seq_file *s, void *v) { - struct xt_hashlimit_htable *htable = PDE_DATA(file_inode(s->file)); + struct xt_hashlimit_htable *htable = pde_data(file_inode(s->file)); unsigned int *bucket = v; struct dsthash_ent *ent; @@ -1197,7 +1197,7 @@ static int dl_seq_show_v1(struct seq_file *s, void *v) static int dl_seq_show(struct seq_file *s, void *v) { - struct xt_hashlimit_htable *htable = PDE_DATA(file_inode(s->file)); + struct xt_hashlimit_htable *htable = pde_data(file_inode(s->file)); unsigned int *bucket = v; struct dsthash_ent *ent; diff --git a/net/netfilter/xt_recent.c b/net/netfilter/xt_recent.c index 0446307516cd..7ddb9a78e3fc 100644 --- a/net/netfilter/xt_recent.c +++ b/net/netfilter/xt_recent.c @@ -551,7 +551,7 @@ static int recent_seq_open(struct inode *inode, struct file *file) if (st == NULL) return -ENOMEM; - st->table = PDE_DATA(inode); + st->table = pde_data(inode); return 0; } @@ -559,7 +559,7 @@ static ssize_t recent_mt_proc_write(struct file *file, const char __user *input, size_t size, loff_t *loff) { - struct recent_table *t = PDE_DATA(file_inode(file)); + struct recent_table *t = pde_data(file_inode(file)); struct recent_entry *e; char buf[sizeof("+b335:1d35:1e55:dead:c0de:1715:5afe:c0de")]; const char *c = buf; diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c index b87565b64928..c2ba9d4cd2c7 100644 --- a/net/sunrpc/auth_gss/svcauth_gss.c +++ b/net/sunrpc/auth_gss/svcauth_gss.c @@ -1433,7 +1433,7 @@ static bool use_gss_proxy(struct net *net) static ssize_t write_gssp(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { - struct net *net = PDE_DATA(file_inode(file)); + struct net *net = pde_data(file_inode(file)); char tbuf[20]; unsigned long i; int res; @@ -1461,7 +1461,7 @@ static ssize_t write_gssp(struct file *file, const char __user *buf, static ssize_t read_gssp(struct file *file, char __user *buf, size_t count, loff_t *ppos) { - struct net *net = PDE_DATA(file_inode(file)); + struct net *net = pde_data(file_inode(file)); struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); unsigned long p = *ppos; char tbuf[10]; diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c index 59641803472c..bb1177395b99 100644 --- a/net/sunrpc/cache.c +++ b/net/sunrpc/cache.c @@ -1536,7 +1536,7 @@ static ssize_t write_flush(struct file *file, const char __user *buf, static ssize_t cache_read_procfs(struct file *filp, char __user *buf, size_t count, loff_t *ppos) { - struct cache_detail *cd = PDE_DATA(file_inode(filp)); + struct cache_detail *cd = pde_data(file_inode(filp)); return cache_read(filp, buf, count, ppos, cd); } @@ -1544,14 +1544,14 @@ static ssize_t cache_read_procfs(struct file *filp, char __user *buf, static ssize_t cache_write_procfs(struct file *filp, const char __user *buf, size_t count, loff_t *ppos) { - struct cache_detail *cd = PDE_DATA(file_inode(filp)); + struct cache_detail *cd = pde_data(file_inode(filp)); return cache_write(filp, buf, count, ppos, cd); } static __poll_t cache_poll_procfs(struct file *filp, poll_table *wait) { - struct cache_detail *cd = PDE_DATA(file_inode(filp)); + struct cache_detail *cd = pde_data(file_inode(filp)); return cache_poll(filp, wait, cd); } @@ -1560,21 +1560,21 @@ static long cache_ioctl_procfs(struct file *filp, unsigned int cmd, unsigned long arg) { struct inode *inode = file_inode(filp); - struct cache_detail *cd = PDE_DATA(inode); + struct cache_detail *cd = pde_data(inode); return cache_ioctl(inode, filp, cmd, arg, cd); } static int cache_open_procfs(struct inode *inode, struct file *filp) { - struct cache_detail *cd = PDE_DATA(inode); + struct cache_detail *cd = pde_data(inode); return cache_open(inode, filp, cd); } static int cache_release_procfs(struct inode *inode, struct file *filp) { - struct cache_detail *cd = PDE_DATA(inode); + struct cache_detail *cd = pde_data(inode); return cache_release(inode, filp, cd); } @@ -1591,14 +1591,14 @@ static const struct proc_ops cache_channel_proc_ops = { static int content_open_procfs(struct inode *inode, struct file *filp) { - struct cache_detail *cd = PDE_DATA(inode); + struct cache_detail *cd = pde_data(inode); return content_open(inode, filp, cd); } static int content_release_procfs(struct inode *inode, struct file *filp) { - struct cache_detail *cd = PDE_DATA(inode); + struct cache_detail *cd = pde_data(inode); return content_release(inode, filp, cd); } @@ -1612,14 +1612,14 @@ static const struct proc_ops content_proc_ops = { static int open_flush_procfs(struct inode *inode, struct file *filp) { - struct cache_detail *cd = PDE_DATA(inode); + struct cache_detail *cd = pde_data(inode); return open_flush(inode, filp, cd); } static int release_flush_procfs(struct inode *inode, struct file *filp) { - struct cache_detail *cd = PDE_DATA(inode); + struct cache_detail *cd = pde_data(inode); return release_flush(inode, filp, cd); } @@ -1627,7 +1627,7 @@ static int release_flush_procfs(struct inode *inode, struct file *filp) static ssize_t read_flush_procfs(struct file *filp, char __user *buf, size_t count, loff_t *ppos) { - struct cache_detail *cd = PDE_DATA(file_inode(filp)); + struct cache_detail *cd = pde_data(file_inode(filp)); return read_flush(filp, buf, count, ppos, cd); } @@ -1636,7 +1636,7 @@ static ssize_t write_flush_procfs(struct file *filp, const char __user *buf, size_t count, loff_t *ppos) { - struct cache_detail *cd = PDE_DATA(file_inode(filp)); + struct cache_detail *cd = pde_data(file_inode(filp)); return write_flush(filp, buf, count, ppos, cd); } diff --git a/net/sunrpc/stats.c b/net/sunrpc/stats.c index c964b48eaaba..52908f9e6eab 100644 --- a/net/sunrpc/stats.c +++ b/net/sunrpc/stats.c @@ -66,7 +66,7 @@ static int rpc_proc_show(struct seq_file *seq, void *v) { static int rpc_proc_open(struct inode *inode, struct file *file) { - return single_open(file, rpc_proc_show, PDE_DATA(inode)); + return single_open(file, rpc_proc_show, pde_data(inode)); } static const struct proc_ops rpc_proc_ops = { diff --git a/sound/core/info.c b/sound/core/info.c index a451b24199c3..782fba87cc04 100644 --- a/sound/core/info.c +++ b/sound/core/info.c @@ -234,7 +234,7 @@ static int snd_info_entry_mmap(struct file *file, struct vm_area_struct *vma) static int snd_info_entry_open(struct inode *inode, struct file *file) { - struct snd_info_entry *entry = PDE_DATA(inode); + struct snd_info_entry *entry = pde_data(inode); struct snd_info_private_data *data; int mode, err; @@ -365,7 +365,7 @@ static int snd_info_seq_show(struct seq_file *seq, void *p) static int snd_info_text_entry_open(struct inode *inode, struct file *file) { - struct snd_info_entry *entry = PDE_DATA(inode); + struct snd_info_entry *entry = pde_data(inode); struct snd_info_private_data *data; int err; |