diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2017-09-06 20:49:49 -0700 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2017-09-06 20:49:49 -0700 |
| commit | d34fc1adf01ff87026da85fb972dc259dc347540 (patch) | |
| tree | 27356073d423187157b7cdb69da32b53102fb9e7 | |
| parent | 1c9fe4409ce3e9c78b1ed96ee8ed699d4f03bf33 (diff) | |
| parent | d2cd9ede6e193dd7d88b6d27399e96229a551b19 (diff) | |
| download | op-kernel-dev-d34fc1adf01ff87026da85fb972dc259dc347540.zip op-kernel-dev-d34fc1adf01ff87026da85fb972dc259dc347540.tar.gz | |
Merge branch 'akpm' (patches from Andrew)
Merge updates from Andrew Morton:
- various misc bits
- DAX updates
- OCFS2
- most of MM
* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (119 commits)
mm,fork: introduce MADV_WIPEONFORK
x86,mpx: make mpx depend on x86-64 to free up VMA flag
mm: add /proc/pid/smaps_rollup
mm: hugetlb: clear target sub-page last when clearing huge page
mm: oom: let oom_reap_task and exit_mmap run concurrently
swap: choose swap device according to numa node
mm: replace TIF_MEMDIE checks by tsk_is_oom_victim
mm, oom: do not rely on TIF_MEMDIE for memory reserves access
z3fold: use per-cpu unbuddied lists
mm, swap: don't use VMA based swap readahead if HDD is used as swap
mm, swap: add sysfs interface for VMA based swap readahead
mm, swap: VMA based swap readahead
mm, swap: fix swap readahead marking
mm, swap: add swap readahead hit statistics
mm/vmalloc.c: don't reinvent the wheel but use existing llist API
mm/vmstat.c: fix wrong comment
selftests/memfd: add memfd_create hugetlbfs selftest
mm/shmem: add hugetlbfs support to memfd_create()
mm, devm_memremap_pages: use multi-order radix for ZONE_DEVICE lookups
mm/vmalloc.c: halve the number of comparisons performed in pcpu_get_vm_areas()
...
139 files changed, 3960 insertions, 2068 deletions
diff --git a/Documentation/ABI/testing/procfs-smaps_rollup b/Documentation/ABI/testing/procfs-smaps_rollup new file mode 100644 index 0000000..0a54ed0 --- /dev/null +++ b/Documentation/ABI/testing/procfs-smaps_rollup @@ -0,0 +1,31 @@ +What: /proc/pid/smaps_rollup +Date: August 2017 +Contact: Daniel Colascione <dancol@google.com> +Description: + This file provides pre-summed memory information for a + process. The format is identical to /proc/pid/smaps, + except instead of an entry for each VMA in a process, + smaps_rollup has a single entry (tagged "[rollup]") + for which each field is the sum of the corresponding + fields from all the maps in /proc/pid/smaps. + For more details, see the procfs man page. + + Typical output looks like this: + + 00100000-ff709000 ---p 00000000 00:00 0 [rollup] + Rss: 884 kB + Pss: 385 kB + Shared_Clean: 696 kB + Shared_Dirty: 0 kB + Private_Clean: 120 kB + Private_Dirty: 68 kB + Referenced: 884 kB + Anonymous: 68 kB + LazyFree: 0 kB + AnonHugePages: 0 kB + ShmemPmdMapped: 0 kB + Shared_Hugetlb: 0 kB + Private_Hugetlb: 0 kB + Swap: 0 kB + SwapPss: 0 kB + Locked: 385 kB diff --git a/Documentation/ABI/testing/sysfs-block-zram b/Documentation/ABI/testing/sysfs-block-zram index 451b6d8..c1513c7 100644 --- a/Documentation/ABI/testing/sysfs-block-zram +++ b/Documentation/ABI/testing/sysfs-block-zram @@ -90,3 +90,11 @@ Description: device's debugging info useful for kernel developers. Its format is not documented intentionally and may change anytime without any notice. + +What: /sys/block/zram<id>/backing_dev +Date: June 2017 +Contact: Minchan Kim <minchan@kernel.org> +Description: + The backing_dev file is read-write and set up backing + device for zram to write incompressible pages. + For using, user should enable CONFIG_ZRAM_WRITEBACK. diff --git a/Documentation/ABI/testing/sysfs-kernel-mm-swap b/Documentation/ABI/testing/sysfs-kernel-mm-swap new file mode 100644 index 0000000..587db52 --- /dev/null +++ b/Documentation/ABI/testing/sysfs-kernel-mm-swap @@ -0,0 +1,26 @@ +What: /sys/kernel/mm/swap/ +Date: August 2017 +Contact: Linux memory management mailing list <linux-mm@kvack.org> +Description: Interface for swapping + +What: /sys/kernel/mm/swap/vma_ra_enabled +Date: August 2017 +Contact: Linux memory management mailing list <linux-mm@kvack.org> +Description: Enable/disable VMA based swap readahead. + + If set to true, the VMA based swap readahead algorithm + will be used for swappable anonymous pages mapped in a + VMA, and the global swap readahead algorithm will be + still used for tmpfs etc. other users. If set to + false, the global swap readahead algorithm will be + used for all swappable pages. + +What: /sys/kernel/mm/swap/vma_ra_max_order +Date: August 2017 +Contact: Linux memory management mailing list <linux-mm@kvack.org> +Description: The max readahead size in order for VMA based swap readahead + + VMA based swap readahead algorithm will readahead at + most 1 << max_order pages for each readahead. The + real readahead size for each readahead will be scaled + according to the estimation algorithm. diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 6996b77..86b0e8e 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -2783,7 +2783,7 @@ Allowed values are enable and disable numa_zonelist_order= [KNL, BOOT] Select zonelist order for NUMA. - one of ['zone', 'node', 'default'] can be specified + 'node', 'default' can be specified This can be set from sysctl after boot. See Documentation/sysctl/vm.txt for details. diff --git a/Documentation/blockdev/zram.txt b/Documentation/blockdev/zram.txt index 4fced8a..257e657 100644 --- a/Documentation/blockdev/zram.txt +++ b/Documentation/blockdev/zram.txt @@ -168,6 +168,7 @@ max_comp_streams RW the number of possible concurrent compress operations comp_algorithm RW show and change the compression algorithm compact WO trigger memory compaction debug_stat RO this file is used for zram debugging purposes +backing_dev RW set up backend storage for zram to write out User space is advised to use the following files to read the device statistics. @@ -231,5 +232,15 @@ line of text and contains the following stats separated by whitespace: resets the disksize to zero. You must set the disksize again before reusing the device. +* Optional Feature + += writeback + +With incompressible pages, there is no memory saving with zram. +Instead, with CONFIG_ZRAM_WRITEBACK, zram can write incompressible page +to backing storage rather than keeping it in memory. +User should set up backing device via /sys/block/zramX/backing_dev +before disksize setting. + Nitin Gupta ngupta@vflare.org diff --git a/Documentation/filesystems/caching/netfs-api.txt b/Documentation/filesystems/caching/netfs-api.txt index aed6b94..0eb31de 100644 --- a/Documentation/filesystems/caching/netfs-api.txt +++ b/Documentation/filesystems/caching/netfs-api.txt @@ -151,8 +151,6 @@ To define an object, a structure of the following type should be filled out: void (*mark_pages_cached)(void *cookie_netfs_data, struct address_space *mapping, struct pagevec *cached_pvec); - - void (*now_uncached)(void *cookie_netfs_data); }; This has the following fields: diff --git a/Documentation/filesystems/dax.txt b/Documentation/filesystems/dax.txt index a7e6e14..3be3b26 100644 --- a/Documentation/filesystems/dax.txt +++ b/Documentation/filesystems/dax.txt @@ -63,9 +63,8 @@ Filesystem support consists of - implementing an mmap file operation for DAX files which sets the VM_MIXEDMAP and VM_HUGEPAGE flags on the VMA, and setting the vm_ops to include handlers for fault, pmd_fault, page_mkwrite, pfn_mkwrite. These - handlers should probably call dax_iomap_fault() (for fault and page_mkwrite - handlers), dax_iomap_pmd_fault(), dax_pfn_mkwrite() passing the appropriate - iomap operations. + handlers should probably call dax_iomap_fault() passing the appropriate + fault size and iomap operations. - calling iomap_zero_range() passing appropriate iomap operations instead of block_truncate_page() for DAX files - ensuring that there is sufficient locking between reads, writes, diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt index 48244c4..9baf66a 100644 --- a/Documentation/sysctl/vm.txt +++ b/Documentation/sysctl/vm.txt @@ -572,7 +572,9 @@ See Documentation/nommu-mmap.txt for more information. numa_zonelist_order -This sysctl is only for NUMA. +This sysctl is only for NUMA and it is deprecated. Anything but +Node order will fail! + 'where the memory is allocated from' is controlled by zonelists. (This documentation ignores ZONE_HIGHMEM/ZONE_DMA32 for simple explanation. you may be able to read ZONE_DMA as ZONE_DMA32...) diff --git a/Documentation/vm/numa b/Documentation/vm/numa index a08f716..a31b85b 100644 --- a/Documentation/vm/numa +++ b/Documentation/vm/numa @@ -79,11 +79,8 @@ memory, Linux must decide whether to order the zonelists such that allocations fall back to the same zone type on a different node, or to a different zone type on the same node. This is an important consideration because some zones, such as DMA or DMA32, represent relatively scarce resources. Linux chooses -a default zonelist order based on the sizes of the various zone types relative -to the total memory of the node and the total memory of the system. The -default zonelist order may be overridden using the numa_zonelist_order kernel -boot parameter or sysctl. [see Documentation/admin-guide/kernel-parameters.rst and -Documentation/sysctl/vm.txt] +a default Node ordered zonelist. This means it tries to fallback to other zones +from the same node before using remote nodes which are ordered by NUMA distance. By default, Linux will attempt to satisfy memory allocation requests from the node to which the CPU that executes the request is assigned. Specifically, diff --git a/Documentation/vm/swap_numa.txt b/Documentation/vm/swap_numa.txt new file mode 100644 index 0000000..d5960c9 --- /dev/null +++ b/Documentation/vm/swap_numa.txt @@ -0,0 +1,69 @@ +Automatically bind swap device to numa node +------------------------------------------- + +If the system has more than one swap device and swap device has the node +information, we can make use of this information to decide which swap +device to use in get_swap_pages() to get better performance. + + +How to use this feature +----------------------- + +Swap device has priority and that decides the order of it to be used. To make +use of automatically binding, there is no need to manipulate priority settings +for swap devices. e.g. on a 2 node machine, assume 2 swap devices swapA and +swapB, with swapA attached to node 0 and swapB attached to node 1, are going +to be swapped on. Simply swapping them on by doing: +# swapon /dev/swapA +# swapon /dev/swapB + +Then node 0 will use the two swap devices in the order of swapA then swapB and +node 1 will use the two swap devices in the order of swapB then swapA. Note +that the order of them being swapped on doesn't matter. + +A more complex example on a 4 node machine. Assume 6 swap devices are going to +be swapped on: swapA and swapB are attached to node 0, swapC is attached to +node 1, swapD and swapE are attached to node 2 and swapF is attached to node3. +The way to swap them on is the same as above: +# swapon /dev/swapA +# swapon /dev/swapB +# swapon /dev/swapC +# swapon /dev/swapD +# swapon /dev/swapE +# swapon /dev/swapF + +Then node 0 will use them in the order of: +swapA/swapB -> swapC -> swapD -> swapE -> swapF +swapA and swapB will be used in a round robin mode before any other swap device. + +node 1 will use them in the order of: +swapC -> swapA -> swapB -> swapD -> swapE -> swapF + +node 2 will use them in the order of: +swapD/swapE -> swapA -> swapB -> swapC -> swapF +Similaly, swapD and swapE will be used in a round robin mode before any +other swap devices. + +node 3 will use them in the order of: +swapF -> swapA -> swapB -> swapC -> swapD -> swapE + + +Implementation details +---------------------- + +The current code uses a priority based list, swap_avail_list, to decide +which swap device to use and if multiple swap devices share the same +priority, they are used round robin. This change here replaces the single +global swap_avail_list with a per-numa-node list, i.e. for each numa node, +it sees its own priority based list of available swap devices. Swap +device's priority can be promoted on its matching node's swap_avail_list. + +The current swap device's priority is set as: user can set a >=0 value, +or the system will pick one starting from -1 then downwards. The priority +value in the swap_avail_list is the negated value of the swap device's +due to plist being sorted from low to high. The new policy doesn't change +the semantics for priority >=0 cases, the previous starting from -1 then +downwards now becomes starting from -2 then downwards and -1 is reserved +as the promoted value. So if multiple swap devices are attached to the same +node, they will all be promoted to priority -1 on that node's plist and will +be used round robin before any other swap devices. diff --git a/arch/alpha/include/uapi/asm/mman.h b/arch/alpha/include/uapi/asm/mman.h index 02760f6..3b26cc6 100644 --- a/arch/alpha/include/uapi/asm/mman.h +++ b/arch/alpha/include/uapi/asm/mman.h @@ -64,20 +64,12 @@ overrides the coredump filter bits */ #define MADV_DODUMP 17 /* Clear the MADV_NODUMP flag */ +#define MADV_WIPEONFORK 18 /* Zero memory on fork, child only */ +#define MADV_KEEPONFORK 19 /* Undo MADV_WIPEONFORK */ + /* compatibility flags */ #define MAP_FILE 0 -/* - * When MAP_HUGETLB is set bits [26:31] encode the log2 of the huge page size. - * This gives us 6 bits, which is enough until someone invents 128 bit address - * spaces. - * - * Assume these are all power of twos. - * When 0 use the default page size. - */ -#define MAP_HUGE_SHIFT 26 -#define MAP_HUGE_MASK 0x3f - #define PKEY_DISABLE_ACCESS 0x1 #define PKEY_DISABLE_WRITE 0x2 #define PKEY_ACCESS_MASK (PKEY_DISABLE_ACCESS |\ diff --git a/arch/metag/include/asm/topology.h b/arch/metag/include/asm/topology.h index e95f874..707c7f7 100644 --- a/arch/metag/include/asm/topology.h +++ b/arch/metag/include/asm/topology.h @@ -4,7 +4,6 @@ #ifdef CONFIG_NUMA #define cpu_to_node(cpu) ((void)(cpu), 0) -#define parent_node(node) ((void)(node), 0) #define cpumask_of_node(node) ((void)node, cpu_online_mask) diff --git a/arch/mips/include/uapi/asm/mman.h b/arch/mips/include/uapi/asm/mman.h index 655e2fb..da32160 100644 --- a/arch/mips/include/uapi/asm/mman.h +++ b/arch/mips/include/uapi/asm/mman.h @@ -91,20 +91,12 @@ overrides the coredump filter bits */ #define MADV_DODUMP 17 /* Clear the MADV_NODUMP flag */ +#define MADV_WIPEONFORK 18 /* Zero memory on fork, child only */ +#define MADV_KEEPONFORK 19 /* Undo MADV_WIPEONFORK */ + /* compatibility flags */ #define MAP_FILE 0 -/* - * When MAP_HUGETLB is set bits [26:31] encode the log2 of the huge page size. - * This gives us 6 bits, which is enough until someone invents 128 bit address - * spaces. - * - * Assume these are all power of twos. - * When 0 use the default page size. - */ -#define MAP_HUGE_SHIFT 26 -#define MAP_HUGE_MASK 0x3f - #define PKEY_DISABLE_ACCESS 0x1 #define PKEY_DISABLE_WRITE 0x2 #define PKEY_ACCESS_MASK (PKEY_DISABLE_ACCESS |\ diff --git a/arch/parisc/include/uapi/asm/mman.h b/arch/parisc/include/uapi/asm/mman.h index 9a9c2fe..775b5d5 100644 --- a/arch/parisc/include/uapi/asm/mman.h +++ b/arch/parisc/include/uapi/asm/mman.h @@ -57,6 +57,9 @@ overrides the coredump filter bits */ #define MADV_DODUMP 70 /* Clear the MADV_NODUMP flag */ +#define MADV_WIPEONFORK 71 /* Zero memory on fork, child only */ +#define MADV_KEEPONFORK 72 /* Undo MADV_WIPEONFORK */ + #define MADV_HWPOISON 100 /* poison a page for testing */ #define MADV_SOFT_OFFLINE 101 /* soft offline page for testing */ @@ -64,17 +67,6 @@ #define MAP_FILE 0 #define MAP_VARIABLE 0 -/* - * When MAP_HUGETLB is set bits [26:31] encode the log2 of the huge page size. - * This gives us 6 bits, which is enough until someone invents 128 bit address - * spaces. - * - * Assume these are all power of twos. - * When 0 use the default page size. - */ -#define MAP_HUGE_SHIFT 26 -#define MAP_HUGE_MASK 0x3f - #define PKEY_DISABLE_ACCESS 0x1 #define PKEY_DISABLE_WRITE 0x2 #define PKEY_ACCESS_MASK (PKEY_DISABLE_ACCESS |\ diff --git a/arch/powerpc/include/uapi/asm/mman.h b/arch/powerpc/include/uapi/asm/mman.h index ab45cc2..03c06ba 100644 --- a/arch/powerpc/include/uapi/asm/mman.h +++ b/arch/powerpc/include/uapi/asm/mman.h @@ -29,20 +29,4 @@ #define MAP_STACK 0x20000 /* give out an address that is best suited for process/thread stacks */ #define MAP_HUGETLB 0x40000 /* create a huge page mapping */ -/* - * When MAP_HUGETLB is set, bits [26:31] of the flags argument to mmap(2), - * encode the log2 of the huge page size. A value of zero indicates that the - * default huge page size should be used. To use a non-default huge page size, - * one of these defines can be used, or the size can be encoded by hand. Note - * that on most systems only a subset, or possibly none, of these sizes will be - * available. - */ -#define MAP_HUGE_512KB (19 << MAP_HUGE_SHIFT) /* 512KB HugeTLB Page */ -#define MAP_HUGE_1MB (20 << MAP_HUGE_SHIFT) /* 1MB HugeTLB Page */ -#define MAP_HUGE_2MB (21 << MAP_HUGE_SHIFT) /* 2MB HugeTLB Page */ -#define MAP_HUGE_8MB (23 << MAP_HUGE_SHIFT) /* 8MB HugeTLB Page */ -#define MAP_HUGE_16MB (24 << MAP_HUGE_SHIFT) /* 16MB HugeTLB Page */ -#define MAP_HUGE_1GB (30 << MAP_HUGE_SHIFT) /* 1GB HugeTLB Page */ -#define MAP_HUGE_16GB (34 << MAP_HUGE_SHIFT) /* 16GB HugeTLB Page */ - #endif /* _UAPI_ASM_POWERPC_MMAN_H */ diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index acb366b..4b278a3 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -1806,7 +1806,9 @@ config X86_SMAP config X86_INTEL_MPX prompt "Intel MPX (Memory Protection Extensions)" def_bool n - depends on CPU_SUP_INTEL + # Note: only available in 64-bit mode due to VMA flags shortage + depends on CPU_SUP_INTEL && X86_64 + select ARCH_USES_HIGH_VMA_FLAGS ---help--- MPX provides hardware features that can be used in conjunction with compiler-instrumented code to check diff --git a/arch/x86/include/uapi/asm/mman.h b/arch/x86/include/uapi/asm/mman.h index 39bca7f..3be08f0 100644 --- a/arch/x86/include/uapi/asm/mman.h +++ b/arch/x86/include/uapi/asm/mman.h @@ -3,9 +3,6 @@ #define MAP_32BIT 0x40 /* only give out 32bit addresses */ -#define MAP_HUGE_2MB (21 << MAP_HUGE_SHIFT) -#define MAP_HUGE_1GB (30 << MAP_HUGE_SHIFT) - #ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS /* * Take the 4 protection key bits out of the vma->vm_flags diff --git a/arch/xtensa/include/uapi/asm/mman.h b/arch/xtensa/include/uapi/asm/mman.h index 24365b3..b15b278 100644 --- a/arch/xtensa/include/uapi/asm/mman.h +++ b/arch/xtensa/include/uapi/asm/mman.h @@ -103,20 +103,12 @@ overrides the coredump filter bits */ #define MADV_DODUMP 17 /* Clear the MADV_NODUMP flag */ +#define MADV_WIPEONFORK 18 /* Zero memory on fork, child only */ +#define MADV_KEEPONFORK 19 /* Undo MADV_WIPEONFORK */ + /* compatibility flags */ #define MAP_FILE 0 -/* - * When MAP_HUGETLB is set bits [26:31] encode the log2 of the huge page size. - * This gives us 6 bits, which is enough until someone invents 128 bit address - * spaces. - * - * Assume these are all power of twos. - * When 0 use the default page size. - */ -#define MAP_HUGE_SHIFT 26 -#define MAP_HUGE_MASK 0x3f - #define PKEY_DISABLE_ACCESS 0x1 #define PKEY_DISABLE_WRITE 0x2 #define PKEY_ACCESS_MASK (PKEY_DISABLE_ACCESS |\ diff --git a/drivers/base/memory.c b/drivers/base/memory.c index c7c4e03..4e3b61c 100644 --- a/drivers/base/memory.c +++ b/drivers/base/memory.c @@ -388,6 +388,19 @@ static ssize_t show_phys_device(struct device *dev, } #ifdef CONFIG_MEMORY_HOTREMOVE +static void print_allowed_zone(char *buf, int nid, unsigned long start_pfn, + unsigned long nr_pages, int online_type, + struct zone *default_zone) +{ + struct zone *zone; + + zone = zone_for_pfn_range(online_type, nid, start_pfn, nr_pages); + if (zone != default_zone) { + strcat(buf, " "); + strcat(buf, zone->name); + } +} + static ssize_t show_valid_zones(struct device *dev, struct device_attribute *attr, char *buf) { @@ -395,7 +408,7 @@ static ssize_t show_valid_zones(struct device *dev, unsigned long start_pfn = section_nr_to_pfn(mem->start_section_nr); unsigned long nr_pages = PAGES_PER_SECTION * sections_per_block; unsigned long valid_start_pfn, valid_end_pfn; - bool append = false; + struct zone *default_zone; int nid; /* @@ -418,16 +431,13 @@ static ssize_t show_valid_zones(struct device *dev, } nid = pfn_to_nid(start_pfn); - if (allow_online_pfn_range(nid, start_pfn, nr_pages, MMOP_ONLINE_KERNEL)) { - strcat(buf, default_zone_for_pfn(nid, start_pfn, nr_pages)->name); - append = true; - } + default_zone = zone_for_pfn_range(MMOP_ONLINE_KEEP, nid, start_pfn, nr_pages); + strcat(buf, default_zone->name); - if (allow_online_pfn_range(nid, start_pfn, nr_pages, MMOP_ONLINE_MOVABLE)) { - if (append) - strcat(buf, " "); - strcat(buf, NODE_DATA(nid)->node_zones[ZONE_MOVABLE].name); - } + print_allowed_zone(buf, nid, start_pfn, nr_pages, MMOP_ONLINE_KERNEL, + default_zone); + print_allowed_zone(buf, nid, start_pfn, nr_pages, MMOP_ONLINE_MOVABLE, + default_zone); out: strcat(buf, "\n"); diff --git a/drivers/block/brd.c b/drivers/block/brd.c index 104b71c..5d9ed06 100644 --- a/drivers/block/brd.c +++ b/drivers/block/brd.c @@ -326,7 +326,11 @@ static int brd_rw_page(struct block_device *bdev, sector_t sector, struct page *page, bool is_write) { struct brd_device *brd = bdev->bd_disk->private_data; - int err = brd_do_bvec(brd, page, PAGE_SIZE, 0, is_write, sector); + int err; + + if (PageTransHuge(page)) + return -ENOTSUPP; + err = brd_do_bvec(brd, page, PAGE_SIZE, 0, is_write, sector); page_endio(page, is_write, err); return err; } diff --git a/drivers/block/zram/Kconfig b/drivers/block/zram/Kconfig index b8ecba6..7cd4a8e 100644 --- a/drivers/block/zram/Kconfig +++ b/drivers/block/zram/Kconfig @@ -13,3 +13,15 @@ config ZRAM disks and maybe many more. See zram.txt for more information. + +config ZRAM_WRITEBACK + bool "Write back incompressible page to backing device" + depends on ZRAM + default n + help + With incompressible page, there is no memory saving to keep it + in memory. Instead, write it out to backing device. + For this feature, admin should set up backing device via + /sys/block/zramX/backing_dev. + + See zram.txt for more infomration. diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index 3b1b634..4a0438c 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -270,6 +270,349 @@ static ssize_t mem_used_max_store(struct device *dev, return len; } +#ifdef CONFIG_ZRAM_WRITEBACK +static bool zram_wb_enabled(struct zram *zram) +{ + return zram->backing_dev; +} + +static void reset_bdev(struct zram *zram) +{ + struct block_device *bdev; + + if (!zram_wb_enabled(zram)) + return; + + bdev = zram->bdev; + if (zram->old_block_size) + set_blocksize(bdev, zram->old_block_size); + blkdev_put(bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL); + /* hope filp_close flush all of IO */ + filp_close(zram->backing_dev, NULL); + zram->backing_dev = NULL; + zram->old_block_size = 0; + zram->bdev = NULL; + + kvfree(zram->bitmap); + zram->bitmap = NULL; +} + +static ssize_t backing_dev_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct zram *zram = dev_to_zram(dev); + struct file *file = zram->backing_dev; + char *p; + ssize_t ret; + + down_read(&zram->init_lock); + if (!zram_wb_enabled(zram)) { + memcpy(buf, "none\n", 5); + up_read(&zram->init_lock); + return 5; + } + + p = file_path(file, buf, PAGE_SIZE - 1); + if (IS_ERR(p)) { + ret = PTR_ERR(p); + goto out; + } + + ret = strlen(p); + memmove(buf, p, ret); + buf[ret++] = '\n'; +out: + up_read(&zram->init_lock); + return ret; +} + +static ssize_t backing_dev_store(struct device *dev, + struct device_attribute *attr, const char *buf, size_t len) +{ + char *file_name; + struct file *backing_dev = NULL; + struct inode *inode; + struct address_space *mapping; + unsigned int bitmap_sz, old_block_size = 0; + unsigned long nr_pages, *bitmap = NULL; + struct block_device *bdev = NULL; + int err; + struct zram *zram = dev_to_zram(dev); + + file_name = kmalloc(PATH_MAX, GFP_KERNEL); + if (!file_name) + return -ENOMEM; + + down_write(&zram->init_lock); + if (init_done(zram)) { + pr_info("Can't setup backing device for initialized device\n"); + err = -EBUSY; + goto out; + } + + strlcpy(file_name, buf, len); + + backing_dev = filp_open(file_name, O_RDWR|O_LARGEFILE, 0); + if (IS_ERR(backing_dev)) { + err = PTR_ERR(backing_dev); + backing_dev = NULL; + goto out; + } + + mapping = backing_dev->f_mapping; + inode = mapping->host; + + /* Support only block device in this moment */ + if (!S_ISBLK(inode->i_mode)) { + err = -ENOTBLK; + goto out; + } + + bdev = bdgrab(I_BDEV(inode)); + err = blkdev_get(bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL, zram); + if (err < 0) + goto out; + + nr_pages = i_size_read(inode) >> PAGE_SHIFT; + bitmap_sz = BITS_TO_LONGS(nr_pages) * sizeof(long); + bitmap = kvzalloc(bitmap_sz, GFP_KERNEL); + if (!bitmap) { + err = -ENOMEM; + goto out; + } + + old_block_size = block_size(bdev); + err = set_blocksize(bdev, PAGE_SIZE); + if (err) + goto out; + + reset_bdev(zram); + spin_lock_init(&zram->bitmap_lock); + + zram->old_block_size = old_block_size; + zram->bdev = bdev; + zram->backing_dev = backing_dev; + zram->bitmap = bitmap; + zram->nr_pages = nr_pages; + up_write(&zram->init_lock); + + pr_info("setup backing device %s\n", file_name); + kfree(file_name); + + return len; +out: + if (bitmap) + kvfree(bitmap); + + if (bdev) + blkdev_put(bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL); + + if (backing_dev) + filp_close(backing_dev, NULL); + + up_write(&zram->init_lock); + + kfree(file_name); + + return err; +} + +static unsigned long get_entry_bdev(struct zram *zram) +{ + unsigned long entry; + + spin_lock(&zram->bitmap_lock); + /* skip 0 bit to confuse zram.handle = 0 */ + entry = find_next_zero_bit(zram->bitmap, zram->nr_pages, 1); + if (entry == zram->nr_pages) { + spin_unlock(&zram->bitmap_lock); + return 0; + } + + set_bit(entry, zram->bitmap); + spin_unlock(&zram->bitmap_lock); + + return entry; +} + +static void put_entry_bdev(struct zram *zram, unsigned long entry) +{ + int was_set; + + spin_lock(&zram->bitmap_lock); + was_set = test_and_clear_bit(entry, zram->bitmap); + spin_unlock(&zram->bitmap_lock); + WARN_ON_ONCE(!was_set); +} + +void zram_page_end_io(struct bio *bio) +{ + struct page *page = bio->bi_io_vec[0].bv_page; + + page_endio(page, op_is_write(bio_op(bio)), + blk_status_to_errno(bio->bi_status)); + bio_put(bio); +} + +/* + * Returns 1 if the submission is successful. + */ +static int read_from_bdev_async(struct zram *zram, struct bio_vec *bvec, + unsigned long entry, struct bio *parent) +{ + struct bio *bio; + + bio = bio_alloc(GFP_ATOMIC, 1); + if (!bio) + return -ENOMEM; + + bio->bi_iter.bi_sector = entry * (PAGE_SIZE >> 9); + bio->bi_bdev = zram->bdev; + if (!bio_add_page(bio, bvec->bv_page, bvec->bv_len, bvec->bv_offset)) { + bio_put(bio); + return -EIO; + } + + if (!parent) { + bio->bi_opf = REQ_OP_READ; + bio->bi_end_io = zram_page_end_io; + } else { + bio->bi_opf = parent->bi_opf; + bio_chain(bio, parent); + } + + submit_bio(bio); + return 1; +} + +struct zram_work { + struct work_struct work; + struct zram *zram; + unsigned long entry; + struct bio *bio; +}; + +#if PAGE_SIZE != 4096 +static void zram_sync_read(struct work_struct *work) +{ + struct bio_vec bvec; + struct zram_work *zw = container_of(work, struct zram_work, work); + struct zram *zram = zw->zram; + unsigned long entry = zw->entry; + struct bio *bio = zw->bio; + + read_from_bdev_async(zram, &bvec, entry, bio); +} + +/* + * Block layer want one ->make_request_fn to be active at a time + * so if we use chained IO with parent IO in same context, + * it's a deadlock. To avoid, it, it uses worker thread context. + */ +static int read_from_bdev_sync(struct zram *zram, struct bio_vec *bvec, + unsigned long entry, struct bio *bio) +{ + struct zram_work work; + + work.zram = zram; + work.entry = entry; + work.bio = bio; + + INIT_WORK_ONSTACK(&work.work, zram_sync_read); + queue_work(system_unbound_wq, &work.work); + flush_work(&work.work); + destroy_work_on_stack(&work.work); + + return 1; +} +#else +static int read_from_bdev_sync(struct zram *zram, struct bio_vec *bvec, + unsigned long entry, struct bio *bio) +{ + WARN_ON(1); + return -EIO; +} +#endif + +static int read_from_bdev(struct zram *zram, struct bio_vec *bvec, + unsigned long entry, struct bio *parent, bool sync) +{ + if (sync) + return read_from_bdev_sync(zram, bvec, entry, parent); + else + return read_from_bdev_async(zram, bvec, entry, parent); +} + +static int write_to_bdev(struct zram *zram, struct bio_vec *bvec, + u32 index, struct bio *parent, + unsigned long *pentry) +{ + struct bio *bio; + unsigned long entry; + + bio = bio_alloc(GFP_ATOMIC, 1); + if (!bio) + return -ENOMEM; + + entry = get_entry_bdev(zram); + if (!entry) { + bio_put(bio); + return -ENOSPC; + } + + bio->bi_iter.bi_sector = entry * (PAGE_SIZE >> 9); + bio->bi_bdev = zram->bdev; + if (!bio_add_page(bio, bvec->bv_page, bvec->bv_len, + bvec->bv_offset)) { + bio_put(bio); + put_entry_bdev(zram, entry); + return -EIO; + } + + if (!parent) { + bio->bi_opf = REQ_OP_WRITE | REQ_SYNC; + bio->bi_end_io = zram_page_end_io; + } else { + bio->bi_opf = parent->bi_opf; + bio_chain(bio, parent); + } + + submit_bio(bio); + *pentry = entry; + + return 0; +} + +static void zram_wb_clear(struct zram *zram, u32 index) +{ + unsigned long entry; + + zram_clear_flag(zram, index, ZRAM_WB); + entry = zram_get_element(zram, index); + zram_set_element(zram, index, 0); + put_entry_bdev(zram, entry); +} + +#else +static bool zram_wb_enabled(struct zram *zram) { return false; } +static inline void reset_bdev(struct zram *zram) {}; +static int write_to_bdev(struct zram *zram, struct bio_vec *bvec, + u32 index, struct bio *parent, + unsigned long *pentry) + +{ + return -EIO; +} + +static int read_from_bdev(struct zram *zram, struct bio_vec *bvec, + unsigned long entry, struct bio *parent, bool sync) +{ + return -EIO; +} +static void zram_wb_clear(struct zram *zram, u32 index) {} +#endif + + /* * We switched to per-cpu streams and this attr is not needed anymore. * However, we will keep it around for some time, because: @@ -453,30 +796,6 @@ static bool zram_same_page_read(struct zram *zram, u32 index, return false; } -static bool zram_same_page_write(struct zram *zram, u32 index, - struct page *page) -{ - unsigned long element; - void *mem = kmap_atomic(page); - - if (page_same_filled(mem, &element)) { - kunmap_atomic(mem); - /* Free memory associated with this sector now. */ - zram_slot_lock(zram, index); - zram_free_page(zram, index); - zram_set_flag(zram, index, ZRAM_SAME); - zram_set_element(zram, index, element); - zram_slot_unlock(zram, index); - - atomic64_inc(&zram->stats.same_pages); - atomic64_inc(&zram->stats.pages_stored); - return true; - } - kunmap_atomic(mem); - - return false; -} - static void zram_meta_free(struct zram *zram, u64 disksize) { size_t num_pages = disksize >> PAGE_SHIFT; @@ -515,7 +834,13 @@ static bool zram_meta_alloc(struct zram *zram, u64 disksize) */ static void zram_free_page(struct zram *zram, size_t index) { - unsigned long handle = zram_get_handle(zram, index); + unsigned long handle; + + if (zram_wb_enabled(zram) && zram_test_flag(zram, index, ZRAM_WB)) { + zram_wb_clear(zram, index); + atomic64_dec(&zram->stats.pages_stored); + return; + } /* * No memory is allocated for same element filled pages. @@ -529,6 +854,7 @@ static void zram_free_page(struct zram *zram, size_t index) return; } + handle = zram_get_handle(zram, index); if (!handle) return; @@ -542,13 +868,31 @@ static void zram_free_page(struct zram *zram, size_t index) zram_set_obj_size(zram, index, 0); } -static int zram_decompress_page(struct zram *zram, struct page *page, u32 index) +static int __zram_bvec_read(struct zram *zram, struct page *page, u32 index, + struct bio *bio, bool partial_io) { int ret; unsigned long handle; unsigned int size; void *src, *dst; + if (zram_wb_enabled(zram)) { + zram_slot_lock(zram, index); + if (zram_test_flag(zram, index, ZRAM_WB)) { + struct bio_vec bvec; + + zram_slot_unlock(zram, index); + + bvec.bv_page = page; + bvec.bv_len = PAGE_SIZE; + bvec.bv_offset = 0; + return read_from_bdev(zram, &bvec, + zram_get_element(zram, index), + bio, partial_io); + } + zram_slot_unlock(zram, index); + } + if (zram_same_page_read(zram, index, page, 0, PAGE_SIZE)) return 0; @@ -581,7 +925,7 @@ static int zram_decompress_page(struct zram *zram, struct page *page, u32 index) } static int zram_bvec_read(struct zram *zram, struct bio_vec *bvec, - u32 index, int offset) + u32 index, int offset, struct bio *bio) { int ret; struct page *page; @@ -594,7 +938,7 @@ static int zram_bvec_read(struct zram *zram, struct bio_vec *bvec, return -ENOMEM; } - ret = zram_decompress_page(zram, page, index); + ret = __zram_bvec_read(zram, page, index, bio, is_partial_io(bvec)); if (unlikely(ret)) goto out; @@ -613,30 +957,57 @@ out: return ret; } -static int zram_compress(struct zram *zram, struct zcomp_strm **zstrm, - struct page *page, - unsigned long *out_handle, unsigned int *out_comp_len) +static int __zram_bvec_write(struct zram *zram, struct bio_vec *bvec, + u32 index, struct bio *bio) { - int ret; - unsigned int comp_len; - void *src; + int ret = 0; unsigned long alloced_pages; unsigned long handle = 0; + unsigned int comp_len = 0; + void *src, *dst, *mem; + struct zcomp_strm *zstrm; + struct page *page = bvec->bv_page; + unsigned long element = 0; + enum zram_pageflags flags = 0; + bool allow_wb = true; + + mem = kmap_atomic(page); + if (page_same_filled(mem, &element)) { + kunmap_atomic(mem); + /* Free memory associated with this sector now. */ + flags = ZRAM_SAME; + atomic64_inc(&zram->stats.same_pages); + goto out; + } + kunmap_atomic(mem); compress_again: + zstrm = zcomp_stream_get(zram->comp); src = kmap_atomic(page); - ret = zcomp_compress(*zstrm, src, &comp_len); + ret = zcomp_compress(zstrm, src, &comp_len); kunmap_atomic(src); if (unlikely(ret)) { + zcomp_stream_put(zram->comp); pr_err("Compression failed! err=%d\n", ret); - if (handle) - zs_free(zram->mem_pool, handle); + zs_free(zram->mem_pool, handle); return ret; } - if (unlikely(comp_len > max_zpage_size)) + if (unlikely(comp_len > max_zpage_size)) { + if (zram_wb_enabled(zram) && allow_wb) { + zcomp_stream_put(zram->comp); + ret = write_to_bdev(zram, bvec, index, bio, &element); + if (!ret) { + flags = ZRAM_WB; + ret = 1; + goto out; + } + allow_wb = false; + goto compress_again; + } comp_len = PAGE_SIZE; + } /* * handle allocation has 2 paths: @@ -663,7 +1034,6 @@ compress_again: handle = zs_malloc(zram->mem_pool, comp_len, GFP_NOIO | __GFP_HIGHMEM | __GFP_MOVABLE); - *zstrm = zcomp_stream_get(zram->comp); if (handle) goto compress_again; return -ENOMEM; @@ -673,34 +1043,11 @@ compress_again: update_used_max(zram, alloced_pages); if (zram->limit_pages && alloced_pages > zram->limit_pages) { + zcomp_stream_put(zram->comp); zs_free(zram->mem_pool, handle); return -ENOMEM; } - *out_handle = handle; - *out_comp_len = comp_len; - return 0; -} - -static int __zram_bvec_write(struct zram *zram, struct bio_vec *bvec, u32 index) -{ - int ret; - unsigned long handle; - unsigned int comp_len; - void *src, *dst; - struct zcomp_strm *zstrm; - struct page *page = bvec->bv_page; - - if (zram_same_page_write(zram, index, page)) - return 0; - - zstrm = zcomp_stream_get(zram->comp); - ret = zram_compress(zram, &zstrm, page, &handle, &comp_len); - if (ret) { - zcomp_stream_put(zram->comp); - return ret; - } - dst = zs_map_object(zram->mem_pool, handle, ZS_MM_WO); src = zstrm->buffer; @@ -712,25 +1059,31 @@ static int __zram_bvec_write(struct zram *zram, struct bio_vec *bvec, u32 index) zcomp_stream_put(zram->comp); zs_unmap_object(zram->mem_pool, handle); - + atomic64_add(comp_len, &zram->stats.compr_data_size); +out: /* * Free memory associated with this sector * before overwriting unused sectors. */ zram_slot_lock(zram, index); zram_free_page(zram, index); - zram_set_handle(zram, index, handle); - zram_set_obj_size(zram, index, comp_len); + + if (flags) { + zram_set_flag(zram, index, flags); + zram_set_element(zram, index, element); + } else { + zram_set_handle(zram, index, handle); + zram_set_obj_size(zram, index, comp_len); + } zram_slot_unlock(zram, index); /* Update stats */ - atomic64_add(comp_len, &zram->stats.compr_data_size); atomic64_inc(&zram->stats.pages_stored); - return 0; + return ret; } static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec, - u32 index, int offset) + u32 index, int offset, struct bio *bio) { int ret; struct page *page = NULL; @@ -748,7 +1101,7 @@ static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec, if (!page) return -ENOMEM; - ret = zram_decompress_page(zram, page, index); + ret = __zram_bvec_read(zram, page, index, bio, true); if (ret) goto out; @@ -763,7 +1116,7 @@ static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec, vec.bv_offset = 0; } - ret = __zram_bvec_write(zram, &vec, index); + ret = __zram_bvec_write(zram, &vec, index, bio); out: if (is_partial_io(bvec)) __free_page(page); @@ -808,8 +1161,13 @@ static void zram_bio_discard(struct zram *zram, u32 index, } } +/* + * Returns errno if it has some problem. Otherwise return 0 or 1. + * Returns 0 if IO request was done synchronously + * Returns 1 if IO request was successfully submitted. + */ static int zram_bvec_rw(struct zram *zram, struct bio_vec *bvec, u32 index, - int offset, bool is_write) + int offset, bool is_write, struct bio *bio) { unsigned long start_time = jiffies; int rw_acct = is_write ? REQ_OP_WRITE : REQ_OP_READ; @@ -820,16 +1178,16 @@ static int zram_bvec_rw(struct zram *zram, struct bio_vec *bvec, u32 index, if (!is_write) { atomic64_inc(&zram->stats.num_reads); - ret = zram_bvec_read(zram, bvec, index, offset); + ret = zram_bvec_read(zram, bvec, index, offset, bio); flush_dcache_page(bvec->bv_page); } else { atomic64_inc(&zram->stats.num_writes); - ret = zram_bvec_write(zram, bvec, index, offset); + ret = zram_bvec_write(zram, bvec, index, offset, bio); } generic_end_io_acct(rw_acct, &zram->disk->part0, start_time); - if (unlikely(ret)) { + if (unlikely(ret < 0)) { if (!is_write) atomic64_inc(&zram->stats.failed_reads); else @@ -868,7 +1226,7 @@ static void __zram_make_request(struct zram *zram, struct bio *bio) bv.bv_len = min_t(unsigned int, PAGE_SIZE - offset, unwritten); if (zram_bvec_rw(zram, &bv, index, offset, - op_is_write(bio_op(bio))) < 0) + op_is_write(bio_op(bio)), bio) < 0) goto out; bv.bv_offset += bv.bv_len; @@ -922,16 +1280,18 @@ static void zram_slot_free_notify(struct block_device *bdev, static int zram_rw_page(struct block_device *bdev, sector_t sector, struct page *page, bool is_write) { - int offset, err = -EIO; + int offset, ret; u32 index; struct zram *zram; struct bio_vec bv; + if (PageTransHuge(page)) + return -ENOTSUPP; zram = bdev->bd_disk->private_data; if (!valid_io_request(zram, sector, PAGE_SIZE)) { atomic64_inc(&zram->stats.invalid_io); - err = -EINVAL; + ret = -EINVAL; goto out; } @@ -942,7 +1302,7 @@ static int zram_rw_page(struct block_device *bdev, sector_t sector, bv.bv_len = PAGE_SIZE; bv.bv_offset = 0; - err = zram_bvec_rw(zram, &bv, index, offset, is_write); + ret = zram_bvec_rw(zram, &bv, index, offset, is_write, NULL); out: /* * If I/O fails, just return error(ie, non-zero) without @@ -952,9 +1312,20 @@ out: * bio->bi_end_io does things to handle the error * (e.g., SetPageError, set_page_dirty and extra works). */ - if (err == 0) + if (unlikely(ret < 0)) + return ret; + + switch (ret) { + case 0: page_endio(page, is_write, 0); - return err; + break; + case 1: + ret = 0; + break; + default: + WARN_ON(1); + } + return ret; } static void zram_reset_device(struct zram *zram) @@ -983,6 +1354,7 @@ static void zram_reset_device(struct zram *zram) zram_meta_free(zram, disksize); memset(&zram->stats, 0, sizeof(zram->stats)); zcomp_destroy(comp); + reset_bdev(zram); } static ssize_t disksize_store(struct device *dev, @@ -1108,6 +1480,9 @@ static DEVICE_ATTR_WO(mem_limit); static DEVICE_ATTR_WO(mem_used_max); static DEVICE_ATTR_RW(max_comp_streams); static DEVICE_ATTR_RW(comp_algorithm); +#ifdef CONFIG_ZRAM_WRITEBACK +static DEVICE_ATTR_RW(backing_dev); +#endif static struct attribute *zram_disk_attrs[] = { &dev_attr_disksize.attr, @@ -1118,6 +1493,9 @@ static struct attribute *zram_disk_attrs[] = { &dev_attr_mem_used_max.attr, &dev_attr_max_comp_streams.attr, &dev_attr_comp_algorithm.attr, +#ifdef CONFIG_ZRAM_WRITEBACK + &dev_attr_backing_dev.attr, +#endif &dev_attr_io_stat.attr, &dev_attr_mm_stat.attr, &dev_attr_debug_stat.attr, diff --git a/drivers/block/zram/zram_drv.h b/drivers/block/zram/zram_drv.h index e34e44d..31762db 100644 --- a/drivers/block/zram/zram_drv.h +++ b/drivers/block/zram/zram_drv.h @@ -60,9 +60,10 @@ static const size_t max_zpage_size = PAGE_SIZE / 4 * 3; /* Flags for zram pages (table[page_no].value) */ enum zram_pageflags { - /* Page consists entirely of zeros */ + /* Page consists the same element */ ZRAM_SAME = ZRAM_FLAG_SHIFT, ZRAM_ACCESS, /* page is now accessed */ + ZRAM_WB, /* page is stored on backing_device */ __NR_ZRAM_PAGEFLAGS, }; @@ -115,5 +116,13 @@ struct zram { * zram is claimed so open request will be failed */ bool claim; /* Protected by bdev->bd_mutex */ +#ifdef CONFIG_ZRAM_WRITEBACK + struct file *backing_dev; + struct block_device *bdev; + unsigned int old_block_size; + unsigned long *bitmap; + unsigned long nr_pages; + spinlock_t bitmap_lock; +#endif }; #endif diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c index a36216b..e4d4b6b 100644 --- a/drivers/gpu/drm/i915/i915_debugfs.c +++ b/drivers/gpu/drm/i915/i915_debugfs.c @@ -4308,10 +4308,10 @@ i915_drop_caches_set(void *data, u64 val) fs_reclaim_acquire(GFP_KERNEL); if (val & DROP_BOUND) - i915_gem_shrink(dev_priv, LONG_MAX, I915_SHRINK_BOUND); + i915_gem_shrink(dev_priv, LONG_MAX, NULL, I915_SHRINK_BOUND); if (val & DROP_UNBOUND) - i915_gem_shrink(dev_priv, LONG_MAX, I915_SHRINK_UNBOUND); + i915_gem_shrink(dev_priv, LONG_MAX, NULL, I915_SHRINK_UNBOUND); if (val & DROP_SHRINK_ALL) i915_gem_shrink_all(dev_priv); diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 60267e3..bd74641 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -3742,6 +3742,7 @@ i915_gem_object_create_internal(struct drm_i915_private *dev_priv, /* i915_gem_shrinker.c */ unsigned long i915_gem_shrink(struct drm_i915_private *dev_priv, unsigned long target, + unsigned long *nr_scanned, unsigned flags); #define I915_SHRINK_PURGEABLE 0x1 #define I915_SHRINK_UNBOUND 0x2 diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index b9e8e0d..287c6ea 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -2354,7 +2354,7 @@ rebuild_st: goto err_sg; } - i915_gem_shrink(dev_priv, 2 * page_count, *s++); + i915_gem_shrink(dev_priv, 2 * page_count, NULL, *s++); cond_resched(); /* We've tried hard to allocate the memory by reaping @@ -5015,7 +5015,7 @@ int i915_gem_freeze_late(struct drm_i915_private *dev_priv) * the objects as well, see i915_gem_freeze() */ - i915_gem_shrink(dev_priv, -1UL, I915_SHRINK_UNBOUND); + i915_gem_shrink(dev_priv, -1UL, NULL, I915_SHRINK_UNBOUND); i915_gem_drain_freed_objects(dev_priv); mutex_lock(&dev_priv->drm.struct_mutex); diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c index d60f38a..6c6b8e8 100644 --- a/drivers/gpu/drm/i915/i915_gem_gtt.c +++ b/drivers/gpu/drm/i915/i915_gem_gtt.c @@ -2062,7 +2062,7 @@ int i915_gem_gtt_prepare_pages(struct drm_i915_gem_object *obj, */ GEM_BUG_ON(obj->mm.pages == pages); } while (i915_gem_shrink(to_i915(obj->base.dev), - obj->base.size >> PAGE_SHIFT, + obj->base.size >> PAGE_SHIFT, NULL, I915_SHRINK_BOUND | I915_SHRINK_UNBOUND | I915_SHRINK_ACTIVE)); diff --git a/drivers/gpu/drm/i915/i915_gem_shrinker.c b/drivers/gpu/drm/i915/i915_gem_shrinker.c index 77fb398..74002b2 100644 --- a/drivers/gpu/drm/i915/i915_gem_shrinker.c +++ b/drivers/gpu/drm/i915/i915_gem_shrinker.c @@ -136,6 +136,7 @@ static bool unsafe_drop_pages(struct drm_i915_gem_object *obj) * i915_gem_shrink - Shrink buffer object caches * @dev_priv: i915 device * @target: amount of memory to make available, in pages + * @nr_scanned: optional output for number of pages scanned (incremental) * @flags: control flags for selecting cache types * * This function is the main interface to the shrinker. It will try to release @@ -158,7 +159,9 @@ static bool unsafe_drop_pages(struct drm_i915_gem_object *obj) */ unsigned long i915_gem_shrink(struct drm_i915_private *dev_priv, - unsigned long target, unsigned flags) + unsigned long target, + unsigned long *nr_scanned, + unsigned flags) { const struct { struct list_head *list; @@ -169,6 +172,7 @@ i915_gem_shrink(struct drm_i915_private *dev_priv, { NULL, 0 }, }, *phase; unsigned long count = 0; + unsigned long scanned = 0; bool unlock; if (!shrinker_lock(dev_priv, &unlock)) @@ -249,6 +253,7 @@ i915_gem_shrink(struct drm_i915_private *dev_priv, count += obj->base.size >> PAGE_SHIFT; } mutex_unlock(&obj->mm.lock); + scanned += obj->base.size >> PAGE_SHIFT; } } list_splice_tail(&still_in_list, phase->list); @@ -261,6 +266,8 @@ i915_gem_shrink(struct drm_i915_private *dev_priv, shrinker_unlock(dev_priv, unlock); + if (nr_scanned) + *nr_scanned += scanned; return count; } @@ -283,7 +290,7 @@ unsigned long i915_gem_shrink_all(struct drm_i915_private *dev_priv) unsigned long freed; intel_runtime_pm_get(dev_priv); - freed = i915_gem_shrink(dev_priv, -1UL, + freed = i915_gem_shrink(dev_priv, -1UL, NULL, I915_SHRINK_BOUND | I915_SHRINK_UNBOUND | I915_SHRINK_ACTIVE); @@ -329,23 +336,28 @@ i915_gem_shrinker_scan(struct shrinker *shrinker, struct shrink_control *sc) unsigned long freed; bool unlock; + sc->nr_scanned = 0; + if (!shrinker_lock(dev_priv, &unlock)) return SHRINK_STOP; freed = i915_gem_shrink(dev_priv, sc->nr_to_scan, + &sc->nr_scanned, I915_SHRINK_BOUND | I915_SHRINK_UNBOUND | I915_SHRINK_PURGEABLE); if (freed < sc->nr_to_scan) freed += i915_gem_shrink(dev_priv, - sc->nr_to_scan - freed, + sc->nr_to_scan - sc->nr_scanned, + &sc->nr_scanned, I915_SHRINK_BOUND | I915_SHRINK_UNBOUND); if (freed < sc->nr_to_scan && current_is_kswapd()) { intel_runtime_pm_get(dev_priv); freed += i915_gem_shrink(dev_priv, - sc->nr_to_scan - freed, + sc->nr_to_scan - sc->nr_scanned, + &sc->nr_scanned, I915_SHRINK_ACTIVE | I915_SHRINK_BOUND | I915_SHRINK_UNBOUND); @@ -354,7 +366,7 @@ i915_gem_shrinker_scan(struct shrinker *shrinker, struct shrink_control *sc) shrinker_unlock(dev_priv, unlock); - return freed; + return sc->nr_scanned ? freed : SHRINK_STOP; } static bool @@ -453,7 +465,7 @@ i915_gem_shrinker_vmap(struct notifier_block *nb, unsigned long event, void *ptr goto out; intel_runtime_pm_get(dev_priv); - freed_pages += i915_gem_shrink(dev_priv, -1UL, + freed_pages += i915_gem_shrink(dev_priv, -1UL, NULL, I915_SHRINK_BOUND | I915_SHRINK_UNBOUND | I915_SHRINK_ACTIVE | diff --git a/drivers/nvdimm/btt.c b/drivers/nvdimm/btt.c index 14323fa..6049164 100644 --- a/drivers/nvdimm/btt.c +++ b/drivers/nvdimm/btt.c @@ -1241,8 +1241,10 @@ static int btt_rw_page(struct block_device *bdev, sector_t sector, { struct btt *btt = bdev->bd_disk->private_data; int rc; + unsigned int len; - rc = btt_do_bvec(btt, NULL, page, PAGE_SIZE, 0, is_write, sector); + len = hpage_nr_pages(page) * PAGE_SIZE; + rc = btt_do_bvec(btt, NULL, page, len, 0, is_write, sector); if (rc == 0) page_endio(page, is_write, 0); diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c index f7099ada..e9aa453 100644 --- a/drivers/nvdimm/pmem.c +++ b/drivers/nvdimm/pmem.c @@ -80,22 +80,40 @@ static blk_status_t pmem_clear_poison(struct pmem_device *pmem, static void write_pmem(void *pmem_addr, struct page *page, unsigned int off, unsigned int len) { - void *mem = kmap_atomic(page); - - memcpy_flushcache(pmem_addr, mem + off, len); - kunmap_atomic(mem); + unsigned int chunk; + void *mem; + + while (len) { + mem = kmap_atomic(page); + chunk = min_t(unsigned int, len, PAGE_SIZE); + memcpy_flushcache(pmem_addr, mem + off, chunk); + kunmap_atomic(mem); + len -= chunk; + off = 0; + page++; + pmem_addr += PAGE_SIZE; + } } static blk_status_t read_pmem(struct page *page, unsigned int off, void *pmem_addr, unsigned int len) { + unsigned int chunk; int rc; - void *mem = kmap_atomic(page); - - rc = memcpy_mcsafe(mem + off, pmem_addr, len); - kunmap_atomic(mem); - if (rc) - return BLK_STS_IOERR; + void *mem; + + while (len) { + mem = kmap_atomic(page); + chunk = min_t(unsigned int, len, PAGE_SIZE); + rc = memcpy_mcsafe(mem + off, pmem_addr, chunk); + kunmap_atomic(mem); + if (rc) + return BLK_STS_IOERR; + len -= chunk; + off = 0; + page++; + pmem_addr += PAGE_SIZE; + } return BLK_STS_OK; } @@ -188,7 +206,8 @@ static int pmem_rw_page(struct block_device *bdev, sector_t sector, struct pmem_device *pmem = bdev->bd_queue->queuedata; blk_status_t rc; - rc = pmem_do_bvec(pmem, page, PAGE_SIZE, 0, is_write, sector); + rc = pmem_do_bvec(pmem, page, hpage_nr_pages(page) * PAGE_SIZE, + 0, is_write, sector); /* * The ->rw_page interface is subtle and tricky. The core diff --git a/fs/9p/cache.c b/fs/9p/cache.c index 103ca5e..64c58eb2 100644 --- a/fs/9p/cache.c +++ b/fs/9p/cache.c @@ -151,34 +151,6 @@ fscache_checkaux v9fs_cache_inode_check_aux(void *cookie_netfs_data, return FSCACHE_CHECKAUX_OKAY; } -static void v9fs_cache_inode_now_uncached(void *cookie_netfs_data) -{ - struct v9fs_inode *v9inode = cookie_netfs_data; - struct pagevec pvec; - pgoff_t first; - int loop, nr_pages; - - pagevec_init(&pvec, 0); - first = 0; - - for (;;) { - nr_pages = pagevec_lookup(&pvec, v9inode->vfs_inode.i_mapping, - first, - PAGEVEC_SIZE - pagevec_count(&pvec)); - if (!nr_pages) - break; - - for (loop = 0; loop < nr_pages; loop++) - ClearPageFsCache(pvec.pages[loop]); - - first = pvec.pages[nr_pages - 1]->index + 1; - - pvec.nr = nr_pages; - pagevec_release(&pvec); - cond_resched(); - } -} - const struct fscache_cookie_def v9fs_cache_inode_index_def = { .name = "9p.inode", .type = FSCACHE_COOKIE_TYPE_DATAFILE, @@ -186,7 +158,6 @@ const struct fscache_cookie_def v9fs_cache_inode_index_def = { .get_attr = v9fs_cache_inode_get_attr, .get_aux = v9fs_cache_inode_get_aux, .check_aux = v9fs_cache_inode_check_aux, - .now_uncached = v9fs_cache_inode_now_uncached, }; void v9fs_cache_inode_get_cookie(struct inode *inode) diff --git a/fs/afs/cache.c b/fs/afs/cache.c index 577763c3..1fe8551 100644 --- a/fs/afs/cache.c +++ b/fs/afs/cache.c @@ -39,7 +39,6 @@ static uint16_t afs_vnode_cache_get_aux(const void *cookie_netfs_data, static enum fscache_checkaux afs_vnode_cache_check_aux(void *cookie_netfs_data, const void *buffer, uint16_t buflen); -static void afs_vnode_cache_now_uncached(void *cookie_netfs_data); struct fscache_netfs afs_cache_netfs = { .name = "afs", @@ -75,7 +74,6 @@ struct fscache_cookie_def afs_vnode_cache_index_def = { .get_attr = afs_vnode_cache_get_attr, .get_aux = afs_vnode_cache_get_aux, .check_aux = afs_vnode_cache_check_aux, - .now_uncached = afs_vnode_cache_now_uncached, }; /* @@ -359,44 +357,3 @@ static enum fscache_checkaux afs_vnode_cache_check_aux(void *cookie_netfs_data, _leave(" = SUCCESS"); return FSCACHE_CHECKAUX_OKAY; } - -/* - * indication the cookie is no longer uncached - * - this function is called when the backing store currently caching a cookie - * is removed - * - the netfs should use this to clean up any markers indicating cached pages - * - this is mandatory for any object that may have data - */ -static void afs_vnode_cache_now_uncached(void *cookie_netfs_data) -{ - struct afs_vnode *vnode = cookie_netfs_data; - struct pagevec pvec; - pgoff_t first; - int loop, nr_pages; - - _enter("{%x,%x,%Lx}", - vnode->fid.vnode, vnode->fid.unique, vnode->status.data_version); - - pagevec_init(&pvec, 0); - first = 0; - - for (;;) { - /* grab a bunch of pages to clean */ - nr_pages = pagevec_lookup(&pvec, vnode->vfs_inode.i_mapping, - first, - PAGEVEC_SIZE - pagevec_count(&pvec)); - if (!nr_pages) - break; - - for (loop = 0; loop < nr_pages; loop++) - ClearPageFsCache(pvec.pages[loop]); - - first = pvec.pages[nr_pages - 1]->index + 1; - - pvec.nr = nr_pages; - pagevec_release(&pvec); - cond_resched(); - } - - _leave(""); -} diff --git a/fs/buffer.c b/fs/buffer.c index 5715dac..50da0e1 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -1627,20 +1627,17 @@ void clean_bdev_aliases(struct block_device *bdev, sector_t block, sector_t len) struct pagevec pvec; pgoff_t index = block >> (PAGE_SHIFT - bd_inode->i_blkbits); pgoff_t end; - int i; + int i, count; struct buffer_head *bh; struct buffer_head *head; end = (block + len - 1) >> (PAGE_SHIFT - bd_inode->i_blkbits); pagevec_init(&pvec, 0); - while (index <= end && pagevec_lookup(&pvec, bd_mapping, index, - min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1)) { - for (i = 0; i < pagevec_count(&pvec); i++) { + while (pagevec_lookup_range(&pvec, bd_mapping, &index, end)) { + count = pagevec_count(&pvec); + for (i = 0; i < count; i++) { struct page *page = pvec.pages[i]; - index = page->index; - if (index > end) - break; if (!page_has_buffers(page)) continue; /* @@ -1670,7 +1667,9 @@ unlock_page: } pagevec_release(&pvec); cond_resched(); - index++; + /* End of range already reached? */ + if (index > end || !index) + break; } } EXPORT_SYMBOL(clean_bdev_aliases); @@ -3549,10 +3548,10 @@ page_cache_seek_hole_data(struct inode *inode, loff_t offset, loff_t length, pagevec_init(&pvec, 0); do { - unsigned want, nr_pages, i; + unsigned nr_pages, i; - want = min_t(unsigned, end - index, PAGEVEC_SIZE); - nr_pages = pagevec_lookup(&pvec, inode->i_mapping, index, want); + nr_pages = pagevec_lookup_range(&pvec, inode->i_mapping, &index, + end - 1); if (nr_pages == 0) break; @@ -3573,10 +3572,6 @@ page_cache_seek_hole_data(struct inode *inode, loff_t offset, loff_t length, lastoff < page_offset(page)) goto check_range; - /* Searching done if the page index is out of range. */ - if (page->index >= end) - goto not_found; - lock_page(page); if (likely(page->mapping == inode->i_mapping) && page_has_buffers(page)) { @@ -3589,12 +3584,6 @@ page_cache_seek_hole_data(struct inode *inode, loff_t offset, loff_t length, unlock_page(page); lastoff = page_offset(page) + PAGE_SIZE; } - - /* Searching done if fewer pages returned than wanted. */ - if (nr_pages < want) - break; - - index = pvec.pages[i - 1]->index + 1; pagevec_release(&pvec); } while (index < end); diff --git a/fs/ceph/cache.c b/fs/ceph/cache.c index 337f886..174d6e6 100644 --- a/fs/ceph/cache.c +++ b/fs/ceph/cache.c @@ -194,36 +194,6 @@ static enum fscache_checkaux ceph_fscache_inode_check_aux( return FSCACHE_CHECKAUX_OKAY; } -static void ceph_fscache_inode_now_uncached(void* cookie_netfs_data) -{ - struct ceph_inode_info* ci = cookie_netfs_data; - struct pagevec pvec; - pgoff_t first; - int loop, nr_pages; - - pagevec_init(&pvec, 0); - first = 0; - - dout("ceph inode 0x%p now uncached", ci); - - while (1) { - nr_pages = pagevec_lookup(&pvec, ci->vfs_inode.i_mapping, first, - PAGEVEC_SIZE - pagevec_count(&pvec)); - - if (!nr_pages) - break; - - for (loop = 0; loop < nr_pages; loop++) - ClearPageFsCache(pvec.pages[loop]); - - first = pvec.pages[nr_pages - 1]->index + 1; - - pvec.nr = nr_pages; - pagevec_release(&pvec); - cond_resched(); - } -} - static const struct fscache_cookie_def ceph_fscache_inode_object_def = { .name = "CEPH.inode", .type = FSCACHE_COOKIE_TYPE_DATAFILE, @@ -231,7 +201,6 @@ static const struct fscache_cookie_def ceph_fscache_inode_object_def = { .get_attr = ceph_fscache_inode_get_attr, .get_aux = ceph_fscache_inode_get_aux, .check_aux = ceph_fscache_inode_check_aux, - .now_uncached = ceph_fscache_inode_now_uncached, }; void ceph_fscache_register_inode_cookie(struct inode *inode) diff --git a/fs/cifs/cache.c b/fs/cifs/cache.c index 6c665bf..2c14020 100644 --- a/fs/cifs/cache.c +++ b/fs/cifs/cache.c @@ -292,36 +292,6 @@ fscache_checkaux cifs_fscache_inode_check_aux(void *cookie_netfs_data, return FSCACHE_CHECKAUX_OKAY; } -static void cifs_fscache_inode_now_uncached(void *cookie_netfs_data) -{ - struct cifsInodeInfo *cifsi = cookie_netfs_data; - struct pagevec pvec; - pgoff_t first; - int loop, nr_pages; - - pagevec_init(&pvec, 0); - first = 0; - - cifs_dbg(FYI, "%s: cifs inode 0x%p now uncached\n", __func__, cifsi); - - for (;;) { - nr_pages = pagevec_lookup(&pvec, - cifsi->vfs_inode.i_mapping, first, - PAGEVEC_SIZE - pagevec_count(&pvec)); - if (!nr_pages) - break; - - for (loop = 0; loop < nr_pages; loop++) - ClearPageFsCache(pvec.pages[loop]); - - first = pvec.pages[nr_pages - 1]->index + 1; - - pvec.nr = nr_pages; - pagevec_release(&pvec); - cond_resched(); - } -} - const struct fscache_cookie_def cifs_fscache_inode_object_def = { .name = "CIFS.uniqueid", .type = FSCACHE_COOKIE_TYPE_DATAFILE, @@ -329,5 +299,4 @@ const struct fscache_cookie_def cifs_fscache_inode_object_def = { .get_attr = cifs_fscache_inode_get_attr, .get_aux = cifs_fscache_inode_get_aux, .check_aux = cifs_fscache_inode_check_aux, - .now_uncached = cifs_fscache_inode_now_uncached, }; @@ -42,6 +42,9 @@ #define DAX_WAIT_TABLE_BITS 12 #define DAX_WAIT_TABLE_ENTRIES (1 << DAX_WAIT_TABLE_BITS) +/* The 'colour' (ie low bits) within a PMD of a page offset. */ +#define PG_PMD_COLOUR ((PMD_SIZE >> PAGE_SHIFT) - 1) + static wait_queue_head_t wait_table[DAX_WAIT_TABLE_ENTRIES]; static int __init init_dax_wait_table(void) @@ -54,6 +57,40 @@ static int __init init_dax_wait_table(void) } fs_initcall(init_dax_wait_table); +/* + * We use lowest available bit in exceptional entry for locking, one bit for + * the entry size (PMD) and two more to tell us if the entry is a zero page or + * an empty entry that is just used for locking. In total four special bits. + * + * If the PMD bit isn't set the entry has size PAGE_SIZE, and if the ZERO_PAGE + * and EMPTY bits aren't set the entry is a normal DAX entry with a filesystem + * block allocation. + */ +#define RADIX_DAX_SHIFT (RADIX_TREE_EXCEPTIONAL_SHIFT + 4) +#define RADIX_DAX_ENTRY_LOCK (1 << RADIX_TREE_EXCEPTIONAL_SHIFT) +#define RADIX_DAX_PMD (1 << (RADIX_TREE_EXCEPTIONAL_SHIFT + 1)) +#define RADIX_DAX_ZERO_PAGE (1 << (RADIX_TREE_EXCEPTIONAL_SHIFT + 2)) +#define RADIX_DAX_EMPTY (1 << (RADIX_TREE_EXCEPTIONAL_SHIFT + 3)) + +static unsigned long dax_radix_sector(void *entry) +{ + return (unsigned long)entry >> RADIX_DAX_SHIFT; +} + +static void *dax_radix_locked_entry(sector_t sector, unsigned long flags) +{ + return (void *)(RADIX_TREE_EXCEPTIONAL_ENTRY | flags | + ((unsigned long)sector << RADIX_DAX_SHIFT) | + RADIX_DAX_ENTRY_LOCK); +} + +static unsigned int dax_radix_order(void *entry) +{ + if ((unsigned long)entry & RADIX_DAX_PMD) + return PMD_SHIFT - PAGE_SHIFT; + return 0; +} + static int dax_is_pmd_entry(void *entry) { return (unsigned long)entry & RADIX_DAX_PMD; @@ -66,7 +103,7 @@ static int dax_is_pte_entry(void *entry) static int dax_is_zero_entry(void *entry) { - return (unsigned long)entry & RADIX_DAX_HZP; + return (unsigned long)entry & RADIX_DAX_ZERO_PAGE; } static int dax_is_empty_entry(void *entry) @@ -98,7 +135,7 @@ static wait_queue_head_t *dax_entry_waitqueue(struct address_space *mapping, * the range covered by the PMD map to the same bit lock. */ if (dax_is_pmd_entry(entry)) - index &= ~((1UL << (PMD_SHIFT - PAGE_SHIFT)) - 1); + index &= ~PG_PMD_COLOUR; key->mapping = mapping; key->entry_start = index; @@ -121,6 +158,31 @@ static int wake_exceptional_entry_func(wait_queue_entry_t *wait, unsigned int mo } /* + * We do not necessarily hold the mapping->tree_lock when we call this + * function so it is possible that 'entry' is no longer a valid item in the + * radix tree. This is okay because all we really need to do is to find the + * correct waitqueue where tasks might be waiting for that old 'entry' and + * wake them. + */ +static void dax_wake_mapping_entry_waiter(struct address_space *mapping, + pgoff_t index, void *entry, bool wake_all) +{ + struct exceptional_entry_key key; + wait_queue_head_t *wq; + + wq = dax_entry_waitqueue(mapping, index, entry, &key); + + /* + * Checking for locked entry and prepare_to_wait_exclusive() happens + * under mapping->tree_lock, ditto for entry handling in our callers. + * So at this point all tasks that could have seen our entry locked + * must be in the waitqueue and the following check will see them. + */ + if (waitqueue_active(wq)) + __wake_up(wq, TASK_NORMAL, wake_all ? 0 : 1, &key); +} + +/* * Check whether the given slot is locked. The function must be called with * mapping->tree_lock held */ @@ -181,7 +243,8 @@ static void *get_unlocked_mapping_entry(struct address_space *mapping, for (;;) { entry = __radix_tree_lookup(&mapping->page_tree, index, NULL, &slot); - if (!entry || !radix_tree_exceptional_entry(entry) || + if (!entry || + WARN_ON_ONCE(!radix_tree_exceptional_entry(entry)) || !slot_locked(mapping, slot)) { if (slotp) *slotp = slot; @@ -216,14 +279,9 @@ static void dax_unlock_mapping_entry(struct address_space *mapping, } static void put_locked_mapping_entry(struct address_space *mapping, - pgoff_t index, void *entry) + pgoff_t index) { - if (!radix_tree_exceptional_entry(entry)) { - unlock_page(entry); - put_page(entry); - } else { - dax_unlock_mapping_entry(mapping, index); - } + dax_unlock_mapping_entry(mapping, index); } /* @@ -233,7 +291,7 @@ static void put_locked_mapping_entry(struct address_space *mapping, static void put_unlocked_mapping_entry(struct address_space *mapping, pgoff_t index, void *entry) { - if (!radix_tree_exceptional_entry(entry)) + if (!entry) return; /* We have to wake up next waiter for the radix tree entry lock */ @@ -241,15 +299,15 @@ static void put_unlocked_mapping_entry(struct address_space *mapping, } /* - * Find radix tree entry at given index. If it points to a page, return with - * the page locked. If it points to the exceptional entry, return with the - * radix tree entry locked. If the radix tree doesn't contain given index, - * create empty exceptional entry for the index and return with it locked. + * Find radix tree entry at given index. If it points to an exceptional entry, + * return it with the radix tree entry locked. If the radix tree doesn't + * contain given index, create an empty exceptional entry for the index and + * return with it locked. * * When requesting an entry with size RADIX_DAX_PMD, grab_mapping_entry() will * either return that locked entry or will return an error. This error will - * happen if there are any 4k entries (either zero pages or DAX entries) - * within the 2MiB range that we are requesting. + * happen if there are any 4k entries within the 2MiB range that we are + * requesting. * * We always favor 4k entries over 2MiB entries. There isn't a flow where we * evict 4k entries in order to 'upgrade' them to a 2MiB entry. A 2MiB @@ -276,18 +334,21 @@ restart: spin_lock_irq(&mapping->tree_lock); entry = get_unlocked_mapping_entry(mapping, index, &slot); + if (WARN_ON_ONCE(entry && !radix_tree_exceptional_entry(entry))) { + entry = ERR_PTR(-EIO); + goto out_unlock; + } + if (entry) { if (size_flag & RADIX_DAX_PMD) { - if (!radix_tree_exceptional_entry(entry) || - dax_is_pte_entry(entry)) { + if (dax_is_pte_entry(entry)) { put_unlocked_mapping_entry(mapping, index, entry); entry = ERR_PTR(-EEXIST); goto out_unlock; } } else { /* trying to grab a PTE entry */ - if (radix_tree_exceptional_entry(entry) && - dax_is_pmd_entry(entry) && + if (dax_is_pmd_entry(entry) && (dax_is_zero_entry(entry) || dax_is_empty_entry(entry))) { pmd_downgrade = true; @@ -321,7 +382,7 @@ restart: mapping_gfp_mask(mapping) & ~__GFP_HIGHMEM); if (err) { if (pmd_downgrade) - put_locked_mapping_entry(mapping, index, entry); + put_locked_mapping_entry(mapping, index); return ERR_PTR(err); } spin_lock_irq(&mapping->tree_lock); @@ -371,52 +432,12 @@ restart: spin_unlock_irq(&mapping->tree_lock); return entry; } - /* Normal page in radix tree? */ - if (!radix_tree_exceptional_entry(entry)) { - struct page *page = entry; - - get_page(page); - spin_unlock_irq(&mapping->tree_lock); - lock_page(page); - /* Page got truncated? Retry... */ - if (unlikely(page->mapping != mapping)) { - unlock_page(page); - put_page(page); - goto restart; - } - return page; - } entry = lock_slot(mapping, slot); out_unlock: spin_unlock_irq(&mapping->tree_lock); return entry; } -/* - * We do not necessarily hold the mapping->tree_lock when we call this - * function so it is possible that 'entry' is no longer a valid item in the - * radix tree. This is okay because all we really need to do is to find the - * correct waitqueue where tasks might be waiting for that old 'entry' and - * wake them. - */ -void dax_wake_mapping_entry_waiter(struct address_space *mapping, - pgoff_t index, void *entry, bool wake_all) -{ - struct exceptional_entry_key key; - wait_queue_head_t *wq; - - wq = dax_entry_waitqueue(mapping, index, entry, &key); - - /* - * Checking for locked entry and prepare_to_wait_exclusive() happens - * under mapping->tree_lock, ditto for entry handling in our callers. - * So at this point all tasks that could have seen our entry locked - * must be in the waitqueue and the following check will see them. - */ - if (waitqueue_active(wq)) - __wake_up(wq, TASK_NORMAL, wake_all ? 0 : 1, &key); -} - static int __dax_invalidate_mapping_entry(struct address_space *mapping, pgoff_t index, bool trunc) { @@ -426,7 +447,7 @@ static int __dax_invalidate_mapping_entry(struct address_space *mapping, spin_lock_irq(&mapping->tree_lock); entry = get_unlocked_mapping_entry(mapping, index, NULL); - if (!entry || !radix_tree_exceptional_entry(entry)) + if (!entry || WARN_ON_ONCE(!radix_tree_exceptional_entry(entry))) goto out; if (!trunc && (radix_tree_tag_get(page_tree, index, PAGECACHE_TAG_DIRTY) || @@ -468,50 +489,6 @@ int dax_invalidate_mapping_entry_sync(struct address_space *mapping, return __dax_invalidate_mapping_entry(mapping, index, false); } -/* - * The user has performed a load from a hole in the file. Allocating - * a new page in the file would cause excessive storage usage for - * workloads with sparse files. We allocate a page cache page instead. - * We'll kick it out of the page cache if it's ever written to, - * otherwise it will simply fall out of the page cache under memory - * pressure without ever having been dirtied. - */ -static int dax_load_hole(struct address_space *mapping, void **entry, - struct vm_fault *vmf) -{ - struct inode *inode = mapping->host; - struct page *page; - int ret; - - /* Hole page already exists? Return it... */ - if (!radix_tree_exceptional_entry(*entry)) { - page = *entry; - goto finish_fault; - } - - /* This will replace locked radix tree entry with a hole page */ - page = find_or_create_page(mapping, vmf->pgoff, - vmf->gfp_mask | __GFP_ZERO); - if (!page) { - ret = VM_FAULT_OOM; - goto out; - } - -finish_fault: - vmf->page = page; - ret = finish_fault(vmf); - vmf->page = NULL; - *entry = page; - if (!ret) { - /* Grab reference for PTE that is now referencing the page */ - get_page(page); - ret = VM_FAULT_NOPAGE; - } -out: - trace_dax_load_hole(inode, vmf, ret); - return ret; -} - static int copy_user_dax(struct block_device *bdev, struct dax_device *dax_dev, sector_t sector, size_t size, struct page *to, unsigned long vaddr) @@ -552,47 +529,27 @@ static void *dax_insert_mapping_entry(struct address_space *mapping, unsigned long flags) { struct radix_tree_root *page_tree = &mapping->page_tree; - int error = 0; - bool hole_fill = false; void *new_entry; pgoff_t index = vmf->pgoff; if (vmf->flags & FAULT_FLAG_WRITE) __mark_inode_dirty(mapping->host, I_DIRTY_PAGES); - /* Replacing hole page with block mapping? */ - if (!radix_tree_exceptional_entry(entry)) { - hole_fill = true; - /* - * Unmap the page now before we remove it from page cache below. - * The page is locked so it cannot be faulted in again. - */ - unmap_mapping_range(mapping, vmf->pgoff << PAGE_SHIFT, - PAGE_SIZE, 0); - error = radix_tree_preload(vmf->gfp_mask & ~__GFP_HIGHMEM); - if (error) - return ERR_PTR(error); - } else if (dax_is_zero_entry(entry) && !(flags & RADIX_DAX_HZP)) { - /* replacing huge zero page with PMD block mapping */ - unmap_mapping_range(mapping, - (vmf->pgoff << PAGE_SHIFT) & PMD_MASK, PMD_SIZE, 0); + if (dax_is_zero_entry(entry) && !(flags & RADIX_DAX_ZERO_PAGE)) { + /* we are replacing a zero page with block mapping */ + if (dax_is_pmd_entry(entry)) + unmap_mapping_range(mapping, + (vmf->pgoff << PAGE_SHIFT) & PMD_MASK, + PMD_SIZE, 0); + else /* pte entry */ + unmap_mapping_range(mapping, vmf->pgoff << PAGE_SHIFT, + PAGE_SIZE, 0); } spin_lock_irq(&mapping->tree_lock); new_entry = dax_radix_locked_entry(sector, flags); - if (hole_fill) { - __delete_from_page_cache(entry, NULL); - /* Drop pagecache reference */ - put_page(entry); - error = __radix_tree_insert(page_tree, index, - dax_radix_order(new_entry), new_entry); - if (error) { - new_entry = ERR_PTR(error); - goto unlock; - } - mapping->nrexceptional++; - } else if (dax_is_zero_entry(entry) || dax_is_empty_entry(entry)) { + if (dax_is_zero_entry(entry) || dax_is_empty_entry(entry)) { /* * Only swap our new entry into the radix tree if the current * entry is a zero page or an empty entry. If a normal PTE or @@ -609,23 +566,14 @@ static void *dax_insert_mapping_entry(struct address_space *mapping, WARN_ON_ONCE(ret != entry); __radix_tree_replace(page_tree, node, slot, new_entry, NULL, NULL); + entry = new_entry; } + if (vmf->flags & FAULT_FLAG_WRITE) radix_tree_tag_set(page_tree, index, PAGECACHE_TAG_DIRTY); - unlock: + spin_unlock_irq(&mapping->tree_lock); - if (hole_fill) { - radix_tree_preload_end(); - /* - * We don't need hole page anymore, it has been replaced with - * locked radix tree entry now. - */ - if (mapping->a_ops->freepage) - mapping->a_ops->freepage(entry); - unlock_page(entry); - put_page(entry); - } - return new_entry; + return entry; } static inline unsigned long @@ -727,7 +675,7 @@ static int dax_writeback_one(struct block_device *bdev, spin_lock_irq(&mapping->tree_lock); entry2 = get_unlocked_mapping_entry(mapping, index, &slot); /* Entry got punched out / reallocated? */ - if (!entry2 || !radix_tree_exceptional_entry(entry2)) + if (!entry2 || WARN_ON_ONCE(!radix_tree_exceptional_entry(entry2))) goto put_unlocked; /* * Entry got reallocated elsewhere? No need to writeback. We have to @@ -799,7 +747,7 @@ static int dax_writeback_one(struct block_device *bdev, trace_dax_writeback_one(mapping->host, index, size >> PAGE_SHIFT); dax_unlock: dax_read_unlock(id); - put_locked_mapping_entry(mapping, index, entry); + put_locked_mapping_entry(mapping, index); return ret; put_unlocked: @@ -874,11 +822,10 @@ EXPORT_SYMBOL_GPL(dax_writeback_mapping_range); static int dax_insert_mapping(struct address_space *mapping, struct block_device *bdev, struct dax_device *dax_dev, - sector_t sector, size_t size, void **entryp, + sector_t sector, size_t size, void *entry, struct vm_area_struct *vma, struct vm_fault *vmf) { unsigned long vaddr = vmf->address; - void *entry = *entryp; void *ret, *kaddr; pgoff_t pgoff; int id, rc; @@ -899,47 +846,48 @@ static int dax_insert_mapping(struct address_space *mapping, ret = dax_insert_mapping_entry(mapping, vmf, entry, sector, 0); if (IS_ERR(ret)) return PTR_ERR(ret); - *entryp = ret; trace_dax_insert_mapping(mapping->host, vmf, ret); - return vm_insert_mixed(vma, vaddr, pfn); + if (vmf->flags & FAULT_FLAG_WRITE) + return vm_insert_mixed_mkwrite(vma, vaddr, pfn); + else + return vm_insert_mixed(vma, vaddr, pfn); } -/** - * dax_pfn_mkwrite - handle first write to DAX page - * @vmf: The description of the fault +/* + * The user has performed a load from a hole in the file. Allocating a new + * page in the file would cause excessive storage usage for workloads with + * sparse files. Instead we insert a read-only mapping of the 4k zero page. + * If this page is ever written to we will re-fault and change the mapping to + * point to real DAX storage instead. */ -int dax_pfn_mkwrite(struct vm_fault *vmf) +static int dax_load_hole(struct address_space *mapping, void *entry, + struct vm_fault *vmf) { - struct file *file = vmf->vma->vm_file; - struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; - void *entry, **slot; - pgoff_t index = vmf->pgoff; + unsigned long vaddr = vmf->address; + int ret = VM_FAULT_NOPAGE; + struct page *zero_page; + void *entry2; - spin_lock_irq(&mapping->tree_lock); - entry = get_unlocked_mapping_entry(mapping, index, &slot); - if (!entry || !radix_tree_exceptional_entry(entry)) { - if (entry) - put_unlocked_mapping_entry(mapping, index, entry); - spin_unlock_irq(&mapping->tree_lock); - trace_dax_pfn_mkwrite_no_entry(inode, vmf, VM_FAULT_NOPAGE); - return VM_FAULT_NOPAGE; + zero_page = ZERO_PAGE(0); + if (unlikely(!zero_page)) { + ret = VM_FAULT_OOM; + goto out; } - radix_tree_tag_set(&mapping->page_tree, index, PAGECACHE_TAG_DIRTY); - entry = lock_slot(mapping, slot); - spin_unlock_irq(&mapping->tree_lock); - /* - * If we race with somebody updating the PTE and finish_mkwrite_fault() - * fails, we don't care. We need to return VM_FAULT_NOPAGE and retry - * the fault in either case. - */ - finish_mkwrite_fault(vmf); - put_locked_mapping_entry(mapping, index, entry); - trace_dax_pfn_mkwrite(inode, vmf, VM_FAULT_NOPAGE); - return VM_FAULT_NOPAGE; + + entry2 = dax_insert_mapping_entry(mapping, vmf, entry, 0, + RADIX_DAX_ZERO_PAGE); + if (IS_ERR(entry2)) { + ret = VM_FAULT_SIGBUS; + goto out; + } + + vm_insert_mixed(vmf->vma, vaddr, page_to_pfn_t(zero_page)); +out: + trace_dax_load_hole(inode, vmf, ret); + return ret; } -EXPORT_SYMBOL_GPL(dax_pfn_mkwrite); static bool dax_range_is_aligned(struct block_device *bdev, unsigned int offset, unsigned int length) @@ -1059,6 +1007,11 @@ dax_iomap_actor(struct inode *inode, loff_t pos, loff_t length, void *data, if (map_len > end - pos) map_len = end - pos; + /* + * The userspace address for the memory copy has already been + * validated via access_ok() in either vfs_read() or + * vfs_write(), depending on which operation we are doing. + */ if (iov_iter_rw(iter) == WRITE) map_len = dax_copy_from_iter(dax_dev, pgoff, kaddr, map_len, iter); @@ -1223,7 +1176,7 @@ static int dax_iomap_pte_fault(struct vm_fault *vmf, major = VM_FAULT_MAJOR; } error = dax_insert_mapping(mapping, iomap.bdev, iomap.dax_dev, - sector, PAGE_SIZE, &entry, vmf->vma, vmf); + sector, PAGE_SIZE, entry, vmf->vma, vmf); /* -EBUSY is fine, somebody else faulted on the same PTE */ if (error == -EBUSY) error = 0; @@ -1231,7 +1184,7 @@ static int dax_iomap_pte_fault(struct vm_fault *vmf, case IOMAP_UNWRITTEN: case IOMAP_HOLE: if (!(vmf->flags & FAULT_FLAG_WRITE)) { - vmf_ret = dax_load_hole(mapping, &entry, vmf); + vmf_ret = dax_load_hole(mapping, entry, vmf); goto finish_iomap; } /*FALLTHRU*/ @@ -1258,21 +1211,15 @@ static int dax_iomap_pte_fault(struct vm_fault *vmf, ops->iomap_end(inode, pos, PAGE_SIZE, copied, flags, &iomap); } unlock_entry: - put_locked_mapping_entry(mapping, vmf->pgoff, entry); + put_locked_mapping_entry(mapping, vmf->pgoff); out: trace_dax_pte_fault_done(inode, vmf, vmf_ret); return vmf_ret; } #ifdef CONFIG_FS_DAX_PMD -/* - * The 'colour' (ie low bits) within a PMD of a page offset. This comes up - * more often than one might expect in the below functions. - */ -#define PG_PMD_COLOUR ((PMD_SIZE >> PAGE_SHIFT) - 1) - static int dax_pmd_insert_mapping(struct vm_fault *vmf, struct iomap *iomap, - loff_t pos, void **entryp) + loff_t pos, void *entry) { struct address_space *mapping = vmf->vma->vm_file->f_mapping; const sector_t sector = dax_iomap_sector(iomap, pos); @@ -1283,7 +1230,7 @@ static int dax_pmd_insert_mapping(struct vm_fault *vmf, struct iomap *iomap, void *ret = NULL, *kaddr; long length = 0; pgoff_t pgoff; - pfn_t pfn; + pfn_t pfn = {}; int id; if (bdev_dax_pgoff(bdev, sector, size, &pgoff) != 0) @@ -1303,11 +1250,10 @@ static int dax_pmd_insert_mapping(struct vm_fault *vmf, struct iomap *iomap, goto unlock_fallback; dax_read_unlock(id); - ret = dax_insert_mapping_entry(mapping, vmf, *entryp, sector, + ret = dax_insert_mapping_entry(mapping, vmf, entry, sector, RADIX_DAX_PMD); if (IS_ERR(ret)) goto fallback; - *entryp = ret; trace_dax_pmd_insert_mapping(inode, vmf, length, pfn, ret); return vmf_insert_pfn_pmd(vmf->vma, vmf->address, vmf->pmd, @@ -1321,7 +1267,7 @@ fallback: } static int dax_pmd_load_hole(struct vm_fault *vmf, struct iomap *iomap, - void **entryp) + void *entry) { struct address_space *mapping = vmf->vma->vm_file->f_mapping; unsigned long pmd_addr = vmf->address & PMD_MASK; @@ -1336,11 +1282,10 @@ static int dax_pmd_load_hole(struct vm_fault *vmf, struct iomap *iomap, if (unlikely(!zero_page)) goto fallback; - ret = dax_insert_mapping_entry(mapping, vmf, *entryp, 0, - RADIX_DAX_PMD | RADIX_DAX_HZP); + ret = dax_insert_mapping_entry(mapping, vmf, entry, 0, + RADIX_DAX_PMD | RADIX_DAX_ZERO_PAGE); if (IS_ERR(ret)) goto fallback; - *entryp = ret; ptl = pmd_lock(vmf->vma->vm_mm, vmf->pmd); if (!pmd_none(*(vmf->pmd))) { @@ -1416,10 +1361,10 @@ static int dax_iomap_pmd_fault(struct vm_fault *vmf, goto fallback; /* - * grab_mapping_entry() will make sure we get a 2M empty entry, a DAX - * PMD or a HZP entry. If it can't (because a 4k page is already in - * the tree, for instance), it will return -EEXIST and we just fall - * back to 4k entries. + * grab_mapping_entry() will make sure we get a 2MiB empty entry, a + * 2MiB zero page entry or a DAX PMD. If it can't (because a 4k page + * is already in the tree, for instance), it will return -EEXIST and + * we just fall back to 4k entries. */ entry = grab_mapping_entry(mapping, pgoff, RADIX_DAX_PMD); if (IS_ERR(entry)) @@ -1452,13 +1397,13 @@ static int dax_iomap_pmd_fault(struct vm_fault *vmf, switch (iomap.type) { case IOMAP_MAPPED: - result = dax_pmd_insert_mapping(vmf, &iomap, pos, &entry); + result = dax_pmd_insert_mapping(vmf, &iomap, pos, entry); break; case IOMAP_UNWRITTEN: case IOMAP_HOLE: if (WARN_ON_ONCE(write)) break; - result = dax_pmd_load_hole(vmf, &iomap, &entry); + result = dax_pmd_load_hole(vmf, &iomap, entry); break; default: WARN_ON_ONCE(1); @@ -1481,7 +1426,7 @@ static int dax_iomap_pmd_fault(struct vm_fault *vmf, &iomap); } unlock_entry: - put_locked_mapping_entry(mapping, pgoff, entry); + put_locked_mapping_entry(mapping, pgoff); fallback: if (result == VM_FAULT_FALLBACK) { split_huge_pmd(vma, vmf->pmd, vmf->address); diff --git a/fs/ext2/file.c b/fs/ext2/file.c index d34d32b..ff3a363 100644 --- a/fs/ext2/file.c +++ b/fs/ext2/file.c @@ -107,29 +107,6 @@ static int ext2_dax_fault(struct vm_fault *vmf) return ret; } -static int ext2_dax_pfn_mkwrite(struct vm_fault *vmf) -{ - struct inode *inode = file_inode(vmf->vma->vm_file); - struct ext2_inode_info *ei = EXT2_I(inode); - loff_t size; - int ret; - - sb_start_pagefault(inode->i_sb); - file_update_time(vmf->vma->vm_file); - down_read(&ei->dax_sem); - - /* check that the faulting page hasn't raced with truncate */ - size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT; - if (vmf->pgoff >= size) - ret = VM_FAULT_SIGBUS; - else - ret = dax_pfn_mkwrite(vmf); - - up_read(&ei->dax_sem); - sb_end_pagefault(inode->i_sb); - return ret; -} - static const struct vm_operations_struct ext2_dax_vm_ops = { .fault = ext2_dax_fault, /* @@ -138,7 +115,7 @@ static const struct vm_operations_struct ext2_dax_vm_ops = { * will always fail and fail back to regular faults. */ .page_mkwrite = ext2_dax_fault, - .pfn_mkwrite = ext2_dax_pfn_mkwrite, + .pfn_mkwrite = ext2_dax_fault, }; static int ext2_file_mmap(struct file *file, struct vm_area_struct *vma) diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 197653e..57dcaea 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -324,41 +324,11 @@ static int ext4_dax_fault(struct vm_fault *vmf) return ext4_dax_huge_fault(vmf, PE_SIZE_PTE); } -/* - * Handle write fault for VM_MIXEDMAP mappings. Similarly to ext4_dax_fault() - * handler we check for races agaist truncate. Note that since we cycle through - * i_mmap_sem, we are sure that also any hole punching that began before we - * were called is finished by now and so if it included part of the file we - * are working on, our pte will get unmapped and the check for pte_same() in - * wp_pfn_shared() fails. Thus fault gets retried and things work out as - * desired. - */ -static int ext4_dax_pfn_mkwrite(struct vm_fault *vmf) -{ - struct inode *inode = file_inode(vmf->vma->vm_file); - struct super_block *sb = inode->i_sb; - loff_t size; - int ret; - - sb_start_pagefault(sb); - file_update_time(vmf->vma->vm_file); - down_read(&EXT4_I(inode)->i_mmap_sem); - size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT; - if (vmf->pgoff >= size) - ret = VM_FAULT_SIGBUS; - else - ret = dax_pfn_mkwrite(vmf); - up_read(&EXT4_I(inode)->i_mmap_sem); - sb_end_pagefault(sb); - - return ret; -} - static const struct vm_operations_struct ext4_dax_vm_ops = { .fault = ext4_dax_fault, .huge_fault = ext4_dax_huge_fault, .page_mkwrite = ext4_dax_fault, - .pfn_mkwrite = ext4_dax_pfn_mkwrite, + .pfn_mkwrite = ext4_dax_fault, }; #else #define ext4_dax_vm_ops ext4_file_vm_ops @@ -507,12 +477,11 @@ static int ext4_find_unwritten_pgoff(struct inode *inode, pagevec_init(&pvec, 0); do { - int i, num; + int i; unsigned long nr_pages; - num = min_t(pgoff_t, end - index, PAGEVEC_SIZE - 1) + 1; - nr_pages = pagevec_lookup(&pvec, inode->i_mapping, index, - (pgoff_t)num); + nr_pages = pagevec_lookup_range(&pvec, inode->i_mapping, + &index, end); if (nr_pages == 0) break; @@ -531,9 +500,6 @@ static int ext4_find_unwritten_pgoff(struct inode *inode, goto out; } - if (page->index > end) - goto out; - lock_page(page); if (unlikely(page->mapping != inode->i_mapping)) { @@ -576,14 +542,10 @@ next: unlock_page(page); } - /* The no. of pages is less than our desired, we are done. */ - if (nr_pages < num) - break; - - index = pvec.pages[i - 1]->index + 1; pagevec_release(&pvec); } while (index <= end); + /* There are no pages upto endoff - that would be a hole in there. */ if (whence == SEEK_HOLE && lastoff < endoff) { found = 1; *offset = lastoff; diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 7143967..e963508 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -1720,13 +1720,12 @@ static void mpage_release_unused_pages(struct mpage_da_data *mpd, pagevec_init(&pvec, 0); while (index <= end) { - nr_pages = pagevec_lookup(&pvec, mapping, index, PAGEVEC_SIZE); + nr_pages = pagevec_lookup_range(&pvec, mapping, &index, end); if (nr_pages == 0) break; for (i = 0; i < nr_pages; i++) { struct page *page = pvec.pages[i]; - if (page->index > end) - break; + BUG_ON(!PageLocked(page)); BUG_ON(PageWriteback(page)); if (invalidate) { @@ -1737,7 +1736,6 @@ static void mpage_release_unused_pages(struct mpage_da_data *mpd, } unlock_page(page); } - index = pvec.pages[nr_pages - 1]->index + 1; pagevec_release(&pvec); } } @@ -2348,17 +2346,13 @@ static int mpage_map_and_submit_buffers(struct mpage_da_data *mpd) pagevec_init(&pvec, 0); while (start <= end) { - nr_pages = pagevec_lookup(&pvec, inode->i_mapping, start, - PAGEVEC_SIZE); + nr_pages = pagevec_lookup_range(&pvec, inode->i_mapping, + &start, end); if (nr_pages == 0) break; for (i = 0; i < nr_pages; i++) { struct page *page = pvec.pages[i]; - if (page->index > end) - break; - /* Up to 'end' pages must be contiguous */ - BUG_ON(page->index != start); bh = head = page_buffers(page); do { if (lblk < mpd->map.m_lblk) @@ -2403,7 +2397,6 @@ static int mpage_map_and_submit_buffers(struct mpage_da_data *mpd) pagevec_release(&pvec); return err; } - start++; } pagevec_release(&pvec); } diff --git a/fs/fscache/page.c b/fs/fscache/page.c index c8c4f79..0ad3fd3 100644 --- a/fs/fscache/page.c +++ b/fs/fscache/page.c @@ -1178,11 +1178,10 @@ void __fscache_uncache_all_inode_pages(struct fscache_cookie *cookie, pagevec_init(&pvec, 0); next = 0; do { - if (!pagevec_lookup(&pvec, mapping, next, PAGEVEC_SIZE)) + if (!pagevec_lookup(&pvec, mapping, &next)) break; for (i = 0; i < pagevec_count(&pvec); i++) { struct page *page = pvec.pages[i]; - next = page->index; if (PageFsCache(page)) { __fscache_wait_on_page_write(cookie, page); __fscache_uncache_page(cookie, page); @@ -1190,7 +1189,7 @@ void __fscache_uncache_all_inode_pages(struct fscache_cookie *cookie, } pagevec_release(&pvec); cond_resched(); - } while (++next); + } while (next); _leave(""); } diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 28d2753..7c02b3f 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -401,9 +401,8 @@ static void remove_inode_hugepages(struct inode *inode, loff_t lstart, const pgoff_t end = lend >> huge_page_shift(h); struct vm_area_struct pseudo_vma; struct pagevec pvec; - pgoff_t next; + pgoff_t next, index; int i, freed = 0; - long lookup_nr = PAGEVEC_SIZE; bool truncate_op = (lend == LLONG_MAX); memset(&pseudo_vma, 0, sizeof(struct vm_area_struct)); @@ -412,33 +411,19 @@ static void remove_inode_hugepages(struct inode *inode, loff_t lstart, next = start; while (next < end) { /* - * Don't grab more pages than the number left in the range. - */ - if (end - next < lookup_nr) - lookup_nr = end - next; - - /* * When no more pages are found, we are done. */ - if (!pagevec_lookup(&pvec, mapping, next, lookup_nr)) + if (!pagevec_lookup_range(&pvec, mapping, &next, end - 1)) break; for (i = 0; i < pagevec_count(&pvec); ++i) { struct page *page = pvec.pages[i]; u32 hash; - /* - * The page (index) could be beyond end. This is - * only possible in the punch hole case as end is - * max page offset in the truncate case. - */ - next = page->index; - if (next >= end) - break; - + index = page->index; hash = hugetlb_fault_mutex_hash(h, current->mm, &pseudo_vma, - mapping, next, 0); + mapping, index, 0); mutex_lock(&hugetlb_fault_mutex_table[hash]); /* @@ -455,8 +440,8 @@ static void remove_inode_hugepages(struct inode *inode, loff_t lstart, i_mmap_lock_write(mapping); hugetlb_vmdelete_list(&mapping->i_mmap, - next * pages_per_huge_page(h), - (next + 1) * pages_per_huge_page(h)); + index * pages_per_huge_page(h), + (index + 1) * pages_per_huge_page(h)); i_mmap_unlock_write(mapping); } @@ -475,14 +460,13 @@ static void remove_inode_hugepages(struct inode *inode, loff_t lstart, freed++; if (!truncate_op) { if (unlikely(hugetlb_unreserve_pages(inode, - next, next + 1, 1))) + index, index + 1, 1))) hugetlb_fix_reserve_counts(inode); } unlock_page(page); mutex_unlock(&hugetlb_fault_mutex_table[hash]); } - ++next; huge_pagevec_release(&pvec); cond_resched(); } diff --git a/fs/nfs/fscache-index.c b/fs/nfs/fscache-index.c index 777b055..3025fe8 100644 --- a/fs/nfs/fscache-index.c +++ b/fs/nfs/fscache-index.c @@ -252,45 +252,6 @@ enum fscache_checkaux nfs_fscache_inode_check_aux(void *cookie_netfs_data, } /* - * Indication from FS-Cache that the cookie is no longer cached - * - This function is called when the backing store currently caching a cookie - * is removed - * - The netfs should use this to clean up any markers indicating cached pages - * - This is mandatory for any object that may have data - */ -static void nfs_fscache_inode_now_uncached(void *cookie_netfs_data) -{ - struct nfs_inode *nfsi = cookie_netfs_data; - struct pagevec pvec; - pgoff_t first; - int loop, nr_pages; - - pagevec_init(&pvec, 0); - first = 0; - - dprintk("NFS: nfs_inode_now_uncached: nfs_inode 0x%p\n", nfsi); - - for (;;) { - /* grab a bunch of pages to unmark */ - nr_pages = pagevec_lookup(&pvec, - nfsi->vfs_inode.i_mapping, - first, - PAGEVEC_SIZE - pagevec_count(&pvec)); - if (!nr_pages) - break; - - for (loop = 0; loop < nr_pages; loop++) - ClearPageFsCache(pvec.pages[loop]); - - first = pvec.pages[nr_pages - 1]->index + 1; - - pvec.nr = nr_pages; - pagevec_release(&pvec); - cond_resched(); - } -} - -/* * Get an extra reference on a read context. * - This function can be absent if the completion function doesn't require a * context. @@ -330,7 +291,6 @@ const struct fscache_cookie_def nfs_fscache_inode_object_def = { .get_attr = nfs_fscache_inode_get_attr, .get_aux = nfs_fscache_inode_get_aux, .check_aux = nfs_fscache_inode_check_aux, - .now_uncached = nfs_fscache_inode_now_uncached, .get_context = nfs_fh_get_context, .put_context = nfs_fh_put_context, }; diff --git a/fs/nilfs2/page.c b/fs/nilfs2/page.c index f11a3ad..8616c46 100644 --- a/fs/nilfs2/page.c +++ b/fs/nilfs2/page.c @@ -312,10 +312,9 @@ void nilfs_copy_back_pages(struct address_space *dmap, pagevec_init(&pvec, 0); repeat: - n = pagevec_lookup(&pvec, smap, index, PAGEVEC_SIZE); + n = pagevec_lookup(&pvec, smap, &index); if (!n) return; - index = pvec.pages[n - 1]->index + 1; for (i = 0; i < pagevec_count(&pvec); i++) { struct page *page = pvec.pages[i], *dpage; diff --git a/fs/ocfs2/acl.c b/fs/ocfs2/acl.c index e50a387..40b5cc9 100644 --- a/fs/ocfs2/acl.c +++ b/fs/ocfs2/acl.c @@ -221,7 +221,7 @@ out: /* * Set the access or default ACL of an inode. */ -int ocfs2_set_acl(handle_t *handle, +static int ocfs2_set_acl(handle_t *handle, struct inode *inode, struct buffer_head *di_bh, int type, diff --git a/fs/ocfs2/acl.h b/fs/ocfs2/acl.h index 2783a75..7be0bb7 100644 --- a/fs/ocfs2/acl.h +++ b/fs/ocfs2/acl.h @@ -28,13 +28,6 @@ struct ocfs2_acl_entry { struct posix_acl *ocfs2_iop_get_acl(struct inode *inode, int type); int ocfs2_iop_set_acl(struct inode *inode, struct posix_acl *acl, int type); -int ocfs2_set_acl(handle_t *handle, - struct inode *inode, - struct buffer_head *di_bh, - int type, - struct posix_acl *acl, - struct ocfs2_alloc_context *meta_ac, - struct ocfs2_alloc_context *data_ac); extern int ocfs2_acl_chmod(struct inode *, struct buffer_head *); extern int ocfs2_init_acl(handle_t *, struct inode *, struct inode *, struct buffer_head *, struct buffer_head *, diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c index fb15a96..a177eae 100644 --- a/fs/ocfs2/alloc.c +++ b/fs/ocfs2/alloc.c @@ -955,8 +955,7 @@ int ocfs2_read_extent_block(struct ocfs2_caching_info *ci, u64 eb_blkno, /* * How many free extents have we got before we need more meta data? */ -int ocfs2_num_free_extents(struct ocfs2_super *osb, - struct ocfs2_extent_tree *et) +int ocfs2_num_free_extents(struct ocfs2_extent_tree *et) { int retval; struct ocfs2_extent_list *el = NULL; @@ -1933,14 +1932,12 @@ out: * the new changes. * * left_rec: the record on the left. - * left_child_el: is the child list pointed to by left_rec * right_rec: the record to the right of left_rec * right_child_el: is the child list pointed to by right_rec * * By definition, this only works on interior nodes. */ static void ocfs2_adjust_adjacent_records(struct ocfs2_extent_rec *left_rec, - struct ocfs2_extent_list *left_child_el, struct ocfs2_extent_rec *right_rec, struct ocfs2_extent_list *right_child_el) { @@ -2003,7 +2000,7 @@ static void ocfs2_adjust_root_records(struct ocfs2_extent_list *root_el, */ BUG_ON(i >= (le16_to_cpu(root_el->l_next_free_rec) - 1)); - ocfs2_adjust_adjacent_records(&root_el->l_recs[i], left_el, + ocfs2_adjust_adjacent_records(&root_el->l_recs[i], &root_el->l_recs[i + 1], right_el); } @@ -2060,8 +2057,7 @@ static void ocfs2_complete_edge_insert(handle_t *handle, el = right_path->p_node[i].el; right_rec = &el->l_recs[0]; - ocfs2_adjust_adjacent_records(left_rec, left_el, right_rec, - right_el); + ocfs2_adjust_adjacent_records(left_rec, right_rec, right_el); ocfs2_journal_dirty(handle, left_path->p_node[i].bh); ocfs2_journal_dirty(handle, right_path->p_node[i].bh); @@ -2509,7 +2505,7 @@ out_ret_path: static int ocfs2_update_edge_lengths(handle_t *handle, struct ocfs2_extent_tree *et, - int subtree_index, struct ocfs2_path *path) + struct ocfs2_path *path) { int i, idx, ret; struct ocfs2_extent_rec *rec; @@ -2755,8 +2751,7 @@ static int ocfs2_rotate_subtree_left(handle_t *handle, if (del_right_subtree) { ocfs2_unlink_subtree(handle, et, left_path, right_path, subtree_index, dealloc); - ret = ocfs2_update_edge_lengths(handle, et, subtree_index, - left_path); + ret = ocfs2_update_edge_lengths(handle, et, left_path); if (ret) { mlog_errno(ret); goto out; @@ -3060,8 +3055,7 @@ static int ocfs2_remove_rightmost_path(handle_t *handle, ocfs2_unlink_subtree(handle, et, left_path, path, subtree_index, dealloc); - ret = ocfs2_update_edge_lengths(handle, et, subtree_index, - left_path); + ret = ocfs2_update_edge_lengths(handle, et, left_path); if (ret) { mlog_errno(ret); goto out; @@ -4790,7 +4784,7 @@ int ocfs2_add_clusters_in_btree(handle_t *handle, if (mark_unwritten) flags = OCFS2_EXT_UNWRITTEN; - free_extents = ocfs2_num_free_extents(osb, et); + free_extents = ocfs2_num_free_extents(et); if (free_extents < 0) { status = free_extents; mlog_errno(status); @@ -5668,7 +5662,7 @@ static int ocfs2_reserve_blocks_for_rec_trunc(struct inode *inode, *ac = NULL; - num_free_extents = ocfs2_num_free_extents(osb, et); + num_free_extents = ocfs2_num_free_extents(et); if (num_free_extents < 0) { ret = num_free_extents; mlog_errno(ret); diff --git a/fs/ocfs2/alloc.h b/fs/ocfs2/alloc.h index 4a5152e..27b75cf 100644 --- a/fs/ocfs2/alloc.h +++ b/fs/ocfs2/alloc.h @@ -144,8 +144,7 @@ int ocfs2_remove_btree_range(struct inode *inode, struct ocfs2_cached_dealloc_ctxt *dealloc, u64 refcount_loc, bool refcount_tree_locked); -int ocfs2_num_free_extents(struct ocfs2_super *osb, - struct ocfs2_extent_tree *et); +int ocfs2_num_free_extents(struct ocfs2_extent_tree *et); /* * how many new metadata chunks would an allocation need at maximum? diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c index ffe0039..56ac07c 100644 --- a/fs/ocfs2/cluster/heartbeat.c +++ b/fs/ocfs2/cluster/heartbeat.c @@ -505,8 +505,7 @@ static inline void o2hb_bio_wait_dec(struct o2hb_bio_wait_ctxt *wc, } } -static void o2hb_wait_on_io(struct o2hb_region *reg, - struct o2hb_bio_wait_ctxt *wc) +static void o2hb_wait_on_io(struct o2hb_bio_wait_ctxt *wc) { o2hb_bio_wait_dec(wc, 1); wait_for_completion(&wc->wc_io_complete); @@ -608,7 +607,7 @@ static int o2hb_read_slots(struct o2hb_region *reg, status = 0; bail_and_wait: - o2hb_wait_on_io(reg, &wc); + o2hb_wait_on_io(&wc); if (wc.wc_error && !status) status = wc.wc_error; @@ -1162,7 +1161,7 @@ static int o2hb_do_disk_heartbeat(struct o2hb_region *reg) * before we can go to steady state. This ensures that * people we find in our steady state have seen us. */ - o2hb_wait_on_io(reg, &write_wc); + o2hb_wait_on_io(&write_wc); if (write_wc.wc_error) { /* Do not re-arm the write timeout on I/O error - we * can't be sure that the new block ever made it to @@ -1275,7 +1274,7 @@ static int o2hb_thread(void *data) o2hb_prepare_block(reg, 0); ret = o2hb_issue_node_write(reg, &write_wc); if (ret == 0) - o2hb_wait_on_io(reg, &write_wc); + o2hb_wait_on_io(&write_wc); else mlog_errno(ret); } @@ -2576,22 +2575,6 @@ void o2hb_unregister_callback(const char *region_uuid, } EXPORT_SYMBOL_GPL(o2hb_unregister_callback); -int o2hb_check_node_heartbeating(u8 node_num) -{ - unsigned long testing_map[BITS_TO_LONGS(O2NM_MAX_NODES)]; - - o2hb_fill_node_map(testing_map, sizeof(testing_map)); - if (!test_bit(node_num, testing_map)) { - mlog(ML_HEARTBEAT, - "node (%u) does not have heartbeating enabled.\n", - node_num); - return 0; - } - - return 1; -} -EXPORT_SYMBOL_GPL(o2hb_check_node_heartbeating); - int o2hb_check_node_heartbeating_no_sem(u8 node_num) { unsigned long testing_map[BITS_TO_LONGS(O2NM_MAX_NODES)]; @@ -2626,23 +2609,6 @@ int o2hb_check_node_heartbeating_from_callback(u8 node_num) } EXPORT_SYMBOL_GPL(o2hb_check_node_heartbeating_from_callback); -/* Makes sure our local node is configured with a node number, and is - * heartbeating. */ -int o2hb_check_local_node_heartbeating(void) -{ - u8 node_num; - - /* if this node was set then we have networking */ - node_num = o2nm_this_node(); - if (node_num == O2NM_MAX_NODES) { - mlog(ML_HEARTBEAT, "this node has not been configured.\n"); - return 0; - } - - return o2hb_check_node_heartbeating(node_num); -} -EXPORT_SYMBOL_GPL(o2hb_check_local_node_heartbeating); - /* * this is just a hack until we get the plumbing which flips file systems * read only and drops the hb ref instead of killing the node dead. diff --git a/fs/ocfs2/dir.c b/fs/ocfs2/dir.c index 3ecb9f3..febe631 100644 --- a/fs/ocfs2/dir.c +++ b/fs/ocfs2/dir.c @@ -3249,7 +3249,7 @@ static int ocfs2_extend_dir(struct ocfs2_super *osb, spin_unlock(&OCFS2_I(dir)->ip_lock); ocfs2_init_dinode_extent_tree(&et, INODE_CACHE(dir), parent_fe_bh); - num_free_extents = ocfs2_num_free_extents(osb, &et); + num_free_extents = ocfs2_num_free_extents(&et); if (num_free_extents < 0) { status = num_free_extents; mlog_errno(status); diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index 66e59d3..6e41fc8 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -713,13 +713,6 @@ leave: return status; } -int ocfs2_extend_allocation(struct inode *inode, u32 logical_start, - u32 clusters_to_add, int mark_unwritten) -{ - return __ocfs2_extend_allocation(inode, logical_start, - clusters_to_add, mark_unwritten); -} - /* * While a write will already be ordering the data, a truncate will not. * Thus, we need to explicitly order the zeroed pages. diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c index d5e5fa7..3630443 100644 --- a/fs/ocfs2/journal.c +++ b/fs/ocfs2/journal.c @@ -1348,7 +1348,6 @@ void ocfs2_complete_mount_recovery(struct ocfs2_super *osb) ocfs2_schedule_truncate_log_flush(osb, 0); osb->local_alloc_copy = NULL; - osb->dirty = 0; /* queue to recover orphan slots for all offline slots */ ocfs2_replay_map_set_state(osb, REPLAY_NEEDED); diff --git a/fs/ocfs2/move_extents.c b/fs/ocfs2/move_extents.c index e52a285..7eb3b0a 100644 --- a/fs/ocfs2/move_extents.c +++ b/fs/ocfs2/move_extents.c @@ -175,7 +175,7 @@ static int ocfs2_lock_allocators_move_extents(struct inode *inode, unsigned int max_recs_needed = 2 * extents_to_split + clusters_to_move; struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); - num_free_extents = ocfs2_num_free_extents(osb, et); + num_free_extents = ocfs2_num_free_extents(et); if (num_free_extents < 0) { ret = num_free_extents; mlog_errno(ret); diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h index 0c39d71..9a50f22 100644 --- a/fs/ocfs2/ocfs2.h +++ b/fs/ocfs2/ocfs2.h @@ -320,7 +320,6 @@ struct ocfs2_super u64 system_dir_blkno; u64 bitmap_blkno; u32 bitmap_cpg; - u8 *uuid; char *uuid_str; u32 uuid_hash; u8 *vol_label; @@ -388,9 +387,8 @@ struct ocfs2_super unsigned int osb_resv_level; unsigned int osb_dir_resv_level; - /* Next three fields are for local node slot recovery during + /* Next two fields are for local node slot recovery during * mount. */ - int dirty; struct ocfs2_dinode *local_alloc_copy; struct ocfs2_quota_recovery *quota_rec; diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c index f8933cb..ab156e3 100644 --- a/fs/ocfs2/refcounttree.c +++ b/fs/ocfs2/refcounttree.c @@ -2851,7 +2851,7 @@ static int ocfs2_lock_refcount_allocators(struct super_block *sb, int *credits) { int ret = 0, meta_add = 0; - int num_free_extents = ocfs2_num_free_extents(OCFS2_SB(sb), et); + int num_free_extents = ocfs2_num_free_extents(et); if (num_free_extents < 0) { ret = num_free_extents; diff --git a/fs/ocfs2/suballoc.c b/fs/ocfs2/suballoc.c index 6ad3533..71f22c8 100644 --- a/fs/ocfs2/suballoc.c +++ b/fs/ocfs2/suballoc.c @@ -2700,7 +2700,7 @@ int ocfs2_lock_allocators(struct inode *inode, BUG_ON(clusters_to_add != 0 && data_ac == NULL); - num_free_extents = ocfs2_num_free_extents(osb, et); + num_free_extents = ocfs2_num_free_extents(et); if (num_free_extents < 0) { ret = num_free_extents; mlog_errno(ret); diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c index 83005f4..3f936be 100644 --- a/fs/ocfs2/super.c +++ b/fs/ocfs2/super.c @@ -2486,7 +2486,6 @@ static int ocfs2_check_volume(struct ocfs2_super *osb) if (dirty) { /* Recovery will be completed after we've mounted the * rest of the volume. */ - osb->dirty = 1; osb->local_alloc_copy = local_alloc; local_alloc = NULL; } diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c index f70c377..5fdf269 100644 --- a/fs/ocfs2/xattr.c +++ b/fs/ocfs2/xattr.c @@ -6800,7 +6800,7 @@ static int ocfs2_lock_reflink_xattr_rec_allocators( *credits += 1; /* count in the xattr tree change. */ - num_free_extents = ocfs2_num_free_extents(osb, xt_et); + num_free_extents = ocfs2_num_free_extents(xt_et); if (num_free_extents < 0) { ret = num_free_extents; mlog_errno(ret); diff --git a/fs/proc/base.c b/fs/proc/base.c index 98fd8f6..e5d89a0 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -2931,6 +2931,7 @@ static const struct pid_entry tgid_base_stuff[] = { #ifdef CONFIG_PROC_PAGE_MONITOR REG("clear_refs", S_IWUSR, proc_clear_refs_operations), REG("smaps", S_IRUGO, proc_pid_smaps_operations), + REG("smaps_rollup", S_IRUGO, proc_pid_smaps_rollup_operations), REG("pagemap", S_IRUSR, proc_pagemap_operations), #endif #ifdef CONFIG_SECURITY @@ -3324,6 +3325,7 @@ static const struct pid_entry tid_base_stuff[] = { #ifdef CONFIG_PROC_PAGE_MONITOR REG("clear_refs", S_IWUSR, proc_clear_refs_operations), REG("smaps", S_IRUGO, proc_tid_smaps_operations), + REG("smaps_rollup", S_IRUGO, proc_pid_smaps_rollup_operations), REG("pagemap", S_IRUSR, proc_pagemap_operations), #endif #ifdef CONFIG_SECURITY diff --git a/fs/proc/internal.h b/fs/proc/internal.h index aa2b890..2cbfcd3 100644 --- a/fs/proc/internal.h +++ b/fs/proc/internal.h @@ -269,10 +269,12 @@ extern int proc_remount(struct super_block *, int *, char *); /* * task_[no]mmu.c */ +struct mem_size_stats; struct proc_maps_private { struct inode *inode; struct task_struct *task; struct mm_struct *mm; + struct mem_size_stats *rollup; #ifdef CONFIG_MMU struct vm_area_struct *tail_vma; #endif @@ -288,6 +290,7 @@ extern const struct file_operations proc_tid_maps_operations; extern const struct file_operations proc_pid_numa_maps_operations; extern const struct file_operations proc_tid_numa_maps_operations; extern const struct file_operations proc_pid_smaps_operations; +extern const struct file_operations proc_pid_smaps_rollup_operations; extern const struct file_operations proc_tid_smaps_operations; extern const struct file_operations proc_clear_refs_operations; extern const struct file_operations proc_pagemap_operations; diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c index 509a616..cdd9797 100644 --- a/fs/proc/meminfo.c +++ b/fs/proc/meminfo.c @@ -80,7 +80,7 @@ static int meminfo_proc_show(struct seq_file *m, void *v) show_val_kb(m, "Active(file): ", pages[LRU_ACTIVE_FILE]); show_val_kb(m, "Inactive(file): ", pages[LRU_INACTIVE_FILE]); show_val_kb(m, "Unevictable: ", pages[LRU_UNEVICTABLE]); - show_val_kb(m, "Mlocked: ", global_page_state(NR_MLOCK)); + show_val_kb(m, "Mlocked: ", global_zone_page_state(NR_MLOCK)); #ifdef CONFIG_HIGHMEM show_val_kb(m, "HighTotal: ", i.totalhigh); @@ -114,9 +114,9 @@ static int meminfo_proc_show(struct seq_file *m, void *v) show_val_kb(m, "SUnreclaim: ", global_node_page_state(NR_SLAB_UNRECLAIMABLE)); seq_printf(m, "KernelStack: %8lu kB\n", - global_page_state(NR_KERNEL_STACK_KB)); + global_zone_page_state(NR_KERNEL_STACK_KB)); show_val_kb(m, "PageTables: ", - global_page_state(NR_PAGETABLE)); + global_zone_page_state(NR_PAGETABLE)); #ifdef CONFIG_QUICKLIST show_val_kb(m, "Quicklists: ", quicklist_total_size()); #endif @@ -124,7 +124,7 @@ static int meminfo_proc_show(struct seq_file *m, void *v) show_val_kb(m, "NFS_Unstable: ", global_node_page_state(NR_UNSTABLE_NFS)); show_val_kb(m, "Bounce: ", - global_page_state(NR_BOUNCE)); + global_zone_page_state(NR_BOUNCE)); show_val_kb(m, "WritebackTmp: ", global_node_page_state(NR_WRITEBACK_TEMP)); show_val_kb(m, "CommitLimit: ", vm_commit_limit()); @@ -151,7 +151,7 @@ static int meminfo_proc_show(struct seq_file *m, void *v) #ifdef CONFIG_CMA show_val_kb(m, "CmaTotal: ", totalcma_pages); show_val_kb(m, "CmaFree: ", - global_page_state(NR_FREE_CMA_PAGES)); + global_zone_page_state(NR_FREE_CMA_PAGES)); #endif hugetlb_report_meminfo(m); diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index fe8f326..a290966 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -253,6 +253,7 @@ static int proc_map_release(struct inode *inode, struct file *file) if (priv->mm) mmdrop(priv->mm); + kfree(priv->rollup); return seq_release_private(inode, file); } @@ -279,6 +280,23 @@ static int is_stack(struct proc_maps_private *priv, vma->vm_end >= vma->vm_mm->start_stack; } +static void show_vma_header_prefix(struct seq_file *m, + unsigned long start, unsigned long end, + vm_flags_t flags, unsigned long long pgoff, + dev_t dev, unsigned long ino) +{ + seq_setwidth(m, 25 + sizeof(void *) * 6 - 1); + seq_printf(m, "%08lx-%08lx %c%c%c%c %08llx %02x:%02x %lu ", + start, + end, + flags & VM_READ ? 'r' : '-', + flags & VM_WRITE ? 'w' : '-', + flags & VM_EXEC ? 'x' : '-', + flags & VM_MAYSHARE ? 's' : 'p', + pgoff, + MAJOR(dev), MINOR(dev), ino); +} + static void show_map_vma(struct seq_file *m, struct vm_area_struct *vma, int is_pid) { @@ -301,17 +319,7 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma, int is_pid) start = vma->vm_start; end = vma->vm_end; - - seq_setwidth(m, 25 + sizeof(void *) * 6 - 1); - seq_printf(m, "%08lx-%08lx %c%c%c%c %08llx %02x:%02x %lu ", - start, - end, - flags & VM_READ ? 'r' : '-', - flags & VM_WRITE ? 'w' : '-', - flags & VM_EXEC ? 'x' : '-', - flags & VM_MAYSHARE ? 's' : 'p', - pgoff, - MAJOR(dev), MINOR(dev), ino); + show_vma_header_prefix(m, start, end, flags, pgoff, dev, ino); /* * Print the dentry name for named mappings, and a @@ -430,6 +438,7 @@ const struct file_operations proc_tid_maps_operations = { #ifdef CONFIG_PROC_PAGE_MONITOR struct mem_size_stats { + bool first; unsigned long resident; unsigned long shared_clean; unsigned long shared_dirty; @@ -443,7 +452,9 @@ struct mem_size_stats { unsigned long swap; unsigned long shared_hugetlb; unsigned long private_hugetlb; + unsigned long first_vma_start; u64 pss; + u64 pss_locked; u64 swap_pss; bool check_shmem_swap; }; @@ -652,6 +663,7 @@ static void show_smap_vma_flags(struct seq_file *m, struct vm_area_struct *vma) [ilog2(VM_NORESERVE)] = "nr", [ilog2(VM_HUGETLB)] = "ht", [ilog2(VM_ARCH_1)] = "ar", + [ilog2(VM_WIPEONFORK)] = "wf", [ilog2(VM_DONTDUMP)] = "dd", #ifdef CONFIG_MEM_SOFT_DIRTY [ilog2(VM_SOFTDIRTY)] = "sd", @@ -719,18 +731,36 @@ void __weak arch_show_smap(struct seq_file *m, struct vm_area_struct *vma) static int show_smap(struct seq_file *m, void *v, int is_pid) { + struct proc_maps_private *priv = m->private; struct vm_area_struct *vma = v; - struct mem_size_stats mss; + struct mem_size_stats mss_stack; + struct mem_size_stats *mss; struct mm_walk smaps_walk = { .pmd_entry = smaps_pte_range, #ifdef CONFIG_HUGETLB_PAGE .hugetlb_entry = smaps_hugetlb_range, #endif .mm = vma->vm_mm, - .private = &mss, }; + int ret = 0; + bool rollup_mode; + bool last_vma; + + if (priv->rollup) { + rollup_mode = true; + mss = priv->rollup; + if (mss->first) { + mss->first_vma_start = vma->vm_start; + mss->first = false; + } + last_vma = !m_next_vma(priv, vma); + } else { + rollup_mode = false; + memset(&mss_stack, 0, sizeof(mss_stack)); + mss = &mss_stack; + } - memset(&mss, 0, sizeof mss); + smaps_walk.private = mss; #ifdef CONFIG_SHMEM if (vma->vm_file && shmem_mapping(vma->vm_file->f_mapping)) { @@ -748,9 +778,9 @@ static int show_smap(struct seq_file *m, void *v, int is_pid) if (!shmem_swapped || (vma->vm_flags & VM_SHARED) || !(vma->vm_flags & VM_WRITE)) { - mss.swap = shmem_swapped; + mss->swap = shmem_swapped; } else { - mss.check_shmem_swap = true; + mss->check_shmem_swap = true; smaps_walk.pte_hole = smaps_pte_hole; } } @@ -758,54 +788,71 @@ static int show_smap(struct seq_file *m, void *v, int is_pid) /* mmap_sem is held in m_start */ walk_page_vma(vma, &smaps_walk); + if (vma->vm_flags & VM_LOCKED) + mss->pss_locked += mss->pss; + + if (!rollup_mode) { + show_map_vma(m, vma, is_pid); + } else if (last_vma) { + show_vma_header_prefix( + m, mss->first_vma_start, vma->vm_end, 0, 0, 0, 0); + seq_pad(m, ' '); + seq_puts(m, "[rollup]\n"); + } else { + ret = SEQ_SKIP; + } - show_map_vma(m, vma, is_pid); - - seq_printf(m, - "Size: %8lu kB\n" - "Rss: %8lu kB\n" - "Pss: %8lu kB\n" - "Shared_Clean: %8lu kB\n" - "Shared_Dirty: %8lu kB\n" - "Private_Clean: %8lu kB\n" - "Private_Dirty: %8lu kB\n" - "Referenced: %8lu kB\n" - "Anonymous: %8lu kB\n" - "LazyFree: %8lu kB\n" - "AnonHugePages: %8lu kB\n" - "ShmemPmdMapped: %8lu kB\n" - "Shared_Hugetlb: %8lu kB\n" - "Private_Hugetlb: %7lu kB\n" - "Swap: %8lu kB\n" - "SwapPss: %8lu kB\n" - "KernelPageSize: %8lu kB\n" - "MMUPageSize: %8lu kB\n" - "Locked: %8lu kB\n", - (vma->vm_end - vma->vm_start) >> 10, - mss.resident >> 10, - (unsigned long)(mss.pss >> (10 + PSS_SHIFT)), - mss.shared_clean >> 10, - mss.shared_dirty >> 10, - mss.private_clean >> 10, - mss.private_dirty >> 10, - mss.referenced >> 10, - mss.anonymous >> 10, - mss.lazyfree >> 10, - mss.anonymous_thp >> 10, - mss.shmem_thp >> 10, - mss.shared_hugetlb >> 10, - mss.private_hugetlb >> 10, - mss.swap >> 10, - (unsigned long)(mss.swap_pss >> (10 + PSS_SHIFT)), - vma_kernel_pagesize(vma) >> 10, - vma_mmu_pagesize(vma) >> 10, - (vma->vm_flags & VM_LOCKED) ? - (unsigned long)(mss.pss >> (10 + PSS_SHIFT)) : 0); - - arch_show_smap(m, vma); - show_smap_vma_flags(m, vma); + if (!rollup_mode) + seq_printf(m, + "Size: %8lu kB\n" + "KernelPageSize: %8lu kB\n" + "MMUPageSize: %8lu kB\n", + (vma->vm_end - vma->vm_start) >> 10, + vma_kernel_pagesize(vma) >> 10, + vma_mmu_pagesize(vma) >> 10); + + + if (!rollup_mode || last_vma) + seq_printf(m, + "Rss: %8lu kB\n" + "Pss: %8lu kB\n" + "Shared_Clean: %8lu kB\n" + "Shared_Dirty: %8lu kB\n" + "Private_Clean: %8lu kB\n" + "Private_Dirty: %8lu kB\n" + "Referenced: %8lu kB\n" + "Anonymous: %8lu kB\n" + "LazyFree: %8lu kB\n" + "AnonHugePages: %8lu kB\n" + "ShmemPmdMapped: %8lu kB\n" + "Shared_Hugetlb: %8lu kB\n" + "Private_Hugetlb: %7lu kB\n" + "Swap: %8lu kB\n" + "SwapPss: %8lu kB\n" + "Locked: %8lu kB\n", + mss->resident >> 10, + (unsigned long)(mss->pss >> (10 + PSS_SHIFT)), + mss->shared_clean >> 10, + mss->shared_dirty >> 10, + mss->private_clean >> 10, + mss->private_dirty >> 10, + mss->referenced >> 10, + mss->anonymous >> 10, + mss->lazyfree >> 10, + mss->anonymous_thp >> 10, + mss->shmem_thp >> 10, + mss->shared_hugetlb >> 10, + mss->private_hugetlb >> 10, + mss->swap >> 10, + (unsigned long)(mss->swap_pss >> (10 + PSS_SHIFT)), + (unsigned long)(mss->pss >> (10 + PSS_SHIFT))); + + if (!rollup_mode) { + arch_show_smap(m, vma); + show_smap_vma_flags(m, vma); + } m_cache_vma(m, vma); - return 0; + return ret; } static int show_pid_smap(struct seq_file *m, void *v) @@ -837,6 +884,25 @@ static int pid_smaps_open(struct inode *inode, struct file *file) return do_maps_open(inode, file, &proc_pid_smaps_op); } +static int pid_smaps_rollup_open(struct inode *inode, struct file *file) +{ + struct seq_file *seq; + struct proc_maps_private *priv; + int ret = do_maps_open(inode, file, &proc_pid_smaps_op); + + if (ret < 0) + return ret; + seq = file->private_data; + priv = seq->private; + priv->rollup = kzalloc(sizeof(*priv->rollup), GFP_KERNEL); + if (!priv->rollup) { + proc_map_release(inode, file); + return -ENOMEM; + } + priv->rollup->first = true; + return 0; +} + static int tid_smaps_open(struct inode *inode, struct file *file) { return do_maps_open(inode, file, &proc_tid_smaps_op); @@ -849,6 +915,13 @@ const struct file_operations proc_pid_smaps_operations = { .release = proc_map_release, }; +const struct file_operations proc_pid_smaps_rollup_operations = { + .open = pid_smaps_rollup_open, + .read = seq_read, + .llseek = seq_lseek, + .release = proc_map_release, +}; + const struct file_operations proc_tid_smaps_operations = { .open = tid_smaps_open, .read = seq_read, diff --git a/fs/ramfs/file-nommu.c b/fs/ramfs/file-nommu.c index 2ef7ce7..3ac1f23 100644 --- a/fs/ramfs/file-nommu.c +++ b/fs/ramfs/file-nommu.c @@ -228,7 +228,7 @@ static unsigned long ramfs_nommu_get_unmapped_area(struct file *file, if (!pages) goto out_free; - nr = find_get_pages(inode->i_mapping, pgoff, lpages, pages); + nr = find_get_pages(inode->i_mapping, &pgoff, lpages, pages); if (nr != lpages) goto out_free_pages; /* leave if some pages were missing */ @@ -335,11 +335,6 @@ SYSCALL_DEFINE4(sync_file_range, int, fd, loff_t, offset, loff_t, nbytes, goto out_put; mapping = f.file->f_mapping; - if (!mapping) { - ret = -EINVAL; - goto out_put; - } - ret = 0; if (flags & SYNC_FILE_RANGE_WAIT_BEFORE) { ret = file_fdatawait_range(f.file, offset, endbyte); diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index 886085b..5419e7d 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -178,7 +178,8 @@ static inline void msg_init(struct uffd_msg *msg) static inline struct uffd_msg userfault_msg(unsigned long address, unsigned int flags, - unsigned long reason) + unsigned long reason, + unsigned int features) { struct uffd_msg msg; msg_init(&msg); @@ -202,6 +203,8 @@ static inline struct uffd_msg userfault_msg(unsigned long address, * write protect fault. */ msg.arg.pagefault.flags |= UFFD_PAGEFAULT_FLAG_WP; + if (features & UFFD_FEATURE_THREAD_ID) + msg.arg.pagefault.feat.ptid = task_pid_vnr(current); return msg; } @@ -370,6 +373,9 @@ int handle_userfault(struct vm_fault *vmf, unsigned long reason) VM_BUG_ON(reason & ~(VM_UFFD_MISSING|VM_UFFD_WP)); VM_BUG_ON(!(reason & VM_UFFD_MISSING) ^ !!(reason & VM_UFFD_WP)); + if (ctx->features & UFFD_FEATURE_SIGBUS) + goto out; + /* * If it's already released don't get it. This avoids to loop * in __get_user_pages if userfaultfd_release waits on the @@ -419,7 +425,8 @@ int handle_userfault(struct vm_fault *vmf, unsigned long reason) init_waitqueue_func_entry(&uwq.wq, userfaultfd_wake_function); uwq.wq.private = current; - uwq.msg = userfault_msg(vmf->address, vmf->flags, reason); + uwq.msg = userfault_msg(vmf->address, vmf->flags, reason, + ctx->features); uwq.ctx = ctx; uwq.waken = false; @@ -1194,7 +1201,7 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx, struct uffdio_register __user *user_uffdio_register; unsigned long vm_flags, new_flags; bool found; - bool non_anon_pages; + bool basic_ioctls; unsigned long start, end, vma_end; user_uffdio_register = (struct uffdio_register __user *) arg; @@ -1260,7 +1267,7 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx, * Search for not compatible vmas. */ found = false; - non_anon_pages = false; + basic_ioctls = false; for (cur = vma; cur && cur->vm_start < end; cur = cur->vm_next) { cond_resched(); @@ -1299,8 +1306,8 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx, /* * Note vmas containing huge pages */ - if (is_vm_hugetlb_page(cur) || vma_is_shmem(cur)) - non_anon_pages = true; + if (is_vm_hugetlb_page(cur)) + basic_ioctls = true; found = true; } @@ -1371,7 +1378,7 @@ out_unlock: * userland which ioctls methods are guaranteed to * succeed on this range. */ - if (put_user(non_anon_pages ? UFFD_API_RANGE_IOCTLS_BASIC : + if (put_user(basic_ioctls ? UFFD_API_RANGE_IOCTLS_BASIC : UFFD_API_RANGE_IOCTLS, &user_uffdio_register->ioctls)) ret = -EFAULT; diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 0debbc7..ec3e44f 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -1101,7 +1101,7 @@ xfs_filemap_pfn_mkwrite( if (vmf->pgoff >= size) ret = VM_FAULT_SIGBUS; else if (IS_DAX(inode)) - ret = dax_pfn_mkwrite(vmf); + ret = dax_iomap_fault(vmf, PE_SIZE_PTE, &xfs_iomap_ops); xfs_iunlock(ip, XFS_MMAPLOCK_SHARED); sb_end_pagefault(inode->i_sb); return ret; diff --git a/include/linux/bio.h b/include/linux/bio.h index 7b1cf4b..1f0720d 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -38,7 +38,15 @@ #define BIO_BUG_ON #endif +#ifdef CONFIG_THP_SWAP +#if HPAGE_PMD_NR > 256 +#define BIO_MAX_PAGES HPAGE_PMD_NR +#else #define BIO_MAX_PAGES 256 +#endif +#else +#define BIO_MAX_PAGES 256 +#endif #define bio_prio(bio) (bio)->bi_ioprio #define bio_set_prio(bio, prio) ((bio)->bi_ioprio = prio) diff --git a/include/linux/dax.h b/include/linux/dax.h index df97b7a..eb0bff6 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -89,34 +89,6 @@ void dax_flush(struct dax_device *dax_dev, pgoff_t pgoff, void *addr, void dax_write_cache(struct dax_device *dax_dev, bool wc); bool dax_write_cache_enabled(struct dax_device *dax_dev); -/* - * We use lowest available bit in exceptional entry for locking, one bit for - * the entry size (PMD) and two more to tell us if the entry is a huge zero - * page (HZP) or an empty entry that is just used for locking. In total four - * special bits. - * - * If the PMD bit isn't set the entry has size PAGE_SIZE, and if the HZP and - * EMPTY bits aren't set the entry is a normal DAX entry with a filesystem - * block allocation. - */ -#define RADIX_DAX_SHIFT (RADIX_TREE_EXCEPTIONAL_SHIFT + 4) -#define RADIX_DAX_ENTRY_LOCK (1 << RADIX_TREE_EXCEPTIONAL_SHIFT) -#define RADIX_DAX_PMD (1 << (RADIX_TREE_EXCEPTIONAL_SHIFT + 1)) -#define RADIX_DAX_HZP (1 << (RADIX_TREE_EXCEPTIONAL_SHIFT + 2)) -#define RADIX_DAX_EMPTY (1 << (RADIX_TREE_EXCEPTIONAL_SHIFT + 3)) - -static inline unsigned long dax_radix_sector(void *entry) -{ - return (unsigned long)entry >> RADIX_DAX_SHIFT; -} - -static inline void *dax_radix_locked_entry(sector_t sector, unsigned long flags) -{ - return (void *)(RADIX_TREE_EXCEPTIONAL_ENTRY | flags | - ((unsigned long)sector << RADIX_DAX_SHIFT) | - RADIX_DAX_ENTRY_LOCK); -} - ssize_t dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter, const struct iomap_ops *ops); int dax_iomap_fault(struct vm_fault *vmf, enum page_entry_size pe_size, @@ -124,8 +96,6 @@ int dax_iomap_fault(struct vm_fault *vmf, enum page_entry_size pe_size, int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index); int dax_invalidate_mapping_entry_sync(struct address_space *mapping, pgoff_t index); -void dax_wake_mapping_entry_waiter(struct address_space *mapping, - pgoff_t index, void *entry, bool wake_all); #ifdef CONFIG_FS_DAX int __dax_zero_page_range(struct block_device *bdev, @@ -140,21 +110,6 @@ static inline int __dax_zero_page_range(struct block_device *bdev, } #endif -#ifdef CONFIG_FS_DAX_PMD -static inline unsigned int dax_radix_order(void *entry) -{ - if ((unsigned long)entry & RADIX_DAX_PMD) - return PMD_SHIFT - PAGE_SHIFT; - return 0; -} -#else -static inline unsigned int dax_radix_order(void *entry) -{ - return 0; -} -#endif -int dax_pfn_mkwrite(struct vm_fault *vmf); - static inline bool dax_mapping(struct address_space *mapping) { return mapping->host && IS_DAX(mapping->host); diff --git a/include/linux/fs.h b/include/linux/fs.h index 5b744a3..c57002a 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1269,8 +1269,6 @@ extern void f_delown(struct file *filp); extern pid_t f_getown(struct file *filp); extern int send_sigurg(struct fown_struct *fown); -struct mm_struct; - /* * Umount options */ diff --git a/include/linux/fscache.h b/include/linux/fscache.h index 115bb81..f4ff47d 100644 --- a/include/linux/fscache.h +++ b/include/linux/fscache.h @@ -143,15 +143,6 @@ struct fscache_cookie_def { void (*mark_page_cached)(void *cookie_netfs_data, struct address_space *mapping, struct page *page); - - /* indicate the cookie is no longer cached - * - this function is called when the backing store currently caching - * a cookie is removed - * - the netfs should use this to clean up any markers indicating - * cached pages - * - this is mandatory for any object that may have data - */ - void (*now_uncached)(void *cookie_netfs_data); }; /* diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 9b15a4b..69966c4 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -488,8 +488,9 @@ struct mem_cgroup *lock_page_memcg(struct page *page); void __unlock_page_memcg(struct mem_cgroup *memcg); void unlock_page_memcg(struct page *page); +/* idx can be of type enum memcg_stat_item or node_stat_item */ static inline unsigned long memcg_page_state(struct mem_cgroup *memcg, - enum memcg_stat_item idx) + int idx) { long val = 0; int cpu; @@ -503,15 +504,17 @@ static inline unsigned long memcg_page_state(struct mem_cgroup *memcg, return val; } +/* idx can be of type enum memcg_stat_item or node_stat_item */ static inline void __mod_memcg_state(struct mem_cgroup *memcg, - enum memcg_stat_item idx, int val) + int idx, int val) { if (!mem_cgroup_disabled()) __this_cpu_add(memcg->stat->count[idx], val); } +/* idx can be of type enum memcg_stat_item or node_stat_item */ static inline void mod_memcg_state(struct mem_cgroup *memcg, - enum memcg_stat_item idx, int val) + int idx, int val) { if (!mem_cgroup_disabled()) this_cpu_add(memcg->stat->count[idx], val); @@ -535,14 +538,14 @@ static inline void mod_memcg_state(struct mem_cgroup *memcg, * Kernel pages are an exception to this, since they'll never move. */ static inline void __mod_memcg_page_state(struct page *page, - enum memcg_stat_item idx, int val) + int idx, int val) { if (page->mem_cgroup) __mod_memcg_state(page->mem_cgroup, idx, val); } static inline void mod_memcg_page_state(struct page *page, - enum memcg_stat_item idx, int val) + int idx, int val) { if (page->mem_cgroup) mod_memcg_state(page->mem_cgroup, idx, val); @@ -632,8 +635,9 @@ static inline void count_memcg_events(struct mem_cgroup *memcg, this_cpu_add(memcg->stat->events[idx], count); } +/* idx can be of type enum memcg_stat_item or node_stat_item */ static inline void count_memcg_page_event(struct page *page, - enum memcg_stat_item idx) + int idx) { if (page->mem_cgroup) count_memcg_events(page->mem_cgroup, idx, 1); @@ -846,31 +850,31 @@ static inline bool mem_cgroup_oom_synchronize(bool wait) } static inline unsigned long memcg_page_state(struct mem_cgroup *memcg, - enum memcg_stat_item idx) + int idx) { return 0; } static inline void __mod_memcg_state(struct mem_cgroup *memcg, - enum memcg_stat_item idx, + int idx, int nr) { } static inline void mod_memcg_state(struct mem_cgroup *memcg, - enum memcg_stat_item idx, + int idx, int nr) { } static inline void __mod_memcg_page_state(struct page *page, - enum memcg_stat_item idx, + int idx, int nr) { } static inline void mod_memcg_page_state(struct page *page, - enum memcg_stat_item idx, + int idx, int nr) { } @@ -924,7 +928,7 @@ static inline void count_memcg_events(struct mem_cgroup *memcg, } static inline void count_memcg_page_event(struct page *page, - enum memcg_stat_item idx) + int idx) { } @@ -934,26 +938,30 @@ void count_memcg_event_mm(struct mm_struct *mm, enum vm_event_item idx) } #endif /* CONFIG_MEMCG */ +/* idx can be of type enum memcg_stat_item or node_stat_item */ static inline void __inc_memcg_state(struct mem_cgroup *memcg, - enum memcg_stat_item idx) + int idx) { __mod_memcg_state(memcg, idx, 1); } +/* idx can be of type enum memcg_stat_item or node_stat_item */ static inline void __dec_memcg_state(struct mem_cgroup *memcg, - enum memcg_stat_item idx) + int idx) { __mod_memcg_state(memcg, idx, -1); } +/* idx can be of type enum memcg_stat_item or node_stat_item */ static inline void __inc_memcg_page_state(struct page *page, - enum memcg_stat_item idx) + int idx) { __mod_memcg_page_state(page, idx, 1); } +/* idx can be of type enum memcg_stat_item or node_stat_item */ static inline void __dec_memcg_page_state(struct page *page, - enum memcg_stat_item idx) + int idx) { __mod_memcg_page_state(page, idx, -1); } @@ -982,26 +990,30 @@ static inline void __dec_lruvec_page_state(struct page *page, __mod_lruvec_page_state(page, idx, -1); } +/* idx can be of type enum memcg_stat_item or node_stat_item */ static inline void inc_memcg_state(struct mem_cgroup *memcg, - enum memcg_stat_item idx) + int idx) { mod_memcg_state(memcg, idx, 1); } +/* idx can be of type enum memcg_stat_item or node_stat_item */ static inline void dec_memcg_state(struct mem_cgroup *memcg, - enum memcg_stat_item idx) + int idx) { mod_memcg_state(memcg, idx, -1); } +/* idx can be of type enum memcg_stat_item or node_stat_item */ static inline void inc_memcg_page_state(struct page *page, - enum memcg_stat_item idx) + int idx) { mod_memcg_page_state(page, idx, 1); } +/* idx can be of type enum memcg_stat_item or node_stat_item */ static inline void dec_memcg_page_state(struct page *page, - enum memcg_stat_item idx) + int idx) { mod_memcg_page_state(page, idx, -1); } diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index c8a5056..5e6e4cc 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -319,6 +319,6 @@ extern struct page *sparse_decode_mem_map(unsigned long coded_mem_map, unsigned long pnum); extern bool allow_online_pfn_range(int nid, unsigned long pfn, unsigned long nr_pages, int online_type); -extern struct zone *default_zone_for_pfn(int nid, unsigned long pfn, +extern struct zone *zone_for_pfn_range(int online_type, int nid, unsigned start_pfn, unsigned long nr_pages); #endif /* __LINUX_MEMORY_HOTPLUG_H */ diff --git a/include/linux/mm.h b/include/linux/mm.h index c1f6c95..39db8e5 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -189,7 +189,7 @@ extern unsigned int kobjsize(const void *objp); #define VM_NORESERVE 0x00200000 /* should the VM suppress accounting */ #define VM_HUGETLB 0x00400000 /* Huge TLB Page VM */ #define VM_ARCH_1 0x01000000 /* Architecture-specific flag */ -#define VM_ARCH_2 0x02000000 +#define VM_WIPEONFORK 0x02000000 /* Wipe VMA contents in child. */ #define VM_DONTDUMP 0x04000000 /* Do not include in the core dump */ #ifdef CONFIG_MEM_SOFT_DIRTY @@ -208,10 +208,12 @@ extern unsigned int kobjsize(const void *objp); #define VM_HIGH_ARCH_BIT_1 33 /* bit only usable on 64-bit architectures */ #define VM_HIGH_ARCH_BIT_2 34 /* bit only usable on 64-bit architectures */ #define VM_HIGH_ARCH_BIT_3 35 /* bit only usable on 64-bit architectures */ +#define VM_HIGH_ARCH_BIT_4 36 /* bit only usable on 64-bit architectures */ #define VM_HIGH_ARCH_0 BIT(VM_HIGH_ARCH_BIT_0) #define VM_HIGH_ARCH_1 BIT(VM_HIGH_ARCH_BIT_1) #define VM_HIGH_ARCH_2 BIT(VM_HIGH_ARCH_BIT_2) #define VM_HIGH_ARCH_3 BIT(VM_HIGH_ARCH_BIT_3) +#define VM_HIGH_ARCH_4 BIT(VM_HIGH_ARCH_BIT_4) #endif /* CONFIG_ARCH_USES_HIGH_VMA_FLAGS */ #if defined(CONFIG_X86) @@ -235,9 +237,11 @@ extern unsigned int kobjsize(const void *objp); # define VM_MAPPED_COPY VM_ARCH_1 /* T if mapped copy of data (nommu mmap) */ #endif -#if defined(CONFIG_X86) +#if defined(CONFIG_X86_INTEL_MPX) /* MPX specific bounds table or bounds directory */ -# define VM_MPX VM_ARCH_2 +# define VM_MPX VM_HIGH_ARCH_BIT_4 +#else +# define VM_MPX VM_NONE #endif #ifndef VM_GROWSUP @@ -2294,6 +2298,8 @@ int vm_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn, pgprot_t pgprot); int vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr, pfn_t pfn); +int vm_insert_mixed_mkwrite(struct vm_area_struct *vma, unsigned long addr, + pfn_t pfn); int vm_iomap_memory(struct vm_area_struct *vma, phys_addr_t start, unsigned long len); @@ -2506,7 +2512,7 @@ enum mf_action_page_type { #if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLBFS) extern void clear_huge_page(struct page *page, - unsigned long addr, + unsigned long addr_hint, unsigned int pages_per_huge_page); extern void copy_user_huge_page(struct page *dst, struct page *src, unsigned long addr, struct vm_area_struct *vma, diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 57378c7..f45ad81 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -335,6 +335,7 @@ struct vm_area_struct { struct file * vm_file; /* File we map to (can be NULL). */ void * vm_private_data; /* was vm_pte (shared mem) */ + atomic_long_t swap_readahead_info; #ifndef CONFIG_MMU struct vm_region *vm_region; /* NOMMU mapping region */ #endif diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index fc14b8b..e7e92c8 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -770,8 +770,7 @@ static inline bool is_dev_zone(const struct zone *zone) #include <linux/memory_hotplug.h> -extern struct mutex zonelists_mutex; -void build_all_zonelists(pg_data_t *pgdat, struct zone *zone); +void build_all_zonelists(pg_data_t *pgdat); void wakeup_kswapd(struct zone *zone, int order, enum zone_type classzone_idx); bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark, int classzone_idx, unsigned int alloc_flags, @@ -896,7 +895,7 @@ int sysctl_min_slab_ratio_sysctl_handler(struct ctl_table *, int, extern int numa_zonelist_order_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *); extern char numa_zonelist_order[]; -#define NUMA_ZONELIST_ORDER_LEN 16 /* string buffer size */ +#define NUMA_ZONELIST_ORDER_LEN 16 #ifndef CONFIG_NEED_MULTIPLE_NODES diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index d33e328..ba2d470 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -303,8 +303,8 @@ PAGEFLAG(OwnerPriv1, owner_priv_1, PF_ANY) * Only test-and-set exist for PG_writeback. The unconditional operators are * risky: they bypass page accounting. */ -TESTPAGEFLAG(Writeback, writeback, PF_NO_COMPOUND) - TESTSCFLAG(Writeback, writeback, PF_NO_COMPOUND) +TESTPAGEFLAG(Writeback, writeback, PF_NO_TAIL) + TESTSCFLAG(Writeback, writeback, PF_NO_TAIL) PAGEFLAG(MappedToDisk, mappedtodisk, PF_NO_TAIL) /* PG_readahead is only used for reads; PG_reclaim is only for writes */ diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 79b36f5..5bbd678 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -353,8 +353,16 @@ struct page *find_lock_entry(struct address_space *mapping, pgoff_t offset); unsigned find_get_entries(struct address_space *mapping, pgoff_t start, unsigned int nr_entries, struct page **entries, pgoff_t *indices); -unsigned find_get_pages(struct address_space *mapping, pgoff_t start, - unsigned int nr_pages, struct page **pages); +unsigned find_get_pages_range(struct address_space *mapping, pgoff_t *start, + pgoff_t end, unsigned int nr_pages, + struct page **pages); +static inline unsigned find_get_pages(struct address_space *mapping, + pgoff_t *start, unsigned int nr_pages, + struct page **pages) +{ + return find_get_pages_range(mapping, start, (pgoff_t)-1, nr_pages, + pages); +} unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t start, unsigned int nr_pages, struct page **pages); unsigned find_get_pages_tag(struct address_space *mapping, pgoff_t *index, diff --git a/include/linux/pagevec.h b/include/linux/pagevec.h index b45d391..4dcd550 100644 --- a/include/linux/pagevec.h +++ b/include/linux/pagevec.h @@ -27,8 +27,16 @@ unsigned pagevec_lookup_entries(struct pagevec *pvec, pgoff_t start, unsigned nr_entries, pgoff_t *indices); void pagevec_remove_exceptionals(struct pagevec *pvec); -unsigned pagevec_lookup(struct pagevec *pvec, struct address_space *mapping, - pgoff_t start, unsigned nr_pages); +unsigned pagevec_lookup_range(struct pagevec *pvec, + struct address_space *mapping, + pgoff_t *start, pgoff_t end); +static inline unsigned pagevec_lookup(struct pagevec *pvec, + struct address_space *mapping, + pgoff_t *start) +{ + return pagevec_lookup_range(pvec, mapping, start, (pgoff_t)-1); +} + unsigned pagevec_lookup_tag(struct pagevec *pvec, struct address_space *mapping, pgoff_t *index, int tag, unsigned nr_pages); diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index 2b0a281..3a19c25 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -84,12 +84,6 @@ static inline bool mmget_not_zero(struct mm_struct *mm) /* mmput gets rid of the mappings and all user-space */ extern void mmput(struct mm_struct *); -#ifdef CONFIG_MMU -/* same as above but performs the slow path from the async context. Can - * be called from the atomic context as well - */ -extern void mmput_async(struct mm_struct *); -#endif /* Grab a reference to a task's mm, if it is not already going away */ extern struct mm_struct *get_task_mm(struct task_struct *task); diff --git a/include/linux/shm.h b/include/linux/shm.h index 0fb7061..21a5e6c 100644 --- a/include/linux/shm.h +++ b/include/linux/shm.h @@ -27,23 +27,6 @@ struct shmid_kernel /* private to the kernel */ /* shm_mode upper byte flags */ #define SHM_DEST 01000 /* segment will be destroyed on last detach */ #define SHM_LOCKED 02000 /* segment will not be swapped */ -#define SHM_HUGETLB 04000 /* segment will use huge TLB pages */ -#define SHM_NORESERVE 010000 /* don't check for reservations */ - -/* Bits [26:31] are reserved */ - -/* - * When SHM_HUGETLB is set bits [26:31] encode the log2 of the huge page size. - * This gives us 6 bits, which is enough until someone invents 128 bit address - * spaces. - * - * Assume these are all power of twos. - * When 0 use the default page size. - */ -#define SHM_HUGE_SHIFT 26 -#define SHM_HUGE_MASK 0x3f -#define SHM_HUGE_2MB (21 << SHM_HUGE_SHIFT) -#define SHM_HUGE_1GB (30 << SHM_HUGE_SHIFT) #ifdef CONFIG_SYSVIPC struct sysv_shm { diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index a7d6bd2..b6c3540 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -137,9 +137,15 @@ extern int shmem_mcopy_atomic_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd, unsigned long dst_addr, unsigned long src_addr, struct page **pagep); +extern int shmem_mfill_zeropage_pte(struct mm_struct *dst_mm, + pmd_t *dst_pmd, + struct vm_area_struct *dst_vma, + unsigned long dst_addr); #else #define shmem_mcopy_atomic_pte(dst_mm, dst_pte, dst_vma, dst_addr, \ src_addr, pagep) ({ BUG(); 0; }) +#define shmem_mfill_zeropage_pte(dst_mm, dst_pmd, dst_vma, \ + dst_addr) ({ BUG(); 0; }) #endif #endif diff --git a/include/linux/shrinker.h b/include/linux/shrinker.h index 4fcacd9..51d1896 100644 --- a/include/linux/shrinker.h +++ b/include/linux/shrinker.h @@ -18,6 +18,13 @@ struct shrink_control { */ unsigned long nr_to_scan; + /* + * How many objects did scan_objects process? + * This defaults to nr_to_scan before every call, but the callee + * should track its actual progress. + */ + unsigned long nr_scanned; + /* current node being shrunk (for NUMA aware shrinkers) */ int nid; diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h index cc0faf3..0783b62 100644 --- a/include/linux/slub_def.h +++ b/include/linux/slub_def.h @@ -115,6 +115,10 @@ struct kmem_cache { #endif #endif +#ifdef CONFIG_SLAB_FREELIST_HARDENED + unsigned long random; +#endif + #ifdef CONFIG_NUMA /* * Defragmentation by allocating from a remote node. diff --git a/include/linux/swap.h b/include/linux/swap.h index d83d28e..8bf3487 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -188,6 +188,7 @@ struct swap_cluster_info { }; #define CLUSTER_FLAG_FREE 1 /* This cluster is free */ #define CLUSTER_FLAG_NEXT_NULL 2 /* This cluster has no next cluster */ +#define CLUSTER_FLAG_HUGE 4 /* This cluster is backing a transparent huge page */ /* * We assign a cluster to each CPU, so each CPU can allocate swap entry from @@ -211,7 +212,7 @@ struct swap_info_struct { unsigned long flags; /* SWP_USED etc: see above */ signed short prio; /* swap priority of this type */ struct plist_node list; /* entry in swap_active_head */ - struct plist_node avail_list; /* entry in swap_avail_head */ + struct plist_node avail_lists[MAX_NUMNODES];/* entry in swap_avail_heads */ signed char type; /* strange name for an index */ unsigned int max; /* extent of the swap_map */ unsigned char *swap_map; /* vmalloc'ed array of usage counts */ @@ -250,6 +251,25 @@ struct swap_info_struct { struct swap_cluster_list discard_clusters; /* discard clusters list */ }; +#ifdef CONFIG_64BIT +#define SWAP_RA_ORDER_CEILING 5 +#else +/* Avoid stack overflow, because we need to save part of page table */ +#define SWAP_RA_ORDER_CEILING 3 +#define SWAP_RA_PTE_CACHE_SIZE (1 << SWAP_RA_ORDER_CEILING) +#endif + +struct vma_swap_readahead { + unsigned short win; + unsigned short offset; + unsigned short nr_pte; +#ifdef CONFIG_64BIT + pte_t *ptes; +#else + pte_t ptes[SWAP_RA_PTE_CACHE_SIZE]; +#endif +}; + /* linux/mm/workingset.c */ void *workingset_eviction(struct address_space *mapping, struct page *page); bool workingset_refault(void *shadow); @@ -262,8 +282,8 @@ extern unsigned long totalreserve_pages; extern unsigned long nr_free_buffer_pages(void); extern unsigned long nr_free_pagecache_pages(void); -/* Definition of global_page_state not available yet */ -#define nr_free_pages() global_page_state(NR_FREE_PAGES) +/* Definition of global_zone_page_state not available yet */ +#define nr_free_pages() global_zone_page_state(NR_FREE_PAGES) /* linux/mm/swap.c */ @@ -349,6 +369,7 @@ int generic_swapfile_activate(struct swap_info_struct *, struct file *, #define SWAP_ADDRESS_SPACE_SHIFT 14 #define SWAP_ADDRESS_SPACE_PAGES (1 << SWAP_ADDRESS_SPACE_SHIFT) extern struct address_space *swapper_spaces[]; +extern bool swap_vma_readahead; #define swap_address_space(entry) \ (&swapper_spaces[swp_type(entry)][swp_offset(entry) \ >> SWAP_ADDRESS_SPACE_SHIFT]) @@ -361,7 +382,9 @@ extern void __delete_from_swap_cache(struct page *); extern void delete_from_swap_cache(struct page *); extern void free_page_and_swap_cache(struct page *); extern void free_pages_and_swap_cache(struct page **, int); -extern struct page *lookup_swap_cache(swp_entry_t); +extern struct page *lookup_swap_cache(swp_entry_t entry, + struct vm_area_struct *vma, + unsigned long addr); extern struct page *read_swap_cache_async(swp_entry_t, gfp_t, struct vm_area_struct *vma, unsigned long addr, bool do_poll); @@ -371,11 +394,23 @@ extern struct page *__read_swap_cache_async(swp_entry_t, gfp_t, extern struct page *swapin_readahead(swp_entry_t, gfp_t, struct vm_area_struct *vma, unsigned long addr); +extern struct page *swap_readahead_detect(struct vm_fault *vmf, + struct vma_swap_readahead *swap_ra); +extern struct page *do_swap_page_readahead(swp_entry_t fentry, gfp_t gfp_mask, + struct vm_fault *vmf, + struct vma_swap_readahead *swap_ra); + /* linux/mm/swapfile.c */ extern atomic_long_t nr_swap_pages; extern long total_swap_pages; +extern atomic_t nr_rotate_swap; extern bool has_usable_swap(void); +static inline bool swap_use_vma_readahead(void) +{ + return READ_ONCE(swap_vma_readahead) && !atomic_read(&nr_rotate_swap); +} + /* Swap 50% full? Release swapcache more aggressively.. */ static inline bool vm_swap_full(void) { @@ -465,12 +500,32 @@ static inline struct page *swapin_readahead(swp_entry_t swp, gfp_t gfp_mask, return NULL; } +static inline bool swap_use_vma_readahead(void) +{ + return false; +} + +static inline struct page *swap_readahead_detect( + struct vm_fault *vmf, struct vma_swap_readahead *swap_ra) +{ + return NULL; +} + +static inline struct page *do_swap_page_readahead( + swp_entry_t fentry, gfp_t gfp_mask, + struct vm_fault *vmf, struct vma_swap_readahead *swap_ra) +{ + return NULL; +} + static inline int swap_writepage(struct page *p, struct writeback_control *wbc) { return 0; } -static inline struct page *lookup_swap_cache(swp_entry_t swp) +static inline struct page *lookup_swap_cache(swp_entry_t swp, + struct vm_area_struct *vma, + unsigned long addr) { return NULL; } @@ -509,8 +564,8 @@ static inline int swp_swapcount(swp_entry_t entry) return 0; } -#define reuse_swap_page(page, total_mapcount) \ - (page_trans_huge_mapcount(page, total_mapcount) == 1) +#define reuse_swap_page(page, total_map_swapcount) \ + (page_trans_huge_mapcount(page, total_map_swapcount) == 1) static inline int try_to_free_swap(struct page *page) { @@ -526,6 +581,15 @@ static inline swp_entry_t get_swap_page(struct page *page) #endif /* CONFIG_SWAP */ +#ifdef CONFIG_THP_SWAP +extern int split_swap_cluster(swp_entry_t entry); +#else +static inline int split_swap_cluster(swp_entry_t entry) +{ + return 0; +} +#endif + #ifdef CONFIG_MEMCG static inline int mem_cgroup_swappiness(struct mem_cgroup *memcg) { diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h index 37e8d31..d77bc35 100644 --- a/include/linux/vm_event_item.h +++ b/include/linux/vm_event_item.h @@ -85,6 +85,8 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, #endif THP_ZERO_PAGE_ALLOC, THP_ZERO_PAGE_ALLOC_FAILED, + THP_SWPOUT, + THP_SWPOUT_FALLBACK, #endif #ifdef CONFIG_MEMORY_BALLOON BALLOON_INFLATE, @@ -104,6 +106,10 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, VMACACHE_FIND_HITS, VMACACHE_FULL_FLUSHES, #endif +#ifdef CONFIG_SWAP + SWAP_RA, + SWAP_RA_HIT, +#endif NR_VM_EVENT_ITEMS }; diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index b3d85f3..97e11ab 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -123,7 +123,7 @@ static inline void node_page_state_add(long x, struct pglist_data *pgdat, atomic_long_add(x, &vm_node_stat[item]); } -static inline unsigned long global_page_state(enum zone_stat_item item) +static inline unsigned long global_zone_page_state(enum zone_stat_item item) { long x = atomic_long_read(&vm_zone_stat[item]); #ifdef CONFIG_SMP @@ -199,7 +199,7 @@ extern unsigned long sum_zone_node_page_state(int node, extern unsigned long node_page_state(struct pglist_data *pgdat, enum node_stat_item item); #else -#define sum_zone_node_page_state(node, item) global_page_state(item) +#define sum_zone_node_page_state(node, item) global_zone_page_state(item) #define node_page_state(node, item) global_node_page_state(item) #endif /* CONFIG_NUMA */ diff --git a/include/trace/events/fs_dax.h b/include/trace/events/fs_dax.h index 08bb3ed..fbc4a06 100644 --- a/include/trace/events/fs_dax.h +++ b/include/trace/events/fs_dax.h @@ -190,8 +190,6 @@ DEFINE_EVENT(dax_pte_fault_class, name, \ DEFINE_PTE_FAULT_EVENT(dax_pte_fault); DEFINE_PTE_FAULT_EVENT(dax_pte_fault_done); -DEFINE_PTE_FAULT_EVENT(dax_pfn_mkwrite_no_entry); -DEFINE_PTE_FAULT_EVENT(dax_pfn_mkwrite); DEFINE_PTE_FAULT_EVENT(dax_load_hole); TRACE_EVENT(dax_insert_mapping, diff --git a/include/trace/events/mmflags.h b/include/trace/events/mmflags.h index 8e50d01..4c2e473 100644 --- a/include/trace/events/mmflags.h +++ b/include/trace/events/mmflags.h @@ -125,12 +125,6 @@ IF_HAVE_PG_IDLE(PG_idle, "idle" ) #define __VM_ARCH_SPECIFIC_1 {VM_ARCH_1, "arch_1" } #endif -#if defined(CONFIG_X86) -#define __VM_ARCH_SPECIFIC_2 {VM_MPX, "mpx" } -#else -#define __VM_ARCH_SPECIFIC_2 {VM_ARCH_2, "arch_2" } -#endif - #ifdef CONFIG_MEM_SOFT_DIRTY #define IF_HAVE_VM_SOFTDIRTY(flag,name) {flag, name }, #else @@ -162,7 +156,7 @@ IF_HAVE_PG_IDLE(PG_idle, "idle" ) {VM_NORESERVE, "noreserve" }, \ {VM_HUGETLB, "hugetlb" }, \ __VM_ARCH_SPECIFIC_1 , \ - __VM_ARCH_SPECIFIC_2 , \ + {VM_WIPEONFORK, "wipeonfork" }, \ {VM_DONTDUMP, "dontdump" }, \ IF_HAVE_VM_SOFTDIRTY(VM_SOFTDIRTY, "softdirty" ) \ {VM_MIXEDMAP, "mixedmap" }, \ diff --git a/include/uapi/asm-generic/hugetlb_encode.h b/include/uapi/asm-generic/hugetlb_encode.h new file mode 100644 index 0000000..e4732d3 --- /dev/null +++ b/include/uapi/asm-generic/hugetlb_encode.h @@ -0,0 +1,34 @@ +#ifndef _ASM_GENERIC_HUGETLB_ENCODE_H_ +#define _ASM_GENERIC_HUGETLB_ENCODE_H_ + +/* + * Several system calls take a flag to request "hugetlb" huge pages. + * Without further specification, these system calls will use the + * system's default huge page size. If a system supports multiple + * huge page sizes, the desired huge page size can be specified in + * bits [26:31] of the flag arguments. The value in these 6 bits + * will encode the log2 of the huge page size. + * + * The following definitions are associated with this huge page size + * encoding in flag arguments. System call specific header files + * that use this encoding should include this file. They can then + * provide definitions based on these with their own specific prefix. + * for example: + * #define MAP_HUGE_SHIFT HUGETLB_FLAG_ENCODE_SHIFT + */ + +#define HUGETLB_FLAG_ENCODE_SHIFT 26 +#define HUGETLB_FLAG_ENCODE_MASK 0x3f + +#define HUGETLB_FLAG_ENCODE_64KB (16 << HUGETLB_FLAG_ENCODE_SHIFT) +#define HUGETLB_FLAG_ENCODE_512KB (19 << HUGETLB_FLAG_ENCODE_SHIFT) +#define HUGETLB_FLAG_ENCODE_1MB (20 << HUGETLB_FLAG_ENCODE_SHIFT) +#define HUGETLB_FLAG_ENCODE_2MB (21 << HUGETLB_FLAG_ENCODE_SHIFT) +#define HUGETLB_FLAG_ENCODE_8MB (23 << HUGETLB_FLAG_ENCODE_SHIFT) +#define HUGETLB_FLAG_ENCODE_16MB (24 << HUGETLB_FLAG_ENCODE_SHIFT) +#define HUGETLB_FLAG_ENCODE_256MB (28 << HUGETLB_FLAG_ENCODE_SHIFT) +#define HUGETLB_FLAG_ENCODE_1GB (30 << HUGETLB_FLAG_ENCODE_SHIFT) +#define HUGETLB_FLAG_ENCODE_2GB (31 << HUGETLB_FLAG_ENCODE_SHIFT) +#define HUGETLB_FLAG_ENCODE_16GB (34 << HUGETLB_FLAG_ENCODE_SHIFT) + +#endif /* _ASM_GENERIC_HUGETLB_ENCODE_H_ */ diff --git a/include/uapi/asm-generic/mman-common.h b/include/uapi/asm-generic/mman-common.h index 8c27db0..203268f 100644 --- a/include/uapi/asm-generic/mman-common.h +++ b/include/uapi/asm-generic/mman-common.h @@ -58,20 +58,12 @@ overrides the coredump filter bits */ #define MADV_DODUMP 17 /* Clear the MADV_DONTDUMP flag */ +#define MADV_WIPEONFORK 18 /* Zero memory on fork, child only */ +#define MADV_KEEPONFORK 19 /* Undo MADV_WIPEONFORK */ + /* compatibility flags */ #define MAP_FILE 0 -/* - * When MAP_HUGETLB is set bits [26:31] encode the log2 of the huge page size. - * This gives us 6 bits, which is enough until someone invents 128 bit address - * spaces. - * - * Assume these are all power of twos. - * When 0 use the default page size. - */ -#define MAP_HUGE_SHIFT 26 -#define MAP_HUGE_MASK 0x3f - #define PKEY_DISABLE_ACCESS 0x1 #define PKEY_DISABLE_WRITE 0x2 #define PKEY_ACCESS_MASK (PKEY_DISABLE_ACCESS |\ diff --git a/include/uapi/linux/memfd.h b/include/uapi/linux/memfd.h index 534e364..7f3a722 100644 --- a/include/uapi/linux/memfd.h +++ b/include/uapi/linux/memfd.h @@ -1,8 +1,32 @@ #ifndef _UAPI_LINUX_MEMFD_H #define _UAPI_LINUX_MEMFD_H +#include <asm-generic/hugetlb_encode.h> + /* flags for memfd_create(2) (unsigned int) */ #define MFD_CLOEXEC 0x0001U #define MFD_ALLOW_SEALING 0x0002U +#define MFD_HUGETLB 0x0004U + +/* + * Huge page size encoding when MFD_HUGETLB is specified, and a huge page + * size other than the default is desired. See hugetlb_encode.h. + * All known huge page size encodings are provided here. It is the + * responsibility of the application to know which sizes are supported on + * the running system. See mmap(2) man page for details. + */ +#define MFD_HUGE_SHIFT HUGETLB_FLAG_ENCODE_SHIFT +#define MFD_HUGE_MASK HUGETLB_FLAG_ENCODE_MASK + +#define MFD_HUGE_64KB HUGETLB_FLAG_ENCODE_64KB +#define MFD_HUGE_512KB HUGETLB_FLAG_ENCODE_512KB +#define MFD_HUGE_1MB HUGETLB_FLAG_ENCODE_1MB +#define MFD_HUGE_2MB HUGETLB_FLAG_ENCODE_2MB +#define MFD_HUGE_8MB HUGETLB_FLAG_ENCODE_8MB +#define MFD_HUGE_16MB HUGETLB_FLAG_ENCODE_16MB +#define MFD_HUGE_256MB HUGETLB_FLAG_ENCODE_256MB +#define MFD_HUGE_1GB HUGETLB_FLAG_ENCODE_1GB +#define MFD_HUGE_2GB HUGETLB_FLAG_ENCODE_2GB +#define MFD_HUGE_16GB HUGETLB_FLAG_ENCODE_16GB #endif /* _UAPI_LINUX_MEMFD_H */ diff --git a/include/uapi/linux/mman.h b/include/uapi/linux/mman.h index ade4acd..a937480 100644 --- a/include/uapi/linux/mman.h +++ b/include/uapi/linux/mman.h @@ -2,6 +2,7 @@ #define _UAPI_LINUX_MMAN_H #include <asm/mman.h> +#include <asm-generic/hugetlb_encode.h> #define MREMAP_MAYMOVE 1 #define MREMAP_FIXED 2 @@ -10,4 +11,25 @@ #define OVERCOMMIT_ALWAYS 1 #define OVERCOMMIT_NEVER 2 +/* + * Huge page size encoding when MAP_HUGETLB is specified, and a huge page + * size other than the default is desired. See hugetlb_encode.h. + * All known huge page size encodings are provided here. It is the + * responsibility of the application to know which sizes are supported on + * the running system. See mmap(2) man page for details. + */ +#define MAP_HUGE_SHIFT HUGETLB_FLAG_ENCODE_SHIFT +#define MAP_HUGE_MASK HUGETLB_FLAG_ENCODE_MASK + +#define MAP_HUGE_64KB HUGETLB_FLAG_ENCODE_64KB +#define MAP_HUGE_512KB HUGETLB_FLAG_ENCODE_512KB +#define MAP_HUGE_1MB HUGETLB_FLAG_ENCODE_1MB +#define MAP_HUGE_2MB HUGETLB_FLAG_ENCODE_2MB +#define MAP_HUGE_8MB HUGETLB_FLAG_ENCODE_8MB +#define MAP_HUGE_16MB HUGETLB_FLAG_ENCODE_16MB +#define MAP_HUGE_256MB HUGETLB_FLAG_ENCODE_256MB +#define MAP_HUGE_1GB HUGETLB_FLAG_ENCODE_1GB +#define MAP_HUGE_2GB HUGETLB_FLAG_ENCODE_2GB +#define MAP_HUGE_16GB HUGETLB_FLAG_ENCODE_16GB + #endif /* _UAPI_LINUX_MMAN_H */ diff --git a/include/uapi/linux/shm.h b/include/uapi/linux/shm.h index 1fbf24e..cf23c87 100644 --- a/include/uapi/linux/shm.h +++ b/include/uapi/linux/shm.h @@ -3,6 +3,7 @@ #include <linux/ipc.h> #include <linux/errno.h> +#include <asm-generic/hugetlb_encode.h> #ifndef __KERNEL__ #include <unistd.h> #endif @@ -40,11 +41,37 @@ struct shmid_ds { /* Include the definition of shmid64_ds and shminfo64 */ #include <asm/shmbuf.h> -/* permission flag for shmget */ +/* + * shmget() shmflg values. + */ +/* The bottom nine bits are the same as open(2) mode flags */ #define SHM_R 0400 /* or S_IRUGO from <linux/stat.h> */ #define SHM_W 0200 /* or S_IWUGO from <linux/stat.h> */ +/* Bits 9 & 10 are IPC_CREAT and IPC_EXCL */ +#define SHM_HUGETLB 04000 /* segment will use huge TLB pages */ +#define SHM_NORESERVE 010000 /* don't check for reservations */ + +/* + * Huge page size encoding when SHM_HUGETLB is specified, and a huge page + * size other than the default is desired. See hugetlb_encode.h + */ +#define SHM_HUGE_SHIFT HUGETLB_FLAG_ENCODE_SHIFT +#define SHM_HUGE_MASK HUGETLB_FLAG_ENCODE_MASK + +#define SHM_HUGE_64KB HUGETLB_FLAG_ENCODE_64KB +#define SHM_HUGE_512KB HUGETLB_FLAG_ENCODE_512KB +#define SHM_HUGE_1MB HUGETLB_FLAG_ENCODE_1MB +#define SHM_HUGE_2MB HUGETLB_FLAG_ENCODE_2MB +#define SHM_HUGE_8MB HUGETLB_FLAG_ENCODE_8MB +#define SHM_HUGE_16MB HUGETLB_FLAG_ENCODE_16MB +#define SHM_HUGE_256MB HUGETLB_FLAG_ENCODE_256MB +#define SHM_HUGE_1GB HUGETLB_FLAG_ENCODE_1GB +#define SHM_HUGE_2GB HUGETLB_FLAG_ENCODE_2GB +#define SHM_HUGE_16GB HUGETLB_FLAG_ENCODE_16GB -/* mode for attach */ +/* + * shmat() shmflg values + */ #define SHM_RDONLY 010000 /* read-only access */ #define SHM_RND 020000 /* round attach address to SHMLBA boundary */ #define SHM_REMAP 040000 /* take-over region on attach */ diff --git a/include/uapi/linux/userfaultfd.h b/include/uapi/linux/userfaultfd.h index 3b05953..d6d1f65 100644 --- a/include/uapi/linux/userfaultfd.h +++ b/include/uapi/linux/userfaultfd.h @@ -23,7 +23,9 @@ UFFD_FEATURE_EVENT_REMOVE | \ UFFD_FEATURE_EVENT_UNMAP | \ UFFD_FEATURE_MISSING_HUGETLBFS | \ - UFFD_FEATURE_MISSING_SHMEM) + UFFD_FEATURE_MISSING_SHMEM | \ + UFFD_FEATURE_SIGBUS | \ + UFFD_FEATURE_THREAD_ID) #define UFFD_API_IOCTLS \ ((__u64)1 << _UFFDIO_REGISTER | \ (__u64)1 << _UFFDIO_UNREGISTER | \ @@ -78,6 +80,9 @@ struct uffd_msg { struct { __u64 flags; __u64 address; + union { + __u32 ptid; + } feat; } pagefault; struct { @@ -153,6 +158,13 @@ struct uffdio_api { * UFFD_FEATURE_MISSING_SHMEM works the same as * UFFD_FEATURE_MISSING_HUGETLBFS, but it applies to shmem * (i.e. tmpfs and other shmem based APIs). + * + * UFFD_FEATURE_SIGBUS feature means no page-fault + * (UFFD_EVENT_PAGEFAULT) event will be delivered, instead + * a SIGBUS signal will be sent to the faulting process. + * + * UFFD_FEATURE_THREAD_ID pid of the page faulted task_struct will + * be returned, if feature is not requested 0 will be returned. */ #define UFFD_FEATURE_PAGEFAULT_FLAG_WP (1<<0) #define UFFD_FEATURE_EVENT_FORK (1<<1) @@ -161,6 +173,8 @@ struct uffdio_api { #define UFFD_FEATURE_MISSING_HUGETLBFS (1<<4) #define UFFD_FEATURE_MISSING_SHMEM (1<<5) #define UFFD_FEATURE_EVENT_UNMAP (1<<6) +#define UFFD_FEATURE_SIGBUS (1<<7) +#define UFFD_FEATURE_THREAD_ID (1<<8) __u64 features; __u64 ioctls; diff --git a/init/Kconfig b/init/Kconfig index 5f0ef85..78cb246 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -1576,6 +1576,15 @@ config SLAB_FREELIST_RANDOM security feature reduces the predictability of the kernel slab allocator against heap overflows. +config SLAB_FREELIST_HARDENED + bool "Harden slab freelist metadata" + depends on SLUB + help + Many kernel heap attacks try to target slab cache metadata and + other infrastructure. This options makes minor performance + sacrifies to harden the kernel slab allocator against common + freelist exploit methods. + config SLUB_CPU_PARTIAL default y depends on SLUB && SMP diff --git a/init/main.c b/init/main.c index 8828fc1..a21a1a8 100644 --- a/init/main.c +++ b/init/main.c @@ -542,7 +542,7 @@ asmlinkage __visible void __init start_kernel(void) boot_cpu_state_init(); smp_prepare_boot_cpu(); /* arch-specific boot-cpu hooks */ - build_all_zonelists(NULL, NULL); + build_all_zonelists(NULL); page_alloc_init(); pr_notice("Kernel command line: %s\n", boot_command_line); diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index df2e0f1..f64fc96 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -4100,9 +4100,6 @@ static void offline_css(struct cgroup_subsys_state *css) if (!(css->flags & CSS_ONLINE)) return; - if (ss->css_reset) - ss->css_reset(css); - if (ss->css_offline) ss->css_offline(css); diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index 2f4039b..e748578 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -56,6 +56,7 @@ #include <linux/time64.h> #include <linux/backing-dev.h> #include <linux/sort.h> +#include <linux/oom.h> #include <linux/uaccess.h> #include <linux/atomic.h> @@ -2500,12 +2501,12 @@ static struct cpuset *nearest_hardwall_ancestor(struct cpuset *cs) * If we're in interrupt, yes, we can always allocate. If @node is set in * current's mems_allowed, yes. If it's not a __GFP_HARDWALL request and this * node is set in the nearest hardwalled cpuset ancestor to current's cpuset, - * yes. If current has access to memory reserves due to TIF_MEMDIE, yes. + * yes. If current has access to memory reserves as an oom victim, yes. * Otherwise, no. * * GFP_USER allocations are marked with the __GFP_HARDWALL bit, * and do not allow allocations outside the current tasks cpuset - * unless the task has been OOM killed as is marked TIF_MEMDIE. + * unless the task has been OOM killed. * GFP_KERNEL allocations are not so marked, so can escape to the * nearest enclosing hardwalled ancestor cpuset. * @@ -2528,7 +2529,7 @@ static struct cpuset *nearest_hardwall_ancestor(struct cpuset *cs) * affect that: * in_interrupt - any node ok (current task context irrelevant) * GFP_ATOMIC - any node ok - * TIF_MEMDIE - any node ok + * tsk_is_oom_victim - any node ok * GFP_KERNEL - any node in enclosing hardwalled cpuset ok * GFP_USER - only nodes in current tasks mems allowed ok. */ @@ -2546,7 +2547,7 @@ bool __cpuset_node_allowed(int node, gfp_t gfp_mask) * Allow tasks that have access to memory reserves because they have * been OOM killed to get memory anywhere. */ - if (unlikely(test_thread_flag(TIF_MEMDIE))) + if (unlikely(tsk_is_oom_victim(current))) return true; if (gfp_mask & __GFP_HARDWALL) /* If hardwall request, stop here */ return false; diff --git a/kernel/fork.c b/kernel/fork.c index 4e5345c..24a4c0b 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -657,7 +657,12 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm, retval = dup_userfaultfd(tmp, &uf); if (retval) goto fail_nomem_anon_vma_fork; - if (anon_vma_fork(tmp, mpnt)) + if (tmp->vm_flags & VM_WIPEONFORK) { + /* VM_WIPEONFORK gets a clean slate in the child. */ + tmp->anon_vma = NULL; + if (anon_vma_prepare(tmp)) + goto fail_nomem_anon_vma_fork; + } else if (anon_vma_fork(tmp, mpnt)) goto fail_nomem_anon_vma_fork; tmp->vm_flags &= ~(VM_LOCKED | VM_LOCKONFAULT); tmp->vm_next = tmp->vm_prev = NULL; @@ -701,7 +706,8 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm, rb_parent = &tmp->vm_rb; mm->map_count++; - retval = copy_page_range(mm, oldmm, mpnt); + if (!(tmp->vm_flags & VM_WIPEONFORK)) + retval = copy_page_range(mm, oldmm, mpnt); if (tmp->vm_ops && tmp->vm_ops->open) tmp->vm_ops->open(tmp); @@ -922,7 +928,6 @@ static inline void __mmput(struct mm_struct *mm) } if (mm->binfmt) module_put(mm->binfmt->module); - set_bit(MMF_OOM_SKIP, &mm->flags); mmdrop(mm); } @@ -938,22 +943,6 @@ void mmput(struct mm_struct *mm) } EXPORT_SYMBOL_GPL(mmput); -#ifdef CONFIG_MMU -static void mmput_async_fn(struct work_struct *work) -{ - struct mm_struct *mm = container_of(work, struct mm_struct, async_put_work); - __mmput(mm); -} - -void mmput_async(struct mm_struct *mm) -{ - if (atomic_dec_and_test(&mm->mm_users)) { - INIT_WORK(&mm->async_put_work, mmput_async_fn); - schedule_work(&mm->async_put_work); - } -} -#endif - /** * set_mm_exe_file - change a reference to the mm's executable file * diff --git a/kernel/memremap.c b/kernel/memremap.c index 9afdc43..066e73c 100644 --- a/kernel/memremap.c +++ b/kernel/memremap.c @@ -194,18 +194,41 @@ struct page_map { struct vmem_altmap altmap; }; -static void pgmap_radix_release(struct resource *res) +static unsigned long order_at(struct resource *res, unsigned long pgoff) { - resource_size_t key, align_start, align_size, align_end; + unsigned long phys_pgoff = PHYS_PFN(res->start) + pgoff; + unsigned long nr_pages, mask; - align_start = res->start & ~(SECTION_SIZE - 1); - align_size = ALIGN(resource_size(res), SECTION_SIZE); - align_end = align_start + align_size - 1; + nr_pages = PHYS_PFN(resource_size(res)); + if (nr_pages == pgoff) + return ULONG_MAX; + + /* + * What is the largest aligned power-of-2 range available from + * this resource pgoff to the end of the resource range, + * considering the alignment of the current pgoff? + */ + mask = phys_pgoff | rounddown_pow_of_two(nr_pages - pgoff); + if (!mask) + return ULONG_MAX; + + return find_first_bit(&mask, BITS_PER_LONG); +} + +#define foreach_order_pgoff(res, order, pgoff) \ + for (pgoff = 0, order = order_at((res), pgoff); order < ULONG_MAX; \ + pgoff += 1UL << order, order = order_at((res), pgoff)) + +static void pgmap_radix_release(struct resource *res) +{ + unsigned long pgoff, order; mutex_lock(&pgmap_lock); - for (key = res->start; key <= res->end; key += SECTION_SIZE) - radix_tree_delete(&pgmap_radix, key >> PA_SECTION_SHIFT); + foreach_order_pgoff(res, order, pgoff) + radix_tree_delete(&pgmap_radix, PHYS_PFN(res->start) + pgoff); mutex_unlock(&pgmap_lock); + + synchronize_rcu(); } static unsigned long pfn_first(struct page_map *page_map) @@ -268,7 +291,7 @@ struct dev_pagemap *find_dev_pagemap(resource_size_t phys) WARN_ON_ONCE(!rcu_read_lock_held()); - page_map = radix_tree_lookup(&pgmap_radix, phys >> PA_SECTION_SHIFT); + page_map = radix_tree_lookup(&pgmap_radix, PHYS_PFN(phys)); return page_map ? &page_map->pgmap : NULL; } @@ -293,12 +316,12 @@ struct dev_pagemap *find_dev_pagemap(resource_size_t phys) void *devm_memremap_pages(struct device *dev, struct resource *res, struct percpu_ref *ref, struct vmem_altmap *altmap) { - resource_size_t key, align_start, align_size, align_end; + resource_size_t align_start, align_size, align_end; + unsigned long pfn, pgoff, order; pgprot_t pgprot = PAGE_KERNEL; struct dev_pagemap *pgmap; struct page_map *page_map; int error, nid, is_ram; - unsigned long pfn; align_start = res->start & ~(SECTION_SIZE - 1); align_size = ALIGN(res->start + resource_size(res), SECTION_SIZE) @@ -337,11 +360,12 @@ void *devm_memremap_pages(struct device *dev, struct resource *res, mutex_lock(&pgmap_lock); error = 0; align_end = align_start + align_size - 1; - for (key = align_start; key <= align_end; key += SECTION_SIZE) { + + foreach_order_pgoff(res, order, pgoff) { struct dev_pagemap *dup; rcu_read_lock(); - dup = find_dev_pagemap(key); + dup = find_dev_pagemap(res->start + PFN_PHYS(pgoff)); rcu_read_unlock(); if (dup) { dev_err(dev, "%s: %pr collides with mapping for %s\n", @@ -349,8 +373,8 @@ void *devm_memremap_pages(struct device *dev, struct resource *res, error = -EBUSY; break; } - error = radix_tree_insert(&pgmap_radix, key >> PA_SECTION_SHIFT, - page_map); + error = __radix_tree_insert(&pgmap_radix, + PHYS_PFN(res->start) + pgoff, order, page_map); if (error) { dev_err(dev, "%s: failed: %d\n", __func__, error); break; @@ -678,6 +678,7 @@ config ZONE_DEVICE depends on MEMORY_HOTREMOVE depends on SPARSEMEM_VMEMMAP depends on ARCH_HAS_ZONE_DEVICE + select RADIX_TREE_MULTIORDER help Device memory hotplug support allows for establishing pmem, diff --git a/mm/filemap.c b/mm/filemap.c index 1e01cb6..9d21afd 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -130,17 +130,8 @@ static int page_cache_tree_insert(struct address_space *mapping, return -EEXIST; mapping->nrexceptional--; - if (!dax_mapping(mapping)) { - if (shadowp) - *shadowp = p; - } else { - /* DAX can replace empty locked entry with a hole */ - WARN_ON_ONCE(p != - dax_radix_locked_entry(0, RADIX_DAX_EMPTY)); - /* Wakeup waiters for exceptional entry lock */ - dax_wake_mapping_entry_waiter(mapping, page->index, p, - true); - } + if (shadowp) + *shadowp = p; } __radix_tree_replace(&mapping->page_tree, node, slot, page, workingset_update_node, mapping); @@ -402,8 +393,7 @@ bool filemap_range_has_page(struct address_space *mapping, { pgoff_t index = start_byte >> PAGE_SHIFT; pgoff_t end = end_byte >> PAGE_SHIFT; - struct pagevec pvec; - bool ret; + struct page *page; if (end_byte < start_byte) return false; @@ -411,12 +401,10 @@ bool filemap_range_has_page(struct address_space *mapping, if (mapping->nrpages == 0) return false; - pagevec_init(&pvec, 0); - if (!pagevec_lookup(&pvec, mapping, index, 1)) + if (!find_get_pages_range(mapping, &index, end, 1, &page)) return false; - ret = (pvec.pages[0]->index <= end); - pagevec_release(&pvec); - return ret; + put_page(page); + return true; } EXPORT_SYMBOL(filemap_range_has_page); @@ -1564,23 +1552,29 @@ export: } /** - * find_get_pages - gang pagecache lookup + * find_get_pages_range - gang pagecache lookup * @mapping: The address_space to search * @start: The starting page index + * @end: The final page index (inclusive) * @nr_pages: The maximum number of pages * @pages: Where the resulting pages are placed * - * find_get_pages() will search for and return a group of up to - * @nr_pages pages in the mapping. The pages are placed at @pages. - * find_get_pages() takes a reference against the returned pages. + * find_get_pages_range() will search for and return a group of up to @nr_pages + * pages in the mapping starting at index @start and up to index @end + * (inclusive). The pages are placed at @pages. find_get_pages_range() takes + * a reference against the returned pages. * * The search returns a group of mapping-contiguous pages with ascending * indexes. There may be holes in the indices due to not-present pages. + * We also update @start to index the next page for the traversal. * - * find_get_pages() returns the number of pages which were found. + * find_get_pages_range() returns the number of pages which were found. If this + * number is smaller than @nr_pages, the end of specified range has been + * reached. */ -unsigned find_get_pages(struct address_space *mapping, pgoff_t start, - unsigned int nr_pages, struct page **pages) +unsigned find_get_pages_range(struct address_space *mapping, pgoff_t *start, + pgoff_t end, unsigned int nr_pages, + struct page **pages) { struct radix_tree_iter iter; void **slot; @@ -1590,8 +1584,11 @@ unsigned find_get_pages(struct address_space *mapping, pgoff_t start, return 0; rcu_read_lock(); - radix_tree_for_each_slot(slot, &mapping->page_tree, &iter, start) { + radix_tree_for_each_slot(slot, &mapping->page_tree, &iter, *start) { struct page *head, *page; + + if (iter.index > end) + break; repeat: page = radix_tree_deref_slot(slot); if (unlikely(!page)) @@ -1627,11 +1624,25 @@ repeat: } pages[ret] = page; - if (++ret == nr_pages) - break; + if (++ret == nr_pages) { + *start = pages[ret - 1]->index + 1; + goto out; + } } + /* + * We come here when there is no page beyond @end. We take care to not + * overflow the index @start as it confuses some of the callers. This + * breaks the iteration when there is page at index -1 but that is + * already broken anyway. + */ + if (end == (pgoff_t)-1) + *start = (pgoff_t)-1; + else + *start = end + 1; +out: rcu_read_unlock(); + return ret; } @@ -1352,7 +1352,7 @@ static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end, } #endif /* __HAVE_ARCH_PTE_SPECIAL */ -#ifdef __HAVE_ARCH_PTE_DEVMAP +#if defined(__HAVE_ARCH_PTE_DEVMAP) && defined(CONFIG_TRANSPARENT_HUGEPAGE) static int __gup_device_huge(unsigned long pfn, unsigned long addr, unsigned long end, struct page **pages, int *nr) { diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 3644ff9..0b51e70 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -328,7 +328,7 @@ static struct attribute *hugepage_attr[] = { NULL, }; -static struct attribute_group hugepage_attr_group = { +static const struct attribute_group hugepage_attr_group = { .attrs = hugepage_attr, }; @@ -567,7 +567,7 @@ static int __do_huge_pmd_anonymous_page(struct vm_fault *vmf, struct page *page, goto release; } - clear_huge_page(page, haddr, HPAGE_PMD_NR); + clear_huge_page(page, vmf->address, HPAGE_PMD_NR); /* * The memory barrier inside __SetPageUptodate makes sure that * clear_huge_page writes become visible before the set_pmd_at() @@ -1240,15 +1240,29 @@ int do_huge_pmd_wp_page(struct vm_fault *vmf, pmd_t orig_pmd) * We can only reuse the page if nobody else maps the huge page or it's * part. */ - if (page_trans_huge_mapcount(page, NULL) == 1) { + if (!trylock_page(page)) { + get_page(page); + spin_unlock(vmf->ptl); + lock_page(page); + spin_lock(vmf->ptl); + if (unlikely(!pmd_same(*vmf->pmd, orig_pmd))) { + unlock_page(page); + put_page(page); + goto out_unlock; + } + put_page(page); + } + if (reuse_swap_page(page, NULL)) { pmd_t entry; entry = pmd_mkyoung(orig_pmd); entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); if (pmdp_set_access_flags(vma, haddr, vmf->pmd, entry, 1)) update_mmu_cache_pmd(vma, vmf->address, vmf->pmd); ret |= VM_FAULT_WRITE; + unlock_page(page); goto out_unlock; } + unlock_page(page); get_page(page); spin_unlock(vmf->ptl); alloc: @@ -1291,7 +1305,7 @@ alloc: count_vm_event(THP_FAULT_ALLOC); if (!page) - clear_huge_page(new_page, haddr, HPAGE_PMD_NR); + clear_huge_page(new_page, vmf->address, HPAGE_PMD_NR); else copy_user_huge_page(new_page, page, haddr, vma, HPAGE_PMD_NR); __SetPageUptodate(new_page); @@ -2467,6 +2481,9 @@ int split_huge_page_to_list(struct page *page, struct list_head *list) VM_BUG_ON_PAGE(!PageLocked(page), page); VM_BUG_ON_PAGE(!PageCompound(page), page); + if (PageWriteback(page)) + return -EBUSY; + if (PageAnon(head)) { /* * The caller does not necessarily hold an mmap_sem that would @@ -2544,7 +2561,12 @@ int split_huge_page_to_list(struct page *page, struct list_head *list) __dec_node_page_state(page, NR_SHMEM_THPS); spin_unlock(&pgdata->split_queue_lock); __split_huge_page(page, list, flags); - ret = 0; + if (PageSwapCache(head)) { + swp_entry_t entry = { .val = page_private(head) }; + + ret = split_swap_cluster(entry); + } else + ret = 0; } else { if (IS_ENABLED(CONFIG_DEBUG_VM) && mapcount) { pr_alert("total_mapcount: %u, page_count(): %u\n", diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 31e207c..34625b2 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1066,11 +1066,11 @@ static void free_gigantic_page(struct page *page, unsigned int order) } static int __alloc_gigantic_page(unsigned long start_pfn, - unsigned long nr_pages) + unsigned long nr_pages, gfp_t gfp_mask) { unsigned long end_pfn = start_pfn + nr_pages; return alloc_contig_range(start_pfn, end_pfn, MIGRATE_MOVABLE, - GFP_KERNEL); + gfp_mask); } static bool pfn_range_valid_gigantic(struct zone *z, @@ -1108,19 +1108,24 @@ static bool zone_spans_last_pfn(const struct zone *zone, return zone_spans_pfn(zone, last_pfn); } -static struct page *alloc_gigantic_page(int nid, unsigned int order) +static struct page *alloc_gigantic_page(int nid, struct hstate *h) { + unsigned int order = huge_page_order(h); unsigned long nr_pages = 1 << order; unsigned long ret, pfn, flags; - struct zone *z; + struct zonelist *zonelist; + struct zone *zone; + struct zoneref *z; + gfp_t gfp_mask; - z = NODE_DATA(nid)->node_zones; - for (; z - NODE_DATA(nid)->node_zones < MAX_NR_ZONES; z++) { - spin_lock_irqsave(&z->lock, flags); + gfp_mask = htlb_alloc_mask(h) | __GFP_THISNODE; + zonelist = node_zonelist(nid, gfp_mask); + for_each_zone_zonelist_nodemask(zone, z, zonelist, gfp_zone(gfp_mask), NULL) { + spin_lock_irqsave(&zone->lock, flags); - pfn = ALIGN(z->zone_start_pfn, nr_pages); - while (zone_spans_last_pfn(z, pfn, nr_pages)) { - if (pfn_range_valid_gigantic(z, pfn, nr_pages)) { + pfn = ALIGN(zone->zone_start_pfn, nr_pages); + while (zone_spans_last_pfn(zone, pfn, nr_pages)) { + if (pfn_range_valid_gigantic(zone, pfn, nr_pages)) { /* * We release the zone lock here because * alloc_contig_range() will also lock the zone @@ -1128,16 +1133,16 @@ static struct page *alloc_gigantic_page(int nid, unsigned int order) * spinning on this lock, it may win the race * and cause alloc_contig_range() to fail... */ - spin_unlock_irqrestore(&z->lock, flags); - ret = __alloc_gigantic_page(pfn, nr_pages); + spin_unlock_irqrestore(&zone->lock, flags); + ret = __alloc_gigantic_page(pfn, nr_pages, gfp_mask); if (!ret) return pfn_to_page(pfn); - spin_lock_irqsave(&z->lock, flags); + spin_lock_irqsave(&zone->lock, flags); } pfn += nr_pages; } - spin_unlock_irqrestore(&z->lock, flags); + spin_unlock_irqrestore(&zone->lock, flags); } return NULL; @@ -1150,7 +1155,7 @@ static struct page *alloc_fresh_gigantic_page_node(struct hstate *h, int nid) { struct page *page; - page = alloc_gigantic_page(nid, huge_page_order(h)); + page = alloc_gigantic_page(nid, h); if (page) { prep_compound_gigantic_page(page, huge_page_order(h)); prep_new_huge_page(h, page, nid); @@ -2569,13 +2574,13 @@ static struct attribute *hstate_attrs[] = { NULL, }; -static struct attribute_group hstate_attr_group = { +static const struct attribute_group hstate_attr_group = { .attrs = hstate_attrs, }; static int hugetlb_sysfs_add_hstate(struct hstate *h, struct kobject *parent, struct kobject **hstate_kobjs, - struct attribute_group *hstate_attr_group) + const struct attribute_group *hstate_attr_group) { int retval; int hi = hstate_index(h); @@ -2633,7 +2638,7 @@ static struct attribute *per_node_hstate_attrs[] = { NULL, }; -static struct attribute_group per_node_hstate_attr_group = { +static const struct attribute_group per_node_hstate_attr_group = { .attrs = per_node_hstate_attrs, }; @@ -4600,6 +4605,15 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, return pte; } +/* + * huge_pte_offset() - Walk the page table to resolve the hugepage + * entry at address @addr + * + * Return: Pointer to page table or swap entry (PUD or PMD) for + * address @addr, or NULL if a p*d_none() entry is encountered and the + * size @sz doesn't match the hugepage size at this level of the page + * table. + */ pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr, unsigned long sz) { @@ -4614,13 +4628,22 @@ pte_t *huge_pte_offset(struct mm_struct *mm, p4d = p4d_offset(pgd, addr); if (!p4d_present(*p4d)) return NULL; + pud = pud_offset(p4d, addr); - if (!pud_present(*pud)) + if (sz != PUD_SIZE && pud_none(*pud)) return NULL; - if (pud_huge(*pud)) + /* hugepage or swap? */ + if (pud_huge(*pud) || !pud_present(*pud)) return (pte_t *)pud; + pmd = pmd_offset(pud, addr); - return (pte_t *) pmd; + if (sz != PMD_SIZE && pmd_none(*pmd)) + return NULL; + /* hugepage or swap? */ + if (pmd_huge(*pmd) || !pmd_present(*pmd)) + return (pte_t *)pmd; + + return NULL; } #endif /* CONFIG_ARCH_WANT_GENERAL_HUGETLB */ diff --git a/mm/internal.h b/mm/internal.h index 4ef49fc..1df011f 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -480,6 +480,17 @@ unsigned long reclaim_clean_pages_from_list(struct zone *zone, /* Mask to get the watermark bits */ #define ALLOC_WMARK_MASK (ALLOC_NO_WATERMARKS-1) +/* + * Only MMU archs have async oom victim reclaim - aka oom_reaper so we + * cannot assume a reduced access to memory reserves is sufficient for + * !MMU + */ +#ifdef CONFIG_MMU +#define ALLOC_OOM 0x08 +#else +#define ALLOC_OOM ALLOC_NO_WATERMARKS +#endif + #define ALLOC_HARDER 0x10 /* try to alloc harder */ #define ALLOC_HIGH 0x20 /* __GFP_HIGH set */ #define ALLOC_CPUSET 0x40 /* check for correct cpuset */ @@ -525,4 +536,5 @@ static inline bool is_migrate_highatomic_page(struct page *page) return get_pageblock_migratetype(page) == MIGRATE_HIGHATOMIC; } +void setup_zone_pageset(struct zone *zone); #endif /* __MM_INTERNAL_H */ @@ -3043,7 +3043,7 @@ static struct attribute *ksm_attrs[] = { NULL, }; -static struct attribute_group ksm_attr_group = { +static const struct attribute_group ksm_attr_group = { .attrs = ksm_attrs, .name = "ksm", }; diff --git a/mm/madvise.c b/mm/madvise.c index 4d7d1e5..eea1c73 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -80,6 +80,17 @@ static long madvise_behavior(struct vm_area_struct *vma, } new_flags &= ~VM_DONTCOPY; break; + case MADV_WIPEONFORK: + /* MADV_WIPEONFORK is only supported on anonymous memory. */ + if (vma->vm_file || vma->vm_flags & VM_SHARED) { + error = -EINVAL; + goto out; + } + new_flags |= VM_WIPEONFORK; + break; + case MADV_KEEPONFORK: + new_flags &= ~VM_WIPEONFORK; + break; case MADV_DONTDUMP: new_flags |= VM_DONTDUMP; break; @@ -696,6 +707,8 @@ madvise_behavior_valid(int behavior) #endif case MADV_DONTDUMP: case MADV_DODUMP: + case MADV_WIPEONFORK: + case MADV_KEEPONFORK: #ifdef CONFIG_MEMORY_FAILURE case MADV_SOFT_OFFLINE: case MADV_HWPOISON: diff --git a/mm/memcontrol.c b/mm/memcontrol.c index e09741a..ad15850 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -550,10 +550,12 @@ mem_cgroup_largest_soft_limit_node(struct mem_cgroup_tree_per_node *mctz) * value, and reading all cpu value can be performance bottleneck in some * common workload, threshold and synchronization as vmstat[] should be * implemented. + * + * The parameter idx can be of type enum memcg_event_item or vm_event_item. */ static unsigned long memcg_sum_events(struct mem_cgroup *memcg, - enum memcg_event_item event) + int event) { unsigned long val = 0; int cpu; @@ -1915,7 +1917,7 @@ retry: * bypass the last charges so that they can exit quickly and * free their memory. */ - if (unlikely(test_thread_flag(TIF_MEMDIE) || + if (unlikely(tsk_is_oom_victim(current) || fatal_signal_pending(current) || current->flags & PF_EXITING)) goto force; @@ -4319,6 +4321,8 @@ static void mem_cgroup_css_offline(struct cgroup_subsys_state *css) } spin_unlock(&memcg->event_list_lock); + memcg->low = 0; + memcg_offline_kmem(memcg); wb_memcg_offline(memcg); @@ -4635,8 +4639,11 @@ static enum mc_target_type get_mctgt_type(struct vm_area_struct *vma, if (!ret || !target) put_page(page); } - /* There is a swap entry and a page doesn't exist or isn't charged */ - if (ent.val && !ret && + /* + * There is a swap entry and a page doesn't exist or isn't charged. + * But we cannot move a tail-page in a THP. + */ + if (ent.val && !ret && (!page || !PageTransCompound(page)) && mem_cgroup_id(mc.from) == lookup_swap_cgroup_id(ent)) { ret = MC_TARGET_SWAP; if (target) @@ -4647,8 +4654,8 @@ static enum mc_target_type get_mctgt_type(struct vm_area_struct *vma, #ifdef CONFIG_TRANSPARENT_HUGEPAGE /* - * We don't consider swapping or file mapped pages because THP does not - * support them for now. + * We don't consider PMD mapped swapping or file mapped pages because THP does + * not support them for now. * Caller should make sure that pmd_trans_huge(pmd) is true. */ static enum mc_target_type get_mctgt_type_thp(struct vm_area_struct *vma, @@ -5423,7 +5430,7 @@ int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm, * in turn serializes uncharging. */ VM_BUG_ON_PAGE(!PageLocked(page), page); - if (page->mem_cgroup) + if (compound_head(page)->mem_cgroup) goto out; if (do_swap_account) { @@ -5906,6 +5913,7 @@ static struct mem_cgroup *mem_cgroup_id_get_online(struct mem_cgroup *memcg) void mem_cgroup_swapout(struct page *page, swp_entry_t entry) { struct mem_cgroup *memcg, *swap_memcg; + unsigned int nr_entries; unsigned short oldid; VM_BUG_ON_PAGE(PageLRU(page), page); @@ -5926,19 +5934,24 @@ void mem_cgroup_swapout(struct page *page, swp_entry_t entry) * ancestor for the swap instead and transfer the memory+swap charge. */ swap_memcg = mem_cgroup_id_get_online(memcg); - oldid = swap_cgroup_record(entry, mem_cgroup_id(swap_memcg), 1); + nr_entries = hpage_nr_pages(page); + /* Get references for the tail pages, too */ + if (nr_entries > 1) + mem_cgroup_id_get_many(swap_memcg, nr_entries - 1); + oldid = swap_cgroup_record(entry, mem_cgroup_id(swap_memcg), + nr_entries); VM_BUG_ON_PAGE(oldid, page); - mem_cgroup_swap_statistics(swap_memcg, 1); + mem_cgroup_swap_statistics(swap_memcg, nr_entries); page->mem_cgroup = NULL; if (!mem_cgroup_is_root(memcg)) - page_counter_uncharge(&memcg->memory, 1); + page_counter_uncharge(&memcg->memory, nr_entries); if (memcg != swap_memcg) { if (!mem_cgroup_is_root(swap_memcg)) - page_counter_charge(&swap_memcg->memsw, 1); - page_counter_uncharge(&memcg->memsw, 1); + page_counter_charge(&swap_memcg->memsw, nr_entries); + page_counter_uncharge(&memcg->memsw, nr_entries); } /* @@ -5948,7 +5961,8 @@ void mem_cgroup_swapout(struct page *page, swp_entry_t entry) * only synchronisation we have for udpating the per-CPU variables. */ VM_BUG_ON(!irqs_disabled()); - mem_cgroup_charge_statistics(memcg, page, false, -1); + mem_cgroup_charge_statistics(memcg, page, PageTransHuge(page), + -nr_entries); memcg_check_events(memcg, page); if (!mem_cgroup_is_root(memcg)) diff --git a/mm/memory.c b/mm/memory.c index 56e48e4..13ee83b 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1513,8 +1513,20 @@ void zap_page_range(struct vm_area_struct *vma, unsigned long start, tlb_gather_mmu(&tlb, mm, start, end); update_hiwater_rss(mm); mmu_notifier_invalidate_range_start(mm, start, end); - for ( ; vma && vma->vm_start < end; vma = vma->vm_next) + for ( ; vma && vma->vm_start < end; vma = vma->vm_next) { unmap_single_vma(&tlb, vma, start, end, NULL); + + /* + * zap_page_range does not specify whether mmap_sem should be + * held for read or write. That allows parallel zap_page_range + * operations to unmap a PTE and defer a flush meaning that + * this call observes pte_none and fails to flush the TLB. + * Rather than adding a complex API, ensure that no stale + * TLB entries exist when this call returns. + */ + flush_tlb_range(vma, start, end); + } + mmu_notifier_invalidate_range_end(mm, start, end); tlb_finish_mmu(&tlb, start, end); } @@ -1676,7 +1688,7 @@ int vm_insert_page(struct vm_area_struct *vma, unsigned long addr, EXPORT_SYMBOL(vm_insert_page); static int insert_pfn(struct vm_area_struct *vma, unsigned long addr, - pfn_t pfn, pgprot_t prot) + pfn_t pfn, pgprot_t prot, bool mkwrite) { struct mm_struct *mm = vma->vm_mm; int retval; @@ -1688,14 +1700,35 @@ static int insert_pfn(struct vm_area_struct *vma, unsigned long addr, if (!pte) goto out; retval = -EBUSY; - if (!pte_none(*pte)) - goto out_unlock; + if (!pte_none(*pte)) { + if (mkwrite) { + /* + * For read faults on private mappings the PFN passed + * in may not match the PFN we have mapped if the + * mapped PFN is a writeable COW page. In the mkwrite + * case we are creating a writable PTE for a shared + * mapping and we expect the PFNs to match. + */ + if (WARN_ON_ONCE(pte_pfn(*pte) != pfn_t_to_pfn(pfn))) + goto out_unlock; + entry = *pte; + goto out_mkwrite; + } else + goto out_unlock; + } /* Ok, finally just insert the thing.. */ if (pfn_t_devmap(pfn)) entry = pte_mkdevmap(pfn_t_pte(pfn, prot)); else entry = pte_mkspecial(pfn_t_pte(pfn, prot)); + +out_mkwrite: + if (mkwrite) { + entry = pte_mkyoung(entry); + entry = maybe_mkwrite(pte_mkdirty(entry), vma); + } + set_pte_at(mm, addr, pte, entry); update_mmu_cache(vma, addr, pte); /* XXX: why not for insert_page? */ @@ -1766,14 +1799,15 @@ int vm_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr, track_pfn_insert(vma, &pgprot, __pfn_to_pfn_t(pfn, PFN_DEV)); - ret = insert_pfn(vma, addr, __pfn_to_pfn_t(pfn, PFN_DEV), pgprot); + ret = insert_pfn(vma, addr, __pfn_to_pfn_t(pfn, PFN_DEV), pgprot, + false); return ret; } EXPORT_SYMBOL(vm_insert_pfn_prot); -int vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr, - pfn_t pfn) +static int __vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr, + pfn_t pfn, bool mkwrite) { pgprot_t pgprot = vma->vm_page_prot; @@ -1802,10 +1836,24 @@ int vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr, page = pfn_to_page(pfn_t_to_pfn(pfn)); return insert_page(vma, addr, page, pgprot); } - return insert_pfn(vma, addr, pfn, pgprot); + return insert_pfn(vma, addr, pfn, pgprot, mkwrite); +} + +int vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr, + pfn_t pfn) +{ + return __vm_insert_mixed(vma, addr, pfn, false); + } EXPORT_SYMBOL(vm_insert_mixed); +int vm_insert_mixed_mkwrite(struct vm_area_struct *vma, unsigned long addr, + pfn_t pfn) +{ + return __vm_insert_mixed(vma, addr, pfn, true); +} +EXPORT_SYMBOL(vm_insert_mixed_mkwrite); + /* * maps a range of physical memory into the requested pages. the old * mappings are removed. any references to nonexistent pages results @@ -2571,7 +2619,7 @@ static int do_wp_page(struct vm_fault *vmf) * not dirty accountable. */ if (PageAnon(vmf->page) && !PageKsm(vmf->page)) { - int total_mapcount; + int total_map_swapcount; if (!trylock_page(vmf->page)) { get_page(vmf->page); pte_unmap_unlock(vmf->pte, vmf->ptl); @@ -2586,8 +2634,8 @@ static int do_wp_page(struct vm_fault *vmf) } put_page(vmf->page); } - if (reuse_swap_page(vmf->page, &total_mapcount)) { - if (total_mapcount == 1) { + if (reuse_swap_page(vmf->page, &total_map_swapcount)) { + if (total_map_swapcount == 1) { /* * The page is all ours. Move it to * our anon_vma so the rmap code will @@ -2704,16 +2752,23 @@ EXPORT_SYMBOL(unmap_mapping_range); int do_swap_page(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; - struct page *page, *swapcache; + struct page *page = NULL, *swapcache; struct mem_cgroup *memcg; + struct vma_swap_readahead swap_ra; swp_entry_t entry; pte_t pte; int locked; int exclusive = 0; int ret = 0; + bool vma_readahead = swap_use_vma_readahead(); - if (!pte_unmap_same(vma->vm_mm, vmf->pmd, vmf->pte, vmf->orig_pte)) + if (vma_readahead) + page = swap_readahead_detect(vmf, &swap_ra); + if (!pte_unmap_same(vma->vm_mm, vmf->pmd, vmf->pte, vmf->orig_pte)) { + if (page) + put_page(page); goto out; + } entry = pte_to_swp_entry(vmf->orig_pte); if (unlikely(non_swap_entry(entry))) { @@ -2729,10 +2784,16 @@ int do_swap_page(struct vm_fault *vmf) goto out; } delayacct_set_flag(DELAYACCT_PF_SWAPIN); - page = lookup_swap_cache(entry); + if (!page) + page = lookup_swap_cache(entry, vma_readahead ? vma : NULL, + vmf->address); if (!page) { - page = swapin_readahead(entry, GFP_HIGHUSER_MOVABLE, vma, - vmf->address); + if (vma_readahead) + page = do_swap_page_readahead(entry, + GFP_HIGHUSER_MOVABLE, vmf, &swap_ra); + else + page = swapin_readahead(entry, + GFP_HIGHUSER_MOVABLE, vma, vmf->address); if (!page) { /* * Back out if somebody else faulted in this pte @@ -4356,19 +4417,53 @@ static void clear_gigantic_page(struct page *page, } } void clear_huge_page(struct page *page, - unsigned long addr, unsigned int pages_per_huge_page) + unsigned long addr_hint, unsigned int pages_per_huge_page) { - int i; + int i, n, base, l; + unsigned long addr = addr_hint & + ~(((unsigned long)pages_per_huge_page << PAGE_SHIFT) - 1); if (unlikely(pages_per_huge_page > MAX_ORDER_NR_PAGES)) { clear_gigantic_page(page, addr, pages_per_huge_page); return; } + /* Clear sub-page to access last to keep its cache lines hot */ might_sleep(); - for (i = 0; i < pages_per_huge_page; i++) { + n = (addr_hint - addr) / PAGE_SIZE; + if (2 * n <= pages_per_huge_page) { + /* If sub-page to access in first half of huge page */ + base = 0; + l = n; + /* Clear sub-pages at the end of huge page */ + for (i = pages_per_huge_page - 1; i >= 2 * n; i--) { + cond_resched(); + clear_user_highpage(page + i, addr + i * PAGE_SIZE); + } + } else { + /* If sub-page to access in second half of huge page */ + base = pages_per_huge_page - 2 * (pages_per_huge_page - n); + l = pages_per_huge_page - n; + /* Clear sub-pages at the begin of huge page */ + for (i = 0; i < base; i++) { + cond_resched(); + clear_user_highpage(page + i, addr + i * PAGE_SIZE); + } + } + /* + * Clear remaining sub-pages in left-right-left-right pattern + * towards the sub-page to access + */ + for (i = 0; i < l; i++) { + int left_idx = base + i; + int right_idx = base + 2 * l - 1 - i; + + cond_resched(); + clear_user_highpage(page + left_idx, + addr + left_idx * PAGE_SIZE); cond_resched(); - clear_user_highpage(page + i, addr + i * PAGE_SIZE); + clear_user_highpage(page + right_idx, + addr + right_idx * PAGE_SIZE); } } diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 8dccc31..73bf17d 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -773,31 +773,6 @@ static void node_states_set_node(int node, struct memory_notify *arg) node_set_state(node, N_MEMORY); } -bool allow_online_pfn_range(int nid, unsigned long pfn, unsigned long nr_pages, int online_type) -{ - struct pglist_data *pgdat = NODE_DATA(nid); - struct zone *movable_zone = &pgdat->node_zones[ZONE_MOVABLE]; - struct zone *default_zone = default_zone_for_pfn(nid, pfn, nr_pages); - - /* - * TODO there shouldn't be any inherent reason to have ZONE_NORMAL - * physically before ZONE_MOVABLE. All we need is they do not - * overlap. Historically we didn't allow ZONE_NORMAL after ZONE_MOVABLE - * though so let's stick with it for simplicity for now. - * TODO make sure we do not overlap with ZONE_DEVICE - */ - if (online_type == MMOP_ONLINE_KERNEL) { - if (zone_is_empty(movable_zone)) - return true; - return movable_zone->zone_start_pfn >= pfn + nr_pages; - } else if (online_type == MMOP_ONLINE_MOVABLE) { - return zone_end_pfn(default_zone) <= pfn; - } - - /* MMOP_ONLINE_KEEP will always succeed and inherits the current zone */ - return online_type == MMOP_ONLINE_KEEP; -} - static void __meminit resize_zone_range(struct zone *zone, unsigned long start_pfn, unsigned long nr_pages) { @@ -856,7 +831,7 @@ void __ref move_pfn_range_to_zone(struct zone *zone, * If no kernel zone covers this pfn range it will automatically go * to the ZONE_NORMAL. */ -struct zone *default_zone_for_pfn(int nid, unsigned long start_pfn, +static struct zone *default_kernel_zone_for_pfn(int nid, unsigned long start_pfn, unsigned long nr_pages) { struct pglist_data *pgdat = NODE_DATA(nid); @@ -872,17 +847,40 @@ struct zone *default_zone_for_pfn(int nid, unsigned long start_pfn, return &pgdat->node_zones[ZONE_NORMAL]; } -static inline bool movable_pfn_range(int nid, struct zone *default_zone, - unsigned long start_pfn, unsigned long nr_pages) +static inline struct zone *default_zone_for_pfn(int nid, unsigned long start_pfn, + unsigned long nr_pages) { - if (!allow_online_pfn_range(nid, start_pfn, nr_pages, - MMOP_ONLINE_KERNEL)) - return true; + struct zone *kernel_zone = default_kernel_zone_for_pfn(nid, start_pfn, + nr_pages); + struct zone *movable_zone = &NODE_DATA(nid)->node_zones[ZONE_MOVABLE]; + bool in_kernel = zone_intersects(kernel_zone, start_pfn, nr_pages); + bool in_movable = zone_intersects(movable_zone, start_pfn, nr_pages); - if (!movable_node_is_enabled()) - return false; + /* + * We inherit the existing zone in a simple case where zones do not + * overlap in the given range + */ + if (in_kernel ^ in_movable) + return (in_kernel) ? kernel_zone : movable_zone; - return !zone_intersects(default_zone, start_pfn, nr_pages); + /* + * If the range doesn't belong to any zone or two zones overlap in the + * given range then we use movable zone only if movable_node is + * enabled because we always online to a kernel zone by default. + */ + return movable_node_enabled ? movable_zone : kernel_zone; +} + +struct zone * zone_for_pfn_range(int online_type, int nid, unsigned start_pfn, + unsigned long nr_pages) +{ + if (online_type == MMOP_ONLINE_KERNEL) + return default_kernel_zone_for_pfn(nid, start_pfn, nr_pages); + + if (online_type == MMOP_ONLINE_MOVABLE) + return &NODE_DATA(nid)->node_zones[ZONE_MOVABLE]; + + return default_zone_for_pfn(nid, start_pfn, nr_pages); } /* @@ -892,28 +890,14 @@ static inline bool movable_pfn_range(int nid, struct zone *default_zone, static struct zone * __meminit move_pfn_range(int online_type, int nid, unsigned long start_pfn, unsigned long nr_pages) { - struct pglist_data *pgdat = NODE_DATA(nid); - struct zone *zone = default_zone_for_pfn(nid, start_pfn, nr_pages); - - if (online_type == MMOP_ONLINE_KEEP) { - struct zone *movable_zone = &pgdat->node_zones[ZONE_MOVABLE]; - /* - * MMOP_ONLINE_KEEP defaults to MMOP_ONLINE_KERNEL but use - * movable zone if that is not possible (e.g. we are within - * or past the existing movable zone). movable_node overrides - * this default and defaults to movable zone - */ - if (movable_pfn_range(nid, zone, start_pfn, nr_pages)) - zone = movable_zone; - } else if (online_type == MMOP_ONLINE_MOVABLE) { - zone = &pgdat->node_zones[ZONE_MOVABLE]; - } + struct zone *zone; + zone = zone_for_pfn_range(online_type, nid, start_pfn, nr_pages); move_pfn_range_to_zone(zone, start_pfn, nr_pages); return zone; } -/* Must be protected by mem_hotplug_begin() */ +/* Must be protected by mem_hotplug_begin() or a device_lock */ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, int online_type) { unsigned long flags; @@ -925,9 +909,6 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, int online_typ struct memory_notify arg; nid = pfn_to_nid(pfn); - if (!allow_online_pfn_range(nid, pfn, nr_pages, online_type)) - return -EINVAL; - /* associate pfn range with the zone */ zone = move_pfn_range(online_type, nid, pfn, nr_pages); @@ -945,10 +926,9 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, int online_typ * This means the page allocator ignores this zone. * So, zonelist must be updated after online. */ - mutex_lock(&zonelists_mutex); if (!populated_zone(zone)) { need_zonelists_rebuild = 1; - build_all_zonelists(NULL, zone); + setup_zone_pageset(zone); } ret = walk_system_ram_range(pfn, nr_pages, &onlined_pages, @@ -956,7 +936,6 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, int online_typ if (ret) { if (need_zonelists_rebuild) zone_pcp_reset(zone); - mutex_unlock(&zonelists_mutex); goto failed_addition; } @@ -969,13 +948,11 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, int online_typ if (onlined_pages) { node_states_set_node(nid, &arg); if (need_zonelists_rebuild) - build_all_zonelists(NULL, NULL); + build_all_zonelists(NULL); else zone_pcp_update(zone); } - mutex_unlock(&zonelists_mutex); - init_per_zone_wmark_min(); if (onlined_pages) { @@ -1046,9 +1023,7 @@ static pg_data_t __ref *hotadd_new_pgdat(int nid, u64 start) * The node we allocated has no zone fallback lists. For avoiding * to access not-initialized zonelist, build here. */ - mutex_lock(&zonelists_mutex); - build_all_zonelists(pgdat, NULL); - mutex_unlock(&zonelists_mutex); + build_all_zonelists(pgdat); /* * zone->managed_pages is set to an approximate value in @@ -1100,13 +1075,6 @@ int try_online_node(int nid) node_set_online(nid); ret = register_one_node(nid); BUG_ON(ret); - - if (pgdat->node_zonelists->_zonerefs->zone == NULL) { - mutex_lock(&zonelists_mutex); - build_all_zonelists(NULL, NULL); - mutex_unlock(&zonelists_mutex); - } - out: mem_hotplug_done(); return ret; @@ -1722,9 +1690,7 @@ repeat: if (!populated_zone(zone)) { zone_pcp_reset(zone); - mutex_lock(&zonelists_mutex); - build_all_zonelists(NULL, NULL); - mutex_unlock(&zonelists_mutex); + build_all_zonelists(NULL); } else zone_pcp_update(zone); @@ -1750,7 +1716,7 @@ failed_removal: return ret; } -/* Must be protected by mem_hotplug_begin() */ +/* Must be protected by mem_hotplug_begin() or a device_lock */ int offline_pages(unsigned long start_pfn, unsigned long nr_pages) { return __offline_pages(start_pfn, start_pfn + nr_pages, 120 * HZ); @@ -44,6 +44,7 @@ #include <linux/userfaultfd_k.h> #include <linux/moduleparam.h> #include <linux/pkeys.h> +#include <linux/oom.h> #include <linux/uaccess.h> #include <asm/cacheflush.h> @@ -2639,13 +2640,6 @@ int do_munmap(struct mm_struct *mm, unsigned long start, size_t len, if (vma->vm_start >= end) return 0; - if (uf) { - int error = userfaultfd_unmap_prep(vma, start, end, uf); - - if (error) - return error; - } - /* * If we need to split any vma, do it now to save pain later. * @@ -2679,6 +2673,21 @@ int do_munmap(struct mm_struct *mm, unsigned long start, size_t len, } vma = prev ? prev->vm_next : mm->mmap; + if (unlikely(uf)) { + /* + * If userfaultfd_unmap_prep returns an error the vmas + * will remain splitted, but userland will get a + * highly unexpected error anyway. This is no + * different than the case where the first of the two + * __split_vma fails, but we don't undo the first + * split, despite we could. This is unlikely enough + * failure that it's not worth optimizing it for. + */ + int error = userfaultfd_unmap_prep(vma, start, end, uf); + if (error) + return error; + } + /* * unlock any mlock()ed ranges before detaching vmas */ @@ -2993,6 +3002,23 @@ void exit_mmap(struct mm_struct *mm) /* Use -1 here to ensure all VMAs in the mm are unmapped */ unmap_vmas(&tlb, vma, 0, -1); + set_bit(MMF_OOM_SKIP, &mm->flags); + if (unlikely(tsk_is_oom_victim(current))) { + /* + * Wait for oom_reap_task() to stop working on this + * mm. Because MMF_OOM_SKIP is already set before + * calling down_read(), oom_reap_task() will not run + * on this "mm" post up_write(). + * + * tsk_is_oom_victim() cannot be set from under us + * either because current->mm is already set to NULL + * under task_lock before calling mmput and oom_mm is + * set not NULL by the OOM killer only if current->mm + * is found not NULL while holding the task_lock. + */ + down_write(&mm->mmap_sem); + up_write(&mm->mmap_sem); + } free_pgtables(&tlb, vma, FIRST_USER_ADDRESS, USER_PGTABLES_CEILING); tlb_finish_mmu(&tlb, 0, -1); @@ -3514,7 +3540,7 @@ static int init_user_reserve(void) { unsigned long free_kbytes; - free_kbytes = global_page_state(NR_FREE_PAGES) << (PAGE_SHIFT - 10); + free_kbytes = global_zone_page_state(NR_FREE_PAGES) << (PAGE_SHIFT - 10); sysctl_user_reserve_kbytes = min(free_kbytes / 32, 1UL << 17); return 0; @@ -3535,7 +3561,7 @@ static int init_admin_reserve(void) { unsigned long free_kbytes; - free_kbytes = global_page_state(NR_FREE_PAGES) << (PAGE_SHIFT - 10); + free_kbytes = global_zone_page_state(NR_FREE_PAGES) << (PAGE_SHIFT - 10); sysctl_admin_reserve_kbytes = min(free_kbytes / 32, 1UL << 13); return 0; @@ -3579,7 +3605,7 @@ static int reserve_mem_notifier(struct notifier_block *nb, break; case MEM_OFFLINE: - free_kbytes = global_page_state(NR_FREE_PAGES) << (PAGE_SHIFT - 10); + free_kbytes = global_zone_page_state(NR_FREE_PAGES) << (PAGE_SHIFT - 10); if (sysctl_user_reserve_kbytes > free_kbytes) { init_user_reserve(); diff --git a/mm/mremap.c b/mm/mremap.c index 3f23715..7395564 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -384,6 +384,19 @@ static struct vm_area_struct *vma_to_resize(unsigned long addr, if (!vma || vma->vm_start > addr) return ERR_PTR(-EFAULT); + /* + * !old_len is a special case where an attempt is made to 'duplicate' + * a mapping. This makes no sense for private mappings as it will + * instead create a fresh/new mapping unrelated to the original. This + * is contrary to the basic idea of mremap which creates new mappings + * based on the original. There are no known use cases for this + * behavior. As a result, fail such attempts. + */ + if (!old_len && !(vma->vm_flags & (VM_SHARED | VM_MAYSHARE))) { + pr_warn_once("%s (%d): attempted to duplicate a private mapping with mremap. This is not supported.\n", current->comm, current->pid); + return ERR_PTR(-EINVAL); + } + if (is_vm_hugetlb_page(vma)) return ERR_PTR(-EINVAL); @@ -1962,7 +1962,7 @@ static int __meminit init_user_reserve(void) { unsigned long free_kbytes; - free_kbytes = global_page_state(NR_FREE_PAGES) << (PAGE_SHIFT - 10); + free_kbytes = global_zone_page_state(NR_FREE_PAGES) << (PAGE_SHIFT - 10); sysctl_user_reserve_kbytes = min(free_kbytes / 32, 1UL << 17); return 0; @@ -1983,7 +1983,7 @@ static int __meminit init_admin_reserve(void) { unsigned long free_kbytes; - free_kbytes = global_page_state(NR_FREE_PAGES) << (PAGE_SHIFT - 10); + free_kbytes = global_zone_page_state(NR_FREE_PAGES) << (PAGE_SHIFT - 10); sysctl_admin_reserve_kbytes = min(free_kbytes / 32, 1UL << 13); return 0; diff --git a/mm/oom_kill.c b/mm/oom_kill.c index 9e8b4f0..99736e0 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -495,11 +495,12 @@ static bool __oom_reap_task_mm(struct task_struct *tsk, struct mm_struct *mm) } /* - * increase mm_users only after we know we will reap something so - * that the mmput_async is called only when we have reaped something - * and delayed __mmput doesn't matter that much + * MMF_OOM_SKIP is set by exit_mmap when the OOM reaper can't + * work on the mm anymore. The check for MMF_OOM_SKIP must run + * under mmap_sem for reading because it serializes against the + * down_write();up_write() cycle in exit_mmap(). */ - if (!mmget_not_zero(mm)) { + if (test_bit(MMF_OOM_SKIP, &mm->flags)) { up_read(&mm->mmap_sem); trace_skip_task_reaping(tsk->pid); goto unlock_oom; @@ -542,12 +543,6 @@ static bool __oom_reap_task_mm(struct task_struct *tsk, struct mm_struct *mm) K(get_mm_counter(mm, MM_SHMEMPAGES))); up_read(&mm->mmap_sem); - /* - * Drop our reference but make sure the mmput slow path is called from a - * different context because we shouldn't risk we get stuck there and - * put the oom_reaper out of the way. - */ - mmput_async(mm); trace_finish_task_reaping(tsk->pid); unlock_oom: mutex_unlock(&oom_lock); @@ -824,7 +819,8 @@ static void oom_kill_process(struct oom_control *oc, const char *message) /* * If the task is already exiting, don't alarm the sysadmin or kill - * its children or threads, just set TIF_MEMDIE so it can die quickly + * its children or threads, just give it access to memory reserves + * so it can die quickly */ task_lock(p); if (task_will_free_mem(p)) { @@ -889,9 +885,9 @@ static void oom_kill_process(struct oom_control *oc, const char *message) count_memcg_event_mm(mm, OOM_KILL); /* - * We should send SIGKILL before setting TIF_MEMDIE in order to prevent - * the OOM victim from depleting the memory reserves from the user - * space under its control. + * We should send SIGKILL before granting access to memory reserves + * in order to prevent the OOM victim from depleting the memory + * reserves from the user space under its control. */ do_send_sig_info(SIGKILL, SEND_SIG_FORCED, victim, true); mark_oom_victim(victim); diff --git a/mm/page-writeback.c b/mm/page-writeback.c index bf050ab..0b9c5cb 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -363,7 +363,7 @@ static unsigned long global_dirtyable_memory(void) { unsigned long x; - x = global_page_state(NR_FREE_PAGES); + x = global_zone_page_state(NR_FREE_PAGES); /* * Pages reserved for the kernel should not be considered * dirtyable, to prevent a situation where reclaim has to @@ -1405,7 +1405,7 @@ void wb_update_bandwidth(struct bdi_writeback *wb, unsigned long start_time) * will look to see if it needs to start dirty throttling. * * If dirty_poll_interval is too low, big NUMA machines will call the expensive - * global_page_state() too often. So scale it near-sqrt to the safety margin + * global_zone_page_state() too often. So scale it near-sqrt to the safety margin * (the number of pages we may dirty without exceeding the dirty limits). */ static unsigned long dirty_poll_interval(unsigned long dirty, diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 9327a94..a9add06 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -2951,7 +2951,7 @@ bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark, { long min = mark; int o; - const bool alloc_harder = (alloc_flags & ALLOC_HARDER); + const bool alloc_harder = (alloc_flags & (ALLOC_HARDER|ALLOC_OOM)); /* free_pages may go negative - that's OK */ free_pages -= (1 << order) - 1; @@ -2964,10 +2964,21 @@ bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark, * the high-atomic reserves. This will over-estimate the size of the * atomic reserve but it avoids a search. */ - if (likely(!alloc_harder)) + if (likely(!alloc_harder)) { free_pages -= z->nr_reserved_highatomic; - else - min -= min / 4; + } else { + /* + * OOM victims can try even harder than normal ALLOC_HARDER + * users on the grounds that it's definitely going to be in + * the exit path shortly and free memory. Any allocation it + * makes during the free path will be small and short-lived. + */ + if (alloc_flags & ALLOC_OOM) + min -= min / 2; + else + min -= min / 4; + } + #ifdef CONFIG_CMA /* If allocation can't use CMA areas don't use free CMA pages */ @@ -3205,7 +3216,7 @@ static void warn_alloc_show_mem(gfp_t gfp_mask, nodemask_t *nodemask) * of allowed nodes. */ if (!(gfp_mask & __GFP_NOMEMALLOC)) - if (test_thread_flag(TIF_MEMDIE) || + if (tsk_is_oom_victim(current) || (current->flags & (PF_MEMALLOC | PF_EXITING))) filter &= ~SHOW_MEM_FILTER_NODES; if (in_interrupt() || !(gfp_mask & __GFP_DIRECT_RECLAIM)) @@ -3668,21 +3679,46 @@ gfp_to_alloc_flags(gfp_t gfp_mask) return alloc_flags; } -bool gfp_pfmemalloc_allowed(gfp_t gfp_mask) +static bool oom_reserves_allowed(struct task_struct *tsk) { - if (unlikely(gfp_mask & __GFP_NOMEMALLOC)) + if (!tsk_is_oom_victim(tsk)) return false; + /* + * !MMU doesn't have oom reaper so give access to memory reserves + * only to the thread with TIF_MEMDIE set + */ + if (!IS_ENABLED(CONFIG_MMU) && !test_thread_flag(TIF_MEMDIE)) + return false; + + return true; +} + +/* + * Distinguish requests which really need access to full memory + * reserves from oom victims which can live with a portion of it + */ +static inline int __gfp_pfmemalloc_flags(gfp_t gfp_mask) +{ + if (unlikely(gfp_mask & __GFP_NOMEMALLOC)) + return 0; if (gfp_mask & __GFP_MEMALLOC) - return true; + return ALLOC_NO_WATERMARKS; if (in_serving_softirq() && (current->flags & PF_MEMALLOC)) - return true; - if (!in_interrupt() && - ((current->flags & PF_MEMALLOC) || - unlikely(test_thread_flag(TIF_MEMDIE)))) - return true; + return ALLOC_NO_WATERMARKS; + if (!in_interrupt()) { + if (current->flags & PF_MEMALLOC) + return ALLOC_NO_WATERMARKS; + else if (oom_reserves_allowed(current)) + return ALLOC_OOM; + } - return false; + return 0; +} + +bool gfp_pfmemalloc_allowed(gfp_t gfp_mask) +{ + return !!__gfp_pfmemalloc_flags(gfp_mask); } /* @@ -3835,6 +3871,7 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order, unsigned long alloc_start = jiffies; unsigned int stall_timeout = 10 * HZ; unsigned int cpuset_mems_cookie; + int reserve_flags; /* * In the slowpath, we sanity check order to avoid ever trying to @@ -3940,15 +3977,16 @@ retry: if (gfp_mask & __GFP_KSWAPD_RECLAIM) wake_all_kswapds(order, ac); - if (gfp_pfmemalloc_allowed(gfp_mask)) - alloc_flags = ALLOC_NO_WATERMARKS; + reserve_flags = __gfp_pfmemalloc_flags(gfp_mask); + if (reserve_flags) + alloc_flags = reserve_flags; /* * Reset the zonelist iterators if memory policies can be ignored. * These allocations are high priority and system rather than user * orientated. */ - if (!(alloc_flags & ALLOC_CPUSET) || (alloc_flags & ALLOC_NO_WATERMARKS)) { + if (!(alloc_flags & ALLOC_CPUSET) || reserve_flags) { ac->zonelist = node_zonelist(numa_node_id(), gfp_mask); ac->preferred_zoneref = first_zones_zonelist(ac->zonelist, ac->high_zoneidx, ac->nodemask); @@ -4025,8 +4063,8 @@ retry: goto got_pg; /* Avoid allocations with no watermarks from looping endlessly */ - if (test_thread_flag(TIF_MEMDIE) && - (alloc_flags == ALLOC_NO_WATERMARKS || + if (tsk_is_oom_victim(current) && + (alloc_flags == ALLOC_OOM || (gfp_mask & __GFP_NOMEMALLOC))) goto nopage; @@ -4509,7 +4547,7 @@ long si_mem_available(void) * Estimate the amount of memory available for userspace allocations, * without causing swapping. */ - available = global_page_state(NR_FREE_PAGES) - totalreserve_pages; + available = global_zone_page_state(NR_FREE_PAGES) - totalreserve_pages; /* * Not all the page cache can be freed, otherwise the system will @@ -4538,7 +4576,7 @@ void si_meminfo(struct sysinfo *val) { val->totalram = totalram_pages; val->sharedram = global_node_page_state(NR_SHMEM); - val->freeram = global_page_state(NR_FREE_PAGES); + val->freeram = global_zone_page_state(NR_FREE_PAGES); val->bufferram = nr_blockdev_pages(); val->totalhigh = totalhigh_pages; val->freehigh = nr_free_highpages(); @@ -4673,11 +4711,11 @@ void show_free_areas(unsigned int filter, nodemask_t *nodemask) global_node_page_state(NR_SLAB_UNRECLAIMABLE), global_node_page_state(NR_FILE_MAPPED), global_node_page_state(NR_SHMEM), - global_page_state(NR_PAGETABLE), - global_page_state(NR_BOUNCE), - global_page_state(NR_FREE_PAGES), + global_zone_page_state(NR_PAGETABLE), + global_zone_page_state(NR_BOUNCE), + global_zone_page_state(NR_FREE_PAGES), free_pcp, - global_page_state(NR_FREE_CMA_PAGES)); + global_zone_page_state(NR_FREE_CMA_PAGES)); for_each_online_pgdat(pgdat) { if (show_mem_node_skip(filter, pgdat->node_id, nodemask)) @@ -4839,18 +4877,17 @@ static void zoneref_set_zone(struct zone *zone, struct zoneref *zoneref) * * Add all populated zones of a node to the zonelist. */ -static int build_zonelists_node(pg_data_t *pgdat, struct zonelist *zonelist, - int nr_zones) +static int build_zonerefs_node(pg_data_t *pgdat, struct zoneref *zonerefs) { struct zone *zone; enum zone_type zone_type = MAX_NR_ZONES; + int nr_zones = 0; do { zone_type--; zone = pgdat->node_zones + zone_type; if (managed_zone(zone)) { - zoneref_set_zone(zone, - &zonelist->_zonerefs[nr_zones++]); + zoneref_set_zone(zone, &zonerefs[nr_zones++]); check_highest_zone(zone_type); } } while (zone_type); @@ -4858,52 +4895,18 @@ static int build_zonelists_node(pg_data_t *pgdat, struct zonelist *zonelist, return nr_zones; } - -/* - * zonelist_order: - * 0 = automatic detection of better ordering. - * 1 = order by ([node] distance, -zonetype) - * 2 = order by (-zonetype, [node] distance) - * - * If not NUMA, ZONELIST_ORDER_ZONE and ZONELIST_ORDER_NODE will create - * the same zonelist. So only NUMA can configure this param. - */ -#define ZONELIST_ORDER_DEFAULT 0 -#define ZONELIST_ORDER_NODE 1 -#define ZONELIST_ORDER_ZONE 2 - -/* zonelist order in the kernel. - * set_zonelist_order() will set this to NODE or ZONE. - */ -static int current_zonelist_order = ZONELIST_ORDER_DEFAULT; -static char zonelist_order_name[3][8] = {"Default", "Node", "Zone"}; - - #ifdef CONFIG_NUMA -/* The value user specified ....changed by config */ -static int user_zonelist_order = ZONELIST_ORDER_DEFAULT; -/* string for sysctl */ -#define NUMA_ZONELIST_ORDER_LEN 16 -char numa_zonelist_order[16] = "default"; - -/* - * interface for configure zonelist ordering. - * command line option "numa_zonelist_order" - * = "[dD]efault - default, automatic configuration. - * = "[nN]ode - order by node locality, then by zone within node - * = "[zZ]one - order by zone, then by locality within zone - */ static int __parse_numa_zonelist_order(char *s) { - if (*s == 'd' || *s == 'D') { - user_zonelist_order = ZONELIST_ORDER_DEFAULT; - } else if (*s == 'n' || *s == 'N') { - user_zonelist_order = ZONELIST_ORDER_NODE; - } else if (*s == 'z' || *s == 'Z') { - user_zonelist_order = ZONELIST_ORDER_ZONE; - } else { - pr_warn("Ignoring invalid numa_zonelist_order value: %s\n", s); + /* + * We used to support different zonlists modes but they turned + * out to be just not useful. Let's keep the warning in place + * if somebody still use the cmd line parameter so that we do + * not fail it silently + */ + if (!(*s == 'd' || *s == 'D' || *s == 'n' || *s == 'N')) { + pr_warn("Ignoring unsupported numa_zonelist_order value: %s\n", s); return -EINVAL; } return 0; @@ -4911,19 +4914,15 @@ static int __parse_numa_zonelist_order(char *s) static __init int setup_numa_zonelist_order(char *s) { - int ret; - if (!s) return 0; - ret = __parse_numa_zonelist_order(s); - if (ret == 0) - strlcpy(numa_zonelist_order, s, NUMA_ZONELIST_ORDER_LEN); - - return ret; + return __parse_numa_zonelist_order(s); } early_param("numa_zonelist_order", setup_numa_zonelist_order); +char numa_zonelist_order[] = "Node"; + /* * sysctl handler for numa_zonelist_order */ @@ -4931,42 +4930,17 @@ int numa_zonelist_order_handler(struct ctl_table *table, int write, void __user *buffer, size_t *length, loff_t *ppos) { - char saved_string[NUMA_ZONELIST_ORDER_LEN]; + char *str; int ret; - static DEFINE_MUTEX(zl_order_mutex); - mutex_lock(&zl_order_mutex); - if (write) { - if (strlen((char *)table->data) >= NUMA_ZONELIST_ORDER_LEN) { - ret = -EINVAL; - goto out; - } - strcpy(saved_string, (char *)table->data); - } - ret = proc_dostring(table, write, buffer, length, ppos); - if (ret) - goto out; - if (write) { - int oldval = user_zonelist_order; + if (!write) + return proc_dostring(table, write, buffer, length, ppos); + str = memdup_user_nul(buffer, 16); + if (IS_ERR(str)) + return PTR_ERR(str); - ret = __parse_numa_zonelist_order((char *)table->data); - if (ret) { - /* - * bogus value. restore saved string - */ - strncpy((char *)table->data, saved_string, - NUMA_ZONELIST_ORDER_LEN); - user_zonelist_order = oldval; - } else if (oldval != user_zonelist_order) { - mem_hotplug_begin(); - mutex_lock(&zonelists_mutex); - build_all_zonelists(NULL, NULL); - mutex_unlock(&zonelists_mutex); - mem_hotplug_done(); - } - } -out: - mutex_unlock(&zl_order_mutex); + ret = __parse_numa_zonelist_order(str); + kfree(str); return ret; } @@ -5040,17 +5014,24 @@ static int find_next_best_node(int node, nodemask_t *used_node_mask) * This results in maximum locality--normal zone overflows into local * DMA zone, if any--but risks exhausting DMA zone. */ -static void build_zonelists_in_node_order(pg_data_t *pgdat, int node) +static void build_zonelists_in_node_order(pg_data_t *pgdat, int *node_order, + unsigned nr_nodes) { - int j; - struct zonelist *zonelist; + struct zoneref *zonerefs; + int i; + + zonerefs = pgdat->node_zonelists[ZONELIST_FALLBACK]._zonerefs; + + for (i = 0; i < nr_nodes; i++) { + int nr_zones; - zonelist = &pgdat->node_zonelists[ZONELIST_FALLBACK]; - for (j = 0; zonelist->_zonerefs[j].zone != NULL; j++) - ; - j = build_zonelists_node(NODE_DATA(node), zonelist, j); - zonelist->_zonerefs[j].zone = NULL; - zonelist->_zonerefs[j].zone_idx = 0; + pg_data_t *node = NODE_DATA(node_order[i]); + + nr_zones = build_zonerefs_node(node, zonerefs); + zonerefs += nr_zones; + } + zonerefs->zone = NULL; + zonerefs->zone_idx = 0; } /* @@ -5058,13 +5039,14 @@ static void build_zonelists_in_node_order(pg_data_t *pgdat, int node) */ static void build_thisnode_zonelists(pg_data_t *pgdat) { - int j; - struct zonelist *zonelist; + struct zoneref *zonerefs; + int nr_zones; - zonelist = &pgdat->node_zonelists[ZONELIST_NOFALLBACK]; - j = build_zonelists_node(pgdat, zonelist, 0); - zonelist->_zonerefs[j].zone = NULL; - zonelist->_zonerefs[j].zone_idx = 0; + zonerefs = pgdat->node_zonelists[ZONELIST_NOFALLBACK]._zonerefs; + nr_zones = build_zonerefs_node(pgdat, zonerefs); + zonerefs += nr_zones; + zonerefs->zone = NULL; + zonerefs->zone_idx = 0; } /* @@ -5073,79 +5055,13 @@ static void build_thisnode_zonelists(pg_data_t *pgdat) * exhausted, but results in overflowing to remote node while memory * may still exist in local DMA zone. */ -static int node_order[MAX_NUMNODES]; - -static void build_zonelists_in_zone_order(pg_data_t *pgdat, int nr_nodes) -{ - int pos, j, node; - int zone_type; /* needs to be signed */ - struct zone *z; - struct zonelist *zonelist; - - zonelist = &pgdat->node_zonelists[ZONELIST_FALLBACK]; - pos = 0; - for (zone_type = MAX_NR_ZONES - 1; zone_type >= 0; zone_type--) { - for (j = 0; j < nr_nodes; j++) { - node = node_order[j]; - z = &NODE_DATA(node)->node_zones[zone_type]; - if (managed_zone(z)) { - zoneref_set_zone(z, - &zonelist->_zonerefs[pos++]); - check_highest_zone(zone_type); - } - } - } - zonelist->_zonerefs[pos].zone = NULL; - zonelist->_zonerefs[pos].zone_idx = 0; -} - -#if defined(CONFIG_64BIT) -/* - * Devices that require DMA32/DMA are relatively rare and do not justify a - * penalty to every machine in case the specialised case applies. Default - * to Node-ordering on 64-bit NUMA machines - */ -static int default_zonelist_order(void) -{ - return ZONELIST_ORDER_NODE; -} -#else -/* - * On 32-bit, the Normal zone needs to be preserved for allocations accessible - * by the kernel. If processes running on node 0 deplete the low memory zone - * then reclaim will occur more frequency increasing stalls and potentially - * be easier to OOM if a large percentage of the zone is under writeback or - * dirty. The problem is significantly worse if CONFIG_HIGHPTE is not set. - * Hence, default to zone ordering on 32-bit. - */ -static int default_zonelist_order(void) -{ - return ZONELIST_ORDER_ZONE; -} -#endif /* CONFIG_64BIT */ - -static void set_zonelist_order(void) -{ - if (user_zonelist_order == ZONELIST_ORDER_DEFAULT) - current_zonelist_order = default_zonelist_order(); - else - current_zonelist_order = user_zonelist_order; -} static void build_zonelists(pg_data_t *pgdat) { - int i, node, load; + static int node_order[MAX_NUMNODES]; + int node, load, nr_nodes = 0; nodemask_t used_mask; int local_node, prev_node; - struct zonelist *zonelist; - unsigned int order = current_zonelist_order; - - /* initialize zonelists */ - for (i = 0; i < MAX_ZONELISTS; i++) { - zonelist = pgdat->node_zonelists + i; - zonelist->_zonerefs[0].zone = NULL; - zonelist->_zonerefs[0].zone_idx = 0; - } /* NUMA-aware ordering of nodes */ local_node = pgdat->node_id; @@ -5154,8 +5070,6 @@ static void build_zonelists(pg_data_t *pgdat) nodes_clear(used_mask); memset(node_order, 0, sizeof(node_order)); - i = 0; - while ((node = find_next_best_node(local_node, &used_mask)) >= 0) { /* * We don't want to pressure a particular node. @@ -5166,19 +5080,12 @@ static void build_zonelists(pg_data_t *pgdat) node_distance(local_node, prev_node)) node_load[node] = load; + node_order[nr_nodes++] = node; prev_node = node; load--; - if (order == ZONELIST_ORDER_NODE) - build_zonelists_in_node_order(pgdat, node); - else - node_order[i++] = node; /* remember order */ - } - - if (order == ZONELIST_ORDER_ZONE) { - /* calculate node order -- i.e., DMA last! */ - build_zonelists_in_zone_order(pgdat, i); } + build_zonelists_in_node_order(pgdat, node_order, nr_nodes); build_thisnode_zonelists(pgdat); } @@ -5204,21 +5111,17 @@ static void setup_min_unmapped_ratio(void); static void setup_min_slab_ratio(void); #else /* CONFIG_NUMA */ -static void set_zonelist_order(void) -{ - current_zonelist_order = ZONELIST_ORDER_ZONE; -} - static void build_zonelists(pg_data_t *pgdat) { int node, local_node; - enum zone_type j; - struct zonelist *zonelist; + struct zoneref *zonerefs; + int nr_zones; local_node = pgdat->node_id; - zonelist = &pgdat->node_zonelists[ZONELIST_FALLBACK]; - j = build_zonelists_node(pgdat, zonelist, 0); + zonerefs = pgdat->node_zonelists[ZONELIST_FALLBACK]._zonerefs; + nr_zones = build_zonerefs_node(pgdat, zonerefs); + zonerefs += nr_zones; /* * Now we build the zonelist so that it contains the zones @@ -5231,16 +5134,18 @@ static void build_zonelists(pg_data_t *pgdat) for (node = local_node + 1; node < MAX_NUMNODES; node++) { if (!node_online(node)) continue; - j = build_zonelists_node(NODE_DATA(node), zonelist, j); + nr_zones = build_zonerefs_node(NODE_DATA(node), zonerefs); + zonerefs += nr_zones; } for (node = 0; node < local_node; node++) { if (!node_online(node)) continue; - j = build_zonelists_node(NODE_DATA(node), zonelist, j); + nr_zones = build_zonerefs_node(NODE_DATA(node), zonerefs); + zonerefs += nr_zones; } - zonelist->_zonerefs[j].zone = NULL; - zonelist->_zonerefs[j].zone_idx = 0; + zonerefs->zone = NULL; + zonerefs->zone_idx = 0; } #endif /* CONFIG_NUMA */ @@ -5263,50 +5168,32 @@ static void build_zonelists(pg_data_t *pgdat) static void setup_pageset(struct per_cpu_pageset *p, unsigned long batch); static DEFINE_PER_CPU(struct per_cpu_pageset, boot_pageset); static DEFINE_PER_CPU(struct per_cpu_nodestat, boot_nodestats); -static void setup_zone_pageset(struct zone *zone); - -/* - * Global mutex to protect against size modification of zonelists - * as well as to serialize pageset setup for the new populated zone. - */ -DEFINE_MUTEX(zonelists_mutex); -/* return values int ....just for stop_machine() */ -static int __build_all_zonelists(void *data) +static void __build_all_zonelists(void *data) { int nid; - int cpu; + int __maybe_unused cpu; pg_data_t *self = data; + static DEFINE_SPINLOCK(lock); + + spin_lock(&lock); #ifdef CONFIG_NUMA memset(node_load, 0, sizeof(node_load)); #endif + /* + * This node is hotadded and no memory is yet present. So just + * building zonelists is fine - no need to touch other nodes. + */ if (self && !node_online(self->node_id)) { build_zonelists(self); - } - - for_each_online_node(nid) { - pg_data_t *pgdat = NODE_DATA(nid); - - build_zonelists(pgdat); - } + } else { + for_each_online_node(nid) { + pg_data_t *pgdat = NODE_DATA(nid); - /* - * Initialize the boot_pagesets that are going to be used - * for bootstrapping processors. The real pagesets for - * each zone will be allocated later when the per cpu - * allocator is available. - * - * boot_pagesets are used also for bootstrapping offline - * cpus if the system is already booted because the pagesets - * are needed to initialize allocators on a specific cpu too. - * F.e. the percpu allocator needs the page allocator which - * needs the percpu allocator in order to allocate its pagesets - * (a chicken-egg dilemma). - */ - for_each_possible_cpu(cpu) { - setup_pageset(&per_cpu(boot_pageset, cpu), 0); + build_zonelists(pgdat); + } #ifdef CONFIG_HAVE_MEMORYLESS_NODES /* @@ -5317,45 +5204,53 @@ static int __build_all_zonelists(void *data) * secondary cpus' numa_mem as they come on-line. During * node/memory hotplug, we'll fixup all on-line cpus. */ - if (cpu_online(cpu)) + for_each_online_cpu(cpu) set_cpu_numa_mem(cpu, local_memory_node(cpu_to_node(cpu))); #endif } - return 0; + spin_unlock(&lock); } static noinline void __init build_all_zonelists_init(void) { + int cpu; + __build_all_zonelists(NULL); + + /* + * Initialize the boot_pagesets that are going to be used + * for bootstrapping processors. The real pagesets for + * each zone will be allocated later when the per cpu + * allocator is available. + * + * boot_pagesets are used also for bootstrapping offline + * cpus if the system is already booted because the pagesets + * are needed to initialize allocators on a specific cpu too. + * F.e. the percpu allocator needs the page allocator which + * needs the percpu allocator in order to allocate its pagesets + * (a chicken-egg dilemma). + */ + for_each_possible_cpu(cpu) + setup_pageset(&per_cpu(boot_pageset, cpu), 0); + mminit_verify_zonelist(); cpuset_init_current_mems_allowed(); } /* - * Called with zonelists_mutex held always * unless system_state == SYSTEM_BOOTING. * - * __ref due to (1) call of __meminit annotated setup_zone_pageset - * [we're only called with non-NULL zone through __meminit paths] and - * (2) call of __init annotated helper build_all_zonelists_init + * __ref due to call of __init annotated helper build_all_zonelists_init * [protected by SYSTEM_BOOTING]. */ -void __ref build_all_zonelists(pg_data_t *pgdat, struct zone *zone) +void __ref build_all_zonelists(pg_data_t *pgdat) { - set_zonelist_order(); - if (system_state == SYSTEM_BOOTING) { build_all_zonelists_init(); } else { -#ifdef CONFIG_MEMORY_HOTPLUG - if (zone) - setup_zone_pageset(zone); -#endif - /* we have to stop all cpus to guarantee there is no user - of zonelist */ - stop_machine_cpuslocked(__build_all_zonelists, pgdat, NULL); + __build_all_zonelists(pgdat); /* cpuset refresh routine should be here */ } vm_total_pages = nr_free_pagecache_pages(); @@ -5371,9 +5266,8 @@ void __ref build_all_zonelists(pg_data_t *pgdat, struct zone *zone) else page_group_by_mobility_disabled = 0; - pr_info("Built %i zonelists in %s order, mobility grouping %s. Total pages: %ld\n", + pr_info("Built %i zonelists, mobility grouping %s. Total pages: %ld\n", nr_online_nodes, - zonelist_order_name[current_zonelist_order], page_group_by_mobility_disabled ? "off" : "on", vm_total_pages); #ifdef CONFIG_NUMA @@ -5627,7 +5521,7 @@ static void __meminit zone_pageset_init(struct zone *zone, int cpu) pageset_set_high_and_batch(zone, pcp); } -static void __meminit setup_zone_pageset(struct zone *zone) +void __meminit setup_zone_pageset(struct zone *zone) { int cpu; zone->pageset = alloc_percpu(struct per_cpu_pageset); @@ -7081,9 +6975,11 @@ static void __setup_per_zone_wmarks(void) */ void setup_per_zone_wmarks(void) { - mutex_lock(&zonelists_mutex); + static DEFINE_SPINLOCK(lock); + + spin_lock(&lock); __setup_per_zone_wmarks(); - mutex_unlock(&zonelists_mutex); + spin_unlock(&lock); } /* diff --git a/mm/page_ext.c b/mm/page_ext.c index 88ccc044..32f1891 100644 --- a/mm/page_ext.c +++ b/mm/page_ext.c @@ -222,10 +222,7 @@ static void *__meminit alloc_page_ext(size_t size, int nid) return addr; } - if (node_state(nid, N_HIGH_MEMORY)) - addr = vzalloc_node(size, nid); - else - addr = vzalloc(size); + addr = vzalloc_node(size, nid); return addr; } @@ -409,6 +406,7 @@ void __init page_ext_init(void) continue; if (init_section_page_ext(pfn, nid)) goto oom; + cond_resched(); } } hotplug_memory_notifier(page_ext_callback, 0); diff --git a/mm/page_idle.c b/mm/page_idle.c index 1b0f48c..4bd03a8 100644 --- a/mm/page_idle.c +++ b/mm/page_idle.c @@ -204,7 +204,7 @@ static struct bin_attribute *page_idle_bin_attrs[] = { NULL, }; -static struct attribute_group page_idle_attr_group = { +static const struct attribute_group page_idle_attr_group = { .bin_attrs = page_idle_bin_attrs, .name = "page_idle", }; diff --git a/mm/page_io.c b/mm/page_io.c index 5f61b54..20139b9 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -28,16 +28,18 @@ static struct bio *get_swap_bio(gfp_t gfp_flags, struct page *page, bio_end_io_t end_io) { + int i, nr = hpage_nr_pages(page); struct bio *bio; - bio = bio_alloc(gfp_flags, 1); + bio = bio_alloc(gfp_flags, nr); if (bio) { bio->bi_iter.bi_sector = map_swap_page(page, &bio->bi_bdev); bio->bi_iter.bi_sector <<= PAGE_SHIFT - 9; bio->bi_end_io = end_io; - bio_add_page(bio, page, PAGE_SIZE, 0); - BUG_ON(bio->bi_iter.bi_size != PAGE_SIZE); + for (i = 0; i < nr; i++) + bio_add_page(bio, page + i, PAGE_SIZE, 0); + VM_BUG_ON(bio->bi_iter.bi_size != PAGE_SIZE * nr); } return bio; } @@ -262,6 +264,15 @@ static sector_t swap_page_sector(struct page *page) return (sector_t)__page_file_index(page) << (PAGE_SHIFT - 9); } +static inline void count_swpout_vm_event(struct page *page) +{ +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + if (unlikely(PageTransHuge(page))) + count_vm_event(THP_SWPOUT); +#endif + count_vm_events(PSWPOUT, hpage_nr_pages(page)); +} + int __swap_writepage(struct page *page, struct writeback_control *wbc, bio_end_io_t end_write_func) { @@ -313,7 +324,7 @@ int __swap_writepage(struct page *page, struct writeback_control *wbc, ret = bdev_write_page(sis->bdev, swap_page_sector(page), page, wbc); if (!ret) { - count_vm_event(PSWPOUT); + count_swpout_vm_event(page); return 0; } @@ -326,7 +337,7 @@ int __swap_writepage(struct page *page, struct writeback_control *wbc, goto out; } bio->bi_opf = REQ_OP_WRITE | wbc_to_write_flags(wbc); - count_vm_event(PSWPOUT); + count_swpout_vm_event(page); set_page_writeback(page); unlock_page(page); submit_bio(bio); diff --git a/mm/page_owner.c b/mm/page_owner.c index 0fd9dcf..8e2d713 100644 --- a/mm/page_owner.c +++ b/mm/page_owner.c @@ -30,6 +30,7 @@ DEFINE_STATIC_KEY_FALSE(page_owner_inited); static depot_stack_handle_t dummy_handle; static depot_stack_handle_t failure_handle; +static depot_stack_handle_t early_handle; static void init_early_allocated_pages(void); @@ -53,7 +54,7 @@ static bool need_page_owner(void) return true; } -static noinline void register_dummy_stack(void) +static __always_inline depot_stack_handle_t create_dummy_stack(void) { unsigned long entries[4]; struct stack_trace dummy; @@ -64,21 +65,22 @@ static noinline void register_dummy_stack(void) dummy.skip = 0; save_stack_trace(&dummy); - dummy_handle = depot_save_stack(&dummy, GFP_KERNEL); + return depot_save_stack(&dummy, GFP_KERNEL); } -static noinline void register_failure_stack(void) +static noinline void register_dummy_stack(void) { - unsigned long entries[4]; - struct stack_trace failure; + dummy_handle = create_dummy_stack(); +} - failure.nr_entries = 0; - failure.max_entries = ARRAY_SIZE(entries); - failure.entries = &entries[0]; - failure.skip = 0; +static noinline void register_failure_stack(void) +{ + failure_handle = create_dummy_stack(); +} - save_stack_trace(&failure); - failure_handle = depot_save_stack(&failure, GFP_KERNEL); +static noinline void register_early_stack(void) +{ + early_handle = create_dummy_stack(); } static void init_page_owner(void) @@ -88,6 +90,7 @@ static void init_page_owner(void) register_dummy_stack(); register_failure_stack(); + register_early_stack(); static_branch_enable(&page_owner_inited); init_early_allocated_pages(); } @@ -165,17 +168,13 @@ static noinline depot_stack_handle_t save_stack(gfp_t flags) return handle; } -noinline void __set_page_owner(struct page *page, unsigned int order, - gfp_t gfp_mask) +static inline void __set_page_owner_handle(struct page_ext *page_ext, + depot_stack_handle_t handle, unsigned int order, gfp_t gfp_mask) { - struct page_ext *page_ext = lookup_page_ext(page); struct page_owner *page_owner; - if (unlikely(!page_ext)) - return; - page_owner = get_page_owner(page_ext); - page_owner->handle = save_stack(gfp_mask); + page_owner->handle = handle; page_owner->order = order; page_owner->gfp_mask = gfp_mask; page_owner->last_migrate_reason = -1; @@ -183,6 +182,19 @@ noinline void __set_page_owner(struct page *page, unsigned int order, __set_bit(PAGE_EXT_OWNER, &page_ext->flags); } +noinline void __set_page_owner(struct page *page, unsigned int order, + gfp_t gfp_mask) +{ + struct page_ext *page_ext = lookup_page_ext(page); + depot_stack_handle_t handle; + + if (unlikely(!page_ext)) + return; + + handle = save_stack(gfp_mask); + __set_page_owner_handle(page_ext, handle, order, gfp_mask); +} + void __set_page_owner_migrate_reason(struct page *page, int reason) { struct page_ext *page_ext = lookup_page_ext(page); @@ -550,11 +562,17 @@ static void init_pages_in_zone(pg_data_t *pgdat, struct zone *zone) continue; /* - * We are safe to check buddy flag and order, because - * this is init stage and only single thread runs. + * To avoid having to grab zone->lock, be a little + * careful when reading buddy page order. The only + * danger is that we skip too much and potentially miss + * some early allocated pages, which is better than + * heavy lock contention. */ if (PageBuddy(page)) { - pfn += (1UL << page_order(page)) - 1; + unsigned long order = page_order_unsafe(page); + + if (order > 0 && order < MAX_ORDER) + pfn += (1UL << order) - 1; continue; } @@ -565,14 +583,15 @@ static void init_pages_in_zone(pg_data_t *pgdat, struct zone *zone) if (unlikely(!page_ext)) continue; - /* Maybe overraping zone */ + /* Maybe overlapping zone */ if (test_bit(PAGE_EXT_OWNER, &page_ext->flags)) continue; /* Found early allocated page */ - set_page_owner(page, 0, 0); + __set_page_owner_handle(page_ext, early_handle, 0, 0); count++; } + cond_resched(); } pr_info("Node %d, zone %8s: page owner found early allocated %lu pages\n", @@ -583,15 +602,12 @@ static void init_zones_in_node(pg_data_t *pgdat) { struct zone *zone; struct zone *node_zones = pgdat->node_zones; - unsigned long flags; for (zone = node_zones; zone - node_zones < MAX_NR_ZONES; ++zone) { if (!populated_zone(zone)) continue; - spin_lock_irqsave(&zone->lock, flags); init_pages_in_zone(pgdat, zone); - spin_unlock_irqrestore(&zone->lock, flags); } } diff --git a/mm/shmem.c b/mm/shmem.c index fbcb3c9..ace53a582b 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -34,6 +34,7 @@ #include <linux/swap.h> #include <linux/uio.h> #include <linux/khugepaged.h> +#include <linux/hugetlb.h> #include <asm/tlbflush.h> /* for arch/microblaze update_mmu_cache() */ @@ -188,6 +189,38 @@ static inline void shmem_unacct_blocks(unsigned long flags, long pages) vm_unacct_memory(pages * VM_ACCT(PAGE_SIZE)); } +static inline bool shmem_inode_acct_block(struct inode *inode, long pages) +{ + struct shmem_inode_info *info = SHMEM_I(inode); + struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb); + + if (shmem_acct_block(info->flags, pages)) + return false; + + if (sbinfo->max_blocks) { + if (percpu_counter_compare(&sbinfo->used_blocks, + sbinfo->max_blocks - pages) > 0) + goto unacct; + percpu_counter_add(&sbinfo->used_blocks, pages); + } + + return true; + +unacct: + shmem_unacct_blocks(info->flags, pages); + return false; +} + +static inline void shmem_inode_unacct_blocks(struct inode *inode, long pages) +{ + struct shmem_inode_info *info = SHMEM_I(inode); + struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb); + + if (sbinfo->max_blocks) + percpu_counter_sub(&sbinfo->used_blocks, pages); + shmem_unacct_blocks(info->flags, pages); +} + static const struct super_operations shmem_ops; static const struct address_space_operations shmem_aops; static const struct file_operations shmem_file_operations; @@ -249,23 +282,20 @@ static void shmem_recalc_inode(struct inode *inode) freed = info->alloced - info->swapped - inode->i_mapping->nrpages; if (freed > 0) { - struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb); - if (sbinfo->max_blocks) - percpu_counter_add(&sbinfo->used_blocks, -freed); info->alloced -= freed; inode->i_blocks -= freed * BLOCKS_PER_PAGE; - shmem_unacct_blocks(info->flags, freed); + shmem_inode_unacct_blocks(inode, freed); } } bool shmem_charge(struct inode *inode, long pages) { struct shmem_inode_info *info = SHMEM_I(inode); - struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb); unsigned long flags; - if (shmem_acct_block(info->flags, pages)) + if (!shmem_inode_acct_block(inode, pages)) return false; + spin_lock_irqsave(&info->lock, flags); info->alloced += pages; inode->i_blocks += pages * BLOCKS_PER_PAGE; @@ -273,26 +303,12 @@ bool shmem_charge(struct inode *inode, long pages) spin_unlock_irqrestore(&info->lock, flags); inode->i_mapping->nrpages += pages; - if (!sbinfo->max_blocks) - return true; - if (percpu_counter_compare(&sbinfo->used_blocks, - sbinfo->max_blocks - pages) > 0) { - inode->i_mapping->nrpages -= pages; - spin_lock_irqsave(&info->lock, flags); - info->alloced -= pages; - shmem_recalc_inode(inode); - spin_unlock_irqrestore(&info->lock, flags); - shmem_unacct_blocks(info->flags, pages); - return false; - } - percpu_counter_add(&sbinfo->used_blocks, pages); return true; } void shmem_uncharge(struct inode *inode, long pages) { struct shmem_inode_info *info = SHMEM_I(inode); - struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb); unsigned long flags; spin_lock_irqsave(&info->lock, flags); @@ -301,9 +317,7 @@ void shmem_uncharge(struct inode *inode, long pages) shmem_recalc_inode(inode); spin_unlock_irqrestore(&info->lock, flags); - if (sbinfo->max_blocks) - percpu_counter_sub(&sbinfo->used_blocks, pages); - shmem_unacct_blocks(info->flags, pages); + shmem_inode_unacct_blocks(inode, pages); } /* @@ -1452,9 +1466,10 @@ static struct page *shmem_alloc_page(gfp_t gfp, } static struct page *shmem_alloc_and_acct_page(gfp_t gfp, - struct shmem_inode_info *info, struct shmem_sb_info *sbinfo, + struct inode *inode, pgoff_t index, bool huge) { + struct shmem_inode_info *info = SHMEM_I(inode); struct page *page; int nr; int err = -ENOSPC; @@ -1463,14 +1478,8 @@ static struct page *shmem_alloc_and_acct_page(gfp_t gfp, huge = false; nr = huge ? HPAGE_PMD_NR : 1; - if (shmem_acct_block(info->flags, nr)) + if (!shmem_inode_acct_block(inode, nr)) goto failed; - if (sbinfo->max_blocks) { - if (percpu_counter_compare(&sbinfo->used_blocks, - sbinfo->max_blocks - nr) > 0) - goto unacct; - percpu_counter_add(&sbinfo->used_blocks, nr); - } if (huge) page = shmem_alloc_hugepage(gfp, info, index); @@ -1483,10 +1492,7 @@ static struct page *shmem_alloc_and_acct_page(gfp_t gfp, } err = -ENOMEM; - if (sbinfo->max_blocks) - percpu_counter_add(&sbinfo->used_blocks, -nr); -unacct: - shmem_unacct_blocks(info->flags, nr); + shmem_inode_unacct_blocks(inode, nr); failed: return ERR_PTR(err); } @@ -1644,7 +1650,7 @@ repeat: if (swap.val) { /* Look it up and read it in.. */ - page = lookup_swap_cache(swap); + page = lookup_swap_cache(swap, NULL, 0); if (!page) { /* Or update major stats only when swapin succeeds?? */ if (fault_type) { @@ -1751,10 +1757,9 @@ repeat: } alloc_huge: - page = shmem_alloc_and_acct_page(gfp, info, sbinfo, - index, true); + page = shmem_alloc_and_acct_page(gfp, inode, index, true); if (IS_ERR(page)) { -alloc_nohuge: page = shmem_alloc_and_acct_page(gfp, info, sbinfo, +alloc_nohuge: page = shmem_alloc_and_acct_page(gfp, inode, index, false); } if (IS_ERR(page)) { @@ -1876,10 +1881,7 @@ clear: * Error recovery. */ unacct: - if (sbinfo->max_blocks) - percpu_counter_sub(&sbinfo->used_blocks, - 1 << compound_order(page)); - shmem_unacct_blocks(info->flags, 1 << compound_order(page)); + shmem_inode_unacct_blocks(inode, 1 << compound_order(page)); if (PageTransHuge(page)) { unlock_page(page); @@ -2206,16 +2208,16 @@ bool shmem_mapping(struct address_space *mapping) return mapping->a_ops == &shmem_aops; } -int shmem_mcopy_atomic_pte(struct mm_struct *dst_mm, - pmd_t *dst_pmd, - struct vm_area_struct *dst_vma, - unsigned long dst_addr, - unsigned long src_addr, - struct page **pagep) +static int shmem_mfill_atomic_pte(struct mm_struct *dst_mm, + pmd_t *dst_pmd, + struct vm_area_struct *dst_vma, + unsigned long dst_addr, + unsigned long src_addr, + bool zeropage, + struct page **pagep) { struct inode *inode = file_inode(dst_vma->vm_file); struct shmem_inode_info *info = SHMEM_I(inode); - struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb); struct address_space *mapping = inode->i_mapping; gfp_t gfp = mapping_gfp_mask(mapping); pgoff_t pgoff = linear_page_index(dst_vma, dst_addr); @@ -2227,33 +2229,30 @@ int shmem_mcopy_atomic_pte(struct mm_struct *dst_mm, int ret; ret = -ENOMEM; - if (shmem_acct_block(info->flags, 1)) + if (!shmem_inode_acct_block(inode, 1)) goto out; - if (sbinfo->max_blocks) { - if (percpu_counter_compare(&sbinfo->used_blocks, - sbinfo->max_blocks) >= 0) - goto out_unacct_blocks; - percpu_counter_inc(&sbinfo->used_blocks); - } if (!*pagep) { page = shmem_alloc_page(gfp, info, pgoff); if (!page) - goto out_dec_used_blocks; - - page_kaddr = kmap_atomic(page); - ret = copy_from_user(page_kaddr, (const void __user *)src_addr, - PAGE_SIZE); - kunmap_atomic(page_kaddr); - - /* fallback to copy_from_user outside mmap_sem */ - if (unlikely(ret)) { - *pagep = page; - if (sbinfo->max_blocks) - percpu_counter_add(&sbinfo->used_blocks, -1); - shmem_unacct_blocks(info->flags, 1); - /* don't free the page */ - return -EFAULT; + goto out_unacct_blocks; + + if (!zeropage) { /* mcopy_atomic */ + page_kaddr = kmap_atomic(page); + ret = copy_from_user(page_kaddr, + (const void __user *)src_addr, + PAGE_SIZE); + kunmap_atomic(page_kaddr); + + /* fallback to copy_from_user outside mmap_sem */ + if (unlikely(ret)) { + *pagep = page; + shmem_inode_unacct_blocks(inode, 1); + /* don't free the page */ + return -EFAULT; + } + } else { /* mfill_zeropage_atomic */ + clear_highpage(page); } } else { page = *pagep; @@ -2314,14 +2313,33 @@ out_release_uncharge: out_release: unlock_page(page); put_page(page); -out_dec_used_blocks: - if (sbinfo->max_blocks) - percpu_counter_add(&sbinfo->used_blocks, -1); out_unacct_blocks: - shmem_unacct_blocks(info->flags, 1); + shmem_inode_unacct_blocks(inode, 1); goto out; } +int shmem_mcopy_atomic_pte(struct mm_struct *dst_mm, + pmd_t *dst_pmd, + struct vm_area_struct *dst_vma, + unsigned long dst_addr, + unsigned long src_addr, + struct page **pagep) +{ + return shmem_mfill_atomic_pte(dst_mm, dst_pmd, dst_vma, + dst_addr, src_addr, false, pagep); +} + +int shmem_mfill_zeropage_pte(struct mm_struct *dst_mm, + pmd_t *dst_pmd, + struct vm_area_struct *dst_vma, + unsigned long dst_addr) +{ + struct page *page = NULL; + + return shmem_mfill_atomic_pte(dst_mm, dst_pmd, dst_vma, + dst_addr, 0, true, &page); +} + #ifdef CONFIG_TMPFS static const struct inode_operations shmem_symlink_inode_operations; static const struct inode_operations shmem_short_symlink_operations; @@ -3635,7 +3653,7 @@ static int shmem_show_options(struct seq_file *seq, struct dentry *root) #define MFD_NAME_PREFIX_LEN (sizeof(MFD_NAME_PREFIX) - 1) #define MFD_NAME_MAX_LEN (NAME_MAX - MFD_NAME_PREFIX_LEN) -#define MFD_ALL_FLAGS (MFD_CLOEXEC | MFD_ALLOW_SEALING) +#define MFD_ALL_FLAGS (MFD_CLOEXEC | MFD_ALLOW_SEALING | MFD_HUGETLB) SYSCALL_DEFINE2(memfd_create, const char __user *, uname, @@ -3647,8 +3665,18 @@ SYSCALL_DEFINE2(memfd_create, char *name; long len; - if (flags & ~(unsigned int)MFD_ALL_FLAGS) - return -EINVAL; + if (!(flags & MFD_HUGETLB)) { + if (flags & ~(unsigned int)MFD_ALL_FLAGS) + return -EINVAL; + } else { + /* Sealing not supported in hugetlbfs (MFD_HUGETLB) */ + if (flags & MFD_ALLOW_SEALING) + return -EINVAL; + /* Allow huge page size encoding in flags. */ + if (flags & ~(unsigned int)(MFD_ALL_FLAGS | + (MFD_HUGE_MASK << MFD_HUGE_SHIFT))) + return -EINVAL; + } /* length includes terminating zero */ len = strnlen_user(uname, MFD_NAME_MAX_LEN + 1); @@ -3679,16 +3707,30 @@ SYSCALL_DEFINE2(memfd_create, goto err_name; } - file = shmem_file_setup(name, 0, VM_NORESERVE); + if (flags & MFD_HUGETLB) { + struct user_struct *user = NULL; + + file = hugetlb_file_setup(name, 0, VM_NORESERVE, &user, + HUGETLB_ANONHUGE_INODE, + (flags >> MFD_HUGE_SHIFT) & + MFD_HUGE_MASK); + } else + file = shmem_file_setup(name, 0, VM_NORESERVE); if (IS_ERR(file)) { error = PTR_ERR(file); goto err_fd; } - info = SHMEM_I(file_inode(file)); file->f_mode |= FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE; file->f_flags |= O_RDWR | O_LARGEFILE; - if (flags & MFD_ALLOW_SEALING) + + if (flags & MFD_ALLOW_SEALING) { + /* + * flags check at beginning of function ensures + * this is not a hugetlbfs (MFD_HUGETLB) file. + */ + info = SHMEM_I(file_inode(file)); info->seals &= ~F_SEAL_SEAL; + } fd_install(fd, file); kfree(name); @@ -34,6 +34,7 @@ #include <linux/stacktrace.h> #include <linux/prefetch.h> #include <linux/memcontrol.h> +#include <linux/random.h> #include <trace/events/kmem.h> @@ -238,30 +239,62 @@ static inline void stat(const struct kmem_cache *s, enum stat_item si) * Core slab cache functions *******************************************************************/ +/* + * Returns freelist pointer (ptr). With hardening, this is obfuscated + * with an XOR of the address where the pointer is held and a per-cache + * random number. + */ +static inline void *freelist_ptr(const struct kmem_cache *s, void *ptr, + unsigned long ptr_addr) +{ +#ifdef CONFIG_SLAB_FREELIST_HARDENED + return (void *)((unsigned long)ptr ^ s->random ^ ptr_addr); +#else + return ptr; +#endif +} + +/* Returns the freelist pointer recorded at location ptr_addr. */ +static inline void *freelist_dereference(const struct kmem_cache *s, + void *ptr_addr) +{ + return freelist_ptr(s, (void *)*(unsigned long *)(ptr_addr), + (unsigned long)ptr_addr); +} + static inline void *get_freepointer(struct kmem_cache *s, void *object) { - return *(void **)(object + s->offset); + return freelist_dereference(s, object + s->offset); } static void prefetch_freepointer(const struct kmem_cache *s, void *object) { - prefetch(object + s->offset); + if (object) + prefetch(freelist_dereference(s, object + s->offset)); } static inline void *get_freepointer_safe(struct kmem_cache *s, void *object) { + unsigned long freepointer_addr; void *p; if (!debug_pagealloc_enabled()) return get_freepointer(s, object); - probe_kernel_read(&p, (void **)(object + s->offset), sizeof(p)); - return p; + freepointer_addr = (unsigned long)object + s->offset; + probe_kernel_read(&p, (void **)freepointer_addr, sizeof(p)); + return freelist_ptr(s, p, freepointer_addr); } static inline void set_freepointer(struct kmem_cache *s, void *object, void *fp) { - *(void **)(object + s->offset) = fp; + unsigned long freeptr_addr = (unsigned long)object + s->offset; + +#ifdef CONFIG_SLAB_FREELIST_HARDENED + BUG_ON(object == fp); /* naive detection of double free or corruption */ +#endif + + *(void **)freeptr_addr = freelist_ptr(s, fp, freeptr_addr); } /* Loop over all objects in a slab */ @@ -3358,8 +3391,8 @@ static void free_kmem_cache_nodes(struct kmem_cache *s) struct kmem_cache_node *n; for_each_kmem_cache_node(s, node, n) { - kmem_cache_free(kmem_cache_node, n); s->node[node] = NULL; + kmem_cache_free(kmem_cache_node, n); } } @@ -3389,8 +3422,8 @@ static int init_kmem_cache_nodes(struct kmem_cache *s) return 0; } - s->node[node] = n; init_kmem_cache_node(n); + s->node[node] = n; } return 1; } @@ -3563,6 +3596,9 @@ static int kmem_cache_open(struct kmem_cache *s, unsigned long flags) { s->flags = kmem_cache_flags(s->size, flags, s->name, s->ctor); s->reserved = 0; +#ifdef CONFIG_SLAB_FREELIST_HARDENED + s->random = get_random_long(); +#endif if (need_reserve_slab_rcu && (s->flags & SLAB_TYPESAFE_BY_RCU)) s->reserved = sizeof(struct rcu_head); @@ -5423,7 +5459,7 @@ static struct attribute *slab_attrs[] = { NULL }; -static struct attribute_group slab_attr_group = { +static const struct attribute_group slab_attr_group = { .attrs = slab_attrs, }; diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c index c50b1a1..d1a39b8 100644 --- a/mm/sparse-vmemmap.c +++ b/mm/sparse-vmemmap.c @@ -54,14 +54,9 @@ void * __meminit vmemmap_alloc_block(unsigned long size, int node) if (slab_is_available()) { struct page *page; - if (node_state(node, N_HIGH_MEMORY)) - page = alloc_pages_node( - node, GFP_KERNEL | __GFP_ZERO | __GFP_RETRY_MAYFAIL, - get_order(size)); - else - page = alloc_pages( - GFP_KERNEL | __GFP_ZERO | __GFP_RETRY_MAYFAIL, - get_order(size)); + page = alloc_pages_node(node, + GFP_KERNEL | __GFP_ZERO | __GFP_RETRY_MAYFAIL, + get_order(size)); if (page) return page_address(page); return NULL; diff --git a/mm/sparse.c b/mm/sparse.c index 7b4be3f..a9783ac 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -65,14 +65,10 @@ static noinline struct mem_section __ref *sparse_index_alloc(int nid) unsigned long array_size = SECTIONS_PER_ROOT * sizeof(struct mem_section); - if (slab_is_available()) { - if (node_state(nid, N_HIGH_MEMORY)) - section = kzalloc_node(array_size, GFP_KERNEL, nid); - else - section = kzalloc(array_size, GFP_KERNEL); - } else { + if (slab_is_available()) + section = kzalloc_node(array_size, GFP_KERNEL, nid); + else section = memblock_virt_alloc_node(array_size, nid); - } return section; } @@ -946,28 +946,34 @@ void pagevec_remove_exceptionals(struct pagevec *pvec) } /** - * pagevec_lookup - gang pagecache lookup + * pagevec_lookup_range - gang pagecache lookup * @pvec: Where the resulting pages are placed * @mapping: The address_space to search * @start: The starting page index + * @end: The final page index * @nr_pages: The maximum number of pages * - * pagevec_lookup() will search for and return a group of up to @nr_pages pages - * in the mapping. The pages are placed in @pvec. pagevec_lookup() takes a + * pagevec_lookup_range() will search for and return a group of up to @nr_pages + * pages in the mapping starting from index @start and upto index @end + * (inclusive). The pages are placed in @pvec. pagevec_lookup() takes a * reference against the pages in @pvec. * * The search returns a group of mapping-contiguous pages with ascending - * indexes. There may be holes in the indices due to not-present pages. + * indexes. There may be holes in the indices due to not-present pages. We + * also update @start to index the next page for the traversal. * - * pagevec_lookup() returns the number of pages which were found. + * pagevec_lookup_range() returns the number of pages which were found. If this + * number is smaller than @nr_pages, the end of specified range has been + * reached. */ -unsigned pagevec_lookup(struct pagevec *pvec, struct address_space *mapping, - pgoff_t start, unsigned nr_pages) +unsigned pagevec_lookup_range(struct pagevec *pvec, + struct address_space *mapping, pgoff_t *start, pgoff_t end) { - pvec->nr = find_get_pages(mapping, start, nr_pages, pvec->pages); + pvec->nr = find_get_pages_range(mapping, start, end, PAGEVEC_SIZE, + pvec->pages); return pagevec_count(pvec); } -EXPORT_SYMBOL(pagevec_lookup); +EXPORT_SYMBOL(pagevec_lookup_range); unsigned pagevec_lookup_tag(struct pagevec *pvec, struct address_space *mapping, pgoff_t *index, int tag, unsigned nr_pages) diff --git a/mm/swap_state.c b/mm/swap_state.c index b68c930..71ce2d1 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -37,6 +37,29 @@ static const struct address_space_operations swap_aops = { struct address_space *swapper_spaces[MAX_SWAPFILES]; static unsigned int nr_swapper_spaces[MAX_SWAPFILES]; +bool swap_vma_readahead = true; + +#define SWAP_RA_MAX_ORDER_DEFAULT 3 + +static int swap_ra_max_order = SWAP_RA_MAX_ORDER_DEFAULT; + +#define SWAP_RA_WIN_SHIFT (PAGE_SHIFT / 2) +#define SWAP_RA_HITS_MASK ((1UL << SWAP_RA_WIN_SHIFT) - 1) +#define SWAP_RA_HITS_MAX SWAP_RA_HITS_MASK +#define SWAP_RA_WIN_MASK (~PAGE_MASK & ~SWAP_RA_HITS_MASK) + +#define SWAP_RA_HITS(v) ((v) & SWAP_RA_HITS_MASK) +#define SWAP_RA_WIN(v) (((v) & SWAP_RA_WIN_MASK) >> SWAP_RA_WIN_SHIFT) +#define SWAP_RA_ADDR(v) ((v) & PAGE_MASK) + +#define SWAP_RA_VAL(addr, win, hits) \ + (((addr) & PAGE_MASK) | \ + (((win) << SWAP_RA_WIN_SHIFT) & SWAP_RA_WIN_MASK) | \ + ((hits) & SWAP_RA_HITS_MASK)) + +/* Initial readahead hits is 4 to start up with a small window */ +#define GET_SWAP_RA_VAL(vma) \ + (atomic_long_read(&(vma)->swap_readahead_info) ? : 4) #define INC_CACHE_INFO(x) do { swap_cache_info.x++; } while (0) #define ADD_CACHE_INFO(x, nr) do { swap_cache_info.x += (nr); } while (0) @@ -297,19 +320,36 @@ void free_pages_and_swap_cache(struct page **pages, int nr) * lock getting page table operations atomic even if we drop the page * lock before returning. */ -struct page * lookup_swap_cache(swp_entry_t entry) +struct page *lookup_swap_cache(swp_entry_t entry, struct vm_area_struct *vma, + unsigned long addr) { struct page *page; + unsigned long ra_info; + int win, hits, readahead; page = find_get_page(swap_address_space(entry), swp_offset(entry)); - if (page && likely(!PageTransCompound(page))) { + INC_CACHE_INFO(find_total); + if (page) { INC_CACHE_INFO(find_success); - if (TestClearPageReadahead(page)) - atomic_inc(&swapin_readahead_hits); + if (unlikely(PageTransCompound(page))) + return page; + readahead = TestClearPageReadahead(page); + if (vma) { + ra_info = GET_SWAP_RA_VAL(vma); + win = SWAP_RA_WIN(ra_info); + hits = SWAP_RA_HITS(ra_info); + if (readahead) + hits = min_t(int, hits + 1, SWAP_RA_HITS_MAX); + atomic_long_set(&vma->swap_readahead_info, + SWAP_RA_VAL(addr, win, hits)); + } + if (readahead) { + count_vm_event(SWAP_RA_HIT); + if (!vma) + atomic_inc(&swapin_readahead_hits); + } } - - INC_CACHE_INFO(find_total); return page; } @@ -424,22 +464,20 @@ struct page *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask, return retpage; } -static unsigned long swapin_nr_pages(unsigned long offset) +static unsigned int __swapin_nr_pages(unsigned long prev_offset, + unsigned long offset, + int hits, + int max_pages, + int prev_win) { - static unsigned long prev_offset; - unsigned int pages, max_pages, last_ra; - static atomic_t last_readahead_pages; - - max_pages = 1 << READ_ONCE(page_cluster); - if (max_pages <= 1) - return 1; + unsigned int pages, last_ra; /* * This heuristic has been found to work well on both sequential and * random loads, swapping to hard disk or to SSD: please don't ask * what the "+ 2" means, it just happens to work well, that's all. */ - pages = atomic_xchg(&swapin_readahead_hits, 0) + 2; + pages = hits + 2; if (pages == 2) { /* * We can have no readahead hits to judge by: but must not get @@ -448,7 +486,6 @@ static unsigned long swapin_nr_pages(unsigned long offset) */ if (offset != prev_offset + 1 && offset != prev_offset - 1) pages = 1; - prev_offset = offset; } else { unsigned int roundup = 4; while (roundup < pages) @@ -460,9 +497,28 @@ static unsigned long swapin_nr_pages(unsigned long offset) pages = max_pages; /* Don't shrink readahead too fast */ - last_ra = atomic_read(&last_readahead_pages) / 2; + last_ra = prev_win / 2; if (pages < last_ra) pages = last_ra; + + return pages; +} + +static unsigned long swapin_nr_pages(unsigned long offset) +{ + static unsigned long prev_offset; + unsigned int hits, pages, max_pages; + static atomic_t last_readahead_pages; + + max_pages = 1 << READ_ONCE(page_cluster); + if (max_pages <= 1) + return 1; + + hits = atomic_xchg(&swapin_readahead_hits, 0); + pages = __swapin_nr_pages(prev_offset, offset, hits, max_pages, + atomic_read(&last_readahead_pages)); + if (!hits) + prev_offset = offset; atomic_set(&last_readahead_pages, pages); return pages; @@ -496,7 +552,7 @@ struct page *swapin_readahead(swp_entry_t entry, gfp_t gfp_mask, unsigned long start_offset, end_offset; unsigned long mask; struct blk_plug plug; - bool do_poll = true; + bool do_poll = true, page_allocated; mask = swapin_nr_pages(offset) - 1; if (!mask) @@ -512,12 +568,19 @@ struct page *swapin_readahead(swp_entry_t entry, gfp_t gfp_mask, blk_start_plug(&plug); for (offset = start_offset; offset <= end_offset ; offset++) { /* Ok, do the async read-ahead now */ - page = read_swap_cache_async(swp_entry(swp_type(entry), offset), - gfp_mask, vma, addr, false); + page = __read_swap_cache_async( + swp_entry(swp_type(entry), offset), + gfp_mask, vma, addr, &page_allocated); if (!page) continue; - if (offset != entry_offset && likely(!PageTransCompound(page))) - SetPageReadahead(page); + if (page_allocated) { + swap_readpage(page, false); + if (offset != entry_offset && + likely(!PageTransCompound(page))) { + SetPageReadahead(page); + count_vm_event(SWAP_RA); + } + } put_page(page); } blk_finish_plug(&plug); @@ -561,3 +624,210 @@ void exit_swap_address_space(unsigned int type) synchronize_rcu(); kvfree(spaces); } + +static inline void swap_ra_clamp_pfn(struct vm_area_struct *vma, + unsigned long faddr, + unsigned long lpfn, + unsigned long rpfn, + unsigned long *start, + unsigned long *end) +{ + *start = max3(lpfn, PFN_DOWN(vma->vm_start), + PFN_DOWN(faddr & PMD_MASK)); + *end = min3(rpfn, PFN_DOWN(vma->vm_end), + PFN_DOWN((faddr & PMD_MASK) + PMD_SIZE)); +} + +struct page *swap_readahead_detect(struct vm_fault *vmf, + struct vma_swap_readahead *swap_ra) +{ + struct vm_area_struct *vma = vmf->vma; + unsigned long swap_ra_info; + struct page *page; + swp_entry_t entry; + unsigned long faddr, pfn, fpfn; + unsigned long start, end; + pte_t *pte; + unsigned int max_win, hits, prev_win, win, left; +#ifndef CONFIG_64BIT + pte_t *tpte; +#endif + + faddr = vmf->address; + entry = pte_to_swp_entry(vmf->orig_pte); + if ((unlikely(non_swap_entry(entry)))) + return NULL; + page = lookup_swap_cache(entry, vma, faddr); + if (page) + return page; + + max_win = 1 << READ_ONCE(swap_ra_max_order); + if (max_win == 1) { + swap_ra->win = 1; + return NULL; + } + + fpfn = PFN_DOWN(faddr); + swap_ra_info = GET_SWAP_RA_VAL(vma); + pfn = PFN_DOWN(SWAP_RA_ADDR(swap_ra_info)); + prev_win = SWAP_RA_WIN(swap_ra_info); + hits = SWAP_RA_HITS(swap_ra_info); + swap_ra->win = win = __swapin_nr_pages(pfn, fpfn, hits, + max_win, prev_win); + atomic_long_set(&vma->swap_readahead_info, + SWAP_RA_VAL(faddr, win, 0)); + + if (win == 1) + return NULL; + + /* Copy the PTEs because the page table may be unmapped */ + if (fpfn == pfn + 1) + swap_ra_clamp_pfn(vma, faddr, fpfn, fpfn + win, &start, &end); + else if (pfn == fpfn + 1) + swap_ra_clamp_pfn(vma, faddr, fpfn - win + 1, fpfn + 1, + &start, &end); + else { + left = (win - 1) / 2; + swap_ra_clamp_pfn(vma, faddr, fpfn - left, fpfn + win - left, + &start, &end); + } + swap_ra->nr_pte = end - start; + swap_ra->offset = fpfn - start; + pte = vmf->pte - swap_ra->offset; +#ifdef CONFIG_64BIT + swap_ra->ptes = pte; +#else + tpte = swap_ra->ptes; + for (pfn = start; pfn != end; pfn++) + *tpte++ = *pte++; +#endif + + return NULL; +} + +struct page *do_swap_page_readahead(swp_entry_t fentry, gfp_t gfp_mask, + struct vm_fault *vmf, + struct vma_swap_readahead *swap_ra) +{ + struct blk_plug plug; + struct vm_area_struct *vma = vmf->vma; + struct page *page; + pte_t *pte, pentry; + swp_entry_t entry; + unsigned int i; + bool page_allocated; + + if (swap_ra->win == 1) + goto skip; + + blk_start_plug(&plug); + for (i = 0, pte = swap_ra->ptes; i < swap_ra->nr_pte; + i++, pte++) { + pentry = *pte; + if (pte_none(pentry)) + continue; + if (pte_present(pentry)) + continue; + entry = pte_to_swp_entry(pentry); + if (unlikely(non_swap_entry(entry))) + continue; + page = __read_swap_cache_async(entry, gfp_mask, vma, + vmf->address, &page_allocated); + if (!page) + continue; + if (page_allocated) { + swap_readpage(page, false); + if (i != swap_ra->offset && + likely(!PageTransCompound(page))) { + SetPageReadahead(page); + count_vm_event(SWAP_RA); + } + } + put_page(page); + } + blk_finish_plug(&plug); + lru_add_drain(); +skip: + return read_swap_cache_async(fentry, gfp_mask, vma, vmf->address, + swap_ra->win == 1); +} + +#ifdef CONFIG_SYSFS +static ssize_t vma_ra_enabled_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + return sprintf(buf, "%s\n", swap_vma_readahead ? "true" : "false"); +} +static ssize_t vma_ra_enabled_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count) +{ + if (!strncmp(buf, "true", 4) || !strncmp(buf, "1", 1)) + swap_vma_readahead = true; + else if (!strncmp(buf, "false", 5) || !strncmp(buf, "0", 1)) + swap_vma_readahead = false; + else + return -EINVAL; + + return count; +} +static struct kobj_attribute vma_ra_enabled_attr = + __ATTR(vma_ra_enabled, 0644, vma_ra_enabled_show, + vma_ra_enabled_store); + +static ssize_t vma_ra_max_order_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + return sprintf(buf, "%d\n", swap_ra_max_order); +} +static ssize_t vma_ra_max_order_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count) +{ + int err, v; + + err = kstrtoint(buf, 10, &v); + if (err || v > SWAP_RA_ORDER_CEILING || v <= 0) + return -EINVAL; + + swap_ra_max_order = v; + + return count; +} +static struct kobj_attribute vma_ra_max_order_attr = + __ATTR(vma_ra_max_order, 0644, vma_ra_max_order_show, + vma_ra_max_order_store); + +static struct attribute *swap_attrs[] = { + &vma_ra_enabled_attr.attr, + &vma_ra_max_order_attr.attr, + NULL, +}; + +static struct attribute_group swap_attr_group = { + .attrs = swap_attrs, +}; + +static int __init swap_init_sysfs(void) +{ + int err; + struct kobject *swap_kobj; + + swap_kobj = kobject_create_and_add("swap", mm_kobj); + if (!swap_kobj) { + pr_err("failed to create swap kobject\n"); + return -ENOMEM; + } + err = sysfs_create_group(swap_kobj, &swap_attr_group); + if (err) { + pr_err("failed to register swap group\n"); + goto delete_obj; + } + return 0; + +delete_obj: + kobject_put(swap_kobj); + return err; +} +subsys_initcall(swap_init_sysfs); +#endif diff --git a/mm/swapfile.c b/mm/swapfile.c index 6ba4aab..d483278 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -60,7 +60,7 @@ atomic_long_t nr_swap_pages; EXPORT_SYMBOL_GPL(nr_swap_pages); /* protected with swap_lock. reading in vm_swap_full() doesn't need lock */ long total_swap_pages; -static int least_priority; +static int least_priority = -1; static const char Bad_file[] = "Bad swap file entry "; static const char Unused_file[] = "Unused swap file entry "; @@ -85,7 +85,7 @@ PLIST_HEAD(swap_active_head); * is held and the locking order requires swap_lock to be taken * before any swap_info_struct->lock. */ -static PLIST_HEAD(swap_avail_head); +struct plist_head *swap_avail_heads; static DEFINE_SPINLOCK(swap_avail_lock); struct swap_info_struct *swap_info[MAX_SWAPFILES]; @@ -96,6 +96,8 @@ static DECLARE_WAIT_QUEUE_HEAD(proc_poll_wait); /* Activity counter to indicate that a swapon or swapoff has occurred */ static atomic_t proc_poll_event = ATOMIC_INIT(0); +atomic_t nr_rotate_swap = ATOMIC_INIT(0); + static inline unsigned char swap_count(unsigned char ent) { return ent & ~SWAP_HAS_CACHE; /* may include SWAP_HAS_CONT flag */ @@ -265,6 +267,16 @@ static inline void cluster_set_null(struct swap_cluster_info *info) info->data = 0; } +static inline bool cluster_is_huge(struct swap_cluster_info *info) +{ + return info->flags & CLUSTER_FLAG_HUGE; +} + +static inline void cluster_clear_huge(struct swap_cluster_info *info) +{ + info->flags &= ~CLUSTER_FLAG_HUGE; +} + static inline struct swap_cluster_info *lock_cluster(struct swap_info_struct *si, unsigned long offset) { @@ -580,6 +592,21 @@ new_cluster: return found_free; } +static void __del_from_avail_list(struct swap_info_struct *p) +{ + int nid; + + for_each_node(nid) + plist_del(&p->avail_lists[nid], &swap_avail_heads[nid]); +} + +static void del_from_avail_list(struct swap_info_struct *p) +{ + spin_lock(&swap_avail_lock); + __del_from_avail_list(p); + spin_unlock(&swap_avail_lock); +} + static void swap_range_alloc(struct swap_info_struct *si, unsigned long offset, unsigned int nr_entries) { @@ -593,10 +620,20 @@ static void swap_range_alloc(struct swap_info_struct *si, unsigned long offset, if (si->inuse_pages == si->pages) { si->lowest_bit = si->max; si->highest_bit = 0; - spin_lock(&swap_avail_lock); - plist_del(&si->avail_list, &swap_avail_head); - spin_unlock(&swap_avail_lock); + del_from_avail_list(si); + } +} + +static void add_to_avail_list(struct swap_info_struct *p) +{ + int nid; + + spin_lock(&swap_avail_lock); + for_each_node(nid) { + WARN_ON(!plist_node_empty(&p->avail_lists[nid])); + plist_add(&p->avail_lists[nid], &swap_avail_heads[nid]); } + spin_unlock(&swap_avail_lock); } static void swap_range_free(struct swap_info_struct *si, unsigned long offset, @@ -611,13 +648,8 @@ static void swap_range_free(struct swap_info_struct *si, unsigned long offset, bool was_full = !si->highest_bit; si->highest_bit = end; - if (was_full && (si->flags & SWP_WRITEOK)) { - spin_lock(&swap_avail_lock); - WARN_ON(!plist_node_empty(&si->avail_list)); - if (plist_node_empty(&si->avail_list)) - plist_add(&si->avail_list, &swap_avail_head); - spin_unlock(&swap_avail_lock); - } + if (was_full && (si->flags & SWP_WRITEOK)) + add_to_avail_list(si); } atomic_long_add(nr_entries, &nr_swap_pages); si->inuse_pages -= nr_entries; @@ -846,7 +878,7 @@ static int swap_alloc_cluster(struct swap_info_struct *si, swp_entry_t *slot) offset = idx * SWAPFILE_CLUSTER; ci = lock_cluster(si, offset); alloc_cluster(si, idx); - cluster_set_count_flag(ci, SWAPFILE_CLUSTER, 0); + cluster_set_count_flag(ci, SWAPFILE_CLUSTER, CLUSTER_FLAG_HUGE); map = si->swap_map + offset; for (i = 0; i < SWAPFILE_CLUSTER; i++) @@ -898,6 +930,7 @@ int get_swap_pages(int n_goal, bool cluster, swp_entry_t swp_entries[]) struct swap_info_struct *si, *next; long avail_pgs; int n_ret = 0; + int node; /* Only single cluster request supported */ WARN_ON_ONCE(n_goal > 1 && cluster); @@ -917,14 +950,15 @@ int get_swap_pages(int n_goal, bool cluster, swp_entry_t swp_entries[]) spin_lock(&swap_avail_lock); start_over: - plist_for_each_entry_safe(si, next, &swap_avail_head, avail_list) { + node = numa_node_id(); + plist_for_each_entry_safe(si, next, &swap_avail_heads[node], avail_lists[node]) { /* requeue si to after same-priority siblings */ - plist_requeue(&si->avail_list, &swap_avail_head); + plist_requeue(&si->avail_lists[node], &swap_avail_heads[node]); spin_unlock(&swap_avail_lock); spin_lock(&si->lock); if (!si->highest_bit || !(si->flags & SWP_WRITEOK)) { spin_lock(&swap_avail_lock); - if (plist_node_empty(&si->avail_list)) { + if (plist_node_empty(&si->avail_lists[node])) { spin_unlock(&si->lock); goto nextsi; } @@ -934,13 +968,14 @@ start_over: WARN(!(si->flags & SWP_WRITEOK), "swap_info %d in list but !SWP_WRITEOK\n", si->type); - plist_del(&si->avail_list, &swap_avail_head); + __del_from_avail_list(si); spin_unlock(&si->lock); goto nextsi; } - if (cluster) - n_ret = swap_alloc_cluster(si, swp_entries); - else + if (cluster) { + if (!(si->flags & SWP_FILE)) + n_ret = swap_alloc_cluster(si, swp_entries); + } else n_ret = scan_swap_map_slots(si, SWAP_HAS_CACHE, n_goal, swp_entries); spin_unlock(&si->lock); @@ -962,7 +997,7 @@ nextsi: * swap_avail_head list then try it, otherwise start over * if we have not gotten any slots. */ - if (plist_node_empty(&next->avail_list)) + if (plist_node_empty(&next->avail_lists[node])) goto start_over; } @@ -1168,22 +1203,57 @@ static void swapcache_free_cluster(swp_entry_t entry) struct swap_cluster_info *ci; struct swap_info_struct *si; unsigned char *map; - unsigned int i; + unsigned int i, free_entries = 0; + unsigned char val; - si = swap_info_get(entry); + si = _swap_info_get(entry); if (!si) return; ci = lock_cluster(si, offset); + VM_BUG_ON(!cluster_is_huge(ci)); map = si->swap_map + offset; for (i = 0; i < SWAPFILE_CLUSTER; i++) { - VM_BUG_ON(map[i] != SWAP_HAS_CACHE); - map[i] = 0; + val = map[i]; + VM_BUG_ON(!(val & SWAP_HAS_CACHE)); + if (val == SWAP_HAS_CACHE) + free_entries++; + } + if (!free_entries) { + for (i = 0; i < SWAPFILE_CLUSTER; i++) + map[i] &= ~SWAP_HAS_CACHE; } + cluster_clear_huge(ci); unlock_cluster(ci); - mem_cgroup_uncharge_swap(entry, SWAPFILE_CLUSTER); - swap_free_cluster(si, idx); - spin_unlock(&si->lock); + if (free_entries == SWAPFILE_CLUSTER) { + spin_lock(&si->lock); + ci = lock_cluster(si, offset); + memset(map, 0, SWAPFILE_CLUSTER); + unlock_cluster(ci); + mem_cgroup_uncharge_swap(entry, SWAPFILE_CLUSTER); + swap_free_cluster(si, idx); + spin_unlock(&si->lock); + } else if (free_entries) { + for (i = 0; i < SWAPFILE_CLUSTER; i++, entry.val++) { + if (!__swap_entry_free(si, entry, SWAP_HAS_CACHE)) + free_swap_slot(entry); + } + } +} + +int split_swap_cluster(swp_entry_t entry) +{ + struct swap_info_struct *si; + struct swap_cluster_info *ci; + unsigned long offset = swp_offset(entry); + + si = _swap_info_get(entry); + if (!si) + return -EBUSY; + ci = lock_cluster(si, offset); + cluster_clear_huge(ci); + unlock_cluster(ci); + return 0; } #else static inline void swapcache_free_cluster(swp_entry_t entry) @@ -1332,29 +1402,161 @@ out: return count; } +#ifdef CONFIG_THP_SWAP +static bool swap_page_trans_huge_swapped(struct swap_info_struct *si, + swp_entry_t entry) +{ + struct swap_cluster_info *ci; + unsigned char *map = si->swap_map; + unsigned long roffset = swp_offset(entry); + unsigned long offset = round_down(roffset, SWAPFILE_CLUSTER); + int i; + bool ret = false; + + ci = lock_cluster_or_swap_info(si, offset); + if (!ci || !cluster_is_huge(ci)) { + if (map[roffset] != SWAP_HAS_CACHE) + ret = true; + goto unlock_out; + } + for (i = 0; i < SWAPFILE_CLUSTER; i++) { + if (map[offset + i] != SWAP_HAS_CACHE) { + ret = true; + break; + } + } +unlock_out: + unlock_cluster_or_swap_info(si, ci); + return ret; +} + +static bool page_swapped(struct page *page) +{ + swp_entry_t entry; + struct swap_info_struct *si; + + if (likely(!PageTransCompound(page))) + return page_swapcount(page) != 0; + + page = compound_head(page); + entry.val = page_private(page); + si = _swap_info_get(entry); + if (si) + return swap_page_trans_huge_swapped(si, entry); + return false; +} + +static int page_trans_huge_map_swapcount(struct page *page, int *total_mapcount, + int *total_swapcount) +{ + int i, map_swapcount, _total_mapcount, _total_swapcount; + unsigned long offset = 0; + struct swap_info_struct *si; + struct swap_cluster_info *ci = NULL; + unsigned char *map = NULL; + int mapcount, swapcount = 0; + + /* hugetlbfs shouldn't call it */ + VM_BUG_ON_PAGE(PageHuge(page), page); + + if (likely(!PageTransCompound(page))) { + mapcount = atomic_read(&page->_mapcount) + 1; + if (total_mapcount) + *total_mapcount = mapcount; + if (PageSwapCache(page)) + swapcount = page_swapcount(page); + if (total_swapcount) + *total_swapcount = swapcount; + return mapcount + swapcount; + } + + page = compound_head(page); + + _total_mapcount = _total_swapcount = map_swapcount = 0; + if (PageSwapCache(page)) { + swp_entry_t entry; + + entry.val = page_private(page); + si = _swap_info_get(entry); + if (si) { + map = si->swap_map; + offset = swp_offset(entry); + } + } + if (map) + ci = lock_cluster(si, offset); + for (i = 0; i < HPAGE_PMD_NR; i++) { + mapcount = atomic_read(&page[i]._mapcount) + 1; + _total_mapcount += mapcount; + if (map) { + swapcount = swap_count(map[offset + i]); + _total_swapcount += swapcount; + } + map_swapcount = max(map_swapcount, mapcount + swapcount); + } + unlock_cluster(ci); + if (PageDoubleMap(page)) { + map_swapcount -= 1; + _total_mapcount -= HPAGE_PMD_NR; + } + mapcount = compound_mapcount(page); + map_swapcount += mapcount; + _total_mapcount += mapcount; + if (total_mapcount) + *total_mapcount = _total_mapcount; + if (total_swapcount) + *total_swapcount = _total_swapcount; + + return map_swapcount; +} +#else +#define swap_page_trans_huge_swapped(si, entry) swap_swapcount(si, entry) +#define page_swapped(page) (page_swapcount(page) != 0) + +static int page_trans_huge_map_swapcount(struct page *page, int *total_mapcount, + int *total_swapcount) +{ + int mapcount, swapcount = 0; + + /* hugetlbfs shouldn't call it */ + VM_BUG_ON_PAGE(PageHuge(page), page); + + mapcount = page_trans_huge_mapcount(page, total_mapcount); + if (PageSwapCache(page)) + swapcount = page_swapcount(page); + if (total_swapcount) + *total_swapcount = swapcount; + return mapcount + swapcount; +} +#endif + /* * We can write to an anon page without COW if there are no other references * to it. And as a side-effect, free up its swap: because the old content * on disk will never be read, and seeking back there to write new content * later would only waste time away from clustering. * - * NOTE: total_mapcount should not be relied upon by the caller if + * NOTE: total_map_swapcount should not be relied upon by the caller if * reuse_swap_page() returns false, but it may be always overwritten * (see the other implementation for CONFIG_SWAP=n). */ -bool reuse_swap_page(struct page *page, int *total_mapcount) +bool reuse_swap_page(struct page *page, int *total_map_swapcount) { - int count; + int count, total_mapcount, total_swapcount; VM_BUG_ON_PAGE(!PageLocked(page), page); if (unlikely(PageKsm(page))) return false; - count = page_trans_huge_mapcount(page, total_mapcount); - if (count <= 1 && PageSwapCache(page)) { - count += page_swapcount(page); - if (count != 1) - goto out; + count = page_trans_huge_map_swapcount(page, &total_mapcount, + &total_swapcount); + if (total_map_swapcount) + *total_map_swapcount = total_mapcount + total_swapcount; + if (count == 1 && PageSwapCache(page) && + (likely(!PageTransCompound(page)) || + /* The remaining swap count will be freed soon */ + total_swapcount == page_swapcount(page))) { if (!PageWriteback(page)) { + page = compound_head(page); delete_from_swap_cache(page); SetPageDirty(page); } else { @@ -1370,7 +1572,7 @@ bool reuse_swap_page(struct page *page, int *total_mapcount) spin_unlock(&p->lock); } } -out: + return count <= 1; } @@ -1386,7 +1588,7 @@ int try_to_free_swap(struct page *page) return 0; if (PageWriteback(page)) return 0; - if (page_swapcount(page)) + if (page_swapped(page)) return 0; /* @@ -1407,6 +1609,7 @@ int try_to_free_swap(struct page *page) if (pm_suspended_storage()) return 0; + page = compound_head(page); delete_from_swap_cache(page); SetPageDirty(page); return 1; @@ -1428,7 +1631,8 @@ int free_swap_and_cache(swp_entry_t entry) p = _swap_info_get(entry); if (p) { count = __swap_entry_free(p, entry, 1); - if (count == SWAP_HAS_CACHE) { + if (count == SWAP_HAS_CACHE && + !swap_page_trans_huge_swapped(p, entry)) { page = find_get_page(swap_address_space(entry), swp_offset(entry)); if (page && !trylock_page(page)) { @@ -1445,7 +1649,8 @@ int free_swap_and_cache(swp_entry_t entry) */ if (PageSwapCache(page) && !PageWriteback(page) && (!page_mapped(page) || mem_cgroup_swap_full(page)) && - !swap_swapcount(p, entry)) { + !swap_page_trans_huge_swapped(p, entry)) { + page = compound_head(page); delete_from_swap_cache(page); SetPageDirty(page); } @@ -1999,7 +2204,7 @@ int try_to_unuse(unsigned int type, bool frontswap, .sync_mode = WB_SYNC_NONE, }; - swap_writepage(page, &wbc); + swap_writepage(compound_head(page), &wbc); lock_page(page); wait_on_page_writeback(page); } @@ -2012,8 +2217,9 @@ int try_to_unuse(unsigned int type, bool frontswap, * delete, since it may not have been written out to swap yet. */ if (PageSwapCache(page) && - likely(page_private(page) == entry.val)) - delete_from_swap_cache(page); + likely(page_private(page) == entry.val) && + !page_swapped(page)) + delete_from_swap_cache(compound_head(page)); /* * So we could skip searching mms once swap count went @@ -2226,10 +2432,24 @@ static int setup_swap_extents(struct swap_info_struct *sis, sector_t *span) return generic_swapfile_activate(sis, swap_file, span); } +static int swap_node(struct swap_info_struct *p) +{ + struct block_device *bdev; + + if (p->bdev) + bdev = p->bdev; + else + bdev = p->swap_file->f_inode->i_sb->s_bdev; + + return bdev ? bdev->bd_disk->node_id : NUMA_NO_NODE; +} + static void _enable_swap_info(struct swap_info_struct *p, int prio, unsigned char *swap_map, struct swap_cluster_info *cluster_info) { + int i; + if (prio >= 0) p->prio = prio; else @@ -2239,7 +2459,16 @@ static void _enable_swap_info(struct swap_info_struct *p, int prio, * low-to-high, while swap ordering is high-to-low */ p->list.prio = -p->prio; - p->avail_list.prio = -p->prio; + for_each_node(i) { + if (p->prio >= 0) + p->avail_lists[i].prio = -p->prio; + else { + if (swap_node(p) == i) + p->avail_lists[i].prio = 1; + else + p->avail_lists[i].prio = -p->prio; + } + } p->swap_map = swap_map; p->cluster_info = cluster_info; p->flags |= SWP_WRITEOK; @@ -2258,9 +2487,7 @@ static void _enable_swap_info(struct swap_info_struct *p, int prio, * swap_info_struct. */ plist_add(&p->list, &swap_active_head); - spin_lock(&swap_avail_lock); - plist_add(&p->avail_list, &swap_avail_head); - spin_unlock(&swap_avail_lock); + add_to_avail_list(p); } static void enable_swap_info(struct swap_info_struct *p, int prio, @@ -2345,17 +2572,19 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) spin_unlock(&swap_lock); goto out_dput; } - spin_lock(&swap_avail_lock); - plist_del(&p->avail_list, &swap_avail_head); - spin_unlock(&swap_avail_lock); + del_from_avail_list(p); spin_lock(&p->lock); if (p->prio < 0) { struct swap_info_struct *si = p; + int nid; plist_for_each_entry_continue(si, &swap_active_head, list) { si->prio++; si->list.prio--; - si->avail_list.prio--; + for_each_node(nid) { + if (si->avail_lists[nid].prio != 1) + si->avail_lists[nid].prio--; + } } least_priority++; } @@ -2387,6 +2616,9 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) if (p->flags & SWP_CONTINUED) free_swap_count_continuations(p); + if (!p->bdev || !blk_queue_nonrot(bdev_get_queue(p->bdev))) + atomic_dec(&nr_rotate_swap); + mutex_lock(&swapon_mutex); spin_lock(&swap_lock); spin_lock(&p->lock); @@ -2596,6 +2828,7 @@ static struct swap_info_struct *alloc_swap_info(void) { struct swap_info_struct *p; unsigned int type; + int i; p = kzalloc(sizeof(*p), GFP_KERNEL); if (!p) @@ -2631,7 +2864,8 @@ static struct swap_info_struct *alloc_swap_info(void) } INIT_LIST_HEAD(&p->first_swap_extent.list); plist_node_init(&p->list, 0); - plist_node_init(&p->avail_list, 0); + for_each_node(i) + plist_node_init(&p->avail_lists[i], 0); p->flags = SWP_USED; spin_unlock(&swap_lock); spin_lock_init(&p->lock); @@ -2873,6 +3107,9 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) if (!capable(CAP_SYS_ADMIN)) return -EPERM; + if (!swap_avail_heads) + return -ENOMEM; + p = alloc_swap_info(); if (IS_ERR(p)) return PTR_ERR(p); @@ -2963,7 +3200,8 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) cluster = per_cpu_ptr(p->percpu_cluster, cpu); cluster_set_null(&cluster->index); } - } + } else + atomic_inc(&nr_rotate_swap); error = swap_cgroup_swapon(p->type, maxpages); if (error) @@ -3457,3 +3695,21 @@ static void free_swap_count_continuations(struct swap_info_struct *si) } } } + +static int __init swapfile_init(void) +{ + int nid; + + swap_avail_heads = kmalloc_array(nr_node_ids, sizeof(struct plist_head), + GFP_KERNEL); + if (!swap_avail_heads) { + pr_emerg("Not enough memory for swap heads, swap is disabled\n"); + return -ENOMEM; + } + + for_each_node(nid) + plist_head_init(&swap_avail_heads[nid]); + + return 0; +} +subsys_initcall(swapfile_init); diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index 8bcb501..8119270 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -371,6 +371,36 @@ extern ssize_t __mcopy_atomic_hugetlb(struct mm_struct *dst_mm, bool zeropage); #endif /* CONFIG_HUGETLB_PAGE */ +static __always_inline ssize_t mfill_atomic_pte(struct mm_struct *dst_mm, + pmd_t *dst_pmd, + struct vm_area_struct *dst_vma, + unsigned long dst_addr, + unsigned long src_addr, + struct page **page, + bool zeropage) +{ + ssize_t err; + + if (vma_is_anonymous(dst_vma)) { + if (!zeropage) + err = mcopy_atomic_pte(dst_mm, dst_pmd, dst_vma, + dst_addr, src_addr, page); + else + err = mfill_zeropage_pte(dst_mm, dst_pmd, + dst_vma, dst_addr); + } else { + if (!zeropage) + err = shmem_mcopy_atomic_pte(dst_mm, dst_pmd, + dst_vma, dst_addr, + src_addr, page); + else + err = shmem_mfill_zeropage_pte(dst_mm, dst_pmd, + dst_vma, dst_addr); + } + + return err; +} + static __always_inline ssize_t __mcopy_atomic(struct mm_struct *dst_mm, unsigned long dst_start, unsigned long src_start, @@ -487,22 +517,8 @@ retry: BUG_ON(pmd_none(*dst_pmd)); BUG_ON(pmd_trans_huge(*dst_pmd)); - if (vma_is_anonymous(dst_vma)) { - if (!zeropage) - err = mcopy_atomic_pte(dst_mm, dst_pmd, dst_vma, - dst_addr, src_addr, - &page); - else - err = mfill_zeropage_pte(dst_mm, dst_pmd, - dst_vma, dst_addr); - } else { - err = -EINVAL; /* if zeropage is true return -EINVAL */ - if (likely(!zeropage)) - err = shmem_mcopy_atomic_pte(dst_mm, dst_pmd, - dst_vma, dst_addr, - src_addr, &page); - } - + err = mfill_atomic_pte(dst_mm, dst_pmd, dst_vma, dst_addr, + src_addr, &page, zeropage); cond_resched(); if (unlikely(err == -EFAULT)) { @@ -614,7 +614,7 @@ int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin) return 0; if (sysctl_overcommit_memory == OVERCOMMIT_GUESS) { - free = global_page_state(NR_FREE_PAGES); + free = global_zone_page_state(NR_FREE_PAGES); free += global_node_page_state(NR_FILE_PAGES); /* diff --git a/mm/vmalloc.c b/mm/vmalloc.c index a47e389..8a43db6 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -49,12 +49,10 @@ static void __vunmap(const void *, int); static void free_work(struct work_struct *w) { struct vfree_deferred *p = container_of(w, struct vfree_deferred, wq); - struct llist_node *llnode = llist_del_all(&p->list); - while (llnode) { - void *p = llnode; - llnode = llist_next(llnode); - __vunmap(p, 1); - } + struct llist_node *t, *llnode; + + llist_for_each_safe(llnode, t, llist_del_all(&p->list)) + __vunmap((void *)llnode, 1); } /*** Page table manipulation functions ***/ @@ -2482,7 +2480,7 @@ static unsigned long pvm_determine_end(struct vmap_area **pnext, * matching slot. While scanning, if any of the areas overlaps with * existing vmap_area, the base address is pulled down to fit the * area. Scanning is repeated till all the areas fit and then all - * necessary data structres are inserted and the result is returned. + * necessary data structures are inserted and the result is returned. */ struct vm_struct **pcpu_get_vm_areas(const unsigned long *offsets, const size_t *sizes, int nr_vms, @@ -2510,15 +2508,11 @@ struct vm_struct **pcpu_get_vm_areas(const unsigned long *offsets, if (start > offsets[last_area]) last_area = area; - for (area2 = 0; area2 < nr_vms; area2++) { + for (area2 = area + 1; area2 < nr_vms; area2++) { unsigned long start2 = offsets[area2]; unsigned long end2 = start2 + sizes[area2]; - if (area2 == area) - continue; - - BUG_ON(start2 >= start && start2 < end); - BUG_ON(end2 <= end && end2 > start); + BUG_ON(start2 < end && start < end2); } } last_end = offsets[last_area] + sizes[last_area]; diff --git a/mm/vmscan.c b/mm/vmscan.c index f957afe..13d711d 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -393,14 +393,15 @@ static unsigned long do_shrink_slab(struct shrink_control *shrinkctl, unsigned long nr_to_scan = min(batch_size, total_scan); shrinkctl->nr_to_scan = nr_to_scan; + shrinkctl->nr_scanned = nr_to_scan; ret = shrinker->scan_objects(shrinker, shrinkctl); if (ret == SHRINK_STOP) break; freed += ret; - count_vm_events(SLABS_SCANNED, nr_to_scan); - total_scan -= nr_to_scan; - scanned += nr_to_scan; + count_vm_events(SLABS_SCANNED, shrinkctl->nr_scanned); + total_scan -= shrinkctl->nr_scanned; + scanned += shrinkctl->nr_scanned; cond_resched(); } @@ -535,7 +536,9 @@ static inline int is_page_cache_freeable(struct page *page) * that isolated the page, the page cache radix tree and * optional buffer heads at page->private. */ - return page_count(page) - page_has_private(page) == 2; + int radix_pins = PageTransHuge(page) && PageSwapCache(page) ? + HPAGE_PMD_NR : 1; + return page_count(page) - page_has_private(page) == 1 + radix_pins; } static int may_write_to_inode(struct inode *inode, struct scan_control *sc) @@ -665,6 +668,7 @@ static int __remove_mapping(struct address_space *mapping, struct page *page, bool reclaimed) { unsigned long flags; + int refcount; BUG_ON(!PageLocked(page)); BUG_ON(mapping != page_mapping(page)); @@ -695,11 +699,15 @@ static int __remove_mapping(struct address_space *mapping, struct page *page, * Note that if SetPageDirty is always performed via set_page_dirty, * and thus under tree_lock, then this ordering is not required. */ - if (!page_ref_freeze(page, 2)) + if (unlikely(PageTransHuge(page)) && PageSwapCache(page)) + refcount = 1 + HPAGE_PMD_NR; + else + refcount = 2; + if (!page_ref_freeze(page, refcount)) goto cannot_free; /* note: atomic_cmpxchg in page_freeze_refs provides the smp_rmb */ if (unlikely(PageDirty(page))) { - page_ref_unfreeze(page, 2); + page_ref_unfreeze(page, refcount); goto cannot_free; } @@ -1121,58 +1129,59 @@ static unsigned long shrink_page_list(struct list_head *page_list, * Try to allocate it some swap space here. * Lazyfree page could be freed directly */ - if (PageAnon(page) && PageSwapBacked(page) && - !PageSwapCache(page)) { - if (!(sc->gfp_mask & __GFP_IO)) - goto keep_locked; - if (PageTransHuge(page)) { - /* cannot split THP, skip it */ - if (!can_split_huge_page(page, NULL)) - goto activate_locked; - /* - * Split pages without a PMD map right - * away. Chances are some or all of the - * tail pages can be freed without IO. - */ - if (!compound_mapcount(page) && - split_huge_page_to_list(page, page_list)) - goto activate_locked; - } - if (!add_to_swap(page)) { - if (!PageTransHuge(page)) - goto activate_locked; - /* Split THP and swap individual base pages */ - if (split_huge_page_to_list(page, page_list)) - goto activate_locked; - if (!add_to_swap(page)) - goto activate_locked; - } - - /* XXX: We don't support THP writes */ - if (PageTransHuge(page) && - split_huge_page_to_list(page, page_list)) { - delete_from_swap_cache(page); - goto activate_locked; - } + if (PageAnon(page) && PageSwapBacked(page)) { + if (!PageSwapCache(page)) { + if (!(sc->gfp_mask & __GFP_IO)) + goto keep_locked; + if (PageTransHuge(page)) { + /* cannot split THP, skip it */ + if (!can_split_huge_page(page, NULL)) + goto activate_locked; + /* + * Split pages without a PMD map right + * away. Chances are some or all of the + * tail pages can be freed without IO. + */ + if (!compound_mapcount(page) && + split_huge_page_to_list(page, + page_list)) + goto activate_locked; + } + if (!add_to_swap(page)) { + if (!PageTransHuge(page)) + goto activate_locked; + /* Fallback to swap normal pages */ + if (split_huge_page_to_list(page, + page_list)) + goto activate_locked; +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + count_vm_event(THP_SWPOUT_FALLBACK); +#endif + if (!add_to_swap(page)) + goto activate_locked; + } - may_enter_fs = 1; + may_enter_fs = 1; - /* Adding to swap updated mapping */ - mapping = page_mapping(page); + /* Adding to swap updated mapping */ + mapping = page_mapping(page); + } } else if (unlikely(PageTransHuge(page))) { /* Split file THP */ if (split_huge_page_to_list(page, page_list)) goto keep_locked; } - VM_BUG_ON_PAGE(PageTransHuge(page), page); - /* * The page is mapped into the page tables of one or more * processes. Try to unmap it here. */ if (page_mapped(page)) { - if (!try_to_unmap(page, ttu_flags | TTU_BATCH_FLUSH)) { + enum ttu_flags flags = ttu_flags | TTU_BATCH_FLUSH; + + if (unlikely(PageTransHuge(page))) + flags |= TTU_SPLIT_HUGE_PMD; + if (!try_to_unmap(page, flags)) { nr_unmap_fail++; goto activate_locked; } @@ -1312,7 +1321,11 @@ free_it: * Is there need to periodically free_page_list? It would * appear not as the counts should be low */ - list_add(&page->lru, &free_pages); + if (unlikely(PageTransHuge(page))) { + mem_cgroup_uncharge(page); + (*get_compound_page_dtor(page))(page); + } else + list_add(&page->lru, &free_pages); continue; activate_locked: @@ -1742,9 +1755,15 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec, int file = is_file_lru(lru); struct pglist_data *pgdat = lruvec_pgdat(lruvec); struct zone_reclaim_stat *reclaim_stat = &lruvec->reclaim_stat; + bool stalled = false; while (unlikely(too_many_isolated(pgdat, file, sc))) { - congestion_wait(BLK_RW_ASYNC, HZ/10); + if (stalled) + return 0; + + /* wait a bit for the reclaimer. */ + msleep(100); + stalled = true; /* We are about to die and free our memory. Return now. */ if (fatal_signal_pending(current)) diff --git a/mm/vmstat.c b/mm/vmstat.c index 9a4441b..c7e4b84 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -870,6 +870,9 @@ static int __fragmentation_index(unsigned int order, struct contig_page_info *in { unsigned long requested = 1UL << order; + if (WARN_ON_ONCE(order >= MAX_ORDER)) + return 0; + if (!info->free_blocks_total) return 0; @@ -1071,6 +1074,8 @@ const char * const vmstat_text[] = { #endif "thp_zero_page_alloc", "thp_zero_page_alloc_failed", + "thp_swpout", + "thp_swpout_fallback", #endif #ifdef CONFIG_MEMORY_BALLOON "balloon_inflate", @@ -1093,6 +1098,10 @@ const char * const vmstat_text[] = { "vmacache_find_hits", "vmacache_full_flushes", #endif +#ifdef CONFIG_SWAP + "swap_ra", + "swap_ra_hit", +#endif #endif /* CONFIG_VM_EVENTS_COUNTERS */ }; #endif /* CONFIG_PROC_FS || CONFIG_SYSFS || CONFIG_NUMA */ @@ -1250,7 +1259,7 @@ static void pagetypeinfo_showblockcount_print(struct seq_file *m, seq_putc(m, '\n'); } -/* Print out the free pages at each order for each migratetype */ +/* Print out the number of pageblocks for each migratetype */ static int pagetypeinfo_showblockcount(struct seq_file *m, void *arg) { int mtype; @@ -1500,7 +1509,7 @@ static void *vmstat_start(struct seq_file *m, loff_t *pos) if (!v) return ERR_PTR(-ENOMEM); for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++) - v[i] = global_page_state(i); + v[i] = global_zone_page_state(i); v += NR_VM_ZONE_STAT_ITEMS; for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++) @@ -1589,7 +1598,7 @@ int vmstat_refresh(struct ctl_table *table, int write, * which can equally be echo'ed to or cat'ted from (by root), * can be used to update the stats just before reading them. * - * Oh, and since global_page_state() etc. are so careful to hide + * Oh, and since global_zone_page_state() etc. are so careful to hide * transiently negative values, report an error here if any of * the stats is negative, so we know to go looking for imbalance. */ diff --git a/mm/z3fold.c b/mm/z3fold.c index 54f63c4..486550d 100644 --- a/mm/z3fold.c +++ b/mm/z3fold.c @@ -23,10 +23,13 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/atomic.h> +#include <linux/sched.h> #include <linux/list.h> #include <linux/mm.h> #include <linux/module.h> +#include <linux/percpu.h> #include <linux/preempt.h> +#include <linux/workqueue.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/zpool.h> @@ -48,11 +51,15 @@ enum buddy { }; /* - * struct z3fold_header - z3fold page metadata occupying the first chunk of each + * struct z3fold_header - z3fold page metadata occupying first chunks of each * z3fold page, except for HEADLESS pages - * @buddy: links the z3fold page into the relevant list in the pool + * @buddy: links the z3fold page into the relevant list in the + * pool * @page_lock: per-page lock - * @refcount: reference cound for the z3fold page + * @refcount: reference count for the z3fold page + * @work: work_struct for page layout optimization + * @pool: pointer to the pool which this page belongs to + * @cpu: CPU which this page "belongs" to * @first_chunks: the size of the first buddy in chunks, 0 if free * @middle_chunks: the size of the middle buddy in chunks, 0 if free * @last_chunks: the size of the last buddy in chunks, 0 if free @@ -62,6 +69,9 @@ struct z3fold_header { struct list_head buddy; spinlock_t page_lock; struct kref refcount; + struct work_struct work; + struct z3fold_pool *pool; + short cpu; unsigned short first_chunks; unsigned short middle_chunks; unsigned short last_chunks; @@ -92,28 +102,39 @@ struct z3fold_header { /** * struct z3fold_pool - stores metadata for each z3fold pool - * @lock: protects all pool fields and first|last_chunk fields of any - * z3fold page in the pool - * @unbuddied: array of lists tracking z3fold pages that contain 2- buddies; - * the lists each z3fold page is added to depends on the size of - * its free region. + * @name: pool name + * @lock: protects pool unbuddied/lru lists + * @stale_lock: protects pool stale page list + * @unbuddied: per-cpu array of lists tracking z3fold pages that contain 2- + * buddies; the list each z3fold page is added to depends on + * the size of its free region. * @lru: list tracking the z3fold pages in LRU order by most recently * added buddy. + * @stale: list of pages marked for freeing * @pages_nr: number of z3fold pages in the pool. * @ops: pointer to a structure of user defined operations specified at * pool creation time. + * @compact_wq: workqueue for page layout background optimization + * @release_wq: workqueue for safe page release + * @work: work_struct for safe page release * * This structure is allocated at pool creation time and maintains metadata * pertaining to a particular z3fold pool. */ struct z3fold_pool { + const char *name; spinlock_t lock; - struct list_head unbuddied[NCHUNKS]; + spinlock_t stale_lock; + struct list_head *unbuddied; struct list_head lru; + struct list_head stale; atomic64_t pages_nr; const struct z3fold_ops *ops; struct zpool *zpool; const struct zpool_ops *zpool_ops; + struct workqueue_struct *compact_wq; + struct workqueue_struct *release_wq; + struct work_struct work; }; /* @@ -122,9 +143,10 @@ struct z3fold_pool { enum z3fold_page_flags { PAGE_HEADLESS = 0, MIDDLE_CHUNK_MAPPED, + NEEDS_COMPACTING, + PAGE_STALE }; - /***************** * Helpers *****************/ @@ -138,14 +160,19 @@ static int size_to_chunks(size_t size) #define for_each_unbuddied_list(_iter, _begin) \ for ((_iter) = (_begin); (_iter) < NCHUNKS; (_iter)++) +static void compact_page_work(struct work_struct *w); + /* Initializes the z3fold header of a newly allocated z3fold page */ -static struct z3fold_header *init_z3fold_page(struct page *page) +static struct z3fold_header *init_z3fold_page(struct page *page, + struct z3fold_pool *pool) { struct z3fold_header *zhdr = page_address(page); INIT_LIST_HEAD(&page->lru); clear_bit(PAGE_HEADLESS, &page->private); clear_bit(MIDDLE_CHUNK_MAPPED, &page->private); + clear_bit(NEEDS_COMPACTING, &page->private); + clear_bit(PAGE_STALE, &page->private); spin_lock_init(&zhdr->page_lock); kref_init(&zhdr->refcount); @@ -154,7 +181,10 @@ static struct z3fold_header *init_z3fold_page(struct page *page) zhdr->last_chunks = 0; zhdr->first_num = 0; zhdr->start_middle = 0; + zhdr->cpu = -1; + zhdr->pool = pool; INIT_LIST_HEAD(&zhdr->buddy); + INIT_WORK(&zhdr->work, compact_page_work); return zhdr; } @@ -164,21 +194,6 @@ static void free_z3fold_page(struct page *page) __free_page(page); } -static void release_z3fold_page(struct kref *ref) -{ - struct z3fold_header *zhdr; - struct page *page; - - zhdr = container_of(ref, struct z3fold_header, refcount); - page = virt_to_page(zhdr); - - if (!list_empty(&zhdr->buddy)) - list_del(&zhdr->buddy); - if (!list_empty(&page->lru)) - list_del(&page->lru); - free_z3fold_page(page); -} - /* Lock a z3fold page */ static inline void z3fold_page_lock(struct z3fold_header *zhdr) { @@ -228,6 +243,76 @@ static enum buddy handle_to_buddy(unsigned long handle) return (handle - zhdr->first_num) & BUDDY_MASK; } +static void __release_z3fold_page(struct z3fold_header *zhdr, bool locked) +{ + struct page *page = virt_to_page(zhdr); + struct z3fold_pool *pool = zhdr->pool; + + WARN_ON(!list_empty(&zhdr->buddy)); + set_bit(PAGE_STALE, &page->private); + spin_lock(&pool->lock); + if (!list_empty(&page->lru)) + list_del(&page->lru); + spin_unlock(&pool->lock); + if (locked) + z3fold_page_unlock(zhdr); + spin_lock(&pool->stale_lock); + list_add(&zhdr->buddy, &pool->stale); + queue_work(pool->release_wq, &pool->work); + spin_unlock(&pool->stale_lock); +} + +static void __attribute__((__unused__)) + release_z3fold_page(struct kref *ref) +{ + struct z3fold_header *zhdr = container_of(ref, struct z3fold_header, + refcount); + __release_z3fold_page(zhdr, false); +} + +static void release_z3fold_page_locked(struct kref *ref) +{ + struct z3fold_header *zhdr = container_of(ref, struct z3fold_header, + refcount); + WARN_ON(z3fold_page_trylock(zhdr)); + __release_z3fold_page(zhdr, true); +} + +static void release_z3fold_page_locked_list(struct kref *ref) +{ + struct z3fold_header *zhdr = container_of(ref, struct z3fold_header, + refcount); + spin_lock(&zhdr->pool->lock); + list_del_init(&zhdr->buddy); + spin_unlock(&zhdr->pool->lock); + + WARN_ON(z3fold_page_trylock(zhdr)); + __release_z3fold_page(zhdr, true); +} + +static void free_pages_work(struct work_struct *w) +{ + struct z3fold_pool *pool = container_of(w, struct z3fold_pool, work); + + spin_lock(&pool->stale_lock); + while (!list_empty(&pool->stale)) { + struct z3fold_header *zhdr = list_first_entry(&pool->stale, + struct z3fold_header, buddy); + struct page *page = virt_to_page(zhdr); + + list_del(&zhdr->buddy); + if (WARN_ON(!test_bit(PAGE_STALE, &page->private))) + continue; + clear_bit(NEEDS_COMPACTING, &page->private); + spin_unlock(&pool->stale_lock); + cancel_work_sync(&zhdr->work); + free_z3fold_page(page); + cond_resched(); + spin_lock(&pool->stale_lock); + } + spin_unlock(&pool->stale_lock); +} + /* * Returns the number of free chunks in a z3fold page. * NB: can't be used with HEADLESS pages. @@ -252,46 +337,6 @@ static int num_free_chunks(struct z3fold_header *zhdr) return nfree; } -/***************** - * API Functions -*****************/ -/** - * z3fold_create_pool() - create a new z3fold pool - * @gfp: gfp flags when allocating the z3fold pool structure - * @ops: user-defined operations for the z3fold pool - * - * Return: pointer to the new z3fold pool or NULL if the metadata allocation - * failed. - */ -static struct z3fold_pool *z3fold_create_pool(gfp_t gfp, - const struct z3fold_ops *ops) -{ - struct z3fold_pool *pool; - int i; - - pool = kzalloc(sizeof(struct z3fold_pool), gfp); - if (!pool) - return NULL; - spin_lock_init(&pool->lock); - for_each_unbuddied_list(i, 0) - INIT_LIST_HEAD(&pool->unbuddied[i]); - INIT_LIST_HEAD(&pool->lru); - atomic64_set(&pool->pages_nr, 0); - pool->ops = ops; - return pool; -} - -/** - * z3fold_destroy_pool() - destroys an existing z3fold pool - * @pool: the z3fold pool to be destroyed - * - * The pool should be emptied before this function is called. - */ -static void z3fold_destroy_pool(struct z3fold_pool *pool) -{ - kfree(pool); -} - static inline void *mchunk_memmove(struct z3fold_header *zhdr, unsigned short dst_chunk) { @@ -347,6 +392,117 @@ static int z3fold_compact_page(struct z3fold_header *zhdr) return 0; } +static void do_compact_page(struct z3fold_header *zhdr, bool locked) +{ + struct z3fold_pool *pool = zhdr->pool; + struct page *page; + struct list_head *unbuddied; + int fchunks; + + page = virt_to_page(zhdr); + if (locked) + WARN_ON(z3fold_page_trylock(zhdr)); + else + z3fold_page_lock(zhdr); + if (test_bit(PAGE_STALE, &page->private) || + !test_and_clear_bit(NEEDS_COMPACTING, &page->private)) { + z3fold_page_unlock(zhdr); + return; + } + spin_lock(&pool->lock); + list_del_init(&zhdr->buddy); + spin_unlock(&pool->lock); + + z3fold_compact_page(zhdr); + unbuddied = get_cpu_ptr(pool->unbuddied); + fchunks = num_free_chunks(zhdr); + if (fchunks < NCHUNKS && + (!zhdr->first_chunks || !zhdr->middle_chunks || + !zhdr->last_chunks)) { + /* the page's not completely free and it's unbuddied */ + spin_lock(&pool->lock); + list_add(&zhdr->buddy, &unbuddied[fchunks]); + spin_unlock(&pool->lock); + zhdr->cpu = smp_processor_id(); + } + put_cpu_ptr(pool->unbuddied); + z3fold_page_unlock(zhdr); +} + +static void compact_page_work(struct work_struct *w) +{ + struct z3fold_header *zhdr = container_of(w, struct z3fold_header, + work); + + do_compact_page(zhdr, false); +} + + +/* + * API Functions + */ + +/** + * z3fold_create_pool() - create a new z3fold pool + * @name: pool name + * @gfp: gfp flags when allocating the z3fold pool structure + * @ops: user-defined operations for the z3fold pool + * + * Return: pointer to the new z3fold pool or NULL if the metadata allocation + * failed. + */ +static struct z3fold_pool *z3fold_create_pool(const char *name, gfp_t gfp, + const struct z3fold_ops *ops) +{ + struct z3fold_pool *pool = NULL; + int i, cpu; + + pool = kzalloc(sizeof(struct z3fold_pool), gfp); + if (!pool) + goto out; + spin_lock_init(&pool->lock); + spin_lock_init(&pool->stale_lock); + pool->unbuddied = __alloc_percpu(sizeof(struct list_head)*NCHUNKS, 2); + for_each_possible_cpu(cpu) { + struct list_head *unbuddied = + per_cpu_ptr(pool->unbuddied, cpu); + for_each_unbuddied_list(i, 0) + INIT_LIST_HEAD(&unbuddied[i]); + } + INIT_LIST_HEAD(&pool->lru); + INIT_LIST_HEAD(&pool->stale); + atomic64_set(&pool->pages_nr, 0); + pool->name = name; + pool->compact_wq = create_singlethread_workqueue(pool->name); + if (!pool->compact_wq) + goto out; + pool->release_wq = create_singlethread_workqueue(pool->name); + if (!pool->release_wq) + goto out_wq; + INIT_WORK(&pool->work, free_pages_work); + pool->ops = ops; + return pool; + +out_wq: + destroy_workqueue(pool->compact_wq); +out: + kfree(pool); + return NULL; +} + +/** + * z3fold_destroy_pool() - destroys an existing z3fold pool + * @pool: the z3fold pool to be destroyed + * + * The pool should be emptied before this function is called. + */ +static void z3fold_destroy_pool(struct z3fold_pool *pool) +{ + destroy_workqueue(pool->release_wq); + destroy_workqueue(pool->compact_wq); + kfree(pool); +} + /** * z3fold_alloc() - allocates a region of a given size * @pool: z3fold pool from which to allocate @@ -371,8 +527,9 @@ static int z3fold_alloc(struct z3fold_pool *pool, size_t size, gfp_t gfp, { int chunks = 0, i, freechunks; struct z3fold_header *zhdr = NULL; + struct page *page = NULL; enum buddy bud; - struct page *page; + bool can_sleep = (gfp & __GFP_RECLAIM) == __GFP_RECLAIM; if (!size || (gfp & __GFP_HIGHMEM)) return -EINVAL; @@ -383,23 +540,57 @@ static int z3fold_alloc(struct z3fold_pool *pool, size_t size, gfp_t gfp, if (size > PAGE_SIZE - ZHDR_SIZE_ALIGNED - CHUNK_SIZE) bud = HEADLESS; else { + struct list_head *unbuddied; chunks = size_to_chunks(size); +lookup: /* First, try to find an unbuddied z3fold page. */ - zhdr = NULL; + unbuddied = get_cpu_ptr(pool->unbuddied); for_each_unbuddied_list(i, chunks) { - spin_lock(&pool->lock); - zhdr = list_first_entry_or_null(&pool->unbuddied[i], + struct list_head *l = &unbuddied[i]; + + zhdr = list_first_entry_or_null(READ_ONCE(l), struct z3fold_header, buddy); - if (!zhdr || !z3fold_page_trylock(zhdr)) { - spin_unlock(&pool->lock); + + if (!zhdr) continue; + + /* Re-check under lock. */ + spin_lock(&pool->lock); + l = &unbuddied[i]; + if (unlikely(zhdr != list_first_entry(READ_ONCE(l), + struct z3fold_header, buddy)) || + !z3fold_page_trylock(zhdr)) { + spin_unlock(&pool->lock); + put_cpu_ptr(pool->unbuddied); + goto lookup; } - kref_get(&zhdr->refcount); list_del_init(&zhdr->buddy); + zhdr->cpu = -1; spin_unlock(&pool->lock); page = virt_to_page(zhdr); + if (test_bit(NEEDS_COMPACTING, &page->private)) { + z3fold_page_unlock(zhdr); + zhdr = NULL; + put_cpu_ptr(pool->unbuddied); + if (can_sleep) + cond_resched(); + goto lookup; + } + + /* + * this page could not be removed from its unbuddied + * list while pool lock was held, and then we've taken + * page lock so kref_put could not be called before + * we got here, so it's safe to just call kref_get() + */ + kref_get(&zhdr->refcount); + break; + } + put_cpu_ptr(pool->unbuddied); + + if (zhdr) { if (zhdr->first_chunks == 0) { if (zhdr->middle_chunks != 0 && chunks >= zhdr->start_middle) @@ -411,32 +602,49 @@ static int z3fold_alloc(struct z3fold_pool *pool, size_t size, gfp_t gfp, else if (zhdr->middle_chunks == 0) bud = MIDDLE; else { - z3fold_page_unlock(zhdr); - spin_lock(&pool->lock); if (kref_put(&zhdr->refcount, - release_z3fold_page)) + release_z3fold_page_locked)) atomic64_dec(&pool->pages_nr); - spin_unlock(&pool->lock); + else + z3fold_page_unlock(zhdr); pr_err("No free chunks in unbuddied\n"); WARN_ON(1); - continue; + goto lookup; } goto found; } bud = FIRST; } - /* Couldn't find unbuddied z3fold page, create new one */ - page = alloc_page(gfp); + spin_lock(&pool->stale_lock); + zhdr = list_first_entry_or_null(&pool->stale, + struct z3fold_header, buddy); + /* + * Before allocating a page, let's see if we can take one from the + * stale pages list. cancel_work_sync() can sleep so we must make + * sure it won't be called in case we're in atomic context. + */ + if (zhdr && (can_sleep || !work_pending(&zhdr->work) || + !unlikely(work_busy(&zhdr->work)))) { + list_del(&zhdr->buddy); + clear_bit(NEEDS_COMPACTING, &page->private); + spin_unlock(&pool->stale_lock); + if (can_sleep) + cancel_work_sync(&zhdr->work); + page = virt_to_page(zhdr); + } else { + spin_unlock(&pool->stale_lock); + page = alloc_page(gfp); + } + if (!page) return -ENOMEM; atomic64_inc(&pool->pages_nr); - zhdr = init_z3fold_page(page); + zhdr = init_z3fold_page(page, pool); if (bud == HEADLESS) { set_bit(PAGE_HEADLESS, &page->private); - spin_lock(&pool->lock); goto headless; } z3fold_page_lock(zhdr); @@ -451,15 +659,21 @@ found: zhdr->start_middle = zhdr->first_chunks + ZHDR_CHUNKS; } - spin_lock(&pool->lock); if (zhdr->first_chunks == 0 || zhdr->last_chunks == 0 || zhdr->middle_chunks == 0) { + struct list_head *unbuddied = get_cpu_ptr(pool->unbuddied); + /* Add to unbuddied list */ freechunks = num_free_chunks(zhdr); - list_add(&zhdr->buddy, &pool->unbuddied[freechunks]); + spin_lock(&pool->lock); + list_add(&zhdr->buddy, &unbuddied[freechunks]); + spin_unlock(&pool->lock); + zhdr->cpu = smp_processor_id(); + put_cpu_ptr(pool->unbuddied); } headless: + spin_lock(&pool->lock); /* Add/move z3fold page to beginning of LRU */ if (!list_empty(&page->lru)) list_del(&page->lru); @@ -487,7 +701,6 @@ headless: static void z3fold_free(struct z3fold_pool *pool, unsigned long handle) { struct z3fold_header *zhdr; - int freechunks; struct page *page; enum buddy bud; @@ -526,25 +739,27 @@ static void z3fold_free(struct z3fold_pool *pool, unsigned long handle) spin_unlock(&pool->lock); free_z3fold_page(page); atomic64_dec(&pool->pages_nr); - } else { - if (zhdr->first_chunks != 0 || zhdr->middle_chunks != 0 || - zhdr->last_chunks != 0) { - z3fold_compact_page(zhdr); - /* Add to the unbuddied list */ - spin_lock(&pool->lock); - if (!list_empty(&zhdr->buddy)) - list_del(&zhdr->buddy); - freechunks = num_free_chunks(zhdr); - list_add(&zhdr->buddy, &pool->unbuddied[freechunks]); - spin_unlock(&pool->lock); - } + return; + } + + if (kref_put(&zhdr->refcount, release_z3fold_page_locked_list)) { + atomic64_dec(&pool->pages_nr); + return; + } + if (test_and_set_bit(NEEDS_COMPACTING, &page->private)) { z3fold_page_unlock(zhdr); + return; + } + if (zhdr->cpu < 0 || !cpu_online(zhdr->cpu)) { spin_lock(&pool->lock); - if (kref_put(&zhdr->refcount, release_z3fold_page)) - atomic64_dec(&pool->pages_nr); + list_del_init(&zhdr->buddy); spin_unlock(&pool->lock); + zhdr->cpu = -1; + do_compact_page(zhdr, true); + return; } - + queue_work_on(zhdr->cpu, pool->compact_wq, &zhdr->work); + z3fold_page_unlock(zhdr); } /** @@ -585,9 +800,10 @@ static void z3fold_free(struct z3fold_pool *pool, unsigned long handle) */ static int z3fold_reclaim_page(struct z3fold_pool *pool, unsigned int retries) { - int i, ret = 0, freechunks; - struct z3fold_header *zhdr; - struct page *page; + int i, ret = 0; + struct z3fold_header *zhdr = NULL; + struct page *page = NULL; + struct list_head *pos; unsigned long first_handle = 0, middle_handle = 0, last_handle = 0; spin_lock(&pool->lock); @@ -600,16 +816,24 @@ static int z3fold_reclaim_page(struct z3fold_pool *pool, unsigned int retries) spin_unlock(&pool->lock); return -EINVAL; } - page = list_last_entry(&pool->lru, struct page, lru); + list_for_each_prev(pos, &pool->lru) { + page = list_entry(pos, struct page, lru); + if (test_bit(PAGE_HEADLESS, &page->private)) + /* candidate found */ + break; + + zhdr = page_address(page); + if (!z3fold_page_trylock(zhdr)) + continue; /* can't evict at this point */ + kref_get(&zhdr->refcount); + list_del_init(&zhdr->buddy); + zhdr->cpu = -1; + } + list_del_init(&page->lru); + spin_unlock(&pool->lock); - zhdr = page_address(page); if (!test_bit(PAGE_HEADLESS, &page->private)) { - if (!list_empty(&zhdr->buddy)) - list_del_init(&zhdr->buddy); - kref_get(&zhdr->refcount); - spin_unlock(&pool->lock); - z3fold_page_lock(zhdr); /* * We need encode the handles before unlocking, since * we can race with free that will set @@ -624,11 +848,14 @@ static int z3fold_reclaim_page(struct z3fold_pool *pool, unsigned int retries) middle_handle = encode_handle(zhdr, MIDDLE); if (zhdr->last_chunks) last_handle = encode_handle(zhdr, LAST); + /* + * it's safe to unlock here because we hold a + * reference to this page + */ z3fold_page_unlock(zhdr); } else { first_handle = encode_handle(zhdr, HEADLESS); last_handle = middle_handle = 0; - spin_unlock(&pool->lock); } /* Issue the eviction callback(s) */ @@ -652,31 +879,12 @@ next: if (ret == 0) { free_z3fold_page(page); return 0; - } else { - spin_lock(&pool->lock); - } - } else { - z3fold_page_lock(zhdr); - if ((zhdr->first_chunks || zhdr->last_chunks || - zhdr->middle_chunks) && - !(zhdr->first_chunks && zhdr->last_chunks && - zhdr->middle_chunks)) { - z3fold_compact_page(zhdr); - /* add to unbuddied list */ - spin_lock(&pool->lock); - freechunks = num_free_chunks(zhdr); - list_add(&zhdr->buddy, - &pool->unbuddied[freechunks]); - spin_unlock(&pool->lock); - } - z3fold_page_unlock(zhdr); - spin_lock(&pool->lock); - if (kref_put(&zhdr->refcount, release_z3fold_page)) { - spin_unlock(&pool->lock); - atomic64_dec(&pool->pages_nr); - return 0; } + } else if (kref_put(&zhdr->refcount, release_z3fold_page)) { + atomic64_dec(&pool->pages_nr); + return 0; } + spin_lock(&pool->lock); /* * Add to the beginning of LRU. @@ -795,7 +1003,8 @@ static void *z3fold_zpool_create(const char *name, gfp_t gfp, { struct z3fold_pool *pool; - pool = z3fold_create_pool(gfp, zpool_ops ? &z3fold_zpool_ops : NULL); + pool = z3fold_create_pool(name, gfp, + zpool_ops ? &z3fold_zpool_ops : NULL); if (pool) { pool->zpool = zpool; pool->zpool_ops = zpool_ops; diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c index 308acb9..62457eb 100644 --- a/mm/zsmalloc.c +++ b/mm/zsmalloc.c @@ -1983,8 +1983,11 @@ int zs_page_migrate(struct address_space *mapping, struct page *newpage, spin_lock(&class->lock); if (!get_zspage_inuse(zspage)) { - ret = -EBUSY; - goto unlock_class; + /* + * Set "offset" to end of the page so that every loops + * skips unnecessary object scanning. + */ + offset = PAGE_SIZE; } pos = offset; @@ -2052,7 +2055,6 @@ unpin_objects: } } kunmap_atomic(s_addr); -unlock_class: spin_unlock(&class->lock); migrate_write_unlock(zspage); diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c index 48397fe..b920d18 100644 --- a/scripts/mod/modpost.c +++ b/scripts/mod/modpost.c @@ -261,7 +261,17 @@ static enum export export_no(const char *s) return export_unknown; } -static const char *sec_name(struct elf_info *elf, int secindex); +static const char *sech_name(struct elf_info *elf, Elf_Shdr *sechdr) +{ + return (void *)elf->hdr + + elf->sechdrs[elf->secindex_strings].sh_offset + + sechdr->sh_name; +} + +static const char *sec_name(struct elf_info *elf, int secindex) +{ + return sech_name(elf, &elf->sechdrs[secindex]); +} #define strstarts(str, prefix) (strncmp(str, prefix, strlen(prefix)) == 0) @@ -775,21 +785,6 @@ static const char *sym_name(struct elf_info *elf, Elf_Sym *sym) return "(unknown)"; } -static const char *sec_name(struct elf_info *elf, int secindex) -{ - Elf_Shdr *sechdrs = elf->sechdrs; - return (void *)elf->hdr + - elf->sechdrs[elf->secindex_strings].sh_offset + - sechdrs[secindex].sh_name; -} - -static const char *sech_name(struct elf_info *elf, Elf_Shdr *sechdr) -{ - return (void *)elf->hdr + - elf->sechdrs[elf->secindex_strings].sh_offset + - sechdr->sh_name; -} - /* The pattern is an array of simple patterns. * "foo" will match an exact string equal to "foo" * "*foo" will match a string that ends with "foo" diff --git a/tools/testing/selftests/memfd/Makefile b/tools/testing/selftests/memfd/Makefile index ad8a089..bc9d02d 100644 --- a/tools/testing/selftests/memfd/Makefile +++ b/tools/testing/selftests/memfd/Makefile @@ -3,7 +3,7 @@ CFLAGS += -I../../../../include/uapi/ CFLAGS += -I../../../../include/ CFLAGS += -I../../../../usr/include/ -TEST_PROGS := run_fuse_test.sh +TEST_PROGS := run_tests.sh TEST_GEN_FILES := memfd_test fuse_mnt fuse_test fuse_mnt.o: CFLAGS += $(shell pkg-config fuse --cflags) diff --git a/tools/testing/selftests/memfd/memfd_test.c b/tools/testing/selftests/memfd/memfd_test.c index 2654689..f94c6d1 100644 --- a/tools/testing/selftests/memfd/memfd_test.c +++ b/tools/testing/selftests/memfd/memfd_test.c @@ -18,12 +18,48 @@ #include <sys/wait.h> #include <unistd.h> +#define MEMFD_STR "memfd:" +#define SHARED_FT_STR "(shared file-table)" + #define MFD_DEF_SIZE 8192 #define STACK_SIZE 65536 +/* + * Default is not to test hugetlbfs + */ +static int hugetlbfs_test; +static size_t mfd_def_size = MFD_DEF_SIZE; + +/* + * Copied from mlock2-tests.c + */ +static unsigned long default_huge_page_size(void) +{ + unsigned long hps = 0; + char *line = NULL; + size_t linelen = 0; + FILE *f = fopen("/proc/meminfo", "r"); + + if (!f) + return 0; + while (getline(&line, &linelen, f) > 0) { + if (sscanf(line, "Hugepagesize: %lu kB", &hps) == 1) { + hps <<= 10; + break; + } + } + + free(line); + fclose(f); + return hps; +} + static int sys_memfd_create(const char *name, unsigned int flags) { + if (hugetlbfs_test) + flags |= MFD_HUGETLB; + return syscall(__NR_memfd_create, name, flags); } @@ -150,7 +186,7 @@ static void *mfd_assert_mmap_shared(int fd) void *p; p = mmap(NULL, - MFD_DEF_SIZE, + mfd_def_size, PROT_READ | PROT_WRITE, MAP_SHARED, fd, @@ -168,7 +204,7 @@ static void *mfd_assert_mmap_private(int fd) void *p; p = mmap(NULL, - MFD_DEF_SIZE, + mfd_def_size, PROT_READ, MAP_PRIVATE, fd, @@ -223,7 +259,7 @@ static void mfd_assert_read(int fd) /* verify PROT_READ *is* allowed */ p = mmap(NULL, - MFD_DEF_SIZE, + mfd_def_size, PROT_READ, MAP_PRIVATE, fd, @@ -232,11 +268,11 @@ static void mfd_assert_read(int fd) printf("mmap() failed: %m\n"); abort(); } - munmap(p, MFD_DEF_SIZE); + munmap(p, mfd_def_size); /* verify MAP_PRIVATE is *always* allowed (even writable) */ p = mmap(NULL, - MFD_DEF_SIZE, + mfd_def_size, PROT_READ | PROT_WRITE, MAP_PRIVATE, fd, @@ -245,7 +281,7 @@ static void mfd_assert_read(int fd) printf("mmap() failed: %m\n"); abort(); } - munmap(p, MFD_DEF_SIZE); + munmap(p, mfd_def_size); } static void mfd_assert_write(int fd) @@ -254,16 +290,22 @@ static void mfd_assert_write(int fd) void *p; int r; - /* verify write() succeeds */ - l = write(fd, "\0\0\0\0", 4); - if (l != 4) { - printf("write() failed: %m\n"); - abort(); + /* + * huegtlbfs does not support write, but we want to + * verify everything else here. + */ + if (!hugetlbfs_test) { + /* verify write() succeeds */ + l = write(fd, "\0\0\0\0", 4); + if (l != 4) { + printf("write() failed: %m\n"); + abort(); + } } /* verify PROT_READ | PROT_WRITE is allowed */ p = mmap(NULL, - MFD_DEF_SIZE, + mfd_def_size, PROT_READ | PROT_WRITE, MAP_SHARED, fd, @@ -273,11 +315,11 @@ static void mfd_assert_write(int fd) abort(); } *(char *)p = 0; - munmap(p, MFD_DEF_SIZE); + munmap(p, mfd_def_size); /* verify PROT_WRITE is allowed */ p = mmap(NULL, - MFD_DEF_SIZE, + mfd_def_size, PROT_WRITE, MAP_SHARED, fd, @@ -287,12 +329,12 @@ static void mfd_assert_write(int fd) abort(); } *(char *)p = 0; - munmap(p, MFD_DEF_SIZE); + munmap(p, mfd_def_size); /* verify PROT_READ with MAP_SHARED is allowed and a following * mprotect(PROT_WRITE) allows writing */ p = mmap(NULL, - MFD_DEF_SIZE, + mfd_def_size, PROT_READ, MAP_SHARED, fd, @@ -302,20 +344,20 @@ static void mfd_assert_write(int fd) abort(); } - r = mprotect(p, MFD_DEF_SIZE, PROT_READ | PROT_WRITE); + r = mprotect(p, mfd_def_size, PROT_READ | PROT_WRITE); if (r < 0) { printf("mprotect() failed: %m\n"); abort(); } *(char *)p = 0; - munmap(p, MFD_DEF_SIZE); + munmap(p, mfd_def_size); /* verify PUNCH_HOLE works */ r = fallocate(fd, FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE, 0, - MFD_DEF_SIZE); + mfd_def_size); if (r < 0) { printf("fallocate(PUNCH_HOLE) failed: %m\n"); abort(); @@ -337,7 +379,7 @@ static void mfd_fail_write(int fd) /* verify PROT_READ | PROT_WRITE is not allowed */ p = mmap(NULL, - MFD_DEF_SIZE, + mfd_def_size, PROT_READ | PROT_WRITE, MAP_SHARED, fd, @@ -349,7 +391,7 @@ static void mfd_fail_write(int fd) /* verify PROT_WRITE is not allowed */ p = mmap(NULL, - MFD_DEF_SIZE, + mfd_def_size, PROT_WRITE, MAP_SHARED, fd, @@ -362,13 +404,13 @@ static void mfd_fail_write(int fd) /* Verify PROT_READ with MAP_SHARED with a following mprotect is not * allowed. Note that for r/w the kernel already prevents the mmap. */ p = mmap(NULL, - MFD_DEF_SIZE, + mfd_def_size, PROT_READ, MAP_SHARED, fd, 0); if (p != MAP_FAILED) { - r = mprotect(p, MFD_DEF_SIZE, PROT_READ | PROT_WRITE); + r = mprotect(p, mfd_def_size, PROT_READ | PROT_WRITE); if (r >= 0) { printf("mmap()+mprotect() didn't fail as expected\n"); abort(); @@ -379,7 +421,7 @@ static void mfd_fail_write(int fd) r = fallocate(fd, FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE, 0, - MFD_DEF_SIZE); + mfd_def_size); if (r >= 0) { printf("fallocate(PUNCH_HOLE) didn't fail as expected\n"); abort(); @@ -390,13 +432,13 @@ static void mfd_assert_shrink(int fd) { int r, fd2; - r = ftruncate(fd, MFD_DEF_SIZE / 2); + r = ftruncate(fd, mfd_def_size / 2); if (r < 0) { printf("ftruncate(SHRINK) failed: %m\n"); abort(); } - mfd_assert_size(fd, MFD_DEF_SIZE / 2); + mfd_assert_size(fd, mfd_def_size / 2); fd2 = mfd_assert_open(fd, O_RDWR | O_CREAT | O_TRUNC, @@ -410,7 +452,7 @@ static void mfd_fail_shrink(int fd) { int r; - r = ftruncate(fd, MFD_DEF_SIZE / 2); + r = ftruncate(fd, mfd_def_size / 2); if (r >= 0) { printf("ftruncate(SHRINK) didn't fail as expected\n"); abort(); @@ -425,31 +467,31 @@ static void mfd_assert_grow(int fd) { int r; - r = ftruncate(fd, MFD_DEF_SIZE * 2); + r = ftruncate(fd, mfd_def_size * 2); if (r < 0) { printf("ftruncate(GROW) failed: %m\n"); abort(); } - mfd_assert_size(fd, MFD_DEF_SIZE * 2); + mfd_assert_size(fd, mfd_def_size * 2); r = fallocate(fd, 0, 0, - MFD_DEF_SIZE * 4); + mfd_def_size * 4); if (r < 0) { printf("fallocate(ALLOC) failed: %m\n"); abort(); } - mfd_assert_size(fd, MFD_DEF_SIZE * 4); + mfd_assert_size(fd, mfd_def_size * 4); } static void mfd_fail_grow(int fd) { int r; - r = ftruncate(fd, MFD_DEF_SIZE * 2); + r = ftruncate(fd, mfd_def_size * 2); if (r >= 0) { printf("ftruncate(GROW) didn't fail as expected\n"); abort(); @@ -458,7 +500,7 @@ static void mfd_fail_grow(int fd) r = fallocate(fd, 0, 0, - MFD_DEF_SIZE * 4); + mfd_def_size * 4); if (r >= 0) { printf("fallocate(ALLOC) didn't fail as expected\n"); abort(); @@ -467,25 +509,37 @@ static void mfd_fail_grow(int fd) static void mfd_assert_grow_write(int fd) { - static char buf[MFD_DEF_SIZE * 8]; + static char *buf; ssize_t l; - l = pwrite(fd, buf, sizeof(buf), 0); - if (l != sizeof(buf)) { + buf = malloc(mfd_def_size * 8); + if (!buf) { + printf("malloc(%d) failed: %m\n", mfd_def_size * 8); + abort(); + } + + l = pwrite(fd, buf, mfd_def_size * 8, 0); + if (l != (mfd_def_size * 8)) { printf("pwrite() failed: %m\n"); abort(); } - mfd_assert_size(fd, MFD_DEF_SIZE * 8); + mfd_assert_size(fd, mfd_def_size * 8); } static void mfd_fail_grow_write(int fd) { - static char buf[MFD_DEF_SIZE * 8]; + static char *buf; ssize_t l; - l = pwrite(fd, buf, sizeof(buf), 0); - if (l == sizeof(buf)) { + buf = malloc(mfd_def_size * 8); + if (!buf) { + printf("malloc(%d) failed: %m\n", mfd_def_size * 8); + abort(); + } + + l = pwrite(fd, buf, mfd_def_size * 8, 0); + if (l == (mfd_def_size * 8)) { printf("pwrite() didn't fail as expected\n"); abort(); } @@ -543,6 +597,8 @@ static void test_create(void) char buf[2048]; int fd; + printf("%s CREATE\n", MEMFD_STR); + /* test NULL name */ mfd_fail_new(NULL, 0); @@ -570,13 +626,18 @@ static void test_create(void) fd = mfd_assert_new("", 0, MFD_CLOEXEC); close(fd); - /* verify MFD_ALLOW_SEALING is allowed */ - fd = mfd_assert_new("", 0, MFD_ALLOW_SEALING); - close(fd); - - /* verify MFD_ALLOW_SEALING | MFD_CLOEXEC is allowed */ - fd = mfd_assert_new("", 0, MFD_ALLOW_SEALING | MFD_CLOEXEC); - close(fd); + if (!hugetlbfs_test) { + /* verify MFD_ALLOW_SEALING is allowed */ + fd = mfd_assert_new("", 0, MFD_ALLOW_SEALING); + close(fd); + + /* verify MFD_ALLOW_SEALING | MFD_CLOEXEC is allowed */ + fd = mfd_assert_new("", 0, MFD_ALLOW_SEALING | MFD_CLOEXEC); + close(fd); + } else { + /* sealing is not supported on hugetlbfs */ + mfd_fail_new("", MFD_ALLOW_SEALING); + } } /* @@ -587,8 +648,14 @@ static void test_basic(void) { int fd; + /* hugetlbfs does not contain sealing support */ + if (hugetlbfs_test) + return; + + printf("%s BASIC\n", MEMFD_STR); + fd = mfd_assert_new("kern_memfd_basic", - MFD_DEF_SIZE, + mfd_def_size, MFD_CLOEXEC | MFD_ALLOW_SEALING); /* add basic seals */ @@ -619,7 +686,7 @@ static void test_basic(void) /* verify sealing does not work without MFD_ALLOW_SEALING */ fd = mfd_assert_new("kern_memfd_basic", - MFD_DEF_SIZE, + mfd_def_size, MFD_CLOEXEC); mfd_assert_has_seals(fd, F_SEAL_SEAL); mfd_fail_add_seals(fd, F_SEAL_SHRINK | @@ -630,6 +697,28 @@ static void test_basic(void) } /* + * hugetlbfs doesn't support seals or write, so just verify grow and shrink + * on a hugetlbfs file created via memfd_create. + */ +static void test_hugetlbfs_grow_shrink(void) +{ + int fd; + + printf("%s HUGETLBFS-GROW-SHRINK\n", MEMFD_STR); + + fd = mfd_assert_new("kern_memfd_seal_write", + mfd_def_size, + MFD_CLOEXEC); + + mfd_assert_read(fd); + mfd_assert_write(fd); + mfd_assert_shrink(fd); + mfd_assert_grow(fd); + + close(fd); +} + +/* * Test SEAL_WRITE * Test whether SEAL_WRITE actually prevents modifications. */ @@ -637,8 +726,17 @@ static void test_seal_write(void) { int fd; + /* + * hugetlbfs does not contain sealing or write support. Just test + * basic grow and shrink via test_hugetlbfs_grow_shrink. + */ + if (hugetlbfs_test) + return test_hugetlbfs_grow_shrink(); + + printf("%s SEAL-WRITE\n", MEMFD_STR); + fd = mfd_assert_new("kern_memfd_seal_write", - MFD_DEF_SIZE, + mfd_def_size, MFD_CLOEXEC | MFD_ALLOW_SEALING); mfd_assert_has_seals(fd, 0); mfd_assert_add_seals(fd, F_SEAL_WRITE); @@ -661,8 +759,14 @@ static void test_seal_shrink(void) { int fd; + /* hugetlbfs does not contain sealing support */ + if (hugetlbfs_test) + return; + + printf("%s SEAL-SHRINK\n", MEMFD_STR); + fd = mfd_assert_new("kern_memfd_seal_shrink", - MFD_DEF_SIZE, + mfd_def_size, MFD_CLOEXEC | MFD_ALLOW_SEALING); mfd_assert_has_seals(fd, 0); mfd_assert_add_seals(fd, F_SEAL_SHRINK); @@ -685,8 +789,14 @@ static void test_seal_grow(void) { int fd; + /* hugetlbfs does not contain sealing support */ + if (hugetlbfs_test) + return; + + printf("%s SEAL-GROW\n", MEMFD_STR); + fd = mfd_assert_new("kern_memfd_seal_grow", - MFD_DEF_SIZE, + mfd_def_size, MFD_CLOEXEC | MFD_ALLOW_SEALING); mfd_assert_has_seals(fd, 0); mfd_assert_add_seals(fd, F_SEAL_GROW); @@ -709,8 +819,14 @@ static void test_seal_resize(void) { int fd; + /* hugetlbfs does not contain sealing support */ + if (hugetlbfs_test) + return; + + printf("%s SEAL-RESIZE\n", MEMFD_STR); + fd = mfd_assert_new("kern_memfd_seal_resize", - MFD_DEF_SIZE, + mfd_def_size, MFD_CLOEXEC | MFD_ALLOW_SEALING); mfd_assert_has_seals(fd, 0); mfd_assert_add_seals(fd, F_SEAL_SHRINK | F_SEAL_GROW); @@ -726,15 +842,52 @@ static void test_seal_resize(void) } /* + * hugetlbfs does not support seals. Basic test to dup the memfd created + * fd and perform some basic operations on it. + */ +static void hugetlbfs_dup(char *b_suffix) +{ + int fd, fd2; + + printf("%s HUGETLBFS-DUP %s\n", MEMFD_STR, b_suffix); + + fd = mfd_assert_new("kern_memfd_share_dup", + mfd_def_size, + MFD_CLOEXEC); + + fd2 = mfd_assert_dup(fd); + + mfd_assert_read(fd); + mfd_assert_write(fd); + + mfd_assert_shrink(fd2); + mfd_assert_grow(fd2); + + close(fd2); + close(fd); +} + +/* * Test sharing via dup() * Test that seals are shared between dupped FDs and they're all equal. */ -static void test_share_dup(void) +static void test_share_dup(char *banner, char *b_suffix) { int fd, fd2; + /* + * hugetlbfs does not contain sealing support. Perform some + * basic testing on dup'ed fd instead via hugetlbfs_dup. + */ + if (hugetlbfs_test) { + hugetlbfs_dup(b_suffix); + return; + } + + printf("%s %s %s\n", MEMFD_STR, banner, b_suffix); + fd = mfd_assert_new("kern_memfd_share_dup", - MFD_DEF_SIZE, + mfd_def_size, MFD_CLOEXEC | MFD_ALLOW_SEALING); mfd_assert_has_seals(fd, 0); @@ -768,13 +921,19 @@ static void test_share_dup(void) * Test sealing with active mmap()s * Modifying seals is only allowed if no other mmap() refs exist. */ -static void test_share_mmap(void) +static void test_share_mmap(char *banner, char *b_suffix) { int fd; void *p; + /* hugetlbfs does not contain sealing support */ + if (hugetlbfs_test) + return; + + printf("%s %s %s\n", MEMFD_STR, banner, b_suffix); + fd = mfd_assert_new("kern_memfd_share_mmap", - MFD_DEF_SIZE, + mfd_def_size, MFD_CLOEXEC | MFD_ALLOW_SEALING); mfd_assert_has_seals(fd, 0); @@ -784,14 +943,40 @@ static void test_share_mmap(void) mfd_assert_has_seals(fd, 0); mfd_assert_add_seals(fd, F_SEAL_SHRINK); mfd_assert_has_seals(fd, F_SEAL_SHRINK); - munmap(p, MFD_DEF_SIZE); + munmap(p, mfd_def_size); /* readable ref allows sealing */ p = mfd_assert_mmap_private(fd); mfd_assert_add_seals(fd, F_SEAL_WRITE); mfd_assert_has_seals(fd, F_SEAL_WRITE | F_SEAL_SHRINK); - munmap(p, MFD_DEF_SIZE); + munmap(p, mfd_def_size); + + close(fd); +} + +/* + * Basic test to make sure we can open the hugetlbfs fd via /proc and + * perform some simple operations on it. + */ +static void hugetlbfs_proc_open(char *b_suffix) +{ + int fd, fd2; + + printf("%s HUGETLBFS-PROC-OPEN %s\n", MEMFD_STR, b_suffix); + fd = mfd_assert_new("kern_memfd_share_open", + mfd_def_size, + MFD_CLOEXEC); + + fd2 = mfd_assert_open(fd, O_RDWR, 0); + + mfd_assert_read(fd); + mfd_assert_write(fd); + + mfd_assert_shrink(fd2); + mfd_assert_grow(fd2); + + close(fd2); close(fd); } @@ -801,12 +986,23 @@ static void test_share_mmap(void) * This is *not* like dup(), but like a real separate open(). Make sure the * semantics are as expected and we correctly check for RDONLY / WRONLY / RDWR. */ -static void test_share_open(void) +static void test_share_open(char *banner, char *b_suffix) { int fd, fd2; + /* + * hugetlbfs does not contain sealing support. So test basic + * functionality of using /proc fd via hugetlbfs_proc_open + */ + if (hugetlbfs_test) { + hugetlbfs_proc_open(b_suffix); + return; + } + + printf("%s %s %s\n", MEMFD_STR, banner, b_suffix); + fd = mfd_assert_new("kern_memfd_share_open", - MFD_DEF_SIZE, + mfd_def_size, MFD_CLOEXEC | MFD_ALLOW_SEALING); mfd_assert_has_seals(fd, 0); @@ -841,13 +1037,19 @@ static void test_share_open(void) * Test sharing via fork() * Test whether seal-modifications work as expected with forked childs. */ -static void test_share_fork(void) +static void test_share_fork(char *banner, char *b_suffix) { int fd; pid_t pid; + /* hugetlbfs does not contain sealing support */ + if (hugetlbfs_test) + return; + + printf("%s %s %s\n", MEMFD_STR, banner, b_suffix); + fd = mfd_assert_new("kern_memfd_share_fork", - MFD_DEF_SIZE, + mfd_def_size, MFD_CLOEXEC | MFD_ALLOW_SEALING); mfd_assert_has_seals(fd, 0); @@ -870,40 +1072,40 @@ int main(int argc, char **argv) { pid_t pid; - printf("memfd: CREATE\n"); + if (argc == 2) { + if (!strcmp(argv[1], "hugetlbfs")) { + unsigned long hpage_size = default_huge_page_size(); + + if (!hpage_size) { + printf("Unable to determine huge page size\n"); + abort(); + } + + hugetlbfs_test = 1; + mfd_def_size = hpage_size * 2; + } + } + test_create(); - printf("memfd: BASIC\n"); test_basic(); - printf("memfd: SEAL-WRITE\n"); test_seal_write(); - printf("memfd: SEAL-SHRINK\n"); test_seal_shrink(); - printf("memfd: SEAL-GROW\n"); test_seal_grow(); - printf("memfd: SEAL-RESIZE\n"); test_seal_resize(); - printf("memfd: SHARE-DUP\n"); - test_share_dup(); - printf("memfd: SHARE-MMAP\n"); - test_share_mmap(); - printf("memfd: SHARE-OPEN\n"); - test_share_open(); - printf("memfd: SHARE-FORK\n"); - test_share_fork(); + test_share_dup("SHARE-DUP", ""); + test_share_mmap("SHARE-MMAP", ""); + test_share_open("SHARE-OPEN", ""); + test_share_fork("SHARE-FORK", ""); /* Run test-suite in a multi-threaded environment with a shared * file-table. */ pid = spawn_idle_thread(CLONE_FILES | CLONE_FS | CLONE_VM); - printf("memfd: SHARE-DUP (shared file-table)\n"); - test_share_dup(); - printf("memfd: SHARE-MMAP (shared file-table)\n"); - test_share_mmap(); - printf("memfd: SHARE-OPEN (shared file-table)\n"); - test_share_open(); - printf("memfd: SHARE-FORK (shared file-table)\n"); - test_share_fork(); + test_share_dup("SHARE-DUP", SHARED_FT_STR); + test_share_mmap("SHARE-MMAP", SHARED_FT_STR); + test_share_open("SHARE-OPEN", SHARED_FT_STR); + test_share_fork("SHARE-FORK", SHARED_FT_STR); join_idle_thread(pid); printf("memfd: DONE\n"); diff --git a/tools/testing/selftests/memfd/run_tests.sh b/tools/testing/selftests/memfd/run_tests.sh new file mode 100644 index 0000000..daabb35 --- /dev/null +++ b/tools/testing/selftests/memfd/run_tests.sh @@ -0,0 +1,69 @@ +#!/bin/bash +# please run as root + +# +# Normal tests requiring no special resources +# +./run_fuse_test.sh +./memfd_test + +# +# To test memfd_create with hugetlbfs, there needs to be hpages_test +# huge pages free. Attempt to allocate enough pages to test. +# +hpages_test=8 + +# +# Get count of free huge pages from /proc/meminfo +# +while read name size unit; do + if [ "$name" = "HugePages_Free:" ]; then + freepgs=$size + fi +done < /proc/meminfo + +# +# If not enough free huge pages for test, attempt to increase +# +if [ -n "$freepgs" ] && [ $freepgs -lt $hpages_test ]; then + nr_hugepgs=`cat /proc/sys/vm/nr_hugepages` + hpages_needed=`expr $hpages_test - $freepgs` + + echo 3 > /proc/sys/vm/drop_caches + echo $(( $hpages_needed + $nr_hugepgs )) > /proc/sys/vm/nr_hugepages + if [ $? -ne 0 ]; then + echo "Please run this test as root" + exit 1 + fi + while read name size unit; do + if [ "$name" = "HugePages_Free:" ]; then + freepgs=$size + fi + done < /proc/meminfo +fi + +# +# If still not enough huge pages available, exit. But, give back any huge +# pages potentially allocated above. +# +if [ $freepgs -lt $hpages_test ]; then + # nr_hugepgs non-zero only if we attempted to increase + if [ -n "$nr_hugepgs" ]; then + echo $nr_hugepgs > /proc/sys/vm/nr_hugepages + fi + printf "Not enough huge pages available (%d < %d)\n" \ + $freepgs $needpgs + exit 1 +fi + +# +# Run the hugetlbfs test +# +./memfd_test hugetlbfs + +# +# Give back any huge pages allocated for the test +# +if [ -n "$nr_hugepgs" ]; then + echo $nr_hugepgs > /proc/sys/vm/nr_hugepages +fi diff --git a/tools/testing/selftests/vm/userfaultfd.c b/tools/testing/selftests/vm/userfaultfd.c index 1eae79a..a2c53a3 100644 --- a/tools/testing/selftests/vm/userfaultfd.c +++ b/tools/testing/selftests/vm/userfaultfd.c @@ -66,6 +66,8 @@ #include <sys/wait.h> #include <pthread.h> #include <linux/userfaultfd.h> +#include <setjmp.h> +#include <stdbool.h> #ifdef __NR_userfaultfd @@ -82,11 +84,17 @@ static int bounces; #define TEST_SHMEM 3 static int test_type; +/* exercise the test_uffdio_*_eexist every ALARM_INTERVAL_SECS */ +#define ALARM_INTERVAL_SECS 10 +static volatile bool test_uffdio_copy_eexist = true; +static volatile bool test_uffdio_zeropage_eexist = true; + +static bool map_shared; static int huge_fd; static char *huge_fd_off0; static unsigned long long *count_verify; static int uffd, uffd_flags, finished, *pipefd; -static char *area_src, *area_dst; +static char *area_src, *area_src_alias, *area_dst, *area_dst_alias; static char *zeropage; pthread_attr_t attr; @@ -125,6 +133,9 @@ static void anon_allocate_area(void **alloc_area) } } +static void noop_alias_mapping(__u64 *start, size_t len, unsigned long offset) +{ +} /* HugeTLB memory */ static int hugetlb_release_pages(char *rel_area) @@ -145,17 +156,51 @@ static int hugetlb_release_pages(char *rel_area) static void hugetlb_allocate_area(void **alloc_area) { + void *area_alias = NULL; + char **alloc_area_alias; *alloc_area = mmap(NULL, nr_pages * page_size, PROT_READ | PROT_WRITE, - MAP_PRIVATE | MAP_HUGETLB, huge_fd, - *alloc_area == area_src ? 0 : - nr_pages * page_size); + (map_shared ? MAP_SHARED : MAP_PRIVATE) | + MAP_HUGETLB, + huge_fd, *alloc_area == area_src ? 0 : + nr_pages * page_size); if (*alloc_area == MAP_FAILED) { fprintf(stderr, "mmap of hugetlbfs file failed\n"); *alloc_area = NULL; } - if (*alloc_area == area_src) + if (map_shared) { + area_alias = mmap(NULL, nr_pages * page_size, PROT_READ | PROT_WRITE, + MAP_SHARED | MAP_HUGETLB, + huge_fd, *alloc_area == area_src ? 0 : + nr_pages * page_size); + if (area_alias == MAP_FAILED) { + if (munmap(*alloc_area, nr_pages * page_size) < 0) + perror("hugetlb munmap"), exit(1); + *alloc_area = NULL; + return; + } + } + if (*alloc_area == area_src) { huge_fd_off0 = *alloc_area; + alloc_area_alias = &area_src_alias; + } else { + alloc_area_alias = &area_dst_alias; + } + if (area_alias) + *alloc_area_alias = area_alias; +} + +static void hugetlb_alias_mapping(__u64 *start, size_t len, unsigned long offset) +{ + if (!map_shared) + return; + /* + * We can't zap just the pagetable with hugetlbfs because + * MADV_DONTEED won't work. So exercise -EEXIST on a alias + * mapping where the pagetables are not established initially, + * this way we'll exercise the -EEXEC at the fs level. + */ + *start = (unsigned long) area_dst_alias + offset; } /* Shared memory */ @@ -185,6 +230,7 @@ struct uffd_test_ops { unsigned long expected_ioctls; void (*allocate_area)(void **alloc_area); int (*release_pages)(char *rel_area); + void (*alias_mapping)(__u64 *start, size_t len, unsigned long offset); }; #define ANON_EXPECTED_IOCTLS ((1 << _UFFDIO_WAKE) | \ @@ -195,18 +241,21 @@ static struct uffd_test_ops anon_uffd_test_ops = { .expected_ioctls = ANON_EXPECTED_IOCTLS, .allocate_area = anon_allocate_area, .release_pages = anon_release_pages, + .alias_mapping = noop_alias_mapping, }; static struct uffd_test_ops shmem_uffd_test_ops = { - .expected_ioctls = UFFD_API_RANGE_IOCTLS_BASIC, + .expected_ioctls = ANON_EXPECTED_IOCTLS, .allocate_area = shmem_allocate_area, .release_pages = shmem_release_pages, + .alias_mapping = noop_alias_mapping, }; static struct uffd_test_ops hugetlb_uffd_test_ops = { .expected_ioctls = UFFD_API_RANGE_IOCTLS_BASIC, .allocate_area = hugetlb_allocate_area, .release_pages = hugetlb_release_pages, + .alias_mapping = hugetlb_alias_mapping, }; static struct uffd_test_ops *uffd_test_ops; @@ -331,6 +380,23 @@ static void *locking_thread(void *arg) return NULL; } +static void retry_copy_page(int ufd, struct uffdio_copy *uffdio_copy, + unsigned long offset) +{ + uffd_test_ops->alias_mapping(&uffdio_copy->dst, + uffdio_copy->len, + offset); + if (ioctl(ufd, UFFDIO_COPY, uffdio_copy)) { + /* real retval in ufdio_copy.copy */ + if (uffdio_copy->copy != -EEXIST) + fprintf(stderr, "UFFDIO_COPY retry error %Ld\n", + uffdio_copy->copy), exit(1); + } else { + fprintf(stderr, "UFFDIO_COPY retry unexpected %Ld\n", + uffdio_copy->copy), exit(1); + } +} + static int copy_page(int ufd, unsigned long offset) { struct uffdio_copy uffdio_copy; @@ -351,8 +417,13 @@ static int copy_page(int ufd, unsigned long offset) } else if (uffdio_copy.copy != page_size) { fprintf(stderr, "UFFDIO_COPY unexpected copy %Ld\n", uffdio_copy.copy), exit(1); - } else + } else { + if (test_uffdio_copy_eexist) { + test_uffdio_copy_eexist = false; + retry_copy_page(ufd, &uffdio_copy, offset); + } return 1; + } return 0; } @@ -408,6 +479,7 @@ static void *uffd_poll_thread(void *arg) userfaults++; break; case UFFD_EVENT_FORK: + close(uffd); uffd = msg.arg.fork.ufd; pollfd[0].fd = uffd; break; @@ -572,6 +644,17 @@ static int userfaultfd_open(int features) return 0; } +sigjmp_buf jbuf, *sigbuf; + +static void sighndl(int sig, siginfo_t *siginfo, void *ptr) +{ + if (sig == SIGBUS) { + if (sigbuf) + siglongjmp(*sigbuf, 1); + abort(); + } +} + /* * For non-cooperative userfaultfd test we fork() a process that will * generate pagefaults, will mremap the area monitored by the @@ -585,19 +668,59 @@ static int userfaultfd_open(int features) * The release of the pages currently generates event for shmem and * anonymous memory (UFFD_EVENT_REMOVE), hence it is not checked * for hugetlb. + * For signal test(UFFD_FEATURE_SIGBUS), signal_test = 1, we register + * monitored area, generate pagefaults and test that signal is delivered. + * Use UFFDIO_COPY to allocate missing page and retry. For signal_test = 2 + * test robustness use case - we release monitored area, fork a process + * that will generate pagefaults and verify signal is generated. + * This also tests UFFD_FEATURE_EVENT_FORK event along with the signal + * feature. Using monitor thread, verify no userfault events are generated. */ -static int faulting_process(void) +static int faulting_process(int signal_test) { unsigned long nr; unsigned long long count; unsigned long split_nr_pages; + unsigned long lastnr; + struct sigaction act; + unsigned long signalled = 0; if (test_type != TEST_HUGETLB) split_nr_pages = (nr_pages + 1) / 2; else split_nr_pages = nr_pages; + if (signal_test) { + sigbuf = &jbuf; + memset(&act, 0, sizeof(act)); + act.sa_sigaction = sighndl; + act.sa_flags = SA_SIGINFO; + if (sigaction(SIGBUS, &act, 0)) { + perror("sigaction"); + return 1; + } + lastnr = (unsigned long)-1; + } + for (nr = 0; nr < split_nr_pages; nr++) { + if (signal_test) { + if (sigsetjmp(*sigbuf, 1) != 0) { + if (nr == lastnr) { + fprintf(stderr, "Signal repeated\n"); + return 1; + } + + lastnr = nr; + if (signal_test == 1) { + if (copy_page(uffd, nr * page_size)) + signalled++; + } else { + signalled++; + continue; + } + } + } + count = *area_count(area_dst, nr); if (count != count_verify[nr]) { fprintf(stderr, @@ -607,6 +730,9 @@ static int faulting_process(void) } } + if (signal_test) + return signalled != split_nr_pages; + if (test_type == TEST_HUGETLB) return 0; @@ -636,6 +762,23 @@ static int faulting_process(void) return 0; } +static void retry_uffdio_zeropage(int ufd, + struct uffdio_zeropage *uffdio_zeropage, + unsigned long offset) +{ + uffd_test_ops->alias_mapping(&uffdio_zeropage->range.start, + uffdio_zeropage->range.len, + offset); + if (ioctl(ufd, UFFDIO_ZEROPAGE, uffdio_zeropage)) { + if (uffdio_zeropage->zeropage != -EEXIST) + fprintf(stderr, "UFFDIO_ZEROPAGE retry error %Ld\n", + uffdio_zeropage->zeropage), exit(1); + } else { + fprintf(stderr, "UFFDIO_ZEROPAGE retry unexpected %Ld\n", + uffdio_zeropage->zeropage), exit(1); + } +} + static int uffdio_zeropage(int ufd, unsigned long offset) { struct uffdio_zeropage uffdio_zeropage; @@ -670,8 +813,14 @@ static int uffdio_zeropage(int ufd, unsigned long offset) if (uffdio_zeropage.zeropage != page_size) { fprintf(stderr, "UFFDIO_ZEROPAGE unexpected %Ld\n", uffdio_zeropage.zeropage), exit(1); - } else + } else { + if (test_uffdio_zeropage_eexist) { + test_uffdio_zeropage_eexist = false; + retry_uffdio_zeropage(ufd, &uffdio_zeropage, + offset); + } return 1; + } } else { fprintf(stderr, "UFFDIO_ZEROPAGE succeeded %Ld\n", @@ -761,7 +910,7 @@ static int userfaultfd_events_test(void) perror("fork"), exit(1); if (!pid) - return faulting_process(); + return faulting_process(0); waitpid(pid, &err, 0); if (err) @@ -778,6 +927,72 @@ static int userfaultfd_events_test(void) return userfaults != nr_pages; } +static int userfaultfd_sig_test(void) +{ + struct uffdio_register uffdio_register; + unsigned long expected_ioctls; + unsigned long userfaults; + pthread_t uffd_mon; + int err, features; + pid_t pid; + char c; + + printf("testing signal delivery: "); + fflush(stdout); + + if (uffd_test_ops->release_pages(area_dst)) + return 1; + + features = UFFD_FEATURE_EVENT_FORK|UFFD_FEATURE_SIGBUS; + if (userfaultfd_open(features) < 0) + return 1; + fcntl(uffd, F_SETFL, uffd_flags | O_NONBLOCK); + + uffdio_register.range.start = (unsigned long) area_dst; + uffdio_register.range.len = nr_pages * page_size; + uffdio_register.mode = UFFDIO_REGISTER_MODE_MISSING; + if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register)) + fprintf(stderr, "register failure\n"), exit(1); + + expected_ioctls = uffd_test_ops->expected_ioctls; + if ((uffdio_register.ioctls & expected_ioctls) != + expected_ioctls) + fprintf(stderr, + "unexpected missing ioctl for anon memory\n"), + exit(1); + + if (faulting_process(1)) + fprintf(stderr, "faulting process failed\n"), exit(1); + + if (uffd_test_ops->release_pages(area_dst)) + return 1; + + if (pthread_create(&uffd_mon, &attr, uffd_poll_thread, NULL)) + perror("uffd_poll_thread create"), exit(1); + + pid = fork(); + if (pid < 0) + perror("fork"), exit(1); + + if (!pid) + exit(faulting_process(2)); + + waitpid(pid, &err, 0); + if (err) + fprintf(stderr, "faulting process failed\n"), exit(1); + + if (write(pipefd[1], &c, sizeof(c)) != sizeof(c)) + perror("pipe write"), exit(1); + if (pthread_join(uffd_mon, (void **)&userfaults)) + return 1; + + printf("done.\n"); + if (userfaults) + fprintf(stderr, "Signal test failed, userfaults: %ld\n", + userfaults); + close(uffd); + return userfaults != 0; +} static int userfaultfd_stress(void) { void *area; @@ -879,6 +1094,15 @@ static int userfaultfd_stress(void) return 1; } + if (area_dst_alias) { + uffdio_register.range.start = (unsigned long) + area_dst_alias; + if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register)) { + fprintf(stderr, "register failure alias\n"); + return 1; + } + } + /* * The madvise done previously isn't enough: some * uffd_thread could have read userfaults (one of @@ -912,9 +1136,17 @@ static int userfaultfd_stress(void) /* unregister */ if (ioctl(uffd, UFFDIO_UNREGISTER, &uffdio_register.range)) { - fprintf(stderr, "register failure\n"); + fprintf(stderr, "unregister failure\n"); return 1; } + if (area_dst_alias) { + uffdio_register.range.start = (unsigned long) area_dst; + if (ioctl(uffd, UFFDIO_UNREGISTER, + &uffdio_register.range)) { + fprintf(stderr, "unregister failure alias\n"); + return 1; + } + } /* verification */ if (bounces & BOUNCE_VERIFY) { @@ -936,6 +1168,10 @@ static int userfaultfd_stress(void) area_src = area_dst; area_dst = tmp_area; + tmp_area = area_src_alias; + area_src_alias = area_dst_alias; + area_dst_alias = tmp_area; + printf("userfaults:"); for (cpu = 0; cpu < nr_cpus; cpu++) printf(" %lu", userfaults[cpu]); @@ -946,7 +1182,8 @@ static int userfaultfd_stress(void) return err; close(uffd); - return userfaultfd_zeropage_test() || userfaultfd_events_test(); + return userfaultfd_zeropage_test() || userfaultfd_sig_test() + || userfaultfd_events_test(); } /* @@ -981,7 +1218,12 @@ static void set_test_type(const char *type) } else if (!strcmp(type, "hugetlb")) { test_type = TEST_HUGETLB; uffd_test_ops = &hugetlb_uffd_test_ops; + } else if (!strcmp(type, "hugetlb_shared")) { + map_shared = true; + test_type = TEST_HUGETLB; + uffd_test_ops = &hugetlb_uffd_test_ops; } else if (!strcmp(type, "shmem")) { + map_shared = true; test_type = TEST_SHMEM; uffd_test_ops = &shmem_uffd_test_ops; } else { @@ -1001,12 +1243,25 @@ static void set_test_type(const char *type) fprintf(stderr, "Impossible to run this test\n"), exit(2); } +static void sigalrm(int sig) +{ + if (sig != SIGALRM) + abort(); + test_uffdio_copy_eexist = true; + test_uffdio_zeropage_eexist = true; + alarm(ALARM_INTERVAL_SECS); +} + int main(int argc, char **argv) { if (argc < 4) fprintf(stderr, "Usage: <test type> <MiB> <bounces> [hugetlbfs_file]\n"), exit(1); + if (signal(SIGALRM, sigalrm) == SIG_ERR) + fprintf(stderr, "failed to arm SIGALRM"), exit(1); + alarm(ALARM_INTERVAL_SECS); + set_test_type(argv[1]); nr_cpus = sysconf(_SC_NPROCESSORS_ONLN); |
