diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2023-04-27 19:42:02 -0700 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2023-04-27 19:42:02 -0700 |
| commit | 7fa8a8ee9400fe8ec188426e40e481717bc5e924 (patch) | |
| tree | cc8fd6b4f936ec01e73238643757451e20478c07 /tools | |
| parent | 91ec4b0d11fe115581ce2835300558802ce55e6c (diff) | |
| parent | 4d4b6d66db63ceed399f1fb1a4b24081d2590eb1 (diff) | |
Merge tag 'mm-stable-2023-04-27-15-30' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
Pull MM updates from Andrew Morton:
- Nick Piggin's "shoot lazy tlbs" series, to improve the peformance of
switching from a user process to a kernel thread.
- More folio conversions from Kefeng Wang, Zhang Peng and Pankaj
Raghav.
- zsmalloc performance improvements from Sergey Senozhatsky.
- Yue Zhao has found and fixed some data race issues around the
alteration of memcg userspace tunables.
- VFS rationalizations from Christoph Hellwig:
- removal of most of the callers of write_one_page()
- make __filemap_get_folio()'s return value more useful
- Luis Chamberlain has changed tmpfs so it no longer requires swap
backing. Use `mount -o noswap'.
- Qi Zheng has made the slab shrinkers operate locklessly, providing
some scalability benefits.
- Keith Busch has improved dmapool's performance, making part of its
operations O(1) rather than O(n).
- Peter Xu adds the UFFD_FEATURE_WP_UNPOPULATED feature to userfaultd,
permitting userspace to wr-protect anon memory unpopulated ptes.
- Kirill Shutemov has changed MAX_ORDER's meaning to be inclusive
rather than exclusive, and has fixed a bunch of errors which were
caused by its unintuitive meaning.
- Axel Rasmussen give userfaultfd the UFFDIO_CONTINUE_MODE_WP feature,
which causes minor faults to install a write-protected pte.
- Vlastimil Babka has done some maintenance work on vma_merge():
cleanups to the kernel code and improvements to our userspace test
harness.
- Cleanups to do_fault_around() by Lorenzo Stoakes.
- Mike Rapoport has moved a lot of initialization code out of various
mm/ files and into mm/mm_init.c.
- Lorenzo Stoakes removd vmf_insert_mixed_prot(), which was added for
DRM, but DRM doesn't use it any more.
- Lorenzo has also coverted read_kcore() and vread() to use iterators
and has thereby removed the use of bounce buffers in some cases.
- Lorenzo has also contributed further cleanups of vma_merge().
- Chaitanya Prakash provides some fixes to the mmap selftesting code.
- Matthew Wilcox changes xfs and afs so they no longer take sleeping
locks in ->map_page(), a step towards RCUification of pagefaults.
- Suren Baghdasaryan has improved mmap_lock scalability by switching to
per-VMA locking.
- Frederic Weisbecker has reworked the percpu cache draining so that it
no longer causes latency glitches on cpu isolated workloads.
- Mike Rapoport cleans up and corrects the ARCH_FORCE_MAX_ORDER Kconfig
logic.
- Liu Shixin has changed zswap's initialization so we no longer waste a
chunk of memory if zswap is not being used.
- Yosry Ahmed has improved the performance of memcg statistics
flushing.
- David Stevens has fixed several issues involving khugepaged,
userfaultfd and shmem.
- Christoph Hellwig has provided some cleanup work to zram's IO-related
code paths.
- David Hildenbrand has fixed up some issues in the selftest code's
testing of our pte state changing.
- Pankaj Raghav has made page_endio() unneeded and has removed it.
- Peter Xu contributed some rationalizations of the userfaultfd
selftests.
- Yosry Ahmed has fixed an issue around memcg's page recalim
accounting.
- Chaitanya Prakash has fixed some arm-related issues in the
selftests/mm code.
- Longlong Xia has improved the way in which KSM handles hwpoisoned
pages.
- Peter Xu fixes a few issues with uffd-wp at fork() time.
- Stefan Roesch has changed KSM so that it may now be used on a
per-process and per-cgroup basis.
* tag 'mm-stable-2023-04-27-15-30' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (369 commits)
mm,unmap: avoid flushing TLB in batch if PTE is inaccessible
shmem: restrict noswap option to initial user namespace
mm/khugepaged: fix conflicting mods to collapse_file()
sparse: remove unnecessary 0 values from rc
mm: move 'mmap_min_addr' logic from callers into vm_unmapped_area()
hugetlb: pte_alloc_huge() to replace huge pte_alloc_map()
maple_tree: fix allocation in mas_sparse_area()
mm: do not increment pgfault stats when page fault handler retries
zsmalloc: allow only one active pool compaction context
selftests/mm: add new selftests for KSM
mm: add new KSM process and sysfs knobs
mm: add new api to enable ksm per process
mm: shrinkers: fix debugfs file permissions
mm: don't check VMA write permissions if the PTE/PMD indicates write permissions
migrate_pages_batch: fix statistics for longterm pin retry
userfaultfd: use helper function range_in_vma()
lib/show_mem.c: use for_each_populated_zone() simplify code
mm: correct arg in reclaim_pages()/reclaim_clean_pages_from_list()
fs/buffer: convert create_page_buffers to folio_create_buffers
fs/buffer: add folio_create_empty_buffers helper
...
Diffstat (limited to 'tools')
32 files changed, 3480 insertions, 2166 deletions
diff --git a/tools/include/uapi/linux/prctl.h b/tools/include/uapi/linux/prctl.h index 1312a137f7fb..759b3f53e53f 100644 --- a/tools/include/uapi/linux/prctl.h +++ b/tools/include/uapi/linux/prctl.h @@ -290,4 +290,6 @@ struct prctl_mm_map { #define PR_SET_VMA 0x53564d41 # define PR_SET_VMA_ANON_NAME 0 +#define PR_SET_MEMORY_MERGE 67 +#define PR_GET_MEMORY_MERGE 68 #endif /* _LINUX_PRCTL_H */ diff --git a/tools/testing/memblock/linux/mmzone.h b/tools/testing/memblock/linux/mmzone.h index e65f89b12f1c..134f8eab0768 100644 --- a/tools/testing/memblock/linux/mmzone.h +++ b/tools/testing/memblock/linux/mmzone.h @@ -17,10 +17,10 @@ enum zone_type { }; #define MAX_NR_ZONES __MAX_NR_ZONES -#define MAX_ORDER 11 -#define MAX_ORDER_NR_PAGES (1 << (MAX_ORDER - 1)) +#define MAX_ORDER 10 +#define MAX_ORDER_NR_PAGES (1 << MAX_ORDER) -#define pageblock_order (MAX_ORDER - 1) +#define pageblock_order MAX_ORDER #define pageblock_nr_pages BIT(pageblock_order) #define pageblock_align(pfn) ALIGN((pfn), pageblock_nr_pages) #define pageblock_start_pfn(pfn) ALIGN_DOWN((pfn), pageblock_nr_pages) diff --git a/tools/testing/radix-tree/maple.c b/tools/testing/radix-tree/maple.c index 4c89ff333f6f..9286d3baa12d 100644 --- a/tools/testing/radix-tree/maple.c +++ b/tools/testing/radix-tree/maple.c @@ -55,6 +55,28 @@ struct rcu_reader_struct { struct rcu_test_struct2 *test; }; +static int get_alloc_node_count(struct ma_state *mas) +{ + int count = 1; + struct maple_alloc *node = mas->alloc; + + if (!node || ((unsigned long)node & 0x1)) + return 0; + while (node->node_count) { + count += node->node_count; + node = node->slot[0]; + } + return count; +} + +static void check_mas_alloc_node_count(struct ma_state *mas) +{ + mas_node_count_gfp(mas, MAPLE_ALLOC_SLOTS + 1, GFP_KERNEL); + mas_node_count_gfp(mas, MAPLE_ALLOC_SLOTS + 3, GFP_KERNEL); + MT_BUG_ON(mas->tree, get_alloc_node_count(mas) != mas->alloc->total); + mas_destroy(mas); +} + /* * check_new_node() - Check the creation of new nodes and error path * verification. @@ -69,6 +91,8 @@ static noinline void check_new_node(struct maple_tree *mt) MA_STATE(mas, mt, 0, 0); + check_mas_alloc_node_count(&mas); + /* Try allocating 3 nodes */ mtree_lock(mt); mt_set_non_kernel(0); diff --git a/tools/testing/selftests/memfd/memfd_test.c b/tools/testing/selftests/memfd/memfd_test.c index ae71f15f790d..dba0e8ba002f 100644 --- a/tools/testing/selftests/memfd/memfd_test.c +++ b/tools/testing/selftests/memfd/memfd_test.c @@ -43,6 +43,9 @@ */ static size_t mfd_def_size = MFD_DEF_SIZE; static const char *memfd_str = MEMFD_STR; +static pid_t spawn_newpid_thread(unsigned int flags, int (*fn)(void *)); +static int newpid_thread_fn2(void *arg); +static void join_newpid_thread(pid_t pid); static ssize_t fd2name(int fd, char *buf, size_t bufsize) { @@ -1111,6 +1114,7 @@ static void test_noexec_seal(void) static void test_sysctl_child(void) { int fd; + int pid; printf("%s sysctl 0\n", memfd_str); sysctl_assert_write("0"); @@ -1129,6 +1133,10 @@ static void test_sysctl_child(void) mfd_def_size, MFD_CLOEXEC | MFD_ALLOW_SEALING); + printf("%s child ns\n", memfd_str); + pid = spawn_newpid_thread(CLONE_NEWPID, newpid_thread_fn2); + join_newpid_thread(pid); + mfd_assert_mode(fd, 0666); mfd_assert_has_seals(fd, F_SEAL_EXEC); mfd_fail_chmod(fd, 0777); @@ -1206,12 +1214,6 @@ static void test_sysctl(void) int pid = spawn_newpid_thread(CLONE_NEWPID, newpid_thread_fn); join_newpid_thread(pid); - - printf("%s child ns\n", memfd_str); - sysctl_assert_write("1"); - - pid = spawn_newpid_thread(CLONE_NEWPID, newpid_thread_fn2); - join_newpid_thread(pid); } /* diff --git a/tools/testing/selftests/mm/.gitignore b/tools/testing/selftests/mm/.gitignore index 1f8c36a9fa10..8917455f4f51 100644 --- a/tools/testing/selftests/mm/.gitignore +++ b/tools/testing/selftests/mm/.gitignore @@ -21,7 +21,8 @@ protection_keys protection_keys_32 protection_keys_64 madv_populate -userfaultfd +uffd-stress +uffd-unit-tests mlock-intersect-test mlock-random-test virtual_address_range @@ -36,3 +37,5 @@ split_huge_page_test ksm_tests local_config.h local_config.mk +ksm_functional_tests +mdwe_test diff --git a/tools/testing/selftests/mm/Makefile b/tools/testing/selftests/mm/Makefile index fc35050b5542..23af4633f0f4 100644 --- a/tools/testing/selftests/mm/Makefile +++ b/tools/testing/selftests/mm/Makefile @@ -20,7 +20,7 @@ MACHINE ?= $(shell echo $(uname_M) | sed -e 's/aarch64.*/arm64/' -e 's/ppc64.*/p # Avoid accidental wrong builds, due to built-in rules working just a little # bit too well--but not quite as well as required for our situation here. # -# In other words, "make userfaultfd" is supposed to fail to build at all, +# In other words, "make $SOME_TEST" is supposed to fail to build at all, # because this Makefile only supports either "make" (all), or "make /full/path". # However, the built-in rules, if not suppressed, will pick up CFLAGS and the # initial LDLIBS (but not the target-specific LDLIBS, because those are only @@ -29,36 +29,39 @@ MACHINE ?= $(shell echo $(uname_M) | sed -e 's/aarch64.*/arm64/' -e 's/ppc64.*/p # LDLIBS. MAKEFLAGS += --no-builtin-rules -CFLAGS = -Wall -I $(top_srcdir) $(EXTRA_CFLAGS) $(KHDR_INCLUDES) +CFLAGS = -Wall -I $(top_srcdir) -I $(top_srcdir)/tools/include/uapi $(EXTRA_CFLAGS) $(KHDR_INCLUDES) LDLIBS = -lrt -lpthread -TEST_GEN_FILES = cow -TEST_GEN_FILES += compaction_test -TEST_GEN_FILES += gup_test -TEST_GEN_FILES += hmm-tests -TEST_GEN_FILES += hugetlb-madvise -TEST_GEN_FILES += hugepage-mmap -TEST_GEN_FILES += hugepage-mremap -TEST_GEN_FILES += hugepage-shm -TEST_GEN_FILES += hugepage-vmemmap -TEST_GEN_FILES += khugepaged -TEST_GEN_PROGS = madv_populate -TEST_GEN_FILES += map_fixed_noreplace -TEST_GEN_FILES += map_hugetlb -TEST_GEN_FILES += map_populate -TEST_GEN_FILES += memfd_secret -TEST_GEN_FILES += migration -TEST_GEN_FILES += mlock-random-test -TEST_GEN_FILES += mlock2-tests -TEST_GEN_FILES += mrelease_test -TEST_GEN_FILES += mremap_dontunmap -TEST_GEN_FILES += mremap_test -TEST_GEN_FILES += on-fault-limit -TEST_GEN_FILES += thuge-gen -TEST_GEN_FILES += transhuge-stress -TEST_GEN_FILES += userfaultfd + +TEST_GEN_PROGS = cow +TEST_GEN_PROGS += compaction_test +TEST_GEN_PROGS += gup_test +TEST_GEN_PROGS += hmm-tests +TEST_GEN_PROGS += hugetlb-madvise +TEST_GEN_PROGS += hugepage-mmap +TEST_GEN_PROGS += hugepage-mremap +TEST_GEN_PROGS += hugepage-shm +TEST_GEN_PROGS += hugepage-vmemmap +TEST_GEN_PROGS += khugepaged +TEST_GEN_PROGS += madv_populate +TEST_GEN_PROGS += map_fixed_noreplace +TEST_GEN_PROGS += map_hugetlb +TEST_GEN_PROGS += map_populate +TEST_GEN_PROGS += memfd_secret +TEST_GEN_PROGS += migration +TEST_GEN_PROGS += mkdirty +TEST_GEN_PROGS += mlock-random-test +TEST_GEN_PROGS += mlock2-tests +TEST_GEN_PROGS += mrelease_test +TEST_GEN_PROGS += mremap_dontunmap +TEST_GEN_PROGS += mremap_test +TEST_GEN_PROGS += on-fault-limit +TEST_GEN_PROGS += thuge-gen +TEST_GEN_PROGS += transhuge-stress +TEST_GEN_PROGS += uffd-stress +TEST_GEN_PROGS += uffd-unit-tests TEST_GEN_PROGS += soft-dirty TEST_GEN_PROGS += split_huge_page_test -TEST_GEN_FILES += ksm_tests +TEST_GEN_PROGS += ksm_tests TEST_GEN_PROGS += ksm_functional_tests TEST_GEN_PROGS += mdwe_test @@ -76,41 +79,38 @@ CFLAGS += -no-pie endif ifeq ($(CAN_BUILD_I386),1) -TEST_GEN_FILES += $(BINARIES_32) +TEST_GEN_PROGS += $(BINARIES_32) endif ifeq ($(CAN_BUILD_X86_64),1) -TEST_GEN_FILES += $(BINARIES_64) +TEST_GEN_PROGS += $(BINARIES_64) endif else ifneq (,$(findstring $(MACHINE),ppc64)) -TEST_GEN_FILES += protection_keys +TEST_GEN_PROGS += protection_keys endif endif ifneq (,$(filter $(MACHINE),arm64 ia64 mips64 parisc64 ppc64 riscv64 s390x sparc64 x86_64)) -TEST_GEN_FILES += va_128TBswitch -TEST_GEN_FILES += virtual_address_range -TEST_GEN_FILES += write_to_hugetlbfs +TEST_GEN_PROGS += va_high_addr_switch +TEST_GEN_PROGS += virtual_address_range +TEST_GEN_PROGS += write_to_hugetlbfs endif TEST_PROGS := run_vmtests.sh TEST_FILES := test_vmalloc.sh TEST_FILES += test_hmm.sh -TEST_FILES += va_128TBswitch.sh +TEST_FILES += va_high_addr_switch.sh include ../lib.mk -$(OUTPUT)/cow: vm_util.c -$(OUTPUT)/khugepaged: vm_util.c -$(OUTPUT)/ksm_functional_tests: vm_util.c -$(OUTPUT)/madv_populate: vm_util.c -$(OUTPUT)/soft-dirty: vm_util.c -$(OUTPUT)/split_huge_page_test: vm_util.c -$(OUTPUT)/userfaultfd: vm_util.c +$(TEST_GEN_PROGS): vm_util.c + +$(OUTPUT)/uffd-stress: uffd-common.c +$(OUTPUT)/uffd-unit-tests: uffd-common.c ifeq ($(MACHINE),x86_64) BINARIES_32 := $(patsubst %,$(OUTPUT)/%,$(BINARIES_32)) @@ -161,8 +161,8 @@ warn_32bit_failure: endif endif -# cow_EXTRA_LIBS may get set in local_config.mk, or it may be left empty. -$(OUTPUT)/cow: LDLIBS += $(COW_EXTRA_LIBS) +# IOURING_EXTRA_LIBS may get set in local_config.mk, or it may be left empty. +$(OUTPUT)/cow: LDLIBS += $(IOURING_EXTRA_LIBS) $(OUTPUT)/mlock-random-test $(OUTPUT)/memfd_secret: LDLIBS += -lcap @@ -175,11 +175,11 @@ local_config.mk local_config.h: check_config.sh EXTRA_CLEAN += local_config.mk local_config.h -ifeq ($(COW_EXTRA_LIBS),) +ifeq ($(IOURING_EXTRA_LIBS),) all: warn_missing_liburing warn_missing_liburing: @echo ; \ - echo "Warning: missing liburing support. Some COW tests will be skipped." ; \ + echo "Warning: missing liburing support. Some tests will be skipped." ; \ echo endif diff --git a/tools/testing/selftests/mm/check_config.sh b/tools/testing/selftests/mm/check_config.sh index bcba3af0acea..3954f4746161 100644 --- a/tools/testing/selftests/mm/check_config.sh +++ b/tools/testing/selftests/mm/check_config.sh @@ -21,11 +21,11 @@ $CC -c $tmpfile_c -o $tmpfile_o >/dev/null 2>&1 if [ -f $tmpfile_o ]; then echo "#define LOCAL_CONFIG_HAVE_LIBURING 1" > $OUTPUT_H_FILE - echo "COW_EXTRA_LIBS = -luring" > $OUTPUT_MKFILE + echo "IOURING_EXTRA_LIBS = -luring" > $OUTPUT_MKFILE else echo "// No liburing support found" > $OUTPUT_H_FILE echo "# No liburing support found, so:" > $OUTPUT_MKFILE - echo "COW_EXTRA_LIBS = " >> $OUTPUT_MKFILE + echo "IOURING_EXTRA_LIBS = " >> $OUTPUT_MKFILE fi rm ${tmpname}.* diff --git a/tools/testing/selftests/mm/cow.c b/tools/testing/selftests/mm/cow.c index 0eb2e8180aa5..dc9d6fe86028 100644 --- a/tools/testing/selftests/mm/cow.c +++ b/tools/testing/selftests/mm/cow.c @@ -45,34 +45,6 @@ static size_t hugetlbsizes[10]; static int gup_fd; static bool has_huge_zeropage; -static void detect_thpsize(void) -{ - int fd = open("/sys/kernel/mm/transparent_hugepage/hpage_pmd_size", - O_RDONLY); - size_t size = 0; - char buf[15]; - int ret; - - if (fd < 0) - return; - - ret = pread(fd, buf, sizeof(buf), 0); - if (ret > 0 && ret < sizeof(buf)) { - buf[ret] = 0; - - size = strtoul(buf, NULL, 10); - if (size < pagesize) - size = 0; - if (size > 0) { - thpsize = size; - ksft_print_msg("[INFO] detected THP size: %zu KiB\n", - thpsize / 1024); - } - } - - close(fd); -} - static void detect_huge_zeropage(void) { int fd = open("/sys/kernel/mm/transparent_hugepage/use_zero_page", @@ -1741,7 +1713,10 @@ int main(int argc, char **argv) int err; pagesize = getpagesize(); - detect_thpsize(); + thpsize = read_pmd_pagesize(); + if (thpsize) + ksft_print_msg("[INFO] detected THP size: %zu KiB\n", + thpsize / 1024); detect_hugetlbsizes(); detect_huge_zeropage(); diff --git a/tools/testing/selftests/mm/gup_test.c b/tools/testing/selftests/mm/gup_test.c index e43879291dac..ec2229136384 100644 --- a/tools/testing/selftests/mm/gup_test.c +++ b/tools/testing/selftests/mm/gup_test.c @@ -12,8 +12,7 @@ #include <assert.h> #include <mm/gup_test.h> #include "../kselftest.h" - -#include "util.h" +#include "vm_util.h" #define MB (1UL << 20) @@ -251,7 +250,7 @@ int main(int argc, char **argv) if (touch) { gup.gup_flags |= FOLL_TOUCH; } else { - for (; (unsigned long)p < gup.addr + size; p += PAGE_SIZE) + for (; (unsigned long)p < gup.addr + size; p += psize()) p[0] = 0; } diff --git a/tools/testing/selftests/mm/hugepage-mremap.c b/tools/testing/selftests/mm/hugepage-mremap.c index e53b5eaa8fce..cabd0084f57b 100644 --- a/tools/testing/selftests/mm/hugepage-mremap.c +++ b/tools/testing/selftests/mm/hugepage-mremap.c @@ -23,6 +23,8 @@ #include <linux/userfaultfd.h> #include <sys/ioctl.h> #include <string.h> +#include <stdbool.h> +#include "vm_util.h" #define DEFAULT_LENGTH_MB 10UL #define MB_TO_BYTES(x) (x * 1024 * 1024) @@ -60,7 +62,6 @@ static void register_region_with_uffd(char *addr, size_t len) { long uffd; /* userfaultfd file descriptor */ struct uffdio_api uffdio_api; - struct uffdio_register uffdio_register; /* Create and enable userfaultfd object. */ @@ -96,11 +97,7 @@ static void register_region_with_uffd(char *addr, size_t len) * handling by the userfaultfd object. In mode, we request to track * missing pages (i.e., pages that have not yet been faulted in). */ - - uffdio_register.range.start = (unsigned long)addr; - uffdio_register.range.len = len; - uffdio_register.mode = UFFDIO_REGISTER_MODE_MISSING; - if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register) == -1) { + if (uffd_register(uffd, addr, len, true, false, false)) { perror("ioctl-UFFDIO_REGISTER"); exit(1); } diff --git a/tools/testing/selftests/mm/hugetlb-madvise.c b/tools/testing/selftests/mm/hugetlb-madvise.c index 9a127a8fe176..28426e30d9bc 100644 --- a/tools/testing/selftests/mm/hugetlb-madvise.c +++ b/tools/testing/selftests/mm/hugetlb-madvise.c @@ -18,6 +18,7 @@ #include <unistd.h> #include <sys/mman.h> #include <fcntl.h> +#include "vm_util.h" #define MIN_FREE_PAGES 20 #define NR_HUGE_PAGES 10 /* common number of pages to map/allocate */ @@ -35,30 +36,6 @@ unsigned long huge_page_size; unsigned long base_page_size; -/* - * default_huge_page_size copied from mlock2-tests.c - */ -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; -} - unsigned long get_free_hugepages(void) { unsigned long fhp = 0; diff --git a/tools/testing/selftests/mm/khugepaged.c b/tools/testing/selftests/mm/khugepaged.c index 64126c8cd561..97adc0f34f9c 100644 --- a/tools/testing/selftests/mm/khugepaged.c +++ b/tools/testing/selftests/mm/khugepaged.c @@ -1476,6 +1476,10 @@ int main(int argc, const char **argv) page_size = getpagesize(); hpage_pmd_size = read_pmd_pagesize(); + if (!hpage_pmd_size) { + printf("Reading PMD pagesize failed"); + exit(EXIT_FAILURE); + } hpage_pmd_nr = hpage_pmd_size / page_size; default_settings.khugepaged.max_ptes_none = hpage_pmd_nr - 1; diff --git a/tools/testing/selftests/mm/ksm_functional_tests.c b/tools/testing/selftests/mm/ksm_functional_tests.c index d8b5b4930412..7bc9fc17c9f0 100644 --- a/tools/testing/selftests/mm/ksm_functional_tests.c +++ b/tools/testing/selftests/mm/ksm_functional_tests.c @@ -15,8 +15,10 @@ #include <errno.h> #include <fcntl.h> #include <sys/mman.h> +#include <sys/prctl.h> #include <sys/syscall.h> #include <sys/ioctl.h> +#include <sys/wait.h> #include <linux/userfaultfd.h> #include "../kselftest.h" @@ -178,7 +180,6 @@ unmap: static void test_unmerge_uffd_wp(void) { struct uffdio_writeprotect uffd_writeprotect; - struct uffdio_register uffdio_register; const unsigned int size = 2 * MiB; struct uffdio_api uffdio_api; char *map; @@ -210,10 +211,7 @@ static void test_unmerge_uffd_wp(void) } /* Register UFFD-WP, no need for an actual handler. */ - uffdio_register.range.start = (unsigned long) map; - uffdio_register.range.len = size; - uffdio_register.mode = UFFDIO_REGISTER_MODE_WP; - if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register) < 0) { + if (uffd_register(uffd, map, size, false, true, false)) { ksft_test_result_fail("UFFDIO_REGISTER_MODE_WP failed\n"); goto close_uffd; } @@ -241,9 +239,93 @@ unmap: } #endif +/* Verify that KSM can be enabled / queried with prctl. */ +static void test_prctl(void) +{ + int ret; + + ksft_print_msg("[RUN] %s\n", __func__); + + ret = prctl(PR_SET_MEMORY_MERGE, 1, 0, 0, 0); + if (ret < 0 && errno == EINVAL) { + ksft_test_result_skip("PR_SET_MEMORY_MERGE not supported\n"); + return; + } else if (ret) { + ksft_test_result_fail("PR_SET_MEMORY_MERGE=1 failed\n"); + return; + } + + ret = prctl(PR_GET_MEMORY_MERGE, 0, 0, 0, 0); + if (ret < 0) { + ksft_test_result_fail("PR_GET_MEMORY_MERGE failed\n"); + return; + } else if (ret != 1) { + ksft_test_result_fail("PR_SET_MEMORY_MERGE=1 not effective\n"); + return; + } + + ret = prctl(PR_SET_MEMORY_MERGE, 0, 0, 0, 0); + if (ret) { + ksft_test_result_fail("PR_SET_MEMORY_MERGE=0 failed\n"); + return; + } + + ret = prctl(PR_GET_MEMORY_MERGE, 0, 0, 0, 0); + if (ret < 0) { + ksft_test_result_fail("PR_GET_MEMORY_MERGE failed\n"); + return; + } else if (ret != 0) { + ksft_test_result_fail("PR_SET_MEMORY_MERGE=0 not effective\n"); + return; + } + + ksft_test_result_pass("Setting/clearing PR_SET_MEMORY_MERGE works\n"); +} + +/* Verify that prctl ksm flag is inherited. */ +static void test_prctl_fork(void) +{ + int ret, status; + pid_t child_pid; + + ksft_print_msg("[RUN] %s\n", __func__); + + ret = prctl(PR_SET_MEMORY_MERGE, 1, 0, 0, 0); + if (ret < 0 && errno == EINVAL) { + ksft_test_result_skip("PR_SET_MEMORY_MERGE not supported\n"); + return; + } else if (ret) { + ksft_test_result_fail("PR_SET_MEMORY_MERGE=1 failed\n"); + return; + } + + child_pid = fork(); + if (!child_pid) { + exit(prctl(PR_GET_MEMORY_MERGE, 0, 0, 0, 0)); + } else if (child_pid < 0) { + ksft_test_result_fail("fork() failed\n"); + return; + } + + if (waitpid(child_pid, &status, 0) < 0) { + ksft_test_result_fail("waitpid() failed\n"); + return; + } else if (WEXITSTATUS(status) != 1) { + ksft_test_result_fail("unexpected PR_GET_MEMORY_MERGE result in child\n"); + return; + } + + if (prctl(PR_SET_MEMORY_MERGE, 0, 0, 0, 0)) { + ksft_test_result_fail("PR_SET_MEMORY_MERGE=0 failed\n"); + return; + } + + ksft_test_result_pass("PR_SET_MEMORY_MERGE value is inherited\n"); +} + int main(int argc, char **argv) { - unsigned int tests = 2; + unsigned int tests = 4; int err; #ifdef __NR_userfaultfd @@ -271,6 +353,9 @@ int main(int argc, char **argv) test_unmerge_uffd_wp(); #endif + test_prctl(); + test_prctl_fork(); + err = ksft_get_fail_cnt(); if (err) ksft_exit_fail_msg("%d out of %d tests failed\n", diff --git a/tools/testing/selftests/mm/ksm_tests.c b/tools/testing/selftests/mm/ksm_tests.c index f9eb4d67e0dd..435acebdc325 100644 --- a/tools/testing/selftests/mm/ksm_tests.c +++ b/tools/testing/selftests/mm/ksm_tests.c @@ -1,6 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 #include <sys/mman.h> +#include <sys/prctl.h> +#include <sys/wait.h> #include <stdbool.h> #include <time.h> #include <string.h> @@ -12,7 +14,7 @@ #include "../kselftest.h" #include <include/vdso/time64.h> -#include "util.h" +#include "vm_util.h" #define KSM_SYSFS_PATH "/sys/kernel/mm/ksm/" #define KSM_FP(s) (KSM_SYSFS_PATH s) @@ -21,6 +23,7 @@ #define KSM_PROT_STR_DEFAULT "rw" #define KSM_USE_ZERO_PAGES_DEFAULT false #define KSM_MERGE_ACROSS_NODES_DEFAULT true +#define KSM_MERGE_TYPE_DEFAULT 0 #define MB (1ul << 20) struct ksm_sysfs { @@ -33,9 +36,16 @@ struct ksm_sysfs { unsigned long use_zero_pages; }; +enum ksm_merge_type { + KSM_MERGE_MADVISE, + KSM_MERGE_PRCTL, + KSM_MERGE_LAST = KSM_MERGE_PRCTL +}; + enum ksm_test_name { CHECK_KSM_MERGE, CHECK_KSM_UNMERGE, + CHECK_KSM_GET_MERGE_TYPE, CHECK_KSM_ZERO_PAGE_MERGE, CHECK_KSM_NUMA_MERGE, KSM_MERGE_TIME, @@ -44,6 +54,8 @@ enum ksm_test_name { KSM_COW_TIME }; +int debug; + static int ksm_write_sysfs(const char *file_path, unsigned long val) { FILE *f = fopen(file_path, "w"); @@ -82,6 +94,53 @@ static int ksm_read_sysfs(const char *file_path, unsigned long *val) return 0; } +static void ksm_print_sysfs(void) +{ + unsigned long max_page_sharing, pages_sharing, pages_shared; + unsigned long full_scans, pages_unshared, pages_volatile; + unsigned long stable_node_chains, stable_node_dups; + long general_profit; + + if (ksm_read_sysfs(KSM_FP("pages_shared"), &pages_shared) || + ksm_read_sysfs(KSM_FP("pages_sharing"), &pages_sharing) || + ksm_read_sysfs(KSM_FP("max_page_sharing"), &max_page_sharing) || + ksm_read_sysfs(KSM_FP("full_scans"), &full_scans) || + ksm_read_sysfs(KSM_FP("pages_unshared"), &pages_unshared) || + ksm_read_sysfs(KSM_FP("pages_volatile"), &pages_volatile) || + ksm_read_sysfs(KSM_FP("stable_node_chains"), &stable_node_chains) || + ksm_read_sysfs(KSM_FP("stable_node_dups"), &stable_node_dups) || + ksm_read_sysfs(KSM_FP("general_profit"), (unsigned long *)&general_profit)) + return; + + printf("pages_shared : %lu\n", pages_shared); + printf("pages_sharing : %lu\n", pages_sharing); + printf("max_page_sharing : %lu\n", max_page_sharing); + printf("full_scans : %lu\n", full_scans); + printf("pages_unshared : %lu\n", pages_unshared); + printf("pages_volatile : %lu\n", pages_volatile); + printf("stable_node_chains: %lu\n", stable_node_chains); + printf("stable_node_dups : %lu\n", stable_node_dups); + printf("general_profit : %ld\n", general_profit); +} + +static void ksm_print_procfs(void) +{ + const char *file_name = "/proc/self/ksm_stat"; + char buffer[512]; + FILE *f = fopen(file_name, "r"); + + if (!f) { + fprintf(stderr, "f %s\n", file_name); + perror("fopen"); + return; + } + + while (fgets(buffer, sizeof(buffer), f)) + printf("%s", buffer); + + fclose(f); +} + static int str_to_prot(char *prot_str) { int prot = 0; @@ -128,7 +187,12 @@ static void print_help(void) " Default: %d\n", KSM_USE_ZERO_PAGES_DEFAULT); printf(" -m: change merge_across_nodes tunable\n" " Default: %d\n", KSM_MERGE_ACROSS_NODES_DEFAULT); + printf(" -d: turn debugging output on\n"); printf(" -s: the size of duplicated memory area (in MiB)\n"); + printf(" -t: KSM merge type\n" + " Default: 0\n" + " 0: madvise merging\n" + " 1: prctl merging\n"); exit(0); } @@ -176,12 +240,21 @@ static int ksm_do_scan(int scan_count, struct timespec start_time, int timeout) return 0; } -static int ksm_merge_pages(void *addr, size_t size, struct timespec start_time, int timeout) +static int ksm_merge_pages(int merge_type, void *addr, size_t size, + struct timespec start_time, int timeout) { - if (madvise(addr, size, MADV_MERGEABLE)) { - perror("madvise"); - return 1; + if (merge_type == KSM_MERGE_MADVISE) { + if (madvise(addr, size, MADV_MERGEABLE)) { + perror("madvise"); + return 1; + } + } else if (merge_type == KSM_MERGE_PRCTL) { + if (prctl(PR_SET_MEMORY_MERGE, 1, 0, 0, 0)) { + perror("prctl"); + return 1; + } } + if (ksm_write_sysfs(KSM_FP("run"), 1)) return 1; @@ -211,6 +284,11 @@ static bool assert_ksm_pages_count(long dupl_page_count) ksm_read_sysfs(KSM_FP("max_page_sharing"), &max_page_sharing)) return false; + if (debug) { + ksm_print_sysfs(); + ksm_print_procfs(); + } + /* * Since there must be at least 2 pages for merging and 1 page can be * shared with the limited number of pages (max_page_sharing), sometimes @@ -266,7 +344,8 @@ static int ksm_restore(struct ksm_sysfs *ksm_sysfs) return 0; } -static int check_ksm_merge(int mapping, int prot, long page_count, int timeout, size_t page_size) +static int check_ksm_merge(int merge_type, int mapping, int prot, + long page_count, int timeout, size_t page_size) { void *map_ptr; struct timespec start_time; @@ -281,13 +360,15 @@ static int check_ksm_merge(int mapping, int prot, long page_count, int timeout, if (!map_ptr) return KSFT_FAIL; - if (ksm_merge_pages(map_ptr, page_size * page_count, start_time, timeout)) + if (ksm_merge_pages(merge_type, map_ptr, page_size * page_count, start_time, timeout)) goto err_out; /* verify that the right number of pages are merged */ if (assert_ksm_pages_count(page_count)) { printf("OK\n"); munmap(map_ptr, page_size * page_count); + if (merge_type == KSM_MERGE_PRCTL) + prctl(PR_SET_MEMORY_MERGE, 0, 0, 0, 0); return KSFT_PASS; } @@ -297,7 +378,7 @@ err_out: return KSFT_FAIL; } -static int check_ksm_unmerge(int mapping, int prot, int timeout, size_t page_size) +static int check_ksm_unmerge(int merge_type, int mapping, int prot, int timeout, size_t page_size) { void *map_ptr; struct timespec start_time; @@ -313,7 +394,7 @@ static int check_ksm_unmerge(int mapping, int prot, int timeout, size_t page_siz if (!map_ptr) return KSFT_FAIL; - if (ksm_merge_pages(map_ptr, page_size * page_count, start_time, timeout)) + if (ksm_merge_pages(merge_type, map_ptr, page_size * page_count, start_time, timeout)) goto err_out; /* change 1 byte in each of the 2 pages -- KSM must automatically unmerge them */ @@ -337,8 +418,8 @@ err_out: return KSFT_FAIL; } -static int check_ksm_zero_page_merge(int mapping, int prot, long page_count, int timeout, - bool use_zero_pages, size_t page_size) +static int check_ksm_zero_page_merge(int merge_type, int mapping, int prot, long page_count, + int timeout, bool use_zero_pages, size_t page_size) { void *map_ptr; struct timespec start_time; @@ -356,7 +437,7 @@ static int check_ksm_zero_page_merge(int mapping, int prot, long page_count, int if (!map_ptr) return KSFT_FAIL; - if (ksm_merge_pages(map_ptr, page_size * page_count, start_time, timeout)) + if (ksm_merge_pages(merge_type, map_ptr, page_size * page_count, start_time, timeout)) goto err_out; /* @@ -402,8 +483,8 @@ static int get_first_mem_node(void) return get_next_mem_node(numa_max_node()); } -static int check_ksm_numa_merge(int mapping, int prot, int timeout, bool merge_across_nodes, - size_t page_size) +static int check_ksm_numa_merge(int merge_type, int mapping, int prot, int timeout, + bool merge_across_nodes, size_t page_size) { void *numa1_map_ptr, *numa2_map_ptr; struct timespec start_time; @@ -439,8 +520,8 @@ static int check_ksm_numa_merge(int mapping, int prot, int timeout, bool merge_a memset(numa2_map_ptr, '*', page_size); /* try to merge the pages */ - if (ksm_merge_pages(numa1_map_ptr, page_size, start_time, timeout) || - ksm_merge_pages(numa2_map_ptr, page_size, start_time, timeout)) + if (ksm_merge_pages(merge_type, numa1_map_ptr, page_size, start_time, timeout) || + ksm_merge_pages(merge_type, numa2_map_ptr, page_size, start_time, timeout)) goto err_out; /* @@ -466,7 +547,8 @@ err_out: return KSFT_FAIL; } -static int ksm_merge_hugepages_time(int mapping, int prot, int timeout, size_t map_size) +static int ksm_merge_hugepages_time(int merge_type, int mapping, int prot, + int timeout, size_t map_size) { void *map_ptr, *map_ptr_orig; struct timespec start_time, end_time; @@ -508,7 +590,7 @@ static int ksm_merge_hugepages_time(int mapping, int prot, int timeout, size_t m perror("clock_gettime"); goto err_out; } - if (ksm_merge_pages(map_ptr, map_size, start_time, timeout)) + if (ksm_merge_pages(merge_type, map_ptr, map_size, start_time, timeout)) goto err_out; if (clock_gettime(CLOCK_MONOTONIC_RAW, &end_time)) { perror("clock_gettime"); @@ -533,7 +615,7 @@ err_out: return KSFT_FAIL; } -static int ksm_merge_time(int mapping, int prot, int timeout, size_t map_size) +static int ksm_merge_time(int merge_type, int mapping, int prot, int timeout, size_t map_size) { void *map_ptr; struct timespec start_time, end_time; @@ -549,7 +631,7 @@ static int ksm_merge_time(int mapping, int prot, int timeout, size_t map_size) perror("clock_gettime"); goto err_out; } - if (ksm_merge_pages(map_ptr, map_size, start_time, timeout)) + if (ksm_merge_pages(merge_type, map_ptr, map_size, start_time, timeout)) goto err_out; if (clock_gettime(CLOCK_MONOTONIC_RAW, &end_time)) { perror("clock_gettime"); @@ -574,7 +656,7 @@ err_out: return KSFT_FAIL; } -static int ksm_unmerge_time(int mapping, int prot, int timeout, size_t map_size) +static int ksm_unmerge_time(int merge_type, int mapping, int prot, int timeout, size_t map_size) { void *map_ptr; struct timespec start_time, end_time; @@ -589,7 +671,7 @@ static int ksm_unmerge_time(int mapping, int prot, int timeout, size_t map_size) perror("clock_gettime"); goto err_out; } - if (ksm_merge_pages(map_ptr, map_size, start_time, timeout)) + if (ksm_merge_pages(merge_type, map_ptr, map_size, start_time, timeout)) goto err_out; if (clock_gettime(CLOCK_MONOTONIC_RAW, &start_time)) { @@ -621,7 +703,7 @@ err_out: return KSFT_FAIL; } -static int ksm_cow_time(int mapping, int prot, int timeout, size_t page_size) +static int ksm_cow_time(int merge_type, int mapping, int prot, int timeout, size_t page_size) { void *map_ptr; struct timespec start_time, end_time; @@ -660,7 +742,7 @@ static int ksm_cow_time(int mapping, int prot, int timeout, size_t page_size) memset(map_ptr + page_size * i, '+', i / 2 + 1); memset(map_ptr + page_size * (i + 1), '+', i / 2 + 1); } - if (ksm_merge_pages(map_ptr, page_size * page_count, start_time, timeout)) + if (ksm_merge_pages(merge_type, map_ptr, page_size * page_count, start_time, timeout)) goto err_out; if (clock_gettime(CLOCK_MONOTONIC_RAW, &start_time)) { @@ -697,6 +779,7 @@ int main(int argc, char *argv[]) int ret, opt; int prot = 0; int ksm_scan_limit_sec = KSM_SCAN_LIMIT_SEC_DEFAULT; + int merge_type = KSM_MERGE_TYPE_DEFAULT; long page_count = KSM_PAGE_COUNT_DEFAULT; size_t page_size = sysconf(_SC_PAGESIZE); struct ksm_sysfs ksm_sysfs_old; @@ -705,7 +788,7 @@ int main(int argc, char *argv[]) bool merge_across_nodes = KSM_MERGE_ACROSS_NODES_DEFAULT; long size_MB = 0; - while ((opt = getopt(argc, argv, "ha:p:l:z:m:s:MUZNPCHD")) != -1) { + while ((opt = getopt(argc, argv, "dha:p:l:z:m:s:t:MUZNPCHD")) != -1) { switch (opt) { case 'a': prot = str_to_prot(optarg); @@ -739,12 +822,26 @@ int main(int argc, char *argv[]) else merge_across_nodes = 1; break; + case 'd': + debug = 1; + break; case 's': size_MB = atoi(optarg); if (size_MB <= 0) { printf("Size must be greater than 0\n"); return KSFT_FAIL; } + case 't': + { + int tmp = atoi(optarg); + + if (tmp < 0 || tmp > KSM_MERGE_LAST) { + printf("Invalid merge type\n"); + return KSFT_FAIL; + } + merge_type = tmp; + } + break; case 'M': break; case 'U': @@ -795,35 +892,36 @@ int main(int argc, char *argv[]) switch (test_name) { case CHECK_KSM_MERGE: - ret = check_ksm_merge(MAP_PRIVATE | MAP_ANONYMOUS, prot, page_count, + ret = check_ksm_merge(merge_type, MAP_PRIVATE | MAP_ANONYMOUS, prot, page_count, ksm_scan_limit_sec, page_size); break; case CHECK_KSM_UNMERGE: - ret = check_ksm_unmerge(MAP_PRIVATE | MAP_ANONYMOUS, prot, ksm_scan_limit_sec, - page_size); + ret = check_ksm_unmerge(merge_type, MAP_PRIVATE | MAP_ANONYMOUS, prot, + ksm_scan_limit_sec, page_size); break; case CHECK_KSM_ZERO_PAGE_MERGE: - ret = check_ksm_zero_page_merge(MAP_PRIVATE | MAP_ANONYMOUS, prot, page_count, - ksm_scan_limit_sec, use_zero_pages, page_size); + ret = check_ksm_zero_page_merge(merge_type, MAP_PRIVATE | MAP_ANONYMOUS, prot, + page_count, ksm_scan_limit_sec, use_zero_pages, + page_size); break; case CHECK_KSM_NUMA_MERGE: - ret = check_ksm_numa_merge(MAP_PRIVATE | MAP_ANONYMOUS, prot, ksm_scan_limit_sec, - merge_across_nodes, page_size); + ret = check_ksm_numa_merge(merge_type, MAP_PRIVATE | MAP_ANONYMOUS, prot, + ksm_scan_limit_sec, merge_across_nodes, page_size); break; case KSM_MERGE_TIME: if (size_MB == 0) { printf("Option '-s' is required.\n"); return KSFT_FAIL; } - ret = ksm_merge_time(MAP_PRIVATE | MAP_ANONYMOUS, prot, ksm_scan_limit_sec, - size_MB); + ret = ksm_merge_time(merge_type, MAP_PRIVATE | MAP_ANONYMOUS, prot, + ksm_scan_limit_sec, size_MB); break; case KSM_MERGE_TIME_HUGE_PAGES: if (size_MB == 0) { printf("Option '-s' is required.\n"); return KSFT_FAIL; } - ret = ksm_merge_hugepages_time(MAP_PRIVATE | MAP_ANONYMOUS, prot, + ret = ksm_merge_hugepages_time(merge_type, MAP_PRIVATE | MAP_ANONYMOUS, prot, ksm_scan_limit_sec, size_MB); break; case KSM_UNMERGE_TIME: @@ -831,12 +929,12 @@ int main(int argc, char *argv[]) printf("Option '-s' is required.\n"); return KSFT_FAIL; } - ret = ksm_unmerge_time(MAP_PRIVATE | MAP_ANONYMOUS, prot, + ret = ksm_unmerge_time(merge_type, MAP_PRIVATE | MAP_ANONYMOUS, prot, ksm_scan_limit_sec, size_MB); break; case KSM_COW_TIME: - ret = ksm_cow_time(MAP_PRIVATE | MAP_ANONYMOUS, prot, ksm_scan_limit_sec, - page_size); + ret = ksm_cow_time(merge_type, MAP_PRIVATE | MAP_ANONYMOUS, prot, + ksm_scan_limit_sec, page_size); break; } diff --git a/tools/testing/selftests/mm/mkdirty.c b/tools/testing/selftests/mm/mkdirty.c new file mode 100644 index 000000000000..6d71d972997b --- /dev/null +++ b/tools/testing/selftests/mm/mkdirty.c @@ -0,0 +1,379 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Test handling of code that might set PTE/PMD dirty in read-only VMAs. + * Setting a PTE/PMD dirty must not accidentally set the PTE/PMD writable. + * + * Copyright 2023, Red Hat, Inc. + * + * Author(s): David Hildenbrand <david@redhat.com> + */ +#include <fcntl.h> +#include <signal.h> +#include <unistd.h> +#include <string.h> +#include <errno.h> +#include <stdlib.h> +#include <stdbool.h> +#include <stdint.h> +#include <sys/mman.h> +#include <setjmp.h> +#include <sys/syscall.h> +#include <sys/ioctl.h> +#include <linux/userfaultfd.h> +#include <linux/mempolicy.h> + +#include "../kselftest.h" +#include "vm_util.h" + +static size_t pagesize; +static size_t thpsize; +static int mem_fd; +static int pagemap_fd; +static sigjmp_buf env; + +static void signal_handler(int sig) +{ + if (sig == SIGSEGV) + siglongjmp(env, 1); + siglongjmp(env, 2); +} + +static void do_test_write_sigsegv(char *mem) +{ + char orig = *mem; + int ret; + + if (signal(SIGSEGV, signal_handler) == SIG_ERR) { + ksft_test_result_fail("signal() failed\n"); + return; + } + + ret = sigsetjmp(env, 1); + if (!ret) + *mem = orig + 1; + + if (signal(SIGSEGV, SIG_DFL) == SIG_ERR) + ksft_test_result_fail("signal() failed\n"); + + ksft_test_result(ret == 1 && *mem == orig, + "SIGSEGV generated, page not modified\n"); +} + +static char *mmap_thp_range(int prot, char **_mmap_mem, size_t *_mmap_size) +{ + const size_t mmap_size = 2 * thpsize; + char *mem, *mmap_mem; + + mmap_mem = mmap(NULL, mmap_size, prot, MAP_PRIVATE|MAP_ANON, + -1, 0); + if (mmap_mem == MAP_FAILED) { + ksft_test_result_fail("mmap() failed\n"); + return MAP_FAILED; + } + mem = (char *)(((uintptr_t)mmap_mem + thpsize) & ~(thpsize - 1)); + + if (madvise(mem, thpsize, MADV_HUGEPAGE)) { + ksft_test_result_skip("MADV_HUGEPAGE failed\n"); + munmap(mmap_mem, mmap_size); + return MAP_FAILED; + } + + *_mmap_mem = mmap_mem; + *_mmap_size = mmap_size; + return mem; +} + +static void test_ptrace_write(void) +{ + char data = 1; + char *mem; + int ret; + + ksft_print_msg("[INFO] PTRACE write access\n"); + + mem = mmap(NULL, pagesize, PROT_READ, MAP_PRIVATE|MAP_ANON, -1, 0); + if (mem == MAP_FAILED) { + ksft_test_result_fail("mmap() failed\n"); + return; + } + + /* Fault in the shared zeropage. */ + if (*mem != 0) { + ksft_test_result_fail("Memory not zero\n"); + goto munmap; + } + + /* + * Unshare the page (populating a fresh anon page that might be set + * dirty in the PTE) in the read-only VMA using ptrace (FOLL_FORCE). + */ + lseek(mem_fd, (uintptr_t) mem, SEEK_SET); + ret = write(mem_fd, &data, 1); + if (ret != 1 || *mem != data) { + ksft_test_result_fail("write() failed\n"); + goto munmap; + } + + do_test_write_sigsegv(mem); +munmap: + munmap(mem, pagesize); +} + +static void test_ptrace_write_thp(void) +{ + char *mem, *mmap_mem; + size_t mmap_size; + char data = 1; + int ret; + + ksft_print_msg("[INFO] PTRACE write access to THP\n"); + + mem = mmap_thp_range(PROT_READ, &mmap_mem, &mmap_size); + if (mem == MAP_FAILED) + return; + + /* + * Write to the first subpage in the read-only VMA using + * ptrace(FOLL_FORCE), eventually placing a fresh THP that is marked + * dirty in the PMD. + */ + lseek(mem_fd, (uintptr_t) mem, SEEK_SET); + ret = write(mem_fd, &data, 1); + if (ret != 1 || *mem != data) { + ksft_test_result_fail("write() failed\n"); + goto munmap; + } + + /* MM populated a THP if we got the last subpage populated as well. */ + if (!pagemap_is_populated(pagemap_fd, mem + thpsize - pagesize)) { + ksft_test_result_skip("Did not get a THP populated\n"); + goto munmap; + } + + do_test_write_sigsegv(mem); +munmap: + munmap(mmap_mem, mmap_size); +} + +static void test_page_migration(void) +{ + char *mem; + + ksft_print_msg("[INFO] Page migration\n"); + + mem = mmap(NULL, pagesize, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANON, + -1, 0); + if (mem == MAP_FAILED) { + ksft_test_result_fail("mmap() failed\n"); + return; + } + + /* Populate a fresh page and dirty it. */ + memset(mem, 1, pagesize); + if (mprotect(mem, pagesize, PROT_READ)) { + ksft_test_result_fail("mprotect() failed\n"); + goto munmap; + } + + /* Trigger page migration. Might not be available or fail. */ + if (syscall(__NR_mbind, mem, pagesize, MPOL_LOCAL, NULL, 0x7fful, + MPOL_MF_MOVE)) { + ksft_test_result_skip("mbind() failed\n"); + goto munmap; + } + + do_test_write_sigsegv(mem); +munmap: + munmap(mem, pagesize); +} + +static void test_page_migration_thp(void) +{ + char *mem, *mmap_mem; + size_t mmap_size; + + ksft_print_msg("[INFO] Page migration of THP\n"); + + mem = mmap_thp_range(PROT_READ|PROT_WRITE, &mmap_mem, &mmap_size); + if (mem == MAP_FAILED) + return; + + /* + * Write to the first page, which might populate a fresh anon THP + * and dirty it. + */ + memset(mem, 1, pagesize); + if (mprotect(mem, thpsize, PROT_READ)) { + ksft_test_result_fail("mprotect() failed\n"); + goto munmap; + } + + /* MM populated a THP if we got the last subpage populated as well. */ + if (!pagemap_is_populated(pagemap_fd, mem + thpsize - pagesize)) { + ksft_test_result_skip("Did not get a THP populated\n"); + goto munmap; + } + + /* Trigger page migration. Might not be available or fail. */ + if (syscall(__NR_mbind, mem, thpsize, MPOL_LOCAL, NULL, 0x7fful, + MPOL_MF_MOVE)) { + ksft_test_result_skip("mbind() failed\n"); + goto munmap; + } + + do_test_write_sigsegv(mem); +munmap: + munmap(mmap_mem, mmap_size); +} + +static void test_pte_mapped_thp(void) +{ + char *mem, *mmap_mem; + size_t mmap_size; + + ksft_print_msg("[INFO] PTE-mapping a THP\n"); + + mem = mmap_thp_range(PROT_READ|PROT_WRITE, &mmap_mem, &mmap_size); + if (mem == MAP_FAILED) + return; + + /* + * Write to the first page, which might populate a fresh anon THP + * and dirty it. + */ + memset(mem, 1, pagesize); + if (mprotect(mem, thpsize, PROT_READ)) { + ksft_test_result_fail("mprotect() failed\n"); + goto munmap; + } + + /* MM populated a THP if we got the last subpage populated as well. */ + if (!pagemap_is_populated(pagemap_fd, mem + thpsize - pagesize)) { + ksft_test_result_skip("Did not get a THP populated\n"); + goto munmap; + } + + /* Trigger PTE-mapping the THP by mprotect'ing the last subpage. */ + if (mprotect(mem + thpsize - pagesize, pagesize, + PROT_READ|PROT_WRITE)) { + ksft_test_result_fail("mprotect() failed\n"); + goto munmap; + } + + do_test_write_sigsegv(mem); +munmap: + munmap(mmap_mem, mmap_size); +} + +#ifdef __NR_userfaultfd +static void test_uffdio_copy(void) +{ + struct uffdio_register uffdio_register; + struct uffdio_copy uffdio_copy; + struct uffdio_api uffdio_api; + char *dst, *src; + int uffd; + + ksft_print_msg("[INFO] UFFDIO_COPY\n"); + + src = malloc(pagesize); + memset(src, 1, pagesize); + dst = mmap(NULL, pagesize, PROT_READ, MAP_PRIVATE|MAP_ANON, -1, 0); + if (dst == MAP_FAILED) { + ksft_test_result_fail("mmap() failed\n"); + return; + } + + uffd = syscall(__NR_userfaultfd, O_CLOEXEC | O_NONBLOCK); + if (uffd < 0) { + ksft_test_result_skip("__NR_userfaultfd failed\n"); + goto munmap; + } + + uffdio_api.api = UFFD_API; + uffdio_api.features = 0; + if (ioctl(uffd, UFFDIO_API, &uffdio_api) < 0) { + ksft_test_result_fail("UFFDIO_API failed\n"); + goto close_uffd; + } + + uffdio_register.range.start = (unsigned long) dst; + uffdio_register.range.len = pagesize; + uffdio_register.mode = UFFDIO_REGISTER_MODE_MISSING; + if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register)) { + ksft_test_result_fail("UFFDIO_REGISTER failed\n"); + goto close_uffd; + } + + /* Place a page in a read-only VMA, which might set the PTE dirty. */ + uffdio_copy.dst = (unsigned long) dst; + uffdio_copy.src = (unsigned long) src; + uffdio_copy.len = pagesize; + uffdio_copy.mode = 0; + if (ioctl(uffd, UFFDIO_COPY, &uffdio_copy)) { + ksft_test_result_fail("UFFDIO_COPY failed\n"); + goto close_uffd; + } + + do_test_write_sigsegv(dst); +close_uffd: + close(uffd); +munmap: + munmap(dst, pagesize); + free(src); +#endif /* __NR_userfaultfd */ +} + +int main(void) +{ + int err, tests = 2; + + pagesize = getpagesize(); + thpsize = read_pmd_pagesize(); + if (thpsize) { + ksft_print_msg("[INFO] detected THP size: %zu KiB\n", + thpsize / 1024); + tests += 3; + } +#ifdef __NR_userfaultfd + tests += 1; +#endif /* __NR_userfaultfd */ + + ksft_print_header(); + ksft_set_plan(tests); + + mem_fd = open("/proc/self/mem", O_RDWR); + if (mem_fd < 0) + ksft_exit_fail_msg("opening /proc/self/mem failed\n"); + pagemap_fd = open("/proc/self/pagemap", O_RDONLY); + if (pagemap_fd < 0) + ksft_exit_fail_msg("opening /proc/self/pagemap failed\n"); + + /* + * On some ptrace(FOLL_FORCE) write access via /proc/self/mem in + * read-only VMAs, the kernel may set the PTE/PMD dirty. + */ + test_ptrace_write(); + if (thpsize) + test_ptrace_write_thp(); + /* + * On page migration, the kernel may set the PTE/PMD dirty when + * remapping the page. + */ + test_page_migration(); + if (thpsize) + test_page_migration_thp(); + /* PTE-mapping a THP might propagate the dirty PMD bit to the PTEs. */ + if (thpsize) + test_pte_mapped_thp(); + /* Placing a fresh page via userfaultfd may set the PTE dirty. */ +#ifdef __NR_userfaultfd + test_uffdio_copy(); +#endif /* __NR_userfaultfd */ + + err = ksft_get_fail_cnt(); + if (err) + ksft_exit_fail_msg("%d out of %d tests failed\n", + err, ksft_test_num()); + return ksft_exit_pass(); +} diff --git a/tools/testing/selftests/mm/mrelease_test.c b/tools/testing/selftests/mm/mrelease_test.c index 6c62966ab5db..37b6d33b9e84 100644 --- a/tools/testing/selftests/mm/mrelease_test.c +++ b/tools/testing/selftests/mm/mrelease_test.c @@ -9,8 +9,7 @@ #include <stdlib.h> #include <sys/wait.h> #include <unistd.h> - -#include "util.h" +#include "vm_util.h" #include "../kselftest.h" @@ -32,7 +31,7 @@ static int alloc_noexit(unsigned long nr_pages, int pipefd) unsigned long i; char *buf; - buf = (char *)mmap(NULL, nr_pages * PAGE_SIZE, PROT_READ | PROT_WRITE, + buf = (char *)mmap(NULL, nr_pages * psize(), PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANON, 0, 0); if (buf == MAP_FAILED) { perror("mmap failed, halting the test"); @@ -40,7 +39,7 @@ static int alloc_noexit(unsigned long nr_pages, int pipefd) } for (i = 0; i < nr_pages; i++) - *((unsigned long *)(buf + (i * PAGE_SIZE))) = i; + *((unsigned long *)(buf + (i * psize()))) = i; /* Signal the parent that the child is ready */ if (write(pipefd, "", 1) < 0) { @@ -54,7 +53,7 @@ static int alloc_noexit(unsigned long nr_pages, int pipefd) timeout--; } - munmap(buf, nr_pages * PAGE_SIZE); + munmap(buf, nr_pages * psize()); return (timeout > 0) ? KSFT_PASS : KSFT_FAIL; } @@ -87,7 +86,7 @@ static int child_main(int pipefd[], size_t size) /* Allocate and fault-in memory and wait to be killed */ close(pipefd[0]); - res = alloc_noexit(MB(size) / PAGE_SIZE, pipefd[1]); + res = alloc_noexit(MB(size) / psize(), pipefd[1]); close(pipefd[1]); return res; } diff --git a/tools/testing/selftests/mm/run_vmtests.sh b/tools/testing/selftests/mm/run_vmtests.sh index a9d6d52596f2..4893eb60d96d 100644 --- a/tools/testing/selftests/mm/run_vmtests.sh +++ b/tools/testing/selftests/mm/run_vmtests.sh @@ -5,6 +5,9 @@ # Kselftest framework requirement - SKIP code is 4. ksft_skip=4 +count_pass=0 +count_fail=0 +count_skip=0 exitcode=0 usage() { @@ -149,11 +152,14 @@ run_test() { "$@" local ret=$? if [ $ret -eq 0 ]; then + count_pass=$(( count_pass + 1 )) echo "[PASS]" elif [ $ret -eq $ksft_skip ]; then + count_skip=$(( count_skip + 1 )) echo "[SKIP]" exitcode=$ksft_skip else + count_fail=$(( count_fail + 1 )) echo "[FAIL]" exitcode=1 fi @@ -190,15 +196,15 @@ CATEGORY="gup_test" run_test ./gup_test -a # Dump pages 0, 19, and 4096, using pin_user_pages: CATEGORY="gup_test" run_test ./gup_test -ct -F 0x1 0 19 0x1000 -uffd_mods=("" ":dev") -for mod in "${uffd_mods[@]}"; do - CATEGORY="userfaultfd" run_test ./userfaultfd anon${mod} 20 16 - # Hugetlb tests require source and destination huge pages. Pass in half - # the size ($half_ufd_size_MB), which is used for *each*. - CATEGORY="userfaultfd" run_test ./userfaultfd hugetlb${mod} "$half_ufd_size_MB" 32 - CATEGORY="userfaultfd" run_test ./userfaultfd hugetlb_shared${mod} "$half_ufd_size_MB" 32 - CATEGORY="userfaultfd" run_test ./userfaultfd shmem${mod} 20 16 -done +CATEGORY="userfaultfd" run_test ./uffd-unit-tests +uffd_stress_bin=./uffd-stress +CATEGORY="userfaultfd" run_test ${uffd_stress_bin} anon 20 16 +# Hugetlb tests require source and destination huge pages. Pass in half +# the size ($half_ufd_size_MB), which is used for *each*. +CATEGORY="userfaultfd" run_test ${uffd_stress_bin} hugetlb "$half_ufd_size_MB" 32 +CATEGORY="userfaultfd" run_test ${uffd_stress_bin} hugetlb-private "$half_ufd_size_MB" 32 +CATEGORY="userfaultfd" run_test ${uffd_stress_bin} shmem 20 16 +CATEGORY="userfaultfd" run_test ${uffd_stress_bin} shmem-private 20 16 #cleanup echo "$nr_hugepgs" > /proc/sys/vm/nr_hugepages @@ -220,10 +226,26 @@ CATEGORY="mremap" run_test ./mremap_test CATEGORY="hugetlb" run_test ./thuge-gen if [ $VADDR64 -ne 0 ]; then + + # set overcommit_policy as OVERCOMMIT_ALWAYS so that kernel + # allows high virtual address allocation requests independent + # of platform's physical memory. + + prev_policy=$(cat /proc/sys/vm/overcommit_memory) + echo 1 > /proc/sys/vm/overcommit_memory CATEGORY="hugevm" run_test ./virtual_address_range + echo $prev_policy > /proc/sys/vm/overcommit_memory - # virtual address 128TB switch test - CATEGORY="hugevm" run_test ./va_128TBswitch.sh + # va high address boundary switch test + ARCH_ARM64="arm64" + prev_nr_hugepages=$(cat /proc/sys/vm/nr_hugepages) + if [ "$ARCH" == "$ARCH_ARM64" ]; then + echo 6 > /proc/sys/vm/nr_hugepages + fi + CATEGORY="hugevm" run_test ./va_high_addr_switch.sh + if [ "$ARCH" == "$ARCH_ARM64" ]; then + echo $prev_nr_hugepages > /proc/sys/vm/nr_hugepages + fi fi # VADDR64 # vmalloc stability smoke test @@ -271,4 +293,6 @@ CATEGORY="soft_dirty" run_test ./soft-dirty # COW tests CATEGORY="cow" run_test ./cow +echo "SUMMARY: PASS=${count_pass} SKIP=${count_skip} FAIL=${count_fail}" + exit $exitcode diff --git a/tools/testing/selftests/mm/soft-dirty.c b/tools/testing/selftests/mm/soft-dirty.c index 21d8830c5f24..cc5f144430d4 100644 --- a/tools/testing/selftests/mm/soft-dirty.c +++ b/tools/testing/selftests/mm/soft-dirty.c @@ -80,6 +80,9 @@ static void test_hugepage(int pagemap_fd, int pagesize) int i, ret; size_t hpage_len = read_pmd_pagesize(); + if (!hpage_len) + ksft_exit_fail_msg("Reading PMD pagesize failed"); + map = memalign(hpage_len, hpage_len); if (!map) ksft_exit_fail_msg("memalign failed\n"); diff --git a/tools/testing/selftests/mm/split_huge_page_test.c b/tools/testing/selftests/mm/split_huge_page_test.c index 76e1c36dd9e5..0e74635c8c3d 100644 --- a/tools/testing/selftests/mm/split_huge_page_test.c +++ b/tools/testing/selftests/mm/split_huge_page_test.c @@ -106,7 +106,7 @@ void split_pmd_thp(void) for (i = 0; i < len; i++) one_page[i] = (char)i; - if (!check_huge_anon(one_page, 1, pmd_pagesize)) { + if (!check_huge_anon(one_page, 4, pmd_pagesize)) { printf("No THP is allocated\n"); exit(EXIT_FAILURE); } @@ -122,7 +122,7 @@ void split_pmd_thp(void) } - if (check_huge_anon(one_page, 0, pmd_pagesize)) { + if (!check_huge_anon(one_page, 0, pmd_pagesize)) { printf("Still AnonHugePages not split\n"); exit(EXIT_FAILURE); } @@ -169,7 +169,7 @@ void split_pte_mapped_thp(void) for (i = 0; i < len; i++) one_page[i] = (char)i; - if (!check_huge_anon(one_page, 1, pmd_pagesize)) { + if (!check_huge_anon(one_page, 4, pmd_pagesize)) { printf("No THP is allocated\n"); exit(EXIT_FAILURE); } @@ -300,6 +300,10 @@ int main(int argc, char **argv) pagesize = getpagesize(); pageshift = ffs(pagesize) - 1; pmd_pagesize = read_pmd_pagesize(); + if (!pmd_pagesize) { + printf("Reading PMD pagesize failed\n"); + exit(EXIT_FAILURE); + } split_pmd_thp(); split_pte_mapped_thp(); diff --git a/tools/testing/selftests/mm/thuge-gen.c b/tools/testing/selftests/mm/thuge-gen.c index 361ef7192cc6..380ab5f0a534 100644 --- a/tools/testing/selftests/mm/thuge-gen.c +++ b/tools/testing/selftests/mm/thuge-gen.c @@ -24,6 +24,7 @@ #include <unistd.h> #include <stdarg.h> #include <string.h> +#include "vm_util.h" #define err(x) perror(x), exit(1) @@ -74,24 +75,6 @@ void find_pagesizes(void) globfree(&g); } -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); - return hps; -} - void show(unsigned long ps) { char buf[100]; diff --git a/tools/testing/selftests/mm/transhuge-stress.c b/tools/testing/selftests/mm/transhuge-stress.c index e3f00adb1b82..ba9d37ad3a89 100644 --- a/tools/testing/selftests/mm/transhuge-stress.c +++ b/tools/testing/selftests/mm/transhuge-stress.c @@ -15,7 +15,7 @@ #include <fcntl.h> #include <string.h> #include <sys/mman.h> -#include "util.h" +#include "vm_util.h" int backing_fd = -1; int mmap_flags = MAP_ANONYMOUS | MAP_NORESERVE | MAP_PRIVATE; @@ -34,10 +34,10 @@ int main(int argc, char **argv) int pagemap_fd; ram = sysconf(_SC_PHYS_PAGES); - if (ram > SIZE_MAX / sysconf(_SC_PAGESIZE) / 4) + if (ram > SIZE_MAX / psize() / 4) ram = SIZE_MAX / 4; else - ram *= sysconf(_SC_PAGESIZE); + ram *= psize(); len = ram; while (++i < argc) { @@ -58,7 +58,7 @@ int main(int argc, char **argv) warnx("allocate %zd transhuge pages, using %zd MiB virtual memory" " and %zd MiB of ram", len >> HPAGE_SHIFT, len >> 20, - ram >> (20 + HPAGE_SHIFT - PAGE_SHIFT - 1)); + ram >> (20 + HPAGE_SHIFT - pshift() - 1)); pagemap_fd = open("/proc/self/pagemap", O_RDONLY); if (pagemap_fd < 0) @@ -92,7 +92,7 @@ int main(int argc, char **argv) if (pfn < 0) { nr_failed++; } else { - size_t idx = pfn >> (HPAGE_SHIFT - PAGE_SHIFT); + size_t idx = pfn >> (HPAGE_SHIFT - pshift()); nr_succeed++; if (idx >= map_len) { @@ -108,7 +108,7 @@ int main(int argc, char **argv) } /* split transhuge page, keep last page */ - if (madvise(p, HPAGE_SIZE - PAGE_SIZE, MADV_DONTNEED)) + if (madvise(p, HPAGE_SIZE - psize(), MADV_DONTNEED)) err(2, "MADV_DONTNEED"); } clock_gettime(CLOCK_MONOTONIC, &b); diff --git a/tools/testing/selftests/mm/uffd-common.c b/tools/testing/selftests/mm/uffd-common.c new file mode 100644 index 000000000000..61c6250adf93 --- /dev/null +++ b/tools/testing/selftests/mm/uffd-common.c @@ -0,0 +1,618 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Userfaultfd tests util functions + * + * Copyright (C) 2015-2023 Red Hat, Inc. + */ + +#include "uffd-common.h" + +#define BASE_PMD_ADDR ((void *)(1UL << 30)) + +volatile bool test_uffdio_copy_eexist = true; +unsigned long nr_cpus, nr_pages, nr_pages_per_cpu, page_size; +char *area_src, *area_src_alias, *area_dst, *area_dst_alias, *area_remap; +int uffd = -1, uffd_flags, finished, *pipefd, test_type; +bool map_shared; +bool test_uffdio_wp = true; +unsigned long long *count_verify; +uffd_test_ops_t *uffd_test_ops; + +static int uffd_mem_fd_create(off_t mem_size, bool hugetlb) +{ + unsigned int memfd_flags = 0; + int mem_fd; + + if (hugetlb) + memfd_flags = MFD_HUGETLB; + mem_fd = memfd_create("uffd-test", memfd_flags); + if (mem_fd < 0) + err("memfd_create"); + if (ftruncate(mem_fd, mem_size)) + err("ftruncate"); + if (fallocate(mem_fd, + FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE, 0, + mem_size)) + err("fallocate"); + + return mem_fd; +} + +static void anon_release_pages(char *rel_area) +{ + if (madvise(rel_area, nr_pages * page_size, MADV_DONTNEED)) + err("madvise(MADV_DONTNEED) failed"); +} + +static int anon_allocate_area(void **alloc_area, bool is_src) +{ + *alloc_area = mmap(NULL, nr_pages * page_size, PROT_READ | PROT_WRITE, + MAP_ANONYMOUS | MAP_PRIVATE, -1, 0); + if (*alloc_area == MAP_FAILED) { + *alloc_area = NULL; + return -errno; + } + return 0; +} + +static void noop_alias_mapping(__u64 *start, size_t len, unsigned long offset) +{ +} + +static void hugetlb_release_pages(char *rel_area) +{ + if (!map_shared) { + if (madvise(rel_area, nr_pages * page_size, MADV_DONTNEED)) + err("madvise(MADV_DONTNEED) failed"); + } else { + if (madvise(rel_area, nr_pages * page_size, MADV_REMOVE)) + err("madvise(MADV_REMOVE) failed"); + } +} + +static int hugetlb_allocate_area(void **alloc_area, bool is_src) +{ + off_t size = nr_pages * page_size; + off_t offset = is_src ? 0 : size; + void *area_alias = NULL; + char **alloc_area_alias; + int mem_fd = uffd_mem_fd_create(size * 2, true); + + *alloc_area = mmap(NULL, size, PROT_READ | PROT_WRITE, + (map_shared ? MAP_SHARED : MAP_PRIVATE) | + (is_src ? 0 : MAP_NORESERVE), + mem_fd, offset); + if (*alloc_area == MAP_FAILED) { + *alloc_area = NULL; + return -errno; + } + + if (map_shared) { + area_alias = mmap(NULL, size, PROT_READ | PROT_WRITE, + MAP_SHARED, mem_fd, offset); + if (area_alias == MAP_FAILED) + return -errno; + } + + if (is_src) { + alloc_area_alias = &area_src_alias; + } else { + alloc_area_alias = &area_dst_alias; + } + if (area_alias) + *alloc_area_alias = area_alias; + + close(mem_fd); + return 0; +} + +static void hugetlb_alias_mapping(__u64 *start, size_t len, unsigned long offset) +{ + if (!map_shared) + return; + + *start = (unsigned long) area_dst_alias + offset; +} + +static void shmem_release_pages(char *rel_area) +{ + if (madvise(rel_area, nr_pages * page_size, MADV_REMOVE)) + err("madvise(MADV_REMOVE) failed"); +} + +static int shmem_allocate_area(void **alloc_area, bool is_src) +{ + void *area_alias = NULL; + size_t bytes = nr_pages * page_size, hpage_size = read_pmd_pagesize(); + unsigned long offset = is_src ? 0 : bytes; + char *p = NULL, *p_alias = NULL; + int mem_fd = uffd_mem_fd_create(bytes * 2, false); + + /* TODO: clean this up. Use a static addr is ugly */ + p = BASE_PMD_ADDR; + if (!is_src) + /* src map + alias + interleaved hpages */ + p += 2 * (bytes + hpage_size); + p_alias = p; + p_alias += bytes; + p_alias += hpage_size; /* Prevent src/dst VMA merge */ + + *alloc_area = mmap(p, bytes, PROT_READ | PROT_WRITE, MAP_SHARED, + mem_fd, offset); + if (*alloc_area == MAP_FAILED) { + *alloc_area = NULL; + return -errno; + } + if (*alloc_area != p) + err("mmap of memfd failed at %p", p); + + area_alias = mmap(p_alias, bytes, PROT_READ | PROT_WRITE, MAP_SHARED, + mem_fd, offset); + if (area_alias == MAP_FAILED) { + munmap(*alloc_area, bytes); + *alloc_area = NULL; + return -errno; + } + if (area_alias != p_alias) + err("mmap of anonymous memory failed at %p", p_alias); + + if (is_src) + area_src_alias = area_alias; + else + area_dst_alias = area_alias; + + close(mem_fd); + return 0; +} + +static void shmem_alias_mapping(__u64 *start, size_t len, unsigned long offset) +{ + *start = (unsigned long)area_dst_alias + offset; +} + +static void shmem_check_pmd_mapping(void *p, int expect_nr_hpages) +{ + if (!check_huge_shmem(area_dst_alias, expect_nr_hpages, + read_pmd_pagesize())) + err("Did not find expected %d number of hugepages", + expect_nr_hpages); +} + +struct uffd_test_ops anon_uffd_test_ops = { + .allocate_area = anon_allocate_area, + .release_pages = anon_release_pages, + .alias_mapping = noop_alias_mapping, + .check_pmd_mapping = NULL, +}; + +struct uffd_test_ops shmem_uffd_test_ops = { + .allocate_area = shmem_allocate_area, + .release_pages = shmem_release_pages, + .alias_mapping = shmem_alias_mapping, + .check_pmd_mapping = shmem_check_pmd_mapping, +}; + +struct uffd_test_ops hugetlb_uffd_test_ops = { + .allocate_area = hugetlb_allocate_area, + .release_pages = hugetlb_release_pages, + .alias_mapping = hugetlb_alias_mapping, + .check_pmd_mapping = NULL, +}; + +void uffd_stats_report(struct uffd_args *args, int n_cpus) +{ + int i; + unsigned long long miss_total = 0, wp_total = 0, minor_total = 0; + + for (i = 0; i < n_cpus; i++) { + miss_total += args[i].missing_faults; + wp_total += args[i].wp_faults; + minor_total += args[i].minor_faults; + } + + printf("userfaults: "); + if (miss_total) { + printf("%llu missing (", miss_total); + for (i = 0; i < n_cpus; i++) + printf("%lu+", args[i].missing_faults); + printf("\b) "); + } + if (wp_total) { + printf("%llu wp (", wp_total); + for (i = 0; i < n_cpus; i++) + printf("%lu+", args[i].wp_faults); + printf("\b) "); + } + if (minor_total) { + printf("%llu minor (", minor_total); + for (i = 0; i < n_cpus; i++) + printf("%lu+", args[i].minor_faults); + printf("\b)"); + } + printf("\n"); +} + +int userfaultfd_open(uint64_t *features) +{ + struct uffdio_api uffdio_api; + + uffd = uffd_open(UFFD_FLAGS); + if (uffd < 0) + return -1; + uffd_flags = fcntl(uffd, F_GETFD, NULL); + + uffdio_api.api = UFFD_API; + uffdio_api.features = *features; + if (ioctl(uffd, UFFDIO_API, &uffdio_api)) + /* Probably lack of CAP_PTRACE? */ + return -1; + if (uffdio_api.api != UFFD_API) + err("UFFDIO_API error: %" PRIu64, (uint64_t)uffdio_api.api); + + *features = uffdio_api.features; + return 0; +} + +static inline void munmap_area(void **area) +{ + if (*area) + if (munmap(*area, nr_pages * page_size)) + err("munmap"); + + *area = NULL; +} + +static void uffd_test_ctx_clear(void) +{ + size_t i; + + if (pipefd) { + for (i = 0; i < nr_cpus * 2; ++i) { + if (close(pipefd[i])) + err("close pipefd"); + } + free(pipefd); + pipefd = NULL; + } + + if (count_verify) { + free(count_verify); + count_verify = NULL; + } + + if (uffd != -1) { + if (close(uffd)) + err("close uffd"); + uffd = -1; + } + + munmap_area((void **)&area_src); + munmap_area((void **)&area_src_alias); + munmap_area((void **)&area_dst); + munmap_area((void **)&area_dst_alias); + munmap_area((void **)&area_remap); +} + +int uffd_test_ctx_init(uint64_t features, const char **errmsg) +{ + unsigned long nr, cpu; + int ret; + + uffd_test_ctx_clear(); + + ret = uffd_test_ops->allocate_area((void **)&area_src, true); + ret |= uffd_test_ops->allocate_area((void **)&area_dst, false); + if (ret) { + if (errmsg) + *errmsg = "memory allocation failed"; + return ret; + } + + ret = userfaultfd_open(&features); + if (ret) { + if (errmsg) + *errmsg = "possible lack of priviledge"; + return ret; + } + + count_verify = malloc(nr_pages * sizeof(unsigned long long)); + if (!count_verify) + err("count_verify"); + + for (nr = 0; nr < nr_pages; nr++) { + *area_mutex(area_src, nr) = + (pthread_mutex_t)PTHREAD_MUTEX_INITIALIZER; + count_verify[nr] = *area_count(area_src, nr) = 1; + /* + * In the transition between 255 to 256, powerpc will + * read out of order in my_bcmp and see both bytes as + * zero, so leave a placeholder below always non-zero + * after the count, to avoid my_bcmp to trigger false + * positives. + */ + *(area_count(area_src, nr) + 1) = 1; + } + + /* + * After initialization of area_src, we must explicitly release pages + * for area_dst to make sure it's fully empty. Otherwise we could have + * some area_dst pages be errornously initialized with zero pages, + * hence we could hit memory corruption later in the test. + * + * One example is when THP is globally enabled, above allocate_area() + * calls could have the two areas merged into a single VMA (as they + * will have the same VMA flags so they're mergeable). When we + * initialize the area_src above, it's possible that some part of + * area_dst could have been faulted in via one huge THP that will be + * shared between area_src and area_dst. It could cause some of the + * area_dst won't be trapped by missing userfaults. + * + * This release_pages() will guarantee even if that happened, we'll + * proactively split the thp and drop any accidentally initialized + * pages within area_dst. + */ + uffd_test_ops->release_pages(area_dst); + + pipefd = malloc(sizeof(int) * nr_cpus * 2); + if (!pipefd) + err("pipefd"); + for (cpu = 0; cpu < nr_cpus; cpu++) + if (pipe2(&pipefd[cpu * 2], O_CLOEXEC | O_NONBLOCK)) + err("pipe"); + + return 0; +} + +void wp_range(int ufd, __u64 start, __u64 len, bool wp) +{ + struct uffdio_writeprotect prms; + + /* Write protection page faults */ + prms.range.start = start; + prms.range.len = len; + /* Undo write-protect, do wakeup after that */ + prms.mode = wp ? UFFDIO_WRITEPROTECT_MODE_WP : 0; + + if (ioctl(ufd, UFFDIO_WRITEPROTECT, &prms)) + err("clear WP failed: address=0x%"PRIx64, (uint64_t)start); +} + +static void continue_range(int ufd, __u64 start, __u64 len, bool wp) +{ + struct uffdio_continue req; + int ret; + + req.range.start = start; + req.range.len = len; + req.mode = 0; + if (wp) + req.mode |= UFFDIO_CONTINUE_MODE_WP; + + if (ioctl(ufd, UFFDIO_CONTINUE, &req)) + err("UFFDIO_CONTINUE failed for address 0x%" PRIx64, + (uint64_t)start); + + /* + * Error handling within the kernel for continue is subtly different + * from copy or zeropage, so it may be a source of bugs. Trigger an + * error (-EEXIST) on purpose, to verify doing so doesn't cause a BUG. + */ + req.mapped = 0; + ret = ioctl(ufd, UFFDIO_CONTINUE, &req); + if (ret >= 0 || req.mapped != -EEXIST) + err("failed to exercise UFFDIO_CONTINUE error handling, ret=%d, mapped=%" PRId64, + ret, (int64_t) req.mapped); +} + +int uffd_read_msg(int ufd, struct uffd_msg *msg) +{ + int ret = read(uffd, msg, sizeof(*msg)); + + if (ret != sizeof(*msg)) { + if (ret < 0) { + if (errno == EAGAIN || errno == EINTR) + return 1; + err("blocking read error"); + } else { + err("short read"); + } + } + + return 0; +} + +void uffd_handle_page_fault(struct uffd_msg *msg, struct uffd_args *args) +{ + unsigned long offset; + + if (msg->event != UFFD_EVENT_PAGEFAULT) + err("unexpected msg event %u", msg->event); + + if (msg->arg.pagefault.flags & UFFD_PAGEFAULT_FLAG_WP) { + /* Write protect page faults */ + wp_range(uffd, msg->arg.pagefault.address, page_size, false); + args->wp_faults++; + } else if (msg->arg.pagefault.flags & UFFD_PAGEFAULT_FLAG_MINOR) { + uint8_t *area; + int b; + + /* + * Minor page faults + * + * To prove we can modify the original range for testing + * purposes, we're going to bit flip this range before + * continuing. + * + * Note that this requires all minor page fault tests operate on + * area_dst (non-UFFD-registered) and area_dst_alias + * (UFFD-registered). + */ + + area = (uint8_t *)(area_dst + + ((char *)msg->arg.pagefault.address - + area_dst_alias)); + for (b = 0; b < page_size; ++b) + area[b] = ~area[b]; + continue_range(uffd, msg->arg.pagefault.address, page_size, + args->apply_wp); + args->minor_faults++; + } else { + /* + * Missing page faults. + * + * Here we force a write check for each of the missing mode + * faults. It's guaranteed because the only threads that + * will trigger uffd faults are the locking threads, and + * their first instruction to touch the missing page will + * always be pthread_mutex_lock(). + * + * Note that here we relied on an NPTL glibc impl detail to + * always read the lock type at the entry of the lock op + * (pthread_mutex_t.__data.__type, offset 0x10) before + * doing any locking operations to guarantee that. It's + * actually not good to rely on this impl detail because + * logically a pthread-compatible lib can implement the + * locks without types and we can fail when linking with + * them. However since we used to find bugs with this + * strict check we still keep it around. Hopefully this + * could be a good hint when it fails again. If one day + * it'll break on some other impl of glibc we'll revisit. + */ + if (msg->arg.pagefault.flags & UFFD_PAGEFAULT_FLAG_WRITE) + err("unexpected write fault"); + + offset = (char *)(unsigned long)msg->arg.pagefault.address - area_dst; + offset &= ~(page_size-1); + + if (copy_page(uffd, offset, args->apply_wp)) + args->missing_faults++; + } +} + +void *uffd_poll_thread(void *arg) +{ + struct uffd_args *args = (struct uffd_args *)arg; + unsigned long cpu = args->cpu; + struct pollfd pollfd[2]; + struct uffd_msg msg; + struct uffdio_register uffd_reg; + int ret; + char tmp_chr; + + pollfd[0].fd = uffd; + pollfd[0].events = POLLIN; + pollfd[1].fd = pipefd[cpu*2]; + pollfd[1].events = POLLIN; + + for (;;) { + ret = poll(pollfd, 2, -1); + if (ret <= 0) { + if (errno == EINTR || errno == EAGAIN) + continue; + err("poll error: %d", ret); + } + if (pollfd[1].revents) { + if (!(pollfd[1].revents & POLLIN)) + err("pollfd[1].revents %d", pollfd[1].revents); + if (read(pollfd[1].fd, &tmp_chr, 1) != 1) + err("read pipefd error"); + break; + } + if (!(pollfd[0].revents & POLLIN)) + err("pollfd[0].revents %d", pollfd[0].revents); + if (uffd_read_msg(uffd, &msg)) + continue; + switch (msg.event) { + default: + err("unexpected msg event %u\n", msg.event); + break; + case UFFD_EVENT_PAGEFAULT: + uffd_handle_page_fault(&msg, args); + break; + case UFFD_EVENT_FORK: + close(uffd); + uffd = msg.arg.fork.ufd; + pollfd[0].fd = uffd; + break; + case UFFD_EVENT_REMOVE: + uffd_reg.range.start = msg.arg.remove.start; + uffd_reg.range.len = msg.arg.remove.end - + msg.arg.remove.start; + if (ioctl(uffd, UFFDIO_UNREGISTER, &uffd_reg.range)) + err("remove failure"); + break; + case UFFD_EVENT_REMAP: + area_remap = area_dst; /* save for later unmap */ + area_dst = (char *)(unsigned long)msg.arg.remap.to; + break; + } + } + + 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) + err("UFFDIO_COPY retry error: %"PRId64, + (int64_t)uffdio_copy->copy); + } else { + err("UFFDIO_COPY retry unexpected: %"PRId64, + (int64_t)uffdio_copy->copy); + } +} + +static void wake_range(int ufd, unsigned long addr, unsigned long len) +{ + struct uffdio_range uffdio_wake; + + uffdio_wake.start = addr; + uffdio_wake.len = len; + + if (ioctl(ufd, UFFDIO_WAKE, &uffdio_wake)) + fprintf(stderr, "error waking %lu\n", + addr), exit(1); +} + +int __copy_page(int ufd, unsigned long offset, bool retry, bool wp) +{ + struct uffdio_copy uffdio_copy; + + if (offset >= nr_pages * page_size) + err("unexpected offset %lu\n", offset); + uffdio_copy.dst = (unsigned long) area_dst + offset; + uffdio_copy.src = (unsigned long) area_src + offset; + uffdio_copy.len = page_size; + if (wp) + uffdio_copy.mode = UFFDIO_COPY_MODE_WP; + else + uffdio_copy.mode = 0; + uffdio_copy.copy = 0; + if (ioctl(ufd, UFFDIO_COPY, &uffdio_copy)) { + /* real retval in ufdio_copy.copy */ + if (uffdio_copy.copy != -EEXIST) + err("UFFDIO_COPY error: %"PRId64, + (int64_t)uffdio_copy.copy); + wake_range(ufd, uffdio_copy.dst, page_size); + } else if (uffdio_copy.copy != page_size) { + err("UFFDIO_COPY error: %"PRId64, (int64_t)uffdio_copy.copy); + } else { + if (test_uffdio_copy_eexist && retry) { + test_uffdio_copy_eexist = false; + retry_copy_page(ufd, &uffdio_copy, offset); + } + return 1; + } + return 0; +} + +int copy_page(int ufd, unsigned long offset, bool wp) +{ + return __copy_page(ufd, offset, false, wp); +} diff --git a/tools/testing/selftests/mm/uffd-common.h b/tools/testing/selftests/mm/uffd-common.h new file mode 100644 index 000000000000..6068f2346b86 --- /dev/null +++ b/tools/testing/selftests/mm/uffd-common.h @@ -0,0 +1,117 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Userfaultfd tests common header + * + * Copyright (C) 2015-2023 Red Hat, Inc. + */ +#ifndef __UFFD_COMMON_H__ +#define __UFFD_COMMON_H__ + +#define _GNU_SOURCE +#include <stdio.h> +#include <errno.h> +#include <unistd.h> +#include <stdlib.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <fcntl.h> +#include <time.h> +#include <signal.h> +#include <poll.h> +#include <string.h> +#include <linux/mman.h> +#include <sys/mman.h> +#include <sys/syscall.h> +#include <sys/ioctl.h> +#include <sys/wait.h> +#include <pthread.h> +#include <linux/userfaultfd.h> +#include <setjmp.h> +#include <stdbool.h> +#include <assert.h> +#include <inttypes.h> +#include <stdint.h> +#include <sys/random.h> + +#include "../kselftest.h" +#include "vm_util.h" + +#define UFFD_FLAGS (O_CLOEXEC | O_NONBLOCK | UFFD_USER_MODE_ONLY) + +#define _err(fmt, ...) \ + do { \ + int ret = errno; \ + fprintf(stderr, "ERROR: " fmt, ##__VA_ARGS__); \ + fprintf(stderr, " (errno=%d, @%s:%d)\n", \ + ret, __FILE__, __LINE__); \ + } while (0) + +#define errexit(exitcode, fmt, ...) \ + do { \ + _err(fmt, ##__VA_ARGS__); \ + exit(exitcode); \ + } while (0) + +#define err(fmt, ...) errexit(1, fmt, ##__VA_ARGS__) + +/* pthread_mutex_t starts at page offset 0 */ +#define area_mutex(___area, ___nr) \ + ((pthread_mutex_t *) ((___area) + (___nr)*page_size)) +/* + * count is placed in the page after pthread_mutex_t naturally aligned + * to avoid non alignment faults on non-x86 archs. + */ +#define area_count(___area, ___nr) \ + ((volatile unsigned long long *) ((unsigned long) \ + ((___area) + (___nr)*page_size + \ + sizeof(pthread_mutex_t) + \ + sizeof(unsigned long long) - 1) & \ + ~(unsigned long)(sizeof(unsigned long long) \ + - 1))) + +/* Userfaultfd test statistics */ +struct uffd_args { + int cpu; + /* Whether apply wr-protects when installing pages */ + bool apply_wp; + unsigned long missing_faults; + unsigned long wp_faults; + unsigned long minor_faults; +}; + +struct uffd_test_ops { + int (*allocate_area)(void **alloc_area, bool is_src); + void (*release_pages)(char *rel_area); + void (*alias_mapping)(__u64 *start, size_t len, unsigned long offset); + void (*check_pmd_mapping)(void *p, int expect_nr_hpages); +}; +typedef struct uffd_test_ops uffd_test_ops_t; + +extern unsigned long nr_cpus, nr_pages, nr_pages_per_cpu, page_size; +extern char *area_src, *area_src_alias, *area_dst, *area_dst_alias, *area_remap; +extern int uffd, uffd_flags, finished, *pipefd, test_type; +extern bool map_shared; +extern bool test_uffdio_wp; +extern unsigned long long *count_verify; +extern volatile bool test_uffdio_copy_eexist; + +extern uffd_test_ops_t anon_uffd_test_ops; +extern uffd_test_ops_t shmem_uffd_test_ops; +extern uffd_test_ops_t hugetlb_uffd_test_ops; +extern uffd_test_ops_t *uffd_test_ops; + +void uffd_stats_report(struct uffd_args *args, int n_cpus); +int uffd_test_ctx_init(uint64_t features, const char **errmsg); +int userfaultfd_open(uint64_t *features); +int uffd_read_msg(int ufd, struct uffd_msg *msg); +void wp_range(int ufd, __u64 start, __u64 len, bool wp); +void uffd_handle_page_fault(struct uffd_msg *msg, struct uffd_args *args); +int __copy_page(int ufd, unsigned long offset, bool retry, bool wp); +int copy_page(int ufd, unsigned long offset, bool wp); +void *uffd_poll_thread(void *arg); + +#define TEST_ANON 1 +#define TEST_HUGETLB 2 +#define TEST_SHMEM 3 + +#endif diff --git a/tools/testing/selftests/mm/uffd-stress.c b/tools/testing/selftests/mm/uffd-stress.c new file mode 100644 index 000000000000..f1ad9eef1c3a --- /dev/null +++ b/tools/testing/selftests/mm/uffd-stress.c @@ -0,0 +1,481 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Stress userfaultfd syscall. + * + * Copyright (C) 2015 Red Hat, Inc. + * + * This test allocates two virtual areas and bounces the physical + * memory across the two virtual areas (from area_src to area_dst) + * using userfaultfd. + * + * There are three threads running per CPU: + * + * 1) one per-CPU thread takes a per-page pthread_mutex in a random + * page of the area_dst (while the physical page may still be in + * area_src), and increments a per-page counter in the same page, + * and checks its value against a verification region. + * + * 2) another per-CPU thread handles the userfaults generated by + * thread 1 above. userfaultfd blocking reads or poll() modes are + * exercised interleaved. + * + * 3) one last per-CPU thread transfers the memory in the background + * at maximum bandwidth (if not already transferred by thread + * 2). Each cpu thread takes cares of transferring a portion of the + * area. + * + * When all threads of type 3 completed the transfer, one bounce is + * complete. area_src and area_dst are then swapped. All threads are + * respawned and so the bounce is immediately restarted in the + * opposite direction. + * + * per-CPU threads 1 by triggering userfaults inside + * pthread_mutex_lock will also verify the atomicity of the memory + * transfer (UFFDIO_COPY). + */ + +#include "uffd-common.h" + +#ifdef __NR_userfaultfd + +#define BOUNCE_RANDOM (1<<0) +#define BOUNCE_RACINGFAULTS (1<<1) +#define BOUNCE_VERIFY (1<<2) +#define BOUNCE_POLL (1<<3) +static int bounces; + +/* exercise the test_uffdio_*_eexist every ALARM_INTERVAL_SECS */ +#define ALARM_INTERVAL_SECS 10 +static char *zeropage; +pthread_attr_t attr; + +#define swap(a, b) \ + do { typeof(a) __tmp = (a); (a) = (b); (b) = __tmp; } while (0) + +const char *examples = + "# Run anonymous memory test on 100MiB region with 99999 bounces:\n" + "./userfaultfd anon 100 99999\n\n" + "# Run share memory test on 1GiB region with 99 bounces:\n" + "./userfaultfd shmem 1000 99\n\n" + "# Run hugetlb memory test on 256MiB region with 50 bounces:\n" + "./userfaultfd hugetlb 256 50\n\n" + "# Run the same hugetlb test but using private file:\n" + "./userfaultfd hugetlb-private 256 50\n\n" + "# 10MiB-~6GiB 999 bounces anonymous test, " + "continue forever unless an error triggers\n" + "while ./userfaultfd anon $[RANDOM % 6000 + 10] 999; do true; done\n\n"; + +static void usage(void) +{ + fprintf(stderr, "\nUsage: ./userfaultfd <test type> <MiB> <bounces>\n\n"); + fprintf(stderr, "Supported <test type>: anon, hugetlb, " + "hugetlb-private, shmem, shmem-private\n\n"); + fprintf(stderr, "Examples:\n\n"); + fprintf(stderr, "%s", examples); + exit(1); +} + +static void uffd_stats_reset(struct uffd_args *args, unsigned long n_cpus) +{ + int i; + + for (i = 0; i < n_cpus; i++) { + args[i].cpu = i; + args[i].apply_wp = test_uffdio_wp; + args[i].missing_faults = 0; + args[i].wp_faults = 0; + args[i].minor_faults = 0; + } +} + +static inline uint64_t uffd_minor_feature(void) +{ + if (test_type == TEST_HUGETLB && map_shared) + return UFFD_FEATURE_MINOR_HUGETLBFS; + else if (test_type == TEST_SHMEM) + return UFFD_FEATURE_MINOR_SHMEM; + else + return 0; +} + +static void *locking_thread(void *arg) +{ + unsigned long cpu = (unsigned long) arg; + unsigned long page_nr; + unsigned long long count; + + if (!(bounces & BOUNCE_RANDOM)) { + page_nr = -bounces; + if (!(bounces & BOUNCE_RACINGFAULTS)) + page_nr += cpu * nr_pages_per_cpu; + } + + while (!finished) { + if (bounces & BOUNCE_RANDOM) { + if (getrandom(&page_nr, sizeof(page_nr), 0) != sizeof(page_nr)) + err("getrandom failed"); + } else + page_nr += 1; + page_nr %= nr_pages; + pthread_mutex_lock(area_mutex(area_dst, page_nr)); + count = *area_count(area_dst, page_nr); + if (count != count_verify[page_nr]) + err("page_nr %lu memory corruption %llu %llu", + page_nr, count, count_verify[page_nr]); + count++; + *area_count(area_dst, page_nr) = count_verify[page_nr] = count; + pthread_mutex_unlock(area_mutex(area_dst, page_nr)); + } + + return NULL; +} + +static int copy_page_retry(int ufd, unsigned long offset) +{ + return __copy_page(ufd, offset, true, test_uffdio_wp); +} + +pthread_mutex_t uffd_read_mutex = PTHREAD_MUTEX_INITIALIZER; + +static void *uffd_read_thread(void *arg) +{ + struct uffd_args *args = (struct uffd_args *)arg; + struct uffd_msg msg; + + pthread_mutex_unlock(&uffd_read_mutex); + /* from here cancellation is ok */ + + for (;;) { + if (uffd_read_msg(uffd, &msg)) + continue; + uffd_handle_page_fault(&msg, args); + } + + return NULL; +} + +static void *background_thread(void *arg) +{ + unsigned long cpu = (unsigned long) arg; + unsigned long page_nr, start_nr, mid_nr, end_nr; + + start_nr = cpu * nr_pages_per_cpu; + end_nr = (cpu+1) * nr_pages_per_cpu; + mid_nr = (start_nr + end_nr) / 2; + + /* Copy the first half of the pages */ + for (page_nr = start_nr; page_nr < mid_nr; page_nr++) + copy_page_retry(uffd, page_nr * page_size); + + /* + * If we need to test uffd-wp, set it up now. Then we'll have + * at least the first half of the pages mapped already which + * can be write-protected for testing + */ + if (test_uffdio_wp) + wp_range(uffd, (unsigned long)area_dst + start_nr * page_size, + nr_pages_per_cpu * page_size, true); + + /* + * Continue the 2nd half of the page copying, handling write + * protection faults if any + */ + for (page_nr = mid_nr; page_nr < end_nr; page_nr++) + copy_page_retry(uffd, page_nr * page_size); + + return NULL; +} + +static int stress(struct uffd_args *args) +{ + unsigned long cpu; + pthread_t locking_threads[nr_cpus]; + pthread_t uffd_threads[nr_cpus]; + pthread_t background_threads[nr_cpus]; + + finished = 0; + for (cpu = 0; cpu < nr_cpus; cpu++) { + if (pthread_create(&locking_threads[cpu], &attr, + locking_thread, (void *)cpu)) + return 1; + if (bounces & BOUNCE_POLL) { + if (pthread_create(&uffd_threads[cpu], &attr, + uffd_poll_thread, + (void *)&args[cpu])) + return 1; + } else { + if (pthread_create(&uffd_threads[cpu], &attr, + uffd_read_thread, + (void *)&args[cpu])) + return 1; + pthread_mutex_lock(&uffd_read_mutex); + } + if (pthread_create(&background_threads[cpu], &attr, + background_thread, (void *)cpu)) + return 1; + } + for (cpu = 0; cpu < nr_cpus; cpu++) + if (pthread_join(background_threads[cpu], NULL)) + return 1; + + /* + * Be strict and immediately zap area_src, the whole area has + * been transferred already by the background treads. The + * area_src could then be faulted in a racy way by still + * running uffdio_threads reading zeropages after we zapped + * area_src (but they're guaranteed to get -EEXIST from + * UFFDIO_COPY without writing zero pages into area_dst + * because the background threads already completed). + */ + uffd_test_ops->release_pages(area_src); + + finished = 1; + for (cpu = 0; cpu < nr_cpus; cpu++) + if (pthread_join(locking_threads[cpu], NULL)) + return 1; + + for (cpu = 0; cpu < nr_cpus; cpu++) { + char c; + if (bounces & BOUNCE_POLL) { + if (write(pipefd[cpu*2+1], &c, 1) != 1) + err("pipefd write error"); + if (pthread_join(uffd_threads[cpu], + (void *)&args[cpu])) + return 1; + } else { + if (pthread_cancel(uffd_threads[cpu])) + return 1; + if (pthread_join(uffd_threads[cpu], NULL)) + return 1; + } + } + + return 0; +} + +static int userfaultfd_stress(void) +{ + void *area; + unsigned long nr; + struct uffd_args args[nr_cpus]; + uint64_t mem_size = nr_pages * page_size; + + if (uffd_test_ctx_init(UFFD_FEATURE_WP_UNPOPULATED, NULL)) + err("context init failed"); + + if (posix_memalign(&area, page_size, page_size)) + err("out of memory"); + zeropage = area; + bzero(zeropage, page_size); + + pthread_mutex_lock(&uffd_read_mutex); + + pthread_attr_init(&attr); + pthread_attr_setstacksize(&attr, 16*1024*1024); + + while (bounces--) { + printf("bounces: %d, mode:", bounces); + if (bounces & BOUNCE_RANDOM) + printf(" rnd"); + if (bounces & BOUNCE_RACINGFAULTS) + printf(" racing"); + if (bounces & BOUNCE_VERIFY) + printf(" ver"); + if (bounces & BOUNCE_POLL) + printf(" poll"); + else + printf(" read"); + printf(", "); + fflush(stdout); + + if (bounces & BOUNCE_POLL) + fcntl(uffd, F_SETFL, uffd_flags | O_NONBLOCK); + else + fcntl(uffd, F_SETFL, uffd_flags & ~O_NONBLOCK); + + /* register */ + if (uffd_register(uffd, area_dst, mem_size, + true, test_uffdio_wp, false)) + err("register failure"); + + if (area_dst_alias) { + if (uffd_register(uffd, area_dst_alias, mem_size, + true, test_uffdio_wp, false)) + err("register failure alias"); + } + + /* + * The madvise done previously isn't enough: some + * uffd_thread could have read userfaults (one of + * those already resolved by the background thread) + * and it may be in the process of calling + * UFFDIO_COPY. UFFDIO_COPY will read the zapped + * area_src and it would map a zero page in it (of + * course such a UFFDIO_COPY is perfectly safe as it'd + * return -EEXIST). The problem comes at the next + * bounce though: that racing UFFDIO_COPY would + * generate zeropages in the area_src, so invalidating + * the previous MADV_DONTNEED. Without this additional + * MADV_DONTNEED those zeropages leftovers in the + * area_src would lead to -EEXIST failure during the + * next bounce, effectively leaving a zeropage in the + * area_dst. + * + * Try to comment this out madvise to see the memory + * corruption being caught pretty quick. + * + * khugepaged is also inhibited to collapse THP after + * MADV_DONTNEED only after the UFFDIO_REGISTER, so it's + * required to MADV_DONTNEED here. + */ + uffd_test_ops->release_pages(area_dst); + + uffd_stats_reset(args, nr_cpus); + + /* bounce pass */ + if (stress(args)) + return 1; + + /* Clear all the write protections if there is any */ + if (test_uffdio_wp) + wp_range(uffd, (unsigned long)area_dst, + nr_pages * page_size, false); + + /* unregister */ + if (uffd_unregister(uffd, area_dst, mem_size)) + err("unregister failure"); + if (area_dst_alias) { + if (uffd_unregister(uffd, area_dst_alias, mem_size)) + err("unregister failure alias"); + } + + /* verification */ + if (bounces & BOUNCE_VERIFY) + for (nr = 0; nr < nr_pages; nr++) + if (*area_count(area_dst, nr) != count_verify[nr]) + err("error area_count %llu %llu %lu\n", + *area_count(area_src, nr), + count_verify[nr], nr); + + /* prepare next bounce */ + swap(area_src, area_dst); + + swap(area_src_alias, area_dst_alias); + + uffd_stats_report(args, nr_cpus); + } + + return 0; +} + +static void set_test_type(const char *type) +{ + if (!strcmp(type, "anon")) { + test_type = TEST_ANON; + uffd_test_ops = &anon_uffd_test_ops; + } else if (!strcmp(type, "hugetlb")) { + test_type = TEST_HUGETLB; + uffd_test_ops = &hugetlb_uffd_test_ops; + map_shared = true; + } else if (!strcmp(type, "hugetlb-private")) { + 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 if (!strcmp(type, "shmem-private")) { + test_type = TEST_SHMEM; + uffd_test_ops = &shmem_uffd_test_ops; + } +} + +static void parse_test_type_arg(const char *raw_type) +{ + uint64_t features = UFFD_API_FEATURES; + + set_test_type(raw_type); + + if (!test_type) + err("failed to parse test type argument: '%s'", raw_type); + + if (test_type == TEST_HUGETLB) + page_size = default_huge_page_size(); + else + page_size = sysconf(_SC_PAGE_SIZE); + + if (!page_size) + err("Unable to determine page size"); + if ((unsigned long) area_count(NULL, 0) + sizeof(unsigned long long) * 2 + > page_size) + err("Impossible to run this test"); + + /* + * Whether we can test certain features depends not just on test type, + * but also on whether or not this particular kernel supports the + * feature. + */ + + if (userfaultfd_open(&features)) + err("Userfaultfd open failed"); + + test_uffdio_wp = test_uffdio_wp && + (features & UFFD_FEATURE_PAGEFAULT_FLAG_WP); + + close(uffd); + uffd = -1; +} + +static void sigalrm(int sig) +{ + if (sig != SIGALRM) + abort(); + test_uffdio_copy_eexist = true; + alarm(ALARM_INTERVAL_SECS); +} + +int main(int argc, char **argv) +{ + size_t bytes; + + if (argc < 4) + usage(); + + if (signal(SIGALRM, sigalrm) == SIG_ERR) + err("failed to arm SIGALRM"); + alarm(ALARM_INTERVAL_SECS); + + parse_test_type_arg(argv[1]); + bytes = atol(argv[2]) * 1024 * 1024; + + nr_cpus = sysconf(_SC_NPROCESSORS_ONLN); + + nr_pages_per_cpu = bytes / page_size / nr_cpus; + if (!nr_pages_per_cpu) { + _err("invalid MiB"); + usage(); + } + + bounces = atoi(argv[3]); + if (bounces <= 0) { + _err("invalid bounces"); + usage(); + } + nr_pages = nr_pages_per_cpu * nr_cpus; + + printf("nr_pages: %lu, nr_pages_per_cpu: %lu\n", + nr_pages, nr_pages_per_cpu); + return userfaultfd_stress(); +} + +#else /* __NR_userfaultfd */ + +#warning "missing __NR_userfaultfd definition" + +int main(void) +{ + printf("skip: Skipping userfaultfd test (missing __NR_userfaultfd)\n"); + return KSFT_SKIP; +} + +#endif /* __NR_userfaultfd */ diff --git a/tools/testing/selftests/mm/uffd-unit-tests.c b/tools/testing/selftests/mm/uffd-unit-tests.c new file mode 100644 index 000000000000..269c86768a02 --- /dev/null +++ b/tools/testing/selftests/mm/uffd-unit-tests.c @@ -0,0 +1,1228 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Userfaultfd unit tests. + * + * Copyright (C) 2015-2023 Red Hat, Inc. + */ + +#include "uffd-common.h" + +#include "../../../../mm/gup_test.h" + +#ifdef __NR_userfaultfd + +/* The unit test doesn't need a large or random size, make it 32MB for now */ +#define UFFD_TEST_MEM_SIZE (32UL << 20) + +#define MEM_ANON BIT_ULL(0) +#define MEM_SHMEM BIT_ULL(1) +#define MEM_SHMEM_PRIVATE BIT_ULL(2) +#define MEM_HUGETLB BIT_ULL(3) +#define MEM_HUGETLB_PRIVATE BIT_ULL(4) + +#define MEM_ALL (MEM_ANON | MEM_SHMEM | MEM_SHMEM_PRIVATE | \ + MEM_HUGETLB | MEM_HUGETLB_PRIVATE) + +struct mem_type { + const char *name; + unsigned int mem_flag; + uffd_test_ops_t *mem_ops; + bool shared; +}; +typedef struct mem_type mem_type_t; + +mem_type_t mem_types[] = { + { + .name = "anon", + .mem_flag = MEM_ANON, + .mem_ops = &anon_uffd_test_ops, + .shared = false, + }, + { + .name = "shmem", + .mem_flag = MEM_SHMEM, + .mem_ops = &shmem_uffd_test_ops, + .shared = true, + }, + { + .name = "shmem-private", + .mem_flag = MEM_SHMEM_PRIVATE, + .mem_ops = &shmem_uffd_test_ops, + .shared = false, + }, + { + .name = "hugetlb", + .mem_flag = MEM_HUGETLB, + .mem_ops = &hugetlb_uffd_test_ops, + .shared = true, + }, + { + .name = "hugetlb-private", + .mem_flag = MEM_HUGETLB_PRIVATE, + .mem_ops = &hugetlb_uffd_test_ops, + .shared = false, + }, +}; + +/* Arguments to be passed over to each uffd unit test */ +struct uffd_test_args { + mem_type_t *mem_type; +}; +typedef struct uffd_test_args uffd_test_args_t; + +/* Returns: UFFD_TEST_* */ +typedef void (*uffd_test_fn)(uffd_test_args_t *); + +typedef struct { + const char *name; + uffd_test_fn uffd_fn; + unsigned int mem_targets; + uint64_t uffd_feature_required; +} uffd_test_case_t; + +static void uffd_test_report(void) +{ + printf("Userfaults unit tests: pass=%u, skip=%u, fail=%u (total=%u)\n", + ksft_get_pass_cnt(), + ksft_get_xskip_cnt(), + ksft_get_fail_cnt(), + ksft_test_num()); +} + +static void uffd_test_pass(void) +{ + printf("done\n"); + ksft_inc_pass_cnt(); +} + +#define uffd_test_start(...) do { \ + printf("Testing "); \ + printf(__VA_ARGS__); \ + printf("... "); \ + fflush(stdout); \ + } while (0) + +#define uffd_test_fail(...) do { \ + printf("failed [reason: "); \ + printf(__VA_ARGS__); \ + printf("]\n"); \ + ksft_inc_fail_cnt(); \ + } while (0) + +#define uffd_test_skip(...) do { \ + printf("skipped [reason: "); \ + printf(__VA_ARGS__); \ + printf("]\n"); \ + ksft_inc_xskip_cnt(); \ + } while (0) + +/* + * Returns 1 if specific userfaultfd supported, 0 otherwise. Note, we'll + * return 1 even if some test failed as long as uffd supported, because in + * that case we still want to proceed with the rest uffd unit tests. + */ +static int test_uffd_api(bool use_dev) +{ + struct uffdio_api uffdio_api; + int uffd; + + uffd_test_start("UFFDIO_API (with %s)", + use_dev ? "/dev/userfaultfd" : "syscall"); + + if (use_dev) + uffd = uffd_open_dev(UFFD_FLAGS); + else + uffd = uffd_open_sys(UFFD_FLAGS); + if (uffd < 0) { + uffd_test_skip("cannot open userfaultfd handle"); + return 0; + } + + /* Test wrong UFFD_API */ + uffdio_api.api = 0xab; + uffdio_api.features = 0; + if (ioctl(uffd, UFFDIO_API, &uffdio_api) == 0) { + uffd_test_fail("UFFDIO_API should fail with wrong api but didn't"); + goto out; + } + + /* Test wrong feature bit */ + uffdio_api.api = UFFD_API; + uffdio_api.features = BIT_ULL(63); + if (ioctl(uffd, UFFDIO_API, &uffdio_api) == 0) { + uffd_test_fail("UFFDIO_API should fail with wrong feature but didn't"); + goto out; + } + + /* Test normal UFFDIO_API */ + uffdio_api.api = UFFD_API; + uffdio_api.features = 0; + if (ioctl(uffd, UFFDIO_API, &uffdio_api)) { + uffd_test_fail("UFFDIO_API should succeed but failed"); + goto out; + } + + /* Test double requests of UFFDIO_API with a random feature set */ + uffdio_api.features = BIT_ULL(0); + if (ioctl(uffd, UFFDIO_API, &uffdio_api) == 0) { + uffd_test_fail("UFFDIO_API should reject initialized uffd"); + goto out; + } + + uffd_test_pass(); +out: + close(uffd); + /* We have a valid uffd handle */ + return 1; +} + +/* + * This function initializes the global variables. TODO: remove global + * vars and then remove this. + */ +static int +uffd_setup_environment(uffd_test_args_t *args, uffd_test_case_t *test, + mem_type_t *mem_type, const char **errmsg) +{ + map_shared = mem_type->shared; + uffd_test_ops = mem_type->mem_ops; + + if (mem_type->mem_flag & (MEM_HUGETLB_PRIVATE | MEM_HUGETLB)) + page_size = default_huge_page_size(); + else + page_size = psize(); + + nr_pages = UFFD_TEST_MEM_SIZE / page_size; + /* TODO: remove this global var.. it's so ugly */ + nr_cpus = 1; + + /* Initialize test arguments */ + args->mem_type = mem_type; + + return uffd_test_ctx_init(test->uffd_feature_required, errmsg); +} + +static bool uffd_feature_supported(uffd_test_case_t *test) +{ + uint64_t features; + + if (uffd_get_features(&features)) + return false; + + return (features & test->uffd_feature_required) == + test->uffd_feature_required; +} + +static int pagemap_open(void) +{ + int fd = open("/proc/self/pagemap", O_RDONLY); + + if (fd < 0) + err("open pagemap"); + + return fd; +} + +/* This macro let __LINE__ works in err() */ +#define pagemap_check_wp(value, wp) do { \ + if (!!(value & PM_UFFD_WP) != wp) \ + err("pagemap uffd-wp bit error: 0x%"PRIx64, value); \ + } while (0) + +typedef struct { + int parent_uffd, child_uffd; +} fork_event_args; + +static void *fork_event_consumer(void *data) +{ + fork_event_args *args = data; + struct uffd_msg msg = { 0 }; + + /* Read until a full msg received */ + while (uffd_read_msg(args->parent_uffd, &msg)); + + if (msg.event != UFFD_EVENT_FORK) + err("wrong message: %u\n", msg.event); + + /* Just to be properly freed later */ + args->child_uffd = msg.arg.fork.ufd; + return NULL; +} + +typedef struct { + int gup_fd; + bool pinned; +} pin_args; + +/* + * Returns 0 if succeed, <0 for errors. pin_pages() needs to be paired + * with unpin_pages(). Currently it needs to be RO longterm pin to satisfy + * all needs of the test cases (e.g., trigger unshare, trigger fork() early + * CoW, etc.). + */ +static int pin_pages(pin_args *args, void *buffer, size_t size) +{ + struct pin_longterm_test test = { + .addr = (uintptr_t)buffer, + .size = size, + /* Read-only pins */ + .flags = 0, + }; + + if (args->pinned) + err("already pinned"); + + args->gup_fd = open("/sys/kernel/debug/gup_test", O_RDWR); + if (args->gup_fd < 0) + return -errno; + + if (ioctl(args->gup_fd, PIN_LONGTERM_TEST_START, &test)) { + /* Even if gup_test existed, can be an old gup_test / kernel */ + close(args->gup_fd); + return -errno; + } + args->pinned = true; + return 0; +} + +static void unpin_pages(pin_args *args) +{ + if (!args->pinned) + err("unpin without pin first"); + if (ioctl(args->gup_fd, PIN_LONGTERM_TEST_STOP)) + err("PIN_LONGTERM_TEST_STOP"); + close(args->gup_fd); + args->pinned = false; +} + +static int pagemap_test_fork(int uffd, bool with_event, bool test_pin) +{ + fork_event_args args = { .parent_uffd = uffd, .child_uffd = -1 }; + pthread_t thread; + pid_t child; + uint64_t value; + int fd, result; + + /* Prepare a thread to resolve EVENT_FORK */ + if (with_event) { + if (pthread_create(&thread, NULL, fork_event_consumer, &args)) + err("pthread_create()"); + } + + child = fork(); + if (!child) { + /* Open the pagemap fd of the child itself */ + pin_args args = {}; + + fd = pagemap_open(); + + if (test_pin && pin_pages(&args, area_dst, page_size)) + /* + * Normally when reach here we have pinned in + * previous tests, so shouldn't fail anymore + */ + err("pin page failed in child"); + + value = pagemap_get_entry(fd, area_dst); + /* + * After fork(), we should handle uffd-wp bit differently: + * + * (1) when with EVENT_FORK, it should persist + * (2) when without EVENT_FORK, it should be dropped + */ + pagemap_check_wp(value, with_event); + if (test_pin) + unpin_pages(&args); + /* Succeed */ + exit(0); + } + waitpid(child, &result, 0); + + if (with_event) { + if (pthread_join(thread, NULL)) + err("pthread_join()"); + if (args.child_uffd < 0) + err("Didn't receive child uffd"); + close(args.child_uffd); + } + + return result; +} + +static void uffd_wp_unpopulated_test(uffd_test_args_t *args) +{ + uint64_t value; + int pagemap_fd; + + if (uffd_register(uffd, area_dst, nr_pages * page_size, + false, true, false)) + err("register failed"); + + pagemap_fd = pagemap_open(); + + /* Test applying pte marker to anon unpopulated */ + wp_range(uffd, (uint64_t)area_dst, page_size, true); + value = pagemap_get_entry(pagemap_fd, area_dst); + pagemap_check_wp(value, true); + + /* Test unprotect on anon pte marker */ + wp_range(uffd, (uint64_t)area_dst, page_size, false); + value = pagemap_get_entry(pagemap_fd, area_dst); + pagemap_check_wp(value, false); + + /* Test zap on anon marker */ + wp_range(uffd, (uint64_t)area_dst, page_size, true); + if (madvise(area_dst, page_size, MADV_DONTNEED)) + err("madvise(MADV_DONTNEED) failed"); + value = pagemap_get_entry(pagemap_fd, area_dst); + pagemap_check_wp(value, false); + + /* Test fault in after marker removed */ + *area_dst = 1; + value = pagemap_get_entry(pagemap_fd, area_dst); + pagemap_check_wp(value, false); + /* Drop it to make pte none again */ + if (madvise(area_dst, page_size, MADV_DONTNEED)) + err("madvise(MADV_DONTNEED) failed"); + + /* Test read-zero-page upon pte marker */ + wp_range(uffd, (uint64_t)area_dst, page_size, true); + *(volatile char *)area_dst; + /* Drop it to make pte none again */ + if (madvise(area_dst, page_size, MADV_DONTNEED)) + err("madvise(MADV_DONTNEED) failed"); + + uffd_test_pass(); +} + +static void uffd_wp_fork_test_common(uffd_test_args_t *args, + bool with_event) +{ + int pagemap_fd; + uint64_t value; + + if (uffd_register(uffd, area_dst, nr_pages * page_size, + false, true, false)) + err("register failed"); + + pagemap_fd = pagemap_open(); + + /* Touch the page */ + *area_dst = 1; + wp_range(uffd, (uint64_t)area_dst, page_size, true); + value = pagemap_get_entry(pagemap_fd, area_dst); + pagemap_check_wp(value, true); + if (pagemap_test_fork(uffd, with_event, false)) { + uffd_test_fail("Detected %s uffd-wp bit in child in present pte", + with_event ? "missing" : "stall"); + goto out; + } + + /* + * This is an attempt for zapping the pgtable so as to test the + * markers. + * + * For private mappings, PAGEOUT will only work on exclusive ptes + * (PM_MMAP_EXCLUSIVE) which we should satisfy. + * + * For shared, PAGEOUT may not work. Use DONTNEED instead which + * plays a similar role of zapping (rather than freeing the page) + * to expose pte markers. + */ + if (args->mem_type->shared) { + if (madvise(area_dst, page_size, MADV_DONTNEED)) + err("MADV_DONTNEED"); + } else { + /* + * NOTE: ignore retval because private-hugetlb doesn't yet + * support swapping, so it could fail. + */ + madvise(area_dst, page_size, MADV_PAGEOUT); + } + + /* Uffd-wp should persist even swapped out */ + value = pagemap_get_entry(pagemap_fd, area_dst); + pagemap_check_wp(value, true); + if (pagemap_test_fork(uffd, with_event, false)) { + uffd_test_fail("Detected %s uffd-wp bit in child in zapped pte", + with_event ? "missing" : "stall"); + goto out; + } + + /* Unprotect; this tests swap pte modifications */ + wp_range(uffd, (uint64_t)area_dst, page_size, false); + value = pagemap_get_entry(pagemap_fd, area_dst); + pagemap_check_wp(value, false); + + /* Fault in the page from disk */ + *area_dst = 2; + value = pagemap_get_entry(pagemap_fd, area_dst); + pagemap_check_wp(value, false); + uffd_test_pass(); +out: + if (uffd_unregister(uffd, area_dst, nr_pages * page_size)) + err("unregister failed"); + close(pagemap_fd); +} + +static void uffd_wp_fork_test(uffd_test_args_t *args) +{ + uffd_wp_fork_test_common(args, false); +} + +static void uffd_wp_fork_with_event_test(uffd_test_args_t *args) +{ + uffd_wp_fork_test_common(args, true); +} + +static void uffd_wp_fork_pin_test_common(uffd_test_args_t *args, + bool with_event) +{ + int pagemap_fd; + pin_args pin_args = {}; + + if (uffd_register(uffd, area_dst, page_size, false, true, false)) + err("register failed"); + + pagemap_fd = pagemap_open(); + + /* Touch the page */ + *area_dst = 1; + wp_range(uffd, (uint64_t)area_dst, page_size, true); + + /* + * 1. First pin, then fork(). This tests fork() special path when + * doing early CoW if the page is private. + */ + if (pin_pages(&pin_args, area_dst, page_size)) { + uffd_test_skip("Possibly CONFIG_GUP_TEST missing " + "or unprivileged"); + close(pagemap_fd); + uffd_unregister(uffd, area_dst, page_size); + return; + } + + if (pagemap_test_fork(uffd, with_event, false)) { + uffd_test_fail("Detected %s uffd-wp bit in early CoW of fork()", + with_event ? "missing" : "stall"); + unpin_pages(&pin_args); + goto out; + } + + unpin_pages(&pin_args); + + /* + * 2. First fork(), then pin (in the child, where test_pin==true). + * This tests COR, aka, page unsharing on private memories. + */ + if (pagemap_test_fork(uffd, with_event, true)) { + uffd_test_fail("Detected %s uffd-wp bit when RO pin", + with_event ? "missing" : "stall"); + goto out; + } + uffd_test_pass(); +out: + if (uffd_unregister(uffd, area_dst, page_size)) + err("register failed"); + close(pagemap_fd); +} + +static void uffd_wp_fork_pin_test(uffd_test_args_t *args) +{ + uffd_wp_fork_pin_test_common(args, false); +} + +static void uffd_wp_fork_pin_with_event_test(uffd_test_args_t *args) +{ + uffd_wp_fork_pin_test_common(args, true); +} + +static void check_memory_contents(char *p) +{ + unsigned long i, j; + uint8_t expected_byte; + + for (i = 0; i < nr_pages; ++i) { + expected_byte = ~((uint8_t)(i % ((uint8_t)-1))); + for (j = 0; j < page_size; j++) { + uint8_t v = *(uint8_t *)(p + (i * page_size) + j); + if (v != expected_byte) + err("unexpected page contents"); + } + } +} + +static void uffd_minor_test_common(bool test_collapse, bool test_wp) +{ + unsigned long p; + pthread_t uffd_mon; + char c; + struct uffd_args args = { 0 }; + + /* + * NOTE: MADV_COLLAPSE is not yet compatible with WP, so testing + * both do not make much sense. + */ + assert(!(test_collapse && test_wp)); + + if (uffd_register(uffd, area_dst_alias, nr_pages * page_size, + /* NOTE! MADV_COLLAPSE may not work with uffd-wp */ + false, test_wp, true)) + err("register failure"); + + /* + * After registering with UFFD, populate the non-UFFD-registered side of + * the shared mapping. This should *not* trigger any UFFD minor faults. + */ + for (p = 0; p < nr_pages; ++p) + memset(area_dst + (p * page_size), p % ((uint8_t)-1), + page_size); + + args.apply_wp = test_wp; + if (pthread_create(&uffd_mon, NULL, uffd_poll_thread, &args)) + err("uffd_poll_thread create"); + + /* + * Read each of the pages back using the UFFD-registered mapping. We + * expect that the first time we touch a page, it will result in a minor + * fault. uffd_poll_thread will resolve the fault by bit-flipping the + * page's contents, and then issuing a CONTINUE ioctl. + */ + check_memory_contents(area_dst_alias); + + if (write(pipefd[1], &c, sizeof(c)) != sizeof(c)) + err("pipe write"); + if (pthread_join(uffd_mon, NULL)) + err("join() failed"); + + if (test_collapse) { + if (madvise(area_dst_alias, nr_pages * page_size, + MADV_COLLAPSE)) { + /* It's fine to fail for this one... */ + uffd_test_skip("MADV_COLLAPSE failed"); + return; + } + + uffd_test_ops->check_pmd_mapping(area_dst, + nr_pages * page_size / + read_pmd_pagesize()); + /* + * This won't cause uffd-fault - it purely just makes sure there + * was no corruption. + */ + check_memory_contents(area_dst_alias); + } + + if (args.missing_faults != 0 || args.minor_faults != nr_pages) + uffd_test_fail("stats check error"); + else + uffd_test_pass(); +} + +void uffd_minor_test(uffd_test_args_t *args) +{ + uffd_minor_test_common(false, false); +} + +void uffd_minor_wp_test(uffd_test_args_t *args) +{ + uffd_minor_test_common(false, true); +} + +void uffd_minor_collapse_test(uffd_test_args_t *args) +{ + uffd_minor_test_common(true, false); +} + +static 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 + * userfaultfd and at last this process will release the monitored + * area. + * For the anonymous and shared memory the area is divided into two + * parts, the first part is accessed before mremap, and the second + * part is accessed after mremap. Since hugetlbfs does not support + * mremap, the entire monitored area is accessed in a single pass for + * HUGETLB_TEST. + * 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(int signal_test, bool wp) +{ + unsigned long nr, i; + unsigned long long count; + unsigned long split_nr_pages; + unsigned long lastnr; + struct sigaction act; + volatile unsigned long signalled = 0; + + split_nr_pages = (nr_pages + 1) / 2; + + if (signal_test) { + sigbuf = &jbuf; + memset(&act, 0, sizeof(act)); + act.sa_sigaction = sighndl; + act.sa_flags = SA_SIGINFO; + if (sigaction(SIGBUS, &act, 0)) + err("sigaction"); + lastnr = (unsigned long)-1; + } + + for (nr = 0; nr < split_nr_pages; nr++) { + volatile int steps = 1; + unsigned long offset = nr * page_size; + + if (signal_test) { + if (sigsetjmp(*sigbuf, 1) != 0) { + if (steps == 1 && nr == lastnr) + err("Signal repeated"); + + lastnr = nr; + if (signal_test == 1) { + if (steps == 1) { + /* This is a MISSING request */ + steps++; + if (copy_page(uffd, offset, wp)) + signalled++; + } else { + /* This is a WP request */ + assert(steps == 2); + wp_range(uffd, + (__u64)area_dst + + offset, + page_size, false); + } + } else { + signalled++; + continue; + } + } + } + + count = *area_count(area_dst, nr); + if (count != count_verify[nr]) + err("nr %lu memory corruption %llu %llu\n", + nr, count, count_verify[nr]); + /* + * Trigger write protection if there is by writing + * the same value back. + */ + *area_count(area_dst, nr) = count; + } + + if (signal_test) + return signalled != split_nr_pages; + + area_dst = mremap(area_dst, nr_pages * page_size, nr_pages * page_size, + MREMAP_MAYMOVE | MREMAP_FIXED, area_src); + if (area_dst == MAP_FAILED) + err("mremap"); + /* Reset area_src since we just clobbered it */ + area_src = NULL; + + for (; nr < nr_pages; nr++) { + count = *area_count(area_dst, nr); + if (count != count_verify[nr]) { + err("nr %lu memory corruption %llu %llu\n", + nr, count, count_verify[nr]); + } + /* + * Trigger write protection if there is by writing + * the same value back. + */ + *area_count(area_dst, nr) = count; + } + + uffd_test_ops->release_pages(area_dst); + + for (nr = 0; nr < nr_pages; nr++) + for (i = 0; i < page_size; i++) + if (*(area_dst + nr * page_size + i) != 0) + err("page %lu offset %lu is not zero", nr, i); + + return 0; +} + +static void uffd_sigbus_test_common(bool wp) +{ + unsigned long userfaults; + pthread_t uffd_mon; + pid_t pid; + int err; + char c; + struct uffd_args args = { 0 }; + + fcntl(uffd, F_SETFL, uffd_flags | O_NONBLOCK); + + if (uffd_register(uffd, area_dst, nr_pages * page_size, + true, wp, false)) + err("register failure"); + + if (faulting_process(1, wp)) + err("faulting process failed"); + + uffd_test_ops->release_pages(area_dst); + + args.apply_wp = wp; + if (pthread_create(&uffd_mon, NULL, uffd_poll_thread, &args)) + err("uffd_poll_thread create"); + + pid = fork(); + if (pid < 0) + err("fork"); + + if (!pid) + exit(faulting_process(2, wp)); + + waitpid(pid, &err, 0); + if (err) + err("faulting process failed"); + if (write(pipefd[1], &c, sizeof(c)) != sizeof(c)) + err("pipe write"); + if (pthread_join(uffd_mon, (void **)&userfaults)) + err("pthread_join()"); + + if (userfaults) + uffd_test_fail("Signal test failed, userfaults: %ld", userfaults); + else + uffd_test_pass(); +} + +static void uffd_sigbus_test(uffd_test_args_t *args) +{ + uffd_sigbus_test_common(false); +} + +static void uffd_sigbus_wp_test(uffd_test_args_t *args) +{ + uffd_sigbus_test_common(true); +} + +static void uffd_events_test_common(bool wp) +{ + pthread_t uffd_mon; + pid_t pid; + int err; + char c; + struct uffd_args args = { 0 }; + + fcntl(uffd, F_SETFL, uffd_flags | O_NONBLOCK); + if (uffd_register(uffd, area_dst, nr_pages * page_size, + true, wp, false)) + err("register failure"); + + args.apply_wp = wp; + if (pthread_create(&uffd_mon, NULL, uffd_poll_thread, &args)) + err("uffd_poll_thread create"); + + pid = fork(); + if (pid < 0) + err("fork"); + + if (!pid) + exit(faulting_process(0, wp)); + + waitpid(pid, &err, 0); + if (err) + err("faulting process failed"); + if (write(pipefd[1], &c, sizeof(c)) != sizeof(c)) + err("pipe write"); + if (pthread_join(uffd_mon, NULL)) + err("pthread_join()"); + + if (args.missing_faults != nr_pages) + uffd_test_fail("Fault counts wrong"); + else + uffd_test_pass(); +} + +static void uffd_events_test(uffd_test_args_t *args) +{ + uffd_events_test_common(false); +} + +static void uffd_events_wp_test(uffd_test_args_t *args) +{ + uffd_events_test_common(true); +} + +static void retry_uffdio_zeropage(int ufd, + struct uffdio_zeropage *uffdio_zeropage) +{ + uffd_test_ops->alias_mapping(&uffdio_zeropage->range.start, + uffdio_zeropage->range.len, + 0); + if (ioctl(ufd, UFFDIO_ZEROPAGE, uffdio_zeropage)) { + if (uffdio_zeropage->zeropage != -EEXIST) + err("UFFDIO_ZEROPAGE error: %"PRId64, + (int64_t)uffdio_zeropage->zeropage); + } else { + err("UFFDIO_ZEROPAGE error: %"PRId64, + (int64_t)uffdio_zeropage->zeropage); + } +} + +static bool do_uffdio_zeropage(int ufd, bool has_zeropage) +{ + struct uffdio_zeropage uffdio_zeropage = { 0 }; + int ret; + __s64 res; + + uffdio_zeropage.range.start = (unsigned long) area_dst; + uffdio_zeropage.range.len = page_size; + uffdio_zeropage.mode = 0; + ret = ioctl(ufd, UFFDIO_ZEROPAGE, &uffdio_zeropage); + res = uffdio_zeropage.zeropage; + if (ret) { + /* real retval in ufdio_zeropage.zeropage */ + if (has_zeropage) + err("UFFDIO_ZEROPAGE error: %"PRId64, (int64_t)res); + else if (res != -EINVAL) + err("UFFDIO_ZEROPAGE not -EINVAL"); + } else if (has_zeropage) { + if (res != page_size) + err("UFFDIO_ZEROPAGE unexpected size"); + else + retry_uffdio_zeropage(ufd, &uffdio_zeropage); + return true; + } else + err("UFFDIO_ZEROPAGE succeeded"); + + return false; +} + +/* + * Registers a range with MISSING mode only for zeropage test. Return true + * if UFFDIO_ZEROPAGE supported, false otherwise. Can't use uffd_register() + * because we want to detect .ioctls along the way. + */ +static bool +uffd_register_detect_zeropage(int uffd, void *addr, uint64_t len) +{ + uint64_t ioctls = 0; + + if (uffd_register_with_ioctls(uffd, addr, len, true, + false, false, &ioctls)) + err("zeropage register fail"); + + return ioctls & (1 << _UFFDIO_ZEROPAGE); +} + +/* exercise UFFDIO_ZEROPAGE */ +static void uffd_zeropage_test(uffd_test_args_t *args) +{ + bool has_zeropage; + int i; + + has_zeropage = uffd_register_detect_zeropage(uffd, area_dst, page_size); + if (area_dst_alias) + /* Ignore the retval; we already have it */ + uffd_register_detect_zeropage(uffd, area_dst_alias, page_size); + + if (do_uffdio_zeropage(uffd, has_zeropage)) + for (i = 0; i < page_size; i++) + if (area_dst[i] != 0) + err("data non-zero at offset %d\n", i); + + if (uffd_unregister(uffd, area_dst, page_size)) + err("unregister"); + + if (area_dst_alias && uffd_unregister(uffd, area_dst_alias, page_size)) + err("unregister"); + + uffd_test_pass(); +} + +/* + * Test the returned uffdio_register.ioctls with different register modes. + * Note that _UFFDIO_ZEROPAGE is tested separately in the zeropage test. + */ +static void +do_register_ioctls_test(uffd_test_args_t *args, bool miss, bool wp, bool minor) +{ + uint64_t ioctls = 0, expected = BIT_ULL(_UFFDIO_WAKE); + mem_type_t *mem_type = args->mem_type; + int ret; + + ret = uffd_register_with_ioctls(uffd, area_dst, page_size, + miss, wp, minor, &ioctls); + + /* + * Handle special cases of UFFDIO_REGISTER here where it should + * just fail with -EINVAL first.. + * + * Case 1: register MINOR on anon + * Case 2: register with no mode selected + */ + if ((minor && (mem_type->mem_flag == MEM_ANON)) || + (!miss && !wp && !minor)) { + if (ret != -EINVAL) + err("register (miss=%d, wp=%d, minor=%d) failed " + "with wrong errno=%d", miss, wp, minor, ret); + return; + } + + /* UFFDIO_REGISTER should succeed, then check ioctls returned */ + if (miss) + expected |= BIT_ULL(_UFFDIO_COPY); + if (wp) + expected |= BIT_ULL(_UFFDIO_WRITEPROTECT); + if (minor) + expected |= BIT_ULL(_UFFDIO_CONTINUE); + + if ((ioctls & expected) != expected) + err("unexpected uffdio_register.ioctls " + "(miss=%d, wp=%d, minor=%d): expected=0x%"PRIx64", " + "returned=0x%"PRIx64, miss, wp, minor, expected, ioctls); + + if (uffd_unregister(uffd, area_dst, page_size)) + err("unregister"); +} + +static void uffd_register_ioctls_test(uffd_test_args_t *args) +{ + int miss, wp, minor; + + for (miss = 0; miss <= 1; miss++) + for (wp = 0; wp <= 1; wp++) + for (minor = 0; minor <= 1; minor++) + do_register_ioctls_test(args, miss, wp, minor); + + uffd_test_pass(); +} + +uffd_test_case_t uffd_tests[] = { + { + /* Test returned uffdio_register.ioctls. */ + .name = "register-ioctls", + .uffd_fn = uffd_register_ioctls_test, + .mem_targets = MEM_ALL, + .uffd_feature_required = UFFD_FEATURE_MISSING_HUGETLBFS | + UFFD_FEATURE_MISSING_SHMEM | + UFFD_FEATURE_PAGEFAULT_FLAG_WP | + UFFD_FEATURE_WP_HUGETLBFS_SHMEM | + UFFD_FEATURE_MINOR_HUGETLBFS | + UFFD_FEATURE_MINOR_SHMEM, + }, + { + .name = "zeropage", + .uffd_fn = uffd_zeropage_test, + .mem_targets = MEM_ALL, + .uffd_feature_required = 0, + }, + { + .name = "wp-fork", + .uffd_fn = uffd_wp_fork_test, + .mem_targets = MEM_ALL, + .uffd_feature_required = UFFD_FEATURE_PAGEFAULT_FLAG_WP | + UFFD_FEATURE_WP_HUGETLBFS_SHMEM, + }, + { + .name = "wp-fork-with-event", + .uffd_fn = uffd_wp_fork_with_event_test, + .mem_targets = MEM_ALL, + .uffd_feature_required = UFFD_FEATURE_PAGEFAULT_FLAG_WP | + UFFD_FEATURE_WP_HUGETLBFS_SHMEM | + /* when set, child process should inherit uffd-wp bits */ + UFFD_FEATURE_EVENT_FORK, + }, + { + .name = "wp-fork-pin", + .uffd_fn = uffd_wp_fork_pin_test, + .mem_targets = MEM_ALL, + .uffd_feature_required = UFFD_FEATURE_PAGEFAULT_FLAG_WP | + UFFD_FEATURE_WP_HUGETLBFS_SHMEM, + }, + { + .name = "wp-fork-pin-with-event", + .uffd_fn = uffd_wp_fork_pin_with_event_test, + .mem_targets = MEM_ALL, + .uffd_feature_required = UFFD_FEATURE_PAGEFAULT_FLAG_WP | + UFFD_FEATURE_WP_HUGETLBFS_SHMEM | + /* when set, child process should inherit uffd-wp bits */ + UFFD_FEATURE_EVENT_FORK, + }, + { + .name = "wp-unpopulated", + .uffd_fn = uffd_wp_unpopulated_test, + .mem_targets = MEM_ANON, + .uffd_feature_required = + UFFD_FEATURE_PAGEFAULT_FLAG_WP | UFFD_FEATURE_WP_UNPOPULATED, + }, + { + .name = "minor", + .uffd_fn = uffd_minor_test, + .mem_targets = MEM_SHMEM | MEM_HUGETLB, + .uffd_feature_required = + UFFD_FEATURE_MINOR_HUGETLBFS | UFFD_FEATURE_MINOR_SHMEM, + }, + { + .name = "minor-wp", + .uffd_fn = uffd_minor_wp_test, + .mem_targets = MEM_SHMEM | MEM_HUGETLB, + .uffd_feature_required = + UFFD_FEATURE_MINOR_HUGETLBFS | UFFD_FEATURE_MINOR_SHMEM | + UFFD_FEATURE_PAGEFAULT_FLAG_WP | + /* + * HACK: here we leveraged WP_UNPOPULATED to detect whether + * minor mode supports wr-protect. There's no feature flag + * for it so this is the best we can test against. + */ + UFFD_FEATURE_WP_UNPOPULATED, + }, + { + .name = "minor-collapse", + .uffd_fn = uffd_minor_collapse_test, + /* MADV_COLLAPSE only works with shmem */ + .mem_targets = MEM_SHMEM, + /* We can't test MADV_COLLAPSE, so try our luck */ + .uffd_feature_required = UFFD_FEATURE_MINOR_SHMEM, + }, + { + .name = "sigbus", + .uffd_fn = uffd_sigbus_test, + .mem_targets = MEM_ALL, + .uffd_feature_required = UFFD_FEATURE_SIGBUS | + UFFD_FEATURE_EVENT_FORK, + }, + { + .name = "sigbus-wp", + .uffd_fn = uffd_sigbus_wp_test, + .mem_targets = MEM_ALL, + .uffd_feature_required = UFFD_FEATURE_SIGBUS | + UFFD_FEATURE_EVENT_FORK | UFFD_FEATURE_PAGEFAULT_FLAG_WP, + }, + { + .name = "events", + .uffd_fn = uffd_events_test, + .mem_targets = MEM_ALL, + .uffd_feature_required = UFFD_FEATURE_EVENT_FORK | + UFFD_FEATURE_EVENT_REMAP | UFFD_FEATURE_EVENT_REMOVE, + }, + { + .name = "events-wp", + .uffd_fn = uffd_events_wp_test, + .mem_targets = MEM_ALL, + .uffd_feature_required = UFFD_FEATURE_EVENT_FORK | + UFFD_FEATURE_EVENT_REMAP | UFFD_FEATURE_EVENT_REMOVE | + UFFD_FEATURE_PAGEFAULT_FLAG_WP | + UFFD_FEATURE_WP_HUGETLBFS_SHMEM, + }, +}; + +static void usage(const char *prog) +{ + printf("usage: %s [-f TESTNAME]\n", prog); + puts(""); + puts(" -f: test name to filter (e.g., event)"); + puts(" -h: show the help msg"); + puts(" -l: list tests only"); + puts(""); + exit(KSFT_FAIL); +} + +int main(int argc, char *argv[]) +{ + int n_tests = sizeof(uffd_tests) / sizeof(uffd_test_case_t); + int n_mems = sizeof(mem_types) / sizeof(mem_type_t); + const char *test_filter = NULL; + bool list_only = false; + uffd_test_case_t *test; + mem_type_t *mem_type; + uffd_test_args_t args; + char test_name[128]; + const char *errmsg; + int has_uffd, opt; + int i, j; + + while ((opt = getopt(argc, argv, "f:hl")) != -1) { + switch (opt) { + case 'f': + test_filter = optarg; + break; + case 'l': + list_only = true; + break; + case 'h': + default: + /* Unknown */ + usage(argv[0]); + break; + } + } + + if (!test_filter && !list_only) { + has_uffd = test_uffd_api(false); + has_uffd |= test_uffd_api(true); + + if (!has_uffd) { + printf("Userfaultfd not supported or unprivileged, skip all tests\n"); + exit(KSFT_SKIP); + } + } + + for (i = 0; i < n_tests; i++) { + test = &uffd_tests[i]; + if (test_filter && !strstr(test->name, test_filter)) + continue; + if (list_only) { + printf("%s\n", test->name); + continue; + } + for (j = 0; j < n_mems; j++) { + mem_type = &mem_types[j]; + if (!(test->mem_targets & mem_type->mem_flag)) + continue; + snprintf(test_name, sizeof(test_name), + "%s on %s", test->name, mem_type->name); + + uffd_test_start(test_name); + if (!uffd_feature_supported(test)) { + uffd_test_skip("feature missing"); + continue; + } + if (uffd_setup_environment(&args, test, mem_type, + &errmsg)) { + uffd_test_skip(errmsg); + continue; + } + test->uffd_fn(&args); + } + } + + if (!list_only) + uffd_test_report(); + + return ksft_get_fail_cnt() ? KSFT_FAIL : KSFT_PASS; +} + +#else /* __NR_userfaultfd */ + +#warning "missing __NR_userfaultfd definition" + +int main(void) +{ + printf("Skipping %s (missing __NR_userfaultfd)\n", __file__); + return KSFT_SKIP; +} + +#endif /* __NR_userfaultfd */ diff --git a/tools/testing/selftests/mm/userfaultfd.c b/tools/testing/selftests/mm/userfaultfd.c deleted file mode 100644 index 7f22844ed704..000000000000 --- a/tools/testing/selftests/mm/userfaultfd.c +++ /dev/null @@ -1,1858 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Stress userfaultfd syscall. - * - * Copyright (C) 2015 Red Hat, Inc. - * - * This test allocates two virtual areas and bounces the physical - * memory across the two virtual areas (from area_src to area_dst) - * using userfaultfd. - * - * There are three threads running per CPU: - * - * 1) one per-CPU thread takes a per-page pthread_mutex in a random - * page of the area_dst (while the physical page may still be in - * area_src), and increments a per-page counter in the same page, - * and checks its value against a verification region. - * - * 2) another per-CPU thread handles the userfaults generated by - * thread 1 above. userfaultfd blocking reads or poll() modes are - * exercised interleaved. - * - * 3) one last per-CPU thread transfers the memory in the background - * at maximum bandwidth (if not already transferred by thread - * 2). Each cpu thread takes cares of transferring a portion of the - * area. - * - * When all threads of type 3 completed the transfer, one bounce is - * complete. area_src and area_dst are then swapped. All threads are - * respawned and so the bounce is immediately restarted in the - * opposite direction. - * - * per-CPU threads 1 by triggering userfaults inside - * pthread_mutex_lock will also verify the atomicity of the memory - * transfer (UFFDIO_COPY). - */ - -#define _GNU_SOURCE -#include <stdio.h> -#include <errno.h> -#include <unistd.h> -#include <stdlib.h> -#include <sys/types.h> -#include <sys/stat.h> -#include <fcntl.h> -#include <time.h> -#include <signal.h> -#include <poll.h> -#include <string.h> -#include <linux/mman.h> -#include <sys/mman.h> -#include <sys/syscall.h> -#include <sys/ioctl.h> -#include <sys/wait.h> -#include <pthread.h> -#include <linux/userfaultfd.h> -#include <setjmp.h> -#include <stdbool.h> -#include <assert.h> -#include <inttypes.h> -#include <stdint.h> -#include <sys/random.h> - -#include "../kselftest.h" -#include "vm_util.h" - -#ifdef __NR_userfaultfd - -static unsigned long nr_cpus, nr_pages, nr_pages_per_cpu, page_size, hpage_size; - -#define BOUNCE_RANDOM (1<<0) -#define BOUNCE_RACINGFAULTS (1<<1) -#define BOUNCE_VERIFY (1<<2) -#define BOUNCE_POLL (1<<3) -static int bounces; - -#define TEST_ANON 1 -#define TEST_HUGETLB 2 -#define TEST_SHMEM 3 -static int test_type; - -#define UFFD_FLAGS (O_CLOEXEC | O_NONBLOCK | UFFD_USER_MODE_ONLY) - -#define BASE_PMD_ADDR ((void *)(1UL << 30)) - -/* test using /dev/userfaultfd, instead of userfaultfd(2) */ -static bool test_dev_userfaultfd; - -/* 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; -/* Whether to test uffd write-protection */ -static bool test_uffdio_wp = true; -/* Whether to test uffd minor faults */ -static bool test_uffdio_minor = false; -static bool map_shared; -static int mem_fd; -static unsigned long long *count_verify; -static int uffd = -1; -static int uffd_flags, finished, *pipefd; -static char *area_src, *area_src_alias, *area_dst, *area_dst_alias, *area_remap; -static char *zeropage; -pthread_attr_t attr; -static bool test_collapse; - -/* Userfaultfd test statistics */ -struct uffd_stats { - int cpu; - unsigned long missing_faults; - unsigned long wp_faults; - unsigned long minor_faults; -}; - -/* pthread_mutex_t starts at page offset 0 */ -#define area_mutex(___area, ___nr) \ - ((pthread_mutex_t *) ((___area) + (___nr)*page_size)) -/* - * count is placed in the page after pthread_mutex_t naturally aligned - * to avoid non alignment faults on non-x86 archs. - */ -#define area_count(___area, ___nr) \ - ((volatile unsigned long long *) ((unsigned long) \ - ((___area) + (___nr)*page_size + \ - sizeof(pthread_mutex_t) + \ - sizeof(unsigned long long) - 1) & \ - ~(unsigned long)(sizeof(unsigned long long) \ - - 1))) - -#define swap(a, b) \ - do { typeof(a) __tmp = (a); (a) = (b); (b) = __tmp; } while (0) - -#define factor_of_2(x) ((x) ^ ((x) & ((x) - 1))) - -const char *examples = - "# Run anonymous memory test on 100MiB region with 99999 bounces:\n" - "./userfaultfd anon 100 99999\n\n" - "# Run the same anonymous memory test, but using /dev/userfaultfd:\n" - "./userfaultfd anon:dev 100 99999\n\n" - "# Run share memory test on 1GiB region with 99 bounces:\n" - "./userfaultfd shmem 1000 99\n\n" - "# Run hugetlb memory test on 256MiB region with 50 bounces:\n" - "./userfaultfd hugetlb 256 50\n\n" - "# Run the same hugetlb test but using shared file:\n" - "./userfaultfd hugetlb_shared 256 50\n\n" - "# 10MiB-~6GiB 999 bounces anonymous test, " - "continue forever unless an error triggers\n" - "while ./userfaultfd anon $[RANDOM % 6000 + 10] 999; do true; done\n\n"; - -static void usage(void) -{ - fprintf(stderr, "\nUsage: ./userfaultfd <test type> <MiB> <bounces> " - "[hugetlbfs_file]\n\n"); - fprintf(stderr, "Supported <test type>: anon, hugetlb, " - "hugetlb_shared, shmem\n\n"); - fprintf(stderr, "'Test mods' can be joined to the test type string with a ':'. " - "Supported mods:\n"); - fprintf(stderr, "\tsyscall - Use userfaultfd(2) (default)\n"); - fprintf(stderr, "\tdev - Use /dev/userfaultfd instead of userfaultfd(2)\n"); - fprintf(stderr, "\tcollapse - Test MADV_COLLAPSE of UFFDIO_REGISTER_MODE_MINOR\n" - "memory\n"); - fprintf(stderr, "\nExample test mod usage:\n"); - fprintf(stderr, "# Run anonymous memory test with /dev/userfaultfd:\n"); - fprintf(stderr, "./userfaultfd anon:dev 100 99999\n\n"); - - fprintf(stderr, "Examples:\n\n"); - fprintf(stderr, "%s", examples); - exit(1); -} - -#define _err(fmt, ...) \ - do { \ - int ret = errno; \ - fprintf(stderr, "ERROR: " fmt, ##__VA_ARGS__); \ - fprintf(stderr, " (errno=%d, line=%d)\n", \ - ret, __LINE__); \ - } while (0) - -#define errexit(exitcode, fmt, ...) \ - do { \ - _err(fmt, ##__VA_ARGS__); \ - exit(exitcode); \ - } while (0) - -#define err(fmt, ...) errexit(1, fmt, ##__VA_ARGS__) - -static void uffd_stats_reset(struct uffd_stats *uffd_stats, - unsigned long n_cpus) -{ - int i; - - for (i = 0; i < n_cpus; i++) { - uffd_stats[i].cpu = i; - uffd_stats[i].missing_faults = 0; - uffd_stats[i].wp_faults = 0; - uffd_stats[i].minor_faults = 0; - } -} - -static void uffd_stats_report(struct uffd_stats *stats, int n_cpus) -{ - int i; - unsigned long long miss_total = 0, wp_total = 0, minor_total = 0; - - for (i = 0; i < n_cpus; i++) { - miss_total += stats[i].missing_faults; - wp_total += stats[i].wp_faults; - minor_total += stats[i].minor_faults; - } - - printf("userfaults: "); - if (miss_total) { - printf("%llu missing (", miss_total); - for (i = 0; i < n_cpus; i++) - printf("%lu+", stats[i].missing_faults); - printf("\b) "); - } - if (wp_total) { - printf("%llu wp (", wp_total); - for (i = 0; i < n_cpus; i++) - printf("%lu+", stats[i].wp_faults); - printf("\b) "); - } - if (minor_total) { - printf("%llu minor (", minor_total); - for (i = 0; i < n_cpus; i++) - printf("%lu+", stats[i].minor_faults); - printf("\b)"); - } - printf("\n"); -} - -static void anon_release_pages(char *rel_area) -{ - if (madvise(rel_area, nr_pages * page_size, MADV_DONTNEED)) - err("madvise(MADV_DONTNEED) failed"); -} - -static void anon_allocate_area(void **alloc_area, bool is_src) -{ - *alloc_area = mmap(NULL, nr_pages * page_size, PROT_READ | PROT_WRITE, - MAP_ANONYMOUS | MAP_PRIVATE, -1, 0); -} - -static void noop_alias_mapping(__u64 *start, size_t len, unsigned long offset) -{ -} - -static void hugetlb_release_pages(char *rel_area) -{ - if (!map_shared) { - if (madvise(rel_area, nr_pages * page_size, MADV_DONTNEED)) - err("madvise(MADV_DONTNEED) failed"); - } else { - if (madvise(rel_area, nr_pages * page_size, MADV_REMOVE)) - err("madvise(MADV_REMOVE) failed"); - } -} - -static void hugetlb_allocate_area(void **alloc_area, bool is_src) -{ - off_t size = nr_pages * page_size; - off_t offset = is_src ? 0 : size; - void *area_alias = NULL; - char **alloc_area_alias; - - *alloc_area = mmap(NULL, size, PROT_READ | PROT_WRITE, - (map_shared ? MAP_SHARED : MAP_PRIVATE) | - (is_src ? 0 : MAP_NORESERVE), - mem_fd, offset); - if (*alloc_area == MAP_FAILED) - err("mmap of hugetlbfs file failed"); - - if (map_shared) { - area_alias = mmap(NULL, size, PROT_READ | PROT_WRITE, - MAP_SHARED, mem_fd, offset); - if (area_alias == MAP_FAILED) - err("mmap of hugetlb file alias failed"); - } - - if (is_src) { - 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; - - *start = (unsigned long) area_dst_alias + offset; -} - -static void shmem_release_pages(char *rel_area) -{ - if (madvise(rel_area, nr_pages * page_size, MADV_REMOVE)) - err("madvise(MADV_REMOVE) failed"); -} - -static void shmem_allocate_area(void **alloc_area, bool is_src) -{ - void *area_alias = NULL; - size_t bytes = nr_pages * page_size; - unsigned long offset = is_src ? 0 : bytes; - char *p = NULL, *p_alias = NULL; - - if (test_collapse) { - p = BASE_PMD_ADDR; - if (!is_src) - /* src map + alias + interleaved hpages */ - p += 2 * (bytes + hpage_size); - p_alias = p; - p_alias += bytes; - p_alias += hpage_size; /* Prevent src/dst VMA merge */ - } - - *alloc_area = mmap(p, bytes, PROT_READ | PROT_WRITE, MAP_SHARED, - mem_fd, offset); - if (*alloc_area == MAP_FAILED) - err("mmap of memfd failed"); - if (test_collapse && *alloc_area != p) - err("mmap of memfd failed at %p", p); - - area_alias = mmap(p_alias, bytes, PROT_READ | PROT_WRITE, MAP_SHARED, - mem_fd, offset); - if (area_alias == MAP_FAILED) - err("mmap of memfd alias failed"); - if (test_collapse && area_alias != p_alias) - err("mmap of anonymous memory failed at %p", p_alias); - - if (is_src) - area_src_alias = area_alias; - else - area_dst_alias = area_alias; -} - -static void shmem_alias_mapping(__u64 *start, size_t len, unsigned long offset) -{ - *start = (unsigned long)area_dst_alias + offset; -} - -static void shmem_check_pmd_mapping(void *p, int expect_nr_hpages) -{ - if (!check_huge_shmem(area_dst_alias, expect_nr_hpages, hpage_size)) - err("Did not find expected %d number of hugepages", - expect_nr_hpages); -} - -struct uffd_test_ops { - void (*allocate_area)(void **alloc_area, bool is_src); - void (*release_pages)(char *rel_area); - void (*alias_mapping)(__u64 *start, size_t len, unsigned long offset); - void (*check_pmd_mapping)(void *p, int expect_nr_hpages); -}; - -static struct uffd_test_ops anon_uffd_test_ops = { - .allocate_area = anon_allocate_area, - .release_pages = anon_release_pages, - .alias_mapping = noop_alias_mapping, - .check_pmd_mapping = NULL, -}; - -static struct uffd_test_ops shmem_uffd_test_ops = { - .allocate_area = shmem_allocate_area, - .release_pages = shmem_release_pages, - .alias_mapping = shmem_alias_mapping, - .check_pmd_mapping = shmem_check_pmd_mapping, -}; - -static struct uffd_test_ops hugetlb_uffd_test_ops = { - .allocate_area = hugetlb_allocate_area, - .release_pages = hugetlb_release_pages, - .alias_mapping = hugetlb_alias_mapping, - .check_pmd_mapping = NULL, -}; - -static struct uffd_test_ops *uffd_test_ops; - -static inline uint64_t uffd_minor_feature(void) -{ - if (test_type == TEST_HUGETLB && map_shared) - return UFFD_FEATURE_MINOR_HUGETLBFS; - else if (test_type == TEST_SHMEM) - return UFFD_FEATURE_MINOR_SHMEM; - else - return 0; -} - -static uint64_t get_expected_ioctls(uint64_t mode) -{ - uint64_t ioctls = UFFD_API_RANGE_IOCTLS; - - if (test_type == TEST_HUGETLB) - ioctls &= ~(1 << _UFFDIO_ZEROPAGE); - - if (!((mode & UFFDIO_REGISTER_MODE_WP) && test_uffdio_wp)) - ioctls &= ~(1 << _UFFDIO_WRITEPROTECT); - - if (!((mode & UFFDIO_REGISTER_MODE_MINOR) && test_uffdio_minor)) - ioctls &= ~(1 << _UFFDIO_CONTINUE); - - return ioctls; -} - -static void assert_expected_ioctls_present(uint64_t mode, uint64_t ioctls) -{ - uint64_t expected = get_expected_ioctls(mode); - uint64_t actual = ioctls & expected; - - if (actual != expected) { - err("missing ioctl(s): expected %"PRIx64" actual: %"PRIx64, - expected, actual); - } -} - -static int __userfaultfd_open_dev(void) -{ - int fd, _uffd; - - fd = open("/dev/userfaultfd", O_RDWR | O_CLOEXEC); - if (fd < 0) - errexit(KSFT_SKIP, "opening /dev/userfaultfd failed"); - - _uffd = ioctl(fd, USERFAULTFD_IOC_NEW, UFFD_FLAGS); - if (_uffd < 0) - errexit(errno == ENOTTY ? KSFT_SKIP : 1, - "creating userfaultfd failed"); - close(fd); - return _uffd; -} - -static void userfaultfd_open(uint64_t *features) -{ - struct uffdio_api uffdio_api; - - if (test_dev_userfaultfd) - uffd = __userfaultfd_open_dev(); - else { - uffd = syscall(__NR_userfaultfd, UFFD_FLAGS); - if (uffd < 0) - errexit(errno == ENOSYS ? KSFT_SKIP : 1, - "creating userfaultfd failed"); - } - uffd_flags = fcntl(uffd, F_GETFD, NULL); - - uffdio_api.api = UFFD_API; - uffdio_api.features = *features; - if (ioctl(uffd, UFFDIO_API, &uffdio_api)) - err("UFFDIO_API failed.\nPlease make sure to " - "run with either root or ptrace capability."); - if (uffdio_api.api != UFFD_API) - err("UFFDIO_API error: %" PRIu64, (uint64_t)uffdio_api.api); - - *features = uffdio_api.features; -} - -static inline void munmap_area(void **area) -{ - if (*area) - if (munmap(*area, nr_pages * page_size)) - err("munmap"); - - *area = NULL; -} - -static void uffd_test_ctx_clear(void) -{ - size_t i; - - if (pipefd) { - for (i = 0; i < nr_cpus * 2; ++i) { - if (close(pipefd[i])) - err("close pipefd"); - } - free(pipefd); - pipefd = NULL; - } - - if (count_verify) { - free(count_verify); - count_verify = NULL; - } - - if (uffd != -1) { - if (close(uffd)) - err("close uffd"); - uffd = -1; - } - - munmap_area((void **)&area_src); - munmap_area((void **)&area_src_alias); - munmap_area((void **)&area_dst); - munmap_area((void **)&area_dst_alias); - munmap_area((void **)&area_remap); -} - -static void uffd_test_ctx_init(uint64_t features) -{ - unsigned long nr, cpu; - - uffd_test_ctx_clear(); - - uffd_test_ops->allocate_area((void **)&area_src, true); - uffd_test_ops->allocate_area((void **)&area_dst, false); - - userfaultfd_open(&features); - - count_verify = malloc(nr_pages * sizeof(unsigned long long)); - if (!count_verify) - err("count_verify"); - - for (nr = 0; nr < nr_pages; nr++) { - *area_mutex(area_src, nr) = - (pthread_mutex_t)PTHREAD_MUTEX_INITIALIZER; - count_verify[nr] = *area_count(area_src, nr) = 1; - /* - * In the transition between 255 to 256, powerpc will - * read out of order in my_bcmp and see both bytes as - * zero, so leave a placeholder below always non-zero - * after the count, to avoid my_bcmp to trigger false - * positives. - */ - *(area_count(area_src, nr) + 1) = 1; - } - - /* - * After initialization of area_src, we must explicitly release pages - * for area_dst to make sure it's fully empty. Otherwise we could have - * some area_dst pages be errornously initialized with zero pages, - * hence we could hit memory corruption later in the test. - * - * One example is when THP is globally enabled, above allocate_area() - * calls could have the two areas merged into a single VMA (as they - * will have the same VMA flags so they're mergeable). When we - * initialize the area_src above, it's possible that some part of - * area_dst could have been faulted in via one huge THP that will be - * shared between area_src and area_dst. It could cause some of the - * area_dst won't be trapped by missing userfaults. - * - * This release_pages() will guarantee even if that happened, we'll - * proactively split the thp and drop any accidentally initialized - * pages within area_dst. - */ - uffd_test_ops->release_pages(area_dst); - - pipefd = malloc(sizeof(int) * nr_cpus * 2); - if (!pipefd) - err("pipefd"); - for (cpu = 0; cpu < nr_cpus; cpu++) - if (pipe2(&pipefd[cpu * 2], O_CLOEXEC | O_NONBLOCK)) - err("pipe"); -} - -static int my_bcmp(char *str1, char *str2, size_t n) -{ - unsigned long i; - for (i = 0; i < n; i++) - if (str1[i] != str2[i]) - return 1; - return 0; -} - -static void wp_range(int ufd, __u64 start, __u64 len, bool wp) -{ - struct uffdio_writeprotect prms; - - /* Write protection page faults */ - prms.range.start = start; - prms.range.len = len; - /* Undo write-protect, do wakeup after that */ - prms.mode = wp ? UFFDIO_WRITEPROTECT_MODE_WP : 0; - - if (ioctl(ufd, UFFDIO_WRITEPROTECT, &prms)) - err("clear WP failed: address=0x%"PRIx64, (uint64_t)start); -} - -static void continue_range(int ufd, __u64 start, __u64 len) -{ - struct uffdio_continue req; - int ret; - - req.range.start = start; - req.range.len = len; - req.mode = 0; - - if (ioctl(ufd, UFFDIO_CONTINUE, &req)) - err("UFFDIO_CONTINUE failed for address 0x%" PRIx64, - (uint64_t)start); - - /* - * Error handling within the kernel for continue is subtly different - * from copy or zeropage, so it may be a source of bugs. Trigger an - * error (-EEXIST) on purpose, to verify doing so doesn't cause a BUG. - */ - req.mapped = 0; - ret = ioctl(ufd, UFFDIO_CONTINUE, &req); - if (ret >= 0 || req.mapped != -EEXIST) - err("failed to exercise UFFDIO_CONTINUE error handling, ret=%d, mapped=%" PRId64, - ret, (int64_t) req.mapped); -} - -static void *locking_thread(void *arg) -{ - unsigned long cpu = (unsigned long) arg; - unsigned long page_nr; - unsigned long long count; - - if (!(bounces & BOUNCE_RANDOM)) { - page_nr = -bounces; - if (!(bounces & BOUNCE_RACINGFAULTS)) - page_nr += cpu * nr_pages_per_cpu; - } - - while (!finished) { - if (bounces & BOUNCE_RANDOM) { - if (getrandom(&page_nr, sizeof(page_nr), 0) != sizeof(page_nr)) - err("getrandom failed"); - } else - page_nr += 1; - page_nr %= nr_pages; - pthread_mutex_lock(area_mutex(area_dst, page_nr)); - count = *area_count(area_dst, page_nr); - if (count != count_verify[page_nr]) - err("page_nr %lu memory corruption %llu %llu", - page_nr, count, count_verify[page_nr]); - count++; - *area_count(area_dst, page_nr) = count_verify[page_nr] = count; - pthread_mutex_unlock(area_mutex(area_dst, page_nr)); - } - - 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) - err("UFFDIO_COPY retry error: %"PRId64, - (int64_t)uffdio_copy->copy); - } else { - err("UFFDIO_COPY retry unexpected: %"PRId64, - (int64_t)uffdio_copy->copy); - } -} - -static void wake_range(int ufd, unsigned long addr, unsigned long len) -{ - struct uffdio_range uffdio_wake; - - uffdio_wake.start = addr; - uffdio_wake.len = len; - - if (ioctl(ufd, UFFDIO_WAKE, &uffdio_wake)) - fprintf(stderr, "error waking %lu\n", - addr), exit(1); -} - -static int __copy_page(int ufd, unsigned long offset, bool retry) -{ - struct uffdio_copy uffdio_copy; - - if (offset >= nr_pages * page_size) - err("unexpected offset %lu\n", offset); - uffdio_copy.dst = (unsigned long) area_dst + offset; - uffdio_copy.src = (unsigned long) area_src + offset; - uffdio_copy.len = page_size; - if (test_uffdio_wp) - uffdio_copy.mode = UFFDIO_COPY_MODE_WP; - else - uffdio_copy.mode = 0; - uffdio_copy.copy = 0; - if (ioctl(ufd, UFFDIO_COPY, &uffdio_copy)) { - /* real retval in ufdio_copy.copy */ - if (uffdio_copy.copy != -EEXIST) - err("UFFDIO_COPY error: %"PRId64, - (int64_t)uffdio_copy.copy); - wake_range(ufd, uffdio_copy.dst, page_size); - } else if (uffdio_copy.copy != page_size) { - err("UFFDIO_COPY error: %"PRId64, (int64_t)uffdio_copy.copy); - } else { - if (test_uffdio_copy_eexist && retry) { - test_uffdio_copy_eexist = false; - retry_copy_page(ufd, &uffdio_copy, offset); - } - return 1; - } - return 0; -} - -static int copy_page_retry(int ufd, unsigned long offset) -{ - return __copy_page(ufd, offset, true); -} - -static int copy_page(int ufd, unsigned long offset) -{ - return __copy_page(ufd, offset, false); -} - -static int uffd_read_msg(int ufd, struct uffd_msg *msg) -{ - int ret = read(uffd, msg, sizeof(*msg)); - - if (ret != sizeof(*msg)) { - if (ret < 0) { - if (errno == EAGAIN || errno == EINTR) - return 1; - err("blocking read error"); - } else { - err("short read"); - } - } - - return 0; -} - -static void uffd_handle_page_fault(struct uffd_msg *msg, - struct uffd_stats *stats) -{ - unsigned long offset; - - if (msg->event != UFFD_EVENT_PAGEFAULT) - err("unexpected msg event %u", msg->event); - - if (msg->arg.pagefault.flags & UFFD_PAGEFAULT_FLAG_WP) { - /* Write protect page faults */ - wp_range(uffd, msg->arg.pagefault.address, page_size, false); - stats->wp_faults++; - } else if (msg->arg.pagefault.flags & UFFD_PAGEFAULT_FLAG_MINOR) { - uint8_t *area; - int b; - - /* - * Minor page faults - * - * To prove we can modify the original range for testing - * purposes, we're going to bit flip this range before - * continuing. - * - * Note that this requires all minor page fault tests operate on - * area_dst (non-UFFD-registered) and area_dst_alias - * (UFFD-registered). - */ - - area = (uint8_t *)(area_dst + - ((char *)msg->arg.pagefault.address - - area_dst_alias)); - for (b = 0; b < page_size; ++b) - area[b] = ~area[b]; - continue_range(uffd, msg->arg.pagefault.address, page_size); - stats->minor_faults++; - } else { - /* - * Missing page faults. - * - * Here we force a write check for each of the missing mode - * faults. It's guaranteed because the only threads that - * will trigger uffd faults are the locking threads, and - * their first instruction to touch the missing page will - * always be pthread_mutex_lock(). - * - * Note that here we relied on an NPTL glibc impl detail to - * always read the lock type at the entry of the lock op - * (pthread_mutex_t.__data.__type, offset 0x10) before - * doing any locking operations to guarantee that. It's - * actually not good to rely on this impl detail because - * logically a pthread-compatible lib can implement the - * locks without types and we can fail when linking with - * them. However since we used to find bugs with this - * strict check we still keep it around. Hopefully this - * could be a good hint when it fails again. If one day - * it'll break on some other impl of glibc we'll revisit. - */ - if (msg->arg.pagefault.flags & UFFD_PAGEFAULT_FLAG_WRITE) - err("unexpected write fault"); - - offset = (char *)(unsigned long)msg->arg.pagefault.address - area_dst; - offset &= ~(page_size-1); - - if (copy_page(uffd, offset)) - stats->missing_faults++; - } -} - -static void *uffd_poll_thread(void *arg) -{ - struct uffd_stats *stats = (struct uffd_stats *)arg; - unsigned long cpu = stats->cpu; - struct pollfd pollfd[2]; - struct uffd_msg msg; - struct uffdio_register uffd_reg; - int ret; - char tmp_chr; - - pollfd[0].fd = uffd; - pollfd[0].events = POLLIN; - pollfd[1].fd = pipefd[cpu*2]; - pollfd[1].events = POLLIN; - - for (;;) { - ret = poll(pollfd, 2, -1); - if (ret <= 0) { - if (errno == EINTR || errno == EAGAIN) - continue; - err("poll error: %d", ret); - } - if (pollfd[1].revents & POLLIN) { - if (read(pollfd[1].fd, &tmp_chr, 1) != 1) - err("read pipefd error"); - break; - } - if (!(pollfd[0].revents & POLLIN)) - err("pollfd[0].revents %d", pollfd[0].revents); - if (uffd_read_msg(uffd, &msg)) - continue; - switch (msg.event) { - default: - err("unexpected msg event %u\n", msg.event); - break; - case UFFD_EVENT_PAGEFAULT: - uffd_handle_page_fault(&msg, stats); - break; - case UFFD_EVENT_FORK: - close(uffd); - uffd = msg.arg.fork.ufd; - pollfd[0].fd = uffd; - break; - case UFFD_EVENT_REMOVE: - uffd_reg.range.start = msg.arg.remove.start; - uffd_reg.range.len = msg.arg.remove.end - - msg.arg.remove.start; - if (ioctl(uffd, UFFDIO_UNREGISTER, &uffd_reg.range)) - err("remove failure"); - break; - case UFFD_EVENT_REMAP: - area_remap = area_dst; /* save for later unmap */ - area_dst = (char *)(unsigned long)msg.arg.remap.to; - break; - } - } - - return NULL; -} - -pthread_mutex_t uffd_read_mutex = PTHREAD_MUTEX_INITIALIZER; - -static void *uffd_read_thread(void *arg) -{ - struct uffd_stats *stats = (struct uffd_stats *)arg; - struct uffd_msg msg; - - pthread_mutex_unlock(&uffd_read_mutex); - /* from here cancellation is ok */ - - for (;;) { - if (uffd_read_msg(uffd, &msg)) - continue; - uffd_handle_page_fault(&msg, stats); - } - - return NULL; -} - -static void *background_thread(void *arg) -{ - unsigned long cpu = (unsigned long) arg; - unsigned long page_nr, start_nr, mid_nr, end_nr; - - start_nr = cpu * nr_pages_per_cpu; - end_nr = (cpu+1) * nr_pages_per_cpu; - mid_nr = (start_nr + end_nr) / 2; - - /* Copy the first half of the pages */ - for (page_nr = start_nr; page_nr < mid_nr; page_nr++) - copy_page_retry(uffd, page_nr * page_size); - - /* - * If we need to test uffd-wp, set it up now. Then we'll have - * at least the first half of the pages mapped already which - * can be write-protected for testing - */ - if (test_uffdio_wp) - wp_range(uffd, (unsigned long)area_dst + start_nr * page_size, - nr_pages_per_cpu * page_size, true); - - /* - * Continue the 2nd half of the page copying, handling write - * protection faults if any - */ - for (page_nr = mid_nr; page_nr < end_nr; page_nr++) - copy_page_retry(uffd, page_nr * page_size); - - return NULL; -} - -static int stress(struct uffd_stats *uffd_stats) -{ - unsigned long cpu; - pthread_t locking_threads[nr_cpus]; - pthread_t uffd_threads[nr_cpus]; - pthread_t background_threads[nr_cpus]; - - finished = 0; - for (cpu = 0; cpu < nr_cpus; cpu++) { - if (pthread_create(&locking_threads[cpu], &attr, - locking_thread, (void *)cpu)) - return 1; - if (bounces & BOUNCE_POLL) { - if (pthread_create(&uffd_threads[cpu], &attr, - uffd_poll_thread, - (void *)&uffd_stats[cpu])) - return 1; - } else { - if (pthread_create(&uffd_threads[cpu], &attr, - uffd_read_thread, - (void *)&uffd_stats[cpu])) - return 1; - pthread_mutex_lock(&uffd_read_mutex); - } - if (pthread_create(&background_threads[cpu], &attr, - background_thread, (void *)cpu)) - return 1; - } - for (cpu = 0; cpu < nr_cpus; cpu++) - if (pthread_join(background_threads[cpu], NULL)) - return 1; - - /* - * Be strict and immediately zap area_src, the whole area has - * been transferred already by the background treads. The - * area_src could then be faulted in a racy way by still - * running uffdio_threads reading zeropages after we zapped - * area_src (but they're guaranteed to get -EEXIST from - * UFFDIO_COPY without writing zero pages into area_dst - * because the background threads already completed). - */ - uffd_test_ops->release_pages(area_src); - - finished = 1; - for (cpu = 0; cpu < nr_cpus; cpu++) - if (pthread_join(locking_threads[cpu], NULL)) - return 1; - - for (cpu = 0; cpu < nr_cpus; cpu++) { - char c; - if (bounces & BOUNCE_POLL) { - if (write(pipefd[cpu*2+1], &c, 1) != 1) - err("pipefd write error"); - if (pthread_join(uffd_threads[cpu], - (void *)&uffd_stats[cpu])) - return 1; - } else { - if (pthread_cancel(uffd_threads[cpu])) - return 1; - if (pthread_join(uffd_threads[cpu], NULL)) - return 1; - } - } - - 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 - * userfaultfd and at last this process will release the monitored - * area. - * For the anonymous and shared memory the area is divided into two - * parts, the first part is accessed before mremap, and the second - * part is accessed after mremap. Since hugetlbfs does not support - * mremap, the entire monitored area is accessed in a single pass for - * HUGETLB_TEST. - * 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(int signal_test) -{ - unsigned long nr; - unsigned long long count; - unsigned long split_nr_pages; - unsigned long lastnr; - struct sigaction act; - volatile unsigned long signalled = 0; - - split_nr_pages = (nr_pages + 1) / 2; - - if (signal_test) { - sigbuf = &jbuf; - memset(&act, 0, sizeof(act)); - act.sa_sigaction = sighndl; - act.sa_flags = SA_SIGINFO; - if (sigaction(SIGBUS, &act, 0)) - err("sigaction"); - lastnr = (unsigned long)-1; - } - - for (nr = 0; nr < split_nr_pages; nr++) { - volatile int steps = 1; - unsigned long offset = nr * page_size; - - if (signal_test) { - if (sigsetjmp(*sigbuf, 1) != 0) { - if (steps == 1 && nr == lastnr) - err("Signal repeated"); - - lastnr = nr; - if (signal_test == 1) { - if (steps == 1) { - /* This is a MISSING request */ - steps++; - if (copy_page(uffd, offset)) - signalled++; - } else { - /* This is a WP request */ - assert(steps == 2); - wp_range(uffd, - (__u64)area_dst + - offset, - page_size, false); - } - } else { - signalled++; - continue; - } - } - } - - count = *area_count(area_dst, nr); - if (count != count_verify[nr]) - err("nr %lu memory corruption %llu %llu\n", - nr, count, count_verify[nr]); - /* - * Trigger write protection if there is by writing - * the same value back. - */ - *area_count(area_dst, nr) = count; - } - - if (signal_test) - return signalled != split_nr_pages; - - area_dst = mremap(area_dst, nr_pages * page_size, nr_pages * page_size, - MREMAP_MAYMOVE | MREMAP_FIXED, area_src); - if (area_dst == MAP_FAILED) - err("mremap"); - /* Reset area_src since we just clobbered it */ - area_src = NULL; - - for (; nr < nr_pages; nr++) { - count = *area_count(area_dst, nr); - if (count != count_verify[nr]) { - err("nr %lu memory corruption %llu %llu\n", - nr, count, count_verify[nr]); - } - /* - * Trigger write protection if there is by writing - * the same value back. - */ - *area_count(area_dst, nr) = count; - } - - uffd_test_ops->release_pages(area_dst); - - for (nr = 0; nr < nr_pages; nr++) - if (my_bcmp(area_dst + nr * page_size, zeropage, page_size)) - err("nr %lu is not zero", nr); - - 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) - err("UFFDIO_ZEROPAGE error: %"PRId64, - (int64_t)uffdio_zeropage->zeropage); - } else { - err("UFFDIO_ZEROPAGE error: %"PRId64, - (int64_t)uffdio_zeropage->zeropage); - } -} - -static int __uffdio_zeropage(int ufd, unsigned long offset, bool retry) -{ - struct uffdio_zeropage uffdio_zeropage; - int ret; - bool has_zeropage = get_expected_ioctls(0) & (1 << _UFFDIO_ZEROPAGE); - __s64 res; - - if (offset >= nr_pages * page_size) - err("unexpected offset %lu", offset); - uffdio_zeropage.range.start = (unsigned long) area_dst + offset; - uffdio_zeropage.range.len = page_size; - uffdio_zeropage.mode = 0; - ret = ioctl(ufd, UFFDIO_ZEROPAGE, &uffdio_zeropage); - res = uffdio_zeropage.zeropage; - if (ret) { - /* real retval in ufdio_zeropage.zeropage */ - if (has_zeropage) - err("UFFDIO_ZEROPAGE error: %"PRId64, (int64_t)res); - else if (res != -EINVAL) - err("UFFDIO_ZEROPAGE not -EINVAL"); - } else if (has_zeropage) { - if (res != page_size) { - err("UFFDIO_ZEROPAGE unexpected size"); - } else { - if (test_uffdio_zeropage_eexist && retry) { - test_uffdio_zeropage_eexist = false; - retry_uffdio_zeropage(ufd, &uffdio_zeropage, - offset); - } - return 1; - } - } else - err("UFFDIO_ZEROPAGE succeeded"); - - return 0; -} - -static int uffdio_zeropage(int ufd, unsigned long offset) -{ - return __uffdio_zeropage(ufd, offset, false); -} - -/* exercise UFFDIO_ZEROPAGE */ -static int userfaultfd_zeropage_test(void) -{ - struct uffdio_register uffdio_register; - - printf("testing UFFDIO_ZEROPAGE: "); - fflush(stdout); - - uffd_test_ctx_init(0); - - uffdio_register.range.start = (unsigned long) area_dst; - uffdio_register.range.len = nr_pages * page_size; - uffdio_register.mode = UFFDIO_REGISTER_MODE_MISSING; - if (test_uffdio_wp) - uffdio_register.mode |= UFFDIO_REGISTER_MODE_WP; - if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register)) - err("register failure"); - - assert_expected_ioctls_present( - uffdio_register.mode, uffdio_register.ioctls); - - if (uffdio_zeropage(uffd, 0)) - if (my_bcmp(area_dst, zeropage, page_size)) - err("zeropage is not zero"); - - printf("done.\n"); - return 0; -} - -static int userfaultfd_events_test(void) -{ - struct uffdio_register uffdio_register; - pthread_t uffd_mon; - int err, features; - pid_t pid; - char c; - struct uffd_stats stats = { 0 }; - - printf("testing events (fork, remap, remove): "); - fflush(stdout); - - features = UFFD_FEATURE_EVENT_FORK | UFFD_FEATURE_EVENT_REMAP | - UFFD_FEATURE_EVENT_REMOVE; - uffd_test_ctx_init(features); - - 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 (test_uffdio_wp) - uffdio_register.mode |= UFFDIO_REGISTER_MODE_WP; - if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register)) - err("register failure"); - - assert_expected_ioctls_present( - uffdio_register.mode, uffdio_register.ioctls); - - if (pthread_create(&uffd_mon, &attr, uffd_poll_thread, &stats)) - err("uffd_poll_thread create"); - - pid = fork(); - if (pid < 0) - err("fork"); - - if (!pid) - exit(faulting_process(0)); - - waitpid(pid, &err, 0); - if (err) - err("faulting process failed"); - if (write(pipefd[1], &c, sizeof(c)) != sizeof(c)) - err("pipe write"); - if (pthread_join(uffd_mon, NULL)) - return 1; - - uffd_stats_report(&stats, 1); - - return stats.missing_faults != nr_pages; -} - -static int userfaultfd_sig_test(void) -{ - struct uffdio_register uffdio_register; - unsigned long userfaults; - pthread_t uffd_mon; - int err, features; - pid_t pid; - char c; - struct uffd_stats stats = { 0 }; - - printf("testing signal delivery: "); - fflush(stdout); - - features = UFFD_FEATURE_EVENT_FORK|UFFD_FEATURE_SIGBUS; - uffd_test_ctx_init(features); - - 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 (test_uffdio_wp) - uffdio_register.mode |= UFFDIO_REGISTER_MODE_WP; - if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register)) - err("register failure"); - - assert_expected_ioctls_present( - uffdio_register.mode, uffdio_register.ioctls); - - if (faulting_process(1)) - err("faulting process failed"); - - uffd_test_ops->release_pages(area_dst); - - if (pthread_create(&uffd_mon, &attr, uffd_poll_thread, &stats)) - err("uffd_poll_thread create"); - - pid = fork(); - if (pid < 0) - err("fork"); - - if (!pid) - exit(faulting_process(2)); - - waitpid(pid, &err, 0); - if (err) - err("faulting process failed"); - if (write(pipefd[1], &c, sizeof(c)) != sizeof(c)) - err("pipe write"); - if (pthread_join(uffd_mon, (void **)&userfaults)) - return 1; - - printf("done.\n"); - if (userfaults) - err("Signal test failed, userfaults: %ld", userfaults); - - return userfaults != 0; -} - -void check_memory_contents(char *p) -{ - unsigned long i; - uint8_t expected_byte; - void *expected_page; - - if (posix_memalign(&expected_page, page_size, page_size)) - err("out of memory"); - - for (i = 0; i < nr_pages; ++i) { - expected_byte = ~((uint8_t)(i % ((uint8_t)-1))); - memset(expected_page, expected_byte, page_size); - if (my_bcmp(expected_page, p + (i * page_size), page_size)) - err("unexpected page contents after minor fault"); - } - - free(expected_page); -} - -static int userfaultfd_minor_test(void) -{ - unsigned long p; - struct uffdio_register uffdio_register; - pthread_t uffd_mon; - char c; - struct uffd_stats stats = { 0 }; - - if (!test_uffdio_minor) - return 0; - - printf("testing minor faults: "); - fflush(stdout); - - uffd_test_ctx_init(uffd_minor_feature()); - - uffdio_register.range.start = (unsigned long)area_dst_alias; - uffdio_register.range.len = nr_pages * page_size; - uffdio_register.mode = UFFDIO_REGISTER_MODE_MINOR; - if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register)) - err("register failure"); - - assert_expected_ioctls_present( - uffdio_register.mode, uffdio_register.ioctls); - - /* - * After registering with UFFD, populate the non-UFFD-registered side of - * the shared mapping. This should *not* trigger any UFFD minor faults. - */ - for (p = 0; p < nr_pages; ++p) { - memset(area_dst + (p * page_size), p % ((uint8_t)-1), - page_size); - } - - if (pthread_create(&uffd_mon, &attr, uffd_poll_thread, &stats)) - err("uffd_poll_thread create"); - - /* - * Read each of the pages back using the UFFD-registered mapping. We - * expect that the first time we touch a page, it will result in a minor - * fault. uffd_poll_thread will resolve the fault by bit-flipping the - * page's contents, and then issuing a CONTINUE ioctl. - */ - check_memory_contents(area_dst_alias); - - if (write(pipefd[1], &c, sizeof(c)) != sizeof(c)) - err("pipe write"); - if (pthread_join(uffd_mon, NULL)) - return 1; - - uffd_stats_report(&stats, 1); - - if (test_collapse) { - printf("testing collapse of uffd memory into PMD-mapped THPs:"); - if (madvise(area_dst_alias, nr_pages * page_size, - MADV_COLLAPSE)) - err("madvise(MADV_COLLAPSE)"); - - uffd_test_ops->check_pmd_mapping(area_dst, - nr_pages * page_size / - hpage_size); - /* - * This won't cause uffd-fault - it purely just makes sure there - * was no corruption. - */ - check_memory_contents(area_dst_alias); - printf(" done.\n"); - } - - return stats.missing_faults != 0 || stats.minor_faults != nr_pages; -} - -#define BIT_ULL(nr) (1ULL << (nr)) -#define PM_SOFT_DIRTY BIT_ULL(55) -#define PM_MMAP_EXCLUSIVE BIT_ULL(56) -#define PM_UFFD_WP BIT_ULL(57) -#define PM_FILE BIT_ULL(61) -#define PM_SWAP BIT_ULL(62) -#define PM_PRESENT BIT_ULL(63) - -static int pagemap_open(void) -{ - int fd = open("/proc/self/pagemap", O_RDONLY); - - if (fd < 0) - err("open pagemap"); - - return fd; -} - -static uint64_t pagemap_read_vaddr(int fd, void *vaddr) -{ - uint64_t value; - int ret; - - ret = pread(fd, &value, sizeof(uint64_t), - ((uint64_t)vaddr >> 12) * sizeof(uint64_t)); - if (ret != sizeof(uint64_t)) - err("pread() on pagemap failed"); - - return value; -} - -/* This macro let __LINE__ works in err() */ -#define pagemap_check_wp(value, wp) do { \ - if (!!(value & PM_UFFD_WP) != wp) \ - err("pagemap uffd-wp bit error: 0x%"PRIx64, value); \ - } while (0) - -static int pagemap_test_fork(bool present) -{ - pid_t child = fork(); - uint64_t value; - int fd, result; - - if (!child) { - /* Open the pagemap fd of the child itself */ - fd = pagemap_open(); - value = pagemap_read_vaddr(fd, area_dst); - /* - * After fork() uffd-wp bit should be gone as long as we're - * without UFFD_FEATURE_EVENT_FORK - */ - pagemap_check_wp(value, false); - /* Succeed */ - exit(0); - } - waitpid(child, &result, 0); - return result; -} - -static void userfaultfd_pagemap_test(unsigned int test_pgsize) -{ - struct uffdio_register uffdio_register; - int pagemap_fd; - uint64_t value; - - /* Pagemap tests uffd-wp only */ - if (!test_uffdio_wp) - return; - - /* Not enough memory to test this page size */ - if (test_pgsize > nr_pages * page_size) - return; - - printf("testing uffd-wp with pagemap (pgsize=%u): ", test_pgsize); - /* Flush so it doesn't flush twice in parent/child later */ - fflush(stdout); - - uffd_test_ctx_init(0); - - if (test_pgsize > page_size) { - /* This is a thp test */ - if (madvise(area_dst, nr_pages * page_size, MADV_HUGEPAGE)) - err("madvise(MADV_HUGEPAGE) failed"); - } else if (test_pgsize == page_size) { - /* This is normal page test; force no thp */ - if (madvise(area_dst, nr_pages * page_size, MADV_NOHUGEPAGE)) - err("madvise(MADV_NOHUGEPAGE) failed"); - } - - uffdio_register.range.start = (unsigned long) area_dst; - uffdio_register.range.len = nr_pages * page_size; - uffdio_register.mode = UFFDIO_REGISTER_MODE_WP; - if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register)) - err("register failed"); - - pagemap_fd = pagemap_open(); - - /* Touch the page */ - *area_dst = 1; - wp_range(uffd, (uint64_t)area_dst, test_pgsize, true); - value = pagemap_read_vaddr(pagemap_fd, area_dst); - pagemap_check_wp(value, true); - /* Make sure uffd-wp bit dropped when fork */ - if (pagemap_test_fork(true)) - err("Detected stall uffd-wp bit in child"); - - /* Exclusive required or PAGEOUT won't work */ - if (!(value & PM_MMAP_EXCLUSIVE)) - err("multiple mapping detected: 0x%"PRIx64, value); - - if (madvise(area_dst, test_pgsize, MADV_PAGEOUT)) - err("madvise(MADV_PAGEOUT) failed"); - - /* Uffd-wp should persist even swapped out */ - value = pagemap_read_vaddr(pagemap_fd, area_dst); - pagemap_check_wp(value, true); - /* Make sure uffd-wp bit dropped when fork */ - if (pagemap_test_fork(false)) - err("Detected stall uffd-wp bit in child"); - - /* Unprotect; this tests swap pte modifications */ - wp_range(uffd, (uint64_t)area_dst, page_size, false); - value = pagemap_read_vaddr(pagemap_fd, area_dst); - pagemap_check_wp(value, false); - - /* Fault in the page from disk */ - *area_dst = 2; - value = pagemap_read_vaddr(pagemap_fd, area_dst); - pagemap_check_wp(value, false); - - close(pagemap_fd); - printf("done\n"); -} - -static int userfaultfd_stress(void) -{ - void *area; - unsigned long nr; - struct uffdio_register uffdio_register; - struct uffd_stats uffd_stats[nr_cpus]; - - uffd_test_ctx_init(0); - - if (posix_memalign(&area, page_size, page_size)) - err("out of memory"); - zeropage = area; - bzero(zeropage, page_size); - - pthread_mutex_lock(&uffd_read_mutex); - - pthread_attr_init(&attr); - pthread_attr_setstacksize(&attr, 16*1024*1024); - - while (bounces--) { - printf("bounces: %d, mode:", bounces); - if (bounces & BOUNCE_RANDOM) - printf(" rnd"); - if (bounces & BOUNCE_RACINGFAULTS) - printf(" racing"); - if (bounces & BOUNCE_VERIFY) - printf(" ver"); - if (bounces & BOUNCE_POLL) - printf(" poll"); - else - printf(" read"); - printf(", "); - fflush(stdout); - - if (bounces & BOUNCE_POLL) - fcntl(uffd, F_SETFL, uffd_flags | O_NONBLOCK); - else - fcntl(uffd, F_SETFL, uffd_flags & ~O_NONBLOCK); - - /* register */ - uffdio_register.range.start = (unsigned long) area_dst; - uffdio_register.range.len = nr_pages * page_size; - uffdio_register.mode = UFFDIO_REGISTER_MODE_MISSING; - if (test_uffdio_wp) - uffdio_register.mode |= UFFDIO_REGISTER_MODE_WP; - if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register)) - err("register failure"); - assert_expected_ioctls_present( - uffdio_register.mode, uffdio_register.ioctls); - - if (area_dst_alias) { - uffdio_register.range.start = (unsigned long) - area_dst_alias; - if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register)) - err("register failure alias"); - } - - /* - * The madvise done previously isn't enough: some - * uffd_thread could have read userfaults (one of - * those already resolved by the background thread) - * and it may be in the process of calling - * UFFDIO_COPY. UFFDIO_COPY will read the zapped - * area_src and it would map a zero page in it (of - * course such a UFFDIO_COPY is perfectly safe as it'd - * return -EEXIST). The problem comes at the next - * bounce though: that racing UFFDIO_COPY would - * generate zeropages in the area_src, so invalidating - * the previous MADV_DONTNEED. Without this additional - * MADV_DONTNEED those zeropages leftovers in the - * area_src would lead to -EEXIST failure during the - * next bounce, effectively leaving a zeropage in the - * area_dst. - * - * Try to comment this out madvise to see the memory - * corruption being caught pretty quick. - * - * khugepaged is also inhibited to collapse THP after - * MADV_DONTNEED only after the UFFDIO_REGISTER, so it's - * required to MADV_DONTNEED here. - */ - uffd_test_ops->release_pages(area_dst); - - uffd_stats_reset(uffd_stats, nr_cpus); - - /* bounce pass */ - if (stress(uffd_stats)) - return 1; - - /* Clear all the write protections if there is any */ - if (test_uffdio_wp) - wp_range(uffd, (unsigned long)area_dst, - nr_pages * page_size, false); - - /* unregister */ - if (ioctl(uffd, UFFDIO_UNREGISTER, &uffdio_register.range)) - err("unregister failure"); - if (area_dst_alias) { - uffdio_register.range.start = (unsigned long) area_dst; - if (ioctl(uffd, UFFDIO_UNREGISTER, - &uffdio_register.range)) - err("unregister failure alias"); - } - - /* verification */ - if (bounces & BOUNCE_VERIFY) - for (nr = 0; nr < nr_pages; nr++) - if (*area_count(area_dst, nr) != count_verify[nr]) - err("error area_count %llu %llu %lu\n", - *area_count(area_src, nr), - count_verify[nr], nr); - - /* prepare next bounce */ - swap(area_src, area_dst); - - swap(area_src_alias, area_dst_alias); - - uffd_stats_report(uffd_stats, nr_cpus); - } - - if (test_type == TEST_ANON) { - /* - * shmem/hugetlb won't be able to run since they have different - * behavior on fork() (file-backed memory normally drops ptes - * directly when fork), meanwhile the pagemap test will verify - * pgtable entry of fork()ed child. - */ - userfaultfd_pagemap_test(page_size); - /* - * Hard-code for x86_64 for now for 2M THP, as x86_64 is - * currently the only one that supports uffd-wp - */ - userfaultfd_pagemap_test(page_size * 512); - } - - return userfaultfd_zeropage_test() || userfaultfd_sig_test() - || userfaultfd_events_test() || userfaultfd_minor_test(); -} - -/* - * Copied from mlock2-tests.c - */ -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 void set_test_type(const char *type) -{ - if (!strcmp(type, "anon")) { - test_type = TEST_ANON; - uffd_test_ops = &anon_uffd_test_ops; - } 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; - /* Minor faults require shared hugetlb; only enable here. */ - test_uffdio_minor = true; - } else if (!strcmp(type, "shmem")) { - map_shared = true; - test_type = TEST_SHMEM; - uffd_test_ops = &shmem_uffd_test_ops; - test_uffdio_minor = true; - } -} - -static void parse_test_type_arg(const char *raw_type) -{ - char *buf = strdup(raw_type); - uint64_t features = UFFD_API_FEATURES; - - while (buf) { - const char *token = strsep(&buf, ":"); - - if (!test_type) - set_test_type(token); - else if (!strcmp(token, "dev")) - test_dev_userfaultfd = true; - else if (!strcmp(token, "syscall")) - test_dev_userfaultfd = false; - else if (!strcmp(token, "collapse")) - test_collapse = true; - else - err("unrecognized test mod '%s'", token); - } - - if (!test_type) - err("failed to parse test type argument: '%s'", raw_type); - - if (test_collapse && test_type != TEST_SHMEM) - err("Unsupported test: %s", raw_type); - - if (test_type == TEST_HUGETLB) - page_size = hpage_size; - else - page_size = sysconf(_SC_PAGE_SIZE); - - if (!page_size) - err("Unable to determine page size"); - if ((unsigned long) area_count(NULL, 0) + sizeof(unsigned long long) * 2 - > page_size) - err("Impossible to run this test"); - - /* - * Whether we can test certain features depends not just on test type, - * but also on whether or not this particular kernel supports the - * feature. - */ - - userfaultfd_open(&features); - - test_uffdio_wp = test_uffdio_wp && - (features & UFFD_FEATURE_PAGEFAULT_FLAG_WP); - test_uffdio_minor = test_uffdio_minor && - (features & uffd_minor_feature()); - - close(uffd); - uffd = -1; -} - -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) -{ - size_t bytes; - - if (argc < 4) - usage(); - - if (signal(SIGALRM, sigalrm) == SIG_ERR) - err("failed to arm SIGALRM"); - alarm(ALARM_INTERVAL_SECS); - - hpage_size = default_huge_page_size(); - parse_test_type_arg(argv[1]); - bytes = atol(argv[2]) * 1024 * 1024; - - if (test_collapse && bytes & (hpage_size - 1)) - err("MiB must be multiple of %lu if :collapse mod set", - hpage_size >> 20); - - nr_cpus = sysconf(_SC_NPROCESSORS_ONLN); - - if (test_collapse) { - /* nr_cpus must divide (bytes / page_size), otherwise, - * area allocations of (nr_pages * paze_size) won't be a - * multiple of hpage_size, even if bytes is a multiple of - * hpage_size. - * - * This means that nr_cpus must divide (N * (2 << (H-P)) - * where: - * bytes = hpage_size * N - * hpage_size = 2 << H - * page_size = 2 << P - * - * And we want to chose nr_cpus to be the largest value - * satisfying this constraint, not larger than the number - * of online CPUs. Unfortunately, prime factorization of - * N and nr_cpus may be arbitrary, so have to search for it. - * Instead, just use the highest power of 2 dividing both - * nr_cpus and (bytes / page_size). - */ - int x = factor_of_2(nr_cpus); - int y = factor_of_2(bytes / page_size); - - nr_cpus = x < y ? x : y; - } - nr_pages_per_cpu = bytes / page_size / nr_cpus; - if (!nr_pages_per_cpu) { - _err("invalid MiB"); - usage(); - } - - bounces = atoi(argv[3]); - if (bounces <= 0) { - _err("invalid bounces"); - usage(); - } - nr_pages = nr_pages_per_cpu * nr_cpus; - - if (test_type == TEST_SHMEM || test_type == TEST_HUGETLB) { - unsigned int memfd_flags = 0; - - if (test_type == TEST_HUGETLB) - memfd_flags = MFD_HUGETLB; - mem_fd = memfd_create(argv[0], memfd_flags); - if (mem_fd < 0) - err("memfd_create"); - if (ftruncate(mem_fd, nr_pages * page_size * 2)) - err("ftruncate"); - if (fallocate(mem_fd, - FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE, 0, - nr_pages * page_size * 2)) - err("fallocate"); - } - printf("nr_pages: %lu, nr_pages_per_cpu: %lu\n", - nr_pages, nr_pages_per_cpu); - return userfaultfd_stress(); -} - -#else /* __NR_userfaultfd */ - -#warning "missing __NR_userfaultfd definition" - -int main(void) -{ - printf("skip: Skipping userfaultfd test (missing __NR_userfaultfd)\n"); - return KSFT_SKIP; -} - -#endif /* __NR_userfaultfd */ diff --git a/tools/testing/selftests/mm/util.h b/tools/testing/selftests/mm/util.h deleted file mode 100644 index b27d26199334..000000000000 --- a/tools/testing/selftests/mm/util.h +++ /dev/null @@ -1,69 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ - -#ifndef __KSELFTEST_VM_UTIL_H -#define __KSELFTEST_VM_UTIL_H - -#include <stdint.h> -#include <sys/mman.h> -#include <err.h> -#include <string.h> /* ffsl() */ -#include <unistd.h> /* _SC_PAGESIZE */ - -static unsigned int __page_size; -static unsigned int __page_shift; - -static inline unsigned int page_size(void) -{ - if (!__page_size) - __page_size = sysconf(_SC_PAGESIZE); - return __page_size; -} - -static inline unsigned int page_shift(void) -{ - if (!__page_shift) - __page_shift = (ffsl(page_size()) - 1); - return __page_shift; -} - -#define PAGE_SHIFT (page_shift()) -#define PAGE_SIZE (page_size()) -/* - * On ppc64 this will only work with radix 2M hugepage size - */ -#define HPAGE_SHIFT 21 -#define HPAGE_SIZE (1 << HPAGE_SHIFT) - -#define PAGEMAP_PRESENT(ent) (((ent) & (1ull << 63)) != 0) -#define PAGEMAP_PFN(ent) ((ent) & ((1ull << 55) - 1)) - - -static inline int64_t allocate_transhuge(void *ptr, int pagemap_fd) -{ - uint64_t ent[2]; - - /* drop pmd */ - if (mmap(ptr, HPAGE_SIZE, PROT_READ | PROT_WRITE, - MAP_FIXED | MAP_ANONYMOUS | - MAP_NORESERVE | MAP_PRIVATE, -1, 0) != ptr) - errx(2, "mmap transhuge"); - - if (madvise(ptr, HPAGE_SIZE, MADV_HUGEPAGE)) - err(2, "MADV_HUGEPAGE"); - - /* allocate transparent huge page */ - *(volatile void **)ptr = ptr; - - if (pread(pagemap_fd, ent, sizeof(ent), - (uintptr_t)ptr >> (PAGE_SHIFT - 3)) != sizeof(ent)) - err(2, "read pagemap"); - - if (PAGEMAP_PRESENT(ent[0]) && PAGEMAP_PRESENT(ent[1]) && - PAGEMAP_PFN(ent[0]) + 1 == PAGEMAP_PFN(ent[1]) && - !(PAGEMAP_PFN(ent[0]) & ((1 << (HPAGE_SHIFT - PAGE_SHIFT)) - 1))) - return PAGEMAP_PFN(ent[0]); - - return -1; -} - -#endif diff --git a/tools/testing/selftests/mm/va_128TBswitch.c b/tools/testing/selftests/mm/va_high_addr_switch.c index 1d2068989883..7cfaf4a74c57 100644 --- a/tools/testing/selftests/mm/va_128TBswitch.c +++ b/tools/testing/selftests/mm/va_high_addr_switch.c @@ -17,18 +17,38 @@ * This will work with 16M and 2M hugepage size */ #define HUGETLB_SIZE (16 << 20) +#elif __aarch64__ +/* + * The default hugepage size for 64k base pagesize + * is 512MB. + */ +#define PAGE_SIZE (64 << 10) +#define HUGETLB_SIZE (512 << 20) #else #define PAGE_SIZE (4 << 10) #define HUGETLB_SIZE (2 << 20) #endif /* - * >= 128TB is the hint addr value we used to select - * large address space. + * The hint addr value is used to allocate addresses + * beyond the high address switch boundary. */ -#define ADDR_SWITCH_HINT (1UL << 47) + +#define ADDR_MARK_128TB (1UL << 47) +#define ADDR_MARK_256TB (1UL << 48) + +#define HIGH_ADDR_128TB ((void *) (1UL << 48)) +#define HIGH_ADDR_256TB ((void *) (1UL << 49)) + #define LOW_ADDR ((void *) (1UL << 30)) -#define HIGH_ADDR ((void *) (1UL << 48)) + +#ifdef __aarch64__ +#define ADDR_SWITCH_HINT ADDR_MARK_256TB +#define HIGH_ADDR HIGH_ADDR_256TB +#else +#define ADDR_SWITCH_HINT ADDR_MARK_128TB +#define HIGH_ADDR HIGH_ADDR_128TB +#endif struct testcase { void *addr; @@ -53,9 +73,10 @@ static struct testcase testcases[] = { }, { /* - * We should never allocate at the requested address or above it - * The len cross the 128TB boundary. Without MAP_FIXED - * we will always search in the lower address space. + * Unless MAP_FIXED is specified, allocation based on hint + * addr is never at requested address or above it, which is + * beyond high address switch boundary in this case. Instead, + * a suitable allocation is found in lower address space. */ .addr = ((void *)(ADDR_SWITCH_HINT - PAGE_SIZE)), .size = 2 * PAGE_SIZE, @@ -65,8 +86,8 @@ static struct testcase testcases[] = { }, { /* - * Exact mapping at 128TB, the area is free we should get that - * even without MAP_FIXED. + * Exact mapping at high address switch boundary, should + * be obtained even without MAP_FIXED as area is free. */ .addr = ((void *)(ADDR_SWITCH_HINT)), .size = PAGE_SIZE, @@ -270,6 +291,8 @@ static int supported_arch(void) return 1; #elif defined(__x86_64__) return 1; +#elif defined(__aarch64__) + return 1; #else return 0; #endif diff --git a/tools/testing/selftests/mm/va_128TBswitch.sh b/tools/testing/selftests/mm/va_high_addr_switch.sh index 41580751dc51..45cae7cab27e 100644 --- a/tools/testing/selftests/mm/va_128TBswitch.sh +++ b/tools/testing/selftests/mm/va_high_addr_switch.sh @@ -51,4 +51,8 @@ check_test_requirements() } check_test_requirements -./va_128TBswitch +./va_high_addr_switch + +# In order to run hugetlb testcases, "--run-hugetlb" must be appended +# to the binary. +./va_high_addr_switch --run-hugetlb diff --git a/tools/testing/selftests/mm/virtual_address_range.c b/tools/testing/selftests/mm/virtual_address_range.c index c0592646ed93..bae0ceaf95b1 100644 --- a/tools/testing/selftests/mm/virtual_address_range.c +++ b/tools/testing/selftests/mm/virtual_address_range.c @@ -15,11 +15,15 @@ /* * Maximum address range mapped with a single mmap() - * call is little bit more than 16GB. Hence 16GB is + * call is little bit more than 1GB. Hence 1GB is * chosen as the single chunk size for address space * mapping. */ -#define MAP_CHUNK_SIZE 17179869184UL /* 16GB */ + +#define SZ_1GB (1024 * 1024 * 1024UL) +#define SZ_1TB (1024 * 1024 * 1024 * 1024UL) + +#define MAP_CHUNK_SIZE SZ_1GB /* * Address space till 128TB is mapped without any hint @@ -32,13 +36,15 @@ * till it reaches 512TB. One with size 128TB and the * other being 384TB. * - * On Arm64 the address space is 256TB and no high mappings - * are supported so far. + * On Arm64 the address space is 256TB and support for + * high mappings up to 4PB virtual address space has + * been added. */ -#define NR_CHUNKS_128TB 8192UL /* Number of 16GB chunks for 128TB */ +#define NR_CHUNKS_128TB ((128 * SZ_1TB) / MAP_CHUNK_SIZE) /* Number of chunks for 128TB */ #define NR_CHUNKS_256TB (NR_CHUNKS_128TB * 2UL) #define NR_CHUNKS_384TB (NR_CHUNKS_128TB * 3UL) +#define NR_CHUNKS_3840TB (NR_CHUNKS_128TB * 30UL) #define ADDR_MARK_128TB (1UL << 47) /* First address beyond 128TB */ #define ADDR_MARK_256TB (1UL << 48) /* First address beyond 256TB */ @@ -47,7 +53,7 @@ #define HIGH_ADDR_MARK ADDR_MARK_256TB #define HIGH_ADDR_SHIFT 49 #define NR_CHUNKS_LOW NR_CHUNKS_256TB -#define NR_CHUNKS_HIGH 0 +#define NR_CHUNKS_HIGH NR_CHUNKS_3840TB #else #define HIGH_ADDR_MARK ADDR_MARK_128TB #define HIGH_ADDR_SHIFT 48 @@ -97,7 +103,7 @@ static int validate_lower_address_hint(void) int main(int argc, char *argv[]) { char *ptr[NR_CHUNKS_LOW]; - char *hptr[NR_CHUNKS_HIGH]; + char **hptr; char *hint; unsigned long i, lchunks, hchunks; @@ -115,6 +121,9 @@ int main(int argc, char *argv[]) return 1; } lchunks = i; + hptr = (char **) calloc(NR_CHUNKS_HIGH, sizeof(char *)); + if (hptr == NULL) + return 1; for (i = 0; i < NR_CHUNKS_HIGH; i++) { hint = hind_addr(); @@ -135,5 +144,6 @@ int main(int argc, char *argv[]) for (i = 0; i < hchunks; i++) munmap(hptr[i], MAP_CHUNK_SIZE); + free(hptr); return 0; } diff --git a/tools/testing/selftests/mm/vm_util.c b/tools/testing/selftests/mm/vm_util.c index 40e795624ff3..9b06a5034808 100644 --- a/tools/testing/selftests/mm/vm_util.c +++ b/tools/testing/selftests/mm/vm_util.c @@ -1,6 +1,10 @@ // SPDX-License-Identifier: GPL-2.0 #include <string.h> #include <fcntl.h> +#include <sys/ioctl.h> +#include <linux/userfaultfd.h> +#include <sys/syscall.h> +#include <unistd.h> #include "../kselftest.h" #include "vm_util.h" @@ -8,6 +12,9 @@ #define SMAP_FILE_PATH "/proc/self/smaps" #define MAX_LINE_LENGTH 500 +unsigned int __page_size; +unsigned int __page_shift; + uint64_t pagemap_get_entry(int fd, char *start) { const unsigned long pfn = (unsigned long)start / getpagesize(); @@ -22,25 +29,17 @@ uint64_t pagemap_get_entry(int fd, char *start) bool pagemap_is_softdirty(int fd, char *start) { - uint64_t entry = pagemap_get_entry(fd, start); - - // Check if dirty bit (55th bit) is set - return entry & 0x0080000000000000ull; + return pagemap_get_entry(fd, start) & PM_SOFT_DIRTY; } bool pagemap_is_swapped(int fd, char *start) { - uint64_t entry = pagemap_get_entry(fd, start); - - return entry & 0x4000000000000000ull; + return pagemap_get_entry(fd, start) & PM_SWAP; } bool pagemap_is_populated(int fd, char *start) { - uint64_t entry = pagemap_get_entry(fd, start); - - /* Present or swapped. */ - return entry & 0xc000000000000000ull; + return pagemap_get_entry(fd, start) & (PM_PRESENT | PM_SWAP); } unsigned long pagemap_get_pfn(int fd, char *start) @@ -48,7 +47,7 @@ unsigned long pagemap_get_pfn(int fd, char *start) uint64_t entry = pagemap_get_entry(fd, start); /* If present (63th bit), PFN is at bit 0 -- 54. */ - if (entry & 0x8000000000000000ull) + if (entry & PM_PRESENT) return entry & 0x007fffffffffffffull; return -1ul; } @@ -84,12 +83,12 @@ uint64_t read_pmd_pagesize(void) fd = open(PMD_SIZE_FILE_PATH, O_RDONLY); if (fd == -1) - ksft_exit_fail_msg("Open hpage_pmd_size failed\n"); + return 0; num_read = read(fd, buf, 19); if (num_read < 1) { close(fd); - ksft_exit_fail_msg("Read hpage_pmd_size failed\n"); + return 0; } buf[num_read] = '\0'; close(fd); @@ -149,3 +148,156 @@ bool check_huge_shmem(void *addr, int nr_hpages, uint64_t hpage_size) { return __check_huge(addr, "ShmemPmdMapped:", nr_hpages, hpage_size); } + +int64_t allocate_transhuge(void *ptr, int pagemap_fd) +{ + uint64_t ent[2]; + + /* drop pmd */ + if (mmap(ptr, HPAGE_SIZE, PROT_READ | PROT_WRITE, + MAP_FIXED | MAP_ANONYMOUS | + MAP_NORESERVE | MAP_PRIVATE, -1, 0) != ptr) + errx(2, "mmap transhuge"); + + if (madvise(ptr, HPAGE_SIZE, MADV_HUGEPAGE)) + err(2, "MADV_HUGEPAGE"); + + /* allocate transparent huge page */ + *(volatile void **)ptr = ptr; + + if (pread(pagemap_fd, ent, sizeof(ent), + (uintptr_t)ptr >> (pshift() - 3)) != sizeof(ent)) + err(2, "read pagemap"); + + if (PAGEMAP_PRESENT(ent[0]) && PAGEMAP_PRESENT(ent[1]) && + PAGEMAP_PFN(ent[0]) + 1 == PAGEMAP_PFN(ent[1]) && + !(PAGEMAP_PFN(ent[0]) & ((1 << (HPAGE_SHIFT - pshift())) - 1))) + return PAGEMAP_PFN(ent[0]); + + return -1; +} + +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; +} + +/* If `ioctls' non-NULL, the allowed ioctls will be returned into the var */ +int uffd_register_with_ioctls(int uffd, void *addr, uint64_t len, + bool miss, bool wp, bool minor, uint64_t *ioctls) +{ + struct uffdio_register uffdio_register = { 0 }; + uint64_t mode = 0; + int ret = 0; + + if (miss) + mode |= UFFDIO_REGISTER_MODE_MISSING; + if (wp) + mode |= UFFDIO_REGISTER_MODE_WP; + if (minor) + mode |= UFFDIO_REGISTER_MODE_MINOR; + + uffdio_register.range.start = (unsigned long)addr; + uffdio_register.range.len = len; + uffdio_register.mode = mode; + + if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register) == -1) + ret = -errno; + else if (ioctls) + *ioctls = uffdio_register.ioctls; + + return ret; +} + +int uffd_register(int uffd, void *addr, uint64_t len, + bool miss, bool wp, bool minor) +{ + return uffd_register_with_ioctls(uffd, addr, len, + miss, wp, minor, NULL); +} + +int uffd_unregister(int uffd, void *addr, uint64_t len) +{ + struct uffdio_range range = { .start = (uintptr_t)addr, .len = len }; + int ret = 0; + + if (ioctl(uffd, UFFDIO_UNREGISTER, &range) == -1) + ret = -errno; + + return ret; +} + +int uffd_open_dev(unsigned int flags) +{ + int fd, uffd; + + fd = open("/dev/userfaultfd", O_RDWR | O_CLOEXEC); + if (fd < 0) + return fd; + uffd = ioctl(fd, USERFAULTFD_IOC_NEW, flags); + close(fd); + + return uffd; +} + +int uffd_open_sys(unsigned int flags) +{ +#ifdef __NR_userfaultfd + return syscall(__NR_userfaultfd, flags); +#else + return -1; +#endif +} + +int uffd_open(unsigned int flags) +{ + int uffd = uffd_open_sys(flags); + + if (uffd < 0) + uffd = uffd_open_dev(flags); + + return uffd; +} + +int uffd_get_features(uint64_t *features) +{ + struct uffdio_api uffdio_api = { .api = UFFD_API, .features = 0 }; + /* + * This should by default work in most kernels; the feature list + * will be the same no matter what we pass in here. + */ + int fd = uffd_open(UFFD_USER_MODE_ONLY); + + if (fd < 0) + /* Maybe the kernel is older than user-only mode? */ + fd = uffd_open(0); + + if (fd < 0) + return fd; + + if (ioctl(fd, UFFDIO_API, &uffdio_api)) { + close(fd); + return -errno; + } + + *features = uffdio_api.features; + close(fd); + + return 0; +} diff --git a/tools/testing/selftests/mm/vm_util.h b/tools/testing/selftests/mm/vm_util.h index 1995ee911ef2..b950bd16083a 100644 --- a/tools/testing/selftests/mm/vm_util.h +++ b/tools/testing/selftests/mm/vm_util.h @@ -1,6 +1,35 @@ /* SPDX-License-Identifier: GPL-2.0 */ #include <stdint.h> #include <stdbool.h> +#include <sys/mman.h> +#include <err.h> +#include <string.h> /* ffsl() */ +#include <unistd.h> /* _SC_PAGESIZE */ + +#define BIT_ULL(nr) (1ULL << (nr)) +#define PM_SOFT_DIRTY BIT_ULL(55) +#define PM_MMAP_EXCLUSIVE BIT_ULL(56) +#define PM_UFFD_WP BIT_ULL(57) +#define PM_FILE BIT_ULL(61) +#define PM_SWAP BIT_ULL(62) +#define PM_PRESENT BIT_ULL(63) + +extern unsigned int __page_size; +extern unsigned int __page_shift; + +static inline unsigned int psize(void) +{ + if (!__page_size) + __page_size = sysconf(_SC_PAGESIZE); + return __page_size; +} + +static inline unsigned int pshift(void) +{ + if (!__page_shift) + __page_shift = (ffsl(psize()) - 1); + return __page_shift; +} uint64_t pagemap_get_entry(int fd, char *start); bool pagemap_is_softdirty(int fd, char *start); @@ -13,3 +42,24 @@ uint64_t read_pmd_pagesize(void); bool check_huge_anon(void *addr, int nr_hpages, uint64_t hpage_size); bool check_huge_file(void *addr, int nr_hpages, uint64_t hpage_size); bool check_huge_shmem(void *addr, int nr_hpages, uint64_t hpage_size); +int64_t allocate_transhuge(void *ptr, int pagemap_fd); +unsigned long default_huge_page_size(void); + +int uffd_register(int uffd, void *addr, uint64_t len, + bool miss, bool wp, bool minor); +int uffd_unregister(int uffd, void *addr, uint64_t len); +int uffd_open_dev(unsigned int flags); +int uffd_open_sys(unsigned int flags); +int uffd_open(unsigned int flags); +int uffd_get_features(uint64_t *features); +int uffd_register_with_ioctls(int uffd, void *addr, uint64_t len, + bool miss, bool wp, bool minor, uint64_t *ioctls); + +/* + * On ppc64 this will only work with radix 2M hugepage size + */ +#define HPAGE_SHIFT 21 +#define HPAGE_SIZE (1 << HPAGE_SHIFT) + +#define PAGEMAP_PRESENT(ent) (((ent) & (1ull << 63)) != 0) +#define PAGEMAP_PFN(ent) ((ent) & ((1ull << 55) - 1)) |