Let's add a test to measure performance of KSM breaking not triggered via COW, but triggered by disabling KSM on an area filled with KSM pages via MADV_UNMERGEABLE.

Signed-off-by: David Hildenbrand david@redhat.com --- tools/testing/selftests/vm/ksm_tests.c | 76 +++++++++++++++++++++++++- 1 file changed, 74 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/vm/ksm_tests.c b/tools/testing/selftests/vm/ksm_tests.c index f5e4e0bbd081..353eee96aeba 100644 --- a/tools/testing/selftests/vm/ksm_tests.c +++ b/tools/testing/selftests/vm/ksm_tests.c @@ -40,6 +40,7 @@ enum ksm_test_name { CHECK_KSM_NUMA_MERGE, KSM_MERGE_TIME, KSM_MERGE_TIME_HUGE_PAGES, + KSM_UNMERGE_TIME, KSM_COW_TIME };

@@ -108,7 +109,10 @@ static void print_help(void) " -P evaluate merging time and speed.\n" " For this test, the size of duplicated memory area (in MiB)\n" " must be provided using -s option\n" - " -H evaluate merging time and speed of area allocated mostly with huge pages\n" + " -H evaluate merging time and speed of area allocated mostly with huge pages\n" + " For this test, the size of duplicated memory area (in MiB)\n" + " must be provided using -s option\n" + " -D evaluate unmerging time and speed when disabling KSM.\n" " For this test, the size of duplicated memory area (in MiB)\n" " must be provided using -s option\n" " -C evaluate the time required to break COW of merged pages.\n\n"); @@ -188,6 +192,16 @@ static int ksm_merge_pages(void *addr, size_t size, struct timespec start_time, return 0; }

+static int ksm_unmerge_pages(void *addr, size_t size, + struct timespec start_time, int timeout) +{ + if (madvise(addr, size, MADV_UNMERGEABLE)) { + perror("madvise"); + return 1; + } + return 0; +} + static bool assert_ksm_pages_count(long dupl_page_count) { unsigned long max_page_sharing, pages_sharing, pages_shared; @@ -560,6 +574,53 @@ static int ksm_merge_time(int mapping, int prot, int timeout, size_t map_size) return KSFT_FAIL; }

+static int ksm_unmerge_time(int mapping, int prot, int timeout, size_t map_size) +{ + void *map_ptr; + struct timespec start_time, end_time; + unsigned long scan_time_ns; + + map_size *= MB; + + map_ptr = allocate_memory(NULL, prot, mapping, '*', map_size); + if (!map_ptr) + return KSFT_FAIL; + if (clock_gettime(CLOCK_MONOTONIC_RAW, &start_time)) { + perror("clock_gettime"); + goto err_out; + } + if (ksm_merge_pages(map_ptr, map_size, start_time, timeout)) + goto err_out; + + if (clock_gettime(CLOCK_MONOTONIC_RAW, &start_time)) { + perror("clock_gettime"); + goto err_out; + } + if (ksm_unmerge_pages(map_ptr, map_size, start_time, timeout)) + goto err_out; + if (clock_gettime(CLOCK_MONOTONIC_RAW, &end_time)) { + perror("clock_gettime"); + goto err_out; + } + + scan_time_ns = (end_time.tv_sec - start_time.tv_sec) * NSEC_PER_SEC + + (end_time.tv_nsec - start_time.tv_nsec); + + printf("Total size: %lu MiB\n", map_size / MB); + printf("Total time: %ld.%09ld s\n", scan_time_ns / NSEC_PER_SEC, + scan_time_ns % NSEC_PER_SEC); + printf("Average speed: %.3f MiB/s\n", (map_size / MB) / + ((double)scan_time_ns / NSEC_PER_SEC)); + + munmap(map_ptr, map_size); + return KSFT_PASS; + +err_out: + printf("Not OK\n"); + munmap(map_ptr, map_size); + return KSFT_FAIL; +} + static int ksm_cow_time(int mapping, int prot, int timeout, size_t page_size) { void *map_ptr; @@ -644,7 +705,7 @@ 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:MUZNPCH")) != -1) { + while ((opt = getopt(argc, argv, "ha:p:l:z:m:s:MUZNPCHD")) != -1) { switch (opt) { case 'a': prot = str_to_prot(optarg); @@ -701,6 +762,9 @@ int main(int argc, char *argv[]) case 'H': test_name = KSM_MERGE_TIME_HUGE_PAGES; break; + case 'D': + test_name = KSM_UNMERGE_TIME; + break; case 'C': test_name = KSM_COW_TIME; break; @@ -762,6 +826,14 @@ int main(int argc, char *argv[]) ret = ksm_merge_hugepages_time(MAP_PRIVATE | MAP_ANONYMOUS, prot, ksm_scan_limit_sec, size_MB); break; + case KSM_UNMERGE_TIME: + if (size_MB == 0) { + printf("Option '-s' is required.\n"); + return KSFT_FAIL; + } + ret = ksm_unmerge_time(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);

Now that GUP no longer requires VM_FAULT_WRITE, break_ksm() is the sole remaining user of VM_FAULT_WRITE. As we also want to stop triggering a fake write fault and instead use FAULT_FLAG_UNSHARE -- similar to GUP-triggered unsharing when taking a R/O pin on a shared anonymous page (including KSM pages), let's stop relying on VM_FAULT_WRITE.

Let's rework break_ksm() to not rely on the return value of handle_mm_fault() anymore to figure out whether COW-breaking was successful. Simply perform another follow_page() lookup to verify the result.

While this makes break_ksm() slightly less efficient, we can simplify handle_mm_fault() a little and easily switch to FAULT_FLAG_UNSHARE without introducing similar KSM-specific behavior for FAULT_FLAG_UNSHARE.

In my setup (AMD Ryzen 9 3900X), running the KSM selftest to test unmerge performance on 2 GiB (taskset 0x8 ./ksm_tests -D -s 2048), this results in a performance degradation of ~4% -- 5% (old: ~5250 MiB/s, new: ~5010 MiB/s).

I don't think that we particularly care about that performance drop when unmerging. If it ever turns out to be an actual performance issue, we can think about a better alternative for FAULT_FLAG_UNSHARE -- let's just keep it simple for now.

Signed-off-by: David Hildenbrand david@redhat.com --- mm/ksm.c | 25 +++++++++++++------------ 1 file changed, 13 insertions(+), 12 deletions(-)

diff --git a/mm/ksm.c b/mm/ksm.c index 0cd2f4b62334..e8d987fb379e 100644 --- a/mm/ksm.c +++ b/mm/ksm.c @@ -473,26 +473,27 @@ static int break_ksm(struct vm_area_struct *vma, unsigned long addr) vm_fault_t ret = 0;

do { + bool ksm_page = false; + cond_resched(); page = follow_page(vma, addr, FOLL_GET | FOLL_MIGRATION | FOLL_REMOTE); if (IS_ERR_OR_NULL(page)) break; if (PageKsm(page)) - ret = handle_mm_fault(vma, addr, - FAULT_FLAG_WRITE | FAULT_FLAG_REMOTE, - NULL); - else - ret = VM_FAULT_WRITE; + ksm_page = true; put_page(page); - } while (!(ret & (VM_FAULT_WRITE | VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV | VM_FAULT_OOM))); + + if (!ksm_page) + return 0; + ret = handle_mm_fault(vma, addr, + FAULT_FLAG_WRITE | FAULT_FLAG_REMOTE, + NULL); + } while (!(ret & (VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV | VM_FAULT_OOM))); /* - * We must loop because handle_mm_fault() may back out if there's - * any difficulty e.g. if pte accessed bit gets updated concurrently. - * - * VM_FAULT_WRITE is what we have been hoping for: it indicates that - * COW has been broken, even if the vma does not permit VM_WRITE; - * but note that a concurrent fault might break PageKsm for us. + * We must loop until we no longer find a KSM page because + * handle_mm_fault() may back out if there's any difficulty e.g. if + * pte accessed bit gets updated concurrently. * * VM_FAULT_SIGBUS could occur if we race with truncation of the * backing file, which also invalidates anonymous pages: that's

All users -- GUP and KSM -- are gone, let's just remove it.

Signed-off-by: David Hildenbrand david@redhat.com --- include/linux/mm_types.h | 3 --- mm/huge_memory.c | 2 +- mm/memory.c | 9 ++++----- 3 files changed, 5 insertions(+), 9 deletions(-)

diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 8f30f262431c..6a1375dcb4ac 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -807,7 +807,6 @@ typedef __bitwise unsigned int vm_fault_t; * @VM_FAULT_OOM: Out Of Memory * @VM_FAULT_SIGBUS: Bad access * @VM_FAULT_MAJOR: Page read from storage - * @VM_FAULT_WRITE: Special case for get_user_pages * @VM_FAULT_HWPOISON: Hit poisoned small page * @VM_FAULT_HWPOISON_LARGE: Hit poisoned large page. Index encoded * in upper bits @@ -828,7 +827,6 @@ enum vm_fault_reason { VM_FAULT_OOM = (__force vm_fault_t)0x000001, VM_FAULT_SIGBUS = (__force vm_fault_t)0x000002, VM_FAULT_MAJOR = (__force vm_fault_t)0x000004, - VM_FAULT_WRITE = (__force vm_fault_t)0x000008, VM_FAULT_HWPOISON = (__force vm_fault_t)0x000010, VM_FAULT_HWPOISON_LARGE = (__force vm_fault_t)0x000020, VM_FAULT_SIGSEGV = (__force vm_fault_t)0x000040, @@ -854,7 +852,6 @@ enum vm_fault_reason { { VM_FAULT_OOM, "OOM" }, \ { VM_FAULT_SIGBUS, "SIGBUS" }, \ { VM_FAULT_MAJOR, "MAJOR" }, \ - { VM_FAULT_WRITE, "WRITE" }, \ { VM_FAULT_HWPOISON, "HWPOISON" }, \ { VM_FAULT_HWPOISON_LARGE, "HWPOISON_LARGE" }, \ { VM_FAULT_SIGSEGV, "SIGSEGV" }, \ diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 84bf1d5f6b7e..b351c1d4f858 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1376,7 +1376,7 @@ vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf) if (pmdp_set_access_flags(vma, haddr, vmf->pmd, entry, 1)) update_mmu_cache_pmd(vma, vmf->address, vmf->pmd); spin_unlock(vmf->ptl); - return VM_FAULT_WRITE; + return 0; }

unlock_fallback: diff --git a/mm/memory.c b/mm/memory.c index e49faa0a1f9a..6e2f47d05f2b 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3240,7 +3240,7 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf) }

delayacct_wpcopy_end(); - return (page_copied && !unshare) ? VM_FAULT_WRITE : 0; + return 0; oom_free_new: put_page(new_page); oom: @@ -3304,14 +3304,14 @@ static vm_fault_t wp_pfn_shared(struct vm_fault *vmf) return finish_mkwrite_fault(vmf); } wp_page_reuse(vmf); - return VM_FAULT_WRITE; + return 0; }

static vm_fault_t wp_page_shared(struct vm_fault *vmf) __releases(vmf->ptl) { struct vm_area_struct *vma = vmf->vma; - vm_fault_t ret = VM_FAULT_WRITE; + vm_fault_t ret = 0;

get_page(vmf->page);

@@ -3462,7 +3462,7 @@ static vm_fault_t do_wp_page(struct vm_fault *vmf) return 0; } wp_page_reuse(vmf); - return VM_FAULT_WRITE; + return 0; } else if (unshare) { /* No anonymous page -> nothing to do. */ pte_unmap_unlock(vmf->pte, vmf->ptl); @@ -3960,7 +3960,6 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) if (vmf->flags & FAULT_FLAG_WRITE) { pte = maybe_mkwrite(pte_mkdirty(pte), vma); vmf->flags &= ~FAULT_FLAG_WRITE; - ret |= VM_FAULT_WRITE; } rmap_flags |= RMAP_EXCLUSIVE; }

Let's stop breaking COW via a fake write fault and let's use FAULT_FLAG_UNSHARE instead. This avoids any wrong side effects of the fake write fault, such as mapping the PTE writable and marking the pte dirty/softdirty.

Also, this fixes KSM interaction with userfaultfd-wp: when we have a KSM page that's write-protected by userfaultfd, break_ksm()->handle_mm_fault() will fail with VM_FAULT_SIGBUS and will simpy return in break_ksm() with 0. The warning in dmesg indicates this wrong handling:

[ 230.096368] FAULT_FLAG_ALLOW_RETRY missing 881 [ 230.100822] CPU: 1 PID: 1643 Comm: ksm-uffd-wp [...] [ 230.110124] Hardware name: [...] [ 230.117775] Call Trace: [ 230.120227] <TASK> [ 230.122334] dump_stack_lvl+0x44/0x5c [ 230.126010] handle_userfault.cold+0x14/0x19 [ 230.130281] ? tlb_finish_mmu+0x65/0x170 [ 230.134207] ? uffd_wp_range+0x65/0xa0 [ 230.137959] ? _raw_spin_unlock+0x15/0x30 [ 230.141972] ? do_wp_page+0x50/0x590 [ 230.145551] __handle_mm_fault+0x9f5/0xf50 [ 230.149652] ? mmput+0x1f/0x40 [ 230.152712] handle_mm_fault+0xb9/0x2a0 [ 230.156550] break_ksm+0x141/0x180 [ 230.159964] unmerge_ksm_pages+0x60/0x90 [ 230.163890] ksm_madvise+0x3c/0xb0 [ 230.167295] do_madvise.part.0+0x10c/0xeb0 [ 230.171396] ? do_syscall_64+0x67/0x80 [ 230.175157] __x64_sys_madvise+0x5a/0x70 [ 230.179082] do_syscall_64+0x58/0x80 [ 230.182661] ? do_syscall_64+0x67/0x80 [ 230.186413] entry_SYSCALL_64_after_hwframe+0x63/0xcd

--------------------------------------------------------------------------

#include <stdio.h> #include <stdlib.h> #include <string.h> #include <fcntl.h> #include <unistd.h> #include <errno.h> #include <sys/mman.h> #include <sys/syscall.h> #include <sys/ioctl.h> #include <linux/userfaultfd.h>

#define MMAP_SIZE (2 * 1024 * 1024u)

static char *map; int uffd;

static int setup_uffd(void) { struct uffdio_api uffdio_api; struct uffdio_register uffdio_register; struct uffdio_writeprotect uffd_writeprotect; struct uffdio_range uffd_range;

uffd = syscall(__NR_userfaultfd, O_CLOEXEC | O_NONBLOCK); if (uffd < 0) { fprintf(stderr, "syscall() failed: %d\n", errno); return -errno; }

uffdio_api.api = UFFD_API; uffdio_api.features = UFFD_FEATURE_PAGEFAULT_FLAG_WP; if (ioctl(uffd, UFFDIO_API, &uffdio_api) < 0) { fprintf(stderr, "UFFDIO_API failed: %d\n", errno); return -errno; }

if (!(uffdio_api.features & UFFD_FEATURE_PAGEFAULT_FLAG_WP)) { fprintf(stderr, "UFFD_FEATURE_WRITEPROTECT missing\n"); return -ENOSYS; }

/* Register UFFD-WP */ uffdio_register.range.start = (unsigned long) map; uffdio_register.range.len = MMAP_SIZE; uffdio_register.mode = UFFDIO_REGISTER_MODE_WP; if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register) < 0) { fprintf(stderr, "UFFDIO_REGISTER failed: %d\n", errno); return -errno; }

/* Writeprotect the range. */ uffd_writeprotect.range.start = (unsigned long) map; uffd_writeprotect.range.len = MMAP_SIZE; uffd_writeprotect.mode = UFFDIO_WRITEPROTECT_MODE_WP; if (ioctl(uffd, UFFDIO_WRITEPROTECT, &uffd_writeprotect)) { fprintf(stderr, "UFFDIO_WRITEPROTECT failed: %d\n", errno); return -errno; }

return 0; }

int main(int argc, char **argv) { int ksm_fd, ret;

ksm_fd = open("/sys/kernel/mm/ksm/run", O_RDWR); if (ksm_fd < 0) { fprintf(stderr, "KSM not available\n"); return -errno; }

map = mmap(NULL, MMAP_SIZE, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANON, -1, 0); if (map == MAP_FAILED) { fprintf(stderr, "mmap() failed\n"); return -errno; } ret = madvise(map, MMAP_SIZE, MADV_NOHUGEPAGE); if (ret) { fprintf(stderr, "MADV_NOHUGEPAGE failed\n"); return -errno; }

/* Fill with same value and trigger merging. */ memset(map, 0xff, MMAP_SIZE); ret = madvise(map, MMAP_SIZE, MADV_MERGEABLE); if (ret) { fprintf(stderr, "MADV_MERGEABLE failed\n"); return -errno; }

/* * Run KSM to trigger merging and wait a bit until merging should be * done. */ if (write(ksm_fd, "1", 1) != 1) { fprintf(stderr, "Running KSM failed\n"); } sleep(10);

/* Write-protect the range with UFFD. */ if (setup_uffd()) return 1;

/* Trigger unsharing. */ ret = madvise(map, MMAP_SIZE, MADV_UNMERGEABLE); if (ret) { fprintf(stderr, "MADV_UNMERGEABLE failed\n"); return -errno; }

return 0; }

--------------------------------------------------------------------------

Consequently, we will no longer trigger a fake write fault and break COW without any such side-effects.

This is primarily a fix for KSM+userfaultfd-wp, however, the fake write fault was always questionable. As this fix is not easy to backport and it's not very critical, let's not cc stable.

Fixes: 529b930b87d9 ("userfaultfd: wp: hook userfault handler to write protection fault") Signed-off-by: David Hildenbrand david@redhat.com --- mm/ksm.c | 12 +++++------- 1 file changed, 5 insertions(+), 7 deletions(-)

diff --git a/mm/ksm.c b/mm/ksm.c index e8d987fb379e..4d7bcf7da7c3 100644 --- a/mm/ksm.c +++ b/mm/ksm.c @@ -453,17 +453,15 @@ static inline bool ksm_test_exit(struct mm_struct *mm) }

/* - * We use break_ksm to break COW on a ksm page: it's a stripped down + * We use break_ksm to break COW on a ksm page by triggering unsharing, + * such that the ksm page will get replaced by an exclusive anonymous page. * - * if (get_user_pages(addr, 1, FOLL_WRITE, &page, NULL) == 1) - * put_page(page); - * - * but taking great care only to touch a ksm page, in a VM_MERGEABLE vma, + * We take great care only to touch a ksm page, in a VM_MERGEABLE vma, * in case the application has unmapped and remapped mm,addr meanwhile. * Could a ksm page appear anywhere else? Actually yes, in a VM_PFNMAP * mmap of /dev/mem, where we would not want to touch it. * - * FAULT_FLAG/FOLL_REMOTE are because we do this outside the context + * FAULT_FLAG_REMOTE/FOLL_REMOTE are because we do this outside the context * of the process that owns 'vma'. We also do not want to enforce * protection keys here anyway. */ @@ -487,7 +485,7 @@ static int break_ksm(struct vm_area_struct *vma, unsigned long addr) if (!ksm_page) return 0; ret = handle_mm_fault(vma, addr, - FAULT_FLAG_WRITE | FAULT_FLAG_REMOTE, + FAULT_FLAG_UNSHARE | FAULT_FLAG_REMOTE, NULL); } while (!(ret & (VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV | VM_FAULT_OOM))); /*

FOLL_MIGRATION exists only for the purpose of break_ksm(), and actually, there is not even the need to wait for the migration to finish, we only want to know if we're dealing with a KSM page.

Using follow_page() just to identify a KSM page overcomplicates GUP code. Let's use walk_page_range_vma() instead, because we don't actually care about the page itself, we only need to know a single property -- no need to even grab a reference on the page.

In my setup (AMD Ryzen 9 3900X), running the KSM selftest to test unmerge performance on 2 GiB (taskset 0x8 ./ksm_tests -D -s 2048), this results in a performance degradation of ~4% (old: ~5010 MiB/s, new: ~4800 MiB/s). I don't think we particularly care for now.

Signed-off-by: David Hildenbrand david@redhat.com --- mm/ksm.c | 70 +++++++++++++++++++++++++++++++++++++++++++++++++------- 1 file changed, 62 insertions(+), 8 deletions(-)

diff --git a/mm/ksm.c b/mm/ksm.c index 4d7bcf7da7c3..814c1a37c323 100644 --- a/mm/ksm.c +++ b/mm/ksm.c @@ -39,6 +39,7 @@ #include <linux/freezer.h> #include <linux/oom.h> #include <linux/numa.h> +#include <linux/pagewalk.h>

#include <asm/tlbflush.h> #include "internal.h" @@ -452,6 +453,60 @@ static inline bool ksm_test_exit(struct mm_struct *mm) return atomic_read(&mm->mm_users) == 0; }

+int break_ksm_pud_entry(pud_t *pud, unsigned long addr, unsigned long next, + struct mm_walk *walk) +{ + /* We only care about page tables to walk to a single base page. */ + if (pud_leaf(*pud) || !pud_present(*pud)) + return 1; + return 0; +} + +int break_ksm_pmd_entry(pmd_t *pmd, unsigned long addr, unsigned long next, + struct mm_walk *walk) +{ + bool *ksm_page = walk->private; + struct page *page = NULL; + pte_t *pte, ptent; + spinlock_t *ptl; + + /* We only care about page tables to walk to a single base page. */ + if (pmd_leaf(*pmd) || !pmd_present(*pmd)) + return 1; + + /* + * We only lookup a single page (a) no need to iterate; and (b) + * always return 1 to exit immediately and not iterate in the caller. + */ + pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl); + ptent = *pte; + + if (pte_none(ptent)) + return 1; + if (!pte_present(ptent)) { + swp_entry_t entry = pte_to_swp_entry(ptent); + + /* + * We only care about migration of KSM pages. As KSM pages + * remain KSM pages until freed, no need to wait here for + * migration to end to identify such. + */ + if (is_migration_entry(entry)) + page = pfn_swap_entry_to_page(entry); + } else { + page = vm_normal_page(walk->vma, addr, ptent); + } + if (page && PageKsm(page)) + *ksm_page = true; + pte_unmap_unlock(pte, ptl); + return 1; +} + +static const struct mm_walk_ops break_ksm_ops = { + .pud_entry = break_ksm_pud_entry, + .pmd_entry = break_ksm_pmd_entry, +}; + /* * We use break_ksm to break COW on a ksm page by triggering unsharing, * such that the ksm page will get replaced by an exclusive anonymous page. @@ -467,20 +522,19 @@ static inline bool ksm_test_exit(struct mm_struct *mm) */ static int break_ksm(struct vm_area_struct *vma, unsigned long addr) { - struct page *page; vm_fault_t ret = 0;

+ if (WARN_ON_ONCE(!IS_ALIGNED(addr, PAGE_SIZE))) + return -EINVAL; + do { bool ksm_page = false;

cond_resched(); - page = follow_page(vma, addr, - FOLL_GET | FOLL_MIGRATION | FOLL_REMOTE); - if (IS_ERR_OR_NULL(page)) - break; - if (PageKsm(page)) - ksm_page = true; - put_page(page); + ret = walk_page_range_vma(vma, addr, addr + PAGE_SIZE, + &break_ksm_ops, &ksm_page); + if (WARN_ON_ONCE(ret < 0)) + return ret;

if (!ksm_page) return 0;

Fortunately, the last user (KSM) is gone, so let's just remove this rather special code from generic GUP handling -- especially because KSM never required the PMD handling as KSM only deals with individual base pages.

Signed-off-by: David Hildenbrand david@redhat.com --- include/linux/mm.h | 1 - mm/gup.c | 55 +++++----------------------------------------- 2 files changed, 5 insertions(+), 51 deletions(-)

diff --git a/include/linux/mm.h b/include/linux/mm.h index e56dd8f7eae1..4c176e308ead 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2942,7 +2942,6 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address, * and return without waiting upon it */ #define FOLL_NOFAULT 0x80 /* do not fault in pages */ #define FOLL_HWPOISON 0x100 /* check page is hwpoisoned */ -#define FOLL_MIGRATION 0x400 /* wait for page to replace migration entry */ #define FOLL_TRIED 0x800 /* a retry, previous pass started an IO */ #define FOLL_REMOTE 0x2000 /* we are working on non-current tsk/mm */ #define FOLL_ANON 0x8000 /* don't do file mappings */ diff --git a/mm/gup.c b/mm/gup.c index ce00a4c40da8..37195c549f68 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -537,30 +537,13 @@ static struct page *follow_page_pte(struct vm_area_struct *vma, if (WARN_ON_ONCE((flags & (FOLL_PIN | FOLL_GET)) == (FOLL_PIN | FOLL_GET))) return ERR_PTR(-EINVAL); -retry: if (unlikely(pmd_bad(*pmd))) return no_page_table(vma, flags);

ptep = pte_offset_map_lock(mm, pmd, address, &ptl); pte = *ptep; - if (!pte_present(pte)) { - swp_entry_t entry; - /* - * KSM's break_ksm() relies upon recognizing a ksm page - * even while it is being migrated, so for that case we - * need migration_entry_wait(). - */ - if (likely(!(flags & FOLL_MIGRATION))) - goto no_page; - if (pte_none(pte)) - goto no_page; - entry = pte_to_swp_entry(pte); - if (!is_migration_entry(entry)) - goto no_page; - pte_unmap_unlock(ptep, ptl); - migration_entry_wait(mm, pmd, address); - goto retry; - } + if (!pte_present(pte)) + goto no_page; if (pte_protnone(pte) && !gup_can_follow_protnone(flags)) goto no_page;

@@ -682,28 +665,8 @@ static struct page *follow_pmd_mask(struct vm_area_struct *vma, return page; return no_page_table(vma, flags); } -retry: - if (!pmd_present(pmdval)) { - /* - * Should never reach here, if thp migration is not supported; - * Otherwise, it must be a thp migration entry. - */ - VM_BUG_ON(!thp_migration_supported() || - !is_pmd_migration_entry(pmdval)); - - if (likely(!(flags & FOLL_MIGRATION))) - return no_page_table(vma, flags); - - pmd_migration_entry_wait(mm, pmd); - pmdval = READ_ONCE(*pmd); - /* - * MADV_DONTNEED may convert the pmd to null because - * mmap_lock is held in read mode - */ - if (pmd_none(pmdval)) - return no_page_table(vma, flags); - goto retry; - } + if (!pmd_present(pmdval)) + return no_page_table(vma, flags); if (pmd_devmap(pmdval)) { ptl = pmd_lock(mm, pmd); page = follow_devmap_pmd(vma, address, pmd, flags, &ctx->pgmap); @@ -717,18 +680,10 @@ static struct page *follow_pmd_mask(struct vm_area_struct *vma, if (pmd_protnone(pmdval) && !gup_can_follow_protnone(flags)) return no_page_table(vma, flags);

-retry_locked: ptl = pmd_lock(mm, pmd); - if (unlikely(pmd_none(*pmd))) { - spin_unlock(ptl); - return no_page_table(vma, flags); - } if (unlikely(!pmd_present(*pmd))) { spin_unlock(ptl); - if (likely(!(flags & FOLL_MIGRATION))) - return no_page_table(vma, flags); - pmd_migration_entry_wait(mm, pmd); - goto retry_locked; + return no_page_table(vma, flags); } if (unlikely(!pmd_trans_huge(*pmd))) { spin_unlock(ptl);