From 964ab0040ff9598783bf37776b5e31b27b50e293 Mon Sep 17 00:00:00 2001 From: Axel Rasmussen Date: Wed, 30 Jun 2021 18:49:27 -0700 Subject: userfaultfd/shmem: advertise shmem minor fault support Now that the feature is fully implemented (the faulting path hooks exist so userspace is notified, and the ioctl to resolve such faults is available), advertise this as a supported feature. Link: https://lkml.kernel.org/r/20210503180737.2487560-6-axelrasmussen@google.com Signed-off-by: Axel Rasmussen Acked-by: Hugh Dickins Acked-by: Peter Xu Cc: Alexander Viro Cc: Andrea Arcangeli Cc: Brian Geffon Cc: "Dr . David Alan Gilbert" Cc: Jerome Glisse Cc: Joe Perches Cc: Kirill A. Shutemov Cc: Lokesh Gidra Cc: Mike Kravetz Cc: Mike Rapoport Cc: Mina Almasry Cc: Oliver Upton Cc: Shaohua Li Cc: Shuah Khan Cc: Stephen Rothwell Cc: Wang Qing Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/uapi/linux/userfaultfd.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/userfaultfd.h b/include/uapi/linux/userfaultfd.h index 650480f41f1d..05b31d60acf6 100644 --- a/include/uapi/linux/userfaultfd.h +++ b/include/uapi/linux/userfaultfd.h @@ -31,7 +31,8 @@ UFFD_FEATURE_MISSING_SHMEM | \ UFFD_FEATURE_SIGBUS | \ UFFD_FEATURE_THREAD_ID | \ - UFFD_FEATURE_MINOR_HUGETLBFS) + UFFD_FEATURE_MINOR_HUGETLBFS | \ + UFFD_FEATURE_MINOR_SHMEM) #define UFFD_API_IOCTLS \ ((__u64)1 << _UFFDIO_REGISTER | \ (__u64)1 << _UFFDIO_UNREGISTER | \ @@ -185,6 +186,9 @@ struct uffdio_api { * UFFD_FEATURE_MINOR_HUGETLBFS indicates that minor faults * can be intercepted (via REGISTER_MODE_MINOR) for * hugetlbfs-backed pages. + * + * UFFD_FEATURE_MINOR_SHMEM indicates the same support as + * UFFD_FEATURE_MINOR_HUGETLBFS, but for shmem-backed pages instead. */ #define UFFD_FEATURE_PAGEFAULT_FLAG_WP (1<<0) #define UFFD_FEATURE_EVENT_FORK (1<<1) @@ -196,6 +200,7 @@ struct uffdio_api { #define UFFD_FEATURE_SIGBUS (1<<7) #define UFFD_FEATURE_THREAD_ID (1<<8) #define UFFD_FEATURE_MINOR_HUGETLBFS (1<<9) +#define UFFD_FEATURE_MINOR_SHMEM (1<<10) __u64 features; __u64 ioctls; -- cgit v1.2.3-59-g8ed1b From 7858d7bca7fbbbbd5b940d2ec371b2d060b21b84 Mon Sep 17 00:00:00 2001 From: Feng Tang Date: Wed, 30 Jun 2021 18:51:00 -0700 Subject: mm/mempolicy: don't handle MPOL_LOCAL like a fake MPOL_PREFERRED policy MPOL_LOCAL policy has been setup as a real policy, but it is still handled like a faked POL_PREFERRED policy with one internal MPOL_F_LOCAL flag bit set, and there are many places having to judge the real 'prefer' or the 'local' policy, which are quite confusing. In current code, there are 4 cases that MPOL_LOCAL are used: 1. user specifies 'local' policy 2. user specifies 'prefer' policy, but with empty nodemask 3. system 'default' policy is used 4. 'prefer' policy + valid 'preferred' node with MPOL_F_STATIC_NODES flag set, and when it is 'rebind' to a nodemask which doesn't contains the 'preferred' node, it will perform as 'local' policy So make 'local' a real policy instead of a fake 'prefer' one, and kill MPOL_F_LOCAL bit, which can greatly reduce the confusion for code reading. For case 4, the logic of mpol_rebind_preferred() is confusing, as Michal Hocko pointed out: : I do believe that rebinding preferred policy is just bogus and it should : be dropped altogether on the ground that a preference is a mere hint from : userspace where to start the allocation. Unless I am missing something : cpusets will be always authoritative for the final placement. The : preferred node just acts as a starting point and it should be really : preserved when cpusets changes. Otherwise we have a very subtle behavior : corner cases. So dump all the tricky transformation between 'prefer' and 'local', and just record the new nodemask of rebinding. [feng.tang@intel.com: fix a problem in mpol_set_nodemask(), per Michal Hocko] Link: https://lkml.kernel.org/r/1622560492-1294-3-git-send-email-feng.tang@intel.com [feng.tang@intel.com: refine code and comments of mpol_set_nodemask(), per Michal] Link: https://lkml.kernel.org/r/20210603081807.GE56979@shbuild999.sh.intel.com Link: https://lkml.kernel.org/r/1622469956-82897-3-git-send-email-feng.tang@intel.com Signed-off-by: Feng Tang Suggested-by: Michal Hocko Acked-by: Michal Hocko Cc: Andi Kleen Cc: Andrea Arcangeli Cc: Ben Widawsky Cc: Dan Williams Cc: Dave Hansen Cc: David Rientjes Cc: Huang Ying Cc: Mel Gorman Cc: Michal Hocko Cc: Mike Kravetz Cc: Randy Dunlap Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/uapi/linux/mempolicy.h | 1 - mm/mempolicy.c | 136 +++++++++++++++++------------------------ 2 files changed, 56 insertions(+), 81 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/mempolicy.h b/include/uapi/linux/mempolicy.h index 4832fd0b5642..19a00bc7fe86 100644 --- a/include/uapi/linux/mempolicy.h +++ b/include/uapi/linux/mempolicy.h @@ -60,7 +60,6 @@ enum { * are never OR'ed into the mode in mempolicy API arguments. */ #define MPOL_F_SHARED (1 << 0) /* identify shared policies */ -#define MPOL_F_LOCAL (1 << 1) /* preferred local allocation */ #define MPOL_F_MOF (1 << 3) /* this policy wants migrate on fault */ #define MPOL_F_MORON (1 << 4) /* Migrate On protnone Reference On Node */ diff --git a/mm/mempolicy.c b/mm/mempolicy.c index bd213b900e71..22addae6c4ee 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -121,8 +121,7 @@ enum zone_type policy_zone = 0; */ static struct mempolicy default_policy = { .refcnt = ATOMIC_INIT(1), /* never free it */ - .mode = MPOL_PREFERRED, - .flags = MPOL_F_LOCAL, + .mode = MPOL_LOCAL, }; static struct mempolicy preferred_node_policy[MAX_NUMNODES]; @@ -200,12 +199,9 @@ static int mpol_new_interleave(struct mempolicy *pol, const nodemask_t *nodes) static int mpol_new_preferred(struct mempolicy *pol, const nodemask_t *nodes) { - if (!nodes) - pol->flags |= MPOL_F_LOCAL; /* local allocation */ - else if (nodes_empty(*nodes)) - return -EINVAL; /* no allowed nodes */ - else - pol->v.preferred_node = first_node(*nodes); + if (nodes_empty(*nodes)) + return -EINVAL; + pol->v.preferred_node = first_node(*nodes); return 0; } @@ -220,8 +216,7 @@ static int mpol_new_bind(struct mempolicy *pol, const nodemask_t *nodes) /* * mpol_set_nodemask is called after mpol_new() to set up the nodemask, if * any, for the new policy. mpol_new() has already validated the nodes - * parameter with respect to the policy mode and flags. But, we need to - * handle an empty nodemask with MPOL_PREFERRED here. + * parameter with respect to the policy mode and flags. * * Must be called holding task's alloc_lock to protect task's mems_allowed * and mempolicy. May also be called holding the mmap_lock for write. @@ -231,33 +226,31 @@ static int mpol_set_nodemask(struct mempolicy *pol, { int ret; - /* if mode is MPOL_DEFAULT, pol is NULL. This is right. */ - if (pol == NULL) + /* + * Default (pol==NULL) resp. local memory policies are not a + * subject of any remapping. They also do not need any special + * constructor. + */ + if (!pol || pol->mode == MPOL_LOCAL) return 0; + /* Check N_MEMORY */ nodes_and(nsc->mask1, cpuset_current_mems_allowed, node_states[N_MEMORY]); VM_BUG_ON(!nodes); - if (pol->mode == MPOL_PREFERRED && nodes_empty(*nodes)) - nodes = NULL; /* explicit local allocation */ - else { - if (pol->flags & MPOL_F_RELATIVE_NODES) - mpol_relative_nodemask(&nsc->mask2, nodes, &nsc->mask1); - else - nodes_and(nsc->mask2, *nodes, nsc->mask1); - if (mpol_store_user_nodemask(pol)) - pol->w.user_nodemask = *nodes; - else - pol->w.cpuset_mems_allowed = - cpuset_current_mems_allowed; - } + if (pol->flags & MPOL_F_RELATIVE_NODES) + mpol_relative_nodemask(&nsc->mask2, nodes, &nsc->mask1); + else + nodes_and(nsc->mask2, *nodes, nsc->mask1); - if (nodes) - ret = mpol_ops[pol->mode].create(pol, &nsc->mask2); + if (mpol_store_user_nodemask(pol)) + pol->w.user_nodemask = *nodes; else - ret = mpol_ops[pol->mode].create(pol, NULL); + pol->w.cpuset_mems_allowed = cpuset_current_mems_allowed; + + ret = mpol_ops[pol->mode].create(pol, &nsc->mask2); return ret; } @@ -290,13 +283,14 @@ static struct mempolicy *mpol_new(unsigned short mode, unsigned short flags, if (((flags & MPOL_F_STATIC_NODES) || (flags & MPOL_F_RELATIVE_NODES))) return ERR_PTR(-EINVAL); + + mode = MPOL_LOCAL; } } else if (mode == MPOL_LOCAL) { if (!nodes_empty(*nodes) || (flags & MPOL_F_STATIC_NODES) || (flags & MPOL_F_RELATIVE_NODES)) return ERR_PTR(-EINVAL); - mode = MPOL_PREFERRED; } else if (nodes_empty(*nodes)) return ERR_PTR(-EINVAL); policy = kmem_cache_alloc(policy_cache, GFP_KERNEL); @@ -344,25 +338,7 @@ static void mpol_rebind_nodemask(struct mempolicy *pol, const nodemask_t *nodes) static void mpol_rebind_preferred(struct mempolicy *pol, const nodemask_t *nodes) { - nodemask_t tmp; - - if (pol->flags & MPOL_F_STATIC_NODES) { - int node = first_node(pol->w.user_nodemask); - - if (node_isset(node, *nodes)) { - pol->v.preferred_node = node; - pol->flags &= ~MPOL_F_LOCAL; - } else - pol->flags |= MPOL_F_LOCAL; - } else if (pol->flags & MPOL_F_RELATIVE_NODES) { - mpol_relative_nodemask(&tmp, &pol->w.user_nodemask, nodes); - pol->v.preferred_node = first_node(tmp); - } else if (!(pol->flags & MPOL_F_LOCAL)) { - pol->v.preferred_node = node_remap(pol->v.preferred_node, - pol->w.cpuset_mems_allowed, - *nodes); - pol->w.cpuset_mems_allowed = *nodes; - } + pol->w.cpuset_mems_allowed = *nodes; } /* @@ -376,7 +352,7 @@ static void mpol_rebind_policy(struct mempolicy *pol, const nodemask_t *newmask) { if (!pol) return; - if (!mpol_store_user_nodemask(pol) && !(pol->flags & MPOL_F_LOCAL) && + if (!mpol_store_user_nodemask(pol) && nodes_equal(pol->w.cpuset_mems_allowed, *newmask)) return; @@ -427,6 +403,9 @@ static const struct mempolicy_operations mpol_ops[MPOL_MAX] = { .create = mpol_new_bind, .rebind = mpol_rebind_nodemask, }, + [MPOL_LOCAL] = { + .rebind = mpol_rebind_default, + }, }; static int migrate_page_add(struct page *page, struct list_head *pagelist, @@ -919,10 +898,12 @@ static void get_policy_nodemask(struct mempolicy *p, nodemask_t *nodes) case MPOL_INTERLEAVE: *nodes = p->v.nodes; break; + case MPOL_LOCAL: + /* return empty node mask for local allocation */ + break; + case MPOL_PREFERRED: - if (!(p->flags & MPOL_F_LOCAL)) - node_set(p->v.preferred_node, *nodes); - /* else return empty node mask for local allocation */ + node_set(p->v.preferred_node, *nodes); break; default: BUG(); @@ -1894,9 +1875,9 @@ nodemask_t *policy_nodemask(gfp_t gfp, struct mempolicy *policy) /* Return the node id preferred by the given mempolicy, or the given id */ static int policy_node(gfp_t gfp, struct mempolicy *policy, int nd) { - if (policy->mode == MPOL_PREFERRED && !(policy->flags & MPOL_F_LOCAL)) + if (policy->mode == MPOL_PREFERRED) { nd = policy->v.preferred_node; - else { + } else { /* * __GFP_THISNODE shouldn't even be used with the bind policy * because we might easily break the expectation to stay on the @@ -1933,14 +1914,11 @@ unsigned int mempolicy_slab_node(void) return node; policy = current->mempolicy; - if (!policy || policy->flags & MPOL_F_LOCAL) + if (!policy) return node; switch (policy->mode) { case MPOL_PREFERRED: - /* - * handled MPOL_F_LOCAL above - */ return policy->v.preferred_node; case MPOL_INTERLEAVE: @@ -1960,6 +1938,8 @@ unsigned int mempolicy_slab_node(void) &policy->v.nodes); return z->zone ? zone_to_nid(z->zone) : node; } + case MPOL_LOCAL: + return node; default: BUG(); @@ -2072,16 +2052,18 @@ bool init_nodemask_of_mempolicy(nodemask_t *mask) mempolicy = current->mempolicy; switch (mempolicy->mode) { case MPOL_PREFERRED: - if (mempolicy->flags & MPOL_F_LOCAL) - nid = numa_node_id(); - else - nid = mempolicy->v.preferred_node; + nid = mempolicy->v.preferred_node; init_nodemask_of_node(mask, nid); break; case MPOL_BIND: case MPOL_INTERLEAVE: - *mask = mempolicy->v.nodes; + *mask = mempolicy->v.nodes; + break; + + case MPOL_LOCAL: + nid = numa_node_id(); + init_nodemask_of_node(mask, nid); break; default: @@ -2188,7 +2170,7 @@ struct page *alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma, * If the policy is interleave, or does not allow the current * node in its nodemask, we allocate the standard way. */ - if (pol->mode == MPOL_PREFERRED && !(pol->flags & MPOL_F_LOCAL)) + if (pol->mode == MPOL_PREFERRED) hpage_node = pol->v.preferred_node; nmask = policy_nodemask(gfp, pol); @@ -2324,10 +2306,9 @@ bool __mpol_equal(struct mempolicy *a, struct mempolicy *b) case MPOL_INTERLEAVE: return !!nodes_equal(a->v.nodes, b->v.nodes); case MPOL_PREFERRED: - /* a's ->flags is the same as b's */ - if (a->flags & MPOL_F_LOCAL) - return true; return a->v.preferred_node == b->v.preferred_node; + case MPOL_LOCAL: + return true; default: BUG(); return false; @@ -2465,10 +2446,11 @@ int mpol_misplaced(struct page *page, struct vm_area_struct *vma, unsigned long break; case MPOL_PREFERRED: - if (pol->flags & MPOL_F_LOCAL) - polnid = numa_node_id(); - else - polnid = pol->v.preferred_node; + polnid = pol->v.preferred_node; + break; + + case MPOL_LOCAL: + polnid = numa_node_id(); break; case MPOL_BIND: @@ -2835,9 +2817,6 @@ void numa_default_policy(void) * Parse and format mempolicy from/to strings */ -/* - * "local" is implemented internally by MPOL_PREFERRED with MPOL_F_LOCAL flag. - */ static const char * const policy_modes[] = { [MPOL_DEFAULT] = "default", @@ -2915,7 +2894,6 @@ int mpol_parse_str(char *str, struct mempolicy **mpol) */ if (nodelist) goto out; - mode = MPOL_PREFERRED; break; case MPOL_DEFAULT: /* @@ -2959,7 +2937,7 @@ int mpol_parse_str(char *str, struct mempolicy **mpol) else if (nodelist) new->v.preferred_node = first_node(nodes); else - new->flags |= MPOL_F_LOCAL; + new->mode = MPOL_LOCAL; /* * Save nodes for contextualization: this will be used to "clone" @@ -3005,12 +2983,10 @@ void mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol) switch (mode) { case MPOL_DEFAULT: + case MPOL_LOCAL: break; case MPOL_PREFERRED: - if (flags & MPOL_F_LOCAL) - mode = MPOL_LOCAL; - else - node_set(pol->v.preferred_node, nodes); + node_set(pol->v.preferred_node, nodes); break; case MPOL_BIND: case MPOL_INTERLEAVE: -- cgit v1.2.3-59-g8ed1b From 4ca9b3859dac14bbef0c27d00667bb5b10917adb Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Wed, 30 Jun 2021 18:52:28 -0700 Subject: mm/madvise: introduce MADV_POPULATE_(READ|WRITE) to prefault page tables I. Background: Sparse Memory Mappings When we manage sparse memory mappings dynamically in user space - also sometimes involving MAP_NORESERVE - we want to dynamically populate/ discard memory inside such a sparse memory region. Example users are hypervisors (especially implementing memory ballooning or similar technologies like virtio-mem) and memory allocators. In addition, we want to fail in a nice way (instead of generating SIGBUS) if populating does not succeed because we are out of backend memory (which can happen easily with file-based mappings, especially tmpfs and hugetlbfs). While MADV_DONTNEED, MADV_REMOVE and FALLOC_FL_PUNCH_HOLE allow for reliably discarding memory for most mapping types, there is no generic approach to populate page tables and preallocate memory. Although mmap() supports MAP_POPULATE, it is not applicable to the concept of sparse memory mappings, where we want to populate/discard dynamically and avoid expensive/problematic remappings. In addition, we never actually report errors during the final populate phase - it is best-effort only. fallocate() can be used to preallocate file-based memory and fail in a safe way. However, it cannot really be used for any private mappings on anonymous files via memfd due to COW semantics. In addition, fallocate() does not actually populate page tables, so we still always get pagefaults on first access - which is sometimes undesired (i.e., real-time workloads) and requires real prefaulting of page tables, not just a preallocation of backend storage. There might be interesting use cases for sparse memory regions along with mlockall(MCL_ONFAULT) which fallocate() cannot satisfy as it does not prefault page tables. II. On preallcoation/prefaulting from user space Because we don't have a proper interface, what applications (like QEMU and databases) end up doing is touching (i.e., reading+writing one byte to not overwrite existing data) all individual pages. However, that approach 1) Can result in wear on storage backing, because we end up reading/writing each page; this is especially a problem for dax/pmem. 2) Can result in mmap_sem contention when prefaulting via multiple threads. 3) Requires expensive signal handling, especially to catch SIGBUS in case of hugetlbfs/shmem/file-backed memory. For example, this is problematic in hypervisors like QEMU where SIGBUS handlers might already be used by other subsystems concurrently to e.g, handle hardware errors. "Simply" doing preallocation concurrently from other thread is not that easy. III. On MADV_WILLNEED Extending MADV_WILLNEED is not an option because 1. It would change the semantics: "Expect access in the near future." and "might be a good idea to read some pages" vs. "Definitely populate/ preallocate all memory and definitely fail on errors.". 2. Existing users (like virtio-balloon in QEMU when deflating the balloon) don't want populate/prealloc semantics. They treat this rather as a hint to give a little performance boost without too much overhead - and don't expect that a lot of memory might get consumed or a lot of time might be spent. IV. MADV_POPULATE_READ and MADV_POPULATE_WRITE Let's introduce MADV_POPULATE_READ and MADV_POPULATE_WRITE, inspired by MAP_POPULATE, with the following semantics: 1. MADV_POPULATE_READ can be used to prefault page tables just like manually reading each individual page. This will not break any COW mappings. The shared zero page might get mapped and no backend storage might get preallocated -- allocation might be deferred to write-fault time. Especially shared file mappings require an explicit fallocate() upfront to actually preallocate backend memory (blocks in the file system) in case the file might have holes. 2. If MADV_POPULATE_READ succeeds, all page tables have been populated (prefaulted) readable once. 3. MADV_POPULATE_WRITE can be used to preallocate backend memory and prefault page tables just like manually writing (or reading+writing) each individual page. This will break any COW mappings -- e.g., the shared zeropage is never populated. 4. If MADV_POPULATE_WRITE succeeds, all page tables have been populated (prefaulted) writable once. 5. MADV_POPULATE_READ and MADV_POPULATE_WRITE cannot be applied to special mappings marked with VM_PFNMAP and VM_IO. Also, proper access permissions (e.g., PROT_READ, PROT_WRITE) are required. If any such mapping is encountered, madvise() fails with -EINVAL. 6. If MADV_POPULATE_READ or MADV_POPULATE_WRITE fails, some page tables might have been populated. 7. MADV_POPULATE_READ and MADV_POPULATE_WRITE will return -EHWPOISON when encountering a HW poisoned page in the range. 8. Similar to MAP_POPULATE, MADV_POPULATE_READ and MADV_POPULATE_WRITE cannot protect from the OOM (Out Of Memory) handler killing the process. While the use case for MADV_POPULATE_WRITE is fairly obvious (i.e., preallocate memory and prefault page tables for VMs), one issue is that whenever we prefault pages writable, the pages have to be marked dirty, because the CPU could dirty them any time. while not a real problem for hugetlbfs or dax/pmem, it can be a problem for shared file mappings: each page will be marked dirty and has to be written back later when evicting. MADV_POPULATE_READ allows for optimizing this scenario: Pre-read a whole mapping from backend storage without marking it dirty, such that eviction won't have to write it back. As discussed above, shared file mappings might require an explciit fallocate() upfront to achieve preallcoation+prepopulation. Although sparse memory mappings are the primary use case, this will also be useful for other preallocate/prefault use cases where MAP_POPULATE is not desired or the semantics of MAP_POPULATE are not sufficient: as one example, QEMU users can trigger preallocation/prefaulting of guest RAM after the mapping was created -- and don't want errors to be silently suppressed. Looking at the history, MADV_POPULATE was already proposed in 2013 [1], however, the main motivation back than was performance improvements -- which should also still be the case. V. Single-threaded performance comparison I did a short experiment, prefaulting page tables on completely *empty mappings/files* and repeated the experiment 10 times. The results correspond to the shortest execution time. In general, the performance benefit for huge pages is negligible with small mappings. V.1: Private mappings POPULATE_READ and POPULATE_WRITE is fastest. Note that Reading/POPULATE_READ will populate the shared zeropage where applicable -- which result in short population times. The fastest way to allocate backend storage (here: swap or huge pages) and prefault page tables is POPULATE_WRITE. V.2: Shared mappings fallocate() is fastest, however, doesn't prefault page tables. POPULATE_WRITE is faster than simple writes and read/writes. POPULATE_READ is faster than simple reads. Without a fd, the fastest way to allocate backend storage and prefault page tables is POPULATE_WRITE. With an fd, the fastest way is usually FALLOCATE+POPULATE_READ or FALLOCATE+POPULATE_WRITE respectively; one exception are actual files: FALLOCATE+Read is slightly faster than FALLOCATE+POPULATE_READ. The fastest way to allocate backend storage prefault page tables is FALLOCATE+POPULATE_WRITE -- except when dealing with actual files; then, FALLOCATE+POPULATE_READ is fastest and won't directly mark all pages as dirty. v.3: Detailed results ================================================== 2 MiB MAP_PRIVATE: ************************************************** Anon 4 KiB : Read : 0.119 ms Anon 4 KiB : Write : 0.222 ms Anon 4 KiB : Read/Write : 0.380 ms Anon 4 KiB : POPULATE_READ : 0.060 ms Anon 4 KiB : POPULATE_WRITE : 0.158 ms Memfd 4 KiB : Read : 0.034 ms Memfd 4 KiB : Write : 0.310 ms Memfd 4 KiB : Read/Write : 0.362 ms Memfd 4 KiB : POPULATE_READ : 0.039 ms Memfd 4 KiB : POPULATE_WRITE : 0.229 ms Memfd 2 MiB : Read : 0.030 ms Memfd 2 MiB : Write : 0.030 ms Memfd 2 MiB : Read/Write : 0.030 ms Memfd 2 MiB : POPULATE_READ : 0.030 ms Memfd 2 MiB : POPULATE_WRITE : 0.030 ms tmpfs : Read : 0.033 ms tmpfs : Write : 0.313 ms tmpfs : Read/Write : 0.406 ms tmpfs : POPULATE_READ : 0.039 ms tmpfs : POPULATE_WRITE : 0.285 ms file : Read : 0.033 ms file : Write : 0.351 ms file : Read/Write : 0.408 ms file : POPULATE_READ : 0.039 ms file : POPULATE_WRITE : 0.290 ms hugetlbfs : Read : 0.030 ms hugetlbfs : Write : 0.030 ms hugetlbfs : Read/Write : 0.030 ms hugetlbfs : POPULATE_READ : 0.030 ms hugetlbfs : POPULATE_WRITE : 0.030 ms ************************************************** 4096 MiB MAP_PRIVATE: ************************************************** Anon 4 KiB : Read : 237.940 ms Anon 4 KiB : Write : 708.409 ms Anon 4 KiB : Read/Write : 1054.041 ms Anon 4 KiB : POPULATE_READ : 124.310 ms Anon 4 KiB : POPULATE_WRITE : 572.582 ms Memfd 4 KiB : Read : 136.928 ms Memfd 4 KiB : Write : 963.898 ms Memfd 4 KiB : Read/Write : 1106.561 ms Memfd 4 KiB : POPULATE_READ : 78.450 ms Memfd 4 KiB : POPULATE_WRITE : 805.881 ms Memfd 2 MiB : Read : 357.116 ms Memfd 2 MiB : Write : 357.210 ms Memfd 2 MiB : Read/Write : 357.606 ms Memfd 2 MiB : POPULATE_READ : 356.094 ms Memfd 2 MiB : POPULATE_WRITE : 356.937 ms tmpfs : Read : 137.536 ms tmpfs : Write : 954.362 ms tmpfs : Read/Write : 1105.954 ms tmpfs : POPULATE_READ : 80.289 ms tmpfs : POPULATE_WRITE : 822.826 ms file : Read : 137.874 ms file : Write : 987.025 ms file : Read/Write : 1107.439 ms file : POPULATE_READ : 80.413 ms file : POPULATE_WRITE : 857.622 ms hugetlbfs : Read : 355.607 ms hugetlbfs : Write : 355.729 ms hugetlbfs : Read/Write : 356.127 ms hugetlbfs : POPULATE_READ : 354.585 ms hugetlbfs : POPULATE_WRITE : 355.138 ms ************************************************** 2 MiB MAP_SHARED: ************************************************** Anon 4 KiB : Read : 0.394 ms Anon 4 KiB : Write : 0.348 ms Anon 4 KiB : Read/Write : 0.400 ms Anon 4 KiB : POPULATE_READ : 0.326 ms Anon 4 KiB : POPULATE_WRITE : 0.273 ms Anon 2 MiB : Read : 0.030 ms Anon 2 MiB : Write : 0.030 ms Anon 2 MiB : Read/Write : 0.030 ms Anon 2 MiB : POPULATE_READ : 0.030 ms Anon 2 MiB : POPULATE_WRITE : 0.030 ms Memfd 4 KiB : Read : 0.412 ms Memfd 4 KiB : Write : 0.372 ms Memfd 4 KiB : Read/Write : 0.419 ms Memfd 4 KiB : POPULATE_READ : 0.343 ms Memfd 4 KiB : POPULATE_WRITE : 0.288 ms Memfd 4 KiB : FALLOCATE : 0.137 ms Memfd 4 KiB : FALLOCATE+Read : 0.446 ms Memfd 4 KiB : FALLOCATE+Write : 0.330 ms Memfd 4 KiB : FALLOCATE+Read/Write : 0.454 ms Memfd 4 KiB : FALLOCATE+POPULATE_READ : 0.379 ms Memfd 4 KiB : FALLOCATE+POPULATE_WRITE : 0.268 ms Memfd 2 MiB : Read : 0.030 ms Memfd 2 MiB : Write : 0.030 ms Memfd 2 MiB : Read/Write : 0.030 ms Memfd 2 MiB : POPULATE_READ : 0.030 ms Memfd 2 MiB : POPULATE_WRITE : 0.030 ms Memfd 2 MiB : FALLOCATE : 0.030 ms Memfd 2 MiB : FALLOCATE+Read : 0.031 ms Memfd 2 MiB : FALLOCATE+Write : 0.031 ms Memfd 2 MiB : FALLOCATE+Read/Write : 0.031 ms Memfd 2 MiB : FALLOCATE+POPULATE_READ : 0.030 ms Memfd 2 MiB : FALLOCATE+POPULATE_WRITE : 0.030 ms tmpfs : Read : 0.416 ms tmpfs : Write : 0.369 ms tmpfs : Read/Write : 0.425 ms tmpfs : POPULATE_READ : 0.346 ms tmpfs : POPULATE_WRITE : 0.295 ms tmpfs : FALLOCATE : 0.139 ms tmpfs : FALLOCATE+Read : 0.447 ms tmpfs : FALLOCATE+Write : 0.333 ms tmpfs : FALLOCATE+Read/Write : 0.454 ms tmpfs : FALLOCATE+POPULATE_READ : 0.380 ms tmpfs : FALLOCATE+POPULATE_WRITE : 0.272 ms file : Read : 0.191 ms file : Write : 0.511 ms file : Read/Write : 0.524 ms file : POPULATE_READ : 0.196 ms file : POPULATE_WRITE : 0.434 ms file : FALLOCATE : 0.004 ms file : FALLOCATE+Read : 0.197 ms file : FALLOCATE+Write : 0.554 ms file : FALLOCATE+Read/Write : 0.480 ms file : FALLOCATE+POPULATE_READ : 0.201 ms file : FALLOCATE+POPULATE_WRITE : 0.381 ms hugetlbfs : Read : 0.030 ms hugetlbfs : Write : 0.030 ms hugetlbfs : Read/Write : 0.030 ms hugetlbfs : POPULATE_READ : 0.030 ms hugetlbfs : POPULATE_WRITE : 0.030 ms hugetlbfs : FALLOCATE : 0.030 ms hugetlbfs : FALLOCATE+Read : 0.031 ms hugetlbfs : FALLOCATE+Write : 0.031 ms hugetlbfs : FALLOCATE+Read/Write : 0.030 ms hugetlbfs : FALLOCATE+POPULATE_READ : 0.030 ms hugetlbfs : FALLOCATE+POPULATE_WRITE : 0.030 ms ************************************************** 4096 MiB MAP_SHARED: ************************************************** Anon 4 KiB : Read : 1053.090 ms Anon 4 KiB : Write : 913.642 ms Anon 4 KiB : Read/Write : 1060.350 ms Anon 4 KiB : POPULATE_READ : 893.691 ms Anon 4 KiB : POPULATE_WRITE : 782.885 ms Anon 2 MiB : Read : 358.553 ms Anon 2 MiB : Write : 358.419 ms Anon 2 MiB : Read/Write : 357.992 ms Anon 2 MiB : POPULATE_READ : 357.533 ms Anon 2 MiB : POPULATE_WRITE : 357.808 ms Memfd 4 KiB : Read : 1078.144 ms Memfd 4 KiB : Write : 942.036 ms Memfd 4 KiB : Read/Write : 1100.391 ms Memfd 4 KiB : POPULATE_READ : 925.829 ms Memfd 4 KiB : POPULATE_WRITE : 804.394 ms Memfd 4 KiB : FALLOCATE : 304.632 ms Memfd 4 KiB : FALLOCATE+Read : 1163.359 ms Memfd 4 KiB : FALLOCATE+Write : 933.186 ms Memfd 4 KiB : FALLOCATE+Read/Write : 1187.304 ms Memfd 4 KiB : FALLOCATE+POPULATE_READ : 1013.660 ms Memfd 4 KiB : FALLOCATE+POPULATE_WRITE : 794.560 ms Memfd 2 MiB : Read : 358.131 ms Memfd 2 MiB : Write : 358.099 ms Memfd 2 MiB : Read/Write : 358.250 ms Memfd 2 MiB : POPULATE_READ : 357.563 ms Memfd 2 MiB : POPULATE_WRITE : 357.334 ms Memfd 2 MiB : FALLOCATE : 356.735 ms Memfd 2 MiB : FALLOCATE+Read : 358.152 ms Memfd 2 MiB : FALLOCATE+Write : 358.331 ms Memfd 2 MiB : FALLOCATE+Read/Write : 358.018 ms Memfd 2 MiB : FALLOCATE+POPULATE_READ : 357.286 ms Memfd 2 MiB : FALLOCATE+POPULATE_WRITE : 357.523 ms tmpfs : Read : 1087.265 ms tmpfs : Write : 950.840 ms tmpfs : Read/Write : 1107.567 ms tmpfs : POPULATE_READ : 922.605 ms tmpfs : POPULATE_WRITE : 810.094 ms tmpfs : FALLOCATE : 306.320 ms tmpfs : FALLOCATE+Read : 1169.796 ms tmpfs : FALLOCATE+Write : 933.730 ms tmpfs : FALLOCATE+Read/Write : 1191.610 ms tmpfs : FALLOCATE+POPULATE_READ : 1020.474 ms tmpfs : FALLOCATE+POPULATE_WRITE : 798.945 ms file : Read : 654.101 ms file : Write : 1259.142 ms file : Read/Write : 1289.509 ms file : POPULATE_READ : 661.642 ms file : POPULATE_WRITE : 1106.816 ms file : FALLOCATE : 1.864 ms file : FALLOCATE+Read : 656.328 ms file : FALLOCATE+Write : 1153.300 ms file : FALLOCATE+Read/Write : 1180.613 ms file : FALLOCATE+POPULATE_READ : 668.347 ms file : FALLOCATE+POPULATE_WRITE : 996.143 ms hugetlbfs : Read : 357.245 ms hugetlbfs : Write : 357.413 ms hugetlbfs : Read/Write : 357.120 ms hugetlbfs : POPULATE_READ : 356.321 ms hugetlbfs : POPULATE_WRITE : 356.693 ms hugetlbfs : FALLOCATE : 355.927 ms hugetlbfs : FALLOCATE+Read : 357.074 ms hugetlbfs : FALLOCATE+Write : 357.120 ms hugetlbfs : FALLOCATE+Read/Write : 356.983 ms hugetlbfs : FALLOCATE+POPULATE_READ : 356.413 ms hugetlbfs : FALLOCATE+POPULATE_WRITE : 356.266 ms ************************************************** [1] https://lkml.org/lkml/2013/6/27/698 [akpm@linux-foundation.org: coding style fixes] Link: https://lkml.kernel.org/r/20210419135443.12822-3-david@redhat.com Signed-off-by: David Hildenbrand Cc: Arnd Bergmann Cc: Michal Hocko Cc: Oscar Salvador Cc: Matthew Wilcox (Oracle) Cc: Andrea Arcangeli Cc: Minchan Kim Cc: Jann Horn Cc: Jason Gunthorpe Cc: Dave Hansen Cc: Hugh Dickins Cc: Rik van Riel Cc: Michael S. Tsirkin Cc: Kirill A. Shutemov Cc: Vlastimil Babka Cc: Richard Henderson Cc: Ivan Kokshaysky Cc: Matt Turner Cc: Thomas Bogendoerfer Cc: "James E.J. Bottomley" Cc: Helge Deller Cc: Chris Zankel Cc: Max Filippov Cc: Mike Kravetz Cc: Peter Xu Cc: Rolf Eike Beer Cc: Ram Pai Cc: Shuah Khan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/alpha/include/uapi/asm/mman.h | 3 ++ arch/mips/include/uapi/asm/mman.h | 3 ++ arch/parisc/include/uapi/asm/mman.h | 3 ++ arch/xtensa/include/uapi/asm/mman.h | 3 ++ include/uapi/asm-generic/mman-common.h | 3 ++ mm/gup.c | 58 ++++++++++++++++++++++++++++++ mm/internal.h | 3 ++ mm/madvise.c | 66 ++++++++++++++++++++++++++++++++++ 8 files changed, 142 insertions(+) (limited to 'include/uapi') diff --git a/arch/alpha/include/uapi/asm/mman.h b/arch/alpha/include/uapi/asm/mman.h index a18ec7f63888..56b4ee5a6c9e 100644 --- a/arch/alpha/include/uapi/asm/mman.h +++ b/arch/alpha/include/uapi/asm/mman.h @@ -71,6 +71,9 @@ #define MADV_COLD 20 /* deactivate these pages */ #define MADV_PAGEOUT 21 /* reclaim these pages */ +#define MADV_POPULATE_READ 22 /* populate (prefault) page tables readable */ +#define MADV_POPULATE_WRITE 23 /* populate (prefault) page tables writable */ + /* compatibility flags */ #define MAP_FILE 0 diff --git a/arch/mips/include/uapi/asm/mman.h b/arch/mips/include/uapi/asm/mman.h index 57dc2ac4f8bd..40b210c65a5a 100644 --- a/arch/mips/include/uapi/asm/mman.h +++ b/arch/mips/include/uapi/asm/mman.h @@ -98,6 +98,9 @@ #define MADV_COLD 20 /* deactivate these pages */ #define MADV_PAGEOUT 21 /* reclaim these pages */ +#define MADV_POPULATE_READ 22 /* populate (prefault) page tables readable */ +#define MADV_POPULATE_WRITE 23 /* populate (prefault) page tables writable */ + /* compatibility flags */ #define MAP_FILE 0 diff --git a/arch/parisc/include/uapi/asm/mman.h b/arch/parisc/include/uapi/asm/mman.h index ab78cba446ed..9e3c010c0f61 100644 --- a/arch/parisc/include/uapi/asm/mman.h +++ b/arch/parisc/include/uapi/asm/mman.h @@ -52,6 +52,9 @@ #define MADV_COLD 20 /* deactivate these pages */ #define MADV_PAGEOUT 21 /* reclaim these pages */ +#define MADV_POPULATE_READ 22 /* populate (prefault) page tables readable */ +#define MADV_POPULATE_WRITE 23 /* populate (prefault) page tables writable */ + #define MADV_MERGEABLE 65 /* KSM may merge identical pages */ #define MADV_UNMERGEABLE 66 /* KSM may not merge identical pages */ diff --git a/arch/xtensa/include/uapi/asm/mman.h b/arch/xtensa/include/uapi/asm/mman.h index e5e643752947..b3a22095371b 100644 --- a/arch/xtensa/include/uapi/asm/mman.h +++ b/arch/xtensa/include/uapi/asm/mman.h @@ -106,6 +106,9 @@ #define MADV_COLD 20 /* deactivate these pages */ #define MADV_PAGEOUT 21 /* reclaim these pages */ +#define MADV_POPULATE_READ 22 /* populate (prefault) page tables readable */ +#define MADV_POPULATE_WRITE 23 /* populate (prefault) page tables writable */ + /* compatibility flags */ #define MAP_FILE 0 diff --git a/include/uapi/asm-generic/mman-common.h b/include/uapi/asm-generic/mman-common.h index f94f65d429be..1567a3294c3d 100644 --- a/include/uapi/asm-generic/mman-common.h +++ b/include/uapi/asm-generic/mman-common.h @@ -72,6 +72,9 @@ #define MADV_COLD 20 /* deactivate these pages */ #define MADV_PAGEOUT 21 /* reclaim these pages */ +#define MADV_POPULATE_READ 22 /* populate (prefault) page tables readable */ +#define MADV_POPULATE_WRITE 23 /* populate (prefault) page tables writable */ + /* compatibility flags */ #define MAP_FILE 0 diff --git a/mm/gup.c b/mm/gup.c index 8651309f8ec3..728d996767cb 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -1500,6 +1500,64 @@ long populate_vma_page_range(struct vm_area_struct *vma, NULL, NULL, locked); } +/* + * faultin_vma_page_range() - populate (prefault) page tables inside the + * given VMA range readable/writable + * + * This takes care of mlocking the pages, too, if VM_LOCKED is set. + * + * @vma: target vma + * @start: start address + * @end: end address + * @write: whether to prefault readable or writable + * @locked: whether the mmap_lock is still held + * + * Returns either number of processed pages in the vma, or a negative error + * code on error (see __get_user_pages()). + * + * vma->vm_mm->mmap_lock must be held. The range must be page-aligned and + * covered by the VMA. + * + * If @locked is NULL, it may be held for read or write and will be unperturbed. + * + * If @locked is non-NULL, it must held for read only and may be released. If + * it's released, *@locked will be set to 0. + */ +long faultin_vma_page_range(struct vm_area_struct *vma, unsigned long start, + unsigned long end, bool write, int *locked) +{ + struct mm_struct *mm = vma->vm_mm; + unsigned long nr_pages = (end - start) / PAGE_SIZE; + int gup_flags; + + VM_BUG_ON(!PAGE_ALIGNED(start)); + VM_BUG_ON(!PAGE_ALIGNED(end)); + VM_BUG_ON_VMA(start < vma->vm_start, vma); + VM_BUG_ON_VMA(end > vma->vm_end, vma); + mmap_assert_locked(mm); + + /* + * FOLL_TOUCH: Mark page accessed and thereby young; will also mark + * the page dirty with FOLL_WRITE -- which doesn't make a + * difference with !FOLL_FORCE, because the page is writable + * in the page table. + * FOLL_HWPOISON: Return -EHWPOISON instead of -EFAULT when we hit + * a poisoned page. + * FOLL_POPULATE: Always populate memory with VM_LOCKONFAULT. + * !FOLL_FORCE: Require proper access permissions. + */ + gup_flags = FOLL_TOUCH | FOLL_POPULATE | FOLL_MLOCK | FOLL_HWPOISON; + if (write) + gup_flags |= FOLL_WRITE; + + /* + * See check_vma_flags(): Will return -EFAULT on incompatible mappings + * or with insufficient permissions. + */ + return __get_user_pages(mm, start, nr_pages, gup_flags, + NULL, NULL, locked); +} + /* * __mm_populate - populate and/or mlock pages within a range of address space. * diff --git a/mm/internal.h b/mm/internal.h index d9c2b33cd2ab..f38bc5d75ab7 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -345,6 +345,9 @@ void __vma_unlink_list(struct mm_struct *mm, struct vm_area_struct *vma); #ifdef CONFIG_MMU extern long populate_vma_page_range(struct vm_area_struct *vma, unsigned long start, unsigned long end, int *locked); +extern long faultin_vma_page_range(struct vm_area_struct *vma, + unsigned long start, unsigned long end, + bool write, int *locked); extern void munlock_vma_pages_range(struct vm_area_struct *vma, unsigned long start, unsigned long end); static inline void munlock_vma_pages_all(struct vm_area_struct *vma) diff --git a/mm/madvise.c b/mm/madvise.c index 63e489e5bfdb..6d3d348b17f4 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -53,6 +53,8 @@ static int madvise_need_mmap_write(int behavior) case MADV_COLD: case MADV_PAGEOUT: case MADV_FREE: + case MADV_POPULATE_READ: + case MADV_POPULATE_WRITE: return 0; default: /* be safe, default to 1. list exceptions explicitly */ @@ -822,6 +824,61 @@ static long madvise_dontneed_free(struct vm_area_struct *vma, return -EINVAL; } +static long madvise_populate(struct vm_area_struct *vma, + struct vm_area_struct **prev, + unsigned long start, unsigned long end, + int behavior) +{ + const bool write = behavior == MADV_POPULATE_WRITE; + struct mm_struct *mm = vma->vm_mm; + unsigned long tmp_end; + int locked = 1; + long pages; + + *prev = vma; + + while (start < end) { + /* + * We might have temporarily dropped the lock. For example, + * our VMA might have been split. + */ + if (!vma || start >= vma->vm_end) { + vma = find_vma(mm, start); + if (!vma || start < vma->vm_start) + return -ENOMEM; + } + + tmp_end = min_t(unsigned long, end, vma->vm_end); + /* Populate (prefault) page tables readable/writable. */ + pages = faultin_vma_page_range(vma, start, tmp_end, write, + &locked); + if (!locked) { + mmap_read_lock(mm); + locked = 1; + *prev = NULL; + vma = NULL; + } + if (pages < 0) { + switch (pages) { + case -EINTR: + return -EINTR; + case -EFAULT: /* Incompatible mappings / permissions. */ + return -EINVAL; + case -EHWPOISON: + return -EHWPOISON; + default: + pr_warn_once("%s: unhandled return value: %ld\n", + __func__, pages); + fallthrough; + case -ENOMEM: + return -ENOMEM; + } + } + start += pages * PAGE_SIZE; + } + return 0; +} + /* * Application wants to free up the pages and associated backing store. * This is effectively punching a hole into the middle of a file. @@ -935,6 +992,9 @@ madvise_vma(struct vm_area_struct *vma, struct vm_area_struct **prev, case MADV_FREE: case MADV_DONTNEED: return madvise_dontneed_free(vma, prev, start, end, behavior); + case MADV_POPULATE_READ: + case MADV_POPULATE_WRITE: + return madvise_populate(vma, prev, start, end, behavior); default: return madvise_behavior(vma, prev, start, end, behavior); } @@ -955,6 +1015,8 @@ madvise_behavior_valid(int behavior) case MADV_FREE: case MADV_COLD: case MADV_PAGEOUT: + case MADV_POPULATE_READ: + case MADV_POPULATE_WRITE: #ifdef CONFIG_KSM case MADV_MERGEABLE: case MADV_UNMERGEABLE: @@ -1042,6 +1104,10 @@ process_madvise_behavior_valid(int behavior) * easily if memory pressure happens. * MADV_PAGEOUT - the application is not expected to use this memory soon, * page out the pages in this range immediately. + * MADV_POPULATE_READ - populate (prefault) page tables readable by + * triggering read faults if required + * MADV_POPULATE_WRITE - populate (prefault) page tables writable by + * triggering write faults if required * * return values: * zero - success -- cgit v1.2.3-59-g8ed1b