Augements hugetlb_cgroup_charge_cgroup to be able to charge hugetlb usage or hugetlb reservation counter.

Adds a new interface to uncharge a hugetlb_cgroup counter via hugetlb_cgroup_uncharge_counter.

Integrates the counter with hugetlb_cgroup, via hugetlb_cgroup_init, hugetlb_cgroup_have_usage, and hugetlb_cgroup_css_offline.

Signed-off-by: Mina Almasry almasrymina@google.com --- include/linux/hugetlb_cgroup.h | 13 ++++-- mm/hugetlb.c | 6 ++- mm/hugetlb_cgroup.c | 82 +++++++++++++++++++++++++++------- 3 files changed, 80 insertions(+), 21 deletions(-)

diff --git a/include/linux/hugetlb_cgroup.h b/include/linux/hugetlb_cgroup.h index 063962f6dfc6a..c467715dd8fb8 100644 --- a/include/linux/hugetlb_cgroup.h +++ b/include/linux/hugetlb_cgroup.h @@ -52,14 +52,19 @@ static inline bool hugetlb_cgroup_disabled(void) }

extern int hugetlb_cgroup_charge_cgroup(int idx, unsigned long nr_pages, - struct hugetlb_cgroup **ptr); + struct hugetlb_cgroup **ptr, + bool reserved); extern void hugetlb_cgroup_commit_charge(int idx, unsigned long nr_pages, struct hugetlb_cgroup *h_cg, struct page *page); extern void hugetlb_cgroup_uncharge_page(int idx, unsigned long nr_pages, struct page *page); extern void hugetlb_cgroup_uncharge_cgroup(int idx, unsigned long nr_pages, - struct hugetlb_cgroup *h_cg); + struct hugetlb_cgroup *h_cg, + bool reserved); +extern void hugetlb_cgroup_uncharge_counter(struct page_counter *p, + unsigned long nr_pages); + extern void hugetlb_cgroup_file_init(void) __init; extern void hugetlb_cgroup_migrate(struct page *oldhpage, struct page *newhpage); @@ -83,7 +88,7 @@ static inline bool hugetlb_cgroup_disabled(void)

static inline int hugetlb_cgroup_charge_cgroup(int idx, unsigned long nr_pages, - struct hugetlb_cgroup **ptr) + struct hugetlb_cgroup **ptr, bool reserved) { return 0; } @@ -102,7 +107,7 @@ hugetlb_cgroup_uncharge_page(int idx, unsigned long nr_pages, struct page *page)

static inline void hugetlb_cgroup_uncharge_cgroup(int idx, unsigned long nr_pages, - struct hugetlb_cgroup *h_cg) + struct hugetlb_cgroup *h_cg, bool reserved) { }

diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 6d7296dd11b83..e975f55aede94 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -2078,7 +2078,8 @@ struct page *alloc_huge_page(struct vm_area_struct *vma, gbl_chg = 1; }

- ret = hugetlb_cgroup_charge_cgroup(idx, pages_per_huge_page(h), &h_cg); + ret = hugetlb_cgroup_charge_cgroup(idx, pages_per_huge_page(h), &h_cg, + false); if (ret) goto out_subpool_put;

@@ -2126,7 +2127,8 @@ struct page *alloc_huge_page(struct vm_area_struct *vma, return page;

out_uncharge_cgroup: - hugetlb_cgroup_uncharge_cgroup(idx, pages_per_huge_page(h), h_cg); + hugetlb_cgroup_uncharge_cgroup(idx, pages_per_huge_page(h), h_cg, + false); out_subpool_put: if (map_chg || avoid_reserve) hugepage_subpool_put_pages(spool, 1); diff --git a/mm/hugetlb_cgroup.c b/mm/hugetlb_cgroup.c index 51a72624bd1ff..2ab36a98d834e 100644 --- a/mm/hugetlb_cgroup.c +++ b/mm/hugetlb_cgroup.c @@ -38,8 +38,8 @@ struct hugetlb_cgroup { static struct hugetlb_cgroup *root_h_cgroup __read_mostly;

static inline -struct page_counter *hugetlb_cgroup_get_counter(struct hugetlb_cgroup *h_cg, int idx, - bool reserved) +struct page_counter *hugetlb_cgroup_get_counter(struct hugetlb_cgroup *h_cg, + int idx, bool reserved) { if (reserved) return &h_cg->reserved_hugepage[idx]; @@ -74,8 +74,12 @@ static inline bool hugetlb_cgroup_have_usage(struct hugetlb_cgroup *h_cg) int idx;

for (idx = 0; idx < hugetlb_max_hstate; idx++) { - if (page_counter_read(&h_cg->hugepage[idx])) + if (page_counter_read(hugetlb_cgroup_get_counter(h_cg, idx, + true)) || + page_counter_read(hugetlb_cgroup_get_counter(h_cg, idx, + false))) { return true; + } } return false; } @@ -86,18 +90,30 @@ static void hugetlb_cgroup_init(struct hugetlb_cgroup *h_cgroup, int idx;

for (idx = 0; idx < HUGE_MAX_HSTATE; idx++) { - struct page_counter *counter = &h_cgroup->hugepage[idx]; struct page_counter *parent = NULL; + struct page_counter *reserved_parent = NULL; unsigned long limit; int ret;

- if (parent_h_cgroup) - parent = &parent_h_cgroup->hugepage[idx]; - page_counter_init(counter, parent); + if (parent_h_cgroup) { + parent = hugetlb_cgroup_get_counter( + parent_h_cgroup, idx, false); + reserved_parent = hugetlb_cgroup_get_counter( + parent_h_cgroup, idx, true); + } + page_counter_init(hugetlb_cgroup_get_counter( + h_cgroup, idx, false), parent); + page_counter_init(hugetlb_cgroup_get_counter( + h_cgroup, idx, true), + reserved_parent);

limit = round_down(PAGE_COUNTER_MAX, 1 << huge_page_order(&hstates[idx])); - ret = page_counter_set_max(counter, limit); + + ret = page_counter_set_max(hugetlb_cgroup_get_counter( + h_cgroup, idx, false), limit); + ret = page_counter_set_max(hugetlb_cgroup_get_counter( + h_cgroup, idx, true), limit); VM_BUG_ON(ret); } } @@ -127,6 +143,26 @@ static void hugetlb_cgroup_css_free(struct cgroup_subsys_state *css) kfree(h_cgroup); }

+static void hugetlb_cgroup_move_parent_reservation(int idx, + struct hugetlb_cgroup *h_cg) +{ + struct hugetlb_cgroup *parent = parent_hugetlb_cgroup(h_cg); + + /* Move the reservation counters. */ + if (!parent_hugetlb_cgroup(h_cg)) { + parent = root_h_cgroup; + /* root has no limit */ + page_counter_charge( + &root_h_cgroup->reserved_hugepage[idx], + page_counter_read(hugetlb_cgroup_get_counter( + h_cg, idx, true))); + } + + /* Take the pages off the local counter */ + page_counter_cancel(hugetlb_cgroup_get_counter(h_cg, idx, true), + page_counter_read(hugetlb_cgroup_get_counter(h_cg, + idx, true))); +}

/* * Should be called with hugetlb_lock held. @@ -181,6 +217,7 @@ static void hugetlb_cgroup_css_offline(struct cgroup_subsys_state *css) do { for_each_hstate(h) { spin_lock(&hugetlb_lock); + hugetlb_cgroup_move_parent_reservation(idx, h_cg); list_for_each_entry(page, &h->hugepage_activelist, lru) hugetlb_cgroup_move_parent(idx, h_cg, page);

@@ -192,7 +229,7 @@ static void hugetlb_cgroup_css_offline(struct cgroup_subsys_state *css) }

int hugetlb_cgroup_charge_cgroup(int idx, unsigned long nr_pages, - struct hugetlb_cgroup **ptr) + struct hugetlb_cgroup **ptr, bool reserved) { int ret = 0; struct page_counter *counter; @@ -215,8 +252,11 @@ int hugetlb_cgroup_charge_cgroup(int idx, unsigned long nr_pages, } rcu_read_unlock();

- if (!page_counter_try_charge(&h_cg->hugepage[idx], nr_pages, &counter)) + if (!page_counter_try_charge(hugetlb_cgroup_get_counter(h_cg, idx, + reserved), + nr_pages, &counter)) { ret = -ENOMEM; + } css_put(&h_cg->css); done: *ptr = h_cg; @@ -250,12 +290,14 @@ void hugetlb_cgroup_uncharge_page(int idx, unsigned long nr_pages, if (unlikely(!h_cg)) return; set_hugetlb_cgroup(page, NULL); - page_counter_uncharge(&h_cg->hugepage[idx], nr_pages); + page_counter_uncharge(hugetlb_cgroup_get_counter(h_cg, idx, false), + nr_pages); + return; }

void hugetlb_cgroup_uncharge_cgroup(int idx, unsigned long nr_pages, - struct hugetlb_cgroup *h_cg) + struct hugetlb_cgroup *h_cg, bool reserved) { if (hugetlb_cgroup_disabled() || !h_cg) return; @@ -263,8 +305,17 @@ void hugetlb_cgroup_uncharge_cgroup(int idx, unsigned long nr_pages, if (huge_page_order(&hstates[idx]) < HUGETLB_CGROUP_MIN_ORDER) return;

- page_counter_uncharge(&h_cg->hugepage[idx], nr_pages); - return; + page_counter_uncharge(hugetlb_cgroup_get_counter(h_cg, idx, reserved), + nr_pages); +} + +void hugetlb_cgroup_uncharge_counter(struct page_counter *p, + unsigned long nr_pages) +{ + if (hugetlb_cgroup_disabled() || !p) + return; + + page_counter_uncharge(p, nr_pages); }

static u64 hugetlb_cgroup_read_u64(struct cgroup_subsys_state *css, @@ -326,7 +377,8 @@ static ssize_t hugetlb_cgroup_write(struct kernfs_open_file *of, /* Fall through. */ case HUGETLB_RES_LIMIT: mutex_lock(&hugetlb_limit_mutex); - ret = page_counter_set_max(hugetlb_cgroup_get_counter(h_cg, idx, reserved), + ret = page_counter_set_max(hugetlb_cgroup_get_counter(h_cg, idx, + reserved), nr_pages); mutex_unlock(&hugetlb_limit_mutex); break; -- 2.23.0.162.g0b9fbb3734-goog

Current behavior is that region_chg provides both a cache entry in resv->region_cache, AND a placeholder entry in resv->regions. region_add first tries to use the placeholder, and if it finds that the placeholder has been deleted by a racing region_del call, it uses the cache entry.

This behavior is completely unnecessary and is removed in this patch for a couple of reasons:

1. region_add needs to either find a cached file_region entry in resv->region_cache, or find an entry in resv->regions to expand. It does not need both. 2. region_chg adding a placeholder entry in resv->regions opens up a possible race with region_del, where region_chg adds a placeholder region in resv->regions, and this region is deleted by a racing call to region_del during region_chg execution or before region_add is called. Removing the race makes the code easier to reason about and maintain.

In addition, a follow up patch in this series disables region coalescing, which would be further complicated if the race with region_del exists.

Signed-off-by: Mina Almasry almasrymina@google.com --- mm/hugetlb.c | 63 +++++++++------------------------------------------- 1 file changed, 11 insertions(+), 52 deletions(-)

diff --git a/mm/hugetlb.c b/mm/hugetlb.c index fbd7c52e17348..bea51ae422f63 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -246,14 +246,10 @@ struct file_region {

/* * Add the huge page range represented by [f, t) to the reserve - * map. In the normal case, existing regions will be expanded - * to accommodate the specified range. Sufficient regions should - * exist for expansion due to the previous call to region_chg - * with the same range. However, it is possible that region_del - * could have been called after region_chg and modifed the map - * in such a way that no region exists to be expanded. In this - * case, pull a region descriptor from the cache associated with - * the map and use that for the new range. + * map. Existing regions will be expanded to accommodate the specified + * range, or a region will be taken from the cache. Sufficient regions + * must exist in the cache due to the previous call to region_chg with + * the same range. * * Return the number of new huge pages added to the map. This * number is greater than or equal to zero. @@ -272,9 +268,8 @@ static long region_add(struct resv_map *resv, long f, long t)

/* * If no region exists which can be expanded to include the - * specified range, the list must have been modified by an - * interleving call to region_del(). Pull a region descriptor - * from the cache and use it for this range. + * specified range, pull a region descriptor from the cache + * and use it for this range. */ if (&rg->link == head || t < rg->from) { VM_BUG_ON(resv->region_cache_count <= 0); @@ -339,15 +334,9 @@ static long region_add(struct resv_map *resv, long f, long t) * call to region_add that will actually modify the reserve * map to add the specified range [f, t). region_chg does * not change the number of huge pages represented by the - * map. However, if the existing regions in the map can not - * be expanded to represent the new range, a new file_region - * structure is added to the map as a placeholder. This is - * so that the subsequent region_add call will have all the - * regions it needs and will not fail. - * - * Upon entry, region_chg will also examine the cache of region descriptors - * associated with the map. If there are not enough descriptors cached, one - * will be allocated for the in progress add operation. + * map. A new file_region structure is added to the cache + * as a placeholder, so that the subsequent region_add + * call will have all the regions it needs and will not fail. * * Returns the number of huge pages that need to be added to the existing * reservation map for the range [f, t). This number is greater or equal to @@ -357,10 +346,9 @@ static long region_add(struct resv_map *resv, long f, long t) static long region_chg(struct resv_map *resv, long f, long t) { struct list_head *head = &resv->regions; - struct file_region *rg, *nrg = NULL; + struct file_region *rg; long chg = 0;

-retry: spin_lock(&resv->lock); retry_locked: resv->adds_in_progress++; @@ -378,10 +366,8 @@ static long region_chg(struct resv_map *resv, long f, long t) spin_unlock(&resv->lock);

trg = kmalloc(sizeof(*trg), GFP_KERNEL); - if (!trg) { - kfree(nrg); + if (!trg) return -ENOMEM; - }

spin_lock(&resv->lock); list_add(&trg->link, &resv->region_cache); @@ -394,28 +380,6 @@ static long region_chg(struct resv_map *resv, long f, long t) if (f <= rg->to) break;

- /* If we are below the current region then a new region is required. - * Subtle, allocate a new region at the position but make it zero - * size such that we can guarantee to record the reservation. */ - if (&rg->link == head || t < rg->from) { - if (!nrg) { - resv->adds_in_progress--; - spin_unlock(&resv->lock); - nrg = kmalloc(sizeof(*nrg), GFP_KERNEL); - if (!nrg) - return -ENOMEM; - - nrg->from = f; - nrg->to = f; - INIT_LIST_HEAD(&nrg->link); - goto retry; - } - - list_add(&nrg->link, rg->link.prev); - chg = t - f; - goto out_nrg; - } - /* Round our left edge to the current segment if it encloses us. */ if (f > rg->from) f = rg->from; @@ -439,11 +403,6 @@ static long region_chg(struct resv_map *resv, long f, long t) }

out: - spin_unlock(&resv->lock); - /* We already know we raced and no longer need the new region */ - kfree(nrg); - return chg; -out_nrg: spin_unlock(&resv->lock); return chg; } -- 2.23.0.162.g0b9fbb3734-goog

A follow up patch in this series adds hugetlb cgroup uncharge info the file_region entries in resv->regions. The cgroup uncharge info may differ for different regions, so they can no longer be coalesced at region_add time. So, disable region coalescing in region_add in this patch.

Behavior change:

Say a resv_map exists like this [0->1], [2->3], and [5->6].

Then a region_chg/add call comes in region_chg/add(f=0, t=5).

Old code would generate resv->regions: [0->5], [5->6]. New code would generate resv->regions: [0->1], [1->2], [2->3], [3->5], [5->6].

Special care needs to be taken to handle the resv->adds_in_progress variable correctly. In the past, only 1 region would be added for every region_chg and region_add call. But now, each call may add multiple regions, so we can no longer increment adds_in_progress by 1 in region_chg, or decrement adds_in_progress by 1 after region_add or region_abort. Instead, region_chg calls add_reservation_in_range() to count the number of regions needed and allocates those, and that info is passed to region_add and region_abort to decrement adds_in_progress correctly.

Signed-off-by: Mina Almasry almasrymina@google.com --- mm/hugetlb.c | 279 ++++++++++++++++++++++++++++++--------------------- 1 file changed, 167 insertions(+), 112 deletions(-)

diff --git a/mm/hugetlb.c b/mm/hugetlb.c index ce5ed1056fefd..5eca34d9b753d 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -244,55 +244,80 @@ struct file_region { long to; };

+/* Helper that removes a struct file_region from the resv_map cache and returns + * it for use. + */ +static struct file_region *get_file_region_entry_from_cache( + struct resv_map *resv, long from, long to); + static long add_reservation_in_range( - struct resv_map *resv, long f, long t, bool count_only) + struct resv_map *resv, + long f, long t, + long *regions_needed, + bool count_only) { - - long chg = 0; + long add = 0; struct list_head *head = &resv->regions; + long last_accounted_offset = f; struct file_region *rg = NULL, *trg = NULL, *nrg = NULL;

- /* Locate the region we are before or in. */ - list_for_each_entry(rg, head, link) - if (f <= rg->to) - break; - - /* Round our left edge to the current segment if it encloses us. */ - if (f > rg->from) - f = rg->from; + if (regions_needed) + *regions_needed = 0;

- chg = t - f; + /* In this loop, we essentially handle an entry for the range + * last_accounted_offset -> rg->from, at every iteration, with some + * bounds checking. + */ + list_for_each_entry_safe(rg, trg, head, link) { + /* Skip irrelevant regions that start before our range. */ + if (rg->from < f) { + /* If this region ends after the last accounted offset, + * then we need to update last_accounted_offset. + */ + if (rg->to > last_accounted_offset) + last_accounted_offset = rg->to; + continue; + }

- /* Check for and consume any regions we now overlap with. */ - nrg = rg; - list_for_each_entry_safe(rg, trg, rg->link.prev, link) { - if (&rg->link == head) - break; + /* When we find a region that starts beyond our range, we've + * finished. + */ if (rg->from > t) break;

- /* We overlap with this area, if it extends further than - * us then we must extend ourselves. Account for its - * existing reservation. + /* Add an entry for last_accounted_offset -> rg->from, and + * update last_accounted_offset. */ - if (rg->to > t) { - chg += rg->to - t; - t = rg->to; + if (rg->from > last_accounted_offset) { + add += rg->from - last_accounted_offset; + if (!count_only) { + nrg = get_file_region_entry_from_cache(resv, + last_accounted_offset, + rg->from); + list_add(&nrg->link, rg->link.prev); + } else if (regions_needed) + *regions_needed += 1; } - chg -= rg->to - rg->from;

- if (!count_only && rg != nrg) { - list_del(&rg->link); - kfree(rg); - } + last_accounted_offset = rg->to; }

- if (!count_only) { - nrg->from = f; - nrg->to = t; + /* Handle the case where our range extends beyond + * last_accounted_offset. + */ + if (last_accounted_offset < t) { + add += t - last_accounted_offset; + if (!count_only) { + nrg = get_file_region_entry_from_cache(resv, + last_accounted_offset, t); + list_add(&nrg->link, rg->link.prev); + } else if (regions_needed) + *regions_needed += 1; + + last_accounted_offset = t; }

- return chg; + return add; }

/* @@ -302,46 +327,24 @@ static long add_reservation_in_range( * must exist in the cache due to the previous call to region_chg with * the same range. * + * regions_needed is the out value provided by a previous + * call to region_chg. + * * Return the number of new huge pages added to the map. This * number is greater than or equal to zero. */ -static long region_add(struct resv_map *resv, long f, long t) +static long region_add(struct resv_map *resv, long f, long t, + long regions_needed) { - struct list_head *head = &resv->regions; - struct file_region *rg, *nrg; long add = 0;

spin_lock(&resv->lock); - /* Locate the region we are either in or before. */ - list_for_each_entry(rg, head, link) - if (f <= rg->to) - break;

- /* - * If no region exists which can be expanded to include the - * specified range, pull a region descriptor from the cache - * and use it for this range. - */ - if (&rg->link == head || t < rg->from) { - VM_BUG_ON(resv->region_cache_count <= 0); - - resv->region_cache_count--; - nrg = list_first_entry(&resv->region_cache, struct file_region, - link); - list_del(&nrg->link); - - nrg->from = f; - nrg->to = t; - list_add(&nrg->link, rg->link.prev); - - add += t - f; - goto out_locked; - } + VM_BUG_ON(resv->region_cache_count < regions_needed);

- add = add_reservation_in_range(resv, f, t, false); + add = add_reservation_in_range(resv, f, t, NULL, false); + resv->adds_in_progress -= regions_needed;

-out_locked: - resv->adds_in_progress--; spin_unlock(&resv->lock); VM_BUG_ON(add < 0); return add; @@ -358,44 +361,54 @@ static long region_add(struct resv_map *resv, long f, long t) * as a placeholder, so that the subsequent region_add * call will have all the regions it needs and will not fail. * + * out_regions_needed is the number of regions added to the + * resv->region_cache_count. This value needs to be provided to a follow up + * call to region_add or region_abort for proper accounting. + * * Returns the number of huge pages that need to be added to the existing * reservation map for the range [f, t). This number is greater or equal to * zero. -ENOMEM is returned if a new file_region structure or cache entry * is needed and can not be allocated. */ -static long region_chg(struct resv_map *resv, long f, long t) +static long region_chg(struct resv_map *resv, long f, long t, + long *out_regions_needed) { - long chg = 0; + struct file_region *trg = NULL; + long chg = 0, regions_needed = 0;

+retry: spin_lock(&resv->lock); -retry_locked: - resv->adds_in_progress++; + + /* Count how many hugepages in this range are NOT respresented. */ + chg = add_reservation_in_range(resv, f, t, &regions_needed, true); +

/* * Check for sufficient descriptors in the cache to accommodate * the number of in progress add operations. */ - if (resv->adds_in_progress > resv->region_cache_count) { - struct file_region *trg; - - VM_BUG_ON(resv->adds_in_progress - resv->region_cache_count > 1); + if (resv->region_cache_count < regions_needed) { /* Must drop lock to allocate a new descriptor. */ - resv->adds_in_progress--; spin_unlock(&resv->lock);

- trg = kmalloc(sizeof(*trg), GFP_KERNEL); - if (!trg) - return -ENOMEM; + while (resv->region_cache_count < regions_needed + 1) { + trg = kmalloc(sizeof(*trg), GFP_KERNEL); + if (!trg) + return -ENOMEM;

- spin_lock(&resv->lock); - list_add(&trg->link, &resv->region_cache); - resv->region_cache_count++; - goto retry_locked; + spin_lock(&resv->lock); + list_add(&trg->link, &resv->region_cache); + resv->region_cache_count++; + spin_unlock(&resv->lock); + } + goto retry; }

- chg = add_reservation_in_range(resv, f, t, true); + resv->adds_in_progress += regions_needed;

spin_unlock(&resv->lock); + if (out_regions_needed) + *out_regions_needed = regions_needed; return chg; }

@@ -404,17 +417,19 @@ static long region_chg(struct resv_map *resv, long f, long t) * of the resv_map keeps track of the operations in progress between * calls to region_chg and region_add. Operations are sometimes * aborted after the call to region_chg. In such cases, region_abort - * is called to decrement the adds_in_progress counter. + * is called to decrement the adds_in_progress counter. regions_needed + * is the value returned by the region_chg call, it is used to decrement + * the adds_in_progress counter. * * NOTE: The range arguments [f, t) are not needed or used in this * routine. They are kept to make reading the calling code easier as * arguments will match the associated region_chg call. */ -static void region_abort(struct resv_map *resv, long f, long t) +static void region_abort(struct resv_map *resv, long f, long t, + long regions_needed) { spin_lock(&resv->lock); - VM_BUG_ON(!resv->region_cache_count); - resv->adds_in_progress--; + resv->adds_in_progress -= regions_needed; spin_unlock(&resv->lock); }

@@ -1865,7 +1880,9 @@ enum vma_resv_mode { }; static long __vma_reservation_common(struct hstate *h, struct vm_area_struct *vma, unsigned long addr, - enum vma_resv_mode mode) + enum vma_resv_mode mode, + long *out_regions_needed, + long in_regions_needed) { struct resv_map *resv; pgoff_t idx; @@ -1878,20 +1895,24 @@ static long __vma_reservation_common(struct hstate *h, idx = vma_hugecache_offset(h, vma, addr); switch (mode) { case VMA_NEEDS_RESV: - ret = region_chg(resv, idx, idx + 1); + VM_BUG_ON(!out_regions_needed); + ret = region_chg(resv, idx, idx + 1, out_regions_needed); break; case VMA_COMMIT_RESV: - ret = region_add(resv, idx, idx + 1); + VM_BUG_ON(in_regions_needed == -1); + ret = region_add(resv, idx, idx + 1, in_regions_needed); break; case VMA_END_RESV: - region_abort(resv, idx, idx + 1); + VM_BUG_ON(in_regions_needed == -1); + region_abort(resv, idx, idx + 1, in_regions_needed); ret = 0; break; case VMA_ADD_RESV: + VM_BUG_ON(in_regions_needed == -1); if (vma->vm_flags & VM_MAYSHARE) - ret = region_add(resv, idx, idx + 1); + ret = region_add(resv, idx, idx + 1, in_regions_needed); else { - region_abort(resv, idx, idx + 1); + region_abort(resv, idx, idx + 1, in_regions_needed); ret = region_del(resv, idx, idx + 1); } break; @@ -1925,27 +1946,35 @@ static long __vma_reservation_common(struct hstate *h, }

static long vma_needs_reservation(struct hstate *h, - struct vm_area_struct *vma, unsigned long addr) + struct vm_area_struct *vma, unsigned long addr, + long *out_regions_needed) { - return __vma_reservation_common(h, vma, addr, VMA_NEEDS_RESV); + return __vma_reservation_common(h, vma, addr, VMA_NEEDS_RESV, + out_regions_needed, -1); }

static long vma_commit_reservation(struct hstate *h, - struct vm_area_struct *vma, unsigned long addr) + struct vm_area_struct *vma, unsigned long addr, + long regions_needed) { - return __vma_reservation_common(h, vma, addr, VMA_COMMIT_RESV); + return __vma_reservation_common(h, vma, addr, VMA_COMMIT_RESV, NULL, + regions_needed); }

static void vma_end_reservation(struct hstate *h, - struct vm_area_struct *vma, unsigned long addr) + struct vm_area_struct *vma, unsigned long addr, + long regions_needed) { - (void)__vma_reservation_common(h, vma, addr, VMA_END_RESV); + (void)__vma_reservation_common(h, vma, addr, VMA_END_RESV, NULL, + regions_needed); }

static long vma_add_reservation(struct hstate *h, - struct vm_area_struct *vma, unsigned long addr) + struct vm_area_struct *vma, unsigned long addr, + long regions_needed) { - return __vma_reservation_common(h, vma, addr, VMA_ADD_RESV); + return __vma_reservation_common(h, vma, addr, VMA_ADD_RESV, NULL, + regions_needed); }

/* @@ -1963,8 +1992,10 @@ static void restore_reserve_on_error(struct hstate *h, struct vm_area_struct *vma, unsigned long address, struct page *page) { + long regions_needed = 0; if (unlikely(PagePrivate(page))) { - long rc = vma_needs_reservation(h, vma, address); + long rc = vma_needs_reservation(h, vma, address, + &regions_needed);

if (unlikely(rc < 0)) { /* @@ -1980,7 +2011,8 @@ static void restore_reserve_on_error(struct hstate *h, */ ClearPagePrivate(page); } else if (rc) { - rc = vma_add_reservation(h, vma, address); + rc = vma_add_reservation(h, vma, address, + regions_needed); if (unlikely(rc < 0)) /* * See above comment about rare out of @@ -1988,7 +2020,7 @@ static void restore_reserve_on_error(struct hstate *h, */ ClearPagePrivate(page); } else - vma_end_reservation(h, vma, address); + vma_end_reservation(h, vma, address, regions_needed); } }

@@ -2002,6 +2034,7 @@ struct page *alloc_huge_page(struct vm_area_struct *vma, long gbl_chg; int ret, idx; struct hugetlb_cgroup *h_cg; + long regions_needed = 0;

idx = hstate_index(h); /* @@ -2009,7 +2042,8 @@ struct page *alloc_huge_page(struct vm_area_struct *vma, * has a reservation for the page to be allocated. A return * code of zero indicates a reservation exists (no change). */ - map_chg = gbl_chg = vma_needs_reservation(h, vma, addr); + map_chg = gbl_chg = vma_needs_reservation(h, vma, addr, + &regions_needed); if (map_chg < 0) return ERR_PTR(-ENOMEM);

@@ -2023,7 +2057,7 @@ struct page *alloc_huge_page(struct vm_area_struct *vma, if (map_chg || avoid_reserve) { gbl_chg = hugepage_subpool_get_pages(spool, 1); if (gbl_chg < 0) { - vma_end_reservation(h, vma, addr); + vma_end_reservation(h, vma, addr, regions_needed); return ERR_PTR(-ENOSPC); }

@@ -2069,7 +2103,7 @@ struct page *alloc_huge_page(struct vm_area_struct *vma,

set_page_private(page, (unsigned long)spool);

- map_commit = vma_commit_reservation(h, vma, addr); + map_commit = vma_commit_reservation(h, vma, addr, regions_needed); if (unlikely(map_chg > map_commit)) { /* * The page was added to the reservation map between @@ -2093,7 +2127,7 @@ struct page *alloc_huge_page(struct vm_area_struct *vma, out_subpool_put: if (map_chg || avoid_reserve) hugepage_subpool_put_pages(spool, 1); - vma_end_reservation(h, vma, addr); + vma_end_reservation(h, vma, addr, regions_needed); return ERR_PTR(-ENOSPC); }

@@ -3778,6 +3812,7 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm, spinlock_t *ptl; unsigned long haddr = address & huge_page_mask(h); bool new_page = false; + long regions_needed = 0;

/* * Currently, we are forced to kill the process in the event the @@ -3895,12 +3930,12 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm, * the spinlock. */ if ((flags & FAULT_FLAG_WRITE) && !(vma->vm_flags & VM_SHARED)) { - if (vma_needs_reservation(h, vma, haddr) < 0) { + if (vma_needs_reservation(h, vma, haddr, &regions_needed) < 0) { ret = VM_FAULT_OOM; goto backout_unlocked; } /* Just decrements count, does not deallocate */ - vma_end_reservation(h, vma, haddr); + vma_end_reservation(h, vma, haddr, regions_needed); }

ptl = huge_pte_lock(h, mm, ptep); @@ -3990,6 +4025,7 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, struct address_space *mapping; int need_wait_lock = 0; unsigned long haddr = address & huge_page_mask(h); + long regions_needed = 0;

ptep = huge_pte_offset(mm, haddr, huge_page_size(h)); if (ptep) { @@ -4044,12 +4080,12 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, * consumed. */ if ((flags & FAULT_FLAG_WRITE) && !huge_pte_write(entry)) { - if (vma_needs_reservation(h, vma, haddr) < 0) { + if (vma_needs_reservation(h, vma, haddr, &regions_needed) < 0) { ret = VM_FAULT_OOM; goto out_mutex; } /* Just decrements count, does not deallocate */ - vma_end_reservation(h, vma, haddr); + vma_end_reservation(h, vma, haddr, regions_needed);

if (!(vma->vm_flags & VM_MAYSHARE)) pagecache_page = hugetlbfs_pagecache_page(h, @@ -4512,7 +4548,7 @@ int hugetlb_reserve_pages(struct inode *inode, struct hugepage_subpool *spool = subpool_inode(inode); struct resv_map *resv_map; struct hugetlb_cgroup *h_cg; - long gbl_reserve; + long gbl_reserve, regions_needed = 0;

/* This should never happen */ if (from > to) { @@ -4542,7 +4578,7 @@ int hugetlb_reserve_pages(struct inode *inode, */ resv_map = inode_resv_map(inode);

- chg = region_chg(resv_map, from, to); + chg = region_chg(resv_map, from, to, &regions_needed);

} else { /* Private mapping. */ @@ -4612,7 +4648,7 @@ int hugetlb_reserve_pages(struct inode *inode, * else has to be done for private mappings here */ if (!vma || vma->vm_flags & VM_MAYSHARE) { - long add = region_add(resv_map, from, to); + long add = region_add(resv_map, from, to, regions_needed);

if (unlikely(chg > add)) { /* @@ -4634,7 +4670,7 @@ int hugetlb_reserve_pages(struct inode *inode, if (!vma || vma->vm_flags & VM_MAYSHARE) /* Don't call region_abort if region_chg failed */ if (chg >= 0) - region_abort(resv_map, from, to); + region_abort(resv_map, from, to, regions_needed); if (vma && is_vma_resv_set(vma, HPAGE_RESV_OWNER)) kref_put(&resv_map->refs, resv_map_release); return ret; @@ -5058,3 +5094,22 @@ void move_hugetlb_state(struct page *oldpage, struct page *newpage, int reason) spin_unlock(&hugetlb_lock); } } + +static struct file_region *get_file_region_entry_from_cache( + struct resv_map *resv, long from, long to) +{ + struct file_region *nrg = NULL; + + VM_BUG_ON(resv->region_cache_count <= 0); + + resv->region_cache_count--; + nrg = list_first_entry(&resv->region_cache, struct file_region, + link); + VM_BUG_ON(!nrg); + list_del(&nrg->link); + + nrg->from = from; + nrg->to = to; + + return nrg; +} -- 2.23.0.162.g0b9fbb3734-goog

The tests use both shared and private mapped hugetlb memory, and monitors the hugetlb usage counter as well as the hugetlb reservation counter. They test different configurations such as hugetlb memory usage via hugetlbfs, or MAP_HUGETLB, or shmget/shmat, and with and without MAP_POPULATE.

Signed-off-by: Mina Almasry almasrymina@google.com --- tools/testing/selftests/vm/.gitignore | 1 + tools/testing/selftests/vm/Makefile | 4 + .../selftests/vm/charge_reserved_hugetlb.sh | 440 ++++++++++++++++++ .../selftests/vm/write_hugetlb_memory.sh | 22 + .../testing/selftests/vm/write_to_hugetlbfs.c | 252 ++++++++++ 5 files changed, 719 insertions(+) create mode 100755 tools/testing/selftests/vm/charge_reserved_hugetlb.sh create mode 100644 tools/testing/selftests/vm/write_hugetlb_memory.sh create mode 100644 tools/testing/selftests/vm/write_to_hugetlbfs.c

diff --git a/tools/testing/selftests/vm/.gitignore b/tools/testing/selftests/vm/.gitignore index 31b3c98b6d34d..d3bed9407773c 100644 --- a/tools/testing/selftests/vm/.gitignore +++ b/tools/testing/selftests/vm/.gitignore @@ -14,3 +14,4 @@ virtual_address_range gup_benchmark va_128TBswitch map_fixed_noreplace +write_to_hugetlbfs diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile index 9534dc2bc9295..8d37d5409b52c 100644 --- a/tools/testing/selftests/vm/Makefile +++ b/tools/testing/selftests/vm/Makefile @@ -18,6 +18,7 @@ TEST_GEN_FILES += transhuge-stress TEST_GEN_FILES += userfaultfd TEST_GEN_FILES += va_128TBswitch TEST_GEN_FILES += virtual_address_range +TEST_GEN_FILES += write_to_hugetlbfs

TEST_PROGS := run_vmtests

@@ -29,3 +30,6 @@ include ../lib.mk $(OUTPUT)/userfaultfd: LDLIBS += -lpthread

$(OUTPUT)/mlock-random-test: LDLIBS += -lcap + +# Why does adding $(OUTPUT)/ like above not apply this flag..? +write_to_hugetlbfs: CFLAGS += -static diff --git a/tools/testing/selftests/vm/charge_reserved_hugetlb.sh b/tools/testing/selftests/vm/charge_reserved_hugetlb.sh new file mode 100755 index 0000000000000..09e90e8f6fab4 --- /dev/null +++ b/tools/testing/selftests/vm/charge_reserved_hugetlb.sh @@ -0,0 +1,440 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 + +set -e + +cgroup_path=/dev/cgroup/memory +if [[ ! -e $cgroup_path ]]; then + mkdir -p $cgroup_path + mount -t cgroup -o hugetlb,memory cgroup $cgroup_path +fi + +cleanup () { + echo $$ > $cgroup_path/tasks + + set +e + if [[ "$(pgrep write_to_hugetlbfs)" != "" ]]; then + kill -2 write_to_hugetlbfs + # Wait for hugetlbfs memory to get depleted. + sleep 0.5 + fi + set -e + + if [[ -e /mnt/huge ]]; then + rm -rf /mnt/huge/* + umount /mnt/huge || echo error + rmdir /mnt/huge + fi + if [[ -e $cgroup_path/hugetlb_cgroup_test ]]; then + rmdir $cgroup_path/hugetlb_cgroup_test + fi + if [[ -e $cgroup_path/hugetlb_cgroup_test1 ]]; then + rmdir $cgroup_path/hugetlb_cgroup_test1 + fi + if [[ -e $cgroup_path/hugetlb_cgroup_test2 ]]; then + rmdir $cgroup_path/hugetlb_cgroup_test2 + fi + echo 0 > /proc/sys/vm/nr_hugepages + echo CLEANUP DONE +} + +cleanup + +function expect_equal() { + local expected="$1" + local actual="$2" + local error="$3" + + if [[ "$expected" != "$actual" ]]; then + echo "expected ($expected) != actual ($actual): $3" + cleanup + exit 1 + fi +} + +function setup_cgroup() { + local name="$1" + local cgroup_limit="$2" + local reservation_limit="$3" + + mkdir $cgroup_path/$name + + echo writing cgroup limit: "$cgroup_limit" + echo "$cgroup_limit" > $cgroup_path/$name/hugetlb.2MB.limit_in_bytes + + echo writing reseravation limit: "$reservation_limit" + echo "$reservation_limit" > \ + $cgroup_path/$name/hugetlb.2MB.reservation_limit_in_bytes + echo 0 > $cgroup_path/$name/cpuset.cpus + echo 0 > $cgroup_path/$name/cpuset.mems +} + +function write_hugetlbfs_and_get_usage() { + local cgroup="$1" + local size="$2" + local populate="$3" + local write="$4" + local path="$5" + local method="$6" + local private="$7" + local expect_failure="$8" + + # Function return values. + reservation_failed=0 + oom_killed=0 + hugetlb_difference=0 + reserved_difference=0 + + local hugetlb_usage=$cgroup_path/$cgroup/hugetlb.2MB.usage_in_bytes + local reserved_usage=$cgroup_path/$cgroup/hugetlb.2MB.reservation_usage_in_bytes + + local hugetlb_before=$(cat $hugetlb_usage) + local reserved_before=$(cat $reserved_usage) + + echo + echo Starting: + echo hugetlb_usage="$hugetlb_before" + echo reserved_usage="$reserved_before" + echo expect_failure is "$expect_failure" + + set +e + if [[ "$method" == "1" ]] || [[ "$method" == 2 ]] || \ + [[ "$private" == "-r" ]] && [[ "$expect_failure" != 1 ]]; then + bash write_hugetlb_memory.sh "$size" "$populate" "$write" \ + "$cgroup" "$path" "$method" "$private" "-l" & + + local write_result=$? + # This sleep is to make sure that the script above has had enough + # time to do its thing, since it runs in the background. This may + # cause races... + sleep 0.5 + echo write_result is $write_result + else + bash write_hugetlb_memory.sh "$size" "$populate" "$write" \ + "$cgroup" "$path" "$method" "$private" + local write_result=$? + fi + set -e + + if [[ "$write_result" == 1 ]]; then + reservation_failed=1 + fi + + # On linus/master, the above process gets SIGBUS'd on oomkill, with + # return code 135. On earlier kernels, it gets actual oomkill, with return + # code 137, so just check for both conditions incase we're testing against + # an earlier kernel. + if [[ "$write_result" == 135 ]] || [[ "$write_result" == 137 ]]; then + oom_killed=1 + fi + + local hugetlb_after=$(cat $hugetlb_usage) + local reserved_after=$(cat $reserved_usage) + + echo After write: + echo hugetlb_usage="$hugetlb_after" + echo reserved_usage="$reserved_after" + + hugetlb_difference=$(($hugetlb_after - $hugetlb_before)) + reserved_difference=$(($reserved_after - $reserved_before)) +} + +function cleanup_hugetlb_memory() { + set +e + if [[ "$(pgrep write_to_hugetlbfs)" != "" ]]; then + echo kiling write_to_hugetlbfs + killall -2 write_to_hugetlbfs + # Wait for hugetlbfs memory to get depleted. + sleep 0.5 + fi + set -e + + if [[ -e /mnt/huge ]]; then + rm -rf /mnt/huge/* + umount /mnt/huge + rmdir /mnt/huge + fi +} + +function run_test() { + local size="$1" + local populate="$2" + local write="$3" + local cgroup_limit="$4" + local reservation_limit="$5" + local nr_hugepages="$6" + local method="$7" + local private="$8" + local expect_failure="$9" + + # Function return values. + hugetlb_difference=0 + reserved_difference=0 + reservation_failed=0 + oom_killed=0 + + echo nr hugepages = "$nr_hugepages" + echo "$nr_hugepages" > /proc/sys/vm/nr_hugepages + + setup_cgroup "hugetlb_cgroup_test" "$cgroup_limit" "$reservation_limit" + + mkdir -p /mnt/huge + mount -t hugetlbfs \ + -o pagesize=2M,size=256M none /mnt/huge + + write_hugetlbfs_and_get_usage "hugetlb_cgroup_test" "$size" "$populate" \ + "$write" "/mnt/huge/test" "$method" "$private" "$expect_failure" + + cleanup_hugetlb_memory + + local final_hugetlb=$(cat $cgroup_path/hugetlb_cgroup_test/hugetlb.2MB.usage_in_bytes) + local final_reservation=$(cat $cgroup_path/hugetlb_cgroup_test/hugetlb.2MB.reservation_usage_in_bytes) + + expect_equal "0" "$final_hugetlb" "final hugetlb is not zero" + expect_equal "0" "$final_reservation" "final reservation is not zero" +} + +function run_multiple_cgroup_test() { + local size1="$1" + local populate1="$2" + local write1="$3" + local cgroup_limit1="$4" + local reservation_limit1="$5" + + local size2="$6" + local populate2="$7" + local write2="$8" + local cgroup_limit2="$9" + local reservation_limit2="${10}" + + local nr_hugepages="${11}" + local method="${12}" + local private="${13}" + local expect_failure="${14}" + + # Function return values. + hugetlb_difference1=0 + reserved_difference1=0 + reservation_failed1=0 + oom_killed1=0 + + hugetlb_difference2=0 + reserved_difference2=0 + reservation_failed2=0 + oom_killed2=0 + + + echo nr hugepages = "$nr_hugepages" + echo "$nr_hugepages" > /proc/sys/vm/nr_hugepages + + setup_cgroup "hugetlb_cgroup_test1" "$cgroup_limit1" "$reservation_limit1" + setup_cgroup "hugetlb_cgroup_test2" "$cgroup_limit2" "$reservation_limit2" + + mkdir -p /mnt/huge + mount -t hugetlbfs \ + -o pagesize=2M,size=256M none /mnt/huge + + write_hugetlbfs_and_get_usage "hugetlb_cgroup_test1" "$size1" \ + "$populate1" "$write1" "/mnt/huge/test1" "$method" "$private" \ + "$expect_failure" + + hugetlb_difference1=$hugetlb_difference + reserved_difference1=$reserved_difference + reservation_failed1=$reservation_failed + oom_killed1=$oom_killed + + local cgroup1_hugetlb_usage=$cgroup_path/hugetlb_cgroup_test1/hugetlb.2MB.usage_in_bytes + local cgroup1_reservation_usage=$cgroup_path/hugetlb_cgroup_test1/hugetlb.2MB.reservation_usage_in_bytes + local cgroup2_hugetlb_usage=$cgroup_path/hugetlb_cgroup_test2/hugetlb.2MB.usage_in_bytes + local cgroup2_reservation_usage=$cgroup_path/hugetlb_cgroup_test2/hugetlb.2MB.reservation_usage_in_bytes + + local usage_before_second_write=$(cat $cgroup1_hugetlb_usage) + local reservation_usage_before_second_write=$(cat \ + $cgroup1_reservation_usage) + + write_hugetlbfs_and_get_usage "hugetlb_cgroup_test2" "$size2" \ + "$populate2" "$write2" "/mnt/huge/test2" "$method" "$private" \ + "$expect_failure" + + hugetlb_difference2=$hugetlb_difference + reserved_difference2=$reserved_difference + reservation_failed2=$reservation_failed + oom_killed2=$oom_killed + + expect_equal "$usage_before_second_write" \ + "$(cat $cgroup1_hugetlb_usage)" "Usage changed." + expect_equal "$reservation_usage_before_second_write" \ + "$(cat $cgroup1_reservation_usage)" "Reservation usage changed." + + cleanup_hugetlb_memory + + local final_hugetlb=$(cat $cgroup1_hugetlb_usage) + local final_reservation=$(cat $cgroup1_reservation_usage) + + expect_equal "0" "$final_hugetlb" \ + "hugetlbt_cgroup_test1 final hugetlb is not zero" + expect_equal "0" "$final_reservation" \ + "hugetlbt_cgroup_test1 final reservation is not zero" + + local final_hugetlb=$(cat $cgroup2_hugetlb_usage) + local final_reservation=$(cat $cgroup2_reservation_usage) + + expect_equal "0" "$final_hugetlb" \ + "hugetlb_cgroup_test2 final hugetlb is not zero" + expect_equal "0" "$final_reservation" \ + "hugetlb_cgroup_test2 final reservation is not zero" +} + +for private in "" "-r" ; do +for populate in "" "-o"; do +for method in 0 1 2; do + +# Skip mmap(MAP_HUGETLB | MAP_SHARED). Doesn't seem to be supported. +if [[ "$method" == 1 ]] && [[ "$private" == "" ]]; then + continue +fi + +# Skip populated shmem tests. Doesn't seem to be supported. +if [[ "$method" == 2"" ]] && [[ "$populate" == "-o" ]]; then + continue +fi + +cleanup +echo +echo +echo +echo Test normal case. +echo private=$private, populate=$populate, method=$method +run_test $((10 * 1024 * 1024)) "$populate" "" $((20 * 1024 * 1024)) \ + $((20 * 1024 * 1024)) 10 "$method" "$private" "0" + +echo Memory charged to hugtlb=$hugetlb_difference +echo Memory charged to reservation=$reserved_difference + +if [[ "$populate" == "-o" ]]; then + expect_equal "$((10 * 1024 * 1024))" "$hugetlb_difference" \ + "Reserved memory charged to hugetlb cgroup." +else + expect_equal "0" "$hugetlb_difference" \ + "Reserved memory charged to hugetlb cgroup." +fi + +expect_equal "$((10 * 1024 * 1024))" "$reserved_difference" \ + "Reserved memory not charged to reservation usage." +echo 'PASS' + +cleanup +echo +echo +echo +echo Test normal case with write. +echo private=$private, populate=$populate, method=$method +run_test $((10 * 1024 * 1024)) "$populate" '-w' $((20 * 1024 * 1024)) \ + $((20 * 1024 * 1024)) 10 "$method" "$private" "0" + +echo Memory charged to hugtlb=$hugetlb_difference +echo Memory charged to reservation=$reserved_difference + +expect_equal "$((10 * 1024 * 1024))" "$hugetlb_difference" \ + "Reserved memory charged to hugetlb cgroup." +expect_equal "$((10 * 1024 * 1024))" "$reserved_difference" \ + "Reserved memory not charged to reservation usage." +echo 'PASS' + + +cleanup +echo +echo +echo +echo Test more than reservation case. +echo private=$private, populate=$populate, method=$method +run_test "$((10 * 1024 * 1024))" "$populate" '' "$((20 * 1024 * 1024))" \ + "$((5 * 1024 * 1024))" "10" "$method" "$private" "1" + +expect_equal "1" "$reservation_failed" "Reservation succeeded." +echo 'PASS' + +cleanup + +echo +echo +echo +echo Test more than cgroup limit case. +echo private=$private, populate=$populate, method=$method + +# Not sure if shm memory can be cleaned up when the process gets sigbus'd. +if [[ "$method" != 2 ]]; then + run_test $((10 * 1024 * 1024)) "$populate" "-w" $((5 * 1024 * 1024)) \ + $((20 * 1024 * 1024)) 10 "$method" "$private" "1" + + expect_equal "1" "$oom_killed" "Not oom killed." +fi +echo 'PASS' + +cleanup + +echo +echo +echo +echo Test normal case, multiple cgroups. +echo private=$private, populate=$populate, method=$method +run_multiple_cgroup_test "$((6 * 1024 * 1024))" "$populate" "" \ + "$((20 * 1024 * 1024))" "$((20 * 1024 * 1024))" "$((10 * 1024 * 1024))" \ + "$populate" "" "$((20 * 1024 * 1024))" "$((20 * 1024 * 1024))" "10" \ + "$method" "$private" "0" + +echo Memory charged to hugtlb1=$hugetlb_difference1 +echo Memory charged to reservation1=$reserved_difference1 +echo Memory charged to hugtlb2=$hugetlb_difference2 +echo Memory charged to reservation2=$reserved_difference2 + +expect_equal "$((6 * 1024 * 1024))" "$reserved_difference1" \ + "Incorrect reservations charged to cgroup 1." +expect_equal "$((10 * 1024 * 1024))" "$reserved_difference2" \ + "Incorrect reservation charged to cgroup 2." +if [[ "$populate" == "-o" ]]; then + expect_equal "$((6 * 1024 * 1024))" "$hugetlb_difference1" \ + "Incorrect hugetlb charged to cgroup 1." + expect_equal "$((10 * 1024 * 1024))" "$hugetlb_difference2" \ + "Incorrect hugetlb charged to cgroup 2." +else + expect_equal "0" "$hugetlb_difference1" \ + "Incorrect hugetlb charged to cgroup 1." + expect_equal "0" "$hugetlb_difference2" \ + "Incorrect hugetlb charged to cgroup 2." +fi +echo 'PASS' + +cleanup +echo +echo +echo +echo Test normal case with write, multiple cgroups. +echo private=$private, populate=$populate, method=$method +run_multiple_cgroup_test "$((6 * 1024 * 1024))" "$populate" "-w" \ + "$((20 * 1024 * 1024))" "$((20 * 1024 * 1024))" "$((10 * 1024 * 1024))" \ + "$populate" "-w" "$((20 * 1024 * 1024))" "$((20 * 1024 * 1024))" "10" \ + "$method" "$private" "0" + +echo Memory charged to hugtlb1=$hugetlb_difference1 +echo Memory charged to reservation1=$reserved_difference1 +echo Memory charged to hugtlb2=$hugetlb_difference2 +echo Memory charged to reservation2=$reserved_difference2 + +expect_equal "$((6 * 1024 * 1024))" "$hugetlb_difference1" \ + "Incorrect hugetlb charged to cgroup 1." +expect_equal "$((6 * 1024 * 1024))" "$reserved_difference1" \ + "Incorrect reservation charged to cgroup 1." +expect_equal "$((10 * 1024 * 1024))" "$hugetlb_difference2" \ + "Incorrect hugetlb charged to cgroup 2." +expect_equal "$((10 * 1024 * 1024))" "$reserved_difference2" \ + "Incorrected reservation charged to cgroup 2." + +echo 'PASS' + +done # private +done # populate +done # method + +umount $cgroup_path +rmdir $cgroup_path diff --git a/tools/testing/selftests/vm/write_hugetlb_memory.sh b/tools/testing/selftests/vm/write_hugetlb_memory.sh new file mode 100644 index 0000000000000..08f5fa5527cfd --- /dev/null +++ b/tools/testing/selftests/vm/write_hugetlb_memory.sh @@ -0,0 +1,22 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 + +set -e + +size=$1 +populate=$2 +write=$3 +cgroup=$4 +path=$5 +method=$6 +private=$7 +want_sleep=$8 + +echo "Putting task in cgroup '$cgroup'" +echo $$ > /dev/cgroup/memory/"$cgroup"/tasks + +echo "Method is $method" + +set +e +./write_to_hugetlbfs -p "$path" -s "$size" "$write" "$populate" -m "$method" \ + "$private" "$want_sleep" diff --git a/tools/testing/selftests/vm/write_to_hugetlbfs.c b/tools/testing/selftests/vm/write_to_hugetlbfs.c new file mode 100644 index 0000000000000..f02a897427a97 --- /dev/null +++ b/tools/testing/selftests/vm/write_to_hugetlbfs.c @@ -0,0 +1,252 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * This program reserves and uses hugetlb memory, supporting a bunch of + * scenorios needed by the charged_reserved_hugetlb.sh test. + */ + +#include <err.h> +#include <errno.h> +#include <signal.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <unistd.h> +#include <fcntl.h> +#include <sys/types.h> +#include <sys/shm.h> +#include <sys/stat.h> +#include <sys/mman.h> + +/* Global definitions. */ +enum method { + HUGETLBFS, + MMAP_MAP_HUGETLB, + SHM, + MAX_METHOD +}; + + +/* Global variables. */ +static const char *self; +static char *shmaddr; +static int shmid; + +/* + * Show usage and exit. + */ +static void exit_usage(void) +{ + + printf("Usage: %s -p <path to hugetlbfs file> -s <size to map> " + "[-m <0=hugetlbfs | 1=mmap(MAP_HUGETLB)>] [-l] [-r] " + "[-o] [-w]\n", self); + exit(EXIT_FAILURE); +} + +void sig_handler(int signo) +{ + printf("Received %d.\n", signo); + if (signo == SIGINT) { + printf("Deleting the memory\n"); + if (shmdt((const void *)shmaddr) != 0) { + perror("Detach failure"); + shmctl(shmid, IPC_RMID, NULL); + exit(4); + } + + shmctl(shmid, IPC_RMID, NULL); + printf("Done deleting the memory\n"); + } + exit(2); +} + +int main(int argc, char **argv) +{ + int fd = 0; + int key = 0; + int *ptr = NULL; + int c = 0; + int size = 0; + char path[256] = ""; + enum method method = MAX_METHOD; + int want_sleep = 0, private = 0; + int populate = 0; + int write = 0; + + unsigned long i; + + + if (signal(SIGINT, sig_handler) == SIG_ERR) + err(1, "\ncan't catch SIGINT\n"); + + /* Parse command-line arguments. */ + setvbuf(stdout, NULL, _IONBF, 0); + self = argv[0]; + + while ((c = getopt(argc, argv, "s:p:m:owlr")) != -1) { + switch (c) { + case 's': + size = atoi(optarg); + break; + case 'p': + strncpy(path, optarg, sizeof(path)); + break; + case 'm': + if (atoi(optarg) >= MAX_METHOD) { + errno = EINVAL; + perror("Invalid -m."); + exit_usage(); + } + method = atoi(optarg); + break; + case 'o': + populate = 1; + break; + case 'w': + write = 1; + break; + case 'l': + want_sleep = 1; + break; + case 'r': + private = 1; + break; + default: + errno = EINVAL; + perror("Invalid arg"); + exit_usage(); + } + } + + if (strncmp(path, "", sizeof(path)) != 0) { + printf("Writing to this path: %s\n", path); + } else { + errno = EINVAL; + perror("path not found"); + exit_usage(); + } + + if (size != 0) { + printf("Writing this size: %d\n", size); + } else { + errno = EINVAL; + perror("size not found"); + exit_usage(); + } + + if (!populate) + printf("Not populating.\n"); + else + printf("Populating.\n"); + + if (!write) + printf("Not writing to memory.\n"); + + if (method == MAX_METHOD) { + errno = EINVAL; + perror("-m Invalid"); + exit_usage(); + } else + printf("Using method=%d\n", method); + + if (!private) + printf("Shared mapping.\n"); + else + printf("Private mapping.\n"); + + + switch (method) { + case HUGETLBFS: + printf("Allocating using HUGETLBFS.\n"); + fd = open(path, O_CREAT | O_RDWR, 0777); + if (fd == -1) + err(1, "Failed to open file."); + + ptr = mmap(NULL, size, PROT_READ | PROT_WRITE, + (private ? MAP_PRIVATE : MAP_SHARED) | (populate ? + MAP_POPULATE : 0), fd, 0); + + if (ptr == MAP_FAILED) { + close(fd); + err(1, "Error mapping the file"); + } + break; + case MMAP_MAP_HUGETLB: + printf("Allocating using MAP_HUGETLB.\n"); + ptr = mmap(NULL, size, + PROT_READ | PROT_WRITE, + (private ? (MAP_PRIVATE | MAP_ANONYMOUS) : MAP_SHARED) | + MAP_HUGETLB | (populate ? + MAP_POPULATE : 0), + -1, 0); + + if (ptr == MAP_FAILED) + err(1, "mmap"); + + printf("Returned address is %p\n", ptr); + break; + case SHM: + printf("Allocating using SHM.\n"); + shmid = shmget(key, size, SHM_HUGETLB | IPC_CREAT | SHM_R | + SHM_W); + if (shmid < 0) { + shmid = shmget(++key, size, SHM_HUGETLB | IPC_CREAT | + SHM_R | SHM_W); + if (shmid < 0) + err(1, "shmget"); + + } + printf("shmid: 0x%x, shmget key:%d\n", shmid, key); + + shmaddr = shmat(shmid, NULL, 0); + if (shmaddr == (char *)-1) { + perror("Shared memory attach failure"); + shmctl(shmid, IPC_RMID, NULL); + exit(2); + } + printf("shmaddr: %p\n", shmaddr); + + break; + default: + errno = EINVAL; + err(1, "Invalid method."); + } + + if (write) { + printf("Writing to memory.\n"); + if (method != SHM) { + memset(ptr, 1, size); + } else { + printf("Starting the writes:\n"); + for (i = 0; i < size; i++) { + shmaddr[i] = (char)(i); + if (!(i % (1024 * 1024))) + printf("."); + } + printf("\n"); + + printf("Starting the Check..."); + for (i = 0; i < size; i++) + if (shmaddr[i] != (char)i) { + printf("\nIndex %lu mismatched\n", i); + exit(3); + } + printf("Done.\n"); + + + } + } + + if (want_sleep) { + /* Signal to caller that we're done. */ + printf("DONE\n"); + + /* Hold memory until external kill signal is delivered. */ + while (1) + sleep(100); + } + + close(fd); + + return 0; +} -- 2.23.0.162.g0b9fbb3734-goog

On 9/10/19 4:31 PM, Mina Almasry wrote:

Current behavior is that region_chg provides both a cache entry in resv->region_cache, AND a placeholder entry in resv->regions. region_add first tries to use the placeholder, and if it finds that the placeholder has been deleted by a racing region_del call, it uses the cache entry.

This behavior is completely unnecessary and is removed in this patch for a couple of reasons:

1. region_add needs to either find a cached file_region entry in resv->region_cache, or find an entry in resv->regions to expand. It does not need both.
2. region_chg adding a placeholder entry in resv->regions opens up a possible race with region_del, where region_chg adds a placeholder region in resv->regions, and this region is deleted by a racing call to region_del during region_chg execution or before region_add is called. Removing the race makes the code easier to reason about and maintain.

In addition, a follow up patch in this series disables region coalescing, which would be further complicated if the race with region_del exists.

Signed-off-by: Mina Almasry almasrymina@google.com

Thanks. I like this modification as it does simplify the code and could be added as a general cleanup independent of the other changes.

Reviewed-by: Mike Kravetz mike.kravetz@oracle.com

On 9/10/19 5:31 PM, Mina Almasry wrote:

These counters will track hugetlb reservations rather than hugetlb memory faulted in. This patch only adds the counter, following patches add the charging and uncharging of the counter.

Why are we adding these counters? I see the reasons in the cover letter. Why not add the details on why this is needed here in this commitlog

Please add more information on why and rephrase the commit log.

Signed-off-by: Mina Almasry almasrymina@google.com Acked-by: Hillf Danton hdanton@sina.com

---

include/linux/hugetlb.h | 16 +++++- mm/hugetlb_cgroup.c | 111 ++++++++++++++++++++++++++++++---------- 2 files changed, 100 insertions(+), 27 deletions(-)

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index edfca42783192..128ff1aff1c93 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -320,6 +320,20 @@ unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr,

#ifdef CONFIG_HUGETLB_PAGE

+enum {

• HUGETLB_RES_USAGE,
• HUGETLB_RES_RESERVATION_USAGE,
• HUGETLB_RES_LIMIT,
• HUGETLB_RES_RESERVATION_LIMIT,
• HUGETLB_RES_MAX_USAGE,
• HUGETLB_RES_RESERVATION_MAX_USAGE,
• HUGETLB_RES_FAILCNT,
• HUGETLB_RES_RESERVATION_FAILCNT,
• HUGETLB_RES_NULL,
• HUGETLB_RES_MAX,

+};

Please add information on what these track. As an example HUGETLB_RES_RESERVATION_LIMIT is so close to HUGETLB_RES_LIMIT

What are we tracking and measuring?

• #define HSTATE_NAME_LEN 32 /* Defines one hugetlb page size */ struct hstate {

@@ -340,7 +354,7 @@ struct hstate { unsigned int surplus_huge_pages_node[MAX_NUMNODES]; #ifdef CONFIG_CGROUP_HUGETLB /* cgroup control files */

• struct cftype cgroup_files[5];

• struct cftype cgroup_files[HUGETLB_RES_MAX]; #endif char name[HSTATE_NAME_LEN]; };

diff --git a/mm/hugetlb_cgroup.c b/mm/hugetlb_cgroup.c index 68c2f2f3c05b7..51a72624bd1ff 100644 --- a/mm/hugetlb_cgroup.c +++ b/mm/hugetlb_cgroup.c @@ -25,6 +25,10 @@ struct hugetlb_cgroup { * the counter to account for hugepages from hugetlb. */ struct page_counter hugepage[HUGE_MAX_HSTATE];

• /*

• * the counter to account for hugepage reservations from hugetlb.
  

• */
  

• struct page_counter reserved_hugepage[HUGE_MAX_HSTATE]; };

  #define MEMFILE_PRIVATE(x, val) (((x) << 16) | (val))

@@ -33,6 +37,15 @@ struct hugetlb_cgroup {

static struct hugetlb_cgroup *root_h_cgroup __read_mostly;

+static inline +struct page_counter *hugetlb_cgroup_get_counter(struct hugetlb_cgroup *h_cg, int idx,

• 		 bool reserved)
  

+{

• if (reserved)

• return  &h_cg->reserved_hugepage[idx];
  

• return &h_cg->hugepage[idx];

+}

• static inline struct hugetlb_cgroup *hugetlb_cgroup_from_css(struct cgroup_subsys_state *s) {

@@ -254,30 +267,33 @@ void hugetlb_cgroup_uncharge_cgroup(int idx, unsigned long nr_pages, return; }

-enum {

• RES_USAGE,
• RES_LIMIT,
• RES_MAX_USAGE,
• RES_FAILCNT,

-};

• static u64 hugetlb_cgroup_read_u64(struct cgroup_subsys_state *css, struct cftype *cft) { struct page_counter *counter;

• struct page_counter *reserved_counter; struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_css(css);

  counter = &h_cg->hugepage[MEMFILE_IDX(cft->private)];

• reserved_counter = &h_cg->reserved_hugepage[MEMFILE_IDX(cft->private)];

  switch (MEMFILE_ATTR(cft->private)) {

• case RES_USAGE:

• case HUGETLB_RES_USAGE: return (u64)page_counter_read(counter) * PAGE_SIZE;

• case RES_LIMIT:

• case HUGETLB_RES_RESERVATION_USAGE:

• return (u64)page_counter_read(reserved_counter) * PAGE_SIZE;
  

• case HUGETLB_RES_LIMIT: return (u64)counter->max * PAGE_SIZE;

• case RES_MAX_USAGE:

• case HUGETLB_RES_RESERVATION_LIMIT:

• return (u64)reserved_counter->max * PAGE_SIZE;
  

• case HUGETLB_RES_MAX_USAGE: return (u64)counter->watermark * PAGE_SIZE;

• case RES_FAILCNT:

• case HUGETLB_RES_RESERVATION_MAX_USAGE:

• return (u64)reserved_counter->watermark * PAGE_SIZE;
  

• case HUGETLB_RES_FAILCNT: return counter->failcnt;
• case HUGETLB_RES_RESERVATION_FAILCNT:

• return reserved_counter->failcnt;
  

  default: BUG(); }

@@ -291,6 +307,7 @@ static ssize_t hugetlb_cgroup_write(struct kernfs_open_file *of, int ret, idx; unsigned long nr_pages; struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_css(of_css(of));

• bool reserved = false;

  if (hugetlb_cgroup_is_root(h_cg)) /* Can't set limit on root */ return -EINVAL;

@@ -304,9 +321,13 @@ static ssize_t hugetlb_cgroup_write(struct kernfs_open_file *of, nr_pages = round_down(nr_pages, 1 << huge_page_order(&hstates[idx]));

switch (MEMFILE_ATTR(of_cft(of)->private)) {

• case RES_LIMIT:

• case HUGETLB_RES_RESERVATION_LIMIT:

• reserved = true;
  

• /* Fall through. */
  

• case HUGETLB_RES_LIMIT: mutex_lock(&hugetlb_limit_mutex);

• ret = page_counter_set_max(&h_cg->hugepage[idx], nr_pages);
  

• ret = page_counter_set_max(hugetlb_cgroup_get_counter(h_cg, idx, reserved),
  

• 			   nr_pages);
  

  mutex_unlock(&hugetlb_limit_mutex); break; default:

@@ -320,18 +341,26 @@ static ssize_t hugetlb_cgroup_reset(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { int ret = 0;

• struct page_counter *counter;

• struct page_counter *counter, *reserved_counter; struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_css(of_css(of));

  counter = &h_cg->hugepage[MEMFILE_IDX(of_cft(of)->private)];

• reserved_counter = &h_cg->reserved_hugepage[

• MEMFILE_IDX(of_cft(of)->private)];
  
  

Please indent this. It is hard to read.

switch (MEMFILE_ATTR(of_cft(of)->private)) {

• case RES_MAX_USAGE:

• case HUGETLB_RES_MAX_USAGE: page_counter_reset_watermark(counter); break;

• case RES_FAILCNT:

• case HUGETLB_RES_RESERVATION_MAX_USAGE:

• page_counter_reset_watermark(reserved_counter);
  

• break;
  

• case HUGETLB_RES_FAILCNT: counter->failcnt = 0; break;
• case HUGETLB_RES_RESERVATION_FAILCNT:

• reserved_counter->failcnt = 0;
  

• break;
  

  default: ret = -EINVAL; break;

@@ -357,37 +386,67 @@ static void __init __hugetlb_cgroup_file_init(int idx) struct hstate *h = &hstates[idx];

/* format the size */

• mem_fmt(buf, 32, huge_page_size(h));

• mem_fmt(buf, sizeof(buf), huge_page_size(h));

  /* Add the limit file */

• cft = &h->cgroup_files[0];

• cft = &h->cgroup_files[HUGETLB_RES_LIMIT]; snprintf(cft->name, MAX_CFTYPE_NAME, "%s.limit_in_bytes", buf);

• cft->private = MEMFILE_PRIVATE(idx, RES_LIMIT);

• cft->private = MEMFILE_PRIVATE(idx, HUGETLB_RES_LIMIT);

• cft->read_u64 = hugetlb_cgroup_read_u64;

• cft->write = hugetlb_cgroup_write;

• /* Add the reservation limit file */

• cft = &h->cgroup_files[HUGETLB_RES_RESERVATION_LIMIT];

• snprintf(cft->name, MAX_CFTYPE_NAME, "%s.reservation_limit_in_bytes",

•  buf);
  

• cft->private = MEMFILE_PRIVATE(idx, HUGETLB_RES_RESERVATION_LIMIT); cft->read_u64 = hugetlb_cgroup_read_u64; cft->write = hugetlb_cgroup_write;

  /* Add the usage file */

• cft = &h->cgroup_files[1];

• cft = &h->cgroup_files[HUGETLB_RES_USAGE]; snprintf(cft->name, MAX_CFTYPE_NAME, "%s.usage_in_bytes", buf);

• cft->private = MEMFILE_PRIVATE(idx, RES_USAGE);

• cft->private = MEMFILE_PRIVATE(idx, HUGETLB_RES_USAGE);
• cft->read_u64 = hugetlb_cgroup_read_u64;
• /* Add the reservation usage file */
• cft = &h->cgroup_files[HUGETLB_RES_RESERVATION_USAGE];
• snprintf(cft->name, MAX_CFTYPE_NAME, "%s.reservation_usage_in_bytes",

• 	buf);
  

Please line buf with cft->name for readability.

• cft->private = MEMFILE_PRIVATE(idx, HUGETLB_RES_RESERVATION_USAGE); cft->read_u64 = hugetlb_cgroup_read_u64;

  /* Add the MAX usage file */

• cft = &h->cgroup_files[2];

• cft = &h->cgroup_files[HUGETLB_RES_MAX_USAGE]; snprintf(cft->name, MAX_CFTYPE_NAME, "%s.max_usage_in_bytes", buf);

• cft->private = MEMFILE_PRIVATE(idx, RES_MAX_USAGE);

• cft->private = MEMFILE_PRIVATE(idx, HUGETLB_RES_MAX_USAGE);
• cft->write = hugetlb_cgroup_reset;
• cft->read_u64 = hugetlb_cgroup_read_u64;
• /* Add the MAX reservation usage file */
• cft = &h->cgroup_files[HUGETLB_RES_RESERVATION_MAX_USAGE];
• snprintf(cft->name, MAX_CFTYPE_NAME,

• 	"%s.reservation_max_usage_in_bytes", buf);
  

Same here.

• cft->private = MEMFILE_PRIVATE(idx, HUGETLB_RES_RESERVATION_MAX_USAGE); cft->write = hugetlb_cgroup_reset; cft->read_u64 = hugetlb_cgroup_read_u64;

  /* Add the failcntfile */

• cft = &h->cgroup_files[3];

• cft = &h->cgroup_files[HUGETLB_RES_FAILCNT]; snprintf(cft->name, MAX_CFTYPE_NAME, "%s.failcnt", buf);

• cft->private = MEMFILE_PRIVATE(idx, RES_FAILCNT);

• cft->private = MEMFILE_PRIVATE(idx, HUGETLB_RES_FAILCNT);

• cft->write = hugetlb_cgroup_reset;

• cft->read_u64 = hugetlb_cgroup_read_u64;

• /* Add the reservation failcntfile */

• cft = &h->cgroup_files[HUGETLB_RES_RESERVATION_FAILCNT];

• snprintf(cft->name, MAX_CFTYPE_NAME, "%s.reservation_failcnt", buf);

• cft->private = MEMFILE_PRIVATE(idx, HUGETLB_RES_RESERVATION_FAILCNT); cft->write = hugetlb_cgroup_reset; cft->read_u64 = hugetlb_cgroup_read_u64;

  /* NULL terminate the last cft */

• cft = &h->cgroup_files[4];

• cft = &h->cgroup_files[HUGETLB_RES_NULL]; memset(cft, 0, sizeof(*cft));

  WARN_ON(cgroup_add_legacy_cftypes(&hugetlb_cgrp_subsys,

-- 2.23.0.162.g0b9fbb3734-goog

thanks, -- Shuah

On 9/10/19 5:31 PM, Mina Almasry wrote:

The tests use both shared and private mapped hugetlb memory, and monitors the hugetlb usage counter as well as the hugetlb reservation counter. They test different configurations such as hugetlb memory usage via hugetlbfs, or MAP_HUGETLB, or shmget/shmat, and with and without MAP_POPULATE.

Signed-off-by: Mina Almasry almasrymina@google.com

tools/testing/selftests/vm/.gitignore | 1 + tools/testing/selftests/vm/Makefile | 4 + .../selftests/vm/charge_reserved_hugetlb.sh | 440 ++++++++++++++++++ .../selftests/vm/write_hugetlb_memory.sh | 22 + .../testing/selftests/vm/write_to_hugetlbfs.c | 252 ++++++++++ 5 files changed, 719 insertions(+) create mode 100755 tools/testing/selftests/vm/charge_reserved_hugetlb.sh create mode 100644 tools/testing/selftests/vm/write_hugetlb_memory.sh create mode 100644 tools/testing/selftests/vm/write_to_hugetlbfs.c

diff --git a/tools/testing/selftests/vm/.gitignore b/tools/testing/selftests/vm/.gitignore index 31b3c98b6d34d..d3bed9407773c 100644 --- a/tools/testing/selftests/vm/.gitignore +++ b/tools/testing/selftests/vm/.gitignore @@ -14,3 +14,4 @@ virtual_address_range gup_benchmark va_128TBswitch map_fixed_noreplace +write_to_hugetlbfs diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile index 9534dc2bc9295..8d37d5409b52c 100644 --- a/tools/testing/selftests/vm/Makefile +++ b/tools/testing/selftests/vm/Makefile @@ -18,6 +18,7 @@ TEST_GEN_FILES += transhuge-stress TEST_GEN_FILES += userfaultfd TEST_GEN_FILES += va_128TBswitch TEST_GEN_FILES += virtual_address_range +TEST_GEN_FILES += write_to_hugetlbfs

TEST_PROGS := run_vmtests

@@ -29,3 +30,6 @@ include ../lib.mk $(OUTPUT)/userfaultfd: LDLIBS += -lpthread

$(OUTPUT)/mlock-random-test: LDLIBS += -lcap

+# Why does adding $(OUTPUT)/ like above not apply this flag..?

Can you verify the following and remove this comment, once you figure out if you need $(OUTPUT)/

+write_to_hugetlbfs: CFLAGS += -static

It should. Did you test "make O=" and "KBUILD_OUTPUT" kselftest use-cases?

diff --git a/tools/testing/selftests/vm/charge_reserved_hugetlb.sh b/tools/testing/selftests/vm/charge_reserved_hugetlb.sh new file mode 100755 index 0000000000000..09e90e8f6fab4 --- /dev/null +++ b/tools/testing/selftests/vm/charge_reserved_hugetlb.sh @@ -0,0 +1,440 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0

+set -e

+cgroup_path=/dev/cgroup/memory +if [[ ! -e $cgroup_path ]]; then

•  mkdir -p $cgroup_path
  

•  mount -t cgroup -o hugetlb,memory cgroup $cgroup_path
  

+fi

Does this test need root access? If yes, please add root check and skip the test when a non-root runs the test.

+cleanup () {

• echo $$ > $cgroup_path/tasks
• set +e
• if [[ "$(pgrep write_to_hugetlbfs)" != "" ]]; then

•      kill -2 write_to_hugetlbfs
  

•      # Wait for hugetlbfs memory to get depleted.
  

•      sleep 0.5
  

This time looks arbitrary. How can you be sure it gets depleted? Is there another way to check for it.

• fi
• set -e
• if [[ -e /mnt/huge ]]; then

•      rm -rf /mnt/huge/*
  

•      umount /mnt/huge || echo error
  

•      rmdir /mnt/huge
  

• fi
• if [[ -e $cgroup_path/hugetlb_cgroup_test ]]; then

•      rmdir $cgroup_path/hugetlb_cgroup_test
  

• fi
• if [[ -e $cgroup_path/hugetlb_cgroup_test1 ]]; then

•      rmdir $cgroup_path/hugetlb_cgroup_test1
  

• fi
• if [[ -e $cgroup_path/hugetlb_cgroup_test2 ]]; then

•      rmdir $cgroup_path/hugetlb_cgroup_test2
  

• fi
• echo 0 > /proc/sys/vm/nr_hugepages
• echo CLEANUP DONE

+}

+cleanup

+function expect_equal() {

•  local expected="$1"
  

•  local actual="$2"
  

•  local error="$3"
  

•  if [[ "$expected" != "$actual" ]]; then
  

•    echo "expected ($expected) != actual ($actual): $3"
  

•    cleanup
  

•    exit 1
  

•  fi
  

+}

+function setup_cgroup() {

•  local name="$1"
  

•  local cgroup_limit="$2"
  

•  local reservation_limit="$3"
  

•  mkdir $cgroup_path/$name
  

•  echo writing cgroup limit: "$cgroup_limit"
  

•  echo "$cgroup_limit" > $cgroup_path/$name/hugetlb.2MB.limit_in_bytes
  

•  echo writing reseravation limit: "$reservation_limit"
  

•  echo "$reservation_limit" > \
  

•    $cgroup_path/$name/hugetlb.2MB.reservation_limit_in_bytes
  

•  echo 0 > $cgroup_path/$name/cpuset.cpus
  

•  echo 0 > $cgroup_path/$name/cpuset.mems
  

+}

+function write_hugetlbfs_and_get_usage() {

•  local cgroup="$1"
  

•  local size="$2"
  

•  local populate="$3"
  

•  local write="$4"
  

•  local path="$5"
  

•  local method="$6"
  

•  local private="$7"
  

•  local expect_failure="$8"
  

•  # Function return values.
  

•  reservation_failed=0
  

•  oom_killed=0
  

•  hugetlb_difference=0
  

•  reserved_difference=0
  

•  local hugetlb_usage=$cgroup_path/$cgroup/hugetlb.2MB.usage_in_bytes
  

•  local reserved_usage=$cgroup_path/$cgroup/hugetlb.2MB.reservation_usage_in_bytes
  

•  local hugetlb_before=$(cat $hugetlb_usage)
  

•  local reserved_before=$(cat $reserved_usage)
  

•  echo
  

•  echo Starting:
  

•  echo hugetlb_usage="$hugetlb_before"
  

•  echo reserved_usage="$reserved_before"
  

•  echo expect_failure is "$expect_failure"
  

•  set +e
  

•  if [[ "$method" == "1" ]] || [[ "$method" == 2 ]] || \
  

•    [[ "$private" == "-r" ]] && [[ "$expect_failure" != 1 ]]; then
  

•    bash write_hugetlb_memory.sh "$size" "$populate" "$write" \
  

•   "$cgroup"  "$path" "$method" "$private" "-l" &
  

•    local write_result=$?
  

•    # This sleep is to make sure that the script above has had enough
  

•    # time to do its thing, since it runs in the background. This may
  

•    # cause races...
  

•    sleep 0.5
  

I am not happy with these arbitrary sleep times, especially coupled with the comment about races above. :)

•    echo write_result is $write_result
  

•  else
  

•    bash write_hugetlb_memory.sh "$size" "$populate" "$write" \
  

•   "$cgroup"  "$path" "$method" "$private"
  

•    local write_result=$?
  

•  fi
  

•  set -e
  

•  if [[ "$write_result" == 1 ]]; then
  

•    reservation_failed=1
  

•  fi
  

•  # On linus/master, the above process gets SIGBUS'd on oomkill, with
  

•  # return code 135. On earlier kernels, it gets actual oomkill, with return
  

•  # code 137, so just check for both conditions incase we're testing against
  

in case

•  # an earlier kernel.
  

•  if [[ "$write_result" == 135 ]] || [[ "$write_result" == 137 ]]; then
  

Please add defines for these return values.

•    oom_killed=1
  

•  fi
  

•  local hugetlb_after=$(cat $hugetlb_usage)
  

•  local reserved_after=$(cat $reserved_usage)
  

•  echo After write:
  

•  echo hugetlb_usage="$hugetlb_after"
  

•  echo reserved_usage="$reserved_after"
  

•  hugetlb_difference=$(($hugetlb_after - $hugetlb_before))
  

•  reserved_difference=$(($reserved_after - $reserved_before))
  

+}

+function cleanup_hugetlb_memory() {

•  set +e
  

•  if [[ "$(pgrep write_to_hugetlbfs)" != "" ]]; then
  

•    echo kiling write_to_hugetlbfs
  

•    killall -2 write_to_hugetlbfs
  

•    # Wait for hugetlbfs memory to get depleted.
  

•    sleep 0.5
  

Sleep time? Rationale for this number?

•  fi
  

•  set -e
  

•  if [[ -e /mnt/huge ]]; then
  

•    rm -rf /mnt/huge/*
  

•      umount /mnt/huge
  

•      rmdir /mnt/huge
  

•  fi
  

+}

+function run_test() {

•  local size="$1"
  

•  local populate="$2"
  

•  local write="$3"
  

•  local cgroup_limit="$4"
  

•  local reservation_limit="$5"
  

•  local nr_hugepages="$6"
  

•  local method="$7"
  

•  local private="$8"
  

•  local expect_failure="$9"
  

•  # Function return values.
  

•  hugetlb_difference=0
  

•  reserved_difference=0
  

•  reservation_failed=0
  

•  oom_killed=0
  

•  echo nr hugepages = "$nr_hugepages"
  

•  echo "$nr_hugepages" > /proc/sys/vm/nr_hugepages
  

•  setup_cgroup "hugetlb_cgroup_test" "$cgroup_limit" "$reservation_limit"
  

•  mkdir -p /mnt/huge
  

•  mount -t hugetlbfs \
  

•    -o pagesize=2M,size=256M none /mnt/huge
  

•  write_hugetlbfs_and_get_usage "hugetlb_cgroup_test" "$size" "$populate" \
  

•    "$write" "/mnt/huge/test" "$method" "$private" "$expect_failure"
  

•  cleanup_hugetlb_memory
  

•  local final_hugetlb=$(cat $cgroup_path/hugetlb_cgroup_test/hugetlb.2MB.usage_in_bytes)
  

•  local final_reservation=$(cat $cgroup_path/hugetlb_cgroup_test/hugetlb.2MB.reservation_usage_in_bytes)
  

•  expect_equal "0" "$final_hugetlb" "final hugetlb is not zero"
  

•  expect_equal "0" "$final_reservation" "final reservation is not zero"
  

+}

+function run_multiple_cgroup_test() {

•  local size1="$1"
  

•  local populate1="$2"
  

•  local write1="$3"
  

•  local cgroup_limit1="$4"
  

•  local reservation_limit1="$5"
  

•  local size2="$6"
  

•  local populate2="$7"
  

•  local write2="$8"
  

•  local cgroup_limit2="$9"
  

•  local reservation_limit2="${10}"
  

•  local nr_hugepages="${11}"
  

•  local method="${12}"
  

•  local private="${13}"
  

•  local expect_failure="${14}"
  

•  # Function return values.
  

•  hugetlb_difference1=0
  

•  reserved_difference1=0
  

•  reservation_failed1=0
  

•  oom_killed1=0
  

•  hugetlb_difference2=0
  

•  reserved_difference2=0
  

•  reservation_failed2=0
  

•  oom_killed2=0
  

•  echo nr hugepages = "$nr_hugepages"
  

•  echo "$nr_hugepages" > /proc/sys/vm/nr_hugepages
  

•  setup_cgroup "hugetlb_cgroup_test1" "$cgroup_limit1" "$reservation_limit1"
  

•  setup_cgroup "hugetlb_cgroup_test2" "$cgroup_limit2" "$reservation_limit2"
  

•  mkdir -p /mnt/huge
  

•  mount -t hugetlbfs \
  

•    -o pagesize=2M,size=256M none /mnt/huge
  

•  write_hugetlbfs_and_get_usage "hugetlb_cgroup_test1" "$size1" \
  

•    "$populate1" "$write1" "/mnt/huge/test1" "$method" "$private" \
  

•    "$expect_failure"
  

•  hugetlb_difference1=$hugetlb_difference
  

•  reserved_difference1=$reserved_difference
  

•  reservation_failed1=$reservation_failed
  

•  oom_killed1=$oom_killed
  

•  local cgroup1_hugetlb_usage=$cgroup_path/hugetlb_cgroup_test1/hugetlb.2MB.usage_in_bytes
  

•  local cgroup1_reservation_usage=$cgroup_path/hugetlb_cgroup_test1/hugetlb.2MB.reservation_usage_in_bytes
  

•  local cgroup2_hugetlb_usage=$cgroup_path/hugetlb_cgroup_test2/hugetlb.2MB.usage_in_bytes
  

•  local cgroup2_reservation_usage=$cgroup_path/hugetlb_cgroup_test2/hugetlb.2MB.reservation_usage_in_bytes
  

•  local usage_before_second_write=$(cat $cgroup1_hugetlb_usage)
  

•  local reservation_usage_before_second_write=$(cat \
  

•    $cgroup1_reservation_usage)
  

•  write_hugetlbfs_and_get_usage "hugetlb_cgroup_test2" "$size2" \
  

•    "$populate2" "$write2" "/mnt/huge/test2" "$method" "$private" \
  

•    "$expect_failure"
  

•  hugetlb_difference2=$hugetlb_difference
  

•  reserved_difference2=$reserved_difference
  

•  reservation_failed2=$reservation_failed
  

•  oom_killed2=$oom_killed
  

•  expect_equal "$usage_before_second_write" \
  

•    "$(cat $cgroup1_hugetlb_usage)" "Usage changed."
  

•  expect_equal "$reservation_usage_before_second_write" \
  

•    "$(cat $cgroup1_reservation_usage)" "Reservation usage changed."
  

•  cleanup_hugetlb_memory
  

•  local final_hugetlb=$(cat $cgroup1_hugetlb_usage)
  

•  local final_reservation=$(cat $cgroup1_reservation_usage)
  

•  expect_equal "0" "$final_hugetlb" \
  

•    "hugetlbt_cgroup_test1 final hugetlb is not zero"
  

•  expect_equal "0" "$final_reservation" \
  

•    "hugetlbt_cgroup_test1 final reservation is not zero"
  

•  local final_hugetlb=$(cat $cgroup2_hugetlb_usage)
  

•  local final_reservation=$(cat $cgroup2_reservation_usage)
  

•  expect_equal "0" "$final_hugetlb" \
  

•    "hugetlb_cgroup_test2 final hugetlb is not zero"
  

•  expect_equal "0" "$final_reservation" \
  

•    "hugetlb_cgroup_test2 final reservation is not zero"
  

+}

+for private in "" "-r" ; do +for populate in "" "-o"; do +for method in 0 1 2; do

+# Skip mmap(MAP_HUGETLB | MAP_SHARED). Doesn't seem to be supported. +if [[ "$method" == 1 ]] && [[ "$private" == "" ]]; then

•  continue
  

+fi

+# Skip populated shmem tests. Doesn't seem to be supported. +if [[ "$method" == 2"" ]] && [[ "$populate" == "-o" ]]; then

•  continue
  

+fi

+cleanup +echo +echo +echo +echo Test normal case. +echo private=$private, populate=$populate, method=$method +run_test $((10 * 1024 * 1024)) "$populate" "" $((20 * 1024 * 1024)) \

•  $((20 * 1024 * 1024)) 10 "$method" "$private" "0"
  

+echo Memory charged to hugtlb=$hugetlb_difference +echo Memory charged to reservation=$reserved_difference

+if [[ "$populate" == "-o" ]]; then

•  expect_equal "$((10 * 1024 * 1024))" "$hugetlb_difference" \
  

•    "Reserved memory charged to hugetlb cgroup."
  

+else

•  expect_equal "0" "$hugetlb_difference" \
  

•    "Reserved memory charged to hugetlb cgroup."
  

+fi

+expect_equal "$((10 * 1024 * 1024))" "$reserved_difference" \

•  "Reserved memory not charged to reservation usage."
  

+echo 'PASS'

+cleanup +echo +echo +echo +echo Test normal case with write. +echo private=$private, populate=$populate, method=$method +run_test $((10 * 1024 * 1024)) "$populate" '-w' $((20 * 1024 * 1024)) \

•  $((20 * 1024 * 1024)) 10 "$method" "$private" "0"
  

+echo Memory charged to hugtlb=$hugetlb_difference +echo Memory charged to reservation=$reserved_difference

+expect_equal "$((10 * 1024 * 1024))" "$hugetlb_difference" \

•  "Reserved memory charged to hugetlb cgroup."
  

+expect_equal "$((10 * 1024 * 1024))" "$reserved_difference" \

•  "Reserved memory not charged to reservation usage."
  

+echo 'PASS'

+cleanup +echo +echo +echo +echo Test more than reservation case. +echo private=$private, populate=$populate, method=$method +run_test "$((10 * 1024 * 1024))" "$populate" '' "$((20 * 1024 * 1024))" \

•  "$((5 * 1024 * 1024))" "10" "$method" "$private" "1"
  

+expect_equal "1" "$reservation_failed" "Reservation succeeded." +echo 'PASS'

+cleanup

+echo +echo +echo +echo Test more than cgroup limit case. +echo private=$private, populate=$populate, method=$method

+# Not sure if shm memory can be cleaned up when the process gets sigbus'd. +if [[ "$method" != 2 ]]; then

•  run_test $((10 * 1024 * 1024)) "$populate" "-w" $((5 * 1024 * 1024)) \
  

•    $((20 * 1024 * 1024)) 10 "$method" "$private" "1"
  

•  expect_equal "1" "$oom_killed" "Not oom killed."
  

+fi +echo 'PASS'

+cleanup

+echo +echo +echo +echo Test normal case, multiple cgroups. +echo private=$private, populate=$populate, method=$method +run_multiple_cgroup_test "$((6 * 1024 * 1024))" "$populate" "" \

•  "$((20 * 1024 * 1024))" "$((20 * 1024 * 1024))" "$((10 * 1024 * 1024))" \
  

•  "$populate" "" "$((20 * 1024 * 1024))" "$((20 * 1024 * 1024))" "10" \
  

•  "$method" "$private" "0"
  

+echo Memory charged to hugtlb1=$hugetlb_difference1 +echo Memory charged to reservation1=$reserved_difference1 +echo Memory charged to hugtlb2=$hugetlb_difference2 +echo Memory charged to reservation2=$reserved_difference2

+expect_equal "$((6 * 1024 * 1024))" "$reserved_difference1" \

•  "Incorrect reservations charged to cgroup 1."
  

+expect_equal "$((10 * 1024 * 1024))" "$reserved_difference2" \

•  "Incorrect reservation charged to cgroup 2."
  

+if [[ "$populate" == "-o" ]]; then

•  expect_equal "$((6 * 1024 * 1024))" "$hugetlb_difference1" \
  

•    "Incorrect hugetlb charged to cgroup 1."
  

•  expect_equal "$((10 * 1024 * 1024))" "$hugetlb_difference2" \
  

•    "Incorrect hugetlb charged to cgroup 2."
  

+else

•  expect_equal "0" "$hugetlb_difference1" \
  

•    "Incorrect hugetlb charged to cgroup 1."
  

•  expect_equal "0" "$hugetlb_difference2" \
  

•    "Incorrect hugetlb charged to cgroup 2."
  

+fi +echo 'PASS'

+cleanup +echo +echo +echo +echo Test normal case with write, multiple cgroups. +echo private=$private, populate=$populate, method=$method +run_multiple_cgroup_test "$((6 * 1024 * 1024))" "$populate" "-w" \

•  "$((20 * 1024 * 1024))" "$((20 * 1024 * 1024))" "$((10 * 1024 * 1024))" \
  

•  "$populate" "-w" "$((20 * 1024 * 1024))" "$((20 * 1024 * 1024))" "10" \
  

•  "$method" "$private" "0"
  

+echo Memory charged to hugtlb1=$hugetlb_difference1 +echo Memory charged to reservation1=$reserved_difference1 +echo Memory charged to hugtlb2=$hugetlb_difference2 +echo Memory charged to reservation2=$reserved_difference2

+expect_equal "$((6 * 1024 * 1024))" "$hugetlb_difference1" \

•  "Incorrect hugetlb charged to cgroup 1."
  

+expect_equal "$((6 * 1024 * 1024))" "$reserved_difference1" \

•  "Incorrect reservation charged to cgroup 1."
  

+expect_equal "$((10 * 1024 * 1024))" "$hugetlb_difference2" \

•  "Incorrect hugetlb charged to cgroup 2."
  

+expect_equal "$((10 * 1024 * 1024))" "$reserved_difference2" \

•  "Incorrected reservation charged to cgroup 2."
  

+echo 'PASS'

+done # private +done # populate +done # method

+umount $cgroup_path +rmdir $cgroup_path diff --git a/tools/testing/selftests/vm/write_hugetlb_memory.sh b/tools/testing/selftests/vm/write_hugetlb_memory.sh new file mode 100644 index 0000000000000..08f5fa5527cfd --- /dev/null +++ b/tools/testing/selftests/vm/write_hugetlb_memory.sh @@ -0,0 +1,22 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0

+set -e

+size=$1 +populate=$2 +write=$3 +cgroup=$4 +path=$5 +method=$6 +private=$7 +want_sleep=$8

+echo "Putting task in cgroup '$cgroup'" +echo $$ > /dev/cgroup/memory/"$cgroup"/tasks

+echo "Method is $method"

+set +e +./write_to_hugetlbfs -p "$path" -s "$size" "$write" "$populate" -m "$method" \

•  "$private" "$want_sleep"
  

diff --git a/tools/testing/selftests/vm/write_to_hugetlbfs.c b/tools/testing/selftests/vm/write_to_hugetlbfs.c new file mode 100644 index 0000000000000..f02a897427a97 --- /dev/null +++ b/tools/testing/selftests/vm/write_to_hugetlbfs.c @@ -0,0 +1,252 @@ +// SPDX-License-Identifier: GPL-2.0 +/*

• • This program reserves and uses hugetlb memory, supporting a bunch of
• • scenorios needed by the charged_reserved_hugetlb.sh test.

Spelling?

• */

+#include <err.h> +#include <errno.h> +#include <signal.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <unistd.h> +#include <fcntl.h> +#include <sys/types.h> +#include <sys/shm.h> +#include <sys/stat.h> +#include <sys/mman.h>

+/* Global definitions. */ +enum method {

• HUGETLBFS,
• MMAP_MAP_HUGETLB,
• SHM,
• MAX_METHOD

+};

+/* Global variables. */ +static const char *self; +static char *shmaddr; +static int shmid;

+/*

• • Show usage and exit.
• */

+static void exit_usage(void) +{

• printf("Usage: %s -p <path to hugetlbfs file> -s <size to map> "

• "[-m <0=hugetlbfs | 1=mmap(MAP_HUGETLB)>] [-l] [-r] "
  

• "[-o] [-w]\n", self);
  

• exit(EXIT_FAILURE);

+}

+void sig_handler(int signo) +{

• printf("Received %d.\n", signo);
• if (signo == SIGINT) {

• printf("Deleting the memory\n");
  

• if (shmdt((const void *)shmaddr) != 0) {
  

• 	perror("Detach failure");
  

• 	shmctl(shmid, IPC_RMID, NULL);
  

• 	exit(4);
  

Is this a skip error code? Please note that kselftest framework interprets this as a skipped test when returb value is 4.

• }
  

• shmctl(shmid, IPC_RMID, NULL);
  

• printf("Done deleting the memory\n");
  

• }
• exit(2);

What about this one? What does exit code 2 mean?

+}

+int main(int argc, char **argv) +{

• int fd = 0;
• int key = 0;
• int *ptr = NULL;
• int c = 0;
• int size = 0;
• char path[256] = "";
• enum method method = MAX_METHOD;
• int want_sleep = 0, private = 0;
• int populate = 0;
• int write = 0;
• unsigned long i;
• if (signal(SIGINT, sig_handler) == SIG_ERR)

• err(1, "\ncan't catch SIGINT\n");
  

• /* Parse command-line arguments. */
• setvbuf(stdout, NULL, _IONBF, 0);
• self = argv[0];
• while ((c = getopt(argc, argv, "s:p:m:owlr")) != -1) {

• switch (c) {
  

• case 's':
  

• 	size = atoi(optarg);
  

• 	break;
  

• case 'p':
  

• 	strncpy(path, optarg, sizeof(path));
  

• 	break;
  

• case 'm':
  

• 	if (atoi(optarg) >= MAX_METHOD) {
  

• 		errno = EINVAL;
  

• 		perror("Invalid -m.");
  

• 		exit_usage();
  

• 	}
  

• 	method = atoi(optarg);
  

• 	break;
  

• case 'o':
  

• 	populate = 1;
  

• 	break;
  

• case 'w':
  

• 	write = 1;
  

• 	break;
  

• case 'l':
  

• 	want_sleep = 1;
  

• 	break;
  

• case 'r':
  

• 	private = 1;
  

• 	break;
  

• default:
  

• 	errno = EINVAL;
  

• 	perror("Invalid arg");
  

• 	exit_usage();
  

• }
  

• }
• if (strncmp(path, "", sizeof(path)) != 0) {

• printf("Writing to this path: %s\n", path);
  

• } else {

• errno = EINVAL;
  

• perror("path not found");
  

• exit_usage();
  

• }
• if (size != 0) {

• printf("Writing this size: %d\n", size);
  

• } else {

• errno = EINVAL;
  

• perror("size not found");
  

• exit_usage();
  

• }
• if (!populate)

• printf("Not populating.\n");
  

• else

• printf("Populating.\n");
  

• if (!write)

• printf("Not writing to memory.\n");
  

• if (method == MAX_METHOD) {

• errno = EINVAL;
  

• perror("-m Invalid");
  

• exit_usage();
  

• } else

• printf("Using method=%d\n", method);
  

• if (!private)

• printf("Shared mapping.\n");
  

• else

• printf("Private mapping.\n");
  

• switch (method) {
• case HUGETLBFS:

• printf("Allocating using HUGETLBFS.\n");
  

• fd = open(path, O_CREAT | O_RDWR, 0777);
  

• if (fd == -1)
  

• 	err(1, "Failed to open file.");
  

• ptr = mmap(NULL, size, PROT_READ | PROT_WRITE,
  

• 	(private ? MAP_PRIVATE : MAP_SHARED) | (populate ?
  

• 		MAP_POPULATE : 0), fd, 0);
  

• if (ptr == MAP_FAILED) {
  

• 	close(fd);
  

• 	err(1, "Error mapping the file");
  

• }
  

• break;
  

• case MMAP_MAP_HUGETLB:

• printf("Allocating using MAP_HUGETLB.\n");
  

• ptr = mmap(NULL, size,
  

• PROT_READ | PROT_WRITE,
  

• (private ? (MAP_PRIVATE | MAP_ANONYMOUS) : MAP_SHARED) |
  

• MAP_HUGETLB | (populate ?
  

• 	MAP_POPULATE : 0),
  

• -1, 0);
  

• if (ptr == MAP_FAILED)
  

• 	err(1, "mmap");
  

• printf("Returned address is %p\n", ptr);
  

• break;
  

• case SHM:

• printf("Allocating using SHM.\n");
  

• shmid = shmget(key, size, SHM_HUGETLB | IPC_CREAT | SHM_R |
  

• 		SHM_W);
  

• if (shmid < 0) {
  

• 	shmid = shmget(++key, size, SHM_HUGETLB | IPC_CREAT |
  

• 			SHM_R | SHM_W);
  

• 	if (shmid < 0)
  

• 		err(1, "shmget");
  

• }
  

• printf("shmid: 0x%x, shmget key:%d\n", shmid, key);
  

• shmaddr = shmat(shmid, NULL, 0);
  

• if (shmaddr == (char *)-1) {
  

• 	perror("Shared memory attach failure");
  

• 	shmctl(shmid, IPC_RMID, NULL);
  

• 	exit(2);
  

• }
  

• printf("shmaddr: %p\n", shmaddr);
  

• break;
  

• default:

• errno = EINVAL;
  

• err(1, "Invalid method.");
  

• }
• if (write) {

• printf("Writing to memory.\n");
  

• if (method != SHM) {
  

• 	memset(ptr, 1, size);
  

• } else {
  

• 	printf("Starting the writes:\n");
  

• 	for (i = 0; i < size; i++) {
  

• 		shmaddr[i] = (char)(i);
  

• 		if (!(i % (1024 * 1024)))
  

• 			printf(".");
  

• 	}
  

• 	printf("\n");
  

• 	printf("Starting the Check...");
  

• 	for (i = 0; i < size; i++)
  

• 		if (shmaddr[i] != (char)i) {
  

• 			printf("\nIndex %lu mismatched\n", i);
  

• 			exit(3);
  

• 		}
  

• 	printf("Done.\n");
  

• }
  

• }
• if (want_sleep) {

• /* Signal to caller that we're done. */
  

• printf("DONE\n");
  

• /* Hold memory until external kill signal is delivered. */
  

• while (1)
  

• 	sleep(100);
  

Please don't add sleeps. This will hold up the kselftest run.

• }
• close(fd);

Is this close() necessary in all cases? Looks like MMAP_MAP_HUGETLB is the only case that opens it.

I am not sure if the error legs are correct.

• return 0;

+}

2.23.0.162.g0b9fbb3734-goog

thanks, -- Shuah

On Mon, Sep 16, 2019 at 6:52 PM shuah shuah@kernel.org wrote:

On 9/10/19 5:31 PM, Mina Almasry wrote:

...

The tests use both shared and private mapped hugetlb memory, and monitors the hugetlb usage counter as well as the hugetlb reservation counter. They test different configurations such as hugetlb memory usage via hugetlbfs, or MAP_HUGETLB, or shmget/shmat, and with and without MAP_POPULATE.

Signed-off-by: Mina Almasry almasrymina@google.com

tools/testing/selftests/vm/.gitignore | 1 + tools/testing/selftests/vm/Makefile | 4 + .../selftests/vm/charge_reserved_hugetlb.sh | 440 ++++++++++++++++++ .../selftests/vm/write_hugetlb_memory.sh | 22 + .../testing/selftests/vm/write_to_hugetlbfs.c | 252 ++++++++++ 5 files changed, 719 insertions(+) create mode 100755 tools/testing/selftests/vm/charge_reserved_hugetlb.sh create mode 100644 tools/testing/selftests/vm/write_hugetlb_memory.sh create mode 100644 tools/testing/selftests/vm/write_to_hugetlbfs.c

diff --git a/tools/testing/selftests/vm/.gitignore b/tools/testing/selftests/vm/.gitignore index 31b3c98b6d34d..d3bed9407773c 100644 --- a/tools/testing/selftests/vm/.gitignore +++ b/tools/testing/selftests/vm/.gitignore @@ -14,3 +14,4 @@ virtual_address_range gup_benchmark va_128TBswitch map_fixed_noreplace +write_to_hugetlbfs diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile index 9534dc2bc9295..8d37d5409b52c 100644 --- a/tools/testing/selftests/vm/Makefile +++ b/tools/testing/selftests/vm/Makefile @@ -18,6 +18,7 @@ TEST_GEN_FILES += transhuge-stress TEST_GEN_FILES += userfaultfd TEST_GEN_FILES += va_128TBswitch TEST_GEN_FILES += virtual_address_range +TEST_GEN_FILES += write_to_hugetlbfs

TEST_PROGS := run_vmtests

@@ -29,3 +30,6 @@ include ../lib.mk $(OUTPUT)/userfaultfd: LDLIBS += -lpthread

$(OUTPUT)/mlock-random-test: LDLIBS += -lcap

+# Why does adding $(OUTPUT)/ like above not apply this flag..?

Can you verify the following and remove this comment, once you figure out if you need $(OUTPUT)/

...

+write_to_hugetlbfs: CFLAGS += -static

It should. Did you test "make O=" and "KBUILD_OUTPUT" kselftest use-cases?

Turns out I don't need -static actually.

...

diff --git a/tools/testing/selftests/vm/charge_reserved_hugetlb.sh b/tools/testing/selftests/vm/charge_reserved_hugetlb.sh new file mode 100755 index 0000000000000..09e90e8f6fab4 --- /dev/null +++ b/tools/testing/selftests/vm/charge_reserved_hugetlb.sh @@ -0,0 +1,440 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0

+set -e

+cgroup_path=/dev/cgroup/memory +if [[ ! -e $cgroup_path ]]; then

•  mkdir -p $cgroup_path
  

•  mount -t cgroup -o hugetlb,memory cgroup $cgroup_path
  

+fi

Does this test need root access? If yes, please add root check and skip the test when a non-root runs the test.

...

+cleanup () {

• echo $$ > $cgroup_path/tasks
  

• set +e
  

• if [[ "$(pgrep write_to_hugetlbfs)" != "" ]]; then
  

•       kill -2 write_to_hugetlbfs
  

•       # Wait for hugetlbfs memory to get depleted.
  

•       sleep 0.5
  

This time looks arbitrary. How can you be sure it gets depleted? Is there another way to check for it.

...

• fi
  

• set -e
  

• if [[ -e /mnt/huge ]]; then
  

•       rm -rf /mnt/huge/*
  

•       umount /mnt/huge || echo error
  

•       rmdir /mnt/huge
  

• fi
  

• if [[ -e $cgroup_path/hugetlb_cgroup_test ]]; then
  

•       rmdir $cgroup_path/hugetlb_cgroup_test
  

• fi
  

• if [[ -e $cgroup_path/hugetlb_cgroup_test1 ]]; then
  

•       rmdir $cgroup_path/hugetlb_cgroup_test1
  

• fi
  

• if [[ -e $cgroup_path/hugetlb_cgroup_test2 ]]; then
  

•       rmdir $cgroup_path/hugetlb_cgroup_test2
  

• fi
  

• echo 0 > /proc/sys/vm/nr_hugepages
  

• echo CLEANUP DONE
  

+}

+cleanup

+function expect_equal() {

•  local expected="$1"
  

•  local actual="$2"
  

•  local error="$3"
  

•  if [[ "$expected" != "$actual" ]]; then
  

•     echo "expected ($expected) != actual ($actual): $3"
  

•     cleanup
  

•     exit 1
  

•  fi
  

+}

+function setup_cgroup() {

•  local name="$1"
  

•  local cgroup_limit="$2"
  

•  local reservation_limit="$3"
  

•  mkdir $cgroup_path/$name
  

•  echo writing cgroup limit: "$cgroup_limit"
  

•  echo "$cgroup_limit" > $cgroup_path/$name/hugetlb.2MB.limit_in_bytes
  

•  echo writing reseravation limit: "$reservation_limit"
  

•  echo "$reservation_limit" > \
  

•     $cgroup_path/$name/hugetlb.2MB.reservation_limit_in_bytes
  

•  echo 0 > $cgroup_path/$name/cpuset.cpus
  

•  echo 0 > $cgroup_path/$name/cpuset.mems
  

+}

+function write_hugetlbfs_and_get_usage() {

•  local cgroup="$1"
  

•  local size="$2"
  

•  local populate="$3"
  

•  local write="$4"
  

•  local path="$5"
  

•  local method="$6"
  

•  local private="$7"
  

•  local expect_failure="$8"
  

•  # Function return values.
  

•  reservation_failed=0
  

•  oom_killed=0
  

•  hugetlb_difference=0
  

•  reserved_difference=0
  

•  local hugetlb_usage=$cgroup_path/$cgroup/hugetlb.2MB.usage_in_bytes
  

•  local reserved_usage=$cgroup_path/$cgroup/hugetlb.2MB.reservation_usage_in_bytes
  

•  local hugetlb_before=$(cat $hugetlb_usage)
  

•  local reserved_before=$(cat $reserved_usage)
  

•  echo
  

•  echo Starting:
  

•  echo hugetlb_usage="$hugetlb_before"
  

•  echo reserved_usage="$reserved_before"
  

•  echo expect_failure is "$expect_failure"
  

•  set +e
  

•  if [[ "$method" == "1" ]] || [[ "$method" == 2 ]] || \
  

•     [[ "$private" == "-r" ]] && [[ "$expect_failure" != 1 ]]; then
  

•     bash write_hugetlb_memory.sh "$size" "$populate" "$write" \
  

•           "$cgroup"  "$path" "$method" "$private" "-l" &
  

•     local write_result=$?
  

•     # This sleep is to make sure that the script above has had enough
  

•     # time to do its thing, since it runs in the background. This may
  

•     # cause races...
  

•     sleep 0.5
  

I am not happy with these arbitrary sleep times, especially coupled with the comment about races above. :)

...

•     echo write_result is $write_result
  

•  else
  

•     bash write_hugetlb_memory.sh "$size" "$populate" "$write" \
  

•           "$cgroup"  "$path" "$method" "$private"
  

•     local write_result=$?
  

•  fi
  

•  set -e
  

•  if [[ "$write_result" == 1 ]]; then
  

•     reservation_failed=1
  

•  fi
  

•  # On linus/master, the above process gets SIGBUS'd on oomkill, with
  

•  # return code 135. On earlier kernels, it gets actual oomkill, with return
  

•  # code 137, so just check for both conditions incase we're testing against
  

in case

...

•  # an earlier kernel.
  

•  if [[ "$write_result" == 135 ]] || [[ "$write_result" == 137 ]]; then
  

Please add defines for these return values.

There is comment that explains this line. Not enough clarity?

...

•     oom_killed=1
  

•  fi
  

•  local hugetlb_after=$(cat $hugetlb_usage)
  

•  local reserved_after=$(cat $reserved_usage)
  

•  echo After write:
  

•  echo hugetlb_usage="$hugetlb_after"
  

•  echo reserved_usage="$reserved_after"
  

•  hugetlb_difference=$(($hugetlb_after - $hugetlb_before))
  

•  reserved_difference=$(($reserved_after - $reserved_before))
  

+}

+function cleanup_hugetlb_memory() {

•  set +e
  

•  if [[ "$(pgrep write_to_hugetlbfs)" != "" ]]; then
  

•     echo kiling write_to_hugetlbfs
  

•     killall -2 write_to_hugetlbfs
  

•     # Wait for hugetlbfs memory to get depleted.
  

•     sleep 0.5
  

Sleep time? Rationale for this number?

...

•  fi
  

•  set -e
  

•  if [[ -e /mnt/huge ]]; then
  

•     rm -rf /mnt/huge/*
  

•       umount /mnt/huge
  

•       rmdir /mnt/huge
  

•  fi
  

+}

+function run_test() {

•  local size="$1"
  

•  local populate="$2"
  

•  local write="$3"
  

•  local cgroup_limit="$4"
  

•  local reservation_limit="$5"
  

•  local nr_hugepages="$6"
  

•  local method="$7"
  

•  local private="$8"
  

•  local expect_failure="$9"
  

•  # Function return values.
  

•  hugetlb_difference=0
  

•  reserved_difference=0
  

•  reservation_failed=0
  

•  oom_killed=0
  

•  echo nr hugepages = "$nr_hugepages"
  

•  echo "$nr_hugepages" > /proc/sys/vm/nr_hugepages
  

•  setup_cgroup "hugetlb_cgroup_test" "$cgroup_limit" "$reservation_limit"
  

•  mkdir -p /mnt/huge
  

•  mount -t hugetlbfs \
  

•     -o pagesize=2M,size=256M none /mnt/huge
  

•  write_hugetlbfs_and_get_usage "hugetlb_cgroup_test" "$size" "$populate" \
  

•     "$write" "/mnt/huge/test" "$method" "$private" "$expect_failure"
  

•  cleanup_hugetlb_memory
  

•  local final_hugetlb=$(cat $cgroup_path/hugetlb_cgroup_test/hugetlb.2MB.usage_in_bytes)
  

•  local final_reservation=$(cat $cgroup_path/hugetlb_cgroup_test/hugetlb.2MB.reservation_usage_in_bytes)
  

•  expect_equal "0" "$final_hugetlb" "final hugetlb is not zero"
  

•  expect_equal "0" "$final_reservation" "final reservation is not zero"
  

+}

+function run_multiple_cgroup_test() {

•  local size1="$1"
  

•  local populate1="$2"
  

•  local write1="$3"
  

•  local cgroup_limit1="$4"
  

•  local reservation_limit1="$5"
  

•  local size2="$6"
  

•  local populate2="$7"
  

•  local write2="$8"
  

•  local cgroup_limit2="$9"
  

•  local reservation_limit2="${10}"
  

•  local nr_hugepages="${11}"
  

•  local method="${12}"
  

•  local private="${13}"
  

•  local expect_failure="${14}"
  

•  # Function return values.
  

•  hugetlb_difference1=0
  

•  reserved_difference1=0
  

•  reservation_failed1=0
  

•  oom_killed1=0
  

•  hugetlb_difference2=0
  

•  reserved_difference2=0
  

•  reservation_failed2=0
  

•  oom_killed2=0
  

•  echo nr hugepages = "$nr_hugepages"
  

•  echo "$nr_hugepages" > /proc/sys/vm/nr_hugepages
  

•  setup_cgroup "hugetlb_cgroup_test1" "$cgroup_limit1" "$reservation_limit1"
  

•  setup_cgroup "hugetlb_cgroup_test2" "$cgroup_limit2" "$reservation_limit2"
  

•  mkdir -p /mnt/huge
  

•  mount -t hugetlbfs \
  

•     -o pagesize=2M,size=256M none /mnt/huge
  

•  write_hugetlbfs_and_get_usage "hugetlb_cgroup_test1" "$size1" \
  

•     "$populate1" "$write1" "/mnt/huge/test1" "$method" "$private" \
  

•     "$expect_failure"
  

•  hugetlb_difference1=$hugetlb_difference
  

•  reserved_difference1=$reserved_difference
  

•  reservation_failed1=$reservation_failed
  

•  oom_killed1=$oom_killed
  

•  local cgroup1_hugetlb_usage=$cgroup_path/hugetlb_cgroup_test1/hugetlb.2MB.usage_in_bytes
  

•  local cgroup1_reservation_usage=$cgroup_path/hugetlb_cgroup_test1/hugetlb.2MB.reservation_usage_in_bytes
  

•  local cgroup2_hugetlb_usage=$cgroup_path/hugetlb_cgroup_test2/hugetlb.2MB.usage_in_bytes
  

•  local cgroup2_reservation_usage=$cgroup_path/hugetlb_cgroup_test2/hugetlb.2MB.reservation_usage_in_bytes
  

•  local usage_before_second_write=$(cat $cgroup1_hugetlb_usage)
  

•  local reservation_usage_before_second_write=$(cat \
  

•     $cgroup1_reservation_usage)
  

•  write_hugetlbfs_and_get_usage "hugetlb_cgroup_test2" "$size2" \
  

•     "$populate2" "$write2" "/mnt/huge/test2" "$method" "$private" \
  

•     "$expect_failure"
  

•  hugetlb_difference2=$hugetlb_difference
  

•  reserved_difference2=$reserved_difference
  

•  reservation_failed2=$reservation_failed
  

•  oom_killed2=$oom_killed
  

•  expect_equal "$usage_before_second_write" \
  

•     "$(cat $cgroup1_hugetlb_usage)" "Usage changed."
  

•  expect_equal "$reservation_usage_before_second_write" \
  

•     "$(cat $cgroup1_reservation_usage)" "Reservation usage changed."
  

•  cleanup_hugetlb_memory
  

•  local final_hugetlb=$(cat $cgroup1_hugetlb_usage)
  

•  local final_reservation=$(cat $cgroup1_reservation_usage)
  

•  expect_equal "0" "$final_hugetlb" \
  

•     "hugetlbt_cgroup_test1 final hugetlb is not zero"
  

•  expect_equal "0" "$final_reservation" \
  

•     "hugetlbt_cgroup_test1 final reservation is not zero"
  

•  local final_hugetlb=$(cat $cgroup2_hugetlb_usage)
  

•  local final_reservation=$(cat $cgroup2_reservation_usage)
  

•  expect_equal "0" "$final_hugetlb" \
  

•     "hugetlb_cgroup_test2 final hugetlb is not zero"
  

•  expect_equal "0" "$final_reservation" \
  

•     "hugetlb_cgroup_test2 final reservation is not zero"
  

+}

+for private in "" "-r" ; do +for populate in "" "-o"; do +for method in 0 1 2; do

+# Skip mmap(MAP_HUGETLB | MAP_SHARED). Doesn't seem to be supported. +if [[ "$method" == 1 ]] && [[ "$private" == "" ]]; then

•  continue
  

+fi

+# Skip populated shmem tests. Doesn't seem to be supported. +if [[ "$method" == 2"" ]] && [[ "$populate" == "-o" ]]; then

•  continue
  

+fi

+cleanup +echo +echo +echo +echo Test normal case. +echo private=$private, populate=$populate, method=$method +run_test $((10 * 1024 * 1024)) "$populate" "" $((20 * 1024 * 1024)) \

•  $((20 * 1024 * 1024)) 10 "$method" "$private" "0"
  

+echo Memory charged to hugtlb=$hugetlb_difference +echo Memory charged to reservation=$reserved_difference

+if [[ "$populate" == "-o" ]]; then

•  expect_equal "$((10 * 1024 * 1024))" "$hugetlb_difference" \
  

•     "Reserved memory charged to hugetlb cgroup."
  

+else

•  expect_equal "0" "$hugetlb_difference" \
  

•     "Reserved memory charged to hugetlb cgroup."
  

+fi

+expect_equal "$((10 * 1024 * 1024))" "$reserved_difference" \

•  "Reserved memory not charged to reservation usage."
  

+echo 'PASS'

+cleanup +echo +echo +echo +echo Test normal case with write. +echo private=$private, populate=$populate, method=$method +run_test $((10 * 1024 * 1024)) "$populate" '-w' $((20 * 1024 * 1024)) \

•  $((20 * 1024 * 1024)) 10 "$method" "$private" "0"
  

+echo Memory charged to hugtlb=$hugetlb_difference +echo Memory charged to reservation=$reserved_difference

+expect_equal "$((10 * 1024 * 1024))" "$hugetlb_difference" \

•  "Reserved memory charged to hugetlb cgroup."
  

+expect_equal "$((10 * 1024 * 1024))" "$reserved_difference" \

•  "Reserved memory not charged to reservation usage."
  

+echo 'PASS'

+cleanup +echo +echo +echo +echo Test more than reservation case. +echo private=$private, populate=$populate, method=$method +run_test "$((10 * 1024 * 1024))" "$populate" '' "$((20 * 1024 * 1024))" \

•  "$((5 * 1024 * 1024))" "10" "$method" "$private" "1"
  

+expect_equal "1" "$reservation_failed" "Reservation succeeded." +echo 'PASS'

+cleanup

+echo +echo +echo +echo Test more than cgroup limit case. +echo private=$private, populate=$populate, method=$method

+# Not sure if shm memory can be cleaned up when the process gets sigbus'd. +if [[ "$method" != 2 ]]; then

•  run_test $((10 * 1024 * 1024)) "$populate" "-w" $((5 * 1024 * 1024)) \
  

•     $((20 * 1024 * 1024)) 10 "$method" "$private" "1"
  

•  expect_equal "1" "$oom_killed" "Not oom killed."
  

+fi +echo 'PASS'

+cleanup

+echo +echo +echo +echo Test normal case, multiple cgroups. +echo private=$private, populate=$populate, method=$method +run_multiple_cgroup_test "$((6 * 1024 * 1024))" "$populate" "" \

•  "$((20 * 1024 * 1024))" "$((20 * 1024 * 1024))" "$((10 * 1024 * 1024))" \
  

•  "$populate" "" "$((20 * 1024 * 1024))" "$((20 * 1024 * 1024))" "10" \
  

•  "$method" "$private" "0"
  

+echo Memory charged to hugtlb1=$hugetlb_difference1 +echo Memory charged to reservation1=$reserved_difference1 +echo Memory charged to hugtlb2=$hugetlb_difference2 +echo Memory charged to reservation2=$reserved_difference2

+expect_equal "$((6 * 1024 * 1024))" "$reserved_difference1" \

•  "Incorrect reservations charged to cgroup 1."
  

+expect_equal "$((10 * 1024 * 1024))" "$reserved_difference2" \

•  "Incorrect reservation charged to cgroup 2."
  

+if [[ "$populate" == "-o" ]]; then

•  expect_equal "$((6 * 1024 * 1024))" "$hugetlb_difference1" \
  

•     "Incorrect hugetlb charged to cgroup 1."
  

•  expect_equal "$((10 * 1024 * 1024))" "$hugetlb_difference2" \
  

•     "Incorrect hugetlb charged to cgroup 2."
  

+else

•  expect_equal "0" "$hugetlb_difference1" \
  

•     "Incorrect hugetlb charged to cgroup 1."
  

•  expect_equal "0" "$hugetlb_difference2" \
  

•     "Incorrect hugetlb charged to cgroup 2."
  

+fi +echo 'PASS'

+cleanup +echo +echo +echo +echo Test normal case with write, multiple cgroups. +echo private=$private, populate=$populate, method=$method +run_multiple_cgroup_test "$((6 * 1024 * 1024))" "$populate" "-w" \

•  "$((20 * 1024 * 1024))" "$((20 * 1024 * 1024))" "$((10 * 1024 * 1024))" \
  

•  "$populate" "-w" "$((20 * 1024 * 1024))" "$((20 * 1024 * 1024))" "10" \
  

•  "$method" "$private" "0"
  

+echo Memory charged to hugtlb1=$hugetlb_difference1 +echo Memory charged to reservation1=$reserved_difference1 +echo Memory charged to hugtlb2=$hugetlb_difference2 +echo Memory charged to reservation2=$reserved_difference2

+expect_equal "$((6 * 1024 * 1024))" "$hugetlb_difference1" \

•  "Incorrect hugetlb charged to cgroup 1."
  

+expect_equal "$((6 * 1024 * 1024))" "$reserved_difference1" \

•  "Incorrect reservation charged to cgroup 1."
  

+expect_equal "$((10 * 1024 * 1024))" "$hugetlb_difference2" \

•  "Incorrect hugetlb charged to cgroup 2."
  

+expect_equal "$((10 * 1024 * 1024))" "$reserved_difference2" \

•  "Incorrected reservation charged to cgroup 2."
  

+echo 'PASS'

+done # private +done # populate +done # method

+umount $cgroup_path +rmdir $cgroup_path diff --git a/tools/testing/selftests/vm/write_hugetlb_memory.sh b/tools/testing/selftests/vm/write_hugetlb_memory.sh new file mode 100644 index 0000000000000..08f5fa5527cfd --- /dev/null +++ b/tools/testing/selftests/vm/write_hugetlb_memory.sh @@ -0,0 +1,22 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0

+set -e

+size=$1 +populate=$2 +write=$3 +cgroup=$4 +path=$5 +method=$6 +private=$7 +want_sleep=$8

+echo "Putting task in cgroup '$cgroup'" +echo $$ > /dev/cgroup/memory/"$cgroup"/tasks

+echo "Method is $method"

+set +e +./write_to_hugetlbfs -p "$path" -s "$size" "$write" "$populate" -m "$method" \

•  "$private" "$want_sleep"
  

diff --git a/tools/testing/selftests/vm/write_to_hugetlbfs.c b/tools/testing/selftests/vm/write_to_hugetlbfs.c new file mode 100644 index 0000000000000..f02a897427a97 --- /dev/null +++ b/tools/testing/selftests/vm/write_to_hugetlbfs.c @@ -0,0 +1,252 @@ +// SPDX-License-Identifier: GPL-2.0 +/*

• • This program reserves and uses hugetlb memory, supporting a bunch of
• • scenorios needed by the charged_reserved_hugetlb.sh test.

Spelling?

...

• */

+#include <err.h> +#include <errno.h> +#include <signal.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <unistd.h> +#include <fcntl.h> +#include <sys/types.h> +#include <sys/shm.h> +#include <sys/stat.h> +#include <sys/mman.h>

+/* Global definitions. */ +enum method {

• HUGETLBFS,
  

• MMAP_MAP_HUGETLB,
  

• SHM,
  

• MAX_METHOD
  

+};

+/* Global variables. */ +static const char *self; +static char *shmaddr; +static int shmid;

+/*

• • Show usage and exit.
• */

+static void exit_usage(void) +{

• printf("Usage: %s -p <path to hugetlbfs file> -s <size to map> "
  

•         "[-m <0=hugetlbfs | 1=mmap(MAP_HUGETLB)>] [-l] [-r] "
  

•         "[-o] [-w]\n", self);
  

• exit(EXIT_FAILURE);
  

+}

+void sig_handler(int signo) +{

• printf("Received %d.\n", signo);
  

• if (signo == SIGINT) {
  

•         printf("Deleting the memory\n");
  

•         if (shmdt((const void *)shmaddr) != 0) {
  

•                 perror("Detach failure");
  

•                 shmctl(shmid, IPC_RMID, NULL);
  

•                 exit(4);
  

Is this a skip error code? Please note that kselftest framework interprets this as a skipped test when returb value is 4.

This is not a kselftest framework binary. It's a tool to be called from charge_reserved_hugetlb.sh The exit value is just to make all the exits in this file return different codes so I can debug easier where the tool exited from. They don't actually mean anything. Is that OK?

...

•         }
  

•         shmctl(shmid, IPC_RMID, NULL);
  

•         printf("Done deleting the memory\n");
  

• }
  

• exit(2);
  

What about this one? What does exit code 2 mean?

...

+}

+int main(int argc, char **argv) +{

• int fd = 0;
  

• int key = 0;
  

• int *ptr = NULL;
  

• int c = 0;
  

• int size = 0;
  

• char path[256] = "";
  

• enum method method = MAX_METHOD;
  

• int want_sleep = 0, private = 0;
  

• int populate = 0;
  

• int write = 0;
  

• unsigned long i;
  

• if (signal(SIGINT, sig_handler) == SIG_ERR)
  

•         err(1, "\ncan't catch SIGINT\n");
  

• /* Parse command-line arguments. */
  

• setvbuf(stdout, NULL, _IONBF, 0);
  

• self = argv[0];
  

• while ((c = getopt(argc, argv, "s:p:m:owlr")) != -1) {
  

•         switch (c) {
  

•         case 's':
  

•                 size = atoi(optarg);
  

•                 break;
  

•         case 'p':
  

•                 strncpy(path, optarg, sizeof(path));
  

•                 break;
  

•         case 'm':
  

•                 if (atoi(optarg) >= MAX_METHOD) {
  

•                         errno = EINVAL;
  

•                         perror("Invalid -m.");
  

•                         exit_usage();
  

•                 }
  

•                 method = atoi(optarg);
  

•                 break;
  

•         case 'o':
  

•                 populate = 1;
  

•                 break;
  

•         case 'w':
  

•                 write = 1;
  

•                 break;
  

•         case 'l':
  

•                 want_sleep = 1;
  

•                 break;
  

•         case 'r':
  

•                 private = 1;
  

•                 break;
  

•         default:
  

•                 errno = EINVAL;
  

•                 perror("Invalid arg");
  

•                 exit_usage();
  

•         }
  

• }
  

• if (strncmp(path, "", sizeof(path)) != 0) {
  

•         printf("Writing to this path: %s\n", path);
  

• } else {
  

•         errno = EINVAL;
  

•         perror("path not found");
  

•         exit_usage();
  

• }
  

• if (size != 0) {
  

•         printf("Writing this size: %d\n", size);
  

• } else {
  

•         errno = EINVAL;
  

•         perror("size not found");
  

•         exit_usage();
  

• }
  

• if (!populate)
  

•         printf("Not populating.\n");
  

• else
  

•         printf("Populating.\n");
  

• if (!write)
  

•         printf("Not writing to memory.\n");
  

• if (method == MAX_METHOD) {
  

•         errno = EINVAL;
  

•         perror("-m Invalid");
  

•         exit_usage();
  

• } else
  

•         printf("Using method=%d\n", method);
  

• if (!private)
  

•         printf("Shared mapping.\n");
  

• else
  

•         printf("Private mapping.\n");
  

• switch (method) {
  

• case HUGETLBFS:
  

•         printf("Allocating using HUGETLBFS.\n");
  

•         fd = open(path, O_CREAT | O_RDWR, 0777);
  

•         if (fd == -1)
  

•                 err(1, "Failed to open file.");
  

•         ptr = mmap(NULL, size, PROT_READ | PROT_WRITE,
  

•                 (private ? MAP_PRIVATE : MAP_SHARED) | (populate ?
  

•                         MAP_POPULATE : 0), fd, 0);
  

•         if (ptr == MAP_FAILED) {
  

•                 close(fd);
  

•                 err(1, "Error mapping the file");
  

•         }
  

•         break;
  

• case MMAP_MAP_HUGETLB:
  

•         printf("Allocating using MAP_HUGETLB.\n");
  

•         ptr = mmap(NULL, size,
  

•         PROT_READ | PROT_WRITE,
  

•         (private ? (MAP_PRIVATE | MAP_ANONYMOUS) : MAP_SHARED) |
  

•         MAP_HUGETLB | (populate ?
  

•                 MAP_POPULATE : 0),
  

•         -1, 0);
  

•         if (ptr == MAP_FAILED)
  

•                 err(1, "mmap");
  

•         printf("Returned address is %p\n", ptr);
  

•         break;
  

• case SHM:
  

•         printf("Allocating using SHM.\n");
  

•         shmid = shmget(key, size, SHM_HUGETLB | IPC_CREAT | SHM_R |
  

•                         SHM_W);
  

•         if (shmid < 0) {
  

•                 shmid = shmget(++key, size, SHM_HUGETLB | IPC_CREAT |
  

•                                 SHM_R | SHM_W);
  

•                 if (shmid < 0)
  

•                         err(1, "shmget");
  

•         }
  

•         printf("shmid: 0x%x, shmget key:%d\n", shmid, key);
  

•         shmaddr = shmat(shmid, NULL, 0);
  

•         if (shmaddr == (char *)-1) {
  

•                 perror("Shared memory attach failure");
  

•                 shmctl(shmid, IPC_RMID, NULL);
  

•                 exit(2);
  

•         }
  

•         printf("shmaddr: %p\n", shmaddr);
  

•         break;
  

• default:
  

•         errno = EINVAL;
  

•         err(1, "Invalid method.");
  

• }
  

• if (write) {
  

•         printf("Writing to memory.\n");
  

•         if (method != SHM) {
  

•                 memset(ptr, 1, size);
  

•         } else {
  

•                 printf("Starting the writes:\n");
  

•                 for (i = 0; i < size; i++) {
  

•                         shmaddr[i] = (char)(i);
  

•                         if (!(i % (1024 * 1024)))
  

•                                 printf(".");
  

•                 }
  

•                 printf("\n");
  

•                 printf("Starting the Check...");
  

•                 for (i = 0; i < size; i++)
  

•                         if (shmaddr[i] != (char)i) {
  

•                                 printf("\nIndex %lu mismatched\n", i);
  

•                                 exit(3);
  

•                         }
  

•                 printf("Done.\n");
  

•         }
  

• }
  

• if (want_sleep) {
  

•         /* Signal to caller that we're done. */
  

•         printf("DONE\n");
  

•         /* Hold memory until external kill signal is delivered. */
  

•         while (1)
  

•                 sleep(100);
  

Please don't add sleeps. This will hold up the kselftest run.

This tool is meant to allocate a bunch of memory and hold it until the code in ./charge_reserved_hugetlb.sh checks that the usage is accounted for. charge_reserved_hugetlb.sh runs this tool in the background, and asks it to hold the memory until it verifies accounting, then asks it to delete the memory. It should not hold up a run.

...

• }
  

• close(fd);
  

Is this close() necessary in all cases? Looks like MMAP_MAP_HUGETLB is the only case that opens it.

I am not sure if the error legs are correct.

...

• return 0;
  

+}

2.23.0.162.g0b9fbb3734-goog

thanks, -- Shuah

Thanks for the review, I should be able to address everything else in the next patchset.