From c76adee3471f7fe0553904be7ab13c33eda64a19 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Fri, 28 Dec 2018 00:38:21 -0800 Subject: mm, thp, proc: report THP eligibility for each vma [ Upstream commit 7635d9cbe8327e131a1d3d8517dc186c2796ce2e ] Userspace falls short when trying to find out whether a specific memory range is eligible for THP. There are usecases that would like to know that http://lkml.kernel.org/r/alpine.DEB.2.21.1809251248450.50347@chino.kir.corp.google.com : This is used to identify heap mappings that should be able to fault thp : but do not, and they normally point to a low-on-memory or fragmentation : issue. The only way to deduce this now is to query for hg resp. nh flags and confronting the state with the global setting. Except that there is also PR_SET_THP_DISABLE that might change the picture. So the final logic is not trivial. Moreover the eligibility of the vma depends on the type of VMA as well. In the past we have supported only anononymous memory VMAs but things have changed and shmem based vmas are supported as well these days and the query logic gets even more complicated because the eligibility depends on the mount option and another global configuration knob. Simplify the current state and report the THP eligibility in /proc//smaps for each existing vma. Reuse transparent_hugepage_enabled for this purpose. The original implementation of this function assumes that the caller knows that the vma itself is supported for THP so make the core checks into __transparent_hugepage_enabled and use it for existing callers. __show_smap just use the new transparent_hugepage_enabled which also checks the vma support status (please note that this one has to be out of line due to include dependency issues). [mhocko@kernel.org: fix oops with NULL ->f_mapping] Link: http://lkml.kernel.org/r/20181224185106.GC16738@dhcp22.suse.cz Link: http://lkml.kernel.org/r/20181211143641.3503-3-mhocko@kernel.org Signed-off-by: Michal Hocko Acked-by: Vlastimil Babka Cc: Dan Williams Cc: David Rientjes Cc: Jan Kara Cc: Mike Rapoport Cc: Paul Oppenheimer Cc: William Kucharski Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Sasha Levin --- Documentation/filesystems/proc.txt | 3 +++ fs/proc/task_mmu.c | 2 ++ include/linux/huge_mm.h | 13 ++++++++++++- mm/huge_memory.c | 12 +++++++++++- mm/memory.c | 4 ++-- 5 files changed, 30 insertions(+), 4 deletions(-) diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt index 06ac6dda9b34..0d0ecc7df260 100644 --- a/Documentation/filesystems/proc.txt +++ b/Documentation/filesystems/proc.txt @@ -425,6 +425,7 @@ SwapPss: 0 kB KernelPageSize: 4 kB MMUPageSize: 4 kB Locked: 0 kB +THPeligible: 0 VmFlags: rd ex mr mw me dw the first of these lines shows the same information as is displayed for the @@ -462,6 +463,8 @@ replaced by copy-on-write) part of the underlying shmem object out on swap. "SwapPss" shows proportional swap share of this mapping. Unlike "Swap", this does not take into account swapped out page of underlying shmem objects. "Locked" indicates whether the mapping is locked in memory or not. +"THPeligible" indicates whether the mapping is eligible for THP pages - 1 if +true, 0 otherwise. "VmFlags" field deserves a separate description. This member represents the kernel flags associated with the particular virtual memory area in two letter encoded diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 71aba44c4fa6..efa6273c0006 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -800,6 +800,8 @@ static int show_smap(struct seq_file *m, void *v) __show_smap(m, &mss); + seq_printf(m, "THPeligible: %d\n", transparent_hugepage_enabled(vma)); + if (arch_pkeys_enabled()) seq_printf(m, "ProtectionKey: %8u\n", vma_pkey(vma)); show_smap_vma_flags(m, vma); diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 77227224ca88..e375f2249f52 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -91,7 +91,11 @@ extern bool is_vma_temporary_stack(struct vm_area_struct *vma); extern unsigned long transparent_hugepage_flags; -static inline bool transparent_hugepage_enabled(struct vm_area_struct *vma) +/* + * to be used on vmas which are known to support THP. + * Use transparent_hugepage_enabled otherwise + */ +static inline bool __transparent_hugepage_enabled(struct vm_area_struct *vma) { if (vma->vm_flags & VM_NOHUGEPAGE) return false; @@ -115,6 +119,8 @@ static inline bool transparent_hugepage_enabled(struct vm_area_struct *vma) return false; } +bool transparent_hugepage_enabled(struct vm_area_struct *vma); + #define transparent_hugepage_use_zero_page() \ (transparent_hugepage_flags & \ (1<ptl); alloc: - if (transparent_hugepage_enabled(vma) && + if (__transparent_hugepage_enabled(vma) && !transparent_hugepage_debug_cow()) { huge_gfp = alloc_hugepage_direct_gfpmask(vma); new_page = alloc_hugepage_vma(huge_gfp, vma, haddr, HPAGE_PMD_ORDER); diff --git a/mm/memory.c b/mm/memory.c index fb5655b518c9..bbf0cc4066c8 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -4106,7 +4106,7 @@ static vm_fault_t __handle_mm_fault(struct vm_area_struct *vma, vmf.pud = pud_alloc(mm, p4d, address); if (!vmf.pud) return VM_FAULT_OOM; - if (pud_none(*vmf.pud) && transparent_hugepage_enabled(vma)) { + if (pud_none(*vmf.pud) && __transparent_hugepage_enabled(vma)) { ret = create_huge_pud(&vmf); if (!(ret & VM_FAULT_FALLBACK)) return ret; @@ -4132,7 +4132,7 @@ static vm_fault_t __handle_mm_fault(struct vm_area_struct *vma, vmf.pmd = pmd_alloc(mm, vmf.pud, address); if (!vmf.pmd) return VM_FAULT_OOM; - if (pmd_none(*vmf.pmd) && transparent_hugepage_enabled(vma)) { + if (pmd_none(*vmf.pmd) && __transparent_hugepage_enabled(vma)) { ret = create_huge_pmd(&vmf); if (!(ret & VM_FAULT_FALLBACK)) return ret; -- cgit v1.2.3