Commit 7635d9cb authored by Michal Hocko's avatar Michal Hocko Committed by Linus Torvalds

mm, thp, proc: report THP eligibility for each vma

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/<pid>/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.orgSigned-off-by: default avatarMichal Hocko <mhocko@suse.com>
Acked-by: default avatarVlastimil Babka <vbabka@suse.cz>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Mike Rapoport <rppt@linux.ibm.com>
Cc: Paul Oppenheimer <bepvte@gmail.com>
Cc: William Kucharski <william.kucharski@oracle.com>
Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: default avatarLinus Torvalds <torvalds@linux-foundation.org>
parent 7550c607
...@@ -425,6 +425,7 @@ SwapPss: 0 kB ...@@ -425,6 +425,7 @@ SwapPss: 0 kB
KernelPageSize: 4 kB KernelPageSize: 4 kB
MMUPageSize: 4 kB MMUPageSize: 4 kB
Locked: 0 kB Locked: 0 kB
THPeligible: 0
VmFlags: rd ex mr mw me dw VmFlags: rd ex mr mw me dw
the first of these lines shows the same information as is displayed for the 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. ...@@ -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 "SwapPss" shows proportional swap share of this mapping. Unlike "Swap", this
does not take into account swapped out page of underlying shmem objects. does not take into account swapped out page of underlying shmem objects.
"Locked" indicates whether the mapping is locked in memory or not. "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 "VmFlags" field deserves a separate description. This member represents the kernel
flags associated with the particular virtual memory area in two letter encoded flags associated with the particular virtual memory area in two letter encoded
......
...@@ -790,6 +790,8 @@ static int show_smap(struct seq_file *m, void *v) ...@@ -790,6 +790,8 @@ static int show_smap(struct seq_file *m, void *v)
__show_smap(m, &mss); __show_smap(m, &mss);
seq_printf(m, "THPeligible: %d\n", transparent_hugepage_enabled(vma));
if (arch_pkeys_enabled()) if (arch_pkeys_enabled())
seq_printf(m, "ProtectionKey: %8u\n", vma_pkey(vma)); seq_printf(m, "ProtectionKey: %8u\n", vma_pkey(vma));
show_smap_vma_flags(m, vma); show_smap_vma_flags(m, vma);
......
...@@ -93,7 +93,11 @@ extern bool is_vma_temporary_stack(struct vm_area_struct *vma); ...@@ -93,7 +93,11 @@ extern bool is_vma_temporary_stack(struct vm_area_struct *vma);
extern unsigned long transparent_hugepage_flags; 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) if (vma->vm_flags & VM_NOHUGEPAGE)
return false; return false;
...@@ -117,6 +121,8 @@ static inline bool transparent_hugepage_enabled(struct vm_area_struct *vma) ...@@ -117,6 +121,8 @@ static inline bool transparent_hugepage_enabled(struct vm_area_struct *vma)
return false; return false;
} }
bool transparent_hugepage_enabled(struct vm_area_struct *vma);
#define transparent_hugepage_use_zero_page() \ #define transparent_hugepage_use_zero_page() \
(transparent_hugepage_flags & \ (transparent_hugepage_flags & \
(1<<TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG)) (1<<TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG))
...@@ -257,6 +263,11 @@ static inline bool thp_migration_supported(void) ...@@ -257,6 +263,11 @@ static inline bool thp_migration_supported(void)
#define hpage_nr_pages(x) 1 #define hpage_nr_pages(x) 1
static inline bool __transparent_hugepage_enabled(struct vm_area_struct *vma)
{
return false;
}
static inline bool transparent_hugepage_enabled(struct vm_area_struct *vma) static inline bool transparent_hugepage_enabled(struct vm_area_struct *vma)
{ {
return false; return false;
......
...@@ -62,6 +62,16 @@ static struct shrinker deferred_split_shrinker; ...@@ -62,6 +62,16 @@ static struct shrinker deferred_split_shrinker;
static atomic_t huge_zero_refcount; static atomic_t huge_zero_refcount;
struct page *huge_zero_page __read_mostly; struct page *huge_zero_page __read_mostly;
bool transparent_hugepage_enabled(struct vm_area_struct *vma)
{
if (vma_is_anonymous(vma))
return __transparent_hugepage_enabled(vma);
if (vma_is_shmem(vma) && shmem_huge_enabled(vma))
return __transparent_hugepage_enabled(vma);
return false;
}
static struct page *get_huge_zero_page(void) static struct page *get_huge_zero_page(void)
{ {
struct page *zero_page; struct page *zero_page;
...@@ -1290,7 +1300,7 @@ vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf, pmd_t orig_pmd) ...@@ -1290,7 +1300,7 @@ vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf, pmd_t orig_pmd)
get_page(page); get_page(page);
spin_unlock(vmf->ptl); spin_unlock(vmf->ptl);
alloc: alloc:
if (transparent_hugepage_enabled(vma) && if (__transparent_hugepage_enabled(vma) &&
!transparent_hugepage_debug_cow()) { !transparent_hugepage_debug_cow()) {
huge_gfp = alloc_hugepage_direct_gfpmask(vma); huge_gfp = alloc_hugepage_direct_gfpmask(vma);
new_page = alloc_hugepage_vma(huge_gfp, vma, haddr, HPAGE_PMD_ORDER); new_page = alloc_hugepage_vma(huge_gfp, vma, haddr, HPAGE_PMD_ORDER);
......
...@@ -3831,7 +3831,7 @@ static vm_fault_t __handle_mm_fault(struct vm_area_struct *vma, ...@@ -3831,7 +3831,7 @@ static vm_fault_t __handle_mm_fault(struct vm_area_struct *vma,
vmf.pud = pud_alloc(mm, p4d, address); vmf.pud = pud_alloc(mm, p4d, address);
if (!vmf.pud) if (!vmf.pud)
return VM_FAULT_OOM; 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); ret = create_huge_pud(&vmf);
if (!(ret & VM_FAULT_FALLBACK)) if (!(ret & VM_FAULT_FALLBACK))
return ret; return ret;
...@@ -3857,7 +3857,7 @@ static vm_fault_t __handle_mm_fault(struct vm_area_struct *vma, ...@@ -3857,7 +3857,7 @@ static vm_fault_t __handle_mm_fault(struct vm_area_struct *vma,
vmf.pmd = pmd_alloc(mm, vmf.pud, address); vmf.pmd = pmd_alloc(mm, vmf.pud, address);
if (!vmf.pmd) if (!vmf.pmd)
return VM_FAULT_OOM; 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); ret = create_huge_pmd(&vmf);
if (!(ret & VM_FAULT_FALLBACK)) if (!(ret & VM_FAULT_FALLBACK))
return ret; return ret;
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment