On Tue, Apr 29, 2025 at 7:49 AM Zi Yan ziy@nvidia.com wrote:
On 28 Apr 2025, at 14:29, Nico Pache wrote:
setting /transparent_hugepages/enabled=always allows applications to benefit from THPs without having to madvise. However, the pf handler
s/pf/page fault
takes very few considerations to decide weather or not to actually use a
s/weather/whether
THP. This can lead to a lot of wasted memory. khugepaged only operates on memory that was either allocated with enabled=always or MADV_HUGEPAGE.
Introduce the ability to set enabled=defer, which will prevent THPs from being allocated by the page fault handler unless madvise is set, leaving it up to khugepaged to decide which allocations will collapse to a THP. This should allow applications to benefits from THPs, while curbing some of the memory waste.
Co-developed-by: Rafael Aquini raquini@redhat.com Signed-off-by: Rafael Aquini raquini@redhat.com Signed-off-by: Nico Pache npache@redhat.com
include/linux/huge_mm.h | 15 +++++++++++++-- mm/huge_memory.c | 31 +++++++++++++++++++++++++++---- 2 files changed, 40 insertions(+), 6 deletions(-)
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index e3d15c737008..57e6c962afb1 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -48,6 +48,7 @@ enum transparent_hugepage_flag { TRANSPARENT_HUGEPAGE_UNSUPPORTED, TRANSPARENT_HUGEPAGE_FLAG, TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG,
TRANSPARENT_HUGEPAGE_DEFER_PF_INST_FLAG,What does INST mean here? Can you add one sentence on this new flag in the commit log to explain what it is short for?
"INSERT". Someone else commented on the length of this FLAG name. I forgot to update it. I can shorten it to something like ..DEFER_FLAG or DEFER_PF_FLAG
TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG,@@ -186,6 +187,7 @@ static inline bool hugepage_global_enabled(void) { return transparent_hugepage_flags & ((1<<TRANSPARENT_HUGEPAGE_FLAG) |
(1<<TRANSPARENT_HUGEPAGE_DEFER_PF_INST_FLAG) | (1<<TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG));}
@@ -195,6 +197,12 @@ static inline bool hugepage_global_always(void) (1<<TRANSPARENT_HUGEPAGE_FLAG); }
+static inline bool hugepage_global_defer(void) +{
return transparent_hugepage_flags &(1<<TRANSPARENT_HUGEPAGE_DEFER_PF_INST_FLAG);+}
static inline int highest_order(unsigned long orders) { return fls_long(orders) - 1; @@ -291,13 +299,16 @@ unsigned long thp_vma_allowable_orders(struct vm_area_struct *vma, unsigned long tva_flags, unsigned long orders) {
if ((tva_flags & TVA_IN_PF) && hugepage_global_defer() &&!(vm_flags & VM_HUGEPAGE))return 0;/* Optimization to check if required orders are enabled early. */ if ((tva_flags & TVA_ENFORCE_SYSFS) && vma_is_anonymous(vma)) { unsigned long mask = READ_ONCE(huge_anon_orders_always);
This newline should stay, right?
Yes, I can fix that.
The rest looks good to me. Thanks. Acked-by: Zi Yan ziy@nvidia.com
Thank you! -- Nico
Best Regards, Yan, Zi