Thread (119 messages) flat view 119 messages, 9 authors, 5d ago
COOLING5d

[RFC PATCH 24/57] mm/collapse: report each candidate's outcome to tracing

From: Kiryl Shutsemau <hidden>
Date: 2026-08-16 22:47:05
Also in: bpf, linux-kselftest, linux-mm, lkml
Subsystem: memory management, memory management - thp (transparent huge page), the rest, tracing · Maintainers: Andrew Morton, David Hildenbrand, Linus Torvalds, Steven Rostedt, Masami Hiramatsu

From: "Kiryl Shutsemau (Meta)" <kas@kernel.org>

The engine decides per candidate, and every one of those decisions is
currently invisible: the mechanism it is about to replace reports through
mm_collapse_huge_page_isolate, which the engine never calls.  Switching
the anonymous path over without something in its place would take
existing tracing with it.

Add one tracepoint, mm_collapse_candidate: a window's address and order,
the pass that reached a verdict on it, and what that verdict was.

Every candidate a pass judged produces exactly one -- the pass that
refused it, or the install for one that made it.  A candidate the round
gave up on before any pass judged it produces none.

That is enough to follow a round: which windows were attempted, and which
ones the batch dropped and where.  It is also what a scan of the trace
buffer can attribute to an address.

It goes in the huge_memory trace system, next to the events it stands in
for, so a consumer enabling that system keeps seeing collapses.

Assisted-by: Claude-Code:claude-opus-5
Signed-off-by: Kiryl Shutsemau (Meta) <kas@kernel.org>
---
 include/trace/events/huge_memory.h | 40 ++++++++++++++++++++++++++++++
 mm/collapse.c                      | 32 +++++++++++++++++++++++-
 mm/collapse.h                      | 13 ++++++++++
 3 files changed, 84 insertions(+), 1 deletion(-)
diff --git a/include/trace/events/huge_memory.h b/include/trace/events/huge_memory.h
index ff938ac9c43c..86131845b761 100644
--- a/include/trace/events/huge_memory.h
+++ b/include/trace/events/huge_memory.h
@@ -44,12 +44,21 @@
 	EM( SCAN_PAGE_NOT_EXCLUSIVE,	"page_not_exclusive")		\
 	EMe(SCAN_ALLOC_LIGHT_MISS,	"alloc_light_miss")
 
+#define COLLAPSE_PASS_STATUS						\
+	EM( COLLAPSE_PASS_ALLOC,	"alloc")			\
+	EM( COLLAPSE_PASS_REVALIDATE,	"revalidate")			\
+	EM( COLLAPSE_PASS_FAULTIN,	"faultin")			\
+	EM( COLLAPSE_PASS_FREEZE,	"freeze")			\
+	EM( COLLAPSE_PASS_COPY,		"copy")				\
+	EMe(COLLAPSE_PASS_INSTALL,	"install")
+
 #undef EM
 #undef EMe
 #define EM(a, b)	TRACE_DEFINE_ENUM(a);
 #define EMe(a, b)	TRACE_DEFINE_ENUM(a);
 
 SCAN_STATUS
+COLLAPSE_PASS_STATUS
 
 #undef EM
 #undef EMe
@@ -117,6 +126,37 @@ TRACE_EVENT(mm_collapse_huge_page,
 		__entry->order)
 );
 
+TRACE_EVENT(mm_collapse_candidate,
+
+	TP_PROTO(struct mm_struct *mm, unsigned long addr, unsigned int order,
+		 int pass, int result),
+
+	TP_ARGS(mm, addr, order, pass, result),
+
+	TP_STRUCT__entry(
+		__field(struct mm_struct *, mm)
+		__field(unsigned long, addr)
+		__field(unsigned int, order)
+		__field(int, pass)
+		__field(int, result)
+	),
+
+	TP_fast_assign(
+		__entry->mm = mm;
+		__entry->addr = addr;
+		__entry->order = order;
+		__entry->pass = pass;
+		__entry->result = result;
+	),
+
+	TP_printk("mm=%p, addr=0x%lx, order=%u, pass=%s, result=%s",
+		__entry->mm,
+		__entry->addr,
+		__entry->order,
+		__print_symbolic(__entry->pass, COLLAPSE_PASS_STATUS),
+		__print_symbolic(__entry->result, SCAN_STATUS))
+);
+
 TRACE_EVENT(mm_collapse_huge_page_isolate,
 
 	TP_PROTO(struct folio *folio, int none_or_zero,
diff --git a/mm/collapse.c b/mm/collapse.c
index 9b73ebff1103..91ff20138a8e 100644
--- a/mm/collapse.c
+++ b/mm/collapse.c
@@ -20,6 +20,7 @@
 #include <linux/vmstat.h>
 
 #include <asm/tlb.h>
+#include <trace/events/huge_memory.h>
 #include "collapse.h"
 #include "internal.h"
 
@@ -195,6 +196,14 @@ static unsigned int candidate_nr_pages(const struct collapse_candidate *cand)
 	return 1U << cand->order;
 }
 
+static void collapse_trace_candidate(struct mm_struct *mm,
+				     const struct collapse_candidate *cand,
+				     enum collapse_pass pass)
+{
+	trace_mm_collapse_candidate(mm, cand->addr, cand->order, pass,
+				    cand->result);
+}
+
 /* Where a candidate sits in the table, in the PTE offsets selection counts in */
 static unsigned int candidate_offset(const struct collapse_candidate *cand,
 				     unsigned long pmd_addr)
@@ -278,6 +287,8 @@ static enum scan_result collapse_revalidate(struct vm_area_struct *vma,
 					      BIT(cand->order))) {
 			cand->state = CAND_SKIPPED;
 			cand->result = SCAN_VMA_CHECK;
+			collapse_trace_candidate(mm, cand,
+						 COLLAPSE_PASS_REVALIDATE);
 			continue;
 		}
 
@@ -420,6 +431,8 @@ static enum scan_result collapse_faultin(struct vm_area_struct *vma,
 			if (r == SCAN_EXCEED_SWAP_PTE) {
 				cand->state = CAND_SKIPPED;
 				cand->result = r;
+				collapse_trace_candidate(vma->vm_mm, cand,
+							 COLLAPSE_PASS_FAULTIN);
 				break;
 			}
 			if (r != SCAN_SUCCEED) {
@@ -878,6 +891,7 @@ static void collapse_freeze(struct vm_area_struct *vma,
 				continue;
 			cand->state = CAND_SKIPPED;
 			cand->result = SCAN_NO_PTE_TABLE;
+			collapse_trace_candidate(mm, cand, COLLAPSE_PASS_FREEZE);
 		}
 		return;
 	}
@@ -904,6 +918,7 @@ static void collapse_freeze(struct vm_area_struct *vma,
 		cand->result = result;
 		if (result != SCAN_SUCCEED) {
 			cand->state = CAND_SKIPPED;
+			collapse_trace_candidate(mm, cand, COLLAPSE_PASS_FREEZE);
 			continue;
 		}
 
@@ -986,6 +1001,7 @@ static void collapse_reserve(struct mm_struct *mm, struct collapse_control *cc)
 
 		cand->state = CAND_SKIPPED;
 		cand->result = result;
+		collapse_trace_candidate(mm, cand, COLLAPSE_PASS_ALLOC);
 	}
 }
 
@@ -1016,6 +1032,7 @@ static void collapse_deposit(struct mm_struct *mm, struct collapse_control *cc)
 	if (!cand->deposit) {
 		cand->state = CAND_SKIPPED;
 		cand->result = SCAN_ALLOC_HUGE_PAGE_FAIL;
+		collapse_trace_candidate(mm, cand, COLLAPSE_PASS_ALLOC);
 	}
 }
 
@@ -1060,6 +1077,8 @@ static void collapse_provision(struct mm_struct *mm,
 			}
 			cand->result = result;
 		}
+
+		collapse_trace_candidate(mm, cand, COLLAPSE_PASS_ALLOC);
 	}
 }
 
@@ -1106,6 +1125,8 @@ static void collapse_copy(struct vm_area_struct *vma,
 			 */
 			if (copy_mc_user_highpage(dst, src, addr, vma)) {
 				cand->result = SCAN_COPY_MC;
+				collapse_trace_candidate(vma->vm_mm, cand,
+							 COLLAPSE_PASS_COPY);
 				break;
 			}
 		}
@@ -1294,6 +1315,7 @@ static void collapse_install_pmd(struct vm_area_struct *vma,
 		/* Table gone under us; see collapse_abort_candidate() on @pte */
 		spin_unlock(pmd_ptl);
 		cand->result = SCAN_NO_PTE_TABLE;
+		collapse_trace_candidate(mm, cand, COLLAPSE_PASS_INSTALL);
 		collapse_abort_candidate(vma, cand, NULL);
 		return;
 	}
@@ -1315,6 +1337,7 @@ static void collapse_install_pmd(struct vm_area_struct *vma,
 
 	if (!collapse_verify_candidate(cand, pte, &nr_populated)) {
 		cand->result = SCAN_PTE_NON_PRESENT;
+		collapse_trace_candidate(mm, cand, COLLAPSE_PASS_INSTALL);
 		collapse_abort_candidate(vma, cand, pte);
 		goto out_unlock;
 	}
@@ -1411,6 +1434,8 @@ static void collapse_install(struct vm_area_struct *vma,
 				continue;
 
 			cand->result = SCAN_NO_PTE_TABLE;
+			collapse_trace_candidate(mm, cand,
+						 COLLAPSE_PASS_INSTALL);
 			collapse_abort_candidate(vma, cand, NULL);
 		}
 		return;
@@ -1439,6 +1464,8 @@ static void collapse_install(struct vm_area_struct *vma,
 
 		if (!collapse_verify_candidate(cand, cand_pte, &nr_populated)) {
 			cand->result = SCAN_PTE_NON_PRESENT;
+			collapse_trace_candidate(mm, cand,
+						 COLLAPSE_PASS_INSTALL);
 			collapse_abort_candidate(vma, cand, cand_pte);
 			continue;
 		}
@@ -1548,8 +1575,11 @@ static unsigned int collapse_finish(struct mm_struct *mm,
 			pte_free(mm, cand->deposit);
 			cand->deposit = NULL;
 		}
-		if (cand->state == CAND_INSTALLED)
+		if (cand->state == CAND_INSTALLED) {
 			nr_installed++;
+			collapse_trace_candidate(mm, cand,
+						 COLLAPSE_PASS_INSTALL);
+		}
 	}
 
 	return nr_installed;
diff --git a/mm/collapse.h b/mm/collapse.h
index 3803f5a89087..34de3ebb05e3 100644
--- a/mm/collapse.h
+++ b/mm/collapse.h
@@ -13,6 +13,19 @@
 struct collapse_candidate;
 struct collapse_retry;
 
+/*
+ * Which pass of a round reached a verdict on a candidate.  Only collapse.c
+ * produces these; the trace header khugepaged.c builds names them.
+ */
+enum collapse_pass {
+	COLLAPSE_PASS_ALLOC,
+	COLLAPSE_PASS_REVALIDATE,
+	COLLAPSE_PASS_FAULTIN,
+	COLLAPSE_PASS_FREEZE,
+	COLLAPSE_PASS_COPY,
+	COLLAPSE_PASS_INSTALL,
+};
+
 enum scan_result {
 	SCAN_FAIL,
 	SCAN_SUCCEED,
-- 
2.54.0
Keyboard shortcuts
hback out one level
jnext message in thread
kprevious message in thread
ldrill in
Escclose help / fold thread tree
?toggle this help