[PATCH V2 1/2] mm/migration: Add trace events for THP migrations

[PATCH V2 1/2] mm/migration: Add trace events for THP migrations

[Anshuman Khandual]

This adds two trace events for PMD based THP migration without split. These
events closely follow the implementation details like setting and removing
of PMD migration entries, which are essential operations for THP migration.

Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Zi Yan <ziy@nvidia.com>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: linux-mm@kvack.org
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Anshuman Khandual <anshuman.khandual@arm.com>
---
 include/trace/events/thp.h | 27 +++++++++++++++++++++++++++
 mm/huge_memory.c           |  5 +++++
 2 files changed, 32 insertions(+)

diff --git a/include/trace/events/thp.h b/include/trace/events/thp.h
index ca3f2767828a..202b3e3e67ff 100644
--- a/include/trace/events/thp.h
+++ b/include/trace/events/thp.h
@@ -48,6 +48,33 @@ TRACE_EVENT(hugepage_update,
 	    TP_printk("hugepage update at addr 0x%lx and pte = 0x%lx clr = 0x%lx, set = 0x%lx", __entry->addr, __entry->pte, __entry->clr, __entry->set)
 );
 
+DECLARE_EVENT_CLASS(migration_pmd,
+
+		TP_PROTO(unsigned long addr, unsigned long pmd),
+
+		TP_ARGS(addr, pmd),
+
+		TP_STRUCT__entry(
+			__field(unsigned long, addr)
+			__field(unsigned long, pmd)
+		),
+
+		TP_fast_assign(
+			__entry->addr = addr;
+			__entry->pmd = pmd;
+		),
+		TP_printk("addr=%lx, pmd=%lx", __entry->addr, __entry->pmd)
+);
+
+DEFINE_EVENT(migration_pmd, set_migration_pmd,
+	TP_PROTO(unsigned long addr, unsigned long pmd),
+	TP_ARGS(addr, pmd)
+);
+
+DEFINE_EVENT(migration_pmd, remove_migration_pmd,
+	TP_PROTO(unsigned long addr, unsigned long pmd),
+	TP_ARGS(addr, pmd)
+);
 #endif /* _TRACE_THP_H */
 
 /* This part must be outside protection */
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 406a3c28c026..ab49f9a3e420 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -39,6 +39,9 @@
 #include <asm/pgalloc.h>
 #include "internal.h"
 
+#define CREATE_TRACE_POINTS
+#include <trace/events/thp.h>
+
 /*
  * By default, transparent hugepage support is disabled in order to avoid
  * risking an increased memory footprint for applications that are not
@@ -3173,6 +3176,7 @@ void set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw,
 	set_pmd_at(mm, address, pvmw->pmd, pmdswp);
 	page_remove_rmap(page, true);
 	put_page(page);
+	trace_set_migration_pmd(address, pmd_val(pmdswp));
 }
 
 void remove_migration_pmd(struct page_vma_mapped_walk *pvmw, struct page *new)
@@ -3206,5 +3210,6 @@ void remove_migration_pmd(struct page_vma_mapped_walk *pvmw, struct page *new)
 	if ((vma->vm_flags & VM_LOCKED) && !PageDoubleMap(new))
 		mlock_vma_page(new);
 	update_mmu_cache_pmd(vma, address, pvmw->pmd);
+	trace_remove_migration_pmd(address, pmd_val(pmde));
 }
 #endif
-- 
2.20.1

[PATCH V2 2/2] mm/migration: Add trace events for base page and HugeTLB migrations

[Anshuman Khandual]

This adds two trace events for base page and HugeTLB page migrations. These
events, closely follow the implementation details like setting and removing
of PTE migration entries, which are essential operations for migration.

Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Zi Yan <ziy@nvidia.com>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: linux-mm@kvack.org
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Anshuman Khandual <anshuman.khandual@arm.com>
---
 include/trace/events/migrate.h | 31 +++++++++++++++++++++++++++++++
 mm/migrate.c                   |  3 +++
 mm/rmap.c                      |  5 +++++
 3 files changed, 39 insertions(+)

diff --git a/include/trace/events/migrate.h b/include/trace/events/migrate.h
index 779f3fad9ecd..061b5128f335 100644
--- a/include/trace/events/migrate.h
+++ b/include/trace/events/migrate.h
@@ -105,6 +105,37 @@ TRACE_EVENT(mm_migrate_pages_start,
 		  __print_symbolic(__entry->reason, MIGRATE_REASON))
 );
 
+DECLARE_EVENT_CLASS(migration_pte,
+
+		TP_PROTO(unsigned long addr, unsigned long pte, int order),
+
+		TP_ARGS(addr, pte, order),
+
+		TP_STRUCT__entry(
+			__field(unsigned long, addr)
+			__field(unsigned long, pte)
+			__field(int, order)
+		),
+
+		TP_fast_assign(
+			__entry->addr = addr;
+			__entry->pte = pte;
+			__entry->order = order;
+		),
+
+		TP_printk("addr=%lx, pte=%lx order=%d", __entry->addr, __entry->pte, __entry->order)
+);
+
+DEFINE_EVENT(migration_pte, set_migration_pte,
+	TP_PROTO(unsigned long addr, unsigned long pte, int order),
+	TP_ARGS(addr, pte, order)
+);
+
+DEFINE_EVENT(migration_pte, remove_migration_pte,
+	TP_PROTO(unsigned long addr, unsigned long pte, int order),
+	TP_ARGS(addr, pte, order)
+);
+
 #endif /* _TRACE_MIGRATE_H */
 
 /* This part must be outside protection */
diff --git a/mm/migrate.c b/mm/migrate.c
index c7da064b4781..253dc5812949 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -257,6 +257,9 @@ static bool remove_migration_pte(struct page *page, struct vm_area_struct *vma,
 		if (PageTransHuge(page) && PageMlocked(page))
 			clear_page_mlock(page);
 
+		trace_remove_migration_pte(pvmw.address, pte_val(pte),
+					   compound_order(new));
+
 		/* No need to invalidate - it was non-present before */
 		update_mmu_cache(vma, pvmw.address, pvmw.pte);
 	}
diff --git a/mm/rmap.c b/mm/rmap.c
index 6a1e8c7f6213..cce5dbae07f2 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -77,6 +77,7 @@
 #include <asm/tlbflush.h>
 
 #include <trace/events/tlb.h>
+#include <trace/events/migrate.h>
 
 #include "internal.h"
 
@@ -1861,6 +1862,8 @@ static bool try_to_migrate_one(struct page *page, struct vm_area_struct *vma,
 			if (pte_swp_uffd_wp(pteval))
 				swp_pte = pte_swp_mkuffd_wp(swp_pte);
 			set_pte_at(mm, pvmw.address, pvmw.pte, swp_pte);
+			trace_set_migration_pte(pvmw.address, pte_val(swp_pte),
+						compound_order(page));
 			/*
 			 * No need to invalidate here it will synchronize on
 			 * against the special swap migration pte.
@@ -1929,6 +1932,8 @@ static bool try_to_migrate_one(struct page *page, struct vm_area_struct *vma,
 			if (pte_uffd_wp(pteval))
 				swp_pte = pte_swp_mkuffd_wp(swp_pte);
 			set_pte_at(mm, address, pvmw.pte, swp_pte);
+			trace_set_migration_pte(address, pte_val(swp_pte),
+						compound_order(page));
 			/*
 			 * No need to invalidate here it will synchronize on
 			 * against the special swap migration pte.
-- 
2.20.1

Re: [PATCH V2 2/2] mm/migration: Add trace events for base page and HugeTLB migrations

[Matthew Wilcox]

On Tue, Jan 25, 2022 at 08:38:25AM +0530, Anshuman Khandual wrote:
> +		TP_printk("addr=%lx, pte=%lx order=%d", __entry->addr, __entry->pte, __entry->order)

In these days of increasingly advanced Rowhammer attacks, is it wise
to let userspace know exactly which physical addresses are being
used for virtual addresses?

Re: [PATCH V2 2/2] mm/migration: Add trace events for base page and HugeTLB migrations

[Steven Rostedt]

On Tue, 25 Jan 2022 13:28:49 +0000
Matthew Wilcox <willy@infradead.org> wrote:

> On Tue, Jan 25, 2022 at 08:38:25AM +0530, Anshuman Khandual wrote:
> > +		TP_printk("addr=%lx, pte=%lx order=%d", __entry->addr, __entry->pte, __entry->order)  
> 
> In these days of increasingly advanced Rowhammer attacks, is it wise
> to let userspace know exactly which physical addresses are being
> used for virtual addresses?

Is it an issue if this is only available for privileged users?

With tracing, you can just create a kprobe to get the same information for
you as well, so this isn't giving a user anything they do not already have.

-- Steve