diff mbox series

[RFC,v3,17/21] mm/pgtable: optimize pmdp_get() and friends for folded pagetable levels

Message ID 20260902-dummy_ptxp3-v3-17-5d8f5b17c25c@arm.com
State New
Headers show
Series mm: change behavior of pXdp_get()/pXd_page() in compile-time folded pgtable | expand

Commit Message

Yeoreum Yun Sept. 2, 2026, 11:56 a.m. UTC 
From: "David Hildenbrand (Arm)" <david@kernel.org>

Using pmdp_get() and friends in common code on a kernel config with
folded page tables is suboptimal: they default to a READ_ONCE(), forcing
the compiler to actually read that value even though it will not actually
be used afterwards.

This was recently reported by Christophe Leroy [1] and block conversion
of more common code to pmdp_get() and friends.

(using pgdp_get() as one example)

Most of the code ignores the result from pgdp_get() on configs with
folded page tables entirely, as it's hardcoded:

        pgd_present()==1 && pgd_leaf()==false

Common code will just treat it as a "this is a page table" and call
p4d_offset() or p4d_offset_lockless() for the next lower level, where
the obtained pgdp_get() result is ignored entirely.

So, return a dummy value and avoid any memory reads.

There is a catch, though:

1) If code calls pgd_val() and somehow relies on the data, it would now
   see dummy values. The code really must be aware of folded page table
   levels. Fortunately, code usually ignores pgd_val() completely for
   page tables (with ptdump being one exception when calculating
   effective permissions). it's checked + fixed the x86 ptdump mechanism.

2) If code passes the pgd_t to a function that would work on the result,
   it would now see dummy values. The only concern is really passing
   the pgd_t on the stack as a pointer to p4d_offset(). Most code that
   would do that, should actually use p4d_offset_lockless(), which
   handles this properly. it's checked + fixed problematic instances.

3) Calling set_pgd() / pgd_page() / pgd_page_vaddr() with a pgd_t obtained through
   pgdp_get(). There was once such case in riscv code with set_pgd(), which
   is fixed.

As an example, this is the generated code for perf_get_page_size() with
PGTABLE_LEVELS=3 on arm64:

Before:
00000000000052a0 <perf_get_page_size>:
    ...
    52dc: d53b4234      mrs     x20, DAIF
    52e0: d50343df      msr     DAIFSet, #0x3
    ...
    52fc: d35e9a69      ubfx    x9, x19, #30, #9        /* pud_offset_lockless() */
    5300: f9403508      ldr     x8, [x8, #0x68]
    5304: f869790a      ldr     x10, [x8, x9, lsl #3]   /* pudp_get() */
    5308: f90007ea      str     x10, [sp, #0x8]
    530c: f8697908      ldr     x8, [x8, x9, lsl #3]    /* pudp_get() */
    ...
    5360: 90000009      adrp    x9, 0x5000 <perf_prepare_sample+0x548>
    5364: 92746908      and     x8, x8, #0x7ffffff000
    5368: d3557675      ubfx    x21, x19, #21, #9       /* pmd_offset_lockless() */
    ...
    5394: f8757ac8      ldr     x8, [x22, x21, lsl #3]  /* pmdp_get() */

After:
0000000000052a0 <perf_get_page_size>:
    ...
    52dc: d53b4234      mrs     x20, DAIF
    52e0: d50343df      msr     DAIFSet, #0x3
    ...                                                 /* no pud_offset_lockless() and pudp_get() */
    5318: 90000009      adrp    x9, 0x5000 <perf_prepare_sample+0x548>
    531c: 92746908      and     x8, x8, #0x7ffffff000
    5320: d3557675      ubfx    x21, x19, #21, #9       /* pmd_offset_lockless() */
    ...
    5334: f8757ac8      ldr     x8, [x22, x21, lsl #3]  /* pmdp_get() */

[1] https://lore.kernel.org/all/0019d675-ce3d-4a5c-89ed-f126c45145c9@kernel.org/

Signed-off-by: David Hildenbrand (Arm) <david@kernel.org>
---
 include/asm-generic/pgtable-nop4d.h | 8 ++++++++
 include/asm-generic/pgtable-nopmd.h | 8 ++++++++
 include/asm-generic/pgtable-nopud.h | 8 ++++++++
 3 files changed, 24 insertions(+)
diff mbox series

Patch

diff --git a/include/asm-generic/pgtable-nop4d.h b/include/asm-generic/pgtable-nop4d.h
index 019c3f074b77..acd62ee23353 100644
--- a/include/asm-generic/pgtable-nop4d.h
+++ b/include/asm-generic/pgtable-nop4d.h
@@ -34,6 +34,14 @@  static inline bool pgd_leaf(pgd_t pgd)		{ return false; }
  */
 #define set_pgd(pgdptr, pgdval)	set_p4d((p4d_t *)(pgdptr), (p4d_t) { pgdval })
 
+static inline pgd_t pgdp_get(pgd_t *pgdp)
+{
+	pgd_t dummy = { 0 };
+
+	return dummy;
+}
+#define pgdp_get pgdp_get
+
 static inline p4d_t *p4d_offset(pgd_t *pgd, unsigned long address)
 {
 	return (p4d_t *)pgd;
diff --git a/include/asm-generic/pgtable-nopmd.h b/include/asm-generic/pgtable-nopmd.h
index 1dd5b165234b..9322f07ddf1e 100644
--- a/include/asm-generic/pgtable-nopmd.h
+++ b/include/asm-generic/pgtable-nopmd.h
@@ -43,6 +43,14 @@  static inline void pud_clear(pud_t *pud)	{ }
  */
 #define set_pud(pudptr, pudval)			set_pmd((pmd_t *)(pudptr), (pmd_t) { pudval })
 
+static inline pud_t pudp_get(pud_t *pudp)
+{
+	pud_t dummy = { 0 };
+
+	return dummy;
+}
+#define pudp_get pudp_get
+
 static inline pmd_t * pmd_offset(pud_t * pud, unsigned long address)
 {
 	return (pmd_t *)pud;
diff --git a/include/asm-generic/pgtable-nopud.h b/include/asm-generic/pgtable-nopud.h
index 5a2b0a81ae19..8f01abbb0050 100644
--- a/include/asm-generic/pgtable-nopud.h
+++ b/include/asm-generic/pgtable-nopud.h
@@ -41,6 +41,14 @@  static inline bool p4d_leaf(p4d_t p4d)		{ return false; }
  */
 #define set_p4d(p4dptr, p4dval)	set_pud((pud_t *)(p4dptr), (pud_t) { p4dval })
 
+static inline p4d_t p4dp_get(p4d_t *p4dp)
+{
+	p4d_t dummy = { 0 };
+
+	return dummy;
+}
+#define p4dp_get p4dp_get
+
 static inline pud_t *pud_offset(p4d_t *p4d, unsigned long address)
 {
 	return (pud_t *)p4d;