[RFC PATCH 34/34] arm64: pgtable: convert pte_present() from macro to static inline

pte_present() is used as the basis for both pmd_present() and pud_present().
It is currently implemented as a macro composed of pte_val() and
pte_present_invalid().

When pte_present() or its higher-level variants are used directly with
ptep_get() or pXdp_get(), for example:

  pte_present(ptep_get(pte));
  pmd_present(pmdp_get(pmd));
  pud_present(pudp_get(pud));

the macro expansion causes the compiler to evaluate the argument twice,
resulting in redundant loads. For example, pte_present() expands to:

  !pte_val(READ_ONCE(*pte) || pte_present_invalid(READ_ONCE(*pte))

A typical example is pud_free_pmd_page(), where the expansion of
pmd_present() generates:
    ...
    /* pmd_present() (x20 = pmdp) */
    1b88: f9400288     ldr	x8, [x20]        // read pmdp.
    1b8c: f9000fa8     str	x8, [x29, #0x18]
    1b90: 3707fec8     tbnz	w8, #0x0, 0x1b68 <pud_free_pmd_page+0xd0>
    1b94: f9400288     ldr	x8, [x20]        // redundant read of pmdp.
    1b98: 8a170109     and	x9, x8, x23
    1b9c: f9000fa8     str	x8, [x29, #0x18]
    1ba0: f120013f     cmp	x9, #0x800
    1ba4: 54fffe20     b.eq	0x1b68 <pud_free_pmd_page+0xd0>
    1ba8: 17fffff4     b	0x1b78 <pud_free_pmd_page+0xe0>
    ...

Convert pte_present() to static inline function so that prevent the
generation of redundant code and move pte_valid() and
pte_present_invalid() further up so the inline function can use them.

After this change, the generated code becomes:
    ...
    /* pmd_present() (x20 = pmdp) */
    1a30: f9400288     ldr	x8, [x20]
    1a34: 8a170109     and	x9, x8, x23
    1a38: f9000fa8     str	x8, [x29, #0x18]
    1a3c: f120013f     cmp	x9, #0x800
    1a40: 54fffe80     b.eq	0x1a10 <pud_free_pmd_page+0xd0>
    1a44: 3607fee8     tbz	w8, #0x0, 0x1a20 <pud_free_pmd_page+0xe0>
    1a48: 17fffff2     b	0x1a10 <pud_free_pmd_page+0xd0>
    ...

This eliminates the redundant load and also reduces code size at
call sites using this pattern. For example, pud_free_pmd_page() shrinks
from 7,500 bytes to 7,148 bytes, a reduction of approximately 4.7%.

Signed-off-by: Yeoreum Yun <[email protected]>
---
 arch/arm64/include/asm/pgtable.h | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index 6185fc291fd7d..aaae3d14895f6 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -140,10 +140,17 @@ static inline pteval_t __phys_to_pte_val(phys_addr_t phys)
 #define pte_none(pte)		(!pte_val(pte))
 #define pte_page(pte)		(pfn_to_page(pte_pfn(pte)))
 
+#define pte_valid(pte)		(!!(pte_val(pte) & PTE_VALID))
+#define pte_present_invalid(pte) \
+	((pte_val(pte) & (PTE_VALID | PTE_PRESENT_INVALID)) == PTE_PRESENT_INVALID)
+
 /*
  * The following only work if pte_present(). Undefined behaviour otherwise.
  */
-#define pte_present(pte)	(pte_valid(pte) || pte_present_invalid(pte))
+static __always_inline bool pte_present(pte_t pte)
+{
+	return pte_valid(pte) || pte_present_invalid(pte);
+}
 #define pte_young(pte)		(!!(pte_val(pte) & PTE_AF))
 #define pte_special(pte)	(!!(pte_val(pte) & PTE_SPECIAL))
 #define pte_write(pte)		(!!(pte_val(pte) & PTE_WRITE))
@@ -168,9 +175,6 @@ static inline pteval_t __phys_to_pte_val(phys_addr_t phys)
 #define pte_sw_dirty(pte)	(!!(pte_val(pte) & PTE_DIRTY))
 #define pte_dirty(pte)		(pte_sw_dirty(pte) || pte_hw_dirty(pte))
 
-#define pte_valid(pte)		(!!(pte_val(pte) & PTE_VALID))
-#define pte_present_invalid(pte) \
-	((pte_val(pte) & (PTE_VALID | PTE_PRESENT_INVALID)) == PTE_PRESENT_INVALID)
 /*
  * Execute-only user mappings do not have the PTE_USER bit set. All valid
  * kernel mappings have the PTE_UXN bit set.
-- 
LEVI:{C3F47F37-75D8-414A-A8BA-3980EC8A46D7}