[PATCH 1/8] mm: Add ptep_try_install() for lockless empty-slot installs

[Tejun Heo]

Add ptep_try_install(ptep, new_pte): atomically set *ptep to new_pte
iff it is currently pte_none(). Returns true on success, false if the
slot was already populated or the arch has no implementation.

The intended caller is the upcoming bpf_arena kernel-side fault
recovery path. The install runs from a page fault and may have to
contend with locks already held by the faulting kernel caller, so
keeping it lock-free via cmpxchg is the safe choice.

The generic version in <linux/pgtable.h> returns false. x86 and arm64
override with try_cmpxchg-based implementations on the underlying
pteval. Other architectures get the false stub - the callers there
already fall through to oops.

Suggested-by: Kumar Kartikeya Dwivedi <memxor at gmail.com>
Suggested-by: Alexei Starovoitov <ast at kernel.org>
Signed-off-by: Tejun Heo <tj at kernel.org>
---
 arch/arm64/include/asm/pgtable.h |  8 ++++++++
 arch/x86/include/asm/pgtable.h   |  8 ++++++++
 include/linux/pgtable.h          | 16 ++++++++++++++++
 3 files changed, 32 insertions(+)

diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index 9029b81ccbe8..eb1dd59aaea3 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -1830,6 +1830,14 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm,
 	return __ptep_get_and_clear(mm, addr, ptep);
 }
 
+#define __HAVE_ARCH_PTEP_TRY_INSTALL
+static inline bool ptep_try_install(pte_t *ptep, pte_t new_pte)
+{
+	pteval_t old = 0;
+
+	return try_cmpxchg(&pte_val(*ptep), &old, pte_val(new_pte));
+}
+
 #define test_and_clear_young_ptes test_and_clear_young_ptes
 static inline bool test_and_clear_young_ptes(struct vm_area_struct *vma,
 		unsigned long addr, pte_t *ptep, unsigned int nr)
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 13e3e9a054cb..afff54a77ffd 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -1284,6 +1284,14 @@ static inline void ptep_set_wrprotect(struct mm_struct *mm,
 	} while (!try_cmpxchg((long *)&ptep->pte, (long *)&old_pte, *(long *)&new_pte));
 }
 
+#define __HAVE_ARCH_PTEP_TRY_INSTALL
+static inline bool ptep_try_install(pte_t *ptep, pte_t new_pte)
+{
+	pte_t old_pte = __pte(0);
+
+	return try_cmpxchg((long *)&ptep->pte, (long *)&old_pte, *(long *)&new_pte);
+}
+
 #define flush_tlb_fix_spurious_fault(vma, address, ptep) do { } while (0)
 
 #define  __HAVE_ARCH_PMDP_SET_ACCESS_FLAGS
diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
index cdd68ed3ae1a..60a4afdc9131 100644
--- a/include/linux/pgtable.h
+++ b/include/linux/pgtable.h
@@ -1036,6 +1036,22 @@ static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addres
 }
 #endif
 
+#ifndef __HAVE_ARCH_PTEP_TRY_INSTALL
+/**
+ * ptep_try_install - atomically install an empty PTE
+ * @ptep: page table entry
+ * @new_pte: value to install
+ *
+ * Atomically set *@ptep to @new_pte iff *@ptep is pte_none(). Return
+ * true on success. Architectures opt in by providing a cmpxchg-based
+ * override. The generic stub returns false.
+ */
+static inline bool ptep_try_install(pte_t *ptep, pte_t new_pte)
+{
+	return false;
+}
+#endif
+
 #ifndef wrprotect_ptes
 /**
  * wrprotect_ptes - Write-protect PTEs that map consecutive pages of the same
-- 
2.54.0