arm64: mm: Add support for folding PUDs at runtime

In order to support LPA2 on 16k pages in a way that permits non-LPA2
systems to run the same kernel image, we have to be able to fall back to
at most 48 bits of virtual addressing.

Falling back to 48 bits would result in a level 0 with only 2 entries,
which is suboptimal in terms of TLB utilization. So instead, let's fall
back to 47 bits in that case. This means we need to be able to fold PUDs
dynamically, similar to how we fold P4Ds for 48 bit virtual addressing
on LPA2 with 4k pages.

Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Link: https://lore.kernel.org/r/20240214122845.2033971-81-ardb+git@google.com
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>

arch/arm64/include/asm/pgalloc.h

@@ -14,6 +14,7 @@
 #include <asm/tlbflush.h>
 
 #define __HAVE_ARCH_PGD_FREE
+#define __HAVE_ARCH_PUD_FREE
 #include <asm-generic/pgalloc.h>
 
 #define PGD_SIZE	(PTRS_PER_PGD * sizeof(pgd_t))
@@ -43,7 +44,8 @@ static inline void __pud_populate(pud_t *pudp, phys_addr_t pmdp, pudval_t prot)
 
 static inline void __p4d_populate(p4d_t *p4dp, phys_addr_t pudp, p4dval_t prot)
 {
-	set_p4d(p4dp, __p4d(__phys_to_p4d_val(pudp) | prot));
+	if (pgtable_l4_enabled())
+		set_p4d(p4dp, __p4d(__phys_to_p4d_val(pudp) | prot));
 }
 
 static inline void p4d_populate(struct mm_struct *mm, p4d_t *p4dp, pud_t *pudp)
@@ -53,6 +55,14 @@ static inline void p4d_populate(struct mm_struct *mm, p4d_t *p4dp, pud_t *pudp)
 	p4dval |= (mm == &init_mm) ? P4D_TABLE_UXN : P4D_TABLE_PXN;
 	__p4d_populate(p4dp, __pa(pudp), p4dval);
 }
+
+static inline void pud_free(struct mm_struct *mm, pud_t *pud)
+{
+	if (!pgtable_l4_enabled())
+		return;
+	BUG_ON((unsigned long)pud & (PAGE_SIZE-1));
+	free_page((unsigned long)pud);
+}
 #else
 static inline void __p4d_populate(p4d_t *p4dp, phys_addr_t pudp, p4dval_t prot)
 {

arch/arm64/include/asm/pgtable.h

@@ -759,12 +759,27 @@ static inline pmd_t *pud_pgtable(pud_t pud)
 
 #if CONFIG_PGTABLE_LEVELS > 3
 
+static __always_inline bool pgtable_l4_enabled(void)
+{
+	if (CONFIG_PGTABLE_LEVELS > 4 || !IS_ENABLED(CONFIG_ARM64_LPA2))
+		return true;
+	if (!alternative_has_cap_likely(ARM64_ALWAYS_BOOT))
+		return vabits_actual == VA_BITS;
+	return alternative_has_cap_unlikely(ARM64_HAS_VA52);
+}
+
+static inline bool mm_pud_folded(const struct mm_struct *mm)
+{
+	return !pgtable_l4_enabled();
+}
+#define mm_pud_folded  mm_pud_folded
+
 #define pud_ERROR(e)	\
 	pr_err("%s:%d: bad pud %016llx.\n", __FILE__, __LINE__, pud_val(e))
 
-#define p4d_none(p4d)		(!p4d_val(p4d))
-#define p4d_bad(p4d)		(!(p4d_val(p4d) & 2))
-#define p4d_present(p4d)	(p4d_val(p4d))
+#define p4d_none(p4d)		(pgtable_l4_enabled() && !p4d_val(p4d))
+#define p4d_bad(p4d)		(pgtable_l4_enabled() && !(p4d_val(p4d) & 2))
+#define p4d_present(p4d)	(!p4d_none(p4d))
 
 static inline void set_p4d(p4d_t *p4dp, p4d_t p4d)
 {
@@ -780,7 +795,8 @@ static inline void set_p4d(p4d_t *p4dp, p4d_t p4d)
 
 static inline void p4d_clear(p4d_t *p4dp)
 {
-	set_p4d(p4dp, __p4d(0));
+	if (pgtable_l4_enabled())
+		set_p4d(p4dp, __p4d(0));
 }
 
 static inline phys_addr_t p4d_page_paddr(p4d_t p4d)
@@ -788,25 +804,74 @@ static inline phys_addr_t p4d_page_paddr(p4d_t p4d)
 	return __p4d_to_phys(p4d);
 }
 
+#define pud_index(addr)		(((addr) >> PUD_SHIFT) & (PTRS_PER_PUD - 1))
+
+static inline pud_t *p4d_to_folded_pud(p4d_t *p4dp, unsigned long addr)
+{
+	return (pud_t *)PTR_ALIGN_DOWN(p4dp, PAGE_SIZE) + pud_index(addr);
+}
+
 static inline pud_t *p4d_pgtable(p4d_t p4d)
 {
 	return (pud_t *)__va(p4d_page_paddr(p4d));
 }
 
-/* Find an entry in the first-level page table. */
-#define pud_offset_phys(dir, addr)	(p4d_page_paddr(READ_ONCE(*(dir))) + pud_index(addr) * sizeof(pud_t))
+static inline phys_addr_t pud_offset_phys(p4d_t *p4dp, unsigned long addr)
+{
+	BUG_ON(!pgtable_l4_enabled());
 
-#define pud_set_fixmap(addr)		((pud_t *)set_fixmap_offset(FIX_PUD, addr))
-#define pud_set_fixmap_offset(p4d, addr)	pud_set_fixmap(pud_offset_phys(p4d, addr))
-#define pud_clear_fixmap()		clear_fixmap(FIX_PUD)
+	return p4d_page_paddr(READ_ONCE(*p4dp)) + pud_index(addr) * sizeof(pud_t);
+}
+
+static inline
+pud_t *pud_offset_lockless(p4d_t *p4dp, p4d_t p4d, unsigned long addr)
+{
+	if (!pgtable_l4_enabled())
+		return p4d_to_folded_pud(p4dp, addr);
+	return (pud_t *)__va(p4d_page_paddr(p4d)) + pud_index(addr);
+}
+#define pud_offset_lockless pud_offset_lockless
+
+static inline pud_t *pud_offset(p4d_t *p4dp, unsigned long addr)
+{
+	return pud_offset_lockless(p4dp, READ_ONCE(*p4dp), addr);
+}
+#define pud_offset	pud_offset
+
+static inline pud_t *pud_set_fixmap(unsigned long addr)
+{
+	if (!pgtable_l4_enabled())
+		return NULL;
+	return (pud_t *)set_fixmap_offset(FIX_PUD, addr);
+}
+
+static inline pud_t *pud_set_fixmap_offset(p4d_t *p4dp, unsigned long addr)
+{
+	if (!pgtable_l4_enabled())
+		return p4d_to_folded_pud(p4dp, addr);
+	return pud_set_fixmap(pud_offset_phys(p4dp, addr));
+}
+
+static inline void pud_clear_fixmap(void)
+{
+	if (pgtable_l4_enabled())
+		clear_fixmap(FIX_PUD);
+}
+
+/* use ONLY for statically allocated translation tables */
+static inline pud_t *pud_offset_kimg(p4d_t *p4dp, u64 addr)
+{
+	if (!pgtable_l4_enabled())
+		return p4d_to_folded_pud(p4dp, addr);
+	return (pud_t *)__phys_to_kimg(pud_offset_phys(p4dp, addr));
+}
 
 #define p4d_page(p4d)		pfn_to_page(__phys_to_pfn(__p4d_to_phys(p4d)))
 
-/* use ONLY for statically allocated translation tables */
-#define pud_offset_kimg(dir,addr)	((pud_t *)__phys_to_kimg(pud_offset_phys((dir), (addr))))
-
 #else
 
+static inline bool pgtable_l4_enabled(void) { return false; }
+
 #define p4d_page_paddr(p4d)	({ BUILD_BUG(); 0;})
 
 /* Match pud_offset folding in <asm/generic/pgtable-nopud.h> */

arch/arm64/include/asm/tlb.h

@@ -103,6 +103,9 @@ static inline void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pudp,
 {
 	struct ptdesc *ptdesc = virt_to_ptdesc(pudp);
 
+	if (!pgtable_l4_enabled())
+		return;
+
 	pagetable_pud_dtor(ptdesc);
 	tlb_remove_ptdesc(tlb, ptdesc);
 }

arch/arm64/kernel/cpufeature.c

@@ -1767,6 +1767,8 @@ static int __init __kpti_install_ng_mappings(void *__unused)
 
 	if (levels == 5 && !pgtable_l5_enabled())
 		levels = 4;
+	else if (levels == 4 && !pgtable_l4_enabled())
+		levels = 3;
 
 	remap_fn = (void *)__pa_symbol(idmap_kpti_install_ng_mappings);
 

arch/arm64/mm/mmu.c

@@ -1065,7 +1065,7 @@ static void free_empty_pud_table(p4d_t *p4dp, unsigned long addr,
 		free_empty_pmd_table(pudp, addr, next, floor, ceiling);
 	} while (addr = next, addr < end);
 
-	if (CONFIG_PGTABLE_LEVELS <= 3)
+	if (!pgtable_l4_enabled())
 		return;
 
 	if (!pgtable_range_aligned(start, end, floor, ceiling, P4D_MASK))

arch/arm64/mm/pgd.c

@@ -21,6 +21,8 @@ static bool pgdir_is_page_size(void)
 {
 	if (PGD_SIZE == PAGE_SIZE)
 		return true;
+	if (CONFIG_PGTABLE_LEVELS == 4)
+		return !pgtable_l4_enabled();
 	if (CONFIG_PGTABLE_LEVELS == 5)
 		return !pgtable_l5_enabled();
 	return false;