arm64: mmu: Make __cpu_replace_ttbr1() out of line

__cpu_replace_ttbr1() is a static inline, and so it gets instantiated
wherever it is used. This is not really necessary, as it is never called
on a hot path. It also has the unfortunate side effect that the symbol
idmap_cpu_replace_ttbr1 may never be referenced from kCFI enabled C
code, and this means the type id symbol may not exist either.  This will
result in a build error once we start referring to this symbol from asm
code as well. (Note that this problem only occurs when CnP, KAsan and
suspend/resume are all disabled in the Kconfig but that is a valid
config, if unusual).

So let's just move it out of line so all callers will share the same
implementation, which will reference idmap_cpu_replace_ttbr1
unconditionally.
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Link: https://lore.kernel.org/r/20240214122845.2033971-62-ardb+git@google.comSigned-off-by: Catalin Marinas <catalin.marinas@arm.com>

arch/arm64/include/asm/mmu_context.h

@@ -148,37 +148,7 @@ static inline void cpu_install_ttbr0(phys_addr_t ttbr0, unsigned long t0sz)
 	isb();
 }
 
-/*
- * Atomically replaces the active TTBR1_EL1 PGD with a new VA-compatible PGD,
- * avoiding the possibility of conflicting TLB entries being allocated.
- */
-static inline void __cpu_replace_ttbr1(pgd_t *pgdp, pgd_t *idmap, bool cnp)
-{
-	typedef void (ttbr_replace_func)(phys_addr_t);
-	extern ttbr_replace_func idmap_cpu_replace_ttbr1;
-	ttbr_replace_func *replace_phys;
-	unsigned long daif;
-
-	/* phys_to_ttbr() zeros lower 2 bits of ttbr with 52-bit PA */
-	phys_addr_t ttbr1 = phys_to_ttbr(virt_to_phys(pgdp));
-
-	if (cnp)
-		ttbr1 |= TTBR_CNP_BIT;
-
-	replace_phys = (void *)__pa_symbol(idmap_cpu_replace_ttbr1);
-
-	__cpu_install_idmap(idmap);
-
-	/*
-	 * We really don't want to take *any* exceptions while TTBR1 is
-	 * in the process of being replaced so mask everything.
-	 */
-	daif = local_daif_save();
-	replace_phys(ttbr1);
-	local_daif_restore(daif);
-
-	cpu_uninstall_idmap();
-}
+void __cpu_replace_ttbr1(pgd_t *pgdp, pgd_t *idmap, bool cnp);
 
 static inline void cpu_enable_swapper_cnp(void)
 {

arch/arm64/mm/mmu.c

@@ -1486,3 +1486,35 @@ void ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, pte
 {
 	set_pte_at(vma->vm_mm, addr, ptep, pte);
 }
+
+/*
+ * Atomically replaces the active TTBR1_EL1 PGD with a new VA-compatible PGD,
+ * avoiding the possibility of conflicting TLB entries being allocated.
+ */
+void __cpu_replace_ttbr1(pgd_t *pgdp, pgd_t *idmap, bool cnp)
+{
+	typedef void (ttbr_replace_func)(phys_addr_t);
+	extern ttbr_replace_func idmap_cpu_replace_ttbr1;
+	ttbr_replace_func *replace_phys;
+	unsigned long daif;
+
+	/* phys_to_ttbr() zeros lower 2 bits of ttbr with 52-bit PA */
+	phys_addr_t ttbr1 = phys_to_ttbr(virt_to_phys(pgdp));
+
+	if (cnp)
+		ttbr1 |= TTBR_CNP_BIT;
+
+	replace_phys = (void *)__pa_symbol(idmap_cpu_replace_ttbr1);
+
+	__cpu_install_idmap(idmap);
+
+	/*
+	 * We really don't want to take *any* exceptions while TTBR1 is
+	 * in the process of being replaced so mask everything.
+	 */
+	daif = local_daif_save();
+	replace_phys(ttbr1);
+	local_daif_restore(daif);
+
+	cpu_uninstall_idmap();
+}