powerpc/book3s64/kuap: Use Key 3 for kernel mapping with hash translation

This patch updates kernel hash page table entries to use storage key 3
for its mapping. This implies all kernel access will now use key 3 to
control READ/WRITE. The patch also prevents the allocation of key 3 from
userspace and UAMOR value is updated such that userspace cannot modify key 3.
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Reviewed-by: Sandipan Das <sandipan@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20201127044424.40686-9-aneesh.kumar@linux.ibm.com

arch/powerpc/include/asm/book3s/64/hash-pkey.h

@@ -2,6 +2,9 @@
 #ifndef _ASM_POWERPC_BOOK3S_64_HASH_PKEY_H
 #define _ASM_POWERPC_BOOK3S_64_HASH_PKEY_H
 
+/*  We use key 3 for KERNEL */
+#define HASH_DEFAULT_KERNEL_KEY (HPTE_R_KEY_BIT0 | HPTE_R_KEY_BIT1)
+
 static inline u64 hash__vmflag_to_pte_pkey_bits(u64 vm_flags)
 {
 	return (((vm_flags & VM_PKEY_BIT0) ? H_PTE_PKEY_BIT0 : 0x0UL) |
@@ -11,13 +14,23 @@ static inline u64 hash__vmflag_to_pte_pkey_bits(u64 vm_flags)
 		((vm_flags & VM_PKEY_BIT4) ? H_PTE_PKEY_BIT4 : 0x0UL));
 }
 
-static inline u64 pte_to_hpte_pkey_bits(u64 pteflags)
+static inline u64 pte_to_hpte_pkey_bits(u64 pteflags, unsigned long flags)
 {
-	return (((pteflags & H_PTE_PKEY_BIT4) ? HPTE_R_KEY_BIT4 : 0x0UL) |
+	unsigned long pte_pkey;
+
+	pte_pkey = (((pteflags & H_PTE_PKEY_BIT4) ? HPTE_R_KEY_BIT4 : 0x0UL) |
 		    ((pteflags & H_PTE_PKEY_BIT3) ? HPTE_R_KEY_BIT3 : 0x0UL) |
 		    ((pteflags & H_PTE_PKEY_BIT2) ? HPTE_R_KEY_BIT2 : 0x0UL) |
 		    ((pteflags & H_PTE_PKEY_BIT1) ? HPTE_R_KEY_BIT1 : 0x0UL) |
 		    ((pteflags & H_PTE_PKEY_BIT0) ? HPTE_R_KEY_BIT0 : 0x0UL));
+
+	if (mmu_has_feature(MMU_FTR_BOOK3S_KUAP) ||
+	    mmu_has_feature(MMU_FTR_BOOK3S_KUEP)) {
+		if ((pte_pkey == 0) && (flags & HPTE_USE_KERNEL_KEY))
+			return HASH_DEFAULT_KERNEL_KEY;
+	}
+
+	return pte_pkey;
 }
 
 static inline u16 hash__pte_to_pkey_bits(u64 pteflags)

arch/powerpc/include/asm/book3s/64/hash.h

@@ -145,7 +145,7 @@ extern void hash__mark_initmem_nx(void);
 
 extern void hpte_need_flush(struct mm_struct *mm, unsigned long addr,
 			    pte_t *ptep, unsigned long pte, int huge);
-extern unsigned long htab_convert_pte_flags(unsigned long pteflags);
+unsigned long htab_convert_pte_flags(unsigned long pteflags, unsigned long flags);
 /* Atomic PTE updates */
 static inline unsigned long hash__pte_update(struct mm_struct *mm,
 					 unsigned long addr,

arch/powerpc/include/asm/book3s/64/mmu-hash.h

@@ -452,6 +452,7 @@ static inline unsigned long hpt_hash(unsigned long vpn,
 
 #define HPTE_LOCAL_UPDATE	0x1
 #define HPTE_NOHPTE_UPDATE	0x2
+#define HPTE_USE_KERNEL_KEY	0x4
 
 extern int __hash_page_4K(unsigned long ea, unsigned long access,
 			  unsigned long vsid, pte_t *ptep, unsigned long trap,

arch/powerpc/include/asm/mmu_context.h

@@ -286,7 +286,7 @@ static inline bool arch_vma_access_permitted(struct vm_area_struct *vma,
 #define thread_pkey_regs_init(thread)
 #define arch_dup_pkeys(oldmm, mm)
 
-static inline u64 pte_to_hpte_pkey_bits(u64 pteflags)
+static inline u64 pte_to_hpte_pkey_bits(u64 pteflags, unsigned long flags)
 {
 	return 0x0UL;
 }

arch/powerpc/mm/book3s64/hash_4k.c

@@ -54,7 +54,7 @@ int __hash_page_4K(unsigned long ea, unsigned long access, unsigned long vsid,
 	 * PP bits. _PAGE_USER is already PP bit 0x2, so we only
 	 * need to add in 0x1 if it's a read-only user page
 	 */
-	rflags = htab_convert_pte_flags(new_pte);
+	rflags = htab_convert_pte_flags(new_pte, flags);
 	rpte = __real_pte(__pte(old_pte), ptep, PTRS_PER_PTE);
 
 	if (cpu_has_feature(CPU_FTR_NOEXECUTE) &&

arch/powerpc/mm/book3s64/hash_64k.c

@@ -72,7 +72,7 @@ int __hash_page_4K(unsigned long ea, unsigned long access, unsigned long vsid,
 	 * Handle the subpage protection bits
 	 */
 	subpg_pte = new_pte & ~subpg_prot;
-	rflags = htab_convert_pte_flags(subpg_pte);
+	rflags = htab_convert_pte_flags(subpg_pte, flags);
 
 	if (cpu_has_feature(CPU_FTR_NOEXECUTE) &&
 	    !cpu_has_feature(CPU_FTR_COHERENT_ICACHE)) {
@@ -260,7 +260,7 @@ int __hash_page_64K(unsigned long ea, unsigned long access,
 			new_pte |= _PAGE_DIRTY;
 	} while (!pte_xchg(ptep, __pte(old_pte), __pte(new_pte)));
 
-	rflags = htab_convert_pte_flags(new_pte);
+	rflags = htab_convert_pte_flags(new_pte, flags);
 	rpte = __real_pte(__pte(old_pte), ptep, PTRS_PER_PTE);
 
 	if (cpu_has_feature(CPU_FTR_NOEXECUTE) &&

arch/powerpc/mm/book3s64/hash_hugepage.c

@@ -57,7 +57,7 @@ int __hash_page_thp(unsigned long ea, unsigned long access, unsigned long vsid,
 	if (!(old_pmd & (H_PAGE_THP_HUGE | _PAGE_DEVMAP)))
 		return 0;
 
-	rflags = htab_convert_pte_flags(new_pmd);
+	rflags = htab_convert_pte_flags(new_pmd, flags);
 
 #if 0
 	if (!cpu_has_feature(CPU_FTR_COHERENT_ICACHE)) {

arch/powerpc/mm/book3s64/hash_hugetlbpage.c

@@ -70,7 +70,7 @@ int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid,
 	if (old_pte & (H_PAGE_THP_HUGE | _PAGE_DEVMAP))
 		return 0;
 
-	rflags = htab_convert_pte_flags(new_pte);
+	rflags = htab_convert_pte_flags(new_pte, flags);
 	if (unlikely(mmu_psize == MMU_PAGE_16G))
 		offset = PTRS_PER_PUD;
 	else

arch/powerpc/mm/book3s64/hash_pgtable.c

@@ -443,7 +443,7 @@ void hash__mark_initmem_nx(void)
 	start = (unsigned long)__init_begin;
 	end = (unsigned long)__init_end;
 
-	pp = htab_convert_pte_flags(pgprot_val(PAGE_KERNEL));
+	pp = htab_convert_pte_flags(pgprot_val(PAGE_KERNEL), HPTE_USE_KERNEL_KEY);
 
 	WARN_ON(!hash__change_memory_range(start, end, pp));
 }

arch/powerpc/mm/book3s64/hash_utils.c

@@ -186,7 +186,7 @@ static struct mmu_psize_def mmu_psize_defaults_gp[] = {
  *    - We make sure R is always set and never lost
  *    - C is _PAGE_DIRTY, and *should* always be set for a writeable mapping
  */
-unsigned long htab_convert_pte_flags(unsigned long pteflags)
+unsigned long htab_convert_pte_flags(unsigned long pteflags, unsigned long flags)
 {
 	unsigned long rflags = 0;
 
@@ -240,7 +240,7 @@ unsigned long htab_convert_pte_flags(unsigned long pteflags)
 		 */
 		rflags |= HPTE_R_M;
 
-	rflags |= pte_to_hpte_pkey_bits(pteflags);
+	rflags |= pte_to_hpte_pkey_bits(pteflags, flags);
 	return rflags;
 }
 
@@ -255,7 +255,7 @@ int htab_bolt_mapping(unsigned long vstart, unsigned long vend,
 	shift = mmu_psize_defs[psize].shift;
 	step = 1 << shift;
 
-	prot = htab_convert_pte_flags(prot);
+	prot = htab_convert_pte_flags(prot, HPTE_USE_KERNEL_KEY);
 
 	DBG("htab_bolt_mapping(%lx..%lx -> %lx (%lx,%d,%d)\n",
 	    vstart, vend, pstart, prot, psize, ssize);
@@ -1316,12 +1316,14 @@ int hash_page_mm(struct mm_struct *mm, unsigned long ea,
 		vsid = get_kernel_vsid(ea, mmu_kernel_ssize);
 		psize = mmu_vmalloc_psize;
 		ssize = mmu_kernel_ssize;
+		flags |= HPTE_USE_KERNEL_KEY;
 		break;
 
 	case IO_REGION_ID:
 		vsid = get_kernel_vsid(ea, mmu_kernel_ssize);
 		psize = mmu_io_psize;
 		ssize = mmu_kernel_ssize;
+		flags |= HPTE_USE_KERNEL_KEY;
 		break;
 	default:
 		/*
@@ -1900,7 +1902,7 @@ static void kernel_map_linear_page(unsigned long vaddr, unsigned long lmi)
 	unsigned long hash;
 	unsigned long vsid = get_kernel_vsid(vaddr, mmu_kernel_ssize);
 	unsigned long vpn = hpt_vpn(vaddr, vsid, mmu_kernel_ssize);
-	unsigned long mode = htab_convert_pte_flags(pgprot_val(PAGE_KERNEL));
+	unsigned long mode = htab_convert_pte_flags(pgprot_val(PAGE_KERNEL), HPTE_USE_KERNEL_KEY);
 	long ret;
 
 	hash = hpt_hash(vpn, PAGE_SHIFT, mmu_kernel_ssize);

arch/powerpc/mm/book3s64/pkeys.c

@@ -205,6 +205,18 @@ void __init pkey_early_init_devtree(void)
 	reserved_allocation_mask |= (0x1 << 1);
 	default_uamor &= ~(0x3ul << pkeyshift(1));
 
+	/*  handle key which is used by kernel for KAUP */
+	reserved_allocation_mask |= (0x1 << 3);
+	/*
+	 * Mark access for KUAP key in default amr so that
+	 * we continue to operate with that AMR in
+	 * copy_to/from_user().
+	 */
+	default_amr   &= ~(0x3ul << pkeyshift(3));
+	default_iamr  &= ~(0x1ul << pkeyshift(3));
+	default_uamor &= ~(0x3ul << pkeyshift(3));
+
+
 	/*
 	 * Prevent the usage of OS reserved keys. Update UAMOR
 	 * for those keys. Also mark the rest of the bits in the