powerpc/32s: Implement Kernel Userspace Access Protection

This patch implements Kernel Userspace Access Protection for
book3s/32.

Due to limitations of the processor page protection capabilities,
the protection is only against writing. read protection cannot be
achieved using page protection.

The previous patch modifies the page protection so that RW user
pages are RW for Key 0 and RO for Key 1, and it sets Key 0 for
both user and kernel.

This patch changes userspace segment registers are set to Ku 0
and Ks 1. When kernel needs to write to RW pages, the associated
segment register is then changed to Ks 0 in order to allow write
access to the kernel.

In order to avoid having the read all segment registers when
locking/unlocking the access, some data is kept in the thread_struct
and saved on stack on exceptions. The field identifies both the
first unlocked segment and the first segment following the last
unlocked one. When no segment is unlocked, it contains value 0.

As the hash_page() function is not able to easily determine if a
protfault is due to a bad kernel access to userspace, protfaults
need to be handled by handle_page_fault when KUAP is set.
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
[mpe: Drop allow_read/write_to/from_user() as they're now in kup.h,
      and adapt allow_user_access() to do nothing when to == NULL]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

arch/powerpc/include/asm/book3s/32/kup.h

@@ -37,6 +37,109 @@
 #endif
 .endm
 
+#ifdef CONFIG_PPC_KUAP
+
+.macro kuap_update_sr	gpr1, gpr2, gpr3	/* NEVER use r0 as gpr2 due to addis */
+101:	mtsrin	\gpr1, \gpr2
+	addi	\gpr1, \gpr1, 0x111		/* next VSID */
+	rlwinm	\gpr1, \gpr1, 0, 0xf0ffffff	/* clear VSID overflow */
+	addis	\gpr2, \gpr2, 0x1000		/* address of next segment */
+	cmplw	\gpr2, \gpr3
+	blt-	101b
+	isync
+.endm
+
+.macro kuap_save_and_lock	sp, thread, gpr1, gpr2, gpr3
+	lwz	\gpr2, KUAP(\thread)
+	rlwinm.	\gpr3, \gpr2, 28, 0xf0000000
+	stw	\gpr2, STACK_REGS_KUAP(\sp)
+	beq+	102f
+	li	\gpr1, 0
+	stw	\gpr1, KUAP(\thread)
+	mfsrin	\gpr1, \gpr2
+	oris	\gpr1, \gpr1, SR_KS@h	/* set Ks */
+	kuap_update_sr	\gpr1, \gpr2, \gpr3
+102:
+.endm
+
+.macro kuap_restore	sp, current, gpr1, gpr2, gpr3
+	lwz	\gpr2, STACK_REGS_KUAP(\sp)
+	rlwinm.	\gpr3, \gpr2, 28, 0xf0000000
+	stw	\gpr2, THREAD + KUAP(\current)
+	beq+	102f
+	mfsrin	\gpr1, \gpr2
+	rlwinm	\gpr1, \gpr1, 0, ~SR_KS	/* Clear Ks */
+	kuap_update_sr	\gpr1, \gpr2, \gpr3
+102:
+.endm
+
+.macro kuap_check	current, gpr
+#ifdef CONFIG_PPC_KUAP_DEBUG
+	lwz	\gpr2, KUAP(thread)
+999:	twnei	\gpr, 0
+	EMIT_BUG_ENTRY 999b, __FILE__, __LINE__, (BUGFLAG_WARNING | BUGFLAG_ONCE)
+#endif
+.endm
+
+#endif /* CONFIG_PPC_KUAP */
+
+#else /* !__ASSEMBLY__ */
+
+#ifdef CONFIG_PPC_KUAP
+
+#include <linux/sched.h>
+
+static inline void kuap_update_sr(u32 sr, u32 addr, u32 end)
+{
+	barrier();	/* make sure thread.kuap is updated before playing with SRs */
+	while (addr < end) {
+		mtsrin(sr, addr);
+		sr += 0x111;		/* next VSID */
+		sr &= 0xf0ffffff;	/* clear VSID overflow */
+		addr += 0x10000000;	/* address of next segment */
+	}
+	isync();	/* Context sync required after mtsrin() */
+}
+
+static inline void allow_user_access(void __user *to, const void __user *from, u32 size)
+{
+	u32 addr, end;
+
+	if (__builtin_constant_p(to) && to == NULL)
+		return;
+
+	addr = (__force u32)to;
+
+	if (!addr || addr >= TASK_SIZE || !size)
+		return;
+
+	end = min(addr + size, TASK_SIZE);
+	current->thread.kuap = (addr & 0xf0000000) | ((((end - 1) >> 28) + 1) & 0xf);
+	kuap_update_sr(mfsrin(addr) & ~SR_KS, addr, end);	/* Clear Ks */
+}
+
+static inline void prevent_user_access(void __user *to, const void __user *from, u32 size)
+{
+	u32 addr = (__force u32)to;
+	u32 end = min(addr + size, TASK_SIZE);
+
+	if (!addr || addr >= TASK_SIZE || !size)
+		return;
+
+	current->thread.kuap = 0;
+	kuap_update_sr(mfsrin(addr) | SR_KS, addr, end);	/* set Ks */
+}
+
+static inline bool bad_kuap_fault(struct pt_regs *regs, bool is_write)
+{
+	if (!is_write)
+		return false;
+
+	return WARN(!regs->kuap, "Bug: write fault blocked by segment registers !");
+}
+
+#endif /* CONFIG_PPC_KUAP */
+
 #endif /* __ASSEMBLY__ */
 
 #endif /* _ASM_POWERPC_BOOK3S_32_KUP_H */

arch/powerpc/include/asm/processor.h

@@ -163,6 +163,9 @@ struct thread_struct {
 #ifdef CONFIG_PPC_RTAS
 	unsigned long	rtas_sp;	/* stack pointer for when in RTAS */
 #endif
+#endif
+#if defined(CONFIG_PPC_BOOK3S_32) && defined(CONFIG_PPC_KUAP)
+	unsigned long	kuap;		/* opened segments for user access */
 #endif
 	/* Debug Registers */
 	struct debug_reg debug;

arch/powerpc/kernel/asm-offsets.c

@@ -147,6 +147,9 @@ int main(void)
 #if defined(CONFIG_KVM) && defined(CONFIG_BOOKE)
 	OFFSET(THREAD_KVM_VCPU, thread_struct, kvm_vcpu);
 #endif
+#if defined(CONFIG_PPC_BOOK3S_32) && defined(CONFIG_PPC_KUAP)
+	OFFSET(KUAP, thread_struct, kuap);
+#endif
 
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
 	OFFSET(PACATMSCRATCH, paca_struct, tm_scratch);

arch/powerpc/kernel/head_32.S

@@ -387,7 +387,11 @@ DataAccess:
 	EXCEPTION_PROLOG
 	mfspr	r10,SPRN_DSISR
 	stw	r10,_DSISR(r11)
+#ifdef CONFIG_PPC_KUAP
+	andis.	r0,r10,(DSISR_BAD_FAULT_32S | DSISR_DABRMATCH | DSISR_PROTFAULT)@h
+#else
 	andis.	r0,r10,(DSISR_BAD_FAULT_32S|DSISR_DABRMATCH)@h
+#endif
 	bne	1f			/* if not, try to put a PTE */
 	mfspr	r4,SPRN_DAR		/* into the hash table */
 	rlwinm	r3,r10,32-15,21,21	/* DSISR_STORE -> _PAGE_RW */
@@ -901,6 +905,9 @@ load_up_mmu:
 	li	r3, 0		/* Kp = 0, Ks = 0, VSID = 0 */
 #ifdef CONFIG_PPC_KUEP
 	oris	r3, r3, SR_NX@h	/* Set Nx */
+#endif
+#ifdef CONFIG_PPC_KUAP
+	oris	r3, r3, SR_KS@h	/* Set Ks */
 #endif
 	li	r4,0
 3:	mtsrin	r3,r4
@@ -910,6 +917,7 @@ load_up_mmu:
 	li	r0, 16 - NUM_USER_SEGMENTS /* load up kernel segment registers */
 	mtctr	r0			/* for context 0 */
 	rlwinm	r3, r3, 0, ~SR_NX	/* Nx = 0 */
+	rlwinm	r3, r3, 0, ~SR_KS	/* Ks = 0 */
 	oris	r3, r3, SR_KP@h		/* Kp = 1 */
 3:	mtsrin	r3, r4
 	addi	r3, r3, 0x111	/* increment VSID */
@@ -1019,6 +1027,9 @@ _ENTRY(switch_mmu_context)
 	rlwinm	r3,r3,4,8,27	/* VSID = (context & 0xfffff) << 4 */
 #ifdef CONFIG_PPC_KUEP
 	oris	r3, r3, SR_NX@h	/* Set Nx */
+#endif
+#ifdef CONFIG_PPC_KUAP
+	oris	r3, r3, SR_KS@h	/* Set Ks */
 #endif
 	li	r0,NUM_USER_SEGMENTS
 	mtctr	r0

arch/powerpc/mm/ppc_mmu_32.c

@@ -407,3 +407,13 @@ void __init setup_kuep(bool disabled)
 		pr_warn("KUEP cannot be disabled yet on 6xx when compiled in\n");
 }
 #endif
+
+#ifdef CONFIG_PPC_KUAP
+void __init setup_kuap(bool disabled)
+{
+	pr_info("Activating Kernel Userspace Access Protection\n");
+
+	if (disabled)
+		pr_warn("KUAP cannot be disabled yet on 6xx when compiled in\n");
+}
+#endif

arch/powerpc/platforms/Kconfig.cputype

@@ -26,6 +26,7 @@ config PPC_BOOK3S_32
 	select PPC_FPU
 	select PPC_HAVE_PMU_SUPPORT
 	select PPC_HAVE_KUEP
+	select PPC_HAVE_KUAP
 
 config PPC_85xx
 	bool "Freescale 85xx"