powerpc fixes for 5.13 #4

Fix breakage of strace (and other ptracers etc.) when using the new scv ABI (Power9 or
 later with glibc >= 2.33).
 
 Fix early_ioremap() on 64-bit, which broke booting on some machines.
 
 Thanks to: Dmitry V. Levin, Nicholas Piggin, Alexey Kardashevskiy, Christophe Leroy.
 -----BEGIN PGP SIGNATURE-----
 
 iQJHBAABCAAxFiEEJFGtCPCthwEv2Y/bUevqPMjhpYAFAmCqKaoTHG1wZUBlbGxl
 cm1hbi5pZC5hdQAKCRBR6+o8yOGlgER4D/9Nqbw1u16uoBrIyHaI4Q6UasXIcktc
 ghFs0tOKNawNUyJUcl8/utH8ilpUTOnZPLeYWX9wP/KZFzHhEoWTmUZI5wcX+hkO
 V0ZabIsJ9+mKZXffSqBliehRQpqQAS5vlpJOWN0WFUx2Jaqv+QAfGLuPMAvvpqx1
 5yis2wVyC0ooo03TiaD2SjK2axzDa3Z+QOwcbAFYrb9/c2THU5J4y3+JeicHIZqi
 pySwBE5INa25zjqgDxw6ONMNpdflQvB4i06rnGlkTnUbqtUW4oGVyE3cLTwkcL+j
 zz6jN27jP0am6pM3+1JTIJcvyUETheMYmL5MPa7yzQqngD4egdNMl62p0WYLIgYo
 LRvPpkF0mfgt9RdIbvCo5+dhni0FcCdqTJcCfmUG6ndQ9vCYFCtCvnRrl/9iqqLJ
 B38Kjaad2T7oFmLBRKOHYVf5p77g1i37xiMcHu0m2Emrbi5ftenLnlOQ9Xk/xW/v
 cp7e0o/D3PJjqy9EsZ+o0DiZq1AZe0dg8nKCVIXXF6UaLNb2copP0ylplBF7aefs
 PW3Fkbq4zjRxE5UYBaz9BZmijtxH9IKywkaCS1/K+EgGjfhIP+XsmH0+qdd1JDqW
 M47B8Bl8ucdOA9eD48GeOY9KBSbvR5sK83NibGAEMRfyNSDZPE7Z3OzI9goeWfCG
 R6LDOridKGOuNQ==
 =qeQq
 -----END PGP SIGNATURE-----

Merge tag 'powerpc-5.13-4' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc fixes from Michael Ellerman:

 - Fix breakage of strace (and other ptracers etc.) when using the new
   scv ABI (Power9 or later with glibc >= 2.33).

 - Fix early_ioremap() on 64-bit, which broke booting on some machines.

Thanks to Dmitry V. Levin, Nicholas Piggin, Alexey Kardashevskiy, and
Christophe Leroy.

* tag 'powerpc-5.13-4' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux:
  powerpc/64s/syscall: Fix ptrace syscall info with scv syscalls
  powerpc/64s/syscall: Use pt_regs.trap to distinguish syscall ABI difference between sc and scv syscalls
  powerpc: Fix early setup to make early_ioremap() work

Documentation/powerpc/syscall64-abi.rst

@@ -109,6 +109,16 @@ auxiliary vector.
 
 scv 0 syscalls will always behave as PPC_FEATURE2_HTM_NOSC.
 
+ptrace
+------
+When ptracing system calls (PTRACE_SYSCALL), the pt_regs.trap value contains
+the system call type that can be used to distinguish between sc and scv 0
+system calls, and the different register conventions can be accounted for.
+
+If the value of (pt_regs.trap & 0xfff0) is 0xc00 then the system call was
+performed with the sc instruction, if it is 0x3000 then the system call was
+performed with the scv 0 instruction.
+
 vsyscall
 ========
 

arch/powerpc/include/asm/ptrace.h

@@ -19,6 +19,7 @@
 #ifndef _ASM_POWERPC_PTRACE_H
 #define _ASM_POWERPC_PTRACE_H
 
+#include <linux/err.h>
 #include <uapi/asm/ptrace.h>
 #include <asm/asm-const.h>
 
@@ -152,25 +153,6 @@ extern unsigned long profile_pc(struct pt_regs *regs);
 long do_syscall_trace_enter(struct pt_regs *regs);
 void do_syscall_trace_leave(struct pt_regs *regs);
 
-#define kernel_stack_pointer(regs) ((regs)->gpr[1])
-static inline int is_syscall_success(struct pt_regs *regs)
-{
-	return !(regs->ccr & 0x10000000);
-}
-
-static inline long regs_return_value(struct pt_regs *regs)
-{
-	if (is_syscall_success(regs))
-		return regs->gpr[3];
-	else
-		return -regs->gpr[3];
-}
-
-static inline void regs_set_return_value(struct pt_regs *regs, unsigned long rc)
-{
-	regs->gpr[3] = rc;
-}
-
 #ifdef __powerpc64__
 #define user_mode(regs) ((((regs)->msr) >> MSR_PR_LG) & 0x1)
 #else
@@ -235,6 +217,31 @@ static __always_inline void set_trap_norestart(struct pt_regs *regs)
 	regs->trap |= 0x1;
 }
 
+#define kernel_stack_pointer(regs) ((regs)->gpr[1])
+static inline int is_syscall_success(struct pt_regs *regs)
+{
+	if (trap_is_scv(regs))
+		return !IS_ERR_VALUE((unsigned long)regs->gpr[3]);
+	else
+		return !(regs->ccr & 0x10000000);
+}
+
+static inline long regs_return_value(struct pt_regs *regs)
+{
+	if (trap_is_scv(regs))
+		return regs->gpr[3];
+
+	if (is_syscall_success(regs))
+		return regs->gpr[3];
+	else
+		return -regs->gpr[3];
+}
+
+static inline void regs_set_return_value(struct pt_regs *regs, unsigned long rc)
+{
+	regs->gpr[3] = rc;
+}
+
 #define arch_has_single_step()	(1)
 #define arch_has_block_step()	(true)
 #define ARCH_HAS_USER_SINGLE_STEP_REPORT

arch/powerpc/include/asm/syscall.h

@@ -41,11 +41,17 @@ static inline void syscall_rollback(struct task_struct *task,
 static inline long syscall_get_error(struct task_struct *task,
 				     struct pt_regs *regs)
 {
-	/*
-	 * If the system call failed,
-	 * regs->gpr[3] contains a positive ERRORCODE.
-	 */
-	return (regs->ccr & 0x10000000UL) ? -regs->gpr[3] : 0;
+	if (trap_is_scv(regs)) {
+		unsigned long error = regs->gpr[3];
+
+		return IS_ERR_VALUE(error) ? error : 0;
+	} else {
+		/*
+		 * If the system call failed,
+		 * regs->gpr[3] contains a positive ERRORCODE.
+		 */
+		return (regs->ccr & 0x10000000UL) ? -regs->gpr[3] : 0;
+	}
 }
 
 static inline long syscall_get_return_value(struct task_struct *task,
@@ -58,18 +64,22 @@ static inline void syscall_set_return_value(struct task_struct *task,
 					    struct pt_regs *regs,
 					    int error, long val)
 {
-	/*
-	 * In the general case it's not obvious that we must deal with CCR
-	 * here, as the syscall exit path will also do that for us. However
-	 * there are some places, eg. the signal code, which check ccr to
-	 * decide if the value in r3 is actually an error.
-	 */
-	if (error) {
-		regs->ccr |= 0x10000000L;
-		regs->gpr[3] = error;
+	if (trap_is_scv(regs)) {
+		regs->gpr[3] = (long) error ?: val;
 	} else {
-		regs->ccr &= ~0x10000000L;
-		regs->gpr[3] = val;
+		/*
+		 * In the general case it's not obvious that we must deal with
+		 * CCR here, as the syscall exit path will also do that for us.
+		 * However there are some places, eg. the signal code, which
+		 * check ccr to decide if the value in r3 is actually an error.
+		 */
+		if (error) {
+			regs->ccr |= 0x10000000L;
+			regs->gpr[3] = error;
+		} else {
+			regs->ccr &= ~0x10000000L;
+			regs->gpr[3] = val;
+		}
 	}
 }
 

arch/powerpc/kernel/setup_64.c

@@ -369,11 +369,11 @@ void __init early_setup(unsigned long dt_ptr)
 	apply_feature_fixups();
 	setup_feature_keys();
 
-	early_ioremap_setup();
-
 	/* Initialize the hash table or TLB handling */
 	early_init_mmu();
 
+	early_ioremap_setup();
+
 	/*
 	 * After firmware and early platform setup code has set things up,
 	 * we note the SPR values for configurable control/performance

tools/testing/selftests/seccomp/seccomp_bpf.c

@@ -1753,16 +1753,25 @@ TEST_F(TRACE_poke, getpid_runs_normally)
 # define SYSCALL_RET_SET(_regs, _val)				\
 	do {							\
 		typeof(_val) _result = (_val);			\
-		/*						\
-		 * A syscall error is signaled by CR0 SO bit	\
-		 * and the code is stored as a positive value.	\
-		 */						\
-		if (_result < 0) {				\
-			SYSCALL_RET(_regs) = -_result;		\
-			(_regs).ccr |= 0x10000000;		\
-		} else {					\
+		if ((_regs.trap & 0xfff0) == 0x3000) {		\
+			/*					\
+			 * scv 0 system call uses -ve result	\
+			 * for error, so no need to adjust.	\
+			 */					\
 			SYSCALL_RET(_regs) = _result;		\
-			(_regs).ccr &= ~0x10000000;		\
+		} else {					\
+			/*					\
+			 * A syscall error is signaled by the	\
+			 * CR0 SO bit and the code is stored as	\
+			 * a positive value.			\
+			 */					\
+			if (_result < 0) {			\
+				SYSCALL_RET(_regs) = -_result;	\
+				(_regs).ccr |= 0x10000000;	\
+			} else {				\
+				SYSCALL_RET(_regs) = _result;	\
+				(_regs).ccr &= ~0x10000000;	\
+			}					\
 		}						\
 	} while (0)
 # define SYSCALL_RET_SET_ON_PTRACE_EXIT