Merge tag 'powerpc-6.1-2' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc fixes from Michael Ellerman:

 - Fix 32-bit syscall wrappers with 64-bit arguments of unaligned
   register-pairs. Notably this broke ftruncate64 & pread/write64, which
   can lead to file corruption.

 - Fix lost interrupts when returning to soft-masked context on 64-bit.

 - Fix build failure when CONFIG_DTL=n.

Thanks to Nicholas Piggin, Jason A. Donenfeld, Guenter Roeck, Arnd
Bergmann, and Sachin Sant.

* tag 'powerpc-6.1-2' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux:
  powerpc/pseries: Fix CONFIG_DTL=n build
  powerpc/64s/interrupt: Fix lost interrupts when returning to soft-masked context
  powerpc/32: fix syscall wrappers with 64-bit arguments of unaligned register-pairs

Author: torvalds

arch/powerpc/include/asm/syscalls.h

@@ -89,6 +89,22 @@ long compat_sys_rt_sigreturn(void);
  * responsible for combining parameter pairs.
  */
 
+#ifdef CONFIG_PPC32
+long sys_ppc_pread64(unsigned int fd,
+		     char __user *ubuf, compat_size_t count,
+		     u32 reg6, u32 pos1, u32 pos2);
+long sys_ppc_pwrite64(unsigned int fd,
+		      const char __user *ubuf, compat_size_t count,
+		      u32 reg6, u32 pos1, u32 pos2);
+long sys_ppc_readahead(int fd, u32 r4,
+		       u32 offset1, u32 offset2, u32 count);
+long sys_ppc_truncate64(const char __user *path, u32 reg4,
+		        unsigned long len1, unsigned long len2);
+long sys_ppc_ftruncate64(unsigned int fd, u32 reg4,
+			 unsigned long len1, unsigned long len2);
+long sys_ppc32_fadvise64(int fd, u32 unused, u32 offset1, u32 offset2,
+			 size_t len, int advice);
+#endif
 #ifdef CONFIG_COMPAT
 long compat_sys_mmap2(unsigned long addr, size_t len,
 		      unsigned long prot, unsigned long flags,

arch/powerpc/kernel/Makefile

@@ -73,6 +73,7 @@ obj-y				:= cputable.o syscalls.o \
 obj-y				+= ptrace/
 obj-$(CONFIG_PPC64)		+= setup_64.o irq_64.o\
 				   paca.o nvram_64.o note.o
+obj-$(CONFIG_PPC32)		+= sys_ppc32.o
 obj-$(CONFIG_COMPAT)		+= sys_ppc32.o signal_32.o
 obj-$(CONFIG_VDSO32)		+= vdso32_wrapper.o
 obj-$(CONFIG_PPC_WATCHDOG)	+= watchdog.o

arch/powerpc/kernel/interrupt_64.S

@@ -538,7 +538,7 @@ _ASM_NOKPROBE_SYMBOL(interrupt_return_\srr\()_kernel)
 	beq	.Lfast_kernel_interrupt_return_\srr\() // EE already disabled
 	lbz	r11,PACAIRQHAPPENED(r13)
 	andi.	r10,r11,PACA_IRQ_MUST_HARD_MASK
-	beq	1f // No HARD_MASK pending
+	beq	.Lfast_kernel_interrupt_return_\srr\() // No HARD_MASK pending
 
 	/* Must clear MSR_EE from _MSR */
 #ifdef CONFIG_PPC_BOOK3S
@@ -555,12 +555,23 @@ _ASM_NOKPROBE_SYMBOL(interrupt_return_\srr\()_kernel)
 	b	.Lfast_kernel_interrupt_return_\srr\()
 
 .Linterrupt_return_\srr\()_soft_enabled:
+	/*
+	 * In the soft-enabled case, need to double-check that we have no
+	 * pending interrupts that might have come in before we reached the
+	 * restart section of code, and restart the exit so those can be
+	 * handled.
+	 *
+	 * If there are none, it is be possible that the interrupt still
+	 * has PACA_IRQ_HARD_DIS set, which needs to be cleared for the
+	 * interrupted context. This clear will not clobber a new pending
+	 * interrupt coming in, because we're in the restart section, so
+	 * such would return to the restart location.
+	 */
 #ifdef CONFIG_PPC_BOOK3S
 	lbz	r11,PACAIRQHAPPENED(r13)
 	andi.	r11,r11,(~PACA_IRQ_HARD_DIS)@l
 	bne-	interrupt_return_\srr\()_kernel_restart
 #endif
-1:
 	li	r11,0
 	stb	r11,PACAIRQHAPPENED(r13) // clear the possible HARD_DIS
 

arch/powerpc/kernel/sys_ppc32.c

@@ -1,13 +1,23 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 /*
- * sys_ppc32.c: Conversion between 32bit and 64bit native syscalls.
+ * sys_ppc32.c: 32-bit system calls with complex calling conventions.
  *
  * Copyright (C) 2001 IBM
  * Copyright (C) 1997,1998 Jakub Jelinek ([email protected])
  * Copyright (C) 1997 David S. Miller ([email protected])
  *
- * These routines maintain argument size conversion between 32bit and 64bit
- * environment.
+ * 32-bit system calls with 64-bit arguments pass those in register pairs.
+ * This must be specially dealt with on 64-bit kernels. The compat_arg_u64_dual
+ * in generic compat syscalls is not always usable because the register
+ * pairing is constrained depending on preceding arguments.
+ *
+ * An analogous problem exists on 32-bit kernels with ARCH_HAS_SYSCALL_WRAPPER,
+ * the defined system call functions take the pt_regs as an argument, and there
+ * is a mapping macro which maps registers to arguments
+ * (SC_POWERPC_REGS_TO_ARGS) which also does not deal with these 64-bit
+ * arguments.
+ *
+ * This file contains these system calls.
  */
 
 #include <linux/kernel.h>
@@ -47,44 +57,54 @@
 #include <asm/syscalls.h>
 #include <asm/switch_to.h>
 
-COMPAT_SYSCALL_DEFINE6(ppc_pread64,
+#ifdef CONFIG_PPC32
+#define PPC32_SYSCALL_DEFINE4	SYSCALL_DEFINE4
+#define PPC32_SYSCALL_DEFINE5	SYSCALL_DEFINE5
+#define PPC32_SYSCALL_DEFINE6	SYSCALL_DEFINE6
+#else
+#define PPC32_SYSCALL_DEFINE4	COMPAT_SYSCALL_DEFINE4
+#define PPC32_SYSCALL_DEFINE5	COMPAT_SYSCALL_DEFINE5
+#define PPC32_SYSCALL_DEFINE6	COMPAT_SYSCALL_DEFINE6
+#endif
+
+PPC32_SYSCALL_DEFINE6(ppc_pread64,
 		       unsigned int, fd,
 		       char __user *, ubuf, compat_size_t, count,
 		       u32, reg6, u32, pos1, u32, pos2)
 {
 	return ksys_pread64(fd, ubuf, count, merge_64(pos1, pos2));
 }
 
-COMPAT_SYSCALL_DEFINE6(ppc_pwrite64,
+PPC32_SYSCALL_DEFINE6(ppc_pwrite64,
 		       unsigned int, fd,
 		       const char __user *, ubuf, compat_size_t, count,
 		       u32, reg6, u32, pos1, u32, pos2)
 {
 	return ksys_pwrite64(fd, ubuf, count, merge_64(pos1, pos2));
 }
 
-COMPAT_SYSCALL_DEFINE5(ppc_readahead,
+PPC32_SYSCALL_DEFINE5(ppc_readahead,
 		       int, fd, u32, r4,
 		       u32, offset1, u32, offset2, u32, count)
 {
 	return ksys_readahead(fd, merge_64(offset1, offset2), count);
 }
 
-COMPAT_SYSCALL_DEFINE4(ppc_truncate64,
+PPC32_SYSCALL_DEFINE4(ppc_truncate64,
 		       const char __user *, path, u32, reg4,
 		       unsigned long, len1, unsigned long, len2)
 {
 	return ksys_truncate(path, merge_64(len1, len2));
 }
 
-COMPAT_SYSCALL_DEFINE4(ppc_ftruncate64,
+PPC32_SYSCALL_DEFINE4(ppc_ftruncate64,
 		       unsigned int, fd, u32, reg4,
 		       unsigned long, len1, unsigned long, len2)
 {
 	return ksys_ftruncate(fd, merge_64(len1, len2));
 }
 
-COMPAT_SYSCALL_DEFINE6(ppc32_fadvise64,
+PPC32_SYSCALL_DEFINE6(ppc32_fadvise64,
 		       int, fd, u32, unused, u32, offset1, u32, offset2,
 		       size_t, len, int, advice)
 {

arch/powerpc/kernel/syscalls/syscall.tbl

@@ -228,8 +228,10 @@
 176	64	rt_sigtimedwait			sys_rt_sigtimedwait
 177	nospu 	rt_sigqueueinfo			sys_rt_sigqueueinfo		compat_sys_rt_sigqueueinfo
 178	nospu 	rt_sigsuspend			sys_rt_sigsuspend		compat_sys_rt_sigsuspend
-179	common	pread64				sys_pread64			compat_sys_ppc_pread64
-180	common	pwrite64			sys_pwrite64			compat_sys_ppc_pwrite64
+179	32	pread64				sys_ppc_pread64			compat_sys_ppc_pread64
+179	64	pread64				sys_pread64
+180	32	pwrite64			sys_ppc_pwrite64		compat_sys_ppc_pwrite64
+180	64	pwrite64			sys_pwrite64
 181	common	chown				sys_chown
 182	common	getcwd				sys_getcwd
 183	common	capget				sys_capget
@@ -242,10 +244,11 @@
 188	common 	putpmsg				sys_ni_syscall
 189	nospu	vfork				sys_vfork
 190	common	ugetrlimit			sys_getrlimit			compat_sys_getrlimit
-191	common	readahead			sys_readahead			compat_sys_ppc_readahead
+191	32	readahead			sys_ppc_readahead		compat_sys_ppc_readahead
+191	64	readahead			sys_readahead
 192	32	mmap2				sys_mmap2			compat_sys_mmap2
-193	32	truncate64			sys_truncate64			compat_sys_ppc_truncate64
-194	32	ftruncate64			sys_ftruncate64			compat_sys_ppc_ftruncate64
+193	32	truncate64			sys_ppc_truncate64		compat_sys_ppc_truncate64
+194	32	ftruncate64			sys_ppc_ftruncate64		compat_sys_ppc_ftruncate64
 195	32	stat64				sys_stat64
 196	32	lstat64				sys_lstat64
 197	32	fstat64				sys_fstat64
@@ -288,7 +291,8 @@
 230	common	io_submit			sys_io_submit			compat_sys_io_submit
 231	common	io_cancel			sys_io_cancel
 232	nospu	set_tid_address			sys_set_tid_address
-233	common	fadvise64			sys_fadvise64			compat_sys_ppc32_fadvise64
+233	32	fadvise64			sys_ppc32_fadvise64		compat_sys_ppc32_fadvise64
+233	64	fadvise64			sys_fadvise64
 234	nospu	exit_group			sys_exit_group
 235	nospu	lookup_dcookie			sys_lookup_dcookie		compat_sys_lookup_dcookie
 236	common	epoll_create			sys_epoll_create

arch/powerpc/platforms/pseries/Makefile

@@ -7,7 +7,7 @@ obj-y			:= lpar.o hvCall.o nvram.o reconfig.o \
 			   setup.o iommu.o event_sources.o ras.o \
 			   firmware.o power.o dlpar.o mobility.o rng.o \
 			   pci.o pci_dlpar.o eeh_pseries.o msi.o \
-			   papr_platform_attributes.o
+			   papr_platform_attributes.o dtl.o
 obj-$(CONFIG_SMP)	+= smp.o
 obj-$(CONFIG_KEXEC_CORE)	+= kexec.o
 obj-$(CONFIG_PSERIES_ENERGY)	+= pseries_energy.o
@@ -19,7 +19,6 @@ obj-$(CONFIG_HVC_CONSOLE)	+= hvconsole.o
 obj-$(CONFIG_HVCS)		+= hvcserver.o
 obj-$(CONFIG_HCALL_STATS)	+= hvCall_inst.o
 obj-$(CONFIG_CMM)		+= cmm.o
-obj-$(CONFIG_DTL)		+= dtl.o
 obj-$(CONFIG_IO_EVENT_IRQ)	+= io_event_irq.o
 obj-$(CONFIG_LPARCFG)		+= lparcfg.o
 obj-$(CONFIG_IBMVIO)		+= vio.o

arch/powerpc/platforms/pseries/dtl.c

@@ -18,6 +18,7 @@
 #include <asm/plpar_wrappers.h>
 #include <asm/machdep.h>
 
+#ifdef CONFIG_DTL
 struct dtl {
 	struct dtl_entry	*buf;
 	int			cpu;
@@ -57,78 +58,6 @@ static DEFINE_PER_CPU(struct dtl_ring, dtl_rings);
 
 static atomic_t dtl_count;
 
-/*
- * Scan the dispatch trace log and count up the stolen time.
- * Should be called with interrupts disabled.
- */
-static notrace u64 scan_dispatch_log(u64 stop_tb)
-{
-	u64 i = local_paca->dtl_ridx;
-	struct dtl_entry *dtl = local_paca->dtl_curr;
-	struct dtl_entry *dtl_end = local_paca->dispatch_log_end;
-	struct lppaca *vpa = local_paca->lppaca_ptr;
-	u64 tb_delta;
-	u64 stolen = 0;
-	u64 dtb;
-
-	if (!dtl)
-		return 0;
-
-	if (i == be64_to_cpu(vpa->dtl_idx))
-		return 0;
-	while (i < be64_to_cpu(vpa->dtl_idx)) {
-		dtb = be64_to_cpu(dtl->timebase);
-		tb_delta = be32_to_cpu(dtl->enqueue_to_dispatch_time) +
-			be32_to_cpu(dtl->ready_to_enqueue_time);
-		barrier();
-		if (i + N_DISPATCH_LOG < be64_to_cpu(vpa->dtl_idx)) {
-			/* buffer has overflowed */
-			i = be64_to_cpu(vpa->dtl_idx) - N_DISPATCH_LOG;
-			dtl = local_paca->dispatch_log + (i % N_DISPATCH_LOG);
-			continue;
-		}
-		if (dtb > stop_tb)
-			break;
-		if (dtl_consumer)
-			dtl_consumer(dtl, i);
-		stolen += tb_delta;
-		++i;
-		++dtl;
-		if (dtl == dtl_end)
-			dtl = local_paca->dispatch_log;
-	}
-	local_paca->dtl_ridx = i;
-	local_paca->dtl_curr = dtl;
-	return stolen;
-}
-
-/*
- * Accumulate stolen time by scanning the dispatch trace log.
- * Called on entry from user mode.
- */
-void notrace pseries_accumulate_stolen_time(void)
-{
-	u64 sst, ust;
-	struct cpu_accounting_data *acct = &local_paca->accounting;
-
-	sst = scan_dispatch_log(acct->starttime_user);
-	ust = scan_dispatch_log(acct->starttime);
-	acct->stime -= sst;
-	acct->utime -= ust;
-	acct->steal_time += ust + sst;
-}
-
-u64 pseries_calculate_stolen_time(u64 stop_tb)
-{
-	if (!firmware_has_feature(FW_FEATURE_SPLPAR))
-		return 0;
-
-	if (get_paca()->dtl_ridx != be64_to_cpu(get_lppaca()->dtl_idx))
-		return scan_dispatch_log(stop_tb);
-
-	return 0;
-}
-
 /*
  * The cpu accounting code controls the DTL ring buffer, and we get
  * given entries as they are processed.
@@ -436,3 +365,81 @@ static int dtl_init(void)
 	return 0;
 }
 machine_arch_initcall(pseries, dtl_init);
+#endif /* CONFIG_DTL */
+
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
+/*
+ * Scan the dispatch trace log and count up the stolen time.
+ * Should be called with interrupts disabled.
+ */
+static notrace u64 scan_dispatch_log(u64 stop_tb)
+{
+	u64 i = local_paca->dtl_ridx;
+	struct dtl_entry *dtl = local_paca->dtl_curr;
+	struct dtl_entry *dtl_end = local_paca->dispatch_log_end;
+	struct lppaca *vpa = local_paca->lppaca_ptr;
+	u64 tb_delta;
+	u64 stolen = 0;
+	u64 dtb;
+
+	if (!dtl)
+		return 0;
+
+	if (i == be64_to_cpu(vpa->dtl_idx))
+		return 0;
+	while (i < be64_to_cpu(vpa->dtl_idx)) {
+		dtb = be64_to_cpu(dtl->timebase);
+		tb_delta = be32_to_cpu(dtl->enqueue_to_dispatch_time) +
+			be32_to_cpu(dtl->ready_to_enqueue_time);
+		barrier();
+		if (i + N_DISPATCH_LOG < be64_to_cpu(vpa->dtl_idx)) {
+			/* buffer has overflowed */
+			i = be64_to_cpu(vpa->dtl_idx) - N_DISPATCH_LOG;
+			dtl = local_paca->dispatch_log + (i % N_DISPATCH_LOG);
+			continue;
+		}
+		if (dtb > stop_tb)
+			break;
+#ifdef CONFIG_DTL
+		if (dtl_consumer)
+			dtl_consumer(dtl, i);
+#endif
+		stolen += tb_delta;
+		++i;
+		++dtl;
+		if (dtl == dtl_end)
+			dtl = local_paca->dispatch_log;
+	}
+	local_paca->dtl_ridx = i;
+	local_paca->dtl_curr = dtl;
+	return stolen;
+}
+
+/*
+ * Accumulate stolen time by scanning the dispatch trace log.
+ * Called on entry from user mode.
+ */
+void notrace pseries_accumulate_stolen_time(void)
+{
+	u64 sst, ust;
+	struct cpu_accounting_data *acct = &local_paca->accounting;
+
+	sst = scan_dispatch_log(acct->starttime_user);
+	ust = scan_dispatch_log(acct->starttime);
+	acct->stime -= sst;
+	acct->utime -= ust;
+	acct->steal_time += ust + sst;
+}
+
+u64 pseries_calculate_stolen_time(u64 stop_tb)
+{
+	if (!firmware_has_feature(FW_FEATURE_SPLPAR))
+		return 0;
+
+	if (get_paca()->dtl_ridx != be64_to_cpu(get_lppaca()->dtl_idx))
+		return scan_dispatch_log(stop_tb);
+
+	return 0;
+}
+
+#endif