powerpc/tm: Abort syscalls in active transactions

This patch changes the syscall handler to doom (tabort) active
transactions when a syscall is made and return very early without
performing the syscall and keeping side effects to a minimum (no CPU
accounting or system call tracing is performed). Also included is a
new HWCAP2 bit, PPC_FEATURE2_HTM_NOSC, to indicate this
behaviour to userspace.

Currently, the system call instruction automatically suspends an
active transaction which causes side effects to persist when an active
transaction fails.

This does change the kernel's behaviour, but in a way that was
documented as unsupported.  It doesn't reduce functionality as
syscalls will still be performed after tsuspend; it just requires that
the transaction be explicitly suspended.  It also provides a
consistent interface and makes the behaviour of user code
substantially the same across powerpc and platforms that do not
support suspended transactions (e.g. x86 and s390).

Performance measurements using
http://ozlabs.org/~anton/junkcode/null_syscall.c indicate the cost of
a normal (non-aborted) system call increases by about 0.25%.

Signed-off-by: Sam Bobroff <sam.bobroff@au1.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

8 files changed, 66 insertions, 25 deletions

diff --git a/Documentation/powerpc/transactional_memory.txt b/Documentation/powerpc/transactional_memory.txt
index ded69794a5c0..ba0a2a4a54ba 100644
--- a/Documentation/powerpc/transactional_memory.txt
+++ b/Documentation/powerpc/transactional_memory.txt
@@ -74,22 +74,23 @@ Causes of transaction aborts
 Syscalls
 ========
 
-Performing syscalls from within transaction is not recommended, and can lead
-to unpredictable results.
+Syscalls made from within an active transaction will not be performed and the
+transaction will be doomed by the kernel with the failure code TM_CAUSE_SYSCALL
+| TM_CAUSE_PERSISTENT.
 
-Syscalls do not by design abort transactions, but beware: The kernel code will
-not be running in transactional state.  The effect of syscalls will always
-remain visible, but depending on the call they may abort your transaction as a
-side-effect, read soon-to-be-aborted transactional data that should not remain
-invisible, etc.  If you constantly retry a transaction that constantly aborts
-itself by calling a syscall, you'll have a livelock & make no progress.
+Syscalls made from within a suspended transaction are performed as normal and
+the transaction is not explicitly doomed by the kernel.  However, what the
+kernel does to perform the syscall may result in the transaction being doomed
+by the hardware.  The syscall is performed in suspended mode so any side
+effects will be persistent, independent of transaction success or failure.  No
+guarantees are provided by the kernel about which syscalls will affect
+transaction success.
 
-Simple syscalls (e.g. sigprocmask()) "could" be OK.  Even things like write()
-from, say, printf() should be OK as long as the kernel does not access any
-memory that was accessed transactionally.
-
-Consider any syscalls that happen to work as debug-only -- not recommended for
-production use.  Best to queue them up till after the transaction is over.
+Care must be taken when relying on syscalls to abort during active transactions
+if the calls are made via a library.  Libraries may cache values (which may
+give the appearance of success) or perform operations that cause transaction
+failure before entering the kernel (which may produce different failure codes).
+Examples are glibc's getpid() and lazy symbol resolution.
 
 
 Signals
@@ -176,8 +177,7 @@ kernel aborted a transaction:
  TM_CAUSE_RESCHED       Thread was rescheduled.
  TM_CAUSE_TLBI          Software TLB invalid.
  TM_CAUSE_FAC_UNAV      FP/VEC/VSX unavailable trap.
- TM_CAUSE_SYSCALL       Currently unused; future syscalls that must abort
-                        transactions for consistency will use this.
+ TM_CAUSE_SYSCALL       Syscall from active transaction.
  TM_CAUSE_SIGNAL        Signal delivered.
  TM_CAUSE_MISC          Currently unused.
  TM_CAUSE_ALIGNMENT     Alignment fault.
diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h
index 6367b8347dad..4994648b9265 100644
--- a/arch/powerpc/include/asm/cputable.h
+++ b/arch/powerpc/include/asm/cputable.h
@@ -242,11 +242,13 @@ enum {
 
 /* We only set the TM feature if the kernel was compiled with TM supprt */
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
-#define CPU_FTR_TM_COMP         CPU_FTR_TM
-#define PPC_FEATURE2_HTM_COMP   PPC_FEATURE2_HTM
+#define CPU_FTR_TM_COMP                 CPU_FTR_TM
+#define PPC_FEATURE2_HTM_COMP           PPC_FEATURE2_HTM
+#define PPC_FEATURE2_HTM_NOSC_COMP      PPC_FEATURE2_HTM_NOSC
 #else
-#define CPU_FTR_TM_COMP         0
-#define PPC_FEATURE2_HTM_COMP   0
+#define CPU_FTR_TM_COMP                 0
+#define PPC_FEATURE2_HTM_COMP           0
+#define PPC_FEATURE2_HTM_NOSC_COMP      0
 #endif
 
 /* We need to mark all pages as being coherent if we're SMP or we have a
diff --git a/arch/powerpc/include/uapi/asm/cputable.h b/arch/powerpc/include/uapi/asm/cputable.h
index de2c0e4ee1aa..43686043e297 100644
--- a/arch/powerpc/include/uapi/asm/cputable.h
+++ b/arch/powerpc/include/uapi/asm/cputable.h
@@ -42,5 +42,6 @@
 #define PPC_FEATURE2_ISEL               0x08000000
 #define PPC_FEATURE2_TAR                0x04000000
 #define PPC_FEATURE2_VEC_CRYPTO         0x02000000
+#define PPC_FEATURE2_HTM_NOSC           0x01000000
 
 #endif /* _UAPI__ASM_POWERPC_CPUTABLE_H */
diff --git a/arch/powerpc/include/uapi/asm/tm.h b/arch/powerpc/include/uapi/asm/tm.h
index 5d836b7c1176..5047659815a5 100644
--- a/arch/powerpc/include/uapi/asm/tm.h
+++ b/arch/powerpc/include/uapi/asm/tm.h
@@ -11,7 +11,7 @@
 #define TM_CAUSE_RESCHED        0xde
 #define TM_CAUSE_TLBI           0xdc
 #define TM_CAUSE_FAC_UNAV       0xda
-#define TM_CAUSE_SYSCALL        0xd8  /* future use */
+#define TM_CAUSE_SYSCALL        0xd8
 #define TM_CAUSE_MISC           0xd6  /* future use */
 #define TM_CAUSE_SIGNAL         0xd4
 #define TM_CAUSE_ALIGNMENT      0xd2
diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c
index 60262fdf35ba..7d80bfdfb15e 100644
--- a/arch/powerpc/kernel/cputable.c
+++ b/arch/powerpc/kernel/cputable.c
@@ -108,7 +108,9 @@ extern void __restore_cpu_e6500(void);
                                  PPC_FEATURE_TRUE_LE | \
                                  PPC_FEATURE_PSERIES_PERFMON_COMPAT)
 #define COMMON_USER2_POWER8     (PPC_FEATURE2_ARCH_2_07 | \
-                                 PPC_FEATURE2_HTM_COMP | PPC_FEATURE2_DSCR | \
+                                 PPC_FEATURE2_HTM_COMP | \
+                                 PPC_FEATURE2_HTM_NOSC_COMP | \
+                                 PPC_FEATURE2_DSCR | \
                                  PPC_FEATURE2_ISEL | PPC_FEATURE2_TAR | \
                                  PPC_FEATURE2_VEC_CRYPTO)
 #define COMMON_USER_PA6T        (COMMON_USER_PPC64 | PPC_FEATURE_PA6T |\
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index 278888e89acc..579e0f9a2d57 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -34,6 +34,7 @@
 #include <asm/ftrace.h>
 #include <asm/hw_irq.h>
 #include <asm/context_tracking.h>
+#include <asm/tm.h>
 
 /*
  * System calls.
@@ -51,6 +52,12 @@ exception_marker:
 
         .globl system_call_common
 system_call_common:
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+BEGIN_FTR_SECTION
+        extrdi. r10, r12, 1, (63-MSR_TS_T_LG) /* transaction active? */
+        bne     tabort_syscall
+END_FTR_SECTION_IFSET(CPU_FTR_TM)
+#endif
         andi.   r10,r12,MSR_PR
         mr      r10,r1
         addi    r1,r1,-INT_FRAME_SIZE
@@ -311,6 +318,34 @@ syscall_exit_work:
         bl      do_syscall_trace_leave
         b       ret_from_except
 
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+tabort_syscall:
+        /* Firstly we need to enable TM in the kernel */
+        mfmsr   r10
+        li      r13, 1
+        rldimi  r10, r13, MSR_TM_LG, 63-MSR_TM_LG
+        mtmsrd  r10, 0
+
+        /* tabort, this dooms the transaction, nothing else */
+        li      r13, (TM_CAUSE_SYSCALL|TM_CAUSE_PERSISTENT)
+        TABORT(R13)
+
+        /*
+         * Return directly to userspace. We have corrupted user register state,
+         * but userspace will never see that register state. Execution will
+         * resume after the tbegin of the aborted transaction with the
+         * checkpointed register state.
+         */
+        li      r13, MSR_RI
+        andc    r10, r10, r13
+        mtmsrd  r10, 1
+        mtspr   SPRN_SRR0, r11
+        mtspr   SPRN_SRR1, r12
+
+        rfid
+        b       .       /* prevent speculative execution */
+#endif
+
 /* Save non-volatile GPRs, if not already saved. */
 _GLOBAL(save_nvgprs)
         ld      r11,_TRAP(r1)
diff --git a/tools/testing/selftests/powerpc/tm/Makefile b/tools/testing/selftests/powerpc/tm/Makefile
index 6bff955e1d55..4bea62a319dc 100644
--- a/tools/testing/selftests/powerpc/tm/Makefile
+++ b/tools/testing/selftests/powerpc/tm/Makefile
@@ -1,11 +1,11 @@
-TEST_PROGS := tm-resched-dscr
+TEST_PROGS := tm-resched-dscr tm-syscall
 
 all: $(TEST_PROGS)
 
 $(TEST_PROGS): ../harness.c
 
 tm-syscall: tm-syscall-asm.S
-tm-syscall: CFLAGS += -mhtm
+tm-syscall: CFLAGS += -mhtm -I../../../../../usr/include
 
 include ../../lib.mk
 
diff --git a/tools/testing/selftests/powerpc/tm/tm-syscall.c b/tools/testing/selftests/powerpc/tm/tm-syscall.c
index 3ed8d4b252fa..1276e23da63b 100644
--- a/tools/testing/selftests/powerpc/tm/tm-syscall.c
+++ b/tools/testing/selftests/powerpc/tm/tm-syscall.c
@@ -82,7 +82,8 @@ int tm_syscall(void)
         unsigned count = 0;
         struct timeval end, now;
 
-        SKIP_IF(!((long)get_auxv_entry(AT_HWCAP2) & PPC_FEATURE2_HTM));
+        SKIP_IF(!((long)get_auxv_entry(AT_HWCAP2)
+                  & PPC_FEATURE2_HTM_NOSC));
         setbuf(stdout, NULL);
 
         printf("Testing transactional syscalls for %d seconds...\n", TEST_DURATION);