s390/cpum_sf: add READ_ONCE() semantics to compare and swap loops

The current cmpxchg_double() loops within the perf hw sampling code do not
have READ_ONCE() semantics to read the old value from memory. This allows
the compiler to generate code which reads the "old" value several times
from memory, which again allows for inconsistencies.

For example:

        /* Reset trailer (using compare-double-and-swap) */
        do {
                te_flags = te->flags & ~SDB_TE_BUFFER_FULL_MASK;
                te_flags |= SDB_TE_ALERT_REQ_MASK;
        } while (!cmpxchg_double(&te->flags, &te->overflow,
                 te->flags, te->overflow,
                 te_flags, 0ULL));

The compiler could generate code where te->flags used within the
cmpxchg_double() call may be refetched from memory and which is not
necessarily identical to the previous read version which was used to
generate te_flags. Which in turn means that an incorrect update could
happen.

Fix this by adding READ_ONCE() semantics to all cmpxchg_double()
loops. Given that READ_ONCE() cannot generate code on s390 which atomically
reads 16 bytes, use a private compare-and-swap-double implementation to
achieve that.

Also replace cmpxchg_double() with the private implementation to be able to
re-use the old value within the loops.

As a side effect this converts the whole code to only use bit fields
to read and modify bits within the hws trailer header.

Reported-by: Alexander Gordeev <agordeev@linux.ibm.com>
Acked-by: Alexander Gordeev <agordeev@linux.ibm.com>
Acked-by: Hendrik Brueckner <brueckner@linux.ibm.com>
Reviewed-by: Thomas Richter <tmricht@linux.ibm.com>
Cc: <stable@vger.kernel.org>
Link: https://lore.kernel.org/linux-s390/Y71QJBhNTIatvxUT@osiris/T/#ma14e2a5f7aa8ed4b94b6f9576799b3ad9c60f333
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>

1 files changed, 15 insertions, 16 deletions

diff --git a/arch/s390/include/asm/cpu_mf.h b/arch/s390/include/asm/cpu_mf.h
index feaba12dbecb..efa103b52a1a 100644
--- a/arch/s390/include/asm/cpu_mf.h
+++ b/arch/s390/include/asm/cpu_mf.h
@@ -131,19 +131,21 @@ struct hws_combined_entry {
 	struct hws_diag_entry	diag;	/* Diagnostic-sampling data entry */
 } __packed;
 
-struct hws_trailer_entry {
-	union {
-		struct {
-			unsigned int f:1;	/* 0 - Block Full Indicator   */
-			unsigned int a:1;	/* 1 - Alert request control  */
-			unsigned int t:1;	/* 2 - Timestamp format	      */
-			unsigned int :29;	/* 3 - 31: Reserved	      */
-			unsigned int bsdes:16;	/* 32-47: size of basic SDE   */
-			unsigned int dsdes:16;	/* 48-63: size of diagnostic SDE */
-		};
-		unsigned long long flags;	/* 0 - 63: All indicators     */
+union hws_trailer_header {
+	struct {
+		unsigned int f:1;	/* 0 - Block Full Indicator   */
+		unsigned int a:1;	/* 1 - Alert request control  */
+		unsigned int t:1;	/* 2 - Timestamp format	      */
+		unsigned int :29;	/* 3 - 31: Reserved	      */
+		unsigned int bsdes:16;	/* 32-47: size of basic SDE   */
+		unsigned int dsdes:16;	/* 48-63: size of diagnostic SDE */
+		unsigned long long overflow; /* 64 - Overflow Count   */
 	};
-	unsigned long long overflow;	 /* 64 - sample Overflow count	      */
+	__uint128_t val;
+};
+
+struct hws_trailer_entry {
+	union hws_trailer_header header; /* 0 - 15 Flags + Overflow Count     */
 	unsigned char timestamp[16];	 /* 16 - 31 timestamp		      */
 	unsigned long long reserved1;	 /* 32 -Reserved		      */
 	unsigned long long reserved2;	 /*				      */
@@ -290,14 +292,11 @@ static inline unsigned long sample_rate_to_freq(struct hws_qsi_info_block *qsi,
 	return USEC_PER_SEC * qsi->cpu_speed / rate;
 }
 
-#define SDB_TE_ALERT_REQ_MASK	0x4000000000000000UL
-#define SDB_TE_BUFFER_FULL_MASK 0x8000000000000000UL
-
 /* Return TOD timestamp contained in an trailer entry */
 static inline unsigned long long trailer_timestamp(struct hws_trailer_entry *te)
 {
 	/* TOD in STCKE format */
-	if (te->t)
+	if (te->header.t)
 		return *((unsigned long long *) &te->timestamp[1]);
 
 	/* TOD in STCK format */