[PATCH 2/2] powerpc/watchpoint: Workaround P10 DD1 issue with VSX-32 byte instructions

[Ravi Bangoria]

POWER10 DD1 has an issue where it generates watchpoint exceptions when it
shouldn't. The conditions where this occur are:

 - octword op
 - ending address of DAWR range is less than starting address of op
 - those addresses need to be in the same or in two consecutive 512B
   blocks
 - 'op address + 64B' generates an address that has a carry into bit
   52 (crosses 2K boundary)

Handle such spurious exception by considering them as extraneous and
emulating/single-steeping instruction without generating an event.

Signed-off-by: Ravi Bangoria <ravi.bangoria at linux.ibm.com>
---

Dependency: VSX-32 byte emulation support patches
  https://lore.kernel.org/r/20201011050908.72173-1-ravi.bangoria@linux.ibm.com

 arch/powerpc/kernel/hw_breakpoint.c | 69 ++++++++++++++++++++++++++++-
 1 file changed, 67 insertions(+), 2 deletions(-)

diff --git a/arch/powerpc/kernel/hw_breakpoint.c b/arch/powerpc/kernel/hw_breakpoint.c
index f4e8f21046f5..4514745d27c3 100644
--- a/arch/powerpc/kernel/hw_breakpoint.c
+++ b/arch/powerpc/kernel/hw_breakpoint.c
@@ -499,6 +499,11 @@ static bool is_larx_stcx_instr(int type)
 	return type == LARX || type == STCX;
 }
 
+static bool is_octword_vsx_instr(int type, int size)
+{
+	return ((type == LOAD_VSX || type == STORE_VSX) && size == 32);
+}
+
 /*
  * We've failed in reliably handling the hw-breakpoint. Unregister
  * it and throw a warning message to let the user know about it.
@@ -549,6 +554,60 @@ static bool stepping_handler(struct pt_regs *regs, struct perf_event **bp,
 	return true;
 }
 
+static void handle_p10dd1_spurious_exception(struct arch_hw_breakpoint **info,
+					     int *hit, unsigned long ea)
+{
+	int i;
+	unsigned long hw_start_addr;
+	unsigned long hw_end_addr;
+
+	/*
+	 * Handle spurious exception only when any bp_per_reg is set.
+	 * Otherwise this might be created by xmon and not actually a
+	 * spurious exception.
+	 */
+	for (i = 0; i < nr_wp_slots(); i++) {
+		if (!info[i])
+			continue;
+
+		hw_start_addr = ALIGN_DOWN(info[i]->address, HW_BREAKPOINT_SIZE);
+		hw_end_addr = ALIGN(info[i]->address + info[i]->len, HW_BREAKPOINT_SIZE);
+
+		/*
+		 * Ending address of DAWR range is less than starting
+		 * address of op.
+		 */
+		if ((hw_end_addr - 1) >= ea)
+			continue;
+
+		/*
+		 * Those addresses need to be in the same or in two
+		 * consecutive 512B blocks;
+		 */
+		if (((hw_end_addr - 1) >> 10) != (ea >> 10))
+			continue;
+
+		/*
+		 * 'op address + 64B' generates an address that has a
+		 * carry into bit 52 (crosses 2K boundary).
+		 */
+		if ((ea & 0x800) == ((ea + 64) & 0x800))
+			continue;
+
+		break;
+	}
+
+	if (i == nr_wp_slots())
+		return;
+
+	for (i = 0; i < nr_wp_slots(); i++) {
+		if (info[i]) {
+			hit[i] = 1;
+			info[i]->type |= HW_BRK_TYPE_EXTRANEOUS_IRQ;
+		}
+	}
+}
+
 int hw_breakpoint_handler(struct die_args *args)
 {
 	bool err = false;
@@ -607,8 +666,14 @@ int hw_breakpoint_handler(struct die_args *args)
 		goto reset;
 
 	if (!nr_hit) {
-		rc = NOTIFY_DONE;
-		goto out;
+		if (cpu_has_feature(CPU_FTR_POWER10_DD1) &&
+		    !IS_ENABLED(CONFIG_PPC_8xx) &&
+		    is_octword_vsx_instr(type, size)) {
+			handle_p10dd1_spurious_exception(info, hit, ea);
+		} else {
+			rc = NOTIFY_DONE;
+			goto out;
+		}
 	}
 
 	/*
-- 
2.25.1