[PATCH v2 3/4] riscv: add option to wait for ack from secondary harts in smp functions

[Lukas Auer]

Add a wait option to smp_call_function() to wait for the secondary harts
to acknowledge the call-function request. The request is considered to
be acknowledged once each secondary hart has cleared the corresponding
IPI.

As part of the call-function request, the secondary harts invalidate the
instruction cache after clearing the IPI. This adds a delay between
acknowledgment (clear IPI) and fulfillment (call function) of the
request. We want to use the acknowledgment to be able to judge when the
request has been completed. Remove the delay by clearing the IPI after
cache invalidation and just before calling the function from the
request.

Signed-off-by: Lukas Auer <lukas.auer at aisec.fraunhofer.de>
Reviewed-by: Rick Chen <rick at andestech.com>
Tested-by: Rick Chen <rick at andestech.com>
Reviewed-by: Anup Patel <anup.patel at wdc.com>
---

Changes in v2: None

 arch/riscv/cpu/start.S       |  2 ++
 arch/riscv/include/asm/smp.h |  3 ++-
 arch/riscv/lib/bootm.c       |  2 +-
 arch/riscv/lib/smp.c         | 31 ++++++++++++++++++++++---------
 arch/riscv/lib/spl.c         |  2 +-
 common/spl/spl_opensbi.c     |  2 +-
 6 files changed, 29 insertions(+), 13 deletions(-)

diff --git a/arch/riscv/cpu/start.S b/arch/riscv/cpu/start.S
index 0a2ce6d691..60631638dd 100644
--- a/arch/riscv/cpu/start.S
+++ b/arch/riscv/cpu/start.S
@@ -197,6 +197,7 @@ spl_secondary_hart_stack_gd_setup:
 	la	a0, secondary_hart_relocate
 	mv	a1, s0
 	mv	a2, s0
+	mv	a3, zero
 	jal	smp_call_function
 
 	/* hang if relocation of secondary harts has failed */
@@ -337,6 +338,7 @@ relocate_secondary_harts:
 
 	mv	a1, s2
 	mv	a2, s3
+	mv	a3, zero
 	jal	smp_call_function
 
 	/* hang if relocation of secondary harts has failed */
diff --git a/arch/riscv/include/asm/smp.h b/arch/riscv/include/asm/smp.h
index bc863fdbaf..74de92ed13 100644
--- a/arch/riscv/include/asm/smp.h
+++ b/arch/riscv/include/asm/smp.h
@@ -46,8 +46,9 @@ void handle_ipi(ulong hart);
  * @addr: Address of function
  * @arg0: First argument of function
  * @arg1: Second argument of function
+ * @wait: Wait for harts to acknowledge request
  * @return 0 if OK, -ve on error
  */
-int smp_call_function(ulong addr, ulong arg0, ulong arg1);
+int smp_call_function(ulong addr, ulong arg0, ulong arg1, int wait);
 
 #endif
diff --git a/arch/riscv/lib/bootm.c b/arch/riscv/lib/bootm.c
index efbd3e23e7..e96137a50c 100644
--- a/arch/riscv/lib/bootm.c
+++ b/arch/riscv/lib/bootm.c
@@ -99,7 +99,7 @@ static void boot_jump_linux(bootm_headers_t *images, int flag)
 		if (IMAGE_ENABLE_OF_LIBFDT && images->ft_len) {
 #ifdef CONFIG_SMP
 			ret = smp_call_function(images->ep,
-						(ulong)images->ft_addr, 0);
+						(ulong)images->ft_addr, 0, 0);
 			if (ret)
 				hang();
 #endif
diff --git a/arch/riscv/lib/smp.c b/arch/riscv/lib/smp.c
index 188a7e34bd..17adb35730 100644
--- a/arch/riscv/lib/smp.c
+++ b/arch/riscv/lib/smp.c
@@ -44,11 +44,11 @@ extern int riscv_clear_ipi(int hart);
  */
 extern int riscv_get_ipi(int hart, int *pending);
 
-static int send_ipi_many(struct ipi_data *ipi)
+static int send_ipi_many(struct ipi_data *ipi, int wait)
 {
 	ofnode node, cpus;
 	u32 reg;
-	int ret;
+	int ret, pending;
 
 	cpus = ofnode_path("/cpus");
 	if (!ofnode_valid(cpus)) {
@@ -91,6 +91,15 @@ static int send_ipi_many(struct ipi_data *ipi)
 			pr_err("Cannot send IPI to hart %d\n", reg);
 			return ret;
 		}
+
+		if (wait) {
+			pending = 1;
+			while (pending) {
+				ret = riscv_get_ipi(reg, &pending);
+				if (ret)
+					return ret;
+			}
+		}
 	}
 
 	return 0;
@@ -104,21 +113,25 @@ void handle_ipi(ulong hart)
 	if (hart >= CONFIG_NR_CPUS)
 		return;
 
+	__smp_mb();
+
+	smp_function = (void (*)(ulong, ulong, ulong))gd->arch.ipi[hart].addr;
+	invalidate_icache_all();
+
+	/*
+	 * Clear the IPI to acknowledge the request before jumping to the
+	 * requested function.
+	 */
 	ret = riscv_clear_ipi(hart);
 	if (ret) {
 		pr_err("Cannot clear IPI of hart %ld\n", hart);
 		return;
 	}
 
-	__smp_mb();
-
-	smp_function = (void (*)(ulong, ulong, ulong))gd->arch.ipi[hart].addr;
-	invalidate_icache_all();
-
 	smp_function(hart, gd->arch.ipi[hart].arg0, gd->arch.ipi[hart].arg1);
 }
 
-int smp_call_function(ulong addr, ulong arg0, ulong arg1)
+int smp_call_function(ulong addr, ulong arg0, ulong arg1, int wait)
 {
 	int ret = 0;
 	struct ipi_data ipi;
@@ -127,7 +140,7 @@ int smp_call_function(ulong addr, ulong arg0, ulong arg1)
 	ipi.arg0 = arg0;
 	ipi.arg1 = arg1;
 
-	ret = send_ipi_many(&ipi);
+	ret = send_ipi_many(&ipi, wait);
 
 	return ret;
 }
diff --git a/arch/riscv/lib/spl.c b/arch/riscv/lib/spl.c
index a544df0a2b..dc7577f751 100644
--- a/arch/riscv/lib/spl.c
+++ b/arch/riscv/lib/spl.c
@@ -41,7 +41,7 @@ void __noreturn jump_to_image_no_args(struct spl_image_info *spl_image)
 
 	debug("image entry point: 0x%lX\n", spl_image->entry_point);
 #ifdef CONFIG_SMP
-	ret = smp_call_function(spl_image->entry_point, (ulong)fdt_blob, 0);
+	ret = smp_call_function(spl_image->entry_point, (ulong)fdt_blob, 0, 0);
 	if (ret)
 		hang();
 #endif
diff --git a/common/spl/spl_opensbi.c b/common/spl/spl_opensbi.c
index fed41b1e66..58bf2468ce 100644
--- a/common/spl/spl_opensbi.c
+++ b/common/spl/spl_opensbi.c
@@ -78,7 +78,7 @@ void spl_invoke_opensbi(struct spl_image_info *spl_image)
 #ifdef CONFIG_SMP
 	ret = smp_call_function((ulong)spl_image->entry_point,
 				(ulong)spl_image->fdt_addr,
-				(ulong)&opensbi_info);
+				(ulong)&opensbi_info, 0);
 	if (ret)
 		hang();
 #endif
-- 
2.21.0