[V3,1/1] riscv: Increase the upper bound of NR_CPUS to 4095

[Leo Yu-Chi Liang]

From: Xiang W <wxjstz at 126.com>

The maximum hart number is 32 and is determined by
the type of gd->arch.available_harts. However, various
RISC-V specifications allow the hart number to be greater
than 32. We can eliminate this limitation through bitmaps.

The patch modifies the upper bound of the hart number to 4095,
which is also the maximum hart number RISC-V Advanced Core Local
Interruptor Specification gives.

Some defconfigs, (e.g. qemu-riscv32_smode_defconfig,
qemu-riscv64_smode_defconfig, openpiton_riscv64_defconfig, ...)
do not define CONFIG_NR_CPUS, and may result in compile error,
so define CONFIG_NR_CPUS to be 1 if CONFIG_NR_CPUS is not defined.

Tested on sifive unmatched.

Signed-off-by: Xiang W <wxjstz at 126.com>
Signed-off-by: Leo Yu-Chi Liang <ycliang at andestech.com>
---
Changes v2 -> v3:
- Fix the calculation of the GD_AVAILABLE_HARTS start address
- Fix compilation error for defconfigs that do not define CONFIG_NR_CPUS
---
 arch/riscv/Kconfig                   |  4 ++--
 arch/riscv/cpu/start.S               | 20 +++++++++++++++-----
 arch/riscv/include/asm/global_data.h |  8 +++++++-
 arch/riscv/lib/smp.c                 |  2 +-
 4 files changed, 25 insertions(+), 9 deletions(-)

diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index ebc4bef220..063734cbb9 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -232,8 +232,8 @@ config SPL_SMP
 	  all, single processor machines.
 
 config NR_CPUS
-	int "Maximum number of CPUs (2-32)"
-	range 2 32
+	int "Maximum number of CPUs (2-4095)"
+	range 2 4095
 	depends on SMP || SPL_SMP
 	default 8
 	help
diff --git a/arch/riscv/cpu/start.S b/arch/riscv/cpu/start.S
index 4687bca3c9..ae19c2b43d 100644
--- a/arch/riscv/cpu/start.S
+++ b/arch/riscv/cpu/start.S
@@ -172,11 +172,21 @@ wait_for_gd_init:
 	bnez	t1, 1b
 
 	/* register available harts in the available_harts mask */
-	li	t1, 1
-	sll	t1, t1, tp
-	LREG	t2, GD_AVAILABLE_HARTS(gp)
-	or	t2, t2, t1
-	SREG	t2, GD_AVAILABLE_HARTS(gp)
+	li	t1, GD_AVAILABLE_HARTS
+	add	t1, t1, gp
+#if defined(CONFIG_ARCH_RV64I)
+	srli	t2, tp, 6
+	slli	t2, t2, 3
+#elif defined(CONFIG_ARCH_RV32I)
+	srli	t2, tp, 5
+	slli	t2, t2, 2
+#endif
+	add	t1, t1, t2
+	LREG	t2, 0(t1)
+	li	t3, 1
+	sll	t3, t3, tp
+	or	t2, t2, t3
+	SREG	t2, 0(t1)
 
 	amoswap.w.rl zero, zero, 0(t0)
 #endif
diff --git a/arch/riscv/include/asm/global_data.h b/arch/riscv/include/asm/global_data.h
index 6fdc86dd8b..7e37e90db0 100644
--- a/arch/riscv/include/asm/global_data.h
+++ b/arch/riscv/include/asm/global_data.h
@@ -10,9 +10,15 @@
 #ifndef	__ASM_GBL_DATA_H
 #define __ASM_GBL_DATA_H
 
+#include <config.h>
 #include <asm/smp.h>
 #include <asm/u-boot.h>
 #include <compiler.h>
+#include <linux/bitops.h>
+
+#ifndef CONFIG_NR_CPUS
+#define CONFIG_NR_CPUS 1
+#endif
 
 /* Architecture-specific global data */
 struct arch_global_data {
@@ -29,7 +35,7 @@ struct arch_global_data {
 #endif
 #if !CONFIG_IS_ENABLED(XIP)
 #ifdef CONFIG_AVAILABLE_HARTS
-	ulong available_harts;
+	ulong available_harts[BITS_TO_LONGS(CONFIG_NR_CPUS)];
 #endif
 #endif
 };
diff --git a/arch/riscv/lib/smp.c b/arch/riscv/lib/smp.c
index 4f073a016f..511e3ed98d 100644
--- a/arch/riscv/lib/smp.c
+++ b/arch/riscv/lib/smp.c
@@ -48,7 +48,7 @@ static int send_ipi_many(struct ipi_data *ipi, int wait)
 #if !CONFIG_IS_ENABLED(XIP)
 #ifdef CONFIG_AVAILABLE_HARTS
 		/* skip if hart is not available */
-		if (!(gd->arch.available_harts & (1 << reg)))
+		if (!test_bit(reg, gd->arch.available_harts))
 			continue;
 #endif
 #endif
-- 
2.38.0.68.ge85701b4af.dirty