riscv: Add support for Zicbop

Zicbop introduces cache blocks prefetching instructions, add the
necessary support for the kernel to use it in the coming commits.

Co-developed-by: Guo Ren <guoren@kernel.org>
Signed-off-by: Guo Ren <guoren@kernel.org>
Tested-by: Andrea Parri <parri.andrea@gmail.com>
Link: https://lore.kernel.org/r/20250421142441.395849-3-alexghiti@rivosinc.com
Signed-off-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Signed-off-by: Palmer Dabbelt <palmer@dabbelt.com>

arch/riscv/Kconfig

@@ -842,6 +842,21 @@ config RISCV_ISA_ZICBOZ
 
 	   If you don't know what to do here, say Y.
 
+config RISCV_ISA_ZICBOP
+	bool "Zicbop extension support for cache block prefetch"
+	depends on MMU
+	depends on RISCV_ALTERNATIVE
+	default y
+	help
+	  Adds support to dynamically detect the presence of the ZICBOP
+	  extension (Cache Block Prefetch Operations) and enable its
+	  usage.
+
+	  The Zicbop extension can be used to prefetch cache blocks for
+	  read/write fetch.
+
+	  If you don't know what to do here, say Y.
+
 config TOOLCHAIN_NEEDS_EXPLICIT_ZICSR_ZIFENCEI
 	def_bool y
 	# https://sourceware.org/git/?p=binutils-gdb.git;a=commit;h=aed44286efa8ae8717a77d94b51ac3614e2ca6dc

arch/riscv/include/asm/barrier.h

@@ -14,11 +14,6 @@
 #include <asm/cmpxchg.h>
 #include <asm/fence.h>
 
-#define nop()		__asm__ __volatile__ ("nop")
-#define __nops(n)	".rept	" #n "\nnop\n.endr\n"
-#define nops(n)		__asm__ __volatile__ (__nops(n))
-
-
 /* These barriers need to enforce ordering on both devices or memory. */
 #define __mb()		RISCV_FENCE(iorw, iorw)
 #define __rmb()		RISCV_FENCE(ir, ir)

arch/riscv/include/asm/cacheflush.h

@@ -80,6 +80,7 @@ void flush_icache_mm(struct mm_struct *mm, bool local);
 
 extern unsigned int riscv_cbom_block_size;
 extern unsigned int riscv_cboz_block_size;
+extern unsigned int riscv_cbop_block_size;
 void riscv_init_cbo_blocksizes(void);
 
 #ifdef CONFIG_RISCV_DMA_NONCOHERENT

arch/riscv/include/asm/hwcap.h

@@ -105,6 +105,7 @@
 #define RISCV_ISA_EXT_ZVFBFWMA		96
 #define RISCV_ISA_EXT_ZAAMO		97
 #define RISCV_ISA_EXT_ZALRSC		98
+#define RISCV_ISA_EXT_ZICBOP		99
 
 #define RISCV_ISA_EXT_XLINUXENVCFG	127
 

arch/riscv/include/asm/insn-def.h

@@ -263,4 +263,10 @@
 
 #define RISCV_INSN_NOP4	_AC(0x00000013, U)
 
+#ifndef __ASSEMBLY__
+#define nop()           __asm__ __volatile__ ("nop")
+#define __nops(n)       ".rept  " #n "\nnop\n.endr\n"
+#define nops(n)         __asm__ __volatile__ (__nops(n))
+#endif
+
 #endif /* __ASM_INSN_DEF_H */

arch/riscv/include/asm/processor.h

@@ -52,7 +52,6 @@
 #endif
 
 #ifndef __ASSEMBLY__
-#include <linux/cpumask.h>
 
 struct task_struct;
 struct pt_regs;

arch/riscv/kernel/cpufeature.c

@@ -32,6 +32,7 @@
 #define NUM_ALPHA_EXTS ('z' - 'a' + 1)
 
 static bool any_cpu_has_zicboz;
+static bool any_cpu_has_zicbop;
 static bool any_cpu_has_zicbom;
 
 unsigned long elf_hwcap __read_mostly;
@@ -119,6 +120,21 @@ static int riscv_ext_zicboz_validate(const struct riscv_isa_ext_data *data,
 	return 0;
 }
 
+static int riscv_ext_zicbop_validate(const struct riscv_isa_ext_data *data,
+				     const unsigned long *isa_bitmap)
+{
+	if (!riscv_cbop_block_size) {
+		pr_err("Zicbop detected in ISA string, disabling as no cbop-block-size found\n");
+		return -EINVAL;
+	}
+	if (!is_power_of_2(riscv_cbop_block_size)) {
+		pr_err("Zicbop disabled as cbop-block-size present, but is not a power-of-2\n");
+		return -EINVAL;
+	}
+	any_cpu_has_zicbop = true;
+	return 0;
+}
+
 static int riscv_ext_f_validate(const struct riscv_isa_ext_data *data,
 				const unsigned long *isa_bitmap)
 {
@@ -442,6 +458,7 @@ const struct riscv_isa_ext_data riscv_isa_ext[] = {
 	__RISCV_ISA_EXT_SUPERSET_VALIDATE(v, RISCV_ISA_EXT_v, riscv_v_exts, riscv_ext_vector_float_validate),
 	__RISCV_ISA_EXT_DATA(h, RISCV_ISA_EXT_h),
 	__RISCV_ISA_EXT_SUPERSET_VALIDATE(zicbom, RISCV_ISA_EXT_ZICBOM, riscv_xlinuxenvcfg_exts, riscv_ext_zicbom_validate),
+	__RISCV_ISA_EXT_DATA_VALIDATE(zicbop, RISCV_ISA_EXT_ZICBOP, riscv_ext_zicbop_validate),
 	__RISCV_ISA_EXT_SUPERSET_VALIDATE(zicboz, RISCV_ISA_EXT_ZICBOZ, riscv_xlinuxenvcfg_exts, riscv_ext_zicboz_validate),
 	__RISCV_ISA_EXT_DATA(ziccrse, RISCV_ISA_EXT_ZICCRSE),
 	__RISCV_ISA_EXT_DATA(zicntr, RISCV_ISA_EXT_ZICNTR),
@@ -1112,6 +1129,10 @@ void __init riscv_user_isa_enable(void)
 		current->thread.envcfg |= ENVCFG_CBCFE;
 	else if (any_cpu_has_zicbom)
 		pr_warn("Zicbom disabled as it is unavailable on some harts\n");
+
+	if (!riscv_has_extension_unlikely(RISCV_ISA_EXT_ZICBOP) &&
+	    any_cpu_has_zicbop)
+		pr_warn("Zicbop disabled as it is unavailable on some harts\n");
 }
 
 #ifdef CONFIG_RISCV_ALTERNATIVE

arch/riscv/mm/cacheflush.c

@@ -101,6 +101,9 @@ EXPORT_SYMBOL_GPL(riscv_cbom_block_size);
 unsigned int riscv_cboz_block_size;
 EXPORT_SYMBOL_GPL(riscv_cboz_block_size);
 
+unsigned int riscv_cbop_block_size;
+EXPORT_SYMBOL_GPL(riscv_cbop_block_size);
+
 static void __init cbo_get_block_size(struct device_node *node,
 				      const char *name, u32 *block_size,
 				      unsigned long *first_hartid)
@@ -125,8 +128,8 @@ static void __init cbo_get_block_size(struct device_node *node,
 
 void __init riscv_init_cbo_blocksizes(void)
 {
-	unsigned long cbom_hartid, cboz_hartid;
-	u32 cbom_block_size = 0, cboz_block_size = 0;
+	unsigned long cbom_hartid, cboz_hartid, cbop_hartid;
+	u32 cbom_block_size = 0, cboz_block_size = 0, cbop_block_size = 0;
 	struct device_node *node;
 	struct acpi_table_header *rhct;
 	acpi_status status;
@@ -138,13 +141,15 @@ void __init riscv_init_cbo_blocksizes(void)
 					   &cbom_block_size, &cbom_hartid);
 			cbo_get_block_size(node, "riscv,cboz-block-size",
 					   &cboz_block_size, &cboz_hartid);
+			cbo_get_block_size(node, "riscv,cbop-block-size",
+					   &cbop_block_size, &cbop_hartid);
 		}
 	} else {
 		status = acpi_get_table(ACPI_SIG_RHCT, 0, &rhct);
 		if (ACPI_FAILURE(status))
 			return;
 
-		acpi_get_cbo_block_size(rhct, &cbom_block_size, &cboz_block_size, NULL);
+		acpi_get_cbo_block_size(rhct, &cbom_block_size, &cboz_block_size, &cbop_block_size);
 		acpi_put_table((struct acpi_table_header *)rhct);
 	}
 
@@ -153,6 +158,9 @@ void __init riscv_init_cbo_blocksizes(void)
 
 	if (cboz_block_size)
 		riscv_cboz_block_size = cboz_block_size;
+
+	if (cbop_block_size)
+		riscv_cbop_block_size = cbop_block_size;
 }
 
 #ifdef CONFIG_SMP