Merge tag 'riscv-for-linus-6.7-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux

Pull RISC-V updates from Palmer Dabbelt:

 - Support for cbo.zero in userspace

 - Support for CBOs on ACPI-based systems

 - A handful of improvements for the T-Head cache flushing ops

 - Support for software shadow call stacks

 - Various cleanups and fixes

* tag 'riscv-for-linus-6.7-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux: (31 commits)
  RISC-V: hwprobe: Fix vDSO SIGSEGV
  riscv: configs: defconfig: Enable configs required for RZ/Five SoC
  riscv: errata: prefix T-Head mnemonics with th.
  riscv: put interrupt entries into .irqentry.text
  riscv: mm: Update the comment of CONFIG_PAGE_OFFSET
  riscv: Using TOOLCHAIN_HAS_ZIHINTPAUSE marco replace zihintpause
  riscv/mm: Fix the comment for swap pte format
  RISC-V: clarify the QEMU workaround in ISA parser
  riscv: correct pt_level name via pgtable_l5/4_enabled
  RISC-V: Provide pgtable_l5_enabled on rv32
  clocksource: timer-riscv: Increase rating of clock_event_device for Sstc
  clocksource: timer-riscv: Don't enable/disable timer interrupt
  lkdtm: Fix CFI_BACKWARD on RISC-V
  riscv: Use separate IRQ shadow call stacks
  riscv: Implement Shadow Call Stack
  riscv: Move global pointer loading to a macro
  riscv: Deduplicate IRQ stack switching
  riscv: VMAP_STACK overflow detection thread-safe
  RISC-V: cacheflush: Initialize CBO variables on ACPI systems
  RISC-V: ACPI: RHCT: Add function to get CBO block sizes
  ...

15 files changed, 156 insertions, 17 deletions

diff --git a/arch/riscv/include/asm/acpi.h b/arch/riscv/include/asm/acpi.h
index d5604d2073bc..7dad0cf9d701 100644
--- a/arch/riscv/include/asm/acpi.h
+++ b/arch/riscv/include/asm/acpi.h
@@ -66,6 +66,8 @@ int acpi_get_riscv_isa(struct acpi_table_header *table,
 		       unsigned int cpu, const char **isa);
 
 static inline int acpi_numa_get_nid(unsigned int cpu) { return NUMA_NO_NODE; }
+void acpi_get_cbo_block_size(struct acpi_table_header *table, u32 *cbom_size,
+			     u32 *cboz_size, u32 *cbop_size);
 #else
 static inline void acpi_init_rintc_map(void) { }
 static inline struct acpi_madt_rintc *acpi_cpu_get_madt_rintc(int cpu)
@@ -79,6 +81,10 @@ static inline int acpi_get_riscv_isa(struct acpi_table_header *table,
 	return -EINVAL;
 }
 
+static inline void acpi_get_cbo_block_size(struct acpi_table_header *table,
+					   u32 *cbom_size, u32 *cboz_size,
+					   u32 *cbop_size) { }
+
 #endif /* CONFIG_ACPI */
 
 #endif /*_ASM_ACPI_H*/
diff --git a/arch/riscv/include/asm/asm-prototypes.h b/arch/riscv/include/asm/asm-prototypes.h
index 61ba8ed43d8f..36b955c762ba 100644
--- a/arch/riscv/include/asm/asm-prototypes.h
+++ b/arch/riscv/include/asm/asm-prototypes.h
@@ -25,7 +25,6 @@ DECLARE_DO_ERROR_INFO(do_trap_ecall_s);
 DECLARE_DO_ERROR_INFO(do_trap_ecall_m);
 DECLARE_DO_ERROR_INFO(do_trap_break);
 
-asmlinkage unsigned long get_overflow_stack(void);
 asmlinkage void handle_bad_stack(struct pt_regs *regs);
 asmlinkage void do_page_fault(struct pt_regs *regs);
 asmlinkage void do_irq(struct pt_regs *regs);
diff --git a/arch/riscv/include/asm/asm.h b/arch/riscv/include/asm/asm.h
index 114bbadaef41..b0487b39e674 100644
--- a/arch/riscv/include/asm/asm.h
+++ b/arch/riscv/include/asm/asm.h
@@ -82,6 +82,47 @@
 	.endr
 .endm
 
+#ifdef CONFIG_SMP
+#ifdef CONFIG_32BIT
+#define PER_CPU_OFFSET_SHIFT 2
+#else
+#define PER_CPU_OFFSET_SHIFT 3
+#endif
+
+.macro asm_per_cpu dst sym tmp
+	REG_L \tmp, TASK_TI_CPU_NUM(tp)
+	slli  \tmp, \tmp, PER_CPU_OFFSET_SHIFT
+	la    \dst, __per_cpu_offset
+	add   \dst, \dst, \tmp
+	REG_L \tmp, 0(\dst)
+	la    \dst, \sym
+	add   \dst, \dst, \tmp
+.endm
+#else /* CONFIG_SMP */
+.macro asm_per_cpu dst sym tmp
+	la    \dst, \sym
+.endm
+#endif /* CONFIG_SMP */
+
+.macro load_per_cpu dst ptr tmp
+	asm_per_cpu \dst \ptr \tmp
+	REG_L \dst, 0(\dst)
+.endm
+
+#ifdef CONFIG_SHADOW_CALL_STACK
+/* gp is used as the shadow call stack pointer instead */
+.macro load_global_pointer
+.endm
+#else
+/* load __global_pointer to gp */
+.macro load_global_pointer
+.option push
+.option norelax
+	la gp, __global_pointer$
+.option pop
+.endm
+#endif /* CONFIG_SHADOW_CALL_STACK */
+
 	/* save all GPs except x1 ~ x5 */
 	.macro save_from_x6_to_x31
 	REG_S x6,  PT_T1(sp)
diff --git a/arch/riscv/include/asm/cpufeature.h b/arch/riscv/include/asm/cpufeature.h
index d0345bd659c9..13b7d35648a9 100644
--- a/arch/riscv/include/asm/cpufeature.h
+++ b/arch/riscv/include/asm/cpufeature.h
@@ -31,5 +31,6 @@ DECLARE_PER_CPU(long, misaligned_access_speed);
 extern struct riscv_isainfo hart_isa[NR_CPUS];
 
 void check_unaligned_access(int cpu);
+void riscv_user_isa_enable(void);
 
 #endif
diff --git a/arch/riscv/include/asm/errata_list.h b/arch/riscv/include/asm/errata_list.h
index b55b434f0059..0ac18a4135be 100644
--- a/arch/riscv/include/asm/errata_list.h
+++ b/arch/riscv/include/asm/errata_list.h
@@ -95,25 +95,25 @@ asm volatile(ALTERNATIVE(						\
 #endif
 
 /*
- * dcache.ipa rs1 (invalidate, physical address)
+ * th.dcache.ipa rs1 (invalidate, physical address)
  * | 31 - 25 | 24 - 20 | 19 - 15 | 14 - 12 | 11 - 7 | 6 - 0 |
  *   0000001    01010      rs1       000      00000  0001011
- * dache.iva rs1 (invalida, virtual address)
+ * th.dache.iva rs1 (invalida, virtual address)
  *   0000001    00110      rs1       000      00000  0001011
  *
- * dcache.cpa rs1 (clean, physical address)
+ * th.dcache.cpa rs1 (clean, physical address)
  * | 31 - 25 | 24 - 20 | 19 - 15 | 14 - 12 | 11 - 7 | 6 - 0 |
  *   0000001    01001      rs1       000      00000  0001011
- * dcache.cva rs1 (clean, virtual address)
+ * th.dcache.cva rs1 (clean, virtual address)
  *   0000001    00101      rs1       000      00000  0001011
  *
- * dcache.cipa rs1 (clean then invalidate, physical address)
+ * th.dcache.cipa rs1 (clean then invalidate, physical address)
  * | 31 - 25 | 24 - 20 | 19 - 15 | 14 - 12 | 11 - 7 | 6 - 0 |
  *   0000001    01011      rs1       000      00000  0001011
- * dcache.civa rs1 (... virtual address)
+ * th.dcache.civa rs1 (... virtual address)
  *   0000001    00111      rs1       000      00000  0001011
  *
- * sync.s (make sure all cache operations finished)
+ * th.sync.s (make sure all cache operations finished)
  * | 31 - 25 | 24 - 20 | 19 - 15 | 14 - 12 | 11 - 7 | 6 - 0 |
  *   0000000    11001     00000      000      00000  0001011
  */
diff --git a/arch/riscv/include/asm/hwcap.h b/arch/riscv/include/asm/hwcap.h
index 6fc51c1b34cf..fe6656af967a 100644
--- a/arch/riscv/include/asm/hwcap.h
+++ b/arch/riscv/include/asm/hwcap.h
@@ -72,6 +72,7 @@
 #ifndef __ASSEMBLY__
 
 #include <linux/jump_label.h>
+#include <asm/cpufeature.h>
 
 unsigned long riscv_get_elf_hwcap(void);
 
@@ -139,6 +140,21 @@ l_yes:
 	return true;
 }
 
+static __always_inline bool riscv_cpu_has_extension_likely(int cpu, const unsigned long ext)
+{
+	if (IS_ENABLED(CONFIG_RISCV_ALTERNATIVE) && riscv_has_extension_likely(ext))
+		return true;
+
+	return __riscv_isa_extension_available(hart_isa[cpu].isa, ext);
+}
+
+static __always_inline bool riscv_cpu_has_extension_unlikely(int cpu, const unsigned long ext)
+{
+	if (IS_ENABLED(CONFIG_RISCV_ALTERNATIVE) && riscv_has_extension_unlikely(ext))
+		return true;
+
+	return __riscv_isa_extension_available(hart_isa[cpu].isa, ext);
+}
 #endif
 
 #endif /* _ASM_RISCV_HWCAP_H */
diff --git a/arch/riscv/include/asm/hwprobe.h b/arch/riscv/include/asm/hwprobe.h
index 78936f4ff513..5c48f48e79a6 100644
--- a/arch/riscv/include/asm/hwprobe.h
+++ b/arch/riscv/include/asm/hwprobe.h
@@ -8,6 +8,11 @@
 
 #include <uapi/asm/hwprobe.h>
 
-#define RISCV_HWPROBE_MAX_KEY 5
+#define RISCV_HWPROBE_MAX_KEY 6
+
+static inline bool riscv_hwprobe_key_is_valid(__s64 key)
+{
+	return key >= 0 && key <= RISCV_HWPROBE_MAX_KEY;
+}
 
 #endif
diff --git a/arch/riscv/include/asm/irq_stack.h b/arch/riscv/include/asm/irq_stack.h
index e4042d297580..6441ded3b0cf 100644
--- a/arch/riscv/include/asm/irq_stack.h
+++ b/arch/riscv/include/asm/irq_stack.h
@@ -12,6 +12,9 @@
 
 DECLARE_PER_CPU(ulong *, irq_stack_ptr);
 
+asmlinkage void call_on_irq_stack(struct pt_regs *regs,
+				  void (*func)(struct pt_regs *));
+
 #ifdef CONFIG_VMAP_STACK
 /*
  * To ensure that VMAP'd stack overflow detection works correctly, all VMAP'd
diff --git a/arch/riscv/include/asm/page.h b/arch/riscv/include/asm/page.h
index 5488ecc337b6..57e887bfa34c 100644
--- a/arch/riscv/include/asm/page.h
+++ b/arch/riscv/include/asm/page.h
@@ -33,8 +33,8 @@
 #define PAGE_OFFSET		_AC(CONFIG_PAGE_OFFSET, UL)
 #endif
 /*
- * By default, CONFIG_PAGE_OFFSET value corresponds to SV48 address space so
- * define the PAGE_OFFSET value for SV39.
+ * By default, CONFIG_PAGE_OFFSET value corresponds to SV57 address space so
+ * define the PAGE_OFFSET value for SV48 and SV39.
  */
 #define PAGE_OFFSET_L4		_AC(0xffffaf8000000000, UL)
 #define PAGE_OFFSET_L3		_AC(0xffffffd800000000, UL)
diff --git a/arch/riscv/include/asm/pgtable-32.h b/arch/riscv/include/asm/pgtable-32.h
index 59ba1fbaf784..00f3369570a8 100644
--- a/arch/riscv/include/asm/pgtable-32.h
+++ b/arch/riscv/include/asm/pgtable-32.h
@@ -33,4 +33,7 @@
 					  _PAGE_WRITE | _PAGE_EXEC |	\
 					  _PAGE_USER | _PAGE_GLOBAL))
 
+static const __maybe_unused int pgtable_l4_enabled;
+static const __maybe_unused int pgtable_l5_enabled;
+
 #endif /* _ASM_RISCV_PGTABLE_32_H */
diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h
index b2ba3f79cfe9..c8e8867c42f6 100644
--- a/arch/riscv/include/asm/pgtable.h
+++ b/arch/riscv/include/asm/pgtable.h
@@ -811,7 +811,7 @@ extern pmd_t pmdp_collapse_flush(struct vm_area_struct *vma,
  *	bit            5:	_PAGE_PROT_NONE (zero)
  *	bit            6:	exclusive marker
  *	bits      7 to 11:	swap type
- *	bits 11 to XLEN-1:	swap offset
+ *	bits 12 to XLEN-1:	swap offset
  */
 #define __SWP_TYPE_SHIFT	7
 #define __SWP_TYPE_BITS		5
@@ -914,7 +914,6 @@ extern uintptr_t _dtb_early_pa;
 #define dtb_early_pa	_dtb_early_pa
 #endif /* CONFIG_XIP_KERNEL */
 extern u64 satp_mode;
-extern bool pgtable_l4_enabled;
 
 void paging_init(void);
 void misc_mem_init(void);
diff --git a/arch/riscv/include/asm/scs.h b/arch/riscv/include/asm/scs.h
new file mode 100644
index 000000000000..0e45db78b24b
--- /dev/null
+++ b/arch/riscv/include/asm/scs.h
@@ -0,0 +1,54 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_SCS_H
+#define _ASM_SCS_H
+
+#ifdef __ASSEMBLY__
+#include <asm/asm-offsets.h>
+
+#ifdef CONFIG_SHADOW_CALL_STACK
+
+/* Load init_shadow_call_stack to gp. */
+.macro scs_load_init_stack
+	la	gp, init_shadow_call_stack
+	XIP_FIXUP_OFFSET gp
+.endm
+
+/* Load the per-CPU IRQ shadow call stack to gp. */
+.macro scs_load_irq_stack tmp
+	load_per_cpu gp, irq_shadow_call_stack_ptr, \tmp
+.endm
+
+/* Load task_scs_sp(current) to gp. */
+.macro scs_load_current
+	REG_L	gp, TASK_TI_SCS_SP(tp)
+.endm
+
+/* Load task_scs_sp(current) to gp, but only if tp has changed. */
+.macro scs_load_current_if_task_changed prev
+	beq	\prev, tp, _skip_scs
+	scs_load_current
+_skip_scs:
+.endm
+
+/* Save gp to task_scs_sp(current). */
+.macro scs_save_current
+	REG_S	gp, TASK_TI_SCS_SP(tp)
+.endm
+
+#else /* CONFIG_SHADOW_CALL_STACK */
+
+.macro scs_load_init_stack
+.endm
+.macro scs_load_irq_stack tmp
+.endm
+.macro scs_load_current
+.endm
+.macro scs_load_current_if_task_changed prev
+.endm
+.macro scs_save_current
+.endm
+
+#endif /* CONFIG_SHADOW_CALL_STACK */
+#endif /* __ASSEMBLY__ */
+
+#endif /* _ASM_SCS_H */
diff --git a/arch/riscv/include/asm/thread_info.h b/arch/riscv/include/asm/thread_info.h
index 1833beb00489..574779900bfb 100644
--- a/arch/riscv/include/asm/thread_info.h
+++ b/arch/riscv/include/asm/thread_info.h
@@ -34,9 +34,6 @@
 
 #ifndef __ASSEMBLY__
 
-extern long shadow_stack[SHADOW_OVERFLOW_STACK_SIZE / sizeof(long)];
-extern unsigned long spin_shadow_stack;
-
 #include <asm/processor.h>
 #include <asm/csr.h>
 
@@ -60,8 +57,20 @@ struct thread_info {
 	long			user_sp;	/* User stack pointer */
 	int			cpu;
 	unsigned long		syscall_work;	/* SYSCALL_WORK_ flags */
+#ifdef CONFIG_SHADOW_CALL_STACK
+	void			*scs_base;
+	void			*scs_sp;
+#endif
 };
 
+#ifdef CONFIG_SHADOW_CALL_STACK
+#define INIT_SCS							\
+	.scs_base	= init_shadow_call_stack,			\
+	.scs_sp		= init_shadow_call_stack,
+#else
+#define INIT_SCS
+#endif
+
 /*
  * macros/functions for gaining access to the thread information structure
  *
@@ -71,6 +80,7 @@ struct thread_info {
 {						\
 	.flags		= 0,			\
 	.preempt_count	= INIT_PREEMPT_COUNT,	\
+	INIT_SCS				\
 }
 
 void arch_release_task_struct(struct task_struct *tsk);
diff --git a/arch/riscv/include/asm/vdso/processor.h b/arch/riscv/include/asm/vdso/processor.h
index 14f5d27783b8..96b65a5396df 100644
--- a/arch/riscv/include/asm/vdso/processor.h
+++ b/arch/riscv/include/asm/vdso/processor.h
@@ -14,7 +14,7 @@ static inline void cpu_relax(void)
 	__asm__ __volatile__ ("div %0, %0, zero" : "=r" (dummy));
 #endif
 
-#ifdef __riscv_zihintpause
+#ifdef CONFIG_TOOLCHAIN_HAS_ZIHINTPAUSE
 	/*
 	 * Reduce instruction retirement.
 	 * This assumes the PC changes.
diff --git a/arch/riscv/include/uapi/asm/hwprobe.h b/arch/riscv/include/uapi/asm/hwprobe.h
index d43e306ce2f9..b659ffcfcdb4 100644
--- a/arch/riscv/include/uapi/asm/hwprobe.h
+++ b/arch/riscv/include/uapi/asm/hwprobe.h
@@ -29,6 +29,7 @@ struct riscv_hwprobe {
 #define		RISCV_HWPROBE_EXT_ZBA		(1 << 3)
 #define		RISCV_HWPROBE_EXT_ZBB		(1 << 4)
 #define		RISCV_HWPROBE_EXT_ZBS		(1 << 5)
+#define		RISCV_HWPROBE_EXT_ZICBOZ	(1 << 6)
 #define RISCV_HWPROBE_KEY_CPUPERF_0	5
 #define		RISCV_HWPROBE_MISALIGNED_UNKNOWN	(0 << 0)
 #define		RISCV_HWPROBE_MISALIGNED_EMULATED	(1 << 0)
@@ -36,6 +37,7 @@ struct riscv_hwprobe {
 #define		RISCV_HWPROBE_MISALIGNED_FAST		(3 << 0)
 #define		RISCV_HWPROBE_MISALIGNED_UNSUPPORTED	(4 << 0)
 #define		RISCV_HWPROBE_MISALIGNED_MASK		(7 << 0)
+#define RISCV_HWPROBE_KEY_ZICBOZ_BLOCK_SIZE	6
 /* Increase RISCV_HWPROBE_MAX_KEY when adding items. */
 
 #endif