Merge patch series "riscv: improve boot time isa extensions handling"

Jisheng Zhang <jszhang@kernel.org> says:

Generally, riscv ISA extensions are fixed for any specific hardware
platform, so a hart's features won't change after booting, this
chacteristic makes it straightforward to use a static branch to check
a specific ISA extension is supported or not to optimize performance.

However, some ISA extensions such as SVPBMT and ZICBOM are handled
via. the alternative sequences.

Basically, for ease of maintenance, we prefer to use static branches
in C code, but recently, Samuel found that the static branch usage in
cpu_relax() breaks building with CONFIG_CC_OPTIMIZE_FOR_SIZE[1]. As
Samuel pointed out, "Having a static branch in cpu_relax() is
problematic because that function is widely inlined, including in some
quite complex functions like in the VDSO. A quick measurement shows
this static branch is responsible by itself for around 40% of the jump
table."

Samuel's findings pointed out one of a few downsides of static branches
usage in C code to handle ISA extensions detected at boot time:
static branch's metadata in the __jump_table section, which is not
discarded after ISA extensions are finalized, wastes some space.

I want to try to solve the issue for all possible dynamic handling of
ISA extensions at boot time. Inspired by Mark[2], this patch introduces
riscv_has_extension_*() helpers, which work like static branches but
are patched using alternatives, thus the metadata can be freed after
patching.

[1]https://lore.kernel.org/linux-riscv/20220922060958.44203-1-samuel@sholland.org/
[2]https://lore.kernel.org/linux-arm-kernel/20220912162210.3626215-8-mark.rutland@arm.com/
[3]https://lore.kernel.org/linux-riscv/20221130225614.1594256-1-heiko@sntech.de/

* b4-shazam-merge:
  riscv: remove riscv_isa_ext_keys[] array and related usage
  riscv: KVM: Switch has_svinval() to riscv_has_extension_unlikely()
  riscv: cpu_relax: switch to riscv_has_extension_likely()
  riscv: alternative: patch alternatives in the vDSO
  riscv: switch to relative alternative entries
  riscv: module: Add ADD16 and SUB16 rela types
  riscv: module: move find_section to module.h
  riscv: fpu: switch has_fpu() to riscv_has_extension_likely()
  riscv: introduce riscv_has_extension_[un]likely()
  riscv: cpufeature: extend riscv_cpufeature_patch_func to all ISA extensions
  riscv: hwcap: make ISA extension ids can be used in asm
  riscv: cpufeature: detect RISCV_ALTERNATIVES_EARLY_BOOT earlier
  riscv: move riscv_noncoherent_supported() out of ZICBOM probe

Link: https://lore.kernel.org/r/20230128172856.3814-1-jszhang@kernel.org
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>

Author: palmer-dabbelt

arch/riscv/errata/sifive/errata.c

@@ -107,7 +107,8 @@ void __init_or_module sifive_errata_patch_func(struct alt_entry *begin,
 
 		tmp = (1U << alt->errata_id);
 		if (cpu_req_errata & tmp) {
-			patch_text_nosync(alt->old_ptr, alt->alt_ptr, alt->alt_len);
+			patch_text_nosync(ALT_OLD_PTR(alt), ALT_ALT_PTR(alt),
+					  alt->alt_len);
 			cpu_apply_errata |= tmp;
 		}
 	}

arch/riscv/errata/thead/errata.c

@@ -87,6 +87,7 @@ void __init_or_module thead_errata_patch_func(struct alt_entry *begin, struct al
 	struct alt_entry *alt;
 	u32 cpu_req_errata = thead_errata_probe(stage, archid, impid);
 	u32 tmp;
+	void *oldptr, *altptr;
 
 	for (alt = begin; alt < end; alt++) {
 		if (alt->vendor_id != THEAD_VENDOR_ID)
@@ -96,12 +97,16 @@ void __init_or_module thead_errata_patch_func(struct alt_entry *begin, struct al
 
 		tmp = (1U << alt->errata_id);
 		if (cpu_req_errata & tmp) {
+			oldptr = ALT_OLD_PTR(alt);
+			altptr = ALT_ALT_PTR(alt);
+
 			/* On vm-alternatives, the mmu isn't running yet */
 			if (stage == RISCV_ALTERNATIVES_EARLY_BOOT)
-				memcpy((void *)__pa_symbol(alt->old_ptr),
-				       (void *)__pa_symbol(alt->alt_ptr), alt->alt_len);
+				memcpy((void *)__pa_symbol(oldptr),
+				       (void *)__pa_symbol(altptr),
+				       alt->alt_len);
 			else
-				patch_text_nosync(alt->old_ptr, alt->alt_ptr, alt->alt_len);
+				patch_text_nosync(oldptr, altptr, alt->alt_len);
 		}
 	}
 

arch/riscv/include/asm/alternative-macros.h

@@ -7,11 +7,11 @@
 #ifdef __ASSEMBLY__
 
 .macro ALT_ENTRY oldptr newptr vendor_id errata_id new_len
-	RISCV_PTR \oldptr
-	RISCV_PTR \newptr
-	REG_ASM \vendor_id
-	REG_ASM \new_len
-	.word	\errata_id
+	.4byte \oldptr - .
+	.4byte \newptr - .
+	.2byte \vendor_id
+	.2byte \new_len
+	.4byte \errata_id
 .endm
 
 .macro ALT_NEW_CONTENT vendor_id, errata_id, enable = 1, new_c : vararg
@@ -59,11 +59,11 @@
 #include <linux/stringify.h>
 
 #define ALT_ENTRY(oldptr, newptr, vendor_id, errata_id, newlen)		\
-	RISCV_PTR " " oldptr "\n"					\
-	RISCV_PTR " " newptr "\n"					\
-	REG_ASM " " vendor_id "\n"					\
-	REG_ASM " " newlen "\n"						\
-	".word " errata_id "\n"
+	".4byte	((" oldptr ") - .) \n"					\
+	".4byte	((" newptr ") - .) \n"					\
+	".2byte	" vendor_id "\n"					\
+	".2byte " newlen "\n"						\
+	".4byte	" errata_id "\n"
 
 #define ALT_NEW_CONTENT(vendor_id, errata_id, enable, new_c)		\
 	".if " __stringify(enable) " == 1\n"				\

arch/riscv/include/asm/alternative.h

@@ -23,6 +23,11 @@
 #define RISCV_ALTERNATIVES_MODULE	1 /* alternatives applied during module-init */
 #define RISCV_ALTERNATIVES_EARLY_BOOT	2 /* alternatives applied before mmu start */
 
+/* add the relative offset to the address of the offset to get the absolute address */
+#define __ALT_PTR(a, f)			((void *)&(a)->f + (a)->f)
+#define ALT_OLD_PTR(a)			__ALT_PTR(a, old_offset)
+#define ALT_ALT_PTR(a)			__ALT_PTR(a, alt_offset)
+
 void __init apply_boot_alternatives(void);
 void __init apply_early_boot_alternatives(void);
 void apply_module_alternatives(void *start, size_t length);
@@ -31,12 +36,12 @@ void riscv_alternative_fix_offsets(void *alt_ptr, unsigned int len,
 				   int patch_offset);
 
 struct alt_entry {
-	void *old_ptr;		 /* address of original instruciton or data  */
-	void *alt_ptr;		 /* address of replacement instruction or data */
-	unsigned long vendor_id; /* cpu vendor id */
-	unsigned long alt_len;   /* The replacement size */
-	unsigned int errata_id;  /* The errata id */
-} __packed;
+	s32 old_offset;		/* offset relative to original instruction or data  */
+	s32 alt_offset;		/* offset relative to replacement instruction or data */
+	u16 vendor_id;		/* cpu vendor id */
+	u16 alt_len;		/* The replacement size */
+	u32 errata_id;		/* The errata id */
+};
 
 struct errata_checkfunc_id {
 	unsigned long vendor_id;

arch/riscv/include/asm/errata_list.h

@@ -7,6 +7,7 @@
 
 #include <asm/alternative.h>
 #include <asm/csr.h>
+#include <asm/hwcap.h>
 #include <asm/vendorid_list.h>
 
 #ifdef CONFIG_ERRATA_SIFIVE
@@ -56,7 +57,7 @@ asm(ALTERNATIVE("sfence.vma %0", "sfence.vma", SIFIVE_VENDOR_ID,	\
 #define ALT_SVPBMT(_val, prot)						\
 asm(ALTERNATIVE_2("li %0, 0\t\nnop",					\
 		  "li %0, %1\t\nslli %0,%0,%3", 0,			\
-			CPUFEATURE_SVPBMT, CONFIG_RISCV_ISA_SVPBMT,	\
+			RISCV_ISA_EXT_SVPBMT, CONFIG_RISCV_ISA_SVPBMT,	\
 		  "li %0, %2\t\nslli %0,%0,%4", THEAD_VENDOR_ID,	\
 			ERRATA_THEAD_PBMT, CONFIG_ERRATA_THEAD_PBMT)	\
 		: "=r"(_val)						\
@@ -130,7 +131,7 @@ asm volatile(ALTERNATIVE_2(						\
 	"add a0, a0, %0\n\t"						\
 	"2:\n\t"							\
 	"bltu a0, %2, 3b\n\t"						\
-	"nop", 0, CPUFEATURE_ZICBOM, CONFIG_RISCV_ISA_ZICBOM,		\
+	"nop", 0, RISCV_ISA_EXT_ZICBOM, CONFIG_RISCV_ISA_ZICBOM,	\
 	"mv a0, %1\n\t"							\
 	"j 2f\n\t"							\
 	"3:\n\t"							\

arch/riscv/include/asm/hwcap.h

@@ -8,24 +8,11 @@
 #ifndef _ASM_RISCV_HWCAP_H
 #define _ASM_RISCV_HWCAP_H
 
+#include <asm/alternative-macros.h>
 #include <asm/errno.h>
 #include <linux/bits.h>
 #include <uapi/asm/hwcap.h>
 
-#ifndef __ASSEMBLY__
-#include <linux/jump_label.h>
-/*
- * This yields a mask that user programs can use to figure out what
- * instruction set this cpu supports.
- */
-#define ELF_HWCAP		(elf_hwcap)
-
-enum {
-	CAP_HWCAP = 1,
-};
-
-extern unsigned long elf_hwcap;
-
 #define RISCV_ISA_EXT_a		('a' - 'a')
 #define RISCV_ISA_EXT_c		('c' - 'a')
 #define RISCV_ISA_EXT_d		('d' - 'a')
@@ -46,61 +33,78 @@ extern unsigned long elf_hwcap;
 #define RISCV_ISA_EXT_BASE 26
 
 /*
- * This enum represent the logical ID for each multi-letter RISC-V ISA extension.
+ * These macros represent the logical ID for each multi-letter RISC-V ISA extension.
  * The logical ID should start from RISCV_ISA_EXT_BASE and must not exceed
  * RISCV_ISA_EXT_MAX. 0-25 range is reserved for single letter
  * extensions while all the multi-letter extensions should define the next
  * available logical extension id.
  * Entries are sorted alphabetically.
  */
-enum riscv_isa_ext_id {
-	RISCV_ISA_EXT_SSCOFPMF = RISCV_ISA_EXT_BASE,
-	RISCV_ISA_EXT_SSTC,
-	RISCV_ISA_EXT_SVINVAL,
-	RISCV_ISA_EXT_SVPBMT,
-	RISCV_ISA_EXT_ZBB,
-	RISCV_ISA_EXT_ZICBOM,
-	RISCV_ISA_EXT_ZIHINTPAUSE,
-	RISCV_ISA_EXT_ID_MAX
-};
-static_assert(RISCV_ISA_EXT_ID_MAX <= RISCV_ISA_EXT_MAX);
+#define RISCV_ISA_EXT_SSCOFPMF         26
+#define RISCV_ISA_EXT_SSTC             27
+#define RISCV_ISA_EXT_SVINVAL          28
+#define RISCV_ISA_EXT_SVPBMT           29
+#define RISCV_ISA_EXT_ZBB              30
+#define RISCV_ISA_EXT_ZICBOM           31
+#define RISCV_ISA_EXT_ZIHINTPAUSE      32
+
+#ifndef __ASSEMBLY__
+
+#include <linux/jump_label.h>
 
 /*
- * This enum represents the logical ID for each RISC-V ISA extension static
- * keys. We can use static key to optimize code path if some ISA extensions
- * are available.
- * Entries are sorted alphabetically.
+ * This yields a mask that user programs can use to figure out what
+ * instruction set this cpu supports.
  */
-enum riscv_isa_ext_key {
-	RISCV_ISA_EXT_KEY_FPU,		/* For 'F' and 'D' */
-	RISCV_ISA_EXT_KEY_SVINVAL,
-	RISCV_ISA_EXT_KEY_ZIHINTPAUSE,
-	RISCV_ISA_EXT_KEY_MAX,
+#define ELF_HWCAP		(elf_hwcap)
+
+enum {
+	CAP_HWCAP = 1,
 };
 
+extern unsigned long elf_hwcap;
+
 struct riscv_isa_ext_data {
 	/* Name of the extension displayed to userspace via /proc/cpuinfo */
 	char uprop[RISCV_ISA_EXT_NAME_LEN_MAX];
 	/* The logical ISA extension ID */
 	unsigned int isa_ext_id;
 };
 
-extern struct static_key_false riscv_isa_ext_keys[RISCV_ISA_EXT_KEY_MAX];
+static __always_inline bool
+riscv_has_extension_likely(const unsigned long ext)
+{
+	compiletime_assert(ext < RISCV_ISA_EXT_MAX,
+			   "ext must be < RISCV_ISA_EXT_MAX");
+
+	asm_volatile_goto(
+	ALTERNATIVE("j	%l[l_no]", "nop", 0, %[ext], 1)
+	:
+	: [ext] "i" (ext)
+	:
+	: l_no);
+
+	return true;
+l_no:
+	return false;
+}
 
-static __always_inline int riscv_isa_ext2key(int num)
+static __always_inline bool
+riscv_has_extension_unlikely(const unsigned long ext)
 {
-	switch (num) {
-	case RISCV_ISA_EXT_f:
-		return RISCV_ISA_EXT_KEY_FPU;
-	case RISCV_ISA_EXT_d:
-		return RISCV_ISA_EXT_KEY_FPU;
-	case RISCV_ISA_EXT_SVINVAL:
-		return RISCV_ISA_EXT_KEY_SVINVAL;
-	case RISCV_ISA_EXT_ZIHINTPAUSE:
-		return RISCV_ISA_EXT_KEY_ZIHINTPAUSE;
-	default:
-		return -EINVAL;
-	}
+	compiletime_assert(ext < RISCV_ISA_EXT_MAX,
+			   "ext must be < RISCV_ISA_EXT_MAX");
+
+	asm_volatile_goto(
+	ALTERNATIVE("nop", "j	%l[l_yes]", 0, %[ext], 1)
+	:
+	: [ext] "i" (ext)
+	:
+	: l_yes);
+
+	return false;
+l_yes:
+	return true;
 }
 
 unsigned long riscv_isa_extension_base(const unsigned long *isa_bitmap);

arch/riscv/include/asm/module.h

@@ -5,6 +5,7 @@
 #define _ASM_RISCV_MODULE_H
 
 #include <asm-generic/module.h>
+#include <linux/elf.h>
 
 struct module;
 unsigned long module_emit_got_entry(struct module *mod, unsigned long val);
@@ -111,4 +112,19 @@ static inline struct plt_entry *get_plt_entry(unsigned long val,
 
 #endif /* CONFIG_MODULE_SECTIONS */
 
+static inline const Elf_Shdr *find_section(const Elf_Ehdr *hdr,
+					   const Elf_Shdr *sechdrs,
+					   const char *name)
+{
+	const Elf_Shdr *s, *se;
+	const char *secstrs = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset;
+
+	for (s = sechdrs, se = sechdrs + hdr->e_shnum; s < se; s++) {
+		if (strcmp(name, secstrs + s->sh_name) == 0)
+			return s;
+	}
+
+	return NULL;
+}
+
 #endif /* _ASM_RISCV_MODULE_H */

arch/riscv/include/asm/switch_to.h

@@ -59,7 +59,8 @@ static inline void __switch_to_aux(struct task_struct *prev,
 
 static __always_inline bool has_fpu(void)
 {
-	return static_branch_likely(&riscv_isa_ext_keys[RISCV_ISA_EXT_KEY_FPU]);
+	return riscv_has_extension_likely(RISCV_ISA_EXT_f) ||
+		riscv_has_extension_likely(RISCV_ISA_EXT_d);
 }
 #else
 static __always_inline bool has_fpu(void) { return false; }

arch/riscv/include/asm/vdso.h

@@ -28,8 +28,12 @@
 #define COMPAT_VDSO_SYMBOL(base, name)						\
 	(void __user *)((unsigned long)(base) + compat__vdso_##name##_offset)
 
+extern char compat_vdso_start[], compat_vdso_end[];
+
 #endif /* CONFIG_COMPAT */
 
+extern char vdso_start[], vdso_end[];
+
 #endif /* !__ASSEMBLY__ */
 
 #endif /* CONFIG_MMU */

arch/riscv/include/asm/vdso/processor.h

@@ -10,7 +10,7 @@
 
 static inline void cpu_relax(void)
 {
-	if (!static_branch_likely(&riscv_isa_ext_keys[RISCV_ISA_EXT_KEY_ZIHINTPAUSE])) {
+	if (!riscv_has_extension_likely(RISCV_ISA_EXT_ZIHINTPAUSE)) {
 #ifdef __riscv_muldiv
 		int dummy;
 		/* In lieu of a halt instruction, induce a long-latency stall. */