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>

6 files changed, 68 insertions, 103 deletions

diff --git a/arch/riscv/kernel/alternative.c b/arch/riscv/kernel/alternative.c
index 3d4f1f32c7f6..fc341b69bf62 100644
--- a/arch/riscv/kernel/alternative.c
+++ b/arch/riscv/kernel/alternative.c
@@ -11,7 +11,9 @@
 #include <linux/cpu.h>
 #include <linux/uaccess.h>
 #include <asm/alternative.h>
+#include <asm/module.h>
 #include <asm/sections.h>
+#include <asm/vdso.h>
 #include <asm/vendorid_list.h>
 #include <asm/sbi.h>
 #include <asm/csr.h>
@@ -160,6 +162,31 @@ static void __init_or_module _apply_alternatives(struct alt_entry *begin,
 				stage);
 }
 
+#ifdef CONFIG_MMU
+static void __init apply_vdso_alternatives(void)
+{
+	const Elf_Ehdr *hdr;
+	const Elf_Shdr *shdr;
+	const Elf_Shdr *alt;
+	struct alt_entry *begin, *end;
+
+	hdr = (Elf_Ehdr *)vdso_start;
+	shdr = (void *)hdr + hdr->e_shoff;
+	alt = find_section(hdr, shdr, ".alternative");
+	if (!alt)
+		return;
+
+	begin = (void *)hdr + alt->sh_offset,
+	end = (void *)hdr + alt->sh_offset + alt->sh_size,
+
+	_apply_alternatives((struct alt_entry *)begin,
+			    (struct alt_entry *)end,
+			    RISCV_ALTERNATIVES_BOOT);
+}
+#else
+static void __init apply_vdso_alternatives(void) { }
+#endif
+
 void __init apply_boot_alternatives(void)
 {
 	/* If called on non-boot cpu things could go wrong */
@@ -168,6 +195,8 @@ void __init apply_boot_alternatives(void)
 	_apply_alternatives((struct alt_entry *)__alt_start,
 			    (struct alt_entry *)__alt_end,
 			    RISCV_ALTERNATIVES_BOOT);
+
+	apply_vdso_alternatives();
 }
 
 /*
diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c
index 9899806cef29..21fb567e1b22 100644
--- a/arch/riscv/kernel/cpufeature.c
+++ b/arch/riscv/kernel/cpufeature.c
@@ -29,9 +29,6 @@ unsigned long elf_hwcap __read_mostly;
 /* Host ISA bitmap */
 static DECLARE_BITMAP(riscv_isa, RISCV_ISA_EXT_MAX) __read_mostly;
 
-DEFINE_STATIC_KEY_ARRAY_FALSE(riscv_isa_ext_keys, RISCV_ISA_EXT_KEY_MAX);
-EXPORT_SYMBOL(riscv_isa_ext_keys);
-
 /**
  * riscv_isa_extension_base() - Get base extension word
  *
@@ -268,102 +265,35 @@ void __init riscv_fill_hwcap(void)
 		if (elf_hwcap & BIT_MASK(i))
 			print_str[j++] = (char)('a' + i);
 	pr_info("riscv: ELF capabilities %s\n", print_str);
-
-	for_each_set_bit(i, riscv_isa, RISCV_ISA_EXT_MAX) {
-		j = riscv_isa_ext2key(i);
-		if (j >= 0)
-			static_branch_enable(&riscv_isa_ext_keys[j]);
-	}
 }
 
 #ifdef CONFIG_RISCV_ALTERNATIVE
-static bool __init_or_module cpufeature_probe_svpbmt(unsigned int stage)
-{
-	if (!IS_ENABLED(CONFIG_RISCV_ISA_SVPBMT))
-		return false;
-
-	if (stage == RISCV_ALTERNATIVES_EARLY_BOOT)
-		return false;
-
-	return riscv_isa_extension_available(NULL, SVPBMT);
-}
-
-static bool __init_or_module cpufeature_probe_zicbom(unsigned int stage)
-{
-	if (!IS_ENABLED(CONFIG_RISCV_ISA_ZICBOM))
-		return false;
-
-	if (stage == RISCV_ALTERNATIVES_EARLY_BOOT)
-		return false;
-
-	if (!riscv_isa_extension_available(NULL, ZICBOM))
-		return false;
-
-	riscv_noncoherent_supported();
-	return true;
-}
-
-static bool __init_or_module cpufeature_probe_zbb(unsigned int stage)
-{
-	if (!IS_ENABLED(CONFIG_RISCV_ISA_ZBB))
-		return false;
-
-	if (stage == RISCV_ALTERNATIVES_EARLY_BOOT)
-		return false;
-
-	if (!riscv_isa_extension_available(NULL, ZBB))
-		return false;
-
-	return true;
-}
-
-/*
- * Probe presence of individual extensions.
- *
- * This code may also be executed before kernel relocation, so we cannot use
- * addresses generated by the address-of operator as they won't be valid in
- * this context.
- * Tests, unless otherwise required, are to be added in alphabetical order.
- */
-static u32 __init_or_module cpufeature_probe(unsigned int stage)
-{
-	u32 cpu_req_feature = 0;
-
-	if (cpufeature_probe_svpbmt(stage))
-		cpu_req_feature |= BIT(CPUFEATURE_SVPBMT);
-
-	if (cpufeature_probe_zicbom(stage))
-		cpu_req_feature |= BIT(CPUFEATURE_ZICBOM);
-
-	if (cpufeature_probe_zbb(stage))
-		cpu_req_feature |= BIT(CPUFEATURE_ZBB);
-
-	return cpu_req_feature;
-}
-
 void __init_or_module riscv_cpufeature_patch_func(struct alt_entry *begin,
 						  struct alt_entry *end,
 						  unsigned int stage)
 {
-	u32 cpu_req_feature = cpufeature_probe(stage);
 	struct alt_entry *alt;
-	u32 tmp;
+	void *oldptr, *altptr;
+
+	if (stage == RISCV_ALTERNATIVES_EARLY_BOOT)
+		return;
 
 	for (alt = begin; alt < end; alt++) {
 		if (alt->vendor_id != 0)
 			continue;
-		if (alt->errata_id >= CPUFEATURE_NUMBER) {
-			WARN(1, "This feature id:%d is not in kernel cpufeature list",
+		if (alt->errata_id >= RISCV_ISA_EXT_MAX) {
+			WARN(1, "This extension id:%d is not in ISA extension list",
 				alt->errata_id);
 			continue;
 		}
 
-		tmp = (1U << alt->errata_id);
-		if (cpu_req_feature & tmp) {
-			patch_text_nosync(alt->old_ptr, alt->alt_ptr, alt->alt_len);
-			riscv_alternative_fix_offsets(alt->old_ptr, alt->alt_len,
-						      alt->old_ptr - alt->alt_ptr);
-		}
+		if (!__riscv_isa_extension_available(NULL, alt->errata_id))
+			continue;
+
+		oldptr = ALT_OLD_PTR(alt);
+		altptr = ALT_ALT_PTR(alt);
+		patch_text_nosync(oldptr, altptr, alt->alt_len);
+		riscv_alternative_fix_offsets(oldptr, alt->alt_len, oldptr - altptr);
 	}
 }
 #endif
diff --git a/arch/riscv/kernel/module.c b/arch/riscv/kernel/module.c
index 91fe16bfaa07..7c651d55fcbd 100644
--- a/arch/riscv/kernel/module.c
+++ b/arch/riscv/kernel/module.c
@@ -268,6 +268,13 @@ static int apply_r_riscv_align_rela(struct module *me, u32 *location,
 	return -EINVAL;
 }
 
+static int apply_r_riscv_add16_rela(struct module *me, u32 *location,
+				    Elf_Addr v)
+{
+	*(u16 *)location += (u16)v;
+	return 0;
+}
+
 static int apply_r_riscv_add32_rela(struct module *me, u32 *location,
 				    Elf_Addr v)
 {
@@ -282,6 +289,13 @@ static int apply_r_riscv_add64_rela(struct module *me, u32 *location,
 	return 0;
 }
 
+static int apply_r_riscv_sub16_rela(struct module *me, u32 *location,
+				    Elf_Addr v)
+{
+	*(u16 *)location -= (u16)v;
+	return 0;
+}
+
 static int apply_r_riscv_sub32_rela(struct module *me, u32 *location,
 				    Elf_Addr v)
 {
@@ -315,8 +329,10 @@ static int (*reloc_handlers_rela[]) (struct module *me, u32 *location,
 	[R_RISCV_CALL]			= apply_r_riscv_call_rela,
 	[R_RISCV_RELAX]			= apply_r_riscv_relax_rela,
 	[R_RISCV_ALIGN]			= apply_r_riscv_align_rela,
+	[R_RISCV_ADD16]			= apply_r_riscv_add16_rela,
 	[R_RISCV_ADD32]			= apply_r_riscv_add32_rela,
 	[R_RISCV_ADD64]			= apply_r_riscv_add64_rela,
+	[R_RISCV_SUB16]			= apply_r_riscv_sub16_rela,
 	[R_RISCV_SUB32]			= apply_r_riscv_sub32_rela,
 	[R_RISCV_SUB64]			= apply_r_riscv_sub64_rela,
 };
@@ -429,21 +445,6 @@ void *module_alloc(unsigned long size)
 }
 #endif
 
-static 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;
-}
-
 int module_finalize(const Elf_Ehdr *hdr,
 		    const Elf_Shdr *sechdrs,
 		    struct module *me)
diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c
index 86acd690d529..376d2827e736 100644
--- a/arch/riscv/kernel/setup.c
+++ b/arch/riscv/kernel/setup.c
@@ -300,6 +300,9 @@ void __init setup_arch(char **cmdline_p)
 	riscv_init_cbom_blocksize();
 	riscv_fill_hwcap();
 	apply_boot_alternatives();
+	if (IS_ENABLED(CONFIG_RISCV_ISA_ZICBOM) &&
+	    riscv_isa_extension_available(NULL, ZICBOM))
+		riscv_noncoherent_supported();
 }
 
 static int __init topology_init(void)
diff --git a/arch/riscv/kernel/vdso.c b/arch/riscv/kernel/vdso.c
index e410275918ac..4e631c098f4d 100644
--- a/arch/riscv/kernel/vdso.c
+++ b/arch/riscv/kernel/vdso.c
@@ -22,11 +22,6 @@ struct vdso_data {
 };
 #endif
 
-extern char vdso_start[], vdso_end[];
-#ifdef CONFIG_COMPAT
-extern char compat_vdso_start[], compat_vdso_end[];
-#endif
-
 enum vvar_pages {
 	VVAR_DATA_PAGE_OFFSET,
 	VVAR_TIMENS_PAGE_OFFSET,
diff --git a/arch/riscv/kernel/vdso/vdso.lds.S b/arch/riscv/kernel/vdso/vdso.lds.S
index 150b1a572e61..4a0606633290 100644
--- a/arch/riscv/kernel/vdso/vdso.lds.S
+++ b/arch/riscv/kernel/vdso/vdso.lds.S
@@ -40,6 +40,13 @@ SECTIONS
 	. = 0x800;
 	.text		: { *(.text .text.*) }		:text
 
+	. = ALIGN(4);
+	.alternative : {
+		__alt_start = .;
+		*(.alternative)
+		__alt_end = .;
+	}
+
 	.data		: {
 		*(.got.plt) *(.got)
 		*(.data .data.* .gnu.linkonce.d.*)