RISC-V Fixes for 5.15-rc5

* A pair of fixes (along with the necessary cleanup) to our VDSO, to
   avoid
 * A fix to checksyscalls to teach it about our rv32 UABI.
 * A fix to add clone3() to the rv32 UABI, which was pointed out by
   checksyscalls.
 * A fix to properly flush the icache on the local CPU in addition to the
   remote CPUs.
 -----BEGIN PGP SIGNATURE-----
 
 iQJHBAABCgAxFiEEKzw3R0RoQ7JKlDp6LhMZ81+7GIkFAmFgdiUTHHBhbG1lckBk
 YWJiZWx0LmNvbQAKCRAuExnzX7sYiUnPD/9xeQ/c8zL3/tAjfdHhKmoFMT7xU2sA
 mshFrYAUSPywaXU8AGH8zCOJnU1qc3IPxCfojhzgNm6mgVDRZB0z0yhvaInQ/pfT
 NoyzYVmhP72sxM2OdAwMyv5al6sR6g+Z3XGnBIa3e33XwMXGED/o70plKrR80f8H
 6ssKVVXsI3pDhUHwVAS7l7FptLNdreWI1RWJMYI+Idv6gKWqY/6l9B+njB7DeLuH
 0kptFXYDAJHeN5wGcStsMk8nLJ8MaUWFqyqYoxetR2Jr6gegPSPlsirz81XdTjtz
 YRdOXsgTF7gsZc/0impTYPXrfSPeYgjGpJYFyZbCducotQLcFgn9VoKSyOVzeoF6
 sd0kE9seo0wT7rbx/S8Hz0koRqi3ZyA7ieRmpNNxLcr5Se4QghI6DIP0MQkuvwlC
 1yJKAIiNormJ48svLyisJQO0FBiiS68fEBlBnnQAqU8dSJYVj7rq+bd+ufJ7HgqP
 k93Dx8bjPvXNUSSAYWwg4ILqvBJIXAhuXg1TNzfMm4ZXLwQYieHOTZmOXek9rovb
 4EyrbqXr1+q/Z4LudFhJBN8kpzNZYWeqO1Nm32IZg9OKTAGnV5zAjxbK8kFkfD4i
 UDvLlcKDbefAx16zOuIN+k85vZt8QIwKx9uD8lBSskbUCgU1ot15kxNH0H/3wkii
 RqFeFATLa5gjjQ==
 =+mKs
 -----END PGP SIGNATURE-----

Merge tag 'riscv-for-linus-5.15-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux

Pull RISC-V fixes from Palmer Dabbelt:

 - A pair of fixes (along with the necessory cleanup) to our VDSO, to
   avoid a locking during OOM and to prevent the text from overflowing
   into the data page

 - A fix to checksyscalls to teach it about our rv32 UABI

 - A fix to add clone3() to the rv32 UABI, which was pointed out by
   checksyscalls

 - A fix to properly flush the icache on the local CPU in addition to
   the remote CPUs

* tag 'riscv-for-linus-5.15-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux:
  checksyscalls: Unconditionally ignore fstat{,at}64
  riscv: Flush current cpu icache before other cpus
  RISC-V: Include clone3() on rv32
  riscv/vdso: make arch_setup_additional_pages wait for mmap_sem for write killable
  riscv/vdso: Move vdso data page up front
  riscv/vdso: Refactor asm/vdso.h

arch/riscv/include/asm/syscall.h

@@ -82,4 +82,5 @@ static inline int syscall_get_arch(struct task_struct *task)
 #endif
 }
 
+asmlinkage long sys_riscv_flush_icache(uintptr_t, uintptr_t, uintptr_t);
 #endif	/* _ASM_RISCV_SYSCALL_H */

arch/riscv/include/asm/vdso.h

@@ -16,18 +16,24 @@
 #ifdef CONFIG_MMU
 
 #include <linux/types.h>
-#include <generated/vdso-offsets.h>
+/*
+ * All systems with an MMU have a VDSO, but systems without an MMU don't
+ * support shared libraries and therefor don't have one.
+ */
+#ifdef CONFIG_MMU
 
-#ifndef CONFIG_GENERIC_TIME_VSYSCALL
+#define __VVAR_PAGES    1
-struct vdso_data {
+
-};
+#ifndef __ASSEMBLY__
-#endif
+#include <generated/vdso-offsets.h>
 
 #define VDSO_SYMBOL(base, name)							\
 	(void __user *)((unsigned long)(base) + __vdso_##name##_offset)
 
 #endif /* CONFIG_MMU */
 
-asmlinkage long sys_riscv_flush_icache(uintptr_t, uintptr_t, uintptr_t);
+#endif /* !__ASSEMBLY__ */
+
+#endif /* CONFIG_MMU */
 
 #endif /* _ASM_RISCV_VDSO_H */

arch/riscv/include/uapi/asm/unistd.h

@@ -18,9 +18,10 @@
 #ifdef __LP64__
 #define __ARCH_WANT_NEW_STAT
 #define __ARCH_WANT_SET_GET_RLIMIT
-#define __ARCH_WANT_SYS_CLONE3
 #endif /* __LP64__ */
 
+#define __ARCH_WANT_SYS_CLONE3
+
 #include <asm-generic/unistd.h>
 
 /*

arch/riscv/kernel/syscall_table.c

@@ -7,7 +7,6 @@
 #include <linux/linkage.h>
 #include <linux/syscalls.h>
 #include <asm-generic/syscalls.h>
-#include <asm/vdso.h>
 #include <asm/syscall.h>
 
 #undef __SYSCALL

arch/riscv/kernel/vdso.c

@@ -12,14 +12,24 @@
 #include <linux/binfmts.h>
 #include <linux/err.h>
 #include <asm/page.h>
+#include <asm/vdso.h>
+
 #ifdef CONFIG_GENERIC_TIME_VSYSCALL
 #include <vdso/datapage.h>
 #else
-#include <asm/vdso.h>
+struct vdso_data {
+};
 #endif
 
 extern char vdso_start[], vdso_end[];
 
+enum vvar_pages {
+	VVAR_DATA_PAGE_OFFSET,
+	VVAR_NR_PAGES,
+};
+
+#define VVAR_SIZE  (VVAR_NR_PAGES << PAGE_SHIFT)
+
 static unsigned int vdso_pages __ro_after_init;
 static struct page **vdso_pagelist __ro_after_init;
 
@@ -38,7 +48,7 @@ static int __init vdso_init(void)
 
 	vdso_pages = (vdso_end - vdso_start) >> PAGE_SHIFT;
 	vdso_pagelist =
-		kcalloc(vdso_pages + 1, sizeof(struct page *), GFP_KERNEL);
+		kcalloc(vdso_pages + VVAR_NR_PAGES, sizeof(struct page *), GFP_KERNEL);
 	if (unlikely(vdso_pagelist == NULL)) {
 		pr_err("vdso: pagelist allocation failed\n");
 		return -ENOMEM;
@@ -63,38 +73,41 @@ int arch_setup_additional_pages(struct linux_binprm *bprm,
 	unsigned long vdso_base, vdso_len;
 	int ret;
 
-	vdso_len = (vdso_pages + 1) << PAGE_SHIFT;
+	BUILD_BUG_ON(VVAR_NR_PAGES != __VVAR_PAGES);
+
+	vdso_len = (vdso_pages + VVAR_NR_PAGES) << PAGE_SHIFT;
+
+	if (mmap_write_lock_killable(mm))
+		return -EINTR;
 
-	mmap_write_lock(mm);
 	vdso_base = get_unmapped_area(NULL, 0, vdso_len, 0, 0);
 	if (IS_ERR_VALUE(vdso_base)) {
 		ret = vdso_base;
 		goto end;
 	}
 
+	mm->context.vdso = NULL;
+	ret = install_special_mapping(mm, vdso_base, VVAR_SIZE,
+		(VM_READ | VM_MAYREAD), &vdso_pagelist[vdso_pages]);
+	if (unlikely(ret))
+		goto end;
+
+	ret =
+	   install_special_mapping(mm, vdso_base + VVAR_SIZE,
+		vdso_pages << PAGE_SHIFT,
+		(VM_READ | VM_EXEC | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC),
+		vdso_pagelist);
+
+	if (unlikely(ret))
+		goto end;
+
 	/*
 	 * Put vDSO base into mm struct. We need to do this before calling
 	 * install_special_mapping or the perf counter mmap tracking code
 	 * will fail to recognise it as a vDSO (since arch_vma_name fails).
 	 */
-	mm->context.vdso = (void *)vdso_base;
+	mm->context.vdso = (void *)vdso_base + VVAR_SIZE;
 
-	ret =
-	   install_special_mapping(mm, vdso_base, vdso_pages << PAGE_SHIFT,
-		(VM_READ | VM_EXEC | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC),
-		vdso_pagelist);
-
-	if (unlikely(ret)) {
-		mm->context.vdso = NULL;
-		goto end;
-	}
-
-	vdso_base += (vdso_pages << PAGE_SHIFT);
-	ret = install_special_mapping(mm, vdso_base, PAGE_SIZE,
-		(VM_READ | VM_MAYREAD), &vdso_pagelist[vdso_pages]);
-
-	if (unlikely(ret))
-		mm->context.vdso = NULL;
 end:
 	mmap_write_unlock(mm);
 	return ret;
@@ -105,7 +118,7 @@ const char *arch_vma_name(struct vm_area_struct *vma)
 	if (vma->vm_mm && (vma->vm_start == (long)vma->vm_mm->context.vdso))
 		return "[vdso]";
 	if (vma->vm_mm && (vma->vm_start ==
-			   (long)vma->vm_mm->context.vdso + PAGE_SIZE))
+			   (long)vma->vm_mm->context.vdso - VVAR_SIZE))
 		return "[vdso_data]";
 	return NULL;
 }

arch/riscv/kernel/vdso/vdso.lds.S

@@ -3,12 +3,13 @@
  * Copyright (C) 2012 Regents of the University of California
  */
 #include <asm/page.h>
+#include <asm/vdso.h>
 
 OUTPUT_ARCH(riscv)
 
 SECTIONS
 {
-	PROVIDE(_vdso_data = . + PAGE_SIZE);
+	PROVIDE(_vdso_data = . - __VVAR_PAGES * PAGE_SIZE);
 	. = SIZEOF_HEADERS;
 
 	.hash		: { *(.hash) }			:text

arch/riscv/mm/cacheflush.c

@@ -16,6 +16,8 @@ static void ipi_remote_fence_i(void *info)
 
 void flush_icache_all(void)
 {
+	local_flush_icache_all();
+
 	if (IS_ENABLED(CONFIG_RISCV_SBI))
 		sbi_remote_fence_i(NULL);
 	else

scripts/checksyscalls.sh

@@ -82,10 +82,8 @@ cat << EOF
 #define __IGNORE_truncate64
 #define __IGNORE_stat64
 #define __IGNORE_lstat64
-#define __IGNORE_fstat64
 #define __IGNORE_fcntl64
 #define __IGNORE_fadvise64_64
-#define __IGNORE_fstatat64
 #define __IGNORE_fstatfs64
 #define __IGNORE_statfs64
 #define __IGNORE_llseek
@@ -253,6 +251,10 @@ cat << EOF
 #define __IGNORE_getpmsg
 #define __IGNORE_putpmsg
 #define __IGNORE_vserver
+
+/* 64-bit ports never needed these, and new 32-bit ports can use statx */
+#define __IGNORE_fstat64
+#define __IGNORE_fstatat64
 EOF
 }