Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.32 as permitted sender) client-ip=23.128.96.32;
Date:   Mon, 4 Dec 2023 20:18:48 +0300
From:   Alexey Dobriyan <adobriyan@gmail.com>
To:     akpm@linux-foundation.org
Cc:     linux-kernel@vger.kernel.org, linux-arch@vger.kernel.org,
        linux-api@vger.kernel.org, x86@kernel.org
Subject: [PATCH] ELF: supply userspace with available page shifts
 (AT_PAGE_SHIFT_LIST)
Message-ID: <6b399b86-a478-48b0-92a1-25240a8ede54@p183>
MIME-Version: 1.0
Content-Type: text/plain; charset=utf-8
Content-Disposition: inline
Precedence: bulk

Report available page shifts in arch independent manner, so that poor
userspace developers won't have to parse /proc/cpuinfo hunting for
arch-specific flag strings:

	unsigned long val = getauxval(AT_PAGE_SHIFT_LIST);
	while (val && (val & 255) != 30) {
		val >>= 8;
	}
	if (val) {
		page_size_1gib = true;
	} else {
		page_size_1gib = false;
	}

Note!

This is strictly for userspace, if some page size is shutdown due
to kernel command line option or CPU bug workaround, than is must not
be reported in aux vector!

x86_64 machine with 1 GiB pages:

	$ hexdump -C /proc/self/auxv
	00000030  06 00 00 00 00 00 00 00  00 10 00 00 00 00 00 00
	00000040  1d 00 00 00 00 00 00 00  0c 15 1e 00 00 00 00 00

x86_64 machine with 2MiB pages only:

	$ hexdump -C /proc/self/auxv
	00000030  06 00 00 00 00 00 00 00  00 10 00 00 00 00 00 00
	00000040  1d 00 00 00 00 00 00 00  0c 15 00 00 00 00 00 00

AT_PAGESZ is always 4096 which is not much information.

Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
---

 arch/x86/include/asm/elf.h  |   13 +++++++++++++
 fs/binfmt_elf.c             |    3 +++
 include/uapi/linux/auxvec.h |   17 +++++++++++++++++
 3 files changed, 33 insertions(+)

--- a/arch/x86/include/asm/elf.h
+++ b/arch/x86/include/asm/elf.h
@@ -358,6 +358,19 @@ else if (IS_ENABLED(CONFIG_IA32_EMULATION))				\
 
 #define COMPAT_ELF_ET_DYN_BASE	(TASK_UNMAPPED_BASE + 0x1000000)
 
+#define ARCH_AT_PAGE_SHIFT_LIST					\
+	do {							\
+		u32 val = 12;					\
+		int s = 0;					\
+		if (boot_cpu_has(X86_FEATURE_PSE)) {		\
+			val |= 21 << (s += 8);			\
+		}						\
+		if (boot_cpu_has(X86_FEATURE_GBPAGES)) {	\
+			val |= 30 << (s += 8);			\
+		}						\
+		NEW_AUX_ENT(AT_PAGE_SHIFT_LIST, val);		\
+	} while (0)
+
 #endif /* !CONFIG_X86_32 */
 
 #define VDSO_CURRENT_BASE	((unsigned long)current->mm->context.vdso)
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -240,6 +240,9 @@ create_elf_tables(struct linux_binprm *bprm, const struct elfhdr *exec,
 #endif
 	NEW_AUX_ENT(AT_HWCAP, ELF_HWCAP);
 	NEW_AUX_ENT(AT_PAGESZ, ELF_EXEC_PAGESIZE);
+#ifdef ARCH_AT_PAGE_SHIFT_LIST
+	ARCH_AT_PAGE_SHIFT_LIST;
+#endif
 	NEW_AUX_ENT(AT_CLKTCK, CLOCKS_PER_SEC);
 	NEW_AUX_ENT(AT_PHDR, phdr_addr);
 	NEW_AUX_ENT(AT_PHENT, sizeof(struct elf_phdr));
--- a/include/uapi/linux/auxvec.h
+++ b/include/uapi/linux/auxvec.h
@@ -33,6 +33,23 @@
 #define AT_RSEQ_FEATURE_SIZE	27	/* rseq supported feature size */
 #define AT_RSEQ_ALIGN		28	/* rseq allocation alignment */
 
+/*
+ * Page sizes available for mmap(2) encoded as 1 page shift per byte in
+ * increasing order.
+ *
+ * Thus 32-bit systems get 4 shifts, 64-bit systems get 8 shifts tops.
+ *
+ * Example:
+ * x86_64 system with "pdpe1gb" reports 4 KiB, 2 MiB and 1 GiB page support.
+ *
+ *	$ hexdump -C /proc/self/auxv
+ *	00000030  06 00 00 00 00 00 00 00  00 10 00 00 00 00 00 00
+ *	00000040  1d 00 00 00 00 00 00 00  0c 15 1e 00 00 00 00 00
+ *
+ * For 2^256 hugepage support please contact your Universe sales representative.
+ */
+#define AT_PAGE_SHIFT_LIST	29
+
 #define AT_EXECFN  31	/* filename of program */
 
 #ifndef AT_MINSIGSTKSZ