Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.34 as permitted sender) client-ip=23.128.96.34;
Date:   Tue, 5 Dec 2023 19:01:34 +0300
From:   Alexey Dobriyan <adobriyan@gmail.com>
To:     Andrew Morton <akpm@linux-foundation.org>
Cc:     Florian Weimer <fweimer@redhat.com>, linux-kernel@vger.kernel.org,
        linux-arch@vger.kernel.org, linux-api@vger.kernel.org,
        x86@kernel.org
Subject: [PATCH v2] ELF: supply userspace with available page shifts
 (AT_PAGE_SHIFT_MASK)
Message-ID: <1d679805-8a82-44a4-ba14-49d4f28ff597@p183>
References: <6b399b86-a478-48b0-92a1-25240a8ede54@p183>
 <87v89dvuxg.fsf@oldenburg.str.redhat.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=utf-8
Content-Disposition: inline
In-Reply-To: <87v89dvuxg.fsf@oldenburg.str.redhat.com>
Precedence: bulk

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

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:

	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  00 10 20 40 00 00 00 00

x86_64 machine with 2 MiB pages only:

	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  00 10 20 00 00 00 00 00

AT_PAGESZ is always 4096 which is not that interesting.

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

	v2: switch to 1 bit per page shift (bitmask)

 arch/x86/include/asm/elf.h  |   12 ++++++++++++
 fs/binfmt_elf.c             |    3 +++
 include/uapi/linux/auxvec.h |   14 ++++++++++++++
 3 files changed, 29 insertions(+)

--- a/arch/x86/include/asm/elf.h
+++ b/arch/x86/include/asm/elf.h
@@ -358,6 +358,18 @@ else if (IS_ENABLED(CONFIG_IA32_EMULATION))				\
 
 #define COMPAT_ELF_ET_DYN_BASE	(TASK_UNMAPPED_BASE + 0x1000000)
 
+#define ARCH_AT_PAGE_SHIFT_MASK					\
+	do {							\
+		u32 val = 1 << 12;				\
+		if (boot_cpu_has(X86_FEATURE_PSE)) {		\
+			val |= 1 << 21;				\
+		}						\
+		if (boot_cpu_has(X86_FEATURE_GBPAGES)) {	\
+			val |= 1 << 30;				\
+		}						\
+		NEW_AUX_ENT(AT_PAGE_SHIFT_MASK, 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_MASK
+	ARCH_AT_PAGE_SHIFT_MASK;
+#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 +33,20 @@
 #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 bitmask.
+ *
+ * Example: x86_64 system with pse, pdpe1gb /proc/cpuinfo flags 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  00 10 20 40 00 00 00 00
+ *
+ * For 2^64 hugepage support please contact your Universe sales representative.
+ */
+#define AT_PAGE_SHIFT_MASK	29
+
 #define AT_EXECFN  31	/* filename of program */
 
 #ifndef AT_MINSIGSTKSZ