vDSO for sparc

Following patch is based on work done by Nick Alcock on 64-bit vDSO for sparc
in Oracle linux. I have extended it to include support for 32-bit vDSO for sparc
on 64-bit kernel.

vDSO for sparc is based on the X86 implementation. This patch
provides vDSO support for both 64-bit and 32-bit programs on 64-bit kernel.
vDSO will be disabled on 32-bit linux kernel on sparc.

*) vclock_gettime.c contains all the vdso functions. Since data page is mapped
   before the vdso code page, the pointer to data page is got by subracting offset
   from an address in the vdso code page. The return address stored in
   %i7 is used for this purpose.
*) During compilation, both 32-bit and 64-bit vdso images are compiled and are
   converted into raw bytes by vdso2c program to be ready for mapping into the
   process. 32-bit images are compiled only if CONFIG_COMPAT is enabled. vdso2c
   generates two files vdso-image-64.c and vdso-image-32.c which contains the
   respective vDSO image in C structure.
*) During vdso initialization, required number of vdso pages are allocated and
   raw bytes are copied into the pages.
*) During every exec, these pages are mapped into the process through
   arch_setup_additional_pages and the location of mapping is passed on to the
   process through aux vector AT_SYSINFO_EHDR which is used by glibc.
*) A new update_vsyscall routine for sparc is added to keep the data page in
   vdso updated.
*) As vDSO cannot contain dynamically relocatable references, a new version of
   cpu_relax is added for the use of vDSO.

This change also requires a putback to glibc to use vDSO. For testing,
programs planning to try vDSO can be compiled against the generated
vdso(64/32).so in the source.

Testing:

========
[root@localhost ~]# cat vdso_test.c
int main() {
        struct timespec tv_start, tv_end;
        struct timeval tv_tmp;
	int i;
        int count = 1 * 1000 * 10000;
	long long diff;

        clock_gettime(0, &tv_start);
        for (i = 0; i < count; i++)
              gettimeofday(&tv_tmp, NULL);
        clock_gettime(0, &tv_end);
        diff = (long long)(tv_end.tv_sec -
		tv_start.tv_sec)*(1*1000*1000*1000);
        diff += (tv_end.tv_nsec - tv_start.tv_nsec);
	printf("Start sec: %d\n", tv_start.tv_sec);
	printf("End sec  : %d\n", tv_end.tv_sec);
        printf("%d cycles in %lld ns = %f ns/cycle\n", count, diff,
		(double)diff / (double)count);
        return 0;
}

[root@localhost ~]# cc vdso_test.c -o t32_without_fix -m32 -lrt
[root@localhost ~]# ./t32_without_fix
Start sec: 1502396130
End sec  : 1502396140
10000000 cycles in 9565148528 ns = 956.514853 ns/cycle
[root@localhost ~]# cc vdso_test.c -o t32_with_fix -m32 ./vdso32.so.dbg
[root@localhost ~]# ./t32_with_fix
Start sec: 1502396168
End sec  : 1502396169
10000000 cycles in 798141262 ns = 79.814126 ns/cycle
[root@localhost ~]# cc vdso_test.c -o t64_without_fix -m64 -lrt
[root@localhost ~]# ./t64_without_fix
Start sec: 1502396208
End sec  : 1502396218
10000000 cycles in 9846091800 ns = 984.609180 ns/cycle
[root@localhost ~]# cc vdso_test.c -o t64_with_fix -m64 ./vdso64.so.dbg
[root@localhost ~]# ./t64_with_fix
Start sec: 1502396257
End sec  : 1502396257
10000000 cycles in 380984048 ns = 38.098405 ns/cycle

V1 to V2 Changes:
=================
	Added hot patching code to switch the read stick instruction to read
tick instruction based on the hardware.

V2 to V3 Changes:
=================
	Merged latest changes from sparc-next and moved the initialization
of clocksource_tick.archdata.vclock_mode to time_init_early. Disabled
queued spinlock and rwlock configuration when simulating 32-bit config
to compile 32-bit VDSO.

V3 to V4 Changes:
=================
	Hardcoded the page size as 8192 in linker script for both 64-bit and
32-bit binaries. Removed unused variables in vdso2c.h. Added -mv8plus flag to
Makefile to prevent the generation of relocation entries for __lshrdi3 in 32-bit
vdso binary.

Signed-off-by: Nick Alcock <nick.alcock@oracle.com>
Signed-off-by: Nagarathnam Muthusamy <nagarathnam.muthusamy@oracle.com>
Reviewed-by: Shannon Nelson <shannon.nelson@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 268 insertions, 0 deletions

diff --git a/arch/sparc/vdso/vma.c b/arch/sparc/vdso/vma.c
new file mode 100644
index 000000000000..0a6f50098e23
--- /dev/null
+++ b/arch/sparc/vdso/vma.c
@@ -0,0 +1,268 @@
+/*
+ * Set up the VMAs to tell the VM about the vDSO.
+ * Copyright 2007 Andi Kleen, SUSE Labs.
+ * Subject to the GPL, v.2
+ */
+
+/*
+ * Copyright (c) 2017 Oracle and/or its affiliates. All rights reserved.
+ */
+
+#include <linux/mm.h>
+#include <linux/err.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/init.h>
+#include <linux/linkage.h>
+#include <linux/random.h>
+#include <linux/elf.h>
+#include <asm/vdso.h>
+#include <asm/vvar.h>
+#include <asm/page.h>
+
+unsigned int __read_mostly vdso_enabled = 1;
+
+static struct vm_special_mapping vvar_mapping = {
+	.name = "[vvar]"
+};
+
+#ifdef	CONFIG_SPARC64
+static struct vm_special_mapping vdso_mapping64 = {
+	.name = "[vdso]"
+};
+#endif
+
+#ifdef CONFIG_COMPAT
+static struct vm_special_mapping vdso_mapping32 = {
+	.name = "[vdso]"
+};
+#endif
+
+struct vvar_data *vvar_data;
+
+#define	SAVE_INSTR_SIZE	4
+
+/*
+ * Allocate pages for the vdso and vvar, and copy in the vdso text from the
+ * kernel image.
+ */
+int __init init_vdso_image(const struct vdso_image *image,
+		struct vm_special_mapping *vdso_mapping)
+{
+	int i;
+	struct page *dp, **dpp = NULL;
+	int dnpages = 0;
+	struct page *cp, **cpp = NULL;
+	int cnpages = (image->size) / PAGE_SIZE;
+
+	/*
+	 * First, the vdso text.  This is initialied data, an integral number of
+	 * pages long.
+	 */
+	if (WARN_ON(image->size % PAGE_SIZE != 0))
+		goto oom;
+
+	cpp = kcalloc(cnpages, sizeof(struct page *), GFP_KERNEL);
+	vdso_mapping->pages = cpp;
+
+	if (!cpp)
+		goto oom;
+
+	if (vdso_fix_stick) {
+		/*
+		 * If the system uses %tick instead of %stick, patch the VDSO
+		 * with instruction reading %tick instead of %stick.
+		 */
+		unsigned int j, k = SAVE_INSTR_SIZE;
+		unsigned char *data = image->data;
+
+		for (j = image->sym_vread_tick_patch_start;
+		     j < image->sym_vread_tick_patch_end; j++) {
+
+			data[image->sym_vread_tick + k] = data[j];
+			k++;
+		}
+	}
+
+	for (i = 0; i < cnpages; i++) {
+		cp = alloc_page(GFP_KERNEL);
+		if (!cp)
+			goto oom;
+		cpp[i] = cp;
+		copy_page(page_address(cp), image->data + i * PAGE_SIZE);
+	}
+
+	/*
+	 * Now the vvar page.  This is uninitialized data.
+	 */
+
+	if (vvar_data == NULL) {
+		dnpages = (sizeof(struct vvar_data) / PAGE_SIZE) + 1;
+		if (WARN_ON(dnpages != 1))
+			goto oom;
+		dpp = kcalloc(dnpages, sizeof(struct page *), GFP_KERNEL);
+		vvar_mapping.pages = dpp;
+
+		if (!dpp)
+			goto oom;
+
+		dp = alloc_page(GFP_KERNEL);
+		if (!dp)
+			goto oom;
+
+		dpp[0] = dp;
+		vvar_data = page_address(dp);
+		memset(vvar_data, 0, PAGE_SIZE);
+
+		vvar_data->seq = 0;
+	}
+
+	return 0;
+ oom:
+	if (cpp != NULL) {
+		for (i = 0; i < cnpages; i++) {
+			if (cpp[i] != NULL)
+				__free_page(cpp[i]);
+		}
+		kfree(cpp);
+		vdso_mapping->pages = NULL;
+	}
+
+	if (dpp != NULL) {
+		for (i = 0; i < dnpages; i++) {
+			if (dpp[i] != NULL)
+				__free_page(dpp[i]);
+		}
+		kfree(dpp);
+		vvar_mapping.pages = NULL;
+	}
+
+	pr_warn("Cannot allocate vdso\n");
+	vdso_enabled = 0;
+	return -ENOMEM;
+}
+
+static int __init init_vdso(void)
+{
+	int err = 0;
+#ifdef CONFIG_SPARC64
+	err = init_vdso_image(&vdso_image_64_builtin, &vdso_mapping64);
+	if (err)
+		return err;
+#endif
+
+#ifdef CONFIG_COMPAT
+	err = init_vdso_image(&vdso_image_32_builtin, &vdso_mapping32);
+#endif
+	return err;
+
+}
+subsys_initcall(init_vdso);
+
+struct linux_binprm;
+
+/* Shuffle the vdso up a bit, randomly. */
+static unsigned long vdso_addr(unsigned long start, unsigned int len)
+{
+	unsigned int offset;
+
+	/* This loses some more bits than a modulo, but is cheaper */
+	offset = get_random_int() & (PTRS_PER_PTE - 1);
+	return start + (offset << PAGE_SHIFT);
+}
+
+static int map_vdso(const struct vdso_image *image,
+		struct vm_special_mapping *vdso_mapping)
+{
+	struct mm_struct *mm = current->mm;
+	struct vm_area_struct *vma;
+	unsigned long text_start, addr = 0;
+	int ret = 0;
+
+	down_write(&mm->mmap_sem);
+
+	/*
+	 * First, get an unmapped region: then randomize it, and make sure that
+	 * region is free.
+	 */
+	if (current->flags & PF_RANDOMIZE) {
+		addr = get_unmapped_area(NULL, 0,
+					 image->size - image->sym_vvar_start,
+					 0, 0);
+		if (IS_ERR_VALUE(addr)) {
+			ret = addr;
+			goto up_fail;
+		}
+		addr = vdso_addr(addr, image->size - image->sym_vvar_start);
+	}
+	addr = get_unmapped_area(NULL, addr,
+				 image->size - image->sym_vvar_start, 0, 0);
+	if (IS_ERR_VALUE(addr)) {
+		ret = addr;
+		goto up_fail;
+	}
+
+	text_start = addr - image->sym_vvar_start;
+	current->mm->context.vdso = (void __user *)text_start;
+
+	/*
+	 * MAYWRITE to allow gdb to COW and set breakpoints
+	 */
+	vma = _install_special_mapping(mm,
+				       text_start,
+				       image->size,
+				       VM_READ|VM_EXEC|
+				       VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC,
+				       vdso_mapping);
+
+	if (IS_ERR(vma)) {
+		ret = PTR_ERR(vma);
+		goto up_fail;
+	}
+
+	vma = _install_special_mapping(mm,
+				       addr,
+				       -image->sym_vvar_start,
+				       VM_READ|VM_MAYREAD,
+				       &vvar_mapping);
+
+	if (IS_ERR(vma)) {
+		ret = PTR_ERR(vma);
+		do_munmap(mm, text_start, image->size, NULL);
+	}
+
+up_fail:
+	if (ret)
+		current->mm->context.vdso = NULL;
+
+	up_write(&mm->mmap_sem);
+	return ret;
+}
+
+int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
+{
+
+	if (!vdso_enabled)
+		return 0;
+
+#if defined CONFIG_COMPAT
+	if (!(is_32bit_task()))
+		return map_vdso(&vdso_image_64_builtin, &vdso_mapping64);
+	else
+		return map_vdso(&vdso_image_32_builtin, &vdso_mapping32);
+#else
+		return map_vdso(&vdso_image_64_builtin, &vdso_mapping64);
+#endif
+
+}
+
+static __init int vdso_setup(char *s)
+{
+	int err;
+	unsigned long val;
+
+	err = kstrtoul(s, 10, &val);
+	vdso_enabled = val;
+	return err;
+}
+__setup("vdso=", vdso_setup);