dfb09f9b7a
This patch provides performance tuning for the "Bulldozer" CPU. With its shared instruction cache there is a chance of generating an excessive number of cache cross-invalidates when running specific workloads on the cores of a compute module. This excessive amount of cross-invalidations can be observed if cache lines backed by shared physical memory alias in bits [14:12] of their virtual addresses, as those bits are used for the index generation. This patch addresses the issue by clearing all the bits in the [14:12] slice of the file mapping's virtual address at generation time, thus forcing those bits the same for all mappings of a single shared library across processes and, in doing so, avoids instruction cache aliases. It also adds the command line option "align_va_addr=(32|64|on|off)" with which virtual address alignment can be enabled for 32-bit or 64-bit x86 individually, or both, or be completely disabled. This change leaves virtual region address allocation on other families and/or vendors unaffected. Signed-off-by: Borislav Petkov <borislav.petkov@amd.com> Link: http://lkml.kernel.org/r/1312550110-24160-2-git-send-email-bp@amd64.org Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
126 lines
2.9 KiB
C
126 lines
2.9 KiB
C
/*
|
|
* Set up the VMAs to tell the VM about the vDSO.
|
|
* Copyright 2007 Andi Kleen, SUSE Labs.
|
|
* Subject to the GPL, v.2
|
|
*/
|
|
#include <linux/mm.h>
|
|
#include <linux/err.h>
|
|
#include <linux/sched.h>
|
|
#include <linux/slab.h>
|
|
#include <linux/init.h>
|
|
#include <linux/random.h>
|
|
#include <linux/elf.h>
|
|
#include <asm/vsyscall.h>
|
|
#include <asm/vgtod.h>
|
|
#include <asm/proto.h>
|
|
#include <asm/vdso.h>
|
|
|
|
unsigned int __read_mostly vdso_enabled = 1;
|
|
|
|
extern char vdso_start[], vdso_end[];
|
|
extern unsigned short vdso_sync_cpuid;
|
|
|
|
static struct page **vdso_pages;
|
|
static unsigned vdso_size;
|
|
|
|
static int __init init_vdso_vars(void)
|
|
{
|
|
int npages = (vdso_end - vdso_start + PAGE_SIZE - 1) / PAGE_SIZE;
|
|
int i;
|
|
|
|
vdso_size = npages << PAGE_SHIFT;
|
|
vdso_pages = kmalloc(sizeof(struct page *) * npages, GFP_KERNEL);
|
|
if (!vdso_pages)
|
|
goto oom;
|
|
for (i = 0; i < npages; i++) {
|
|
struct page *p;
|
|
p = alloc_page(GFP_KERNEL);
|
|
if (!p)
|
|
goto oom;
|
|
vdso_pages[i] = p;
|
|
copy_page(page_address(p), vdso_start + i*PAGE_SIZE);
|
|
}
|
|
|
|
return 0;
|
|
|
|
oom:
|
|
printk("Cannot allocate vdso\n");
|
|
vdso_enabled = 0;
|
|
return -ENOMEM;
|
|
}
|
|
subsys_initcall(init_vdso_vars);
|
|
|
|
struct linux_binprm;
|
|
|
|
/* Put the vdso above the (randomized) stack with another randomized offset.
|
|
This way there is no hole in the middle of address space.
|
|
To save memory make sure it is still in the same PTE as the stack top.
|
|
This doesn't give that many random bits */
|
|
static unsigned long vdso_addr(unsigned long start, unsigned len)
|
|
{
|
|
unsigned long addr, end;
|
|
unsigned offset;
|
|
end = (start + PMD_SIZE - 1) & PMD_MASK;
|
|
if (end >= TASK_SIZE_MAX)
|
|
end = TASK_SIZE_MAX;
|
|
end -= len;
|
|
/* This loses some more bits than a modulo, but is cheaper */
|
|
offset = get_random_int() & (PTRS_PER_PTE - 1);
|
|
addr = start + (offset << PAGE_SHIFT);
|
|
if (addr >= end)
|
|
addr = end;
|
|
|
|
/*
|
|
* page-align it here so that get_unmapped_area doesn't
|
|
* align it wrongfully again to the next page. addr can come in 4K
|
|
* unaligned here as a result of stack start randomization.
|
|
*/
|
|
addr = PAGE_ALIGN(addr);
|
|
addr = align_addr(addr, NULL, ALIGN_VDSO);
|
|
|
|
return addr;
|
|
}
|
|
|
|
/* Setup a VMA at program startup for the vsyscall page.
|
|
Not called for compat tasks */
|
|
int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
|
|
{
|
|
struct mm_struct *mm = current->mm;
|
|
unsigned long addr;
|
|
int ret;
|
|
|
|
if (!vdso_enabled)
|
|
return 0;
|
|
|
|
down_write(&mm->mmap_sem);
|
|
addr = vdso_addr(mm->start_stack, vdso_size);
|
|
addr = get_unmapped_area(NULL, addr, vdso_size, 0, 0);
|
|
if (IS_ERR_VALUE(addr)) {
|
|
ret = addr;
|
|
goto up_fail;
|
|
}
|
|
|
|
current->mm->context.vdso = (void *)addr;
|
|
|
|
ret = install_special_mapping(mm, addr, vdso_size,
|
|
VM_READ|VM_EXEC|
|
|
VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC|
|
|
VM_ALWAYSDUMP,
|
|
vdso_pages);
|
|
if (ret) {
|
|
current->mm->context.vdso = NULL;
|
|
goto up_fail;
|
|
}
|
|
|
|
up_fail:
|
|
up_write(&mm->mmap_sem);
|
|
return ret;
|
|
}
|
|
|
|
static __init int vdso_setup(char *s)
|
|
{
|
|
vdso_enabled = simple_strtoul(s, NULL, 0);
|
|
return 0;
|
|
}
|
|
__setup("vdso=", vdso_setup);
|