--- linux/arch/i386/mm/Makefile.orig +++ linux/arch/i386/mm/Makefile @@ -2,7 +2,7 @@ # Makefile for the linux i386-specific parts of the memory manager. # -obj-y := init.o pgtable.o fault.o ioremap.o extable.o pageattr.o +obj-y := init.o pgtable.o fault.o ioremap.o extable.o pageattr.o mmap.o obj-$(CONFIG_DISCONTIGMEM) += discontig.o obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o --- linux/arch/i386/mm/mmap.c.orig +++ linux/arch/i386/mm/mmap.c @@ -0,0 +1,70 @@ +/* + * linux/arch/i386/mm/mmap.c + * + * flexible mmap layout support + * + * Copyright 2003-2004 Red Hat Inc., Durham, North Carolina. + * All Rights Reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * + * + * Started by Ingo Molnar + */ + +#include +#include + +/* + * Top of mmap area (just below the process stack). + * + * Leave an at least ~128 MB hole. + */ +#define MIN_GAP (128*1024*1024) +#define MAX_GAP (TASK_SIZE/6*5) + +static inline unsigned long mmap_base(struct mm_struct *mm) +{ + unsigned long gap = current->rlim[RLIMIT_STACK].rlim_cur; + + if (gap < MIN_GAP) + gap = MIN_GAP; + else if (gap > MAX_GAP) + gap = MAX_GAP; + + return TASK_SIZE - (gap & PAGE_MASK); +} + +/* + * This function, called very early during the creation of a new + * process VM image, sets up which VM layout function to use: + */ +void arch_pick_mmap_layout(struct mm_struct *mm) +{ + /* + * Fall back to the standard layout if the personality + * bit is set: + */ + if (current->personality & ADDR_COMPAT_LAYOUT) { + mm->mmap_base = TASK_UNMAPPED_BASE; + mm->get_unmapped_area = arch_get_unmapped_area; + mm->unmap_area = arch_unmap_area; + } else { + mm->mmap_base = mmap_base(mm); + mm->get_unmapped_area = arch_get_unmapped_area_topdown; + mm->unmap_area = arch_unmap_area_topdown; + } +} + --- linux/fs/binfmt_aout.c.orig +++ linux/fs/binfmt_aout.c @@ -307,7 +307,7 @@ static int load_aout_binary(struct linux (current->mm->start_data = N_DATADDR(ex)); current->mm->brk = ex.a_bss + (current->mm->start_brk = N_BSSADDR(ex)); - current->mm->free_area_cache = TASK_UNMAPPED_BASE; + current->mm->free_area_cache = current->mm->mmap_base; current->mm->rss = 0; current->mm->mmap = NULL; --- linux/fs/binfmt_elf.c.orig +++ linux/fs/binfmt_elf.c @@ -702,7 +702,7 @@ static int load_elf_binary(struct linux_ /* Do this so that we can load the interpreter, if need be. We will change some of these later */ current->mm->rss = 0; - current->mm->free_area_cache = TASK_UNMAPPED_BASE; + current->mm->free_area_cache = current->mm->mmap_base; retval = setup_arg_pages(bprm, executable_stack); if (retval < 0) { send_sig(SIGKILL, current, 0); --- linux/fs/exec.c.orig +++ linux/fs/exec.c @@ -546,6 +546,7 @@ static int exec_mmap(struct mm_struct *m tsk->active_mm = mm; activate_mm(active_mm, mm); task_unlock(tsk); + arch_pick_mmap_layout(mm); if (old_mm) { if (active_mm != old_mm) BUG(); mmput(old_mm); --- linux/include/linux/sched.h.orig +++ linux/include/linux/sched.h @@ -189,10 +189,26 @@ extern int sysctl_max_map_count; #include +extern unsigned long +arch_get_unmapped_area(struct file *, unsigned long, unsigned long, + unsigned long, unsigned long); +extern unsigned long +arch_get_unmapped_area_topdown(struct file *filp, unsigned long addr, + unsigned long len, unsigned long pgoff, + unsigned long flags); +extern void arch_unmap_area(struct vm_area_struct *area); +extern void arch_unmap_area_topdown(struct vm_area_struct *area); + + struct mm_struct { struct vm_area_struct * mmap; /* list of VMAs */ struct rb_root mm_rb; struct vm_area_struct * mmap_cache; /* last find_vma result */ + unsigned long (*get_unmapped_area) (struct file *filp, + unsigned long addr, unsigned long len, + unsigned long pgoff, unsigned long flags); + void (*unmap_area) (struct vm_area_struct *area); + unsigned long mmap_base; /* base of mmap area */ unsigned long free_area_cache; /* first hole */ pgd_t * pgd; atomic_t mm_users; /* How many users with user space? */ @@ -1075,6 +1091,17 @@ static inline void set_task_cpu(struct t #endif /* CONFIG_SMP */ +#ifdef HAVE_ARCH_PICK_MMAP_LAYOUT +extern void arch_pick_mmap_layout(struct mm_struct *mm); +#else +static inline void arch_pick_mmap_layout(struct mm_struct *mm) +{ + mm->mmap_base = TASK_UNMAPPED_BASE; + mm->get_unmapped_area = arch_get_unmapped_area; + mm->unmap_area = arch_unmap_area; +} +#endif + #endif /* __KERNEL__ */ #endif --- linux/include/linux/personality.h.orig +++ linux/include/linux/personality.h @@ -30,6 +30,7 @@ extern int abi_fake_utsname; */ enum { MMAP_PAGE_ZERO = 0x0100000, + ADDR_COMPAT_LAYOUT = 0x0200000, ADDR_LIMIT_32BIT = 0x0800000, SHORT_INODE = 0x1000000, WHOLE_SECONDS = 0x2000000, --- linux/include/asm-i386/elf.h.orig +++ linux/include/asm-i386/elf.h @@ -117,7 +117,7 @@ typedef struct user_fxsr_struct elf_fpxr #define AT_SYSINFO_EHDR 33 #ifdef __KERNEL__ -#define SET_PERSONALITY(ex, ibcs2) set_personality((ibcs2)?PER_SVR4:PER_LINUX) +#define SET_PERSONALITY(ex, ibcs2) do { } while (0) extern int dump_task_regs (struct task_struct *, elf_gregset_t *); extern int dump_task_fpu (struct task_struct *, elf_fpregset_t *); --- linux/include/asm-i386/processor.h.orig +++ linux/include/asm-i386/processor.h @@ -296,6 +296,8 @@ extern unsigned int mca_pentium_flag; */ #define TASK_UNMAPPED_BASE (PAGE_ALIGN(TASK_SIZE / 3)) +#define HAVE_ARCH_PICK_MMAP_LAYOUT + /* * Size of io_bitmap. */ --- linux/kernel/fork.c.orig +++ linux/kernel/fork.c @@ -279,7 +279,7 @@ static inline int dup_mmap(struct mm_str mm->locked_vm = 0; mm->mmap = NULL; mm->mmap_cache = NULL; - mm->free_area_cache = TASK_UNMAPPED_BASE; + mm->free_area_cache = oldmm->mmap_base; mm->map_count = 0; mm->rss = 0; cpus_clear(mm->cpu_vm_mask); --- linux/mm/mmap.c.orig +++ linux/mm/mmap.c @@ -1014,7 +1014,7 @@ EXPORT_SYMBOL(do_mmap_pgoff); * This function "knows" that -ENOMEM has the bits set. */ #ifndef HAVE_ARCH_UNMAPPED_AREA -static inline unsigned long +unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) { @@ -1058,12 +1058,103 @@ full_search: addr = vma->vm_end; } } -#else -extern unsigned long -arch_get_unmapped_area(struct file *, unsigned long, unsigned long, - unsigned long, unsigned long); #endif +void arch_unmap_area(struct vm_area_struct *area) +{ + /* + * Is this a new hole at the lowest possible address? + */ + if (area->vm_start >= TASK_UNMAPPED_BASE && + area->vm_start < area->vm_mm->free_area_cache) + area->vm_mm->free_area_cache = area->vm_start; +} + +/* + * This mmap-allocator allocates new areas top-down from below the + * stack's low limit (the base): + */ +unsigned long +arch_get_unmapped_area_topdown(struct file *filp, unsigned long addr, + unsigned long len, unsigned long pgoff, + unsigned long flags) +{ + struct vm_area_struct *vma, *prev_vma; + struct mm_struct *mm = current->mm; + unsigned long base = mm->mmap_base; + int first_time = 1; + + /* requested length too big for entire address space */ + if (len > TASK_SIZE) + return -ENOMEM; + + /* dont allow allocations above current base */ + if (mm->free_area_cache > base) + mm->free_area_cache = base; + + /* requesting a specific address */ + if (addr) { + addr = PAGE_ALIGN(addr); + vma = find_vma(mm, addr); + if (TASK_SIZE - len >= addr && + (!vma || addr + len <= vma->vm_start)) + return addr; + } + + /* make sure it can fit in the remaining address space */ + if (mm->free_area_cache < len) + goto fail; + + /* either no address requested or cant fit in requested address hole */ +try_again: + addr = (mm->free_area_cache - len) & PAGE_MASK; + do { + /* + * Lookup failure means no vma is above this address, + * i.e. return with success: + */ + if (!(vma = find_vma_prev(mm, addr, &prev_vma))) + return addr; + + /* + * new region fits between prev_vma->vm_end and + * vma->vm_start, use it: + */ + if (addr+len <= vma->vm_start && + (!prev_vma || (addr >= prev_vma->vm_end))) + /* remember the address as a hint for next time */ + return (mm->free_area_cache = addr); + else + /* pull free_area_cache down to the first hole */ + if (mm->free_area_cache == vma->vm_end) + mm->free_area_cache = vma->vm_start; + + /* try just below the current vma->vm_start */ + addr = vma->vm_start-len; + } while (len <= vma->vm_start); + +fail: + /* + * if hint left us with no space for the requested + * mapping then try again: + */ + if (first_time) { + mm->free_area_cache = base; + first_time = 0; + goto try_again; + } + return -ENOMEM; +} + +void arch_unmap_area_topdown(struct vm_area_struct *area) +{ + /* + * Is this a new hole at the highest possible address? + */ + if (area->vm_end > area->vm_mm->free_area_cache) + area->vm_mm->free_area_cache = area->vm_end; +} + unsigned long get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) @@ -1098,7 +1189,7 @@ get_unmapped_area(struct file *file, uns return file->f_op->get_unmapped_area(file, addr, len, pgoff, flags); - return arch_get_unmapped_area(file, addr, len, pgoff, flags); + return current->mm->get_unmapped_area(file, addr, len, pgoff, flags); } EXPORT_SYMBOL(get_unmapped_area); @@ -1388,13 +1479,7 @@ static void unmap_vma(struct mm_struct * area->vm_mm->total_vm -= len >> PAGE_SHIFT; if (area->vm_flags & VM_LOCKED) area->vm_mm->locked_vm -= len >> PAGE_SHIFT; - /* - * Is this a new hole at the lowest possible address? - */ - if (area->vm_start >= TASK_UNMAPPED_BASE && - area->vm_start < area->vm_mm->free_area_cache) - area->vm_mm->free_area_cache = area->vm_start; - + area->vm_mm->unmap_area(area); remove_vm_struct(area); }