linux_dsm_epyc7002/arch/arm/mm/pgd.c

175 lines
3.7 KiB
C
Raw Normal View History

/*
* linux/arch/arm/mm/pgd.c
*
* Copyright (C) 1998-2005 Russell King
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*/
#include <linux/mm.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 15:04:11 +07:00
#include <linux/gfp.h>
#include <linux/highmem.h>
#include <linux/slab.h>
#include <asm/cp15.h>
#include <asm/pgalloc.h>
#include <asm/page.h>
#include <asm/tlbflush.h>
#include "mm.h"
#ifdef CONFIG_ARM_LPAE
#define __pgd_alloc() kmalloc(PTRS_PER_PGD * sizeof(pgd_t), GFP_KERNEL)
#define __pgd_free(pgd) kfree(pgd)
#else
#define __pgd_alloc() (pgd_t *)__get_free_pages(GFP_KERNEL | __GFP_REPEAT, 2)
#define __pgd_free(pgd) free_pages((unsigned long)pgd, 2)
#endif
/*
* need to get a 16k page for level 1
*/
pgd_t *pgd_alloc(struct mm_struct *mm)
{
pgd_t *new_pgd, *init_pgd;
pud_t *new_pud, *init_pud;
pmd_t *new_pmd, *init_pmd;
pte_t *new_pte, *init_pte;
new_pgd = __pgd_alloc();
if (!new_pgd)
goto no_pgd;
memset(new_pgd, 0, USER_PTRS_PER_PGD * sizeof(pgd_t));
/*
* Copy over the kernel and IO PGD entries
*/
init_pgd = pgd_offset_k(0);
memcpy(new_pgd + USER_PTRS_PER_PGD, init_pgd + USER_PTRS_PER_PGD,
(PTRS_PER_PGD - USER_PTRS_PER_PGD) * sizeof(pgd_t));
clean_dcache_area(new_pgd, PTRS_PER_PGD * sizeof(pgd_t));
#ifdef CONFIG_ARM_LPAE
/*
* Allocate PMD table for modules and pkmap mappings.
*/
new_pud = pud_alloc(mm, new_pgd + pgd_index(MODULES_VADDR),
MODULES_VADDR);
if (!new_pud)
goto no_pud;
new_pmd = pmd_alloc(mm, new_pud, 0);
if (!new_pmd)
goto no_pmd;
#endif
if (!vectors_high()) {
/*
* On ARM, first page must always be allocated since it
* contains the machine vectors. The vectors are always high
* with LPAE.
*/
new_pud = pud_alloc(mm, new_pgd, 0);
if (!new_pud)
goto no_pud;
new_pmd = pmd_alloc(mm, new_pud, 0);
if (!new_pmd)
goto no_pmd;
new_pte = pte_alloc_map(mm, new_pmd, 0);
if (!new_pte)
goto no_pte;
#ifndef CONFIG_ARM_LPAE
/*
* Modify the PTE pointer to have the correct domain. This
* needs to be the vectors domain to avoid the low vectors
* being unmapped.
*/
pmd_val(*new_pmd) &= ~PMD_DOMAIN_MASK;
pmd_val(*new_pmd) |= PMD_DOMAIN(DOMAIN_VECTORS);
#endif
init_pud = pud_offset(init_pgd, 0);
init_pmd = pmd_offset(init_pud, 0);
init_pte = pte_offset_map(init_pmd, 0);
set_pte_ext(new_pte + 0, init_pte[0], 0);
set_pte_ext(new_pte + 1, init_pte[1], 0);
pte_unmap(init_pte);
pte_unmap(new_pte);
}
return new_pgd;
no_pte:
pmd_free(mm, new_pmd);
mm: fix false-positive warning on exit due mm_nr_pmds(mm) The problem is that we check nr_ptes/nr_pmds in exit_mmap() which happens *before* pgd_free(). And if an arch does pte/pmd allocation in pgd_alloc() and frees them in pgd_free() we see offset in counters by the time of the checks. We tried to workaround this by offsetting expected counter value according to FIRST_USER_ADDRESS for both nr_pte and nr_pmd in exit_mmap(). But it doesn't work in some cases: 1. ARM with LPAE enabled also has non-zero USER_PGTABLES_CEILING, but upper addresses occupied with huge pmd entries, so the trick with offsetting expected counter value will get really ugly: we will have to apply it nr_pmds, but not nr_ptes. 2. Metag has non-zero FIRST_USER_ADDRESS, but doesn't do allocation pte/pmd page tables allocation in pgd_alloc(), just setup a pgd entry which is allocated at boot and shared accross all processes. The proposal is to move the check to check_mm() which happens *after* pgd_free() and do proper accounting during pgd_alloc() and pgd_free() which would bring counters to zero if nothing leaked. Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Reported-by: Tyler Baker <tyler.baker@linaro.org> Tested-by: Tyler Baker <tyler.baker@linaro.org> Tested-by: Nishanth Menon <nm@ti.com> Cc: Russell King <linux@arm.linux.org.uk> Cc: James Hogan <james.hogan@imgtec.com> Cc: Guan Xuetao <gxt@mprc.pku.edu.cn> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-02-12 06:26:53 +07:00
mm_dec_nr_pmds(mm);
no_pmd:
pud_free(mm, new_pud);
no_pud:
__pgd_free(new_pgd);
no_pgd:
return NULL;
}
void pgd_free(struct mm_struct *mm, pgd_t *pgd_base)
{
pgd_t *pgd;
pud_t *pud;
pmd_t *pmd;
pgtable_t pte;
if (!pgd_base)
return;
pgd = pgd_base + pgd_index(0);
if (pgd_none_or_clear_bad(pgd))
goto no_pgd;
pud = pud_offset(pgd, 0);
if (pud_none_or_clear_bad(pud))
goto no_pud;
pmd = pmd_offset(pud, 0);
if (pmd_none_or_clear_bad(pmd))
goto no_pmd;
pte = pmd_pgtable(*pmd);
pmd_clear(pmd);
pte_free(mm, pte);
mm: fix false-positive warning on exit due mm_nr_pmds(mm) The problem is that we check nr_ptes/nr_pmds in exit_mmap() which happens *before* pgd_free(). And if an arch does pte/pmd allocation in pgd_alloc() and frees them in pgd_free() we see offset in counters by the time of the checks. We tried to workaround this by offsetting expected counter value according to FIRST_USER_ADDRESS for both nr_pte and nr_pmd in exit_mmap(). But it doesn't work in some cases: 1. ARM with LPAE enabled also has non-zero USER_PGTABLES_CEILING, but upper addresses occupied with huge pmd entries, so the trick with offsetting expected counter value will get really ugly: we will have to apply it nr_pmds, but not nr_ptes. 2. Metag has non-zero FIRST_USER_ADDRESS, but doesn't do allocation pte/pmd page tables allocation in pgd_alloc(), just setup a pgd entry which is allocated at boot and shared accross all processes. The proposal is to move the check to check_mm() which happens *after* pgd_free() and do proper accounting during pgd_alloc() and pgd_free() which would bring counters to zero if nothing leaked. Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Reported-by: Tyler Baker <tyler.baker@linaro.org> Tested-by: Tyler Baker <tyler.baker@linaro.org> Tested-by: Nishanth Menon <nm@ti.com> Cc: Russell King <linux@arm.linux.org.uk> Cc: James Hogan <james.hogan@imgtec.com> Cc: Guan Xuetao <gxt@mprc.pku.edu.cn> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-02-12 06:26:53 +07:00
atomic_long_dec(&mm->nr_ptes);
no_pmd:
pud_clear(pud);
pmd_free(mm, pmd);
mm: fix false-positive warning on exit due mm_nr_pmds(mm) The problem is that we check nr_ptes/nr_pmds in exit_mmap() which happens *before* pgd_free(). And if an arch does pte/pmd allocation in pgd_alloc() and frees them in pgd_free() we see offset in counters by the time of the checks. We tried to workaround this by offsetting expected counter value according to FIRST_USER_ADDRESS for both nr_pte and nr_pmd in exit_mmap(). But it doesn't work in some cases: 1. ARM with LPAE enabled also has non-zero USER_PGTABLES_CEILING, but upper addresses occupied with huge pmd entries, so the trick with offsetting expected counter value will get really ugly: we will have to apply it nr_pmds, but not nr_ptes. 2. Metag has non-zero FIRST_USER_ADDRESS, but doesn't do allocation pte/pmd page tables allocation in pgd_alloc(), just setup a pgd entry which is allocated at boot and shared accross all processes. The proposal is to move the check to check_mm() which happens *after* pgd_free() and do proper accounting during pgd_alloc() and pgd_free() which would bring counters to zero if nothing leaked. Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Reported-by: Tyler Baker <tyler.baker@linaro.org> Tested-by: Tyler Baker <tyler.baker@linaro.org> Tested-by: Nishanth Menon <nm@ti.com> Cc: Russell King <linux@arm.linux.org.uk> Cc: James Hogan <james.hogan@imgtec.com> Cc: Guan Xuetao <gxt@mprc.pku.edu.cn> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-02-12 06:26:53 +07:00
mm_dec_nr_pmds(mm);
no_pud:
pgd_clear(pgd);
pud_free(mm, pud);
no_pgd:
#ifdef CONFIG_ARM_LPAE
/*
* Free modules/pkmap or identity pmd tables.
*/
for (pgd = pgd_base; pgd < pgd_base + PTRS_PER_PGD; pgd++) {
if (pgd_none_or_clear_bad(pgd))
continue;
if (pgd_val(*pgd) & L_PGD_SWAPPER)
continue;
pud = pud_offset(pgd, 0);
if (pud_none_or_clear_bad(pud))
continue;
pmd = pmd_offset(pud, 0);
pud_clear(pud);
pmd_free(mm, pmd);
mm: fix false-positive warning on exit due mm_nr_pmds(mm) The problem is that we check nr_ptes/nr_pmds in exit_mmap() which happens *before* pgd_free(). And if an arch does pte/pmd allocation in pgd_alloc() and frees them in pgd_free() we see offset in counters by the time of the checks. We tried to workaround this by offsetting expected counter value according to FIRST_USER_ADDRESS for both nr_pte and nr_pmd in exit_mmap(). But it doesn't work in some cases: 1. ARM with LPAE enabled also has non-zero USER_PGTABLES_CEILING, but upper addresses occupied with huge pmd entries, so the trick with offsetting expected counter value will get really ugly: we will have to apply it nr_pmds, but not nr_ptes. 2. Metag has non-zero FIRST_USER_ADDRESS, but doesn't do allocation pte/pmd page tables allocation in pgd_alloc(), just setup a pgd entry which is allocated at boot and shared accross all processes. The proposal is to move the check to check_mm() which happens *after* pgd_free() and do proper accounting during pgd_alloc() and pgd_free() which would bring counters to zero if nothing leaked. Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Reported-by: Tyler Baker <tyler.baker@linaro.org> Tested-by: Tyler Baker <tyler.baker@linaro.org> Tested-by: Nishanth Menon <nm@ti.com> Cc: Russell King <linux@arm.linux.org.uk> Cc: James Hogan <james.hogan@imgtec.com> Cc: Guan Xuetao <gxt@mprc.pku.edu.cn> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-02-12 06:26:53 +07:00
mm_dec_nr_pmds(mm);
pgd_clear(pgd);
pud_free(mm, pud);
}
#endif
__pgd_free(pgd_base);
}