This is the third version of the patchset previously sent [1]. I have basically only rebased it on top of 4.7-rc1 tree and dropped "dm: get rid of superfluous gfp flags" which went through dm tree. I am sending it now because it is tree wide and chances for conflicts are reduced considerably when we want to target rc2. I plan to send the next step and rename the flag and move to a better semantic later during this release cycle so we will have a new semantic ready for 4.8 merge window hopefully. Motivation: While working on something unrelated I've checked the current usage of __GFP_REPEAT in the tree. It seems that a majority of the usage is and always has been bogus because __GFP_REPEAT has always been about costly high order allocations while we are using it for order-0 or very small orders very often. It seems that a big pile of them is just a copy&paste when a code has been adopted from one arch to another. I think it makes some sense to get rid of them because they are just making the semantic more unclear. Please note that GFP_REPEAT is documented as * __GFP_REPEAT: Try hard to allocate the memory, but the allocation attempt * _might_ fail. This depends upon the particular VM implementation. while !costly requests have basically nofail semantic. So one could reasonably expect that order-0 request with __GFP_REPEAT will not loop for ever. This is not implemented right now though. I would like to move on with __GFP_REPEAT and define a better semantic for it. $ git grep __GFP_REPEAT origin/master | wc -l 111 $ git grep __GFP_REPEAT | wc -l 36 So we are down to the third after this patch series. The remaining places really seem to be relying on __GFP_REPEAT due to large allocation requests. This still needs some double checking which I will do later after all the simple ones are sorted out. I am touching a lot of arch specific code here and I hope I got it right but as a matter of fact I even didn't compile test for some archs as I do not have cross compiler for them. Patches should be quite trivial to review for stupid compile mistakes though. The tricky parts are usually hidden by macro definitions and thats where I would appreciate help from arch maintainers. [1] http://lkml.kernel.org/r/1461849846-27209-1-git-send-email-mhocko@kernel.org This patch (of 19): __GFP_REPEAT has a rather weak semantic but since it has been introduced around 2.6.12 it has been ignored for low order allocations. Yet we have the full kernel tree with its usage for apparently order-0 allocations. This is really confusing because __GFP_REPEAT is explicitly documented to allow allocation failures which is a weaker semantic than the current order-0 has (basically nofail). Let's simply drop __GFP_REPEAT from those places. This would allow to identify place which really need allocator to retry harder and formulate a more specific semantic for what the flag is supposed to do actually. Link: http://lkml.kernel.org/r/1464599699-30131-2-git-send-email-mhocko@kernel.org Signed-off-by: Michal Hocko <mhocko@suse.com> Cc: "David S. Miller" <davem@davemloft.net> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: "James E.J. Bottomley" <jejb@parisc-linux.org> Cc: "Theodore Ts'o" <tytso@mit.edu> Cc: Andy Lutomirski <luto@kernel.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Chen Liqin <liqin.linux@gmail.com> Cc: Chris Metcalf <cmetcalf@mellanox.com> [for tile] Cc: Guan Xuetao <gxt@mprc.pku.edu.cn> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Helge Deller <deller@gmx.de> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jan Kara <jack@suse.cz> Cc: John Crispin <blogic@openwrt.org> Cc: Lennox Wu <lennox.wu@gmail.com> Cc: Ley Foon Tan <lftan@altera.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Matt Fleming <matt@codeblueprint.co.uk> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Rich Felker <dalias@libc.org> Cc: Russell King <linux@arm.linux.org.uk> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vineet Gupta <vgupta@synopsys.com> Cc: Will Deacon <will.deacon@arm.com> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
157 lines
4.2 KiB
C
157 lines
4.2 KiB
C
#ifndef _ASM_PGALLOC_H
|
|
#define _ASM_PGALLOC_H
|
|
|
|
#include <linux/gfp.h>
|
|
#include <linux/mm.h>
|
|
#include <linux/threads.h>
|
|
#include <asm/processor.h>
|
|
#include <asm/fixmap.h>
|
|
|
|
#include <asm/cache.h>
|
|
|
|
/* Allocate the top level pgd (page directory)
|
|
*
|
|
* Here (for 64 bit kernels) we implement a Hybrid L2/L3 scheme: we
|
|
* allocate the first pmd adjacent to the pgd. This means that we can
|
|
* subtract a constant offset to get to it. The pmd and pgd sizes are
|
|
* arranged so that a single pmd covers 4GB (giving a full 64-bit
|
|
* process access to 8TB) so our lookups are effectively L2 for the
|
|
* first 4GB of the kernel (i.e. for all ILP32 processes and all the
|
|
* kernel for machines with under 4GB of memory) */
|
|
static inline pgd_t *pgd_alloc(struct mm_struct *mm)
|
|
{
|
|
pgd_t *pgd = (pgd_t *)__get_free_pages(GFP_KERNEL,
|
|
PGD_ALLOC_ORDER);
|
|
pgd_t *actual_pgd = pgd;
|
|
|
|
if (likely(pgd != NULL)) {
|
|
memset(pgd, 0, PAGE_SIZE<<PGD_ALLOC_ORDER);
|
|
#if CONFIG_PGTABLE_LEVELS == 3
|
|
actual_pgd += PTRS_PER_PGD;
|
|
/* Populate first pmd with allocated memory. We mark it
|
|
* with PxD_FLAG_ATTACHED as a signal to the system that this
|
|
* pmd entry may not be cleared. */
|
|
__pgd_val_set(*actual_pgd, (PxD_FLAG_PRESENT |
|
|
PxD_FLAG_VALID |
|
|
PxD_FLAG_ATTACHED)
|
|
+ (__u32)(__pa((unsigned long)pgd) >> PxD_VALUE_SHIFT));
|
|
/* The first pmd entry also is marked with PxD_FLAG_ATTACHED as
|
|
* a signal that this pmd may not be freed */
|
|
__pgd_val_set(*pgd, PxD_FLAG_ATTACHED);
|
|
#endif
|
|
}
|
|
return actual_pgd;
|
|
}
|
|
|
|
static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
|
|
{
|
|
#if CONFIG_PGTABLE_LEVELS == 3
|
|
pgd -= PTRS_PER_PGD;
|
|
#endif
|
|
free_pages((unsigned long)pgd, PGD_ALLOC_ORDER);
|
|
}
|
|
|
|
#if CONFIG_PGTABLE_LEVELS == 3
|
|
|
|
/* Three Level Page Table Support for pmd's */
|
|
|
|
static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, pmd_t *pmd)
|
|
{
|
|
__pgd_val_set(*pgd, (PxD_FLAG_PRESENT | PxD_FLAG_VALID) +
|
|
(__u32)(__pa((unsigned long)pmd) >> PxD_VALUE_SHIFT));
|
|
}
|
|
|
|
static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long address)
|
|
{
|
|
pmd_t *pmd = (pmd_t *)__get_free_pages(GFP_KERNEL|__GFP_REPEAT,
|
|
PMD_ORDER);
|
|
if (pmd)
|
|
memset(pmd, 0, PAGE_SIZE<<PMD_ORDER);
|
|
return pmd;
|
|
}
|
|
|
|
static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
|
|
{
|
|
if (pmd_flag(*pmd) & PxD_FLAG_ATTACHED) {
|
|
/*
|
|
* This is the permanent pmd attached to the pgd;
|
|
* cannot free it.
|
|
* Increment the counter to compensate for the decrement
|
|
* done by generic mm code.
|
|
*/
|
|
mm_inc_nr_pmds(mm);
|
|
return;
|
|
}
|
|
free_pages((unsigned long)pmd, PMD_ORDER);
|
|
}
|
|
|
|
#else
|
|
|
|
/* Two Level Page Table Support for pmd's */
|
|
|
|
/*
|
|
* allocating and freeing a pmd is trivial: the 1-entry pmd is
|
|
* inside the pgd, so has no extra memory associated with it.
|
|
*/
|
|
|
|
#define pmd_alloc_one(mm, addr) ({ BUG(); ((pmd_t *)2); })
|
|
#define pmd_free(mm, x) do { } while (0)
|
|
#define pgd_populate(mm, pmd, pte) BUG()
|
|
|
|
#endif
|
|
|
|
static inline void
|
|
pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd, pte_t *pte)
|
|
{
|
|
#if CONFIG_PGTABLE_LEVELS == 3
|
|
/* preserve the gateway marker if this is the beginning of
|
|
* the permanent pmd */
|
|
if(pmd_flag(*pmd) & PxD_FLAG_ATTACHED)
|
|
__pmd_val_set(*pmd, (PxD_FLAG_PRESENT |
|
|
PxD_FLAG_VALID |
|
|
PxD_FLAG_ATTACHED)
|
|
+ (__u32)(__pa((unsigned long)pte) >> PxD_VALUE_SHIFT));
|
|
else
|
|
#endif
|
|
__pmd_val_set(*pmd, (PxD_FLAG_PRESENT | PxD_FLAG_VALID)
|
|
+ (__u32)(__pa((unsigned long)pte) >> PxD_VALUE_SHIFT));
|
|
}
|
|
|
|
#define pmd_populate(mm, pmd, pte_page) \
|
|
pmd_populate_kernel(mm, pmd, page_address(pte_page))
|
|
#define pmd_pgtable(pmd) pmd_page(pmd)
|
|
|
|
static inline pgtable_t
|
|
pte_alloc_one(struct mm_struct *mm, unsigned long address)
|
|
{
|
|
struct page *page = alloc_page(GFP_KERNEL|__GFP_ZERO);
|
|
if (!page)
|
|
return NULL;
|
|
if (!pgtable_page_ctor(page)) {
|
|
__free_page(page);
|
|
return NULL;
|
|
}
|
|
return page;
|
|
}
|
|
|
|
static inline pte_t *
|
|
pte_alloc_one_kernel(struct mm_struct *mm, unsigned long addr)
|
|
{
|
|
pte_t *pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_ZERO);
|
|
return pte;
|
|
}
|
|
|
|
static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
|
|
{
|
|
free_page((unsigned long)pte);
|
|
}
|
|
|
|
static inline void pte_free(struct mm_struct *mm, struct page *pte)
|
|
{
|
|
pgtable_page_dtor(pte);
|
|
pte_free_kernel(mm, page_address(pte));
|
|
}
|
|
|
|
#define check_pgt_cache() do { } while (0)
|
|
|
|
#endif
|