mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-28 01:15:15 +07:00
32d6bd9059
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>
158 lines
3.9 KiB
C
158 lines
3.9 KiB
C
/* pgalloc.c: page directory & page table allocation
|
|
*
|
|
* Copyright (C) 2004 Red Hat, Inc. All Rights Reserved.
|
|
* Written by David Howells (dhowells@redhat.com)
|
|
*
|
|
* 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.
|
|
*/
|
|
|
|
#include <linux/sched.h>
|
|
#include <linux/gfp.h>
|
|
#include <linux/mm.h>
|
|
#include <linux/highmem.h>
|
|
#include <linux/quicklist.h>
|
|
#include <asm/pgalloc.h>
|
|
#include <asm/page.h>
|
|
#include <asm/cacheflush.h>
|
|
|
|
pgd_t swapper_pg_dir[PTRS_PER_PGD] __attribute__((aligned(PAGE_SIZE)));
|
|
|
|
pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address)
|
|
{
|
|
pte_t *pte = (pte_t *)__get_free_page(GFP_KERNEL);
|
|
if (pte)
|
|
clear_page(pte);
|
|
return pte;
|
|
}
|
|
|
|
pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long address)
|
|
{
|
|
struct page *page;
|
|
|
|
#ifdef CONFIG_HIGHPTE
|
|
page = alloc_pages(GFP_KERNEL|__GFP_HIGHMEM, 0);
|
|
#else
|
|
page = alloc_pages(GFP_KERNEL, 0);
|
|
#endif
|
|
if (!page)
|
|
return NULL;
|
|
|
|
clear_highpage(page);
|
|
if (!pgtable_page_ctor(page)) {
|
|
__free_page(page);
|
|
return NULL;
|
|
}
|
|
flush_dcache_page(page);
|
|
return page;
|
|
}
|
|
|
|
void __set_pmd(pmd_t *pmdptr, unsigned long pmd)
|
|
{
|
|
unsigned long *__ste_p = pmdptr->ste;
|
|
int loop;
|
|
|
|
if (!pmd) {
|
|
memset(__ste_p, 0, PME_SIZE);
|
|
}
|
|
else {
|
|
BUG_ON(pmd & (0x3f00 | xAMPRx_SS | 0xe));
|
|
|
|
for (loop = PME_SIZE; loop > 0; loop -= 4) {
|
|
*__ste_p++ = pmd;
|
|
pmd += __frv_PT_SIZE;
|
|
}
|
|
}
|
|
|
|
frv_dcache_writeback((unsigned long) pmdptr, (unsigned long) (pmdptr + 1));
|
|
}
|
|
|
|
/*
|
|
* List of all pgd's needed for non-PAE so it can invalidate entries
|
|
* in both cached and uncached pgd's; not needed for PAE since the
|
|
* kernel pmd is shared. If PAE were not to share the pmd a similar
|
|
* tactic would be needed. This is essentially codepath-based locking
|
|
* against pageattr.c; it is the unique case in which a valid change
|
|
* of kernel pagetables can't be lazily synchronized by vmalloc faults.
|
|
* vmalloc faults work because attached pagetables are never freed.
|
|
* If the locking proves to be non-performant, a ticketing scheme with
|
|
* checks at dup_mmap(), exec(), and other mmlist addition points
|
|
* could be used. The locking scheme was chosen on the basis of
|
|
* manfred's recommendations and having no core impact whatsoever.
|
|
* -- nyc
|
|
*/
|
|
DEFINE_SPINLOCK(pgd_lock);
|
|
struct page *pgd_list;
|
|
|
|
static inline void pgd_list_add(pgd_t *pgd)
|
|
{
|
|
struct page *page = virt_to_page(pgd);
|
|
page->index = (unsigned long) pgd_list;
|
|
if (pgd_list)
|
|
set_page_private(pgd_list, (unsigned long) &page->index);
|
|
pgd_list = page;
|
|
set_page_private(page, (unsigned long)&pgd_list);
|
|
}
|
|
|
|
static inline void pgd_list_del(pgd_t *pgd)
|
|
{
|
|
struct page *next, **pprev, *page = virt_to_page(pgd);
|
|
next = (struct page *) page->index;
|
|
pprev = (struct page **) page_private(page);
|
|
*pprev = next;
|
|
if (next)
|
|
set_page_private(next, (unsigned long) pprev);
|
|
}
|
|
|
|
void pgd_ctor(void *pgd)
|
|
{
|
|
unsigned long flags;
|
|
|
|
if (PTRS_PER_PMD == 1)
|
|
spin_lock_irqsave(&pgd_lock, flags);
|
|
|
|
memcpy((pgd_t *) pgd + USER_PGDS_IN_LAST_PML4,
|
|
swapper_pg_dir + USER_PGDS_IN_LAST_PML4,
|
|
(PTRS_PER_PGD - USER_PGDS_IN_LAST_PML4) * sizeof(pgd_t));
|
|
|
|
if (PTRS_PER_PMD > 1)
|
|
return;
|
|
|
|
pgd_list_add(pgd);
|
|
spin_unlock_irqrestore(&pgd_lock, flags);
|
|
memset(pgd, 0, USER_PGDS_IN_LAST_PML4 * sizeof(pgd_t));
|
|
}
|
|
|
|
/* never called when PTRS_PER_PMD > 1 */
|
|
void pgd_dtor(void *pgd)
|
|
{
|
|
unsigned long flags; /* can be called from interrupt context */
|
|
|
|
spin_lock_irqsave(&pgd_lock, flags);
|
|
pgd_list_del(pgd);
|
|
spin_unlock_irqrestore(&pgd_lock, flags);
|
|
}
|
|
|
|
pgd_t *pgd_alloc(struct mm_struct *mm)
|
|
{
|
|
return quicklist_alloc(0, GFP_KERNEL, pgd_ctor);
|
|
}
|
|
|
|
void pgd_free(struct mm_struct *mm, pgd_t *pgd)
|
|
{
|
|
/* in the non-PAE case, clear_page_tables() clears user pgd entries */
|
|
quicklist_free(0, pgd_dtor, pgd);
|
|
}
|
|
|
|
void __init pgtable_cache_init(void)
|
|
{
|
|
}
|
|
|
|
void check_pgt_cache(void)
|
|
{
|
|
quicklist_trim(0, pgd_dtor, 25, 16);
|
|
}
|
|
|