1
0
Fork 0
alistair23-linux/arch/openrisc/include/asm/pgalloc.h

105 lines
2.3 KiB
C
Raw Normal View History

/* SPDX-License-Identifier: GPL-2.0-or-later */
/*
* OpenRISC Linux
*
* Linux architectural port borrowing liberally from similar works of
* others. All original copyrights apply as per the original source
* declaration.
*
* OpenRISC implementation:
* Copyright (C) 2003 Matjaz Breskvar <phoenix@bsemi.com>
* Copyright (C) 2010-2011 Jonas Bonn <jonas@southpole.se>
* et al.
*/
#ifndef __ASM_OPENRISC_PGALLOC_H
#define __ASM_OPENRISC_PGALLOC_H
#include <asm/page.h>
#include <linux/threads.h>
#include <linux/mm.h>
#include <linux/memblock.h>
extern int mem_init_done;
#define pmd_populate_kernel(mm, pmd, pte) \
set_pmd(pmd, __pmd(_KERNPG_TABLE + __pa(pte)))
static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd,
struct page *pte)
{
set_pmd(pmd, __pmd(_KERNPG_TABLE +
((unsigned long)page_to_pfn(pte) <<
(unsigned long) PAGE_SHIFT)));
}
/*
* Allocate and free page tables.
*/
static inline pgd_t *pgd_alloc(struct mm_struct *mm)
{
pgd_t *ret = (pgd_t *)__get_free_page(GFP_KERNEL);
if (ret) {
memset(ret, 0, USER_PTRS_PER_PGD * sizeof(pgd_t));
memcpy(ret + USER_PTRS_PER_PGD,
swapper_pg_dir + USER_PTRS_PER_PGD,
(PTRS_PER_PGD - USER_PTRS_PER_PGD) * sizeof(pgd_t));
}
return ret;
}
#if 0
/* FIXME: This seems to be the preferred style, but we are using
* current_pgd (from mm->pgd) to load kernel pages so we need it
* initialized. This needs to be looked into.
*/
extern inline pgd_t *pgd_alloc(struct mm_struct *mm)
{
return (pgd_t *)get_zeroed_page(GFP_KERNEL);
}
#endif
static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
{
free_page((unsigned long)pgd);
}
mm: treewide: remove unused address argument from pte_alloc functions Patch series "Add support for fast mremap". This series speeds up the mremap(2) syscall by copying page tables at the PMD level even for non-THP systems. There is concern that the extra 'address' argument that mremap passes to pte_alloc may do something subtle architecture related in the future that may make the scheme not work. Also we find that there is no point in passing the 'address' to pte_alloc since its unused. This patch therefore removes this argument tree-wide resulting in a nice negative diff as well. Also ensuring along the way that the enabled architectures do not do anything funky with the 'address' argument that goes unnoticed by the optimization. Build and boot tested on x86-64. Build tested on arm64. The config enablement patch for arm64 will be posted in the future after more testing. The changes were obtained by applying the following Coccinelle script. (thanks Julia for answering all Coccinelle questions!). Following fix ups were done manually: * Removal of address argument from pte_fragment_alloc * Removal of pte_alloc_one_fast definitions from m68k and microblaze. // Options: --include-headers --no-includes // Note: I split the 'identifier fn' line, so if you are manually // running it, please unsplit it so it runs for you. virtual patch @pte_alloc_func_def depends on patch exists@ identifier E2; identifier fn =~ "^(__pte_alloc|pte_alloc_one|pte_alloc|__pte_alloc_kernel|pte_alloc_one_kernel)$"; type T2; @@ fn(... - , T2 E2 ) { ... } @pte_alloc_func_proto_noarg depends on patch exists@ type T1, T2, T3, T4; identifier fn =~ "^(__pte_alloc|pte_alloc_one|pte_alloc|__pte_alloc_kernel|pte_alloc_one_kernel)$"; @@ ( - T3 fn(T1, T2); + T3 fn(T1); | - T3 fn(T1, T2, T4); + T3 fn(T1, T2); ) @pte_alloc_func_proto depends on patch exists@ identifier E1, E2, E4; type T1, T2, T3, T4; identifier fn =~ "^(__pte_alloc|pte_alloc_one|pte_alloc|__pte_alloc_kernel|pte_alloc_one_kernel)$"; @@ ( - T3 fn(T1 E1, T2 E2); + T3 fn(T1 E1); | - T3 fn(T1 E1, T2 E2, T4 E4); + T3 fn(T1 E1, T2 E2); ) @pte_alloc_func_call depends on patch exists@ expression E2; identifier fn =~ "^(__pte_alloc|pte_alloc_one|pte_alloc|__pte_alloc_kernel|pte_alloc_one_kernel)$"; @@ fn(... -, E2 ) @pte_alloc_macro depends on patch exists@ identifier fn =~ "^(__pte_alloc|pte_alloc_one|pte_alloc|__pte_alloc_kernel|pte_alloc_one_kernel)$"; identifier a, b, c; expression e; position p; @@ ( - #define fn(a, b, c) e + #define fn(a, b) e | - #define fn(a, b) e + #define fn(a) e ) Link: http://lkml.kernel.org/r/20181108181201.88826-2-joelaf@google.com Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org> Suggested-by: Kirill A. Shutemov <kirill@shutemov.name> Acked-by: Kirill A. Shutemov <kirill@shutemov.name> Cc: Michal Hocko <mhocko@kernel.org> Cc: Julia Lawall <Julia.Lawall@lip6.fr> Cc: Kirill A. Shutemov <kirill@shutemov.name> Cc: William Kucharski <william.kucharski@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-01-03 16:28:34 -07:00
extern pte_t *pte_alloc_one_kernel(struct mm_struct *mm);
mm: treewide: remove unused address argument from pte_alloc functions Patch series "Add support for fast mremap". This series speeds up the mremap(2) syscall by copying page tables at the PMD level even for non-THP systems. There is concern that the extra 'address' argument that mremap passes to pte_alloc may do something subtle architecture related in the future that may make the scheme not work. Also we find that there is no point in passing the 'address' to pte_alloc since its unused. This patch therefore removes this argument tree-wide resulting in a nice negative diff as well. Also ensuring along the way that the enabled architectures do not do anything funky with the 'address' argument that goes unnoticed by the optimization. Build and boot tested on x86-64. Build tested on arm64. The config enablement patch for arm64 will be posted in the future after more testing. The changes were obtained by applying the following Coccinelle script. (thanks Julia for answering all Coccinelle questions!). Following fix ups were done manually: * Removal of address argument from pte_fragment_alloc * Removal of pte_alloc_one_fast definitions from m68k and microblaze. // Options: --include-headers --no-includes // Note: I split the 'identifier fn' line, so if you are manually // running it, please unsplit it so it runs for you. virtual patch @pte_alloc_func_def depends on patch exists@ identifier E2; identifier fn =~ "^(__pte_alloc|pte_alloc_one|pte_alloc|__pte_alloc_kernel|pte_alloc_one_kernel)$"; type T2; @@ fn(... - , T2 E2 ) { ... } @pte_alloc_func_proto_noarg depends on patch exists@ type T1, T2, T3, T4; identifier fn =~ "^(__pte_alloc|pte_alloc_one|pte_alloc|__pte_alloc_kernel|pte_alloc_one_kernel)$"; @@ ( - T3 fn(T1, T2); + T3 fn(T1); | - T3 fn(T1, T2, T4); + T3 fn(T1, T2); ) @pte_alloc_func_proto depends on patch exists@ identifier E1, E2, E4; type T1, T2, T3, T4; identifier fn =~ "^(__pte_alloc|pte_alloc_one|pte_alloc|__pte_alloc_kernel|pte_alloc_one_kernel)$"; @@ ( - T3 fn(T1 E1, T2 E2); + T3 fn(T1 E1); | - T3 fn(T1 E1, T2 E2, T4 E4); + T3 fn(T1 E1, T2 E2); ) @pte_alloc_func_call depends on patch exists@ expression E2; identifier fn =~ "^(__pte_alloc|pte_alloc_one|pte_alloc|__pte_alloc_kernel|pte_alloc_one_kernel)$"; @@ fn(... -, E2 ) @pte_alloc_macro depends on patch exists@ identifier fn =~ "^(__pte_alloc|pte_alloc_one|pte_alloc|__pte_alloc_kernel|pte_alloc_one_kernel)$"; identifier a, b, c; expression e; position p; @@ ( - #define fn(a, b, c) e + #define fn(a, b) e | - #define fn(a, b) e + #define fn(a) e ) Link: http://lkml.kernel.org/r/20181108181201.88826-2-joelaf@google.com Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org> Suggested-by: Kirill A. Shutemov <kirill@shutemov.name> Acked-by: Kirill A. Shutemov <kirill@shutemov.name> Cc: Michal Hocko <mhocko@kernel.org> Cc: Julia Lawall <Julia.Lawall@lip6.fr> Cc: Kirill A. Shutemov <kirill@shutemov.name> Cc: William Kucharski <william.kucharski@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-01-03 16:28:34 -07:00
static inline struct page *pte_alloc_one(struct mm_struct *mm)
{
struct page *pte;
tree wide: get rid of __GFP_REPEAT for order-0 allocations part I 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>
2016-06-24 15:48:47 -06:00
pte = alloc_pages(GFP_KERNEL, 0);
if (!pte)
return NULL;
clear_page(page_address(pte));
if (!pgtable_page_ctor(pte)) {
__free_page(pte);
return NULL;
}
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);
__free_page(pte);
}
openrisc: Call destructor during __pte_free_tlb This fixes an issue uncovered when a recent change to add the "page table" flag was merged. During bootup we see many errors like the following: BUG: Bad page state in process mkdir pfn:00bae page:c1ff15c0 count:0 mapcount:-1024 mapping:00000000 index:0x0 flags: 0x0() raw: 00000000 00000000 00000000 fffffbff 00000000 00000100 00000200 00000000 page dumped because: nonzero mapcount Modules linked in: CPU: 0 PID: 46 Comm: mkdir Tainted: G B 4.17.0-simple-smp-07461-g1d40a5ea01d5-dirty #993 Call trace: [<(ptrval)>] show_stack+0x44/0x54 [<(ptrval)>] dump_stack+0xb0/0xe8 [<(ptrval)>] bad_page+0x138/0x174 [<(ptrval)>] ? cpumask_next+0x24/0x34 [<(ptrval)>] free_pages_check_bad+0x6c/0xd0 [<(ptrval)>] free_pcppages_bulk+0x174/0x42c [<(ptrval)>] free_unref_page_commit.isra.17+0xb8/0xc8 [<(ptrval)>] free_unref_page_list+0x10c/0x190 [<(ptrval)>] ? set_reset_devices+0x0/0x2c [<(ptrval)>] release_pages+0x3a0/0x414 [<(ptrval)>] tlb_flush_mmu_free+0x5c/0x90 [<(ptrval)>] tlb_flush_mmu+0x90/0xa4 [<(ptrval)>] arch_tlb_finish_mmu+0x50/0x94 [<(ptrval)>] tlb_finish_mmu+0x30/0x64 [<(ptrval)>] exit_mmap+0x110/0x1e0 [<(ptrval)>] mmput+0x50/0xf0 [<(ptrval)>] do_exit+0x274/0xa94 [<(ptrval)>] do_group_exit+0x50/0x110 [<(ptrval)>] __wake_up_parent+0x0/0x38 [<(ptrval)>] _syscall_return+0x0/0x4 During the __pte_free_tlb path openrisc fails to call the page destructor which would clear the new bits that were introduced. To fix this we are calling the destructor. It seem openrisc was the only architecture missing this, all other architectures either call the destructor like we are doing here or use pte_free. Note: failing to call the destructor was also messing up the zone stats (and will be cause other problems if you were using SPLIT_PTE_PTLOCKS, which we are not yet). Fixes: 1d40a5ea01d53 ("mm: mark pages in use for page tables") Acked-by: Matthew Wilcox <willy@infradead.org> Signed-off-by: Stafford Horne <shorne@gmail.com>
2018-06-17 15:52:58 -06:00
#define __pte_free_tlb(tlb, pte, addr) \
do { \
pgtable_page_dtor(pte); \
tlb_remove_page((tlb), (pte)); \
} while (0)
#define pmd_pgtable(pmd) pmd_page(pmd)
#endif