2022-05-31 18:04:11 +08:00
|
|
|
/* SPDX-License-Identifier: GPL-2.0 */
|
|
|
|
|
/*
|
|
|
|
|
* Copyright (C) 2020-2022 Loongson Technology Corporation Limited
|
|
|
|
|
*/
|
|
|
|
|
#ifndef _ASM_PGALLOC_H
|
|
|
|
|
#define _ASM_PGALLOC_H
|
|
|
|
|
|
|
|
|
|
#include <linux/mm.h>
|
|
|
|
|
#include <linux/sched.h>
|
|
|
|
|
|
|
|
|
|
#define __HAVE_ARCH_PMD_ALLOC_ONE
|
|
|
|
|
#define __HAVE_ARCH_PUD_ALLOC_ONE
|
LoongArch: Set initial pte entry with PAGE_GLOBAL for kernel space
There are two pages in one TLB entry on LoongArch system. For kernel
space, it requires both two pte entries (buddies) with PAGE_GLOBAL bit
set, otherwise HW treats it as non-global tlb, there will be potential
problems if tlb entry for kernel space is not global. Such as fail to
flush kernel tlb with the function local_flush_tlb_kernel_range() which
supposed only flush tlb with global bit.
Kernel address space areas include percpu, vmalloc, vmemmap, fixmap and
kasan areas. For these areas both two consecutive page table entries
should be enabled with PAGE_GLOBAL bit. So with function set_pte() and
pte_clear(), pte buddy entry is checked and set besides its own pte
entry. However it is not atomic operation to set both two pte entries,
there is problem with test_vmalloc test case.
So function kernel_pte_init() is added to init a pte table when it is
created for kernel address space, and the default initial pte value is
PAGE_GLOBAL rather than zero at beginning. Then only its own pte entry
need update with function set_pte() and pte_clear(), nothing to do with
the pte buddy entry.
Signed-off-by: Bibo Mao <maobibo@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
2024-10-21 22:11:19 +08:00
|
|
|
#define __HAVE_ARCH_PTE_ALLOC_ONE_KERNEL
|
2022-05-31 18:04:11 +08:00
|
|
|
#include <asm-generic/pgalloc.h>
|
|
|
|
|
|
|
|
|
|
static inline void pmd_populate_kernel(struct mm_struct *mm,
|
|
|
|
|
pmd_t *pmd, pte_t *pte)
|
|
|
|
|
{
|
|
|
|
|
set_pmd(pmd, __pmd((unsigned long)pte));
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd, pgtable_t pte)
|
|
|
|
|
{
|
|
|
|
|
set_pmd(pmd, __pmd((unsigned long)page_address(pte)));
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#ifndef __PAGETABLE_PMD_FOLDED
|
|
|
|
|
|
|
|
|
|
static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd)
|
|
|
|
|
{
|
|
|
|
|
set_pud(pud, __pud((unsigned long)pmd));
|
|
|
|
|
}
|
|
|
|
|
#endif
|
|
|
|
|
|
|
|
|
|
#ifndef __PAGETABLE_PUD_FOLDED
|
|
|
|
|
|
|
|
|
|
static inline void p4d_populate(struct mm_struct *mm, p4d_t *p4d, pud_t *pud)
|
|
|
|
|
{
|
|
|
|
|
set_p4d(p4d, __p4d((unsigned long)pud));
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#endif /* __PAGETABLE_PUD_FOLDED */
|
|
|
|
|
|
|
|
|
|
extern void pagetable_init(void);
|
|
|
|
|
|
|
|
|
|
extern pgd_t *pgd_alloc(struct mm_struct *mm);
|
|
|
|
|
|
LoongArch: Set initial pte entry with PAGE_GLOBAL for kernel space
There are two pages in one TLB entry on LoongArch system. For kernel
space, it requires both two pte entries (buddies) with PAGE_GLOBAL bit
set, otherwise HW treats it as non-global tlb, there will be potential
problems if tlb entry for kernel space is not global. Such as fail to
flush kernel tlb with the function local_flush_tlb_kernel_range() which
supposed only flush tlb with global bit.
Kernel address space areas include percpu, vmalloc, vmemmap, fixmap and
kasan areas. For these areas both two consecutive page table entries
should be enabled with PAGE_GLOBAL bit. So with function set_pte() and
pte_clear(), pte buddy entry is checked and set besides its own pte
entry. However it is not atomic operation to set both two pte entries,
there is problem with test_vmalloc test case.
So function kernel_pte_init() is added to init a pte table when it is
created for kernel address space, and the default initial pte value is
PAGE_GLOBAL rather than zero at beginning. Then only its own pte entry
need update with function set_pte() and pte_clear(), nothing to do with
the pte buddy entry.
Signed-off-by: Bibo Mao <maobibo@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
2024-10-21 22:11:19 +08:00
|
|
|
static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm)
|
|
|
|
|
{
|
|
|
|
|
pte_t *pte = __pte_alloc_one_kernel(mm);
|
|
|
|
|
|
|
|
|
|
if (pte)
|
|
|
|
|
kernel_pte_init(pte);
|
|
|
|
|
|
|
|
|
|
return pte;
|
|
|
|
|
}
|
|
|
|
|
|
mm: pgtable: convert some architectures to use tlb_remove_ptdesc()
Now, the nine architectures of csky, hexagon, loongarch, m68k, mips,
nios2, openrisc, sh and um do not select CONFIG_MMU_GATHER_RCU_TABLE_FREE,
and just call pagetable_dtor() + tlb_remove_page_ptdesc() (the wrapper of
tlb_remove_page()). This is the same as the implementation of
tlb_remove_{ptdesc|table}() under !CONFIG_MMU_GATHER_TABLE_FREE, so
convert these architectures to use tlb_remove_ptdesc().
The ultimate goal is to make the architecture only use tlb_remove_ptdesc()
or tlb_remove_table() for page table pages.
[zhengqi.arch@bytedance.com: v2]
Link: https://lkml.kernel.org/r/20250303072603.45423-1-zhengqi.arch@bytedance.com
[akpm@linux-foundation.org: remove trailing semi in arch/loongarch/include/asm/pgalloc.h]
Link: https://lkml.kernel.org/r/19db3e8673b67bad2f1df1ab37f1c89d99eacfea.1740454179.git.zhengqi.arch@bytedance.com
Signed-off-by: Qi Zheng <zhengqi.arch@bytedance.com>
Suggested-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Kevin Brodsky <kevin.brodsky@arm.com>
Acked-by: Geert Uytterhoeven <geert@linux-m68k.org> [m68k]
Cc: Alexandre Ghiti <alexghiti@rivosinc.com>
Cc: "Aneesh Kumar K.V" <aneesh.kumar@kernel.org>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Hugh Dickens <hughd@google.com>
Cc: Jann Horn <jannh@google.com>
Cc: Matthew Wilcow (Oracle) <willy@infradead.org>
Cc: "Mike Rapoport (IBM)" <rppt@kernel.org>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Rik van Riel <riel@surriel.com>
Cc: Vishal Moola (Oracle) <vishal.moola@gmail.com>
Cc: Will Deacon <will@kernel.org>
Cc: Yu Zhao <yuzhao@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2025-02-25 11:45:53 +08:00
|
|
|
#define __pte_free_tlb(tlb, pte, address) \
|
|
|
|
|
tlb_remove_ptdesc((tlb), page_ptdesc(pte))
|
2022-05-31 18:04:11 +08:00
|
|
|
|
|
|
|
|
#ifndef __PAGETABLE_PMD_FOLDED
|
|
|
|
|
|
|
|
|
|
static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long address)
|
|
|
|
|
{
|
|
|
|
|
pmd_t *pmd;
|
2023-08-07 16:05:03 -07:00
|
|
|
struct ptdesc *ptdesc;
|
2022-05-31 18:04:11 +08:00
|
|
|
|
2023-08-07 16:05:03 -07:00
|
|
|
ptdesc = pagetable_alloc(GFP_KERNEL_ACCOUNT, 0);
|
|
|
|
|
if (!ptdesc)
|
2022-05-31 18:04:11 +08:00
|
|
|
return NULL;
|
|
|
|
|
|
mm: pass mm down to pagetable_{pte,pmd}_ctor
Patch series "Always call constructor for kernel page tables", v2.
There has been much confusion around exactly when page table
constructors/destructors (pagetable_*_[cd]tor) are supposed to be called.
They were initially introduced for user PTEs only (to support split page
table locks), then at the PMD level for the same purpose. Accounting was
added later on, starting at the PTE level and then moving to higher levels
(PMD, PUD). Finally, with my earlier series "Account page tables at all
levels" [1], the ctor/dtor is run for all levels, all the way to PGD.
I thought this was the end of the story, and it hopefully is for user
pgtables, but I was wrong for what concerns kernel pgtables. The current
situation there makes very little sense:
* At the PTE level, the ctor/dtor is not called (at least in the generic
implementation). Specific helpers are used for kernel pgtables at this
level (pte_{alloc,free}_kernel()) and those have never called the
ctor/dtor, most likely because they were initially irrelevant in the
kernel case.
* At all other levels, the ctor/dtor is normally called. This is
potentially wasteful at the PMD level (more on that later).
This series aims to ensure that the ctor/dtor is always called for kernel
pgtables, as it already is for user pgtables. Besides consistency, the
main motivation is to guarantee that ctor/dtor hooks are systematically
called; this makes it possible to insert hooks to protect page tables [2],
for instance. There is however an extra challenge: split locks are not
used for kernel pgtables, and it would therefore be wasteful to initialise
them (ptlock_init()).
It is worth clarifying exactly when split locks are used. They clearly
are for user pgtables, but as illustrated in commit 61444cde9170 ("ARM:
8591/1: mm: use fully constructed struct pages for EFI pgd allocations"),
they also are for special page tables like efi_mm. The one case where
split locks are definitely unused is pgtables owned by init_mm; this is
consistent with the behaviour of apply_to_pte_range().
The approach chosen in this series is therefore to pass the mm associated
to the pgtables being constructed to pagetable_{pte,pmd}_ctor() (patch 1),
and skip ptlock_init() if mm == &init_mm (patch 3 and 7). This makes it
possible to call the PTE ctor/dtor from pte_{alloc,free}_kernel() without
unintended consequences (patch 3). As a result the accounting functions
are now called at all levels for kernel pgtables, and split locks are
never initialised.
In configurations where ptlocks are dynamically allocated (32-bit,
PREEMPT_RT, etc.) and ARCH_ENABLE_SPLIT_PMD_PTLOCK is selected, this
series results in the removal of a kmem_cache allocation for every kernel
PMD. Additionally, for certain architectures that do not use
<asm-generic/pgalloc.h> such as s390, the same optimisation occurs at the
PTE level.
===
Things get more complicated when it comes to special pgtable allocators
(patch 8-12). All architectures need such allocators to create initial
kernel pgtables; we are not concerned with those as the ctor cannot be
called so early in the boot sequence. However, those allocators may also
be used later in the boot sequence or during normal operations. There are
two main use-cases:
1. Mapping EFI memory: efi_mm (arm, arm64, riscv)
2. arch_add_memory(): init_mm
The ctor is already explicitly run (at the PTE/PMD level) in the first
case, as required for pgtables that are not associated with init_mm.
However the same allocators may also be used for the second use-case (or
others), and this is where it gets messy. Patch 1 calls the ctor with
NULL as mm in those situations, as the actual mm isn't available.
Practically this means that ptlocks will be unconditionally initialised.
This is fine on arm - create_mapping_late() is only used for the EFI
mapping. On arm64, __create_pgd_mapping() is also used by
arch_add_memory(); patch 8/9/11 ensure that ctors are called at all levels
with the appropriate mm. The situation is similar on riscv, but
propagating the mm down to the ctor would require significant refactoring.
Since they are already called unconditionally, this series leaves riscv
no worse off - patch 10 adds comments to clarify the situation.
From a cursory look at other architectures implementing arch_add_memory(),
s390 and x86 may also need a similar treatment to add constructor calls.
This is to be taken care of in a future version or as a follow-up.
===
The complications in those special pgtable allocators beg the question:
does it really make sense to treat efi_mm and init_mm differently in e.g.
apply_to_pte_range()? Maybe what we really need is a way to tell if an mm
corresponds to user memory or not, and never use split locks for non-user
mm's. Feedback and suggestions welcome!
This patch (of 12):
In preparation for calling constructors for all kernel page tables while
eliding unnecessary ptlock initialisation, let's pass down the associated
mm to the PTE/PMD level ctors. (These are the two levels where ptlocks
are used.)
In most cases the mm is already around at the point of calling the ctor so
we simply pass it down. This is however not the case for special page
table allocators:
* arch/arm/mm/mmu.c
* arch/arm64/mm/mmu.c
* arch/riscv/mm/init.c
In those cases, the page tables being allocated are either for standard
kernel memory (init_mm) or special page directories, which may not be
associated to any mm. For now let's pass NULL as mm; this will be refined
where possible in future patches.
No functional change in this patch.
Link: https://lore.kernel.org/linux-mm/20250103184415.2744423-1-kevin.brodsky@arm.com/ [1]
Link: https://lore.kernel.org/linux-hardening/20250203101839.1223008-1-kevin.brodsky@arm.com/ [2]
Link: https://lkml.kernel.org/r/20250408095222.860601-1-kevin.brodsky@arm.com
Link: https://lkml.kernel.org/r/20250408095222.860601-2-kevin.brodsky@arm.com
Signed-off-by: Kevin Brodsky <kevin.brodsky@arm.com>
Reviewed-by: Alexander Gordeev <agordeev@linux.ibm.com> [s390]
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Andreas Larsson <andreas@gaisler.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Cc: Kevin Brodsky <kevin.brodsky@arm.com>
Cc: Linus Waleij <linus.walleij@linaro.org>
Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Qi Zheng <zhengqi.arch@bytedance.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Will Deacon <will@kernel.org>
Cc: Yang Shi <yang@os.amperecomputing.com>
Cc: <x86@kernel.org>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2025-04-08 10:52:11 +01:00
|
|
|
if (!pagetable_pmd_ctor(mm, ptdesc)) {
|
2023-08-07 16:05:03 -07:00
|
|
|
pagetable_free(ptdesc);
|
2022-05-31 18:04:11 +08:00
|
|
|
return NULL;
|
|
|
|
|
}
|
|
|
|
|
|
2023-08-07 16:05:03 -07:00
|
|
|
pmd = ptdesc_address(ptdesc);
|
2022-10-27 20:52:50 +08:00
|
|
|
pmd_init(pmd);
|
2022-05-31 18:04:11 +08:00
|
|
|
return pmd;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#define __pmd_free_tlb(tlb, x, addr) pmd_free((tlb)->mm, x)
|
|
|
|
|
|
|
|
|
|
#endif
|
|
|
|
|
|
|
|
|
|
#ifndef __PAGETABLE_PUD_FOLDED
|
|
|
|
|
|
|
|
|
|
static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long address)
|
|
|
|
|
{
|
|
|
|
|
pud_t *pud;
|
2023-08-07 16:05:03 -07:00
|
|
|
struct ptdesc *ptdesc = pagetable_alloc(GFP_KERNEL & ~__GFP_HIGHMEM, 0);
|
2022-05-31 18:04:11 +08:00
|
|
|
|
2023-08-07 16:05:03 -07:00
|
|
|
if (!ptdesc)
|
|
|
|
|
return NULL;
|
2023-09-18 14:31:42 +08:00
|
|
|
pagetable_pud_ctor(ptdesc);
|
2023-08-07 16:05:03 -07:00
|
|
|
pud = ptdesc_address(ptdesc);
|
|
|
|
|
|
|
|
|
|
pud_init(pud);
|
2022-05-31 18:04:11 +08:00
|
|
|
return pud;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
#define __pud_free_tlb(tlb, x, addr) pud_free((tlb)->mm, x)
|
|
|
|
|
|
|
|
|
|
#endif /* __PAGETABLE_PUD_FOLDED */
|
|
|
|
|
|
2023-09-06 22:53:09 +08:00
|
|
|
extern pte_t * __init populate_kernel_pte(unsigned long addr);
|
2022-05-31 18:04:11 +08:00
|
|
|
#endif /* _ASM_PGALLOC_H */
|