OpenCloudOS-Kernel/arch/powerpc/mm/copro_fault.c

156 lines
3.7 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-or-later
/*
* CoProcessor (SPU/AFU) mm fault handler
*
* (C) Copyright IBM Deutschland Entwicklung GmbH 2007
*
* Author: Arnd Bergmann <arndb@de.ibm.com>
* Author: Jeremy Kerr <jk@ozlabs.org>
*/
#include <linux/sched.h>
#include <linux/mm.h>
#include <linux/export.h>
#include <asm/reg.h>
#include <asm/copro.h>
#include <asm/spu.h>
#include <misc/cxl-base.h>
/*
* This ought to be kept in sync with the powerpc specific do_page_fault
* function. Currently, there are a few corner cases that we haven't had
* to handle fortunately.
*/
int copro_handle_mm_fault(struct mm_struct *mm, unsigned long ea,
mm: convert return type of handle_mm_fault() caller to vm_fault_t Use new return type vm_fault_t for fault handler. For now, this is just documenting that the function returns a VM_FAULT value rather than an errno. Once all instances are converted, vm_fault_t will become a distinct type. Ref-> commit 1c8f422059ae ("mm: change return type to vm_fault_t") In this patch all the caller of handle_mm_fault() are changed to return vm_fault_t type. Link: http://lkml.kernel.org/r/20180617084810.GA6730@jordon-HP-15-Notebook-PC Signed-off-by: Souptick Joarder <jrdr.linux@gmail.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Richard Henderson <rth@twiddle.net> Cc: Tony Luck <tony.luck@intel.com> Cc: Matt Turner <mattst88@gmail.com> Cc: Vineet Gupta <vgupta@synopsys.com> Cc: Russell King <linux@armlinux.org.uk> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Will Deacon <will.deacon@arm.com> Cc: Richard Kuo <rkuo@codeaurora.org> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Michal Simek <monstr@monstr.eu> Cc: James Hogan <jhogan@kernel.org> Cc: Ley Foon Tan <lftan@altera.com> Cc: Jonas Bonn <jonas@southpole.se> Cc: James E.J. Bottomley <jejb@parisc-linux.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Palmer Dabbelt <palmer@sifive.com> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Cc: David S. Miller <davem@davemloft.net> Cc: Richard Weinberger <richard@nod.at> Cc: Guan Xuetao <gxt@pku.edu.cn> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: "Levin, Alexander (Sasha Levin)" <alexander.levin@verizon.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-08-18 06:44:47 +08:00
unsigned long dsisr, vm_fault_t *flt)
{
struct vm_area_struct *vma;
unsigned long is_write;
int ret;
if (mm == NULL)
return -EFAULT;
if (mm->pgd == NULL)
return -EFAULT;
mmap locking API: use coccinelle to convert mmap_sem rwsem call sites This change converts the existing mmap_sem rwsem calls to use the new mmap locking API instead. The change is generated using coccinelle with the following rule: // spatch --sp-file mmap_lock_api.cocci --in-place --include-headers --dir . @@ expression mm; @@ ( -init_rwsem +mmap_init_lock | -down_write +mmap_write_lock | -down_write_killable +mmap_write_lock_killable | -down_write_trylock +mmap_write_trylock | -up_write +mmap_write_unlock | -downgrade_write +mmap_write_downgrade | -down_read +mmap_read_lock | -down_read_killable +mmap_read_lock_killable | -down_read_trylock +mmap_read_trylock | -up_read +mmap_read_unlock ) -(&mm->mmap_sem) +(mm) Signed-off-by: Michel Lespinasse <walken@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Daniel Jordan <daniel.m.jordan@oracle.com> Reviewed-by: Laurent Dufour <ldufour@linux.ibm.com> Reviewed-by: Vlastimil Babka <vbabka@suse.cz> Cc: Davidlohr Bueso <dbueso@suse.de> Cc: David Rientjes <rientjes@google.com> Cc: Hugh Dickins <hughd@google.com> Cc: Jason Gunthorpe <jgg@ziepe.ca> Cc: Jerome Glisse <jglisse@redhat.com> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Liam Howlett <Liam.Howlett@oracle.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ying Han <yinghan@google.com> Link: http://lkml.kernel.org/r/20200520052908.204642-5-walken@google.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-06-09 12:33:25 +08:00
mmap_read_lock(mm);
ret = -EFAULT;
vma = find_vma(mm, ea);
if (!vma)
goto out_unlock;
if (ea < vma->vm_start) {
if (!(vma->vm_flags & VM_GROWSDOWN))
goto out_unlock;
if (expand_stack(vma, ea))
goto out_unlock;
}
is_write = dsisr & DSISR_ISSTORE;
if (is_write) {
if (!(vma->vm_flags & VM_WRITE))
goto out_unlock;
} else {
if (!(vma->vm_flags & (VM_READ | VM_EXEC)))
goto out_unlock;
/*
* PROT_NONE is covered by the VMA check above.
* and hash should get a NOHPTE fault instead of
* a PROTFAULT in case fixup is needed for things
* like autonuma.
*/
if (!radix_enabled())
WARN_ON_ONCE(dsisr & DSISR_PROTFAULT);
}
ret = 0;
mm: do page fault accounting in handle_mm_fault Patch series "mm: Page fault accounting cleanups", v5. This is v5 of the pf accounting cleanup series. It originates from Gerald Schaefer's report on an issue a week ago regarding to incorrect page fault accountings for retried page fault after commit 4064b9827063 ("mm: allow VM_FAULT_RETRY for multiple times"): https://lore.kernel.org/lkml/20200610174811.44b94525@thinkpad/ What this series did: - Correct page fault accounting: we do accounting for a page fault (no matter whether it's from #PF handling, or gup, or anything else) only with the one that completed the fault. For example, page fault retries should not be counted in page fault counters. Same to the perf events. - Unify definition of PERF_COUNT_SW_PAGE_FAULTS: currently this perf event is used in an adhoc way across different archs. Case (1): for many archs it's done at the entry of a page fault handler, so that it will also cover e.g. errornous faults. Case (2): for some other archs, it is only accounted when the page fault is resolved successfully. Case (3): there're still quite some archs that have not enabled this perf event. Since this series will touch merely all the archs, we unify this perf event to always follow case (1), which is the one that makes most sense. And since we moved the accounting into handle_mm_fault, the other two MAJ/MIN perf events are well taken care of naturally. - Unify definition of "major faults": the definition of "major fault" is slightly changed when used in accounting (not VM_FAULT_MAJOR). More information in patch 1. - Always account the page fault onto the one that triggered the page fault. This does not matter much for #PF handlings, but mostly for gup. More information on this in patch 25. Patchset layout: Patch 1: Introduced the accounting in handle_mm_fault(), not enabled. Patch 2-23: Enable the new accounting for arch #PF handlers one by one. Patch 24: Enable the new accounting for the rest outliers (gup, iommu, etc.) Patch 25: Cleanup GUP task_struct pointer since it's not needed any more This patch (of 25): This is a preparation patch to move page fault accountings into the general code in handle_mm_fault(). This includes both the per task flt_maj/flt_min counters, and the major/minor page fault perf events. To do this, the pt_regs pointer is passed into handle_mm_fault(). PERF_COUNT_SW_PAGE_FAULTS should still be kept in per-arch page fault handlers. So far, all the pt_regs pointer that passed into handle_mm_fault() is NULL, which means this patch should have no intented functional change. Suggested-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Peter Xu <peterx@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Cc: Albert Ou <aou@eecs.berkeley.edu> Cc: Alexander Gordeev <agordeev@linux.ibm.com> Cc: Andy Lutomirski <luto@kernel.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Cain <bcain@codeaurora.org> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Christian Borntraeger <borntraeger@de.ibm.com> Cc: Chris Zankel <chris@zankel.net> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David S. Miller <davem@davemloft.net> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Gerald Schaefer <gerald.schaefer@de.ibm.com> Cc: Greentime Hu <green.hu@gmail.com> Cc: Guo Ren <guoren@kernel.org> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Helge Deller <deller@gmx.de> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru> Cc: James E.J. Bottomley <James.Bottomley@HansenPartnership.com> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Jonas Bonn <jonas@southpole.se> Cc: Ley Foon Tan <ley.foon.tan@intel.com> Cc: "Luck, Tony" <tony.luck@intel.com> Cc: Matt Turner <mattst88@gmail.com> Cc: Max Filippov <jcmvbkbc@gmail.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Michal Simek <monstr@monstr.eu> Cc: Nick Hu <nickhu@andestech.com> Cc: Palmer Dabbelt <palmer@dabbelt.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Paul Walmsley <paul.walmsley@sifive.com> Cc: Pekka Enberg <penberg@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Richard Henderson <rth@twiddle.net> Cc: Rich Felker <dalias@libc.org> Cc: Russell King <linux@armlinux.org.uk> Cc: Stafford Horne <shorne@gmail.com> Cc: Stefan Kristiansson <stefan.kristiansson@saunalahti.fi> Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vasily Gorbik <gor@linux.ibm.com> Cc: Vincent Chen <deanbo422@gmail.com> Cc: Vineet Gupta <vgupta@synopsys.com> Cc: Will Deacon <will@kernel.org> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Link: http://lkml.kernel.org/r/20200707225021.200906-1-peterx@redhat.com Link: http://lkml.kernel.org/r/20200707225021.200906-2-peterx@redhat.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-08-12 09:37:44 +08:00
*flt = handle_mm_fault(vma, ea, is_write ? FAULT_FLAG_WRITE : 0, NULL);
mm: avoid unnecessary page fault retires on shared memory types I observed that for each of the shared file-backed page faults, we're very likely to retry one more time for the 1st write fault upon no page. It's because we'll need to release the mmap lock for dirty rate limit purpose with balance_dirty_pages_ratelimited() (in fault_dirty_shared_page()). Then after that throttling we return VM_FAULT_RETRY. We did that probably because VM_FAULT_RETRY is the only way we can return to the fault handler at that time telling it we've released the mmap lock. However that's not ideal because it's very likely the fault does not need to be retried at all since the pgtable was well installed before the throttling, so the next continuous fault (including taking mmap read lock, walk the pgtable, etc.) could be in most cases unnecessary. It's not only slowing down page faults for shared file-backed, but also add more mmap lock contention which is in most cases not needed at all. To observe this, one could try to write to some shmem page and look at "pgfault" value in /proc/vmstat, then we should expect 2 counts for each shmem write simply because we retried, and vm event "pgfault" will capture that. To make it more efficient, add a new VM_FAULT_COMPLETED return code just to show that we've completed the whole fault and released the lock. It's also a hint that we should very possibly not need another fault immediately on this page because we've just completed it. This patch provides a ~12% perf boost on my aarch64 test VM with a simple program sequentially dirtying 400MB shmem file being mmap()ed and these are the time it needs: Before: 650.980 ms (+-1.94%) After: 569.396 ms (+-1.38%) I believe it could help more than that. We need some special care on GUP and the s390 pgfault handler (for gmap code before returning from pgfault), the rest changes in the page fault handlers should be relatively straightforward. Another thing to mention is that mm_account_fault() does take this new fault as a generic fault to be accounted, unlike VM_FAULT_RETRY. I explicitly didn't touch hmm_vma_fault() and break_ksm() because they do not handle VM_FAULT_RETRY even with existing code, so I'm literally keeping them as-is. Link: https://lkml.kernel.org/r/20220530183450.42886-1-peterx@redhat.com Signed-off-by: Peter Xu <peterx@redhat.com> Acked-by: Geert Uytterhoeven <geert@linux-m68k.org> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Acked-by: Vineet Gupta <vgupta@kernel.org> Acked-by: Guo Ren <guoren@kernel.org> Acked-by: Max Filippov <jcmvbkbc@gmail.com> Acked-by: Christian Borntraeger <borntraeger@linux.ibm.com> Acked-by: Michael Ellerman <mpe@ellerman.id.au> (powerpc) Acked-by: Catalin Marinas <catalin.marinas@arm.com> Reviewed-by: Alistair Popple <apopple@nvidia.com> Reviewed-by: Ingo Molnar <mingo@kernel.org> Acked-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk> [arm part] Acked-by: Heiko Carstens <hca@linux.ibm.com> Cc: Vasily Gorbik <gor@linux.ibm.com> Cc: Stafford Horne <shorne@gmail.com> Cc: David S. Miller <davem@davemloft.net> Cc: Johannes Berg <johannes@sipsolutions.net> Cc: Brian Cain <bcain@quicinc.com> Cc: Richard Henderson <rth@twiddle.net> Cc: Richard Weinberger <richard@nod.at> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Janosch Frank <frankja@linux.ibm.com> Cc: Albert Ou <aou@eecs.berkeley.edu> Cc: Anton Ivanov <anton.ivanov@cambridgegreys.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Borislav Petkov <bp@alien8.de> Cc: Sven Schnelle <svens@linux.ibm.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: James Bottomley <James.Bottomley@HansenPartnership.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Alexander Gordeev <agordeev@linux.ibm.com> Cc: Jonas Bonn <jonas@southpole.se> Cc: Will Deacon <will@kernel.org> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Michal Simek <monstr@monstr.eu> Cc: Matt Turner <mattst88@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: David Hildenbrand <david@redhat.com> Cc: Nicholas Piggin <npiggin@gmail.com> Cc: Palmer Dabbelt <palmer@dabbelt.com> Cc: Stefan Kristiansson <stefan.kristiansson@saunalahti.fi> Cc: Paul Walmsley <paul.walmsley@sifive.com> Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru> Cc: Chris Zankel <chris@zankel.net> Cc: Hugh Dickins <hughd@google.com> Cc: Dinh Nguyen <dinguyen@kernel.org> Cc: Rich Felker <dalias@libc.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Andy Lutomirski <luto@kernel.org> Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de> Cc: Helge Deller <deller@gmx.de> Cc: Yoshinori Sato <ysato@users.osdn.me> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2022-05-31 02:34:50 +08:00
/* The fault is fully completed (including releasing mmap lock) */
if (*flt & VM_FAULT_COMPLETED)
return 0;
if (unlikely(*flt & VM_FAULT_ERROR)) {
if (*flt & VM_FAULT_OOM) {
ret = -ENOMEM;
goto out_unlock;
vm: add VM_FAULT_SIGSEGV handling support The core VM already knows about VM_FAULT_SIGBUS, but cannot return a "you should SIGSEGV" error, because the SIGSEGV case was generally handled by the caller - usually the architecture fault handler. That results in lots of duplication - all the architecture fault handlers end up doing very similar "look up vma, check permissions, do retries etc" - but it generally works. However, there are cases where the VM actually wants to SIGSEGV, and applications _expect_ SIGSEGV. In particular, when accessing the stack guard page, libsigsegv expects a SIGSEGV. And it usually got one, because the stack growth is handled by that duplicated architecture fault handler. However, when the generic VM layer started propagating the error return from the stack expansion in commit fee7e49d4514 ("mm: propagate error from stack expansion even for guard page"), that now exposed the existing VM_FAULT_SIGBUS result to user space. And user space really expected SIGSEGV, not SIGBUS. To fix that case, we need to add a VM_FAULT_SIGSEGV, and teach all those duplicate architecture fault handlers about it. They all already have the code to handle SIGSEGV, so it's about just tying that new return value to the existing code, but it's all a bit annoying. This is the mindless minimal patch to do this. A more extensive patch would be to try to gather up the mostly shared fault handling logic into one generic helper routine, and long-term we really should do that cleanup. Just from this patch, you can generally see that most architectures just copied (directly or indirectly) the old x86 way of doing things, but in the meantime that original x86 model has been improved to hold the VM semaphore for shorter times etc and to handle VM_FAULT_RETRY and other "newer" things, so it would be a good idea to bring all those improvements to the generic case and teach other architectures about them too. Reported-and-tested-by: Takashi Iwai <tiwai@suse.de> Tested-by: Jan Engelhardt <jengelh@inai.de> Acked-by: Heiko Carstens <heiko.carstens@de.ibm.com> # "s390 still compiles and boots" Cc: linux-arch@vger.kernel.org Cc: stable@vger.kernel.org Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-01-30 02:51:32 +08:00
} else if (*flt & (VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV)) {
ret = -EFAULT;
goto out_unlock;
}
BUG();
}
out_unlock:
mmap locking API: use coccinelle to convert mmap_sem rwsem call sites This change converts the existing mmap_sem rwsem calls to use the new mmap locking API instead. The change is generated using coccinelle with the following rule: // spatch --sp-file mmap_lock_api.cocci --in-place --include-headers --dir . @@ expression mm; @@ ( -init_rwsem +mmap_init_lock | -down_write +mmap_write_lock | -down_write_killable +mmap_write_lock_killable | -down_write_trylock +mmap_write_trylock | -up_write +mmap_write_unlock | -downgrade_write +mmap_write_downgrade | -down_read +mmap_read_lock | -down_read_killable +mmap_read_lock_killable | -down_read_trylock +mmap_read_trylock | -up_read +mmap_read_unlock ) -(&mm->mmap_sem) +(mm) Signed-off-by: Michel Lespinasse <walken@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Daniel Jordan <daniel.m.jordan@oracle.com> Reviewed-by: Laurent Dufour <ldufour@linux.ibm.com> Reviewed-by: Vlastimil Babka <vbabka@suse.cz> Cc: Davidlohr Bueso <dbueso@suse.de> Cc: David Rientjes <rientjes@google.com> Cc: Hugh Dickins <hughd@google.com> Cc: Jason Gunthorpe <jgg@ziepe.ca> Cc: Jerome Glisse <jglisse@redhat.com> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Liam Howlett <Liam.Howlett@oracle.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ying Han <yinghan@google.com> Link: http://lkml.kernel.org/r/20200520052908.204642-5-walken@google.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-06-09 12:33:25 +08:00
mmap_read_unlock(mm);
return ret;
}
EXPORT_SYMBOL_GPL(copro_handle_mm_fault);
#ifdef CONFIG_PPC_64S_HASH_MMU
int copro_calculate_slb(struct mm_struct *mm, u64 ea, struct copro_slb *slb)
{
u64 vsid, vsidkey;
int psize, ssize;
switch (get_region_id(ea)) {
case USER_REGION_ID:
pr_devel("%s: 0x%llx -- USER_REGION_ID\n", __func__, ea);
if (mm == NULL)
return 1;
psize = get_slice_psize(mm, ea);
ssize = user_segment_size(ea);
vsid = get_user_vsid(&mm->context, ea, ssize);
vsidkey = SLB_VSID_USER;
break;
case VMALLOC_REGION_ID:
pr_devel("%s: 0x%llx -- VMALLOC_REGION_ID\n", __func__, ea);
psize = mmu_vmalloc_psize;
ssize = mmu_kernel_ssize;
vsid = get_kernel_vsid(ea, mmu_kernel_ssize);
vsidkey = SLB_VSID_KERNEL;
break;
case IO_REGION_ID:
pr_devel("%s: 0x%llx -- IO_REGION_ID\n", __func__, ea);
psize = mmu_io_psize;
ssize = mmu_kernel_ssize;
vsid = get_kernel_vsid(ea, mmu_kernel_ssize);
vsidkey = SLB_VSID_KERNEL;
break;
case LINEAR_MAP_REGION_ID:
pr_devel("%s: 0x%llx -- LINEAR_MAP_REGION_ID\n", __func__, ea);
psize = mmu_linear_psize;
ssize = mmu_kernel_ssize;
vsid = get_kernel_vsid(ea, mmu_kernel_ssize);
vsidkey = SLB_VSID_KERNEL;
break;
default:
pr_debug("%s: invalid region access at %016llx\n", __func__, ea);
return 1;
}
/* Bad address */
if (!vsid)
return 1;
vsid = (vsid << slb_vsid_shift(ssize)) | vsidkey;
vsid |= mmu_psize_defs[psize].sllp |
((ssize == MMU_SEGSIZE_1T) ? SLB_VSID_B_1T : 0);
slb->esid = (ea & (ssize == MMU_SEGSIZE_1T ? ESID_MASK_1T : ESID_MASK)) | SLB_ESID_V;
slb->vsid = vsid;
return 0;
}
EXPORT_SYMBOL_GPL(copro_calculate_slb);
void copro_flush_all_slbs(struct mm_struct *mm)
{
#ifdef CONFIG_SPU_BASE
spu_flush_all_slbs(mm);
#endif
cxl_slbia(mm);
}
EXPORT_SYMBOL_GPL(copro_flush_all_slbs);
#endif