1
linux/arch/hexagon/mm/vm_fault.c

178 lines
3.8 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-only
/*
* Memory fault handling for Hexagon
*
* Copyright (c) 2010-2011, The Linux Foundation. All rights reserved.
*/
/*
* Page fault handling for the Hexagon Virtual Machine.
* Can also be called by a native port emulating the HVM
* execptions.
*/
#include <asm/traps.h>
hexagon: vm_fault: include asm/vm_fault.h for prototypes Clang warns: arch/hexagon/mm/vm_fault.c:157:6: warning: no previous prototype for function 'read_protection_fault' [-Wmissing-prototypes] 157 | void read_protection_fault(struct pt_regs *regs) | ^ arch/hexagon/mm/vm_fault.c:157:1: note: declare 'static' if the function is not intended to be used outside of this translation unit 157 | void read_protection_fault(struct pt_regs *regs) | ^ | static arch/hexagon/mm/vm_fault.c:164:6: warning: no previous prototype for function 'write_protection_fault' [-Wmissing-prototypes] 164 | void write_protection_fault(struct pt_regs *regs) | ^ arch/hexagon/mm/vm_fault.c:164:1: note: declare 'static' if the function is not intended to be used outside of this translation unit 164 | void write_protection_fault(struct pt_regs *regs) | ^ | static arch/hexagon/mm/vm_fault.c:171:6: warning: no previous prototype for function 'execute_protection_fault' [-Wmissing-prototypes] 171 | void execute_protection_fault(struct pt_regs *regs) | ^ arch/hexagon/mm/vm_fault.c:171:1: note: declare 'static' if the function is not intended to be used outside of this translation unit 171 | void execute_protection_fault(struct pt_regs *regs) | ^ | static The prototypes for these functions are defined in asm/vm_fault.h, so include it to pick them up and silence the warnings. Link: https://lkml.kernel.org/r/20231130-hexagon-missing-prototypes-v1-6-5c34714afe9e@kernel.org Signed-off-by: Nathan Chancellor <nathan@kernel.org> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Brian Cain <bcain@quicinc.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-11-30 15:58:19 -07:00
#include <asm/vm_fault.h>
#include <linux/uaccess.h>
#include <linux/mm.h>
#include <linux/sched/signal.h>
#include <linux/signal.h>
#include <linux/extable.h>
#include <linux/hardirq.h>
#include <linux/perf_event.h>
/*
* Decode of hardware exception sends us to one of several
* entry points. At each, we generate canonical arguments
* for handling by the abstract memory management code.
*/
#define FLT_IFETCH -1
#define FLT_LOAD 0
#define FLT_STORE 1
/*
* Canonical page fault handler
*/
static void do_page_fault(unsigned long address, long cause, struct pt_regs *regs)
{
struct vm_area_struct *vma;
struct mm_struct *mm = current->mm;
int si_signo;
int si_code = SEGV_MAPERR;
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>
2018-08-17 15:44:47 -07:00
vm_fault_t fault;
const struct exception_table_entry *fixup;
mm: introduce FAULT_FLAG_DEFAULT Although there're tons of arch-specific page fault handlers, most of them are still sharing the same initial value of the page fault flags. Say, merely all of the page fault handlers would allow the fault to be retried, and they also allow the fault to respond to SIGKILL. Let's define a default value for the fault flags to replace those initial page fault flags that were copied over. With this, it'll be far easier to introduce new fault flag that can be used by all the architectures instead of touching all the archs. Signed-off-by: Peter Xu <peterx@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Tested-by: Brian Geffon <bgeffon@google.com> Reviewed-by: David Hildenbrand <david@redhat.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Bobby Powers <bobbypowers@gmail.com> Cc: Denis Plotnikov <dplotnikov@virtuozzo.com> Cc: "Dr . David Alan Gilbert" <dgilbert@redhat.com> Cc: Hugh Dickins <hughd@google.com> Cc: Jerome Glisse <jglisse@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: "Kirill A . Shutemov" <kirill@shutemov.name> Cc: Martin Cracauer <cracauer@cons.org> Cc: Marty McFadden <mcfadden8@llnl.gov> Cc: Matthew Wilcox <willy@infradead.org> Cc: Maya Gokhale <gokhale2@llnl.gov> Cc: Mel Gorman <mgorman@suse.de> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Mike Rapoport <rppt@linux.vnet.ibm.com> Cc: Pavel Emelyanov <xemul@openvz.org> Link: http://lkml.kernel.org/r/20200220160238.9694-1-peterx@redhat.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-04-01 21:08:37 -07:00
unsigned int flags = FAULT_FLAG_DEFAULT;
/*
* If we're in an interrupt or have no user context,
* then must not take the fault.
*/
if (unlikely(in_interrupt() || !mm))
goto no_context;
local_irq_enable();
if (user_mode(regs))
flags |= FAULT_FLAG_USER;
perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
retry:
vma = lock_mm_and_find_vma(mm, address, regs);
if (unlikely(!vma))
goto bad_area_nosemaphore;
/* Address space is OK. Now check access rights. */
si_code = SEGV_ACCERR;
switch (cause) {
case FLT_IFETCH:
if (!(vma->vm_flags & VM_EXEC))
goto bad_area;
break;
case FLT_LOAD:
if (!(vma->vm_flags & VM_READ))
goto bad_area;
break;
case FLT_STORE:
if (!(vma->vm_flags & VM_WRITE))
goto bad_area;
flags |= FAULT_FLAG_WRITE;
break;
}
fault = handle_mm_fault(vma, address, flags, regs);
if (fault_signal_pending(fault, regs)) {
if (!user_mode(regs))
goto no_context;
return;
}
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>
2022-05-30 11:34:50 -07:00
/* The fault is fully completed (including releasing mmap lock) */
if (fault & VM_FAULT_COMPLETED)
return;
/* The most common case -- we are done. */
if (likely(!(fault & VM_FAULT_ERROR))) {
if (fault & VM_FAULT_RETRY) {
flags |= FAULT_FLAG_TRIED;
goto retry;
}
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>
2020-06-08 21:33:25 -07:00
mmap_read_unlock(mm);
return;
}
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>
2020-06-08 21:33:25 -07:00
mmap_read_unlock(mm);
/* Handle copyin/out exception cases */
if (!user_mode(regs))
goto no_context;
if (fault & VM_FAULT_OOM) {
pagefault_out_of_memory();
return;
}
/* User-mode address is in the memory map, but we are
* unable to fix up the page fault.
*/
if (fault & VM_FAULT_SIGBUS) {
si_signo = SIGBUS;
si_code = BUS_ADRERR;
}
/* Address is not in the memory map */
else {
si_signo = SIGSEGV;
si_code = SEGV_ACCERR;
}
force_sig_fault(si_signo, si_code, (void __user *)address);
return;
bad_area:
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>
2020-06-08 21:33:25 -07:00
mmap_read_unlock(mm);
bad_area_nosemaphore:
if (user_mode(regs)) {
force_sig_fault(SIGSEGV, si_code, (void __user *)address);
return;
}
/* Kernel-mode fault falls through */
no_context:
fixup = search_exception_tables(pt_elr(regs));
if (fixup) {
pt_set_elr(regs, fixup->fixup);
return;
}
/* Things are looking very, very bad now */
bust_spinlocks(1);
printk(KERN_EMERG "Unable to handle kernel paging request at "
"virtual address 0x%08lx, regs %p\n", address, regs);
die("Bad Kernel VA", regs, SIGKILL);
}
void read_protection_fault(struct pt_regs *regs)
{
unsigned long badvadr = pt_badva(regs);
do_page_fault(badvadr, FLT_LOAD, regs);
}
void write_protection_fault(struct pt_regs *regs)
{
unsigned long badvadr = pt_badva(regs);
do_page_fault(badvadr, FLT_STORE, regs);
}
void execute_protection_fault(struct pt_regs *regs)
{
unsigned long badvadr = pt_badva(regs);
do_page_fault(badvadr, FLT_IFETCH, regs);
}