forked from Minki/linux
a2beb5f1ef
Here're the last pieces of page fault accounting that were still done outside handle_mm_fault() where we still have regs==NULL when calling handle_mm_fault(): arch/powerpc/mm/copro_fault.c: copro_handle_mm_fault arch/sparc/mm/fault_32.c: force_user_fault arch/um/kernel/trap.c: handle_page_fault mm/gup.c: faultin_page fixup_user_fault mm/hmm.c: hmm_vma_fault mm/ksm.c: break_ksm Some of them has the issue of duplicated accounting for page fault retries. Some of them didn't do the accounting at all. This patch cleans all these up by letting handle_mm_fault() to do per-task page fault accounting even if regs==NULL (though we'll still skip the perf event accountings). With that, we can safely remove all the outliers now. There's another functional change in that now we account the page faults to the caller of gup, rather than the task_struct that passed into the gup code. More information of this can be found at [1]. After this patch, below things should never be touched again outside handle_mm_fault(): - task_struct.[maj|min]_flt - PERF_COUNT_SW_PAGE_FAULTS_[MAJ|MIN] [1] https://lore.kernel.org/lkml/CAHk-=wj_V2Tps2QrMn20_W0OJF9xqNh52XSGA42s-ZJ8Y+GyKw@mail.gmail.com/ 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/20200707225021.200906-25-peterx@redhat.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
318 lines
7.9 KiB
C
318 lines
7.9 KiB
C
// SPDX-License-Identifier: GPL-2.0
|
|
/*
|
|
* Copyright (C) 2000 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
|
|
*/
|
|
|
|
#include <linux/mm.h>
|
|
#include <linux/sched/signal.h>
|
|
#include <linux/hardirq.h>
|
|
#include <linux/module.h>
|
|
#include <linux/uaccess.h>
|
|
#include <linux/sched/debug.h>
|
|
#include <asm/current.h>
|
|
#include <asm/tlbflush.h>
|
|
#include <arch.h>
|
|
#include <as-layout.h>
|
|
#include <kern_util.h>
|
|
#include <os.h>
|
|
#include <skas.h>
|
|
|
|
/*
|
|
* Note this is constrained to return 0, -EFAULT, -EACCES, -ENOMEM by
|
|
* segv().
|
|
*/
|
|
int handle_page_fault(unsigned long address, unsigned long ip,
|
|
int is_write, int is_user, int *code_out)
|
|
{
|
|
struct mm_struct *mm = current->mm;
|
|
struct vm_area_struct *vma;
|
|
pmd_t *pmd;
|
|
pte_t *pte;
|
|
int err = -EFAULT;
|
|
unsigned int flags = FAULT_FLAG_DEFAULT;
|
|
|
|
*code_out = SEGV_MAPERR;
|
|
|
|
/*
|
|
* If the fault was with pagefaults disabled, don't take the fault, just
|
|
* fail.
|
|
*/
|
|
if (faulthandler_disabled())
|
|
goto out_nosemaphore;
|
|
|
|
if (is_user)
|
|
flags |= FAULT_FLAG_USER;
|
|
retry:
|
|
mmap_read_lock(mm);
|
|
vma = find_vma(mm, address);
|
|
if (!vma)
|
|
goto out;
|
|
else if (vma->vm_start <= address)
|
|
goto good_area;
|
|
else if (!(vma->vm_flags & VM_GROWSDOWN))
|
|
goto out;
|
|
else if (is_user && !ARCH_IS_STACKGROW(address))
|
|
goto out;
|
|
else if (expand_stack(vma, address))
|
|
goto out;
|
|
|
|
good_area:
|
|
*code_out = SEGV_ACCERR;
|
|
if (is_write) {
|
|
if (!(vma->vm_flags & VM_WRITE))
|
|
goto out;
|
|
flags |= FAULT_FLAG_WRITE;
|
|
} else {
|
|
/* Don't require VM_READ|VM_EXEC for write faults! */
|
|
if (!(vma->vm_flags & (VM_READ | VM_EXEC)))
|
|
goto out;
|
|
}
|
|
|
|
do {
|
|
vm_fault_t fault;
|
|
|
|
fault = handle_mm_fault(vma, address, flags, NULL);
|
|
|
|
if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
|
|
goto out_nosemaphore;
|
|
|
|
if (unlikely(fault & VM_FAULT_ERROR)) {
|
|
if (fault & VM_FAULT_OOM) {
|
|
goto out_of_memory;
|
|
} else if (fault & VM_FAULT_SIGSEGV) {
|
|
goto out;
|
|
} else if (fault & VM_FAULT_SIGBUS) {
|
|
err = -EACCES;
|
|
goto out;
|
|
}
|
|
BUG();
|
|
}
|
|
if (flags & FAULT_FLAG_ALLOW_RETRY) {
|
|
if (fault & VM_FAULT_RETRY) {
|
|
flags |= FAULT_FLAG_TRIED;
|
|
|
|
goto retry;
|
|
}
|
|
}
|
|
|
|
pmd = pmd_off(mm, address);
|
|
pte = pte_offset_kernel(pmd, address);
|
|
} while (!pte_present(*pte));
|
|
err = 0;
|
|
/*
|
|
* The below warning was added in place of
|
|
* pte_mkyoung(); if (is_write) pte_mkdirty();
|
|
* If it's triggered, we'd see normally a hang here (a clean pte is
|
|
* marked read-only to emulate the dirty bit).
|
|
* However, the generic code can mark a PTE writable but clean on a
|
|
* concurrent read fault, triggering this harmlessly. So comment it out.
|
|
*/
|
|
#if 0
|
|
WARN_ON(!pte_young(*pte) || (is_write && !pte_dirty(*pte)));
|
|
#endif
|
|
flush_tlb_page(vma, address);
|
|
out:
|
|
mmap_read_unlock(mm);
|
|
out_nosemaphore:
|
|
return err;
|
|
|
|
out_of_memory:
|
|
/*
|
|
* We ran out of memory, call the OOM killer, and return the userspace
|
|
* (which will retry the fault, or kill us if we got oom-killed).
|
|
*/
|
|
mmap_read_unlock(mm);
|
|
if (!is_user)
|
|
goto out_nosemaphore;
|
|
pagefault_out_of_memory();
|
|
return 0;
|
|
}
|
|
EXPORT_SYMBOL(handle_page_fault);
|
|
|
|
static void show_segv_info(struct uml_pt_regs *regs)
|
|
{
|
|
struct task_struct *tsk = current;
|
|
struct faultinfo *fi = UPT_FAULTINFO(regs);
|
|
|
|
if (!unhandled_signal(tsk, SIGSEGV))
|
|
return;
|
|
|
|
if (!printk_ratelimit())
|
|
return;
|
|
|
|
printk("%s%s[%d]: segfault at %lx ip %px sp %px error %x",
|
|
task_pid_nr(tsk) > 1 ? KERN_INFO : KERN_EMERG,
|
|
tsk->comm, task_pid_nr(tsk), FAULT_ADDRESS(*fi),
|
|
(void *)UPT_IP(regs), (void *)UPT_SP(regs),
|
|
fi->error_code);
|
|
|
|
print_vma_addr(KERN_CONT " in ", UPT_IP(regs));
|
|
printk(KERN_CONT "\n");
|
|
}
|
|
|
|
static void bad_segv(struct faultinfo fi, unsigned long ip)
|
|
{
|
|
current->thread.arch.faultinfo = fi;
|
|
force_sig_fault(SIGSEGV, SEGV_ACCERR, (void __user *) FAULT_ADDRESS(fi));
|
|
}
|
|
|
|
void fatal_sigsegv(void)
|
|
{
|
|
force_sigsegv(SIGSEGV);
|
|
do_signal(¤t->thread.regs);
|
|
/*
|
|
* This is to tell gcc that we're not returning - do_signal
|
|
* can, in general, return, but in this case, it's not, since
|
|
* we just got a fatal SIGSEGV queued.
|
|
*/
|
|
os_dump_core();
|
|
}
|
|
|
|
/**
|
|
* segv_handler() - the SIGSEGV handler
|
|
* @sig: the signal number
|
|
* @unused_si: the signal info struct; unused in this handler
|
|
* @regs: the ptrace register information
|
|
*
|
|
* The handler first extracts the faultinfo from the UML ptrace regs struct.
|
|
* If the userfault did not happen in an UML userspace process, bad_segv is called.
|
|
* Otherwise the signal did happen in a cloned userspace process, handle it.
|
|
*/
|
|
void segv_handler(int sig, struct siginfo *unused_si, struct uml_pt_regs *regs)
|
|
{
|
|
struct faultinfo * fi = UPT_FAULTINFO(regs);
|
|
|
|
if (UPT_IS_USER(regs) && !SEGV_IS_FIXABLE(fi)) {
|
|
show_segv_info(regs);
|
|
bad_segv(*fi, UPT_IP(regs));
|
|
return;
|
|
}
|
|
segv(*fi, UPT_IP(regs), UPT_IS_USER(regs), regs);
|
|
}
|
|
|
|
/*
|
|
* We give a *copy* of the faultinfo in the regs to segv.
|
|
* This must be done, since nesting SEGVs could overwrite
|
|
* the info in the regs. A pointer to the info then would
|
|
* give us bad data!
|
|
*/
|
|
unsigned long segv(struct faultinfo fi, unsigned long ip, int is_user,
|
|
struct uml_pt_regs *regs)
|
|
{
|
|
jmp_buf *catcher;
|
|
int si_code;
|
|
int err;
|
|
int is_write = FAULT_WRITE(fi);
|
|
unsigned long address = FAULT_ADDRESS(fi);
|
|
|
|
if (!is_user && regs)
|
|
current->thread.segv_regs = container_of(regs, struct pt_regs, regs);
|
|
|
|
if (!is_user && (address >= start_vm) && (address < end_vm)) {
|
|
flush_tlb_kernel_vm();
|
|
goto out;
|
|
}
|
|
else if (current->mm == NULL) {
|
|
show_regs(container_of(regs, struct pt_regs, regs));
|
|
panic("Segfault with no mm");
|
|
}
|
|
else if (!is_user && address > PAGE_SIZE && address < TASK_SIZE) {
|
|
show_regs(container_of(regs, struct pt_regs, regs));
|
|
panic("Kernel tried to access user memory at addr 0x%lx, ip 0x%lx",
|
|
address, ip);
|
|
}
|
|
|
|
if (SEGV_IS_FIXABLE(&fi))
|
|
err = handle_page_fault(address, ip, is_write, is_user,
|
|
&si_code);
|
|
else {
|
|
err = -EFAULT;
|
|
/*
|
|
* A thread accessed NULL, we get a fault, but CR2 is invalid.
|
|
* This code is used in __do_copy_from_user() of TT mode.
|
|
* XXX tt mode is gone, so maybe this isn't needed any more
|
|
*/
|
|
address = 0;
|
|
}
|
|
|
|
catcher = current->thread.fault_catcher;
|
|
if (!err)
|
|
goto out;
|
|
else if (catcher != NULL) {
|
|
current->thread.fault_addr = (void *) address;
|
|
UML_LONGJMP(catcher, 1);
|
|
}
|
|
else if (current->thread.fault_addr != NULL)
|
|
panic("fault_addr set but no fault catcher");
|
|
else if (!is_user && arch_fixup(ip, regs))
|
|
goto out;
|
|
|
|
if (!is_user) {
|
|
show_regs(container_of(regs, struct pt_regs, regs));
|
|
panic("Kernel mode fault at addr 0x%lx, ip 0x%lx",
|
|
address, ip);
|
|
}
|
|
|
|
show_segv_info(regs);
|
|
|
|
if (err == -EACCES) {
|
|
current->thread.arch.faultinfo = fi;
|
|
force_sig_fault(SIGBUS, BUS_ADRERR, (void __user *)address);
|
|
} else {
|
|
BUG_ON(err != -EFAULT);
|
|
current->thread.arch.faultinfo = fi;
|
|
force_sig_fault(SIGSEGV, si_code, (void __user *) address);
|
|
}
|
|
|
|
out:
|
|
if (regs)
|
|
current->thread.segv_regs = NULL;
|
|
|
|
return 0;
|
|
}
|
|
|
|
void relay_signal(int sig, struct siginfo *si, struct uml_pt_regs *regs)
|
|
{
|
|
int code, err;
|
|
if (!UPT_IS_USER(regs)) {
|
|
if (sig == SIGBUS)
|
|
printk(KERN_ERR "Bus error - the host /dev/shm or /tmp "
|
|
"mount likely just ran out of space\n");
|
|
panic("Kernel mode signal %d", sig);
|
|
}
|
|
|
|
arch_examine_signal(sig, regs);
|
|
|
|
/* Is the signal layout for the signal known?
|
|
* Signal data must be scrubbed to prevent information leaks.
|
|
*/
|
|
code = si->si_code;
|
|
err = si->si_errno;
|
|
if ((err == 0) && (siginfo_layout(sig, code) == SIL_FAULT)) {
|
|
struct faultinfo *fi = UPT_FAULTINFO(regs);
|
|
current->thread.arch.faultinfo = *fi;
|
|
force_sig_fault(sig, code, (void __user *)FAULT_ADDRESS(*fi));
|
|
} else {
|
|
printk(KERN_ERR "Attempted to relay unknown signal %d (si_code = %d) with errno %d\n",
|
|
sig, code, err);
|
|
force_sig(sig);
|
|
}
|
|
}
|
|
|
|
void bus_handler(int sig, struct siginfo *si, struct uml_pt_regs *regs)
|
|
{
|
|
if (current->thread.fault_catcher != NULL)
|
|
UML_LONGJMP(current->thread.fault_catcher, 1);
|
|
else
|
|
relay_signal(sig, si, regs);
|
|
}
|
|
|
|
void winch(int sig, struct siginfo *unused_si, struct uml_pt_regs *regs)
|
|
{
|
|
do_IRQ(WINCH_IRQ, regs);
|
|
}
|
|
|
|
void trap_init(void)
|
|
{
|
|
}
|