iv/linux
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

x86/mm: Break out kernel address space handling

Browse Source 
The page fault handler (__do_page_fault())  basically has two sections:
one for handling faults in the kernel portion of the address space
and another for faults in the user portion of the address space.

But, these two parts don't stick out that well.  Let's make that more
clear from code separation and naming.  Pull kernel fault
handling into its own helper, and reflect that naming by renaming
spurious_fault() -> spurious_kernel_fault().

Also, rewrite the vmalloc() handling comment a bit.  It was a bit
stale and also glossed over the reserved bit handling.

Cc: x86@kernel.org
Cc: Jann Horn <jannh@google.com>
Cc: Sean Christopherson <sean.j.christopherson@intel.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Andy Lutomirski <luto@kernel.org>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20180928160222.401F4E10@viggo.jf.intel.com
This commit is contained in:
Dave Hansen 2018-09-28 09:02:22 -07:00 committed by Peter Zijlstra
parent 164477c233
commit 8fed620000
1 changed files with 62 additions and 39 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

101
arch/x86/mm/fault.c
View File

@ -1032,7 +1032,7 @@ mm_fault_error(struct pt_regs *regs, unsigned long error_code,
}
}
static int spurious_fault_check(unsigned long error_code, pte_t *pte)
static int spurious_kernel_fault_check(unsigned long error_code, pte_t *pte)
{
if ((error_code & X86_PF_WRITE) && !pte_write(*pte))
return 0;
@ -1071,7 +1071,7 @@ static int spurious_fault_check(unsigned long error_code, pte_t *pte)
* (Optional Invalidation).
*/
static noinline int
spurious_fault(unsigned long error_code, unsigned long address)
spurious_kernel_fault(unsigned long error_code, unsigned long address)
{
pgd_t *pgd;
p4d_t *p4d;
@ -1102,27 +1102,27 @@ spurious_fault(unsigned long error_code, unsigned long address)
return 0;
if (p4d_large(*p4d))
return spurious_fault_check(error_code, (pte_t *) p4d);
return spurious_kernel_fault_check(error_code, (pte_t *) p4d);
pud = pud_offset(p4d, address);
if (!pud_present(*pud))
return 0;
if (pud_large(*pud))
return spurious_fault_check(error_code, (pte_t *) pud);
return spurious_kernel_fault_check(error_code, (pte_t *) pud);
pmd = pmd_offset(pud, address);
if (!pmd_present(*pmd))
return 0;
if (pmd_large(*pmd))
return spurious_fault_check(error_code, (pte_t *) pmd);
return spurious_kernel_fault_check(error_code, (pte_t *) pmd);
pte = pte_offset_kernel(pmd, address);
if (!pte_present(*pte))
return 0;
ret = spurious_fault_check(error_code, pte);
ret = spurious_kernel_fault_check(error_code, pte);
if (!ret)
return 0;
@ -1130,12 +1130,12 @@ spurious_fault(unsigned long error_code, unsigned long address)
* Make sure we have permissions in PMD.
* If not, then there's a bug in the page tables:
*/
ret = spurious_fault_check(error_code, (pte_t *) pmd);
ret = spurious_kernel_fault_check(error_code, (pte_t *) pmd);
WARN_ONCE(!ret, "PMD has incorrect permission bits\n");
return ret;
}
NOKPROBE_SYMBOL(spurious_fault);
NOKPROBE_SYMBOL(spurious_kernel_fault);
int show_unhandled_signals = 1;
@ -1202,6 +1202,58 @@ static inline bool smap_violation(int error_code, struct pt_regs *regs)
return true;
}
/*
* Called for all faults where 'address' is part of the kernel address
* space. Might get called for faults that originate from *code* that
* ran in userspace or the kernel.
*/
static void
do_kern_addr_fault(struct pt_regs *regs, unsigned long hw_error_code,
unsigned long address)
{
/*
* We can fault-in kernel-space virtual memory on-demand. The
* 'reference' page table is init_mm.pgd.
*
* NOTE! We MUST NOT take any locks for this case. We may
* be in an interrupt or a critical region, and should
* only copy the information from the master page table,
* nothing more.
*
* Before doing this on-demand faulting, ensure that the
* fault is not any of the following:
* 1. A fault on a PTE with a reserved bit set.
* 2. A fault caused by a user-mode access. (Do not demand-
* fault kernel memory due to user-mode accesses).
* 3. A fault caused by a page-level protection violation.
* (A demand fault would be on a non-present page which
* would have X86_PF_PROT==0).
*/
if (!(hw_error_code & (X86_PF_RSVD | X86_PF_USER | X86_PF_PROT))) {
if (vmalloc_fault(address) >= 0)
return;
}
/* Was the fault spurious, caused by lazy TLB invalidation? */
if (spurious_kernel_fault(hw_error_code, address))
return;
/* kprobes don't want to hook the spurious faults: */
if (kprobes_fault(regs))
return;
/*
* Note, despite being a "bad area", there are quite a few
* acceptable reasons to get here, such as erratum fixups
* and handling kernel code that can fault, like get_user().
*
* Don't take the mm semaphore here. If we fixup a prefetch
* fault we could otherwise deadlock:
*/
bad_area_nosemaphore(regs, hw_error_code, address, NULL);
}
NOKPROBE_SYMBOL(do_kern_addr_fault);
/*
* This routine handles page faults. It determines the address,
* and the problem, and then passes it off to one of the appropriate
@ -1227,38 +1279,9 @@ __do_page_fault(struct pt_regs *regs, unsigned long hw_error_code,
if (unlikely(kmmio_fault(regs, address)))
return;
/*
* We fault-in kernel-space virtual memory on-demand. The
* 'reference' page table is init_mm.pgd.
*
* NOTE! We MUST NOT take any locks for this case. We may
* be in an interrupt or a critical region, and should
* only copy the information from the master page table,
* nothing more.
*
* This verifies that the fault happens in kernel space
* (hw_error_code & 4) == 0, and that the fault was not a
* protection error (hw_error_code & 9) == 0.
*/
/* Was the fault on kernel-controlled part of the address space? */
if (unlikely(fault_in_kernel_space(address))) {
if (!(hw_error_code & (X86_PF_RSVD | X86_PF_USER | X86_PF_PROT))) {
if (vmalloc_fault(address) >= 0)
return;
}
/* Can handle a stale RO->RW TLB: */
if (spurious_fault(hw_error_code, address))
return;
/* kprobes don't want to hook the spurious faults: */
if (kprobes_fault(regs))
return;
/*
* Don't take the mm semaphore here. If we fixup a prefetch
* fault we could otherwise deadlock:
*/
bad_area_nosemaphore(regs, hw_error_code, address, NULL);
do_kern_addr_fault(regs, hw_error_code, address);
return;
}