mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-05 16:06:42 +07:00
cdd6c482c9
Bye-bye Performance Counters, welcome Performance Events! In the past few months the perfcounters subsystem has grown out its initial role of counting hardware events, and has become (and is becoming) a much broader generic event enumeration, reporting, logging, monitoring, analysis facility. Naming its core object 'perf_counter' and naming the subsystem 'perfcounters' has become more and more of a misnomer. With pending code like hw-breakpoints support the 'counter' name is less and less appropriate. All in one, we've decided to rename the subsystem to 'performance events' and to propagate this rename through all fields, variables and API names. (in an ABI compatible fashion) The word 'event' is also a bit shorter than 'counter' - which makes it slightly more convenient to write/handle as well. Thanks goes to Stephane Eranian who first observed this misnomer and suggested a rename. User-space tooling and ABI compatibility is not affected - this patch should be function-invariant. (Also, defconfigs were not touched to keep the size down.) This patch has been generated via the following script: FILES=$(find * -type f | grep -vE 'oprofile|[^K]config') sed -i \ -e 's/PERF_EVENT_/PERF_RECORD_/g' \ -e 's/PERF_COUNTER/PERF_EVENT/g' \ -e 's/perf_counter/perf_event/g' \ -e 's/nb_counters/nb_events/g' \ -e 's/swcounter/swevent/g' \ -e 's/tpcounter_event/tp_event/g' \ $FILES for N in $(find . -name perf_counter.[ch]); do M=$(echo $N | sed 's/perf_counter/perf_event/g') mv $N $M done FILES=$(find . -name perf_event.*) sed -i \ -e 's/COUNTER_MASK/REG_MASK/g' \ -e 's/COUNTER/EVENT/g' \ -e 's/\<event\>/event_id/g' \ -e 's/counter/event/g' \ -e 's/Counter/Event/g' \ $FILES ... to keep it as correct as possible. This script can also be used by anyone who has pending perfcounters patches - it converts a Linux kernel tree over to the new naming. We tried to time this change to the point in time where the amount of pending patches is the smallest: the end of the merge window. Namespace clashes were fixed up in a preparatory patch - and some stylistic fallout will be fixed up in a subsequent patch. ( NOTE: 'counters' are still the proper terminology when we deal with hardware registers - and these sed scripts are a bit over-eager in renaming them. I've undone some of that, but in case there's something left where 'counter' would be better than 'event' we can undo that on an individual basis instead of touching an otherwise nicely automated patch. ) Suggested-by: Stephane Eranian <eranian@google.com> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Acked-by: Paul Mackerras <paulus@samba.org> Reviewed-by: Arjan van de Ven <arjan@linux.intel.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: David Howells <dhowells@redhat.com> Cc: Kyle McMartin <kyle@mcmartin.ca> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: "David S. Miller" <davem@davemloft.net> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: <linux-arch@vger.kernel.org> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
378 lines
8.5 KiB
C
378 lines
8.5 KiB
C
/*
|
|
* Page fault handler for SH with an MMU.
|
|
*
|
|
* Copyright (C) 1999 Niibe Yutaka
|
|
* Copyright (C) 2003 - 2009 Paul Mundt
|
|
*
|
|
* Based on linux/arch/i386/mm/fault.c:
|
|
* Copyright (C) 1995 Linus Torvalds
|
|
*
|
|
* This file is subject to the terms and conditions of the GNU General Public
|
|
* License. See the file "COPYING" in the main directory of this archive
|
|
* for more details.
|
|
*/
|
|
#include <linux/kernel.h>
|
|
#include <linux/mm.h>
|
|
#include <linux/hardirq.h>
|
|
#include <linux/kprobes.h>
|
|
#include <linux/perf_event.h>
|
|
#include <asm/io_trapped.h>
|
|
#include <asm/system.h>
|
|
#include <asm/mmu_context.h>
|
|
#include <asm/tlbflush.h>
|
|
|
|
static inline int notify_page_fault(struct pt_regs *regs, int trap)
|
|
{
|
|
int ret = 0;
|
|
|
|
if (kprobes_built_in() && !user_mode(regs)) {
|
|
preempt_disable();
|
|
if (kprobe_running() && kprobe_fault_handler(regs, trap))
|
|
ret = 1;
|
|
preempt_enable();
|
|
}
|
|
|
|
return ret;
|
|
}
|
|
|
|
static inline pmd_t *vmalloc_sync_one(pgd_t *pgd, unsigned long address)
|
|
{
|
|
unsigned index = pgd_index(address);
|
|
pgd_t *pgd_k;
|
|
pud_t *pud, *pud_k;
|
|
pmd_t *pmd, *pmd_k;
|
|
|
|
pgd += index;
|
|
pgd_k = init_mm.pgd + index;
|
|
|
|
if (!pgd_present(*pgd_k))
|
|
return NULL;
|
|
|
|
pud = pud_offset(pgd, address);
|
|
pud_k = pud_offset(pgd_k, address);
|
|
if (!pud_present(*pud_k))
|
|
return NULL;
|
|
|
|
pmd = pmd_offset(pud, address);
|
|
pmd_k = pmd_offset(pud_k, address);
|
|
if (!pmd_present(*pmd_k))
|
|
return NULL;
|
|
|
|
if (!pmd_present(*pmd))
|
|
set_pmd(pmd, *pmd_k);
|
|
else {
|
|
/*
|
|
* The page tables are fully synchronised so there must
|
|
* be another reason for the fault. Return NULL here to
|
|
* signal that we have not taken care of the fault.
|
|
*/
|
|
BUG_ON(pmd_page(*pmd) != pmd_page(*pmd_k));
|
|
return NULL;
|
|
}
|
|
|
|
return pmd_k;
|
|
}
|
|
|
|
/*
|
|
* Handle a fault on the vmalloc or module mapping area
|
|
*/
|
|
static noinline int vmalloc_fault(unsigned long address)
|
|
{
|
|
pgd_t *pgd_k;
|
|
pmd_t *pmd_k;
|
|
pte_t *pte_k;
|
|
|
|
/* Make sure we are in vmalloc/module/P3 area: */
|
|
if (!(address >= VMALLOC_START && address < P3_ADDR_MAX))
|
|
return -1;
|
|
|
|
/*
|
|
* Synchronize this task's top level page-table
|
|
* with the 'reference' page table.
|
|
*
|
|
* Do _not_ use "current" here. We might be inside
|
|
* an interrupt in the middle of a task switch..
|
|
*/
|
|
pgd_k = get_TTB();
|
|
pmd_k = vmalloc_sync_one(pgd_k, address);
|
|
if (!pmd_k)
|
|
return -1;
|
|
|
|
pte_k = pte_offset_kernel(pmd_k, address);
|
|
if (!pte_present(*pte_k))
|
|
return -1;
|
|
|
|
return 0;
|
|
}
|
|
|
|
static int fault_in_kernel_space(unsigned long address)
|
|
{
|
|
return address >= TASK_SIZE;
|
|
}
|
|
|
|
/*
|
|
* This routine handles page faults. It determines the address,
|
|
* and the problem, and then passes it off to one of the appropriate
|
|
* routines.
|
|
*/
|
|
asmlinkage void __kprobes do_page_fault(struct pt_regs *regs,
|
|
unsigned long writeaccess,
|
|
unsigned long address)
|
|
{
|
|
unsigned long vec;
|
|
struct task_struct *tsk;
|
|
struct mm_struct *mm;
|
|
struct vm_area_struct * vma;
|
|
int si_code;
|
|
int fault;
|
|
siginfo_t info;
|
|
|
|
tsk = current;
|
|
mm = tsk->mm;
|
|
si_code = SEGV_MAPERR;
|
|
vec = lookup_exception_vector();
|
|
|
|
/*
|
|
* 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.
|
|
*/
|
|
if (unlikely(fault_in_kernel_space(address))) {
|
|
if (vmalloc_fault(address) >= 0)
|
|
return;
|
|
if (notify_page_fault(regs, vec))
|
|
return;
|
|
|
|
goto bad_area_nosemaphore;
|
|
}
|
|
|
|
if (unlikely(notify_page_fault(regs, vec)))
|
|
return;
|
|
|
|
/* Only enable interrupts if they were on before the fault */
|
|
if ((regs->sr & SR_IMASK) != SR_IMASK)
|
|
local_irq_enable();
|
|
|
|
perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, 0, regs, address);
|
|
|
|
/*
|
|
* If we're in an interrupt, have no user context or are running
|
|
* in an atomic region then we must not take the fault:
|
|
*/
|
|
if (in_atomic() || !mm)
|
|
goto no_context;
|
|
|
|
down_read(&mm->mmap_sem);
|
|
|
|
vma = find_vma(mm, address);
|
|
if (!vma)
|
|
goto bad_area;
|
|
if (vma->vm_start <= address)
|
|
goto good_area;
|
|
if (!(vma->vm_flags & VM_GROWSDOWN))
|
|
goto bad_area;
|
|
if (expand_stack(vma, address))
|
|
goto bad_area;
|
|
|
|
/*
|
|
* Ok, we have a good vm_area for this memory access, so
|
|
* we can handle it..
|
|
*/
|
|
good_area:
|
|
si_code = SEGV_ACCERR;
|
|
if (writeaccess) {
|
|
if (!(vma->vm_flags & VM_WRITE))
|
|
goto bad_area;
|
|
} else {
|
|
if (!(vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE)))
|
|
goto bad_area;
|
|
}
|
|
|
|
/*
|
|
* If for any reason at all we couldn't handle the fault,
|
|
* make sure we exit gracefully rather than endlessly redo
|
|
* the fault.
|
|
*/
|
|
survive:
|
|
fault = handle_mm_fault(mm, vma, address, writeaccess ? FAULT_FLAG_WRITE : 0);
|
|
if (unlikely(fault & VM_FAULT_ERROR)) {
|
|
if (fault & VM_FAULT_OOM)
|
|
goto out_of_memory;
|
|
else if (fault & VM_FAULT_SIGBUS)
|
|
goto do_sigbus;
|
|
BUG();
|
|
}
|
|
if (fault & VM_FAULT_MAJOR) {
|
|
tsk->maj_flt++;
|
|
perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, 0,
|
|
regs, address);
|
|
} else {
|
|
tsk->min_flt++;
|
|
perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, 0,
|
|
regs, address);
|
|
}
|
|
|
|
up_read(&mm->mmap_sem);
|
|
return;
|
|
|
|
/*
|
|
* Something tried to access memory that isn't in our memory map..
|
|
* Fix it, but check if it's kernel or user first..
|
|
*/
|
|
bad_area:
|
|
up_read(&mm->mmap_sem);
|
|
|
|
bad_area_nosemaphore:
|
|
if (user_mode(regs)) {
|
|
info.si_signo = SIGSEGV;
|
|
info.si_errno = 0;
|
|
info.si_code = si_code;
|
|
info.si_addr = (void *) address;
|
|
force_sig_info(SIGSEGV, &info, tsk);
|
|
return;
|
|
}
|
|
|
|
no_context:
|
|
/* Are we prepared to handle this kernel fault? */
|
|
if (fixup_exception(regs))
|
|
return;
|
|
|
|
if (handle_trapped_io(regs, address))
|
|
return;
|
|
/*
|
|
* Oops. The kernel tried to access some bad page. We'll have to
|
|
* terminate things with extreme prejudice.
|
|
*
|
|
*/
|
|
|
|
bust_spinlocks(1);
|
|
|
|
if (oops_may_print()) {
|
|
unsigned long page;
|
|
|
|
if (address < PAGE_SIZE)
|
|
printk(KERN_ALERT "Unable to handle kernel NULL "
|
|
"pointer dereference");
|
|
else
|
|
printk(KERN_ALERT "Unable to handle kernel paging "
|
|
"request");
|
|
printk(" at virtual address %08lx\n", address);
|
|
printk(KERN_ALERT "pc = %08lx\n", regs->pc);
|
|
page = (unsigned long)get_TTB();
|
|
if (page) {
|
|
page = ((__typeof__(page) *)page)[address >> PGDIR_SHIFT];
|
|
printk(KERN_ALERT "*pde = %08lx\n", page);
|
|
if (page & _PAGE_PRESENT) {
|
|
page &= PAGE_MASK;
|
|
address &= 0x003ff000;
|
|
page = ((__typeof__(page) *)
|
|
__va(page))[address >>
|
|
PAGE_SHIFT];
|
|
printk(KERN_ALERT "*pte = %08lx\n", page);
|
|
}
|
|
}
|
|
}
|
|
|
|
die("Oops", regs, writeaccess);
|
|
bust_spinlocks(0);
|
|
do_exit(SIGKILL);
|
|
|
|
/*
|
|
* We ran out of memory, or some other thing happened to us that made
|
|
* us unable to handle the page fault gracefully.
|
|
*/
|
|
out_of_memory:
|
|
up_read(&mm->mmap_sem);
|
|
if (is_global_init(current)) {
|
|
yield();
|
|
down_read(&mm->mmap_sem);
|
|
goto survive;
|
|
}
|
|
printk("VM: killing process %s\n", tsk->comm);
|
|
if (user_mode(regs))
|
|
do_group_exit(SIGKILL);
|
|
goto no_context;
|
|
|
|
do_sigbus:
|
|
up_read(&mm->mmap_sem);
|
|
|
|
/*
|
|
* Send a sigbus, regardless of whether we were in kernel
|
|
* or user mode.
|
|
*/
|
|
info.si_signo = SIGBUS;
|
|
info.si_errno = 0;
|
|
info.si_code = BUS_ADRERR;
|
|
info.si_addr = (void *)address;
|
|
force_sig_info(SIGBUS, &info, tsk);
|
|
|
|
/* Kernel mode? Handle exceptions or die */
|
|
if (!user_mode(regs))
|
|
goto no_context;
|
|
}
|
|
|
|
/*
|
|
* Called with interrupts disabled.
|
|
*/
|
|
asmlinkage int __kprobes
|
|
handle_tlbmiss(struct pt_regs *regs, unsigned long writeaccess,
|
|
unsigned long address)
|
|
{
|
|
pgd_t *pgd;
|
|
pud_t *pud;
|
|
pmd_t *pmd;
|
|
pte_t *pte;
|
|
pte_t entry;
|
|
|
|
/*
|
|
* We don't take page faults for P1, P2, and parts of P4, these
|
|
* are always mapped, whether it be due to legacy behaviour in
|
|
* 29-bit mode, or due to PMB configuration in 32-bit mode.
|
|
*/
|
|
if (address >= P3SEG && address < P3_ADDR_MAX) {
|
|
pgd = pgd_offset_k(address);
|
|
} else {
|
|
if (unlikely(address >= TASK_SIZE || !current->mm))
|
|
return 1;
|
|
|
|
pgd = pgd_offset(current->mm, address);
|
|
}
|
|
|
|
pud = pud_offset(pgd, address);
|
|
if (pud_none_or_clear_bad(pud))
|
|
return 1;
|
|
pmd = pmd_offset(pud, address);
|
|
if (pmd_none_or_clear_bad(pmd))
|
|
return 1;
|
|
pte = pte_offset_kernel(pmd, address);
|
|
entry = *pte;
|
|
if (unlikely(pte_none(entry) || pte_not_present(entry)))
|
|
return 1;
|
|
if (unlikely(writeaccess && !pte_write(entry)))
|
|
return 1;
|
|
|
|
if (writeaccess)
|
|
entry = pte_mkdirty(entry);
|
|
entry = pte_mkyoung(entry);
|
|
|
|
set_pte(pte, entry);
|
|
|
|
#if defined(CONFIG_CPU_SH4) && !defined(CONFIG_SMP)
|
|
/*
|
|
* SH-4 does not set MMUCR.RC to the corresponding TLB entry in
|
|
* the case of an initial page write exception, so we need to
|
|
* flush it in order to avoid potential TLB entry duplication.
|
|
*/
|
|
if (writeaccess == 2)
|
|
local_flush_tlb_one(get_asid(), address & PAGE_MASK);
|
|
#endif
|
|
|
|
update_mmu_cache(NULL, address, entry);
|
|
|
|
return 0;
|
|
}
|