powerpc/mm/thp: Make page table walk safe against thp split/collapse

We can disable a THP split or a hugepage collapse by disabling irq.
We do send IPI to all the cpus in the early part of split/collapse,
and disabling local irq ensure we don't make progress with
split/collapse. If the THP is getting split we return NULL from
find_linux_pte_or_hugepte(). For all the current callers it should be ok.
We need to be careful if we want to use returned pte_t pointer outside
the irq disabled region. W.r.t to THP split, the pfn remains the same,
but then a hugepage collapse will result in a pfn change. There are
few steps we can take to avoid a hugepage collapse.One way is to take page
reference inside the irq disable region. Other option is to take
mmap_sem so that a parallel collapse will not happen. We can also
disable collapse by taking pmd_lock. Another method used by kvm
subsystem is to check whether we had a mmu_notifer update in between
using mmu_notifier_retry().

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

1 files changed, 14 insertions, 10 deletions

diff --git a/arch/powerpc/perf/callchain.c b/arch/powerpc/perf/callchain.c
index ead55351b254..ff09cde20cd2 100644
--- a/arch/powerpc/perf/callchain.c
+++ b/arch/powerpc/perf/callchain.c
@@ -111,41 +111,45 @@ perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs)
  * interrupt context, so if the access faults, we read the page tables
  * to find which page (if any) is mapped and access it directly.
  */
-static int read_user_stack_slow(void __user *ptr, void *ret, int nb)
+static int read_user_stack_slow(void __user *ptr, void *buf, int nb)
 {
+	int ret = -EFAULT;
 	pgd_t *pgdir;
 	pte_t *ptep, pte;
 	unsigned shift;
 	unsigned long addr = (unsigned long) ptr;
 	unsigned long offset;
-	unsigned long pfn;
+	unsigned long pfn, flags;
 	void *kaddr;
 
 	pgdir = current->mm->pgd;
 	if (!pgdir)
 		return -EFAULT;
 
+	local_irq_save(flags);
 	ptep = find_linux_pte_or_hugepte(pgdir, addr, &shift);
+	if (!ptep)
+		goto err_out;
 	if (!shift)
 		shift = PAGE_SHIFT;
 
 	/* align address to page boundary */
 	offset = addr & ((1UL << shift) - 1);
-	addr -= offset;
 
-	if (ptep == NULL)
-		return -EFAULT;
-	pte = *ptep;
+	pte = READ_ONCE(*ptep);
 	if (!pte_present(pte) || !(pte_val(pte) & _PAGE_USER))
-		return -EFAULT;
+		goto err_out;
 	pfn = pte_pfn(pte);
 	if (!page_is_ram(pfn))
-		return -EFAULT;
+		goto err_out;
 
 	/* no highmem to worry about here */
 	kaddr = pfn_to_kaddr(pfn);
-	memcpy(ret, kaddr + offset, nb);
-	return 0;
+	memcpy(buf, kaddr + offset, nb);
+	ret = 0;
+err_out:
+	local_irq_restore(flags);
+	return ret;
 }
 
 static int read_user_stack_64(unsigned long __user *ptr, unsigned long *ret)