[RFC PATCH 08/21] powerpc/perf/callchain: Use __get_user_pages_fast in read_user_stack_slow

[Aneesh Kumar K.V]

read_user_stack_slow is called with interrupts soft disabled and it copies contents
from the page which we find mapped to a specific address. To convert
userspace address to pfn, the kernel now uses lockless page table walk.

The kernel needs to make sure the pfn value read remains stable and is not released
and reused for another process while the contents are read from the page. This
can only be achieved by holding a page reference.

One of the first approaches I tried was to check the pte value after the kernel
copies the contents from the page. But as shown below we can still get it wrong

CPU0                           CPU1
pte = READ_ONCE(*ptep);
                               pte_clear(pte);
                               put_page(page);
                               page = alloc_page();
                               memcpy(page_address(page), "secret password", nr);
memcpy(buf, kaddr + offset, nb);
                               put_page(page);
                               handle_mm_fault()
                               page = alloc_page();
                               set_pte(pte, page);
if (pte_val(pte) != pte_val(*ptep))

Hence switch to __get_user_pages_fast.

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar at linux.ibm.com>
---
 arch/powerpc/perf/callchain.c | 53 ++++++++++++++---------------------
 1 file changed, 21 insertions(+), 32 deletions(-)

diff --git a/arch/powerpc/perf/callchain.c b/arch/powerpc/perf/callchain.c
index cbc251981209..7b7b3ff53180 100644
--- a/arch/powerpc/perf/callchain.c
+++ b/arch/powerpc/perf/callchain.c
@@ -107,46 +107,35 @@ perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *re
  * On 64-bit we don't want to invoke hash_page on user addresses from
  * interrupt context, so if the access faults, we read the page tables
  * to find which page (if any) is mapped and access it directly.
+
+ * This should get called only if the PMU interrupt occurred while
+ * interrupts are soft-disabled, and there is no MMU hash table entry
+ * for the page . In this case we will get an -EFAULT return from
+ * __get_user_inatomic even if there is a valid Linux PTE for the page,
+ * since hash_page isn't reentrant.  Thus we have code here to read the
+ * Linux PTE and access the page via the kernel linear mapping.
  */
 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, flags;
+	struct page *page;
+	int nrpages;
 	void *kaddr;
 
-	pgdir = current->mm->pgd;
-	if (!pgdir)
-		return -EFAULT;
+	nrpages = __get_user_pages_fast(addr, 1, 1, &page);
+	if (nrpages == 1) {
+		kaddr = page_address(page);
 
-	local_irq_save(flags);
-	ptep = find_current_mm_pte(pgdir, addr, NULL, &shift);
-	if (!ptep)
-		goto err_out;
-	if (!shift)
-		shift = PAGE_SHIFT;
-
-	/* align address to page boundary */
-	offset = addr & ((1UL << shift) - 1);
-
-	pte = READ_ONCE(*ptep);
-	if (!pte_present(pte) || !pte_user(pte))
-		goto err_out;
-	pfn = pte_pfn(pte);
-	if (!page_is_ram(pfn))
-		goto err_out;
-
-	/* no highmem to worry about here */
-	kaddr = pfn_to_kaddr(pfn);
-	memcpy(buf, kaddr + offset, nb);
-	ret = 0;
-err_out:
-	local_irq_restore(flags);
-	return ret;
+		/* align address to page boundary */
+		offset = addr & ~PAGE_MASK;
+
+		memcpy(buf, kaddr + offset, nb);
+		put_page(page);
+		return 0;
+	}
+	return -EFAULT;
 }
 
 static int read_user_stack_64(unsigned long __user *ptr, unsigned long *ret)
-- 
2.24.1