powerpc/mm/hash: Handle user access of kernel address gracefully

In commit 2865d08dd9ea ("powerpc/mm: Move the DSISR_PROTFAULT sanity
check") we moved the protection fault access check before the vma
lookup. That means we hit that WARN_ON when user space accesses a
kernel address. Before that commit this was handled by find_vma() not
finding vma for the kernel address and considering that access as bad
area access.

Avoid the confusing WARN_ON and convert that to a ratelimited printk.

With the patch we now get:

for load:
  a.out[5997]: User access of kernel address (c00000000000dea0) - exploit attempt? (uid: 1000)
  a.out[5997]: segfault (11) at c00000000000dea0 nip 1317c0798 lr 7fff80d6441c code 1 in a.out[1317c0000+10000]
  a.out[5997]: code: 60000000 60420000 3c4c0002 38427790 4bffff20 3c4c0002 38427784 fbe1fff8
  a.out[5997]: code: f821ffc1 7c3f0b78 60000000 e9228030 <89290000> 993f002f 60000000 383f0040

for exec:
  a.out[6067]: User access of kernel address (c00000000000dea0) - exploit attempt? (uid: 1000)
  a.out[6067]: segfault (11) at c00000000000dea0 nip c00000000000dea0 lr 129d507b0 code 1
  a.out[6067]: Bad NIP, not dumping instructions.

Fixes: 2865d08dd9ea ("powerpc/mm: Move the DSISR_PROTFAULT sanity check")
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Tested-by: Breno Leitao <leitao@debian.org>
[mpe: Don't split printk() string across lines]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index 01b9bcc..c448ca7 100644 (file)
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -342,9 +342,20 @@ static inline void cmo_account_page_fault(void) { }
 #endif /* CONFIG_PPC_SMLPAR */
 
 #ifdef CONFIG_PPC_BOOK3S
-static void sanity_check_fault(bool is_write, unsigned long error_code)
+static void sanity_check_fault(bool is_write, bool is_user,
+                              unsigned long error_code, unsigned long address)
 {
        /*
+        * Userspace trying to access kernel address, we get PROTFAULT for that.
+        */
+       if (is_user && address >= TASK_SIZE) {
+               pr_crit_ratelimited("%s[%d]: User access of kernel address (%lx) - exploit attempt? (uid: %d)\n",
+                                  current->comm, current->pid, address,
+                                  from_kuid(&init_user_ns, current_uid()));
+               return;
+       }
+
+       /*
         * For hash translation mode, we should never get a
         * PROTFAULT. Any update to pte to reduce access will result in us
         * removing the hash page table entry, thus resulting in a DSISR_NOHPTE
@@ -373,11 +384,14 @@ static void sanity_check_fault(bool is_write, unsigned long error_code)
         * For radix, we can get prot fault for autonuma case, because radix
         * page table will have them marked noaccess for user.
         */
-       if (!radix_enabled() && !is_write)
-               WARN_ON_ONCE(error_code & DSISR_PROTFAULT);
+       if (radix_enabled() || is_write)
+               return;
+
+       WARN_ON_ONCE(error_code & DSISR_PROTFAULT);
 }
 #else
-static void sanity_check_fault(bool is_write, unsigned long error_code) { }
+static void sanity_check_fault(bool is_write, bool is_user,
+                              unsigned long error_code, unsigned long address) { }
 #endif /* CONFIG_PPC_BOOK3S */
 
 /*
@@ -435,7 +449,7 @@ static int __do_page_fault(struct pt_regs *regs, unsigned long address,
        }
 
        /* Additional sanity check(s) */
-       sanity_check_fault(is_write, error_code);
+       sanity_check_fault(is_write, is_user, error_code, address);
 
        /*
         * The kernel should never take an execute fault nor should it