selftests/vm/pkeys: introduce powerpc support

This makes use of the abstractions added earlier and introduces support
for powerpc.

For powerpc, after receiving the SIGSEGV, the signal handler must
explicitly restore access permissions for the faulting pkey to allow the
test to continue.  As this makes use of pkey_access_allow(), all of its
dependencies and other similar functions have been moved ahead of the
signal handler.

[sandipan@linux.ibm.com: fix powerpc access right updates]
  Link: http://lkml.kernel.org/r/5f65cf37be993760de8112a88da194e3ccbb2bf8.1588959697.git.sandipan@linux.ibm.com
Signed-off-by: Ram Pai <linuxram@us.ibm.com>
Signed-off-by: Sandipan Das <sandipan@linux.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Dave Hansen <dave.hansen@intel.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Florian Weimer <fweimer@redhat.com>
Cc: "Desnes A. Nunes do Rosario" <desnesn@linux.vnet.ibm.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Thiago Jung Bauermann <bauerman@linux.ibm.com>
Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Michal Suchanek <msuchanek@suse.de>
Cc: Shuah Khan <shuah@kernel.org>
Link: http://lkml.kernel.org/r/b121e9fd33789ed9195276e32fe4e80bb6b88a31.1585646528.git.sandipan@linux.ibm.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 141 insertions, 128 deletions

diff --git a/tools/testing/selftests/vm/protection_keys.c b/tools/testing/selftests/vm/protection_keys.c
index 57c71056c93d..e6de078a9196 100644
--- a/tools/testing/selftests/vm/protection_keys.c
+++ b/tools/testing/selftests/vm/protection_keys.c
@@ -169,6 +169,125 @@ void dump_mem(void *dumpme, int len_bytes)
 	}
 }
 
+static u32 hw_pkey_get(int pkey, unsigned long flags)
+{
+	u64 pkey_reg = __read_pkey_reg();
+
+	dprintf1("%s(pkey=%d, flags=%lx) = %x / %d\n",
+			__func__, pkey, flags, 0, 0);
+	dprintf2("%s() raw pkey_reg: %016llx\n", __func__, pkey_reg);
+
+	return (u32) get_pkey_bits(pkey_reg, pkey);
+}
+
+static int hw_pkey_set(int pkey, unsigned long rights, unsigned long flags)
+{
+	u32 mask = (PKEY_DISABLE_ACCESS|PKEY_DISABLE_WRITE);
+	u64 old_pkey_reg = __read_pkey_reg();
+	u64 new_pkey_reg;
+
+	/* make sure that 'rights' only contains the bits we expect: */
+	assert(!(rights & ~mask));
+
+	/* modify bits accordingly in old pkey_reg and assign it */
+	new_pkey_reg = set_pkey_bits(old_pkey_reg, pkey, rights);
+
+	__write_pkey_reg(new_pkey_reg);
+
+	dprintf3("%s(pkey=%d, rights=%lx, flags=%lx) = %x"
+		" pkey_reg now: %016llx old_pkey_reg: %016llx\n",
+		__func__, pkey, rights, flags, 0, __read_pkey_reg(),
+		old_pkey_reg);
+	return 0;
+}
+
+void pkey_disable_set(int pkey, int flags)
+{
+	unsigned long syscall_flags = 0;
+	int ret;
+	int pkey_rights;
+	u64 orig_pkey_reg = read_pkey_reg();
+
+	dprintf1("START->%s(%d, 0x%x)\n", __func__,
+		pkey, flags);
+	pkey_assert(flags & (PKEY_DISABLE_ACCESS | PKEY_DISABLE_WRITE));
+
+	pkey_rights = hw_pkey_get(pkey, syscall_flags);
+
+	dprintf1("%s(%d) hw_pkey_get(%d): %x\n", __func__,
+			pkey, pkey, pkey_rights);
+
+	pkey_assert(pkey_rights >= 0);
+
+	pkey_rights |= flags;
+
+	ret = hw_pkey_set(pkey, pkey_rights, syscall_flags);
+	assert(!ret);
+	/* pkey_reg and flags have the same format */
+	shadow_pkey_reg = set_pkey_bits(shadow_pkey_reg, pkey, pkey_rights);
+	dprintf1("%s(%d) shadow: 0x%016llx\n",
+		__func__, pkey, shadow_pkey_reg);
+
+	pkey_assert(ret >= 0);
+
+	pkey_rights = hw_pkey_get(pkey, syscall_flags);
+	dprintf1("%s(%d) hw_pkey_get(%d): %x\n", __func__,
+			pkey, pkey, pkey_rights);
+
+	dprintf1("%s(%d) pkey_reg: 0x%016llx\n",
+		__func__, pkey, read_pkey_reg());
+	if (flags)
+		pkey_assert(read_pkey_reg() >= orig_pkey_reg);
+	dprintf1("END<---%s(%d, 0x%x)\n", __func__,
+		pkey, flags);
+}
+
+void pkey_disable_clear(int pkey, int flags)
+{
+	unsigned long syscall_flags = 0;
+	int ret;
+	int pkey_rights = hw_pkey_get(pkey, syscall_flags);
+	u64 orig_pkey_reg = read_pkey_reg();
+
+	pkey_assert(flags & (PKEY_DISABLE_ACCESS | PKEY_DISABLE_WRITE));
+
+	dprintf1("%s(%d) hw_pkey_get(%d): %x\n", __func__,
+			pkey, pkey, pkey_rights);
+	pkey_assert(pkey_rights >= 0);
+
+	pkey_rights &= ~flags;
+
+	ret = hw_pkey_set(pkey, pkey_rights, 0);
+	shadow_pkey_reg = set_pkey_bits(shadow_pkey_reg, pkey, pkey_rights);
+	pkey_assert(ret >= 0);
+
+	pkey_rights = hw_pkey_get(pkey, syscall_flags);
+	dprintf1("%s(%d) hw_pkey_get(%d): %x\n", __func__,
+			pkey, pkey, pkey_rights);
+
+	dprintf1("%s(%d) pkey_reg: 0x%016llx\n", __func__,
+			pkey, read_pkey_reg());
+	if (flags)
+		assert(read_pkey_reg() <= orig_pkey_reg);
+}
+
+void pkey_write_allow(int pkey)
+{
+	pkey_disable_clear(pkey, PKEY_DISABLE_WRITE);
+}
+void pkey_write_deny(int pkey)
+{
+	pkey_disable_set(pkey, PKEY_DISABLE_WRITE);
+}
+void pkey_access_allow(int pkey)
+{
+	pkey_disable_clear(pkey, PKEY_DISABLE_ACCESS);
+}
+void pkey_access_deny(int pkey)
+{
+	pkey_disable_set(pkey, PKEY_DISABLE_ACCESS);
+}
+
 /* Failed address bound checks: */
 #ifndef SEGV_BNDERR
 # define SEGV_BNDERR		3
@@ -199,11 +318,12 @@ void signal_handler(int signum, siginfo_t *si, void *vucontext)
 	int trapno;
 	unsigned long ip;
 	char *fpregs;
+#if defined(__i386__) || defined(__x86_64__) /* arch */
 	u32 *pkey_reg_ptr;
+	int pkey_reg_offset;
+#endif /* arch */
 	u64 siginfo_pkey;
 	u32 *si_pkey_ptr;
-	int pkey_reg_offset;
-	fpregset_t fpregset;
 
 	dprint_in_signal = 1;
 	dprintf1(">>>>===============SIGSEGV============================\n");
@@ -213,12 +333,13 @@ void signal_handler(int signum, siginfo_t *si, void *vucontext)
 
 	trapno = uctxt->uc_mcontext.gregs[REG_TRAPNO];
 	ip = uctxt->uc_mcontext.gregs[REG_IP_IDX];
-	fpregset = uctxt->uc_mcontext.fpregs;
-	fpregs = (void *)fpregset;
+	fpregs = (char *) uctxt->uc_mcontext.fpregs;
 
 	dprintf2("%s() trapno: %d ip: 0x%016lx info->si_code: %s/%d\n",
 			__func__, trapno, ip, si_code_str(si->si_code),
 			si->si_code);
+
+#if defined(__i386__) || defined(__x86_64__) /* arch */
 #ifdef __i386__
 	/*
 	 * 32-bit has some extra padding so that userspace can tell whether
@@ -226,12 +347,10 @@ void signal_handler(int signum, siginfo_t *si, void *vucontext)
 	 * state.  We just assume that it is here.
 	 */
 	fpregs += 0x70;
-#endif
+#endif /* i386 */
 	pkey_reg_offset = pkey_reg_xstate_offset();
 	pkey_reg_ptr = (void *)(&fpregs[pkey_reg_offset]);
 
-	dprintf1("siginfo: %p\n", si);
-	dprintf1(" fpregs: %p\n", fpregs);
 	/*
 	 * If we got a PKEY fault, we *HAVE* to have at least one bit set in
 	 * here.
@@ -240,6 +359,10 @@ void signal_handler(int signum, siginfo_t *si, void *vucontext)
 	if (DEBUG_LEVEL > 4)
 		dump_mem(pkey_reg_ptr - 128, 256);
 	pkey_assert(*pkey_reg_ptr);
+#endif /* arch */
+
+	dprintf1("siginfo: %p\n", si);
+	dprintf1(" fpregs: %p\n", fpregs);
 
 	if ((si->si_code == SEGV_MAPERR) ||
 	    (si->si_code == SEGV_ACCERR) ||
@@ -248,14 +371,13 @@ void signal_handler(int signum, siginfo_t *si, void *vucontext)
 		exit(4);
 	}
 
-	si_pkey_ptr = (u32 *)(((u8 *)si) + si_pkey_offset);
+	si_pkey_ptr = siginfo_get_pkey_ptr(si);
 	dprintf1("si_pkey_ptr: %p\n", si_pkey_ptr);
 	dump_mem((u8 *)si_pkey_ptr - 8, 24);
 	siginfo_pkey = *si_pkey_ptr;
 	pkey_assert(siginfo_pkey < NR_PKEYS);
 	last_si_pkey = siginfo_pkey;
 
-	dprintf1("signal pkey_reg from xsave: %08x\n", *pkey_reg_ptr);
 	/*
 	 * need __read_pkey_reg() version so we do not do shadow_pkey_reg
 	 * checking
@@ -263,8 +385,14 @@ void signal_handler(int signum, siginfo_t *si, void *vucontext)
 	dprintf1("signal pkey_reg from  pkey_reg: %016llx\n",
 			__read_pkey_reg());
 	dprintf1("pkey from siginfo: %016llx\n", siginfo_pkey);
+#if defined(__i386__) || defined(__x86_64__) /* arch */
+	dprintf1("signal pkey_reg from xsave: %08x\n", *pkey_reg_ptr);
 	*(u64 *)pkey_reg_ptr = 0x00000000;
 	dprintf1("WARNING: set PKEY_REG=0 to allow faulting instruction to continue\n");
+#elif defined(__powerpc64__) /* arch */
+	/* restore access and let the faulting instruction continue */
+	pkey_access_allow(siginfo_pkey);
+#endif /* arch */
 	pkey_faults++;
 	dprintf1("<<<<==================================================\n");
 	dprint_in_signal = 0;
@@ -333,125 +461,6 @@ pid_t fork_lazy_child(void)
 	return forkret;
 }
 
-static u32 hw_pkey_get(int pkey, unsigned long flags)
-{
-	u64 pkey_reg = __read_pkey_reg();
-
-	dprintf1("%s(pkey=%d, flags=%lx) = %x / %d\n",
-			__func__, pkey, flags, 0, 0);
-	dprintf2("%s() raw pkey_reg: %016llx\n", __func__, pkey_reg);
-
-	return (u32) get_pkey_bits(pkey_reg, pkey);
-}
-
-static int hw_pkey_set(int pkey, unsigned long rights, unsigned long flags)
-{
-	u32 mask = (PKEY_DISABLE_ACCESS|PKEY_DISABLE_WRITE);
-	u64 old_pkey_reg = __read_pkey_reg();
-	u64 new_pkey_reg;
-
-	/* make sure that 'rights' only contains the bits we expect: */
-	assert(!(rights & ~mask));
-
-	/* modify bits accordingly in old pkey_reg and assign it */
-	new_pkey_reg = set_pkey_bits(old_pkey_reg, pkey, rights);
-
-	__write_pkey_reg(new_pkey_reg);
-
-	dprintf3("%s(pkey=%d, rights=%lx, flags=%lx) = %x"
-		" pkey_reg now: %016llx old_pkey_reg: %016llx\n",
-		__func__, pkey, rights, flags, 0, __read_pkey_reg(),
-		old_pkey_reg);
-	return 0;
-}
-
-void pkey_disable_set(int pkey, int flags)
-{
-	unsigned long syscall_flags = 0;
-	int ret;
-	int pkey_rights;
-	u64 orig_pkey_reg = read_pkey_reg();
-
-	dprintf1("START->%s(%d, 0x%x)\n", __func__,
-		pkey, flags);
-	pkey_assert(flags & (PKEY_DISABLE_ACCESS | PKEY_DISABLE_WRITE));
-
-	pkey_rights = hw_pkey_get(pkey, syscall_flags);
-
-	dprintf1("%s(%d) hw_pkey_get(%d): %x\n", __func__,
-			pkey, pkey, pkey_rights);
-
-	pkey_assert(pkey_rights >= 0);
-
-	pkey_rights |= flags;
-
-	ret = hw_pkey_set(pkey, pkey_rights, syscall_flags);
-	assert(!ret);
-	/* pkey_reg and flags have the same format */
-	shadow_pkey_reg = set_pkey_bits(shadow_pkey_reg, pkey, pkey_rights);
-	dprintf1("%s(%d) shadow: 0x%016llx\n",
-		__func__, pkey, shadow_pkey_reg);
-
-	pkey_assert(ret >= 0);
-
-	pkey_rights = hw_pkey_get(pkey, syscall_flags);
-	dprintf1("%s(%d) hw_pkey_get(%d): %x\n", __func__,
-			pkey, pkey, pkey_rights);
-
-	dprintf1("%s(%d) pkey_reg: 0x%016llx\n",
-		__func__, pkey, read_pkey_reg());
-	if (flags)
-		pkey_assert(read_pkey_reg() >= orig_pkey_reg);
-	dprintf1("END<---%s(%d, 0x%x)\n", __func__,
-		pkey, flags);
-}
-
-void pkey_disable_clear(int pkey, int flags)
-{
-	unsigned long syscall_flags = 0;
-	int ret;
-	int pkey_rights = hw_pkey_get(pkey, syscall_flags);
-	u64 orig_pkey_reg = read_pkey_reg();
-
-	pkey_assert(flags & (PKEY_DISABLE_ACCESS | PKEY_DISABLE_WRITE));
-
-	dprintf1("%s(%d) hw_pkey_get(%d): %x\n", __func__,
-			pkey, pkey, pkey_rights);
-	pkey_assert(pkey_rights >= 0);
-
-	pkey_rights &= ~flags;
-
-	ret = hw_pkey_set(pkey, pkey_rights, 0);
-	shadow_pkey_reg = set_pkey_bits(shadow_pkey_reg, pkey, pkey_rights);
-	pkey_assert(ret >= 0);
-
-	pkey_rights = hw_pkey_get(pkey, syscall_flags);
-	dprintf1("%s(%d) hw_pkey_get(%d): %x\n", __func__,
-			pkey, pkey, pkey_rights);
-
-	dprintf1("%s(%d) pkey_reg: 0x%016llx\n", __func__,
-			pkey, read_pkey_reg());
-	if (flags)
-		assert(read_pkey_reg() <= orig_pkey_reg);
-}
-
-void pkey_write_allow(int pkey)
-{
-	pkey_disable_clear(pkey, PKEY_DISABLE_WRITE);
-}
-void pkey_write_deny(int pkey)
-{
-	pkey_disable_set(pkey, PKEY_DISABLE_WRITE);
-}
-void pkey_access_allow(int pkey)
-{
-	pkey_disable_clear(pkey, PKEY_DISABLE_ACCESS);
-}
-void pkey_access_deny(int pkey)
-{
-	pkey_disable_set(pkey, PKEY_DISABLE_ACCESS);
-}
-
 int sys_mprotect_pkey(void *ptr, size_t size, unsigned long orig_prot,
 		unsigned long pkey)
 {
@@ -890,11 +899,15 @@ void expected_pkey_fault(int pkey)
 	if (pkey != UNKNOWN_PKEY)
 		pkey_assert(last_si_pkey == pkey);
 
+#if defined(__i386__) || defined(__x86_64__) /* arch */
 	/*
 	 * The signal handler shold have cleared out PKEY register to let the
 	 * test program continue.  We now have to restore it.
 	 */
 	if (__read_pkey_reg() != 0)
+#else /* arch */
+	if (__read_pkey_reg() != shadow_pkey_reg)
+#endif /* arch */
 		pkey_assert(0);
 
 	__write_pkey_reg(shadow_pkey_reg);