selftests, powerpc, x86 : Memory Protection Keys

223 lines not on this page · raw message

1,407 lines not on this page · raw message

223 lines not on this page · raw message

1,132 lines not on this page · raw message

index b3cb767..a568166 100644
@@ -14,7 +14,7 @@
 #include <sys/mman.h>
 
 #define NR_PKEYS 16
-#define PKRU_BITS_PER_PKEY 2
+#define PKEY_BITS_PER_PKEY 2
 
 #ifndef DEBUG_LEVEL
 #define DEBUG_LEVEL 0

@@ -57,85 +57,88 @@ static inline void sigsafe_printf(const char *format, ...)
 #define dprintf3(args...) dprintf_level(3, args)
 #define dprintf4(args...) dprintf_level(4, args)
 
-extern unsigned int shadow_pkru;
-static inline unsigned int __rdpkru(void)
+extern unsigned int shadow_pkey_reg;
+static inline unsigned int __rdpkey_reg(void)
 {
 	unsigned int eax, edx;
 	unsigned int ecx = 0;
-	unsigned int pkru;
+	unsigned int pkey_reg;
 
 	asm volatile(".byte 0x0f,0x01,0xee\n\t"
 		     : "=a" (eax), "=d" (edx)
 		     : "c" (ecx));
-	pkru = eax;
-	return pkru;
+	pkey_reg = eax;
+	return pkey_reg;
 }
 
-static inline unsigned int _rdpkru(int line)
+static inline unsigned int _rdpkey_reg(int line)
 {
-	unsigned int pkru = __rdpkru();
+	unsigned int pkey_reg = __rdpkey_reg();
 
-	dprintf4("rdpkru(line=%d) pkru: %x shadow: %x\n",
-			line, pkru, shadow_pkru);
-	assert(pkru == shadow_pkru);
+	dprintf4("rdpkey_reg(line=%d) pkey_reg: %x shadow: %x\n",
+			line, pkey_reg, shadow_pkey_reg);
+	assert(pkey_reg == shadow_pkey_reg);
 
-	return pkru;
+	return pkey_reg;
 }
 
-#define rdpkru() _rdpkru(__LINE__)
+#define rdpkey_reg() _rdpkey_reg(__LINE__)
 
-static inline void __wrpkru(unsigned int pkru)
+static inline void __wrpkey_reg(unsigned int pkey_reg)
 {
-	unsigned int eax = pkru;
+	unsigned int eax = pkey_reg;
 	unsigned int ecx = 0;
 	unsigned int edx = 0;
 
-	dprintf4("%s() changing %08x to %08x\n", __func__, __rdpkru(), pkru);
+	dprintf4("%s() changing %08x to %08x\n", __func__,
+			__rdpkey_reg(), pkey_reg);
 	asm volatile(".byte 0x0f,0x01,0xef\n\t"
 		     : : "a" (eax), "c" (ecx), "d" (edx));
-	assert(pkru == __rdpkru());
+	assert(pkey_reg == __rdpkey_reg());
 }
 
-static inline void wrpkru(unsigned int pkru)
+static inline void wrpkey_reg(unsigned int pkey_reg)
 {
-	dprintf4("%s() changing %08x to %08x\n", __func__, __rdpkru(), pkru);
+	dprintf4("%s() changing %08x to %08x\n", __func__,
+			__rdpkey_reg(), pkey_reg);
 	/* will do the shadow check for us: */
-	rdpkru();
-	__wrpkru(pkru);
-	shadow_pkru = pkru;
-	dprintf4("%s(%08x) pkru: %08x\n", __func__, pkru, __rdpkru());
+	rdpkey_reg();
+	__wrpkey_reg(pkey_reg);
+	shadow_pkey_reg = pkey_reg;
+	dprintf4("%s(%08x) pkey_reg: %08x\n", __func__,
+			pkey_reg, __rdpkey_reg());
 }
 
 /*
  * These are technically racy. since something could
- * change PKRU between the read and the write.
+ * change PKEY register between the read and the write.
  */
 static inline void __pkey_access_allow(int pkey, int do_allow)
 {
-	unsigned int pkru = rdpkru();
+	unsigned int pkey_reg = rdpkey_reg();
 	int bit = pkey * 2;
 
 	if (do_allow)
-		pkru &= (1<<bit);
+		pkey_reg &= (1<<bit);
 	else
-		pkru |= (1<<bit);
+		pkey_reg |= (1<<bit);
 
-	dprintf4("pkru now: %08x\n", rdpkru());
-	wrpkru(pkru);
+	dprintf4("pkey_reg now: %08x\n", rdpkey_reg());
+	wrpkey_reg(pkey_reg);
 }
 
 static inline void __pkey_write_allow(int pkey, int do_allow_write)
 {
-	long pkru = rdpkru();
+	long pkey_reg = rdpkey_reg();
 	int bit = pkey * 2 + 1;
 
 	if (do_allow_write)
-		pkru &= (1<<bit);
+		pkey_reg &= (1<<bit);
 	else
-		pkru |= (1<<bit);
+		pkey_reg |= (1<<bit);
 
-	wrpkru(pkru);
-	dprintf4("pkru now: %08x\n", rdpkru());
+	wrpkey_reg(pkey_reg);
+	dprintf4("pkey_reg now: %08x\n", rdpkey_reg());
 }
 
 #define PROT_PKEY0     0x10            /* protection key value (bit 0) */

@@ -185,10 +188,10 @@ static inline int cpu_has_pku(void)
 	return 1;
 }
 
-#define XSTATE_PKRU_BIT	(9)
-#define XSTATE_PKRU	0x200
+#define XSTATE_PKEY_BIT	(9)
+#define XSTATE_PKEY	0x200
 
-int pkru_xstate_offset(void)
+int pkey_reg_xstate_offset(void)
 {
 	unsigned int eax;
 	unsigned int ebx;

@@ -199,21 +202,21 @@ int pkru_xstate_offset(void)
 	unsigned long XSTATE_CPUID = 0xd;
 	int leaf;
 
-	/* assume that XSTATE_PKRU is set in XCR0 */
-	leaf = XSTATE_PKRU_BIT;
+	/* assume that XSTATE_PKEY is set in XCR0 */
+	leaf = XSTATE_PKEY_BIT;
 	{
 		eax = XSTATE_CPUID;
 		ecx = leaf;
 		__cpuid(&eax, &ebx, &ecx, &edx);
 
-		if (leaf == XSTATE_PKRU_BIT) {
+		if (leaf == XSTATE_PKEY_BIT) {
 			xstate_offset = ebx;
 			xstate_size = eax;
 		}
 	}
 
 	if (xstate_size == 0) {
-		printf("could not find size/offset of PKRU in xsave state\n");
+		printf("could not find size/offset of PKEY in xsave state\n");
 		return 0;
 	}
 

493 lines not on this page · raw message

index a568166..c1bc761 100644
@@ -13,8 +13,31 @@
 #include <ucontext.h>
 #include <sys/mman.h>
 
+/* Define some kernel-like types */
+#define  u8 uint8_t
+#define u16 uint16_t
+#define u32 uint32_t
+#define u64 uint64_t
+
+#ifdef __i386__
+#define SYS_mprotect_key 380
+#define SYS_pkey_alloc	 381
+#define SYS_pkey_free	 382
+#define REG_IP_IDX REG_EIP
+#define si_pkey_offset 0x14
+#else
+#define SYS_mprotect_key 329
+#define SYS_pkey_alloc	 330
+#define SYS_pkey_free	 331
+#define REG_IP_IDX REG_RIP
+#define si_pkey_offset 0x20
+#endif
+
 #define NR_PKEYS 16
 #define PKEY_BITS_PER_PKEY 2
+#define PKEY_DISABLE_ACCESS    0x1
+#define PKEY_DISABLE_WRITE     0x2
+#define HPAGE_SIZE	(1UL<<21)
 
 #ifndef DEBUG_LEVEL
 #define DEBUG_LEVEL 0

@@ -141,11 +164,6 @@ static inline void __pkey_write_allow(int pkey, int do_allow_write)
 	dprintf4("pkey_reg now: %08x\n", rdpkey_reg());
 }
 
-#define PROT_PKEY0     0x10            /* protection key value (bit 0) */
-#define PROT_PKEY1     0x20            /* protection key value (bit 1) */
-#define PROT_PKEY2     0x40            /* protection key value (bit 2) */
-#define PROT_PKEY3     0x80            /* protection key value (bit 3) */
-
 #define PAGE_SIZE 4096
 #define MB	(1<<20)
 

@@ -223,4 +241,38 @@ int pkey_reg_xstate_offset(void)
 	return xstate_offset;
 }
 
+static inline void __page_o_noops(void)
+{
+	/* 8-bytes of instruction * 512 bytes = 1 page */
+	asm(".rept 512 ; nopl 0x7eeeeeee(%eax) ; .endr");
+}
+
 #endif /* _PKEYS_HELPER_H */
+
+#define ARRAY_SIZE(x) (sizeof(x) / sizeof(*(x)))
+#define ALIGN_UP(x, align_to)	(((x) + ((align_to)-1)) & ~((align_to)-1))
+#define ALIGN_DOWN(x, align_to) ((x) & ~((align_to)-1))
+#define ALIGN_PTR_UP(p, ptr_align_to)	\
+		((typeof(p))ALIGN_UP((unsigned long)(p), ptr_align_to))
+#define ALIGN_PTR_DOWN(p, ptr_align_to) \
+	((typeof(p))ALIGN_DOWN((unsigned long)(p), ptr_align_to))
+#define __stringify_1(x...)     #x
+#define __stringify(x...)       __stringify_1(x)
+
+#define PTR_ERR_ENOTSUP ((void *)-ENOTSUP)
+
+int dprint_in_signal;
+char dprint_in_signal_buffer[DPRINT_IN_SIGNAL_BUF_SIZE];
+
+extern void abort_hooks(void);
+#define pkey_assert(condition) do {		\
+	if (!(condition)) {			\
+		dprintf0("assert() at %s::%d test_nr: %d iteration: %d\n", \
+				__FILE__, __LINE__,	\
+				test_nr, iteration_nr);	\
+		dprintf0("errno at assert: %d", errno);	\
+		abort_hooks();			\
+		assert(condition);		\
+	}					\
+} while (0)
+#define raw_assert(cond) assert(cond)

93 lines not on this page · raw message

index c1bc761..b6c2133 100644
@@ -18,6 +18,7 @@
 #define u16 uint16_t
 #define u32 uint32_t
 #define u64 uint64_t
+#define pkey_reg_t u32
 
 #ifdef __i386__
 #define SYS_mprotect_key 380

@@ -80,12 +81,12 @@ static inline void sigsafe_printf(const char *format, ...)
 #define dprintf3(args...) dprintf_level(3, args)
 #define dprintf4(args...) dprintf_level(4, args)
 
-extern unsigned int shadow_pkey_reg;
-static inline unsigned int __rdpkey_reg(void)
+extern pkey_reg_t shadow_pkey_reg;
+static inline pkey_reg_t __rdpkey_reg(void)
 {
 	unsigned int eax, edx;
 	unsigned int ecx = 0;
-	unsigned int pkey_reg;
+	pkey_reg_t pkey_reg;
 
 	asm volatile(".byte 0x0f,0x01,0xee\n\t"
 		     : "=a" (eax), "=d" (edx)

@@ -94,11 +95,11 @@ static inline unsigned int __rdpkey_reg(void)
 	return pkey_reg;
 }
 
-static inline unsigned int _rdpkey_reg(int line)
+static inline pkey_reg_t _rdpkey_reg(int line)
 {
-	unsigned int pkey_reg = __rdpkey_reg();
+	pkey_reg_t pkey_reg = __rdpkey_reg();
 
-	dprintf4("rdpkey_reg(line=%d) pkey_reg: %x shadow: %x\n",
+	dprintf4("rdpkey_reg(line=%d) pkey_reg: %016lx shadow: %016lx\n",
 			line, pkey_reg, shadow_pkey_reg);
 	assert(pkey_reg == shadow_pkey_reg);
 

@@ -107,11 +108,11 @@ static inline unsigned int _rdpkey_reg(int line)
 
 #define rdpkey_reg() _rdpkey_reg(__LINE__)
 
-static inline void __wrpkey_reg(unsigned int pkey_reg)
+static inline void __wrpkey_reg(pkey_reg_t pkey_reg)
 {
-	unsigned int eax = pkey_reg;
-	unsigned int ecx = 0;
-	unsigned int edx = 0;
+	pkey_reg_t eax = pkey_reg;
+	pkey_reg_t ecx = 0;
+	pkey_reg_t edx = 0;
 
 	dprintf4("%s() changing %08x to %08x\n", __func__,
 			__rdpkey_reg(), pkey_reg);

@@ -120,7 +121,7 @@ static inline void __wrpkey_reg(unsigned int pkey_reg)
 	assert(pkey_reg == __rdpkey_reg());
 }
 
-static inline void wrpkey_reg(unsigned int pkey_reg)
+static inline void wrpkey_reg(pkey_reg_t pkey_reg)
 {
 	dprintf4("%s() changing %08x to %08x\n", __func__,
 			__rdpkey_reg(), pkey_reg);

@@ -138,7 +139,7 @@ static inline void wrpkey_reg(unsigned int pkey_reg)
  */
 static inline void __pkey_access_allow(int pkey, int do_allow)
 {
-	unsigned int pkey_reg = rdpkey_reg();
+	pkey_reg_t pkey_reg = rdpkey_reg();
 	int bit = pkey * 2;
 
 	if (do_allow)

@@ -152,7 +153,7 @@ static inline void __pkey_access_allow(int pkey, int do_allow)
 
 static inline void __pkey_write_allow(int pkey, int do_allow_write)
 {
-	long pkey_reg = rdpkey_reg();
+	pkey_reg_t pkey_reg = rdpkey_reg();
 	int bit = pkey * 2 + 1;
 
 	if (do_allow_write)

203 lines not on this page · raw message

index b6c2133..7c979ad 100644
@@ -44,6 +44,33 @@
 #define DEBUG_LEVEL 0
 #endif
 #define DPRINT_IN_SIGNAL_BUF_SIZE 4096
+
+static inline u32 pkey_to_shift(int pkey)
+{
+	return pkey * PKEY_BITS_PER_PKEY;
+}
+
+static inline pkey_reg_t reset_bits(int pkey, pkey_reg_t bits)
+{
+	u32 shift = pkey_to_shift(pkey);
+
+	return ~(bits << shift);
+}
+
+static inline pkey_reg_t left_shift_bits(int pkey, pkey_reg_t bits)
+{
+	u32 shift = pkey_to_shift(pkey);
+
+	return (bits << shift);
+}
+
+static inline pkey_reg_t right_shift_bits(int pkey, pkey_reg_t bits)
+{
+	u32 shift = pkey_to_shift(pkey);
+
+	return (bits >> shift);
+}
+
 extern int dprint_in_signal;
 extern char dprint_in_signal_buffer[DPRINT_IN_SIGNAL_BUF_SIZE];
 static inline void sigsafe_printf(const char *format, ...)

index 3ef2569..83216c5 100644
@@ -374,7 +374,7 @@ u32 pkey_get(int pkey, unsigned long flags)
 			__func__, pkey, flags, 0, 0);
 	dprintf2("%s() raw pkey_reg: %x\n", __func__, pkey_reg);
 
-	shifted_pkey_reg = (pkey_reg >> (pkey * PKEY_BITS_PER_PKEY));
+	shifted_pkey_reg = right_shift_bits(pkey, pkey_reg);
 	dprintf2("%s() shifted_pkey_reg: %x\n", __func__, shifted_pkey_reg);
 	masked_pkey_reg = shifted_pkey_reg & mask;
 	dprintf2("%s() masked  pkey_reg: %x\n", __func__, masked_pkey_reg);

@@ -397,9 +397,9 @@ int pkey_set(int pkey, unsigned long rights, unsigned long flags)
 	/* copy old pkey_reg */
 	new_pkey_reg = old_pkey_reg;
 	/* mask out bits from pkey in old value: */
-	new_pkey_reg &= ~(mask << (pkey * PKEY_BITS_PER_PKEY));
+	new_pkey_reg &= reset_bits(pkey, mask);
 	/* OR in new bits for pkey: */
-	new_pkey_reg |= (rights << (pkey * PKEY_BITS_PER_PKEY));
+	new_pkey_reg |= left_shift_bits(pkey, rights);
 
 	__wrpkey_reg(new_pkey_reg);
 

@@ -430,7 +430,7 @@ void pkey_disable_set(int pkey, int flags)
 	ret = pkey_set(pkey, pkey_rights, syscall_flags);
 	assert(!ret);
 	/*pkey_reg and flags have the same format */
-	shadow_pkey_reg |= flags << (pkey * 2);
+	shadow_pkey_reg |= left_shift_bits(pkey, flags);
 	dprintf1("%s(%d) shadow: 0x%016lx\n",
 		__func__, pkey, shadow_pkey_reg);
 

@@ -465,7 +465,7 @@ void pkey_disable_clear(int pkey, int flags)
 
 	ret = pkey_set(pkey, pkey_rights, 0);
 	/* pkey_reg and flags have the same format */
-	shadow_pkey_reg &= ~(flags << (pkey * 2));
+	shadow_pkey_reg &= reset_bits(pkey, flags);
 	pkey_assert(ret >= 0);
 
 	pkey_rights = pkey_get(pkey, syscall_flags);

@@ -523,6 +523,21 @@ int sys_pkey_alloc(unsigned long flags, unsigned long init_val)
 	return ret;
 }
 
+void pkey_setup_shadow(void)
+{
+	shadow_pkey_reg = __rdpkey_reg();
+}
+
+void pkey_reset_shadow(u32 key)
+{
+	shadow_pkey_reg &= reset_bits(key, 0x3);
+}
+
+void pkey_set_shadow(u32 key, u64 init_val)
+{
+	shadow_pkey_reg |=  left_shift_bits(key, init_val);
+}
+
 int alloc_pkey(void)
 {
 	int ret;

@@ -540,7 +555,7 @@ int alloc_pkey(void)
 			shadow_pkey_reg);
 	if (ret) {
 		/* clear both the bits: */
-		shadow_pkey_reg &= ~(0x3      << (ret * 2));
+		pkey_reset_shadow(ret);
 		dprintf4("%s()::%d, ret: %d pkey_reg: 0x%016lx "
 				"shadow: 0x%016lx\n",
 				__func__,

@@ -550,7 +565,7 @@ int alloc_pkey(void)
 		 * move the new state in from init_val
 		 * (remember, we cheated and init_val == pkey_reg format)
 		 */
-		shadow_pkey_reg |=  (init_val << (ret * 2));
+		pkey_set_shadow(ret, init_val);
 	}
 	dprintf4("%s()::%d, ret: %d pkey_reg: 0x%016lx shadow: 0x%016lx\n",
 			__func__, __LINE__, ret, __rdpkey_reg(),

@@ -1322,11 +1337,6 @@ void run_tests_once(void)
 	iteration_nr++;
 }
 
-void pkey_setup_shadow(void)
-{
-	shadow_pkey_reg = __rdpkey_reg();
-}
-
 int main(void)
 {
 	int nr_iterations = 22;

index 83216c5..0109388 100644
@@ -443,7 +443,7 @@ void pkey_disable_set(int pkey, int flags)
 	dprintf1("%s(%d) pkey_reg: 0x%lx\n",
 		__func__, pkey, rdpkey_reg());
 	if (flags)
-		pkey_assert(rdpkey_reg() > orig_pkey_reg);
+		pkey_assert(rdpkey_reg() >= orig_pkey_reg);
 	dprintf1("END<---%s(%d, 0x%x)\n", __func__,
 		pkey, flags);
 }

index 0109388..ca54a95 100644
@@ -461,7 +461,7 @@ void pkey_disable_clear(int pkey, int flags)
 			pkey, pkey, pkey_rights);
 	pkey_assert(pkey_rights >= 0);
 
-	pkey_rights |= flags;
+	pkey_rights &= ~flags;
 
 	ret = pkey_set(pkey, pkey_rights, 0);
 	/* pkey_reg and flags have the same format */

@@ -475,7 +475,7 @@ void pkey_disable_clear(int pkey, int flags)
 	dprintf1("%s(%d) pkey_reg: 0x%016lx\n", __func__,
 			pkey, rdpkey_reg());
 	if (flags)
-		assert(rdpkey_reg() > orig_pkey_reg);
+		assert(rdpkey_reg() < orig_pkey_reg);
 }
 
 void pkey_write_allow(int pkey)

index ca54a95..aaf9f09 100644
@@ -582,6 +582,9 @@ int alloc_pkey(void)
 int sys_pkey_free(unsigned long pkey)
 {
 	int ret = syscall(SYS_pkey_free, pkey);
+
+	if (!ret)
+		shadow_pkey_reg &= reset_bits(pkey, PKEY_DISABLE_ACCESS);
 	dprintf1("%s(pkey=%ld) syscall ret: %d\n", __func__, pkey, ret);
 	return ret;
 }

index aaf9f09..2e4b636 100644
@@ -24,6 +24,7 @@
 #define _GNU_SOURCE
 #include <errno.h>
 #include <linux/futex.h>
+#include <time.h>
 #include <sys/time.h>
 #include <sys/syscall.h>
 #include <string.h>

@@ -602,13 +603,15 @@ int alloc_random_pkey(void)
 	int alloced_pkeys[NR_PKEYS];
 	int nr_alloced = 0;
 	int random_index;
+
 	memset(alloced_pkeys, 0, sizeof(alloced_pkeys));
+	srand((unsigned int)time(NULL));
 
 	/* allocate every possible key and make a note of which ones we got */
 	max_nr_pkey_allocs = NR_PKEYS;
-	max_nr_pkey_allocs = 1;
 	for (i = 0; i < max_nr_pkey_allocs; i++) {
 		int new_pkey = alloc_pkey();
+
 		if (new_pkey < 0)
 			break;
 		alloced_pkeys[nr_alloced++] = new_pkey;

@@ -624,13 +627,14 @@ int alloc_random_pkey(void)
 	/* go through the allocated ones that we did not want and free them */
 	for (i = 0; i < nr_alloced; i++) {
 		int free_ret;
+
 		if (!alloced_pkeys[i])
 			continue;
 		free_ret = sys_pkey_free(alloced_pkeys[i]);
 		pkey_assert(!free_ret);
 	}
-	dprintf1("%s()::%d, ret: %d pkey_reg: 0x%x shadow: 0x%x\n", __func__,
-			__LINE__, ret, __rdpkey_reg(), shadow_pkey_reg);
+	dprintf1("%s()::%d, ret: %d pkey_reg: 0x%x shadow: 0x%016lx\n",
+		__func__, __LINE__, ret, __rdpkey_reg(), shadow_pkey_reg);
 	return ret;
 }
 

index 7c979ad..c8f5739 100644
@@ -304,3 +304,14 @@ static inline void __page_o_noops(void)
 	}					\
 } while (0)
 #define raw_assert(cond) assert(cond)
+
+static inline int open_hugepage_file(int flag)
+{
+	return open("/sys/kernel/mm/hugepages/hugepages-2048kB/nr_hugepages",
+		 O_RDONLY);
+}
+
+static inline int get_start_key(void)
+{
+	return 1;
+}

index 2e4b636..254b66d 100644
@@ -809,7 +809,7 @@ void setup_hugetlbfs(void)
 	 * Now go make sure that we got the pages and that they
 	 * are 2M pages.  Someone might have made 1G the default.
 	 */
-	fd = open("/sys/kernel/mm/hugepages/hugepages-2048kB/nr_hugepages", O_RDONLY);
+	fd = open_hugepage_file(O_RDONLY);
 	if (fd < 0) {
 		perror("opening sysfs 2M hugetlb config");
 		return;

@@ -1087,10 +1087,10 @@ void test_kernel_gup_write_to_write_disabled_region(int *ptr, u16 pkey)
 void test_pkey_syscalls_on_non_allocated_pkey(int *ptr, u16 pkey)
 {
 	int err;
-	int i;
+	int i = get_start_key();
 
 	/* Note: 0 is the default pkey, so don't mess with it */
-	for (i = 1; i < NR_PKEYS; i++) {
+	for (; i < NR_PKEYS; i++) {
 		if (pkey == i)
 			continue;
 

index 254b66d..6054093 100644
@@ -926,10 +926,10 @@ void expected_pkey_fault(int pkey)
 	pkey_assert(last_pkey_faults + 1 == pkey_faults);
 	pkey_assert(last_si_pkey == pkey);
 	/*
-	 * The signal handler shold have cleared out PKEY register to let the
+	 * The signal handler shold have cleared out pkey-register to let the
 	 * test program continue.  We now have to restore it.
 	 */
-	if (__rdpkey_reg() != 0)
+	if (__rdpkey_reg() != shadow_pkey_reg)
 		pkey_assert(0);
 
 	__wrpkey_reg(shadow_pkey_reg);

index 6054093..6fdd8f5 100644
@@ -4,7 +4,7 @@
  *
  * There are examples in here of:
  *  * how to set protection keys on memory
- *  * how to set/clear bits in pkey registers (the rights register)
+ *  * how to set/clear bits in Protection Key registers (the rights register)
  *  * how to handle SEGV_PKUERR signals and extract pkey-relevant
  *    information from the siginfo
  *

@@ -13,13 +13,18 @@
  *	prefault pages in at malloc, or not
  *	protect MPX bounds tables with protection keys?
  *	make sure VMA splitting/merging is working correctly
- *	OOMs can destroy mm->mmap (see exit_mmap()), so make sure it is immune to pkeys
- *	look for pkey "leaks" where it is still set on a VMA but "freed" back to the kernel
- *	do a plain mprotect() to a mprotect_pkey() area and make sure the pkey sticks
+ *	OOMs can destroy mm->mmap (see exit_mmap()),
+ *			so make sure it is immune to pkeys
+ *	look for pkey "leaks" where it is still set on a VMA
+ *			 but "freed" back to the kernel
+ *	do a plain mprotect() to a mprotect_pkey() area and make
+ *			 sure the pkey sticks
  *
  * Compile like this:
- *	gcc      -o protection_keys    -O2 -g -std=gnu99 -pthread -Wall protection_keys.c -lrt -ldl -lm
- *	gcc -m32 -o protection_keys_32 -O2 -g -std=gnu99 -pthread -Wall protection_keys.c -lrt -ldl -lm
+ *	gcc      -o protection_keys    -O2 -g -std=gnu99
+ *			 -pthread -Wall protection_keys.c -lrt -ldl -lm
+ *	gcc -m32 -o protection_keys_32 -O2 -g -std=gnu99
+ *			 -pthread -Wall protection_keys.c -lrt -ldl -lm
  */
 #define _GNU_SOURCE
 #include <errno.h>

@@ -251,26 +256,11 @@ void signal_handler(int signum, siginfo_t *si, void *vucontext)
 	dprintf1("signal pkey_reg from  pkey_reg: %016lx\n", __rdpkey_reg());
 	dprintf1("pkey from siginfo: %jx\n", siginfo_pkey);
 	*(u64 *)pkey_reg_ptr = 0x00000000;
-	dprintf1("WARNING: set PRKU=0 to allow faulting instruction to continue\n");
+	dprintf1("WARNING: set PKEY_REG=0 to allow faulting instruction "
+			"to continue\n");
 	pkey_faults++;
 	dprintf1("<<<<==================================================\n");
 	return;
-	if (trapno == 14) {
-		fprintf(stderr,
-			"ERROR: In signal handler, page fault, trapno = %d, ip = %016lx\n",
-			trapno, ip);
-		fprintf(stderr, "si_addr %p\n", si->si_addr);
-		fprintf(stderr, "REG_ERR: %lx\n",
-				(unsigned long)uctxt->uc_mcontext.gregs[REG_ERR]);
-		exit(1);
-	} else {
-		fprintf(stderr, "unexpected trap %d! at 0x%lx\n", trapno, ip);
-		fprintf(stderr, "si_addr %p\n", si->si_addr);
-		fprintf(stderr, "REG_ERR: %lx\n",
-				(unsigned long)uctxt->uc_mcontext.gregs[REG_ERR]);
-		exit(2);
-	}
-	dprint_in_signal = 0;
 }
 
 int wait_all_children(void)

@@ -415,7 +405,7 @@ void pkey_disable_set(int pkey, int flags)
 {
 	unsigned long syscall_flags = 0;
 	int ret;
-	int pkey_rights;
+	u32 pkey_rights;
 	pkey_reg_t orig_pkey_reg = rdpkey_reg();
 
 	dprintf1("START->%s(%d, 0x%x)\n", __func__,

@@ -453,7 +443,7 @@ void pkey_disable_clear(int pkey, int flags)
 {
 	unsigned long syscall_flags = 0;
 	int ret;
-	int pkey_rights = pkey_get(pkey, syscall_flags);
+	u32 pkey_rights = pkey_get(pkey, syscall_flags);
 	pkey_reg_t orig_pkey_reg = rdpkey_reg();
 
 	pkey_assert(flags & (PKEY_DISABLE_ACCESS | PKEY_DISABLE_WRITE));

@@ -516,9 +506,10 @@ int sys_mprotect_pkey(void *ptr, size_t size, unsigned long orig_prot,
 	return sret;
 }
 
-int sys_pkey_alloc(unsigned long flags, unsigned long init_val)
+int sys_pkey_alloc(unsigned long flags, u64 init_val)
 {
 	int ret = syscall(SYS_pkey_alloc, flags, init_val);
+
 	dprintf1("%s(flags=%lx, init_val=%lx) syscall ret: %d errno: %d\n",
 			__func__, flags, init_val, ret, errno);
 	return ret;

@@ -542,7 +533,7 @@ void pkey_set_shadow(u32 key, u64 init_val)
 int alloc_pkey(void)
 {
 	int ret;
-	unsigned long init_val = 0x0;
+	u64 init_val = 0x0;
 
 	dprintf1("%s()::%d, pkey_reg: 0x%016lx shadow: %016lx\n", __func__,
 			__LINE__, __rdpkey_reg(), shadow_pkey_reg);

@@ -692,7 +683,9 @@ void record_pkey_malloc(void *ptr, long size)
 		/* every record is full */
 		size_t old_nr_records = nr_pkey_malloc_records;
 		size_t new_nr_records = (nr_pkey_malloc_records * 2 + 1);
-		size_t new_size = new_nr_records * sizeof(struct pkey_malloc_record);
+		size_t new_size = new_nr_records *
+				sizeof(struct pkey_malloc_record);
+
 		dprintf2("new_nr_records: %zd\n", new_nr_records);
 		dprintf2("new_size: %zd\n", new_size);
 		pkey_malloc_records = realloc(pkey_malloc_records, new_size);

@@ -716,9 +709,11 @@ void free_pkey_malloc(void *ptr)
 {
 	long i;
 	int ret;
+
 	dprintf3("%s(%p)\n", __func__, ptr);
 	for (i = 0; i < nr_pkey_malloc_records; i++) {
 		struct pkey_malloc_record *rec = &pkey_malloc_records[i];
+
 		dprintf4("looking for ptr %p at record[%ld/%p]: {%p, %ld}\n",
 				ptr, i, rec, rec->ptr, rec->size);
 		if ((ptr <  rec->ptr) ||

@@ -799,11 +794,13 @@ void setup_hugetlbfs(void)
 	char buf[] = "123";
 
 	if (geteuid() != 0) {
-		fprintf(stderr, "WARNING: not run as root, can not do hugetlb test\n");
+		fprintf(stderr,
+			"WARNING: not run as root, can not do hugetlb test\n");
 		return;
 	}
 
-	cat_into_file(__stringify(GET_NR_HUGE_PAGES), "/proc/sys/vm/nr_hugepages");
+	cat_into_file(__stringify(GET_NR_HUGE_PAGES),
+				"/proc/sys/vm/nr_hugepages");
 
 	/*
 	 * Now go make sure that we got the pages and that they

@@ -824,7 +821,8 @@ void setup_hugetlbfs(void)
 	}
 
 	if (atoi(buf) != GET_NR_HUGE_PAGES) {
-		fprintf(stderr, "could not confirm 2M pages, got: '%s' expected %d\n",
+		fprintf(stderr, "could not confirm 2M pages, got:"
+			       " '%s' expected %d\n",
 			buf, GET_NR_HUGE_PAGES);
 		return;
 	}

@@ -957,6 +955,7 @@ void __save_test_fd(int fd)
 int get_test_read_fd(void)
 {
 	int test_fd = open("/etc/passwd", O_RDONLY);
+
 	__save_test_fd(test_fd);
 	return test_fd;
 }

@@ -998,7 +997,8 @@ void test_read_of_access_disabled_region(int *ptr, u16 pkey)
 {
 	int ptr_contents;
 
-	dprintf1("disabling access to PKEY[%02d], doing read @ %p\n", pkey, ptr);
+	dprintf1("disabling access to PKEY[%02d], doing read @ %p\n",
+			 pkey, ptr);
 	rdpkey_reg();
 	pkey_access_deny(pkey);
 	ptr_contents = read_ptr(ptr);

@@ -1120,13 +1120,14 @@ void test_pkey_syscalls_bad_args(int *ptr, u16 pkey)
 /* Assumes that all pkeys other than 'pkey' are unallocated */
 void test_pkey_alloc_exhaust(int *ptr, u16 pkey)
 {
-	int err;
+	int err = 0;
 	int allocated_pkeys[NR_PKEYS] = {0};
 	int nr_allocated_pkeys = 0;
 	int i;
 
 	for (i = 0; i < NR_PKEYS*2; i++) {
 		int new_pkey;
+
 		dprintf1("%s() alloc loop: %d\n", __func__, i);
 		new_pkey = alloc_pkey();
 		dprintf4("%s()::%d, err: %d pkey_reg: 0x%016lx "

@@ -1134,9 +1135,11 @@ void test_pkey_alloc_exhaust(int *ptr, u16 pkey)
 			__func__, __LINE__, err, __rdpkey_reg(),
 			shadow_pkey_reg);
 		rdpkey_reg(); /* for shadow checking */
-		dprintf2("%s() errno: %d ENOSPC: %d\n", __func__, errno, ENOSPC);
+		dprintf2("%s() errno: %d ENOSPC: %d\n",
+				__func__, errno, ENOSPC);
 		if ((new_pkey == -1) && (errno == ENOSPC)) {
-			dprintf2("%s() failed to allocate pkey after %d tries\n",
+			dprintf2("%s() failed to allocate pkey "
+					"after %d tries\n",
 				__func__, nr_allocated_pkeys);
 			break;
 		}

@@ -1338,7 +1341,8 @@ void run_tests_once(void)
 		tracing_off();
 		close_test_fds();
 
-		printf("test %2d PASSED (iteration %d)\n", test_nr, iteration_nr);
+		printf("test %2d PASSED (iteration %d)\n",
+				test_nr, iteration_nr);
 		dprintf1("======================\n\n");
 	}
 	iteration_nr++;

@@ -1350,7 +1354,7 @@ int main(void)
 
 	setup_handlers();
 
-	printf("has pku: %d\n", cpu_has_pku());
+	printf("has pkey: %d\n", cpu_has_pku());
 
 	if (!cpu_has_pku()) {
 		int size = PAGE_SIZE;

@@ -1358,7 +1362,8 @@ int main(void)
 
 		printf("running PKEY tests for unsupported CPU/OS\n");
 
-		ptr  = mmap(NULL, size, PROT_NONE, MAP_ANONYMOUS|MAP_PRIVATE, -1, 0);
+		ptr  = mmap(NULL, size, PROT_NONE,
+				MAP_ANONYMOUS|MAP_PRIVATE, -1, 0);
 		assert(ptr != (void *)-1);
 		test_mprotect_pkey_on_unsupported_cpu(ptr, 1);
 		exit(0);

index c8f5739..cfc1a18 100644
@@ -18,27 +18,54 @@
 #define u16 uint16_t
 #define u32 uint32_t
 #define u64 uint64_t
-#define pkey_reg_t u32
 
-#ifdef __i386__
+#if defined(__i386__) || defined(__x86_64__) /* arch */
+
+#ifdef __i386__ /* arch */
 #define SYS_mprotect_key 380
-#define SYS_pkey_alloc	 381
-#define SYS_pkey_free	 382
+#define SYS_pkey_alloc   381
+#define SYS_pkey_free    382
 #define REG_IP_IDX REG_EIP
 #define si_pkey_offset 0x14
-#else
+#elif __x86_64__
 #define SYS_mprotect_key 329
-#define SYS_pkey_alloc	 330
-#define SYS_pkey_free	 331
+#define SYS_pkey_alloc   330
+#define SYS_pkey_free    331
 #define REG_IP_IDX REG_RIP
 #define si_pkey_offset 0x20
-#endif
+#endif /* __x86_64__ */
+
+#define NR_PKEYS		16
+#define NR_RESERVED_PKEYS	1
+#define PKEY_BITS_PER_PKEY	2
+#define PKEY_DISABLE_ACCESS	0x1
+#define PKEY_DISABLE_WRITE	0x2
+#define HPAGE_SIZE		(1UL<<21)
+#define pkey_reg_t u32
 
-#define NR_PKEYS 16
-#define PKEY_BITS_PER_PKEY 2
-#define PKEY_DISABLE_ACCESS    0x1
-#define PKEY_DISABLE_WRITE     0x2
-#define HPAGE_SIZE	(1UL<<21)
+#elif __powerpc64__ /* arch */
+
+#define SYS_mprotect_key 386
+#define SYS_pkey_alloc	 384
+#define SYS_pkey_free	 385
+#define si_pkey_offset	0x20
+#define REG_IP_IDX PT_NIP
+#define REG_TRAPNO PT_TRAP
+#define gregs gp_regs
+#define fpregs fp_regs
+
+#define NR_PKEYS		32
+#define NR_RESERVED_PKEYS_4K	26
+#define NR_RESERVED_PKEYS_64K	3
+#define PKEY_BITS_PER_PKEY	2
+#define PKEY_DISABLE_ACCESS	0x3  /* disable read and write */
+#define PKEY_DISABLE_WRITE	0x2
+#define HPAGE_SIZE		(1UL<<24)
+#define pkey_reg_t u64
+
+#else /* arch */
+	NOT SUPPORTED
+#endif /* arch */
 
 #ifndef DEBUG_LEVEL
 #define DEBUG_LEVEL 0

@@ -47,7 +74,11 @@
 
 static inline u32 pkey_to_shift(int pkey)
 {
+#if defined(__i386__) || defined(__x86_64__) /* arch */
 	return pkey * PKEY_BITS_PER_PKEY;
+#elif __powerpc64__ /* arch */
+	return (NR_PKEYS - pkey - 1) * PKEY_BITS_PER_PKEY;
+#endif /* arch */
 }
 
 static inline pkey_reg_t reset_bits(int pkey, pkey_reg_t bits)

@@ -111,6 +142,7 @@ static inline void sigsafe_printf(const char *format, ...)
 extern pkey_reg_t shadow_pkey_reg;
 static inline pkey_reg_t __rdpkey_reg(void)
 {
+#if defined(__i386__) || defined(__x86_64__) /* arch */
 	unsigned int eax, edx;
 	unsigned int ecx = 0;
 	pkey_reg_t pkey_reg;

@@ -118,7 +150,13 @@ static inline pkey_reg_t __rdpkey_reg(void)
 	asm volatile(".byte 0x0f,0x01,0xee\n\t"
 		     : "=a" (eax), "=d" (edx)
 		     : "c" (ecx));
-	pkey_reg = eax;
+#elif __powerpc64__ /* arch */
+	pkey_reg_t eax;
+	pkey_reg_t pkey_reg;
+
+	asm volatile("mfspr %0, 0xd" : "=r" ((pkey_reg_t)(eax)));
+#endif /* arch */
+	pkey_reg = (pkey_reg_t)eax;
 	return pkey_reg;
 }
 

@@ -138,6 +176,7 @@ static inline pkey_reg_t _rdpkey_reg(int line)
 static inline void __wrpkey_reg(pkey_reg_t pkey_reg)
 {
 	pkey_reg_t eax = pkey_reg;
+#if defined(__i386__) || defined(__x86_64__) /* arch */
 	pkey_reg_t ecx = 0;
 	pkey_reg_t edx = 0;
 

@@ -146,6 +185,14 @@ static inline void __wrpkey_reg(pkey_reg_t pkey_reg)
 	asm volatile(".byte 0x0f,0x01,0xef\n\t"
 		     : : "a" (eax), "c" (ecx), "d" (edx));
 	assert(pkey_reg == __rdpkey_reg());
+
+#elif __powerpc64__ /* arch */
+	dprintf4("%s() changing %llx to %llx\n",
+			 __func__, __rdpkey_reg(), pkey_reg);
+	asm volatile("mtspr 0xd, %0" : : "r" ((unsigned long)(eax)) : "memory");
+#endif /* arch */
+	dprintf4("%s() pkey register after changing %016lx to %016lx\n",
+			 __func__, __rdpkey_reg(), pkey_reg);
 }
 
 static inline void wrpkey_reg(pkey_reg_t pkey_reg)

@@ -192,6 +239,8 @@ static inline void __pkey_write_allow(int pkey, int do_allow_write)
 	dprintf4("pkey_reg now: %08x\n", rdpkey_reg());
 }
 
+#if defined(__i386__) || defined(__x86_64__) /* arch */
+
 #define PAGE_SIZE 4096
 #define MB	(1<<20)
 

@@ -274,8 +323,18 @@ static inline void __page_o_noops(void)
 	/* 8-bytes of instruction * 512 bytes = 1 page */
 	asm(".rept 512 ; nopl 0x7eeeeeee(%eax) ; .endr");
 }
+#elif __powerpc64__ /* arch */
 
-#endif /* _PKEYS_HELPER_H */
+#define PAGE_SIZE (0x1UL << 16)
+static inline int cpu_has_pku(void)
+{
+	return 1;
+}
+
+/* 8-bytes of instruction * 16384bytes = 1 page */
+#define __page_o_noops() asm(".rept 16384 ; nop; .endr")
+
+#endif /* arch */
 
 #define ARRAY_SIZE(x) (sizeof(x) / sizeof(*(x)))
 #define ALIGN_UP(x, align_to)	(((x) + ((align_to)-1)) & ~((align_to)-1))

@@ -307,11 +366,29 @@ static inline void __page_o_noops(void)
 
 static inline int open_hugepage_file(int flag)
 {
-	return open("/sys/kernel/mm/hugepages/hugepages-2048kB/nr_hugepages",
+	int fd;
+
+#if defined(__i386__) || defined(__x86_64__) /* arch */
+	fd = open("/sys/kernel/mm/hugepages/hugepages-2048kB/nr_hugepages",
 		 O_RDONLY);
+#elif __powerpc64__ /* arch */
+	fd = open("/sys/kernel/mm/hugepages/hugepages-16384kB/nr_hugepages",
+		O_RDONLY);
+#else /* arch */
+	NOT SUPPORTED
+#endif /* arch */
+	return fd;
 }
 
 static inline int get_start_key(void)
 {
+#if defined(__i386__) || defined(__x86_64__) /* arch */
 	return 1;
+#elif __powerpc64__ /* arch */
+	return 0;
+#else /* arch */
+	NOT SUPPORTED
+#endif /* arch */
 }
+
+#endif /* _PKEYS_HELPER_H */

index 6fdd8f5..55a25e1 100644
@@ -186,17 +186,18 @@ void dump_mem(void *dumpme, int len_bytes)
 
 int pkey_faults;
 int last_si_pkey = -1;
+void pkey_access_allow(int pkey);
 void signal_handler(int signum, siginfo_t *si, void *vucontext)
 {
 	ucontext_t *uctxt = vucontext;
 	int trapno;
 	unsigned long ip;
 	char *fpregs;
+#if defined(__i386__) || defined(__x86_64__) /* arch */
 	pkey_reg_t *pkey_reg_ptr;
-	u64 siginfo_pkey;
+#endif /* defined(__i386__) || defined(__x86_64__) */
+	u32 siginfo_pkey;
 	u32 *si_pkey_ptr;
-	int pkey_reg_offset;
-	fpregset_t fpregset;
 
 	dprint_in_signal = 1;
 	dprintf1(">>>>===============SIGSEGV============================\n");

@@ -206,12 +207,14 @@ 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

@@ -219,20 +222,21 @@ void signal_handler(int signum, siginfo_t *si, void *vucontext)
 	 * state.  We just assume that it is here.
 	 */
 	fpregs += 0x70;
-#endif
-	pkey_reg_offset = pkey_reg_xstate_offset();
-	pkey_reg_ptr = (void *)(&fpregs[pkey_reg_offset]);
+#endif /* __i386__ */
 
-	dprintf1("siginfo: %p\n", si);
-	dprintf1(" fpregs: %p\n", fpregs);
+	pkey_reg_ptr = (void *)(&fpregs[pkey_reg_xstate_offset()]);
 	/*
-	 * If we got a PKEY fault, we *HAVE* to have at least one bit set in
+	 * If we got a key fault, we *HAVE* to have at least one bit set in
 	 * here.
 	 */
 	dprintf1("pkey_reg_xstate_offset: %d\n", pkey_reg_xstate_offset());
 	if (DEBUG_LEVEL > 4)
 		dump_mem(pkey_reg_ptr - 128, 256);
 	pkey_assert(*pkey_reg_ptr);
+#endif /* defined(__i386__) || defined(__x86_64__) */
+
+	dprintf1("siginfo: %p\n", si);
+	dprintf1(" fpregs: %p\n", fpregs);
 
 	si_pkey_ptr = (u32 *)(((u8 *)si) + si_pkey_offset);
 	dprintf1("si_pkey_ptr: %p\n", si_pkey_ptr);

@@ -248,19 +252,25 @@ void signal_handler(int signum, siginfo_t *si, void *vucontext)
 		exit(4);
 	}
 
-	dprintf1("signal pkey_reg from xsave: %016lx\n", *pkey_reg_ptr);
 	/*
 	 * need __rdpkey_reg() version so we do not do shadow_pkey_reg
 	 * checking
 	 */
 	dprintf1("signal pkey_reg from  pkey_reg: %016lx\n", __rdpkey_reg());
-	dprintf1("pkey from siginfo: %jx\n", siginfo_pkey);
-	*(u64 *)pkey_reg_ptr = 0x00000000;
+	dprintf1("pkey from siginfo: %lx\n", siginfo_pkey);
+#if defined(__i386__) || defined(__x86_64__) /* arch */
+	dprintf1("signal pkey_reg from xsave: %016lx\n", *pkey_reg_ptr);
+	*(u64 *)pkey_reg_ptr &= reset_bits(siginfo_pkey,
+			PKEY_DISABLE_ACCESS | PKEY_DISABLE_WRITE);
+#elif __powerpc64__
+	pkey_access_allow(siginfo_pkey);
+#endif
+	shadow_pkey_reg &= reset_bits(siginfo_pkey,
+			PKEY_DISABLE_ACCESS | PKEY_DISABLE_WRITE);
 	dprintf1("WARNING: set PKEY_REG=0 to allow faulting instruction "
 			"to continue\n");
 	pkey_faults++;
 	dprintf1("<<<<==================================================\n");
-	return;
 }
 
 int wait_all_children(void)

index 55a25e1..d1cbdfe 100644
@@ -586,7 +586,8 @@ int sys_pkey_free(unsigned long pkey)
 	int ret = syscall(SYS_pkey_free, pkey);
 
 	if (!ret)
-		shadow_pkey_reg &= reset_bits(pkey, PKEY_DISABLE_ACCESS);
+		shadow_pkey_reg &= reset_bits(pkey,
+				PKEY_DISABLE_ACCESS | PKEY_DISABLE_WRITE);
 	dprintf1("%s(pkey=%ld) syscall ret: %d\n", __func__, pkey, ret);
 	return ret;
 }

index cfc1a18..3559527 100644
@@ -261,7 +261,7 @@ static inline void __cpuid(unsigned int *eax, unsigned int *ebx,
 #define X86_FEATURE_PKU        (1<<3) /* Protection Keys for Userspace */
 #define X86_FEATURE_OSPKE      (1<<4) /* OS Protection Keys Enable */
 
-static inline int cpu_has_pku(void)
+static inline bool is_pkey_supported(void)
 {
 	unsigned int eax;
 	unsigned int ebx;

@@ -274,13 +274,13 @@ static inline int cpu_has_pku(void)
 
 	if (!(ecx & X86_FEATURE_PKU)) {
 		dprintf2("cpu does not have PKU\n");
-		return 0;
+		return false;
 	}
 	if (!(ecx & X86_FEATURE_OSPKE)) {
 		dprintf2("cpu does not have OSPKE\n");
-		return 0;
+		return false;
 	}
-	return 1;
+	return true;
 }
 
 #define XSTATE_PKEY_BIT	(9)

@@ -326,9 +326,19 @@ static inline void __page_o_noops(void)
 #elif __powerpc64__ /* arch */
 
 #define PAGE_SIZE (0x1UL << 16)
-static inline int cpu_has_pku(void)
+static inline bool is_pkey_supported(void)
 {
-	return 1;
+	/*
+	 * No simple way to determine this.
+	 * lets try allocating a key and see if it succeeds.
+	 */
+	int ret = sys_pkey_alloc(0, 0);
+
+	if (ret > 0) {
+		sys_pkey_free(ret);
+		return true;
+	}
+	return false;
 }
 
 /* 8-bytes of instruction * 16384bytes = 1 page */

index d1cbdfe..65e6dd6 100644
@@ -1299,8 +1299,8 @@ void test_mprotect_pkey_on_unsupported_cpu(int *ptr, u16 pkey)
 	int size = PAGE_SIZE;
 	int sret;
 
-	if (cpu_has_pku()) {
-		dprintf1("SKIP: %s: no CPU support\n", __func__);
+	if (is_pkey_supported()) {
+		dprintf1("SKIP: %s: no CPU/kernel support\n", __func__);
 		return;
 	}
 

@@ -1362,12 +1362,13 @@ void run_tests_once(void)
 int main(void)
 {
 	int nr_iterations = 22;
+	int pkey_supported = is_pkey_supported();
 
 	setup_handlers();
 
-	printf("has pkey: %d\n", cpu_has_pku());
+	printf("has pkey: %s\n", pkey_supported ? "Yes" : "No");
 
-	if (!cpu_has_pku()) {
+	if (!pkey_supported) {
 		int size = PAGE_SIZE;
 		int *ptr;
 

index 3559527..9d06b4a 100644
@@ -401,4 +401,18 @@ static inline int get_start_key(void)
 #endif /* arch */
 }
 
+static inline int arch_reserved_keys(void)
+{
+#if defined(__i386__) || defined(__x86_64__) /* arch */
+	return NR_RESERVED_PKEYS;
+#elif __powerpc64__ /* arch */
+	if (sysconf(_SC_PAGESIZE) == 4096)
+		return NR_RESERVED_PKEYS_4K;
+	else
+		return NR_RESERVED_PKEYS_64K;
+#else /* arch */
+	NOT SUPPORTED
+#endif /* arch */
+}
+
 #endif /* _PKEYS_HELPER_H */

index 65e6dd6..33d5839 100644
@@ -1167,12 +1167,11 @@ void test_pkey_alloc_exhaust(int *ptr, u16 pkey)
 	pkey_assert(i < NR_PKEYS*2);
 
 	/*
-	 * There are 16 pkeys supported in hardware.  One is taken
-	 * up for the default (0) and another can be taken up by
-	 * an execute-only mapping.  Ensure that we can allocate
-	 * at least 14 (16-2).
+	 * There are NR_PKEYS pkeys supported in hardware. arch_reserved_keys()
+	 * are reserved. One   can   be   taken   up by an execute-only mapping.
+	 * Ensure that we can allocate at least the remaining.
 	 */
-	pkey_assert(i >= NR_PKEYS-2);
+	pkey_assert(i >= (NR_PKEYS-arch_reserved_keys()-1));
 
 	for (i = 0; i < nr_allocated_pkeys; i++) {
 		err = sys_pkey_free(allocated_pkeys[i]);

index 33d5839..1d3f596 100644
@@ -1016,6 +1016,24 @@ void test_read_of_access_disabled_region(int *ptr, u16 pkey)
 	dprintf1("*ptr: %d\n", ptr_contents);
 	expected_pkey_fault(pkey);
 }
+
+void test_read_of_access_disabled_region_with_page_already_mapped(int *ptr,
+		u16 pkey)
+{
+	int ptr_contents;
+
+	dprintf1("disabling access to PKEY[%02d], doing read @ %p\n",
+				pkey, ptr);
+	ptr_contents = read_ptr(ptr);
+	dprintf1("reading ptr before disabling the read : %d\n",
+			ptr_contents);
+	rdpkey_reg();
+	pkey_access_deny(pkey);
+	ptr_contents = read_ptr(ptr);
+	dprintf1("*ptr: %d\n", ptr_contents);
+	expected_pkey_fault(pkey);
+}
+
 void test_write_of_write_disabled_region(int *ptr, u16 pkey)
 {
 	dprintf1("disabling write access to PKEY[%02d], doing write\n", pkey);

@@ -1310,6 +1328,7 @@ void test_mprotect_pkey_on_unsupported_cpu(int *ptr, u16 pkey)
 void (*pkey_tests[])(int *ptr, u16 pkey) = {
 	test_read_of_write_disabled_region,
 	test_read_of_access_disabled_region,
+	test_read_of_access_disabled_region_with_page_already_mapped,
 	test_write_of_write_disabled_region,
 	test_write_of_access_disabled_region,
 	test_kernel_write_of_access_disabled_region,

index 1d3f596..f90a8b6 100644
@@ -1034,6 +1034,17 @@ void test_read_of_access_disabled_region_with_page_already_mapped(int *ptr,
 	expected_pkey_fault(pkey);
 }
 
+void test_write_of_write_disabled_region_with_page_already_mapped(int *ptr,
+		u16 pkey)
+{
+	*ptr = __LINE__;
+	dprintf1("disabling write access; after accessing the page, "
+		"to PKEY[%02d], doing write\n", pkey);
+	pkey_write_deny(pkey);
+	*ptr = __LINE__;
+	expected_pkey_fault(pkey);
+}
+
 void test_write_of_write_disabled_region(int *ptr, u16 pkey)
 {
 	dprintf1("disabling write access to PKEY[%02d], doing write\n", pkey);

@@ -1330,6 +1341,7 @@ void test_mprotect_pkey_on_unsupported_cpu(int *ptr, u16 pkey)
 	test_read_of_access_disabled_region,
 	test_read_of_access_disabled_region_with_page_already_mapped,
 	test_write_of_write_disabled_region,
+	test_write_of_write_disabled_region_with_page_already_mapped,
 	test_write_of_access_disabled_region,
 	test_kernel_write_of_access_disabled_region,
 	test_kernel_write_of_write_disabled_region,

index f90a8b6..3e9e36d 100644
@@ -1059,6 +1059,18 @@ void test_write_of_access_disabled_region(int *ptr, u16 pkey)
 	*ptr = __LINE__;
 	expected_pkey_fault(pkey);
 }
+
+void test_write_of_access_disabled_region_with_page_already_mapped(int *ptr,
+			u16 pkey)
+{
+	*ptr = __LINE__;
+	dprintf1("disabling access; after accessing the page, "
+		" to PKEY[%02d], doing write\n", pkey);
+	pkey_access_deny(pkey);
+	*ptr = __LINE__;
+	expected_pkey_fault(pkey);
+}
+
 void test_kernel_write_of_access_disabled_region(int *ptr, u16 pkey)
 {
 	int ret;

@@ -1343,6 +1355,7 @@ void test_mprotect_pkey_on_unsupported_cpu(int *ptr, u16 pkey)
 	test_write_of_write_disabled_region,
 	test_write_of_write_disabled_region_with_page_already_mapped,
 	test_write_of_access_disabled_region,
+	test_write_of_access_disabled_region_with_page_already_mapped,
 	test_kernel_write_of_access_disabled_region,
 	test_kernel_write_of_write_disabled_region,
 	test_kernel_gup_of_access_disabled_region,

index 3e9e36d..5783587 100644
@@ -1003,6 +1003,7 @@ void test_read_of_write_disabled_region(int *ptr, u16 pkey)
 	ptr_contents = read_ptr(ptr);
 	dprintf1("*ptr: %d\n", ptr_contents);
 	dprintf1("\n");
+	pkey_write_allow(pkey);
 }
 void test_read_of_access_disabled_region(int *ptr, u16 pkey)
 {

@@ -1082,6 +1083,7 @@ void test_kernel_write_of_access_disabled_region(int *ptr, u16 pkey)
 	ret = read(test_fd, ptr, 1);
 	dprintf1("read ret: %d\n", ret);
 	pkey_assert(ret);
+	pkey_access_allow(pkey);
 }
 void test_kernel_write_of_write_disabled_region(int *ptr, u16 pkey)
 {

@@ -1094,6 +1096,7 @@ void test_kernel_write_of_write_disabled_region(int *ptr, u16 pkey)
 	if (ret < 0 && (DEBUG_LEVEL > 0))
 		perror("verbose read result (OK for this to be bad)");
 	pkey_assert(ret);
+	pkey_write_allow(pkey);
 }
 
 void test_kernel_gup_of_access_disabled_region(int *ptr, u16 pkey)

@@ -1113,6 +1116,7 @@ void test_kernel_gup_of_access_disabled_region(int *ptr, u16 pkey)
 	vmsplice_ret = vmsplice(pipe_fds[1], &iov, 1, SPLICE_F_GIFT);
 	dprintf1("vmsplice() ret: %d\n", vmsplice_ret);
 	pkey_assert(vmsplice_ret == -1);
+	pkey_access_allow(pkey);
 
 	close(pipe_fds[0]);
 	close(pipe_fds[1]);

@@ -1133,6 +1137,7 @@ void test_kernel_gup_write_to_write_disabled_region(int *ptr, u16 pkey)
 	if (DEBUG_LEVEL > 0)
 		perror("futex");
 	dprintf1("futex() ret: %d\n", futex_ret);
+	pkey_write_allow(pkey);
 }
 
 /* Assumes that all pkeys other than 'pkey' are unallocated */

index 5783587..ae71dad 100644
@@ -766,6 +766,35 @@ void free_pkey_malloc(void *ptr)
 	return ptr;
 }
 
+void *malloc_pkey_with_mprotect_subpage(long size, int prot, u16 pkey)
+{
+#ifdef __powerpc64__
+	void *ptr;
+	int ret;
+
+	dprintf1("doing %s(size=%ld, prot=0x%x, pkey=%d)\n", __func__,
+			size, prot, pkey);
+	pkey_assert(pkey < NR_PKEYS);
+	ptr = mmap(NULL, size, prot, MAP_ANONYMOUS|MAP_PRIVATE, -1, 0);
+	pkey_assert(ptr != (void *)-1);
+
+	ret = syscall(__NR_subpage_prot, ptr, size, NULL);
+	if (ret) {
+		perror("subpage_perm");
+		return PTR_ERR_ENOTSUP;
+	}
+
+	ret = mprotect_pkey((void *)ptr, PAGE_SIZE, prot, pkey);
+	pkey_assert(!ret);
+	record_pkey_malloc(ptr, size);
+
+	dprintf1("%s() for pkey %d @ %p\n", __func__, pkey, ptr);
+	return ptr;
+#else /*  __powerpc64__ */
+	return PTR_ERR_ENOTSUP;
+#endif /*  __powerpc64__ */
+}
+
 void *malloc_pkey_anon_huge(long size, int prot, u16 pkey)
 {
 	int ret;

@@ -888,6 +917,7 @@ void setup_hugetlbfs(void)
 void *(*pkey_malloc[])(long size, int prot, u16 pkey) = {
 
 	malloc_pkey_with_mprotect,
+	malloc_pkey_with_mprotect_subpage,
 	malloc_pkey_anon_huge,
 	malloc_pkey_hugetlb
 /* can not do direct with the pkey_mprotect() API:

index 9d06b4a..965cfcd 100644
@@ -131,7 +131,8 @@ static inline void sigsafe_printf(const char *format, ...)
 #define dprintf_level(level, args...) do {	\
 	if (level <= DEBUG_LEVEL)		\
 		sigsafe_printf(args);		\
-	fflush(NULL);				\
+	if (!dprint_in_signal)			\
+		fflush(NULL);			\
 } while (0)
 #define dprintf0(args...) dprintf_level(0, args)
 #define dprintf1(args...) dprintf_level(1, args)

index 4afdebc..7f348c0 100644
@@ -54,6 +54,7 @@
 #define SPRN_DSCR_PRIV 0x11	/* Privilege State DSCR */
 #define SPRN_DSCR      0x03	/* Data Stream Control Register */
 #define SPRN_PPR       896	/* Program Priority Register */
+#define SPRN_AMR       13	/* Authority Mask Register - problem state */
 
 /* TEXASR register bits */
 #define TEXASR_FC	0xFE00000000000000

443 lines not on this page · raw message

438 lines not on this page · raw message